diff options
Diffstat (limited to '')
1185 files changed, 13726 insertions, 10161 deletions
diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq index b8ebff4b1..4514cf9fc 100644 --- a/Documentation/ABI/testing/sysfs-class-devfreq +++ b/Documentation/ABI/testing/sysfs-class-devfreq @@ -66,6 +66,9 @@ Description: echo 0 > /sys/class/devfreq/.../trans_stat + If the transition table is bigger than PAGE_SIZE, reading + this will return an -EFBIG error. + What: /sys/class/devfreq/.../userspace/set_freq Date: September 2011 Contact: MyungJoo Ham <myungjoo.ham@samsung.com> diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues index 978b76358..40d5aab84 100644 --- a/Documentation/ABI/testing/sysfs-class-net-queues +++ b/Documentation/ABI/testing/sysfs-class-net-queues @@ -1,4 +1,4 @@ -What: /sys/class/<iface>/queues/rx-<queue>/rps_cpus +What: /sys/class/net/<iface>/queues/rx-<queue>/rps_cpus Date: March 2010 KernelVersion: 2.6.35 Contact: netdev@vger.kernel.org @@ -8,7 +8,7 @@ Description: network device queue. Possible values depend on the number of available CPU(s) in the system. -What: /sys/class/<iface>/queues/rx-<queue>/rps_flow_cnt +What: /sys/class/net/<iface>/queues/rx-<queue>/rps_flow_cnt Date: April 2010 KernelVersion: 2.6.35 Contact: netdev@vger.kernel.org @@ -16,7 +16,7 @@ Description: Number of Receive Packet Steering flows being currently processed by this particular network device receive queue. -What: /sys/class/<iface>/queues/tx-<queue>/tx_timeout +What: /sys/class/net/<iface>/queues/tx-<queue>/tx_timeout Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org @@ -24,7 +24,7 @@ Description: Indicates the number of transmit timeout events seen by this network interface transmit queue. -What: /sys/class/<iface>/queues/tx-<queue>/tx_maxrate +What: /sys/class/net/<iface>/queues/tx-<queue>/tx_maxrate Date: March 2015 KernelVersion: 4.1 Contact: netdev@vger.kernel.org @@ -32,7 +32,7 @@ Description: A Mbps max-rate set for the queue, a value of zero means disabled, default is disabled. -What: /sys/class/<iface>/queues/tx-<queue>/xps_cpus +What: /sys/class/net/<iface>/queues/tx-<queue>/xps_cpus Date: November 2010 KernelVersion: 2.6.38 Contact: netdev@vger.kernel.org @@ -42,7 +42,7 @@ Description: network device transmit queue. Possible vaules depend on the number of available CPU(s) in the system. -What: /sys/class/<iface>/queues/tx-<queue>/xps_rxqs +What: /sys/class/net/<iface>/queues/tx-<queue>/xps_rxqs Date: June 2018 KernelVersion: 4.18.0 Contact: netdev@vger.kernel.org @@ -53,7 +53,7 @@ Description: number of available receive queue(s) in the network device. Default is disabled. -What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org @@ -62,7 +62,7 @@ Description: of this particular network device transmit queue. Default value is 1000. -What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/inflight +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/inflight Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org @@ -70,7 +70,7 @@ Description: Indicates the number of bytes (objects) in flight on this network device transmit queue. -What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org @@ -79,7 +79,7 @@ Description: on this network device transmit queue. This value is clamped to be within the bounds defined by limit_max and limit_min. -What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org @@ -88,7 +88,7 @@ Description: queued on this network device transmit queue. See include/linux/dynamic_queue_limits.h for the default value. -What: /sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min Date: November 2011 KernelVersion: 3.3 Contact: netdev@vger.kernel.org diff --git a/Documentation/ABI/testing/sysfs-class-net-statistics b/Documentation/ABI/testing/sysfs-class-net-statistics index 55db27815..53e508c69 100644 --- a/Documentation/ABI/testing/sysfs-class-net-statistics +++ b/Documentation/ABI/testing/sysfs-class-net-statistics @@ -1,4 +1,4 @@ -What: /sys/class/<iface>/statistics/collisions +What: /sys/class/net/<iface>/statistics/collisions Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -6,7 +6,7 @@ Description: Indicates the number of collisions seen by this network device. This value might not be relevant with all MAC layers. -What: /sys/class/<iface>/statistics/multicast +What: /sys/class/net/<iface>/statistics/multicast Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -14,7 +14,7 @@ Description: Indicates the number of multicast packets received by this network device. -What: /sys/class/<iface>/statistics/rx_bytes +What: /sys/class/net/<iface>/statistics/rx_bytes Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -23,7 +23,7 @@ Description: See the network driver for the exact meaning of when this value is incremented. -What: /sys/class/<iface>/statistics/rx_compressed +What: /sys/class/net/<iface>/statistics/rx_compressed Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -32,7 +32,7 @@ Description: network device. This value might only be relevant for interfaces that support packet compression (e.g: PPP). -What: /sys/class/<iface>/statistics/rx_crc_errors +What: /sys/class/net/<iface>/statistics/rx_crc_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -41,7 +41,7 @@ Description: by this network device. Note that the specific meaning might depend on the MAC layer used by the interface. -What: /sys/class/<iface>/statistics/rx_dropped +What: /sys/class/net/<iface>/statistics/rx_dropped Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -51,7 +51,7 @@ Description: packet processing. See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/rx_errors +What: /sys/class/net/<iface>/statistics/rx_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -59,7 +59,7 @@ Description: Indicates the number of receive errors on this network device. See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/rx_fifo_errors +What: /sys/class/net/<iface>/statistics/rx_fifo_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -68,7 +68,7 @@ Description: network device. See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/rx_frame_errors +What: /sys/class/net/<iface>/statistics/rx_frame_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -78,7 +78,7 @@ Description: on the MAC layer protocol used. See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/rx_length_errors +What: /sys/class/net/<iface>/statistics/rx_length_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -87,7 +87,7 @@ Description: error, oversized or undersized. See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/rx_missed_errors +What: /sys/class/net/<iface>/statistics/rx_missed_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -96,7 +96,7 @@ Description: due to lack of capacity in the receive side. See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/rx_nohandler +What: /sys/class/net/<iface>/statistics/rx_nohandler Date: February 2016 KernelVersion: 4.6 Contact: netdev@vger.kernel.org @@ -104,7 +104,7 @@ Description: Indicates the number of received packets that were dropped on an inactive device by the network core. -What: /sys/class/<iface>/statistics/rx_over_errors +What: /sys/class/net/<iface>/statistics/rx_over_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -114,7 +114,7 @@ Description: (e.g: larger than MTU). See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/rx_packets +What: /sys/class/net/<iface>/statistics/rx_packets Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -122,7 +122,7 @@ Description: Indicates the total number of good packets received by this network device. -What: /sys/class/<iface>/statistics/tx_aborted_errors +What: /sys/class/net/<iface>/statistics/tx_aborted_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -132,7 +132,7 @@ Description: a medium collision). See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/tx_bytes +What: /sys/class/net/<iface>/statistics/tx_bytes Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -143,7 +143,7 @@ Description: transmitted packets or all packets that have been queued for transmission. -What: /sys/class/<iface>/statistics/tx_carrier_errors +What: /sys/class/net/<iface>/statistics/tx_carrier_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -152,7 +152,7 @@ Description: because of carrier errors (e.g: physical link down). See the network driver for the exact meaning of this value. -What: /sys/class/<iface>/statistics/tx_compressed +What: /sys/class/net/<iface>/statistics/tx_compressed Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -161,7 +161,7 @@ Description: this might only be relevant for devices that support compression (e.g: PPP). -What: /sys/class/<iface>/statistics/tx_dropped +What: /sys/class/net/<iface>/statistics/tx_dropped Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -170,7 +170,7 @@ Description: See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class/<iface>/statistics/tx_errors +What: /sys/class/net/<iface>/statistics/tx_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -179,7 +179,7 @@ Description: a network device. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class/<iface>/statistics/tx_fifo_errors +What: /sys/class/net/<iface>/statistics/tx_fifo_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -188,7 +188,7 @@ Description: FIFO error. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class/<iface>/statistics/tx_heartbeat_errors +What: /sys/class/net/<iface>/statistics/tx_heartbeat_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -197,7 +197,7 @@ Description: reported as heartbeat errors. See the driver for the exact reasons as to why the packets were dropped. -What: /sys/class/<iface>/statistics/tx_packets +What: /sys/class/net/<iface>/statistics/tx_packets Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org @@ -206,7 +206,7 @@ Description: device. See the driver for whether this reports the number of all attempted or successful transmissions. -What: /sys/class/<iface>/statistics/tx_window_errors +What: /sys/class/net/<iface>/statistics/tx_window_errors Date: April 2005 KernelVersion: 2.6.12 Contact: netdev@vger.kernel.org diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index bfb4f4fad..2a273bfeb 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -507,6 +507,7 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/mds /sys/devices/system/cpu/vulnerabilities/meltdown /sys/devices/system/cpu/vulnerabilities/mmio_stale_data + /sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling /sys/devices/system/cpu/vulnerabilities/retbleed /sys/devices/system/cpu/vulnerabilities/spec_store_bypass /sys/devices/system/cpu/vulnerabilities/spectre_v1 diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index 84742be22..e020d1637 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -18,3 +18,4 @@ are configurable at compile, boot or run time. processor_mmio_stale_data.rst gather_data_sampling.rst srso + reg-file-data-sampling diff --git a/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst new file mode 100644 index 000000000..810424b4b --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst @@ -0,0 +1,104 @@ +================================== +Register File Data Sampling (RFDS) +================================== + +Register File Data Sampling (RFDS) is a microarchitectural vulnerability that +only affects Intel Atom parts(also branded as E-cores). RFDS may allow +a malicious actor to infer data values previously used in floating point +registers, vector registers, or integer registers. RFDS does not provide the +ability to choose which data is inferred. CVE-2023-28746 is assigned to RFDS. + +Affected Processors +=================== +Below is the list of affected Intel processors [#f1]_: + + =================== ============ + Common name Family_Model + =================== ============ + ATOM_GOLDMONT 06_5CH + ATOM_GOLDMONT_D 06_5FH + ATOM_GOLDMONT_PLUS 06_7AH + ATOM_TREMONT_D 06_86H + ATOM_TREMONT 06_96H + ALDERLAKE 06_97H + ALDERLAKE_L 06_9AH + ATOM_TREMONT_L 06_9CH + RAPTORLAKE 06_B7H + RAPTORLAKE_P 06_BAH + ALDERLAKE_N 06_BEH + RAPTORLAKE_S 06_BFH + =================== ============ + +As an exception to this table, Intel Xeon E family parts ALDERLAKE(06_97H) and +RAPTORLAKE(06_B7H) codenamed Catlow are not affected. They are reported as +vulnerable in Linux because they share the same family/model with an affected +part. Unlike their affected counterparts, they do not enumerate RFDS_CLEAR or +CPUID.HYBRID. This information could be used to distinguish between the +affected and unaffected parts, but it is deemed not worth adding complexity as +the reporting is fixed automatically when these parts enumerate RFDS_NO. + +Mitigation +========== +Intel released a microcode update that enables software to clear sensitive +information using the VERW instruction. Like MDS, RFDS deploys the same +mitigation strategy to force the CPU to clear the affected buffers before an +attacker can extract the secrets. This is achieved by using the otherwise +unused and obsolete VERW instruction in combination with a microcode update. +The microcode clears the affected CPU buffers when the VERW instruction is +executed. + +Mitigation points +----------------- +VERW is executed by the kernel before returning to user space, and by KVM +before VMentry. None of the affected cores support SMT, so VERW is not required +at C-state transitions. + +New bits in IA32_ARCH_CAPABILITIES +---------------------------------- +Newer processors and microcode update on existing affected processors added new +bits to IA32_ARCH_CAPABILITIES MSR. These bits can be used to enumerate +vulnerability and mitigation capability: + +- Bit 27 - RFDS_NO - When set, processor is not affected by RFDS. +- Bit 28 - RFDS_CLEAR - When set, processor is affected by RFDS, and has the + microcode that clears the affected buffers on VERW execution. + +Mitigation control on the kernel command line +--------------------------------------------- +The kernel command line allows to control RFDS mitigation at boot time with the +parameter "reg_file_data_sampling=". The valid arguments are: + + ========== ================================================================= + on If the CPU is vulnerable, enable mitigation; CPU buffer clearing + on exit to userspace and before entering a VM. + off Disables mitigation. + ========== ================================================================= + +Mitigation default is selected by CONFIG_MITIGATION_RFDS. + +Mitigation status information +----------------------------- +The Linux kernel provides a sysfs interface to enumerate the current +vulnerability status of the system: whether the system is vulnerable, and +which mitigations are active. The relevant sysfs file is: + + /sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling + +The possible values in this file are: + + .. list-table:: + + * - 'Not affected' + - The processor is not vulnerable + * - 'Vulnerable' + - The processor is vulnerable, but no mitigation enabled + * - 'Vulnerable: No microcode' + - The processor is vulnerable but microcode is not updated. + * - 'Mitigation: Clear Register File' + - The processor is vulnerable and the CPU buffer clearing mitigation is + enabled. + +References +---------- +.. [#f1] Affected Processors + https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index 0fba3758d..305600351 100644 --- a/Documentation/admin-guide/hw-vuln/spectre.rst +++ b/Documentation/admin-guide/hw-vuln/spectre.rst @@ -484,11 +484,14 @@ Spectre variant 2 Systems which support enhanced IBRS (eIBRS) enable IBRS protection once at boot, by setting the IBRS bit, and they're automatically protected against - Spectre v2 variant attacks, including cross-thread branch target injections - on SMT systems (STIBP). In other words, eIBRS enables STIBP too. + Spectre v2 variant attacks. - Legacy IBRS systems clear the IBRS bit on exit to userspace and - therefore explicitly enable STIBP for that + On Intel's enhanced IBRS systems, this includes cross-thread branch target + injections on SMT systems (STIBP). In other words, Intel eIBRS enables + STIBP, too. + + AMD Automatic IBRS does not protect userspace, and Legacy IBRS systems clear + the IBRS bit on exit to userspace, therefore both explicitly enable STIBP. The retpoline mitigation is turned on by default on vulnerable CPUs. It can be forced on or off by the administrator @@ -622,9 +625,10 @@ kernel command line. retpoline,generic Retpolines retpoline,lfence LFENCE; indirect branch retpoline,amd alias for retpoline,lfence - eibrs enhanced IBRS - eibrs,retpoline enhanced IBRS + Retpolines - eibrs,lfence enhanced IBRS + LFENCE + eibrs Enhanced/Auto IBRS + eibrs,retpoline Enhanced/Auto IBRS + Retpolines + eibrs,lfence Enhanced/Auto IBRS + LFENCE + ibrs use IBRS to protect kernel Not specifying this option is equivalent to spectre_v2=auto. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index f1f7c068c..8e4882bb8 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -993,6 +993,26 @@ The filter can be disabled or changed to another driver later using sysfs. + reg_file_data_sampling= + [X86] Controls mitigation for Register File Data + Sampling (RFDS) vulnerability. RFDS is a CPU + vulnerability which may allow userspace to infer + kernel data values previously stored in floating point + registers, vector registers, or integer registers. + RFDS only affects Intel Atom processors. + + on: Turns ON the mitigation. + off: Turns OFF the mitigation. + + This parameter overrides the compile time default set + by CONFIG_MITIGATION_RFDS. Mitigation cannot be + disabled when other VERW based mitigations (like MDS) + are enabled. In order to disable RFDS mitigation all + VERW based mitigations need to be disabled. + + For details see: + Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst + driver_async_probe= [KNL] List of driver names to be probed asynchronously. Format: <driver_name1>,<driver_name2>... @@ -2919,6 +2939,7 @@ nopti [X86,PPC] nospectre_v1 [X86,PPC] nospectre_v2 [X86,PPC,S390,ARM64] + reg_file_data_sampling=off [X86] retbleed=off [X86] spec_store_bypass_disable=off [X86,PPC] spectre_v2_user=off [X86] @@ -5091,9 +5112,9 @@ retpoline,generic - Retpolines retpoline,lfence - LFENCE; indirect branch retpoline,amd - alias for retpoline,lfence - eibrs - enhanced IBRS - eibrs,retpoline - enhanced IBRS + Retpolines - eibrs,lfence - enhanced IBRS + LFENCE + eibrs - Enhanced/Auto IBRS + eibrs,retpoline - Enhanced/Auto IBRS + Retpolines + eibrs,lfence - Enhanced/Auto IBRS + LFENCE ibrs - use IBRS to protect kernel Not specifying this option is equivalent to diff --git a/Documentation/block/queue-sysfs.rst b/Documentation/block/queue-sysfs.rst index 2638d3446..c8bf8bc3c 100644 --- a/Documentation/block/queue-sysfs.rst +++ b/Documentation/block/queue-sysfs.rst @@ -273,4 +273,11 @@ devices are described in the ZBC (Zoned Block Commands) and ZAC do not support zone commands, they will be treated as regular block devices and zoned will report "none". +zone_write_granularity (RO) +--------------------------- +This indicates the alignment constraint, in bytes, for write operations in +sequential zones of zoned block devices (devices with a zoned attributed +that reports "host-managed" or "host-aware"). This value is always 0 for +regular block devices. + Jens Axboe <jens.axboe@oracle.com>, February 2009 diff --git a/Documentation/filesystems/directory-locking.rst b/Documentation/filesystems/directory-locking.rst index dccd61c7c..193c22687 100644 --- a/Documentation/filesystems/directory-locking.rst +++ b/Documentation/filesystems/directory-locking.rst @@ -22,13 +22,16 @@ exclusive. 3) object removal. Locking rules: caller locks parent, finds victim, locks victim and calls the method. Locks are exclusive. -4) rename() that is _not_ cross-directory. Locking rules: caller locks the -parent and finds source and target. We lock both (provided they exist). If we -need to lock two inodes of different type (dir vs non-dir), we lock directory -first. If we need to lock two inodes of the same type, lock them in inode -pointer order. Then call the method. All locks are exclusive. -NB: we might get away with locking the source (and target in exchange -case) shared. +4) rename() that is _not_ cross-directory. Locking rules: caller locks +the parent and finds source and target. Then we decide which of the +source and target need to be locked. Source needs to be locked if it's a +non-directory; target - if it's a non-directory or about to be removed. +Take the locks that need to be taken, in inode pointer order if need +to take both (that can happen only when both source and target are +non-directories - the source because it wouldn't be locked otherwise +and the target because mixing directory and non-directory is allowed +only with RENAME_EXCHANGE, and that won't be removing the target). +After the locks had been taken, call the method. All locks are exclusive. 5) link creation. Locking rules: @@ -44,20 +47,17 @@ rules: * lock the filesystem * lock parents in "ancestors first" order. If one is not ancestor of - the other, lock them in inode pointer order. + the other, lock the parent of source first. * find source and target. * if old parent is equal to or is a descendent of target fail with -ENOTEMPTY * if new parent is equal to or is a descendent of source fail with -ELOOP - * Lock both the source and the target provided they exist. If we - need to lock two inodes of different type (dir vs non-dir), we lock - the directory first. If we need to lock two inodes of the same type, - lock them in inode pointer order. + * Lock subdirectories involved (source before target). + * Lock non-directories involved, in inode pointer order. * call the method. -All ->i_rwsem are taken exclusive. Again, we might get away with locking -the source (and target in exchange case) shared. +All ->i_rwsem are taken exclusive. The rules above obviously guarantee that all directories that are going to be read, modified or removed by method will be locked by caller. @@ -67,6 +67,7 @@ If no directory is its own ancestor, the scheme above is deadlock-free. Proof: +[XXX: will be updated once we are done massaging the lock_rename()] First of all, at any moment we have a linear ordering of the objects - A < B iff (A is an ancestor of B) or (B is not an ancestor of A and ptr(A) < ptr(B)). diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index c0f2c7586..fbd695d66 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -95,7 +95,7 @@ symlink: exclusive mkdir: exclusive unlink: exclusive (both) rmdir: exclusive (both)(see below) -rename: exclusive (all) (see below) +rename: exclusive (both parents, some children) (see below) readlink: no get_link: no setattr: exclusive @@ -113,6 +113,9 @@ tmpfile: no Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_rwsem exclusive on victim. cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem. + ->unlink() and ->rename() have ->i_rwsem exclusive on all non-directories + involved. + ->rename() has ->i_rwsem exclusive on any subdirectory that changes parent. See Documentation/filesystems/directory-locking.rst for more detailed discussion of the locking scheme for directory operations. diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index 867036aa9..0a2d29d84 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -865,3 +865,21 @@ no matter what. Everything is handled by the caller. clone_private_mount() returns a longterm mount now, so the proper destructor of its result is kern_unmount() or kern_unmount_array(). + +--- + +**mandatory** + +If ->rename() update of .. on cross-directory move needs an exclusion with +directory modifications, do *not* lock the subdirectory in question in your +->rename() - it's done by the caller now [that item should've been added in +28eceeda130f "fs: Lock moved directories"]. + +--- + +**mandatory** + +On same-directory ->rename() the (tautological) update of .. is not protected +by any locks; just don't do it if the old parent is the same as the new one. +We really can't lock two subdirectories in same-directory rename - not without +deadlocks. diff --git a/Documentation/sound/soc/dapm.rst b/Documentation/sound/soc/dapm.rst index 8e4410793..c3154ce6e 100644 --- a/Documentation/sound/soc/dapm.rst +++ b/Documentation/sound/soc/dapm.rst @@ -234,7 +234,7 @@ corresponding soft power control. In this case it is necessary to create a virtual widget - a widget with no control bits e.g. :: - SND_SOC_DAPM_MIXER("AC97 Mixer", SND_SOC_DAPM_NOPM, 0, 0, NULL, 0), + SND_SOC_DAPM_MIXER("AC97 Mixer", SND_SOC_NOPM, 0, 0, NULL, 0), This can be used to merge to signal paths together in software. diff --git a/Documentation/x86/mds.rst b/Documentation/x86/mds.rst index 5d4330be2..e801df0bb 100644 --- a/Documentation/x86/mds.rst +++ b/Documentation/x86/mds.rst @@ -95,6 +95,9 @@ The kernel provides a function to invoke the buffer clearing: mds_clear_cpu_buffers() +Also macro CLEAR_CPU_BUFFERS can be used in ASM late in exit-to-user path. +Other than CFLAGS.ZF, this macro doesn't clobber any registers. + The mitigation is invoked on kernel/userspace, hypervisor/guest and C-state (idle) transitions. @@ -138,17 +141,30 @@ Mitigation points When transitioning from kernel to user space the CPU buffers are flushed on affected CPUs when the mitigation is not disabled on the kernel - command line. The migitation is enabled through the static key - mds_user_clear. - - The mitigation is invoked in prepare_exit_to_usermode() which covers - all but one of the kernel to user space transitions. The exception - is when we return from a Non Maskable Interrupt (NMI), which is - handled directly in do_nmi(). - - (The reason that NMI is special is that prepare_exit_to_usermode() can - enable IRQs. In NMI context, NMIs are blocked, and we don't want to - enable IRQs with NMIs blocked.) + command line. The mitigation is enabled through the feature flag + X86_FEATURE_CLEAR_CPU_BUF. + + The mitigation is invoked just before transitioning to userspace after + user registers are restored. This is done to minimize the window in + which kernel data could be accessed after VERW e.g. via an NMI after + VERW. + + **Corner case not handled** + Interrupts returning to kernel don't clear CPUs buffers since the + exit-to-user path is expected to do that anyways. But, there could be + a case when an NMI is generated in kernel after the exit-to-user path + has cleared the buffers. This case is not handled and NMI returning to + kernel don't clear CPU buffers because: + + 1. It is rare to get an NMI after VERW, but before returning to userspace. + 2. For an unprivileged user, there is no known way to make that NMI + less rare or target it. + 3. It would take a large number of these precisely-timed NMIs to mount + an actual attack. There's presumably not enough bandwidth. + 4. The NMI in question occurs after a VERW, i.e. when user state is + restored and most interesting data is already scrubbed. Whats left + is only the data that NMI touches, and that may or may not be of + any interest. 2. C-State transition @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 209 +SUBLEVEL = 216 EXTRAVERSION = NAME = Dare mighty things diff --git a/arch/Kconfig b/arch/Kconfig index 240277d56..72e4cef06 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -9,6 +9,14 @@ # source "arch/$(SRCARCH)/Kconfig" +config ARCH_CONFIGURES_CPU_MITIGATIONS + bool + +if !ARCH_CONFIGURES_CPU_MITIGATIONS +config CPU_MITIGATIONS + def_bool y +endif + menu "General architecture-dependent options" config CRASH_CORE diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index dcaa44e40..27f4194b3 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -205,7 +205,6 @@ }; gmac: ethernet@8000 { - #interrupt-cells = <1>; compatible = "snps,dwmac"; reg = <0x8000 0x2000>; interrupts = <10>; diff --git a/arch/arm/boot/dts/arm-realview-pb1176.dts b/arch/arm/boot/dts/arm-realview-pb1176.dts index f925782f8..f0be83eeb 100644 --- a/arch/arm/boot/dts/arm-realview-pb1176.dts +++ b/arch/arm/boot/dts/arm-realview-pb1176.dts @@ -435,7 +435,7 @@ /* Direct-mapped development chip ROM */ pb1176_rom@10200000 { - compatible = "direct-mapped"; + compatible = "mtd-rom"; reg = <0x10200000 0x4000>; bank-width = <1>; }; diff --git a/arch/arm/boot/dts/bcm47189-luxul-xap-1440.dts b/arch/arm/boot/dts/bcm47189-luxul-xap-1440.dts index 00e688b45..590116091 100644 --- a/arch/arm/boot/dts/bcm47189-luxul-xap-1440.dts +++ b/arch/arm/boot/dts/bcm47189-luxul-xap-1440.dts @@ -26,7 +26,6 @@ wlan { label = "bcm53xx:blue:wlan"; gpios = <&chipcommon 10 GPIO_ACTIVE_LOW>; - linux,default-trigger = "default-off"; }; system { diff --git a/arch/arm/boot/dts/bcm47189-luxul-xap-810.dts b/arch/arm/boot/dts/bcm47189-luxul-xap-810.dts index 78c80a5d3..8e7483272 100644 --- a/arch/arm/boot/dts/bcm47189-luxul-xap-810.dts +++ b/arch/arm/boot/dts/bcm47189-luxul-xap-810.dts @@ -26,7 +26,6 @@ 5ghz { label = "bcm53xx:blue:5ghz"; gpios = <&chipcommon 11 GPIO_ACTIVE_HIGH>; - linux,default-trigger = "default-off"; }; system { @@ -42,7 +41,6 @@ 2ghz { label = "bcm53xx:blue:2ghz"; gpios = <&pcie0_chipcommon 3 GPIO_ACTIVE_HIGH>; - linux,default-trigger = "default-off"; }; }; diff --git a/arch/arm/boot/dts/exynos4210-i9100.dts b/arch/arm/boot/dts/exynos4210-i9100.dts index d186b9314..525618197 100644 --- a/arch/arm/boot/dts/exynos4210-i9100.dts +++ b/arch/arm/boot/dts/exynos4210-i9100.dts @@ -464,6 +464,14 @@ regulator-name = "VT_CAM_1.8V"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + + /* + * Force-enable this regulator; otherwise the + * kernel hangs very early in the boot process + * for about 12 seconds, without apparent + * reason. + */ + regulator-always-on; }; vcclcd_reg: LDO13 { diff --git a/arch/arm/boot/dts/imx1-ads.dts b/arch/arm/boot/dts/imx1-ads.dts index 5833fb6f1..2c817c4a4 100644 --- a/arch/arm/boot/dts/imx1-ads.dts +++ b/arch/arm/boot/dts/imx1-ads.dts @@ -65,7 +65,7 @@ pinctrl-0 = <&pinctrl_weim>; status = "okay"; - nor: nor@0,0 { + nor: flash@0,0 { compatible = "cfi-flash"; reg = <0 0x00000000 0x02000000>; bank-width = <4>; diff --git a/arch/arm/boot/dts/imx1-apf9328.dts b/arch/arm/boot/dts/imx1-apf9328.dts index 77b21aa7a..27e72b07b 100644 --- a/arch/arm/boot/dts/imx1-apf9328.dts +++ b/arch/arm/boot/dts/imx1-apf9328.dts @@ -45,7 +45,7 @@ pinctrl-0 = <&pinctrl_weim>; status = "okay"; - nor: nor@0,0 { + nor: flash@0,0 { compatible = "cfi-flash"; reg = <0 0x00000000 0x02000000>; bank-width = <2>; diff --git a/arch/arm/boot/dts/imx1.dtsi b/arch/arm/boot/dts/imx1.dtsi index 9b9409878..8d6e900a9 100644 --- a/arch/arm/boot/dts/imx1.dtsi +++ b/arch/arm/boot/dts/imx1.dtsi @@ -268,9 +268,12 @@ status = "disabled"; }; - esram: esram@300000 { + esram: sram@300000 { compatible = "mmio-sram"; reg = <0x00300000 0x20000>; + ranges = <0 0x00300000 0x20000>; + #address-cells = <1>; + #size-cells = <1>; }; }; }; diff --git a/arch/arm/boot/dts/imx23-sansa.dts b/arch/arm/boot/dts/imx23-sansa.dts index 46057d9bf..c2efcc20a 100644 --- a/arch/arm/boot/dts/imx23-sansa.dts +++ b/arch/arm/boot/dts/imx23-sansa.dts @@ -175,10 +175,8 @@ #address-cells = <1>; #size-cells = <0>; compatible = "i2c-gpio"; - gpios = < - &gpio1 24 0 /* SDA */ - &gpio1 22 0 /* SCL */ - >; + sda-gpios = <&gpio1 24 0>; + scl-gpios = <&gpio1 22 0>; i2c-gpio,delay-us = <2>; /* ~100 kHz */ }; @@ -186,10 +184,8 @@ #address-cells = <1>; #size-cells = <0>; compatible = "i2c-gpio"; - gpios = < - &gpio0 31 0 /* SDA */ - &gpio0 30 0 /* SCL */ - >; + sda-gpios = <&gpio0 31 0>; + scl-gpios = <&gpio0 30 0>; i2c-gpio,delay-us = <2>; /* ~100 kHz */ touch: touch@20 { diff --git a/arch/arm/boot/dts/imx23.dtsi b/arch/arm/boot/dts/imx23.dtsi index ce3d6360a..b236d23f8 100644 --- a/arch/arm/boot/dts/imx23.dtsi +++ b/arch/arm/boot/dts/imx23.dtsi @@ -414,7 +414,7 @@ status = "disabled"; }; - dma_apbx: dma-apbx@80024000 { + dma_apbx: dma-controller@80024000 { compatible = "fsl,imx23-dma-apbx"; reg = <0x80024000 0x2000>; interrupts = <7 5 9 26 diff --git a/arch/arm/boot/dts/imx25-eukrea-cpuimx25.dtsi b/arch/arm/boot/dts/imx25-eukrea-cpuimx25.dtsi index 0703f62d1..93a6e4e68 100644 --- a/arch/arm/boot/dts/imx25-eukrea-cpuimx25.dtsi +++ b/arch/arm/boot/dts/imx25-eukrea-cpuimx25.dtsi @@ -27,7 +27,7 @@ pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; - pcf8563@51 { + rtc@51 { compatible = "nxp,pcf8563"; reg = <0x51>; }; diff --git a/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts b/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts index 7d4301b22..1ed3fb7b9 100644 --- a/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts +++ b/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-cmo-qvga.dts @@ -16,7 +16,7 @@ bus-width = <18>; display-timings { native-mode = <&qvga_timings>; - qvga_timings: 320x240 { + qvga_timings: timing0 { clock-frequency = <6500000>; hactive = <320>; vactive = <240>; diff --git a/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts b/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts index 80a7f96de..64b2ffac4 100644 --- a/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts +++ b/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-svga.dts @@ -16,7 +16,7 @@ bus-width = <18>; display-timings { native-mode = <&dvi_svga_timings>; - dvi_svga_timings: 800x600 { + dvi_svga_timings: timing0 { clock-frequency = <40000000>; hactive = <800>; vactive = <600>; diff --git a/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts b/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts index 24027a1fb..fb074bfda 100644 --- a/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts +++ b/arch/arm/boot/dts/imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dts @@ -16,7 +16,7 @@ bus-width = <18>; display-timings { native-mode = <&dvi_vga_timings>; - dvi_vga_timings: 640x480 { + dvi_vga_timings: timing0 { clock-frequency = <31250000>; hactive = <640>; vactive = <480>; diff --git a/arch/arm/boot/dts/imx25-pdk.dts b/arch/arm/boot/dts/imx25-pdk.dts index fb66884d8..59b40d13a 100644 --- a/arch/arm/boot/dts/imx25-pdk.dts +++ b/arch/arm/boot/dts/imx25-pdk.dts @@ -78,7 +78,7 @@ bus-width = <18>; display-timings { native-mode = <&wvga_timings>; - wvga_timings: 640x480 { + wvga_timings: timing0 { hactive = <640>; vactive = <480>; hback-porch = <45>; diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi index d24b1da18..99886ba36 100644 --- a/arch/arm/boot/dts/imx25.dtsi +++ b/arch/arm/boot/dts/imx25.dtsi @@ -543,7 +543,7 @@ }; iim: efuse@53ff0000 { - compatible = "fsl,imx25-iim", "fsl,imx27-iim"; + compatible = "fsl,imx25-iim"; reg = <0x53ff0000 0x4000>; interrupts = <19>; clocks = <&clks 99>; diff --git a/arch/arm/boot/dts/imx27-apf27dev.dts b/arch/arm/boot/dts/imx27-apf27dev.dts index 6f1e8ce9e..3d9bb7fc3 100644 --- a/arch/arm/boot/dts/imx27-apf27dev.dts +++ b/arch/arm/boot/dts/imx27-apf27dev.dts @@ -16,7 +16,7 @@ fsl,pcr = <0xfae80083>; /* non-standard but required */ display-timings { native-mode = <&timing0>; - timing0: 800x480 { + timing0: timing0 { clock-frequency = <33000033>; hactive = <800>; vactive = <480>; @@ -47,7 +47,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_gpio_leds>; - user { + led-user { label = "Heartbeat"; gpios = <&gpio6 14 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; diff --git a/arch/arm/boot/dts/imx27-eukrea-cpuimx27.dtsi b/arch/arm/boot/dts/imx27-eukrea-cpuimx27.dtsi index 74110bbcd..c7e923584 100644 --- a/arch/arm/boot/dts/imx27-eukrea-cpuimx27.dtsi +++ b/arch/arm/boot/dts/imx27-eukrea-cpuimx27.dtsi @@ -33,7 +33,7 @@ pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; - pcf8563@51 { + rtc@51 { compatible = "nxp,pcf8563"; reg = <0x51>; }; @@ -90,7 +90,7 @@ &weim { status = "okay"; - nor: nor@0,0 { + nor: flash@0,0 { #address-cells = <1>; #size-cells = <1>; compatible = "cfi-flash"; diff --git a/arch/arm/boot/dts/imx27-eukrea-mbimxsd27-baseboard.dts b/arch/arm/boot/dts/imx27-eukrea-mbimxsd27-baseboard.dts index 9c3ec82ec..50fa0bd4c 100644 --- a/arch/arm/boot/dts/imx27-eukrea-mbimxsd27-baseboard.dts +++ b/arch/arm/boot/dts/imx27-eukrea-mbimxsd27-baseboard.dts @@ -16,7 +16,7 @@ display-timings { native-mode = <&timing0>; - timing0: 320x240 { + timing0: timing0 { clock-frequency = <6500000>; hactive = <320>; vactive = <240>; diff --git a/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts index 188639738..7f36af150 100644 --- a/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts +++ b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts @@ -19,7 +19,7 @@ fsl,pcr = <0xf0c88080>; /* non-standard but required */ display-timings { native-mode = <&timing0>; - timing0: 640x480 { + timing0: timing0 { hactive = <640>; vactive = <480>; hback-porch = <112>; diff --git a/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts b/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts index 344e77790..d133b9f08 100644 --- a/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts +++ b/arch/arm/boot/dts/imx27-phytec-phycore-rdk.dts @@ -19,7 +19,7 @@ display-timings { native-mode = <&timing0>; - timing0: 240x320 { + timing0: timing0 { clock-frequency = <5500000>; hactive = <240>; vactive = <320>; diff --git a/arch/arm/boot/dts/imx27-phytec-phycore-som.dtsi b/arch/arm/boot/dts/imx27-phytec-phycore-som.dtsi index 3d1027317..a5fdc2fd4 100644 --- a/arch/arm/boot/dts/imx27-phytec-phycore-som.dtsi +++ b/arch/arm/boot/dts/imx27-phytec-phycore-som.dtsi @@ -322,7 +322,7 @@ &weim { status = "okay"; - nor: nor@0,0 { + nor: flash@0,0 { compatible = "cfi-flash"; reg = <0 0x00000000 0x02000000>; bank-width = <2>; diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi index 7bc132737..8ae24c865 100644 --- a/arch/arm/boot/dts/imx27.dtsi +++ b/arch/arm/boot/dts/imx27.dtsi @@ -588,6 +588,9 @@ iram: sram@ffff4c00 { compatible = "mmio-sram"; reg = <0xffff4c00 0xb400>; + ranges = <0 0xffff4c00 0xb400>; + #address-cells = <1>; + #size-cells = <1>; }; }; }; diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi index 6cab8b66d..23ef4a322 100644 --- a/arch/arm/boot/dts/imx28.dtsi +++ b/arch/arm/boot/dts/imx28.dtsi @@ -982,7 +982,7 @@ status = "disabled"; }; - dma_apbx: dma-apbx@80024000 { + dma_apbx: dma-controller@80024000 { compatible = "fsl,imx28-dma-apbx"; reg = <0x80024000 0x2000>; interrupts = <78 79 66 0 diff --git a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi index ebc0892e3..cbf5a7662 100644 --- a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi +++ b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi @@ -103,8 +103,6 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; phy-mode = "rgmii-id"; - phy-reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; - phy-reset-duration = <20>; phy-supply = <&sw2_reg>; status = "okay"; @@ -117,17 +115,10 @@ #address-cells = <1>; #size-cells = <0>; - phy_port2: phy@1 { - reg = <1>; - }; - - phy_port3: phy@2 { - reg = <2>; - }; - switch@10 { compatible = "qca,qca8334"; - reg = <10>; + reg = <0x10>; + reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; switch_ports: ports { #address-cells = <1>; @@ -148,15 +139,30 @@ eth2: port@2 { reg = <2>; label = "eth2"; + phy-mode = "internal"; phy-handle = <&phy_port2>; }; eth1: port@3 { reg = <3>; label = "eth1"; + phy-mode = "internal"; phy-handle = <&phy_port3>; }; }; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + phy_port2: ethernet-phy@1 { + reg = <1>; + }; + + phy_port3: ethernet-phy@2 { + reg = <2>; + }; + }; }; }; }; diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi index 08332f70a..51491b741 100644 --- a/arch/arm/boot/dts/imx6sx.dtsi +++ b/arch/arm/boot/dts/imx6sx.dtsi @@ -981,6 +981,8 @@ <&clks IMX6SX_CLK_USDHC1>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; + fsl,tuning-start-tap = <20>; + fsl,tuning-step= <2>; status = "disabled"; }; @@ -993,6 +995,8 @@ <&clks IMX6SX_CLK_USDHC2>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; + fsl,tuning-start-tap = <20>; + fsl,tuning-step= <2>; status = "disabled"; }; @@ -1005,6 +1009,8 @@ <&clks IMX6SX_CLK_USDHC3>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; + fsl,tuning-start-tap = <20>; + fsl,tuning-step= <2>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi index b0bcfa909..8ad3e60fd 100644 --- a/arch/arm/boot/dts/imx7d.dtsi +++ b/arch/arm/boot/dts/imx7d.dtsi @@ -209,9 +209,6 @@ }; &ca_funnel_in_ports { - #address-cells = <1>; - #size-cells = <0>; - port@1 { reg = <1>; ca_funnel_in_port1: endpoint { diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 03bde2fb9..b4cab6a21 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -173,7 +173,11 @@ clock-names = "apb_pclk"; ca_funnel_in_ports: in-ports { - port { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; ca_funnel_in_port0: endpoint { remote-endpoint = <&etm0_out_port>; }; @@ -769,7 +773,7 @@ }; lcdif: lcdif@30730000 { - compatible = "fsl,imx7d-lcdif", "fsl,imx28-lcdif"; + compatible = "fsl,imx7d-lcdif", "fsl,imx6sx-lcdif"; reg = <0x30730000 0x10000>; interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>, @@ -1231,7 +1235,7 @@ gpmi: nand-controller@33002000{ compatible = "fsl,imx7d-gpmi-nand"; #address-cells = <1>; - #size-cells = <1>; + #size-cells = <0>; reg = <0x33002000 0x2000>, <0x33004000 0x4000>; reg-names = "gpmi-nand", "bch"; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/boot/dts/mmp2-brownstone.dts b/arch/arm/boot/dts/mmp2-brownstone.dts index 04f1ae138..bc64348b8 100644 --- a/arch/arm/boot/dts/mmp2-brownstone.dts +++ b/arch/arm/boot/dts/mmp2-brownstone.dts @@ -28,7 +28,7 @@ &twsi1 { status = "okay"; pmic: max8925@3c { - compatible = "maxium,max8925"; + compatible = "maxim,max8925"; reg = <0x3c>; interrupts = <1>; interrupt-parent = <&intcmux4>; diff --git a/arch/arm/boot/dts/rk3036.dtsi b/arch/arm/boot/dts/rk3036.dtsi index 093567022..5f47b638f 100644 --- a/arch/arm/boot/dts/rk3036.dtsi +++ b/arch/arm/boot/dts/rk3036.dtsi @@ -336,12 +336,20 @@ pinctrl-0 = <&hdmi_ctl>; status = "disabled"; - hdmi_in: port { + ports { #address-cells = <1>; #size-cells = <0>; - hdmi_in_vop: endpoint@0 { + + hdmi_in: port@0 { reg = <0>; - remote-endpoint = <&vop_out_hdmi>; + + hdmi_in_vop: endpoint { + remote-endpoint = <&vop_out_hdmi>; + }; + }; + + hdmi_out: port@1 { + reg = <1>; }; }; }; diff --git a/arch/arm/boot/dts/sun8i-h2-plus-bananapi-m2-zero.dts b/arch/arm/boot/dts/sun8i-h2-plus-bananapi-m2-zero.dts index 4c6704e4c..74d5732c4 100644 --- a/arch/arm/boot/dts/sun8i-h2-plus-bananapi-m2-zero.dts +++ b/arch/arm/boot/dts/sun8i-h2-plus-bananapi-m2-zero.dts @@ -62,6 +62,30 @@ states = <1100000 0>, <1300000 1>; }; + reg_vcc_dram: vcc-dram { + compatible = "regulator-fixed"; + regulator-name = "vcc-dram"; + regulator-min-microvolt = <1500000>; + regulator-max-microvolt = <1500000>; + regulator-always-on; + regulator-boot-on; + enable-active-high; + gpio = <&r_pio 0 9 GPIO_ACTIVE_HIGH>; /* PL9 */ + vin-supply = <®_vcc5v0>; + }; + + reg_vcc1v2: vcc1v2 { + compatible = "regulator-fixed"; + regulator-name = "vcc1v2"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-always-on; + regulator-boot-on; + enable-active-high; + gpio = <&r_pio 0 8 GPIO_ACTIVE_HIGH>; /* PL8 */ + vin-supply = <®_vcc5v0>; + }; + wifi_pwrseq: wifi_pwrseq { compatible = "mmc-pwrseq-simple"; reset-gpios = <&r_pio 0 7 GPIO_ACTIVE_LOW>; /* PL7 */ diff --git a/arch/arm/crypto/sha256_glue.c b/arch/arm/crypto/sha256_glue.c index b8a4f7902..e36b86778 100644 --- a/arch/arm/crypto/sha256_glue.c +++ b/arch/arm/crypto/sha256_glue.c @@ -24,8 +24,8 @@ #include "sha256_glue.h" -asmlinkage void sha256_block_data_order(u32 *digest, const void *data, - unsigned int num_blks); +asmlinkage void sha256_block_data_order(struct sha256_state *state, + const u8 *data, int num_blks); int crypto_sha256_arm_update(struct shash_desc *desc, const u8 *data, unsigned int len) @@ -33,23 +33,20 @@ int crypto_sha256_arm_update(struct shash_desc *desc, const u8 *data, /* make sure casting to sha256_block_fn() is safe */ BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0); - return sha256_base_do_update(desc, data, len, - (sha256_block_fn *)sha256_block_data_order); + return sha256_base_do_update(desc, data, len, sha256_block_data_order); } EXPORT_SYMBOL(crypto_sha256_arm_update); static int crypto_sha256_arm_final(struct shash_desc *desc, u8 *out) { - sha256_base_do_finalize(desc, - (sha256_block_fn *)sha256_block_data_order); + sha256_base_do_finalize(desc, sha256_block_data_order); return sha256_base_finish(desc, out); } int crypto_sha256_arm_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { - sha256_base_do_update(desc, data, len, - (sha256_block_fn *)sha256_block_data_order); + sha256_base_do_update(desc, data, len, sha256_block_data_order); return crypto_sha256_arm_final(desc, out); } EXPORT_SYMBOL(crypto_sha256_arm_finup); diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c index 8775aa42b..1a16b98ec 100644 --- a/arch/arm/crypto/sha512-glue.c +++ b/arch/arm/crypto/sha512-glue.c @@ -25,27 +25,25 @@ MODULE_ALIAS_CRYPTO("sha512"); MODULE_ALIAS_CRYPTO("sha384-arm"); MODULE_ALIAS_CRYPTO("sha512-arm"); -asmlinkage void sha512_block_data_order(u64 *state, u8 const *src, int blocks); +asmlinkage void sha512_block_data_order(struct sha512_state *state, + u8 const *src, int blocks); int sha512_arm_update(struct shash_desc *desc, const u8 *data, unsigned int len) { - return sha512_base_do_update(desc, data, len, - (sha512_block_fn *)sha512_block_data_order); + return sha512_base_do_update(desc, data, len, sha512_block_data_order); } static int sha512_arm_final(struct shash_desc *desc, u8 *out) { - sha512_base_do_finalize(desc, - (sha512_block_fn *)sha512_block_data_order); + sha512_base_do_finalize(desc, sha512_block_data_order); return sha512_base_finish(desc, out); } int sha512_arm_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { - sha512_base_do_update(desc, data, len, - (sha512_block_fn *)sha512_block_data_order); + sha512_base_do_update(desc, data, len, sha512_block_data_order); return sha512_arm_final(desc, out); } diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c index 6fb19a393..c06ae33dc 100644 --- a/arch/arm/mach-ep93xx/core.c +++ b/arch/arm/mach-ep93xx/core.c @@ -337,6 +337,7 @@ static struct gpiod_lookup_table ep93xx_i2c_gpiod_table = { GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), GPIO_LOOKUP_IDX("G", 0, NULL, 1, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), + { } }, }; diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi index 0f4bcd15d..086c3cc7d 100644 --- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi @@ -414,14 +414,14 @@ crypto: crypto@90000 { compatible = "inside-secure,safexcel-eip97ies"; reg = <0x90000 0x20000>; - interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>, + interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "mem", "ring0", "ring1", - "ring2", "ring3", "eip"; + <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "ring0", "ring1", "ring2", + "ring3", "eip", "mem"; clocks = <&nb_periph_clk 15>; }; diff --git a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi index 9dcf16bea..da83bfdbe 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi @@ -477,14 +477,14 @@ CP11X_LABEL(crypto): crypto@800000 { compatible = "inside-secure,safexcel-eip197b"; reg = <0x800000 0x200000>; - interrupts = <87 IRQ_TYPE_LEVEL_HIGH>, - <88 IRQ_TYPE_LEVEL_HIGH>, + interrupts = <88 IRQ_TYPE_LEVEL_HIGH>, <89 IRQ_TYPE_LEVEL_HIGH>, <90 IRQ_TYPE_LEVEL_HIGH>, <91 IRQ_TYPE_LEVEL_HIGH>, - <92 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "mem", "ring0", "ring1", - "ring2", "ring3", "eip"; + <92 IRQ_TYPE_LEVEL_HIGH>, + <87 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "ring0", "ring1", "ring2", "ring3", + "eip", "mem"; clock-names = "core", "reg"; clocks = <&CP11X_LABEL(clk) 1 26>, <&CP11X_LABEL(clk) 1 17>; diff --git a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts index 9d20cabf4..99515c13d 100644 --- a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts +++ b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts @@ -127,7 +127,7 @@ }; &pio { - eth_default: eth_default { + eth_default: eth-default-pins { tx_pins { pinmux = <MT2712_PIN_71_GBE_TXD3__FUNC_GBE_TXD3>, <MT2712_PIN_72_GBE_TXD2__FUNC_GBE_TXD2>, @@ -154,7 +154,7 @@ }; }; - eth_sleep: eth_sleep { + eth_sleep: eth-sleep-pins { tx_pins { pinmux = <MT2712_PIN_71_GBE_TXD3__FUNC_GPIO71>, <MT2712_PIN_72_GBE_TXD2__FUNC_GPIO72>, @@ -180,14 +180,14 @@ }; }; - usb0_id_pins_float: usb0_iddig { + usb0_id_pins_float: usb0-iddig-pins { pins_iddig { pinmux = <MT2712_PIN_12_IDDIG_P0__FUNC_IDDIG_A>; bias-pull-up; }; }; - usb1_id_pins_float: usb1_iddig { + usb1_id_pins_float: usb1-iddig-pins { pins_iddig { pinmux = <MT2712_PIN_14_IDDIG_P1__FUNC_IDDIG_B>; bias-pull-up; diff --git a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi index cc3d1c995..f7ce2eba1 100644 --- a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi @@ -249,10 +249,11 @@ #clock-cells = <1>; }; - infracfg: syscon@10001000 { + infracfg: clock-controller@10001000 { compatible = "mediatek,mt2712-infracfg", "syscon"; reg = <0 0x10001000 0 0x1000>; #clock-cells = <1>; + #reset-cells = <1>; }; pericfg: syscon@10003000 { diff --git a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts index 7e6cffdc5..778174a7d 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts @@ -71,6 +71,7 @@ memory@40000000 { reg = <0 0x40000000 0 0x40000000>; + device_type = "memory"; }; reg_1p8v: regulator-1p8v { diff --git a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts index 993f033d0..810575de6 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts @@ -57,6 +57,7 @@ memory@40000000 { reg = <0 0x40000000 0 0x20000000>; + device_type = "memory"; }; reg_1p8v: regulator-1p8v { diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi index 884930a58..4454115ad 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi @@ -244,7 +244,7 @@ clock-names = "hif_sel"; }; - cir: cir@10009000 { + cir: ir-receiver@10009000 { compatible = "mediatek,mt7622-cir"; reg = <0 0x10009000 0 0x1000>; interrupts = <GIC_SPI 175 IRQ_TYPE_LEVEL_LOW>; @@ -275,16 +275,14 @@ }; }; - apmixedsys: apmixedsys@10209000 { - compatible = "mediatek,mt7622-apmixedsys", - "syscon"; + apmixedsys: clock-controller@10209000 { + compatible = "mediatek,mt7622-apmixedsys"; reg = <0 0x10209000 0 0x1000>; #clock-cells = <1>; }; - topckgen: topckgen@10210000 { - compatible = "mediatek,mt7622-topckgen", - "syscon"; + topckgen: clock-controller@10210000 { + compatible = "mediatek,mt7622-topckgen"; reg = <0 0x10210000 0 0x1000>; #clock-cells = <1>; }; @@ -357,7 +355,7 @@ }; cci_control2: slave-if@5000 { - compatible = "arm,cci-400-ctrl-if"; + compatible = "arm,cci-400-ctrl-if", "syscon"; interface-type = "ace"; reg = <0x5000 0x1000>; }; @@ -507,7 +505,6 @@ <&pericfg CLK_PERI_AUXADC_PD>; clock-names = "therm", "auxadc"; resets = <&pericfg MT7622_PERI_THERM_SW_RST>; - reset-names = "therm"; mediatek,auxadc = <&auxadc>; mediatek,apmixedsys = <&apmixedsys>; nvmem-cells = <&thermal_calibration>; @@ -715,9 +712,8 @@ power-domains = <&scpsys MT7622_POWER_DOMAIN_WB>; }; - ssusbsys: ssusbsys@1a000000 { - compatible = "mediatek,mt7622-ssusbsys", - "syscon"; + ssusbsys: clock-controller@1a000000 { + compatible = "mediatek,mt7622-ssusbsys"; reg = <0 0x1a000000 0 0x1000>; #clock-cells = <1>; #reset-cells = <1>; @@ -774,9 +770,8 @@ }; }; - pciesys: pciesys@1a100800 { - compatible = "mediatek,mt7622-pciesys", - "syscon"; + pciesys: clock-controller@1a100800 { + compatible = "mediatek,mt7622-pciesys"; reg = <0 0x1a100800 0 0x1000>; #clock-cells = <1>; #reset-cells = <1>; @@ -893,7 +888,13 @@ }; }; - ethsys: syscon@1b000000 { + hifsys: clock-controller@1af00000 { + compatible = "mediatek,mt7622-hifsys"; + reg = <0 0x1af00000 0 0x70>; + #clock-cells = <1>; + }; + + ethsys: clock-controller@1b000000 { compatible = "mediatek,mt7622-ethsys", "syscon"; reg = <0 0x1b000000 0 0x1000>; @@ -911,10 +912,28 @@ #dma-cells = <1>; }; - eth: ethernet@1b100000 { - compatible = "mediatek,mt7622-eth", - "mediatek,mt2701-eth", + pcie_mirror: pcie-mirror@10000400 { + compatible = "mediatek,mt7622-pcie-mirror", "syscon"; + reg = <0 0x10000400 0 0x10>; + }; + + wed0: wed@1020a000 { + compatible = "mediatek,mt7622-wed", + "syscon"; + reg = <0 0x1020a000 0 0x1000>; + interrupts = <GIC_SPI 214 IRQ_TYPE_LEVEL_LOW>; + }; + + wed1: wed@1020b000 { + compatible = "mediatek,mt7622-wed", + "syscon"; + reg = <0 0x1020b000 0 0x1000>; + interrupts = <GIC_SPI 215 IRQ_TYPE_LEVEL_LOW>; + }; + + eth: ethernet@1b100000 { + compatible = "mediatek,mt7622-eth"; reg = <0 0x1b100000 0 0x20000>; interrupts = <GIC_SPI 223 IRQ_TYPE_LEVEL_LOW>, <GIC_SPI 224 IRQ_TYPE_LEVEL_LOW>, @@ -937,6 +956,11 @@ power-domains = <&scpsys MT7622_POWER_DOMAIN_ETHSYS>; mediatek,ethsys = <ðsys>; mediatek,sgmiisys = <&sgmiisys>; + mediatek,cci-control = <&cci_control2>; + mediatek,wed = <&wed0>, <&wed1>; + mediatek,pcie-mirror = <&pcie_mirror>; + mediatek,hifsys = <&hifsys>; + dma-coherent; #address-cells = <1>; #size-cells = <0>; status = "disabled"; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 0bc5fefb7..d766f3b5c 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -139,6 +139,19 @@ reg = <0 0 0 0>; }; + etm { + compatible = "qcom,coresight-remote-etm"; + + out-ports { + port { + modem_etm_out_funnel_in2: endpoint { + remote-endpoint = + <&funnel_in2_in_modem_etm>; + }; + }; + }; + }; + psci { compatible = "arm,psci-1.0"; method = "smc"; @@ -1374,6 +1387,14 @@ clocks = <&rpmcc RPM_QDSS_CLK>, <&rpmcc RPM_QDSS_A_CLK>; clock-names = "apb_pclk", "atclk"; + in-ports { + port { + funnel_in2_in_modem_etm: endpoint { + remote-endpoint = + <&modem_etm_out_funnel_in2>; + }; + }; + }; out-ports { port { diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi index 7c8d69ca9..ca8e78487 100644 --- a/arch/arm64/boot/dts/qcom/msm8998.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi @@ -1577,9 +1577,11 @@ cpu = <&CPU4>; - port{ - etm4_out: endpoint { - remote-endpoint = <&apss_funnel_in4>; + out-ports { + port{ + etm4_out: endpoint { + remote-endpoint = <&apss_funnel_in4>; + }; }; }; }; @@ -1594,9 +1596,11 @@ cpu = <&CPU5>; - port{ - etm5_out: endpoint { - remote-endpoint = <&apss_funnel_in5>; + out-ports { + port{ + etm5_out: endpoint { + remote-endpoint = <&apss_funnel_in5>; + }; }; }; }; @@ -1611,9 +1615,11 @@ cpu = <&CPU6>; - port{ - etm6_out: endpoint { - remote-endpoint = <&apss_funnel_in6>; + out-ports { + port{ + etm6_out: endpoint { + remote-endpoint = <&apss_funnel_in6>; + }; }; }; }; @@ -1628,9 +1634,11 @@ cpu = <&CPU7>; - port{ - etm7_out: endpoint { - remote-endpoint = <&apss_funnel_in7>; + out-ports { + port{ + etm7_out: endpoint { + remote-endpoint = <&apss_funnel_in7>; + }; }; }; }; diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi index cb2c47f13..9ce8bfbf7 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi @@ -810,7 +810,8 @@ ap_spi_fp: &spi10 { vddrf-supply = <&pp1300_l2c>; vddch0-supply = <&pp3300_l10c>; max-speed = <3200000>; - clocks = <&rpmhcc RPMH_RF_CLK2>; + + qcom,local-bd-address-broken; }; }; diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi index eb07a882d..be40821df 100644 --- a/arch/arm64/boot/dts/qcom/sc7180.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi @@ -2688,10 +2688,10 @@ <&gcc GCC_USB30_PRIM_MASTER_CLK>; assigned-clock-rates = <19200000>, <150000000>; - interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 488 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 489 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 8 IRQ_TYPE_EDGE_BOTH>, + <&pdc 9 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index 5c696ebf5..e3c6b0586 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -3565,10 +3565,10 @@ <&gcc GCC_USB30_PRIM_MASTER_CLK>; assigned-clock-rates = <19200000>, <150000000>; - interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 488 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 489 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>, + <&pdc_intc 8 IRQ_TYPE_EDGE_BOTH>, + <&pdc_intc 9 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; @@ -3613,10 +3613,10 @@ <&gcc GCC_USB30_SEC_MASTER_CLK>; assigned-clock-rates = <19200000>, <150000000>; - interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 487 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 490 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 491 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 487 IRQ_TYPE_LEVEL_HIGH>, + <&pdc_intc 10 IRQ_TYPE_EDGE_BOTH>, + <&pdc_intc 11 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq"; diff --git a/arch/arm64/boot/dts/rockchip/px30.dtsi b/arch/arm64/boot/dts/rockchip/px30.dtsi index 0d6761074..f241e7c31 100644 --- a/arch/arm64/boot/dts/rockchip/px30.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30.dtsi @@ -577,6 +577,7 @@ clock-names = "spiclk", "apb_pclk"; dmas = <&dmac 12>, <&dmac 13>; dma-names = "tx", "rx"; + num-cs = <2>; pinctrl-names = "default"; pinctrl-0 = <&spi0_clk &spi0_csn &spi0_miso &spi0_mosi>; #address-cells = <1>; @@ -592,6 +593,7 @@ clock-names = "spiclk", "apb_pclk"; dmas = <&dmac 14>, <&dmac 15>; dma-names = "tx", "rx"; + num-cs = <2>; pinctrl-names = "default"; pinctrl-0 = <&spi1_clk &spi1_csn0 &spi1_csn1 &spi1_miso &spi1_mosi>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 72112fe05..10df6636a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -732,11 +732,20 @@ status = "disabled"; ports { - hdmi_in: port { + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; + hdmi_in_vop: endpoint { remote-endpoint = <&vop_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts index 4297c1db5..913ba25ea 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts @@ -784,7 +784,6 @@ }; &pcie0 { - bus-scan-delay-ms = <1000>; ep-gpios = <&gpio2 RK_PD4 GPIO_ACTIVE_HIGH>; num-lanes = <4>; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index 95bc7a5f6..0cf656824 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -430,16 +430,22 @@ gpio1830-supply = <&vcc_1v8>; }; -&pmu_io_domains { - status = "okay"; - pmu1830-supply = <&vcc_1v8>; -}; - -&pwm2 { - status = "okay"; +&pcie_clkreqn_cpm { + rockchip,pins = + <2 RK_PD2 RK_FUNC_GPIO &pcfg_pull_up>; }; &pinctrl { + pinctrl-names = "default"; + pinctrl-0 = <&q7_thermal_pin>; + + gpios { + q7_thermal_pin: q7-thermal-pin { + rockchip,pins = + <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; + i2c8 { i2c8_xfer_a: i2c8-xfer { rockchip,pins = @@ -470,6 +476,15 @@ }; }; +&pmu_io_domains { + status = "okay"; + pmu1830-supply = <&vcc_1v8>; +}; + +&pwm2 { + status = "okay"; +}; + &sdhci { /* * Signal integrity isn't great at 200MHz but 100MHz has proven stable diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index 3180f576e..e2515218f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1769,6 +1769,7 @@ hdmi: hdmi@ff940000 { compatible = "rockchip,rk3399-dw-hdmi"; reg = <0x0 0xff940000 0x0 0x20000>; + reg-io-width = <4>; interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH 0>; clocks = <&cru PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_SFR>, @@ -1777,13 +1778,16 @@ <&cru PLL_VPLL>; clock-names = "iahb", "isfr", "cec", "grf", "vpll"; power-domains = <&power RK3399_PD_HDCP>; - reg-io-width = <4>; rockchip,grf = <&grf>; #sound-dai-cells = <0>; status = "disabled"; ports { - hdmi_in: port { + #address-cells = <1>; + #size-cells = <0>; + + hdmi_in: port@0 { + reg = <0>; #address-cells = <1>; #size-cells = <0>; @@ -1796,6 +1800,10 @@ remote-endpoint = <&vopl_out_hdmi>; }; }; + + hdmi_out: port@1 { + reg = <1>; + }; }; }; diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index a94acea77..020a45582 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -431,7 +431,9 @@ SYM_CODE_END(__swpan_exit_el0) .macro irq_stack_entry mov x19, sp // preserve the original sp - scs_save tsk // preserve the original shadow stack +#ifdef CONFIG_SHADOW_CALL_STACK + mov x24, scs_sp // preserve the original shadow stack +#endif /* * Compare sp with the base of the task stack. @@ -465,7 +467,9 @@ SYM_CODE_END(__swpan_exit_el0) */ .macro irq_stack_exit mov sp, x19 - scs_load_current +#ifdef CONFIG_SHADOW_CALL_STACK + mov scs_sp, x24 +#endif .endm /* GPRs used by entry code */ diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index cdb3d4549..8e428f8dd 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -171,7 +171,11 @@ armv8pmu_events_sysfs_show(struct device *dev, }).attr.attr) static struct attribute *armv8_pmuv3_event_attrs[] = { - ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR), + /* + * Don't expose the sw_incr event in /sys. It's not usable as writes to + * PMSWINC_EL0 will trap as PMUSERENR.{SW,EN}=={0,0} and event rotation + * means we don't have a fixed event<->counter relationship regardless. + */ ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL), ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL), ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL), diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 62f261b8e..93c0365cd 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -462,6 +462,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) } irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]); + if (!irq) + continue; + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = pendmask & (1U << bit_nr); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); @@ -1374,6 +1377,8 @@ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its, for (i = 0; i < irq_count; i++) { irq = vgic_get_irq(kvm, NULL, intids[i]); + if (!irq) + continue; update_affinity(irq, vcpu2); diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S index 57465bff1..df7f349c8 100644 --- a/arch/hexagon/kernel/vmlinux.lds.S +++ b/arch/hexagon/kernel/vmlinux.lds.S @@ -64,6 +64,7 @@ SECTIONS STABS_DEBUG DWARF_DEBUG ELF_DETAILS + .hexagon.attributes 0 : { *(.hexagon.attributes) } DISCARDS } diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h index 5f80c28f5..6c837a256 100644 --- a/arch/mips/include/asm/checksum.h +++ b/arch/mips/include/asm/checksum.h @@ -242,7 +242,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " .set pop" : "=&r" (sum), "=&r" (tmp) : "r" (saddr), "r" (daddr), - "0" (htonl(len)), "r" (htonl(proto)), "r" (sum)); + "0" (htonl(len)), "r" (htonl(proto)), "r" (sum) + : "memory"); return csum_fold(sum); } diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index 1e76774b3..2849a9b65 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -60,6 +60,7 @@ static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { regs->cp0_epc = val; + regs->cp0_cause &= ~CAUSEF_BD; } /* Query offset/name of register from its name/offset */ diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c index 7b045d2a0..bbc6f07d8 100644 --- a/arch/mips/kernel/elf.c +++ b/arch/mips/kernel/elf.c @@ -11,6 +11,7 @@ #include <asm/cpu-features.h> #include <asm/cpu-info.h> +#include <asm/fpu.h> #ifdef CONFIG_MIPS_FP_SUPPORT @@ -309,6 +310,11 @@ void mips_set_personality_nan(struct arch_elf_state *state) struct cpuinfo_mips *c = &boot_cpu_data; struct task_struct *t = current; + /* Do this early so t->thread.fpu.fcr31 won't be clobbered in case + * we are preempted before the lose_fpu(0) in start_thread. + */ + lose_fpu(0); + t->thread.fpu.fcr31 = c->fpu_csr31; switch (state->nan_2008) { case 0: diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 07e84a774..32e7b869a 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -421,7 +421,12 @@ void __init paging_init(void) (highend_pfn - max_low_pfn) << (PAGE_SHIFT - 10)); max_zone_pfns[ZONE_HIGHMEM] = max_low_pfn; } + + max_mapnr = highend_pfn ? highend_pfn : max_low_pfn; +#else + max_mapnr = max_low_pfn; #endif + high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); free_area_init(max_zone_pfns); } @@ -457,16 +462,6 @@ void __init mem_init(void) */ BUILD_BUG_ON(IS_ENABLED(CONFIG_32BIT) && (_PFN_SHIFT > PAGE_SHIFT)); -#ifdef CONFIG_HIGHMEM -#ifdef CONFIG_DISCONTIGMEM -#error "CONFIG_HIGHMEM and CONFIG_DISCONTIGMEM dont work together yet" -#endif - max_mapnr = highend_pfn ? highend_pfn : max_low_pfn; -#else - max_mapnr = max_low_pfn; -#endif - high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); - maar_init(); memblock_free_all(); setup_zero_pages(); /* Setup zeroed pages. */ diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index a39250cb7..d3f23ed57 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -83,26 +83,28 @@ * version takes two arguments: a src and destination register. * However, the source and destination registers can not be * the same register. + * + * We use add,l to avoid clobbering the C/B bits in the PSW. */ .macro tophys grvirt, grphys - ldil L%(__PAGE_OFFSET), \grphys - sub \grvirt, \grphys, \grphys + ldil L%(-__PAGE_OFFSET), \grphys + addl \grvirt, \grphys, \grphys .endm - + .macro tovirt grphys, grvirt ldil L%(__PAGE_OFFSET), \grvirt - add \grphys, \grvirt, \grvirt + addl \grphys, \grvirt, \grvirt .endm .macro tophys_r1 gr - ldil L%(__PAGE_OFFSET), %r1 - sub \gr, %r1, \gr + ldil L%(-__PAGE_OFFSET), %r1 + addl \gr, %r1, \gr .endm - + .macro tovirt_r1 gr ldil L%(__PAGE_OFFSET), %r1 - add \gr, %r1, \gr + addl \gr, %r1, \gr .endm .macro delay value diff --git a/arch/parisc/include/asm/checksum.h b/arch/parisc/include/asm/checksum.h index 3c43baca7..2aceebcd6 100644 --- a/arch/parisc/include/asm/checksum.h +++ b/arch/parisc/include/asm/checksum.h @@ -40,7 +40,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) " addc %0, %5, %0\n" " addc %0, %3, %0\n" "1: ldws,ma 4(%1), %3\n" -" addib,< 0, %2, 1b\n" +" addib,> -1, %2, 1b\n" " addc %0, %3, %0\n" "\n" " extru %0, 31, 16, %4\n" @@ -126,6 +126,7 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, ** Try to keep 4 registers with "live" values ahead of the ALU. */ +" depdi 0, 31, 32, %0\n"/* clear upper half of incoming checksum */ " ldd,ma 8(%1), %4\n" /* get 1st saddr word */ " ldd,ma 8(%2), %5\n" /* get 1st daddr word */ " add %4, %0, %0\n" @@ -137,8 +138,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " add,dc %3, %0, %0\n" /* fold in proto+len | carry bit */ " extrd,u %0, 31, 32, %4\n"/* copy upper half down */ " depdi 0, 31, 32, %0\n"/* clear upper half */ -" add %4, %0, %0\n" /* fold into 32-bits */ -" addc 0, %0, %0\n" /* add carry */ +" add,dc %4, %0, %0\n" /* fold into 32-bits, plus carry */ +" addc 0, %0, %0\n" /* add final carry */ #else @@ -163,7 +164,8 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, " ldw,ma 4(%2), %7\n" /* 4th daddr */ " addc %6, %0, %0\n" " addc %7, %0, %0\n" -" addc %3, %0, %0\n" /* fold in proto+len, catch carry */ +" addc %3, %0, %0\n" /* fold in proto+len */ +" addc 0, %0, %0\n" /* add carry */ #endif : "=r" (sum), "=r" (saddr), "=r" (daddr), "=r" (len), diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 7ed28ddca..25050b0ab 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -123,10 +123,10 @@ static unsigned long f_extend(unsigned long address) #ifdef CONFIG_64BIT if(unlikely(parisc_narrow_firmware)) { if((address & 0xff000000) == 0xf0000000) - return 0xf0f0f0f000000000UL | (u32)address; + return (0xfffffff0UL << 32) | (u32)address; if((address & 0xf0000000) == 0xf0000000) - return 0xffffffff00000000UL | (u32)address; + return (0xffffffffUL << 32) | (u32)address; } #endif return address; diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index 63e3ecb9d..8538425cc 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -81,7 +81,7 @@ void notrace __hot ftrace_function_trampoline(unsigned long parent, #endif } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_FUNCTION_GRAPH_TRACER) int ftrace_enable_ftrace_graph_caller(void) { return 0; diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 255a1837e..3a5a27318 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -390,5 +390,9 @@ extern void *abatron_pteptrs[2]; #include <asm/nohash/mmu.h> #endif +#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP) +#define __HAVE_ARCH_RESERVED_KERNEL_PAGES +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MMU_H_ */ diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 6cda76b57..bd1a8d725 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -42,9 +42,6 @@ u64 memory_hotplug_max(void); #else #define memory_hotplug_max() memblock_end_of_DRAM() #endif /* CONFIG_NEED_MULTIPLE_NODES */ -#ifdef CONFIG_FA_DUMP -#define __HAVE_ARCH_RESERVED_KERNEL_PAGES -#endif #ifdef CONFIG_MEMORY_HOTPLUG extern int create_section_mapping(unsigned long start, unsigned long end, diff --git a/arch/powerpc/include/asm/reg_fsl_emb.h b/arch/powerpc/include/asm/reg_fsl_emb.h index a21f529c4..8359c06d9 100644 --- a/arch/powerpc/include/asm/reg_fsl_emb.h +++ b/arch/powerpc/include/asm/reg_fsl_emb.h @@ -12,9 +12,16 @@ #ifndef __ASSEMBLY__ /* Performance Monitor Registers */ #define mfpmr(rn) ({unsigned int rval; \ - asm volatile("mfpmr %0," __stringify(rn) \ + asm volatile(".machine push; " \ + ".machine e300; " \ + "mfpmr %0," __stringify(rn) ";" \ + ".machine pop; " \ : "=r" (rval)); rval;}) -#define mtpmr(rn, v) asm volatile("mtpmr " __stringify(rn) ",%0" : : "r" (v)) +#define mtpmr(rn, v) asm volatile(".machine push; " \ + ".machine e300; " \ + "mtpmr " __stringify(rn) ",%0; " \ + ".machine pop; " \ + : : "r" (v)) #endif /* __ASSEMBLY__ */ /* Freescale Book E Performance Monitor APU Registers */ diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 6e5bed50c..ca3374c6f 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -504,6 +504,11 @@ static bool is_larx_stcx_instr(int type) return type == LARX || type == STCX; } +static bool is_octword_vsx_instr(int type, int size) +{ + return ((type == LOAD_VSX || type == STORE_VSX) && size == 32); +} + /* * We've failed in reliably handling the hw-breakpoint. Unregister * it and throw a warning message to let the user know about it. @@ -554,6 +559,63 @@ static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp, return true; } +static void handle_p10dd1_spurious_exception(struct arch_hw_breakpoint **info, + int *hit, unsigned long ea) +{ + int i; + unsigned long hw_end_addr; + + /* + * Handle spurious exception only when any bp_per_reg is set. + * Otherwise this might be created by xmon and not actually a + * spurious exception. + */ + for (i = 0; i < nr_wp_slots(); i++) { + if (!info[i]) + continue; + + hw_end_addr = ALIGN(info[i]->address + info[i]->len, HW_BREAKPOINT_SIZE); + + /* + * Ending address of DAWR range is less than starting + * address of op. + */ + if ((hw_end_addr - 1) >= ea) + continue; + + /* + * Those addresses need to be in the same or in two + * consecutive 512B blocks; + */ + if (((hw_end_addr - 1) >> 10) != (ea >> 10)) + continue; + + /* + * 'op address + 64B' generates an address that has a + * carry into bit 52 (crosses 2K boundary). + */ + if ((ea & 0x800) == ((ea + 64) & 0x800)) + continue; + + break; + } + + if (i == nr_wp_slots()) + return; + + for (i = 0; i < nr_wp_slots(); i++) { + if (info[i]) { + hit[i] = 1; + info[i]->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; + } + } +} + +/* + * Handle a DABR or DAWR exception. + * + * Called in atomic context. + */ int hw_breakpoint_handler(struct die_args *args) { bool err = false; @@ -612,8 +674,14 @@ int hw_breakpoint_handler(struct die_args *args) goto reset; if (!nr_hit) { - rc = NOTIFY_DONE; - goto out; + /* Workaround for Power10 DD1 */ + if (!IS_ENABLED(CONFIG_PPC_8xx) && mfspr(SPRN_PVR) == 0x800100 && + is_octword_vsx_instr(type, size)) { + handle_p10dd1_spurious_exception(info, hit, ea); + } else { + rc = NOTIFY_DONE; + goto out; + } } /* @@ -674,6 +742,8 @@ NOKPROBE_SYMBOL(hw_breakpoint_handler); /* * Handle single-step exceptions following a DABR hit. + * + * Called in atomic context. */ static int single_step_dabr_instruction(struct die_args *args) { @@ -731,6 +801,8 @@ NOKPROBE_SYMBOL(single_step_dabr_instruction); /* * Handle debug exception notifications. + * + * Called in atomic context. */ int hw_breakpoint_exceptions_notify( struct notifier_block *unused, unsigned long val, void *data) diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 5e5a2448a..b0e87dce2 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1432,10 +1432,12 @@ static int emulate_instruction(struct pt_regs *regs) return -EINVAL; } +#ifdef CONFIG_GENERIC_BUG int is_valid_bugaddr(unsigned long addr) { return is_kernel_addr(addr); } +#endif #ifdef CONFIG_MATH_EMULATION static int emulate_math(struct pt_regs *regs) diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 3dd58b4ee..5f6b3f800 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -250,7 +250,7 @@ int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot) p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) return -ENOMEM; - p->pfns = vzalloc(array_size(slot->npages, sizeof(*p->pfns))); + p->pfns = vcalloc(slot->npages, sizeof(*p->pfns)); if (!p->pfns) { kfree(p); return -ENOMEM; diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 321cab5c3..bd5012aa9 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -67,6 +67,6 @@ obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o obj-$(CONFIG_ALTIVEC) += xor_vmx.o xor_vmx_glue.o -CFLAGS_xor_vmx.o += -maltivec $(call cc-option,-mabi=altivec) +CFLAGS_xor_vmx.o += -mhard-float -maltivec $(call cc-option,-mabi=altivec) obj-$(CONFIG_PPC64) += $(obj64-y) diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 2d1965532..ca4733fbd 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -512,6 +512,8 @@ static int do_fp_load(struct instruction_op *op, unsigned long ea, } u; nb = GETSIZE(op->type); + if (nb > sizeof(u)) + return -EINVAL; if (!address_ok(regs, ea, nb)) return -EFAULT; rn = op->reg; @@ -562,6 +564,8 @@ static int do_fp_store(struct instruction_op *op, unsigned long ea, } u; nb = GETSIZE(op->type); + if (nb > sizeof(u)) + return -EINVAL; if (!address_ok(regs, ea, nb)) return -EFAULT; rn = op->reg; @@ -606,6 +610,9 @@ static nokprobe_inline int do_vec_load(int rn, unsigned long ea, u8 b[sizeof(__vector128)]; } u = {}; + if (size > sizeof(u)) + return -EINVAL; + if (!address_ok(regs, ea & ~0xfUL, 16)) return -EFAULT; /* align to multiple of size */ @@ -633,6 +640,9 @@ static nokprobe_inline int do_vec_store(int rn, unsigned long ea, u8 b[sizeof(__vector128)]; } u; + if (size > sizeof(u)) + return -EINVAL; + if (!address_ok(regs, ea & ~0xfUL, 16)) return -EFAULT; /* align to multiple of size */ diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index e18ae50a2..a86d932a7 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -446,6 +446,7 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, set_pte_at(vma->vm_mm, addr, ptep, pte); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * For hash translation mode, we use the deposited table to store hash slot * information and they are stored at PTRS_PER_PMD offset from related pmd @@ -467,6 +468,7 @@ int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, return true; } +#endif /* * Does the CPU support tlbie? diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c index 8e0d792ac..52a20c97e 100644 --- a/arch/powerpc/mm/init-common.c +++ b/arch/powerpc/mm/init-common.c @@ -111,7 +111,7 @@ void pgtable_cache_add(unsigned int shift) * as to leave enough 0 bits in the address to contain it. */ unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1, HUGEPD_SHIFT_MASK + 1); - struct kmem_cache *new; + struct kmem_cache *new = NULL; /* It would be nice if this was a BUILD_BUG_ON(), but at the * moment, gcc doesn't seem to recognize is_power_of_2 as a @@ -124,7 +124,8 @@ void pgtable_cache_add(unsigned int shift) align = max_t(unsigned long, align, minalign); name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift); - new = kmem_cache_create(name, table_size, align, 0, ctor(shift)); + if (name) + new = kmem_cache_create(name, table_size, align, 0, ctor(shift)); if (!new) panic("Could not allocate pgtable cache for order %d", shift); diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index f3e4d069e..643fc5258 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -64,6 +64,7 @@ int __init __weak kasan_init_region(void *start, size_t size) if (ret) return ret; + k_start = k_start & PAGE_MASK; block = memblock_alloc(k_end - k_start, PAGE_SIZE); if (!block) return -ENOMEM; diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 28b770bbc..2a054de80 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -164,6 +164,20 @@ static unsigned long single_gpci_request(u32 req, u32 starting_index, ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, virt_to_phys(arg), HGPCI_REQ_BUFFER_SIZE); + + /* + * ret value as 'H_PARAMETER' with detail_rc as 'GEN_BUF_TOO_SMALL', + * specifies that the current buffer size cannot accommodate + * all the information and a partial buffer returned. + * Since in this function we are only accessing data for a given starting index, + * we don't need to accommodate whole data and can get required count by + * accessing first entry data. + * Hence hcall fails only incase the ret value is other than H_SUCCESS or + * H_PARAMETER with detail_rc value as GEN_BUF_TOO_SMALL(0x1B). + */ + if (ret == H_PARAMETER && be32_to_cpu(arg->params.detail_rc) == 0x1B) + ret = 0; + if (ret) { pr_devel("hcall failed: 0x%lx\n", ret); goto out; @@ -228,6 +242,7 @@ static int h_gpci_event_init(struct perf_event *event) { u64 count; u8 length; + unsigned long ret; /* Not our event */ if (event->attr.type != event->pmu->type) @@ -258,13 +273,23 @@ static int h_gpci_event_init(struct perf_event *event) } /* check if the request works... */ - if (single_gpci_request(event_get_request(event), + ret = single_gpci_request(event_get_request(event), event_get_starting_index(event), event_get_secondary_index(event), event_get_counter_info_version(event), event_get_offset(event), length, - &count)) { + &count); + + /* + * ret value as H_AUTHORITY implies that partition is not permitted to retrieve + * performance information, and required to set + * "Enable Performance Information Collection" option. + */ + if (ret == H_AUTHORITY) + return -EPERM; + + if (ret) { pr_devel("gpci hcall failed\n"); return -EINVAL; } diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c index f514d5d28..3f3821eb4 100644 --- a/arch/powerpc/platforms/embedded6xx/linkstation.c +++ b/arch/powerpc/platforms/embedded6xx/linkstation.c @@ -97,9 +97,6 @@ static void __init linkstation_init_IRQ(void) mpic_init(mpic); } -extern void avr_uart_configure(void); -extern void avr_uart_send(const char); - static void __noreturn linkstation_restart(char *cmd) { local_irq_disable(); diff --git a/arch/powerpc/platforms/embedded6xx/mpc10x.h b/arch/powerpc/platforms/embedded6xx/mpc10x.h index 5ad12023e..ebc258fa4 100644 --- a/arch/powerpc/platforms/embedded6xx/mpc10x.h +++ b/arch/powerpc/platforms/embedded6xx/mpc10x.h @@ -156,4 +156,7 @@ int mpc10x_disable_store_gathering(struct pci_controller *hose); /* For MPC107 boards that use the built-in openpic */ void mpc10x_set_openpic(void); +void avr_uart_configure(void); +void avr_uart_send(const char c); + #endif /* __PPC_KERNEL_MPC10X_H */ diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index b28fabfc9..70271db83 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -445,6 +445,14 @@ config EFI allow the kernel to be booted as an EFI application. This is only useful on systems that have UEFI firmware. +config CC_HAVE_STACKPROTECTOR_TLS + def_bool $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=tp -mstack-protector-guard-offset=0) + +config STACKPROTECTOR_PER_TASK + def_bool y + depends on !GCC_PLUGIN_RANDSTRUCT + depends on STACKPROTECTOR && CC_HAVE_STACKPROTECTOR_TLS + endmenu config BUILTIN_DTB diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index daa679440..8572d23fb 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -88,6 +88,16 @@ KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax) # architectures. It's faster to have GCC emit only aligned accesses. KBUILD_CFLAGS += $(call cc-option,-mstrict-align) +ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y) +prepare: stack_protector_prepare +stack_protector_prepare: prepare0 + $(eval KBUILD_CFLAGS += -mstack-protector-guard=tls \ + -mstack-protector-guard-reg=tp \ + -mstack-protector-guard-offset=$(shell \ + awk '{if ($$2 == "TSK_STACK_CANARY") print $$3;}' \ + include/generated/asm-offsets.h)) +endif + # arch specific predefines for sparse CHECKFLAGS += -D__riscv -D__riscv_xlen=$(BITS) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index b16304fdf..982745572 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -44,7 +44,7 @@ * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. */ -#define vmemmap ((struct page *)VMEMMAP_START) +#define vmemmap ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT)) #define PCI_IO_SIZE SZ_16M #define PCI_IO_END VMEMMAP_START @@ -456,8 +456,8 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, #define PAGE_SHARED __pgprot(0) #define PAGE_KERNEL __pgprot(0) #define swapper_pg_dir NULL -#define TASK_SIZE 0xffffffffUL -#define VMALLOC_START 0 +#define TASK_SIZE _AC(-1, UL) +#define VMALLOC_START _AC(0, UL) #define VMALLOC_END TASK_SIZE static inline void __kernel_map_pages(struct page *page, int numpages, int enable) {} diff --git a/arch/riscv/include/asm/stackprotector.h b/arch/riscv/include/asm/stackprotector.h index 5962f8891..09093af46 100644 --- a/arch/riscv/include/asm/stackprotector.h +++ b/arch/riscv/include/asm/stackprotector.h @@ -24,6 +24,7 @@ static __always_inline void boot_init_stack_canary(void) canary &= CANARY_MASK; current->stack_canary = canary; - __stack_chk_guard = current->stack_canary; + if (!IS_ENABLED(CONFIG_STACKPROTECTOR_PER_TASK)) + __stack_chk_guard = current->stack_canary; } #endif /* _ASM_RISCV_STACKPROTECTOR_H */ diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index 66af6abfe..c351231b7 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -468,7 +468,7 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n) #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ - long __kr_err; \ + long __kr_err = 0; \ \ __get_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \ if (unlikely(__kr_err)) \ @@ -477,7 +477,7 @@ do { \ #define __put_kernel_nofault(dst, src, type, err_label) \ do { \ - long __kr_err; \ + long __kr_err = 0; \ \ __put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \ if (unlikely(__kr_err)) \ diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index db203442c..877ff65b4 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -66,6 +66,9 @@ void asm_offsets(void) OFFSET(TASK_THREAD_F30, task_struct, thread.fstate.f[30]); OFFSET(TASK_THREAD_F31, task_struct, thread.fstate.f[31]); OFFSET(TASK_THREAD_FCSR, task_struct, thread.fstate.fcsr); +#ifdef CONFIG_STACKPROTECTOR + OFFSET(TSK_STACK_CANARY, task_struct, stack_canary); +#endif DEFINE(PT_SIZE, sizeof(struct pt_regs)); OFFSET(PT_EPC, pt_regs, epc); diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 7868050ff..9dac6bec3 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -22,9 +22,7 @@ #include <asm/switch_to.h> #include <asm/thread_info.h> -register unsigned long gp_in_global __asm__("gp"); - -#ifdef CONFIG_STACKPROTECTOR +#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) #include <linux/stackprotector.h> unsigned long __stack_chk_guard __read_mostly; EXPORT_SYMBOL(__stack_chk_guard); @@ -117,7 +115,6 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* Kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); - childregs->gp = gp_in_global; /* Supervisor/Machine, irqs on: */ childregs->status = SR_PP | SR_PIE; diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index 812730e6b..8ef4e5034 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -600,7 +600,9 @@ static int ctr_aes_crypt(struct skcipher_request *req) * final block may be < AES_BLOCK_SIZE, copy only nbytes */ if (nbytes) { - cpacf_kmctr(sctx->fc, sctx->key, buf, walk.src.virt.addr, + memset(buf, 0, AES_BLOCK_SIZE); + memcpy(buf, walk.src.virt.addr, nbytes); + cpacf_kmctr(sctx->fc, sctx->key, buf, buf, AES_BLOCK_SIZE, walk.iv); memcpy(walk.dst.virt.addr, buf, nbytes); crypto_inc(walk.iv, AES_BLOCK_SIZE); diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index a6727ad58..6a0a22621 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -676,9 +676,11 @@ static int ctr_paes_crypt(struct skcipher_request *req) * final block may be < AES_BLOCK_SIZE, copy only nbytes */ if (nbytes) { + memset(buf, 0, AES_BLOCK_SIZE); + memcpy(buf, walk.src.virt.addr, nbytes); while (1) { if (cpacf_kmctr(ctx->fc, ¶m, buf, - walk.src.virt.addr, AES_BLOCK_SIZE, + buf, AES_BLOCK_SIZE, walk.iv) == AES_BLOCK_SIZE) break; if (__paes_convert_key(ctx)) diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 88ecbcf09..127a8d295 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -1298,6 +1298,7 @@ ENDPROC(stack_overflow) #endif .section .rodata, "a" + .balign 8 #define SYSCALL(esame,emu) .quad __s390x_ ## esame .globl sys_call_table sys_call_table: diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 3009bb527..f381caddd 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -411,6 +411,7 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) /* * floating point control reg. is in the thread structure */ + save_fpu_regs(); if ((unsigned int) data != 0 || test_fp_ctl(data >> (BITS_PER_LONG - 32))) return -EINVAL; @@ -771,6 +772,7 @@ static int __poke_user_compat(struct task_struct *child, /* * floating point control reg. is in the thread structure */ + save_fpu_regs(); if (test_fp_ctl(tmp)) return -EINVAL; child->thread.fpu.fpc = data; @@ -1010,9 +1012,7 @@ static int s390_fpregs_set(struct task_struct *target, int rc = 0; freg_t fprs[__NUM_FPRS]; - if (target == current) - save_fpu_regs(); - + save_fpu_regs(); if (MACHINE_HAS_VX) convert_vx_to_fp(fprs, target->thread.fpu.vxrs); else diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 579ec3a8c..bd65ff88c 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -214,13 +214,13 @@ void vtime_flush(struct task_struct *tsk) virt_timer_expire(); steal = S390_lowcore.steal_timer; - avg_steal = S390_lowcore.avg_steal_timer / 2; + avg_steal = S390_lowcore.avg_steal_timer; if ((s64) steal > 0) { S390_lowcore.steal_timer = 0; account_steal_time(cputime_to_nsecs(steal)); avg_steal += steal; } - S390_lowcore.avg_steal_timer = avg_steal; + S390_lowcore.avg_steal_timer = avg_steal / 2; } /* diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 7a326d030..f6c27b447 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3649,10 +3649,6 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) vcpu_load(vcpu); - if (test_fp_ctl(fpu->fpc)) { - ret = -EINVAL; - goto out; - } vcpu->run->s.regs.fpc = fpu->fpc; if (MACHINE_HAS_VX) convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs, @@ -3660,7 +3656,6 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) else memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs)); -out: vcpu_put(vcpu); return ret; } diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 74799439b..beecc36c3 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -225,7 +225,7 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res, /* combine single writes by using store-block insn */ void __iowrite64_copy(void __iomem *to, const void *from, size_t count) { - zpci_memcpy_toio(to, from, count); + zpci_memcpy_toio(to, from, count * 8); } static void __iomem *__ioremap(phys_addr_t addr, size_t size, pgprot_t prot) diff --git a/arch/sparc/kernel/leon_pci_grpci1.c b/arch/sparc/kernel/leon_pci_grpci1.c index e6935d0ac..c32590bdd 100644 --- a/arch/sparc/kernel/leon_pci_grpci1.c +++ b/arch/sparc/kernel/leon_pci_grpci1.c @@ -696,7 +696,7 @@ err1: return err; } -static const struct of_device_id grpci1_of_match[] __initconst = { +static const struct of_device_id grpci1_of_match[] = { { .name = "GAISLER_PCIFBRG", }, diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c index ca22f93d9..dd06abc61 100644 --- a/arch/sparc/kernel/leon_pci_grpci2.c +++ b/arch/sparc/kernel/leon_pci_grpci2.c @@ -887,7 +887,7 @@ err1: return err; } -static const struct of_device_id grpci2_of_match[] __initconst = { +static const struct of_device_id grpci2_of_match[] = { { .name = "GAISLER_GRPCI2", }, diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 060fff95a..fbf25e926 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -274,7 +274,7 @@ static int __init setup_nmi_watchdog(char *str) if (!strncmp(str, "panic", 5)) panic_on_timeout = 1; - return 0; + return 1; } __setup("nmi_watchdog=", setup_nmi_watchdog); diff --git a/arch/sparc/vdso/vma.c b/arch/sparc/vdso/vma.c index cc19e09b0..b073153c7 100644 --- a/arch/sparc/vdso/vma.c +++ b/arch/sparc/vdso/vma.c @@ -449,9 +449,8 @@ static __init int vdso_setup(char *s) unsigned long val; err = kstrtoul(s, 10, &val); - if (err) - return err; - vdso_enabled = val; - return 0; + if (!err) + vdso_enabled = val; + return 1; } __setup("vdso=", vdso_setup); diff --git a/arch/um/Kconfig b/arch/um/Kconfig index eb1c6880b..20264b47d 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -92,6 +92,19 @@ config LD_SCRIPT_DYN depends on !LD_SCRIPT_STATIC select MODULE_REL_CRCS if MODVERSIONS +config LD_SCRIPT_DYN_RPATH + bool "set rpath in the binary" if EXPERT + default y + depends on LD_SCRIPT_DYN + help + Add /lib (and /lib64 for 64-bit) to the linux binary's rpath + explicitly. + + You may need to turn this off if compiling for nix systems + that have their libraries in random /nix directories and + might otherwise unexpected use libraries from /lib or /lib64 + instead of the desired ones. + config HOSTFS tristate "Host filesystem" help diff --git a/arch/um/Makefile b/arch/um/Makefile index 56e5320da..4211e23a2 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -118,7 +118,8 @@ archprepare: $(Q)$(MAKE) $(build)=$(HOST_DIR)/um include/generated/user_constants.h LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static -LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib $(call cc-option, -no-pie) +LINK-$(CONFIG_LD_SCRIPT_DYN) += $(call cc-option, -no-pie) +LINK-$(CONFIG_LD_SCRIPT_DYN_RPATH) += -Wl,-rpath,/lib CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \ -fno-stack-protector $(call cc-option, -fno-stack-protector-all) diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 1802cf4ef..ee5533325 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -204,7 +204,7 @@ static int uml_net_close(struct net_device *dev) return 0; } -static int uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct uml_net_private *lp = netdev_priv(dev); unsigned long flags; diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h index 9c08e728a..83171f9e0 100644 --- a/arch/um/include/shared/kern_util.h +++ b/arch/um/include/shared/kern_util.h @@ -51,7 +51,7 @@ extern void do_uml_exitcalls(void); * Are we disallowed to sleep? Used to choose between GFP_KERNEL and * GFP_ATOMIC. */ -extern int __cant_sleep(void); +extern int __uml_cant_sleep(void); extern int get_current_pid(void); extern int copy_from_user_proc(void *to, void *from, int size); extern int cpu(void); diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index e6c9b11b2..76faaf108 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -221,7 +221,7 @@ void arch_cpu_idle(void) raw_local_irq_enable(); } -int __cant_sleep(void) { +int __uml_cant_sleep(void) { return in_atomic() || irqs_disabled() || in_interrupt(); /* Is in_interrupt() really needed? */ } diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c index 9fa6e4187..57a275550 100644 --- a/arch/um/os-Linux/helper.c +++ b/arch/um/os-Linux/helper.c @@ -45,7 +45,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv) unsigned long stack, sp; int pid, fds[2], ret, n; - stack = alloc_stack(0, __cant_sleep()); + stack = alloc_stack(0, __uml_cant_sleep()); if (stack == 0) return -ENOMEM; @@ -69,7 +69,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv) data.pre_data = pre_data; data.argv = argv; data.fd = fds[1]; - data.buf = __cant_sleep() ? uml_kmalloc(PATH_MAX, UM_GFP_ATOMIC) : + data.buf = __uml_cant_sleep() ? uml_kmalloc(PATH_MAX, UM_GFP_ATOMIC) : uml_kmalloc(PATH_MAX, UM_GFP_KERNEL); pid = clone(helper_child, (void *) sp, CLONE_VM, &data); if (pid < 0) { @@ -116,7 +116,7 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags, unsigned long stack, sp; int pid, status, err; - stack = alloc_stack(0, __cant_sleep()); + stack = alloc_stack(0, __uml_cant_sleep()); if (stack == 0) return -ENOMEM; diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c index 07327425d..56d9589e1 100644 --- a/arch/um/os-Linux/util.c +++ b/arch/um/os-Linux/util.c @@ -166,23 +166,38 @@ __uml_setup("quiet", quiet_cmd_param, "quiet\n" " Turns off information messages during boot.\n\n"); +/* + * The os_info/os_warn functions will be called by helper threads. These + * have a very limited stack size and using the libc formatting functions + * may overflow the stack. + * So pull in the kernel vscnprintf and use that instead with a fixed + * on-stack buffer. + */ +int vscnprintf(char *buf, size_t size, const char *fmt, va_list args); + void os_info(const char *fmt, ...) { + char buf[256]; va_list list; + int len; if (quiet_info) return; va_start(list, fmt); - vfprintf(stderr, fmt, list); + len = vscnprintf(buf, sizeof(buf), fmt, list); + fwrite(buf, len, 1, stderr); va_end(list); } void os_warn(const char *fmt, ...) { + char buf[256]; va_list list; + int len; va_start(list, fmt); - vfprintf(stderr, fmt, list); + len = vscnprintf(buf, sizeof(buf), fmt, list); + fwrite(buf, len, 1, stderr); va_end(list); } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6dc670e36..0c802ade8 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -57,6 +57,7 @@ config X86 select ACPI_LEGACY_TABLES_LOOKUP if ACPI select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI select ARCH_32BIT_OFF_T if X86_32 + select ARCH_CONFIGURES_CPU_MITIGATIONS select ARCH_CLOCKSOURCE_INIT select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_CPU_FINALIZE_INIT @@ -352,10 +353,6 @@ config X86_64_SMP def_bool y depends on X86_64 && SMP -config X86_32_LAZY_GS - def_bool y - depends on X86_32 && !STACKPROTECTOR - config ARCH_SUPPORTS_UPROBES def_bool y @@ -378,7 +375,8 @@ config CC_HAS_SANE_STACKPROTECTOR default $(success,$(srctree)/scripts/gcc-x86_32-has-stack-protector.sh $(CC)) help We have to make sure stack protector is unconditionally disabled if - the compiler produces broken code. + the compiler produces broken code or if it does not let us control + the segment on 32-bit kernels. menu "Processor type and features" @@ -2411,17 +2409,17 @@ config CC_HAS_SLS config CC_HAS_RETURN_THUNK def_bool $(cc-option,-mfunction-return=thunk-extern) -menuconfig SPECULATION_MITIGATIONS - bool "Mitigations for speculative execution vulnerabilities" +menuconfig CPU_MITIGATIONS + bool "Mitigations for CPU vulnerabilities" default y help - Say Y here to enable options which enable mitigations for - speculative execution hardware vulnerabilities. + Say Y here to enable options which enable mitigations for hardware + vulnerabilities (usually related to speculative execution). If you say N, all mitigations will be disabled. You really should know what you are doing to say so. -if SPECULATION_MITIGATIONS +if CPU_MITIGATIONS config PAGE_TABLE_ISOLATION bool "Remove the kernel mapping in user mode" @@ -2511,6 +2509,17 @@ config GDS_FORCE_MITIGATION If in doubt, say N. +config MITIGATION_RFDS + bool "RFDS Mitigation" + depends on CPU_SUP_INTEL + default y + help + Enable mitigation for Register File Data Sampling (RFDS) by default. + RFDS is a hardware vulnerability which affects Intel Atom CPUs. It + allows unprivileged speculative access to stale data previously + stored in floating point, vector and integer registers. + See also <file:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst> + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 814fe0d34..6f55609ba 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -379,7 +379,7 @@ config X86_CMOV config X86_MINIMUM_CPU_FAMILY int default "64" if X86_64 - default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8) + default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8) default "5" if X86_32 && X86_CMPXCHG64 default "4" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 1f796050c..8b9fa777f 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -87,6 +87,14 @@ ifeq ($(CONFIG_X86_32),y) # temporary until string.h is fixed KBUILD_CFLAGS += -ffreestanding + + ifeq ($(CONFIG_STACKPROTECTOR),y) + ifeq ($(CONFIG_SMP),y) + KBUILD_CFLAGS += -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard + else + KBUILD_CFLAGS += -mstack-protector-guard=global + endif + endif else BITS := 64 UTS_MACHINE := x86_64 diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um index 1db791379..b3c1ae084 100644 --- a/arch/x86/Makefile.um +++ b/arch/x86/Makefile.um @@ -44,7 +44,7 @@ ELF_FORMAT := elf64-x86-64 # Not on all 64-bit distros /lib is a symlink to /lib64. PLD is an example. -LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib64 +LINK-$(CONFIG_LD_SCRIPT_DYN_RPATH) += -Wl,-rpath,/lib64 LINK-y += -m64 endif diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index f4a2e6d37..1e4eb3894 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -367,3 +367,8 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) */ add_identity_map(address, end); } + +void do_boot_nmi_trap(struct pt_regs *regs, unsigned long error_code) +{ + /* Empty handler to ignore NMI during early boot */ +} diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 804a502ee..eb30bb20c 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -45,6 +45,7 @@ void load_stage2_idt(void) boot_idt_desc.address = (unsigned long)boot_idt; set_idt_entry(X86_TRAP_PF, boot_page_fault); + set_idt_entry(X86_TRAP_NMI, boot_nmi_trap); #ifdef CONFIG_AMD_MEM_ENCRYPT set_idt_entry(X86_TRAP_VC, boot_stage2_vc); diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S index 22890e199..4d03c8562 100644 --- a/arch/x86/boot/compressed/idt_handlers_64.S +++ b/arch/x86/boot/compressed/idt_handlers_64.S @@ -70,6 +70,7 @@ SYM_FUNC_END(\name) .code64 EXCEPTION_HANDLER boot_page_fault do_boot_page_fault error_code=1 +EXCEPTION_HANDLER boot_nmi_trap do_boot_nmi_trap error_code=0 #ifdef CONFIG_AMD_MEM_ENCRYPT EXCEPTION_HANDLER boot_stage1_vc do_vc_no_ghcb error_code=1 diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index d9a631c59..0ccc32718 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -156,6 +156,7 @@ extern struct desc_ptr boot_idt_desc; /* IDT Entry Points */ void boot_page_fault(void); +void boot_nmi_trap(void); void boot_stage1_vc(void); void boot_stage2_vc(void); diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index bfb7bcb36..09e99d13f 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -6,6 +6,9 @@ #include <linux/linkage.h> #include <asm/export.h> #include <asm/msr-index.h> +#include <asm/unwind_hints.h> +#include <asm/segment.h> +#include <asm/cache.h> .pushsection .noinstr.text, "ax" @@ -20,3 +23,23 @@ SYM_FUNC_END(entry_ibpb) EXPORT_SYMBOL_GPL(entry_ibpb); .popsection + +/* + * Define the VERW operand that is disguised as entry code so that + * it can be referenced with KPTI enabled. This ensure VERW can be + * used late in exit-to-user path after page tables are switched. + */ +.pushsection .entry.text, "ax" + +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_START_NOALIGN(mds_verw_sel) + UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR + .word __KERNEL_DS +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_END(mds_verw_sel); +/* For KVM */ +EXPORT_SYMBOL_GPL(mds_verw_sel); + +.popsection + diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 70bd81b6c..97d422f31 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -20,7 +20,7 @@ * 1C(%esp) - %ds * 20(%esp) - %es * 24(%esp) - %fs - * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS + * 28(%esp) - unused -- was %gs on old stackprotector kernels * 2C(%esp) - orig_eax * 30(%esp) - %eip * 34(%esp) - %cs @@ -56,14 +56,9 @@ /* * User gs save/restore * - * %gs is used for userland TLS and kernel only uses it for stack - * canary which is required to be at %gs:20 by gcc. Read the comment - * at the top of stackprotector.h for more info. - * - * Local labels 98 and 99 are used. + * This is leftover junk from CONFIG_X86_32_LAZY_GS. A subsequent patch + * will remove it entirely. */ -#ifdef CONFIG_X86_32_LAZY_GS - /* unfortunately push/pop can't be no-op */ .macro PUSH_GS pushl $0 @@ -86,49 +81,6 @@ .macro SET_KERNEL_GS reg .endm -#else /* CONFIG_X86_32_LAZY_GS */ - -.macro PUSH_GS - pushl %gs -.endm - -.macro POP_GS pop=0 -98: popl %gs - .if \pop <> 0 - add $\pop, %esp - .endif -.endm -.macro POP_GS_EX -.pushsection .fixup, "ax" -99: movl $0, (%esp) - jmp 98b -.popsection - _ASM_EXTABLE(98b, 99b) -.endm - -.macro PTGS_TO_GS -98: mov PT_GS(%esp), %gs -.endm -.macro PTGS_TO_GS_EX -.pushsection .fixup, "ax" -99: movl $0, PT_GS(%esp) - jmp 98b -.popsection - _ASM_EXTABLE(98b, 99b) -.endm - -.macro GS_TO_REG reg - movl %gs, \reg -.endm -.macro REG_TO_PTGS reg - movl \reg, PT_GS(%esp) -.endm -.macro SET_KERNEL_GS reg - movl $(__KERNEL_STACK_CANARY), \reg - movl \reg, %gs -.endm - -#endif /* CONFIG_X86_32_LAZY_GS */ /* Unconditionally switch to user cr3 */ .macro SWITCH_TO_USER_CR3 scratch_reg:req @@ -779,7 +731,7 @@ SYM_CODE_START(__switch_to_asm) #ifdef CONFIG_STACKPROTECTOR movl TASK_stack_canary(%edx), %ebx - movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset + movl %ebx, PER_CPU_VAR(__stack_chk_guard) #endif /* @@ -997,6 +949,7 @@ SYM_FUNC_START(entry_SYSENTER_32) BUG_IF_WRONG_CR3 no_user_check=1 popfl popl %eax + CLEAR_CPU_BUFFERS /* * Return back to the vDSO, which will pop ecx and edx. @@ -1069,6 +1022,7 @@ restore_all_switch_stack: /* Restore user state */ RESTORE_REGS pop=4 # skip orig_eax/error_code + CLEAR_CPU_BUFFERS .Lirq_return: /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization @@ -1267,6 +1221,7 @@ SYM_CODE_START(asm_exc_nmi) /* Not on SYSENTER stack. */ call exc_nmi + CLEAR_CPU_BUFFERS jmp .Lnmi_return .Lnmi_from_sysenter_stack: diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 23212c53c..1631a9a15 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -615,6 +615,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) /* Restore RDI. */ popq %rdi SWAPGS + CLEAR_CPU_BUFFERS INTERRUPT_RETURN @@ -721,6 +722,8 @@ native_irq_return_ldt: */ popq %rax /* Restore user RAX */ + CLEAR_CPU_BUFFERS + /* * RSP now points to an ordinary IRET frame, except that the page * is read-only and RSP[31:16] are preloaded with the userspace @@ -1488,6 +1491,12 @@ nmi_restore: movq $0, 5*8(%rsp) /* clear "NMI executing" */ /* + * Skip CLEAR_CPU_BUFFERS here, since it only helps in rare cases like + * NMI in kernel after user state is restored. For an unprivileged user + * these conditions are hard to meet. + */ + + /* * iretq reads the "iret" frame and exits the NMI stack in a * single instruction. We are returning to kernel mode, so this * cannot result in a fault. Similarly, we don't need to worry @@ -1504,6 +1513,7 @@ SYM_CODE_END(asm_exc_nmi) SYM_CODE_START(ignore_sysret) UNWIND_HINT_EMPTY mov $-ENOSYS, %eax + CLEAR_CPU_BUFFERS sysretl SYM_CODE_END(ignore_sysret) #endif diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 4d637a965..7f09e7ad3 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -319,6 +319,7 @@ sysret32_from_system_call: xorl %r9d, %r9d xorl %r10d, %r10d swapgs + CLEAR_CPU_BUFFERS sysretl SYM_CODE_END(entry_SYSCALL_compat) diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 3b4412c83..01064ba1a 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -12,6 +12,7 @@ #include <asm/mpspec.h> #include <asm/msr.h> #include <asm/hardirq.h> +#include <asm/io.h> #define ARCH_APICTIMER_STOPS_ON_C3 1 @@ -111,7 +112,7 @@ static inline void native_apic_mem_write(u32 reg, u32 v) static inline u32 native_apic_mem_read(u32 reg) { - return *((volatile u32 *)(APIC_BASE + reg)); + return readl((void __iomem *)(APIC_BASE + reg)); } extern void native_apic_wait_icr_idle(void); diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 8f80de627..5cdccea45 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -12,6 +12,7 @@ #include <asm/special_insns.h> #include <asm/preempt.h> #include <asm/asm.h> +#include <asm/nospec-branch.h> #ifndef CONFIG_X86_CMPXCHG64 extern void cmpxchg8b_emu(void); diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 0603c7423..c01005d7a 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -6,12 +6,14 @@ # define __ASM_FORM(x) x # define __ASM_FORM_RAW(x) x # define __ASM_FORM_COMMA(x) x, +# define __ASM_REGPFX % #else #include <linux/stringify.h> # define __ASM_FORM(x) " " __stringify(x) " " # define __ASM_FORM_RAW(x) __stringify(x) # define __ASM_FORM_COMMA(x) " " __stringify(x) "," +# define __ASM_REGPFX %% #endif #ifndef __x86_64__ @@ -48,6 +50,9 @@ #define _ASM_SI __ASM_REG(si) #define _ASM_DI __ASM_REG(di) +/* Adds a (%rip) suffix on 64 bits only; for immediate memory references */ +#define _ASM_RIP(x) __ASM_SEL_RAW(x, x (__ASM_REGPFX rip)) + #ifndef __x86_64__ /* 32 bit */ diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h index dd5ea1bdf..75efc4c6f 100644 --- a/arch/x86/include/asm/cpu_entry_area.h +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -143,7 +143,7 @@ extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags); extern struct cpu_entry_area *get_cpu_entry_area(int cpu); -static inline struct entry_stack *cpu_entry_stack(int cpu) +static __always_inline struct entry_stack *cpu_entry_stack(int cpu) { return &get_cpu_entry_area(cpu)->entry_stack_page.stack; } diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index cc3f62f5d..955ca6b13 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -33,6 +33,8 @@ enum cpuid_leafs CPUID_7_EDX, CPUID_8000_001F_EAX, CPUID_8000_0021_EAX, + CPUID_LNX_5, + NR_CPUID_WORDS, }; #ifdef CONFIG_X86_FEATURE_NAMES @@ -93,8 +95,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -118,8 +121,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 5a54c3685..e1bc2bad8 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 21 /* N 32-bit words worth of info */ +#define NCAPINTS 22 /* N 32-bit words worth of info */ #define NBUGINTS 2 /* N 32-bit bug flags */ /* @@ -300,6 +300,7 @@ #define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ #define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ #define X86_FEATURE_MSR_TSX_CTRL (11*32+18) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_CLEAR_CPU_BUF (11*32+19) /* "" Clear CPU buffers using VERW */ #define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ #define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ @@ -403,6 +404,7 @@ #define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ #define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */ #define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ #define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ @@ -452,4 +454,5 @@ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 3c24378e6..e5f44a3e2 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -103,6 +103,7 @@ #define DISABLED_MASK18 0 #define DISABLED_MASK19 0 #define DISABLED_MASK20 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define DISABLED_MASK21 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index 5443851d3..264ab414e 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -77,7 +77,6 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, static __always_inline void arch_exit_to_user_mode(void) { - mds_user_clear_cpu_buffers(); amd_clear_divider(); } #define arch_exit_to_user_mode arch_exit_to_user_mode diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 8c86edefa..f40dea50d 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -134,6 +134,7 @@ static __always_inline unsigned long arch_local_irq_save(void) #define INTERRUPT_RETURN jmp native_iret #define USERGS_SYSRET64 \ swapgs; \ + CLEAR_CPU_BUFFERS; \ sysretq; #define USERGS_SYSRET32 \ swapgs; \ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 7d7a3cbb8..52a6d43ed 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -30,6 +30,7 @@ #define _EFER_SVME 12 /* Enable virtualization */ #define _EFER_LMSLE 13 /* Long Mode Segment Limit Enable */ #define _EFER_FFXSR 14 /* Enable Fast FXSAVE/FXRSTOR */ +#define _EFER_AUTOIBRS 21 /* Enable Automatic IBRS */ #define EFER_SCE (1<<_EFER_SCE) #define EFER_LME (1<<_EFER_LME) @@ -38,6 +39,7 @@ #define EFER_SVME (1<<_EFER_SVME) #define EFER_LMSLE (1<<_EFER_LMSLE) #define EFER_FFXSR (1<<_EFER_FFXSR) +#define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) /* Intel MSRs. Some also available on other CPUs */ @@ -166,6 +168,14 @@ * CPU is not vulnerable to Gather * Data Sampling (GDS). */ +#define ARCH_CAP_RFDS_NO BIT(27) /* + * Not susceptible to Register + * File Data Sampling. + */ +#define ARCH_CAP_RFDS_CLEAR BIT(28) /* + * VERW clears CPU Register + * File. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 7b4782249..87e1ff064 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -155,11 +155,20 @@ .Lskip_rsb_\@: .endm +/* + * The CALL to srso_alias_untrain_ret() must be patched in directly at + * the spot where untraining must be done, ie., srso_alias_untrain_ret() + * must be the target of a CALL instruction instead of indirectly + * jumping to a wrapper which then calls it. Therefore, this macro is + * called outside of __UNTRAIN_RET below, for the time being, before the + * kernel can support nested alternatives with arbitrary nesting. + */ +.macro CALL_UNTRAIN_RET #ifdef CONFIG_CPU_UNRET_ENTRY -#define CALL_UNTRAIN_RET "call entry_untrain_ret" -#else -#define CALL_UNTRAIN_RET "" + ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \ + "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS #endif +.endm /* * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the @@ -176,12 +185,24 @@ #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ defined(CONFIG_CPU_SRSO) ANNOTATE_UNRET_END - ALTERNATIVE_2 "", \ - CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ - "call entry_ibpb", X86_FEATURE_ENTRY_IBPB + CALL_UNTRAIN_RET + ALTERNATIVE "", "call entry_ibpb", X86_FEATURE_ENTRY_IBPB #endif .endm +/* + * Macro to execute VERW instruction that mitigate transient data sampling + * attacks such as MDS. On affected systems a microcode update overloaded VERW + * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF. + * + * Note: Only the memory operand variant of VERW clears the CPU buffers. + */ +.macro CLEAR_CPU_BUFFERS + ALTERNATIVE "jmp .Lskip_verw_\@", "", X86_FEATURE_CLEAR_CPU_BUF + verw _ASM_RIP(mds_verw_sel) +.Lskip_verw_\@: +.endm + #else /* __ASSEMBLY__ */ #define ANNOTATE_RETPOLINE_SAFE \ @@ -207,6 +228,8 @@ extern void srso_alias_untrain_ret(void); extern void entry_untrain_ret(void); extern void entry_ibpb(void); +extern void (*x86_return_thunk)(void); + #ifdef CONFIG_RETPOLINE typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; @@ -355,11 +378,12 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -DECLARE_STATIC_KEY_FALSE(mds_user_clear); DECLARE_STATIC_KEY_FALSE(mds_idle_clear); DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); +extern u16 mds_verw_sel; + #include <asm/segment.h> /** @@ -386,17 +410,6 @@ static __always_inline void mds_clear_cpu_buffers(void) } /** - * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability - * - * Clear CPU buffers if the corresponding static key is enabled - */ -static __always_inline void mds_user_clear_cpu_buffers(void) -{ - if (static_branch_likely(&mds_user_clear)) - mds_clear_cpu_buffers(); -} - -/** * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability * * Clear CPU buffers if the corresponding static key is enabled diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d7e017b0b..6dc3c5f0b 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -441,6 +441,9 @@ struct fixed_percpu_data { * GCC hardcodes the stack canary as %gs:40. Since the * irq_stack is the object at %gs:0, we reserve the bottom * 48 bytes of the irq stack for the canary. + * + * Once we are willing to require -mstack-protector-guard-symbol= + * support for x86_64 stackprotector, we can get rid of this. */ char gs_base[40]; unsigned long stack_canary; @@ -461,17 +464,7 @@ extern asmlinkage void ignore_sysret(void); void current_save_fsgs(void); #else /* X86_64 */ #ifdef CONFIG_STACKPROTECTOR -/* - * Make sure stack canary segment base is cached-aligned: - * "For Intel Atom processors, avoid non zero segment base address - * that is not aligned to cache line boundary at all cost." - * (Optim Ref Manual Assembly/Compiler Coding Rule 15.) - */ -struct stack_canary { - char __pad[20]; /* canary at %gs:20 */ - unsigned long canary; -}; -DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary); +DECLARE_PER_CPU(unsigned long, __stack_chk_guard); #endif /* Per CPU softirq stack pointer */ DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr); diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 409f66148..b94f61560 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -37,7 +37,10 @@ struct pt_regs { unsigned short __esh; unsigned short fs; unsigned short __fsh; - /* On interrupt, gs and __gsh store the vector number. */ + /* + * On interrupt, gs and __gsh store the vector number. They never + * store gs any more. + */ unsigned short gs; unsigned short __gsh; /* On interrupt, this is the error code. */ diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 9bf60a8b9..1fbe53583 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -103,6 +103,7 @@ #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 #define REQUIRED_MASK20 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define REQUIRED_MASK21 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 7fdd4facf..72044026e 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -95,7 +95,7 @@ * * 26 - ESPFIX small SS * 27 - per-cpu [ offset to per-cpu data area ] - * 28 - stack_canary-20 [ for stack protector ] <=== cacheline #8 + * 28 - unused * 29 - unused * 30 - unused * 31 - TSS for double fault handler @@ -118,7 +118,6 @@ #define GDT_ENTRY_ESPFIX_SS 26 #define GDT_ENTRY_PERCPU 27 -#define GDT_ENTRY_STACK_CANARY 28 #define GDT_ENTRY_DOUBLEFAULT_TSS 31 @@ -158,12 +157,6 @@ # define __KERNEL_PERCPU 0 #endif -#ifdef CONFIG_STACKPROTECTOR -# define __KERNEL_STACK_CANARY (GDT_ENTRY_STACK_CANARY*8) -#else -# define __KERNEL_STACK_CANARY 0 -#endif - #else /* 64-bit: */ #include <asm/cache.h> @@ -364,22 +357,15 @@ static inline void __loadsegment_fs(unsigned short value) asm("mov %%" #seg ",%0":"=r" (value) : : "memory") /* - * x86-32 user GS accessors: + * x86-32 user GS accessors. This is ugly and could do with some cleaning up. */ #ifdef CONFIG_X86_32 -# ifdef CONFIG_X86_32_LAZY_GS -# define get_user_gs(regs) (u16)({ unsigned long v; savesegment(gs, v); v; }) -# define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v)) -# define task_user_gs(tsk) ((tsk)->thread.gs) -# define lazy_save_gs(v) savesegment(gs, (v)) -# define lazy_load_gs(v) loadsegment(gs, (v)) -# else /* X86_32_LAZY_GS */ -# define get_user_gs(regs) (u16)((regs)->gs) -# define set_user_gs(regs, v) do { (regs)->gs = (v); } while (0) -# define task_user_gs(tsk) (task_pt_regs(tsk)->gs) -# define lazy_save_gs(v) do { } while (0) -# define lazy_load_gs(v) do { } while (0) -# endif /* X86_32_LAZY_GS */ +# define get_user_gs(regs) (u16)({ unsigned long v; savesegment(gs, v); v; }) +# define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v)) +# define task_user_gs(tsk) ((tsk)->thread.gs) +# define lazy_save_gs(v) savesegment(gs, (v)) +# define lazy_load_gs(v) loadsegment(gs, (v)) +# define load_gs_index(v) loadsegment(gs, (v)) #endif /* X86_32 */ #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 4e1757bf6..d65bfc293 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -49,7 +49,6 @@ extern unsigned long saved_video_mode; extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp); -extern unsigned long __startup_secondary_64(void); extern void startup_64_setup_env(unsigned long physbase); extern void early_setup_idt(void); extern void __init do_early_exception(struct pt_regs *regs, int trapnr); diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 7fb482f0f..b6ffe58c7 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -5,30 +5,23 @@ * Stack protector works by putting predefined pattern at the start of * the stack frame and verifying that it hasn't been overwritten when * returning from the function. The pattern is called stack canary - * and unfortunately gcc requires it to be at a fixed offset from %gs. - * On x86_64, the offset is 40 bytes and on x86_32 20 bytes. x86_64 - * and x86_32 use segment registers differently and thus handles this - * requirement differently. + * and unfortunately gcc historically required it to be at a fixed offset + * from the percpu segment base. On x86_64, the offset is 40 bytes. * - * On x86_64, %gs is shared by percpu area and stack canary. All - * percpu symbols are zero based and %gs points to the base of percpu - * area. The first occupant of the percpu area is always - * fixed_percpu_data which contains stack_canary at offset 40. Userland - * %gs is always saved and restored on kernel entry and exit using - * swapgs, so stack protector doesn't add any complexity there. + * The same segment is shared by percpu area and stack canary. On + * x86_64, percpu symbols are zero based and %gs (64-bit) points to the + * base of percpu area. The first occupant of the percpu area is always + * fixed_percpu_data which contains stack_canary at the approproate + * offset. On x86_32, the stack canary is just a regular percpu + * variable. * - * On x86_32, it's slightly more complicated. As in x86_64, %gs is - * used for userland TLS. Unfortunately, some processors are much - * slower at loading segment registers with different value when - * entering and leaving the kernel, so the kernel uses %fs for percpu - * area and manages %gs lazily so that %gs is switched only when - * necessary, usually during task switch. + * Putting percpu data in %fs on 32-bit is a minor optimization compared to + * using %gs. Since 32-bit userspace normally has %fs == 0, we are likely + * to load 0 into %fs on exit to usermode, whereas with percpu data in + * %gs, we are likely to load a non-null %gs on return to user mode. * - * As gcc requires the stack canary at %gs:20, %gs can't be managed - * lazily if stack protector is enabled, so the kernel saves and - * restores userland %gs on kernel entry and exit. This behavior is - * controlled by CONFIG_X86_32_LAZY_GS and accessors are defined in - * system.h to hide the details. + * Once we are willing to require GCC 8.1 or better for 64-bit stackprotector + * support, we can remove some of this complexity. */ #ifndef _ASM_STACKPROTECTOR_H @@ -45,14 +38,6 @@ #include <linux/sched.h> /* - * 24 byte read-only segment initializer for stack canary. Linker - * can't handle the address bit shifting. Address will be set in - * head_32 for boot CPU and setup_per_cpu_areas() for others. - */ -#define GDT_STACK_CANARY_INIT \ - [GDT_ENTRY_STACK_CANARY] = GDT_ENTRY_INIT(0x4090, 0, 0x18), - -/* * Initialize the stackprotector canary value. * * NOTE: this must only be called from functions that never return @@ -86,7 +71,7 @@ static __always_inline void boot_init_stack_canary(void) #ifdef CONFIG_X86_64 this_cpu_write(fixed_percpu_data.stack_canary, canary); #else - this_cpu_write(stack_canary.canary, canary); + this_cpu_write(__stack_chk_guard, canary); #endif } @@ -95,48 +80,16 @@ static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle) #ifdef CONFIG_X86_64 per_cpu(fixed_percpu_data.stack_canary, cpu) = idle->stack_canary; #else - per_cpu(stack_canary.canary, cpu) = idle->stack_canary; -#endif -} - -static inline void setup_stack_canary_segment(int cpu) -{ -#ifdef CONFIG_X86_32 - unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu); - struct desc_struct *gdt_table = get_cpu_gdt_rw(cpu); - struct desc_struct desc; - - desc = gdt_table[GDT_ENTRY_STACK_CANARY]; - set_desc_base(&desc, canary); - write_gdt_entry(gdt_table, GDT_ENTRY_STACK_CANARY, &desc, DESCTYPE_S); -#endif -} - -static inline void load_stack_canary_segment(void) -{ -#ifdef CONFIG_X86_32 - asm("mov %0, %%gs" : : "r" (__KERNEL_STACK_CANARY) : "memory"); + per_cpu(__stack_chk_guard, cpu) = idle->stack_canary; #endif } #else /* STACKPROTECTOR */ -#define GDT_STACK_CANARY_INIT - /* dummy boot_init_stack_canary() is defined in linux/stackprotector.h */ -static inline void setup_stack_canary_segment(int cpu) -{ } - static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle) { } -static inline void load_stack_canary_segment(void) -{ -#ifdef CONFIG_X86_32 - asm volatile ("mov %0, %%gs" : : "r" (0)); -#endif -} - #endif /* STACKPROTECTOR */ #endif /* _ASM_STACKPROTECTOR_H */ diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index 3b97aa921..d8416b3bf 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -12,13 +12,6 @@ /* image of the saved processor state */ struct saved_context { - /* - * On x86_32, all segment registers, with the possible exception of - * gs, are saved at kernel entry in pt_regs. - */ -#ifdef CONFIG_X86_32_LAZY_GS - u16 gs; -#endif unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; struct saved_msrs saved_msrs; @@ -29,6 +22,11 @@ struct saved_context { unsigned long tr; unsigned long safety; unsigned long return_address; + /* + * On x86_32, all segment registers except gs are saved at kernel + * entry in pt_regs. + */ + u16 gs; bool misc_enable_saved; } __attribute__((packed)); diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index a84333ade..a507be368 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -58,12 +58,29 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); ,,regs->di,,regs->si,,regs->dx \ ,,regs->r10,,regs->r8,,regs->r9) \ + +/* SYSCALL_PT_ARGS is Adapted from s390x */ +#define SYSCALL_PT_ARG6(m, t1, t2, t3, t4, t5, t6) \ + SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5), m(t6, (regs->bp)) +#define SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5) \ + SYSCALL_PT_ARG4(m, t1, t2, t3, t4), m(t5, (regs->di)) +#define SYSCALL_PT_ARG4(m, t1, t2, t3, t4) \ + SYSCALL_PT_ARG3(m, t1, t2, t3), m(t4, (regs->si)) +#define SYSCALL_PT_ARG3(m, t1, t2, t3) \ + SYSCALL_PT_ARG2(m, t1, t2), m(t3, (regs->dx)) +#define SYSCALL_PT_ARG2(m, t1, t2) \ + SYSCALL_PT_ARG1(m, t1), m(t2, (regs->cx)) +#define SYSCALL_PT_ARG1(m, t1) m(t1, (regs->bx)) +#define SYSCALL_PT_ARGS(x, ...) SYSCALL_PT_ARG##x(__VA_ARGS__) + +#define __SC_COMPAT_CAST(t, a) \ + (__typeof(__builtin_choose_expr(__TYPE_IS_L(t), 0, 0U))) \ + (unsigned int)a + /* Mapping of registers to parameters for syscalls on i386 */ #define SC_IA32_REGS_TO_ARGS(x, ...) \ - __MAP(x,__SC_ARGS \ - ,,(unsigned int)regs->bx,,(unsigned int)regs->cx \ - ,,(unsigned int)regs->dx,,(unsigned int)regs->si \ - ,,(unsigned int)regs->di,,(unsigned int)regs->bp) + SYSCALL_PT_ARGS(x, __SC_COMPAT_CAST, \ + __MAP(x, __SC_TYPE, __VA_ARGS__)) \ #define __SYS_STUB0(abi, name) \ long __##abi##_##name(const struct pt_regs *regs); \ diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index b7421780e..c6015b407 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -96,24 +96,40 @@ union text_poke_insn { }; static __always_inline -void *text_gen_insn(u8 opcode, const void *addr, const void *dest) +void __text_gen_insn(void *buf, u8 opcode, const void *addr, const void *dest, int size) { - static union text_poke_insn insn; /* per instance */ - int size = text_opcode_size(opcode); + union text_poke_insn *insn = buf; + + BUG_ON(size < text_opcode_size(opcode)); + + /* + * Hide the addresses to avoid the compiler folding in constants when + * referencing code, these can mess up annotations like + * ANNOTATE_NOENDBR. + */ + OPTIMIZER_HIDE_VAR(insn); + OPTIMIZER_HIDE_VAR(addr); + OPTIMIZER_HIDE_VAR(dest); - insn.opcode = opcode; + insn->opcode = opcode; if (size > 1) { - insn.disp = (long)dest - (long)(addr + size); + insn->disp = (long)dest - (long)(addr + size); if (size == 2) { /* - * Ensure that for JMP9 the displacement + * Ensure that for JMP8 the displacement * actually fits the signed byte. */ - BUG_ON((insn.disp >> 31) != (insn.disp >> 7)); + BUG_ON((insn->disp >> 31) != (insn->disp >> 7)); } } +} +static __always_inline +void *text_gen_insn(u8 opcode, const void *addr, const void *dest) +{ + static union text_poke_insn insn; /* per instance */ + __text_gen_insn(&insn, opcode, addr, dest, text_opcode_size(opcode)); return &insn.text; } diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index bf2561a5e..3616fd4ba 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -414,6 +414,103 @@ do { \ #endif // CONFIG_CC_ASM_GOTO_OUTPUT +#ifdef CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT +#define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ + bool success; \ + __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ + __typeof__(*(_ptr)) __old = *_old; \ + __typeof__(*(_ptr)) __new = (_new); \ + asm_volatile_goto("\n" \ + "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ + _ASM_EXTABLE_UA(1b, %l[label]) \ + : CC_OUT(z) (success), \ + [ptr] "+m" (*_ptr), \ + [old] "+a" (__old) \ + : [new] ltype (__new) \ + : "memory" \ + : label); \ + if (unlikely(!success)) \ + *_old = __old; \ + likely(success); }) + +#ifdef CONFIG_X86_32 +#define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ + bool success; \ + __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ + __typeof__(*(_ptr)) __old = *_old; \ + __typeof__(*(_ptr)) __new = (_new); \ + asm_volatile_goto("\n" \ + "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ + _ASM_EXTABLE_UA(1b, %l[label]) \ + : CC_OUT(z) (success), \ + "+A" (__old), \ + [ptr] "+m" (*_ptr) \ + : "b" ((u32)__new), \ + "c" ((u32)((u64)__new >> 32)) \ + : "memory" \ + : label); \ + if (unlikely(!success)) \ + *_old = __old; \ + likely(success); }) +#endif // CONFIG_X86_32 +#else // !CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT +#define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ + int __err = 0; \ + bool success; \ + __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ + __typeof__(*(_ptr)) __old = *_old; \ + __typeof__(*(_ptr)) __new = (_new); \ + asm volatile("\n" \ + "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ + CC_SET(z) \ + "2:\n" \ + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, \ + %[errout]) \ + : CC_OUT(z) (success), \ + [errout] "+r" (__err), \ + [ptr] "+m" (*_ptr), \ + [old] "+a" (__old) \ + : [new] ltype (__new) \ + : "memory"); \ + if (unlikely(__err)) \ + goto label; \ + if (unlikely(!success)) \ + *_old = __old; \ + likely(success); }) + +#ifdef CONFIG_X86_32 +/* + * Unlike the normal CMPXCHG, hardcode ECX for both success/fail and error. + * There are only six GPRs available and four (EAX, EBX, ECX, and EDX) are + * hardcoded by CMPXCHG8B, leaving only ESI and EDI. If the compiler uses + * both ESI and EDI for the memory operand, compilation will fail if the error + * is an input+output as there will be no register available for input. + */ +#define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ + int __result; \ + __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ + __typeof__(*(_ptr)) __old = *_old; \ + __typeof__(*(_ptr)) __new = (_new); \ + asm volatile("\n" \ + "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ + "mov $0, %%ecx\n\t" \ + "setz %%cl\n" \ + "2:\n" \ + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %%ecx) \ + : [result]"=c" (__result), \ + "+A" (__old), \ + [ptr] "+m" (*_ptr) \ + : "b" ((u32)__new), \ + "c" ((u32)((u64)__new >> 32)) \ + : "memory", "cc"); \ + if (unlikely(__result < 0)) \ + goto label; \ + if (unlikely(!__result)) \ + *_old = __old; \ + likely(__result); }) +#endif // CONFIG_X86_32 +#endif // CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT + /* FIXME: this hack is definitely wrong -AK */ struct __large_struct { unsigned long buf[100]; }; #define __m(x) (*(struct __large_struct __user *)(x)) @@ -506,6 +603,51 @@ do { \ } while (0) #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT +extern void __try_cmpxchg_user_wrong_size(void); + +#ifndef CONFIG_X86_32 +#define __try_cmpxchg64_user_asm(_ptr, _oldp, _nval, _label) \ + __try_cmpxchg_user_asm("q", "r", (_ptr), (_oldp), (_nval), _label) +#endif + +/* + * Force the pointer to u<size> to match the size expected by the asm helper. + * clang/LLVM compiles all cases and only discards the unused paths after + * processing errors, which breaks i386 if the pointer is an 8-byte value. + */ +#define unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ + bool __ret; \ + __chk_user_ptr(_ptr); \ + switch (sizeof(*(_ptr))) { \ + case 1: __ret = __try_cmpxchg_user_asm("b", "q", \ + (__force u8 *)(_ptr), (_oldp), \ + (_nval), _label); \ + break; \ + case 2: __ret = __try_cmpxchg_user_asm("w", "r", \ + (__force u16 *)(_ptr), (_oldp), \ + (_nval), _label); \ + break; \ + case 4: __ret = __try_cmpxchg_user_asm("l", "r", \ + (__force u32 *)(_ptr), (_oldp), \ + (_nval), _label); \ + break; \ + case 8: __ret = __try_cmpxchg64_user_asm((__force u64 *)(_ptr), (_oldp),\ + (_nval), _label); \ + break; \ + default: __try_cmpxchg_user_wrong_size(); \ + } \ + __ret; }) + +/* "Returns" 0 on success, 1 on failure, -EFAULT if the access faults. */ +#define __try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ + int __ret = -EFAULT; \ + __uaccess_begin_nospec(); \ + __ret = !unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label); \ +_label: \ + __uaccess_end(); \ + __ret; \ + }) + /* * We want the unsafe accessors to always be inlined and use * the error labels - thus the macro games. diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index ab60a71a8..472f0263d 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -4,6 +4,7 @@ #include <linux/seqlock.h> #include <uapi/asm/vsyscall.h> +#include <asm/page_types.h> #ifdef CONFIG_X86_VSYSCALL_EMULATION extern void map_vsyscall(void); @@ -24,4 +25,13 @@ static inline bool emulate_vsyscall(unsigned long error_code, } #endif +/* + * The (legacy) vsyscall page is the long page in the kernel portion + * of the address space that has user-accessible permissions. + */ +static inline bool is_vsyscall_vaddr(unsigned long vaddr) +{ + return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); +} + #endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index c06f3a961..fd5a2a53f 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -49,7 +49,6 @@ endif # non-deterministic coverage. KCOV_INSTRUMENT := n -CFLAGS_head$(BITS).o += -fno-stack-protector CFLAGS_cc_platform.o += -fno-stack-protector CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 9e0a3daa8..9ceef8515 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -676,6 +676,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) } #ifdef CONFIG_RETHUNK + /* * Rewrite the compiler generated return thunk tail-calls. * @@ -691,14 +692,18 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes) { int i = 0; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) - return -1; + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { + if (x86_return_thunk == __x86_return_thunk) + return -1; - bytes[i++] = RET_INSN_OPCODE; + i = JMP32_INSN_SIZE; + __text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i); + } else { + bytes[i++] = RET_INSN_OPCODE; + } for (; i < insn->length;) bytes[i++] = INT3_INSN_OPCODE; - return i; } diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 6e043f295..2b411cd00 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -53,11 +53,6 @@ void foo(void) offsetof(struct cpu_entry_area, tss.x86_tss.sp1) - offsetofend(struct cpu_entry_area, entry_stack_page.stack)); -#ifdef CONFIG_STACKPROTECTOR - BLANK(); - OFFSET(stack_canary_offset, stack_canary, canary); -#endif - BLANK(); DEFINE(EFI_svam, offsetof(efi_runtime_services_t, set_virtual_address_map)); } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f29c6bed9..3b02cb8b0 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1049,11 +1049,11 @@ static bool cpu_has_zenbleed_microcode(void) u32 good_rev = 0; switch (boot_cpu_data.x86_model) { - case 0x30 ... 0x3f: good_rev = 0x0830107a; break; - case 0x60 ... 0x67: good_rev = 0x0860010b; break; - case 0x68 ... 0x6f: good_rev = 0x08608105; break; - case 0x70 ... 0x7f: good_rev = 0x08701032; break; - case 0xa0 ... 0xaf: good_rev = 0x08a00008; break; + case 0x30 ... 0x3f: good_rev = 0x0830107b; break; + case 0x60 ... 0x67: good_rev = 0x0860010c; break; + case 0x68 ... 0x6f: good_rev = 0x08608107; break; + case 0x70 ... 0x7f: good_rev = 0x08701033; break; + case 0xa0 ... 0xaf: good_rev = 0x08a00009; break; default: return false; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d9fda0b6e..d6e14190c 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -109,9 +109,6 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); /* Control unconditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -/* Control MDS CPU buffer clear before returning to user space */ -DEFINE_STATIC_KEY_FALSE(mds_user_clear); -EXPORT_SYMBOL_GPL(mds_user_clear); /* Control MDS CPU buffer clear before idling (halt, mwait) */ DEFINE_STATIC_KEY_FALSE(mds_idle_clear); EXPORT_SYMBOL_GPL(mds_idle_clear); @@ -249,7 +246,7 @@ static void __init mds_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_MD_CLEAR)) mds_mitigation = MDS_MITIGATION_VMWERV; - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) && (mds_nosmt || cpu_mitigations_auto_nosmt())) @@ -353,7 +350,7 @@ static void __init taa_select_mitigation(void) * For guests that can't determine whether the correct microcode is * present on host, enable the mitigation for UCODE_NEEDED as well. */ - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); @@ -421,7 +418,14 @@ static void __init mmio_select_mitigation(void) */ if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM))) - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + + /* + * X86_FEATURE_CLEAR_CPU_BUF could be enabled by other VERW based + * mitigations, disable KVM-only mitigation in that case. + */ + if (boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) + static_branch_disable(&mmio_stale_data_clear); else static_branch_enable(&mmio_stale_data_clear); @@ -474,6 +478,57 @@ static int __init mmio_stale_data_parse_cmdline(char *str) early_param("mmio_stale_data", mmio_stale_data_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "Register File Data Sampling: " fmt + +enum rfds_mitigations { + RFDS_MITIGATION_OFF, + RFDS_MITIGATION_VERW, + RFDS_MITIGATION_UCODE_NEEDED, +}; + +/* Default mitigation for Register File Data Sampling */ +static enum rfds_mitigations rfds_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF; + +static const char * const rfds_strings[] = { + [RFDS_MITIGATION_OFF] = "Vulnerable", + [RFDS_MITIGATION_VERW] = "Mitigation: Clear Register File", + [RFDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", +}; + +static void __init rfds_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_RFDS) || cpu_mitigations_off()) { + rfds_mitigation = RFDS_MITIGATION_OFF; + return; + } + if (rfds_mitigation == RFDS_MITIGATION_OFF) + return; + + if (x86_read_arch_cap_msr() & ARCH_CAP_RFDS_CLEAR) + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + else + rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED; +} + +static __init int rfds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + return 0; + + if (!strcmp(str, "off")) + rfds_mitigation = RFDS_MITIGATION_OFF; + else if (!strcmp(str, "on")) + rfds_mitigation = RFDS_MITIGATION_VERW; + + return 0; +} +early_param("reg_file_data_sampling", rfds_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "" fmt static void __init md_clear_update_mitigation(void) @@ -481,12 +536,12 @@ static void __init md_clear_update_mitigation(void) if (cpu_mitigations_off()) return; - if (!static_key_enabled(&mds_user_clear)) + if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) goto out; /* - * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data - * mitigation, if necessary. + * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO + * Stale Data mitigation, if necessary. */ if (mds_mitigation == MDS_MITIGATION_OFF && boot_cpu_has_bug(X86_BUG_MDS)) { @@ -498,11 +553,19 @@ static void __init md_clear_update_mitigation(void) taa_mitigation = TAA_MITIGATION_VERW; taa_select_mitigation(); } - if (mmio_mitigation == MMIO_MITIGATION_OFF && - boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { + /* + * MMIO_MITIGATION_OFF is not checked here so that mmio_stale_data_clear + * gets updated correctly as per X86_FEATURE_CLEAR_CPU_BUF state. + */ + if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { mmio_mitigation = MMIO_MITIGATION_VERW; mmio_select_mitigation(); } + if (rfds_mitigation == RFDS_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_RFDS)) { + rfds_mitigation = RFDS_MITIGATION_VERW; + rfds_select_mitigation(); + } out: if (boot_cpu_has_bug(X86_BUG_MDS)) pr_info("MDS: %s\n", mds_strings[mds_mitigation]); @@ -512,6 +575,8 @@ out: pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]); else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) pr_info("MMIO Stale Data: Unknown: No mitigations\n"); + if (boot_cpu_has_bug(X86_BUG_RFDS)) + pr_info("Register File Data Sampling: %s\n", rfds_strings[rfds_mitigation]); } static void __init md_clear_select_mitigation(void) @@ -519,11 +584,12 @@ static void __init md_clear_select_mitigation(void) mds_select_mitigation(); taa_select_mitigation(); mmio_select_mitigation(); + rfds_select_mitigation(); /* - * As MDS, TAA and MMIO Stale Data mitigations are inter-related, update - * and print their mitigation after MDS, TAA and MMIO Stale Data - * mitigation selection is done. + * As these mitigations are inter-related and rely on VERW instruction + * to clear the microarchitural buffers, update and print their status + * after mitigation selection is done for each of these vulnerabilities. */ md_clear_update_mitigation(); } @@ -1251,19 +1317,21 @@ spectre_v2_user_select_mitigation(void) } /* - * If no STIBP, enhanced IBRS is enabled, or SMT impossible, STIBP + * If no STIBP, Intel enhanced IBRS is enabled, or SMT impossible, STIBP * is not required. * - * Enhanced IBRS also protects against cross-thread branch target + * Intel's Enhanced IBRS also protects against cross-thread branch target * injection in user-mode as the IBRS bit remains always set which * implicitly enables cross-thread protections. However, in legacy IBRS * mode, the IBRS bit is set only on kernel entry and cleared on return - * to userspace. This disables the implicit cross-thread protection, - * so allow for STIBP to be selected in that case. + * to userspace. AMD Automatic IBRS also does not protect userspace. + * These modes therefore disable the implicit cross-thread protection, + * so allow for STIBP to be selected in those cases. */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && + !boot_cpu_has(X86_FEATURE_AUTOIBRS))) return; /* @@ -1293,9 +1361,9 @@ static const char * const spectre_v2_strings[] = { [SPECTRE_V2_NONE] = "Vulnerable", [SPECTRE_V2_RETPOLINE] = "Mitigation: Retpolines", [SPECTRE_V2_LFENCE] = "Mitigation: LFENCE", - [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced IBRS", - [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced IBRS + LFENCE", - [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced IBRS + Retpolines", + [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced / Automatic IBRS", + [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced / Automatic IBRS + LFENCE", + [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced / Automatic IBRS + Retpolines", [SPECTRE_V2_IBRS] = "Mitigation: IBRS", }; @@ -1364,7 +1432,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && !boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) { - pr_err("%s selected but CPU doesn't have eIBRS. Switching to AUTO select\n", + pr_err("%s selected but CPU doesn't have Enhanced or Automatic IBRS. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } @@ -1549,8 +1617,12 @@ static void __init spectre_v2_select_mitigation(void) pr_err(SPECTRE_V2_EIBRS_EBPF_MSG); if (spectre_v2_in_ibrs_mode(mode)) { - x86_spec_ctrl_base |= SPEC_CTRL_IBRS; - update_spec_ctrl(x86_spec_ctrl_base); + if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) { + msr_set_bit(MSR_EFER, _EFER_AUTOIBRS); + } else { + x86_spec_ctrl_base |= SPEC_CTRL_IBRS; + update_spec_ctrl(x86_spec_ctrl_base); + } } switch (mode) { @@ -1634,8 +1706,8 @@ static void __init spectre_v2_select_mitigation(void) /* * Retpoline protects the kernel, but doesn't protect firmware. IBRS * and Enhanced IBRS protect firmware too, so enable IBRS around - * firmware calls only when IBRS / Enhanced IBRS aren't otherwise - * enabled. + * firmware calls only when IBRS / Enhanced / Automatic IBRS aren't + * otherwise enabled. * * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because * the user might select retpoline on the kernel command line and if @@ -2432,74 +2504,74 @@ static const char * const l1tf_vmx_states[] = { static ssize_t l1tf_show_state(char *buf) { if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) - return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); + return sysfs_emit(buf, "%s\n", L1TF_DEFAULT_MSG); if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED || (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER && sched_smt_active())) { - return sprintf(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, - l1tf_vmx_states[l1tf_vmx_mitigation]); + return sysfs_emit(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation]); } - return sprintf(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, - l1tf_vmx_states[l1tf_vmx_mitigation], - sched_smt_active() ? "vulnerable" : "disabled"); + return sysfs_emit(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t itlb_multihit_show_state(char *buf) { if (!boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || !boot_cpu_has(X86_FEATURE_VMX)) - return sprintf(buf, "KVM: Mitigation: VMX unsupported\n"); + return sysfs_emit(buf, "KVM: Mitigation: VMX unsupported\n"); else if (!(cr4_read_shadow() & X86_CR4_VMXE)) - return sprintf(buf, "KVM: Mitigation: VMX disabled\n"); + return sysfs_emit(buf, "KVM: Mitigation: VMX disabled\n"); else if (itlb_multihit_kvm_mitigation) - return sprintf(buf, "KVM: Mitigation: Split huge pages\n"); + return sysfs_emit(buf, "KVM: Mitigation: Split huge pages\n"); else - return sprintf(buf, "KVM: Vulnerable\n"); + return sysfs_emit(buf, "KVM: Vulnerable\n"); } #else static ssize_t l1tf_show_state(char *buf) { - return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); + return sysfs_emit(buf, "%s\n", L1TF_DEFAULT_MSG); } static ssize_t itlb_multihit_show_state(char *buf) { - return sprintf(buf, "Processor vulnerable\n"); + return sysfs_emit(buf, "Processor vulnerable\n"); } #endif static ssize_t mds_show_state(char *buf) { if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { - return sprintf(buf, "%s; SMT Host state unknown\n", - mds_strings[mds_mitigation]); + return sysfs_emit(buf, "%s; SMT Host state unknown\n", + mds_strings[mds_mitigation]); } if (boot_cpu_has(X86_BUG_MSBDS_ONLY)) { - return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], - (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" : - sched_smt_active() ? "mitigated" : "disabled")); + return sysfs_emit(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], + (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" : + sched_smt_active() ? "mitigated" : "disabled")); } - return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], - sched_smt_active() ? "vulnerable" : "disabled"); + return sysfs_emit(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t tsx_async_abort_show_state(char *buf) { if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) || (taa_mitigation == TAA_MITIGATION_OFF)) - return sprintf(buf, "%s\n", taa_strings[taa_mitigation]); + return sysfs_emit(buf, "%s\n", taa_strings[taa_mitigation]); if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { - return sprintf(buf, "%s; SMT Host state unknown\n", - taa_strings[taa_mitigation]); + return sysfs_emit(buf, "%s; SMT Host state unknown\n", + taa_strings[taa_mitigation]); } - return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], - sched_smt_active() ? "vulnerable" : "disabled"); + return sysfs_emit(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t mmio_stale_data_show_state(char *buf) @@ -2519,9 +2591,15 @@ static ssize_t mmio_stale_data_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t rfds_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]); +} + static char *stibp_state(void) { - if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && + !boot_cpu_has(X86_FEATURE_AUTOIBRS)) return ""; switch (spectre_v2_user_stibp) { @@ -2567,47 +2645,46 @@ static char *pbrsb_eibrs_state(void) static ssize_t spectre_v2_show_state(char *buf) { if (spectre_v2_enabled == SPECTRE_V2_LFENCE) - return sprintf(buf, "Vulnerable: LFENCE\n"); + return sysfs_emit(buf, "Vulnerable: LFENCE\n"); if (spectre_v2_enabled == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) - return sprintf(buf, "Vulnerable: eIBRS with unprivileged eBPF\n"); + return sysfs_emit(buf, "Vulnerable: eIBRS with unprivileged eBPF\n"); if (sched_smt_active() && unprivileged_ebpf_enabled() && spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) - return sprintf(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); + return sysfs_emit(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); - return sprintf(buf, "%s%s%s%s%s%s%s\n", - spectre_v2_strings[spectre_v2_enabled], - ibpb_state(), - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", - stibp_state(), - boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", - pbrsb_eibrs_state(), - spectre_v2_module_string()); + return sysfs_emit(buf, "%s%s%s%s%s%s%s\n", + spectre_v2_strings[spectre_v2_enabled], + ibpb_state(), + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + stibp_state(), + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", + pbrsb_eibrs_state(), + spectre_v2_module_string()); } static ssize_t srbds_show_state(char *buf) { - return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); + return sysfs_emit(buf, "%s\n", srbds_strings[srbds_mitigation]); } static ssize_t retbleed_show_state(char *buf) { if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET || retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && - boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) - return sprintf(buf, "Vulnerable: untrained return thunk / IBPB on non-AMD based uarch\n"); + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) + return sysfs_emit(buf, "Vulnerable: untrained return thunk / IBPB on non-AMD based uarch\n"); - return sprintf(buf, "%s; SMT %s\n", - retbleed_strings[retbleed_mitigation], - !sched_smt_active() ? "disabled" : - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ? - "enabled with STIBP protection" : "vulnerable"); + return sysfs_emit(buf, "%s; SMT %s\n", retbleed_strings[retbleed_mitigation], + !sched_smt_active() ? "disabled" : + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ? + "enabled with STIBP protection" : "vulnerable"); } - return sprintf(buf, "%s\n", retbleed_strings[retbleed_mitigation]); + return sysfs_emit(buf, "%s\n", retbleed_strings[retbleed_mitigation]); } static ssize_t gds_show_state(char *buf) @@ -2629,26 +2706,26 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr char *buf, unsigned int bug) { if (!boot_cpu_has_bug(bug)) - return sprintf(buf, "Not affected\n"); + return sysfs_emit(buf, "Not affected\n"); switch (bug) { case X86_BUG_CPU_MELTDOWN: if (boot_cpu_has(X86_FEATURE_PTI)) - return sprintf(buf, "Mitigation: PTI\n"); + return sysfs_emit(buf, "Mitigation: PTI\n"); if (hypervisor_is_type(X86_HYPER_XEN_PV)) - return sprintf(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n"); + return sysfs_emit(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n"); break; case X86_BUG_SPECTRE_V1: - return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); + return sysfs_emit(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); case X86_BUG_SPECTRE_V2: return spectre_v2_show_state(buf); case X86_BUG_SPEC_STORE_BYPASS: - return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); + return sysfs_emit(buf, "%s\n", ssb_strings[ssb_mode]); case X86_BUG_L1TF: if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV)) @@ -2680,11 +2757,14 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_SRSO: return srso_show_state(buf); + case X86_BUG_RFDS: + return rfds_show_state(buf); + default: break; } - return sprintf(buf, "Vulnerable\n"); + return sysfs_emit(buf, "Vulnerable\n"); } ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) @@ -2754,4 +2834,9 @@ ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribut { return cpu_show_common(dev, attr, buf, X86_BUG_SRSO); } + +ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4ecc6072e..a496a9867 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -166,7 +166,6 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { [GDT_ENTRY_ESPFIX_SS] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff), [GDT_ENTRY_PERCPU] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff), - GDT_STACK_CANARY_INIT #endif } }; EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); @@ -600,7 +599,6 @@ void load_percpu_segment(int cpu) __loadsegment_simple(gs, 0); wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu)); #endif - load_stack_canary_segment(); } #ifdef CONFIG_X86_32 @@ -1098,8 +1096,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), /* Zhaoxin Family 7 */ VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), @@ -1134,6 +1132,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define SRSO BIT(5) /* CPU is affected by GDS */ #define GDS BIT(6) +/* CPU is affected by Register File Data Sampling */ +#define RFDS BIT(7) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1161,14 +1161,23 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE_L, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_P, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_S, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE_N, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), VULNBL_AMD(0x17, RETBLEED | SRSO), - VULNBL_HYGON(0x18, RETBLEED), + VULNBL_HYGON(0x18, RETBLEED | SRSO), VULNBL_AMD(0x19, SRSO), {} }; @@ -1197,6 +1206,24 @@ static bool arch_cap_mmio_immune(u64 ia32_cap) ia32_cap & ARCH_CAP_SBDR_SSDP_NO); } +static bool __init vulnerable_to_rfds(u64 ia32_cap) +{ + /* The "immunity" bit trumps everything else: */ + if (ia32_cap & ARCH_CAP_RFDS_NO) + return false; + + /* + * VMMs set ARCH_CAP_RFDS_CLEAR for processors not in the blacklist to + * indicate that mitigation is needed because guest is running on a + * vulnerable hardware or may migrate to such hardware: + */ + if (ia32_cap & ARCH_CAP_RFDS_CLEAR) + return true; + + /* Only consult the blacklist when there is no enumeration: */ + return cpu_matches(cpu_vuln_blacklist, RFDS); +} + static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = x86_read_arch_cap_msr(); @@ -1219,8 +1246,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); - if (ia32_cap & ARCH_CAP_IBRS_ALL) + /* + * AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature + * flag and protect from vendor-specific bugs via the whitelist. + */ + if ((ia32_cap & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) { setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); + if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && + !(ia32_cap & ARCH_CAP_PBRSB_NO)) + setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); + } if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) { @@ -1282,11 +1317,6 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_RETBLEED); } - if (cpu_has(c, X86_FEATURE_IBRS_ENHANCED) && - !cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && - !(ia32_cap & ARCH_CAP_PBRSB_NO)) - setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); - /* * Check if CPU is vulnerable to GDS. If running in a virtual machine on * an affected processor, the VMM may have disabled the use of GATHER by @@ -1302,6 +1332,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_SRSO); } + if (vulnerable_to_rfds(ia32_cap)) + setup_force_cpu_bug(X86_BUG_RFDS); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; @@ -1937,7 +1970,8 @@ DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) = EXPORT_PER_CPU_SYMBOL(cpu_current_top_of_stack); #ifdef CONFIG_STACKPROTECTOR -DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary); +DEFINE_PER_CPU(unsigned long, __stack_chk_guard); +EXPORT_PER_CPU_SYMBOL(__stack_chk_guard); #endif #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index d50224199..24fca3d56 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -44,7 +44,10 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_F16C, X86_FEATURE_XMM2, }, { X86_FEATURE_AES, X86_FEATURE_XMM2 }, { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 }, + { X86_FEATURE_GFNI, X86_FEATURE_XMM2 }, { X86_FEATURE_FMA, X86_FEATURE_AVX }, + { X86_FEATURE_VAES, X86_FEATURE_AVX }, + { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX }, { X86_FEATURE_AVX2, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512F, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F }, @@ -56,9 +59,6 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL }, - { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VAES, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index c6ad53e38..a7a8c7731 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -178,6 +178,90 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) return false; } +#define MSR_IA32_TME_ACTIVATE 0x982 + +/* Helpers to access TME_ACTIVATE MSR */ +#define TME_ACTIVATE_LOCKED(x) (x & 0x1) +#define TME_ACTIVATE_ENABLED(x) (x & 0x2) + +#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ +#define TME_ACTIVATE_POLICY_AES_XTS_128 0 + +#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ + +#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ +#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 + +/* Values for mktme_status (SW only construct) */ +#define MKTME_ENABLED 0 +#define MKTME_DISABLED 1 +#define MKTME_UNINITIALIZED 2 +static int mktme_status = MKTME_UNINITIALIZED; + +static void detect_tme_early(struct cpuinfo_x86 *c) +{ + u64 tme_activate, tme_policy, tme_crypto_algs; + int keyid_bits = 0, nr_keyids = 0; + static u64 tme_activate_cpu0 = 0; + + rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); + + if (mktme_status != MKTME_UNINITIALIZED) { + if (tme_activate != tme_activate_cpu0) { + /* Broken BIOS? */ + pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); + pr_err_once("x86/tme: MKTME is not usable\n"); + mktme_status = MKTME_DISABLED; + + /* Proceed. We may need to exclude bits from x86_phys_bits. */ + } + } else { + tme_activate_cpu0 = tme_activate; + } + + if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { + pr_info_once("x86/tme: not enabled by BIOS\n"); + mktme_status = MKTME_DISABLED; + return; + } + + if (mktme_status != MKTME_UNINITIALIZED) + goto detect_keyid_bits; + + pr_info("x86/tme: enabled by BIOS\n"); + + tme_policy = TME_ACTIVATE_POLICY(tme_activate); + if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) + pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); + + tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); + if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { + pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", + tme_crypto_algs); + mktme_status = MKTME_DISABLED; + } +detect_keyid_bits: + keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); + nr_keyids = (1UL << keyid_bits) - 1; + if (nr_keyids) { + pr_info_once("x86/mktme: enabled by BIOS\n"); + pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); + } else { + pr_info_once("x86/mktme: disabled by BIOS\n"); + } + + if (mktme_status == MKTME_UNINITIALIZED) { + /* MKTME is usable */ + mktme_status = MKTME_ENABLED; + } + + /* + * KeyID bits effectively lower the number of physical address + * bits. Update cpuinfo_x86::x86_phys_bits accordingly. + */ + c->x86_phys_bits -= keyid_bits; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -329,6 +413,13 @@ static void early_init_intel(struct cpuinfo_x86 *c) */ if (detect_extended_topology_early(c) < 0) detect_ht_early(c); + + /* + * Adjust the number of physical bits early because it affects the + * valid bits of the MTRR mask registers. + */ + if (cpu_has(c, X86_FEATURE_TME)) + detect_tme_early(c); } static void bsp_init_intel(struct cpuinfo_x86 *c) @@ -489,90 +580,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -#define MSR_IA32_TME_ACTIVATE 0x982 - -/* Helpers to access TME_ACTIVATE MSR */ -#define TME_ACTIVATE_LOCKED(x) (x & 0x1) -#define TME_ACTIVATE_ENABLED(x) (x & 0x2) - -#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ -#define TME_ACTIVATE_POLICY_AES_XTS_128 0 - -#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ - -#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ -#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 - -/* Values for mktme_status (SW only construct) */ -#define MKTME_ENABLED 0 -#define MKTME_DISABLED 1 -#define MKTME_UNINITIALIZED 2 -static int mktme_status = MKTME_UNINITIALIZED; - -static void detect_tme(struct cpuinfo_x86 *c) -{ - u64 tme_activate, tme_policy, tme_crypto_algs; - int keyid_bits = 0, nr_keyids = 0; - static u64 tme_activate_cpu0 = 0; - - rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); - - if (mktme_status != MKTME_UNINITIALIZED) { - if (tme_activate != tme_activate_cpu0) { - /* Broken BIOS? */ - pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); - pr_err_once("x86/tme: MKTME is not usable\n"); - mktme_status = MKTME_DISABLED; - - /* Proceed. We may need to exclude bits from x86_phys_bits. */ - } - } else { - tme_activate_cpu0 = tme_activate; - } - - if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { - pr_info_once("x86/tme: not enabled by BIOS\n"); - mktme_status = MKTME_DISABLED; - return; - } - - if (mktme_status != MKTME_UNINITIALIZED) - goto detect_keyid_bits; - - pr_info("x86/tme: enabled by BIOS\n"); - - tme_policy = TME_ACTIVATE_POLICY(tme_activate); - if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) - pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); - - tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); - if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { - pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", - tme_crypto_algs); - mktme_status = MKTME_DISABLED; - } -detect_keyid_bits: - keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); - nr_keyids = (1UL << keyid_bits) - 1; - if (nr_keyids) { - pr_info_once("x86/mktme: enabled by BIOS\n"); - pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); - } else { - pr_info_once("x86/mktme: disabled by BIOS\n"); - } - - if (mktme_status == MKTME_UNINITIALIZED) { - /* MKTME is usable */ - mktme_status = MKTME_ENABLED; - } - - /* - * KeyID bits effectively lower the number of physical address - * bits. Update cpuinfo_x86::x86_phys_bits accordingly. - */ - c->x86_phys_bits -= keyid_bits; -} - static void init_cpuid_fault(struct cpuinfo_x86 *c) { u64 msr; @@ -708,9 +715,6 @@ static void init_intel(struct cpuinfo_x86 *c) init_ia32_feat_ctl(c); - if (cpu_has(c, X86_FEATURE_TME)) - detect_tme(c); - init_intel_misc_features(c); if (tsx_ctrl_state == TSX_CTRL_ENABLE) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 0b7c81389..97ab29429 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -44,6 +44,7 @@ #include <linux/sync_core.h> #include <linux/task_work.h> #include <linux/hardirq.h> +#include <linux/kexec.h> #include <asm/intel-family.h> #include <asm/processor.h> @@ -274,6 +275,7 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) struct llist_node *pending; struct mce_evt_llist *l; int apei_err = 0; + struct page *p; /* * Allow instrumentation around external facilities usage. Not that it @@ -329,6 +331,20 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) if (!fake_panic) { if (panic_timeout == 0) panic_timeout = mca_cfg.panic_timeout; + + /* + * Kdump skips the poisoned page in order to avoid + * touching the error bits again. Poison the page even + * if the error is fatal and the machine is about to + * panic. + */ + if (kexec_crash_loaded()) { + if (final && (final->status & MCI_STATUS_ADDRV)) { + p = pfn_to_online_page(final->addr >> PAGE_SHIFT); + if (p) + SetPageHWPoison(p); + } + } panic(msg); } else pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg); @@ -2373,12 +2389,14 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr, return -EINVAL; b = &per_cpu(mce_banks_array, s->id)[bank]; - if (!b->init) return -ENODEV; b->ctl = new; + + mutex_lock(&mce_sysfs_mutex); mce_restart(); + mutex_unlock(&mce_sysfs_mutex); return size; } diff --git a/arch/x86/kernel/doublefault_32.c b/arch/x86/kernel/doublefault_32.c index 759d392cb..d1d49e3d5 100644 --- a/arch/x86/kernel/doublefault_32.c +++ b/arch/x86/kernel/doublefault_32.c @@ -100,9 +100,7 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct doublefault_stack, doublefault_stack) = { .ss = __KERNEL_DS, .ds = __USER_DS, .fs = __KERNEL_PERCPU, -#ifndef CONFIG_X86_32_LAZY_GS - .gs = __KERNEL_STACK_CANARY, -#endif + .gs = 0, .__cr3 = __pa_nodebug(swapper_pg_dir), }, diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 6d546f442..46447877b 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -367,10 +367,8 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) goto fail; ip = trampoline + size; - - /* The trampoline ends with ret(q) */ if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) - memcpy(ip, text_gen_insn(JMP32_INSN_OPCODE, ip, &__x86_return_thunk), JMP32_INSN_SIZE); + __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE); else memcpy(ip, retq, sizeof(retq)); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 8596b4dca..2988ffd09 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -302,15 +302,6 @@ unsigned long __head __startup_64(unsigned long physaddr, return sme_get_me_mask(); } -unsigned long __startup_secondary_64(void) -{ - /* - * Return the SME encryption mask (if SME is active) to be used as a - * modifier for the initial pgdir entry programmed into CR3. - */ - return sme_get_me_mask(); -} - /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) { diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 3f1691b89..0359333f6 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -319,8 +319,8 @@ SYM_FUNC_START(startup_32_smp) movl $(__KERNEL_PERCPU), %eax movl %eax,%fs # set this cpu's percpu - movl $(__KERNEL_STACK_CANARY),%eax - movl %eax,%gs + xorl %eax,%eax + movl %eax,%gs # clear possible garbage in %gs xorl %eax,%eax # Clear LDT lldt %ax @@ -340,20 +340,6 @@ SYM_FUNC_END(startup_32_smp) */ __INIT setup_once: -#ifdef CONFIG_STACKPROTECTOR - /* - * Configure the stack canary. The linker can't handle this by - * relocation. Manually set base address in stack canary - * segment descriptor. - */ - movl $gdt_page,%eax - movl $stack_canary,%ecx - movw %cx, 8 * GDT_ENTRY_STACK_CANARY + 2(%eax) - shrl $16, %ecx - movb %cl, 8 * GDT_ENTRY_STACK_CANARY + 4(%eax) - movb %ch, 8 * GDT_ENTRY_STACK_CANARY + 7(%eax) -#endif - andl $0,setup_once_ref /* Once is enough, thanks */ RET diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 0424c2a6c..713b1ac34 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -74,6 +74,22 @@ SYM_CODE_START_NOALIGN(startup_64) leaq (__end_init_task - SIZEOF_PTREGS)(%rip), %rsp leaq _text(%rip), %rdi + + /* + * initial_gs points to initial fixed_percpu_data struct with storage for + * the stack protector canary. Global pointer fixups are needed at this + * stage, so apply them as is done in fixup_pointer(), and initialize %gs + * such that the canary can be accessed at %gs:40 for subsequent C calls. + */ + movl $MSR_GS_BASE, %ecx + movq initial_gs(%rip), %rax + movq $_text, %rdx + subq %rdx, %rax + addq %rdi, %rax + movq %rax, %rdx + shrq $32, %rdx + wrmsr + pushq %rsi call startup_64_setup_env popq %rsi @@ -141,9 +157,11 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) * Retrieve the modifier (SME encryption mask if SME is active) to be * added to the initial pgdir entry that will be programmed into CR3. */ - pushq %rsi - call __startup_secondary_64 - popq %rsi +#ifdef CONFIG_AMD_MEM_ENCRYPT + movq sme_me_mask, %rax +#else + xorq %rax, %rax +#endif /* Form the CR3 value being sure to include the CR3 modifier */ addq $(init_top_pgt - __START_KERNEL_map), %rax diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 2ef961cf4..f2e53b20d 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -519,9 +519,6 @@ nmi_restart: write_cr2(this_cpu_read(nmi_cr2)); if (this_cpu_dec_return(nmi_state)) goto nmi_restart; - - if (user_mode(regs)) - mds_user_clear_cpu_buffers(); } #if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL) diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index e21937680..f0e4ad859 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -31,6 +31,7 @@ #include <asm/special_insns.h> #include <asm/tlb.h> #include <asm/io_bitmap.h> +#include <asm/text-patching.h> /* * nop stub, which must not clobber anything *including the stack* to @@ -55,28 +56,16 @@ void __init default_banner(void) static const unsigned char ud2a[] = { 0x0f, 0x0b }; struct branch { - unsigned char opcode; - u32 delta; + unsigned char opcode; + u32 delta; } __attribute__((packed)); static unsigned paravirt_patch_call(void *insn_buff, const void *target, unsigned long addr, unsigned len) { - const int call_len = 5; - struct branch *b = insn_buff; - unsigned long delta = (unsigned long)target - (addr+call_len); - - if (len < call_len) { - pr_warn("paravirt: Failed to patch indirect CALL at %ps\n", (void *)addr); - /* Kernel might not be viable if patching fails, bail out: */ - BUG_ON(1); - } - - b->opcode = 0xe8; /* call */ - b->delta = delta; - BUILD_BUG_ON(sizeof(*b) != call_len); - - return call_len; + __text_gen_insn(insn_buff, CALL_INSN_OPCODE, + (void *)addr, target, CALL_INSN_SIZE); + return CALL_INSN_SIZE; } #ifdef CONFIG_PARAVIRT_XXL diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index fd945ce78..0941d2f44 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -224,7 +224,6 @@ void __init setup_per_cpu_areas(void) per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu); per_cpu(cpu_number, cpu) = cpu; setup_percpu_segment(cpu); - setup_stack_canary_segment(cpu); /* * Copy data used in early init routines from the * initial arrays to the per cpu data areas. These diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 759b986b7..273e9b77b 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -41,7 +41,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, case RET: if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) - code = text_gen_insn(JMP32_INSN_OPCODE, insn, &__x86_return_thunk); + code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk); else code = &retinsn; break; diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 64a496a06..3c883e064 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -164,17 +164,11 @@ int do_set_thread_area(struct task_struct *p, int idx, savesegment(fs, sel); if (sel == modified_sel) loadsegment(fs, sel); - - savesegment(gs, sel); - if (sel == modified_sel) - load_gs_index(sel); #endif -#ifdef CONFIG_X86_32_LAZY_GS savesegment(gs, sel); if (sel == modified_sel) - loadsegment(gs, sel); -#endif + load_gs_index(sel); } else { #ifdef CONFIG_X86_64 if (p->thread.fsindex == modified_sel) diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 1ba9313d2..e25853c2e 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -76,10 +76,12 @@ static const struct cpuid_reg reverse_cpuid[] = { */ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) { + BUILD_BUG_ON(NR_CPUID_WORDS != NCAPINTS); BUILD_BUG_ON(x86_leaf == CPUID_LNX_1); BUILD_BUG_ON(x86_leaf == CPUID_LNX_2); BUILD_BUG_ON(x86_leaf == CPUID_LNX_3); BUILD_BUG_ON(x86_leaf == CPUID_LNX_4); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_5); BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid)); BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0); } diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 81cf4babb..3c379335e 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -35,7 +35,7 @@ int kvm_page_track_create_memslot(struct kvm_memory_slot *slot, for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) { slot->arch.gfn_track[i] = - kvcalloc(npages, sizeof(*slot->arch.gfn_track[i]), + __vcalloc(npages, sizeof(*slot->arch.gfn_track[i]), GFP_KERNEL_ACCOUNT); if (!slot->arch.gfn_track[i]) goto track_free; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index c2b34998c..52e14d6aa 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1024,20 +1024,22 @@ int svm_register_enc_region(struct kvm *kvm, goto e_free; } - region->uaddr = range->addr; - region->size = range->size; - - list_add_tail(®ion->list, &sev->regions_list); - mutex_unlock(&kvm->lock); - /* * The guest may change the memory encryption attribute from C=0 -> C=1 * or vice versa for this memory range. Lets make sure caches are * flushed to ensure that guest data gets written into memory with - * correct C-bit. + * correct C-bit. Note, this must be done before dropping kvm->lock, + * as region and its array of pages can be freed by a different task + * once kvm->lock is released. */ sev_clflush_pages(region->pages, region->npages); + region->uaddr = range->addr; + region->size = range->size; + + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + return ret; e_free: diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h index edc3f16cc..6a9bfdfbb 100644 --- a/arch/x86/kvm/vmx/run_flags.h +++ b/arch/x86/kvm/vmx/run_flags.h @@ -2,7 +2,10 @@ #ifndef __KVM_X86_VMX_RUN_FLAGS_H #define __KVM_X86_VMX_RUN_FLAGS_H -#define VMX_RUN_VMRESUME (1 << 0) -#define VMX_RUN_SAVE_SPEC_CTRL (1 << 1) +#define VMX_RUN_VMRESUME_SHIFT 0 +#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT 1 + +#define VMX_RUN_VMRESUME BIT(VMX_RUN_VMRESUME_SHIFT) +#define VMX_RUN_SAVE_SPEC_CTRL BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT) #endif /* __KVM_X86_VMX_RUN_FLAGS_H */ diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 982138beb..7a4b999d5 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -77,7 +77,7 @@ SYM_FUNC_START(__vmx_vcpu_run) mov (%_ASM_SP), %_ASM_AX /* Check if vmlaunch or vmresume is needed */ - testb $VMX_RUN_VMRESUME, %bl + bt $VMX_RUN_VMRESUME_SHIFT, %bx /* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX @@ -99,8 +99,11 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX - /* Check EFLAGS.ZF from 'testb' above */ - jz .Lvmlaunch + /* Clobbers EFLAGS.ZF */ + CLEAR_CPU_BUFFERS + + /* Check EFLAGS.CF from the VMX_RUN_VMRESUME bit test above. */ + jnc .Lvmlaunch /* * After a successful VMRESUME/VMLAUNCH, control flow "magically" diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 2445c6103..3e9bb9ae8 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -397,7 +397,8 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx) static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - vmx->disable_fb_clear = vmx_fb_clear_ctrl_available; + vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) && + vmx_fb_clear_ctrl_available; /* * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS @@ -6792,11 +6793,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, guest_enter_irqoff(); lockdep_hardirqs_on(CALLER_ADDR0); - /* L1D Flush includes CPU buffer clear to mitigate MDS */ + /* + * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW + * mitigation for MDS is done late in VMentry and is still + * executed in spite of L1D Flush. This is because an extra VERW + * should not matter much after the big hammer L1D Flush. + */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); - else if (static_branch_unlikely(&mds_user_clear)) - mds_clear_cpu_buffers(); else if (static_branch_unlikely(&mmio_stale_data_clear) && kvm_arch_has_assigned_device(vcpu->kvm)) mds_clear_cpu_buffers(); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 13e4699a0..8e0b957c6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1389,7 +1389,8 @@ static unsigned int num_msr_based_features; ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ - ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO) + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR) static u64 kvm_get_arch_capabilities(void) { @@ -1426,6 +1427,8 @@ static u64 kvm_get_arch_capabilities(void) data |= ARCH_CAP_SSB_NO; if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + data |= ARCH_CAP_RFDS_NO; if (!boot_cpu_has(X86_FEATURE_RTM)) { /* @@ -10826,14 +10829,14 @@ static int kvm_alloc_memslot_metadata(struct kvm_memory_slot *slot, slot->base_gfn, level) + 1; slot->arch.rmap[i] = - kvcalloc(lpages, sizeof(*slot->arch.rmap[i]), + __vcalloc(lpages, sizeof(*slot->arch.rmap[i]), GFP_KERNEL_ACCOUNT); if (!slot->arch.rmap[i]) goto out_free; if (i == 0) continue; - linfo = kvcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT); + linfo = __vcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT); if (!linfo) goto out_free; diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index ffc8b7dcf..6ed542e31 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -404,10 +404,6 @@ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx) case INAT_SEG_REG_FS: return (unsigned short)(regs->fs & 0xffff); case INAT_SEG_REG_GS: - /* - * GS may or may not be in regs as per CONFIG_X86_32_LAZY_GS. - * The macro below takes care of both cases. - */ return get_user_gs(regs); case INAT_SEG_REG_IGNORE: default: diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 6f5321b36..ab9b04779 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -108,6 +108,7 @@ SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) ret int3 SYM_FUNC_END(srso_alias_untrain_ret) +__EXPORT_THUNK(srso_alias_untrain_ret) #endif SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE) @@ -249,9 +250,7 @@ SYM_CODE_START(srso_return_thunk) SYM_CODE_END(srso_return_thunk) SYM_FUNC_START(entry_untrain_ret) - ALTERNATIVE_2 "jmp retbleed_untrain_ret", \ - "jmp srso_untrain_ret", X86_FEATURE_SRSO, \ - "jmp srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS + ALTERNATIVE "jmp retbleed_untrain_ret", "jmp srso_untrain_ret", X86_FEATURE_SRSO SYM_FUNC_END(entry_untrain_ret) __EXPORT_THUNK(entry_untrain_ret) @@ -259,6 +258,7 @@ SYM_CODE_START(__x86_return_thunk) UNWIND_HINT_FUNC ANNOTATE_NOENDBR ANNOTATE_UNRET_SAFE + ANNOTATE_NOENDBR ret int3 SYM_CODE_END(__x86_return_thunk) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 9c1545c37..cdb337cf9 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -781,15 +781,6 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, show_opcodes(regs, loglvl); } -/* - * The (legacy) vsyscall page is the long page in the kernel portion - * of the address space that has user-accessible permissions. - */ -static bool is_vsyscall_vaddr(unsigned long vaddr) -{ - return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); -} - static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c index 6993f026a..42115ac07 100644 --- a/arch/x86/mm/maccess.c +++ b/arch/x86/mm/maccess.c @@ -3,6 +3,8 @@ #include <linux/uaccess.h> #include <linux/kernel.h> +#include <asm/vsyscall.h> + #ifdef CONFIG_X86_64 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { @@ -16,6 +18,14 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) return false; /* + * Reading from the vsyscall page may cause an unhandled fault in + * certain cases. Though it is at an address above TASK_SIZE_MAX, it is + * usually considered as a user space address. + */ + if (is_vsyscall_vaddr(vaddr)) + return false; + + /* * Allow everything during early boot before 'x86_virt_bits' * is initialized. Needed for instruction decoding in early * exception handlers. diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index f9c53a710..adc76b413 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -56,6 +56,7 @@ #include "memtype.h" #include "../mm_internal.h" +#include "../../../mm/internal.h" /* is_cow_mapping() */ #undef pr_fmt #define pr_fmt(fmt) "" fmt @@ -987,6 +988,38 @@ static void free_pfn_range(u64 paddr, unsigned long size) memtype_free(paddr, paddr + size); } +static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, + pgprot_t *pgprot) +{ + unsigned long prot; + + VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT)); + + /* + * We need the starting PFN and cachemode used for track_pfn_remap() + * that covered the whole VMA. For most mappings, we can obtain that + * information from the page tables. For COW mappings, we might now + * suddenly have anon folios mapped and follow_phys() will fail. + * + * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to + * detect the PFN. If we need the cachemode as well, we're out of luck + * for now and have to fail fork(). + */ + if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) { + if (pgprot) + *pgprot = __pgprot(prot); + return 0; + } + if (is_cow_mapping(vma->vm_flags)) { + if (pgprot) + return -EINVAL; + *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; + return 0; + } + WARN_ON_ONCE(1); + return -EINVAL; +} + /* * track_pfn_copy is called when vma that is covering the pfnmap gets * copied through copy_page_range(). @@ -997,20 +1030,13 @@ static void free_pfn_range(u64 paddr, unsigned long size) int track_pfn_copy(struct vm_area_struct *vma) { resource_size_t paddr; - unsigned long prot; unsigned long vma_size = vma->vm_end - vma->vm_start; pgprot_t pgprot; if (vma->vm_flags & VM_PAT) { - /* - * reserve the whole chunk covered by vma. We need the - * starting address and protection from pte. - */ - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, &pgprot)) return -EINVAL; - } - pgprot = __pgprot(prot); + /* reserve the whole chunk covered by vma. */ return reserve_pfn_range(paddr, vma_size, &pgprot, 1); } @@ -1085,7 +1111,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size) { resource_size_t paddr; - unsigned long prot; if (vma && !(vma->vm_flags & VM_PAT)) return; @@ -1093,11 +1118,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, /* free the chunk starting from pfn or the whole chunk */ paddr = (resource_size_t)pfn << PAGE_SHIFT; if (!paddr && !size) { - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, NULL)) return; - } - size = vma->vm_end - vma->vm_start; } free_pfn_range(paddr, size); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8e3c3d891..d7d592c09 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -405,7 +405,7 @@ static void emit_return(u8 **pprog, u8 *ip) int cnt = 0; if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { - emit_jump(&prog, &__x86_return_thunk, ip); + emit_jump(&prog, x86_return_thunk, ip); } else { EMIT1(0xC3); /* ret */ if (IS_ENABLED(CONFIG_SLS)) diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S index 43b4d8648..afbf0bb25 100644 --- a/arch/x86/platform/pvh/head.S +++ b/arch/x86/platform/pvh/head.S @@ -45,10 +45,8 @@ #define PVH_GDT_ENTRY_CS 1 #define PVH_GDT_ENTRY_DS 2 -#define PVH_GDT_ENTRY_CANARY 3 #define PVH_CS_SEL (PVH_GDT_ENTRY_CS * 8) #define PVH_DS_SEL (PVH_GDT_ENTRY_DS * 8) -#define PVH_CANARY_SEL (PVH_GDT_ENTRY_CANARY * 8) SYM_CODE_START_LOCAL(pvh_start_xen) cld @@ -109,17 +107,6 @@ SYM_CODE_START_LOCAL(pvh_start_xen) #else /* CONFIG_X86_64 */ - /* Set base address in stack canary descriptor. */ - movl $_pa(gdt_start),%eax - movl $_pa(canary),%ecx - movw %cx, (PVH_GDT_ENTRY_CANARY * 8) + 2(%eax) - shrl $16, %ecx - movb %cl, (PVH_GDT_ENTRY_CANARY * 8) + 4(%eax) - movb %ch, (PVH_GDT_ENTRY_CANARY * 8) + 7(%eax) - - mov $PVH_CANARY_SEL,%eax - mov %eax,%gs - call mk_early_pgtbl_32 mov $_pa(initial_page_table), %eax @@ -163,7 +150,6 @@ SYM_DATA_START_LOCAL(gdt_start) .quad GDT_ENTRY(0xc09a, 0, 0xfffff) /* PVH_CS_SEL */ #endif .quad GDT_ENTRY(0xc092, 0, 0xfffff) /* PVH_DS_SEL */ - .quad GDT_ENTRY(0x4090, 0, 0x18) /* PVH_CANARY_SEL */ SYM_DATA_END_LABEL(gdt_start, SYM_L_LOCAL, gdt_end) .balign 16 diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 4e4e76ecd..84c7b2312 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -101,11 +101,8 @@ static void __save_processor_state(struct saved_context *ctxt) /* * segment registers */ -#ifdef CONFIG_X86_32_LAZY_GS savesegment(gs, ctxt->gs); -#endif #ifdef CONFIG_X86_64 - savesegment(gs, ctxt->gs); savesegment(fs, ctxt->fs); savesegment(ds, ctxt->ds); savesegment(es, ctxt->es); @@ -234,7 +231,6 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) wrmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base); #else loadsegment(fs, __KERNEL_PERCPU); - loadsegment(gs, __KERNEL_STACK_CANARY); #endif /* Restore the TSS, RO GDT, LDT, and usermode-relevant MSRs. */ @@ -257,7 +253,7 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) */ wrmsrl(MSR_FS_BASE, ctxt->fs_base); wrmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base); -#elif defined(CONFIG_X86_32_LAZY_GS) +#else loadsegment(gs, ctxt->gs); #endif diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 1c3a1962c..0043fd374 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -596,6 +596,14 @@ static void print_absolute_relocs(void) if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) { continue; } + /* + * Do not perform relocations in .notes section; any + * values there are meant for pre-boot consumption (e.g. + * startup_xen). + */ + if (sec_applies->shdr.sh_type == SHT_NOTE) { + continue; + } sh_symtab = sec_symtab->symtab; sym_strtab = sec_symtab->link->strtab; for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) { diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 815030b7f..94804670c 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1193,7 +1193,6 @@ static void __init xen_setup_gdt(int cpu) pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry_boot; pv_ops.cpu.load_gdt = xen_load_gdt_boot; - setup_stack_canary_segment(cpu); switch_to_new_gdt(cpu); pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry; diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index cdec892b2..a641e0d45 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -65,6 +65,8 @@ int xen_smp_intr_init(unsigned int cpu) char *resched_name, *callfunc_name, *debug_name; resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu); + if (!resched_name) + goto fail_mem; per_cpu(xen_resched_irq, cpu).name = resched_name; rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, cpu, @@ -77,6 +79,8 @@ int xen_smp_intr_init(unsigned int cpu) per_cpu(xen_resched_irq, cpu).irq = rc; callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu); + if (!callfunc_name) + goto fail_mem; per_cpu(xen_callfunc_irq, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR, cpu, @@ -90,6 +94,9 @@ int xen_smp_intr_init(unsigned int cpu) if (!xen_fifo_events) { debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu); + if (!debug_name) + goto fail_mem; + per_cpu(xen_debug_irq, cpu).name = debug_name; rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt, @@ -101,6 +108,9 @@ int xen_smp_intr_init(unsigned int cpu) } callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu); + if (!callfunc_name) + goto fail_mem; + per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR, cpu, @@ -114,6 +124,8 @@ int xen_smp_intr_init(unsigned int cpu) return 0; + fail_mem: + rc = -ENOMEM; fail: xen_smp_intr_free(cpu); return rc; diff --git a/block/bio.c b/block/bio.c index 6d6e7b96b..6f7a1aa9e 100644 --- a/block/bio.c +++ b/block/bio.c @@ -770,7 +770,7 @@ static bool bio_try_merge_hw_seg(struct request_queue *q, struct bio *bio, if ((addr1 | mask) != (addr2 | mask)) return false; - if (bv->bv_len + len > queue_max_segment_size(q)) + if (len > queue_max_segment_size(q) - bv->bv_len) return false; return __bio_try_merge_page(bio, page, len, offset, same_page); } @@ -954,7 +954,7 @@ void bio_release_pages(struct bio *bio, bool mark_dirty) return; bio_for_each_segment_all(bvec, bio, iter_all) { - if (mark_dirty && !PageCompound(bvec->bv_page)) + if (mark_dirty) set_page_dirty_lock(bvec->bv_page); put_page(bvec->bv_page); } @@ -1326,8 +1326,7 @@ void bio_set_pages_dirty(struct bio *bio) struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) { - if (!PageCompound(bvec->bv_page)) - set_page_dirty_lock(bvec->bv_page); + set_page_dirty_lock(bvec->bv_page); } } @@ -1375,7 +1374,7 @@ void bio_check_pages_dirty(struct bio *bio) struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) { - if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page)) + if (!PageDirty(bvec->bv_page)) goto defer; } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 7ba7c4e4e..63a8fb456 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1296,6 +1296,13 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) lockdep_assert_held(&iocg->waitq.lock); + /* + * If the delay is set by another CPU, we may be in the past. No need to + * change anything if so. This avoids decay calculation underflow. + */ + if (time_before64(now->now, iocg->delay_at)) + return false; + /* calculate the current delay in effect - 1/2 every second */ tdelta = now->now - iocg->delay_at; if (iocg->delay) diff --git a/block/blk-mq.c b/block/blk-mq.c index e153a36c9..a7a31d709 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1189,6 +1189,22 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, __add_wait_queue(wq, wait); /* + * Add one explicit barrier since blk_mq_get_driver_tag() may + * not imply barrier in case of failure. + * + * Order adding us to wait queue and allocating driver tag. + * + * The pair is the one implied in sbitmap_queue_wake_up() which + * orders clearing sbitmap tag bits and waitqueue_active() in + * __sbitmap_queue_wake_up(), since waitqueue_active() is lockless + * + * Otherwise, re-order of adding wait queue and getting driver tag + * may cause __sbitmap_queue_wake_up() to wake up nothing because + * the waitqueue_active() may not observe us in wait queue. + */ + smp_mb(); + + /* * It's possible that a tag was freed in the window between the * allocation failure and adding the hardware queue to the wait * queue. diff --git a/block/blk-settings.c b/block/blk-settings.c index c3aa7f8ee..ebd373469 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -60,6 +60,7 @@ void blk_set_default_limits(struct queue_limits *lim) lim->io_opt = 0; lim->misaligned = 0; lim->zoned = BLK_ZONED_NONE; + lim->zone_write_granularity = 0; } EXPORT_SYMBOL(blk_set_default_limits); @@ -354,6 +355,28 @@ void blk_queue_physical_block_size(struct request_queue *q, unsigned int size) EXPORT_SYMBOL(blk_queue_physical_block_size); /** + * blk_queue_zone_write_granularity - set zone write granularity for the queue + * @q: the request queue for the zoned device + * @size: the zone write granularity size, in bytes + * + * Description: + * This should be set to the lowest possible size allowing to write in + * sequential zones of a zoned block device. + */ +void blk_queue_zone_write_granularity(struct request_queue *q, + unsigned int size) +{ + if (WARN_ON_ONCE(!blk_queue_is_zoned(q))) + return; + + q->limits.zone_write_granularity = size; + + if (q->limits.zone_write_granularity < q->limits.logical_block_size) + q->limits.zone_write_granularity = q->limits.logical_block_size; +} +EXPORT_SYMBOL_GPL(blk_queue_zone_write_granularity); + +/** * blk_queue_alignment_offset - set physical block alignment offset * @q: the request queue for the device * @offset: alignment offset in bytes @@ -630,7 +653,13 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->discard_granularity; } + t->zone_write_granularity = max(t->zone_write_granularity, + b->zone_write_granularity); t->zoned = max(t->zoned, b->zoned); + if (!t->zoned) { + t->zone_write_granularity = 0; + t->max_zone_append_sectors = 0; + } return ret; } EXPORT_SYMBOL(blk_stack_limits); @@ -846,6 +875,8 @@ EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging); */ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model) { + struct request_queue *q = disk->queue; + switch (model) { case BLK_ZONED_HM: /* @@ -874,7 +905,15 @@ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model) break; } - disk->queue->limits.zoned = model; + q->limits.zoned = model; + if (model != BLK_ZONED_NONE) { + /* + * Set the zone write granularity to the device logical block + * size by default. The driver can change this value if needed. + */ + blk_queue_zone_write_granularity(q, + queue_logical_block_size(q)); + } } EXPORT_SYMBOL_GPL(blk_queue_set_zoned); diff --git a/block/blk-stat.c b/block/blk-stat.c index ae3dd1fb8..6e602f9b9 100644 --- a/block/blk-stat.c +++ b/block/blk-stat.c @@ -28,7 +28,7 @@ void blk_rq_stat_init(struct blk_rq_stat *stat) /* src is a per-cpu stat, mean isn't initialized */ void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src) { - if (!src->nr_samples) + if (dst->nr_samples + src->nr_samples <= dst->nr_samples) return; dst->min = min(dst->min, src->min); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 9174137a9..ddf23bf3e 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -219,6 +219,12 @@ static ssize_t queue_write_zeroes_max_show(struct request_queue *q, char *page) (unsigned long long)q->limits.max_write_zeroes_sectors << 9); } +static ssize_t queue_zone_write_granularity_show(struct request_queue *q, + char *page) +{ + return queue_var_show(queue_zone_write_granularity(q), page); +} + static ssize_t queue_zone_append_max_show(struct request_queue *q, char *page) { unsigned long long max_sectors = q->limits.max_zone_append_sectors; @@ -585,6 +591,7 @@ QUEUE_RO_ENTRY(queue_discard_zeroes_data, "discard_zeroes_data"); QUEUE_RO_ENTRY(queue_write_same_max, "write_same_max_bytes"); QUEUE_RO_ENTRY(queue_write_zeroes_max, "write_zeroes_max_bytes"); QUEUE_RO_ENTRY(queue_zone_append_max, "zone_append_max_bytes"); +QUEUE_RO_ENTRY(queue_zone_write_granularity, "zone_write_granularity"); QUEUE_RO_ENTRY(queue_zoned, "zoned"); QUEUE_RO_ENTRY(queue_nr_zones, "nr_zones"); @@ -639,6 +646,7 @@ static struct attribute *queue_attrs[] = { &queue_write_same_max_entry.attr, &queue_write_zeroes_max_entry.attr, &queue_zone_append_max_entry.attr, + &queue_zone_write_granularity_entry.attr, &queue_nonrot_entry.attr, &queue_zoned_entry.attr, &queue_nr_zones_entry.attr, diff --git a/block/ioctl.c b/block/ioctl.c index e7eed7dad..bc97698e0 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -17,7 +17,7 @@ static int blkpg_do_ioctl(struct block_device *bdev, struct blkpg_partition __user *upart, int op) { struct blkpg_partition p; - long long start, length; + sector_t start, length; if (!capable(CAP_SYS_ADMIN)) return -EACCES; @@ -32,6 +32,12 @@ static int blkpg_do_ioctl(struct block_device *bdev, if (op == BLKPG_DEL_PARTITION) return bdev_del_partition(bdev, p.pno); + if (p.start < 0 || p.length <= 0 || p.start + p.length < 0) + return -EINVAL; + /* Check that the partition is aligned to the block size */ + if (!IS_ALIGNED(p.start | p.length, bdev_logical_block_size(bdev))) + return -EINVAL; + start = p.start >> SECTOR_SHIFT; length = p.length >> SECTOR_SHIFT; @@ -46,9 +52,6 @@ static int blkpg_do_ioctl(struct block_device *bdev, switch (op) { case BLKPG_ADD_PARTITION: - /* check if partition is aligned to blocksize */ - if (p.start & (bdev_logical_block_size(bdev) - 1)) - return -EINVAL; return bdev_add_partition(bdev, p.pno, start, length); case BLKPG_RESIZE_PARTITION: return bdev_resize_partition(bdev, p.pno, start, length); @@ -405,6 +408,11 @@ static int blkdev_roset(struct block_device *bdev, fmode_t mode, return ret; if (get_user(n, (int __user *)arg)) return -EFAULT; + if (bdev->bd_disk->fops->set_read_only) { + ret = bdev->bd_disk->fops->set_read_only(bdev, n); + if (ret) + return ret; + } set_device_ro(bdev, n); return 0; } diff --git a/block/opal_proto.h b/block/opal_proto.h index b486b3ec7..a50191bdd 100644 --- a/block/opal_proto.h +++ b/block/opal_proto.h @@ -66,6 +66,7 @@ enum opal_response_token { #define SHORT_ATOM_BYTE 0xBF #define MEDIUM_ATOM_BYTE 0xDF #define LONG_ATOM_BYTE 0xE3 +#define EMPTY_ATOM_BYTE 0xFF #define OPAL_INVAL_PARAM 12 #define OPAL_MANUFACTURED_INACTIVE 0x08 diff --git a/block/sed-opal.c b/block/sed-opal.c index 0ac5a4f3f..00e4d23ac 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -895,16 +895,20 @@ static int response_parse(const u8 *buf, size_t length, token_length = response_parse_medium(iter, pos); else if (pos[0] <= LONG_ATOM_BYTE) /* long atom */ token_length = response_parse_long(iter, pos); + else if (pos[0] == EMPTY_ATOM_BYTE) /* empty atom */ + token_length = 1; else /* TOKEN */ token_length = response_parse_token(iter, pos); if (token_length < 0) return token_length; + if (pos[0] != EMPTY_ATOM_BYTE) + num_entries++; + pos += token_length; total -= token_length; iter++; - num_entries++; } resp->num = num_entries; diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c index 63c5444f0..7598778cf 100644 --- a/drivers/accessibility/speakup/main.c +++ b/drivers/accessibility/speakup/main.c @@ -576,7 +576,7 @@ static u_long get_word(struct vc_data *vc) } attr_ch = get_char(vc, (u_short *)tmp_pos, &spk_attr); buf[cnt++] = attr_ch; - while (tmpx < vc->vc_cols - 1) { + while (tmpx < vc->vc_cols - 1 && cnt < sizeof(buf) - 1) { tmp_pos += 2; tmpx++; ch = get_char(vc, (u_short *)tmp_pos, &temp); diff --git a/drivers/accessibility/speakup/synth.c b/drivers/accessibility/speakup/synth.c index ac47dbac7..82cfc5ec6 100644 --- a/drivers/accessibility/speakup/synth.c +++ b/drivers/accessibility/speakup/synth.c @@ -208,8 +208,10 @@ void spk_do_flush(void) wake_up_process(speakup_task); } -void synth_write(const char *buf, size_t count) +void synth_write(const char *_buf, size_t count) { + const unsigned char *buf = (const unsigned char *) _buf; + while (count--) synth_buffer_add(*buf++); synth_start(); diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c index 088db2356..0a84d5afd 100644 --- a/drivers/acpi/acpi_extlog.c +++ b/drivers/acpi/acpi_extlog.c @@ -308,9 +308,10 @@ err: static void __exit extlog_exit(void) { mce_unregister_decode_chain(&extlog_mce_dec); - ((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN; - if (extlog_l1_addr) + if (extlog_l1_addr) { + ((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN; acpi_os_unmap_iomem(extlog_l1_addr, l1_size); + } if (elog_addr) acpi_os_unmap_iomem(elog_addr, elog_size); release_mem_region(elog_base, elog_size); diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 9d3846563..b2364ac45 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -568,6 +568,15 @@ static const struct dmi_system_id video_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 3350"), }, }, + { + .callback = video_set_report_key_events, + .driver_data = (void *)((uintptr_t)REPORT_BRIGHTNESS_KEY_EVENTS), + .ident = "COLORFUL X15 AT 23", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "COLORFUL"), + DMI_MATCH(DMI_PRODUCT_NAME, "X15 AT 23"), + }, + }, /* * Some machines change the brightness themselves when a brightness * hotkey gets pressed, despite us telling them not to. In this case diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c index b91155ea9..c9131259f 100644 --- a/drivers/acpi/acpica/dbnames.c +++ b/drivers/acpi/acpica/dbnames.c @@ -550,8 +550,12 @@ acpi_db_walk_for_fields(acpi_handle obj_handle, ACPI_FREE(buffer.pointer); buffer.length = ACPI_ALLOCATE_LOCAL_BUFFER; - acpi_evaluate_object(obj_handle, NULL, NULL, &buffer); - + status = acpi_evaluate_object(obj_handle, NULL, NULL, &buffer); + if (ACPI_FAILURE(status)) { + acpi_os_printf("Could Not evaluate object %p\n", + obj_handle); + return (AE_OK); + } /* * Since this is a field unit, surround the output in braces */ diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 8678e1621..160606af8 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -100,6 +100,20 @@ static inline bool is_hest_type_generic_v2(struct ghes *ghes) } /* + * A platform may describe one error source for the handling of synchronous + * errors (e.g. MCE or SEA), or for handling asynchronous errors (e.g. SCI + * or External Interrupt). On x86, the HEST notifications are always + * asynchronous, so only SEA on ARM is delivered as a synchronous + * notification. + */ +static inline bool is_hest_sync_notify(struct ghes *ghes) +{ + u8 notify_type = ghes->generic->notify.type; + + return notify_type == ACPI_HEST_NOTIFY_SEA; +} + +/* * This driver isn't really modular, however for the time being, * continuing to use module_param is the easiest way to remain * compatible with existing boot arg use cases. @@ -461,7 +475,7 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags) } static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, - int sev) + int sev, bool sync) { int flags = -1; int sec_sev = ghes_severity(gdata->error_severity); @@ -475,7 +489,7 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED)) flags = MF_SOFT_OFFLINE; if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE) - flags = 0; + flags = sync ? MF_ACTION_REQUIRED : 0; if (flags != -1) return ghes_do_memory_failure(mem_err->physical_addr, flags); @@ -483,9 +497,11 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, return false; } -static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev) +static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, + int sev, bool sync) { struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata); + int flags = sync ? MF_ACTION_REQUIRED : 0; bool queued = false; int sec_sev, i; char *p; @@ -510,7 +526,7 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int s * and don't filter out 'corrected' error here. */ if (is_cache && has_pa) { - queued = ghes_do_memory_failure(err_info->physical_fault_addr, 0); + queued = ghes_do_memory_failure(err_info->physical_fault_addr, flags); p += err_info->length; continue; } @@ -631,6 +647,7 @@ static bool ghes_do_proc(struct ghes *ghes, const guid_t *fru_id = &guid_null; char *fru_text = ""; bool queued = false; + bool sync = is_hest_sync_notify(ghes); sev = ghes_severity(estatus->error_severity); apei_estatus_for_each_section(estatus, gdata) { @@ -648,13 +665,13 @@ static bool ghes_do_proc(struct ghes *ghes, ghes_edac_report_mem_error(sev, mem_err); arch_apei_report_mem_error(sev, mem_err); - queued = ghes_handle_memory_failure(gdata, sev); + queued = ghes_handle_memory_failure(gdata, sev, sync); } else if (guid_equal(sec_type, &CPER_SEC_PCIE)) { ghes_handle_aer(gdata); } else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) { - queued = ghes_handle_arm_hw_error(gdata, sev); + queued = ghes_handle_arm_hw_error(gdata, sev, sync); } else { void *err = acpi_hest_get_payload(gdata); diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 59781e765..3deeabb27 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -1427,6 +1427,8 @@ int acpi_processor_power_exit(struct acpi_processor *pr) acpi_processor_registered--; if (acpi_processor_registered == 0) cpuidle_unregister_driver(&acpi_idle_driver); + + kfree(dev); } pr->flags.power_setup_done = 0; diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 67a5ee2fe..f17f48bc1 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -321,18 +321,14 @@ static int acpi_scan_device_check(struct acpi_device *adev) * again). */ if (adev->handler) { - dev_warn(&adev->dev, "Already enumerated\n"); - return -EALREADY; + dev_dbg(&adev->dev, "Already enumerated\n"); + return 0; } error = acpi_bus_scan(adev->handle); if (error) { dev_warn(&adev->dev, "Namespace scan failure\n"); return error; } - if (!adev->handler) { - dev_warn(&adev->dev, "Enumeration failure\n"); - error = -ENODEV; - } } else { error = acpi_scan_device_not_present(adev); } diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 097a5b5f4..e79c004ca 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -385,18 +385,6 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "20GGA00L00"), }, }, - /* - * ASUS B1400CEAE hangs on resume from suspend (see - * https://bugzilla.kernel.org/show_bug.cgi?id=215742). - */ - { - .callback = init_default_s3, - .ident = "ASUS B1400CEAE", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK B1400CEAE"), - }, - }, {}, }; diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 7db748cfc..bcbaa4d6a 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -836,6 +836,16 @@ binder_enqueue_thread_work_ilocked(struct binder_thread *thread, { WARN_ON(!list_empty(&thread->waiting_thread_node)); binder_enqueue_work_ilocked(work, &thread->todo); + + /* (e)poll-based threads require an explicit wakeup signal when + * queuing their own work; they rely on these events to consume + * messages without I/O block. Without it, threads risk waiting + * indefinitely without handling the work. + */ + if (thread->looper & BINDER_LOOPER_STATE_POLL && + thread->pid == current->pid && !thread->process_todo) + wake_up_interruptible_sync(&thread->wait); + thread->process_todo = true; } @@ -2032,8 +2042,10 @@ static size_t binder_get_object(struct binder_proc *proc, size_t object_size = 0; read_size = min_t(size_t, sizeof(*object), buffer->data_size - offset); - if (offset > buffer->data_size || read_size < sizeof(*hdr)) + if (offset > buffer->data_size || read_size < sizeof(*hdr) || + !IS_ALIGNED(offset, sizeof(u32))) return 0; + if (u) { if (copy_from_user(object, u + offset, read_size)) return 0; diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 4297a8d69..55a07dbe1 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -49,6 +49,7 @@ enum { enum board_ids { /* board IDs by feature in alphabetical order */ board_ahci, + board_ahci_43bit_dma, board_ahci_ign_iferr, board_ahci_low_power, board_ahci_no_debounce_delay, @@ -129,6 +130,13 @@ static const struct ata_port_info ahci_port_info[] = { .udma_mask = ATA_UDMA6, .port_ops = &ahci_ops, }, + [board_ahci_43bit_dma] = { + AHCI_HFLAGS (AHCI_HFLAG_43BIT_ONLY), + .flags = AHCI_FLAG_COMMON, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_ops, + }, [board_ahci_ign_iferr] = { AHCI_HFLAGS (AHCI_HFLAG_IGN_IRQ_IF_ERR), .flags = AHCI_FLAG_COMMON, @@ -594,11 +602,11 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(PROMISE, 0x3f20), board_ahci }, /* PDC42819 */ { PCI_VDEVICE(PROMISE, 0x3781), board_ahci }, /* FastTrak TX8660 ahci-mode */ - /* Asmedia */ + /* ASMedia */ { PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci }, /* ASM1060 */ { PCI_VDEVICE(ASMEDIA, 0x0602), board_ahci }, /* ASM1060 */ - { PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci }, /* ASM1061 */ - { PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci }, /* ASM1062 */ + { PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci_43bit_dma }, /* ASM1061 */ + { PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci_43bit_dma }, /* ASM1061/1062 */ { PCI_VDEVICE(ASMEDIA, 0x0621), board_ahci }, /* ASM1061R */ { PCI_VDEVICE(ASMEDIA, 0x0622), board_ahci }, /* ASM1062R */ @@ -946,11 +954,20 @@ static int ahci_pci_device_resume(struct device *dev) #endif /* CONFIG_PM */ -static int ahci_configure_dma_masks(struct pci_dev *pdev, int using_dac) +static int ahci_configure_dma_masks(struct pci_dev *pdev, + struct ahci_host_priv *hpriv) { - const int dma_bits = using_dac ? 