diff options
Diffstat (limited to '')
199 files changed, 25088 insertions, 0 deletions
diff --git a/debian/patches-rt/0001-vduse-Remove-include-of-rwlock.h.patch b/debian/patches-rt/0001-vduse-Remove-include-of-rwlock.h.patch new file mode 100644 index 000000000..891081a3a --- /dev/null +++ b/debian/patches-rt/0001-vduse-Remove-include-of-rwlock.h.patch @@ -0,0 +1,33 @@ +From 52072a197524e62baa4ac9a5f33d15cd8b27fb17 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 16 Aug 2022 09:45:22 +0200 +Subject: [PATCH 01/62] vduse: Remove include of rwlock.h +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +rwlock.h should not be included directly. Instead linux/splinlock.h +should be included. Including it directly will break the RT build. + +Remove the rwlock.h include. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Acked-by: Michael S. Tsirkin <mst@redhat.com> +Link: https://lkml.kernel.org/r/20221026134407.711768-1-bigeasy@linutronix.de +--- + drivers/vdpa/vdpa_user/iova_domain.h | 1 - + 1 file changed, 1 deletion(-) + +diff --git a/drivers/vdpa/vdpa_user/iova_domain.h b/drivers/vdpa/vdpa_user/iova_domain.h +index 4e0e50e7ac15..173e979b84a9 100644 +--- a/drivers/vdpa/vdpa_user/iova_domain.h ++++ b/drivers/vdpa/vdpa_user/iova_domain.h +@@ -14,7 +14,6 @@ + #include <linux/iova.h> + #include <linux/dma-mapping.h> + #include <linux/vhost_iotlb.h> +-#include <linux/rwlock.h> + + #define IOVA_START_PFN 1 + +-- +2.43.0 + diff --git a/debian/patches-rt/0002-signal-Don-t-disable-preemption-in-ptrace_stop-on-PR.patch b/debian/patches-rt/0002-signal-Don-t-disable-preemption-in-ptrace_stop-on-PR.patch new file mode 100644 index 000000000..05ec116ad --- /dev/null +++ b/debian/patches-rt/0002-signal-Don-t-disable-preemption-in-ptrace_stop-on-PR.patch @@ -0,0 +1,66 @@ +From d5541b6ef4eccee650abfe3095b9e7365773494c Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 22 Jun 2022 11:36:17 +0200 +Subject: [PATCH 02/62] signal: Don't disable preemption in ptrace_stop() on + PREEMPT_RT. +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Commit + 53da1d9456fe7 ("fix ptrace slowness") + +is just band aid around the problem. +The invocation of do_notify_parent_cldstop() wakes the parent and makes +it runnable. The scheduler then wants to replace this still running task +with the parent. With the read_lock() acquired this is not possible +because preemption is disabled and so this is deferred until read_unlock(). +This scheduling point is undesired and is avoided by disabling preemption +around the unlock operation enabled again before the schedule() invocation +without a preemption point. +This is only undesired because the parent sleeps a cycle in +wait_task_inactive() until the traced task leaves the run-queue in +schedule(). It is not a correctness issue, it is just band aid to avoid the +visbile delay which sums up over multiple invocations. +The task can still be preempted if an interrupt occurs between +preempt_enable_no_resched() and freezable_schedule() because on the IRQ-exit +path of the interrupt scheduling _will_ happen. This is ignored since it does +not happen very often. + +On PREEMPT_RT keeping preemption disabled during the invocation of +cgroup_enter_frozen() becomes a problem because the function acquires +css_set_lock which is a sleeping lock on PREEMPT_RT and must not be +acquired with disabled preemption. + +Don't disable preemption on PREEMPT_RT. Remove the TODO regarding adding +read_unlock_no_resched() as there is no need for it and will cause harm. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Link: https://lkml.kernel.org/r/20220720154435.232749-2-bigeasy@linutronix.de +--- + kernel/signal.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/kernel/signal.c b/kernel/signal.c +index 5d45f5da2b36..58e919c7c936 100644 +--- a/kernel/signal.c ++++ b/kernel/signal.c +@@ -2302,13 +2302,13 @@ static int ptrace_stop(int exit_code, int why, unsigned long message, + /* + * Don't want to allow preemption here, because + * sys_ptrace() needs this task to be inactive. +- * +- * XXX: implement read_unlock_no_resched(). + */ +- preempt_disable(); ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ++ preempt_disable(); + read_unlock(&tasklist_lock); + cgroup_enter_frozen(); +- preempt_enable_no_resched(); ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ++ preempt_enable_no_resched(); + schedule(); + cgroup_leave_frozen(true); + +-- +2.43.0 + diff --git a/debian/patches-rt/0003-sched-Consider-task_struct-saved_state-in-wait_task_.patch b/debian/patches-rt/0003-sched-Consider-task_struct-saved_state-in-wait_task_.patch new file mode 100644 index 000000000..933385ab9 --- /dev/null +++ b/debian/patches-rt/0003-sched-Consider-task_struct-saved_state-in-wait_task_.patch @@ -0,0 +1,152 @@ +From e4742fc784660e012dc23090a72614bf1f9a0ca1 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 22 Jun 2022 12:27:05 +0200 +Subject: [PATCH 03/62] sched: Consider task_struct::saved_state in + wait_task_inactive(). +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Ptrace is using wait_task_inactive() to wait for the tracee to reach a +certain task state. On PREEMPT_RT that state may be stored in +task_struct::saved_state while the tracee blocks on a sleeping lock and +task_struct::__state is set to TASK_RTLOCK_WAIT. +It is not possible to check only for TASK_RTLOCK_WAIT to be sure that the task +is blocked on a sleeping lock because during wake up (after the sleeping lock +has been acquired) the task state is set TASK_RUNNING. After the task in on CPU +and acquired the pi_lock it will reset the state accordingly but until then +TASK_RUNNING will be observed (with the desired state saved in saved_state). + +Check also for task_struct::saved_state if the desired match was not found in +task_struct::__state on PREEMPT_RT. If the state was found in saved_state, wait +until the task is idle and state is visible in task_struct::__state. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Reviewed-by: Valentin Schneider <vschneid@redhat.com> +Link: https://lkml.kernel.org/r/Yt%2FpQAFQ1xKNK0RY@linutronix.de +--- + kernel/sched/core.c | 81 ++++++++++++++++++++++++++++++++++++++++++--- + 1 file changed, 76 insertions(+), 5 deletions(-) + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 18a4f8f28a25..6bd06122850a 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -3281,6 +3281,76 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p, + } + #endif /* CONFIG_NUMA_BALANCING */ + ++#ifdef CONFIG_PREEMPT_RT ++ ++/* ++ * Consider: ++ * ++ * set_special_state(X); ++ * ++ * do_things() ++ * // Somewhere in there is an rtlock that can be contended: ++ * current_save_and_set_rtlock_wait_state(); ++ * [...] ++ * schedule_rtlock(); (A) ++ * [...] ++ * current_restore_rtlock_saved_state(); ++ * ++ * schedule(); (B) ++ * ++ * If p->saved_state is anything else than TASK_RUNNING, then p blocked on an ++ * rtlock (A) *before* voluntarily calling into schedule() (B) after setting its ++ * state to X. For things like ptrace (X=TASK_TRACED), the task could have more ++ * work to do upon acquiring the lock in do_things() before whoever called ++ * wait_task_inactive() should return. IOW, we have to wait for: ++ * ++ * p.saved_state = TASK_RUNNING ++ * p.__state = X ++ * ++ * which implies the task isn't blocked on an RT lock and got to schedule() (B). ++ * ++ * Also see comments in ttwu_state_match(). ++ */ ++ ++static __always_inline bool state_mismatch(struct task_struct *p, unsigned int match_state) ++{ ++ unsigned long flags; ++ bool mismatch; ++ ++ raw_spin_lock_irqsave(&p->pi_lock, flags); ++ if (READ_ONCE(p->__state) & match_state) ++ mismatch = false; ++ else if (READ_ONCE(p->saved_state) & match_state) ++ mismatch = false; ++ else ++ mismatch = true; ++ ++ raw_spin_unlock_irqrestore(&p->pi_lock, flags); ++ return mismatch; ++} ++static __always_inline bool state_match(struct task_struct *p, unsigned int match_state, ++ bool *wait) ++{ ++ if (READ_ONCE(p->__state) & match_state) ++ return true; ++ if (READ_ONCE(p->saved_state) & match_state) { ++ *wait = true; ++ return true; ++ } ++ return false; ++} ++#else ++static __always_inline bool state_mismatch(struct task_struct *p, unsigned int match_state) ++{ ++ return !(READ_ONCE(p->__state) & match_state); ++} ++static __always_inline bool state_match(struct task_struct *p, unsigned int match_state, ++ bool *wait) ++{ ++ return (READ_ONCE(p->__state) & match_state); ++} ++#endif ++ + /* + * wait_task_inactive - wait for a thread to unschedule. + * +@@ -3299,7 +3369,7 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p, + */ + unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state) + { +- int running, queued; ++ bool running, wait; + struct rq_flags rf; + unsigned long ncsw; + struct rq *rq; +@@ -3325,7 +3395,7 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state + * is actually now running somewhere else! + */ + while (task_on_cpu(rq, p)) { +- if (!(READ_ONCE(p->__state) & match_state)) ++ if (state_mismatch(p, match_state)) + return 0; + cpu_relax(); + } +@@ -3338,9 +3408,10 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state + rq = task_rq_lock(p, &rf); + trace_sched_wait_task(p); + running = task_on_cpu(rq, p); +- queued = task_on_rq_queued(p); ++ wait = task_on_rq_queued(p); + ncsw = 0; +- if (READ_ONCE(p->__state) & match_state) ++ ++ if (state_match(p, match_state, &wait)) + ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ + task_rq_unlock(rq, p, &rf); + +@@ -3370,7 +3441,7 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state + * running right now), it's preempted, and we should + * yield - it could be a while. + */ +- if (unlikely(queued)) { ++ if (unlikely(wait)) { + ktime_t to = NSEC_PER_SEC / HZ; + + set_current_state(TASK_UNINTERRUPTIBLE); +-- +2.43.0 + diff --git a/debian/patches-rt/0004-spi-Remove-the-obsolte-u64_stats_fetch_-_irq-users.patch b/debian/patches-rt/0004-spi-Remove-the-obsolte-u64_stats_fetch_-_irq-users.patch new file mode 100644 index 000000000..0f1b0f221 --- /dev/null +++ b/debian/patches-rt/0004-spi-Remove-the-obsolte-u64_stats_fetch_-_irq-users.patch @@ -0,0 +1,40 @@ +From 638117350cb3452dd5043156c7e394befe7d6eb9 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 25 Aug 2022 16:15:32 +0200 +Subject: [PATCH 04/62] spi: Remove the obsolte u64_stats_fetch_*_irq() users. +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Now that the 32bit UP oddity is gone and 32bit uses always a sequence +count, there is no need for the fetch_irq() variants anymore. + +Convert to the regular interface. + +Cc: Mark Brown <broonie@kernel.org> +Cc: linux-spi@vger.kernel.org +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> +--- + drivers/spi/spi.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c +index 5d046be8b2dd..716e6d6ecf98 100644 +--- a/drivers/spi/spi.c ++++ b/drivers/spi/spi.c +@@ -127,10 +127,10 @@ do { \ + unsigned int start; \ + pcpu_stats = per_cpu_ptr(in, i); \ + do { \ +- start = u64_stats_fetch_begin_irq( \ ++ start = u64_stats_fetch_begin( \ + &pcpu_stats->syncp); \ + inc = u64_stats_read(&pcpu_stats->field); \ +- } while (u64_stats_fetch_retry_irq( \ ++ } while (u64_stats_fetch_retry( \ + &pcpu_stats->syncp, start)); \ + ret += inc; \ + } \ +-- +2.43.0 + diff --git a/debian/patches-rt/0005-net-Remove-the-obsolte-u64_stats_fetch_-_irq-users-d.patch b/debian/patches-rt/0005-net-Remove-the-obsolte-u64_stats_fetch_-_irq-users-d.patch new file mode 100644 index 000000000..a4d96ec61 --- /dev/null +++ b/debian/patches-rt/0005-net-Remove-the-obsolte-u64_stats_fetch_-_irq-users-d.patch @@ -0,0 +1,2087 @@ +From d1c3fb886c8b630c3a70f2f7192d53f545798283 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 25 Aug 2022 16:15:44 +0200 +Subject: [PATCH 05/62] net: Remove the obsolte u64_stats_fetch_*_irq() users + (drivers). +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Now that the 32bit UP oddity is gone and 32bit uses always a sequence +count, there is no need for the fetch_irq() variants anymore. + +Convert to the regular interface. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> +--- + drivers/net/ethernet/alacritech/slic.h | 12 +++---- + drivers/net/ethernet/amazon/ena/ena_ethtool.c | 4 +-- + drivers/net/ethernet/amazon/ena/ena_netdev.c | 12 +++---- + .../net/ethernet/aquantia/atlantic/aq_ring.c | 8 ++--- + drivers/net/ethernet/asix/ax88796c_main.c | 4 +-- + drivers/net/ethernet/broadcom/b44.c | 8 ++--- + drivers/net/ethernet/broadcom/bcmsysport.c | 12 +++---- + drivers/net/ethernet/cortina/gemini.c | 24 +++++++------- + .../net/ethernet/emulex/benet/be_ethtool.c | 12 +++---- + drivers/net/ethernet/emulex/benet/be_main.c | 16 +++++----- + .../ethernet/fungible/funeth/funeth_txrx.h | 4 +-- + drivers/net/ethernet/google/gve/gve_ethtool.c | 16 +++++----- + drivers/net/ethernet/google/gve/gve_main.c | 12 +++---- + .../net/ethernet/hisilicon/hns3/hns3_enet.c | 4 +-- + drivers/net/ethernet/huawei/hinic/hinic_rx.c | 4 +-- + drivers/net/ethernet/huawei/hinic/hinic_tx.c | 4 +-- + .../net/ethernet/intel/fm10k/fm10k_netdev.c | 8 ++--- + .../net/ethernet/intel/i40e/i40e_ethtool.c | 8 ++--- + drivers/net/ethernet/intel/i40e/i40e_main.c | 20 ++++++------ + .../net/ethernet/intel/iavf/iavf_ethtool.c | 8 ++--- + drivers/net/ethernet/intel/ice/ice_main.c | 4 +-- + drivers/net/ethernet/intel/igb/igb_ethtool.c | 12 +++---- + drivers/net/ethernet/intel/igb/igb_main.c | 8 ++--- + drivers/net/ethernet/intel/igc/igc_ethtool.c | 12 +++---- + drivers/net/ethernet/intel/igc/igc_main.c | 8 ++--- + .../net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 8 ++--- + drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 8 ++--- + drivers/net/ethernet/intel/ixgbevf/ethtool.c | 12 +++---- + .../net/ethernet/intel/ixgbevf/ixgbevf_main.c | 8 ++--- + drivers/net/ethernet/marvell/mvneta.c | 8 ++--- + .../net/ethernet/marvell/mvpp2/mvpp2_main.c | 8 ++--- + drivers/net/ethernet/marvell/sky2.c | 8 ++--- + drivers/net/ethernet/mediatek/mtk_eth_soc.c | 8 ++--- + .../net/ethernet/mellanox/mlxsw/spectrum.c | 4 +-- + drivers/net/ethernet/microsoft/mana/mana_en.c | 8 ++--- + .../ethernet/microsoft/mana/mana_ethtool.c | 8 ++--- + .../ethernet/netronome/nfp/nfp_net_common.c | 8 ++--- + .../ethernet/netronome/nfp/nfp_net_ethtool.c | 8 ++--- + .../net/ethernet/netronome/nfp/nfp_net_repr.c | 4 +-- + drivers/net/ethernet/nvidia/forcedeth.c | 8 ++--- + .../net/ethernet/qualcomm/rmnet/rmnet_vnd.c | 4 +-- + drivers/net/ethernet/realtek/8139too.c | 8 ++--- + drivers/net/ethernet/socionext/sni_ave.c | 8 ++--- + drivers/net/ethernet/ti/am65-cpsw-nuss.c | 4 +-- + drivers/net/ethernet/ti/netcp_core.c | 8 ++--- + drivers/net/ethernet/via/via-rhine.c | 8 ++--- + .../net/ethernet/xilinx/xilinx_axienet_main.c | 8 ++--- + drivers/net/hyperv/netvsc_drv.c | 32 +++++++++---------- + drivers/net/ifb.c | 12 +++---- + drivers/net/ipvlan/ipvlan_main.c | 4 +-- + drivers/net/loopback.c | 4 +-- + drivers/net/macsec.c | 12 +++---- + drivers/net/macvlan.c | 4 +-- + drivers/net/mhi_net.c | 8 ++--- + drivers/net/netdevsim/netdev.c | 4 +-- + drivers/net/team/team.c | 4 +-- + drivers/net/team/team_mode_loadbalance.c | 4 +-- + drivers/net/veth.c | 12 +++---- + drivers/net/virtio_net.c | 16 +++++----- + drivers/net/vrf.c | 4 +-- + drivers/net/vxlan/vxlan_vnifilter.c | 4 +-- + drivers/net/wwan/mhi_wwan_mbim.c | 8 ++--- + drivers/net/xen-netfront.c | 8 ++--- + 63 files changed, 274 insertions(+), 274 deletions(-) + +diff --git a/drivers/net/ethernet/alacritech/slic.h b/drivers/net/ethernet/alacritech/slic.h +index 4eecbdfff3ff..82071d0e5f7f 100644 +--- a/drivers/net/ethernet/alacritech/slic.h ++++ b/drivers/net/ethernet/alacritech/slic.h +@@ -288,13 +288,13 @@ do { \ + u64_stats_update_end(&(st)->syncp); \ + } while (0) + +-#define SLIC_GET_STATS_COUNTER(newst, st, counter) \ +-{ \ +- unsigned int start; \ ++#define SLIC_GET_STATS_COUNTER(newst, st, counter) \ ++{ \ ++ unsigned int start; \ + do { \ +- start = u64_stats_fetch_begin_irq(&(st)->syncp); \ +- newst = (st)->counter; \ +- } while (u64_stats_fetch_retry_irq(&(st)->syncp, start)); \ ++ start = u64_stats_fetch_begin(&(st)->syncp); \ ++ newst = (st)->counter; \ ++ } while (u64_stats_fetch_retry(&(st)->syncp, start)); \ + } + + struct slic_upr { +diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c +index 444ccef76da2..8da79eedc057 100644 +--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c ++++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c +@@ -118,9 +118,9 @@ static void ena_safe_update_stat(u64 *src, u64 *dst, + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(syncp); ++ start = u64_stats_fetch_begin(syncp); + *(dst) = *src; +- } while (u64_stats_fetch_retry_irq(syncp, start)); ++ } while (u64_stats_fetch_retry(syncp, start)); + } + + static void ena_queue_stats(struct ena_adapter *adapter, u64 **data) +diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c +index 044b8afde69a..e296546f03cd 100644 +--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c ++++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c +@@ -3312,10 +3312,10 @@ static void ena_get_stats64(struct net_device *netdev, + tx_ring = &adapter->tx_ring[i]; + + do { +- start = u64_stats_fetch_begin_irq(&tx_ring->syncp); ++ start = u64_stats_fetch_begin(&tx_ring->syncp); + packets = tx_ring->tx_stats.cnt; + bytes = tx_ring->tx_stats.bytes; +- } while (u64_stats_fetch_retry_irq(&tx_ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&tx_ring->syncp, start)); + + stats->tx_packets += packets; + stats->tx_bytes += bytes; +@@ -3323,20 +3323,20 @@ static void ena_get_stats64(struct net_device *netdev, + rx_ring = &adapter->rx_ring[i]; + + do { +- start = u64_stats_fetch_begin_irq(&rx_ring->syncp); ++ start = u64_stats_fetch_begin(&rx_ring->syncp); + packets = rx_ring->rx_stats.cnt; + bytes = rx_ring->rx_stats.bytes; +- } while (u64_stats_fetch_retry_irq(&rx_ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&rx_ring->syncp, start)); + + stats->rx_packets += packets; + stats->rx_bytes += bytes; + } + + do { +- start = u64_stats_fetch_begin_irq(&adapter->syncp); ++ start = u64_stats_fetch_begin(&adapter->syncp); + rx_drops = adapter->dev_stats.rx_drops; + tx_drops = adapter->dev_stats.tx_drops; +- } while (u64_stats_fetch_retry_irq(&adapter->syncp, start)); ++ } while (u64_stats_fetch_retry(&adapter->syncp, start)); + + stats->rx_dropped = rx_drops; + stats->tx_dropped = tx_drops; +diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +index 4d9d7d1edb9b..697ce83eeae1 100644 +--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c ++++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +@@ -957,7 +957,7 @@ unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data) + /* This data should mimic aq_ethtool_queue_rx_stat_names structure */ + do { + count = 0; +- start = u64_stats_fetch_begin_irq(&self->stats.rx.syncp); ++ start = u64_stats_fetch_begin(&self->stats.rx.syncp); + data[count] = self->stats.rx.packets; + data[++count] = self->stats.rx.jumbo_packets; + data[++count] = self->stats.rx.lro_packets; +@@ -974,15 +974,15 @@ unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data) + data[++count] = self->stats.rx.xdp_tx; + data[++count] = self->stats.rx.xdp_invalid; + data[++count] = self->stats.rx.xdp_redirect; +- } while (u64_stats_fetch_retry_irq(&self->stats.rx.syncp, start)); ++ } while (u64_stats_fetch_retry(&self->stats.rx.syncp, start)); + } else { + /* This data should mimic aq_ethtool_queue_tx_stat_names structure */ + do { + count = 0; +- start = u64_stats_fetch_begin_irq(&self->stats.tx.syncp); ++ start = u64_stats_fetch_begin(&self->stats.tx.syncp); + data[count] = self->stats.tx.packets; + data[++count] = self->stats.tx.queue_restarts; +- } while (u64_stats_fetch_retry_irq(&self->stats.tx.syncp, start)); ++ } while (u64_stats_fetch_retry(&self->stats.tx.syncp, start)); + } + + return ++count; +diff --git a/drivers/net/ethernet/asix/ax88796c_main.c b/drivers/net/ethernet/asix/ax88796c_main.c +index 8b7cdf015a16..21376c79f671 100644 +--- a/drivers/net/ethernet/asix/ax88796c_main.c ++++ b/drivers/net/ethernet/asix/ax88796c_main.c +@@ -662,12 +662,12 @@ static void ax88796c_get_stats64(struct net_device *ndev, + s = per_cpu_ptr(ax_local->stats, cpu); + + do { +- start = u64_stats_fetch_begin_irq(&s->syncp); ++ start = u64_stats_fetch_begin(&s->syncp); + rx_packets = u64_stats_read(&s->rx_packets); + rx_bytes = u64_stats_read(&s->rx_bytes); + tx_packets = u64_stats_read(&s->tx_packets); + tx_bytes = u64_stats_read(&s->tx_bytes); +- } while (u64_stats_fetch_retry_irq(&s->syncp, start)); ++ } while (u64_stats_fetch_retry(&s->syncp, start)); + + stats->rx_packets += rx_packets; + stats->rx_bytes += rx_bytes; +diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c +index 7f876721596c..b751dc8486dc 100644 +--- a/drivers/net/ethernet/broadcom/b44.c ++++ b/drivers/net/ethernet/broadcom/b44.c +@@ -1680,7 +1680,7 @@ static void b44_get_stats64(struct net_device *dev, + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&hwstat->syncp); ++ start = u64_stats_fetch_begin(&hwstat->syncp); + + /* Convert HW stats into rtnl_link_stats64 stats. */ + nstat->rx_packets = hwstat->rx_pkts; +@@ -1714,7 +1714,7 @@ static void b44_get_stats64(struct net_device *dev, + /* Carrier lost counter seems to be broken for some devices */ + nstat->tx_carrier_errors = hwstat->tx_carrier_lost; + #endif +- } while (u64_stats_fetch_retry_irq(&hwstat->syncp, start)); ++ } while (u64_stats_fetch_retry(&hwstat->syncp, start)); + + } + +@@ -2082,12 +2082,12 @@ static void b44_get_ethtool_stats(struct net_device *dev, + do { + data_src = &hwstat->tx_good_octets; + data_dst = data; +- start = u64_stats_fetch_begin_irq(&hwstat->syncp); ++ start = u64_stats_fetch_begin(&hwstat->syncp); + + for (i = 0; i < ARRAY_SIZE(b44_gstrings); i++) + *data_dst++ = *data_src++; + +- } while (u64_stats_fetch_retry_irq(&hwstat->syncp, start)); ++ } while (u64_stats_fetch_retry(&hwstat->syncp, start)); + } + + static void b44_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) +diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c +index 425d6ccd5413..f8b1adc389b3 100644 +--- a/drivers/net/ethernet/broadcom/bcmsysport.c ++++ b/drivers/net/ethernet/broadcom/bcmsysport.c +@@ -457,10 +457,10 @@ static void bcm_sysport_update_tx_stats(struct bcm_sysport_priv *priv, + for (q = 0; q < priv->netdev->num_tx_queues; q++) { + ring = &priv->tx_rings[q]; + do { +- start = u64_stats_fetch_begin_irq(&priv->syncp); ++ start = u64_stats_fetch_begin(&priv->syncp); + bytes = ring->bytes; + packets = ring->packets; +- } while (u64_stats_fetch_retry_irq(&priv->syncp, start)); ++ } while (u64_stats_fetch_retry(&priv->syncp, start)); + + *tx_bytes += bytes; + *tx_packets += packets; +@@ -504,9 +504,9 @@ static void bcm_sysport_get_stats(struct net_device *dev, + if (s->stat_sizeof == sizeof(u64) && + s->type == BCM_SYSPORT_STAT_NETDEV64) { + do { +- start = u64_stats_fetch_begin_irq(syncp); ++ start = u64_stats_fetch_begin(syncp); + data[i] = *(u64 *)p; +- } while (u64_stats_fetch_retry_irq(syncp, start)); ++ } while (u64_stats_fetch_retry(syncp, start)); + } else + data[i] = *(u32 *)p; + j++; +@@ -1878,10 +1878,10 @@ static void bcm_sysport_get_stats64(struct net_device *dev, + &stats->tx_packets); + + do { +- start = u64_stats_fetch_begin_irq(&priv->syncp); ++ start = u64_stats_fetch_begin(&priv->syncp); + stats->rx_packets = stats64->rx_packets; + stats->rx_bytes = stats64->rx_bytes; +- } while (u64_stats_fetch_retry_irq(&priv->syncp, start)); ++ } while (u64_stats_fetch_retry(&priv->syncp, start)); + } + + static void bcm_sysport_netif_start(struct net_device *dev) +diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c +index 7c0b0bc033c9..e7137b468f5b 100644 +--- a/drivers/net/ethernet/cortina/gemini.c ++++ b/drivers/net/ethernet/cortina/gemini.c +@@ -1941,7 +1941,7 @@ static void gmac_get_stats64(struct net_device *netdev, + + /* Racing with RX NAPI */ + do { +- start = u64_stats_fetch_begin_irq(&port->rx_stats_syncp); ++ start = u64_stats_fetch_begin(&port->rx_stats_syncp); + + stats->rx_packets = port->stats.rx_packets; + stats->rx_bytes = port->stats.rx_bytes; +@@ -1953,11 +1953,11 @@ static void gmac_get_stats64(struct net_device *netdev, + stats->rx_crc_errors = port->stats.rx_crc_errors; + stats->rx_frame_errors = port->stats.rx_frame_errors; + +- } while (u64_stats_fetch_retry_irq(&port->rx_stats_syncp, start)); ++ } while (u64_stats_fetch_retry(&port->rx_stats_syncp, start)); + + /* Racing with MIB and TX completion interrupts */ + do { +- start = u64_stats_fetch_begin_irq(&port->ir_stats_syncp); ++ start = u64_stats_fetch_begin(&port->ir_stats_syncp); + + stats->tx_errors = port->stats.tx_errors; + stats->tx_packets = port->stats.tx_packets; +@@ -1967,15 +1967,15 @@ static void gmac_get_stats64(struct net_device *netdev, + stats->rx_missed_errors = port->stats.rx_missed_errors; + stats->rx_fifo_errors = port->stats.rx_fifo_errors; + +- } while (u64_stats_fetch_retry_irq(&port->ir_stats_syncp, start)); ++ } while (u64_stats_fetch_retry(&port->ir_stats_syncp, start)); + + /* Racing with hard_start_xmit */ + do { +- start = u64_stats_fetch_begin_irq(&port->tx_stats_syncp); ++ start = u64_stats_fetch_begin(&port->tx_stats_syncp); + + stats->tx_dropped = port->stats.tx_dropped; + +- } while (u64_stats_fetch_retry_irq(&port->tx_stats_syncp, start)); ++ } while (u64_stats_fetch_retry(&port->tx_stats_syncp, start)); + + stats->rx_dropped += stats->rx_missed_errors; + } +@@ -2044,18 +2044,18 @@ static void gmac_get_ethtool_stats(struct net_device *netdev, + /* Racing with MIB interrupt */ + do { + p = values; +- start = u64_stats_fetch_begin_irq(&port->ir_stats_syncp); ++ start = u64_stats_fetch_begin(&port->ir_stats_syncp); + + for (i = 0; i < RX_STATS_NUM; i++) + *p++ = port->hw_stats[i]; + +- } while (u64_stats_fetch_retry_irq(&port->ir_stats_syncp, start)); ++ } while (u64_stats_fetch_retry(&port->ir_stats_syncp, start)); + values = p; + + /* Racing with RX NAPI */ + do { + p = values; +- start = u64_stats_fetch_begin_irq(&port->rx_stats_syncp); ++ start = u64_stats_fetch_begin(&port->rx_stats_syncp); + + for (i = 0; i < RX_STATUS_NUM; i++) + *p++ = port->rx_stats[i]; +@@ -2063,13 +2063,13 @@ static void gmac_get_ethtool_stats(struct net_device *netdev, + *p++ = port->rx_csum_stats[i]; + *p++ = port->rx_napi_exits; + +- } while (u64_stats_fetch_retry_irq(&port->rx_stats_syncp, start)); ++ } while (u64_stats_fetch_retry(&port->rx_stats_syncp, start)); + values = p; + + /* Racing with TX start_xmit */ + do { + p = values; +- start = u64_stats_fetch_begin_irq(&port->tx_stats_syncp); ++ start = u64_stats_fetch_begin(&port->tx_stats_syncp); + + for (i = 0; i < TX_MAX_FRAGS; i++) { + *values++ = port->tx_frag_stats[i]; +@@ -2078,7 +2078,7 @@ static void gmac_get_ethtool_stats(struct net_device *netdev, + *values++ = port->tx_frags_linearized; + *values++ = port->tx_hw_csummed; + +- } while (u64_stats_fetch_retry_irq(&port->tx_stats_syncp, start)); ++ } while (u64_stats_fetch_retry(&port->tx_stats_syncp, start)); + } + + static int gmac_get_ksettings(struct net_device *netdev, +diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c +index 77edc3d9b505..a29de29bdf23 100644 +--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c ++++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c +@@ -389,10 +389,10 @@ static void be_get_ethtool_stats(struct net_device *netdev, + struct