64 : 32; + int dma_bits; int rc; + if (hpriv->cap & HOST_CAP_64) { + dma_bits = 64; + if (hpriv->flags & AHCI_HFLAG_43BIT_ONLY) + dma_bits = 43; + } else { + dma_bits = 32; + } + /* * If the device fixup already set the dma_mask to some non-standard * value, don't extend it here. This happens on STA2X11, for example. @@ -1928,7 +1945,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) ahci_gtf_filter_workaround(host); /* initialize adapter */ - rc = ahci_configure_dma_masks(pdev, hpriv->cap & HOST_CAP_64); + rc = ahci_configure_dma_masks(pdev, hpriv); if (rc) return rc; diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 7cc6feb17..b8db2b0d7 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -244,6 +244,7 @@ enum { AHCI_HFLAG_IGN_NOTSUPP_POWER_ON = BIT(27), /* ignore -EOPNOTSUPP from phy_power_on() */ AHCI_HFLAG_NO_SXS = BIT(28), /* SXS not supported */ + AHCI_HFLAG_43BIT_ONLY = BIT(29), /* 43bit DMA addr limit */ /* ap->flags bits */ diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 2308c2be8..48130b254 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -1607,7 +1607,7 @@ static unsigned int ata_eh_analyze_tf(struct ata_queued_cmd *qc, } if (qc->flags & ATA_QCFLAG_SENSE_VALID) { - int ret = scsi_check_sense(qc->scsicmd); + enum scsi_disposition ret = scsi_check_sense(qc->scsicmd); /* * SUCCESS here means that the sense code could be * evaluated and should be passed to the upper layers diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index 11be88f70..cede4b517 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -783,37 +783,6 @@ static const struct ata_port_info mv_port_info[] = { }, }; -static const struct pci_device_id mv_pci_tbl[] = { - { PCI_VDEVICE(MARVELL, 0x5040), chip_504x }, - { PCI_VDEVICE(MARVELL, 0x5041), chip_504x }, - { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 }, - { PCI_VDEVICE(MARVELL, 0x5081), chip_508x }, - /* RocketRAID 1720/174x have different identifiers */ - { PCI_VDEVICE(TTI, 0x1720), chip_6042 }, - { PCI_VDEVICE(TTI, 0x1740), chip_6042 }, - { PCI_VDEVICE(TTI, 0x1742), chip_6042 }, - - { PCI_VDEVICE(MARVELL, 0x6040), chip_604x }, - { PCI_VDEVICE(MARVELL, 0x6041), chip_604x }, - { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 }, - { PCI_VDEVICE(MARVELL, 0x6080), chip_608x }, - { PCI_VDEVICE(MARVELL, 0x6081), chip_608x }, - - { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x }, - - /* Adaptec 1430SA */ - { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 }, - - /* Marvell 7042 support */ - { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 }, - - /* Highpoint RocketRAID PCIe series */ - { PCI_VDEVICE(TTI, 0x2300), chip_7042 }, - { PCI_VDEVICE(TTI, 0x2310), chip_7042 }, - - { } /* terminate list */ -}; - static const struct mv_hw_ops mv5xxx_ops = { .phy_errata = mv5_phy_errata, .enable_leds = mv5_enable_leds, @@ -4307,6 +4276,36 @@ static int mv_pci_init_one(struct pci_dev *pdev, static int mv_pci_device_resume(struct pci_dev *pdev); #endif +static const struct pci_device_id mv_pci_tbl[] = { + { PCI_VDEVICE(MARVELL, 0x5040), chip_504x }, + { PCI_VDEVICE(MARVELL, 0x5041), chip_504x }, + { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 }, + { PCI_VDEVICE(MARVELL, 0x5081), chip_508x }, + /* RocketRAID 1720/174x have different identifiers */ + { PCI_VDEVICE(TTI, 0x1720), chip_6042 }, + { PCI_VDEVICE(TTI, 0x1740), chip_6042 }, + { PCI_VDEVICE(TTI, 0x1742), chip_6042 }, + + { PCI_VDEVICE(MARVELL, 0x6040), chip_604x }, + { PCI_VDEVICE(MARVELL, 0x6041), chip_604x }, + { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 }, + { PCI_VDEVICE(MARVELL, 0x6080), chip_608x }, + { PCI_VDEVICE(MARVELL, 0x6081), chip_608x }, + + { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x }, + + /* Adaptec 1430SA */ + { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 }, + + /* Marvell 7042 support */ + { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 }, + + /* Highpoint RocketRAID PCIe series */ + { PCI_VDEVICE(TTI, 0x2300), chip_7042 }, + { PCI_VDEVICE(TTI, 0x2310), chip_7042 }, + + { } /* terminate list */ +}; static struct pci_driver mv_pci_driver = { .name = DRV_NAME, @@ -4319,6 +4318,7 @@ static struct pci_driver mv_pci_driver = { #endif }; +MODULE_DEVICE_TABLE(pci, mv_pci_tbl); /** * mv_print_info - Dump key info to kernel log for perusal. @@ -4491,7 +4491,6 @@ static void __exit mv_exit(void) MODULE_AUTHOR("Brett Russ"); MODULE_DESCRIPTION("SCSI low-level driver for Marvell SATA controllers"); MODULE_LICENSE("GPL v2"); -MODULE_DEVICE_TABLE(pci, mv_pci_tbl); MODULE_VERSION(DRV_VERSION); MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c index 4c01190a5..c95685f69 100644 --- a/drivers/ata/sata_sx4.c +++ b/drivers/ata/sata_sx4.c @@ -1004,8 +1004,7 @@ static void pdc20621_get_from_dimm(struct ata_host *host, void *psource, offset -= (idx * window_size); idx++; - dist = ((long) (window_size - (offset + size))) >= 0 ? size : - (long) (window_size - offset); + dist = min(size, window_size - offset); memcpy_fromio(psource, dimm_mmio + offset / 4, dist); psource += dist; @@ -1053,8 +1052,7 @@ static void pdc20621_put_to_dimm(struct ata_host *host, void *psource, readl(mmio + PDC_DIMM_WINDOW_CTLR); offset -= (idx * window_size); idx++; - dist = ((long)(s32)(window_size - (offset + size))) >= 0 ? size : - (long) (window_size - offset); + dist = min(size, window_size - offset); memcpy_toio(dimm_mmio + offset / 4, psource, dist); writel(0x01, mmio + PDC_GENERAL_CTLR); readl(mmio + PDC_GENERAL_CTLR); diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index a217b5043..e616e33c8 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -2936,6 +2936,8 @@ open_card_ubr0(struct idt77252_dev *card) vc->scq = alloc_scq(card, vc->class); if (!vc->scq) { printk("%s: can't get SCQ.\n", card->name); + kfree(card->vcs[0]); + card->vcs[0] = NULL; return -ENOMEM; } diff --git a/drivers/base/core.c b/drivers/base/core.c index d98cab88c..2c978941b 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -53,6 +53,7 @@ static unsigned int defer_sync_state_count = 1; static unsigned int defer_fw_devlink_count; static LIST_HEAD(deferred_fw_devlink); static DEFINE_MUTEX(defer_fw_devlink_lock); +static struct workqueue_struct *device_link_wq; static bool fw_devlink_is_permissive(void); #ifdef CONFIG_SRCU @@ -364,12 +365,26 @@ static void devlink_dev_release(struct device *dev) /* * It may take a while to complete this work because of the SRCU * synchronization in device_link_release_fn() and if the consumer or - * supplier devices get deleted when it runs, so put it into the "long" - * workqueue. + * supplier devices get deleted when it runs, so put it into the + * dedicated workqueue. */ - queue_work(system_long_wq, &link->rm_work); + queue_work(device_link_wq, &link->rm_work); } +/** + * device_link_wait_removal - Wait for ongoing devlink removal jobs to terminate + */ +void device_link_wait_removal(void) +{ + /* + * devlink removal jobs are queued in the dedicated work queue. + * To be sure that all removal jobs are terminated, ensure that any + * scheduled work has run to completion. + */ + flush_workqueue(device_link_wq); +} +EXPORT_SYMBOL_GPL(device_link_wait_removal); + static struct class devlink_class = { .name = "devlink", .owner = THIS_MODULE, @@ -3415,9 +3430,14 @@ int __init devices_init(void) sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj); if (!sysfs_dev_char_kobj) goto char_kobj_err; + device_link_wq = alloc_workqueue("device_link_wq", 0, 0); + if (!device_link_wq) + goto wq_err; return 0; + wq_err: + kobject_put(sysfs_dev_char_kobj); char_kobj_err: kobject_put(sysfs_dev_block_kobj); block_kobj_err: diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 2db1e0e8c..e3aed8333 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -591,6 +591,12 @@ ssize_t __weak cpu_show_spec_rstack_overflow(struct device *dev, return sysfs_emit(buf, "Not affected\n"); } +ssize_t __weak cpu_show_reg_file_data_sampling(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); @@ -604,6 +610,7 @@ static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL); +static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -619,6 +626,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_retbleed.attr, &dev_attr_gather_data_sampling.attr, &dev_attr_spec_rstack_overflow.attr, + &dev_attr_reg_file_data_sampling.attr, NULL }; diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 8a90f08c9..f5a032b6b 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -958,7 +958,7 @@ static int __init genpd_power_off_unused(void) return 0; } -late_initcall(genpd_power_off_unused); +late_initcall_sync(genpd_power_off_unused); #ifdef CONFIG_PM_SLEEP diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 1dbaaddf5..fbc57c4fc 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -16,6 +16,7 @@ */ #define pr_fmt(fmt) "PM: " fmt +#define dev_fmt pr_fmt #include <linux/device.h> #include <linux/export.h> @@ -449,8 +450,8 @@ static void pm_dev_dbg(struct device *dev, pm_message_t state, const char *info) static void pm_dev_err(struct device *dev, pm_message_t state, const char *info, int error) { - pr_err("Device %s failed to %s%s: error %d\n", - dev_name(dev), pm_verb(state.event), info, error); + dev_err(dev, "failed to %s%s: error %d\n", pm_verb(state.event), info, + error); } static void dpm_show_time(ktime_t starttime, pm_message_t state, int error, @@ -582,7 +583,7 @@ bool dev_pm_skip_resume(struct device *dev) } /** - * device_resume_noirq - Execute a "noirq resume" callback for given device. + * __device_resume_noirq - Execute a "noirq resume" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. @@ -590,7 +591,7 @@ bool dev_pm_skip_resume(struct device *dev) * The driver of @dev will not receive interrupts while this function is being * executed. */ -static int device_resume_noirq(struct device *dev, pm_message_t state, bool async) +static void __device_resume_noirq(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -658,7 +659,13 @@ Skip: Out: complete_all(&dev->power.completion); TRACE_RESUME(error); - return error; + + if (error) { + suspend_stats.failed_resume_noirq++; + dpm_save_failed_step(SUSPEND_RESUME_NOIRQ); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async noirq" : " noirq", error); + } } static bool is_async(struct device *dev) @@ -671,27 +678,35 @@ static bool dpm_async_fn(struct device *dev, async_func_t func) { reinit_completion(&dev->power.completion); - if (is_async(dev)) { - get_device(dev); - async_schedule_dev(func, dev); + if (!is_async(dev)) + return false; + + get_device(dev); + + if (async_schedule_dev_nocall(func, dev)) return true; - } + + put_device(dev); return false; } static void async_resume_noirq(void *data, async_cookie_t cookie) { - struct device *dev = (struct device *)data; - int error; - - error = device_resume_noirq(dev, pm_transition, true); - if (error) - pm_dev_err(dev, pm_transition, " async", error); + struct device *dev = data; + __device_resume_noirq(dev, pm_transition, true); put_device(dev); } +static void device_resume_noirq(struct device *dev) +{ + if (dpm_async_fn(dev, async_resume_noirq)) + return; + + __device_resume_noirq(dev, pm_transition, false); +} + static void dpm_noirq_resume_devices(pm_message_t state) { struct device *dev; @@ -701,34 +716,18 @@ static void dpm_noirq_resume_devices(pm_message_t state) mutex_lock(&dpm_list_mtx); pm_transition = state; - /* - * Advanced the async threads upfront, - * in case the starting of async threads is - * delayed by non-async resuming devices. - */ - list_for_each_entry(dev, &dpm_noirq_list, power.entry) - dpm_async_fn(dev, async_resume_noirq); - while (!list_empty(&dpm_noirq_list)) { dev = to_device(dpm_noirq_list.next); get_device(dev); list_move_tail(&dev->power.entry, &dpm_late_early_list); + mutex_unlock(&dpm_list_mtx); - if (!is_async(dev)) { - int error; + device_resume_noirq(dev); - error = device_resume_noirq(dev, state, false); - if (error) { - suspend_stats.failed_resume_noirq++; - dpm_save_failed_step(SUSPEND_RESUME_NOIRQ); - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, state, " noirq", error); - } - } + put_device(dev); mutex_lock(&dpm_list_mtx); - put_device(dev); } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); @@ -754,14 +753,14 @@ void dpm_resume_noirq(pm_message_t state) } /** - * device_resume_early - Execute an "early resume" callback for given device. + * __device_resume_early - Execute an "early resume" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. * * Runtime PM is disabled for @dev while this function is being executed. */ -static int device_resume_early(struct device *dev, pm_message_t state, bool async) +static void __device_resume_early(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -814,21 +813,31 @@ Out: pm_runtime_enable(dev); complete_all(&dev->power.completion); - return error; + + if (error) { + suspend_stats.failed_resume_early++; + dpm_save_failed_step(SUSPEND_RESUME_EARLY); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async early" : " early", error); + } } static void async_resume_early(void *data, async_cookie_t cookie) { - struct device *dev = (struct device *)data; - int error; - - error = device_resume_early(dev, pm_transition, true); - if (error) - pm_dev_err(dev, pm_transition, " async", error); + struct device *dev = data; + __device_resume_early(dev, pm_transition, true); put_device(dev); } +static void device_resume_early(struct device *dev) +{ + if (dpm_async_fn(dev, async_resume_early)) + return; + + __device_resume_early(dev, pm_transition, false); +} + /** * dpm_resume_early - Execute "early resume" callbacks for all devices. * @state: PM transition of the system being carried out. @@ -842,33 +851,18 @@ void dpm_resume_early(pm_message_t state) mutex_lock(&dpm_list_mtx); pm_transition = state; - /* - * Advanced the async threads upfront, - * in case the starting of async threads is - * delayed by non-async resuming devices. - */ - list_for_each_entry(dev, &dpm_late_early_list, power.entry) - dpm_async_fn(dev, async_resume_early); - while (!list_empty(&dpm_late_early_list)) { dev = to_device(dpm_late_early_list.next); get_device(dev); list_move_tail(&dev->power.entry, &dpm_suspended_list); + mutex_unlock(&dpm_list_mtx); - if (!is_async(dev)) { - int error; + device_resume_early(dev); - error = device_resume_early(dev, state, false); - if (error) { - suspend_stats.failed_resume_early++; - dpm_save_failed_step(SUSPEND_RESUME_EARLY); - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, state, " early", error); - } - } - mutex_lock(&dpm_list_mtx); put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); @@ -888,12 +882,12 @@ void dpm_resume_start(pm_message_t state) EXPORT_SYMBOL_GPL(dpm_resume_start); /** - * device_resume - Execute "resume" callbacks for given device. + * __device_resume - Execute "resume" callbacks for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. */ -static int device_resume(struct device *dev, pm_message_t state, bool async) +static void __device_resume(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -975,20 +969,30 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) TRACE_RESUME(error); - return error; + if (error) { + suspend_stats.failed_resume++; + dpm_save_failed_step(SUSPEND_RESUME); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async" : "", error); + } } static void async_resume(void *data, async_cookie_t cookie) { - struct device *dev = (struct device *)data; - int error; + struct device *dev = data; - error = device_resume(dev, pm_transition, true); - if (error) - pm_dev_err(dev, pm_transition, " async", error); + __device_resume(dev, pm_transition, true); put_device(dev); } +static void device_resume(struct device *dev) +{ + if (dpm_async_fn(dev, async_resume)) + return; + + __device_resume(dev, pm_transition, false); +} + /** * dpm_resume - Execute "resume" callbacks for non-sysdev devices. * @state: PM transition of the system being carried out. @@ -1008,30 +1012,25 @@ void dpm_resume(pm_message_t state) pm_transition = state; async_error = 0; - list_for_each_entry(dev, &dpm_suspended_list, power.entry) - dpm_async_fn(dev, async_resume); - while (!list_empty(&dpm_suspended_list)) { dev = to_device(dpm_suspended_list.next); + get_device(dev); - if (!is_async(dev)) { - int error; - mutex_unlock(&dpm_list_mtx); + mutex_unlock(&dpm_list_mtx); - error = device_resume(dev, state, false); - if (error) { - suspend_stats.failed_resume++; - dpm_save_failed_step(SUSPEND_RESUME); - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, state, "", error); - } + device_resume(dev); + + mutex_lock(&dpm_list_mtx); - mutex_lock(&dpm_list_mtx); - } if (!list_empty(&dev->power.entry)) list_move_tail(&dev->power.entry, &dpm_prepared_list); + + mutex_unlock(&dpm_list_mtx); + put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); @@ -1109,14 +1108,16 @@ void dpm_complete(pm_message_t state) get_device(dev); dev->power.is_prepared = false; list_move(&dev->power.entry, &list); + mutex_unlock(&dpm_list_mtx); trace_device_pm_callback_start(dev, "", state.event); device_complete(dev, state); trace_device_pm_callback_end(dev, 0); - mutex_lock(&dpm_list_mtx); put_device(dev); + + mutex_lock(&dpm_list_mtx); } list_splice(&list, &dpm_list); mutex_unlock(&dpm_list_mtx); @@ -1262,7 +1263,7 @@ Complete: static void async_suspend_noirq(void *data, async_cookie_t cookie) { - struct device *dev = (struct device *)data; + struct device *dev = data; int error; error = __device_suspend_noirq(dev, pm_transition, true); @@ -1301,17 +1302,21 @@ static int dpm_noirq_suspend_devices(pm_message_t state) error = device_suspend_noirq(dev); mutex_lock(&dpm_list_mtx); + if (error) { pm_dev_err(dev, state, " noirq", error); dpm_save_failed_dev(dev_name(dev)); - put_device(dev); - break; - } - if (!list_empty(&dev->power.entry)) + } else if (!list_empty(&dev->power.entry)) { list_move(&dev->power.entry, &dpm_noirq_list); + } + + mutex_unlock(&dpm_list_mtx); + put_device(dev); - if (async_error) + mutex_lock(&dpm_list_mtx); + + if (error || async_error) break; } mutex_unlock(&dpm_list_mtx); @@ -1441,7 +1446,7 @@ Complete: static void async_suspend_late(void *data, async_cookie_t cookie) { - struct device *dev = (struct device *)data; + struct device *dev = data; int error; error = __device_suspend_late(dev, pm_transition, true); @@ -1478,23 +1483,28 @@ int dpm_suspend_late(pm_message_t state) struct device *dev = to_device(dpm_suspended_list.prev); get_device(dev); + mutex_unlock(&dpm_list_mtx); error = device_suspend_late(dev); mutex_lock(&dpm_list_mtx); + if (!list_empty(&dev->power.entry)) list_move(&dev->power.entry, &dpm_late_early_list); if (error) { pm_dev_err(dev, state, " late", error); dpm_save_failed_dev(dev_name(dev)); - put_device(dev); - break; } + + mutex_unlock(&dpm_list_mtx); + put_device(dev); - if (async_error) + mutex_lock(&dpm_list_mtx); + + if (error || async_error) break; } mutex_unlock(&dpm_list_mtx); @@ -1712,7 +1722,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) static void async_suspend(void *data, async_cookie_t cookie) { - struct device *dev = (struct device *)data; + struct device *dev = data; int error; error = __device_suspend(dev, pm_transition, true); @@ -1754,21 +1764,27 @@ int dpm_suspend(pm_message_t state) struct device *dev = to_device(dpm_prepared_list.prev); get_device(dev); + mutex_unlock(&dpm_list_mtx); error = device_suspend(dev); mutex_lock(&dpm_list_mtx); + if (error) { pm_dev_err(dev, state, "", error); dpm_save_failed_dev(dev_name(dev)); - put_device(dev); - break; - } - if (!list_empty(&dev->power.entry)) + } else if (!list_empty(&dev->power.entry)) { list_move(&dev->power.entry, &dpm_suspended_list); + } + + mutex_unlock(&dpm_list_mtx); + put_device(dev); - if (async_error) + + mutex_lock(&dpm_list_mtx); + + if (error || async_error) break; } mutex_unlock(&dpm_list_mtx); @@ -1881,10 +1897,11 @@ int dpm_prepare(pm_message_t state) device_block_probing(); mutex_lock(&dpm_list_mtx); - while (!list_empty(&dpm_list)) { + while (!list_empty(&dpm_list) && !error) { struct device *dev = to_device(dpm_list.next); get_device(dev); + mutex_unlock(&dpm_list_mtx); trace_device_pm_callback_start(dev, "", state.event); @@ -1892,21 +1909,23 @@ int dpm_prepare(pm_message_t state) trace_device_pm_callback_end(dev, error); mutex_lock(&dpm_list_mtx); - if (error) { - if (error == -EAGAIN) { - put_device(dev); - error = 0; - continue; - } - pr_info("Device %s not prepared for power transition: code %d\n", - dev_name(dev), error); - put_device(dev); - break; + + if (!error) { + dev->power.is_prepared = true; + if (!list_empty(&dev->power.entry)) + list_move_tail(&dev->power.entry, &dpm_prepared_list); + } else if (error == -EAGAIN) { + error = 0; + } else { + dev_info(dev, "not prepared for power transition: code %d\n", + error); } - dev->power.is_prepared = true; - if (!list_empty(&dev->power.entry)) - list_move_tail(&dev->power.entry, &dpm_prepared_list); + + mutex_unlock(&dpm_list_mtx); + put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); trace_suspend_resume(TPS("dpm_prepare"), state.event, false); diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index fbbc3ed14..f5c9e6629 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -1479,6 +1479,28 @@ void pm_runtime_enable(struct device *dev) } EXPORT_SYMBOL_GPL(pm_runtime_enable); +static void pm_runtime_disable_action(void *data) +{ + pm_runtime_dont_use_autosuspend(data); + pm_runtime_disable(data); +} + +/** + * devm_pm_runtime_enable - devres-enabled version of pm_runtime_enable. + * + * NOTE: this will also handle calling pm_runtime_dont_use_autosuspend() for + * you at driver exit time if needed. + * + * @dev: Device to handle. + */ +int devm_pm_runtime_enable(struct device *dev) +{ + pm_runtime_enable(dev); + + return devm_add_action_or_reset(dev, pm_runtime_disable_action, dev); +} +EXPORT_SYMBOL_GPL(devm_pm_runtime_enable); + /** * pm_runtime_forbid - Block runtime PM of a device. * @dev: Device to handle. diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index aea690c64..4f4310724 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -365,8 +365,10 @@ void dev_pm_enable_wake_irq_complete(struct device *dev) return; if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED && - wirq->status & WAKE_IRQ_DEDICATED_REVERSE) + wirq->status & WAKE_IRQ_DEDICATED_REVERSE) { enable_irq(wirq->irq); + wirq->status |= WAKE_IRQ_DEDICATED_ENABLED; + } } /** diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index 0097696c3..2720d8d7b 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -104,6 +104,10 @@ struct regmap { int (*reg_write)(void *context, unsigned int reg, unsigned int val); int (*reg_update_bits)(void *context, unsigned int reg, unsigned int mask, unsigned int val); + /* Bulk read/write */ + int (*read)(void *context, const void *reg_buf, size_t reg_size, + void *val_buf, size_t val_size); + int (*write)(void *context, const void *data, size_t count); bool defer_caching; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 7bc603145..a3c408660 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -800,12 +800,15 @@ struct regmap *__regmap_init(struct device *dev, map->reg_stride_order = ilog2(map->reg_stride); else map->reg_stride_order = -1; - map->use_single_read = config->use_single_read || !bus || !bus->read; - map->use_single_write = config->use_single_write || !bus || !bus->write; - map->can_multi_write = config->can_multi_write && bus && bus->write; + map->use_single_read = config->use_single_read || !(config->read || (bus && bus->read)); + map->use_single_write = config->use_single_write || !(config->write || (bus && bus->write)); + map->can_multi_write = config->can_multi_write && (config->write || (bus && bus->write)); if (bus) { map->max_raw_read = bus->max_raw_read; map->max_raw_write = bus->max_raw_write; + } else if (config->max_raw_read && config->max_raw_write) { + map->max_raw_read = config->max_raw_read; + map->max_raw_write = config->max_raw_write; } map->dev = dev; map->bus = bus; @@ -839,9 +842,19 @@ struct regmap *__regmap_init(struct device *dev, map->read_flag_mask = bus->read_flag_mask; } - if (!bus) { + if (config && config->read && config->write) { + map->reg_read = _regmap_bus_read; + + /* Bulk read/write */ + map->read = config->read; + map->write = config->write; + + reg_endian = REGMAP_ENDIAN_NATIVE; + val_endian = REGMAP_ENDIAN_NATIVE; + } else if (!bus) { map->reg_read = config->reg_read; map->reg_write = config->reg_write; + map->reg_update_bits = config->reg_update_bits; map->defer_caching = false; goto skip_format_initialization; @@ -855,10 +868,13 @@ struct regmap *__regmap_init(struct device *dev, } else { map->reg_read = _regmap_bus_read; map->reg_update_bits = bus->reg_update_bits; - } + /* Bulk read/write */ + map->read = bus->read; + map->write = bus->write; - reg_endian = regmap_get_reg_endian(bus, config); - val_endian = regmap_get_val_endian(dev, bus, config); + reg_endian = regmap_get_reg_endian(bus, config); + val_endian = regmap_get_val_endian(dev, bus, config); + } switch (config->reg_bits + map->reg_shift) { case 2: @@ -1627,8 +1643,6 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, size_t len; int i; - WARN_ON(!map->bus); - /* Check for unwritable or noinc registers in range * before we start */ @@ -1710,7 +1724,7 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, val = work_val; } - if (map->async && map->bus->async_write) { + if (map->async && map->bus && map->bus->async_write) { struct regmap_async *async; trace_regmap_async_write_start(map, reg, val_len); @@ -1778,11 +1792,11 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, * write. */ if (val == work_val) - ret = map->bus->write(map->bus_context, map->work_buf, - map->format.reg_bytes + - map->format.pad_bytes + - val_len); - else if (map->bus->gather_write) + ret = map->write(map->bus_context, map->work_buf, + map->format.reg_bytes + + map->format.pad_bytes + + val_len); + else if (map->bus && map->bus->gather_write) ret = map->bus->gather_write(map->bus_context, map->work_buf, map->format.reg_bytes + map->format.pad_bytes, @@ -1800,7 +1814,7 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, memcpy(buf, map->work_buf, map->format.reg_bytes); memcpy(buf + map->format.reg_bytes + map->format.pad_bytes, val, val_len); - ret = map->bus->write(map->bus_context, buf, len); + ret = map->write(map->bus_context, buf, len); kfree(buf); } else if (ret != 0 && !map->cache_bypass && map->format.parse_val) { @@ -1857,7 +1871,7 @@ static int _regmap_bus_formatted_write(void *context, unsigned int reg, struct regmap_range_node *range; struct regmap *map = context; - WARN_ON(!map->bus || !map->format.format_write); + WARN_ON(!map->format.format_write); range = _regmap_range_lookup(map, reg); if (range) { @@ -1870,8 +1884,7 @@ static int _regmap_bus_formatted_write(void *context, unsigned int reg, trace_regmap_hw_write_start(map, reg, 1); - ret = map->bus->write(map->bus_context, map->work_buf, - map->format.buf_size); + ret = map->write(map->bus_context, map->work_buf, map->format.buf_size); trace_regmap_hw_write_done(map, reg, 1); @@ -1891,7 +1904,7 @@ static int _regmap_bus_raw_write(void *context, unsigned int reg, { struct regmap *map = context; - WARN_ON(!map->bus || !map->format.format_val); + WARN_ON(!map->format.format_val); map->format.format_val(map->work_buf + map->format.reg_bytes + map->format.pad_bytes, val, 0); @@ -1905,7 +1918,7 @@ static int _regmap_bus_raw_write(void *context, unsigned int reg, static inline void *_regmap_map_get_context(struct regmap *map) { - return (map->bus) ? map : map->bus_context; + return (map->bus || (!map->bus && map->read)) ? map : map->bus_context; } int _regmap_write(struct regmap *map, unsigned int reg, @@ -2312,7 +2325,7 @@ static int _regmap_raw_multi_reg_write(struct regmap *map, u8 = buf; *u8 |= map->write_flag_mask; - ret = map->bus->write(map->bus_context, buf, len); + ret = map->write(map->bus_context, buf, len); kfree(buf); @@ -2618,9 +2631,7 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, struct regmap_range_node *range; int ret; - WARN_ON(!map->bus); - - if (!map->bus || !map->bus->read) + if (!map->read) return -EINVAL; range = _regmap_range_lookup(map, reg); @@ -2636,9 +2647,9 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, map->read_flag_mask); trace_regmap_hw_read_start(map, reg, val_len / map->format.val_bytes); - ret = map->bus->read(map->bus_context, map->work_buf, - map->format.reg_bytes + map->format.pad_bytes, - val, val_len); + ret = map->read(map->bus_context, map->work_buf, + map->format.reg_bytes + map->format.pad_bytes, + val, val_len); trace_regmap_hw_read_done(map, reg, val_len / map->format.val_bytes); @@ -2749,8 +2760,6 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, unsigned int v; int ret, i; - if (!map->bus) - return -EINVAL; if (val_len % map->format.val_bytes) return -EINVAL; if (!IS_ALIGNED(reg, map->reg_stride)) @@ -2765,7 +2774,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t chunk_count, chunk_bytes; size_t chunk_regs = val_count; - if (!map->bus->read) { + if (!map->read) { ret = -ENOTSUPP; goto out; } @@ -2825,7 +2834,7 @@ EXPORT_SYMBOL_GPL(regmap_raw_read); * @val: Pointer to data buffer * @val_len: Length of output buffer in bytes. * - * The regmap API usually assumes that bulk bus read operations will read a + * The regmap API usually assumes that bulk read operations will read a * range of registers. Some devices have certain registers for which a read * operation read will read from an internal FIFO. * @@ -2843,10 +2852,6 @@ int regmap_noinc_read(struct regmap *map, unsigned int reg, size_t read_len; int ret; - if (!map->bus) - return -EINVAL; - if (!map->bus->read) - return -ENOTSUPP; if (val_len % map->format.val_bytes) return -EINVAL; if (!IS_ALIGNED(reg, map->reg_stride)) @@ -2960,7 +2965,7 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, if (val_count == 0) return -EINVAL; - if (map->bus && map->format.parse_inplace && (vol || map->cache_type == REGCACHE_NONE)) { + if (map->format.parse_inplace && (vol || map->cache_type == REGCACHE_NONE)) { ret = regmap_raw_read(map, reg, val, val_bytes * val_count); if (ret != 0) return ret; diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 313f0b946..c805909c8 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -420,13 +420,16 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu rcu_read_lock(); for_each_netdev_rcu(&init_net, ifp) { dev_hold(ifp); - if (!is_aoe_netif(ifp)) - goto cont; + if (!is_aoe_netif(ifp)) { + dev_put(ifp); + continue; + } skb = new_skb(sizeof *h + sizeof *ch); if (skb == NULL) { printk(KERN_INFO "aoe: skb alloc failure\n"); - goto cont; + dev_put(ifp); + continue; } skb_put(skb, sizeof *h + sizeof *ch); skb->dev = ifp; @@ -441,9 +444,6 @@ aoecmd_cfg_pkts(ushort aoemajor, unsigned char aoeminor, struct sk_buff_head *qu h->major = cpu_to_be16(aoemajor); h->minor = aoeminor; h->cmd = AOECMD_CFG; - -cont: - dev_put(ifp); } rcu_read_unlock(); } diff --git a/drivers/block/aoe/aoenet.c b/drivers/block/aoe/aoenet.c index 63773a905..1e66c7a18 100644 --- a/drivers/block/aoe/aoenet.c +++ b/drivers/block/aoe/aoenet.c @@ -64,6 +64,7 @@ tx(int id) __must_hold(&txlock) pr_warn("aoe: packet could not be sent on %s. %s\n", ifp ? ifp->name : "netif", "consider increasing tx_queue_len"); + dev_put(ifp); spin_lock_irq(&txlock); } return 0; diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index 3e881fdb0..224450c90 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -456,10 +456,20 @@ static DEFINE_TIMER(fd_timer, check_change); static void fd_end_request_cur(blk_status_t err) { + DPRINT(("fd_end_request_cur(), bytes %d of %d\n", + blk_rq_cur_bytes(fd_request), + blk_rq_bytes(fd_request))); + if (!blk_update_request(fd_request, err, blk_rq_cur_bytes(fd_request))) { + DPRINT(("calling __blk_mq_end_request()\n")); __blk_mq_end_request(fd_request, err); fd_request = NULL; + } else { + /* requeue rest of request */ + DPRINT(("calling blk_mq_requeue_request()\n")); + blk_mq_requeue_request(fd_request, true); + fd_request = NULL; } } @@ -653,9 +663,6 @@ static inline void copy_buffer(void *from, void *to) *p2++ = *p1++; } - - - /* General Interrupt Handling */ static void (*FloppyIRQHandler)( int status ) = NULL; @@ -700,12 +707,21 @@ static void fd_error( void ) if (fd_request->error_count >= MAX_ERRORS) { printk(KERN_ERR "fd%d: too many errors.\n", SelectedDrive ); fd_end_request_cur(BLK_STS_IOERR); + finish_fdc(); + return; } else if (fd_request->error_count == RECALIBRATE_ERRORS) { printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive ); if (SelectedDrive != -1) SUD.track = -1; } + /* need to re-run request to recalibrate */ + atari_disable_irq( IRQ_MFP_FDC ); + + setup_req_params( SelectedDrive ); + do_fd_action( SelectedDrive ); + + atari_enable_irq( IRQ_MFP_FDC ); } @@ -740,6 +756,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) if (type) { if (--type >= NUM_DISK_MINORS || minor2disktype[type].drive_types > DriveType) { + finish_fdc(); ret = -EINVAL; goto out; } @@ -748,6 +765,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) } if (!UDT || desc->track >= UDT->blocks/UDT->spt/2 || desc->head >= 2) { + finish_fdc(); ret = -EINVAL; goto out; } @@ -788,6 +806,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) wait_for_completion(&format_wait); + finish_fdc(); ret = FormatError ? -EIO : 0; out: blk_mq_unquiesce_queue(q); @@ -822,6 +841,7 @@ static void do_fd_action( int drive ) else { /* all sectors finished */ fd_end_request_cur(BLK_STS_OK); + finish_fdc(); return; } } @@ -1226,6 +1246,7 @@ static void fd_rwsec_done1(int status) else { /* all sectors finished */ fd_end_request_cur(BLK_STS_OK); + finish_fdc(); } return; @@ -1347,7 +1368,7 @@ static void fd_times_out(struct timer_list *unused) static void finish_fdc( void ) { - if (!NeedSeek) { + if (!NeedSeek || !stdma_is_locked_by(floppy_irq)) { finish_fdc_done( 0 ); } else { @@ -1382,7 +1403,8 @@ static void finish_fdc_done( int dummy ) start_motor_off_timer(); local_irq_save(flags); - stdma_release(); + if (stdma_is_locked_by(floppy_irq)) + stdma_release(); local_irq_restore(flags); DPRINT(("finish_fdc() finished\n")); @@ -1472,15 +1494,6 @@ static void setup_req_params( int drive ) ReqTrack, ReqSector, (unsigned long)ReqData )); } -static void ataflop_commit_rqs(struct blk_mq_hw_ctx *hctx) -{ - spin_lock_irq(&ataflop_lock); - atari_disable_irq(IRQ_MFP_FDC); - finish_fdc(); - atari_enable_irq(IRQ_MFP_FDC); - spin_unlock_irq(&ataflop_lock); -} - static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -1488,6 +1501,10 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, int drive = floppy - unit; int type = floppy->type; + DPRINT(("Queue request: drive %d type %d sectors %d of %d last %d\n", + drive, type, blk_rq_cur_sectors(bd->rq), + blk_rq_sectors(bd->rq), bd->last)); + spin_lock_irq(&ataflop_lock); if (fd_request) { spin_unlock_irq(&ataflop_lock); @@ -1508,6 +1525,7 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, /* drive not connected */ printk(KERN_ERR "Unknown Device: fd%d\n", drive ); fd_end_request_cur(BLK_STS_IOERR); + stdma_release(); goto out; } @@ -1524,11 +1542,13 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, if (--type >= NUM_DISK_MINORS) { printk(KERN_WARNING "fd%d: invalid disk format", drive ); fd_end_request_cur(BLK_STS_IOERR); + stdma_release(); goto out; } if (minor2disktype[type].drive_types > DriveType) { printk(KERN_WARNING "fd%d: unsupported disk format", drive ); fd_end_request_cur(BLK_STS_IOERR); + stdma_release(); goto out; } type = minor2disktype[type].index; @@ -1547,8 +1567,6 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, setup_req_params( drive ); do_fd_action( drive ); - if (bd->last) - finish_fdc(); atari_enable_irq( IRQ_MFP_FDC ); out: @@ -1631,6 +1649,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, /* what if type > 0 here? Overwrite specified entry ? */ if (type) { /* refuse to re-set a predefined type for now */ + finish_fdc(); return -EINVAL; } @@ -1698,8 +1717,10 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, /* sanity check */ if (setprm.track != dtp->blocks/dtp->spt/2 || - setprm.head != 2) + setprm.head != 2) { + finish_fdc(); return -EINVAL; + } UDT = dtp; set_capacity(floppy->disk, UDT->blocks); @@ -1959,7 +1980,6 @@ static const struct block_device_operations floppy_fops = { static const struct blk_mq_ops ataflop_mq_ops = { .queue_rq = ataflop_queue_rq, - .commit_rqs = ataflop_commit_rqs, }; static struct kobject *floppy_find(dev_t dev, int *part, void *data) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index e0f805ca0..d6e3edb40 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -2339,6 +2339,12 @@ static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info) } dev_list = nla_nest_start_noflag(reply, NBD_ATTR_DEVICE_LIST); + if (!dev_list) { + nlmsg_free(reply); + ret = -EMSGSIZE; + goto out; + } + if (index == -1) { ret = idr_for_each(&nbd_index_idr, &status_cb, reply); if (ret) { diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index b0f793052..5b102d333 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3517,14 +3517,15 @@ static bool rbd_lock_add_request(struct rbd_img_request *img_req) static void rbd_lock_del_request(struct rbd_img_request *img_req) { struct rbd_device *rbd_dev = img_req->rbd_dev; - bool need_wakeup; + bool need_wakeup = false; lockdep_assert_held(&rbd_dev->lock_rwsem); spin_lock(&rbd_dev->lock_lists_lock); - rbd_assert(!list_empty(&img_req->lock_item)); - list_del_init(&img_req->lock_item); - need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING && - list_empty(&rbd_dev->running_list)); + if (!list_empty(&img_req->lock_item)) { + list_del_init(&img_req->lock_item); + need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING && + list_empty(&rbd_dev->running_list)); + } spin_unlock(&rbd_dev->lock_lists_lock); if (need_wakeup) complete(&rbd_dev->releasing_wait); @@ -3907,14 +3908,19 @@ static void wake_lock_waiters(struct rbd_device *rbd_dev, int result) return; } - list_for_each_entry(img_req, &rbd_dev->acquiring_list, lock_item) { + while (!list_empty(&rbd_dev->acquiring_list)) { + img_req = list_first_entry(&rbd_dev->acquiring_list, + struct rbd_img_request, lock_item); mutex_lock(&img_req->state_mutex); rbd_assert(img_req->state == RBD_IMG_EXCLUSIVE_LOCK); + if (!result) + list_move_tail(&img_req->lock_item, + &rbd_dev->running_list); + else + list_del_init(&img_req->lock_item); rbd_img_schedule(img_req, result); mutex_unlock(&img_req->state_mutex); } - - list_splice_tail_init(&rbd_dev->acquiring_list, &rbd_dev->running_list); } static bool locker_equal(const struct ceph_locker *lhs, diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c index e1bc8b4cd..9c5d52335 100644 --- a/drivers/block/rnbd/rnbd-srv.c +++ b/drivers/block/rnbd/rnbd-srv.c @@ -591,6 +591,7 @@ static char *rnbd_srv_get_full_path(struct rnbd_srv_session *srv_sess, { char *full_path; char *a, *b; + int len; full_path = kmalloc(PATH_MAX, GFP_KERNEL); if (!full_path) @@ -602,19 +603,19 @@ static char *rnbd_srv_get_full_path(struct rnbd_srv_session *srv_sess, */ a = strnstr(dev_search_path, "%SESSNAME%", sizeof(dev_search_path)); if (a) { - int len = a - dev_search_path; + len = a - dev_search_path; len = snprintf(full_path, PATH_MAX, "%.*s/%s/%s", len, dev_search_path, srv_sess->sessname, dev_name); - if (len >= PATH_MAX) { - pr_err("Too long path: %s, %s, %s\n", - dev_search_path, srv_sess->sessname, dev_name); - kfree(full_path); - return ERR_PTR(-EINVAL); - } } else { - snprintf(full_path, PATH_MAX, "%s/%s", - dev_search_path, dev_name); + len = snprintf(full_path, PATH_MAX, "%s/%s", + dev_search_path, dev_name); + } + if (len >= PATH_MAX) { + pr_err("Too long path: %s, %s, %s\n", + dev_search_path, srv_sess->sessname, dev_name); + kfree(full_path); + return ERR_PTR(-EINVAL); } /* eliminitate duplicated slashes */ diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 9b54eec9b..7eae3f373 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -952,14 +952,15 @@ static int virtblk_freeze(struct virtio_device *vdev) { struct virtio_blk *vblk = vdev->priv; + /* Ensure no requests in virtqueues before deleting vqs. */ + blk_mq_freeze_queue(vblk->disk->queue); + /* Ensure we don't receive any more interrupts */ vdev->config->reset(vdev); /* Make sure no work handler is accessing the device. */ flush_work(&vblk->config_work); - blk_mq_quiesce_queue(vblk->disk->queue); - vdev->config->del_vqs(vdev); kfree(vblk->vqs); @@ -977,7 +978,7 @@ static int virtblk_restore(struct virtio_device *vdev) virtio_device_ready(vdev); - blk_mq_unquiesce_queue(vblk->disk->queue); + blk_mq_unfreeze_queue(vblk->disk->queue); return 0; } #endif diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 88ce5f0ff..2538bdee3 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -350,7 +350,7 @@ int btintel_read_version(struct hci_dev *hdev, struct intel_version *ver) return PTR_ERR(skb); } - if (skb->len != sizeof(*ver)) { + if (!skb || skb->len != sizeof(*ver)) { bt_dev_err(hdev, "Intel version event size mismatch"); kfree_skb(skb); return -EILSEQ; diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index a1a8b282b..b2836e8ef 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -418,6 +418,8 @@ static const struct usb_device_id blacklist_table[] = { /* Realtek 8852BE Bluetooth devices */ { USB_DEVICE(0x0cb8, 0xc559), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0bda, 0x4853), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0bda, 0x887b), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0bda, 0xb85b), .driver_info = BTUSB_REALTEK | diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index bc0850d3f..6e0c0762f 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -1814,6 +1814,7 @@ static const struct qca_device_data qca_soc_data_wcn3998 = { static const struct qca_device_data qca_soc_data_qca6390 = { .soc_type = QCA_QCA6390, .num_vregs = 0, + .capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES, }; static void qca_power_shutdown(struct hci_uart *hu) diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig index 0c262c2ae..01f2349db 100644 --- a/drivers/bus/Kconfig +++ b/drivers/bus/Kconfig @@ -176,11 +176,12 @@ config SUNXI_RSB config TEGRA_ACONNECT tristate "Tegra ACONNECT Bus Driver" - depends on ARCH_TEGRA_210_SOC + depends on ARCH_TEGRA depends on OF && PM help Driver for the Tegra ACONNECT bus which is used to interface with - the devices inside the Audio Processing Engine (APE) for Tegra210. + the devices inside the Audio Processing Engine (APE) for + Tegra210 and later. config TEGRA_GMI tristate "Tegra Generic Memory Interface bus driver" diff --git a/drivers/bus/mhi/host/main.c b/drivers/bus/mhi/host/main.c index 614dd287c..49c0f5ad0 100644 --- a/drivers/bus/mhi/host/main.c +++ b/drivers/bus/mhi/host/main.c @@ -569,6 +569,8 @@ static int parse_xfer_event(struct mhi_controller *mhi_cntrl, mhi_del_ring_element(mhi_cntrl, tre_ring); local_rp = tre_ring->rp; + read_unlock_bh(&mhi_chan->lock); + /* notify client */ mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result); @@ -591,6 +593,8 @@ static int parse_xfer_event(struct mhi_controller *mhi_cntrl, kfree(buf_info->cb_buf); } } + + read_lock_bh(&mhi_chan->lock); } break; } /* CC_EOT */ diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c index b20fdcbd0..34377195b 100644 --- a/drivers/bus/moxtet.c +++ b/drivers/bus/moxtet.c @@ -832,6 +832,12 @@ static int moxtet_remove(struct spi_device *spi) return 0; } +static const struct spi_device_id moxtet_spi_ids[] = { + { "moxtet" }, + { }, +}; +MODULE_DEVICE_TABLE(spi, moxtet_spi_ids); + static const struct of_device_id moxtet_dt_ids[] = { { .compatible = "cznic,moxtet" }, {}, @@ -843,6 +849,7 @@ static struct spi_driver moxtet_spi_driver = { .name = "moxtet", .of_match_table = moxtet_dt_ids, }, + .id_table = moxtet_spi_ids, .probe = moxtet_probe, .remove = moxtet_remove, }; diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index 5749998fe..6e2c1ba18 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -24,10 +24,13 @@ #include <linux/random.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/string.h> #include <linux/uaccess.h> #define RNG_MODULE_NAME "hw_random" +#define RNG_BUFFER_SIZE (SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES) + static struct hwrng *current_rng; /* the current rng has been explicitly chosen by user via sysfs */ static int cur_rng_set_by_user; @@ -59,7 +62,7 @@ static inline int rng_get_data(struct hwrng *rng, u8 *buffer, size_t size, static size_t rng_buffer_size(void) { - return SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES; + return RNG_BUFFER_SIZE; } static void add_early_randomness(struct hwrng *rng) @@ -206,6 +209,7 @@ static inline int rng_get_data(struct hwrng *rng, u8 *buffer, size_t size, static ssize_t rng_dev_read(struct file *filp, char __user *buf, size_t size, loff_t *offp) { + u8 buffer[RNG_BUFFER_SIZE]; ssize_t ret = 0; int err = 0; int bytes_read, len; @@ -233,34 +237,37 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, if (bytes_read < 0) { err = bytes_read; goto out_unlock_reading; + } else if (bytes_read == 0 && + (filp->f_flags & O_NONBLOCK)) { + err = -EAGAIN; + goto out_unlock_reading; } + data_avail = bytes_read; } - if (!data_avail) { - if (filp->f_flags & O_NONBLOCK) { - err = -EAGAIN; - goto out_unlock_reading; - } - } else { - len = data_avail; + len = data_avail; + if (len) { if (len > size) len = size; data_avail -= len; - if (copy_to_user(buf + ret, rng_buffer + data_avail, - len)) { + memcpy(buffer, rng_buffer + data_avail, len); + } + mutex_unlock(&reading_mutex); + put_rng(rng); + + if (len) { + if (copy_to_user(buf + ret, buffer, len)) { err = -EFAULT; - goto out_unlock_reading; + goto out; } size -= len; ret += len; } - mutex_unlock(&reading_mutex); - put_rng(rng); if (need_resched()) schedule_timeout_interruptible(1); @@ -271,6 +278,7 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, } } out: + memzero_explicit(buffer, sizeof(buffer)); return ret ? : err; out_unlock_reading: diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 62572d59e..a0927c7f8 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -37,7 +37,11 @@ static HLIST_HEAD(clk_root_list); static HLIST_HEAD(clk_orphan_list); static LIST_HEAD(clk_notifier_list); -static struct hlist_head *all_lists[] = { +/* List of registered clks that use runtime PM */ +static HLIST_HEAD(clk_rpm_list); +static DEFINE_MUTEX(clk_rpm_list_lock); + +static const struct hlist_head *all_lists[] = { &clk_root_list, &clk_orphan_list, NULL, @@ -59,6 +63,7 @@ struct clk_core { struct clk_hw *hw; struct module *owner; struct device *dev; + struct hlist_node rpm_node; struct device_node *of_node; struct clk_core *parent; struct clk_parent_map *parents; @@ -129,6 +134,89 @@ static void clk_pm_runtime_put(struct clk_core *core) pm_runtime_put_sync(core->dev); } +/** + * clk_pm_runtime_get_all() - Runtime "get" all clk provider devices + * + * Call clk_pm_runtime_get() on all runtime PM enabled clks in the clk tree so + * that disabling unused clks avoids a deadlock where a device is runtime PM + * resuming/suspending and the runtime PM callback is trying to grab the + * prepare_lock for something like clk_prepare_enable() while + * clk_disable_unused_subtree() holds the prepare_lock and is trying to runtime + * PM resume/suspend the device as well. + * + * Context: Acquires the 'clk_rpm_list_lock' and returns with the lock held on + * success. Otherwise the lock is released on failure. + * + * Return: 0 on success, negative errno otherwise. + */ +static int clk_pm_runtime_get_all(void) +{ + int ret; + struct clk_core *core, *failed; + + /* + * Grab the list lock to prevent any new clks from being registered + * or unregistered until clk_pm_runtime_put_all(). + */ + mutex_lock(&clk_rpm_list_lock); + + /* + * Runtime PM "get" all the devices that are needed for the clks + * currently registered. Do this without holding the prepare_lock, to + * avoid the deadlock. + */ + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) { + ret = clk_pm_runtime_get(core); + if (ret) { + failed = core; + pr_err("clk: Failed to runtime PM get '%s' for clk '%s'\n", + dev_name(failed->dev), failed->name); + goto err; + } + } + + return 0; + +err: + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) { + if (core == failed) + break; + + clk_pm_runtime_put(core); + } + mutex_unlock(&clk_rpm_list_lock); + + return ret; +} + +/** + * clk_pm_runtime_put_all() - Runtime "put" all clk provider devices + * + * Put the runtime PM references taken in clk_pm_runtime_get_all() and release + * the 'clk_rpm_list_lock'. + */ +static void clk_pm_runtime_put_all(void) +{ + struct clk_core *core; + + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) + clk_pm_runtime_put(core); + mutex_unlock(&clk_rpm_list_lock); +} + +static void clk_pm_runtime_init(struct clk_core *core) +{ + struct device *dev = core->dev; + + if (dev && pm_runtime_enabled(dev)) { + core->rpm_enabled = true; + + mutex_lock(&clk_rpm_list_lock); + hlist_add_head(&core->rpm_node, &clk_rpm_list); + mutex_unlock(&clk_rpm_list_lock); + } +} + /*** locking ***/ static void clk_prepare_lock(void) { @@ -425,6 +513,9 @@ static struct clk_core *clk_core_get(struct clk_core *core, u8 p_index) if (IS_ERR(hw)) return ERR_CAST(hw); + if (!hw) + return NULL; + return hw->core; } @@ -1228,9 +1319,6 @@ static void __init clk_unprepare_unused_subtree(struct clk_core *core) if (core->flags & CLK_IGNORE_UNUSED) return; - if (clk_pm_runtime_get(core)) - return; - if (clk_core_is_prepared(core)) { trace_clk_unprepare(core); if (core->ops->unprepare_unused) @@ -1239,8 +1327,6 @@ static void __init clk_unprepare_unused_subtree(struct clk_core *core) core->ops->unprepare(core->hw); trace_clk_unprepare_complete(core); } - - clk_pm_runtime_put(core); } static void __init clk_disable_unused_subtree(struct clk_core *core) @@ -1256,9 +1342,6 @@ static void __init clk_disable_unused_subtree(struct clk_core *core) if (core->flags & CLK_OPS_PARENT_ENABLE) clk_core_prepare_enable(core->parent); - if (clk_pm_runtime_get(core)) - goto unprepare_out; - flags = clk_enable_lock(); if (core->enable_count) @@ -1283,8 +1366,6 @@ static void __init clk_disable_unused_subtree(struct clk_core *core) unlock_out: clk_enable_unlock(flags); - clk_pm_runtime_put(core); -unprepare_out: if (core->flags & CLK_OPS_PARENT_ENABLE) clk_core_disable_unprepare(core->parent); } @@ -1300,12 +1381,22 @@ __setup("clk_ignore_unused", clk_ignore_unused_setup); static int __init clk_disable_unused(void) { struct clk_core *core; + int ret; if (clk_ignore_unused) { pr_warn("clk: Not disabling unused clocks\n"); return 0; } + pr_info("clk: Disabling unused clocks\n"); + + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; + /* + * Grab the prepare lock to keep the clk topology stable while iterating + * over clks. + */ clk_prepare_lock(); hlist_for_each_entry(core, &clk_root_list, child_node) @@ -1322,6 +1413,8 @@ static int __init clk_disable_unused(void) clk_prepare_unlock(); + clk_pm_runtime_put_all(); + return 0; } late_initcall_sync(clk_disable_unused); @@ -3627,9 +3720,6 @@ static int __clk_core_init(struct clk_core *core) } clk_core_reparent_orphans_nolock(); - - - kref_init(&core->ref); out: clk_pm_runtime_put(core); unlock: @@ -3839,6 +3929,22 @@ static void clk_core_free_parent_map(struct clk_core *core) kfree(core->parents); } +/* Free memory allocated for a struct clk_core */ +static void __clk_release(struct kref *ref) +{ + struct clk_core *core = container_of(ref, struct clk_core, ref); + + if (core->rpm_enabled) { + mutex_lock(&clk_rpm_list_lock); + hlist_del(&core->rpm_node); + mutex_unlock(&clk_rpm_list_lock); + } + + clk_core_free_parent_map(core); + kfree_const(core->name); + kfree(core); +} + static struct clk * __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) { @@ -3859,6 +3965,8 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) goto fail_out; } + kref_init(&core->ref); + core->name = kstrdup_const(init->name, GFP_KERNEL); if (!core->name) { ret = -ENOMEM; @@ -3871,9 +3979,8 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) } core->ops = init->ops; - if (dev && pm_runtime_enabled(dev)) - core->rpm_enabled = true; core->dev = dev; + clk_pm_runtime_init(core); core->of_node = np; if (dev && dev->driver) core->owner = dev->driver->owner; @@ -3913,12 +4020,10 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) hw->clk = NULL; fail_create_clk: - clk_core_free_parent_map(core); fail_parents: fail_ops: - kfree_const(core->name); fail_name: - kfree(core); + kref_put(&core->ref, __clk_release); fail_out: return ERR_PTR(ret); } @@ -3998,18 +4103,6 @@ int of_clk_hw_register(struct device_node *node, struct clk_hw *hw) } EXPORT_SYMBOL_GPL(of_clk_hw_register); -/* Free memory allocated for a clock. */ -static void __clk_release(struct kref *ref) -{ - struct clk_core *core = container_of(ref, struct clk_core, ref); - - lockdep_assert_held(&prepare_lock); - - clk_core_free_parent_map(core); - kfree_const(core->name); - kfree(core); -} - /* * Empty clk_ops for unregistered clocks. These are used temporarily * after clk_unregister() was called on a clock and until last clock @@ -4062,7 +4155,7 @@ static void clk_core_evict_parent_cache_subtree(struct clk_core *root, /* Remove this clk from all parent caches */ static void clk_core_evict_parent_cache(struct clk_core *core) { - struct hlist_head **lists; + const struct hlist_head **lists; struct clk_core *root; lockdep_assert_held(&prepare_lock); diff --git a/drivers/clk/hisilicon/clk-hi3519.c b/drivers/clk/hisilicon/clk-hi3519.c index ad0c7f350..60d8a27a9 100644 --- a/drivers/clk/hisilicon/clk-hi3519.c +++ b/drivers/clk/hisilicon/clk-hi3519.c @@ -130,7 +130,7 @@ static void hi3519_clk_unregister(struct platform_device *pdev) of_clk_del_provider(pdev->dev.of_node); hisi_clk_unregister_gate(hi3519_gate_clks, - ARRAY_SIZE(hi3519_mux_clks), + ARRAY_SIZE(hi3519_gate_clks), crg->clk_data); hisi_clk_unregister_mux(hi3519_mux_clks, ARRAY_SIZE(hi3519_mux_clks), diff --git a/drivers/clk/hisilicon/clk-hi3620.c b/drivers/clk/hisilicon/clk-hi3620.c index a3d04c7c3..eb9c139ba 100644 --- a/drivers/clk/hisilicon/clk-hi3620.c +++ b/drivers/clk/hisilicon/clk-hi3620.c @@ -467,8 +467,10 @@ static void __init hi3620_mmc_clk_init(struct device_node *node) return; clk_data->clks = kcalloc(num, sizeof(*clk_data->clks), GFP_KERNEL); - if (!clk_data->clks) + if (!clk_data->clks) { + kfree(clk_data); return; + } for (i = 0; i < num; i++) { struct hisi_mmc_clock *mmc_clk = &hi3620_mmc_clks[i]; diff --git a/drivers/clk/mmp/clk-of-pxa168.c b/drivers/clk/mmp/clk-of-pxa168.c index f110c02e8..9674c6c06 100644 --- a/drivers/clk/mmp/clk-of-pxa168.c +++ b/drivers/clk/mmp/clk-of-pxa168.c @@ -258,18 +258,21 @@ static void __init pxa168_clk_init(struct device_node *np) pxa_unit->mpmu_base = of_iomap(np, 0); if (!pxa_unit->mpmu_base) { pr_err("failed to map mpmu registers\n"); + kfree(pxa_unit); return; } pxa_unit->apmu_base = of_iomap(np, 1); if (!pxa_unit->apmu_base) { pr_err("failed to map apmu registers\n"); + kfree(pxa_unit); return; } pxa_unit->apbc_base = of_iomap(np, 2); if (!pxa_unit->apbc_base) { pr_err("failed to map apbc registers\n"); + kfree(pxa_unit); return; } diff --git a/drivers/clk/qcom/dispcc-sdm845.c b/drivers/clk/qcom/dispcc-sdm845.c index 5c932cd17..8cd8174ac 100644 --- a/drivers/clk/qcom/dispcc-sdm845.c +++ b/drivers/clk/qcom/dispcc-sdm845.c @@ -768,6 +768,8 @@ static struct clk_branch disp_cc_mdss_vsync_clk = { static struct gdsc mdss_gdsc = { .gdscr = 0x3000, + .en_few_wait_val = 0x6, + .en_rest_wait_val = 0x5, .pd = { .name = "mdss_gdsc", }, diff --git a/drivers/clk/qcom/gcc-ipq6018.c b/drivers/clk/qcom/gcc-ipq6018.c index 4c5c7a8f4..b9844e41c 100644 --- a/drivers/clk/qcom/gcc-ipq6018.c +++ b/drivers/clk/qcom/gcc-ipq6018.c @@ -1557,6 +1557,7 @@ static struct clk_regmap_div nss_ubi0_div_clk_src = { static const struct freq_tbl ftbl_pcie_aux_clk_src[] = { F(24000000, P_XO, 1, 0, 0), + { } }; static const struct clk_parent_data gcc_xo_gpll0_core_pi_sleep_clk[] = { @@ -1737,6 +1738,7 @@ static const struct freq_tbl ftbl_sdcc_ice_core_clk_src[] = { F(160000000, P_GPLL0, 5, 0, 0), F(216000000, P_GPLL6, 5, 0, 0), F(308570000, P_GPLL6, 3.5, 0, 0), + { } }; static const struct clk_parent_data gcc_xo_gpll0_gpll6_gpll0_div2[] = { diff --git a/drivers/clk/qcom/gcc-ipq8074.c b/drivers/clk/qcom/gcc-ipq8074.c index 0393154fe..649e75a41 100644 --- a/drivers/clk/qcom/gcc-ipq8074.c +++ b/drivers/clk/qcom/gcc-ipq8074.c @@ -972,6 +972,7 @@ static struct clk_rcg2 pcie0_axi_clk_src = { static const struct freq_tbl ftbl_pcie_aux_clk_src[] = { F(19200000, P_XO, 1, 0, 0), + { } }; static struct clk_rcg2 pcie0_aux_clk_src = { @@ -1077,6 +1078,7 @@ static const struct freq_tbl ftbl_sdcc_ice_core_clk_src[] = { F(19200000, P_XO, 1, 0, 0), F(160000000, P_GPLL0, 5, 0, 0), F(308570000, P_GPLL6, 3.5, 0, 0), + { } }; static struct clk_rcg2 sdcc1_ice_core_clk_src = { diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c index 90f7febaf..a6b07aa8e 100644 --- a/drivers/clk/qcom/gcc-sdm845.c +++ b/drivers/clk/qcom/gcc-sdm845.c @@ -3646,3 +3646,4 @@ module_exit(gcc_sdm845_exit); MODULE_DESCRIPTION("QTI GCC SDM845 Driver"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("platform:gcc-sdm845"); +MODULE_SOFTDEP("pre: rpmhpd"); diff --git a/drivers/clk/qcom/mmcc-apq8084.c b/drivers/clk/qcom/mmcc-apq8084.c index fbfcf0006..c2fd0e8f4 100644 --- a/drivers/clk/qcom/mmcc-apq8084.c +++ b/drivers/clk/qcom/mmcc-apq8084.c @@ -333,6 +333,7 @@ static struct freq_tbl ftbl_mmss_axi_clk[] = { F(333430000, P_MMPLL1, 3.5, 0, 0), F(400000000, P_MMPLL0, 2, 0, 0), F(466800000, P_MMPLL1, 2.5, 0, 0), + { } }; static struct clk_rcg2 mmss_axi_clk_src = { @@ -357,6 +358,7 @@ static struct freq_tbl ftbl_ocmemnoc_clk[] = { F(150000000, P_GPLL0, 4, 0, 0), F(228570000, P_MMPLL0, 3.5, 0, 0), F(320000000, P_MMPLL0, 2.5, 0, 0), + { } }; static struct clk_rcg2 ocmemnoc_clk_src = { diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c index 015426262..dfc377463 100644 --- a/drivers/clk/qcom/mmcc-msm8974.c +++ b/drivers/clk/qcom/mmcc-msm8974.c @@ -283,6 +283,7 @@ static struct freq_tbl ftbl_mmss_axi_clk[] = { F(291750000, P_MMPLL1, 4, 0, 0), F(400000000, P_MMPLL0, 2, 0, 0), F(466800000, P_MMPLL1, 2.5, 0, 0), + { } }; static struct clk_rcg2 mmss_axi_clk_src = { @@ -307,6 +308,7 @@ static struct freq_tbl ftbl_ocmemnoc_clk[] = { F(150000000, P_GPLL0, 4, 0, 0), F(291750000, P_MMPLL1, 4, 0, 0), F(400000000, P_MMPLL0, 2, 0, 0), + { } }; static struct clk_rcg2 ocmemnoc_clk_src = { diff --git a/drivers/clk/qcom/reset.c b/drivers/clk/qcom/reset.c index e45e32804..d96c96a90 100644 --- a/drivers/clk/qcom/reset.c +++ b/drivers/clk/qcom/reset.c @@ -22,8 +22,8 @@ static int qcom_reset(struct reset_controller_dev *rcdev, unsigned long id) return 0; } -static int -qcom_reset_assert(struct reset_controller_dev *rcdev, unsigned long id) +static int qcom_reset_set_assert(struct reset_controller_dev *rcdev, + unsigned long id, bool assert) { struct qcom_reset_controller *rst; const struct qcom_reset_map *map; @@ -33,21 +33,22 @@ qcom_reset_assert(struct reset_controller_dev *rcdev, unsigned long id) map = &rst->reset_map[id]; mask = map->bitmask ? map->bitmask : BIT(map->bit); - return regmap_update_bits(rst->regmap, map->reg, mask, mask); + regmap_update_bits(rst->regmap, map->reg, mask, assert ? mask : 0); + + /* Read back the register to ensure write completion, ignore the value */ + regmap_read(rst->regmap, map->reg, &mask); + + return 0; } -static int -qcom_reset_deassert(struct reset_controller_dev *rcdev, unsigned long id) +static int qcom_reset_assert(struct reset_controller_dev *rcdev, unsigned long id) { - struct qcom_reset_controller *rst; - const struct qcom_reset_map *map; - u32 mask; - - rst = to_qcom_reset_controller(rcdev); - map = &rst->reset_map[id]; - mask = map->bitmask ? map->bitmask : BIT(map->bit); + return qcom_reset_set_assert(rcdev, id, true); +} - return regmap_update_bits(rst->regmap, map->reg, mask, 0); +static int qcom_reset_deassert(struct reset_controller_dev *rcdev, unsigned long id) +{ + return qcom_reset_set_assert(rcdev, id, false); } const struct reset_control_ops qcom_reset_ops = { diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index f644c5e32..552db816e 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -481,8 +481,11 @@ static bool brcm_avs_is_firmware_loaded(struct private_data *priv) static unsigned int brcm_avs_cpufreq_get(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - struct private_data *priv = policy->driver_data; + struct private_data *priv; + if (!policy) + return 0; + priv = policy->driver_data; cpufreq_cpu_put(policy); return brcm_avs_get_frequency(priv->base); diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index e363ae04a..44cc596ca 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -251,7 +251,7 @@ static int dt_cpufreq_early_init(struct device *dev, int cpu) if (!priv) return -ENOMEM; - if (!alloc_cpumask_var(&priv->cpus, GFP_KERNEL)) + if (!zalloc_cpumask_var(&priv->cpus, GFP_KERNEL)) return -ENOMEM; priv->cpu_dev = cpu_dev; diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 8e2672ec6..055cbb2ad 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -304,10 +304,16 @@ EXPORT_SYMBOL_GPL(sev_platform_init); static int __sev_platform_shutdown_locked(int *error) { - struct sev_device *sev = psp_master->sev_data; + struct psp_device *psp = psp_master; + struct sev_device *sev; int ret; - if (!sev || sev->state == SEV_STATE_UNINIT) + if (!psp || !psp->sev_data) + return 0; + + sev = psp->sev_data; + + if (sev->state == SEV_STATE_UNINIT) return 0; ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error); diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c index d2ae293d0..dc0feedf5 100644 --- a/drivers/crypto/qat/qat_common/adf_aer.c +++ b/drivers/crypto/qat/qat_common/adf_aer.c @@ -95,18 +95,28 @@ static void adf_device_reset_worker(struct work_struct *work) if (adf_dev_init(accel_dev) || adf_dev_start(accel_dev)) { /* The device hanged and we can't restart it so stop here */ dev_err(&GET_DEV(accel_dev), "Restart device failed\n"); - kfree(reset_data); + if (reset_data->mode == ADF_DEV_RESET_ASYNC || + completion_done(&reset_data->compl)) + kfree(reset_data); WARN(1, "QAT: device restart failed. Device is unusable\n"); return; } adf_dev_restarted_notify(accel_dev); clear_bit(ADF_STATUS_RESTARTING, &accel_dev->status); - /* The dev is back alive. Notify the caller if in sync mode */ - if (reset_data->mode == ADF_DEV_RESET_SYNC) - complete(&reset_data->compl); - else + /* + * The dev is back alive. Notify the caller if in sync mode + * + * If device restart will take a more time than expected, + * the schedule_reset() function can timeout and exit. This can be + * detected by calling the completion_done() function. In this case + * the reset_data structure needs to be freed here. + */ + if (reset_data->mode == ADF_DEV_RESET_ASYNC || + completion_done(&reset_data->compl)) kfree(reset_data); + else + complete(&reset_data->compl); } static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev, @@ -139,8 +149,9 @@ static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev, dev_err(&GET_DEV(accel_dev), "Reset device timeout expired\n"); ret = -EFAULT; + } else { + kfree(reset_data); } - kfree(reset_data); return ret; } return 0; diff --git a/drivers/crypto/stm32/stm32-crc32.c b/drivers/crypto/stm32/stm32-crc32.c index 90a920e7f..c439be165 100644 --- a/drivers/crypto/stm32/stm32-crc32.c +++ b/drivers/crypto/stm32/stm32-crc32.c @@ -104,7 +104,7 @@ static struct stm32_crc *stm32_crc_get_next_crc(void) struct stm32_crc *crc; spin_lock_bh(&crc_list.lock); - crc = list_first_entry(&crc_list.dev_list, struct stm32_crc, list); + crc = list_first_entry_or_null(&crc_list.dev_list, struct stm32_crc, list); if (crc) list_move_tail(&crc->list, &crc_list.dev_list); spin_unlock_bh(&crc_list.lock); diff --git a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c index 2cfc36d14..c58fac574 100644 --- a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c +++ b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c @@ -101,7 +101,8 @@ static void virtio_crypto_dataq_akcipher_callback(struct virtio_crypto_request * } static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher_ctx *ctx, - struct virtio_crypto_ctrl_header *header, void *para, + struct virtio_crypto_ctrl_header *header, + struct virtio_crypto_akcipher_session_para *para, const uint8_t *key, unsigned int keylen) { struct scatterlist outhdr_sg, key_sg, inhdr_sg, *sgs[3]; @@ -125,7 +126,7 @@ static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher ctrl = &vc_ctrl_req->ctrl; memcpy(&ctrl->header, header, sizeof(ctrl->header)); - memcpy(&ctrl->u, para, sizeof(ctrl->u)); + memcpy(&ctrl->u.akcipher_create_session.para, para, sizeof(*para)); input = &vc_ctrl_req->input; input->status = cpu_to_le32(VIRTIO_CRYPTO_ERR); diff --git a/drivers/crypto/xilinx/zynqmp-aes-gcm.c b/drivers/crypto/xilinx/zynqmp-aes-gcm.c index bf1f421e0..74bd3eb63 100644 --- a/drivers/crypto/xilinx/zynqmp-aes-gcm.c +++ b/drivers/crypto/xilinx/zynqmp-aes-gcm.c @@ -231,7 +231,10 @@ static int zynqmp_handle_aes_req(struct crypto_engine *engine, err = zynqmp_aes_aead_cipher(areq); } + local_bh_disable(); crypto_finalize_aead_request(engine, areq, err); + local_bh_enable(); + return 0; } diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 42c1eed44..93df6cef4 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -438,10 +438,14 @@ static void devfreq_monitor(struct work_struct *work) if (err) dev_err(&devfreq->dev, "dvfs failed with (%d) error\n", err); + if (devfreq->stop_polling) + goto out; + queue_delayed_work(devfreq_wq, &devfreq->work, msecs_to_jiffies(devfreq->profile->polling_ms)); - mutex_unlock(&devfreq->lock); +out: + mutex_unlock(&devfreq->lock); trace_devfreq_monitor(devfreq); } @@ -459,6 +463,10 @@ void devfreq_monitor_start(struct devfreq *devfreq) if (devfreq->governor->interrupt_driven) return; + mutex_lock(&devfreq->lock); + if (delayed_work_pending(&devfreq->work)) + goto out; + switch (devfreq->profile->timer) { case DEVFREQ_TIMER_DEFERRABLE: INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor); @@ -467,12 +475,16 @@ void devfreq_monitor_start(struct devfreq *devfreq) INIT_DELAYED_WORK(&devfreq->work, devfreq_monitor); break; default: - return; + goto out; } if (devfreq->profile->polling_ms) queue_delayed_work(devfreq_wq, &devfreq->work, msecs_to_jiffies(devfreq->profile->polling_ms)); + +out: + devfreq->stop_polling = false; + mutex_unlock(&devfreq->lock); } EXPORT_SYMBOL(devfreq_monitor_start); @@ -489,6 +501,14 @@ void devfreq_monitor_stop(struct devfreq *devfreq) if (devfreq->governor->interrupt_driven) return; + mutex_lock(&devfreq->lock); + if (devfreq->stop_polling) { + mutex_unlock(&devfreq->lock); + return; + } + + devfreq->stop_polling = true; + mutex_unlock(&devfreq->lock); cancel_delayed_work_sync(&devfreq->work); } EXPORT_SYMBOL(devfreq_monitor_stop); @@ -1619,7 +1639,7 @@ static ssize_t trans_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { struct devfreq *df = to_devfreq(dev); - ssize_t len; + ssize_t len = 0; int i, j; unsigned int max_state; @@ -1628,7 +1648,7 @@ static ssize_t trans_stat_show(struct device *dev, max_state = df->profile->max_state; if (max_state == 0) - return sprintf(buf, "Not Supported.\n"); + return scnprintf(buf, PAGE_SIZE, "Not Supported.\n"); mutex_lock(&df->lock); if (!df->stop_polling && @@ -1638,33 +1658,54 @@ static ssize_t trans_stat_show(struct device *dev, } mutex_unlock(&df->lock); - len = sprintf(buf, " From : To\n"); - len += sprintf(buf + len, " :"); - for (i = 0; i < max_state; i++) - len += sprintf(buf + len, "%10lu", - df->profile->freq_table[i]); + len += scnprintf(buf + len, PAGE_SIZE - len, " From : To\n"); + len += scnprintf(buf + len, PAGE_SIZE - len, " :"); + for (i = 0; i < max_state; i++) { + if (len >= PAGE_SIZE - 1) + break; + len += scnprintf(buf + len, PAGE_SIZE - len, "%10lu", + df->profile->freq_table[i]); + } + if (len >= PAGE_SIZE - 1) + return PAGE_SIZE - 1; - len += sprintf(buf + len, " time(ms)\n"); + len += scnprintf(buf + len, PAGE_SIZE - len, " time(ms)\n"); for (i = 0; i < max_state; i++) { + if (len >= PAGE_SIZE - 1) + break; if (df->profile->freq_table[i] == df->previous_freq) { - len += sprintf(buf + len, "*"); + len += scnprintf(buf + len, PAGE_SIZE - len, "*"); } else { - len += sprintf(buf + len, " "); + len += scnprintf(buf + len, PAGE_SIZE - len, " "); + } + if (len >= PAGE_SIZE - 1) + break; + + len += scnprintf(buf + len, PAGE_SIZE - len, "%10lu:", + df->profile->freq_table[i]); + for (j = 0; j < max_state; j++) { + if (len >= PAGE_SIZE - 1) + break; + len += scnprintf(buf + len, PAGE_SIZE - len, "%10u", + df->stats.trans_table[(i * max_state) + j]); } - len += sprintf(buf + len, "%10lu:", - df->profile->freq_table[i]); - for (j = 0; j < max_state; j++) - len += sprintf(buf + len, "%10u", - df->stats.trans_table[(i * max_state) + j]); + if (len >= PAGE_SIZE - 1) + break; + len += scnprintf(buf + len, PAGE_SIZE - len, "%10llu\n", (u64) + jiffies64_to_msecs(df->stats.time_in_state[i])); + } + + if (len < PAGE_SIZE - 1) + len += scnprintf(buf + len, PAGE_SIZE - len, "Total transition : %u\n", + df->stats.total_trans); - len += sprintf(buf + len, "%10llu\n", (u64) - jiffies64_to_msecs(df->stats.time_in_state[i])); + if (len >= PAGE_SIZE - 1) { + pr_warn_once("devfreq transition table exceeds PAGE_SIZE. Disabling\n"); + return -EFBIG; } - len += sprintf(buf + len, "Total transition : %u\n", - df->stats.total_trans); return len; } diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 7e1bd79fb..02b98f979 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -614,16 +614,16 @@ config TEGRA20_APB_DMA config TEGRA210_ADMA tristate "NVIDIA Tegra210 ADMA support" - depends on (ARCH_TEGRA_210_SOC || COMPILE_TEST) + depends on (ARCH_TEGRA || COMPILE_TEST) select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help - Support for the NVIDIA Tegra210 ADMA controller driver. The - DMA controller has multiple DMA channels and is used to service - various audio clients in the Tegra210 audio processing engine - (APE). This DMA controller transfers data from memory to - peripheral and vice versa. It does not support memory to - memory data transfer. + Support for the NVIDIA Tegra210/Tegra186/Tegra194/Tegra234 ADMA + controller driver. The DMA controller has multiple DMA channels + and is used to service various audio clients in the Tegra210 + audio processing engine (APE). This DMA controller transfers + data from memory to peripheral and vice versa. It does not + support memory to memory data transfer. config TIMB_DMA tristate "Timberdale FPGA DMA support" diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 4ec7bb58c..9559ebd61 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -1108,6 +1108,9 @@ EXPORT_SYMBOL_GPL(dma_async_device_channel_register); static void __dma_async_device_channel_unregister(struct dma_device *device, struct dma_chan *chan) { + if (chan->local == NULL) + return; + WARN_ONCE(!device->device_release && chan->client_count, "%s called while %d clients hold a reference\n", __func__, chan->client_count); diff --git a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c index 4ae057922..2d905f063 100644 --- a/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c +++ b/drivers/dma/fsl-dpaa2-qdma/dpaa2-qdma.c @@ -38,15 +38,17 @@ static int dpaa2_qdma_alloc_chan_resources(struct dma_chan *chan) if (!dpaa2_chan->fd_pool) goto err; - dpaa2_chan->fl_pool = dma_pool_create("fl_pool", dev, - sizeof(struct dpaa2_fl_entry), - sizeof(struct dpaa2_fl_entry), 0); + dpaa2_chan->fl_pool = + dma_pool_create("fl_pool", dev, + sizeof(struct dpaa2_fl_entry) * 3, + sizeof(struct dpaa2_fl_entry), 0); + if (!dpaa2_chan->fl_pool) goto err_fd; dpaa2_chan->sdd_pool = dma_pool_create("sdd_pool", dev, - sizeof(struct dpaa2_qdma_sd_d), + sizeof(struct dpaa2_qdma_sd_d) * 2, sizeof(struct dpaa2_qdma_sd_d), 0); if (!dpaa2_chan->sdd_pool) goto err_fl; diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c index 045ead46e..7082a5a68 100644 --- a/drivers/dma/fsl-qdma.c +++ b/drivers/dma/fsl-qdma.c @@ -109,6 +109,7 @@ #define FSL_QDMA_CMD_WTHROTL_OFFSET 20 #define FSL_QDMA_CMD_DSEN_OFFSET 19 #define FSL_QDMA_CMD_LWC_OFFSET 16 +#define FSL_QDMA_CMD_PF BIT(17) /* Field definition for Descriptor status */ #define QDMA_CCDF_STATUS_RTE BIT(5) @@ -384,7 +385,8 @@ static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp, qdma_csgf_set_f(csgf_dest, len); /* Descriptor Buffer */ cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE << - FSL_QDMA_CMD_RWTTYPE_OFFSET); + FSL_QDMA_CMD_RWTTYPE_OFFSET) | + FSL_QDMA_CMD_PF; sdf->data = QDMA_SDDF_CMD(cmd); cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE << @@ -514,11 +516,11 @@ static struct fsl_qdma_queue queue_temp = queue_head + i + (j * queue_num); queue_temp->cq = - dma_alloc_coherent(&pdev->dev, - sizeof(struct fsl_qdma_format) * - queue_size[i], - &queue_temp->bus_addr, - GFP_KERNEL); + dmam_alloc_coherent(&pdev->dev, + sizeof(struct fsl_qdma_format) * + queue_size[i], + &queue_temp->bus_addr, + GFP_KERNEL); if (!queue_temp->cq) return NULL; queue_temp->block_base = fsl_qdma->block_base + @@ -563,11 +565,11 @@ static struct fsl_qdma_queue /* * Buffer for queue command */ - status_head->cq = dma_alloc_coherent(&pdev->dev, - sizeof(struct fsl_qdma_format) * - status_size, - &status_head->bus_addr, - GFP_KERNEL); + status_head->cq = dmam_alloc_coherent(&pdev->dev, + sizeof(struct fsl_qdma_format) * + status_size, + &status_head->bus_addr, + GFP_KERNEL); if (!status_head->cq) { devm_kfree(&pdev->dev, status_head); return NULL; @@ -805,7 +807,7 @@ fsl_qdma_irq_init(struct platform_device *pdev, int i; int cpu; int ret; - char irq_name[20]; + char irq_name[32]; fsl_qdma->error_irq = platform_get_irq_byname(pdev, "qdma-error"); @@ -1201,10 +1203,6 @@ static int fsl_qdma_probe(struct platform_device *pdev) if (!fsl_qdma->queue) return -ENOMEM; - ret = fsl_qdma_irq_init(pdev, fsl_qdma); - if (ret) - return ret; - fsl_qdma->irq_base = platform_get_irq_byname(pdev, "qdma-queue0"); if (fsl_qdma->irq_base < 0) return fsl_qdma->irq_base; @@ -1243,16 +1241,19 @@ static int fsl_qdma_probe(struct platform_device *pdev) platform_set_drvdata(pdev, fsl_qdma); - ret = dma_async_device_register(&fsl_qdma->dma_dev); + ret = fsl_qdma_reg_init(fsl_qdma); if (ret) { - dev_err(&pdev->dev, - "Can't register NXP Layerscape qDMA engine.\n"); + dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n"); return ret; } - ret = fsl_qdma_reg_init(fsl_qdma); + ret = fsl_qdma_irq_init(pdev, fsl_qdma); + if (ret) + return ret; + + ret = dma_async_device_register(&fsl_qdma->dma_dev); if (ret) { - dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n"); + dev_err(&pdev->dev, "Can't register NXP Layerscape qDMA engine.\n"); return ret; } @@ -1272,8 +1273,6 @@ static void fsl_qdma_cleanup_vchan(struct dma_device *dmadev) static int fsl_qdma_remove(struct platform_device *pdev) { - int i; - struct fsl_qdma_queue *status; struct device_node *np = pdev->dev.of_node; struct fsl_qdma_engine *fsl_qdma = platform_get_drvdata(pdev); @@ -1282,11 +1281,6 @@ static int fsl_qdma_remove(struct platform_device *pdev) of_dma_controller_free(np); dma_async_device_unregister(&fsl_qdma->dma_dev); - for (i = 0; i < fsl_qdma->block_number; i++) { - status = fsl_qdma->status[i]; - dma_free_coherent(&pdev->dev, sizeof(struct fsl_qdma_format) * - status->n_cq, status->cq, status->bus_addr); - } return 0; } diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c index f5a84c846..db506e1f7 100644 --- a/drivers/dma/idma64.c +++ b/drivers/dma/idma64.c @@ -167,6 +167,10 @@ static irqreturn_t idma64_irq(int irq, void *dev) u32 status_err; unsigned short i; + /* Since IRQ may be shared, check if DMA controller is powered on */ + if (status == GENMASK(31, 0)) + return IRQ_NONE; + dev_vdbg(idma64->dma.dev, "%s: status=%#x\n", __func__, status); /* Check if we have any interrupt from the DMA controller */ diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c index 04202d75f..695feb344 100644 --- a/drivers/dma/owl-dma.c +++ b/drivers/dma/owl-dma.c @@ -249,7 +249,7 @@ static void pchan_update(struct owl_dma_pchan *pchan, u32 reg, else regval &= ~val; - writel(val, pchan->base + reg); + writel(regval, pchan->base + reg); } static void pchan_writel(struct owl_dma_pchan *pchan, u32 reg, u32 data) @@ -273,7 +273,7 @@ static void dma_update(struct owl_dma *od, u32 reg, u32 val, bool state) else regval &= ~val; - writel(val, od->base + reg); + writel(regval, od->base + reg); } static void dma_writel(struct owl_dma *od, u32 reg, u32 data) diff --git a/drivers/dma/sh/shdma.h b/drivers/dma/sh/shdma.h index 9c121a4b3..f97d80343 100644 --- a/drivers/dma/sh/shdma.h +++ b/drivers/dma/sh/shdma.h @@ -25,7 +25,7 @@ struct sh_dmae_chan { const struct sh_dmae_slave_config *config; /* Slave DMA configuration */ int xmit_shift; /* log_2(bytes_per_xfer) */ void __iomem *base; - char dev_id[16]; /* unique name per DMAC of channel */ + char dev_id[32]; /* unique name per DMAC of channel */ int pm_error; dma_addr_t slave_addr; }; diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c index a1adc8d91..69292d4a0 100644 --- a/drivers/dma/ti/edma.c +++ b/drivers/dma/ti/edma.c @@ -2462,6 +2462,11 @@ static int edma_probe(struct platform_device *pdev) if (irq > 0) { irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccint", dev_name(dev)); + if (!irq_name) { + ret = -ENOMEM; + goto err_disable_pm; + } + ret = devm_request_irq(dev, irq, dma_irq_handler, 0, irq_name, ecc); if (ret) { @@ -2478,6 +2483,11 @@ static int edma_probe(struct platform_device *pdev) if (irq > 0) { irq_name = devm_kasprintf(dev, GFP_KERNEL, "%s_ccerrint", dev_name(dev)); + if (!irq_name) { + ret = -ENOMEM; + goto err_disable_pm; + } + ret = devm_request_irq(dev, irq, dma_ccerr_handler, 0, irq_name, ecc); if (ret) { diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index d3902784c..15eecb757 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -2877,6 +2877,7 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc, { struct udma_chan *uc = to_udma_chan(&vc->chan); struct udma_desc *d; + u8 status; if (!vd) return; @@ -2886,12 +2887,12 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc, if (d->metadata_size) udma_fetch_epib(uc, d); - /* Provide residue information for the client */ if (result) { void *desc_vaddr = udma_curr_cppi5_desc_vaddr(d, d->desc_idx); if (cppi5_desc_get_type(desc_vaddr) == CPPI5_INFO0_DESC_TYPE_VAL_HOST) { + /* Provide residue information for the client */ result->residue = d->residue - cppi5_hdesc_get_pktlen(desc_vaddr); if (result->residue) @@ -2900,7 +2901,12 @@ static void udma_desc_pre_callback(struct virt_dma_chan *vc, result->result = DMA_TRANS_NOERROR; } else { result->residue = 0; - result->result = DMA_TRANS_NOERROR; + /* Propagate TR Response errors to the client */ + status = d->hwdesc[0].tr_resp_base->status; + if (status) + result->result = DMA_TRANS_ABORTED; + else + result->result = DMA_TRANS_NOERROR; } } } diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c index 6c7098032..058c3a6ed 100644 --- a/drivers/dma/xilinx/xilinx_dpdma.c +++ b/drivers/dma/xilinx/xilinx_dpdma.c @@ -213,7 +213,8 @@ struct xilinx_dpdma_tx_desc { * @running: true if the channel is running * @first_frame: flag for the first frame of stream * @video_group: flag if multi-channel operation is needed for video channels - * @lock: lock to access struct xilinx_dpdma_chan + * @lock: lock to access struct xilinx_dpdma_chan. Must be taken before + * @vchan.lock, if both are to be held. * @desc_pool: descriptor allocation pool * @err_task: error IRQ bottom half handler * @desc: References to descriptors being processed @@ -1101,12 +1102,14 @@ static void xilinx_dpdma_chan_vsync_irq(struct xilinx_dpdma_chan *chan) * Complete the active descriptor, if any, promote the pending * descriptor to active, and queue the next transfer, if any. */ + spin_lock(&chan->vchan.lock); if (chan->desc.active) vchan_cookie_complete(&chan->desc.active->vdesc); chan->desc.active = pending; chan->desc.pending = NULL; xilinx_dpdma_chan_queue_transfer(chan); + spin_unlock(&chan->vchan.lock); out: spin_unlock_irqrestore(&chan->lock, flags); @@ -1264,10 +1267,12 @@ static void xilinx_dpdma_issue_pending(struct dma_chan *dchan) struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan); unsigned long flags; - spin_lock_irqsave(&chan->vchan.lock, flags); + spin_lock_irqsave(&chan->lock, flags); + spin_lock(&chan->vchan.lock); if (vchan_issue_pending(&chan->vchan)) xilinx_dpdma_chan_queue_transfer(chan); - spin_unlock_irqrestore(&chan->vchan.lock, flags); + spin_unlock(&chan->vchan.lock); + spin_unlock_irqrestore(&chan->lock, flags); } static int xilinx_dpdma_config(struct dma_chan *dchan, @@ -1491,7 +1496,9 @@ static void xilinx_dpdma_chan_err_task(struct tasklet_struct *t) XILINX_DPDMA_EINTR_CHAN_ERR_MASK << chan->id); spin_lock_irqsave(&chan->lock, flags); + spin_lock(&chan->vchan.lock); xilinx_dpdma_chan_queue_transfer(chan); + spin_unlock(&chan->vchan.lock); spin_unlock_irqrestore(&chan->lock, flags); } diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index f3b3953ca..d446a7262 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -429,7 +429,23 @@ static void bm_work(struct work_struct *work) */ card->bm_generation = generation; - if (root_device == NULL) { + if (card->gap_count == 0) { + /* + * If self IDs have inconsistent gap counts, do a + * bus reset ASAP. The config rom read might never + * complete, so don't wait for it. However, still + * send a PHY configuration packet prior to the + * bus reset. The PHY configuration packet might + * fail, but 1394-2008 8.4.5.2 explicitly permits + * it in this case, so it should be safe to try. + */ + new_root_id = local_id; + /* + * We must always send a bus reset if the gap count + * is inconsistent, so bypass the 5-reset limit. + */ + card->bm_retries = 0; + } else if (root_device == NULL) { /* * Either link_on is false, or we failed to read the * config rom. In either case, pick another root. @@ -484,7 +500,19 @@ static void bm_work(struct work_struct *work) fw_notice(card, "phy config: new root=%x, gap_count=%d\n", new_root_id, gap_count); fw_send_phy_config(card, new_root_id, generation, gap_count); - reset_bus(card, true); + /* + * Where possible, use a short bus reset to minimize + * disruption to isochronous transfers. But in the event + * of a gap count inconsistency, use a long bus reset. + * + * As noted in 1394a 8.4.6.2, nodes on a mixed 1394/1394a bus + * may set different gap counts after a bus reset. On a mixed + * 1394/1394a bus, a short bus reset can get doubled. Some + * nodes may treat the double reset as one bus reset and others + * may treat it as two, causing a gap count inconsistency + * again. Using a long bus reset prevents this. + */ + reset_bus(card, card->gap_count != 0); /* Will allocate broadcast channel after the reset. */ goto out; } diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index 94ae27865..9bc181865 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -100,10 +100,9 @@ static int textual_leaf_to_string(const u32 *block, char *buf, size_t size) * @buf: where to put the string * @size: size of @buf, in bytes * - * The string is taken from a minimal ASCII text descriptor leaf after - * the immediate entry with @key. The string is zero-terminated. - * An overlong string is silently truncated such that it and the - * zero byte fit into @size. + * The string is taken from a minimal ASCII text descriptor leaf just after the entry with the + * @key. The string is zero-terminated. An overlong string is silently truncated such that it + * and the zero byte fit into @size. * * Returns strlen(buf) or a negative error code. */ diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c index 3359ae2ad..9054c2852 100644 --- a/drivers/firmware/efi/arm-runtime.c +++ b/drivers/firmware/efi/arm-runtime.c @@ -107,7 +107,7 @@ static int __init arm_enable_runtime_services(void) efi_memory_desc_t *md; for_each_efi_memory_desc(md) { - int md_size = md->num_pages << EFI_PAGE_SHIFT; + u64 md_size = md->num_pages << EFI_PAGE_SHIFT; struct resource *res; if (!(md->attribute & EFI_MEMORY_SP)) diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c index 3e8d4b51a..97bafb5f7 100644 --- a/drivers/firmware/efi/capsule-loader.c +++ b/drivers/firmware/efi/capsule-loader.c @@ -292,7 +292,7 @@ static int efi_capsule_open(struct inode *inode, struct file *file) return -ENOMEM; } - cap_info->phys = kzalloc(sizeof(void *), GFP_KERNEL); + cap_info->phys = kzalloc(sizeof(phys_addr_t), GFP_KERNEL); if (!cap_info->phys) { kfree(cap_info->pages); kfree(cap_info); diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c index f55a92ff1..86da3c7a5 100644 --- a/drivers/firmware/efi/efi-init.c +++ b/drivers/firmware/efi/efi-init.c @@ -142,15 +142,6 @@ static __init int is_usable_memory(efi_memory_desc_t *md) case EFI_CONVENTIONAL_MEMORY: case EFI_PERSISTENT_MEMORY: /* - * Special purpose memory is 'soft reserved', which means it - * is set aside initially, but can be hotplugged back in or - * be assigned to the dax driver after boot. - */ - if (efi_soft_reserve_enabled() && - (md->attribute & EFI_MEMORY_SP)) - return false; - - /* * According to the spec, these regions are no longer reserved * after calling ExitBootServices(). However, we can only use * them as System RAM if they can be mapped writeback cacheable. @@ -194,6 +185,16 @@ static __init void reserve_regions(void) size = npages << PAGE_SHIFT; if (is_memory(md)) { + /* + * Special purpose memory is 'soft reserved', which + * means it is set aside initially. Don't add a memblock + * for it now so that it can be hotplugged back in or + * be assigned to the dax driver after boot. + */ + if (efi_soft_reserve_enabled() && + (md->attribute & EFI_MEMORY_SP)) + continue; + early_init_dt_add_memory_arch(paddr, size); if (!is_usable_memory(md)) diff --git a/drivers/firmware/efi/riscv-runtime.c b/drivers/firmware/efi/riscv-runtime.c index d28e715d2..6711e64eb 100644 --- a/drivers/firmware/efi/riscv-runtime.c +++ b/drivers/firmware/efi/riscv-runtime.c @@ -85,7 +85,7 @@ static int __init riscv_enable_runtime_services(void) efi_memory_desc_t *md; for_each_efi_memory_desc(md) { - int md_size = md->num_pages << EFI_PAGE_SHIFT; + u64 md_size = md->num_pages << EFI_PAGE_SHIFT; struct resource *res; if (!(md->attribute & EFI_MEMORY_SP)) diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index cae590bd0..eaed1ddcc 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -415,7 +415,7 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), void *data, bool duplicates, struct list_head *head) { const struct efivar_operations *ops; - unsigned long variable_name_size = 1024; + unsigned long variable_name_size = 512; efi_char16_t *variable_name; efi_status_t status; efi_guid_t vendor_guid; @@ -438,12 +438,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), } /* - * Per EFI spec, the maximum storage allocated for both - * the variable name and variable data is 1024 bytes. + * A small set of old UEFI implementations reject sizes + * above a certain threshold, the lowest seen in the wild + * is 512. */ do { - variable_name_size = 1024; + variable_name_size = 512; status = ops->get_next_variable(&variable_name_size, variable_name, @@ -491,9 +492,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), break; case EFI_NOT_FOUND: break; + case EFI_BUFFER_TOO_SMALL: + pr_warn("efivars: Variable name size exceeds maximum (%lu > 512)\n", + variable_name_size); + status = EFI_NOT_FOUND; + break; default: - printk(KERN_WARNING "efivars: get_next_variable: status=%lx\n", - status); + pr_warn("efivars: get_next_variable: status=%lx\n", status); status = EFI_NOT_FOUND; break; } diff --git a/drivers/gpio/gpio-74x164.c b/drivers/gpio/gpio-74x164.c index 05637d585..1b50470c4 100644 --- a/drivers/gpio/gpio-74x164.c +++ b/drivers/gpio/gpio-74x164.c @@ -127,8 +127,6 @@ static int gen_74x164_probe(struct spi_device *spi) if (IS_ERR(chip->gpiod_oe)) return PTR_ERR(chip->gpiod_oe); - gpiod_set_value_cansleep(chip->gpiod_oe, 1); - spi_set_drvdata(spi, chip); chip->gpio_chip.label = spi->modalias; @@ -153,6 +151,8 @@ static int gen_74x164_probe(struct spi_device *spi) goto exit_destroy; } + gpiod_set_value_cansleep(chip->gpiod_oe, 1); + ret = gpiochip_add_data(&chip->gpio_chip, chip); if (!ret) return 0; diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c index 865ab2b34..3dfb8b6c6 100644 --- a/drivers/gpio/gpio-eic-sprd.c +++ b/drivers/gpio/gpio-eic-sprd.c @@ -318,20 +318,27 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) switch (flow_type) { case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 1); + sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IC, 1); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 0); + sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IC, 1); break; case IRQ_TYPE_EDGE_RISING: case IRQ_TYPE_EDGE_FALLING: case IRQ_TYPE_EDGE_BOTH: state = sprd_eic_get(chip, offset); - if (state) + if (state) { sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 0); - else + sprd_eic_update(chip, offset, + SPRD_EIC_DBNC_IC, 1); + } else { sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 1); + sprd_eic_update(chip, offset, + SPRD_EIC_DBNC_IC, 1); + } break; default: return -ENOTSUPP; @@ -343,20 +350,27 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) switch (flow_type) { case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTCLR, 1); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTCLR, 1); break; case IRQ_TYPE_EDGE_RISING: case IRQ_TYPE_EDGE_FALLING: case IRQ_TYPE_EDGE_BOTH: state = sprd_eic_get(chip, offset); - if (state) + if (state) { sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 0); - else + sprd_eic_update(chip, offset, + SPRD_EIC_LATCH_INTCLR, 1); + } else { sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 1); + sprd_eic_update(chip, offset, + SPRD_EIC_LATCH_INTCLR, 1); + } break; default: return -ENOTSUPP; @@ -370,29 +384,34 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_FALLING: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_BOTH: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 1); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; default: @@ -405,29 +424,34 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_FALLING: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_BOTH: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 1); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; default: diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 44ee319da..12012e164 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -1479,6 +1479,20 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = { .ignore_wake = "INT33FF:01@0", }, }, + { + /* + * Spurious wakeups from TP_ATTN# pin + * Found in BIOS 0.35 + * https://gitlab.freedesktop.org/drm/amd/-/issues/3073 + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GPD"), + DMI_MATCH(DMI_PRODUCT_NAME, "G1619-04"), + }, + .driver_data = &(struct acpi_gpiolib_dmi_quirk) { + .ignore_wake = "PNP0C50:00@8", + }, + }, {} /* Terminating entry */ }; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index d10f62108..374bb9f43 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -732,11 +732,11 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, ret = gpiochip_irqchip_init_valid_mask(gc); if (ret) - goto err_remove_acpi_chip; + goto err_free_hogs; ret = gpiochip_irqchip_init_hw(gc); if (ret) - goto err_remove_acpi_chip; + goto err_remove_irqchip_mask; ret = gpiochip_add_irqchip(gc, lock_key, request_key); if (ret) @@ -761,13 +761,13 @@ err_remove_irqchip: gpiochip_irqchip_remove(gc); err_remove_irqchip_mask: gpiochip_irqchip_free_valid_mask(gc); -err_remove_acpi_chip: +err_free_hogs: + gpiochip_free_hogs(gc); acpi_gpiochip_remove(gc); + gpiochip_remove_pin_ranges(gc); err_remove_of_chip: - gpiochip_free_hogs(gc); of_gpiochip_remove(gc); err_free_gpiochip_mask: - gpiochip_remove_pin_ranges(gc); gpiochip_free_valid_mask(gc); err_remove_from_list: spin_lock_irqsave(&gpio_lock, flags); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c index 3107b9575..eef7517c9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c @@ -88,7 +88,7 @@ struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f) return NULL; fence = container_of(f, struct amdgpu_amdkfd_fence, base); - if (fence && f->ops == &amdkfd_fence_ops) + if (f->ops == &amdkfd_fence_ops) return fence; return NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 1b4c7ced8..4a95a624f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1259,6 +1259,7 @@ allocate_init_user_pages_failed: err_bo_create: unreserve_mem_limit(adev, size, alloc_domain, !!sg); err_reserve_limit: + amdgpu_sync_free(&(*mem)->sync); mutex_destroy(&(*mem)->lock); kfree(*mem); err: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index a093f1b27..e833c02fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1184,6 +1184,7 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev) return true; fw_ver = *((uint32_t *)adev->pm.fw->data + 69); + release_firmware(adev->pm.fw); if (fw_ver < 0x00160e00) return true; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index 8ea6c4952..6a22bc41c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -241,7 +241,8 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync, /* Never sync to VM updates either. */ if (fence_owner == AMDGPU_FENCE_OWNER_VM && - owner != AMDGPU_FENCE_OWNER_UNDEFINED) + owner != AMDGPU_FENCE_OWNER_UNDEFINED && + owner != AMDGPU_FENCE_OWNER_KFD) continue; /* Ignore fences depending on the sync mode */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 8445bb7ae..ad3de971a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2201,6 +2201,37 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev, trace_amdgpu_vm_bo_map(bo_va, mapping); } +/* Validate operation parameters to prevent potential abuse */ +static int amdgpu_vm_verify_parameters(struct amdgpu_device *adev, + struct amdgpu_bo *bo, + uint64_t saddr, + uint64_t offset, + uint64_t size) +{ + uint64_t tmp, lpfn; + + if (saddr & AMDGPU_GPU_PAGE_MASK + || offset & AMDGPU_GPU_PAGE_MASK + || size & AMDGPU_GPU_PAGE_MASK) + return -EINVAL; + + if (check_add_overflow(saddr, size, &tmp) + || check_add_overflow(offset, size, &tmp) + || size == 0 /* which also leads to end < begin */) + return -EINVAL; + + /* make sure object fit at this offset */ + if (bo && offset + size > amdgpu_bo_size(bo)) + return -EINVAL; + + /* Ensure last pfn not exceed max_pfn */ + lpfn = (saddr + size - 1) >> AMDGPU_GPU_PAGE_SHIFT; + if (lpfn >= adev->vm_manager.max_pfn) + return -EINVAL; + + return 0; +} + /** * amdgpu_vm_bo_map - map bo inside a vm * @@ -2227,21 +2258,14 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, struct amdgpu_bo *bo = bo_va->base.bo; struct amdgpu_vm *vm = bo_va->base.vm; uint64_t eaddr; + int r; - /* validate the parameters */ - if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK) - return -EINVAL; - if (saddr + size <= saddr || offset + size <= offset) - return -EINVAL; - - /* make sure object fit at this offset */ - eaddr = saddr + size - 1; - if ((bo && offset + size > amdgpu_bo_size(bo)) || - (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT)) - return -EINVAL; + r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size); + if (r) + return r; saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; tmp = amdgpu_vm_it_iter_first(&vm->va, saddr, eaddr); if (tmp) { @@ -2294,17 +2318,9 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, uint64_t eaddr; int r; - /* validate the parameters */ - if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK) - return -EINVAL; - if (saddr + size <= saddr || offset + size <= offset) - return -EINVAL; - - /* make sure object fit at this offset */ - eaddr = saddr + size - 1; - if ((bo && offset + size > amdgpu_bo_size(bo)) || - (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT)) - return -EINVAL; + r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size); + if (r) + return r; /* Allocate all the needed memory */ mapping = kmalloc(sizeof(*mapping), GFP_KERNEL); @@ -2318,7 +2334,7 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, } saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; mapping->start = saddr; mapping->last = eaddr; @@ -2405,10 +2421,14 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, struct amdgpu_bo_va_mapping *before, *after, *tmp, *next; LIST_HEAD(removed); uint64_t eaddr; + int r; + + r = amdgpu_vm_verify_parameters(adev, NULL, saddr, 0, size); + if (r) + return r; - eaddr = saddr + size - 1; saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; /* Allocate all the needed memory */ before = kzalloc(sizeof(*before), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c index 4cfc78669..c1841fa87 100644 --- a/drivers/gpu/drm/amd/amdgpu/atom.c +++ b/drivers/gpu/drm/amd/amdgpu/atom.c @@ -310,7 +310,7 @@ static uint32_t atom_get_src_int(atom_exec_context *ctx, uint8_t attr, DEBUG("IMM 0x%02X\n", val); return val; } - return 0; + break; case ATOM_ARG_PLL: idx = U8(*ptr); (*ptr)++; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 1bd330d43..ad36f337c 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -390,17 +390,21 @@ static void sdma_v5_2_ring_emit_hdp_flush(struct amdgpu_ring *ring) u32 ref_and_mask = 0; const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg; - ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me; - - amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) | - SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) | - SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */ - amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_done_offset(adev)) << 2); - amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_req_offset(adev)) << 2); - amdgpu_ring_write(ring, ref_and_mask); /* reference */ - amdgpu_ring_write(ring, ref_and_mask); /* mask */ - amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) | - SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); /* retry count, poll interval */ + if (ring->me > 1) { + amdgpu_asic_flush_hdp(adev, ring); + } else { + ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me; + + amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) | + SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) | + SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */ + amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_done_offset(adev)) << 2); + amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_req_offset(adev)) << 2); + amdgpu_ring_write(ring, ref_and_mask); /* reference */ + amdgpu_ring_write(ring, ref_and_mask); /* mask */ + amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) | + SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); /* retry count, poll interval */ + } } /** diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 8cc51cec9..799a91a06 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -959,8 +959,8 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, * nodes, but not more than args->num_of_nodes as that is * the amount of memory allocated by user */ - pa = kzalloc((sizeof(struct kfd_process_device_apertures) * - args->num_of_nodes), GFP_KERNEL); + pa = kcalloc(args->num_of_nodes, sizeof(struct kfd_process_device_apertures), + GFP_KERNEL); if (!pa) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 54d6b4128..3578e3b35 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1456,6 +1456,7 @@ static int dm_sw_fini(void *handle) if (adev->dm.dmub_srv) { dmub_srv_destroy(adev->dm.dmub_srv); + kfree(adev->dm.dmub_srv); adev->dm.dmub_srv = NULL; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index e43f82bcb..32dbd2a27 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -1179,7 +1179,7 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf, const uint32_t rd_buf_size = 10; struct pipe_ctx *pipe_ctx; ssize_t result = 0; - int i, r, str_len = 30; + int i, r, str_len = 10; rd_buf = kcalloc(rd_buf_size, sizeof(char), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 36a9e9c84..272252cd0 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1440,6 +1440,10 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c wait_for_no_pipes_pending(dc, context); /* pplib is notified if disp_num changed */ dc->hwss.optimize_bandwidth(dc, context); + /* Need to do otg sync again as otg could be out of sync due to otg + * workaround applied during clock update + */ + dc_trigger_sync(dc, context); } context->stream_mask = get_stream_mask(dc, context); diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 1c669f115..8cf6e307a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1669,6 +1669,9 @@ bool dcn10_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx, { struct dpp *dpp = pipe_ctx->plane_res.dpp; + if (!stream) + return false; + if (dpp == NULL) return false; @@ -1691,8 +1694,8 @@ bool dcn10_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx, } else dpp->funcs->dpp_program_regamma_pwl(dpp, NULL, OPP_REGAMMA_BYPASS); - if (stream != NULL && stream->ctx != NULL && - stream->out_transfer_func != NULL) { + if (stream->ctx && + stream->out_transfer_func) { log_tf(stream->ctx, stream->out_transfer_func, dpp->regamma_params.hw_points_num); diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index 22c77e96f..02d22f62c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -641,10 +641,20 @@ void dcn30_set_avmute(struct pipe_ctx *pipe_ctx, bool enable) if (pipe_ctx == NULL) return; - if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal) && pipe_ctx->stream_res.stream_enc != NULL) + if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal) && pipe_ctx->stream_res.stream_enc != NULL) { pipe_ctx->stream_res.stream_enc->funcs->set_avmute( pipe_ctx->stream_res.stream_enc, enable); + + /* Wait for two frame to make sure AV mute is sent out */ + if (enable) { + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK); + pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE); + } + } } void dcn30_update_info_frame(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c index 972f2600f..05d96fa68 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -405,6 +405,9 @@ enum mod_hdcp_status mod_hdcp_hdcp2_create_session(struct mod_hdcp *hdcp) hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf; memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory)); + if (!display) + return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND; + hdcp_cmd->in_msg.hdcp2_create_session_v2.display_handle = display->index; if (hdcp->connection.link.adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_0) diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h b/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h index 4220fd8fd..54cd86060 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_stats.h @@ -57,10 +57,10 @@ void mod_stats_update_event(struct mod_stats *mod_stats, unsigned int length); void mod_stats_update_flip(struct mod_stats *mod_stats, - unsigned long timestamp_in_ns); + unsigned long long timestamp_in_ns); void mod_stats_update_vupdate(struct mod_stats *mod_stats, - unsigned long timestamp_in_ns); + unsigned long long timestamp_in_ns); void mod_stats_update_freesync(struct mod_stats *mod_stats, unsigned int v_total_min, diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c index b760f95e7..5998c78ad 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/process_pptables_v1_0.c @@ -204,7 +204,7 @@ static int get_platform_power_management_table( struct pp_hwmgr *hwmgr, ATOM_Tonga_PPM_Table *atom_ppm_table) { - struct phm_ppm_table *ptr = kzalloc(sizeof(ATOM_Tonga_PPM_Table), GFP_KERNEL); + struct phm_ppm_table *ptr = kzalloc(sizeof(*ptr), GFP_KERNEL); struct phm_ppt_v1_information *pp_table_information = (struct phm_ppt_v1_information *)(hwmgr->pptable); diff --git a/drivers/gpu/drm/bridge/nxp-ptn3460.c b/drivers/gpu/drm/bridge/nxp-ptn3460.c index e941c1132..eebb2dece 100644 --- a/drivers/gpu/drm/bridge/nxp-ptn3460.c +++ b/drivers/gpu/drm/bridge/nxp-ptn3460.c @@ -54,13 +54,13 @@ static int ptn3460_read_bytes(struct ptn3460_bridge *ptn_bridge, char addr, int ret; ret = i2c_master_send(ptn_bridge->client, &addr, 1); - if (ret <= 0) { + if (ret < 0) { DRM_ERROR("Failed to send i2c command, ret=%d\n", ret); return ret; } ret = i2c_master_recv(ptn_bridge->client, buf, len); - if (ret <= 0) { + if (ret < 0) { DRM_ERROR("Failed to recv i2c data, ret=%d\n", ret); return ret; } @@ -78,7 +78,7 @@ static int ptn3460_write_byte(struct ptn3460_bridge *ptn_bridge, char addr, buf[1] = val; ret = i2c_master_send(ptn_bridge->client, buf, ARRAY_SIZE(buf)); - if (ret <= 0) { + if (ret < 0) { DRM_ERROR("Failed to send i2c command, ret=%d\n", ret); return ret; } diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index d5fd41823..7872a04e9 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -774,6 +774,7 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, unsigned int total_modes_count = 0; struct drm_client_offset *offsets; unsigned int connector_count = 0; + /* points to modes protected by mode_config.mutex */ struct drm_display_mode **modes; struct drm_crtc **crtcs; int i, ret = 0; @@ -842,7 +843,6 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, drm_client_pick_crtcs(client, connectors, connector_count, crtcs, modes, 0, width, height); } - mutex_unlock(&dev->mode_config.mutex); drm_client_modeset_release(client); @@ -872,6 +872,7 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, modeset->y = offset->y; } } + mutex_unlock(&dev->mode_config.mutex); mutex_unlock(&client->modeset_mutex); out: diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index 537e7de8e..93da7b5d7 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -411,7 +411,7 @@ int drm_open(struct inode *inode, struct file *filp) { struct drm_device *dev; struct drm_minor *minor; - int retcode; + int retcode = 0; int need_setup = 0; minor = drm_minor_acquire(iminor(inode)); diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c index 2f5b0c2bb..e490ef424 100644 --- a/drivers/gpu/drm/drm_framebuffer.c +++ b/drivers/gpu/drm/drm_framebuffer.c @@ -570,7 +570,7 @@ int drm_mode_getfb2_ioctl(struct drm_device *dev, struct drm_mode_fb_cmd2 *r = data; struct drm_framebuffer *fb; unsigned int i; - int ret; + int ret = 0; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EINVAL; diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index 0c806e99e..83918ac1f 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -300,7 +300,8 @@ static int mipi_dsi_remove_device_fn(struct device *dev, void *priv) { struct mipi_dsi_device *dsi = to_mipi_dsi_device(dev); - mipi_dsi_detach(dsi); + if (dsi->attached) + mipi_dsi_detach(dsi); mipi_dsi_device_unregister(dsi); return 0; @@ -323,11 +324,18 @@ EXPORT_SYMBOL(mipi_dsi_host_unregister); int mipi_dsi_attach(struct mipi_dsi_device *dsi) { const struct mipi_dsi_host_ops *ops = dsi->host->ops; + int ret; if (!ops || !ops->attach) return -ENOSYS; - return ops->attach(dsi->host, dsi); + ret = ops->attach(dsi->host, dsi); + if (ret) + return ret; + + dsi->attached = true; + + return 0; } EXPORT_SYMBOL(mipi_dsi_attach); @@ -339,9 +347,14 @@ int mipi_dsi_detach(struct mipi_dsi_device *dsi) { const struct mipi_dsi_host_ops *ops = dsi->host->ops; + if (WARN_ON(!dsi->attached)) + return -EINVAL; + if (!ops || !ops->detach) return -ENOSYS; + dsi->attached = false; + return ops->detach(dsi->host, dsi); } EXPORT_SYMBOL(mipi_dsi_detach); diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c index f634371c7..7fd3de89e 100644 --- a/drivers/gpu/drm/drm_panel.c +++ b/drivers/gpu/drm/drm_panel.c @@ -207,19 +207,24 @@ EXPORT_SYMBOL(drm_panel_disable); * The modes probed from the panel are automatically added to the connector * that the panel is attached to. * - * Return: The number of modes available from the panel on success or a - * negative error code on failure. + * Return: The number of modes available from the panel on success, or 0 on + * failure (no modes). */ int drm_panel_get_modes(struct drm_panel *panel, struct drm_connector *connector) { if (!panel) - return -EINVAL; + return 0; - if (panel->funcs && panel->funcs->get_modes) - return panel->funcs->get_modes(panel, connector); + if (panel->funcs && panel->funcs->get_modes) { + int num; - return -EOPNOTSUPP; + num = panel->funcs->get_modes(panel, connector); + if (num > 0) + return num; + } + + return 0; } EXPORT_SYMBOL(drm_panel_get_modes); diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index 24f643982..79249568b 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -1213,6 +1213,7 @@ retry: out: if (fb) drm_framebuffer_put(fb); + fb = NULL; if (plane->old_fb) drm_framebuffer_put(plane->old_fb); plane->old_fb = NULL; diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 738e60139..6ce446cc8 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -387,6 +387,15 @@ int drm_syncobj_find_fence(struct drm_file *file_private, if (!syncobj) return -ENOENT; + /* Waiting for userspace with locks help is illegal cause that can + * trivial deadlock with page faults for example. Make lockdep complain + * about it early on. + */ + if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) { + might_sleep(); + lockdep_assert_none_held_once(); + } + *fence = drm_syncobj_fence_get(syncobj); if (*fence) { @@ -951,6 +960,10 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, uint64_t *points; uint32_t signaled_count, i; + if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | + DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) + lockdep_assert_none_held_once(); + points = kmalloc_array(count, sizeof(*points), GFP_KERNEL); if (points == NULL) return -ENOMEM; @@ -1017,7 +1030,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, * fallthough and try a 0 timeout wait! */ - if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) { + if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | + DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) { for (i = 0; i < count; ++i) drm_syncobj_fence_add_wait(syncobjs[i], &entries[i]); } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index a9a3afaef..edf938706 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -511,7 +511,7 @@ static struct drm_driver etnaviv_drm_driver = { .desc = "etnaviv DRM", .date = "20151214", .major = 1, - .minor = 3, + .minor = 4, }; /* diff --git a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c index 167971a09..e9b777ab3 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c @@ -73,6 +73,9 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { bool etnaviv_fill_identity_from_hwdb(struct etnaviv_gpu *gpu) { struct etnaviv_chip_identity *ident = &gpu->identity; + const u32 product_id = ident->product_id; + const u32 customer_id = ident->customer_id; + const u32 eco_id = ident->eco_id; int i; for (i = 0; i < ARRAY_SIZE(etnaviv_chip_identities); i++) { @@ -86,6 +89,12 @@ bool etnaviv_fill_identity_from_hwdb(struct etnaviv_gpu *gpu) etnaviv_chip_identities[i].eco_id == ~0U)) { memcpy(ident, &etnaviv_chip_identities[i], sizeof(*ident)); + + /* Restore some id values as ~0U aka 'don't care' might been used. */ + ident->product_id = product_id; + ident->customer_id = customer_id; + ident->eco_id = eco_id; + return true; } } diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index c277d2fc5..e43dfea09 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -318,9 +318,9 @@ static void decon_win_set_bldmod(struct decon_context *ctx, unsigned int win, static void decon_win_set_pixfmt(struct decon_context *ctx, unsigned int win, struct drm_framebuffer *fb) { - struct exynos_drm_plane plane = ctx->planes[win]; + struct exynos_drm_plane *plane = &ctx->planes[win]; struct exynos_drm_plane_state *state = - to_exynos_plane_state(plane.base.state); + to_exynos_plane_state(plane->base.state); unsigned int alpha = state->base.alpha; unsigned int pixel_alpha; unsigned long val; diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index dbd80f1e4..7e13c1550 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -344,6 +344,7 @@ err_mode_config_cleanup: drm_mode_config_cleanup(drm); exynos_drm_cleanup_dma(drm); kfree(private); + dev_set_drvdata(dev, NULL); err_free_drm: drm_dev_put(drm); @@ -358,6 +359,7 @@ static void exynos_drm_unbind(struct device *dev) exynos_drm_fbdev_fini(drm); drm_kms_helper_poll_fini(drm); + drm_atomic_helper_shutdown(drm); component_unbind_all(drm->dev, drm); drm_mode_config_cleanup(drm); @@ -395,9 +397,18 @@ static int exynos_drm_platform_remove(struct platform_device *pdev) return 0; } +static void exynos_drm_platform_shutdown(struct platform_device *pdev) +{ + struct drm_device *drm = platform_get_drvdata(pdev); + + if (drm) + drm_atomic_helper_shutdown(drm); +} + static struct platform_driver exynos_drm_platform_driver = { .probe = exynos_drm_platform_probe, .remove = exynos_drm_platform_remove, + .shutdown = exynos_drm_platform_shutdown, .driver = { .name = "exynos-drm", .pm = &exynos_drm_pm_ops, diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index bb67cad83..c045330f9 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -637,9 +637,9 @@ static void fimd_win_set_bldmod(struct fimd_context *ctx, unsigned int win, static void fimd_win_set_pixfmt(struct fimd_context *ctx, unsigned int win, struct drm_framebuffer *fb, int width) { - struct exynos_drm_plane plane = ctx->planes[win]; + struct exynos_drm_plane *plane = &ctx->planes[win]; struct exynos_drm_plane_state *state = - to_exynos_plane_state(plane.base.state); + to_exynos_plane_state(plane->base.state); uint32_t pixel_format = fb->format->format; unsigned int alpha = state->base.alpha; u32 val = WINCONx_ENWIN; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 45e9aee83..bcf830c5b 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -1344,7 +1344,7 @@ static int __maybe_unused gsc_runtime_resume(struct device *dev) for (i = 0; i < ctx->num_clocks; i++) { ret = clk_prepare_enable(ctx->clocks[i]); if (ret) { - while (--i > 0) + while (--i >= 0) clk_disable_unprepare(ctx->clocks[i]); return ret; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index e96436e11..e1ffe8a28 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -315,14 +315,14 @@ static int vidi_get_modes(struct drm_connector *connector) */ if (!ctx->raw_edid) { DRM_DEV_DEBUG_KMS(ctx->dev, "raw_edid is null.\n"); - return -EFAULT; + return 0; } edid_len = (1 + ctx->raw_edid->extensions) * EDID_LENGTH; edid = kmemdup(ctx->raw_edid, edid_len, GFP_KERNEL); if (!edid) { DRM_DEV_DEBUG_KMS(ctx->dev, "failed to allocate edid\n"); - return -ENOMEM; + return 0; } drm_connector_update_edid_property(connector, edid); diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index 981bffacd..576fcf180 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -878,11 +878,11 @@ static int hdmi_get_modes(struct drm_connector *connector) int ret; if (!hdata->ddc_adpt) - return -ENODEV; + return 0; edid = drm_get_edid(connector, hdata->ddc_adpt); if (!edid) - return -ENODEV; + return 0; hdata->dvi_mode = !drm_detect_hdmi_monitor(edid); DRM_DEV_DEBUG_KMS(hdata->dev, "%s : width[%d] x height[%d]\n", diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index f7b2e07e2..f9fdbd79c 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -250,9 +250,6 @@ static int __engine_park(struct intel_wakeref *wf) intel_engine_park_heartbeat(engine); intel_breadcrumbs_park(engine->breadcrumbs); - /* Must be reset upon idling, or we may miss the busy wakeup. */ - GEM_BUG_ON(engine->execlists.queue_priority_hint != INT_MIN); - if (engine->park) engine->park(engine); diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index ee9b33c3a..5a414d989 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -5032,6 +5032,9 @@ static void execlists_park(struct intel_engine_cs *engine) { cancel_timer(&engine->execlists.timer); cancel_timer(&engine->execlists.preempt); + + /* Reset upon idling, or we may delay the busy wakeup. */ + WRITE_ONCE(engine->execlists.queue_priority_hint, INT_MIN); } void intel_execlists_set_default_submission(struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index b61bfa84b..bcd6b9ee8 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -65,14 +65,14 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector) int ret; if (!mode) - return -EINVAL; + return 0; ret = of_get_drm_display_mode(np, &imxpd->mode, &imxpd->bus_flags, OF_USE_NATIVE_MODE); if (ret) { drm_mode_destroy(connector->dev, mode); - return ret; + return 0; } drm_mode_copy(mode, &imxpd->mode); diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c index 11223fe34..894175f2e 100644 --- a/drivers/gpu/drm/lima/lima_gem.c +++ b/drivers/gpu/drm/lima/lima_gem.c @@ -74,29 +74,34 @@ int lima_heap_alloc(struct lima_bo *bo, struct lima_vm *vm) } else { bo->base.sgt = kmalloc(sizeof(*bo->base.sgt), GFP_KERNEL); if (!bo->base.sgt) { - sg_free_table(&sgt); - return -ENOMEM; + ret = -ENOMEM; + goto err_out0; } } ret = dma_map_sgtable(dev, &sgt, DMA_BIDIRECTIONAL, 0); - if (ret) { - sg_free_table(&sgt); - kfree(bo->base.sgt); - bo->base.sgt = NULL; - return ret; - } + if (ret) + goto err_out1; *bo->base.sgt = sgt; if (vm) { ret = lima_vm_map_bo(vm, bo, old_size >> PAGE_SHIFT); if (ret) - return ret; + goto err_out2; } bo->heap_size = new_size; return 0; + +err_out2: + dma_unmap_sgtable(dev, &sgt, DMA_BIDIRECTIONAL, 0); +err_out1: + kfree(bo->base.sgt); + bo->base.sgt = NULL; +err_out0: + sg_free_table(&sgt); + return ret; } int lima_gem_create_handle(struct drm_device *dev, struct drm_file *file, diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 1eaf51316..d08827803 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -84,11 +84,13 @@ static void mtk_drm_crtc_finish_page_flip(struct mtk_drm_crtc *mtk_crtc) struct drm_crtc *crtc = &mtk_crtc->base; unsigned long flags; - spin_lock_irqsave(&crtc->dev->event_lock, flags); - drm_crtc_send_vblank_event(crtc, mtk_crtc->event); - drm_crtc_vblank_put(crtc); - mtk_crtc->event = NULL; - spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + if (mtk_crtc->event) { + spin_lock_irqsave(&crtc->dev->event_lock, flags); + drm_crtc_send_vblank_event(crtc, mtk_crtc->event); + drm_crtc_vblank_put(crtc); + mtk_crtc->event = NULL; + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + } } static void mtk_drm_finish_page_flip(struct mtk_drm_crtc *mtk_crtc) diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index a6e71b7b6..17d45f06c 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -68,8 +68,8 @@ #define DSI_PS_WC 0x3fff #define DSI_PS_SEL (3 << 16) #define PACKED_PS_16BIT_RGB565 (0 << 16) -#define LOOSELY_PS_18BIT_RGB666 (1 << 16) -#define PACKED_PS_18BIT_RGB666 (2 << 16) +#define PACKED_PS_18BIT_RGB666 (1 << 16) +#define LOOSELY_PS_24BIT_RGB666 (2 << 16) #define PACKED_PS_24BIT_RGB888 (3 << 16) #define DSI_VSA_NL 0x20 @@ -365,10 +365,10 @@ static void mtk_dsi_ps_control_vact(struct mtk_dsi *dsi) ps_bpp_mode |= PACKED_PS_24BIT_RGB888; break; case MIPI_DSI_FMT_RGB666: - ps_bpp_mode |= PACKED_PS_18BIT_RGB666; + ps_bpp_mode |= LOOSELY_PS_24BIT_RGB666; break; case MIPI_DSI_FMT_RGB666_PACKED: - ps_bpp_mode |= LOOSELY_PS_18BIT_RGB666; + ps_bpp_mode |= PACKED_PS_18BIT_RGB666; break; case MIPI_DSI_FMT_RGB565: ps_bpp_mode |= PACKED_PS_16BIT_RGB565; @@ -419,7 +419,7 @@ static void mtk_dsi_ps_control(struct mtk_dsi *dsi) dsi_tmp_buf_bpp = 3; break; case MIPI_DSI_FMT_RGB666: - tmp_reg = LOOSELY_PS_18BIT_RGB666; + tmp_reg = LOOSELY_PS_24BIT_RGB666; dsi_tmp_buf_bpp = 3; break; case MIPI_DSI_FMT_RGB666_PACKED: diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 408fc6c8a..44033a639 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -45,6 +45,9 @@ (p) ? ((p)->hw_pp ? (p)->hw_pp->idx - PINGPONG_0 : -1) : -1, \ ##__VA_ARGS__) +#define DPU_ERROR_ENC_RATELIMITED(e, fmt, ...) DPU_ERROR_RATELIMITED("enc%d " fmt,\ + (e) ? (e)->base.base.id : -1, ##__VA_ARGS__) + /* * Two to anticipate panels that can do cmd/vid dynamic switching * plan is to create all possible physical encoder types, and switch between @@ -2135,7 +2138,7 @@ static void dpu_encoder_frame_done_timeout(struct timer_list *t) return; } - DPU_ERROR_ENC(dpu_enc, "frame done timeout\n"); + DPU_ERROR_ENC_RATELIMITED(dpu_enc, "frame done timeout\n"); event = DPU_ENCODER_FRAME_EVENT_ERROR; trace_dpu_enc_frame_done_timeout(DRMID(drm_enc), event); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c index 805e059b5..33880f666 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c @@ -265,12 +265,14 @@ static void dpu_encoder_phys_vid_setup_timing_engine( mode.htotal >>= 1; mode.hsync_start >>= 1; mode.hsync_end >>= 1; + mode.hskew >>= 1; DPU_DEBUG_VIDENC(phys_enc, - "split_role %d, halve horizontal %d %d %d %d\n", + "split_role %d, halve horizontal %d %d %d %d %d\n", phys_enc->split_role, mode.hdisplay, mode.htotal, - mode.hsync_start, mode.hsync_end); + mode.hsync_start, mode.hsync_end, + mode.hskew); } drm_mode_to_intf_timing_params(phys_enc, &mode, &timing_params); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h index 1c0e4c0c9..bb7c7e437 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h @@ -52,6 +52,7 @@ } while (0) #define DPU_ERROR(fmt, ...) pr_err("[dpu error]" fmt, ##__VA_ARGS__) +#define DPU_ERROR_RATELIMITED(fmt, ...) pr_err_ratelimited("[dpu error]" fmt, ##__VA_ARGS__) /** * ktime_compare_safe - compare two ktime structures diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c index be986da78..172a33e8f 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.c +++ b/drivers/gpu/drm/msm/dp/dp_link.c @@ -7,6 +7,7 @@ #include <drm/drm_print.h> +#include "dp_reg.h" #include "dp_link.h" #include "dp_panel.h" @@ -1078,7 +1079,7 @@ int dp_link_process_request(struct dp_link *dp_link) int dp_link_get_colorimetry_config(struct dp_link *dp_link) { - u32 cc; + u32 cc = DP_MISC0_COLORIMERY_CFG_LEGACY_RGB; struct dp_link_private *link; if (!dp_link) { @@ -1092,10 +1093,11 @@ int dp_link_get_colorimetry_config(struct dp_link *dp_link) * Unless a video pattern CTS test is ongoing, use RGB_VESA * Only RGB_VESA and RGB_CEA supported for now */ - if (dp_link_is_video_pattern_requested(link)) - cc = link->dp_link.test_video.test_dyn_range; - else - cc = DP_TEST_DYNAMIC_RANGE_VESA; + if (dp_link_is_video_pattern_requested(link)) { + if (link->dp_link.test_video.test_dyn_range & + DP_TEST_DYNAMIC_RANGE_CEA) + cc = DP_MISC0_COLORIMERY_CFG_CEA_RGB; + } return cc; } diff --git a/drivers/gpu/drm/msm/dp/dp_reg.h b/drivers/gpu/drm/msm/dp/dp_reg.h index 268602803..176a503ec 100644 --- a/drivers/gpu/drm/msm/dp/dp_reg.h +++ b/drivers/gpu/drm/msm/dp/dp_reg.h @@ -129,6 +129,9 @@ #define DP_MISC0_COLORIMETRY_CFG_SHIFT (0x00000001) #define DP_MISC0_TEST_BITS_DEPTH_SHIFT (0x00000005) +#define DP_MISC0_COLORIMERY_CFG_LEGACY_RGB (0) +#define DP_MISC0_COLORIMERY_CFG_CEA_RGB (0x04) + #define REG_DP_VALID_BOUNDARY (0x00000030) #define REG_DP_VALID_BOUNDARY_2 (0x00000034) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index 10eacfd95..b49135f38 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -710,6 +710,10 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) goto fail; } + ret = devm_pm_runtime_enable(&pdev->dev); + if (ret) + return ret; + /* PLL init will call into clk_register which requires * register access, so we need to enable power and ahb clock. */ diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c index d204ea8a5..5cdf0d8d4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bios.c +++ b/drivers/gpu/drm/nouveau/nouveau_bios.c @@ -23,6 +23,7 @@ */ #include "nouveau_drv.h" +#include "nouveau_bios.h" #include "nouveau_reg.h" #include "dispnv04/hw.h" #include "nouveau_encoder.h" @@ -1672,7 +1673,7 @@ apply_dcb_encoder_quirks(struct drm_device *dev, int idx, u32 *conn, u32 *conf) */ if (nv_match_device(dev, 0x0201, 0x1462, 0x8851)) { if (*conn == 0xf2005014 && *conf == 0xffffffff) { - fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, 1); + fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, DCB_OUTPUT_B); return false; } } @@ -1758,26 +1759,26 @@ fabricate_dcb_encoder_table(struct drm_device *dev, struct nvbios *bios) #ifdef __powerpc__ /* Apple iMac G4 NV17 */ if (of_machine_is_compatible("PowerMac4,5")) { - fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, 1); - fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, 2); + fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, DCB_OUTPUT_B); + fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, DCB_OUTPUT_C); return; } #endif /* Make up some sane defaults */ fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, - bios->legacy.i2c_indices.crt, 1, 1); + bios->legacy.i2c_indices.crt, 1, DCB_OUTPUT_B); if (nv04_tv_identify(dev, bios->legacy.i2c_indices.tv) >= 0) fabricate_dcb_output(dcb, DCB_OUTPUT_TV, bios->legacy.i2c_indices.tv, - all_heads, 0); + all_heads, DCB_OUTPUT_A); else if (bios->tmds.output0_script_ptr || bios->tmds.output1_script_ptr) fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, bios->legacy.i2c_indices.panel, - all_heads, 1); + all_heads, DCB_OUTPUT_B); } static int diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c index a49e88129..ce1d53b85 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c @@ -108,6 +108,9 @@ nouveau_vma_new(struct nouveau_bo *nvbo, struct nouveau_vmm *vmm, } else { ret = nvif_vmm_get(&vmm->vmm, PTES, false, mem->mem.page, 0, mem->mem.size, &tmp); + if (ret) + goto done; + vma->addr = tmp.addr; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c index 4b571cc6b..6597def18 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c @@ -154,11 +154,17 @@ shadow_fw_init(struct nvkm_bios *bios, const char *name) return (void *)fw; } +static void +shadow_fw_release(void *fw) +{ + release_firmware(fw); +} + static const struct nvbios_source shadow_fw = { .name = "firmware", .init = shadow_fw_init, - .fini = (void(*)(void *))release_firmware, + .fini = shadow_fw_release, .read = shadow_fw_read, .rw = false, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c index 4bf486b57..cb05f7f48 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c @@ -66,11 +66,16 @@ of_init(struct nvkm_bios *bios, const char *name) return ERR_PTR(-EINVAL); } +static void of_fini(void *p) +{ + kfree(p); +} + const struct nvbios_source nvbios_of = { .name = "OpenFirmware", .init = of_init, - .fini = (void(*)(void *))kfree, + .fini = of_fini, .read = of_read, .size = of_size, .rw = false, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c index 02c4eb28c..f3db07325 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c @@ -221,8 +221,11 @@ nv50_instobj_acquire(struct nvkm_memory *memory) void __iomem *map = NULL; /* Already mapped? */ - if (refcount_inc_not_zero(&iobj->maps)) + if (refcount_inc_not_zero(&iobj->maps)) { + /* read barrier match the wmb on refcount set */ + smp_rmb(); return iobj->map; + } /* Take the lock, and re-check that another thread hasn't * already mapped the object in the meantime. @@ -249,6 +252,8 @@ nv50_instobj_acquire(struct nvkm_memory *memory) iobj->base.memory.ptrs = &nv50_instobj_fast; else iobj->base.memory.ptrs = &nv50_instobj_slow; + /* barrier to ensure the ptrs are written before refcount is set */ + smp_wmb(); refcount_set(&iobj->maps, 1); } diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index ee01b61a6..51470020b 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -3635,6 +3635,7 @@ static const struct panel_desc tianma_tm070jdhg30 = { }, .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG, .connector_type = DRM_MODE_CONNECTOR_LVDS, + .bus_flags = DRM_BUS_FLAG_DE_HIGH, }; static const struct panel_desc tianma_tm070jvhg33 = { @@ -3647,6 +3648,7 @@ static const struct panel_desc tianma_tm070jvhg33 = { }, .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG, .connector_type = DRM_MODE_CONNECTOR_LVDS, + .bus_flags = DRM_BUS_FLAG_DE_HIGH, }; static const struct display_timing tianma_tm070rvhg71_timing = { diff --git a/drivers/gpu/drm/panel/panel-visionox-rm69299.c b/drivers/gpu/drm/panel/panel-visionox-rm69299.c index eb43503ec..6134432e4 100644 --- a/drivers/gpu/drm/panel/panel-visionox-rm69299.c +++ b/drivers/gpu/drm/panel/panel-visionox-rm69299.c @@ -261,8 +261,6 @@ static int visionox_rm69299_remove(struct mipi_dsi_device *dsi) struct visionox_rm69299 *ctx = mipi_dsi_get_drvdata(dsi); mipi_dsi_detach(ctx->dsi); - mipi_dsi_device_unregister(ctx->dsi); - drm_panel_remove(&ctx->panel); return 0; } diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index 02feb0801..50c7430f8 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -826,7 +826,7 @@ int ni_init_microcode(struct radeon_device *rdev) err = 0; } else if (rdev->smc_fw->size != smc_req_size) { pr_err("ni_mc: Bogus length %zu in firmware \"%s\"\n", - rdev->mc_fw->size, fw_name); + rdev->smc_fw->size, fw_name); err = -EINVAL; } } diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c index 78120da5e..27540d308 100644 --- a/drivers/gpu/drm/rockchip/inno_hdmi.c +++ b/drivers/gpu/drm/rockchip/inno_hdmi.c @@ -402,7 +402,7 @@ static int inno_hdmi_config_video_timing(struct inno_hdmi *hdmi, hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HBLANK_L, value & 0xFF); hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HBLANK_H, (value >> 8) & 0xFF); - value = mode->hsync_start - mode->hdisplay; + value = mode->htotal - mode->hsync_start; hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HDELAY_L, value & 0xFF); hdmi_writeb(hdmi, HDMI_VIDEO_EXT_HDELAY_H, (value >> 8) & 0xFF); @@ -417,7 +417,7 @@ static int inno_hdmi_config_video_timing(struct inno_hdmi *hdmi, value = mode->vtotal - mode->vdisplay; hdmi_writeb(hdmi, HDMI_VIDEO_EXT_VBLANK, value & 0xFF); - value = mode->vsync_start - mode->vdisplay; + value = mode->vtotal - mode->vsync_start; hdmi_writeb(hdmi, HDMI_VIDEO_EXT_VDELAY, value & 0xFF); value = mode->vsync_end - mode->vsync_start; diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c index e2487937c..96c13c182 100644 --- a/drivers/gpu/drm/rockchip/rockchip_lvds.c +++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c @@ -572,8 +572,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master, ret = -EINVAL; goto err_put_port; } else if (ret) { - DRM_DEV_ERROR(dev, "failed to find panel and bridge node\n"); - ret = -EPROBE_DEFER; + dev_err_probe(dev, ret, "failed to find panel and bridge node\n"); goto err_put_port; } if (lvds->panel) diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c index de1333dc0..7bb26655c 100644 --- a/drivers/gpu/drm/tegra/dsi.c +++ b/drivers/gpu/drm/tegra/dsi.c @@ -1534,9 +1534,11 @@ static int tegra_dsi_ganged_probe(struct tegra_dsi *dsi) np = of_parse_phandle(dsi->dev->of_node, "nvidia,ganged-mode", 0); if (np) { struct platform_device *gangster = of_find_device_by_node(np); + of_node_put(np); + if (!gangster) + return -EPROBE_DEFER; dsi->slave = platform_get_drvdata(gangster); - of_node_put(np); if (!dsi->slave) { put_device(&gangster->dev); @@ -1584,48 +1586,58 @@ static int tegra_dsi_probe(struct platform_device *pdev) if (!pdev->dev.pm_domain) { dsi->rst = devm_reset_control_get(&pdev->dev, "dsi"); - if (IS_ERR(dsi->rst)) - return PTR_ERR(dsi->rst); + if (IS_ERR(dsi->rst)) { + err = PTR_ERR(dsi->rst); + goto remove; + } } dsi->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(dsi->clk)) { - dev_err(&pdev->dev, "cannot get DSI clock\n"); - return PTR_ERR(dsi->clk); + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->clk), + "cannot get DSI clock\n"); + goto remove; } dsi->clk_lp = devm_clk_get(&pdev->dev, "lp"); if (IS_ERR(dsi->clk_lp)) { - dev_err(&pdev->dev, "cannot get low-power clock\n"); - return PTR_ERR(dsi->clk_lp); + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->clk_lp), + "cannot get low-power clock\n"); + goto remove; } dsi->clk_parent = devm_clk_get(&pdev->dev, "parent"); if (IS_ERR(dsi->clk_parent)) { - dev_err(&pdev->dev, "cannot get parent clock\n"); - return PTR_ERR(dsi->clk_parent); + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->clk_parent), + "cannot get parent clock\n"); + goto remove; } dsi->vdd = devm_regulator_get(&pdev->dev, "avdd-dsi-csi"); if (IS_ERR(dsi->vdd)) { - dev_err(&pdev->dev, "cannot get VDD supply\n"); - return PTR_ERR(dsi->vdd); + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->vdd), + "cannot get VDD supply\n"); + goto remove; } err = tegra_dsi_setup_clocks(dsi); if (err < 0) { dev_err(&pdev->dev, "cannot setup clocks\n"); - return err; + goto remove; } regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); dsi->regs = devm_ioremap_resource(&pdev->dev, regs); - if (IS_ERR(dsi->regs)) - return PTR_ERR(dsi->regs); + if (IS_ERR(dsi->regs)) { + err = PTR_ERR(dsi->regs); + goto remove; + } dsi->mipi = tegra_mipi_request(&pdev->dev, pdev->dev.of_node); - if (IS_ERR(dsi->mipi)) - return PTR_ERR(dsi->mipi); + if (IS_ERR(dsi->mipi)) { + err = PTR_ERR(dsi->mipi); + goto remove; + } dsi->host.ops = &tegra_dsi_host_ops; dsi->host.dev = &pdev->dev; @@ -1653,9 +1665,12 @@ static int tegra_dsi_probe(struct platform_device *pdev) return 0; unregister: + pm_runtime_disable(&pdev->dev); mipi_dsi_host_unregister(&dsi->host); mipi_free: tegra_mipi_free(dsi->mipi); +remove: + tegra_output_remove(&dsi->output); return err; } diff --git a/drivers/gpu/drm/tegra/fb.c b/drivers/gpu/drm/tegra/fb.c index 01939c57f..2040dbfed 100644 --- a/drivers/gpu/drm/tegra/fb.c +++ b/drivers/gpu/drm/tegra/fb.c @@ -155,6 +155,7 @@ struct drm_framebuffer *tegra_fb_create(struct drm_device *drm, if (gem->size < size) { err = -EINVAL; + drm_gem_object_put(gem); goto unreference; } diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c index 47d26b5d9..7ccd010a8 100644 --- a/drivers/gpu/drm/tegra/output.c +++ b/drivers/gpu/drm/tegra/output.c @@ -139,8 +139,10 @@ int tegra_output_probe(struct tegra_output *output) GPIOD_IN, "HDMI hotplug detect"); if (IS_ERR(output->hpd_gpio)) { - if (PTR_ERR(output->hpd_gpio) != -ENOENT) - return PTR_ERR(output->hpd_gpio); + if (PTR_ERR(output->hpd_gpio) != -ENOENT) { + err = PTR_ERR(output->hpd_gpio); + goto put_i2c; + } output->hpd_gpio = NULL; } @@ -149,7 +151,7 @@ int tegra_output_probe(struct tegra_output *output) err = gpiod_to_irq(output->hpd_gpio); if (err < 0) { dev_err(output->dev, "gpiod_to_irq(): %d\n", err); - return err; + goto put_i2c; } output->hpd_irq = err; @@ -162,7 +164,7 @@ int tegra_output_probe(struct tegra_output *output) if (err < 0) { dev_err(output->dev, "failed to request IRQ#%u: %d\n", output->hpd_irq, err); - return err; + goto put_i2c; } output->connector.polled = DRM_CONNECTOR_POLL_HPD; @@ -176,6 +178,12 @@ int tegra_output_probe(struct tegra_output *output) } return 0; + +put_i2c: + if (output->ddc) + i2c_put_adapter(output->ddc); + + return err; } void tegra_output_remove(struct tegra_output *output) diff --git a/drivers/gpu/drm/tidss/tidss_crtc.c b/drivers/gpu/drm/tidss/tidss_crtc.c index 3c5744a91..26fd2761e 100644 --- a/drivers/gpu/drm/tidss/tidss_crtc.c +++ b/drivers/gpu/drm/tidss/tidss_crtc.c @@ -168,13 +168,13 @@ static void tidss_crtc_atomic_flush(struct drm_crtc *crtc, struct tidss_device *tidss = to_tidss(ddev); unsigned long flags; - dev_dbg(ddev->dev, - "%s: %s enabled %d, needs modeset %d, event %p\n", __func__, - crtc->name, drm_atomic_crtc_needs_modeset(crtc->state), - crtc->state->enable, crtc->state->event); + dev_dbg(ddev->dev, "%s: %s is %sactive, %s modeset, event %p\n", + __func__, crtc->name, crtc->state->active ? "" : "not ", + drm_atomic_crtc_needs_modeset(crtc->state) ? "needs" : "doesn't need", + crtc->state->event); /* There is nothing to do if CRTC is not going to be enabled. */ - if (!crtc->state->enable) + if (!crtc->state->active) return; /* diff --git a/drivers/gpu/drm/tidss/tidss_plane.c b/drivers/gpu/drm/tidss/tidss_plane.c index 43e72d0b2..e2ebd5fdc 100644 --- a/drivers/gpu/drm/tidss/tidss_plane.c +++ b/drivers/gpu/drm/tidss/tidss_plane.c @@ -202,7 +202,7 @@ struct tidss_plane *tidss_plane_create(struct tidss_device *tidss, drm_plane_helper_add(&tplane->plane, &tidss_plane_helper_funcs); - drm_plane_create_zpos_property(&tplane->plane, hw_plane_id, 0, + drm_plane_create_zpos_property(&tplane->plane, tidss->num_planes, 0, num_planes - 1); ret = drm_plane_create_color_properties(&tplane->plane, diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c index 89d50f38c..5af52012f 100644 --- a/drivers/gpu/drm/ttm/ttm_memory.c +++ b/drivers/gpu/drm/ttm/ttm_memory.c @@ -431,8 +431,10 @@ int ttm_mem_global_init(struct ttm_mem_global *glob) si_meminfo(&si); + spin_lock(&glob->lock); /* set it as 0 by default to keep original behavior of OOM */ glob->lower_mem_limit = 0; + spin_unlock(&glob->lock); ret = ttm_mem_init_kernel_zone(glob, &si); if (unlikely(ret != 0)) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 7e8620838..6d0125834 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -197,7 +197,7 @@ static int vc4_hdmi_connector_get_modes(struct drm_connector *connector) edid = drm_get_edid(connector, vc4_hdmi->ddc); cec_s_phys_addr_from_edid(vc4_hdmi->cec_adap, edid); if (!edid) - return -ENODEV; + return 0; vc4_encoder->hdmi_monitor = drm_detect_hdmi_monitor(edid); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c index f41550797..4da4bf3b7 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c @@ -713,7 +713,7 @@ static int vmw_binding_scrub_cb(struct vmw_ctx_bindinfo *bi, bool rebind) * without checking which bindings actually need to be emitted * * @cbs: Pointer to the context's struct vmw_ctx_binding_state - * @bi: Pointer to where the binding info array is stored in @cbs + * @biv: Pointer to where the binding info array is stored in @cbs * @max_num: Maximum number of entries in the @bi array. * * Scans the @bi array for bindings and builds a buffer of view id data. @@ -723,11 +723,9 @@ static int vmw_binding_scrub_cb(struct vmw_ctx_bindinfo *bi, bool rebind) * contains the command data. */ static void vmw_collect_view_ids(struct vmw_ctx_binding_state *cbs, - const struct vmw_ctx_bindinfo *bi, + const struct vmw_ctx_bindinfo_view *biv, u32 max_num) { - const struct vmw_ctx_bindinfo_view *biv = - container_of(bi, struct vmw_ctx_bindinfo_view, bi); unsigned long i; cbs->bind_cmd_count = 0; @@ -835,7 +833,7 @@ static int vmw_emit_set_sr(struct vmw_ctx_binding_state *cbs, */ static int vmw_emit_set_rt(struct vmw_ctx_binding_state *cbs) { - const struct vmw_ctx_bindinfo *loc = &cbs->render_targets[0].bi; + const struct vmw_ctx_bindinfo_view *loc = &cbs->render_targets[0]; struct { SVGA3dCmdHeader header; SVGA3dCmdDXSetRenderTargets body; @@ -871,7 +869,7 @@ static int vmw_emit_set_rt(struct vmw_ctx_binding_state *cbs) * without checking which bindings actually need to be emitted * * @cbs: Pointer to the context's struct vmw_ctx_binding_state - * @bi: Pointer to where the binding info array is stored in @cbs + * @biso: Pointer to where the binding info array is stored in @cbs * @max_num: Maximum number of entries in the @bi array. * * Scans the @bi array for bindings and builds a buffer of SVGA3dSoTarget data. @@ -881,11 +879,9 @@ static int vmw_emit_set_rt(struct vmw_ctx_binding_state *cbs) * contains the command data. */ static void vmw_collect_so_targets(struct vmw_ctx_binding_state *cbs, - const struct vmw_ctx_bindinfo *bi, + const struct vmw_ctx_bindinfo_so_target *biso, u32 max_num) { - const struct vmw_ctx_bindinfo_so_target *biso = - container_of(bi, struct vmw_ctx_bindinfo_so_target, bi); unsigned long i; SVGA3dSoTarget *so_buffer = (SVGA3dSoTarget *) cbs->bind_cmd_buffer; @@ -916,7 +912,7 @@ static void vmw_collect_so_targets(struct vmw_ctx_binding_state *cbs, */ static int vmw_emit_set_so_target(struct vmw_ctx_binding_state *cbs) { - const struct vmw_ctx_bindinfo *loc = &cbs->so_targets[0].bi; + const struct vmw_ctx_bindinfo_so_target *loc = &cbs->so_targets[0]; struct { SVGA3dCmdHeader header; SVGA3dCmdDXSetSOTargets body; @@ -1063,7 +1059,7 @@ static int vmw_emit_set_vb(struct vmw_ctx_binding_state *cbs) static int vmw_emit_set_uav(struct vmw_ctx_binding_state *cbs) { - const struct vmw_ctx_bindinfo *loc = &cbs->ua_views[0].views[0].bi; + const struct vmw_ctx_bindinfo_view *loc = &cbs->ua_views[0].views[0]; struct { SVGA3dCmdHeader header; SVGA3dCmdDXSetUAViews body; @@ -1093,7 +1089,7 @@ static int vmw_emit_set_uav(struct vmw_ctx_binding_state *cbs) static int vmw_emit_set_cs_uav(struct vmw_ctx_binding_state *cbs) { - const struct vmw_ctx_bindinfo *loc = &cbs->ua_views[1].views[0].bi; + const struct vmw_ctx_bindinfo_view *loc = &cbs->ua_views[1].views[0]; struct { SVGA3dCmdHeader header; SVGA3dCmdDXSetCSUAViews body; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c index e8d66182c..ea2f2f937 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c @@ -459,9 +459,9 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst, int ret = 0; /* Buffer objects need to be either pinned or reserved: */ - if (!(dst->mem.placement & TTM_PL_FLAG_NO_EVICT)) + if (!(dst->pin_count)) dma_resv_assert_held(dst->base.resv); - if (!(src->mem.placement & TTM_PL_FLAG_NO_EVICT)) + if (!(src->pin_count)) dma_resv_assert_held(src->base.resv); if (!ttm_tt_is_populated(dst->ttm)) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 813f1b148..9a66ba254 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -106,7 +106,7 @@ int vmw_bo_pin_in_placement(struct vmw_private *dev_priv, if (unlikely(ret != 0)) goto err; - if (buf->pin_count > 0) + if (buf->base.pin_count > 0) ret = ttm_bo_mem_compat(placement, &bo->mem, &new_flags) == true ? 0 : -EINVAL; else @@ -155,7 +155,7 @@ int vmw_bo_pin_in_vram_or_gmr(struct vmw_private *dev_priv, if (unlikely(ret != 0)) goto err; - if (buf->pin_count > 0) { + if (buf->base.pin_count > 0) { ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem, &new_flags) == true ? 0 : -EINVAL; goto out_unreserve; @@ -246,12 +246,12 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv, if (bo->mem.mem_type == TTM_PL_VRAM && bo->mem.start < bo->num_pages && bo->mem.start > 0 && - buf->pin_count == 0) { + buf->base.pin_count == 0) { ctx.interruptible = false; (void) ttm_bo_validate(bo, &vmw_sys_placement, &ctx); } - if (buf->pin_count > 0) + if (buf->base.pin_count > 0) ret = ttm_bo_mem_compat(&placement, &bo->mem, &new_flags) == true ? 0 : -EINVAL; else @@ -343,23 +343,13 @@ void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin) dma_resv_assert_held(bo->base.resv); - if (pin) { - if (vbo->pin_count++ > 0) - return; - } else { - WARN_ON(vbo->pin_count <= 0); - if (--vbo->pin_count > 0) - return; - } + if (pin == !!bo->pin_count) + return; pl.fpfn = 0; pl.lpfn = 0; pl.mem_type = bo->mem.mem_type; pl.flags = bo->mem.placement; - if (pin) - pl.flags |= TTM_PL_FLAG_NO_EVICT; - else - pl.flags &= ~TTM_PL_FLAG_NO_EVICT; memset(&placement, 0, sizeof(placement)); placement.num_placement = 1; @@ -368,8 +358,12 @@ void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin) ret = ttm_bo_validate(bo, &placement, &ctx); BUG_ON(ret != 0 || bo->mem.mem_type != old_mem_type); -} + if (pin) + ttm_bo_pin(bo); + else + ttm_bo_unpin(bo); +} /** * vmw_bo_map_and_cache - Map a buffer object and cache the map @@ -487,6 +481,49 @@ static void vmw_user_bo_destroy(struct ttm_buffer_object *bo) ttm_prime_object_kfree(vmw_user_bo, prime); } +/** + * vmw_bo_create_kernel - Create a pinned BO for internal kernel use. + * + * @dev_priv: Pointer to the device private struct + * @size: size of the BO we need + * @placement: where to put it + * @p_bo: resulting BO + * + * Creates and pin a simple BO for in kernel use. + */ +int vmw_bo_create_kernel(struct vmw_private *dev_priv, unsigned long size, + struct ttm_placement *placement, + struct ttm_buffer_object **p_bo) +{ + unsigned npages = PAGE_ALIGN(size) >> PAGE_SHIFT; + struct ttm_operation_ctx ctx = { false, false }; + struct ttm_buffer_object *bo; + size_t acc_size; + int ret; + + bo = kzalloc(sizeof(*bo), GFP_KERNEL); + if (unlikely(!bo)) + return -ENOMEM; + + acc_size = ttm_round_pot(sizeof(*bo)); + acc_size += ttm_round_pot(npages * sizeof(void *)); + acc_size += ttm_round_pot(sizeof(struct ttm_tt)); + ret = ttm_bo_init_reserved(&dev_priv->bdev, bo, size, + ttm_bo_type_device, placement, 0, + &ctx, acc_size, NULL, NULL, NULL); + if (unlikely(ret)) + goto error_free; + + ttm_bo_pin(bo); + ttm_bo_unreserve(bo); + *p_bo = bo; + + return 0; + +error_free: + kfree(bo); + return ret; +} /** * vmw_bo_init - Initialize a vmw buffer object @@ -496,6 +533,7 @@ static void vmw_user_bo_destroy(struct ttm_buffer_object *bo) * @size: Buffer object size in bytes. * @placement: Initial placement. * @interruptible: Whether waits should be performed interruptible. + * @pin: If the BO should be created pinned at a fixed location. * @bo_free: The buffer object destructor. * Returns: Zero on success, negative error code on error. * @@ -504,9 +542,10 @@ static void vmw_user_bo_destroy(struct ttm_buffer_object *bo) int vmw_bo_init(struct vmw_private *dev_priv, struct vmw_buffer_object *vmw_bo, size_t size, struct ttm_placement *placement, - bool interruptible, + bool interruptible, bool pin, void (*bo_free)(struct ttm_buffer_object *bo)) { + struct ttm_operation_ctx ctx = { interruptible, false }; struct ttm_bo_device *bdev = &dev_priv->bdev; size_t acc_size; int ret; @@ -520,11 +559,16 @@ int vmw_bo_init(struct vmw_private *dev_priv, vmw_bo->base.priority = 3; vmw_bo->res_tree = RB_ROOT; - ret = ttm_bo_init(bdev, &vmw_bo->base, size, - ttm_bo_type_device, placement, - 0, interruptible, acc_size, - NULL, NULL, bo_free); - return ret; + ret = ttm_bo_init_reserved(bdev, &vmw_bo->base, size, + ttm_bo_type_device, placement, + 0, &ctx, acc_size, NULL, NULL, bo_free); + if (unlikely(ret)) + return ret; + + if (pin) + ttm_bo_pin(&vmw_bo->base); + ttm_bo_unreserve(&vmw_bo->base); + return 0; } @@ -613,7 +657,7 @@ int vmw_user_bo_alloc(struct vmw_private *dev_priv, ret = vmw_bo_init(dev_priv, &user_bo->vbo, size, (dev_priv->has_mob) ? &vmw_sys_placement : - &vmw_vram_sys_placement, true, + &vmw_vram_sys_placement, true, false, &vmw_user_bo_destroy); if (unlikely(ret != 0)) return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c index 3b41cf631..87a39721e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c @@ -514,7 +514,7 @@ static void vmw_cmdbuf_work_func(struct work_struct *work) struct vmw_cmdbuf_man *man = container_of(work, struct vmw_cmdbuf_man, work); struct vmw_cmdbuf_header *entry, *next; - uint32_t dummy; + uint32_t dummy = 0; bool send_fence = false; struct list_head restart_head[SVGA_CB_CONTEXT_MAX]; int i; @@ -1245,9 +1245,9 @@ int vmw_cmdbuf_set_pool_size(struct vmw_cmdbuf_man *man, !dev_priv->has_mob) return -ENOMEM; - ret = ttm_bo_create(&dev_priv->bdev, size, ttm_bo_type_device, - &vmw_mob_ne_placement, 0, false, - &man->cmd_space); + ret = vmw_bo_create_kernel(dev_priv, size, + &vmw_mob_placement, + &man->cmd_space); if (ret) return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c index 44d858ce4..f212368c0 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c @@ -168,8 +168,8 @@ void vmw_cmdbuf_res_revert(struct list_head *list) vmw_cmdbuf_res_free(entry->man, entry); break; case VMW_CMDBUF_RES_DEL: - ret = drm_ht_insert_item(&entry->man->resources, - &entry->hash); + ret = drm_ht_insert_item(&entry->man->resources, &entry->hash); + BUG_ON(ret); list_del(&entry->head); list_add_tail(&entry->head, &entry->man->list); entry->state = VMW_CMDBUF_RES_COMMITTED; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c index 65e8e7a97..984d88843 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c @@ -410,8 +410,8 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size) if (!buf) return -ENOMEM; - ret = vmw_bo_init(dev_priv, buf, new_size, &vmw_mob_ne_placement, - true, vmw_bo_bo_free); + ret = vmw_bo_init(dev_priv, buf, new_size, &vmw_mob_placement, + true, true, vmw_bo_bo_free); if (ret) { DRM_ERROR("Failed initializing new cotable MOB.\n"); return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 31e3e5c9f..bdb7a5e96 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -372,7 +372,7 @@ static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv) return -ENOMEM; ret = vmw_bo_init(dev_priv, vbo, PAGE_SIZE, - &vmw_sys_ne_placement, false, + &vmw_sys_placement, false, true, &vmw_bo_bo_free); if (unlikely(ret != 0)) return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 0a79c57c7..fa285c20d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -99,7 +99,6 @@ struct vmw_fpriv { * struct vmw_buffer_object - TTM buffer object with vmwgfx additions * @base: The TTM buffer object * @res_tree: RB tree of resources using this buffer object as a backing MOB - * @pin_count: pin depth * @cpu_writers: Number of synccpu write grabs. Protected by reservation when * increased. May be decreased without reservation. * @dx_query_ctx: DX context if this buffer object is used as a DX query MOB @@ -110,7 +109,6 @@ struct vmw_fpriv { struct vmw_buffer_object { struct ttm_buffer_object base; struct rb_root res_tree; - s32 pin_count; atomic_t cpu_writers; /* Not ref-counted. Protected by binding_mutex */ struct vmw_resource *dx_query_ctx; @@ -845,10 +843,14 @@ extern void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *buf, SVGAGuestPtr *ptr); extern void vmw_bo_pin_reserved(struct vmw_buffer_object *bo, bool pin); extern void vmw_bo_bo_free(struct ttm_buffer_object *bo); +extern int vmw_bo_create_kernel(struct vmw_private *dev_priv, + unsigned long size, + struct ttm_placement *placement, + struct ttm_buffer_object **p_bo); extern int vmw_bo_init(struct vmw_private *dev_priv, struct vmw_buffer_object *vmw_bo, size_t size, struct ttm_placement *placement, - bool interruptible, + bool interruptible, bool pin, void (*bo_free)(struct ttm_buffer_object *bo)); extern int vmw_user_bo_verify_access(struct ttm_buffer_object *bo, struct ttm_object_file *tfile); @@ -1005,16 +1007,13 @@ extern void vmw_validation_mem_init_ttm(struct vmw_private *dev_priv, extern const size_t vmw_tt_size; extern struct ttm_placement vmw_vram_placement; -extern struct ttm_placement vmw_vram_ne_placement; extern struct ttm_placement vmw_vram_sys_placement; extern struct ttm_placement vmw_vram_gmr_placement; extern struct ttm_placement vmw_vram_gmr_ne_placement; extern struct ttm_placement vmw_sys_placement; -extern struct ttm_placement vmw_sys_ne_placement; extern struct ttm_placement vmw_evictable_placement; extern struct ttm_placement vmw_srf_placement; extern struct ttm_placement vmw_mob_placement; -extern struct ttm_placement vmw_mob_ne_placement; extern struct ttm_placement vmw_nonfixed_placement; extern struct ttm_bo_driver vmw_bo_driver; extern const struct vmw_sg_table * diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 00082c679..616f6cb62 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -467,7 +467,7 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv, vmw_res_type(ctx) == vmw_res_dx_context) { for (i = 0; i < cotable_max; ++i) { res = vmw_context_cotable(ctx, i); - if (IS_ERR(res)) + if (IS_ERR_OR_NULL(res)) continue; ret = vmw_execbuf_res_noctx_val_add(sw_context, res, @@ -1272,6 +1272,8 @@ static int vmw_cmd_dx_define_query(struct vmw_private *dev_priv, return -EINVAL; cotable_res = vmw_context_cotable(ctx_node->ctx, SVGA_COTABLE_DXQUERY); + if (IS_ERR_OR_NULL(cotable_res)) + return cotable_res ? PTR_ERR(cotable_res) : -EINVAL; ret = vmw_cotable_notify(cotable_res, cmd->body.queryId); return ret; @@ -2450,6 +2452,8 @@ static int vmw_cmd_dx_view_define(struct vmw_private *dev_priv, return ret; res = vmw_context_cotable(ctx_node->ctx, vmw_view_cotables[view_type]); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; ret = vmw_cotable_notify(res, cmd->defined_id); if (unlikely(ret != 0)) return ret; @@ -2535,6 +2539,8 @@ static int vmw_cmd_dx_so_define(struct vmw_private *dev_priv, so_type = vmw_so_cmd_to_type(header->id); res = vmw_context_cotable(ctx_node->ctx, vmw_so_cotables[so_type]); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; cmd = container_of(header, typeof(*cmd), header); ret = vmw_cotable_notify(res, cmd->defined_id); @@ -2653,6 +2659,8 @@ static int vmw_cmd_dx_define_shader(struct vmw_private *dev_priv, return -EINVAL; res = vmw_context_cotable(ctx_node->ctx, SVGA_COTABLE_DXSHADER); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; ret = vmw_cotable_notify(res, cmd->body.shaderId); if (ret) return ret; @@ -2974,6 +2982,8 @@ static int vmw_cmd_dx_define_streamoutput(struct vmw_private *dev_priv, } res = vmw_context_cotable(ctx_node->ctx, SVGA_COTABLE_STREAMOUTPUT); + if (IS_ERR_OR_NULL(res)) + return res ? PTR_ERR(res) : -EINVAL; ret = vmw_cotable_notify(res, cmd->body.soid); if (ret) return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c index 97d9d2557..3923acc3a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c @@ -406,7 +406,7 @@ static int vmw_fb_create_bo(struct vmw_private *vmw_priv, ret = vmw_bo_init(vmw_priv, vmw_bo, size, &vmw_sys_placement, - false, + false, false, &vmw_bo_bo_free); if (unlikely(ret != 0)) goto err_unlock; /* init frees the buffer on failure */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c index 7f95ed6aa..fb0797b38 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c @@ -494,11 +494,13 @@ static void vmw_mob_pt_setup(struct vmw_mob *mob, { unsigned long num_pt_pages = 0; struct ttm_buffer_object *bo = mob->pt_bo; - struct vmw_piter save_pt_iter; + struct vmw_piter save_pt_iter = {0}; struct vmw_piter pt_iter; const struct vmw_sg_table *vsgt; int ret; + BUG_ON(num_data_pages == 0); + ret = ttm_bo_reserve(bo, false, true, NULL); BUG_ON(ret != 0); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c index 15b5bde69..751582f5a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c @@ -154,6 +154,7 @@ static unsigned long vmw_port_hb_out(struct rpc_channel *channel, /* HB port can't access encrypted memory. */ if (hb && !mem_encrypt_active()) { unsigned long bp = channel->cookie_high; + u32 channel_id = (channel->channel_id << 16); si = (uintptr_t) msg; di = channel->cookie_low; @@ -161,7 +162,7 @@ static unsigned long vmw_port_hb_out(struct rpc_channel *channel, VMW_PORT_HB_OUT( (MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG, msg_len, si, di, - VMWARE_HYPERVISOR_HB | (channel->channel_id << 16) | + VMWARE_HYPERVISOR_HB | channel_id | VMWARE_HYPERVISOR_OUT, VMW_HYPERVISOR_MAGIC, bp, eax, ebx, ecx, edx, si, di); @@ -209,6 +210,7 @@ static unsigned long vmw_port_hb_in(struct rpc_channel *channel, char *reply, /* HB port can't access encrypted memory */ if (hb && !mem_encrypt_active()) { unsigned long bp = channel->cookie_low; + u32 channel_id = (channel->channel_id << 16); si = channel->cookie_high; di = (uintptr_t) reply; @@ -216,7 +218,7 @@ static unsigned long vmw_port_hb_in(struct rpc_channel *channel, char *reply, VMW_PORT_HB_IN( (MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG, reply_len, si, di, - VMWARE_HYPERVISOR_HB | (channel->channel_id << 16), + VMWARE_HYPERVISOR_HB | channel_id, VMW_HYPERVISOR_MAGIC, bp, eax, ebx, ecx, edx, si, di); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index c0f156078..26f88d648 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -114,6 +114,7 @@ static void vmw_resource_release(struct kref *kref) container_of(kref, struct vmw_resource, kref); struct vmw_private *dev_priv = res->dev_priv; int id; + int ret; struct idr *idr = &dev_priv->res_idr[res->func->res_type]; spin_lock(&dev_priv->resource_lock); @@ -122,7 +123,8 @@ static void vmw_resource_release(struct kref *kref) if (res->backup) { struct ttm_buffer_object *bo = &res->backup->base; - ttm_bo_reserve(bo, false, false, NULL); + ret = ttm_bo_reserve(bo, false, false, NULL); + BUG_ON(ret); if (vmw_resource_mob_attached(res) && res->func->unbind != NULL) { struct ttm_validate_buffer val_buf; @@ -370,7 +372,7 @@ static int vmw_resource_buf_alloc(struct vmw_resource *res, ret = vmw_bo_init(res->dev_priv, backup, res->backup_size, res->func->backup_placement, - interruptible, + interruptible, false, &vmw_bo_bo_free); if (unlikely(ret != 0)) goto out_no_bo; @@ -1001,8 +1003,10 @@ int vmw_resource_pin(struct vmw_resource *res, bool interruptible) if (res->backup) { vbo = res->backup; - ttm_bo_reserve(&vbo->base, interruptible, false, NULL); - if (!vbo->pin_count) { + ret = ttm_bo_reserve(&vbo->base, interruptible, false, NULL); + if (ret) + goto out_no_validate; + if (!vbo->base.pin_count) { ret = ttm_bo_validate (&vbo->base, res->func->backup_placement, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c index 2b6590344..9c8109efe 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c @@ -451,8 +451,8 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane, */ vmw_overlay_pause_all(dev_priv); ret = vmw_bo_init(dev_priv, vps->bo, size, - &vmw_vram_ne_placement, - false, &vmw_bo_bo_free); + &vmw_vram_placement, + false, true, &vmw_bo_bo_free); vmw_overlay_resume_all(dev_priv); if (ret) { vps->bo = NULL; /* vmw_bo_init frees on error */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index e139fdfd1..f328aa583 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -978,8 +978,8 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv, if (unlikely(!buf)) return -ENOMEM; - ret = vmw_bo_init(dev_priv, buf, size, &vmw_sys_ne_placement, - true, vmw_bo_bo_free); + ret = vmw_bo_init(dev_priv, buf, size, &vmw_sys_placement, + true, true, vmw_bo_bo_free); if (unlikely(ret != 0)) goto out; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_so.c b/drivers/gpu/drm/vmwgfx/vmwgfx_so.c index 3f97b61dd..9330f1a0f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_so.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_so.c @@ -538,7 +538,8 @@ const SVGACOTableType vmw_so_cotables[] = { [vmw_so_ds] = SVGA_COTABLE_DEPTHSTENCIL, [vmw_so_rs] = SVGA_COTABLE_RASTERIZERSTATE, [vmw_so_ss] = SVGA_COTABLE_SAMPLER, - [vmw_so_so] = SVGA_COTABLE_STREAMOUTPUT + [vmw_so_so] = SVGA_COTABLE_STREAMOUTPUT, + [vmw_so_max]= SVGA_COTABLE_MAX }; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index 73116ec70..89b3356ec 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -37,13 +37,6 @@ static const struct ttm_place vram_placement_flags = { .flags = TTM_PL_FLAG_CACHED }; -static const struct ttm_place vram_ne_placement_flags = { - .fpfn = 0, - .lpfn = 0, - .mem_type = TTM_PL_VRAM, - .flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT -}; - static const struct ttm_place sys_placement_flags = { .fpfn = 0, .lpfn = 0, @@ -51,13 +44,6 @@ static const struct ttm_place sys_placement_flags = { .flags = TTM_PL_FLAG_CACHED }; -static const struct ttm_place sys_ne_placement_flags = { - .fpfn = 0, - .lpfn = 0, - .mem_type = TTM_PL_SYSTEM, - .flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT -}; - static const struct ttm_place gmr_placement_flags = { .fpfn = 0, .lpfn = 0, @@ -79,13 +65,6 @@ static const struct ttm_place mob_placement_flags = { .flags = TTM_PL_FLAG_CACHED }; -static const struct ttm_place mob_ne_placement_flags = { - .fpfn = 0, - .lpfn = 0, - .mem_type = VMW_PL_MOB, - .flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT -}; - struct ttm_placement vmw_vram_placement = { .num_placement = 1, .placement = &vram_placement_flags, @@ -158,13 +137,6 @@ struct ttm_placement vmw_vram_sys_placement = { .busy_placement = &sys_placement_flags }; -struct ttm_placement vmw_vram_ne_placement = { - .num_placement = 1, - .placement = &vram_ne_placement_flags, - .num_busy_placement = 1, - .busy_placement = &vram_ne_placement_flags -}; - struct ttm_placement vmw_sys_placement = { .num_placement = 1, .placement = &sys_placement_flags, @@ -172,13 +144,6 @@ struct ttm_placement vmw_sys_placement = { .busy_placement = &sys_placement_flags }; -struct ttm_placement vmw_sys_ne_placement = { - .num_placement = 1, - .placement = &sys_ne_placement_flags, - .num_busy_placement = 1, - .busy_placement = &sys_ne_placement_flags -}; - static const struct ttm_place evictable_placement_flags[] = { { .fpfn = 0, @@ -243,13 +208,6 @@ struct ttm_placement vmw_mob_placement = { .busy_placement = &mob_placement_flags }; -struct ttm_placement vmw_mob_ne_placement = { - .num_placement = 1, - .num_busy_placement = 1, - .placement = &mob_ne_placement_flags, - .busy_placement = &mob_ne_placement_flags -}; - struct ttm_placement vmw_nonfixed_placement = { .num_placement = 3, .placement = nonfixed_placement_flags, @@ -817,11 +775,9 @@ int vmw_bo_create_and_populate(struct vmw_private *dev_priv, struct ttm_buffer_object *bo; int ret; - ret = ttm_bo_create(&dev_priv->bdev, bo_size, - ttm_bo_type_device, - &vmw_sys_ne_placement, - 0, false, &bo); - + ret = vmw_bo_create_kernel(dev_priv, bo_size, + &vmw_sys_placement, + &bo); if (unlikely(ret != 0)) return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c index e69bc373a..cc1cfc827 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c @@ -540,7 +540,7 @@ int vmw_validation_bo_validate_single(struct ttm_buffer_object *bo, if (atomic_read(&vbo->cpu_writers)) return -EBUSY; - if (vbo->pin_count > 0) + if (vbo->base.pin_count > 0) return 0; if (validate_as_mob) @@ -585,13 +585,13 @@ int vmw_validation_bo_validate(struct vmw_validation_context *ctx, bool intr) container_of(entry->base.bo, typeof(*vbo), base); if (entry->cpu_blit) { - struct ttm_operation_ctx ctx = { + struct ttm_operation_ctx ttm_ctx = { .interruptible = intr, .no_wait_gpu = false }; ret = ttm_bo_validate(entry->base.bo, - &vmw_nonfixed_placement, &ctx); + &vmw_nonfixed_placement, &ttm_ctx); } else { ret = vmw_validation_bo_validate_single (entry->base.bo, intr, entry->as_mob); diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index e5d2e7e95..0dc55465b 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -70,6 +70,28 @@ struct apple_key_translation { u8 flags; }; +static const struct apple_key_translation apple2021_fn_keys[] = { + { KEY_BACKSPACE, KEY_DELETE }, + { KEY_ENTER, KEY_INSERT }, + { KEY_F1, KEY_BRIGHTNESSDOWN, APPLE_FLAG_FKEY }, + { KEY_F2, KEY_BRIGHTNESSUP, APPLE_FLAG_FKEY }, + { KEY_F3, KEY_SCALE, APPLE_FLAG_FKEY }, + { KEY_F4, KEY_SEARCH, APPLE_FLAG_FKEY }, + { KEY_F5, KEY_MICMUTE, APPLE_FLAG_FKEY }, + { KEY_F6, KEY_SLEEP, APPLE_FLAG_FKEY }, + { KEY_F7, KEY_PREVIOUSSONG, APPLE_FLAG_FKEY }, + { KEY_F8, KEY_PLAYPAUSE, APPLE_FLAG_FKEY }, + { KEY_F9, KEY_NEXTSONG, APPLE_FLAG_FKEY }, + { KEY_F10, KEY_MUTE, APPLE_FLAG_FKEY }, + { KEY_F11, KEY_VOLUMEDOWN, APPLE_FLAG_FKEY }, + { KEY_F12, KEY_VOLUMEUP, APPLE_FLAG_FKEY }, + { KEY_UP, KEY_PAGEUP }, + { KEY_DOWN, KEY_PAGEDOWN }, + { KEY_LEFT, KEY_HOME }, + { KEY_RIGHT, KEY_END }, + { } +}; + static const struct apple_key_translation macbookair_fn_keys[] = { { KEY_BACKSPACE, KEY_DELETE }, { KEY_ENTER, KEY_INSERT }, @@ -204,7 +226,9 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input, } if (fnmode) { - if (hid->product >= USB_DEVICE_ID_APPLE_WELLSPRING4_ANSI && + if (hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021) + table = apple2021_fn_keys; + else if (hid->product >= USB_DEVICE_ID_APPLE_WELLSPRING4_ANSI && hid->product <= USB_DEVICE_ID_APPLE_WELLSPRING4A_JIS) table = macbookair_fn_keys; else if (hid->product < 0x21d || hid->product >= 0x300) @@ -363,6 +387,9 @@ static void apple_setup_input(struct input_dev *input) for (trans = apple_iso_keyboard; trans->from; trans++) set_bit(trans->to, input->keybit); + for (trans = apple2021_fn_keys; trans->from; trans++) + set_bit(trans->to, input->keybit); + if (swap_fn_leftctrl) { for (trans = swapped_fn_leftctrl_keys; trans->from; trans++) set_bit(trans->to, input->keybit); @@ -624,6 +651,10 @@ static const struct hid_device_id apple_devices[] = { .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY), .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021), + .driver_data = APPLE_HAS_FN }, + { HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021), + .driver_data = APPLE_HAS_FN }, { } }; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 6273ab615..0732fe6c7 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -173,6 +173,7 @@ #define USB_DEVICE_ID_APPLE_IRCONTROL3 0x8241 #define USB_DEVICE_ID_APPLE_IRCONTROL4 0x8242 #define USB_DEVICE_ID_APPLE_IRCONTROL5 0x8243 +#define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021 0x029c #define USB_VENDOR_ID_ASUS 0x0486 #define USB_DEVICE_ID_ASUS_T91MT 0x0185 diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index 249af8d26..c9fdeffbe 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -53,10 +53,10 @@ struct lenovo_drvdata { /* 0: Up * 1: Down (undecided) * 2: Scrolling - * 3: Patched firmware, disable workaround */ u8 middlebutton_state; bool fn_lock; + bool middleclick_workaround_cptkbd; }; #define map_key_clear(c) hid_map_usage_clear(hi, usage, bit, max, EV_KEY, (c)) @@ -418,6 +418,36 @@ static ssize_t attr_sensitivity_store_cptkbd(struct device *dev, return count; } +static ssize_t attr_middleclick_workaround_show_cptkbd(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hid_device *hdev = to_hid_device(dev); + struct lenovo_drvdata *cptkbd_data = hid_get_drvdata(hdev); + + return snprintf(buf, PAGE_SIZE, "%u\n", + cptkbd_data->middleclick_workaround_cptkbd); +} + +static ssize_t attr_middleclick_workaround_store_cptkbd(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t count) +{ + struct hid_device *hdev = to_hid_device(dev); + struct lenovo_drvdata *cptkbd_data = hid_get_drvdata(hdev); + int value; + + if (kstrtoint(buf, 10, &value)) + return -EINVAL; + if (value < 0 || value > 1) + return -EINVAL; + + cptkbd_data->middleclick_workaround_cptkbd = !!value; + + return count; +} + static struct device_attribute dev_attr_fn_lock = __ATTR(fn_lock, S_IWUSR | S_IRUGO, @@ -429,10 +459,16 @@ static struct device_attribute dev_attr_sensitivity_cptkbd = attr_sensitivity_show_cptkbd, attr_sensitivity_store_cptkbd); +static struct device_attribute dev_attr_middleclick_workaround_cptkbd = + __ATTR(middleclick_workaround, S_IWUSR | S_IRUGO, + attr_middleclick_workaround_show_cptkbd, + attr_middleclick_workaround_store_cptkbd); + static struct attribute *lenovo_attributes_cptkbd[] = { &dev_attr_fn_lock.attr, &dev_attr_sensitivity_cptkbd.attr, + &dev_attr_middleclick_workaround_cptkbd.attr, NULL }; @@ -483,23 +519,7 @@ static int lenovo_event_cptkbd(struct hid_device *hdev, { struct lenovo_drvdata *cptkbd_data = hid_get_drvdata(hdev); - if (cptkbd_data->middlebutton_state != 3) { - /* REL_X and REL_Y events during middle button pressed - * are only possible on patched, bug-free firmware - * so set middlebutton_state to 3 - * to never apply workaround anymore - */ - if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD && - cptkbd_data->middlebutton_state == 1 && - usage->type == EV_REL && - (usage->code == REL_X || usage->code == REL_Y)) { - cptkbd_data->middlebutton_state = 3; - /* send middle button press which was hold before */ - input_event(field->hidinput->input, - EV_KEY, BTN_MIDDLE, 1); - input_sync(field->hidinput->input); - } - + if (cptkbd_data->middleclick_workaround_cptkbd) { /* "wheel" scroll events */ if (usage->type == EV_REL && (usage->code == REL_WHEEL || usage->code == REL_HWHEEL)) { @@ -976,6 +996,7 @@ static int lenovo_probe_cptkbd(struct hid_device *hdev) cptkbd_data->middlebutton_state = 0; cptkbd_data->fn_lock = true; cptkbd_data->sensitivity = 0x05; + cptkbd_data->middleclick_workaround_cptkbd = true; lenovo_features_set_cptkbd(hdev); ret = sysfs_create_group(&hdev->dev.kobj, &lenovo_attr_group_cptkbd); diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 7d43d62df..8dcd636da 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -2069,6 +2069,10 @@ static const struct hid_device_id mt_devices[] = { { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_SYNAPTICS, 0xcddc) }, + + { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, + HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, USB_VENDOR_ID_SYNAPTICS, 0xce08) }, { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 1b3a83fa7..67953cdae 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -309,6 +309,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_ANSI) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021) }, #endif #if IS_ENABLED(CONFIG_HID_APPLEIR) { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_IRCONTROL) }, diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 14811d42a..4f8e8f392 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -56,7 +56,6 @@ /* flags */ #define I2C_HID_STARTED 0 #define I2C_HID_RESET_PENDING 1 -#define I2C_HID_READ_PENDING 2 #define I2C_HID_PWR_ON 0x00 #define I2C_HID_PWR_SLEEP 0x01 @@ -256,7 +255,6 @@ static int __i2c_hid_command(struct i2c_client *client, msg[1].len = data_len; msg[1].buf = buf_recv; msg_num = 2; - set_bit(I2C_HID_READ_PENDING, &ihid->flags); } if (wait) @@ -264,9 +262,6 @@ static int __i2c_hid_command(struct i2c_client *client, ret = i2c_transfer(client->adapter, msg, msg_num); - if (data_len > 0) - clear_bit(I2C_HID_READ_PENDING, &ihid->flags); - if (ret != msg_num) return ret < 0 ? ret : -EIO; @@ -538,9 +533,6 @@ static irqreturn_t i2c_hid_irq(int irq, void *dev_id) { struct i2c_hid *ihid = dev_id; - if (test_bit(I2C_HID_READ_PENDING, &ihid->flags)) - return IRQ_HANDLED; - i2c_hid_get_input(ihid); return IRQ_HANDLED; diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 1a7e1d3e7..eacbd7eae 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2088,7 +2088,7 @@ static int wacom_allocate_inputs(struct wacom *wacom) return 0; } -static int wacom_register_inputs(struct wacom *wacom) +static int wacom_setup_inputs(struct wacom *wacom) { struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev; struct wacom_wac *wacom_wac = &(wacom->wacom_wac); @@ -2107,10 +2107,6 @@ static int wacom_register_inputs(struct wacom *wacom) input_free_device(pen_input_dev); wacom_wac->pen_input = NULL; pen_input_dev = NULL; - } else { - error = input_register_device(pen_input_dev); - if (error) - goto fail; } error = wacom_setup_touch_input_capabilities(touch_input_dev, wacom_wac); @@ -2119,10 +2115,6 @@ static int wacom_register_inputs(struct wacom *wacom) input_free_device(touch_input_dev); wacom_wac->touch_input = NULL; touch_input_dev = NULL; - } else { - error = input_register_device(touch_input_dev); - if (error) - goto fail; } error = wacom_setup_pad_input_capabilities(pad_input_dev, wacom_wac); @@ -2131,7 +2123,34 @@ static int wacom_register_inputs(struct wacom *wacom) input_free_device(pad_input_dev); wacom_wac->pad_input = NULL; pad_input_dev = NULL; - } else { + } + + return 0; +} + +static int wacom_register_inputs(struct wacom *wacom) +{ + struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev; + struct wacom_wac *wacom_wac = &(wacom->wacom_wac); + int error = 0; + + pen_input_dev = wacom_wac->pen_input; + touch_input_dev = wacom_wac->touch_input; + pad_input_dev = wacom_wac->pad_input; + + if (pen_input_dev) { + error = input_register_device(pen_input_dev); + if (error) + goto fail; + } + + if (touch_input_dev) { + error = input_register_device(touch_input_dev); + if (error) + goto fail; + } + + if (pad_input_dev) { error = input_register_device(pad_input_dev); if (error) goto fail; @@ -2381,6 +2400,20 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless) goto fail; } + error = wacom_setup_inputs(wacom); + if (error) + goto fail; + + if (features->type == HID_GENERIC) + connect_mask |= HID_CONNECT_DRIVER; + + /* Regular HID work starts now */ + error = hid_hw_start(hdev, connect_mask); + if (error) { + hid_err(hdev, "hw start failed\n"); + goto fail; + } + error = wacom_register_inputs(wacom); if (error) goto fail; @@ -2395,16 +2428,6 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless) goto fail; } - if (features->type == HID_GENERIC) - connect_mask |= HID_CONNECT_DRIVER; - - /* Regular HID work starts now */ - error = hid_hw_start(hdev, connect_mask); - if (error) { - hid_err(hdev, "hw start failed\n"); - goto fail; - } - if (!wireless) { /* Note that if query fails it is not a hard failure */ wacom_query_tablet_data(wacom); diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 726a5d766..c454768ff 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2540,7 +2540,14 @@ static void wacom_wac_pen_report(struct hid_device *hdev, wacom_wac->hid_data.tipswitch); input_report_key(input, wacom_wac->tool[0], sense); if (wacom_wac->serial[0]) { - input_event(input, EV_MSC, MSC_SERIAL, wacom_wac->serial[0]); + /* + * xf86-input-wacom does not accept a serial number + * of '0'. Report the low 32 bits if possible, but + * if they are zero, report the upper ones instead. + */ + __u32 serial_lo = wacom_wac->serial[0] & 0xFFFFFFFFu; + __u32 serial_hi = wacom_wac->serial[0] >> 32; + input_event(input, EV_MSC, MSC_SERIAL, (int)(serial_lo ? serial_lo : serial_hi)); input_report_abs(input, ABS_MISC, sense ? id : 0); } diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index f064fa6ef..a59ab2f3d 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -503,6 +503,70 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, } EXPORT_SYMBOL_GPL(vmbus_establish_gpadl); +/** + * request_arr_init - Allocates memory for the requestor array. Each slot + * keeps track of the next available slot in the array. Initially, each + * slot points to the next one (as in a Linked List). The last slot + * does not point to anything, so its value is U64_MAX by default. + * @size The size of the array + */ +static u64 *request_arr_init(u32 size) +{ + int i; + u64 *req_arr; + + req_arr = kcalloc(size, sizeof(u64), GFP_KERNEL); + if (!req_arr) + return NULL; + + for (i = 0; i < size - 1; i++) + req_arr[i] = i + 1; + + /* Last slot (no more available slots) */ + req_arr[i] = U64_MAX; + + return req_arr; +} + +/* + * vmbus_alloc_requestor - Initializes @rqstor's fields. + * Index 0 is the first free slot + * @size: Size of the requestor array + */ +static int vmbus_alloc_requestor(struct vmbus_requestor *rqstor, u32 size) +{ + u64 *rqst_arr; + unsigned long *bitmap; + + rqst_arr = request_arr_init(size); + if (!rqst_arr) + return -ENOMEM; + + bitmap = bitmap_zalloc(size, GFP_KERNEL); + if (!bitmap) { + kfree(rqst_arr); + return -ENOMEM; + } + + rqstor->req_arr = rqst_arr; + rqstor->req_bitmap = bitmap; + rqstor->size = size; + rqstor->next_request_id = 0; + spin_lock_init(&rqstor->req_lock); + + return 0; +} + +/* + * vmbus_free_requestor - Frees memory allocated for @rqstor + * @rqstor: Pointer to the requestor struct + */ +static void vmbus_free_requestor(struct vmbus_requestor *rqstor) +{ + kfree(rqstor->req_arr); + bitmap_free(rqstor->req_bitmap); +} + static int __vmbus_open(struct vmbus_channel *newchannel, void *userdata, u32 userdatalen, void (*onchannelcallback)(void *context), void *context) @@ -523,6 +587,12 @@ static int __vmbus_open(struct vmbus_channel *newchannel, if (newchannel->state != CHANNEL_OPEN_STATE) return -EINVAL; + /* Create and init requestor */ + if (newchannel->rqstor_size) { + if (vmbus_alloc_requestor(&newchannel->requestor, newchannel->rqstor_size)) + return -ENOMEM; + } + newchannel->state = CHANNEL_OPENING_STATE; newchannel->onchannel_callback = onchannelcallback; newchannel->channel_callback_context = context; @@ -626,6 +696,7 @@ error_free_gpadl: error_clean_ring: hv_ringbuffer_cleanup(&newchannel->outbound); hv_ringbuffer_cleanup(&newchannel->inbound); + vmbus_free_requestor(&newchannel->requestor); newchannel->state = CHANNEL_OPEN_STATE; return err; } @@ -808,6 +879,9 @@ static int vmbus_close_internal(struct vmbus_channel *channel) channel->ringbuffer_gpadlhandle = 0; } + if (!ret) + vmbus_free_requestor(&channel->requestor); + return ret; } @@ -888,7 +962,7 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer, /* in 8-bytes granularity */ desc.offset8 = sizeof(struct vmpacket_descriptor) >> 3; desc.len8 = (u16)(packetlen_aligned >> 3); - desc.trans_id = requestid; + desc.trans_id = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */ bufferlist[0].iov_base = &desc; bufferlist[0].iov_len = sizeof(struct vmpacket_descriptor); @@ -897,7 +971,7 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer, bufferlist[2].iov_base = &aligned_data; bufferlist[2].iov_len = (packetlen_aligned - packetlen); - return hv_ringbuffer_write(channel, bufferlist, num_vecs); + return hv_ringbuffer_write(channel, bufferlist, num_vecs, requestid); } EXPORT_SYMBOL(vmbus_sendpacket); @@ -939,7 +1013,7 @@ int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, desc.flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED; desc.dataoffset8 = descsize >> 3; /* in 8-bytes granularity */ desc.length8 = (u16)(packetlen_aligned >> 3); - desc.transactionid = requestid; + desc.transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */ desc.reserved = 0; desc.rangecount = pagecount; @@ -956,7 +1030,7 @@ int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, bufferlist[2].iov_base = &aligned_data; bufferlist[2].iov_len = (packetlen_aligned - packetlen); - return hv_ringbuffer_write(channel, bufferlist, 3); + return hv_ringbuffer_write(channel, bufferlist, 3, requestid); } EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer); @@ -983,7 +1057,7 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, desc->flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED; desc->dataoffset8 = desc_size >> 3; /* in 8-bytes granularity */ desc->length8 = (u16)(packetlen_aligned >> 3); - desc->transactionid = requestid; + desc->transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */ desc->reserved = 0; desc->rangecount = 1; @@ -994,7 +1068,7 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, bufferlist[2].iov_base = &aligned_data; bufferlist[2].iov_len = (packetlen_aligned - packetlen); - return hv_ringbuffer_write(channel, bufferlist, 3); + return hv_ringbuffer_write(channel, bufferlist, 3, requestid); } EXPORT_SYMBOL_GPL(vmbus_sendpacket_mpb_desc); @@ -1042,3 +1116,91 @@ int vmbus_recvpacket_raw(struct vmbus_channel *channel, void *buffer, buffer_actual_len, requestid, true); } EXPORT_SYMBOL_GPL(vmbus_recvpacket_raw); + +/* + * vmbus_next_request_id - Returns a new request id. It is also + * the index at which the guest memory address is stored. + * Uses a spin lock to avoid race conditions. + * @rqstor: Pointer to the requestor struct + * @rqst_add: Guest memory address to be stored in the array + */ +u64 vmbus_next_request_id(struct vmbus_requestor *rqstor, u64 rqst_addr) +{ + unsigned long flags; + u64 current_id; + const struct vmbus_channel *channel = + container_of(rqstor, const struct vmbus_channel, requestor); + + /* Check rqstor has been initialized */ + if (!channel->rqstor_size) + return VMBUS_NO_RQSTOR; + + spin_lock_irqsave(&rqstor->req_lock, flags); + current_id = rqstor->next_request_id; + + /* Requestor array is full */ + if (current_id >= rqstor->size) { + spin_unlock_irqrestore(&rqstor->req_lock, flags); + return VMBUS_RQST_ERROR; + } + + rqstor->next_request_id = rqstor->req_arr[current_id]; + rqstor->req_arr[current_id] = rqst_addr; + + /* The already held spin lock provides atomicity */ + bitmap_set(rqstor->req_bitmap, current_id, 1); + + spin_unlock_irqrestore(&rqstor->req_lock, flags); + + /* + * Cannot return an ID of 0, which is reserved for an unsolicited + * message from Hyper-V. + */ + return current_id + 1; +} +EXPORT_SYMBOL_GPL(vmbus_next_request_id); + +/* + * vmbus_request_addr - Returns the memory address stored at @trans_id + * in @rqstor. Uses a spin lock to avoid race conditions. + * @rqstor: Pointer to the requestor struct + * @trans_id: Request id sent back from Hyper-V. Becomes the requestor's + * next request id. + */ +u64 vmbus_request_addr(struct vmbus_requestor *rqstor, u64 trans_id) +{ + unsigned long flags; + u64 req_addr; + const struct vmbus_channel *channel = + container_of(rqstor, const struct vmbus_channel, requestor); + + /* Check rqstor has been initialized */ + if (!channel->rqstor_size) + return VMBUS_NO_RQSTOR; + + /* Hyper-V can send an unsolicited message with ID of 0 */ + if (!trans_id) + return trans_id; + + spin_lock_irqsave(&rqstor->req_lock, flags); + + /* Data corresponding to trans_id is stored at trans_id - 1 */ + trans_id--; + + /* Invalid trans_id */ + if (trans_id >= rqstor->size || !test_bit(trans_id, rqstor->req_bitmap)) { + spin_unlock_irqrestore(&rqstor->req_lock, flags); + return VMBUS_RQST_ERROR; + } + + req_addr = rqstor->req_arr[trans_id]; + rqstor->req_arr[trans_id] = rqstor->next_request_id; + rqstor->next_request_id = trans_id; + + /* The already held spin lock provides atomicity */ + bitmap_clear(rqstor->req_bitmap, trans_id, 1); + + spin_unlock_irqrestore(&rqstor->req_lock, flags); + return req_addr; +} +EXPORT_SYMBOL_GPL(vmbus_request_addr); diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 7845fa5de..601660bca 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -180,7 +180,8 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info); int hv_ringbuffer_write(struct vmbus_channel *channel, - const struct kvec *kv_list, u32 kv_count); + const struct kvec *kv_list, u32 kv_count, + u64 requestid); int hv_ringbuffer_read(struct vmbus_channel *channel, void *buffer, u32 buflen, u32 *buffer_actual_len, diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 7ed6fad3f..a49cc69c5 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -261,7 +261,8 @@ EXPORT_SYMBOL_GPL(hv_ringbuffer_spinlock_busy); /* Write to the ring buffer. */ int hv_ringbuffer_write(struct vmbus_channel *channel, - const struct kvec *kv_list, u32 kv_count) + const struct kvec *kv_list, u32 kv_count, + u64 requestid) { int i; u32 bytes_avail_towrite; @@ -271,6 +272,8 @@ int hv_ringbuffer_write(struct vmbus_channel *channel, u64 prev_indices; unsigned long flags; struct hv_ring_buffer_info *outring_info = &channel->outbound; + struct vmpacket_descriptor *desc = kv_list[0].iov_base; + u64 rqst_id = VMBUS_NO_RQSTOR; if (channel->rescind) return -ENODEV; @@ -313,6 +316,22 @@ int hv_ringbuffer_write(struct vmbus_channel *channel, kv_list[i].iov_len); } + /* + * Allocate the request ID after the data has been copied into the + * ring buffer. Once this request ID is allocated, the completion + * path could find the data and free it. + */ + + if (desc->flags == VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED) { + rqst_id = vmbus_next_request_id(&channel->requestor, requestid); + if (rqst_id == VMBUS_RQST_ERROR) { + spin_unlock_irqrestore(&outring_info->ring_lock, flags); + return -EAGAIN; + } + } + desc = hv_get_ring_buffer(outring_info) + old_write; + desc->trans_id = (rqst_id == VMBUS_NO_RQSTOR) ? requestid : rqst_id; + /* Set previous packet start */ prev_indices = hv_get_ring_bufferindices(outring_info); @@ -332,8 +351,13 @@ int hv_ringbuffer_write(struct vmbus_channel *channel, hv_signal_on_write(old_write, channel); - if (channel->rescind) + if (channel->rescind) { + if (rqst_id != VMBUS_NO_RQSTOR) { + /* Reclaim request ID to avoid leak of IDs */ + vmbus_request_addr(&channel->requestor, rqst_id); + } return -ENODEV; + } return 0; } diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c index 6b1ce2242..60dfdb0f5 100644 --- a/drivers/hwmon/amc6821.c +++ b/drivers/hwmon/amc6821.c @@ -934,10 +934,21 @@ static const struct i2c_device_id amc6821_id[] = { MODULE_DEVICE_TABLE(i2c, amc6821_id); +static const struct of_device_id __maybe_unused amc6821_of_match[] = { + { + .compatible = "ti,amc6821", + .data = (void *)amc6821, + }, + { } +}; + +MODULE_DEVICE_TABLE(of, amc6821_of_match); + static struct i2c_driver amc6821_driver = { .class = I2C_CLASS_HWMON, .driver = { .name = "amc6821", + .of_match_table = of_match_ptr(amc6821_of_match), }, .probe_new = amc6821_probe, .id_table = amc6821_id, diff --git a/drivers/hwmon/aspeed-pwm-tacho.c b/drivers/hwmon/aspeed-pwm-tacho.c index 3d8239fd6..3dc97041a 100644 --- a/drivers/hwmon/aspeed-pwm-tacho.c +++ b/drivers/hwmon/aspeed-pwm-tacho.c @@ -194,6 +194,8 @@ struct aspeed_pwm_tacho_data { u8 fan_tach_ch_source[16]; struct aspeed_cooling_device *cdev[8]; const struct attribute_group *groups[3]; + /* protects access to shared ASPEED_PTCR_RESULT */ + struct mutex tach_lock; }; enum type { TYPEM, TYPEN, TYPEO }; @@ -528,6 +530,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv, u8 fan_tach_ch_source, type, mode, both; int ret; + mutex_lock(&priv->tach_lock); + regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0); regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0x1 << fan_tach_ch); @@ -545,6 +549,8 @@ static int aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv, ASPEED_RPM_STATUS_SLEEP_USEC, usec); + mutex_unlock(&priv->tach_lock); + /* return -ETIMEDOUT if we didn't get an answer. */ if (ret) return ret; @@ -904,6 +910,7 @@ static int aspeed_pwm_tacho_probe(struct platform_device *pdev) priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; + mutex_init(&priv->tach_lock); priv->regmap = devm_regmap_init(dev, NULL, (__force void *)regs, &aspeed_pwm_tacho_regmap_config); if (IS_ERR(priv->regmap)) diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 5b2057ce5..cbe2f874b 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -40,7 +40,7 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius"); #define PKG_SYSFS_ATTR_NO 1 /* Sysfs attribute for package temp */ #define BASE_SYSFS_ATTR_NO 2 /* Sysfs Base attr no for coretemp */ -#define NUM_REAL_CORES 128 /* Number of Real cores per cpu */ +#define NUM_REAL_CORES 512 /* Number of Real cores per cpu */ #define CORETEMP_NAME_LENGTH 28 /* String Length of attrs */ #define MAX_CORE_ATTRS 4 /* Maximum no of basic attrs */ #define TOTAL_ATTRS (MAX_CORE_ATTRS + 1) @@ -380,7 +380,7 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev) } static int create_core_attrs(struct temp_data *tdata, struct device *dev, - int attr_no) + int index) { int i; static ssize_t (*const rd_ptr[TOTAL_ATTRS]) (struct device *dev, @@ -392,13 +392,20 @@ static int create_core_attrs(struct temp_data *tdata, struct device *dev, }; for (i = 0; i < tdata->attr_size; i++) { + /* + * We map the attr number to core id of the CPU + * The attr number is always core id + 2 + * The Pkgtemp will always show up as temp1_*, if available + */ + int attr_no = tdata->is_pkg_data ? 1 : tdata->cpu_core_id + 2; + snprintf(tdata->attr_name[i], CORETEMP_NAME_LENGTH, "temp%d_%s", attr_no, suffixes[i]); sysfs_attr_init(&tdata->sd_attrs[i].dev_attr.attr); tdata->sd_attrs[i].dev_attr.attr.name = tdata->attr_name[i]; tdata->sd_attrs[i].dev_attr.attr.mode = 0444; tdata->sd_attrs[i].dev_attr.show = rd_ptr[i]; - tdata->sd_attrs[i].index = attr_no; + tdata->sd_attrs[i].index = index; tdata->attrs[i] = &tdata->sd_attrs[i].dev_attr.attr; } tdata->attr_group.attrs = tdata->attrs; @@ -456,27 +463,22 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, struct platform_data *pdata = platform_get_drvdata(pdev); struct cpuinfo_x86 *c = &cpu_data(cpu); u32 eax, edx; - int err, index, attr_no; + int err, index; /* - * Find attr number for sysfs: - * We map the attr number to core id of the CPU - * The attr number is always core id + 2 - * The Pkgtemp will always show up as temp1_*, if available + * Get the index of tdata in pdata->core_data[] + * tdata for package: pdata->core_data[1] + * tdata for core: pdata->core_data[2] .. pdata->core_data[NUM_REAL_CORES + 1] */ if (pkg_flag) { - attr_no = PKG_SYSFS_ATTR_NO; + index = PKG_SYSFS_ATTR_NO; } else { - index = ida_alloc(&pdata->ida, GFP_KERNEL); + index = ida_alloc_max(&pdata->ida, NUM_REAL_CORES - 1, GFP_KERNEL); if (index < 0) return index; - pdata->cpu_map[index] = topology_core_id(cpu); - attr_no = index + BASE_SYSFS_ATTR_NO; - } - if (attr_no > MAX_CORE_DATA - 1) { - err = -ERANGE; - goto ida_free; + pdata->cpu_map[index] = topology_core_id(cpu); + index += BASE_SYSFS_ATTR_NO; } tdata = init_temp_data(cpu, pkg_flag); @@ -508,20 +510,20 @@ static int create_core_data(struct platform_device *pdev, unsigned int cpu, } } - pdata->core_data[attr_no] = tdata; + pdata->core_data[index] = tdata; /* Create sysfs interfaces */ - err = create_core_attrs(tdata, pdata->hwmon_dev, attr_no); + err = create_core_attrs(tdata, pdata->hwmon_dev, index); if (err) goto exit_free; return 0; exit_free: - pdata->core_data[attr_no] = NULL; + pdata->core_data[index] = NULL; kfree(tdata); ida_free: if (!pkg_flag) - ida_free(&pdata->ida, index); + ida_free(&pdata->ida, index - BASE_SYSFS_ATTR_NO); return err; } diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index cb8f56022..d6b945f5b 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -540,12 +540,13 @@ static int i801_block_transaction_by_block(struct i801_priv *priv, return -EOPNOTSUPP; } - inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */ + /* Set block buffer mode */ + outb_p(inb_p(SMBAUXCTL(priv)) | SMBAUXCTL_E32B, SMBAUXCTL(priv)); - /* Use 32-byte buffer to process this transaction */ if (read_write == I2C_SMBUS_WRITE) { len = data->block[0]; outb_p(len, SMBHSTDAT0(priv)); + inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */ for (i = 0; i < len; i++) outb_p(data->block[i+1], SMBBLKDAT(priv)); } @@ -561,6 +562,7 @@ static int i801_block_transaction_by_block(struct i801_priv *priv, return -EPROTO; data->block[0] = len; + inb_p(SMBHSTCNT(priv)); /* reset the data buffer index */ for (i = 0; i < len; i++) data->block[i + 1] = inb_p(SMBBLKDAT(priv)); } @@ -780,14 +782,6 @@ exit: return i801_check_post(priv, status); } -static int i801_set_block_buffer_mode(struct i801_priv *priv) -{ - outb_p(inb_p(SMBAUXCTL(priv)) | SMBAUXCTL_E32B, SMBAUXCTL(priv)); - if ((inb_p(SMBAUXCTL(priv)) & SMBAUXCTL_E32B) == 0) - return -EIO; - return 0; -} - /* Block transaction function */ static int i801_block_transaction(struct i801_priv *priv, union i2c_smbus_data *data, char read_write, @@ -817,9 +811,8 @@ static int i801_block_transaction(struct i801_priv *priv, /* Experience has shown that the block buffer can only be used for SMBus (not I2C) block transactions, even though the datasheet doesn't mention this limitation. */ - if ((priv->features & FEATURE_BLOCK_BUFFER) - && command != I2C_SMBUS_I2C_BLOCK_DATA - && i801_set_block_buffer_mode(priv) == 0) + if ((priv->features & FEATURE_BLOCK_BUFFER) && + command != I2C_SMBUS_I2C_BLOCK_DATA) result = i801_block_transaction_by_block(priv, data, read_write, command, hwpec); diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 34fecf97a..e8a89e18c 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -2013,13 +2013,18 @@ static int i2c_check_for_quirks(struct i2c_adapter *adap, struct i2c_msg *msgs, * Returns negative errno, else the number of messages executed. * * Adapter lock must be held when calling this function. No debug logging - * takes place. adap->algo->master_xfer existence isn't checked. + * takes place. */ int __i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) { unsigned long orig_jiffies; int ret, try; + if (!adap->algo->master_xfer) { + dev_dbg(&adap->dev, "I2C level transfers not supported\n"); + return -EOPNOTSUPP; + } + if (WARN_ON(!msgs || num < 1)) return -EINVAL; @@ -2086,11 +2091,6 @@ int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) { int ret; - if (!adap->algo->master_xfer) { - dev_dbg(&adap->dev, "I2C level transfers not supported\n"); - return -EOPNOTSUPP; - } - /* REVISIT the fault reporting model here is weak: * * - When we get an error after receiving N bytes from a slave, diff --git a/drivers/i3c/master/i3c-master-cdns.c b/drivers/i3c/master/i3c-master-cdns.c index 6b9df33ac..6b126fce5 100644 --- a/drivers/i3c/master/i3c-master-cdns.c +++ b/drivers/i3c/master/i3c-master-cdns.c @@ -77,7 +77,8 @@ #define PRESCL_CTRL0 0x14 #define PRESCL_CTRL0_I2C(x) ((x) << 16) #define PRESCL_CTRL0_I3C(x) (x) -#define PRESCL_CTRL0_MAX GENMASK(9, 0) +#define PRESCL_CTRL0_I3C_MAX GENMASK(9, 0) +#define PRESCL_CTRL0_I2C_MAX GENMASK(15, 0) #define PRESCL_CTRL1 0x18 #define PRESCL_CTRL1_PP_LOW_MASK GENMASK(15, 8) @@ -1234,7 +1235,7 @@ static int cdns_i3c_master_bus_init(struct i3c_master_controller *m) return -EINVAL; pres = DIV_ROUND_UP(sysclk_rate, (bus->scl_rate.i3c * 4)) - 1; - if (pres > PRESCL_CTRL0_MAX) + if (pres > PRESCL_CTRL0_I3C_MAX) return -ERANGE; bus->scl_rate.i3c = sysclk_rate / ((pres + 1) * 4); @@ -1247,7 +1248,7 @@ static int cdns_i3c_master_bus_init(struct i3c_master_controller *m) max_i2cfreq = bus->scl_rate.i2c; pres = (sysclk_rate / (max_i2cfreq * 5)) - 1; - if (pres > PRESCL_CTRL0_MAX) + if (pres > PRESCL_CTRL0_I2C_MAX) return -ERANGE; bus->scl_rate.i2c = sysclk_rate / ((pres + 1) * 5); diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig index 8acf277b8..1c82840ac 100644 --- a/drivers/iio/accel/Kconfig +++ b/drivers/iio/accel/Kconfig @@ -128,10 +128,12 @@ config BMA400 config BMA400_I2C tristate + select REGMAP_I2C depends on BMA400 config BMA400_SPI tristate + select REGMAP_SPI depends on BMA400 config BMC150_ACCEL diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c index 811f04448..76002b91c 100644 --- a/drivers/iio/adc/ad7091r-base.c +++ b/drivers/iio/adc/ad7091r-base.c @@ -6,6 +6,7 @@ */ #include <linux/bitops.h> +#include <linux/bitfield.h> #include <linux/iio/events.h> #include <linux/iio/iio.h> #include <linux/interrupt.h> @@ -28,6 +29,7 @@ #define AD7091R_REG_RESULT_CONV_RESULT(x) ((x) & 0xfff) /* AD7091R_REG_CONF */ +#define AD7091R_REG_CONF_ALERT_EN BIT(4) #define AD7091R_REG_CONF_AUTO BIT(8) #define AD7091R_REG_CONF_CMD BIT(10) @@ -49,6 +51,27 @@ struct ad7091r_state { struct mutex lock; /*lock to prevent concurent reads */ }; +const struct iio_event_spec ad7091r_events[] = { + { + .type = IIO_EV_TYPE_THRESH, + .dir = IIO_EV_DIR_RISING, + .mask_separate = BIT(IIO_EV_INFO_VALUE) | + BIT(IIO_EV_INFO_ENABLE), + }, + { + .type = IIO_EV_TYPE_THRESH, + .dir = IIO_EV_DIR_FALLING, + .mask_separate = BIT(IIO_EV_INFO_VALUE) | + BIT(IIO_EV_INFO_ENABLE), + }, + { + .type = IIO_EV_TYPE_THRESH, + .dir = IIO_EV_DIR_EITHER, + .mask_separate = BIT(IIO_EV_INFO_HYSTERESIS), + }, +}; +EXPORT_SYMBOL_NS_GPL(ad7091r_events, IIO_AD7091R); + static int ad7091r_set_mode(struct ad7091r_state *st, enum ad7091r_mode mode) { int ret, conf; @@ -168,8 +191,142 @@ unlock: return ret; } +static int ad7091r_read_event_config(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir) +{ + struct ad7091r_state *st = iio_priv(indio_dev); + int val, ret; + + switch (dir) { + case IIO_EV_DIR_RISING: + ret = regmap_read(st->map, + AD7091R_REG_CH_HIGH_LIMIT(chan->channel), + &val); + if (ret) + return ret; + return val != AD7091R_HIGH_LIMIT; + case IIO_EV_DIR_FALLING: + ret = regmap_read(st->map, + AD7091R_REG_CH_LOW_LIMIT(chan->channel), + &val); + if (ret) + return ret; + return val != AD7091R_LOW_LIMIT; + default: + return -EINVAL; + } +} + +static int ad7091r_write_event_config(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir, int state) +{ + struct ad7091r_state *st = iio_priv(indio_dev); + + if (state) { + return regmap_set_bits(st->map, AD7091R_REG_CONF, + AD7091R_REG_CONF_ALERT_EN); + } else { + /* + * Set thresholds either to 0 or to 2^12 - 1 as appropriate to + * prevent alerts and thus disable event generation. + */ + switch (dir) { + case IIO_EV_DIR_RISING: + return regmap_write(st->map, + AD7091R_REG_CH_HIGH_LIMIT(chan->channel), + AD7091R_HIGH_LIMIT); + case IIO_EV_DIR_FALLING: + return regmap_write(st->map, + AD7091R_REG_CH_LOW_LIMIT(chan->channel), + AD7091R_LOW_LIMIT); + default: + return -EINVAL; + } + } +} + +static int ad7091r_read_event_value(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir, + enum iio_event_info info, int *val, int *val2) +{ + struct ad7091r_state *st = iio_priv(indio_dev); + int ret; + + switch (info) { + case IIO_EV_INFO_VALUE: + switch (dir) { + case IIO_EV_DIR_RISING: + ret = regmap_read(st->map, + AD7091R_REG_CH_HIGH_LIMIT(chan->channel), + val); + if (ret) + return ret; + return IIO_VAL_INT; + case IIO_EV_DIR_FALLING: + ret = regmap_read(st->map, + AD7091R_REG_CH_LOW_LIMIT(chan->channel), + val); + if (ret) + return ret; + return IIO_VAL_INT; + default: + return -EINVAL; + } + case IIO_EV_INFO_HYSTERESIS: + ret = regmap_read(st->map, + AD7091R_REG_CH_HYSTERESIS(chan->channel), + val); + if (ret) + return ret; + return IIO_VAL_INT; + default: + return -EINVAL; + } +} + +static int ad7091r_write_event_value(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir, + enum iio_event_info info, int val, int val2) +{ + struct ad7091r_state *st = iio_priv(indio_dev); + + switch (info) { + case IIO_EV_INFO_VALUE: + switch (dir) { + case IIO_EV_DIR_RISING: + return regmap_write(st->map, + AD7091R_REG_CH_HIGH_LIMIT(chan->channel), + val); + case IIO_EV_DIR_FALLING: + return regmap_write(st->map, + AD7091R_REG_CH_LOW_LIMIT(chan->channel), + val); + default: + return -EINVAL; + } + case IIO_EV_INFO_HYSTERESIS: + return regmap_write(st->map, + AD7091R_REG_CH_HYSTERESIS(chan->channel), + val); + default: + return -EINVAL; + } +} + static const struct iio_info ad7091r_info = { .read_raw = ad7091r_read_raw, + .read_event_config = &ad7091r_read_event_config, + .write_event_config = &ad7091r_write_event_config, + .read_event_value = &ad7091r_read_event_value, + .write_event_value = &ad7091r_write_event_value, }; static irqreturn_t ad7091r_event_handler(int irq, void *private) @@ -232,6 +389,11 @@ int ad7091r_probe(struct device *dev, const char *name, iio_dev->channels = chip_info->channels; if (irq) { + ret = regmap_update_bits(st->map, AD7091R_REG_CONF, + AD7091R_REG_CONF_ALERT_EN, BIT(4)); + if (ret) + return ret; + ret = devm_request_threaded_irq(dev, irq, NULL, ad7091r_event_handler, IRQF_TRIGGER_FALLING | IRQF_ONESHOT, name, iio_dev); @@ -243,7 +405,14 @@ int ad7091r_probe(struct device *dev, const char *name, if (IS_ERR(st->vref)) { if (PTR_ERR(st->vref) == -EPROBE_DEFER) return -EPROBE_DEFER; + st->vref = NULL; + /* Enable internal vref */ + ret = regmap_set_bits(st->map, AD7091R_REG_CONF, + AD7091R_REG_CONF_INT_VREF); + if (ret) + return dev_err_probe(st->dev, ret, + "Error on enable internal reference\n"); } else { ret = regulator_enable(st->vref); if (ret) @@ -260,7 +429,7 @@ int ad7091r_probe(struct device *dev, const char *name, return devm_iio_device_register(dev, iio_dev); } -EXPORT_SYMBOL_GPL(ad7091r_probe); +EXPORT_SYMBOL_NS_GPL(ad7091r_probe, IIO_AD7091R); static bool ad7091r_writeable_reg(struct device *dev, unsigned int reg) { @@ -290,7 +459,7 @@ const struct regmap_config ad7091r_regmap_config = { .writeable_reg = ad7091r_writeable_reg, .volatile_reg = ad7091r_volatile_reg, }; -EXPORT_SYMBOL_GPL(ad7091r_regmap_config); +EXPORT_SYMBOL_NS_GPL(ad7091r_regmap_config, IIO_AD7091R); MODULE_AUTHOR("Beniamin Bia <beniamin.bia@analog.com>"); MODULE_DESCRIPTION("Analog Devices AD7091Rx multi-channel converters"); diff --git a/drivers/iio/adc/ad7091r-base.h b/drivers/iio/adc/ad7091r-base.h index 509748aef..b9e1c8bf3 100644 --- a/drivers/iio/adc/ad7091r-base.h +++ b/drivers/iio/adc/ad7091r-base.h @@ -8,6 +8,12 @@ #ifndef __DRIVERS_IIO_ADC_AD7091R_BASE_H__ #define __DRIVERS_IIO_ADC_AD7091R_BASE_H__ +#define AD7091R_REG_CONF_INT_VREF BIT(0) + +/* AD7091R_REG_CH_LIMIT */ +#define AD7091R_HIGH_LIMIT 0xFFF +#define AD7091R_LOW_LIMIT 0x0 + struct device; struct ad7091r_state; @@ -17,6 +23,8 @@ struct ad7091r_chip_info { unsigned int vref_mV; }; +extern const struct iio_event_spec ad7091r_events[3]; + extern const struct regmap_config ad7091r_regmap_config; int ad7091r_probe(struct device *dev, const char *name, diff --git a/drivers/iio/adc/ad7091r5.c b/drivers/iio/adc/ad7091r5.c index 9665679c3..12d475463 100644 --- a/drivers/iio/adc/ad7091r5.c +++ b/drivers/iio/adc/ad7091r5.c @@ -12,26 +12,6 @@ #include "ad7091r-base.h" -static const struct iio_event_spec ad7091r5_events[] = { - { - .type = IIO_EV_TYPE_THRESH, - .dir = IIO_EV_DIR_RISING, - .mask_separate = BIT(IIO_EV_INFO_VALUE) | - BIT(IIO_EV_INFO_ENABLE), - }, - { - .type = IIO_EV_TYPE_THRESH, - .dir = IIO_EV_DIR_FALLING, - .mask_separate = BIT(IIO_EV_INFO_VALUE) | - BIT(IIO_EV_INFO_ENABLE), - }, - { - .type = IIO_EV_TYPE_THRESH, - .dir = IIO_EV_DIR_EITHER, - .mask_separate = BIT(IIO_EV_INFO_HYSTERESIS), - }, -}; - #define AD7091R_CHANNEL(idx, bits, ev, num_ev) { \ .type = IIO_VOLTAGE, \ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), \ @@ -44,10 +24,10 @@ static const struct iio_event_spec ad7091r5_events[] = { .scan_type.realbits = bits, \ } static const struct iio_chan_spec ad7091r5_channels_irq[] = { - AD7091R_CHANNEL(0, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)), - AD7091R_CHANNEL(1, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)), - AD7091R_CHANNEL(2, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)), - AD7091R_CHANNEL(3, 12, ad7091r5_events, ARRAY_SIZE(ad7091r5_events)), + AD7091R_CHANNEL(0, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)), + AD7091R_CHANNEL(1, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)), + AD7091R_CHANNEL(2, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)), + AD7091R_CHANNEL(3, 12, ad7091r_events, ARRAY_SIZE(ad7091r_events)), }; static const struct iio_chan_spec ad7091r5_channels_noirq[] = { @@ -111,3 +91,4 @@ module_i2c_driver(ad7091r5_driver); MODULE_AUTHOR("Beniamin Bia <beniamin.bia@analog.com>"); MODULE_DESCRIPTION("Analog Devices AD7091R5 multi-channel ADC driver"); MODULE_LICENSE("GPL v2"); +MODULE_IMPORT_NS(IIO_AD7091R); diff --git a/drivers/iio/magnetometer/rm3100-core.c b/drivers/iio/magnetometer/rm3100-core.c index 720234a91..e7690d386 100644 --- a/drivers/iio/magnetometer/rm3100-core.c +++ b/drivers/iio/magnetometer/rm3100-core.c @@ -538,6 +538,7 @@ int rm3100_common_probe(struct device *dev, struct regmap *regmap, int irq) struct rm3100_data *data; unsigned int tmp; int ret; + int samp_rate_index; indio_dev = devm_iio_device_alloc(dev, sizeof(*data)); if (!indio_dev) @@ -596,9 +597,14 @@ int rm3100_common_probe(struct device *dev, struct regmap *regmap, int irq) ret = regmap_read(regmap, RM3100_REG_TMRC, &tmp); if (ret < 0) return ret; + + samp_rate_index = tmp - RM3100_TMRC_OFFSET; + if (samp_rate_index < 0 || samp_rate_index >= RM3100_SAMP_NUM) { + dev_err(dev, "The value read from RM3100_REG_TMRC is invalid!\n"); + return -EINVAL; + } /* Initializing max wait time, which is double conversion time. */ - data->conversion_time = rm3100_samp_rates[tmp - RM3100_TMRC_OFFSET][2] - * 2; + data->conversion_time = rm3100_samp_rates[samp_rate_index][2] * 2; /* Cycle count values may not be what we want. */ if ((tmp - RM3100_TMRC_OFFSET) == 0) diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index db1a25fbe..26c66685a 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -33,6 +33,7 @@ MODULE_AUTHOR("Sean Hefty"); MODULE_DESCRIPTION("InfiniBand CM"); MODULE_LICENSE("Dual BSD/GPL"); +#define CM_DESTROY_ID_WAIT_TIMEOUT 10000 /* msecs */ static const char * const ibcm_rej_reason_strs[] = { [IB_CM_REJ_NO_QP] = "no QP", [IB_CM_REJ_NO_EEC] = "no EEC", @@ -1056,13 +1057,26 @@ static void cm_reset_to_idle(struct cm_id_private *cm_id_priv) } } +static noinline void cm_destroy_id_wait_timeout(struct ib_cm_id *cm_id, + enum ib_cm_state old_state) +{ + struct cm_id_private *cm_id_priv; + + cm_id_priv = container_of(cm_id, struct cm_id_private, id); + pr_err("%s: cm_id=%p timed out. state %d -> %d, refcnt=%d\n", __func__, + cm_id, old_state, cm_id->state, refcount_read(&cm_id_priv->refcount)); +} + static void cm_destroy_id(struct ib_cm_id *cm_id, int err) { struct cm_id_private *cm_id_priv; + enum ib_cm_state old_state; struct cm_work *work; + int ret; cm_id_priv = container_of(cm_id, struct cm_id_private, id); spin_lock_irq(&cm_id_priv->lock); + old_state = cm_id->state; retest: switch (cm_id->state) { case IB_CM_LISTEN: @@ -1171,7 +1185,14 @@ retest: xa_erase(&cm.local_id_table, cm_local_id(cm_id->local_id)); cm_deref_id(cm_id_priv); - wait_for_completion(&cm_id_priv->comp); + do { + ret = wait_for_completion_timeout(&cm_id_priv->comp, + msecs_to_jiffies( + CM_DESTROY_ID_WAIT_TIMEOUT)); + if (!ret) /* timeout happened */ + cm_destroy_id_wait_timeout(cm_id, old_state); + } while (!ret); + while ((work = cm_dequeue_work(cm_id_priv)) != NULL) cm_free_work(work); diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 3c29fd04b..94c3bad72 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -1686,7 +1686,7 @@ static int assign_client_id(struct ib_client *client) { int ret; - down_write(&clients_rwsem); + lockdep_assert_held(&clients_rwsem); /* * The add/remove callbacks must be called in FIFO/LIFO order. To * achieve this we assign client_ids so they are sorted in @@ -1695,14 +1695,11 @@ static int assign_client_id(struct ib_client *client) client->client_id = highest_client_id; ret = xa_insert(&clients, client->client_id, client, GFP_KERNEL); if (ret) - goto out; + return ret; highest_client_id++; xa_set_mark(&clients, client->client_id, CLIENT_REGISTERED); - -out: - up_write(&clients_rwsem); - return ret; + return 0; } static void remove_client_id(struct ib_client *client) @@ -1732,25 +1729,35 @@ int ib_register_client(struct ib_client *client) { struct ib_device *device; unsigned long index; + bool need_unreg = false; int ret; refcount_set(&client->uses, 1); init_completion(&client->uses_zero); + + /* + * The devices_rwsem is held in write mode to ensure that a racing + * ib_register_device() sees a consisent view of clients and devices. + */ + down_write(&devices_rwsem); + down_write(&clients_rwsem); ret = assign_client_id(client); if (ret) - return ret; + goto out; - down_read(&devices_rwsem); + need_unreg = true; xa_for_each_marked (&devices, index, device, DEVICE_REGISTERED) { ret = add_client_context(device, client); - if (ret) { - up_read(&devices_rwsem); - ib_unregister_client(client); - return ret; - } + if (ret) + goto out; } - up_read(&devices_rwsem); - return 0; + ret = 0; +out: + up_write(&clients_rwsem); + up_write(&devices_rwsem); + if (need_unreg && ret) + ib_unregister_client(client); + return ret; } EXPORT_SYMBOL(ib_register_client); diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 2a973a139..a0d7777ac 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -1711,7 +1711,7 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr, switch (srq_attr_mask) { case IB_SRQ_MAX_WR: /* SRQ resize is not supported */ - break; + return -EINVAL; case IB_SRQ_LIMIT: /* Change the SRQ threshold */ if (srq_attr->srq_limit > srq->qplib_srq.max_wqe) @@ -1726,13 +1726,12 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr, /* On success, update the shadow */ srq->srq_limit = srq_attr->srq_limit; /* No need to Build and send response back to udata */ - break; + return 0; default: ibdev_err(&rdev->ibdev, "Unsupported srq_attr_mask 0x%x", srq_attr_mask); return -EINVAL; } - return 0; } int bnxt_re_query_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr) diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index 60eb3a645..969004258 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -2131,7 +2131,7 @@ int init_credit_return(struct hfi1_devdata *dd) "Unable to allocate credit return DMA range for NUMA %d\n", i); ret = -ENOMEM; - goto done; + goto free_cr_base; } } set_dev_node(&dd->pcidev->dev, dd->node); @@ -2139,6 +2139,10 @@ int init_credit_return(struct hfi1_devdata *dd) ret = 0; done: return ret; + +free_cr_base: + free_credit_return(dd); + goto done; } void free_credit_return(struct hfi1_devdata *dd) diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 2dc97de43..68a8557e9 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -3200,7 +3200,7 @@ int _pad_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx) { int rval = 0; - if ((unlikely(tx->num_desc + 1 == tx->desc_limit))) { + if ((unlikely(tx->num_desc == tx->desc_limit))) { rval = _extend_sdma_tx_descs(dd, tx); if (rval) { __sdma_txclean(dd, tx); diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index a56ebdc15..f67ebd9f3 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -2780,7 +2780,7 @@ DECLARE_UVERBS_NAMED_METHOD( MLX5_IB_METHOD_DEVX_OBJ_MODIFY, UVERBS_ATTR_IDR(MLX5_IB_ATTR_DEVX_OBJ_MODIFY_HANDLE, UVERBS_IDR_ANY_OBJECT, - UVERBS_ACCESS_WRITE, + UVERBS_ACCESS_READ, UA_MANDATORY), UVERBS_ATTR_PTR_IN( MLX5_IB_ATTR_DEVX_OBJ_MODIFY_CMD_IN, diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index cca7a4a6b..7f12a9b05 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -166,7 +166,8 @@ static int process_pma_cmd(struct mlx5_ib_dev *dev, u8 port_num, mdev = dev->mdev; mdev_port_num = 1; } - if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1) { + if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1 && + !mlx5_core_mp_enabled(mdev)) { /* set local port to one for Function-Per-Port HCA. */ mdev = dev->mdev; mdev_port_num = 1; diff --git a/drivers/infiniband/hw/mlx5/wr.c b/drivers/infiniband/hw/mlx5/wr.c index d6038fb6c..19fd440a6 100644 --- a/drivers/infiniband/hw/mlx5/wr.c +++ b/drivers/infiniband/hw/mlx5/wr.c @@ -128,7 +128,7 @@ static void set_eth_seg(const struct ib_send_wr *wr, struct mlx5_ib_qp *qp, */ copysz = min_t(u64, *cur_edge - (void *)eseg->inline_hdr.start, left); - memcpy(eseg->inline_hdr.start, pdata, copysz); + memcpy(eseg->inline_hdr.data, pdata, copysz); stride = ALIGN(sizeof(struct mlx5_wqe_eth_seg) - sizeof(eseg->inline_hdr.start) + copysz, 16); *size += stride / 16; diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 3543b9af1..d382ac211 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1865,8 +1865,17 @@ static int qedr_create_user_qp(struct qedr_dev *dev, /* RQ - read access only (0) */ rc = qedr_init_user_queue(udata, dev, &qp->urq, ureq.rq_addr, ureq.rq_len, true, 0, alloc_and_init); - if (rc) + if (rc) { + ib_umem_release(qp->usq.umem); + qp->usq.umem = NULL; + if (rdma_protocol_roce(&dev->ibdev, 1)) { + qedr_free_pbl(dev, &qp->usq.pbl_info, + qp->usq.pbl_tbl); + } else { + kfree(qp->usq.pbl_tbl); + } return rc; + } } memset(&in_params, 0, sizeof(in_params)); diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index 95f0de0c8..0505c81aa 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -35,6 +35,8 @@ void rxe_dealloc(struct ib_device *ib_dev) if (rxe->tfm) crypto_free_shash(rxe->tfm); + + mutex_destroy(&rxe->usdev_lock); } /* initialize rxe device parameters */ diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 86e4ed64e..e009123c7 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -542,21 +542,18 @@ static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) /* SM supports sendonly-fullmember, otherwise fallback to full-member */ rec.join_state = SENDONLY_FULLMEMBER_JOIN; } - spin_unlock_irq(&priv->lock); multicast = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port, - &rec, comp_mask, GFP_KERNEL, + &rec, comp_mask, GFP_ATOMIC, ipoib_mcast_join_complete, mcast); - spin_lock_irq(&priv->lock); if (IS_ERR(multicast)) { ret = PTR_ERR(multicast); ipoib_warn(priv, "ib_sa_join_multicast failed, status %d\n", ret); /* Requeue this join task with a backoff delay */ __ipoib_mcast_schedule_join_thread(priv, mcast, 1); clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); - spin_unlock_irq(&priv->lock); complete(&mcast->done); - spin_lock_irq(&priv->lock); + return ret; } return 0; } diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 983f59c87..960f870a9 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -79,12 +79,16 @@ module_param(srpt_srq_size, int, 0444); MODULE_PARM_DESC(srpt_srq_size, "Shared receive queue (SRQ) size."); +static int srpt_set_u64_x(const char *buffer, const struct kernel_param *kp) +{ + return kstrtou64(buffer, 16, (u64 *)kp->arg); +} static int srpt_get_u64_x(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "0x%016llx\n", *(u64 *)kp->arg); } -module_param_call(srpt_service_guid, NULL, srpt_get_u64_x, &srpt_service_guid, - 0444); +module_param_call(srpt_service_guid, srpt_set_u64_x, srpt_get_u64_x, + &srpt_service_guid, 0444); MODULE_PARM_DESC(srpt_service_guid, "Using this value for ioc_guid, id_ext, and cm_listen_id instead of using the node_guid of the first HCA."); @@ -210,10 +214,12 @@ static const char *get_ch_state_name(enum rdma_ch_state s) /** * srpt_qp_event - QP event callback function * @event: Description of the event that occurred. - * @ch: SRPT RDMA channel. + * @ptr: SRPT RDMA channel. */ -static void srpt_qp_event(struct ib_event *event, struct srpt_rdma_ch *ch) +static void srpt_qp_event(struct ib_event *event, void *ptr) { + struct srpt_rdma_ch *ch = ptr; + pr_debug("QP event %d on ch=%p sess_name=%s-%d state=%s\n", event->event, ch, ch->sess_name, ch->qp->qp_num, get_ch_state_name(ch->state)); @@ -1803,8 +1809,7 @@ retry: ch->cq_size = ch->rq_size + sq_size; qp_init->qp_context = (void *)ch; - qp_init->event_handler - = (void(*)(struct ib_event *, void*))srpt_qp_event; + qp_init->event_handler = srpt_qp_event; qp_init->send_cq = ch->cq; qp_init->recv_cq = ch->cq; qp_init->sq_sig_type = IB_SIGNAL_REQ_WR; @@ -3200,7 +3205,6 @@ static int srpt_add_one(struct ib_device *device) INIT_IB_EVENT_HANDLER(&sdev->event_handler, sdev->device, srpt_event_handler); - ib_register_event_handler(&sdev->event_handler); for (i = 1; i <= sdev->device->phys_port_cnt; i++) { sport = &sdev->port[i - 1]; @@ -3223,6 +3227,7 @@ static int srpt_add_one(struct ib_device *device) } } + ib_register_event_handler(&sdev->event_handler); spin_lock(&srpt_dev_lock); list_add_tail(&sdev->list, &srpt_dev_list); spin_unlock(&srpt_dev_lock); @@ -3233,7 +3238,6 @@ static int srpt_add_one(struct ib_device *device) err_port: srpt_unregister_mad_agent(sdev, i); - ib_unregister_event_handler(&sdev->event_handler); err_cm: if (sdev->cm_id) ib_destroy_cm_id(sdev->cm_id); diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c index 4912582c5..3e73eb465 100644 --- a/drivers/input/keyboard/atkbd.c +++ b/drivers/input/keyboard/atkbd.c @@ -802,7 +802,6 @@ static int atkbd_probe(struct atkbd *atkbd) { struct ps2dev *ps2dev = &atkbd->ps2dev; unsigned char param[2]; - bool skip_getid; /* * Some systems, where the bit-twiddling when testing the io-lines of the @@ -816,6 +815,11 @@ static int atkbd_probe(struct atkbd *atkbd) "keyboard reset failed on %s\n", ps2dev->serio->phys); + if (atkbd_skip_getid(atkbd)) { + atkbd->id = 0xab83; + return 0; + } + /* * Then we check the keyboard ID. We should get 0xab83 under normal conditions. * Some keyboards report different values, but the first byte is always 0xab or @@ -824,18 +828,17 @@ static int atkbd_probe(struct atkbd *atkbd) */ param[0] = param[1] = 0xa5; /* initialize with invalid values */ - skip_getid = atkbd_skip_getid(atkbd); - if (skip_getid || ps2_command(ps2dev, param, ATKBD_CMD_GETID)) { + if (ps2_command(ps2dev, param, ATKBD_CMD_GETID)) { /* - * If the get ID command was skipped or failed, we check if we can at least set + * If the get ID command failed, we check if we can at least set * the LEDs on the keyboard. This should work on every keyboard out there. * It also turns the LEDs off, which we want anyway. */ param[0] = 0; if (ps2_command(ps2dev, param, ATKBD_CMD_SETLEDS)) return -1; - atkbd->id = skip_getid ? 0xab83 : 0xabba; + atkbd->id = 0xabba; return 0; } diff --git a/drivers/input/keyboard/gpio_keys_polled.c b/drivers/input/keyboard/gpio_keys_polled.c index c3937d2fc..a0f9978c6 100644 --- a/drivers/input/keyboard/gpio_keys_polled.c +++ b/drivers/input/keyboard/gpio_keys_polled.c @@ -319,12 +319,10 @@ static int gpio_keys_polled_probe(struct platform_device *pdev) error = devm_gpio_request_one(dev, button->gpio, flags, button->desc ? : DRV_NAME); - if (error) { - dev_err(dev, - "unable to claim gpio %u, err=%d\n", - button->gpio, error); - return error; - } + if (error) + return dev_err_probe(dev, error, + "unable to claim gpio %u\n", + button->gpio); bdata->gpiod = gpio_to_desc(button->gpio); if (!bdata->gpiod) { diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c index 258d5fe3d..aa32371f0 100644 --- a/drivers/input/rmi4/rmi_driver.c +++ b/drivers/input/rmi4/rmi_driver.c @@ -1196,7 +1196,11 @@ static int rmi_driver_probe(struct device *dev) } rmi_driver_set_input_params(rmi_dev, data->input); data->input->phys = devm_kasprintf(dev, GFP_KERNEL, - "%s/input0", dev_name(dev)); + "%s/input0", dev_name(dev)); + if (!data->input->phys) { + retval = -ENOMEM; + goto err; + } } retval = rmi_init_functions(data); diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 124ab98ea..6804970d8 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -626,6 +626,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { .driver_data = (void *)(SERIO_QUIRK_NOAUX) }, { + /* Fujitsu Lifebook U728 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U728"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOAUX) + }, + { /* Gigabyte M912 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), @@ -1181,6 +1189,12 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { }, { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "NS5x_7xPU"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOAUX) + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "NJ50_70CU"), }, .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 603f625a7..91cc3a564 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -1827,6 +1827,9 @@ static int __init iommu_init_pci(struct amd_iommu *iommu) /* Prevent binding other PCI device drivers to IOMMU devices */ iommu->dev->match_driver = false; + /* ACPI _PRT won't have an IRQ for IOMMU */ + iommu->dev->irq_managed = 1; + pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET, &iommu->cap); diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index 9b24e8224..586b289cf 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -489,6 +489,9 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu, if (!info || !info->ats_enabled) return; + if (pci_dev_is_disconnected(to_pci_dev(dev))) + return; + sid = info->bus << 8 | info->devfn; qdep = info->ats_qdep; pfsid = info->pfsid; diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index aabf56272..02e3183a4 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -33,7 +33,7 @@ int intel_svm_enable_prq(struct intel_iommu *iommu) struct page *pages; int irq, ret; - pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, PRQ_ORDER); + pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO, PRQ_ORDER); if (!pages) { pr_warn("IOMMU: %s: Failed to allocate page request queue\n", iommu->name); diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c index a4aee16db..a46a4f836 100644 --- a/drivers/irqchip/irq-brcmstb-l2.c +++ b/drivers/irqchip/irq-brcmstb-l2.c @@ -2,7 +2,7 @@ /* * Generic Broadcom Set Top Box Level 2 Interrupt controller driver * - * Copyright (C) 2014-2017 Broadcom + * Copyright (C) 2014-2024 Broadcom */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -113,6 +113,9 @@ static void brcmstb_l2_intc_irq_handle(struct irq_desc *desc) generic_handle_irq(irq_linear_revmap(b->domain, irq)); } while (status); out: + /* Don't ack parent before all device writes are done */ + wmb(); + chained_irq_exit(chip, desc); } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index f1fa98e5e..4e486cccc 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3782,8 +3782,9 @@ static int its_vpe_set_affinity(struct irq_data *d, bool force) { struct its_vpe *vpe = irq_data_get_irq_chip_data(d); - int from, cpu = cpumask_first(mask_val); + struct cpumask common, *table_mask; unsigned long flags; + int from, cpu; /* * Changing affinity is mega expensive, so let's be as lazy as @@ -3799,19 +3800,22 @@ static int its_vpe_set_affinity(struct irq_data *d, * taken on any vLPI handling path that evaluates vpe->col_idx. */ from = vpe_to_cpuid_lock(vpe, &flags); - if (from == cpu) - goto out; - - vpe->col_idx = cpu; + table_mask = gic_data_rdist_cpu(from)->vpe_table_mask; /* - * GICv4.1 allows us to skip VMOVP if moving to a cpu whose RD - * is sharing its VPE table with the current one. + * If we are offered another CPU in the same GICv4.1 ITS + * affinity, pick this one. Otherwise, any CPU will do. */ - if (gic_data_rdist_cpu(cpu)->vpe_table_mask && - cpumask_test_cpu(from, gic_data_rdist_cpu(cpu)->vpe_table_mask)) + if (table_mask && cpumask_and(&common, mask_val, table_mask)) + cpu = cpumask_test_cpu(from, &common) ? from : cpumask_first(&common); + else + cpu = cpumask_first(mask_val); + + if (from == cpu) goto out; + vpe->col_idx = cpu; + its_send_vmovp(vpe); its_vpe_db_proxy_move(vpe, from, cpu); @@ -4504,13 +4508,8 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq set_bit(i, bitmap); } - if (err) { - if (i > 0) - its_vpe_irq_domain_free(domain, virq, i); - - its_lpi_free(bitmap, base, nr_ids); - its_free_prop_table(vprop_page); - } + if (err) + its_vpe_irq_domain_free(domain, virq, i); return err; } diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index fc25b900c..7888e3c08 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -398,6 +398,8 @@ static void gic_all_vpes_irq_cpu_online(void) unsigned int intr = local_intrs[i]; struct gic_all_vpes_chip_data *cd; + if (!gic_local_irq_is_routable(intr)) + continue; cd = &gic_all_vpes_chip_data[intr]; write_gic_vl_map(mips_gic_vx_map_reg(intr), cd->map); if (cd->mask) diff --git a/drivers/leds/leds-aw2013.c b/drivers/leds/leds-aw2013.c index 80d937454..f7d9795ce 100644 --- a/drivers/leds/leds-aw2013.c +++ b/drivers/leds/leds-aw2013.c @@ -397,6 +397,7 @@ error_reg: regulator_disable(chip->vcc_regulator); error: + mutex_unlock(&chip->mutex); mutex_destroy(&chip->mutex); return ret; } diff --git a/drivers/leds/leds-sgm3140.c b/drivers/leds/leds-sgm3140.c index f4f831570..e72017b11 100644 --- a/drivers/leds/leds-sgm3140.c +++ b/drivers/leds/leds-sgm3140.c @@ -114,8 +114,11 @@ static int sgm3140_brightness_set(struct led_classdev *led_cdev, "failed to enable regulator: %d\n", ret); return ret; } + gpiod_set_value_cansleep(priv->flash_gpio, 0); gpiod_set_value_cansleep(priv->enable_gpio, 1); } else { + del_timer_sync(&priv->powerdown_timer); + gpiod_set_value_cansleep(priv->flash_gpio, 0); gpiod_set_value_cansleep(priv->enable_gpio, 0); ret = regulator_disable(priv->vin_regulator); if (ret) { diff --git a/drivers/leds/trigger/ledtrig-panic.c b/drivers/leds/trigger/ledtrig-panic.c index 5751cd032..4bf232465 100644 --- a/drivers/leds/trigger/ledtrig-panic.c +++ b/drivers/leds/trigger/ledtrig-panic.c @@ -63,10 +63,13 @@ static long led_panic_blink(int state) static int __init ledtrig_panic_init(void) { + led_trigger_register_simple("panic", &trigger); + if (!trigger) + return -ENOMEM; + atomic_notifier_chain_register(&panic_notifier_list, &led_trigger_panic_nb); - led_trigger_register_simple("panic", &trigger); panic_blink = led_panic_blink; return 0; } diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c index c5663398c..28f5450e4 100644 --- a/drivers/mailbox/imx-mailbox.c +++ b/drivers/mailbox/imx-mailbox.c @@ -331,8 +331,6 @@ static int imx_mu_startup(struct mbox_chan *chan) break; } - priv->suspend = true; - return 0; } @@ -550,8 +548,6 @@ static int imx_mu_probe(struct platform_device *pdev) clk_disable_unprepare(priv->clk); - priv->suspend = false; - return 0; disable_runtime_pm: @@ -614,6 +610,8 @@ static int __maybe_unused imx_mu_suspend_noirq(struct device *dev) if (!priv->clk) priv->xcr = imx_mu_read(priv, priv->dcfg->xCR); + priv->suspend = true; + return 0; } @@ -632,6 +630,8 @@ static int __maybe_unused imx_mu_resume_noirq(struct device *dev) if (!imx_mu_read(priv, priv->dcfg->xCR) && !priv->clk) imx_mu_write(priv, priv->xcr, priv->dcfg->xCR); + priv->suspend = false; + return 0; } diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 3db92d9a0..ff73b2c17 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -19,6 +19,8 @@ #include "dm.h" #define DM_RESERVED_MAX_IOS 1024 +#define DM_MAX_TARGETS 1048576 +#define DM_MAX_TARGET_PARAMS 1024 struct dm_kobject_holder { struct kobject kobj; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 5d772f322..5deda6c6f 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -48,11 +48,11 @@ struct convert_context { struct completion restart; struct bio *bio_in; - struct bio *bio_out; struct bvec_iter iter_in; + struct bio *bio_out; struct bvec_iter iter_out; - u64 cc_sector; atomic_t cc_pending; + u64 cc_sector; union { struct skcipher_request *req; struct aead_request *req_aead; @@ -2064,6 +2064,12 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) io->ctx.bio_out = clone; io->ctx.iter_out = clone->bi_iter; + if (crypt_integrity_aead(cc)) { + bio_copy_data(clone, io->base_bio); + io->ctx.bio_in = clone; + io->ctx.iter_in = clone->bi_iter; + } + sector += bio_sectors(clone); crypt_inc_pending(io); diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 62cae34ca..067be1d9f 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -3937,7 +3937,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) } else if (sscanf(opt_string, "sectors_per_bit:%llu%c", &llval, &dummy) == 1) { log2_sectors_per_bitmap_bit = !llval ? 0 : __ilog2_u64(llval); } else if (sscanf(opt_string, "bitmap_flush_interval:%u%c", &val, &dummy) == 1) { - if (val >= (uint64_t)UINT_MAX * 1000 / HZ) { + if ((uint64_t)val >= (uint64_t)UINT_MAX * 1000 / HZ) { r = -EINVAL; ti->error = "Invalid bitmap_flush_interval argument"; goto bad; diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 5f9b9178c..4184c8a2d 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1760,7 +1760,8 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern if (copy_from_user(param_kernel, user, minimum_data_size)) return -EFAULT; - if (param_kernel->data_size < minimum_data_size) + if (unlikely(param_kernel->data_size < minimum_data_size) || + unlikely(param_kernel->data_size > DM_MAX_TARGETS * DM_MAX_TARGET_PARAMS)) return -EINVAL; secure_data = param_kernel->flags & DM_SECURE_DATA_FLAG; diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 140bdf2a6..99995b180 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3329,14 +3329,14 @@ static int raid_map(struct dm_target *ti, struct bio *bio) struct mddev *mddev = &rs->md; /* - * If we're reshaping to add disk(s)), ti->len and + * If we're reshaping to add disk(s), ti->len and * mddev->array_sectors will differ during the process * (ti->len > mddev->array_sectors), so we have to requeue * bios with addresses > mddev->array_sectors here or * there will occur accesses past EOD of the component * data images thus erroring the raid set. */ - if (unlikely(bio_end_sector(bio) > mddev->array_sectors)) + if (unlikely(bio_has_data(bio) && bio_end_sector(bio) > mddev->array_sectors)) return DM_MAPIO_REQUEUE; md_handle_request(mddev, bio); @@ -4019,7 +4019,9 @@ static void raid_resume(struct dm_target *ti) * Take this opportunity to check whether any failed * devices are reachable again. */ + mddev_lock_nointr(mddev); attempt_restore_of_faulty_devices(rs); + mddev_unlock(mddev); } if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) { diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 41735a25d..de73fe796 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -685,8 +685,10 @@ static void dm_exception_table_exit(struct dm_exception_table *et, for (i = 0; i < size; i++) { slot = et->table + i; - hlist_bl_for_each_entry_safe(ex, pos, n, slot, hash_list) + hlist_bl_for_each_entry_safe(ex, pos, n, slot, hash_list) { kmem_cache_free(mem, ex); + cond_resched(); + } } vfree(et->table); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 5c590895c..31bcdcd93 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -144,7 +144,12 @@ static int alloc_targets(struct dm_table *t, unsigned int num) int dm_table_create(struct dm_table **result, fmode_t mode, unsigned num_targets, struct mapped_device *md) { - struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL); + struct dm_table *t; + + if (num_targets > DM_MAX_TARGETS) + return -EOVERFLOW; + + t = kzalloc(sizeof(*t), GFP_KERNEL); if (!t) return -ENOMEM; @@ -158,7 +163,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode, if (!num_targets) { kfree(t); - return -ENOMEM; + return -EOVERFLOW; } if (alloc_targets(t, num_targets)) { diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h index 78d1e5119..f61c89c79 100644 --- a/drivers/md/dm-verity.h +++ b/drivers/md/dm-verity.h @@ -74,11 +74,11 @@ struct dm_verity_io { /* original value of bio->bi_end_io */ bio_end_io_t *orig_bi_end_io; + struct bvec_iter iter; + sector_t block; unsigned n_blocks; - struct bvec_iter iter; - struct work_struct work; /* diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 9029c1004..dc8498b4b 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2733,6 +2733,9 @@ static void __dm_internal_suspend(struct mapped_device *md, unsigned suspend_fla static void __dm_internal_resume(struct mapped_device *md) { + int r; + struct dm_table *map; + BUG_ON(!md->internal_suspend_count); if (--md->internal_suspend_count) @@ -2741,12 +2744,23 @@ static void __dm_internal_resume(struct mapped_device *md) if (dm_suspended_md(md)) goto done; /* resume from nested suspend */ - /* - * NOTE: existing callers don't need to call dm_table_resume_targets - * (which may fail -- so best to avoid it for now by passing NULL map) - */ - (void) __dm_resume(md, NULL); - + map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock)); + r = __dm_resume(md, map); + if (r) { + /* + * If a preresume method of some target failed, we are in a + * tricky situation. We can't return an error to the caller. We + * can't fake success because then the "resume" and + * "postsuspend" methods would not be paired correctly, and it + * would break various targets, for example it would cause list + * corruption in the "origin" target. + * + * So, we fake normal suspend here, to make sure that the + * "resume" and "postsuspend" methods will be paired correctly. + */ + DMERR("Preresume method failed: %d", r); + set_bit(DMF_SUSPENDED, &md->flags); + } done: clear_bit(DMF_SUSPENDED_INTERNALLY, &md->flags); smp_mb__after_atomic(); diff --git a/drivers/md/md.c b/drivers/md/md.c index 6efe49f7b..09c7f5215 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1179,6 +1179,7 @@ struct super_type { struct md_rdev *refdev, int minor_version); int (*validate_super)(struct mddev *mddev, + struct md_rdev *freshest, struct md_rdev *rdev); void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); @@ -1317,8 +1318,9 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor /* * validate_super for 0.90.0 + * note: we are not using "freshest" for 0.9 superblock */ -static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev) +static int super_90_validate(struct mddev *mddev, struct md_rdev *freshest, struct md_rdev *rdev) { mdp_disk_t *desc; mdp_super_t *sb = page_address(rdev->sb_page); @@ -1833,7 +1835,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ return ret; } -static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) +static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struct md_rdev *rdev) { struct mdp_superblock_1 *sb = page_address(rdev->sb_page); __u64 ev1 = le64_to_cpu(sb->events); @@ -1929,13 +1931,15 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) } } else if (mddev->pers == NULL) { /* Insist of good event counter while assembling, except for - * spares (which don't need an event count) */ - ++ev1; + * spares (which don't need an event count). + * Similar to mdadm, we allow event counter difference of 1 + * from the freshest device. + */ if (rdev->desc_nr >= 0 && rdev->desc_nr < le32_to_cpu(sb->max_dev) && (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX || le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL)) - if (ev1 < mddev->events) + if (ev1 + 1 < mddev->events) return -EINVAL; } else if (mddev->bitmap) { /* If adding to array with a bitmap, then we can accept an @@ -1956,8 +1960,38 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) rdev->desc_nr >= le32_to_cpu(sb->max_dev)) { role = MD_DISK_ROLE_SPARE; rdev->desc_nr = -1; - } else + } else if (mddev->pers == NULL && freshest && ev1 < mddev->events) { + /* + * If we are assembling, and our event counter is smaller than the + * highest event counter, we cannot trust our superblock about the role. + * It could happen that our rdev was marked as Faulty, and all other + * superblocks were updated with +1 event counter. + * Then, before the next superblock update, which typically happens when + * remove_and_add_spares() removes the device from the array, there was + * a crash or reboot. + * If we allow current rdev without consulting the freshest superblock, + * we could cause data corruption. + * Note that in this case our event counter is smaller by 1 than the + * highest, otherwise, this rdev would not be allowed into array; + * both kernel and mdadm allow event counter difference of 1. + */ + struct mdp_superblock_1 *freshest_sb = page_address(freshest->sb_page); + u32 freshest_max_dev = le32_to_cpu(freshest_sb->max_dev); + + if (rdev->desc_nr >= freshest_max_dev) { + /* this is unexpected, better not proceed */ + pr_warn("md: %s: rdev[%pg]: desc_nr(%d) >= freshest(%pg)->sb->max_dev(%u)\n", + mdname(mddev), rdev->bdev, rdev->desc_nr, + freshest->bdev, freshest_max_dev); + return -EUCLEAN; + } + + role = le16_to_cpu(freshest_sb->dev_roles[rdev->desc_nr]); + pr_debug("md: %s: rdev[%pg]: role=%d(0x%x) according to freshest %pg\n", + mdname(mddev), rdev->bdev, role, role, freshest->bdev); + } else { role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]); + } switch(role) { case MD_DISK_ROLE_SPARE: /* spare */ break; @@ -2896,7 +2930,7 @@ static int add_bound_rdev(struct md_rdev *rdev) * and should be added immediately. */ super_types[mddev->major_version]. - validate_super(mddev, rdev); + validate_super(mddev, NULL/*freshest*/, rdev); if (add_journal) mddev_suspend(mddev); err = mddev->pers->hot_add_disk(mddev, rdev); @@ -3814,7 +3848,7 @@ static int analyze_sbs(struct mddev *mddev) } super_types[mddev->major_version]. - validate_super(mddev, freshest); + validate_super(mddev, NULL/*freshest*/, freshest); i = 0; rdev_for_each_safe(rdev, tmp, mddev) { @@ -3829,7 +3863,7 @@ static int analyze_sbs(struct mddev *mddev) } if (rdev != freshest) { if (super_types[mddev->major_version]. - validate_super(mddev, rdev)) { + validate_super(mddev, freshest, rdev)) { pr_warn("md: kicking non-fresh %s from array!\n", bdevname(rdev->bdev,b)); md_kick_rdev_from_array(rdev); @@ -6209,7 +6243,15 @@ static void md_clean(struct mddev *mddev) mddev->persistent = 0; mddev->level = LEVEL_NONE; mddev->clevel[0] = 0; - mddev->flags = 0; + /* + * Don't clear MD_CLOSING, or mddev can be opened again. + * 'hold_active != 0' means mddev is still in the creation + * process and will be used later. + */ + if (mddev->hold_active) + mddev->flags = 0; + else + mddev->flags &= BIT_ULL_MASK(MD_CLOSING); mddev->sb_flags = 0; mddev->ro = 0; mddev->metadata_type[0] = 0; @@ -6817,7 +6859,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) rdev->saved_raid_disk = rdev->raid_disk; } else super_types[mddev->major_version]. - validate_super(mddev, rdev); + validate_super(mddev, NULL/*freshest*/, rdev); if ((info->state & (1<<MD_DISK_SYNC)) && rdev->raid_disk != info->raid_disk) { /* This was a hot-add request, but events doesn't @@ -7502,7 +7544,6 @@ static inline bool md_ioctl_valid(unsigned int cmd) { switch (cmd) { case ADD_NEW_DISK: - case BLKROSET: case GET_ARRAY_INFO: case GET_BITMAP_FILE: case GET_DISK_INFO: @@ -7529,8 +7570,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, int err = 0; void __user *argp = (void __user *)arg; struct mddev *mddev = NULL; - int ro; - bool did_set_md_closing = false; if (!md_ioctl_valid(cmd)) return -ENOTTY; @@ -7617,7 +7656,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, err = -EBUSY; goto out; } - did_set_md_closing = true; mutex_unlock(&mddev->open_mutex); sync_blockdev(bdev); } @@ -7712,35 +7750,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, goto unlock; } break; - - case BLKROSET: - if (get_user(ro, (int __user *)(arg))) { - err = -EFAULT; - goto unlock; - } - err = -EINVAL; - - /* if the bdev is going readonly the value of mddev->ro - * does not matter, no writes are coming - */ - if (ro) - goto unlock; - - /* are we are already prepared for writes? */ - if (mddev->ro != 1) - goto unlock; - - /* transitioning to readauto need only happen for - * arrays that call md_write_start - */ - if (mddev->pers) { - err = restart_array(mddev); - if (err == 0) { - mddev->ro = 2; - set_disk_ro(mddev->gendisk, 0); - } - } - goto unlock; } /* @@ -7810,7 +7819,7 @@ unlock: mddev->hold_active = 0; mddev_unlock(mddev); out: - if(did_set_md_closing) + if (cmd == STOP_ARRAY_RO || (err && cmd == STOP_ARRAY)) clear_bit(MD_CLOSING, &mddev->flags); return err; } @@ -7834,6 +7843,36 @@ static int md_compat_ioctl(struct block_device *bdev, fmode_t mode, } #endif /* CONFIG_COMPAT */ +static int md_set_read_only(struct block_device *bdev, bool ro) +{ + struct mddev *mddev = bdev->bd_disk->private_data; + int err; + + err = mddev_lock(mddev); + if (err) + return err; + + if (!mddev->raid_disks && !mddev->external) { + err = -ENODEV; + goto out_unlock; + } + + /* + * Transitioning to read-auto need only happen for arrays that call + * md_write_start and which are not ready for writes yet. + */ + if (!ro && mddev->ro == 1 && mddev->pers) { + err = restart_array(mddev); + if (err) + goto out_unlock; + mddev->ro = 2; + } + +out_unlock: + mddev_unlock(mddev); + return err; +} + static int md_open(struct block_device *bdev, fmode_t mode) { /* @@ -7910,6 +7949,7 @@ const struct block_device_operations md_fops = #endif .getgeo = md_getgeo, .check_events = md_check_events, + .set_read_only = md_set_read_only, }; static int md_thread(void *arg) diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index 97b479223..2f7ab5df1 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -1116,20 +1116,6 @@ void cec_received_msg_ts(struct cec_adapter *adap, if (valid_la && min_len) { /* These messages have special length requirements */ switch (cmd) { - case CEC_MSG_TIMER_STATUS: - if (msg->msg[2] & 0x10) { - switch (msg->msg[2] & 0xf) { - case CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE: - case CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE: - if (msg->len < 5) - valid_la = false; - break; - } - } else if ((msg->msg[2] & 0xf) == CEC_OP_PROG_ERROR_DUPLICATE) { - if (msg->len < 5) - valid_la = false; - } - break; case CEC_MSG_RECORD_ON: switch (msg->msg[2]) { case CEC_OP_RECORD_SRC_OWN: diff --git a/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c b/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c index 7607b516a..68968bfa2 100644 --- a/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c +++ b/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c @@ -113,6 +113,7 @@ int tpg_alloc(struct tpg_data *tpg, unsigned max_w) { unsigned pat; unsigned plane; + int ret = 0; tpg->max_line_width = max_w; for (pat = 0; pat < TPG_MAX_PAT_LINES; pat++) { @@ -121,14 +122,18 @@ int tpg_alloc(struct tpg_data *tpg, unsigned max_w) tpg->lines[pat][plane] = vzalloc(array3_size(max_w, 2, pixelsz)); - if (!tpg->lines[pat][plane]) - return -ENOMEM; + if (!tpg->lines[pat][plane]) { + ret = -ENOMEM; + goto free_lines; + } if (plane == 0) continue; tpg->downsampled_lines[pat][plane] = vzalloc(array3_size(max_w, 2, pixelsz)); - if (!tpg->downsampled_lines[pat][plane]) - return -ENOMEM; + if (!tpg->downsampled_lines[pat][plane]) { + ret = -ENOMEM; + goto free_lines; + } } } for (plane = 0; plane < TPG_MAX_PLANES; plane++) { @@ -136,18 +141,45 @@ int tpg_alloc(struct tpg_data *tpg, unsigned max_w) tpg->contrast_line[plane] = vzalloc(array_size(pixelsz, max_w)); - if (!tpg->contrast_line[plane]) - return -ENOMEM; + if (!tpg->contrast_line[plane]) { + ret = -ENOMEM; + goto free_contrast_line; + } tpg->black_line[plane] = vzalloc(array_size(pixelsz, max_w)); - if (!tpg->black_line[plane]) - return -ENOMEM; + if (!tpg->black_line[plane]) { + ret = -ENOMEM; + goto free_contrast_line; + } tpg->random_line[plane] = vzalloc(array3_size(max_w, 2, pixelsz)); - if (!tpg->random_line[plane]) - return -ENOMEM; + if (!tpg->random_line[plane]) { + ret = -ENOMEM; + goto free_contrast_line; + } } return 0; + +free_contrast_line: + for (plane = 0; plane < TPG_MAX_PLANES; plane++) { + vfree(tpg->contrast_line[plane]); + vfree(tpg->black_line[plane]); + vfree(tpg->random_line[plane]); + tpg->contrast_line[plane] = NULL; + tpg->black_line[plane] = NULL; + tpg->random_line[plane] = NULL; + } +free_lines: + for (pat = 0; pat < TPG_MAX_PAT_LINES; pat++) + for (plane = 0; plane < TPG_MAX_PLANES; plane++) { + vfree(tpg->lines[pat][plane]); + tpg->lines[pat][plane] = NULL; + if (plane == 0) + continue; + vfree(tpg->downsampled_lines[pat][plane]); + tpg->downsampled_lines[pat][plane] = NULL; + } + return ret; } EXPORT_SYMBOL_GPL(tpg_alloc); diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index 3a83e8e09..23a0c2097 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -504,6 +504,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, dvbdevfops = kmemdup(template->fops, sizeof(*dvbdevfops), GFP_KERNEL); if (!dvbdevfops) { kfree(dvbdev); + *pdvbdev = NULL; mutex_unlock(&dvbdev_register_lock); return -ENOMEM; } @@ -512,6 +513,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, if (!new_node) { kfree(dvbdevfops); kfree(dvbdev); + *pdvbdev = NULL; mutex_unlock(&dvbdev_register_lock); return -ENOMEM; } @@ -545,6 +547,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, } list_del (&dvbdev->list_head); kfree(dvbdev); + *pdvbdev = NULL; up_write(&minor_rwsem); mutex_unlock(&dvbdev_register_lock); return -EINVAL; @@ -567,6 +570,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); kfree(dvbdev); + *pdvbdev = NULL; mutex_unlock(&dvbdev_register_lock); return ret; } @@ -585,6 +589,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); kfree(dvbdev); + *pdvbdev = NULL; mutex_unlock(&dvbdev_register_lock); return PTR_ERR(clsdev); } diff --git a/drivers/media/dvb-frontends/stv0367.c b/drivers/media/dvb-frontends/stv0367.c index 0bfca1174..8cbae8235 100644 --- a/drivers/media/dvb-frontends/stv0367.c +++ b/drivers/media/dvb-frontends/stv0367.c @@ -118,50 +118,32 @@ static const s32 stv0367cab_RF_LookUp2[RF_LOOKUP_TABLE2_SIZE][RF_LOOKUP_TABLE2_S } }; -static -int stv0367_writeregs(struct stv0367_state *state, u16 reg, u8 *data, int len) +static noinline_for_stack +int stv0367_writereg(struct stv0367_state *state, u16 reg, u8 data) { - u8 buf[MAX_XFER_SIZE]; + u8 buf[3] = { MSB(reg), LSB(reg), data }; struct i2c_msg msg = { .addr = state->config->demod_address, .flags = 0, .buf = buf, - .len = len + 2 + .len = 3, }; int ret; - if (2 + len > sizeof(buf)) { - printk(KERN_WARNING - "%s: i2c wr reg=%04x: len=%d is too big!\n", - KBUILD_MODNAME, reg, len); - return -EINVAL; - } - - - buf[0] = MSB(reg); - buf[1] = LSB(reg); - memcpy(buf + 2, data, len); - if (i2cdebug) printk(KERN_DEBUG "%s: [%02x] %02x: %02x\n", __func__, - state->config->demod_address, reg, buf[2]); + state->config->demod_address, reg, data); ret = i2c_transfer(state->i2c, &msg, 1); if (ret != 1) printk(KERN_ERR "%s: i2c write error! ([%02x] %02x: %02x)\n", - __func__, state->config->demod_address, reg, buf[2]); + __func__, state->config->demod_address, reg, data); return (ret != 1) ? -EREMOTEIO : 0; } -static int stv0367_writereg(struct stv0367_state *state, u16 reg, u8 data) -{ - u8 tmp = data; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */ - - return stv0367_writeregs(state, reg, &tmp, 1); -} - -static u8 stv0367_readreg(struct stv0367_state *state, u16 reg) +static noinline_for_stack +u8 stv0367_readreg(struct stv0367_state *state, u16 reg) { u8 b0[] = { 0, 0 }; u8 b1[] = { 0 }; diff --git a/drivers/media/i2c/tc358743.c b/drivers/media/i2c/tc358743.c index f21da11ca..8bcb4b354 100644 --- a/drivers/media/i2c/tc358743.c +++ b/drivers/media/i2c/tc358743.c @@ -2108,9 +2108,6 @@ static int tc358743_probe(struct i2c_client *client) state->mbus_fmt_code = MEDIA_BUS_FMT_RGB888_1X24; sd->dev = &client->dev; - err = v4l2_async_register_subdev(sd); - if (err < 0) - goto err_hdl; mutex_init(&state->confctl_mutex); @@ -2168,6 +2165,10 @@ static int tc358743_probe(struct i2c_client *client) if (err) goto err_work_queues; + err = v4l2_async_register_subdev(sd); + if (err < 0) + goto err_work_queues; + v4l2_info(sd, "%s found @ 0x%x (%s)\n", client->name, client->addr << 1, client->adapter->name); diff --git a/drivers/media/pci/ddbridge/ddbridge-main.c b/drivers/media/pci/ddbridge/ddbridge-main.c index 03dc9924f..bb7fb6402 100644 --- a/drivers/media/pci/ddbridge/ddbridge-main.c +++ b/drivers/media/pci/ddbridge/ddbridge-main.c @@ -247,7 +247,7 @@ fail: ddb_unmap(dev); pci_set_drvdata(pdev, NULL); pci_disable_device(pdev); - return -1; + return stat; } /****************************************************************************/ diff --git a/drivers/media/pci/sta2x11/sta2x11_vip.c b/drivers/media/pci/sta2x11/sta2x11_vip.c index 336df65c8..01ca940ae 100644 --- a/drivers/media/pci/sta2x11/sta2x11_vip.c +++ b/drivers/media/pci/sta2x11/sta2x11_vip.c @@ -760,7 +760,7 @@ static const struct video_device video_dev_template = { /** * vip_irq - interrupt routine * @irq: Number of interrupt ( not used, correct number is assumed ) - * @vip: local data structure containing all information + * @data: local data structure containing all information * * check for both frame interrupts set ( top and bottom ). * check FIFO overflow, but limit number of log messages after open. @@ -770,8 +770,9 @@ static const struct video_device video_dev_template = { * * IRQ_HANDLED, interrupt done. */ -static irqreturn_t vip_irq(int irq, struct sta2x11_vip *vip) +static irqreturn_t vip_irq(int irq, void *data) { + struct sta2x11_vip *vip = data; unsigned int status; status = reg_read(vip, DVP_ITS); @@ -1053,9 +1054,7 @@ static int sta2x11_vip_init_one(struct pci_dev *pdev, spin_lock_init(&vip->slock); - ret = request_irq(pdev->irq, - (irq_handler_t) vip_irq, - IRQF_SHARED, KBUILD_MODNAME, vip); + ret = request_irq(pdev->irq, vip_irq, IRQF_SHARED, KBUILD_MODNAME, vip); if (ret) { dev_err(&pdev->dev, "request_irq failed\n"); ret = -ENODEV; diff --git a/drivers/media/pci/ttpci/av7110_av.c b/drivers/media/pci/ttpci/av7110_av.c index ea9f7d005..e201d5a56 100644 --- a/drivers/media/pci/ttpci/av7110_av.c +++ b/drivers/media/pci/ttpci/av7110_av.c @@ -822,10 +822,10 @@ static int write_ts_to_decoder(struct av7110 *av7110, int type, const u8 *buf, s av7110_ipack_flush(ipack); if (buf[3] & ADAPT_FIELD) { + if (buf[4] > len - 1 - 4) + return 0; len -= buf[4] + 1; buf += buf[4] + 1; - if (!len) - return 0; } av7110_ipack_instant_repack(buf + 4, len - 4, ipack); diff --git a/drivers/media/pci/ttpci/budget-av.c b/drivers/media/pci/ttpci/budget-av.c index 3cb83005c..519f85e0a 100644 --- a/drivers/media/pci/ttpci/budget-av.c +++ b/drivers/media/pci/ttpci/budget-av.c @@ -1462,7 +1462,8 @@ static int budget_av_attach(struct saa7146_dev *dev, struct saa7146_pci_extensio budget_av->has_saa7113 = 1; err = saa7146_vv_init(dev, &vv_data); if (err != 0) { - /* fixme: proper cleanup here */ + ttpci_budget_deinit(&budget_av->budget); + kfree(budget_av); ERR("cannot init vv subsystem\n"); return err; } @@ -1471,9 +1472,10 @@ static int budget_av_attach(struct saa7146_dev *dev, struct saa7146_pci_extensio vv_data.vid_ops.vidioc_s_input = vidioc_s_input; if ((err = saa7146_register_device(&budget_av->vd, dev, "knc1", VFL_TYPE_VIDEO))) { - /* fixme: proper cleanup here */ - ERR("cannot register capture v4l2 device\n"); saa7146_vv_release(dev); + ttpci_budget_deinit(&budget_av->budget); + kfree(budget_av); + ERR("cannot register capture v4l2 device\n"); return err; } diff --git a/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c b/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c index 36109c324..3519c2252 100644 --- a/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c +++ b/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c @@ -977,13 +977,13 @@ static void mtk_jpeg_dec_device_run(void *priv) if (ret < 0) goto dec_end; - schedule_delayed_work(&jpeg->job_timeout_work, - msecs_to_jiffies(MTK_JPEG_HW_TIMEOUT_MSEC)); - mtk_jpeg_set_dec_src(ctx, &src_buf->vb2_buf, &bs); if (mtk_jpeg_set_dec_dst(ctx, &jpeg_src_buf->dec_param, &dst_buf->vb2_buf, &fb)) goto dec_end; + schedule_delayed_work(&jpeg->job_timeout_work, + msecs_to_jiffies(MTK_JPEG_HW_TIMEOUT_MSEC)); + spin_lock_irqsave(&jpeg->hw_lock, flags); mtk_jpeg_dec_reset(jpeg->reg_base); mtk_jpeg_dec_set_config(jpeg->reg_base, diff --git a/drivers/media/platform/mtk-mdp/mtk_mdp_vpu.c b/drivers/media/platform/mtk-mdp/mtk_mdp_vpu.c index b065ccd06..378a1cba0 100644 --- a/drivers/media/platform/mtk-mdp/mtk_mdp_vpu.c +++ b/drivers/media/platform/mtk-mdp/mtk_mdp_vpu.c @@ -26,7 +26,7 @@ static void mtk_mdp_vpu_handle_init_ack(const struct mdp_ipi_comm_ack *msg) vpu->inst_addr = msg->vpu_inst_addr; } -static void mtk_mdp_vpu_ipi_handler(const void *data, unsigned int len, +static void mtk_mdp_vpu_ipi_handler(void *data, unsigned int len, void *priv) { const struct mdp_ipi_comm_ack *msg = data; diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_vpu.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_vpu.c index cfc7ebed8..1ec29f1b1 100644 --- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_vpu.c +++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_fw_vpu.c @@ -29,15 +29,7 @@ static int mtk_vcodec_vpu_set_ipi_register(struct mtk_vcodec_fw *fw, int id, mtk_vcodec_ipi_handler handler, const char *name, void *priv) { - /* - * The handler we receive takes a void * as its first argument. We - * cannot change this because it needs to be passed down to the rproc - * subsystem when SCP is used. VPU takes a const argument, which is - * more constrained, so the conversion below is safe. - */ - ipi_handler_t handler_const = (ipi_handler_t)handler; - - return vpu_ipi_register(fw->pdev, id, handler_const, name, priv); + return vpu_ipi_register(fw->pdev, id, handler, name, priv); } static int mtk_vcodec_vpu_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf, diff --git a/drivers/media/platform/mtk-vpu/mtk_vpu.c b/drivers/media/platform/mtk-vpu/mtk_vpu.c index e7c4b0dd5..a2f61d97f 100644 --- a/drivers/media/platform/mtk-vpu/mtk_vpu.c +++ b/drivers/media/platform/mtk-vpu/mtk_vpu.c @@ -612,7 +612,7 @@ OUT_LOAD_FW: } EXPORT_SYMBOL_GPL(vpu_load_firmware); -static void vpu_init_ipi_handler(const void *data, unsigned int len, void *priv) +static void vpu_init_ipi_handler(void *data, unsigned int len, void *priv) { struct mtk_vpu *vpu = priv; const struct vpu_run *run = data; diff --git a/drivers/media/platform/mtk-vpu/mtk_vpu.h b/drivers/media/platform/mtk-vpu/mtk_vpu.h index ee7c552ce..d4453b4bc 100644 --- a/drivers/media/platform/mtk-vpu/mtk_vpu.h +++ b/drivers/media/platform/mtk-vpu/mtk_vpu.h @@ -15,7 +15,7 @@ * VPU interfaces with other blocks by share memory and interrupt. **/ -typedef void (*ipi_handler_t) (const void *data, +typedef void (*ipi_handler_t) (void *data, unsigned int len, void *priv); diff --git a/drivers/media/platform/rockchip/rga/rga.c b/drivers/media/platform/rockchip/rga/rga.c index e3246344f..bcbbd1408 100644 --- a/drivers/media/platform/rockchip/rga/rga.c +++ b/drivers/media/platform/rockchip/rga/rga.c @@ -187,7 +187,7 @@ static int rga_setup_ctrls(struct rga_ctx *ctx) static struct rga_fmt formats[] = { { .fourcc = V4L2_PIX_FMT_ARGB32, - .color_swap = RGA_COLOR_RB_SWAP, + .color_swap = RGA_COLOR_ALPHA_SWAP, .hw_format = RGA_COLOR_FMT_ABGR8888, .depth = 32, .uv_factor = 1, @@ -195,17 +195,8 @@ static struct rga_fmt formats[] = { .x_div = 1, }, { - .fourcc = V4L2_PIX_FMT_XRGB32, - .color_swap = RGA_COLOR_RB_SWAP, - .hw_format = RGA_COLOR_FMT_XBGR8888, - .depth = 32, - .uv_factor = 1, - .y_div = 1, - .x_div = 1, - }, - { .fourcc = V4L2_PIX_FMT_ABGR32, - .color_swap = RGA_COLOR_ALPHA_SWAP, + .color_swap = RGA_COLOR_RB_SWAP, .hw_format = RGA_COLOR_FMT_ABGR8888, .depth = 32, .uv_factor = 1, @@ -214,7 +205,7 @@ static struct rga_fmt formats[] = { }, { .fourcc = V4L2_PIX_FMT_XBGR32, - .color_swap = RGA_COLOR_ALPHA_SWAP, + .color_swap = RGA_COLOR_RB_SWAP, .hw_format = RGA_COLOR_FMT_XBGR8888, .depth = 32, .uv_factor = 1, diff --git a/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c b/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c index 2c159483c..f0d2bcbe2 100644 --- a/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c +++ b/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c @@ -66,6 +66,7 @@ static void deinterlace_device_run(void *priv) struct vb2_v4l2_buffer *src, *dst; unsigned int hstep, vstep; dma_addr_t addr; + int i; src = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx); dst = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx); @@ -160,6 +161,26 @@ static void deinterlace_device_run(void *priv) deinterlace_write(dev, DEINTERLACE_CH1_HORZ_FACT, hstep); deinterlace_write(dev, DEINTERLACE_CH1_VERT_FACT, vstep); + /* neutral filter coefficients */ + deinterlace_set_bits(dev, DEINTERLACE_FRM_CTRL, + DEINTERLACE_FRM_CTRL_COEF_ACCESS); + readl_poll_timeout(dev->base + DEINTERLACE_STATUS, val, + val & DEINTERLACE_STATUS_COEF_STATUS, 2, 40); + + for (i = 0; i < 32; i++) { + deinterlace_write(dev, DEINTERLACE_CH0_HORZ_COEF0 + i * 4, + DEINTERLACE_IDENTITY_COEF); + deinterlace_write(dev, DEINTERLACE_CH0_VERT_COEF + i * 4, + DEINTERLACE_IDENTITY_COEF); + deinterlace_write(dev, DEINTERLACE_CH1_HORZ_COEF0 + i * 4, + DEINTERLACE_IDENTITY_COEF); + deinterlace_write(dev, DEINTERLACE_CH1_VERT_COEF + i * 4, + DEINTERLACE_IDENTITY_COEF); + } + + deinterlace_clr_set_bits(dev, DEINTERLACE_FRM_CTRL, + DEINTERLACE_FRM_CTRL_COEF_ACCESS, 0); + deinterlace_clr_set_bits(dev, DEINTERLACE_FIELD_CTRL, DEINTERLACE_FIELD_CTRL_FIELD_CNT_MSK, DEINTERLACE_FIELD_CTRL_FIELD_CNT(ctx->field)); @@ -248,7 +269,6 @@ static irqreturn_t deinterlace_irq(int irq, void *data) static void deinterlace_init(struct deinterlace_dev *dev) { u32 val; - int i; deinterlace_write(dev, DEINTERLACE_BYPASS, DEINTERLACE_BYPASS_CSC); @@ -284,27 +304,7 @@ static void deinterlace_init(struct deinterlace_dev *dev) deinterlace_clr_set_bits(dev, DEINTERLACE_CHROMA_DIFF, DEINTERLACE_CHROMA_DIFF_TH_MSK, - DEINTERLACE_CHROMA_DIFF_TH(5)); - - /* neutral filter coefficients */ - deinterlace_set_bits(dev, DEINTERLACE_FRM_CTRL, - DEINTERLACE_FRM_CTRL_COEF_ACCESS); - readl_poll_timeout(dev->base + DEINTERLACE_STATUS, val, - val & DEINTERLACE_STATUS_COEF_STATUS, 2, 40); - - for (i = 0; i < 32; i++) { - deinterlace_write(dev, DEINTERLACE_CH0_HORZ_COEF0 + i * 4, - DEINTERLACE_IDENTITY_COEF); - deinterlace_write(dev, DEINTERLACE_CH0_VERT_COEF + i * 4, - DEINTERLACE_IDENTITY_COEF); - deinterlace_write(dev, DEINTERLACE_CH1_HORZ_COEF0 + i * 4, - DEINTERLACE_IDENTITY_COEF); - deinterlace_write(dev, DEINTERLACE_CH1_VERT_COEF + i * 4, - DEINTERLACE_IDENTITY_COEF); - } - - deinterlace_clr_set_bits(dev, DEINTERLACE_FRM_CTRL, - DEINTERLACE_FRM_CTRL_COEF_ACCESS, 0); + DEINTERLACE_CHROMA_DIFF_TH(31)); } static inline struct deinterlace_ctx *deinterlace_file2ctx(struct file *file) @@ -937,11 +937,18 @@ static int deinterlace_runtime_resume(struct device *device) return ret; } + ret = reset_control_deassert(dev->rstc); + if (ret) { + dev_err(dev->dev, "Failed to apply reset\n"); + + goto err_exclusive_rate; + } + ret = clk_prepare_enable(dev->bus_clk); if (ret) { dev_err(dev->dev, "Failed to enable bus clock\n"); - goto err_exclusive_rate; + goto err_rst; } ret = clk_prepare_enable(dev->mod_clk); @@ -958,23 +965,16 @@ static int deinterlace_runtime_resume(struct device *device) goto err_mod_clk; } - ret = reset_control_deassert(dev->rstc); - if (ret) { - dev_err(dev->dev, "Failed to apply reset\n"); - - goto err_ram_clk; - } - deinterlace_init(dev); return 0; -err_ram_clk: - clk_disable_unprepare(dev->ram_clk); err_mod_clk: clk_disable_unprepare(dev->mod_clk); err_bus_clk: clk_disable_unprepare(dev->bus_clk); +err_rst: + reset_control_assert(dev->rstc); err_exclusive_rate: clk_rate_exclusive_put(dev->mod_clk); @@ -985,11 +985,12 @@ static int deinterlace_runtime_suspend(struct device *device) { struct deinterlace_dev *dev = dev_get_drvdata(device); - reset_control_assert(dev->rstc); - clk_disable_unprepare(dev->ram_clk); clk_disable_unprepare(dev->mod_clk); clk_disable_unprepare(dev->bus_clk); + + reset_control_assert(dev->rstc); + clk_rate_exclusive_put(dev->mod_clk); return 0; diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index afae0afe3..a8c55e4bf 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -249,7 +249,7 @@ int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) if (attr->attach_flags) return -EINVAL; - rcdev = rc_dev_get_from_fd(attr->target_fd); + rcdev = rc_dev_get_from_fd(attr->target_fd, true); if (IS_ERR(rcdev)) return PTR_ERR(rcdev); @@ -274,7 +274,7 @@ int lirc_prog_detach(const union bpf_attr *attr) if (IS_ERR(prog)) return PTR_ERR(prog); - rcdev = rc_dev_get_from_fd(attr->target_fd); + rcdev = rc_dev_get_from_fd(attr->target_fd, true); if (IS_ERR(rcdev)) { bpf_prog_put(prog); return PTR_ERR(rcdev); @@ -299,7 +299,7 @@ int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) if (attr->query.query_flags) return -EINVAL; - rcdev = rc_dev_get_from_fd(attr->query.target_fd); + rcdev = rc_dev_get_from_fd(attr->query.target_fd, false); if (IS_ERR(rcdev)) return PTR_ERR(rcdev); diff --git a/drivers/media/rc/ir_toy.c b/drivers/media/rc/ir_toy.c index 7f3942774..cd2fddf00 100644 --- a/drivers/media/rc/ir_toy.c +++ b/drivers/media/rc/ir_toy.c @@ -324,6 +324,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count) sizeof(COMMAND_SMODE_EXIT), STATE_RESET); if (err) { dev_err(irtoy->dev, "exit sample mode: %d\n", err); + kfree(buf); return err; } @@ -331,6 +332,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count) sizeof(COMMAND_SMODE_ENTER), STATE_COMMAND); if (err) { dev_err(irtoy->dev, "enter sample mode: %d\n", err); + kfree(buf); return err; } diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c index 9c888047f..14243ce03 100644 --- a/drivers/media/rc/lirc_dev.c +++ b/drivers/media/rc/lirc_dev.c @@ -826,7 +826,7 @@ void __exit lirc_dev_exit(void) unregister_chrdev_region(lirc_base_dev, RC_DEV_MAX); } -struct rc_dev *rc_dev_get_from_fd(int fd) +struct rc_dev *rc_dev_get_from_fd(int fd, bool write) { struct fd f = fdget(fd); struct lirc_fh *fh; @@ -840,6 +840,9 @@ struct rc_dev *rc_dev_get_from_fd(int fd) return ERR_PTR(-EINVAL); } + if (write && !(f.file->f_mode & FMODE_WRITE)) + return ERR_PTR(-EPERM); + fh = f.file->private_data; dev = fh->rc; diff --git a/drivers/media/rc/rc-core-priv.h b/drivers/media/rc/rc-core-priv.h index 62f032dff..dfe0352c0 100644 --- a/drivers/media/rc/rc-core-priv.h +++ b/drivers/media/rc/rc-core-priv.h @@ -325,7 +325,7 @@ void lirc_raw_event(struct rc_dev *dev, struct ir_raw_event ev); void lirc_scancode_event(struct rc_dev *dev, struct lirc_scancode *lsc); int lirc_register(struct rc_dev *dev); void lirc_unregister(struct rc_dev *dev); -struct rc_dev *rc_dev_get_from_fd(int fd); +struct rc_dev *rc_dev_get_from_fd(int fd, bool write); #else static inline int lirc_dev_init(void) { return 0; } static inline void lirc_dev_exit(void) {} diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c index ef9af0520..849df4d1c 100644 --- a/drivers/media/tuners/xc4000.c +++ b/drivers/media/tuners/xc4000.c @@ -1517,10 +1517,10 @@ static int xc4000_get_frequency(struct dvb_frontend *fe, u32 *freq) { struct xc4000_priv *priv = fe->tuner_priv; + mutex_lock(&priv->lock); *freq = priv->freq_hz + priv->freq_offset; if (debug) { - mutex_lock(&priv->lock); if ((priv->cur_fw.type & (BASE | FM | DTV6 | DTV7 | DTV78 | DTV8)) == BASE) { u16 snr = 0; @@ -1531,8 +1531,8 @@ static int xc4000_get_frequency(struct dvb_frontend *fe, u32 *freq) return 0; } } - mutex_unlock(&priv->lock); } + mutex_unlock(&priv->lock); dprintk(1, "%s()\n", __func__); diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c index 26408a972..5deee8313 100644 --- a/drivers/media/usb/em28xx/em28xx-cards.c +++ b/drivers/media/usb/em28xx/em28xx-cards.c @@ -4049,6 +4049,10 @@ static int em28xx_usb_probe(struct usb_interface *intf, * topology will likely change after the load of the em28xx subdrivers. */ #ifdef CONFIG_MEDIA_CONTROLLER + /* + * No need to check the return value, the device will still be + * usable without media controller API. + */ retval = media_device_register(dev->media_dev); #endif diff --git a/drivers/media/usb/go7007/go7007-driver.c b/drivers/media/usb/go7007/go7007-driver.c index 6650eab91..3c66542ce 100644 --- a/drivers/media/usb/go7007/go7007-driver.c +++ b/drivers/media/usb/go7007/go7007-driver.c @@ -80,7 +80,7 @@ static int go7007_load_encoder(struct go7007 *go) const struct firmware *fw_entry; char fw_name[] = "go7007/go7007fw.bin"; void *bounce; - int fw_len, rv = 0; + int fw_len; u16 intr_val, intr_data; if (go->boot_fw == NULL) { @@ -109,9 +109,11 @@ static int go7007_load_encoder(struct go7007 *go) go7007_read_interrupt(go, &intr_val, &intr_data) < 0 || (intr_val & ~0x1) != 0x5a5a) { v4l2_err(go, "error transferring firmware\n"); - rv = -1; + kfree(go->boot_fw); + go->boot_fw = NULL; + return -1; } - return rv; + return 0; } MODULE_FIRMWARE("go7007/go7007fw.bin"); diff --git a/drivers/media/usb/go7007/go7007-usb.c b/drivers/media/usb/go7007/go7007-usb.c index eeb85981e..762c13e49 100644 --- a/drivers/media/usb/go7007/go7007-usb.c +++ b/drivers/media/usb/go7007/go7007-usb.c @@ -1201,7 +1201,9 @@ static int go7007_usb_probe(struct usb_interface *intf, u16 channel; /* read channel number from GPIO[1:0] */ - go7007_read_addr(go, 0x3c81, &channel); + if (go7007_read_addr(go, 0x3c81, &channel)) + goto allocfail; + channel &= 0x3; go->board_id = GO7007_BOARDID_ADLINK_MPG24; usb->board = board = &board_adlink_mpg24; diff --git a/drivers/media/usb/pvrusb2/pvrusb2-context.c b/drivers/media/usb/pvrusb2/pvrusb2-context.c index 1764674de..73c95ba23 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-context.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-context.c @@ -90,8 +90,10 @@ static void pvr2_context_destroy(struct pvr2_context *mp) } -static void pvr2_context_notify(struct pvr2_context *mp) +static void pvr2_context_notify(void *ptr) { + struct pvr2_context *mp = ptr; + pvr2_context_set_notify(mp,!0); } @@ -106,9 +108,7 @@ static void pvr2_context_check(struct pvr2_context *mp) pvr2_trace(PVR2_TRACE_CTXT, "pvr2_context %p (initialize)", mp); /* Finish hardware initialization */ - if (pvr2_hdw_initialize(mp->hdw, - (void (*)(void *))pvr2_context_notify, - mp)) { + if (pvr2_hdw_initialize(mp->hdw, pvr2_context_notify, mp)) { mp->video_stream.stream = pvr2_hdw_get_video_stream(mp->hdw); /* Trigger interface initialization. By doing this @@ -267,9 +267,9 @@ static void pvr2_context_exit(struct pvr2_context *mp) void pvr2_context_disconnect(struct pvr2_context *mp) { pvr2_hdw_disconnect(mp->hdw); - mp->disconnect_flag = !0; if (!pvr2_context_shutok()) pvr2_context_notify(mp); + mp->disconnect_flag = !0; } diff --git a/drivers/media/usb/pvrusb2/pvrusb2-dvb.c b/drivers/media/usb/pvrusb2/pvrusb2-dvb.c index 695458452..1b768e746 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-dvb.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-dvb.c @@ -88,8 +88,10 @@ static int pvr2_dvb_feed_thread(void *data) return stat; } -static void pvr2_dvb_notify(struct pvr2_dvb_adapter *adap) +static void pvr2_dvb_notify(void *ptr) { + struct pvr2_dvb_adapter *adap = ptr; + wake_up(&adap->buffer_wait_data); } @@ -149,7 +151,7 @@ static int pvr2_dvb_stream_do_start(struct pvr2_dvb_adapter *adap) } pvr2_stream_set_callback(pvr->video_stream.stream, - (pvr2_stream_callback) pvr2_dvb_notify, adap); + pvr2_dvb_notify, adap); ret = pvr2_stream_set_buffer_count(stream, PVR2_DVB_BUFFER_COUNT); if (ret < 0) return ret; diff --git a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c index 9657c1883..29f2e767f 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c @@ -1037,8 +1037,10 @@ static int pvr2_v4l2_open(struct file *file) } -static void pvr2_v4l2_notify(struct pvr2_v4l2_fh *fhp) +static void pvr2_v4l2_notify(void *ptr) { + struct pvr2_v4l2_fh *fhp = ptr; + wake_up(&fhp->wait_data); } @@ -1071,7 +1073,7 @@ static int pvr2_v4l2_iosetup(struct pvr2_v4l2_fh *fh) hdw = fh->channel.mc_head->hdw; sp = fh->pdi->stream->stream; - pvr2_stream_set_callback(sp,(pvr2_stream_callback)pvr2_v4l2_notify,fh); + pvr2_stream_set_callback(sp, pvr2_v4l2_notify, fh); pvr2_hdw_set_stream_type(hdw,fh->pdi->config); if ((ret = pvr2_hdw_set_streaming(hdw,!0)) < 0) return ret; return pvr2_ioread_set_enabled(fh->rhp,!0); @@ -1202,11 +1204,6 @@ static void pvr2_v4l2_dev_init(struct pvr2_v4l2_dev *dip, dip->minor_type = pvr2_v4l_type_video; nr_ptr = video_nr; caps |= V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_AUDIO; - if (!dip->stream) { - pr_err(KBUILD_MODNAME - ": Failed to set up pvrusb2 v4l video dev due to missing stream instance\n"); - return; - } break; case VFL_TYPE_VBI: dip->config = pvr2_config_vbi; diff --git a/drivers/media/usb/stk1160/stk1160-video.c b/drivers/media/usb/stk1160/stk1160-video.c index 202b084f6..4cf540d1b 100644 --- a/drivers/media/usb/stk1160/stk1160-video.c +++ b/drivers/media/usb/stk1160/stk1160-video.c @@ -107,8 +107,7 @@ void stk1160_copy_video(struct stk1160 *dev, u8 *src, int len) /* * TODO: These stk1160_dbg are very spammy! - * We should 1) check why we are getting them - * and 2) add ratelimit. + * We should check why we are getting them. * * UPDATE: One of the reasons (the only one?) for getting these * is incorrect standard (mismatch between expected and configured). @@ -151,7 +150,7 @@ void stk1160_copy_video(struct stk1160 *dev, u8 *src, int len) /* Let the bug hunt begin! sanity checks! */ if (lencopy < 0) { - stk1160_dbg("copy skipped: negative lencopy\n"); + printk_ratelimited(KERN_DEBUG "copy skipped: negative lencopy\n"); return; } diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c index ad14d5214..56d320b1a 100644 --- a/drivers/media/v4l2-core/v4l2-mem2mem.c +++ b/drivers/media/v4l2-core/v4l2-mem2mem.c @@ -1053,11 +1053,17 @@ static int v4l2_m2m_register_entity(struct media_device *mdev, entity->function = function; ret = media_entity_pads_init(entity, num_pads, pads); - if (ret) + if (ret) { + kfree(entity->name); + entity->name = NULL; return ret; + } ret = media_device_register_entity(mdev, entity); - if (ret) + if (ret) { + kfree(entity->name); + entity->name = NULL; return ret; + } return 0; } diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index b8847ae04..c5c6608cc 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1382,6 +1382,7 @@ config MFD_DAVINCI_VOICECODEC config MFD_TI_AM335X_TSCADC tristate "TI ADC / Touch Screen chip support" + depends on ARCH_OMAP2PLUS || ARCH_K3 || COMPILE_TEST select MFD_CORE select REGMAP select REGMAP_MMIO diff --git a/drivers/mfd/altera-sysmgr.c b/drivers/mfd/altera-sysmgr.c index 591b300d9..59efe7d5d 100644 --- a/drivers/mfd/altera-sysmgr.c +++ b/drivers/mfd/altera-sysmgr.c @@ -110,7 +110,9 @@ struct regmap *altr_sysmgr_regmap_lookup_by_phandle(struct device_node *np, dev = driver_find_device_by_of_node(&altr_sysmgr_driver.driver, (void *)sysmgr_np); - of_node_put(sysmgr_np); + if (property) + of_node_put(sysmgr_np); + if (!dev) return ERR_PTR(-EPROBE_DEFER); diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c index 60f74144a..4d536a097 100644 --- a/drivers/mfd/syscon.c +++ b/drivers/mfd/syscon.c @@ -224,7 +224,9 @@ struct regmap *syscon_regmap_lookup_by_phandle(struct device_node *np, return ERR_PTR(-ENODEV); regmap = syscon_node_to_regmap(syscon_np); - of_node_put(syscon_np); + + if (property) + of_node_put(syscon_np); return regmap; } diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 9822efdc6..af050cfdc 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -1592,7 +1592,7 @@ static int fastrpc_cb_remove(struct platform_device *pdev) int i; spin_lock_irqsave(&cctx->lock, flags); - for (i = 1; i < FASTRPC_MAX_SESSIONS; i++) { + for (i = 0; i < FASTRPC_MAX_SESSIONS; i++) { if (cctx->session[i].sid == sess->sid) { cctx->session[i].valid = false; cctx->sesscount--; diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index eabbdf17b..28acedb10 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -112,6 +112,8 @@ #define MEI_DEV_ID_RPL_S 0x7A68 /* Raptor Lake Point S */ #define MEI_DEV_ID_MTL_M 0x7E70 /* Meteor Lake Point M */ +#define MEI_DEV_ID_ARL_S 0x7F68 /* Arrow Lake Point S */ +#define MEI_DEV_ID_ARL_H 0x7770 /* Arrow Lake Point H */ /* * MEI HW Section diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index f2765d6b8..2809338a5 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -115,9 +115,11 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_ADP_P, MEI_ME_PCH15_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_ADP_N, MEI_ME_PCH15_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_SPS_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_MTL_M, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ARL_S, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ARL_H, MEI_ME_PCH15_CFG)}, /* required last entry */ {0, } diff --git a/drivers/misc/vmw_vmci/vmci_datagram.c b/drivers/misc/vmw_vmci/vmci_datagram.c index f50d22882..a0ad1f3a6 100644 --- a/drivers/misc/vmw_vmci/vmci_datagram.c +++ b/drivers/misc/vmw_vmci/vmci_datagram.c @@ -234,7 +234,8 @@ static int dg_dispatch_as_host(u32 context_id, struct vmci_datagram *dg) dg_info->in_dg_host_queue = true; dg_info->entry = dst_entry; - memcpy(&dg_info->msg, dg, dg_size); + dg_info->msg = *dg; + memcpy(&dg_info->msg_payload, dg + 1, dg->payload_size); INIT_WORK(&dg_info->work, dg_delayed_dispatch); schedule_work(&dg_info->work); @@ -377,7 +378,8 @@ int vmci_datagram_invoke_guest_handler(struct vmci_datagram *dg) dg_info->in_dg_host_queue = false; dg_info->entry = dst_entry; - memcpy(&dg_info->msg, dg, VMCI_DG_SIZE(dg)); + dg_info->msg = *dg; + memcpy(&dg_info->msg_payload, dg + 1, dg->payload_size); INIT_WORK(&dg_info->work, dg_delayed_dispatch); schedule_work(&dg_info->work); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 8d842ff24..71ecdb134 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -346,6 +346,10 @@ struct mmc_blk_ioc_data { struct mmc_ioc_cmd ic; unsigned char *buf; u64 buf_bytes; + unsigned int flags; +#define MMC_BLK_IOC_DROP BIT(0) /* drop this mrq */ +#define MMC_BLK_IOC_SBC BIT(1) /* use mrq.sbc */ + struct mmc_rpmb_data *rpmb; }; @@ -355,7 +359,7 @@ static struct mmc_blk_ioc_data *mmc_blk_ioctl_copy_from_user( struct mmc_blk_ioc_data *idata; int err; - idata = kmalloc(sizeof(*idata), GFP_KERNEL); + idata = kzalloc(sizeof(*idata), GFP_KERNEL); if (!idata) { err = -ENOMEM; goto out; @@ -447,7 +451,7 @@ static int card_busy_detect(struct mmc_card *card, unsigned int timeout_ms, } static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, - struct mmc_blk_ioc_data *idata) + struct mmc_blk_ioc_data **idatas, int i) { struct mmc_command cmd = {}, sbc = {}; struct mmc_data data = {}; @@ -455,10 +459,18 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, struct scatterlist sg; int err; unsigned int target_part; + struct mmc_blk_ioc_data *idata = idatas[i]; + struct mmc_blk_ioc_data *prev_idata = NULL; if (!card || !md || !idata) return -EINVAL; + if (idata->flags & MMC_BLK_IOC_DROP) + return 0; + + if (idata->flags & MMC_BLK_IOC_SBC && i > 0) + prev_idata = idatas[i - 1]; + /* * The RPMB accesses comes in from the character device, so we * need to target these explicitly. Else we just target the @@ -525,7 +537,7 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, return err; } - if (idata->rpmb) { + if (idata->rpmb || prev_idata) { sbc.opcode = MMC_SET_BLOCK_COUNT; /* * We don't do any blockcount validation because the max size @@ -533,6 +545,8 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, * 'Reliable Write' bit here. */ sbc.arg = data.blocks | (idata->ic.write_flag & BIT(31)); + if (prev_idata) + sbc.arg = prev_idata->ic.arg; sbc.flags = MMC_RSP_R1 | MMC_CMD_AC; mrq.sbc = &sbc; } @@ -544,6 +558,15 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, mmc_wait_for_req(card->host, &mrq); memcpy(&idata->ic.response, cmd.resp, sizeof(cmd.resp)); + if (prev_idata) { + memcpy(&prev_idata->ic.response, sbc.resp, sizeof(sbc.resp)); + if (sbc.error) { + dev_err(mmc_dev(card->host), "%s: sbc error %d\n", + __func__, sbc.error); + return sbc.error; + } + } + if (cmd.error) { dev_err(mmc_dev(card->host), "%s: cmd error %d\n", __func__, cmd.error); @@ -800,10 +823,11 @@ static const struct block_device_operations mmc_bdops = { static int mmc_blk_part_switch_pre(struct mmc_card *card, unsigned int part_type) { - const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_MASK; + const unsigned int rpmb = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if ((part_type & mask) == mask) { + if ((part_type & mask) == rpmb) { if (card->ext_csd.cmdq_en) { ret = mmc_cmdq_disable(card); if (ret) @@ -818,10 +842,11 @@ static int mmc_blk_part_switch_pre(struct mmc_card *card, static int mmc_blk_part_switch_post(struct mmc_card *card, unsigned int part_type) { - const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_MASK; + const unsigned int rpmb = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if ((part_type & mask) == mask) { + if ((part_type & mask) == rpmb) { mmc_retune_unpause(card->host); if (card->reenable_cmdq && !card->ext_csd.cmdq_en) ret = mmc_cmdq_enable(card); @@ -985,6 +1010,20 @@ static inline void mmc_blk_reset_success(struct mmc_blk_data *md, int type) md->reset_done &= ~type; } +static void mmc_blk_check_sbc(struct mmc_queue_req *mq_rq) +{ + struct mmc_blk_ioc_data **idata = mq_rq->drv_op_data; + int i; + + for (i = 1; i < mq_rq->ioc_count; i++) { + if (idata[i - 1]->ic.opcode == MMC_SET_BLOCK_COUNT && + mmc_op_multi(idata[i]->ic.opcode)) { + idata[i - 1]->flags |= MMC_BLK_IOC_DROP; + idata[i]->flags |= MMC_BLK_IOC_SBC; + } + } +} + /* * The non-block commands come back from the block layer after it queued it and * processed it with all other requests and then they get issued in this @@ -1012,11 +1051,14 @@ static void mmc_blk_issue_drv_op(struct mmc_queue *mq, struct request *req) if (ret) break; } + + mmc_blk_check_sbc(mq_rq); + fallthrough; case MMC_DRV_OP_IOCTL_RPMB: idata = mq_rq->drv_op_data; for (i = 0, ret = 0; i < mq_rq->ioc_count; i++) { - ret = __mmc_blk_ioctl_cmd(card, md, idata[i]); + ret = __mmc_blk_ioctl_cmd(card, md, idata, i); if (ret) break; } diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 87807ef01..2059cd226 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -997,10 +997,12 @@ static int mmc_select_bus_width(struct mmc_card *card) static unsigned ext_csd_bits[] = { EXT_CSD_BUS_WIDTH_8, EXT_CSD_BUS_WIDTH_4, + EXT_CSD_BUS_WIDTH_1, }; static unsigned bus_widths[] = { MMC_BUS_WIDTH_8, MMC_BUS_WIDTH_4, + MMC_BUS_WIDTH_1, }; struct mmc_host *host = card->host; unsigned idx, bus_width = 0; diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c index 05e907451..681653d09 100644 --- a/drivers/mmc/core/slot-gpio.c +++ b/drivers/mmc/core/slot-gpio.c @@ -62,11 +62,15 @@ int mmc_gpio_alloc(struct mmc_host *host) int mmc_gpio_get_ro(struct mmc_host *host) { struct mmc_gpio *ctx = host->slot.handler_priv; + int cansleep; if (!ctx || !ctx->ro_gpio) return -ENOSYS; - return gpiod_get_value_cansleep(ctx->ro_gpio); + cansleep = gpiod_cansleep(ctx->ro_gpio); + return cansleep ? + gpiod_get_value_cansleep(ctx->ro_gpio) : + gpiod_get_value(ctx->ro_gpio); } EXPORT_SYMBOL(mmc_gpio_get_ro); diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c index 1d814919e..a1fb5d0e9 100644 --- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -15,7 +15,7 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/bio.h> -#include <linux/dma-mapping.h> +#include <linux/dma-direction.h> #include <linux/crc7.h> #include <linux/crc-itu-t.h> #include <linux/scatterlist.h> @@ -119,19 +119,14 @@ struct mmc_spi_host { struct spi_transfer status; struct spi_message readback; - /* underlying DMA-aware controller, or null */ - struct device *dma_dev; - /* buffer used for commands and for message "overhead" */ struct scratch *data; - dma_addr_t data_dma; /* Specs say to write ones most of the time, even when the card * has no need to read its input data; and many cards won't care. * This is our source of those ones. */ void *ones; - dma_addr_t ones_dma; }; @@ -147,11 +142,8 @@ static inline int mmc_cs_off(struct mmc_spi_host *host) return spi_setup(host->spi); } -static int -mmc_spi_readbytes(struct mmc_spi_host *host, unsigned len) +static int mmc_spi_readbytes(struct mmc_spi_host *host, unsigned int len) { - int status; - if (len > sizeof(*host->data)) { WARN_ON(1); return -EIO; @@ -159,19 +151,7 @@ mmc_spi_readbytes(struct mmc_spi_host *host, unsigned len) host->status.len = len; - if (host->dma_dev) - dma_sync_single_for_device(host->dma_dev, - host->data_dma, sizeof(*host->data), - DMA_FROM_DEVICE); - - status = spi_sync_locked(host->spi, &host->readback); - - if (host->dma_dev) - dma_sync_single_for_cpu(host->dma_dev, - host->data_dma, sizeof(*host->data), - DMA_FROM_DEVICE); - - return status; + return spi_sync_locked(host->spi, &host->readback); } static int mmc_spi_skip(struct mmc_spi_host *host, unsigned long timeout, @@ -513,23 +493,11 @@ mmc_spi_command_send(struct mmc_spi_host *host, t = &host->t; memset(t, 0, sizeof(*t)); t->tx_buf = t->rx_buf = data->status; - t->tx_dma = t->rx_dma = host->data_dma; t->len = cp - data->status; t->cs_change = 1; spi_message_add_tail(t, &host->m); - if (host->dma_dev) { - host->m.is_dma_mapped = 1; - dma_sync_single_for_device(host->dma_dev, - host->data_dma, sizeof(*host->data), - DMA_BIDIRECTIONAL); - } status = spi_sync_locked(host->spi, &host->m); - - if (host->dma_dev) - dma_sync_single_for_cpu(host->dma_dev, - host->data_dma, sizeof(*host->data), - DMA_BIDIRECTIONAL); if (status < 0) { dev_dbg(&host->spi->dev, " ... write returned %d\n", status); cmd->error = status; @@ -547,9 +515,6 @@ mmc_spi_command_send(struct mmc_spi_host *host, * We always provide TX data for data and CRC. The MMC/SD protocol * requires us to write ones; but Linux defaults to writing zeroes; * so we explicitly initialize it to all ones on RX paths. - * - * We also handle DMA mapping, so the underlying SPI controller does - * not need to (re)do it for each message. */ static void mmc_spi_setup_data_message( @@ -559,11 +524,8 @@ mmc_spi_setup_data_message( { struct spi_transfer *t; struct scratch *scratch = host->data; - dma_addr_t dma = host->data_dma; spi_message_init(&host->m); - if (dma) - host->m.is_dma_mapped = 1; /* for reads, readblock() skips 0xff bytes before finding * the token; for writes, this transfer issues that token. @@ -577,8 +539,6 @@ mmc_spi_setup_data_message( else scratch->data_token = SPI_TOKEN_SINGLE; t->tx_buf = &scratch->data_token; - if (dma) - t->tx_dma = dma + offsetof(struct scratch, data_token); spi_message_add_tail(t, &host->m); } @@ -588,7 +548,6 @@ mmc_spi_setup_data_message( t = &host->t; memset(t, 0, sizeof(*t)); t->tx_buf = host->ones; - t->tx_dma = host->ones_dma; /* length and actual buffer info are written later */ spi_message_add_tail(t, &host->m); @@ -598,14 +557,9 @@ mmc_spi_setup_data_message( if (direction == DMA_TO_DEVICE) { /* the actual CRC may get written later */ t->tx_buf = &scratch->crc_val; - if (dma) - t->tx_dma = dma + offsetof(struct scratch, crc_val); } else { t->tx_buf = host->ones; - t->tx_dma = host->ones_dma; t->rx_buf = &scratch->crc_val; - if (dma) - t->rx_dma = dma + offsetof(struct scratch, crc_val); } spi_message_add_tail(t, &host->m); @@ -628,10 +582,7 @@ mmc_spi_setup_data_message( memset(t, 0, sizeof(*t)); t->len = (direction == DMA_TO_DEVICE) ? sizeof(scratch->status) : 1; t->tx_buf = host->ones; - t->tx_dma = host->ones_dma; t->rx_buf = scratch->status; - if (dma) - t->rx_dma = dma + offsetof(struct scratch, status); t->cs_change = 1; spi_message_add_tail(t, &host->m); } @@ -660,23 +611,13 @@ mmc_spi_writeblock(struct mmc_spi_host *host, struct spi_transfer *t, if (host->mmc->use_spi_crc) scratch->crc_val = cpu_to_be16(crc_itu_t(0, t->tx_buf, t->len)); - if (host->dma_dev) - dma_sync_single_for_device(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); status = spi_sync_locked(spi, &host->m); - if (status != 0) { dev_dbg(&spi->dev, "write error (%d)\n", status); return status; } - if (host->dma_dev) - dma_sync_single_for_cpu(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); - /* * Get the transmission data-response reply. It must follow * immediately after the data block we transferred. This reply @@ -725,8 +666,6 @@ mmc_spi_writeblock(struct mmc_spi_host *host, struct spi_transfer *t, } t->tx_buf += t->len; - if (host->dma_dev) - t->tx_dma += t->len; /* Return when not busy. If we didn't collect that status yet, * we'll need some more I/O. @@ -790,30 +729,12 @@ mmc_spi_readblock(struct mmc_spi_host *host, struct spi_transfer *t, } leftover = status << 1; - if (host->dma_dev) { - dma_sync_single_for_device(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); - dma_sync_single_for_device(host->dma_dev, - t->rx_dma, t->len, - DMA_FROM_DEVICE); - } - status = spi_sync_locked(spi, &host->m); if (status < 0) { dev_dbg(&spi->dev, "read error %d\n", status); return status; } - if (host->dma_dev) { - dma_sync_single_for_cpu(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); - dma_sync_single_for_cpu(host->dma_dev, - t->rx_dma, t->len, - DMA_FROM_DEVICE); - } - if (bitshift) { /* Walk through the data and the crc and do * all the magic to get byte-aligned data. @@ -848,8 +769,6 @@ mmc_spi_readblock(struct mmc_spi_host *host, struct spi_transfer *t, } t->rx_buf += t->len; - if (host->dma_dev) - t->rx_dma += t->len; return 0; } @@ -864,7 +783,6 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd, struct mmc_data *data, u32 blk_size) { struct spi_device *spi = host->spi; - struct device *dma_dev = host->dma_dev; struct spi_transfer *t; enum dma_data_direction direction; struct scatterlist *sg; @@ -891,31 +809,8 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd, */ for_each_sg(data->sg, sg, data->sg_len, n_sg) { int status = 0; - dma_addr_t dma_addr = 0; void *kmap_addr; unsigned length = sg->length; - enum dma_data_direction dir = direction; - - /* set up dma mapping for controller drivers that might - * use DMA ... though they may fall back to PIO - */ - if (dma_dev) { - /* never invalidate whole *shared* pages ... */ - if ((sg->offset != 0 || length != PAGE_SIZE) - && dir == DMA_FROM_DEVICE) - dir = DMA_BIDIRECTIONAL; - - dma_addr = dma_map_page(dma_dev, sg_page(sg), 0, - PAGE_SIZE, dir); - if (dma_mapping_error(dma_dev, dma_addr)) { - data->error = -EFAULT; - break; - } - if (direction == DMA_TO_DEVICE) - t->tx_dma = dma_addr + sg->offset; - else - t->rx_dma = dma_addr + sg->offset; - } /* allow pio too; we don't allow highmem */ kmap_addr = kmap(sg_page(sg)); @@ -951,8 +846,6 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd, if (direction == DMA_FROM_DEVICE) flush_kernel_dcache_page(sg_page(sg)); kunmap(sg_page(sg)); - if (dma_dev) - dma_unmap_page(dma_dev, dma_addr, PAGE_SIZE, dir); if (status < 0) { data->error = status; @@ -989,21 +882,9 @@ mmc_spi_data_do(struct mmc_spi_host *host, struct mmc_command *cmd, scratch->status[0] = SPI_TOKEN_STOP_TRAN; host->early_status.tx_buf = host->early_status.rx_buf; - host->early_status.tx_dma = host->early_status.rx_dma; host->early_status.len = statlen; - if (host->dma_dev) - dma_sync_single_for_device(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); - tmp = spi_sync_locked(spi, &host->m); - - if (host->dma_dev) - dma_sync_single_for_cpu(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); - if (tmp < 0) { if (!data->error) data->error = tmp; @@ -1278,52 +1159,6 @@ mmc_spi_detect_irq(int irq, void *mmc) return IRQ_HANDLED; } -#ifdef CONFIG_HAS_DMA -static int mmc_spi_dma_alloc(struct mmc_spi_host *host) -{ - struct spi_device *spi = host->spi; - struct device *dev; - - if (!spi->master->dev.parent->dma_mask) - return 0; - - dev = spi->master->dev.parent; - - host->ones_dma = dma_map_single(dev, host->ones, MMC_SPI_BLOCKSIZE, - DMA_TO_DEVICE); - if (dma_mapping_error(dev, host->ones_dma)) - return -ENOMEM; - - host->data_dma = dma_map_single(dev, host->data, sizeof(*host->data), - DMA_BIDIRECTIONAL); - if (dma_mapping_error(dev, host->data_dma)) { - dma_unmap_single(dev, host->ones_dma, MMC_SPI_BLOCKSIZE, - DMA_TO_DEVICE); - return -ENOMEM; - } - - dma_sync_single_for_cpu(dev, host->data_dma, sizeof(*host->data), - DMA_BIDIRECTIONAL); - - host->dma_dev = dev; - return 0; -} - -static void mmc_spi_dma_free(struct mmc_spi_host *host) -{ - if (!host->dma_dev) - return; - - dma_unmap_single(host->dma_dev, host->ones_dma, MMC_SPI_BLOCKSIZE, - DMA_TO_DEVICE); - dma_unmap_single(host->dma_dev, host->data_dma, sizeof(*host->data), - DMA_BIDIRECTIONAL); -} -#else -static inline int mmc_spi_dma_alloc(struct mmc_spi_host *host) { return 0; } -static inline void mmc_spi_dma_free(struct mmc_spi_host *host) {} -#endif - static int mmc_spi_probe(struct spi_device *spi) { void *ones; @@ -1415,24 +1250,17 @@ static int mmc_spi_probe(struct spi_device *spi) dev_set_drvdata(&spi->dev, mmc); - /* preallocate dma buffers */ + /* Preallocate buffers */ host->data = kmalloc(sizeof(*host->data), GFP_KERNEL); if (!host->data) goto fail_nobuf1; - status = mmc_spi_dma_alloc(host); - if (status) - goto fail_dma; - /* setup message for status/busy readback */ spi_message_init(&host->readback); - host->readback.is_dma_mapped = (host->dma_dev != NULL); spi_message_add_tail(&host->status, &host->readback); host->status.tx_buf = host->ones; - host->status.tx_dma = host->ones_dma; host->status.rx_buf = &host->data->status; - host->status.rx_dma = host->data_dma + offsetof(struct scratch, status); host->status.cs_change = 1; /* register card detect irq */ @@ -1477,9 +1305,8 @@ static int mmc_spi_probe(struct spi_device *spi) if (!status) has_ro = true; - dev_info(&spi->dev, "SD/MMC host %s%s%s%s%s\n", + dev_info(&spi->dev, "SD/MMC host %s%s%s%s\n", dev_name(&mmc->class_dev), - host->dma_dev ? "" : ", no DMA", has_ro ? "" : ", no WP", (host->pdata && host->pdata->setpower) ? "" : ", no poweroff", @@ -1490,8 +1317,6 @@ static int mmc_spi_probe(struct spi_device *spi) fail_gpiod_request: mmc_remove_host(mmc); fail_glue_init: - mmc_spi_dma_free(host); -fail_dma: kfree(host->data); fail_nobuf1: mmc_free_host(mmc); @@ -1513,7 +1338,6 @@ static int mmc_spi_remove(struct spi_device *spi) mmc_remove_host(mmc); - mmc_spi_dma_free(host); kfree(host->data); kfree(host->ones); diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c index 4cceb9bab..e3201a621 100644 --- a/drivers/mmc/host/mmci_stm32_sdmmc.c +++ b/drivers/mmc/host/mmci_stm32_sdmmc.c @@ -43,6 +43,9 @@ struct sdmmc_lli_desc { struct sdmmc_idma { dma_addr_t sg_dma; void *sg_cpu; + dma_addr_t bounce_dma_addr; + void *bounce_buf; + bool use_bounce_buffer; }; struct sdmmc_dlyb { @@ -54,6 +57,8 @@ struct sdmmc_dlyb { static int sdmmc_idma_validate_data(struct mmci_host *host, struct mmc_data *data) { + struct sdmmc_idma *idma = host->dma_priv; + struct device *dev = mmc_dev(host->mmc); struct scatterlist *sg; int i; @@ -61,41 +66,69 @@ static int sdmmc_idma_validate_data(struct mmci_host *host, * idma has constraints on idmabase & idmasize for each element * excepted the last element which has no constraint on idmasize */ + idma->use_bounce_buffer = false; for_each_sg(data->sg, sg, data->sg_len - 1, i) { if (!IS_ALIGNED(sg->offset, sizeof(u32)) || !IS_ALIGNED(sg->length, SDMMC_IDMA_BURST)) { - dev_err(mmc_dev(host->mmc), + dev_dbg(mmc_dev(host->mmc), "unaligned scatterlist: ofst:%x length:%d\n", data->sg->offset, data->sg->length); - return -EINVAL; + goto use_bounce_buffer; } } if (!IS_ALIGNED(sg->offset, sizeof(u32))) { - dev_err(mmc_dev(host->mmc), + dev_dbg(mmc_dev(host->mmc), "unaligned last scatterlist: ofst:%x length:%d\n", data->sg->offset, data->sg->length); - return -EINVAL; + goto use_bounce_buffer; } return 0; + +use_bounce_buffer: + if (!idma->bounce_buf) { + idma->bounce_buf = dmam_alloc_coherent(dev, + host->mmc->max_req_size, + &idma->bounce_dma_addr, + GFP_KERNEL); + if (!idma->bounce_buf) { + dev_err(dev, "Unable to map allocate DMA bounce buffer.\n"); + return -ENOMEM; + } + } + + idma->use_bounce_buffer = true; + + return 0; } static int _sdmmc_idma_prep_data(struct mmci_host *host, struct mmc_data *data) { - int n_elem; + struct sdmmc_idma *idma = host->dma_priv; - n_elem = dma_map_sg(mmc_dev(host->mmc), - data->sg, - data->sg_len, - mmc_get_dma_dir(data)); + if (idma->use_bounce_buffer) { + if (data->flags & MMC_DATA_WRITE) { + unsigned int xfer_bytes = data->blksz * data->blocks; - if (!n_elem) { - dev_err(mmc_dev(host->mmc), "dma_map_sg failed\n"); - return -EINVAL; - } + sg_copy_to_buffer(data->sg, data->sg_len, + idma->bounce_buf, xfer_bytes); + dma_wmb(); + } + } else { + int n_elem; + n_elem = dma_map_sg(mmc_dev(host->mmc), + data->sg, + data->sg_len, + mmc_get_dma_dir(data)); + + if (!n_elem) { + dev_err(mmc_dev(host->mmc), "dma_map_sg failed\n"); + return -EINVAL; + } + } return 0; } @@ -112,8 +145,19 @@ static int sdmmc_idma_prep_data(struct mmci_host *host, static void sdmmc_idma_unprep_data(struct mmci_host *host, struct mmc_data *data, int err) { - dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, - mmc_get_dma_dir(data)); + struct sdmmc_idma *idma = host->dma_priv; + + if (idma->use_bounce_buffer) { + if (data->flags & MMC_DATA_READ) { + unsigned int xfer_bytes = data->blksz * data->blocks; + + sg_copy_from_buffer(data->sg, data->sg_len, + idma->bounce_buf, xfer_bytes); + } + } else { + dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, + mmc_get_dma_dir(data)); + } } static int sdmmc_idma_setup(struct mmci_host *host) @@ -137,6 +181,8 @@ static int sdmmc_idma_setup(struct mmci_host *host) host->mmc->max_segs = SDMMC_LLI_BUF_LEN / sizeof(struct sdmmc_lli_desc); host->mmc->max_seg_size = host->variant->stm32_idmabsize_mask; + + host->mmc->max_req_size = SZ_1M; } else { host->mmc->max_segs = 1; host->mmc->max_seg_size = host->mmc->max_req_size; @@ -154,8 +200,18 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl) struct scatterlist *sg; int i; - if (!host->variant->dma_lli || data->sg_len == 1) { - writel_relaxed(sg_dma_address(data->sg), + host->dma_in_progress = true; + + if (!host->variant->dma_lli || data->sg_len == 1 || + idma->use_bounce_buffer) { + u32 dma_addr; + + if (idma->use_bounce_buffer) + dma_addr = idma->bounce_dma_addr; + else + dma_addr = sg_dma_address(data->sg); + + writel_relaxed(dma_addr, host->base + MMCI_STM32_IDMABASE0R); writel_relaxed(MMCI_STM32_IDMAEN, host->base + MMCI_STM32_IDMACTRLR); @@ -184,9 +240,30 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl) return 0; } +static void sdmmc_idma_error(struct mmci_host *host) +{ + struct mmc_data *data = host->data; + struct sdmmc_idma *idma = host->dma_priv; + + if (!dma_inprogress(host)) + return; + + writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR); + host->dma_in_progress = false; + data->host_cookie = 0; + + if (!idma->use_bounce_buffer) + dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, + mmc_get_dma_dir(data)); +} + static void sdmmc_idma_finalize(struct mmci_host *host, struct mmc_data *data) { + if (!dma_inprogress(host)) + return; + writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR); + host->dma_in_progress = false; if (!data->host_cookie) sdmmc_idma_unprep_data(host, data, 0); @@ -512,6 +589,7 @@ static struct mmci_host_ops sdmmc_variant_ops = { .dma_setup = sdmmc_idma_setup, .dma_start = sdmmc_idma_start, .dma_finalize = sdmmc_idma_finalize, + .dma_error = sdmmc_idma_error, .set_clkreg = mmci_sdmmc_set_clkreg, .set_pwrreg = mmci_sdmmc_set_pwrreg, .busy_complete = sdmmc_busy_complete, diff --git a/drivers/mmc/host/sdhci-xenon-phy.c b/drivers/mmc/host/sdhci-xenon-phy.c index 03ce57ef4..53bf9870c 100644 --- a/drivers/mmc/host/sdhci-xenon-phy.c +++ b/drivers/mmc/host/sdhci-xenon-phy.c @@ -11,6 +11,7 @@ #include <linux/slab.h> #include <linux/delay.h> #include <linux/ktime.h> +#include <linux/iopoll.h> #include <linux/of_address.h> #include "sdhci-pltfm.h" @@ -109,6 +110,8 @@ #define XENON_EMMC_PHY_LOGIC_TIMING_ADJUST (XENON_EMMC_PHY_REG_BASE + 0x18) #define XENON_LOGIC_TIMING_VALUE 0x00AA8977 +#define XENON_MAX_PHY_TIMEOUT_LOOPS 100 + /* * List offset of PHY registers and some special register values * in eMMC PHY 5.0 or eMMC PHY 5.1 @@ -216,6 +219,19 @@ static int xenon_alloc_emmc_phy(struct sdhci_host *host) return 0; } +static int xenon_check_stability_internal_clk(struct sdhci_host *host) +{ + u32 reg; + int err; + + err = read_poll_timeout(sdhci_readw, reg, reg & SDHCI_CLOCK_INT_STABLE, + 1100, 20000, false, host, SDHCI_CLOCK_CONTROL); + if (err) + dev_err(mmc_dev(host->mmc), "phy_init: Internal clock never stabilized.\n"); + + return err; +} + /* * eMMC 5.0/5.1 PHY init/re-init. * eMMC PHY init should be executed after: @@ -232,6 +248,11 @@ static int xenon_emmc_phy_init(struct sdhci_host *host) struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host); struct xenon_emmc_phy_regs *phy_regs = priv->emmc_phy_regs; + int ret = xenon_check_stability_internal_clk(host); + + if (ret) + return ret; + reg = sdhci_readl(host, phy_regs->timing_adj); reg |= XENON_PHY_INITIALIZAION; sdhci_writel(host, reg, phy_regs->timing_adj); @@ -259,18 +280,27 @@ static int xenon_emmc_phy_init(struct sdhci_host *host) /* get the wait time */ wait /= clock; wait++; - /* wait for host eMMC PHY init completes */ - udelay(wait); - reg = sdhci_readl(host, phy_regs->timing_adj); - reg &= XENON_PHY_INITIALIZAION; - if (reg) { + /* + * AC5X spec says bit must be polled until zero. + * We see cases in which timeout can take longer + * than the standard calculation on AC5X, which is + * expected following the spec comment above. + * According to the spec, we must wait as long as + * it takes for that bit to toggle on AC5X. + * Cap that with 100 delay loops so we won't get + * stuck here forever: + */ + + ret = read_poll_timeout(sdhci_readl, reg, + !(reg & XENON_PHY_INITIALIZAION), + wait, XENON_MAX_PHY_TIMEOUT_LOOPS * wait, + false, host, phy_regs->timing_adj); + if (ret) dev_err(mmc_dev(host->mmc), "eMMC PHY init cannot complete after %d us\n", - wait); - return -ETIMEDOUT; - } + wait * XENON_MAX_PHY_TIMEOUT_LOOPS); - return 0; + return ret; } #define ARMADA_3700_SOC_PAD_1_8V 0x1 diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index abf36acb2..0482920a7 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -216,6 +216,8 @@ static void tmio_mmc_reset_work(struct work_struct *work) else mrq->cmd->error = -ETIMEDOUT; + /* No new calls yet, but disallow concurrent tmio_mmc_done_work() */ + host->mrq = ERR_PTR(-EBUSY); host->cmd = NULL; host->data = NULL; diff --git a/drivers/mmc/host/wmt-sdmmc.c b/drivers/mmc/host/wmt-sdmmc.c index 393319548..3fcc81e48 100644 --- a/drivers/mmc/host/wmt-sdmmc.c +++ b/drivers/mmc/host/wmt-sdmmc.c @@ -889,7 +889,6 @@ static int wmt_mci_remove(struct platform_device *pdev) { struct mmc_host *mmc; struct wmt_mci_priv *priv; - struct resource *res; u32 reg_tmp; mmc = platform_get_drvdata(pdev); @@ -917,9 +916,6 @@ static int wmt_mci_remove(struct platform_device *pdev) clk_disable_unprepare(priv->clk_sdmmc); clk_put(priv->clk_sdmmc); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - release_mem_region(res->start, resource_size(res)); - mmc_free_host(mmc); dev_info(&pdev->dev, "WMT MCI device removed\n"); diff --git a/drivers/mtd/maps/physmap-core.c b/drivers/mtd/maps/physmap-core.c index 9ab795f03..e55520935 100644 --- a/drivers/mtd/maps/physmap-core.c +++ b/drivers/mtd/maps/physmap-core.c @@ -528,7 +528,7 @@ static int physmap_flash_probe(struct platform_device *dev) if (!info->maps[i].phys) info->maps[i].phys = res->start; - info->win_order = get_bitmask_order(resource_size(res)) - 1; + info->win_order = fls64(resource_size(res)) - 1; info->maps[i].size = BIT(info->win_order + (info->gpios ? info->gpios->ndescs : 0)); diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c index 26b265e43..9ee7daa6f 100644 --- a/drivers/mtd/nand/raw/diskonchip.c +++ b/drivers/mtd/nand/raw/diskonchip.c @@ -53,7 +53,7 @@ static unsigned long doc_locations[] __initdata = { 0xe8000, 0xea000, 0xec000, 0xee000, #endif #endif - 0xffffffff }; +}; static struct mtd_info *doclist = NULL; @@ -1552,7 +1552,7 @@ static int __init init_nanddoc(void) if (ret < 0) return ret; } else { - for (i = 0; (doc_locations[i] != 0xffffffff); i++) { + for (i = 0; i < ARRAY_SIZE(doc_locations); i++) { doc_probe(doc_locations[i]); } } diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c index 9e728c731..db228460a 100644 --- a/drivers/mtd/nand/raw/lpc32xx_mlc.c +++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c @@ -304,8 +304,9 @@ static int lpc32xx_nand_device_ready(struct nand_chip *nand_chip) return 0; } -static irqreturn_t lpc3xxx_nand_irq(int irq, struct lpc32xx_nand_host *host) +static irqreturn_t lpc3xxx_nand_irq(int irq, void *data) { + struct lpc32xx_nand_host *host = data; uint8_t sr; /* Clear interrupt flag by reading status */ @@ -780,7 +781,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev) goto release_dma_chan; } - if (request_irq(host->irq, (irq_handler_t)&lpc3xxx_nand_irq, + if (request_irq(host->irq, &lpc3xxx_nand_irq, IRQF_TRIGGER_HIGH, DRV_NAME, host)) { dev_err(&pdev->dev, "Error requesting NAND IRQ\n"); res = -ENXIO; diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index 6bb0fca4a..9a64190f3 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -59,7 +59,7 @@ #define CMDRWGEN(cmd_dir, ran, bch, short_mode, page_size, pages) \ ( \ (cmd_dir) | \ - ((ran) << 19) | \ + (ran) | \ ((bch) << 14) | \ ((short_mode) << 13) | \ (((page_size) & 0x7f) << 6) | \ diff --git a/drivers/mtd/nand/spi/gigadevice.c b/drivers/mtd/nand/spi/gigadevice.c index 33c67403c..56d1b5661 100644 --- a/drivers/mtd/nand/spi/gigadevice.c +++ b/drivers/mtd/nand/spi/gigadevice.c @@ -13,7 +13,10 @@ #define GD5FXGQ4XA_STATUS_ECC_1_7_BITFLIPS (1 << 4) #define GD5FXGQ4XA_STATUS_ECC_8_BITFLIPS (3 << 4) -#define GD5FXGQ4UEXXG_REG_STATUS2 0xf0 +#define GD5FXGQ5XE_STATUS_ECC_1_4_BITFLIPS (1 << 4) +#define GD5FXGQ5XE_STATUS_ECC_4_BITFLIPS (3 << 4) + +#define GD5FXGQXXEXXG_REG_STATUS2 0xf0 #define GD5FXGQ4UXFXXG_STATUS_ECC_MASK (7 << 4) #define GD5FXGQ4UXFXXG_STATUS_ECC_NO_BITFLIPS (0 << 4) @@ -36,6 +39,14 @@ static SPINAND_OP_VARIANTS(read_cache_variants_f, SPINAND_PAGE_READ_FROM_CACHE_OP_3A(true, 0, 1, NULL, 0), SPINAND_PAGE_READ_FROM_CACHE_OP_3A(false, 0, 0, NULL, 0)); +static SPINAND_OP_VARIANTS(read_cache_variants_1gq5, + SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + static SPINAND_OP_VARIANTS(write_cache_variants, SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), SPINAND_PROG_LOAD(true, 0, NULL, 0)); @@ -102,7 +113,7 @@ static int gd5fxgq4xa_ecc_get_status(struct spinand_device *spinand, return -EINVAL; } -static int gd5fxgq4_variant2_ooblayout_ecc(struct mtd_info *mtd, int section, +static int gd5fxgqx_variant2_ooblayout_ecc(struct mtd_info *mtd, int section, struct mtd_oob_region *region) { if (section) @@ -114,7 +125,7 @@ static int gd5fxgq4_variant2_ooblayout_ecc(struct mtd_info *mtd, int section, return 0; } -static int gd5fxgq4_variant2_ooblayout_free(struct mtd_info *mtd, int section, +static int gd5fxgqx_variant2_ooblayout_free(struct mtd_info *mtd, int section, struct mtd_oob_region *region) { if (section) @@ -127,9 +138,10 @@ static int gd5fxgq4_variant2_ooblayout_free(struct mtd_info *mtd, int section, return 0; } -static const struct mtd_ooblayout_ops gd5fxgq4_variant2_ooblayout = { - .ecc = gd5fxgq4_variant2_ooblayout_ecc, - .free = gd5fxgq4_variant2_ooblayout_free, +/* Valid for Q4/Q5 and Q6 (untested) devices */ +static const struct mtd_ooblayout_ops gd5fxgqx_variant2_ooblayout = { + .ecc = gd5fxgqx_variant2_ooblayout_ecc, + .free = gd5fxgqx_variant2_ooblayout_free, }; static int gd5fxgq4xc_ooblayout_256_ecc(struct mtd_info *mtd, int section, @@ -165,8 +177,8 @@ static int gd5fxgq4uexxg_ecc_get_status(struct spinand_device *spinand, u8 status) { u8 status2; - struct spi_mem_op op = SPINAND_GET_FEATURE_OP(GD5FXGQ4UEXXG_REG_STATUS2, - &status2); + struct spi_mem_op op = SPINAND_GET_FEATURE_OP(GD5FXGQXXEXXG_REG_STATUS2, + spinand->scratchbuf); int ret; switch (status & STATUS_ECC_MASK) { @@ -187,6 +199,7 @@ static int gd5fxgq4uexxg_ecc_get_status(struct spinand_device *spinand, * report the maximum of 4 in this case */ /* bits sorted this way (3...0): ECCS1,ECCS0,ECCSE1,ECCSE0 */ + status2 = *(spinand->scratchbuf); return ((status & STATUS_ECC_MASK) >> 2) | ((status2 & STATUS_ECC_MASK) >> 4); @@ -203,6 +216,44 @@ static int gd5fxgq4uexxg_ecc_get_status(struct spinand_device *spinand, return -EINVAL; } +static int gd5fxgq5xexxg_ecc_get_status(struct spinand_device *spinand, + u8 status) +{ + u8 status2; + struct spi_mem_op op = SPINAND_GET_FEATURE_OP(GD5FXGQXXEXXG_REG_STATUS2, + spinand->scratchbuf); + int ret; + + switch (status & STATUS_ECC_MASK) { + case STATUS_ECC_NO_BITFLIPS: + return 0; + + case GD5FXGQ5XE_STATUS_ECC_1_4_BITFLIPS: + /* + * Read status2 register to determine a more fine grained + * bit error status + */ + ret = spi_mem_exec_op(spinand->spimem, &op); + if (ret) + return ret; + + /* + * 1 ... 4 bits are flipped (and corrected) + */ + /* bits sorted this way (1...0): ECCSE1, ECCSE0 */ + status2 = *(spinand->scratchbuf); + return ((status2 & STATUS_ECC_MASK) >> 4) + 1; + + case STATUS_ECC_UNCOR_ERROR: + return -EBADMSG; + + default: + break; + } + + return -EINVAL; +} + static int gd5fxgq4ufxxg_ecc_get_status(struct spinand_device *spinand, u8 status) { @@ -282,7 +333,7 @@ static const struct spinand_info gigadevice_spinand_table[] = { &write_cache_variants, &update_cache_variants), SPINAND_HAS_QE_BIT, - SPINAND_ECCINFO(&gd5fxgq4_variant2_ooblayout, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, gd5fxgq4uexxg_ecc_get_status)), SPINAND_INFO("GD5F1GQ4UFxxG", SPINAND_ID(SPINAND_READID_METHOD_OPCODE, 0xb1, 0x48), @@ -292,8 +343,18 @@ static const struct spinand_info gigadevice_spinand_table[] = { &write_cache_variants, &update_cache_variants), SPINAND_HAS_QE_BIT, - SPINAND_ECCINFO(&gd5fxgq4_variant2_ooblayout, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, gd5fxgq4ufxxg_ecc_get_status)), + SPINAND_INFO("GD5F1GQ5UExxG", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x51), + NAND_MEMORG(1, 2048, 128, 64, 1024, 20, 1, 1, 1), + NAND_ECCREQ(4, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants_1gq5, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&gd5fxgqx_variant2_ooblayout, + gd5fxgq5xexxg_ecc_get_status)), }; static const struct spinand_manufacturer_ops gigadevice_spinand_manuf_ops = { diff --git a/drivers/mtd/nand/spi/macronix.c b/drivers/mtd/nand/spi/macronix.c index cd7a9cacc..8bd3f6bf9 100644 --- a/drivers/mtd/nand/spi/macronix.c +++ b/drivers/mtd/nand/spi/macronix.c @@ -119,6 +119,26 @@ static const struct spinand_info macronix_spinand_table[] = { &update_cache_variants), SPINAND_HAS_QE_BIT, SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, NULL)), + SPINAND_INFO("MX35LF2GE4AD", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x26), + NAND_MEMORG(1, 2048, 64, 64, 2048, 40, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + 0, + SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, + mx35lf1ge4ab_ecc_get_status)), + SPINAND_INFO("MX35LF4GE4AD", + SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x37), + NAND_MEMORG(1, 4096, 128, 64, 2048, 40, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + 0, + SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, + mx35lf1ge4ab_ecc_get_status)), SPINAND_INFO("MX31LF1GE4BC", SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0x1e), NAND_MEMORG(1, 2048, 64, 64, 1024, 20, 1, 1, 1), diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c index 6e95c4b14..8081fc760 100644 --- a/drivers/mtd/ubi/fastmap.c +++ b/drivers/mtd/ubi/fastmap.c @@ -86,9 +86,10 @@ size_t ubi_calc_fm_size(struct ubi_device *ubi) sizeof(struct ubi_fm_scan_pool) + sizeof(struct ubi_fm_scan_pool) + (ubi->peb_count * sizeof(struct ubi_fm_ec)) + - (sizeof(struct ubi_fm_eba) + - (ubi->peb_count * sizeof(__be32))) + - sizeof(struct ubi_fm_volhdr) * UBI_MAX_VOLUMES; + ((sizeof(struct ubi_fm_eba) + + sizeof(struct ubi_fm_volhdr)) * + (UBI_MAX_VOLUMES + UBI_INT_VOL_COUNT)) + + (ubi->peb_count * sizeof(__be32)); return roundup(size, ubi->leb_size); } diff --git a/drivers/mtd/ubi/vtbl.c b/drivers/mtd/ubi/vtbl.c index f700f0e4f..6e5489e23 100644 --- a/drivers/mtd/ubi/vtbl.c +++ b/drivers/mtd/ubi/vtbl.c @@ -791,6 +791,12 @@ int ubi_read_volume_table(struct ubi_device *ubi, struct ubi_attach_info *ai) * The number of supported volumes is limited by the eraseblock size * and by the UBI_MAX_VOLUMES constant. */ + + if (ubi->leb_size < UBI_VTBL_RECORD_SIZE) { + ubi_err(ubi, "LEB size too small for a volume record"); + return -EINVAL; + } + ubi->vtbl_slots = ubi->leb_size / UBI_VTBL_RECORD_SIZE; if (ubi->vtbl_slots > UBI_MAX_VOLUMES) ubi->vtbl_slots = UBI_MAX_VOLUMES; diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 64ba46574..81a5e7622 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -971,7 +971,8 @@ static int alb_upper_dev_walk(struct net_device *upper, if (netif_is_macvlan(upper) && !strict_match) { tags = bond_verify_device_path(bond->dev, upper, 0); if (IS_ERR_OR_NULL(tags)) - BUG(); + return -ENOMEM; + alb_send_lp_vid(slave, upper->dev_addr, tags[0].vlan_proto, tags[0].vlan_id); kfree(tags); diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 4056ca425..0fbed76bb 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1581,11 +1581,11 @@ mt7530_setup(struct dsa_switch *ds) */ if (priv->mcm) { reset_control_assert(priv->rstc); - usleep_range(1000, 1100); + usleep_range(5000, 5100); reset_control_deassert(priv->rstc); } else { gpiod_set_value_cansleep(priv->reset, 0); - usleep_range(1000, 1100); + usleep_range(5000, 5100); gpiod_set_value_cansleep(priv->reset, 1); } @@ -1704,11 +1704,11 @@ mt7531_setup(struct dsa_switch *ds) */ if (priv->mcm) { reset_control_assert(priv->rstc); - usleep_range(1000, 1100); + usleep_range(5000, 5100); reset_control_deassert(priv->rstc); } else { gpiod_set_value_cansleep(priv->reset, 0); - usleep_range(1000, 1100); + usleep_range(5000, 5100); gpiod_set_value_cansleep(priv->reset, 1); } diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 51a7ff444..67e52c481 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -536,8 +536,8 @@ struct mv88e6xxx_ops { int (*serdes_get_sset_count)(struct mv88e6xxx_chip *chip, int port); int (*serdes_get_strings)(struct mv88e6xxx_chip *chip, int port, uint8_t *data); - int (*serdes_get_stats)(struct mv88e6xxx_chip *chip, int port, - uint64_t *data); + size_t (*serdes_get_stats)(struct mv88e6xxx_chip *chip, int port, + uint64_t *data); /* SERDES registers for ethtool */ int (*serdes_get_regs_len)(struct mv88e6xxx_chip *chip, int port); diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index 6920e62c8..9494d75ee 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -314,8 +314,8 @@ static uint64_t mv88e6352_serdes_get_stat(struct mv88e6xxx_chip *chip, return val; } -int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, - uint64_t *data) +size_t mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, + uint64_t *data) { struct mv88e6xxx_port *mv88e6xxx_port = &chip->ports[port]; struct mv88e6352_serdes_hw_stat *stat; @@ -631,8 +631,8 @@ static uint64_t mv88e6390_serdes_get_stat(struct mv88e6xxx_chip *chip, int lane, return reg[0] | ((u64)reg[1] << 16) | ((u64)reg[2] << 32); } -int mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, - uint64_t *data) +size_t mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, + uint64_t *data) { struct mv88e6390_serdes_hw_stat *stat; int lane; diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h index 14315f262..035688659 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.h +++ b/drivers/net/dsa/mv88e6xxx/serdes.h @@ -116,13 +116,13 @@ irqreturn_t mv88e6390_serdes_irq_status(struct mv88e6xxx_chip *chip, int port, int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port); int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip, int port, uint8_t *data); -int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, - uint64_t *data); +size_t mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, + uint64_t *data); int mv88e6390_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port); int mv88e6390_serdes_get_strings(struct mv88e6xxx_chip *chip, int port, uint8_t *data); -int mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, - uint64_t *data); +size_t mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, + uint64_t *data); int mv88e6352_serdes_get_regs_len(struct mv88e6xxx_chip *chip, int port); void mv88e6352_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p); diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index d59ea5148..60645ea7c 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -352,7 +352,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev, ENA_COM_BOUNCE_BUFFER_CNTRL_CNT; io_sq->bounce_buf_ctrl.next_to_use = 0; - size = io_sq->bounce_buf_ctrl.buffer_size * + size = (size_t)io_sq->bounce_buf_ctrl.buffer_size * io_sq->bounce_buf_ctrl.buffers_num; dev_node = dev_to_node(ena_dev->dmadev); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index e13ae04d2..9149c82c0 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1105,8 +1105,11 @@ static void ena_unmap_tx_buff(struct ena_ring *tx_ring, static void ena_free_tx_bufs(struct ena_ring *tx_ring) { bool print_once = true; + bool is_xdp_ring; u32 i; + is_xdp_ring = ENA_IS_XDP_INDEX(tx_ring->adapter, tx_ring->qid); + for (i = 0; i < tx_ring->ring_size; i++) { struct ena_tx_buffer *tx_info = &tx_ring->tx_buffer_info[i]; @@ -1126,10 +1129,15 @@ static void ena_free_tx_bufs(struct ena_ring *tx_ring) ena_unmap_tx_buff(tx_ring, tx_info); - dev_kfree_skb_any(tx_info->skb); + if (is_xdp_ring) + xdp_return_frame(tx_info->xdpf); + else + dev_kfree_skb_any(tx_info->skb); } - netdev_tx_reset_queue(netdev_get_tx_queue(tx_ring->netdev, - tx_ring->qid)); + + if (!is_xdp_ring) + netdev_tx_reset_queue(netdev_get_tx_queue(tx_ring->netdev, + tx_ring->qid)); } static void ena_free_all_tx_bufs(struct ena_adapter *adapter) @@ -3057,22 +3065,6 @@ error_drop_packet: return NETDEV_TX_OK; } -static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev) -{ - u16 qid; - /* we suspect that this is good for in--kernel network services that - * want to loop incoming skb rx to tx in normal user generated traffic, - * most probably we will not get to this - */ - if (skb_rx_queue_recorded(skb)) - qid = skb_get_rx_queue(skb); - else - qid = netdev_pick_tx(dev, skb, NULL); - - return qid; -} - static void ena_config_host_info(struct ena_com_dev *ena_dev, struct pci_dev *pdev) { struct device *dev = &pdev->dev; @@ -3242,7 +3234,6 @@ static const struct net_device_ops ena_netdev_ops = { .ndo_open = ena_open, .ndo_stop = ena_close, .ndo_start_xmit = ena_start_xmit, - .ndo_select_queue = ena_select_queue, .ndo_get_stats64 = ena_get_stats64, .ndo_tx_timeout = ena_tx_timeout, .ndo_change_mtu = ena_change_mtu, @@ -3689,10 +3680,11 @@ static void check_for_missing_completions(struct ena_adapter *adapter) { struct ena_ring *tx_ring; struct ena_ring *rx_ring; - int i, budget, rc; + int qid, budget, rc; int io_queue_count; io_queue_count = adapter->xdp_num_queues + adapter->num_io_queues; + /* Make sure the driver doesn't turn the device in other process */ smp_rmb(); @@ -3705,27 +3697,29 @@ static void check_for_missing_completions(struct ena_adapter *adapter) if (adapter->missing_tx_completion_to == ENA_HW_HINTS_NO_TIMEOUT) return; - budget = ENA_MONITORED_TX_QUEUES; + budget = min_t(u32, io_queue_count, ENA_MONITORED_TX_QUEUES); - for (i = adapter->last_monitored_tx_qid; i < io_queue_count; i++) { - tx_ring = &adapter->tx_ring[i]; - rx_ring = &adapter->rx_ring[i]; + qid = adapter->last_monitored_tx_qid; + + while (budget) { + qid = (qid + 1) % io_queue_count; + + tx_ring = &adapter->tx_ring[qid]; + rx_ring = &adapter->rx_ring[qid]; rc = check_missing_comp_in_tx_queue(adapter, tx_ring); if (unlikely(rc)) return; - rc = !ENA_IS_XDP_INDEX(adapter, i) ? + rc = !ENA_IS_XDP_INDEX(adapter, qid) ? check_for_rx_interrupt_queue(adapter, rx_ring) : 0; if (unlikely(rc)) return; budget--; - if (!budget) - break; } - adapter->last_monitored_tx_qid = i % io_queue_count; + adapter->last_monitored_tx_qid = qid; } /* trigger napi schedule after 2 consecutive detections */ diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index b455b60a5..7ad9a4715 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -2027,12 +2027,14 @@ static int b44_set_pauseparam(struct net_device *dev, bp->flags |= B44_FLAG_TX_PAUSE; else bp->flags &= ~B44_FLAG_TX_PAUSE; - if (bp->flags & B44_FLAG_PAUSE_AUTO) { - b44_halt(bp); - b44_init_rings(bp); - b44_init_hw(bp, B44_FULL_RESET); - } else { - __b44_set_flow_ctrl(bp, bp->flags); + if (netif_running(dev)) { + if (bp->flags & B44_FLAG_PAUSE_AUTO) { + b44_halt(bp); + b44_init_rings(bp); + b44_init_hw(bp, B44_FULL_RESET); + } else { + __b44_set_flow_ctrl(bp, bp->flags); + } } spin_unlock_irq(&bp->lock); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index d8b1824c3..0bc1367fd 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -1002,9 +1002,6 @@ static inline void bnx2x_set_fw_mac_addr(__le16 *fw_hi, __le16 *fw_mid, static inline void bnx2x_free_rx_mem_pool(struct bnx2x *bp, struct bnx2x_alloc_pool *pool) { - if (!pool->page) - return; - put_page(pool->page); pool->page = NULL; @@ -1015,6 +1012,9 @@ static inline void bnx2x_free_rx_sge_range(struct bnx2x *bp, { int i; + if (!fp->page_pool.page) + return; + if (fp->mode == TPA_MODE_DISABLED) return; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 584f365de..059552f41 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11331,6 +11331,11 @@ static int bnxt_fw_init_one_p1(struct bnxt *bp) bp->fw_cap = 0; rc = bnxt_hwrm_ver_get(bp); + /* FW may be unresponsive after FLR. FLR must complete within 100 msec + * so wait before continuing with recovery. + */ + if (rc) + msleep(100); bnxt_try_map_fw_health_reg(bp); if (rc) { if (bp->fw_health && bp->fw_health->status_reliable) { diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 8edf12077..ed0589a1a 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1244,7 +1244,8 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev, } } -static void bcmgenet_eee_enable_set(struct net_device *dev, bool enable) +void bcmgenet_eee_enable_set(struct net_device *dev, bool enable, + bool tx_lpi_enabled) { struct bcmgenet_priv *priv = netdev_priv(dev); u32 off = priv->hw_params->tbuf_offset + TBUF_ENERGY_CTRL; @@ -1264,7 +1265,7 @@ static void bcmgenet_eee_enable_set(struct net_device *dev, bool enable) /* Enable EEE and switch to a 27Mhz clock automatically */ reg = bcmgenet_readl(priv->base + off); - if (enable) + if (tx_lpi_enabled) reg |= TBUF_EEE_EN | TBUF_PM_EN; else reg &= ~(TBUF_EEE_EN | TBUF_PM_EN); @@ -1285,6 +1286,7 @@ static void bcmgenet_eee_enable_set(struct net_device *dev, bool enable) priv->eee.eee_enabled = enable; priv->eee.eee_active = enable; + priv->eee.tx_lpi_enabled = tx_lpi_enabled; } static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_eee *e) @@ -1300,6 +1302,7 @@ static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_eee *e) e->eee_enabled = p->eee_enabled; e->eee_active = p->eee_active; + e->tx_lpi_enabled = p->tx_lpi_enabled; e->tx_lpi_timer = bcmgenet_umac_readl(priv, UMAC_EEE_LPI_TIMER); return phy_ethtool_get_eee(dev->phydev, e); @@ -1309,7 +1312,6 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e) { struct bcmgenet_priv *priv = netdev_priv(dev); struct ethtool_eee *p = &priv->eee; - int ret = 0; if (GENET_IS_V1(priv)) return -EOPNOTSUPP; @@ -1320,16 +1322,11 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e) p->eee_enabled = e->eee_enabled; if (!p->eee_enabled) { - bcmgenet_eee_enable_set(dev, false); + bcmgenet_eee_enable_set(dev, false, false); } else { - ret = phy_init_eee(dev->phydev, 0); - if (ret) { - netif_err(priv, hw, dev, "EEE initialization failed\n"); - return ret; - } - + p->eee_active = phy_init_eee(dev->phydev, false) >= 0; bcmgenet_umac_writel(priv, e->tx_lpi_timer, UMAC_EEE_LPI_TIMER); - bcmgenet_eee_enable_set(dev, true); + bcmgenet_eee_enable_set(dev, p->eee_active, e->tx_lpi_enabled); } return phy_ethtool_set_eee(dev->phydev, e); @@ -4217,9 +4214,6 @@ static int bcmgenet_resume(struct device *d) if (!device_may_wakeup(d)) phy_resume(dev->phydev); - if (priv->eee.eee_enabled) - bcmgenet_eee_enable_set(dev, true); - bcmgenet_netif_start(dev); netif_device_attach(dev); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index f6ca01da1..c7853d530 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -756,4 +756,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv, enum bcmgenet_power_mode mode); +void bcmgenet_eee_enable_set(struct net_device *dev, bool enable, + bool tx_lpi_enabled); + #endif /* __BCMGENET_H__ */ diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 2b0538f2a..becc717aa 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -25,6 +25,7 @@ #include "bcmgenet.h" + /* setup netdev link state when PHY link status change and * update UMAC and RGMII block when link up */ @@ -102,6 +103,11 @@ void bcmgenet_mii_setup(struct net_device *dev) reg |= CMD_TX_EN | CMD_RX_EN; } bcmgenet_umac_writel(priv, reg, UMAC_CMD); + + priv->eee.eee_active = phy_init_eee(phydev, 0) >= 0; + bcmgenet_eee_enable_set(dev, + priv->eee.eee_enabled && priv->eee.eee_active, + priv->eee.tx_lpi_enabled); } else { /* done if nothing has changed */ if (!status_changed) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 4ce913559..fe29769cb 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1766,6 +1766,7 @@ static void fec_enet_adjust_link(struct net_device *ndev) /* if any of the above changed restart the FEC */ if (status_change) { + netif_stop_queue(ndev); napi_disable(&fep->napi); netif_tx_lock_bh(ndev); fec_restart(ndev); @@ -1775,6 +1776,7 @@ static void fec_enet_adjust_link(struct net_device *ndev) } } else { if (fep->link) { + netif_stop_queue(ndev); napi_disable(&fep->napi); netif_tx_lock_bh(ndev); fec_stop(ndev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index deba485ce..c14c391a0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2723,7 +2723,10 @@ static int hclge_mac_init(struct hclge_dev *hdev) int ret; hdev->support_sfp_query = true; - hdev->hw.mac.duplex = HCLGE_MAC_FULL; + + if (!test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) + hdev->hw.mac.duplex = HCLGE_MAC_FULL; + ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed, hdev->hw.mac.duplex); if (ret) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h index 5b0b71bd6..e8e67321e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_trace.h @@ -24,7 +24,7 @@ TRACE_EVENT(hclge_pf_mbx_get, __field(u8, code) __field(u8, subcode) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->vport[0].nic.kinfo.netdev->name) + __string(devname, hdev->vport[0].nic.kinfo.netdev->name) __array(u32, mbx_data, PF_GET_MBX_LEN) ), @@ -33,7 +33,7 @@ TRACE_EVENT(hclge_pf_mbx_get, __entry->code = req->msg.code; __entry->subcode = req->msg.subcode; __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->vport[0].nic.kinfo.netdev->name); + __assign_str(devname, hdev->vport[0].nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_vf_to_pf_cmd)); ), @@ -56,7 +56,7 @@ TRACE_EVENT(hclge_pf_mbx_send, __field(u8, vfid) __field(u16, code) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->vport[0].nic.kinfo.netdev->name) + __string(devname, hdev->vport[0].nic.kinfo.netdev->name) __array(u32, mbx_data, PF_SEND_MBX_LEN) ), @@ -64,7 +64,7 @@ TRACE_EVENT(hclge_pf_mbx_send, __entry->vfid = req->dest_vfid; __entry->code = req->msg.code; __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->vport[0].nic.kinfo.netdev->name); + __assign_str(devname, hdev->vport[0].nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_pf_to_vf_cmd)); ), diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h index e4bfb6191..a208af567 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_trace.h @@ -23,7 +23,7 @@ TRACE_EVENT(hclge_vf_mbx_get, __field(u8, vfid) __field(u16, code) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->nic.kinfo.netdev->name) + __string(devname, hdev->nic.kinfo.netdev->name) __array(u32, mbx_data, VF_GET_MBX_LEN) ), @@ -31,7 +31,7 @@ TRACE_EVENT(hclge_vf_mbx_get, __entry->vfid = req->dest_vfid; __entry->code = req->msg.code; __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->nic.kinfo.netdev->name); + __assign_str(devname, hdev->nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_pf_to_vf_cmd)); ), @@ -55,7 +55,7 @@ TRACE_EVENT(hclge_vf_mbx_send, __field(u8, code) __field(u8, subcode) __string(pciname, pci_name(hdev->pdev)) - __string(devname, &hdev->nic.kinfo.netdev->name) + __string(devname, hdev->nic.kinfo.netdev->name) __array(u32, mbx_data, VF_SEND_MBX_LEN) ), @@ -64,7 +64,7 @@ TRACE_EVENT(hclge_vf_mbx_send, __entry->code = req->msg.code; __entry->subcode = req->msg.subcode; __assign_str(pciname, pci_name(hdev->pdev)); - __assign_str(devname, &hdev->nic.kinfo.netdev->name); + __assign_str(devname, hdev->nic.kinfo.netdev->name); memcpy(__entry->mbx_data, req, sizeof(struct hclge_mbx_vf_to_pf_cmd)); ), diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index d83b96aa3..35a903f6d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1230,8 +1230,11 @@ int i40e_count_filters(struct i40e_vsi *vsi) int bkt; int cnt = 0; - hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) - ++cnt; + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + if (f->state == I40E_FILTER_NEW || + f->state == I40E_FILTER_ACTIVE) + ++cnt; + } return cnt; } @@ -5153,7 +5156,7 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf) { int v, ret = 0; - for (v = 0; v < pf->hw.func_caps.num_vsis; v++) { + for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v]) { ret = i40e_vsi_wait_queues_disabled(pf->vsi[v]); if (ret) @@ -12944,9 +12947,9 @@ int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair) return err; i40e_queue_pair_disable_irq(vsi, queue_pair); + i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */); i40e_clean_rx_ring(vsi->rx_rings[queue_pair]); - i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); i40e_queue_pair_clean_rings(vsi, queue_pair); i40e_queue_pair_reset_stats(vsi, queue_pair); @@ -15485,8 +15488,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) val = (rd32(&pf->hw, I40E_PRTGL_SAH) & I40E_PRTGL_SAH_MFS_MASK) >> I40E_PRTGL_SAH_MFS_SHIFT; if (val < MAX_FRAME_SIZE_DEFAULT) - dev_warn(&pdev->dev, "MFS for port %x has been set below the default: %x\n", - pf->hw.port, val); + dev_warn(&pdev->dev, "MFS for port %x (%d) has been set below the default (%d)\n", + pf->hw.port, val, MAX_FRAME_SIZE_DEFAULT); /* Add a filter to drop all Flow control frames from any VSI from being * transmitted. By doing so we stop a malicious VF from sending out @@ -16020,7 +16023,7 @@ static int __init i40e_init_module(void) * since we need to be able to guarantee forward progress even under * memory pressure. */ - i40e_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, i40e_driver_name); + i40e_wq = alloc_workqueue("%s", 0, 0, i40e_driver_name); if (!i40e_wq) { pr_err("%s: Failed to create workqueue\n", i40e_driver_name); return -ENOMEM; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 7b0ed15f4..4f23243bb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1573,8 +1573,8 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) { struct i40e_hw *hw = &pf->hw; struct i40e_vf *vf; - int i, v; u32 reg; + int i; /* If we don't have any VFs, then there is nothing to reset */ if (!pf->num_alloc_vfs) @@ -1585,11 +1585,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) return false; /* Begin reset on all VFs at once */ - for (v = 0; v < pf->num_alloc_vfs; v++) { - vf = &pf->vf[v]; + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* If VF is being reset no need to trigger reset again */ if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) - i40e_trigger_vf_reset(&pf->vf[v], flr); + i40e_trigger_vf_reset(vf, flr); } /* HW requires some time to make sure it can flush the FIFO for a VF @@ -1598,14 +1597,13 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) * the VFs using a simple iterator that increments once that VF has * finished resetting. */ - for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) { + for (i = 0, vf = &pf->vf[0]; i < 10 && vf < &pf->vf[pf->num_alloc_vfs]; ++i) { usleep_range(10000, 20000); /* Check each VF in sequence, beginning with the VF to fail * the previous check. */ - while (v < pf->num_alloc_vfs) { - vf = &pf->vf[v]; + while (vf < &pf->vf[pf->num_alloc_vfs]) { if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) { reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id)); if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK)) @@ -1615,7 +1613,7 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) /* If the current VF has finished resetting, move on * to the next VF in sequence. */ - v++; + ++vf; } } @@ -1625,39 +1623,39 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) /* Display a warning if at least one VF didn't manage to reset in * time, but continue on with the operation. */ - if (v < pf->num_alloc_vfs) + if (vf < &pf->vf[pf->num_alloc_vfs]) dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n", - pf->vf[v].vf_id); + vf->vf_id); usleep_range(10000, 20000); /* Begin disabling all the rings associated with VFs, but do not wait * between each VF. */ - for (v = 0; v < pf->num_alloc_vfs; v++) { + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* On initial reset, we don't have any queues to disable */ - if (pf->vf[v].lan_vsi_idx == 0) + if (vf->lan_vsi_idx == 0) continue; /* If VF is reset in another thread just continue */ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) continue; - i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[v].lan_vsi_idx]); + i40e_vsi_stop_rings_no_wait(pf->vsi[vf->lan_vsi_idx]); } /* Now that we've notified HW to disable all of the VF rings, wait * until they finish. */ - for (v = 0; v < pf->num_alloc_vfs; v++) { + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* On initial reset, we don't have any queues to disable */ - if (pf->vf[v].lan_vsi_idx == 0) + if (vf->lan_vsi_idx == 0) continue; /* If VF is reset in another thread just continue */ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) continue; - i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[v].lan_vsi_idx]); + i40e_vsi_wait_queues_disabled(pf->vsi[vf->lan_vsi_idx]); } /* Hw may need up to 50ms to finish disabling the RX queues. We @@ -1666,12 +1664,12 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) mdelay(50); /* Finish the reset on each VF */ - for (v = 0; v < pf->num_alloc_vfs; v++) { + for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) { /* If VF is reset in another thread just continue */ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) continue; - i40e_cleanup_reset_vf(&pf->vf[v]); + i40e_cleanup_reset_vf(vf); } i40e_flush(hw); @@ -2545,6 +2543,14 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; int i; + if (vf->is_disabled_from_host) { + aq_ret = -EPERM; + dev_info(&pf->pdev->dev, + "Admin has disabled VF %d, will not enable queues\n", + vf->vf_id); + goto error_param; + } + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; @@ -4587,9 +4593,12 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link) struct i40e_pf *pf = np->vsi->back; struct virtchnl_pf_event pfe; struct i40e_hw *hw = &pf->hw; + struct i40e_vsi *vsi; + unsigned long q_map; struct i40e_vf *vf; int abs_vf_id; int ret = 0; + int tmp; if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) { dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n"); @@ -4612,6 +4621,9 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link) switch (link) { case IFLA_VF_LINK_STATE_AUTO: vf->link_forced = false; + vf->is_disabled_from_host = false; + /* reset needed to reinit VF resources */ + i40e_vc_reset_vf(vf, true); pfe.event_data.link_event.link_status = pf->hw.phy.link_info.link_info & I40E_AQ_LINK_UP; pfe.event_data.link_event.link_speed = @@ -4621,6 +4633,9 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link) case IFLA_VF_LINK_STATE_ENABLE: vf->link_forced = true; vf->link_up = true; + vf->is_disabled_from_host = false; + /* reset needed to reinit VF resources */ + i40e_vc_reset_vf(vf, true); pfe.event_data.link_event.link_status = true; pfe.event_data.link_event.link_speed = VIRTCHNL_LINK_SPEED_40GB; break; @@ -4629,6 +4644,21 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link) vf->link_up = false; pfe.event_data.link_event.link_status = false; pfe.event_data.link_event.link_speed = 0; + + vsi = pf->vsi[vf->lan_vsi_idx]; + q_map = BIT(vsi->num_queue_pairs) - 1; + + vf->is_disabled_from_host = true; + + /* Try to stop both Tx&Rx rings even if one of the calls fails + * to ensure we stop the rings even in case of errors. + * If any of them returns with an error then the first + * error that occurred will be returned. + */ + tmp = i40e_ctrl_vf_tx_rings(vsi, q_map, false); + ret = i40e_ctrl_vf_rx_rings(vsi, q_map, false); + + ret = tmp ? tmp : ret; break; default: ret = -EINVAL; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index bd497cc53..97e9c34d7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -98,6 +98,7 @@ struct i40e_vf { bool link_forced; bool link_up; /* only valid if VF link is forced */ bool spoofchk; + bool is_disabled_from_host; /* PF ctrl of VF enable/disable */ u16 num_vlan; /* ADq related variables */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index b64801bc2..65259722a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2643,6 +2643,34 @@ static void iavf_del_all_cloud_filters(struct iavf_adapter *adapter) } /** + * iavf_is_tc_config_same - Compare the mqprio TC config with the + * TC config already configured on this adapter. + * @adapter: board private structure + * @mqprio_qopt: TC config received from kernel. + * + * This function compares the TC config received from the kernel + * with the config already configured on the adapter. + * + * Return: True if configuration is same, false otherwise. + **/ +static bool iavf_is_tc_config_same(struct iavf_adapter *adapter, + struct tc_mqprio_qopt *mqprio_qopt) +{ + struct virtchnl_channel_info *ch = &adapter->ch_config.ch_info[0]; + int i; + + if (adapter->num_tc != mqprio_qopt->num_tc) + return false; + + for (i = 0; i < adapter->num_tc; i++) { + if (ch[i].count != mqprio_qopt->count[i] || + ch[i].offset != mqprio_qopt->offset[i]) + return false; + } + return true; +} + +/** * __iavf_setup_tc - configure multiple traffic classes * @netdev: network interface device structure * @type_data: tc offload data @@ -2698,7 +2726,7 @@ static int __iavf_setup_tc(struct net_device *netdev, void *type_data) if (ret) return ret; /* Return if same TC config is requested */ - if (adapter->num_tc == num_tc) + if (iavf_is_tc_config_same(adapter, &mqprio_qopt->qopt)) return 0; adapter->num_tc = num_tc; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 02f72fbec..035bc90c8 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -6546,6 +6546,8 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, pf_sw = pf->first_sw; /* find the attribute in the netlink message */ br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (!br_spec) + return -EINVAL; nla_for_each_nested(attr, br_spec, rem) { __u16 mode; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 01176c86b..0848613c3 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6762,77 +6762,75 @@ void igb_update_stats(struct igb_adapter *adapter) } } +static void igb_perout(struct igb_adapter *adapter, int tsintr_tt) +{ + int pin = ptp_find_pin(adapter->ptp_clock, PTP_PF_PEROUT, tsintr_tt); + struct e1000_hw *hw = &adapter->hw; + struct timespec64 ts; + u32 tsauxc; + + if (pin < 0 || pin >= IGB_N_PEROUT) + return; + + spin_lock(&adapter->tmreg_lock); + ts = timespec64_add(adapter->perout[pin].start, + adapter->perout[pin].period); + /* u32 conversion of tv_sec is safe until y2106 */ + wr32((tsintr_tt == 1) ? E1000_TRGTTIML1 : E1000_TRGTTIML0, ts.tv_nsec); + wr32((tsintr_tt == 1) ? E1000_TRGTTIMH1 : E1000_TRGTTIMH0, (u32)ts.tv_sec); + tsauxc = rd32(E1000_TSAUXC); + tsauxc |= TSAUXC_EN_TT0; + wr32(E1000_TSAUXC, tsauxc); + adapter->perout[pin].start = ts; + spin_unlock(&adapter->tmreg_lock); +} + +static void igb_extts(struct igb_adapter *adapter, int tsintr_tt) +{ + int pin = ptp_find_pin(adapter->ptp_clock, PTP_PF_EXTTS, tsintr_tt); + struct e1000_hw *hw = &adapter->hw; + struct ptp_clock_event event; + u32 sec, nsec; + + if (pin < 0 || pin >= IGB_N_EXTTS) + return; + + nsec = rd32((tsintr_tt == 1) ? E1000_AUXSTMPL1 : E1000_AUXSTMPL0); + sec = rd32((tsintr_tt == 1) ? E1000_AUXSTMPH1 : E1000_AUXSTMPH0); + event.type = PTP_CLOCK_EXTTS; + event.index = tsintr_tt; + event.timestamp = sec * 1000000000ULL + nsec; + ptp_clock_event(adapter->ptp_clock, &event); +} + static void igb_tsync_interrupt(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; + u32 tsicr = rd32(E1000_TSICR); struct ptp_clock_event event; - struct timespec64 ts; - u32 ack = 0, tsauxc, sec, nsec, tsicr = rd32(E1000_TSICR); if (tsicr & TSINTR_SYS_WRAP) { event.type = PTP_CLOCK_PPS; if (adapter->ptp_caps.pps) ptp_clock_event(adapter->ptp_clock, &event); - ack |= TSINTR_SYS_WRAP; } if (tsicr & E1000_TSICR_TXTS) { /* retrieve hardware timestamp */ schedule_work(&adapter->ptp_tx_work); - ack |= E1000_TSICR_TXTS; - } - - if (tsicr & TSINTR_TT0) { - spin_lock(&adapter->tmreg_lock); - ts = timespec64_add(adapter->perout[0].start, - adapter->perout[0].period); - /* u32 conversion of tv_sec is safe until y2106 */ - wr32(E1000_TRGTTIML0, ts.tv_nsec); - wr32(E1000_TRGTTIMH0, (u32)ts.tv_sec); - tsauxc = rd32(E1000_TSAUXC); - tsauxc |= TSAUXC_EN_TT0; - wr32(E1000_TSAUXC, tsauxc); - adapter->perout[0].start = ts; - spin_unlock(&adapter->tmreg_lock); - ack |= TSINTR_TT0; - } - - if (tsicr & TSINTR_TT1) { - spin_lock(&adapter->tmreg_lock); - ts = timespec64_add(adapter->perout[1].start, - adapter->perout[1].period); - wr32(E1000_TRGTTIML1, ts.tv_nsec); - wr32(E1000_TRGTTIMH1, (u32)ts.tv_sec); - tsauxc = rd32(E1000_TSAUXC); - tsauxc |= TSAUXC_EN_TT1; - wr32(E1000_TSAUXC, tsauxc); - adapter->perout[1].start = ts; - spin_unlock(&adapter->tmreg_lock); - ack |= TSINTR_TT1; - } - - if (tsicr & TSINTR_AUTT0) { - nsec = rd32(E1000_AUXSTMPL0); - sec = rd32(E1000_AUXSTMPH0); - event.type = PTP_CLOCK_EXTTS; - event.index = 0; - event.timestamp = sec * 1000000000ULL + nsec; - ptp_clock_event(adapter->ptp_clock, &event); - ack |= TSINTR_AUTT0; - } - - if (tsicr & TSINTR_AUTT1) { - nsec = rd32(E1000_AUXSTMPL1); - sec = rd32(E1000_AUXSTMPH1); - event.type = PTP_CLOCK_EXTTS; - event.index = 1; - event.timestamp = sec * 1000000000ULL + nsec; - ptp_clock_event(adapter->ptp_clock, &event); - ack |= TSINTR_AUTT1; - } - - /* acknowledge the interrupts */ - wr32(E1000_TSICR, ack); + } + + if (tsicr & TSINTR_TT0) + igb_perout(adapter, 0); + + if (tsicr & TSINTR_TT1) + igb_perout(adapter, 1); + + if (tsicr & TSINTR_AUTT0) + igb_extts(adapter, 0); + + if (tsicr & TSINTR_AUTT1) + igb_extts(adapter, 1); } static irqreturn_t igb_msix_other(int irq, void *data) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c index 95c92fe89..ed35e0653 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -123,14 +123,14 @@ static s32 ixgbe_init_phy_ops_82598(struct ixgbe_hw *hw) if (ret_val) return ret_val; if (hw->phy.sfp_type == ixgbe_sfp_type_unknown) - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; /* Check to see if SFP+ module is supported */ ret_val = ixgbe_get_sfp_init_sequence_offsets(hw, &list_offset, &data_offset); if (ret_val) - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; break; default: break; @@ -213,7 +213,7 @@ static s32 ixgbe_get_link_capabilities_82598(struct ixgbe_hw *hw, break; default: - return IXGBE_ERR_LINK_SETUP; + return -EIO; } return 0; @@ -283,7 +283,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw) /* Validate the water mark configuration */ if (!hw->fc.pause_time) - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; /* Low water mark of zero causes XOFF floods */ for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { @@ -292,7 +292,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw) if (!hw->fc.low_water[i] || hw->fc.low_water[i] >= hw->fc.high_water[i]) { hw_dbg(hw, "Invalid water mark configuration\n"); - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; } } } @@ -369,7 +369,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw) break; default: hw_dbg(hw, "Flow control param set incorrectly\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } /* Set 802.3x based flow control settings. */ @@ -438,7 +438,7 @@ static s32 ixgbe_start_mac_link_82598(struct ixgbe_hw *hw, msleep(100); } if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) { - status = IXGBE_ERR_AUTONEG_NOT_COMPLETE; + status = -EIO; hw_dbg(hw, "Autonegotiation did not complete.\n"); } } @@ -478,7 +478,7 @@ static s32 ixgbe_validate_link_ready(struct ixgbe_hw *hw) if (timeout == IXGBE_VALIDATE_LINK_READY_TIMEOUT) { hw_dbg(hw, "Link was indicated but link is down\n"); - return IXGBE_ERR_LINK_SETUP; + return -EIO; } return 0; @@ -594,7 +594,7 @@ static s32 ixgbe_setup_mac_link_82598(struct ixgbe_hw *hw, speed &= link_capabilities; if (speed == IXGBE_LINK_SPEED_UNKNOWN) - return IXGBE_ERR_LINK_SETUP; + return -EINVAL; /* Set KX4/KX support according to speed requested */ else if (link_mode == IXGBE_AUTOC_LMS_KX4_AN || @@ -701,9 +701,9 @@ static s32 ixgbe_reset_hw_82598(struct ixgbe_hw *hw) /* Init PHY and function pointers, perform SFP setup */ phy_status = hw->phy.ops.init(hw); - if (phy_status == IXGBE_ERR_SFP_NOT_SUPPORTED) + if (phy_status == -EOPNOTSUPP) return phy_status; - if (phy_status == IXGBE_ERR_SFP_NOT_PRESENT) + if (phy_status == -ENOENT) goto mac_reset_top; hw->phy.ops.reset(hw); @@ -727,7 +727,7 @@ mac_reset_top: udelay(1); } if (ctrl & IXGBE_CTRL_RST) { - status = IXGBE_ERR_RESET_FAILED; + status = -EIO; hw_dbg(hw, "Reset polling failed to complete.\n"); } @@ -789,7 +789,7 @@ static s32 ixgbe_set_vmdq_82598(struct ixgbe_hw *hw, u32 rar, u32 vmdq) /* Make sure we are using a valid rar index range */ if (rar >= rar_entries) { hw_dbg(hw, "RAR index %d is out of range.\n", rar); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(rar)); @@ -814,7 +814,7 @@ static s32 ixgbe_clear_vmdq_82598(struct ixgbe_hw *hw, u32 rar, u32 vmdq) /* Make sure we are using a valid rar index range */ if (rar >= rar_entries) { hw_dbg(hw, "RAR index %d is out of range.\n", rar); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(rar)); @@ -845,7 +845,7 @@ static s32 ixgbe_set_vfta_82598(struct ixgbe_hw *hw, u32 vlan, u32 vind, u32 vftabyte; if (vlan > 4095) - return IXGBE_ERR_PARAM; + return -EINVAL; /* Determine 32-bit word position in array */ regindex = (vlan >> 5) & 0x7F; /* upper seven bits */ @@ -964,7 +964,7 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr, gssr = IXGBE_GSSR_PHY0_SM; if (hw->mac.ops.acquire_swfw_sync(hw, gssr) != 0) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; if (hw->phy.type == ixgbe_phy_nl) { /* @@ -993,7 +993,7 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr, if (sfp_stat != IXGBE_I2C_EEPROM_STATUS_PASS) { hw_dbg(hw, "EEPROM read did not pass.\n"); - status = IXGBE_ERR_SFP_NOT_PRESENT; + status = -ENOENT; goto out; } @@ -1003,7 +1003,7 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr, *eeprom_data = (u8)(sfp_data >> 8); } else { - status = IXGBE_ERR_PHY; + status = -EIO; } out: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index 8d3798a32..46ed20005 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -117,7 +117,7 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw) ret_val = hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); if (ret_val) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; if (hw->eeprom.ops.read(hw, ++data_offset, &data_value)) goto setup_sfp_err; @@ -144,7 +144,7 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw) if (ret_val) { hw_dbg(hw, " sfp module setup not complete\n"); - return IXGBE_ERR_SFP_SETUP_NOT_COMPLETE; + return -EIO; } } @@ -159,7 +159,7 @@ setup_sfp_err: usleep_range(hw->eeprom.semaphore_delay * 1000, hw->eeprom.semaphore_delay * 2000); hw_err(hw, "eeprom read at offset %d failed\n", data_offset); - return IXGBE_ERR_SFP_SETUP_NOT_COMPLETE; + return -EIO; } /** @@ -184,7 +184,7 @@ static s32 prot_autoc_read_82599(struct ixgbe_hw *hw, bool *locked, ret_val = hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); if (ret_val) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; *locked = true; } @@ -219,7 +219,7 @@ static s32 prot_autoc_write_82599(struct ixgbe_hw *hw, u32 autoc, bool locked) ret_val = hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); if (ret_val) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; locked = true; } @@ -400,7 +400,7 @@ static s32 ixgbe_get_link_capabilities_82599(struct ixgbe_hw *hw, break; default: - return IXGBE_ERR_LINK_SETUP; + return -EIO; } if (hw->phy.multispeed_fiber) { @@ -541,7 +541,7 @@ static s32 ixgbe_start_mac_link_82599(struct ixgbe_hw *hw, msleep(100); } if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) { - status = IXGBE_ERR_AUTONEG_NOT_COMPLETE; + status = -EIO; hw_dbg(hw, "Autoneg did not complete.\n"); } } @@ -794,7 +794,7 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, speed &= link_capabilities; if (speed == IXGBE_LINK_SPEED_UNKNOWN) - return IXGBE_ERR_LINK_SETUP; + return -EINVAL; /* Use stored value (EEPROM defaults) of AUTOC to find KR/KX4 support*/ if (hw->mac.orig_link_settings_stored) @@ -861,8 +861,7 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, msleep(100); } if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) { - status = - IXGBE_ERR_AUTONEG_NOT_COMPLETE; + status = -EIO; hw_dbg(hw, "Autoneg did not complete.\n"); } } @@ -927,7 +926,7 @@ static s32 ixgbe_reset_hw_82599(struct ixgbe_hw *hw) /* Identify PHY and related function pointers */ status = hw->phy.ops.init(hw); - if (status == IXGBE_ERR_SFP_NOT_SUPPORTED) + if (status == -EOPNOTSUPP) return status; /* Setup SFP module if there is one present. */ @@ -936,7 +935,7 @@ static s32 ixgbe_reset_hw_82599(struct ixgbe_hw *hw) hw->phy.sfp_setup_needed = false; } - if (status == IXGBE_ERR_SFP_NOT_SUPPORTED) + if (status == -EOPNOTSUPP) return status; /* Reset PHY */ @@ -974,7 +973,7 @@ mac_reset_top: } if (ctrl & IXGBE_CTRL_RST_MASK) { - status = IXGBE_ERR_RESET_FAILED; + status = -EIO; hw_dbg(hw, "Reset polling failed to complete.\n"); } @@ -1093,7 +1092,7 @@ static s32 ixgbe_fdir_check_cmd_complete(struct ixgbe_hw *hw, u32 *fdircmd) udelay(10); } - return IXGBE_ERR_FDIR_CMD_INCOMPLETE; + return -EIO; } /** @@ -1155,7 +1154,7 @@ s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw) } if (i >= IXGBE_FDIR_INIT_DONE_POLL) { hw_dbg(hw, "Flow Director Signature poll time exceeded!\n"); - return IXGBE_ERR_FDIR_REINIT_FAILED; + return -EIO; } /* Clear FDIR statistics registers (read to clear) */ @@ -1387,7 +1386,7 @@ s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw, break; default: hw_dbg(hw, " Error on flow type input\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } /* configure FDIRCMD register */ @@ -1546,7 +1545,7 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, break; default: hw_dbg(hw, " Error on vm pool mask\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } switch (input_mask->formatted.flow_type & IXGBE_ATR_L4TYPE_MASK) { @@ -1555,13 +1554,13 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, if (input_mask->formatted.dst_port || input_mask->formatted.src_port) { hw_dbg(hw, " Error on src/dst port mask\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } case IXGBE_ATR_L4TYPE_MASK: break; default: hw_dbg(hw, " Error on flow type mask\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } switch (ntohs(input_mask->formatted.vlan_id) & 0xEFFF) { @@ -1582,7 +1581,7 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, break; default: hw_dbg(hw, " Error on VLAN mask\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } switch ((__force u16)input_mask->formatted.flex_bytes & 0xFFFF) { @@ -1594,7 +1593,7 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, break; default: hw_dbg(hw, " Error on flexible byte mask\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } /* Now mask VM pool and destination IPv6 - bits 5 and 2 */ @@ -1823,7 +1822,7 @@ static s32 ixgbe_identify_phy_82599(struct ixgbe_hw *hw) /* Return error if SFP module has been detected but is not supported */ if (hw->phy.type == ixgbe_phy_sfp_unsupported) - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; return status; } @@ -1862,13 +1861,13 @@ static s32 ixgbe_enable_rx_dma_82599(struct ixgbe_hw *hw, u32 regval) * Verifies that installed the firmware version is 0.6 or higher * for SFI devices. All 82599 SFI devices should have version 0.6 or higher. * - * Returns IXGBE_ERR_EEPROM_VERSION if the FW is not present or - * if the FW version is not supported. + * Return: -EACCES if the FW is not present or if the FW version is + * not supported. **/ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw) { - s32 status = IXGBE_ERR_EEPROM_VERSION; u16 fw_offset, fw_ptp_cfg_offset; + s32 status = -EACCES; u16 offset; u16 fw_version = 0; @@ -1882,7 +1881,7 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw) goto fw_version_err; if (fw_offset == 0 || fw_offset == 0xFFFF) - return IXGBE_ERR_EEPROM_VERSION; + return -EACCES; /* get the offset to the Pass Through Patch Configuration block */ offset = fw_offset + IXGBE_FW_PASSTHROUGH_PATCH_CONFIG_PTR; @@ -1890,7 +1889,7 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw) goto fw_version_err; if (fw_ptp_cfg_offset == 0 || fw_ptp_cfg_offset == 0xFFFF) - return IXGBE_ERR_EEPROM_VERSION; + return -EACCES; /* get the firmware version */ offset = fw_ptp_cfg_offset + IXGBE_FW_PATCH_VERSION_4; @@ -1904,7 +1903,7 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw) fw_version_err: hw_err(hw, "eeprom read at offset %d failed\n", offset); - return IXGBE_ERR_EEPROM_VERSION; + return -EACCES; } /** @@ -2037,7 +2036,7 @@ static s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw) if (!(anlp1_reg & IXGBE_ANLP1_AN_STATE_MASK)) { hw_dbg(hw, "auto negotiation not completed\n"); - ret_val = IXGBE_ERR_RESET_FAILED; + ret_val = -EIO; goto reset_pipeline_out; } @@ -2086,7 +2085,7 @@ static s32 ixgbe_read_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, if (!timeout) { hw_dbg(hw, "Driver can't access resource, acquiring I2C bus timeout.\n"); - status = IXGBE_ERR_I2C; + status = -EIO; goto release_i2c_access; } } @@ -2140,7 +2139,7 @@ static s32 ixgbe_write_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, if (!timeout) { hw_dbg(hw, "Driver can't access resource, acquiring I2C bus timeout.\n"); - status = IXGBE_ERR_I2C; + status = -EIO; goto release_i2c_access; } } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 62ddb452f..22595d221 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -30,7 +30,7 @@ static s32 ixgbe_write_eeprom_buffer_bit_bang(struct ixgbe_hw *hw, u16 offset, u16 words, u16 *data); static s32 ixgbe_detect_eeprom_page_size_generic(struct ixgbe_hw *hw, u16 offset); -static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw); +static s32 ixgbe_disable_pcie_primary(struct ixgbe_hw *hw); /* Base table for registers values that change by MAC */ const u32 ixgbe_mvals_8259X[IXGBE_MVALS_IDX_LIMIT] = { @@ -123,7 +123,7 @@ s32 ixgbe_setup_fc_generic(struct ixgbe_hw *hw) */ if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { hw_dbg(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n"); - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; } /* @@ -214,7 +214,7 @@ s32 ixgbe_setup_fc_generic(struct ixgbe_hw *hw) break; default: hw_dbg(hw, "Flow control param set incorrectly\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } if (hw->mac.type != ixgbe_mac_X540) { @@ -499,7 +499,7 @@ s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num, if (pba_num == NULL) { hw_dbg(hw, "PBA string buffer was null\n"); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } ret_val = hw->eeprom.ops.read(hw, IXGBE_PBANUM0_PTR, &data); @@ -525,7 +525,7 @@ s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num, /* we will need 11 characters to store the PBA */ if (pba_num_size < 11) { hw_dbg(hw, "PBA string buffer too small\n"); - return IXGBE_ERR_NO_SPACE; + return -ENOSPC; } /* extract hex string from data and pba_ptr */ @@ -562,13 +562,13 @@ s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num, if (length == 0xFFFF || length == 0) { hw_dbg(hw, "NVM PBA number section invalid length\n"); - return IXGBE_ERR_PBA_SECTION; + return -EIO; } /* check if pba_num buffer is big enough */ if (pba_num_size < (((u32)length * 2) - 1)) { hw_dbg(hw, "PBA string buffer too small\n"); - return IXGBE_ERR_NO_SPACE; + return -ENOSPC; } /* trim pba length from start of string */ @@ -745,10 +745,10 @@ s32 ixgbe_stop_adapter_generic(struct ixgbe_hw *hw) usleep_range(1000, 2000); /* - * Prevent the PCI-E bus from from hanging by disabling PCI-E master + * Prevent the PCI-E bus from hanging by disabling PCI-E primary * access and verify no pending requests */ - return ixgbe_disable_pcie_master(hw); + return ixgbe_disable_pcie_primary(hw); } /** @@ -804,7 +804,7 @@ s32 ixgbe_led_on_generic(struct ixgbe_hw *hw, u32 index) u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); if (index > 3) - return IXGBE_ERR_PARAM; + return -EINVAL; /* To turn on the LED, set mode to ON. */ led_reg &= ~IXGBE_LED_MODE_MASK(index); @@ -825,7 +825,7 @@ s32 ixgbe_led_off_generic(struct ixgbe_hw *hw, u32 index) u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); if (index > 3) - return IXGBE_ERR_PARAM; + return -EINVAL; /* To turn off the LED, set mode to OFF. */ led_reg &= ~IXGBE_LED_MODE_MASK(index); @@ -903,11 +903,8 @@ s32 ixgbe_write_eeprom_buffer_bit_bang_generic(struct ixgbe_hw *hw, u16 offset, hw->eeprom.ops.init_params(hw); - if (words == 0) - return IXGBE_ERR_INVALID_ARGUMENT; - - if (offset + words > hw->eeprom.word_size) - return IXGBE_ERR_EEPROM; + if (words == 0 || (offset + words > hw->eeprom.word_size)) + return -EINVAL; /* * The EEPROM page size cannot be queried from the chip. We do lazy @@ -961,7 +958,7 @@ static s32 ixgbe_write_eeprom_buffer_bit_bang(struct ixgbe_hw *hw, u16 offset, if (ixgbe_ready_eeprom(hw) != 0) { ixgbe_release_eeprom(hw); - return IXGBE_ERR_EEPROM; + return -EIO; } for (i = 0; i < words; i++) { @@ -1027,7 +1024,7 @@ s32 ixgbe_write_eeprom_generic(struct ixgbe_hw *hw, u16 offset, u16 data) hw->eeprom.ops.init_params(hw); if (offset >= hw->eeprom.word_size) - return IXGBE_ERR_EEPROM; + return -EINVAL; return ixgbe_write_eeprom_buffer_bit_bang(hw, offset, 1, &data); } @@ -1049,11 +1046,8 @@ s32 ixgbe_read_eeprom_buffer_bit_bang_generic(struct ixgbe_hw *hw, u16 offset, hw->eeprom.ops.init_params(hw); - if (words == 0) - return IXGBE_ERR_INVALID_ARGUMENT; - - if (offset + words > hw->eeprom.word_size) - return IXGBE_ERR_EEPROM; + if (words == 0 || (offset + words > hw->eeprom.word_size)) + return -EINVAL; /* * We cannot hold synchronization semaphores for too long @@ -1098,7 +1092,7 @@ static s32 ixgbe_read_eeprom_buffer_bit_bang(struct ixgbe_hw *hw, u16 offset, if (ixgbe_ready_eeprom(hw) != 0) { ixgbe_release_eeprom(hw); - return IXGBE_ERR_EEPROM; + return -EIO; } for (i = 0; i < words; i++) { @@ -1141,7 +1135,7 @@ s32 ixgbe_read_eeprom_bit_bang_generic(struct ixgbe_hw *hw, u16 offset, hw->eeprom.ops.init_params(hw); if (offset >= hw->eeprom.word_size) - return IXGBE_ERR_EEPROM; + return -EINVAL; return ixgbe_read_eeprom_buffer_bit_bang(hw, offset, 1, data); } @@ -1164,11 +1158,8 @@ s32 ixgbe_read_eerd_buffer_generic(struct ixgbe_hw *hw, u16 offset, hw->eeprom.ops.init_params(hw); - if (words == 0) - return IXGBE_ERR_INVALID_ARGUMENT; - - if (offset >= hw->eeprom.word_size) - return IXGBE_ERR_EEPROM; + if (words == 0 || offset >= hw->eeprom.word_size) + return -EINVAL; for (i = 0; i < words; i++) { eerd = ((offset + i) << IXGBE_EEPROM_RW_ADDR_SHIFT) | @@ -1261,11 +1252,8 @@ s32 ixgbe_write_eewr_buffer_generic(struct ixgbe_hw *hw, u16 offset, hw->eeprom.ops.init_params(hw); - if (words == 0) - return IXGBE_ERR_INVALID_ARGUMENT; - - if (offset >= hw->eeprom.word_size) - return IXGBE_ERR_EEPROM; + if (words == 0 || offset >= hw->eeprom.word_size) + return -EINVAL; for (i = 0; i < words; i++) { eewr = ((offset + i) << IXGBE_EEPROM_RW_ADDR_SHIFT) | @@ -1327,7 +1315,7 @@ static s32 ixgbe_poll_eerd_eewr_done(struct ixgbe_hw *hw, u32 ee_reg) } udelay(5); } - return IXGBE_ERR_EEPROM; + return -EIO; } /** @@ -1343,7 +1331,7 @@ static s32 ixgbe_acquire_eeprom(struct ixgbe_hw *hw) u32 i; if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM) != 0) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); @@ -1365,7 +1353,7 @@ static s32 ixgbe_acquire_eeprom(struct ixgbe_hw *hw) hw_dbg(hw, "Could not acquire EEPROM grant\n"); hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); - return IXGBE_ERR_EEPROM; + return -EIO; } /* Setup EEPROM for Read/Write */ @@ -1418,7 +1406,7 @@ static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw) swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw)); if (swsm & IXGBE_SWSM_SMBI) { hw_dbg(hw, "Software semaphore SMBI between device drivers not granted.\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } } @@ -1446,7 +1434,7 @@ static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw) if (i >= timeout) { hw_dbg(hw, "SWESMBI Software EEPROM semaphore not granted.\n"); ixgbe_release_eeprom_semaphore(hw); - return IXGBE_ERR_EEPROM; + return -EIO; } return 0; @@ -1502,7 +1490,7 @@ static s32 ixgbe_ready_eeprom(struct ixgbe_hw *hw) */ if (i >= IXGBE_EEPROM_MAX_RETRY_SPI) { hw_dbg(hw, "SPI EEPROM Status error\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } return 0; @@ -1714,7 +1702,7 @@ s32 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw) for (i = IXGBE_PCIE_ANALOG_PTR; i < IXGBE_FW_PTR; i++) { if (hw->eeprom.ops.read(hw, i, &pointer)) { hw_dbg(hw, "EEPROM read failed\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } /* If the pointer seems invalid */ @@ -1723,7 +1711,7 @@ s32 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw) if (hw->eeprom.ops.read(hw, pointer, &length)) { hw_dbg(hw, "EEPROM read failed\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } if (length == 0xFFFF || length == 0) @@ -1732,7 +1720,7 @@ s32 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw) for (j = pointer + 1; j <= pointer + length; j++) { if (hw->eeprom.ops.read(hw, j, &word)) { hw_dbg(hw, "EEPROM read failed\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } checksum += word; } @@ -1785,7 +1773,7 @@ s32 ixgbe_validate_eeprom_checksum_generic(struct ixgbe_hw *hw, * calculated checksum */ if (read_checksum != checksum) - status = IXGBE_ERR_EEPROM_CHECKSUM; + status = -EIO; /* If the user cares, return the calculated checksum */ if (checksum_val) @@ -1844,7 +1832,7 @@ s32 ixgbe_set_rar_generic(struct ixgbe_hw *hw, u32 index, u8 *addr, u32 vmdq, /* Make sure we are using a valid rar index range */ if (index >= rar_entries) { hw_dbg(hw, "RAR index %d is out of range.\n", index); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } /* setup VMDq pool selection before this RAR gets enabled */ @@ -1896,7 +1884,7 @@ s32 ixgbe_clear_rar_generic(struct ixgbe_hw *hw, u32 index) /* Make sure we are using a valid rar index range */ if (index >= rar_entries) { hw_dbg(hw, "RAR index %d is out of range.\n", index); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } /* @@ -2145,7 +2133,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw) /* Validate the water mark configuration. */ if (!hw->fc.pause_time) - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; /* Low water mark of zero causes XOFF floods */ for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { @@ -2154,7 +2142,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw) if (!hw->fc.low_water[i] || hw->fc.low_water[i] >= hw->fc.high_water[i]) { hw_dbg(hw, "Invalid water mark configuration\n"); - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; } } } @@ -2211,7 +2199,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw) break; default: hw_dbg(hw, "Flow control param set incorrectly\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } /* Set 802.3x based flow control settings. */ @@ -2268,7 +2256,7 @@ s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg, u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm) { if ((!(adv_reg)) || (!(lp_reg))) - return IXGBE_ERR_FC_NOT_NEGOTIATED; + return -EINVAL; if ((adv_reg & adv_sym) && (lp_reg & lp_sym)) { /* @@ -2320,7 +2308,7 @@ static s32 ixgbe_fc_autoneg_fiber(struct ixgbe_hw *hw) linkstat = IXGBE_READ_REG(hw, IXGBE_PCS1GLSTA); if ((!!(linkstat & IXGBE_PCS1GLSTA_AN_COMPLETE) == 0) || (!!(linkstat & IXGBE_PCS1GLSTA_AN_TIMED_OUT) == 1)) - return IXGBE_ERR_FC_NOT_NEGOTIATED; + return -EIO; pcs_anadv_reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANA); pcs_lpab_reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANLP); @@ -2352,12 +2340,12 @@ static s32 ixgbe_fc_autoneg_backplane(struct ixgbe_hw *hw) */ links = IXGBE_READ_REG(hw, IXGBE_LINKS); if ((links & IXGBE_LINKS_KX_AN_COMP) == 0) - return IXGBE_ERR_FC_NOT_NEGOTIATED; + return -EIO; if (hw->mac.type == ixgbe_mac_82599EB) { links2 = IXGBE_READ_REG(hw, IXGBE_LINKS2); if ((links2 & IXGBE_LINKS2_AN_SUPPORTED) == 0) - return IXGBE_ERR_FC_NOT_NEGOTIATED; + return -EIO; } /* * Read the 10g AN autoc and LP ability registers and resolve @@ -2406,8 +2394,8 @@ static s32 ixgbe_fc_autoneg_copper(struct ixgbe_hw *hw) **/ void ixgbe_fc_autoneg(struct ixgbe_hw *hw) { - s32 ret_val = IXGBE_ERR_FC_NOT_NEGOTIATED; ixgbe_link_speed speed; + s32 ret_val = -EIO; bool link_up; /* @@ -2505,15 +2493,15 @@ static u32 ixgbe_pcie_timeout_poll(struct ixgbe_hw *hw) } /** - * ixgbe_disable_pcie_master - Disable PCI-express master access + * ixgbe_disable_pcie_primary - Disable PCI-express primary access * @hw: pointer to hardware structure * - * Disables PCI-Express master access and verifies there are no pending - * requests. IXGBE_ERR_MASTER_REQUESTS_PENDING is returned if master disable - * bit hasn't caused the master requests to be disabled, else 0 - * is returned signifying master requests disabled. + * Disables PCI-Express primary access and verifies there are no pending + * requests. -EALREADY is returned if primary disable + * bit hasn't caused the primary requests to be disabled, else 0 + * is returned signifying primary requests disabled. **/ -static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw) +static s32 ixgbe_disable_pcie_primary(struct ixgbe_hw *hw) { u32 i, poll; u16 value; @@ -2522,23 +2510,23 @@ static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw) IXGBE_WRITE_REG(hw, IXGBE_CTRL, IXGBE_CTRL_GIO_DIS); /* Poll for bit to read as set */ - for (i = 0; i < IXGBE_PCI_MASTER_DISABLE_TIMEOUT; i++) { + for (i = 0; i < IXGBE_PCI_PRIMARY_DISABLE_TIMEOUT; i++) { if (IXGBE_READ_REG(hw, IXGBE_CTRL) & IXGBE_CTRL_GIO_DIS) break; usleep_range(100, 120); } - if (i >= IXGBE_PCI_MASTER_DISABLE_TIMEOUT) { + if (i >= IXGBE_PCI_PRIMARY_DISABLE_TIMEOUT) { hw_dbg(hw, "GIO disable did not set - requesting resets\n"); goto gio_disable_fail; } - /* Exit if master requests are blocked */ + /* Exit if primary requests are blocked */ if (!(IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_GIO) || ixgbe_removed(hw->hw_addr)) return 0; - /* Poll for master request bit to clear */ - for (i = 0; i < IXGBE_PCI_MASTER_DISABLE_TIMEOUT; i++) { + /* Poll for primary request bit to clear */ + for (i = 0; i < IXGBE_PCI_PRIMARY_DISABLE_TIMEOUT; i++) { udelay(100); if (!(IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_GIO)) return 0; @@ -2546,13 +2534,13 @@ static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw) /* * Two consecutive resets are required via CTRL.RST per datasheet - * 5.2.5.3.2 Master Disable. We set a flag to inform the reset routine - * of this need. The first reset prevents new master requests from + * 5.2.5.3.2 Primary Disable. We set a flag to inform the reset routine + * of this need. The first reset prevents new primary requests from * being issued by our device. We then must wait 1usec or more for any * remaining completions from the PCIe bus to trickle in, and then reset * again to clear out any effects they may have had on our device. */ - hw_dbg(hw, "GIO Master Disable bit didn't clear - requesting resets\n"); + hw_dbg(hw, "GIO Primary Disable bit didn't clear - requesting resets\n"); gio_disable_fail: hw->mac.flags |= IXGBE_FLAGS_DOUBLE_RESET_REQUIRED; @@ -2574,7 +2562,7 @@ gio_disable_fail: } hw_dbg(hw, "PCIe transaction pending bit also did not clear.\n"); - return IXGBE_ERR_MASTER_REQUESTS_PENDING; + return -EALREADY; } /** @@ -2599,7 +2587,7 @@ s32 ixgbe_acquire_swfw_sync(struct ixgbe_hw *hw, u32 mask) * SW_FW_SYNC bits (not just NVM) */ if (ixgbe_get_eeprom_semaphore(hw)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; gssr = IXGBE_READ_REG(hw, IXGBE_GSSR); if (!(gssr & (fwmask | swmask))) { @@ -2619,7 +2607,7 @@ s32 ixgbe_acquire_swfw_sync(struct ixgbe_hw *hw, u32 mask) ixgbe_release_swfw_sync(hw, gssr & (fwmask | swmask)); usleep_range(5000, 10000); - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; } /** @@ -2756,7 +2744,7 @@ s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index) s32 ret_val; if (index > 3) - return IXGBE_ERR_PARAM; + return -EINVAL; /* * Link must be up to auto-blink the LEDs; @@ -2802,7 +2790,7 @@ s32 ixgbe_blink_led_stop_generic(struct ixgbe_hw *hw, u32 index) s32 ret_val; if (index > 3) - return IXGBE_ERR_PARAM; + return -EINVAL; ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, &autoc_reg); if (ret_val) @@ -2962,7 +2950,7 @@ s32 ixgbe_clear_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq) /* Make sure we are using a valid rar index range */ if (rar >= rar_entries) { hw_dbg(hw, "RAR index %d is out of range.\n", rar); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } mpsar_lo = IXGBE_READ_REG(hw, IXGBE_MPSAR_LO(rar)); @@ -3013,7 +3001,7 @@ s32 ixgbe_set_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq) /* Make sure we are using a valid rar index range */ if (rar >= rar_entries) { hw_dbg(hw, "RAR index %d is out of range.\n", rar); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } if (vmdq < 32) { @@ -3090,7 +3078,7 @@ static s32 ixgbe_find_vlvf_slot(struct ixgbe_hw *hw, u32 vlan, bool vlvf_bypass) * will simply bypass the VLVF if there are no entries present in the * VLVF that contain our VLAN */ - first_empty_slot = vlvf_bypass ? IXGBE_ERR_NO_SPACE : 0; + first_empty_slot = vlvf_bypass ? -ENOSPC : 0; /* add VLAN enable bit for comparison */ vlan |= IXGBE_VLVF_VIEN; @@ -3114,7 +3102,7 @@ static s32 ixgbe_find_vlvf_slot(struct ixgbe_hw *hw, u32 vlan, bool vlvf_bypass) if (!first_empty_slot) hw_dbg(hw, "No space in VLVF.\n"); - return first_empty_slot ? : IXGBE_ERR_NO_SPACE; + return first_empty_slot ? : -ENOSPC; } /** @@ -3134,7 +3122,7 @@ s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, u32 vind, s32 vlvf_index; if ((vlan > 4095) || (vind > 63)) - return IXGBE_ERR_PARAM; + return -EINVAL; /* * this is a 2 part operation - first the VFTA, then the @@ -3595,7 +3583,8 @@ u8 ixgbe_calculate_checksum(u8 *buffer, u32 length) * * Communicates with the manageability block. On success return 0 * else returns semaphore error when encountering an error acquiring - * semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails. + * semaphore, -EINVAL when incorrect parameters passed or -EIO when + * command fails. * * This function assumes that the IXGBE_GSSR_SW_MNG_SM semaphore is held * by the caller. @@ -3608,7 +3597,7 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length, if (!length || length > IXGBE_HI_MAX_BLOCK_BYTE_LENGTH) { hw_dbg(hw, "Buffer length failure buffersize-%d.\n", length); - return IXGBE_ERR_HOST_INTERFACE_COMMAND; + return -EINVAL; } /* Set bit 9 of FWSTS clearing FW reset indication */ @@ -3619,13 +3608,13 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length, hicr = IXGBE_READ_REG(hw, IXGBE_HICR); if (!(hicr & IXGBE_HICR_EN)) { hw_dbg(hw, "IXGBE_HOST_EN bit disabled.\n"); - return IXGBE_ERR_HOST_INTERFACE_COMMAND; + return -EIO; } /* Calculate length in DWORDs. We must be DWORD aligned */ if (length % sizeof(u32)) { hw_dbg(hw, "Buffer length failure, not aligned to dword"); - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; } dword_len = length >> 2; @@ -3650,7 +3639,7 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length, /* Check command successful completion. */ if ((timeout && i == timeout) || !(IXGBE_READ_REG(hw, IXGBE_HICR) & IXGBE_HICR_SV)) - return IXGBE_ERR_HOST_INTERFACE_COMMAND; + return -EIO; return 0; } @@ -3670,7 +3659,7 @@ s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length, * in these cases. * * Communicates with the manageability block. On success return 0 - * else return IXGBE_ERR_HOST_INTERFACE_COMMAND. + * else return -EIO or -EINVAL. **/ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, u32 length, u32 timeout, @@ -3687,7 +3676,7 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, if (!length || length > IXGBE_HI_MAX_BLOCK_BYTE_LENGTH) { hw_dbg(hw, "Buffer length failure buffersize-%d.\n", length); - return IXGBE_ERR_HOST_INTERFACE_COMMAND; + return -EINVAL; } /* Take management host interface semaphore */ status = hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_SW_MNG_SM); @@ -3717,7 +3706,7 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, if (length < round_up(buf_len, 4) + hdr_size) { hw_dbg(hw, "Buffer not large enough for reply message.\n"); - status = IXGBE_ERR_HOST_INTERFACE_COMMAND; + status = -EIO; goto rel_out; } @@ -3748,8 +3737,8 @@ rel_out: * * Sends driver version number to firmware through the manageability * block. On success return 0 - * else returns IXGBE_ERR_SWFW_SYNC when encountering an error acquiring - * semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails. + * else returns -EBUSY when encountering an error acquiring + * semaphore or -EIO when command fails. **/ s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min, u8 build, u8 sub, __always_unused u16 len, @@ -3785,7 +3774,7 @@ s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min, FW_CEM_RESP_STATUS_SUCCESS) ret_val = 0; else - ret_val = IXGBE_ERR_HOST_INTERFACE_COMMAND; + ret_val = -EIO; break; } @@ -3883,14 +3872,14 @@ static s32 ixgbe_get_ets_data(struct ixgbe_hw *hw, u16 *ets_cfg, return status; if ((*ets_offset == 0x0000) || (*ets_offset == 0xFFFF)) - return IXGBE_NOT_IMPLEMENTED; + return -EOPNOTSUPP; status = hw->eeprom.ops.read(hw, *ets_offset, ets_cfg); if (status) return status; if ((*ets_cfg & IXGBE_ETS_TYPE_MASK) != IXGBE_ETS_TYPE_EMC_SHIFTED) - return IXGBE_NOT_IMPLEMENTED; + return -EOPNOTSUPP; return 0; } @@ -3913,7 +3902,7 @@ s32 ixgbe_get_thermal_sensor_data_generic(struct ixgbe_hw *hw) /* Only support thermal sensors attached to physical port 0 */ if ((IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1)) - return IXGBE_NOT_IMPLEMENTED; + return -EOPNOTSUPP; status = ixgbe_get_ets_data(hw, &ets_cfg, &ets_offset); if (status) @@ -3973,7 +3962,7 @@ s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw) /* Only support thermal sensors attached to physical port 0 */ if ((IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1)) - return IXGBE_NOT_IMPLEMENTED; + return -EOPNOTSUPP; status = ixgbe_get_ets_data(hw, &ets_cfg, &ets_offset); if (status) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 2eb133183..93532f3a3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -3346,7 +3346,7 @@ static int ixgbe_get_module_eeprom(struct net_device *dev, { struct ixgbe_adapter *adapter = netdev_priv(dev); struct ixgbe_hw *hw = &adapter->hw; - s32 status = IXGBE_ERR_PHY_ADDR_INVALID; + s32 status = -EFAULT; u8 databyte = 0xFF; int i = 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index 319620856..512da34e7 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -909,7 +909,13 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) goto err_out; } - xs = kzalloc(sizeof(*xs), GFP_KERNEL); + algo = xfrm_aead_get_byname(aes_gcm_name, IXGBE_IPSEC_AUTH_BITS, 1); + if (unlikely(!algo)) { + err = -ENOENT; + goto err_out; + } + + xs = kzalloc(sizeof(*xs), GFP_ATOMIC); if (unlikely(!xs)) { err = -ENOMEM; goto err_out; @@ -925,14 +931,8 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) memcpy(&xs->id.daddr.a4, sam->addr, sizeof(xs->id.daddr.a4)); xs->xso.dev = adapter->netdev; - algo = xfrm_aead_get_byname(aes_gcm_name, IXGBE_IPSEC_AUTH_BITS, 1); - if (unlikely(!algo)) { - err = -ENOENT; - goto err_xs; - } - aead_len = sizeof(*xs->aead) + IXGBE_IPSEC_KEY_BITS / 8; - xs->aead = kzalloc(aead_len, GFP_KERNEL); + xs->aead = kzalloc(aead_len, GFP_ATOMIC); if (unlikely(!xs->aead)) { err = -ENOMEM; goto err_xs; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 5829d81f2..b7672200d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2766,7 +2766,6 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; u32 eicr = adapter->interrupt_event; - s32 rc; if (test_bit(__IXGBE_DOWN, &adapter->state)) return; @@ -2800,14 +2799,13 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter) } /* Check if this is not due to overtemp */ - if (hw->phy.ops.check_overtemp(hw) != IXGBE_ERR_OVERTEMP) + if (!hw->phy.ops.check_overtemp(hw)) return; break; case IXGBE_DEV_ID_X550EM_A_1G_T: case IXGBE_DEV_ID_X550EM_A_1G_T_L: - rc = hw->phy.ops.check_overtemp(hw); - if (rc != IXGBE_ERR_OVERTEMP) + if (!hw->phy.ops.check_overtemp(hw)) return; break; default: @@ -2951,8 +2949,8 @@ static void ixgbe_check_lsc(struct ixgbe_adapter *adapter) static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter, u64 qmask) { - u32 mask; struct ixgbe_hw *hw = &adapter->hw; + u32 mask; switch (hw->mac.type) { case ixgbe_mac_82598EB: @@ -5520,7 +5518,7 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw) { u32 speed; bool autoneg, link_up = false; - int ret = IXGBE_ERR_LINK_SETUP; + int ret = -EIO; if (hw->mac.ops.check_link) ret = hw->mac.ops.check_link(hw, &speed, &link_up, false); @@ -5946,13 +5944,13 @@ void ixgbe_reset(struct ixgbe_adapter *adapter) err = hw->mac.ops.init_hw(hw); switch (err) { case 0: - case IXGBE_ERR_SFP_NOT_PRESENT: - case IXGBE_ERR_SFP_NOT_SUPPORTED: + case -ENOENT: + case -EOPNOTSUPP: break; - case IXGBE_ERR_MASTER_REQUESTS_PENDING: - e_dev_err("master disable timed out\n"); + case -EALREADY: + e_dev_err("primary disable timed out\n"); break; - case IXGBE_ERR_EEPROM_VERSION: + case -EACCES: /* We are running on a pre-production device, log a warning */ e_dev_warn("This device is a pre-production adapter/LOM. " "Please be aware there may be issues associated with " @@ -7735,10 +7733,10 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) adapter->sfp_poll_time = jiffies + IXGBE_SFP_POLL_JIFFIES - 1; err = hw->phy.ops.identify_sfp(hw); - if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) + if (err == -EOPNOTSUPP) goto sfp_out; - if (err == IXGBE_ERR_SFP_NOT_PRESENT) { + if (err == -ENOENT) { /* If no cable is present, then we need to reset * the next time we find a good cable. */ adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET; @@ -7764,7 +7762,7 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) else err = hw->mac.ops.setup_sfp(hw); - if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) + if (err == -EOPNOTSUPP) goto sfp_out; adapter->flags |= IXGBE_FLAG_NEED_LINK_CONFIG; @@ -7773,8 +7771,8 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) sfp_out: clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state); - if ((err == IXGBE_ERR_SFP_NOT_SUPPORTED) && - (adapter->netdev->reg_state == NETREG_REGISTERED)) { + if (err == -EOPNOTSUPP && + adapter->netdev->reg_state == NETREG_REGISTERED) { e_dev_err("failed to initialize because an unsupported " "SFP+ module type was detected.\n"); e_dev_err("Reload the driver after installing a " @@ -7844,7 +7842,7 @@ static void ixgbe_service_timer(struct timer_list *t) static void ixgbe_phy_interrupt_subtask(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - u32 status; + bool overtemp; if (!(adapter->flags2 & IXGBE_FLAG2_PHY_INTERRUPT)) return; @@ -7854,11 +7852,9 @@ static void ixgbe_phy_interrupt_subtask(struct ixgbe_adapter *adapter) if (!hw->phy.ops.handle_lasi) return; - status = hw->phy.ops.handle_lasi(&adapter->hw); - if (status != IXGBE_ERR_OVERTEMP) - return; - - e_crit(drv, "%s\n", ixgbe_overheat_msg); + hw->phy.ops.handle_lasi(&adapter->hw, &overtemp); + if (overtemp) + e_crit(drv, "%s\n", ixgbe_overheat_msg); } static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter) @@ -10399,6 +10395,44 @@ static void ixgbe_reset_rxr_stats(struct ixgbe_ring *rx_ring) } /** + * ixgbe_irq_disable_single - Disable single IRQ vector + * @adapter: adapter structure + * @ring: ring index + **/ +static void ixgbe_irq_disable_single(struct ixgbe_adapter *adapter, u32 ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u64 qmask = BIT_ULL(ring); + u32 mask; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + mask = qmask & IXGBE_EIMC_RTX_QUEUE; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, mask); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + mask = (qmask & 0xFFFFFFFF); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask); + mask = (qmask >> 32); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask); + break; + default: + break; + } + IXGBE_WRITE_FLUSH(&adapter->hw); + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) + synchronize_irq(adapter->msix_entries[ring].vector); + else + synchronize_irq(adapter->pdev->irq); +} + +/** * ixgbe_txrx_ring_disable - Disable Rx/Tx/XDP Tx rings * @adapter: adapter structure * @ring: ring index @@ -10414,6 +10448,11 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) tx_ring = adapter->tx_ring[ring]; xdp_ring = adapter->xdp_ring[ring]; + ixgbe_irq_disable_single(adapter, ring); + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_disable(&rx_ring->q_vector->napi); + ixgbe_disable_txr(adapter, tx_ring); if (xdp_ring) ixgbe_disable_txr(adapter, xdp_ring); @@ -10422,9 +10461,6 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) if (xdp_ring) synchronize_rcu(); - /* Rx/Tx/XDP Tx share the same napi context. */ - napi_disable(&rx_ring->q_vector->napi); - ixgbe_clean_tx_ring(tx_ring); if (xdp_ring) ixgbe_clean_tx_ring(xdp_ring); @@ -10452,9 +10488,6 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) tx_ring = adapter->tx_ring[ring]; xdp_ring = adapter->xdp_ring[ring]; - /* Rx/Tx/XDP Tx share the same napi context. */ - napi_enable(&rx_ring->q_vector->napi); - ixgbe_configure_tx_ring(adapter, tx_ring); if (xdp_ring) ixgbe_configure_tx_ring(adapter, xdp_ring); @@ -10463,6 +10496,11 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state); if (xdp_ring) clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state); + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_enable(&rx_ring->q_vector->napi); + ixgbe_irq_enable_queues(adapter, BIT_ULL(ring)); + IXGBE_WRITE_FLUSH(&adapter->hw); } /** @@ -10796,9 +10834,9 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = hw->mac.ops.reset_hw(hw); hw->phy.reset_if_overtemp = false; ixgbe_set_eee_capable(adapter); - if (err == IXGBE_ERR_SFP_NOT_PRESENT) { + if (err == -ENOENT) { err = 0; - } else if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) { + } else if (err == -EOPNOTSUPP) { e_dev_err("failed to load because an unsupported SFP+ or QSFP module type was detected.\n"); e_dev_err("Reload the driver after installing a supported module.\n"); goto err_sw_init; @@ -11015,7 +11053,7 @@ skip_sriov: /* reset the hardware with the new settings */ err = hw->mac.ops.start_hw(hw); - if (err == IXGBE_ERR_EEPROM_VERSION) { + if (err == -EACCES) { /* We are running on a pre-production device, log a warning */ e_dev_warn("This device is a pre-production adapter/LOM. " "Please be aware there may be issues associated " diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c index 5679293e5..fe7ef5773 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c @@ -24,7 +24,7 @@ s32 ixgbe_read_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 mbx_id) size = mbx->size; if (!mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; return mbx->ops->read(hw, msg, size, mbx_id); } @@ -43,10 +43,10 @@ s32 ixgbe_write_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 mbx_id) struct ixgbe_mbx_info *mbx = &hw->mbx; if (size > mbx->size) - return IXGBE_ERR_MBX; + return -EINVAL; if (!mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; return mbx->ops->write(hw, msg, size, mbx_id); } @@ -63,7 +63,7 @@ s32 ixgbe_check_for_msg(struct ixgbe_hw *hw, u16 mbx_id) struct ixgbe_mbx_info *mbx = &hw->mbx; if (!mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; return mbx->ops->check_for_msg(hw, mbx_id); } @@ -80,7 +80,7 @@ s32 ixgbe_check_for_ack(struct ixgbe_hw *hw, u16 mbx_id) struct ixgbe_mbx_info *mbx = &hw->mbx; if (!mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; return mbx->ops->check_for_ack(hw, mbx_id); } @@ -97,7 +97,7 @@ s32 ixgbe_check_for_rst(struct ixgbe_hw *hw, u16 mbx_id) struct ixgbe_mbx_info *mbx = &hw->mbx; if (!mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; return mbx->ops->check_for_rst(hw, mbx_id); } @@ -115,12 +115,12 @@ static s32 ixgbe_poll_for_msg(struct ixgbe_hw *hw, u16 mbx_id) int countdown = mbx->timeout; if (!countdown || !mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; while (mbx->ops->check_for_msg(hw, mbx_id)) { countdown--; if (!countdown) - return IXGBE_ERR_MBX; + return -EIO; udelay(mbx->usec_delay); } @@ -140,12 +140,12 @@ static s32 ixgbe_poll_for_ack(struct ixgbe_hw *hw, u16 mbx_id) int countdown = mbx->timeout; if (!countdown || !mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; while (mbx->ops->check_for_ack(hw, mbx_id)) { countdown--; if (!countdown) - return IXGBE_ERR_MBX; + return -EIO; udelay(mbx->usec_delay); } @@ -169,7 +169,7 @@ static s32 ixgbe_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, s32 ret_val; if (!mbx->ops) - return IXGBE_ERR_MBX; + return -EIO; ret_val = ixgbe_poll_for_msg(hw, mbx_id); if (ret_val) @@ -197,7 +197,7 @@ static s32 ixgbe_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, /* exit if either we can't write or there isn't a defined timeout */ if (!mbx->ops || !mbx->timeout) - return IXGBE_ERR_MBX; + return -EIO; /* send msg */ ret_val = mbx->ops->write(hw, msg, size, mbx_id); @@ -217,7 +217,7 @@ static s32 ixgbe_check_for_bit_pf(struct ixgbe_hw *hw, u32 mask, s32 index) return 0; } - return IXGBE_ERR_MBX; + return -EIO; } /** @@ -238,7 +238,7 @@ static s32 ixgbe_check_for_msg_pf(struct ixgbe_hw *hw, u16 vf_number) return 0; } - return IXGBE_ERR_MBX; + return -EIO; } /** @@ -259,7 +259,7 @@ static s32 ixgbe_check_for_ack_pf(struct ixgbe_hw *hw, u16 vf_number) return 0; } - return IXGBE_ERR_MBX; + return -EIO; } /** @@ -295,7 +295,7 @@ static s32 ixgbe_check_for_rst_pf(struct ixgbe_hw *hw, u16 vf_number) return 0; } - return IXGBE_ERR_MBX; + return -EIO; } /** @@ -317,7 +317,7 @@ static s32 ixgbe_obtain_mbx_lock_pf(struct ixgbe_hw *hw, u16 vf_number) if (p2v_mailbox & IXGBE_PFMAILBOX_PFU) return 0; - return IXGBE_ERR_MBX; + return -EIO; } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h index a148534d7..def067b15 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h @@ -7,7 +7,6 @@ #include "ixgbe_type.h" #define IXGBE_VFMAILBOX_SIZE 16 /* 16 32 bit words - 64 bytes */ -#define IXGBE_ERR_MBX -100 #define IXGBE_VFMAILBOX 0x002FC #define IXGBE_VFMBMEM 0x00200 diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index b0413904b..9d8b018b4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -102,7 +102,7 @@ s32 ixgbe_read_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, csum = ~csum; do { if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; ixgbe_i2c_start(hw); /* Device Address and write indication */ if (ixgbe_out_i2c_byte_ack(hw, addr)) @@ -150,7 +150,7 @@ fail: hw_dbg(hw, "I2C byte read combined error.\n"); } while (retry < max_retry); - return IXGBE_ERR_I2C; + return -EIO; } /** @@ -179,7 +179,7 @@ s32 ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, csum = ~csum; do { if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; ixgbe_i2c_start(hw); /* Device Address and write indication */ if (ixgbe_out_i2c_byte_ack(hw, addr)) @@ -215,7 +215,7 @@ fail: hw_dbg(hw, "I2C byte write combined error.\n"); } while (retry < max_retry); - return IXGBE_ERR_I2C; + return -EIO; } /** @@ -262,8 +262,8 @@ static bool ixgbe_probe_phy(struct ixgbe_hw *hw, u16 phy_addr) **/ s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw) { + u32 status = -EFAULT; u32 phy_addr; - u32 status = IXGBE_ERR_PHY_ADDR_INVALID; if (!hw->phy.phy_semaphore_mask) { if (hw->bus.lan_id) @@ -282,7 +282,7 @@ s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw) if (ixgbe_probe_phy(hw, phy_addr)) return 0; else - return IXGBE_ERR_PHY_ADDR_INVALID; + return -EFAULT; } for (phy_addr = 0; phy_addr < IXGBE_MAX_PHY_ADDR; phy_addr++) { @@ -405,8 +405,7 @@ s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw) return status; /* Don't reset PHY if it's shut down due to overtemp. */ - if (!hw->phy.reset_if_overtemp && - (IXGBE_ERR_OVERTEMP == hw->phy.ops.check_overtemp(hw))) + if (!hw->phy.reset_if_overtemp && hw->phy.ops.check_overtemp(hw)) return 0; /* Blocked by MNG FW so bail */ @@ -454,7 +453,7 @@ s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw) if (ctrl & MDIO_CTRL1_RESET) { hw_dbg(hw, "PHY reset polling failed to complete.\n"); - return IXGBE_ERR_RESET_FAILED; + return -EIO; } return 0; @@ -496,7 +495,7 @@ s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { hw_dbg(hw, "PHY address command did not complete.\n"); - return IXGBE_ERR_PHY; + return -EIO; } /* Address cycle complete, setup and write the read @@ -523,7 +522,7 @@ s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { hw_dbg(hw, "PHY read command didn't complete\n"); - return IXGBE_ERR_PHY; + return -EIO; } /* Read operation is complete. Get the data @@ -555,7 +554,7 @@ s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, phy_data); hw->mac.ops.release_swfw_sync(hw, gssr); } else { - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; } return status; @@ -600,7 +599,7 @@ s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { hw_dbg(hw, "PHY address cmd didn't complete\n"); - return IXGBE_ERR_PHY; + return -EIO; } /* @@ -628,7 +627,7 @@ s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { hw_dbg(hw, "PHY write cmd didn't complete\n"); - return IXGBE_ERR_PHY; + return -EIO; } return 0; @@ -653,7 +652,7 @@ s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, phy_data); hw->mac.ops.release_swfw_sync(hw, gssr); } else { - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; } return status; @@ -1299,7 +1298,7 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) if ((phy_data & MDIO_CTRL1_RESET) != 0) { hw_dbg(hw, "PHY reset did not complete.\n"); - return IXGBE_ERR_PHY; + return -EIO; } /* Get init offsets */ @@ -1356,12 +1355,12 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) hw_dbg(hw, "SOL\n"); } else { hw_dbg(hw, "Bad control value\n"); - return IXGBE_ERR_PHY; + return -EIO; } break; default: hw_dbg(hw, "Bad control type\n"); - return IXGBE_ERR_PHY; + return -EIO; } } @@ -1369,7 +1368,7 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) err_eeprom: hw_err(hw, "eeprom read at offset %d failed\n", data_offset); - return IXGBE_ERR_PHY; + return -EIO; } /** @@ -1387,10 +1386,10 @@ s32 ixgbe_identify_module_generic(struct ixgbe_hw *hw) return ixgbe_identify_qsfp_module_generic(hw); default: hw->phy.sfp_type = ixgbe_sfp_type_not_present; - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; } - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; } /** @@ -1415,7 +1414,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_fiber) { hw->phy.sfp_type = ixgbe_sfp_type_not_present; - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; } /* LAN ID is needed for sfp_type determination */ @@ -1430,7 +1429,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) if (identifier != IXGBE_SFF_IDENTIFIER_SFP) { hw->phy.type = ixgbe_phy_sfp_unsupported; - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_1GBE_COMP_CODES, @@ -1621,7 +1620,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1)) { hw->phy.type = ixgbe_phy_sfp_unsupported; - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } /* Anything else 82598-based is supported */ @@ -1645,7 +1644,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) } hw_dbg(hw, "SFP+ module not supported\n"); hw->phy.type = ixgbe_phy_sfp_unsupported; - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } return 0; @@ -1655,7 +1654,7 @@ err_read_i2c_eeprom: hw->phy.id = 0; hw->phy.type = ixgbe_phy_unknown; } - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; } /** @@ -1682,7 +1681,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_fiber_qsfp) { hw->phy.sfp_type = ixgbe_sfp_type_not_present; - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; } /* LAN ID is needed for sfp_type determination */ @@ -1696,7 +1695,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) if (identifier != IXGBE_SFF_IDENTIFIER_QSFP_PLUS) { hw->phy.type = ixgbe_phy_sfp_unsupported; - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } hw->phy.id = identifier; @@ -1764,7 +1763,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) } else { /* unsupported module type */ hw->phy.type = ixgbe_phy_sfp_unsupported; - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } } @@ -1824,7 +1823,7 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) } hw_dbg(hw, "QSFP module not supported\n"); hw->phy.type = ixgbe_phy_sfp_unsupported; - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } return 0; } @@ -1835,7 +1834,7 @@ err_read_i2c_eeprom: hw->phy.id = 0; hw->phy.type = ixgbe_phy_unknown; - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; } /** @@ -1855,14 +1854,14 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, u16 sfp_type = hw->phy.sfp_type; if (hw->phy.sfp_type == ixgbe_sfp_type_unknown) - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; if (hw->phy.sfp_type == ixgbe_sfp_type_not_present) - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; if ((hw->device_id == IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM) && (hw->phy.sfp_type == ixgbe_sfp_type_da_cu)) - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; /* * Limiting active cables and 1G Phys must be initialized as @@ -1883,11 +1882,11 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, if (hw->eeprom.ops.read(hw, IXGBE_PHY_INIT_OFFSET_NL, list_offset)) { hw_err(hw, "eeprom read at %d failed\n", IXGBE_PHY_INIT_OFFSET_NL); - return IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT; + return -EIO; } if ((!*list_offset) || (*list_offset == 0xFFFF)) - return IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT; + return -EIO; /* Shift offset to first ID word */ (*list_offset)++; @@ -1906,7 +1905,7 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, goto err_phy; if ((!*data_offset) || (*data_offset == 0xFFFF)) { hw_dbg(hw, "SFP+ module not supported\n"); - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } else { break; } @@ -1919,14 +1918,14 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, if (sfp_id == IXGBE_PHY_INIT_END_NL) { hw_dbg(hw, "No matching SFP+ module found\n"); - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } return 0; err_phy: hw_err(hw, "eeprom read at offset %d failed\n", *list_offset); - return IXGBE_ERR_PHY; + return -EIO; } /** @@ -2021,7 +2020,7 @@ static s32 ixgbe_read_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset, do { if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; ixgbe_i2c_start(hw); @@ -2137,7 +2136,7 @@ static s32 ixgbe_write_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset, u32 swfw_mask = hw->phy.phy_semaphore_mask; if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; do { ixgbe_i2c_start(hw); @@ -2379,7 +2378,7 @@ static s32 ixgbe_get_i2c_ack(struct ixgbe_hw *hw) if (ack == 1) { hw_dbg(hw, "I2C ack was not received.\n"); - status = IXGBE_ERR_I2C; + status = -EIO; } ixgbe_lower_i2c_clk(hw, &i2cctl); @@ -2451,7 +2450,7 @@ static s32 ixgbe_clock_out_i2c_bit(struct ixgbe_hw *hw, bool data) udelay(IXGBE_I2C_T_LOW); } else { hw_dbg(hw, "I2C data was not set to %X\n", data); - return IXGBE_ERR_I2C; + return -EIO; } return 0; @@ -2547,7 +2546,7 @@ static s32 ixgbe_set_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl, bool data) *i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); if (data != ixgbe_get_i2c_data(hw, i2cctl)) { hw_dbg(hw, "Error - I2C data was not set to %X.\n", data); - return IXGBE_ERR_I2C; + return -EIO; } return 0; @@ -2617,22 +2616,24 @@ static void ixgbe_i2c_bus_clear(struct ixgbe_hw *hw) * @hw: pointer to hardware structure * * Checks if the LASI temp alarm status was triggered due to overtemp + * + * Return true when an overtemp event detected, otherwise false. **/ -s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw) +bool ixgbe_tn_check_overtemp(struct ixgbe_hw *hw) { u16 phy_data = 0; + u32 status; if (hw->device_id != IXGBE_DEV_ID_82599_T3_LOM) - return 0; + return false; /* Check that the LASI temp alarm status was triggered */ - hw->phy.ops.read_reg(hw, IXGBE_TN_LASI_STATUS_REG, - MDIO_MMD_PMAPMD, &phy_data); - - if (!(phy_data & IXGBE_TN_LASI_STATUS_TEMP_ALARM)) - return 0; + status = hw->phy.ops.read_reg(hw, IXGBE_TN_LASI_STATUS_REG, + MDIO_MMD_PMAPMD, &phy_data); + if (status) + return false; - return IXGBE_ERR_OVERTEMP; + return !!(phy_data & IXGBE_TN_LASI_STATUS_TEMP_ALARM); } /** ixgbe_set_copper_phy_power - Control power for copper phy diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h index 6544c4539..ef72729d7 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h @@ -155,7 +155,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw); s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, u16 *list_offset, u16 *data_offset); -s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw); +bool ixgbe_tn_check_overtemp(struct ixgbe_hw *hw); s32 ixgbe_read_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, u8 dev_addr, u8 *data); s32 ixgbe_read_i2c_byte_generic_unlocked(struct ixgbe_hw *hw, u8 byte_offset, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 5eba08669..0cd8bec6a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -1279,7 +1279,7 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) break; default: e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]); - retval = IXGBE_ERR_MBX; + retval = -EIO; break; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 2be1c4c72..e84dbf6a3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -1247,7 +1247,7 @@ struct ixgbe_nvm_version { #define IXGBE_PSRTYPE_RQPL_SHIFT 29 /* CTRL Bit Masks */ -#define IXGBE_CTRL_GIO_DIS 0x00000004 /* Global IO Master Disable bit */ +#define IXGBE_CTRL_GIO_DIS 0x00000004 /* Global IO Primary Disable bit */ #define IXGBE_CTRL_LNK_RST 0x00000008 /* Link Reset. Resets everything. */ #define IXGBE_CTRL_RST 0x04000000 /* Reset (SW) */ #define IXGBE_CTRL_RST_MASK (IXGBE_CTRL_LNK_RST | IXGBE_CTRL_RST) @@ -1810,7 +1810,7 @@ enum { /* STATUS Bit Masks */ #define IXGBE_STATUS_LAN_ID 0x0000000C /* LAN ID */ #define IXGBE_STATUS_LAN_ID_SHIFT 2 /* LAN ID Shift*/ -#define IXGBE_STATUS_GIO 0x00080000 /* GIO Master Enable Status */ +#define IXGBE_STATUS_GIO 0x00080000 /* GIO Primary Enable Status */ #define IXGBE_STATUS_LAN_ID_0 0x00000000 /* LAN ID 0 */ #define IXGBE_STATUS_LAN_ID_1 0x00000004 /* LAN ID 1 */ @@ -2192,8 +2192,8 @@ enum { #define IXGBE_PCIDEVCTRL2_4_8s 0xd #define IXGBE_PCIDEVCTRL2_17_34s 0xe -/* Number of 100 microseconds we wait for PCI Express master disable */ -#define IXGBE_PCI_MASTER_DISABLE_TIMEOUT 800 +/* Number of 100 microseconds we wait for PCI Express primary disable */ +#define IXGBE_PCI_PRIMARY_DISABLE_TIMEOUT 800 /* RAH */ #define IXGBE_RAH_VIND_MASK 0x003C0000 @@ -3505,10 +3505,10 @@ struct ixgbe_phy_operations { s32 (*read_i2c_sff8472)(struct ixgbe_hw *, u8 , u8 *); s32 (*read_i2c_eeprom)(struct ixgbe_hw *, u8 , u8 *); s32 (*write_i2c_eeprom)(struct ixgbe_hw *, u8, u8); - s32 (*check_overtemp)(struct ixgbe_hw *); + bool (*check_overtemp)(struct ixgbe_hw *); s32 (*set_phy_power)(struct ixgbe_hw *, bool on); s32 (*enter_lplu)(struct ixgbe_hw *); - s32 (*handle_lasi)(struct ixgbe_hw *hw); + s32 (*handle_lasi)(struct ixgbe_hw *hw, bool *); s32 (*read_i2c_byte_unlocked)(struct ixgbe_hw *, u8 offset, u8 addr, u8 *value); s32 (*write_i2c_byte_unlocked)(struct ixgbe_hw *, u8 offset, u8 addr, @@ -3661,45 +3661,6 @@ struct ixgbe_info { const u32 *mvals; }; - -/* Error Codes */ -#define IXGBE_ERR_EEPROM -1 -#define IXGBE_ERR_EEPROM_CHECKSUM -2 -#define IXGBE_ERR_PHY -3 -#define IXGBE_ERR_CONFIG -4 -#define IXGBE_ERR_PARAM -5 -#define IXGBE_ERR_MAC_TYPE -6 -#define IXGBE_ERR_UNKNOWN_PHY -7 -#define IXGBE_ERR_LINK_SETUP -8 -#define IXGBE_ERR_ADAPTER_STOPPED -9 -#define IXGBE_ERR_INVALID_MAC_ADDR -10 -#define IXGBE_ERR_DEVICE_NOT_SUPPORTED -11 -#define IXGBE_ERR_MASTER_REQUESTS_PENDING -12 -#define IXGBE_ERR_INVALID_LINK_SETTINGS -13 -#define IXGBE_ERR_AUTONEG_NOT_COMPLETE -14 -#define IXGBE_ERR_RESET_FAILED -15 -#define IXGBE_ERR_SWFW_SYNC -16 -#define IXGBE_ERR_PHY_ADDR_INVALID -17 -#define IXGBE_ERR_I2C -18 -#define IXGBE_ERR_SFP_NOT_SUPPORTED -19 -#define IXGBE_ERR_SFP_NOT_PRESENT -20 -#define IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT -21 -#define IXGBE_ERR_NO_SAN_ADDR_PTR -22 -#define IXGBE_ERR_FDIR_REINIT_FAILED -23 -#define IXGBE_ERR_EEPROM_VERSION -24 -#define IXGBE_ERR_NO_SPACE -25 -#define IXGBE_ERR_OVERTEMP -26 -#define IXGBE_ERR_FC_NOT_NEGOTIATED -27 -#define IXGBE_ERR_FC_NOT_SUPPORTED -28 -#define IXGBE_ERR_SFP_SETUP_NOT_COMPLETE -30 -#define IXGBE_ERR_PBA_SECTION -31 -#define IXGBE_ERR_INVALID_ARGUMENT -32 -#define IXGBE_ERR_HOST_INTERFACE_COMMAND -33 -#define IXGBE_ERR_FDIR_CMD_INCOMPLETE -38 -#define IXGBE_ERR_FW_RESP_INVALID -39 -#define IXGBE_ERR_TOKEN_RETRY -40 -#define IXGBE_NOT_IMPLEMENTED 0x7FFFFFFF - #define IXGBE_FUSES0_GROUP(_i) (0x11158 + ((_i) * 4)) #define IXGBE_FUSES0_300MHZ BIT(5) #define IXGBE_FUSES0_REV_MASK (3u << 6) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index 4b93ba149..fb4ced963 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -84,7 +84,7 @@ mac_reset_top: status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); if (status) { hw_dbg(hw, "semaphore failed with %d", status); - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; } ctrl = IXGBE_CTRL_RST; @@ -103,7 +103,7 @@ mac_reset_top: } if (ctrl & IXGBE_CTRL_RST_MASK) { - status = IXGBE_ERR_RESET_FAILED; + status = -EIO; hw_dbg(hw, "Reset polling failed to complete.\n"); } msleep(100); @@ -220,7 +220,7 @@ static s32 ixgbe_read_eerd_X540(struct ixgbe_hw *hw, u16 offset, u16 *data) s32 status; if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = ixgbe_read_eerd_generic(hw, offset, data); @@ -243,7 +243,7 @@ static s32 ixgbe_read_eerd_buffer_X540(struct ixgbe_hw *hw, s32 status; if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = ixgbe_read_eerd_buffer_generic(hw, offset, words, data); @@ -264,7 +264,7 @@ static s32 ixgbe_write_eewr_X540(struct ixgbe_hw *hw, u16 offset, u16 data) s32 status; if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = ixgbe_write_eewr_generic(hw, offset, data); @@ -287,7 +287,7 @@ static s32 ixgbe_write_eewr_buffer_X540(struct ixgbe_hw *hw, s32 status; if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = ixgbe_write_eewr_buffer_generic(hw, offset, words, data); @@ -324,7 +324,7 @@ static s32 ixgbe_calc_eeprom_checksum_X540(struct ixgbe_hw *hw) for (i = 0; i < checksum_last_word; i++) { if (ixgbe_read_eerd_generic(hw, i, &word)) { hw_dbg(hw, "EEPROM read failed\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } checksum += word; } @@ -349,7 +349,7 @@ static s32 ixgbe_calc_eeprom_checksum_X540(struct ixgbe_hw *hw) if (ixgbe_read_eerd_generic(hw, pointer, &length)) { hw_dbg(hw, "EEPROM read failed\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } /* Skip pointer section if length is invalid. */ @@ -360,7 +360,7 @@ static s32 ixgbe_calc_eeprom_checksum_X540(struct ixgbe_hw *hw) for (j = pointer + 1; j <= pointer + length; j++) { if (ixgbe_read_eerd_generic(hw, j, &word)) { hw_dbg(hw, "EEPROM read failed\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } checksum += word; } @@ -397,7 +397,7 @@ static s32 ixgbe_validate_eeprom_checksum_X540(struct ixgbe_hw *hw, } if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = hw->eeprom.ops.calc_checksum(hw); if (status < 0) @@ -418,7 +418,7 @@ static s32 ixgbe_validate_eeprom_checksum_X540(struct ixgbe_hw *hw, */ if (read_checksum != checksum) { hw_dbg(hw, "Invalid EEPROM checksum"); - status = IXGBE_ERR_EEPROM_CHECKSUM; + status = -EIO; } /* If the user cares, return the calculated checksum */ @@ -455,7 +455,7 @@ static s32 ixgbe_update_eeprom_checksum_X540(struct ixgbe_hw *hw) } if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = hw->eeprom.ops.calc_checksum(hw); if (status < 0) @@ -490,7 +490,7 @@ static s32 ixgbe_update_flash_X540(struct ixgbe_hw *hw) s32 status; status = ixgbe_poll_flash_update_done_X540(hw); - if (status == IXGBE_ERR_EEPROM) { + if (status == -EIO) { hw_dbg(hw, "Flash update time out\n"); return status; } @@ -540,7 +540,7 @@ static s32 ixgbe_poll_flash_update_done_X540(struct ixgbe_hw *hw) return 0; udelay(5); } - return IXGBE_ERR_EEPROM; + return -EIO; } /** @@ -575,7 +575,7 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) * SW_FW_SYNC bits (not just NVM) */ if (ixgbe_get_swfw_sync_semaphore(hw)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw)); if (!(swfw_sync & (fwmask | swmask | hwmask))) { @@ -599,7 +599,7 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) * bits in the SW_FW_SYNC register. */ if (ixgbe_get_swfw_sync_semaphore(hw)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw)); if (swfw_sync & (fwmask | hwmask)) { swfw_sync |= swmask; @@ -622,11 +622,11 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) rmask |= IXGBE_GSSR_I2C_MASK; ixgbe_release_swfw_sync_X540(hw, rmask); ixgbe_release_swfw_sync_semaphore(hw); - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; } ixgbe_release_swfw_sync_semaphore(hw); - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; } /** @@ -680,7 +680,7 @@ static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw) if (i == timeout) { hw_dbg(hw, "Software semaphore SMBI between device drivers not granted.