be_rx_stats *stats = rx_stats(rxo); + + do { +- start = u64_stats_fetch_begin_irq(&stats->sync); ++ start = u64_stats_fetch_begin(&stats->sync); + data[base] = stats->rx_bytes; + data[base + 1] = stats->rx_pkts; +- } while (u64_stats_fetch_retry_irq(&stats->sync, start)); ++ } while (u64_stats_fetch_retry(&stats->sync, start)); + + for (i = 2; i < ETHTOOL_RXSTATS_NUM; i++) { + p = (u8 *)stats + et_rx_stats[i].offset; +@@ -405,19 +405,19 @@ static void be_get_ethtool_stats(struct net_device *netdev, + struct be_tx_stats *stats = tx_stats(txo); + + do { +- start = u64_stats_fetch_begin_irq(&stats->sync_compl); ++ start = u64_stats_fetch_begin(&stats->sync_compl); + data[base] = stats->tx_compl; +- } while (u64_stats_fetch_retry_irq(&stats->sync_compl, start)); ++ } while (u64_stats_fetch_retry(&stats->sync_compl, start)); + + do { +- start = u64_stats_fetch_begin_irq(&stats->sync); ++ start = u64_stats_fetch_begin(&stats->sync); + for (i = 1; i < ETHTOOL_TXSTATS_NUM; i++) { + p = (u8 *)stats + et_tx_stats[i].offset; + data[base + i] = + (et_tx_stats[i].size == sizeof(u64)) ? + *(u64 *)p : *(u32 *)p; + } +- } while (u64_stats_fetch_retry_irq(&stats->sync, start)); ++ } while (u64_stats_fetch_retry(&stats->sync, start)); + base += ETHTOOL_TXSTATS_NUM; + } + } +diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c +index a9e4e6464a04..968fecfc03bd 100644 +--- a/drivers/net/ethernet/emulex/benet/be_main.c ++++ b/drivers/net/ethernet/emulex/benet/be_main.c +@@ -665,10 +665,10 @@ static void be_get_stats64(struct net_device *netdev, + const struct be_rx_stats *rx_stats = rx_stats(rxo); + + do { +- start = u64_stats_fetch_begin_irq(&rx_stats->sync); ++ start = u64_stats_fetch_begin(&rx_stats->sync); + pkts = rx_stats(rxo)->rx_pkts; + bytes = rx_stats(rxo)->rx_bytes; +- } while (u64_stats_fetch_retry_irq(&rx_stats->sync, start)); ++ } while (u64_stats_fetch_retry(&rx_stats->sync, start)); + stats->rx_packets += pkts; + stats->rx_bytes += bytes; + stats->multicast += rx_stats(rxo)->rx_mcast_pkts; +@@ -680,10 +680,10 @@ static void be_get_stats64(struct net_device *netdev, + const struct be_tx_stats *tx_stats = tx_stats(txo); + + do { +- start = u64_stats_fetch_begin_irq(&tx_stats->sync); ++ start = u64_stats_fetch_begin(&tx_stats->sync); + pkts = tx_stats(txo)->tx_pkts; + bytes = tx_stats(txo)->tx_bytes; +- } while (u64_stats_fetch_retry_irq(&tx_stats->sync, start)); ++ } while (u64_stats_fetch_retry(&tx_stats->sync, start)); + stats->tx_packets += pkts; + stats->tx_bytes += bytes; + } +@@ -2156,16 +2156,16 @@ static int be_get_new_eqd(struct be_eq_obj *eqo) + + for_all_rx_queues_on_eq(adapter, eqo, rxo, i) { + do { +- start = u64_stats_fetch_begin_irq(&rxo->stats.sync); ++ start = u64_stats_fetch_begin(&rxo->stats.sync); + rx_pkts += rxo->stats.rx_pkts; +- } while (u64_stats_fetch_retry_irq(&rxo->stats.sync, start)); ++ } while (u64_stats_fetch_retry(&rxo->stats.sync, start)); + } + + for_all_tx_queues_on_eq(adapter, eqo, txo, i) { + do { +- start = u64_stats_fetch_begin_irq(&txo->stats.sync); ++ start = u64_stats_fetch_begin(&txo->stats.sync); + tx_pkts += txo->stats.tx_reqs; +- } while (u64_stats_fetch_retry_irq(&txo->stats.sync, start)); ++ } while (u64_stats_fetch_retry(&txo->stats.sync, start)); + } + + /* Skip, if wrapped around or first calculation */ +diff --git a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h +index 671f51135c26..53b7e95213a8 100644 +--- a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h ++++ b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h +@@ -206,9 +206,9 @@ struct funeth_rxq { + + #define FUN_QSTAT_READ(q, seq, stats_copy) \ + do { \ +- seq = u64_stats_fetch_begin_irq(&(q)->syncp); \ ++ seq = u64_stats_fetch_begin(&(q)->syncp); \ + stats_copy = (q)->stats; \ +- } while (u64_stats_fetch_retry_irq(&(q)->syncp, (seq))) ++ } while (u64_stats_fetch_retry(&(q)->syncp, (seq))) + + #define FUN_INT_NAME_LEN (IFNAMSIZ + 16) + +diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c +index 033f17cb96be..0a5953089a24 100644 +--- a/drivers/net/ethernet/google/gve/gve_ethtool.c ++++ b/drivers/net/ethernet/google/gve/gve_ethtool.c +@@ -177,14 +177,14 @@ gve_get_ethtool_stats(struct net_device *netdev, + struct gve_rx_ring *rx = &priv->rx[ring]; + + start = +- u64_stats_fetch_begin_irq(&priv->rx[ring].statss); ++ u64_stats_fetch_begin(&priv->rx[ring].statss); + tmp_rx_pkts = rx->rpackets; + tmp_rx_bytes = rx->rbytes; + tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail; + tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail; + tmp_rx_desc_err_dropped_pkt = + rx->rx_desc_err_dropped_pkt; +- } while (u64_stats_fetch_retry_irq(&priv->rx[ring].statss, ++ } while (u64_stats_fetch_retry(&priv->rx[ring].statss, + start)); + rx_pkts += tmp_rx_pkts; + rx_bytes += tmp_rx_bytes; +@@ -198,10 +198,10 @@ gve_get_ethtool_stats(struct net_device *netdev, + if (priv->tx) { + do { + start = +- u64_stats_fetch_begin_irq(&priv->tx[ring].statss); ++ u64_stats_fetch_begin(&priv->tx[ring].statss); + tmp_tx_pkts = priv->tx[ring].pkt_done; + tmp_tx_bytes = priv->tx[ring].bytes_done; +- } while (u64_stats_fetch_retry_irq(&priv->tx[ring].statss, ++ } while (u64_stats_fetch_retry(&priv->tx[ring].statss, + start)); + tx_pkts += tmp_tx_pkts; + tx_bytes += tmp_tx_bytes; +@@ -259,13 +259,13 @@ gve_get_ethtool_stats(struct net_device *netdev, + data[i++] = rx->fill_cnt - rx->cnt; + do { + start = +- u64_stats_fetch_begin_irq(&priv->rx[ring].statss); ++ u64_stats_fetch_begin(&priv->rx[ring].statss); + tmp_rx_bytes = rx->rbytes; + tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail; + tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail; + tmp_rx_desc_err_dropped_pkt = + rx->rx_desc_err_dropped_pkt; +- } while (u64_stats_fetch_retry_irq(&priv->rx[ring].statss, ++ } while (u64_stats_fetch_retry(&priv->rx[ring].statss, + start)); + data[i++] = tmp_rx_bytes; + data[i++] = rx->rx_cont_packet_cnt; +@@ -331,9 +331,9 @@ gve_get_ethtool_stats(struct net_device *netdev, + } + do { + start = +- u64_stats_fetch_begin_irq(&priv->tx[ring].statss); ++ u64_stats_fetch_begin(&priv->tx[ring].statss); + tmp_tx_bytes = tx->bytes_done; +- } while (u64_stats_fetch_retry_irq(&priv->tx[ring].statss, ++ } while (u64_stats_fetch_retry(&priv->tx[ring].statss, + start)); + data[i++] = tmp_tx_bytes; + data[i++] = tx->wake_queue; +diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c +index d3f6ad586ba1..1c2cd3ee1956 100644 +--- a/drivers/net/ethernet/google/gve/gve_main.c ++++ b/drivers/net/ethernet/google/gve/gve_main.c +@@ -51,10 +51,10 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s) + for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) { + do { + start = +- u64_stats_fetch_begin_irq(&priv->rx[ring].statss); ++ u64_stats_fetch_begin(&priv->rx[ring].statss); + packets = priv->rx[ring].rpackets; + bytes = priv->rx[ring].rbytes; +- } while (u64_stats_fetch_retry_irq(&priv->rx[ring].statss, ++ } while (u64_stats_fetch_retry(&priv->rx[ring].statss, + start)); + s->rx_packets += packets; + s->rx_bytes += bytes; +@@ -64,10 +64,10 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s) + for (ring = 0; ring < priv->tx_cfg.num_queues; ring++) { + do { + start = +- u64_stats_fetch_begin_irq(&priv->tx[ring].statss); ++ u64_stats_fetch_begin(&priv->tx[ring].statss); + packets = priv->tx[ring].pkt_done; + bytes = priv->tx[ring].bytes_done; +- } while (u64_stats_fetch_retry_irq(&priv->tx[ring].statss, ++ } while (u64_stats_fetch_retry(&priv->tx[ring].statss, + start)); + s->tx_packets += packets; + s->tx_bytes += bytes; +@@ -1260,9 +1260,9 @@ void gve_handle_report_stats(struct gve_priv *priv) + } + + do { +- start = u64_stats_fetch_begin_irq(&priv->tx[idx].statss); ++ start = u64_stats_fetch_begin(&priv->tx[idx].statss); + tx_bytes = priv->tx[idx].bytes_done; +- } while (u64_stats_fetch_retry_irq(&priv->tx[idx].statss, start)); ++ } while (u64_stats_fetch_retry(&priv->tx[idx].statss, start)); + stats[stats_idx++] = (struct stats) { + .stat_name = cpu_to_be32(TX_WAKE_CNT), + .value = cpu_to_be64(priv->tx[idx].wake_queue), +diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +index 78d6752fe051..5bf81dca14fa 100644 +--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c ++++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +@@ -2496,7 +2496,7 @@ static void hns3_fetch_stats(struct rtnl_link_stats64 *stats, + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&ring->syncp); ++ start = u64_stats_fetch_begin(&ring->syncp); + if (is_tx) { + stats->tx_bytes += ring->stats.tx_bytes; + stats->tx_packets += ring->stats.tx_pkts; +@@ -2530,7 +2530,7 @@ static void hns3_fetch_stats(struct rtnl_link_stats64 *stats, + stats->multicast += ring->stats.rx_multicast; + stats->rx_length_errors += ring->stats.err_pkt_len; + } +- } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->syncp, start)); + } + + static void hns3_nic_get_stats64(struct net_device *netdev, +diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c +index d649c6e323c8..ceec8be2a73b 100644 +--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c ++++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c +@@ -74,14 +74,14 @@ void hinic_rxq_get_stats(struct hinic_rxq *rxq, struct hinic_rxq_stats *stats) + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&rxq_stats->syncp); ++ start = u64_stats_fetch_begin(&rxq_stats->syncp); + stats->pkts = rxq_stats->pkts; + stats->bytes = rxq_stats->bytes; + stats->errors = rxq_stats->csum_errors + + rxq_stats->other_errors; + stats->csum_errors = rxq_stats->csum_errors; + stats->other_errors = rxq_stats->other_errors; +- } while (u64_stats_fetch_retry_irq(&rxq_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&rxq_stats->syncp, start)); + } + + /** +diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c +index e91476c8ff8b..ad47ac51a139 100644 +--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c ++++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c +@@ -99,14 +99,14 @@ void hinic_txq_get_stats(struct hinic_txq *txq, struct hinic_txq_stats *stats) + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&txq_stats->syncp); ++ start = u64_stats_fetch_begin(&txq_stats->syncp); + stats->pkts = txq_stats->pkts; + stats->bytes = txq_stats->bytes; + stats->tx_busy = txq_stats->tx_busy; + stats->tx_wake = txq_stats->tx_wake; + stats->tx_dropped = txq_stats->tx_dropped; + stats->big_frags_pkts = txq_stats->big_frags_pkts; +- } while (u64_stats_fetch_retry_irq(&txq_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&txq_stats->syncp, start)); + } + + /** +diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +index 2cca9e84e31e..34ab5ff9823b 100644 +--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c ++++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +@@ -1229,10 +1229,10 @@ static void fm10k_get_stats64(struct net_device *netdev, + continue; + + do { +- start = u64_stats_fetch_begin_irq(&ring->syncp); ++ start = u64_stats_fetch_begin(&ring->syncp); + packets = ring->stats.packets; + bytes = ring->stats.bytes; +- } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->syncp, start)); + + stats->rx_packets += packets; + stats->rx_bytes += bytes; +@@ -1245,10 +1245,10 @@ static void fm10k_get_stats64(struct net_device *netdev, + continue; + + do { +- start = u64_stats_fetch_begin_irq(&ring->syncp); ++ start = u64_stats_fetch_begin(&ring->syncp); + packets = ring->stats.packets; + bytes = ring->stats.bytes; +- } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->syncp, start)); + + stats->tx_packets += packets; + stats->tx_bytes += bytes; +diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +index 107bcca7db8c..8f36fe90180f 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +@@ -154,7 +154,7 @@ __i40e_add_ethtool_stats(u64 **data, void *pointer, + * @ring: the ring to copy + * + * Queue statistics must be copied while protected by +- * u64_stats_fetch_begin_irq, so we can't directly use i40e_add_ethtool_stats. ++ * u64_stats_fetch_begin, so we can't directly use i40e_add_ethtool_stats. + * Assumes that queue stats are defined in i40e_gstrings_queue_stats. If the + * ring pointer is null, zero out the queue stat values and update the data + * pointer. Otherwise safely copy the stats from the ring into the supplied +@@ -172,16 +172,16 @@ i40e_add_queue_stats(u64 **data, struct i40e_ring *ring) + + /* To avoid invalid statistics values, ensure that we keep retrying + * the copy until we get a consistent value according to +- * u64_stats_fetch_retry_irq. But first, make sure our ring is ++ * u64_stats_fetch_retry. But first, make sure our ring is + * non-null before attempting to access its syncp. + */ + do { +- start = !ring ? 0 : u64_stats_fetch_begin_irq(&ring->syncp); ++ start = !ring ? 0 : u64_stats_fetch_begin(&ring->syncp); + for (i = 0; i < size; i++) { + i40e_add_one_ethtool_stat(&(*data)[i], ring, + &stats[i]); + } +- } while (ring && u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (ring && u64_stats_fetch_retry(&ring->syncp, start)); + + /* Once we successfully copy the stats in, update the data pointer */ + *data += size; +diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c +index b4157ff370a3..3b1f912c4c2b 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_main.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_main.c +@@ -419,10 +419,10 @@ static void i40e_get_netdev_stats_struct_tx(struct i40e_ring *ring, + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&ring->syncp); ++ start = u64_stats_fetch_begin(&ring->syncp); + packets = ring->stats.packets; + bytes = ring->stats.bytes; +- } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->syncp, start)); + + stats->tx_packets += packets; + stats->tx_bytes += bytes; +@@ -472,10 +472,10 @@ static void i40e_get_netdev_stats_struct(struct net_device *netdev, + if (!ring) + continue; + do { +- start = u64_stats_fetch_begin_irq(&ring->syncp); ++ start = u64_stats_fetch_begin(&ring->syncp); + packets = ring->stats.packets; + bytes = ring->stats.bytes; +- } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->syncp, start)); + + stats->rx_packets += packets; + stats->rx_bytes += bytes; +@@ -897,10 +897,10 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) + continue; + + do { +- start = u64_stats_fetch_begin_irq(&p->syncp); ++ start = u64_stats_fetch_begin(&p->syncp); + packets = p->stats.packets; + bytes = p->stats.bytes; +- } while (u64_stats_fetch_retry_irq(&p->syncp, start)); ++ } while (u64_stats_fetch_retry(&p->syncp, start)); + tx_b += bytes; + tx_p += packets; + tx_restart += p->tx_stats.restart_queue; +@@ -915,10 +915,10 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) + continue; + + do { +- start = u64_stats_fetch_begin_irq(&p->syncp); ++ start = u64_stats_fetch_begin(&p->syncp); + packets = p->stats.packets; + bytes = p->stats.bytes; +- } while (u64_stats_fetch_retry_irq(&p->syncp, start)); ++ } while (u64_stats_fetch_retry(&p->syncp, start)); + rx_b += bytes; + rx_p += packets; + rx_buf += p->rx_stats.alloc_buff_failed; +@@ -935,10 +935,10 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) + continue; + + do { +- start = u64_stats_fetch_begin_irq(&p->syncp); ++ start = u64_stats_fetch_begin(&p->syncp); + packets = p->stats.packets; + bytes = p->stats.bytes; +- } while (u64_stats_fetch_retry_irq(&p->syncp, start)); ++ } while (u64_stats_fetch_retry(&p->syncp, start)); + tx_b += bytes; + tx_p += packets; + tx_restart += p->tx_stats.restart_queue; +diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +index f4ac2b164b3e..892c6a4f03bb 100644 +--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c ++++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +@@ -147,7 +147,7 @@ __iavf_add_ethtool_stats(u64 **data, void *pointer, + * @ring: the ring to copy + * + * Queue statistics must be copied while protected by +- * u64_stats_fetch_begin_irq, so we can't directly use iavf_add_ethtool_stats. ++ * u64_stats_fetch_begin, so we can't directly use iavf_add_ethtool_stats. + * Assumes that queue stats are defined in iavf_gstrings_queue_stats. If the + * ring pointer is null, zero out the queue stat values and update the data + * pointer. Otherwise safely copy the stats from the ring into the supplied +@@ -165,14 +165,14 @@ iavf_add_queue_stats(u64 **data, struct iavf_ring *ring) + + /* To avoid invalid statistics values, ensure that we keep retrying + * the copy until we get a consistent value according to +- * u64_stats_fetch_retry_irq. But first, make sure our ring is ++ * u64_stats_fetch_retry. But first, make sure our ring is + * non-null before attempting to access its syncp. + */ + do { +- start = !ring ? 0 : u64_stats_fetch_begin_irq(&ring->syncp); ++ start = !ring ? 0 : u64_stats_fetch_begin(&ring->syncp); + for (i = 0; i < size; i++) + iavf_add_one_ethtool_stat(&(*data)[i], ring, &stats[i]); +- } while (ring && u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (ring && u64_stats_fetch_retry(&ring->syncp, start)); + + /* Once we successfully copy the stats in, update the data pointer */ + *data += size; +diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c +index f0f39364819a..f8d722339e89 100644 +--- a/drivers/net/ethernet/intel/ice/ice_main.c ++++ b/drivers/net/ethernet/intel/ice/ice_main.c +@@ -6419,10 +6419,10 @@ ice_fetch_u64_stats_per_ring(struct u64_stats_sync *syncp, + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(syncp); ++ start = u64_stats_fetch_begin(syncp); + *pkts = stats.pkts; + *bytes = stats.bytes; +- } while (u64_stats_fetch_retry_irq(syncp, start)); ++ } while (u64_stats_fetch_retry(syncp, start)); + } + + /** +diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c +index ceff537d9d22..4ee849985e2b 100644 +--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c ++++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c +@@ -2316,15 +2316,15 @@ static void igb_get_ethtool_stats(struct net_device *netdev, + + ring = adapter->tx_ring[j]; + do { +- start = u64_stats_fetch_begin_irq(&ring->tx_syncp); ++ start = u64_stats_fetch_begin(&ring->tx_syncp); + data[i] = ring->tx_stats.packets; + data[i+1] = ring->tx_stats.bytes; + data[i+2] = ring->tx_stats.restart_queue; +- } while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->tx_syncp, start)); + do { +- start = u64_stats_fetch_begin_irq(&ring->tx_syncp2); ++ start = u64_stats_fetch_begin(&ring->tx_syncp2); + restart2 = ring->tx_stats.restart_queue2; +- } while (u64_stats_fetch_retry_irq(&ring->tx_syncp2, start)); ++ } while (u64_stats_fetch_retry(&ring->tx_syncp2, start)); + data[i+2] += restart2; + + i += IGB_TX_QUEUE_STATS_LEN; +@@ -2332,13 +2332,13 @@ static void igb_get_ethtool_stats(struct net_device *netdev, + for (j = 0; j < adapter->num_rx_queues; j++) { + ring = adapter->rx_ring[j]; + do { +- start = u64_stats_fetch_begin_irq(&ring->rx_syncp); ++ start = u64_stats_fetch_begin(&ring->rx_syncp); + data[i] = ring->rx_stats.packets; + data[i+1] = ring->rx_stats.bytes; + data[i+2] = ring->rx_stats.drops; + data[i+3] = ring->rx_stats.csum_err; + data[i+4] = ring->rx_stats.alloc_failed; +- } while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->rx_syncp, start)); + i += IGB_RX_QUEUE_STATS_LEN; + } + spin_unlock(&adapter->stats64_lock); +diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c +index 45ce4ed16146..9824f7cfaca4 100644 +--- a/drivers/net/ethernet/intel/igb/igb_main.c ++++ b/drivers/net/ethernet/intel/igb/igb_main.c +@@ -6660,10 +6660,10 @@ void igb_update_stats(struct igb_adapter *adapter) + } + + do { +- start = u64_stats_fetch_begin_irq(&ring->rx_syncp); ++ start = u64_stats_fetch_begin(&ring->rx_syncp); + _bytes = ring->rx_stats.bytes; + _packets = ring->rx_stats.packets; +- } while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->rx_syncp, start)); + bytes += _bytes; + packets += _packets; + } +@@ -6676,10 +6676,10 @@ void igb_update_stats(struct igb_adapter *adapter) + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igb_ring *ring = adapter->tx_ring[i]; + do { +- start = u64_stats_fetch_begin_irq(&ring->tx_syncp); ++ start = u64_stats_fetch_begin(&ring->tx_syncp); + _bytes = ring->tx_stats.bytes; + _packets = ring->tx_stats.packets; +- } while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->tx_syncp, start)); + bytes += _bytes; + packets += _packets; + } +diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c +index 81897f7a90a9..dd8a9d27a167 100644 +--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c ++++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c +@@ -840,15 +840,15 @@ static void igc_ethtool_get_stats(struct net_device *netdev, + + ring = adapter->tx_ring[j]; + do { +- start = u64_stats_fetch_begin_irq(&ring->tx_syncp); ++ start = u64_stats_fetch_begin(&ring->tx_syncp); + data[i] = ring->tx_stats.packets; + data[i + 1] = ring->tx_stats.bytes; + data[i + 2] = ring->tx_stats.restart_queue; +- } while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->tx_syncp, start)); + do { +- start = u64_stats_fetch_begin_irq(&ring->tx_syncp2); ++ start = u64_stats_fetch_begin(&ring->tx_syncp2); + restart2 = ring->tx_stats.restart_queue2; +- } while (u64_stats_fetch_retry_irq(&ring->tx_syncp2, start)); ++ } while (u64_stats_fetch_retry(&ring->tx_syncp2, start)); + data[i + 2] += restart2; + + i += IGC_TX_QUEUE_STATS_LEN; +@@ -856,13 +856,13 @@ static void igc_ethtool_get_stats(struct net_device *netdev, + for (j = 0; j < adapter->num_rx_queues; j++) { + ring = adapter->rx_ring[j]; + do { +- start = u64_stats_fetch_begin_irq(&ring->rx_syncp); ++ start = u64_stats_fetch_begin(&ring->rx_syncp); + data[i] = ring->rx_stats.packets; + data[i + 1] = ring->rx_stats.bytes; + data[i + 2] = ring->rx_stats.drops; + data[i + 3] = ring->rx_stats.csum_err; + data[i + 4] = ring->rx_stats.alloc_failed; +- } while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->rx_syncp, start)); + i += IGC_RX_QUEUE_STATS_LEN; + } + spin_unlock(&adapter->stats64_lock); +diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c +index 4b6f882b380d..c8c5c9d96ba2 100644 +--- a/drivers/net/ethernet/intel/igc/igc_main.c ++++ b/drivers/net/ethernet/intel/igc/igc_main.c +@@ -4868,10 +4868,10 @@ void igc_update_stats(struct igc_adapter *adapter) + } + + do { +- start = u64_stats_fetch_begin_irq(&ring->rx_syncp); ++ start = u64_stats_fetch_begin(&ring->rx_syncp); + _bytes = ring->rx_stats.bytes; + _packets = ring->rx_stats.packets; +- } while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->rx_syncp, start)); + bytes += _bytes; + packets += _packets; + } +@@ -4885,10 +4885,10 @@ void igc_update_stats(struct igc_adapter *adapter) + struct igc_ring *ring = adapter->tx_ring[i]; + + do { +- start = u64_stats_fetch_begin_irq(&ring->tx_syncp); ++ start = u64_stats_fetch_begin(&ring->tx_syncp); + _bytes = ring->tx_stats.bytes; + _packets = ring->tx_stats.packets; +- } while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->tx_syncp, start)); + bytes += _bytes; + packets += _packets; + } +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +index 0051aa676e19..1c22ff2dba9b 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +@@ -1335,10 +1335,10 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev, + } + + do { +- start = u64_stats_fetch_begin_irq(&ring->syncp); ++ start = u64_stats_fetch_begin(&ring->syncp); + data[i] = ring->stats.packets; + data[i+1] = ring->stats.bytes; +- } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->syncp, start)); + i += 2; + } + for (j = 0; j < IXGBE_NUM_RX_QUEUES; j++) { +@@ -1351,10 +1351,10 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev, + } + + do { +- start = u64_stats_fetch_begin_irq(&ring->syncp); ++ start = u64_stats_fetch_begin(&ring->syncp); + data[i] = ring->stats.packets; + data[i+1] = ring->stats.bytes; +- } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->syncp, start)); + i += 2; + } + +diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +index 9e0e13638c46..ec86b61a8db8 100644 +--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c ++++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +@@ -9051,10 +9051,10 @@ static void ixgbe_get_ring_stats64(struct rtnl_link_stats64 *stats, + + if (ring) { + do { +- start = u64_stats_fetch_begin_irq(&ring->syncp); ++ start = u64_stats_fetch_begin(&ring->syncp); + packets = ring->stats.packets; + bytes = ring->stats.bytes; +- } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->syncp, start)); + stats->tx_packets += packets; + stats->tx_bytes += bytes; + } +@@ -9074,10 +9074,10 @@ static void ixgbe_get_stats64(struct net_device *netdev, + + if (ring) { + do { +- start = u64_stats_fetch_begin_irq(&ring->syncp); ++ start = u64_stats_fetch_begin(&ring->syncp); + packets = ring->stats.packets; + bytes = ring->stats.bytes; +- } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->syncp, start)); + stats->rx_packets += packets; + stats->rx_bytes += bytes; + } +diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c +index ccfa6b91aac6..296915414a7c 100644 +--- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c ++++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c +@@ -458,10 +458,10 @@ static void ixgbevf_get_ethtool_stats(struct net_device *netdev, + } + + do { +- start = u64_stats_fetch_begin_irq(&ring->syncp); ++ start = u64_stats_fetch_begin(&ring->syncp); + data[i] = ring->stats.packets; + data[i + 1] = ring->stats.bytes; +- } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->syncp, start)); + i += 2; + } + +@@ -475,10 +475,10 @@ static void ixgbevf_get_ethtool_stats(struct net_device *netdev, + } + + do { +- start = u64_stats_fetch_begin_irq(&ring->syncp); ++ start = u64_stats_fetch_begin(&ring->syncp); + data[i] = ring->stats.packets; + data[i + 1] = ring->stats.bytes; +- } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->syncp, start)); + i += 2; + } + +@@ -492,10 +492,10 @@ static void ixgbevf_get_ethtool_stats(struct net_device *netdev, + } + + do { +- start = u64_stats_fetch_begin_irq(&ring->syncp); ++ start = u64_stats_fetch_begin(&ring->syncp); + data[i] = ring->stats.packets; + data[i + 1] = ring->stats.bytes; +- } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->syncp, start)); + i += 2; + } + } +diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +index e338fa572793..a9479ddf68eb 100644 +--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c ++++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +@@ -4350,10 +4350,10 @@ static void ixgbevf_get_tx_ring_stats(struct rtnl_link_stats64 *stats, + + if (ring) { + do { +- start = u64_stats_fetch_begin_irq(&ring->syncp); ++ start = u64_stats_fetch_begin(&ring->syncp); + bytes = ring->stats.bytes; + packets = ring->stats.packets; +- } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->syncp, start)); + stats->tx_bytes += bytes; + stats->tx_packets += packets; + } +@@ -4376,10 +4376,10 @@ static void ixgbevf_get_stats(struct net_device *netdev, + for (i = 0; i < adapter->num_rx_queues; i++) { + ring = adapter->rx_ring[i]; + do { +- start = u64_stats_fetch_begin_irq(&ring->syncp); ++ start = u64_stats_fetch_begin(&ring->syncp); + bytes = ring->stats.bytes; + packets = ring->stats.packets; +- } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); ++ } while (u64_stats_fetch_retry(&ring->syncp, start)); + stats->rx_bytes += bytes; + stats->rx_packets += packets; + } +diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c +index eb4ebaa1c92f..327f03f80836 100644 +--- a/drivers/net/ethernet/marvell/mvneta.c ++++ b/drivers/net/ethernet/marvell/mvneta.c +@@ -813,14 +813,14 @@ mvneta_get_stats64(struct net_device *dev, + + cpu_stats = per_cpu_ptr(pp->stats, cpu); + do { +- start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); ++ start = u64_stats_fetch_begin(&cpu_stats->syncp); + rx_packets = cpu_stats->es.ps.rx_packets; + rx_bytes = cpu_stats->es.ps.rx_bytes; + rx_dropped = cpu_stats->rx_dropped; + rx_errors = cpu_stats->rx_errors; + tx_packets = cpu_stats->es.ps.tx_packets; + tx_bytes = cpu_stats->es.ps.tx_bytes; +- } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); + + stats->rx_packets += rx_packets; + stats->rx_bytes += rx_bytes; +@@ -4765,7 +4765,7 @@ mvneta_ethtool_update_pcpu_stats(struct mvneta_port *pp, + + stats = per_cpu_ptr(pp->stats, cpu); + do { +- start = u64_stats_fetch_begin_irq(&stats->syncp); ++ start = u64_stats_fetch_begin(&stats->syncp); + skb_alloc_error = stats->es.skb_alloc_error; + refill_error = stats->es.refill_error; + xdp_redirect = stats->es.ps.xdp_redirect; +@@ -4775,7 +4775,7 @@ mvneta_ethtool_update_pcpu_stats(struct mvneta_port *pp, + xdp_xmit_err = stats->es.ps.xdp_xmit_err; + xdp_tx = stats->es.ps.xdp_tx; + xdp_tx_err = stats->es.ps.xdp_tx_err; +- } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&stats->syncp, start)); + + es->skb_alloc_error += skb_alloc_error; + es->refill_error += refill_error; +diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +index f936640cca4e..8c7470ab4985 100644 +--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c ++++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +@@ -2008,7 +2008,7 @@ mvpp2_get_xdp_stats(struct mvpp2_port *port, struct mvpp2_pcpu_stats *xdp_stats) + + cpu_stats = per_cpu_ptr(port->stats, cpu); + do { +- start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); ++ start = u64_stats_fetch_begin(&cpu_stats->syncp); + xdp_redirect = cpu_stats->xdp_redirect; + xdp_pass = cpu_stats->xdp_pass; + xdp_drop = cpu_stats->xdp_drop; +@@ -2016,7 +2016,7 @@ mvpp2_get_xdp_stats(struct mvpp2_port *port, struct mvpp2_pcpu_stats *xdp_stats) + xdp_xmit_err = cpu_stats->xdp_xmit_err; + xdp_tx = cpu_stats->xdp_tx; + xdp_tx_err = cpu_stats->xdp_tx_err; +- } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); + + xdp_stats->xdp_redirect += xdp_redirect; + xdp_stats->xdp_pass += xdp_pass; +@@ -5115,12 +5115,12 @@ mvpp2_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) + + cpu_stats = per_cpu_ptr(port->stats, cpu); + do { +- start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); ++ start = u64_stats_fetch_begin(&cpu_stats->syncp); + rx_packets = cpu_stats->rx_packets; + rx_bytes = cpu_stats->rx_bytes; + tx_packets = cpu_stats->tx_packets; + tx_bytes = cpu_stats->tx_bytes; +- } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); + + stats->rx_packets += rx_packets; + stats->rx_bytes += rx_bytes; +diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c +index ab33ba1c3023..ff97b140886a 100644 +--- a/drivers/net/ethernet/marvell/sky2.c ++++ b/drivers/net/ethernet/marvell/sky2.c +@@ -3894,19 +3894,19 @@ static void sky2_get_stats(struct net_device *dev, + u64 _bytes, _packets; + + do { +- start = u64_stats_fetch_begin_irq(&sky2->rx_stats.syncp); ++ start = u64_stats_fetch_begin(&sky2->rx_stats.syncp); + _bytes = sky2->rx_stats.bytes; + _packets = sky2->rx_stats.packets; +- } while (u64_stats_fetch_retry_irq(&sky2->rx_stats.syncp, start)); ++ } while (u64_stats_fetch_retry(&sky2->rx_stats.syncp, start)); + + stats->rx_packets = _packets; + stats->rx_bytes = _bytes; + + do { +- start = u64_stats_fetch_begin_irq(&sky2->tx_stats.syncp); ++ start = u64_stats_fetch_begin(&sky2->tx_stats.syncp); + _bytes = sky2->tx_stats.bytes; + _packets = sky2->tx_stats.packets; +- } while (u64_stats_fetch_retry_irq(&sky2->tx_stats.syncp, start)); ++ } while (u64_stats_fetch_retry(&sky2->tx_stats.syncp, start)); + + stats->tx_packets = _packets; + stats->tx_bytes = _bytes; +diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c +index 17e6ac4445af..f737e2b9a29e 100644 +--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c ++++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c +@@ -866,7 +866,7 @@ static void mtk_get_stats64(struct net_device *dev, + } + + do { +- start = u64_stats_fetch_begin_irq(&hw_stats->syncp); ++ start = u64_stats_fetch_begin(&hw_stats->syncp); + storage->rx_packets = hw_stats->rx_packets; + storage->tx_packets = hw_stats->tx_packets; + storage->rx_bytes = hw_stats->rx_bytes; +@@ -878,7 +878,7 @@ static void mtk_get_stats64(struct net_device *dev, + storage->rx_crc_errors = hw_stats->rx_fcs_errors; + storage->rx_errors = hw_stats->rx_checksum_errors; + storage->tx_aborted_errors = hw_stats->tx_skip; +- } while (u64_stats_fetch_retry_irq(&hw_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&hw_stats->syncp, start)); + + storage->tx_errors = dev->stats.tx_errors; + storage->rx_dropped = dev->stats.rx_dropped; +@@ -3694,13 +3694,13 @@ static void mtk_get_ethtool_stats(struct net_device *dev, + + do { + data_dst = data; +- start = u64_stats_fetch_begin_irq(&hwstats->syncp); ++ start = u64_stats_fetch_begin(&hwstats->syncp); + + for (i = 0; i < ARRAY_SIZE(mtk_ethtool_stats); i++) + *data_dst++ = *(data_src + mtk_ethtool_stats[i].offset); + if (mtk_page_pool_enabled(mac->hw)) + mtk_ethtool_pp_stats(mac->hw, data_dst); +- } while (u64_stats_fetch_retry_irq(&hwstats->syncp, start)); ++ } while (u64_stats_fetch_retry(&hwstats->syncp, start)); + } + + static int mtk_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, +diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +index 67ecdb9e708f..8345499563a4 100644 +--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c ++++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +@@ -827,12 +827,12 @@ mlxsw_sp_port_get_sw_stats64(const struct net_device *dev, + for_each_possible_cpu(i) { + p = per_cpu_ptr(mlxsw_sp_port->pcpu_stats, i); + do { +- start = u64_stats_fetch_begin_irq(&p->syncp); ++ start = u64_stats_fetch_begin(&p->syncp); + rx_packets = p->rx_packets; + rx_bytes = p->rx_bytes; + tx_packets = p->tx_packets; + tx_bytes = p->tx_bytes; +- } while (u64_stats_fetch_retry_irq(&p->syncp, start)); ++ } while (u64_stats_fetch_retry(&p->syncp, start)); + + stats->rx_packets += rx_packets; + stats->rx_bytes += rx_bytes; +diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +index 27f4786ace4f..a5ca5c4a7896 100644 +--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c ++++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +@@ -1631,21 +1631,21 @@ static void nfp_net_stat64(struct net_device *netdev, + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&r_vec->rx_sync); ++ start = u64_stats_fetch_begin(&r_vec->rx_sync); + data[0] = r_vec->rx_pkts; + data[1] = r_vec->rx_bytes; + data[2] = r_vec->rx_drops; +- } while (u64_stats_fetch_retry_irq(&r_vec->rx_sync, start)); ++ } while (u64_stats_fetch_retry(&r_vec->rx_sync, start)); + stats->rx_packets += data[0]; + stats->rx_bytes += data[1]; + stats->rx_dropped += data[2]; + + do { +- start = u64_stats_fetch_begin_irq(&r_vec->tx_sync); ++ start = u64_stats_fetch_begin(&r_vec->tx_sync); + data[0] = r_vec->tx_pkts; + data[1] = r_vec->tx_bytes; + data[2] = r_vec->tx_errors; +- } while (u64_stats_fetch_retry_irq(&r_vec->tx_sync, start)); ++ } while (u64_stats_fetch_retry(&r_vec->tx_sync, start)); + stats->tx_packets += data[0]; + stats->tx_bytes += data[1]; + stats->tx_errors += data[2]; +diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +index af376b900067..cc97b3d00414 100644 +--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c ++++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +@@ -881,7 +881,7 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data) + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&nn->r_vecs[i].rx_sync); ++ start = u64_stats_fetch_begin(&nn->r_vecs[i].rx_sync); + data[0] = nn->r_vecs[i].rx_pkts; + tmp[0] = nn->r_vecs[i].hw_csum_rx_ok; + tmp[1] = nn->r_vecs[i].hw_csum_rx_inner_ok; +@@ -889,10 +889,10 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data) + tmp[3] = nn->r_vecs[i].hw_csum_rx_error; + tmp[4] = nn->r_vecs[i].rx_replace_buf_alloc_fail; + tmp[5] = nn->r_vecs[i].hw_tls_rx; +- } while (u64_stats_fetch_retry_irq(&nn->r_vecs[i].rx_sync, start)); ++ } while (u64_stats_fetch_retry(&nn->r_vecs[i].rx_sync, start)); + + do { +- start = u64_stats_fetch_begin_irq(&nn->r_vecs[i].tx_sync); ++ start = u64_stats_fetch_begin(&nn->r_vecs[i].tx_sync); + data[1] = nn->r_vecs[i].tx_pkts; + data[2] = nn->r_vecs[i].tx_busy; + tmp[6] = nn->r_vecs[i].hw_csum_tx; +@@ -902,7 +902,7 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data) + tmp[10] = nn->r_vecs[i].hw_tls_tx; + tmp[11] = nn->r_vecs[i].tls_tx_fallback; + tmp[12] = nn->r_vecs[i].tls_tx_no_fallback; +- } while (u64_stats_fetch_retry_irq(&nn->r_vecs[i].tx_sync, start)); ++ } while (u64_stats_fetch_retry(&nn->r_vecs[i].tx_sync, start)); + + data += NN_RVEC_PER_Q_STATS; + +diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +index 8b77582bdfa0..a6b6ca1fd55e 100644 +--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c ++++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +@@ -134,13 +134,13 @@ nfp_repr_get_host_stats64(const struct net_device *netdev, + + repr_stats = per_cpu_ptr(repr->stats, i); + do { +- start = u64_stats_fetch_begin_irq(&repr_stats->syncp); ++ start = u64_stats_fetch_begin(&repr_stats->syncp); + tbytes = repr_stats->tx_bytes; + tpkts = repr_stats->tx_packets; + tdrops = repr_stats->tx_drops; + rbytes = repr_stats->rx_bytes; + rpkts = repr_stats->rx_packets; +- } while (u64_stats_fetch_retry_irq(&repr_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&repr_stats->syncp, start)); + + stats->tx_bytes += tbytes; + stats->tx_packets += tpkts; +diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c +index 486cbc8ab224..7a549b834e97 100644 +--- a/drivers/net/ethernet/nvidia/forcedeth.c ++++ b/drivers/net/ethernet/nvidia/forcedeth.c +@@ -1734,12 +1734,12 @@ static void nv_get_stats(int cpu, struct fe_priv *np, + u64 tx_packets, tx_bytes, tx_dropped; + + do { +- syncp_start = u64_stats_fetch_begin_irq(&np->swstats_rx_syncp); ++ syncp_start = u64_stats_fetch_begin(&np->swstats_rx_syncp); + rx_packets = src->stat_rx_packets; + rx_bytes = src->stat_rx_bytes; + rx_dropped = src->stat_rx_dropped; + rx_missed_errors = src->stat_rx_missed_errors; +- } while (u64_stats_fetch_retry_irq(&np->swstats_rx_syncp, syncp_start)); ++ } while (u64_stats_fetch_retry(&np->swstats_rx_syncp, syncp_start)); + + storage->rx_packets += rx_packets; + storage->rx_bytes += rx_bytes; +@@ -1747,11 +1747,11 @@ static void nv_get_stats(int cpu, struct fe_priv *np, + storage->rx_missed_errors += rx_missed_errors; + + do { +- syncp_start = u64_stats_fetch_begin_irq(&np->swstats_tx_syncp); ++ syncp_start = u64_stats_fetch_begin(&np->swstats_tx_syncp); + tx_packets = src->stat_tx_packets; + tx_bytes = src->stat_tx_bytes; + tx_dropped = src->stat_tx_dropped; +- } while (u64_stats_fetch_retry_irq(&np->swstats_tx_syncp, syncp_start)); ++ } while (u64_stats_fetch_retry(&np->swstats_tx_syncp, syncp_start)); + + storage->tx_packets += tx_packets; + storage->tx_bytes += tx_bytes; +diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +index 1b2119b1d48a..3f5e6572d20e 100644 +--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c ++++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +@@ -135,9 +135,9 @@ static void rmnet_get_stats64(struct net_device *dev, + pcpu_ptr = per_cpu_ptr(priv->pcpu_stats, cpu); + + do { +- start = u64_stats_fetch_begin_irq(&pcpu_ptr->syncp); ++ start = u64_stats_fetch_begin(&pcpu_ptr->syncp); + snapshot = pcpu_ptr->stats; /* struct assignment */ +- } while (u64_stats_fetch_retry_irq(&pcpu_ptr->syncp, start)); ++ } while (u64_stats_fetch_retry(&pcpu_ptr->syncp, start)); + + total_stats.rx_pkts += snapshot.rx_pkts; + total_stats.rx_bytes += snapshot.rx_bytes; +diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c +index 469e2e229c6e..9ce0e8a64ba8 100644 +--- a/drivers/net/ethernet/realtek/8139too.c ++++ b/drivers/net/ethernet/realtek/8139too.c +@@ -2532,16 +2532,16 @@ rtl8139_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) + netdev_stats_to_stats64(stats, &dev->stats); + + do { +- start = u64_stats_fetch_begin_irq(&tp->rx_stats.syncp); ++ start = u64_stats_fetch_begin(&tp->rx_stats.syncp); + stats->rx_packets = tp->rx_stats.packets; + stats->rx_bytes = tp->rx_stats.bytes; +- } while (u64_stats_fetch_retry_irq(&tp->rx_stats.syncp, start)); ++ } while (u64_stats_fetch_retry(&tp->rx_stats.syncp, start)); + + do { +- start = u64_stats_fetch_begin_irq(&tp->tx_stats.syncp); ++ start = u64_stats_fetch_begin(&tp->tx_stats.syncp); + stats->tx_packets = tp->tx_stats.packets; + stats->tx_bytes = tp->tx_stats.bytes; +- } while (u64_stats_fetch_retry_irq(&tp->tx_stats.syncp, start)); ++ } while (u64_stats_fetch_retry(&tp->tx_stats.syncp, start)); + } + + /* Set or clear the multicast filter for this adaptor. +diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c +index d2c6a5dfdc0e..b7e24ae92525 100644 +--- a/drivers/net/ethernet/socionext/sni_ave.c ++++ b/drivers/net/ethernet/socionext/sni_ave.c +@@ -1508,16 +1508,16 @@ static void ave_get_stats64(struct net_device *ndev, + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&priv->stats_rx.syncp); ++ start = u64_stats_fetch_begin(&priv->stats_rx.syncp); + stats->rx_packets = priv->stats_rx.packets; + stats->rx_bytes = priv->stats_rx.bytes; +- } while (u64_stats_fetch_retry_irq(&priv->stats_rx.syncp, start)); ++ } while (u64_stats_fetch_retry(&priv->stats_rx.syncp, start)); + + do { +- start = u64_stats_fetch_begin_irq(&priv->stats_tx.syncp); ++ start = u64_stats_fetch_begin(&priv->stats_tx.syncp); + stats->tx_packets = priv->stats_tx.packets; + stats->tx_bytes = priv->stats_tx.bytes; +- } while (u64_stats_fetch_retry_irq(&priv->stats_tx.syncp, start)); ++ } while (u64_stats_fetch_retry(&priv->stats_tx.syncp, start)); + + stats->rx_errors = priv->stats_rx.errors; + stats->tx_errors = priv->stats_tx.errors; +diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c +index 9f2553799895..1085b0642c28 100644 +--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c ++++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c +@@ -1376,12 +1376,12 @@ static void am65_cpsw_nuss_ndo_get_stats(struct net_device *dev, + + cpu_stats = per_cpu_ptr(ndev_priv->stats, cpu); + do { +- start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); ++ start = u64_stats_fetch_begin(&cpu_stats->syncp); + rx_packets = cpu_stats->rx_packets; + rx_bytes = cpu_stats->rx_bytes; + tx_packets = cpu_stats->tx_packets; + tx_bytes = cpu_stats->tx_bytes; +- } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); + + stats->rx_packets += rx_packets; + stats->rx_bytes += rx_bytes; +diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c +index 9eb9eaff4dc9..1bb596a9d8a2 100644 +--- a/drivers/net/ethernet/ti/netcp_core.c ++++ b/drivers/net/ethernet/ti/netcp_core.c +@@ -1916,16 +1916,16 @@ netcp_get_stats(struct net_device *ndev, struct rtnl_link_stats64 *stats) + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&p->syncp_rx); ++ start = u64_stats_fetch_begin(&p->syncp_rx); + rxpackets = p->rx_packets; + rxbytes = p->rx_bytes; +- } while (u64_stats_fetch_retry_irq(&p->syncp_rx, start)); ++ } while (u64_stats_fetch_retry(&p->syncp_rx, start)); + + do { +- start = u64_stats_fetch_begin_irq(&p->syncp_tx); ++ start = u64_stats_fetch_begin(&p->syncp_tx); + txpackets = p->tx_packets; + txbytes = p->tx_bytes; +- } while (u64_stats_fetch_retry_irq(&p->syncp_tx, start)); ++ } while (u64_stats_fetch_retry(&p->syncp_tx, start)); + + stats->rx_packets = rxpackets; + stats->rx_bytes = rxbytes; +diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c +index 0fb15a17b547..d716e6fe26e1 100644 +--- a/drivers/net/ethernet/via/via-rhine.c ++++ b/drivers/net/ethernet/via/via-rhine.c +@@ -2217,16 +2217,16 @@ rhine_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) + netdev_stats_to_stats64(stats, &dev->stats); + + do { +- start = u64_stats_fetch_begin_irq(&rp->rx_stats.syncp); ++ start = u64_stats_fetch_begin(&rp->rx_stats.syncp); + stats->rx_packets = rp->rx_stats.packets; + stats->rx_bytes = rp->rx_stats.bytes; +- } while (u64_stats_fetch_retry_irq(&rp->rx_stats.syncp, start)); ++ } while (u64_stats_fetch_retry(&rp->rx_stats.syncp, start)); + + do { +- start = u64_stats_fetch_begin_irq(&rp->tx_stats.syncp); ++ start = u64_stats_fetch_begin(&rp->tx_stats.syncp); + stats->tx_packets = rp->tx_stats.packets; + stats->tx_bytes = rp->tx_stats.bytes; +- } while (u64_stats_fetch_retry_irq(&rp->tx_stats.syncp, start)); ++ } while (u64_stats_fetch_retry(&rp->tx_stats.syncp, start)); + } + + static void rhine_set_rx_mode(struct net_device *dev) +diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +index 5ea9dc251dd9..c678876a7826 100644 +--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c ++++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +@@ -1305,16 +1305,16 @@ axienet_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) + netdev_stats_to_stats64(stats, &dev->stats); + + do { +- start = u64_stats_fetch_begin_irq(&lp->rx_stat_sync); ++ start = u64_stats_fetch_begin(&lp->rx_stat_sync); + stats->rx_packets = u64_stats_read(&lp->rx_packets); + stats->rx_bytes = u64_stats_read(&lp->rx_bytes); +- } while (u64_stats_fetch_retry_irq(&lp->rx_stat_sync, start)); ++ } while (u64_stats_fetch_retry(&lp->rx_stat_sync, start)); + + do { +- start = u64_stats_fetch_begin_irq(&lp->tx_stat_sync); ++ start = u64_stats_fetch_begin(&lp->tx_stat_sync); + stats->tx_packets = u64_stats_read(&lp->tx_packets); + stats->tx_bytes = u64_stats_read(&lp->tx_bytes); +- } while (u64_stats_fetch_retry_irq(&lp->tx_stat_sync, start)); ++ } while (u64_stats_fetch_retry(&lp->tx_stat_sync, start)); + } + + static const struct net_device_ops axienet_netdev_ops = { +diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c +index 0285894c892a..cf87d7ed3779 100644 +--- a/drivers/net/hyperv/netvsc_drv.c ++++ b/drivers/net/hyperv/netvsc_drv.c +@@ -1264,12 +1264,12 @@ static void netvsc_get_vf_stats(struct net_device *net, + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&stats->syncp); ++ start = u64_stats_fetch_begin(&stats->syncp); + rx_packets = stats->rx_packets; + tx_packets = stats->tx_packets; + rx_bytes = stats->rx_bytes; + tx_bytes = stats->tx_bytes; +- } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&stats->syncp, start)); + + tot->rx_packets += rx_packets; + tot->tx_packets += tx_packets; +@@ -1294,12 +1294,12 @@ static void netvsc_get_pcpu_stats(struct net_device *net, + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&stats->syncp); ++ start = u64_stats_fetch_begin(&stats->syncp); + this_tot->vf_rx_packets = stats->rx_packets; + this_tot->vf_tx_packets = stats->tx_packets; + this_tot->vf_rx_bytes = stats->rx_bytes; + this_tot->vf_tx_bytes = stats->tx_bytes; +- } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&stats->syncp, start)); + this_tot->rx_packets = this_tot->vf_rx_packets; + this_tot->tx_packets = this_tot->vf_tx_packets; + this_tot->rx_bytes = this_tot->vf_rx_bytes; +@@ -1318,20 +1318,20 @@ static void netvsc_get_pcpu_stats(struct net_device *net, + + tx_stats = &nvchan->tx_stats; + do { +- start = u64_stats_fetch_begin_irq(&tx_stats->syncp); ++ start = u64_stats_fetch_begin(&tx_stats->syncp); + packets = tx_stats->packets; + bytes = tx_stats->bytes; +- } while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&tx_stats->syncp, start)); + + this_tot->tx_bytes += bytes; + this_tot->tx_packets += packets; + + rx_stats = &nvchan->rx_stats; + do { +- start = u64_stats_fetch_begin_irq(&rx_stats->syncp); ++ start = u64_stats_fetch_begin(&rx_stats->syncp); + packets = rx_stats->packets; + bytes = rx_stats->bytes; +- } while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&rx_stats->syncp, start)); + + this_tot->rx_bytes += bytes; + this_tot->rx_packets += packets; +@@ -1370,21 +1370,21 @@ static void netvsc_get_stats64(struct net_device *net, + + tx_stats = &nvchan->tx_stats; + do { +- start = u64_stats_fetch_begin_irq(&tx_stats->syncp); ++ start = u64_stats_fetch_begin(&tx_stats->syncp); + packets = tx_stats->packets; + bytes = tx_stats->bytes; +- } while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&tx_stats->syncp, start)); + + t->tx_bytes += bytes; + t->tx_packets += packets; + + rx_stats = &nvchan->rx_stats; + do { +- start = u64_stats_fetch_begin_irq(&rx_stats->syncp); ++ start = u64_stats_fetch_begin(&rx_stats->syncp); + packets = rx_stats->packets; + bytes = rx_stats->bytes; + multicast = rx_stats->multicast + rx_stats->broadcast; +- } while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&rx_stats->syncp, start)); + + t->rx_bytes += bytes; + t->rx_packets += packets; +@@ -1527,24 +1527,24 @@ static void netvsc_get_ethtool_stats(struct net_device *dev, + tx_stats = &nvdev->chan_table[j].tx_stats; + + do { +- start = u64_stats_fetch_begin_irq(&tx_stats->syncp); ++ start = u64_stats_fetch_begin(&tx_stats->syncp); + packets = tx_stats->packets; + bytes = tx_stats->bytes; + xdp_xmit = tx_stats->xdp_xmit; +- } while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&tx_stats->syncp, start)); + data[i++] = packets; + data[i++] = bytes; + data[i++] = xdp_xmit; + + rx_stats = &nvdev->chan_table[j].rx_stats; + do { +- start = u64_stats_fetch_begin_irq(&rx_stats->syncp); ++ start = u64_stats_fetch_begin(&rx_stats->syncp); + packets = rx_stats->packets; + bytes = rx_stats->bytes; + xdp_drop = rx_stats->xdp_drop; + xdp_redirect = rx_stats->xdp_redirect; + xdp_tx = rx_stats->xdp_tx; +- } while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&rx_stats->syncp, start)); + data[i++] = packets; + data[i++] = bytes; + data[i++] = xdp_drop; +diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c +index 1c64d5347b8e..78253ad57b2e 100644 +--- a/drivers/net/ifb.c ++++ b/drivers/net/ifb.c +@@ -162,18 +162,18 @@ static void ifb_stats64(struct net_device *dev, + + for (i = 0; i < dev->num_tx_queues; i++,txp++) { + do { +- start = u64_stats_fetch_begin_irq(&txp->rx_stats.sync); ++ start = u64_stats_fetch_begin(&txp->rx_stats.sync); + packets = txp->rx_stats.packets; + bytes = txp->rx_stats.bytes; +- } while (u64_stats_fetch_retry_irq(&txp->rx_stats.sync, start)); ++ } while (u64_stats_fetch_retry(&txp->rx_stats.sync, start)); + stats->rx_packets += packets; + stats->rx_bytes += bytes; + + do { +- start = u64_stats_fetch_begin_irq(&txp->tx_stats.sync); ++ start = u64_stats_fetch_begin(&txp->tx_stats.sync); + packets = txp->tx_stats.packets; + bytes = txp->tx_stats.bytes; +- } while (u64_stats_fetch_retry_irq(&txp->tx_stats.sync, start)); ++ } while (u64_stats_fetch_retry(&txp->tx_stats.sync, start)); + stats->tx_packets += packets; + stats->tx_bytes += bytes; + } +@@ -245,12 +245,12 @@ static void ifb_fill_stats_data(u64 **data, + int j; + + do { +- start = u64_stats_fetch_begin_irq(&q_stats->sync); ++ start = u64_stats_fetch_begin(&q_stats->sync); + for (j = 0; j < IFB_Q_STATS_LEN; j++) { + offset = ifb_q_stats_desc[j].offset; + (*data)[j] = *(u64 *)(stats_base + offset); + } +- } while (u64_stats_fetch_retry_irq(&q_stats->sync, start)); ++ } while (u64_stats_fetch_retry(&q_stats->sync, start)); + + *data += IFB_Q_STATS_LEN; + } +diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c +index fbf2d5b67aaf..57c79f5f2991 100644 +--- a/drivers/net/ipvlan/ipvlan_main.c ++++ b/drivers/net/ipvlan/ipvlan_main.c +@@ -301,13 +301,13 @@ static void ipvlan_get_stats64(struct net_device *dev, + for_each_possible_cpu(idx) { + pcptr = per_cpu_ptr(ipvlan->pcpu_stats, idx); + do { +- strt= u64_stats_fetch_begin_irq(&pcptr->syncp); ++ strt = u64_stats_fetch_begin(&pcptr->syncp); + rx_pkts = u64_stats_read(&pcptr->rx_pkts); + rx_bytes = u64_stats_read(&pcptr->rx_bytes); + rx_mcast = u64_stats_read(&pcptr->rx_mcast); + tx_pkts = u64_stats_read(&pcptr->tx_pkts); + tx_bytes = u64_stats_read(&pcptr->tx_bytes); +- } while (u64_stats_fetch_retry_irq(&pcptr->syncp, ++ } while (u64_stats_fetch_retry(&pcptr->syncp, + strt)); + + s->rx_packets += rx_pkts; +diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c +index 2e9742952c4e..f6d53e63ef4e 100644 +--- a/drivers/net/loopback.c ++++ b/drivers/net/loopback.c +@@ -106,10 +106,10 @@ void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes) + + lb_stats = per_cpu_ptr(dev->lstats, i); + do { +- start = u64_stats_fetch_begin_irq(&lb_stats->syncp); ++ start = u64_stats_fetch_begin(&lb_stats->syncp); + tpackets = u64_stats_read(&lb_stats->packets); + tbytes = u64_stats_read(&lb_stats->bytes); +- } while (u64_stats_fetch_retry_irq(&lb_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&lb_stats->syncp, start)); + *bytes += tbytes; + *packets += tpackets; + } +diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c +index 209ee9f35275..f9f25b5f1745 100644 +--- a/drivers/net/macsec.c ++++ b/drivers/net/macsec.c +@@ -2802,9 +2802,9 @@ static void get_rx_sc_stats(struct net_device *dev, + + stats = per_cpu_ptr(rx_sc->stats, cpu); + do { +- start = u64_stats_fetch_begin_irq(&stats->syncp); ++ start = u64_stats_fetch_begin(&stats->syncp); + memcpy(&tmp, &stats->stats, sizeof(tmp)); +- } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&stats->syncp, start)); + + sum->InOctetsValidated += tmp.InOctetsValidated; + sum->InOctetsDecrypted += tmp.InOctetsDecrypted; +@@ -2883,9 +2883,9 @@ static void get_tx_sc_stats(struct net_device *dev, + + stats = per_cpu_ptr(macsec_priv(dev)->secy.tx_sc.stats, cpu); + do { +- start = u64_stats_fetch_begin_irq(&stats->syncp); ++ start = u64_stats_fetch_begin(&stats->syncp); + memcpy(&tmp, &stats->stats, sizeof(tmp)); +- } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&stats->syncp, start)); + + sum->OutPktsProtected += tmp.OutPktsProtected; + sum->OutPktsEncrypted += tmp.OutPktsEncrypted; +@@ -2939,9 +2939,9 @@ static void get_secy_stats(struct net_device *dev, struct macsec_dev_stats *sum) + + stats = per_cpu_ptr(macsec_priv(dev)->stats, cpu); + do { +- start = u64_stats_fetch_begin_irq(&stats->syncp); ++ start = u64_stats_fetch_begin(&stats->syncp); + memcpy(&tmp, &stats->stats, sizeof(tmp)); +- } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&stats->syncp, start)); + + sum->OutPktsUntagged += tmp.OutPktsUntagged; + sum->InPktsUntagged += tmp.InPktsUntagged; +diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c +index 012830d12fde..9bea3f1b0a8a 100644 +--- a/drivers/net/macvlan.c ++++ b/drivers/net/macvlan.c +@@ -948,13 +948,13 @@ static void macvlan_dev_get_stats64(struct net_device *dev, + for_each_possible_cpu(i) { + p = per_cpu_ptr(vlan->pcpu_stats, i); + do { +- start = u64_stats_fetch_begin_irq(&p->syncp); ++ start = u64_stats_fetch_begin(&p->syncp); + rx_packets = u64_stats_read(&p->rx_packets); + rx_bytes = u64_stats_read(&p->rx_bytes); + rx_multicast = u64_stats_read(&p->rx_multicast); + tx_packets = u64_stats_read(&p->tx_packets); + tx_bytes = u64_stats_read(&p->tx_bytes); +- } while (u64_stats_fetch_retry_irq(&p->syncp, start)); ++ } while (u64_stats_fetch_retry(&p->syncp, start)); + + stats->rx_packets += rx_packets; + stats->rx_bytes += rx_bytes; +diff --git a/drivers/net/mhi_net.c b/drivers/net/mhi_net.c +index 0b9d37979133..3d322ac4f6a5 100644 +--- a/drivers/net/mhi_net.c ++++ b/drivers/net/mhi_net.c +@@ -104,19 +104,19 @@ static void mhi_ndo_get_stats64(struct net_device *ndev, + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&mhi_netdev->stats.rx_syncp); ++ start = u64_stats_fetch_begin(&mhi_netdev->stats.rx_syncp); + stats->rx_packets = u64_stats_read(&mhi_netdev->stats.rx_packets); + stats->rx_bytes = u64_stats_read(&mhi_netdev->stats.rx_bytes); + stats->rx_errors = u64_stats_read(&mhi_netdev->stats.rx_errors); +- } while (u64_stats_fetch_retry_irq(&mhi_netdev->stats.rx_syncp, start)); ++ } while (u64_stats_fetch_retry(&mhi_netdev->stats.rx_syncp, start)); + + do { +- start = u64_stats_fetch_begin_irq(&mhi_netdev->stats.tx_syncp); ++ start = u64_stats_fetch_begin(&mhi_netdev->stats.tx_syncp); + stats->tx_packets = u64_stats_read(&mhi_netdev->stats.tx_packets); + stats->tx_bytes = u64_stats_read(&mhi_netdev->stats.tx_bytes); + stats->tx_errors = u64_stats_read(&mhi_netdev->stats.tx_errors); + stats->tx_dropped = u64_stats_read(&mhi_netdev->stats.tx_dropped); +- } while (u64_stats_fetch_retry_irq(&mhi_netdev->stats.tx_syncp, start)); ++ } while (u64_stats_fetch_retry(&mhi_netdev->stats.tx_syncp, start)); + } + + static const struct net_device_ops mhi_netdev_ops = { +diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c +index 9a1a5b203624..e470e3398abc 100644 +--- a/drivers/net/netdevsim/netdev.c ++++ b/drivers/net/netdevsim/netdev.c +@@ -67,10 +67,10 @@ nsim_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&ns->syncp); ++ start = u64_stats_fetch_begin(&ns->syncp); + stats->tx_bytes = ns->tx_bytes; + stats->tx_packets = ns->tx_packets; +- } while (u64_stats_fetch_retry_irq(&ns->syncp, start)); ++ } while (u64_stats_fetch_retry(&ns->syncp, start)); + } + + static int +diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c +index 293eaf6b3ec9..eccf9df0c88c 100644 +--- a/drivers/net/team/team.c ++++ b/drivers/net/team/team.c +@@ -1868,13 +1868,13 @@ team_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) + for_each_possible_cpu(i) { + p = per_cpu_ptr(team->pcpu_stats, i); + do { +- start = u64_stats_fetch_begin_irq(&p->syncp); ++ start = u64_stats_fetch_begin(&p->syncp); + rx_packets = u64_stats_read(&p->rx_packets); + rx_bytes = u64_stats_read(&p->rx_bytes); + rx_multicast = u64_stats_read(&p->rx_multicast); + tx_packets = u64_stats_read(&p->tx_packets); + tx_bytes = u64_stats_read(&p->tx_bytes); +- } while (u64_stats_fetch_retry_irq(&p->syncp, start)); ++ } while (u64_stats_fetch_retry(&p->syncp, start)); + + stats->rx_packets += rx_packets; + stats->rx_bytes += rx_bytes; +diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c +index b095a4b4957b..18d99fda997c 100644 +--- a/drivers/net/team/team_mode_loadbalance.c ++++ b/drivers/net/team/team_mode_loadbalance.c +@@ -466,9 +466,9 @@ static void __lb_one_cpu_stats_add(struct lb_stats *acc_stats, + struct lb_stats tmp; + + do { +- start = u64_stats_fetch_begin_irq(syncp); ++ start = u64_stats_fetch_begin(syncp); + tmp.tx_bytes = cpu_stats->tx_bytes; +- } while (u64_stats_fetch_retry_irq(syncp, start)); ++ } while (u64_stats_fetch_retry(syncp, start)); + acc_stats->tx_bytes += tmp.tx_bytes; + } + +diff --git a/drivers/net/veth.c b/drivers/net/veth.c +index 36c5a41f84e4..605f511a886c 100644 +--- a/drivers/net/veth.c ++++ b/drivers/net/veth.c +@@ -182,12 +182,12 @@ static void veth_get_ethtool_stats(struct net_device *dev, + size_t offset; + + do { +- start = u64_stats_fetch_begin_irq(&rq_stats->syncp); ++ start = u64_stats_fetch_begin(&rq_stats->syncp); + for (j = 0; j < VETH_RQ_STATS_LEN; j++) { + offset = veth_rq_stats_desc[j].offset; + data[idx + j] = *(u64 *)(stats_base + offset); + } +- } while (u64_stats_fetch_retry_irq(&rq_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&rq_stats->syncp, start)); + idx += VETH_RQ_STATS_LEN; + } + +@@ -203,12 +203,12 @@ static void veth_get_ethtool_stats(struct net_device *dev, + + tx_idx += (i % dev->real_num_tx_queues) * VETH_TQ_STATS_LEN; + do { +- start = u64_stats_fetch_begin_irq(&rq_stats->syncp); ++ start = u64_stats_fetch_begin(&rq_stats->syncp); + for (j = 0; j < VETH_TQ_STATS_LEN; j++) { + offset = veth_tq_stats_desc[j].offset; + data[tx_idx + j] += *(u64 *)(base + offset); + } +- } while (u64_stats_fetch_retry_irq(&rq_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&rq_stats->syncp, start)); + } + } + +@@ -381,13 +381,13 @@ static void veth_stats_rx(struct veth_stats *result, struct net_device *dev) + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&stats->syncp); ++ start = u64_stats_fetch_begin(&stats->syncp); + peer_tq_xdp_xmit_err = stats->vs.peer_tq_xdp_xmit_err; + xdp_tx_err = stats->vs.xdp_tx_err; + packets = stats->vs.xdp_packets; + bytes = stats->vs.xdp_bytes; + drops = stats->vs.rx_drops; +- } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&stats->syncp, start)); + result->peer_tq_xdp_xmit_err += peer_tq_xdp_xmit_err; + result->xdp_tx_err += xdp_tx_err; + result->xdp_packets += packets; +diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c +index 21d3461fb5d1..666622ae4b9d 100644 +--- a/drivers/net/virtio_net.c ++++ b/drivers/net/virtio_net.c +@@ -2107,18 +2107,18 @@ static void virtnet_stats(struct net_device *dev, + struct send_queue *sq = &vi->sq[i]; + + do { +- start = u64_stats_fetch_begin_irq(&sq->stats.syncp); ++ start = u64_stats_fetch_begin(&sq->stats.syncp); + tpackets = sq->stats.packets; + tbytes = sq->stats.bytes; + terrors = sq->stats.tx_timeouts; +- } while (u64_stats_fetch_retry_irq(&sq->stats.syncp, start)); ++ } while (u64_stats_fetch_retry(&sq->stats.syncp, start)); + + do { +- start = u64_stats_fetch_begin_irq(&rq->stats.syncp); ++ start = u64_stats_fetch_begin(&rq->stats.syncp); + rpackets = rq->stats.packets; + rbytes = rq->stats.bytes; + rdrops = rq->stats.drops; +- } while (u64_stats_fetch_retry_irq(&rq->stats.syncp, start)); ++ } while (u64_stats_fetch_retry(&rq->stats.syncp, start)); + + tot->rx_packets += rpackets; + tot->tx_packets += tpackets; +@@ -2726,12 +2726,12 @@ static void virtnet_get_ethtool_stats(struct net_device *dev, + + stats_base = (u8 *)&rq->stats; + do { +- start = u64_stats_fetch_begin_irq(&rq->stats.syncp); ++ start = u64_stats_fetch_begin(&rq->stats.syncp); + for (j = 0; j < VIRTNET_RQ_STATS_LEN; j++) { + offset = virtnet_rq_stats_desc[j].offset; + data[idx + j] = *(u64 *)(stats_base + offset); + } +- } while (u64_stats_fetch_retry_irq(&rq->stats.syncp, start)); ++ } while (u64_stats_fetch_retry(&rq->stats.syncp, start)); + idx += VIRTNET_RQ_STATS_LEN; + } + +@@ -2740,12 +2740,12 @@ static void virtnet_get_ethtool_stats(struct net_device *dev, + + stats_base = (u8 *)&sq->stats; + do { +- start = u64_stats_fetch_begin_irq(&sq->stats.syncp); ++ start = u64_stats_fetch_begin(&sq->stats.syncp); + for (j = 0; j < VIRTNET_SQ_STATS_LEN; j++) { + offset = virtnet_sq_stats_desc[j].offset; + data[idx + j] = *(u64 *)(stats_base + offset); + } +- } while (u64_stats_fetch_retry_irq(&sq->stats.syncp, start)); ++ } while (u64_stats_fetch_retry(&sq->stats.syncp, start)); + idx += VIRTNET_SQ_STATS_LEN; + } + } +diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c +index 208df4d41939..6043e63b42f9 100644 +--- a/drivers/net/vrf.c ++++ b/drivers/net/vrf.c +@@ -159,13 +159,13 @@ static void vrf_get_stats64(struct net_device *dev, + + dstats = per_cpu_ptr(dev->dstats, i); + do { +- start = u64_stats_fetch_begin_irq(&dstats->syncp); ++ start = u64_stats_fetch_begin(&dstats->syncp); + tbytes = dstats->tx_bytes; + tpkts = dstats->tx_pkts; + tdrops = dstats->tx_drps; + rbytes = dstats->rx_bytes; + rpkts = dstats->rx_pkts; +- } while (u64_stats_fetch_retry_irq(&dstats->syncp, start)); ++ } while (u64_stats_fetch_retry(&dstats->syncp, start)); + stats->tx_bytes += tbytes; + stats->tx_packets += tpkts; + stats->tx_dropped += tdrops; +diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c +index c5cf55030158..c3ff30ab782e 100644 +--- a/drivers/net/vxlan/vxlan_vnifilter.c ++++ b/drivers/net/vxlan/vxlan_vnifilter.c +@@ -129,9 +129,9 @@ static void vxlan_vnifilter_stats_get(const struct vxlan_vni_node *vninode, + + pstats = per_cpu_ptr(vninode->stats, i); + do { +- start = u64_stats_fetch_begin_irq(&pstats->syncp); ++ start = u64_stats_fetch_begin(&pstats->syncp); + memcpy(&temp, &pstats->stats, sizeof(temp)); +- } while (u64_stats_fetch_retry_irq(&pstats->syncp, start)); ++ } while (u64_stats_fetch_retry(&pstats->syncp, start)); + + dest->rx_packets += temp.rx_packets; + dest->rx_bytes += temp.rx_bytes; +diff --git a/drivers/net/wwan/mhi_wwan_mbim.c b/drivers/net/wwan/mhi_wwan_mbim.c +index ef70bb7c88ad..3f72ae943b29 100644 +--- a/drivers/net/wwan/mhi_wwan_mbim.c ++++ b/drivers/net/wwan/mhi_wwan_mbim.c +@@ -456,19 +456,19 @@ static void mhi_mbim_ndo_get_stats64(struct net_device *ndev, + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&link->rx_syncp); ++ start = u64_stats_fetch_begin(&link->rx_syncp); + stats->rx_packets = u64_stats_read(&link->rx_packets); + stats->rx_bytes = u64_stats_read(&link->rx_bytes); + stats->rx_errors = u64_stats_read(&link->rx_errors); +- } while (u64_stats_fetch_retry_irq(&link->rx_syncp, start)); ++ } while (u64_stats_fetch_retry(&link->rx_syncp, start)); + + do { +- start = u64_stats_fetch_begin_irq(&link->tx_syncp); ++ start = u64_stats_fetch_begin(&link->tx_syncp); + stats->tx_packets = u64_stats_read(&link->tx_packets); + stats->tx_bytes = u64_stats_read(&link->tx_bytes); + stats->tx_errors = u64_stats_read(&link->tx_errors); + stats->tx_dropped = u64_stats_read(&link->tx_dropped); +- } while (u64_stats_fetch_retry_irq(&link->tx_syncp, start)); ++ } while (u64_stats_fetch_retry(&link->tx_syncp, start)); + } + + static void mhi_mbim_ul_callback(struct mhi_device *mhi_dev, +diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c +index dc404e05970c..14aec417fa06 100644 +--- a/drivers/net/xen-netfront.c ++++ b/drivers/net/xen-netfront.c +@@ -1392,16 +1392,16 @@ static void xennet_get_stats64(struct net_device *dev, + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&tx_stats->syncp); ++ start = u64_stats_fetch_begin(&tx_stats->syncp); + tx_packets = tx_stats->packets; + tx_bytes = tx_stats->bytes; +- } while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&tx_stats->syncp, start)); + + do { +- start = u64_stats_fetch_begin_irq(&rx_stats->syncp); ++ start = u64_stats_fetch_begin(&rx_stats->syncp); + rx_packets = rx_stats->packets; + rx_bytes = rx_stats->bytes; +- } while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&rx_stats->syncp, start)); + + tot->rx_packets += rx_packets; + tot->tx_packets += tx_packets; +-- +2.43.0 + diff --git a/debian/patches-rt/0006-net-Remove-the-obsolte-u64_stats_fetch_-_irq-users-n.patch b/debian/patches-rt/0006-net-Remove-the-obsolte-u64_stats_fetch_-_irq-users-n.patch new file mode 100644 index 000000000..ff493ddaf --- /dev/null +++ b/debian/patches-rt/0006-net-Remove-the-obsolte-u64_stats_fetch_-_irq-users-n.patch @@ -0,0 +1,393 @@ +From a0c8ef7e6160582c71c0d8b1786d8e45dcc02132 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 25 Aug 2022 16:17:37 +0200 +Subject: [PATCH 06/62] net: Remove the obsolte u64_stats_fetch_*_irq() users + (net). +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Now that the 32bit UP oddity is gone and 32bit uses always a sequence +count, there is no need for the fetch_irq() variants anymore. + +Convert to the regular interface. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> +--- + net/8021q/vlan_dev.c | 4 ++-- + net/bridge/br_multicast.c | 4 ++-- + net/bridge/br_vlan.c | 4 ++-- + net/core/dev.c | 4 ++-- + net/core/drop_monitor.c | 8 ++++---- + net/core/gen_stats.c | 16 ++++++++-------- + net/devlink/leftover.c | 4 ++-- + net/dsa/slave.c | 4 ++-- + net/ipv4/af_inet.c | 4 ++-- + net/ipv6/seg6_local.c | 4 ++-- + net/mac80211/sta_info.c | 8 ++++---- + net/mpls/af_mpls.c | 4 ++-- + net/netfilter/ipvs/ip_vs_ctl.c | 4 ++-- + net/netfilter/nf_tables_api.c | 4 ++-- + net/openvswitch/datapath.c | 4 ++-- + net/openvswitch/flow_table.c | 9 ++++----- + 16 files changed, 44 insertions(+), 45 deletions(-) + +diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c +index d3e511e1eba8..0fa52bcc296b 100644 +--- a/net/8021q/vlan_dev.c ++++ b/net/8021q/vlan_dev.c +@@ -712,13 +712,13 @@ static void vlan_dev_get_stats64(struct net_device *dev, + + p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i); + do { +- start = u64_stats_fetch_begin_irq(&p->syncp); ++ start = u64_stats_fetch_begin(&p->syncp); + rxpackets = u64_stats_read(&p->rx_packets); + rxbytes = u64_stats_read(&p->rx_bytes); + rxmulticast = u64_stats_read(&p->rx_multicast); + txpackets = u64_stats_read(&p->tx_packets); + txbytes = u64_stats_read(&p->tx_bytes); +- } while (u64_stats_fetch_retry_irq(&p->syncp, start)); ++ } while (u64_stats_fetch_retry(&p->syncp, start)); + + stats->rx_packets += rxpackets; + stats->rx_bytes += rxbytes; +diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c +index db4f2641d1cd..7e2a9fb5786c 100644 +--- a/net/bridge/br_multicast.c ++++ b/net/bridge/br_multicast.c +@@ -4899,9 +4899,9 @@ void br_multicast_get_stats(const struct net_bridge *br, + unsigned int start; + + do { +- start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); ++ start = u64_stats_fetch_begin(&cpu_stats->syncp); + memcpy(&temp, &cpu_stats->mstats, sizeof(temp)); +- } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); + + mcast_stats_add_dir(tdst.igmp_v1queries, temp.igmp_v1queries); + mcast_stats_add_dir(tdst.igmp_v2queries, temp.igmp_v2queries); +diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c +index 9ffd40b8270c..bc75fa1e4666 100644 +--- a/net/bridge/br_vlan.c ++++ b/net/bridge/br_vlan.c +@@ -1389,12 +1389,12 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v, + + cpu_stats = per_cpu_ptr(v->stats, i); + do { +- start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); ++ start = u64_stats_fetch_begin(&cpu_stats->syncp); + rxpackets = u64_stats_read(&cpu_stats->rx_packets); + rxbytes = u64_stats_read(&cpu_stats->rx_bytes); + txbytes = u64_stats_read(&cpu_stats->tx_bytes); + txpackets = u64_stats_read(&cpu_stats->tx_packets); +- } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); + + u64_stats_add(&stats->rx_packets, rxpackets); + u64_stats_add(&stats->rx_bytes, rxbytes); +diff --git a/net/core/dev.c b/net/core/dev.c +index 0d5aa820fd83..070039f9296c 100644 +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -10505,12 +10505,12 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, + + stats = per_cpu_ptr(netstats, cpu); + do { +- start = u64_stats_fetch_begin_irq(&stats->syncp); ++ start = u64_stats_fetch_begin(&stats->syncp); + rx_packets = u64_stats_read(&stats->rx_packets); + rx_bytes = u64_stats_read(&stats->rx_bytes); + tx_packets = u64_stats_read(&stats->tx_packets); + tx_bytes = u64_stats_read(&stats->tx_bytes); +- } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&stats->syncp, start)); + + s->rx_packets += rx_packets; + s->rx_bytes += rx_bytes; +diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c +index 8e0a90b45df2..4d5e8b317c47 100644 +--- a/net/core/drop_monitor.c ++++ b/net/core/drop_monitor.c +@@ -1432,9 +1432,9 @@ static void net_dm_stats_read(struct net_dm_stats *stats) + u64 dropped; + + do { +- start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); ++ start = u64_stats_fetch_begin(&cpu_stats->syncp); + dropped = u64_stats_read(&cpu_stats->dropped); +- } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); + + u64_stats_add(&stats->dropped, dropped); + } +@@ -1476,9 +1476,9 @@ static void net_dm_hw_stats_read(struct net_dm_stats *stats) + u64 dropped; + + do { +- start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); ++ start = u64_stats_fetch_begin(&cpu_stats->syncp); + dropped = u64_stats_read(&cpu_stats->dropped); +- } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); + + u64_stats_add(&stats->dropped, dropped); + } +diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c +index c8d137ef5980..b71ccaec0991 100644 +--- a/net/core/gen_stats.c ++++ b/net/core/gen_stats.c +@@ -135,10 +135,10 @@ static void gnet_stats_add_basic_cpu(struct gnet_stats_basic_sync *bstats, + u64 bytes, packets; + + do { +- start = u64_stats_fetch_begin_irq(&bcpu->syncp); ++ start = u64_stats_fetch_begin(&bcpu->syncp); + bytes = u64_stats_read(&bcpu->bytes); + packets = u64_stats_read(&bcpu->packets); +- } while (u64_stats_fetch_retry_irq(&bcpu->syncp, start)); ++ } while (u64_stats_fetch_retry(&bcpu->syncp, start)); + + t_bytes += bytes; + t_packets += packets; +@@ -162,10 +162,10 @@ void gnet_stats_add_basic(struct gnet_stats_basic_sync *bstats, + } + do { + if (running) +- start = u64_stats_fetch_begin_irq(&b->syncp); ++ start = u64_stats_fetch_begin(&b->syncp); + bytes = u64_stats_read(&b->bytes); + packets = u64_stats_read(&b->packets); +- } while (running && u64_stats_fetch_retry_irq(&b->syncp, start)); ++ } while (running && u64_stats_fetch_retry(&b->syncp, start)); + + _bstats_update(bstats, bytes, packets); + } +@@ -187,10 +187,10 @@ static void gnet_stats_read_basic(u64 *ret_bytes, u64 *ret_packets, + u64 bytes, packets; + + do { +- start = u64_stats_fetch_begin_irq(&bcpu->syncp); ++ start = u64_stats_fetch_begin(&bcpu->syncp); + bytes = u64_stats_read(&bcpu->bytes); + packets = u64_stats_read(&bcpu->packets); +- } while (u64_stats_fetch_retry_irq(&bcpu->syncp, start)); ++ } while (u64_stats_fetch_retry(&bcpu->syncp, start)); + + t_bytes += bytes; + t_packets += packets; +@@ -201,10 +201,10 @@ static void gnet_stats_read_basic(u64 *ret_bytes, u64 *ret_packets, + } + do { + if (running) +- start = u64_stats_fetch_begin_irq(&b->syncp); ++ start = u64_stats_fetch_begin(&b->syncp); + *ret_bytes = u64_stats_read(&b->bytes); + *ret_packets = u64_stats_read(&b->packets); +- } while (running && u64_stats_fetch_retry_irq(&b->syncp, start)); ++ } while (running && u64_stats_fetch_retry(&b->syncp, start)); + } + + static int +diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c +index 032c7af065cd..94e8cc3de330 100644 +--- a/net/devlink/leftover.c ++++ b/net/devlink/leftover.c +@@ -8307,10 +8307,10 @@ static void devlink_trap_stats_read(struct devlink_stats __percpu *trap_stats, + + cpu_stats = per_cpu_ptr(trap_stats, i); + do { +- start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); ++ start = u64_stats_fetch_begin(&cpu_stats->syncp); + rx_packets = u64_stats_read(&cpu_stats->rx_packets); + rx_bytes = u64_stats_read(&cpu_stats->rx_bytes); +- } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); + + u64_stats_add(&stats->rx_packets, rx_packets); + u64_stats_add(&stats->rx_bytes, rx_bytes); +diff --git a/net/dsa/slave.c b/net/dsa/slave.c +index 5fe075bf479e..28ee63ec1d1d 100644 +--- a/net/dsa/slave.c ++++ b/net/dsa/slave.c +@@ -976,12 +976,12 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev, + + s = per_cpu_ptr(dev->tstats, i); + do { +- start = u64_stats_fetch_begin_irq(&s->syncp); ++ start = u64_stats_fetch_begin(&s->syncp); + tx_packets = u64_stats_read(&s->tx_packets); + tx_bytes = u64_stats_read(&s->tx_bytes); + rx_packets = u64_stats_read(&s->rx_packets); + rx_bytes = u64_stats_read(&s->rx_bytes); +- } while (u64_stats_fetch_retry_irq(&s->syncp, start)); ++ } while (u64_stats_fetch_retry(&s->syncp, start)); + data[0] += tx_packets; + data[1] += tx_bytes; + data[2] += rx_packets; +diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c +index 5d379df90c82..312c730b725f 100644 +--- a/net/ipv4/af_inet.c ++++ b/net/ipv4/af_inet.c +@@ -1708,9 +1708,9 @@ u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offt, + bhptr = per_cpu_ptr(mib, cpu); + syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); + do { +- start = u64_stats_fetch_begin_irq(syncp); ++ start = u64_stats_fetch_begin(syncp); + v = *(((u64 *)bhptr) + offt); +- } while (u64_stats_fetch_retry_irq(syncp, start)); ++ } while (u64_stats_fetch_retry(syncp, start)); + + return v; + } +diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c +index 8370726ae7bf..487f8e98deaa 100644 +--- a/net/ipv6/seg6_local.c ++++ b/net/ipv6/seg6_local.c +@@ -1644,13 +1644,13 @@ static int put_nla_counters(struct sk_buff *skb, struct seg6_local_lwt *slwt) + + pcounters = per_cpu_ptr(slwt->pcpu_counters, i); + do { +- start = u64_stats_fetch_begin_irq(&pcounters->syncp); ++ start = u64_stats_fetch_begin(&pcounters->syncp); + + packets = u64_stats_read(&pcounters->packets); + bytes = u64_stats_read(&pcounters->bytes); + errors = u64_stats_read(&pcounters->errors); + +- } while (u64_stats_fetch_retry_irq(&pcounters->syncp, start)); ++ } while (u64_stats_fetch_retry(&pcounters->syncp, start)); + + counters.packets += packets; + counters.bytes += bytes; +diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c +index 49b71453dec3..c462e20ccc8d 100644 +--- a/net/mac80211/sta_info.c ++++ b/net/mac80211/sta_info.c +@@ -2397,9 +2397,9 @@ static inline u64 sta_get_tidstats_msdu(struct ieee80211_sta_rx_stats *rxstats, + u64 value; + + do { +- start = u64_stats_fetch_begin_irq(&rxstats->syncp); ++ start = u64_stats_fetch_begin(&rxstats->syncp); + value = rxstats->msdu[tid]; +- } while (u64_stats_fetch_retry_irq(&rxstats->syncp, start)); ++ } while (u64_stats_fetch_retry(&rxstats->syncp, start)); + + return value; + } +@@ -2465,9 +2465,9 @@ static inline u64 sta_get_stats_bytes(struct ieee80211_sta_rx_stats *rxstats) + u64 value; + + do { +- start = u64_stats_fetch_begin_irq(&rxstats->syncp); ++ start = u64_stats_fetch_begin(&rxstats->syncp); + value = rxstats->bytes; +- } while (u64_stats_fetch_retry_irq(&rxstats->syncp, start)); ++ } while (u64_stats_fetch_retry(&rxstats->syncp, start)); + + return value; + } +diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c +index f1f43894efb8..dc5165d3eec4 100644 +--- a/net/mpls/af_mpls.c ++++ b/net/mpls/af_mpls.c +@@ -1079,9 +1079,9 @@ static void mpls_get_stats(struct mpls_dev *mdev, + + p = per_cpu_ptr(mdev->stats, i); + do { +- start = u64_stats_fetch_begin_irq(&p->syncp); ++ start = u64_stats_fetch_begin(&p->syncp); + local = p->stats; +- } while (u64_stats_fetch_retry_irq(&p->syncp, start)); ++ } while (u64_stats_fetch_retry(&p->syncp, start)); + + stats->rx_packets += local.rx_packets; + stats->rx_bytes += local.rx_bytes; +diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c +index 17a1b731a76b..2be696513629 100644 +--- a/net/netfilter/ipvs/ip_vs_ctl.c ++++ b/net/netfilter/ipvs/ip_vs_ctl.c +@@ -2299,13 +2299,13 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) + u64 conns, inpkts, outpkts, inbytes, outbytes; + + do { +- start = u64_stats_fetch_begin_irq(&u->syncp); ++ start = u64_stats_fetch_begin(&u->syncp); + conns = u64_stats_read(&u->cnt.conns); + inpkts = u64_stats_read(&u->cnt.inpkts); + outpkts = u64_stats_read(&u->cnt.outpkts); + inbytes = u64_stats_read(&u->cnt.inbytes); + outbytes = u64_stats_read(&u->cnt.outbytes); +- } while (u64_stats_fetch_retry_irq(&u->syncp, start)); ++ } while (u64_stats_fetch_retry(&u->syncp, start)); + + seq_printf(seq, "%3X %8LX %8LX %8LX %16LX %16LX\n", + i, (u64)conns, (u64)inpkts, +diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c +index 05fa5141af51..ab1888991ae5 100644 +--- a/net/netfilter/nf_tables_api.c ++++ b/net/netfilter/nf_tables_api.c +@@ -1692,10 +1692,10 @@ static int nft_dump_stats(struct sk_buff *skb, struct nft_stats __percpu *stats) + for_each_possible_cpu(cpu) { + cpu_stats = per_cpu_ptr(stats, cpu); + do { +- seq = u64_stats_fetch_begin_irq(&cpu_stats->syncp); ++ seq = u64_stats_fetch_begin(&cpu_stats->syncp); + pkts = cpu_stats->pkts; + bytes = cpu_stats->bytes; +- } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, seq)); ++ } while (u64_stats_fetch_retry(&cpu_stats->syncp, seq)); + total.pkts += pkts; + total.bytes += bytes; + } +diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c +index 3c7b24535409..0953f531f984 100644 +--- a/net/openvswitch/datapath.c ++++ b/net/openvswitch/datapath.c +@@ -716,9 +716,9 @@ static void get_dp_stats(const struct datapath *dp, struct ovs_dp_stats *stats, + percpu_stats = per_cpu_ptr(dp->stats_percpu, i); + + do { +- start = u64_stats_fetch_begin_irq(&percpu_stats->syncp); ++ start = u64_stats_fetch_begin(&percpu_stats->syncp); + local_stats = *percpu_stats; +- } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&percpu_stats->syncp, start)); + + stats->n_hit += local_stats.n_hit; + stats->n_missed += local_stats.n_missed; +diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c +index d4a2db0b2299..0a0e4c283f02 100644 +--- a/net/openvswitch/flow_table.c ++++ b/net/openvswitch/flow_table.c +@@ -205,9 +205,9 @@ static void tbl_mask_array_reset_counters(struct mask_array *ma) + + stats = per_cpu_ptr(ma->masks_usage_stats, cpu); + do { +- start = u64_stats_fetch_begin_irq(&stats->syncp); ++ start = u64_stats_fetch_begin(&stats->syncp); + counter = stats->usage_cntrs[i]; +- } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&stats->syncp, start)); + + ma->masks_usage_zero_cntr[i] += counter; + } +@@ -1136,10 +1136,9 @@ void ovs_flow_masks_rebalance(struct flow_table *table) + + stats = per_cpu_ptr(ma->masks_usage_stats, cpu); + do { +- start = u64_stats_fetch_begin_irq(&stats->syncp); ++ start = u64_stats_fetch_begin(&stats->syncp); + counter = stats->usage_cntrs[i]; +- } while (u64_stats_fetch_retry_irq(&stats->syncp, +- start)); ++ } while (u64_stats_fetch_retry(&stats->syncp, start)); + + masks_and_count[i].counter += counter; + } +-- +2.43.0 + diff --git a/debian/patches-rt/0007-bpf-Remove-the-obsolte-u64_stats_fetch_-_irq-users.patch b/debian/patches-rt/0007-bpf-Remove-the-obsolte-u64_stats_fetch_-_irq-users.patch new file mode 100644 index 000000000..6b725886f --- /dev/null +++ b/debian/patches-rt/0007-bpf-Remove-the-obsolte-u64_stats_fetch_-_irq-users.patch @@ -0,0 +1,51 @@ +From b8cff7d0320e3b39f098d9562373e1c16c54c46c Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 25 Aug 2022 16:17:57 +0200 +Subject: [PATCH 07/62] bpf: Remove the obsolte u64_stats_fetch_*_irq() users. +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Now that the 32bit UP oddity is gone and 32bit uses always a sequence +count, there is no need for the fetch_irq() variants anymore. + +Convert to the regular interface. + +Cc: Alexei Starovoitov <ast@kernel.org> +Cc: Andrii Nakryiko <andrii@kernel.org> +Cc: Daniel Borkmann <daniel@iogearbox.net> +Cc: Hao Luo <haoluo@google.com> +Cc: Jiri Olsa <jolsa@kernel.org> +Cc: John Fastabend <john.fastabend@gmail.com> +Cc: KP Singh <kpsingh@kernel.org> +Cc: Martin KaFai Lau <martin.lau@linux.dev> +Cc: Song Liu <song@kernel.org> +Cc: Stanislav Fomichev <sdf@google.com> +Cc: Yonghong Song <yhs@fb.com> +Cc: bpf@vger.kernel.org +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> +--- + kernel/bpf/syscall.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c +index 0c8b7733573e..c0915e2424f1 100644 +--- a/kernel/bpf/syscall.c ++++ b/kernel/bpf/syscall.c +@@ -2115,11 +2115,11 @@ static void bpf_prog_get_stats(const struct bpf_prog *prog, + + st = per_cpu_ptr(prog->stats, cpu); + do { +- start = u64_stats_fetch_begin_irq(&st->syncp); ++ start = u64_stats_fetch_begin(&st->syncp); + tnsecs = u64_stats_read(&st->nsecs); + tcnt = u64_stats_read(&st->cnt); + tmisses = u64_stats_read(&st->misses); +- } while (u64_stats_fetch_retry_irq(&st->syncp, start)); ++ } while (u64_stats_fetch_retry(&st->syncp, start)); + nsecs += tnsecs; + cnt += tcnt; + misses += tmisses; +-- +2.43.0 + diff --git a/debian/patches-rt/0008-u64_stat-Remove-the-obsolete-fetch_irq-variants.patch b/debian/patches-rt/0008-u64_stat-Remove-the-obsolete-fetch_irq-variants.patch new file mode 100644 index 000000000..176dbf1e5 --- /dev/null +++ b/debian/patches-rt/0008-u64_stat-Remove-the-obsolete-fetch_irq-variants.patch @@ -0,0 +1,42 @@ +From b908a7b47d95003c498f2f575285f528148602d6 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 25 Aug 2022 16:43:46 +0200 +Subject: [PATCH 08/62] u64_stat: Remove the obsolete fetch_irq() variants. +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Now that the 32bit UP oddity is gone and 32bit uses always a sequence +count, there is no need for the fetch_irq() variants anymore. + +Delete the obsolete interfaces. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> +--- + include/linux/u64_stats_sync.h | 12 ------------ + 1 file changed, 12 deletions(-) + +diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h +index 46040d66334a..ffe48e69b3f3 100644 +--- a/include/linux/u64_stats_sync.h ++++ b/include/linux/u64_stats_sync.h +@@ -213,16 +213,4 @@ static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, + return __u64_stats_fetch_retry(syncp, start); + } + +-/* Obsolete interfaces */ +-static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync *syncp) +-{ +- return u64_stats_fetch_begin(syncp); +-} +- +-static inline bool u64_stats_fetch_retry_irq(const struct u64_stats_sync *syncp, +- unsigned int start) +-{ +- return u64_stats_fetch_retry(syncp, start); +-} +- + #endif /* _LINUX_U64_STATS_SYNC_H */ +-- +2.43.0 + diff --git a/debian/patches-rt/0009-net-Avoid-the-IPI-to-free-the.patch b/debian/patches-rt/0009-net-Avoid-the-IPI-to-free-the.patch new file mode 100644 index 000000000..1f6687796 --- /dev/null +++ b/debian/patches-rt/0009-net-Avoid-the-IPI-to-free-the.patch @@ -0,0 +1,125 @@ +From c910f301d71266e18f63407ec6c65d19ae90e779 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 15 Aug 2022 17:29:50 +0200 +Subject: [PATCH 09/62] net: Avoid the IPI to free the +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +skb_attempt_defer_free() collects a skbs, which was allocated on a +remote CPU, on a per-CPU list. These skbs are either freed on that +remote CPU once the CPU enters NET_RX or an remote IPI function is +invoked in to raise the NET_RX softirq if a threshold of pending skb has +been exceeded. +This remote IPI can cause the wakeup of ksoftirqd on PREEMPT_RT if the +remote CPU idle was idle. This is undesired because once the ksoftirqd +is running it will acquire all pending softirqs and they will not be +executed as part of the threaded interrupt until ksoftird goes idle +again. + +To void all this, schedule the deferred clean up from a worker. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/netdevice.h | 4 ++++ + net/core/dev.c | 37 ++++++++++++++++++++++++++++--------- + net/core/skbuff.c | 7 ++++++- + 3 files changed, 38 insertions(+), 10 deletions(-) + +diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h +index 0373e0935990..55d698367883 100644 +--- a/include/linux/netdevice.h ++++ b/include/linux/netdevice.h +@@ -3169,7 +3169,11 @@ struct softnet_data { + int defer_count; + int defer_ipi_scheduled; + struct sk_buff *defer_list; ++#ifndef CONFIG_PREEMPT_RT + call_single_data_t defer_csd; ++#else ++ struct work_struct defer_work; ++#endif + }; + + static inline void input_queue_head_incr(struct softnet_data *sd) +diff --git a/net/core/dev.c b/net/core/dev.c +index 070039f9296c..a3caa23be3cf 100644 +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -4618,15 +4618,6 @@ static void rps_trigger_softirq(void *data) + + #endif /* CONFIG_RPS */ + +-/* Called from hardirq (IPI) context */ +-static void trigger_rx_softirq(void *data) +-{ +- struct softnet_data *sd = data; +- +- __raise_softirq_irqoff(NET_RX_SOFTIRQ); +- smp_store_release(&sd->defer_ipi_scheduled, 0); +-} +- + /* + * Check if this softnet_data structure is another cpu one + * If yes, queue it to our IPI list and return 1 +@@ -6684,6 +6675,30 @@ static void skb_defer_free_flush(struct softnet_data *sd) + } + } + ++#ifndef CONFIG_PREEMPT_RT ++/* Called from hardirq (IPI) context */ ++static void trigger_rx_softirq(void *data) ++{ ++ struct softnet_data *sd = data; ++ ++ __raise_softirq_irqoff(NET_RX_SOFTIRQ); ++ smp_store_release(&sd->defer_ipi_scheduled, 0); ++} ++ ++#else ++ ++static void trigger_rx_softirq(struct work_struct *defer_work) ++{ ++ struct softnet_data *sd; ++ ++ sd = container_of(defer_work, struct softnet_data, defer_work); ++ smp_store_release(&sd->defer_ipi_scheduled, 0); ++ local_bh_disable(); ++ skb_defer_free_flush(sd); ++ local_bh_enable(); ++} ++#endif ++ + static __latent_entropy void net_rx_action(struct softirq_action *h) + { + struct softnet_data *sd = this_cpu_ptr(&softnet_data); +@@ -11435,7 +11450,11 @@ static int __init net_dev_init(void) + INIT_CSD(&sd->csd, rps_trigger_softirq, sd); + sd->cpu = i; + #endif ++#ifndef CONFIG_PREEMPT_RT + INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd); ++#else ++ INIT_WORK(&sd->defer_work, trigger_rx_softirq); ++#endif + spin_lock_init(&sd->defer_lock); + + init_gro_hash(&sd->backlog); +diff --git a/net/core/skbuff.c b/net/core/skbuff.c +index 73b1e0e53534..a457a3445469 100644 +--- a/net/core/skbuff.c ++++ b/net/core/skbuff.c +@@ -6680,6 +6680,11 @@ nodefer: __kfree_skb(skb); + /* Make sure to trigger NET_RX_SOFTIRQ on the remote CPU + * if we are unlucky enough (this seems very unlikely). + */ +- if (unlikely(kick) && !cmpxchg(&sd->defer_ipi_scheduled, 0, 1)) ++ if (unlikely(kick) && !cmpxchg(&sd->defer_ipi_scheduled, 0, 1)) { ++#ifndef CONFIG_PREEMPT_RT + smp_call_function_single_async(cpu, &sd->defer_csd); ++#else ++ schedule_work_on(cpu, &sd->defer_work); ++#endif ++ } + } +-- +2.43.0 + diff --git a/debian/patches-rt/0010-x86-Allow-to-enable-RT.patch b/debian/patches-rt/0010-x86-Allow-to-enable-RT.patch new file mode 100644 index 000000000..e7681047e --- /dev/null +++ b/debian/patches-rt/0010-x86-Allow-to-enable-RT.patch @@ -0,0 +1,29 @@ +From ce04e41eb149fcd93a71b63a605423d7f18ec8b4 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 7 Aug 2019 18:15:38 +0200 +Subject: [PATCH 10/62] x86: Allow to enable RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Allow to select RT. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/x86/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig +index 4c9bfc4be58d..f7f81e3012cc 100644 +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -27,6 +27,7 @@ config X86_64 + # Options that are inherently 64-bit kernel only: + select ARCH_HAS_GIGANTIC_PAGE + select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 ++ select ARCH_SUPPORTS_RT + select ARCH_USE_CMPXCHG_LOCKREF + select HAVE_ARCH_SOFT_DIRTY + select MODULES_USE_ELF_RELA +-- +2.43.0 + diff --git a/debian/patches-rt/0011-x86-Enable-RT-also-on-32bit.patch b/debian/patches-rt/0011-x86-Enable-RT-also-on-32bit.patch new file mode 100644 index 000000000..de093669b --- /dev/null +++ b/debian/patches-rt/0011-x86-Enable-RT-also-on-32bit.patch @@ -0,0 +1,35 @@ +From 28dbe0fc30a2d3e519fac1ffe18fe7427f1f49b3 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 7 Nov 2019 17:49:20 +0100 +Subject: [PATCH 11/62] x86: Enable RT also on 32bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/x86/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig +index f7f81e3012cc..c9bed9c69423 100644 +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -27,7 +27,6 @@ config X86_64 + # Options that are inherently 64-bit kernel only: + select ARCH_HAS_GIGANTIC_PAGE + select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 +- select ARCH_SUPPORTS_RT + select ARCH_USE_CMPXCHG_LOCKREF + select HAVE_ARCH_SOFT_DIRTY + select MODULES_USE_ELF_RELA +@@ -114,6 +113,7 @@ config X86 + select ARCH_USES_CFI_TRAPS if X86_64 && CFI_CLANG + select ARCH_SUPPORTS_LTO_CLANG + select ARCH_SUPPORTS_LTO_CLANG_THIN ++ select ARCH_SUPPORTS_RT + select ARCH_USE_BUILTIN_BSWAP + select ARCH_USE_MEMTEST + select ARCH_USE_QUEUED_RWLOCKS +-- +2.43.0 + diff --git a/debian/patches-rt/0012-softirq-Use-a-dedicated-thread-for-timer-wakeups.patch b/debian/patches-rt/0012-softirq-Use-a-dedicated-thread-for-timer-wakeups.patch new file mode 100644 index 000000000..720116187 --- /dev/null +++ b/debian/patches-rt/0012-softirq-Use-a-dedicated-thread-for-timer-wakeups.patch @@ -0,0 +1,234 @@ +From 454343a4f08e5de772024588aec2bd396177ee89 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 1 Dec 2021 17:41:09 +0100 +Subject: [PATCH 12/62] softirq: Use a dedicated thread for timer wakeups. +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +A timer/hrtimer softirq is raised in-IRQ context. With threaded +interrupts enabled or on PREEMPT_RT this leads to waking the ksoftirqd +for the processing of the softirq. +Once the ksoftirqd is marked as pending (or is running) it will collect +all raised softirqs. This in turn means that a softirq which would have +been processed at the end of the threaded interrupt, which runs at an +elevated priority, is now moved to ksoftirqd which runs at SCHED_OTHER +priority and competes with every regular task for CPU resources. +This introduces long delays on heavy loaded systems and is not desired +especially if the system is not overloaded by the softirqs. + +Split the TIMER_SOFTIRQ and HRTIMER_SOFTIRQ processing into a dedicated +timers thread and let it run at the lowest SCHED_FIFO priority. +RT tasks are are woken up from hardirq context so only timer_list timers +and hrtimers for "regular" tasks are processed here. The higher priority +ensures that wakeups are performed before scheduling SCHED_OTHER tasks. + +Using a dedicated variable to store the pending softirq bits values +ensure that the timer are not accidentally picked up by ksoftirqd and +other threaded interrupts. +It shouldn't be picked up by ksoftirqd since it runs at lower priority. +However if the timer bits are ORed while a threaded interrupt is +running, then the timer softirq would be performed at higher priority. +The new timer thread will block on the softirq lock before it starts +softirq work. This "race window" isn't closed because while timer thread +is performing the softirq it can get PI-boosted via the softirq lock by +a random force-threaded thread. +The timer thread can pick up pending softirqs from ksoftirqd but only +if the softirq load is high. It is not be desired that the picked up +softirqs are processed at SCHED_FIFO priority under high softirq load +but this can already happen by a PI-boost by a force-threaded interrupt. + +Reported-by: kernel test robot <lkp@intel.com> [ static timer_threads ] +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/interrupt.h | 16 +++++++ + kernel/softirq.c | 92 +++++++++++++++++++++++++++++++++++++-- + kernel/time/hrtimer.c | 4 +- + kernel/time/timer.c | 2 +- + 4 files changed, 108 insertions(+), 6 deletions(-) + +diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h +index 4a1dc88ddbff..0efba74a835c 100644 +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -609,6 +609,22 @@ extern void __raise_softirq_irqoff(unsigned int nr); + extern void raise_softirq_irqoff(unsigned int nr); + extern void raise_softirq(unsigned int nr); + ++#ifdef CONFIG_PREEMPT_RT ++extern void raise_timer_softirq(void); ++extern void raise_hrtimer_softirq(void); ++ ++#else ++static inline void raise_timer_softirq(void) ++{ ++ raise_softirq(TIMER_SOFTIRQ); ++} ++ ++static inline void raise_hrtimer_softirq(void) ++{ ++ raise_softirq_irqoff(HRTIMER_SOFTIRQ); ++} ++#endif ++ + DECLARE_PER_CPU(struct task_struct *, ksoftirqd); + + static inline struct task_struct *this_cpu_ksoftirqd(void) +diff --git a/kernel/softirq.c b/kernel/softirq.c +index c8a6913c067d..ed6d7c41aa17 100644 +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -637,6 +637,29 @@ static inline void tick_irq_exit(void) + #endif + } + ++#ifdef CONFIG_PREEMPT_RT ++static DEFINE_PER_CPU(struct task_struct *, timersd); ++static DEFINE_PER_CPU(unsigned long, pending_timer_softirq); ++ ++static unsigned int local_pending_timers(void) ++{ ++ return __this_cpu_read(pending_timer_softirq); ++} ++ ++static void wake_timersd(void) ++{ ++ struct task_struct *tsk = __this_cpu_read(timersd); ++ ++ if (tsk) ++ wake_up_process(tsk); ++} ++ ++#else ++ ++static inline void wake_timersd(void) { } ++ ++#endif ++ + static inline void __irq_exit_rcu(void) + { + #ifndef __ARCH_IRQ_EXIT_IRQS_DISABLED +@@ -646,8 +669,13 @@ static inline void __irq_exit_rcu(void) + #endif + account_hardirq_exit(current); + preempt_count_sub(HARDIRQ_OFFSET); +- if (!in_interrupt() && local_softirq_pending()) +- invoke_softirq(); ++ if (!in_interrupt()) { ++ if (local_softirq_pending()) ++ invoke_softirq(); ++ ++ if (IS_ENABLED(CONFIG_PREEMPT_RT) && local_pending_timers()) ++ wake_timersd(); ++ } + + tick_irq_exit(); + } +@@ -976,12 +1004,70 @@ static struct smp_hotplug_thread softirq_threads = { + .thread_comm = "ksoftirqd/%u", + }; + ++#ifdef CONFIG_PREEMPT_RT ++static void timersd_setup(unsigned int cpu) ++{ ++ sched_set_fifo_low(current); ++} ++ ++static int timersd_should_run(unsigned int cpu) ++{ ++ return local_pending_timers(); ++} ++ ++static void run_timersd(unsigned int cpu) ++{ ++ unsigned int timer_si; ++ ++ ksoftirqd_run_begin(); ++ ++ timer_si = local_pending_timers(); ++ __this_cpu_write(pending_timer_softirq, 0); ++ or_softirq_pending(timer_si); ++ ++ __do_softirq(); ++ ++ ksoftirqd_run_end(); ++} ++ ++static void raise_ktimers_thread(unsigned int nr) ++{ ++ trace_softirq_raise(nr); ++ __this_cpu_or(pending_timer_softirq, 1 << nr); ++} ++ ++void raise_hrtimer_softirq(void) ++{ ++ raise_ktimers_thread(HRTIMER_SOFTIRQ); ++} ++ ++void raise_timer_softirq(void) ++{ ++ unsigned long flags; ++ ++ local_irq_save(flags); ++ raise_ktimers_thread(TIMER_SOFTIRQ); ++ wake_timersd(); ++ local_irq_restore(flags); ++} ++ ++static struct smp_hotplug_thread timer_threads = { ++ .store = &timersd, ++ .setup = timersd_setup, ++ .thread_should_run = timersd_should_run, ++ .thread_fn = run_timersd, ++ .thread_comm = "ktimers/%u", ++}; ++#endif ++ + static __init int spawn_ksoftirqd(void) + { + cpuhp_setup_state_nocalls(CPUHP_SOFTIRQ_DEAD, "softirq:dead", NULL, + takeover_tasklets); + BUG_ON(smpboot_register_percpu_thread(&softirq_threads)); +- ++#ifdef CONFIG_PREEMPT_RT ++ BUG_ON(smpboot_register_percpu_thread(&timer_threads)); ++#endif + return 0; + } + early_initcall(spawn_ksoftirqd); +diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c +index 5561dabc9b22..c5d480d5da15 100644 +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -1805,7 +1805,7 @@ void hrtimer_interrupt(struct clock_event_device *dev) + if (!ktime_before(now, cpu_base->softirq_expires_next)) { + cpu_base->softirq_expires_next = KTIME_MAX; + cpu_base->softirq_activated = 1; +- raise_softirq_irqoff(HRTIMER_SOFTIRQ); ++ raise_hrtimer_softirq(); + } + + __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); +@@ -1918,7 +1918,7 @@ void hrtimer_run_queues(void) + if (!ktime_before(now, cpu_base->softirq_expires_next)) { + cpu_base->softirq_expires_next = KTIME_MAX; + cpu_base->softirq_activated = 1; +- raise_softirq_irqoff(HRTIMER_SOFTIRQ); ++ raise_hrtimer_softirq(); + } + + __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); +diff --git a/kernel/time/timer.c b/kernel/time/timer.c +index 717fcb9fb14a..e6219da89933 100644 +--- a/kernel/time/timer.c ++++ b/kernel/time/timer.c +@@ -1822,7 +1822,7 @@ static void run_local_timers(void) + if (time_before(jiffies, base->next_expiry)) + return; + } +- raise_softirq(TIMER_SOFTIRQ); ++ raise_timer_softirq(); + } + + /* +-- +2.43.0 + diff --git a/debian/patches-rt/0013-rcutorture-Also-force-sched-priority-to-timersd-on-b.patch b/debian/patches-rt/0013-rcutorture-Also-force-sched-priority-to-timersd-on-b.patch new file mode 100644 index 000000000..9e062b97c --- /dev/null +++ b/debian/patches-rt/0013-rcutorture-Also-force-sched-priority-to-timersd-on-b.patch @@ -0,0 +1,81 @@ +From a10aa54ef224bbd46ca1777e4b9fe960360961cc Mon Sep 17 00:00:00 2001 +From: Frederic Weisbecker <frederic@kernel.org> +Date: Tue, 5 Apr 2022 03:07:51 +0200 +Subject: [PATCH 13/62] rcutorture: Also force sched priority to timersd on + boosting test. +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +ksoftirqd is statically boosted to the priority level right above the +one of rcu_torture_boost() so that timers, which torture readers rely on, +get a chance to run while rcu_torture_boost() is polling. + +However timers processing got split from ksoftirqd into their own kthread +(timersd) that isn't boosted. It has the same SCHED_FIFO low prio as +rcu_torture_boost() and therefore timers can't preempt it and may +starve. + +The issue can be triggered in practice on v5.17.1-rt17 using: + + ./kvm.sh --allcpus --configs TREE04 --duration 10m --kconfig "CONFIG_EXPERT=y CONFIG_PREEMPT_RT=y" + +Fix this with statically boosting timersd just like is done with +ksoftirqd in commit + ea6d962e80b61 ("rcutorture: Judge RCU priority boosting on grace periods, not callbacks") + +Suggested-by: Mel Gorman <mgorman@suse.de> +Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Cc: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Frederic Weisbecker <frederic@kernel.org> +Link: https://lkml.kernel.org/r/20220405010752.1347437-1-frederic@kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/interrupt.h | 1 + + kernel/rcu/rcutorture.c | 6 ++++++ + kernel/softirq.c | 2 +- + 3 files changed, 8 insertions(+), 1 deletion(-) + +diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h +index 0efba74a835c..f459b0f27c94 100644 +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -610,6 +610,7 @@ extern void raise_softirq_irqoff(unsigned int nr); + extern void raise_softirq(unsigned int nr); + + #ifdef CONFIG_PREEMPT_RT ++DECLARE_PER_CPU(struct task_struct *, timersd); + extern void raise_timer_softirq(void); + extern void raise_hrtimer_softirq(void); + +diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c +index 503c2aa845a4..dcd8c0e44c00 100644 +--- a/kernel/rcu/rcutorture.c ++++ b/kernel/rcu/rcutorture.c +@@ -2363,6 +2363,12 @@ static int rcutorture_booster_init(unsigned int cpu) + WARN_ON_ONCE(!t); + sp.sched_priority = 2; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); ++#ifdef CONFIG_PREEMPT_RT ++ t = per_cpu(timersd, cpu); ++ WARN_ON_ONCE(!t); ++ sp.sched_priority = 2; ++ sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); ++#endif + } + + /* Don't allow time recalculation while creating a new task. */ +diff --git a/kernel/softirq.c b/kernel/softirq.c +index ed6d7c41aa17..1892af494cdd 100644 +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -638,7 +638,7 @@ static inline void tick_irq_exit(void) + } + + #ifdef CONFIG_PREEMPT_RT +-static DEFINE_PER_CPU(struct task_struct *, timersd); ++DEFINE_PER_CPU(struct task_struct *, timersd); + static DEFINE_PER_CPU(unsigned long, pending_timer_softirq); + + static unsigned int local_pending_timers(void) +-- +2.43.0 + diff --git a/debian/patches-rt/0014-tick-Fix-timer-storm-since-introduction-of-timersd.patch b/debian/patches-rt/0014-tick-Fix-timer-storm-since-introduction-of-timersd.patch new file mode 100644 index 000000000..11eeed939 --- /dev/null +++ b/debian/patches-rt/0014-tick-Fix-timer-storm-since-introduction-of-timersd.patch @@ -0,0 +1,116 @@ +From ae3e63c4320c0c2d3865ba8ecff64a6d03948ce7 Mon Sep 17 00:00:00 2001 +From: Frederic Weisbecker <frederic@kernel.org> +Date: Tue, 5 Apr 2022 03:07:52 +0200 +Subject: [PATCH 14/62] tick: Fix timer storm since introduction of timersd +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +If timers are pending while the tick is reprogrammed on nohz_mode, the +next expiry is not armed to fire now, it is delayed one jiffy forward +instead so as not to raise an inextinguishable timer storm with such +scenario: + +1) IRQ triggers and queue a timer +2) ksoftirqd() is woken up +3) IRQ tail: timer is reprogrammed to fire now +4) IRQ exit +5) TIMER interrupt +6) goto 3) + +...all that until we finally reach ksoftirqd. + +Unfortunately we are checking the wrong softirq vector bitmask since +timersd kthread has split from ksoftirqd. Timers now have their own +vector state field that must be checked separately. As a result, the +old timer storm is back. This shows up early on boot with extremely long +initcalls: + + [ 333.004807] initcall dquot_init+0x0/0x111 returned 0 after 323822879 usecs + +and the cause is uncovered with the right trace events showing just +10 microseconds between ticks (~100 000 Hz): + +|swapper/-1 1dn.h111 60818582us : hrtimer_expire_entry: hrtimer=00000000e0ef0f6b function=tick_sched_timer now=60415486608 +|swapper/-1 1dn.h111 60818592us : hrtimer_expire_entry: hrtimer=00000000e0ef0f6b function=tick_sched_timer now=60415496082 +|swapper/-1 1dn.h111 60818601us : hrtimer_expire_entry: hrtimer=00000000e0ef0f6b function=tick_sched_timer now=60415505550 + +Fix this by checking the right timer vector state from the nohz code. + +Signed-off-by: Frederic Weisbecker <frederic@kernel.org> +Cc: Mel Gorman <mgorman@suse.de> +Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Cc: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Link: https://lkml.kernel.org/r/20220405010752.1347437-2-frederic@kernel.org +--- + include/linux/interrupt.h | 12 ++++++++++++ + kernel/softirq.c | 7 +------ + kernel/time/tick-sched.c | 2 +- + 3 files changed, 14 insertions(+), 7 deletions(-) + +diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h +index f459b0f27c94..a5091ac97fc6 100644 +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -611,9 +611,16 @@ extern void raise_softirq(unsigned int nr); + + #ifdef CONFIG_PREEMPT_RT + DECLARE_PER_CPU(struct task_struct *, timersd); ++DECLARE_PER_CPU(unsigned long, pending_timer_softirq); ++ + extern void raise_timer_softirq(void); + extern void raise_hrtimer_softirq(void); + ++static inline unsigned int local_pending_timers(void) ++{ ++ return __this_cpu_read(pending_timer_softirq); ++} ++ + #else + static inline void raise_timer_softirq(void) + { +@@ -624,6 +631,11 @@ static inline void raise_hrtimer_softirq(void) + { + raise_softirq_irqoff(HRTIMER_SOFTIRQ); + } ++ ++static inline unsigned int local_pending_timers(void) ++{ ++ return local_softirq_pending(); ++} + #endif + + DECLARE_PER_CPU(struct task_struct *, ksoftirqd); +diff --git a/kernel/softirq.c b/kernel/softirq.c +index 1892af494cdd..ab1fe34326ba 100644 +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -639,12 +639,7 @@ static inline void tick_irq_exit(void) + + #ifdef CONFIG_PREEMPT_RT + DEFINE_PER_CPU(struct task_struct *, timersd); +-static DEFINE_PER_CPU(unsigned long, pending_timer_softirq); +- +-static unsigned int local_pending_timers(void) +-{ +- return __this_cpu_read(pending_timer_softirq); +-} ++DEFINE_PER_CPU(unsigned long, pending_timer_softirq); + + static void wake_timersd(void) + { +diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c +index 798e1841d286..b52e1861b913 100644 +--- a/kernel/time/tick-sched.c ++++ b/kernel/time/tick-sched.c +@@ -800,7 +800,7 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) + + static inline bool local_timer_softirq_pending(void) + { +- return local_softirq_pending() & BIT(TIMER_SOFTIRQ); ++ return local_pending_timers() & BIT(TIMER_SOFTIRQ); + } + + static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) +-- +2.43.0 + diff --git a/debian/patches-rt/0015-softirq-Wake-ktimers-thread-also-in-softirq.patch b/debian/patches-rt/0015-softirq-Wake-ktimers-thread-also-in-softirq.patch new file mode 100644 index 000000000..3b938739e --- /dev/null +++ b/debian/patches-rt/0015-softirq-Wake-ktimers-thread-also-in-softirq.patch @@ -0,0 +1,50 @@ +From ca98adaa69af0a5f3bb28cccb6543ee3e0c4a23f Mon Sep 17 00:00:00 2001 +From: Junxiao Chang <junxiao.chang@intel.com> +Date: Mon, 20 Feb 2023 09:12:20 +0100 +Subject: [PATCH 15/62] softirq: Wake ktimers thread also in softirq. +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +If the hrtimer is raised while a softirq is processed then it does not +wake the corresponding ktimers thread. This is due to the optimisation in the +irq-exit path which is also used to wake the ktimers thread. For the other +softirqs, this is okay because the additional softirq bits will be handled by +the currently running softirq handler. +The timer related softirq bits are added to a different variable and rely on +the ktimers thread. +As a consuequence the wake up of ktimersd is delayed until the next timer tick. + +Always wake the ktimers thread if a timer related softirq is pending. + +Reported-by: Peh, Hock Zhang <hock.zhang.peh@intel.com> +Signed-off-by: Junxiao Chang <junxiao.chang@intel.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/softirq.c | 11 +++++------ + 1 file changed, 5 insertions(+), 6 deletions(-) + +diff --git a/kernel/softirq.c b/kernel/softirq.c +index ab1fe34326ba..82f3e68fbe22 100644 +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -664,13 +664,12 @@ static inline void __irq_exit_rcu(void) + #endif + account_hardirq_exit(current); + preempt_count_sub(HARDIRQ_OFFSET); +- if (!in_interrupt()) { +- if (local_softirq_pending()) +- invoke_softirq(); ++ if (!in_interrupt() && local_softirq_pending()) ++ invoke_softirq(); + +- if (IS_ENABLED(CONFIG_PREEMPT_RT) && local_pending_timers()) +- wake_timersd(); +- } ++ if (IS_ENABLED(CONFIG_PREEMPT_RT) && local_pending_timers() && ++ !(in_nmi() | in_hardirq())) ++ wake_timersd(); + + tick_irq_exit(); + } +-- +2.43.0 + diff --git a/debian/patches-rt/0016-tpm_tis-fix-stall-after-iowrite-s.patch b/debian/patches-rt/0016-tpm_tis-fix-stall-after-iowrite-s.patch new file mode 100644 index 000000000..4004bbf47 --- /dev/null +++ b/debian/patches-rt/0016-tpm_tis-fix-stall-after-iowrite-s.patch @@ -0,0 +1,82 @@ +From 87e5c70f401b5230b5125dedc88e10f54909a37e Mon Sep 17 00:00:00 2001 +From: Haris Okanovic <haris.okanovic@ni.com> +Date: Tue, 15 Aug 2017 15:13:08 -0500 +Subject: [PATCH 16/62] tpm_tis: fix stall after iowrite*()s +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +ioread8() operations to TPM MMIO addresses can stall the cpu when +immediately following a sequence of iowrite*()'s to the same region. + +For example, cyclitest measures ~400us latency spikes when a non-RT +usermode application communicates with an SPI-based TPM chip (Intel Atom +E3940 system, PREEMPT_RT kernel). The spikes are caused by a +stalling ioread8() operation following a sequence of 30+ iowrite8()s to +the same address. I believe this happens because the write sequence is +buffered (in cpu or somewhere along the bus), and gets flushed on the +first LOAD instruction (ioread*()) that follows. + +The enclosed change appears to fix this issue: read the TPM chip's +access register (status code) after every iowrite*() operation to +amortize the cost of flushing data to chip across multiple instructions. + +Signed-off-by: Haris Okanovic <haris.okanovic@ni.