\n"); - return IXGBE_ERR_EEPROM; + return -EIO; } /* Now get the semaphore between SW/FW through the REGSMP bit */ @@ -697,7 +697,7 @@ static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw) */ hw_dbg(hw, "REGSMP Software NVM semaphore not granted\n"); ixgbe_release_swfw_sync_semaphore(hw); - return IXGBE_ERR_EEPROM; + return -EIO; } /** @@ -768,7 +768,7 @@ s32 ixgbe_blink_led_start_X540(struct ixgbe_hw *hw, u32 index) bool link_up; if (index > 3) - return IXGBE_ERR_PARAM; + return -EINVAL; /* Link should be up in order for the blink bit in the LED control * register to work. Force link and speed in the MAC if link is down. @@ -804,7 +804,7 @@ s32 ixgbe_blink_led_stop_X540(struct ixgbe_hw *hw, u32 index) u32 ledctl_reg; if (index > 3) - return IXGBE_ERR_PARAM; + return -EINVAL; /* Restore the LED to its default value. */ ledctl_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 37f2bc6de..9347dc786 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -206,13 +206,13 @@ static s32 ixgbe_reset_cs4227(struct ixgbe_hw *hw) } if (retry == IXGBE_CS4227_RETRIES) { hw_err(hw, "CS4227 reset did not complete\n"); - return IXGBE_ERR_PHY; + return -EIO; } status = ixgbe_read_cs4227(hw, IXGBE_CS4227_EEPROM_STATUS, &value); if (status || !(value & IXGBE_CS4227_EEPROM_LOAD_OK)) { hw_err(hw, "CS4227 EEPROM did not load successfully\n"); - return IXGBE_ERR_PHY; + return -EIO; } return 0; @@ -350,13 +350,13 @@ static s32 ixgbe_identify_phy_x550em(struct ixgbe_hw *hw) static s32 ixgbe_read_phy_reg_x550em(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, u16 *phy_data) { - return IXGBE_NOT_IMPLEMENTED; + return -EOPNOTSUPP; } static s32 ixgbe_write_phy_reg_x550em(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, u16 phy_data) { - return IXGBE_NOT_IMPLEMENTED; + return -EOPNOTSUPP; } /** @@ -463,7 +463,7 @@ s32 ixgbe_fw_phy_activity(struct ixgbe_hw *hw, u16 activity, --retries; } while (retries > 0); - return IXGBE_ERR_HOST_INTERFACE_COMMAND; + return -EIO; } static const struct { @@ -511,7 +511,7 @@ static s32 ixgbe_get_phy_id_fw(struct ixgbe_hw *hw) hw->phy.id |= phy_id_lo & IXGBE_PHY_REVISION_MASK; hw->phy.revision = phy_id_lo & ~IXGBE_PHY_REVISION_MASK; if (!hw->phy.id || hw->phy.id == IXGBE_PHY_REVISION_MASK) - return IXGBE_ERR_PHY_ADDR_INVALID; + return -EFAULT; hw->phy.autoneg_advertised = hw->phy.speeds_supported; hw->phy.eee_speeds_supported = IXGBE_LINK_SPEED_100_FULL | @@ -568,7 +568,7 @@ static s32 ixgbe_setup_fw_link(struct ixgbe_hw *hw) if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { hw_err(hw, "rx_pause not valid in strict IEEE mode\n"); - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; } switch (hw->fc.requested_mode) { @@ -600,8 +600,10 @@ static s32 ixgbe_setup_fw_link(struct ixgbe_hw *hw) rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_SETUP_LINK, &setup); if (rc) return rc; + if (setup[0] == FW_PHY_ACT_SETUP_LINK_RSP_DOWN) - return IXGBE_ERR_OVERTEMP; + return -EIO; + return 0; } @@ -675,7 +677,7 @@ static s32 ixgbe_iosf_wait(struct ixgbe_hw *hw, u32 *ctrl) *ctrl = command; if (i == IXGBE_MDIO_COMMAND_TIMEOUT) { hw_dbg(hw, "IOSF wait timed out\n"); - return IXGBE_ERR_PHY; + return -EIO; } return 0; @@ -715,7 +717,8 @@ static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >> IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT; hw_dbg(hw, "Failed to read, error %x\n", error); - return IXGBE_ERR_PHY; + ret = -EIO; + goto out; } if (!ret) @@ -750,9 +753,9 @@ static s32 ixgbe_get_phy_token(struct ixgbe_hw *hw) if (token_cmd.hdr.cmd_or_resp.ret_status == FW_PHY_TOKEN_OK) return 0; if (token_cmd.hdr.cmd_or_resp.ret_status != FW_PHY_TOKEN_RETRY) - return IXGBE_ERR_FW_RESP_INVALID; + return -EIO; - return IXGBE_ERR_TOKEN_RETRY; + return -EAGAIN; } /** @@ -778,7 +781,7 @@ static s32 ixgbe_put_phy_token(struct ixgbe_hw *hw) return status; if (token_cmd.hdr.cmd_or_resp.ret_status == FW_PHY_TOKEN_OK) return 0; - return IXGBE_ERR_FW_RESP_INVALID; + return -EIO; } /** @@ -942,7 +945,7 @@ static s32 ixgbe_checksum_ptr_x550(struct ixgbe_hw *hw, u16 ptr, local_buffer = buf; } else { if (buffer_size < ptr) - return IXGBE_ERR_PARAM; + return -EINVAL; local_buffer = &buffer[ptr]; } @@ -960,7 +963,7 @@ static s32 ixgbe_checksum_ptr_x550(struct ixgbe_hw *hw, u16 ptr, } if (buffer && ((u32)start + (u32)length > buffer_size)) - return IXGBE_ERR_PARAM; + return -EINVAL; for (i = start; length; i++, length--) { if (i == bufsz && !buffer) { @@ -1012,7 +1015,7 @@ static s32 ixgbe_calc_checksum_X550(struct ixgbe_hw *hw, u16 *buffer, local_buffer = eeprom_ptrs; } else { if (buffer_size < IXGBE_EEPROM_LAST_WORD) - return IXGBE_ERR_PARAM; + return -EINVAL; local_buffer = buffer; } @@ -1148,7 +1151,7 @@ static s32 ixgbe_validate_eeprom_checksum_X550(struct ixgbe_hw *hw, * calculated checksum */ if (read_checksum != checksum) { - status = IXGBE_ERR_EEPROM_CHECKSUM; + status = -EIO; hw_dbg(hw, "Invalid EEPROM checksum"); } @@ -1203,7 +1206,7 @@ static s32 ixgbe_write_ee_hostif_X550(struct ixgbe_hw *hw, u16 offset, u16 data) hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); } else { hw_dbg(hw, "write ee hostif failed to get semaphore"); - status = IXGBE_ERR_SWFW_SYNC; + status = -EBUSY; } return status; @@ -1415,7 +1418,7 @@ static s32 ixgbe_write_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >> IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT; hw_dbg(hw, "Failed to write, error %x\n", error); - return IXGBE_ERR_PHY; + return -EIO; } out: @@ -1558,7 +1561,7 @@ static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed) /* iXFI is only supported with X552 */ if (mac->type != ixgbe_mac_X550EM_x) - return IXGBE_ERR_LINK_SETUP; + return -EIO; /* Disable AN and force speed to 10G Serial. */ status = ixgbe_read_iosf_sb_reg_x550(hw, @@ -1580,7 +1583,7 @@ static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed) break; default: /* Other link speeds are not supported by internal KR PHY. */ - return IXGBE_ERR_LINK_SETUP; + return -EINVAL; } status = ixgbe_write_iosf_sb_reg_x550(hw, @@ -1611,7 +1614,7 @@ static s32 ixgbe_supported_sfp_modules_X550em(struct ixgbe_hw *hw, bool *linear) { switch (hw->phy.sfp_type) { case ixgbe_sfp_type_not_present: - return IXGBE_ERR_SFP_NOT_PRESENT; + return -ENOENT; case ixgbe_sfp_type_da_cu_core0: case ixgbe_sfp_type_da_cu_core1: *linear = true; @@ -1630,7 +1633,7 @@ static s32 ixgbe_supported_sfp_modules_X550em(struct ixgbe_hw *hw, bool *linear) case ixgbe_sfp_type_1g_cu_core0: case ixgbe_sfp_type_1g_cu_core1: default: - return IXGBE_ERR_SFP_NOT_SUPPORTED; + return -EOPNOTSUPP; } return 0; @@ -1660,7 +1663,7 @@ ixgbe_setup_mac_link_sfp_x550em(struct ixgbe_hw *hw, * there is no reason to configure CS4227 and SFP not present error is * not accepted in the setup MAC link flow. */ - if (status == IXGBE_ERR_SFP_NOT_PRESENT) + if (status == -ENOENT) return 0; if (status) @@ -1718,7 +1721,7 @@ static s32 ixgbe_setup_sfi_x550a(struct ixgbe_hw *hw, ixgbe_link_speed *speed) break; default: /* Other link speeds are not supported by internal PHY. */ - return IXGBE_ERR_LINK_SETUP; + return -EINVAL; } status = mac->ops.write_iosf_sb_reg(hw, @@ -1753,7 +1756,7 @@ ixgbe_setup_mac_link_sfp_n(struct ixgbe_hw *hw, ixgbe_link_speed speed, /* If no SFP module present, then return success. Return success since * SFP not present error is not excepted in the setup MAC link flow. */ - if (ret_val == IXGBE_ERR_SFP_NOT_PRESENT) + if (ret_val == -ENOENT) return 0; if (ret_val) @@ -1803,7 +1806,7 @@ ixgbe_setup_mac_link_sfp_x550a(struct ixgbe_hw *hw, ixgbe_link_speed speed, /* If no SFP module present, then return success. Return success since * SFP not present error is not excepted in the setup MAC link flow. */ - if (ret_val == IXGBE_ERR_SFP_NOT_PRESENT) + if (ret_val == -ENOENT) return 0; if (ret_val) @@ -1813,7 +1816,7 @@ ixgbe_setup_mac_link_sfp_x550a(struct ixgbe_hw *hw, ixgbe_link_speed speed, ixgbe_setup_kr_speed_x550em(hw, speed); if (hw->phy.mdio.prtad == MDIO_PRTAD_NONE) - return IXGBE_ERR_PHY_ADDR_INVALID; + return -EFAULT; /* Get external PHY SKU id */ ret_val = hw->phy.ops.read_reg(hw, IXGBE_CS4227_EFUSE_PDF_SKU, @@ -1912,7 +1915,7 @@ static s32 ixgbe_check_link_t_X550em(struct ixgbe_hw *hw, u16 i, autoneg_status; if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper) - return IXGBE_ERR_CONFIG; + return -EIO; status = ixgbe_check_mac_link_generic(hw, speed, link_up, link_up_wait_to_complete); @@ -2095,9 +2098,9 @@ static s32 ixgbe_setup_sgmii_fw(struct ixgbe_hw *hw, ixgbe_link_speed speed, */ static void ixgbe_fc_autoneg_sgmii_x550em_a(struct ixgbe_hw *hw) { - s32 status = IXGBE_ERR_FC_NOT_NEGOTIATED; u32 info[FW_PHY_ACT_DATA_COUNT] = { 0 }; ixgbe_link_speed speed; + s32 status = -EIO; bool link_up; /* AN should have completed when the cable was plugged in. @@ -2115,7 +2118,7 @@ static void ixgbe_fc_autoneg_sgmii_x550em_a(struct ixgbe_hw *hw) /* Check if auto-negotiation has completed */ status = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_GET_LINK_INFO, &info); if (status || !(info[0] & FW_PHY_ACT_GET_LINK_INFO_AN_COMPLETE)) { - status = IXGBE_ERR_FC_NOT_NEGOTIATED; + status = -EIO; goto out; } @@ -2319,18 +2322,18 @@ static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw, * @hw: pointer to hardware structure * @lsc: pointer to boolean flag which indicates whether external Base T * PHY interrupt is lsc + * @is_overtemp: indicate whether an overtemp event encountered * * Determime if external Base T PHY interrupt cause is high temperature * failure alarm or link status change. - * - * Return IXGBE_ERR_OVERTEMP if interrupt is high temperature - * failure alarm, else return PHY access status. **/ -static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) +static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc, + bool *is_overtemp) { u32 status; u16 reg; + *is_overtemp = false; *lsc = false; /* Vendor alarm triggered */ @@ -2362,7 +2365,8 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) if (reg & IXGBE_MDIO_GLOBAL_ALM_1_HI_TMP_FAIL) { /* power down the PHY in case the PHY FW didn't already */ ixgbe_set_copper_phy_power(hw, false); - return IXGBE_ERR_OVERTEMP; + *is_overtemp = true; + return -EIO; } if (reg & IXGBE_MDIO_GLOBAL_ALM_1_DEV_FAULT) { /* device fault alarm triggered */ @@ -2376,7 +2380,8 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) if (reg == IXGBE_MDIO_GLOBAL_FAULT_MSG_HI_TMP) { /* power down the PHY in case the PHY FW didn't */ ixgbe_set_copper_phy_power(hw, false); - return IXGBE_ERR_OVERTEMP; + *is_overtemp = true; + return -EIO; } } @@ -2412,12 +2417,12 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) **/ static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw) { + bool lsc, overtemp; u32 status; u16 reg; - bool lsc; /* Clear interrupt flags */ - status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc); + status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc, &overtemp); /* Enable link status change alarm */ @@ -2496,21 +2501,20 @@ static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw) /** * ixgbe_handle_lasi_ext_t_x550em - Handle external Base T PHY interrupt * @hw: pointer to hardware structure + * @is_overtemp: indicate whether an overtemp event encountered * * Handle external Base T PHY interrupt. If high temperature * failure alarm then return error, else if link status change * then setup internal/external PHY link - * - * Return IXGBE_ERR_OVERTEMP if interrupt is high temperature - * failure alarm, else return PHY access status. **/ -static s32 ixgbe_handle_lasi_ext_t_x550em(struct ixgbe_hw *hw) +static s32 ixgbe_handle_lasi_ext_t_x550em(struct ixgbe_hw *hw, + bool *is_overtemp) { struct ixgbe_phy_info *phy = &hw->phy; bool lsc; u32 status; - status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc); + status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc, is_overtemp); if (status) return status; @@ -2642,7 +2646,7 @@ static s32 ixgbe_setup_internal_phy_t_x550em(struct ixgbe_hw *hw) u16 speed; if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper) - return IXGBE_ERR_CONFIG; + return -EIO; if (!(hw->mac.type == ixgbe_mac_X550EM_x && !(hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE))) { @@ -2685,7 +2689,7 @@ static s32 ixgbe_setup_internal_phy_t_x550em(struct ixgbe_hw *hw) break; default: /* Internal PHY does not support anything else */ - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; } return ixgbe_setup_ixfi_x550em(hw, &force_speed); @@ -2717,7 +2721,7 @@ static s32 ixgbe_led_on_t_x550em(struct ixgbe_hw *hw, u32 led_idx) u16 phy_data; if (led_idx >= IXGBE_X557_MAX_LED_INDEX) - return IXGBE_ERR_PARAM; + return -EINVAL; /* To turn on the LED, set mode to ON. */ hw->phy.ops.read_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx, @@ -2739,7 +2743,7 @@ static s32 ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx) u16 phy_data; if (led_idx >= IXGBE_X557_MAX_LED_INDEX) - return IXGBE_ERR_PARAM; + return -EINVAL; /* To turn on the LED, set mode to ON. */ hw->phy.ops.read_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx, @@ -2763,8 +2767,9 @@ static s32 ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx) * * Sends driver version number to firmware through the manageability * block. On success return 0 - * else returns IXGBE_ERR_SWFW_SYNC when encountering an error acquiring - * semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails. + * else returns -EBUSY when encountering an error acquiring + * semaphore, -EIO when command fails or -ENIVAL when incorrect + * params passed. **/ static s32 ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, u8 build, u8 sub, u16 len, @@ -2775,7 +2780,7 @@ static s32 ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, int i; if (!len || !driver_ver || (len > sizeof(fw_cmd.driver_string))) - return IXGBE_ERR_INVALID_ARGUMENT; + return -EINVAL; fw_cmd.hdr.cmd = FW_CEM_CMD_DRIVER_INFO; fw_cmd.hdr.buf_len = FW_CEM_CMD_DRIVER_INFO_LEN + len; @@ -2800,7 +2805,7 @@ static s32 ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, if (fw_cmd.hdr.cmd_or_resp.ret_status != FW_CEM_RESP_STATUS_SUCCESS) - return IXGBE_ERR_HOST_INTERFACE_COMMAND; + return -EIO; return 0; } @@ -2857,7 +2862,7 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw) /* Validate the requested mode */ if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { hw_err(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n"); - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; } /* 10gig parts do not have a word in the EEPROM to determine the @@ -2892,7 +2897,7 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw) break; default: hw_err(hw, "Flow control param set incorrectly\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } switch (hw->device_id) { @@ -2936,8 +2941,8 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw) static void ixgbe_fc_autoneg_backplane_x550em_a(struct ixgbe_hw *hw) { u32 link_s1, lp_an_page_low, an_cntl_1; - s32 status = IXGBE_ERR_FC_NOT_NEGOTIATED; ixgbe_link_speed speed; + s32 status = -EIO; bool link_up; /* AN should have completed when the cable was plugged in. @@ -2963,7 +2968,7 @@ static void ixgbe_fc_autoneg_backplane_x550em_a(struct ixgbe_hw *hw) if (status || (link_s1 & IXGBE_KRM_LINK_S1_MAC_AN_COMPLETE) == 0) { hw_dbg(hw, "Auto-Negotiation did not complete\n"); - status = IXGBE_ERR_FC_NOT_NEGOTIATED; + status = -EIO; goto out; } @@ -3137,21 +3142,23 @@ static s32 ixgbe_reset_phy_fw(struct ixgbe_hw *hw) /** * ixgbe_check_overtemp_fw - Check firmware-controlled PHYs for overtemp * @hw: pointer to hardware structure + * + * Return true when an overtemp event detected, otherwise false. */ -static s32 ixgbe_check_overtemp_fw(struct ixgbe_hw *hw) +static bool ixgbe_check_overtemp_fw(struct ixgbe_hw *hw) { u32 store[FW_PHY_ACT_DATA_COUNT] = { 0 }; s32 rc; rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_GET_LINK_INFO, &store); if (rc) - return rc; + return false; if (store[0] & FW_PHY_ACT_GET_LINK_INFO_TEMP) { ixgbe_shutdown_fw_phy(hw); - return IXGBE_ERR_OVERTEMP; + return true; } - return 0; + return false; } /** @@ -3201,8 +3208,7 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) /* Identify the PHY or SFP module */ ret_val = phy->ops.identify(hw); - if (ret_val == IXGBE_ERR_SFP_NOT_SUPPORTED || - ret_val == IXGBE_ERR_PHY_ADDR_INVALID) + if (ret_val == -EOPNOTSUPP || ret_val == -EFAULT) return ret_val; /* Setup function pointers based on detected hardware */ @@ -3410,8 +3416,7 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) /* PHY ops must be identified and initialized prior to reset */ status = hw->phy.ops.init(hw); - if (status == IXGBE_ERR_SFP_NOT_SUPPORTED || - status == IXGBE_ERR_PHY_ADDR_INVALID) + if (status == -EOPNOTSUPP || status == -EFAULT) return status; /* start the external PHY */ @@ -3427,7 +3432,7 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) hw->phy.sfp_setup_needed = false; } - if (status == IXGBE_ERR_SFP_NOT_SUPPORTED) + if (status == -EOPNOTSUPP) return status; /* Reset PHY */ @@ -3451,7 +3456,7 @@ mac_reset_top: status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); if (status) { hw_dbg(hw, "semaphore failed with %d", status); - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; } ctrl |= IXGBE_READ_REG(hw, IXGBE_CTRL); @@ -3469,7 +3474,7 @@ mac_reset_top: } if (ctrl & IXGBE_CTRL_RST_MASK) { - status = IXGBE_ERR_RESET_FAILED; + status = -EIO; hw_dbg(hw, "Reset polling failed to complete.\n"); } @@ -3565,7 +3570,7 @@ static s32 ixgbe_setup_fc_backplane_x550em_a(struct ixgbe_hw *hw) /* Validate the requested mode */ if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { hw_err(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n"); - return IXGBE_ERR_INVALID_LINK_SETTINGS; + return -EINVAL; } if (hw->fc.requested_mode == ixgbe_fc_default) @@ -3622,7 +3627,7 @@ static s32 ixgbe_setup_fc_backplane_x550em_a(struct ixgbe_hw *hw) break; default: hw_err(hw, "Flow control param set incorrectly\n"); - return IXGBE_ERR_CONFIG; + return -EIO; } status = hw->mac.ops.write_iosf_sb_reg(hw, @@ -3718,7 +3723,7 @@ static s32 ixgbe_acquire_swfw_sync_x550em_a(struct ixgbe_hw *hw, u32 mask) return 0; if (hmask) ixgbe_release_swfw_sync_X540(hw, hmask); - if (status != IXGBE_ERR_TOKEN_RETRY) + if (status != -EAGAIN) return status; msleep(FW_PHY_TOKEN_DELAY); } @@ -3762,7 +3767,7 @@ static s32 ixgbe_read_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr, s32 status; if (hw->mac.ops.acquire_swfw_sync(hw, mask)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = hw->phy.ops.read_reg_mdi(hw, reg_addr, device_type, phy_data); @@ -3788,7 +3793,7 @@ static s32 ixgbe_write_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr, s32 status; if (hw->mac.ops.acquire_swfw_sync(hw, mask)) - return IXGBE_ERR_SWFW_SYNC; + return -EBUSY; status = ixgbe_write_phy_reg_mdi(hw, reg_addr, device_type, phy_data); hw->mac.ops.release_swfw_sync(hw, mask); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index e0e6275b3..e4e80c2b1 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -581,12 +581,38 @@ err_unroll_pools: return err; } +/* Cleanup pool before actual initialization in the OS */ +static void mvpp2_bm_pool_cleanup(struct mvpp2 *priv, int pool_id) +{ + unsigned int thread = mvpp2_cpu_to_thread(priv, get_cpu()); + u32 val; + int i; + + /* Drain the BM from all possible residues left by firmware */ + for (i = 0; i < MVPP2_BM_POOL_SIZE_MAX; i++) + mvpp2_thread_read(priv, thread, MVPP2_BM_PHY_ALLOC_REG(pool_id)); + + put_cpu(); + + /* Stop the BM pool */ + val = mvpp2_read(priv, MVPP2_BM_POOL_CTRL_REG(pool_id)); + val |= MVPP2_BM_STOP_MASK; + mvpp2_write(priv, MVPP2_BM_POOL_CTRL_REG(pool_id), val); +} + static int mvpp2_bm_init(struct device *dev, struct mvpp2 *priv) { enum dma_data_direction dma_dir = DMA_FROM_DEVICE; int i, err, poolnum = MVPP2_BM_POOLS_NUM; struct mvpp2_port *port; + if (priv->percpu_pools) + poolnum = mvpp2_get_nrxqs(priv) * 2; + + /* Clean up the pool state in case it contains stale state */ + for (i = 0; i < poolnum; i++) + mvpp2_bm_pool_cleanup(priv, i); + if (priv->percpu_pools) { for (i = 0; i < priv->port_count; i++) { port = priv->port_list[i]; @@ -596,7 +622,6 @@ static int mvpp2_bm_init(struct device *dev, struct mvpp2 *priv) } } - poolnum = mvpp2_get_nrxqs(priv) * 2; for (i = 0; i < poolnum; i++) { /* the pool in use */ int pn = i / (poolnum / 2); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index c0a0a3127..7f82baf8e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -403,6 +403,11 @@ int cgx_lmac_set_pause_frm(void *cgxd, int lmac_id, if (!cgx || lmac_id >= cgx->lmac_count) return -ENODEV; + cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); + cfg &= ~CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK; + cfg |= rx_pause ? CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK : 0x0; + cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg); + cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL); cfg &= ~CGX_SMUX_RX_FRM_CTL_CTL_BCK; cfg |= rx_pause ? CGX_SMUX_RX_FRM_CTL_CTL_BCK : 0x0; @@ -714,7 +719,7 @@ static irqreturn_t cgx_fwi_event_handler(int irq, void *data) /* Release thread waiting for completion */ lmac->cmd_pend = false; - wake_up_interruptible(&lmac->wq_cmd_cmplt); + wake_up(&lmac->wq_cmd_cmplt); break; case CGX_EVT_ASYNC: if (cgx_event_is_linkevent(event)) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index acbc67074..23b829f97 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -1969,10 +1969,9 @@ static void rvu_queue_work(struct mbox_wq_info *mw, int first, } } -static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq) +static irqreturn_t rvu_mbox_pf_intr_handler(int irq, void *rvu_irq) { struct rvu *rvu = (struct rvu *)rvu_irq; - int vfs = rvu->vfs; u64 intr; intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT); @@ -1986,6 +1985,18 @@ static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq) rvu_queue_work(&rvu->afpf_wq_info, 0, rvu->hw->total_pfs, intr); + return IRQ_HANDLED; +} + +static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq) +{ + struct rvu *rvu = (struct rvu *)rvu_irq; + int vfs = rvu->vfs; + u64 intr; + + /* Sync with mbox memory region */ + rmb(); + /* Handle VF interrupts */ if (vfs > 64) { intr = rvupf_read64(rvu, RVU_PF_VFPF_MBOX_INTX(1)); @@ -2300,7 +2311,7 @@ static int rvu_register_interrupts(struct rvu *rvu) /* Register mailbox interrupt handler */ sprintf(&rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], "RVUAF Mbox"); ret = request_irq(pci_irq_vector(rvu->pdev, RVU_AF_INT_VEC_MBOX), - rvu_mbox_intr_handler, 0, + rvu_mbox_pf_intr_handler, 0, &rvu->irq_name[RVU_AF_INT_VEC_MBOX * NAME_SIZE], rvu); if (ret) { dev_err(rvu->dev, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index e549b09c3..fb4b18be5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -3146,18 +3146,18 @@ int rvu_nix_init(struct rvu *rvu) */ rvu_write64(rvu, blkaddr, NIX_AF_CFG, rvu_read64(rvu, blkaddr, NIX_AF_CFG) | 0x40ULL); + } - /* Set chan/link to backpressure TL3 instead of TL2 */ - rvu_write64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL, 0x01); + /* Set chan/link to backpressure TL3 instead of TL2 */ + rvu_write64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL, 0x01); - /* Disable SQ manager's sticky mode operation (set TM6 = 0) - * This sticky mode is known to cause SQ stalls when multiple - * SQs are mapped to same SMQ and transmitting pkts at a time. - */ - cfg = rvu_read64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS); - cfg &= ~BIT_ULL(15); - rvu_write64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS, cfg); - } + /* Disable SQ manager's sticky mode operation (set TM6 = 0) + * This sticky mode is known to cause SQ stalls when multiple + * SQs are mapped to same SMQ and transmitting pkts at a time. + */ + cfg = rvu_read64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS); + cfg &= ~BIT_ULL(15); + rvu_write64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS, cfg); ltdefs = rvu->kpu.lt_def; /* Calibrate X2P bus to check if CGX/LBK links are fine */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index d6f7a2a58..aada28868 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1598,7 +1598,7 @@ int otx2_open(struct net_device *netdev) * mcam entries are enabled to receive the packets. Hence disable the * packet I/O. */ - if (err == EIO) + if (err == -EIO) goto err_disable_rxtx; else if (err) goto err_tx_stop_queues; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 39c17e903..0ba43c93a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -114,15 +114,18 @@ static u8 alloc_token(struct mlx5_cmd *cmd) return token; } -static int cmd_alloc_index(struct mlx5_cmd *cmd) +static int cmd_alloc_index(struct mlx5_cmd *cmd, struct mlx5_cmd_work_ent *ent) { unsigned long flags; int ret; spin_lock_irqsave(&cmd->alloc_lock, flags); ret = find_first_bit(&cmd->bitmask, cmd->max_reg_cmds); - if (ret < cmd->max_reg_cmds) + if (ret < cmd->max_reg_cmds) { clear_bit(ret, &cmd->bitmask); + ent->idx = ret; + cmd->ent_arr[ent->idx] = ent; + } spin_unlock_irqrestore(&cmd->alloc_lock, flags); return ret < cmd->max_reg_cmds ? ret : -ENOMEM; @@ -912,7 +915,7 @@ static void cmd_work_handler(struct work_struct *work) sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); if (!ent->page_queue) { - alloc_ret = cmd_alloc_index(cmd); + alloc_ret = cmd_alloc_index(cmd, ent); if (alloc_ret < 0) { mlx5_core_err_rl(dev, "failed to allocate command entry\n"); if (ent->callback) { @@ -927,15 +930,14 @@ static void cmd_work_handler(struct work_struct *work) up(sem); return; } - ent->idx = alloc_ret; } else { ent->idx = cmd->max_reg_cmds; spin_lock_irqsave(&cmd->alloc_lock, flags); clear_bit(ent->idx, &cmd->bitmask); + cmd->ent_arr[ent->idx] = ent; spin_unlock_irqrestore(&cmd->alloc_lock, flags); } - cmd->ent_arr[ent->idx] = ent; lay = get_inst(cmd, ent->idx); ent->lay = lay; memset(lay, 0, sizeof(*lay)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 39475f656..7c436bdcf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -208,11 +208,13 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, ft->g = kcalloc(MLX5E_ARFS_NUM_GROUPS, sizeof(*ft->g), GFP_KERNEL); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in || !ft->g) { - kfree(ft->g); - kvfree(in); + if (!ft->g) return -ENOMEM; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) { + err = -ENOMEM; + goto err_free_g; } mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); @@ -232,7 +234,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, break; default: err = -EINVAL; - goto out; + goto err_free_in; } switch (type) { @@ -254,7 +256,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, break; default: err = -EINVAL; - goto out; + goto err_free_in; } MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); @@ -263,7 +265,7 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, MLX5_SET_CFG(in, end_flow_index, ix - 1); ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); if (IS_ERR(ft->g[ft->num_groups])) - goto err; + goto err_clean_group; ft->num_groups++; memset(in, 0, inlen); @@ -272,18 +274,20 @@ static int arfs_create_groups(struct mlx5e_flow_table *ft, MLX5_SET_CFG(in, end_flow_index, ix - 1); ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); if (IS_ERR(ft->g[ft->num_groups])) - goto err; + goto err_clean_group; ft->num_groups++; kvfree(in); return 0; -err: +err_clean_group: err = PTR_ERR(ft->g[ft->num_groups]); ft->g[ft->num_groups] = NULL; -out: +err_free_in: kvfree(in); - +err_free_g: + kfree(ft->g); + ft->g = NULL; return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 4e8e3797a..074c9eb44 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1675,8 +1675,9 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg, } trace_mlx5_fs_set_fte(fte, false); + /* Link newly added rules into the tree. */ for (i = 0; i < handle->num_rules; i++) { - if (refcount_read(&handle->rule[i]->node.refcount) == 1) { + if (!handle->rule[i]->node.parent) { tree_add_node(&handle->rule[i]->node, &fte->node); trace_mlx5_fs_add_rule(handle->rule[i]); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index df1363a34..9721fe58e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -667,6 +667,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, switch (action_type) { case DR_ACTION_TYP_DROP: attr.final_icm_addr = nic_dmn->drop_icm_addr; + attr.hit_gvmi = nic_dmn->drop_icm_addr >> 48; break; case DR_ACTION_TYP_FT: dest_action = action; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 1a86535c4..f568ae250 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -697,7 +697,7 @@ free_skb: static const struct mlxsw_listener mlxsw_emad_rx_listener = MLXSW_RXL(mlxsw_emad_rx_listener_func, ETHEMAD, TRAP_TO_CPU, false, - EMAD, DISCARD); + EMAD, FORWARD); static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 483c8b75b..46b1120a8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -713,7 +713,9 @@ static void mlxsw_sp_acl_tcam_vregion_rehash_work(struct work_struct *work) rehash.dw.work); int credits = MLXSW_SP_ACL_TCAM_VREGION_REHASH_CREDITS; + mutex_lock(&vregion->lock); mlxsw_sp_acl_tcam_vregion_rehash(vregion->mlxsw_sp, vregion, &credits); + mutex_unlock(&vregion->lock); if (credits < 0) /* Rehash gone out of credits so it was interrupted. * Schedule the work as soon as possible to continue. @@ -724,6 +726,17 @@ static void mlxsw_sp_acl_tcam_vregion_rehash_work(struct work_struct *work) } static void +mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(struct mlxsw_sp_acl_tcam_rehash_ctx *ctx) +{ + /* The entry markers are relative to the current chunk and therefore + * needs to be reset together with the chunk marker. + */ + ctx->current_vchunk = NULL; + ctx->start_ventry = NULL; + ctx->stop_ventry = NULL; +} + +static void mlxsw_sp_acl_tcam_rehash_ctx_vchunk_changed(struct mlxsw_sp_acl_tcam_vchunk *vchunk) { struct mlxsw_sp_acl_tcam_vregion *vregion = vchunk->vregion; @@ -745,7 +758,7 @@ mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(struct mlxsw_sp_acl_tcam_vregion *v * the current chunk pointer to make sure all chunks * are properly migrated. */ - vregion->rehash.ctx.current_vchunk = NULL; + mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(&vregion->rehash.ctx); } static struct mlxsw_sp_acl_tcam_vregion * @@ -818,10 +831,14 @@ mlxsw_sp_acl_tcam_vregion_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam *tcam = vregion->tcam; if (vgroup->vregion_rehash_enabled && ops->region_rehash_hints_get) { + struct mlxsw_sp_acl_tcam_rehash_ctx *ctx = &vregion->rehash.ctx; + mutex_lock(&tcam->lock); list_del(&vregion->tlist); mutex_unlock(&tcam->lock); - cancel_delayed_work_sync(&vregion->rehash.dw); + if (cancel_delayed_work_sync(&vregion->rehash.dw) && + ctx->hints_priv) + ops->region_rehash_hints_put(ctx->hints_priv); } mlxsw_sp_acl_tcam_vgroup_vregion_detach(mlxsw_sp, vregion); if (vregion->region2) @@ -1187,8 +1204,14 @@ mlxsw_sp_acl_tcam_ventry_activity_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_ventry *ventry, bool *activity) { - return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, - ventry->entry, activity); + struct mlxsw_sp_acl_tcam_vregion *vregion = ventry->vchunk->vregion; + int err; + + mutex_lock(&vregion->lock); + err = mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, ventry->entry, + activity); + mutex_unlock(&vregion->lock); + return err; } static int @@ -1222,6 +1245,8 @@ mlxsw_sp_acl_tcam_vchunk_migrate_start(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_tcam_chunk *new_chunk; + WARN_ON(vchunk->chunk2); + new_chunk = mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, vchunk, region); if (IS_ERR(new_chunk)) return PTR_ERR(new_chunk); @@ -1240,7 +1265,7 @@ mlxsw_sp_acl_tcam_vchunk_migrate_end(struct mlxsw_sp *mlxsw_sp, { mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk2); vchunk->chunk2 = NULL; - ctx->current_vchunk = NULL; + mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(ctx); } static int @@ -1263,6 +1288,9 @@ mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp, return 0; } + if (list_empty(&vchunk->ventry_list)) + goto out; + /* If the migration got interrupted, we have the ventry to start from * stored in context. */ @@ -1272,6 +1300,8 @@ mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp, ventry = list_first_entry(&vchunk->ventry_list, typeof(*ventry), list); + WARN_ON(ventry->vchunk != vchunk); + list_for_each_entry_from(ventry, &vchunk->ventry_list, list) { /* During rollback, once we reach the ventry that failed * to migrate, we are done. @@ -1312,6 +1342,7 @@ mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp, } } +out: mlxsw_sp_acl_tcam_vchunk_migrate_end(mlxsw_sp, vchunk, ctx); return 0; } @@ -1325,6 +1356,9 @@ mlxsw_sp_acl_tcam_vchunk_migrate_all(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_vchunk *vchunk; int err; + if (list_empty(&vregion->vchunk_list)) + return 0; + /* If the migration got interrupted, we have the vchunk * we are working on stored in context. */ @@ -1353,16 +1387,17 @@ mlxsw_sp_acl_tcam_vregion_migrate(struct mlxsw_sp *mlxsw_sp, int err, err2; trace_mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion); - mutex_lock(&vregion->lock); err = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion, ctx, credits); if (err) { + if (ctx->this_is_rollback) + return err; /* In case migration was not successful, we need to swap * so the original region pointer is assigned again * to vregion->region. */ swap(vregion->region, vregion->region2); - ctx->current_vchunk = NULL; + mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(ctx); ctx->this_is_rollback = true; err2 = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion, ctx, credits); @@ -1373,7 +1408,6 @@ mlxsw_sp_acl_tcam_vregion_migrate(struct mlxsw_sp *mlxsw_sp, /* Let the rollback to be continued later on. */ } } - mutex_unlock(&vregion->lock); trace_mlxsw_sp_acl_tcam_vregion_migrate_end(mlxsw_sp, vregion); return err; } @@ -1422,6 +1456,7 @@ mlxsw_sp_acl_tcam_vregion_rehash_start(struct mlxsw_sp *mlxsw_sp, ctx->hints_priv = hints_priv; ctx->this_is_rollback = false; + mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(ctx); return 0; @@ -1474,7 +1509,8 @@ mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp, err = mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion, ctx, credits); if (err) { - dev_err(mlxsw_sp->bus_info->dev, "Failed to migrate vregion\n"); + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to migrate vregion\n"); + return; } if (*credits >= 0) diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c index dcde496da..c5de8f46c 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c @@ -780,7 +780,9 @@ static void lan743x_ethtool_get_wol(struct net_device *netdev, wol->supported = 0; wol->wolopts = 0; - phy_ethtool_get_wol(netdev->phydev, wol); + + if (netdev->phydev) + phy_ethtool_get_wol(netdev->phydev, wol); wol->supported |= WAKE_BCAST | WAKE_UCAST | WAKE_MCAST | WAKE_MAGIC | WAKE_PHY | WAKE_ARP; @@ -809,9 +811,8 @@ static int lan743x_ethtool_set_wol(struct net_device *netdev, device_set_wakeup_enable(&adapter->pdev->dev, (bool)wol->wolopts); - phy_ethtool_set_wol(netdev->phydev, wol); - - return 0; + return netdev->phydev ? phy_ethtool_set_wol(netdev->phydev, wol) + : -ENETDOWN; } #endif /* CONFIG_PM */ diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c index f5d48d7c4..da48dd857 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c @@ -1121,7 +1121,7 @@ static void __vxge_hw_blockpool_destroy(struct __vxge_hw_blockpool *blockpool) list_for_each_safe(p, n, &blockpool->free_entry_list) { list_del(&((struct __vxge_hw_blockpool_entry *)p)->item); - kfree((void *)p); + kfree(p); } return; diff --git a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c index 63907aeb3..3167f9675 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c @@ -308,6 +308,11 @@ static void nfp_fl_lag_do_work(struct work_struct *work) acti_netdevs = kmalloc_array(entry->slave_cnt, sizeof(*acti_netdevs), GFP_KERNEL); + if (!acti_netdevs) { + schedule_delayed_work(&lag->work, + NFP_FL_LAG_DELAY); + continue; + } /* Include sanity check in the loop. It may be that a bond has * changed between processing the last notification and the diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 088ceac07..08d74d001 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -927,7 +927,7 @@ nfp_tunnel_add_shared_mac(struct nfp_app *app, struct net_device *netdev, u16 nfp_mac_idx = 0; entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr); - if (entry && nfp_tunnel_is_mac_idx_global(entry->index)) { + if (entry && (nfp_tunnel_is_mac_idx_global(entry->index) || netif_is_lag_port(netdev))) { if (entry->bridge_count || !nfp_flower_is_supported_bridge(netdev)) { nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c index 252fe06f5..4c513e775 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c @@ -542,11 +542,13 @@ static int enable_bars(struct nfp6000_pcie *nfp, u16 interface) const u32 barcfg_msix_general = NFP_PCIE_BAR_PCIE2CPP_MapType( NFP_PCIE_BAR_PCIE2CPP_MapType_GENERAL) | - NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT; + NFP_PCIE_BAR_PCIE2CPP_LengthSelect( + NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT); const u32 barcfg_msix_xpb = NFP_PCIE_BAR_PCIE2CPP_MapType( NFP_PCIE_BAR_PCIE2CPP_MapType_BULK) | - NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT | + NFP_PCIE_BAR_PCIE2CPP_LengthSelect( + NFP_PCIE_BAR_PCIE2CPP_LengthSelect_32BIT) | NFP_PCIE_BAR_PCIE2CPP_Target_BaseAddress( NFP_CPP_TARGET_ISLAND_XPB); const u32 barcfg_explicit[4] = { diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index dc5fbc270..b5f681918 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -200,6 +200,7 @@ void ionic_dev_cmd_comp(struct ionic_dev *idev, union ionic_dev_cmd_comp *comp) void ionic_dev_cmd_go(struct ionic_dev *idev, union ionic_dev_cmd *cmd) { + idev->opcode = cmd->cmd.opcode; memcpy_toio(&idev->dev_cmd_regs->cmd, cmd, sizeof(*cmd)); iowrite32(0, &idev->dev_cmd_regs->done); iowrite32(1, &idev->dev_cmd_regs->doorbell); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index 64d27e8e0..1ce0d307a 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -136,6 +136,7 @@ struct ionic_dev { unsigned long last_hb_time; u32 last_hb; u8 last_fw_status; + u8 opcode; u64 __iomem *db_pages; dma_addr_t phy_db_pages; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 49c28134a..a37ca4b1e 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -2708,9 +2708,12 @@ static int ionic_lif_adminq_init(struct ionic_lif *lif) napi_enable(&qcq->napi); - if (qcq->flags & IONIC_QCQ_F_INTR) + if (qcq->flags & IONIC_QCQ_F_INTR) { + irq_set_affinity_hint(qcq->intr.vector, + &qcq->intr.affinity_mask); ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, IONIC_INTR_MASK_CLEAR); + } qcq->flags |= IONIC_QCQ_F_INITED; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index 00b6985ed..694e71024 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -333,7 +333,7 @@ int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds) */ max_wait = jiffies + (max_seconds * HZ); try_again: - opcode = readb(&idev->dev_cmd_regs->cmd.cmd.opcode); + opcode = idev->opcode; start_time = jiffies; do { done = ionic_dev_cmd_done(idev); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index c72ff0fd3..c29d43c5f 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -5181,6 +5181,15 @@ static int r8169_mdio_register(struct rtl8169_private *tp) struct mii_bus *new_bus; int ret; + /* On some boards with this chip version the BIOS is buggy and misses + * to reset the PHY page selector. This results in the PHY ID read + * accessing registers on a different page, returning a more or + * less random value. Fix this by resetting the page selector first. + */ + if (tp->mac_version == RTL_GIGA_MAC_VER_25 || + tp->mac_version == RTL_GIGA_MAC_VER_26) + r8169_mdio_write(tp, 0x1f, 0); + new_bus = devm_mdiobus_alloc(&pdev->dev); if (!new_bus) return -ENOMEM; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 8a4dff056..b08478aab 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -911,12 +911,12 @@ static int ravb_poll(struct napi_struct *napi, int budget) int q = napi - priv->napi; int mask = BIT(q); int quota = budget; + bool unmask; /* Processing RX Descriptor Ring */ /* Clear RX interrupt */ ravb_write(ndev, ~(mask | RIS0_RESERVED), RIS0); - if (ravb_rx(ndev, "a, q)) - goto out; + unmask = !ravb_rx(ndev, "a, q); /* Processing RX Descriptor Ring */ spin_lock_irqsave(&priv->lock, flags); @@ -926,6 +926,9 @@ static int ravb_poll(struct napi_struct *napi, int budget) netif_wake_subqueue(ndev, q); spin_unlock_irqrestore(&priv->lock, flags); + if (!unmask) + goto out; + napi_complete(napi); /* Re-enable RX/TX interrupts */ diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index af4303523..0bc345aff 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -189,6 +189,7 @@ struct stmmac_safety_stats { unsigned long mac_errors[32]; unsigned long mtl_errors[32]; unsigned long dma_errors[32]; + unsigned long dma_dpp_errors[32]; }; /* Number of fields in Safety Stats */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index cd11be005..5c6073d95 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -75,19 +75,41 @@ static void dwmac4_rx_queue_priority(struct mac_device_info *hw, u32 prio, u32 queue) { void __iomem *ioaddr = hw->pcsr; - u32 base_register; - u32 value; + u32 clear_mask = 0; + u32 ctrl2, ctrl3; + int i; - base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3; - if (queue >= 4) - queue -= 4; + ctrl2 = readl(ioaddr + GMAC_RXQ_CTRL2); + ctrl3 = readl(ioaddr + GMAC_RXQ_CTRL3); - value = readl(ioaddr + base_register); + /* The software must ensure that the same priority + * is not mapped to multiple Rx queues + */ + for (i = 0; i < 4; i++) + clear_mask |= ((prio << GMAC_RXQCTRL_PSRQX_SHIFT(i)) & + GMAC_RXQCTRL_PSRQX_MASK(i)); - value &= ~GMAC_RXQCTRL_PSRQX_MASK(queue); - value |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & + ctrl2 &= ~clear_mask; + ctrl3 &= ~clear_mask; + + /* First assign new priorities to a queue, then + * clear them from others queues + */ + if (queue < 4) { + ctrl2 |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & GMAC_RXQCTRL_PSRQX_MASK(queue); - writel(value, ioaddr + base_register); + + writel(ctrl2, ioaddr + GMAC_RXQ_CTRL2); + writel(ctrl3, ioaddr + GMAC_RXQ_CTRL3); + } else { + queue -= 4; + + ctrl3 |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) & + GMAC_RXQCTRL_PSRQX_MASK(queue); + + writel(ctrl3, ioaddr + GMAC_RXQ_CTRL3); + writel(ctrl2, ioaddr + GMAC_RXQ_CTRL2); + } } static void dwmac4_tx_queue_priority(struct mac_device_info *hw, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index eee58e051..4426cb923 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -282,6 +282,8 @@ #define XGMAC_RXCEIE BIT(4) #define XGMAC_TXCEIE BIT(0) #define XGMAC_MTL_ECC_INT_STATUS 0x000010cc +#define XGMAC_MTL_DPP_CONTROL 0x000010e0 +#define XGMAC_DPP_DISABLE BIT(0) #define XGMAC_MTL_TXQ_OPMODE(x) (0x00001100 + (0x80 * (x))) #define XGMAC_TQS GENMASK(25, 16) #define XGMAC_TQS_SHIFT 16 @@ -364,6 +366,7 @@ #define XGMAC_DCEIE BIT(1) #define XGMAC_TCEIE BIT(0) #define XGMAC_DMA_ECC_INT_STATUS 0x0000306c +#define XGMAC_DMA_DPP_INT_STATUS 0x00003074 #define XGMAC_DMA_CH_CONTROL(x) (0x00003100 + (0x80 * (x))) #define XGMAC_SPH BIT(24) #define XGMAC_PBLx8 BIT(16) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index b06066746..86f70ea9a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -97,17 +97,41 @@ static void dwxgmac2_rx_queue_prio(struct mac_device_info *hw, u32 prio, u32 queue) { void __iomem *ioaddr = hw->pcsr; - u32 value, reg; + u32 clear_mask = 0; + u32 ctrl2, ctrl3; + int i; - reg = (queue < 4) ? XGMAC_RXQ_CTRL2 : XGMAC_RXQ_CTRL3; - if (queue >= 4) + ctrl2 = readl(ioaddr + XGMAC_RXQ_CTRL2); + ctrl3 = readl(ioaddr + XGMAC_RXQ_CTRL3); + + /* The software must ensure that the same priority + * is not mapped to multiple Rx queues + */ + for (i = 0; i < 4; i++) + clear_mask |= ((prio << XGMAC_PSRQ_SHIFT(i)) & + XGMAC_PSRQ(i)); + + ctrl2 &= ~clear_mask; + ctrl3 &= ~clear_mask; + + /* First assign new priorities to a queue, then + * clear them from others queues + */ + if (queue < 4) { + ctrl2 |= (prio << XGMAC_PSRQ_SHIFT(queue)) & + XGMAC_PSRQ(queue); + + writel(ctrl2, ioaddr + XGMAC_RXQ_CTRL2); + writel(ctrl3, ioaddr + XGMAC_RXQ_CTRL3); + } else { queue -= 4; - value = readl(ioaddr + reg); - value &= ~XGMAC_PSRQ(queue); - value |= (prio << XGMAC_PSRQ_SHIFT(queue)) & XGMAC_PSRQ(queue); + ctrl3 |= (prio << XGMAC_PSRQ_SHIFT(queue)) & + XGMAC_PSRQ(queue); - writel(value, ioaddr + reg); + writel(ctrl3, ioaddr + XGMAC_RXQ_CTRL3); + writel(ctrl2, ioaddr + XGMAC_RXQ_CTRL2); + } } static void dwxgmac2_tx_queue_prio(struct mac_device_info *hw, u32 prio, @@ -788,6 +812,44 @@ static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= { { false, "UNKNOWN", "Unknown Error" }, /* 31 */ }; +#define DPP_RX_ERR "Read Rx Descriptor Parity checker Error" +#define DPP_TX_ERR "Read Tx Descriptor Parity checker Error" + +static const struct dwxgmac3_error_desc dwxgmac3_dma_dpp_errors[32] = { + { true, "TDPES0", DPP_TX_ERR }, + { true, "TDPES1", DPP_TX_ERR }, + { true, "TDPES2", DPP_TX_ERR }, + { true, "TDPES3", DPP_TX_ERR }, + { true, "TDPES4", DPP_TX_ERR }, + { true, "TDPES5", DPP_TX_ERR }, + { true, "TDPES6", DPP_TX_ERR }, + { true, "TDPES7", DPP_TX_ERR }, + { true, "TDPES8", DPP_TX_ERR }, + { true, "TDPES9", DPP_TX_ERR }, + { true, "TDPES10", DPP_TX_ERR }, + { true, "TDPES11", DPP_TX_ERR }, + { true, "TDPES12", DPP_TX_ERR }, + { true, "TDPES13", DPP_TX_ERR }, + { true, "TDPES14", DPP_TX_ERR }, + { true, "TDPES15", DPP_TX_ERR }, + { true, "RDPES0", DPP_RX_ERR }, + { true, "RDPES1", DPP_RX_ERR }, + { true, "RDPES2", DPP_RX_ERR }, + { true, "RDPES3", DPP_RX_ERR }, + { true, "RDPES4", DPP_RX_ERR }, + { true, "RDPES5", DPP_RX_ERR }, + { true, "RDPES6", DPP_RX_ERR }, + { true, "RDPES7", DPP_RX_ERR }, + { true, "RDPES8", DPP_RX_ERR }, + { true, "RDPES9", DPP_RX_ERR }, + { true, "RDPES10", DPP_RX_ERR }, + { true, "RDPES11", DPP_RX_ERR }, + { true, "RDPES12", DPP_RX_ERR }, + { true, "RDPES13", DPP_RX_ERR }, + { true, "RDPES14", DPP_RX_ERR }, + { true, "RDPES15", DPP_RX_ERR }, +}; + static void dwxgmac3_handle_dma_err(struct net_device *ndev, void __iomem *ioaddr, bool correctable, struct stmmac_safety_stats *stats) @@ -799,6 +861,13 @@ static void dwxgmac3_handle_dma_err(struct net_device *ndev, dwxgmac3_log_error(ndev, value, correctable, "DMA", dwxgmac3_dma_errors, STAT_OFF(dma_errors), stats); + + value = readl(ioaddr + XGMAC_DMA_DPP_INT_STATUS); + writel(value, ioaddr + XGMAC_DMA_DPP_INT_STATUS); + + dwxgmac3_log_error(ndev, value, false, "DMA_DPP", + dwxgmac3_dma_dpp_errors, + STAT_OFF(dma_dpp_errors), stats); } static int dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp) @@ -835,6 +904,12 @@ static int dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp) value |= XGMAC_TMOUTEN; /* FSM Timeout Feature */ writel(value, ioaddr + XGMAC_MAC_FSM_CONTROL); + /* 5. Enable Data Path Parity Protection */ + value = readl(ioaddr + XGMAC_MTL_DPP_CONTROL); + /* already enabled by default, explicit enable it again */ + value &= ~XGMAC_DPP_DISABLE; + writel(value, ioaddr + XGMAC_MTL_DPP_CONTROL); + return 0; } @@ -868,7 +943,11 @@ static int dwxgmac3_safety_feat_irq_status(struct net_device *ndev, ret |= !corr; } - err = dma & (XGMAC_DEUIS | XGMAC_DECIS); + /* DMA_DPP_Interrupt_Status is indicated by MCSIS bit in + * DMA_Safety_Interrupt_Status, so we handle DMA Data Path + * Parity Errors here + */ + err = dma & (XGMAC_DEUIS | XGMAC_DECIS | XGMAC_MCSIS); corr = dma & XGMAC_DECIS; if (err) { dwxgmac3_handle_dma_err(ndev, ioaddr, corr, stats); @@ -884,6 +963,7 @@ static const struct dwxgmac3_error { { dwxgmac3_mac_errors }, { dwxgmac3_mtl_errors }, { dwxgmac3_dma_errors }, + { dwxgmac3_dma_dpp_errors }, }; static int dwxgmac3_safety_feat_dump(struct stmmac_safety_stats *stats, diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index 5dc60ecab..e0fcdbadf 100644 --- a/drivers/net/ethernet/ti/am65-cpts.c +++ b/drivers/net/ethernet/ti/am65-cpts.c @@ -649,6 +649,11 @@ static bool am65_cpts_match_tx_ts(struct am65_cpts *cpts, struct am65_cpts_skb_cb_data *skb_cb = (struct am65_cpts_skb_cb_data *)skb->cb; + if ((ptp_classify_raw(skb) & PTP_CLASS_V1) && + ((mtype_seqid & AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK) == + (skb_cb->skb_mtype_seqid & AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK))) + mtype_seqid = skb_cb->skb_mtype_seqid; + if (mtype_seqid == skb_cb->skb_mtype_seqid) { u64 ns = event->timestamp; diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index da136abba..e50b59efe 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1427,7 +1427,7 @@ static int temac_probe(struct platform_device *pdev) } /* map device registers */ - lp->regs = devm_platform_ioremap_resource_byname(pdev, 0); + lp->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(lp->regs)) { dev_err(&pdev->dev, "could not map TEMAC registers\n"); return -ENOMEM; diff --git a/drivers/net/fjes/fjes_hw.c b/drivers/net/fjes/fjes_hw.c index 065bb0a40..a1405a3e2 100644 --- a/drivers/net/fjes/fjes_hw.c +++ b/drivers/net/fjes/fjes_hw.c @@ -220,21 +220,25 @@ static int fjes_hw_setup(struct fjes_hw *hw) mem_size = FJES_DEV_REQ_BUF_SIZE(hw->max_epid); hw->hw_info.req_buf = kzalloc(mem_size, GFP_KERNEL); - if (!(hw->hw_info.req_buf)) - return -ENOMEM; + if (!(hw->hw_info.req_buf)) { + result = -ENOMEM; + goto free_ep_info; + } hw->hw_info.req_buf_size = mem_size; mem_size = FJES_DEV_RES_BUF_SIZE(hw->max_epid); hw->hw_info.res_buf = kzalloc(mem_size, GFP_KERNEL); - if (!(hw->hw_info.res_buf)) - return -ENOMEM; + if (!(hw->hw_info.res_buf)) { + result = -ENOMEM; + goto free_req_buf; + } hw->hw_info.res_buf_size = mem_size; result = fjes_hw_alloc_shared_status_region(hw); if (result) - return result; + goto free_res_buf; hw->hw_info.buffer_share_bit = 0; hw->hw_info.buffer_unshare_reserve_bit = 0; @@ -245,11 +249,11 @@ static int fjes_hw_setup(struct fjes_hw *hw) result = fjes_hw_alloc_epbuf(&buf_pair->tx); if (result) - return result; + goto free_epbuf; result = fjes_hw_alloc_epbuf(&buf_pair->rx); if (result) - return result; + goto free_epbuf; spin_lock_irqsave(&hw->rx_status_lock, flags); fjes_hw_setup_epbuf(&buf_pair->tx, mac, @@ -272,6 +276,25 @@ static int fjes_hw_setup(struct fjes_hw *hw) fjes_hw_init_command_registers(hw, ¶m); return 0; + +free_epbuf: + for (epidx = 0; epidx < hw->max_epid ; epidx++) { + if (epidx == hw->my_epid) + continue; + fjes_hw_free_epbuf(&hw->ep_shm_info[epidx].tx); + fjes_hw_free_epbuf(&hw->ep_shm_info[epidx].rx); + } + fjes_hw_free_shared_status_region(hw); +free_res_buf: + kfree(hw->hw_info.res_buf); + hw->hw_info.res_buf = NULL; +free_req_buf: + kfree(hw->hw_info.req_buf); + hw->hw_info.req_buf = NULL; +free_ep_info: + kfree(hw->ep_shm_info); + hw->ep_shm_info = NULL; + return result; } static void fjes_hw_cleanup(struct fjes_hw *hw) diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 081939cb4..af35361a3 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -218,7 +218,7 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, struct genevehdr *gnvh = geneve_hdr(skb); struct metadata_dst *tun_dst = NULL; unsigned int len; - int err = 0; + int nh, err = 0; void *oiph; if (ip_tunnel_collect_metadata() || gs->collect_md) { @@ -262,9 +262,23 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, goto drop; } - oiph = skb_network_header(skb); + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_reset_network_header(skb); + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(geneve->dev, rx_length_errors); + DEV_STATS_INC(geneve->dev, rx_errors); + goto drop; + } + + /* Get the outer header. */ + oiph = skb->head + nh; + if (geneve_get_sk_family(gs) == AF_INET) err = IP_ECN_decapsulate(oiph, skb); #if IS_ENABLED(CONFIG_IPV6) @@ -893,7 +907,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; - if (!pskb_inet_may_pull(skb)) + if (!skb_vlan_inet_prepare(skb)) return -EINVAL; sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); @@ -990,7 +1004,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; - if (!pskb_inet_may_pull(skb)) + if (!skb_vlan_inet_prepare(skb)) return -EINVAL; sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index ed247cba2..c8246363d 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -700,11 +700,12 @@ out_hashtable: static void gtp_dellink(struct net_device *dev, struct list_head *head) { struct gtp_dev *gtp = netdev_priv(dev); + struct hlist_node *next; struct pdp_ctx *pctx; int i; for (i = 0; i < gtp->hash_size; i++) - hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) + hlist_for_each_entry_safe(pctx, next, >p->tid_hash[i], hlist_tid) pdp_context_delete(pctx); list_del_rcu(>p->list); @@ -1406,26 +1407,26 @@ static int __init gtp_init(void) get_random_bytes(>p_h_initval, sizeof(gtp_h_initval)); - err = rtnl_link_register(>p_link_ops); + err = register_pernet_subsys(>p_net_ops); if (err < 0) goto error_out; - err = genl_register_family(>p_genl_family); + err = rtnl_link_register(>p_link_ops); if (err < 0) - goto unreg_rtnl_link; + goto unreg_pernet_subsys; - err = register_pernet_subsys(>p_net_ops); + err = genl_register_family(>p_genl_family); if (err < 0) - goto unreg_genl_family; + goto unreg_rtnl_link; pr_info("GTP module loaded (pdp ctx size %zd bytes)\n", sizeof(struct pdp_ctx)); return 0; -unreg_genl_family: - genl_unregister_family(>p_genl_family); unreg_rtnl_link: rtnl_link_unregister(>p_link_ops); +unreg_pernet_subsys: + unregister_pernet_subsys(>p_net_ops); error_out: pr_err("error loading GTP module loaded\n"); return err; diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 367878493..15652d795 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -847,6 +847,19 @@ struct nvsp_message { #define NETVSC_XDP_HDRM 256 +#define NETVSC_MIN_OUT_MSG_SIZE (sizeof(struct vmpacket_descriptor) + \ + sizeof(struct nvsp_message)) +#define NETVSC_MIN_IN_MSG_SIZE sizeof(struct vmpacket_descriptor) + +/* Estimated requestor size: + * out_ring_size/min_out_msg_size + in_ring_size/min_in_msg_size + */ +static inline u32 netvsc_rqstor_size(unsigned long ringbytes) +{ + return ringbytes / NETVSC_MIN_OUT_MSG_SIZE + + ringbytes / NETVSC_MIN_IN_MSG_SIZE; +} + #define NETVSC_XFER_HEADER_SIZE(rng_cnt) \ (offsetof(struct vmtransfer_page_packet_header, ranges) + \ (rng_cnt) * sizeof(struct vmtransfer_page_range)) diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index d15da8287..03333a413 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -37,6 +37,10 @@ void netvsc_switch_datapath(struct net_device *ndev, bool vf) struct netvsc_device *nv_dev = rtnl_dereference(net_device_ctx->nvdev); struct nvsp_message *init_pkt = &nv_dev->channel_init_pkt; + /* Block sending traffic to VF if it's about to be gone */ + if (!vf) + net_device_ctx->data_path_is_vf = vf; + memset(init_pkt, 0, sizeof(struct nvsp_message)); init_pkt->hdr.msg_type = NVSP_MSG4_TYPE_SWITCH_DATA_PATH; if (vf) @@ -51,7 +55,10 @@ void netvsc_switch_datapath(struct net_device *ndev, bool vf) vmbus_sendpacket(dev->channel, init_pkt, sizeof(struct nvsp_message), (unsigned long)init_pkt, - VM_PKT_DATA_INBAND, 0); + VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + wait_for_completion(&nv_dev->channel_init_wait); + net_device_ctx->data_path_is_vf = vf; } /* Worker to setup sub channels on initial setup @@ -163,7 +170,7 @@ static void netvsc_revoke_recv_buf(struct hv_device *device, ret = vmbus_sendpacket(device->channel, revoke_packet, sizeof(struct nvsp_message), - (unsigned long)revoke_packet, + VMBUS_RQST_ID_NO_RESPONSE, VM_PKT_DATA_INBAND, 0); /* If the failure is because the channel is rescinded; * ignore the failure since we cannot send on a rescinded @@ -213,7 +220,7 @@ static void netvsc_revoke_send_buf(struct hv_device *device, ret = vmbus_sendpacket(device->channel, revoke_packet, sizeof(struct nvsp_message), - (unsigned long)revoke_packet, + VMBUS_RQST_ID_NO_RESPONSE, VM_PKT_DATA_INBAND, 0); /* If the failure is because the channel is rescinded; @@ -557,7 +564,7 @@ static int negotiate_nvsp_ver(struct hv_device *device, ret = vmbus_sendpacket(device->channel, init_packet, sizeof(struct nvsp_message), - (unsigned long)init_packet, + VMBUS_RQST_ID_NO_RESPONSE, VM_PKT_DATA_INBAND, 0); return ret; @@ -614,7 +621,7 @@ static int netvsc_connect_vsp(struct hv_device *device, /* Send the init request */ ret = vmbus_sendpacket(device->channel, init_packet, sizeof(struct nvsp_message), - (unsigned long)init_packet, + VMBUS_RQST_ID_NO_RESPONSE, VM_PKT_DATA_INBAND, 0); if (ret != 0) goto cleanup; @@ -654,7 +661,10 @@ void netvsc_device_remove(struct hv_device *device) /* Disable NAPI and disassociate its context from the device. */ for (i = 0; i < net_device->num_chn; i++) { /* See also vmbus_reset_channel_cb(). */ - napi_disable(&net_device->chan_table[i].napi); + /* only disable enabled NAPI channel */ + if (i < ndev->real_num_rx_queues) + napi_disable(&net_device->chan_table[i].napi); + netif_napi_del(&net_device->chan_table[i].napi); } @@ -695,10 +705,19 @@ static void netvsc_send_tx_complete(struct net_device *ndev, const struct vmpacket_descriptor *desc, int budget) { - struct sk_buff *skb = (struct sk_buff *)(unsigned long)desc->trans_id; struct net_device_context *ndev_ctx = netdev_priv(ndev); + struct sk_buff *skb; u16 q_idx = 0; int queue_sends; + u64 cmd_rqst; + + cmd_rqst = vmbus_request_addr(&channel->requestor, (u64)desc->trans_id); + if (cmd_rqst == VMBUS_RQST_ERROR) { + netdev_err(ndev, "Incorrect transaction id\n"); + return; + } + + skb = (struct sk_buff *)(unsigned long)cmd_rqst; /* Notify the layer above us */ if (likely(skb)) { @@ -745,8 +764,31 @@ static void netvsc_send_completion(struct net_device *ndev, const struct vmpacket_descriptor *desc, int budget) { - const struct nvsp_message *nvsp_packet = hv_pkt_data(desc); + const struct nvsp_message *nvsp_packet; u32 msglen = hv_pkt_datalen(desc); + struct nvsp_message *pkt_rqst; + u64 cmd_rqst; + + /* First check if this is a VMBUS completion without data payload */ + if (!msglen) { + cmd_rqst = vmbus_request_addr(&incoming_channel->requestor, + (u64)desc->trans_id); + if (cmd_rqst == VMBUS_RQST_ERROR) { + netdev_err(ndev, "Invalid transaction id\n"); + return; + } + + pkt_rqst = (struct nvsp_message *)(uintptr_t)cmd_rqst; + switch (pkt_rqst->hdr.msg_type) { + case NVSP_MSG4_TYPE_SWITCH_DATA_PATH: + complete(&net_device->channel_init_wait); + break; + + default: + netdev_err(ndev, "Unexpected VMBUS completion!!\n"); + } + return; + } /* Ensure packet is big enough to read header fields */ if (msglen < sizeof(struct nvsp_message_header)) { @@ -754,6 +796,7 @@ static void netvsc_send_completion(struct net_device *ndev, return; } + nvsp_packet = hv_pkt_data(desc); switch (nvsp_packet->hdr.msg_type) { case NVSP_MSG_TYPE_INIT_COMPLETE: if (msglen < sizeof(struct nvsp_message_header) + @@ -1527,6 +1570,7 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device, netvsc_poll, NAPI_POLL_WEIGHT); /* Open the channel */ + device->channel->rqstor_size = netvsc_rqstor_size(netvsc_ring_bytes); ret = vmbus_open(device->channel, netvsc_ring_bytes, netvsc_ring_bytes, NULL, 0, netvsc_channel_cb, net_device->chan_table); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 790bf7502..0fc0f9cb3 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -44,6 +44,10 @@ #define LINKCHANGE_INT (2 * HZ) #define VF_TAKEOVER_INT (HZ / 10) +/* Macros to define the context of vf registration */ +#define VF_REG_IN_PROBE 1 +#define VF_REG_IN_NOTIFIER 2 + static unsigned int ring_size __ro_after_init = 128; module_param(ring_size, uint, 0444); MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)"); @@ -2194,7 +2198,7 @@ static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb) } static int netvsc_vf_join(struct net_device *vf_netdev, - struct net_device *ndev) + struct net_device *ndev, int context) { struct net_device_context *ndev_ctx = netdev_priv(ndev); int ret; @@ -2217,7 +2221,11 @@ static int netvsc_vf_join(struct net_device *vf_netdev, goto upper_link_failed; } - schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); + /* If this registration is called from probe context vf_takeover + * is taken care of later in probe itself. + */ + if (context == VF_REG_IN_NOTIFIER) + schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); call_netdevice_notifiers(NETDEV_JOIN, vf_netdev); @@ -2310,8 +2318,17 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev) if (!ndev_ctx->vf_alloc) continue; - if (ndev_ctx->vf_serial == serial) - return hv_get_drvdata(ndev_ctx->device_ctx); + if (ndev_ctx->vf_serial != serial) + continue; + + ndev = hv_get_drvdata(ndev_ctx->device_ctx); + if (ndev->addr_len != vf_netdev->addr_len || + memcmp(ndev->perm_addr, vf_netdev->perm_addr, + ndev->addr_len) != 0) + continue; + + return ndev; + } /* Fallback path to check synthetic vf with help of mac addr. @@ -2346,7 +2363,7 @@ static int netvsc_prepare_bonding(struct net_device *vf_netdev) return NOTIFY_DONE; } -static int netvsc_register_vf(struct net_device *vf_netdev) +static int netvsc_register_vf(struct net_device *vf_netdev, int context) { struct net_device_context *net_device_ctx; struct netvsc_device *netvsc_dev; @@ -2386,7 +2403,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev) netdev_info(ndev, "VF registering: %s\n", vf_netdev->name); - if (netvsc_vf_join(vf_netdev, ndev) != 0) + if (netvsc_vf_join(vf_netdev, ndev, context) != 0) return NOTIFY_DONE; dev_hold(vf_netdev); @@ -2411,12 +2428,15 @@ static int netvsc_register_vf(struct net_device *vf_netdev) * During hibernation, if a VF NIC driver (e.g. mlx5) preserves the network * interface, there is only the CHANGE event and no UP or DOWN event. */ -static int netvsc_vf_changed(struct net_device *vf_netdev) +static int netvsc_vf_changed(struct net_device *vf_netdev, unsigned long event) { struct net_device_context *net_device_ctx; struct netvsc_device *netvsc_dev; struct net_device *ndev; - bool vf_is_up = netif_running(vf_netdev); + bool vf_is_up = false; + + if (event != NETDEV_GOING_DOWN) + vf_is_up = netif_running(vf_netdev); ndev = get_netvsc_byref(vf_netdev); if (!ndev) @@ -2429,7 +2449,6 @@ static int netvsc_vf_changed(struct net_device *vf_netdev) if (net_device_ctx->data_path_is_vf == vf_is_up) return NOTIFY_OK; - net_device_ctx->data_path_is_vf = vf_is_up; if (vf_is_up && !net_device_ctx->vf_alloc) { netdev_info(ndev, "Waiting for the VF association from host\n"); @@ -2468,10 +2487,31 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev) return NOTIFY_OK; } +static int check_dev_is_matching_vf(struct net_device *event_ndev) +{ + /* Skip NetVSC interfaces */ + if (event_ndev->netdev_ops == &device_ops) + return -ENODEV; + + /* Avoid non-Ethernet type devices */ + if (event_ndev->type != ARPHRD_ETHER) + return -ENODEV; + + /* Avoid Vlan dev with same MAC registering as VF */ + if (is_vlan_dev(event_ndev)) + return -ENODEV; + + /* Avoid Bonding master dev with same MAC registering as VF */ + if (netif_is_bond_master(event_ndev)) + return -ENODEV; + + return 0; +} + static int netvsc_probe(struct hv_device *dev, const struct hv_vmbus_device_id *dev_id) { - struct net_device *net = NULL; + struct net_device *net = NULL, *vf_netdev; struct net_device_context *net_device_ctx; struct netvsc_device_info *device_info = NULL; struct netvsc_device *nvdev; @@ -2579,6 +2619,30 @@ static int netvsc_probe(struct hv_device *dev, } list_add(&net_device_ctx->list, &netvsc_dev_list); + + /* When the hv_netvsc driver is unloaded and reloaded, the + * NET_DEVICE_REGISTER for the vf device is replayed before probe + * is complete. This is because register_netdevice_notifier() gets + * registered before vmbus_driver_register() so that callback func + * is set before probe and we don't miss events like NETDEV_POST_INIT + * So, in this section we try to register the matching vf device that + * is present as a netdevice, knowing that its register call is not + * processed in the netvsc_netdev_notifier(as probing is progress and + * get_netvsc_byslot fails). + */ + for_each_netdev(dev_net(net), vf_netdev) { + ret = check_dev_is_matching_vf(vf_netdev); + if (ret != 0) + continue; + + if (net != get_netvsc_byslot(vf_netdev)) + continue; + + netvsc_prepare_bonding(vf_netdev); + netvsc_register_vf(vf_netdev, VF_REG_IN_PROBE); + __netvsc_vf_setup(net, vf_netdev); + break; + } rtnl_unlock(); netvsc_devinfo_put(device_info); @@ -2735,35 +2799,24 @@ static int netvsc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); + int ret = 0; - /* Skip our own events */ - if (event_dev->netdev_ops == &device_ops) - return NOTIFY_DONE; - - /* Avoid non-Ethernet type devices */ - if (event_dev->type != ARPHRD_ETHER) - return NOTIFY_DONE; - - /* Avoid Vlan dev with same MAC registering as VF */ - if (is_vlan_dev(event_dev)) - return NOTIFY_DONE; - - /* Avoid Bonding master dev with same MAC registering as VF */ - if ((event_dev->priv_flags & IFF_BONDING) && - (event_dev->flags & IFF_MASTER)) + ret = check_dev_is_matching_vf(event_dev); + if (ret != 0) return NOTIFY_DONE; switch (event) { case NETDEV_POST_INIT: return netvsc_prepare_bonding(event_dev); case NETDEV_REGISTER: - return netvsc_register_vf(event_dev); + return netvsc_register_vf(event_dev, VF_REG_IN_NOTIFIER); case NETDEV_UNREGISTER: return netvsc_unregister_vf(event_dev); case NETDEV_UP: case NETDEV_DOWN: case NETDEV_CHANGE: - return netvsc_vf_changed(event_dev); + case NETDEV_GOING_DOWN: + return netvsc_vf_changed(event_dev, event); default: return NOTIFY_DONE; } diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 90bc0008f..13f62950e 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1170,6 +1170,7 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc) /* Set the channel before opening.*/ nvchan->channel = new_sc; + new_sc->rqstor_size = netvsc_rqstor_size(netvsc_ring_bytes); ret = vmbus_open(new_sc, netvsc_ring_bytes, netvsc_ring_bytes, NULL, 0, netvsc_channel_cb, nvchan); diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 814129994..14c5e082c 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -94,7 +94,8 @@ #define DP83822_WOL_INDICATION_SEL BIT(8) #define DP83822_WOL_CLR_INDICATION BIT(11) -/* RSCR bits */ +/* RCSR bits */ +#define DP83822_RGMII_MODE_EN BIT(9) #define DP83822_RX_CLK_SHIFT BIT(12) #define DP83822_TX_CLK_SHIFT BIT(11) @@ -358,7 +359,7 @@ static int dp83822_config_init(struct phy_device *phydev) { struct dp83822_private *dp83822 = phydev->priv; struct device *dev = &phydev->mdio.dev; - int rgmii_delay; + int rgmii_delay = 0; s32 rx_int_delay; s32 tx_int_delay; int err = 0; @@ -368,24 +369,33 @@ static int dp83822_config_init(struct phy_device *phydev) rx_int_delay = phy_get_internal_delay(phydev, dev, NULL, 0, true); - if (rx_int_delay <= 0) - rgmii_delay = 0; - else - rgmii_delay = DP83822_RX_CLK_SHIFT; + /* Set DP83822_RX_CLK_SHIFT to enable rx clk internal delay */ + if (rx_int_delay > 0) + rgmii_delay |= DP83822_RX_CLK_SHIFT; tx_int_delay = phy_get_internal_delay(phydev, dev, NULL, 0, false); + + /* Set DP83822_TX_CLK_SHIFT to disable tx clk internal delay */ if (tx_int_delay <= 0) - rgmii_delay &= ~DP83822_TX_CLK_SHIFT; - else rgmii_delay |= DP83822_TX_CLK_SHIFT; - if (rgmii_delay) { - err = phy_set_bits_mmd(phydev, DP83822_DEVADDR, - MII_DP83822_RCSR, rgmii_delay); - if (err) - return err; - } + err = phy_modify_mmd(phydev, DP83822_DEVADDR, MII_DP83822_RCSR, + DP83822_RX_CLK_SHIFT | DP83822_TX_CLK_SHIFT, rgmii_delay); + if (err) + return err; + + err = phy_set_bits_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RCSR, DP83822_RGMII_MODE_EN); + + if (err) + return err; + } else { + err = phy_clear_bits_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RCSR, DP83822_RGMII_MODE_EN); + + if (err) + return err; } if (dp83822->fx_enabled) { diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 095d16cea..8654e05dd 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2769,7 +2769,7 @@ s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, if (delay < 0) return delay; - if (delay && size == 0) + if (size == 0) return delay; if (delay < delay_values[0] || delay > delay_values[size - 1]) { diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index f14a9d190..aada8a3c1 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -471,6 +471,10 @@ ppp_async_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg) case PPPIOCSMRU: if (get_user(val, p)) break; + if (val > U16_MAX) { + err = -EINVAL; + break; + } if (val < PPP_MRU) val = PPP_MRU; ap->mru = val; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 0b25b59f4..77e63e736 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -665,6 +665,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean) tun->tfiles[tun->numqueues - 1]); ntfile = rtnl_dereference(tun->tfiles[index]); ntfile->queue_index = index; + ntfile->xdp_rxq.queue_index = index; rcu_assign_pointer(tun->tfiles[tun->numqueues - 1], NULL); @@ -2140,14 +2141,16 @@ static ssize_t tun_put_user(struct tun_struct *tun, tun_is_little_endian(tun), true, vlan_hlen)) { struct skb_shared_info *sinfo = skb_shinfo(skb); - pr_err("unexpected GSO type: " - "0x%x, gso_size %d, hdr_len %d\n", - sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), - tun16_to_cpu(tun, gso.hdr_len)); - print_hex_dump(KERN_ERR, "tun: ", - DUMP_PREFIX_NONE, - 16, 1, skb->head, - min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + + if (net_ratelimit()) { + netdev_err(tun->dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", + sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), + tun16_to_cpu(tun, gso.hdr_len)); + print_hex_dump(KERN_ERR, "tun: ", + DUMP_PREFIX_NONE, + 16, 1, skb->head, + min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + } WARN_ON_ONCE(1); return -EINVAL; } diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 38cb863cc..da4a2427b 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1558,21 +1558,16 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb) /* Skip IP alignment pseudo header */ skb_pull(skb, 2); - skb->truesize = SKB_TRUESIZE(pkt_len_plus_padd); ax88179_rx_checksum(skb, pkt_hdr); return 1; } - ax_skb = skb_clone(skb, GFP_ATOMIC); + ax_skb = netdev_alloc_skb_ip_align(dev->net, pkt_len); if (!ax_skb) return 0; - skb_trim(ax_skb, pkt_len); + skb_put(ax_skb, pkt_len); + memcpy(ax_skb->data, skb->data + 2, pkt_len); - /* Skip IP alignment pseudo header */ - skb_pull(ax_skb, 2); - - skb->truesize = pkt_len_plus_padd + - SKB_DATA_ALIGN(sizeof(struct sk_buff)); ax88179_rx_checksum(ax_skb, pkt_hdr); usbnet_skb_return(dev, ax_skb); diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index 5aad26600..9b7db5fd9 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -231,7 +231,7 @@ static int dm9601_mdio_read(struct net_device *netdev, int phy_id, int loc) err = dm_read_shared_word(dev, 1, loc, &res); if (err < 0) { netdev_err(dev->net, "MDIO read error: %d\n", err); - return err; + return 0; } netdev_dbg(dev->net, diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 667984efe..96d3d0bd2 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -90,6 +90,12 @@ /* statistic update interval (mSec) */ #define STAT_UPDATE_TIMER (1 * 1000) +/* time to wait for MAC or FCT to stop (jiffies) */ +#define HW_DISABLE_TIMEOUT (HZ / 10) + +/* time to wait between polling MAC or FCT state (ms) */ +#define HW_DISABLE_DELAY_MS 1 + /* defines interrupts from interrupt EP */ #define MAX_INT_EP (32) #define INT_EP_INTEP (31) @@ -384,8 +390,9 @@ struct lan78xx_net { struct urb *urb_intr; struct usb_anchor deferred; + struct mutex dev_mutex; /* serialise open/stop wrt suspend/resume */ struct mutex phy_mutex; /* for phy access */ - unsigned pipe_in, pipe_out, pipe_intr; + unsigned int pipe_in, pipe_out, pipe_intr; u32 hard_mtu; /* count any extra framing */ size_t rx_urb_size; /* size for rx urbs */ @@ -395,7 +402,7 @@ struct lan78xx_net { wait_queue_head_t *wait; unsigned char suspend_count; - unsigned maxpacket; + unsigned int maxpacket; struct timer_list delay; struct timer_list stat_monitor; @@ -479,6 +486,26 @@ static int lan78xx_write_reg(struct lan78xx_net *dev, u32 index, u32 data) return ret; } +static int lan78xx_update_reg(struct lan78xx_net *dev, u32 reg, u32 mask, + u32 data) +{ + int ret; + u32 buf; + + ret = lan78xx_read_reg(dev, reg, &buf); + if (ret < 0) + return ret; + + buf &= ~mask; + buf |= (mask & data); + + ret = lan78xx_write_reg(dev, reg, buf); + if (ret < 0) + return ret; + + return 0; +} + static int lan78xx_read_stats(struct lan78xx_net *dev, struct lan78xx_statstage *data) { @@ -504,7 +531,7 @@ static int lan78xx_read_stats(struct lan78xx_net *dev, if (likely(ret >= 0)) { src = (u32 *)stats; dst = (u32 *)data; - for (i = 0; i < sizeof(*stats)/sizeof(u32); i++) { + for (i = 0; i < sizeof(*stats) / sizeof(u32); i++) { le32_to_cpus(&src[i]); dst[i] = src[i]; } @@ -518,10 +545,11 @@ static int lan78xx_read_stats(struct lan78xx_net *dev, return ret; } -#define check_counter_rollover(struct1, dev_stats, member) { \ - if (struct1->member < dev_stats.saved.member) \ - dev_stats.rollover_count.member++; \ - } +#define check_counter_rollover(struct1, dev_stats, member) \ + do { \ + if ((struct1)->member < (dev_stats).saved.member) \ + (dev_stats).rollover_count.member++; \ + } while (0) static void lan78xx_check_stat_rollover(struct lan78xx_net *dev, struct lan78xx_statstage *stats) @@ -847,9 +875,9 @@ static int lan78xx_read_raw_otp(struct lan78xx_net *dev, u32 offset, for (i = 0; i < length; i++) { lan78xx_write_reg(dev, OTP_ADDR1, - ((offset + i) >> 8) & OTP_ADDR1_15_11); + ((offset + i) >> 8) & OTP_ADDR1_15_11); lan78xx_write_reg(dev, OTP_ADDR2, - ((offset + i) & OTP_ADDR2_10_3)); + ((offset + i) & OTP_ADDR2_10_3)); lan78xx_write_reg(dev, OTP_FUNC_CMD, OTP_FUNC_CMD_READ_); lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); @@ -903,9 +931,9 @@ static int lan78xx_write_raw_otp(struct lan78xx_net *dev, u32 offset, for (i = 0; i < length; i++) { lan78xx_write_reg(dev, OTP_ADDR1, - ((offset + i) >> 8) & OTP_ADDR1_15_11); + ((offset + i) >> 8) & OTP_ADDR1_15_11); lan78xx_write_reg(dev, OTP_ADDR2, - ((offset + i) & OTP_ADDR2_10_3)); + ((offset + i) & OTP_ADDR2_10_3)); lan78xx_write_reg(dev, OTP_PRGM_DATA, data[i]); lan78xx_write_reg(dev, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_); lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); @@ -962,7 +990,7 @@ static int lan78xx_dataport_wait_not_busy(struct lan78xx_net *dev) usleep_range(40, 100); } - netdev_warn(dev->net, "lan78xx_dataport_wait_not_busy timed out"); + netdev_warn(dev->net, "%s timed out", __func__); return -EIO; } @@ -975,7 +1003,7 @@ static int lan78xx_dataport_write(struct lan78xx_net *dev, u32 ram_select, int i, ret; if (usb_autopm_get_interface(dev->intf) < 0) - return 0; + return 0; mutex_lock(&pdata->dataport_mutex); @@ -1048,9 +1076,9 @@ static void lan78xx_deferred_multicast_write(struct work_struct *param) for (i = 1; i < NUM_OF_MAF; i++) { lan78xx_write_reg(dev, MAF_HI(i), 0); lan78xx_write_reg(dev, MAF_LO(i), - pdata->pfilter_table[i][1]); + pdata->pfilter_table[i][1]); lan78xx_write_reg(dev, MAF_HI(i), - pdata->pfilter_table[i][0]); + pdata->pfilter_table[i][0]); } lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); @@ -1069,11 +1097,12 @@ static void lan78xx_set_multicast(struct net_device *netdev) RFE_CTL_DA_PERFECT_ | RFE_CTL_MCAST_HASH_); for (i = 0; i < DP_SEL_VHF_HASH_LEN; i++) - pdata->mchash_table[i] = 0; + pdata->mchash_table[i] = 0; + /* pfilter_table[0] has own HW address */ for (i = 1; i < NUM_OF_MAF; i++) { - pdata->pfilter_table[i][0] = - pdata->pfilter_table[i][1] = 0; + pdata->pfilter_table[i][0] = 0; + pdata->pfilter_table[i][1] = 0; } pdata->rfe_ctl |= RFE_CTL_BCAST_EN_; @@ -1163,7 +1192,7 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) /* clear LAN78xx interrupt status */ ret = lan78xx_write_reg(dev, INT_STS, INT_STS_PHY_INT_); if (unlikely(ret < 0)) - return -EIO; + return ret; mutex_lock(&phydev->lock); phy_read_status(phydev); @@ -1176,11 +1205,11 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) /* reset MAC */ ret = lan78xx_read_reg(dev, MAC_CR, &buf); if (unlikely(ret < 0)) - return -EIO; + return ret; buf |= MAC_CR_RST_; ret = lan78xx_write_reg(dev, MAC_CR, buf); if (unlikely(ret < 0)) - return -EIO; + return ret; del_timer(&dev->stat_monitor); } else if (link && !dev->link_on) { @@ -1192,18 +1221,30 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) if (ecmd.base.speed == 1000) { /* disable U2 */ ret = lan78xx_read_reg(dev, USB_CFG1, &buf); + if (ret < 0) + return ret; buf &= ~USB_CFG1_DEV_U2_INIT_EN_; ret = lan78xx_write_reg(dev, USB_CFG1, buf); + if (ret < 0) + return ret; /* enable U1 */ ret = lan78xx_read_reg(dev, USB_CFG1, &buf); + if (ret < 0) + return ret; buf |= USB_CFG1_DEV_U1_INIT_EN_; ret = lan78xx_write_reg(dev, USB_CFG1, buf); + if (ret < 0) + return ret; } else { /* enable U1 & U2 */ ret = lan78xx_read_reg(dev, USB_CFG1, &buf); + if (ret < 0) + return ret; buf |= USB_CFG1_DEV_U2_INIT_EN_; buf |= USB_CFG1_DEV_U1_INIT_EN_; ret = lan78xx_write_reg(dev, USB_CFG1, buf); + if (ret < 0) + return ret; } } @@ -1221,6 +1262,8 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) ret = lan78xx_update_flowcontrol(dev, ecmd.base.duplex, ladv, radv); + if (ret < 0) + return ret; if (!timer_pending(&dev->stat_monitor)) { dev->delta = 1; @@ -1231,7 +1274,7 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) tasklet_schedule(&dev->bh); } - return ret; + return 0; } /* some work can't be done in tasklets, so we use keventd @@ -1267,9 +1310,10 @@ static void lan78xx_status(struct lan78xx_net *dev, struct urb *urb) generic_handle_irq(dev->domain_data.phyirq); local_irq_enable(); } - } else + } else { netdev_warn(dev->net, "unexpected interrupt: 0x%08x\n", intdata); + } } static int lan78xx_ethtool_get_eeprom_len(struct net_device *netdev) @@ -1358,7 +1402,7 @@ static void lan78xx_get_wol(struct net_device *netdev, struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); if (usb_autopm_get_interface(dev->intf) < 0) - return; + return; ret = lan78xx_read_reg(dev, USB_CFG0, &buf); if (unlikely(ret < 0)) { @@ -1980,7 +2024,7 @@ static int lan8835_fixup(struct phy_device *phydev) /* RGMII MAC TXC Delay Enable */ lan78xx_write_reg(dev, MAC_RGMII_ID, - MAC_RGMII_ID_TXC_DELAY_EN_); + MAC_RGMII_ID_TXC_DELAY_EN_); /* RGMII TX DLL Tune Adjust */ lan78xx_write_reg(dev, RGMII_TX_BYP_DLL, 0x3D00); @@ -2244,11 +2288,16 @@ static int lan78xx_change_mtu(struct net_device *netdev, int new_mtu) int ll_mtu = new_mtu + netdev->hard_header_len; int old_hard_mtu = dev->hard_mtu; int old_rx_urb_size = dev->rx_urb_size; + int ret; /* no second zero-length packet read wanted after mtu-sized packets */ if ((ll_mtu % dev->maxpacket) == 0) return -EDOM; + ret = usb_autopm_get_interface(dev->intf); + if (ret < 0) + return ret; + lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN); netdev->mtu = new_mtu; @@ -2264,6 +2313,8 @@ static int lan78xx_change_mtu(struct net_device *netdev, int new_mtu) } } + usb_autopm_put_interface(dev->intf); + return 0; } @@ -2420,26 +2471,186 @@ static void lan78xx_init_ltm(struct lan78xx_net *dev) lan78xx_write_reg(dev, LTM_INACTIVE1, regs[5]); } +static int lan78xx_start_hw(struct lan78xx_net *dev, u32 reg, u32 hw_enable) +{ + return lan78xx_update_reg(dev, reg, hw_enable, hw_enable); +} + +static int lan78xx_stop_hw(struct lan78xx_net *dev, u32 reg, u32 hw_enabled, + u32 hw_disabled) +{ + unsigned long timeout; + bool stopped = true; + int ret; + u32 buf; + + /* Stop the h/w block (if not already stopped) */ + + ret = lan78xx_read_reg(dev, reg, &buf); + if (ret < 0) + return ret; + + if (buf & hw_enabled) { + buf &= ~hw_enabled; + + ret = lan78xx_write_reg(dev, reg, buf); + if (ret < 0) + return ret; + + stopped = false; + timeout = jiffies + HW_DISABLE_TIMEOUT; + do { + ret = lan78xx_read_reg(dev, reg, &buf); + if (ret < 0) + return ret; + + if (buf & hw_disabled) + stopped = true; + else + msleep(HW_DISABLE_DELAY_MS); + } while (!stopped && !time_after(jiffies, timeout)); + } + + ret = stopped ? 0 : -ETIME; + + return ret; +} + +static int lan78xx_flush_fifo(struct lan78xx_net *dev, u32 reg, u32 fifo_flush) +{ + return lan78xx_update_reg(dev, reg, fifo_flush, fifo_flush); +} + +static int lan78xx_start_tx_path(struct lan78xx_net *dev) +{ + int ret; + + netif_dbg(dev, drv, dev->net, "start tx path"); + + /* Start the MAC transmitter */ + + ret = lan78xx_start_hw(dev, MAC_TX, MAC_TX_TXEN_); + if (ret < 0) + return ret; + + /* Start the Tx FIFO */ + + ret = lan78xx_start_hw(dev, FCT_TX_CTL, FCT_TX_CTL_EN_); + if (ret < 0) + return ret; + + return 0; +} + +static int lan78xx_stop_tx_path(struct lan78xx_net *dev) +{ + int ret; + + netif_dbg(dev, drv, dev->net, "stop tx path"); + + /* Stop the Tx FIFO */ + + ret = lan78xx_stop_hw(dev, FCT_TX_CTL, FCT_TX_CTL_EN_, FCT_TX_CTL_DIS_); + if (ret < 0) + return ret; + + /* Stop the MAC transmitter */ + + ret = lan78xx_stop_hw(dev, MAC_TX, MAC_TX_TXEN_, MAC_TX_TXD_); + if (ret < 0) + return ret; + + return 0; +} + +/* The caller must ensure the Tx path is stopped before calling + * lan78xx_flush_tx_fifo(). + */ +static int lan78xx_flush_tx_fifo(struct lan78xx_net *dev) +{ + return lan78xx_flush_fifo(dev, FCT_TX_CTL, FCT_TX_CTL_RST_); +} + +static int lan78xx_start_rx_path(struct lan78xx_net *dev) +{ + int ret; + + netif_dbg(dev, drv, dev->net, "start rx path"); + + /* Start the Rx FIFO */ + + ret = lan78xx_start_hw(dev, FCT_RX_CTL, FCT_RX_CTL_EN_); + if (ret < 0) + return ret; + + /* Start the MAC receiver*/ + + ret = lan78xx_start_hw(dev, MAC_RX, MAC_RX_RXEN_); + if (ret < 0) + return ret; + + return 0; +} + +static int lan78xx_stop_rx_path(struct lan78xx_net *dev) +{ + int ret; + + netif_dbg(dev, drv, dev->net, "stop rx path"); + + /* Stop the MAC receiver */ + + ret = lan78xx_stop_hw(dev, MAC_RX, MAC_RX_RXEN_, MAC_RX_RXD_); + if (ret < 0) + return ret; + + /* Stop the Rx FIFO */ + + ret = lan78xx_stop_hw(dev, FCT_RX_CTL, FCT_RX_CTL_EN_, FCT_RX_CTL_DIS_); + if (ret < 0) + return ret; + + return 0; +} + +/* The caller must ensure the Rx path is stopped before calling + * lan78xx_flush_rx_fifo(). + */ +static int lan78xx_flush_rx_fifo(struct lan78xx_net *dev) +{ + return lan78xx_flush_fifo(dev, FCT_RX_CTL, FCT_RX_CTL_RST_); +} + static int lan78xx_reset(struct lan78xx_net *dev) { struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); - u32 buf; - int ret = 0; unsigned long timeout; + int ret; + u32 buf; u8 sig; ret = lan78xx_read_reg(dev, HW_CFG, &buf); + if (ret < 0) + return ret; + buf |= HW_CFG_LRST_; + ret = lan78xx_write_reg(dev, HW_CFG, buf); + if (ret < 0) + return ret; timeout = jiffies + HZ; do { mdelay(1); ret = lan78xx_read_reg(dev, HW_CFG, &buf); + if (ret < 0) + return ret; + if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout on completion of LiteReset"); - return -EIO; + ret = -ETIMEDOUT; + return ret; } } while (buf & HW_CFG_LRST_); @@ -2447,13 +2658,22 @@ static int lan78xx_reset(struct lan78xx_net *dev) /* save DEVID for later usage */ ret = lan78xx_read_reg(dev, ID_REV, &buf); + if (ret < 0) + return ret; + dev->chipid = (buf & ID_REV_CHIP_ID_MASK_) >> 16; dev->chiprev = buf & ID_REV_CHIP_REV_MASK_; /* Respond to the IN token with a NAK */ ret = lan78xx_read_reg(dev, USB_CFG0, &buf); + if (ret < 0) + return ret; + buf |= USB_CFG_BIR_; + ret = lan78xx_write_reg(dev, USB_CFG0, buf); + if (ret < 0) + return ret; /* Init LTM */ lan78xx_init_ltm(dev); @@ -2476,58 +2696,111 @@ static int lan78xx_reset(struct lan78xx_net *dev) } ret = lan78xx_write_reg(dev, BURST_CAP, buf); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, BULK_IN_DLY, DEFAULT_BULK_IN_DELAY); + if (ret < 0) + return ret; ret = lan78xx_read_reg(dev, HW_CFG, &buf); + if (ret < 0) + return ret; + buf |= HW_CFG_MEF_; + ret = lan78xx_write_reg(dev, HW_CFG, buf); + if (ret < 0) + return ret; ret = lan78xx_read_reg(dev, USB_CFG0, &buf); + if (ret < 0) + return ret; + buf |= USB_CFG_BCE_; + ret = lan78xx_write_reg(dev, USB_CFG0, buf); + if (ret < 0) + return ret; /* set FIFO sizes */ buf = (MAX_RX_FIFO_SIZE - 512) / 512; + ret = lan78xx_write_reg(dev, FCT_RX_FIFO_END, buf); + if (ret < 0) + return ret; buf = (MAX_TX_FIFO_SIZE - 512) / 512; + ret = lan78xx_write_reg(dev, FCT_TX_FIFO_END, buf); + if (ret < 0) + return ret; ret = lan78xx_write_reg(dev, INT_STS, INT_STS_CLEAR_ALL_); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, FLOW, 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, FCT_FLOW, 0); + if (ret < 0) + return ret; /* Don't need rfe_ctl_lock during initialisation */ ret = lan78xx_read_reg(dev, RFE_CTL, &pdata->rfe_ctl); + if (ret < 0) + return ret; + pdata->rfe_ctl |= RFE_CTL_BCAST_EN_ | RFE_CTL_DA_PERFECT_; + ret = lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); + if (ret < 0) + return ret; /* Enable or disable checksum offload engines */ - lan78xx_set_features(dev->net, dev->net->features); + ret = lan78xx_set_features(dev->net, dev->net->features); + if (ret < 0) + return ret; lan78xx_set_multicast(dev->net); /* reset PHY */ ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) + return ret; + buf |= PMT_CTL_PHY_RST_; + ret = lan78xx_write_reg(dev, PMT_CTL, buf); + if (ret < 0) + return ret; timeout = jiffies + HZ; do { mdelay(1); ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) + return ret; + if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout waiting for PHY Reset"); - return -EIO; + ret = -ETIMEDOUT; + return ret; } } while ((buf & PMT_CTL_PHY_RST_) || !(buf & PMT_CTL_READY_)); ret = lan78xx_read_reg(dev, MAC_CR, &buf); + if (ret < 0) + return ret; + /* LAN7801 only has RGMII mode */ if (dev->chipid == ID_REV_CHIP_ID_7801_) buf &= ~MAC_CR_GMII_EN_; - if (dev->chipid == ID_REV_CHIP_ID_7800_) { + if (dev->chipid == ID_REV_CHIP_ID_7800_ || + dev->chipid == ID_REV_CHIP_ID_7850_) { ret = lan78xx_read_raw_eeprom(dev, 0, 1, &sig); if (!ret && sig != EEPROM_INDICATOR) { /* Implies there is no external eeprom. Set mac speed */ @@ -2536,27 +2809,13 @@ static int lan78xx_reset(struct lan78xx_net *dev) } } ret = lan78xx_write_reg(dev, MAC_CR, buf); - - ret = lan78xx_read_reg(dev, MAC_TX, &buf); - buf |= MAC_TX_TXEN_; - ret = lan78xx_write_reg(dev, MAC_TX, buf); - - ret = lan78xx_read_reg(dev, FCT_TX_CTL, &buf); - buf |= FCT_TX_CTL_EN_; - ret = lan78xx_write_reg(dev, FCT_TX_CTL, buf); + if (ret < 0) + return ret; ret = lan78xx_set_rx_max_frame_length(dev, dev->net->mtu + VLAN_ETH_HLEN); - ret = lan78xx_read_reg(dev, MAC_RX, &buf); - buf |= MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); - - ret = lan78xx_read_reg(dev, FCT_RX_CTL, &buf); - buf |= FCT_RX_CTL_EN_; - ret = lan78xx_write_reg(dev, FCT_RX_CTL, buf); - - return 0; + return ret; } static void lan78xx_init_stats(struct lan78xx_net *dev) @@ -2590,9 +2849,13 @@ static int lan78xx_open(struct net_device *net) struct lan78xx_net *dev = netdev_priv(net); int ret; + netif_dbg(dev, ifup, dev->net, "open device"); + ret = usb_autopm_get_interface(dev->intf); if (ret < 0) - goto out; + return ret; + + mutex_lock(&dev->dev_mutex); phy_start(net->phydev); @@ -2608,6 +2871,20 @@ static int lan78xx_open(struct net_device *net) } } + ret = lan78xx_flush_rx_fifo(dev); + if (ret < 0) + goto done; + ret = lan78xx_flush_tx_fifo(dev); + if (ret < 0) + goto done; + + ret = lan78xx_start_tx_path(dev); + if (ret < 0) + goto done; + ret = lan78xx_start_rx_path(dev); + if (ret < 0) + goto done; + lan78xx_init_stats(dev); set_bit(EVENT_DEV_OPEN, &dev->flags); @@ -2618,9 +2895,11 @@ static int lan78xx_open(struct net_device *net) lan78xx_defer_kevent(dev, EVENT_LINK_RESET); done: - usb_autopm_put_interface(dev->intf); + mutex_unlock(&dev->dev_mutex); + + if (ret < 0) + usb_autopm_put_interface(dev->intf); -out: return ret; } @@ -2637,38 +2916,56 @@ static void lan78xx_terminate_urbs(struct lan78xx_net *dev) temp = unlink_urbs(dev, &dev->txq) + unlink_urbs(dev, &dev->rxq); /* maybe wait for deletions to finish. */ - while (!skb_queue_empty(&dev->rxq) && - !skb_queue_empty(&dev->txq) && - !skb_queue_empty(&dev->done)) { + while (!skb_queue_empty(&dev->rxq) || + !skb_queue_empty(&dev->txq)) { schedule_timeout(msecs_to_jiffies(UNLINK_TIMEOUT_MS)); set_current_state(TASK_UNINTERRUPTIBLE); netif_dbg(dev, ifdown, dev->net, - "waited for %d urb completions\n", temp); + "waited for %d urb completions", temp); } set_current_state(TASK_RUNNING); dev->wait = NULL; remove_wait_queue(&unlink_wakeup, &wait); + + while (!skb_queue_empty(&dev->done)) { + struct skb_data *entry; + struct sk_buff *skb; + + skb = skb_dequeue(&dev->done); + entry = (struct skb_data *)(skb->cb); + usb_free_urb(entry->urb); + dev_kfree_skb(skb); + } } static int lan78xx_stop(struct net_device *net) { struct lan78xx_net *dev = netdev_priv(net); + netif_dbg(dev, ifup, dev->net, "stop device"); + + mutex_lock(&dev->dev_mutex); + if (timer_pending(&dev->stat_monitor)) del_timer_sync(&dev->stat_monitor); - if (net->phydev) - phy_stop(net->phydev); - clear_bit(EVENT_DEV_OPEN, &dev->flags); netif_stop_queue(net); + tasklet_kill(&dev->bh); + + lan78xx_terminate_urbs(dev); netif_info(dev, ifdown, dev->net, "stop stats: rx/tx %lu/%lu, errs %lu/%lu\n", net->stats.rx_packets, net->stats.tx_packets, net->stats.rx_errors, net->stats.tx_errors); - lan78xx_terminate_urbs(dev); + /* ignore errors that occur stopping the Tx and Rx data paths */ + lan78xx_stop_tx_path(dev); + lan78xx_stop_rx_path(dev); + + if (net->phydev) + phy_stop(net->phydev); usb_kill_urb(dev->urb_intr); @@ -2678,12 +2975,17 @@ static int lan78xx_stop(struct net_device *net) * can't flush_scheduled_work() until we drop rtnl (later), * else workers could deadlock; so make workers a NOP. */ - dev->flags = 0; + clear_bit(EVENT_TX_HALT, &dev->flags); + clear_bit(EVENT_RX_HALT, &dev->flags); + clear_bit(EVENT_LINK_RESET, &dev->flags); + clear_bit(EVENT_STAT_UPDATE, &dev->flags); + cancel_delayed_work_sync(&dev->wq); - tasklet_kill(&dev->bh); usb_autopm_put_interface(dev->intf); + mutex_unlock(&dev->dev_mutex); + return 0; } @@ -2806,6 +3108,9 @@ lan78xx_start_xmit(struct sk_buff *skb, struct net_device *net) struct lan78xx_net *dev = netdev_priv(net); struct sk_buff *skb2 = NULL; + if (test_bit(EVENT_DEV_ASLEEP, &dev->flags)) + schedule_delayed_work(&dev->wq, 0); + if (skb) { skb_tx_timestamp(skb); skb2 = lan78xx_tx_prep(dev, skb, GFP_ATOMIC); @@ -3333,9 +3638,10 @@ drop: if (skb) dev_kfree_skb_any(skb); usb_free_urb(urb); - } else + } else { netif_dbg(dev, tx_queued, dev->net, "> tx, len %d, type 0x%x\n", length, skb->protocol); + } } static void lan78xx_rx_bh(struct lan78xx_net *dev) @@ -3411,18 +3717,17 @@ static void lan78xx_delayedwork(struct work_struct *work) dev = container_of(work, struct lan78xx_net, wq.work); + if (usb_autopm_get_interface(dev->intf) < 0) + return; + if (test_bit(EVENT_TX_HALT, &dev->flags)) { unlink_urbs(dev, &dev->txq); - status = usb_autopm_get_interface(dev->intf); - if (status < 0) - goto fail_pipe; + status = usb_clear_halt(dev->udev, dev->pipe_out); - usb_autopm_put_interface(dev->intf); if (status < 0 && status != -EPIPE && status != -ESHUTDOWN) { if (netif_msg_tx_err(dev)) -fail_pipe: netdev_err(dev->net, "can't clear tx halt, status %d\n", status); @@ -3432,18 +3737,14 @@ fail_pipe: netif_wake_queue(dev->net); } } + if (test_bit(EVENT_RX_HALT, &dev->flags)) { unlink_urbs(dev, &dev->rxq); - status = usb_autopm_get_interface(dev->intf); - if (status < 0) - goto fail_halt; status = usb_clear_halt(dev->udev, dev->pipe_in); - usb_autopm_put_interface(dev->intf); if (status < 0 && status != -EPIPE && status != -ESHUTDOWN) { if (netif_msg_rx_err(dev)) -fail_halt: netdev_err(dev->net, "can't clear rx halt, status %d\n", status); @@ -3457,16 +3758,9 @@ fail_halt: int ret = 0; clear_bit(EVENT_LINK_RESET, &dev->flags); - status = usb_autopm_get_interface(dev->intf); - if (status < 0) - goto skip_reset; if (lan78xx_link_reset(dev) < 0) { - usb_autopm_put_interface(dev->intf); -skip_reset: netdev_info(dev->net, "link reset failed (%d)\n", ret); - } else { - usb_autopm_put_interface(dev->intf); } } @@ -3480,6 +3774,8 @@ skip_reset: dev->delta = min((dev->delta * 2), 50); } + + usb_autopm_put_interface(dev->intf); } static void intr_complete(struct urb *urb) @@ -3609,8 +3905,8 @@ static int lan78xx_probe(struct usb_interface *intf, struct net_device *netdev; struct usb_device *udev; int ret; - unsigned maxp; - unsigned period; + unsigned int maxp; + unsigned int period; u8 *buf = NULL; udev = interface_to_usbdev(intf); @@ -3639,6 +3935,7 @@ static int lan78xx_probe(struct usb_interface *intf, skb_queue_head_init(&dev->rxq_pause); skb_queue_head_init(&dev->txq_pend); mutex_init(&dev->phy_mutex); + mutex_init(&dev->dev_mutex); tasklet_init(&dev->bh, lan78xx_bh, (unsigned long)dev); INIT_DELAYED_WORK(&dev->wq, lan78xx_delayedwork); @@ -3781,37 +4078,119 @@ static u16 lan78xx_wakeframe_crc16(const u8 *buf, int len) return crc; } -static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) +static int lan78xx_set_auto_suspend(struct lan78xx_net *dev) { u32 buf; - int mask_index; - u16 crc; - u32 temp_wucsr; - u32 temp_pmt_ctl; + int ret; + + ret = lan78xx_stop_tx_path(dev); + if (ret < 0) + return ret; + + ret = lan78xx_stop_rx_path(dev); + if (ret < 0) + return ret; + + /* auto suspend (selective suspend) */ + + ret = lan78xx_write_reg(dev, WUCSR, 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUCSR2, 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); + if (ret < 0) + return ret; + + /* set goodframe wakeup */ + + ret = lan78xx_read_reg(dev, WUCSR, &buf); + if (ret < 0) + return ret; + + buf |= WUCSR_RFE_WAKE_EN_; + buf |= WUCSR_STORE_WAKE_; + + ret = lan78xx_write_reg(dev, WUCSR, buf); + if (ret < 0) + return ret; + + ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) + return ret; + + buf &= ~PMT_CTL_RES_CLR_WKP_EN_; + buf |= PMT_CTL_RES_CLR_WKP_STS_; + buf |= PMT_CTL_PHY_WAKE_EN_; + buf |= PMT_CTL_WOL_EN_; + buf &= ~PMT_CTL_SUS_MODE_MASK_; + buf |= PMT_CTL_SUS_MODE_3_; + + ret = lan78xx_write_reg(dev, PMT_CTL, buf); + if (ret < 0) + return ret; + + ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) + return ret; + + buf |= PMT_CTL_WUPS_MASK_; + + ret = lan78xx_write_reg(dev, PMT_CTL, buf); + if (ret < 0) + return ret; + + ret = lan78xx_start_rx_path(dev); + + return ret; +} + +static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) +{ const u8 ipv4_multicast[3] = { 0x01, 0x00, 0x5E }; const u8 ipv6_multicast[3] = { 0x33, 0x33 }; const u8 arp_type[2] = { 0x08, 0x06 }; + u32 temp_pmt_ctl; + int mask_index; + u32 temp_wucsr; + u32 buf; + u16 crc; + int ret; - lan78xx_read_reg(dev, MAC_TX, &buf); - buf &= ~MAC_TX_TXEN_; - lan78xx_write_reg(dev, MAC_TX, buf); - lan78xx_read_reg(dev, MAC_RX, &buf); - buf &= ~MAC_RX_RXEN_; - lan78xx_write_reg(dev, MAC_RX, buf); + ret = lan78xx_stop_tx_path(dev); + if (ret < 0) + return ret; + ret = lan78xx_stop_rx_path(dev); + if (ret < 0) + return ret; - lan78xx_write_reg(dev, WUCSR, 0); - lan78xx_write_reg(dev, WUCSR2, 0); - lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); + ret = lan78xx_write_reg(dev, WUCSR, 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUCSR2, 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); + if (ret < 0) + return ret; temp_wucsr = 0; temp_pmt_ctl = 0; - lan78xx_read_reg(dev, PMT_CTL, &temp_pmt_ctl); + + ret = lan78xx_read_reg(dev, PMT_CTL, &temp_pmt_ctl); + if (ret < 0) + return ret; + temp_pmt_ctl &= ~PMT_CTL_RES_CLR_WKP_EN_; temp_pmt_ctl |= PMT_CTL_RES_CLR_WKP_STS_; - for (mask_index = 0; mask_index < NUM_OF_WUF_CFG; mask_index++) - lan78xx_write_reg(dev, WUF_CFG(mask_index), 0); + for (mask_index = 0; mask_index < NUM_OF_WUF_CFG; mask_index++) { + ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), 0); + if (ret < 0) + return ret; + } mask_index = 0; if (wol & WAKE_PHY) { @@ -3840,30 +4219,52 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) /* set WUF_CFG & WUF_MASK for IPv4 Multicast */ crc = lan78xx_wakeframe_crc16(ipv4_multicast, 3); - lan78xx_write_reg(dev, WUF_CFG(mask_index), + ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), WUF_CFGX_EN_ | WUF_CFGX_TYPE_MCAST_ | (0 << WUF_CFGX_OFFSET_SHIFT_) | (crc & WUF_CFGX_CRC16_MASK_)); + if (ret < 0) + return ret; + + ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 7); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); + if (ret < 0) + return ret; - lan78xx_write_reg(dev, WUF_MASK0(mask_index), 7); - lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); - lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); - lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); mask_index++; /* for IPv6 Multicast */ crc = lan78xx_wakeframe_crc16(ipv6_multicast, 2); - lan78xx_write_reg(dev, WUF_CFG(mask_index), + ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), WUF_CFGX_EN_ | WUF_CFGX_TYPE_MCAST_ | (0 << WUF_CFGX_OFFSET_SHIFT_) | (crc & WUF_CFGX_CRC16_MASK_)); + if (ret < 0) + return ret; + + ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 3); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); + if (ret < 0) + return ret; - lan78xx_write_reg(dev, WUF_MASK0(mask_index), 3); - lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); - lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); - lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); mask_index++; temp_pmt_ctl |= PMT_CTL_WOL_EN_; @@ -3884,16 +4285,27 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) * for packettype (offset 12,13) = ARP (0x0806) */ crc = lan78xx_wakeframe_crc16(arp_type, 2); - lan78xx_write_reg(dev, WUF_CFG(mask_index), + ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), WUF_CFGX_EN_ | WUF_CFGX_TYPE_ALL_ | (0 << WUF_CFGX_OFFSET_SHIFT_) | (crc & WUF_CFGX_CRC16_MASK_)); + if (ret < 0) + return ret; + + ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 0x3000); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); + if (ret < 0) + return ret; - lan78xx_write_reg(dev, WUF_MASK0(mask_index), 0x3000); - lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); - lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); - lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); mask_index++; temp_pmt_ctl |= PMT_CTL_WOL_EN_; @@ -3901,7 +4313,9 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_; } - lan78xx_write_reg(dev, WUCSR, temp_wucsr); + ret = lan78xx_write_reg(dev, WUCSR, temp_wucsr); + if (ret < 0) + return ret; /* when multiple WOL bits are set */ if (hweight_long((unsigned long)wol) > 1) { @@ -3909,33 +4323,45 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) temp_pmt_ctl &= ~PMT_CTL_SUS_MODE_MASK_; temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_; } - lan78xx_write_reg(dev, PMT_CTL, temp_pmt_ctl); + ret = lan78xx_write_reg(dev, PMT_CTL, temp_pmt_ctl); + if (ret < 0) + return ret; /* clear WUPS */ - lan78xx_read_reg(dev, PMT_CTL, &buf); + ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) + return ret; + buf |= PMT_CTL_WUPS_MASK_; - lan78xx_write_reg(dev, PMT_CTL, buf); - lan78xx_read_reg(dev, MAC_RX, &buf); - buf |= MAC_RX_RXEN_; - lan78xx_write_reg(dev, MAC_RX, buf); + ret = lan78xx_write_reg(dev, PMT_CTL, buf); + if (ret < 0) + return ret; - return 0; + ret = lan78xx_start_rx_path(dev); + + return ret; } static int lan78xx_suspend(struct usb_interface *intf, pm_message_t message) { struct lan78xx_net *dev = usb_get_intfdata(intf); - struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); - u32 buf; + bool dev_open; int ret; - if (!dev->suspend_count++) { + mutex_lock(&dev->dev_mutex); + + netif_dbg(dev, ifdown, dev->net, + "suspending: pm event %#x", message.event); + + dev_open = test_bit(EVENT_DEV_OPEN, &dev->flags); + + if (dev_open) { spin_lock_irq(&dev->txq.lock); /* don't autosuspend while transmitting */ if ((skb_queue_len(&dev->txq) || skb_queue_len(&dev->txq_pend)) && - PMSG_IS_AUTO(message)) { + PMSG_IS_AUTO(message)) { spin_unlock_irq(&dev->txq.lock); ret = -EBUSY; goto out; @@ -3944,129 +4370,207 @@ static int lan78xx_suspend(struct usb_interface *intf, pm_message_t message) spin_unlock_irq(&dev->txq.lock); } - /* stop TX & RX */ - ret = lan78xx_read_reg(dev, MAC_TX, &buf); - buf &= ~MAC_TX_TXEN_; - ret = lan78xx_write_reg(dev, MAC_TX, buf); - ret = lan78xx_read_reg(dev, MAC_RX, &buf); - buf &= ~MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); + /* stop RX */ + ret = lan78xx_stop_rx_path(dev); + if (ret < 0) + goto out; - /* empty out the rx and queues */ + ret = lan78xx_flush_rx_fifo(dev); + if (ret < 0) + goto out; + + /* stop Tx */ + ret = lan78xx_stop_tx_path(dev); + if (ret < 0) + goto out; + + /* empty out the Rx and Tx queues */ netif_device_detach(dev->net); lan78xx_terminate_urbs(dev); usb_kill_urb(dev->urb_intr); /* reattach */ netif_device_attach(dev->net); - } - if (test_bit(EVENT_DEV_ASLEEP, &dev->flags)) { del_timer(&dev->stat_monitor); if (PMSG_IS_AUTO(message)) { - /* auto suspend (selective suspend) */ - ret = lan78xx_read_reg(dev, MAC_TX, &buf); - buf &= ~MAC_TX_TXEN_; - ret = lan78xx_write_reg(dev, MAC_TX, buf); - ret = lan78xx_read_reg(dev, MAC_RX, &buf); - buf &= ~MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); + ret = lan78xx_set_auto_suspend(dev); + if (ret < 0) + goto out; + } else { + struct lan78xx_priv *pdata; - ret = lan78xx_write_reg(dev, WUCSR, 0); - ret = lan78xx_write_reg(dev, WUCSR2, 0); - ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); + pdata = (struct lan78xx_priv *)(dev->data[0]); + netif_carrier_off(dev->net); + ret = lan78xx_set_suspend(dev, pdata->wol); + if (ret < 0) + goto out; + } + } else { + /* Interface is down; don't allow WOL and PHY + * events to wake up the host + */ + u32 buf; - /* set goodframe wakeup */ - ret = lan78xx_read_reg(dev, WUCSR, &buf); + set_bit(EVENT_DEV_ASLEEP, &dev->flags); - buf |= WUCSR_RFE_WAKE_EN_; - buf |= WUCSR_STORE_WAKE_; + ret = lan78xx_write_reg(dev, WUCSR, 0); + if (ret < 0) + goto out; + ret = lan78xx_write_reg(dev, WUCSR2, 0); + if (ret < 0) + goto out; - ret = lan78xx_write_reg(dev, WUCSR, buf); + ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) + goto out; - ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + buf &= ~PMT_CTL_RES_CLR_WKP_EN_; + buf |= PMT_CTL_RES_CLR_WKP_STS_; + buf &= ~PMT_CTL_SUS_MODE_MASK_; + buf |= PMT_CTL_SUS_MODE_3_; - buf &= ~PMT_CTL_RES_CLR_WKP_EN_; - buf |= PMT_CTL_RES_CLR_WKP_STS_; + ret = lan78xx_write_reg(dev, PMT_CTL, buf); + if (ret < 0) + goto out; - buf |= PMT_CTL_PHY_WAKE_EN_; - buf |= PMT_CTL_WOL_EN_; - buf &= ~PMT_CTL_SUS_MODE_MASK_; - buf |= PMT_CTL_SUS_MODE_3_; + ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) + goto out; - ret = lan78xx_write_reg(dev, PMT_CTL, buf); + buf |= PMT_CTL_WUPS_MASK_; - ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + ret = lan78xx_write_reg(dev, PMT_CTL, buf); + if (ret < 0) + goto out; + } + + ret = 0; +out: + mutex_unlock(&dev->dev_mutex); + + return ret; +} - buf |= PMT_CTL_WUPS_MASK_; +static bool lan78xx_submit_deferred_urbs(struct lan78xx_net *dev) +{ + bool pipe_halted = false; + struct urb *urb; + + while ((urb = usb_get_from_anchor(&dev->deferred))) { + struct sk_buff *skb = urb->context; + int ret; + + if (!netif_device_present(dev->net) || + !netif_carrier_ok(dev->net) || + pipe_halted) { + usb_free_urb(urb); + dev_kfree_skb(skb); + continue; + } - ret = lan78xx_write_reg(dev, PMT_CTL, buf); + ret = usb_submit_urb(urb, GFP_ATOMIC); - ret = lan78xx_read_reg(dev, MAC_RX, &buf); - buf |= MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); + if (ret == 0) { + netif_trans_update(dev->net); + lan78xx_queue_skb(&dev->txq, skb, tx_start); } else { - lan78xx_set_suspend(dev, pdata->wol); + usb_free_urb(urb); + dev_kfree_skb(skb); + + if (ret == -EPIPE) { + netif_stop_queue(dev->net); + pipe_halted = true; + } else if (ret == -ENODEV) { + netif_device_detach(dev->net); + } } } - ret = 0; -out: - return ret; + return pipe_halted; } static int lan78xx_resume(struct usb_interface *intf) { struct lan78xx_net *dev = usb_get_intfdata(intf); - struct sk_buff *skb; - struct urb *res; + bool dev_open; int ret; - u32 buf; - if (!timer_pending(&dev->stat_monitor)) { - dev->delta = 1; - mod_timer(&dev->stat_monitor, - jiffies + STAT_UPDATE_TIMER); - } + mutex_lock(&dev->dev_mutex); - if (!--dev->suspend_count) { - /* resume interrupt URBs */ - if (dev->urb_intr && test_bit(EVENT_DEV_OPEN, &dev->flags)) - usb_submit_urb(dev->urb_intr, GFP_NOIO); + netif_dbg(dev, ifup, dev->net, "resuming device"); + + dev_open = test_bit(EVENT_DEV_OPEN, &dev->flags); + + if (dev_open) { + bool pipe_halted = false; + + ret = lan78xx_flush_tx_fifo(dev); + if (ret < 0) + goto out; + + if (dev->urb_intr) { + int ret = usb_submit_urb(dev->urb_intr, GFP_KERNEL); - spin_lock_irq(&dev->txq.lock); - while ((res = usb_get_from_anchor(&dev->deferred))) { - skb = (struct sk_buff *)res->context; - ret = usb_submit_urb(res, GFP_ATOMIC); if (ret < 0) { - dev_kfree_skb_any(skb); - usb_free_urb(res); - usb_autopm_put_interface_async(dev->intf); - } else { - netif_trans_update(dev->net); - lan78xx_queue_skb(&dev->txq, skb, tx_start); + if (ret == -ENODEV) + netif_device_detach(dev->net); + + netdev_warn(dev->net, "Failed to submit intr URB"); } } + spin_lock_irq(&dev->txq.lock); + + if (netif_device_present(dev->net)) { + pipe_halted = lan78xx_submit_deferred_urbs(dev); + + if (pipe_halted) + lan78xx_defer_kevent(dev, EVENT_TX_HALT); + } + clear_bit(EVENT_DEV_ASLEEP, &dev->flags); + spin_unlock_irq(&dev->txq.lock); - if (test_bit(EVENT_DEV_OPEN, &dev->flags)) { - if (!(skb_queue_len(&dev->txq) >= dev->tx_qlen)) - netif_start_queue(dev->net); - tasklet_schedule(&dev->bh); + if (!pipe_halted && + netif_device_present(dev->net) && + (skb_queue_len(&dev->txq) < dev->tx_qlen)) + netif_start_queue(dev->net); + + ret = lan78xx_start_tx_path(dev); + if (ret < 0) + goto out; + + tasklet_schedule(&dev->bh); + + if (!timer_pending(&dev->stat_monitor)) { + dev->delta = 1; + mod_timer(&dev->stat_monitor, + jiffies + STAT_UPDATE_TIMER); } + + } else { + clear_bit(EVENT_DEV_ASLEEP, &dev->flags); } ret = lan78xx_write_reg(dev, WUCSR2, 0); + if (ret < 0) + goto out; ret = lan78xx_write_reg(dev, WUCSR, 0); + if (ret < 0) + goto out; ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); + if (ret < 0) + goto out; ret = lan78xx_write_reg(dev, WUCSR2, WUCSR2_NS_RCD_ | WUCSR2_ARP_RCD_ | WUCSR2_IPV6_TCPSYN_RCD_ | WUCSR2_IPV4_TCPSYN_RCD_); + if (ret < 0) + goto out; ret = lan78xx_write_reg(dev, WUCSR, WUCSR_EEE_TX_WAKE_ | WUCSR_EEE_RX_WAKE_ | @@ -4075,23 +4579,32 @@ static int lan78xx_resume(struct usb_interface *intf) WUCSR_WUFR_ | WUCSR_MPR_ | WUCSR_BCST_FR_); + if (ret < 0) + goto out; - ret = lan78xx_read_reg(dev, MAC_TX, &buf); - buf |= MAC_TX_TXEN_; - ret = lan78xx_write_reg(dev, MAC_TX, buf); + ret = 0; +out: + mutex_unlock(&dev->dev_mutex); - return 0; + return ret; } static int lan78xx_reset_resume(struct usb_interface *intf) { struct lan78xx_net *dev = usb_get_intfdata(intf); + int ret; - lan78xx_reset(dev); + netif_dbg(dev, ifup, dev->net, "(reset) resuming device"); + + ret = lan78xx_reset(dev); + if (ret < 0) + return ret; phy_start(dev->net->phydev); - return lan78xx_resume(intf); + ret = lan78xx_resume(intf); + + return ret; } static const struct usb_device_id products[] = { diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index 681e0def6..a5332e991 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -736,7 +736,9 @@ static int sr9800_bind(struct usbnet *dev, struct usb_interface *intf) data->eeprom_len = SR9800_EEPROM_LEN; - usbnet_get_endpoints(dev, intf); + ret = usbnet_get_endpoints(dev, intf); + if (ret) + goto out; /* LED Setting Rule : * AABB:CCDD diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 2fd5d2b7a..4029c56df 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2819,10 +2819,11 @@ static int virtnet_find_vqs(struct virtnet_info *vi) { vq_callback_t **callbacks; struct virtqueue **vqs; - int ret = -ENOMEM; - int i, total_vqs; const char **names; + int ret = -ENOMEM; + int total_vqs; bool *ctx; + u16 i; /* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by * possible N-1 RX/TX queue pairs used in multiqueue mode, followed by @@ -2859,8 +2860,8 @@ static int virtnet_find_vqs(struct virtnet_info *vi) for (i = 0; i < vi->max_queue_pairs; i++) { callbacks[rxq2vq(i)] = skb_recv_done; callbacks[txq2vq(i)] = skb_xmit_done; - sprintf(vi->rq[i].name, "input.%d", i); - sprintf(vi->sq[i].name, "output.%d", i); + sprintf(vi->rq[i].name, "input.%u", i); + sprintf(vi->sq[i].name, "output.%u", i); names[rxq2vq(i)] = vi->rq[i].name; names[txq2vq(i)] = vi->sq[i].name; if (ctx) diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 3096769e7..b173497a3 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -1778,6 +1778,10 @@ static bool vxlan_set_mac(struct vxlan_dev *vxlan, if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr)) return false; + /* Ignore packets from invalid src-address */ + if (!is_valid_ether_addr(eth_hdr(skb)->h_source)) + return false; + /* Get address from the outer IP header */ if (vxlan_get_sk_family(vs) == AF_INET) { saddr.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index f5bc279c9..9dc02fa51 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -164,8 +164,8 @@ get_peer(struct wg_peer *peer, struct sk_buff *skb, struct dump_ctx *ctx) if (!allowedips_node) goto no_allowedips; if (!ctx->allowedips_seq) - ctx->allowedips_seq = peer->device->peer_allowedips.seq; - else if (ctx->allowedips_seq != peer->device->peer_allowedips.seq) + ctx->allowedips_seq = ctx->wg->peer_allowedips.seq; + else if (ctx->allowedips_seq != ctx->wg->peer_allowedips.seq) goto no_allowedips; allowedips_nest = nla_nest_start(skb, WGPEER_A_ALLOWEDIPS); @@ -255,17 +255,17 @@ static int wg_get_device_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!peers_nest) goto out; ret = 0; - /* If the last cursor was removed via list_del_init in peer_remove, then + lockdep_assert_held(&wg->device_update_lock); + /* If the last cursor was removed in peer_remove or peer_remove_all, then * we just treat this the same as there being no more peers left. The * reason is that seq_nr should indicate to userspace that this isn't a * coherent dump anyway, so they'll try again. */ if (list_empty(&wg->peer_list) || - (ctx->next_peer && list_empty(&ctx->next_peer->peer_list))) { + (ctx->next_peer && ctx->next_peer->is_dead)) { nla_nest_cancel(skb, peers_nest); goto out; } - lockdep_assert_held(&wg->device_update_lock); peer = list_prepare_entry(ctx->next_peer, &wg->peer_list, peer_list); list_for_each_entry_continue(peer, &wg->peer_list, peer_list) { if (get_peer(peer, skb, ctx)) { diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index d38b24339..ed274e9bd 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -258,7 +258,7 @@ static bool decrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair) if (unlikely(!READ_ONCE(keypair->receiving.is_valid) || wg_birthdate_has_expired(keypair->receiving.birthdate, REJECT_AFTER_TIME) || - keypair->receiving_counter.counter >= REJECT_AFTER_MESSAGES)) { + READ_ONCE(keypair->receiving_counter.counter) >= REJECT_AFTER_MESSAGES)) { WRITE_ONCE(keypair->receiving.is_valid, false); return false; } @@ -325,7 +325,7 @@ static bool counter_validate(struct noise_replay_counter *counter, u64 their_cou for (i = 1; i <= top; ++i) counter->backtrack[(i + index_current) & ((COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1)] = 0; - counter->counter = their_counter; + WRITE_ONCE(counter->counter, their_counter); } index &= (COUNTER_BITS_TOTAL / BITS_PER_LONG) - 1; @@ -470,7 +470,7 @@ int wg_packet_rx_poll(struct napi_struct *napi, int budget) net_dbg_ratelimited("%s: Packet has invalid nonce %llu (max %llu)\n", peer->device->dev->name, PACKET_CB(skb)->nonce, - keypair->receiving_counter.counter); + READ_ONCE(keypair->receiving_counter.counter)); goto next; } diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c index d0967bb1f..57ac80997 100644 --- a/drivers/net/wireless/ath/ath10k/core.c +++ b/drivers/net/wireless/ath/ath10k/core.c @@ -3381,13 +3381,10 @@ EXPORT_SYMBOL(ath10k_core_create); void ath10k_core_destroy(struct ath10k *ar) { - flush_workqueue(ar->workqueue); destroy_workqueue(ar->workqueue); - flush_workqueue(ar->workqueue_aux); destroy_workqueue(ar->workqueue_aux); - flush_workqueue(ar->workqueue_tx_complete); destroy_workqueue(ar->workqueue_tx_complete); ath10k_debug_destroy(ar); diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c index 0fe639710..9d1b0890f 100644 --- a/drivers/net/wireless/ath/ath10k/sdio.c +++ b/drivers/net/wireless/ath/ath10k/sdio.c @@ -2651,7 +2651,6 @@ static void ath10k_sdio_remove(struct sdio_func *func) ath10k_core_destroy(ar); - flush_workqueue(ar_sdio->workqueue); destroy_workqueue(ar_sdio->workqueue); } diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c index 4f2fbc610..0eeb74245 100644 --- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c +++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c @@ -844,6 +844,10 @@ ath10k_wmi_tlv_op_pull_mgmt_tx_compl_ev(struct ath10k *ar, struct sk_buff *skb, } ev = tb[WMI_TLV_TAG_STRUCT_MGMT_TX_COMPL_EVENT]; + if (!ev) { + kfree(tb); + return -EPROTO; + } arg->desc_id = ev->desc_id; arg->status = ev->status; diff --git a/drivers/net/wireless/ath/ath9k/antenna.c b/drivers/net/wireless/ath/ath9k/antenna.c index 988222cea..acc84e671 100644 --- a/drivers/net/wireless/ath/ath9k/antenna.c +++ b/drivers/net/wireless/ath/ath9k/antenna.c @@ -643,7 +643,7 @@ static void ath_ant_try_scan(struct ath_ant_comb *antcomb, conf->main_lna_conf = ATH_ANT_DIV_COMB_LNA1; conf->alt_lna_conf = ATH_ANT_DIV_COMB_LNA1_PLUS_LNA2; } else if (antcomb->rssi_sub > - antcomb->rssi_lna1) { + antcomb->rssi_lna2) { /* set to A-B */ conf->main_lna_conf = ATH_ANT_DIV_COMB_LNA1; conf->alt_lna_conf = ATH_ANT_DIV_COMB_LNA1_MINUS_LNA2; diff --git a/drivers/net/wireless/ath/ath9k/htc.h b/drivers/net/wireless/ath/ath9k/htc.h index 237f4ec2c..6c33e898b 100644 --- a/drivers/net/wireless/ath/ath9k/htc.h +++ b/drivers/net/wireless/ath/ath9k/htc.h @@ -306,7 +306,6 @@ struct ath9k_htc_tx { DECLARE_BITMAP(tx_slot, MAX_TX_BUF_NUM); struct timer_list cleanup_timer; spinlock_t tx_lock; - bool initialized; }; struct ath9k_htc_tx_ctl { @@ -515,6 +514,7 @@ struct ath9k_htc_priv { unsigned long ps_usecount; bool ps_enabled; bool ps_idle; + bool initialized; #ifdef CONFIG_MAC80211_LEDS enum led_brightness brightness; diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c index 96a3185a9..b01418537 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c @@ -966,6 +966,10 @@ int ath9k_htc_probe_device(struct htc_target *htc_handle, struct device *dev, htc_handle->drv_priv = priv; + /* Allow ath9k_wmi_event_tasklet() to operate. */ + smp_wmb(); + priv->initialized = true; + return 0; err_init: diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c index 622fc7f17..95146ec75 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c @@ -647,9 +647,10 @@ void ath9k_htc_txstatus(struct ath9k_htc_priv *priv, void *wmi_event) struct ath9k_htc_tx_event *tx_pend; int i; - for (i = 0; i < txs->cnt; i++) { - WARN_ON(txs->cnt > HTC_MAX_TX_STATUS); + if (WARN_ON_ONCE(txs->cnt > HTC_MAX_TX_STATUS)) + return; + for (i = 0; i < txs->cnt; i++) { __txs = &txs->txstatus[i]; skb = ath9k_htc_tx_get_packet(priv, __txs); @@ -809,10 +810,6 @@ int ath9k_tx_init(struct ath9k_htc_priv *priv) skb_queue_head_init(&priv->tx.data_vo_queue); skb_queue_head_init(&priv->tx.tx_failed); - /* Allow ath9k_wmi_event_tasklet(WMI_TXSTATUS_EVENTID) to operate. */ - smp_wmb(); - priv->tx.initialized = true; - return 0; } diff --git a/drivers/net/wireless/ath/ath9k/wmi.c b/drivers/net/wireless/ath/ath9k/wmi.c index 1476b42b5..805ad31ed 100644 --- a/drivers/net/wireless/ath/ath9k/wmi.c +++ b/drivers/net/wireless/ath/ath9k/wmi.c @@ -155,6 +155,12 @@ void ath9k_wmi_event_tasklet(struct tasklet_struct *t) } spin_unlock_irqrestore(&wmi->wmi_lock, flags); + /* Check if ath9k_htc_probe_device() completed. */ + if (!data_race(priv->initialized)) { + kfree_skb(skb); + continue; + } + hdr = (struct wmi_cmd_hdr *) skb->data; cmd_id = be16_to_cpu(hdr->command_id); wmi_event = skb_pull(skb, sizeof(struct wmi_cmd_hdr)); @@ -169,10 +175,6 @@ void ath9k_wmi_event_tasklet(struct tasklet_struct *t) &wmi->drv_priv->fatal_work); break; case WMI_TXSTATUS_EVENTID: - /* Check if ath9k_tx_init() completed. */ - if (!data_race(priv->tx.initialized)) - break; - spin_lock_bh(&priv->tx.tx_lock); if (priv->tx.flags & ATH9K_HTC_OP_TX_DRAIN) { spin_unlock_bh(&priv->tx.tx_lock); diff --git a/drivers/net/wireless/broadcom/b43/b43.h b/drivers/net/wireless/broadcom/b43/b43.h index 67b4bac04..c0d8fc0b2 100644 --- a/drivers/net/wireless/broadcom/b43/b43.h +++ b/drivers/net/wireless/broadcom/b43/b43.h @@ -1082,6 +1082,22 @@ static inline bool b43_using_pio_transfers(struct b43_wldev *dev) return dev->__using_pio_transfers; } +static inline void b43_wake_queue(struct b43_wldev *dev, int queue_prio) +{ + if (dev->qos_enabled) + ieee80211_wake_queue(dev->wl->hw, queue_prio); + else + ieee80211_wake_queue(dev->wl->hw, 0); +} + +static inline void b43_stop_queue(struct b43_wldev *dev, int queue_prio) +{ + if (dev->qos_enabled) + ieee80211_stop_queue(dev->wl->hw, queue_prio); + else + ieee80211_stop_queue(dev->wl->hw, 0); +} + /* Message printing */ __printf(2, 3) void b43info(struct b43_wl *wl, const char *fmt, ...); __printf(2, 3) void b43err(struct b43_wl *wl, const char *fmt, ...); diff --git a/drivers/net/wireless/broadcom/b43/dma.c b/drivers/net/wireless/broadcom/b43/dma.c index 9a7c62bd5..cfaf2f9d6 100644 --- a/drivers/net/wireless/broadcom/b43/dma.c +++ b/drivers/net/wireless/broadcom/b43/dma.c @@ -1399,7 +1399,7 @@ int b43_dma_tx(struct b43_wldev *dev, struct sk_buff *skb) should_inject_overflow(ring)) { /* This TX ring is full. */ unsigned int skb_mapping = skb_get_queue_mapping(skb); - ieee80211_stop_queue(dev->wl->hw, skb_mapping); + b43_stop_queue(dev, skb_mapping); dev->wl->tx_queue_stopped[skb_mapping] = true; ring->stopped = true; if (b43_debug(dev, B43_DBG_DMAVERBOSE)) { @@ -1570,7 +1570,7 @@ void b43_dma_handle_txstatus(struct b43_wldev *dev, } else { /* If the driver queue is running wake the corresponding * mac80211 queue. */ - ieee80211_wake_queue(dev->wl->hw, ring->queue_prio); + b43_wake_queue(dev, ring->queue_prio); if (b43_debug(dev, B43_DBG_DMAVERBOSE)) { b43dbg(dev->wl, "Woke up TX ring %d\n", ring->index); } diff --git a/drivers/net/wireless/broadcom/b43/main.c b/drivers/net/wireless/broadcom/b43/main.c index f175dbaff..29f97ab9b 100644 --- a/drivers/net/wireless/broadcom/b43/main.c +++ b/drivers/net/wireless/broadcom/b43/main.c @@ -2587,7 +2587,8 @@ static void b43_request_firmware(struct work_struct *work) start_ieee80211: wl->hw->queues = B43_QOS_QUEUE_NUM; - if (!modparam_qos || dev->fw.opensource) + if (!modparam_qos || dev->fw.opensource || + dev->dev->chip_id == BCMA_CHIP_ID_BCM4331) wl->hw->queues = 1; err = ieee80211_register_hw(wl->hw); @@ -3603,7 +3604,7 @@ static void b43_tx_work(struct work_struct *work) err = b43_dma_tx(dev, skb); if (err == -ENOSPC) { wl->tx_queue_stopped[queue_num] = true; - ieee80211_stop_queue(wl->hw, queue_num); + b43_stop_queue(dev, queue_num); skb_queue_head(&wl->tx_queue[queue_num], skb); break; } @@ -3627,6 +3628,7 @@ static void b43_op_tx(struct ieee80211_hw *hw, struct sk_buff *skb) { struct b43_wl *wl = hw_to_b43_wl(hw); + u16 skb_queue_mapping; if (unlikely(skb->len < 2 + 2 + 6)) { /* Too short, this can't be a valid frame. */ @@ -3635,12 +3637,12 @@ static void b43_op_tx(struct ieee80211_hw *hw, } B43_WARN_ON(skb_shinfo(skb)->nr_frags); - skb_queue_tail(&wl->tx_queue[skb->queue_mapping], skb); - if (!wl->tx_queue_stopped[skb->queue_mapping]) { + skb_queue_mapping = skb_get_queue_mapping(skb); + skb_queue_tail(&wl->tx_queue[skb_queue_mapping], skb); + if (!wl->tx_queue_stopped[skb_queue_mapping]) ieee80211_queue_work(wl->hw, &wl->tx_work); - } else { - ieee80211_stop_queue(wl->hw, skb->queue_mapping); - } + else + b43_stop_queue(wl->current_dev, skb_queue_mapping); } static void b43_qos_params_upload(struct b43_wldev *dev, diff --git a/drivers/net/wireless/broadcom/b43/pio.c b/drivers/net/wireless/broadcom/b43/pio.c index 8c28a9250..cc19b589f 100644 --- a/drivers/net/wireless/broadcom/b43/pio.c +++ b/drivers/net/wireless/broadcom/b43/pio.c @@ -525,7 +525,7 @@ int b43_pio_tx(struct b43_wldev *dev, struct sk_buff *skb) if (total_len > (q->buffer_size - q->buffer_used)) { /* Not enough memory on the queue. */ err = -EBUSY; - ieee80211_stop_queue(dev->wl->hw, skb_get_queue_mapping(skb)); + b43_stop_queue(dev, skb_get_queue_mapping(skb)); q->stopped = true; goto out; } @@ -552,7 +552,7 @@ int b43_pio_tx(struct b43_wldev *dev, struct sk_buff *skb) if (((q->buffer_size - q->buffer_used) < roundup(2 + 2 + 6, 4)) || (q->free_packet_slots == 0)) { /* The queue is full. */ - ieee80211_stop_queue(dev->wl->hw, skb_get_queue_mapping(skb)); + b43_stop_queue(dev, skb_get_queue_mapping(skb)); q->stopped = true; } @@ -587,7 +587,7 @@ void b43_pio_handle_txstatus(struct b43_wldev *dev, list_add(&pack->list, &q->packets_list); if (q->stopped) { - ieee80211_wake_queue(dev->wl->hw, q->queue_prio); + b43_wake_queue(dev, q->queue_prio); q->stopped = false; } } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index baf5f0afe..fbb5e2953 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -790,8 +790,7 @@ s32 brcmf_notify_escan_complete(struct brcmf_cfg80211_info *cfg, scan_request = cfg->scan_request; cfg->scan_request = NULL; - if (timer_pending(&cfg->escan_timeout)) - del_timer_sync(&cfg->escan_timeout); + timer_delete_sync(&cfg->escan_timeout); if (fw_abort) { /* Do a scan abort to stop the driver's scan engine */ @@ -7674,6 +7673,7 @@ void brcmf_cfg80211_detach(struct brcmf_cfg80211_info *cfg) brcmf_btcoex_detach(cfg); wiphy_unregister(cfg->wiphy); wl_deinit_priv(cfg); + cancel_work_sync(&cfg->escan_timeout_work); brcmf_free_wiphy(cfg->wiphy); kfree(cfg); } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c index ccc621b8e..4a1fe982a 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c @@ -383,8 +383,9 @@ struct shared_phy *wlc_phy_shared_attach(struct shared_phy_params *shp) return sh; } -static void wlc_phy_timercb_phycal(struct brcms_phy *pi) +static void wlc_phy_timercb_phycal(void *ptr) { + struct brcms_phy *pi = ptr; uint delay = 5; if (PHY_PERICAL_MPHASE_PENDING(pi)) { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c index a0de5db0c..b72381791 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.c @@ -57,12 +57,11 @@ void wlc_phy_shim_detach(struct phy_shim_info *physhim) } struct wlapi_timer *wlapi_init_timer(struct phy_shim_info *physhim, - void (*fn)(struct brcms_phy *pi), + void (*fn)(void *pi), void *arg, const char *name) { return (struct wlapi_timer *) - brcms_init_timer(physhim->wl, (void (*)(void *))fn, - arg, name); + brcms_init_timer(physhim->wl, fn, arg, name); } void wlapi_free_timer(struct wlapi_timer *t) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.h index dd8774717..27d0934e6 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy_shim.h @@ -131,7 +131,7 @@ void wlc_phy_shim_detach(struct phy_shim_info *physhim); /* PHY to WL utility functions */ struct wlapi_timer *wlapi_init_timer(struct phy_shim_info *physhim, - void (*fn)(struct brcms_phy *pi), + void (*fn)(void *pi), void *arg, const char *name); void wlapi_free_timer(struct wlapi_timer *t); void wlapi_add_timer(struct wlapi_timer *t, uint ms, int periodic); diff --git a/drivers/net/wireless/intel/iwlegacy/3945-mac.c b/drivers/net/wireless/intel/iwlegacy/3945-mac.c index ef0ac42a5..55c00a07b 100644 --- a/drivers/net/wireless/intel/iwlegacy/3945-mac.c +++ b/drivers/net/wireless/intel/iwlegacy/3945-mac.c @@ -3831,7 +3831,6 @@ il3945_pci_remove(struct pci_dev *pdev) il3945_unset_hw_params(il); /*netif_stop_queue(dev); */ - flush_workqueue(il->workqueue); /* ieee80211_unregister_hw calls il3945_mac_stop, which flushes * il->workqueue... so we can't take down the workqueue diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c index 12cf22d0e..254990255 100644 --- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c +++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c @@ -6745,7 +6745,6 @@ il4965_pci_remove(struct pci_dev *pdev) il_eeprom_free(il); /*netif_stop_queue(dev); */ - flush_workqueue(il->workqueue); /* ieee80211_unregister_hw calls il_mac_stop, which flushes * il->workqueue... so we can't take down the workqueue diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c index 461af5831..6a19fc4c6 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c @@ -1526,7 +1526,6 @@ static void iwl_op_mode_dvm_stop(struct iwl_op_mode *op_mode) kfree(priv->nvm_data); /*netif_stop_queue(dev); */ - flush_workqueue(priv->workqueue); /* ieee80211_unregister_hw calls iwlagn_mac_stop, which flushes * priv->workqueue... so we can't take down the workqueue diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index 5e4faf9ce..fc35f8f84 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -555,7 +555,7 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt) * from index 1, so the maximum value allowed here is * ACPI_SAR_PROFILES_NUM - 1. */ - if (n_profiles <= 0 || n_profiles >= ACPI_SAR_PROFILE_NUM) { + if (n_profiles >= ACPI_SAR_PROFILE_NUM) { ret = -EINVAL; goto out_free; } diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c index fdf2c6ea4..299819d2d 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c @@ -155,6 +155,12 @@ static int iwl_dbg_tlv_alloc_debug_info(struct iwl_trans *trans, if (le32_to_cpu(tlv->length) != sizeof(*debug_info)) return -EINVAL; + /* we use this as a string, ensure input was NUL terminated */ + if (strnlen(debug_info->debug_cfg_name, + sizeof(debug_info->debug_cfg_name)) == + sizeof(debug_info->debug_cfg_name)) + return -EINVAL; + IWL_DEBUG_FW(trans, "WRT: Loading debug cfg: %s\n", debug_info->debug_cfg_name); @@ -876,7 +882,7 @@ static int iwl_dbg_tlv_override_trig_node(struct iwl_fw_runtime *fwrt, node_trig = (void *)node_tlv->data; } - memcpy(node_trig->data + offset, trig->data, trig_data_len); + memcpy((u8 *)node_trig->data + offset, trig->data, trig_data_len); node_tlv->length = cpu_to_le32(size); if (policy & IWL_FW_INI_APPLY_POLICY_OVERRIDE_CFG) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c index b1335fe3b..e2df8ddc1 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c @@ -106,6 +106,8 @@ int iwl_mvm_ftm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, if (!pasn) return -ENOBUFS; + iwl_mvm_ftm_remove_pasn_sta(mvm, addr); + pasn->cipher = iwl_mvm_cipher_to_location_cipher(cipher); switch (pasn->cipher) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index d2c6fdb70..08008b0c0 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -5155,8 +5155,7 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm, if (notif->sync) { notif->cookie = mvm->queue_sync_cookie; - atomic_set(&mvm->queue_sync_counter, - mvm->trans->num_rx_queues); + mvm->queue_sync_state = (1 << mvm->trans->num_rx_queues) - 1; } ret = iwl_mvm_notify_rx_queue(mvm, qmask, (u8 *)notif, @@ -5169,16 +5168,19 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm, if (notif->sync) { lockdep_assert_held(&mvm->mutex); ret = wait_event_timeout(mvm->rx_sync_waitq, - atomic_read(&mvm->queue_sync_counter) == 0 || + READ_ONCE(mvm->queue_sync_state) == 0 || iwl_mvm_is_radio_killed(mvm), HZ); - WARN_ON_ONCE(!ret && !iwl_mvm_is_radio_killed(mvm)); + WARN_ONCE(!ret && !iwl_mvm_is_radio_killed(mvm), + "queue sync: failed to sync, state is 0x%lx\n", + mvm->queue_sync_state); } out: - atomic_set(&mvm->queue_sync_counter, 0); - if (notif->sync) + if (notif->sync) { + mvm->queue_sync_state = 0; mvm->queue_sync_cookie++; + } } static void iwl_mvm_sync_rx_queues(struct ieee80211_hw *hw) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 64f5a4cb3..8b779c3a9 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -842,7 +842,7 @@ struct iwl_mvm { unsigned long status; u32 queue_sync_cookie; - atomic_t queue_sync_counter; + unsigned long queue_sync_state; /* * for beacon filtering - * currently only one interface can be supported diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index 5b173f21e..3548eb57f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -725,7 +725,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, init_waitqueue_head(&mvm->rx_sync_waitq); - atomic_set(&mvm->queue_sync_counter, 0); + mvm->queue_sync_state = 0; SET_IEEE80211_DEV(mvm->hw, mvm->trans->dev); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 86b3fb321..e2a39e8b9 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -853,9 +853,13 @@ void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct napi_struct *napi, WARN_ONCE(1, "Invalid identifier %d", internal_notif->type); } - if (internal_notif->sync && - !atomic_dec_return(&mvm->queue_sync_counter)) - wake_up(&mvm->rx_sync_waitq); + if (internal_notif->sync) { + WARN_ONCE(!test_and_clear_bit(queue, &mvm->queue_sync_state), + "queue sync: queue %d responded a second time!\n", + queue); + if (READ_ONCE(mvm->queue_sync_state) == 0) + wake_up(&mvm->rx_sync_waitq); + } } static void iwl_mvm_oldsn_workaround(struct iwl_mvm *mvm, diff --git a/drivers/net/wireless/marvell/libertas/cmd.c b/drivers/net/wireless/marvell/libertas/cmd.c index a4d9dd73b..db9a852fa 100644 --- a/drivers/net/wireless/marvell/libertas/cmd.c +++ b/drivers/net/wireless/marvell/libertas/cmd.c @@ -1133,7 +1133,7 @@ int lbs_allocate_cmd_buffer(struct lbs_private *priv) if (!cmdarray[i].cmdbuf) { lbs_deb_host("ALLOC_CMD_BUF: ptempvirtualaddr is NULL\n"); ret = -1; - goto done; + goto free_cmd_array; } } @@ -1141,8 +1141,17 @@ int lbs_allocate_cmd_buffer(struct lbs_private *priv) init_waitqueue_head(&cmdarray[i].cmdwait_q); lbs_cleanup_and_insert_cmd(priv, &cmdarray[i]); } - ret = 0; + return 0; +free_cmd_array: + for (i = 0; i < LBS_NUM_CMD_BUFFERS; i++) { + if (cmdarray[i].cmdbuf) { + kfree(cmdarray[i].cmdbuf); + cmdarray[i].cmdbuf = NULL; + } + } + kfree(priv->cmd_array); + priv->cmd_array = NULL; done: return ret; } diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c index 2f5f1ff22..e1196c565 100644 --- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c +++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c @@ -3155,13 +3155,11 @@ int mwifiex_del_virtual_intf(struct wiphy *wiphy, struct wireless_dev *wdev) unregister_netdevice(wdev->netdev); if (priv->dfs_cac_workqueue) { - flush_workqueue(priv->dfs_cac_workqueue); destroy_workqueue(priv->dfs_cac_workqueue); priv->dfs_cac_workqueue = NULL; } if (priv->dfs_chan_sw_workqueue) { - flush_workqueue(priv->dfs_chan_sw_workqueue); destroy_workqueue(priv->dfs_chan_sw_workqueue); priv->dfs_chan_sw_workqueue = NULL; } diff --git a/drivers/net/wireless/marvell/mwifiex/debugfs.c b/drivers/net/wireless/marvell/mwifiex/debugfs.c index 1e7dc724c..d48a3e0b3 100644 --- a/drivers/net/wireless/marvell/mwifiex/debugfs.c +++ b/drivers/net/wireless/marvell/mwifiex/debugfs.c @@ -976,9 +976,6 @@ mwifiex_dev_debugfs_init(struct mwifiex_private *priv) priv->dfs_dev_dir = debugfs_create_dir(priv->netdev->name, mwifiex_dfs_dir); - if (!priv->dfs_dev_dir) - return; - MWIFIEX_DFS_ADD_FILE(info); MWIFIEX_DFS_ADD_FILE(debug); MWIFIEX_DFS_ADD_FILE(getlog); diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c index 6283df5aa..b8b79fe50 100644 --- a/drivers/net/wireless/marvell/mwifiex/main.c +++ b/drivers/net/wireless/marvell/mwifiex/main.c @@ -498,13 +498,11 @@ static void mwifiex_free_adapter(struct mwifiex_adapter *adapter) static void mwifiex_terminate_workqueue(struct mwifiex_adapter *adapter) { if (adapter->workqueue) { - flush_workqueue(adapter->workqueue); destroy_workqueue(adapter->workqueue); adapter->workqueue = NULL; } if (adapter->rx_workqueue) { - flush_workqueue(adapter->rx_workqueue); destroy_workqueue(adapter->rx_workqueue); adapter->rx_workqueue = NULL; } diff --git a/drivers/net/wireless/microchip/wilc1000/cfg80211.c b/drivers/net/wireless/microchip/wilc1000/cfg80211.c index dd26f2086..5d4f9e9a8 100644 --- a/drivers/net/wireless/microchip/wilc1000/cfg80211.c +++ b/drivers/net/wireless/microchip/wilc1000/cfg80211.c @@ -1562,7 +1562,6 @@ static int del_virtual_intf(struct wiphy *wiphy, struct wireless_dev *wdev) unregister_netdevice(vif->ndev); vif->monitor_flag = 0; - wilc_set_operation_mode(vif, 0, 0, 0); mutex_lock(&wl->vif_mutex); list_del_rcu(&vif->list); wl->vif_num--; diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c index 884f45e62..457386f9d 100644 --- a/drivers/net/wireless/microchip/wilc1000/hif.c +++ b/drivers/net/wireless/microchip/wilc1000/hif.c @@ -359,38 +359,49 @@ out: void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, struct cfg80211_crypto_settings *crypto) { - struct wilc_join_bss_param *param; - struct ieee80211_p2p_noa_attr noa_attr; - u8 rates_len = 0; - const u8 *tim_elm, *ssid_elm, *rates_ie, *supp_rates_ie; + const u8 *ies_data, *tim_elm, *ssid_elm, *rates_ie, *supp_rates_ie; const u8 *ht_ie, *wpa_ie, *wmm_ie, *rsn_ie; + struct ieee80211_p2p_noa_attr noa_attr; + const struct cfg80211_bss_ies *ies; + struct wilc_join_bss_param *param; + u8 rates_len = 0, ies_len; int ret; - const struct cfg80211_bss_ies *ies = rcu_dereference(bss->ies); param = kzalloc(sizeof(*param), GFP_KERNEL); if (!param) return NULL; + rcu_read_lock(); + ies = rcu_dereference(bss->ies); + ies_data = kmemdup(ies->data, ies->len, GFP_ATOMIC); + if (!ies_data) { + rcu_read_unlock(); + kfree(param); + return NULL; + } + ies_len = ies->len; + rcu_read_unlock(); + param->beacon_period = cpu_to_le16(bss->beacon_interval); param->cap_info = cpu_to_le16(bss->capability); param->bss_type = WILC_FW_BSS_TYPE_INFRA; param->ch = ieee80211_frequency_to_channel(bss->channel->center_freq); ether_addr_copy(param->bssid, bss->bssid); - ssid_elm = cfg80211_find_ie(WLAN_EID_SSID, ies->data, ies->len); + ssid_elm = cfg80211_find_ie(WLAN_EID_SSID, ies_data, ies_len); if (ssid_elm) { if (ssid_elm[1] <= IEEE80211_MAX_SSID_LEN) memcpy(param->ssid, ssid_elm + 2, ssid_elm[1]); } - tim_elm = cfg80211_find_ie(WLAN_EID_TIM, ies->data, ies->len); + tim_elm = cfg80211_find_ie(WLAN_EID_TIM, ies_data, ies_len); if (tim_elm && tim_elm[1] >= 2) param->dtim_period = tim_elm[3]; memset(param->p_suites, 0xFF, 3); memset(param->akm_suites, 0xFF, 3); - rates_ie = cfg80211_find_ie(WLAN_EID_SUPP_RATES, ies->data, ies->len); + rates_ie = cfg80211_find_ie(WLAN_EID_SUPP_RATES, ies_data, ies_len); if (rates_ie) { rates_len = rates_ie[1]; if (rates_len > WILC_MAX_RATES_SUPPORTED) @@ -401,7 +412,7 @@ void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, if (rates_len < WILC_MAX_RATES_SUPPORTED) { supp_rates_ie = cfg80211_find_ie(WLAN_EID_EXT_SUPP_RATES, - ies->data, ies->len); + ies_data, ies_len); if (supp_rates_ie) { u8 ext_rates = supp_rates_ie[1]; @@ -416,11 +427,11 @@ void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, } } - ht_ie = cfg80211_find_ie(WLAN_EID_HT_CAPABILITY, ies->data, ies->len); + ht_ie = cfg80211_find_ie(WLAN_EID_HT_CAPABILITY, ies_data, ies_len); if (ht_ie) param->ht_capable = true; - ret = cfg80211_get_p2p_attr(ies->data, ies->len, + ret = cfg80211_get_p2p_attr(ies_data, ies_len, IEEE80211_P2P_ATTR_ABSENCE_NOTICE, (u8 *)&noa_attr, sizeof(noa_attr)); if (ret > 0) { @@ -444,7 +455,7 @@ void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, } wmm_ie = cfg80211_find_vendor_ie(WLAN_OUI_MICROSOFT, WLAN_OUI_TYPE_MICROSOFT_WMM, - ies->data, ies->len); + ies_data, ies_len); if (wmm_ie) { struct ieee80211_wmm_param_ie *ie; @@ -459,13 +470,13 @@ void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, wpa_ie = cfg80211_find_vendor_ie(WLAN_OUI_MICROSOFT, WLAN_OUI_TYPE_MICROSOFT_WPA, - ies->data, ies->len); + ies_data, ies_len); if (wpa_ie) { param->mode_802_11i = 1; param->rsn_found = true; } - rsn_ie = cfg80211_find_ie(WLAN_EID_RSN, ies->data, ies->len); + rsn_ie = cfg80211_find_ie(WLAN_EID_RSN, ies_data, ies_len); if (rsn_ie) { int rsn_ie_len = sizeof(struct element) + rsn_ie[1]; int offset = 8; @@ -499,6 +510,7 @@ void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, param->akm_suites[i] = crypto->akm_suites[i] & 0xFF; } + kfree(ies_data); return (void *)param; } diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.c b/drivers/net/wireless/microchip/wilc1000/netdev.c index c508f4299..ab84b146a 100644 --- a/drivers/net/wireless/microchip/wilc1000/netdev.c +++ b/drivers/net/wireless/microchip/wilc1000/netdev.c @@ -821,8 +821,7 @@ static const struct net_device_ops wilc_netdev_ops = { void wilc_netdev_cleanup(struct wilc *wilc) { - struct wilc_vif *vif; - int srcu_idx, ifc_cnt = 0; + struct wilc_vif *vif, *vif_tmp; if (!wilc) return; @@ -832,33 +831,19 @@ void wilc_netdev_cleanup(struct wilc *wilc) wilc->firmware = NULL; } - srcu_idx = srcu_read_lock(&wilc->srcu); - list_for_each_entry_rcu(vif, &wilc->vif_list, list) { + list_for_each_entry_safe(vif, vif_tmp, &wilc->vif_list, list) { + mutex_lock(&wilc->vif_mutex); + list_del_rcu(&vif->list); + wilc->vif_num--; + mutex_unlock(&wilc->vif_mutex); + synchronize_srcu(&wilc->srcu); if (vif->ndev) unregister_netdev(vif->ndev); } - srcu_read_unlock(&wilc->srcu, srcu_idx); wilc_wfi_deinit_mon_interface(wilc, false); - flush_workqueue(wilc->hif_workqueue); destroy_workqueue(wilc->hif_workqueue); - while (ifc_cnt < WILC_NUM_CONCURRENT_IFC) { - mutex_lock(&wilc->vif_mutex); - if (wilc->vif_num <= 0) { - mutex_unlock(&wilc->vif_mutex); - break; - } - vif = wilc_get_wl_to_vif(wilc); - if (!IS_ERR(vif)) - list_del_rcu(&vif->list); - - wilc->vif_num--; - mutex_unlock(&wilc->vif_mutex); - synchronize_srcu(&wilc->srcu); - ifc_cnt++; - } - wilc_wlan_cfg_deinit(wilc); wlan_deinit_locks(wilc); kfree(wilc->bus_data); diff --git a/drivers/net/wireless/quantenna/qtnfmac/core.c b/drivers/net/wireless/quantenna/qtnfmac/core.c index bf6dbeb61..d39c210da 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/core.c +++ b/drivers/net/wireless/quantenna/qtnfmac/core.c @@ -816,13 +816,11 @@ void qtnf_core_detach(struct qtnf_bus *bus) bus->fw_state = QTNF_FW_STATE_DETACHED; if (bus->workqueue) { - flush_workqueue(bus->workqueue); destroy_workqueue(bus->workqueue); bus->workqueue = NULL; } if (bus->hprio_workqueue) { - flush_workqueue(bus->hprio_workqueue); destroy_workqueue(bus->hprio_workqueue); bus->hprio_workqueue = NULL; } diff --git a/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c b/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c index 0f328ce47..f65eb6e5b 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c +++ b/drivers/net/wireless/quantenna/qtnfmac/pcie/pcie.c @@ -387,7 +387,6 @@ static int qtnf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; error: - flush_workqueue(pcie_priv->workqueue); destroy_workqueue(pcie_priv->workqueue); pci_set_drvdata(pdev, NULL); return ret; @@ -416,7 +415,6 @@ static void qtnf_pcie_remove(struct pci_dev *dev) qtnf_core_detach(bus); netif_napi_del(&bus->mux_napi); - flush_workqueue(priv->workqueue); destroy_workqueue(priv->workqueue); tasklet_kill(&priv->reclaim_tq); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c index b04f76551..be3c153ab 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c @@ -101,6 +101,7 @@ void rt2x00lib_disable_radio(struct rt2x00_dev *rt2x00dev) rt2x00link_stop_tuner(rt2x00dev); rt2x00queue_stop_queues(rt2x00dev); rt2x00queue_flush_queues(rt2x00dev, true); + rt2x00queue_stop_queue(rt2x00dev->bcn); /* * Disable radio. @@ -1272,6 +1273,7 @@ int rt2x00lib_start(struct rt2x00_dev *rt2x00dev) rt2x00dev->intf_ap_count = 0; rt2x00dev->intf_sta_count = 0; rt2x00dev->intf_associated = 0; + rt2x00dev->intf_beaconing = 0; /* Enable the radio */ retval = rt2x00lib_enable_radio(rt2x00dev); @@ -1298,6 +1300,7 @@ void rt2x00lib_stop(struct rt2x00_dev *rt2x00dev) rt2x00dev->intf_ap_count = 0; rt2x00dev->intf_sta_count = 0; rt2x00dev->intf_associated = 0; + rt2x00dev->intf_beaconing = 0; } static inline void rt2x00lib_set_if_combinations(struct rt2x00_dev *rt2x00dev) diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c index 2f68a3107..795bd3b0e 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c @@ -599,6 +599,17 @@ void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw, */ if (changes & BSS_CHANGED_BEACON_ENABLED) { mutex_lock(&intf->beacon_skb_mutex); + + /* + * Clear the 'enable_beacon' flag and clear beacon because + * the beacon queue has been stopped after hardware reset. + */ + if (test_bit(DEVICE_STATE_RESET, &rt2x00dev->flags) && + intf->enable_beacon) { + intf->enable_beacon = false; + rt2x00queue_clear_beacon(rt2x00dev, vif); + } + if (!bss_conf->enable_beacon && intf->enable_beacon) { rt2x00dev->intf_beaconing--; intf->enable_beacon = false; diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index 004778faf..9efc15e69 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -6483,6 +6483,7 @@ static void rtl8xxxu_stop(struct ieee80211_hw *hw) if (priv->usb_interrupts) rtl8xxxu_write32(priv, REG_USB_HIMR, 0); + cancel_work_sync(&priv->c2hcmd_work); cancel_delayed_work_sync(&priv->ra_watchdog); rtl8xxxu_free_rx_resources(priv); @@ -6973,6 +6974,18 @@ static const struct usb_device_id dev_table[] = { .driver_info = (unsigned long)&rtl8192eu_fops}, {USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x818c, 0xff, 0xff, 0xff), .driver_info = (unsigned long)&rtl8192eu_fops}, +/* D-Link DWA-131 rev C1 */ +{USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x3312, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192eu_fops}, +/* TP-Link TL-WN8200ND V2 */ +{USB_DEVICE_AND_INTERFACE_INFO(0x2357, 0x0126, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192eu_fops}, +/* Mercusys MW300UM */ +{USB_DEVICE_AND_INTERFACE_INFO(0x2c4e, 0x0100, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192eu_fops}, +/* Mercusys MW300UH */ +{USB_DEVICE_AND_INTERFACE_INFO(0x2c4e, 0x0104, 0xff, 0xff, 0xff), + .driver_info = (unsigned long)&rtl8192eu_fops}, #endif { } }; diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c index 679ae786c..6d9f2a623 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.c +++ b/drivers/net/wireless/realtek/rtlwifi/pci.c @@ -1704,7 +1704,6 @@ static void rtl_pci_deinit(struct ieee80211_hw *hw) tasklet_kill(&rtlpriv->works.irq_tasklet); cancel_work_sync(&rtlpriv->works.lps_change_work); - flush_workqueue(rtlpriv->works.rtl_wq); destroy_workqueue(rtlpriv->works.rtl_wq); } diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c index fa0eed434..d26dda8e4 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/phy.c @@ -49,7 +49,7 @@ u32 rtl8723e_phy_query_rf_reg(struct ieee80211_hw *hw, rfpath, regaddr); } - bitshift = rtl8723_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); readback_value = (original_value & bitmask) >> bitshift; spin_unlock(&rtlpriv->locks.rf_lock); @@ -80,7 +80,7 @@ void rtl8723e_phy_set_rf_reg(struct ieee80211_hw *hw, original_value = rtl8723_phy_rf_serial_read(hw, rfpath, regaddr); - bitshift = rtl8723_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((original_value & (~bitmask)) | (data << bitshift)); @@ -89,7 +89,7 @@ void rtl8723e_phy_set_rf_reg(struct ieee80211_hw *hw, rtl8723_phy_rf_serial_write(hw, rfpath, regaddr, data); } else { if (bitmask != RFREG_OFFSET_MASK) { - bitshift = rtl8723_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((original_value & (~bitmask)) | (data << bitshift)); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c index f09f55b04..35dfea54a 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c @@ -41,7 +41,7 @@ u32 rtl8723be_phy_query_rf_reg(struct ieee80211_hw *hw, enum radio_path rfpath, spin_lock(&rtlpriv->locks.rf_lock); original_value = rtl8723_phy_rf_serial_read(hw, rfpath, regaddr); - bitshift = rtl8723_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); readback_value = (original_value & bitmask) >> bitshift; spin_unlock(&rtlpriv->locks.rf_lock); @@ -68,7 +68,7 @@ void rtl8723be_phy_set_rf_reg(struct ieee80211_hw *hw, enum radio_path path, if (bitmask != RFREG_OFFSET_MASK) { original_value = rtl8723_phy_rf_serial_read(hw, path, regaddr); - bitshift = rtl8723_phy_calculate_bit_shift(bitmask); + bitshift = calculate_bit_shift(bitmask); data = ((original_value & (~bitmask)) | (data << bitshift)); } diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.c b/drivers/net/wireless/realtek/rtw88/rtw8821c.c index f9615f76f..d517f92b6 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c @@ -579,9 +579,9 @@ static void rtw8821c_false_alarm_statistics(struct rtw_dev *rtwdev) dm_info->cck_fa_cnt = cck_fa_cnt; dm_info->ofdm_fa_cnt = ofdm_fa_cnt; + dm_info->total_fa_cnt = ofdm_fa_cnt; if (cck_enable) dm_info->total_fa_cnt += cck_fa_cnt; - dm_info->total_fa_cnt = ofdm_fa_cnt; crc32_cnt = rtw_read32(rtwdev, REG_CRC_CCK); dm_info->cck_ok_cnt = FIELD_GET(GENMASK(15, 0), crc32_cnt); diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c index dc076d844..75c78e1c9 100644 --- a/drivers/net/wireless/rndis_wlan.c +++ b/drivers/net/wireless/rndis_wlan.c @@ -3497,7 +3497,6 @@ fail: cancel_delayed_work_sync(&priv->dev_poller_work); cancel_delayed_work_sync(&priv->scan_work); cancel_work_sync(&priv->work); - flush_workqueue(priv->workqueue); destroy_workqueue(priv->workqueue); wiphy_free(wiphy); @@ -3514,7 +3513,6 @@ static void rndis_wlan_unbind(struct usbnet *usbdev, struct usb_interface *intf) cancel_delayed_work_sync(&priv->dev_poller_work); cancel_delayed_work_sync(&priv->scan_work); cancel_work_sync(&priv->work); - flush_workqueue(priv->workqueue); destroy_workqueue(priv->workqueue); rndis_unbind(usbdev, intf); diff --git a/drivers/net/wireless/st/cw1200/bh.c b/drivers/net/wireless/st/cw1200/bh.c index 02efe8483..361fef6e1 100644 --- a/drivers/net/wireless/st/cw1200/bh.c +++ b/drivers/net/wireless/st/cw1200/bh.c @@ -88,8 +88,6 @@ void cw1200_unregister_bh(struct cw1200_common *priv) atomic_add(1, &priv->bh_term); wake_up(&priv->bh_wq); - flush_workqueue(priv->bh_workqueue); - destroy_workqueue(priv->bh_workqueue); priv->bh_workqueue = NULL; diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index d25bb5b9a..f5c5cf650 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -104,13 +104,12 @@ bool provides_xdp_headroom = true; module_param(provides_xdp_headroom, bool, 0644); static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, - u8 status); + s8 status); static void make_tx_response(struct xenvif_queue *queue, - struct xen_netif_tx_request *txp, + const struct xen_netif_tx_request *txp, unsigned int extra_count, - s8 st); -static void push_tx_responses(struct xenvif_queue *queue); + s8 status); static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx); @@ -208,13 +207,9 @@ static void xenvif_tx_err(struct xenvif_queue *queue, unsigned int extra_count, RING_IDX end) { RING_IDX cons = queue->tx.req_cons; - unsigned long flags; do { - spin_lock_irqsave(&queue->response_lock, flags); make_tx_response(queue, txp, extra_count, XEN_NETIF_RSP_ERROR); - push_tx_responses(queue); - spin_unlock_irqrestore(&queue->response_lock, flags); if (cons == end) break; RING_COPY_REQUEST(&queue->tx, cons++, txp); @@ -465,12 +460,7 @@ static void xenvif_get_requests(struct xenvif_queue *queue, for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS; nr_slots--) { if (unlikely(!txp->size)) { - unsigned long flags; - - spin_lock_irqsave(&queue->response_lock, flags); make_tx_response(queue, txp, 0, XEN_NETIF_RSP_OKAY); - push_tx_responses(queue); - spin_unlock_irqrestore(&queue->response_lock, flags); ++txp; continue; } @@ -496,14 +486,8 @@ static void xenvif_get_requests(struct xenvif_queue *queue, for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; ++txp) { if (unlikely(!txp->size)) { - unsigned long flags; - - spin_lock_irqsave(&queue->response_lock, flags); make_tx_response(queue, txp, 0, XEN_NETIF_RSP_OKAY); - push_tx_responses(queue); - spin_unlock_irqrestore(&queue->response_lock, - flags); continue; } @@ -997,7 +981,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, (ret == 0) ? XEN_NETIF_RSP_OKAY : XEN_NETIF_RSP_ERROR); - push_tx_responses(queue); continue; } @@ -1009,7 +992,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, make_tx_response(queue, &txreq, extra_count, XEN_NETIF_RSP_OKAY); - push_tx_responses(queue); continue; } @@ -1444,8 +1426,35 @@ int xenvif_tx_action(struct xenvif_queue *queue, int budget) return work_done; } +static void _make_tx_response(struct xenvif_queue *queue, + const struct xen_netif_tx_request *txp, + unsigned int extra_count, + s8 status) +{ + RING_IDX i = queue->tx.rsp_prod_pvt; + struct xen_netif_tx_response *resp; + + resp = RING_GET_RESPONSE(&queue->tx, i); + resp->id = txp->id; + resp->status = status; + + while (extra_count-- != 0) + RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL; + + queue->tx.rsp_prod_pvt = ++i; +} + +static void push_tx_responses(struct xenvif_queue *queue) +{ + int notify; + + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); + if (notify) + notify_remote_via_irq(queue->tx_irq); +} + static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, - u8 status) + s8 status) { struct pending_tx_info *pending_tx_info; pending_ring_idx_t index; @@ -1455,8 +1464,8 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, spin_lock_irqsave(&queue->response_lock, flags); - make_tx_response(queue, &pending_tx_info->req, - pending_tx_info->extra_count, status); + _make_tx_response(queue, &pending_tx_info->req, + pending_tx_info->extra_count, status); /* Release the pending index before pusing the Tx response so * its available before a new Tx request is pushed by the @@ -1470,32 +1479,19 @@ static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx, spin_unlock_irqrestore(&queue->response_lock, flags); } - static void make_tx_response(struct xenvif_queue *queue, - struct xen_netif_tx_request *txp, + const struct xen_netif_tx_request *txp, unsigned int extra_count, - s8 st) + s8 status) { - RING_IDX i = queue->tx.rsp_prod_pvt; - struct xen_netif_tx_response *resp; - - resp = RING_GET_RESPONSE(&queue->tx, i); - resp->id = txp->id; - resp->status = st; - - while (extra_count-- != 0) - RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL; + unsigned long flags; - queue->tx.rsp_prod_pvt = ++i; -} + spin_lock_irqsave(&queue->response_lock, flags); -static void push_tx_responses(struct xenvif_queue *queue) -{ - int notify; + _make_tx_response(queue, txp, extra_count, status); + push_tx_responses(queue); - RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify); - if (notify) - notify_remote_via_irq(queue->tx_irq); + spin_unlock_irqrestore(&queue->response_lock, flags); } static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx) diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c index c70f62fe3..081ec1105 100644 --- a/drivers/nfc/trf7970a.c +++ b/drivers/nfc/trf7970a.c @@ -424,7 +424,8 @@ struct trf7970a { enum trf7970a_state state; struct device *dev; struct spi_device *spi; - struct regulator *regulator; + struct regulator *vin_regulator; + struct regulator *vddio_regulator; struct nfc_digital_dev *ddev; u32 quirks; bool is_initiator; @@ -1882,7 +1883,7 @@ static int trf7970a_power_up(struct trf7970a *trf) if (trf->state != TRF7970A_ST_PWR_OFF) return 0; - ret = regulator_enable(trf->regulator); + ret = regulator_enable(trf->vin_regulator); if (ret) { dev_err(trf->dev, "%s - Can't enable VIN: %d\n", __func__, ret); return ret; @@ -1925,7 +1926,7 @@ static int trf7970a_power_down(struct trf7970a *trf) if (trf->en2_gpiod && !(trf->quirks & TRF7970A_QUIRK_EN2_MUST_STAY_LOW)) gpiod_set_value_cansleep(trf->en2_gpiod, 0); - ret = regulator_disable(trf->regulator); + ret = regulator_disable(trf->vin_regulator); if (ret) dev_err(trf->dev, "%s - Can't disable VIN: %d\n", __func__, ret); @@ -2064,37 +2065,37 @@ static int trf7970a_probe(struct spi_device *spi) mutex_init(&trf->lock); INIT_DELAYED_WORK(&trf->timeout_work, trf7970a_timeout_work_handler); - trf->regulator = devm_regulator_get(&spi->dev, "vin"); - if (IS_ERR(trf->regulator)) { - ret = PTR_ERR(trf->regulator); + trf->vin_regulator = devm_regulator_get(&spi->dev, "vin"); + if (IS_ERR(trf->vin_regulator)) { + ret = PTR_ERR(trf->vin_regulator); dev_err(trf->dev, "Can't get VIN regulator: %d\n", ret); goto err_destroy_lock; } - ret = regulator_enable(trf->regulator); + ret = regulator_enable(trf->vin_regulator); if (ret) { dev_err(trf->dev, "Can't enable VIN: %d\n", ret); goto err_destroy_lock; } - uvolts = regulator_get_voltage(trf->regulator); + uvolts = regulator_get_voltage(trf->vin_regulator); if (uvolts > 4000000) trf->chip_status_ctrl = TRF7970A_CHIP_STATUS_VRS5_3; - trf->regulator = devm_regulator_get(&spi->dev, "vdd-io"); - if (IS_ERR(trf->regulator)) { - ret = PTR_ERR(trf->regulator); + trf->vddio_regulator = devm_regulator_get(&spi->dev, "vdd-io"); + if (IS_ERR(trf->vddio_regulator)) { + ret = PTR_ERR(trf->vddio_regulator); dev_err(trf->dev, "Can't get VDD_IO regulator: %d\n", ret); - goto err_destroy_lock; + goto err_disable_vin_regulator; } - ret = regulator_enable(trf->regulator); + ret = regulator_enable(trf->vddio_regulator); if (ret) { dev_err(trf->dev, "Can't enable VDD_IO: %d\n", ret); - goto err_destroy_lock; + goto err_disable_vin_regulator; } - if (regulator_get_voltage(trf->regulator) == 1800000) { + if (regulator_get_voltage(trf->vddio_regulator) == 1800000) { trf->io_ctrl = TRF7970A_REG_IO_CTRL_IO_LOW; dev_dbg(trf->dev, "trf7970a config vdd_io to 1.8V\n"); } @@ -2107,7 +2108,7 @@ static int trf7970a_probe(struct spi_device *spi) if (!trf->ddev) { dev_err(trf->dev, "Can't allocate NFC digital device\n"); ret = -ENOMEM; - goto err_disable_regulator; + goto err_disable_vddio_regulator; } nfc_digital_set_parent_dev(trf->ddev, trf->dev); @@ -2136,8 +2137,10 @@ err_shutdown: trf7970a_shutdown(trf); err_free_ddev: nfc_digital_free_device(trf->ddev); -err_disable_regulator: - regulator_disable(trf->regulator); +err_disable_vddio_regulator: + regulator_disable(trf->vddio_regulator); +err_disable_vin_regulator: + regulator_disable(trf->vin_regulator); err_destroy_lock: mutex_destroy(&trf->lock); return ret; @@ -2156,7 +2159,8 @@ static int trf7970a_remove(struct spi_device *spi) nfc_digital_unregister_device(trf->ddev); nfc_digital_free_device(trf->ddev); - regulator_disable(trf->regulator); + regulator_disable(trf->vddio_regulator); + regulator_disable(trf->vin_regulator); mutex_destroy(&trf->lock); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 906cab35a..8e0523907 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -220,11 +220,6 @@ static LIST_HEAD(nvme_fc_lport_list); static DEFINE_IDA(nvme_fc_local_port_cnt); static DEFINE_IDA(nvme_fc_ctrl_cnt); -static struct workqueue_struct *nvme_fc_wq; - -static bool nvme_fc_waiting_to_unload; -static DECLARE_COMPLETION(nvme_fc_unload_proceed); - /* * These items are short-term. They will eventually be moved into * a generic FC class. See comments in module init. @@ -254,8 +249,6 @@ nvme_fc_free_lport(struct kref *ref) /* remove from transport list */ spin_lock_irqsave(&nvme_fc_lock, flags); list_del(&lport->port_list); - if (nvme_fc_waiting_to_unload && list_empty(&nvme_fc_lport_list)) - complete(&nvme_fc_unload_proceed); spin_unlock_irqrestore(&nvme_fc_lock, flags); ida_simple_remove(&nvme_fc_local_port_cnt, lport->localport.port_num); @@ -3823,10 +3816,6 @@ static int __init nvme_fc_init_module(void) { int ret; - nvme_fc_wq = alloc_workqueue("nvme_fc_wq", WQ_MEM_RECLAIM, 0); - if (!nvme_fc_wq) - return -ENOMEM; - /* * NOTE: * It is expected that in the future the kernel will combine @@ -3844,7 +3833,7 @@ static int __init nvme_fc_init_module(void) ret = class_register(&fc_class); if (ret) { pr_err("couldn't register class fc\n"); - goto out_destroy_wq; + return ret; } /* @@ -3868,8 +3857,6 @@ out_destroy_device: device_destroy(&fc_class, MKDEV(0, 0)); out_destroy_class: class_unregister(&fc_class); -out_destroy_wq: - destroy_workqueue(nvme_fc_wq); return ret; } @@ -3889,45 +3876,23 @@ nvme_fc_delete_controllers(struct nvme_fc_rport *rport) spin_unlock(&rport->lock); } -static void -nvme_fc_cleanup_for_unload(void) +static void __exit nvme_fc_exit_module(void) { struct nvme_fc_lport *lport; struct nvme_fc_rport *rport; - - list_for_each_entry(lport, &nvme_fc_lport_list, port_list) { - list_for_each_entry(rport, &lport->endp_list, endp_list) { - nvme_fc_delete_controllers(rport); - } - } -} - -static void __exit nvme_fc_exit_module(void) -{ unsigned long flags; - bool need_cleanup = false; spin_lock_irqsave(&nvme_fc_lock, flags); - nvme_fc_waiting_to_unload = true; - if (!list_empty(&nvme_fc_lport_list)) { - need_cleanup = true; - nvme_fc_cleanup_for_unload(); - } + list_for_each_entry(lport, &nvme_fc_lport_list, port_list) + list_for_each_entry(rport, &lport->endp_list, endp_list) + nvme_fc_delete_controllers(rport); spin_unlock_irqrestore(&nvme_fc_lock, flags); - if (need_cleanup) { - pr_info("%s: waiting for ctlr deletes\n", __func__); - wait_for_completion(&nvme_fc_unload_proceed); - pr_info("%s: ctrl deletes complete\n", __func__); - } + flush_workqueue(nvme_delete_wq); nvmf_unregister_transport(&nvme_fc_transport); - ida_destroy(&nvme_fc_local_port_cnt); - ida_destroy(&nvme_fc_ctrl_cnt); - device_destroy(&fc_class, MKDEV(0, 0)); class_unregister(&fc_class); - destroy_workqueue(nvme_fc_wq); } module_init(nvme_fc_init_module); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 970a1b374..5242feda5 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3199,6 +3199,9 @@ static const struct pci_device_id nvme_id_table[] = { NVME_QUIRK_BOGUS_NID, }, { PCI_VDEVICE(REDHAT, 0x0010), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x126f, 0x2262), /* Silicon Motion generic */ + .driver_data = NVME_QUIRK_NO_DEEPEST_PS | + NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x126f, 0x2263), /* Silicon Motion unidentified */ .driver_data = NVME_QUIRK_NO_NS_DESC_LIST, }, { PCI_DEVICE(0x1bb1, 0x0100), /* Seagate Nytro Flash Storage */ diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 46fc44ce8..846fb41da 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -357,7 +357,7 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop) if (!lsop->req_queued) { spin_unlock_irqrestore(&tgtport->lock, flags); - return; + goto out_puttgtport; } list_del(&lsop->lsreq_list); @@ -370,6 +370,7 @@ __nvmet_fc_finish_ls_req(struct nvmet_fc_ls_req_op *lsop) (lsreq->rqstlen + lsreq->rsplen), DMA_BIDIRECTIONAL); +out_puttgtport: nvmet_fc_tgtport_put(tgtport); } @@ -1101,6 +1102,9 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle) int idx; bool needrandom = true; + if (!tgtport->pe) + return NULL; + assoc = kzalloc(sizeof(*assoc), GFP_KERNEL); if (!assoc) return NULL; @@ -2528,8 +2532,9 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, fod->req.cmd = &fod->cmdiubuf.sqe; fod->req.cqe = &fod->rspiubuf.cqe; - if (tgtport->pe) - fod->req.port = tgtport->pe->port; + if (!tgtport->pe) + goto transport_error; + fod->req.port = tgtport->pe->port; /* clear any response payload */ memset(&fod->rspiubuf, 0, sizeof(fod->rspiubuf)); diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 80a208fb3..f2c5136bf 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -358,7 +358,7 @@ fcloop_h2t_ls_req(struct nvme_fc_local_port *localport, if (!rport->targetport) { tls_req->status = -ECONNREFUSED; spin_lock(&rport->lock); - list_add_tail(&rport->ls_list, &tls_req->ls_list); + list_add_tail(&tls_req->ls_list, &rport->ls_list); spin_unlock(&rport->lock); schedule_work(&rport->ls_work); return ret; @@ -391,7 +391,7 @@ fcloop_h2t_xmt_ls_rsp(struct nvmet_fc_target_port *targetport, if (remoteport) { rport = remoteport->private; spin_lock(&rport->lock); - list_add_tail(&rport->ls_list, &tls_req->ls_list); + list_add_tail(&tls_req->ls_list, &rport->ls_list); spin_unlock(&rport->lock); schedule_work(&rport->ls_work); } @@ -446,7 +446,7 @@ fcloop_t2h_ls_req(struct nvmet_fc_target_port *targetport, void *hosthandle, if (!tport->remoteport) { tls_req->status = -ECONNREFUSED; spin_lock(&tport->lock); - list_add_tail(&tport->ls_list, &tls_req->ls_list); + list_add_tail(&tls_req->ls_list, &tport->ls_list); spin_unlock(&tport->lock); schedule_work(&tport->ls_work); return ret; diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 116ae6fd3..d70a2fa4b 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1852,6 +1852,7 @@ static void __exit nvmet_tcp_exit(void) flush_scheduled_work(); destroy_workqueue(nvmet_tcp_wq); + ida_destroy(&nvmet_tcp_queue_ida); } module_init(nvmet_tcp_init); diff --git a/drivers/nvmem/meson-efuse.c b/drivers/nvmem/meson-efuse.c index d6b533497..ba2714bef 100644 --- a/drivers/nvmem/meson-efuse.c +++ b/drivers/nvmem/meson-efuse.c @@ -47,7 +47,6 @@ static int meson_efuse_probe(struct platform_device *pdev) struct nvmem_config *econfig; struct clk *clk; unsigned int size; - int ret; sm_np = of_parse_phandle(pdev->dev.of_node, "secure-monitor", 0); if (!sm_np) { @@ -60,27 +59,9 @@ static int meson_efuse_probe(struct platform_device *pdev) if (!fw) return -EPROBE_DEFER; - clk = devm_clk_get(dev, NULL); - if (IS_ERR(clk)) { - ret = PTR_ERR(clk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get efuse gate"); - return ret; - } - - ret = clk_prepare_enable(clk); - if (ret) { - dev_err(dev, "failed to enable gate"); - return ret; - } - - ret = devm_add_action_or_reset(dev, - (void(*)(void *))clk_disable_unprepare, - clk); - if (ret) { - dev_err(dev, "failed to add disable callback"); - return ret; - } + clk = devm_clk_get_enabled(dev, NULL); + if (IS_ERR(clk)) + return dev_err_probe(dev, PTR_ERR(clk), "failed to get efuse gate"); if (meson_sm_call(fw, SM_EFUSE_USER_MAX, &size, 0, 0, 0, 0, 0) < 0) { dev_err(dev, "failed to get max user"); diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index b6a3ee654..4d80167d3 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -9,6 +9,7 @@ #define pr_fmt(fmt) "OF: " fmt +#include <linux/device.h> #include <linux/of.h> #include <linux/spinlock.h> #include <linux/slab.h> @@ -675,6 +676,17 @@ void of_changeset_destroy(struct of_changeset *ocs) { struct of_changeset_entry *ce, *cen; + /* + * When a device is deleted, the device links to/from it are also queued + * for deletion. Until these device links are freed, the devices + * themselves aren't freed. If the device being deleted is due to an + * overlay change, this device might be holding a reference to a device + * node that will be freed. So, wait until all already pending device + * links are deleted before freeing a device node. This ensures we don't + * free any device node that has a non-zero reference count. + */ + device_link_wait_removal(); + list_for_each_entry_safe_reverse(ce, cen, &ocs->entries, node) __of_changeset_entry_destroy(ce); } diff --git a/drivers/of/property.c b/drivers/of/property.c index a411460d2..758d6db59 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1306,7 +1306,7 @@ DEFINE_SIMPLE_PROP(clocks, "clocks", "#clock-cells") DEFINE_SIMPLE_PROP(interconnects, "interconnects", "#interconnect-cells") DEFINE_SIMPLE_PROP(iommus, "iommus", "#iommu-cells") DEFINE_SIMPLE_PROP(mboxes, "mboxes", "#mbox-cells") -DEFINE_SIMPLE_PROP(io_channels, "io-channel", "#io-channel-cells") +DEFINE_SIMPLE_PROP(io_channels, "io-channels", "#io-channel-cells") DEFINE_SIMPLE_PROP(interrupt_parent, "interrupt-parent", NULL) DEFINE_SIMPLE_PROP(dmas, "dmas", "#dma-cells") DEFINE_SIMPLE_PROP(power_domains, "power-domains", "#power-domain-cells") diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index f9083c868..a334c68db 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -48,6 +48,12 @@ static struct unittest_results { failed; \ }) +#ifdef CONFIG_OF_KOBJ +#define OF_KREF_READ(NODE) kref_read(&(NODE)->kobj.kref) +#else +#define OF_KREF_READ(NODE) 1 +#endif + /* * Expected message may have a message level other than KERN_INFO. * Print the expected message only if the current loglevel will allow @@ -561,7 +567,7 @@ static void __init of_unittest_parse_phandle_with_args_map(void) pr_err("missing testcase data\n"); return; } - prefs[i] = kref_read(&p[i]->kobj.kref); + prefs[i] = OF_KREF_READ(p[i]); } rc = of_count_phandle_with_args(np, "phandle-list", "#phandle-cells"); @@ -684,9 +690,9 @@ static void __init of_unittest_parse_phandle_with_args_map(void) unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); for (i = 0; i < ARRAY_SIZE(p); ++i) { - unittest(prefs[i] == kref_read(&p[i]->kobj.kref), + unittest(prefs[i] == OF_KREF_READ(p[i]), "provider%d: expected:%d got:%d\n", - i, prefs[i], kref_read(&p[i]->kobj.kref)); + i, prefs[i], OF_KREF_READ(p[i])); of_node_put(p[i]); } } diff --git a/drivers/opp/debugfs.c b/drivers/opp/debugfs.c index 60f4ff8e0..016dea5a4 100644 --- a/drivers/opp/debugfs.c +++ b/drivers/opp/debugfs.c @@ -36,10 +36,12 @@ static ssize_t bw_name_read(struct file *fp, char __user *userbuf, size_t count, loff_t *ppos) { struct icc_path *path = fp->private_data; + const char *name = icc_get_name(path); char buf[64]; - int i; + int i = 0; - i = scnprintf(buf, sizeof(buf), "%.62s\n", icc_get_name(path)); + if (name) + i = scnprintf(buf, sizeof(buf), "%.62s\n", name); return simple_read_from_buffer(userbuf, count, ppos, buf, i); } diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 95ed71940..8ed1df61f 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -6,6 +6,7 @@ * Author: Kishon Vijay Abraham I <kishon@ti.com> */ +#include <linux/kernel.h> #include <linux/of.h> #include "pcie-designware.h" @@ -593,6 +594,7 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, } aligned_offset = msg_addr & (epc->mem->window.page_size - 1); + msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size); ret = dw_pcie_ep_map_addr(epc, func_no, ep->msi_mem_phys, msg_addr, epc->mem->window.page_size); if (ret) @@ -660,8 +662,13 @@ int dw_pcie_ep_init_complete(struct dw_pcie_ep *ep) nbars = (reg & PCI_REBAR_CTRL_NBAR_MASK) >> PCI_REBAR_CTRL_NBAR_SHIFT; + /* + * PCIe r6.0, sec 7.8.6.2 require us to support at least one + * size in the range from 1 MB to 512 GB. Advertise support + * for 1 MB BAR size only. + */ for (i = 0; i < nbars; i++, offset += PCI_REBAR_CTRL) - dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, 0x0); + dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, BIT(4)); } dw_pcie_setup(pci); diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index 23548b517..ea91d63c8 100644 --- a/drivers/pci/controller/pcie-mediatek.c +++ b/drivers/pci/controller/pcie-mediatek.c @@ -620,14 +620,20 @@ static void mtk_pcie_intr_handler(struct irq_desc *desc) if (status & MSI_STATUS){ unsigned long imsi_status; + /* + * The interrupt status can be cleared even if the + * MSI status remains pending. As such, given the + * edge-triggered interrupt type, its status should + * be cleared before being dispatched to the + * handler of the underlying device. + */ + writel(MSI_STATUS, port->base + PCIE_INT_STATUS); while ((imsi_status = readl(port->base + PCIE_IMSI_STATUS))) { for_each_set_bit(bit, &imsi_status, MTK_MSI_IRQS_NUM) { virq = irq_find_mapping(port->inner_domain, bit); generic_handle_irq(virq); } } - /* Clear MSI interrupt status */ - writel(MSI_STATUS, port->base + PCIE_INT_STATUS); } } diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 3da69b26e..27377f2f9 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1409,7 +1409,7 @@ static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc) return (irq_hw_number_t)desc->msi_attrib.entry_nr | pci_dev_id(dev) << 11 | - (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27; + ((irq_hw_number_t)(pci_domain_nr(dev->bus) & 0xFFFFFFFF)) << 27; } static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc) diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index c22cc20db..ae675c5a4 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -444,16 +444,21 @@ static int pci_device_remove(struct device *dev) struct pci_dev *pci_dev = to_pci_dev(dev); struct pci_driver *drv = pci_dev->driver; - if (drv) { - if (drv->remove) { - pm_runtime_get_sync(dev); - drv->remove(pci_dev); - pm_runtime_put_noidle(dev); - } - pcibios_free_irq(pci_dev); - pci_dev->driver = NULL; - pci_iov_remove(pci_dev); + if (drv->remove) { + pm_runtime_get_sync(dev); + /* + * If the driver provides a .runtime_idle() callback and it has + * started to run already, it may continue to run in parallel + * with the code below, so wait until all of the runtime PM + * activity has completed. + */ + pm_runtime_barrier(dev); + drv->remove(pci_dev); + pm_runtime_put_noidle(dev); } + pcibios_free_irq(pci_dev); + pci_dev->driver = NULL; + pci_iov_remove(pci_dev); /* Undo the runtime PM settings in local_pci_probe() */ pm_runtime_put_sync(dev); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 1f8106ec7..d1631109b 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -31,6 +31,7 @@ #include <linux/vmalloc.h> #include <asm/dma.h> #include <linux/aer.h> +#include <linux/bitfield.h> #include "pci.h" DEFINE_MUTEX(pci_slot_mutex); @@ -4572,13 +4573,10 @@ EXPORT_SYMBOL(pci_wait_for_pending_transaction); */ bool pcie_has_flr(struct pci_dev *dev) { - u32 cap; - if (dev->dev_flags & PCI_DEV_FLAGS_NO_FLR_RESET) return false; - pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &cap); - return cap & PCI_EXP_DEVCAP_FLR; + return FIELD_GET(PCI_EXP_DEVCAP_FLR, dev->devcap) == 1; } EXPORT_SYMBOL_GPL(pcie_has_flr); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 72436000f..da40f2903 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -399,11 +399,6 @@ static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused) return 0; } -static inline bool pci_dev_is_disconnected(const struct pci_dev *dev) -{ - return dev->error_state == pci_channel_io_perm_failure; -} - /* pci_dev priv_flags */ #define PCI_DEV_ADDED 0 #define PCI_DPC_RECOVERED 1 @@ -447,6 +442,15 @@ int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info); void aer_print_error(struct pci_dev *dev, struct aer_err_info *info); #endif /* CONFIG_PCIEAER */ +#ifdef CONFIG_PCIEPORTBUS +/* Cached RCEC Endpoint Association */ +struct rcec_ea { + u8 nextbusn; + u8 lastbusn; + u32 bitmap; +}; +#endif + #ifdef CONFIG_PCIE_DPC void pci_save_dpc_state(struct pci_dev *dev); void pci_restore_dpc_state(struct pci_dev *dev); @@ -461,6 +465,14 @@ static inline void pci_dpc_init(struct pci_dev *pdev) {} static inline bool pci_dpc_recovered(struct pci_dev *pdev) { return false; } #endif +#ifdef CONFIG_PCIEPORTBUS +void pci_rcec_init(struct pci_dev *dev); +void pci_rcec_exit(struct pci_dev *dev); +#else +static inline void pci_rcec_init(struct pci_dev *dev) {} +static inline void pci_rcec_exit(struct pci_dev *dev) {} +#endif + #ifdef CONFIG_PCI_ATS /* Address Translation Service */ void pci_ats_init(struct pci_dev *dev); diff --git a/drivers/pci/pcie/Makefile b/drivers/pci/pcie/Makefile index 9a7085668..b2980db88 100644 --- a/drivers/pci/pcie/Makefile +++ b/drivers/pci/pcie/Makefile @@ -2,7 +2,7 @@ # # Makefile for PCI Express features and port driver -pcieportdrv-y := portdrv_core.o portdrv_pci.o err.o +pcieportdrv-y := portdrv_core.o portdrv_pci.o err.o rcec.o obj-$(CONFIG_PCIEPORTBUS) += pcieportdrv.o diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index 9564b7400..d58b02237 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -741,7 +741,7 @@ static void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info) u8 bus = info->id >> 8; u8 devfn = info->id & 0xff; - pci_info(dev, "%s%s error received: %04x:%02x:%02x.%d\n", + pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d\n", info->multi_error_valid ? "Multiple " : "", aer_error_severity_string[info->severity], pci_domain_nr(dev->bus), bus, PCI_SLOT(devfn), @@ -926,7 +926,12 @@ static bool find_source_device(struct pci_dev *parent, pci_walk_bus(parent->subordinate, find_device_iter, e_info); if (!e_info->error_dev_num) { - pci_info(parent, "can't find device of ID%04x\n", e_info->id); + u8 bus = e_info->id >> 8; + u8 devfn = e_info->id & 0xff; + + pci_info(parent, "found no error details for %04x:%02x:%02x.%d\n", + pci_domain_nr(parent->bus), bus, PCI_SLOT(devfn), + PCI_FUNC(devfn)); return false; } return true; diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index f21d64ae4..ab83f78f3 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -231,7 +231,7 @@ static void dpc_process_rp_pio_error(struct pci_dev *pdev) for (i = 0; i < pdev->dpc_rp_log_size - 5; i++) { pci_read_config_dword(pdev, - cap + PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG, &prefix); + cap + PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG + i * 4, &prefix); pci_err(pdev, "TLP Prefix Header: dw%d, %#010x\n", i, prefix); } clear_status: @@ -335,11 +335,16 @@ void pci_dpc_init(struct pci_dev *pdev) return; pdev->dpc_rp_extensions = true; - pdev->dpc_rp_log_size = (cap & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8; - if (pdev->dpc_rp_log_size < 4 || pdev->dpc_rp_log_size > 9) { - pci_err(pdev, "RP PIO log size %u is invalid\n", - pdev->dpc_rp_log_size); - pdev->dpc_rp_log_size = 0; + + /* Quirks may set dpc_rp_log_size if device or firmware is buggy */ + if (!pdev->dpc_rp_log_size) { + pdev->dpc_rp_log_size = + (cap & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8; + if (pdev->dpc_rp_log_size < 4 || pdev->dpc_rp_log_size > 9) { + pci_err(pdev, "RP PIO log size %u is invalid\n", + pdev->dpc_rp_log_size); + pdev->dpc_rp_log_size = 0; + } } } diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index 984aa023c..bb4febcf4 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -13,6 +13,7 @@ #define dev_fmt(fmt) "AER: " fmt #include <linux/pci.h> +#include <linux/pm_runtime.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/errno.h> @@ -79,6 +80,18 @@ static int report_error_detected(struct pci_dev *dev, return 0; } +static int pci_pm_runtime_get_sync(struct pci_dev *pdev, void *data) +{ + pm_runtime_get_sync(&pdev->dev); + return 0; +} + +static int pci_pm_runtime_put(struct pci_dev *pdev, void *data) +{ + pm_runtime_put(&pdev->dev); + return 0; +} + static int report_frozen_detected(struct pci_dev *dev, void *data) { return report_error_detected(dev, pci_channel_io_frozen, data); @@ -176,6 +189,7 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev, int type = pci_pcie_type(dev); struct pci_dev *bridge; pci_ers_result_t status = PCI_ERS_RESULT_CAN_RECOVER; + struct pci_host_bridge *host = pci_find_host_bridge(dev->bus); /* * If the error was detected by a Root Port, Downstream Port, or @@ -193,6 +207,8 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev, else bridge = pci_upstream_bridge(dev); + pci_walk_bridge(bridge, pci_pm_runtime_get_sync, NULL); + pci_dbg(bridge, "broadcast error_detected message\n"); if (state == pci_channel_io_frozen) { pci_walk_bridge(bridge, report_frozen_detected, &status); @@ -227,13 +243,26 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev, pci_dbg(bridge, "broadcast resume message\n"); pci_walk_bridge(bridge, report_resume, &status); - if (pcie_aer_is_native(bridge)) + /* + * If we have native control of AER, clear error status in the Root + * Port or Downstream Port that signaled the error. If the + * platform retained control of AER, it is responsible for clearing + * this status. In that case, the signaling device may not even be + * visible to the OS. + */ + if (host->native_aer || pcie_ports_native) { pcie_clear_device_status(bridge); - pci_aer_clear_nonfatal_status(bridge); + pci_aer_clear_nonfatal_status(bridge); + } + + pci_walk_bridge(bridge, pci_pm_runtime_put, NULL); + pci_info(bridge, "device recovery successful\n"); return status; failed: + pci_walk_bridge(bridge, pci_pm_runtime_put, NULL); + pci_uevent_ers(bridge, PCI_ERS_RESULT_DISCONNECT); /* TODO: Should kernel panic here? */ diff --git a/drivers/pci/pcie/rcec.c b/drivers/pci/pcie/rcec.c new file mode 100644 index 000000000..038e9d706 --- /dev/null +++ b/drivers/pci/pcie/rcec.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Root Complex Event Collector Support + * + * Authors: + * Sean V Kelley <sean.v.kelley@intel.com> + * Qiuxu Zhuo <qiuxu.zhuo@intel.com> + * + * Copyright (C) 2020 Intel Corp. + */ + +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/pci_regs.h> + +#include "../pci.h" + +void pci_rcec_init(struct pci_dev *dev) +{ + struct rcec_ea *rcec_ea; + u32 rcec, hdr, busn; + u8 ver; + + /* Only for Root Complex Event Collectors */ + if (pci_pcie_type(dev) != PCI_EXP_TYPE_RC_EC) + return; + + rcec = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_RCEC); + if (!rcec) + return; + + rcec_ea = kzalloc(sizeof(*rcec_ea), GFP_KERNEL); + if (!rcec_ea) + return; + + pci_read_config_dword(dev, rcec + PCI_RCEC_RCIEP_BITMAP, + &rcec_ea->bitmap); + + /* Check whether RCEC BUSN register is present */ + pci_read_config_dword(dev, rcec, &hdr); + ver = PCI_EXT_CAP_VER(hdr); + if (ver >= PCI_RCEC_BUSN_REG_VER) { + pci_read_config_dword(dev, rcec + PCI_RCEC_BUSN, &busn); + rcec_ea->nextbusn = PCI_RCEC_BUSN_NEXT(busn); + rcec_ea->lastbusn = PCI_RCEC_BUSN_LAST(busn); + } else { + /* Avoid later ver check by setting nextbusn */ + rcec_ea->nextbusn = 0xff; + rcec_ea->lastbusn = 0x00; + } + + dev->rcec_ea = rcec_ea; +} + +void pci_rcec_exit(struct pci_dev *dev) +{ + kfree(dev->rcec_ea); + dev->rcec_ea = NULL; +} diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ece90a239..02a75f3b5 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -19,6 +19,7 @@ #include <linux/hypervisor.h> #include <linux/irqdomain.h> #include <linux/pm_runtime.h> +#include <linux/bitfield.h> #include "pci.h" #define CARDBUS_LATENCY_TIMER 176 /* secondary latency timer */ @@ -1496,8 +1497,8 @@ void set_pcie_port_type(struct pci_dev *pdev) pdev->pcie_cap = pos; pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, ®16); pdev->pcie_flags_reg = reg16; - pci_read_config_word(pdev, pos + PCI_EXP_DEVCAP, ®16); - pdev->pcie_mpss = reg16 & PCI_EXP_DEVCAP_PAYLOAD; + pci_read_config_dword(pdev, pos + PCI_EXP_DEVCAP, &pdev->devcap); + pdev->pcie_mpss = FIELD_GET(PCI_EXP_DEVCAP_PAYLOAD, pdev->devcap); parent = pci_upstream_bridge(pdev); if (!parent) @@ -2216,6 +2217,7 @@ static void pci_configure_device(struct pci_dev *dev) static void pci_release_capabilities(struct pci_dev *dev) { pci_aer_exit(dev); + pci_rcec_exit(dev); pci_vpd_release(dev); pci_iov_release(dev); pci_free_cap_save_buffers(dev); @@ -2416,6 +2418,7 @@ static void pci_init_capabilities(struct pci_dev *dev) pci_ptm_init(dev); /* Precision Time Measurement */ pci_aer_init(dev); /* Advanced Error Reporting */ pci_dpc_init(dev); /* Downstream Port Containment */ + pci_rcec_init(dev); /* Root Complex Event Collector */ pcie_report_downtraining(dev); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 21661feee..60a469bdc 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -12,6 +12,7 @@ * file, where their drivers can use them. */ +#include <linux/bitfield.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/export.h> @@ -609,10 +610,13 @@ static void quirk_amd_dwc_class(struct pci_dev *pdev) { u32 class = pdev->class; - /* Use "USB Device (not host controller)" class */ - pdev->class = PCI_CLASS_SERIAL_USB_DEVICE; - pci_info(pdev, "PCI class overridden (%#08x -> %#08x) so dwc3 driver can claim this instead of xhci\n", - class, pdev->class); + if (class != PCI_CLASS_SERIAL_USB_DEVICE) { + /* Use "USB Device (not host controller)" class */ + pdev->class = PCI_CLASS_SERIAL_USB_DEVICE; + pci_info(pdev, + "PCI class overridden (%#08x -> %#08x) so dwc3 driver can claim this instead of xhci\n", + class, pdev->class); + } } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB, quirk_amd_dwc_class); @@ -3639,6 +3643,19 @@ DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_ATI, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, 8, quirk_no_pm_reset); /* + * Spectrum-{1,2,3,4} devices report that a D3hot->D0 transition causes a reset + * (i.e., they advertise NoSoftRst-). However, this transition does not have + * any effect on the device: It continues to be operational and network ports + * remain up. Advertising this support makes it seem as if a PM reset is viable + * for these devices. Mark it as unavailable to skip it when testing reset + * methods. + */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MELLANOX, 0xcb84, quirk_no_pm_reset); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MELLANOX, 0xcf6c, quirk_no_pm_reset); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MELLANOX, 0xcf70, quirk_no_pm_reset); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MELLANOX, 0xcf80, quirk_no_pm_reset); + +/* * Thunderbolt controllers with broken MSI hotplug signaling: * Entire 1st generation (Light Ridge, Eagle Ridge, Light Peak) and part * of the 2nd generation (Cactus Ridge 4C up to revision 1, Port Ridge). @@ -5348,6 +5365,7 @@ static void quirk_no_ext_tags(struct pci_dev *pdev) pci_walk_bus(bridge->bus, pci_configure_extended_tags, NULL); } +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_3WARE, 0x1004, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0132, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0140, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0141, quirk_no_ext_tags); @@ -5835,3 +5853,102 @@ static void nvidia_ion_ahci_fixup(struct pci_dev *pdev) pdev->dev_flags |= PCI_DEV_FLAGS_HAS_MSI_MASKING; } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0ab8, nvidia_ion_ahci_fixup); + +static void rom_bar_overlap_defect(struct pci_dev *dev) +{ + pci_info(dev, "working around ROM BAR overlap defect\n"); + dev->rom_bar_overlap = 1; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1533, rom_bar_overlap_defect); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1536, rom_bar_overlap_defect); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1537, rom_bar_overlap_defect); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1538, rom_bar_overlap_defect); + +#ifdef CONFIG_PCIEASPM +/* + * Several Intel DG2 graphics devices advertise that they can only tolerate + * 1us latency when transitioning from L1 to L0, which may prevent ASPM L1 + * from being enabled. But in fact these devices can tolerate unlimited + * latency. Override their Device Capabilities value to allow ASPM L1 to + * be enabled. + */ +static void aspm_l1_acceptable_latency(struct pci_dev *dev) +{ + u32 l1_lat = FIELD_GET(PCI_EXP_DEVCAP_L1, dev->devcap); + + if (l1_lat < 7) { + dev->devcap |= FIELD_PREP(PCI_EXP_DEVCAP_L1, 7); + pci_info(dev, "ASPM: overriding L1 acceptable latency from %#x to 0x7\n", + l1_lat); + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f80, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f81, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f82, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f83, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f84, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f85, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f86, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f87, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x4f88, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x5690, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x5691, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x5692, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x5693, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x5694, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x5695, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56a0, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56a1, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56a2, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56a3, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56a4, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56a5, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56a6, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56b0, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56b1, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56c0, aspm_l1_acceptable_latency); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56c1, aspm_l1_acceptable_latency); +#endif + +#ifdef CONFIG_PCIE_DPC +/* + * Intel Ice Lake, Tiger Lake and Alder Lake BIOS has a bug that clears + * the DPC RP PIO Log Size of the integrated Thunderbolt PCIe Root + * Ports. + */ +static void dpc_log_size(struct pci_dev *dev) +{ + u16 dpc, val; + + dpc = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_DPC); + if (!dpc) + return; + + pci_read_config_word(dev, dpc + PCI_EXP_DPC_CAP, &val); + if (!(val & PCI_EXP_DPC_CAP_RP_EXT)) + return; + + if (!((val & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8)) { + pci_info(dev, "Overriding RP PIO Log Size to 4\n"); + dev->dpc_rp_log_size = 4; + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x461f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x462f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x463f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x466e, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a1d, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a1f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a21, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a23, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a23, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a25, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a27, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a29, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2b, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2d, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a2f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a31, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0xa73f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0xa76e, dpc_log_size); +#endif diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index 875d50c16..b492e67c3 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -75,12 +75,16 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno) * as zero when disabled, so don't update ROM BARs unless * they're enabled. See * https://lore.kernel.org/r/43147B3D.1030309@vc.cvut.cz/ + * But we must update ROM BAR for buggy devices where even a + * disabled ROM can conflict with other BARs. */ - if (!(res->flags & IORESOURCE_ROM_ENABLE)) + if (!(res->flags & IORESOURCE_ROM_ENABLE) && + !dev->rom_bar_overlap) return; reg = dev->rom_base_reg; - new |= PCI_ROM_ADDRESS_ENABLE; + if (res->flags & IORESOURCE_ROM_ENABLE) + new |= PCI_ROM_ADDRESS_ENABLE; } else return; diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index ba5245992..9aa230c32 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -1251,13 +1251,6 @@ static void stdev_release(struct device *dev) { struct switchtec_dev *stdev = to_stdev(dev); - if (stdev->dma_mrpc) { - iowrite32(0, &stdev->mmio_mrpc->dma_en); - flush_wc_buf(stdev); - writeq(0, &stdev->mmio_mrpc->dma_addr); - dma_free_coherent(&stdev->pdev->dev, sizeof(*stdev->dma_mrpc), - stdev->dma_mrpc, stdev->dma_mrpc_dma_addr); - } kfree(stdev); } @@ -1301,7 +1294,7 @@ static struct switchtec_dev *stdev_create(struct pci_dev *pdev) return ERR_PTR(-ENOMEM); stdev->alive = true; - stdev->pdev = pdev; + stdev->pdev = pci_dev_get(pdev); INIT_LIST_HEAD(&stdev->mrpc_queue); mutex_init(&stdev->mrpc_mutex); stdev->mrpc_busy = 0; @@ -1335,6 +1328,7 @@ static struct switchtec_dev *stdev_create(struct pci_dev *pdev) return stdev; err_put: + pci_dev_put(stdev->pdev); put_device(&stdev->dev); return ERR_PTR(rc); } @@ -1587,6 +1581,18 @@ static int switchtec_init_pci(struct switchtec_dev *stdev, return 0; } +static void switchtec_exit_pci(struct switchtec_dev *stdev) +{ + if (stdev->dma_mrpc) { + iowrite32(0, &stdev->mmio_mrpc->dma_en); + flush_wc_buf(stdev); + writeq(0, &stdev->mmio_mrpc->dma_addr); + dma_free_coherent(&stdev->pdev->dev, sizeof(*stdev->dma_mrpc), + stdev->dma_mrpc, stdev->dma_mrpc_dma_addr); + stdev->dma_mrpc = NULL; + } +} + static int switchtec_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { @@ -1609,7 +1615,7 @@ static int switchtec_pci_probe(struct pci_dev *pdev, rc = switchtec_init_isr(stdev); if (rc) { dev_err(&stdev->dev, "failed to init isr.\n"); - goto err_put; + goto err_exit_pci; } iowrite32(SWITCHTEC_EVENT_CLEAR | @@ -1630,6 +1636,8 @@ static int switchtec_pci_probe(struct pci_dev *pdev, err_devadd: stdev_kill(stdev); +err_exit_pci: + switchtec_exit_pci(stdev); err_put: ida_simple_remove(&switchtec_minor_ida, MINOR(stdev->dev.devt)); put_device(&stdev->dev); @@ -1646,6 +1654,9 @@ static void switchtec_pci_remove(struct pci_dev *pdev) ida_simple_remove(&switchtec_minor_ida, MINOR(stdev->dev.devt)); dev_info(&stdev->dev, "unregistered.\n"); stdev_kill(stdev); + switchtec_exit_pci(stdev); + pci_dev_put(stdev->pdev); + stdev->pdev = NULL; put_device(&stdev->dev); } diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c index 2cb949f93..c0802152f 100644 --- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c +++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c @@ -633,8 +633,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) channel->irq = platform_get_irq_optional(pdev, 0); channel->dr_mode = rcar_gen3_get_dr_mode(dev->of_node); if (channel->dr_mode != USB_DR_MODE_UNKNOWN) { - int ret; - channel->is_otg_channel = true; channel->uses_otg_pins = !of_property_read_bool(dev->of_node, "renesas,no-otg-pins"); @@ -693,8 +691,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) ret = PTR_ERR(provider); goto error; } else if (channel->is_otg_channel) { - int ret; - ret = device_create_file(dev, &dev_attr_role); if (ret < 0) goto error; diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index 8f11b293c..856397def 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -1399,6 +1399,19 @@ int tegra_xusb_padctl_get_usb3_companion(struct tegra_xusb_padctl *padctl, } EXPORT_SYMBOL_GPL(tegra_xusb_padctl_get_usb3_companion); +int tegra_xusb_padctl_get_port_number(struct phy *phy) +{ + struct tegra_xusb_lane *lane; + + if (!phy) + return -ENODEV; + + lane = phy_get_drvdata(phy); + + return lane->index; +} +EXPORT_SYMBOL_GPL(tegra_xusb_padctl_get_port_number); + MODULE_AUTHOR("Thierry Reding <treding@nvidia.com>"); MODULE_DESCRIPTION("Tegra XUSB Pad Controller driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c index f77ac041d..95e72f7a3 100644 --- a/drivers/phy/ti/phy-omap-usb2.c +++ b/drivers/phy/ti/phy-omap-usb2.c @@ -116,7 +116,7 @@ static int omap_usb_set_vbus(struct usb_otg *otg, bool enabled) { struct omap_usb *phy = phy_to_omapusb(otg->usb_phy); - if (!phy->comparator) + if (!phy->comparator || !phy->comparator->set_vbus) return -ENODEV; return phy->comparator->set_vbus(phy->comparator, enabled); @@ -126,7 +126,7 @@ static int omap_usb_start_srp(struct usb_otg *otg) { struct omap_usb *phy = phy_to_omapusb(otg->usb_phy); - if (!phy->comparator) + if (!phy->comparator || !phy->comparator->start_srp) return -ENODEV; return phy->comparator->start_srp(phy->comparator); diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8192.c b/drivers/pinctrl/mediatek/pinctrl-mt8192.c index 0c16b2c75..f3020e3c8 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt8192.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt8192.c @@ -1346,7 +1346,6 @@ static const struct mtk_pin_reg_calc mt8192_reg_cals[PINCTRL_PIN_REG_MAX] = { [PINCTRL_PIN_REG_DIR] = MTK_RANGE(mt8192_pin_dir_range), [PINCTRL_PIN_REG_DI] = MTK_RANGE(mt8192_pin_di_range), [PINCTRL_PIN_REG_DO] = MTK_RANGE(mt8192_pin_do_range), - [PINCTRL_PIN_REG_SR] = MTK_RANGE(mt8192_pin_dir_range), [PINCTRL_PIN_REG_SMT] = MTK_RANGE(mt8192_pin_smt_range), [PINCTRL_PIN_REG_IES] = MTK_RANGE(mt8192_pin_ies_range), [PINCTRL_PIN_REG_PU] = MTK_RANGE(mt8192_pin_pu_range), diff --git a/drivers/pinctrl/renesas/core.c b/drivers/pinctrl/renesas/core.c index 54f1a7334..c39085448 100644 --- a/drivers/pinctrl/renesas/core.c +++ b/drivers/pinctrl/renesas/core.c @@ -868,9 +868,11 @@ static void __init sh_pfc_check_cfg_reg(const char *drvname, sh_pfc_err("reg 0x%x: var_field_width declares %u instead of %u bits\n", cfg_reg->reg, rw, cfg_reg->reg_width); - if (n != cfg_reg->nr_enum_ids) + if (n != cfg_reg->nr_enum_ids) { sh_pfc_err("reg 0x%x: enum_ids[] has %u instead of %u values\n", cfg_reg->reg, cfg_reg->nr_enum_ids, n); + n = cfg_reg->nr_enum_ids; + } check_enum_ids: sh_pfc_check_reg_enums(drvname, cfg_reg->reg, cfg_reg->enum_ids, n); diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index a90c32d07..9c8a6722f 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -230,6 +230,12 @@ static const struct dmi_system_id dmi_switches_allow_list[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7352"), }, }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion 13 x360 PC"), + }, + }, {} /* Array terminator */ }; diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index eedff2ae2..fbaa61859 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -50,7 +50,7 @@ static const struct property_entry chuwi_hi8_air_props[] = { }; static const struct ts_dmi_data chuwi_hi8_air_data = { - .acpi_name = "MSSL1680:00", + .acpi_name = "MSSL1680", .properties = chuwi_hi8_air_props, }; @@ -1085,6 +1085,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* Chuwi Vi8 dual-boot (CWI506) */ + .driver_data = (void *)&chuwi_vi8_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_MATCH(DMI_PRODUCT_NAME, "i86"), + DMI_MATCH(DMI_BIOS_VERSION, "CHUWI2.D86JHBNR02"), + }, + }, + { /* Chuwi Vi8 Plus (CWI519) */ .driver_data = (void *)&chuwi_vi8_plus_data, .matches = { @@ -1648,7 +1657,7 @@ static void ts_dmi_add_props(struct i2c_client *client) int error; if (has_acpi_companion(dev) && - !strncmp(ts_data->acpi_name, client->name, I2C_NAME_SIZE)) { + strstarts(client->name, ts_data->acpi_name)) { error = device_add_properties(dev, ts_data->properties); if (error) dev_err(dev, "failed to add properties: %d\n", error); diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c index da78dc77a..9879deb4d 100644 --- a/drivers/pnp/pnpacpi/rsparser.c +++ b/drivers/pnp/pnpacpi/rsparser.c @@ -151,13 +151,13 @@ static int vendor_resource_matches(struct pnp_dev *dev, static void pnpacpi_parse_allocated_vendor(struct pnp_dev *dev, struct acpi_resource_vendor_typed *vendor) { - if (vendor_resource_matches(dev, vendor, &hp_ccsr_uuid, 16)) { - u64 start, length; + struct { u64 start, length; } range; - memcpy(&start, vendor->byte_data, sizeof(start)); - memcpy(&length, vendor->byte_data + 8, sizeof(length)); - - pnp_add_mem_resource(dev, start, start + length - 1, 0); + if (vendor_resource_matches(dev, vendor, &hp_ccsr_uuid, + sizeof(range))) { + memcpy(&range, vendor->byte_data, sizeof(range)); + pnp_add_mem_resource(dev, range.start, range.start + + range.length - 1, 0); } } diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c index 0e32efb10..6fbae8fc2 100644 --- a/drivers/power/supply/bq27xxx_battery_i2c.c +++ b/drivers/power/supply/bq27xxx_battery_i2c.c @@ -209,7 +209,9 @@ static int bq27xxx_battery_i2c_remove(struct i2c_client *client) { struct bq27xxx_device_info *di = i2c_get_clientdata(client); - free_irq(client->irq, di); + if (client->irq) + free_irq(client->irq, di); + bq27xxx_battery_teardown(di); mutex_lock(&battery_mutex); diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 51c4f604d..54330eb0d 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -2768,7 +2768,8 @@ static int _regulator_enable(struct regulator *regulator) /* Fallthrough on positive return values - already enabled */ } - rdev->use_count++; + if (regulator->enable_count == 1) + rdev->use_count++; return 0; @@ -2846,37 +2847,40 @@ static int _regulator_disable(struct regulator *regulator) lockdep_assert_held_once(&rdev->mutex.base); - if (WARN(rdev->use_count <= 0, + if (WARN(regulator->enable_count == 0, "unbalanced disables for %s\n", rdev_get_name(rdev))) return -EIO; - /* are we the last user and permitted to disable ? */ - if (rdev->use_count == 1 && - (rdev->constraints && !rdev->constraints->always_on)) { - - /* we are last user */ - if (regulator_ops_is_valid(rdev, REGULATOR_CHANGE_STATUS)) { - ret = _notifier_call_chain(rdev, - REGULATOR_EVENT_PRE_DISABLE, - NULL); - if (ret & NOTIFY_STOP_MASK) - return -EINVAL; - - ret = _regulator_do_disable(rdev); - if (ret < 0) { - rdev_err(rdev, "failed to disable: %pe\n", ERR_PTR(ret)); - _notifier_call_chain(rdev, - REGULATOR_EVENT_ABORT_DISABLE, + if (regulator->enable_count == 1) { + /* disabling last enable_count from this regulator */ + /* are we the last user and permitted to disable ? */ + if (rdev->use_count == 1 && + (rdev->constraints && !rdev->constraints->always_on)) { + + /* we are last user */ + if (regulator_ops_is_valid(rdev, REGULATOR_CHANGE_STATUS)) { + ret = _notifier_call_chain(rdev, + REGULATOR_EVENT_PRE_DISABLE, + NULL); + if (ret & NOTIFY_STOP_MASK) + return -EINVAL; + + ret = _regulator_do_disable(rdev); + if (ret < 0) { + rdev_err(rdev, "failed to disable: %pe\n", ERR_PTR(ret)); + _notifier_call_chain(rdev, + REGULATOR_EVENT_ABORT_DISABLE, + NULL); + return ret; + } + _notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE, NULL); - return ret; } - _notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE, - NULL); - } - rdev->use_count = 0; - } else if (rdev->use_count > 1) { - rdev->use_count--; + rdev->use_count = 0; + } else if (rdev->use_count > 1) { + rdev->use_count--; + } } if (ret == 0) diff --git a/drivers/regulator/pwm-regulator.c b/drivers/regulator/pwm-regulator.c index 7629476d9..f4d9d9455 100644 --- a/drivers/regulator/pwm-regulator.c +++ b/drivers/regulator/pwm-regulator.c @@ -158,6 +158,9 @@ static int pwm_regulator_get_voltage(struct regulator_dev *rdev) pwm_get_state(drvdata->pwm, &pstate); voltage = pwm_get_relative_duty_cycle(&pstate, duty_unit); + if (voltage < min(max_uV_duty, min_uV_duty) || + voltage > max(max_uV_duty, min_uV_duty)) + return -ENOTRECOVERABLE; /* * The dutycycle for min_uV might be greater than the one for max_uV. diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig index d99548fb5..6dbf6ed10 100644 --- a/drivers/remoteproc/Kconfig +++ b/drivers/remoteproc/Kconfig @@ -249,7 +249,7 @@ config ST_SLIM_REMOTEPROC config STM32_RPROC tristate "STM32 remoteproc support" - depends on ARCH_STM32 + depends on ARCH_STM32 || COMPILE_TEST depends on REMOTEPROC select MAILBOX help diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index cc55ff012..a933e3456 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1539,6 +1539,32 @@ disable_iommu: return ret; } +static int rproc_set_rsc_table(struct rproc *rproc) +{ + struct resource_table *table_ptr; + struct device *dev = &rproc->dev; + size_t table_sz; + int ret; + + table_ptr = rproc_get_loaded_rsc_table(rproc, &table_sz); + if (!table_ptr) { + /* Not having a resource table is acceptable */ + return 0; + } + + if (IS_ERR(table_ptr)) { + ret = PTR_ERR(table_ptr); + dev_err(dev, "can't load resource table: %d\n", ret); + return ret; + } + + rproc->cached_table = NULL; + rproc->table_ptr = table_ptr; + rproc->table_sz = table_sz; + + return 0; +} + /* * Attach to remote processor - similar to rproc_fw_boot() but without * the steps that deal with the firmware image. @@ -1558,6 +1584,12 @@ static int rproc_actuate(struct rproc *rproc) return ret; } + ret = rproc_set_rsc_table(rproc); + if (ret) { + dev_err(dev, "can't load resource table: %d\n", ret); + goto disable_iommu; + } + /* reset max_notifyid */ rproc->max_notifyid = -1; diff --git a/drivers/remoteproc/remoteproc_internal.h b/drivers/remoteproc/remoteproc_internal.h index c34002888..4f73aac7e 100644 --- a/drivers/remoteproc/remoteproc_internal.h +++ b/drivers/remoteproc/remoteproc_internal.h @@ -178,6 +178,16 @@ struct resource_table *rproc_find_loaded_rsc_table(struct rproc *rproc, } static inline +struct resource_table *rproc_get_loaded_rsc_table(struct rproc *rproc, + size_t *size) +{ + if (rproc->ops->get_loaded_rsc_table) + return rproc->ops->get_loaded_rsc_table(rproc, size); + + return NULL; +} + +static inline bool rproc_u64_fit_in_size_t(u64 val) { if (sizeof(size_t) == sizeof(u64)) diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c index df784fec1..3d411e18a 100644 --- a/drivers/remoteproc/stm32_rproc.c +++ b/drivers/remoteproc/stm32_rproc.c @@ -117,10 +117,10 @@ static int stm32_rproc_mem_alloc(struct rproc *rproc, struct device *dev = rproc->dev.parent; void *va; - dev_dbg(dev, "map memory: %pa+%x\n", &mem->dma, mem->len); - va = ioremap_wc(mem->dma, mem->len); + dev_dbg(dev, "map memory: %pad+%zx\n", &mem->dma, mem->len); + va = (__force void *)ioremap_wc(mem->dma, mem->len); if (IS_ERR_OR_NULL(va)) { - dev_err(dev, "Unable to map memory region: %pa+%x\n", + dev_err(dev, "Unable to map memory region: %pad+0x%zx\n", &mem->dma, mem->len); return -ENOMEM; } @@ -135,7 +135,7 @@ static int stm32_rproc_mem_release(struct rproc *rproc, struct rproc_mem_entry *mem) { dev_dbg(rproc->dev.parent, "unmap memory: %pa\n", &mem->dma); - iounmap(mem->va); + iounmap((__force __iomem void *)mem->va); return 0; } @@ -553,7 +553,74 @@ static void stm32_rproc_kick(struct rproc *rproc, int vqid) } } -static struct rproc_ops st_rproc_ops = { +static int stm32_rproc_da_to_pa(struct rproc *rproc, + u64 da, phys_addr_t *pa) +{ + struct stm32_rproc *ddata = rproc->priv; + struct device *dev = rproc->dev.parent; + struct stm32_rproc_mem *p_mem; + unsigned int i; + + for (i = 0; i < ddata->nb_rmems; i++) { + p_mem = &ddata->rmems[i]; + + if (da < p_mem->dev_addr || + da >= p_mem->dev_addr + p_mem->size) + continue; + + *pa = da - p_mem->dev_addr + p_mem->bus_addr; + dev_dbg(dev, "da %llx to pa %pap\n", da, pa); + + return 0; + } + + dev_err(dev, "can't translate da %llx\n", da); + + return -EINVAL; +} + +static struct resource_table * +stm32_rproc_get_loaded_rsc_table(struct rproc *rproc, size_t *table_sz) +{ + struct stm32_rproc *ddata = rproc->priv; + struct device *dev = rproc->dev.parent; + phys_addr_t rsc_pa; + u32 rsc_da; + int err; + + /* The resource table has already been mapped, nothing to do */ + if (ddata->rsc_va) + goto done; + + err = regmap_read(ddata->rsctbl.map, ddata->rsctbl.reg, &rsc_da); + if (err) { + dev_err(dev, "failed to read rsc tbl addr\n"); + return ERR_PTR(-EINVAL); + } + + if (!rsc_da) + /* no rsc table */ + return ERR_PTR(-ENOENT); + + err = stm32_rproc_da_to_pa(rproc, rsc_da, &rsc_pa); + if (err) + return ERR_PTR(err); + + ddata->rsc_va = devm_ioremap_wc(dev, rsc_pa, RSC_TBL_SIZE); + if (IS_ERR_OR_NULL(ddata->rsc_va)) { + dev_err(dev, "Unable to map memory region: %pa+%x\n", + &rsc_pa, RSC_TBL_SIZE); + ddata->rsc_va = NULL; + return ERR_PTR(-ENOMEM); + } + +done: + /* Assuming the resource table fits in 1kB is fair */ + *table_sz = RSC_TBL_SIZE; + return (__force struct resource_table *)ddata->rsc_va; +} + +static const struct rproc_ops st_rproc_ops = { .start = stm32_rproc_start, .stop = stm32_rproc_stop, .attach = stm32_rproc_attach, @@ -561,6 +628,7 @@ static struct rproc_ops st_rproc_ops = { .load = rproc_elf_load_segments, .parse_fw = stm32_rproc_parse_fw, .find_loaded_rsc_table = rproc_elf_find_loaded_rsc_table, + .get_loaded_rsc_table = stm32_rproc_get_loaded_rsc_table, .sanity_check = rproc_elf_sanity_check, .get_boot_addr = rproc_elf_get_boot_addr, }; @@ -704,75 +772,6 @@ static int stm32_rproc_get_m4_status(struct stm32_rproc *ddata, return regmap_read(ddata->m4_state.map, ddata->m4_state.reg, state); } -static int stm32_rproc_da_to_pa(struct platform_device *pdev, - struct stm32_rproc *ddata, - u64 da, phys_addr_t *pa) -{ - struct device *dev = &pdev->dev; - struct stm32_rproc_mem *p_mem; - unsigned int i; - - for (i = 0; i < ddata->nb_rmems; i++) { - p_mem = &ddata->rmems[i]; - - if (da < p_mem->dev_addr || - da >= p_mem->dev_addr + p_mem->size) - continue; - - *pa = da - p_mem->dev_addr + p_mem->bus_addr; - dev_dbg(dev, "da %llx to pa %#x\n", da, *pa); - - return 0; - } - - dev_err(dev, "can't translate da %llx\n", da); - - return -EINVAL; -} - -static int stm32_rproc_get_loaded_rsc_table(struct platform_device *pdev, - struct rproc *rproc, - struct stm32_rproc *ddata) -{ - struct device *dev = &pdev->dev; - phys_addr_t rsc_pa; - u32 rsc_da; - int err; - - err = regmap_read(ddata->rsctbl.map, ddata->rsctbl.reg, &rsc_da); - if (err) { - dev_err(dev, "failed to read rsc tbl addr\n"); - return err; - } - - if (!rsc_da) - /* no rsc table */ - return 0; - - err = stm32_rproc_da_to_pa(pdev, ddata, rsc_da, &rsc_pa); - if (err) - return err; - - ddata->rsc_va = devm_ioremap_wc(dev, rsc_pa, RSC_TBL_SIZE); - if (IS_ERR_OR_NULL(ddata->rsc_va)) { - dev_err(dev, "Unable to map memory region: %pa+%zx\n", - &rsc_pa, RSC_TBL_SIZE); - ddata->rsc_va = NULL; - return -ENOMEM; - } - - /* - * The resource table is already loaded in device memory, no need - * to work with a cached table. - */ - rproc->cached_table = NULL; - /* Assuming the resource table fits in 1kB is fair */ - rproc->table_sz = RSC_TBL_SIZE; - rproc->table_ptr = (struct resource_table *)ddata->rsc_va; - - return 0; -} - static int stm32_rproc_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -812,10 +811,6 @@ static int stm32_rproc_probe(struct platform_device *pdev) ret = stm32_rproc_parse_memory_regions(rproc); if (ret) goto free_resources; - - ret = stm32_rproc_get_loaded_rsc_table(pdev, rproc, ddata); - if (ret) - goto free_resources; } rproc->has_iommu = false; diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index 7d7ed4e5c..a8b5d1088 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -387,6 +387,7 @@ static void virtio_rpmsg_release_device(struct device *dev) struct rpmsg_device *rpdev = to_rpmsg_device(dev); struct virtio_rpmsg_channel *vch = to_virtio_rpmsg_channel(rpdev); + kfree(rpdev->driver_override); kfree(vch); } diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 54cf5ec8f..8ddd334e0 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -1833,7 +1833,8 @@ config RTC_DRV_MT2712 config RTC_DRV_MT6397 tristate "MediaTek PMIC based RTC" - depends on MFD_MT6397 || (COMPILE_TEST && IRQ_DOMAIN) + depends on MFD_MT6397 || COMPILE_TEST + select IRQ_DOMAIN help This selects the MediaTek(R) RTC driver. RTC is part of MediaTek MT6397 PMIC. You should enable MT6397 PMIC MFD before select diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 7f560937b..2c4ccab6e 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -292,7 +292,7 @@ static int cmos_read_alarm(struct device *dev, struct rtc_wkalrm *t) /* This not only a rtc_op, but also called directly */ if (!is_valid_irq(cmos->irq)) - return -EIO; + return -ETIMEDOUT; /* Basic alarms only support hour, minute, and seconds fields. * Some also support day and month, for alarms up to a year in @@ -557,7 +557,7 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t) * Use mc146818_avoid_UIP() to avoid this. */ if (!mc146818_avoid_UIP(cmos_set_alarm_callback, &p)) - return -EIO; + return -ETIMEDOUT; cmos->alarm_expires = rtc_tm_to_time64(&t->time); diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c index c533d1dad..a5dba3829 100644 --- a/drivers/s390/cio/device_ops.c +++ b/drivers/s390/cio/device_ops.c @@ -202,7 +202,8 @@ int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa, return -EINVAL; if (cdev->private->state == DEV_STATE_NOT_OPER) return -ENODEV; - if (cdev->private->state == DEV_STATE_VERIFY) { + if (cdev->private->state == DEV_STATE_VERIFY || + cdev->private->flags.doverify) { /* Remember to fake irb when finished. */ if (!cdev->private->flags.fake_irb) { cdev->private->flags.fake_irb = FAKE_CMD_IRB; @@ -214,8 +215,7 @@ int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa, } if (cdev->private->state != DEV_STATE_ONLINE || ((sch->schib.scsw.cmd.stctl & SCSW_STCTL_PRIM_STATUS) && - !(sch->schib.scsw.cmd.stctl & SCSW_STCTL_SEC_STATUS)) || - cdev->private->flags.doverify) + !(sch->schib.scsw.cmd.stctl & SCSW_STCTL_SEC_STATUS))) return -EBUSY; ret = cio_set_options (sch, flags); if (ret) diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index b51800971..dde10a5c7 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -576,6 +576,7 @@ static inline struct zcrypt_queue *zcrypt_pick_queue(struct zcrypt_card *zc, { if (!zq || !try_module_get(zq->queue->ap_dev.drv->driver.owner)) return NULL; + zcrypt_card_get(zc); zcrypt_queue_get(zq); get_device(&zq->queue->ap_dev.device); atomic_add(weight, &zc->load); @@ -595,6 +596,7 @@ static inline void zcrypt_drop_queue(struct zcrypt_card *zc, atomic_sub(weight, &zq->load); put_device(&zq->queue->ap_dev.device); zcrypt_queue_put(zq); + zcrypt_card_put(zc); module_put(mod); } diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index d8cdf9024..fee7b09eb 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -257,9 +257,10 @@ static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover) if (!recover) { hash_del(&addr->hnode); kfree(addr); - continue; + } else { + /* prepare for recovery */ + addr->disp_flag = QETH_DISP_ADDR_ADD; } - addr->disp_flag = QETH_DISP_ADDR_ADD; } mutex_unlock(&card->ip_lock); @@ -280,9 +281,11 @@ static void qeth_l3_recover_ip(struct qeth_card *card) if (addr->disp_flag == QETH_DISP_ADDR_ADD) { rc = qeth_l3_register_addr_entry(card, addr); - if (!rc) { + if (!rc || rc == -EADDRINUSE || rc == -ENETDOWN) { + /* keep it in the records */ addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING; } else { + /* bad address */ hash_del(&addr->hnode); kfree(addr); } diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 6524e1fe5..f59c90024 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -1289,7 +1289,7 @@ source "drivers/scsi/arm/Kconfig" config JAZZ_ESP bool "MIPS JAZZ FAS216 SCSI support" - depends on MACH_JAZZ && SCSI + depends on MACH_JAZZ && SCSI=y select SCSI_SPI_ATTRS help This is the driver for the onboard SCSI host adapter of MIPS Magnum diff --git a/drivers/scsi/arcmsr/arcmsr.h b/drivers/scsi/arcmsr/arcmsr.h index 5d054d5c7..f2e587e66 100644 --- a/drivers/scsi/arcmsr/arcmsr.h +++ b/drivers/scsi/arcmsr/arcmsr.h @@ -77,9 +77,13 @@ struct device_attribute; #ifndef PCI_DEVICE_ID_ARECA_1203 #define PCI_DEVICE_ID_ARECA_1203 0x1203 #endif +#ifndef PCI_DEVICE_ID_ARECA_1883 +#define PCI_DEVICE_ID_ARECA_1883 0x1883 +#endif #ifndef PCI_DEVICE_ID_ARECA_1884 #define PCI_DEVICE_ID_ARECA_1884 0x1884 #endif +#define PCI_DEVICE_ID_ARECA_1886_0 0x1886 #define PCI_DEVICE_ID_ARECA_1886 0x188A #define ARCMSR_HOURS (1000 * 60 * 60 * 4) #define ARCMSR_MINUTES (1000 * 60 * 60) diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c index 9294a2c67..199b102f3 100644 --- a/drivers/scsi/arcmsr/arcmsr_hba.c +++ b/drivers/scsi/arcmsr/arcmsr_hba.c @@ -208,8 +208,12 @@ static struct pci_device_id arcmsr_device_id_table[] = { .driver_data = ACB_ADAPTER_TYPE_A}, {PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1880), .driver_data = ACB_ADAPTER_TYPE_C}, + {PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1883), + .driver_data = ACB_ADAPTER_TYPE_C}, {PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1884), .driver_data = ACB_ADAPTER_TYPE_E}, + {PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1886_0), + .driver_data = ACB_ADAPTER_TYPE_F}, {PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1886), .driver_data = ACB_ADAPTER_TYPE_F}, {0, 0}, /* Terminating entry */ @@ -4701,9 +4705,11 @@ static const char *arcmsr_info(struct Scsi_Host *host) case PCI_DEVICE_ID_ARECA_1680: case PCI_DEVICE_ID_ARECA_1681: case PCI_DEVICE_ID_ARECA_1880: + case PCI_DEVICE_ID_ARECA_1883: case PCI_DEVICE_ID_ARECA_1884: type = "SAS/SATA"; break; + case PCI_DEVICE_ID_ARECA_1886_0: case PCI_DEVICE_ID_ARECA_1886: type = "NVMe/SAS/SATA"; break; diff --git a/drivers/scsi/bfa/bfa.h b/drivers/scsi/bfa/bfa.h index 7bd2ba1ad..f30fe324e 100644 --- a/drivers/scsi/bfa/bfa.h +++ b/drivers/scsi/bfa/bfa.h @@ -20,7 +20,6 @@ struct bfa_s; typedef void (*bfa_isr_func_t) (struct bfa_s *bfa, struct bfi_msg_s *m); -typedef void (*bfa_cb_cbfn_status_t) (void *cbarg, bfa_status_t status); /* * Interrupt message handlers @@ -437,4 +436,12 @@ struct bfa_cb_pending_q_s { (__qe)->data = (__data); \ } while (0) +#define bfa_pending_q_init_status(__qe, __cbfn, __cbarg, __data) do { \ + bfa_q_qe_init(&((__qe)->hcb_qe.qe)); \ + (__qe)->hcb_qe.cbfn_status = (__cbfn); \ + (__qe)->hcb_qe.cbarg = (__cbarg); \ + (__qe)->hcb_qe.pre_rmv = BFA_TRUE; \ + (__qe)->data = (__data); \ +} while (0) + #endif /* __BFA_H__ */ diff --git a/drivers/scsi/bfa/bfa_core.c b/drivers/scsi/bfa/bfa_core.c index 6846ca8f7..3438d0b8b 100644 --- a/drivers/scsi/bfa/bfa_core.c +++ b/drivers/scsi/bfa/bfa_core.c @@ -1907,15 +1907,13 @@ bfa_comp_process(struct bfa_s *bfa, struct list_head *comp_q) struct list_head *qe; struct list_head *qen; struct bfa_cb_qe_s *hcb_qe; - bfa_cb_cbfn_status_t cbfn; list_for_each_safe(qe, qen, comp_q) { hcb_qe = (struct bfa_cb_qe_s *) qe; if (hcb_qe->pre_rmv) { /* qe is invalid after return, dequeue before cbfn() */ list_del(qe); - cbfn = (bfa_cb_cbfn_status_t)(hcb_qe->cbfn); - cbfn(hcb_qe->cbarg, hcb_qe->fw_status); + hcb_qe->cbfn_status(hcb_qe->cbarg, hcb_qe->fw_status); } else hcb_qe->cbfn(hcb_qe->cbarg, BFA_TRUE); } diff --git a/drivers/scsi/bfa/bfa_ioc.h b/drivers/scsi/bfa/bfa_ioc.h index 933a1c389..5e568d6d7 100644 --- a/drivers/scsi/bfa/bfa_ioc.h +++ b/drivers/scsi/bfa/bfa_ioc.h @@ -361,14 +361,18 @@ struct bfa_reqq_wait_s { void *cbarg; }; -typedef void (*bfa_cb_cbfn_t) (void *cbarg, bfa_boolean_t complete); +typedef void (*bfa_cb_cbfn_t) (void *cbarg, bfa_boolean_t complete); +typedef void (*bfa_cb_cbfn_status_t) (void *cbarg, bfa_status_t status); /* * Generic BFA callback element. */ struct bfa_cb_qe_s { struct list_head qe; - bfa_cb_cbfn_t cbfn; + union { + bfa_cb_cbfn_status_t cbfn_status; + bfa_cb_cbfn_t cbfn; + }; bfa_boolean_t once; bfa_boolean_t pre_rmv; /* set for stack based qe(s) */ bfa_status_t fw_status; /* to access fw status in comp proc */ diff --git a/drivers/scsi/bfa/bfad_bsg.c b/drivers/scsi/bfa/bfad_bsg.c index fc515424c..eb589f9e8 100644 --- a/drivers/scsi/bfa/bfad_bsg.c +++ b/drivers/scsi/bfa/bfad_bsg.c @@ -2135,8 +2135,7 @@ bfad_iocmd_fcport_get_stats(struct bfad_s *bfad, void *cmd) struct bfa_cb_pending_q_s cb_qe; init_completion(&fcomp.comp); - bfa_pending_q_init(&cb_qe, (bfa_cb_cbfn_t)bfad_hcb_comp, - &fcomp, &iocmd->stats); + bfa_pending_q_init_status(&cb_qe, bfad_hcb_comp, &fcomp, &iocmd->stats); spin_lock_irqsave(&bfad->bfad_lock, flags); iocmd->status = bfa_fcport_get_stats(&bfad->bfa, &cb_qe); spin_unlock_irqrestore(&bfad->bfad_lock, flags); @@ -2159,7 +2158,7 @@ bfad_iocmd_fcport_reset_stats(struct bfad_s *bfad, void *cmd) struct bfa_cb_pending_q_s cb_qe; init_completion(&fcomp.comp); - bfa_pending_q_init(&cb_qe, (bfa_cb_cbfn_t)bfad_hcb_comp, &fcomp, NULL); + bfa_pending_q_init_status(&cb_qe, bfad_hcb_comp, &fcomp, NULL); spin_lock_irqsave(&bfad->bfad_lock, flags); iocmd->status = bfa_fcport_clear_stats(&bfad->bfa, &cb_qe); @@ -2443,8 +2442,7 @@ bfad_iocmd_qos_get_stats(struct bfad_s *bfad, void *cmd) struct bfa_fcport_s *fcport = BFA_FCPORT_MOD(&bfad->bfa); init_completion(&fcomp.comp); - bfa_pending_q_init(&cb_qe, (bfa_cb_cbfn_t)bfad_hcb_comp, - &fcomp, &iocmd->stats); + bfa_pending_q_init_status(&cb_qe, bfad_hcb_comp, &fcomp, &iocmd->stats); spin_lock_irqsave(&bfad->bfad_lock, flags); WARN_ON(!bfa_ioc_get_fcmode(&bfad->bfa.ioc)); @@ -2474,8 +2472,7 @@ bfad_iocmd_qos_reset_stats(struct bfad_s *bfad, void *cmd) struct bfa_fcport_s *fcport = BFA_FCPORT_MOD(&bfad->bfa); init_completion(&fcomp.comp); - bfa_pending_q_init(&cb_qe, (bfa_cb_cbfn_t)bfad_hcb_comp, - &fcomp, NULL); + bfa_pending_q_init_status(&cb_qe, bfad_hcb_comp, &fcomp, NULL); spin_lock_irqsave(&bfad->bfad_lock, flags); WARN_ON(!bfa_ioc_get_fcmode(&bfad->bfa.ioc)); diff --git a/drivers/scsi/csiostor/csio_defs.h b/drivers/scsi/csiostor/csio_defs.h index c38017b4a..e50e93e7f 100644 --- a/drivers/scsi/csiostor/csio_defs.h +++ b/drivers/scsi/csiostor/csio_defs.h @@ -73,7 +73,21 @@ csio_list_deleted(struct list_head *list) #define csio_list_prev(elem) (((struct list_head *)(elem))->prev) /* State machine */ -typedef void (*csio_sm_state_t)(void *, uint32_t); +struct csio_lnode; + +/* State machine evets */ +enum csio_ln_ev { + CSIO_LNE_NONE = (uint32_t)0, + CSIO_LNE_LINKUP, + CSIO_LNE_FAB_INIT_DONE, + CSIO_LNE_LINK_DOWN, + CSIO_LNE_DOWN_LINK, + CSIO_LNE_LOGO, + CSIO_LNE_CLOSE, + CSIO_LNE_MAX_EVENT, +}; + +typedef void (*csio_sm_state_t)(struct csio_lnode *ln, enum csio_ln_ev evt); struct csio_sm { struct list_head sm_list; @@ -83,7 +97,7 @@ struct csio_sm { static inline void csio_set_state(void *smp, void *state) { - ((struct csio_sm *)smp)->sm_state = (csio_sm_state_t)state; + ((struct csio_sm *)smp)->sm_state = state; } static inline void diff --git a/drivers/scsi/csiostor/csio_lnode.c b/drivers/scsi/csiostor/csio_lnode.c index d5ac93897..5b3ffefae 100644 --- a/drivers/scsi/csiostor/csio_lnode.c +++ b/drivers/scsi/csiostor/csio_lnode.c @@ -1095,7 +1095,7 @@ csio_handle_link_down(struct csio_hw *hw, uint8_t portid, uint32_t fcfi, int csio_is_lnode_ready(struct csio_lnode *ln) { - return (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_ready)); + return (csio_get_state(ln) == csio_lns_ready); } /*****************************************************************************/ @@ -1366,15 +1366,15 @@ csio_free_fcfinfo(struct kref *kref) void csio_lnode_state_to_str(struct csio_lnode *ln, int8_t *str) { - if (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_uninit)) { + if (csio_get_state(ln) == csio_lns_uninit) { strcpy(str, "UNINIT"); return; } - if (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_ready)) { + if (csio_get_state(ln) == csio_lns_ready) { strcpy(str, "READY"); return; } - if (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_offline)) { + if (csio_get_state(ln) == csio_lns_offline) { strcpy(str, "OFFLINE"); return; } diff --git a/drivers/scsi/csiostor/csio_lnode.h b/drivers/scsi/csiostor/csio_lnode.h index 372a67d12..607698a0f 100644 --- a/drivers/scsi/csiostor/csio_lnode.h +++ b/drivers/scsi/csiostor/csio_lnode.h @@ -53,19 +53,6 @@ extern int csio_fcoe_rnodes; extern int csio_fdmi_enable; -/* State machine evets */ -enum csio_ln_ev { - CSIO_LNE_NONE = (uint32_t)0, - CSIO_LNE_LINKUP, - CSIO_LNE_FAB_INIT_DONE, - CSIO_LNE_LINK_DOWN, - CSIO_LNE_DOWN_LINK, - CSIO_LNE_LOGO, - CSIO_LNE_CLOSE, - CSIO_LNE_MAX_EVENT, -}; - - struct csio_fcf_info { struct list_head list; uint8_t priority; diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index bf0b3178f..4371d8b00 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -405,8 +405,8 @@ static char print_alua_state(unsigned char state) } } -static int alua_check_sense(struct scsi_device *sdev, - struct scsi_sense_hdr *sense_hdr) +static enum scsi_disposition alua_check_sense(struct scsi_device *sdev, + struct scsi_sense_hdr *sense_hdr) { switch (sense_hdr->sense_key) { case NOT_READY: diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c index caa685cfe..bd28ec6cf 100644 --- a/drivers/scsi/device_handler/scsi_dh_emc.c +++ b/drivers/scsi/device_handler/scsi_dh_emc.c @@ -280,8 +280,8 @@ static int send_trespass_cmd(struct scsi_device *sdev, return res; } -static int clariion_check_sense(struct scsi_device *sdev, - struct scsi_sense_hdr *sense_hdr) +static enum scsi_disposition clariion_check_sense(struct scsi_device *sdev, + struct scsi_sense_hdr *sense_hdr) { switch (sense_hdr->sense_key) { case NOT_READY: diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c index 85a71bafa..66652ab40 100644 --- a/drivers/scsi/device_handler/scsi_dh_rdac.c +++ b/drivers/scsi/device_handler/scsi_dh_rdac.c @@ -656,8 +656,8 @@ static blk_status_t rdac_prep_fn(struct scsi_device *sdev, struct request *req) return BLK_STS_OK; } -static int rdac_check_sense(struct scsi_device *sdev, - struct scsi_sense_hdr *sense_hdr) +static enum scsi_disposition rdac_check_sense(struct scsi_device *sdev, + struct scsi_sense_hdr *sense_hdr) { struct rdac_dh_data *h = sdev->handler_data; diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index a2d60ad2a..bbc5d6b9b 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -319,17 +319,16 @@ static void fcoe_ctlr_announce(struct fcoe_ctlr *fip) { struct fcoe_fcf *sel; struct fcoe_fcf *fcf; - unsigned long flags; mutex_lock(&fip->ctlr_mutex); - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); kfree_skb(fip->flogi_req); fip->flogi_req = NULL; list_for_each_entry(fcf, &fip->fcfs, list) fcf->flogi_sent = 0; - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); sel = fip->sel_fcf; if (sel && ether_addr_equal(sel->fcf_mac, fip->dest_addr)) @@ -700,7 +699,6 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport, { struct fc_frame *fp; struct fc_frame_header *fh; - unsigned long flags; u16 old_xid; u8 op; u8 mac[ETH_ALEN]; @@ -734,11 +732,11 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport, op = FIP_DT_FLOGI; if (fip->mode == FIP_MODE_VN2VN) break; - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); kfree_skb(fip->flogi_req); fip->flogi_req = skb; fip->flogi_req_send = 1; - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); schedule_work(&fip->timer_work); return -EINPROGRESS; case ELS_FDISC: @@ -1715,11 +1713,10 @@ static int fcoe_ctlr_flogi_send_locked(struct fcoe_ctlr *fip) static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip) { struct fcoe_fcf *fcf; - unsigned long flags; int error; mutex_lock(&fip->ctlr_mutex); - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); LIBFCOE_FIP_DBG(fip, "re-sending FLOGI - reselect\n"); fcf = fcoe_ctlr_select(fip); if (!fcf || fcf->flogi_sent) { @@ -1730,7 +1727,7 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip) fcoe_ctlr_solicit(fip, NULL); error = fcoe_ctlr_flogi_send_locked(fip); } - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); mutex_unlock(&fip->ctlr_mutex); return error; } @@ -1747,9 +1744,8 @@ static int fcoe_ctlr_flogi_retry(struct fcoe_ctlr *fip) static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip) { struct fcoe_fcf *fcf; - unsigned long flags; - spin_lock_irqsave(&fip->ctlr_lock, flags); + spin_lock_bh(&fip->ctlr_lock); fcf = fip->sel_fcf; if (!fcf || !fip->flogi_req_send) goto unlock; @@ -1776,7 +1772,7 @@ static void fcoe_ctlr_flogi_send(struct fcoe_ctlr *fip) } else /* XXX */ LIBFCOE_FIP_DBG(fip, "No FCF selected - defer send\n"); unlock: - spin_unlock_irqrestore(&fip->ctlr_lock, flags); + spin_unlock_bh(&fip->ctlr_lock); } /** diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 59eb6c296..297f2b412 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -334,12 +334,13 @@ static void scsi_host_dev_release(struct device *dev) if (shost->shost_state == SHOST_CREATED) { /* - * Free the shost_dev device name here if scsi_host_alloc() - * and scsi_host_put() have been called but neither + * Free the shost_dev device name and remove the proc host dir + * here if scsi_host_{alloc,put}() have been called but neither * scsi_host_add() nor scsi_host_remove() has been called. * This avoids that the memory allocated for the shost_dev - * name is leaked. + * name as well as the proc dir structure are leaked. */ + scsi_proc_hostdir_rm(shost->hostt); kfree(dev_name(&shost->shost_dev)); } diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c index b6d68d871..a4129e456 100644 --- a/drivers/scsi/isci/request.c +++ b/drivers/scsi/isci/request.c @@ -3398,7 +3398,7 @@ static enum sci_status isci_io_request_build(struct isci_host *ihost, return SCI_FAILURE; } - return SCI_SUCCESS; + return status; } static struct isci_request *isci_request_from_tag(struct isci_host *ihost, u16 tag) diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c index 7cfeb6886..61c12dde9 100644 --- a/drivers/scsi/libfc/fc_fcp.c +++ b/drivers/scsi/libfc/fc_fcp.c @@ -270,6 +270,11 @@ static int fc_fcp_send_abort(struct fc_fcp_pkt *fsp) if (!fsp->seq_ptr) return -EINVAL; + if (fsp->state & FC_SRB_ABORT_PENDING) { + FC_FCP_DBG(fsp, "abort already pending\n"); + return -EBUSY; + } + per_cpu_ptr(fsp->lp->stats, get_cpu())->FcpPktAborts++; put_cpu(); @@ -1681,7 +1686,7 @@ static void fc_fcp_rec_error(struct fc_fcp_pkt *fsp, struct fc_frame *fp) if (fsp->recov_retry++ < FC_MAX_RECOV_RETRY) fc_fcp_rec(fsp); else - fc_fcp_recovery(fsp, FC_ERROR); + fc_fcp_recovery(fsp, FC_TIMED_OUT); break; } fc_fcp_unlock_pkt(fsp); @@ -1700,11 +1705,12 @@ static void fc_fcp_recovery(struct fc_fcp_pkt *fsp, u8 code) fsp->status_code = code; fsp->cdb_status = 0; fsp->io_status = 0; - /* - * if this fails then we let the scsi command timer fire and - * scsi-ml escalate. - */ - fc_fcp_send_abort(fsp); + if (!fsp->cmd) + /* + * Only abort non-scsi commands; otherwise let the + * scsi command timer fire and scsi-ml escalate. + */ + fc_fcp_send_abort(fsp); } /** diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index 03bc472f3..cf69f831a 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -32,6 +32,7 @@ struct lpfc_sli2_slim; #define ELX_MODEL_NAME_SIZE 80 +#define ELX_FW_NAME_SIZE 84 #define LPFC_PCI_DEV_LP 0x1 #define LPFC_PCI_DEV_OC 0x2 diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 1bb3c96a0..5f2009327 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -13026,7 +13026,7 @@ out: int lpfc_sli4_request_firmware_update(struct lpfc_hba *phba, uint8_t fw_upgrade) { - uint8_t file_name[ELX_MODEL_NAME_SIZE]; + char file_name[ELX_FW_NAME_SIZE] = {0}; int ret; const struct firmware *fw; @@ -13035,7 +13035,7 @@ lpfc_sli4_request_firmware_update(struct lpfc_hba *phba, uint8_t fw_upgrade) LPFC_SLI_INTF_IF_TYPE_2) return -EPERM; - snprintf(file_name, ELX_MODEL_NAME_SIZE, "%s.grp", phba->ModelName); + scnprintf(file_name, sizeof(file_name), "%s.grp", phba->ModelName); if (fw_upgrade == INT_FW_UPGRADE) { ret = request_firmware_nowait(THIS_MODULE, FW_ACTION_HOTPLUG, diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c index 1e22364a3..d6287c58d 100644 --- a/drivers/scsi/lpfc/lpfc_nportdisc.c +++ b/drivers/scsi/lpfc/lpfc_nportdisc.c @@ -784,8 +784,10 @@ lpfc_rcv_padisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, /* Save the ELS cmd */ elsiocb->drvrTimeout = cmd; - lpfc_sli4_resume_rpi(ndlp, - lpfc_mbx_cmpl_resume_rpi, elsiocb); + if (lpfc_sli4_resume_rpi(ndlp, + lpfc_mbx_cmpl_resume_rpi, + elsiocb)) + kfree(elsiocb); goto out; } } diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c index deab8931a..59dc37925 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.c +++ b/drivers/scsi/lpfc/lpfc_nvmet.c @@ -1579,7 +1579,7 @@ lpfc_nvmet_setup_io_context(struct lpfc_hba *phba) wqe = &nvmewqe->wqe; /* Initialize WQE */ - memset(wqe, 0, sizeof(union lpfc_wqe)); + memset(wqe, 0, sizeof(*wqe)); ctx_buf->iocbq->context1 = NULL; spin_lock(&phba->sli4_hba.sgl_list_lock); diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 983eeb0e3..b4b87e5d8 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -1944,7 +1944,7 @@ out: * * Returns the number of SGEs added to the SGL. **/ -static int +static uint32_t lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc, struct sli4_sge *sgl, int datasegcnt, struct lpfc_io_buf *lpfc_cmd) @@ -1952,8 +1952,8 @@ lpfc_bg_setup_sgl(struct lpfc_hba *phba, struct scsi_cmnd *sc, struct scatterlist *sgde = NULL; /* s/g data entry */ struct sli4_sge_diseed *diseed = NULL; dma_addr_t physaddr; - int i = 0, num_sge = 0, status; - uint32_t reftag; + int i = 0, status; + uint32_t reftag, num_sge = 0; uint8_t txop, rxop; #ifdef CONFIG_SCSI_LPFC_DEBUG_FS uint32_t rc; @@ -2124,7 +2124,7 @@ out: * * Returns the number of SGEs added to the SGL. **/ -static int +static uint32_t lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, struct sli4_sge *sgl, int datacnt, int protcnt, struct lpfc_io_buf *lpfc_cmd) @@ -2148,8 +2148,8 @@ lpfc_bg_setup_sgl_prot(struct lpfc_hba *phba, struct scsi_cmnd *sc, uint32_t rc; #endif uint32_t checking = 1; - uint32_t dma_offset = 0; - int num_sge = 0, j = 2; + uint32_t dma_offset = 0, num_sge = 0; + int j = 2; struct sli4_hybrid_sgl *sgl_xtra = NULL; sgpe = scsi_prot_sglist(sc); diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 814ac2523..105d781d0 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -6357,7 +6357,9 @@ _base_wait_for_iocstate(struct MPT3SAS_ADAPTER *ioc, int timeout) return -EFAULT; } - issue_diag_reset: + return 0; + +issue_diag_reset: rc = _base_diag_reset(ioc); return rc; } diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c index ad17c2bea..d4c3f00fa 100644 --- a/drivers/scsi/myrb.c +++ b/drivers/scsi/myrb.c @@ -1803,9 +1803,9 @@ static ssize_t raid_state_show(struct device *dev, name = myrb_devstate_name(ldev_info->state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->state); } else { struct myrb_pdev_state *pdev_info = sdev->hostdata; @@ -1824,9 +1824,9 @@ static ssize_t raid_state_show(struct device *dev, else name = myrb_devstate_name(pdev_info->state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", pdev_info->state); } return ret; @@ -1914,11 +1914,11 @@ static ssize_t raid_level_show(struct device *dev, name = myrb_raidlevel_name(ldev_info->raid_level); if (!name) - return snprintf(buf, 32, "Invalid (%02X)\n", + return snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->state); - return snprintf(buf, 32, "%s\n", name); + return snprintf(buf, 64, "%s\n", name); } - return snprintf(buf, 32, "Physical Drive\n"); + return snprintf(buf, 64, "Physical Drive\n"); } static DEVICE_ATTR_RO(raid_level); @@ -1931,15 +1931,15 @@ static ssize_t rebuild_show(struct device *dev, unsigned char status; if (sdev->channel < myrb_logical_channel(sdev->host)) - return snprintf(buf, 32, "physical device - not rebuilding\n"); + return snprintf(buf, 64, "physical device - not rebuilding\n"); status = myrb_get_rbld_progress(cb, &rbld_buf); if (rbld_buf.ldev_num != sdev->id || status != MYRB_STATUS_SUCCESS) - return snprintf(buf, 32, "not rebuilding\n"); + return snprintf(buf, 64, "not rebuilding\n"); - return snprintf(buf, 32, "rebuilding block %u of %u\n", + return snprintf(buf, 64, "rebuilding block %u of %u\n", rbld_buf.ldev_size - rbld_buf.blocks_left, rbld_buf.ldev_size); } diff --git a/drivers/scsi/myrs.c b/drivers/scsi/myrs.c index e6a667896..857a73e85 100644 --- a/drivers/scsi/myrs.c +++ b/drivers/scsi/myrs.c @@ -950,9 +950,9 @@ static ssize_t raid_state_show(struct device *dev, name = myrs_devstate_name(ldev_info->dev_state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->dev_state); } else { struct myrs_pdev_info *pdev_info; @@ -961,9 +961,9 @@ static ssize_t raid_state_show(struct device *dev, pdev_info = sdev->hostdata; name = myrs_devstate_name(pdev_info->dev_state); if (name) - ret = snprintf(buf, 32, "%s\n", name); + ret = snprintf(buf, 64, "%s\n", name); else - ret = snprintf(buf, 32, "Invalid (%02X)\n", + ret = snprintf(buf, 64, "Invalid (%02X)\n", pdev_info->dev_state); } return ret; @@ -1069,13 +1069,13 @@ static ssize_t raid_level_show(struct device *dev, ldev_info = sdev->hostdata; name = myrs_raid_level_name(ldev_info->raid_level); if (!name) - return snprintf(buf, 32, "Invalid (%02X)\n", + return snprintf(buf, 64, "Invalid (%02X)\n", ldev_info->dev_state); } else name = myrs_raid_level_name(MYRS_RAID_PHYSICAL); - return snprintf(buf, 32, "%s\n", name); + return snprintf(buf, 64, "%s\n", name); } static DEVICE_ATTR_RO(raid_level); @@ -1089,7 +1089,7 @@ static ssize_t rebuild_show(struct device *dev, unsigned char status; if (sdev->channel < cs->ctlr_info->physchan_present) - return snprintf(buf, 32, "physical device - not rebuilding\n"); + return snprintf(buf, 64, "physical device - not rebuilding\n"); ldev_info = sdev->hostdata; ldev_num = ldev_info->ldev_num; @@ -1101,11 +1101,11 @@ static ssize_t rebuild_show(struct device *dev, return -EIO; } if (ldev_info->rbld_active) { - return snprintf(buf, 32, "rebuilding block %zu of %zu\n", + return snprintf(buf, 64, "rebuilding block %zu of %zu\n", (size_t)ldev_info->rbld_lba, (size_t)ldev_info->cfg_devsize); } else - return snprintf(buf, 32, "not rebuilding\n"); + return snprintf(buf, 64, "not rebuilding\n"); } static ssize_t rebuild_store(struct device *dev, @@ -1194,7 +1194,7 @@ static ssize_t consistency_check_show(struct device *dev, unsigned char status; if (sdev->channel < cs->ctlr_info->physchan_present) - return snprintf(buf, 32, "physical device - not checking\n"); + return snprintf(buf, 64, "physical device - not checking\n"); ldev_info = sdev->hostdata; if (!ldev_info) @@ -1202,11 +1202,11 @@ static ssize_t consistency_check_show(struct device *dev, ldev_num = ldev_info->ldev_num; status = myrs_get_ldev_info(cs, ldev_num, ldev_info); if (ldev_info->cc_active) - return snprintf(buf, 32, "checking block %zu of %zu\n", + return snprintf(buf, 64, "checking block %zu of %zu\n", (size_t)ldev_info->cc_lba, (size_t)ldev_info->cfg_devsize); else - return snprintf(buf, 32, "not checking\n"); + return snprintf(buf, 64, "not checking\n"); } static ssize_t consistency_check_store(struct device *dev, diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index f919da0bb..e23a93374 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -2689,7 +2689,13 @@ qla2x00_dev_loss_tmo_callbk(struct fc_rport *rport) return; if (unlikely(pci_channel_offline(fcport->vha->hw->pdev))) { - qla2x00_abort_all_cmds(fcport->vha, DID_NO_CONNECT << 16); + /* Will wait for wind down of adapter */ + ql_dbg(ql_dbg_aer, fcport->vha, 0x900c, + "%s pci offline detected (id %06x)\n", __func__, + fcport->d_id.b24); + qla_pci_set_eeh_busy(fcport->vha); + qla2x00_eh_wait_for_pending_commands(fcport->vha, fcport->d_id.b24, + 0, WAIT_TARGET); return; } } @@ -2711,7 +2717,11 @@ qla2x00_terminate_rport_io(struct fc_rport *rport) vha = fcport->vha; if (unlikely(pci_channel_offline(fcport->vha->hw->pdev))) { - qla2x00_abort_all_cmds(fcport->vha, DID_NO_CONNECT << 16); + /* Will wait for wind down of adapter */ + ql_dbg(ql_dbg_aer, fcport->vha, 0x900b, + "%s pci offline detected (id %06x)\n", __func__, + fcport->d_id.b24); + qla_pci_set_eeh_busy(vha); qla2x00_eh_wait_for_pending_commands(fcport->vha, fcport->d_id.b24, 0, WAIT_TARGET); return; diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 6645b69fc..b8628bceb 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -56,7 +56,7 @@ typedef struct { #include "qla_nvme.h" #define QLA2XXX_DRIVER_NAME "qla2xxx" #define QLA2XXX_APIDEV "ql2xapidev" -#define QLA2XXX_MANUFACTURER "QLogic Corporation" +#define QLA2XXX_MANUFACTURER "Marvell" /* * We have MAILBOX_REGISTER_COUNT sized arrays in a few places, diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index 20bbd69e3..d9ac17dba 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -1614,7 +1614,7 @@ qla2x00_hba_attributes(scsi_qla_host_t *vha, void *entries, eiter->type = cpu_to_be16(FDMI_HBA_MANUFACTURER); alen = scnprintf( eiter->a.manufacturer, sizeof(eiter->a.manufacturer), - "%s", "QLogic Corporation"); + "%s", QLA2XXX_MANUFACTURER); alen += FDMI_ATTR_ALIGNMENT(alen); alen += FDMI_ATTR_TYPELEN(eiter); eiter->len = cpu_to_be16(alen); diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index a8d2c0628..3d56f971c 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -2280,6 +2280,40 @@ exit: return rval; } +static void qla_enable_fce_trace(scsi_qla_host_t *vha) +{ + int rval; + struct qla_hw_data *ha = vha->hw; + + if (ha->fce) { + ha->flags.fce_enabled = 1; + memset(ha->fce, 0, fce_calc_size(ha->fce_bufs)); + rval = qla2x00_enable_fce_trace(vha, + ha->fce_dma, ha->fce_bufs, ha->fce_mb, &ha->fce_bufs); + + if (rval) { + ql_log(ql_log_warn, vha, 0x8033, + "Unable to reinitialize FCE (%d).\n", rval); + ha->flags.fce_enabled = 0; + } + } +} + +static void qla_enable_eft_trace(scsi_qla_host_t *vha) +{ + int rval; + struct qla_hw_data *ha = vha->hw; + + if (ha->eft) { + memset(ha->eft, 0, EFT_SIZE); + rval = qla2x00_enable_eft_trace(vha, ha->eft_dma, EFT_NUM_BUFFERS); + + if (rval) { + ql_log(ql_log_warn, vha, 0x8034, + "Unable to reinitialize EFT (%d).\n", rval); + } + } +} /* * qla2x00_initialize_adapter * Initialize board. @@ -3230,9 +3264,8 @@ qla24xx_chip_diag(scsi_qla_host_t *vha) } static void -qla2x00_init_fce_trace(scsi_qla_host_t *vha) +qla2x00_alloc_fce_trace(scsi_qla_host_t *vha) { - int rval; dma_addr_t tc_dma; void *tc; struct qla_hw_data *ha = vha->hw; @@ -3261,27 +3294,17 @@ qla2x00_init_fce_trace(scsi_qla_host_t *vha) return; } - rval = qla2x00_enable_fce_trace(vha, tc_dma, FCE_NUM_BUFFERS, - ha->fce_mb, &ha->fce_bufs); - if (rval) { - ql_log(ql_log_warn, vha, 0x00bf, - "Unable to initialize FCE (%d).\n", rval); - dma_free_coherent(&ha->pdev->dev, FCE_SIZE, tc, tc_dma); - return; - } - ql_dbg(ql_dbg_init, vha, 0x00c0, "Allocated (%d KB) for FCE...\n", FCE_SIZE / 1024); - ha->flags.fce_enabled = 1; ha->fce_dma = tc_dma; ha->fce = tc; + ha->fce_bufs = FCE_NUM_BUFFERS; } static void -qla2x00_init_eft_trace(scsi_qla_host_t *vha) +qla2x00_alloc_eft_trace(scsi_qla_host_t *vha) { - int rval; dma_addr_t tc_dma; void *tc; struct qla_hw_data *ha = vha->hw; @@ -3306,14 +3329,6 @@ qla2x00_init_eft_trace(scsi_qla_host_t *vha) return; } - rval = qla2x00_enable_eft_trace(vha, tc_dma, EFT_NUM_BUFFERS); - if (rval) { - ql_log(ql_log_warn, vha, 0x00c2, - "Unable to initialize EFT (%d).\n", rval); - dma_free_coherent(&ha->pdev->dev, EFT_SIZE, tc, tc_dma); - return; - } - ql_dbg(ql_dbg_init, vha, 0x00c3, "Allocated (%d KB) EFT ...\n", EFT_SIZE / 1024); @@ -3321,13 +3336,6 @@ qla2x00_init_eft_trace(scsi_qla_host_t *vha) ha->eft = tc; } -static void -qla2x00_alloc_offload_mem(scsi_qla_host_t *vha) -{ - qla2x00_init_fce_trace(vha); - qla2x00_init_eft_trace(vha); -} - void qla2x00_alloc_fw_dump(scsi_qla_host_t *vha) { @@ -3382,10 +3390,10 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha) if (ha->tgt.atio_ring) mq_size += ha->tgt.atio_q_length * sizeof(request_t); - qla2x00_init_fce_trace(vha); + qla2x00_alloc_fce_trace(vha); if (ha->fce) fce_size = sizeof(struct qla2xxx_fce_chain) + FCE_SIZE; - qla2x00_init_eft_trace(vha); + qla2x00_alloc_eft_trace(vha); if (ha->eft) eft_size = EFT_SIZE; } @@ -3784,7 +3792,6 @@ qla2x00_setup_chip(scsi_qla_host_t *vha) struct qla_hw_data *ha = vha->hw; struct device_reg_2xxx __iomem *reg = &ha->iobase->isp; unsigned long flags; - uint16_t fw_major_version; int done_once = 0; if (IS_P3P_TYPE(ha)) { @@ -3851,7 +3858,6 @@ execute_fw_with_lr: goto failed; enable_82xx_npiv: - fw_major_version = ha->fw_major_version; if (IS_P3P_TYPE(ha)) qla82xx_check_md_needed(vha); else @@ -3880,12 +3886,11 @@ enable_82xx_npiv: if (rval != QLA_SUCCESS) goto failed; - if (!fw_major_version && !(IS_P3P_TYPE(ha))) - qla2x00_alloc_offload_mem(vha); - if (ql2xallocfwdump && !(IS_P3P_TYPE(ha))) qla2x00_alloc_fw_dump(vha); + qla_enable_fce_trace(vha); + qla_enable_eft_trace(vha); } else { goto failed; } @@ -7012,7 +7017,6 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha) int qla2x00_abort_isp(scsi_qla_host_t *vha) { - int rval; uint8_t status = 0; struct qla_hw_data *ha = vha->hw; struct scsi_qla_host *vp; @@ -7100,31 +7104,7 @@ qla2x00_abort_isp(scsi_qla_host_t *vha) if (IS_QLA81XX(ha) || IS_QLA8031(ha)) qla2x00_get_fw_version(vha); - if (ha->fce) { - ha->flags.fce_enabled = 1; - memset(ha->fce, 0, - fce_calc_size(ha->fce_bufs)); - rval = qla2x00_enable_fce_trace(vha, - ha->fce_dma, ha->fce_bufs, ha->fce_mb, - &ha->fce_bufs); - if (rval) { - ql_log(ql_log_warn, vha, 0x8033, - "Unable to reinitialize FCE " - "(%d).\n", rval); - ha->flags.fce_enabled = 0; - } - } - if (ha->eft) { - memset(ha->eft, 0, EFT_SIZE); - rval = qla2x00_enable_eft_trace(vha, - ha->eft_dma, EFT_NUM_BUFFERS); - if (rval) { - ql_log(ql_log_warn, vha, 0x8034, - "Unable to reinitialize EFT " - "(%d).\n", rval); - } - } } else { /* failed the ISP abort */ vha->flags.online = 1; if (test_bit(ISP_ABORT_RETRY, &vha->dpc_flags)) { diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index fdb424501..d2433f162 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1038,6 +1038,16 @@ void qlt_free_session_done(struct work_struct *work) "%s: sess %p logout completed\n", __func__, sess); } + /* check for any straggling io left behind */ + if (!(sess->flags & FCF_FCP2_DEVICE) && + qla2x00_eh_wait_for_pending_commands(sess->vha, sess->d_id.b24, 0, WAIT_TARGET)) { + ql_log(ql_log_warn, vha, 0x3027, + "IO not return. Resetting.\n"); + set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags); + qla2xxx_wake_dpc(vha); + qla2x00_wait_for_chip_reset(vha); + } + if (sess->logo_ack_needed) { sess->logo_ack_needed = 0; qla24xx_async_notify_ack(vha, sess, diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 3d3d13912..ffc6f3031 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -60,14 +60,14 @@ static void scsi_eh_done(struct scsi_cmnd *scmd); #define HOST_RESET_SETTLE_TIME (10) static int scsi_eh_try_stu(struct scsi_cmnd *scmd); -static int scsi_try_to_abort_cmd(struct scsi_host_template *, - struct scsi_cmnd *); +static enum scsi_disposition scsi_try_to_abort_cmd(struct scsi_host_template *, + struct scsi_cmnd *); -void scsi_eh_wakeup(struct Scsi_Host *shost) +void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy) { lockdep_assert_held(shost->host_lock); - if (scsi_host_busy(shost) == shost->host_failed) { + if (busy == shost->host_failed) { trace_scsi_eh_wakeup(shost); wake_up_process(shost->ehandler); SCSI_LOG_ERROR_RECOVERY(5, shost_printk(KERN_INFO, shost, @@ -90,7 +90,7 @@ void scsi_schedule_eh(struct Scsi_Host *shost) if (scsi_host_set_state(shost, SHOST_RECOVERY) == 0 || scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY) == 0) { shost->host_eh_scheduled++; - scsi_eh_wakeup(shost); + scsi_eh_wakeup(shost, scsi_host_busy(shost)); } spin_unlock_irqrestore(shost->host_lock, flags); @@ -140,7 +140,7 @@ scmd_eh_abort_handler(struct work_struct *work) struct scsi_cmnd *scmd = container_of(work, struct scsi_cmnd, abort_work.work); struct scsi_device *sdev = scmd->device; - int rtn; + enum scsi_disposition rtn; if (scsi_host_eh_past_deadline(sdev->host)) { SCSI_LOG_ERROR_RECOVERY(3, @@ -241,11 +241,12 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head) { struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu); struct Scsi_Host *shost = scmd->device->host; + unsigned int busy = scsi_host_busy(shost); unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); shost->host_failed++; - scsi_eh_wakeup(shost); + scsi_eh_wakeup(shost, busy); spin_unlock_irqrestore(shost->host_lock, flags); } @@ -478,7 +479,7 @@ static void scsi_report_sense(struct scsi_device *sdev, * When a deferred error is detected the current command has * not been executed and needs retrying. */ -int scsi_check_sense(struct scsi_cmnd *scmd) +enum scsi_disposition scsi_check_sense(struct scsi_cmnd *scmd) { struct scsi_device *sdev = scmd->device; struct scsi_sense_hdr sshdr; @@ -492,7 +493,7 @@ int scsi_check_sense(struct scsi_cmnd *scmd) return NEEDS_RETRY; if (sdev->handler && sdev->handler->check_sense) { - int rc; + enum scsi_disposition rc; rc = sdev->handler->check_sense(sdev, &sshdr); if (rc != SCSI_RETURN_NOT_HANDLED) @@ -703,7 +704,7 @@ static void scsi_handle_queue_full(struct scsi_device *sdev) * don't allow for the possibility of retries here, and we are a lot * more restrictive about what we consider acceptable. */ -static int scsi_eh_completed_normally(struct scsi_cmnd *scmd) +static enum scsi_disposition scsi_eh_completed_normally(struct scsi_cmnd *scmd) { /* * first check the host byte, to see if there is anything in there @@ -784,10 +785,10 @@ static void scsi_eh_done(struct scsi_cmnd *scmd) * scsi_try_host_reset - ask host adapter to reset itself * @scmd: SCSI cmd to send host reset. */ -static int scsi_try_host_reset(struct scsi_cmnd *scmd) +static enum scsi_disposition scsi_try_host_reset(struct scsi_cmnd *scmd) { unsigned long flags; - int rtn; + enum scsi_disposition rtn; struct Scsi_Host *host = scmd->device->host; struct scsi_host_template *hostt = host->hostt; @@ -814,10 +815,10 @@ static int scsi_try_host_reset(struct scsi_cmnd *scmd) * scsi_try_bus_reset - ask host to perform a bus reset * @scmd: SCSI cmd to send bus reset. */ -static int scsi_try_bus_reset(struct scsi_cmnd *scmd) +static enum scsi_disposition scsi_try_bus_reset(struct scsi_cmnd *scmd) { unsigned long flags; - int rtn; + enum scsi_disposition rtn; struct Scsi_Host *host = scmd->device->host; struct scsi_host_template *hostt = host->hostt; @@ -856,10 +857,10 @@ static void __scsi_report_device_reset(struct scsi_device *sdev, void *data) * timer on it, and set the host back to a consistent state prior to * returning. */ -static int scsi_try_target_reset(struct scsi_cmnd *scmd) +static enum scsi_disposition scsi_try_target_reset(struct scsi_cmnd *scmd) { unsigned long flags; - int rtn; + enum scsi_disposition rtn; struct Scsi_Host *host = scmd->device->host; struct scsi_host_template *hostt = host->hostt; @@ -887,9 +888,9 @@ static int scsi_try_target_reset(struct scsi_cmnd *scmd) * timer on it, and set the host back to a consistent state prior to * returning. */ -static int scsi_try_bus_device_reset(struct scsi_cmnd *scmd) +static enum scsi_disposition scsi_try_bus_device_reset(struct scsi_cmnd *scmd) { - int rtn; + enum scsi_disposition rtn; struct scsi_host_template *hostt = scmd->device->host->hostt; if (!hostt->eh_device_reset_handler) @@ -918,8 +919,8 @@ static int scsi_try_bus_device_reset(struct scsi_cmnd *scmd) * if the device is temporarily unavailable (eg due to a * link down on FibreChannel) */ -static int scsi_try_to_abort_cmd(struct scsi_host_template *hostt, - struct scsi_cmnd *scmd) +static enum scsi_disposition +scsi_try_to_abort_cmd(struct scsi_host_template *hostt, struct scsi_cmnd *scmd) { if (!hostt->eh_abort_handler) return FAILED; @@ -1052,8 +1053,8 @@ EXPORT_SYMBOL(scsi_eh_restore_cmnd); * Return value: * SUCCESS or FAILED or NEEDS_RETRY */ -static int scsi_send_eh_cmnd(struct scsi_cmnd *scmd, unsigned char *cmnd, - int cmnd_size, int timeout, unsigned sense_bytes) +static enum scsi_disposition scsi_send_eh_cmnd(struct scsi_cmnd *scmd, + unsigned char *cmnd, int cmnd_size, int timeout, unsigned sense_bytes) { struct scsi_device *sdev = scmd->device; struct Scsi_Host *shost = sdev->host; @@ -1161,12 +1162,13 @@ retry: * that we obtain it on our own. This function will *not* return until * the command either times out, or it completes. */ -static int scsi_request_sense(struct scsi_cmnd *scmd) +static enum scsi_disposition scsi_request_sense(struct scsi_cmnd *scmd) { return scsi_send_eh_cmnd(scmd, NULL, 0, scmd->device->eh_timeout, ~0); } -static int scsi_eh_action(struct scsi_cmnd *scmd, int rtn) +static enum scsi_disposition +scsi_eh_action(struct scsi_cmnd *scmd, enum scsi_disposition rtn) { if (!blk_rq_is_passthrough(scmd->request)) { struct scsi_driver *sdrv = scsi_cmd_to_driver(scmd); @@ -1219,7 +1221,7 @@ int scsi_eh_get_sense(struct list_head *work_q, { struct scsi_cmnd *scmd, *next; struct Scsi_Host *shost; - int rtn; + enum scsi_disposition rtn; /* * If SCSI_EH_ABORT_SCHEDULED has been set, it is timeout IO, @@ -1297,7 +1299,8 @@ EXPORT_SYMBOL_GPL(scsi_eh_get_sense); static int scsi_eh_tur(struct scsi_cmnd *scmd) { static unsigned char tur_command[6] = {TEST_UNIT_READY, 0, 0, 0, 0, 0}; - int retry_cnt = 1, rtn; + int retry_cnt = 1; + enum scsi_disposition rtn; retry_tur: rtn = scsi_send_eh_cmnd(scmd, tur_command, 6, @@ -1385,7 +1388,8 @@ static int scsi_eh_try_stu(struct scsi_cmnd *scmd) static unsigned char stu_command[6] = {START_STOP, 0, 0, 0, 1, 0}; if (scmd->device->allow_restart) { - int i, rtn = NEEDS_RETRY; + int i; + enum scsi_disposition rtn = NEEDS_RETRY; for (i = 0; rtn == NEEDS_RETRY && i < 2; i++) rtn = scsi_send_eh_cmnd(scmd, stu_command, 6, scmd->device->request_queue->rq_timeout, 0); @@ -1479,7 +1483,7 @@ static int scsi_eh_bus_device_reset(struct Scsi_Host *shost, { struct scsi_cmnd *scmd, *bdr_scmd, *next; struct scsi_device *sdev; - int rtn; + enum scsi_disposition rtn; shost_for_each_device(sdev, shost) { if (scsi_host_eh_past_deadline(shost)) { @@ -1546,7 +1550,7 @@ static int scsi_eh_target_reset(struct Scsi_Host *shost, while (!list_empty(&tmp_list)) { struct scsi_cmnd *next, *scmd; - int rtn; + enum scsi_disposition rtn; unsigned int id; if (scsi_host_eh_past_deadline(shost)) { @@ -1604,7 +1608,7 @@ static int scsi_eh_bus_reset(struct Scsi_Host *shost, struct scsi_cmnd *scmd, *chan_scmd, *next; LIST_HEAD(check_list); unsigned int channel; - int rtn; + enum scsi_disposition rtn; /* * we really want to loop over the various channels, and do this on @@ -1675,7 +1679,7 @@ static int scsi_eh_host_reset(struct Scsi_Host *shost, { struct scsi_cmnd *scmd, *next; LIST_HEAD(check_list); - int rtn; + enum scsi_disposition rtn; if (!list_empty(work_q)) { scmd = list_entry(work_q->next, @@ -1781,9 +1785,9 @@ check_type: * doesn't require the error handler read (i.e. we don't need to * abort/reset), this function should return SUCCESS. */ -int scsi_decide_disposition(struct scsi_cmnd *scmd) +enum scsi_disposition scsi_decide_disposition(struct scsi_cmnd *scmd) { - int rtn; + enum scsi_disposition rtn; /* * if the device is offline, then we clearly just pass the result back @@ -2339,7 +2343,8 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg) struct Scsi_Host *shost = dev->host; struct request *rq; unsigned long flags; - int error = 0, rtn, val; + int error = 0, val; + enum scsi_disposition rtn; if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO)) return -EACCES; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 99b900315..14dec86ff 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -310,9 +310,11 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd) rcu_read_lock(); __clear_bit(SCMD_STATE_INFLIGHT, &cmd->state); if (unlikely(scsi_host_in_recovery(shost))) { + unsigned int busy = scsi_host_busy(shost); + spin_lock_irqsave(shost->host_lock, flags); if (shost->host_failed || shost->host_eh_scheduled) - scsi_eh_wakeup(shost); + scsi_eh_wakeup(shost, busy); spin_unlock_irqrestore(shost->host_lock, flags); } rcu_read_unlock(); @@ -1426,7 +1428,7 @@ static bool scsi_mq_lld_busy(struct request_queue *q) static void scsi_softirq_done(struct request *rq) { struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq); - int disposition; + enum scsi_disposition disposition; INIT_LIST_HEAD(&cmd->eh_entry); diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h index 180636d54..1183dbed6 100644 --- a/drivers/scsi/scsi_priv.h +++ b/drivers/scsi/scsi_priv.h @@ -73,8 +73,8 @@ extern void scsi_exit_devinfo(void); extern void scmd_eh_abort_handler(struct work_struct *work); extern enum blk_eh_timer_return scsi_times_out(struct request *req); extern int scsi_error_handler(void *host); -extern int scsi_decide_disposition(struct scsi_cmnd *cmd); -extern void scsi_eh_wakeup(struct Scsi_Host *shost); +extern enum scsi_disposition scsi_decide_disposition(struct scsi_cmnd *cmd); +extern void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy); extern void scsi_eh_scmd_add(struct scsi_cmnd *); void scsi_eh_ready_devs(struct Scsi_Host *shost, struct list_head *work_q, diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 58f66176b..f2dfd9853 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3026,8 +3026,13 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp) } if (sdkp->device->type == TYPE_ZBC) { - /* Host-managed */ + /* + * Host-managed: Per ZBC and ZAC specifications, writes in + * sequential write required zones of host-managed devices must + * be aligned to the device physical block size. + */ blk_queue_set_zoned(sdkp->disk, BLK_ZONED_HM); + blk_queue_zone_write_granularity(q, sdkp->physical_block_size); } else { sdkp->zoned = (buffer[8] >> 4) & 3; if (sdkp->zoned == 1) { diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c index 1d2bc181d..69f6178f2 100644 --- a/drivers/slimbus/core.c +++ b/drivers/slimbus/core.c @@ -438,8 +438,8 @@ static int slim_device_alloc_laddr(struct slim_device *sbdev, if (ret < 0) goto err; } else if (report_present) { - ret = ida_simple_get(&ctrl->laddr_ida, - 0, SLIM_LA_MANAGER - 1, GFP_KERNEL); + ret = ida_alloc_max(&ctrl->laddr_ida, + SLIM_LA_MANAGER - 1, GFP_KERNEL); if (ret < 0) goto err; diff --git a/drivers/soc/fsl/dpio/dpio-service.c b/drivers/soc/fsl/dpio/dpio-service.c index 779c319a4..6cdd2c517 100644 --- a/drivers/soc/fsl/dpio/dpio-service.c +++ b/drivers/soc/fsl/dpio/dpio-service.c @@ -485,7 +485,7 @@ int dpaa2_io_service_enqueue_multiple_desc_fq(struct dpaa2_io *d, struct qbman_eq_desc *ed; int i, ret; - ed = kcalloc(sizeof(struct qbman_eq_desc), 32, GFP_KERNEL); + ed = kcalloc(32, sizeof(struct qbman_eq_desc), GFP_KERNEL); if (!ed) return -ENOMEM; diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index feb974706..7abc9b6a0 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -991,7 +991,7 @@ struct qman_portal { /* linked-list of CSCN handlers. */ struct list_head cgr_cbs; /* list lock */ - spinlock_t cgr_lock; + raw_spinlock_t cgr_lock; struct work_struct congestion_work; struct work_struct mr_work; char irqname[MAX_IRQNAME]; @@ -1281,7 +1281,7 @@ static int qman_create_portal(struct qman_portal *portal, /* if the given mask is NULL, assume all CGRs can be seen */ qman_cgrs_fill(&portal->cgrs[0]); INIT_LIST_HEAD(&portal->cgr_cbs); - spin_lock_init(&portal->cgr_lock); + raw_spin_lock_init(&portal->cgr_lock); INIT_WORK(&portal->congestion_work, qm_congestion_task); INIT_WORK(&portal->mr_work, qm_mr_process_task); portal->bits = 0; @@ -1456,11 +1456,14 @@ static void qm_congestion_task(struct work_struct *work) union qm_mc_result *mcr; struct qman_cgr *cgr; - spin_lock(&p->cgr_lock); + /* + * FIXME: QM_MCR_TIMEOUT is 10ms, which is too long for a raw spinlock! + */ + raw_spin_lock_irq(&p->cgr_lock); qm_mc_start(&p->p); qm_mc_commit(&p->p, QM_MCC_VERB_QUERYCONGESTION); if (!qm_mc_result_timeout(&p->p, &mcr)) { - spin_unlock(&p->cgr_lock); + raw_spin_unlock_irq(&p->cgr_lock); dev_crit(p->config->dev, "QUERYCONGESTION timeout\n"); qman_p_irqsource_add(p, QM_PIRQ_CSCI); return; @@ -1476,7 +1479,7 @@ static void qm_congestion_task(struct work_struct *work) list_for_each_entry(cgr, &p->cgr_cbs, node) if (cgr->cb && qman_cgrs_get(&c, cgr->cgrid)) cgr->cb(p, cgr, qman_cgrs_get(&rr, cgr->cgrid)); - spin_unlock(&p->cgr_lock); + raw_spin_unlock_irq(&p->cgr_lock); qman_p_irqsource_add(p, QM_PIRQ_CSCI); } @@ -2440,7 +2443,7 @@ int qman_create_cgr(struct qman_cgr *cgr, u32 flags, preempt_enable(); cgr->chan = p->config->channel; - spin_lock(&p->cgr_lock); + raw_spin_lock_irq(&p->cgr_lock); if (opts) { struct qm_mcc_initcgr local_opts = *opts; @@ -2477,19 +2480,14 @@ int qman_create_cgr(struct qman_cgr *cgr, u32 flags, qman_cgrs_get(&p->cgrs[1], cgr->cgrid)) cgr->cb(p, cgr, 1); out: - spin_unlock(&p->cgr_lock); + raw_spin_unlock_irq(&p->cgr_lock); put_affine_portal(); return ret; } EXPORT_SYMBOL(qman_create_cgr); -int qman_delete_cgr(struct qman_cgr *cgr) +static struct qman_portal *qman_cgr_get_affine_portal(struct qman_cgr *cgr) { - unsigned long irqflags; - struct qm_mcr_querycgr cgr_state; - struct qm_mcc_initcgr local_opts; - int ret = 0; - struct qman_cgr *i; struct qman_portal *p = get_affine_portal(); if (cgr->chan != p->config->channel) { @@ -2497,12 +2495,27 @@ int qman_delete_cgr(struct qman_cgr *cgr) dev_err(p->config->dev, "CGR not owned by current portal"); dev_dbg(p->config->dev, " create 0x%x, delete 0x%x\n", cgr->chan, p->config->channel); - - ret = -EINVAL; - goto put_portal; + put_affine_portal(); + return NULL; } + + return p; +} + +int qman_delete_cgr(struct qman_cgr *cgr) +{ + unsigned long irqflags; + struct qm_mcr_querycgr cgr_state; + struct qm_mcc_initcgr local_opts; + int ret = 0; + struct qman_cgr *i; + struct qman_portal *p = qman_cgr_get_affine_portal(cgr); + + if (!p) + return -EINVAL; + memset(&local_opts, 0, sizeof(struct qm_mcc_initcgr)); - spin_lock_irqsave(&p->cgr_lock, irqflags); + raw_spin_lock_irqsave(&p->cgr_lock, irqflags); list_del(&cgr->node); /* * If there are no other CGR objects for this CGRID in the list, @@ -2527,8 +2540,7 @@ int qman_delete_cgr(struct qman_cgr *cgr) /* add back to the list */ list_add(&cgr->node, &p->cgr_cbs); release_lock: - spin_unlock_irqrestore(&p->cgr_lock, irqflags); -put_portal: + raw_spin_unlock_irqrestore(&p->cgr_lock, irqflags); put_affine_portal(); return ret; } @@ -2559,6 +2571,54 @@ void qman_delete_cgr_safe(struct qman_cgr *cgr) } EXPORT_SYMBOL(qman_delete_cgr_safe); +static int qman_update_cgr(struct qman_cgr *cgr, struct qm_mcc_initcgr *opts) +{ + int ret; + unsigned long irqflags; + struct qman_portal *p = qman_cgr_get_affine_portal(cgr); + + if (!p) + return -EINVAL; + + raw_spin_lock_irqsave(&p->cgr_lock, irqflags); + ret = qm_modify_cgr(cgr, 0, opts); + raw_spin_unlock_irqrestore(&p->cgr_lock, irqflags); + put_affine_portal(); + return ret; +} + +struct update_cgr_params { + struct qman_cgr *cgr; + struct qm_mcc_initcgr *opts; + int ret; +}; + +static void qman_update_cgr_smp_call(void *p) +{ + struct update_cgr_params *params = p; + + params->ret = qman_update_cgr(params->cgr, params->opts); +} + +int qman_update_cgr_safe(struct qman_cgr *cgr, struct qm_mcc_initcgr *opts) +{ + struct update_cgr_params params = { + .cgr = cgr, + .opts = opts, + }; + + preempt_disable(); + if (qman_cgr_cpus[cgr->cgrid] != smp_processor_id()) + smp_call_function_single(qman_cgr_cpus[cgr->cgrid], + qman_update_cgr_smp_call, ¶ms, + true); + else + params.ret = qman_update_cgr(cgr, opts); + preempt_enable(); + return params.ret; +} +EXPORT_SYMBOL(qman_update_cgr_safe); + /* Cleanup FQs */ static int _qm_mr_consume_and_match_verb(struct qm_portal *p, int v) diff --git a/drivers/soc/qcom/rpmhpd.c b/drivers/soc/qcom/rpmhpd.c index 436ec7912..d228e7717 100644 --- a/drivers/soc/qcom/rpmhpd.c +++ b/drivers/soc/qcom/rpmhpd.c @@ -261,12 +261,15 @@ static int rpmhpd_aggregate_corner(struct rpmhpd *pd, unsigned int corner) unsigned int active_corner, sleep_corner; unsigned int this_active_corner = 0, this_sleep_corner = 0; unsigned int peer_active_corner = 0, peer_sleep_corner = 0; + unsigned int peer_enabled_corner; to_active_sleep(pd, corner, &this_active_corner, &this_sleep_corner); - if (peer && peer->enabled) - to_active_sleep(peer, peer->corner, &peer_active_corner, + if (peer && peer->enabled) { + peer_enabled_corner = max(peer->corner, peer->enable_corner); + to_active_sleep(peer, peer_enabled_corner, &peer_active_corner, &peer_sleep_corner); + } active_corner = max(this_active_corner, peer_active_corner); diff --git a/drivers/soc/renesas/r8a77980-sysc.c b/drivers/soc/renesas/r8a77980-sysc.c index 39ca84a67..621e411fc 100644 --- a/drivers/soc/renesas/r8a77980-sysc.c +++ b/drivers/soc/renesas/r8a77980-sysc.c @@ -25,7 +25,8 @@ static const struct rcar_sysc_area r8a77980_areas[] __initconst = { PD_CPU_NOCR }, { "ca53-cpu3", 0x200, 3, R8A77980_PD_CA53_CPU3, R8A77980_PD_CA53_SCU, PD_CPU_NOCR }, - { "cr7", 0x240, 0, R8A77980_PD_CR7, R8A77980_PD_ALWAYS_ON }, + { "cr7", 0x240, 0, R8A77980_PD_CR7, R8A77980_PD_ALWAYS_ON, + PD_CPU_NOCR }, { "a3ir", 0x180, 0, R8A77980_PD_A3IR, R8A77980_PD_ALWAYS_ON }, { "a2ir0", 0x400, 0, R8A77980_PD_A2IR0, R8A77980_PD_A3IR }, { "a2ir1", 0x400, 1, R8A77980_PD_A2IR1, R8A77980_PD_A3IR }, diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 2c734ea07..898658ab1 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -19,7 +19,7 @@ #include <linux/platform_device.h> #include <linux/slab.h> #include <linux/spi/spi.h> -#include <linux/spi/spi-mem.h> +#include <linux/mtd/spi-nor.h> #include <linux/sysfs.h> #include <linux/types.h> #include "spi-bcm-qspi.h" @@ -1048,7 +1048,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem, /* non-aligned and very short transfers are handled by MSPI */ if (!IS_ALIGNED((uintptr_t)addr, 4) || !IS_ALIGNED((uintptr_t)buf, 4) || - len < 4) + len < 4 || op->cmd.opcode == SPINOR_OP_RDSFDP) mspi_read = true; if (!has_bspi(qspi) || mspi_read) diff --git a/drivers/spi/spi-hisi-sfc-v3xx.c b/drivers/spi/spi-hisi-sfc-v3xx.c index 4650b483a..e0c3ad73c 100644 --- a/drivers/spi/spi-hisi-sfc-v3xx.c +++ b/drivers/spi/spi-hisi-sfc-v3xx.c @@ -365,6 +365,11 @@ static const struct spi_controller_mem_ops hisi_sfc_v3xx_mem_ops = { static irqreturn_t hisi_sfc_v3xx_isr(int irq, void *data) { struct hisi_sfc_v3xx_host *host = data; + u32 reg; + + reg = readl(host->regbase + HISI_SFC_V3XX_INT_STAT); + if (!reg) + return IRQ_NONE; hisi_sfc_v3xx_disable_int(host); diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 92a09dfb9..0bcf4a281 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -566,17 +566,19 @@ static irqreturn_t mtk_spi_interrupt(int irq, void *dev_id) mdata->xfer_len = min(MTK_SPI_MAX_FIFO_SIZE, len); mtk_spi_setup_packet(master); - cnt = mdata->xfer_len / 4; - iowrite32_rep(mdata->base + SPI_TX_DATA_REG, - trans->tx_buf + mdata->num_xfered, cnt); + if (trans->tx_buf) { + cnt = mdata->xfer_len / 4; + iowrite32_rep(mdata->base + SPI_TX_DATA_REG, + trans->tx_buf + mdata->num_xfered, cnt); - remainder = mdata->xfer_len % 4; - if (remainder > 0) { - reg_val = 0; - memcpy(®_val, - trans->tx_buf + (cnt * 4) + mdata->num_xfered, - remainder); - writel(reg_val, mdata->base + SPI_TX_DATA_REG); + remainder = mdata->xfer_len % 4; + if (remainder > 0) { + reg_val = 0; + memcpy(®_val, + trans->tx_buf + (cnt * 4) + mdata->num_xfered, + remainder); + writel(reg_val, mdata->base + SPI_TX_DATA_REG); + } } mtk_spi_enable_transfer(master); diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c index d8ee363fb..4200b12fc 100644 --- a/drivers/spi/spi-ppc4xx.c +++ b/drivers/spi/spi-ppc4xx.c @@ -166,10 +166,8 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t) int scr; u8 cdm = 0; u32 speed; - u8 bits_per_word; /* Start with the generic configuration for this device. */ - bits_per_word = spi->bits_per_word; speed = spi->max_speed_hz; /* @@ -177,9 +175,6 @@ static int spi_ppc4xx_setupxfer(struct spi_device *spi, struct spi_transfer *t) * the transfer to overwrite the generic configuration with zeros. */ if (t) { - if (t->bits_per_word) - bits_per_word = t->bits_per_word; - if (t->speed_hz) speed = min(t->speed_hz, spi->max_speed_hz); } diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c index 35d303782..12fd02f92 100644 --- a/drivers/spi/spi-sh-msiof.c +++ b/drivers/spi/spi-sh-msiof.c @@ -137,14 +137,14 @@ struct sh_msiof_spi_priv { /* SIFCTR */ #define SIFCTR_TFWM_MASK GENMASK(31, 29) /* Transmit FIFO Watermark */ -#define SIFCTR_TFWM_64 (0 << 29) /* Transfer Request when 64 empty stages */ -#define SIFCTR_TFWM_32 (1 << 29) /* Transfer Request when 32 empty stages */ -#define SIFCTR_TFWM_24 (2 << 29) /* Transfer Request when 24 empty stages */ -#define SIFCTR_TFWM_16 (3 << 29) /* Transfer Request when 16 empty stages */ -#define SIFCTR_TFWM_12 (4 << 29) /* Transfer Request when 12 empty stages */ -#define SIFCTR_TFWM_8 (5 << 29) /* Transfer Request when 8 empty stages */ -#define SIFCTR_TFWM_4 (6 << 29) /* Transfer Request when 4 empty stages */ -#define SIFCTR_TFWM_1 (7 << 29) /* Transfer Request when 1 empty stage */ +#define SIFCTR_TFWM_64 (0UL << 29) /* Transfer Request when 64 empty stages */ +#define SIFCTR_TFWM_32 (1UL << 29) /* Transfer Request when 32 empty stages */ +#define SIFCTR_TFWM_24 (2UL << 29) /* Transfer Request when 24 empty stages */ +#define SIFCTR_TFWM_16 (3UL << 29) /* Transfer Request when 16 empty stages */ +#define SIFCTR_TFWM_12 (4UL << 29) /* Transfer Request when 12 empty stages */ +#define SIFCTR_TFWM_8 (5UL << 29) /* Transfer Request when 8 empty stages */ +#define SIFCTR_TFWM_4 (6UL << 29) /* Transfer Request when 4 empty stages */ +#define SIFCTR_TFWM_1 (7UL << 29) /* Transfer Request when 1 empty stage */ #define SIFCTR_TFUA_MASK GENMASK(26, 20) /* Transmit FIFO Usable Area */ #define SIFCTR_TFUA_SHIFT 20 #define SIFCTR_TFUA(i) ((i) << SIFCTR_TFUA_SHIFT) diff --git a/drivers/staging/comedi/drivers/comedi_test.c b/drivers/staging/comedi/drivers/comedi_test.c index cbc225eb1..bea9a3adf 100644 --- a/drivers/staging/comedi/drivers/comedi_test.c +++ b/drivers/staging/comedi/drivers/comedi_test.c @@ -87,6 +87,8 @@ struct waveform_private { struct comedi_device *dev; /* parent comedi device */ u64 ao_last_scan_time; /* time of previous AO scan in usec */ unsigned int ao_scan_period; /* AO scan period in usec */ + bool ai_timer_enable:1; /* should AI timer be running? */ + bool ao_timer_enable:1; /* should AO timer be running? */ unsigned short ao_loopbacks[N_CHANS]; }; @@ -236,8 +238,12 @@ static void waveform_ai_timer(struct timer_list *t) time_increment = devpriv->ai_convert_time - now; else time_increment = 1; - mod_timer(&devpriv->ai_timer, - jiffies + usecs_to_jiffies(time_increment)); + spin_lock(&dev->spinlock); + if (devpriv->ai_timer_enable) { + mod_timer(&devpriv->ai_timer, + jiffies + usecs_to_jiffies(time_increment)); + } + spin_unlock(&dev->spinlock); } overrun: @@ -393,9 +399,12 @@ static int waveform_ai_cmd(struct comedi_device *dev, * Seem to need an extra jiffy here, otherwise timer expires slightly * early! */ + spin_lock_bh(&dev->spinlock); + devpriv->ai_timer_enable = true; devpriv->ai_timer.expires = jiffies + usecs_to_jiffies(devpriv->ai_convert_period) + 1; add_timer(&devpriv->ai_timer); + spin_unlock_bh(&dev->spinlock); return 0; } @@ -404,6 +413,9 @@ static int waveform_ai_cancel(struct comedi_device *dev, { struct waveform_private *devpriv = dev->private; + spin_lock_bh(&dev->spinlock); + devpriv->ai_timer_enable = false; + spin_unlock_bh(&dev->spinlock); if (in_softirq()) { /* Assume we were called from the timer routine itself. */ del_timer(&devpriv->ai_timer); @@ -495,8 +507,12 @@ static void waveform_ao_timer(struct timer_list *t) unsigned int time_inc = devpriv->ao_last_scan_time + devpriv->ao_scan_period - now; - mod_timer(&devpriv->ao_timer, - jiffies + usecs_to_jiffies(time_inc)); + spin_lock(&dev->spinlock); + if (devpriv->ao_timer_enable) { + mod_timer(&devpriv->ao_timer, + jiffies + usecs_to_jiffies(time_inc)); + } + spin_unlock(&dev->spinlock); } underrun: @@ -517,9 +533,12 @@ static int waveform_ao_inttrig_start(struct comedi_device *dev, async->inttrig = NULL; devpriv->ao_last_scan_time = ktime_to_us(ktime_get()); + spin_lock_bh(&dev->spinlock); + devpriv->ao_timer_enable = true; devpriv->ao_timer.expires = jiffies + usecs_to_jiffies(devpriv->ao_scan_period); add_timer(&devpriv->ao_timer); + spin_unlock_bh(&dev->spinlock); return 1; } @@ -604,6 +623,9 @@ static int waveform_ao_cancel(struct comedi_device *dev, struct waveform_private *devpriv = dev->private; s->async->inttrig = NULL; + spin_lock_bh(&dev->spinlock); + devpriv->ao_timer_enable = false; + spin_unlock_bh(&dev->spinlock); if (in_softirq()) { /* Assume we were called from the timer routine itself. */ del_timer(&devpriv->ao_timer); diff --git a/drivers/staging/comedi/drivers/vmk80xx.c b/drivers/staging/comedi/drivers/vmk80xx.c index ccc65cfc5..51b814e44 100644 --- a/drivers/staging/comedi/drivers/vmk80xx.c +++ b/drivers/staging/comedi/drivers/vmk80xx.c @@ -642,33 +642,22 @@ static int vmk80xx_find_usb_endpoints(struct comedi_device *dev) struct vmk80xx_private *devpriv = dev->private; struct usb_interface *intf = comedi_to_usb_interface(dev); struct usb_host_interface *iface_desc = intf->cur_altsetting; - struct usb_endpoint_descriptor *ep_desc; - int i; - - if (iface_desc->desc.bNumEndpoints != 2) - return -ENODEV; - - for (i = 0; i < iface_desc->desc.bNumEndpoints; i++) { - ep_desc = &iface_desc->endpoint[i].desc; - - if (usb_endpoint_is_int_in(ep_desc) || - usb_endpoint_is_bulk_in(ep_desc)) { - if (!devpriv->ep_rx) - devpriv->ep_rx = ep_desc; - continue; - } + struct usb_endpoint_descriptor *ep_rx_desc, *ep_tx_desc; + int ret; - if (usb_endpoint_is_int_out(ep_desc) || - usb_endpoint_is_bulk_out(ep_desc)) { - if (!devpriv->ep_tx) - devpriv->ep_tx = ep_desc; - continue; - } - } + if (devpriv->model == VMK8061_MODEL) + ret = usb_find_common_endpoints(iface_desc, &ep_rx_desc, + &ep_tx_desc, NULL, NULL); + else + ret = usb_find_common_endpoints(iface_desc, NULL, NULL, + &ep_rx_desc, &ep_tx_desc); - if (!devpriv->ep_rx || !devpriv->ep_tx) + if (ret) return -ENODEV; + devpriv->ep_rx = ep_rx_desc; + devpriv->ep_tx = ep_tx_desc; + if (!usb_endpoint_maxp(devpriv->ep_rx) || !usb_endpoint_maxp(devpriv->ep_tx)) return -EINVAL; diff --git a/drivers/staging/greybus/light.c b/drivers/staging/greybus/light.c index d2672b65c..e59bb2723 100644 --- a/drivers/staging/greybus/light.c +++ b/drivers/staging/greybus/light.c @@ -100,15 +100,15 @@ static struct led_classdev *get_channel_cdev(struct gb_channel *channel) static struct gb_channel *get_channel_from_mode(struct gb_light *light, u32 mode) { - struct gb_channel *channel = NULL; + struct gb_channel *channel; int i; for (i = 0; i < light->channels_count; i++) { channel = &light->channels[i]; - if (channel && channel->mode == mode) - break; + if (channel->mode == mode) + return channel; } - return channel; + return NULL; } static int __gb_lights_flash_intensity_set(struct gb_channel *channel, diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c index dba78896e..7d91d64b2 100644 --- a/drivers/staging/iio/impedance-analyzer/ad5933.c +++ b/drivers/staging/iio/impedance-analyzer/ad5933.c @@ -625,7 +625,7 @@ static void ad5933_work(struct work_struct *work) struct ad5933_state, work.work); struct iio_dev *indio_dev = i2c_get_clientdata(st->client); __be16 buf[2]; - int val[2]; + u16 val[2]; unsigned char status; int ret; diff --git a/drivers/staging/media/imx/imx-media-csc-scaler.c b/drivers/staging/media/imx/imx-media-csc-scaler.c index 63a020450..939843b89 100644 --- a/drivers/staging/media/imx/imx-media-csc-scaler.c +++ b/drivers/staging/media/imx/imx-media-csc-scaler.c @@ -803,6 +803,7 @@ static int ipu_csc_scaler_release(struct file *file) dev_dbg(priv->dev, "Releasing instance %p\n", ctx); + v4l2_ctrl_handler_free(&ctx->ctrl_hdlr); v4l2_m2m_ctx_release(ctx->fh.m2m_ctx); v4l2_fh_del(&ctx->fh); v4l2_fh_exit(&ctx->fh); diff --git a/drivers/staging/media/ipu3/ipu3-v4l2.c b/drivers/staging/media/ipu3/ipu3-v4l2.c index 103f84466..371117b51 100644 --- a/drivers/staging/media/ipu3/ipu3-v4l2.c +++ b/drivers/staging/media/ipu3/ipu3-v4l2.c @@ -1063,6 +1063,11 @@ static int imgu_v4l2_subdev_register(struct imgu_device *imgu, struct imgu_media_pipe *imgu_pipe = &imgu->imgu_pipe[pipe]; /* Initialize subdev media entity */ + imgu_sd->subdev.entity.ops = &imgu_media_ops; + for (i = 0; i < IMGU_NODE_NUM; i++) { + imgu_sd->subdev_pads[i].flags = imgu_pipe->nodes[i].output ? + MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE; + } r = media_entity_pads_init(&imgu_sd->subdev.entity, IMGU_NODE_NUM, imgu_sd->subdev_pads); if (r) { @@ -1070,11 +1075,6 @@ static int imgu_v4l2_subdev_register(struct imgu_device *imgu, "failed initialize subdev media entity (%d)\n", r); return r; } - imgu_sd->subdev.entity.ops = &imgu_media_ops; - for (i = 0; i < IMGU_NODE_NUM; i++) { - imgu_sd->subdev_pads[i].flags = imgu_pipe->nodes[i].output ? - MEDIA_PAD_FL_SINK : MEDIA_PAD_FL_SOURCE; - } /* Initialize subdev */ v4l2_subdev_init(&imgu_sd->subdev, &imgu_subdev_ops); @@ -1169,15 +1169,15 @@ static int imgu_v4l2_node_setup(struct imgu_device *imgu, unsigned int pipe, } /* Initialize media entities */ + node->vdev_pad.flags = node->output ? + MEDIA_PAD_FL_SOURCE : MEDIA_PAD_FL_SINK; + vdev->entity.ops = NULL; r = media_entity_pads_init(&vdev->entity, 1, &node->vdev_pad); if (r) { dev_err(dev, "failed initialize media entity (%d)\n", r); mutex_destroy(&node->lock); return r; } - node->vdev_pad.flags = node->output ? - MEDIA_PAD_FL_SOURCE : MEDIA_PAD_FL_SINK; - vdev->entity.ops = NULL; /* Initialize vbq */ vbq->type = node->vdev_fmt.type; diff --git a/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c b/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c index d697ea55a..3306ec5bb 100644 --- a/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c +++ b/drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c @@ -940,8 +940,9 @@ static int create_component(struct vchiq_mmal_instance *instance, /* build component create message */ m.h.type = MMAL_MSG_TYPE_COMPONENT_CREATE; m.u.component_create.client_component = component->client_component; - strncpy(m.u.component_create.name, name, - sizeof(m.u.component_create.name)); + strscpy_pad(m.u.component_create.name, name, + sizeof(m.u.component_create.name)); + m.u.component_create.pid = 0; ret = send_synchronous_mmal_msg(instance, &m, sizeof(m.u.component_create), diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 9aeedcff7..daa4d06ce 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -150,7 +150,6 @@ int transport_lookup_tmr_lun(struct se_cmd *se_cmd) struct se_session *se_sess = se_cmd->se_sess; struct se_node_acl *nacl = se_sess->se_node_acl; struct se_tmr_req *se_tmr = se_cmd->se_tmr_req; - unsigned long flags; rcu_read_lock(); deve = target_nacl_find_deve(nacl, se_cmd->orig_fe_lun); @@ -181,10 +180,6 @@ out_unlock: se_cmd->se_dev = rcu_dereference_raw(se_lun->lun_se_dev); se_tmr->tmr_dev = rcu_dereference_raw(se_lun->lun_se_dev); - spin_lock_irqsave(&se_tmr->tmr_dev->se_tmr_lock, flags); - list_add_tail(&se_tmr->tmr_list, &se_tmr->tmr_dev->dev_tmr_list); - spin_unlock_irqrestore(&se_tmr->tmr_dev->se_tmr_lock, flags); - return 0; } EXPORT_SYMBOL(transport_lookup_tmr_lun); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 2e97937f0..8d294b658 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -3436,6 +3436,10 @@ int transport_generic_handle_tmr( unsigned long flags; bool aborted = false; + spin_lock_irqsave(&cmd->se_dev->se_tmr_lock, flags); + list_add_tail(&cmd->se_tmr_req->tmr_list, &cmd->se_dev->dev_tmr_list); + spin_unlock_irqrestore(&cmd->se_dev->se_tmr_lock, flags); + spin_lock_irqsave(&cmd->t_state_lock, flags); if (cmd->transport_state & CMD_T_ABORTED) { aborted = true; diff --git a/drivers/tee/optee/device.c b/drivers/tee/optee/device.c index 3cb39f02f..26683697c 100644 --- a/drivers/tee/optee/device.c +++ b/drivers/tee/optee/device.c @@ -90,13 +90,14 @@ static int optee_register_device(const uuid_t *device_uuid, u32 func) if (rc) { pr_err("device registration failed, err: %d\n", rc); put_device(&optee_device->dev); + return rc; } if (func == PTA_CMD_GET_DEVICES_SUPP) device_create_file(&optee_device->dev, &dev_attr_need_supplicant); - return rc; + return 0; } static int __optee_enumerate_devices(u32 func) diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 22e5c4de3..b13a944eb 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -2402,22 +2402,29 @@ void tb_switch_unconfigure_link(struct tb_switch *sw) { struct tb_port *up, *down; - if (sw->is_unplugged) - return; if (!tb_route(sw) || tb_switch_is_icm(sw)) return; + /* + * Unconfigure downstream port so that wake-on-connect can be + * configured after router unplug. No need to unconfigure upstream port + * since its router is unplugged. + */ up = tb_upstream_port(sw); - if (tb_switch_is_usb4(up->sw)) - usb4_port_unconfigure(up); - else - tb_lc_unconfigure_port(up); - down = up->remote; if (tb_switch_is_usb4(down->sw)) usb4_port_unconfigure(down); else tb_lc_unconfigure_port(down); + + if (sw->is_unplugged) + return; + + up = tb_upstream_port(sw); + if (tb_switch_is_usb4(up->sw)) + usb4_port_unconfigure(up); + else + tb_lc_unconfigure_port(up); } static int tb_switch_port_hotplug_enable(struct tb_switch *sw) @@ -2631,7 +2638,26 @@ static int tb_switch_set_wake(struct tb_switch *sw, unsigned int flags) return tb_lc_set_wake(sw, flags); } -int tb_switch_resume(struct tb_switch *sw) +static void tb_switch_check_wakes(struct tb_switch *sw) +{ + if (device_may_wakeup(&sw->dev)) { + if (tb_switch_is_usb4(sw)) + usb4_switch_check_wakes(sw); + } +} + +/** + * tb_switch_resume() - Resume a switch after sleep + * @sw: Switch to resume + * @runtime: Is this resume from runtime suspend or system sleep + * + * Resumes and re-enumerates router (and all its children), if still plugged + * after suspend. Don't enumerate device router whose UID was changed during + * suspend. If this is resume from system sleep, notifies PM core about the + * wakes occurred during suspend. Disables all wakes, except USB4 wake of + * upstream port for USB4 routers that shall be always enabled. + */ +int tb_switch_resume(struct tb_switch *sw, bool runtime) { struct tb_port *port; int err; @@ -2676,6 +2702,9 @@ int tb_switch_resume(struct tb_switch *sw) if (err) return err; + if (!runtime) + tb_switch_check_wakes(sw); + /* Disable wakes */ tb_switch_set_wake(sw, 0); @@ -2702,7 +2731,8 @@ int tb_switch_resume(struct tb_switch *sw) */ if (tb_port_unlock(port)) tb_port_warn(port, "failed to unlock port\n"); - if (port->remote && tb_switch_resume(port->remote->sw)) { + if (port->remote && + tb_switch_resume(port->remote->sw, runtime)) { tb_port_warn(port, "lost during suspend, disconnecting\n"); tb_sw_set_unplugged(port->remote->sw); diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index a56ea540a..26a788479 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -1385,7 +1385,7 @@ static int tb_resume_noirq(struct tb *tb) /* remove any pci devices the firmware might have setup */ tb_switch_reset(tb->root_switch); - tb_switch_resume(tb->root_switch); + tb_switch_resume(tb->root_switch, false); tb_free_invalid_tunnels(tb); tb_free_unplugged_children(tb->root_switch); tb_restore_children(tb->root_switch); @@ -1488,7 +1488,7 @@ static int tb_runtime_resume(struct tb *tb) struct tb_tunnel *tunnel, *n; mutex_lock(&tb->lock); - tb_switch_resume(tb->root_switch); + tb_switch_resume(tb->root_switch, true); tb_free_invalid_tunnels(tb); tb_restore_children(tb->root_switch); list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list) diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 266f3bf8f..f3df5655f 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -653,7 +653,7 @@ int tb_switch_configure(struct tb_switch *sw); int tb_switch_add(struct tb_switch *sw); void tb_switch_remove(struct tb_switch *sw); void tb_switch_suspend(struct tb_switch *sw, bool runtime); -int tb_switch_resume(struct tb_switch *sw); +int tb_switch_resume(struct tb_switch *sw, bool runtime); int tb_switch_reset(struct tb_switch *sw); void tb_sw_set_unplugged(struct tb_switch *sw); struct tb_port *tb_switch_find_port(struct tb_switch *sw, @@ -957,6 +957,7 @@ static inline struct tb_retimer *tb_to_retimer(struct device *dev) return NULL; } +void usb4_switch_check_wakes(struct tb_switch *sw); int usb4_switch_setup(struct tb_switch *sw); int usb4_switch_read_uid(struct tb_switch *sw, u64 *uid); int usb4_switch_drom_read(struct tb_switch *sw, unsigned int address, void *buf, diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 5b45c45e7..78c895abb 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -197,15 +197,18 @@ static int usb4_switch_op(struct tb_switch *sw, u16 opcode, u8 *status) return 0; } -static void usb4_switch_check_wakes(struct tb_switch *sw) +/** + * usb4_switch_check_wakes() - Check for wakes and notify PM core about them + * @sw: Router whose wakes to check + * + * Checks wakes occurred during suspend and notify the PM core about them. + */ +void usb4_switch_check_wakes(struct tb_switch *sw) { struct tb_port *port; bool wakeup = false; u32 val; - if (!device_may_wakeup(&sw->dev)) - return; - if (tb_route(sw)) { if (tb_sw_read(sw, &val, TB_CFG_SWITCH, ROUTER_CS_6, 1)) return; @@ -270,8 +273,6 @@ int usb4_switch_setup(struct tb_switch *sw) u32 val = 0; int ret; - usb4_switch_check_wakes(sw); - if (!tb_route(sw)) return 0; diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c index cf0fb650a..4886cad0f 100644 --- a/drivers/tty/hvc/hvc_xen.c +++ b/drivers/tty/hvc/hvc_xen.c @@ -43,6 +43,7 @@ struct xencons_info { int irq; int vtermno; grant_ref_t gntref; + spinlock_t ring_lock; }; static LIST_HEAD(xenconsoles); @@ -89,12 +90,15 @@ static int __write_console(struct xencons_info *xencons, XENCONS_RING_IDX cons, prod; struct xencons_interface *intf = xencons->intf; int sent = 0; + unsigned long flags; + spin_lock_irqsave(&xencons->ring_lock, flags); cons = intf->out_cons; prod = intf->out_prod; mb(); /* update queue values before going on */ if ((prod - cons) > sizeof(intf->out)) { + spin_unlock_irqrestore(&xencons->ring_lock, flags); pr_err_once("xencons: Illegal ring page indices"); return -EINVAL; } @@ -104,6 +108,7 @@ static int __write_console(struct xencons_info *xencons, wmb(); /* write ring before updating pointer */ intf->out_prod = prod; + spin_unlock_irqrestore(&xencons->ring_lock, flags); if (sent) notify_daemon(xencons); @@ -146,16 +151,19 @@ static int domU_read_console(uint32_t vtermno, char *buf, int len) int recv = 0; struct xencons_info *xencons = vtermno_to_xencons(vtermno); unsigned int eoiflag = 0; + unsigned long flags; if (xencons == NULL) return -EINVAL; intf = xencons->intf; + spin_lock_irqsave(&xencons->ring_lock, flags); cons = intf->in_cons; prod = intf->in_prod; mb(); /* get pointers before reading ring */ if ((prod - cons) > sizeof(intf->in)) { + spin_unlock_irqrestore(&xencons->ring_lock, flags); pr_err_once("xencons: Illegal ring page indices"); return -EINVAL; } @@ -179,10 +187,13 @@ static int domU_read_console(uint32_t vtermno, char *buf, int len) xencons->out_cons = intf->out_cons; xencons->out_cons_same = 0; } + if (!recv && xencons->out_cons_same++ > 1) { + eoiflag = XEN_EOI_FLAG_SPURIOUS; + } + spin_unlock_irqrestore(&xencons->ring_lock, flags); + if (recv) { notify_daemon(xencons); - } else if (xencons->out_cons_same++ > 1) { - eoiflag = XEN_EOI_FLAG_SPURIOUS; } xen_irq_lateeoi(xencons->irq, eoiflag); @@ -239,6 +250,7 @@ static int xen_hvm_console_init(void) info = kzalloc(sizeof(struct xencons_info), GFP_KERNEL); if (!info) return -ENOMEM; + spin_lock_init(&info->ring_lock); } else if (info->intf != NULL) { /* already configured */ return 0; @@ -275,6 +287,7 @@ err: static int xencons_info_pv_init(struct xencons_info *info, int vtermno) { + spin_lock_init(&info->ring_lock); info->evtchn = xen_start_info->console.domU.evtchn; /* GFN == MFN for PV guest */ info->intf = gfn_to_virt(xen_start_info->console.domU.mfn); @@ -325,6 +338,7 @@ static int xen_initial_domain_console_init(void) info = kzalloc(sizeof(struct xencons_info), GFP_KERNEL); if (!info) return -ENOMEM; + spin_lock_init(&info->ring_lock); } info->irq = bind_virq_to_irq(VIRQ_CONSOLE, 0, false); @@ -485,6 +499,7 @@ static int xencons_probe(struct xenbus_device *dev, info = kzalloc(sizeof(struct xencons_info), GFP_KERNEL); if (!info) return -ENOMEM; + spin_lock_init(&info->ring_lock); dev_set_drvdata(&dev->dev, info); info->xbdev = dev; info->vtermno = xenbus_devid_to_vtermno(devid); diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index fa4952968..c20f69a4c 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2661,6 +2661,9 @@ static int gsmld_open(struct tty_struct *tty) { struct gsm_mux *gsm; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (tty->ops->write == NULL) return -EINVAL; diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 43f2eed6d..355ee338d 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -1026,6 +1026,7 @@ int serial8250_register_8250_port(struct uart_8250_port *up) uart->port.throttle = up->port.throttle; uart->port.unthrottle = up->port.unthrottle; uart->port.rs485_config = up->port.rs485_config; + uart->port.rs485_supported = up->port.rs485_supported; uart->port.rs485 = up->port.rs485; uart->rs485_start_tx = up->rs485_start_tx; uart->rs485_stop_tx = up->rs485_stop_tx; diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 5c2adf140..7c28d2752 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -123,6 +123,7 @@ struct exar8250; struct exar8250_platform { int (*rs485_config)(struct uart_port *, struct serial_rs485 *); + const struct serial_rs485 *rs485_supported; int (*register_gpio)(struct pci_dev *, struct uart_8250_port *); }; @@ -423,9 +424,14 @@ static int generic_rs485_config(struct uart_port *port, return 0; } +static const struct serial_rs485 generic_rs485_supported = { + .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND, +}; + static const struct exar8250_platform exar8250_default_platform = { .register_gpio = xr17v35x_register_gpio, .rs485_config = generic_rs485_config, + .rs485_supported = &generic_rs485_supported, }; static int iot2040_rs485_config(struct uart_port *port, @@ -461,6 +467,11 @@ static int iot2040_rs485_config(struct uart_port *port, return generic_rs485_config(port, rs485); } +static const struct serial_rs485 iot2040_rs485_supported = { + .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | + SER_RS485_RX_DURING_TX | SER_RS485_TERMINATE_BUS, +}; + static const struct property_entry iot2040_gpio_properties[] = { PROPERTY_ENTRY_U32("exar,first-pin", 10), PROPERTY_ENTRY_U32("ngpios", 1), @@ -485,6 +496,7 @@ static int iot2040_register_gpio(struct pci_dev *pcidev, static const struct exar8250_platform iot2040_platform = { .rs485_config = iot2040_rs485_config, + .rs485_supported = &iot2040_rs485_supported, .register_gpio = iot2040_register_gpio, }; @@ -522,6 +534,7 @@ pci_xr17v35x_setup(struct exar8250 *priv, struct pci_dev *pcidev, port->port.uartclk = baud * 16; port->port.rs485_config = platform->rs485_config; + port->port.rs485_supported = platform->rs485_supported; /* * Setup the UART clock for the devices on expansion slot to @@ -675,6 +688,7 @@ static void exar_pci_remove(struct pci_dev *pcidev) for (i = 0; i < priv->nr; i++) serial8250_unregister_port(priv->line[i]); + /* Ensure that every init quirk is properly torn down */ if (priv->board->exit) priv->board->exit(pcidev); } @@ -689,10 +703,6 @@ static int __maybe_unused exar_suspend(struct device *dev) if (priv->line[i] >= 0) serial8250_suspend_port(priv->line[i]); - /* Ensure that every init quirk is properly torn down */ - if (priv->board->exit) - priv->board->exit(pcidev); - return 0; } diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 8b49ac485..6098e87a3 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1358,9 +1358,6 @@ static void autoconfig_irq(struct uart_8250_port *up) inb_p(ICP); } - if (uart_console(port)) - console_lock(); - /* forget possible initially masked and pending IRQ */ probe_irq_off(probe_irq_on()); save_mcr = serial8250_in_MCR(up); @@ -1391,9 +1388,6 @@ static void autoconfig_irq(struct uart_8250_port *up) if (port->flags & UPF_FOURPORT) outb_p(save_ICP, ICP); - if (uart_console(port)) - console_unlock(); - port->irq = (irq > 0) ? irq : 0; } diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 28f22e586..bd30ae975 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -343,6 +343,7 @@ config SERIAL_MAX310X depends on SPI_MASTER select SERIAL_CORE select REGMAP_SPI if SPI_MASTER + select REGMAP_I2C if I2C help This selects support for an advanced UART from Maxim (Dallas). Supported ICs are MAX3107, MAX3108, MAX3109, MAX14830. diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 227fb2d32..b16ad6db1 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2178,9 +2178,12 @@ lpuart32_set_termios(struct uart_port *port, struct ktermios *termios, UARTCTRL); lpuart32_serial_setbrg(sport, baud); - lpuart32_write(&sport->port, modem, UARTMODIR); - lpuart32_write(&sport->port, ctrl, UARTCTRL); + /* disable CTS before enabling UARTCTRL_TE to avoid pending idle preamble */ + lpuart32_write(&sport->port, modem & ~UARTMODIR_TXCTSE, UARTMODIR); /* restore control register */ + lpuart32_write(&sport->port, ctrl, UARTCTRL); + /* re-enable the CTS if needed */ + lpuart32_write(&sport->port, modem, UARTMODIR); if (old && sport->lpuart_dma_rx_use) { if (!lpuart_start_rx_dma(sport)) diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index 5bf8dd619..363b68555 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -14,9 +14,10 @@ #include <linux/delay.h> #include <linux/device.h> #include <linux/gpio/driver.h> +#include <linux/i2c.h> #include <linux/module.h> -#include <linux/of.h> -#include <linux/of_device.h> +#include <linux/mod_devicetable.h> +#include <linux/property.h> #include <linux/regmap.h> #include <linux/serial_core.h> #include <linux/serial.h> @@ -72,7 +73,8 @@ #define MAX310X_GLOBALCMD_REG MAX310X_REG_1F /* Global Command (WO) */ /* Extended registers */ -#define MAX310X_REVID_EXTREG MAX310X_REG_05 /* Revision ID */ +#define MAX310X_SPI_REVID_EXTREG MAX310X_REG_05 /* Revision ID */ +#define MAX310X_I2C_REVID_EXTREG (0x25) /* Revision ID */ /* IRQ register bits */ #define MAX310X_IRQ_LSR_BIT (1 << 0) /* LSR interrupt */ @@ -235,6 +237,14 @@ #define MAX310x_REV_MASK (0xf8) #define MAX310X_WRITE_BIT 0x80 +/* Port startup definitions */ +#define MAX310X_PORT_STARTUP_WAIT_RETRIES 20 /* Number of retries */ +#define MAX310X_PORT_STARTUP_WAIT_DELAY_MS 10 /* Delay between retries */ + +/* Crystal-related definitions */ +#define MAX310X_XTAL_WAIT_RETRIES 20 /* Number of retries */ +#define MAX310X_XTAL_WAIT_DELAY_MS 10 /* Delay between retries */ + /* MAX3107 specific */ #define MAX3107_REV_ID (0xa0) @@ -245,7 +255,17 @@ #define MAX14830_BRGCFG_CLKDIS_BIT (1 << 6) /* Clock Disable */ #define MAX14830_REV_ID (0xb0) +struct max310x_if_cfg { + int (*extended_reg_enable)(struct device *dev, bool enable); + + unsigned int rev_id_reg; +}; + struct max310x_devtype { + struct { + unsigned short min; + unsigned short max; + } slave_addr; char name[9]; int nr; u8 mode1; @@ -258,16 +278,16 @@ struct max310x_one { struct work_struct tx_work; struct work_struct md_work; struct work_struct rs_work; + struct regmap *regmap; - u8 wr_header; - u8 rd_header; u8 rx_buf[MAX310X_FIFO_SIZE]; }; #define to_max310x_port(_port) \ container_of(_port, struct max310x_one, port) struct max310x_port { - struct max310x_devtype *devtype; + const struct max310x_devtype *devtype; + const struct max310x_if_cfg *if_cfg; struct regmap *regmap; struct clk *clk; #ifdef CONFIG_GPIOLIB @@ -289,26 +309,26 @@ static DECLARE_BITMAP(max310x_lines, MAX310X_UART_NRMAX); static u8 max310x_port_read(struct uart_port *port, u8 reg) { - struct max310x_port *s = dev_get_drvdata(port->dev); + struct max310x_one *one = to_max310x_port(port); unsigned int val = 0; - regmap_read(s->regmap, port->iobase + reg, &val); + regmap_read(one->regmap, reg, &val); return val; } static void max310x_port_write(struct uart_port *port, u8 reg, u8 val) { - struct max310x_port *s = dev_get_drvdata(port->dev); + struct max310x_one *one = to_max310x_port(port); - regmap_write(s->regmap, port->iobase + reg, val); + regmap_write(one->regmap, reg, val); } static void max310x_port_update(struct uart_port *port, u8 reg, u8 mask, u8 val) { - struct max310x_port *s = dev_get_drvdata(port->dev); + struct max310x_one *one = to_max310x_port(port); - regmap_update_bits(s->regmap, port->iobase + reg, mask, val); + regmap_update_bits(one->regmap, reg, mask, val); } static int max3107_detect(struct device *dev) @@ -357,13 +377,12 @@ static int max3109_detect(struct device *dev) unsigned int val = 0; int ret; - ret = regmap_write(s->regmap, MAX310X_GLOBALCMD_REG, - MAX310X_EXTREG_ENBL); + ret = s->if_cfg->extended_reg_enable(dev, true); if (ret) return ret; - regmap_read(s->regmap, MAX310X_REVID_EXTREG, &val); - regmap_write(s->regmap, MAX310X_GLOBALCMD_REG, MAX310X_EXTREG_DSBL); + regmap_read(s->regmap, s->if_cfg->rev_id_reg, &val); + s->if_cfg->extended_reg_enable(dev, false); if (((val & MAX310x_REV_MASK) != MAX3109_REV_ID)) { dev_err(dev, "%s ID 0x%02x does not match\n", s->devtype->name, val); @@ -388,13 +407,12 @@ static int max14830_detect(struct device *dev) unsigned int val = 0; int ret; - ret = regmap_write(s->regmap, MAX310X_GLOBALCMD_REG, - MAX310X_EXTREG_ENBL); + ret = s->if_cfg->extended_reg_enable(dev, true); if (ret) return ret; - regmap_read(s->regmap, MAX310X_REVID_EXTREG, &val); - regmap_write(s->regmap, MAX310X_GLOBALCMD_REG, MAX310X_EXTREG_DSBL); + regmap_read(s->regmap, s->if_cfg->rev_id_reg, &val); + s->if_cfg->extended_reg_enable(dev, false); if (((val & MAX310x_REV_MASK) != MAX14830_REV_ID)) { dev_err(dev, "%s ID 0x%02x does not match\n", s->devtype->name, val); @@ -419,6 +437,10 @@ static const struct max310x_devtype max3107_devtype = { .mode1 = MAX310X_MODE1_AUTOSLEEP_BIT | MAX310X_MODE1_IRQSEL_BIT, .detect = max3107_detect, .power = max310x_power, + .slave_addr = { + .min = 0x2c, + .max = 0x2f, + }, }; static const struct max310x_devtype max3108_devtype = { @@ -427,6 +449,10 @@ static const struct max310x_devtype max3108_devtype = { .mode1 = MAX310X_MODE1_AUTOSLEEP_BIT, .detect = max3108_detect, .power = max310x_power, + .slave_addr = { + .min = 0x60, + .max = 0x6f, + }, }; static const struct max310x_devtype max3109_devtype = { @@ -435,6 +461,10 @@ static const struct max310x_devtype max3109_devtype = { .mode1 = MAX310X_MODE1_AUTOSLEEP_BIT, .detect = max3109_detect, .power = max310x_power, + .slave_addr = { + .min = 0x60, + .max = 0x6f, + }, }; static const struct max310x_devtype max14830_devtype = { @@ -443,11 +473,15 @@ static const struct max310x_devtype max14830_devtype = { .mode1 = MAX310X_MODE1_IRQSEL_BIT, .detect = max14830_detect, .power = max14830_power, + .slave_addr = { + .min = 0x60, + .max = 0x6f, + }, }; static bool max310x_reg_writeable(struct device *dev, unsigned int reg) { - switch (reg & 0x1f) { + switch (reg) { case MAX310X_IRQSTS_REG: case MAX310X_LSR_IRQSTS_REG: case MAX310X_SPCHR_IRQSTS_REG: @@ -464,7 +498,7 @@ static bool max310x_reg_writeable(struct device *dev, unsigned int reg) static bool max310x_reg_volatile(struct device *dev, unsigned int reg) { - switch (reg & 0x1f) { + switch (reg) { case MAX310X_RHR_REG: case MAX310X_IRQSTS_REG: case MAX310X_LSR_IRQSTS_REG: @@ -486,7 +520,7 @@ static bool max310x_reg_volatile(struct device *dev, unsigned int reg) static bool max310x_reg_precious(struct device *dev, unsigned int reg) { - switch (reg & 0x1f) { + switch (reg) { case MAX310X_RHR_REG: case MAX310X_IRQSTS_REG: case MAX310X_SPCHR_IRQSTS_REG: @@ -499,6 +533,11 @@ static bool max310x_reg_precious(struct device *dev, unsigned int reg) return false; } +static bool max310x_reg_noinc(struct device *dev, unsigned int reg) +{ + return reg == MAX310X_RHR_REG; +} + static int max310x_set_baud(struct uart_port *port, int baud) { unsigned int mode = 0, div = 0, frac = 0, c = 0, F = 0; @@ -552,7 +591,7 @@ static int max310x_update_best_err(unsigned long f, long *besterr) return 1; } -static int max310x_set_ref_clk(struct device *dev, struct max310x_port *s, +static s32 max310x_set_ref_clk(struct device *dev, struct max310x_port *s, unsigned long freq, bool xtal) { unsigned int div, clksrc, pllcfg = 0; @@ -610,45 +649,37 @@ static int max310x_set_ref_clk(struct device *dev, struct max310x_port *s, /* Wait for crystal */ if (xtal) { - unsigned int val; - msleep(10); - regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &val); - if (!(val & MAX310X_STS_CLKREADY_BIT)) { - dev_warn(dev, "clock is not stable yet\n"); - } + bool stable = false; + unsigned int try = 0, val = 0; + + do { + msleep(MAX310X_XTAL_WAIT_DELAY_MS); + regmap_read(s->regmap, MAX310X_STS_IRQSTS_REG, &val); + + if (val & MAX310X_STS_CLKREADY_BIT) + stable = true; + } while (!stable && (++try < MAX310X_XTAL_WAIT_RETRIES)); + + if (!stable) + return dev_err_probe(dev, -EAGAIN, + "clock is not stable\n"); } - return (int)bestfreq; + return bestfreq; } static void max310x_batch_write(struct uart_port *port, u8 *txbuf, unsigned int len) { struct max310x_one *one = to_max310x_port(port); - struct spi_transfer xfer[] = { - { - .tx_buf = &one->wr_header, - .len = sizeof(one->wr_header), - }, { - .tx_buf = txbuf, - .len = len, - } - }; - spi_sync_transfer(to_spi_device(port->dev), xfer, ARRAY_SIZE(xfer)); + + regmap_noinc_write(one->regmap, MAX310X_THR_REG, txbuf, len); } static void max310x_batch_read(struct uart_port *port, u8 *rxbuf, unsigned int len) { struct max310x_one *one = to_max310x_port(port); - struct spi_transfer xfer[] = { - { - .tx_buf = &one->rd_header, - .len = sizeof(one->rd_header), - }, { - .rx_buf = rxbuf, - .len = len, - } - }; - spi_sync_transfer(to_spi_device(port->dev), xfer, ARRAY_SIZE(xfer)); + + regmap_noinc_read(one->regmap, MAX310X_RHR_REG, rxbuf, len); } static void max310x_handle_rx(struct uart_port *port, unsigned int rxlen) @@ -1250,16 +1281,18 @@ static int max310x_gpio_set_config(struct gpio_chip *chip, unsigned int offset, } #endif -static int max310x_probe(struct device *dev, struct max310x_devtype *devtype, - struct regmap *regmap, int irq) +static int max310x_probe(struct device *dev, const struct max310x_devtype *devtype, + const struct max310x_if_cfg *if_cfg, + struct regmap *regmaps[], int irq) { - int i, ret, fmin, fmax, freq, uartclk; - struct clk *clk_osc, *clk_xtal; + int i, ret, fmin, fmax, freq; struct max310x_port *s; - bool xtal = false; + s32 uartclk = 0; + bool xtal; - if (IS_ERR(regmap)) - return PTR_ERR(regmap); + for (i = 0; i < devtype->nr; i++) + if (IS_ERR(regmaps[i])) + return PTR_ERR(regmaps[i]); /* Alloc port structure */ s = devm_kzalloc(dev, struct_size(s, p, devtype->nr), GFP_KERNEL); @@ -1268,23 +1301,20 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype, return -ENOMEM; } - clk_osc = devm_clk_get(dev, "osc"); - clk_xtal = devm_clk_get(dev, "xtal"); - if (!IS_ERR(clk_osc)) { - s->clk = clk_osc; - fmin = 500000; - fmax = 35000000; - } else if (!IS_ERR(clk_xtal)) { - s->clk = clk_xtal; - fmin = 1000000; - fmax = 4000000; - xtal = true; - } else if (PTR_ERR(clk_osc) == -EPROBE_DEFER || - PTR_ERR(clk_xtal) == -EPROBE_DEFER) { - return -EPROBE_DEFER; + /* Always ask for fixed clock rate from a property. */ + device_property_read_u32(dev, "clock-frequency", &uartclk); + + s->clk = devm_clk_get_optional(dev, "osc"); + if (IS_ERR(s->clk)) + return PTR_ERR(s->clk); + if (s->clk) { + xtal = false; } else { - dev_err(dev, "Cannot get clock\n"); - return -EINVAL; + s->clk = devm_clk_get_optional(dev, "xtal"); + if (IS_ERR(s->clk)) + return PTR_ERR(s->clk); + + xtal = true; } ret = clk_prepare_enable(s->clk); @@ -1292,14 +1322,31 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype, return ret; freq = clk_get_rate(s->clk); + if (freq == 0) + freq = uartclk; + if (freq == 0) { + dev_err(dev, "Cannot get clock rate\n"); + ret = -EINVAL; + goto out_clk; + } + + if (xtal) { + fmin = 1000000; + fmax = 4000000; + } else { + fmin = 500000; + fmax = 35000000; + } + /* Check frequency limits */ if (freq < fmin || freq > fmax) { ret = -ERANGE; goto out_clk; } - s->regmap = regmap; + s->regmap = regmaps[0]; s->devtype = devtype; + s->if_cfg = if_cfg; dev_set_drvdata(dev, s); /* Check device to ensure we are talking to what we expect */ @@ -1308,25 +1355,38 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype, goto out_clk; for (i = 0; i < devtype->nr; i++) { - unsigned int offs = i << 5; + bool started = false; + unsigned int try = 0, val = 0; /* Reset port */ - regmap_write(s->regmap, MAX310X_MODE2_REG + offs, + regmap_write(regmaps[i], MAX310X_MODE2_REG, MAX310X_MODE2_RST_BIT); /* Clear port reset */ - regmap_write(s->regmap, MAX310X_MODE2_REG + offs, 0); + regmap_write(regmaps[i], MAX310X_MODE2_REG, 0); /* Wait for port startup */ do { - regmap_read(s->regmap, - MAX310X_BRGDIVLSB_REG + offs, &ret); - } while (ret != 0x01); + msleep(MAX310X_PORT_STARTUP_WAIT_DELAY_MS); + regmap_read(regmaps[i], MAX310X_BRGDIVLSB_REG, &val); + + if (val == 0x01) + started = true; + } while (!started && (++try < MAX310X_PORT_STARTUP_WAIT_RETRIES)); + + if (!started) { + ret = dev_err_probe(dev, -EAGAIN, "port reset failed\n"); + goto out_uart; + } - regmap_write(s->regmap, MAX310X_MODE1_REG + offs, - devtype->mode1); + regmap_write(regmaps[i], MAX310X_MODE1_REG, devtype->mode1); } uartclk = max310x_set_ref_clk(dev, s, freq, xtal); + if (uartclk < 0) { + ret = uartclk; + goto out_uart; + } + dev_dbg(dev, "Reference clock set to %i Hz\n", uartclk); for (i = 0; i < devtype->nr; i++) { @@ -1346,11 +1406,13 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype, s->p[i].port.fifosize = MAX310X_FIFO_SIZE; s->p[i].port.flags = UPF_FIXED_TYPE | UPF_LOW_LATENCY; s->p[i].port.iotype = UPIO_PORT; - s->p[i].port.iobase = i * 0x20; + s->p[i].port.iobase = i; s->p[i].port.membase = (void __iomem *)~0; s->p[i].port.uartclk = uartclk; s->p[i].port.rs485_config = max310x_rs485_config; s->p[i].port.ops = &max310x_ops; + s->p[i].regmap = regmaps[i]; + /* Disable all interrupts */ max310x_port_write(&s->p[i].port, MAX310X_IRQEN_REG, 0); /* Clear IRQ status register */ @@ -1361,10 +1423,6 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype, INIT_WORK(&s->p[i].md_work, max310x_md_proc); /* Initialize queue for changing RS485 mode */ INIT_WORK(&s->p[i].rs_work, max310x_rs_proc); - /* Initialize SPI-transfer buffers */ - s->p[i].wr_header = (s->p[i].port.iobase + MAX310X_THR_REG) | - MAX310X_WRITE_BIT; - s->p[i].rd_header = (s->p[i].port.iobase + MAX310X_RHR_REG); /* Register port */ ret = uart_add_one_port(&max310x_uart, &s->p[i].port); @@ -1402,7 +1460,7 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype, if (!ret) return 0; - dev_err(dev, "Unable to reguest IRQ %i\n", irq); + dev_err(dev, "Unable to request IRQ %i\n", irq); out_uart: for (i = 0; i < devtype->nr; i++) { @@ -1451,16 +1509,35 @@ static struct regmap_config regcfg = { .val_bits = 8, .write_flag_mask = MAX310X_WRITE_BIT, .cache_type = REGCACHE_RBTREE, + .max_register = MAX310X_REG_1F, .writeable_reg = max310x_reg_writeable, .volatile_reg = max310x_reg_volatile, .precious_reg = max310x_reg_precious, + .writeable_noinc_reg = max310x_reg_noinc, + .readable_noinc_reg = max310x_reg_noinc, + .max_raw_read = MAX310X_FIFO_SIZE, + .max_raw_write = MAX310X_FIFO_SIZE, }; #ifdef CONFIG_SPI_MASTER +static int max310x_spi_extended_reg_enable(struct device *dev, bool enable) +{ + struct max310x_port *s = dev_get_drvdata(dev); + + return regmap_write(s->regmap, MAX310X_GLOBALCMD_REG, + enable ? MAX310X_EXTREG_ENBL : MAX310X_EXTREG_DSBL); +} + +static const struct max310x_if_cfg __maybe_unused max310x_spi_if_cfg = { + .extended_reg_enable = max310x_spi_extended_reg_enable, + .rev_id_reg = MAX310X_SPI_REVID_EXTREG, +}; + static int max310x_spi_probe(struct spi_device *spi) { - struct max310x_devtype *devtype; - struct regmap *regmap; + const struct max310x_devtype *devtype; + struct regmap *regmaps[4]; + unsigned int i; int ret; /* Setup SPI bus */ @@ -1471,23 +1548,18 @@ static int max310x_spi_probe(struct spi_device *spi) if (ret) return ret; - if (spi->dev.of_node) { - const struct of_device_id *of_id = - of_match_device(max310x_dt_ids, &spi->dev); - if (!of_id) - return -ENODEV; + devtype = device_get_match_data(&spi->dev); + if (!devtype) + devtype = (struct max310x_devtype *)spi_get_device_id(spi)->driver_data; - devtype = (struct max310x_devtype *)of_id->data; - } else { - const struct spi_device_id *id_entry = spi_get_device_id(spi); - - devtype = (struct max310x_devtype *)id_entry->driver_data; + for (i = 0; i < devtype->nr; i++) { + u8 port_mask = i * 0x20; + regcfg.read_flag_mask = port_mask; + regcfg.write_flag_mask = port_mask | MAX310X_WRITE_BIT; + regmaps[i] = devm_regmap_init_spi(spi, ®cfg); } - regcfg.max_register = devtype->nr * 0x20 - 1; - regmap = devm_regmap_init_spi(spi, ®cfg); - - return max310x_probe(&spi->dev, devtype, regmap, spi->irq); + return max310x_probe(&spi->dev, devtype, &max310x_spi_if_cfg, regmaps, spi->irq); } static int max310x_spi_remove(struct spi_device *spi) @@ -1507,7 +1579,7 @@ MODULE_DEVICE_TABLE(spi, max310x_id_table); static struct spi_driver max310x_spi_driver = { .driver = { .name = MAX310X_NAME, - .of_match_table = of_match_ptr(max310x_dt_ids), + .of_match_table = max310x_dt_ids, .pm = &max310x_pm_ops, }, .probe = max310x_spi_probe, @@ -1516,6 +1588,104 @@ static struct spi_driver max310x_spi_driver = { }; #endif +#ifdef CONFIG_I2C +static int max310x_i2c_extended_reg_enable(struct device *dev, bool enable) +{ + return 0; +} + +static struct regmap_config regcfg_i2c = { + .reg_bits = 8, + .val_bits = 8, + .cache_type = REGCACHE_RBTREE, + .writeable_reg = max310x_reg_writeable, + .volatile_reg = max310x_reg_volatile, + .precious_reg = max310x_reg_precious, + .max_register = MAX310X_I2C_REVID_EXTREG, + .writeable_noinc_reg = max310x_reg_noinc, + .readable_noinc_reg = max310x_reg_noinc, + .max_raw_read = MAX310X_FIFO_SIZE, + .max_raw_write = MAX310X_FIFO_SIZE, +}; + +static const struct max310x_if_cfg max310x_i2c_if_cfg = { + .extended_reg_enable = max310x_i2c_extended_reg_enable, + .rev_id_reg = MAX310X_I2C_REVID_EXTREG, +}; + +static unsigned short max310x_i2c_slave_addr(unsigned short addr, + unsigned int nr) +{ + /* + * For MAX14830 and MAX3109, the slave address depends on what the + * A0 and A1 pins are tied to. + * See Table I2C Address Map of the datasheet. + * Based on that table, the following formulas were determined. + * UART1 - UART0 = 0x10 + * UART2 - UART1 = 0x20 + 0x10 + * UART3 - UART2 = 0x10 + */ + + addr -= nr * 0x10; + + if (nr >= 2) + addr -= 0x20; + + return addr; +} + +static int max310x_i2c_probe(struct i2c_client *client) +{ + const struct max310x_devtype *devtype; + struct i2c_client *port_client; + struct regmap *regmaps[4]; + unsigned int i; + u8 port_addr; + + devtype = device_get_match_data(&client->dev); + if (!devtype) + return dev_err_probe(&client->dev, -ENODEV, "Failed to match device\n"); + + if (client->addr < devtype->slave_addr.min || + client->addr > devtype->slave_addr.max) + return dev_err_probe(&client->dev, -EINVAL, + "Slave addr 0x%x outside of range [0x%x, 0x%x]\n", + client->addr, devtype->slave_addr.min, + devtype->slave_addr.max); + + regmaps[0] = devm_regmap_init_i2c(client, ®cfg_i2c); + + for (i = 1; i < devtype->nr; i++) { + port_addr = max310x_i2c_slave_addr(client->addr, i); + port_client = devm_i2c_new_dummy_device(&client->dev, + client->adapter, + port_addr); + + regmaps[i] = devm_regmap_init_i2c(port_client, ®cfg_i2c); + } + + return max310x_probe(&client->dev, devtype, &max310x_i2c_if_cfg, + regmaps, client->irq); +} + +static int max310x_i2c_remove(struct i2c_client *client) +{ + max310x_remove(&client->dev); + + return 0; +} + +static struct i2c_driver max310x_i2c_driver = { + .driver = { + .name = MAX310X_NAME, + .of_match_table = max310x_dt_ids, + .pm = &max310x_pm_ops, + }, + .probe_new = max310x_i2c_probe, + .remove = max310x_i2c_remove, +}; +#endif + static int __init max310x_uart_init(void) { int ret; @@ -1529,15 +1699,35 @@ static int __init max310x_uart_init(void) #ifdef CONFIG_SPI_MASTER ret = spi_register_driver(&max310x_spi_driver); if (ret) - uart_unregister_driver(&max310x_uart); + goto err_spi_register; +#endif + +#ifdef CONFIG_I2C + ret = i2c_add_driver(&max310x_i2c_driver); + if (ret) + goto err_i2c_register; +#endif + + return 0; + +#ifdef CONFIG_I2C +err_i2c_register: + spi_unregister_driver(&max310x_spi_driver); #endif +err_spi_register: + uart_unregister_driver(&max310x_uart); + return ret; } module_init(max310x_uart_init); static void __exit max310x_uart_exit(void) { +#ifdef CONFIG_I2C + i2c_del_driver(&max310x_i2c_driver); +#endif + #ifdef CONFIG_SPI_MASTER spi_unregister_driver(&max310x_spi_driver); #endif diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c index b784323a6..be6c8b9f1 100644 --- a/drivers/tty/serial/mxs-auart.c +++ b/drivers/tty/serial/mxs-auart.c @@ -1122,11 +1122,13 @@ static void mxs_auart_set_ldisc(struct uart_port *port, static irqreturn_t mxs_auart_irq_handle(int irq, void *context) { - u32 istat; + u32 istat, stat; struct mxs_auart_port *s = context; u32 mctrl_temp = s->mctrl_prev; - u32 stat = mxs_read(s, REG_STAT); + uart_port_lock(&s->port); + + stat = mxs_read(s, REG_STAT); istat = mxs_read(s, REG_INTR); /* ack irq */ @@ -1162,6 +1164,8 @@ static irqreturn_t mxs_auart_irq_handle(int irq, void *context) istat &= ~AUART_INTR_TXIS; } + uart_port_unlock(&s->port); + return IRQ_HANDLED; } diff --git a/drivers/tty/serial/pmac_zilog.c b/drivers/tty/serial/pmac_zilog.c index d6aef8a1f..1d0717fc3 100644 --- a/drivers/tty/serial/pmac_zilog.c +++ b/drivers/tty/serial/pmac_zilog.c @@ -217,7 +217,6 @@ static bool pmz_receive_chars(struct uart_pmac_port *uap) { struct tty_port *port; unsigned char ch, r1, drop, flag; - int loops = 0; /* Sanity check, make sure the old bug is no longer happening */ if (uap->port.state == NULL) { @@ -298,25 +297,12 @@ static bool pmz_receive_chars(struct uart_pmac_port *uap) if (r1 & Rx_OVR) tty_insert_flip_char(port, 0, TTY_OVERRUN); next_char: - /* We can get stuck in an infinite loop getting char 0 when the - * line is in a wrong HW state, we break that here. - * When that happens, I disable the receive side of the driver. - * Note that what I've been experiencing is a real irq loop where - * I'm getting flooded regardless of the actual port speed. - * Something strange is going on with the HW - */ - if ((++loops) > 1000) - goto flood; ch = read_zsreg(uap, R0); if (!(ch & Rx_CH_AV)) break; } return true; - flood: - pmz_interrupt_control(uap, 0); - pmz_error("pmz: rx irq flood !\n"); - return true; } static void pmz_status_handle(struct uart_pmac_port *uap) diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c index fa5b1321d..5388eb7fa 100644 --- a/drivers/tty/serial/samsung_tty.c +++ b/drivers/tty/serial/samsung_tty.c @@ -922,11 +922,10 @@ static unsigned int s3c24xx_serial_tx_empty(struct uart_port *port) if ((ufstat & info->tx_fifomask) != 0 || (ufstat & info->tx_fifofull)) return 0; - - return 1; + return TIOCSER_TEMT; } - return s3c24xx_serial_txempty_nofifo(port); + return s3c24xx_serial_txempty_nofifo(port) ? TIOCSER_TEMT : 0; } /* no modem control lines */ diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index fd9be81bc..29f05db0d 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -24,6 +24,7 @@ #include <linux/tty_flip.h> #include <linux/spi/spi.h> #include <linux/uaccess.h> +#include <linux/units.h> #include <uapi/linux/sched/types.h> #define SC16IS7XX_NAME "sc16is7xx" @@ -375,9 +376,7 @@ static void sc16is7xx_fifo_read(struct uart_port *port, unsigned int rxlen) const u8 line = sc16is7xx_line(port); u8 addr = (SC16IS7XX_RHR_REG << SC16IS7XX_REG_SHIFT) | line; - regcache_cache_bypass(s->regmap, true); - regmap_raw_read(s->regmap, addr, s->buf, rxlen); - regcache_cache_bypass(s->regmap, false); + regmap_noinc_read(s->regmap, addr, s->buf, rxlen); } static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send) @@ -393,9 +392,7 @@ static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send) if (unlikely(!to_send)) return; - regcache_cache_bypass(s->regmap, true); - regmap_raw_write(s->regmap, addr, s->buf, to_send); - regcache_cache_bypass(s->regmap, false); + regmap_noinc_write(s->regmap, addr, s->buf, to_send); } static void sc16is7xx_port_update(struct uart_port *port, u8 reg, @@ -488,6 +485,11 @@ static bool sc16is7xx_regmap_precious(struct device *dev, unsigned int reg) return false; } +static bool sc16is7xx_regmap_noinc(struct device *dev, unsigned int reg) +{ + return reg == SC16IS7XX_RHR_REG; +} + static int sc16is7xx_set_baud(struct uart_port *port, int baud) { struct sc16is7xx_port *s = dev_get_drvdata(port->dev); @@ -1438,6 +1440,8 @@ static struct regmap_config regcfg = { .cache_type = REGCACHE_RBTREE, .volatile_reg = sc16is7xx_regmap_volatile, .precious_reg = sc16is7xx_regmap_precious, + .writeable_noinc_reg = sc16is7xx_regmap_noinc, + .readable_noinc_reg = sc16is7xx_regmap_noinc, }; #ifdef CONFIG_SERIAL_SC16IS7XX_SPI @@ -1449,9 +1453,12 @@ static int sc16is7xx_spi_probe(struct spi_device *spi) /* Setup SPI bus */ spi->bits_per_word = 8; - /* only supports mode 0 on SC16IS762 */ + /* For all variants, only mode 0 is supported */ + if ((spi->mode & SPI_MODE_X_MASK) != SPI_MODE_0) + return dev_err_probe(&spi->dev, -EINVAL, "Unsupported SPI mode\n"); + spi->mode = spi->mode ? : SPI_MODE_0; - spi->max_speed_hz = spi->max_speed_hz ? : 15000000; + spi->max_speed_hz = spi->max_speed_hz ? : 4 * HZ_PER_MHZ; ret = spi_setup(spi); if (ret) return ret; diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 40fff3858..10b8785b9 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -2431,7 +2431,12 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, port->type = PORT_UNKNOWN; flags |= UART_CONFIG_TYPE; } + /* Synchronize with possible boot console. */ + if (uart_console(port)) + console_lock(); port->ops->config_port(port, flags); + if (uart_console(port)) + console_unlock(); } if (port->type != PORT_UNKNOWN) { @@ -2439,6 +2444,10 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, uart_report_port(drv, port); + /* Synchronize with possible boot console. */ + if (uart_console(port)) + console_lock(); + /* Power up port for set_mctrl() */ uart_change_pm(state, UART_PM_STATE_ON); @@ -2455,6 +2464,9 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, port->rs485_config(port, &port->rs485); spin_unlock_irqrestore(&port->lock, flags); + if (uart_console(port)) + console_unlock(); + /* * If this driver supports console, and it hasn't been * successfully registered yet, try to re-register it. diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 12a30329a..7ae2630cb 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -763,7 +763,7 @@ int tty_mode_ioctl(struct tty_struct *tty, struct file *file, ret = -EFAULT; return ret; case TIOCSLCKTRMIOS: - if (!capable(CAP_SYS_ADMIN)) + if (!checkpoint_restore_ns_capable(&init_user_ns)) return -EPERM; copy_termios_locked(real_tty, &kterm); if (user_termios_to_kernel_termios(&kterm, @@ -780,7 +780,7 @@ int tty_mode_ioctl(struct tty_struct *tty, struct file *file, ret = -EFAULT; return ret; case TIOCSLCKTRMIOS: - if (!capable(CAP_SYS_ADMIN)) + if (!checkpoint_restore_ns_capable(&init_user_ns)) return -EPERM; copy_termios_locked(real_tty, &kterm); if (user_termios_to_kernel_termios_1(&kterm, diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 0252c0562..a070f2e7d 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -398,7 +398,7 @@ static void vc_uniscr_delete(struct vc_data *vc, unsigned int nr) char32_t *ln = uniscr->lines[vc->state.y]; unsigned int x = vc->state.x, cols = vc->vc_cols; - memcpy(&ln[x], &ln[x + nr], (cols - x - nr) * sizeof(*ln)); + memmove(&ln[x], &ln[x + nr], (cols - x - nr) * sizeof(*ln)); memset32(&ln[cols - nr], ' ', nr); } } @@ -2516,7 +2516,7 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c) } return; case EScsiignore: - if (c >= 20 && c <= 0x3f) + if (c >= 0x20 && c <= 0x3f) return; vc->vc_state = ESnormal; return; diff --git a/drivers/usb/cdns3/ep0.c b/drivers/usb/cdns3/ep0.c index 30d3516c7..4241c513b 100644 --- a/drivers/usb/cdns3/ep0.c +++ b/drivers/usb/cdns3/ep0.c @@ -364,7 +364,7 @@ static int cdns3_ep0_feature_handle_endpoint(struct cdns3_device *priv_dev, if (le16_to_cpu(ctrl->wValue) != USB_ENDPOINT_HALT) return -EINVAL; - if (!(ctrl->wIndex & ~USB_DIR_IN)) + if (!(le16_to_cpu(ctrl->wIndex) & ~USB_DIR_IN)) return 0; index = cdns3_ep_addr_to_index(le16_to_cpu(ctrl->wIndex)); @@ -790,7 +790,7 @@ int cdns3_gadget_ep_set_wedge(struct usb_ep *ep) return 0; } -const struct usb_ep_ops cdns3_gadget_ep0_ops = { +static const struct usb_ep_ops cdns3_gadget_ep0_ops = { .enable = cdns3_gadget_ep0_enable, .disable = cdns3_gadget_ep0_disable, .alloc_request = cdns3_gadget_ep_alloc_request, diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c index 210c1d615..eeea89224 100644 --- a/drivers/usb/cdns3/gadget.c +++ b/drivers/usb/cdns3/gadget.c @@ -837,7 +837,11 @@ void cdns3_gadget_giveback(struct cdns3_endpoint *priv_ep, return; } - if (request->complete) { + /* + * zlp request is appended by driver, needn't call usb_gadget_giveback_request() to notify + * gadget composite driver. + */ + if (request->complete && request->buf != priv_dev->zlp_buf) { spin_unlock(&priv_dev->lock); usb_gadget_giveback_request(&priv_ep->endpoint, request); @@ -1118,6 +1122,8 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, dma_addr_t trb_dma; u32 togle_pcs = 1; int sg_iter = 0; + int num_trb_req; + int trb_burst; int num_trb; int address; u32 control; @@ -1126,15 +1132,13 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, struct scatterlist *s = NULL; bool sg_supported = !!(request->num_mapped_sgs); + num_trb_req = sg_supported ? request->num_mapped_sgs : 1; + + /* ISO transfer require each SOF have a TD, each TD include some TRBs */ if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) - num_trb = priv_ep->interval; + num_trb = priv_ep->interval * num_trb_req; else - num_trb = sg_supported ? request->num_mapped_sgs : 1; - - if (num_trb > priv_ep->free_trbs) { - priv_ep->flags |= EP_RING_FULL; - return -ENOBUFS; - } + num_trb = num_trb_req; priv_req = to_cdns3_request(request); address = priv_ep->endpoint.desc->bEndpointAddress; @@ -1183,14 +1187,31 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, link_trb->control = cpu_to_le32(((priv_ep->pcs) ? TRB_CYCLE : 0) | TRB_TYPE(TRB_LINK) | TRB_TOGGLE | ch_bit); + + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) { + /* + * ISO require LINK TRB must be first one of TD. + * Fill LINK TRBs for left trb space to simply software process logic. + */ + while (priv_ep->enqueue) { + *trb = *link_trb; + trace_cdns3_prepare_trb(priv_ep, trb); + + cdns3_ep_inc_enq(priv_ep); + trb = priv_ep->trb_pool + priv_ep->enqueue; + priv_req->trb = trb; + } + } + } + + if (num_trb > priv_ep->free_trbs) { + priv_ep->flags |= EP_RING_FULL; + return -ENOBUFS; } if (priv_dev->dev_ver <= DEV_VER_V2) togle_pcs = cdns3_wa1_update_guard(priv_ep, trb); - if (sg_supported) - s = request->sg; - /* set incorrect Cycle Bit for first trb*/ control = priv_ep->pcs ? 0 : TRB_CYCLE; trb->length = 0; @@ -1200,7 +1221,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, td_size = DIV_ROUND_UP(request->length, priv_ep->endpoint.maxpacket); if (priv_dev->gadget.speed == USB_SPEED_SUPER) - trb->length = TRB_TDL_SS_SIZE(td_size); + trb->length = cpu_to_le32(TRB_TDL_SS_SIZE(td_size)); else control |= TRB_TDL_HS_SIZE(td_size); } @@ -1208,6 +1229,9 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, do { u32 length; + if (!(sg_iter % num_trb_req) && sg_supported) + s = request->sg; + /* fill TRB */ control |= TRB_TYPE(TRB_NORMAL); if (sg_supported) { @@ -1222,7 +1246,36 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, total_tdl += DIV_ROUND_UP(length, priv_ep->endpoint.maxpacket); - trb->length |= cpu_to_le32(TRB_BURST_LEN(priv_ep->trb_burst_size) | + trb_burst = priv_ep->trb_burst_size; + + /* + * Supposed DMA cross 4k bounder problem should be fixed at DEV_VER_V2, but still + * met problem when do ISO transfer if sg enabled. + * + * Data pattern likes below when sg enabled, package size is 1k and mult is 2 + * [UVC Header(8B) ] [data(3k - 8)] ... + * + * The received data at offset 0xd000 will get 0xc000 data, len 0x70. Error happen + * as below pattern: + * 0xd000: wrong + * 0xe000: wrong + * 0xf000: correct + * 0x10000: wrong + * 0x11000: wrong + * 0x12000: correct + * ... + * + * But it is still unclear about why error have not happen below 0xd000, it should + * cross 4k bounder. But anyway, the below code can fix this problem. + * + * To avoid DMA cross 4k bounder at ISO transfer, reduce burst len according to 16. + */ + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && priv_dev->dev_ver <= DEV_VER_V2) + if (ALIGN_DOWN(trb->buffer, SZ_4K) != + ALIGN_DOWN(trb->buffer + length, SZ_4K)) + trb_burst = 16; + + trb->length |= cpu_to_le32(TRB_BURST_LEN(trb_burst) | TRB_LEN(length)); pcs = priv_ep->pcs ? TRB_CYCLE : 0; @@ -1247,10 +1300,10 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, priv_req->trb->control = cpu_to_le32(control); if (sg_supported) { - trb->control |= TRB_ISP; + trb->control |= cpu_to_le32(TRB_ISP); /* Don't set chain bit for last TRB */ - if (sg_iter < num_trb - 1) - trb->control |= TRB_CHAIN; + if ((sg_iter % num_trb_req) < num_trb_req - 1) + trb->control |= cpu_to_le32(TRB_CHAIN); s = sg_next(s); } @@ -1507,6 +1560,12 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev, /* The TRB was changed as link TRB, and the request was handled at ep_dequeue */ while (TRB_FIELD_TO_TYPE(le32_to_cpu(trb->control)) == TRB_LINK) { + + /* ISO ep_traddr may stop at LINK TRB */ + if (priv_ep->dequeue == cdns3_get_dma_pos(priv_dev, priv_ep) && + priv_ep->type == USB_ENDPOINT_XFER_ISOC) + break; + trace_cdns3_complete_trb(priv_ep, trb); cdns3_ep_inc_deq(priv_ep); trb = priv_ep->trb_pool + priv_ep->dequeue; @@ -1539,6 +1598,10 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev, } if (request_handled) { + /* TRBs are duplicated by priv_ep->interval time for ISO IN */ + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && priv_ep->dir) + request->actual /= priv_ep->interval; + cdns3_gadget_giveback(priv_ep, priv_req, 0); request_handled = false; transfer_end = false; @@ -2034,11 +2097,10 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) bool is_iso_ep = (priv_ep->type == USB_ENDPOINT_XFER_ISOC); struct cdns3_device *priv_dev = priv_ep->cdns3_dev; u32 bEndpointAddress = priv_ep->num | priv_ep->dir; - u32 max_packet_size = 0; - u8 maxburst = 0; + u32 max_packet_size = priv_ep->wMaxPacketSize; + u8 maxburst = priv_ep->bMaxBurst; u32 ep_cfg = 0; u8 buffering; - u8 mult = 0; int ret; buffering = priv_dev->ep_buf_size - 1; @@ -2060,8 +2122,7 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) break; default: ep_cfg = EP_CFG_EPTYPE(USB_ENDPOINT_XFER_ISOC); - mult = priv_dev->ep_iso_burst - 1; - buffering = mult + 1; + buffering = (priv_ep->bMaxBurst + 1) * (priv_ep->mult + 1) - 1; } switch (priv_dev->gadget.speed) { @@ -2072,17 +2133,8 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) max_packet_size = is_iso_ep ? 1024 : 512; break; case USB_SPEED_SUPER: - /* It's limitation that driver assumes in driver. */ - mult = 0; - max_packet_size = 1024; - if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) { - maxburst = priv_dev->ep_iso_burst - 1; - buffering = (mult + 1) * - (maxburst + 1); - - if (priv_ep->interval > 1) - buffering++; - } else { + if (priv_ep->type != USB_ENDPOINT_XFER_ISOC) { + max_packet_size = 1024; maxburst = priv_dev->ep_buf_size - 1; } break; @@ -2111,7 +2163,6 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) if (priv_dev->dev_ver < DEV_VER_V2) priv_ep->trb_burst_size = 16; - mult = min_t(u8, mult, EP_CFG_MULT_MAX); buffering = min_t(u8, buffering, EP_CFG_BUFFERING_MAX); maxburst = min_t(u8, maxburst, EP_CFG_MAXBURST_MAX); @@ -2145,7 +2196,7 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) } ep_cfg |= EP_CFG_MAXPKTSIZE(max_packet_size) | - EP_CFG_MULT(mult) | + EP_CFG_MULT(priv_ep->mult) | /* must match EP setting */ EP_CFG_BUFFERING(buffering) | EP_CFG_MAXBURST(maxburst); @@ -2235,6 +2286,13 @@ usb_ep *cdns3_gadget_match_ep(struct usb_gadget *gadget, priv_ep->type = usb_endpoint_type(desc); priv_ep->flags |= EP_CLAIMED; priv_ep->interval = desc->bInterval ? BIT(desc->bInterval - 1) : 0; + priv_ep->wMaxPacketSize = usb_endpoint_maxp(desc); + priv_ep->mult = USB_EP_MAXP_MULT(priv_ep->wMaxPacketSize); + priv_ep->wMaxPacketSize &= USB_ENDPOINT_MAXP_MASK; + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && comp_desc) { + priv_ep->mult = USB_SS_MULT(comp_desc->bmAttributes) - 1; + priv_ep->bMaxBurst = comp_desc->bMaxBurst; + } spin_unlock_irqrestore(&priv_dev->lock, flags); return &priv_ep->endpoint; @@ -2484,11 +2542,11 @@ static int cdns3_gadget_ep_disable(struct usb_ep *ep) while (!list_empty(&priv_ep->wa2_descmiss_req_list)) { priv_req = cdns3_next_priv_request(&priv_ep->wa2_descmiss_req_list); + list_del_init(&priv_req->list); kfree(priv_req->request.buf); cdns3_gadget_ep_free_request(&priv_ep->endpoint, &priv_req->request); - list_del_init(&priv_req->list); --priv_ep->wa2_counter; } @@ -3001,23 +3059,43 @@ static int cdns3_gadget_udc_stop(struct usb_gadget *gadget) static int cdns3_gadget_check_config(struct usb_gadget *gadget) { struct cdns3_device *priv_dev = gadget_to_cdns3_device(gadget); + struct cdns3_endpoint *priv_ep; struct usb_ep *ep; int n_in = 0; + int iso = 0; + int out = 1; int total; + int n; list_for_each_entry(ep, &gadget->ep_list, ep_list) { - if (ep->claimed && (ep->address & USB_DIR_IN)) - n_in++; + priv_ep = ep_to_cdns3_ep(ep); + if (!(priv_ep->flags & EP_CLAIMED)) + continue; + + n = (priv_ep->mult + 1) * (priv_ep->bMaxBurst + 1); + if (ep->address & USB_DIR_IN) { + /* + * ISO transfer: DMA start move data when get ISO, only transfer + * data as min(TD size, iso). No benefit for allocate bigger + * internal memory than 'iso'. + */ + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) + iso += n; + else + n_in++; + } else { + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) + out = max_t(int, out, n); + } } /* 2KB are reserved for EP0, 1KB for out*/ - total = 2 + n_in + 1; + total = 2 + n_in + out + iso; if (total > priv_dev->onchip_buffers) return -ENOMEM; - priv_dev->ep_buf_size = priv_dev->ep_iso_burst = - (priv_dev->onchip_buffers - 2) / (n_in + 1); + priv_dev->ep_buf_size = (priv_dev->onchip_buffers - 2 - iso) / (n_in + out); return 0; } diff --git a/drivers/usb/cdns3/gadget.h b/drivers/usb/cdns3/gadget.h index 32825477e..aeb221122 100644 --- a/drivers/usb/cdns3/gadget.h +++ b/drivers/usb/cdns3/gadget.h @@ -1167,6 +1167,9 @@ struct cdns3_endpoint { u8 dir; u8 num; u8 type; + u8 mult; + u8 bMaxBurst; + u16 wMaxPacketSize; int interval; int free_trbs; diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 331f41c6c..eef78141f 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -46,8 +46,8 @@ #define USB_VENDOR_TEXAS_INSTRUMENTS 0x0451 #define USB_PRODUCT_TUSB8041_USB3 0x8140 #define USB_PRODUCT_TUSB8041_USB2 0x8142 -#define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND 0x01 -#define HUB_QUIRK_DISABLE_AUTOSUSPEND 0x02 +#define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND BIT(0) +#define HUB_QUIRK_DISABLE_AUTOSUSPEND BIT(1) #define USB_TP_TRANSMISSION_DELAY 40 /* ns */ #define USB_TP_TRANSMISSION_DELAY_MAX 65535 /* ns */ @@ -116,7 +116,6 @@ EXPORT_SYMBOL_GPL(ehci_cf_port_reset_rwsem); #define HUB_DEBOUNCE_STEP 25 #define HUB_DEBOUNCE_STABLE 100 -static void hub_release(struct kref *kref); static int usb_reset_and_verify_device(struct usb_device *udev); static int hub_port_disable(struct usb_hub *hub, int port1, int set_state); static bool hub_port_warm_reset_required(struct usb_hub *hub, int port1, @@ -678,14 +677,14 @@ static void kick_hub_wq(struct usb_hub *hub) */ intf = to_usb_interface(hub->intfdev); usb_autopm_get_interface_no_resume(intf); - kref_get(&hub->kref); + hub_get(hub); if (queue_work(hub_wq, &hub->events)) return; /* the work has already been scheduled */ usb_autopm_put_interface_async(intf); - kref_put(&hub->kref, hub_release); + hub_put(hub); } void usb_kick_hub_wq(struct usb_device *hdev) @@ -1053,7 +1052,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) goto init2; goto init3; } - kref_get(&hub->kref); + hub_get(hub); /* The superspeed hub except for root hub has to use Hub Depth * value as an offset into the route string to locate the bits @@ -1301,7 +1300,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) device_unlock(&hdev->dev); } - kref_put(&hub->kref, hub_release); + hub_put(hub); } /* Implement the continuations for the delays above */ @@ -1717,6 +1716,16 @@ static void hub_release(struct kref *kref) kfree(hub); } +void hub_get(struct usb_hub *hub) +{ + kref_get(&hub->kref); +} + +void hub_put(struct usb_hub *hub) +{ + kref_put(&hub->kref, hub_release); +} + static unsigned highspeed_hubs; static void hub_disconnect(struct usb_interface *intf) @@ -1763,7 +1772,7 @@ static void hub_disconnect(struct usb_interface *intf) if (hub->quirk_disable_autosuspend) usb_autopm_put_interface(intf); - kref_put(&hub->kref, hub_release); + hub_put(hub); } static bool hub_descriptor_is_sane(struct usb_host_interface *desc) @@ -2367,17 +2376,25 @@ static int usb_enumerate_device_otg(struct usb_device *udev) } } else if (desc->bLength == sizeof (struct usb_otg_descriptor)) { - /* Set a_alt_hnp_support for legacy otg device */ - err = usb_control_msg(udev, - usb_sndctrlpipe(udev, 0), - USB_REQ_SET_FEATURE, 0, - USB_DEVICE_A_ALT_HNP_SUPPORT, - 0, NULL, 0, - USB_CTRL_SET_TIMEOUT); - if (err < 0) - dev_err(&udev->dev, - "set a_alt_hnp_support failed: %d\n", - err); + /* + * We are operating on a legacy OTP device + * These should be told that they are operating + * on the wrong port if we have another port that does + * support HNP + */ + if (bus->otg_port != 0) { + /* Set a_alt_hnp_support for legacy otg device */ + err = usb_control_msg(udev, + usb_sndctrlpipe(udev, 0), + USB_REQ_SET_FEATURE, 0, + USB_DEVICE_A_ALT_HNP_SUPPORT, + 0, NULL, 0, + USB_CTRL_SET_TIMEOUT); + if (err < 0) + dev_err(&udev->dev, + "set a_alt_hnp_support failed: %d\n", + err); + } } } #endif @@ -5849,7 +5866,7 @@ out_hdev_lock: /* Balance the stuff in kick_hub_wq() and allow autosuspend */ usb_autopm_put_interface(intf); - kref_put(&hub->kref, hub_release); + hub_put(hub); kcov_remote_stop(); } diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h index db4c7e2c5..dd049bc85 100644 --- a/drivers/usb/core/hub.h +++ b/drivers/usb/core/hub.h @@ -117,6 +117,8 @@ extern void usb_hub_remove_port_device(struct usb_hub *hub, extern int usb_hub_set_port_power(struct usb_device *hdev, struct usb_hub *hub, int port1, bool set); extern struct usb_hub *usb_hub_to_struct_hub(struct usb_device *hdev); +extern void hub_get(struct usb_hub *hub); +extern void hub_put(struct usb_hub *hub); extern int hub_port_debounce(struct usb_hub *hub, int port1, bool must_be_connected); extern int usb_clear_port_feature(struct usb_device *hdev, diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index 235a7c645..86e8585a5 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -295,8 +295,10 @@ static void usb_port_shutdown(struct device *dev) { struct usb_port *port_dev = to_usb_port(dev); - if (port_dev->child) + if (port_dev->child) { usb_disable_usb2_hardware_lpm(port_dev->child); + usb_unlocked_disable_lpm(port_dev->child); + } } static const struct dev_pm_ops usb_port_pm_ops = { @@ -450,7 +452,7 @@ static int match_location(struct usb_device *peer_hdev, void *p) struct usb_hub *peer_hub = usb_hub_to_struct_hub(peer_hdev); struct usb_device *hdev = to_usb_device(port_dev->dev.parent->parent); - if (!peer_hub) + if (!peer_hub || port_dev->connect_type == USB_PORT_NOT_USED) return 0; hcd = bus_to_hcd(hdev->bus); @@ -461,7 +463,8 @@ static int match_location(struct usb_device *peer_hdev, void *p) for (port1 = 1; port1 <= peer_hdev->maxchild; port1++) { peer = peer_hub->ports[port1 - 1]; - if (peer && peer->location == port_dev->location) { + if (peer && peer->connect_type != USB_PORT_NOT_USED && + peer->location == port_dev->location) { link_peers_report(port_dev, peer); return 1; /* done */ } diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c index 35ce8b87e..366c09521 100644 --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -1166,14 +1166,24 @@ static ssize_t interface_authorized_store(struct device *dev, { struct usb_interface *intf = to_usb_interface(dev); bool val; + struct kernfs_node *kn; if (strtobool(buf, &val) != 0) return -EINVAL; - if (val) + if (val) { usb_authorize_interface(intf); - else - usb_deauthorize_interface(intf); + } else { + /* + * Prevent deadlock if another process is concurrently + * trying to unregister intf. + */ + kn = sysfs_break_active_protection(&dev->kobj, &attr->attr); + if (kn) { + usb_deauthorize_interface(intf); + sysfs_unbreak_active_protection(kn); + } + } return count; } diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h index 03d16a082..03cc331d3 100644 --- a/drivers/usb/dwc2/core.h +++ b/drivers/usb/dwc2/core.h @@ -748,8 +748,14 @@ struct dwc2_dregs_backup { * struct dwc2_hregs_backup - Holds host registers state before * entering partial power down * @hcfg: Backup of HCFG register + * @hflbaddr: Backup of HFLBADDR register * @haintmsk: Backup of HAINTMSK register + * @hcchar: Backup of HCCHAR register + * @hcsplt: Backup of HCSPLT register * @hcintmsk: Backup of HCINTMSK register + * @hctsiz: Backup of HCTSIZ register + * @hdma: Backup of HCDMA register + * @hcdmab: Backup of HCDMAB register * @hprt0: Backup of HPTR0 register * @hfir: Backup of HFIR register * @hptxfsiz: Backup of HPTXFSIZ register @@ -757,8 +763,14 @@ struct dwc2_dregs_backup { */ struct dwc2_hregs_backup { u32 hcfg; + u32 hflbaddr; u32 haintmsk; + u32 hcchar[MAX_EPS_CHANNELS]; + u32 hcsplt[MAX_EPS_CHANNELS]; u32 hcintmsk[MAX_EPS_CHANNELS]; + u32 hctsiz[MAX_EPS_CHANNELS]; + u32 hcidma[MAX_EPS_CHANNELS]; + u32 hcidmab[MAX_EPS_CHANNELS]; u32 hprt0; u32 hfir; u32 hptxfsiz; @@ -1097,6 +1109,7 @@ struct dwc2_hsotg { bool needs_byte_swap; /* DWC OTG HW Release versions */ +#define DWC2_CORE_REV_4_30a 0x4f54430a #define DWC2_CORE_REV_2_71a 0x4f54271a #define DWC2_CORE_REV_2_72a 0x4f54272a #define DWC2_CORE_REV_2_80a 0x4f54280a @@ -1335,6 +1348,7 @@ int dwc2_backup_global_registers(struct dwc2_hsotg *hsotg); int dwc2_restore_global_registers(struct dwc2_hsotg *hsotg); void dwc2_enable_acg(struct dwc2_hsotg *hsotg); +void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg, bool remotewakeup); /* This function should be called on every hardware interrupt. */ irqreturn_t dwc2_handle_common_intr(int irq, void *dev); diff --git a/drivers/usb/dwc2/core_intr.c b/drivers/usb/dwc2/core_intr.c index e3f429f15..8deb2ea21 100644 --- a/drivers/usb/dwc2/core_intr.c +++ b/drivers/usb/dwc2/core_intr.c @@ -344,10 +344,11 @@ static void dwc2_handle_session_req_intr(struct dwc2_hsotg *hsotg) * @hsotg: Programming view of DWC_otg controller * */ -static void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg) +void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg, bool remotewakeup) { u32 glpmcfg; - u32 i = 0; + u32 pcgctl; + u32 dctl; if (hsotg->lx_state != DWC2_L1) { dev_err(hsotg->dev, "Core isn't in DWC2_L1 state\n"); @@ -356,37 +357,57 @@ static void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg) glpmcfg = dwc2_readl(hsotg, GLPMCFG); if (dwc2_is_device_mode(hsotg)) { - dev_dbg(hsotg->dev, "Exit from L1 state\n"); + dev_dbg(hsotg->dev, "Exit from L1 state, remotewakeup=%d\n", remotewakeup); glpmcfg &= ~GLPMCFG_ENBLSLPM; - glpmcfg &= ~GLPMCFG_HIRD_THRES_EN; + glpmcfg &= ~GLPMCFG_HIRD_THRES_MASK; dwc2_writel(hsotg, glpmcfg, GLPMCFG); - do { - glpmcfg = dwc2_readl(hsotg, GLPMCFG); + pcgctl = dwc2_readl(hsotg, PCGCTL); + pcgctl &= ~PCGCTL_ENBL_SLEEP_GATING; + dwc2_writel(hsotg, pcgctl, PCGCTL); - if (!(glpmcfg & (GLPMCFG_COREL1RES_MASK | - GLPMCFG_L1RESUMEOK | GLPMCFG_SLPSTS))) - break; + glpmcfg = dwc2_readl(hsotg, GLPMCFG); + if (glpmcfg & GLPMCFG_ENBESL) { + glpmcfg |= GLPMCFG_RSTRSLPSTS; + dwc2_writel(hsotg, glpmcfg, GLPMCFG); + } + + if (remotewakeup) { + if (dwc2_hsotg_wait_bit_set(hsotg, GLPMCFG, GLPMCFG_L1RESUMEOK, 1000)) { + dev_warn(hsotg->dev, "%s: timeout GLPMCFG_L1RESUMEOK\n", __func__); + goto fail; + return; + } + + dctl = dwc2_readl(hsotg, DCTL); + dctl |= DCTL_RMTWKUPSIG; + dwc2_writel(hsotg, dctl, DCTL); - udelay(1); - } while (++i < 200); + if (dwc2_hsotg_wait_bit_set(hsotg, GINTSTS, GINTSTS_WKUPINT, 1000)) { + dev_warn(hsotg->dev, "%s: timeout GINTSTS_WKUPINT\n", __func__); + goto fail; + return; + } + } - if (i == 200) { - dev_err(hsotg->dev, "Failed to exit L1 sleep state in 200us.\n"); + glpmcfg = dwc2_readl(hsotg, GLPMCFG); + if (glpmcfg & GLPMCFG_COREL1RES_MASK || glpmcfg & GLPMCFG_SLPSTS || + glpmcfg & GLPMCFG_L1RESUMEOK) { + goto fail; return; } - dwc2_gadget_init_lpm(hsotg); + + /* Inform gadget to exit from L1 */ + call_gadget(hsotg, resume); + /* Change to L0 state */ + hsotg->lx_state = DWC2_L0; + hsotg->bus_suspended = false; +fail: dwc2_gadget_init_lpm(hsotg); } else { /* TODO */ dev_err(hsotg->dev, "Host side LPM is not supported.\n"); return; } - - /* Change to L0 state */ - hsotg->lx_state = DWC2_L0; - - /* Inform gadget to exit from L1 */ - call_gadget(hsotg, resume); } /* @@ -407,7 +428,7 @@ static void dwc2_handle_wakeup_detected_intr(struct dwc2_hsotg *hsotg) dev_dbg(hsotg->dev, "%s lxstate = %d\n", __func__, hsotg->lx_state); if (hsotg->lx_state == DWC2_L1) { - dwc2_wakeup_from_lpm_l1(hsotg); + dwc2_wakeup_from_lpm_l1(hsotg, false); return; } diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index da0df69cc..d8b836655 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -1416,6 +1416,10 @@ static int dwc2_hsotg_ep_queue(struct usb_ep *ep, struct usb_request *req, ep->name, req, req->length, req->buf, req->no_interrupt, req->zero, req->short_not_ok); + if (hs->lx_state == DWC2_L1) { + dwc2_wakeup_from_lpm_l1(hs, true); + } + /* Prevent new request submission when controller is suspended */ if (hs->lx_state != DWC2_L0) { dev_dbg(hs->dev, "%s: submit request only in active state\n", diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index 14925fedb..9c32a64bc 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -2736,8 +2736,11 @@ enum dwc2_transaction_type dwc2_hcd_select_transactions( hsotg->available_host_channels--; } qh = list_entry(qh_ptr, struct dwc2_qh, qh_list_entry); - if (dwc2_assign_and_init_hc(hsotg, qh)) + if (dwc2_assign_and_init_hc(hsotg, qh)) { + if (hsotg->params.uframe_sched) + hsotg->available_host_channels++; break; + } /* * Move the QH from the periodic ready schedule to the @@ -2770,8 +2773,11 @@ enum dwc2_transaction_type dwc2_hcd_select_transactions( hsotg->available_host_channels--; } - if (dwc2_assign_and_init_hc(hsotg, qh)) + if (dwc2_assign_and_init_hc(hsotg, qh)) { + if (hsotg->params.uframe_sched) + hsotg->available_host_channels++; break; + } /* * Move the QH from the non-periodic inactive schedule to the @@ -4125,6 +4131,8 @@ void dwc2_host_complete(struct dwc2_hsotg *hsotg, struct dwc2_qtd *qtd, urb->actual_length); if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) { + if (!hsotg->params.dma_desc_enable) + urb->start_frame = qtd->qh->start_active_frame; urb->error_count = dwc2_hcd_urb_get_error_count(qtd->urb); for (i = 0; i < urb->number_of_packets; ++i) { urb->iso_frame_desc[i].actual_length = @@ -5319,9 +5327,16 @@ int dwc2_backup_host_registers(struct dwc2_hsotg *hsotg) /* Backup Host regs */ hr = &hsotg->hr_backup; hr->hcfg = dwc2_readl(hsotg, HCFG); + hr->hflbaddr = dwc2_readl(hsotg, HFLBADDR); hr->haintmsk = dwc2_readl(hsotg, HAINTMSK); - for (i = 0; i < hsotg->params.host_channels; ++i) + for (i = 0; i < hsotg->params.host_channels; ++i) { + hr->hcchar[i] = dwc2_readl(hsotg, HCCHAR(i)); + hr->hcsplt[i] = dwc2_readl(hsotg, HCSPLT(i)); hr->hcintmsk[i] = dwc2_readl(hsotg, HCINTMSK(i)); + hr->hctsiz[i] = dwc2_readl(hsotg, HCTSIZ(i)); + hr->hcidma[i] = dwc2_readl(hsotg, HCDMA(i)); + hr->hcidmab[i] = dwc2_readl(hsotg, HCDMAB(i)); + } hr->hprt0 = dwc2_read_hprt0(hsotg); hr->hfir = dwc2_readl(hsotg, HFIR); @@ -5355,10 +5370,17 @@ int dwc2_restore_host_registers(struct dwc2_hsotg *hsotg) hr->valid = false; dwc2_writel(hsotg, hr->hcfg, HCFG); + dwc2_writel(hsotg, hr->hflbaddr, HFLBADDR); dwc2_writel(hsotg, hr->haintmsk, HAINTMSK); - for (i = 0; i < hsotg->params.host_channels; ++i) + for (i = 0; i < hsotg->params.host_channels; ++i) { + dwc2_writel(hsotg, hr->hcchar[i], HCCHAR(i)); + dwc2_writel(hsotg, hr->hcsplt[i], HCSPLT(i)); dwc2_writel(hsotg, hr->hcintmsk[i], HCINTMSK(i)); + dwc2_writel(hsotg, hr->hctsiz[i], HCTSIZ(i)); + dwc2_writel(hsotg, hr->hcidma[i], HCDMA(i)); + dwc2_writel(hsotg, hr->hcidmab[i], HCDMAB(i)); + } dwc2_writel(hsotg, hr->hprt0, HPRT0); dwc2_writel(hsotg, hr->hfir, HFIR); @@ -5523,10 +5545,12 @@ int dwc2_host_exit_hibernation(struct dwc2_hsotg *hsotg, int rem_wakeup, dwc2_writel(hsotg, hr->hcfg, HCFG); /* De-assert Wakeup Logic */ - gpwrdn = dwc2_readl(hsotg, GPWRDN); - gpwrdn &= ~GPWRDN_PMUACTV; - dwc2_writel(hsotg, gpwrdn, GPWRDN); - udelay(10); + if (!(rem_wakeup && hsotg->hw_params.snpsid >= DWC2_CORE_REV_4_30a)) { + gpwrdn = dwc2_readl(hsotg, GPWRDN); + gpwrdn &= ~GPWRDN_PMUACTV; + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + } hprt0 = hr->hprt0; hprt0 |= HPRT0_PWR; @@ -5551,6 +5575,13 @@ int dwc2_host_exit_hibernation(struct dwc2_hsotg *hsotg, int rem_wakeup, hprt0 |= HPRT0_RES; dwc2_writel(hsotg, hprt0, HPRT0); + /* De-assert Wakeup Logic */ + if ((rem_wakeup && hsotg->hw_params.snpsid >= DWC2_CORE_REV_4_30a)) { + gpwrdn = dwc2_readl(hsotg, GPWRDN); + gpwrdn &= ~GPWRDN_PMUACTV; + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + } /* Wait for Resume time and then program HPRT again */ mdelay(100); hprt0 &= ~HPRT0_RES; diff --git a/drivers/usb/dwc2/hcd_ddma.c b/drivers/usb/dwc2/hcd_ddma.c index a858b5f9c..d6fa02d85 100644 --- a/drivers/usb/dwc2/hcd_ddma.c +++ b/drivers/usb/dwc2/hcd_ddma.c @@ -589,7 +589,7 @@ static void dwc2_init_isoc_dma_desc(struct dwc2_hsotg *hsotg, idx = qh->td_last; inc = qh->host_interval; hsotg->frame_number = dwc2_hcd_get_frame_number(hsotg); - cur_idx = dwc2_frame_list_idx(hsotg->frame_number); + cur_idx = idx; next_idx = dwc2_desclist_idx_inc(qh->td_last, inc, qh->dev_speed); /* @@ -896,20 +896,27 @@ static int dwc2_cmpl_host_isoc_dma_desc(struct dwc2_hsotg *hsotg, { struct dwc2_dma_desc *dma_desc; struct dwc2_hcd_iso_packet_desc *frame_desc; + u16 frame_desc_idx; + struct urb *usb_urb; u16 remain = 0; int rc = 0; if (!qtd->urb) return -EINVAL; + usb_urb = qtd->urb->priv; + dma_sync_single_for_cpu(hsotg->dev, qh->desc_list_dma + (idx * sizeof(struct dwc2_dma_desc)), sizeof(struct dwc2_dma_desc), DMA_FROM_DEVICE); dma_desc = &qh->desc_list[idx]; + frame_desc_idx = (idx - qtd->isoc_td_first) & (usb_urb->number_of_packets - 1); - frame_desc = &qtd->urb->iso_descs[qtd->isoc_frame_index_last]; + frame_desc = &qtd->urb->iso_descs[frame_desc_idx]; + if (idx == qtd->isoc_td_first) + usb_urb->start_frame = dwc2_hcd_get_frame_number(hsotg); dma_desc->buf = (u32)(qtd->urb->dma + frame_desc->offset); if (chan->ep_is_in) remain = (dma_desc->status & HOST_DMA_ISOC_NBYTES_MASK) >> @@ -930,7 +937,7 @@ static int dwc2_cmpl_host_isoc_dma_desc(struct dwc2_hsotg *hsotg, frame_desc->status = 0; } - if (++qtd->isoc_frame_index == qtd->urb->packet_count) { + if (++qtd->isoc_frame_index == usb_urb->number_of_packets) { /* * urb->status is not used for isoc transfers here. The * individual frame_desc status are used instead. @@ -1035,11 +1042,11 @@ static void dwc2_complete_isoc_xfer_ddma(struct dwc2_hsotg *hsotg, return; idx = dwc2_desclist_idx_inc(idx, qh->host_interval, chan->speed); - if (!rc) + if (rc == 0) continue; - if (rc == DWC2_CMPL_DONE) - break; + if (rc == DWC2_CMPL_DONE || rc == DWC2_CMPL_STOP) + goto stop_scan; /* rc == DWC2_CMPL_STOP */ diff --git a/drivers/usb/dwc2/hw.h b/drivers/usb/dwc2/hw.h index c3d6dde2a..6ad7ba054 100644 --- a/drivers/usb/dwc2/hw.h +++ b/drivers/usb/dwc2/hw.h @@ -727,7 +727,7 @@ #define TXSTS_QTOP_TOKEN_MASK (0x3 << 25) #define TXSTS_QTOP_TOKEN_SHIFT 25 #define TXSTS_QTOP_TERMINATE BIT(24) -#define TXSTS_QSPCAVAIL_MASK (0xff << 16) +#define TXSTS_QSPCAVAIL_MASK (0x7f << 16) #define TXSTS_QSPCAVAIL_SHIFT 16 #define TXSTS_FSPCAVAIL_MASK (0xffff << 0) #define TXSTS_FSPCAVAIL_SHIFT 0 diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index 553547f12..d20ca5974 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -575,21 +575,37 @@ static int start_transfer(struct fsg_dev *fsg, struct usb_ep *ep, static bool start_in_transfer(struct fsg_common *common, struct fsg_buffhd *bh) { + int rc; + if (!fsg_is_set(common)) return false; bh->state = BUF_STATE_SENDING; - if (start_transfer(common->fsg, common->fsg->bulk_in, bh->inreq)) + rc = start_transfer(common->fsg, common->fsg->bulk_in, bh->inreq); + if (rc) { bh->state = BUF_STATE_EMPTY; + if (rc == -ESHUTDOWN) { + common->running = 0; + return false; + } + } return true; } static bool start_out_transfer(struct fsg_common *common, struct fsg_buffhd *bh) { + int rc; + if (!fsg_is_set(common)) return false; bh->state = BUF_STATE_RECEIVING; - if (start_transfer(common->fsg, common->fsg->bulk_out, bh->outreq)) + rc = start_transfer(common->fsg, common->fsg->bulk_out, bh->outreq); + if (rc) { bh->state = BUF_STATE_FULL; + if (rc == -ESHUTDOWN) { + common->running = 0; + return false; + } + } return true; } diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index d42cd1d03..752951b56 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -1349,7 +1349,15 @@ parse_ntb: "Parsed NTB with %d frames\n", dgram_counter); to_process -= block_len; - if (to_process != 0) { + + /* + * Windows NCM driver avoids USB ZLPs by adding a 1-byte + * zero pad as needed. + */ + if (to_process == 1 && + (*(unsigned char *)(ntb_ptr + block_len) == 0x00)) { + to_process--; + } else if ((to_process > 0) && (block_len != 0)) { ntb_ptr = (unsigned char *)(ntb_ptr + block_len); goto parse_ntb; } diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 7b3c0787d..e80aa717c 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -273,7 +273,9 @@ int usb_ep_queue(struct usb_ep *ep, { int ret = 0; - if (WARN_ON_ONCE(!ep->enabled && ep->address)) { + if (!ep->enabled && ep->address) { + pr_debug("USB gadget: queue request to disabled ep 0x%x (%s)\n", + ep->address, ep->name); ret = -ESHUTDOWN; goto out; } diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c index 23a735641..8c56efe6a 100644 --- a/drivers/usb/gadget/udc/net2272.c +++ b/drivers/usb/gadget/udc/net2272.c @@ -2636,7 +2636,7 @@ net2272_plat_probe(struct platform_device *pdev) goto err_req; } - ret = net2272_probe_fin(dev, IRQF_TRIGGER_LOW); + ret = net2272_probe_fin(dev, irqflags); if (ret) goto err_io; diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c index c5f0fbb8f..9d3e36c86 100644 --- a/drivers/usb/gadget/udc/tegra-xudc.c +++ b/drivers/usb/gadget/udc/tegra-xudc.c @@ -3480,8 +3480,8 @@ static void tegra_xudc_device_params_init(struct tegra_xudc *xudc) static int tegra_xudc_phy_get(struct tegra_xudc *xudc) { - int err = 0, usb3; - unsigned int i; + int err = 0, usb3_companion_port; + unsigned int i, j; xudc->utmi_phy = devm_kcalloc(xudc->dev, xudc->soc->num_phys, sizeof(*xudc->utmi_phy), GFP_KERNEL); @@ -3508,10 +3508,8 @@ static int tegra_xudc_phy_get(struct tegra_xudc *xudc) xudc->utmi_phy[i] = devm_phy_optional_get(xudc->dev, phy_name); if (IS_ERR(xudc->utmi_phy[i])) { err = PTR_ERR(xudc->utmi_phy[i]); - if (err != -EPROBE_DEFER) - dev_err(xudc->dev, "failed to get usb2-%d PHY: %d\n", - i, err); - + dev_err_probe(xudc->dev, err, + "failed to get PHY for phy-name usb2-%d\n", i); goto clean_up; } else if (xudc->utmi_phy[i]) { /* Get usb-phy, if utmi phy is available */ @@ -3530,21 +3528,30 @@ static int tegra_xudc_phy_get(struct tegra_xudc *xudc) } /* Get USB3 phy */ - usb3 = tegra_xusb_padctl_get_usb3_companion(xudc->padctl, i); - if (usb3 < 0) + usb3_companion_port = tegra_xusb_padctl_get_usb3_companion(xudc->padctl, i); + if (usb3_companion_port < 0) continue; - snprintf(phy_name, sizeof(phy_name), "usb3-%d", usb3); - xudc->usb3_phy[i] = devm_phy_optional_get(xudc->dev, phy_name); - if (IS_ERR(xudc->usb3_phy[i])) { - err = PTR_ERR(xudc->usb3_phy[i]); - if (err != -EPROBE_DEFER) - dev_err(xudc->dev, "failed to get usb3-%d PHY: %d\n", - usb3, err); - - goto clean_up; - } else if (xudc->usb3_phy[i]) - dev_dbg(xudc->dev, "usb3-%d PHY registered", usb3); + for (j = 0; j < xudc->soc->num_phys; j++) { + snprintf(phy_name, sizeof(phy_name), "usb3-%d", j); + xudc->usb3_phy[i] = devm_phy_optional_get(xudc->dev, phy_name); + if (IS_ERR(xudc->usb3_phy[i])) { + err = PTR_ERR(xudc->usb3_phy[i]); + dev_err_probe(xudc->dev, err, + "failed to get PHY for phy-name usb3-%d\n", j); + goto clean_up; + } else if (xudc->usb3_phy[i]) { + int usb2_port = + tegra_xusb_padctl_get_port_number(xudc->utmi_phy[i]); + int usb3_port = + tegra_xusb_padctl_get_port_number(xudc->usb3_phy[i]); + if (usb3_port == usb3_companion_port) { + dev_dbg(xudc->dev, "USB2 port %d is paired with USB3 port %d for device mode port %d\n", + usb2_port, usb3_port, i); + break; + } + } + } } return err; @@ -3781,9 +3788,7 @@ static int tegra_xudc_probe(struct platform_device *pdev) err = devm_clk_bulk_get(&pdev->dev, xudc->soc->num_clks, xudc->clks); if (err) { - if (err != -EPROBE_DEFER) - dev_err(xudc->dev, "failed to request clocks: %d\n", err); - + dev_err_probe(xudc->dev, err, "failed to request clocks\n"); return err; } @@ -3798,9 +3803,7 @@ static int tegra_xudc_probe(struct platform_device *pdev) err = devm_regulator_bulk_get(&pdev->dev, xudc->soc->num_supplies, xudc->supplies); if (err) { - if (err != -EPROBE_DEFER) - dev_err(xudc->dev, "failed to request regulators: %d\n", err); - + dev_err_probe(xudc->dev, err, "failed to request regulators\n"); return err; } diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c index 9465fce99..f803079a9 100644 --- a/drivers/usb/host/sl811-hcd.c +++ b/drivers/usb/host/sl811-hcd.c @@ -585,6 +585,7 @@ done(struct sl811 *sl811, struct sl811h_ep *ep, u8 bank) finish_request(sl811, ep, urb, urbstat); } +#ifdef QUIRK2 static inline u8 checkdone(struct sl811 *sl811) { u8 ctl; @@ -616,6 +617,7 @@ static inline u8 checkdone(struct sl811 *sl811) #endif return irqstat; } +#endif static irqreturn_t sl811h_irq(struct usb_hcd *hcd) { diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index e56a1fb97..83c7dffa9 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -323,6 +323,9 @@ static int xhci_plat_probe(struct platform_device *pdev) if (device_property_read_bool(tmpdev, "quirk-broken-port-ped")) xhci->quirks |= XHCI_BROKEN_PORT_PED; + if (device_property_read_bool(tmpdev, "xhci-sg-trb-cache-size-quirk")) + xhci->quirks |= XHCI_SG_TRB_CACHE_SIZE_QUIRK; + device_property_read_u32(tmpdev, "imod-interval-ns", &xhci->imod_interval); } diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index eb70f07e3..4fa387e44 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -2059,16 +2059,13 @@ int xhci_is_vendor_info_code(struct xhci_hcd *xhci, unsigned int trb_comp_code) return 0; } -static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td, - struct xhci_transfer_event *event, struct xhci_virt_ep *ep) +static int finish_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, + struct xhci_ring *ep_ring, struct xhci_td *td, + u32 trb_comp_code) { struct xhci_ep_ctx *ep_ctx; - struct xhci_ring *ep_ring; - u32 trb_comp_code; - ep_ring = xhci_dma_to_transfer_ring(ep, le64_to_cpu(event->buffer)); ep_ctx = xhci_get_ep_ctx(xhci, ep->vdev->out_ctx, ep->ep_index); - trb_comp_code = GET_COMP_CODE(le32_to_cpu(event->transfer_len)); if (trb_comp_code == COMP_STOPPED_LENGTH_INVALID || trb_comp_code == COMP_STOPPED || @@ -2099,8 +2096,9 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_td *td, EP_HARD_RESET); } else { /* Update ring dequeue pointer */ - while (ep_ring->dequeue != td->last_trb) - inc_deq(xhci, ep_ring); + ep_ring->dequeue = td->last_trb; + ep_ring->deq_seg = td->last_trb_seg; + ep_ring->num_trbs_free += td->num_trbs - 1; inc_deq(xhci, ep_ring); } @@ -2125,9 +2123,9 @@ static int sum_trb_lengths(struct xhci_hcd *xhci, struct xhci_ring *ring, /* * Process control tds, update urb status and actual_length. */ -static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td, - union xhci_trb *ep_trb, struct xhci_transfer_event *event, - struct xhci_virt_ep *ep) +static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, + struct xhci_ring *ep_ring, struct xhci_td *td, + union xhci_trb *ep_trb, struct xhci_transfer_event *event) { struct xhci_ep_ctx *ep_ctx; u32 trb_comp_code; @@ -2215,15 +2213,15 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td, td->urb->actual_length = requested; finish_td: - return finish_td(xhci, td, event, ep); + return finish_td(xhci, ep, ep_ring, td, trb_comp_code); } /* * Process isochronous tds, update urb packet status and actual_length. */ -static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, - union xhci_trb *ep_trb, struct xhci_transfer_event *event, - struct xhci_virt_ep *ep) +static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, + struct xhci_ring *ep_ring, struct xhci_td *td, + union xhci_trb *ep_trb, struct xhci_transfer_event *event) { struct urb_priv *urb_priv; int idx; @@ -2246,6 +2244,9 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, /* handle completion code */ switch (trb_comp_code) { case COMP_SUCCESS: + /* Don't overwrite status if TD had an error, see xHCI 4.9.1 */ + if (td->error_mid_td) + break; if (remaining) { frame->status = short_framestatus; if (xhci->quirks & XHCI_TRUST_TX_LENGTH) @@ -2261,9 +2262,13 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, case COMP_BANDWIDTH_OVERRUN_ERROR: frame->status = -ECOMM; break; - case COMP_ISOCH_BUFFER_OVERRUN: case COMP_BABBLE_DETECTED_ERROR: + sum_trbs_for_length = true; + fallthrough; + case COMP_ISOCH_BUFFER_OVERRUN: frame->status = -EOVERFLOW; + if (ep_trb != td->last_trb) + td->error_mid_td = true; break; case COMP_INCOMPATIBLE_DEVICE_ERROR: case COMP_STALL_ERROR: @@ -2271,8 +2276,9 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, break; case COMP_USB_TRANSACTION_ERROR: frame->status = -EPROTO; + sum_trbs_for_length = true; if (ep_trb != td->last_trb) - return 0; + td->error_mid_td = true; break; case COMP_STOPPED: sum_trbs_for_length = true; @@ -2292,6 +2298,9 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, break; } + if (td->urb_length_set) + goto finish_td; + if (sum_trbs_for_length) frame->actual_length = sum_trb_lengths(xhci, ep->ring, ep_trb) + ep_trb_len - remaining; @@ -2300,7 +2309,15 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, td->urb->actual_length += frame->actual_length; - return finish_td(xhci, td, event, ep); +finish_td: + /* Don't give back TD yet if we encountered an error mid TD */ + if (td->error_mid_td && ep_trb != td->last_trb) { + xhci_dbg(xhci, "Error mid isoc TD, wait for final completion event\n"); + td->urb_length_set = true; + return 0; + } + + return finish_td(xhci, ep, ep_ring, td, trb_comp_code); } static int skip_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, @@ -2321,8 +2338,9 @@ static int skip_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, frame->actual_length = 0; /* Update ring dequeue pointer */ - while (ep->ring->dequeue != td->last_trb) - inc_deq(xhci, ep->ring); + ep->ring->dequeue = td->last_trb; + ep->ring->deq_seg = td->last_trb_seg; + ep->ring->num_trbs_free += td->num_trbs - 1; inc_deq(xhci, ep->ring); return xhci_td_cleanup(xhci, td, ep->ring, status); @@ -2331,17 +2349,15 @@ static int skip_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, /* * Process bulk and interrupt tds, update urb status and actual_length. */ -static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, - union xhci_trb *ep_trb, struct xhci_transfer_event *event, - struct xhci_virt_ep *ep) +static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, + struct xhci_ring *ep_ring, struct xhci_td *td, + union xhci_trb *ep_trb, struct xhci_transfer_event *event) { struct xhci_slot_ctx *slot_ctx; - struct xhci_ring *ep_ring; u32 trb_comp_code; u32 remaining, requested, ep_trb_len; slot_ctx = xhci_get_slot_ctx(xhci, ep->vdev->out_ctx); - ep_ring = xhci_dma_to_transfer_ring(ep, le64_to_cpu(event->buffer)); trb_comp_code = GET_COMP_CODE(le32_to_cpu(event->transfer_len)); remaining = EVENT_TRB_LEN(le32_to_cpu(event->transfer_len)); ep_trb_len = TRB_LEN(le32_to_cpu(ep_trb->generic.field[2])); @@ -2401,7 +2417,8 @@ finish_td: remaining); td->urb->actual_length = 0; } - return finish_td(xhci, td, event, ep); + + return finish_td(xhci, ep, ep_ring, td, trb_comp_code); } /* @@ -2686,17 +2703,51 @@ static int handle_tx_event(struct xhci_hcd *xhci, } if (!ep_seg) { - if (!ep->skip || - !usb_endpoint_xfer_isoc(&td->urb->ep->desc)) { - /* Some host controllers give a spurious - * successful event after a short transfer. - * Ignore it. - */ - if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) && - ep_ring->last_td_was_short) { - ep_ring->last_td_was_short = false; - goto cleanup; + + if (ep->skip && usb_endpoint_xfer_isoc(&td->urb->ep->desc)) { + skip_isoc_td(xhci, td, ep, status); + goto cleanup; + } + + /* + * Some hosts give a spurious success event after a short + * transfer. Ignore it. + */ + if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) && + ep_ring->last_td_was_short) { + ep_ring->last_td_was_short = false; + goto cleanup; + } + + /* + * xhci 4.10.2 states isoc endpoints should continue + * processing the next TD if there was an error mid TD. + * So host like NEC don't generate an event for the last + * isoc TRB even if the IOC flag is set. + * xhci 4.9.1 states that if there are errors in mult-TRB + * TDs xHC should generate an error for that TRB, and if xHC + * proceeds to the next TD it should genete an event for + * any TRB with IOC flag on the way. Other host follow this. + * So this event might be for the next TD. + */ + if (td->error_mid_td && + !list_is_last(&td->td_list, &ep_ring->td_list)) { + struct xhci_td *td_next = list_next_entry(td, td_list); + + ep_seg = trb_in_td(xhci, td_next->start_seg, td_next->first_trb, + td_next->last_trb, ep_trb_dma, false); + if (ep_seg) { + /* give back previous TD, start handling new */ + xhci_dbg(xhci, "Missing TD completion event after mid TD error\n"); + ep_ring->dequeue = td->last_trb; + ep_ring->deq_seg = td->last_trb_seg; + inc_deq(xhci, ep_ring); + xhci_td_cleanup(xhci, td, ep_ring, td->status); + td = td_next; } + } + + if (!ep_seg) { /* HC is busted, give up! */ xhci_err(xhci, "ERROR Transfer event TRB DMA ptr not " @@ -2708,9 +2759,6 @@ static int handle_tx_event(struct xhci_hcd *xhci, ep_trb_dma, true); return -ESHUTDOWN; } - - skip_isoc_td(xhci, td, ep, status); - goto cleanup; } if (trb_comp_code == COMP_SHORT_PACKET) ep_ring->last_td_was_short = true; @@ -2752,11 +2800,11 @@ static int handle_tx_event(struct xhci_hcd *xhci, /* update the urb's actual_length and give back to the core */ if (usb_endpoint_xfer_control(&td->urb->ep->desc)) - process_ctrl_td(xhci, td, ep_trb, event, ep); + process_ctrl_td(xhci, ep, ep_ring, td, ep_trb, event); else if (usb_endpoint_xfer_isoc(&td->urb->ep->desc)) - process_isoc_td(xhci, td, ep_trb, event, ep); + process_isoc_td(xhci, ep, ep_ring, td, ep_trb, event); else - process_bulk_intr_td(xhci, td, ep_trb, event, ep); + process_bulk_intr_td(xhci, ep, ep_ring, td, ep_trb, event); cleanup: handling_skipped_tds = ep->skip && trb_comp_code != COMP_MISSED_SERVICE_ERROR && @@ -3487,7 +3535,7 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags, field |= TRB_IOC; more_trbs_coming = false; td->last_trb = ring->enqueue; - + td->last_trb_seg = ring->enq_seg; if (xhci_urb_suitable_for_idt(urb)) { memcpy(&send_addr, urb->transfer_buffer, trb_buff_len); @@ -3513,7 +3561,7 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags, upper_32_bits(send_addr), length_field, field); - + td->num_trbs++; addr += trb_buff_len; sent_len = trb_buff_len; @@ -3537,8 +3585,10 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags, ep_index, urb->stream_id, 1, urb, 1, mem_flags); urb_priv->td[1].last_trb = ring->enqueue; + urb_priv->td[1].last_trb_seg = ring->enq_seg; field = TRB_TYPE(TRB_NORMAL) | ring->cycle_state | TRB_IOC; queue_trb(xhci, ring, 0, 0, 0, TRB_INTR_TARGET(0), field); + urb_priv->td[1].num_trbs++; } check_trb_math(urb, enqd_len); @@ -3589,6 +3639,7 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags, urb_priv = urb->hcpriv; td = &urb_priv->td[0]; + td->num_trbs = num_trbs; /* * Don't give the first TRB to the hardware (by toggling the cycle bit) @@ -3661,6 +3712,7 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags, /* Save the DMA address of the last TRB in the TD */ td->last_trb = ep_ring->enqueue; + td->last_trb_seg = ep_ring->enq_seg; /* Queue status TRB - see Table 7 and sections 4.11.2.2 and 6.4.1.2.3 */ /* If the device sent data, the status stage is an OUT transfer */ @@ -3905,7 +3957,7 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags, goto cleanup; } td = &urb_priv->td[i]; - + td->num_trbs = trbs_per_td; /* use SIA as default, if frame id is used overwrite it */ sia_frame_id = TRB_SIA; if (!(urb->transfer_flags & URB_ISO_ASAP) && @@ -3948,6 +4000,7 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags, } else { more_trbs_coming = false; td->last_trb = ep_ring->enqueue; + td->last_trb_seg = ep_ring->enq_seg; field |= TRB_IOC; if (trb_block_event_intr(xhci, num_tds, i)) field |= TRB_BEI; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index bb3c362a1..5a8443f6e 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1550,9 +1550,12 @@ struct xhci_td { struct xhci_segment *start_seg; union xhci_trb *first_trb; union xhci_trb *last_trb; + struct xhci_segment *last_trb_seg; struct xhci_segment *bounce_seg; /* actual_length of the URB has already been set */ bool urb_length_set; + bool error_mid_td; + unsigned int num_trbs; }; /* xHCI command default timeout value */ diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c index 34b9f8140..661a229c1 100644 --- a/drivers/usb/phy/phy-generic.c +++ b/drivers/usb/phy/phy-generic.c @@ -268,13 +268,6 @@ int usb_phy_gen_create_phy(struct device *dev, struct usb_phy_generic *nop) return -EPROBE_DEFER; } - nop->vbus_draw = devm_regulator_get_exclusive(dev, "vbus"); - if (PTR_ERR(nop->vbus_draw) == -ENODEV) - nop->vbus_draw = NULL; - if (IS_ERR(nop->vbus_draw)) - return dev_err_probe(dev, PTR_ERR(nop->vbus_draw), - "could not get vbus regulator\n"); - nop->dev = dev; nop->phy.dev = nop->dev; nop->phy.label = "nop-xceiv"; diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index 5cc202753..e1dff4a44 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -19,7 +19,9 @@ static struct class *role_class; struct usb_role_switch { struct device dev; struct mutex lock; /* device lock*/ + struct module *module; /* the module this device depends on */ enum usb_role role; + bool registered; /* From descriptor */ struct device *usb2_port; @@ -46,6 +48,9 @@ int usb_role_switch_set_role(struct usb_role_switch *sw, enum usb_role role) if (IS_ERR_OR_NULL(sw)) return 0; + if (!sw->registered) + return -EOPNOTSUPP; + mutex_lock(&sw->lock); ret = sw->set(sw, role); @@ -71,7 +76,7 @@ enum usb_role usb_role_switch_get_role(struct usb_role_switch *sw) { enum usb_role role; - if (IS_ERR_OR_NULL(sw)) + if (IS_ERR_OR_NULL(sw) || !sw->registered) return USB_ROLE_NONE; mutex_lock(&sw->lock); @@ -133,7 +138,7 @@ struct usb_role_switch *usb_role_switch_get(struct device *dev) usb_role_switch_match); if (!IS_ERR_OR_NULL(sw)) - WARN_ON(!try_module_get(sw->dev.parent->driver->owner)); + WARN_ON(!try_module_get(sw->module)); return sw; } @@ -155,7 +160,7 @@ struct usb_role_switch *fwnode_usb_role_switch_get(struct fwnode_handle *fwnode) sw = fwnode_connection_find_match(fwnode, "usb-role-switch", NULL, usb_role_switch_match); if (!IS_ERR_OR_NULL(sw)) - WARN_ON(!try_module_get(sw->dev.parent->driver->owner)); + WARN_ON(!try_module_get(sw->module)); return sw; } @@ -170,7 +175,7 @@ EXPORT_SYMBOL_GPL(fwnode_usb_role_switch_get); void usb_role_switch_put(struct usb_role_switch *sw) { if (!IS_ERR_OR_NULL(sw)) { - module_put(sw->dev.parent->driver->owner); + module_put(sw->module); put_device(&sw->dev); } } @@ -187,15 +192,18 @@ struct usb_role_switch * usb_role_switch_find_by_fwnode(const struct fwnode_handle *fwnode) { struct device *dev; + struct usb_role_switch *sw = NULL; if (!fwnode) return NULL; dev = class_find_device_by_fwnode(role_class, fwnode); - if (dev) - WARN_ON(!try_module_get(dev->parent->driver->owner)); + if (dev) { + sw = to_role_switch(dev); + WARN_ON(!try_module_get(sw->module)); + } - return dev ? to_role_switch(dev) : NULL; + return sw; } EXPORT_SYMBOL_GPL(usb_role_switch_find_by_fwnode); @@ -328,6 +336,7 @@ usb_role_switch_register(struct device *parent, sw->set = desc->set; sw->get = desc->get; + sw->module = parent->driver->owner; sw->dev.parent = parent; sw->dev.fwnode = desc->fwnode; sw->dev.class = role_class; @@ -342,6 +351,8 @@ usb_role_switch_register(struct device *parent, return ERR_PTR(ret); } + sw->registered = true; + /* TODO: Symlinks for the host port and the device controller. */ return sw; @@ -356,8 +367,10 @@ EXPORT_SYMBOL_GPL(usb_role_switch_register); */ void usb_role_switch_unregister(struct usb_role_switch *sw) { - if (!IS_ERR_OR_NULL(sw)) + if (!IS_ERR_OR_NULL(sw)) { + sw->registered = false; device_unregister(&sw->dev); + } } EXPORT_SYMBOL_GPL(usb_role_switch_unregister); diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 045e24174..294f7f016 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -60,6 +60,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x0471, 0x066A) }, /* AKTAKOM ACE-1001 cable */ { USB_DEVICE(0x0489, 0xE000) }, /* Pirelli Broadband S.p.A, DP-L10 SIP/GSM Mobile */ { USB_DEVICE(0x0489, 0xE003) }, /* Pirelli Broadband S.p.A, DP-L10 SIP/GSM Mobile */ + { USB_DEVICE(0x04BF, 0x1301) }, /* TDK Corporation NC0110013M - Network Controller */ + { USB_DEVICE(0x04BF, 0x1303) }, /* TDK Corporation MM0110113M - i3 Micro Module */ { USB_DEVICE(0x0745, 0x1000) }, /* CipherLab USB CCD Barcode Scanner 1000 */ { USB_DEVICE(0x0846, 0x1100) }, /* NetGear Managed Switch M4100 series, M5300 series, M7100 series */ { USB_DEVICE(0x08e6, 0x5501) }, /* Gemalto Prox-PU/CU contactless smartcard reader */ @@ -148,8 +150,10 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x85EA) }, /* AC-Services IBUS-IF */ { USB_DEVICE(0x10C4, 0x85EB) }, /* AC-Services CIS-IBUS */ { USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */ + { USB_DEVICE(0x10C4, 0x863C) }, /* MGP Instruments PDS100 */ { USB_DEVICE(0x10C4, 0x8664) }, /* AC-Services CAN-IF */ { USB_DEVICE(0x10C4, 0x8665) }, /* AC-Services OBD-IF */ + { USB_DEVICE(0x10C4, 0x87ED) }, /* IMST USB-Stick for Smart Meter */ { USB_DEVICE(0x10C4, 0x8856) }, /* CEL EM357 ZigBee USB Stick - LR */ { USB_DEVICE(0x10C4, 0x8857) }, /* CEL EM357 ZigBee USB Stick */ { USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */ @@ -180,6 +184,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0xF004) }, /* Elan Digital Systems USBcount50 */ { USB_DEVICE(0x10C5, 0xEA61) }, /* Silicon Labs MobiData GPRS USB Modem */ { USB_DEVICE(0x10CE, 0xEA6A) }, /* Silicon Labs MobiData GPRS USB Modem 100EU */ + { USB_DEVICE(0x11CA, 0x0212) }, /* Verifone USB to Printer (UART, CP2102) */ { USB_DEVICE(0x12B8, 0xEC60) }, /* Link G4 ECU */ { USB_DEVICE(0x12B8, 0xEC62) }, /* Link G4+ ECU */ { USB_DEVICE(0x13AD, 0x9999) }, /* Baltech card reader */ diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 4d7f4a4ab..66aa999ef 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1055,6 +1055,8 @@ static const struct usb_device_id id_table_combined[] = { .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(FTDI_VID, FTDI_FALCONIA_JTAG_UNBUF_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + /* GMC devices */ + { USB_DEVICE(GMC_VID, GMC_Z216C_PID) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 9a0f9fc99..b2aec1106 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -1599,3 +1599,9 @@ #define UBLOX_VID 0x1546 #define UBLOX_C099F9P_ZED_PID 0x0502 #define UBLOX_C099F9P_ODIN_PID 0x0503 + +/* + * GMC devices + */ +#define GMC_VID 0x1cd7 +#define GMC_Z216C_PID 0x0217 /* GMC Z216C Adapter IR-USB */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 6be7358ca..400e3e10b 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -255,6 +255,10 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EM061K_LMS 0x0124 #define QUECTEL_PRODUCT_EC25 0x0125 #define QUECTEL_PRODUCT_EM060K_128 0x0128 +#define QUECTEL_PRODUCT_EM060K_129 0x0129 +#define QUECTEL_PRODUCT_EM060K_12a 0x012a +#define QUECTEL_PRODUCT_EM060K_12b 0x012b +#define QUECTEL_PRODUCT_EM060K_12c 0x012c #define QUECTEL_PRODUCT_EG91 0x0191 #define QUECTEL_PRODUCT_EG95 0x0195 #define QUECTEL_PRODUCT_BG96 0x0296 @@ -613,6 +617,11 @@ static void option_instat_callback(struct urb *urb); /* Luat Air72*U series based on UNISOC UIS8910 uses UNISOC's vendor ID */ #define LUAT_PRODUCT_AIR720U 0x4e00 +/* MeiG Smart Technology products */ +#define MEIGSMART_VENDOR_ID 0x2dee +/* MeiG Smart SLM320 based on UNISOC UIS8910 */ +#define MEIGSMART_PRODUCT_SLM320 0x4d41 + /* Device flags */ /* Highest interface number which can be used with NCTRL() and RSVD() */ @@ -1213,6 +1222,18 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_128, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_128, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_128, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_129, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_129, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_129, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12a, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12a, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12a, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12b, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12b, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12b, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12c, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12c, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12c, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0xff, 0x40) }, @@ -1355,6 +1376,12 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1083, 0xff), /* Telit FE990 (ECM) */ .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a0, 0xff), /* Telit FN20C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a4, 0xff), /* Telit FN20C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a9, 0xff), /* Telit FN20C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), @@ -2047,6 +2074,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, 0x9803, 0xff), .driver_info = RSVD(4) }, + { USB_DEVICE(LONGCHEER_VENDOR_ID, 0x9b05), /* Longsung U8300 */ + .driver_info = RSVD(4) | RSVD(5) }, + { USB_DEVICE(LONGCHEER_VENDOR_ID, 0x9b3c), /* Longsung U9300 */ + .driver_info = RSVD(0) | RSVD(4) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, ZOOM_PRODUCT_4597) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, IBALL_3_5G_CONNECT) }, { USB_DEVICE(HAIER_VENDOR_ID, HAIER_PRODUCT_CE100) }, @@ -2267,20 +2298,36 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0xff, 0x30) }, /* Fibocom FG150 Diag */ { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0, 0) }, /* Fibocom FG150 AT */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0111, 0xff) }, /* Fibocom FM160 (MBIM mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0115, 0xff), /* Fibocom FM135 (laptop MBIM) */ + .driver_info = RSVD(5) }, { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a3, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff), /* Fibocom FM101-GL (laptop MBIM) */ .driver_info = RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a04, 0xff) }, /* Fibocom FM650-CN (ECM mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a05, 0xff) }, /* Fibocom FM650-CN (NCM mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a06, 0xff) }, /* Fibocom FM650-CN (RNDIS mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a07, 0xff) }, /* Fibocom FM650-CN (MBIM mode) */ { USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) }, /* LongSung M5710 */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) }, /* GosunCn GM500 RNDIS */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) }, /* GosunCn GM500 MBIM */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1406, 0xff) }, /* GosunCn GM500 ECM/NCM */ + { USB_DEVICE(0x33f8, 0x0104), /* Rolling RW101-GL (laptop RMNET) */ + .driver_info = RSVD(4) | RSVD(5) }, + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x01a2, 0xff) }, /* Rolling RW101-GL (laptop MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x01a3, 0xff) }, /* Rolling RW101-GL (laptop MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x01a4, 0xff), /* Rolling RW101-GL (laptop MBIM) */ + .driver_info = RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x0115, 0xff), /* Rolling RW135-GL (laptop MBIM) */ + .driver_info = RSVD(5) }, { USB_DEVICE_AND_INTERFACE_INFO(OPPO_VENDOR_ID, OPPO_PRODUCT_R11, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM320, 0xff, 0, 0) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index b1e844bf3..703a9c563 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -184,6 +184,8 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x413c, 0x81d0)}, /* Dell Wireless 5819 */ {DEVICE_SWI(0x413c, 0x81d1)}, /* Dell Wireless 5818 */ {DEVICE_SWI(0x413c, 0x81d2)}, /* Dell Wireless 5818 */ + {DEVICE_SWI(0x413c, 0x8217)}, /* Dell Wireless DW5826e */ + {DEVICE_SWI(0x413c, 0x8218)}, /* Dell Wireless DW5826e QDL */ /* Huawei devices */ {DEVICE_HWI(0x03f0, 0x581d)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */ diff --git a/drivers/usb/storage/isd200.c b/drivers/usb/storage/isd200.c index 3c76336e4..1d22db59f 100644 --- a/drivers/usb/storage/isd200.c +++ b/drivers/usb/storage/isd200.c @@ -1105,7 +1105,7 @@ static void isd200_dump_driveid(struct us_data *us, u16 *id) static int isd200_get_inquiry_data( struct us_data *us ) { struct isd200_info *info = (struct isd200_info *)us->extra; - int retStatus = ISD200_GOOD; + int retStatus; u16 *id = info->id; usb_stor_dbg(us, "Entering isd200_get_inquiry_data\n"); @@ -1137,6 +1137,13 @@ static int isd200_get_inquiry_data( struct us_data *us ) isd200_fix_driveid(id); isd200_dump_driveid(us, id); + /* Prevent division by 0 in isd200_scsi_to_ata() */ + if (id[ATA_ID_HEADS] == 0 || id[ATA_ID_SECTORS] == 0) { + usb_stor_dbg(us, " Invalid ATA Identify data\n"); + retStatus = ISD200_ERROR; + goto Done; + } + memset(&info->InquiryData, 0, sizeof(info->InquiryData)); /* Standard IDE interface only supports disks */ @@ -1202,6 +1209,7 @@ static int isd200_get_inquiry_data( struct us_data *us ) } } + Done: usb_stor_dbg(us, "Leaving isd200_get_inquiry_data %08X\n", retStatus); return(retStatus); @@ -1481,22 +1489,27 @@ static int isd200_init_info(struct us_data *us) static int isd200_Initialization(struct us_data *us) { + int rc = 0; + usb_stor_dbg(us, "ISD200 Initialization...\n"); /* Initialize ISD200 info struct */ - if (isd200_init_info(us) == ISD200_ERROR) { + if (isd200_init_info(us) < 0) { usb_stor_dbg(us, "ERROR Initializing ISD200 Info struct\n"); + rc = -ENOMEM; } else { /* Get device specific data */ - if (isd200_get_inquiry_data(us) != ISD200_GOOD) + if (isd200_get_inquiry_data(us) != ISD200_GOOD) { usb_stor_dbg(us, "ISD200 Initialization Failure\n"); - else + rc = -EINVAL; + } else { usb_stor_dbg(us, "ISD200 Initialization complete\n"); + } } - return 0; + return rc; } diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index e34e46df8..33c67adf7 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -732,6 +732,7 @@ MODULE_DEVICE_TABLE(i2c, tcpci_id); #ifdef CONFIG_OF static const struct of_device_id tcpci_of_match[] = { { .compatible = "nxp,ptn5110", }, + { .compatible = "tcpci", }, {}, }; MODULE_DEVICE_TABLE(of, tcpci_of_match); diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index cd3689005..2ddc8936a 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -138,8 +138,12 @@ static int ucsi_exec_command(struct ucsi *ucsi, u64 cmd) if (!(cci & UCSI_CCI_COMMAND_COMPLETE)) return -EIO; - if (cci & UCSI_CCI_NOT_SUPPORTED) + if (cci & UCSI_CCI_NOT_SUPPORTED) { + if (ucsi_acknowledge_command(ucsi) < 0) + dev_err(ucsi->dev, + "ACK of unsupported command failed\n"); return -EOPNOTSUPP; + } if (cci & UCSI_CCI_ERROR) { if (cmd == UCSI_GET_ERROR_STATUS) @@ -848,13 +852,47 @@ static int ucsi_reset_connector(struct ucsi_connector *con, bool hard) static int ucsi_reset_ppm(struct ucsi *ucsi) { - u64 command = UCSI_PPM_RESET; + u64 command; unsigned long tmo; u32 cci; int ret; mutex_lock(&ucsi->ppm_lock); + ret = ucsi->ops->read(ucsi, UCSI_CCI, &cci, sizeof(cci)); + if (ret < 0) + goto out; + + /* + * If UCSI_CCI_RESET_COMPLETE is already set we must clear + * the flag before we start another reset. Send a + * UCSI_SET_NOTIFICATION_ENABLE command to achieve this. + * Ignore a timeout and try the reset anyway if this fails. + */ + if (cci & UCSI_CCI_RESET_COMPLETE) { + command = UCSI_SET_NOTIFICATION_ENABLE; + ret = ucsi->ops->async_write(ucsi, UCSI_CONTROL, &command, + sizeof(command)); + if (ret < 0) + goto out; + + tmo = jiffies + msecs_to_jiffies(UCSI_TIMEOUT_MS); + do { + ret = ucsi->ops->read(ucsi, UCSI_CCI, + &cci, sizeof(cci)); + if (ret < 0) + goto out; + if (cci & UCSI_CCI_COMMAND_COMPLETE) + break; + if (time_is_before_jiffies(tmo)) + break; + msleep(20); + } while (1); + + WARN_ON(cci & UCSI_CCI_RESET_COMPLETE); + } + + command = UCSI_PPM_RESET; ret = ucsi->ops->async_write(ucsi, UCSI_CONTROL, &command, sizeof(command)); if (ret < 0) diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index fce23ad16..41e1a64da 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -219,12 +219,12 @@ struct ucsi_cable_property { #define UCSI_CABLE_PROP_FLAG_VBUS_IN_CABLE BIT(0) #define UCSI_CABLE_PROP_FLAG_ACTIVE_CABLE BIT(1) #define UCSI_CABLE_PROP_FLAG_DIRECTIONALITY BIT(2) -#define UCSI_CABLE_PROP_FLAG_PLUG_TYPE(_f_) ((_f_) & GENMASK(3, 0)) +#define UCSI_CABLE_PROP_FLAG_PLUG_TYPE(_f_) (((_f_) & GENMASK(4, 3)) >> 3) #define UCSI_CABLE_PROPERTY_PLUG_TYPE_A 0 #define UCSI_CABLE_PROPERTY_PLUG_TYPE_B 1 #define UCSI_CABLE_PROPERTY_PLUG_TYPE_C 2 #define UCSI_CABLE_PROPERTY_PLUG_OTHER 3 -#define UCSI_CABLE_PROP_MODE_SUPPORT BIT(5) +#define UCSI_CABLE_PROP_FLAG_MODE_SUPPORT BIT(5) u8 latency; } __packed; diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c index 04976435a..0c88d5bf0 100644 --- a/drivers/usb/typec/ucsi/ucsi_acpi.c +++ b/drivers/usb/typec/ucsi/ucsi_acpi.c @@ -70,9 +70,13 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset, const void *val, size_t val_len) { struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi); + bool ack = UCSI_COMMAND(*(u64 *)val) == UCSI_ACK_CC_CI; int ret; - set_bit(COMMAND_PENDING, &ua->flags); + if (ack) + set_bit(ACK_PENDING, &ua->flags); + else + set_bit(COMMAND_PENDING, &ua->flags); ret = ucsi_acpi_async_write(ucsi, offset, val, val_len); if (ret) @@ -82,7 +86,10 @@ static int ucsi_acpi_sync_write(struct ucsi *ucsi, unsigned int offset, ret = -ETIMEDOUT; out_clear_bit: - clear_bit(COMMAND_PENDING, &ua->flags); + if (ack) + clear_bit(ACK_PENDING, &ua->flags); + else + clear_bit(COMMAND_PENDING, &ua->flags); return ret; } @@ -106,8 +113,10 @@ static void ucsi_acpi_notify(acpi_handle handle, u32 event, void *data) if (UCSI_CCI_CONNECTOR(cci)) ucsi_connector_change(ua->ucsi, UCSI_CCI_CONNECTOR(cci)); - if (test_bit(COMMAND_PENDING, &ua->flags) && - cci & (UCSI_CCI_ACK_COMPLETE | UCSI_CCI_COMMAND_COMPLETE)) + if (cci & UCSI_CCI_ACK_COMPLETE && test_bit(ACK_PENDING, &ua->flags)) + complete(&ua->complete); + if (cci & UCSI_CCI_COMMAND_COMPLETE && + test_bit(COMMAND_PENDING, &ua->flags)) complete(&ua->complete); } diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c index 0d9f3002d..86f770e6d 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c @@ -142,13 +142,14 @@ static int vfio_fsl_mc_set_irq_trigger(struct vfio_fsl_mc_device *vdev, irq = &vdev->mc_irqs[index]; if (flags & VFIO_IRQ_SET_DATA_NONE) { - vfio_fsl_mc_irq_handler(hwirq, irq); + if (irq->trigger) + eventfd_signal(irq->trigger, 1); } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { u8 trigger = *(u8 *)data; - if (trigger) - vfio_fsl_mc_irq_handler(hwirq, irq); + if (trigger && irq->trigger) + eventfd_signal(irq->trigger, 1); } return 0; diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 869dce5f1..5b0b7fab3 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -29,15 +29,22 @@ static void vfio_send_intx_eventfd(void *opaque, void *unused) { struct vfio_pci_device *vdev = opaque; - if (likely(is_intx(vdev) && !vdev->virq_disabled)) - eventfd_signal(vdev->ctx[0].trigger, 1); + if (likely(is_intx(vdev) && !vdev->virq_disabled)) { + struct eventfd_ctx *trigger; + + trigger = READ_ONCE(vdev->ctx[0].trigger); + if (likely(trigger)) + eventfd_signal(trigger, 1); + } } -void vfio_pci_intx_mask(struct vfio_pci_device *vdev) +static void __vfio_pci_intx_mask(struct vfio_pci_device *vdev) { struct pci_dev *pdev = vdev->pdev; unsigned long flags; + lockdep_assert_held(&vdev->igate); + spin_lock_irqsave(&vdev->irqlock, flags); /* @@ -65,6 +72,13 @@ void vfio_pci_intx_mask(struct vfio_pci_device *vdev) spin_unlock_irqrestore(&vdev->irqlock, flags); } +void vfio_pci_intx_mask(struct vfio_pci_device *vdev) +{ + mutex_lock(&vdev->igate); + __vfio_pci_intx_mask(vdev); + mutex_unlock(&vdev->igate); +} + /* * If this is triggered by an eventfd, we can't call eventfd_signal * or else we'll deadlock on the eventfd wait queue. Return >0 when @@ -107,12 +121,21 @@ static int vfio_pci_intx_unmask_handler(void *opaque, void *unused) return ret; } -void vfio_pci_intx_unmask(struct vfio_pci_device *vdev) +static void __vfio_pci_intx_unmask(struct vfio_pci_device *vdev) { + lockdep_assert_held(&vdev->igate); + if (vfio_pci_intx_unmask_handler(vdev, NULL) > 0) vfio_send_intx_eventfd(vdev, NULL); } +void vfio_pci_intx_unmask(struct vfio_pci_device *vdev) +{ + mutex_lock(&vdev->igate); + __vfio_pci_intx_unmask(vdev); + mutex_unlock(&vdev->igate); +} + static irqreturn_t vfio_intx_handler(int irq, void *dev_id) { struct vfio_pci_device *vdev = dev_id; @@ -139,95 +162,104 @@ static irqreturn_t vfio_intx_handler(int irq, void *dev_id) return ret; } -static int vfio_intx_enable(struct vfio_pci_device *vdev) +static int vfio_intx_enable(struct vfio_pci_device *vdev, + struct eventfd_ctx *trigger) { + struct pci_dev *pdev = vdev->pdev; + unsigned long irqflags; + char *name; + int ret; + if (!is_irq_none(vdev)) return -EINVAL; - if (!vdev->pdev->irq) + if (!pdev->irq) return -ENODEV; + name = kasprintf(GFP_KERNEL, "vfio-intx(%s)", pci_name(pdev)); + if (!name) + return -ENOMEM; + vdev->ctx = kzalloc(sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL); if (!vdev->ctx) return -ENOMEM; vdev->num_ctx = 1; + vdev->ctx[0].name = name; + vdev->ctx[0].trigger = trigger; + /* - * If the virtual interrupt is masked, restore it. Devices - * supporting DisINTx can be masked at the hardware level - * here, non-PCI-2.3 devices will have to wait until the - * interrupt is enabled. + * Fill the initial masked state based on virq_disabled. After + * enable, changing the DisINTx bit in vconfig directly changes INTx + * masking. igate prevents races during setup, once running masked + * is protected via irqlock. + * + * Devices supporting DisINTx also reflect the current mask state in + * the physical DisINTx bit, which is not affected during IRQ setup. + * + * Devices without DisINTx support require an exclusive interrupt. + * IRQ masking is performed at the IRQ chip. Again, igate protects + * against races during setup and IRQ handlers and irqfds are not + * yet active, therefore masked is stable and can be used to + * conditionally auto-enable the IRQ. + * + * irq_type must be stable while the IRQ handler is registered, + * therefore it must be set before request_irq(). */ vdev->ctx[0].masked = vdev->virq_disabled; - if (vdev->pci_2_3) - pci_intx(vdev->pdev, !vdev->ctx[0].masked); + if (vdev->pci_2_3) { + pci_intx(pdev, !vdev->ctx[0].masked); + irqflags = IRQF_SHARED; + } else { + irqflags = vdev->ctx[0].masked ? IRQF_NO_AUTOEN : 0; + } vdev->irq_type = VFIO_PCI_INTX_IRQ_INDEX; + ret = request_irq(pdev->irq, vfio_intx_handler, + irqflags, vdev->ctx[0].name, vdev); + if (ret) { + vdev->irq_type = VFIO_PCI_NUM_IRQS; + kfree(name); + vdev->num_ctx = 0; + kfree(vdev->ctx); + return ret; + } + return 0; } -static int vfio_intx_set_signal(struct vfio_pci_device *vdev, int fd) +static int vfio_intx_set_signal(struct vfio_pci_device *vdev, + struct eventfd_ctx *trigger) { struct pci_dev *pdev = vdev->pdev; - unsigned long irqflags = IRQF_SHARED; - struct eventfd_ctx *trigger; - unsigned long flags; - int ret; + struct eventfd_ctx *old; - if (vdev->ctx[0].trigger) { - free_irq(pdev->irq, vdev); - kfree(vdev->ctx[0].name); - eventfd_ctx_put(vdev->ctx[0].trigger); - vdev->ctx[0].trigger = NULL; - } - - if (fd < 0) /* Disable only */ - return 0; - - vdev->ctx[0].name = kasprintf(GFP_KERNEL, "vfio-intx(%s)", - pci_name(pdev)); - if (!vdev->ctx[0].name) - return -ENOMEM; - - trigger = eventfd_ctx_fdget(fd); - if (IS_ERR(trigger)) { - kfree(vdev->ctx[0].name); - return PTR_ERR(trigger); - } - - vdev->ctx[0].trigger = trigger; + old = vdev->ctx[0].trigger; - if (!vdev->pci_2_3) - irqflags = 0; + WRITE_ONCE(vdev->ctx[0].trigger, trigger); - ret = request_irq(pdev->irq, vfio_intx_handler, - irqflags, vdev->ctx[0].name, vdev); - if (ret) { - vdev->ctx[0].trigger = NULL; - kfree(vdev->ctx[0].name); - eventfd_ctx_put(trigger); - return ret; + /* Releasing an old ctx requires synchronizing in-flight users */ + if (old) { + synchronize_irq(pdev->irq); + vfio_virqfd_flush_thread(&vdev->ctx[0].unmask); + eventfd_ctx_put(old); } - /* - * INTx disable will stick across the new irq setup, - * disable_irq won't. - */ - spin_lock_irqsave(&vdev->irqlock, flags); - if (!vdev->pci_2_3 && vdev->ctx[0].masked) - disable_irq_nosync(pdev->irq); - spin_unlock_irqrestore(&vdev->irqlock, flags); - return 0; } static void vfio_intx_disable(struct vfio_pci_device *vdev) { + struct pci_dev *pdev = vdev->pdev; + vfio_virqfd_disable(&vdev->ctx[0].unmask); vfio_virqfd_disable(&vdev->ctx[0].mask); - vfio_intx_set_signal(vdev, -1); + free_irq(pdev->irq, vdev); + if (vdev->ctx[0].trigger) + eventfd_ctx_put(vdev->ctx[0].trigger); + kfree(vdev->ctx[0].name); vdev->irq_type = VFIO_PCI_NUM_IRQS; vdev->num_ctx = 0; kfree(vdev->ctx); @@ -425,11 +457,11 @@ static int vfio_pci_set_intx_unmask(struct vfio_pci_device *vdev, return -EINVAL; if (flags & VFIO_IRQ_SET_DATA_NONE) { - vfio_pci_intx_unmask(vdev); + __vfio_pci_intx_unmask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { uint8_t unmask = *(uint8_t *)data; if (unmask) - vfio_pci_intx_unmask(vdev); + __vfio_pci_intx_unmask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { int32_t fd = *(int32_t *)data; if (fd >= 0) @@ -452,11 +484,11 @@ static int vfio_pci_set_intx_mask(struct vfio_pci_device *vdev, return -EINVAL; if (flags & VFIO_IRQ_SET_DATA_NONE) { - vfio_pci_intx_mask(vdev); + __vfio_pci_intx_mask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { uint8_t mask = *(uint8_t *)data; if (mask) - vfio_pci_intx_mask(vdev); + __vfio_pci_intx_mask(vdev); } else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { return -ENOTTY; /* XXX implement me */ } @@ -477,19 +509,23 @@ static int vfio_pci_set_intx_trigger(struct vfio_pci_device *vdev, return -EINVAL; if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { + struct eventfd_ctx *trigger = NULL; int32_t fd = *(int32_t *)data; int ret; - if (is_intx(vdev)) - return vfio_intx_set_signal(vdev, fd); + if (fd >= 0) { + trigger = eventfd_ctx_fdget(fd); + if (IS_ERR(trigger)) + return PTR_ERR(trigger); + } - ret = vfio_intx_enable(vdev); - if (ret) - return ret; + if (is_intx(vdev)) + ret = vfio_intx_set_signal(vdev, trigger); + else + ret = vfio_intx_enable(vdev, trigger); - ret = vfio_intx_set_signal(vdev, fd); - if (ret) - vfio_intx_disable(vdev); + if (ret && trigger) + eventfd_ctx_put(trigger); return ret; } diff --git a/drivers/vfio/platform/vfio_platform_irq.c b/drivers/vfio/platform/vfio_platform_irq.c index c5b09ec0a..7f4341a8d 100644 --- a/drivers/vfio/platform/vfio_platform_irq.c +++ b/drivers/vfio/platform/vfio_platform_irq.c @@ -136,6 +136,16 @@ static int vfio_platform_set_irq_unmask(struct vfio_platform_device *vdev, return 0; } +/* + * The trigger eventfd is guaranteed valid in the interrupt path + * and protected by the igate mutex when triggered via ioctl. + */ +static void vfio_send_eventfd(struct vfio_platform_irq *irq_ctx) +{ + if (likely(irq_ctx->trigger)) + eventfd_signal(irq_ctx->trigger, 1); +} + static irqreturn_t vfio_automasked_irq_handler(int irq, void *dev_id) { struct vfio_platform_irq *irq_ctx = dev_id; @@ -155,7 +165,7 @@ static irqreturn_t vfio_automasked_irq_handler(int irq, void *dev_id) spin_unlock_irqrestore(&irq_ctx->lock, flags); if (ret == IRQ_HANDLED) - eventfd_signal(irq_ctx->trigger, 1); + vfio_send_eventfd(irq_ctx); return ret; } @@ -164,22 +174,19 @@ static irqreturn_t vfio_irq_handler(int irq, void *dev_id) { struct vfio_platform_irq *irq_ctx = dev_id; - eventfd_signal(irq_ctx->trigger, 1); + vfio_send_eventfd(irq_ctx); return IRQ_HANDLED; } static int vfio_set_trigger(struct vfio_platform_device *vdev, int index, - int fd, irq_handler_t handler) + int fd) { struct vfio_platform_irq *irq = &vdev->irqs[index]; struct eventfd_ctx *trigger; - int ret; if (irq->trigger) { - irq_clear_status_flags(irq->hwirq, IRQ_NOAUTOEN); - free_irq(irq->hwirq, irq); - kfree(irq->name); + disable_irq(irq->hwirq); eventfd_ctx_put(irq->trigger); irq->trigger = NULL; } @@ -187,30 +194,20 @@ static int vfio_set_trigger(struct vfio_platform_device *vdev, int index, if (fd < 0) /* Disable only */ return 0; - irq->name = kasprintf(GFP_KERNEL, "vfio-irq[%d](%s)", - irq->hwirq, vdev->name); - if (!irq->name) - return -ENOMEM; - trigger = eventfd_ctx_fdget(fd); - if (IS_ERR(trigger)) { - kfree(irq->name); + if (IS_ERR(trigger)) return PTR_ERR(trigger); - } irq->trigger = trigger; - irq_set_status_flags(irq->hwirq, IRQ_NOAUTOEN); - ret = request_irq(irq->hwirq, handler, 0, irq->name, irq); - if (ret) { - kfree(irq->name); - eventfd_ctx_put(trigger); - irq->trigger = NULL; - return ret; - } - - if (!irq->masked) - enable_irq(irq->hwirq); + /* + * irq->masked effectively provides nested disables within the overall + * enable relative to trigger. Specifically request_irq() is called + * with NO_AUTOEN, therefore the IRQ is initially disabled. The user + * may only further disable the IRQ with a MASK operations because + * irq->masked is initially false. + */ + enable_irq(irq->hwirq); return 0; } @@ -229,7 +226,7 @@ static int vfio_platform_set_irq_trigger(struct vfio_platform_device *vdev, handler = vfio_irq_handler; if (!count && (flags & VFIO_IRQ_SET_DATA_NONE)) - return vfio_set_trigger(vdev, index, -1, handler); + return vfio_set_trigger(vdev, index, -1); if (start != 0 || count != 1) return -EINVAL; @@ -237,7 +234,7 @@ static int vfio_platform_set_irq_trigger(struct vfio_platform_device *vdev, if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { int32_t fd = *(int32_t *)data; - return vfio_set_trigger(vdev, index, fd, handler); + return vfio_set_trigger(vdev, index, fd); } if (flags & VFIO_IRQ_SET_DATA_NONE) { @@ -261,6 +258,14 @@ int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev, unsigned start, unsigned count, uint32_t flags, void *data) = NULL; + /* + * For compatibility, errors from request_irq() are local to the + * SET_IRQS path and reflected in the name pointer. This allows, + * for example, polling mode fallback for an exclusive IRQ failure. + */ + if (IS_ERR(vdev->irqs[index].name)) + return PTR_ERR(vdev->irqs[index].name); + switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) { case VFIO_IRQ_SET_ACTION_MASK: func = vfio_platform_set_irq_mask; @@ -281,7 +286,7 @@ int vfio_platform_set_irqs_ioctl(struct vfio_platform_device *vdev, int vfio_platform_irq_init(struct vfio_platform_device *vdev) { - int cnt = 0, i; + int cnt = 0, i, ret = 0; while (vdev->get_irq(vdev, cnt) >= 0) cnt++; @@ -292,37 +297,70 @@ int vfio_platform_irq_init(struct vfio_platform_device *vdev) for (i = 0; i < cnt; i++) { int hwirq = vdev->get_irq(vdev, i); + irq_handler_t handler = vfio_irq_handler; - if (hwirq < 0) + if (hwirq < 0) { + ret = -EINVAL; goto err; + } spin_lock_init(&vdev->irqs[i].lock); vdev->irqs[i].flags = VFIO_IRQ_INFO_EVENTFD; - if (irq_get_trigger_type(hwirq) & IRQ_TYPE_LEVEL_MASK) + if (irq_get_trigger_type(hwirq) & IRQ_TYPE_LEVEL_MASK) { vdev->irqs[i].flags |= VFIO_IRQ_INFO_MASKABLE | VFIO_IRQ_INFO_AUTOMASKED; + handler = vfio_automasked_irq_handler; + } vdev->irqs[i].count = 1; vdev->irqs[i].hwirq = hwirq; vdev->irqs[i].masked = false; + vdev->irqs[i].name = kasprintf(GFP_KERNEL, + "vfio-irq[%d](%s)", hwirq, + vdev->name); + if (!vdev->irqs[i].name) { + ret = -ENOMEM; + goto err; + } + + ret = request_irq(hwirq, handler, IRQF_NO_AUTOEN, + vdev->irqs[i].name, &vdev->irqs[i]); + if (ret) { + kfree(vdev->irqs[i].name); + vdev->irqs[i].name = ERR_PTR(ret); + } } vdev->num_irqs = cnt; return 0; err: + for (--i; i >= 0; i--) { + if (!IS_ERR(vdev->irqs[i].name)) { + free_irq(vdev->irqs[i].hwirq, &vdev->irqs[i]); + kfree(vdev->irqs[i].name); + } + } kfree(vdev->irqs); - return -EINVAL; + return ret; } void vfio_platform_irq_cleanup(struct vfio_platform_device *vdev) { int i; - for (i = 0; i < vdev->num_irqs; i++) - vfio_set_trigger(vdev, i, -1, NULL); + for (i = 0; i < vdev->num_irqs; i++) { + vfio_virqfd_disable(&vdev->irqs[i].mask); + vfio_virqfd_disable(&vdev->irqs[i].unmask); + if (!IS_ERR(vdev->irqs[i].name)) { + free_irq(vdev->irqs[i].hwirq, &vdev->irqs[i]); + if (vdev->irqs[i].trigger) + eventfd_ctx_put(vdev->irqs[i].trigger); + kfree(vdev->irqs[i].name); + } + } vdev->num_irqs = 0; kfree(vdev->irqs); diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c index 997cb5d0a..1cff53301 100644 --- a/drivers/vfio/virqfd.c +++ b/drivers/vfio/virqfd.c @@ -101,6 +101,13 @@ static void virqfd_inject(struct work_struct *work) virqfd->thread(virqfd->opaque, virqfd->data); } +static void virqfd_flush_inject(struct work_struct *work) +{ + struct virqfd *virqfd = container_of(work, struct virqfd, flush_inject); + + flush_work(&virqfd->inject); +} + int vfio_virqfd_enable(void *opaque, int (*handler)(void *, void *), void (*thread)(void *, void *), @@ -124,6 +131,7 @@ int vfio_virqfd_enable(void *opaque, INIT_WORK(&virqfd->shutdown, virqfd_shutdown); INIT_WORK(&virqfd->inject, virqfd_inject); + INIT_WORK(&virqfd->flush_inject, virqfd_flush_inject); irqfd = fdget(fd); if (!irqfd.file) { @@ -214,6 +222,19 @@ void vfio_virqfd_disable(struct virqfd **pvirqfd) } EXPORT_SYMBOL_GPL(vfio_virqfd_disable); +void vfio_virqfd_flush_thread(struct virqfd **pvirqfd) +{ + unsigned long flags; + + spin_lock_irqsave(&virqfd_lock, flags); + if (*pvirqfd && (*pvirqfd)->thread) + queue_work(vfio_irqfd_cleanup_wq, &(*pvirqfd)->flush_inject); + spin_unlock_irqrestore(&virqfd_lock, flags); + + flush_workqueue(vfio_irqfd_cleanup_wq); +} +EXPORT_SYMBOL_GPL(vfio_virqfd_flush_thread); + module_init(vfio_virqfd_init); module_exit(vfio_virqfd_exit); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index de110363a..8ed9c9b63 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2513,9 +2513,19 @@ bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq) r = vhost_get_avail_idx(vq, &avail_idx); if (unlikely(r)) return false; + vq->avail_idx = vhost16_to_cpu(vq, avail_idx); + if (vq->avail_idx != vq->last_avail_idx) { + /* Since we have updated avail_idx, the following + * call to vhost_get_vq_desc() will read available + * ring entries. Make sure that read happens after + * the avail_idx read. + */ + smp_rmb(); + return false; + } - return vq->avail_idx == vq->last_avail_idx; + return true; } EXPORT_SYMBOL_GPL(vhost_vq_avail_empty); @@ -2577,12 +2587,11 @@ EXPORT_SYMBOL_GPL(vhost_disable_notify); /* Create a new message. */ struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type) { - struct vhost_msg_node *node = kmalloc(sizeof *node, GFP_KERNEL); + /* Make sure all padding within the structure is initialized. */ + struct vhost_msg_node *node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return NULL; - /* Make sure all padding within the structure is initialized. */ - memset(&node->msg, 0, sizeof node->msg); node->vq = vq; node->msg.type = type; return node; diff --git a/drivers/video/backlight/da9052_bl.c b/drivers/video/backlight/da9052_bl.c index 882359dd2..aa0037939 100644 --- a/drivers/video/backlight/da9052_bl.c +++ b/drivers/video/backlight/da9052_bl.c @@ -117,6 +117,7 @@ static int da9052_backlight_probe(struct platform_device *pdev) wleds->led_reg = platform_get_device_id(pdev)->driver_data; wleds->state = DA9052_WLEDS_OFF; + memset(&props, 0, sizeof(struct backlight_properties)); props.type = BACKLIGHT_RAW; props.max_brightness = DA9052_MAX_BRIGHTNESS; diff --git a/drivers/video/backlight/lm3630a_bl.c b/drivers/video/backlight/lm3630a_bl.c index 419b0334c..2134342c2 100644 --- a/drivers/video/backlight/lm3630a_bl.c +++ b/drivers/video/backlight/lm3630a_bl.c @@ -229,7 +229,7 @@ static int lm3630a_bank_a_get_brightness(struct backlight_device *bl) if (rval < 0) goto out_i2c_err; brightness |= rval; - goto out; + return brightness; } /* disable sleep */ @@ -240,11 +240,8 @@ static int lm3630a_bank_a_get_brightness(struct backlight_device *bl) rval = lm3630a_read(pchip, REG_BRT_A); if (rval < 0) goto out_i2c_err; - brightness = rval; + return rval; -out: - bl->props.brightness = brightness; - return bl->props.brightness; out_i2c_err: dev_err(pchip->dev, "i2c failed to access register\n"); return 0; @@ -306,7 +303,7 @@ static int lm3630a_bank_b_get_brightness(struct backlight_device *bl) if (rval < 0) goto out_i2c_err; brightness |= rval; - goto out; + return brightness; } /* disable sleep */ @@ -317,11 +314,8 @@ static int lm3630a_bank_b_get_brightness(struct backlight_device *bl) rval = lm3630a_read(pchip, REG_BRT_B); if (rval < 0) goto out_i2c_err; - brightness = rval; + return rval; -out: - bl->props.brightness = brightness; - return bl->props.brightness; out_i2c_err: dev_err(pchip->dev, "i2c failed to access register\n"); return 0; @@ -339,6 +333,7 @@ static int lm3630a_backlight_register(struct lm3630a_chip *pchip) struct backlight_properties props; const char *label; + memset(&props, 0, sizeof(struct backlight_properties)); props.type = BACKLIGHT_RAW; if (pdata->leda_ctrl != LM3630A_LEDA_DISABLE) { props.brightness = pdata->leda_init_brt; diff --git a/drivers/video/backlight/lm3639_bl.c b/drivers/video/backlight/lm3639_bl.c index 48c04155a..bb617f467 100644 --- a/drivers/video/backlight/lm3639_bl.c +++ b/drivers/video/backlight/lm3639_bl.c @@ -339,6 +339,7 @@ static int lm3639_probe(struct i2c_client *client, } /* backlight */ + memset(&props, 0, sizeof(struct backlight_properties)); props.type = BACKLIGHT_RAW; props.brightness = pdata->init_brt_led; props.max_brightness = pdata->max_brt_led; diff --git a/drivers/video/backlight/lp8788_bl.c b/drivers/video/backlight/lp8788_bl.c index ba42f3fe0..d9b95dbd4 100644 --- a/drivers/video/backlight/lp8788_bl.c +++ b/drivers/video/backlight/lp8788_bl.c @@ -191,6 +191,7 @@ static int lp8788_backlight_register(struct lp8788_bl *bl) int init_brt; char *name; + memset(&props, 0, sizeof(struct backlight_properties)); props.type = BACKLIGHT_PLATFORM; props.max_brightness = MAX_BRIGHTNESS; diff --git a/drivers/video/fbdev/core/fbmon.c b/drivers/video/fbdev/core/fbmon.c index 1bf82dbc9..3c29a5eb4 100644 --- a/drivers/video/fbdev/core/fbmon.c +++ b/drivers/video/fbdev/core/fbmon.c @@ -1311,7 +1311,7 @@ int fb_get_mode(int flags, u32 val, struct fb_var_screeninfo *var, struct fb_inf int fb_videomode_from_videomode(const struct videomode *vm, struct fb_videomode *fbmode) { - unsigned int htotal, vtotal; + unsigned int htotal, vtotal, total; fbmode->xres = vm->hactive; fbmode->left_margin = vm->hback_porch; @@ -1344,8 +1344,9 @@ int fb_videomode_from_videomode(const struct videomode *vm, vtotal = vm->vactive + vm->vfront_porch + vm->vback_porch + vm->vsync_len; /* prevent division by zero */ - if (htotal && vtotal) { - fbmode->refresh = vm->pixelclock / (htotal * vtotal); + total = htotal * vtotal; + if (total) { + fbmode->refresh = vm->pixelclock / total; /* a mode must have htotal and vtotal != 0 or it is invalid */ } else { fbmode->refresh = 0; diff --git a/drivers/video/fbdev/savage/savagefb_driver.c b/drivers/video/fbdev/savage/savagefb_driver.c index 0ac750cc5..94ebd8af5 100644 --- a/drivers/video/fbdev/savage/savagefb_driver.c +++ b/drivers/video/fbdev/savage/savagefb_driver.c @@ -868,6 +868,9 @@ static int savagefb_check_var(struct fb_var_screeninfo *var, DBG("savagefb_check_var"); + if (!var->pixclock) + return -EINVAL; + var->transp.offset = 0; var->transp.length = 0; switch (var->bits_per_pixel) { diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c index 03c736f6f..e540cb0c5 100644 --- a/drivers/video/fbdev/sis/sis_main.c +++ b/drivers/video/fbdev/sis/sis_main.c @@ -1474,6 +1474,8 @@ sisfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) vtotal = var->upper_margin + var->lower_margin + var->vsync_len; + if (!var->pixclock) + return -EINVAL; pixclock = var->pixclock; if((var->vmode & FB_VMODE_MASK) == FB_VMODE_NONINTERLACED) { diff --git a/drivers/video/fbdev/via/accel.c b/drivers/video/fbdev/via/accel.c index 0a1bc7a4d..1e04026f0 100644 --- a/drivers/video/fbdev/via/accel.c +++ b/drivers/video/fbdev/via/accel.c @@ -115,7 +115,7 @@ static int hw_bitblt_1(void __iomem *engine, u8 op, u32 width, u32 height, if (op != VIA_BITBLT_FILL) { tmp = src_mem ? 0 : src_addr; - if (dst_addr & 0xE0000007) { + if (tmp & 0xE0000007) { printk(KERN_WARNING "hw_bitblt_1: Unsupported source " "address %X\n", tmp); return -EINVAL; @@ -260,7 +260,7 @@ static int hw_bitblt_2(void __iomem *engine, u8 op, u32 width, u32 height, writel(tmp, engine + 0x18); tmp = src_mem ? 0 : src_addr; - if (dst_addr & 0xE0000007) { + if (tmp & 0xE0000007) { printk(KERN_WARNING "hw_bitblt_2: Unsupported source " "address %X\n", tmp); return -EINVAL; diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 441bc0578..5df51095d 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -403,13 +403,19 @@ EXPORT_SYMBOL_GPL(unregister_virtio_device); int virtio_device_freeze(struct virtio_device *dev) { struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); + int ret; virtio_config_disable(dev); dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED; - if (drv && drv->freeze) - return drv->freeze(dev); + if (drv && drv->freeze) { + ret = drv->freeze(dev); + if (ret) { + virtio_config_enable(dev); + return ret; + } + } return 0; } diff --git a/drivers/watchdog/it87_wdt.c b/drivers/watchdog/it87_wdt.c index 2b4831842..6340ca058 100644 --- a/drivers/watchdog/it87_wdt.c +++ b/drivers/watchdog/it87_wdt.c @@ -263,6 +263,7 @@ static struct watchdog_device wdt_dev = { static int __init it87_wdt_init(void) { u8 chip_rev; + u8 ctrl; int rc; rc = superio_enter(); @@ -321,7 +322,18 @@ static int __init it87_wdt_init(void) superio_select(GPIO); superio_outb(WDT_TOV1, WDTCFG); - superio_outb(0x00, WDTCTRL); + + switch (chip_type) { + case IT8784_ID: + case IT8786_ID: + ctrl = superio_inb(WDTCTRL); + ctrl &= 0x08; + superio_outb(ctrl, WDTCTRL); + break; + default: + superio_outb(0x00, WDTCTRL); + } + superio_exit(); if (timeout < 1 || timeout > max_units * 60) { diff --git a/drivers/watchdog/stm32_iwdg.c b/drivers/watchdog/stm32_iwdg.c index 25188d6bb..16dd1aab7 100644 --- a/drivers/watchdog/stm32_iwdg.c +++ b/drivers/watchdog/stm32_iwdg.c @@ -21,6 +21,8 @@ #include <linux/platform_device.h> #include <linux/watchdog.h> +#define DEFAULT_TIMEOUT 10 + /* IWDG registers */ #define IWDG_KR 0x00 /* Key register */ #define IWDG_PR 0x04 /* Prescaler Register */ @@ -254,6 +256,7 @@ static int stm32_iwdg_probe(struct platform_device *pdev) wdd->parent = dev; wdd->info = &stm32_iwdg_info; wdd->ops = &stm32_iwdg_ops; + wdd->timeout = DEFAULT_TIMEOUT; wdd->min_timeout = DIV_ROUND_UP((RLR_MIN + 1) * PR_MIN, wdt->rate); wdd->max_hw_heartbeat_ms = ((RLR_MAX + 1) * wdt->data->max_prescaler * 1000) / wdt->rate; diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 24e399849..f608663bd 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -885,8 +885,8 @@ static void shutdown_pirq(struct irq_data *data) return; do_mask(info, EVT_MASK_REASON_EXPLICIT); - xen_evtchn_close(evtchn); xen_irq_info_cleanup(info); + xen_evtchn_close(evtchn); } static void enable_pirq(struct irq_data *data) @@ -929,8 +929,6 @@ static void __unbind_from_irq(unsigned int irq) if (VALID_EVTCHN(evtchn)) { unsigned int cpu = cpu_from_irq(irq); - xen_evtchn_close(evtchn); - switch (type_from_irq(irq)) { case IRQT_VIRQ: per_cpu(virq_to_irq, cpu)[virq_from_irq(irq)] = -1; @@ -943,6 +941,7 @@ static void __unbind_from_irq(unsigned int irq) } xen_irq_info_cleanup(info); + xen_evtchn_close(evtchn); } xen_free_irq(irq); diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c index 4c13cbc99..398ea69c1 100644 --- a/drivers/xen/gntdev-dmabuf.c +++ b/drivers/xen/gntdev-dmabuf.