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + drivers/char/tpm/tpm_tis.c | 29 +++++++++++++++++++++++++++-- + 1 file changed, 27 insertions(+), 2 deletions(-) + +diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c +index 0d084d6652c4..5d620322bdc2 100644 +--- a/drivers/char/tpm/tpm_tis.c ++++ b/drivers/char/tpm/tpm_tis.c +@@ -50,6 +50,31 @@ static inline struct tpm_tis_tcg_phy *to_tpm_tis_tcg_phy(struct tpm_tis_data *da + return container_of(data, struct tpm_tis_tcg_phy, priv); + } + ++#ifdef CONFIG_PREEMPT_RT ++/* ++ * Flushes previous write operations to chip so that a subsequent ++ * ioread*()s won't stall a cpu. ++ */ ++static inline void tpm_tis_flush(void __iomem *iobase) ++{ ++ ioread8(iobase + TPM_ACCESS(0)); ++} ++#else ++#define tpm_tis_flush(iobase) do { } while (0) ++#endif ++ ++static inline void tpm_tis_iowrite8(u8 b, void __iomem *iobase, u32 addr) ++{ ++ iowrite8(b, iobase + addr); ++ tpm_tis_flush(iobase); ++} ++ ++static inline void tpm_tis_iowrite32(u32 b, void __iomem *iobase, u32 addr) ++{ ++ iowrite32(b, iobase + addr); ++ tpm_tis_flush(iobase); ++} ++ + static int interrupts = -1; + module_param(interrupts, int, 0444); + MODULE_PARM_DESC(interrupts, "Enable interrupts"); +@@ -202,12 +227,12 @@ static int tpm_tcg_write_bytes(struct tpm_tis_data *data, u32 addr, u16 len, + switch (io_mode) { + case TPM_TIS_PHYS_8: + while (len--) +- iowrite8(*value++, phy->iobase + addr); ++ tpm_tis_iowrite8(*value++, phy->iobase, addr); + break; + case TPM_TIS_PHYS_16: + return -EINVAL; + case TPM_TIS_PHYS_32: +- iowrite32(le32_to_cpu(*((__le32 *)value)), phy->iobase + addr); ++ tpm_tis_iowrite32(le32_to_cpu(*((__le32 *)value)), phy->iobase, addr); + break; + } + +-- +2.43.0 + diff --git a/debian/patches-rt/0017-zram-Replace-bit-spinlocks-with-spinlock_t-for-PREEM.patch b/debian/patches-rt/0017-zram-Replace-bit-spinlocks-with-spinlock_t-for-PREEM.patch new file mode 100644 index 000000000..b3f1a71bc --- /dev/null +++ b/debian/patches-rt/0017-zram-Replace-bit-spinlocks-with-spinlock_t-for-PREEM.patch @@ -0,0 +1,100 @@ +From 8397109d43ef57d5e91d738354b9c30f49cb2f95 Mon Sep 17 00:00:00 2001 +From: Mike Galbraith <umgwanakikbuti@gmail.com> +Date: Thu, 31 Mar 2016 04:08:28 +0200 +Subject: [PATCH 17/62] zram: Replace bit spinlocks with spinlock_t for + PREEMPT_RT. +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +The bit spinlock disables preemption on PREEMPT_RT. With disabled preemption it +is not allowed to acquire other sleeping locks which includes invoking +zs_free(). + +Use a spinlock_t on PREEMPT_RT for locking and set/ clear ZRAM_LOCK after the +lock has been acquired/ dropped. + +Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Link: https://lkml.kernel.org/r/YqIbMuHCPiQk+Ac2@linutronix.de +--- + drivers/block/zram/zram_drv.c | 36 +++++++++++++++++++++++++++++++++++ + drivers/block/zram/zram_drv.h | 3 +++ + 2 files changed, 39 insertions(+) + +diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c +index 966aab902d19..ee69e4443691 100644 +--- a/drivers/block/zram/zram_drv.c ++++ b/drivers/block/zram/zram_drv.c +@@ -57,6 +57,40 @@ static void zram_free_page(struct zram *zram, size_t index); + static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, + u32 index, int offset, struct bio *bio); + ++#ifdef CONFIG_PREEMPT_RT ++static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages) ++{ ++ size_t index; ++ ++ for (index = 0; index < num_pages; index++) ++ spin_lock_init(&zram->table[index].lock); ++} ++ ++static int zram_slot_trylock(struct zram *zram, u32 index) ++{ ++ int ret; ++ ++ ret = spin_trylock(&zram->table[index].lock); ++ if (ret) ++ __set_bit(ZRAM_LOCK, &zram->table[index].flags); ++ return ret; ++} ++ ++static void zram_slot_lock(struct zram *zram, u32 index) ++{ ++ spin_lock(&zram->table[index].lock); ++ __set_bit(ZRAM_LOCK, &zram->table[index].flags); ++} ++ ++static void zram_slot_unlock(struct zram *zram, u32 index) ++{ ++ __clear_bit(ZRAM_LOCK, &zram->table[index].flags); ++ spin_unlock(&zram->table[index].lock); ++} ++ ++#else ++ ++static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages) { } + + static int zram_slot_trylock(struct zram *zram, u32 index) + { +@@ -72,6 +106,7 @@ static void zram_slot_unlock(struct zram *zram, u32 index) + { + bit_spin_unlock(ZRAM_LOCK, &zram->table[index].flags); + } ++#endif + + static inline bool init_done(struct zram *zram) + { +@@ -1187,6 +1222,7 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize) + + if (!huge_class_size) + huge_class_size = zs_huge_class_size(zram->mem_pool); ++ zram_meta_init_table_locks(zram, num_pages); + return true; + } + +diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h +index a2bda53020fd..ae7950b26db5 100644 +--- a/drivers/block/zram/zram_drv.h ++++ b/drivers/block/zram/zram_drv.h +@@ -62,6 +62,9 @@ struct zram_table_entry { + unsigned long element; + }; + unsigned long flags; ++#ifdef CONFIG_PREEMPT_RT ++ spinlock_t lock; ++#endif + #ifdef CONFIG_ZRAM_MEMORY_TRACKING + ktime_t ac_time; + #endif +-- +2.43.0 + diff --git a/debian/patches-rt/0018-locking-lockdep-Remove-lockdep_init_map_crosslock.patch b/debian/patches-rt/0018-locking-lockdep-Remove-lockdep_init_map_crosslock.patch new file mode 100644 index 000000000..3dcd8cb9b --- /dev/null +++ b/debian/patches-rt/0018-locking-lockdep-Remove-lockdep_init_map_crosslock.patch @@ -0,0 +1,34 @@ +From dd162e2589601c792a81a3c19ef4a87510ed6ce5 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 11 Mar 2022 17:44:57 +0100 +Subject: [PATCH 18/62] locking/lockdep: Remove lockdep_init_map_crosslock. +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +The cross-release bits have been removed, lockdep_init_map_crosslock() is +a leftover. + +Remove lockdep_init_map_crosslock. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Reviewed-by: Waiman Long <longman@redhat.com> +Link: https://lore.kernel.org/r/20220311164457.46461-1-bigeasy@linutronix.de +Link: https://lore.kernel.org/r/YqITgY+2aPITu96z@linutronix.de +--- + include/linux/lockdep.h | 1 - + 1 file changed, 1 deletion(-) + +diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h +index 1f1099dac3f0..1023f349af71 100644 +--- a/include/linux/lockdep.h ++++ b/include/linux/lockdep.h +@@ -435,7 +435,6 @@ enum xhlock_context_t { + XHLOCK_CTX_NR, + }; + +-#define lockdep_init_map_crosslock(m, n, k, s) do {} while (0) + /* + * To initialize a lockdep_map statically use this macro. + * Note that _name must not be NULL. +-- +2.43.0 + diff --git a/debian/patches-rt/0019-printk-Bring-back-the-RT-bits.patch b/debian/patches-rt/0019-printk-Bring-back-the-RT-bits.patch new file mode 100644 index 000000000..969f44377 --- /dev/null +++ b/debian/patches-rt/0019-printk-Bring-back-the-RT-bits.patch @@ -0,0 +1,1234 @@ +From dd4e52ae061806da556008ca819481befcff0fd3 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 19 Jul 2022 20:08:01 +0200 +Subject: [PATCH 19/62] printk: Bring back the RT bits. +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +This is a revert of the commits: +| 07a22b61946f0 Revert "printk: add functions to prefer direct printing" +| 5831788afb17b Revert "printk: add kthread console printers" +| 2d9ef940f89e0 Revert "printk: extend console_lock for per-console locking" +| 007eeab7e9f03 Revert "printk: remove @console_locked" +| 05c96b3713aa2 Revert "printk: Block console kthreads when direct printing will be required" +| 20fb0c8272bbb Revert "printk: Wait for the global console lock when the system is going down" + +which is needed for the atomic consoles which are used on PREEMPT_RT. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/tty/sysrq.c | 2 + + include/linux/console.h | 17 ++ + include/linux/printk.h | 15 + + kernel/hung_task.c | 11 +- + kernel/panic.c | 4 + + kernel/printk/internal.h | 2 + + kernel/printk/printk.c | 586 ++++++++++++++++++++++++++++++++---- + kernel/printk/printk_safe.c | 32 ++ + kernel/rcu/tree_stall.h | 2 + + kernel/reboot.c | 16 +- + kernel/watchdog.c | 4 + + kernel/watchdog_hld.c | 4 + + 12 files changed, 636 insertions(+), 59 deletions(-) + +diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c +index 248067197287..0db9dad8c99f 100644 +--- a/drivers/tty/sysrq.c ++++ b/drivers/tty/sysrq.c +@@ -582,6 +582,7 @@ void __handle_sysrq(int key, bool check_mask) + + rcu_sysrq_start(); + rcu_read_lock(); ++ printk_prefer_direct_enter(); + /* + * Raise the apparent loglevel to maximum so that the sysrq header + * is shown to provide the user with positive feedback. We do not +@@ -623,6 +624,7 @@ void __handle_sysrq(int key, bool check_mask) + pr_cont("\n"); + console_loglevel = orig_log_level; + } ++ printk_prefer_direct_exit(); + rcu_read_unlock(); + rcu_sysrq_end(); + +diff --git a/include/linux/console.h b/include/linux/console.h +index 8c1686e2c233..143653090c48 100644 +--- a/include/linux/console.h ++++ b/include/linux/console.h +@@ -16,6 +16,7 @@ + + #include <linux/atomic.h> + #include <linux/types.h> ++#include <linux/mutex.h> + + struct vc_data; + struct console_font_op; +@@ -153,6 +154,22 @@ struct console { + uint ospeed; + u64 seq; + unsigned long dropped; ++ struct task_struct *thread; ++ bool blocked; ++ ++ /* ++ * The per-console lock is used by printing kthreads to synchronize ++ * this console with callers of console_lock(). This is necessary in ++ * order to allow printing kthreads to run in parallel to each other, ++ * while each safely accessing the @blocked field and synchronizing ++ * against direct printing via console_lock/console_unlock. ++ * ++ * Note: For synchronizing against direct printing via ++ * console_trylock/console_unlock, see the static global ++ * variable @console_kthreads_active. ++ */ ++ struct mutex lock; ++ + void *data; + struct console *next; + }; +diff --git a/include/linux/printk.h b/include/linux/printk.h +index 8c81806c2e99..f8c4e4fa6d7d 100644 +--- a/include/linux/printk.h ++++ b/include/linux/printk.h +@@ -168,6 +168,9 @@ extern void __printk_safe_exit(void); + */ + #define printk_deferred_enter __printk_safe_enter + #define printk_deferred_exit __printk_safe_exit ++extern void printk_prefer_direct_enter(void); ++extern void printk_prefer_direct_exit(void); ++extern void try_block_console_kthreads(int timeout_ms); + + /* + * Please don't use printk_ratelimit(), because it shares ratelimiting state +@@ -219,6 +222,18 @@ static inline void printk_deferred_exit(void) + { + } + ++static inline void printk_prefer_direct_enter(void) ++{ ++} ++ ++static inline void printk_prefer_direct_exit(void) ++{ ++} ++ ++static inline void try_block_console_kthreads(int timeout_ms) ++{ ++} ++ + static inline int printk_ratelimit(void) + { + return 0; +diff --git a/kernel/hung_task.c b/kernel/hung_task.c +index c71889f3f3fc..e2d2344cb9f4 100644 +--- a/kernel/hung_task.c ++++ b/kernel/hung_task.c +@@ -127,6 +127,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) + * complain: + */ + if (sysctl_hung_task_warnings) { ++ printk_prefer_direct_enter(); ++ + if (sysctl_hung_task_warnings > 0) + sysctl_hung_task_warnings--; + pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n", +@@ -142,6 +144,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) + + if (sysctl_hung_task_all_cpu_backtrace) + hung_task_show_all_bt = true; ++ ++ printk_prefer_direct_exit(); + } + + touch_nmi_watchdog(); +@@ -212,12 +216,17 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) + } + unlock: + rcu_read_unlock(); +- if (hung_task_show_lock) ++ if (hung_task_show_lock) { ++ printk_prefer_direct_enter(); + debug_show_all_locks(); ++ printk_prefer_direct_exit(); ++ } + + if (hung_task_show_all_bt) { + hung_task_show_all_bt = false; ++ printk_prefer_direct_enter(); + trigger_all_cpu_backtrace(); ++ printk_prefer_direct_exit(); + } + + if (hung_task_call_panic) +diff --git a/kernel/panic.c b/kernel/panic.c +index 63e94f3bd8dc..88cd873c7c30 100644 +--- a/kernel/panic.c ++++ b/kernel/panic.c +@@ -653,6 +653,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint, + { + disable_trace_on_warning(); + ++ printk_prefer_direct_enter(); ++ + if (file) + pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n", + raw_smp_processor_id(), current->pid, file, line, +@@ -681,6 +683,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint, + + /* Just a warning, don't kill lockdep. */ + add_taint(taint, LOCKDEP_STILL_OK); ++ ++ printk_prefer_direct_exit(); + } + + #ifndef __WARN_FLAGS +diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h +index d947ca6c84f9..e7d8578860ad 100644 +--- a/kernel/printk/internal.h ++++ b/kernel/printk/internal.h +@@ -20,6 +20,8 @@ enum printk_info_flags { + LOG_CONT = 8, /* text is a fragment of a continuation line */ + }; + ++extern bool block_console_kthreads; ++ + __printf(4, 0) + int vprintk_store(int facility, int level, + const struct dev_printk_info *dev_info, +diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c +index cc53fb77f77c..e9f9b66608a0 100644 +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -220,6 +220,36 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, + } + #endif /* CONFIG_PRINTK && CONFIG_SYSCTL */ + ++/* ++ * Used to synchronize printing kthreads against direct printing via ++ * console_trylock/console_unlock. ++ * ++ * Values: ++ * -1 = console kthreads atomically blocked (via global trylock) ++ * 0 = no kthread printing, console not locked (via trylock) ++ * >0 = kthread(s) actively printing ++ * ++ * Note: For synchronizing against direct printing via ++ * console_lock/console_unlock, see the @lock variable in ++ * struct console. ++ */ ++static atomic_t console_kthreads_active = ATOMIC_INIT(0); ++ ++#define console_kthreads_atomic_tryblock() \ ++ (atomic_cmpxchg(&console_kthreads_active, 0, -1) == 0) ++#define console_kthreads_atomic_unblock() \ ++ atomic_cmpxchg(&console_kthreads_active, -1, 0) ++#define console_kthreads_atomically_blocked() \ ++ (atomic_read(&console_kthreads_active) == -1) ++ ++#define console_kthread_printing_tryenter() \ ++ atomic_inc_unless_negative(&console_kthreads_active) ++#define console_kthread_printing_exit() \ ++ atomic_dec(&console_kthreads_active) ++ ++/* Block console kthreads to avoid processing new messages. */ ++bool block_console_kthreads; ++ + /* + * Helper macros to handle lockdep when locking/unlocking console_sem. We use + * macros instead of functions so that _RET_IP_ contains useful information. +@@ -268,14 +298,49 @@ static bool panic_in_progress(void) + } + + /* +- * This is used for debugging the mess that is the VT code by +- * keeping track if we have the console semaphore held. It's +- * definitely not the perfect debug tool (we don't know if _WE_ +- * hold it and are racing, but it helps tracking those weird code +- * paths in the console code where we end up in places I want +- * locked without the console semaphore held). ++ * Tracks whether kthread printers are all blocked. A value of true implies ++ * that the console is locked via console_lock() or the console is suspended. ++ * Writing to this variable requires holding @console_sem. ++ */ ++static bool console_kthreads_blocked; ++ ++/* ++ * Block all kthread printers from a schedulable context. ++ * ++ * Requires holding @console_sem. ++ */ ++static void console_kthreads_block(void) ++{ ++ struct console *con; ++ ++ for_each_console(con) { ++ mutex_lock(&con->lock); ++ con->blocked = true; ++ mutex_unlock(&con->lock); ++ } ++ ++ console_kthreads_blocked = true; ++} ++ ++/* ++ * Unblock all kthread printers from a schedulable context. ++ * ++ * Requires holding @console_sem. + */ +-static int console_locked, console_suspended; ++static void console_kthreads_unblock(void) ++{ ++ struct console *con; ++ ++ for_each_console(con) { ++ mutex_lock(&con->lock); ++ con->blocked = false; ++ mutex_unlock(&con->lock); ++ } ++ ++ console_kthreads_blocked = false; ++} ++ ++static int console_suspended; + + /* + * Array of consoles built from command line options (console=) +@@ -358,7 +423,75 @@ static int console_msg_format = MSG_FORMAT_DEFAULT; + /* syslog_lock protects syslog_* variables and write access to clear_seq. */ + static DEFINE_MUTEX(syslog_lock); + ++/* ++ * A flag to signify if printk_activate_kthreads() has already started the ++ * kthread printers. If true, any later registered consoles must start their ++ * own kthread directly. The flag is write protected by the console_lock. ++ */ ++static bool printk_kthreads_available; ++ + #ifdef CONFIG_PRINTK ++static atomic_t printk_prefer_direct = ATOMIC_INIT(0); ++ ++/** ++ * printk_prefer_direct_enter - cause printk() calls to attempt direct ++ * printing to all enabled consoles ++ * ++ * Since it is not possible to call into the console printing code from any ++ * context, there is no guarantee that direct printing will occur. ++ * ++ * This globally effects all printk() callers. ++ * ++ * Context: Any context. ++ */ ++void printk_prefer_direct_enter(void) ++{ ++ atomic_inc(&printk_prefer_direct); ++} ++ ++/** ++ * printk_prefer_direct_exit - restore printk() behavior ++ * ++ * Context: Any context. ++ */ ++void printk_prefer_direct_exit(void) ++{ ++ WARN_ON(atomic_dec_if_positive(&printk_prefer_direct) < 0); ++} ++ ++/* ++ * Calling printk() always wakes kthread printers so that they can ++ * flush the new message to their respective consoles. Also, if direct ++ * printing is allowed, printk() tries to flush the messages directly. ++ * ++ * Direct printing is allowed in situations when the kthreads ++ * are not available or the system is in a problematic state. ++ * ++ * See the implementation about possible races. ++ */ ++static inline bool allow_direct_printing(void) ++{ ++ /* ++ * Checking kthread availability is a possible race because the ++ * kthread printers can become permanently disabled during runtime. ++ * However, doing that requires holding the console_lock, so any ++ * pending messages will be direct printed by console_unlock(). ++ */ ++ if (!printk_kthreads_available) ++ return true; ++ ++ /* ++ * Prefer direct printing when the system is in a problematic state. ++ * The context that sets this state will always see the updated value. ++ * The other contexts do not care. Anyway, direct printing is just a ++ * best effort. The direct output is only possible when console_lock ++ * is not already taken and no kthread printers are actively printing. ++ */ ++ return (system_state > SYSTEM_RUNNING || ++ oops_in_progress || ++ atomic_read(&printk_prefer_direct)); ++} ++ + DECLARE_WAIT_QUEUE_HEAD(log_wait); + /* All 3 protected by @syslog_lock. */ + /* the next printk record to read by syslog(READ) or /proc/kmsg */ +@@ -2249,10 +2382,10 @@ asmlinkage int vprintk_emit(int facility, int level, + printed_len = vprintk_store(facility, level, dev_info, fmt, args); + + /* If called from the scheduler, we can not call up(). */ +- if (!in_sched) { ++ if (!in_sched && allow_direct_printing()) { + /* + * The caller may be holding system-critical or +- * timing-sensitive locks. Disable preemption during ++ * timing-sensitive locks. Disable preemption during direct + * printing of all remaining records to all consoles so that + * this context can return as soon as possible. Hopefully + * another printk() caller will take over the printing. +@@ -2300,6 +2433,8 @@ EXPORT_SYMBOL(_printk); + static bool pr_flush(int timeout_ms, bool reset_on_progress); + static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress); + ++static void printk_start_kthread(struct console *con); ++ + #else /* CONFIG_PRINTK */ + + #define CONSOLE_LOG_MAX 0 +@@ -2334,6 +2469,8 @@ static void call_console_driver(struct console *con, const char *text, size_t le + static bool suppress_message_printing(int level) { return false; } + static bool pr_flush(int timeout_ms, bool reset_on_progress) { return true; } + static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; } ++static void printk_start_kthread(struct console *con) { } ++static bool allow_direct_printing(void) { return true; } + + #endif /* CONFIG_PRINTK */ + +@@ -2552,6 +2689,14 @@ static int console_cpu_notify(unsigned int cpu) + /* If trylock fails, someone else is doing the printing */ + if (console_trylock()) + console_unlock(); ++ else { ++ /* ++ * If a new CPU comes online, the conditions for ++ * printer_should_wake() may have changed for some ++ * kthread printer with !CON_ANYTIME. ++ */ ++ wake_up_klogd(); ++ } + } + return 0; + } +@@ -2594,7 +2739,7 @@ void console_lock(void) + down_console_sem(); + if (console_suspended) + return; +- console_locked = 1; ++ console_kthreads_block(); + console_may_schedule = 1; + } + EXPORT_SYMBOL(console_lock); +@@ -2618,15 +2763,30 @@ int console_trylock(void) + up_console_sem(); + return 0; + } +- console_locked = 1; ++ if (!console_kthreads_atomic_tryblock()) { ++ up_console_sem(); ++ return 0; ++ } + console_may_schedule = 0; + return 1; + } + EXPORT_SYMBOL(console_trylock); + ++/* ++ * This is used to help to make sure that certain paths within the VT code are ++ * running with the console lock held. It is definitely not the perfect debug ++ * tool (it is not known if the VT code is the task holding the console lock), ++ * but it helps tracking those weird code paths in the console code such as ++ * when the console is suspended: where the console is not locked but no ++ * console printing may occur. ++ * ++ * Note: This returns true when the console is suspended but is not locked. ++ * This is intentional because the VT code must consider that situation ++ * the same as if the console was locked. ++ */ + int is_console_locked(void) + { +- return console_locked; ++ return (console_kthreads_blocked || atomic_read(&console_kthreads_active)); + } + EXPORT_SYMBOL(is_console_locked); + +@@ -2636,12 +2796,9 @@ EXPORT_SYMBOL(is_console_locked); + * + * Requires the console_lock. + */ +-static inline bool console_is_usable(struct console *con) ++static inline bool __console_is_usable(short flags) + { +- if (!(con->flags & CON_ENABLED)) +- return false; +- +- if (!con->write) ++ if (!(flags & CON_ENABLED)) + return false; + + /* +@@ -2650,15 +2807,43 @@ static inline bool console_is_usable(struct console *con) + * cope (CON_ANYTIME) don't call them until this CPU is officially up. + */ + if (!cpu_online(raw_smp_processor_id()) && +- !(con->flags & CON_ANYTIME)) ++ !(flags & CON_ANYTIME)) + return false; + + return true; + } + ++/* ++ * Check if the given console is currently capable and allowed to print ++ * records. ++ * ++ * Requires holding the console_lock. ++ */ ++static inline bool console_is_usable(struct console *con) ++{ ++ if (!con->write) ++ return false; ++ ++ return __console_is_usable(con->flags); ++} ++ + static void __console_unlock(void) + { +- console_locked = 0; ++ /* ++ * Depending on whether console_lock() or console_trylock() was used, ++ * appropriately allow the kthread printers to continue. ++ */ ++ if (console_kthreads_blocked) ++ console_kthreads_unblock(); ++ else ++ console_kthreads_atomic_unblock(); ++ ++ /* ++ * New records may have arrived while the console was locked. ++ * Wake the kthread printers to print them. ++ */ ++ wake_up_klogd(); ++ + up_console_sem(); + } + +@@ -2676,17 +2861,19 @@ static void __console_unlock(void) + * + * @handover will be set to true if a printk waiter has taken over the + * console_lock, in which case the caller is no longer holding the +- * console_lock. Otherwise it is set to false. ++ * console_lock. Otherwise it is set to false. A NULL pointer may be provided ++ * to disable allowing the console_lock to be taken over by a printk waiter. + * + * Returns false if the given console has no next record to print, otherwise + * true. + * +- * Requires the console_lock. ++ * Requires the console_lock if @handover is non-NULL. ++ * Requires con->lock otherwise. + */ +-static bool console_emit_next_record(struct console *con, char *text, char *ext_text, +- char *dropped_text, bool *handover) ++static bool __console_emit_next_record(struct console *con, char *text, char *ext_text, ++ char *dropped_text, bool *handover) + { +- static int panic_console_dropped; ++ static atomic_t panic_console_dropped = ATOMIC_INIT(0); + struct printk_info info; + struct printk_record r; + unsigned long flags; +@@ -2695,7 +2882,8 @@ static bool console_emit_next_record(struct console *con, char *text, char *ext_ + + prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); + +- *handover = false; ++ if (handover) ++ *handover = false; + + if (!prb_read_valid(prb, con->seq, &r)) + return false; +@@ -2703,7 +2891,8 @@ static bool console_emit_next_record(struct console *con, char *text, char *ext_ + if (con->seq != r.info->seq) { + con->dropped += r.info->seq - con->seq; + con->seq = r.info->seq; +- if (panic_in_progress() && panic_console_dropped++ > 10) { ++ if (panic_in_progress() && ++ atomic_fetch_inc_relaxed(&panic_console_dropped) > 10) { + suppress_panic_printk = 1; + pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n"); + } +@@ -2725,31 +2914,61 @@ static bool console_emit_next_record(struct console *con, char *text, char *ext_ + len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); + } + +- /* +- * While actively printing out messages, if another printk() +- * were to occur on another CPU, it may wait for this one to +- * finish. This task can not be preempted if there is a +- * waiter waiting to take over. +- * +- * Interrupts are disabled because the hand over to a waiter +- * must not be interrupted until the hand over is completed +- * (@console_waiter is cleared). +- */ +- printk_safe_enter_irqsave(flags); +- console_lock_spinning_enable(); ++ if (handover) { ++ /* ++ * While actively printing out messages, if another printk() ++ * were to occur on another CPU, it may wait for this one to ++ * finish. This task can not be preempted if there is a ++ * waiter waiting to take over. ++ * ++ * Interrupts are disabled because the hand over to a waiter ++ * must not be interrupted until the hand over is completed ++ * (@console_waiter is cleared). ++ */ ++ printk_safe_enter_irqsave(flags); ++ console_lock_spinning_enable(); ++ ++ /* don't trace irqsoff print latency */ ++ stop_critical_timings(); ++ } + +- stop_critical_timings(); /* don't trace print latency */ + call_console_driver(con, write_text, len, dropped_text); +- start_critical_timings(); + + con->seq++; + +- *handover = console_lock_spinning_disable_and_check(); +- printk_safe_exit_irqrestore(flags); ++ if (handover) { ++ start_critical_timings(); ++ *handover = console_lock_spinning_disable_and_check(); ++ printk_safe_exit_irqrestore(flags); ++ } + skip: + return true; + } + ++/* ++ * Print a record for a given console, but allow another printk() caller to ++ * take over the console_lock and continue printing. ++ * ++ * Requires the console_lock, but depending on @handover after the call, the ++ * caller may no longer have the console_lock. ++ * ++ * See __console_emit_next_record() for argument and return details. ++ */ ++static bool console_emit_next_record_transferable(struct console *con, char *text, char *ext_text, ++ char *dropped_text, bool *handover) ++{ ++ /* ++ * Handovers are only supported if threaded printers are atomically ++ * blocked. The context taking over the console_lock may be atomic. ++ */ ++ if (!console_kthreads_atomically_blocked()) { ++ *handover = false; ++ handover = NULL; ++ } ++ ++ return __console_emit_next_record(con, text, ext_text, dropped_text, handover); ++} ++ + /* + * Print out all remaining records to all consoles. + * +@@ -2768,8 +2987,8 @@ static bool console_emit_next_record(struct console *con, char *text, char *ext_ + * were flushed to all usable consoles. A returned false informs the caller + * that everything was not flushed (either there were no usable consoles or + * another context has taken over printing or it is a panic situation and this +- * is not the panic CPU). Regardless the reason, the caller should assume it +- * is not useful to immediately try again. ++ * is not the panic CPU or direct printing is not preferred). Regardless the ++ * reason, the caller should assume it is not useful to immediately try again. + * + * Requires the console_lock. + */ +@@ -2786,6 +3005,10 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove + *handover = false; + + do { ++ /* Let the kthread printers do the work if they can. */ ++ if (!allow_direct_printing()) ++ return false; ++ + any_progress = false; + + for_each_console(con) { +@@ -2797,13 +3020,11 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove + + if (con->flags & CON_EXTENDED) { + /* Extended consoles do not print "dropped messages". */ +- progress = console_emit_next_record(con, &text[0], +- &ext_text[0], NULL, +- handover); ++ progress = console_emit_next_record_transferable(con, &text[0], ++ &ext_text[0], NULL, handover); + } else { +- progress = console_emit_next_record(con, &text[0], +- NULL, &dropped_text[0], +- handover); ++ progress = console_emit_next_record_transferable(con, &text[0], ++ NULL, &dropped_text[0], handover); + } + if (*handover) + return false; +@@ -2918,10 +3139,13 @@ void console_unblank(void) + if (oops_in_progress) { + if (down_trylock_console_sem() != 0) + return; ++ if (!console_kthreads_atomic_tryblock()) { ++ up_console_sem(); ++ return; ++ } + } else + console_lock(); + +- console_locked = 1; + console_may_schedule = 0; + for_each_console(c) + if ((c->flags & CON_ENABLED) && c->unblank) +@@ -3197,6 +3421,10 @@ void register_console(struct console *newcon) + } + + newcon->dropped = 0; ++ newcon->thread = NULL; ++ newcon->blocked = true; ++ mutex_init(&newcon->lock); ++ + if (newcon->flags & CON_PRINTBUFFER) { + /* Get a consistent copy of @syslog_seq. */ + mutex_lock(&syslog_lock); +@@ -3206,6 +3434,10 @@ void register_console(struct console *newcon) + /* Begin with next message. */ + newcon->seq = prb_next_seq(prb); + } ++ ++ if (printk_kthreads_available) ++ printk_start_kthread(newcon); ++ + console_unlock(); + console_sysfs_notify(); + +@@ -3229,6 +3461,7 @@ EXPORT_SYMBOL(register_console); + + int unregister_console(struct console *console) + { ++ struct task_struct *thd; + struct console *con; + int res; + +@@ -3266,7 +3499,20 @@ int unregister_console(struct console *console) + console_drivers->flags |= CON_CONSDEV; + + console->flags &= ~CON_ENABLED; ++ ++ /* ++ * console->thread can only be cleared under the console lock. But ++ * stopping the thread must be done without the console lock. The ++ * task that clears @thread is the task that stops the kthread. ++ */ ++ thd = console->thread; ++ console->thread = NULL; ++ + console_unlock(); ++ ++ if (thd) ++ kthread_stop(thd); ++ + console_sysfs_notify(); + + if (console->exit) +@@ -3362,6 +3608,20 @@ static int __init printk_late_init(void) + } + late_initcall(printk_late_init); + ++static int __init printk_activate_kthreads(void) ++{ ++ struct console *con; ++ ++ console_lock(); ++ printk_kthreads_available = true; ++ for_each_console(con) ++ printk_start_kthread(con); ++ console_unlock(); ++ ++ return 0; ++} ++early_initcall(printk_activate_kthreads); ++ + #if defined CONFIG_PRINTK + /* If @con is specified, only wait for that console. Otherwise wait for all. */ + static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) +@@ -3444,11 +3704,208 @@ static bool pr_flush(int timeout_ms, bool reset_on_progress) + return __pr_flush(NULL, timeout_ms, reset_on_progress); + } + ++static void __printk_fallback_preferred_direct(void) ++{ ++ printk_prefer_direct_enter(); ++ pr_err("falling back to preferred direct printing\n"); ++ printk_kthreads_available = false; ++} ++ ++/* ++ * Enter preferred direct printing, but never exit. Mark console threads as ++ * unavailable. The system is then forever in preferred direct printing and ++ * any printing threads will exit. ++ * ++ * Must *not* be called under console_lock. Use ++ * __printk_fallback_preferred_direct() if already holding console_lock. ++ */ ++static void printk_fallback_preferred_direct(void) ++{ ++ console_lock(); ++ __printk_fallback_preferred_direct(); ++ console_unlock(); ++} ++ ++/* ++ * Print a record for a given console, not allowing another printk() caller ++ * to take over. This is appropriate for contexts that do not have the ++ * console_lock. ++ * ++ * See __console_emit_next_record() for argument and return details. ++ */ ++static bool console_emit_next_record(struct console *con, char *text, char *ext_text, ++ char *dropped_text) ++{ ++ return __console_emit_next_record(con, text, ext_text, dropped_text, NULL); ++} ++ ++static bool printer_should_wake(struct console *con, u64 seq) ++{ ++ short flags; ++ ++ if (kthread_should_stop() || !printk_kthreads_available) ++ return true; ++ ++ if (con->blocked || ++ console_kthreads_atomically_blocked() || ++ block_console_kthreads || ++ system_state > SYSTEM_RUNNING || ++ oops_in_progress) { ++ return false; ++ } ++ ++ /* ++ * This is an unsafe read from con->flags, but a false positive is ++ * not a problem. Worst case it would allow the printer to wake up ++ * although it is disabled. But the printer will notice that when ++ * attempting to print and instead go back to sleep. ++ */ ++ flags = data_race(READ_ONCE(con->flags)); ++ ++ if (!__console_is_usable(flags)) ++ return false; ++ ++ return prb_read_valid(prb, seq, NULL); ++} ++ ++static int printk_kthread_func(void *data) ++{ ++ struct console *con = data; ++ char *dropped_text = NULL; ++ char *ext_text = NULL; ++ u64 seq = 0; ++ char *text; ++ int error; ++ ++ text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL); ++ if (!text) { ++ con_printk(KERN_ERR, con, "failed to allocate text buffer\n"); ++ printk_fallback_preferred_direct(); ++ goto out; ++ } ++ ++ if (con->flags & CON_EXTENDED) { ++ ext_text = kmalloc(CONSOLE_EXT_LOG_MAX, GFP_KERNEL); ++ if (!ext_text) { ++ con_printk(KERN_ERR, con, "failed to allocate ext_text buffer\n"); ++ printk_fallback_preferred_direct(); ++ goto out; ++ } ++ } else { ++ dropped_text = kmalloc(DROPPED_TEXT_MAX, GFP_KERNEL); ++ if (!dropped_text) { ++ con_printk(KERN_ERR, con, "failed to allocate dropped_text buffer\n"); ++ printk_fallback_preferred_direct(); ++ goto out; ++ } ++ } ++ ++ con_printk(KERN_INFO, con, "printing thread started\n"); ++ for (;;) { ++ /* ++ * Guarantee this task is visible on the waitqueue before ++ * checking the wake condition. ++ * ++ * The full memory barrier within set_current_state() of ++ * prepare_to_wait_event() pairs with the full memory barrier ++ * within wq_has_sleeper(). ++ * ++ * This pairs with __wake_up_klogd:A. ++ */ ++ error = wait_event_interruptible(log_wait, ++ printer_should_wake(con, seq)); /* LMM(printk_kthread_func:A) */ ++ ++ if (kthread_should_stop() || !printk_kthreads_available) ++ break; ++ ++ if (error) ++ continue; ++ ++ error = mutex_lock_interruptible(&con->lock); ++ if (error) ++ continue; ++ ++ if (con->blocked || ++ !console_kthread_printing_tryenter()) { ++ /* Another context has locked the console_lock. */ ++ mutex_unlock(&con->lock); ++ continue; ++ } ++ ++ /* ++ * Although this context has not locked the console_lock, it ++ * is known that the console_lock is not locked and it is not ++ * possible for any other context to lock the console_lock. ++ * Therefore it is safe to read con->flags. ++ */ ++ ++ if (!__console_is_usable(con->flags)) { ++ console_kthread_printing_exit(); ++ mutex_unlock(&con->lock); ++ continue; ++ } ++ ++ /* ++ * Even though the printk kthread is always preemptible, it is ++ * still not allowed to call cond_resched() from within ++ * console drivers. The task may become non-preemptible in the ++ * console driver call chain. For example, vt_console_print() ++ * takes a spinlock and then can call into fbcon_redraw(), ++ * which can conditionally invoke cond_resched(). ++ */ ++ console_may_schedule = 0; ++ console_emit_next_record(con, text, ext_text, dropped_text); ++ ++ seq = con->seq; ++ ++ console_kthread_printing_exit(); ++ ++ mutex_unlock(&con->lock); ++ } ++ ++ con_printk(KERN_INFO, con, "printing thread stopped\n"); ++out: ++ kfree(dropped_text); ++ kfree(ext_text); ++ kfree(text); ++ ++ console_lock(); ++ /* ++ * If this kthread is being stopped by another task, con->thread will ++ * already be NULL. That is fine. The important thing is that it is ++ * NULL after the kthread exits. ++ */ ++ con->thread = NULL; ++ console_unlock(); ++ ++ return 0; ++} ++ ++/* Must be called under console_lock. */ ++static void printk_start_kthread(struct console *con) ++{ ++ /* ++ * Do not start a kthread if there is no write() callback. The ++ * kthreads assume the write() callback exists. ++ */ ++ if (!con->write) ++ return; ++ ++ con->thread = kthread_run(printk_kthread_func, con, ++ "pr/%s%d", con->name, con->index); ++ if (IS_ERR(con->thread)) { ++ con->thread = NULL; ++ con_printk(KERN_ERR, con, "unable to start printing thread\n"); ++ __printk_fallback_preferred_direct(); ++ return; ++ } ++} ++ + /* + * Delayed printk version, for scheduler-internal messages: + */ +-#define PRINTK_PENDING_WAKEUP 0x01 +-#define PRINTK_PENDING_OUTPUT 0x02 ++#define PRINTK_PENDING_WAKEUP 0x01 ++#define PRINTK_PENDING_DIRECT_OUTPUT 0x02 + + static DEFINE_PER_CPU(int, printk_pending); + +@@ -3456,10 +3913,14 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work) + { + int pending = this_cpu_xchg(printk_pending, 0); + +- if (pending & PRINTK_PENDING_OUTPUT) { ++ if (pending & PRINTK_PENDING_DIRECT_OUTPUT) { ++ printk_prefer_direct_enter(); ++ + /* If trylock fails, someone else is doing the printing */ + if (console_trylock()) + console_unlock(); ++ ++ printk_prefer_direct_exit(); + } + + if (pending & PRINTK_PENDING_WAKEUP) +@@ -3484,10 +3945,11 @@ static void __wake_up_klogd(int val) + * prepare_to_wait_event(), which is called after ___wait_event() adds + * the waiter but before it has checked the wait condition. + * +- * This pairs with devkmsg_read:A and syslog_print:A. ++ * This pairs with devkmsg_read:A, syslog_print:A, and ++ * printk_kthread_func:A. + */ + if (wq_has_sleeper(&log_wait) || /* LMM(__wake_up_klogd:A) */ +- (val & PRINTK_PENDING_OUTPUT)) { ++ (val & PRINTK_PENDING_DIRECT_OUTPUT)) { + this_cpu_or(printk_pending, val); + irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); + } +@@ -3527,7 +3989,17 @@ void defer_console_output(void) + * New messages may have been added directly to the ringbuffer + * using vprintk_store(), so wake any waiters as well. + */ +- __wake_up_klogd(PRINTK_PENDING_WAKEUP | PRINTK_PENDING_OUTPUT); ++ int val = PRINTK_PENDING_WAKEUP; ++ ++ /* ++ * Make sure that some context will print the messages when direct ++ * printing is allowed. This happens in situations when the kthreads ++ * may not be as reliable or perhaps unusable. ++ */ ++ if (allow_direct_printing()) ++ val |= PRINTK_PENDING_DIRECT_OUTPUT; ++ ++ __wake_up_klogd(val); + } + + void printk_trigger_flush(void) +diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c +index 6d10927a07d8..8e8fd2fb0a5b 100644 +--- a/kernel/printk/printk_safe.c ++++ b/kernel/printk/printk_safe.c +@@ -8,7 +8,9 @@ + #include <linux/smp.h> + #include <linux/cpumask.h> + #include <linux/printk.h> ++#include <linux/console.h> + #include <linux/kprobes.h> ++#include <linux/delay.h> + + #include "internal.h" + +@@ -45,3 +47,33 @@ asmlinkage int vprintk(const char *fmt, va_list args) + return vprintk_default(fmt, args); + } + EXPORT_SYMBOL(vprintk); ++ ++/** ++ * try_block_console_kthreads() - Try to block console kthreads and ++ * make the global console_lock() avaialble ++ * ++ * @timeout_ms: The maximum time (in ms) to wait. ++ * ++ * Prevent console kthreads from starting processing new messages. Wait ++ * until the global console_lock() become available. ++ * ++ * Context: Can be called in any context. ++ */ ++void try_block_console_kthreads(int timeout_ms) ++{ ++ block_console_kthreads = true; ++ ++ /* Do not wait when the console lock could not be safely taken. */ ++ if (this_cpu_read(printk_context) || in_nmi()) ++ return; ++ ++ while (timeout_ms > 0) { ++ if (console_trylock()) { ++ console_unlock(); ++ return; ++ } ++ ++ udelay(1000); ++ timeout_ms -= 1; ++ } ++} +diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h +index 7d15b5b5a235..7b411d663e8f 100644 +--- a/kernel/rcu/tree_stall.h ++++ b/kernel/rcu/tree_stall.h +@@ -648,6 +648,7 @@ static void print_cpu_stall(unsigned long gps) + * See Documentation/RCU/stallwarn.rst for info on how to debug + * RCU CPU stall warnings. + */ ++ printk_prefer_direct_enter(); + trace_rcu_stall_warning(rcu_state.name, TPS("SelfDetected")); + pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name); + raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags); +@@ -682,6 +683,7 @@ static void print_cpu_stall(unsigned long gps) + */ + set_tsk_need_resched(current); + set_preempt_need_resched(); ++ printk_prefer_direct_exit(); + } + + static void check_cpu_stall(struct rcu_data *rdp) +diff --git a/kernel/reboot.c b/kernel/reboot.c +index 6ebef11c8876..23a8cfed1a72 100644 +--- a/kernel/reboot.c ++++ b/kernel/reboot.c +@@ -83,6 +83,7 @@ void kernel_restart_prepare(char *cmd) + { + blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd); + system_state = SYSTEM_RESTART; ++ try_block_console_kthreads(10000); + usermodehelper_disable(); + device_shutdown(); + } +@@ -283,6 +284,7 @@ static void kernel_shutdown_prepare(enum system_states state) + blocking_notifier_call_chain(&reboot_notifier_list, + (state == SYSTEM_HALT) ? SYS_HALT : SYS_POWER_OFF, NULL); + system_state = state; ++ try_block_console_kthreads(10000); + usermodehelper_disable(); + device_shutdown(); + } +@@ -837,9 +839,11 @@ static int __orderly_reboot(void) + ret = run_cmd(reboot_cmd); + + if (ret) { ++ printk_prefer_direct_enter(); + pr_warn("Failed to start orderly reboot: forcing the issue\n"); + emergency_sync(); + kernel_restart(NULL); ++ printk_prefer_direct_exit(); + } + + return ret; +@@ -852,6 +856,7 @@ static int __orderly_poweroff(bool force) + ret = run_cmd(poweroff_cmd); + + if (ret && force) { ++ printk_prefer_direct_enter(); + pr_warn("Failed to start orderly shutdown: forcing the issue\n"); + + /* +@@ -861,6 +866,7 @@ static int __orderly_poweroff(bool force) + */ + emergency_sync(); + kernel_power_off(); ++ printk_prefer_direct_exit(); + } + + return ret; +@@ -918,6 +924,8 @@ EXPORT_SYMBOL_GPL(orderly_reboot); + */ + static void hw_failure_emergency_poweroff_func(struct work_struct *work) + { ++ printk_prefer_direct_enter(); ++ + /* + * We have reached here after the emergency shutdown waiting period has + * expired. This means orderly_poweroff has not been able to shut off +@@ -934,6 +942,8 @@ static void hw_failure_emergency_poweroff_func(struct work_struct *work) + */ + pr_emerg("Hardware protection shutdown failed. Trying emergency restart\n"); + emergency_restart(); ++ ++ printk_prefer_direct_exit(); + } + + static DECLARE_DELAYED_WORK(hw_failure_emergency_poweroff_work, +@@ -972,11 +982,13 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced) + { + static atomic_t allow_proceed = ATOMIC_INIT(1); + ++ printk_prefer_direct_enter(); ++ + pr_emerg("HARDWARE PROTECTION shutdown (%s)\n", reason); + + /* Shutdown should be initiated only once. */ + if (!atomic_dec_and_test(&allow_proceed)) +- return; ++ goto out; + + /* + * Queue a backup emergency shutdown in the event of +@@ -984,6 +996,8 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced) + */ + hw_failure_emergency_poweroff(ms_until_forced); + orderly_poweroff(true); ++out: ++ printk_prefer_direct_exit(); + } + EXPORT_SYMBOL_GPL(hw_protection_shutdown); + +diff --git a/kernel/watchdog.c b/kernel/watchdog.c +index 45693fb3e08d..f366008298ac 100644 +--- a/kernel/watchdog.c ++++ b/kernel/watchdog.c +@@ -431,6 +431,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) + /* Start period for the next softlockup warning. */ + update_report_ts(); + ++ printk_prefer_direct_enter(); ++ + pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", + smp_processor_id(), duration, + current->comm, task_pid_nr(current)); +@@ -449,6 +451,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) + add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); + if (softlockup_panic) + panic("softlockup: hung tasks"); ++ ++ printk_prefer_direct_exit(); + } + + return HRTIMER_RESTART; +diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c +index 1e8a49dc956e..7c977b945c92 100644 +--- a/kernel/watchdog_hld.c ++++ b/kernel/watchdog_hld.c +@@ -135,6 +135,8 @@ static void watchdog_overflow_callback(struct perf_event *event, + if (__this_cpu_read(hard_watchdog_warn) == true) + return; + ++ printk_prefer_direct_enter(); ++ + pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", + this_cpu); + print_modules(); +@@ -155,6 +157,8 @@ static void watchdog_overflow_callback(struct perf_event *event, + if (hardlockup_panic) + nmi_panic(regs, "Hard LOCKUP"); + ++ printk_prefer_direct_exit(); ++ + __this_cpu_write(hard_watchdog_warn, true); + return; + } +-- +2.43.0 + diff --git a/debian/patches-rt/0020-printk-add-infrastucture-for-atomic-consoles.patch b/debian/patches-rt/0020-printk-add-infrastucture-for-atomic-consoles.patch new file mode 100644 index 000000000..b86b20007 --- /dev/null +++ b/debian/patches-rt/0020-printk-add-infrastucture-for-atomic-consoles.patch @@ -0,0 +1,608 @@ +From 18343f23a5f1d466a0c74806983066efba932d5d Mon Sep 17 00:00:00 2001 +From: John Ogness <john.ogness@linutronix.de> +Date: Fri, 4 Feb 2022 16:01:17 +0106 +Subject: [PATCH 20/62] printk: add infrastucture for atomic consoles +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Many times it is not possible to see the console output on +panic because printing threads cannot be scheduled and/or the +console is already taken and forcibly overtaking/busting the +locks does provide the hoped results. + +Introduce a new infrastructure to support "atomic consoles". +A new optional callback in struct console, write_atomic(), is +available for consoles to provide an implemention for writing +console messages. The implementation must be NMI safe if they +can run on an architecture where NMIs exist. + +Console drivers implementing the write_atomic() callback must +also select CONFIG_HAVE_ATOMIC_CONSOLE in order to enable the +atomic console code within the printk subsystem. + +If atomic consoles are available, panic() will flush the kernel +log only to the atomic consoles (before busting spinlocks). +Afterwards, panic() will continue as before, which includes +attempting to flush the other (non-atomic) consoles. + +Signed-off-by: John Ogness <john.ogness@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + include/linux/console.h | 16 ++- + init/Kconfig | 4 + + kernel/panic.c | 6 +- + kernel/printk/printk.c | 293 ++++++++++++++++++++++++++++++++++++---- + 4 files changed, 290 insertions(+), 29 deletions(-) + +diff --git a/include/linux/console.h b/include/linux/console.h +index 143653090c48..8a813cbaf928 100644 +--- a/include/linux/console.h ++++ b/include/linux/console.h +@@ -138,9 +138,19 @@ static inline int con_debug_leave(void) + #define CON_BRL (32) /* Used for a braille device */ + #define CON_EXTENDED (64) /* Use the extended output format a la /dev/kmsg */ + ++#ifdef CONFIG_HAVE_ATOMIC_CONSOLE ++struct console_atomic_data { ++ u64 seq; ++ char *text; ++ char *ext_text; ++ char *dropped_text; ++}; ++#endif ++ + struct console { + char name[16]; + void (*write)(struct console *, const char *, unsigned); ++ void (*write_atomic)(struct console *, const char *, unsigned); + int (*read)(struct console *, char *, unsigned); + struct tty_driver *(*device)(struct console *, int *); + void (*unblank)(void); +@@ -153,7 +163,10 @@ struct console { + uint ispeed; + uint ospeed; + u64 seq; +- unsigned long dropped; ++ atomic_long_t dropped; ++#ifdef CONFIG_HAVE_ATOMIC_CONSOLE ++ struct console_atomic_data *atomic_data; ++#endif + struct task_struct *thread; + bool blocked; + +@@ -184,6 +197,7 @@ extern int console_set_on_cmdline; + extern struct console *early_console; + + enum con_flush_mode { ++ CONSOLE_ATOMIC_FLUSH_PENDING, + CONSOLE_FLUSH_PENDING, + CONSOLE_REPLAY_ALL, + }; +diff --git a/init/Kconfig b/init/Kconfig +index de255842f5d0..d45312780b3a 100644 +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -1582,6 +1582,10 @@ config PRINTK + very difficult to diagnose system problems, saying N here is + strongly discouraged. + ++config HAVE_ATOMIC_CONSOLE ++ bool ++ default n ++ + config BUG + bool "BUG() support" if EXPERT + default y +diff --git a/kernel/panic.c b/kernel/panic.c +index 88cd873c7c30..97cc495d95f8 100644 +--- a/kernel/panic.c ++++ b/kernel/panic.c +@@ -322,7 +322,6 @@ void panic(const char *fmt, ...) + panic_smp_self_stop(); + + console_verbose(); +- bust_spinlocks(1); + va_start(args, fmt); + len = vscnprintf(buf, sizeof(buf), fmt, args); + va_end(args); +@@ -339,6 +338,11 @@ void panic(const char *fmt, ...) + dump_stack(); + #endif + ++ /* If atomic consoles are available, flush the kernel log. */ ++ console_flush_on_panic(CONSOLE_ATOMIC_FLUSH_PENDING); ++ ++ bust_spinlocks(1); ++ + /* + * If kgdb is enabled, give it a chance to run before we stop all + * the other CPUs or else we won't be able to debug processes left +diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c +index e9f9b66608a0..73b1727087c7 100644 +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -44,6 +44,7 @@ + #include <linux/irq_work.h> + #include <linux/ctype.h> + #include <linux/uio.h> ++#include <linux/clocksource.h> + #include <linux/sched/clock.h> + #include <linux/sched/debug.h> + #include <linux/sched/task_stack.h> +@@ -2060,19 +2061,28 @@ static int console_trylock_spinning(void) + * dropped, a dropped message will be written out first. + */ + static void call_console_driver(struct console *con, const char *text, size_t len, +- char *dropped_text) ++ char *dropped_text, bool atomic_printing) + { ++ unsigned long dropped = 0; + size_t dropped_len; + +- if (con->dropped && dropped_text) { ++ if (dropped_text) ++ dropped = atomic_long_xchg_relaxed(&con->dropped, 0); ++ ++ if (dropped) { + dropped_len = snprintf(dropped_text, DROPPED_TEXT_MAX, + "** %lu printk messages dropped **\n", +- con->dropped); +- con->dropped = 0; +- con->write(con, dropped_text, dropped_len); ++ dropped); ++ if (atomic_printing) ++ con->write_atomic(con, dropped_text, dropped_len); ++ else ++ con->write(con, dropped_text, dropped_len); + } + +- con->write(con, text, len); ++ if (atomic_printing) ++ con->write_atomic(con, text, len); ++ else ++ con->write(con, text, len); + } + + /* +@@ -2430,6 +2440,76 @@ asmlinkage __visible int _printk(const char *fmt, ...) + } + EXPORT_SYMBOL(_printk); + ++#ifdef CONFIG_HAVE_ATOMIC_CONSOLE ++static void __free_atomic_data(struct console_atomic_data *d) ++{ ++ kfree(d->text); ++ kfree(d->ext_text); ++ kfree(d->dropped_text); ++} ++ ++static void free_atomic_data(struct console_atomic_data *d) ++{ ++ int count = 1; ++ int i; ++ ++ if (!d) ++ return; ++ ++#ifdef CONFIG_HAVE_NMI ++ count = 2; ++#endif ++ ++ for (i = 0; i < count; i++) ++ __free_atomic_data(&d[i]); ++ kfree(d); ++} ++ ++static int __alloc_atomic_data(struct console_atomic_data *d, short flags) ++{ ++ d->text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL); ++ if (!d->text) ++ return -1; ++ ++ if (flags & CON_EXTENDED) { ++ d->ext_text = kmalloc(CONSOLE_EXT_LOG_MAX, GFP_KERNEL); ++ if (!d->ext_text) ++ return -1; ++ } else { ++ d->dropped_text = kmalloc(DROPPED_TEXT_MAX, GFP_KERNEL); ++ if (!d->dropped_text) ++ return -1; ++ } ++ ++ return 0; ++} ++ ++static struct console_atomic_data *alloc_atomic_data(short flags) ++{ ++ struct console_atomic_data *d; ++ int count = 1; ++ int i; ++ ++#ifdef CONFIG_HAVE_NMI ++ count = 2; ++#endif ++ ++ d = kzalloc(sizeof(*d) * count, GFP_KERNEL); ++ if (!d) ++ goto err_out; ++ ++ for (i = 0; i < count; i++) { ++ if (__alloc_atomic_data(&d[i], flags) != 0) ++ goto err_out; ++ } ++ ++ return d; ++err_out: ++ free_atomic_data(d); ++ return NULL; ++} ++#endif /* CONFIG_HAVE_ATOMIC_CONSOLE */ ++ + static bool pr_flush(int timeout_ms, bool reset_on_progress); + static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress); + +@@ -2445,6 +2525,8 @@ static void printk_start_kthread(struct console *con); + #define prb_first_valid_seq(rb) 0 + #define prb_next_seq(rb) 0 + ++#define free_atomic_data(d) ++ + static u64 syslog_seq; + + static size_t record_print_text(const struct printk_record *r, +@@ -2463,7 +2545,7 @@ static ssize_t msg_print_ext_body(char *buf, size_t size, + static void console_lock_spinning_enable(void) { } + static int console_lock_spinning_disable_and_check(void) { return 0; } + static void call_console_driver(struct console *con, const char *text, size_t len, +- char *dropped_text) ++ char *dropped_text, bool atomic_printing) + { + } + static bool suppress_message_printing(int level) { return false; } +@@ -2819,10 +2901,20 @@ static inline bool __console_is_usable(short flags) + * + * Requires holding the console_lock. + */ +-static inline bool console_is_usable(struct console *con) ++static inline bool console_is_usable(struct console *con, bool atomic_printing) + { +- if (!con->write) ++ if (atomic_printing) { ++#ifdef CONFIG_HAVE_ATOMIC_CONSOLE ++ if (!con->write_atomic) ++ return false; ++ if (!con->atomic_data) ++ return false; ++#else ++ return false; ++#endif ++ } else if (!con->write) { + return false; ++ } + + return __console_is_usable(con->flags); + } +@@ -2847,6 +2939,66 @@ static void __console_unlock(void) + up_console_sem(); + } + ++static u64 read_console_seq(struct console *con) ++{ ++#ifdef CONFIG_HAVE_ATOMIC_CONSOLE ++ unsigned long flags; ++ u64 seq2; ++ u64 seq; ++ ++ if (!con->atomic_data) ++ return con->seq; ++ ++ printk_cpu_sync_get_irqsave(flags); ++ ++ seq = con->seq; ++ seq2 = con->atomic_data[0].seq; ++ if (seq2 > seq) ++ seq = seq2; ++#ifdef CONFIG_HAVE_NMI ++ seq2 = con->atomic_data[1].seq; ++ if (seq2 > seq) ++ seq = seq2; ++#endif ++ ++ printk_cpu_sync_put_irqrestore(flags); ++ ++ return seq; ++#else /* CONFIG_HAVE_ATOMIC_CONSOLE */ ++ return con->seq; ++#endif ++} ++ ++static void write_console_seq(struct console *con, u64 val, bool atomic_printing) ++{ ++#ifdef CONFIG_HAVE_ATOMIC_CONSOLE ++ unsigned long flags; ++ u64 *seq; ++ ++ if (!con->atomic_data) { ++ con->seq = val; ++ return; ++ } ++ ++ printk_cpu_sync_get_irqsave(flags); ++ ++ if (atomic_printing) { ++ seq = &con->atomic_data[0].seq; ++#ifdef CONFIG_HAVE_NMI ++ if (in_nmi()) ++ seq = &con->atomic_data[1].seq; ++#endif ++ } else { ++ seq = &con->seq; ++ } ++ *seq = val; ++ ++ printk_cpu_sync_put_irqrestore(flags); ++#else /* CONFIG_HAVE_ATOMIC_CONSOLE */ ++ con->seq = val; ++#endif ++} ++ + /* + * Print one record for the given console. The record printed is whatever + * record is the next available record for the given console. +@@ -2859,6 +3011,8 @@ static void __console_unlock(void) + * If dropped messages should be printed, @dropped_text is a buffer of size + * DROPPED_TEXT_MAX. Otherwise @dropped_text must be NULL. + * ++ * @atomic_printing specifies if atomic printing should be used. ++ * + * @handover will be set to true if a printk waiter has taken over the + * console_lock, in which case the caller is no longer holding the + * console_lock. Otherwise it is set to false. A NULL pointer may be provided +@@ -2871,7 +3025,8 @@ static void __console_unlock(void) + * Requires con->lock otherwise. + */ + static bool __console_emit_next_record(struct console *con, char *text, char *ext_text, +- char *dropped_text, bool *handover) ++ char *dropped_text, bool atomic_printing, ++ bool *handover) + { + static atomic_t