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/dma-buf.h> +#include <linux/dma-direct.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/uaccess.h> @@ -56,7 +57,7 @@ struct gntdev_dmabuf { /* Number of pages this buffer has. */ int nr_pages; - /* Pages of this buffer. */ + /* Pages of this buffer (only for dma-buf export). */ struct page **pages; }; @@ -490,7 +491,7 @@ out: /* DMA buffer import support. */ static int -dmabuf_imp_grant_foreign_access(struct page **pages, u32 *refs, +dmabuf_imp_grant_foreign_access(unsigned long *gfns, u32 *refs, int count, int domid) { grant_ref_t priv_gref_head; @@ -513,7 +514,7 @@ dmabuf_imp_grant_foreign_access(struct page **pages, u32 *refs, } gnttab_grant_foreign_access_ref(cur_ref, domid, - xen_page_to_gfn(pages[i]), 0); + gfns[i], 0); refs[i] = cur_ref; } @@ -535,7 +536,6 @@ static void dmabuf_imp_end_foreign_access(u32 *refs, int count) static void dmabuf_imp_free_storage(struct gntdev_dmabuf *gntdev_dmabuf) { - kfree(gntdev_dmabuf->pages); kfree(gntdev_dmabuf->u.imp.refs); kfree(gntdev_dmabuf); } @@ -555,12 +555,6 @@ static struct gntdev_dmabuf *dmabuf_imp_alloc_storage(int count) if (!gntdev_dmabuf->u.imp.refs) goto fail; - gntdev_dmabuf->pages = kcalloc(count, - sizeof(gntdev_dmabuf->pages[0]), - GFP_KERNEL); - if (!gntdev_dmabuf->pages) - goto fail; - gntdev_dmabuf->nr_pages = count; for (i = 0; i < count; i++) @@ -582,7 +576,8 @@ dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev, struct dma_buf *dma_buf; struct dma_buf_attachment *attach; struct sg_table *sgt; - struct sg_page_iter sg_iter; + struct sg_dma_page_iter sg_iter; + unsigned long *gfns; int i; dma_buf = dma_buf_get(fd); @@ -630,26 +625,31 @@ dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev, gntdev_dmabuf->u.imp.sgt = sgt; - /* Now convert sgt to array of pages and check for page validity. */ + gfns = kcalloc(count, sizeof(*gfns), GFP_KERNEL); + if (!gfns) { + ret = ERR_PTR(-ENOMEM); + goto fail_unmap; + } + + /* + * Now convert sgt to array of gfns without accessing underlying pages. + * It is not allowed to access the underlying struct page of an sg table + * exported by DMA-buf, but since we deal with special Xen dma device here + * (not a normal physical one) look at the dma addresses in the sg table + * and then calculate gfns directly from them. + */ i = 0; - for_each_sgtable_page(sgt, &sg_iter, 0) { - struct page *page = sg_page_iter_page(&sg_iter); - /* - * Check if page is valid: this can happen if we are given - * a page from VRAM or other resources which are not backed - * by a struct page. - */ - if (!pfn_valid(page_to_pfn(page))) { - ret = ERR_PTR(-EINVAL); - goto fail_unmap; - } + for_each_sgtable_dma_page(sgt, &sg_iter, 0) { + dma_addr_t addr = sg_page_iter_dma_address(&sg_iter); + unsigned long pfn = bfn_to_pfn(XEN_PFN_DOWN(dma_to_phys(dev, addr))); - gntdev_dmabuf->pages[i++] = page; + gfns[i++] = pfn_to_gfn(pfn); } - ret = ERR_PTR(dmabuf_imp_grant_foreign_access(gntdev_dmabuf->pages, + ret = ERR_PTR(dmabuf_imp_grant_foreign_access(gfns, gntdev_dmabuf->u.imp.refs, count, domid)); + kfree(gfns); if (IS_ERR(ret)) goto fail_end_access; diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 7d9b23d98..229308c7f 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -70,13 +70,14 @@ static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell, { struct afs_volume *volume = NULL; struct rb_node *p; - int seq = 0; + int seq = 1; do { /* Unfortunately, rbtree walking doesn't give reliable results * under just the RCU read lock, so we have to check for * changes. */ + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&cell->volume_lock, &seq); p = rcu_dereference_raw(cell->volumes.rb_node); diff --git a/fs/afs/server.c b/fs/afs/server.c index 684a2b02b..733e3c470 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -27,7 +27,7 @@ struct afs_server *afs_find_server(struct afs_net *net, const struct afs_addr_list *alist; struct afs_server *server = NULL; unsigned int i; - int seq = 0, diff; + int seq = 1, diff; rcu_read_lock(); @@ -35,6 +35,7 @@ struct afs_server *afs_find_server(struct afs_net *net, if (server) afs_unuse_server_notime(net, server, afs_server_trace_put_find_rsq); server = NULL; + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&net->fs_addr_lock, &seq); if (srx->transport.family == AF_INET6) { @@ -90,7 +91,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu { struct afs_server *server = NULL; struct rb_node *p; - int diff, seq = 0; + int diff, seq = 1; _enter("%pU", uuid); @@ -102,7 +103,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu if (server) afs_unuse_server(net, server, afs_server_trace_put_uuid_rsq); server = NULL; - + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&net->fs_lock, &seq); p = net->fs_servers.rb_node; diff --git a/fs/afs/volume.c b/fs/afs/volume.c index f84194b79..fb19c6928 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -302,7 +302,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) { struct afs_server_list *new, *old, *discard; struct afs_vldb_entry *vldb; - char idbuf[16]; + char idbuf[24]; int ret, idsz; _enter(""); @@ -310,7 +310,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) /* We look up an ID by passing it as a decimal string in the * operation's name parameter. */ - idsz = sprintf(idbuf, "%llu", volume->vid); + idsz = snprintf(idbuf, sizeof(idbuf), "%llu", volume->vid); vldb = afs_vl_lookup_vldb(volume->cell, key, idbuf, idsz); if (IS_ERR(vldb)) { @@ -565,13 +565,24 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) { - struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw); - struct kioctx *ctx = req->ki_ctx; + struct aio_kiocb *req; + struct kioctx *ctx; unsigned long flags; + /* + * kiocb didn't come from aio or is neither a read nor a write, hence + * ignore it. + */ + if (!(iocb->ki_flags & IOCB_AIO_RW)) + return; + + req = container_of(iocb, struct aio_kiocb, rw); + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; + ctx = req->ki_ctx; + spin_lock_irqsave(&ctx->ctx_lock, flags); list_add_tail(&req->ki_list, &ctx->active_reqs); req->ki_cancel = cancel; @@ -1454,7 +1465,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; - req->ki_flags = iocb_flags(req->ki_filp); + req->ki_flags = iocb_flags(req->ki_filp) | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; req->ki_hint = ki_hint_validate(file_write_hint(req->ki_filp)); diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index d2f77b124..f1731eeb8 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -2315,20 +2315,14 @@ struct btrfs_data_container *init_data_container(u32 total_bytes) size_t alloc_bytes; alloc_bytes = max_t(size_t, total_bytes, sizeof(*data)); - data = kvmalloc(alloc_bytes, GFP_KERNEL); + data = kvzalloc(alloc_bytes, GFP_KERNEL); if (!data) return ERR_PTR(-ENOMEM); - if (total_bytes >= sizeof(*data)) { + if (total_bytes >= sizeof(*data)) data->bytes_left = total_bytes - sizeof(*data); - data->bytes_missing = 0; - } else { + else data->bytes_missing = sizeof(*data) - total_bytes; - data->bytes_left = 0; - } - - data->elem_cnt = 0; - data->elem_missed = 0; return data; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 67831868e..3ddb09f2b 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2879,7 +2879,7 @@ struct btrfs_dir_item * btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - u64 objectid, const char *name, int name_len, + u64 index, const char *name, int name_len, int mod); struct btrfs_dir_item * btrfs_search_dir_index_item(struct btrfs_root *root, diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index bcffe7886..cdfc791b3 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1135,6 +1135,9 @@ __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, if (ret) return ret; + ret = btrfs_record_root_in_trans(trans, node->root); + if (ret) + return ret; ret = btrfs_update_delayed_inode(trans, node->root, path, node); return ret; } diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index be6935d19..9a6055659 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -566,6 +566,23 @@ leave: return ret; } +static int btrfs_check_replace_dev_names(struct btrfs_ioctl_dev_replace_args *args) +{ + if (args->start.srcdevid == 0) { + if (memchr(args->start.srcdev_name, 0, + sizeof(args->start.srcdev_name)) == NULL) + return -ENAMETOOLONG; + } else { + args->start.srcdev_name[0] = 0; + } + + if (memchr(args->start.tgtdev_name, 0, + sizeof(args->start.tgtdev_name)) == NULL) + return -ENAMETOOLONG; + + return 0; +} + int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_dev_replace_args *args) { @@ -578,10 +595,9 @@ int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info, default: return -EINVAL; } - - if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') || - args->start.tgtdev_name[0] == '\0') - return -EINVAL; + ret = btrfs_check_replace_dev_names(args); + if (ret < 0) + return ret; ret = btrfs_dev_replace_start(fs_info, args->start.tgtdev_name, args->start.srcdevid, diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 863367c2c..98c6faa8c 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -171,10 +171,40 @@ out_free: return 0; } +static struct btrfs_dir_item *btrfs_lookup_match_dir( + struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct btrfs_path *path, + struct btrfs_key *key, const char *name, + int name_len, int mod) +{ + const int ins_len = (mod < 0 ? -1 : 0); + const int cow = (mod != 0); + int ret; + + ret = btrfs_search_slot(trans, root, key, path, ins_len, cow); + if (ret < 0) + return ERR_PTR(ret); + if (ret > 0) + return ERR_PTR(-ENOENT); + + return btrfs_match_dir_item_name(root->fs_info, path, name, name_len); +} + /* - * lookup a directory item based on name. 'dir' is the objectid - * we're searching in, and 'mod' tells us if you plan on deleting the - * item (use mod < 0) or changing the options (use mod > 0) + * Lookup for a directory item by name. + * + * @trans: The transaction handle to use. Can be NULL if @mod is 0. + * @root: The root of the target tree. + * @path: Path to use for the search. + * @dir: The inode number (objectid) of the directory. + * @name: The name associated to the directory entry we are looking for. + * @name_len: The length of the name. + * @mod: Used to indicate if the tree search is meant for a read only + * lookup, for a modification lookup or for a deletion lookup, so + * its value should be 0, 1 or -1, respectively. + * + * Returns: NULL if the dir item does not exists, an error pointer if an error + * happened, or a pointer to a dir item if a dir item exists for the given name. */ struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -182,23 +212,18 @@ struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, const char *name, int name_len, int mod) { - int ret; struct btrfs_key key; - int ins_len = mod < 0 ? -1 : 0; - int cow = mod != 0; + struct btrfs_dir_item *di; key.objectid = dir; key.type = BTRFS_DIR_ITEM_KEY; - key.offset = btrfs_name_hash(name, name_len); - ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow); - if (ret < 0) - return ERR_PTR(ret); - if (ret > 0) + di = btrfs_lookup_match_dir(trans, root, path, &key, name, name_len, mod); + if (IS_ERR(di) && PTR_ERR(di) == -ENOENT) return NULL; - return btrfs_match_dir_item_name(root->fs_info, path, name, name_len); + return di; } int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, @@ -212,7 +237,6 @@ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, int slot; struct btrfs_path *path; - path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -221,20 +245,20 @@ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir, key.type = BTRFS_DIR_ITEM_KEY; key.offset = btrfs_name_hash(name, name_len); - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - - /* return back any errors */ - if (ret < 0) - goto out; + di = btrfs_lookup_match_dir(NULL, root, path, &key, name, name_len, 0); + if (IS_ERR(di)) { + ret = PTR_ERR(di); + /* Nothing found, we're safe */ + if (ret == -ENOENT) { + ret = 0; + goto out; + } - /* nothing found, we're safe */ - if (ret > 0) { - ret = 0; - goto out; + if (ret < 0) + goto out; } /* we found an item, look for our name in the item */ - di = btrfs_match_dir_item_name(root->fs_info, path, name, name_len); if (di) { /* our exact name was found */ ret = -EEXIST; @@ -261,35 +285,42 @@ out: } /* - * lookup a directory item based on index. 'dir' is the objectid - * we're searching in, and 'mod' tells us if you plan on deleting the - * item (use mod < 0) or changing the options (use mod > 0) + * Lookup for a directory index item by name and index number. + * + * @trans: The transaction handle to use. Can be NULL if @mod is 0. + * @root: The root of the target tree. + * @path: Path to use for the search. + * @dir: The inode number (objectid) of the directory. + * @index: The index number. + * @name: The name associated to the directory entry we are looking for. + * @name_len: The length of the name. + * @mod: Used to indicate if the tree search is meant for a read only + * lookup, for a modification lookup or for a deletion lookup, so + * its value should be 0, 1 or -1, respectively. * - * The name is used to make sure the index really points to the name you were - * looking for. + * Returns: NULL if the dir index item does not exists, an error pointer if an + * error happened, or a pointer to a dir item if the dir index item exists and + * matches the criteria (name and index number). */ struct btrfs_dir_item * btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - u64 objectid, const char *name, int name_len, + u64 index, const char *name, int name_len, int mod) { - int ret; + struct btrfs_dir_item *di; struct btrfs_key key; - int ins_len = mod < 0 ? -1 : 0; - int cow = mod != 0; key.objectid = dir; key.type = BTRFS_DIR_INDEX_KEY; - key.offset = objectid; + key.offset = index; - ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow); - if (ret < 0) - return ERR_PTR(ret); - if (ret > 0) - return ERR_PTR(-ENOENT); - return btrfs_match_dir_item_name(root->fs_info, path, name, name_len); + di = btrfs_lookup_match_dir(trans, root, path, &key, name, name_len, mod); + if (di == ERR_PTR(-ENOENT)) + return NULL; + + return di; } struct btrfs_dir_item * @@ -346,21 +377,18 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, const char *name, u16 name_len, int mod) { - int ret; struct btrfs_key key; - int ins_len = mod < 0 ? -1 : 0; - int cow = mod != 0; + struct btrfs_dir_item *di; key.objectid = dir; key.type = BTRFS_XATTR_ITEM_KEY; key.offset = btrfs_name_hash(name, name_len); - ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow); - if (ret < 0) - return ERR_PTR(ret); - if (ret > 0) + + di = btrfs_lookup_match_dir(trans, root, path, &key, name, name_len, mod); + if (IS_ERR(di) && PTR_ERR(di) == -ENOENT) return NULL; - return btrfs_match_dir_item_name(root->fs_info, path, name, name_len); + return di; } /* diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 0e25a3f64..019f0925f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1553,8 +1553,17 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { - /* Shouldn't get preallocated anon_dev for cached roots */ - ASSERT(!anon_dev); + /* + * Some other caller may have read out the newly inserted + * subvolume already (for things like backref walk etc). Not + * that common but still possible. In that case, we just need + * to free the anon_dev. + */ + if (unlikely(anon_dev)) { + free_anon_bdev(anon_dev); + anon_dev = 0; + } + if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index bfa2bf445..d908afa1f 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -161,8 +161,15 @@ struct dentry *btrfs_get_parent(struct dentry *child) ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto fail; + if (ret == 0) { + /* + * Key with offset of -1 found, there would have to exist an + * inode with such number or a root with such id. + */ + ret = -EUCLEAN; + goto fail; + } - BUG_ON(ret == 0); /* Key with offset of -1 found */ if (path->slots[0] == 0) { ret = -ENOENT; goto fail; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 8f62e1710..3ba43a400 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1202,7 +1202,8 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len, u64 bytes_left, end; u64 aligned_start = ALIGN(start, 1 << 9); - if (WARN_ON(start != aligned_start)) { + /* Adjust the range to be aligned to 512B sectors if necessary. */ + if (start != aligned_start) { len -= aligned_start - start; len = round_down(len, 1 << 9); start = aligned_start; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c900a3966..591caac2b 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4007,7 +4007,8 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) struct btrfs_block_rsv block_rsv; u64 root_flags; int ret; - int err; + + down_write(&fs_info->subvol_sem); /* * Don't allow to delete a subvolume with send in progress. This is @@ -4020,25 +4021,25 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) btrfs_warn(fs_info, "attempt to delete subvolume %llu during send", dest->root_key.objectid); - return -EPERM; + ret = -EPERM; + goto out_up_write; } if (atomic_read(&dest->nr_swapfiles)) { spin_unlock(&dest->root_item_lock); btrfs_warn(fs_info, "attempt to delete subvolume %llu with active swapfile", root->root_key.objectid); - return -EPERM; + ret = -EPERM; + goto out_up_write; } root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, root_flags | BTRFS_ROOT_SUBVOL_DEAD); spin_unlock(&dest->root_item_lock); - down_write(&fs_info->subvol_sem); - - err = may_destroy_subvol(dest); - if (err) - goto out_up_write; + ret = may_destroy_subvol(dest); + if (ret) + goto out_undead; btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP); /* @@ -4046,13 +4047,13 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) * two for dir entries, * two for root ref/backref. */ - err = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true); - if (err) - goto out_up_write; + ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true); + if (ret) + goto out_undead; trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { - err = PTR_ERR(trans); + ret = PTR_ERR(trans); goto out_release; } trans->block_rsv = &block_rsv; @@ -4062,7 +4063,6 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) ret = btrfs_unlink_subvol(trans, dir, dentry); if (ret) { - err = ret; btrfs_abort_transaction(trans, ret); goto out_end_trans; } @@ -4080,7 +4080,6 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) dest->root_key.objectid); if (ret) { btrfs_abort_transaction(trans, ret); - err = ret; goto out_end_trans; } } @@ -4090,7 +4089,6 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) dest->root_key.objectid); if (ret && ret != -ENOENT) { btrfs_abort_transaction(trans, ret); - err = ret; goto out_end_trans; } if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) { @@ -4100,7 +4098,6 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) dest->root_key.objectid); if (ret && ret != -ENOENT) { btrfs_abort_transaction(trans, ret); - err = ret; goto out_end_trans; } } @@ -4111,20 +4108,20 @@ out_end_trans: trans->block_rsv = NULL; trans->bytes_reserved = 0; ret = btrfs_end_transaction(trans); - if (ret && !err) - err = ret; inode->i_flags |= S_DEAD; out_release: btrfs_subvolume_release_metadata(root, &block_rsv); -out_up_write: - up_write(&fs_info->subvol_sem); - if (err) { +out_undead: + if (ret) { spin_lock(&dest->root_item_lock); root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, root_flags & ~BTRFS_ROOT_SUBVOL_DEAD); spin_unlock(&dest->root_item_lock); - } else { + } +out_up_write: + up_write(&fs_info->subvol_sem); + if (!ret) { d_invalidate(dentry); btrfs_prune_dentries(dest); ASSERT(dest->send_in_progress == 0); @@ -4136,7 +4133,7 @@ out_up_write: } } - return err; + return ret; } static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) @@ -8971,8 +8968,6 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - btrfs_pin_log_trans(root); - root_log_pinned = true; ret = btrfs_insert_inode_ref(trans, dest, new_dentry->d_name.name, new_dentry->d_name.len, @@ -8989,8 +8984,6 @@ static int btrfs_rename_exchange(struct inode *old_dir, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - btrfs_pin_log_trans(dest); - dest_log_pinned = true; ret = btrfs_insert_inode_ref(trans, root, old_dentry->d_name.name, old_dentry->d_name.len, @@ -9021,6 +9014,29 @@ static int btrfs_rename_exchange(struct inode *old_dir, BTRFS_I(new_inode), 1); } + /* + * Now pin the logs of the roots. We do it to ensure that no other task + * can sync the logs while we are in progress with the rename, because + * that could result in an inconsistency in case any of the inodes that + * are part of this rename operation were logged before. + * + * We pin the logs even if at this precise moment none of the inodes was + * logged before. This is because right after we checked for that, some + * other task fsyncing some other inode not involved with this rename + * operation could log that one of our inodes exists. + * + * We don't need to pin the logs before the above calls to + * btrfs_insert_inode_ref(), since those don't ever need to change a log. + */ + if (old_ino != BTRFS_FIRST_FREE_OBJECTID) { + btrfs_pin_log_trans(root); + root_log_pinned = true; + } + if (new_ino != BTRFS_FIRST_FREE_OBJECTID) { + btrfs_pin_log_trans(dest); + dest_log_pinned = true; + } + /* src is a subvolume */ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) { ret = btrfs_unlink_subvol(trans, old_dir, old_dentry); @@ -9270,8 +9286,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(trans); } else { - btrfs_pin_log_trans(root); - log_pinned = true; ret = btrfs_insert_inode_ref(trans, dest, new_dentry->d_name.name, new_dentry->d_name.len, @@ -9295,6 +9309,25 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) { ret = btrfs_unlink_subvol(trans, old_dir, old_dentry); } else { + /* + * Now pin the log. We do it to ensure that no other task can + * sync the log while we are in progress with the rename, as + * that could result in an inconsistency in case any of the + * inodes that are part of this rename operation were logged + * before. + * + * We pin the log even if at this precise moment none of the + * inodes was logged before. This is because right after we + * checked for that, some other task fsyncing some other inode + * not involved with this rename operation could log that one of + * our inodes exists. + * + * We don't need to pin the logs before the above call to + * btrfs_insert_inode_ref(), since that does not need to change + * a log. + */ + btrfs_pin_log_trans(root); + log_pinned = true; ret = __btrfs_unlink_inode(trans, root, BTRFS_I(old_dir), BTRFS_I(d_inode(old_dentry)), old_dentry->d_name.name, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index f06824bea..ab8ed1877 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -798,6 +798,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, struct btrfs_trans_handle *trans; int ret; + if (btrfs_root_refs(&root->root_item) == 0) + return -ENOENT; + if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) return -EINVAL; @@ -3145,7 +3148,7 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) { struct inode *inode = file_inode(file); struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_ioctl_defrag_range_args *range; + struct btrfs_ioctl_defrag_range_args range = {0}; int ret; ret = mnt_want_write_file(file); @@ -3177,33 +3180,28 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) goto out; } - range = kzalloc(sizeof(*range), GFP_KERNEL); - if (!range) { - ret = -ENOMEM; - goto out; - } - if (argp) { - if (copy_from_user(range, argp, - sizeof(*range))) { + if (copy_from_user(&range, argp, sizeof(range))) { ret = -EFAULT; - kfree(range); + goto out; + } + if (range.flags & ~BTRFS_DEFRAG_RANGE_FLAGS_SUPP) { + ret = -EOPNOTSUPP; goto out; } /* compression requires us to start the IO */ - if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) { - range->flags |= BTRFS_DEFRAG_RANGE_START_IO; - range->extent_thresh = (u32)-1; + if ((range.flags & BTRFS_DEFRAG_RANGE_COMPRESS)) { + range.flags |= BTRFS_DEFRAG_RANGE_START_IO; + range.extent_thresh = (u32)-1; } } else { /* the rest are all set to zero by kzalloc */ - range->len = (u64)-1; + range.len = (u64)-1; } ret = btrfs_defrag_file(file_inode(file), file, - range, BTRFS_OLDEST_GENERATION, 0); + &range, BTRFS_OLDEST_GENERATION, 0); if (ret > 0) ret = 0; - kfree(range); break; default: ret = -EINVAL; @@ -4318,6 +4316,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg) goto out; } + if (sa->create && is_fstree(sa->qgroupid)) { + ret = -EINVAL; + goto out; + } + trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { ret = PTR_ERR(trans); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a67323c2d..50669ff93 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1608,6 +1608,15 @@ out: return ret; } +static bool qgroup_has_usage(struct btrfs_qgroup *qgroup) +{ + return (qgroup->rfer > 0 || qgroup->rfer_cmpr > 0 || + qgroup->excl > 0 || qgroup->excl_cmpr > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > 0); +} + int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -1627,6 +1636,11 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) goto out; } + if (is_fstree(qgroupid) && qgroup_has_usage(qgroup)) { + ret = -EBUSY; + goto out; + } + /* Check if there are no children of this qgroup */ if (!list_empty(&qgroup->members)) { ret = -EBUSY; @@ -4100,6 +4114,8 @@ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes) BTRFS_QGROUP_RSV_META_PREALLOC); trace_qgroup_meta_convert(root, num_bytes); qgroup_convert_meta(fs_info, root->root_key.objectid, num_bytes); + if (!sb_rdonly(fs_info->sb)) + add_root_meta_rsv(root, num_bytes, BTRFS_QGROUP_RSV_META_PERTRANS); } /* diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index bd3bb94cc..c3711598a 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -899,8 +899,10 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, out_unlock: spin_unlock(&fs_info->ref_verify_lock); out: - if (ret) + if (ret) { + btrfs_free_ref_cache(fs_info); btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); + } return ret; } @@ -1029,8 +1031,8 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info) } } if (ret) { - btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); btrfs_free_ref_cache(fs_info); + btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); } btrfs_free_path(path); return ret; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index af9701afc..0519a3557 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -966,7 +966,15 @@ static int iterate_inode_ref(struct btrfs_root *root, struct btrfs_path *path, ret = PTR_ERR(start); goto out; } - BUG_ON(start < p->buf); + if (unlikely(start < p->buf)) { + btrfs_err(root->fs_info, + "send: path ref buffer underflow for key (%llu %u %llu)", + found_key->objectid, + found_key->type, + found_key->offset); + ret = -EINVAL; + goto out; + } } p->start = start; } else { @@ -7285,7 +7293,7 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) } if (arg->flags & ~BTRFS_SEND_FLAG_MASK) { - ret = -EINVAL; + ret = -EOPNOTSUPP; goto out; } diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 32f1b15b2..5b952f69b 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1189,7 +1189,8 @@ static void extent_err(const struct extent_buffer *eb, int slot, } static int check_extent_item(struct extent_buffer *leaf, - struct btrfs_key *key, int slot) + struct btrfs_key *key, int slot, + struct btrfs_key *prev_key) { struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_extent_item *ei; @@ -1334,7 +1335,7 @@ static int check_extent_item(struct extent_buffer *leaf, if (ptr + btrfs_extent_inline_ref_size(inline_type) > end) { extent_err(leaf, slot, "inline ref item overflows extent item, ptr %lu iref size %u end %lu", - ptr, inline_type, end); + ptr, btrfs_extent_inline_ref_size(inline_type), end); return -EUCLEAN; } @@ -1400,6 +1401,26 @@ static int check_extent_item(struct extent_buffer *leaf, total_refs, inline_refs); return -EUCLEAN; } + + if ((prev_key->type == BTRFS_EXTENT_ITEM_KEY) || + (prev_key->type == BTRFS_METADATA_ITEM_KEY)) { + u64 prev_end = prev_key->objectid; + + if (prev_key->type == BTRFS_METADATA_ITEM_KEY) + prev_end += fs_info->nodesize; + else + prev_end += prev_key->offset; + + if (unlikely(prev_end > key->objectid)) { + extent_err(leaf, slot, + "previous extent [%llu %u %llu] overlaps current extent [%llu %u %llu]", + prev_key->objectid, prev_key->type, + prev_key->offset, key->objectid, key->type, + key->offset); + return -EUCLEAN; + } + } + return 0; } @@ -1568,7 +1589,7 @@ static int check_leaf_item(struct extent_buffer *leaf, break; case BTRFS_EXTENT_ITEM_KEY: case BTRFS_METADATA_ITEM_KEY: - ret = check_extent_item(leaf, key, slot); + ret = check_extent_item(leaf, key, slot, prev_key); break; case BTRFS_TREE_BLOCK_REF_KEY: case BTRFS_SHARED_DATA_REF_KEY: diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 10a0913ff..34e9eb501 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -912,8 +912,7 @@ static noinline int inode_in_dir(struct btrfs_root *root, di = btrfs_lookup_dir_index_item(NULL, root, path, dirid, index, name, name_len, 0); if (IS_ERR(di)) { - if (PTR_ERR(di) != -ENOENT) - ret = PTR_ERR(di); + ret = PTR_ERR(di); goto out; } else if (di) { btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); @@ -1149,8 +1148,7 @@ next: di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir), ref_index, name, namelen, 0); if (IS_ERR(di)) { - if (PTR_ERR(di) != -ENOENT) - return PTR_ERR(di); + return PTR_ERR(di); } else if (di) { ret = drop_one_dir_item(trans, root, path, dir, di); if (ret) @@ -1976,9 +1974,6 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, goto out; } - if (dst_di == ERR_PTR(-ENOENT)) - dst_di = NULL; - if (IS_ERR(dst_di)) { ret = PTR_ERR(dst_di); goto out; @@ -2286,7 +2281,7 @@ again: dir_key->offset, name, name_len, 0); } - if (!log_di || log_di == ERR_PTR(-ENOENT)) { + if (!log_di) { btrfs_dir_item_key_to_cpu(eb, di, &location); btrfs_release_path(path); btrfs_release_path(log_path); @@ -3495,8 +3490,7 @@ out_unlock: if (err == -ENOSPC) { btrfs_set_log_full_commit(trans); err = 0; - } else if (err < 0 && err != -ENOENT) { - /* ENOENT can be returned if the entry hasn't been fsynced yet */ + } else if (err < 0) { btrfs_abort_transaction(trans, err); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index eaf5cd043..09c23626f 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1471,7 +1471,7 @@ static bool contains_pending_extent(struct btrfs_device *device, u64 *start, if (in_range(physical_start, *start, len) || in_range(*start, physical_start, - physical_end - physical_start)) { + physical_end + 1 - physical_start)) { *start = physical_end + 1; return true; } @@ -3178,7 +3178,17 @@ again: mutex_unlock(&fs_info->delete_unused_bgs_mutex); goto error; } - BUG_ON(ret == 0); /* Corruption */ + if (ret == 0) { + /* + * On the first search we would find chunk tree with + * offset -1, which is not possible. On subsequent + * loops this would find an existing item on an invalid + * offset (one less than the previous one, wrong + * alignment and size). + */ + ret = -EUCLEAN; + goto error; + } ret = btrfs_previous_item(chunk_root, path, key.objectid, key.type); diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c index dfb14dbdd..3b39552c2 100644 --- a/fs/cachefiles/bind.c +++ b/fs/cachefiles/bind.c @@ -245,6 +245,8 @@ error_open_root: kmem_cache_free(cachefiles_object_jar, fsdef); error_root_object: cachefiles_end_secure(cache, saved_cred); + put_cred(cache->cache_cred); + cache->cache_cred = NULL; pr_err("Failed to register: %d\n", ret); return ret; } @@ -265,6 +267,7 @@ void cachefiles_daemon_unbind(struct cachefiles_cache *cache) dput(cache->graveyard); mntput(cache->mnt); + put_cred(cache->cache_cred); kfree(cache->rootdirname); kfree(cache->secctx); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 432dc2a16..8e43d07ff 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1402,7 +1402,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap, if (flushing & CEPH_CAP_XATTR_EXCL) { arg->old_xattr_buf = __ceph_build_xattrs_blob(ci); arg->xattr_version = ci->i_xattrs.version; - arg->xattr_buf = ci->i_xattrs.blob; + arg->xattr_buf = ceph_buffer_get(ci->i_xattrs.blob); } else { arg->xattr_buf = NULL; arg->old_xattr_buf = NULL; @@ -1468,6 +1468,7 @@ static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci) encode_cap_msg(msg, arg); ceph_con_send(&arg->session->s_con, msg); ceph_buffer_put(arg->old_xattr_buf); + ceph_buffer_put(arg->xattr_buf); if (arg->wake) wake_up_all(&ci->i_cap_wq); } @@ -4598,12 +4599,14 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry, struct inode *dir, int mds, int drop, int unless) { - struct dentry *parent = NULL; struct ceph_mds_request_release *rel = *p; struct ceph_dentry_info *di = ceph_dentry(dentry); int force = 0; int ret; + /* This shouldn't happen */ + BUG_ON(!dir); + /* * force an record for the directory caps if we have a dentry lease. * this is racy (can't take i_ceph_lock and d_lock together), but it @@ -4613,14 +4616,9 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry, spin_lock(&dentry->d_lock); if (di->lease_session && di->lease_session->s_mds == mds) force = 1; - if (!dir) { - parent = dget(dentry->d_parent); - dir = d_inode(parent); - } spin_unlock(&dentry->d_lock); ret = ceph_encode_inode_release(p, dir, mds, drop, unless, force); - dput(parent); spin_lock(&dentry->d_lock); if (ret && di->lease_session && di->lease_session->s_mds == mds) { diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index b98bba887..660e00eb4 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -117,7 +117,7 @@ static __u32 get_neg_ctxt_len(struct smb2_sync_hdr *hdr, __u32 len, } else if (nc_offset + 1 == non_ctxlen) { cifs_dbg(FYI, "no SPNEGO security blob in negprot rsp\n"); size_of_pad_before_neg_ctxts = 0; - } else if (non_ctxlen == SMB311_NEGPROT_BASE_SIZE) + } else if (non_ctxlen == SMB311_NEGPROT_BASE_SIZE + 1) /* has padding, but no SPNEGO blob */ size_of_pad_before_neg_ctxts = nc_offset - non_ctxlen + 1; else diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 26edaeb42..b2a7238a3 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -82,6 +82,7 @@ smb2_add_credits(struct TCP_Server_Info *server, *val = 65000; /* Don't get near 64K credits, avoid srv bugs */ pr_warn_once("server overflowed SMB3 credits\n"); } + WARN_ON_ONCE(server->in_flight == 0); server->in_flight--; if (server->in_flight == 0 && (optype & CIFS_OP_MASK) != CIFS_NEG_OP) rc = change_conf(server); @@ -818,10 +819,12 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) { kref_get(&tcon->crfid.refcount); tcon->crfid.has_lease = true; - smb2_parse_contexts(server, o_rsp, + rc = smb2_parse_contexts(server, rsp_iov, &oparms.fid->epoch, oparms.fid->lease_key, &oplock, NULL, NULL); + if (rc) + goto oshr_exit; } else goto oshr_exit; @@ -4892,6 +4895,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server, struct smb2_sync_hdr *shdr; unsigned int pdu_length = server->pdu_size; unsigned int buf_size; + unsigned int next_cmd; struct mid_q_entry *mid_entry; int next_is_large; char *next_buffer = NULL; @@ -4920,14 +4924,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server, next_is_large = server->large_buf; one_more: shdr = (struct smb2_sync_hdr *)buf; - if (shdr->NextCommand) { + next_cmd = le32_to_cpu(shdr->NextCommand); + if (next_cmd) { + if (WARN_ON_ONCE(next_cmd > pdu_length)) + return -1; if (next_is_large) next_buffer = (char *)cifs_buf_get(); else next_buffer = (char *)cifs_small_buf_get(); - memcpy(next_buffer, - buf + le32_to_cpu(shdr->NextCommand), - pdu_length - le32_to_cpu(shdr->NextCommand)); + memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd); } mid_entry = smb2_find_mid(server, buf); @@ -4951,8 +4956,8 @@ one_more: else ret = cifs_handle_standard(server, mid_entry); - if (ret == 0 && shdr->NextCommand) { - pdu_length -= le32_to_cpu(shdr->NextCommand); + if (ret == 0 && next_cmd) { + pdu_length -= next_cmd; server->large_buf = next_is_large; if (next_is_large) server->bigbuf = buf = next_buffer; @@ -5561,7 +5566,7 @@ struct smb_version_values smb20_values = { .header_size = sizeof(struct smb2_sync_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5583,7 +5588,7 @@ struct smb_version_values smb21_values = { .header_size = sizeof(struct smb2_sync_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5604,7 +5609,7 @@ struct smb_version_values smb3any_values = { .header_size = sizeof(struct smb2_sync_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5625,7 +5630,7 @@ struct smb_version_values smbdefault_values = { .header_size = sizeof(struct smb2_sync_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5646,7 +5651,7 @@ struct smb_version_values smb30_values = { .header_size = sizeof(struct smb2_sync_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5667,7 +5672,7 @@ struct smb_version_values smb302_values = { .header_size = sizeof(struct smb2_sync_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5688,7 +5693,7 @@ struct smb_version_values smb311_values = { .header_size = sizeof(struct smb2_sync_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 76679dc4e..aa3211d8c 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1261,7 +1261,7 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data) /* Testing shows that buffer offset must be at location of Buffer[0] */ req->SecurityBufferOffset = - cpu_to_le16(sizeof(struct smb2_sess_setup_req) - 1 /* pad */); + cpu_to_le16(sizeof(struct smb2_sess_setup_req)); req->SecurityBufferLength = cpu_to_le16(sess_data->iov[1].iov_len); memset(&rqst, 0, sizeof(struct smb_rqst)); @@ -1760,8 +1760,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, iov[0].iov_len = total_len - 1; /* Testing shows that buffer offset must be at location of Buffer[0] */ - req->PathOffset = cpu_to_le16(sizeof(struct smb2_tree_connect_req) - - 1 /* pad */); + req->PathOffset = cpu_to_le16(sizeof(struct smb2_tree_connect_req)); req->PathLength = cpu_to_le16(unc_path_len - 2); iov[1].iov_base = unc_path; iov[1].iov_len = unc_path_len; @@ -1992,17 +1991,18 @@ parse_posix_ctxt(struct create_context *cc, struct smb2_file_all_info *info, posix->nlink, posix->mode, posix->reparse_tag); } -void -smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, __u8 *oplock, - struct smb2_file_all_info *buf, - struct create_posix_rsp *posix) +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix) { - char *data_offset; + struct smb2_create_rsp *rsp = rsp_iov->iov_base; struct create_context *cc; - unsigned int next; - unsigned int remaining; + size_t rem, off, len; + size_t doff, dlen; + size_t noff, nlen; char *name; static const char smb3_create_tag_posix[] = { 0x93, 0xAD, 0x25, 0x50, 0x9C, @@ -2011,45 +2011,63 @@ smb2_parse_contexts(struct TCP_Server_Info *server, }; *oplock = 0; - data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset); - remaining = le32_to_cpu(rsp->CreateContextsLength); - cc = (struct create_context *)data_offset; + + off = le32_to_cpu(rsp->CreateContextsOffset); + rem = le32_to_cpu(rsp->CreateContextsLength); + if (check_add_overflow(off, rem, &len) || len > rsp_iov->iov_len) + return -EINVAL; + cc = (struct create_context *)((u8 *)rsp + off); /* Initialize inode number to 0 in case no valid data in qfid context */ if (buf) buf->IndexNumber = 0; - while (remaining >= sizeof(struct create_context)) { - name = le16_to_cpu(cc->NameOffset) + (char *)cc; - if (le16_to_cpu(cc->NameLength) == 4 && - strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4) == 0) - *oplock = server->ops->parse_lease_buf(cc, epoch, - lease_key); - else if (buf && (le16_to_cpu(cc->NameLength) == 4) && - strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4) == 0) - parse_query_id_ctxt(cc, buf); - else if ((le16_to_cpu(cc->NameLength) == 16)) { - if (posix && - memcmp(name, smb3_create_tag_posix, 16) == 0) + while (rem >= sizeof(*cc)) { + doff = le16_to_cpu(cc->DataOffset); + dlen = le32_to_cpu(cc->DataLength); + if (check_add_overflow(doff, dlen, &len) || len > rem) + return -EINVAL; + + noff = le16_to_cpu(cc->NameOffset); + nlen = le16_to_cpu(cc->NameLength); + if (noff + nlen > doff) + return -EINVAL; + + name = (char *)cc + noff; + switch (nlen) { + case 4: + if (!strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4)) { + *oplock = server->ops->parse_lease_buf(cc, epoch, + lease_key); + } else if (buf && + !strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4)) { + parse_query_id_ctxt(cc, buf); + } + break; + case 16: + if (posix && !memcmp(name, smb3_create_tag_posix, 16)) parse_posix_ctxt(cc, buf, posix); + break; + default: + cifs_dbg(FYI, "%s: unhandled context (nlen=%zu dlen=%zu)\n", + __func__, nlen, dlen); + if (IS_ENABLED(CONFIG_CIFS_DEBUG2)) + cifs_dump_mem("context data: ", cc, dlen); + break; } - /* else { - cifs_dbg(FYI, "Context not matched with len %d\n", - le16_to_cpu(cc->NameLength)); - cifs_dump_mem("Cctxt name: ", name, 4); - } */ - - next = le32_to_cpu(cc->Next); - if (!next) + + off = le32_to_cpu(cc->Next); + if (!off) break; - remaining -= next; - cc = (struct create_context *)((char *)cc + next); + if (check_sub_overflow(rem, off, &rem)) + return -EINVAL; + cc = (struct create_context *)((u8 *)cc + off); } if (rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) *oplock = rsp->OplockLevel; - return; + return 0; } static int @@ -2916,8 +2934,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, } - smb2_parse_contexts(server, rsp, &oparms->fid->epoch, - oparms->fid->lease_key, oplock, buf, posix); + rc = smb2_parse_contexts(server, &rsp_iov, &oparms->fid->epoch, + oparms->fid->lease_key, oplock, buf, posix); creat_exit: SMB2_open_free(&rqst); free_rsp_buf(resp_buftype, rsp); @@ -4676,7 +4694,7 @@ int SMB2_query_directory_init(const unsigned int xid, memcpy(bufptr, &asteriks, len); req->FileNameOffset = - cpu_to_le16(sizeof(struct smb2_query_directory_req) - 1); + cpu_to_le16(sizeof(struct smb2_query_directory_req)); req->FileNameLength = cpu_to_le16(len); /* * BB could be 30 bytes or so longer if we used SMB2 specific @@ -4873,7 +4891,7 @@ SMB2_set_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, req->AdditionalInformation = cpu_to_le32(additional_info); req->BufferOffset = - cpu_to_le16(sizeof(struct smb2_set_info_req) - 1); + cpu_to_le16(sizeof(struct smb2_set_info_req)); req->BufferLength = cpu_to_le32(*size); memcpy(req->Buffer, *data, *size); @@ -5105,9 +5123,9 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, req->VolatileFileId = volatile_fid; /* 1 for pad */ req->InputBufferOffset = - cpu_to_le16(sizeof(struct smb2_query_info_req) - 1); + cpu_to_le16(sizeof(struct smb2_query_info_req)); req->OutputBufferLength = cpu_to_le32( - outbuf_len + sizeof(struct smb2_query_info_rsp) - 1); + outbuf_len + sizeof(struct smb2_query_info_rsp)); iov->iov_base = (char *)req; iov->iov_len = total_len; diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 89a732b31..eaa873175 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -220,7 +220,7 @@ struct smb2_err_rsp { __le16 StructureSize; __le16 Reserved; /* MBZ */ __le32 ByteCount; /* even if zero, at least one byte follows */ - __u8 ErrorData[1]; /* variable length */ + __u8 ErrorData[]; /* variable length */ } __packed; #define SYMLINK_ERROR_TAG 0x4c4d5953 @@ -464,7 +464,7 @@ struct smb2_negotiate_rsp { __le16 SecurityBufferOffset; __le16 SecurityBufferLength; __le32 NegotiateContextOffset; /* Pre:SMB3.1.1 was reserved/ignored */ - __u8 Buffer[1]; /* variable length GSS security buffer */ + __u8 Buffer[]; /* variable length GSS security buffer */ } __packed; /* Flags */ @@ -481,7 +481,7 @@ struct smb2_sess_setup_req { __le16 SecurityBufferOffset; __le16 SecurityBufferLength; __u64 PreviousSessionId; - __u8 Buffer[1]; /* variable length GSS security buffer */ + __u8 Buffer[]; /* variable length GSS security buffer */ } __packed; /* Currently defined SessionFlags */ @@ -494,7 +494,7 @@ struct smb2_sess_setup_rsp { __le16 SessionFlags; __le16 SecurityBufferOffset; __le16 SecurityBufferLength; - __u8 Buffer[1]; /* variable length GSS security buffer */ + __u8 Buffer[]; /* variable length GSS security buffer */ } __packed; struct smb2_logoff_req { @@ -520,7 +520,7 @@ struct smb2_tree_connect_req { __le16 Flags; /* Reserved MBZ for dialects prior to SMB3.1.1 */ __le16 PathOffset; __le16 PathLength; - __u8 Buffer[1]; /* variable length */ + __u8 Buffer[]; /* variable length */ } __packed; /* See MS-SMB2 section 2.2.9.2 */ @@ -828,7 +828,7 @@ struct smb2_create_rsp { __u64 VolatileFileId; /* opaque endianness */ __le32 CreateContextsOffset; __le32 CreateContextsLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct create_context { @@ -1289,7 +1289,7 @@ struct smb2_read_plain_req { __le32 RemainingBytes; __le16 ReadChannelInfoOffset; __le16 ReadChannelInfoLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* Read flags */ @@ -1304,7 +1304,7 @@ struct smb2_read_rsp { __le32 DataLength; __le32 DataRemaining; __u32 Flags; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* For write request Flags field below the following flags are defined: */ @@ -1324,7 +1324,7 @@ struct smb2_write_req { __le16 WriteChannelInfoOffset; __le16 WriteChannelInfoLength; __le32 Flags; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_write_rsp { @@ -1335,7 +1335,7 @@ struct smb2_write_rsp { __le32 DataLength; __le32 DataRemaining; __u32 Reserved2; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* notify flags */ @@ -1371,7 +1371,7 @@ struct smb2_change_notify_rsp { __le16 StructureSize; /* Must be 9 */ __le16 OutputBufferOffset; __le32 OutputBufferLength; - __u8 Buffer[1]; /* array of file notify structs */ + __u8 Buffer[]; /* array of file notify structs */ } __packed; #define SMB2_LOCKFLAG_SHARED_LOCK 0x0001 @@ -1394,7 +1394,10 @@ struct smb2_lock_req { __u64 PersistentFileId; /* opaque endianness */ __u64 VolatileFileId; /* opaque endianness */ /* Followed by at least one */ - struct smb2_lock_element locks[1]; + union { + struct smb2_lock_element lock; + DECLARE_FLEX_ARRAY(struct smb2_lock_element, locks); + }; } __packed; struct smb2_lock_rsp { @@ -1434,7 +1437,7 @@ struct smb2_query_directory_req { __le16 FileNameOffset; __le16 FileNameLength; __le32 OutputBufferLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_query_directory_rsp { @@ -1442,7 +1445,7 @@ struct smb2_query_directory_rsp { __le16 StructureSize; /* Must be 9 */ __le16 OutputBufferOffset; __le32 OutputBufferLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* Possible InfoType values */ @@ -1483,7 +1486,7 @@ struct smb2_query_info_req { __le32 Flags; __u64 PersistentFileId; /* opaque endianness */ __u64 VolatileFileId; /* opaque endianness */ - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_query_info_rsp { @@ -1491,7 +1494,7 @@ struct smb2_query_info_rsp { __le16 StructureSize; /* Must be 9 */ __le16 OutputBufferOffset; __le32 OutputBufferLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* @@ -1514,7 +1517,7 @@ struct smb2_set_info_req { __le32 AdditionalInformation; __u64 PersistentFileId; /* opaque endianness */ __u64 VolatileFileId; /* opaque endianness */ - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_set_info_rsp { @@ -1716,7 +1719,10 @@ struct smb2_file_all_info { /* data block encoding of response to level 18 */ __le32 Mode; __le32 AlignmentRequirement; __le32 FileNameLength; - char FileName[1]; + union { + char __pad; /* Legacy structure padding */ + DECLARE_FLEX_ARRAY(char, FileName); + }; } __packed; /* level 18 Query */ struct smb2_file_eof_info { /* encoding of request for level 10 */ diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index ed2b4fb01..3184a5efc 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -270,11 +270,13 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *); extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *, enum securityEnum); -extern void smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, - __u8 *oplock, struct smb2_file_all_info *buf, - struct create_posix_rsp *posix); +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix); + extern int smb3_encryption_required(const struct cifs_tcon *tcon); extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length, struct kvec *iov, unsigned int min_buf_size); diff --git a/fs/dcache.c b/fs/dcache.c index ea0485861..976c7474d 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -759,12 +759,12 @@ static inline bool fast_dput(struct dentry *dentry) */ if (unlikely(ret < 0)) { spin_lock(&dentry->d_lock); - if (dentry->d_lockref.count > 1) { - dentry->d_lockref.count--; + if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) { spin_unlock(&dentry->d_lock); return true; } - return false; + dentry->d_lockref.count--; + goto locked; } /* @@ -815,6 +815,7 @@ static inline bool fast_dput(struct dentry *dentry) * else could have killed it and marked it dead. Either way, we * don't need to do anything else. */ +locked: if (dentry->d_lockref.count) { spin_unlock(&dentry->d_lock); return true; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index e23752d9a..c867a0d62 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -76,6 +76,14 @@ static struct inode *__ecryptfs_get_inode(struct inode *lower_inode, if (lower_inode->i_sb != ecryptfs_superblock_to_lower(sb)) return ERR_PTR(-EXDEV); + + /* Reject dealing with casefold directories. */ + if (IS_CASEFOLDED(lower_inode)) { + pr_err_ratelimited("%s: Can't handle casefolded directory.\n", + __func__); + return ERR_PTR(-EREMOTE); + } + if (!igrab(lower_inode)) return ERR_PTR(-ESTALE); inode = iget5_locked(sb, (unsigned long)lower_inode, diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index f921580b5..36693924d 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -24,7 +24,8 @@ struct z_erofs_decompressor { */ int (*prepare_destpages)(struct z_erofs_decompress_req *rq, struct list_head *pagepool); - int (*decompress)(struct z_erofs_decompress_req *rq, u8 *out); + int (*decompress)(struct z_erofs_decompress_req *rq, u8 *out, + u8 *obase); char *name; }; @@ -114,10 +115,13 @@ static void *generic_copy_inplace_data(struct z_erofs_decompress_req *rq, return tmp; } -static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out) +static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out, + u8 *obase) { + const uint nrpages_out = PAGE_ALIGN(rq->pageofs_out + + rq->outputsize) >> PAGE_SHIFT; unsigned int inputmargin, inlen; - u8 *src; + u8 *src, *src2; bool copied, support_0padding; int ret; @@ -125,6 +129,7 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out) return -EOPNOTSUPP; src = kmap_atomic(*rq->in); + src2 = src; inputmargin = 0; support_0padding = false; @@ -148,16 +153,15 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out) if (rq->inplace_io) { const uint oend = (rq->pageofs_out + rq->outputsize) & ~PAGE_MASK; - const uint nr = PAGE_ALIGN(rq->pageofs_out + - rq->outputsize) >> PAGE_SHIFT; - if (rq->partial_decoding || !support_0padding || - rq->out[nr - 1] != rq->in[0] || + rq->out[nrpages_out - 1] != rq->in[0] || rq->inputsize - oend < LZ4_DECOMPRESS_INPLACE_MARGIN(inlen)) { src = generic_copy_inplace_data(rq, src, inputmargin); inputmargin = 0; copied = true; + } else { + src = obase + ((nrpages_out - 1) << PAGE_SHIFT); } } @@ -187,7 +191,7 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out) if (copied) erofs_put_pcpubuf(src); else - kunmap_atomic(src); + kunmap_atomic(src2); return ret; } @@ -257,7 +261,7 @@ static int z_erofs_decompress_generic(struct z_erofs_decompress_req *rq, return PTR_ERR(dst); rq->inplace_io = false; - ret = alg->decompress(rq, dst); + ret = alg->decompress(rq, dst, NULL); if (!ret) copy_from_pcpubuf(rq->out, dst, rq->pageofs_out, rq->outputsize); @@ -291,7 +295,7 @@ static int z_erofs_decompress_generic(struct z_erofs_decompress_req *rq, dst_maptype = 2; dstmap_out: - ret = alg->decompress(rq, dst + rq->pageofs_out); + ret = alg->decompress(rq, dst + rq->pageofs_out, dst); if (!dst_maptype) kunmap_atomic(dst); @@ -888,6 +888,7 @@ int transfer_args_to_stack(struct linux_binprm *bprm, goto out; } + bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE; *sp_location = sp; out: @@ -1392,6 +1393,9 @@ int begin_new_exec(struct linux_binprm * bprm) out_unlock: up_write(&me->signal->exec_update_lock); + if (!bprm->cred) + mutex_unlock(&me->signal->cred_guard_mutex); + out: return retval; } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 193b13630..9e1259272 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2222,7 +2222,7 @@ static int ext4_fill_es_cache_info(struct inode *inode, /* - * ext4_ext_determine_hole - determine hole around given block + * ext4_ext_find_hole - find hole around given block according to the given path * @inode: inode we lookup in * @path: path in extent tree to @lblk * @lblk: pointer to logical block around which we want to determine hole @@ -2234,9 +2234,9 @@ static int ext4_fill_es_cache_info(struct inode *inode, * The function returns the length of a hole starting at @lblk. We update @lblk * to the beginning of the hole if we managed to find it. */ -static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode, - struct ext4_ext_path *path, - ext4_lblk_t *lblk) +static ext4_lblk_t ext4_ext_find_hole(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t *lblk) { int depth = ext_depth(inode); struct ext4_extent *ex; @@ -2264,30 +2264,6 @@ static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode, } /* - * ext4_ext_put_gap_in_cache: - * calculate boundaries of the gap that the requested block fits into - * and cache this gap - */ -static void -ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start, - ext4_lblk_t hole_len) -{ - struct extent_status es; - - ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, - hole_start + hole_len - 1, &es); - if (es.es_len) { - /* There's delayed extent containing lblock? */ - if (es.es_lblk <= hole_start) - return; - hole_len = min(es.es_lblk - hole_start, hole_len); - } - ext_debug(inode, " -> %u:%u\n", hole_start, hole_len); - ext4_es_insert_extent(inode, hole_start, hole_len, ~0, - EXTENT_STATUS_HOLE); -} - -/* * ext4_ext_rm_idx: * removes index from the index block. */ @@ -3131,8 +3107,9 @@ static int ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex) if (ee_len == 0) return 0; - return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock, - EXTENT_STATUS_WRITTEN); + ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock, + EXTENT_STATUS_WRITTEN); + return 0; } /* FIXME!! we need to try to merge to left or right after zero-out */ @@ -4058,6 +4035,69 @@ static int get_implied_cluster_alloc(struct super_block *sb, return 0; } +/* + * Determine hole length around the given logical block, first try to + * locate and expand the hole from the given @path, and then adjust it + * if it's partially or completely converted to delayed extents, insert + * it into the extent cache tree if it's indeed a hole, finally return + * the length of the determined extent. + */ +static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t lblk) +{ + ext4_lblk_t hole_start, len; + struct extent_status es; + + hole_start = lblk; + len = ext4_ext_find_hole(inode, path, &hole_start); +again: + ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, + hole_start + len - 1, &es); + if (!es.es_len) + goto insert_hole; + + /* + * There's a delalloc extent in the hole, handle it if the delalloc + * extent is in front of, behind and straddle the queried range. + */ + if (lblk >= es.es_lblk + es.es_len) { + /* + * The delalloc extent is in front of the queried range, + * find again from the queried start block. + */ + len -= lblk - hole_start; + hole_start = lblk; + goto again; + } else if (in_range(lblk, es.es_lblk, es.es_len)) { + /* + * The delalloc extent containing lblk, it must have been + * added after ext4_map_blocks() checked the extent status + * tree, adjust the length to the delalloc extent's after + * lblk. + */ + len = es.es_lblk + es.es_len - lblk; + return len; + } else { + /* + * The delalloc extent is partially or completely behind + * the queried range, update hole length until the + * beginning of the delalloc extent. + */ + len = min(es.es_lblk - hole_start, len); + } + +insert_hole: + /* Put just found gap into cache to speed up subsequent requests */ + ext_debug(inode, " -> %u:%u\n", hole_start, len); + ext4_es_insert_extent(inode, hole_start, len, ~0, EXTENT_STATUS_HOLE); + + /* Update hole_len to reflect hole size after lblk */ + if (hole_start != lblk) + len -= lblk - hole_start; + + return len; +} /* * Block allocation/map/preallocation routine for extents based files @@ -4175,22 +4215,12 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, * we couldn't try to create block if create flag is zero */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { - ext4_lblk_t hole_start, hole_len; + ext4_lblk_t len; - hole_start = map->m_lblk; - hole_len = ext4_ext_determine_hole(inode, path, &hole_start); - /* - * put just found gap into cache to speed up - * subsequent requests - */ - ext4_ext_put_gap_in_cache(inode, hole_start, hole_len); + len = ext4_ext_determine_insert_hole(inode, path, map->m_lblk); - /* Update hole_len to reflect hole size after map->m_lblk */ - if (hole_start != map->m_lblk) - hole_len -= map->m_lblk - hole_start; map->m_pblk = 0; - map->m_len = min_t(unsigned int, map->m_len, hole_len); - + map->m_len = min_t(unsigned int, map->m_len, len); goto out; } diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index cccbdfd49..f37e62546 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -846,12 +846,10 @@ out: /* * ext4_es_insert_extent() adds information to an inode's extent * status tree. - * - * Return 0 on success, error code on failure. */ -int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len, ext4_fsblk_t pblk, - unsigned int status) +void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, ext4_fsblk_t pblk, + unsigned int status) { struct extent_status newes; ext4_lblk_t end = lblk + len - 1; @@ -863,13 +861,13 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, bool revise_pending = false; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) - return 0; + return; es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n", lblk, len, pblk, status, inode->i_ino); if (!len) - return 0; + return; BUG_ON(end < lblk); @@ -938,7 +936,7 @@ error: goto retry; ext4_es_print_tree(inode); - return 0; + return; } /* diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h index 4ec30a798..481ec4381 100644 --- a/fs/ext4/extents_status.h +++ b/fs/ext4/extents_status.h @@ -127,9 +127,9 @@ extern int __init ext4_init_es(void); extern void ext4_exit_es(void); extern void ext4_es_init_tree(struct ext4_es_tree *tree); -extern int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len, ext4_fsblk_t pblk, - unsigned int status); +extern void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, ext4_fsblk_t pblk, + unsigned int status); extern void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, unsigned int status); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 365c4d3a4..8b48ed351 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -589,10 +589,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk, map->m_lblk + map->m_len - 1)) status |= EXTENT_STATUS_DELAYED; - ret = ext4_es_insert_extent(inode, map->m_lblk, - map->m_len, map->m_pblk, status); - if (ret < 0) - retval = ret; + ext4_es_insert_extent(inode, map->m_lblk, map->m_len, + map->m_pblk, status); } up_read((&EXT4_I(inode)->i_data_sem)); @@ -701,12 +699,8 @@ found: ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk, map->m_lblk + map->m_len - 1)) status |= EXTENT_STATUS_DELAYED; - ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, - map->m_pblk, status); - if (ret < 0) { - retval = ret; - goto out_sem; - } + ext4_es_insert_extent(inode, map->m_lblk, map->m_len, + map->m_pblk, status); } out_sem: @@ -1734,11 +1728,8 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) { - if (ext4_es_is_hole(&es)) { - retval = 0; - down_read(&EXT4_I(inode)->i_data_sem); + if (ext4_es_is_hole(&es)) goto add_delayed; - } /* * Delayed extent could be allocated by fallocate. @@ -1780,27 +1771,11 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, retval = ext4_ext_map_blocks(NULL, inode, map, 0); else retval = ext4_ind_map_blocks(NULL, inode, map, 0); - -add_delayed: - if (retval == 0) { - int ret; - - /* - * XXX: __block_prepare_write() unmaps passed block, - * is it OK? - */ - - ret = ext4_insert_delayed_block(inode, map->m_lblk); - if (ret != 0) { - retval = ret; - goto out_unlock; - } - - map_bh(bh, inode->i_sb, invalid_block); - set_buffer_new(bh); - set_buffer_delay(bh); - } else if (retval > 0) { - int ret; + if (retval < 0) { + up_read(&EXT4_I(inode)->i_data_sem); + return retval; + } + if (retval > 0) { unsigned int status; if (unlikely(retval != map->m_len)) { @@ -1813,15 +1788,23 @@ add_delayed: status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; - ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, - map->m_pblk, status); - if (ret != 0) - retval = ret; + ext4_es_insert_extent(inode, map->m_lblk, map->m_len, + map->m_pblk, status); + up_read(&EXT4_I(inode)->i_data_sem); + return retval; } + up_read(&EXT4_I(inode)->i_data_sem); -out_unlock: - up_read((&EXT4_I(inode)->i_data_sem)); +add_delayed: + down_write(&EXT4_I(inode)->i_data_sem); + retval = ext4_insert_delayed_block(inode, map->m_lblk); + up_write(&EXT4_I(inode)->i_data_sem); + if (retval) + return retval; + map_bh(bh, inode->i_sb, invalid_block); + set_buffer_new(bh); + set_buffer_delay(bh); return retval; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 3babc07ae..c1d632725 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -823,6 +823,24 @@ void ext4_mb_generate_buddy(struct super_block *sb, atomic64_add(period, &sbi->s_mb_generation_time); } +static void mb_regenerate_buddy(struct ext4_buddy *e4b) +{ + int count; + int order = 1; + void *buddy; + + while ((buddy = mb_find_buddy(e4b, order++, &count))) + ext4_set_bits(buddy, 0, count); + + e4b->bd_info->bb_fragments = 0; + memset(e4b->bd_info->bb_counters, 0, + sizeof(*e4b->bd_info->bb_counters) * + (e4b->bd_sb->s_blocksize_bits + 2)); + + ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, + e4b->bd_bitmap, e4b->bd_group, e4b->bd_info); +} + /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve @@ -1476,11 +1494,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); - this_cpu_inc(discard_pa_seq); - e4b->bd_info->bb_free += count; - if (first < e4b->bd_info->bb_first_free) - e4b->bd_info->bb_first_free = first; - /* access memory sequentially: check left neighbour, * clear range and then check right neighbour */ @@ -1494,21 +1507,31 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t blocknr; + /* + * Fastcommit replay can free already freed blocks which + * corrupts allocation info. Regenerate it. + */ + if (sbi->s_mount_state & EXT4_FC_REPLAY) { + mb_regenerate_buddy(e4b); + goto check; + } + blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(sbi, block); - if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { - ext4_grp_locked_error(sb, e4b->bd_group, - inode ? inode->i_ino : 0, - blocknr, - "freeing already freed block (bit %u); block bitmap corrupt.", - block); - ext4_mark_group_bitmap_corrupted( - sb, e4b->bd_group, + ext4_grp_locked_error(sb, e4b->bd_group, + inode ? inode->i_ino : 0, blocknr, + "freeing already freed block (bit %u); block bitmap corrupt.", + block); + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); - } - goto done; + return; } + this_cpu_inc(discard_pa_seq); + e4b->bd_info->bb_free += count; + if (first < e4b->bd_info->bb_first_free) + e4b->bd_info->bb_first_free = first; + /* let's maintain fragments counter */ if (left_is_free && right_is_free) e4b->bd_info->bb_fragments--; @@ -1533,8 +1556,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, if (first <= last) mb_buddy_mark_free(e4b, first >> 1, last >> 1); -done: mb_set_largest_free_order(sb, e4b->bd_info); +check: mb_check_buddy(e4b); } @@ -1854,6 +1877,9 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac, return err; ext4_lock_group(ac->ac_sb, group); + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) + goto out; + max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex); if (max > 0) { @@ -1861,6 +1887,7 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac, ext4_mb_use_best_found(ac, e4b); } +out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); @@ -1889,12 +1916,10 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, if (err) return err; - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) { - ext4_mb_unload_buddy(e4b); - return 0; - } - ext4_lock_group(ac->ac_sb, group); + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) + goto out; + max = mb_find_extent(e4b, ac->ac_g_ex.fe_start, ac->ac_g_ex.fe_len, &ex); ex.fe_logical = 0xDEADFA11; /* debug value */ @@ -1927,6 +1952,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } +out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); @@ -2565,7 +2591,10 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) for (i = 0; i <= 13; i++) seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ? sg.info.bb_counters[i] : 0); - seq_puts(seq, " ]\n"); + seq_puts(seq, " ]"); + if (EXT4_MB_GRP_BBITMAP_CORRUPT(&sg.info)) + seq_puts(seq, " Block bitmap corrupted!"); + seq_puts(seq, "\n"); return 0; } @@ -4136,10 +4165,16 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) .fe_len = ac->ac_g_ex.fe_len, }; loff_t orig_goal_end = extent_logical_end(sbi, &ex); + loff_t o_ex_end = extent_logical_end(sbi, &ac->ac_o_ex); - /* we can't allocate as much as normalizer wants. - * so, found space must get proper lstart - * to cover original request */ + /* + * We can't allocate as much as normalizer wants, so we try + * to get proper lstart to cover the original request, except + * when the goal doesn't cover the original request as below: + * + * orig_ex:2045/2055(10), isize:8417280 -> normalized:0/2048 + * best_ex:0/200(200) -> adjusted: 1848/2048(200) + */ BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical); BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len); @@ -4151,7 +4186,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) * 1. Check if best ex can be kept at end of goal and still * cover original start * 2. Else, check if best ex can be kept at start of goal and - * still cover original start + * still cover original end * 3. Else, keep the best ex at start of original request. */ ex.fe_len = ac->ac_b_ex.fe_len; @@ -4161,7 +4196,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) goto adjust_bex; ex.fe_logical = ac->ac_g_ex.fe_logical; - if (ac->ac_o_ex.fe_logical < extent_logical_end(sbi, &ex)) + if (o_ex_end <= extent_logical_end(sbi, &ex)) goto adjust_bex; ex.fe_logical = ac->ac_o_ex.fe_logical; @@ -4169,7 +4204,6 @@ adjust_bex: ac->ac_b_ex.fe_logical = ex.fe_logical; BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); - BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len); BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end); } @@ -5895,11 +5929,16 @@ __acquires(bitlock) static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb, ext4_group_t grp) { - if (grp < ext4_get_groups_count(sb)) - return EXT4_CLUSTERS_PER_GROUP(sb) - 1; - return (ext4_blocks_count(EXT4_SB(sb)->s_es) - - ext4_group_first_block_no(sb, grp) - 1) >> - EXT4_CLUSTER_BITS(sb); + unsigned long nr_clusters_in_group; + + if (grp < (ext4_get_groups_count(sb) - 1)) + nr_clusters_in_group = EXT4_CLUSTERS_PER_GROUP(sb); + else + nr_clusters_in_group = (ext4_blocks_count(EXT4_SB(sb)->s_es) - + ext4_group_first_block_no(sb, grp)) + >> EXT4_CLUSTER_BITS(sb); + + return nr_clusters_in_group - 1; } static bool ext4_trim_interrupted(void) @@ -5911,13 +5950,15 @@ static int ext4_try_to_trim_range(struct super_block *sb, struct ext4_buddy *e4b, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) { - ext4_grpblk_t next, count, free_count; + ext4_grpblk_t next, count, free_count, last, origin_start; bool set_trimmed = false; void *bitmap; + last = ext4_last_grp_cluster(sb, e4b->bd_group); bitmap = e4b->bd_bitmap; - if (start == 0 && max >= ext4_last_grp_cluster(sb, e4b->bd_group)) + if (start == 0 && max >= last) set_trimmed = true; + origin_start = start; start = max(e4b->bd_info->bb_first_free, start); count = 0; free_count = 0; @@ -5926,7 +5967,10 @@ static int ext4_try_to_trim_range(struct super_block *sb, start = mb_find_next_zero_bit(bitmap, max + 1, start); if (start > max) break; - next = mb_find_next_bit(bitmap, max + 1, start); + + next = mb_find_next_bit(bitmap, last + 1, start); + if (origin_start == 0 && next >= last) + set_trimmed = true; if ((next - start) >= minblocks) { int ret = ext4_trim_extent(sb, start, next - start, e4b); diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 64a579734..f8dd5d972 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -615,6 +615,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, goto out; o_end = o_start + len; + *moved_len = 0; while (o_start < o_end) { struct ext4_extent *ex; ext4_lblk_t cur_blk, next_blk; @@ -670,7 +671,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, */ ext4_double_up_write_data_sem(orig_inode, donor_inode); /* Swap original branches with new branches */ - move_extent_per_page(o_filp, donor_inode, + *moved_len += move_extent_per_page(o_filp, donor_inode, orig_page_index, donor_page_index, offset_in_page, cur_len, unwritten, &ret); @@ -680,9 +681,6 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, o_start += cur_len; d_start += cur_len; } - *moved_len = o_start - orig_blk; - if (*moved_len > len) - *moved_len = len; out: if (*moved_len) { diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 9b4199a1e..5d45ec29e 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -227,17 +227,24 @@ struct ext4_new_flex_group_data { in the flex group */ __u16 *bg_flags; /* block group flags of groups in @groups */ + ext4_group_t resize_bg; /* number of allocated + new_group_data */ ext4_group_t count; /* number of groups in @groups */ }; /* + * Avoiding memory allocation failures due to too many groups added each time. + */ +#define MAX_RESIZE_BG 16384 + +/* * alloc_flex_gd() allocates a ext4_new_flex_group_data with size of * @flexbg_size. * * Returns NULL on failure otherwise address of the allocated structure. */ -static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) +static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned int flexbg_size) { struct ext4_new_flex_group_data *flex_gd; @@ -245,17 +252,18 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) if (flex_gd == NULL) goto out3; - if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data)) - goto out2; - flex_gd->count = flexbg_size; + if (unlikely(flexbg_size > MAX_RESIZE_BG)) + flex_gd->resize_bg = MAX_RESIZE_BG; + else + flex_gd->resize_bg = flexbg_size; - flex_gd->groups = kmalloc_array(flexbg_size, + flex_gd->groups = kmalloc_array(flex_gd->resize_bg, sizeof(struct ext4_new_group_data), GFP_NOFS); if (flex_gd->groups == NULL) goto out2; - flex_gd->bg_flags = kmalloc_array(flexbg_size, sizeof(__u16), + flex_gd->bg_flags = kmalloc_array(flex_gd->resize_bg, sizeof(__u16), GFP_NOFS); if (flex_gd->bg_flags == NULL) goto out1; @@ -292,7 +300,7 @@ static void free_flex_gd(struct ext4_new_flex_group_data *flex_gd) */ static int ext4_alloc_group_tables(struct super_block *sb, struct ext4_new_flex_group_data *flex_gd, - int flexbg_size) + unsigned int flexbg_size) { struct ext4_new_group_data *group_data = flex_gd->groups; ext4_fsblk_t start_blk; @@ -393,12 +401,12 @@ next_group: group = group_data[0].group; printk(KERN_DEBUG "EXT4-fs: adding a flex group with " - "%d groups, flexbg size is %d:\n", flex_gd->count, + "%u groups, flexbg size is %u:\n", flex_gd->count, flexbg_size); for (i = 0; i < flex_gd->count; i++) { ext4_debug( - "adding %s group %u: %u blocks (%d free, %d mdata blocks)\n", + "adding %s group %u: %u blocks (%u free, %u mdata blocks)\n", ext4_bg_has_super(sb, group + i) ? "normal" : "no-super", group + i, group_data[i].blocks_count, @@ -1537,7 +1545,8 @@ exit_journal: int gdb_num = group / EXT4_DESC_PER_BLOCK(sb); int gdb_num_end = ((group + flex_gd->count - 1) / EXT4_DESC_PER_BLOCK(sb)); - int meta_bg = ext4_has_feature_meta_bg(sb); + int meta_bg = ext4_has_feature_meta_bg(sb) && + gdb_num >= le32_to_cpu(es->s_first_meta_bg); sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr - ext4_group_first_block_no(sb, 0); sector_t old_gdb = 0; @@ -1562,8 +1571,7 @@ exit: static int ext4_setup_next_flex_gd(struct super_block *sb, struct ext4_new_flex_group_data *flex_gd, - ext4_fsblk_t n_blocks_count, - unsigned long flexbg_size) + ext4_fsblk_t n_blocks_count) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; @@ -1587,7 +1595,7 @@ static int ext4_setup_next_flex_gd(struct super_block *sb, BUG_ON(last); ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &last); - last_group = group | (flexbg_size - 1); + last_group = group | (flex_gd->resize_bg - 1); if (last_group > n_group) last_group = n_group; @@ -1941,8 +1949,9 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) ext4_fsblk_t o_blocks_count; ext4_fsblk_t n_blocks_count_retry = 0; unsigned long last_update_time = 0; - int err = 0, flexbg_size = 1 << sbi->s_log_groups_per_flex; + int err = 0; int meta_bg; + unsigned int flexbg_size = ext4_flex_bg_size(sbi); /* See if the device is actually as big as what was requested */ bh = ext4_sb_bread(sb, n_blocks_count - 1, 0); @@ -2083,8 +2092,7 @@ retry: /* Add flex groups. Note that a regular group is a * flex group with 1 group. */ - while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count, - flexbg_size)) { + while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count)) { if (jiffies - last_update_time > HZ * 10) { if (last_update_time) ext4_msg(sb, KERN_INFO, diff --git a/fs/ext4/super.c b/fs/ext4/super.c index e386d67cf..0149d3c2c 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -6205,6 +6205,10 @@ static int ext4_write_dquot(struct dquot *dquot) if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to commit dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; @@ -6221,6 +6225,10 @@ static int ext4_acquire_dquot(struct dquot *dquot) if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_acquire(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to acquire dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; @@ -6240,6 +6248,10 @@ static int ext4_release_dquot(struct dquot *dquot) return PTR_ERR(handle); } ret = dquot_release(dquot); + if (ret < 0) + ext4_error_err(dquot->dq_sb, -ret, + "Failed to release dquot type %d", + dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 55818bd51..40e805014 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -3663,7 +3663,13 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count) goto next; } - if (__is_valid_data_blkaddr(blkaddr)) { + /* + * compressed cluster was not released due to it + * fails in release_compress_blocks(), so NEW_ADDR + * is a possible case. + */ + if (blkaddr == NEW_ADDR || + __is_valid_data_blkaddr(blkaddr)) { compr_blocks++; continue; } @@ -3673,6 +3679,11 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count) } reserved = cluster_size - compr_blocks; + + /* for the case all blocks in cluster were reserved */ + if (reserved == 1) + goto next; + ret = inc_valid_block_count(sbi, dn->inode, &reserved); if (ret) return ret; diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index c3c527afd..cd56af93d 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -641,7 +641,16 @@ retry_dn: */ if (dest == NEW_ADDR) { f2fs_truncate_data_blocks_range(&dn, 1); - f2fs_reserve_new_block(&dn); + do { + err = f2fs_reserve_new_block(&dn); + if (err == -ENOSPC) { + f2fs_bug_on(sbi, 1); + break; + } + } while (err && + IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); + if (err) + goto err; continue; } @@ -649,12 +658,14 @@ retry_dn: if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) { if (src == NULL_ADDR) { - err = f2fs_reserve_new_block(&dn); - while (err && - IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) + do { err = f2fs_reserve_new_block(&dn); - /* We should not get -ENOSPC */ - f2fs_bug_on(sbi, err); + if (err == -ENOSPC) { + f2fs_bug_on(sbi, 1); + break; + } + } while (err && + IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); if (err) goto err; } @@ -844,6 +855,8 @@ skip: if (!err && fix_curseg_write_pointer && !f2fs_readonly(sbi->sb) && f2fs_sb_has_blkzoned(sbi)) { err = f2fs_fix_curseg_write_pointer(sbi); + if (!err) + err = f2fs_check_write_pointer(sbi); ret = err; } diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c index af191371c..bab63eeaf 100644 --- a/fs/fat/nfs.c +++ b/fs/fat/nfs.c @@ -130,6 +130,12 @@ fat_encode_fh_nostale(struct inode *inode, __u32 *fh, int *lenp, fid->parent_i_gen = parent->i_generation; type = FILEID_FAT_WITH_PARENT; *lenp = FAT_FID_SIZE_WITH_PARENT; + } else { + /* + * We need to initialize this field because the fh is actually + * 12 bytes long + */ + fid->parent_i_pos_hi = 0; } return type; diff --git a/fs/fhandle.c b/fs/fhandle.c index 01263ffbc..9a5f153c8 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -37,7 +37,7 @@ static long do_sys_name_to_handle(struct path *path, if (f_handle.handle_bytes > MAX_HANDLE_SZ) return -EINVAL; - handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes, + handle = kzalloc(sizeof(struct file_handle) + f_handle.handle_bytes, GFP_KERNEL); if (!handle) return -ENOMEM; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index b0c701c00..d131f34cd 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -451,6 +451,10 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name goto out_put_forget; if (fuse_invalid_attr(&outarg->attr)) goto out_put_forget; + if (outarg->nodeid == FUSE_ROOT_ID && outarg->generation != 0) { + pr_warn_once("root generation should be zero\n"); + outarg->generation = 0; + } *inode = fuse_iget(sb, outarg->nodeid, outarg->generation, &outarg->attr, entry_attr_timeout(outarg), diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index ceaa68683..33eb5fefc 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -873,7 +873,6 @@ static inline bool fuse_stale_inode(const struct inode *inode, int generation, static inline void fuse_make_bad(struct inode *inode) { - remove_inode_hash(inode); set_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state); } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 9ea175ff9..4a7ebccd3 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -352,8 +352,11 @@ retry: } else if (fuse_stale_inode(inode, generation, attr)) { /* nodeid was reused, any I/O on the old inode should fail */ fuse_make_bad(inode); - iput(inode); - goto retry; + if (inode != d_inode(sb->s_root)) { + remove_inode_hash(inode); + iput(inode); + goto retry; + } } done: fi = get_fuse_inode(inode); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 5181e6d4e..bf3cda498 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -135,6 +135,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); + vm_flags_t vm_flags; /* * vma address alignment (but not the pgoff alignment) has @@ -176,10 +177,20 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) file_accessed(file); ret = -ENOMEM; - if (hugetlb_reserve_pages(inode, + + vm_flags = vma->vm_flags; + /* + * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip + * reserving here. Note: only for SHM hugetlbfs file, the inode + * flag S_PRIVATE is set. + */ + if (inode->i_flags & S_PRIVATE) + vm_flags |= VM_NORESERVE; + + if (!hugetlb_reserve_pages(inode, vma->vm_pgoff >> huge_page_order(h), len >> huge_page_shift(h), vma, - vma->vm_flags)) + vm_flags)) goto out; ret = 0; @@ -1234,6 +1245,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par { struct hugetlbfs_fs_context *ctx = fc->fs_private; struct fs_parse_result result; + struct hstate *h; char *rest; unsigned long ps; int opt; @@ -1278,11 +1290,12 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par case Opt_pagesize: ps = memparse(param->string, &rest); - ctx->hstate = size_to_hstate(ps); - if (!ctx->hstate) { + h = size_to_hstate(ps); + if (!h) { pr_err("Unsupported page size %lu MB\n", ps >> 20); return -EINVAL; } + ctx->hstate = h; return 0; case Opt_min_size: @@ -1498,7 +1511,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size, inode->i_size = size; clear_nlink(inode); - if (hugetlb_reserve_pages(inode, 0, + if (!hugetlb_reserve_pages(inode, 0, size >> huge_page_shift(hstate_inode(inode)), NULL, acctflag)) file = ERR_PTR(-ENOMEM); diff --git a/fs/ioctl.c b/fs/ioctl.c index 7bcc60091..b2d06f016 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -799,8 +799,7 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, if (!f.file) return -EBADF; - /* RED-PEN how should LSM module know it's handling 32bit? */ - error = security_file_ioctl(f.file, cmd, arg); + error = security_file_ioctl_compat(f.file, cmd, arg); if (error) goto out; diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index f62b5a501..4c763f573 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -907,8 +907,22 @@ root_found: * we then decide whether to use the Joliet descriptor. */ inode = isofs_iget(s, sbi->s_firstdatazone, 0); - if (IS_ERR(inode)) - goto out_no_root; + + /* + * Fix for broken CDs with a corrupt root inode but a correct Joliet + * root directory. + */ + if (IS_ERR(inode)) { + if (joliet_level && sbi->s_firstdatazone != first_data_zone) { + printk(KERN_NOTICE + "ISOFS: root inode is unusable. " + "Disabling Rock Ridge and switching to Joliet."); + sbi->s_rock = 0; + inode = NULL; + } else { + goto out_no_root; + } + } /* * Fix for broken CDs with Rock Ridge and empty ISO root directory but diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 472932b9e..7898983c9 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -58,28 +58,6 @@ static inline void __buffer_unlink(struct journal_head *jh) } /* - * Move a buffer from the checkpoint list to the checkpoint io list - * - * Called with j_list_lock held - */ -static inline void __buffer_relink_io(struct journal_head *jh) -{ - transaction_t *transaction = jh->b_cp_transaction; - - __buffer_unlink_first(jh); - - if (!transaction->t_checkpoint_io_list) { - jh->b_cpnext = jh->b_cpprev = jh; - } else { - jh->b_cpnext = transaction->t_checkpoint_io_list; - jh->b_cpprev = transaction->t_checkpoint_io_list->b_cpprev; - jh->b_cpprev->b_cpnext = jh; - jh->b_cpnext->b_cpprev = jh; - } - transaction->t_checkpoint_io_list = jh; -} - -/* * Try to release a checkpointed buffer from its transaction. * Returns 1 if we released it and 2 if we also released the * whole transaction. @@ -91,8 +69,7 @@ static int __try_to_free_cp_buf(struct journal_head *jh) int ret = 0; struct buffer_head *bh = jh2bh(jh); - if (jh->b_transaction == NULL && !buffer_locked(bh) && - !buffer_dirty(bh) && !buffer_write_io_error(bh)) { + if (!jh->b_transaction && !buffer_locked(bh) && !buffer_dirty(bh)) { JBUFFER_TRACE(jh, "remove from checkpoint list"); ret = __jbd2_journal_remove_checkpoint(jh) + 1; } @@ -191,6 +168,7 @@ __flush_batch(journal_t *journal, int *batch_count) struct buffer_head *bh = journal->j_chkpt_bhs[i]; BUFFER_TRACE(bh, "brelse"); __brelse(bh); + journal->j_chkpt_bhs[i] = NULL; } *batch_count = 0; } @@ -228,7 +206,6 @@ int jbd2_log_do_checkpoint(journal_t *journal) * OK, we need to start writing disk blocks. Take one transaction * and write it. */ - result = 0; spin_lock(&journal->j_list_lock); if (!journal->j_checkpoint_transactions) goto out; @@ -251,15 +228,6 @@ restart: jh = transaction->t_checkpoint_list; bh = jh2bh(jh); - if (buffer_locked(bh)) { - get_bh(bh); - spin_unlock(&journal->j_list_lock); - wait_on_buffer(bh); - /* the journal_head may have gone by now */ - BUFFER_TRACE(bh, "brelse"); - __brelse(bh); - goto retry; - } if (jh->b_transaction != NULL) { transaction_t *t = jh->b_transaction; tid_t tid = t->t_tid; @@ -294,32 +262,50 @@ restart: spin_lock(&journal->j_list_lock); goto restart; } - if (!buffer_dirty(bh)) { - if (unlikely(buffer_write_io_error(bh)) && !result) - result = -EIO; + if (!trylock_buffer(bh)) { + /* + * The buffer is locked, it may be writing back, or + * flushing out in the last couple of cycles, or + * re-adding into a new transaction, need to check + * it again until it's unlocked. + */ + get_bh(bh); + spin_unlock(&journal->j_list_lock); + wait_on_buffer(bh); + /* the journal_head may have gone by now */ + BUFFER_TRACE(bh, "brelse"); + __brelse(bh); + goto retry; + } else if (!buffer_dirty(bh)) { + unlock_buffer(bh); BUFFER_TRACE(bh, "remove from checkpoint"); - if (__jbd2_journal_remove_checkpoint(jh)) - /* The transaction was released; we're done */ + /* + * If the transaction was released or the checkpoint + * list was empty, we're done. + */ + if (__jbd2_journal_remove_checkpoint(jh) || + !transaction->t_checkpoint_list) goto out; - continue; + } else { + unlock_buffer(bh); + /* + * We are about to write the buffer, it could be + * raced by some other transaction shrink or buffer + * re-log logic once we release the j_list_lock, + * leave it on the checkpoint list and check status + * again to make sure it's clean. + */ + BUFFER_TRACE(bh, "queue"); + get_bh(bh); + J_ASSERT_BH(bh, !buffer_jwrite(bh)); + journal->j_chkpt_bhs[batch_count++] = bh; + transaction->t_chp_stats.cs_written++; + transaction->t_checkpoint_list = jh->b_cpnext; } - /* - * Important: we are about to write the buffer, and - * possibly block, while still holding the journal - * lock. We cannot afford to let the transaction - * logic start messing around with this buffer before - * we write it to disk, as that would break - * recoverability. - */ - BUFFER_TRACE(bh, "queue"); - get_bh(bh); - J_ASSERT_BH(bh, !buffer_jwrite(bh)); - journal->j_chkpt_bhs[batch_count++] = bh; - __buffer_relink_io(jh); - transaction->t_chp_stats.cs_written++; + if ((batch_count == JBD2_NR_BATCH) || - need_resched() || - spin_needbreak(&journal->j_list_lock)) + need_resched() || spin_needbreak(&journal->j_list_lock) || + jh2bh(transaction->t_checkpoint_list) == journal->j_chkpt_bhs[0]) goto unlock_and_flush; } @@ -333,46 +319,9 @@ restart: goto restart; } - /* - * Now we issued all of the transaction's buffers, let's deal - * with the buffers that are out for I/O. - */ -restart2: - /* Did somebody clean up the transaction in the meanwhile? */ - if (journal->j_checkpoint_transactions != transaction || - transaction->t_tid != this_tid) - goto out; - - while (transaction->t_checkpoint_io_list) { - jh = transaction->t_checkpoint_io_list; - bh = jh2bh(jh); - if (buffer_locked(bh)) { - get_bh(bh); - spin_unlock(&journal->j_list_lock); - wait_on_buffer(bh); - /* the journal_head may have gone by now */ - BUFFER_TRACE(bh, "brelse"); - __brelse(bh); - spin_lock(&journal->j_list_lock); - goto restart2; - } - if (unlikely(buffer_write_io_error(bh)) && !result) - result = -EIO; - - /* - * Now in whatever state the buffer currently is, we - * know that it has been written out and so we can - * drop it from the list - */ - if (__jbd2_journal_remove_checkpoint(jh)) - break; - } out: spin_unlock(&journal->j_list_lock); - if (result < 0) - jbd2_journal_abort(journal, result); - else - result = jbd2_cleanup_journal_tail(journal); + result = jbd2_cleanup_journal_tail(journal); return (result < 0) ? result : 0; } diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 72eb5ed54..9b6849b9b 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -63,10 +63,10 @@ */ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); -static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval); -static int dbBackSplit(dmtree_t * tp, int leafno); -static int dbJoin(dmtree_t * tp, int leafno, int newval); -static void dbAdjTree(dmtree_t * tp, int leafno, int newval); +static void dbSplit(dmtree_t *tp, int leafno, int splitsz, int newval, bool is_ctl); +static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl); +static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl); +static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl); static int dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level); static int dbAllocAny(struct bmap * bmp, s64 nblocks, int l2nb, s64 * results); @@ -2171,7 +2171,7 @@ static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, * system. */ if (dp->tree.stree[word] == NOFREE) - dbBackSplit((dmtree_t *) & dp->tree, word); + dbBackSplit((dmtree_t *)&dp->tree, word, false); dbAllocBits(bmp, dp, blkno, nblocks); } @@ -2257,7 +2257,7 @@ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, * the binary system of the leaves if need be. */ dbSplit(tp, word, BUDMIN, - dbMaxBud((u8 *) & dp->wmap[word])); + dbMaxBud((u8 *)&dp->wmap[word]), false); word += 1; } else { @@ -2297,7 +2297,7 @@ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, * system of the leaves to reflect the current * allocation (size). */ - dbSplit(tp, word, size, NOFREE); + dbSplit(tp, word, size, NOFREE, false); /* get the number of dmap words handled */ nw = BUDSIZE(size, BUDMIN); @@ -2404,7 +2404,7 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, /* update the leaf for this dmap word. */ rc = dbJoin(tp, word, - dbMaxBud((u8 *) & dp->wmap[word])); + dbMaxBud((u8 *)&dp->wmap[word]), false); if (rc) return rc; @@ -2437,7 +2437,7 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, /* update the leaf. */ - rc = dbJoin(tp, word, size); + rc = dbJoin(tp, word, size, false); if (rc) return rc; @@ -2589,14 +2589,14 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) * that it is at the front of a binary buddy system. */ if (oldval == NOFREE) { - rc = dbBackSplit((dmtree_t *) dcp, leafno); + rc = dbBackSplit((dmtree_t *)dcp, leafno, true); if (rc) return rc; oldval = dcp->stree[ti]; } - dbSplit((dmtree_t *) dcp, leafno, dcp->budmin, newval); + dbSplit((dmtree_t *) dcp, leafno, dcp->budmin, newval, true); } else { - rc = dbJoin((dmtree_t *) dcp, leafno, newval); + rc = dbJoin((dmtree_t *) dcp, leafno, newval, true); if (rc) return rc; } @@ -2625,7 +2625,7 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) */ if (alloc) { dbJoin((dmtree_t *) dcp, leafno, - oldval); + oldval, true); } else { /* the dbJoin() above might have * caused a larger binary buddy system @@ -2635,9 +2635,9 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) */ if (dcp->stree[ti] == NOFREE) dbBackSplit((dmtree_t *) - dcp, leafno); + dcp, leafno, true); dbSplit((dmtree_t *) dcp, leafno, - dcp->budmin, oldval); + dcp->budmin, oldval, true); } /* release the buffer and return the error. @@ -2685,7 +2685,7 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ -static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) +static void dbSplit(dmtree_t *tp, int leafno, int splitsz, int newval, bool is_ctl) { int budsz; int cursz; @@ -2707,7 +2707,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) while (cursz >= splitsz) { /* update the buddy's leaf with its new value. */ - dbAdjTree(tp, leafno ^ budsz, cursz); + dbAdjTree(tp, leafno ^ budsz, cursz, is_ctl); /* on to the next size and buddy. */ @@ -2719,7 +2719,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) /* adjust the dmap tree to reflect the specified leaf's new * value. */ - dbAdjTree(tp, leafno, newval); + dbAdjTree(tp, leafno, newval, is_ctl); } @@ -2750,7 +2750,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ -static int dbBackSplit(dmtree_t * tp, int leafno) +static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl) { int budsz, bud, w, bsz, size; int cursz; @@ -2801,7 +2801,7 @@ static int dbBackSplit(dmtree_t * tp, int leafno) * system in two. */ cursz = leaf[bud] - 1; - dbSplit(tp, bud, cursz, cursz); + dbSplit(tp, bud, cursz, cursz, is_ctl); break; } } @@ -2829,7 +2829,7 @@ static int dbBackSplit(dmtree_t * tp, int leafno) * * RETURN VALUES: none */ -static int dbJoin(dmtree_t * tp, int leafno, int newval) +static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl) { int budsz, buddy; s8 *leaf; @@ -2884,12 +2884,12 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval) if (leafno < buddy) { /* leafno is the left buddy. */ - dbAdjTree(tp, buddy, NOFREE); + dbAdjTree(tp, buddy, NOFREE, is_ctl); } else { /* buddy is the left buddy and becomes * leafno. */ - dbAdjTree(tp, leafno, NOFREE); + dbAdjTree(tp, leafno, NOFREE, is_ctl); leafno = buddy; } @@ -2902,7 +2902,7 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval) /* update the leaf value. */ - dbAdjTree(tp, leafno, newval); + dbAdjTree(tp, leafno, newval, is_ctl); return 0; } @@ -2923,15 +2923,20 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval) * * RETURN VALUES: none */ -static void dbAdjTree(dmtree_t * tp, int leafno, int newval) +static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl) { int lp, pp, k; - int max; + int max, size; + + size = is_ctl ? CTLTREESIZE : TREESIZE; /* pick up the index of the leaf for this leafno. */ lp = leafno + le32_to_cpu(tp->dmt_leafidx); + if (WARN_ON_ONCE(lp >= size || lp < 0)) + return; + /* is the current value the same as the old value ? if so, * there is nothing to do. */ diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c index 837d42f61..a222a9d71 100644 --- a/fs/jfs/jfs_dtree.c +++ b/fs/jfs/jfs_dtree.c @@ -633,6 +633,11 @@ int dtSearch(struct inode *ip, struct component_name * key, ino_t * data, for (base = 0, lim = p->header.nextindex; lim; lim >>= 1) { index = base + (lim >> 1); + if (stbl[index] < 0) { + rc = -EIO; + goto out; + } + if (p->header.flag & BT_LEAF) { /* uppercase leaf name to compare */ cmp = @@ -1970,7 +1975,7 @@ static int dtSplitRoot(tid_t tid, do { f = &rp->slot[fsi]; fsi = f->next; - } while (fsi != -1); + } while (fsi >= 0); f->next = n; } diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 14f918a48..b0965f3ef 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -2181,6 +2181,9 @@ static int diNewExt(struct inomap * imap, struct iag * iagp, int extno) /* get the ag and iag numbers for this iag. */ agno = BLKTOAG(le64_to_cpu(iagp->agstart), sbi); + if (agno >= MAXAG || agno < 0) + return -EIO; + iagno = le32_to_cpu(iagp->iagnum); /* check if this is the last free extent within the diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index aa4ff7bca..55702b31a 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -172,15 +172,15 @@ int jfs_mount(struct super_block *sb) } jfs_info("jfs_mount: ipimap:0x%p", ipimap); - /* map further access of per fileset inodes by the fileset inode */ - sbi->ipimap = ipimap; - /* initialize fileset inode allocation map */ if ((rc = diMount(ipimap))) { jfs_err("jfs_mount: diMount failed w/rc = %d", rc); goto err_ipimap; } + /* map further access of per fileset inodes by the fileset inode */ + sbi->ipimap = ipimap; + return rc; /* diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index c91ee05cc..0ba056e06 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -696,6 +696,18 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, { struct kernfs_node *kn; + if (parent->mode & S_ISGID) { + /* this code block imitates inode_init_owner() for + * kernfs + */ + + if (parent->iattr) + gid = parent->iattr->ia_gid; + + if (flags & KERNFS_DIR) + mode |= S_ISGID; + } + kn = __kernfs_new_node(kernfs_root(parent), parent, name, mode, uid, gid, flags); if (kn) { diff --git a/fs/namei.c b/fs/namei.c index 3ff954a2b..cb37d7c47 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2771,20 +2771,14 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) p = d_ancestor(p2, p1); if (p) { inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); - inode_lock_nested(p1->d_inode, I_MUTEX_CHILD); + inode_lock_nested(p1->d_inode, I_MUTEX_PARENT2); return p; } p = d_ancestor(p1, p2); - if (p) { - inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); - inode_lock_nested(p2->d_inode, I_MUTEX_CHILD); - return p; - } - - lock_two_inodes(p1->d_inode, p2->d_inode, - I_MUTEX_PARENT, I_MUTEX_PARENT2); - return NULL; + inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); + inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); + return p; } EXPORT_SYMBOL(lock_rename); @@ -4260,11 +4254,12 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * * a) we can get into loop creation. * b) race potential - two innocent renames can create a loop together. - * That's where 4.4 screws up. Current fix: serialization on + * That's where 4.4BSD screws up. Current fix: serialization on * sb->s_vfs_rename_mutex. We might be more accurate, but that's another * story. - * c) we have to lock _four_ objects - parents and victim (if it exists), - * and source. + * c) we may have to lock up to _four_ objects - parents and victim (if it exists), + * and source (if it's a non-directory or a subdirectory that moves to + * different parent). * And that - after we got ->i_mutex on parents (until then we don't know * whether the target exists). Solution: try to be smart with locking * order for inodes. We rely on the fact that tree topology may change @@ -4293,6 +4288,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; struct name_snapshot old_name; + bool lock_old_subdir, lock_new_subdir; if (source == target) return 0; @@ -4342,15 +4338,32 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); /* - * Lock all moved children. Moved directories may need to change parent - * pointer so they need the lock to prevent against concurrent - * directory changes moving parent pointer. For regular files we've - * historically always done this. The lockdep locking subclasses are - * somewhat arbitrary but RENAME_EXCHANGE in particular can swap - * regular files and directories so it's difficult to tell which - * subclasses to use. + * Lock children. + * The source subdirectory needs to be locked on cross-directory + * rename or cross-directory exchange since its parent changes. + * The target subdirectory needs to be locked on cross-directory + * exchange due to parent change and on any rename due to becoming + * a victim. + * Non-directories need locking in all cases (for NFS reasons); + * they get locked after any subdirectories (in inode address order). + * + * NOTE: WE ONLY LOCK UNRELATED DIRECTORIES IN CROSS-DIRECTORY CASE. + * NEVER, EVER DO THAT WITHOUT ->s_vfs_rename_mutex. */ - lock_two_inodes(source, target, I_MUTEX_NORMAL, I_MUTEX_NONDIR2); + lock_old_subdir = new_dir != old_dir; + lock_new_subdir = new_dir != old_dir || !(flags & RENAME_EXCHANGE); + if (is_dir) { + if (lock_old_subdir) + inode_lock_nested(source, I_MUTEX_CHILD); + if (target && (!new_is_dir || lock_new_subdir)) + inode_lock(target); + } else if (new_is_dir) { + if (lock_new_subdir) + inode_lock_nested(target, I_MUTEX_CHILD); + inode_lock(source); + } else { + lock_two_nondirectories(source, target); + } error = -EBUSY; if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry)) @@ -4394,8 +4407,9 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, d_exchange(old_dentry, new_dentry); } out: - inode_unlock(source); - if (target) + if (!is_dir || lock_old_subdir) + inode_unlock(source); + if (target && (!new_is_dir || lock_new_subdir)) inode_unlock(target); dput(new_dentry); if (!error) { diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 5d86ffa72..499519f0f 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -678,10 +678,17 @@ static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq) LIST_HEAD(mds_list); nfs_init_cinfo_from_dreq(&cinfo, dreq); + nfs_commit_begin(cinfo.mds); nfs_scan_commit(dreq->inode, &mds_list, &cinfo); res = nfs_generic_commit_list(dreq->inode, &mds_list, 0, &cinfo); - if (res < 0) /* res == -ENOMEM */ - nfs_direct_write_reschedule(dreq); + if (res < 0) { /* res == -ENOMEM */ + spin_lock(&dreq->lock); + if (dreq->flags == 0) + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + spin_unlock(&dreq->lock); + } + if (nfs_commit_end(cinfo.mds)) + nfs_direct_write_complete(dreq); } static void nfs_direct_write_clear_reqs(struct nfs_direct_req *dreq) diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index 0fe5aacbc..e7192d0ee 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -54,11 +54,14 @@ int nfs42_proc_removexattr(struct inode *inode, const char *name); * They would be 7 bytes long in the eventual buffer ("user.x\0"), and * 8 bytes long XDR-encoded. * - * Include the trailing eof word as well. + * Include the trailing eof word as well and make the result a multiple + * of 4 bytes. */ static inline u32 nfs42_listxattr_xdrsize(u32 buflen) { - return ((buflen / (XATTR_USER_PREFIX_LEN + 2)) * 8) + 4; + u32 size = 8 * buflen / (XATTR_USER_PREFIX_LEN + 2) + 4; + + return (size + 3) & ~3; } #endif /* CONFIG_NFS_V4_2 */ #endif /* __LINUX_FS_NFS_NFS4_2_H */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 7c3c96ed6..8e546e6a5 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -10370,29 +10370,33 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = { static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) { ssize_t error, error2, error3; + size_t left = size; - error = generic_listxattr(dentry, list, size); + error = generic_listxattr(dentry, list, left); if (error < 0) return error; if (list) { list += error; - size -= error; + left -= error; } - error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, size); + error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, left); if (error2 < 0) return error2; if (list) { list += error2; - size -= error2; + left -= error2; } - error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, size); + error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, left); if (error3 < 0) return error3; - return error + error2 + error3; + error += error2 + error3; + if (size && error > size) + return -ERANGE; + return error; } static void nfs4_enable_swap(struct inode *inode) diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index fa1483088..c2cf4ff62 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -175,10 +175,10 @@ static int __init root_nfs_cat(char *dest, const char *src, size_t len = strlen(dest); if (len && dest[len - 1] != ',') - if (strlcat(dest, ",", destlen) > destlen) + if (strlcat(dest, ",", destlen) >= destlen) return -1; - if (strlcat(dest, src, destlen) > destlen) + if (strlcat(dest, src, destlen) >= destlen) return -1; return 0; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index d3cd099ff..4cf060691 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1637,7 +1637,7 @@ static int wait_on_commit(struct nfs_mds_commit_info *cinfo) !atomic_read(&cinfo->rpcs_out)); } -static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) +void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) { atomic_inc(&cinfo->rpcs_out); } diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 65cd599cb..4905b7cd7 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -724,7 +724,7 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, dat = nilfs_bmap_get_dat(btree); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) - goto out; + goto dat_error; ptr = blocknr; } cnt = 1; @@ -743,7 +743,7 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) - goto out; + goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt || ++cnt == maxblocks) @@ -782,6 +782,11 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, out: nilfs_btree_free_path(path); return ret; + + dat_error: + if (ret == -ENOENT) + ret = -EINVAL; /* Notify bmap layer of metadata corruption */ + goto out; } static void nilfs_btree_promote_key(struct nilfs_bmap *btree, diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index 8fedc7104..22b1ca5c3 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -40,8 +40,21 @@ static inline struct nilfs_dat_info *NILFS_DAT_I(struct inode *dat) static int nilfs_dat_prepare_entry(struct inode *dat, struct nilfs_palloc_req *req, int create) { - return nilfs_palloc_get_entry_block(dat, req->pr_entry_nr, - create, &req->pr_entry_bh); + int ret; + + ret = nilfs_palloc_get_entry_block(dat, req->pr_entry_nr, + create, &req->pr_entry_bh); + if (unlikely(ret == -ENOENT)) { + nilfs_err(dat->i_sb, + "DAT doesn't have a block to manage vblocknr = %llu", + (unsigned long long)req->pr_entry_nr); + /* + * Return internal code -EINVAL to notify bmap layer of + * metadata corruption. + */ + ret = -EINVAL; + } + return ret; } static void nilfs_dat_commit_entry(struct inode *dat, @@ -123,11 +136,7 @@ static void nilfs_dat_commit_free(struct inode *dat, int nilfs_dat_prepare_start(struct inode *dat, struct nilfs_palloc_req *req) { - int ret; - - ret = nilfs_dat_prepare_entry(dat, req, 0); - WARN_ON(ret == -ENOENT); - return ret; + return nilfs_dat_prepare_entry(dat, req, 0); } void nilfs_dat_commit_start(struct inode *dat, struct nilfs_palloc_req *req, @@ -154,10 +163,8 @@ int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req) int ret; ret = nilfs_dat_prepare_entry(dat, req, 0); - if (ret < 0) { - WARN_ON(ret == -ENOENT); + if (ret < 0) return ret; - } kaddr = kmap_atomic(req->pr_entry_bh->b_page); entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr, diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index 81394e22d..eb7de9e2a 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -243,7 +243,7 @@ nilfs_filetype_table[NILFS_FT_MAX] = { #define S_SHIFT 12 static unsigned char -nilfs_type_by_mode[S_IFMT >> S_SHIFT] = { +nilfs_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = { [S_IFREG >> S_SHIFT] = NILFS_FT_REG_FILE, [S_IFDIR >> S_SHIFT] = NILFS_FT_DIR, [S_IFCHR >> S_SHIFT] = NILFS_FT_CHRDEV, diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index f35310195..7faf8c285 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -66,7 +66,7 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, dat = nilfs_bmap_get_dat(direct); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) - return ret; + goto dat_error; ptr = blocknr; } @@ -79,7 +79,7 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) - return ret; + goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt) @@ -87,6 +87,11 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, } *ptrp = ptr; return cnt; + + dat_error: + if (ret == -ENOENT) + ret = -EINVAL; /* Notify bmap layer of metadata corruption */ + return ret; } static __u64 diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index e1bd592ce..5611a3534 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -105,7 +105,13 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf) nilfs_transaction_commit(inode->i_sb); mapped: - wait_for_stable_page(page); + /* + * Since checksumming including data blocks is performed to determine + * the validity of the log to be written and used for recovery, it is + * necessary to wait for writeback to finish here, regardless of the + * stable write requirement of the backing device. + */ + wait_on_page_writeback(page); out: sb_end_pagefault(inode->i_sb); return block_page_mkwrite_return(ret); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index d144e08a9..06f4deb55 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -112,7 +112,7 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, "%s (ino=%lu): a race condition while inserting a data block at offset=%llu", __func__, inode->i_ino, (unsigned long long)blkoff); - err = 0; + err = -EAGAIN; } nilfs_transaction_abort(inode->i_sb); goto out; diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 2217f904a..188b8cc52 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -472,9 +472,10 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs, static int nilfs_recovery_copy_block(struct the_nilfs *nilfs, struct nilfs_recovery_block *rb, - struct page *page) + loff_t pos, struct page *page) { struct buffer_head *bh_org; + size_t from = pos & ~PAGE_MASK; void *kaddr; bh_org = __bread(nilfs->ns_bdev, rb->blocknr, nilfs->ns_blocksize); @@ -482,7 +483,7 @@ static int nilfs_recovery_copy_block(struct the_nilfs *nilfs, return -EIO; kaddr = kmap_atomic(page); - memcpy(kaddr + bh_offset(bh_org), bh_org->b_data, bh_org->b_size); + memcpy(kaddr + from, bh_org->b_data, bh_org->b_size); kunmap_atomic(kaddr); brelse(bh_org); return 0; @@ -521,7 +522,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, goto failed_inode; } - err = nilfs_recovery_copy_block(nilfs, rb, page); + err = nilfs_recovery_copy_block(nilfs, rb, pos, page); if (unlikely(err)) goto failed_page; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 418055ac9..be0ca35b8 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1707,7 +1707,6 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { - set_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { if (bh->b_page != bd_page) { lock_page(bd_page); @@ -1718,6 +1717,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) } break; } + set_buffer_async_write(bh); if (bh->b_page != fs_page) { nilfs_begin_page_io(fs_page); fs_page = bh->b_page; @@ -1803,7 +1803,6 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { - clear_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { @@ -1812,6 +1811,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) } break; } + clear_buffer_async_write(bh); if (bh->b_page != fs_page) { nilfs_end_page_io(fs_page, err); fs_page = bh->b_page; @@ -1899,8 +1899,9 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) BIT(BH_Delay) | BIT(BH_NILFS_Volatile) | BIT(BH_NILFS_Redirected)); - set_mask_bits(&bh->b_state, clear_bits, set_bits); if (bh == segbuf->sb_super_root) { + set_buffer_uptodate(bh); + clear_buffer_dirty(bh); if (bh->b_page != bd_page) { end_page_writeback(bd_page); bd_page = bh->b_page; @@ -1908,6 +1909,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) update_sr = true; break; } + set_mask_bits(&bh->b_state, clear_bits, set_bits); if (bh->b_page != fs_page) { nilfs_end_page_io(fs_page, 0); fs_page = bh->b_page; @@ -435,12 +435,10 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) goto out; } -#ifdef CONFIG_WATCH_QUEUE - if (pipe->watch_queue) { + if (pipe_has_watch_queue(pipe)) { ret = -EXDEV; goto out; } -#endif /* * If it wasn't empty we try to merge new data into @@ -1302,6 +1300,11 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) pipe->tail = tail; pipe->head = head; + if (!pipe_has_watch_queue(pipe)) { + pipe->max_usage = nr_slots; + pipe->nr_accounted = nr_slots; + } + spin_unlock_irq(&pipe->rd_wait.lock); /* This might have made more room for writers */ @@ -1319,10 +1322,8 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) unsigned int nr_slots, size; long ret = 0; -#ifdef CONFIG_WATCH_QUEUE - if (pipe->watch_queue) + if (pipe_has_watch_queue(pipe)) return -EBUSY; -#endif size = round_pipe_size(arg); nr_slots = size >> PAGE_SHIFT; @@ -1355,8 +1356,6 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) if (ret < 0) goto out_revert_acct; - pipe->max_usage = nr_slots; - pipe->nr_accounted = nr_slots; return pipe->max_usage * PAGE_SIZE; out_revert_acct: @@ -1375,10 +1374,8 @@ struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) if (file->f_op != &pipefifo_fops || !pipe) return NULL; -#ifdef CONFIG_WATCH_QUEUE - if (for_splice && pipe->watch_queue) + if (for_splice && pipe_has_watch_queue(pipe)) return NULL; -#endif return pipe; } diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 98e579ce0..44fc3b396 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -519,6 +519,7 @@ static int ramoops_init_przs(const char *name, } zone_sz = mem_sz / *cnt; + zone_sz = ALIGN_DOWN(zone_sz, 2); if (!zone_sz) { dev_err(dev, "%s zone size == 0\n", name); goto fail; diff --git a/fs/pstore/zone.c b/fs/pstore/zone.c index b50fc33f2..2426fb679 100644 --- a/fs/pstore/zone.c +++ b/fs/pstore/zone.c @@ -973,6 +973,8 @@ static ssize_t psz_kmsg_read(struct pstore_zone *zone, char *buf = kasprintf(GFP_KERNEL, "%s: Total %d times\n", kmsg_dump_reason_str(record->reason), record->count); + if (!buf) + return -ENOMEM; hlen = strlen(buf); record->buf = krealloc(buf, hlen + size, GFP_KERNEL); if (!record->buf) { diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 4bb4b4b79..6a7b7d447 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -401,15 +401,17 @@ int dquot_mark_dquot_dirty(struct dquot *dquot) EXPORT_SYMBOL(dquot_mark_dquot_dirty); /* Dirtify all the dquots - this can block when journalling */ -static inline int mark_all_dquot_dirty(struct dquot * const *dquot) +static inline int mark_all_dquot_dirty(struct dquot __rcu * const *dquots) { int ret, err, cnt; + struct dquot *dquot; ret = err = 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquot[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) /* Even in case of error we have to continue */ - ret = mark_dquot_dirty(dquot[cnt]); + ret = mark_dquot_dirty(dquot); if (!err) err = ret; } @@ -1006,14 +1008,15 @@ out: } EXPORT_SYMBOL(dqget); -static inline struct dquot **i_dquot(struct inode *inode) +static inline struct dquot __rcu **i_dquot(struct inode *inode) { - return inode->i_sb->s_op->get_dquots(inode); + /* Force __rcu for now until filesystems are fixed */ + return (struct dquot __rcu **)inode->i_sb->s_op->get_dquots(inode); } static int dqinit_needed(struct inode *inode, int type) { - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) @@ -1086,59 +1089,7 @@ out: return err; } -/* - * Remove references to dquots from inode and add dquot to list for freeing - * if we have the last reference to dquot - */ -static void remove_inode_dquot_ref(struct inode *inode, int type, - struct list_head *tofree_head) -{ - struct dquot **dquots = i_dquot(inode); - struct dquot *dquot = dquots[type]; - - if (!dquot) - return; - - dquots[type] = NULL; - if (list_empty(&dquot->dq_free)) { - /* - * The inode still has reference to dquot so it can't be in the - * free list - */ - spin_lock(&dq_list_lock); - list_add(&dquot->dq_free, tofree_head); - spin_unlock(&dq_list_lock); - } else { - /* - * Dquot is already in a list to put so we won't drop the last - * reference here. - */ - dqput(dquot); - } -} - -/* - * Free list of dquots - * Dquots are removed from inodes and no new references can be got so we are - * the only ones holding reference - */ -static void put_dquot_list(struct list_head *tofree_head) -{ - struct list_head *act_head; - struct dquot *dquot; - - act_head = tofree_head->next; - while (act_head != tofree_head) { - dquot = list_entry(act_head, struct dquot, dq_free); - act_head = act_head->next; - /* Remove dquot from the list so we won't have problems... */ - list_del_init(&dquot->dq_free); - dqput(dquot); - } -} - -static void remove_dquot_ref(struct super_block *sb, int type, - struct list_head *tofree_head) +static void remove_dquot_ref(struct super_block *sb, int type) { struct inode *inode; #ifdef CONFIG_QUOTA_DEBUG @@ -1155,11 +1106,18 @@ static void remove_dquot_ref(struct super_block *sb, int type, */ spin_lock(&dq_data_lock); if (!IS_NOQUOTA(inode)) { + struct dquot __rcu **dquots = i_dquot(inode); + struct dquot *dquot = srcu_dereference_check( + dquots[type], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + #ifdef CONFIG_QUOTA_DEBUG if (unlikely(inode_get_rsv_space(inode) > 0)) reserved = 1; #endif - remove_inode_dquot_ref(inode, type, tofree_head); + rcu_assign_pointer(dquots[type], NULL); + if (dquot) + dqput(dquot); } spin_unlock(&dq_data_lock); } @@ -1176,13 +1134,8 @@ static void remove_dquot_ref(struct super_block *sb, int type, /* Gather all references from inodes and drop them */ static void drop_dquot_ref(struct super_block *sb, int type) { - LIST_HEAD(tofree_head); - - if (sb->dq_op) { - remove_dquot_ref(sb, type, &tofree_head); - synchronize_srcu(&dquot_srcu); - put_dquot_list(&tofree_head); - } + if (sb->dq_op) + remove_dquot_ref(sb, type); } static inline @@ -1515,7 +1468,8 @@ static int inode_quota_active(const struct inode *inode) static int __dquot_initialize(struct inode *inode, int type) { int cnt, init_needed = 0; - struct dquot **dquots, *got[MAXQUOTAS] = {}; + struct dquot __rcu **dquots; + struct dquot *got[MAXQUOTAS] = {}; struct super_block *sb = inode->i_sb; qsize_t rsv; int ret = 0; @@ -1590,7 +1544,7 @@ static int __dquot_initialize(struct inode *inode, int type) if (!got[cnt]) continue; if (!dquots[cnt]) { - dquots[cnt] = got[cnt]; + rcu_assign_pointer(dquots[cnt], got[cnt]); got[cnt] = NULL; /* * Make quota reservation system happy if someone @@ -1598,12 +1552,16 @@ static int __dquot_initialize(struct inode *inode, int type) */ rsv = inode_get_rsv_space(inode); if (unlikely(rsv)) { + struct dquot *dquot = srcu_dereference_check( + dquots[cnt], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + spin_lock(&inode->i_lock); /* Get reservation again under proper lock */ rsv = __inode_get_rsv_space(inode); - spin_lock(&dquots[cnt]->dq_dqb_lock); - dquots[cnt]->dq_dqb.dqb_rsvspace += rsv; - spin_unlock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); + dquot->dq_dqb.dqb_rsvspace += rsv; + spin_unlock(&dquot->dq_dqb_lock); spin_unlock(&inode->i_lock); } } @@ -1625,7 +1583,7 @@ EXPORT_SYMBOL(dquot_initialize); bool dquot_initialize_needed(struct inode *inode) { - struct dquot **dquots; + struct dquot __rcu **dquots; int i; if (!inode_quota_active(inode)) @@ -1650,13 +1608,14 @@ EXPORT_SYMBOL(dquot_initialize_needed); static void __dquot_drop(struct inode *inode) { int cnt; - struct dquot **dquots = i_dquot(inode); + struct dquot __rcu **dquots = i_dquot(inode); struct dquot *put[MAXQUOTAS]; spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - put[cnt] = dquots[cnt]; - dquots[cnt] = NULL; + put[cnt] = srcu_dereference_check(dquots[cnt], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + rcu_assign_pointer(dquots[cnt], NULL); } spin_unlock(&dq_data_lock); dqput_all(put); @@ -1664,7 +1623,7 @@ static void __dquot_drop(struct inode *inode) void dquot_drop(struct inode *inode) { - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) @@ -1737,7 +1696,8 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; int reserve = flags & DQUOT_SPACE_RESERVE; - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; if (!inode_quota_active(inode)) { if (reserve) { @@ -1757,27 +1717,26 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; if (reserve) { - ret = dquot_add_space(dquots[cnt], 0, number, flags, - &warn[cnt]); + ret = dquot_add_space(dquot, 0, number, flags, &warn[cnt]); } else { - ret = dquot_add_space(dquots[cnt], number, 0, flags, - &warn[cnt]); + ret = dquot_add_space(dquot, number, 0, flags, &warn[cnt]); } if (ret) { /* Back out changes we already did */ for (cnt--; cnt >= 0; cnt--) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); if (reserve) - dquot_free_reserved_space(dquots[cnt], - number); + dquot_free_reserved_space(dquot, number); else - dquot_decr_space(dquots[cnt], number); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + dquot_decr_space(dquot, number); + spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); goto out_flush_warn; @@ -1807,7 +1766,8 @@ int dquot_alloc_inode(struct inode *inode) { int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; + struct dquot *dquot; if (!inode_quota_active(inode)) return 0; @@ -1818,17 +1778,19 @@ int dquot_alloc_inode(struct inode *inode) index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - ret = dquot_add_inodes(dquots[cnt], 1, &warn[cnt]); + ret = dquot_add_inodes(dquot, 1, &warn[cnt]); if (ret) { for (cnt--; cnt >= 0; cnt--) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; /* Back out changes we already did */ - spin_lock(&dquots[cnt]->dq_dqb_lock); - dquot_decr_inodes(dquots[cnt], 1); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); + dquot_decr_inodes(dquot, 1); + spin_unlock(&dquot->dq_dqb_lock); } goto warn_put_all; } @@ -1849,7 +1811,8 @@ EXPORT_SYMBOL(dquot_alloc_inode); */ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) { - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { @@ -1865,9 +1828,8 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquots[cnt]) { - struct dquot *dquot = dquots[cnt]; - + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_rsvspace < number)) number = dquot->dq_dqb.dqb_rsvspace; @@ -1891,7 +1853,8 @@ EXPORT_SYMBOL(dquot_claim_space_nodirty); */ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) { - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { @@ -1907,9 +1870,8 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquots[cnt]) { - struct dquot *dquot = dquots[cnt]; - + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number)) number = dquot->dq_dqb.dqb_curspace; @@ -1935,7 +1897,8 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int reserve = flags & DQUOT_SPACE_RESERVE, index; if (!inode_quota_active(inode)) { @@ -1956,17 +1919,18 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) int wtype; warn[cnt].w_type = QUOTA_NL_NOWARN; - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); - wtype = info_bdq_free(dquots[cnt], number); + spin_lock(&dquot->dq_dqb_lock); + wtype = info_bdq_free(dquot, number); if (wtype != QUOTA_NL_NOWARN) - prepare_warning(&warn[cnt], dquots[cnt], wtype); + prepare_warning(&warn[cnt], dquot, wtype); if (reserve) - dquot_free_reserved_space(dquots[cnt], number); + dquot_free_reserved_space(dquot, number); else - dquot_decr_space(dquots[cnt], number); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + dquot_decr_space(dquot, number); + spin_unlock(&dquot->dq_dqb_lock); } if (reserve) *inode_reserved_space(inode) -= number; @@ -1990,7 +1954,8 @@ void dquot_free_inode(struct inode *inode) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; + struct dquot *dquot; int index; if (!inode_quota_active(inode)) @@ -2001,16 +1966,16 @@ void dquot_free_inode(struct inode *inode) spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { int wtype; - warn[cnt].w_type = QUOTA_NL_NOWARN; - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); - wtype = info_idq_free(dquots[cnt], 1); + spin_lock(&dquot->dq_dqb_lock); + wtype = info_idq_free(dquot, 1); if (wtype != QUOTA_NL_NOWARN) - prepare_warning(&warn[cnt], dquots[cnt], wtype); - dquot_decr_inodes(dquots[cnt], 1); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + prepare_warning(&warn[cnt], dquot, wtype); + dquot_decr_inodes(dquot, 1); + spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); mark_all_dquot_dirty(dquots); @@ -2036,8 +2001,9 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) qsize_t cur_space; qsize_t rsv_space = 0; qsize_t inode_usage = 1; + struct dquot __rcu **dquots; struct dquot *transfer_from[MAXQUOTAS] = {}; - int cnt, ret = 0; + int cnt, index, ret = 0; char is_valid[MAXQUOTAS] = {}; struct dquot_warn warn_to[MAXQUOTAS]; struct dquot_warn warn_from_inodes[MAXQUOTAS]; @@ -2068,6 +2034,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) } cur_space = __inode_get_bytes(inode); rsv_space = __inode_get_rsv_space(inode); + dquots = i_dquot(inode); /* * Build the transfer_from list, check limits, and update usage in * the target structures. @@ -2082,7 +2049,8 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) if (!sb_has_quota_active(inode->i_sb, cnt)) continue; is_valid[cnt] = 1; - transfer_from[cnt] = i_dquot(inode)[cnt]; + transfer_from[cnt] = srcu_dereference_check(dquots[cnt], + &dquot_srcu, lockdep_is_held(&dq_data_lock)); ret = dquot_add_inodes(transfer_to[cnt], inode_usage, &warn_to[cnt]); if (ret) @@ -2121,13 +2089,21 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) rsv_space); spin_unlock(&transfer_from[cnt]->dq_dqb_lock); } - i_dquot(inode)[cnt] = transfer_to[cnt]; + rcu_assign_pointer(dquots[cnt], transfer_to[cnt]); } spin_unlock(&inode->i_lock); spin_unlock(&dq_data_lock); - mark_all_dquot_dirty(transfer_from); - mark_all_dquot_dirty(transfer_to); + /* + * These arrays are local and we hold dquot references so we don't need + * the srcu protection but still take dquot_srcu to avoid warning in + * mark_all_dquot_dirty(). + */ + index = srcu_read_lock(&dquot_srcu); + mark_all_dquot_dirty((struct dquot __rcu **)transfer_from); + mark_all_dquot_dirty((struct dquot __rcu **)transfer_to); + srcu_read_unlock(&dquot_srcu, index); + flush_warnings(warn_to); flush_warnings(warn_from_inodes); flush_warnings(warn_from_space); diff --git a/fs/select.c b/fs/select.c index 5edffee11..668a52005 100644 --- a/fs/select.c +++ b/fs/select.c @@ -475,7 +475,7 @@ static inline void wait_key_set(poll_table *wait, unsigned long in, wait->_key |= POLLOUT_SET; } -static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) +static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) { ktime_t expire, *to = NULL; struct poll_wqueues table; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 96d0da65e..f51b23968 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -429,6 +429,8 @@ struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, kn = kernfs_find_and_get(kobj->sd, attr->name); if (kn) kernfs_break_active_protection(kn); + else + kobject_put(kobj); return kn; } EXPORT_SYMBOL_GPL(sysfs_break_active_protection); diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index e3d1673b8..ef9bcfeec 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -82,9 +82,6 @@ static inline sysv_zone_t *block_end(struct buffer_head *bh) return (sysv_zone_t*)((char*)bh->b_data + bh->b_size); } -/* - * Requires read_lock(&pointers_lock) or write_lock(&pointers_lock) - */ static Indirect *get_branch(struct inode *inode, int depth, int offsets[], @@ -104,15 +101,18 @@ static Indirect *get_branch(struct inode *inode, bh = sb_bread(sb, block); if (!bh) goto failure; + read_lock(&pointers_lock); if (!verify_chain(chain, p)) goto changed; add_chain(++p, bh, (sysv_zone_t*)bh->b_data + *++offsets); + read_unlock(&pointers_lock); if (!p->key) goto no_block; } return NULL; changed: + read_unlock(&pointers_lock); brelse(bh); *err = -EAGAIN; goto no_block; @@ -218,9 +218,7 @@ static int get_block(struct inode *inode, sector_t iblock, struct buffer_head *b goto out; reread: - read_lock(&pointers_lock); partial = get_branch(inode, depth, offsets, chain, &err); - read_unlock(&pointers_lock); /* Simplest case - block found, no allocation needed */ if (!partial) { @@ -290,9 +288,9 @@ static Indirect *find_shared(struct inode *inode, *top = 0; for (k = depth; k > 1 && !offsets[k-1]; k--) ; + partial = get_branch(inode, k, offsets, chain, &err); write_lock(&pointers_lock); - partial = get_branch(inode, k, offsets, chain, &err); if (!partial) partial = chain + k-1; /* diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index bc562b107..11cd921df 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -1198,6 +1198,8 @@ out_cancel: dir_ui->ui_size = dir->i_size; mutex_unlock(&dir_ui->ui_mutex); out_inode: + /* Free inode->i_link before inode is marked as bad. */ + fscrypt_free_inode(inode); make_bad_inode(inode); iput(inode); out_fname: diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 19fdcda04..18df7a825 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -262,9 +262,6 @@ static int write_begin_slow(struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } if (PagePrivate(page)) @@ -463,9 +460,6 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } err = allocate_budget(c, page, ui, appending); @@ -475,10 +469,8 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, * If we skipped reading the page because we were going to * write all of it, then it is not up to date. */ - if (skipped_read) { + if (skipped_read) ClearPageChecked(page); - ClearPageUptodate(page); - } /* * Budgeting failed which means it would have to force * write-back but didn't, because we set the @fast flag in the @@ -569,6 +561,9 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping, goto out; } + if (len == PAGE_SIZE) + SetPageUptodate(page); + if (!PagePrivate(page)) { attach_page_private(page, (void *)1); atomic_long_inc(&c->dirty_pg_cnt); diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index c578e772c..f11bcbac7 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -151,7 +151,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc) if (!sbi->nls) { vbg_err("vboxsf: Count not load '%s' nls\n", nls_name); err = -EINVAL; - goto fail_free; + goto fail_destroy_idr; } } @@ -224,6 +224,7 @@ fail_free: ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id); if (sbi->nls) unload_nls(sbi->nls); +fail_destroy_idr: idr_destroy(&sbi->ino_idr); kfree(sbi); return err; diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index b9522eee1..f9ecade9e 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -319,16 +319,18 @@ static loff_t zonefs_check_zone_condition(struct inode *inode, } } -struct zonefs_ioerr_data { - struct inode *inode; - bool write; -}; - static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, void *data) { - struct zonefs_ioerr_data *err = data; - struct inode *inode = err->inode; + struct blk_zone *z = data; + + *z = *zone; + return 0; +} + +static void zonefs_handle_io_error(struct inode *inode, struct blk_zone *zone, + bool write) +{ struct zonefs_inode_info *zi = ZONEFS_I(inode); struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); @@ -344,8 +346,8 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, isize = i_size_read(inode); if (zone->cond != BLK_ZONE_COND_OFFLINE && zone->cond != BLK_ZONE_COND_READONLY && - !err->write && isize == data_size) - return 0; + !write && isize == data_size) + return; /* * At this point, we detected either a bad zone or an inconsistency @@ -366,8 +368,9 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, * In all cases, warn about inode size inconsistency and handle the * IO error according to the zone condition and to the mount options. */ - if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && isize != data_size) - zonefs_warn(sb, "inode %lu: invalid size %lld (should be %lld)\n", + if (isize != data_size) + zonefs_warn(sb, + "inode %lu: invalid size %lld (should be %lld)\n", inode->i_ino, isize, data_size); /* @@ -427,8 +430,6 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, zonefs_update_stats(inode, data_size); zonefs_i_size_write(inode, data_size); zi->i_wpoffset = data_size; - - return 0; } /* @@ -442,23 +443,25 @@ static void __zonefs_io_error(struct inode *inode, bool write) { struct zonefs_inode_info *zi = ZONEFS_I(inode); struct super_block *sb = inode->i_sb; - struct zonefs_sb_info *sbi = ZONEFS_SB(sb); unsigned int noio_flag; - unsigned int nr_zones = 1; - struct zonefs_ioerr_data err = { - .inode = inode, - .write = write, - }; + struct blk_zone zone; int ret; /* - * The only files that have more than one zone are conventional zone - * files with aggregated conventional zones, for which the inode zone - * size is always larger than the device zone size. + * Conventional zone have no write pointer and cannot become read-only + * or offline. So simply fake a report for a single or aggregated zone + * and let zonefs_handle_io_error() correct the zone inode information + * according to the mount options. */ - if (zi->i_zone_size > bdev_zone_sectors(sb->s_bdev)) - nr_zones = zi->i_zone_size >> - (sbi->s_zone_sectors_shift + SECTOR_SHIFT); + if (zi->i_ztype != ZONEFS_ZTYPE_SEQ) { + zone.start = zi->i_zsector; + zone.len = zi->i_max_size >> SECTOR_SHIFT; + zone.wp = zone.start + zone.len; + zone.type = BLK_ZONE_TYPE_CONVENTIONAL; + zone.cond = BLK_ZONE_COND_NOT_WP; + zone.capacity = zone.len; + goto handle_io_error; + } /* * Memory allocations in blkdev_report_zones() can trigger a memory @@ -469,12 +472,19 @@ static void __zonefs_io_error(struct inode *inode, bool write) * the GFP_NOIO context avoids both problems. */ noio_flag = memalloc_noio_save(); - ret = blkdev_report_zones(sb->s_bdev, zi->i_zsector, nr_zones, - zonefs_io_error_cb, &err); - if (ret != nr_zones) + ret = blkdev_report_zones(sb->s_bdev, zi->i_zsector, 1, + zonefs_io_error_cb, &zone); + memalloc_noio_restore(noio_flag); + if (ret != 1) { zonefs_err(sb, "Get inode %lu zone information failed %d\n", inode->i_ino, ret); - memalloc_noio_restore(noio_flag); + zonefs_warn(sb, "remounting filesystem read-only\n"); + sb->s_flags |= SB_RDONLY; + return; + } + +handle_io_error: + zonefs_handle_io_error(inode, &zone, write); } static void zonefs_io_error(struct inode *inode, bool write) diff --git a/include/drm/drm_color_mgmt.h b/include/drm/drm_color_mgmt.h index 81c298488..6b5eec10c 100644 --- a/include/drm/drm_color_mgmt.h +++ b/include/drm/drm_color_mgmt.h @@ -24,6 +24,7 @@ #define __DRM_COLOR_MGMT_H__ #include <linux/ctype.h> +#include <linux/math64.h> #include <drm/drm_property.h> struct drm_crtc; diff --git a/include/drm/drm_fixed.h b/include/drm/drm_fixed.h index 553210c02..627efa56e 100644 --- a/include/drm/drm_fixed.h +++ b/include/drm/drm_fixed.h @@ -88,7 +88,7 @@ static inline int drm_fixp2int(s64 a) static inline int drm_fixp2int_ceil(s64 a) { - if (a > 0) + if (a >= 0) return drm_fixp2int(a + DRM_FIXED_ALMOST_ONE); else return drm_fixp2int(a - DRM_FIXED_ALMOST_ONE); diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h index 31ba85a41..3c0d1495c 100644 --- a/include/drm/drm_mipi_dsi.h +++ b/include/drm/drm_mipi_dsi.h @@ -161,6 +161,7 @@ struct mipi_dsi_device_info { * struct mipi_dsi_device - DSI peripheral device * @host: DSI host for this peripheral * @dev: driver model device node for this peripheral + * @attached: the DSI device has been successfully attached * @name: DSI peripheral chip type * @channel: virtual channel assigned to the peripheral * @format: pixel format for video mode @@ -176,6 +177,7 @@ struct mipi_dsi_device_info { struct mipi_dsi_device { struct mipi_dsi_host *host; struct device dev; + bool attached; char name[DSI_DEV_NAME_SIZE]; unsigned int channel; diff --git a/include/linux/async.h b/include/linux/async.h index 0a17cd27f..d5496a520 100644 --- a/include/linux/async.h +++ b/include/linux/async.h @@ -90,6 +90,8 @@ async_schedule_dev(async_func_t func, struct device *dev) return async_schedule_node(func, dev, dev_to_node(dev)); } +bool async_schedule_dev_nocall(async_func_t func, struct device *dev); + /** * async_schedule_dev_domain - A device specific version of async_schedule_domain * @func: function to execute asynchronously diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 98fdf5a31..a47e1aeba 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -345,6 +345,7 @@ struct queue_limits { unsigned int max_zone_append_sectors; unsigned int discard_granularity; unsigned int discard_alignment; + unsigned int zone_write_granularity; unsigned short max_segments; unsigned short max_integrity_segments; @@ -1169,6 +1170,8 @@ extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); extern void blk_queue_max_zone_append_sectors(struct request_queue *q, unsigned int max_zone_append_sectors); extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); +void blk_queue_zone_write_granularity(struct request_queue *q, + unsigned int size); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); void blk_queue_update_readahead(struct request_queue *q); @@ -1480,6 +1483,18 @@ static inline int bdev_io_opt(struct block_device *bdev) return queue_io_opt(bdev_get_queue(bdev)); } +static inline unsigned int +queue_zone_write_granularity(const struct request_queue *q) +{ + return q->limits.zone_write_granularity; +} + +static inline unsigned int +bdev_zone_write_granularity(struct block_device *bdev) +{ + return queue_zone_write_granularity(bdev_get_queue(bdev)); +} + static inline int queue_alignment_offset(const struct request_queue *q) { if (q->limits.misaligned) @@ -1883,6 +1898,7 @@ struct block_device_operations { void (*unlock_native_capacity) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); + int (*set_read_only)(struct block_device *bdev, bool ro); /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8f4379e93..a75faf437 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -82,7 +82,11 @@ struct bpf_map_ops { /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); - void (*map_fd_put_ptr)(void *ptr); + /* If need_defer is true, the implementation should guarantee that + * the to-be-put element is still alive before the bpf program, which + * may manipulate it, exists. + */ + void (*map_fd_put_ptr)(struct bpf_map *map, void *ptr, bool need_defer); int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, @@ -171,9 +175,14 @@ struct bpf_map { */ atomic64_t refcnt ____cacheline_aligned; atomic64_t usercnt; - struct work_struct work; + /* rcu is used before freeing and work is only used during freeing */ + union { + struct work_struct work; + struct rcu_head rcu; + }; struct mutex freeze_mutex; atomic64_t writecnt; + bool free_after_mult_rcu_gp; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 6d7ab0161..2099226d8 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -74,6 +74,8 @@ extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/device.h b/include/linux/device.h index 6394c4b70..9c9ce573c 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -973,6 +973,7 @@ void device_link_del(struct device_link *link); void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); +void device_link_wait_removal(void); extern __printf(3, 4) int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index dd357a747..4e4cce0ad 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -949,7 +949,8 @@ static inline int dmaengine_slave_config(struct dma_chan *chan, static inline bool is_slave_direction(enum dma_transfer_direction direction) { - return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM); + return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM) || + (direction == DMA_DEV_TO_DEV); } static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single( diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index b060514bf..bbd3aeb2f 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -543,6 +543,31 @@ static inline unsigned long compare_ether_header(const void *a, const void *b) } /** + * eth_skb_pkt_type - Assign packet type if destination address does not match + * @skb: Assigned a packet type if address does not match @dev address + * @dev: Network device used to compare packet address against + * + * If the destination MAC address of the packet does not match the network + * device address, assign an appropriate packet type. + */ +static inline void eth_skb_pkt_type(struct sk_buff *skb, + const struct net_device *dev) +{ + const struct ethhdr *eth = eth_hdr(skb); + + if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) { + if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { + if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) + skb->pkt_type = PACKET_BROADCAST; + else + skb->pkt_type = PACKET_MULTICAST; + } else { + skb->pkt_type = PACKET_OTHERHOST; + } + } +} + +/** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad * diff --git a/include/linux/filter.h b/include/linux/filter.h index bc6ce4b20..840b2a05c 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -480,24 +480,27 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) __BPF_MAP(n, __BPF_DECL_ARGS, __BPF_N, u64, __ur_1, u64, __ur_2, \ u64, __ur_3, u64, __ur_4, u64, __ur_5) -#define BPF_CALL_x(x, name, ...) \ +#define BPF_CALL_x(x, attr, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ - u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ - u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ + attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ + attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) -#define BPF_CALL_0(name, ...) BPF_CALL_x(0, name, __VA_ARGS__) -#define BPF_CALL_1(name, ...) BPF_CALL_x(1, name, __VA_ARGS__) -#define BPF_CALL_2(name, ...) BPF_CALL_x(2, name, __VA_ARGS__) -#define BPF_CALL_3(name, ...) BPF_CALL_x(3, name, __VA_ARGS__) -#define BPF_CALL_4(name, ...) BPF_CALL_x(4, name, __VA_ARGS__) -#define BPF_CALL_5(name, ...) BPF_CALL_x(5, name, __VA_ARGS__) +#define __NOATTR +#define BPF_CALL_0(name, ...) BPF_CALL_x(0, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_1(name, ...) BPF_CALL_x(1, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_2(name, ...) BPF_CALL_x(2, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_3(name, ...) BPF_CALL_x(3, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_4(name, ...) BPF_CALL_x(4, __NOATTR, name, __VA_ARGS__) +#define BPF_CALL_5(name, ...) BPF_CALL_x(5, __NOATTR, name, __VA_ARGS__) + +#define NOTRACE_BPF_CALL_1(name, ...) BPF_CALL_x(1, notrace, name, __VA_ARGS__) #define bpf_ctx_range(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 @@ -892,8 +895,7 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk); void sk_reuseport_prog_free(struct bpf_prog *prog); int sk_detach_filter(struct sock *sk); -int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, - unsigned int len); +int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len); bool sk_filter_charge(struct sock *sk, struct sk_filter *fp); void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); diff --git a/include/linux/fs.h b/include/linux/fs.h index 82316863c..6de70634e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -316,6 +316,8 @@ enum rw_hint { /* iocb->ki_waitq is valid */ #define IOCB_WAITQ (1 << 19) #define IOCB_NOIO (1 << 20) +/* kiocb is a read or write operation submitted by fs/aio.c. */ +#define IOCB_AIO_RW (1 << 23) struct kiocb { struct file *ki_filp; diff --git a/include/linux/gfp.h b/include/linux/gfp.h index c603237e0..973f4143f 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -623,6 +623,15 @@ static inline bool pm_suspended_storage(void) } #endif /* CONFIG_PM_SLEEP */ +/* + * Check if the gfp flags allow compaction - GFP_NOIO is a really + * tricky context because the migration might require IO. + */ +static inline bool gfp_compaction_allowed(gfp_t gfp_mask) +{ + return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO); +} + #ifdef CONFIG_CONTIG_ALLOC /* The below functions must be run on a range from a single zone. */ extern int alloc_contig_range(unsigned long start, unsigned long end, diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index a88be8bd4..54a3ad7bf 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -197,6 +197,7 @@ enum hrtimer_base_type { * @max_hang_time: Maximum time spent in hrtimer_interrupt * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are * expired + * @online: CPU is online from an hrtimers point of view * @timer_waiters: A hrtimer_cancel() invocation waits for the timer * callback to finish. * @expires_next: absolute time of the next event, is required for remote @@ -219,7 +220,8 @@ struct hrtimer_cpu_base { unsigned int hres_active : 1, in_hrtirq : 1, hang_detected : 1, - softirq_activated : 1; + softirq_activated : 1, + online : 1; #ifdef CONFIG_HIGH_RES_TIMERS unsigned int nr_events; unsigned short nr_retries; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 99b73fc4a..90c66b945 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -140,7 +140,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, unsigned long dst_addr, unsigned long src_addr, struct page **pagep); -int hugetlb_reserve_pages(struct inode *inode, long from, long to, +bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index eada4d8d6..b606a203d 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -164,8 +164,28 @@ struct hv_ring_buffer { u8 buffer[]; } __packed; + +/* + * If the requested ring buffer size is at least 8 times the size of the + * header, steal space from the ring buffer for the header. Otherwise, add + * space for the header so that is doesn't take too much of the ring buffer + * space. + * + * The factor of 8 is somewhat arbitrary. The goal is to prevent adding a + * relatively small header (4 Kbytes on x86) to a large-ish power-of-2 ring + * buffer size (such as 128 Kbytes) and so end up making a nearly twice as + * large allocation that will be almost half wasted. As a contrasting example, + * on ARM64 with 64 Kbyte page size, we don't want to take 64 Kbytes for the + * header from a 128 Kbyte allocation, leaving only 64 Kbytes for the ring. + * In this latter case, we must add 64 Kbytes for the header and not worry + * about what's wasted. + */ +#define VMBUS_HEADER_ADJ(payload_sz) \ + ((payload_sz) >= 8 * sizeof(struct hv_ring_buffer) ? \ + 0 : sizeof(struct hv_ring_buffer)) + /* Calculate the proper size of a ringbuffer, it must be page-aligned */ -#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(sizeof(struct hv_ring_buffer) + \ +#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(VMBUS_HEADER_ADJ(payload_sz) + \ (payload_sz)) struct hv_ring_buffer_info { @@ -764,6 +784,23 @@ enum vmbus_device_type { HV_UNKNOWN, }; +/* + * Provides request ids for VMBus. Encapsulates guest memory + * addresses and stores the next available slot in req_arr + * to generate new ids in constant time. + */ +struct vmbus_requestor { + u64 *req_arr; + unsigned long *req_bitmap; /* is a given slot available? */ + u32 size; + u64 next_request_id; + spinlock_t req_lock; /* provides atomicity */ +}; + +#define VMBUS_NO_RQSTOR U64_MAX +#define VMBUS_RQST_ERROR (U64_MAX - 1) +#define VMBUS_RQST_ID_NO_RESPONSE (U64_MAX - 2) + struct vmbus_device { u16 dev_type; guid_t guid; @@ -988,8 +1025,14 @@ struct vmbus_channel { u32 fuzz_testing_interrupt_delay; u32 fuzz_testing_message_delay; + /* request/transaction ids for VMBus */ + struct vmbus_requestor requestor; + u32 rqstor_size; }; +u64 vmbus_next_request_id(struct vmbus_requestor *rqstor, u64 rqst_addr); +u64 vmbus_request_addr(struct vmbus_requestor *rqstor, u64 trans_id); + static inline bool is_hvsock_channel(const struct vmbus_channel *c) { return !!(c->offermsg.offer.chn_flags & diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 64ce8cd1c..4adab8ada 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -121,9 +121,9 @@ extern int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex); extern int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf,int ifindex); extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, - struct ip_msfilter __user *optval, int __user *optlen); + sockptr_t optval, sockptr_t optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, - struct sockaddr_storage __user *p); + sockptr_t optval, size_t offset); extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 649a4d7c2..55d09f594 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -6,9 +6,9 @@ #include <linux/xarray.h> #if defined(CONFIG_IO_URING) -struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); +bool io_is_uring_fops(struct file *file); static inline void io_uring_files_cancel(void) { @@ -26,10 +26,6 @@ static inline void io_uring_free(struct task_struct *tsk) __io_uring_free(tsk); } #else -static inline struct sock *io_uring_get_socket(struct file *file) -{ - return NULL; -} static inline void io_uring_task_cancel(void) { } @@ -39,6 +35,10 @@ static inline void io_uring_files_cancel(void) static inline void io_uring_free(struct task_struct *tsk) { } +static inline bool io_is_uring_fops(struct file *file) +{ + return false; +} #endif #endif diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 3ed4e8771..a53adf431 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -133,7 +133,7 @@ do { \ # define lockdep_softirq_enter() do { } while (0) # define lockdep_softirq_exit() do { } while (0) # define lockdep_hrtimer_enter(__hrtimer) false -# define lockdep_hrtimer_exit(__context) do { } while (0) +# define lockdep_hrtimer_exit(__context) do { (void)(__context); } while (0) # define lockdep_posixtimer_enter() do { } while (0) # define lockdep_posixtimer_exit() do { } while (0) # define lockdep_irq_work_enter(__work) do { } while (0) diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 2c2586312..3eca9f91b 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -321,6 +321,10 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); WARN_ON_ONCE(debug_locks && !lockdep_is_held(l)); \ } while (0) +#define lockdep_assert_none_held_once() do { \ + WARN_ON_ONCE(debug_locks && current->lockdep_depth); \ + } while (0) + #define lockdep_recursing(tsk) ((tsk)->lockdep_recursion) #define lockdep_pin_lock(l) lock_pin_lock(&(l)->dep_map) @@ -394,6 +398,7 @@ static inline void lockdep_unregister_key(struct lock_class_key *key) #define lockdep_assert_held_write(l) do { (void)(l); } while (0) #define lockdep_assert_held_read(l) do { (void)(l); } while (0) #define lockdep_assert_held_once(l) do { (void)(l); } while (0) +#define lockdep_assert_none_held_once() do { } while (0) #define lockdep_recursing(tsk) (0) diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 693ed9c61..07abcd384 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -158,6 +158,8 @@ LSM_HOOK(int, 0, file_alloc_security, struct file *file) LSM_HOOK(void, LSM_RET_VOID, file_free_security, struct file *file) LSM_HOOK(int, 0, file_ioctl, struct file *file, unsigned int cmd, unsigned long arg) +LSM_HOOK(int, 0, file_ioctl_compat, struct file *file, unsigned int cmd, + unsigned long arg) LSM_HOOK(int, 0, mmap_addr, unsigned long addr) LSM_HOOK(int, 0, mmap_file, struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) @@ -291,9 +293,9 @@ LSM_HOOK(int, 0, socket_getsockopt, struct socket *sock, int level, int optname) LSM_HOOK(int, 0, socket_setsockopt, struct socket *sock, int level, int optname) LSM_HOOK(int, 0, socket_shutdown, struct socket *sock, int how) LSM_HOOK(int, 0, socket_sock_rcv_skb, struct sock *sk, struct sk_buff *skb) -LSM_HOOK(int, 0, socket_getpeersec_stream, struct socket *sock, - char __user *optval, int __user *optlen, unsigned len) -LSM_HOOK(int, 0, socket_getpeersec_dgram, struct socket *sock, +LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_stream, struct socket *sock, + sockptr_t optval, sockptr_t optlen, unsigned int len) +LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_dgram, struct socket *sock, struct sk_buff *skb, u32 *secid) LSM_HOOK(int, 0, sk_alloc_security, struct sock *sk, int family, gfp_t priority) LSM_HOOK(void, LSM_RET_VOID, sk_free_security, struct sock *sk) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 64cdf4d7b..bbf9c8c7b 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -926,8 +926,8 @@ * SO_GETPEERSEC. For tcp sockets this can be meaningful if the * socket is associated with an ipsec SA. * @sock is the local socket. - * @optval userspace memory where the security state is to be copied. - * @optlen userspace int where the module should copy the actual length + * @optval memory where the security state is to be copied. + * @optlen memory where the module should copy the actual length * of the security state. * @len as input is the maximum length to copy to userspace provided * by the caller. diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index d75ef8aa8..28d44061d 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -261,7 +261,10 @@ struct mlx5_wqe_eth_seg { union { struct { __be16 sz; - u8 start[2]; + union { + u8 start[2]; + DECLARE_FLEX_ARRAY(u8, data); + }; } inline_hdr; struct { __be16 type; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b2e4599b8..ffae2b330 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1188,6 +1188,7 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec) #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK) struct mem_section_usage { + struct rcu_head rcu; #ifdef CONFIG_SPARSEMEM_VMEMMAP DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); #endif @@ -1353,7 +1354,7 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { int idx = subsection_map_index(pfn); - return test_bit(idx, ms->usage->subsection_map); + return test_bit(idx, READ_ONCE(ms->usage)->subsection_map); } #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) @@ -1366,17 +1367,24 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; + int ret; if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; - ms = __nr_to_section(pfn_to_section_nr(pfn)); - if (!valid_section(ms)) + ms = __pfn_to_section(pfn); + rcu_read_lock(); + if (!valid_section(ms)) { + rcu_read_unlock(); return 0; + } /* * Traditionally early sections always returned pfn_valid() for * the entire section-sized span. */ - return early_section(ms) || pfn_section_valid(ms, pfn); + ret = early_section(ms) || pfn_section_valid(ms, pfn); + rcu_read_unlock(); + + return ret; } #endif @@ -1384,7 +1392,7 @@ static inline int pfn_in_present_section(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; - return present_section(__nr_to_section(pfn_to_section_nr(pfn))); + return present_section(__pfn_to_section(pfn)); } static inline unsigned long next_present_section_nr(unsigned long section_nr) diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 6cbbfe943..80b8400ab 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -17,7 +17,7 @@ static inline int ip_mroute_opt(int opt) } int ip_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int); -int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *); +int ip_mroute_getsockopt(struct sock *, int, sockptr_t, sockptr_t); int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); int ip_mr_init(void); @@ -29,8 +29,8 @@ static inline int ip_mroute_setsockopt(struct sock *sock, int optname, return -ENOPROTOOPT; } -static inline int ip_mroute_getsockopt(struct sock *sock, int optname, - char __user *optval, int __user *optlen) +static inline int ip_mroute_getsockopt(struct sock *sk, int optname, + sockptr_t optval, sockptr_t optlen) { return -ENOPROTOOPT; } diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 62f7e7e25..f27894e50 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -188,6 +188,8 @@ struct ip_set_type_variant { /* Return true if "b" set is the same as "a" * according to the create set parameters */ bool (*same_set)(const struct ip_set *a, const struct ip_set *b); + /* Cancel ongoing garbage collectors before destroying the set*/ + void (*cancel_gc)(struct ip_set *set); /* Region-locking is used */ bool region_lock; }; @@ -239,6 +241,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type); /* A generic IP set */ struct ip_set { + /* For call_cru in destroy */ + struct rcu_head rcu; /* The name of the set */ char name[IPSET_MAXNAMELEN]; /* Lock protecting the set data */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index e39342945..748886458 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -553,6 +553,7 @@ extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); +void nfs_commit_begin(struct nfs_mds_commit_info *cinfo); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); static inline int diff --git a/include/linux/objtool.h b/include/linux/objtool.h index d17fa7f40..0f13875ac 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -141,6 +141,12 @@ struct unwind_hint { .popsection .endm +.macro STACK_FRAME_NON_STANDARD func:req + .pushsection .discard.func_stack_frame_non_standard, "aw" + .long \func - . + .popsection +.endm + #endif /* __ASSEMBLY__ */ #else /* !CONFIG_STACK_VALIDATION */ @@ -158,6 +164,8 @@ struct unwind_hint { .endm .macro ANNOTATE_NOENDBR .endm +.macro STACK_FRAME_NON_STANDARD func:req +.endm #endif #endif /* CONFIG_STACK_VALIDATION */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 550e1cdb4..5b24a6fbf 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -306,6 +306,7 @@ struct pcie_link_state; struct pci_vpd; struct pci_sriov; struct pci_p2pdma; +struct rcec_ea; /* The pci_dev structure describes PCI devices */ struct pci_dev { @@ -329,6 +330,10 @@ struct pci_dev { u16 aer_cap; /* AER capability offset */ struct aer_stats *aer_stats; /* AER stats for this device */ #endif +#ifdef CONFIG_PCIEPORTBUS + struct rcec_ea *rcec_ea; /* RCEC cached endpoint association */ +#endif + u32 devcap; /* PCIe Device Capabilities */ u8 pcie_cap; /* PCIe capability offset */ u8 msi_cap; /* MSI capability offset */ u8 msix_cap; /* MSI-X capability offset */ @@ -449,6 +454,7 @@ struct pci_dev { unsigned int link_active_reporting:1;/* Device capable of reporting link active */ unsigned int no_vf_scan:1; /* Don't scan for VFs after IOV enablement */ unsigned int no_command_memory:1; /* No PCI_COMMAND_MEMORY */ + unsigned int rom_bar_overlap:1; /* ROM BAR disable broken */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ @@ -2191,6 +2197,11 @@ static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev) return NULL; } +static inline bool pci_dev_is_disconnected(const struct pci_dev *dev) +{ + return dev->error_state == pci_channel_io_perm_failure; +} + void pci_request_acs(void); bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags); bool pci_acs_path_enabled(struct pci_dev *start, diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 1a41147b2..80744a7b5 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3020,6 +3020,7 @@ #define PCI_DEVICE_ID_INTEL_82443GX_0 0x71a0 #define PCI_DEVICE_ID_INTEL_82443GX_2 0x71a2 #define PCI_DEVICE_ID_INTEL_82372FB_1 0x7601 +#define PCI_DEVICE_ID_INTEL_HDA_ARL 0x7728 #define PCI_DEVICE_ID_INTEL_SCH_LPC 0x8119 #define PCI_DEVICE_ID_INTEL_SCH_IDE 0x811a #define PCI_DEVICE_ID_INTEL_E6XX_CU 0x8183 diff --git a/include/linux/phy/tegra/xusb.h b/include/linux/phy/tegra/xusb.h index 71d956935..86ccd90e4 100644 --- a/include/linux/phy/tegra/xusb.h +++ b/include/linux/phy/tegra/xusb.h @@ -23,4 +23,6 @@ int tegra_xusb_padctl_set_vbus_override(struct tegra_xusb_padctl *padctl, int tegra_phy_xusb_utmi_port_reset(struct phy *phy); int tegra_xusb_padctl_get_usb3_companion(struct tegra_xusb_padctl *padctl, unsigned int port); +int tegra_xusb_padctl_get_port_number(struct phy *phy); + #endif /* PHY_TEGRA_XUSB_H */ diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index ef236dbaa..7b72d93c2 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -125,6 +125,22 @@ struct pipe_buf_operations { }; /** + * pipe_has_watch_queue - Check whether the pipe is a watch_queue, + * i.e. it was created with O_NOTIFICATION_PIPE + * @pipe: The pipe to check + * + * Return: true if pipe is a watch queue, false otherwise. + */ +static inline bool pipe_has_watch_queue(const struct pipe_inode_info *pipe) +{ +#ifdef CONFIG_WATCH_QUEUE + return pipe->watch_queue != NULL; +#else + return false; +#endif +} + +/** * pipe_empty - Return true if the pipe is empty * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 718600e83..ca856e582 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -60,6 +60,8 @@ extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device_link *link); extern void pm_runtime_release_supplier(struct device_link *link); +extern int devm_pm_runtime_enable(struct device *dev); + /** * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter. * @dev: Target device. @@ -254,6 +256,8 @@ static inline void __pm_runtime_disable(struct device *dev, bool c) {} static inline void pm_runtime_allow(struct device *dev) {} static inline void pm_runtime_forbid(struct device *dev) {} +static inline int devm_pm_runtime_enable(struct device *dev) { return 0; } + static inline void pm_suspend_ignore_children(struct device *dev, bool enable) {} static inline void pm_runtime_get_noresume(struct device *dev) {} static inline void pm_runtime_put_noidle(struct device *dev) {} @@ -535,6 +539,10 @@ static inline void pm_runtime_disable(struct device *dev) * Allow the runtime PM autosuspend mechanism to be used for @dev whenever * requested (or "autosuspend" will be handled as direct runtime-suspend for * it). + * + * NOTE: It's important to undo this with pm_runtime_dont_use_autosuspend() + * at driver exit time unless your driver initially enabled pm_runtime + * with devm_pm_runtime_enable() (which handles it for you). */ static inline void pm_runtime_use_autosuspend(struct device *dev) { diff --git a/include/linux/poll.h b/include/linux/poll.h index 1cdc32b1f..7e0fdcf90 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -16,11 +16,7 @@ extern struct ctl_table epoll_table[]; /* for sysctl */ /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating additional memory. */ -#ifdef __clang__ -#define MAX_STACK_ALLOC 768 -#else #define MAX_STACK_ALLOC 832 -#endif #define FRONTEND_STACK_ALLOC 256 #define SELECT_STACK_ALLOC FRONTEND_STACK_ALLOC #define POLL_STACK_ALLOC FRONTEND_STACK_ALLOC diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 8716a1706..9db6710e6 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -202,6 +202,18 @@ static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ /** + * rcu_trace_implies_rcu_gp - does an RCU Tasks Trace grace period imply an RCU grace period? + * + * As an accident of implementation, an RCU Tasks Trace grace period also + * acts as an RCU grace period. However, this could change at any time. + * Code relying on this accident must call this function to verify that + * this accident is still happening. + * + * You have been warned! + */ +static inline bool rcu_trace_implies_rcu_gp(void) { return true; } + +/** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to @@ -214,6 +226,37 @@ do { \ cond_resched(); \ } while (0) +/** + * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states + * @old_ts: jiffies at start of processing. + * + * This helper is for long-running softirq handlers, such as NAPI threads in + * networking. The caller should initialize the variable passed in as @old_ts + * at the beginning of the softirq handler. When invoked frequently, this macro + * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will + * provide both RCU and RCU-Tasks quiescent states. Note that this macro + * modifies its old_ts argument. + * + * Because regions of code that have disabled softirq act as RCU read-side + * critical sections, this macro should be invoked with softirq (and + * preemption) enabled. + * + * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would + * have more chance to invoke schedule() calls and provide necessary quiescent + * states. As a contrast, calling cond_resched() only won't achieve the same + * effect because cond_resched() does not provide RCU-Tasks quiescent states. + */ +#define rcu_softirq_qs_periodic(old_ts) \ +do { \ + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ + time_after(jiffies, (old_ts) + HZ / 10)) { \ + preempt_disable(); \ + rcu_softirq_qs(); \ + preempt_enable(); \ + (old_ts) = jiffies; \ + } \ +} while (0) + /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. diff --git a/include/linux/regmap.h b/include/linux/regmap.h index e7834d982..83a7485de 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -289,6 +289,17 @@ typedef void (*regmap_unlock)(void *); * read operation on a bus such as SPI, I2C, etc. Most of the * devices do not need this. * @reg_write: Same as above for writing. + * @reg_update_bits: Optional callback that if filled will be used to perform + * all the update_bits(rmw) operation. Should only be provided + * if the function require special handling with lock and reg + * handling and the operation cannot be represented as a simple + * update_bits operation on a bus such as SPI, I2C, etc. + * @read: Optional callback that if filled will be used to perform all the + * bulk reads from the registers. Data is returned in the buffer used + * to transmit data. + * @write: Same as above for writing. + * @max_raw_read: Max raw read size that can be used on the device. + * @max_raw_write: Max raw write size that can be used on the device. * @fast_io: Register IO is fast. Use a spinlock instead of a mutex * to perform locking. This field is ignored if custom lock/unlock * functions are used (see fields lock/unlock of struct regmap_config). @@ -366,6 +377,14 @@ struct regmap_config { int (*reg_read)(void *context, unsigned int reg, unsigned int *val); int (*reg_write)(void *context, unsigned int reg, unsigned int val); + int (*reg_update_bits)(void *context, unsigned int reg, + unsigned int mask, unsigned int val); + /* Bulk read/write */ + int (*read)(void *context, const void *reg_buf, size_t reg_size, + void *val_buf, size_t val_size); + int (*write)(void *context, const void *data, size_t count); + size_t max_raw_read; + size_t max_raw_write; bool fast_io; diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 3fa3ba649..2546758f1 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -368,7 +368,9 @@ enum rsc_handling_status { * RSC_HANDLED if resource was handled, RSC_IGNORED if not handled and a * negative value on error * @load_rsc_table: load resource table from firmware image - * @find_loaded_rsc_table: find the loaded resouce table + * @find_loaded_rsc_table: find the loaded resource table from firmware image + * @get_loaded_rsc_table: get resource table installed in memory + * by external entity * @load: load firmware to memory, where the remote processor * expects to find it * @sanity_check: sanity check the fw image @@ -389,6 +391,8 @@ struct rproc_ops { int offset, int avail); struct resource_table *(*find_loaded_rsc_table)( struct rproc *rproc, const struct firmware *fw); + struct resource_table *(*get_loaded_rsc_table)( + struct rproc *rproc, size_t *size); int (*load)(struct rproc *rproc, const struct firmware *fw); int (*sanity_check)(struct rproc *rproc, const struct firmware *fw); u64 (*get_boot_addr)(struct rproc *rproc, const struct firmware *fw); diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index f24575942..879a5c8f9 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -16,7 +16,7 @@ * try_get_task_stack() instead. task_stack_page will return a pointer * that could get freed out from under you. */ -static inline void *task_stack_page(const struct task_struct *task) +static __always_inline void *task_stack_page(const struct task_struct *task) { return task->stack; } diff --git a/include/linux/security.h b/include/linux/security.h index e9b4b5410..5b61aa19f 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -31,6 +31,7 @@ #include <linux/err.h> #include <linux/string.h> #include <linux/mm.h> +#include <linux/sockptr.h> struct linux_binprm; struct cred; @@ -368,6 +369,8 @@ int security_file_permission(struct file *file, int mask); int security_file_alloc(struct file *file); void security_file_free(struct file *file); int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +int security_file_ioctl_compat(struct file *file, unsigned int cmd, + unsigned long arg); int security_mmap_file(struct file *file, unsigned long prot, unsigned long flags); int security_mmap_addr(unsigned long addr); @@ -925,6 +928,13 @@ static inline int security_file_ioctl(struct file *file, unsigned int cmd, return 0; } +static inline int security_file_ioctl_compat(struct file *file, + unsigned int cmd, + unsigned long arg) +{ + return 0; +} + static inline int security_mmap_file(struct file *file, unsigned long prot, unsigned long flags) { @@ -1357,8 +1367,8 @@ int security_socket_getsockopt(struct socket *sock, int level, int optname); int security_socket_setsockopt(struct socket *sock, int level, int optname); int security_socket_shutdown(struct socket *sock, int how); int security_sock_rcv_skb(struct sock *sk, struct sk_buff *skb); -int security_socket_getpeersec_stream(struct socket *sock, char __user *optval, - int __user *optlen, unsigned len); +int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, + sockptr_t optlen, unsigned int len); int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid); int security_sk_alloc(struct sock *sk, int family, gfp_t priority); void security_sk_free(struct sock *sk); @@ -1492,8 +1502,10 @@ static inline int security_sock_rcv_skb(struct sock *sk, return 0; } -static inline int security_socket_getpeersec_stream(struct socket *sock, char __user *optval, - int __user *optlen, unsigned len) +static inline int security_socket_getpeersec_stream(struct socket *sock, + sockptr_t optval, + sockptr_t optlen, + unsigned int len) { return -ENOPROTOOPT; } diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 6df4c3356..48b9cd8fd 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -254,11 +254,91 @@ struct uart_port { struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ struct serial_rs485 rs485; + const struct serial_rs485 *rs485_supported; /* Supported mask for serial_rs485 */ struct gpio_desc *rs485_term_gpio; /* enable RS485 bus termination */ struct serial_iso7816 iso7816; void *private_data; /* generic platform data pointer */ }; +/** + * uart_port_lock - Lock the UART port + * @up: Pointer to UART port structure + */ +static inline void uart_port_lock(struct uart_port *up) +{ + spin_lock(&up->lock); +} + +/** + * uart_port_lock_irq - Lock the UART port and disable interrupts + * @up: Pointer to UART port structure + */ +static inline void uart_port_lock_irq(struct uart_port *up) +{ + spin_lock_irq(&up->lock); +} + +/** + * uart_port_lock_irqsave - Lock the UART port, save and disable interrupts + * @up: Pointer to UART port structure + * @flags: Pointer to interrupt flags storage + */ +static inline void uart_port_lock_irqsave(struct uart_port *up, unsigned long *flags) +{ + spin_lock_irqsave(&up->lock, *flags); +} + +/** + * uart_port_trylock - Try to lock the UART port + * @up: Pointer to UART port structure + * + * Returns: True if lock was acquired, false otherwise + */ +static inline bool uart_port_trylock(struct uart_port *up) +{ + return spin_trylock(&up->lock); +} + +/** + * uart_port_trylock_irqsave - Try to lock the UART port, save and disable interrupts + * @up: Pointer to UART port structure + * @flags: Pointer to interrupt flags storage + * + * Returns: True if lock was acquired, false otherwise + */ +static inline bool uart_port_trylock_irqsave(struct uart_port *up, unsigned long *flags) +{ + return spin_trylock_irqsave(&up->lock, *flags); +} + +/** + * uart_port_unlock - Unlock the UART port + * @up: Pointer to UART port structure + */ +static inline void uart_port_unlock(struct uart_port *up) +{ + spin_unlock(&up->lock); +} + +/** + * uart_port_unlock_irq - Unlock the UART port and re-enable interrupts + * @up: Pointer to UART port structure + */ +static inline void uart_port_unlock_irq(struct uart_port *up) +{ + spin_unlock_irq(&up->lock); +} + +/** + * uart_port_unlock_irqrestore - Unlock the UART port, restore interrupts + * @up: Pointer to UART port structure + * @flags: The saved interrupt flags for restore + */ +static inline void uart_port_unlock_irqrestore(struct uart_port *up, unsigned long flags) +{ + spin_unlock_irqrestore(&up->lock, flags); +} + static inline int serial_port_in(struct uart_port *up, int offset) { return up->serial_in(up, offset); diff --git a/include/linux/socket.h b/include/linux/socket.h index c3b35d18b..daf51fef5 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -31,7 +31,10 @@ typedef __kernel_sa_family_t sa_family_t; struct sockaddr { sa_family_t sa_family; /* address family, AF_xxx */ - char sa_data[14]; /* 14 bytes of protocol address */ + union { + char sa_data_min[14]; /* Minimum 14 bytes of protocol address */ + DECLARE_FLEX_ARRAY(char, sa_data); + }; }; struct linger { diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index ea1934142..38862819e 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -64,6 +64,11 @@ static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset, return 0; } +static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size) +{ + return copy_to_sockptr_offset(dst, 0, src, size); +} + static inline void *memdup_sockptr(sockptr_t src, size_t len) { void *p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index e1d88630f..ab7747549 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -171,6 +171,7 @@ struct spi_device { #define SPI_MODE_1 (0|SPI_CPHA) #define SPI_MODE_2 (SPI_CPOL|0) #define SPI_MODE_3 (SPI_CPOL|SPI_CPHA) +#define SPI_MODE_X_MASK (SPI_CPOL|SPI_CPHA) #define SPI_CS_HIGH 0x04 /* chipselect active high? */ #define SPI_LSB_FIRST 0x08 /* per-word bits-on-wire */ #define SPI_3WIRE 0x10 /* SI/SO signals shared */ diff --git a/include/linux/stddef.h b/include/linux/stddef.h index 938216f8a..31fdbb784 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -84,4 +84,17 @@ enum { #define struct_group_tagged(TAG, NAME, MEMBERS...) \ __struct_group(TAG, NAME, /* no attrs */, MEMBERS) +/** + * DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union + * + * @TYPE: The type of each flexible array element + * @NAME: The name of the flexible array member + * + * In order to have a flexible array member in a union or alone in a + * struct, it needs to be wrapped in an anonymous struct with at least 1 + * named member, but that member can be empty. + */ +#define DECLARE_FLEX_ARRAY(TYPE, NAME) \ + __DECLARE_FLEX_ARRAY(TYPE, NAME) + #endif diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 256dff36c..0527a4bc9 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -197,7 +197,7 @@ struct rpc_wait_queue { unsigned char maxpriority; /* maximum priority (0 if queue is not a priority queue) */ unsigned char priority; /* current priority */ unsigned char nr; /* # tasks remaining for cookie */ - unsigned short qlen; /* total # tasks waiting in queue */ + unsigned int qlen; /* total # tasks waiting in queue */ struct rpc_timer timer_list; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) const char * name; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a058c96cf..17a24e118 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -119,6 +119,7 @@ struct open_how; #define __TYPE_IS_LL(t) (__TYPE_AS(t, 0LL) || __TYPE_AS(t, 0ULL)) #define __SC_LONG(t, a) __typeof(__builtin_choose_expr(__TYPE_IS_LL(t), 0LL, 0L)) a #define __SC_CAST(t, a) (__force t) a +#define __SC_TYPE(t, a) t #define __SC_ARGS(t, a) a #define __SC_TEST(t, a) (void)BUILD_BUG_ON_ZERO(!__TYPE_IS_LL(t) && sizeof(t) > sizeof(long)) diff --git a/include/linux/timer.h b/include/linux/timer.h index d10bc7e73..a3d04c4f1 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -183,12 +183,20 @@ extern int timer_reduce(struct timer_list *timer, unsigned long expires); extern void add_timer(struct timer_list *timer); extern int try_to_del_timer_sync(struct timer_list *timer); +extern int timer_delete_sync(struct timer_list *timer); -#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) - extern int del_timer_sync(struct timer_list *timer); -#else -# define del_timer_sync(t) del_timer(t) -#endif +/** + * del_timer_sync - Delete a pending timer and wait for a running callback + * @timer: The timer to be deleted + * + * See timer_delete_sync() for detailed explanation. + * + * Do not use in new code. Use timer_delete_sync() instead. + */ +static inline int del_timer_sync(struct timer_list *timer) +{ + return timer_delete_sync(timer); +} #define del_singleshot_timer_sync(t) del_timer_sync(t) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index f7ed0471d..dbf099315 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -577,7 +577,7 @@ struct trace_event_file { } \ early_initcall(trace_init_perf_perm_##name); -#define PERF_MAX_TRACE_SIZE 2048 +#define PERF_MAX_TRACE_SIZE 8192 #define MAX_FILTER_STR_VAL 256U /* Should handle KSYM_SYMBOL_LEN */ diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index e81856c0b..7c6f81b89 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -116,7 +116,11 @@ static inline void u64_stats_inc(u64_stats_t *p) #endif #if BITS_PER_LONG == 32 && defined(CONFIG_SMP) -#define u64_stats_init(syncp) seqcount_init(&(syncp)->seq) +#define u64_stats_init(syncp) \ + do { \ + struct u64_stats_sync *__s = (syncp); \ + seqcount_init(&__s->seq); \ + } while (0) #else static inline void u64_stats_init(struct u64_stats_sync *syncp) { diff --git a/include/linux/udp.h b/include/linux/udp.h index ae58ff3b6..a22088001 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -131,6 +131,24 @@ static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, } } +DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); +#if IS_ENABLED(CONFIG_IPV6) +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +#endif + +static inline bool udp_encap_needed(void) +{ + if (static_branch_unlikely(&udp_encap_needed_key)) + return true; + +#if IS_ENABLED(CONFIG_IPV6) + if (static_branch_unlikely(&udpv6_encap_needed_key)) + return true; +#endif + + return false; +} + static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) { if (!skb_is_gso(skb)) @@ -142,6 +160,16 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && !udp_sk(sk)->accept_udp_fraglist) return true; + /* GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits might still + * land in a tunnel as the socket check in udp_gro_receive cannot be + * foolproof. + */ + if (udp_encap_needed() && + READ_ONCE(udp_sk(sk)->encap_rcv) && + !(skb_shinfo(skb)->gso_type & + (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM))) + return true; + return false; } diff --git a/include/linux/units.h b/include/linux/units.h index 3457179f7..b61e3f6d5 100644 --- a/include/linux/units.h +++ b/include/linux/units.h @@ -20,9 +20,13 @@ #define PICO 1000000000000ULL #define FEMTO 1000000000000000ULL -#define MILLIWATT_PER_WATT 1000L -#define MICROWATT_PER_MILLIWATT 1000L -#define MICROWATT_PER_WATT 1000000L +#define HZ_PER_KHZ 1000UL +#define KHZ_PER_MHZ 1000UL +#define HZ_PER_MHZ 1000000UL + +#define MILLIWATT_PER_WATT 1000UL +#define MICROWATT_PER_MILLIWATT 1000UL +#define MICROWATT_PER_WATT 1000000UL #define ABSOLUTE_ZERO_MILLICELSIUS -273150 diff --git a/include/linux/vfio.h b/include/linux/vfio.h index f479c5d7f..56d18912c 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -221,6 +221,7 @@ struct virqfd { wait_queue_entry_t wait; poll_table pt; struct work_struct shutdown; + struct work_struct flush_inject; struct virqfd **pvirqfd; }; @@ -229,5 +230,6 @@ extern int vfio_virqfd_enable(void *opaque, void (*thread)(void *, void *), void *data, struct virqfd **pvirqfd, int fd); extern void vfio_virqfd_disable(struct virqfd **pvirqfd); +void vfio_virqfd_flush_thread(struct virqfd **pvirqfd); #endif /* VFIO_H */ diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 76dad53a4..0fd47f2f3 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -112,6 +112,11 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller); +extern void *__vmalloc_array(size_t n, size_t size, gfp_t flags); +extern void *vmalloc_array(size_t n, size_t size); +extern void *__vcalloc(size_t n, size_t size, gfp_t flags); +extern void *vcalloc(size_t n, size_t size); + extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 4d0c4cf1d..f666d3628 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -437,6 +437,10 @@ static inline void in6_ifa_hold(struct inet6_ifaddr *ifp) refcount_inc(&ifp->refcnt); } +static inline bool in6_ifa_hold_safe(struct inet6_ifaddr *ifp) +{ + return refcount_inc_not_zero(&ifp->refcnt); +} /* * compute link-local solicited-node multicast address diff --git a/include/net/af_unix.h b/include/net/af_unix.h index f42fdddec..349279c4d 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -47,12 +47,6 @@ struct scm_stat { #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) -#define unix_state_lock(s) spin_lock(&unix_sk(s)->lock) -#define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock) -#define unix_state_lock_nested(s) \ - spin_lock_nested(&unix_sk(s)->lock, \ - SINGLE_DEPTH_NESTING) - /* The AF_UNIX socket */ struct unix_sock { /* WARNING: sk has to be the first member */ @@ -62,7 +56,7 @@ struct unix_sock { struct mutex iolock, bindlock; struct sock *peer; struct list_head link; - atomic_long_t inflight; + unsigned long inflight; spinlock_t lock; unsigned long gc_flags; #define UNIX_GC_CANDIDATE 0 @@ -77,6 +71,23 @@ static inline struct unix_sock *unix_sk(const struct sock *sk) return (struct unix_sock *)sk; } +#define unix_state_lock(s) spin_lock(&unix_sk(s)->lock) +#define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock) +enum unix_socket_lock_class { + U_LOCK_NORMAL, + U_LOCK_SECOND, /* for double locking, see unix_state_double_lock(). */ + U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */ + U_LOCK_GC_LISTENER, /* used for listening socket while determining gc + * candidates to close a small race window. + */ +}; + +static inline void unix_state_lock_nested(struct sock *sk, + enum unix_socket_lock_class subclass) +{ + spin_lock_nested(&unix_sk(sk)->lock, subclass); +} + #define peer_wait peer_wq.wait long unix_inq_len(struct sock *sk); diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 355835639..7d2bd562d 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -487,6 +487,15 @@ static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk, return skb; } +static inline int bt_copy_from_sockptr(void *dst, size_t dst_size, + sockptr_t src, size_t src_size) +{ + if (dst_size > src_size) + return -EINVAL; + + return copy_from_sockptr(dst, src, dst_size); +} + int bt_to_errno(u16 code); void hci_sock_set_flag(struct sock *sk, int nr); diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 6ed07844e..5290781ab 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -257,6 +257,7 @@ struct ieee802154_llsec_key { struct ieee802154_llsec_key_entry { struct list_head list; + struct rcu_head rcu; struct ieee802154_llsec_key_id id; struct ieee802154_llsec_key *key; diff --git a/include/net/compat.h b/include/net/compat.h index 745db0d60..52bf5f0ee 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -81,13 +81,26 @@ struct compat_group_source_req { } __packed; struct compat_group_filter { - __u32 gf_interface; - struct __kernel_sockaddr_storage gf_group - __aligned(4); - __u32 gf_fmode; - __u32 gf_numsrc; - struct __kernel_sockaddr_storage gf_slist[1] - __aligned(4); + union { + struct { + __u32 gf_interface_aux; + struct __kernel_sockaddr_storage gf_group_aux + __aligned(4); + __u32 gf_fmode_aux; + __u32 gf_numsrc_aux; + struct __kernel_sockaddr_storage gf_slist[1] + __aligned(4); + } __packed; + struct { + __u32 gf_interface; + struct __kernel_sockaddr_storage gf_group + __aligned(4); + __u32 gf_fmode; + __u32 gf_numsrc; + struct __kernel_sockaddr_storage gf_slist_flex[] + __aligned(4); + } __packed; + }; } __packed; #endif /* NET_COMPAT_H */ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index ff901aade..f5967805c 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -172,6 +172,7 @@ void inet_csk_init_xmit_timers(struct sock *sk, void (*delack_handler)(struct timer_list *), void (*keepalive_handler)(struct timer_list *)); void inet_csk_clear_xmit_timers(struct sock *sk); +void inet_csk_clear_xmit_timers_sync(struct sock *sk); static inline void inet_csk_schedule_ack(struct sock *sk) { @@ -339,4 +340,12 @@ static inline bool inet_csk_has_ulp(struct sock *sk) return inet_sk(sk)->is_icsk && !!inet_csk(sk)->icsk_ulp_ops; } +static inline void inet_init_csk_locks(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + spin_lock_init(&icsk->icsk_accept_queue.rskq_lock); + spin_lock_init(&icsk->icsk_accept_queue.fastopenq.lock); +} + #endif /* _INET_CONNECTION_SOCK_H */ diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 58d8e6260..1f016af06 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -333,6 +333,39 @@ static inline bool pskb_inet_may_pull(struct sk_buff *skb) return pskb_network_may_pull(skb, nhlen); } +/* Variant of pskb_inet_may_pull(). + */ +static inline bool skb_vlan_inet_prepare(struct sk_buff *skb) +{ + int nhlen = 0, maclen = ETH_HLEN; + __be16 type = skb->protocol; + + /* Essentially this is skb_protocol(skb, true) + * And we get MAC len. + */ + if (eth_type_vlan(type)) + type = __vlan_get_protocol(skb, type, &maclen); + + switch (type) { +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + nhlen = sizeof(struct ipv6hdr); + break; +#endif + case htons(ETH_P_IP): + nhlen = sizeof(struct iphdr); + break; + } + /* For ETH_P_IPV6/ETH_P_IP we make sure to pull + * a base network header in skb->head. + */ + if (!pskb_may_pull(skb, maclen + nhlen)) + return false; + + skb_set_network_header(skb, maclen); + return true; +} + static inline int ip_encap_hlen(struct ip_tunnel_encap *e) { const struct ip_tunnel_encap_ops *ops; diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index 49aa79c7b..581cd37aa 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -262,8 +262,7 @@ static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, */ static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa) { - if (skb->protocol == htons(ETH_P_802_2)) - memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN); + memcpy(sa, eth_hdr(skb)->h_source, ETH_ALEN); } /** @@ -275,8 +274,7 @@ static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa) */ static inline void llc_pdu_decode_da(struct sk_buff *skb, u8 *da) { - if (skb->protocol == htons(ETH_P_802_2)) - memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN); + memcpy(da, eth_hdr(skb)->h_dest, ETH_ALEN); } /** diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 223765751..2da11d8c0 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -142,9 +142,9 @@ static inline u16 nft_reg_load16(const u32 *sreg) return *(u16 *)sreg; } -static inline void nft_reg_store64(u32 *dreg, u64 val) +static inline void nft_reg_store64(u64 *dreg, u64 val) { - put_unaligned(val, (u64 *)dreg); + put_unaligned(val, dreg); } static inline u64 nft_reg_load64(const u32 *sreg) diff --git a/include/net/sock.h b/include/net/sock.h index 87ee284ea..8bcc96bf2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1681,6 +1681,13 @@ static inline void sock_owned_by_me(const struct sock *sk) #endif } +static inline void sock_not_owned_by_me(const struct sock *sk) +{ +#ifdef CONFIG_LOCKDEP + WARN_ON_ONCE(lockdep_sock_is_held(sk) && debug_locks); +#endif +} + static inline bool sock_owned_by_user(const struct sock *sk) { sock_owned_by_me(sk); diff --git a/include/net/tcp.h b/include/net/tcp.h index 5c03dc6d0..d6e4b6f7d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2224,7 +2224,7 @@ struct tcp_ulp_ops { /* cleanup ulp */ void (*release)(struct sock *sk); /* diagnostic */ - int (*get_info)(const struct sock *sk, struct sk_buff *skb); + int (*get_info)(struct sock *sk, struct sk_buff *skb); size_t (*get_info_size)(const struct sock *sk); /* clone ulp */ void (*clone)(const struct request_sock *req, struct sock *newsk, diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h index 5339baadc..39c7a36cd 100644 --- a/include/scsi/scsi.h +++ b/include/scsi/scsi.h @@ -178,16 +178,17 @@ static inline int scsi_is_wlun(u64 lun) /* * Internal return values. */ - -#define NEEDS_RETRY 0x2001 -#define SUCCESS 0x2002 -#define FAILED 0x2003 -#define QUEUED 0x2004 -#define SOFT_ERROR 0x2005 -#define ADD_TO_MLQUEUE 0x2006 -#define TIMEOUT_ERROR 0x2007 -#define SCSI_RETURN_NOT_HANDLED 0x2008 -#define FAST_IO_FAIL 0x2009 +enum scsi_disposition { + NEEDS_RETRY = 0x2001, + SUCCESS = 0x2002, + FAILED = 0x2003, + QUEUED = 0x2004, + SOFT_ERROR = 0x2005, + ADD_TO_MLQUEUE = 0x2006, + TIMEOUT_ERROR = 0x2007, + SCSI_RETURN_NOT_HANDLED = 0x2008, + FAST_IO_FAIL = 0x2009, +}; /* * Midlevel queue return values. diff --git a/include/scsi/scsi_dh.h b/include/scsi/scsi_dh.h index 2852e470a..47ccf2f11 100644 --- a/include/scsi/scsi_dh.h +++ b/include/scsi/scsi_dh.h @@ -52,7 +52,8 @@ struct scsi_device_handler { /* Filled by the hardware handler */ struct module *module; const char *name; - int (*check_sense)(struct scsi_device *, struct scsi_sense_hdr *); + enum scsi_disposition (*check_sense)(struct scsi_device *, + struct scsi_sense_hdr *); int (*attach)(struct scsi_device *); void (*detach)(struct scsi_device *); int (*activate)(struct scsi_device *, activate_complete, void *); diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h index 6bd5ed695..468094254 100644 --- a/include/scsi/scsi_eh.h +++ b/include/scsi/scsi_eh.h @@ -17,7 +17,7 @@ extern void scsi_report_device_reset(struct Scsi_Host *, int, int); extern int scsi_block_when_processing_errors(struct scsi_device *); extern bool scsi_command_normalize_sense(const struct scsi_cmnd *cmd, struct scsi_sense_hdr *sshdr); -extern int scsi_check_sense(struct scsi_cmnd *); +extern enum scsi_disposition scsi_check_sense(struct scsi_cmnd *); static inline bool scsi_sense_is_deferred(const struct scsi_sense_hdr *sshdr) { diff --git a/include/soc/fsl/qman.h b/include/soc/fsl/qman.h index 9f484113c..3cecbfdb0 100644 --- a/include/soc/fsl/qman.h +++ b/include/soc/fsl/qman.h @@ -1171,6 +1171,15 @@ int qman_delete_cgr(struct qman_cgr *cgr); void qman_delete_cgr_safe(struct qman_cgr *cgr); /** + * qman_update_cgr_safe - Modifies a congestion group object from any CPU + * @cgr: the 'cgr' object to modify + * @opts: state of the CGR settings + * + * This will select the proper CPU and modify the CGR settings. + */ +int qman_update_cgr_safe(struct qman_cgr *cgr, struct qm_mcc_initcgr *opts); + +/** * qman_query_cgr_congested - Queries CGR's congestion status * @cgr: the 'cgr' object to query * @result: returns 'cgr's congestion status, 1 (true) if congested diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h index 330d32d84..a50df4163 100644 --- a/include/trace/events/qdisc.h +++ b/include/trace/events/qdisc.h @@ -53,14 +53,14 @@ TRACE_EVENT(qdisc_reset, TP_ARGS(q), TP_STRUCT__entry( - __string( dev, qdisc_dev(q) ) - __string( kind, q->ops->id ) - __field( u32, parent ) - __field( u32, handle ) + __string( dev, qdisc_dev(q)->name ) + __string( kind, q->ops->id ) + __field( u32, parent ) + __field( u32, handle ) ), TP_fast_assign( - __assign_str(dev, qdisc_dev(q)); + __assign_str(dev, qdisc_dev(q)->name); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; @@ -78,14 +78,14 @@ TRACE_EVENT(qdisc_destroy, TP_ARGS(q), TP_STRUCT__entry( - __string( dev, qdisc_dev(q) ) - __string( kind, q->ops->id ) - __field( u32, parent ) - __field( u32, handle ) + __string( dev, qdisc_dev(q)->name ) + __string( kind, q->ops->id ) + __field( u32, parent ) + __field( u32, handle ) ), TP_fast_assign( - __assign_str(dev, qdisc_dev(q)); + __assign_str(dev, qdisc_dev(q)->name); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index e65300d63..cf4431b74 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -576,6 +576,9 @@ struct btrfs_ioctl_clone_range_args { */ #define BTRFS_DEFRAG_RANGE_COMPRESS 1 #define BTRFS_DEFRAG_RANGE_START_IO 2 +#define BTRFS_DEFRAG_RANGE_FLAGS_SUPP (BTRFS_DEFRAG_RANGE_COMPRESS | \ + BTRFS_DEFRAG_RANGE_START_IO) + struct btrfs_ioctl_defrag_range_args { /* start of the defrag operation */ __u64 start; diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 3960bc3da..c4702fff6 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -190,11 +190,22 @@ struct ip_mreq_source { }; struct ip_msfilter { - __be32 imsf_multiaddr; - __be32 imsf_interface; - __u32 imsf_fmode; - __u32 imsf_numsrc; - __be32 imsf_slist[1]; + union { + struct { + __be32 imsf_multiaddr_aux; + __be32 imsf_interface_aux; + __u32 imsf_fmode_aux; + __u32 imsf_numsrc_aux; + __be32 imsf_slist[1]; + }; + struct { + __be32 imsf_multiaddr; + __be32 imsf_interface; + __u32 imsf_fmode; + __u32 imsf_numsrc; + __be32 imsf_slist_flex[]; + }; + }; }; #define IP_MSFILTER_SIZE(numsrc) \ @@ -213,11 +224,22 @@ struct group_source_req { }; struct group_filter { - __u32 gf_interface; /* interface index */ - struct __kernel_sockaddr_storage gf_group; /* multicast address */ - __u32 gf_fmode; /* filter mode */ - __u32 gf_numsrc; /* number of sources */ - struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */ + union { + struct { + __u32 gf_interface_aux; /* interface index */ + struct __kernel_sockaddr_storage gf_group_aux; /* multicast address */ + __u32 gf_fmode_aux; /* filter mode */ + __u32 gf_numsrc_aux; /* number of sources */ + struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */ + }; + struct { + __u32 gf_interface; /* interface index */ + struct __kernel_sockaddr_storage gf_group; /* multicast address */ + __u32 gf_fmode; /* filter mode */ + __u32 gf_numsrc; /* number of sources */ + struct __kernel_sockaddr_storage gf_slist_flex[]; /* interface index */ + }; + }; }; #define GROUP_FILTER_SIZE(numsrc) \ diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 7989d9483..bed20a89c 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -602,6 +602,7 @@ #define KEY_ALS_TOGGLE 0x230 /* Ambient light sensor */ #define KEY_ROTATE_LOCK_TOGGLE 0x231 /* Display rotation lock */ +#define KEY_REFRESH_RATE_TOGGLE 0x232 /* Display refresh rate toggle */ #define KEY_BUTTONCONFIG 0x240 /* AL Button Configuration */ #define KEY_TASKMANAGER 0x241 /* AL Task/Project Manager */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 163b7ec57..f93ffb1b6 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -262,9 +262,11 @@ enum nft_rule_attributes { /** * enum nft_rule_compat_flags - nf_tables rule compat flags * + * @NFT_RULE_COMPAT_F_UNUSED: unused * @NFT_RULE_COMPAT_F_INV: invert the check result */ enum nft_rule_compat_flags { + NFT_RULE_COMPAT_F_UNUSED = (1 << 0), NFT_RULE_COMPAT_F_INV = (1 << 1), NFT_RULE_COMPAT_F_MASK = NFT_RULE_COMPAT_F_INV, }; diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index c3725b492..46c7bab50 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -28,4 +28,27 @@ struct { MEMBERS } ATTRS; \ struct TAG { MEMBERS } ATTRS NAME; \ } + +#ifdef __cplusplus +/* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */ +#define __DECLARE_FLEX_ARRAY(T, member) \ + T member[0] +#else +/** + * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union + * + * @TYPE: The type of each flexible array element + * @NAME: The name of the flexible array member + * + * In order to have a flexible array member in a union or alone in a + * struct, it needs to be wrapped in an anonymous struct with at least 1 + * named member, but that member can be empty. + */ +#define __DECLARE_FLEX_ARRAY(TYPE, NAME) \ + struct { \ + struct { } __empty_ ## NAME; \ + TYPE NAME[]; \ + } +#endif + #endif diff --git a/include/uapi/scsi/fc/fc_els.h b/include/uapi/scsi/fc/fc_els.h index 8c704e510..91d4be987 100644 --- a/include/uapi/scsi/fc/fc_els.h +++ b/include/uapi/scsi/fc/fc_els.h @@ -916,7 +916,9 @@ enum fc_els_clid_ic { ELS_CLID_IC_LIP = 8, /* receiving LIP */ }; - +/* + * Link Integrity event types + */ enum fc_fpin_li_event_types { FPIN_LI_UNKNOWN = 0x0, FPIN_LI_LINK_FAILURE = 0x1, @@ -943,6 +945,54 @@ enum fc_fpin_li_event_types { { FPIN_LI_DEVICE_SPEC, "Device Specific" }, \ } +/* + * Delivery event types + */ +enum fc_fpin_deli_event_types { + FPIN_DELI_UNKNOWN = 0x0, + FPIN_DELI_TIMEOUT = 0x1, + FPIN_DELI_UNABLE_TO_ROUTE = 0x2, + FPIN_DELI_DEVICE_SPEC = 0xF, +}; + +/* + * Initializer useful for decoding table. + * Please keep this in sync with the above definitions. + */ +#define FC_FPIN_DELI_EVT_TYPES_INIT { \ + { FPIN_DELI_UNKNOWN, "Unknown" }, \ + { FPIN_DELI_TIMEOUT, "Timeout" }, \ + { FPIN_DELI_UNABLE_TO_ROUTE, "Unable to Route" }, \ + { FPIN_DELI_DEVICE_SPEC, "Device Specific" }, \ +} + +/* + * Congestion event types + */ +enum fc_fpin_congn_event_types { + FPIN_CONGN_CLEAR = 0x0, + FPIN_CONGN_LOST_CREDIT = 0x1, + FPIN_CONGN_CREDIT_STALL = 0x2, + FPIN_CONGN_OVERSUBSCRIPTION = 0x3, + FPIN_CONGN_DEVICE_SPEC = 0xF, +}; + +/* + * Initializer useful for decoding table. + * Please keep this in sync with the above definitions. + */ +#define FC_FPIN_CONGN_EVT_TYPES_INIT { \ + { FPIN_CONGN_CLEAR, "Clear" }, \ + { FPIN_CONGN_LOST_CREDIT, "Lost Credit" }, \ + { FPIN_CONGN_CREDIT_STALL, "Credit Stall" }, \ + { FPIN_CONGN_OVERSUBSCRIPTION, "Oversubscription" }, \ + { FPIN_CONGN_DEVICE_SPEC, "Device Specific" }, \ +} + +enum fc_fpin_congn_severity_types { + FPIN_CONGN_SEVERITY_WARNING = 0xF1, + FPIN_CONGN_SEVERITY_ERROR = 0xF7, +}; /* * Link Integrity Notification Descriptor @@ -975,6 +1025,68 @@ struct fc_fn_li_desc { }; /* + * Delivery Notification Descriptor + */ +struct fc_fn_deli_desc { + __be32 desc_tag; /* Descriptor Tag (0x00020002) */ + __be32 desc_len; /* Length of Descriptor (in bytes). + * Size of descriptor excluding + * desc_tag and desc_len fields. + */ + __be64 detecting_wwpn; /* Port Name that detected event */ + __be64 attached_wwpn; /* Port Name of device attached to + * detecting Port Name + */ + __be32 deli_reason_code;/* see enum fc_fpin_deli_event_types */ +}; + +/* + * Peer Congestion Notification Descriptor + */ +struct fc_fn_peer_congn_desc { + __be32 desc_tag; /* Descriptor Tag (0x00020003) */ + __be32 desc_len; /* Length of Descriptor (in bytes). + * Size of descriptor excluding + * desc_tag and desc_len fields. + */ + __be64 detecting_wwpn; /* Port Name that detected event */ + __be64 attached_wwpn; /* Port Name of device attached to + * detecting Port Name + */ + __be16 event_type; /* see enum fc_fpin_congn_event_types */ + __be16 event_modifier; /* Implementation specific value + * describing the event type + */ + __be32 event_period; /* duration (ms) of the detected + * congestion event + */ + __be32 pname_count; /* number of portname_list elements */ + __be64 pname_list[0]; /* list of N_Port_Names accessible + * through the attached port + */ +}; + +/* + * Congestion Notification Descriptor + */ +struct fc_fn_congn_desc { + __be32 desc_tag; /* Descriptor Tag (0x00020004) */ + __be32 desc_len; /* Length of Descriptor (in bytes). + * Size of descriptor excluding + * desc_tag and desc_len fields. + */ + __be16 event_type; /* see enum fc_fpin_congn_event_types */ + __be16 event_modifier; /* Implementation specific value + * describing the event type + */ + __be32 event_period; /* duration (ms) of the detected + * congestion event + */ + __u8 severity; /* command */ + __u8 resv[3]; /* reserved - must be zero */ +}; + +/* * ELS_FPIN - Fabric Performance Impact Notification */ struct fc_els_fpin { diff --git a/init/initramfs.c b/init/initramfs.c index 55b74d7e5..ff0946072 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -589,7 +589,7 @@ static void __init populate_initrd_image(char *err) printk(KERN_INFO "rootfs image is not initramfs (%s); looks like an initrd\n", err); - file = filp_open("/initrd.image", O_WRONLY | O_CREAT, 0700); + file = filp_open("/initrd.image", O_WRONLY|O_CREAT|O_LARGEFILE, 0700); if (IS_ERR(file)) return; diff --git a/init/main.c b/init/main.c index 298989b0d..b1593bdaf 100644 --- a/init/main.c +++ b/init/main.c @@ -627,6 +627,8 @@ static void __init setup_command_line(char *command_line) if (!saved_command_line) panic("%s: Failed to allocate %zu bytes\n", __func__, len + ilen); + len = xlen + strlen(command_line) + 1; + static_command_line = memblock_alloc(len, SMP_CACHE_BYTES); if (!static_command_line) panic("%s: Failed to allocate %zu bytes\n", __func__, len); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 936abc6ee..93f9ecedc 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -62,7 +62,6 @@ #include <linux/net.h> #include <net/sock.h> #include <net/af_unix.h> -#include <net/scm.h> #include <linux/anon_inodes.h> #include <linux/sched/mm.h> #include <linux/uaccess.h> @@ -440,9 +439,6 @@ struct io_ring_ctx { /* Keep this last, we don't need it for the fast path */ struct { - #if defined(CONFIG_UNIX) - struct socket *ring_sock; - #endif /* hashed buffered write serialization */ struct io_wq_hash *hash_map; @@ -1113,19 +1109,6 @@ static struct kmem_cache *req_cachep; static const struct file_operations io_uring_fops; -struct sock *io_uring_get_socket(struct file *file) -{ -#if defined(CONFIG_UNIX) - if (file->f_op == &io_uring_fops) { - struct io_ring_ctx *ctx = file->private_data; - - return ctx->ring_sock->sk; - } -#endif - return NULL; -} -EXPORT_SYMBOL(io_uring_get_socket); - static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked) { if (!*locked) { @@ -7657,7 +7640,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, ktime_t *timeout) { - int io_wait, ret; + int ret; /* make sure we run task_work before checking for signals */ ret = io_run_task_work_sig(); @@ -7672,13 +7655,12 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, * can take into account that the task is waiting for IO - turns out * to be important for low QD IO. */ - io_wait = current->in_iowait; if (current_pending_io()) current->in_iowait = 1; ret = 1; if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS)) ret = -ETIME; - current->in_iowait = io_wait; + current->in_iowait = 0; return ret; } @@ -7989,15 +7971,6 @@ static void io_free_file_tables(struct io_file_table *table) static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) { -#if defined(CONFIG_UNIX) - if (ctx->ring_sock) { - struct sock *sock = ctx->ring_sock->sk; - struct sk_buff *skb; - - while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL) - kfree_skb(skb); - } -#else int i; for (i = 0; i < ctx->nr_user_files; i++) { @@ -8007,7 +7980,6 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) if (file) fput(file); } -#endif io_free_file_tables(&ctx->file_table); io_rsrc_data_free(ctx->file_data); ctx->file_data = NULL; @@ -8159,170 +8131,11 @@ static struct io_sq_data *io_get_sq_data(struct io_uring_params *p, return sqd; } -#if defined(CONFIG_UNIX) -/* - * Ensure the UNIX gc is aware of our file set, so we are certain that - * the io_uring can be safely unregistered on process exit, even if we have - * loops in the file referencing. - */ -static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) -{ - struct sock *sk = ctx->ring_sock->sk; - struct scm_fp_list *fpl; - struct sk_buff *skb; - int i, nr_files; - - fpl = kzalloc(sizeof(*fpl), GFP_KERNEL); - if (!fpl) - return -ENOMEM; - - skb = alloc_skb(0, GFP_KERNEL); - if (!skb) { - kfree(fpl); - return -ENOMEM; - } - - skb->sk = sk; - skb->scm_io_uring = 1; - - nr_files = 0; - fpl->user = get_uid(current_user()); - for (i = 0; i < nr; i++) { - struct file *file = io_file_from_index(ctx, i + offset); - - if (!file) - continue; - fpl->fp[nr_files] = get_file(file); - unix_inflight(fpl->user, fpl->fp[nr_files]); - nr_files++; - } - - if (nr_files) { - fpl->max = SCM_MAX_FD; - fpl->count = nr_files; - UNIXCB(skb).fp = fpl; - skb->destructor = unix_destruct_scm; - refcount_add(skb->truesize, &sk->sk_wmem_alloc); - skb_queue_head(&sk->sk_receive_queue, skb); - - for (i = 0; i < nr; i++) { - struct file *file = io_file_from_index(ctx, i + offset); - - if (file) - fput(file); - } - } else { - kfree_skb(skb); - free_uid(fpl->user); - kfree(fpl); - } - - return 0; -} - -/* - * If UNIX sockets are enabled, fd passing can cause a reference cycle which - * causes regular reference counting to break down. We rely on the UNIX - * garbage collection to take care of this problem for us. - */ -static int io_sqe_files_scm(struct io_ring_ctx *ctx) -{ - unsigned left, total; - int ret = 0; - - total = 0; - left = ctx->nr_user_files; - while (left) { - unsigned this_files = min_t(unsigned, left, SCM_MAX_FD); - - ret = __io_sqe_files_scm(ctx, this_files, total); - if (ret) - break; - left -= this_files; - total += this_files; - } - - if (!ret) - return 0; - - while (total < ctx->nr_user_files) { - struct file *file = io_file_from_index(ctx, total); - - if (file) - fput(file); - total++; - } - - return ret; -} -#else -static int io_sqe_files_scm(struct io_ring_ctx *ctx) -{ - return 0; -} -#endif - static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) { struct file *file = prsrc->file; -#if defined(CONFIG_UNIX) - struct sock *sock = ctx->ring_sock->sk; - struct sk_buff_head list, *head = &sock->sk_receive_queue; - struct sk_buff *skb; - int i; - - __skb_queue_head_init(&list); - - /* - * Find the skb that holds this file in its SCM_RIGHTS. When found, - * remove this entry and rearrange the file array. - */ - skb = skb_dequeue(head); - while (skb) { - struct scm_fp_list *fp; - - fp = UNIXCB(skb).fp; - for (i = 0; i < fp->count; i++) { - int left; - - if (fp->fp[i] != file) - continue; - - unix_notinflight(fp->user, fp->fp[i]); - left = fp->count - 1 - i; - if (left) { - memmove(&fp->fp[i], &fp->fp[i + 1], - left * sizeof(struct file *)); - } - fp->count--; - if (!fp->count) { - kfree_skb(skb); - skb = NULL; - } else { - __skb_queue_tail(&list, skb); - } - fput(file); - file = NULL; - break; - } - - if (!file) - break; - - __skb_queue_tail(&list, skb); - - skb = skb_dequeue(head); - } - if (skb_peek(&list)) { - spin_lock_irq(&head->lock); - while ((skb = __skb_dequeue(&list)) != NULL) - __skb_queue_tail(head, skb); - spin_unlock_irq(&head->lock); - } -#else fput(file); -#endif } static void __io_rsrc_put_work(struct io_rsrc_node *ref_node) @@ -8433,14 +8246,8 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, io_fixed_file_set(io_fixed_file_slot(&ctx->file_table, i), file); } - ret = io_sqe_files_scm(ctx); - if (ret) { - __io_sqe_files_unregister(ctx); - return ret; - } - io_rsrc_node_switch(ctx, NULL); - return ret; + return 0; out_fput: for (i = 0; i < ctx->nr_user_files; i++) { file = io_file_from_index(ctx, i); @@ -9395,12 +9202,6 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list)); WARN_ON_ONCE(!llist_empty(&ctx->rsrc_put_llist)); -#if defined(CONFIG_UNIX) - if (ctx->ring_sock) { - ctx->ring_sock->file = NULL; /* so that iput() is called */ - sock_release(ctx->ring_sock); - } -#endif WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); if (ctx->mm_account) { @@ -10275,6 +10076,11 @@ static const struct file_operations io_uring_fops = { #endif }; +bool io_is_uring_fops(struct file *file) +{ + return file->f_op == &io_uring_fops; +} + static int io_allocate_scq_urings(struct io_ring_ctx *ctx, struct io_uring_params *p) { @@ -10337,32 +10143,12 @@ static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file) /* * Allocate an anonymous fd, this is what constitutes the application * visible backing of an io_uring instance. The application mmaps this - * fd to gain access to the SQ/CQ ring details. If UNIX sockets are enabled, - * we have to tie this fd to a socket for file garbage collection purposes. + * fd to gain access to the SQ/CQ ring details. */ static struct file *io_uring_get_file(struct io_ring_ctx *ctx) { - struct file *file; -#if defined(CONFIG_UNIX) - int ret; - - ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP, - &ctx->ring_sock); - if (ret) - return ERR_PTR(ret); -#endif - - file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx, - O_RDWR | O_CLOEXEC); -#if defined(CONFIG_UNIX) - if (IS_ERR(file)) { - sock_release(ctx->ring_sock); - ctx->ring_sock = NULL; - } else { - ctx->ring_sock->file = file; - } -#endif - return file; + return anon_inode_getfile("[io_uring]", &io_uring_fops, ctx, + O_RDWR | O_CLOEXEC); } static int io_uring_create(unsigned entries, struct io_uring_params *p, diff --git a/kernel/async.c b/kernel/async.c index 1746cd65e..5dba7461f 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -145,6 +145,39 @@ static void async_run_entry_fn(struct work_struct *work) wake_up(&async_done); } +static async_cookie_t __async_schedule_node_domain(async_func_t func, + void *data, int node, + struct async_domain *domain, + struct async_entry *entry) +{ + async_cookie_t newcookie; + unsigned long flags; + + INIT_LIST_HEAD(&entry->domain_list); + INIT_LIST_HEAD(&entry->global_list); + INIT_WORK(&entry->work, async_run_entry_fn); + entry->func = func; + entry->data = data; + entry->domain = domain; + + spin_lock_irqsave(&async_lock, flags); + + /* allocate cookie and queue */ + newcookie = entry->cookie = next_cookie++; + + list_add_tail(&entry->domain_list, &domain->pending); + if (domain->registered) + list_add_tail(&entry->global_list, &async_global_pending); + + atomic_inc(&entry_count); + spin_unlock_irqrestore(&async_lock, flags); + + /* schedule for execution */ + queue_work_node(node, system_unbound_wq, &entry->work); + + return newcookie; +} + /** * async_schedule_node_domain - NUMA specific version of async_schedule_domain * @func: function to execute asynchronously @@ -186,29 +219,8 @@ async_cookie_t async_schedule_node_domain(async_func_t func, void *data, func(data, newcookie); return newcookie; } - INIT_LIST_HEAD(&entry->domain_list); - INIT_LIST_HEAD(&entry->global_list); - INIT_WORK(&entry->work, async_run_entry_fn); - entry->func = func; - entry->data = data; - entry->domain = domain; - - spin_lock_irqsave(&async_lock, flags); - - /* allocate cookie and queue */ - newcookie = entry->cookie = next_cookie++; - - list_add_tail(&entry->domain_list, &domain->pending); - if (domain->registered) - list_add_tail(&entry->global_list, &async_global_pending); - - atomic_inc(&entry_count); - spin_unlock_irqrestore(&async_lock, flags); - - /* schedule for execution */ - queue_work_node(node, system_unbound_wq, &entry->work); - return newcookie; + return __async_schedule_node_domain(func, data, node, domain, entry); } EXPORT_SYMBOL_GPL(async_schedule_node_domain); @@ -232,6 +244,35 @@ async_cookie_t async_schedule_node(async_func_t func, void *data, int node) EXPORT_SYMBOL_GPL(async_schedule_node); /** + * async_schedule_dev_nocall - A simplified variant of async_schedule_dev() + * @func: function to execute asynchronously + * @dev: device argument to be passed to function + * + * @dev is used as both the argument for the function and to provide NUMA + * context for where to run the function. + * + * If the asynchronous execution of @func is scheduled successfully, return + * true. Otherwise, do nothing and return false, unlike async_schedule_dev() + * that will run the function synchronously then. + */ +bool async_schedule_dev_nocall(async_func_t func, struct device *dev) +{ + struct async_entry *entry; + + entry = kzalloc(sizeof(struct async_entry), GFP_KERNEL); + + /* Give up if there is no memory or too much work. */ + if (!entry || atomic_read(&entry_count) > MAX_WORK) { + kfree(entry); + return false; + } + + __async_schedule_node_domain(func, dev, dev_to_node(dev), + &async_dfl_domain, entry); + return true; +} + +/** * async_synchronize_full - synchronize all asynchronous function calls * * This function waits until all asynchronous function calls have been done. diff --git a/kernel/audit.c b/kernel/audit.c index aeec86ed4..2ab04e0a7 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -490,15 +490,19 @@ static void auditd_conn_free(struct rcu_head *rcu) * @pid: auditd PID * @portid: auditd netlink portid * @net: auditd network namespace pointer + * @skb: the netlink command from the audit daemon + * @ack: netlink ack flag, cleared if ack'd here * * Description: * This function will obtain and drop network namespace references as * necessary. Returns zero on success, negative values on failure. */ -static int auditd_set(struct pid *pid, u32 portid, struct net *net) +static int auditd_set(struct pid *pid, u32 portid, struct net *net, + struct sk_buff *skb, bool *ack) { unsigned long flags; struct auditd_connection *ac_old, *ac_new; + struct nlmsghdr *nlh; if (!pid || !net) return -EINVAL; @@ -510,6 +514,13 @@ static int auditd_set(struct pid *pid, u32 portid, struct net *net) ac_new->portid = portid; ac_new->net = get_net(net); + /* send the ack now to avoid a race with the queue backlog */ + if (*ack) { + nlh = nlmsg_hdr(skb); + netlink_ack(skb, nlh, 0, NULL); + *ack = false; + } + spin_lock_irqsave(&auditd_conn_lock, flags); ac_old = rcu_dereference_protected(auditd_conn, lockdep_is_held(&auditd_conn_lock)); @@ -1203,7 +1214,8 @@ static int audit_replace(struct pid *pid) return auditd_send_unicast_skb(skb); } -static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) +static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, + bool *ack) { u32 seq; void *data; @@ -1296,7 +1308,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) /* register a new auditd connection */ err = auditd_set(req_pid, NETLINK_CB(skb).portid, - sock_net(NETLINK_CB(skb).sk)); + sock_net(NETLINK_CB(skb).sk), + skb, ack); if (audit_enabled != AUDIT_OFF) audit_log_config_change("audit_pid", new_pid, @@ -1541,9 +1554,10 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) * Parse the provided skb and deal with any messages that may be present, * malformed skbs are discarded. */ -static void audit_receive(struct sk_buff *skb) +static void audit_receive(struct sk_buff *skb) { struct nlmsghdr *nlh; + bool ack; /* * len MUST be signed for nlmsg_next to be able to dec it below 0 * if the nlmsg_len was not aligned @@ -1556,9 +1570,12 @@ static void audit_receive(struct sk_buff *skb) audit_ctl_lock(); while (nlmsg_ok(nlh, len)) { - err = audit_receive_msg(skb, nlh); - /* if err or if this message says it wants a response */ - if (err || (nlh->nlmsg_flags & NLM_F_ACK)) + ack = nlh->nlmsg_flags & NLM_F_ACK; + err = audit_receive_msg(skb, nlh, &ack); + + /* send an ack if the user asked for one and audit_receive_msg + * didn't already do it, or if there was an error. */ + if (ack || err) netlink_ack(skb, nlh, err, NULL); nlh = nlmsg_next(nlh, &len); diff --git a/kernel/bounds.c b/kernel/bounds.c index 9795d75b0..a3e1d3dfa 100644 --- a/kernel/bounds.c +++ b/kernel/bounds.c @@ -19,7 +19,7 @@ int main(void) DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS); DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES); #ifdef CONFIG_SMP - DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS)); + DEFINE(NR_CPUS_BITS, order_base_2(CONFIG_NR_CPUS)); #endif DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t)); /* End of constants */ diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index f241bda26..510233812 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -764,7 +764,7 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, } if (old_ptr) - map->ops->map_fd_put_ptr(old_ptr); + map->ops->map_fd_put_ptr(map, old_ptr, true); return 0; } @@ -787,7 +787,7 @@ static int fd_array_map_delete_elem(struct bpf_map *map, void *key) } if (old_ptr) { - map->ops->map_fd_put_ptr(old_ptr); + map->ops->map_fd_put_ptr(map, old_ptr, true); return 0; } else { return -ENOENT; @@ -811,8 +811,9 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map, return prog; } -static void prog_fd_array_put_ptr(void *ptr) +static void prog_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { + /* bpf_prog is freed after one RCU or tasks trace grace period */ bpf_prog_put(ptr); } @@ -1139,8 +1140,9 @@ err_out: return ee; } -static void perf_event_fd_array_put_ptr(void *ptr) +static void perf_event_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { + /* bpf_perf_event is freed after one RCU grace period */ bpf_event_entry_free_rcu(ptr); } @@ -1195,7 +1197,7 @@ static void *cgroup_fd_array_get_ptr(struct bpf_map *map, return cgroup_get_from_fd(fd); } -static void cgroup_fd_array_put_ptr(void *ptr) +static void cgroup_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { /* cgroup_put free cgrp after a rcu grace period */ cgroup_put(ptr); diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index c61a23b56..9a4378df4 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -229,7 +229,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, void **frames, int n, struct xdp_cpumap_stats *stats) { - struct xdp_rxq_info rxq; + struct xdp_rxq_info rxq = {}; struct xdp_buff xdp; int i, nframes = 0; @@ -299,6 +299,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; + unsigned long last_qs = jiffies; set_current_state(TASK_INTERRUPTIBLE); @@ -322,10 +323,12 @@ static int cpu_map_kthread_run(void *data) if (__ptr_ring_empty(rcpu->queue)) { schedule(); sched = 1; + last_qs = jiffies; } else { __set_current_state(TASK_RUNNING); } } else { + rcu_softirq_qs_periodic(last_qs); sched = cond_resched(); } diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 01149821d..07b5edb2c 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -109,8 +109,6 @@ static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { u32 valsize = attr->value_size; - u64 cost = 0; - int err; /* check sanity of attributes. 2 value sizes supported: * 4 bytes: ifindex @@ -131,25 +129,18 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) bpf_map_init_from_attr(&dtab->map, attr); if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { - dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); - - if (!dtab->n_buckets) /* Overflow check */ + /* hash table size must be power of 2; roundup_pow_of_two() can + * overflow into UB on 32-bit arches, so check that first + */ + if (dtab->map.max_entries > 1UL << 31) return -EINVAL; - cost += (u64) sizeof(struct hlist_head) * dtab->n_buckets; - } else { - cost += (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); - } - /* if map size is larger than memlock limit, reject it */ - err = bpf_map_charge_init(&dtab->map.memory, cost); - if (err) - return -EINVAL; + dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); - if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, dtab->map.numa_node); if (!dtab->dev_index_head) - goto free_charge; + return -ENOMEM; spin_lock_init(&dtab->index_lock); } else { @@ -157,14 +148,10 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) sizeof(struct bpf_dtab_netdev *), dtab->map.numa_node); if (!dtab->netdev_map) - goto free_charge; + return -ENOMEM; } return 0; - -free_charge: - bpf_map_charge_finish(&dtab->map.memory); - return -ENOMEM; } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 0ce445aad..72bc5f575 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -443,7 +443,13 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) num_possible_cpus()); } - /* hash table size must be power of 2 */ + /* hash table size must be power of 2; roundup_pow_of_two() can overflow + * into UB on 32-bit arches, so check that first + */ + err = -E2BIG; + if (htab->map.max_entries > 1UL << 31) + goto free_htab; + htab->n_buckets = roundup_pow_of_two(htab->map.max_entries); htab->elem_size = sizeof(struct htab_elem) + @@ -453,10 +459,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) else htab->elem_size += round_up(htab->map.value_size, 8); - err = -E2BIG; - /* prevent zero size kmalloc and check for u32 overflow */ - if (htab->n_buckets == 0 || - htab->n_buckets > U32_MAX / sizeof(struct bucket)) + /* check for u32 overflow */ + if (htab->n_buckets > U32_MAX / sizeof(struct bucket)) goto free_htab; cost = (u64) htab->n_buckets * sizeof(struct bucket) + @@ -786,7 +790,7 @@ static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l) if (map->ops->map_fd_put_ptr) { ptr = fd_htab_map_get_ptr(map, l); - map->ops->map_fd_put_ptr(ptr); + map->ops->map_fd_put_ptr(map, ptr, true); } } @@ -2023,7 +2027,7 @@ static void fd_htab_map_free(struct bpf_map *map) hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { void *ptr = fd_htab_map_get_ptr(map, l); - map->ops->map_fd_put_ptr(ptr); + map->ops->map_fd_put_ptr(map, ptr, false); } } @@ -2064,7 +2068,7 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, ret = htab_map_update_elem(map, key, &ptr, map_flags); if (ret) - map->ops->map_fd_put_ptr(ptr); + map->ops->map_fd_put_ptr(map, ptr, false); return ret; } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 0efe7c7bf..084ac7e42 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -278,13 +278,18 @@ static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock) static DEFINE_PER_CPU(unsigned long, irqsave_flags); -notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) +static inline void __bpf_spin_lock_irqsave(struct bpf_spin_lock *lock) { unsigned long flags; local_irq_save(flags); __bpf_spin_lock(lock); __this_cpu_write(irqsave_flags, flags); +} + +NOTRACE_BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) +{ + __bpf_spin_lock_irqsave(lock); return 0; } @@ -295,13 +300,18 @@ const struct bpf_func_proto bpf_spin_lock_proto = { .arg1_type = ARG_PTR_TO_SPIN_LOCK, }; -notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) +static inline void __bpf_spin_unlock_irqrestore(struct bpf_spin_lock *lock) { unsigned long flags; flags = __this_cpu_read(irqsave_flags); __bpf_spin_unlock(lock); local_irq_restore(flags); +} + +NOTRACE_BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) +{ + __bpf_spin_unlock_irqrestore(lock); return 0; } @@ -322,9 +332,9 @@ void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, else lock = dst + map->spin_lock_off; preempt_disable(); - ____bpf_spin_lock(lock); + __bpf_spin_lock_irqsave(lock); copy_map_value(map, dst, src); - ____bpf_spin_unlock(lock); + __bpf_spin_unlock_irqrestore(lock); preempt_enable(); } diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 39ab0b68c..caa1a17cb 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -100,12 +100,17 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map, return inner_map; } -void bpf_map_fd_put_ptr(void *ptr) +void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { - /* ptr->ops->map_free() has to go through one - * rcu grace period by itself. + struct bpf_map *inner_map = ptr; + + /* The inner map may still be used by both non-sleepable and sleepable + * bpf program, so free it after one RCU grace period and one tasks + * trace RCU grace period. */ - bpf_map_put(ptr); + if (need_defer) + WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true); + bpf_map_put(inner_map); } u32 bpf_map_fd_sys_lookup_elem(void *ptr) diff --git a/kernel/bpf/map_in_map.h b/kernel/bpf/map_in_map.h index bcb7534af..7d6160235 100644 --- a/kernel/bpf/map_in_map.h +++ b/kernel/bpf/map_in_map.h @@ -13,7 +13,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd); void bpf_map_meta_free(struct bpf_map *map_meta); void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file, int ufd); -void bpf_map_fd_put_ptr(void *ptr); +void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer); u32 bpf_map_fd_sys_lookup_elem(void *ptr); #endif diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index b8afea2ce..3ec76cb5f 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -115,11 +115,14 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) } else if (value_size / 8 > sysctl_perf_event_max_stack) return ERR_PTR(-EINVAL); - /* hash table size must be power of 2 */ - n_buckets = roundup_pow_of_two(attr->max_entries); - if (!n_buckets) + /* hash table size must be power of 2; roundup_pow_of_two() can overflow + * into UB on 32-bit arches, so check that first + */ + if (attr->max_entries > 1UL << 31) return ERR_PTR(-E2BIG); + n_buckets = roundup_pow_of_two(attr->max_entries); + cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); err = bpf_map_charge_init(&mem, cost + attr->max_entries * (sizeof(struct stack_map_bucket) + (u64)value_size)); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index aaad2dce2..e1bee8cd3 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -493,6 +493,25 @@ static void bpf_map_put_uref(struct bpf_map *map) } } +static void bpf_map_free_in_work(struct bpf_map *map) +{ + INIT_WORK(&map->work, bpf_map_free_deferred); + schedule_work(&map->work); +} + +static void bpf_map_free_rcu_gp(struct rcu_head *rcu) +{ + bpf_map_free_in_work(container_of(rcu, struct bpf_map, rcu)); +} + +static void bpf_map_free_mult_rcu_gp(struct rcu_head *rcu) +{ + if (rcu_trace_implies_rcu_gp()) + bpf_map_free_rcu_gp(rcu); + else + call_rcu(rcu, bpf_map_free_rcu_gp); +} + /* decrement map refcnt and schedule it for freeing via workqueue * (unrelying map implementation ops->map_free() might sleep) */ @@ -502,8 +521,11 @@ static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) /* bpf_map_free_id() must be called first */ bpf_map_free_id(map, do_idr_lock); btf_put(map->btf); - INIT_WORK(&map->work, bpf_map_free_deferred); - schedule_work(&map->work); + + if (READ_ONCE(map->free_after_mult_rcu_gp)) + call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp); + else + bpf_map_free_in_work(map); } } @@ -1285,6 +1307,9 @@ int generic_map_delete_batch(struct bpf_map *map, if (!max_count) return 0; + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; @@ -1343,6 +1368,9 @@ int generic_map_update_batch(struct bpf_map *map, if (!max_count) return 0; + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fce2345f6..25f8a8716 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3941,6 +3941,11 @@ static int check_stack_access_within_bounds( err = check_stack_slot_within_bounds(min_off, state, type); if (!err && max_off > 0) err = -EINVAL; /* out of stack access into non-negative offsets */ + if (!err && access_size < 0) + /* access_size should not be negative (or overflow an int); others checks + * along the way should have prevented such an access. + */ + err = -EFAULT; /* invalid negative access size; integer overflow? */ if (err) { if (tnum_is_const(reg->var_off)) { diff --git a/kernel/cpu.c b/kernel/cpu.c index abf717c4f..d84ba5a13 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2600,7 +2600,8 @@ enum cpu_mitigations { }; static enum cpu_mitigations cpu_mitigations __ro_after_init = - CPU_MITIGATIONS_AUTO; + IS_ENABLED(CONFIG_CPU_MITIGATIONS) ? CPU_MITIGATIONS_AUTO : + CPU_MITIGATIONS_OFF; static int __init mitigations_parse_cmdline(char *arg) { diff --git a/kernel/events/core.c b/kernel/events/core.c index afedd008e..e0b47bed8 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6890,9 +6890,16 @@ static void perf_output_read_group(struct perf_output_handle *handle, { struct perf_event *leader = event->group_leader, *sub; u64 read_format = event->attr.read_format; + unsigned long flags; u64 values[6]; int n = 0; + /* + * Disabling interrupts avoids all counter scheduling + * (context switches, timer based rotation and IPIs). + */ + local_irq_save(flags); + values[n++] = 1 + leader->nr_siblings; if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) @@ -6928,6 +6935,8 @@ static void perf_output_read_group(struct perf_output_handle *handle, __output_copy(handle, values, n * sizeof(u64)); } + + local_irq_restore(flags); } #define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\ @@ -10855,9 +10864,30 @@ static DEVICE_ATTR_RW(perf_event_mux_interval_ms); static struct attribute *pmu_dev_attrs[] = { &dev_attr_type.attr, &dev_attr_perf_event_mux_interval_ms.attr, + &dev_attr_nr_addr_filters.attr, + NULL, +}; + +static umode_t pmu_dev_is_visible(struct kobject *kobj, struct attribute *a, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct pmu *pmu = dev_get_drvdata(dev); + + if (n == 2 && !pmu->nr_addr_filters) + return 0; + + return a->mode; +} + +static struct attribute_group pmu_dev_attr_group = { + .is_visible = pmu_dev_is_visible, + .attrs = pmu_dev_attrs, +}; + +static const struct attribute_group *pmu_dev_groups[] = { + &pmu_dev_attr_group, NULL, }; -ATTRIBUTE_GROUPS(pmu_dev); static int pmu_bus_running; static struct bus_type pmu_bus = { @@ -10893,18 +10923,11 @@ static int pmu_dev_alloc(struct pmu *pmu) if (ret) goto free_dev; - /* For PMUs with address filters, throw in an extra attribute: */ - if (pmu->nr_addr_filters) - ret = device_create_file(pmu->dev, &dev_attr_nr_addr_filters); - - if (ret) - goto del_dev; - - if (pmu->attr_update) + if (pmu->attr_update) { ret = sysfs_update_groups(&pmu->dev->kobj, pmu->attr_update); - - if (ret) - goto del_dev; + if (ret) + goto del_dev; + } out: return ret; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 05d3e156a..dba6541c0 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1647,10 +1647,17 @@ static int check_kprobe_address_safe(struct kprobe *p, jump_label_lock(); preempt_disable(); - /* Ensure it is not in reserved area nor out of text */ - if (!(core_kernel_text((unsigned long) p->addr) || - is_module_text_address((unsigned long) p->addr)) || - in_gate_area_no_mm((unsigned long) p->addr) || + /* Ensure the address is in a text area, and find a module if exists. */ + *probed_mod = NULL; + if (!core_kernel_text((unsigned long) p->addr)) { + *probed_mod = __module_text_address((unsigned long) p->addr); + if (!(*probed_mod)) { + ret = -EINVAL; + goto out; + } + } + /* Ensure it is not in reserved area. */ + if (in_gate_area_no_mm((unsigned long) p->addr) || within_kprobe_blacklist((unsigned long) p->addr) || jump_label_text_reserved(p->addr, p->addr) || static_call_text_reserved(p->addr, p->addr) || @@ -1660,8 +1667,7 @@ static int check_kprobe_address_safe(struct kprobe *p, goto out; } - /* Check if are we probing a module */ - *probed_mod = __module_text_address((unsigned long) p->addr); + /* Get module refcount and reject __init functions for loaded modules. */ if (*probed_mod) { /* * We must hold a refcount of the probed module while updating diff --git a/kernel/panic.c b/kernel/panic.c index bc39e2b27..30d8da0d4 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -427,6 +427,14 @@ void panic(const char *fmt, ...) /* Do not scroll important messages printed above */ suppress_printk = 1; + + /* + * The final messages may not have been printed if in a context that + * defers printing (such as NMI) and irq_work is not available. + * Explicitly flush the kernel log buffer one last time. + */ + console_flush_on_panic(CONSOLE_FLUSH_PENDING); + local_irq_enable(); for (i = 0; ; i += PANIC_TIMER_STEP) { touch_softlockup_watchdog(); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 4aa4d5d39..14e981c05 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -187,6 +187,7 @@ static int __init mem_sleep_default_setup(char *str) if (mem_sleep_labels[state] && !strcmp(str, mem_sleep_labels[state])) { mem_sleep_default = state; + mem_sleep_current = state; break; } diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 25e7cb96b..b288aba80 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -603,11 +603,11 @@ static int crc32_threadfn(void *data) unsigned i; while (1) { - wait_event(d->go, atomic_read(&d->ready) || + wait_event(d->go, atomic_read_acquire(&d->ready) || kthread_should_stop()); if (kthread_should_stop()) { d->thr = NULL; - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); break; } @@ -616,7 +616,7 @@ static int crc32_threadfn(void *data) for (i = 0; i < d->run_threads; i++) *d->crc32 = crc32_le(*d->crc32, d->unc[i], *d->unc_len[i]); - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); } return 0; @@ -646,12 +646,12 @@ static int lzo_compress_threadfn(void *data) struct cmp_data *d = data; while (1) { - wait_event(d->go, atomic_read(&d->ready) || + wait_event(d->go, atomic_read_acquire(&d->ready) || kthread_should_stop()); if (kthread_should_stop()) { d->thr = NULL; d->ret = -1; - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); break; } @@ -660,7 +660,7 @@ static int lzo_compress_threadfn(void *data) d->ret = lzo1x_1_compress(d->unc, d->unc_len, d->cmp + LZO_HEADER, &d->cmp_len, d->wrk); - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); } return 0; @@ -798,7 +798,7 @@ static int save_image_lzo(struct swap_map_handle *handle, data[thr].unc_len = off; - atomic_set(&data[thr].ready, 1); + atomic_set_release(&data[thr].ready, 1); wake_up(&data[thr].go); } @@ -806,12 +806,12 @@ static int save_image_lzo(struct swap_map_handle *handle, break; crc->run_threads = thr; - atomic_set(&crc->ready, 1); + atomic_set_release(&crc->ready, 1); wake_up(&crc->go); for (run_threads = thr, thr = 0; thr < run_threads; thr++) { wait_event(data[thr].done, - atomic_read(&data[thr].stop)); + atomic_read_acquire(&data[thr].stop)); atomic_set(&data[thr].stop, 0); ret = data[thr].ret; @@ -850,7 +850,7 @@ static int save_image_lzo(struct swap_map_handle *handle, } } - wait_event(crc->done, atomic_read(&crc->stop)); + wait_event(crc->done, atomic_read_acquire(&crc->stop)); atomic_set(&crc->stop, 0); } @@ -1132,12 +1132,12 @@ static int lzo_decompress_threadfn(void *data) struct dec_data *d = data; while (1) { - wait_event(d->go, atomic_read(&d->ready) || + wait_event(d->go, atomic_read_acquire(&d->ready) || kthread_should_stop()); if (kthread_should_stop()) { d->thr = NULL; d->ret = -1; - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); break; } @@ -1150,7 +1150,7 @@ static int lzo_decompress_threadfn(void *data) flush_icache_range((unsigned long)d->unc, (unsigned long)d->unc + d->unc_len); - atomic_set(&d->stop, 1); + atomic_set_release(&d->stop, 1); wake_up(&d->done); } return 0; @@ -1338,7 +1338,7 @@ static int load_image_lzo(struct swap_map_handle *handle, } if (crc->run_threads) { - wait_event(crc->done, atomic_read(&crc->stop)); + wait_event(crc->done, atomic_read_acquire(&crc->stop)); atomic_set(&crc->stop, 0); crc->run_threads = 0; } @@ -1374,7 +1374,7 @@ static int load_image_lzo(struct swap_map_handle *handle, pg = 0; } - atomic_set(&data[thr].ready, 1); + atomic_set_release(&data[thr].ready, 1); wake_up(&data[thr].go); } @@ -1393,7 +1393,7 @@ static int load_image_lzo(struct swap_map_handle *handle, for (run_threads = thr, thr = 0; thr < run_threads; thr++) { wait_event(data[thr].done, - atomic_read(&data[thr].stop)); + atomic_read_acquire(&data[thr].stop)); atomic_set(&data[thr].stop, 0); ret = data[thr].ret; @@ -1424,7 +1424,7 @@ static int load_image_lzo(struct swap_map_handle *handle, ret = snapshot_write_next(snapshot); if (ret <= 0) { crc->run_threads = thr + 1; - atomic_set(&crc->ready, 1); + atomic_set_release(&crc->ready, 1); wake_up(&crc->go); goto out_finish; } @@ -1432,13 +1432,13 @@ static int load_image_lzo(struct swap_map_handle *handle, } crc->run_threads = thr; - atomic_set(&crc->ready, 1); + atomic_set_release(&crc->ready, 1); wake_up(&crc->go); } out_finish: if (crc->run_threads) { - wait_event(crc->done, atomic_read(&crc->stop)); + wait_event(crc->done, atomic_read_acquire(&crc->stop)); atomic_set(&crc->stop, 0); } stop = ktime_get(); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 17a310dcb..a8af93cbc 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1866,6 +1866,12 @@ static int console_trylock_spinning(void) */ mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_); + /* + * Update @console_may_schedule for trylock because the previous + * owner may have been schedulable. + */ + console_may_schedule = 0; + return 1; } @@ -2684,6 +2690,21 @@ static int __init keep_bootcon_setup(char *str) early_param("keep_bootcon", keep_bootcon_setup); +static int console_call_setup(struct console *newcon, char *options) +{ + int err; + + if (!newcon->setup) + return 0; + + /* Synchronize with possible boot console. */ + console_lock(); + err = newcon->setup(newcon, options); + console_unlock(); + + return err; +} + /* * This is called by register_console() to try to match * the newly registered console with any of the ones selected @@ -2693,7 +2714,8 @@ early_param("keep_bootcon", keep_bootcon_setup); * Care need to be taken with consoles that are statically * enabled such as netconsole */ -static int try_enable_new_console(struct console *newcon, bool user_specified) +static int try_enable_preferred_console(struct console *newcon, + bool user_specified) { struct console_cmdline *c; int i, err; @@ -2718,8 +2740,8 @@ static int try_enable_new_console(struct console *newcon, bool user_specified) if (_braille_register_console(newcon, c)) return 0; - if (newcon->setup && - (err = newcon->setup(newcon, c->options)) != 0) + err = console_call_setup(newcon, c->options); + if (err) return err; } newcon->flags |= CON_ENABLED; @@ -2741,6 +2763,23 @@ static int try_enable_new_console(struct console *newcon, bool user_specified) return -ENOENT; } +/* Try to enable the console unconditionally */ +static void try_enable_default_console(struct console *newcon) +{ + if (newcon->index < 0) + newcon->index = 0; + + if (console_call_setup(newcon, NULL) != 0) + return; + + newcon->flags |= CON_ENABLED; + + if (newcon->device) { + newcon->flags |= CON_CONSDEV; + has_preferred_console = true; + } +} + /* * The console driver calls this routine during kernel initialization * to register the console printing procedure with printk() and to @@ -2797,25 +2836,15 @@ void register_console(struct console *newcon) * didn't select a console we take the first one * that registers here. */ - if (!has_preferred_console) { - if (newcon->index < 0) - newcon->index = 0; - if (newcon->setup == NULL || - newcon->setup(newcon, NULL) == 0) { - newcon->flags |= CON_ENABLED; - if (newcon->device) { - newcon->flags |= CON_CONSDEV; - has_preferred_console = true; - } - } - } + if (!has_preferred_console) + try_enable_default_console(newcon); /* See if this console matches one we selected on the command line */ - err = try_enable_new_console(newcon, true); + err = try_enable_preferred_console(newcon, true); /* If not, try to match against the platform default(s) */ if (err == -ENOENT) - err = try_enable_new_console(newcon, false); + err = try_enable_preferred_console(newcon, false); /* printk() messages are not printed to the Braille console. */ if (err || newcon->flags & CON_BRL) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index c5624ab05..105fdc2bb 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -1015,6 +1015,8 @@ static void rcu_tasks_trace_postscan(struct list_head *hop) // Wait for late-stage exiting tasks to finish exiting. // These might have passed the call to exit_tasks_rcu_finish(). + + // If you remove the following line, update rcu_trace_implies_rcu_gp()!!! synchronize_rcu(); // Any tasks that exit after this point will set ->trc_reader_checked. } diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index cc7cd512e..1b7c3bdba 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -34,6 +34,8 @@ | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK \ | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK) +static DEFINE_MUTEX(membarrier_ipi_mutex); + static void ipi_mb(void *info) { smp_mb(); /* IPIs should be serializing but paranoid. */ @@ -119,6 +121,7 @@ static int membarrier_global_expedited(void) if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) return -ENOMEM; + mutex_lock(&membarrier_ipi_mutex); cpus_read_lock(); rcu_read_lock(); for_each_online_cpu(cpu) { @@ -165,6 +168,8 @@ static int membarrier_global_expedited(void) * rq->curr modification in scheduler. */ smp_mb(); /* exit from system call is not a mb */ + mutex_unlock(&membarrier_ipi_mutex); + return 0; } @@ -208,6 +213,7 @@ static int membarrier_private_expedited(int flags, int cpu_id) if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) return -ENOMEM; + mutex_lock(&membarrier_ipi_mutex); cpus_read_lock(); if (cpu_id >= 0) { @@ -280,6 +286,7 @@ out: * rq->curr modification in scheduler. */ smp_mb(); /* exit from system call is not a mb */ + mutex_unlock(&membarrier_ipi_mutex); return 0; } @@ -321,6 +328,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm) * between threads which are users of @mm has its membarrier state * updated. */ + mutex_lock(&membarrier_ipi_mutex); cpus_read_lock(); rcu_read_lock(); for_each_online_cpu(cpu) { @@ -337,6 +345,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm) free_cpumask_var(tmpmask); cpus_read_unlock(); + mutex_unlock(&membarrier_ipi_mutex); return 0; } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index f690f901b..1289991c9 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -8,7 +8,7 @@ #include "pelt.h" int sched_rr_timeslice = RR_TIMESLICE; -int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; +int sysctl_sched_rr_timeslice = (MSEC_PER_SEC * RR_TIMESLICE) / HZ; /* More than 4 hours if BW_SHIFT equals 20. */ static const u64 max_rt_runtime = MAX_BW; @@ -2727,9 +2727,6 @@ static int sched_rt_global_constraints(void) static int sched_rt_global_validate(void) { - if (sysctl_sched_rt_period <= 0) - return -EINVAL; - if ((sysctl_sched_rt_runtime != RUNTIME_INF) && ((sysctl_sched_rt_runtime > sysctl_sched_rt_period) || ((u64)sysctl_sched_rt_runtime * @@ -2760,7 +2757,7 @@ int sched_rt_handler(struct ctl_table *table, int write, void *buffer, old_period = sysctl_sched_rt_period; old_runtime = sysctl_sched_rt_runtime; - ret = proc_dointvec(table, write, buffer, lenp, ppos); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!ret && write) { ret = sched_rt_global_validate(); @@ -2804,6 +2801,9 @@ int sched_rr_handler(struct ctl_table *table, int write, void *buffer, sched_rr_timeslice = sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE : msecs_to_jiffies(sysctl_sched_rr_timeslice); + + if (sysctl_sched_rr_timeslice <= 0) + sysctl_sched_rr_timeslice = jiffies_to_msecs(RR_TIMESLICE); } mutex_unlock(&mutex); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 305f0eca1..0b0331346 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -29,6 +29,9 @@ #include <linux/syscalls.h> #include <linux/sysctl.h> +/* Not exposed in headers: strictly internal use only. */ +#define SECCOMP_MODE_DEAD (SECCOMP_MODE_FILTER + 1) + #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER #include <asm/syscall.h> #endif @@ -795,6 +798,7 @@ static void __secure_computing_strict(int this_syscall) #ifdef SECCOMP_DEBUG dump_stack(); #endif + current->seccomp.mode = SECCOMP_MODE_DEAD; seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL_THREAD, true); do_exit(SIGKILL); } @@ -1023,6 +1027,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, case SECCOMP_RET_KILL_THREAD: case SECCOMP_RET_KILL_PROCESS: default: + current->seccomp.mode = SECCOMP_MODE_DEAD; seccomp_log(this_syscall, SIGSYS, action, true); /* Dump core only if this is the last remaining thread. */ if (action != SECCOMP_RET_KILL_THREAD || @@ -1075,6 +1080,11 @@ int __secure_computing(const struct seccomp_data *sd) return 0; case SECCOMP_MODE_FILTER: return __seccomp_filter(this_syscall, sd, false); + /* Surviving SECCOMP_RET_KILL_* must be proactively impossible. */ + case SECCOMP_MODE_DEAD: + WARN_ON_ONCE(1); + do_exit(SIGKILL); + return -1; default: BUG(); } diff --git a/kernel/sys.c b/kernel/sys.c index bff14910b..efc213ae4 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1736,74 +1736,87 @@ void getrusage(struct task_struct *p, int who, struct rusage *r) struct task_struct *t; unsigned long flags; u64 tgutime, tgstime, utime, stime; - unsigned long maxrss = 0; + unsigned long maxrss; + struct mm_struct *mm; + struct signal_struct *sig = p->signal; + unsigned int seq = 0; - memset((char *)r, 0, sizeof (*r)); +retry: + memset(r, 0, sizeof(*r)); utime = stime = 0; + maxrss = 0; if (who == RUSAGE_THREAD) { task_cputime_adjusted(current, &utime, &stime); accumulate_thread_rusage(p, r); - maxrss = p->signal->maxrss; - goto out; + maxrss = sig->maxrss; + goto out_thread; } - if (!lock_task_sighand(p, &flags)) - return; + flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); switch (who) { case RUSAGE_BOTH: case RUSAGE_CHILDREN: - utime = p->signal->cutime; - stime = p->signal->cstime; - r->ru_nvcsw = p->signal->cnvcsw; - r->ru_nivcsw = p->signal->cnivcsw; - r->ru_minflt = p->signal->cmin_flt; - r->ru_majflt = p->signal->cmaj_flt; - r->ru_inblock = p->signal->cinblock; - r->ru_oublock = p->signal->coublock; - maxrss = p->signal->cmaxrss; + utime = sig->cutime; + stime = sig->cstime; + r->ru_nvcsw = sig->cnvcsw; + r->ru_nivcsw = sig->cnivcsw; + r->ru_minflt = sig->cmin_flt; + r->ru_majflt = sig->cmaj_flt; + r->ru_inblock = sig->cinblock; + r->ru_oublock = sig->coublock; + maxrss = sig->cmaxrss; if (who == RUSAGE_CHILDREN) break; fallthrough; case RUSAGE_SELF: - thread_group_cputime_adjusted(p, &tgutime, &tgstime); - utime += tgutime; - stime += tgstime; - r->ru_nvcsw += p->signal->nvcsw; - r->ru_nivcsw += p->signal->nivcsw; - r->ru_minflt += p->signal->min_flt; - r->ru_majflt += p->signal->maj_flt; - r->ru_inblock += p->signal->inblock; - r->ru_oublock += p->signal->oublock; - if (maxrss < p->signal->maxrss) - maxrss = p->signal->maxrss; - t = p; - do { + r->ru_nvcsw += sig->nvcsw; + r->ru_nivcsw += sig->nivcsw; + r->ru_minflt += sig->min_flt; + r->ru_majflt += sig->maj_flt; + r->ru_inblock += sig->inblock; + r->ru_oublock += sig->oublock; + if (maxrss < sig->maxrss) + maxrss = sig->maxrss; + + rcu_read_lock(); + __for_each_thread(sig, t) accumulate_thread_rusage(t, r); - } while_each_thread(p, t); + rcu_read_unlock(); + break; default: BUG(); } - unlock_task_sighand(p, &flags); -out: - r->ru_utime = ns_to_kernel_old_timeval(utime); - r->ru_stime = ns_to_kernel_old_timeval(stime); + if (need_seqretry(&sig->stats_lock, seq)) { + seq = 1; + goto retry; + } + done_seqretry_irqrestore(&sig->stats_lock, seq, flags); - if (who != RUSAGE_CHILDREN) { - struct mm_struct *mm = get_task_mm(p); + if (who == RUSAGE_CHILDREN) + goto out_children; - if (mm) { - setmax_mm_hiwater_rss(&maxrss, mm); - mmput(mm); - } + thread_group_cputime_adjusted(p, &tgutime, &tgstime); + utime += tgutime; + stime += tgstime; + +out_thread: + mm = get_task_mm(p); + if (mm) { + setmax_mm_hiwater_rss(&maxrss, mm); + mmput(mm); } + +out_children: r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */ + r->ru_utime = ns_to_kernel_old_timeval(utime); + r->ru_stime = ns_to_kernel_old_timeval(stime); } SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index a45f0dd10..99a191901 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1859,6 +1859,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = sched_rt_handler, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_INT_MAX, }, { .procname = "sched_rt_runtime_us", @@ -1866,6 +1868,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = sched_rt_handler, + .extra1 = SYSCTL_NEG_ONE, + .extra2 = SYSCTL_INT_MAX, }, { .procname = "sched_deadline_period_max_us", diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 86e0fbe58..754e93edb 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -118,6 +118,7 @@ static DECLARE_WORK(watchdog_work, clocksource_watchdog_work); static DEFINE_SPINLOCK(watchdog_lock); static int watchdog_running; static atomic_t watchdog_reset_pending; +static int64_t watchdog_max_interval; static inline void clocksource_watchdog_lock(unsigned long *flags) { @@ -136,6 +137,7 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating); * Interval: 0.5sec. */ #define WATCHDOG_INTERVAL (HZ >> 1) +#define WATCHDOG_INTERVAL_MAX_NS ((2 * WATCHDOG_INTERVAL) * (NSEC_PER_SEC / HZ)) static void clocksource_watchdog_work(struct work_struct *work) { @@ -324,8 +326,8 @@ static inline void clocksource_reset_watchdog(void) static void clocksource_watchdog(struct timer_list *unused) { u64 csnow, wdnow, cslast, wdlast, delta; + int64_t wd_nsec, cs_nsec, interval; int next_cpu, reset_pending; - int64_t wd_nsec, cs_nsec; struct clocksource *cs; enum wd_read_status read_ret; unsigned long extra_wait = 0; @@ -395,6 +397,27 @@ static void clocksource_watchdog(struct timer_list *unused) if (atomic_read(&watchdog_reset_pending)) continue; + /* + * The processing of timer softirqs can get delayed (usually + * on account of ksoftirqd not getting to run in a timely + * manner), which causes the watchdog interval to stretch. + * Skew detection may fail for longer watchdog intervals + * on account of fixed margins being used. + * Some clocksources, e.g. acpi_pm, cannot tolerate + * watchdog intervals longer than a few seconds. + */ + interval = max(cs_nsec, wd_nsec); + if (unlikely(interval > WATCHDOG_INTERVAL_MAX_NS)) { + if (system_state > SYSTEM_SCHEDULING && + interval > 2 * watchdog_max_interval) { + watchdog_max_interval = interval; + pr_warn("Long readout interval, skipping watchdog check: cs_nsec: %lld wd_nsec: %lld\n", + cs_nsec, wd_nsec); + } + watchdog_timer.expires = jiffies; + continue; + } + /* Check the deviation from the watchdog clocksource. */ md = cs->uncertainty_margin + watchdog->uncertainty_margin; if (abs(cs_nsec - wd_nsec) > md) { diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index ede09dda3..2b2a6e292 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -980,6 +980,7 @@ static int enqueue_hrtimer(struct hrtimer *timer, enum hrtimer_mode mode) { debug_activate(timer, mode); + WARN_ON_ONCE(!base->cpu_base->online); base->cpu_base->active_bases |= 1 << base->index; @@ -2078,6 +2079,7 @@ int hrtimers_prepare_cpu(unsigned int cpu) cpu_base->softirq_next_timer = NULL; cpu_base->expires_next = KTIME_MAX; cpu_base->softirq_expires_next = KTIME_MAX; + cpu_base->online = 1; hrtimer_cpu_base_init_expiry_lock(cpu_base); return 0; } @@ -2145,6 +2147,7 @@ int hrtimers_cpu_dying(unsigned int dying_cpu) smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); raw_spin_unlock(&new_base->lock); + old_base->online = 0; raw_spin_unlock(&old_base->lock); return 0; @@ -2161,7 +2164,7 @@ void __init hrtimers_init(void) /** * schedule_hrtimeout_range_clock - sleep until timeout * @expires: timeout value (ktime_t) - * @delta: slack in expires timeout (ktime_t) + * @delta: slack in expires timeout (ktime_t) for SCHED_OTHER tasks * @mode: timer mode * @clock_id: timer clock to be used */ @@ -2188,6 +2191,13 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, return -EINTR; } + /* + * Override any slack passed by the user if under + * rt contraints. + */ + if (rt_task(current)) + delta = 0; + hrtimer_init_sleeper_on_stack(&t, clock_id, mode); hrtimer_set_expires_range_ns(&t.timer, *expires, delta); hrtimer_sleeper_start_expires(&t, mode); @@ -2207,7 +2217,7 @@ EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); /** * schedule_hrtimeout_range - sleep until timeout * @expires: timeout value (ktime_t) - * @delta: slack in expires timeout (ktime_t) + * @delta: slack in expires timeout (ktime_t) for SCHED_OTHER tasks * @mode: timer mode * * Make the current task sleep until the given expiry time has @@ -2215,7 +2225,8 @@ EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); * the current task state has been set (see set_current_state()). * * The @delta argument gives the kernel the freedom to schedule the - * actual wakeup to a time that is both power and performance friendly. + * actual wakeup to a time that is both power and performance friendly + * for regular (non RT/DL) tasks. * The kernel give the normal best effort behavior for "@expires+@delta", * but may decide to fire the timer earlier, but no earlier than @expires. * diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index bc00ab011..d1693c269 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -1440,6 +1440,7 @@ void tick_cancel_sched_timer(int cpu) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); ktime_t idle_sleeptime, iowait_sleeptime; + unsigned long idle_calls, idle_sleeps; # ifdef CONFIG_HIGH_RES_TIMERS if (ts->sched_timer.base) @@ -1448,9 +1449,13 @@ void tick_cancel_sched_timer(int cpu) idle_sleeptime = ts->idle_sleeptime; iowait_sleeptime = ts->iowait_sleeptime; + idle_calls = ts->idle_calls; + idle_sleeps = ts->idle_sleeps; memset(ts, 0, sizeof(*ts)); ts->idle_sleeptime = idle_sleeptime; ts->iowait_sleeptime = iowait_sleeptime; + ts->idle_calls = idle_calls; + ts->idle_sleeps = idle_sleeps; } #endif diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index d9b48f7a3..629a07e6a 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1167,13 +1167,15 @@ static int adjust_historical_crosststamp(struct system_time_snapshot *history, } /* - * cycle_between - true if test occurs chronologically between before and after + * timestamp_in_interval - true if ts is chronologically in [start, end] + * + * True if ts occurs chronologically at or after start, and before or at end. */ -static bool cycle_between(u64 before, u64 test, u64 after) +static bool timestamp_in_interval(u64 start, u64 end, u64 ts) { - if (test > before && test < after) + if (ts >= start && ts <= end) return true; - if (test < before && before > after) + if (start > end && (ts >= start || ts <= end)) return true; return false; } @@ -1233,7 +1235,7 @@ int get_device_system_crosststamp(int (*get_time_fn) */ now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; - if (!cycle_between(interval_start, cycles, now)) { + if (!timestamp_in_interval(interval_start, now, cycles)) { clock_was_set_seq = tk->clock_was_set_seq; cs_was_changed_seq = tk->cs_was_changed_seq; cycles = interval_start; @@ -1246,10 +1248,8 @@ int get_device_system_crosststamp(int (*get_time_fn) tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; - nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, - system_counterval.cycles); - nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, - system_counterval.cycles); + nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); + nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); @@ -1264,13 +1264,13 @@ int get_device_system_crosststamp(int (*get_time_fn) bool discontinuity; /* - * Check that the counter value occurs after the provided + * Check that the counter value is not before the provided * history reference and that the history doesn't cross a * clocksource change */ if (!history_begin || - !cycle_between(history_begin->cycles, - system_counterval.cycles, cycles) || + !timestamp_in_interval(history_begin->cycles, + cycles, system_counterval.cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; partial_history_cycles = cycles - system_counterval.cycles; diff --git a/kernel/time/timer.c b/kernel/time/timer.c index e87e638c3..c135cefa4 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1030,7 +1030,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option /* * We are trying to schedule the timer on the new base. * However we can't change timer's base while it is running, - * otherwise del_timer_sync() can't detect that the timer's + * otherwise timer_delete_sync() can't detect that the timer's * handler yet has not finished. This also guarantees that the * timer is serialized wrt itself. */ @@ -1068,14 +1068,16 @@ out_unlock: } /** - * mod_timer_pending - modify a pending timer's timeout - * @timer: the pending timer to be modified - * @expires: new timeout in jiffies + * mod_timer_pending - Modify a pending timer's timeout + * @timer: The pending timer to be modified + * @expires: New absolute timeout in jiffies * - * mod_timer_pending() is the same for pending timers as mod_timer(), - * but will not re-activate and modify already deleted timers. + * mod_timer_pending() is the same for pending timers as mod_timer(), but + * will not activate inactive timers. * - * It is useful for unserialized use of timers. + * Return: + * * %0 - The timer was inactive and not modified + * * %1 - The timer was active and requeued to expire at @expires */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { @@ -1084,24 +1086,27 @@ int mod_timer_pending(struct timer_list *timer, unsigned long expires) EXPORT_SYMBOL(mod_timer_pending); /** - * mod_timer - modify a timer's timeout - * @timer: the timer to be modified - * @expires: new timeout in jiffies - * - * mod_timer() is a more efficient way to update the expire field of an - * active timer (if the timer is inactive it will be activated) + * mod_timer - Modify a timer's timeout + * @timer: The timer to be modified + * @expires: New absolute timeout in jiffies * * mod_timer(timer, expires) is equivalent to: * * del_timer(timer); timer->expires = expires; add_timer(timer); * + * mod_timer() is more efficient than the above open coded sequence. In + * case that the timer is inactive, the del_timer() part is a NOP. The + * timer is in any case activated with the new expiry time @expires. + * * Note that if there are multiple unserialized concurrent users of the * same timer, then mod_timer() is the only safe way to modify the timeout, * since add_timer() cannot modify an already running timer. * - * The function returns whether it has modified a pending timer or not. - * (ie. mod_timer() of an inactive timer returns 0, mod_timer() of an - * active timer returns 1.) + * Return: + * * %0 - The timer was inactive and started + * * %1 - The timer was active and requeued to expire at @expires or + * the timer was active and not modified because @expires did + * not change the effective expiry time */ int mod_timer(struct timer_list *timer, unsigned long expires) { @@ -1112,11 +1117,18 @@ EXPORT_SYMBOL(mod_timer); /** * timer_reduce - Modify a timer's timeout if it would reduce the timeout * @timer: The timer to be modified - * @expires: New timeout in jiffies + * @expires: New absolute timeout in jiffies * * timer_reduce() is very similar to mod_timer(), except that it will only - * modify a running timer if that would reduce the expiration time (it will - * start a timer that isn't running). + * modify an enqueued timer if that would reduce the expiration time. If + * @timer is not enqueued it starts the timer. + * + * Return: + * * %0 - The timer was inactive and started + * * %1 - The timer was active and requeued to expire at @expires or + * the timer was active and not modified because @expires + * did not change the effective expiry time such that the + * timer would expire earlier than already scheduled */ int timer_reduce(struct timer_list *timer, unsigned long expires) { @@ -1125,18 +1137,21 @@ int timer_reduce(struct timer_list *timer, unsigned long expires) EXPORT_SYMBOL(timer_reduce); /** - * add_timer - start a timer - * @timer: the timer to be added + * add_timer - Start a timer + * @timer: The timer to be started * - * The kernel will do a ->function(@timer) callback from the - * timer interrupt at the ->expires point in the future. The - * current time is 'jiffies'. + * Start @timer to expire at @timer->expires in the future. @timer->expires + * is the absolute expiry time measured in 'jiffies'. When the timer expires + * timer->function(timer) will be invoked from soft interrupt context. * - * The timer's ->expires, ->function fields must be set prior calling this - * function. + * The @timer->expires and @timer->function fields must be set prior + * to calling this function. * - * Timers with an ->expires field in the past will be executed in the next - * timer tick. + * If @timer->expires is already in the past @timer will be queued to + * expire at the next timer tick. + * + * This can only operate on an inactive timer. Attempts to invoke this on + * an active timer are rejected with a warning. */ void add_timer(struct timer_list *timer) { @@ -1146,11 +1161,13 @@ void add_timer(struct timer_list *timer) EXPORT_SYMBOL(add_timer); /** - * add_timer_on - start a timer on a particular CPU - * @timer: the timer to be added - * @cpu: the CPU to start it on + * add_timer_on - Start a timer on a particular CPU + * @timer: The timer to be started + * @cpu: The CPU to start it on + * + * Same as add_timer() except that it starts the timer on the given CPU. * - * This is not very scalable on SMP. Double adds are not possible. + * See add_timer() for further details. */ void add_timer_on(struct timer_list *timer, int cpu) { @@ -1185,15 +1202,18 @@ void add_timer_on(struct timer_list *timer, int cpu) EXPORT_SYMBOL_GPL(add_timer_on); /** - * del_timer - deactivate a timer. - * @timer: the timer to be deactivated - * - * del_timer() deactivates a timer - this works on both active and inactive - * timers. - * - * The function returns whether it has deactivated a pending timer or not. - * (ie. del_timer() of an inactive timer returns 0, del_timer() of an - * active timer returns 1.) + * del_timer - Deactivate a timer. + * @timer: The timer to be deactivated + * + * The function only deactivates a pending timer, but contrary to + * timer_delete_sync() it does not take into account whether the timer's + * callback function is concurrently executed on a different CPU or not. + * It neither prevents rearming of the timer. If @timer can be rearmed + * concurrently then the return value of this function is meaningless. + * + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ int del_timer(struct timer_list *timer) { @@ -1215,10 +1235,19 @@ EXPORT_SYMBOL(del_timer); /** * try_to_del_timer_sync - Try to deactivate a timer - * @timer: timer to delete + * @timer: Timer to deactivate + * + * This function tries to deactivate a timer. On success the timer is not + * queued and the timer callback function is not running on any CPU. + * + * This function does not guarantee that the timer cannot be rearmed right + * after dropping the base lock. That needs to be prevented by the calling + * code if necessary. * - * This function tries to deactivate a timer. Upon successful (ret >= 0) - * exit the timer is not queued and the handler is not running on any CPU. + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated + * * %-1 - The timer callback function is running on a different CPU */ int try_to_del_timer_sync(struct timer_list *timer) { @@ -1312,25 +1341,20 @@ static inline void timer_sync_wait_running(struct timer_base *base) { } static inline void del_timer_wait_running(struct timer_list *timer) { } #endif -#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT) /** - * del_timer_sync - deactivate a timer and wait for the handler to finish. - * @timer: the timer to be deactivated - * - * This function only differs from del_timer() on SMP: besides deactivating - * the timer it also makes sure the handler has finished executing on other - * CPUs. + * timer_delete_sync - Deactivate a timer and wait for the handler to finish. + * @timer: The timer to be deactivated * * Synchronization rules: Callers must prevent restarting of the timer, * otherwise this function is meaningless. It must not be called from * interrupt contexts unless the timer is an irqsafe one. The caller must - * not hold locks which would prevent completion of the timer's - * handler. The timer's handler must not call add_timer_on(). Upon exit the - * timer is not queued and the handler is not running on any CPU. + * not hold locks which would prevent completion of the timer's callback + * function. The timer's handler must not call add_timer_on(). Upon exit + * the timer is not queued and the handler is not running on any CPU. * - * Note: For !irqsafe timers, you must not hold locks that are held in - * interrupt context while calling this function. Even if the lock has - * nothing to do with the timer in question. Here's why:: + * For !irqsafe timers, the caller must not hold locks that are held in + * interrupt context. Even if the lock has nothing to do with the timer in + * question. Here's why:: * * CPU0 CPU1 * ---- ---- @@ -1340,16 +1364,23 @@ static inline void del_timer_wait_running(struct timer_list *timer) { } * spin_lock_irq(somelock); * <IRQ> * spin_lock(somelock); - * del_timer_sync(mytimer); + * timer_delete_sync(mytimer); * while (base->running_timer == mytimer); * - * Now del_timer_sync() will never return and never release somelock. - * The interrupt on the other CPU is waiting to grab somelock but - * it has interrupted the softirq that CPU0 is waiting to finish. + * Now timer_delete_sync() will never return and never release somelock. + * The interrupt on the other CPU is waiting to grab somelock but it has + * interrupted the softirq that CPU0 is waiting to finish. + * + * This function cannot guarantee that the timer is not rearmed again by + * some concurrent or preempting code, right after it dropped the base + * lock. If there is the possibility of a concurrent rearm then the return + * value of the function is meaningless. * - * The function returns whether it has deactivated a pending timer or not. + * Return: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ -int del_timer_sync(struct timer_list *timer) +int timer_delete_sync(struct timer_list *timer) { int ret; @@ -1382,8 +1413,7 @@ int del_timer_sync(struct timer_list *timer) return ret; } -EXPORT_SYMBOL(del_timer_sync); -#endif +EXPORT_SYMBOL(timer_delete_sync); static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *), @@ -1405,8 +1435,8 @@ static void call_timer_fn(struct timer_list *timer, #endif /* * Couple the lock chain with the lock chain at - * del_timer_sync() by acquiring the lock_map around the fn() - * call here and in del_timer_sync(). + * timer_delete_sync() by acquiring the lock_map around the fn() + * call here and in timer_delete_sync(). */ lock_map_acquire(&lockdep_map); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 041b91c2b..2df8e13a2 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -415,7 +415,6 @@ struct rb_irq_work { struct irq_work work; wait_queue_head_t waiters; wait_queue_head_t full_waiters; - long wait_index; bool waiters_pending; bool full_waiters_pending; bool wakeup_full; @@ -832,8 +831,19 @@ static void rb_wake_up_waiters(struct irq_work *work) wake_up_all(&rbwork->waiters); if (rbwork->full_waiters_pending || rbwork->wakeup_full) { + /* Only cpu_buffer sets the above flags */ + struct ring_buffer_per_cpu *cpu_buffer = + container_of(rbwork, struct ring_buffer_per_cpu, irq_work); + + /* Called from interrupt context */ + raw_spin_lock(&cpu_buffer->reader_lock); rbwork->wakeup_full = false; rbwork->full_waiters_pending = false; + + /* Waking up all waiters, they will reset the shortest full */ + cpu_buffer->shortest_full = 0; + raw_spin_unlock(&cpu_buffer->reader_lock); + wake_up_all(&rbwork->full_waiters); } } @@ -862,14 +872,41 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) rbwork = &cpu_buffer->irq_work; } - rbwork->wait_index++; - /* make sure the waiters see the new index */ - smp_wmb(); - /* This can be called in any context */ irq_work_queue(&rbwork->work); } +static bool rb_watermark_hit(struct trace_buffer *buffer, int cpu, int full) +{ + struct ring_buffer_per_cpu *cpu_buffer; + bool ret = false; + + /* Reads of all CPUs always waits for any data */ + if (cpu == RING_BUFFER_ALL_CPUS) + return !ring_buffer_empty(buffer); + + cpu_buffer = buffer->buffers[cpu]; + + if (!ring_buffer_empty_cpu(buffer, cpu)) { + unsigned long flags; + bool pagebusy; + + if (!full) + return true; + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; + ret = !pagebusy && full_hit(buffer, cpu, full); + + if (!ret && (!cpu_buffer->shortest_full || + cpu_buffer->shortest_full > full)) { + cpu_buffer->shortest_full = full; + } + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + } + return ret; +} + /** * ring_buffer_wait - wait for input to the ring buffer * @buffer: buffer to wait on @@ -885,7 +922,6 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) struct ring_buffer_per_cpu *cpu_buffer; DEFINE_WAIT(wait); struct rb_irq_work *work; - long wait_index; int ret = 0; /* @@ -904,81 +940,54 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) work = &cpu_buffer->irq_work; } - wait_index = READ_ONCE(work->wait_index); - - while (true) { - if (full) - prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE); - else - prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE); - - /* - * The events can happen in critical sections where - * checking a work queue can cause deadlocks. - * After adding a task to the queue, this flag is set - * only to notify events to try to wake up the queue - * using irq_work. - * - * We don't clear it even if the buffer is no longer - * empty. The flag only causes the next event to run - * irq_work to do the work queue wake up. The worse - * that can happen if we race with !trace_empty() is that - * an event will cause an irq_work to try to wake up - * an empty queue. - * - * There's no reason to protect this flag either, as - * the work queue and irq_work logic will do the necessary - * synchronization for the wake ups. The only thing - * that is necessary is that the wake up happens after - * a task has been queued. It's OK for spurious wake ups. - */ - if (full) - work->full_waiters_pending = true; - else - work->waiters_pending = true; - - if (signal_pending(current)) { - ret = -EINTR; - break; - } - - if (cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) - break; - - if (cpu != RING_BUFFER_ALL_CPUS && - !ring_buffer_empty_cpu(buffer, cpu)) { - unsigned long flags; - bool pagebusy; - bool done; - - if (!full) - break; - - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); - pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; - done = !pagebusy && full_hit(buffer, cpu, full); + if (full) + prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE); + else + prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE); - if (!cpu_buffer->shortest_full || - cpu_buffer->shortest_full > full) - cpu_buffer->shortest_full = full; - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - if (done) - break; - } + /* + * The events can happen in critical sections where + * checking a work queue can cause deadlocks. + * After adding a task to the queue, this flag is set + * only to notify events to try to wake up the queue + * using irq_work. + * + * We don't clear it even if the buffer is no longer + * empty. The flag only causes the next event to run + * irq_work to do the work queue wake up. The worse + * that can happen if we race with !trace_empty() is that + * an event will cause an irq_work to try to wake up + * an empty queue. + * + * There's no reason to protect this flag either, as + * the work queue and irq_work logic will do the necessary + * synchronization for the wake ups. The only thing + * that is necessary is that the wake up happens after + * a task has been queued. It's OK for spurious wake ups. + */ + if (full) + work->full_waiters_pending = true; + else + work->waiters_pending = true; - schedule(); + if (rb_watermark_hit(buffer, cpu, full)) + goto out; - /* Make sure to see the new wait index */ - smp_rmb(); - if (wait_index != work->wait_index) - break; + if (signal_pending(current)) { + ret = -EINTR; + goto out; } + schedule(); + out: if (full) finish_wait(&work->full_waiters, &wait); else finish_wait(&work->waiters, &wait); + if (!ret && !rb_watermark_hit(buffer, cpu, full) && signal_pending(current)) + ret = -EINTR; + return ret; } @@ -1001,30 +1010,51 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table, int full) { struct ring_buffer_per_cpu *cpu_buffer; - struct rb_irq_work *work; + struct rb_irq_work *rbwork; if (cpu == RING_BUFFER_ALL_CPUS) { - work = &buffer->irq_work; + rbwork = &buffer->irq_work; full = 0; } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) - return -EINVAL; + return EPOLLERR; cpu_buffer = buffer->buffers[cpu]; - work = &cpu_buffer->irq_work; + rbwork = &cpu_buffer->irq_work; } if (full) { - poll_wait(filp, &work->full_waiters, poll_table); - work->full_waiters_pending = true; + unsigned long flags; + + poll_wait(filp, &rbwork->full_waiters, poll_table); + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); if (!cpu_buffer->shortest_full || cpu_buffer->shortest_full > full) cpu_buffer->shortest_full = full; - } else { - poll_wait(filp, &work->waiters, poll_table); - work->waiters_pending = true; + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + if (full_hit(buffer, cpu, full)) + return EPOLLIN | EPOLLRDNORM; + /* + * Only allow full_waiters_pending update to be seen after + * the shortest_full is set. If the writer sees the + * full_waiters_pending flag set, it will compare the + * amount in the ring buffer to shortest_full. If the amount + * in the ring buffer is greater than the shortest_full + * percent, it will call the irq_work handler to wake up + * this list. The irq_handler will reset shortest_full + * back to zero. That's done under the reader_lock, but + * the below smp_mb() makes sure that the update to + * full_waiters_pending doesn't leak up into the above. + */ + smp_mb(); + rbwork->full_waiters_pending = true; + return 0; } + poll_wait(filp, &rbwork->waiters, poll_table); + rbwork->waiters_pending = true; + /* * There's a tight race between setting the waiters_pending and * checking if the ring buffer is empty. Once the waiters_pending bit @@ -1040,9 +1070,6 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, */ smp_mb(); - if (full) - return full_hit(buffer, cpu, full) ? EPOLLIN | EPOLLRDNORM : 0; - if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) return EPOLLIN | EPOLLRDNORM; @@ -4184,7 +4211,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter) cpu_buffer = iter->cpu_buffer; reader = cpu_buffer->reader_page; head_page = cpu_buffer->head_page; - commit_page = cpu_buffer->commit_page; + commit_page = READ_ONCE(cpu_buffer->commit_page); commit_ts = commit_page->page->time_stamp; /* diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 548f694fc..22e1e5711 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -39,6 +39,7 @@ #include <linux/slab.h> #include <linux/ctype.h> #include <linux/init.h> +#include <linux/kmemleak.h> #include <linux/poll.h> #include <linux/nmi.h> #include <linux/fs.h> @@ -2239,7 +2240,7 @@ struct saved_cmdlines_buffer { unsigned *map_cmdline_to_pid; unsigned cmdline_num; int cmdline_idx; - char *saved_cmdlines; + char saved_cmdlines[]; }; static struct saved_cmdlines_buffer *savedcmd; @@ -2253,47 +2254,60 @@ static inline void set_cmdline(int idx, const char *cmdline) strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN); } -static int allocate_cmdlines_buffer(unsigned int val, - struct saved_cmdlines_buffer *s) +static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) { + int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN); + + kfree(s->map_cmdline_to_pid); + kmemleak_free(s); + free_pages((unsigned long)s, order); +} + +static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val) +{ + struct saved_cmdlines_buffer *s; + struct page *page; + int orig_size, size; + int order; + + /* Figure out how much is needed to hold the given number of cmdlines */ + orig_size = sizeof(*s) + val * TASK_COMM_LEN; + order = get_order(orig_size); + size = 1 << (order + PAGE_SHIFT); + page = alloc_pages(GFP_KERNEL, order); + if (!page) + return NULL; + + s = page_address(page); + kmemleak_alloc(s, size, 1, GFP_KERNEL); + memset(s, 0, sizeof(*s)); + + /* Round up to actual allocation */ + val = (size - sizeof(*s)) / TASK_COMM_LEN; + s->cmdline_num = val; + s->map_cmdline_to_pid = kmalloc_array(val, sizeof(*s->map_cmdline_to_pid), GFP_KERNEL); - if (!s->map_cmdline_to_pid) - return -ENOMEM; - - s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL); - if (!s->saved_cmdlines) { - kfree(s->map_cmdline_to_pid); - return -ENOMEM; + if (!s->map_cmdline_to_pid) { + free_saved_cmdlines_buffer(s); + return NULL; } s->cmdline_idx = 0; - s->cmdline_num = val; memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP, sizeof(s->map_pid_to_cmdline)); memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP, val * sizeof(*s->map_cmdline_to_pid)); - return 0; + return s; } static int trace_create_savedcmd(void) { - int ret; - - savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL); - if (!savedcmd) - return -ENOMEM; + savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT); - ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd); - if (ret < 0) { - kfree(savedcmd); - savedcmd = NULL; - return -ENOMEM; - } - - return 0; + return savedcmd ? 0 : -ENOMEM; } int is_tracing_stopped(void) @@ -5603,26 +5617,14 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf, return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } -static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) -{ - kfree(s->saved_cmdlines); - kfree(s->map_cmdline_to_pid); - kfree(s); -} - static int tracing_resize_saved_cmdlines(unsigned int val) { struct saved_cmdlines_buffer *s, *savedcmd_temp; - s = kmalloc(sizeof(*s), GFP_KERNEL); + s = allocate_cmdlines_buffer(val); if (!s) return -ENOMEM; - if (allocate_cmdlines_buffer(val, s) < 0) { - kfree(s); - return -ENOMEM; - } - preempt_disable(); arch_spin_lock(&trace_cmdline_lock); savedcmd_temp = savedcmd; diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 643e0b199..eb81ad523 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -400,7 +400,8 @@ void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp) BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long)); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, - "perf buffer not large enough")) + "perf buffer not large enough, wanted %d, have %d", + size, PERF_MAX_TRACE_SIZE)) return NULL; *rctxp = rctx = perf_swevent_get_recursion_context(); diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 51a9d1185..d47641f97 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -574,7 +574,12 @@ __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only) } memcpy(elt->key, key, map->key_size); - entry->val = elt; + /* + * Ensure the initialization is visible and + * publish the elt. + */ + smp_wmb(); + WRITE_ONCE(entry->val, elt); atomic64_inc(&map->hits); return entry->val; diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 4dd9283f6..b055741a5 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -612,9 +612,8 @@ static void debug_objects_fill_pool(void) static void __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack) { - enum debug_obj_state state; + struct debug_obj *obj, o; struct debug_bucket *db; - struct debug_obj *obj; unsigned long flags; debug_objects_fill_pool(); @@ -635,24 +634,18 @@ __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack case ODEBUG_STATE_INIT: case ODEBUG_STATE_INACTIVE: obj->state = ODEBUG_STATE_INIT; - break; - - case ODEBUG_STATE_ACTIVE: - state = obj->state; - raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "init"); - debug_object_fixup(descr->fixup_init, addr, state); - return; - - case ODEBUG_STATE_DESTROYED: raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "init"); return; default: break; } + o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(&o, "init"); + + if (o.state == ODEBUG_STATE_ACTIVE) + debug_object_fixup(descr->fixup_init, addr, o.state); } /** @@ -693,11 +686,9 @@ EXPORT_SYMBOL_GPL(debug_object_init_on_stack); int debug_object_activate(void *addr, const struct debug_obj_descr *descr) { struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; - enum debug_obj_state state; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; - int ret; if (!debug_objects_enabled) return 0; @@ -709,49 +700,38 @@ int debug_object_activate(void *addr, const struct debug_obj_descr *descr) raw_spin_lock_irqsave(&db->lock, flags); obj = lookup_object_or_alloc(addr, db, descr, false, true); - if (likely(!IS_ERR_OR_NULL(obj))) { - bool print_object = false; - + if (unlikely(!obj)) { + raw_spin_unlock_irqrestore(&db->lock, flags); + debug_objects_oom(); + return 0; + } else if (likely(!IS_ERR(obj))) { switch (obj->state) { - case ODEBUG_STATE_INIT: - case ODEBUG_STATE_INACTIVE: - obj->state = ODEBUG_STATE_ACTIVE; - ret = 0; - break; - case ODEBUG_STATE_ACTIVE: - state = obj->state; - raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "activate"); - ret = debug_object_fixup(descr->fixup_activate, addr, state); - return ret ? 0 : -EINVAL; - case ODEBUG_STATE_DESTROYED: - print_object = true; - ret = -EINVAL; + o = *obj; break; + case ODEBUG_STATE_INIT: + case ODEBUG_STATE_INACTIVE: + obj->state = ODEBUG_STATE_ACTIVE; + fallthrough; default: - ret = 0; - break; + raw_spin_unlock_irqrestore(&db->lock, flags); + return 0; } - raw_spin_unlock_irqrestore(&db->lock, flags); - if (print_object) - debug_print_object(obj, "activate"); - return ret; } raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(&o, "activate"); - /* If NULL the allocation has hit OOM */ - if (!obj) { - debug_objects_oom(); - return 0; + switch (o.state) { + case ODEBUG_STATE_ACTIVE: + case ODEBUG_STATE_NOTAVAILABLE: + if (debug_object_fixup(descr->fixup_activate, addr, o.state)) + return 0; + fallthrough; + default: + return -EINVAL; } - - /* Object is neither static nor tracked. It's not initialized */ - debug_print_object(&o, "activate"); - ret = debug_object_fixup(descr->fixup_activate, addr, ODEBUG_STATE_NOTAVAILABLE); - return ret ? 0 : -EINVAL; } EXPORT_SYMBOL_GPL(debug_object_activate); @@ -762,10 +742,10 @@ EXPORT_SYMBOL_GPL(debug_object_activate); */ void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr) { + struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; - bool print_object = false; if (!debug_objects_enabled) return; @@ -777,33 +757,24 @@ void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr) obj = lookup_object(addr, db); if (obj) { switch (obj->state) { + case ODEBUG_STATE_DESTROYED: + break; case ODEBUG_STATE_INIT: case ODEBUG_STATE_INACTIVE: case ODEBUG_STATE_ACTIVE: - if (!obj->astate) - obj->state = ODEBUG_STATE_INACTIVE; - else - print_object = true; - break; - - case ODEBUG_STATE_DESTROYED: - print_object = true; - break; + if (obj->astate) + break; + obj->state = ODEBUG_STATE_INACTIVE; + fallthrough; default: - break; + raw_spin_unlock_irqrestore(&db->lock, flags); + return; } + o = *obj; } raw_spin_unlock_irqrestore(&db->lock, flags); - if (!obj) { - struct debug_obj o = { .object = addr, - .state = ODEBUG_STATE_NOTAVAILABLE, - .descr = descr }; - - debug_print_object(&o, "deactivate"); - } else if (print_object) { - debug_print_object(obj, "deactivate"); - } + debug_print_object(&o, "deactivate"); } EXPORT_SYMBOL_GPL(debug_object_deactivate); @@ -814,11 +785,9 @@ EXPORT_SYMBOL_GPL(debug_object_deactivate); */ void debug_object_destroy(void *addr, const struct debug_obj_descr *descr) { - enum debug_obj_state state; + struct debug_obj *obj, o; struct debug_bucket *db; - struct debug_obj *obj; unsigned long flags; - bool print_object = false; if (!debug_objects_enabled) return; @@ -828,32 +797,31 @@ void debug_object_destroy(void *addr, const struct debug_obj_descr *descr) raw_spin_lock_irqsave(&db->lock, flags); obj = lookup_object(addr, db); - if (!obj) - goto out_unlock; + if (!obj) { + raw_spin_unlock_irqrestore(&db->lock, flags); + return; + } switch (obj->state) { + case ODEBUG_STATE_ACTIVE: + case ODEBUG_STATE_DESTROYED: + break; case ODEBUG_STATE_NONE: case ODEBUG_STATE_INIT: case ODEBUG_STATE_INACTIVE: obj->state = ODEBUG_STATE_DESTROYED; - break; - case ODEBUG_STATE_ACTIVE: - state = obj->state; + fallthrough; + default: raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "destroy"); - debug_object_fixup(descr->fixup_destroy, addr, state); return; - - case ODEBUG_STATE_DESTROYED: - print_object = true; - break; - default: - break; } -out_unlock: + + o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); - if (print_object) - debug_print_object(obj, "destroy"); + debug_print_object(&o, "destroy"); + + if (o.state == ODEBUG_STATE_ACTIVE) + debug_object_fixup(descr->fixup_destroy, addr, o.state); } EXPORT_SYMBOL_GPL(debug_object_destroy); @@ -864,9 +832,8 @@ EXPORT_SYMBOL_GPL(debug_object_destroy); */ void debug_object_free(void *addr, const struct debug_obj_descr *descr) { - enum debug_obj_state state; + struct debug_obj *obj, o; struct debug_bucket *db; - struct debug_obj *obj; unsigned long flags; if (!debug_objects_enabled) @@ -877,24 +844,26 @@ void debug_object_free(void *addr, const struct debug_obj_descr *descr) raw_spin_lock_irqsave(&db->lock, flags); obj = lookup_object(addr, db); - if (!obj) - goto out_unlock; + if (!obj) { + raw_spin_unlock_irqrestore(&db->lock, flags); + return; + } switch (obj->state) { case ODEBUG_STATE_ACTIVE: - state = obj->state; - raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "free"); - debug_object_fixup(descr->fixup_free, addr, state); - return; + break; default: hlist_del(&obj->node); raw_spin_unlock_irqrestore(&db->lock, flags); free_object(obj); return; } -out_unlock: + + o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(&o, "free"); + + debug_object_fixup(descr->fixup_free, addr, o.state); } EXPORT_SYMBOL_GPL(debug_object_free); @@ -946,10 +915,10 @@ void debug_object_active_state(void *addr, const struct debug_obj_descr *descr, unsigned int expect, unsigned int next) { + struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; - bool print_object = false; if (!debug_objects_enabled) return; @@ -962,28 +931,19 @@ debug_object_active_state(void *addr, const struct debug_obj_descr *descr, if (obj) { switch (obj->state) { case ODEBUG_STATE_ACTIVE: - if (obj->astate == expect) - obj->astate = next; - else - print_object = true; - break; - + if (obj->astate != expect) + break; + obj->astate = next; + raw_spin_unlock_irqrestore(&db->lock, flags); + return; default: - print_object = true; break; } + o = *obj; } raw_spin_unlock_irqrestore(&db->lock, flags); - if (!obj) { - struct debug_obj o = { .object = addr, - .state = ODEBUG_STATE_NOTAVAILABLE, - .descr = descr }; - - debug_print_object(&o, "active_state"); - } else if (print_object) { - debug_print_object(obj, "active_state"); - } + debug_print_object(&o, "active_state"); } EXPORT_SYMBOL_GPL(debug_object_active_state); @@ -991,12 +951,10 @@ EXPORT_SYMBOL_GPL(debug_object_active_state); static void __debug_check_no_obj_freed(const void *address, unsigned long size) { unsigned long flags, oaddr, saddr, eaddr, paddr, chunks; - const struct debug_obj_descr *descr; - enum debug_obj_state state; + int cnt, objs_checked = 0; + struct debug_obj *obj, o; struct debug_bucket *db; struct hlist_node *tmp; - struct debug_obj *obj; - int cnt, objs_checked = 0; saddr = (unsigned long) address; eaddr = saddr + size; @@ -1018,12 +976,10 @@ repeat: switch (obj->state) { case ODEBUG_STATE_ACTIVE: - descr = obj->descr; - state = obj->state; + o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "free"); - debug_object_fixup(descr->fixup_free, - (void *) oaddr, state); + debug_print_object(&o, "free"); + debug_object_fixup(o.descr->fixup_free, (void *)oaddr, o.state); goto repeat; default: hlist_del(&obj->node); diff --git a/lib/mpi/ec.c b/lib/mpi/ec.c index c21470122..941ba0b00 100644 --- a/lib/mpi/ec.c +++ b/lib/mpi/ec.c @@ -584,6 +584,9 @@ void mpi_ec_init(struct mpi_ec_ctx *ctx, enum gcry_mpi_ec_models model, ctx->a = mpi_copy(a); ctx->b = mpi_copy(b); + ctx->d = NULL; + ctx->t.two_inv_p = NULL; + ctx->t.p_barrett = use_barrett > 0 ? mpi_barrett_init(ctx->p, 0) : NULL; mpi_ec_get_reset(ctx); diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 25bbac466..308a7c851 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -271,10 +271,10 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, /* * Zero out zone modifiers, as we don't have specific zone * requirements. Keep the flags related to allocation in atomic - * contexts and I/O. + * contexts, I/O, nolockdep. */ alloc_flags &= ~GFP_ZONEMASK; - alloc_flags &= (GFP_ATOMIC | GFP_KERNEL); + alloc_flags &= (GFP_ATOMIC | GFP_KERNEL | __GFP_NOLOCKDEP); alloc_flags |= __GFP_NOWARN; page = alloc_pages(alloc_flags, STACK_ALLOC_ORDER); if (page) diff --git a/lib/test_blackhole_dev.c b/lib/test_blackhole_dev.c index 4c40580a9..f247089d6 100644 --- a/lib/test_blackhole_dev.c +++ b/lib/test_blackhole_dev.c @@ -29,7 +29,6 @@ static int __init test_blackholedev_init(void) { struct ipv6hdr *ip6h; struct sk_buff *skb; - struct ethhdr *ethh; struct udphdr *uh; int data_len; int ret; @@ -61,7 +60,7 @@ static int __init test_blackholedev_init(void) ip6h->saddr = in6addr_loopback; ip6h->daddr = in6addr_loopback; /* Ether */ - ethh = (struct ethhdr *)skb_push(skb, sizeof(struct ethhdr)); + skb_push(skb, sizeof(struct ethhdr)); skb_set_mac_header(skb, 0); skb->protocol = htons(ETH_P_IPV6); diff --git a/mm/compaction.c b/mm/compaction.c index b58021666..77ca5e6f4 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2466,16 +2466,11 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, enum compact_priority prio, struct page **capture) { - int may_perform_io = gfp_mask & __GFP_IO; struct zoneref *z; struct zone *zone; enum compact_result rc = COMPACT_SKIPPED; - /* - * Check if the GFP flags allow compaction - GFP_NOIO is really - * tricky context because the migration might require IO - */ - if (!may_perform_io) + if (!gfp_compaction_allowed(gfp_mask)) return COMPACT_SKIPPED; trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 81949f6d2..02b7c8f9b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5108,12 +5108,13 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, return pages << h->order; } -int hugetlb_reserve_pages(struct inode *inode, +/* Return true if reservation was successful, false otherwise. */ +bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags) { - long ret, chg, add = -1; + long chg, add = -1; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; @@ -5123,7 +5124,7 @@ int hugetlb_reserve_pages(struct inode *inode, /* This should never happen */ if (from > to) { VM_WARN(1, "%s called with a negative range\n", __func__); - return -EINVAL; + return false; } /* @@ -5132,7 +5133,7 @@ int hugetlb_reserve_pages(struct inode *inode, * without using reserves */ if (vm_flags & VM_NORESERVE) - return 0; + return true; /* * Shared mappings base their reservation on the number of pages that @@ -5154,7 +5155,7 @@ int hugetlb_reserve_pages(struct inode *inode, /* Private mapping. */ resv_map = resv_map_alloc(); if (!resv_map) - return -ENOMEM; + return false; chg = to - from; @@ -5162,18 +5163,12 @@ int hugetlb_reserve_pages(struct inode *inode, set_vma_resv_flags(vma, HPAGE_RESV_OWNER); } - if (chg < 0) { - ret = chg; + if (chg < 0) goto out_err; - } - - ret = hugetlb_cgroup_charge_cgroup_rsvd( - hstate_index(h), chg * pages_per_huge_page(h), &h_cg); - if (ret < 0) { - ret = -ENOMEM; + if (hugetlb_cgroup_charge_cgroup_rsvd(hstate_index(h), + chg * pages_per_huge_page(h), &h_cg) < 0) goto out_err; - } if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) { /* For private mappings, the hugetlb_cgroup uncharge info hangs @@ -5188,19 +5183,15 @@ int hugetlb_reserve_pages(struct inode *inode, * reservations already in place (gbl_reserve). */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); - if (gbl_reserve < 0) { - ret = -ENOSPC; + if (gbl_reserve < 0) goto out_uncharge_cgroup; - } /* * Check enough hugepages are available for the reservation. * Hand the pages back to the subpool if there are not */ - ret = hugetlb_acct_memory(h, gbl_reserve); - if (ret < 0) { + if (hugetlb_acct_memory(h, gbl_reserve) < 0) goto out_put_pages; - } /* * Account for the reservations made. Shared mappings record regions @@ -5218,7 +5209,6 @@ int hugetlb_reserve_pages(struct inode *inode, if (unlikely(add < 0)) { hugetlb_acct_memory(h, -gbl_reserve); - ret = add; goto out_put_pages; } else if (unlikely(chg > add)) { /* @@ -5251,7 +5241,8 @@ int hugetlb_reserve_pages(struct inode *inode, hugetlb_cgroup_put_rsvd_cgroup(h_cg); } } - return 0; + return true; + out_put_pages: /* put back original number of pages, chg */ (void)hugepage_subpool_put_pages(spool, chg); @@ -5267,7 +5258,7 @@ out_err: region_abort(resv_map, from, to, regions_needed); if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) kref_put(&resv_map->refs, resv_map_release); - return ret; + return false; } long hugetlb_unreserve_pages(struct inode *inode, long start, long end, diff --git a/mm/memory-failure.c b/mm/memory-failure.c index f320ff02c..dba293629 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1075,7 +1075,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, unmap_success = false; } } else { - unmap_success = try_to_unmap(p, ttu); + unmap_success = try_to_unmap(hpage, ttu); } } if (!unmap_success) diff --git a/mm/memory.c b/mm/memory.c index 1d101aeae..218300368 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4934,6 +4934,10 @@ int follow_phys(struct vm_area_struct *vma, goto out; pte = *ptep; + /* Never return PFNs of anon folios in COW mappings. */ + if (vm_normal_page(vma, address, pte)) + goto unlock; + if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; diff --git a/mm/memtest.c b/mm/memtest.c index f53ace709..d407373f2 100644 --- a/mm/memtest.c +++ b/mm/memtest.c @@ -46,10 +46,10 @@ static void __init memtest(u64 pattern, phys_addr_t start_phys, phys_addr_t size last_bad = 0; for (p = start; p < end; p++) - *p = pattern; + WRITE_ONCE(*p, pattern); for (p = start; p < end; p++, start_phys_aligned += incr) { - if (*p == pattern) + if (READ_ONCE(*p) == pattern) continue; if (start_phys_aligned == last_bad + incr) { last_bad += incr; diff --git a/mm/migrate.c b/mm/migrate.c index fcb7eb6a6..c0a8f3c9e 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -447,8 +447,12 @@ int migrate_page_move_mapping(struct address_space *mapping, if (PageSwapBacked(page)) { __SetPageSwapBacked(newpage); if (PageSwapCache(page)) { + int i; + SetPageSwapCache(newpage); - set_page_private(newpage, page_private(page)); + for (i = 0; i < (1 << compound_order(page)); i++) + set_page_private(newpage + i, + page_private(page + i)); } } else { VM_BUG_ON_PAGE(PageSwapCache(page), page); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index eb34d204d..e8d7d3c2b 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1524,7 +1524,7 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) */ dtc->wb_thresh = __wb_calc_thresh(dtc); dtc->wb_bg_thresh = dtc->thresh ? - div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; + div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 124ab9324..ed6660104 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4644,6 +4644,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct alloc_context *ac) { bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM; + bool can_compact = gfp_compaction_allowed(gfp_mask); const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER; struct page *page = NULL; unsigned int alloc_flags; @@ -4709,7 +4710,7 @@ restart: * Don't try this for allocations that are allowed to ignore * watermarks, as the ALLOC_NO_WATERMARKS attempt didn't yet happen. */ - if (can_direct_reclaim && + if (can_direct_reclaim && can_compact && (costly_order || (order > 0 && ac->migratetype != MIGRATE_MOVABLE)) && !gfp_pfmemalloc_allowed(gfp_mask)) { @@ -4806,9 +4807,10 @@ retry: /* * Do not retry costly high order allocations unless they are - * __GFP_RETRY_MAYFAIL + * __GFP_RETRY_MAYFAIL and we can compact */ - if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL)) + if (costly_order && (!can_compact || + !(gfp_mask & __GFP_RETRY_MAYFAIL))) goto nopage; if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags, @@ -4821,7 +4823,7 @@ retry: * implementation of the compaction depends on the sufficient amount * of free memory (see __compaction_suitable) */ - if (did_some_progress > 0 && + if (did_some_progress > 0 && can_compact && should_compact_retry(ac, order, alloc_flags, compact_result, &compact_priority, &compaction_retries)) diff --git a/mm/sparse.c b/mm/sparse.c index 33406ea2e..db0a7c537 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -810,6 +810,13 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages, unsigned long section_nr = pfn_to_section_nr(pfn); /* + * Mark the section invalid so that valid_section() + * return false. This prevents code from dereferencing + * ms->usage array. + */ + ms->section_mem_map &= ~SECTION_HAS_MEM_MAP; + + /* * When removing an early section, the usage map is kept (as the * usage maps of other sections fall into the same page). It * will be re-used when re-adding the section - which is then no @@ -817,16 +824,10 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages, * was allocated during boot. */ if (!PageReserved(virt_to_page(ms->usage))) { - kfree(ms->usage); - ms->usage = NULL; + kfree_rcu(ms->usage, rcu); + WRITE_ONCE(ms->usage, NULL); } memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); - /* - * Mark the section invalid so that valid_section() - * return false. This prevents code from dereferencing - * ms->usage array. - */ - ms->section_mem_map &= ~SECTION_HAS_MEM_MAP; } /* diff --git a/mm/swapfile.c b/mm/swapfile.c index 86ade667a..4ca1d04d8 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1271,6 +1271,11 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, } /* + * Note that when only holding the PTL, swapoff might succeed immediately + * after freeing a swap entry. Therefore, immediately after + * __swap_entry_free(), the swap info might become stale and should not + * be touched without a prior get_swap_device(). + * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until @@ -1797,13 +1802,19 @@ int free_swap_and_cache(swp_entry_t entry) if (non_swap_entry(entry)) return 1; - p = _swap_info_get(entry); + p = get_swap_device(entry); if (p) { + if (WARN_ON(data_race(!p->swap_map[swp_offset(entry)]))) { + put_swap_device(p); + return 0; + } + count = __swap_entry_free(p, entry); if (count == SWAP_HAS_CACHE && !swap_page_trans_huge_swapped(p, entry)) __try_to_reclaim_swap(p, swp_offset(entry), TTRS_UNMAPPED | TTRS_FULL); + put_swap_device(p); } return p != NULL; } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 078d95cd3..c28ff36f5 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -209,6 +209,7 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, + bool *mmap_changing, bool zeropage) { int vm_alloc_shared = dst_vma->vm_flags & VM_SHARED; @@ -329,6 +330,15 @@ retry: goto out; } mmap_read_lock(dst_mm); + /* + * If memory mappings are changing because of non-cooperative + * operation (e.g. mremap) running in parallel, bail out and + * request the user to retry later + */ + if (mmap_changing && READ_ONCE(*mmap_changing)) { + err = -EAGAIN; + break; + } dst_vma = NULL; goto retry; @@ -410,6 +420,7 @@ extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, + bool *mmap_changing, bool zeropage); #endif /* CONFIG_HUGETLB_PAGE */ @@ -529,7 +540,8 @@ retry: */ if (is_vm_hugetlb_page(dst_vma)) return __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start, - src_start, len, zeropage); + src_start, len, mmap_changing, + zeropage); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; @@ -686,6 +686,56 @@ static inline void *__page_rmapping(struct page *page) return (void *)mapping; } +/** + * __vmalloc_array - allocate memory for a virtually contiguous array. + * @n: number of elements. + * @size: element size. + * @flags: the type of memory to allocate (see kmalloc). + */ +void *__vmalloc_array(size_t n, size_t size, gfp_t flags) +{ + size_t bytes; + + if (unlikely(check_mul_overflow(n, size, &bytes))) + return NULL; + return __vmalloc(bytes, flags); +} +EXPORT_SYMBOL(__vmalloc_array); + +/** + * vmalloc_array - allocate memory for a virtually contiguous array. + * @n: number of elements. + * @size: element size. + */ +void *vmalloc_array(size_t n, size_t size) +{ + return __vmalloc_array(n, size, GFP_KERNEL); +} +EXPORT_SYMBOL(vmalloc_array); + +/** + * __vcalloc - allocate and zero memory for a virtually contiguous array. + * @n: number of elements. + * @size: element size. + * @flags: the type of memory to allocate (see kmalloc). + */ +void *__vcalloc(size_t n, size_t size, gfp_t flags) +{ + return __vmalloc_array(n, size, flags | __GFP_ZERO); +} +EXPORT_SYMBOL(__vcalloc); + +/** + * vcalloc - allocate and zero memory for a virtually contiguous array. + * @n: number of elements. + * @size: element size. + */ +void *vcalloc(size_t n, size_t size) +{ + return __vmalloc_array(n, size, GFP_KERNEL | __GFP_ZERO); +} +EXPORT_SYMBOL(vcalloc); + /* Neutral page->mapping pointer to address_space or anon_vma or other */ void *page_rmapping(struct page *page) { diff --git a/mm/vmscan.c b/mm/vmscan.c index 51ccd80e7..e2b8cee1d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2546,7 +2546,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) /* Use reclaim/compaction for costly allocs or under memory pressure */ static bool in_reclaim_compaction(struct scan_control *sc) { - if (IS_ENABLED(CONFIG_COMPACTION) && sc->order && + if (gfp_compaction_allowed(sc->gfp_mask) && sc->order && (sc->order > PAGE_ALLOC_COSTLY_ORDER || sc->priority < DEF_PRIORITY - 2)) return true; @@ -2873,6 +2873,9 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) unsigned long watermark; enum compact_result suitable; + if (!gfp_compaction_allowed(sc->gfp_mask)) + return false; + suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx); if (suitable == COMPACT_SUCCESS) /* Allocation should succeed already. Don't reclaim. */ diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 0db85aeb1..99b277775 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -118,12 +118,16 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[], } if (data[IFLA_VLAN_INGRESS_QOS]) { nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) { + if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING) + continue; m = nla_data(attr); vlan_dev_set_ingress_priority(dev, m->to, m->from); } } if (data[IFLA_VLAN_EGRESS_QOS]) { nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) { + if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING) + continue; m = nla_data(attr); err = vlan_dev_set_egress_priority(dev, m->from, m->to); if (err) diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 9e8ebac9b..f5019f698 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -4188,7 +4188,7 @@ void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface) spin_lock_bh(&bat_priv->tt.commit_lock); - while (true) { + while (timeout) { table_size = batadv_tt_local_table_transmit_size(bat_priv); if (packet_size_max >= table_size) break; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index e33fe4b1c..b9cf5bc93 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2175,7 +2175,7 @@ int hci_get_dev_info(void __user *arg) else flags = hdev->flags; - strcpy(di.name, hdev->name); + strscpy(di.name, hdev->name, sizeof(di.name)); di.bdaddr = hdev->bdaddr; di.type = (hdev->bus & 0x0f) | ((hdev->dev_type & 0x03) << 4); di.flags = flags; @@ -2318,6 +2318,7 @@ static void hci_error_reset(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, error_reset); + hci_dev_hold(hdev); BT_DBG("%s", hdev->name); if (hdev->hw_error) @@ -2325,10 +2326,10 @@ static void hci_error_reset(struct work_struct *work) else bt_dev_err(hdev, "hardware error 0x%2.2x", hdev->hw_error_code); - if (hci_dev_do_close(hdev)) - return; + if (!hci_dev_do_close(hdev)) + hci_dev_do_open(hdev); - hci_dev_do_open(hdev); + hci_dev_put(hdev); } void hci_uuids_clear(struct hci_dev *hdev) diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index d4efc4aa5..131bb56bf 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -216,10 +216,12 @@ static int conn_info_min_age_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val > hdev->conn_info_max_age) + hci_dev_lock(hdev); + if (val == 0 || val > hdev->conn_info_max_age) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->conn_info_min_age = val; hci_dev_unlock(hdev); @@ -244,10 +246,12 @@ static int conn_info_max_age_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val < hdev->conn_info_min_age) + hci_dev_lock(hdev); + if (val == 0 || val < hdev->conn_info_min_age) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->conn_info_max_age = val; hci_dev_unlock(hdev); @@ -526,10 +530,12 @@ static int sniff_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val % 2 || val > hdev->sniff_max_interval) + hci_dev_lock(hdev); + if (val == 0 || val % 2 || val > hdev->sniff_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->sniff_min_interval = val; hci_dev_unlock(hdev); @@ -554,10 +560,12 @@ static int sniff_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val % 2 || val < hdev->sniff_min_interval) + hci_dev_lock(hdev); + if (val == 0 || val % 2 || val < hdev->sniff_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->sniff_max_interval = val; hci_dev_unlock(hdev); @@ -798,10 +806,12 @@ static int conn_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) + hci_dev_lock(hdev); + if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_conn_min_interval = val; hci_dev_unlock(hdev); @@ -826,10 +836,12 @@ static int conn_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) + hci_dev_lock(hdev); + if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_conn_max_interval = val; hci_dev_unlock(hdev); @@ -938,10 +950,12 @@ static int adv_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) + hci_dev_lock(hdev); + if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_adv_min_interval = val; hci_dev_unlock(hdev); @@ -966,10 +980,12 @@ static int adv_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) + hci_dev_lock(hdev); + if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_adv_max_interval = val; hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 4027c7978..58c029958 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2636,6 +2636,31 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) if (test_bit(HCI_ENCRYPT, &hdev->flags)) set_bit(HCI_CONN_ENCRYPT, &conn->flags); + /* "Link key request" completed ahead of "connect request" completes */ + if (ev->encr_mode == 1 && !test_bit(HCI_CONN_ENCRYPT, &conn->flags) && + ev->link_type == ACL_LINK) { + struct link_key *key; + struct hci_cp_read_enc_key_size cp; + + key = hci_find_link_key(hdev, &ev->bdaddr); + if (key) { + set_bit(HCI_CONN_ENCRYPT, &conn->flags); + + if (!(hdev->commands[20] & 0x10)) { + conn->enc_key_size = HCI_LINK_KEY_SIZE; + } else { + cp.handle = cpu_to_le16(conn->handle); + if (hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE, + sizeof(cp), &cp)) { + bt_dev_err(hdev, "sending read key size failed"); + conn->enc_key_size = HCI_LINK_KEY_SIZE; + } + } + + hci_encrypt_cfm(conn, ev->status); + } + } + /* Get remote features */ if (conn->type == ACL_LINK) { struct hci_cp_read_remote_features cp; @@ -2979,8 +3004,6 @@ static void hci_remote_name_evt(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s", hdev->name); - hci_conn_check_pending(hdev); - hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); @@ -4612,9 +4635,12 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (!conn || !hci_conn_ssp_enabled(conn)) + if (!conn || !hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) goto unlock; + /* Assume remote supports SSP since it has triggered this event */ + set_bit(HCI_CONN_SSP_ENABLED, &conn->flags); + hci_conn_hold(conn); if (!hci_dev_test_flag(hdev, HCI_MGMT)) @@ -5922,6 +5948,10 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, return send_conn_param_neg_reply(hdev, handle, HCI_ERROR_UNKNOWN_CONN_ID); + if (max > hcon->le_conn_max_interval) + return send_conn_param_neg_reply(hdev, handle, + HCI_ERROR_INVALID_LL_PARAMS); + if (hci_check_conn_params(min, max, latency, timeout)) return send_conn_param_neg_reply(hdev, handle, HCI_ERROR_INVALID_LL_PARAMS); @@ -6139,10 +6169,10 @@ static void hci_store_wake_reason(struct hci_dev *hdev, u8 event, * keep track of the bdaddr of the connection event that woke us up. */ if (event == HCI_EV_CONN_REQUEST) { - bacpy(&hdev->wake_addr, &conn_complete->bdaddr); + bacpy(&hdev->wake_addr, &conn_request->bdaddr); hdev->wake_addr_type = BDADDR_BREDR; } else if (event == HCI_EV_CONN_COMPLETE) { - bacpy(&hdev->wake_addr, &conn_request->bdaddr); + bacpy(&hdev->wake_addr, &conn_complete->bdaddr); hdev->wake_addr_type = BDADDR_BREDR; } else if (event == HCI_EV_LE_META) { struct hci_ev_le_meta *le_ev = (void *)skb->data; diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index a0f980e61..7ce6db1ac 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -107,8 +107,10 @@ static void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, if (hdev->req_status == HCI_REQ_PEND) { hdev->req_result = result; hdev->req_status = HCI_REQ_DONE; - if (skb) + if (skb) { + kfree_skb(hdev->req_skb); hdev->req_skb = skb_get(skb); + } wake_up_interruptible(&hdev->req_wait_q); } } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index cf78a4808..580b6d6b9 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -5609,7 +5609,13 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, memset(&rsp, 0, sizeof(rsp)); - err = hci_check_conn_params(min, max, latency, to_multiplier); + if (max > hcon->le_conn_max_interval) { + BT_DBG("requested connection interval exceeds current bounds."); + err = -EINVAL; + } else { + err = hci_check_conn_params(min, max, latency, to_multiplier); + } + if (err) rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED); else @@ -6522,7 +6528,8 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn, if (len > skb->len || !cmd->ident) { BT_DBG("corrupted command"); l2cap_sig_send_rej(conn, cmd->ident); - break; + skb_pull(skb, len > skb->len ? skb->len : len); + continue; } err = l2cap_bredr_sig_cmd(conn, cmd, len, skb->data); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 756523e54..3a2be1b4a 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -456,7 +456,8 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, struct l2cap_chan *chan = l2cap_pi(sk)->chan; struct l2cap_options opts; struct l2cap_conninfo cinfo; - int len, err = 0; + int err = 0; + size_t len; u32 opt; BT_DBG("sk %p", sk); @@ -503,7 +504,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, BT_DBG("mode 0x%2.2x", chan->mode); - len = min_t(unsigned int, len, sizeof(opts)); + len = min(len, sizeof(opts)); if (copy_to_user(optval, (char *) &opts, len)) err = -EFAULT; @@ -553,7 +554,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, cinfo.hci_handle = chan->conn->hcon->handle; memcpy(cinfo.dev_class, chan->conn->hcon->dev_class, 3); - len = min_t(unsigned int, len, sizeof(cinfo)); + len = min(len, sizeof(cinfo)); if (copy_to_user(optval, (char *) &cinfo, len)) err = -EFAULT; diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 8d6fce900..4f54c7df3 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1937,7 +1937,7 @@ static struct rfcomm_session *rfcomm_process_rx(struct rfcomm_session *s) /* Get data directly from socket receive queue without copying it. */ while ((skb = skb_dequeue(&sk->sk_receive_queue))) { skb_orphan(skb); - if (!skb_linearize(skb)) { + if (!skb_linearize(skb) && sk->sk_state != BT_CLOSED) { s = rfcomm_recv_frame(s, skb); if (!s) break; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 8244d3ae1..2115ca6d7 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -825,7 +825,7 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; - int len, err = 0; + int err = 0; struct bt_voice voice; u32 opt; @@ -841,10 +841,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); @@ -861,11 +860,10 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, voice.setting = sco_pi(sk)->setting; - len = min_t(unsigned int, sizeof(voice), optlen); - if (copy_from_sockptr(&voice, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&voice, sizeof(voice), optval, + optlen); + if (err) break; - } /* Explicitly check for these values */ if (voice.setting != BT_VOICE_TRANSPARENT && @@ -878,10 +876,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_PKT_STATUS: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) sco_pi(sk)->cmsg_mask |= SCO_CMSG_PKT_STATUS; @@ -904,7 +901,8 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, struct sock *sk = sock->sk; struct sco_options opts; struct sco_conninfo cinfo; - int len, err = 0; + int err = 0; + size_t len; BT_DBG("sk %p", sk); @@ -926,7 +924,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, BT_DBG("mtu %d", opts.mtu); - len = min_t(unsigned int, len, sizeof(opts)); + len = min(len, sizeof(opts)); if (copy_to_user(optval, (char *)&opts, len)) err = -EFAULT; @@ -944,7 +942,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, cinfo.hci_handle = sco_pi(sk)->conn->hcon->handle; memcpy(cinfo.dev_class, sco_pi(sk)->conn->hcon->dev_class, 3); - len = min_t(unsigned int, len, sizeof(cinfo)); + len = min(len, sizeof(cinfo)); if (copy_to_user(optval, (char *)&cinfo, len)) err = -EFAULT; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index bab14186f..14a06d8b1 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1070,6 +1070,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) struct ebt_table_info *newinfo; struct ebt_replace tmp; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1309,6 +1311,8 @@ static int update_counters(struct net *net, sockptr_t arg, unsigned int len) { struct ebt_replace hlp; + if (len < sizeof(hlp)) + return -EINVAL; if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; @@ -2238,6 +2242,8 @@ static int compat_update_counters(struct net *net, sockptr_t arg, { struct compat_ebt_replace hlp; + if (len < sizeof(hlp)) + return -EINVAL; if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index cea712fb2..9ac2a10b1 100644 --- a/net/can/j1939/j1939-priv.h +++ b/net/can/j1939/j1939-priv.h @@ -297,6 +297,7 @@ struct j1939_sock { int ifindex; struct j1939_addr addr; + spinlock_t filters_lock; struct j1939_filter *filters; int nfilters; pgn_t pgn_rx_filter; diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 906a08d38..c216c60f5 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -262,12 +262,17 @@ static bool j1939_sk_match_dst(struct j1939_sock *jsk, static bool j1939_sk_match_filter(struct j1939_sock *jsk, const struct j1939_sk_buff_cb *skcb) { - const struct j1939_filter *f = jsk->filters; - int nfilter = jsk->nfilters; + const struct j1939_filter *f; + int nfilter; + + spin_lock_bh(&jsk->filters_lock); + + f = jsk->filters; + nfilter = jsk->nfilters; if (!nfilter) /* receive all when no filters are assigned */ - return true; + goto filter_match_found; for (; nfilter; ++f, --nfilter) { if ((skcb->addr.pgn & f->pgn_mask) != f->pgn) @@ -276,9 +281,15 @@ static bool j1939_sk_match_filter(struct j1939_sock *jsk, continue; if ((skcb->addr.src_name & f->name_mask) != f->name) continue; - return true; + goto filter_match_found; } + + spin_unlock_bh(&jsk->filters_lock); return false; + +filter_match_found: + spin_unlock_bh(&jsk->filters_lock); + return true; } static bool j1939_sk_recv_match_one(struct j1939_sock *jsk, @@ -401,6 +412,7 @@ static int j1939_sk_init(struct sock *sk) atomic_set(&jsk->skb_pending, 0); spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); + spin_lock_init(&jsk->filters_lock); /* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */ sock_set_flag(sk, SOCK_RCU_FREE); @@ -703,9 +715,11 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname, } lock_sock(&jsk->sk); + spin_lock_bh(&jsk->filters_lock); ofilters = jsk->filters; jsk->filters = filters; jsk->nfilters = count; + spin_unlock_bh(&jsk->filters_lock); release_sock(&jsk->sk); kfree(ofilters); return 0; diff --git a/net/core/dev.c b/net/core/dev.c index fc881d60a..0e2c433be 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2324,7 +2324,7 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); again: list_for_each_entry_rcu(ptype, ptype_list, list) { - if (ptype->ignore_outgoing) + if (READ_ONCE(ptype->ignore_outgoing)) continue; /* Never send packets back to the socket @@ -8787,7 +8787,7 @@ EXPORT_SYMBOL(dev_set_mac_address_user); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { - size_t size = sizeof(sa->sa_data); + size_t size = sizeof(sa->sa_data_min); struct net_device *dev; int ret = 0; diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 993420da2..60e815a71 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -245,7 +245,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) if (ifr->ifr_hwaddr.sa_family != dev->type) return -EINVAL; memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, - min(sizeof(ifr->ifr_hwaddr.sa_data), + min(sizeof(ifr->ifr_hwaddr.sa_data_min), (size_t)dev->addr_len)); call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return 0; diff --git a/net/core/filter.c b/net/core/filter.c index 6cfc8fb05..49e4d1535 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -9903,8 +9903,7 @@ int sk_detach_filter(struct sock *sk) } EXPORT_SYMBOL_GPL(sk_detach_filter); -int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, - unsigned int len) +int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len) { struct sock_fprog_kern *fprog; struct sk_filter *filter; @@ -9935,7 +9934,7 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, goto out; ret = -EFAULT; - if (copy_to_user(ubuf, fprog->filter, bpf_classic_proglen(fprog))) + if (copy_to_sockptr(optval, fprog->filter, bpf_classic_proglen(fprog))) goto out; /* Instead of bytes, the API requests to return the number diff --git a/net/core/request_sock.c b/net/core/request_sock.c index f35c2e998..63de5c635 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -33,9 +33,6 @@ void reqsk_queue_alloc(struct request_sock_queue *queue) { - spin_lock_init(&queue->rskq_lock); - - spin_lock_init(&queue->fastopenq.lock); queue->fastopenq.rskq_rst_head = NULL; queue->fastopenq.rskq_rst_tail = NULL; queue->fastopenq.qlen = 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 021dcfdae..8938320f7 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4903,10 +4903,9 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; struct net_device *dev; - struct nlattr *br_spec, *attr = NULL; + struct nlattr *br_spec, *attr, *br_flags_attr = NULL; int rem, err = -EOPNOTSUPP; u16 flags = 0; - bool have_flags = false; if (nlmsg_len(nlh) < sizeof(*ifm)) return -EINVAL; @@ -4924,11 +4923,11 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (br_spec) { nla_for_each_nested(attr, br_spec, rem) { - if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !br_flags_attr) { if (nla_len(attr) < sizeof(flags)) return -EINVAL; - have_flags = true; + br_flags_attr = attr; flags = nla_get_u16(attr); } @@ -4972,8 +4971,8 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, } } - if (have_flags) - memcpy(nla_data(attr), &flags, sizeof(flags)); + if (br_flags_attr) + memcpy(nla_data(br_flags_attr), &flags, sizeof(flags)); out: return err; } diff --git a/net/core/scm.c b/net/core/scm.c index 3c7f16072..d09849cb6 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -105,7 +105,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) if (fd < 0 || !(file = fget_raw(fd))) return -EBADF; /* don't allow io_uring files */ - if (io_uring_get_socket(file)) { + if (io_is_uring_fops(file)) { fput(file); return -EINVAL; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 196278a13..50261f3ae 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3877,8 +3877,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, /* GSO partial only requires that we trim off any excess that * doesn't fit into an MSS sized block, so take care of that * now. + * Cap len to not accidentally hit GSO_BY_FRAGS. */ - partial_segs = len / mss; + partial_segs = min(len, GSO_BY_FRAGS - 1U) / mss; if (partial_segs > 1) mss *= partial_segs; else diff --git a/net/core/sock.c b/net/core/sock.c index 769e969cd..016c0b9e0 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -644,8 +644,8 @@ out: return ret; } -static int sock_getbindtodevice(struct sock *sk, char __user *optval, - int __user *optlen, int len) +static int sock_getbindtodevice(struct sock *sk, sockptr_t optval, + sockptr_t optlen, int len) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES @@ -668,12 +668,12 @@ static int sock_getbindtodevice(struct sock *sk, char __user *optval, len = strlen(devname) + 1; ret = -EFAULT; - if (copy_to_user(optval, devname, len)) + if (copy_to_sockptr(optval, devname, len)) goto out; zero: ret = -EFAULT; - if (put_user(len, optlen)) + if (copy_to_sockptr(optlen, &len, sizeof(int))) goto out; ret = 0; @@ -1281,22 +1281,25 @@ static void cred_to_ucred(struct pid *pid, const struct cred *cred, } } -static int groups_to_user(gid_t __user *dst, const struct group_info *src) +static int groups_to_user(sockptr_t dst, const struct group_info *src) { struct user_namespace *user_ns = current_user_ns(); int i; - for (i = 0; i < src->ngroups; i++) - if (put_user(from_kgid_munged(user_ns, src->gid[i]), dst + i)) + for (i = 0; i < src->ngroups; i++) { + gid_t gid = from_kgid_munged(user_ns, src->gid[i]); + + if (copy_to_sockptr_offset(dst, i * sizeof(gid), &gid, sizeof(gid))) return -EFAULT; + } return 0; } -int sock_getsockopt(struct socket *sock, int level, int optname, - char __user *optval, int __user *optlen) +static int sk_getsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, sockptr_t optlen) { - struct sock *sk = sock->sk; + struct socket *sock = sk->sk_socket; union { int val; @@ -1312,7 +1315,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, int lv = sizeof(int); int len; - if (get_user(len, optlen)) + if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; @@ -1445,7 +1448,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); spin_unlock(&sk->sk_peer_lock); - if (copy_to_user(optval, &peercred, len)) + if (copy_to_sockptr(optval, &peercred, len)) return -EFAULT; goto lenout; } @@ -1463,11 +1466,11 @@ int sock_getsockopt(struct socket *sock, int level, int optname, if (len < n * sizeof(gid_t)) { len = n * sizeof(gid_t); put_cred(cred); - return put_user(len, optlen) ? -EFAULT : -ERANGE; + return copy_to_sockptr(optlen, &len, sizeof(int)) ? -EFAULT : -ERANGE; } len = n * sizeof(gid_t); - ret = groups_to_user((gid_t __user *)optval, cred->group_info); + ret = groups_to_user(optval, cred->group_info); put_cred(cred); if (ret) return ret; @@ -1483,7 +1486,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, return -ENOTCONN; if (lv < len) return -EINVAL; - if (copy_to_user(optval, address, len)) + if (copy_to_sockptr(optval, address, len)) return -EFAULT; goto lenout; } @@ -1500,7 +1503,8 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_PEERSEC: - return security_socket_getpeersec_stream(sock, optval, optlen, len); + return security_socket_getpeersec_stream(sock, + optval, optlen, len); case SO_MARK: v.val = sk->sk_mark; @@ -1528,7 +1532,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, return sock_getbindtodevice(sk, optval, optlen, len); case SO_GET_FILTER: - len = sk_get_filter(sk, (struct sock_filter __user *)optval, len); + len = sk_get_filter(sk, optval, len); if (len < 0) return len; @@ -1575,7 +1579,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, sk_get_meminfo(sk, meminfo); len = min_t(unsigned int, len, sizeof(meminfo)); - if (copy_to_user(optval, &meminfo, len)) + if (copy_to_sockptr(optval, &meminfo, len)) return -EFAULT; goto lenout; @@ -1625,14 +1629,22 @@ int sock_getsockopt(struct socket *sock, int level, int optname, if (len > lv) len = lv; - if (copy_to_user(optval, &v, len)) + if (copy_to_sockptr(optval, &v, len)) return -EFAULT; lenout: - if (put_user(len, optlen)) + if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; return 0; } +int sock_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + return sk_getsockopt(sock->sk, level, optname, + USER_SOCKPTR(optval), + USER_SOCKPTR(optlen)); +} + /* * Initialize an sk_lock. * diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index c9c45b935..bce65b519 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -189,7 +189,7 @@ int sock_diag_register(const struct sock_diag_handler *hndl) if (sock_diag_handlers[hndl->family]) err = -EBUSY; else - sock_diag_handlers[hndl->family] = hndl; + WRITE_ONCE(sock_diag_handlers[hndl->family], hndl); mutex_unlock(&sock_diag_table_mutex); return err; @@ -205,7 +205,7 @@ void sock_diag_unregister(const struct sock_diag_handler *hnld) mutex_lock(&sock_diag_table_mutex); BUG_ON(sock_diag_handlers[family] != hnld); - sock_diag_handlers[family] = NULL; + WRITE_ONCE(sock_diag_handlers[family], NULL); mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_unregister); @@ -223,7 +223,7 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) return -EINVAL; req->sdiag_family = array_index_nospec(req->sdiag_family, AF_MAX); - if (sock_diag_handlers[req->sdiag_family] == NULL) + if (READ_ONCE(sock_diag_handlers[req->sdiag_family]) == NULL) sock_load_diag_module(req->sdiag_family, 0); mutex_lock(&sock_diag_table_mutex); @@ -282,12 +282,12 @@ static int sock_diag_bind(struct net *net, int group) switch (group) { case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: - if (!sock_diag_handlers[AF_INET]) + if (!READ_ONCE(sock_diag_handlers[AF_INET])) sock_load_diag_module(AF_INET, 0); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: - if (!sock_diag_handlers[AF_INET6]) + if (!READ_ONCE(sock_diag_handlers[AF_INET6])) sock_load_diag_module(AF_INET6, 0); break; } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index f375ef150..52e395a18 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -422,6 +422,9 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock *sk; int err = 0; + if (irqs_disabled()) + return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ + raw_spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) @@ -955,6 +958,9 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key) struct bpf_shtab_elem *elem; int ret = -ENOENT; + if (irqs_disabled()) + return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ + hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index dac65180c..61cb40368 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -164,17 +164,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) eth = (struct ethhdr *)skb->data; skb_pull_inline(skb, ETH_HLEN); - if (unlikely(!ether_addr_equal_64bits(eth->h_dest, - dev->dev_addr))) { - if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { - if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) - skb->pkt_type = PACKET_BROADCAST; - else - skb->pkt_type = PACKET_MULTICAST; - } else { - skb->pkt_type = PACKET_OTHERHOST; - } - } + eth_skb_pkt_type(skb, dev); /* * Some variants of DSA tagging don't have an ethertype field diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 84e6ef4f3..c5a4c5fb7 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -291,7 +291,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, skb = hsr_init_skb(master); if (!skb) { - WARN_ONCE(1, "HSR: Could not send supervision frame\n"); + netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n"); return; } @@ -338,7 +338,7 @@ static void send_prp_supervision_frame(struct hsr_port *master, skb = hsr_init_skb(master); if (!skb) { - WARN_ONCE(1, "PRP: Could not send supervision frame\n"); + netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index afc97d65c..fc9fb3e5a 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -237,6 +237,10 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, */ if (ethhdr->h_proto == htons(ETH_P_PRP) || ethhdr->h_proto == htons(ETH_P_HSR)) { + /* Check if skb contains hsr_ethhdr */ + if (skb->mac_len < sizeof(struct hsr_ethhdr)) + return NULL; + /* Use the existing sequence_nr from the tag as starting point * for filtering duplicate frames. */ @@ -327,9 +331,12 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) node_real->addr_B_port = port_rcv->type; spin_lock_bh(&hsr->list_lock); - list_del_rcu(&node_curr->mac_list); + if (!node_curr->removed) { + list_del_rcu(&node_curr->mac_list); + node_curr->removed = true; + kfree_rcu(node_curr, rcu_head); + } spin_unlock_bh(&hsr->list_lock); - kfree_rcu(node_curr, rcu_head); done: /* PRP uses v0 header */ @@ -506,9 +513,12 @@ void hsr_prune_nodes(struct timer_list *t) if (time_is_before_jiffies(timestamp + msecs_to_jiffies(HSR_NODE_FORGET_TIME))) { hsr_nl_nodedown(hsr, node->macaddress_A); - list_del_rcu(&node->mac_list); - /* Note that we need to free this entry later: */ - kfree_rcu(node, rcu_head); + if (!node->removed) { + list_del_rcu(&node->mac_list); + node->removed = true; + /* Note that we need to free this entry later: */ + kfree_rcu(node, rcu_head); + } } } spin_unlock_bh(&hsr->list_lock); diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 5a771cb3f..48990166e 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -82,6 +82,7 @@ struct hsr_node { bool san_a; bool san_b; u16 seq_out[HSR_PT_PORTS]; + bool removed; struct rcu_head rcu_head; }; diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index 2fd1976e5..bea7f935f 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -137,14 +137,21 @@ static struct notifier_block hsr_nb = { static int __init hsr_init(void) { - int res; + int err; BUILD_BUG_ON(sizeof(struct hsr_tag) != HSR_HLEN); - register_netdevice_notifier(&hsr_nb); - res = hsr_netlink_init(); + err = register_netdevice_notifier(&hsr_nb); + if (err) + return err; + + err = hsr_netlink_init(); + if (err) { + unregister_netdevice_notifier(&hsr_nb); + return err; + } - return res; + return 0; } static void __exit hsr_exit(void) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index acb488735..5f1b334e6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -327,6 +327,9 @@ lookup_protocol: if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; + if (INET_PROTOSW_ICSK & answer_flags) + inet_init_csk_locks(sk); + inet = inet_sk(sk); inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; @@ -1597,10 +1600,12 @@ EXPORT_SYMBOL(inet_current_timestamp); int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { - if (sk->sk_family == AF_INET) + unsigned int family = READ_ONCE(sk->sk_family); + + if (family == AF_INET) return ip_recv_error(sk, msg, len, addr_len); #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) + if (family == AF_INET6) return pingv6_ops.ipv6_recv_error(sk, msg, len, addr_len); #endif return -EINVAL; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 83a47998c..8ae9bd6f9 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1104,7 +1104,8 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) if (neigh) { if (!(neigh->nud_state & NUD_NOARP)) { read_lock_bh(&neigh->lock); - memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len); + memcpy(r->arp_ha.sa_data, neigh->ha, + min(dev->addr_len, (unsigned char)sizeof(r->arp_ha.sa_data_min))); r->arp_flags = arp_state_to_flags(neigh); read_unlock_bh(&neigh->lock); r->arp_ha.sa_family = dev->type; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index da1ca8081..9ac7d47d2 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1798,6 +1798,21 @@ done: return err; } +/* Combine dev_addr_genid and dev_base_seq to detect changes. + */ +static u32 inet_base_seq(const struct net *net) +{ + u32 res = atomic_read(&net->ipv4.dev_addr_genid) + + net->dev_base_seq; + + /* Must not return 0 (see nl_dump_check_consistent()). + * Chose a value far away from 0. + */ + if (!res) + res = 0x80000000; + return res; +} + static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; @@ -1849,8 +1864,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; head = &tgt_net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&tgt_net->ipv4.dev_addr_genid) ^ - tgt_net->dev_base_seq; + cb->seq = inet_base_seq(tgt_net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -2249,8 +2263,7 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb, idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = inet_base_seq(net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index cb55fede0..f0a313747 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2493,8 +2493,8 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) goto done; } newpsl->sl_max = newpsl->sl_count = msf->imsf_numsrc; - memcpy(newpsl->sl_addr, msf->imsf_slist, - msf->imsf_numsrc * sizeof(msf->imsf_slist[0])); + memcpy(newpsl->sl_addr, msf->imsf_slist_flex, + flex_array_size(msf, imsf_slist_flex, msf->imsf_numsrc)); err = ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { @@ -2526,11 +2526,10 @@ done: err = ip_mc_leave_group(sk, &imr); return err; } - int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, - struct ip_msfilter __user *optval, int __user *optlen) + sockptr_t optval, sockptr_t optlen) { - int err, len, count, copycount; + int err, len, count, copycount, msf_size; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; @@ -2571,14 +2570,17 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, count = psl->sl_count; } copycount = count < msf->imsf_numsrc ? count : msf->imsf_numsrc; - len = copycount * sizeof(psl->sl_addr[0]); + len = flex_array_size(psl, sl_addr, copycount); msf->imsf_numsrc = count; - if (put_user(IP_MSFILTER_SIZE(copycount), optlen) || - copy_to_user(optval, msf, IP_MSFILTER_SIZE(0))) { + msf_size = IP_MSFILTER_SIZE(copycount); + if (copy_to_sockptr(optlen, &msf_size, sizeof(int)) || + copy_to_sockptr(optval, msf, IP_MSFILTER_SIZE(0))) { return -EFAULT; } if (len && - copy_to_user(&optval->imsf_slist[0], psl->sl_addr, len)) + copy_to_sockptr_offset(optval, + offsetof(struct ip_msfilter, imsf_slist_flex), + psl->sl_addr, len)) return -EFAULT; return 0; done: @@ -2586,7 +2588,7 @@ done: } int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, - struct sockaddr_storage __user *p) + sockptr_t optval, size_t ss_offset) { int i, count, copycount; struct sockaddr_in *psin; @@ -2616,15 +2618,17 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; gsf->gf_numsrc = count; - for (i = 0; i < copycount; i++, p++) { + for (i = 0; i < copycount; i++) { struct sockaddr_storage ss; psin = (struct sockaddr_in *)&ss; memset(&ss, 0, sizeof(ss)); psin->sin_family = AF_INET; psin->sin_addr.s_addr = psl->sl_addr[i]; - if (copy_to_user(p, &ss, sizeof(ss))) + if (copy_to_sockptr_offset(optval, ss_offset, + &ss, sizeof(ss))) return -EFAULT; + ss_offset += sizeof(ss); } return 0; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 5f71a1c74..6ebe43b4d 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -536,6 +536,10 @@ out: } if (req) reqsk_put(req); + + if (newsk) + inet_init_csk_locks(newsk); + return newsk; out_err: newsk = NULL; @@ -576,6 +580,20 @@ void inet_csk_clear_xmit_timers(struct sock *sk) } EXPORT_SYMBOL(inet_csk_clear_xmit_timers); +void inet_csk_clear_xmit_timers_sync(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + /* ongoing timer handlers need to acquire socket lock. */ + sock_not_owned_by_me(sk); + + icsk->icsk_pending = icsk->icsk_ack.pending = 0; + + sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer); + sk_stop_timer_sync(sk, &icsk->icsk_delack_timer); + sk_stop_timer_sync(sk, &sk->sk_timer); +} + void inet_csk_delete_keepalive_timer(struct sock *sk) { sk_stop_timer(sk, &sk->sk_timer); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index fa9f1de58..27a5a7d66 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -57,7 +57,7 @@ static const struct inet_diag_handler *inet_diag_lock_handler(int proto) return ERR_PTR(-ENOENT); } - if (!inet_diag_table[proto]) + if (!READ_ONCE(inet_diag_table[proto])) sock_load_diag_module(AF_INET, proto); mutex_lock(&inet_diag_table_mutex); @@ -1413,7 +1413,7 @@ int inet_diag_register(const struct inet_diag_handler *h) mutex_lock(&inet_diag_table_mutex); err = -EEXIST; if (!inet_diag_table[type]) { - inet_diag_table[type] = h; + WRITE_ONCE(inet_diag_table[type], h); err = 0; } mutex_unlock(&inet_diag_table_mutex); @@ -1430,7 +1430,7 @@ void inet_diag_unregister(const struct inet_diag_handler *h) return; mutex_lock(&inet_diag_table_mutex); - inet_diag_table[type] = NULL; + WRITE_ONCE(inet_diag_table[type], NULL); mutex_unlock(&inet_diag_table_mutex); } EXPORT_SYMBOL_GPL(inet_diag_unregister); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index c411c87ae..85cb44bfa 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -254,12 +254,12 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) } EXPORT_SYMBOL_GPL(__inet_twsk_schedule); +/* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */ void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) { - struct inet_timewait_sock *tw; - struct sock *sk; struct hlist_nulls_node *node; unsigned int slot; + struct sock *sk; for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; @@ -268,25 +268,35 @@ restart_rcu: rcu_read_lock(); restart: sk_nulls_for_each_rcu(sk, node, &head->chain) { - if (sk->sk_state != TCP_TIME_WAIT) + int state = inet_sk_state_load(sk); + + if ((1 << state) & ~(TCPF_TIME_WAIT | + TCPF_NEW_SYN_RECV)) continue; - tw = inet_twsk(sk); - if ((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->count)) + + if (sk->sk_family != family || + refcount_read(&sock_net(sk)->count)) continue; - if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) + if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) continue; - if (unlikely((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->count))) { - inet_twsk_put(tw); + if (unlikely(sk->sk_family != family || + refcount_read(&sock_net(sk)->count))) { + sock_gen_put(sk); goto restart; } rcu_read_unlock(); local_bh_disable(); - inet_twsk_deschedule_put(tw); + if (state == TCP_TIME_WAIT) { + inet_twsk_deschedule_put(inet_twsk(sk)); + } else { + struct request_sock *req = inet_reqsk(sk); + + inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, + req); + } local_bh_enable(); goto restart_rcu; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index a6ad0fe13..0ac652fef 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -278,8 +278,13 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, tpi->flags | TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); } else { + if (unlikely(!pskb_may_pull(skb, + gre_hdr_len + sizeof(*ershdr)))) + return PACKET_REJECT; + ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; + iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_KEY, iph->saddr, iph->daddr, tpi->key); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a99c37410..12ee857d6 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1260,6 +1260,12 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, if (unlikely(!rt)) return -EFAULT; + cork->fragsize = ip_sk_use_pmtu(sk) ? + dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); + + if (!inetdev_valid_mtu(cork->fragsize)) + return -ENETUNREACH; + /* * setup for corking. */ @@ -1276,12 +1282,6 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->addr = ipc->addr; } - cork->fragsize = ip_sk_use_pmtu(sk) ? - dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); - - if (!inetdev_valid_mtu(cork->fragsize)) - return -ENETUNREACH; - cork->gso_size = ipc->gso_size; cork->dst = &rt->dst; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 1b35afd32..b300d0988 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -670,12 +670,11 @@ static int set_mcast_msfilter(struct sock *sk, int ifindex, struct sockaddr_storage *group, struct sockaddr_storage *list) { - int msize = IP_MSFILTER_SIZE(numsrc); struct ip_msfilter *msf; struct sockaddr_in *psin; int err, i; - msf = kmalloc(msize, GFP_KERNEL); + msf = kmalloc(IP_MSFILTER_SIZE(numsrc), GFP_KERNEL); if (!msf) return -ENOBUFS; @@ -691,7 +690,7 @@ static int set_mcast_msfilter(struct sock *sk, int ifindex, if (psin->sin_family != AF_INET) goto Eaddrnotavail; - msf->imsf_slist[i] = psin->sin_addr.s_addr; + msf->imsf_slist_flex[i] = psin->sin_addr.s_addr; } err = ip_mc_msfilter(sk, msf, ifindex); kfree(msf); @@ -798,7 +797,8 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) goto out_free_gsf; err = set_mcast_msfilter(sk, gsf->gf_interface, gsf->gf_numsrc, - gsf->gf_fmode, &gsf->gf_group, gsf->gf_slist); + gsf->gf_fmode, &gsf->gf_group, + gsf->gf_slist_flex); out_free_gsf: kfree(gsf); return err; @@ -807,7 +807,7 @@ out_free_gsf: static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) { - const int size0 = offsetof(struct compat_group_filter, gf_slist); + const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter *gf32; unsigned int n; void *p; @@ -821,7 +821,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, p = kmalloc(optlen + 4, GFP_KERNEL); if (!p) return -ENOMEM; - gf32 = p + 4; /* we want ->gf_group and ->gf_slist aligned */ + gf32 = p + 4; /* we want ->gf_group and ->gf_slist_flex aligned */ err = -EFAULT; if (copy_from_sockptr(gf32, optval, optlen)) @@ -834,7 +834,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, goto out_free_gsf; err = -EINVAL; - if (offsetof(struct compat_group_filter, gf_slist[n]) > optlen) + if (offsetof(struct compat_group_filter, gf_slist_flex[n]) > optlen) goto out_free_gsf; /* numsrc >= (4G-140)/128 overflow in 32 bits */ @@ -842,7 +842,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (n > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf)) goto out_free_gsf; err = set_mcast_msfilter(sk, gf32->gf_interface, n, gf32->gf_fmode, - &gf32->gf_group, gf32->gf_slist); + &gf32->gf_group, gf32->gf_slist_flex); out_free_gsf: kfree(p); return err; @@ -1460,37 +1460,37 @@ static bool getsockopt_needs_rtnl(int optname) return false; } -static int ip_get_mcast_msfilter(struct sock *sk, void __user *optval, - int __user *optlen, int len) +static int ip_get_mcast_msfilter(struct sock *sk, sockptr_t optval, + sockptr_t optlen, int len) { - const int size0 = offsetof(struct group_filter, gf_slist); - struct group_filter __user *p = optval; + const int size0 = offsetof(struct group_filter, gf_slist_flex); struct group_filter gsf; - int num; + int num, gsf_size; int err; if (len < size0) return -EINVAL; - if (copy_from_user(&gsf, p, size0)) + if (copy_from_sockptr(&gsf, optval, size0)) return -EFAULT; num = gsf.gf_numsrc; - err = ip_mc_gsfget(sk, &gsf, p->gf_slist); + err = ip_mc_gsfget(sk, &gsf, optval, + offsetof(struct group_filter, gf_slist_flex)); if (err) return err; if (gsf.gf_numsrc < num) num = gsf.gf_numsrc; - if (put_user(GROUP_FILTER_SIZE(num), optlen) || - copy_to_user(p, &gsf, size0)) + gsf_size = GROUP_FILTER_SIZE(num); + if (copy_to_sockptr(optlen, &gsf_size, sizeof(int)) || + copy_to_sockptr(optval, &gsf, size0)) return -EFAULT; return 0; } -static int compat_ip_get_mcast_msfilter(struct sock *sk, void __user *optval, - int __user *optlen, int len) +static int compat_ip_get_mcast_msfilter(struct sock *sk, sockptr_t optval, + sockptr_t optlen, int len) { - const int size0 = offsetof(struct compat_group_filter, gf_slist); - struct compat_group_filter __user *p = optval; + const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter gf32; struct group_filter gf; int num; @@ -1498,7 +1498,7 @@ static int compat_ip_get_mcast_msfilter(struct sock *sk, void __user *optval, if (len < size0) return -EINVAL; - if (copy_from_user(&gf32, p, size0)) + if (copy_from_sockptr(&gf32, optval, size0)) return -EFAULT; gf.gf_interface = gf32.gf_interface; @@ -1506,21 +1506,24 @@ static int compat_ip_get_mcast_msfilter(struct sock *sk, void __user *optval, num = gf.gf_numsrc = gf32.gf_numsrc; gf.gf_group = gf32.gf_group; - err = ip_mc_gsfget(sk, &gf, p->gf_slist); + err = ip_mc_gsfget(sk, &gf, optval, + offsetof(struct compat_group_filter, gf_slist_flex)); if (err) return err; if (gf.gf_numsrc < num) num = gf.gf_numsrc; len = GROUP_FILTER_SIZE(num) - (sizeof(gf) - sizeof(gf32)); - if (put_user(len, optlen) || - put_user(gf.gf_fmode, &p->gf_fmode) || - put_user(gf.gf_numsrc, &p->gf_numsrc)) + if (copy_to_sockptr(optlen, &len, sizeof(int)) || + copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_fmode), + &gf.gf_fmode, sizeof(gf.gf_fmode)) || + copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_numsrc), + &gf.gf_numsrc, sizeof(gf.gf_numsrc))) return -EFAULT; return 0; } static int do_ip_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) + sockptr_t optval, sockptr_t optlen) { struct inet_sock *inet = inet_sk(sk); bool needs_rtnl = getsockopt_needs_rtnl(optname); @@ -1533,7 +1536,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, if (ip_mroute_opt(optname)) return ip_mroute_getsockopt(sk, optname, optval, optlen); - if (get_user(len, optlen)) + if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; @@ -1558,15 +1561,17 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, inet_opt->opt.optlen); release_sock(sk); - if (opt->optlen == 0) - return put_user(0, optlen); + if (opt->optlen == 0) { + len = 0; + return copy_to_sockptr(optlen, &len, sizeof(int)); + } ip_options_undo(opt); len = min_t(unsigned int, len, opt->optlen); - if (put_user(len, optlen)) + if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; - if (copy_to_user(optval, opt->__data, len)) + if (copy_to_sockptr(optval, opt->__data, len)) return -EFAULT; return 0; } @@ -1657,9 +1662,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, addr.s_addr = inet->mc_addr; release_sock(sk); - if (put_user(len, optlen)) + if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; - if (copy_to_user(optval, &addr, len)) + if (copy_to_sockptr(optval, &addr, len)) return -EFAULT; return 0; } @@ -1671,12 +1676,11 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, err = -EINVAL; goto out; } - if (copy_from_user(&msf, optval, IP_MSFILTER_SIZE(0))) { + if (copy_from_sockptr(&msf, optval, IP_MSFILTER_SIZE(0))) { err = -EFAULT; goto out; } - err = ip_mc_msfget(sk, &msf, - (struct ip_msfilter __user *)optval, optlen); + err = ip_mc_msfget(sk, &msf, optval, optlen); goto out; } case MCAST_MSFILTER: @@ -1698,8 +1702,13 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, if (sk->sk_type != SOCK_STREAM) return -ENOPROTOOPT; - msg.msg_control_is_user = true; - msg.msg_control_user = optval; + if (optval.is_kernel) { + msg.msg_control_is_user = false; + msg.msg_control = optval.kernel; + } else { + msg.msg_control_is_user = true; + msg.msg_control_user = optval.user; + } msg.msg_controllen = len; msg.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0; @@ -1720,7 +1729,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos); } len -= msg.msg_controllen; - return put_user(len, optlen); + return copy_to_sockptr(optlen, &len, sizeof(int)); } case IP_FREEBIND: val = inet->freebind; @@ -1743,15 +1752,15 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, if (len < sizeof(int) && len > 0 && val >= 0 && val <= 255) { unsigned char ucval = (unsigned char)val; len = 1; - if (put_user(len, optlen)) + if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; - if (copy_to_user(optval, &ucval, 1)) + if (copy_to_sockptr(optval, &ucval, 1)) return -EFAULT; } else { len = min_t(unsigned int, sizeof(int), len); - if (put_user(len, optlen)) + if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; - if (copy_to_user(optval, &val, len)) + if (copy_to_sockptr(optval, &val, len)) return -EFAULT; } return 0; @@ -1768,7 +1777,8 @@ int ip_getsockopt(struct sock *sk, int level, { int err; - err = do_ip_getsockopt(sk, level, optname, optval, optlen); + err = do_ip_getsockopt(sk, level, optname, + USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); #if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_GET_INFO && diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 99f70b990..0953d805c 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -364,7 +364,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, bool log_ecn_error) { const struct iphdr *iph = ip_hdr(skb); - int err; + int nh, err; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { @@ -390,8 +390,21 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, tunnel->i_seqno = ntohl(tpi->seq) + 1; } + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0); + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(tunnel->dev, rx_length_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); + goto drop; + } + iph = (struct iphdr *)(skb->head + nh); + err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) @@ -540,6 +553,20 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, return 0; } +static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom) +{ + /* we must cap headroom to some upperlimit, else pskb_expand_head + * will overflow header offsets in skb_headers_offset_update(). + */ + static const unsigned int max_allowed = 512; + + if (headroom > max_allowed) + headroom = max_allowed; + + if (headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, headroom); +} + void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto, int tunnel_hlen) { @@ -613,13 +640,13 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; - if (headroom > READ_ONCE(dev->needed_headroom)) - WRITE_ONCE(dev->needed_headroom, headroom); - - if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { + if (skb_cow_head(skb, headroom)) { ip_rt_put(rt); goto tx_dropped; } + + ip_tunnel_adj_headroom(dev, headroom); + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; @@ -797,16 +824,16 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); - if (max_headroom > READ_ONCE(dev->needed_headroom)) - WRITE_ONCE(dev->needed_headroom, max_headroom); - if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { + if (skb_cow_head(skb, max_headroom)) { ip_rt_put(rt); dev->stats.tx_dropped++; kfree_skb(skb); return; } + ip_tunnel_adj_headroom(dev, max_headroom); + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index da9a55c68..ba1388ba6 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -332,7 +332,7 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu) }; skb_reset_network_header(skb); - csum = csum_partial(icmp6h, len, 0); + csum = skb_checksum(skb, skb_transport_offset(skb), len, 0); icmp6h->icmp6_cksum = csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, len, IPPROTO_ICMPV6, csum); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index be1976536..db184cb82 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1540,7 +1540,8 @@ out: } /* Getsock opt support for the multicast routing system. */ -int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen) +int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval, + sockptr_t optlen) { int olr; int val; @@ -1571,14 +1572,16 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int return -ENOPROTOOPT; } - if (get_user(olr, optlen)) + if (copy_from_sockptr(&olr, optlen, sizeof(int))) return -EFAULT; - olr = min_t(unsigned int, olr, sizeof(int)); if (olr < 0) return -EINVAL; - if (put_user(olr, optlen)) + + olr = min_t(unsigned int, olr, sizeof(int)); + + if (copy_to_sockptr(optlen, &olr, sizeof(int))) return -EFAULT; - if (copy_to_user(optval, &val, olr)) + if (copy_to_sockptr(optval, &val, olr)) return -EFAULT; return 0; } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index d6d45d820..5823e89b8 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -955,6 +955,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct arpt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -963,6 +965,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1253,6 +1257,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct arpt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1261,6 +1267,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index ec981618b..22e9ff592 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1109,6 +1109,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ipt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1117,6 +1119,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1493,6 +1497,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ipt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1501,6 +1507,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d360c7d70..cc409cc07 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -955,13 +955,11 @@ void ip_rt_send_redirect(struct sk_buff *skb) icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->n_redirects; -#ifdef CONFIG_IP_ROUTE_VERBOSE - if (log_martians && + if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians && peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); -#endif } out_put_peer: inet_putpeer(peer); @@ -2090,6 +2088,9 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, int err = -EINVAL; u32 tag = 0; + if (!in_dev) + return -EINVAL; + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3dd9b76f4..ac6cb2dc6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -726,6 +726,7 @@ void tcp_push(struct sock *sk, int flags, int mss_now, if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING); set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); + smp_mb__after_atomic(); } /* It is possible TX completion already happened * before we set TSQ_THROTTLED. @@ -1777,6 +1778,36 @@ static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, return frag; } +static bool can_map_frag(const skb_frag_t *frag) +{ + struct page *page; + + if (skb_frag_size(frag) != PAGE_SIZE || skb_frag_off(frag)) + return false; + + page = skb_frag_page(frag); + + if (PageCompound(page) || page->mapping) + return false; + + return true; +} + +static int find_next_mappable_frag(const skb_frag_t *frag, + int remaining_in_skb) +{ + int offset = 0; + + if (likely(can_map_frag(frag))) + return 0; + + while (offset < remaining_in_skb && !can_map_frag(frag)) { + offset += skb_frag_size(frag); + ++frag; + } + return offset; +} + static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 copylen, u32 *offset, u32 *seq) @@ -1902,6 +1933,8 @@ static int tcp_zerocopy_receive(struct sock *sk, ret = 0; curr_addr = address; while (length + PAGE_SIZE <= zc->length) { + int mappable_offset; + if (zc->recv_skip_hint < PAGE_SIZE) { u32 offset_frag; @@ -1929,15 +1962,11 @@ static int tcp_zerocopy_receive(struct sock *sk, if (!frags || offset_frag) break; } - if (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags)) { - int remaining = zc->recv_skip_hint; - while (remaining && (skb_frag_size(frags) != PAGE_SIZE || - skb_frag_off(frags))) { - remaining -= skb_frag_size(frags); - frags++; - } - zc->recv_skip_hint -= remaining; + mappable_offset = find_next_mappable_frag(frags, + zc->recv_skip_hint); + if (mappable_offset) { + zc->recv_skip_hint = mappable_offset; break; } pages[pg_idx] = skb_frag_page(frags); @@ -2688,6 +2717,8 @@ void tcp_close(struct sock *sk, long timeout) lock_sock(sk); __tcp_close(sk, timeout); release_sock(sk); + if (!sk->sk_net_refcnt) + inet_csk_clear_xmit_timers_sync(sk); sock_put(sk); } EXPORT_SYMBOL(tcp_close); @@ -3713,11 +3744,11 @@ static int do_tcp_getsockopt(struct sock *sk, int level, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 476f79f15..16ff3962b 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -602,6 +602,13 @@ static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk, } DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); +EXPORT_SYMBOL(udp_encap_needed_key); + +#if IS_ENABLED(CONFIG_IPV6) +DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +EXPORT_SYMBOL(udpv6_encap_needed_key); +#endif + void udp_encap_enable(void) { static_branch_inc(&udp_encap_needed_key); @@ -1118,16 +1125,17 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = udp_cmsg_send(sk, msg, &ipc.gso_size); - if (err > 0) + if (err > 0) { err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6); + connected = 0; + } if (unlikely(err < 0)) { kfree(ipc.opt); return err; } if (ipc.opt) free = 1; - connected = 0; } if (!ipc.opt) { struct ip_options_rcu *inet_opt; @@ -2748,11 +2756,11 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case UDP_CORK: val = READ_ONCE(up->corkflag); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index f4b8e5606..445d8bc30 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -512,6 +512,11 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, unsigned int off = skb_gro_offset(skb); int flush = 1; + /* We can do L4 aggregation only if the packet can't land in a tunnel + * otherwise we could corrupt the inner stream. Detecting such packets + * cannot be foolproof and the aggregation might still happen in some + * cases. Such packets should be caught in udp_unexpected_gso later. + */ NAPI_GRO_CB(skb)->is_flist = 0; if (skb->dev->features & NETIF_F_GRO_FRAGLIST) NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled: 1; @@ -668,13 +673,7 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { - if (skb->csum_level < SKB_MAX_CSUM_LEVEL) - skb->csum_level++; - } else { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = 0; - } + __skb_incr_checksum_unnecessary(skb); return 0; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 79787a1f5..8a6f4cdd5 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -698,6 +698,22 @@ errout: return err; } +/* Combine dev_addr_genid and dev_base_seq to detect changes. + */ +static u32 inet6_base_seq(const struct net *net) +{ + u32 res = atomic_read(&net->ipv6.dev_addr_genid) + + net->dev_base_seq; + + /* Must not return 0 (see nl_dump_check_consistent()). + * Chose a value far away from 0. + */ + if (!res) + res = 0x80000000; + return res; +} + + static int inet6_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { @@ -731,8 +747,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb, idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = inet6_base_seq(net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -2029,9 +2044,10 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add if (ipv6_addr_equal(&ifp->addr, addr)) { if (!dev || ifp->idev->dev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) { - result = ifp; - in6_ifa_hold(ifp); - break; + if (in6_ifa_hold_safe(ifp)) { + result = ifp; + break; + } } } } @@ -5288,7 +5304,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, } rcu_read_lock(); - cb->seq = atomic_read(&tgt_net->ipv6.dev_addr_genid) ^ tgt_net->dev_base_seq; + cb->seq = inet6_base_seq(tgt_net); for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &tgt_net->dev_index_head[h]; @@ -5421,9 +5437,10 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, } addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); - if (!addr) - return -EINVAL; - + if (!addr) { + err = -EINVAL; + goto errout; + } ifm = nlmsg_data(nlh); if (ifm->ifa_index) dev = dev_get_by_index(tgt_net, ifm->ifa_index); diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index c70c192bc..5e0e2b5ba 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -213,19 +213,26 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { EXPORT_SYMBOL_GPL(ipv6_stub); /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ -const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT; +const struct in6_addr in6addr_loopback __aligned(BITS_PER_LONG/8) + = IN6ADDR_LOOPBACK_INIT; EXPORT_SYMBOL(in6addr_loopback); -const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT; +const struct in6_addr in6addr_any __aligned(BITS_PER_LONG/8) + = IN6ADDR_ANY_INIT; EXPORT_SYMBOL(in6addr_any); -const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT; +const struct in6_addr in6addr_linklocal_allnodes __aligned(BITS_PER_LONG/8) + = IN6ADDR_LINKLOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_linklocal_allnodes); -const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_linklocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_linklocal_allrouters); -const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; +const struct in6_addr in6addr_interfacelocal_allnodes __aligned(BITS_PER_LONG/8) + = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allnodes); -const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_interfacelocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allrouters); -const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_sitelocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_sitelocal_allrouters); static void snmp6_free_dev(struct inet6_dev *idev) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 424799707..329b3b366 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -197,6 +197,9 @@ lookup_protocol: if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; + if (INET_PROTOSW_ICSK & answer_flags) + inet_init_csk_locks(sk); + inet = inet_sk(sk); inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 3e4c87b29..55cd23b7a 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -446,6 +446,11 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) + nla_total_size(16); /* src */ } +static void fib6_rule_flush_cache(struct fib_rules_ops *ops) +{ + rt_genid_bump_ipv6(ops->fro_net); +} + static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .family = AF_INET6, .rule_size = sizeof(struct fib6_rule), @@ -458,6 +463,7 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .compare = fib6_rule_compare, .fill = fib6_rule_fill, .nlmsg_payload = fib6_rule_nlmsg_payload, + .flush_cache = fib6_rule_flush_cache, .nlgroup = RTNLGRP_IPV6_RULE, .policy = fib6_rule_policy, .owner = THIS_MODULE, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 608205c63..b79e571e5 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -643,19 +643,19 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (!w) { /* New dump: * - * 1. hook callback destructor. - */ - cb->args[3] = (long)cb->done; - cb->done = fib6_dump_done; - - /* - * 2. allocate and initialize walker. + * 1. allocate and initialize walker. */ w = kzalloc(sizeof(*w), GFP_ATOMIC); if (!w) return -ENOMEM; w->func = fib6_dump_node; cb->args[2] = (long)w; + + /* 2. hook callback destructor. + */ + cb->args[3] = (long)cb->done; + cb->done = fib6_dump_done; + } arg.skb = skb; @@ -1373,7 +1373,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { struct fib6_table *table = rt->fib6_table; - struct fib6_node *fn, *pn = NULL; + struct fib6_node *fn; +#ifdef CONFIG_IPV6_SUBTREES + struct fib6_node *pn = NULL; +#endif int err = -ENOMEM; int allow_create = 1; int replace_required = 0; @@ -1397,9 +1400,9 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, goto out; } +#ifdef CONFIG_IPV6_SUBTREES pn = fn; -#ifdef CONFIG_IPV6_SUBTREES if (rt->fib6_src.plen) { struct fib6_node *sn; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 2df103633..13ac0ccdc 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -533,6 +533,9 @@ static int ip6erspan_rcv(struct sk_buff *skb, struct ip6_tnl *tunnel; u8 ver; + if (unlikely(!pskb_may_pull(skb, sizeof(*ershdr)))) + return PACKET_REJECT; + ipv6h = ipv6_hdr(skb); ershdr = (struct erspan_base_hdr *)skb->data; ver = ershdr->ver; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index edf4a8425..d1f819238 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -829,9 +829,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, struct sk_buff *skb), bool log_ecn_err) { - struct pcpu_sw_netstats *tstats; - const struct ipv6hdr *ipv6h = ipv6_hdr(skb); - int err; + const struct ipv6hdr *ipv6h; + int nh, err; if ((!(tpi->flags & TUNNEL_CSUM) && (tunnel->parms.i_flags & TUNNEL_CSUM)) || @@ -863,14 +862,29 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, goto drop; } - ipv6h = ipv6_hdr(skb); skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { skb->dev = tunnel->dev; } + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_reset_network_header(skb); + + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(tunnel->dev, rx_length_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); + goto drop; + } + + /* Get the outer header. */ + ipv6h = (struct ipv6hdr *)(skb->head + nh); + memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); @@ -888,11 +902,7 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, } } - tstats = this_cpu_ptr(tunnel->dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); + dev_sw_netstats_rx_add(tunnel->dev, skb->len); skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 7b4b457a8..0ac527cd5 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -225,7 +225,7 @@ static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) goto out_free_gsf; - ret = ip6_mc_msfilter(sk, gsf, gsf->gf_slist); + ret = ip6_mc_msfilter(sk, gsf, gsf->gf_slist_flex); out_free_gsf: kfree(gsf); return ret; @@ -234,7 +234,7 @@ out_free_gsf: static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) { - const int size0 = offsetof(struct compat_group_filter, gf_slist); + const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter *gf32; void *p; int ret; @@ -249,7 +249,7 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (!p) return -ENOMEM; - gf32 = p + 4; /* we want ->gf_group and ->gf_slist aligned */ + gf32 = p + 4; /* we want ->gf_group and ->gf_slist_flex aligned */ ret = -EFAULT; if (copy_from_sockptr(gf32, optval, optlen)) goto out_free_p; @@ -261,14 +261,14 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, goto out_free_p; ret = -EINVAL; - if (offsetof(struct compat_group_filter, gf_slist[n]) > optlen) + if (offsetof(struct compat_group_filter, gf_slist_flex[n]) > optlen) goto out_free_p; ret = ip6_mc_msfilter(sk, &(struct group_filter){ .gf_interface = gf32->gf_interface, .gf_group = gf32->gf_group, .gf_fmode = gf32->gf_fmode, - .gf_numsrc = gf32->gf_numsrc}, gf32->gf_slist); + .gf_numsrc = gf32->gf_numsrc}, gf32->gf_slist_flex); out_free_p: kfree(p); @@ -1051,7 +1051,7 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt, static int ipv6_get_msfilter(struct sock *sk, void __user *optval, int __user *optlen, int len) { - const int size0 = offsetof(struct group_filter, gf_slist); + const int size0 = offsetof(struct group_filter, gf_slist_flex); struct group_filter __user *p = optval; struct group_filter gsf; int num; @@ -1065,7 +1065,7 @@ static int ipv6_get_msfilter(struct sock *sk, void __user *optval, return -EADDRNOTAVAIL; num = gsf.gf_numsrc; lock_sock(sk); - err = ip6_mc_msfget(sk, &gsf, p->gf_slist); + err = ip6_mc_msfget(sk, &gsf, p->gf_slist_flex); if (!err) { if (num > gsf.gf_numsrc) num = gsf.gf_numsrc; @@ -1080,7 +1080,7 @@ static int ipv6_get_msfilter(struct sock *sk, void __user *optval, static int compat_ipv6_get_msfilter(struct sock *sk, void __user *optval, int __user *optlen) { - const int size0 = offsetof(struct compat_group_filter, gf_slist); + const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter __user *p = optval; struct compat_group_filter gf32; struct group_filter gf; @@ -1103,7 +1103,7 @@ static int compat_ipv6_get_msfilter(struct sock *sk, void __user *optval, return -EADDRNOTAVAIL; lock_sock(sk); - err = ip6_mc_msfget(sk, &gf, p->gf_slist); + err = ip6_mc_msfget(sk, &gf, p->gf_slist_flex); release_sock(sk); if (err) return err; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 99bb11d16..df7cd3d28 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1127,6 +1127,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ip6t_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1135,6 +1137,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1503,6 +1507,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ip6t_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1511,6 +1517,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b23e42efb..2d53c362f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5235,19 +5235,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, next) { err = __ip6_ins_rt(nh->fib6_info, info, extack); - fib6_info_release(nh->fib6_info); - - if (!err) { - /* save reference to last route successfully inserted */ - rt_last = nh->fib6_info; - - /* save reference to first route for notification */ - if (!rt_notif) - rt_notif = nh->fib6_info; - } - /* nh->fib6_info is used or freed at this point, reset to NULL*/ - nh->fib6_info = NULL; if (err) { if (replace && nhn) NL_SET_ERR_MSG_MOD(extack, @@ -5255,6 +5243,12 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, err_nh = nh; goto add_errout; } + /* save reference to last route successfully inserted */ + rt_last = nh->fib6_info; + + /* save reference to first route for notification */ + if (!rt_notif) + rt_notif = nh->fib6_info; /* Because each route is added like a single route we remove * these flags after the first nexthop: if there is a collision, @@ -5315,8 +5309,7 @@ add_errout: cleanup: list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { - if (nh->fib6_info) - fib6_info_release(nh->fib6_info); + fib6_info_release(nh->fib6_info); list_del(&nh->next); kfree(nh); } diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 2278c0234..a8439fded 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -451,22 +451,24 @@ int __init seg6_init(void) { int err; - err = genl_register_family(&seg6_genl_family); + err = register_pernet_subsys(&ip6_segments_ops); if (err) goto out; - err = register_pernet_subsys(&ip6_segments_ops); + err = genl_register_family(&seg6_genl_family); if (err) - goto out_unregister_genl; + goto out_unregister_pernet; #ifdef CONFIG_IPV6_SEG6_LWTUNNEL err = seg6_iptunnel_init(); if (err) - goto out_unregister_pernet; + goto out_unregister_genl; err = seg6_local_init(); - if (err) - goto out_unregister_pernet; + if (err) { + seg6_iptunnel_exit(); + goto out_unregister_genl; + } #endif #ifdef CONFIG_IPV6_SEG6_HMAC @@ -487,11 +489,11 @@ out_unregister_iptun: #endif #endif #ifdef CONFIG_IPV6_SEG6_LWTUNNEL -out_unregister_pernet: - unregister_pernet_subsys(&ip6_segments_ops); -#endif out_unregister_genl: genl_unregister_family(&seg6_genl_family); +#endif +out_unregister_pernet: + unregister_pernet_subsys(&ip6_segments_ops); goto out; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 538503720..8c9672e7a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -474,7 +474,7 @@ csum_copy_err: goto try_again; } -DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void) { static_branch_inc(&udpv6_encap_needed_key); @@ -1453,9 +1453,11 @@ do_udp_sendmsg: ipc6.opt = opt; err = udp_cmsg_send(sk, msg, &ipc6.gso_size); - if (err > 0) + if (err > 0) { err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); + connected = false; + } if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -1467,7 +1469,6 @@ do_udp_sendmsg: } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; - connected = false; } if (!opt) { opt = txopt_get(np); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index ebee748f2..7752e1e92 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -169,13 +169,7 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { - if (skb->csum_level < SKB_MAX_CSUM_LEVEL) - skb->csum_level++; - } else { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = 0; - } + __skb_incr_checksum_unnecessary(skb); return 0; } diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index e14368ced..7c73faa53 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -2310,7 +2310,7 @@ static int __init afiucv_init(void) { int err; - if (MACHINE_IS_VM) { + if (MACHINE_IS_VM && IS_ENABLED(CONFIG_IUCV)) { cpcmd("QUERY USERID", iucv_userid, sizeof(iucv_userid), &err); if (unlikely(err)) { WARN_ON(err); @@ -2318,11 +2318,7 @@ static int __init afiucv_init(void) goto out; } - pr_iucv = try_then_request_module(symbol_get(iucv_if), "iucv"); - if (!pr_iucv) { - printk(KERN_WARNING "iucv_if lookup failed\n"); - memset(&iucv_userid, 0, sizeof(iucv_userid)); - } + pr_iucv = &iucv_if; } else { memset(&iucv_userid, 0, sizeof(iucv_userid)); pr_iucv = NULL; @@ -2356,17 +2352,13 @@ out_sock: out_proto: proto_unregister(&iucv_proto); out: - if (pr_iucv) - symbol_put(iucv_if); return err; } static void __exit afiucv_exit(void) { - if (pr_iucv) { + if (pr_iucv) afiucv_iucv_exit(); - symbol_put(iucv_if); - } unregister_netdevice_notifier(&afiucv_netdev_notifier); dev_remove_pack(&iucv_packet_type); diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 6f84978a7..ed0dbdbba 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -156,7 +156,7 @@ static char iucv_error_pathid[16] = "INVALID PATHID"; static LIST_HEAD(iucv_handler_list); /* - * iucv_path_table: an array of iucv_path structures. + * iucv_path_table: array of pointers to iucv_path structures. */ static struct iucv_path **iucv_path_table; static unsigned long iucv_max_pathid; @@ -542,7 +542,7 @@ static int iucv_enable(void) get_online_cpus(); rc = -ENOMEM; - alloc_size = iucv_max_pathid * sizeof(struct iucv_path); + alloc_size = iucv_max_pathid * sizeof(*iucv_path_table); iucv_path_table = kzalloc(alloc_size, GFP_KERNEL); if (!iucv_path_table) goto out; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 39b3c7fbf..7420b4f19 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1275,10 +1275,11 @@ static int kcm_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case KCM_RECV_DISABLE: val = kcm->rx_disabled; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 9746c624a..eb3d81bcc 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -628,7 +628,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) back_from_confirm: lock_sock(sk); - ulen = len + skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0; + ulen = len + (skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0); err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, &ipc6, &fl6, (struct rt6_info *)dst, diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 5ecc0f200..b1d89c850 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1357,11 +1357,11 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + err = -ENOTCONN; if (!sk->sk_user_data) goto end; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 01e266982..dae978bad 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -227,6 +227,8 @@ static int llc_ui_release(struct socket *sock) if (llc->dev) dev_put(llc->dev); sock_put(sk); + sock_orphan(sk); + sock->sk = NULL; llc_sk_free(sk); out: return 0; @@ -927,14 +929,15 @@ copy_uaddr: */ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { + DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); - DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); int flags = msg->msg_flags; int noblock = flags & MSG_DONTWAIT; + int rc = -EINVAL, copied = 0, hdrlen, hh_len; struct sk_buff *skb = NULL; + struct net_device *dev; size_t size = 0; - int rc = -EINVAL, copied = 0, hdrlen; dprintk("%s: sending from %02X to %02X\n", __func__, llc->laddr.lsap, llc->daddr.lsap); @@ -954,22 +957,29 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (rc) goto out; } - hdrlen = llc->dev->hard_header_len + llc_ui_header_len(sk, addr); + dev = llc->dev; + hh_len = LL_RESERVED_SPACE(dev); + hdrlen = llc_ui_header_len(sk, addr); size = hdrlen + len; - if (size > llc->dev->mtu) - size = llc->dev->mtu; + size = min_t(size_t, size, READ_ONCE(dev->mtu)); copied = size - hdrlen; rc = -EINVAL; if (copied < 0) goto out; release_sock(sk); - skb = sock_alloc_send_skb(sk, size, noblock, &rc); + skb = sock_alloc_send_skb(sk, hh_len + size, noblock, &rc); lock_sock(sk); if (!skb) goto out; - skb->dev = llc->dev; + if (sock_flag(sk, SOCK_ZAPPED) || + llc->dev != dev || + hdrlen != llc_ui_header_len(sk, addr) || + hh_len != LL_RESERVED_SPACE(dev) || + size > READ_ONCE(dev->mtu)) + goto out; + skb->dev = dev; skb->protocol = llc_proto_type(addr->sllc_arphrd); - skb_reserve(skb, hdrlen); + skb_reserve(skb, hh_len + hdrlen); rc = memcpy_from_msg(skb_put(skb, copied), msg, copied); if (rc) goto out; diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index 64d4bef04..4900a27b5 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -135,22 +135,15 @@ static struct packet_type llc_packet_type __read_mostly = { .func = llc_rcv, }; -static struct packet_type llc_tr_packet_type __read_mostly = { - .type = cpu_to_be16(ETH_P_TR_802_2), - .func = llc_rcv, -}; - static int __init llc_init(void) { dev_add_pack(&llc_packet_type); - dev_add_pack(&llc_tr_packet_type); return 0; } static void __exit llc_exit(void) { dev_remove_pack(&llc_packet_type); - dev_remove_pack(&llc_tr_packet_type); } module_init(llc_init); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 45bb6f275..0c3da7771 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1811,15 +1811,14 @@ static int ieee80211_change_station(struct wiphy *wiphy, } if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && - sta->sdata->u.vlan.sta) { - ieee80211_clear_fast_rx(sta); + sta->sdata->u.vlan.sta) RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL); - } if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ieee80211_vif_dec_num_mcast(sta->sdata); sta->sdata = vlansdata; + ieee80211_check_fast_rx(sta); ieee80211_check_fast_xmit(sta); if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 2e8436099..44bd03c6b 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -700,6 +700,8 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) if (ieee80211_vif_is_mesh(&sdata->vif)) mesh_accept_plinks_update(sdata); + ieee80211_check_fast_xmit(sta); + return 0; out_remove: sta_info_hash_del(local, sta); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 788b6a3c1..0d6d12fc3 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2959,7 +2959,7 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) sdata->vif.type == NL80211_IFTYPE_STATION) goto out; - if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED) || !sta->uploaded) goto out; if (test_sta_flag(sta, WLAN_STA_PS_STA) || @@ -3721,6 +3721,7 @@ begin: goto begin; skb = __skb_dequeue(&tx.skbs); + info = IEEE80211_SKB_CB(skb); if (!skb_queue_empty(&tx.skbs)) { spin_lock_bh(&fq->lock); @@ -3765,7 +3766,7 @@ begin: } encap_out: - IEEE80211_SKB_CB(skb)->control.vif = vif; + info->control.vif = vif; if (vif && wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index 55550ead2..a4cc9d077 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -265,19 +265,27 @@ fail: return -ENOMEM; } +static void mac802154_llsec_key_del_rcu(struct rcu_head *rcu) +{ + struct ieee802154_llsec_key_entry *pos; + struct mac802154_llsec_key *mkey; + + pos = container_of(rcu, struct ieee802154_llsec_key_entry, rcu); + mkey = container_of(pos->key, struct mac802154_llsec_key, key); + + llsec_key_put(mkey); + kfree_sensitive(pos); +} + int mac802154_llsec_key_del(struct mac802154_llsec *sec, const struct ieee802154_llsec_key_id *key) { struct ieee802154_llsec_key_entry *pos; list_for_each_entry(pos, &sec->table.keys, list) { - struct mac802154_llsec_key *mkey; - - mkey = container_of(pos->key, struct mac802154_llsec_key, key); - if (llsec_key_id_equal(&pos->id, key)) { list_del_rcu(&pos->list); - llsec_key_put(mkey); + call_rcu(&pos->rcu, mac802154_llsec_key_del_rcu); return 0; } } diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index a53658674..d7ca71c59 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -13,17 +13,22 @@ #include <uapi/linux/mptcp.h> #include "protocol.h" -static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) +static int subflow_get_info(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *sf; struct nlattr *start; u32 flags = 0; + bool slow; int err; + if (inet_sk_state_load(sk) == TCP_LISTEN) + return 0; + start = nla_nest_start_noflag(skb, INET_ULP_INFO_MPTCP); if (!start) return -EMSGSIZE; + slow = lock_sock_fast(sk); rcu_read_lock(); sf = rcu_dereference(inet_csk(sk)->icsk_ulp_data); if (!sf) { @@ -69,11 +74,13 @@ static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) } rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_end(skb, start); return 0; nla_failure: rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_cancel(skb, start); return err; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 72d944e6a..6be7e7592 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2052,8 +2052,50 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } + +static void mptcp_copy_ip6_options(struct sock *newsk, const struct sock *sk) +{ + const struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_txoptions *opt; + struct ipv6_pinfo *newnp; + + newnp = inet6_sk(newsk); + + rcu_read_lock(); + opt = rcu_dereference(np->opt); + if (opt) { + opt = ipv6_dup_options(newsk, opt); + if (!opt) + net_warn_ratelimited("%s: Failed to copy ip6 options\n", __func__); + } + RCU_INIT_POINTER(newnp->opt, opt); + rcu_read_unlock(); +} #endif +static void mptcp_copy_ip_options(struct sock *newsk, const struct sock *sk) +{ + struct ip_options_rcu *inet_opt, *newopt = NULL; + const struct inet_sock *inet = inet_sk(sk); + struct inet_sock *newinet; + + newinet = inet_sk(newsk); + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt) { + newopt = sock_kmalloc(newsk, sizeof(*inet_opt) + + inet_opt->opt.optlen, GFP_ATOMIC); + if (newopt) + memcpy(newopt, inet_opt, sizeof(*inet_opt) + + inet_opt->opt.optlen); + else + net_warn_ratelimited("%s: Failed to copy ip options\n", __func__); + } + RCU_INIT_POINTER(newinet->inet_opt, newopt); + rcu_read_unlock(); +} + struct sock *mptcp_sk_clone(const struct sock *sk, const struct mptcp_options_received *mp_opt, struct request_sock *req) @@ -2073,6 +2115,13 @@ struct sock *mptcp_sk_clone(const struct sock *sk, __mptcp_init_sock(nsk); +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if (nsk->sk_family == AF_INET6) + mptcp_copy_ip6_options(nsk, sk); + else +#endif + mptcp_copy_ip_options(nsk, sk); + msk = mptcp_sk(nsk); msk->local_key = subflow_req->local_key; msk->token = subflow_req->token; @@ -2169,9 +2218,6 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK); local_bh_enable(); - } else { - MPTCP_INC_STATS(sock_net(sk), - MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); } out: diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 607519246..276fe9f44 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -595,6 +595,9 @@ create_child: if (fallback_is_fatal) goto dispose_child; + if (fallback) + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); + subflow_drop_ctx(child); goto out; } diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 26ab0e961..9523104a9 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -28,6 +28,7 @@ #define mtype_del IPSET_TOKEN(MTYPE, _del) #define mtype_list IPSET_TOKEN(MTYPE, _list) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype MTYPE #define get_ext(set, map, id) ((map)->extensions + ((set)->dsize * (id))) @@ -57,9 +58,6 @@ mtype_destroy(struct ip_set *set) { struct mtype *map = set->data; - if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&map->gc); - if (set->dsize && set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set); ip_set_free(map->members); @@ -288,6 +286,15 @@ mtype_gc(struct timer_list *t) add_timer(&map->gc); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct mtype *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + del_timer_sync(&map->gc); +} + static const struct ip_set_type_variant mtype = { .kadt = mtype_kadt, .uadt = mtype_uadt, @@ -301,6 +308,7 @@ static const struct ip_set_type_variant mtype = { .head = mtype_head, .list = mtype_list, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, }; #endif /* __IP_SET_BITMAP_IP_GEN_H */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 24f81826e..cc04c4d79 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1158,6 +1158,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl, return ret; cleanup: + set->variant->cancel_gc(set); set->variant->destroy(set); put_out: module_put(set->type->me); @@ -1186,6 +1187,14 @@ ip_set_destroy_set(struct ip_set *set) kfree(set); } +static void +ip_set_destroy_set_rcu(struct rcu_head *head) +{ + struct ip_set *set = container_of(head, struct ip_set, rcu); + + ip_set_destroy_set(set); +} + static int ip_set_destroy(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const attr[], @@ -1199,8 +1208,6 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl, if (unlikely(protocol_min_failed(attr))) return -IPSET_ERR_PROTOCOL; - /* Must wait for flush to be really finished in list:set */ - rcu_barrier(); /* Commands are serialized and references are * protected by the ip_set_ref_lock. @@ -1212,8 +1219,10 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl, * counter, so if it's already zero, we can proceed * without holding the lock. */ - read_lock_bh(&ip_set_ref_lock); if (!attr[IPSET_ATTR_SETNAME]) { + /* Must wait for flush to be really finished in list:set */ + rcu_barrier(); + read_lock_bh(&ip_set_ref_lock); for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); if (s && (s->ref || s->ref_netlink)) { @@ -1227,12 +1236,17 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl, s = ip_set(inst, i); if (s) { ip_set(inst, i) = NULL; + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); ip_set_destroy_set(s); } } /* Modified by ip_set_destroy() only, which is serialized */ inst->is_destroyed = false; } else { + u16 features = 0; + + read_lock_bh(&ip_set_ref_lock); s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]), &i); if (!s) { @@ -1242,10 +1256,16 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl, ret = -IPSET_ERR_BUSY; goto out; } + features = s->type->features; ip_set(inst, i) = NULL; read_unlock_bh(&ip_set_ref_lock); - - ip_set_destroy_set(s); + if (features & IPSET_TYPE_NAME) { + /* Must wait for flush to be really finished */ + rcu_barrier(); + } + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); + call_rcu(&s->rcu, ip_set_destroy_set_rcu); } return 0; out: @@ -1404,9 +1424,6 @@ static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb, ip_set(inst, to_id) = from; write_unlock_bh(&ip_set_ref_lock); - /* Make sure all readers of the old set pointers are completed. */ - synchronize_rcu(); - return 0; } @@ -2397,6 +2414,7 @@ ip_set_net_exit(struct net *net) set = ip_set(inst, i); if (set) { ip_set(inst, i) = NULL; + set->variant->cancel_gc(set); ip_set_destroy_set(set); } } @@ -2444,8 +2462,11 @@ ip_set_fini(void) { nf_unregister_sockopt(&so_set); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); - unregister_pernet_subsys(&ip_set_net_ops); + + /* Wait for call_rcu() in destroy */ + rcu_barrier(); + pr_debug("these are the famous last words\n"); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index b0670388d..093ec5214 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -235,6 +235,7 @@ htable_size(u8 hbits) #undef mtype_gc_do #undef mtype_gc #undef mtype_gc_init +#undef mtype_cancel_gc #undef mtype_variant #undef mtype_data_match @@ -279,6 +280,7 @@ htable_size(u8 hbits) #define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) #define mtype_data_match IPSET_TOKEN(MTYPE, _data_match) @@ -444,7 +446,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) u32 i; for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference(hbucket(t, i)); + n = (__force struct hbucket *)hbucket(t, i); if (!n) continue; if (set->extensions & IPSET_EXT_DESTROY && ext_destroy) @@ -464,10 +466,7 @@ mtype_destroy(struct ip_set *set) struct htype *h = set->data; struct list_head *l, *lt; - if (SET_WITH_TIMEOUT(set)) - cancel_delayed_work_sync(&h->gc.dwork); - - mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true); + mtype_ahash_destroy(set, (__force struct htable *)h->table, true); list_for_each_safe(l, lt, &h->ad) { list_del(l); kfree(l); @@ -613,6 +612,15 @@ mtype_gc_init(struct htable_gc *gc) queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct htype *h = set->data; + + if (SET_WITH_TIMEOUT(set)) + cancel_delayed_work_sync(&h->gc.dwork); +} + static int mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags); @@ -1433,6 +1441,7 @@ static const struct ip_set_type_variant mtype_variant = { .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, .region_lock = true, }; diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 5a67f7966..6bc701998 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -426,9 +426,6 @@ list_set_destroy(struct ip_set *set) struct list_set *map = set->data; struct set_elem *e, *n; - if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&map->gc); - list_for_each_entry_safe(e, n, &map->members, list) { list_del(&e->list); ip_set_put_byindex(map->net, e->id); @@ -545,6 +542,15 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b) a->extensions == b->extensions; } +static void +list_set_cancel_gc(struct ip_set *set) +{ + struct list_set *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + del_timer_sync(&map->gc); +} + static const struct ip_set_type_variant set_variant = { .kadt = list_set_kadt, .uadt = list_set_uadt, @@ -558,6 +564,7 @@ static const struct ip_set_type_variant set_variant = { .head = list_set_head, .list = list_set_list, .same_set = list_set_same_set, + .cancel_gc = list_set_cancel_gc, }; static void diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index a0921adc3..1e689c714 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -126,7 +126,8 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, if (sctph->source != cp->vport || payload_csum || skb->ip_summed == CHECKSUM_PARTIAL) { sctph->source = cp->vport; - sctp_nat_csum(skb, sctph, sctphoff); + if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + sctp_nat_csum(skb, sctph, sctphoff); } else { skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -174,7 +175,8 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, (skb->ip_summed == CHECKSUM_PARTIAL && !(skb_dst(skb)->dev->features & NETIF_F_SCTP_CRC))) { sctph->dest = cp->dport; - sctp_nat_csum(skb, sctph, sctphoff); + if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + sctp_nat_csum(skb, sctph, sctphoff); } else if (skb->ip_summed != CHECKSUM_PARTIAL) { skb->ip_summed = CHECKSUM_UNNECESSARY; } diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index e697a824b..540d97715 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -533,6 +533,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, /* Get fields bitmap */ if (nf_h323_error_boundary(bs, 0, f->sz)) return H323_ERROR_BOUND; + if (f->sz > 32) + return H323_ERROR_RANGE; bmp = get_bitmap(bs, f->sz); if (base) *(unsigned int *)base = bmp; @@ -589,6 +591,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, bmp2_len = get_bits(bs, 7) + 1; if (nf_h323_error_boundary(bs, 0, bmp2_len)) return H323_ERROR_BOUND; + if (bmp2_len > 32) + return H323_ERROR_RANGE; bmp2 = get_bitmap(bs, bmp2_len); bmp |= bmp2 >> f->sz; if (base) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index e7545bcca..6b2a215b2 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -299,7 +299,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb, pr_debug("Setting vtag %x for secondary conntrack\n", sh->vtag); ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag; - } else { + } else if (sch->type == SCTP_CID_SHUTDOWN_ACK) { /* If it is a shutdown ack OOTB packet, we expect a return shutdown complete, otherwise an ABORT Sec 8.4 (5) and (8) */ pr_debug("Setting vtag %x for new conn OOTB\n", diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 6cb9f9474..28c6cb5cf 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -203,11 +203,12 @@ void nf_logger_put(int pf, enum nf_log_type type) return; } - BUG_ON(loggers[pf][type] == NULL); - rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); - module_put(logger->me); + if (!logger) + WARN_ON_ONCE(1); + else + module_put(logger->me); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_logger_put); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fca8f9a36..858d09b54 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -25,6 +25,7 @@ #include <net/sock.h> #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-")) +#define NFT_SET_MAX_ANONLEN 16 unsigned int nf_tables_net_id __read_mostly; @@ -1083,6 +1084,24 @@ static void nf_tables_table_disable(struct net *net, struct nft_table *table) #define __NFT_TABLE_F_UPDATE (__NFT_TABLE_F_WAS_DORMANT | \ __NFT_TABLE_F_WAS_AWAKEN) +static bool nft_table_pending_update(const struct nft_ctx *ctx) +{ + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); + struct nft_trans *trans; + + if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + return true; + + list_for_each_entry(trans, &nft_net->commit_list, list) { + if (trans->ctx.table == ctx->table && + trans->msg_type == NFT_MSG_DELCHAIN && + nft_is_base_chain(trans->ctx.chain)) + return true; + } + + return false; +} + static int nf_tables_updtable(struct nft_ctx *ctx) { struct nft_trans *trans; @@ -1096,11 +1115,11 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if (flags & ~NFT_TABLE_F_DORMANT) return -EINVAL; - if (flags == ctx->table->flags) + if (flags == (ctx->table->flags & NFT_TABLE_F_MASK)) return 0; /* No dormant off/on/off/on games in single transaction */ - if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + if (nft_table_pending_update(ctx)) return -EINVAL; trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, @@ -1131,6 +1150,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) return 0; err_register_hooks: + ctx->table->flags |= NFT_TABLE_F_DORMANT; nft_trans_destroy(trans); return ret; } @@ -2223,6 +2243,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct nft_stats __percpu *stats = NULL; struct nft_chain_hook hook; + if (table->flags & __NFT_TABLE_F_UPDATE) + return -EINVAL; + if (flags & NFT_CHAIN_BINDING) return -EOPNOTSUPP; @@ -2716,7 +2739,7 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family, { const struct nft_expr_type *type, *candidate = NULL; - list_for_each_entry(type, &nf_tables_expressions, list) { + list_for_each_entry_rcu(type, &nf_tables_expressions, list) { if (!nla_strcmp(nla, type->name)) { if (!type->family && !candidate) candidate = type; @@ -2748,9 +2771,13 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net, if (nla == NULL) return ERR_PTR(-EINVAL); + rcu_read_lock(); type = __nft_expr_type_get(family, nla); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -3930,6 +3957,9 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, if (p[1] != 'd' || strchr(p + 2, '%')) return -EINVAL; + if (strnlen(name, NFT_SET_MAX_ANONLEN) >= NFT_SET_MAX_ANONLEN) + return -EINVAL; + inuse = (unsigned long *)get_zeroed_page(GFP_KERNEL); if (inuse == NULL) return -ENOMEM; @@ -4405,6 +4435,12 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if ((flags & (NFT_SET_EVAL | NFT_SET_OBJECT)) == (NFT_SET_EVAL | NFT_SET_OBJECT)) return -EOPNOTSUPP; + if ((flags & (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT | NFT_SET_EVAL)) == + (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; + if ((flags & (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) == + (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; } dtype = 0; @@ -4446,6 +4482,9 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; + if (flags & NFT_SET_ANONYMOUS) + return -EOPNOTSUPP; + err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &timeout); if (err) return err; @@ -4454,6 +4493,10 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_GC_INTERVAL] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; + + if (flags & NFT_SET_ANONYMOUS) + return -EOPNOTSUPP; + gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL])); } @@ -4749,6 +4792,7 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) { list_del_rcu(&set->list); + set->dead = 1; if (event) nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_KERNEL); @@ -6857,11 +6901,12 @@ static int nft_flowtable_parse_hook(const struct nft_ctx *ctx, return err; } +/* call under rcu_read_lock */ static const struct nf_flowtable_type *__nft_flowtable_type_get(u8 family) { const struct nf_flowtable_type *type; - list_for_each_entry(type, &nf_tables_flowtables, list) { + list_for_each_entry_rcu(type, &nf_tables_flowtables, list) { if (family == type->family) return type; } @@ -6873,9 +6918,13 @@ nft_flowtable_type_get(struct net *net, u8 family) { const struct nf_flowtable_type *type; + rcu_read_lock(); type = __nft_flowtable_type_get(family); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -8773,10 +8822,11 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) struct nft_trans *trans, *next; LIST_HEAD(set_update_list); struct nft_trans_elem *te; + int err = 0; if (action == NFNL_ABORT_VALIDATE && nf_tables_validate(net) < 0) - return -EAGAIN; + err = -EAGAIN; list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { @@ -8936,12 +8986,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nf_tables_abort_release(trans); } - if (action == NFNL_ABORT_AUTOLOAD) - nf_tables_module_autoload(net); - else - nf_tables_module_autoload_cleanup(net); - - return 0; + return err; } static int nf_tables_abort(struct net *net, struct sk_buff *skb, @@ -8955,6 +9000,16 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb, ret = __nf_tables_abort(net, action); nft_gc_seq_end(nft_net, gc_seq); + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + + /* module autoload needs to happen after GC sequence update because it + * temporarily releases and grabs mutex again. + */ + if (action == NFNL_ABORT_AUTOLOAD) + nf_tables_module_autoload(net); + else + nf_tables_module_autoload_cleanup(net); + mutex_unlock(&nft_net->commit_mutex); return ret; @@ -9336,16 +9391,10 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); switch (data->verdict.code) { - default: - switch (data->verdict.code & NF_VERDICT_MASK) { - case NF_ACCEPT: - case NF_DROP: - case NF_QUEUE: - break; - default: - return -EINVAL; - } - fallthrough; + case NF_ACCEPT: + case NF_DROP: + case NF_QUEUE: + break; case NFT_CONTINUE: case NFT_BREAK: case NFT_RETURN: @@ -9380,6 +9429,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, data->verdict.chain = chain; break; + default: + return -EINVAL; } desc->len = sizeof(data->verdict); @@ -9693,8 +9744,11 @@ static void __net_exit nf_tables_exit_net(struct net *net) gc_seq = nft_gc_seq_begin(nft_net); - if (!list_empty(&nft_net->commit_list)) - __nf_tables_abort(net, NFNL_ABORT_NONE); + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + + if (!list_empty(&nft_net->module_list)) + nf_tables_module_autoload_cleanup(net); + __nft_release_tables(net); nft_gc_seq_end(nft_net, gc_seq); @@ -9778,6 +9832,7 @@ static void __exit nf_tables_module_exit(void) unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); nft_chain_route_fini(); + nf_tables_trans_destroy_flush_work(); unregister_pernet_subsys(&nf_tables_net_ops); cancel_work_sync(&trans_gc_work); cancel_work_sync(&trans_destroy_work); diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 7b0b8fecb..9d250bd60 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -38,20 +38,21 @@ void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->size) { case 8: { + u64 *dst64 = (void *)dst; u64 src64; switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 8; i++) { src64 = nft_reg_load64(&src[i]); - nft_reg_store64(&dst[i], be64_to_cpu(src64)); + nft_reg_store64(&dst64[i], be64_to_cpu(src64)); } break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 8; i++) { src64 = (__force __u64) cpu_to_be64(nft_reg_load64(&src[i])); - nft_reg_store64(&dst[i], src64); + nft_reg_store64(&dst64[i], src64); } break; } diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 7a9aa57b1..aad676402 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -339,7 +339,9 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev, return; if (n > 1) { - nf_unregister_net_hook(ctx->net, &found->ops); + if (!(ctx->chain->table->flags & NFT_TABLE_F_DORMANT)) + nf_unregister_net_hook(ctx->net, &found->ops); + list_del_rcu(&found->list); kfree_rcu(found, rcu); return; @@ -358,9 +360,10 @@ static int nf_tables_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct nft_base_chain *basechain; struct nftables_pernet *nft_net; - struct nft_table *table; struct nft_chain *chain, *nr; + struct nft_table *table; struct nft_ctx ctx = { .net = dev_net(dev), }; @@ -372,7 +375,8 @@ static int nf_tables_netdev_event(struct notifier_block *this, nft_net = net_generic(ctx.net, nf_tables_net_id); mutex_lock(&nft_net->commit_mutex); list_for_each_entry(table, &nft_net->tables, list) { - if (table->family != NFPROTO_NETDEV) + if (table->family != NFPROTO_NETDEV && + table->family != NFPROTO_INET) continue; ctx.family = table->family; @@ -381,6 +385,11 @@ static int nf_tables_netdev_event(struct notifier_block *this, if (!nft_is_base_chain(chain)) continue; + basechain = nft_base_chain(chain); + if (table->family == NFPROTO_INET && + basechain->ops.hooknum != NF_INET_INGRESS) + continue; + ctx.chain = chain; nft_netdev_event(event, dev, &ctx); } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index b8dbd20a6..3e0a6e793 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -192,6 +192,7 @@ static const struct nla_policy nft_rule_compat_policy[NFTA_RULE_COMPAT_MAX + 1] static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) { struct nlattr *tb[NFTA_RULE_COMPAT_MAX+1]; + u32 l4proto; u32 flags; int err; @@ -204,12 +205,18 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) return -EINVAL; flags = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_FLAGS])); - if (flags & ~NFT_RULE_COMPAT_F_MASK) + if (flags & NFT_RULE_COMPAT_F_UNUSED || + flags & ~NFT_RULE_COMPAT_F_MASK) return -EINVAL; if (flags & NFT_RULE_COMPAT_F_INV) *inv = true; - *proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO])); + l4proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO])); + if (l4proto > U16_MAX) + return -EINVAL; + + *proto = l4proto; + return 0; } @@ -327,6 +334,22 @@ static int nft_target_validate(const struct nft_ctx *ctx, unsigned int hook_mask = 0; int ret; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET && + ctx->family != NFPROTO_BRIDGE && + ctx->family != NFPROTO_ARP) + return -EOPNOTSUPP; + + ret = nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING)); + if (ret) + return ret; + if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); @@ -569,6 +592,22 @@ static int nft_match_validate(const struct nft_ctx *ctx, unsigned int hook_mask = 0; int ret; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET && + ctx->family != NFPROTO_BRIDGE && + ctx->family != NFPROTO_ARP) + return -EOPNOTSUPP; + + ret = nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING)); + if (ret) + return ret; + if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 14093d86e..2a8dfa68f 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -482,6 +482,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, break; #endif case NFT_CT_ID: + if (tb[NFTA_CT_DIRECTION]) + return -EINVAL; + len = sizeof(u32); break; default: @@ -1182,7 +1185,30 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx, if (tb[NFTA_CT_EXPECT_L3PROTO]) priv->l3num = ntohs(nla_get_be16(tb[NFTA_CT_EXPECT_L3PROTO])); + switch (priv->l3num) { + case NFPROTO_IPV4: + case NFPROTO_IPV6: + if (priv->l3num == ctx->family || ctx->family == NFPROTO_INET) + break; + + return -EINVAL; + case NFPROTO_INET: /* tuple.src.l3num supports NFPROTO_IPV4/6 only */ + default: + return -EAFNOSUPPORT; + } + priv->l4proto = nla_get_u8(tb[NFTA_CT_EXPECT_L4PROTO]); + switch (priv->l4proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + case IPPROTO_DCCP: + case IPPROTO_SCTP: + break; + default: + return -EOPNOTSUPP; + } + priv->dport = nla_get_be16(tb[NFTA_CT_EXPECT_DPORT]); priv->timeout = nla_get_u32(tb[NFTA_CT_EXPECT_TIMEOUT]); priv->size = nla_get_u8(tb[NFTA_CT_EXPECT_SIZE]); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index a44340dd3..c2a5d05f5 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -150,6 +150,11 @@ static int nft_flow_offload_validate(const struct nft_ctx *ctx, { unsigned int hook_mask = (1 << NF_INET_FORWARD); + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, hook_mask); } diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 44d9b38e5..cb5bb0e21 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -63,7 +63,7 @@ nft_meta_get_eval_time(enum nft_meta_keys key, { switch (key) { case NFT_META_TIME_NS: - nft_reg_store64(dest, ktime_get_real_ns()); + nft_reg_store64((u64 *)dest, ktime_get_real_ns()); break; case NFT_META_TIME_DAY: nft_reg_store8(dest, nft_meta_weekday()); diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index cd4eb4996..2e1ee7d9d 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -142,6 +142,11 @@ static int nft_nat_validate(const struct nft_ctx *ctx, struct nft_nat *priv = nft_expr_priv(expr); int err; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT); if (err < 0) return err; diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index bcd01a63e..f4a96164a 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -166,6 +166,11 @@ static int nft_rt_validate(const struct nft_ctx *ctx, const struct nft_expr *exp const struct nft_rt *priv = nft_expr_priv(expr); unsigned int hooks; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + switch (priv->key) { case NFT_RT_NEXTHOP4: case NFT_RT_NEXTHOP6: diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index bc30bd121..5a8521abd 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -342,9 +342,6 @@ #include "nft_set_pipapo_avx2.h" #include "nft_set_pipapo.h" -/* Current working bitmap index, toggled between field matches */ -static DEFINE_PER_CPU(bool, nft_pipapo_scratch_index); - /** * pipapo_refill() - For each set bit, set bits from selected mapping table item * @map: Bitmap to be scanned for set bits @@ -412,6 +409,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_scratch *scratch; unsigned long *res_map, *fill_map; u8 genmask = nft_genmask_cur(net); const u8 *rp = (const u8 *)key; @@ -422,15 +420,17 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, local_bh_disable(); - map_index = raw_cpu_read(nft_pipapo_scratch_index); - m = rcu_dereference(priv->match); if (unlikely(!m || !*raw_cpu_ptr(m->scratch))) goto out; - res_map = *raw_cpu_ptr(m->scratch) + (map_index ? m->bsize_max : 0); - fill_map = *raw_cpu_ptr(m->scratch) + (map_index ? 0 : m->bsize_max); + scratch = *raw_cpu_ptr(m->scratch); + + map_index = scratch->map_index; + + res_map = scratch->map + (map_index ? m->bsize_max : 0); + fill_map = scratch->map + (map_index ? 0 : m->bsize_max); memset(res_map, 0xff, m->bsize_max * sizeof(*res_map)); @@ -460,7 +460,7 @@ next_match: b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt, last); if (b < 0) { - raw_cpu_write(nft_pipapo_scratch_index, map_index); + scratch->map_index = map_index; local_bh_enable(); return false; @@ -477,7 +477,7 @@ next_match: * current inactive bitmap is clean and can be reused as * *next* bitmap (not initial) for the next packet. */ - raw_cpu_write(nft_pipapo_scratch_index, map_index); + scratch->map_index = map_index; local_bh_enable(); return true; @@ -1102,6 +1102,25 @@ static void pipapo_map(struct nft_pipapo_match *m, } /** + * pipapo_free_scratch() - Free per-CPU map at original (not aligned) address + * @m: Matching data + * @cpu: CPU number + */ +static void pipapo_free_scratch(const struct nft_pipapo_match *m, unsigned int cpu) +{ + struct nft_pipapo_scratch *s; + void *mem; + + s = *per_cpu_ptr(m->scratch, cpu); + if (!s) + return; + + mem = s; + mem -= s->align_off; + kfree(mem); +} + +/** * pipapo_realloc_scratch() - Reallocate scratch maps for partial match results * @clone: Copy of matching data with pending insertions and deletions * @bsize_max: Maximum bucket size, scratch maps cover two buckets @@ -1114,12 +1133,13 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, int i; for_each_possible_cpu(i) { - unsigned long *scratch; + struct nft_pipapo_scratch *scratch; #ifdef NFT_PIPAPO_ALIGN - unsigned long *scratch_aligned; + void *scratch_aligned; + u32 align_off; #endif - - scratch = kzalloc_node(bsize_max * sizeof(*scratch) * 2 + + scratch = kzalloc_node(struct_size(scratch, map, + bsize_max * 2) + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL, cpu_to_node(i)); if (!scratch) { @@ -1133,14 +1153,25 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, return -ENOMEM; } - kfree(*per_cpu_ptr(clone->scratch, i)); - - *per_cpu_ptr(clone->scratch, i) = scratch; + pipapo_free_scratch(clone, i); #ifdef NFT_PIPAPO_ALIGN - scratch_aligned = NFT_PIPAPO_LT_ALIGN(scratch); - *per_cpu_ptr(clone->scratch_aligned, i) = scratch_aligned; + /* Align &scratch->map (not the struct itself): the extra + * %NFT_PIPAPO_ALIGN_HEADROOM bytes passed to kzalloc_node() + * above guarantee we can waste up to those bytes in order + * to align the map field regardless of its offset within + * the struct. + */ + BUILD_BUG_ON(offsetof(struct nft_pipapo_scratch, map) > NFT_PIPAPO_ALIGN_HEADROOM); + + scratch_aligned = NFT_PIPAPO_LT_ALIGN(&scratch->map); + scratch_aligned -= offsetof(struct nft_pipapo_scratch, map); + align_off = scratch_aligned - (void *)scratch; + + scratch = scratch_aligned; + scratch->align_off = align_off; #endif + *per_cpu_ptr(clone->scratch, i) = scratch; } return 0; @@ -1294,11 +1325,6 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old) if (!new->scratch) goto out_scratch; -#ifdef NFT_PIPAPO_ALIGN - new->scratch_aligned = alloc_percpu(*new->scratch_aligned); - if (!new->scratch_aligned) - goto out_scratch; -#endif for_each_possible_cpu(i) *per_cpu_ptr(new->scratch, i) = NULL; @@ -1350,10 +1376,7 @@ out_lt: } out_scratch_realloc: for_each_possible_cpu(i) - kfree(*per_cpu_ptr(new->scratch, i)); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(new->scratch_aligned); -#endif + pipapo_free_scratch(new, i); out_scratch: free_percpu(new->scratch); kfree(new); @@ -1635,13 +1658,9 @@ static void pipapo_free_match(struct nft_pipapo_match *m) int i; for_each_possible_cpu(i) - kfree(*per_cpu_ptr(m->scratch, i)); + pipapo_free_scratch(m, i); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(m->scratch_aligned); -#endif free_percpu(m->scratch); - pipapo_free_fields(m); kfree(m); @@ -1961,6 +1980,8 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, rules_fx = rules_f0; nft_pipapo_for_each_field(f, i, m) { + bool last = i == m->field_count - 1; + if (!pipapo_match_field(f, start, rules_fx, match_start, match_end)) break; @@ -1973,16 +1994,18 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, match_start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); - } - if (i == m->field_count) { - priv->dirty = true; - pipapo_drop(m, rulemap); - return; + if (last && f->mt[rulemap[i].to].e == e) { + priv->dirty = true; + pipapo_drop(m, rulemap); + return; + } } first_rule += rules_f0; } + + WARN_ON_ONCE(1); /* elem_priv not found */ } /** @@ -2118,7 +2141,7 @@ static int nft_pipapo_init(const struct nft_set *set, m->field_count = field_count; m->bsize_max = 0; - m->scratch = alloc_percpu(unsigned long *); + m->scratch = alloc_percpu(struct nft_pipapo_scratch *); if (!m->scratch) { err = -ENOMEM; goto out_scratch; @@ -2126,16 +2149,6 @@ static int nft_pipapo_init(const struct nft_set *set, for_each_possible_cpu(i) *per_cpu_ptr(m->scratch, i) = NULL; -#ifdef NFT_PIPAPO_ALIGN - m->scratch_aligned = alloc_percpu(unsigned long *); - if (!m->scratch_aligned) { - err = -ENOMEM; - goto out_free; - } - for_each_possible_cpu(i) - *per_cpu_ptr(m->scratch_aligned, i) = NULL; -#endif - rcu_head_init(&m->rcu); nft_pipapo_for_each_field(f, i, m) { @@ -2166,9 +2179,6 @@ static int nft_pipapo_init(const struct nft_set *set, return 0; out_free: -#ifdef NFT_PIPAPO_ALIGN - free_percpu(m->scratch_aligned); -#endif free_percpu(m->scratch); out_scratch: kfree(m); @@ -2220,13 +2230,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, if (m) { rcu_barrier(); - nft_set_pipapo_match_destroy(ctx, set, m); - -#ifdef NFT_PIPAPO_ALIGN - free_percpu(m->scratch_aligned); -#endif for_each_possible_cpu(cpu) - kfree(*per_cpu_ptr(m->scratch, cpu)); + pipapo_free_scratch(m, cpu); free_percpu(m->scratch); pipapo_free_fields(m); kfree(m); @@ -2236,14 +2241,10 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, if (priv->clone) { m = priv->clone; - if (priv->dirty) - nft_set_pipapo_match_destroy(ctx, set, m); + nft_set_pipapo_match_destroy(ctx, set, m); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(priv->clone->scratch_aligned); -#endif for_each_possible_cpu(cpu) - kfree(*per_cpu_ptr(priv->clone->scratch, cpu)); + pipapo_free_scratch(priv->clone, cpu); free_percpu(priv->clone->scratch); pipapo_free_fields(priv->clone); diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index d84afb8fa..2e709ae01 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -131,20 +131,28 @@ struct nft_pipapo_field { }; /** + * struct nft_pipapo_scratch - percpu data used for lookup and matching + * @map_index: Current working bitmap index, toggled between field matches + * @align_off: Offset to get the originally allocated address + * @map: store partial matching results during lookup + */ +struct nft_pipapo_scratch { + u8 map_index; + u32 align_off; + unsigned long map[]; +}; + +/** * struct nft_pipapo_match - Data used for lookup and matching * @field_count Amount of fields in set * @scratch: Preallocated per-CPU maps for partial matching results - * @scratch_aligned: Version of @scratch aligned to NFT_PIPAPO_ALIGN bytes * @bsize_max: Maximum lookup table bucket size of all fields, in longs * @rcu Matching data is swapped on commits * @f: Fields, with lookup and mapping tables */ struct nft_pipapo_match { int field_count; -#ifdef NFT_PIPAPO_ALIGN - unsigned long * __percpu *scratch_aligned; -#endif - unsigned long * __percpu *scratch; + struct nft_pipapo_scratch * __percpu *scratch; size_t bsize_max; struct rcu_head rcu; struct nft_pipapo_field f[]; diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index 10332178d..60fb8bc0f 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -71,9 +71,6 @@ #define NFT_PIPAPO_AVX2_ZERO(reg) \ asm volatile("vpxor %ymm" #reg ", %ymm" #reg ", %ymm" #reg) -/* Current working bitmap index, toggled between field matches */ -static DEFINE_PER_CPU(bool, nft_pipapo_avx2_scratch_index); - /** * nft_pipapo_avx2_prepare() - Prepare before main algorithm body * @@ -1123,11 +1120,12 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_pipapo *priv = nft_set_priv(set); - unsigned long *res, *fill, *scratch; + struct nft_pipapo_scratch *scratch; u8 genmask = nft_genmask_cur(net); const u8 *rp = (const u8 *)key; struct nft_pipapo_match *m; struct nft_pipapo_field *f; + unsigned long *res, *fill; bool map_index; int i, ret = 0; @@ -1139,15 +1137,16 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, /* This also protects access to all data related to scratch maps */ kernel_fpu_begin(); - scratch = *raw_cpu_ptr(m->scratch_aligned); + scratch = *raw_cpu_ptr(m->scratch); if (unlikely(!scratch)) { kernel_fpu_end(); return false; } - map_index = raw_cpu_read(nft_pipapo_avx2_scratch_index); - res = scratch + (map_index ? m->bsize_max : 0); - fill = scratch + (map_index ? 0 : m->bsize_max); + map_index = scratch->map_index; + + res = scratch->map + (map_index ? m->bsize_max : 0); + fill = scratch->map + (map_index ? 0 : m->bsize_max); /* Starting map doesn't need to be set for this implementation */ @@ -1219,7 +1218,7 @@ next_match: out: if (i % 2) - raw_cpu_write(nft_pipapo_avx2_scratch_index, !map_index); + scratch->map_index = !map_index; kernel_fpu_end(); return ret >= 0; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 12d9d0d0c..18c0d163d 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -237,7 +237,7 @@ static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, static const struct nft_rbtree_elem * nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, - struct nft_rbtree_elem *rbe, u8 genmask) + struct nft_rbtree_elem *rbe) { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); @@ -256,7 +256,7 @@ nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe_prev) && - nft_set_elem_active(&rbe_prev->ext, genmask)) + nft_set_elem_active(&rbe_prev->ext, NFT_GENMASK_ANY)) break; prev = rb_prev(prev); @@ -367,7 +367,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, nft_set_elem_active(&rbe->ext, cur_genmask)) { const struct nft_rbtree_elem *removed_end; - removed_end = nft_rbtree_gc_elem(set, priv, rbe, genmask); + removed_end = nft_rbtree_gc_elem(set, priv, rbe); if (IS_ERR(removed_end)) return PTR_ERR(removed_end); diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index f6d517185..826e5f8c7 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -166,6 +166,11 @@ static int nft_socket_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index 1133e06f3..0806813d3 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -186,7 +186,6 @@ static int nft_synproxy_do_init(const struct nft_ctx *ctx, break; #endif case NFPROTO_INET: - case NFPROTO_BRIDGE: err = nf_synproxy_ipv4_init(snet, ctx->net); if (err) goto nf_ct_failure; @@ -219,7 +218,6 @@ static void nft_synproxy_do_destroy(const struct nft_ctx *ctx) break; #endif case NFPROTO_INET: - case NFPROTO_BRIDGE: nf_synproxy_ipv4_fini(snet, ctx->net); nf_synproxy_ipv6_fini(snet, ctx->net); break; @@ -253,6 +251,11 @@ static int nft_synproxy_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD)); } diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index f8d277e05..6b606e83c 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -293,6 +293,11 @@ static int nft_tproxy_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING); } diff --git a/net/netfilter/nft_xfrm.c b/net/netfilter/nft_xfrm.c index cbbbc4eca..7f762fc42 100644 --- a/net/netfilter/nft_xfrm.c +++ b/net/netfilter/nft_xfrm.c @@ -233,6 +233,11 @@ static int nft_xfrm_validate(const struct nft_ctx *ctx, const struct nft_expr *e const struct nft_xfrm *priv = nft_expr_priv(expr); unsigned int hooks; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + switch (priv->dir) { case XFRM_POLICY_IN: hooks = (1 << NF_INET_FORWARD) | diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 901358a5b..a2b14434d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -157,7 +157,7 @@ static inline u32 netlink_group_mask(u32 group) static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb, gfp_t gfp_mask) { - unsigned int len = skb_end_offset(skb); + unsigned int len = skb->len; struct sk_buff *new; new = alloc_skb(len, gfp_mask); @@ -366,7 +366,7 @@ static void netlink_skb_destructor(struct sk_buff *skb) if (is_vmalloc_addr(skb->head)) { if (!skb->cloned || !atomic_dec_return(&(skb_shinfo(skb)->dataref))) - vfree(skb->head); + vfree_atomic(skb->head); skb->head = NULL; } diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 247471631..37d0bf6ca 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -453,16 +453,16 @@ static int nr_create(struct net *net, struct socket *sock, int protocol, nr_init_timers(sk); nr->t1 = - msecs_to_jiffies(sysctl_netrom_transport_timeout); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_timeout)); nr->t2 = - msecs_to_jiffies(sysctl_netrom_transport_acknowledge_delay); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_acknowledge_delay)); nr->n2 = - msecs_to_jiffies(sysctl_netrom_transport_maximum_tries); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_maximum_tries)); nr->t4 = - msecs_to_jiffies(sysctl_netrom_transport_busy_delay); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_busy_delay)); nr->idle = - msecs_to_jiffies(sysctl_netrom_transport_no_activity_timeout); - nr->window = sysctl_netrom_transport_requested_window_size; + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_no_activity_timeout)); + nr->window = READ_ONCE(sysctl_netrom_transport_requested_window_size); nr->bpqext = 1; nr->state = NR_STATE_0; @@ -954,7 +954,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) * G8PZT's Xrouter which is sending packets with command type 7 * as an extension of the protocol. */ - if (sysctl_netrom_reset_circuit && + if (READ_ONCE(sysctl_netrom_reset_circuit) && (frametype != NR_RESET || flags != 0)) nr_transmit_reset(skb, 1); diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c index 29e418c8c..4caee8754 100644 --- a/net/netrom/nr_dev.c +++ b/net/netrom/nr_dev.c @@ -81,7 +81,7 @@ static int nr_header(struct sk_buff *skb, struct net_device *dev, buff[6] |= AX25_SSSID_SPARE; buff += AX25_ADDR_LEN; - *buff++ = sysctl_netrom_network_ttl_initialiser; + *buff++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); *buff++ = NR_PROTO_IP; *buff++ = NR_PROTO_IP; diff --git a/net/netrom/nr_in.c b/net/netrom/nr_in.c index 69e58906c..034f79d11 100644 --- a/net/netrom/nr_in.c +++ b/net/netrom/nr_in.c @@ -97,7 +97,7 @@ static int nr_state1_machine(struct sock *sk, struct sk_buff *skb, break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; @@ -128,7 +128,7 @@ static int nr_state2_machine(struct sock *sk, struct sk_buff *skb, break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; @@ -263,7 +263,7 @@ static int nr_state3_machine(struct sock *sk, struct sk_buff *skb, int frametype break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; diff --git a/net/netrom/nr_out.c b/net/netrom/nr_out.c index 44929657f..5e531394a 100644 --- a/net/netrom/nr_out.c +++ b/net/netrom/nr_out.c @@ -204,7 +204,7 @@ void nr_transmit_buffer(struct sock *sk, struct sk_buff *skb) dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; - *dptr++ = sysctl_netrom_network_ttl_initialiser; + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); if (!nr_route_frame(skb, NULL)) { kfree_skb(skb); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 78da5eab2..895702337 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -153,7 +153,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, nr_neigh->digipeat = NULL; nr_neigh->ax25 = NULL; nr_neigh->dev = dev; - nr_neigh->quality = sysctl_netrom_default_path_quality; + nr_neigh->quality = READ_ONCE(sysctl_netrom_default_path_quality); nr_neigh->locked = 0; nr_neigh->count = 0; nr_neigh->number = nr_neigh_no++; @@ -725,7 +725,7 @@ void nr_link_failed(ax25_cb *ax25, int reason) nr_neigh->ax25 = NULL; ax25_cb_put(ax25); - if (++nr_neigh->failed < sysctl_netrom_link_fails_count) { + if (++nr_neigh->failed < READ_ONCE(sysctl_netrom_link_fails_count)) { nr_neigh_put(nr_neigh); return; } @@ -763,7 +763,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) if (ax25 != NULL) { ret = nr_add_node(nr_src, "", &ax25->dest_addr, ax25->digipeat, ax25->ax25_dev->dev, 0, - sysctl_netrom_obsolescence_count_initialiser); + READ_ONCE(sysctl_netrom_obsolescence_count_initialiser)); if (ret) return ret; } @@ -777,7 +777,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) return ret; } - if (!sysctl_netrom_routing_control && ax25 != NULL) + if (!READ_ONCE(sysctl_netrom_routing_control) && ax25 != NULL) return 0; /* Its Time-To-Live has expired */ diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c index e2d2af924..c3bbd5880 100644 --- a/net/netrom/nr_subr.c +++ b/net/netrom/nr_subr.c @@ -182,7 +182,8 @@ void nr_write_internal(struct sock *sk, int frametype) *dptr++ = nr->my_id; *dptr++ = frametype; *dptr++ = nr->window; - if (nr->bpqext) *dptr++ = sysctl_netrom_network_ttl_initialiser; + if (nr->bpqext) + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); break; case NR_DISCREQ: @@ -236,7 +237,7 @@ void __nr_transmit_reply(struct sk_buff *skb, int mine, unsigned char cmdflags) dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; - *dptr++ = sysctl_netrom_network_ttl_initialiser; + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); if (mine) { *dptr++ = 0; diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 4c931bd1c..d8002065b 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1197,6 +1197,10 @@ void nci_free_device(struct nci_dev *ndev) { nfc_free_device(ndev->nfc_dev); nci_hci_deallocate(ndev); + + /* drop partial rx data packet if present */ + if (ndev->rx_data_reassembly) + kfree_skb(ndev->rx_data_reassembly); kfree(ndev); } EXPORT_SYMBOL(nci_free_device); @@ -1498,6 +1502,11 @@ static void nci_rx_work(struct work_struct *work) nfc_send_to_raw_sock(ndev->nfc_dev, skb, RAW_PAYLOAD_NCI, NFC_DIRECTION_RX); + if (!nci_plen(skb->data)) { + kfree_skb(skb); + break; + } + /* Process frame */ switch (nci_mt(skb->data)) { case NCI_MT_RSP_PKT: diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 0f0f380e8..30f5e4140 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1692,8 +1692,9 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, if (ct_info.timeout[0]) { if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto, ct_info.timeout)) - pr_info_ratelimited("Failed to associated timeout " - "policy `%s'\n", ct_info.timeout); + OVS_NLERR(log, + "Failed to associated timeout policy '%s'", + ct_info.timeout); else ct_info.nf_ct_timeout = rcu_dereference( nf_ct_timeout_find(ct_info.ct)->timeout); @@ -1901,9 +1902,9 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { struct hlist_head *head = &info->limits[i]; struct ovs_ct_limit *ct_limit; + struct hlist_node *next; - hlist_for_each_entry_rcu(ct_limit, head, hlist_node, - lockdep_ovsl_is_held()) + hlist_for_each_entry_safe(ct_limit, next, head, hlist_node) kfree_rcu(ct_limit, rcu); } kfree(info->limits); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 293a798e8..cff18a5bb 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -47,6 +47,7 @@ struct ovs_len_tbl { #define OVS_ATTR_NESTED -1 #define OVS_ATTR_VARIABLE -2 +#define OVS_COPY_ACTIONS_MAX_DEPTH 16 static bool actions_may_change_flow(const struct nlattr *actions) { @@ -2514,13 +2515,15 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log); + u32 mpls_label_count, bool log, + u32 depth); static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log, bool last) + u32 mpls_label_count, bool log, bool last, + u32 depth) { const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1]; const struct nlattr *probability, *actions; @@ -2571,7 +2574,8 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, return err; err = __ovs_nla_copy_actions(net, actions, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -2586,7 +2590,8 @@ static int validate_and_copy_dec_ttl(struct net *net, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log) + u32 mpls_label_count, bool log, + u32 depth) { const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1]; int start, action_start, err, rem; @@ -2619,7 +2624,8 @@ static int validate_and_copy_dec_ttl(struct net *net, return action_start; err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, - vlan_tci, mpls_label_count, log); + vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -2633,7 +2639,8 @@ static int validate_and_copy_clone(struct net *net, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log, bool last) + u32 mpls_label_count, bool log, bool last, + u32 depth) { int start, err; u32 exec; @@ -2653,7 +2660,8 @@ static int validate_and_copy_clone(struct net *net, return err; err = __ovs_nla_copy_actions(net, attr, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3022,7 +3030,7 @@ static int validate_and_copy_check_pkt_len(struct net *net, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, - bool log, bool last) + bool log, bool last, u32 depth) { const struct nlattr *acts_if_greater, *acts_if_lesser_eq; struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1]; @@ -3070,7 +3078,8 @@ static int validate_and_copy_check_pkt_len(struct net *net, return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3083,7 +3092,8 @@ static int validate_and_copy_check_pkt_len(struct net *net, return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3111,12 +3121,16 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log) + u32 mpls_label_count, bool log, + u32 depth) { u8 mac_proto = ovs_key_mac_proto(key); const struct nlattr *a; int rem, err; + if (depth > OVS_COPY_ACTIONS_MAX_DEPTH) + return -EOVERFLOW; + nla_for_each_nested(a, attr, rem) { /* Expected argument lengths, (u32)-1 for variable length. */ static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = { @@ -3311,7 +3325,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, err = validate_and_copy_sample(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, depth); if (err) return err; skip_copy = true; @@ -3382,7 +3396,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, err = validate_and_copy_clone(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, depth); if (err) return err; skip_copy = true; @@ -3396,7 +3410,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, + depth); if (err) return err; skip_copy = true; @@ -3406,7 +3421,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, case OVS_ACTION_ATTR_DEC_TTL: err = validate_and_copy_dec_ttl(net, a, key, sfa, eth_type, vlan_tci, - mpls_label_count, log); + mpls_label_count, log, + depth); if (err) return err; skip_copy = true; @@ -3446,7 +3462,8 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, (*sfa)->orig_len = nla_len(attr); err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type, - key->eth.vlan.tci, mpls_label_count, log); + key->eth.vlan.tci, mpls_label_count, log, + 0); if (err) ovs_nla_free_flow_actions(*sfa); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b292d58fd..db5d16c5d 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1871,7 +1871,7 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, */ spkt->spkt_family = dev->type; - strlcpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device)); + strscpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device)); spkt->spkt_protocol = skb->protocol; /* @@ -3252,7 +3252,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; - char name[sizeof(uaddr->sa_data) + 1]; + char name[sizeof(uaddr->sa_data_min) + 1]; /* * Check legality @@ -3263,8 +3263,8 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, /* uaddr->sa_data comes from the userspace, it's not guaranteed to be * zero-terminated. */ - memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data)); - name[sizeof(uaddr->sa_data)] = 0; + memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); + name[sizeof(uaddr->sa_data_min)] = 0; return packet_do_bind(sk, name, 0, 0); } @@ -3536,11 +3536,11 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; - memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); + memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data_min)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) - strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); + strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data_min)); rcu_read_unlock(); return sizeof(*uaddr); @@ -3951,7 +3951,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, if (val < 0 || val > 1) return -EINVAL; - po->prot_hook.ignore_outgoing = !!val; + WRITE_ONCE(po->prot_hook.ignore_outgoing, !!val); return 0; } case PACKET_TX_HAS_OFF: @@ -4083,7 +4083,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, 0); break; case PACKET_IGNORE_OUTGOING: - val = po->prot_hook.ignore_outgoing; + val = READ_ONCE(po->prot_hook.ignore_outgoing); break; case PACKET_ROLLOVER_STATS: if (!po->rollover) diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index b239120dd..0ec0ae148 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -419,7 +419,7 @@ static int rds_recv_track_latency(struct rds_sock *rs, sockptr_t optval, rs->rs_rx_traces = trace.rx_traces; for (i = 0; i < rs->rs_rx_traces; i++) { - if (trace.rx_trace_pos[i] > RDS_MSG_RX_DGRAM_TRACE_MAX) { + if (trace.rx_trace_pos[i] >= RDS_MSG_RX_DGRAM_TRACE_MAX) { rs->rs_rx_traces = 0; return -EFAULT; } diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 6f1a50d50..3df0affff 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -301,6 +301,9 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, kfree(sg); } ret = PTR_ERR(trans_private); + /* Trigger connection so that its ready for the next retry */ + if (ret == -ENODEV && cp) + rds_conn_connect_if_down(cp->cp_conn); goto out; } diff --git a/net/rds/send.c b/net/rds/send.c index 985d0b771..1923eaa91 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -103,13 +103,12 @@ EXPORT_SYMBOL_GPL(rds_send_path_reset); static int acquire_in_xmit(struct rds_conn_path *cp) { - return test_and_set_bit(RDS_IN_XMIT, &cp->cp_flags) == 0; + return test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags) == 0; } static void release_in_xmit(struct rds_conn_path *cp) { - clear_bit(RDS_IN_XMIT, &cp->cp_flags); - smp_mb__after_atomic(); + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); /* * We don't use wait_on_bit()/wake_up_bit() because our waking is in a * hot path and finding waiters is very rare. We don't want to walk @@ -1314,12 +1313,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* Parse any control messages the user may have included. */ ret = rds_cmsg_send(rs, rm, msg, &allocated_mr, &vct); - if (ret) { - /* Trigger connection so that its ready for the next retry */ - if (ret == -EAGAIN) - rds_conn_connect_if_down(conn); + if (ret) goto out; - } if (rm->rdma.op_active && !conn->c_trans->xmit_rdma) { printk_ratelimited(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n", diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index aff184145..9081e8429 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -41,6 +41,14 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, _enter("%d", conn->debug_id); + if (sp && sp->hdr.type == RXRPC_PACKET_TYPE_ACK) { + if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), + &pkt.ack, sizeof(pkt.ack)) < 0) + return; + if (pkt.ack.reason == RXRPC_ACK_PING_RESPONSE) + return; + } + chan = &conn->channels[channel]; /* If the last call got moved on whilst we were waiting to run, just diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 68508166b..af0e95ef9 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -31,7 +31,7 @@ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *peer, struct rxrpc_conn_proto k; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rb_node *p; - unsigned int seq = 0; + unsigned int seq = 1; k.epoch = sp->hdr.epoch; k.cid = sp->hdr.cid & RXRPC_CIDMASK; @@ -41,6 +41,7 @@ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *peer, * under just the RCU read lock, so we have to check for * changes. */ + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&peer->service_conn_lock, &seq); p = rcu_dereference_raw(peer->service_conns.rb_node); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 2046c16b2..e5f7675e5 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -45,23 +45,6 @@ if NET_SCHED comment "Queueing/Scheduling" -config NET_SCH_CBQ - tristate "Class Based Queueing (CBQ)" - help - Say Y here if you want to use the Class-Based Queueing (CBQ) packet - scheduling algorithm. This algorithm classifies the waiting packets - into a tree-like hierarchy of classes; the leaves of this tree are - in turn scheduled by separate algorithms. - - See the top of <file:net/sched/sch_cbq.c> for more details. - - CBQ is a commonly used scheduler, so if you're unsure, you should - say Y here. Then say Y to all the queueing algorithms below that you - want to use as leaf disciplines. - - To compile this code as a module, choose M here: the - module will be called sch_cbq. - config NET_SCH_HTB tristate "Hierarchical Token Bucket (HTB)" help @@ -85,20 +68,6 @@ config NET_SCH_HFSC To compile this code as a module, choose M here: the module will be called sch_hfsc. -config NET_SCH_ATM - tristate "ATM Virtual Circuits (ATM)" - depends on ATM - help - Say Y here if you want to use the ATM pseudo-scheduler. This - provides a framework for invoking classifiers, which in turn - select classes of this queuing discipline. Each class maps - the flow(s) it is handling to a given virtual circuit. - - See the top of <file:net/sched/sch_atm.c> for more details. - - To compile this code as a module, choose M here: the - module will be called sch_atm. - config NET_SCH_PRIO tristate "Multi Band Priority Queueing (PRIO)" help @@ -217,17 +186,6 @@ config NET_SCH_GRED To compile this code as a module, choose M here: the module will be called sch_gred. -config NET_SCH_DSMARK - tristate "Differentiated Services marker (DSMARK)" - help - Say Y if you want to schedule packets according to the - Differentiated Services architecture proposed in RFC 2475. - Technical information on this method, with pointers to associated - RFCs, is available at <http://www.gta.ufrj.br/diffserv/>. - - To compile this code as a module, choose M here: the - module will be called sch_dsmark. - config NET_SCH_NETEM tristate "Network emulator (NETEM)" help diff --git a/net/sched/Makefile b/net/sched/Makefile index df2bcd785..1b8d0fc66 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -32,20 +32,17 @@ obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o obj-$(CONFIG_NET_ACT_CT) += act_ct.o obj-$(CONFIG_NET_ACT_GATE) += act_gate.o obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o -obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o obj-$(CONFIG_NET_SCH_HFSC) += sch_hfsc.o obj-$(CONFIG_NET_SCH_RED) += sch_red.o obj-$(CONFIG_NET_SCH_GRED) += sch_gred.o obj-$(CONFIG_NET_SCH_INGRESS) += sch_ingress.o -obj-$(CONFIG_NET_SCH_DSMARK) += sch_dsmark.o obj-$(CONFIG_NET_SCH_SFB) += sch_sfb.o obj-$(CONFIG_NET_SCH_SFQ) += sch_sfq.o obj-$(CONFIG_NET_SCH_TBF) += sch_tbf.o obj-$(CONFIG_NET_SCH_TEQL) += sch_teql.o obj-$(CONFIG_NET_SCH_PRIO) += sch_prio.o obj-$(CONFIG_NET_SCH_MULTIQ) += sch_multiq.o -obj-$(CONFIG_NET_SCH_ATM) += sch_atm.o obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index aa98dcac9..934765a2e 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -219,13 +219,13 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_skbmod *d = to_skbmod(a); unsigned char *b = skb_tail_pointer(skb); struct tcf_skbmod_params *p; - struct tc_skbmod opt = { - .index = d->tcf_index, - .refcnt = refcount_read(&d->tcf_refcnt) - ref, - .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, - }; + struct tc_skbmod opt; struct tcf_t t; + memset(&opt, 0, sizeof(opt)); + opt.index = d->tcf_index; + opt.refcnt = refcount_read(&d->tcf_refcnt) - ref, + opt.bindcnt = atomic_read(&d->tcf_bindcnt) - bind; spin_lock_bh(&d->tcf_lock); opt.action = d->tcf_action; p = rcu_dereference_protected(d->skbmod_p, diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c deleted file mode 100644 index 95967ce1f..000000000 --- a/net/sched/sch_atm.c +++ /dev/null @@ -1,709 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* net/sched/sch_atm.c - ATM VC selection "queueing discipline" */ - -/* Written 1998-2000 by Werner Almesberger, EPFL ICA */ - -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <linux/atmdev.h> -#include <linux/atmclip.h> -#include <linux/rtnetlink.h> -#include <linux/file.h> /* for fput */ -#include <net/netlink.h> -#include <net/pkt_sched.h> -#include <net/pkt_cls.h> - -/* - * The ATM queuing discipline provides a framework for invoking classifiers - * (aka "filters"), which in turn select classes of this queuing discipline. - * Each class maps the flow(s) it is handling to a given VC. Multiple classes - * may share the same VC. - * - * When creating a class, VCs are specified by passing the number of the open - * socket descriptor by which the calling process references the VC. The kernel - * keeps the VC open at least until all classes using it are removed. - * - * In this file, most functions are named atm_tc_* to avoid confusion with all - * the atm_* in net/atm. This naming convention differs from what's used in the - * rest of net/sched. - * - * Known bugs: - * - sometimes messes up the IP stack - * - any manipulations besides the few operations described in the README, are - * untested and likely to crash the system - * - should lock the flow while there is data in the queue (?) - */ - -#define VCC2FLOW(vcc) ((struct atm_flow_data *) ((vcc)->user_back)) - -struct atm_flow_data { - struct Qdisc_class_common common; - struct Qdisc *q; /* FIFO, TBF, etc. */ - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - struct atm_vcc *vcc; /* VCC; NULL if VCC is closed */ - void (*old_pop)(struct atm_vcc *vcc, - struct sk_buff *skb); /* chaining */ - struct atm_qdisc_data *parent; /* parent qdisc */ - struct socket *sock; /* for closing */ - int ref; /* reference count */ - struct gnet_stats_basic_packed bstats; - struct gnet_stats_queue qstats; - struct list_head list; - struct atm_flow_data *excess; /* flow for excess traffic; - NULL to set CLP instead */ - int hdr_len; - unsigned char hdr[]; /* header data; MUST BE LAST */ -}; - -struct atm_qdisc_data { - struct atm_flow_data link; /* unclassified skbs go here */ - struct list_head flows; /* NB: "link" is also on this - list */ - struct tasklet_struct task; /* dequeue tasklet */ -}; - -/* ------------------------- Class/flow operations ------------------------- */ - -static inline struct atm_flow_data *lookup_flow(struct Qdisc *sch, u32 classid) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - list_for_each_entry(flow, &p->flows, list) { - if (flow->common.classid == classid) - return flow; - } - return NULL; -} - -static int atm_tc_graft(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - pr_debug("atm_tc_graft(sch %p,[qdisc %p],flow %p,new %p,old %p)\n", - sch, p, flow, new, old); - if (list_empty(&flow->list)) - return -EINVAL; - if (!new) - new = &noop_qdisc; - *old = flow->q; - flow->q = new; - if (*old) - qdisc_reset(*old); - return 0; -} - -static struct Qdisc *atm_tc_leaf(struct Qdisc *sch, unsigned long cl) -{ - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_leaf(sch %p,flow %p)\n", sch, flow); - return flow ? flow->q : NULL; -} - -static unsigned long atm_tc_find(struct Qdisc *sch, u32 classid) -{ - struct atm_qdisc_data *p __maybe_unused = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", __func__, sch, p, classid); - flow = lookup_flow(sch, classid); - pr_debug("%s: flow %p\n", __func__, flow); - return (unsigned long)flow; -} - -static unsigned long atm_tc_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) -{ - struct atm_qdisc_data *p __maybe_unused = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", __func__, sch, p, classid); - flow = lookup_flow(sch, classid); - if (flow) - flow->ref++; - pr_debug("%s: flow %p\n", __func__, flow); - return (unsigned long)flow; -} - -/* - * atm_tc_put handles all destructions, including the ones that are explicitly - * requested (atm_tc_destroy, etc.). The assumption here is that we never drop - * anything that still seems to be in use. - */ -static void atm_tc_put(struct Qdisc *sch, unsigned long cl) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_put(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - if (--flow->ref) - return; - pr_debug("atm_tc_put: destroying\n"); - list_del_init(&flow->list); - pr_debug("atm_tc_put: qdisc %p\n", flow->q); - qdisc_put(flow->q); - tcf_block_put(flow->block); - if (flow->sock) { - pr_debug("atm_tc_put: f_count %ld\n", - file_count(flow->sock->file)); - flow->vcc->pop = flow->old_pop; - sockfd_put(flow->sock); - } - if (flow->excess) - atm_tc_put(sch, (unsigned long)flow->excess); - if (flow != &p->link) - kfree(flow); - /* - * If flow == &p->link, the qdisc no longer works at this point and - * needs to be removed. (By the caller of atm_tc_put.) - */ -} - -static void sch_atm_pop(struct atm_vcc *vcc, struct sk_buff *skb) -{ - struct atm_qdisc_data *p = VCC2FLOW(vcc)->parent; - - pr_debug("sch_atm_pop(vcc %p,skb %p,[qdisc %p])\n", vcc, skb, p); - VCC2FLOW(vcc)->old_pop(vcc, skb); - tasklet_schedule(&p->task); -} - -static const u8 llc_oui_ip[] = { - 0xaa, /* DSAP: non-ISO */ - 0xaa, /* SSAP: non-ISO */ - 0x03, /* Ctrl: Unnumbered Information Command PDU */ - 0x00, /* OUI: EtherType */ - 0x00, 0x00, - 0x08, 0x00 -}; /* Ethertype IP (0800) */ - -static const struct nla_policy atm_policy[TCA_ATM_MAX + 1] = { - [TCA_ATM_FD] = { .type = NLA_U32 }, - [TCA_ATM_EXCESS] = { .type = NLA_U32 }, -}; - -static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, - struct nlattr **tca, unsigned long *arg, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)*arg; - struct atm_flow_data *excess = NULL; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_ATM_MAX + 1]; - struct socket *sock; - int fd, error, hdr_len; - void *hdr; - - pr_debug("atm_tc_change(sch %p,[qdisc %p],classid %x,parent %x," - "flow %p,opt %p)\n", sch, p, classid, parent, flow, opt); - /* - * The concept of parents doesn't apply for this qdisc. - */ - if (parent && parent != TC_H_ROOT && parent != sch->handle) - return -EINVAL; - /* - * ATM classes cannot be changed. In order to change properties of the - * ATM connection, that socket needs to be modified directly (via the - * native ATM API. In order to send a flow to a different VC, the old - * class needs to be removed and a new one added. (This may be changed - * later.) - */ - if (flow) - return -EBUSY; - if (opt == NULL) - return -EINVAL; - - error = nla_parse_nested_deprecated(tb, TCA_ATM_MAX, opt, atm_policy, - NULL); - if (error < 0) - return error; - - if (!tb[TCA_ATM_FD]) - return -EINVAL; - fd = nla_get_u32(tb[TCA_ATM_FD]); - pr_debug("atm_tc_change: fd %d\n", fd); - if (tb[TCA_ATM_HDR]) { - hdr_len = nla_len(tb[TCA_ATM_HDR]); - hdr = nla_data(tb[TCA_ATM_HDR]); - } else { - hdr_len = RFC1483LLC_LEN; - hdr = NULL; /* default LLC/SNAP for IP */ - } - if (!tb[TCA_ATM_EXCESS]) - excess = NULL; - else { - excess = (struct atm_flow_data *) - atm_tc_find(sch, nla_get_u32(tb[TCA_ATM_EXCESS])); - if (!excess) - return -ENOENT; - } - pr_debug("atm_tc_change: type %d, payload %d, hdr_len %d\n", - opt->nla_type, nla_len(opt), hdr_len); - sock = sockfd_lookup(fd, &error); - if (!sock) - return error; /* f_count++ */ - pr_debug("atm_tc_change: f_count %ld\n", file_count(sock->file)); - if (sock->ops->family != PF_ATMSVC && sock->ops->family != PF_ATMPVC) { - error = -EPROTOTYPE; - goto err_out; - } - /* @@@ should check if the socket is really operational or we'll crash - on vcc->send */ - if (classid) { - if (TC_H_MAJ(classid ^ sch->handle)) { - pr_debug("atm_tc_change: classid mismatch\n"); - error = -EINVAL; - goto err_out; - } - } else { - int i; - unsigned long cl; - - for (i = 1; i < 0x8000; i++) { - classid = TC_H_MAKE(sch->handle, 0x8000 | i); - cl = atm_tc_find(sch, classid); - if (!cl) - break; - } - } - pr_debug("atm_tc_change: new id %x\n", classid); - flow = kzalloc(sizeof(struct atm_flow_data) + hdr_len, GFP_KERNEL); - pr_debug("atm_tc_change: flow %p\n", flow); - if (!flow) { - error = -ENOBUFS; - goto err_out; - } - - error = tcf_block_get(&flow->block, &flow->filter_list, sch, - extack); - if (error) { - kfree(flow); - goto err_out; - } - - flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, - extack); - if (!flow->q) - flow->q = &noop_qdisc; - pr_debug("atm_tc_change: qdisc %p\n", flow->q); - flow->sock = sock; - flow->vcc = ATM_SD(sock); /* speedup */ - flow->vcc->user_back = flow; - pr_debug("atm_tc_change: vcc %p\n", flow->vcc); - flow->old_pop = flow->vcc->pop; - flow->parent = p; - flow->vcc->pop = sch_atm_pop; - flow->common.classid = classid; - flow->ref = 1; - flow->excess = excess; - list_add(&flow->list, &p->link.list); - flow->hdr_len = hdr_len; - if (hdr) - memcpy(flow->hdr, hdr, hdr_len); - else - memcpy(flow->hdr, llc_oui_ip, sizeof(llc_oui_ip)); - *arg = (unsigned long)flow; - return 0; -err_out: - sockfd_put(sock); - return error; -} - -static int atm_tc_delete(struct Qdisc *sch, unsigned long arg) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - pr_debug("atm_tc_delete(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - if (list_empty(&flow->list)) - return -EINVAL; - if (rcu_access_pointer(flow->filter_list) || flow == &p->link) - return -EBUSY; - /* - * Reference count must be 2: one for "keepalive" (set at class - * creation), and one for the reference held when calling delete. - */ - if (flow->ref < 2) { - pr_err("atm_tc_delete: flow->ref == %d\n", flow->ref); - return -EINVAL; - } - if (flow->ref > 2) - return -EBUSY; /* catch references via excess, etc. */ - atm_tc_put(sch, arg); - return 0; -} - -static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("atm_tc_walk(sch %p,[qdisc %p],walker %p)\n", sch, p, walker); - if (walker->stop) - return; - list_for_each_entry(flow, &p->flows, list) { - if (walker->count >= walker->skip && - walker->fn(sch, (unsigned long)flow, walker) < 0) { - walker->stop = 1; - break; - } - walker->count++; - } -} - -static struct tcf_block *atm_tc_tcf_block(struct Qdisc *sch, unsigned long cl, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_find_tcf(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - return flow ? flow->block : p->link.block; -} - -/* --------------------------- Qdisc operations ---------------------------- */ - -static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - struct tcf_result res; - int result; - int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - - pr_debug("atm_tc_enqueue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); - result = TC_ACT_OK; /* be nice to gcc */ - flow = NULL; - if (TC_H_MAJ(skb->priority) != sch->handle || - !(flow = (struct atm_flow_data *)atm_tc_find(sch, skb->priority))) { - struct tcf_proto *fl; - - list_for_each_entry(flow, &p->flows, list) { - fl = rcu_dereference_bh(flow->filter_list); - if (fl) { - result = tcf_classify(skb, fl, &res, true); - if (result < 0) - continue; - if (result == TC_ACT_SHOT) - goto done; - - flow = (struct atm_flow_data *)res.class; - if (!flow) - flow = lookup_flow(sch, res.classid); - goto drop; - } - } - flow = NULL; -done: - ; - } - if (!flow) { - flow = &p->link; - } else { - if (flow->vcc) - ATM_SKB(skb)->atm_options = flow->vcc->atm_options; - /*@@@ looks good ... but it's not supposed to work :-) */ -#ifdef CONFIG_NET_CLS_ACT - switch (result) { - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - __qdisc_drop(skb, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - case TC_ACT_SHOT: - __qdisc_drop(skb, to_free); - goto drop; - case TC_ACT_RECLASSIFY: - if (flow->excess) - flow = flow->excess; - else - ATM_SKB(skb)->atm_options |= ATM_ATMOPT_CLP; - break; - } -#endif - } - - ret = qdisc_enqueue(skb, flow->q, to_free); - if (ret != NET_XMIT_SUCCESS) { -drop: __maybe_unused - if (net_xmit_drop_count(ret)) { - qdisc_qstats_drop(sch); - if (flow) - flow->qstats.drops++; - } - return ret; - } - /* - * Okay, this may seem weird. We pretend we've dropped the packet if - * it goes via ATM. The reason for this is that the outer qdisc - * expects to be able to q->dequeue the packet later on if we return - * success at this place. Also, sch->q.qdisc needs to reflect whether - * there is a packet egligible for dequeuing or not. Note that the - * statistics of the outer qdisc are necessarily wrong because of all - * this. There's currently no correct solution for this. - */ - if (flow == &p->link) { - sch->q.qlen++; - return NET_XMIT_SUCCESS; - } - tasklet_schedule(&p->task); - return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; -} - -/* - * Dequeue packets and send them over ATM. Note that we quite deliberately - * avoid checking net_device's flow control here, simply because sch_atm - * uses its own channels, which have nothing to do with any CLIP/LANE/or - * non-ATM interfaces. - */ - -static void sch_atm_dequeue(unsigned long data) -{ - struct Qdisc *sch = (struct Qdisc *)data; - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - struct sk_buff *skb; - - pr_debug("sch_atm_dequeue(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) { - if (flow == &p->link) - continue; - /* - * If traffic is properly shaped, this won't generate nasty - * little bursts. Otherwise, it may ... (but that's okay) - */ - while ((skb = flow->q->ops->peek(flow->q))) { - if (!atm_may_send(flow->vcc, skb->truesize)) - break; - - skb = qdisc_dequeue_peeked(flow->q); - if (unlikely(!skb)) - break; - - qdisc_bstats_update(sch, skb); - bstats_update(&flow->bstats, skb); - pr_debug("atm_tc_dequeue: sending on class %p\n", flow); - /* remove any LL header somebody else has attached */ - skb_pull(skb, skb_network_offset(skb)); - if (skb_headroom(skb) < flow->hdr_len) { - struct sk_buff *new; - - new = skb_realloc_headroom(skb, flow->hdr_len); - dev_kfree_skb(skb); - if (!new) - continue; - skb = new; - } - pr_debug("sch_atm_dequeue: ip %p, data %p\n", - skb_network_header(skb), skb->data); - ATM_SKB(skb)->vcc = flow->vcc; - memcpy(skb_push(skb, flow->hdr_len), flow->hdr, - flow->hdr_len); - refcount_add(skb->truesize, - &sk_atm(flow->vcc)->sk_wmem_alloc); - /* atm.atm_options are already set by atm_tc_enqueue */ - flow->vcc->send(flow->vcc, skb); - } - } -} - -static struct sk_buff *atm_tc_dequeue(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct sk_buff *skb; - - pr_debug("atm_tc_dequeue(sch %p,[qdisc %p])\n", sch, p); - tasklet_schedule(&p->task); - skb = qdisc_dequeue_peeked(p->link.q); - if (skb) - sch->q.qlen--; - return skb; -} - -static struct sk_buff *atm_tc_peek(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - - pr_debug("atm_tc_peek(sch %p,[qdisc %p])\n", sch, p); - - return p->link.q->ops->peek(p->link.q); -} - -static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - int err; - - pr_debug("atm_tc_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); - INIT_LIST_HEAD(&p->flows); - INIT_LIST_HEAD(&p->link.list); - list_add(&p->link.list, &p->flows); - p->link.q = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, sch->handle, extack); - if (!p->link.q) - p->link.q = &noop_qdisc; - pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); - p->link.vcc = NULL; - p->link.sock = NULL; - p->link.common.classid = sch->handle; - p->link.ref = 1; - - err = tcf_block_get(&p->link.block, &p->link.filter_list, sch, - extack); - if (err) - return err; - - tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch); - return 0; -} - -static void atm_tc_reset(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("atm_tc_reset(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) - qdisc_reset(flow->q); -} - -static void atm_tc_destroy(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow, *tmp; - - pr_debug("atm_tc_destroy(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) { - tcf_block_put(flow->block); - flow->block = NULL; - } - - list_for_each_entry_safe(flow, tmp, &p->flows, list) { - if (flow->ref > 1) - pr_err("atm_destroy: %p->ref = %d\n", flow, flow->ref); - atm_tc_put(sch, (unsigned long)flow); - } - tasklet_kill(&p->task); -} - -static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - struct nlattr *nest; - - pr_debug("atm_tc_dump_class(sch %p,[qdisc %p],flow %p,skb %p,tcm %p)\n", - sch, p, flow, skb, tcm); - if (list_empty(&flow->list)) - return -EINVAL; - tcm->tcm_handle = flow->common.classid; - tcm->tcm_info = flow->q->handle; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (nla_put(skb, TCA_ATM_HDR, flow->hdr_len, flow->hdr)) - goto nla_put_failure; - if (flow->vcc) { - struct sockaddr_atmpvc pvc; - int state; - - memset(&pvc, 0, sizeof(pvc)); - pvc.sap_family = AF_ATMPVC; - pvc.sap_addr.itf = flow->vcc->dev ? flow->vcc->dev->number : -1; - pvc.sap_addr.vpi = flow->vcc->vpi; - pvc.sap_addr.vci = flow->vcc->vci; - if (nla_put(skb, TCA_ATM_ADDR, sizeof(pvc), &pvc)) - goto nla_put_failure; - state = ATM_VF2VS(flow->vcc->flags); - if (nla_put_u32(skb, TCA_ATM_STATE, state)) - goto nla_put_failure; - } - if (flow->excess) { - if (nla_put_u32(skb, TCA_ATM_EXCESS, flow->common.classid)) - goto nla_put_failure; - } else { - if (nla_put_u32(skb, TCA_ATM_EXCESS, 0)) - goto nla_put_failure; - } - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} -static int -atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg, - struct gnet_dump *d) -{ - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &flow->bstats) < 0 || - gnet_stats_copy_queue(d, NULL, &flow->qstats, flow->q->q.qlen) < 0) - return -1; - - return 0; -} - -static int atm_tc_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - return 0; -} - -static const struct Qdisc_class_ops atm_class_ops = { - .graft = atm_tc_graft, - .leaf = atm_tc_leaf, - .find = atm_tc_find, - .change = atm_tc_change, - .delete = atm_tc_delete, - .walk = atm_tc_walk, - .tcf_block = atm_tc_tcf_block, - .bind_tcf = atm_tc_bind_filter, - .unbind_tcf = atm_tc_put, - .dump = atm_tc_dump_class, - .dump_stats = atm_tc_dump_class_stats, -}; - -static struct Qdisc_ops atm_qdisc_ops __read_mostly = { - .cl_ops = &atm_class_ops, - .id = "atm", - .priv_size = sizeof(struct atm_qdisc_data), - .enqueue = atm_tc_enqueue, - .dequeue = atm_tc_dequeue, - .peek = atm_tc_peek, - .init = atm_tc_init, - .reset = atm_tc_reset, - .destroy = atm_tc_destroy, - .dump = atm_tc_dump, - .owner = THIS_MODULE, -}; - -static int __init atm_init(void) -{ - return register_qdisc(&atm_qdisc_ops); -} - -static void __exit atm_exit(void) -{ - unregister_qdisc(&atm_qdisc_ops); -} - -module_init(atm_init) -module_exit(atm_exit) -MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c deleted file mode 100644 index 3da5eb313..000000000 --- a/net/sched/sch_cbq.c +++ /dev/null @@ -1,1816 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/sched/sch_cbq.c Class-Based Queueing discipline. - * - * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> - */ - -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <net/netlink.h> -#include <net/pkt_sched.h> -#include <net/pkt_cls.h> - - -/* Class-Based Queueing (CBQ) algorithm. - ======================================= - - Sources: [1] Sally Floyd and Van Jacobson, "Link-sharing and Resource - Management Models for Packet Networks", - IEEE/ACM Transactions on Networking, Vol.3, No.4, 1995 - - [2] Sally Floyd, "Notes on CBQ and Guaranteed Service", 1995 - - [3] Sally Floyd, "Notes on Class-Based Queueing: Setting - Parameters", 1996 - - [4] Sally Floyd and Michael Speer, "Experimental Results - for Class-Based Queueing", 1998, not published. - - ----------------------------------------------------------------------- - - Algorithm skeleton was taken from NS simulator cbq.cc. - If someone wants to check this code against the LBL version, - he should take into account that ONLY the skeleton was borrowed, - the implementation is different. Particularly: - - --- The WRR algorithm is different. Our version looks more - reasonable (I hope) and works when quanta are allowed to be - less than MTU, which is always the case when real time classes - have small rates. Note, that the statement of [3] is - incomplete, delay may actually be estimated even if class - per-round allotment is less than MTU. Namely, if per-round - allotment is W*r_i, and r_1+...+r_k = r < 1 - - delay_i <= ([MTU/(W*r_i)]*W*r + W*r + k*MTU)/B - - In the worst case we have IntServ estimate with D = W*r+k*MTU - and C = MTU*r. The proof (if correct at all) is trivial. - - - --- It seems that cbq-2.0 is not very accurate. At least, I cannot - interpret some places, which look like wrong translations - from NS. Anyone is advised to find these differences - and explain to me, why I am wrong 8). - - --- Linux has no EOI event, so that we cannot estimate true class - idle time. Workaround is to consider the next dequeue event - as sign that previous packet is finished. This is wrong because of - internal device queueing, but on a permanently loaded link it is true. - Moreover, combined with clock integrator, this scheme looks - very close to an ideal solution. */ - -struct cbq_sched_data; - - -struct cbq_class { - struct Qdisc_class_common common; - struct cbq_class *next_alive; /* next class with backlog in this priority band */ - -/* Parameters */ - unsigned char priority; /* class priority */ - unsigned char priority2; /* priority to be used after overlimit */ - unsigned char ewma_log; /* time constant for idle time calculation */ - - u32 defmap; - - /* Link-sharing scheduler parameters */ - long maxidle; /* Class parameters: see below. */ - long offtime; - long minidle; - u32 avpkt; - struct qdisc_rate_table *R_tab; - - /* General scheduler (WRR) parameters */ - long allot; - long quantum; /* Allotment per WRR round */ - long weight; /* Relative allotment: see below */ - - struct Qdisc *qdisc; /* Ptr to CBQ discipline */ - struct cbq_class *split; /* Ptr to split node */ - struct cbq_class *share; /* Ptr to LS parent in the class tree */ - struct cbq_class *tparent; /* Ptr to tree parent in the class tree */ - struct cbq_class *borrow; /* NULL if class is bandwidth limited; - parent otherwise */ - struct cbq_class *sibling; /* Sibling chain */ - struct cbq_class *children; /* Pointer to children chain */ - - struct Qdisc *q; /* Elementary queueing discipline */ - - -/* Variables */ - unsigned char cpriority; /* Effective priority */ - unsigned char delayed; - unsigned char level; /* level of the class in hierarchy: - 0 for leaf classes, and maximal - level of children + 1 for nodes. - */ - - psched_time_t last; /* Last end of service */ - psched_time_t undertime; - long avgidle; - long deficit; /* Saved deficit for WRR */ - psched_time_t penalized; - struct gnet_stats_basic_packed bstats; - struct gnet_stats_queue qstats; - struct net_rate_estimator __rcu *rate_est; - struct tc_cbq_xstats xstats; - - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - - int filters; - - struct cbq_class *defaults[TC_PRIO_MAX + 1]; -}; - -struct cbq_sched_data { - struct Qdisc_class_hash clhash; /* Hash table of all classes */ - int nclasses[TC_CBQ_MAXPRIO + 1]; - unsigned int quanta[TC_CBQ_MAXPRIO + 1]; - - struct cbq_class link; - - unsigned int activemask; - struct cbq_class *active[TC_CBQ_MAXPRIO + 1]; /* List of all classes - with backlog */ - -#ifdef CONFIG_NET_CLS_ACT - struct cbq_class *rx_class; -#endif - struct cbq_class *tx_class; - struct cbq_class *tx_borrowed; - int tx_len; - psched_time_t now; /* Cached timestamp */ - unsigned int pmask; - - struct hrtimer delay_timer; - struct qdisc_watchdog watchdog; /* Watchdog timer, - started when CBQ has - backlog, but cannot - transmit just now */ - psched_tdiff_t wd_expires; - int toplevel; - u32 hgenerator; -}; - - -#define L2T(cl, len) qdisc_l2t((cl)->R_tab, len) - -static inline struct cbq_class * -cbq_class_lookup(struct cbq_sched_data *q, u32 classid) -{ - struct Qdisc_class_common *clc; - - clc = qdisc_class_find(&q->clhash, classid); - if (clc == NULL) - return NULL; - return container_of(clc, struct cbq_class, common); -} - -#ifdef CONFIG_NET_CLS_ACT - -static struct cbq_class * -cbq_reclassify(struct sk_buff *skb, struct cbq_class *this) -{ - struct cbq_class *cl; - - for (cl = this->tparent; cl; cl = cl->tparent) { - struct cbq_class *new = cl->defaults[TC_PRIO_BESTEFFORT]; - - if (new != NULL && new != this) - return new; - } - return NULL; -} - -#endif - -/* Classify packet. The procedure is pretty complicated, but - * it allows us to combine link sharing and priority scheduling - * transparently. - * - * Namely, you can put link sharing rules (f.e. route based) at root of CBQ, - * so that it resolves to split nodes. Then packets are classified - * by logical priority, or a more specific classifier may be attached - * to the split node. - */ - -static struct cbq_class * -cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *head = &q->link; - struct cbq_class **defmap; - struct cbq_class *cl = NULL; - u32 prio = skb->priority; - struct tcf_proto *fl; - struct tcf_result res; - - /* - * Step 1. If skb->priority points to one of our classes, use it. - */ - if (TC_H_MAJ(prio ^ sch->handle) == 0 && - (cl = cbq_class_lookup(q, prio)) != NULL) - return cl; - - *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - for (;;) { - int result = 0; - defmap = head->defaults; - - fl = rcu_dereference_bh(head->filter_list); - /* - * Step 2+n. Apply classifier. - */ - result = tcf_classify(skb, fl, &res, true); - if (!fl || result < 0) - goto fallback; - if (result == TC_ACT_SHOT) - return NULL; - - cl = (void *)res.class; - if (!cl) { - if (TC_H_MAJ(res.classid)) - cl = cbq_class_lookup(q, res.classid); - else if ((cl = defmap[res.classid & TC_PRIO_MAX]) == NULL) - cl = defmap[TC_PRIO_BESTEFFORT]; - - if (cl == NULL) - goto fallback; - } - if (cl->level >= head->level) - goto fallback; -#ifdef CONFIG_NET_CLS_ACT - switch (result) { - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - fallthrough; - case TC_ACT_RECLASSIFY: - return cbq_reclassify(skb, cl); - } -#endif - if (cl->level == 0) - return cl; - - /* - * Step 3+n. If classifier selected a link sharing class, - * apply agency specific classifier. - * Repeat this procdure until we hit a leaf node. - */ - head = cl; - } - -fallback: - cl = head; - - /* - * Step 4. No success... - */ - if (TC_H_MAJ(prio) == 0 && - !(cl = head->defaults[prio & TC_PRIO_MAX]) && - !(cl = head->defaults[TC_PRIO_BESTEFFORT])) - return head; - - return cl; -} - -/* - * A packet has just been enqueued on the empty class. - * cbq_activate_class adds it to the tail of active class list - * of its priority band. - */ - -static inline void cbq_activate_class(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - int prio = cl->cpriority; - struct cbq_class *cl_tail; - - cl_tail = q->active[prio]; - q->active[prio] = cl; - - if (cl_tail != NULL) { - cl->next_alive = cl_tail->next_alive; - cl_tail->next_alive = cl; - } else { - cl->next_alive = cl; - q->activemask |= (1<<prio); - } -} - -/* - * Unlink class from active chain. - * Note that this same procedure is done directly in cbq_dequeue* - * during round-robin procedure. - */ - -static void cbq_deactivate_class(struct cbq_class *this) -{ - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - int prio = this->cpriority; - struct cbq_class *cl; - struct cbq_class *cl_prev = q->active[prio]; - - do { - cl = cl_prev->next_alive; - if (cl == this) { - cl_prev->next_alive = cl->next_alive; - cl->next_alive = NULL; - - if (cl == q->active[prio]) { - q->active[prio] = cl_prev; - if (cl == q->active[prio]) { - q->active[prio] = NULL; - q->activemask &= ~(1<<prio); - return; - } - } - return; - } - } while ((cl_prev = cl) != q->active[prio]); -} - -static void -cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl) -{ - int toplevel = q->toplevel; - - if (toplevel > cl->level) { - psched_time_t now = psched_get_time(); - - do { - if (cl->undertime < now) { - q->toplevel = cl->level; - return; - } - } while ((cl = cl->borrow) != NULL && toplevel > cl->level); - } -} - -static int -cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - int ret; - struct cbq_class *cl = cbq_classify(skb, sch, &ret); - -#ifdef CONFIG_NET_CLS_ACT - q->rx_class = cl; -#endif - if (cl == NULL) { - if (ret & __NET_XMIT_BYPASS) - qdisc_qstats_drop(sch); - __qdisc_drop(skb, to_free); - return ret; - } - - ret = qdisc_enqueue(skb, cl->q, to_free); - if (ret == NET_XMIT_SUCCESS) { - sch->q.qlen++; - cbq_mark_toplevel(q, cl); - if (!cl->next_alive) - cbq_activate_class(cl); - return ret; - } - - if (net_xmit_drop_count(ret)) { - qdisc_qstats_drop(sch); - cbq_mark_toplevel(q, cl); - cl->qstats.drops++; - } - return ret; -} - -/* Overlimit action: penalize leaf class by adding offtime */ -static void cbq_overlimit(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - psched_tdiff_t delay = cl->undertime - q->now; - - if (!cl->delayed) { - delay += cl->offtime; - - /* - * Class goes to sleep, so that it will have no - * chance to work avgidle. Let's forgive it 8) - * - * BTW cbq-2.0 has a crap in this - * place, apparently they forgot to shift it by cl->ewma_log. - */ - if (cl->avgidle < 0) - delay -= (-cl->avgidle) - ((-cl->avgidle) >> cl->ewma_log); - if (cl->avgidle < cl->minidle) - cl->avgidle = cl->minidle; - if (delay <= 0) - delay = 1; - cl->undertime = q->now + delay; - - cl->xstats.overactions++; - cl->delayed = 1; - } - if (q->wd_expires == 0 || q->wd_expires > delay) - q->wd_expires = delay; - - /* Dirty work! We must schedule wakeups based on - * real available rate, rather than leaf rate, - * which may be tiny (even zero). - */ - if (q->toplevel == TC_CBQ_MAXLEVEL) { - struct cbq_class *b; - psched_tdiff_t base_delay = q->wd_expires; - - for (b = cl->borrow; b; b = b->borrow) { - delay = b->undertime - q->now; - if (delay < base_delay) { - if (delay <= 0) - delay = 1; - base_delay = delay; - } - } - - q->wd_expires = base_delay; - } -} - -static psched_tdiff_t cbq_undelay_prio(struct cbq_sched_data *q, int prio, - psched_time_t now) -{ - struct cbq_class *cl; - struct cbq_class *cl_prev = q->active[prio]; - psched_time_t sched = now; - - if (cl_prev == NULL) - return 0; - - do { - cl = cl_prev->next_alive; - if (now - cl->penalized > 0) { - cl_prev->next_alive = cl->next_alive; - cl->next_alive = NULL; - cl->cpriority = cl->priority; - cl->delayed = 0; - cbq_activate_class(cl); - - if (cl == q->active[prio]) { - q->active[prio] = cl_prev; - if (cl == q->active[prio]) { - q->active[prio] = NULL; - return 0; - } - } - - cl = cl_prev->next_alive; - } else if (sched - cl->penalized > 0) - sched = cl->penalized; - } while ((cl_prev = cl) != q->active[prio]); - - return sched - now; -} - -static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) -{ - struct cbq_sched_data *q = container_of(timer, struct cbq_sched_data, - delay_timer); - struct Qdisc *sch = q->watchdog.qdisc; - psched_time_t now; - psched_tdiff_t delay = 0; - unsigned int pmask; - - now = psched_get_time(); - - pmask = q->pmask; - q->pmask = 0; - - while (pmask) { - int prio = ffz(~pmask); - psched_tdiff_t tmp; - - pmask &= ~(1<<prio); - - tmp = cbq_undelay_prio(q, prio, now); - if (tmp > 0) { - q->pmask |= 1<<prio; - if (tmp < delay || delay == 0) - delay = tmp; - } - } - - if (delay) { - ktime_t time; - - time = 0; - time = ktime_add_ns(time, PSCHED_TICKS2NS(now + delay)); - hrtimer_start(&q->delay_timer, time, HRTIMER_MODE_ABS_PINNED); - } - - __netif_schedule(qdisc_root(sch)); - return HRTIMER_NORESTART; -} - -/* - * It is mission critical procedure. - * - * We "regenerate" toplevel cutoff, if transmitting class - * has backlog and it is not regulated. It is not part of - * original CBQ description, but looks more reasonable. - * Probably, it is wrong. This question needs further investigation. - */ - -static inline void -cbq_update_toplevel(struct cbq_sched_data *q, struct cbq_class *cl, - struct cbq_class *borrowed) -{ - if (cl && q->toplevel >= borrowed->level) { - if (cl->q->q.qlen > 1) { - do { - if (borrowed->undertime == PSCHED_PASTPERFECT) { - q->toplevel = borrowed->level; - return; - } - } while ((borrowed = borrowed->borrow) != NULL); - } -#if 0 - /* It is not necessary now. Uncommenting it - will save CPU cycles, but decrease fairness. - */ - q->toplevel = TC_CBQ_MAXLEVEL; -#endif - } -} - -static void -cbq_update(struct cbq_sched_data *q) -{ - struct cbq_class *this = q->tx_class; - struct cbq_class *cl = this; - int len = q->tx_len; - psched_time_t now; - - q->tx_class = NULL; - /* Time integrator. We calculate EOS time - * by adding expected packet transmission time. - */ - now = q->now + L2T(&q->link, len); - - for ( ; cl; cl = cl->share) { - long avgidle = cl->avgidle; - long idle; - - cl->bstats.packets++; - cl->bstats.bytes += len; - - /* - * (now - last) is total time between packet right edges. - * (last_pktlen/rate) is "virtual" busy time, so that - * - * idle = (now - last) - last_pktlen/rate - */ - - idle = now - cl->last; - if ((unsigned long)idle > 128*1024*1024) { - avgidle = cl->maxidle; - } else { - idle -= L2T(cl, len); - - /* true_avgidle := (1-W)*true_avgidle + W*idle, - * where W=2^{-ewma_log}. But cl->avgidle is scaled: - * cl->avgidle == true_avgidle/W, - * hence: - */ - avgidle += idle - (avgidle>>cl->ewma_log); - } - - if (avgidle <= 0) { - /* Overlimit or at-limit */ - - if (avgidle < cl->minidle) - avgidle = cl->minidle; - - cl->avgidle = avgidle; - - /* Calculate expected time, when this class - * will be allowed to send. - * It will occur, when: - * (1-W)*true_avgidle + W*delay = 0, i.e. - * idle = (1/W - 1)*(-true_avgidle) - * or - * idle = (1 - W)*(-cl->avgidle); - */ - idle = (-avgidle) - ((-avgidle) >> cl->ewma_log); - - /* - * That is not all. - * To maintain the rate allocated to the class, - * we add to undertime virtual clock, - * necessary to complete transmitted packet. - * (len/phys_bandwidth has been already passed - * to the moment of cbq_update) - */ - - idle -= L2T(&q->link, len); - idle += L2T(cl, len); - - cl->undertime = now + idle; - } else { - /* Underlimit */ - - cl->undertime = PSCHED_PASTPERFECT; - if (avgidle > cl->maxidle) - cl->avgidle = cl->maxidle; - else - cl->avgidle = avgidle; - } - if ((s64)(now - cl->last) > 0) - cl->last = now; - } - - cbq_update_toplevel(q, this, q->tx_borrowed); -} - -static inline struct cbq_class * -cbq_under_limit(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - struct cbq_class *this_cl = cl; - - if (cl->tparent == NULL) - return cl; - - if (cl->undertime == PSCHED_PASTPERFECT || q->now >= cl->undertime) { - cl->delayed = 0; - return cl; - } - - do { - /* It is very suspicious place. Now overlimit - * action is generated for not bounded classes - * only if link is completely congested. - * Though it is in agree with ancestor-only paradigm, - * it looks very stupid. Particularly, - * it means that this chunk of code will either - * never be called or result in strong amplification - * of burstiness. Dangerous, silly, and, however, - * no another solution exists. - */ - cl = cl->borrow; - if (!cl) { - this_cl->qstats.overlimits++; - cbq_overlimit(this_cl); - return NULL; - } - if (cl->level > q->toplevel) - return NULL; - } while (cl->undertime != PSCHED_PASTPERFECT && q->now < cl->undertime); - - cl->delayed = 0; - return cl; -} - -static inline struct sk_buff * -cbq_dequeue_prio(struct Qdisc *sch, int prio) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl_tail, *cl_prev, *cl; - struct sk_buff *skb; - int deficit; - - cl_tail = cl_prev = q->active[prio]; - cl = cl_prev->next_alive; - - do { - deficit = 0; - - /* Start round */ - do { - struct cbq_class *borrow = cl; - - if (cl->q->q.qlen && - (borrow = cbq_under_limit(cl)) == NULL) - goto skip_class; - - if (cl->deficit <= 0) { - /* Class exhausted its allotment per - * this round. Switch to the next one. - */ - deficit = 1; - cl->deficit += cl->quantum; - goto next_class; - } - - skb = cl->q->dequeue(cl->q); - - /* Class did not give us any skb :-( - * It could occur even if cl->q->q.qlen != 0 - * f.e. if cl->q == "tbf" - */ - if (skb == NULL) - goto skip_class; - - cl->deficit -= qdisc_pkt_len(skb); - q->tx_class = cl; - q->tx_borrowed = borrow; - if (borrow != cl) { -#ifndef CBQ_XSTATS_BORROWS_BYTES - borrow->xstats.borrows++; - cl->xstats.borrows++; -#else - borrow->xstats.borrows += qdisc_pkt_len(skb); - cl->xstats.borrows += qdisc_pkt_len(skb); -#endif - } - q->tx_len = qdisc_pkt_len(skb); - - if (cl->deficit <= 0) { - q->active[prio] = cl; - cl = cl->next_alive; - cl->deficit += cl->quantum; - } - return skb; - -skip_class: - if (cl->q->q.qlen == 0 || prio != cl->cpriority) { - /* Class is empty or penalized. - * Unlink it from active chain. - */ - cl_prev->next_alive = cl->next_alive; - cl->next_alive = NULL; - - /* Did cl_tail point to it? */ - if (cl == cl_tail) { - /* Repair it! */ - cl_tail = cl_prev; - - /* Was it the last class in this band? */ - if (cl == cl_tail) { - /* Kill the band! */ - q->active[prio] = NULL; - q->activemask &= ~(1<<prio); - if (cl->q->q.qlen) - cbq_activate_class(cl); - return NULL; - } - - q->active[prio] = cl_tail; - } - if (cl->q->q.qlen) - cbq_activate_class(cl); - - cl = cl_prev; - } - -next_class: - cl_prev = cl; - cl = cl->next_alive; - } while (cl_prev != cl_tail); - } while (deficit); - - q->active[prio] = cl_prev; - - return NULL; -} - -static inline struct sk_buff * -cbq_dequeue_1(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct sk_buff *skb; - unsigned int activemask; - - activemask = q->activemask & 0xFF; - while (activemask) { - int prio = ffz(~activemask); - activemask &= ~(1<<prio); - skb = cbq_dequeue_prio(sch, prio); - if (skb) - return skb; - } - return NULL; -} - -static struct sk_buff * -cbq_dequeue(struct Qdisc *sch) -{ - struct sk_buff *skb; - struct cbq_sched_data *q = qdisc_priv(sch); - psched_time_t now; - - now = psched_get_time(); - - if (q->tx_class) - cbq_update(q); - - q->now = now; - - for (;;) { - q->wd_expires = 0; - - skb = cbq_dequeue_1(sch); - if (skb) { - qdisc_bstats_update(sch, skb); - sch->q.qlen--; - return skb; - } - - /* All the classes are overlimit. - * - * It is possible, if: - * - * 1. Scheduler is empty. - * 2. Toplevel cutoff inhibited borrowing. - * 3. Root class is overlimit. - * - * Reset 2d and 3d conditions and retry. - * - * Note, that NS and cbq-2.0 are buggy, peeking - * an arbitrary class is appropriate for ancestor-only - * sharing, but not for toplevel algorithm. - * - * Our version is better, but slower, because it requires - * two passes, but it is unavoidable with top-level sharing. - */ - - if (q->toplevel == TC_CBQ_MAXLEVEL && - q->link.undertime == PSCHED_PASTPERFECT) - break; - - q->toplevel = TC_CBQ_MAXLEVEL; - q->link.undertime = PSCHED_PASTPERFECT; - } - - /* No packets in scheduler or nobody wants to give them to us :-( - * Sigh... start watchdog timer in the last case. - */ - - if (sch->q.qlen) { - qdisc_qstats_overlimit(sch); - if (q->wd_expires) - qdisc_watchdog_schedule(&q->watchdog, - now + q->wd_expires); - } - return NULL; -} - -/* CBQ class maintanance routines */ - -static void cbq_adjust_levels(struct cbq_class *this) -{ - if (this == NULL) - return; - - do { - int level = 0; - struct cbq_class *cl; - - cl = this->children; - if (cl) { - do { - if (cl->level > level) - level = cl->level; - } while ((cl = cl->sibling) != this->children); - } - this->level = level + 1; - } while ((this = this->tparent) != NULL); -} - -static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio) -{ - struct cbq_class *cl; - unsigned int h; - - if (q->quanta[prio] == 0) - return; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - /* BUGGGG... Beware! This expression suffer of - * arithmetic overflows! - */ - if (cl->priority == prio) { - cl->quantum = (cl->weight*cl->allot*q->nclasses[prio])/ - q->quanta[prio]; - } - if (cl->quantum <= 0 || - cl->quantum > 32*qdisc_dev(cl->qdisc)->mtu) { - pr_warn("CBQ: class %08x has bad quantum==%ld, repaired.\n", - cl->common.classid, cl->quantum); - cl->quantum = qdisc_dev(cl->qdisc)->mtu/2 + 1; - } - } - } -} - -static void cbq_sync_defmap(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - struct cbq_class *split = cl->split; - unsigned int h; - int i; - - if (split == NULL) - return; - - for (i = 0; i <= TC_PRIO_MAX; i++) { - if (split->defaults[i] == cl && !(cl->defmap & (1<<i))) - split->defaults[i] = NULL; - } - - for (i = 0; i <= TC_PRIO_MAX; i++) { - int level = split->level; - - if (split->defaults[i]) - continue; - - for (h = 0; h < q->clhash.hashsize; h++) { - struct cbq_class *c; - - hlist_for_each_entry(c, &q->clhash.hash[h], - common.hnode) { - if (c->split == split && c->level < level && - c->defmap & (1<<i)) { - split->defaults[i] = c; - level = c->level; - } - } - } - } -} - -static void cbq_change_defmap(struct cbq_class *cl, u32 splitid, u32 def, u32 mask) -{ - struct cbq_class *split = NULL; - - if (splitid == 0) { - split = cl->split; - if (!split) - return; - splitid = split->common.classid; - } - - if (split == NULL || split->common.classid != splitid) { - for (split = cl->tparent; split; split = split->tparent) - if (split->common.classid == splitid) - break; - } - - if (split == NULL) - return; - - if (cl->split != split) { - cl->defmap = 0; - cbq_sync_defmap(cl); - cl->split = split; - cl->defmap = def & mask; - } else - cl->defmap = (cl->defmap & ~mask) | (def & mask); - - cbq_sync_defmap(cl); -} - -static void cbq_unlink_class(struct cbq_class *this) -{ - struct cbq_class *cl, **clp; - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - - qdisc_class_hash_remove(&q->clhash, &this->common); - - if (this->tparent) { - clp = &this->sibling; - cl = *clp; - do { - if (cl == this) { - *clp = cl->sibling; - break; - } - clp = &cl->sibling; - } while ((cl = *clp) != this->sibling); - - if (this->tparent->children == this) { - this->tparent->children = this->sibling; - if (this->sibling == this) - this->tparent->children = NULL; - } - } else { - WARN_ON(this->sibling != this); - } -} - -static void cbq_link_class(struct cbq_class *this) -{ - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - struct cbq_class *parent = this->tparent; - - this->sibling = this; - qdisc_class_hash_insert(&q->clhash, &this->common); - - if (parent == NULL) - return; - - if (parent->children == NULL) { - parent->children = this; - } else { - this->sibling = parent->children->sibling; - parent->children->sibling = this; - } -} - -static void -cbq_reset(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl; - int prio; - unsigned int h; - - q->activemask = 0; - q->pmask = 0; - q->tx_class = NULL; - q->tx_borrowed = NULL; - qdisc_watchdog_cancel(&q->watchdog); - hrtimer_cancel(&q->delay_timer); - q->toplevel = TC_CBQ_MAXLEVEL; - q->now = psched_get_time(); - - for (prio = 0; prio <= TC_CBQ_MAXPRIO; prio++) - q->active[prio] = NULL; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - qdisc_reset(cl->q); - - cl->next_alive = NULL; - cl->undertime = PSCHED_PASTPERFECT; - cl->avgidle = cl->maxidle; - cl->deficit = cl->quantum; - cl->cpriority = cl->priority; - } - } -} - - -static int cbq_set_lss(struct cbq_class *cl, struct tc_cbq_lssopt *lss) -{ - if (lss->change & TCF_CBQ_LSS_FLAGS) { - cl->share = (lss->flags & TCF_CBQ_LSS_ISOLATED) ? NULL : cl->tparent; - cl->borrow = (lss->flags & TCF_CBQ_LSS_BOUNDED) ? NULL : cl->tparent; - } - if (lss->change & TCF_CBQ_LSS_EWMA) - cl->ewma_log = lss->ewma_log; - if (lss->change & TCF_CBQ_LSS_AVPKT) - cl->avpkt = lss->avpkt; - if (lss->change & TCF_CBQ_LSS_MINIDLE) - cl->minidle = -(long)lss->minidle; - if (lss->change & TCF_CBQ_LSS_MAXIDLE) { - cl->maxidle = lss->maxidle; - cl->avgidle = lss->maxidle; - } - if (lss->change & TCF_CBQ_LSS_OFFTIME) - cl->offtime = lss->offtime; - return 0; -} - -static void cbq_rmprio(struct cbq_sched_data *q, struct cbq_class *cl) -{ - q->nclasses[cl->priority]--; - q->quanta[cl->priority] -= cl->weight; - cbq_normalize_quanta(q, cl->priority); -} - -static void cbq_addprio(struct cbq_sched_data *q, struct cbq_class *cl) -{ - q->nclasses[cl->priority]++; - q->quanta[cl->priority] += cl->weight; - cbq_normalize_quanta(q, cl->priority); -} - -static int cbq_set_wrr(struct cbq_class *cl, struct tc_cbq_wrropt *wrr) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - - if (wrr->allot) - cl->allot = wrr->allot; - if (wrr->weight) - cl->weight = wrr->weight; - if (wrr->priority) { - cl->priority = wrr->priority - 1; - cl->cpriority = cl->priority; - if (cl->priority >= cl->priority2) - cl->priority2 = TC_CBQ_MAXPRIO - 1; - } - - cbq_addprio(q, cl); - return 0; -} - -static int cbq_set_fopt(struct cbq_class *cl, struct tc_cbq_fopt *fopt) -{ - cbq_change_defmap(cl, fopt->split, fopt->defmap, fopt->defchange); - return 0; -} - -static const struct nla_policy cbq_policy[TCA_CBQ_MAX + 1] = { - [TCA_CBQ_LSSOPT] = { .len = sizeof(struct tc_cbq_lssopt) }, - [TCA_CBQ_WRROPT] = { .len = sizeof(struct tc_cbq_wrropt) }, - [TCA_CBQ_FOPT] = { .len = sizeof(struct tc_cbq_fopt) }, - [TCA_CBQ_OVL_STRATEGY] = { .len = sizeof(struct tc_cbq_ovl) }, - [TCA_CBQ_RATE] = { .len = sizeof(struct tc_ratespec) }, - [TCA_CBQ_RTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE }, - [TCA_CBQ_POLICE] = { .len = sizeof(struct tc_cbq_police) }, -}; - -static int cbq_opt_parse(struct nlattr *tb[TCA_CBQ_MAX + 1], - struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - int err; - - if (!opt) { - NL_SET_ERR_MSG(extack, "CBQ options are required for this operation"); - return -EINVAL; - } - - err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, - cbq_policy, extack); - if (err < 0) - return err; - - if (tb[TCA_CBQ_WRROPT]) { - const struct tc_cbq_wrropt *wrr = nla_data(tb[TCA_CBQ_WRROPT]); - - if (wrr->priority > TC_CBQ_MAXPRIO) { - NL_SET_ERR_MSG(extack, "priority is bigger than TC_CBQ_MAXPRIO"); - err = -EINVAL; - } - } - return err; -} - -static int cbq_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct nlattr *tb[TCA_CBQ_MAX + 1]; - struct tc_ratespec *r; - int err; - - qdisc_watchdog_init(&q->watchdog, sch); - hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); - q->delay_timer.function = cbq_undelay; - - err = cbq_opt_parse(tb, opt, extack); - if (err < 0) - return err; - - if (!tb[TCA_CBQ_RTAB] || !tb[TCA_CBQ_RATE]) { - NL_SET_ERR_MSG(extack, "Rate specification missing or incomplete"); - return -EINVAL; - } - - r = nla_data(tb[TCA_CBQ_RATE]); - - q->link.R_tab = qdisc_get_rtab(r, tb[TCA_CBQ_RTAB], extack); - if (!q->link.R_tab) - return -EINVAL; - - err = tcf_block_get(&q->link.block, &q->link.filter_list, sch, extack); - if (err) - goto put_rtab; - - err = qdisc_class_hash_init(&q->clhash); - if (err < 0) - goto put_block; - - q->link.sibling = &q->link; - q->link.common.classid = sch->handle; - q->link.qdisc = sch; - q->link.q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle, NULL); - if (!q->link.q) - q->link.q = &noop_qdisc; - else - qdisc_hash_add(q->link.q, true); - - q->link.priority = TC_CBQ_MAXPRIO - 1; - q->link.priority2 = TC_CBQ_MAXPRIO - 1; - q->link.cpriority = TC_CBQ_MAXPRIO - 1; - q->link.allot = psched_mtu(qdisc_dev(sch)); - q->link.quantum = q->link.allot; - q->link.weight = q->link.R_tab->rate.rate; - - q->link.ewma_log = TC_CBQ_DEF_EWMA; - q->link.avpkt = q->link.allot/2; - q->link.minidle = -0x7FFFFFFF; - - q->toplevel = TC_CBQ_MAXLEVEL; - q->now = psched_get_time(); - - cbq_link_class(&q->link); - - if (tb[TCA_CBQ_LSSOPT]) - cbq_set_lss(&q->link, nla_data(tb[TCA_CBQ_LSSOPT])); - - cbq_addprio(q, &q->link); - return 0; - -put_block: - tcf_block_put(q->link.block); - -put_rtab: - qdisc_put_rtab(q->link.R_tab); - return err; -} - -static int cbq_dump_rate(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - - if (nla_put(skb, TCA_CBQ_RATE, sizeof(cl->R_tab->rate), &cl->R_tab->rate)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_lss(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_lssopt opt; - - opt.flags = 0; - if (cl->borrow == NULL) - opt.flags |= TCF_CBQ_LSS_BOUNDED; - if (cl->share == NULL) - opt.flags |= TCF_CBQ_LSS_ISOLATED; - opt.ewma_log = cl->ewma_log; - opt.level = cl->level; - opt.avpkt = cl->avpkt; - opt.maxidle = cl->maxidle; - opt.minidle = (u32)(-cl->minidle); - opt.offtime = cl->offtime; - opt.change = ~0; - if (nla_put(skb, TCA_CBQ_LSSOPT, sizeof(opt), &opt)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_wrropt opt; - - memset(&opt, 0, sizeof(opt)); - opt.flags = 0; - opt.allot = cl->allot; - opt.priority = cl->priority + 1; - opt.cpriority = cl->cpriority + 1; - opt.weight = cl->weight; - if (nla_put(skb, TCA_CBQ_WRROPT, sizeof(opt), &opt)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_fopt opt; - - if (cl->split || cl->defmap) { - opt.split = cl->split ? cl->split->common.classid : 0; - opt.defmap = cl->defmap; - opt.defchange = ~0; - if (nla_put(skb, TCA_CBQ_FOPT, sizeof(opt), &opt)) - goto nla_put_failure; - } - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_attr(struct sk_buff *skb, struct cbq_class *cl) -{ - if (cbq_dump_lss(skb, cl) < 0 || - cbq_dump_rate(skb, cl) < 0 || - cbq_dump_wrr(skb, cl) < 0 || - cbq_dump_fopt(skb, cl) < 0) - return -1; - return 0; -} - -static int cbq_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct nlattr *nest; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - if (cbq_dump_attr(skb, &q->link) < 0) - goto nla_put_failure; - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static int -cbq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - q->link.xstats.avgidle = q->link.avgidle; - return gnet_stats_copy_app(d, &q->link.xstats, sizeof(q->link.xstats)); -} - -static int -cbq_dump_class(struct Qdisc *sch, unsigned long arg, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - struct nlattr *nest; - - if (cl->tparent) - tcm->tcm_parent = cl->tparent->common.classid; - else - tcm->tcm_parent = TC_H_ROOT; - tcm->tcm_handle = cl->common.classid; - tcm->tcm_info = cl->q->handle; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - if (cbq_dump_attr(skb, cl) < 0) - goto nla_put_failure; - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static int -cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, - struct gnet_dump *d) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - __u32 qlen; - - cl->xstats.avgidle = cl->avgidle; - cl->xstats.undertime = 0; - qdisc_qstats_qlen_backlog(cl->q, &qlen, &cl->qstats.backlog); - - if (cl->undertime != PSCHED_PASTPERFECT) - cl->xstats.undertime = cl->undertime - q->now; - - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || - gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || - gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) - return -1; - - return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats)); -} - -static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old, struct netlink_ext_ack *extack) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - cl->common.classid, extack); - if (new == NULL) - return -ENOBUFS; - } - - *old = qdisc_replace(sch, new, &cl->q); - return 0; -} - -static struct Qdisc *cbq_leaf(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - return cl->q; -} - -static void cbq_qlen_notify(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - cbq_deactivate_class(cl); -} - -static unsigned long cbq_find(struct Qdisc *sch, u32 classid) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - return (unsigned long)cbq_class_lookup(q, classid); -} - -static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - WARN_ON(cl->filters); - - tcf_block_put(cl->block); - qdisc_put(cl->q); - qdisc_put_rtab(cl->R_tab); - gen_kill_estimator(&cl->rate_est); - if (cl != &q->link) - kfree(cl); -} - -static void cbq_destroy(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct hlist_node *next; - struct cbq_class *cl; - unsigned int h; - -#ifdef CONFIG_NET_CLS_ACT - q->rx_class = NULL; -#endif - /* - * Filters must be destroyed first because we don't destroy the - * classes from root to leafs which means that filters can still - * be bound to classes which have been destroyed already. --TGR '04 - */ - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - tcf_block_put(cl->block); - cl->block = NULL; - } - } - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry_safe(cl, next, &q->clhash.hash[h], - common.hnode) - cbq_destroy_class(sch, cl); - } - qdisc_class_hash_destroy(&q->clhash); -} - -static int -cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, - unsigned long *arg, struct netlink_ext_ack *extack) -{ - int err; - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)*arg; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_CBQ_MAX + 1]; - struct cbq_class *parent; - struct qdisc_rate_table *rtab = NULL; - - err = cbq_opt_parse(tb, opt, extack); - if (err < 0) - return err; - - if (tb[TCA_CBQ_OVL_STRATEGY] || tb[TCA_CBQ_POLICE]) { - NL_SET_ERR_MSG(extack, "Neither overlimit strategy nor policing attributes can be used for changing class params"); - return -EOPNOTSUPP; - } - - if (cl) { - /* Check parent */ - if (parentid) { - if (cl->tparent && - cl->tparent->common.classid != parentid) { - NL_SET_ERR_MSG(extack, "Invalid parent id"); - return -EINVAL; - } - if (!cl->tparent && parentid != TC_H_ROOT) { - NL_SET_ERR_MSG(extack, "Parent must be root"); - return -EINVAL; - } - } - - if (tb[TCA_CBQ_RATE]) { - rtab = qdisc_get_rtab(nla_data(tb[TCA_CBQ_RATE]), - tb[TCA_CBQ_RTAB], extack); - if (rtab == NULL) - return -EINVAL; - } - - if (tca[TCA_RATE]) { - err = gen_replace_estimator(&cl->bstats, NULL, - &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); - if (err) { - NL_SET_ERR_MSG(extack, "Failed to replace specified rate estimator"); - qdisc_put_rtab(rtab); - return err; - } - } - - /* Change class parameters */ - sch_tree_lock(sch); - - if (cl->next_alive != NULL) - cbq_deactivate_class(cl); - - if (rtab) { - qdisc_put_rtab(cl->R_tab); - cl->R_tab = rtab; - } - - if (tb[TCA_CBQ_LSSOPT]) - cbq_set_lss(cl, nla_data(tb[TCA_CBQ_LSSOPT])); - - if (tb[TCA_CBQ_WRROPT]) { - cbq_rmprio(q, cl); - cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); - } - - if (tb[TCA_CBQ_FOPT]) - cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT])); - - if (cl->q->q.qlen) - cbq_activate_class(cl); - - sch_tree_unlock(sch); - - return 0; - } - - if (parentid == TC_H_ROOT) - return -EINVAL; - - if (!tb[TCA_CBQ_WRROPT] || !tb[TCA_CBQ_RATE] || !tb[TCA_CBQ_LSSOPT]) { - NL_SET_ERR_MSG(extack, "One of the following attributes MUST be specified: WRR, rate or link sharing"); - return -EINVAL; - } - - rtab = qdisc_get_rtab(nla_data(tb[TCA_CBQ_RATE]), tb[TCA_CBQ_RTAB], - extack); - if (rtab == NULL) - return -EINVAL; - - if (classid) { - err = -EINVAL; - if (TC_H_MAJ(classid ^ sch->handle) || - cbq_class_lookup(q, classid)) { - NL_SET_ERR_MSG(extack, "Specified class not found"); - goto failure; - } - } else { - int i; - classid = TC_H_MAKE(sch->handle, 0x8000); - - for (i = 0; i < 0x8000; i++) { - if (++q->hgenerator >= 0x8000) - q->hgenerator = 1; - if (cbq_class_lookup(q, classid|q->hgenerator) == NULL) - break; - } - err = -ENOSR; - if (i >= 0x8000) { - NL_SET_ERR_MSG(extack, "Unable to generate classid"); - goto failure; - } - classid = classid|q->hgenerator; - } - - parent = &q->link; - if (parentid) { - parent = cbq_class_lookup(q, parentid); - err = -EINVAL; - if (!parent) { - NL_SET_ERR_MSG(extack, "Failed to find parentid"); - goto failure; - } - } - - err = -ENOBUFS; - cl = kzalloc(sizeof(*cl), GFP_KERNEL); - if (cl == NULL) - goto failure; - - err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); - if (err) { - kfree(cl); - goto failure; - } - - if (tca[TCA_RATE]) { - err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); - if (err) { - NL_SET_ERR_MSG(extack, "Couldn't create new estimator"); - tcf_block_put(cl->block); - kfree(cl); - goto failure; - } - } - - cl->R_tab = rtab; - rtab = NULL; - cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, - NULL); - if (!cl->q) - cl->q = &noop_qdisc; - else - qdisc_hash_add(cl->q, true); - - cl->common.classid = classid; - cl->tparent = parent; - cl->qdisc = sch; - cl->allot = parent->allot; - cl->quantum = cl->allot; - cl->weight = cl->R_tab->rate.rate; - - sch_tree_lock(sch); - cbq_link_class(cl); - cl->borrow = cl->tparent; - if (cl->tparent != &q->link) - cl->share = cl->tparent; - cbq_adjust_levels(parent); - cl->minidle = -0x7FFFFFFF; - cbq_set_lss(cl, nla_data(tb[TCA_CBQ_LSSOPT])); - cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); - if (cl->ewma_log == 0) - cl->ewma_log = q->link.ewma_log; - if (cl->maxidle == 0) - cl->maxidle = q->link.maxidle; - if (cl->avpkt == 0) - cl->avpkt = q->link.avpkt; - if (tb[TCA_CBQ_FOPT]) - cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT])); - sch_tree_unlock(sch); - - qdisc_class_hash_grow(sch, &q->clhash); - - *arg = (unsigned long)cl; - return 0; - -failure: - qdisc_put_rtab(rtab); - return err; -} - -static int cbq_delete(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - - if (cl->filters || cl->children || cl == &q->link) - return -EBUSY; - - sch_tree_lock(sch); - - qdisc_purge_queue(cl->q); - - if (cl->next_alive) - cbq_deactivate_class(cl); - - if (q->tx_borrowed == cl) - q->tx_borrowed = q->tx_class; - if (q->tx_class == cl) { - q->tx_class = NULL; - q->tx_borrowed = NULL; - } -#ifdef CONFIG_NET_CLS_ACT - if (q->rx_class == cl) - q->rx_class = NULL; -#endif - - cbq_unlink_class(cl); - cbq_adjust_levels(cl->tparent); - cl->defmap = 0; - cbq_sync_defmap(cl); - - cbq_rmprio(q, cl); - sch_tree_unlock(sch); - - cbq_destroy_class(sch, cl); - return 0; -} - -static struct tcf_block *cbq_tcf_block(struct Qdisc *sch, unsigned long arg, - struct netlink_ext_ack *extack) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - - if (cl == NULL) - cl = &q->link; - - return cl->block; -} - -static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent, - u32 classid) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *p = (struct cbq_class *)parent; - struct cbq_class *cl = cbq_class_lookup(q, classid); - - if (cl) { - if (p && p->level <= cl->level) - return 0; - cl->filters++; - return (unsigned long)cl; - } - return 0; -} - -static void cbq_unbind_filter(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - cl->filters--; -} - -static void cbq_walk(struct Qdisc *sch, struct qdisc_walker *arg) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl; - unsigned int h; - - if (arg->stop) - return; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - if (arg->count < arg->skip) { - arg->count++; - continue; - } - if (arg->fn(sch, (unsigned long)cl, arg) < 0) { - arg->stop = 1; - return; - } - arg->count++; - } - } -} - -static const struct Qdisc_class_ops cbq_class_ops = { - .graft = cbq_graft, - .leaf = cbq_leaf, - .qlen_notify = cbq_qlen_notify, - .find = cbq_find, - .change = cbq_change_class, - .delete = cbq_delete, - .walk = cbq_walk, - .tcf_block = cbq_tcf_block, - .bind_tcf = cbq_bind_filter, - .unbind_tcf = cbq_unbind_filter, - .dump = cbq_dump_class, - .dump_stats = cbq_dump_class_stats, -}; - -static struct Qdisc_ops cbq_qdisc_ops __read_mostly = { - .next = NULL, - .cl_ops = &cbq_class_ops, - .id = "cbq", - .priv_size = sizeof(struct cbq_sched_data), - .enqueue = cbq_enqueue, - .dequeue = cbq_dequeue, - .peek = qdisc_peek_dequeued, - .init = cbq_init, - .reset = cbq_reset, - .destroy = cbq_destroy, - .change = NULL, - .dump = cbq_dump, - .dump_stats = cbq_dump_stats, - .owner = THIS_MODULE, -}; - -static int __init cbq_module_init(void) -{ - return register_qdisc(&cbq_qdisc_ops); -} -static void __exit cbq_module_exit(void) -{ - unregister_qdisc(&cbq_qdisc_ops); -} -module_init(cbq_module_init) -module_exit(cbq_module_exit) -MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c deleted file mode 100644 index a75bc7f80..000000000 --- a/net/sched/sch_dsmark.c +++ /dev/null @@ -1,521 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* net/sched/sch_dsmark.c - Differentiated Services field marker */ - -/* Written 1998-2000 by Werner Almesberger, EPFL ICA */ - - -#include <linux/module.h> -#include <linux/init.h> -#include <linux/slab.h> -#include <linux/types.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <linux/rtnetlink.h> -#include <linux/bitops.h> -#include <net/pkt_sched.h> -#include <net/pkt_cls.h> -#include <net/dsfield.h> -#include <net/inet_ecn.h> -#include <asm/byteorder.h> - -/* - * classid class marking - * ------- ----- ------- - * n/a 0 n/a - * x:0 1 use entry [0] - * ... ... ... - * x:y y>0 y+1 use entry [y] - * ... ... ... - * x:indices-1 indices use entry [indices-1] - * ... ... ... - * x:y y+1 use entry [y & (indices-1)] - * ... ... ... - * 0xffff 0x10000 use entry [indices-1] - */ - - -#define NO_DEFAULT_INDEX (1 << 16) - -struct mask_value { - u8 mask; - u8 value; -}; - -struct dsmark_qdisc_data { - struct Qdisc *q; - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - struct mask_value *mv; - u16 indices; - u8 set_tc_index; - u32 default_index; /* index range is 0...0xffff */ -#define DSMARK_EMBEDDED_SZ 16 - struct mask_value embedded[DSMARK_EMBEDDED_SZ]; -}; - -static inline int dsmark_valid_index(struct dsmark_qdisc_data *p, u16 index) -{ - return index <= p->indices && index > 0; -} - -/* ------------------------- Class/flow operations ------------------------- */ - -static int dsmark_graft(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p],new %p,old %p)\n", - __func__, sch, p, new, old); - - if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle, NULL); - if (new == NULL) - new = &noop_qdisc; - } - - *old = qdisc_replace(sch, new, &p->q); - return 0; -} - -static struct Qdisc *dsmark_leaf(struct Qdisc *sch, unsigned long arg) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - return p->q; -} - -static unsigned long dsmark_find(struct Qdisc *sch, u32 classid) -{ - return TC_H_MIN(classid) + 1; -} - -static unsigned long dsmark_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) -{ - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", - __func__, sch, qdisc_priv(sch), classid); - - return dsmark_find(sch, classid); -} - -static void dsmark_unbind_filter(struct Qdisc *sch, unsigned long cl) -{ -} - -static const struct nla_policy dsmark_policy[TCA_DSMARK_MAX + 1] = { - [TCA_DSMARK_INDICES] = { .type = NLA_U16 }, - [TCA_DSMARK_DEFAULT_INDEX] = { .type = NLA_U16 }, - [TCA_DSMARK_SET_TC_INDEX] = { .type = NLA_FLAG }, - [TCA_DSMARK_MASK] = { .type = NLA_U8 }, - [TCA_DSMARK_VALUE] = { .type = NLA_U8 }, -}; - -static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, - struct nlattr **tca, unsigned long *arg, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_DSMARK_MAX + 1]; - int err = -EINVAL; - - pr_debug("%s(sch %p,[qdisc %p],classid %x,parent %x), arg 0x%lx\n", - __func__, sch, p, classid, parent, *arg); - - if (!dsmark_valid_index(p, *arg)) { - err = -ENOENT; - goto errout; - } - - if (!opt) - goto errout; - - err = nla_parse_nested_deprecated(tb, TCA_DSMARK_MAX, opt, - dsmark_policy, NULL); - if (err < 0) - goto errout; - - if (tb[TCA_DSMARK_VALUE]) - p->mv[*arg - 1].value = nla_get_u8(tb[TCA_DSMARK_VALUE]); - - if (tb[TCA_DSMARK_MASK]) - p->mv[*arg - 1].mask = nla_get_u8(tb[TCA_DSMARK_MASK]); - - err = 0; - -errout: - return err; -} - -static int dsmark_delete(struct Qdisc *sch, unsigned long arg) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - if (!dsmark_valid_index(p, arg)) - return -EINVAL; - - p->mv[arg - 1].mask = 0xff; - p->mv[arg - 1].value = 0; - - return 0; -} - -static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - int i; - - pr_debug("%s(sch %p,[qdisc %p],walker %p)\n", - __func__, sch, p, walker); - - if (walker->stop) - return; - - for (i = 0; i < p->indices; i++) { - if (p->mv[i].mask == 0xff && !p->mv[i].value) - goto ignore; - if (walker->count >= walker->skip) { - if (walker->fn(sch, i + 1, walker) < 0) { - walker->stop = 1; - break; - } - } -ignore: - walker->count++; - } -} - -static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - return p->block; -} - -/* --------------------------- Qdisc operations ---------------------------- */ - -static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - unsigned int len = qdisc_pkt_len(skb); - struct dsmark_qdisc_data *p = qdisc_priv(sch); - int err; - - pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p); - - if (p->set_tc_index) { - int wlen = skb_network_offset(skb); - - switch (skb_protocol(skb, true)) { - case htons(ETH_P_IP): - wlen += sizeof(struct iphdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) - goto drop; - - skb->tc_index = ipv4_get_dsfield(ip_hdr(skb)) - & ~INET_ECN_MASK; - break; - - case htons(ETH_P_IPV6): - wlen += sizeof(struct ipv6hdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) - goto drop; - - skb->tc_index = ipv6_get_dsfield(ipv6_hdr(skb)) - & ~INET_ECN_MASK; - break; - default: - skb->tc_index = 0; - break; - } - } - - if (TC_H_MAJ(skb->priority) == sch->handle) - skb->tc_index = TC_H_MIN(skb->priority); - else { - struct tcf_result res; - struct tcf_proto *fl = rcu_dereference_bh(p->filter_list); - int result = tcf_classify(skb, fl, &res, false); - - pr_debug("result %d class 0x%04x\n", result, res.classid); - - switch (result) { -#ifdef CONFIG_NET_CLS_ACT - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - __qdisc_drop(skb, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - - case TC_ACT_SHOT: - goto drop; -#endif - case TC_ACT_OK: - skb->tc_index = TC_H_MIN(res.classid); - break; - - default: - if (p->default_index != NO_DEFAULT_INDEX) - skb->tc_index = p->default_index; - break; - } - } - - err = qdisc_enqueue(skb, p->q, to_free); - if (err != NET_XMIT_SUCCESS) { - if (net_xmit_drop_count(err)) - qdisc_qstats_drop(sch); - return err; - } - - sch->qstats.backlog += len; - sch->q.qlen++; - - return NET_XMIT_SUCCESS; - -drop: - qdisc_drop(skb, sch, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; -} - -static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct sk_buff *skb; - u32 index; - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - skb = qdisc_dequeue_peeked(p->q); - if (skb == NULL) - return NULL; - - qdisc_bstats_update(sch, skb); - qdisc_qstats_backlog_dec(sch, skb); - sch->q.qlen--; - - index = skb->tc_index & (p->indices - 1); - pr_debug("index %d->%d\n", skb->tc_index, index); - - switch (skb_protocol(skb, true)) { - case htons(ETH_P_IP): - ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask, - p->mv[index].value); - break; - case htons(ETH_P_IPV6): - ipv6_change_dsfield(ipv6_hdr(skb), p->mv[index].mask, - p->mv[index].value); - break; - default: - /* - * Only complain if a change was actually attempted. - * This way, we can send non-IP traffic through dsmark - * and don't need yet another qdisc as a bypass. - */ - if (p->mv[index].mask != 0xff || p->mv[index].value) - pr_warn("%s: unsupported protocol %d\n", - __func__, ntohs(skb_protocol(skb, true))); - break; - } - - return skb; -} - -static struct sk_buff *dsmark_peek(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - return p->q->ops->peek(p->q); -} - -static int dsmark_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *tb[TCA_DSMARK_MAX + 1]; - int err = -EINVAL; - u32 default_index = NO_DEFAULT_INDEX; - u16 indices; - int i; - - pr_debug("%s(sch %p,[qdisc %p],opt %p)\n", __func__, sch, p, opt); - - if (!opt) - goto errout; - - err = tcf_block_get(&p->block, &p->filter_list, sch, extack); - if (err) - return err; - - err = nla_parse_nested_deprecated(tb, TCA_DSMARK_MAX, opt, - dsmark_policy, NULL); - if (err < 0) - goto errout; - - err = -EINVAL; - if (!tb[TCA_DSMARK_INDICES]) - goto errout; - indices = nla_get_u16(tb[TCA_DSMARK_INDICES]); - - if (hweight32(indices) != 1) - goto errout; - - if (tb[TCA_DSMARK_DEFAULT_INDEX]) - default_index = nla_get_u16(tb[TCA_DSMARK_DEFAULT_INDEX]); - - if (indices <= DSMARK_EMBEDDED_SZ) - p->mv = p->embedded; - else - p->mv = kmalloc_array(indices, sizeof(*p->mv), GFP_KERNEL); - if (!p->mv) { - err = -ENOMEM; - goto errout; - } - for (i = 0; i < indices; i++) { - p->mv[i].mask = 0xff; - p->mv[i].value = 0; - } - p->indices = indices; - p->default_index = default_index; - p->set_tc_index = nla_get_flag(tb[TCA_DSMARK_SET_TC_INDEX]); - - p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle, - NULL); - if (p->q == NULL) - p->q = &noop_qdisc; - else - qdisc_hash_add(p->q, true); - - pr_debug("%s: qdisc %p\n", __func__, p->q); - - err = 0; -errout: - return err; -} - -static void dsmark_reset(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - if (p->q) - qdisc_reset(p->q); -} - -static void dsmark_destroy(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - tcf_block_put(p->block); - qdisc_put(p->q); - if (p->mv != p->embedded) - kfree(p->mv); -} - -static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opts = NULL; - - pr_debug("%s(sch %p,[qdisc %p],class %ld\n", __func__, sch, p, cl); - - if (!dsmark_valid_index(p, cl)) - return -EINVAL; - - tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl - 1); - tcm->tcm_info = p->q->handle; - - opts = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (opts == NULL) - goto nla_put_failure; - if (nla_put_u8(skb, TCA_DSMARK_MASK, p->mv[cl - 1].mask) || - nla_put_u8(skb, TCA_DSMARK_VALUE, p->mv[cl - 1].value)) - goto nla_put_failure; - - return nla_nest_end(skb, opts); - -nla_put_failure: - nla_nest_cancel(skb, opts); - return -EMSGSIZE; -} - -static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opts = NULL; - - opts = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (opts == NULL) - goto nla_put_failure; - if (nla_put_u16(skb, TCA_DSMARK_INDICES, p->indices)) - goto nla_put_failure; - - if (p->default_index != NO_DEFAULT_INDEX && - nla_put_u16(skb, TCA_DSMARK_DEFAULT_INDEX, p->default_index)) - goto nla_put_failure; - - if (p->set_tc_index && - nla_put_flag(skb, TCA_DSMARK_SET_TC_INDEX)) - goto nla_put_failure; - - return nla_nest_end(skb, opts); - -nla_put_failure: - nla_nest_cancel(skb, opts); - return -EMSGSIZE; -} - -static const struct Qdisc_class_ops dsmark_class_ops = { - .graft = dsmark_graft, - .leaf = dsmark_leaf, - .find = dsmark_find, - .change = dsmark_change, - .delete = dsmark_delete, - .walk = dsmark_walk, - .tcf_block = dsmark_tcf_block, - .bind_tcf = dsmark_bind_filter, - .unbind_tcf = dsmark_unbind_filter, - .dump = dsmark_dump_class, -}; - -static struct Qdisc_ops dsmark_qdisc_ops __read_mostly = { - .next = NULL, - .cl_ops = &dsmark_class_ops, - .id = "dsmark", - .priv_size = sizeof(struct dsmark_qdisc_data), - .enqueue = dsmark_enqueue, - .dequeue = dsmark_dequeue, - .peek = dsmark_peek, - .init = dsmark_init, - .reset = dsmark_reset, - .destroy = dsmark_destroy, - .change = NULL, - .dump = dsmark_dump, - .owner = THIS_MODULE, -}; - -static int __init dsmark_module_init(void) -{ - return register_qdisc(&dsmark_qdisc_ops); -} - -static void __exit dsmark_module_exit(void) -{ - unregister_qdisc(&dsmark_qdisc_ops); -} - -module_init(dsmark_module_init) -module_exit(dsmark_module_exit) - -MODULE_LICENSE("GPL"); diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index f15fca59b..7c921760d 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -177,7 +177,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, } if (smc->conn.lgr && smc->conn.lgr->is_smcd && (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) && - !list_empty(&smc->conn.lgr->list)) { + !list_empty(&smc->conn.lgr->list) && smc->conn.rmb_desc) { struct smc_connection *conn = &smc->conn; struct smcd_diag_dmbinfo dinfo; diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 30bae60d6..ed9cfa11b 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -797,6 +797,16 @@ static void smc_pnet_create_pnetids_list(struct net *net) u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *dev; + /* Newly created netns do not have devices. + * Do not even acquire rtnl. + */ + if (list_empty(&net->dev_base_head)) + return; + + /* Note: This might not be needed, because smc_pnet_netdev_event() + * is also calling smc_pnet_add_base_pnetid() when handling + * NETDEV_UP event. + */ rtnl_lock(); for_each_netdev(net, dev) smc_pnet_add_base_pnetid(net, dev, ndev_pnetid); diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c index d435bffc6..97ff11973 100644 --- a/net/sunrpc/addr.c +++ b/net/sunrpc/addr.c @@ -284,10 +284,10 @@ char *rpc_sockaddr2uaddr(const struct sockaddr *sap, gfp_t gfp_flags) } if (snprintf(portbuf, sizeof(portbuf), - ".%u.%u", port >> 8, port & 0xff) > (int)sizeof(portbuf)) + ".%u.%u", port >> 8, port & 0xff) >= (int)sizeof(portbuf)) return NULL; - if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) > sizeof(addrbuf)) + if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) >= sizeof(addrbuf)) return NULL; return kstrdup(addrbuf, gfp_flags); diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index 2ff7b7083..e265b8d38 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -250,8 +250,8 @@ static int gssx_dec_option_array(struct xdr_stream *xdr, creds = kzalloc(sizeof(struct svc_cred), GFP_KERNEL); if (!creds) { - kfree(oa->data); - return -ENOMEM; + err = -ENOMEM; + goto free_oa; } oa->data[0].option.data = CREDS_VALUE; @@ -265,29 +265,40 @@ static int gssx_dec_option_array(struct xdr_stream *xdr, /* option buffer */ p = xdr_inline_decode(xdr, 4); - if (unlikely(p == NULL)) - return -ENOSPC; + if (unlikely(p == NULL)) { + err = -ENOSPC; + goto free_creds; + } length = be32_to_cpup(p); p = xdr_inline_decode(xdr, length); - if (unlikely(p == NULL)) - return -ENOSPC; + if (unlikely(p == NULL)) { + err = -ENOSPC; + goto free_creds; + } if (length == sizeof(CREDS_VALUE) && memcmp(p, CREDS_VALUE, sizeof(CREDS_VALUE)) == 0) { /* We have creds here. parse them */ err = gssx_dec_linux_creds(xdr, creds); if (err) - return err; + goto free_creds; oa->data[0].value.len = 1; /* presence */ } else { /* consume uninteresting buffer */ err = gssx_dec_buffer(xdr, &dummy); if (err) - return err; + goto free_creds; } } return 0; + +free_creds: + kfree(creds); +free_oa: + kfree(oa->data); + oa->data = NULL; + return err; } static int gssx_dec_status(struct xdr_stream *xdr, diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c index 78c075a68..a11e80d17 100644 --- a/net/sunrpc/xprtmultipath.c +++ b/net/sunrpc/xprtmultipath.c @@ -253,8 +253,9 @@ struct rpc_xprt *xprt_iter_current_entry(struct rpc_xprt_iter *xpi) return xprt_switch_find_current_entry(head, xpi->xpi_cursor); } -bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, - const struct sockaddr *sap) +static +bool __rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, + const struct sockaddr *sap) { struct list_head *head; struct rpc_xprt *pos; @@ -273,6 +274,18 @@ bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, return false; } +bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, + const struct sockaddr *sap) +{ + bool res; + + rcu_read_lock(); + res = __rpc_xprt_switch_has_addr(xps, sap); + rcu_read_unlock(); + + return res; +} + static struct rpc_xprt *xprt_switch_find_next_entry(struct list_head *head, const struct rpc_xprt *cur) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index df6aba224..2511718b8 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -1072,6 +1072,12 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) #ifdef CONFIG_TIPC_MEDIA_UDP if (attrs[TIPC_NLA_BEARER_UDP_OPTS]) { + if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) { + rtnl_unlock(); + NL_SET_ERR_MSG(info->extack, "UDP option is unsupported"); + return -EINVAL; + } + err = tipc_udp_nl_bearer_add(b, attrs[TIPC_NLA_BEARER_UDP_OPTS]); if (err) { diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 7ee3c8b03..2bbacd9b9 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -800,7 +800,7 @@ static void tls_update(struct sock *sk, struct proto *p, } } -static int tls_get_info(const struct sock *sk, struct sk_buff *skb) +static int tls_get_info(struct sock *sk, struct sk_buff *skb) { u16 version, cipher_type; struct tls_context *ctx; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index dd980438f..46f1c19f7 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1754,6 +1754,7 @@ int tls_sw_recvmsg(struct sock *sk, struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct tls_prot_info *prot = &tls_ctx->prot_info; struct sk_psock *psock; + int num_async, pending; unsigned char control = 0; ssize_t decrypted = 0; struct strp_msg *rxm; @@ -1766,8 +1767,6 @@ int tls_sw_recvmsg(struct sock *sk, bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool is_peek = flags & MSG_PEEK; bool bpf_strp_enabled; - int num_async = 0; - int pending; flags |= nonblock; @@ -1784,17 +1783,18 @@ int tls_sw_recvmsg(struct sock *sk, if (err < 0) { tls_err_abort(sk, err); goto end; - } else { - copied = err; } - if (len <= copied) - goto recv_end; + copied = err; + if (len <= copied || (copied && control != TLS_RECORD_TYPE_DATA)) + goto end; target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); len = len - copied; timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + decrypted = 0; + num_async = 0; while (len && (decrypted + copied < target || ctx->recv_pkt)) { bool retain_skb = false; bool zc = false; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 237488b1b..224b1fdc8 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -817,11 +817,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern) sk->sk_write_space = unix_write_space; sk->sk_max_ack_backlog = net->unx.sysctl_max_dgram_qlen; sk->sk_destruct = unix_sock_destructor; - u = unix_sk(sk); + u = unix_sk(sk); + u->inflight = 0; u->path.dentry = NULL; u->path.mnt = NULL; spin_lock_init(&u->lock); - atomic_long_set(&u->inflight, 0); INIT_LIST_HEAD(&u->link); mutex_init(&u->iolock); /* single task reading lock */ mutex_init(&u->bindlock); /* single task binding lock */ @@ -1126,13 +1126,11 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2) unix_state_lock(sk1); return; } - if (sk1 < sk2) { - unix_state_lock(sk1); - unix_state_lock_nested(sk2); - } else { - unix_state_lock(sk2); - unix_state_lock_nested(sk1); - } + if (sk1 > sk2) + swap(sk1, sk2); + + unix_state_lock(sk1); + unix_state_lock_nested(sk2, U_LOCK_SECOND); } static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2) @@ -1352,7 +1350,7 @@ restart: goto out_unlock; } - unix_state_lock_nested(sk); + unix_state_lock_nested(sk, U_LOCK_SECOND); if (sk->sk_state != st) { unix_state_unlock(sk); diff --git a/net/unix/diag.c b/net/unix/diag.c index 951b33fa8..2975e7a06 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -83,7 +83,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb) * queue lock. With the other's queue locked it's * OK to lock the state. */ - unix_state_lock_nested(req); + unix_state_lock_nested(req, U_LOCK_DIAG); peer = unix_sk(req)->peer; buf[i++] = (peer ? sock_i_ino(peer) : 0); unix_state_unlock(req); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index dc2763540..133ba5be4 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -166,17 +166,18 @@ static void scan_children(struct sock *x, void (*func)(struct unix_sock *), static void dec_inflight(struct unix_sock *usk) { - atomic_long_dec(&usk->inflight); + usk->inflight--; } static void inc_inflight(struct unix_sock *usk) { - atomic_long_inc(&usk->inflight); + usk->inflight++; } static void inc_inflight_move_tail(struct unix_sock *u) { - atomic_long_inc(&u->inflight); + u->inflight++; + /* If this still might be part of a cycle, move it to the end * of the list, so that it's checked even if it was already * passed over @@ -198,7 +199,7 @@ void wait_for_unix_gc(void) if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && !READ_ONCE(gc_in_progress)) unix_gc(); - wait_event(unix_gc_wait, gc_in_progress == false); + wait_event(unix_gc_wait, !READ_ONCE(gc_in_progress)); } /* The external entry point: unix_gc() */ @@ -234,20 +235,34 @@ void unix_gc(void) * receive queues. Other, non candidate sockets _can_ be * added to queue, so we must make sure only to touch * candidates. + * + * Embryos, though never candidates themselves, affect which + * candidates are reachable by the garbage collector. Before + * being added to a listener's queue, an embryo may already + * receive data carrying SCM_RIGHTS, potentially making the + * passed socket a candidate that is not yet reachable by the + * collector. It becomes reachable once the embryo is + * enqueued. Therefore, we must ensure that no SCM-laden + * embryo appears in a (candidate) listener's queue between + * consecutive scan_children() calls. */ list_for_each_entry_safe(u, next, &gc_inflight_list, link) { + struct sock *sk = &u->sk; long total_refs; - long inflight_refs; - total_refs = file_count(u->sk.sk_socket->file); - inflight_refs = atomic_long_read(&u->inflight); + total_refs = file_count(sk->sk_socket->file); - BUG_ON(inflight_refs < 1); - BUG_ON(total_refs < inflight_refs); - if (total_refs == inflight_refs) { + BUG_ON(!u->inflight); + BUG_ON(total_refs < u->inflight); + if (total_refs == u->inflight) { list_move_tail(&u->link, &gc_candidates); __set_bit(UNIX_GC_CANDIDATE, &u->gc_flags); __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); + + if (sk->sk_state == TCP_LISTEN) { + unix_state_lock_nested(sk, U_LOCK_GC_LISTENER); + unix_state_unlock(sk); + } } } @@ -271,7 +286,7 @@ void unix_gc(void) /* Move cursor to after the current position. */ list_move(&cursor, &u->link); - if (atomic_long_read(&u->inflight) > 0) { + if (u->inflight) { list_move_tail(&u->link, ¬_cycle_list); __clear_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); scan_children(&u->sk, inc_inflight_move_tail, NULL); diff --git a/net/unix/scm.c b/net/unix/scm.c index e8e2a00bb..4eff7da9f 100644 --- a/net/unix/scm.c +++ b/net/unix/scm.c @@ -34,10 +34,8 @@ struct sock *unix_get_socket(struct file *filp) /* PF_UNIX ? */ if (s && sock->ops && sock->ops->family == PF_UNIX) u_sock = s; - } else { - /* Could be an io_uring instance */ - u_sock = io_uring_get_socket(filp); } + return u_sock; } EXPORT_SYMBOL(unix_get_socket); @@ -54,12 +52,13 @@ void unix_inflight(struct user_struct *user, struct file *fp) if (s) { struct unix_sock *u = unix_sk(s); - if (atomic_long_inc_return(&u->inflight) == 1) { + if (!u->inflight) { BUG_ON(!list_empty(&u->link)); list_add_tail(&u->link, &gc_inflight_list); } else { BUG_ON(list_empty(&u->link)); } + u->inflight++; /* Paired with READ_ONCE() in wait_for_unix_gc() */ WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1); } @@ -76,10 +75,11 @@ void unix_notinflight(struct user_struct *user, struct file *fp) if (s) { struct unix_sock *u = unix_sk(s); - BUG_ON(!atomic_long_read(&u->inflight)); + BUG_ON(!u->inflight); BUG_ON(list_empty(&u->link)); - if (atomic_long_dec_and_test(&u->inflight)) + u->inflight--; + if (!u->inflight) list_del_init(&u->link); /* Paired with READ_ONCE() in wait_for_unix_gc() */ WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0ac829c8f..933591f97 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3595,6 +3595,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * if_idx++; } + if_start = 0; wp_idx++; } out: @@ -3771,6 +3772,8 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) if (ntype != NL80211_IFTYPE_MESH_POINT) return -EINVAL; + if (otype != NL80211_IFTYPE_MESH_POINT) + return -EINVAL; if (netif_running(dev)) return -EBUSY; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 1e6dfe204..a6c289a61 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1801,8 +1801,12 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, list_add(&new->hidden_list, &hidden->hidden_list); hidden->refcount++; + + ies = (void *)rcu_access_pointer(new->pub.beacon_ies); rcu_assign_pointer(new->pub.beacon_ies, hidden->pub.beacon_ies); + if (ies) + kfree_rcu(ies, rcu_head); } } else { /* diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 161dc194e..a7ecf2956 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -470,12 +470,12 @@ static int x25_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) goto out; - len = min_t(unsigned int, len, sizeof(int)); - rc = -EINVAL; if (len < 0) goto out; + len = min_t(unsigned int, len, sizeof(int)); + rc = -EFAULT; if (put_user(len, optlen)) goto out; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index d04f91f4d..562d69f17 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -895,6 +895,8 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, struct xsk_queue **q; int entries; + if (optlen < sizeof(entries)) + return -EINVAL; if (copy_from_sockptr(&entries, optval, sizeof(entries))) return -EFAULT; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 8fce2e93b..070946d09 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1753,6 +1753,9 @@ static int copy_to_user_tmpl(struct xfrm_policy *xp, struct sk_buff *skb) if (xp->xfrm_nr == 0) return 0; + if (xp->xfrm_nr > XFRM_MAX_DEPTH) + return -ENOBUFS; + for (i = 0; i < xp->xfrm_nr; i++) { struct xfrm_user_tmpl *up = &vec[i]; struct xfrm_tmpl *kp = &xp->xfrm_vec[i]; diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index fe327a453..eb01e8d07 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -53,6 +53,8 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-to-enum-cast) KBUILD_CFLAGS += -Wno-tautological-constant-out-of-range-compare KBUILD_CFLAGS += $(call cc-disable-warning, unaligned-access) KBUILD_CFLAGS += $(call cc-disable-warning, cast-function-type-strict) +KBUILD_CFLAGS += -Wno-enum-compare-conditional +KBUILD_CFLAGS += -Wno-enum-enum-conversion endif endif diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index 31484377b..806240dda 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -284,7 +284,7 @@ eBPF programs can have an associated license, passed along with the bytecode instructions to the kernel when the programs are loaded. The format for that string is identical to the one in use for kernel modules (Dual licenses, such as "Dual BSD/GPL", may be used). Some helper functions are only accessible to -programs that are compatible with the GNU Privacy License (GPL). +programs that are compatible with the GNU General Public License (GNU GPL). In order to use such helpers, the eBPF program must be loaded with the correct license string passed (via **attr**) to the **bpf**\ () system call, and this diff --git a/scripts/clang-tools/gen_compile_commands.py b/scripts/clang-tools/gen_compile_commands.py index 8bf55bb4f..96e4865ee 100755 --- a/scripts/clang-tools/gen_compile_commands.py +++ b/scripts/clang-tools/gen_compile_commands.py @@ -176,7 +176,7 @@ def process_line(root_directory, command_prefix, file_path): # escape the pound sign '#', either as '\#' or '$(pound)' (depending on the # kernel version). The compile_commands.json file is not interepreted # by Make, so this code replaces the escaped version with '#'. - prefix = command_prefix.replace('\#', '#').replace('$(pound)', '#') + prefix = command_prefix.replace(r'\#', '#').replace('$(pound)', '#') # Use os.path.abspath() to normalize the path resolving '.' and '..' . abs_path = os.path.abspath(os.path.join(root_directory, file_path)) diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh index 90398347e..3463f0f6c 100755 --- a/scripts/decode_stacktrace.sh +++ b/scripts/decode_stacktrace.sh @@ -9,6 +9,29 @@ if [[ $# < 1 ]]; then exit 1 fi +# Try to find a Rust demangler +if type llvm-cxxfilt >/dev/null 2>&1 ; then + cppfilt=llvm-cxxfilt +elif type c++filt >/dev/null 2>&1 ; then + cppfilt=c++filt + cppfilt_opts=-i +fi + +UTIL_SUFFIX= +if [[ -z ${LLVM:-} ]]; then + UTIL_PREFIX=${CROSS_COMPILE:-} +else + UTIL_PREFIX=llvm- + if [[ ${LLVM} == */ ]]; then + UTIL_PREFIX=${LLVM}${UTIL_PREFIX} + elif [[ ${LLVM} == -* ]]; then + UTIL_SUFFIX=${LLVM} + fi +fi + +READELF=${UTIL_PREFIX}readelf${UTIL_SUFFIX} +ADDR2LINE=${UTIL_PREFIX}addr2line${UTIL_SUFFIX} + if [[ $1 == "-r" ]] ; then vmlinux="" basepath="auto" @@ -33,13 +56,18 @@ else release="" fi -declare -A cache -declare -A modcache +declare aarray_support=true +declare -A cache 2>/dev/null +if [[ $? != 0 ]]; then + aarray_support=false +else + declare -A modcache +fi find_module() { if [[ "$modpath" != "" ]] ; then for fn in $(find "$modpath" -name "${module//_/[-_]}.ko*") ; do - if readelf -WS "$fn" | grep -qwF .debug_line ; then + if ${READELF} -WS "$fn" | grep -qwF .debug_line ; then echo $fn return fi @@ -51,7 +79,7 @@ find_module() { find_module && return if [[ $release == "" ]] ; then - release=$(gdb -ex 'print init_uts_ns.name.release' -ex 'quit' -quiet -batch "$vmlinux" | sed -n 's/\$1 = "\(.*\)".*/\1/p') + release=$(gdb -ex 'print init_uts_ns.name.release' -ex 'quit' -quiet -batch "$vmlinux" 2>/dev/null | sed -n 's/\$1 = "\(.*\)".*/\1/p') fi for dn in {/usr/lib/debug,}/lib/modules/$release ; do @@ -74,7 +102,7 @@ parse_symbol() { if [[ $module == "" ]] ; then local objfile=$vmlinux - elif [[ "${modcache[$module]+isset}" == "isset" ]]; then + elif [[ $aarray_support == true && "${modcache[$module]+isset}" == "isset" ]]; then local objfile=${modcache[$module]} else local objfile=$(find_module) @@ -82,7 +110,9 @@ parse_symbol() { echo "WARNING! Modules path isn't set, but is needed to parse this symbol" >&2 return fi - modcache[$module]=$objfile + if [[ $aarray_support == true ]]; then + modcache[$module]=$objfile + fi fi # Remove the englobing parenthesis @@ -102,15 +132,17 @@ parse_symbol() { # Use 'nm vmlinux' to figure out the base address of said symbol. # It's actually faster to call it every time than to load it # all into bash. - if [[ "${cache[$module,$name]+isset}" == "isset" ]]; then + if [[ $aarray_support == true && "${cache[$module,$name]+isset}" == "isset" ]]; then local base_addr=${cache[$module,$name]} else - local base_addr=$(nm "$objfile" | awk '$3 == "'$name'" && ($2 == "t" || $2 == "T") {print $1; exit}') + local base_addr=$(nm "$objfile" 2>/dev/null | awk '$3 == "'$name'" && ($2 == "t" || $2 == "T") {print $1; exit}') if [[ $base_addr == "" ]] ; then # address not found return fi - cache[$module,$name]="$base_addr" + if [[ $aarray_support == true ]]; then + cache[$module,$name]="$base_addr" + fi fi # Let's start doing the math to get the exact address into the # symbol. First, strip out the symbol total length. @@ -126,11 +158,13 @@ parse_symbol() { # Pass it to addr2line to get filename and line number # Could get more than one result - if [[ "${cache[$module,$address]+isset}" == "isset" ]]; then + if [[ $aarray_support == true && "${cache[$module,$address]+isset}" == "isset" ]]; then local code=${cache[$module,$address]} else - local code=$(${CROSS_COMPILE}addr2line -i -e "$objfile" "$address") - cache[$module,$address]=$code + local code=$(${ADDR2LINE} -i -e "$objfile" "$address" 2>/dev/null) + if [[ $aarray_support == true ]]; then + cache[$module,$address]=$code + fi fi # addr2line doesn't return a proper error code if it fails, so @@ -146,6 +180,12 @@ parse_symbol() { # In the case of inlines, move everything to same line code=${code//$'\n'/' '} + # Demangle if the name looks like a Rust symbol and if + # we got a Rust demangler + if [[ $name =~ ^_R && $cppfilt != "" ]] ; then + name=$("$cppfilt" "$cppfilt_opts" "$name") + fi + # Replace old address with pretty line numbers symbol="$segment$name ($code)" } diff --git a/scripts/dummy-tools/gcc b/scripts/dummy-tools/gcc index 485427f40..91df612bf 100755 --- a/scripts/dummy-tools/gcc +++ b/scripts/dummy-tools/gcc @@ -76,7 +76,11 @@ fi if arg_contain -S "$@"; then # For scripts/gcc-x86-*-has-stack-protector.sh if arg_contain -fstack-protector "$@"; then - echo "%gs" + if arg_contain -mstack-protector-guard-reg=fs "$@"; then + echo "%fs" + else + echo "%gs" + fi exit 0 fi fi diff --git a/scripts/gcc-x86_32-has-stack-protector.sh b/scripts/gcc-x86_32-has-stack-protector.sh index f5c119495..825c75c5b 100755 --- a/scripts/gcc-x86_32-has-stack-protector.sh +++ b/scripts/gcc-x86_32-has-stack-protector.sh @@ -1,4 +1,8 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 -echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -m32 -O0 -fstack-protector - -o - 2> /dev/null | grep -q "%gs" +# This requires GCC 8.1 or better. Specifically, we require +# -mstack-protector-guard-reg, added by +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81708 + +echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -m32 -O0 -fstack-protector -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard - -o - 2> /dev/null | grep -q "%fs" diff --git a/scripts/get_abi.pl b/scripts/get_abi.pl index 92d9aa6cc..db6098c42 100755 --- a/scripts/get_abi.pl +++ b/scripts/get_abi.pl @@ -75,7 +75,7 @@ sub parse_abi { $name =~ s,.*/,,; my $fn = $file; - $fn =~ s,Documentation/ABI/,,; + $fn =~ s,.*Documentation/ABI/,,; my $nametag = "File $fn"; $data{$nametag}->{what} = "File $name"; diff --git a/scripts/kconfig/lexer.l b/scripts/kconfig/lexer.l index 240109f96..72e5e9ac5 100644 --- a/scripts/kconfig/lexer.l +++ b/scripts/kconfig/lexer.l @@ -305,8 +305,11 @@ static char *expand_token(const char *in, size_t n) new_string(); append_string(in, n); - /* get the whole line because we do not know the end of token. */ - while ((c = input()) != EOF) { + /* + * get the whole line because we do not know the end of token. + * input() returns 0 (not EOF!) when it reachs the end of file. + */ + while ((c = input()) != 0) { if (c == '\n') { unput(c); break; diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 19af6dd16..8e3257f1e 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1232,7 +1232,8 @@ sub dump_struct($$) { $members =~ s/DECLARE_KFIFO\s*\(([^,)]+),\s*([^,)]+),\s*([^,)]+)\)/$2 \*$1/gos; # replace DECLARE_KFIFO_PTR $members =~ s/DECLARE_KFIFO_PTR\s*\(([^,)]+),\s*([^,)]+)\)/$2 \*$1/gos; - + # replace DECLARE_FLEX_ARRAY + $members =~ s/(?:__)?DECLARE_FLEX_ARRAY\s*\(([^,)]+),\s*([^,)]+)\)/$1 $2\[\]/gos; my $declaration = $members; # Split nested struct/union elements as newer ones diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index acd07a70a..3a1ffd84e 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -171,8 +171,13 @@ gen_btf() ${OBJCOPY} --only-section=.BTF --set-section-flags .BTF=alloc,readonly \ --strip-all ${1} ${2} 2>/dev/null # Change e_type to ET_REL so that it can be used to link final vmlinux. - # Unlike GNU ld, lld does not allow an ET_EXEC input. - printf '\1' | dd of=${2} conv=notrunc bs=1 seek=16 status=none + # GNU ld 2.35+ and lld do not allow an ET_EXEC input. + if [ -n "${CONFIG_CPU_BIG_ENDIAN}" ]; then + et_rel='\0\1' + else + et_rel='\1\0' + fi + printf "${et_rel}" | dd of=${2} conv=notrunc bs=1 seek=16 status=none } # Create ${2} .S file with all symbols from the ${1} object file diff --git a/scripts/mod/sumversion.c b/scripts/mod/sumversion.c index d587f40f1..b6eda411b 100644 --- a/scripts/mod/sumversion.c +++ b/scripts/mod/sumversion.c @@ -328,7 +328,12 @@ static int parse_source_files(const char *objfile, struct md4_ctx *md) /* Sum all files in the same dir or subdirs. */ while ((line = get_line(&pos))) { - char* p = line; + char* p; + + /* trim the leading spaces away */ + while (isspace(*line)) + line++; + p = line; if (strncmp(line, "source_", sizeof("source_")-1) == 0) { p = strrchr(line, ' '); diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 585edcc68..052f1b920 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1070,11 +1070,10 @@ static struct aa_label *sk_peer_label(struct sock *sk) * Note: for tcp only valid if using ipsec or cipso on lan */ static int apparmor_socket_getpeersec_stream(struct socket *sock, - char __user *optval, - int __user *optlen, + sockptr_t optval, sockptr_t optlen, unsigned int len) { - char *name; + char *name = NULL; int slen, error = 0; struct aa_label *label; struct aa_label *peer; @@ -1091,23 +1090,21 @@ static int apparmor_socket_getpeersec_stream(struct socket *sock, /* don't include terminating \0 in slen, it breaks some apps */ if (slen < 0) { error = -ENOMEM; - } else { - if (slen > len) { - error = -ERANGE; - } else if (copy_to_user(optval, name, slen)) { - error = -EFAULT; - goto out; - } - if (put_user(slen, optlen)) - error = -EFAULT; -out: - kfree(name); - + goto done; + } + if (slen > len) { + error = -ERANGE; + goto done_len; } + if (copy_to_sockptr(optval, name, slen)) + error = -EFAULT; +done_len: + if (copy_to_sockptr(optlen, &slen, sizeof(slen))) + error = -EFAULT; done: end_current_label_crit_section(label); - + kfree(name); return error; } diff --git a/security/security.c b/security/security.c index f9157d502..0bbcb100b 100644 --- a/security/security.c +++ b/security/security.c @@ -1498,6 +1498,24 @@ int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } EXPORT_SYMBOL_GPL(security_file_ioctl); +/** + * security_file_ioctl_compat() - Check if an ioctl is allowed in compat mode + * @file: associated file + * @cmd: ioctl cmd + * @arg: ioctl arguments + * + * Compat version of security_file_ioctl() that correctly handles 32-bit + * processes running on 64-bit kernels. + * + * Return: Returns 0 if permission is granted. + */ +int security_file_ioctl_compat(struct file *file, unsigned int cmd, + unsigned long arg) +{ + return call_int_hook(file_ioctl_compat, 0, file, cmd, arg); +} +EXPORT_SYMBOL_GPL(security_file_ioctl_compat); + static inline unsigned long mmap_prot(struct file *file, unsigned long prot) { /* @@ -2080,7 +2098,19 @@ EXPORT_SYMBOL(security_inode_setsecctx); int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { - return call_int_hook(inode_getsecctx, -EOPNOTSUPP, inode, ctx, ctxlen); + struct security_hook_list *hp; + int rc; + + /* + * Only one module will provide a security context. + */ + hlist_for_each_entry(hp, &security_hook_heads.inode_getsecctx, list) { + rc = hp->hook.inode_getsecctx(inode, ctx, ctxlen); + if (rc != LSM_RET_DEFAULT(inode_getsecctx)) + return rc; + } + + return LSM_RET_DEFAULT(inode_getsecctx); } EXPORT_SYMBOL(security_inode_getsecctx); @@ -2194,17 +2224,40 @@ int security_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(security_sock_rcv_skb); -int security_socket_getpeersec_stream(struct socket *sock, char __user *optval, - int __user *optlen, unsigned len) +int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, + sockptr_t optlen, unsigned int len) { - return call_int_hook(socket_getpeersec_stream, -ENOPROTOOPT, sock, - optval, optlen, len); + struct security_hook_list *hp; + int rc; + + /* + * Only one module will provide a security context. + */ + hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_stream, + list) { + rc = hp->hook.socket_getpeersec_stream(sock, optval, optlen, + len); + if (rc != LSM_RET_DEFAULT(socket_getpeersec_stream)) + return rc; + } + return LSM_RET_DEFAULT(socket_getpeersec_stream); } int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { - return call_int_hook(socket_getpeersec_dgram, -ENOPROTOOPT, sock, - skb, secid); + struct security_hook_list *hp; + int rc; + + /* + * Only one module will provide a security context. + */ + hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_dgram, + list) { + rc = hp->hook.socket_getpeersec_dgram(sock, skb, secid); + if (rc != LSM_RET_DEFAULT(socket_getpeersec_dgram)) + return rc; + } + return LSM_RET_DEFAULT(socket_getpeersec_dgram); } EXPORT_SYMBOL(security_socket_getpeersec_dgram); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index f545321d9..46c00a68b 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3662,6 +3662,33 @@ static int selinux_file_ioctl(struct file *file, unsigned int cmd, return error; } +static int selinux_file_ioctl_compat(struct file *file, unsigned int cmd, + unsigned long arg) +{ + /* + * If we are in a 64-bit kernel running 32-bit userspace, we need to + * make sure we don't compare 32-bit flags to 64-bit flags. + */ + switch (cmd) { + case FS_IOC32_GETFLAGS: + cmd = FS_IOC_GETFLAGS; + break; + case FS_IOC32_SETFLAGS: + cmd = FS_IOC_SETFLAGS; + break; + case FS_IOC32_GETVERSION: + cmd = FS_IOC_GETVERSION; + break; + case FS_IOC32_SETVERSION: + cmd = FS_IOC_SETVERSION; + break; + default: + break; + } + + return selinux_file_ioctl(file, cmd, arg); +} + static int default_noexec __ro_after_init; static int file_map_prot_check(struct file *file, unsigned long prot, int shared) @@ -5083,11 +5110,12 @@ static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) return err; } -static int selinux_socket_getpeersec_stream(struct socket *sock, char __user *optval, - int __user *optlen, unsigned len) +static int selinux_socket_getpeersec_stream(struct socket *sock, + sockptr_t optval, sockptr_t optlen, + unsigned int len) { int err = 0; - char *scontext; + char *scontext = NULL; u32 scontext_len; struct sk_security_struct *sksec = sock->sk->sk_security; u32 peer_sid = SECSID_NULL; @@ -5103,17 +5131,15 @@ static int selinux_socket_getpeersec_stream(struct socket *sock, char __user *op &scontext_len); if (err) return err; - if (scontext_len > len) { err = -ERANGE; goto out_len; } - if (copy_to_user(optval, scontext, scontext_len)) + if (copy_to_sockptr(optval, scontext, scontext_len)) err = -EFAULT; - out_len: - if (put_user(scontext_len, optlen)) + if (copy_to_sockptr(optlen, &scontext_len, sizeof(scontext_len))) err = -EFAULT; kfree(scontext); return err; @@ -7049,6 +7075,7 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(file_permission, selinux_file_permission), LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security), LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl), + LSM_HOOK_INIT(file_ioctl_compat, selinux_file_ioctl_compat), LSM_HOOK_INIT(mmap_file, selinux_mmap_file), LSM_HOOK_INIT(mmap_addr, selinux_mmap_addr), LSM_HOOK_INIT(file_mprotect, selinux_file_mprotect), diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 814518ad4..750f6007b 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1280,7 +1280,8 @@ static int smack_inode_setxattr(struct dentry *dentry, const char *name, check_star = 1; } else if (strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0) { check_priv = 1; - if (size != TRANS_TRUE_SIZE || + if (!S_ISDIR(d_backing_inode(dentry)->i_mode) || + size != TRANS_TRUE_SIZE || strncmp(value, TRANS_TRUE, TRANS_TRUE_SIZE) != 0) rc = -EINVAL; } else @@ -2721,6 +2722,15 @@ static int smack_inode_setsecurity(struct inode *inode, const char *name, if (value == NULL || size > SMK_LONGLABEL || size == 0) return -EINVAL; + if (strcmp(name, XATTR_SMACK_TRANSMUTE) == 0) { + if (!S_ISDIR(inode->i_mode) || size != TRANS_TRUE_SIZE || + strncmp(value, TRANS_TRUE, TRANS_TRUE_SIZE) != 0) + return -EINVAL; + + nsp->smk_flags |= SMK_INODE_TRANSMUTE; + return 0; + } + skp = smk_import_entry(value, size); if (IS_ERR(skp)) return PTR_ERR(skp); @@ -4022,12 +4032,12 @@ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) * returns zero on success, an error code otherwise */ static int smack_socket_getpeersec_stream(struct socket *sock, - char __user *optval, - int __user *optlen, unsigned len) + sockptr_t optval, sockptr_t optlen, + unsigned int len) { struct socket_smack *ssp; char *rcp = ""; - int slen = 1; + u32 slen = 1; int rc = 0; ssp = sock->sk->sk_security; @@ -4035,15 +4045,16 @@ static int smack_socket_getpeersec_stream(struct socket *sock, rcp = ssp->smk_packet->smk_known; slen = strlen(rcp) + 1; } - - if (slen > len) + if (slen > len) { rc = -ERANGE; - else if (copy_to_user(optval, rcp, slen) != 0) - rc = -EFAULT; + goto out_len; + } - if (put_user(slen, optlen) != 0) + if (copy_to_sockptr(optval, rcp, slen)) + rc = -EFAULT; +out_len: + if (copy_to_sockptr(optlen, &slen, sizeof(slen))) rc = -EFAULT; - return rc; } @@ -4767,6 +4778,7 @@ static struct security_hook_list smack_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(file_alloc_security, smack_file_alloc_security), LSM_HOOK_INIT(file_ioctl, smack_file_ioctl), + LSM_HOOK_INIT(file_ioctl_compat, smack_file_ioctl), LSM_HOOK_INIT(file_lock, smack_file_lock), LSM_HOOK_INIT(file_fcntl, smack_file_fcntl), LSM_HOOK_INIT(mmap_file, smack_mmap_file), diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index 4bee32bfe..6235c3be8 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -2657,13 +2657,14 @@ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, { int error = buffer_len; size_t avail_len = buffer_len; - char *cp0 = head->write_buf; + char *cp0; int idx; if (!head->write) return -EINVAL; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; + cp0 = head->write_buf; head->read_user_buf_avail = 0; idx = tomoyo_read_lock(); /* Read a line and dispatch it to the policy handler. */ diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index 1f3cd432d..a8dc3ae93 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -548,6 +548,7 @@ static struct security_hook_list tomoyo_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(path_rename, tomoyo_path_rename), LSM_HOOK_INIT(inode_getattr, tomoyo_inode_getattr), LSM_HOOK_INIT(file_ioctl, tomoyo_file_ioctl), + LSM_HOOK_INIT(file_ioctl_compat, tomoyo_file_ioctl), LSM_HOOK_INIT(path_chmod, tomoyo_path_chmod), LSM_HOOK_INIT(path_chown, tomoyo_path_chown), LSM_HOOK_INIT(path_chroot, tomoyo_path_chroot), diff --git a/sound/core/Makefile b/sound/core/Makefile index d123587c0..bc04acf4a 100644 --- a/sound/core/Makefile +++ b/sound/core/Makefile @@ -32,7 +32,6 @@ snd-pcm-dmaengine-objs := pcm_dmaengine.o snd-rawmidi-objs := rawmidi.o snd-timer-objs := timer.o snd-hrtimer-objs := hrtimer.o -snd-rtctimer-objs := rtctimer.o snd-hwdep-objs := hwdep.o snd-seq-device-objs := seq_device.o diff --git a/sound/core/seq/seq_midi.c b/sound/core/seq/seq_midi.c index 6825940ea..a741d1ae6 100644 --- a/sound/core/seq/seq_midi.c +++ b/sound/core/seq/seq_midi.c @@ -111,6 +111,12 @@ static int dump_midi(struct snd_rawmidi_substream *substream, const char *buf, i return 0; } +/* callback for snd_seq_dump_var_event(), bridging to dump_midi() */ +static int __dump_midi(void *ptr, void *buf, int count) +{ + return dump_midi(ptr, buf, count); +} + static int event_process_midi(struct snd_seq_event *ev, int direct, void *private_data, int atomic, int hop) { @@ -130,7 +136,7 @@ static int event_process_midi(struct snd_seq_event *ev, int direct, pr_debug("ALSA: seq_midi: invalid sysex event flags = 0x%x\n", ev->flags); return 0; } - snd_seq_dump_var_event(ev, (snd_seq_dump_func_t)dump_midi, substream); + snd_seq_dump_var_event(ev, __dump_midi, substream); snd_midi_event_reset_decode(msynth->parser); } else { if (msynth->parser == NULL) diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c index 77d7037d1..82396b8c8 100644 --- a/sound/core/seq/seq_virmidi.c +++ b/sound/core/seq/seq_virmidi.c @@ -62,6 +62,13 @@ static void snd_virmidi_init_event(struct snd_virmidi *vmidi, /* * decode input event and put to read buffer of each opened file */ + +/* callback for snd_seq_dump_var_event(), bridging to snd_rawmidi_receive() */ +static int dump_to_rawmidi(void *ptr, void *buf, int count) +{ + return snd_rawmidi_receive(ptr, buf, count); +} + static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev, struct snd_seq_event *ev, bool atomic) @@ -80,7 +87,7 @@ static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev, if (ev->type == SNDRV_SEQ_EVENT_SYSEX) { if ((ev->flags & SNDRV_SEQ_EVENT_LENGTH_MASK) != SNDRV_SEQ_EVENT_LENGTH_VARIABLE) continue; - snd_seq_dump_var_event(ev, (snd_seq_dump_func_t)snd_rawmidi_receive, vmidi->substream); + snd_seq_dump_var_event(ev, dump_to_rawmidi, vmidi->substream); snd_midi_event_reset_decode(vmidi->parser); } else { len = snd_midi_event_decode(vmidi->parser, msg, sizeof(msg), ev); diff --git a/sound/hda/hdac_stream.c b/sound/hda/hdac_stream.c index 557072245..e510bf099 100644 --- a/sound/hda/hdac_stream.c +++ b/sound/hda/hdac_stream.c @@ -605,17 +605,15 @@ void snd_hdac_stream_timecounter_init(struct hdac_stream *azx_dev, struct hdac_stream *s; bool inited = false; u64 cycle_last = 0; - int i = 0; list_for_each_entry(s, &bus->stream_list, list) { - if (streams & (1 << i)) { + if ((streams & (1 << s->index))) { azx_timecounter_init(s, inited, cycle_last); if (!inited) { inited = true; cycle_last = s->tc.cycle_last; } } - i++; } snd_pcm_gettime(runtime, &runtime->trigger_tstamp); @@ -660,14 +658,13 @@ void snd_hdac_stream_sync(struct hdac_stream *azx_dev, bool start, unsigned int streams) { struct hdac_bus *bus = azx_dev->bus; - int i, nwait, timeout; + int nwait, timeout; struct hdac_stream *s; for (timeout = 5000; timeout; timeout--) { nwait = 0; - i = 0; list_for_each_entry(s, &bus->stream_list, list) { - if (!(streams & (1 << i++))) + if (!(streams & (1 << s->index))) continue; if (start) { diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 48c78388c..ea0a2b1d2 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -372,6 +372,16 @@ static const struct config_entry config_table[] = { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x7e28, }, + /* ArrowLake-S */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = PCI_DEVICE_ID_INTEL_HDA_ARL_S, + }, + /* ArrowLake */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = PCI_DEVICE_ID_INTEL_HDA_ARL, + }, #endif /* Lunar Lake */ diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 12c6eb76f..a3c6a5eeb 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2581,6 +2581,8 @@ static const struct pci_device_id azx_ids[] = { .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, { PCI_DEVICE(0x8086, 0x4b58), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* Arrow Lake */ + { PCI_DEVICE_DATA(INTEL, HDA_ARL, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE) }, /* Broxton-P(Apollolake) */ { PCI_DEVICE(0x8086, 0x5a98), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_BROXTON }, diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index e35c470eb..5b37f5f14 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -235,6 +235,7 @@ enum { CXT_FIXUP_HP_ZBOOK_MUTE_LED, CXT_FIXUP_HEADSET_MIC, CXT_FIXUP_HP_MIC_NO_PRESENCE, + CXT_PINCFG_SWS_JS201D, }; /* for hda_fixup_thinkpad_acpi() */ @@ -732,6 +733,17 @@ static const struct hda_pintbl cxt_pincfg_lemote[] = { {} }; +/* SuoWoSi/South-holding JS201D with sn6140 */ +static const struct hda_pintbl cxt_pincfg_sws_js201d[] = { + { 0x16, 0x03211040 }, /* hp out */ + { 0x17, 0x91170110 }, /* SPK/Class_D */ + { 0x18, 0x95a70130 }, /* Internal mic */ + { 0x19, 0x03a11020 }, /* Headset Mic */ + { 0x1a, 0x40f001f0 }, /* Not used */ + { 0x21, 0x40f001f0 }, /* Not used */ + {} +}; + static const struct hda_fixup cxt_fixups[] = { [CXT_PINCFG_LENOVO_X200] = { .type = HDA_FIXUP_PINS, @@ -887,6 +899,10 @@ static const struct hda_fixup cxt_fixups[] = { .chained = true, .chain_id = CXT_FIXUP_HEADSET_MIC, }, + [CXT_PINCFG_SWS_JS201D] = { + .type = HDA_FIXUP_PINS, + .v.pins = cxt_pincfg_sws_js201d, + }, }; static const struct snd_pci_quirk cxt5045_fixups[] = { @@ -960,6 +976,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x8457, "HP Z2 G4 mini", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8458, "HP Z2 G4 mini premium", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN), + SND_PCI_QUIRK(0x14f1, 0x0265, "SWS JS201D", CXT_PINCFG_SWS_JS201D), SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO), SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo T410", CXT_PINCFG_LENOVO_TP410), @@ -1000,6 +1017,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = { { .id = CXT_FIXUP_HP_ZBOOK_MUTE_LED, .name = "hp-zbook-mute-led" }, { .id = CXT_FIXUP_HP_MIC_NO_PRESENCE, .name = "hp-mic-fix" }, { .id = CXT_PINCFG_LENOVO_NOTEBOOK, .name = "lenovo-20149" }, + { .id = CXT_PINCFG_SWS_JS201D, .name = "sws-js201d" }, {} }; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 412fbe098..84df5582c 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6612,6 +6612,60 @@ static void alc285_fixup_hp_spectre_x360(struct hda_codec *codec, } } +static void alc285_fixup_hp_envy_x360(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + static const struct coef_fw coefs[] = { + WRITE_COEF(0x08, 0x6a0c), WRITE_COEF(0x0d, 0xa023), + WRITE_COEF(0x10, 0x0320), WRITE_COEF(0x1a, 0x8c03), + WRITE_COEF(0x25, 0x1800), WRITE_COEF(0x26, 0x003a), + WRITE_COEF(0x28, 0x1dfe), WRITE_COEF(0x29, 0xb014), + WRITE_COEF(0x2b, 0x1dfe), WRITE_COEF(0x37, 0xfe15), + WRITE_COEF(0x38, 0x7909), WRITE_COEF(0x45, 0xd489), + WRITE_COEF(0x46, 0x00f4), WRITE_COEF(0x4a, 0x21e0), + WRITE_COEF(0x66, 0x03f0), WRITE_COEF(0x67, 0x1000), + WRITE_COEF(0x6e, 0x1005), { } + }; + + static const struct hda_pintbl pincfgs[] = { + { 0x12, 0xb7a60130 }, /* Internal microphone*/ + { 0x14, 0x90170150 }, /* B&O soundbar speakers */ + { 0x17, 0x90170153 }, /* Side speakers */ + { 0x19, 0x03a11040 }, /* Headset microphone */ + { } + }; + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + snd_hda_apply_pincfgs(codec, pincfgs); + + /* Fixes volume control problem for side speakers */ + alc295_fixup_disable_dac3(codec, fix, action); + + /* Fixes no sound from headset speaker */ + snd_hda_codec_amp_stereo(codec, 0x21, HDA_OUTPUT, 0, -1, 0); + + /* Auto-enable headset mic when plugged */ + snd_hda_jack_set_gating_jack(codec, 0x19, 0x21); + + /* Headset mic volume enhancement */ + snd_hda_codec_set_pin_target(codec, 0x19, PIN_VREF50); + break; + case HDA_FIXUP_ACT_INIT: + alc_process_coef_fw(codec, coefs); + break; + case HDA_FIXUP_ACT_BUILD: + rename_ctl(codec, "Bass Speaker Playback Volume", + "B&O-Tuned Playback Volume"); + rename_ctl(codec, "Front Playback Switch", + "B&O Soundbar Playback Switch"); + rename_ctl(codec, "Bass Speaker Playback Switch", + "Side Speaker Playback Switch"); + break; + } +} + /* for hda_fixup_thinkpad_acpi() */ #include "thinkpad_helper.c" @@ -6819,6 +6873,7 @@ enum { ALC280_FIXUP_HP_9480M, ALC245_FIXUP_HP_X360_AMP, ALC285_FIXUP_HP_SPECTRE_X360_EB1, + ALC285_FIXUP_HP_ENVY_X360, ALC288_FIXUP_DELL_HEADSET_MODE, ALC288_FIXUP_DELL1_MIC_NO_PRESENCE, ALC288_FIXUP_DELL_XPS_13, @@ -8614,6 +8669,12 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_hp_spectre_x360_eb1 }, + [ALC285_FIXUP_HP_ENVY_X360] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_hp_envy_x360, + .chained = true, + .chain_id = ALC285_FIXUP_HP_GPIO_AMP_INIT, + }, [ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_ideapad_s740_coef, @@ -8841,6 +8902,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1247, "Acer vCopperbox", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1025, 0x1248, "Acer Veriton N4660G", ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1269, "Acer SWIFT SF314-54", ALC256_FIXUP_ACER_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x126a, "Acer Swift SF114-32", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x128f, "Acer Veriton Z6860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), @@ -9000,6 +9062,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360), SND_PCI_QUIRK(0x103c, 0x8537, "HP ProBook 440 G6", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x85de, "HP Envy x360 13-ar0xxx", ALC285_FIXUP_HP_ENVY_X360), SND_PCI_QUIRK(0x103c, 0x860f, "HP ZBook 15 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x861f, "HP Elite Dragonfly G1", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED), @@ -9025,6 +9088,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8786, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8787, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8788, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x87b7, "HP Laptop 14-fq0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87e5, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87e7, "HP ProBook 450 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), @@ -9128,7 +9192,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10ec, 0x124c, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1252, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), - SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), + SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP), @@ -9331,6 +9395,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO), + SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC), SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED), SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10), @@ -9514,6 +9579,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC295_FIXUP_HP_OMEN, .name = "alc295-hp-omen"}, {.id = ALC285_FIXUP_HP_SPECTRE_X360, .name = "alc285-hp-spectre-x360"}, {.id = ALC285_FIXUP_HP_SPECTRE_X360_EB1, .name = "alc285-hp-spectre-x360-eb1"}, + {.id = ALC285_FIXUP_HP_ENVY_X360, .name = "alc285-hp-envy-x360"}, {.id = ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP, .name = "alc287-ideapad-bass-spk-amp"}, {.id = ALC623_FIXUP_LENOVO_THINKSTATION_P340, .name = "alc623-lenovo-thinkstation-p340"}, {.id = ALC255_FIXUP_ACER_HEADPHONE_AND_MIC, .name = "alc255-acer-headphone-and-mic"}, @@ -10626,8 +10692,7 @@ static void alc897_hp_automute_hook(struct hda_codec *codec, snd_hda_gen_hp_automute(codec, jack); vref = spec->gen.hp_jack_present ? (PIN_HP | AC_PINCTL_VREF_100) : PIN_HP; - snd_hda_codec_write(codec, 0x1b, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, - vref); + snd_hda_set_pin_ctl(codec, 0x1b, vref); } static void alc897_fixup_lenovo_headset_mic(struct hda_codec *codec, @@ -10636,6 +10701,10 @@ static void alc897_fixup_lenovo_headset_mic(struct hda_codec *codec, struct alc_spec *spec = codec->spec; if (action == HDA_FIXUP_ACT_PRE_PROBE) { spec->gen.hp_automute_hook = alc897_hp_automute_hook; + spec->no_shutup_pins = 1; + } + if (action == HDA_FIXUP_ACT_PROBE) { + snd_hda_set_pin_ctl_cache(codec, 0x1a, PIN_IN | AC_PINCTL_VREF_100); } } diff --git a/sound/sh/aica.c b/sound/sh/aica.c index 8fa68432d..2d59e3907 100644 --- a/sound/sh/aica.c +++ b/sound/sh/aica.c @@ -279,7 +279,8 @@ static void run_spu_dma(struct work_struct *work) dreamcastcard->clicks++; if (unlikely(dreamcastcard->clicks >= AICA_PERIOD_NUMBER)) dreamcastcard->clicks %= AICA_PERIOD_NUMBER; - mod_timer(&dreamcastcard->timer, jiffies + 1); + if (snd_pcm_running(dreamcastcard->substream)) + mod_timer(&dreamcastcard->timer, jiffies + 1); } } @@ -291,6 +292,8 @@ static void aica_period_elapsed(struct timer_list *t) /*timer function - so cannot sleep */ int play_period; struct snd_pcm_runtime *runtime; + if (!snd_pcm_running(substream)) + return; runtime = substream->runtime; dreamcastcard = substream->pcm->private_data; /* Have we played out an additional period? */ @@ -351,12 +354,19 @@ static int snd_aicapcm_pcm_open(struct snd_pcm_substream return 0; } +static int snd_aicapcm_pcm_sync_stop(struct snd_pcm_substream *substream) +{ + struct snd_card_aica *dreamcastcard = substream->pcm->private_data; + + del_timer_sync(&dreamcastcard->timer); + cancel_work_sync(&dreamcastcard->spu_dma_work); + return 0; +} + static int snd_aicapcm_pcm_close(struct snd_pcm_substream *substream) { struct snd_card_aica *dreamcastcard = substream->pcm->private_data; - flush_work(&(dreamcastcard->spu_dma_work)); - del_timer(&dreamcastcard->timer); dreamcastcard->substream = NULL; kfree(dreamcastcard->channel); spu_disable(); @@ -402,6 +412,7 @@ static const struct snd_pcm_ops snd_aicapcm_playback_ops = { .prepare = snd_aicapcm_pcm_prepare, .trigger = snd_aicapcm_pcm_trigger, .pointer = snd_aicapcm_pcm_pointer, + .sync_stop = snd_aicapcm_pcm_sync_stop, }; /* TO DO: set up to handle more than one pcm instance */ diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index 7dc801839..5db63ef33 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -3276,6 +3276,7 @@ static void rt5645_jack_detect_work(struct work_struct *work) report, SND_JACK_HEADPHONE); snd_soc_jack_report(rt5645->mic_jack, report, SND_JACK_MICROPHONE); + mutex_unlock(&rt5645->jd_mutex); return; case 4: val = snd_soc_component_read(rt5645->component, RT5645_A_JD_CTRL1) & 0x0020; @@ -3771,6 +3772,16 @@ static const struct dmi_system_id dmi_platform_data[] = { DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), DMI_EXACT_MATCH(DMI_BOARD_NAME, "Cherry Trail CR"), DMI_EXACT_MATCH(DMI_BOARD_VERSION, "Default string"), + /* + * Above strings are too generic, LattePanda BIOS versions for + * all 4 hw revisions are: + * DF-BI-7-S70CR100-* + * DF-BI-7-S70CR110-* + * DF-BI-7-S70CR200-* + * LP-BS-7-S70CR700-* + * Do a partial match for S70CR to avoid false positive matches. + */ + DMI_MATCH(DMI_BIOS_VERSION, "S70CR"), }, .driver_data = (void *)&lattepanda_board_platform_data, }, diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index 57aeded97..272932e20 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -2219,6 +2219,9 @@ SND_SOC_DAPM_PGA_E("HPOUT", SND_SOC_NOPM, 0, 0, NULL, 0, hp_event, SND_SOC_DAPM_OUTPUT("HPOUTL"), SND_SOC_DAPM_OUTPUT("HPOUTR"), + +SND_SOC_DAPM_PGA("SPKOUTL Output", WM8962_CLASS_D_CONTROL_1, 6, 0, NULL, 0), +SND_SOC_DAPM_PGA("SPKOUTR Output", WM8962_CLASS_D_CONTROL_1, 7, 0, NULL, 0), }; static const struct snd_soc_dapm_widget wm8962_dapm_spk_mono_widgets[] = { @@ -2226,7 +2229,6 @@ SND_SOC_DAPM_MIXER("Speaker Mixer", WM8962_MIXER_ENABLES, 1, 0, spkmixl, ARRAY_SIZE(spkmixl)), SND_SOC_DAPM_MUX_E("Speaker PGA", WM8962_PWR_MGMT_2, 4, 0, &spkoutl_mux, out_pga_event, SND_SOC_DAPM_POST_PMU), -SND_SOC_DAPM_PGA("Speaker Output", WM8962_CLASS_D_CONTROL_1, 7, 0, NULL, 0), SND_SOC_DAPM_OUTPUT("SPKOUT"), }; @@ -2241,9 +2243,6 @@ SND_SOC_DAPM_MUX_E("SPKOUTL PGA", WM8962_PWR_MGMT_2, 4, 0, &spkoutl_mux, SND_SOC_DAPM_MUX_E("SPKOUTR PGA", WM8962_PWR_MGMT_2, 3, 0, &spkoutr_mux, out_pga_event, SND_SOC_DAPM_POST_PMU), -SND_SOC_DAPM_PGA("SPKOUTR Output", WM8962_CLASS_D_CONTROL_1, 7, 0, NULL, 0), -SND_SOC_DAPM_PGA("SPKOUTL Output", WM8962_CLASS_D_CONTROL_1, 6, 0, NULL, 0), - SND_SOC_DAPM_OUTPUT("SPKOUTL"), SND_SOC_DAPM_OUTPUT("SPKOUTR"), }; @@ -2353,12 +2352,18 @@ static const struct snd_soc_dapm_route wm8962_spk_mono_intercon[] = { { "Speaker PGA", "Mixer", "Speaker Mixer" }, { "Speaker PGA", "DAC", "DACL" }, - { "Speaker Output", NULL, "Speaker PGA" }, - { "Speaker Output", NULL, "SYSCLK" }, - { "Speaker Output", NULL, "TOCLK" }, - { "Speaker Output", NULL, "TEMP_SPK" }, + { "SPKOUTL Output", NULL, "Speaker PGA" }, + { "SPKOUTL Output", NULL, "SYSCLK" }, + { "SPKOUTL Output", NULL, "TOCLK" }, + { "SPKOUTL Output", NULL, "TEMP_SPK" }, - { "SPKOUT", NULL, "Speaker Output" }, + { "SPKOUTR Output", NULL, "Speaker PGA" }, + { "SPKOUTR Output", NULL, "SYSCLK" }, + { "SPKOUTR Output", NULL, "TOCLK" }, + { "SPKOUTR Output", NULL, "TEMP_SPK" }, + + { "SPKOUT", NULL, "SPKOUTL Output" }, + { "SPKOUT", NULL, "SPKOUTR Output" }, }; static const struct snd_soc_dapm_route wm8962_spk_stereo_intercon[] = { @@ -2898,8 +2903,12 @@ static int wm8962_set_fll(struct snd_soc_component *component, int fll_id, int s switch (fll_id) { case WM8962_FLL_MCLK: case WM8962_FLL_BCLK: + fll1 |= (fll_id - 1) << WM8962_FLL_REFCLK_SRC_SHIFT; + break; case WM8962_FLL_OSC: fll1 |= (fll_id - 1) << WM8962_FLL_REFCLK_SRC_SHIFT; + snd_soc_component_update_bits(component, WM8962_PLL2, + WM8962_OSC_ENA, WM8962_OSC_ENA); break; case WM8962_FLL_INT: snd_soc_component_update_bits(component, WM8962_FLL_CONTROL_1, @@ -2908,7 +2917,7 @@ static int wm8962_set_fll(struct snd_soc_component *component, int fll_id, int s WM8962_FLL_FRC_NCO, WM8962_FLL_FRC_NCO); break; default: - dev_err(component->dev, "Unknown FLL source %d\n", ret); + dev_err(component->dev, "Unknown FLL source %d\n", source); return -EINVAL; } diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 97f83c63e..826829e3f 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -756,18 +756,23 @@ static int fsl_micfil_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); + /* + * Register platform component before registering cpu dai for there + * is not defer probe for platform component in snd_soc_add_pcm_runtime(). + */ + ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0); + if (ret) { + dev_err(&pdev->dev, "failed to pcm register\n"); + return ret; + } + ret = devm_snd_soc_register_component(&pdev->dev, &fsl_micfil_component, &fsl_micfil_dai, 1); if (ret) { dev_err(&pdev->dev, "failed to register component %s\n", fsl_micfil_component.name); - return ret; } - ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0); - if (ret) - dev_err(&pdev->dev, "failed to pcm register\n"); - return ret; } diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c index 81269ed5a..03b9cdbd3 100644 --- a/sound/soc/intel/boards/bytcht_es8316.c +++ b/sound/soc/intel/boards/bytcht_es8316.c @@ -37,6 +37,7 @@ struct byt_cht_es8316_private { struct clk *mclk; struct snd_soc_jack jack; struct gpio_desc *speaker_en_gpio; + struct device *codec_dev; bool speaker_en; }; @@ -549,9 +550,10 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev) } /* get speaker enable GPIO */ - codec_dev = bus_find_device_by_name(&i2c_bus_type, NULL, codec_name); + codec_dev = acpi_get_first_physical_node(adev); if (!codec_dev) return -EPROBE_DEFER; + priv->codec_dev = get_device(codec_dev); if (quirk & BYT_CHT_ES8316_JD_INVERTED) props[cnt++] = PROPERTY_ENTRY_BOOL("everest,jack-detect-inverted"); @@ -569,7 +571,6 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev) gpiod_get_index(codec_dev, "speaker-enable", 0, /* see comment in byt_cht_es8316_resume */ GPIOD_OUT_LOW | GPIOD_FLAGS_BIT_NONEXCLUSIVE); - put_device(codec_dev); if (IS_ERR(priv->speaker_en_gpio)) { ret = PTR_ERR(priv->speaker_en_gpio); @@ -581,7 +582,7 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev) dev_err(dev, "get speaker GPIO failed: %d\n", ret); fallthrough; case -EPROBE_DEFER: - return ret; + goto err_put_codec; } } @@ -604,10 +605,14 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev) if (ret) { gpiod_put(priv->speaker_en_gpio); dev_err(dev, "snd_soc_register_card failed: %d\n", ret); - return ret; + goto err_put_codec; } platform_set_drvdata(pdev, &byt_cht_es8316_card); return 0; + +err_put_codec: + put_device(priv->codec_dev); + return ret; } static int snd_byt_cht_es8316_mc_remove(struct platform_device *pdev) @@ -616,6 +621,7 @@ static int snd_byt_cht_es8316_mc_remove(struct platform_device *pdev) struct byt_cht_es8316_private *priv = snd_soc_card_get_drvdata(card); gpiod_put(priv->speaker_en_gpio); + put_device(priv->codec_dev); return 0; } diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 9a5ab96f9..1d049685e 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -86,6 +86,7 @@ enum { struct byt_rt5640_private { struct snd_soc_jack jack; struct clk *mclk; + struct device *codec_dev; }; static bool is_bytcr; @@ -528,6 +529,18 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF1 | BYT_RT5640_MCLK_EN), }, + { /* Chuwi Vi8 dual-boot (CWI506) */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "i86"), + /* The above are too generic, also match BIOS info */ + DMI_MATCH(DMI_BIOS_VERSION, "CHUWI2.D86JHBNR02"), + }, + .driver_data = (void *)(BYTCR_INPUT_DEFAULTS | + BYT_RT5640_MONO_SPEAKER | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { /* Chuwi Vi10 (CWI505) */ .matches = { @@ -941,15 +954,11 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { * Note this MUST be called before snd_soc_register_card(), so that the props * are in place before the codec component driver's probe function parses them. */ -static int byt_rt5640_add_codec_device_props(const char *i2c_dev_name) +static int byt_rt5640_add_codec_device_props(struct device *i2c_dev, + struct byt_rt5640_private *priv) { struct property_entry props[MAX_NO_PROPS] = {}; - struct device *i2c_dev; - int ret, cnt = 0; - - i2c_dev = bus_find_device_by_name(&i2c_bus_type, NULL, i2c_dev_name); - if (!i2c_dev) - return -EPROBE_DEFER; + int cnt = 0; switch (BYT_RT5640_MAP(byt_rt5640_quirk)) { case BYT_RT5640_DMIC1_MAP: @@ -989,10 +998,7 @@ static int byt_rt5640_add_codec_device_props(const char *i2c_dev_name) if (byt_rt5640_quirk & BYT_RT5640_JD_NOT_INV) props[cnt++] = PROPERTY_ENTRY_BOOL("realtek,jack-detect-not-inverted"); - ret = device_add_properties(i2c_dev, props); - put_device(i2c_dev); - - return ret; + return device_add_properties(i2c_dev, props); } static int byt_rt5640_init(struct snd_soc_pcm_runtime *runtime) @@ -1324,6 +1330,7 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) struct snd_soc_acpi_mach *mach; const char *platform_name; struct acpi_device *adev; + struct device *codec_dev; int ret_val = 0; int dai_index = 0; int i, cfg_spk; @@ -1430,10 +1437,15 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) byt_rt5640_quirk = quirk_override; } + codec_dev = acpi_get_first_physical_node(adev); + if (!codec_dev) + return -EPROBE_DEFER; + priv->codec_dev = get_device(codec_dev); + /* Must be called before register_card, also see declaration comment. */ - ret_val = byt_rt5640_add_codec_device_props(byt_rt5640_codec_name); + ret_val = byt_rt5640_add_codec_device_props(codec_dev, priv); if (ret_val) - return ret_val; + goto err; log_quirks(&pdev->dev); @@ -1460,7 +1472,7 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) * for all other errors, including -EPROBE_DEFER */ if (ret_val != -ENOENT) - return ret_val; + goto err; byt_rt5640_quirk &= ~BYT_RT5640_MCLK_EN; } } @@ -1493,17 +1505,30 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) ret_val = snd_soc_fixup_dai_links_platform_name(&byt_rt5640_card, platform_name); if (ret_val) - return ret_val; + goto err; ret_val = devm_snd_soc_register_card(&pdev->dev, &byt_rt5640_card); if (ret_val) { dev_err(&pdev->dev, "devm_snd_soc_register_card failed %d\n", ret_val); - return ret_val; + goto err; } platform_set_drvdata(pdev, &byt_rt5640_card); return ret_val; + +err: + put_device(priv->codec_dev); + return ret_val; +} + +static int snd_byt_rt5640_mc_remove(struct platform_device *pdev) +{ + struct snd_soc_card *card = platform_get_drvdata(pdev); + struct byt_rt5640_private *priv = snd_soc_card_get_drvdata(card); + + put_device(priv->codec_dev); + return 0; } static struct platform_driver snd_byt_rt5640_mc_driver = { @@ -1514,6 +1539,7 @@ static struct platform_driver snd_byt_rt5640_mc_driver = { #endif }, .probe = snd_byt_rt5640_mc_probe, + .remove = snd_byt_rt5640_mc_remove, }; module_platform_driver(snd_byt_rt5640_mc_driver); diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c index bf8b87d45..a8289f744 100644 --- a/sound/soc/intel/boards/bytcr_rt5651.c +++ b/sound/soc/intel/boards/bytcr_rt5651.c @@ -85,6 +85,7 @@ struct byt_rt5651_private { struct gpio_desc *ext_amp_gpio; struct gpio_desc *hp_detect; struct snd_soc_jack jack; + struct device *codec_dev; }; static const struct acpi_gpio_mapping *byt_rt5651_gpios; @@ -918,17 +919,17 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev) if (adev) { snprintf(byt_rt5651_codec_name, sizeof(byt_rt5651_codec_name), "i2c-%s", acpi_dev_name(adev)); - put_device(&adev->dev); byt_rt5651_dais[dai_index].codecs->name = byt_rt5651_codec_name; } else { dev_err(&pdev->dev, "Error cannot find '%s' dev\n", mach->id); return -ENODEV; } - codec_dev = bus_find_device_by_name(&i2c_bus_type, NULL, - byt_rt5651_codec_name); + codec_dev = acpi_get_first_physical_node(adev); + acpi_dev_put(adev); if (!codec_dev) return -EPROBE_DEFER; + priv->codec_dev = get_device(codec_dev); /* * swap SSP0 if bytcr is detected @@ -997,10 +998,8 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev) /* Must be called before register_card, also see declaration comment. */ ret_val = byt_rt5651_add_codec_device_props(codec_dev); - if (ret_val) { - put_device(codec_dev); - return ret_val; - } + if (ret_val) + goto err; /* Cherry Trail devices use an external amplifier enable gpio */ if (soc_intel_is_cht() && !byt_rt5651_gpios) @@ -1024,8 +1023,7 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev) ret_val); fallthrough; case -EPROBE_DEFER: - put_device(codec_dev); - return ret_val; + goto err; } } priv->hp_detect = devm_fwnode_gpiod_get(&pdev->dev, @@ -1044,14 +1042,11 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev) ret_val); fallthrough; case -EPROBE_DEFER: - put_device(codec_dev); - return ret_val; + goto err; } } } - put_device(codec_dev); - log_quirks(&pdev->dev); if ((byt_rt5651_quirk & BYT_RT5651_SSP2_AIF2) || @@ -1075,7 +1070,7 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev) * for all other errors, including -EPROBE_DEFER */ if (ret_val != -ENOENT) - return ret_val; + goto err; byt_rt5651_quirk &= ~BYT_RT5651_MCLK_EN; } } @@ -1104,17 +1099,30 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev) ret_val = snd_soc_fixup_dai_links_platform_name(&byt_rt5651_card, platform_name); if (ret_val) - return ret_val; + goto err; ret_val = devm_snd_soc_register_card(&pdev->dev, &byt_rt5651_card); if (ret_val) { dev_err(&pdev->dev, "devm_snd_soc_register_card failed %d\n", ret_val); - return ret_val; + goto err; } platform_set_drvdata(pdev, &byt_rt5651_card); return ret_val; + +err: + put_device(priv->codec_dev); + return ret_val; +} + +static int snd_byt_rt5651_mc_remove(struct platform_device *pdev) +{ + struct snd_soc_card *card = platform_get_drvdata(pdev); + struct byt_rt5651_private *priv = snd_soc_card_get_drvdata(card); + + put_device(priv->codec_dev); + return 0; } static struct platform_driver snd_byt_rt5651_mc_driver = { @@ -1125,6 +1133,7 @@ static struct platform_driver snd_byt_rt5651_mc_driver = { #endif }, .probe = snd_byt_rt5651_mc_probe, + .remove = snd_byt_rt5651_mc_remove, }; module_platform_driver(snd_byt_rt5651_mc_driver); diff --git a/sound/soc/meson/aiu.c b/sound/soc/meson/aiu.c index dc35ca790..03bc3e5b6 100644 --- a/sound/soc/meson/aiu.c +++ b/sound/soc/meson/aiu.c @@ -215,49 +215,27 @@ static const char * const aiu_spdif_ids[] = { static int aiu_clk_get(struct device *dev) { struct aiu *aiu = dev_get_drvdata(dev); + struct clk *pclk; int ret; - aiu->pclk = devm_clk_get(dev, "pclk"); - if (IS_ERR(aiu->pclk)) { - if (PTR_ERR(aiu->pclk) != -EPROBE_DEFER) - dev_err(dev, "Can't get the aiu pclk\n"); - return PTR_ERR(aiu->pclk); - } + pclk = devm_clk_get_enabled(dev, "pclk"); + if (IS_ERR(pclk)) + return dev_err_probe(dev, PTR_ERR(pclk), "Can't get the aiu pclk\n"); aiu->spdif_mclk = devm_clk_get(dev, "spdif_mclk"); - if (IS_ERR(aiu->spdif_mclk)) { - if (PTR_ERR(aiu->spdif_mclk) != -EPROBE_DEFER) - dev_err(dev, "Can't get the aiu spdif master clock\n"); - return PTR_ERR(aiu->spdif_mclk); - } + if (IS_ERR(aiu->spdif_mclk)) + return dev_err_probe(dev, PTR_ERR(aiu->spdif_mclk), + "Can't get the aiu spdif master clock\n"); ret = aiu_clk_bulk_get(dev, aiu_i2s_ids, ARRAY_SIZE(aiu_i2s_ids), &aiu->i2s); - if (ret) { - if (ret != -EPROBE_DEFER) - dev_err(dev, "Can't get the i2s clocks\n"); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, "Can't get the i2s clocks\n"); ret = aiu_clk_bulk_get(dev, aiu_spdif_ids, ARRAY_SIZE(aiu_spdif_ids), &aiu->spdif); - if (ret) { - if (ret != -EPROBE_DEFER) - dev_err(dev, "Can't get the spdif clocks\n"); - return ret; - } - - ret = clk_prepare_enable(aiu->pclk); - if (ret) { - dev_err(dev, "peripheral clock enable failed\n"); - return ret; - } - - ret = devm_add_action_or_reset(dev, - (void(*)(void *))clk_disable_unprepare, - aiu->pclk); if (ret) - dev_err(dev, "failed to add reset action on pclk"); + return dev_err_probe(dev, ret, "Can't get the spdif clocks\n"); return ret; } @@ -281,11 +259,8 @@ static int aiu_probe(struct platform_device *pdev) platform_set_drvdata(pdev, aiu); ret = device_reset(dev); - if (ret) { - if (ret != -EPROBE_DEFER) - dev_err(dev, "Failed to reset device\n"); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, "Failed to reset device\n"); regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(regs)) diff --git a/sound/soc/meson/aiu.h b/sound/soc/meson/aiu.h index 87aa19ac4..44f8c213d 100644 --- a/sound/soc/meson/aiu.h +++ b/sound/soc/meson/aiu.h @@ -33,7 +33,6 @@ struct aiu_platform_data { }; struct aiu { - struct clk *pclk; struct clk *spdif_mclk; struct aiu_interface i2s; struct aiu_interface spdif; diff --git a/sound/soc/meson/axg-fifo.c b/sound/soc/meson/axg-fifo.c index b2e867113..295c0fc30 100644 --- a/sound/soc/meson/axg-fifo.c +++ b/sound/soc/meson/axg-fifo.c @@ -350,20 +350,12 @@ int axg_fifo_probe(struct platform_device *pdev) } fifo->pclk = devm_clk_get(dev, NULL); - if (IS_ERR(fifo->pclk)) { - if (PTR_ERR(fifo->pclk) != -EPROBE_DEFER) - dev_err(dev, "failed to get pclk: %ld\n", - PTR_ERR(fifo->pclk)); - return PTR_ERR(fifo->pclk); - } + if (IS_ERR(fifo->pclk)) + return dev_err_probe(dev, PTR_ERR(fifo->pclk), "failed to get pclk\n"); fifo->arb = devm_reset_control_get_exclusive(dev, NULL); - if (IS_ERR(fifo->arb)) { - if (PTR_ERR(fifo->arb) != -EPROBE_DEFER) - dev_err(dev, "failed to get arb reset: %ld\n", - PTR_ERR(fifo->arb)); - return PTR_ERR(fifo->arb); - } + if (IS_ERR(fifo->arb)) + return dev_err_probe(dev, PTR_ERR(fifo->arb), "failed to get arb reset\n"); fifo->irq = of_irq_get(dev->of_node, 0); if (fifo->irq <= 0) { diff --git a/sound/soc/meson/axg-pdm.c b/sound/soc/meson/axg-pdm.c index bfd37d49a..672e43a97 100644 --- a/sound/soc/meson/axg-pdm.c +++ b/sound/soc/meson/axg-pdm.c @@ -586,7 +586,6 @@ static int axg_pdm_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct axg_pdm *priv; void __iomem *regs; - int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -611,28 +610,16 @@ static int axg_pdm_probe(struct platform_device *pdev) } priv->pclk = devm_clk_get(dev, "pclk"); - if (IS_ERR(priv->pclk)) { - ret = PTR_ERR(priv->pclk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get pclk: %d\n", ret); - return ret; - } + if (IS_ERR(priv->pclk)) + return dev_err_probe(dev, PTR_ERR(priv->pclk), "failed to get pclk\n"); priv->dclk = devm_clk_get(dev, "dclk"); - if (IS_ERR(priv->dclk)) { - ret = PTR_ERR(priv->dclk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get dclk: %d\n", ret); - return ret; - } + if (IS_ERR(priv->dclk)) + return dev_err_probe(dev, PTR_ERR(priv->dclk), "failed to get dclk\n"); priv->sysclk = devm_clk_get(dev, "sysclk"); - if (IS_ERR(priv->sysclk)) { - ret = PTR_ERR(priv->sysclk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get dclk: %d\n", ret); - return ret; - } + if (IS_ERR(priv->sysclk)) + return dev_err_probe(dev, PTR_ERR(priv->sysclk), "failed to get dclk\n"); return devm_snd_soc_register_component(dev, &axg_pdm_component_drv, &axg_pdm_dai_drv, 1); diff --git a/sound/soc/meson/axg-spdifin.c b/sound/soc/meson/axg-spdifin.c index 7aaded1fc..245189d2e 100644 --- a/sound/soc/meson/axg-spdifin.c +++ b/sound/soc/meson/axg-spdifin.c @@ -439,7 +439,6 @@ static int axg_spdifin_probe(struct platform_device *pdev) struct axg_spdifin *priv; struct snd_soc_dai_driver *dai_drv; void __iomem *regs; - int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -464,20 +463,12 @@ static int axg_spdifin_probe(struct platform_device *pdev) } priv->pclk = devm_clk_get(dev, "pclk"); - if (IS_ERR(priv->pclk)) { - ret = PTR_ERR(priv->pclk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get pclk: %d\n", ret); - return ret; - } + if (IS_ERR(priv->pclk)) + return dev_err_probe(dev, PTR_ERR(priv->pclk), "failed to get pclk\n"); priv->refclk = devm_clk_get(dev, "refclk"); - if (IS_ERR(priv->refclk)) { - ret = PTR_ERR(priv->refclk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get mclk: %d\n", ret); - return ret; - } + if (IS_ERR(priv->refclk)) + return dev_err_probe(dev, PTR_ERR(priv->refclk), "failed to get mclk\n"); dai_drv = axg_spdifin_get_dai_drv(dev, priv); if (IS_ERR(dai_drv)) { diff --git a/sound/soc/meson/axg-spdifout.c b/sound/soc/meson/axg-spdifout.c index e769a5ee6..3960d082e 100644 --- a/sound/soc/meson/axg-spdifout.c +++ b/sound/soc/meson/axg-spdifout.c @@ -403,7 +403,6 @@ static int axg_spdifout_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct axg_spdifout *priv; void __iomem *regs; - int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -422,20 +421,12 @@ static int axg_spdifout_probe(struct platform_device *pdev) } priv->pclk = devm_clk_get(dev, "pclk"); - if (IS_ERR(priv->pclk)) { - ret = PTR_ERR(priv->pclk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get pclk: %d\n", ret); - return ret; - } + if (IS_ERR(priv->pclk)) + return dev_err_probe(dev, PTR_ERR(priv->pclk), "failed to get pclk\n"); priv->mclk = devm_clk_get(dev, "mclk"); - if (IS_ERR(priv->mclk)) { - ret = PTR_ERR(priv->mclk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get mclk: %d\n", ret); - return ret; - } + if (IS_ERR(priv->mclk)) + return dev_err_probe(dev, PTR_ERR(priv->mclk), "failed to get mclk\n"); return devm_snd_soc_register_component(dev, &axg_spdifout_component_drv, axg_spdifout_dai_drv, ARRAY_SIZE(axg_spdifout_dai_drv)); diff --git a/sound/soc/meson/axg-tdm-formatter.c b/sound/soc/meson/axg-tdm-formatter.c index 4834cfd16..63333a2b0 100644 --- a/sound/soc/meson/axg-tdm-formatter.c +++ b/sound/soc/meson/axg-tdm-formatter.c @@ -265,7 +265,6 @@ int axg_tdm_formatter_probe(struct platform_device *pdev) const struct axg_tdm_formatter_driver *drv; struct axg_tdm_formatter *formatter; void __iomem *regs; - int ret; drv = of_device_get_match_data(dev); if (!drv) { @@ -292,57 +291,34 @@ int axg_tdm_formatter_probe(struct platform_device *pdev) /* Peripharal clock */ formatter->pclk = devm_clk_get(dev, "pclk"); - if (IS_ERR(formatter->pclk)) { - ret = PTR_ERR(formatter->pclk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get pclk: %d\n", ret); - return ret; - } + if (IS_ERR(formatter->pclk)) + return dev_err_probe(dev, PTR_ERR(formatter->pclk), "failed to get pclk\n"); /* Formatter bit clock */ formatter->sclk = devm_clk_get(dev, "sclk"); - if (IS_ERR(formatter->sclk)) { - ret = PTR_ERR(formatter->sclk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get sclk: %d\n", ret); - return ret; - } + if (IS_ERR(formatter->sclk)) + return dev_err_probe(dev, PTR_ERR(formatter->sclk), "failed to get sclk\n"); /* Formatter sample clock */ formatter->lrclk = devm_clk_get(dev, "lrclk"); - if (IS_ERR(formatter->lrclk)) { - ret = PTR_ERR(formatter->lrclk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get lrclk: %d\n", ret); - return ret; - } + if (IS_ERR(formatter->lrclk)) + return dev_err_probe(dev, PTR_ERR(formatter->lrclk), "failed to get lrclk\n"); /* Formatter bit clock input multiplexer */ formatter->sclk_sel = devm_clk_get(dev, "sclk_sel"); - if (IS_ERR(formatter->sclk_sel)) { - ret = PTR_ERR(formatter->sclk_sel); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get sclk_sel: %d\n", ret); - return ret; - } + if (IS_ERR(formatter->sclk_sel)) + return dev_err_probe(dev, PTR_ERR(formatter->sclk_sel), "failed to get sclk_sel\n"); /* Formatter sample clock input multiplexer */ formatter->lrclk_sel = devm_clk_get(dev, "lrclk_sel"); - if (IS_ERR(formatter->lrclk_sel)) { - ret = PTR_ERR(formatter->lrclk_sel); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get lrclk_sel: %d\n", ret); - return ret; - } + if (IS_ERR(formatter->lrclk_sel)) + return dev_err_probe(dev, PTR_ERR(formatter->lrclk_sel), + "failed to get lrclk_sel\n"); /* Formatter dedicated reset line */ formatter->reset = devm_reset_control_get_optional_exclusive(dev, NULL); - if (IS_ERR(formatter->reset)) { - ret = PTR_ERR(formatter->reset); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get reset: %d\n", ret); - return ret; - } + if (IS_ERR(formatter->reset)) + return dev_err_probe(dev, PTR_ERR(formatter->reset), "failed to get reset\n"); return devm_snd_soc_register_component(dev, drv->component_drv, NULL, 0); diff --git a/sound/soc/meson/axg-tdm-interface.c b/sound/soc/meson/axg-tdm-interface.c index 87cac440b..60d132ab1 100644 --- a/sound/soc/meson/axg-tdm-interface.c +++ b/sound/soc/meson/axg-tdm-interface.c @@ -12,6 +12,9 @@ #include "axg-tdm.h" +/* Maximum bit clock frequency according the datasheets */ +#define MAX_SCLK 100000000 /* Hz */ + enum { TDM_IFACE_PAD, TDM_IFACE_LOOPBACK, @@ -155,19 +158,27 @@ static int axg_tdm_iface_startup(struct snd_pcm_substream *substream, return -EINVAL; } - /* Apply component wide rate symmetry */ if (snd_soc_component_active(dai->component)) { + /* Apply component wide rate symmetry */ ret = snd_pcm_hw_constraint_single(substream->runtime, SNDRV_PCM_HW_PARAM_RATE, iface->rate); - if (ret < 0) { - dev_err(dai->dev, - "can't set iface rate constraint\n"); - return ret; - } + + } else { + /* Limit rate according to the slot number and width */ + unsigned int max_rate = + MAX_SCLK / (iface->slots * iface->slot_width); + ret = snd_pcm_hw_constraint_minmax(substream->runtime, + SNDRV_PCM_HW_PARAM_RATE, + 0, max_rate); } - return 0; + if (ret < 0) + dev_err(dai->dev, "can't set iface rate constraint\n"); + else + ret = 0; + + return ret; } static int axg_tdm_iface_set_stream(struct snd_pcm_substream *substream, @@ -266,8 +277,8 @@ static int axg_tdm_iface_set_sclk(struct snd_soc_dai *dai, srate = iface->slots * iface->slot_width * params_rate(params); if (!iface->mclk_rate) { - /* If no specific mclk is requested, default to bit clock * 4 */ - clk_set_rate(iface->mclk, 4 * srate); + /* If no specific mclk is requested, default to bit clock * 2 */ + clk_set_rate(iface->mclk, 2 * srate); } else { /* Check if we can actually get the bit clock from mclk */ if (iface->mclk_rate % srate) { @@ -517,21 +528,13 @@ static int axg_tdm_iface_probe(struct platform_device *pdev) /* Bit clock provided on the pad */ iface->sclk = devm_clk_get(dev, "sclk"); - if (IS_ERR(iface->sclk)) { - ret = PTR_ERR(iface->sclk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get sclk: %d\n", ret); - return ret; - } + if (IS_ERR(iface->sclk)) + return dev_err_probe(dev, PTR_ERR(iface->sclk), "failed to get sclk\n"); /* Sample clock provided on the pad */ iface->lrclk = devm_clk_get(dev, "lrclk"); - if (IS_ERR(iface->lrclk)) { - ret = PTR_ERR(iface->lrclk); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get lrclk: %d\n", ret); - return ret; - } + if (IS_ERR(iface->lrclk)) + return dev_err_probe(dev, PTR_ERR(iface->lrclk), "failed to get lrclk\n"); /* * mclk maybe be missing when the cpu dai is in slave mode and @@ -542,13 +545,10 @@ static int axg_tdm_iface_probe(struct platform_device *pdev) iface->mclk = devm_clk_get(dev, "mclk"); if (IS_ERR(iface->mclk)) { ret = PTR_ERR(iface->mclk); - if (ret == -ENOENT) { + if (ret == -ENOENT) iface->mclk = NULL; - } else { - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to get mclk: %d\n", ret); - return ret; - } + else + return dev_err_probe(dev, ret, "failed to get mclk\n"); } return devm_snd_soc_register_component(dev, diff --git a/sound/soc/meson/meson-card-utils.c b/sound/soc/meson/meson-card-utils.c index 300ac8be4..0e2691f01 100644 --- a/sound/soc/meson/meson-card-utils.c +++ b/sound/soc/meson/meson-card-utils.c @@ -85,11 +85,9 @@ int meson_card_parse_dai(struct snd_soc_card *card, ret = of_parse_phandle_with_args(node, "sound-dai", "#sound-dai-cells", 0, &args); - if (ret) { - if (ret != -EPROBE_DEFER) - dev_err(card->dev, "can't parse dai %d\n", ret); - return ret; - } + if (ret) + return dev_err_probe(card->dev, ret, "can't parse dai\n"); + *dai_of_node = args.np; return snd_soc_get_dai_name(&args, dai_name); diff --git a/sound/soc/meson/t9015.c b/sound/soc/meson/t9015.c index 56d2592c1..b085aa65c 100644 --- a/sound/soc/meson/t9015.c +++ b/sound/soc/meson/t9015.c @@ -48,7 +48,6 @@ #define POWER_CFG 0x10 struct t9015 { - struct clk *pclk; struct regulator *avdd; }; @@ -250,6 +249,7 @@ static int t9015_probe(struct platform_device *pdev) struct t9015 *priv; void __iomem *regs; struct regmap *regmap; + struct clk *pclk; int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -257,31 +257,13 @@ static int t9015_probe(struct platform_device *pdev) return -ENOMEM; platform_set_drvdata(pdev, priv); - priv->pclk = devm_clk_get(dev, "pclk"); - if (IS_ERR(priv->pclk)) { - if (PTR_ERR(priv->pclk) != -EPROBE_DEFER) - dev_err(dev, "failed to get core clock\n"); - return PTR_ERR(priv->pclk); - } + pclk = devm_clk_get_enabled(dev, "pclk"); + if (IS_ERR(pclk)) + return dev_err_probe(dev, PTR_ERR(pclk), "failed to get core clock\n"); priv->avdd = devm_regulator_get(dev, "AVDD"); - if (IS_ERR(priv->avdd)) { - if (PTR_ERR(priv->avdd) != -EPROBE_DEFER) - dev_err(dev, "failed to AVDD\n"); - return PTR_ERR(priv->avdd); - } - - ret = clk_prepare_enable(priv->pclk); - if (ret) { - dev_err(dev, "core clock enable failed\n"); - return ret; - } - - ret = devm_add_action_or_reset(dev, - (void(*)(void *))clk_disable_unprepare, - priv->pclk); - if (ret) - return ret; + if (IS_ERR(priv->avdd)) + return dev_err_probe(dev, PTR_ERR(priv->avdd), "failed to AVDD\n"); ret = device_reset(dev); if (ret) { diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index daecd386d..a83cd8d8a 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -246,7 +246,7 @@ int snd_soc_get_volsw(struct snd_kcontrol *kcontrol, int max = mc->max; int min = mc->min; int sign_bit = mc->sign_bit; - unsigned int mask = (1 << fls(max)) - 1; + unsigned int mask = (1ULL << fls(max)) - 1; unsigned int invert = mc->invert; int val; int ret; diff --git a/sound/soc/sunxi/sun4i-spdif.c b/sound/soc/sunxi/sun4i-spdif.c index 228485fe0..6dcad1aa2 100644 --- a/sound/soc/sunxi/sun4i-spdif.c +++ b/sound/soc/sunxi/sun4i-spdif.c @@ -464,6 +464,11 @@ static const struct of_device_id sun4i_spdif_of_match[] = { .compatible = "allwinner,sun50i-h6-spdif", .data = &sun50i_h6_spdif_quirks, }, + { + .compatible = "allwinner,sun50i-h616-spdif", + /* Essentially the same as the H6, but without RX */ + .data = &sun50i_h6_spdif_quirks, + }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, sun4i_spdif_of_match); diff --git a/sound/usb/stream.c b/sound/usb/stream.c index c4f4585f9..f51e901a9 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -301,9 +301,12 @@ static struct snd_pcm_chmap_elem *convert_chmap(int channels, unsigned int bits, c = 0; if (bits) { - for (; bits && *maps; maps++, bits >>= 1) + for (; bits && *maps; maps++, bits >>= 1) { if (bits & 1) chmap->map[c++] = *maps; + if (c == chmap->channels) + break; + } } else { /* If we're missing wChannelConfig, then guess something to make sure the channel map is not skipped entirely */ diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index d2bcce627..d07996e79 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -1946,7 +1946,7 @@ static int profile_open_perf_events(struct profiler_bpf *obj) int map_fd; profile_perf_events = calloc( - sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric); + obj->rodata->num_cpu * obj->rodata->num_metric, sizeof(int)); if (!profile_perf_events) { p_err("failed to allocate memory for perf_event array: %s", strerror(errno)); diff --git a/tools/iio/iio_utils.c b/tools/iio/iio_utils.c index 48360994c..b87458739 100644 --- a/tools/iio/iio_utils.c +++ b/tools/iio/iio_utils.c @@ -373,7 +373,7 @@ int build_channel_array(const char *device_dir, goto error_close_dir; } - seekdir(dp, 0); + rewinddir(dp); while (ent = readdir(dp), ent) { if (strcmp(ent->d_name + strlen(ent->d_name) - strlen("_en"), "_en") == 0) { diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h index d17fa7f40..0f13875ac 100644 --- a/tools/include/linux/objtool.h +++ b/tools/include/linux/objtool.h @@ -141,6 +141,12 @@ struct unwind_hint { .popsection .endm +.macro STACK_FRAME_NON_STANDARD func:req + .pushsection .discard.func_stack_frame_non_standard, "aw" + .long \func - . + .popsection +.endm + #endif /* __ASSEMBLY__ */ #else /* !CONFIG_STACK_VALIDATION */ @@ -158,6 +164,8 @@ struct unwind_hint { .endm .macro ANNOTATE_NOENDBR .endm +.macro STACK_FRAME_NON_STANDARD func:req +.endm #endif #endif /* CONFIG_STACK_VALIDATION */ diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index f76b1a9d5..53cff32b2 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -226,10 +226,10 @@ u64 perf_evlist__read_format(struct perf_evlist *evlist) static void perf_evlist__id_hash(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id) + int cpu_map_idx, int thread, u64 id) { int hash; - struct perf_sample_id *sid = SID(evsel, cpu, thread); + struct perf_sample_id *sid = SID(evsel, cpu_map_idx, thread); sid->id = id; sid->evsel = evsel; @@ -239,21 +239,27 @@ static void perf_evlist__id_hash(struct perf_evlist *evlist, void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id) + int cpu_map_idx, int thread, u64 id) { - perf_evlist__id_hash(evlist, evsel, cpu, thread, id); + if (!SID(evsel, cpu_map_idx, thread)) + return; + + perf_evlist__id_hash(evlist, evsel, cpu_map_idx, thread, id); evsel->id[evsel->ids++] = id; } int perf_evlist__id_add_fd(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, int fd) + int cpu_map_idx, int thread, int fd) { u64 read_data[4] = { 0, }; int id_idx = 1; /* The first entry is the counter value */ u64 id; int ret; + if (!SID(evsel, cpu_map_idx, thread)) + return -1; + ret = ioctl(fd, PERF_EVENT_IOC_ID, &id); if (!ret) goto add; @@ -282,7 +288,7 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist, id = read_data[id_idx]; add: - perf_evlist__id_add(evlist, evsel, cpu, thread, id); + perf_evlist__id_add(evlist, evsel, cpu_map_idx, thread, id); return 0; } diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h index 2d0fa02b0..8999f2cc8 100644 --- a/tools/lib/perf/include/internal/evlist.h +++ b/tools/lib/perf/include/internal/evlist.h @@ -118,10 +118,10 @@ u64 perf_evlist__read_format(struct perf_evlist *evlist); void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, u64 id); + int cpu_map_idx, int thread, u64 id); int perf_evlist__id_add_fd(struct perf_evlist *evlist, struct perf_evsel *evsel, - int cpu, int thread, int fd); + int cpu_map_idx, int thread, int fd); #endif /* __LIBPERF_INTERNAL_EVLIST_H */ diff --git a/tools/lib/subcmd/help.c b/tools/lib/subcmd/help.c index bf02d62a3..42f57b640 100644 --- a/tools/lib/subcmd/help.c +++ b/tools/lib/subcmd/help.c @@ -50,11 +50,21 @@ void uniq(struct cmdnames *cmds) if (!cmds->cnt) return; - for (i = j = 1; i < cmds->cnt; i++) - if (strcmp(cmds->names[i]->name, cmds->names[i-1]->name)) - cmds->names[j++] = cmds->names[i]; - + for (i = 1; i < cmds->cnt; i++) { + if (!strcmp(cmds->names[i]->name, cmds->names[i-1]->name)) + zfree(&cmds->names[i - 1]); + } + for (i = 0, j = 0; i < cmds->cnt; i++) { + if (cmds->names[i]) { + if (i == j) + j++; + else + cmds->names[j++] = cmds->names[i]; + } + } cmds->cnt = j; + while (j < i) + cmds->names[j++] = NULL; } void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index e5c938d53..167cd8d3b 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1264,8 +1264,8 @@ static int record__switch_output(struct record *rec, bool at_exit) { struct perf_data *data = &rec->data; + char *new_filename = NULL; int fd, err; - char *new_filename; /* Same Size: "2015122520103046"*/ char timestamp[] = "InvalidTimestamp"; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 1a1cbd16d..d9a4c0202 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2109,7 +2109,6 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, data->period = evsel->core.attr.sample_period; data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; data->misc = event->header.misc; - data->id = -1ULL; data->data_src = PERF_MEM_DATA_SRC_NONE; if (event->header.type != PERF_RECORD_SAMPLE) { diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 4688e39de..971fd77bd 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -271,7 +271,7 @@ static void print_metric_only(struct perf_stat_config *config, if (color) mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1; - color_snprintf(str, sizeof(str), color ?: "", fmt, val); + color_snprintf(str, sizeof(str), color ?: "", fmt ?: "", val); fprintf(out, "%*s ", mlen, str); } diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index c9bfe4696..cee7fc3b5 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -279,13 +279,13 @@ struct perf_thread_map *thread_map__new_by_tid_str(const char *tid_str) threads->nr = ntasks; } out: + strlist__delete(slist); if (threads) refcount_set(&threads->refcnt, 1); return threads; out_free_threads: zfree(&threads); - strlist__delete(slist); goto out; } diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c index ff6c6661f..1c80aa498 100644 --- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c +++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c @@ -1152,6 +1152,7 @@ unsigned int get_pkg_num(int cpu) retval = fscanf(fp, "%d\n", &pkg); if (retval != 1) errx(1, "%s: failed to parse", pathname); + fclose(fp); return pkg; } diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index ea26f2b0c..f72da3079 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -773,6 +773,7 @@ sub set_value { if ($lvalue =~ /^(TEST|BISECT|CONFIG_BISECT)_TYPE(\[.*\])?$/ && $prvalue !~ /^(config_|)bisect$/ && $prvalue !~ /^build$/ && + $prvalue !~ /^make_warnings_file$/ && $buildonly) { # Note if a test is something other than build, then we diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 28d22265b..cbdc28399 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -4611,6 +4611,7 @@ static size_t get_pprint_mapv_size(enum pprint_mapv_kind_t mapv_kind) #endif assert(0); + return 0; } static void set_pprint_mapv(enum pprint_mapv_kind_t mapv_kind, diff --git a/tools/testing/selftests/bpf/progs/pyperf180.c b/tools/testing/selftests/bpf/progs/pyperf180.c index c39f559d3..42c4a8b62 100644 --- a/tools/testing/selftests/bpf/progs/pyperf180.c +++ b/tools/testing/selftests/bpf/progs/pyperf180.c @@ -1,4 +1,26 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook #define STACK_MAX_LEN 180 + +/* llvm upstream commit at clang18 + * https://github.com/llvm/llvm-project/commit/1a2e77cf9e11dbf56b5720c607313a566eebb16e + * changed inlining behavior and caused compilation failure as some branch + * target distance exceeded 16bit representation which is the maximum for + * cpu v1/v2/v3. Macro __BPF_CPU_VERSION__ is later implemented in clang18 + * to specify which cpu version is used for compilation. So a smaller + * unroll_count can be set if __BPF_CPU_VERSION__ is less than 4, which + * reduced some branch target distances and resolved the compilation failure. + * + * To capture the case where a developer/ci uses clang18 but the corresponding + * repo checkpoint does not have __BPF_CPU_VERSION__, a smaller unroll_count + * will be set as well to prevent potential compilation failures. + */ +#ifdef __BPF_CPU_VERSION__ +#if __BPF_CPU_VERSION__ < 4 +#define UNROLL_COUNT 90 +#endif +#elif __clang_major__ == 18 +#define UNROLL_COUNT 90 +#endif + #include "pyperf.h" diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh index 1b08e042c..185b02d2d 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -269,6 +269,7 @@ for port in 0 1; do echo 1 > $NSIM_DEV_SYS/new_port fi NSIM_NETDEV=`get_netdev_name old_netdevs` + ifconfig $NSIM_NETDEV up msg="new NIC device created" exp0=( 0 0 0 0 ) @@ -430,6 +431,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up overflow_table0 "overflow NIC table" @@ -487,6 +489,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up overflow_table0 "overflow NIC table" @@ -543,6 +546,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up overflow_table0 "destroy NIC" @@ -572,6 +576,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up msg="create VxLANs v6" @@ -632,6 +637,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error @@ -687,6 +693,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up msg="create VxLANs v6" @@ -746,6 +753,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up msg="create VxLANs v6" @@ -876,6 +884,7 @@ msg="re-add a port" echo 2 > $NSIM_DEV_SYS/del_port echo 2 > $NSIM_DEV_SYS/new_port +NSIM_NETDEV=`get_netdev_name old_netdevs` check_tables msg="replace VxLAN in overflow table" diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc index b1ede6249..b7c8f29c0 100644 --- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc +++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc @@ -18,7 +18,7 @@ echo 'sched:*' > set_event yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -lt 3 ]; then fail "at least fork, exec and exit events should be recorded" fi @@ -29,7 +29,7 @@ echo 1 > events/sched/enable yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -lt 3 ]; then fail "at least fork, exec and exit events should be recorded" fi @@ -40,7 +40,7 @@ echo 0 > events/sched/enable yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -ne 0 ]; then fail "any of scheduler events should not be recorded" fi diff --git a/tools/testing/selftests/mqueue/setting b/tools/testing/selftests/mqueue/setting new file mode 100644 index 000000000..a953c96aa --- /dev/null +++ b/tools/testing/selftests/mqueue/setting @@ -0,0 +1 @@ +timeout=180 diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 3253fdc78..9cd5cf800 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -1583,6 +1583,13 @@ check_command() { return 0 } +check_running() { + pid=${1} + cmd=${2} + + [ "$(cat /proc/${pid}/cmdline 2>/dev/null | tr -d '\0')" = "{cmd}" ] +} + test_cleanup_vxlanX_exception() { outer="${1}" encap="vxlan" @@ -1613,11 +1620,12 @@ test_cleanup_vxlanX_exception() { ${ns_a} ip link del dev veth_A-R1 & iplink_pid=$! - sleep 1 - if [ "$(cat /proc/${iplink_pid}/cmdline 2>/dev/null | tr -d '\0')" = "iplinkdeldevveth_A-R1" ]; then - err " can't delete veth device in a timely manner, PMTU dst likely leaked" - return 1 - fi + for i in $(seq 1 20); do + check_running ${iplink_pid} "iplinkdeldevveth_A-R1" || return 0 + sleep 0.1 + done + err " can't delete veth device in a timely manner, PMTU dst likely leaked" + return 1 } test_cleanup_ipv6_exception() { diff --git a/tools/testing/selftests/net/reuseaddr_conflict.c b/tools/testing/selftests/net/reuseaddr_conflict.c index 7c5b12664..bfb07dc49 100644 --- a/tools/testing/selftests/net/reuseaddr_conflict.c +++ b/tools/testing/selftests/net/reuseaddr_conflict.c @@ -109,6 +109,6 @@ int main(void) fd1 = open_port(0, 1); if (fd1 >= 0) error(1, 0, "Was allowed to create an ipv4 reuseport on an already bound non-reuseport socket with no ipv6"); - fprintf(stderr, "Success"); + fprintf(stderr, "Success\n"); return 0; } diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 44a25a9f1..956ee3c01 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -653,12 +653,12 @@ TEST_F(tls, recv_partial) memset(recv_mem, 0, sizeof(recv_mem)); EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); - EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_first), - MSG_WAITALL), -1); + EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_first), + MSG_WAITALL), strlen(test_str_first)); EXPECT_EQ(memcmp(test_str_first, recv_mem, strlen(test_str_first)), 0); memset(recv_mem, 0, sizeof(recv_mem)); - EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_second), - MSG_WAITALL), -1); + EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_second), + MSG_WAITALL), strlen(test_str_second)); EXPECT_EQ(memcmp(test_str_second, recv_mem, strlen(test_str_second)), 0); } diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index 0ba500056..193a984f5 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -66,7 +66,7 @@ static int check_diff(struct timeval start, struct timeval end) diff = end.tv_usec - start.tv_usec; diff += (end.tv_sec - start.tv_sec) * USECS_PER_SEC; - if (abs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) { + if (llabs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) { printf("Diff too high: %lld..", diff); return -1; } diff --git a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh index 7536ff2f8..d0107f8ae 100644 --- a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh +++ b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/testing/selftests/vm/map_hugetlb.c b/tools/testing/selftests/vm/map_hugetlb.c index 312889edb..c65c55b7a 100644 --- a/tools/testing/selftests/vm/map_hugetlb.c +++ b/tools/testing/selftests/vm/map_hugetlb.c @@ -15,6 +15,7 @@ #include <unistd.h> #include <sys/mman.h> #include <fcntl.h> +#include "vm_util.h" #define LENGTH (256UL*1024*1024) #define PROTECTION (PROT_READ | PROT_WRITE) @@ -70,10 +71,16 @@ int main(int argc, char **argv) { void *addr; int ret; + size_t hugepage_size; size_t length = LENGTH; int flags = FLAGS; int shift = 0; + hugepage_size = default_huge_page_size(); + /* munmap with fail if the length is not page aligned */ + if (hugepage_size > length) + length = hugepage_size; + if (argc > 1) length = atol(argv[1]) << 20; if (argc > 2) { diff --git a/tools/testing/selftests/vm/write_hugetlb_memory.sh b/tools/testing/selftests/vm/write_hugetlb_memory.sh index 70a02301f..3d2d2eb9d 100644 --- a/tools/testing/selftests/vm/write_hugetlb_memory.sh +++ b/tools/testing/selftests/vm/write_hugetlb_memory.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index dd777688d..952afb1bc 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -88,7 +88,27 @@ static void async_pf_execute(struct work_struct *work) rcuwait_wake_up(&vcpu->wait); mmput(mm); - kvm_put_kvm(vcpu->kvm); +} + +static void kvm_flush_and_free_async_pf_work(struct kvm_async_pf *work) +{ + /* + * The async #PF is "done", but KVM must wait for the work item itself, + * i.e. async_pf_execute(), to run to completion. If KVM is a module, + * KVM must ensure *no* code owned by the KVM (the module) can be run + * after the last call to module_put(). Note, flushing the work item + * is always required when the item is taken off the completion queue. + * E.g. even if the vCPU handles the item in the "normal" path, the VM + * could be terminated before async_pf_execute() completes. + * + * Wake all events skip the queue and go straight done, i.e. don't + * need to be flushed (but sanity check that the work wasn't queued). + */ + if (work->wakeup_all) + WARN_ON_ONCE(work->work.func); + else + flush_work(&work->work); + kmem_cache_free(async_pf_cache, work); } void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) @@ -115,7 +135,6 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) #else if (cancel_work_sync(&work->work)) { mmput(work->mm); - kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */ kmem_cache_free(async_pf_cache, work); } #endif @@ -127,7 +146,10 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) list_first_entry(&vcpu->async_pf.done, typeof(*work), link); list_del(&work->link); - kmem_cache_free(async_pf_cache, work); + + spin_unlock(&vcpu->async_pf.lock); + kvm_flush_and_free_async_pf_work(work); + spin_lock(&vcpu->async_pf.lock); } spin_unlock(&vcpu->async_pf.lock); @@ -152,7 +174,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) list_del(&work->queue); vcpu->async_pf.queued--; - kmem_cache_free(async_pf_cache, work); + kvm_flush_and_free_async_pf_work(work); } } @@ -187,7 +209,6 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, work->arch = *arch; work->mm = current->mm; mmget(work->mm); - kvm_get_kvm(work->vcpu->kvm); INIT_WORK(&work->work, async_pf_execute); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 356fd5d1a..b7638c3c9 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1008,9 +1008,9 @@ static int kvm_vm_release(struct inode *inode, struct file *filp) */ static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot) { - unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot); + unsigned long dirty_bytes = kvm_dirty_bitmap_bytes(memslot); - memslot->dirty_bitmap = kvzalloc(dirty_bytes, GFP_KERNEL_ACCOUNT); + memslot->dirty_bitmap = __vcalloc(2, dirty_bytes, GFP_KERNEL_ACCOUNT); if (!memslot->dirty_bitmap) return -ENOMEM; |