panic_console_dropped = ATOMIC_INIT(0); + struct printk_info info; +@@ -2879,18 +3034,22 @@ static bool __console_emit_next_record(struct console *con, char *text, char *ex + unsigned long flags; + char *write_text; + size_t len; ++ u64 seq; + + prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); + + if (handover) + *handover = false; + +- if (!prb_read_valid(prb, con->seq, &r)) ++ seq = read_console_seq(con); ++ ++ if (!prb_read_valid(prb, seq, &r)) + return false; + +- if (con->seq != r.info->seq) { +- con->dropped += r.info->seq - con->seq; +- con->seq = r.info->seq; ++ if (seq != r.info->seq) { ++ atomic_long_add((unsigned long)(r.info->seq - seq), &con->dropped); ++ write_console_seq(con, r.info->seq, atomic_printing); ++ seq = r.info->seq; + if (panic_in_progress() && + atomic_fetch_inc_relaxed(&panic_console_dropped) > 10) { + suppress_panic_printk = 1; +@@ -2900,7 +3059,7 @@ static bool __console_emit_next_record(struct console *con, char *text, char *ex + + /* Skip record that has level above the console loglevel. */ + if (suppress_message_printing(r.info->level)) { +- con->seq++; ++ write_console_seq(con, seq + 1, atomic_printing); + goto skip; + } + +@@ -2932,9 +3091,9 @@ static bool __console_emit_next_record(struct console *con, char *text, char *ex + stop_critical_timings(); + } + +- call_console_driver(con, write_text, len, dropped_text); ++ call_console_driver(con, write_text, len, dropped_text, atomic_printing); + +- con->seq++; ++ write_console_seq(con, seq + 1, atomic_printing); + + if (handover) { + start_critical_timings(); +@@ -2966,7 +3125,7 @@ static bool console_emit_next_record_transferable(struct console *con, char *tex + handover = NULL; + } + +- return __console_emit_next_record(con, text, ext_text, dropped_text, handover); ++ return __console_emit_next_record(con, text, ext_text, dropped_text, false, handover); + } + + /* +@@ -3014,7 +3173,7 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove + for_each_console(con) { + bool progress; + +- if (!console_is_usable(con)) ++ if (!console_is_usable(con, false)) + continue; + any_usable = true; + +@@ -3049,6 +3208,68 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove + return any_usable; + } + ++#if defined(CONFIG_HAVE_ATOMIC_CONSOLE) && defined(CONFIG_PRINTK) ++static bool console_emit_next_record(struct console *con, char *text, char *ext_text, ++ char *dropped_text, bool atomic_printing); ++ ++static void atomic_console_flush_all(void) ++{ ++ unsigned long flags; ++ struct console *con; ++ bool any_progress; ++ int index = 0; ++ ++ if (console_suspended) ++ return; ++ ++#ifdef CONFIG_HAVE_NMI ++ if (in_nmi()) ++ index = 1; ++#endif ++ ++ printk_cpu_sync_get_irqsave(flags); ++ ++ do { ++ any_progress = false; ++ ++ for_each_console(con) { ++ bool progress; ++ ++ if (!console_is_usable(con, true)) ++ continue; ++ ++ if (con->flags & CON_EXTENDED) { ++ /* Extended consoles do not print "dropped messages". */ ++ progress = console_emit_next_record(con, ++ &con->atomic_data->text[index], ++ &con->atomic_data->ext_text[index], ++ NULL, ++ true); ++ } else { ++ progress = console_emit_next_record(con, ++ &con->atomic_data->text[index], ++ NULL, ++ &con->atomic_data->dropped_text[index], ++ true); ++ } ++ ++ if (!progress) ++ continue; ++ any_progress = true; ++ ++ touch_softlockup_watchdog_sync(); ++ clocksource_touch_watchdog(); ++ rcu_cpu_stall_reset(); ++ touch_nmi_watchdog(); ++ } ++ } while (any_progress); ++ ++ printk_cpu_sync_put_irqrestore(flags); ++} ++#else /* CONFIG_HAVE_ATOMIC_CONSOLE && CONFIG_PRINTK */ ++#define atomic_console_flush_all() ++#endif ++ + /** + * console_unlock - unlock the console system + * +@@ -3164,6 +3385,11 @@ void console_unblank(void) + */ + void console_flush_on_panic(enum con_flush_mode mode) + { ++ if (mode == CONSOLE_ATOMIC_FLUSH_PENDING) { ++ atomic_console_flush_all(); ++ return; ++ } ++ + /* + * If someone else is holding the console lock, trylock will fail + * and may_schedule may be set. Ignore and proceed to unlock so +@@ -3180,7 +3406,7 @@ void console_flush_on_panic(enum con_flush_mode mode) + + seq = prb_first_valid_seq(prb); + for_each_console(c) +- c->seq = seq; ++ write_console_seq(c, seq, false); + } + console_unlock(); + } +@@ -3420,19 +3646,22 @@ void register_console(struct console *newcon) + console_drivers->next = newcon; + } + +- newcon->dropped = 0; ++ atomic_long_set(&newcon->dropped, 0); + newcon->thread = NULL; + newcon->blocked = true; + mutex_init(&newcon->lock); ++#ifdef CONFIG_HAVE_ATOMIC_CONSOLE ++ newcon->atomic_data = NULL; ++#endif + + if (newcon->flags & CON_PRINTBUFFER) { + /* Get a consistent copy of @syslog_seq. */ + mutex_lock(&syslog_lock); +- newcon->seq = syslog_seq; ++ write_console_seq(newcon, syslog_seq, false); + mutex_unlock(&syslog_lock); + } else { + /* Begin with next message. */ +- newcon->seq = prb_next_seq(prb); ++ write_console_seq(newcon, prb_next_seq(prb), false); + } + + if (printk_kthreads_available) +@@ -3515,6 +3744,10 @@ int unregister_console(struct console *console) + + console_sysfs_notify(); + ++#ifdef CONFIG_HAVE_ATOMIC_CONSOLE ++ free_atomic_data(console->atomic_data); ++#endif ++ + if (console->exit) + res = console->exit(console); + +@@ -3645,7 +3878,7 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre + for_each_console(c) { + if (con && con != c) + continue; +- if (!console_is_usable(c)) ++ if (!console_is_usable(c, false)) + continue; + printk_seq = c->seq; + if (printk_seq < seq) +@@ -3734,9 +3967,10 @@ static void printk_fallback_preferred_direct(void) + * See __console_emit_next_record() for argument and return details. + */ + static bool console_emit_next_record(struct console *con, char *text, char *ext_text, +- char *dropped_text) ++ char *dropped_text, bool atomic_printing) + { +- return __console_emit_next_record(con, text, ext_text, dropped_text, NULL); ++ return __console_emit_next_record(con, text, ext_text, dropped_text, ++ atomic_printing, NULL); + } + + static bool printer_should_wake(struct console *con, u64 seq) +@@ -3777,6 +4011,11 @@ static int printk_kthread_func(void *data) + char *text; + int error; + ++#ifdef CONFIG_HAVE_ATOMIC_CONSOLE ++ if (con->write_atomic) ++ con->atomic_data = alloc_atomic_data(con->flags); ++#endif ++ + text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL); + if (!text) { + con_printk(KERN_ERR, con, "failed to allocate text buffer\n"); +@@ -3854,7 +4093,7 @@ static int printk_kthread_func(void *data) + * which can conditionally invoke cond_resched(). + */ + console_may_schedule = 0; +- console_emit_next_record(con, text, ext_text, dropped_text); ++ console_emit_next_record(con, text, ext_text, dropped_text, false); + + seq = con->seq; + +-- +2.43.0 + diff --git a/debian/patches-rt/0021-serial-8250-implement-write_atomic.patch b/debian/patches-rt/0021-serial-8250-implement-write_atomic.patch new file mode 100644 index 000000000..6a5f5abe2 --- /dev/null +++ b/debian/patches-rt/0021-serial-8250-implement-write_atomic.patch @@ -0,0 +1,938 @@ +From 08b8c0b589806331dc645a8ead6be51c174d93e0 Mon Sep 17 00:00:00 2001 +From: John Ogness <john.ogness@linutronix.de> +Date: Fri, 4 Feb 2022 16:01:17 +0106 +Subject: [PATCH 21/62] serial: 8250: implement write_atomic +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Implement a non-sleeping NMI-safe write_atomic() console function in +order to support atomic console printing during a panic. + +Trasmitting data requires disabling interrupts. Since write_atomic() +can be called from any context, it may be called while another CPU +is executing in console code. In order to maintain the correct state +of the IER register, use the global cpu_sync to synchronize all +access to the IER register. This synchronization is only necessary +for serial ports that are being used as consoles. + +The global cpu_sync is also used to synchronize between the write() +and write_atomic() callbacks. write() synchronizes per character, +write_atomic() synchronizes per line. + +Signed-off-by: John Ogness <john.ogness@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/tty/serial/8250/8250.h | 41 ++++- + drivers/tty/serial/8250/8250_aspeed_vuart.c | 2 +- + drivers/tty/serial/8250/8250_bcm7271.c | 21 ++- + drivers/tty/serial/8250/8250_core.c | 24 ++- + drivers/tty/serial/8250/8250_exar.c | 4 +- + drivers/tty/serial/8250/8250_fsl.c | 3 +- + drivers/tty/serial/8250/8250_ingenic.c | 3 +- + drivers/tty/serial/8250/8250_mtk.c | 32 +++- + drivers/tty/serial/8250/8250_omap.c | 18 +-- + drivers/tty/serial/8250/8250_port.c | 158 ++++++++++++++++---- + drivers/tty/serial/8250/Kconfig | 1 + + include/linux/serial_8250.h | 5 + + 12 files changed, 261 insertions(+), 51 deletions(-) + +diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h +index eeb7b43ebe53..b17715d340c3 100644 +--- a/drivers/tty/serial/8250/8250.h ++++ b/drivers/tty/serial/8250/8250.h +@@ -176,12 +176,49 @@ static inline void serial_dl_write(struct uart_8250_port *up, int value) + up->dl_write(up, value); + } + ++static inline int serial8250_in_IER(struct uart_8250_port *up) ++{ ++ struct uart_port *port = &up->port; ++ unsigned long flags; ++ bool is_console; ++ int ier; ++ ++ is_console = uart_console(port); ++ ++ if (is_console) ++ printk_cpu_sync_get_irqsave(flags); ++ ++ ier = serial_in(up, UART_IER); ++ ++ if (is_console) ++ printk_cpu_sync_put_irqrestore(flags); ++ ++ return ier; ++} ++ ++static inline void serial8250_set_IER(struct uart_8250_port *up, int ier) ++{ ++ struct uart_port *port = &up->port; ++ unsigned long flags; ++ bool is_console; ++ ++ is_console = uart_console(port); ++ ++ if (is_console) ++ printk_cpu_sync_get_irqsave(flags); ++ ++ serial_out(up, UART_IER, ier); ++ ++ if (is_console) ++ printk_cpu_sync_put_irqrestore(flags); ++} ++ + static inline bool serial8250_set_THRI(struct uart_8250_port *up) + { + if (up->ier & UART_IER_THRI) + return false; + up->ier |= UART_IER_THRI; +- serial_out(up, UART_IER, up->ier); ++ serial8250_set_IER(up, up->ier); + return true; + } + +@@ -190,7 +227,7 @@ static inline bool serial8250_clear_THRI(struct uart_8250_port *up) + if (!(up->ier & UART_IER_THRI)) + return false; + up->ier &= ~UART_IER_THRI; +- serial_out(up, UART_IER, up->ier); ++ serial8250_set_IER(up, up->ier); + return true; + } + +diff --git a/drivers/tty/serial/8250/8250_aspeed_vuart.c b/drivers/tty/serial/8250/8250_aspeed_vuart.c +index 9d2a7856784f..7cc6b527c088 100644 +--- a/drivers/tty/serial/8250/8250_aspeed_vuart.c ++++ b/drivers/tty/serial/8250/8250_aspeed_vuart.c +@@ -278,7 +278,7 @@ static void __aspeed_vuart_set_throttle(struct uart_8250_port *up, + up->ier &= ~irqs; + if (!throttle) + up->ier |= irqs; +- serial_out(up, UART_IER, up->ier); ++ serial8250_set_IER(up, up->ier); + } + static void aspeed_vuart_set_throttle(struct uart_port *port, bool throttle) + { +diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c +index ffc7f67e27e3..8b211e668bc0 100644 +--- a/drivers/tty/serial/8250/8250_bcm7271.c ++++ b/drivers/tty/serial/8250/8250_bcm7271.c +@@ -609,7 +609,7 @@ static int brcmuart_startup(struct uart_port *port) + * will handle this. + */ + up->ier &= ~UART_IER_RDI; +- serial_port_out(port, UART_IER, up->ier); ++ serial8250_set_IER(up, up->ier); + + priv->tx_running = false; + priv->dma.rx_dma = NULL; +@@ -775,10 +775,12 @@ static int brcmuart_handle_irq(struct uart_port *p) + unsigned int iir = serial_port_in(p, UART_IIR); + struct brcmuart_priv *priv = p->private_data; + struct uart_8250_port *up = up_to_u8250p(p); ++ unsigned long cs_flags; + unsigned int status; + unsigned long flags; + unsigned int ier; + unsigned int mcr; ++ bool is_console; + int handled = 0; + + /* +@@ -789,6 +791,10 @@ static int brcmuart_handle_irq(struct uart_port *p) + spin_lock_irqsave(&p->lock, flags); + status = serial_port_in(p, UART_LSR); + if ((status & UART_LSR_DR) == 0) { ++ is_console = uart_console(p); ++ ++ if (is_console) ++ printk_cpu_sync_get_irqsave(cs_flags); + + ier = serial_port_in(p, UART_IER); + /* +@@ -809,6 +815,9 @@ static int brcmuart_handle_irq(struct uart_port *p) + serial_port_in(p, UART_RX); + } + ++ if (is_console) ++ printk_cpu_sync_put_irqrestore(cs_flags); ++ + handled = 1; + } + spin_unlock_irqrestore(&p->lock, flags); +@@ -823,8 +832,10 @@ static enum hrtimer_restart brcmuart_hrtimer_func(struct hrtimer *t) + struct brcmuart_priv *priv = container_of(t, struct brcmuart_priv, hrt); + struct uart_port *p = priv->up; + struct uart_8250_port *up = up_to_u8250p(p); ++ unsigned long cs_flags; + unsigned int status; + unsigned long flags; ++ bool is_console; + + if (priv->shutdown) + return HRTIMER_NORESTART; +@@ -846,12 +857,20 @@ static enum hrtimer_restart brcmuart_hrtimer_func(struct hrtimer *t) + /* re-enable receive unless upper layer has disabled it */ + if ((up->ier & (UART_IER_RLSI | UART_IER_RDI)) == + (UART_IER_RLSI | UART_IER_RDI)) { ++ is_console = uart_console(p); ++ ++ if (is_console) ++ printk_cpu_sync_get_irqsave(cs_flags); ++ + status = serial_port_in(p, UART_IER); + status |= (UART_IER_RLSI | UART_IER_RDI); + serial_port_out(p, UART_IER, status); + status = serial_port_in(p, UART_MCR); + status |= UART_MCR_RTS; + serial_port_out(p, UART_MCR, status); ++ ++ if (is_console) ++ printk_cpu_sync_put_irqrestore(cs_flags); + } + spin_unlock_irqrestore(&p->lock, flags); + return HRTIMER_NORESTART; +diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c +index 81a5dab1a828..536f639ff56c 100644 +--- a/drivers/tty/serial/8250/8250_core.c ++++ b/drivers/tty/serial/8250/8250_core.c +@@ -255,8 +255,11 @@ static void serial8250_timeout(struct timer_list *t) + static void serial8250_backup_timeout(struct timer_list *t) + { + struct uart_8250_port *up = from_timer(up, t, timer); ++ struct uart_port *port = &up->port; + unsigned int iir, ier = 0, lsr; ++ unsigned long cs_flags; + unsigned long flags; ++ bool is_console; + + spin_lock_irqsave(&up->port.lock, flags); + +@@ -265,8 +268,16 @@ static void serial8250_backup_timeout(struct timer_list *t) + * based handler. + */ + if (up->port.irq) { ++ is_console = uart_console(port); ++ ++ if (is_console) ++ printk_cpu_sync_get_irqsave(cs_flags); ++ + ier = serial_in(up, UART_IER); + serial_out(up, UART_IER, 0); ++ ++ if (is_console) ++ printk_cpu_sync_put_irqrestore(cs_flags); + } + + iir = serial_in(up, UART_IIR); +@@ -289,7 +300,7 @@ static void serial8250_backup_timeout(struct timer_list *t) + serial8250_tx_chars(up); + + if (up->port.irq) +- serial_out(up, UART_IER, ier); ++ serial8250_set_IER(up, ier); + + spin_unlock_irqrestore(&up->port.lock, flags); + +@@ -575,6 +586,14 @@ serial8250_register_ports(struct uart_driver *drv, struct device *dev) + + #ifdef CONFIG_SERIAL_8250_CONSOLE + ++static void univ8250_console_write_atomic(struct console *co, const char *s, ++ unsigned int count) ++{ ++ struct uart_8250_port *up = &serial8250_ports[co->index]; ++ ++ serial8250_console_write_atomic(up, s, count); ++} ++ + static void univ8250_console_write(struct console *co, const char *s, + unsigned int count) + { +@@ -668,6 +687,7 @@ static int univ8250_console_match(struct console *co, char *name, int idx, + + static struct console univ8250_console = { + .name = "ttyS", ++ .write_atomic = univ8250_console_write_atomic, + .write = univ8250_console_write, + .device = uart_console_device, + .setup = univ8250_console_setup, +@@ -961,7 +981,7 @@ static void serial_8250_overrun_backoff_work(struct work_struct *work) + spin_lock_irqsave(&port->lock, flags); + up->ier |= UART_IER_RLSI | UART_IER_RDI; + up->port.read_status_mask |= UART_LSR_DR; +- serial_out(up, UART_IER, up->ier); ++ serial8250_set_IER(up, up->ier); + spin_unlock_irqrestore(&port->lock, flags); + } + +diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c +index b406cba10b0e..246c32c75a4c 100644 +--- a/drivers/tty/serial/8250/8250_exar.c ++++ b/drivers/tty/serial/8250/8250_exar.c +@@ -189,6 +189,8 @@ static void xr17v35x_set_divisor(struct uart_port *p, unsigned int baud, + + static int xr17v35x_startup(struct uart_port *port) + { ++ struct uart_8250_port *up = up_to_u8250p(port); ++ + /* + * First enable access to IER [7:5], ISR [5:4], FCR [5:4], + * MCR [7:5] and MSR [7:0] +@@ -199,7 +201,7 @@ static int xr17v35x_startup(struct uart_port *port) + * Make sure all interrups are masked until initialization is + * complete and the FIFOs are cleared + */ +- serial_port_out(port, UART_IER, 0); ++ serial8250_set_IER(up, 0); + + return serial8250_do_startup(port); + } +diff --git a/drivers/tty/serial/8250/8250_fsl.c b/drivers/tty/serial/8250/8250_fsl.c +index 8adfaa183f77..eaf148245a10 100644 +--- a/drivers/tty/serial/8250/8250_fsl.c ++++ b/drivers/tty/serial/8250/8250_fsl.c +@@ -58,7 +58,8 @@ int fsl8250_handle_irq(struct uart_port *port) + if ((orig_lsr & UART_LSR_OE) && (up->overrun_backoff_time_ms > 0)) { + unsigned long delay; + +- up->ier = port->serial_in(port, UART_IER); ++ up->ier = serial8250_in_IER(up); ++ + if (up->ier & (UART_IER_RLSI | UART_IER_RDI)) { + port->ops->stop_rx(port); + } else { +diff --git a/drivers/tty/serial/8250/8250_ingenic.c b/drivers/tty/serial/8250/8250_ingenic.c +index 2b2f5d8d24b9..2b78e6c394fb 100644 +--- a/drivers/tty/serial/8250/8250_ingenic.c ++++ b/drivers/tty/serial/8250/8250_ingenic.c +@@ -146,6 +146,7 @@ OF_EARLYCON_DECLARE(x1000_uart, "ingenic,x1000-uart", + + static void ingenic_uart_serial_out(struct uart_port *p, int offset, int value) + { ++ struct uart_8250_port *up = up_to_u8250p(p); + int ier; + + switch (offset) { +@@ -167,7 +168,7 @@ static void ingenic_uart_serial_out(struct uart_port *p, int offset, int value) + * If we have enabled modem status IRQs we should enable + * modem mode. + */ +- ier = p->serial_in(p, UART_IER); ++ ier = serial8250_in_IER(up); + + if (ier & UART_IER_MSI) + value |= UART_MCR_MDCE | UART_MCR_FCM; +diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c +index fb1d5ec0940e..3e7203909d6a 100644 +--- a/drivers/tty/serial/8250/8250_mtk.c ++++ b/drivers/tty/serial/8250/8250_mtk.c +@@ -222,12 +222,40 @@ static void mtk8250_shutdown(struct uart_port *port) + + static void mtk8250_disable_intrs(struct uart_8250_port *up, int mask) + { +- serial_out(up, UART_IER, serial_in(up, UART_IER) & (~mask)); ++ struct uart_port *port = &up->port; ++ unsigned long flags; ++ bool is_console; ++ int ier; ++ ++ is_console = uart_console(port); ++ ++ if (is_console) ++ printk_cpu_sync_get_irqsave(flags); ++ ++ ier = serial_in(up, UART_IER); ++ serial_out(up, UART_IER, ier & (~mask)); ++ ++ if (is_console) ++ printk_cpu_sync_put_irqrestore(flags); + } + + static void mtk8250_enable_intrs(struct uart_8250_port *up, int mask) + { +- serial_out(up, UART_IER, serial_in(up, UART_IER) | mask); ++ struct uart_port *port = &up->port; ++ unsigned long flags; ++ bool is_console; ++ int ier; ++ ++ is_console = uart_console(port); ++ ++ if (is_console) ++ printk_cpu_sync_get_irqsave(flags); ++ ++ ier = serial_in(up, UART_IER); ++ serial_out(up, UART_IER, ier | mask); ++ ++ if (is_console) ++ printk_cpu_sync_put_irqrestore(flags); + } + + static void mtk8250_set_flow_ctrl(struct uart_8250_port *up, int mode) +diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c +index 0b04d810b3e6..2b8ad5176399 100644 +--- a/drivers/tty/serial/8250/8250_omap.c ++++ b/drivers/tty/serial/8250/8250_omap.c +@@ -330,7 +330,7 @@ static void omap8250_restore_regs(struct uart_8250_port *up) + /* drop TCR + TLR access, we setup XON/XOFF later */ + serial8250_out_MCR(up, mcr); + +- serial_out(up, UART_IER, up->ier); ++ serial8250_set_IER(up, up->ier); + + serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); + serial_dl_write(up, priv->quot); +@@ -520,7 +520,7 @@ static void omap_8250_pm(struct uart_port *port, unsigned int state, + serial_out(up, UART_EFR, efr | UART_EFR_ECB); + serial_out(up, UART_LCR, 0); + +- serial_out(up, UART_IER, (state != 0) ? UART_IERX_SLEEP : 0); ++ serial8250_set_IER(up, (state != 0) ? UART_IERX_SLEEP : 0); + serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); + serial_out(up, UART_EFR, efr); + serial_out(up, UART_LCR, 0); +@@ -703,7 +703,7 @@ static int omap_8250_startup(struct uart_port *port) + goto err; + + up->ier = UART_IER_RLSI | UART_IER_RDI; +- serial_out(up, UART_IER, up->ier); ++ serial8250_set_IER(up, up->ier); + + #ifdef CONFIG_PM + up->capabilities |= UART_CAP_RPM; +@@ -744,7 +744,7 @@ static void omap_8250_shutdown(struct uart_port *port) + serial_out(up, UART_OMAP_EFR2, 0x0); + + up->ier = 0; +- serial_out(up, UART_IER, 0); ++ serial8250_set_IER(up, 0); + + if (up->dma) + serial8250_release_dma(up); +@@ -792,7 +792,7 @@ static void omap_8250_unthrottle(struct uart_port *port) + up->dma->rx_dma(up); + up->ier |= UART_IER_RLSI | UART_IER_RDI; + port->read_status_mask |= UART_LSR_DR; +- serial_out(up, UART_IER, up->ier); ++ serial8250_set_IER(up, up->ier); + spin_unlock_irqrestore(&port->lock, flags); + + pm_runtime_mark_last_busy(port->dev); +@@ -883,7 +883,7 @@ static void __dma_rx_complete(void *param) + __dma_rx_do_complete(p); + if (!priv->throttled) { + p->ier |= UART_IER_RLSI | UART_IER_RDI; +- serial_out(p, UART_IER, p->ier); ++ serial8250_set_IER(p, p->ier); + if (!(priv->habit & UART_HAS_EFR2)) + omap_8250_rx_dma(p); + } +@@ -940,7 +940,7 @@ static int omap_8250_rx_dma(struct uart_8250_port *p) + * callback to run. + */ + p->ier &= ~(UART_IER_RLSI | UART_IER_RDI); +- serial_out(p, UART_IER, p->ier); ++ serial8250_set_IER(p, p->ier); + } + goto out; + } +@@ -1153,12 +1153,12 @@ static void am654_8250_handle_rx_dma(struct uart_8250_port *up, u8 iir, + * periodic timeouts, re-enable interrupts. + */ + up->ier &= ~(UART_IER_RLSI | UART_IER_RDI); +- serial_out(up, UART_IER, up->ier); ++ serial8250_set_IER(up, up->ier); + omap_8250_rx_dma_flush(up); + serial_in(up, UART_IIR); + serial_out(up, UART_OMAP_EFR2, 0x0); + up->ier |= UART_IER_RLSI | UART_IER_RDI; +- serial_out(up, UART_IER, up->ier); ++ serial8250_set_IER(up, up->ier); + } + } + +diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c +index 8efe31448df3..975c16267196 100644 +--- a/drivers/tty/serial/8250/8250_port.c ++++ b/drivers/tty/serial/8250/8250_port.c +@@ -744,7 +744,7 @@ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep) + serial_out(p, UART_EFR, UART_EFR_ECB); + serial_out(p, UART_LCR, 0); + } +- serial_out(p, UART_IER, sleep ? UART_IERX_SLEEP : 0); ++ serial8250_set_IER(p, sleep ? UART_IERX_SLEEP : 0); + if (p->capabilities & UART_CAP_EFR) { + serial_out(p, UART_LCR, UART_LCR_CONF_MODE_B); + serial_out(p, UART_EFR, efr); +@@ -755,12 +755,29 @@ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep) + serial8250_rpm_put(p); + } + +-static void serial8250_clear_IER(struct uart_8250_port *up) ++static unsigned int serial8250_clear_IER(struct uart_8250_port *up) + { ++ struct uart_port *port = &up->port; ++ unsigned int clearval = 0; ++ unsigned long flags; ++ bool is_console; ++ unsigned int prior; ++ ++ is_console = uart_console(port); ++ + if (up->capabilities & UART_CAP_UUE) +- serial_out(up, UART_IER, UART_IER_UUE); +- else +- serial_out(up, UART_IER, 0); ++ clearval = UART_IER_UUE; ++ ++ if (is_console) ++ printk_cpu_sync_get_irqsave(flags); ++ ++ prior = serial_in(up, UART_IER); ++ serial_out(up, UART_IER, clearval); ++ ++ if (is_console) ++ printk_cpu_sync_put_irqrestore(flags); ++ ++ return prior; + } + + #ifdef CONFIG_SERIAL_8250_RSA +@@ -1026,8 +1043,11 @@ static int broken_efr(struct uart_8250_port *up) + */ + static void autoconfig_16550a(struct uart_8250_port *up) + { ++ struct uart_port *port = &up->port; + unsigned char status1, status2; + unsigned int iersave; ++ unsigned long flags; ++ bool is_console; + + up->port.type = PORT_16550A; + up->capabilities |= UART_CAP_FIFO; +@@ -1139,6 +1159,11 @@ static void autoconfig_16550a(struct uart_8250_port *up) + return; + } + ++ is_console = uart_console(port); ++ ++ if (is_console) ++ printk_cpu_sync_get_irqsave(flags); ++ + /* + * Try writing and reading the UART_IER_UUE bit (b6). + * If it works, this is probably one of the Xscale platform's +@@ -1174,6 +1199,9 @@ static void autoconfig_16550a(struct uart_8250_port *up) + } + serial_out(up, UART_IER, iersave); + ++ if (is_console) ++ printk_cpu_sync_put_irqrestore(flags); ++ + /* + * We distinguish between 16550A and U6 16550A by counting + * how many bytes are in the FIFO. +@@ -1196,8 +1224,10 @@ static void autoconfig(struct uart_8250_port *up) + unsigned char status1, scratch, scratch2, scratch3; + unsigned char save_lcr, save_mcr; + struct uart_port *port = &up->port; ++ unsigned long cs_flags; + unsigned long flags; + unsigned int old_capabilities; ++ bool is_console; + + if (!port->iobase && !port->mapbase && !port->membase) + return; +@@ -1215,6 +1245,11 @@ static void autoconfig(struct uart_8250_port *up) + up->bugs = 0; + + if (!(port->flags & UPF_BUGGY_UART)) { ++ is_console = uart_console(port); ++ ++ if (is_console) ++ printk_cpu_sync_get_irqsave(cs_flags); ++ + /* + * Do a simple existence test first; if we fail this, + * there's no point trying anything else. +@@ -1244,6 +1279,10 @@ static void autoconfig(struct uart_8250_port *up) + #endif + scratch3 = serial_in(up, UART_IER) & 0x0f; + serial_out(up, UART_IER, scratch); ++ ++ if (is_console) ++ printk_cpu_sync_put_irqrestore(cs_flags); ++ + if (scratch2 != 0 || scratch3 != 0x0F) { + /* + * We failed; there's nothing here +@@ -1367,7 +1406,9 @@ static void autoconfig_irq(struct uart_8250_port *up) + unsigned char save_mcr, save_ier; + unsigned char save_ICP = 0; + unsigned int ICP = 0; ++ unsigned long flags; + unsigned long irqs; ++ bool is_console; + int irq; + + if (port->flags & UPF_FOURPORT) { +@@ -1377,8 +1418,12 @@ static void autoconfig_irq(struct uart_8250_port *up) + inb_p(ICP); + } + +- if (uart_console(port)) ++ is_console = uart_console(port); ++ ++ if (is_console) { + console_lock(); ++ printk_cpu_sync_get_irqsave(flags); ++ } + + /* forget possible initially masked and pending IRQ */ + probe_irq_off(probe_irq_on()); +@@ -1410,8 +1455,10 @@ static void autoconfig_irq(struct uart_8250_port *up) + if (port->flags & UPF_FOURPORT) + outb_p(save_ICP, ICP); + +- if (uart_console(port)) ++ if (is_console) { ++ printk_cpu_sync_put_irqrestore(flags); + console_unlock(); ++ } + + port->irq = (irq > 0) ? irq : 0; + } +@@ -1424,7 +1471,7 @@ static void serial8250_stop_rx(struct uart_port *port) + + up->ier &= ~(UART_IER_RLSI | UART_IER_RDI); + up->port.read_status_mask &= ~UART_LSR_DR; +- serial_port_out(port, UART_IER, up->ier); ++ serial8250_set_IER(up, up->ier); + + serial8250_rpm_put(up); + } +@@ -1454,7 +1501,7 @@ void serial8250_em485_stop_tx(struct uart_8250_port *p) + serial8250_clear_and_reinit_fifos(p); + + p->ier |= UART_IER_RLSI | UART_IER_RDI; +- serial_port_out(&p->port, UART_IER, p->ier); ++ serial8250_set_IER(p, p->ier); + } + } + EXPORT_SYMBOL_GPL(serial8250_em485_stop_tx); +@@ -1703,7 +1750,7 @@ static void serial8250_disable_ms(struct uart_port *port) + mctrl_gpio_disable_ms(up->gpios); + + up->ier &= ~UART_IER_MSI; +- serial_port_out(port, UART_IER, up->ier); ++ serial8250_set_IER(up, up->ier); + } + + static void serial8250_enable_ms(struct uart_port *port) +@@ -1719,7 +1766,7 @@ static void serial8250_enable_ms(struct uart_port *port) + up->ier |= UART_IER_MSI; + + serial8250_rpm_get(up); +- serial_port_out(port, UART_IER, up->ier); ++ serial8250_set_IER(up, up->ier); + serial8250_rpm_put(up); + } + +@@ -2174,8 +2221,7 @@ static void serial8250_put_poll_char(struct uart_port *port, + /* + * First save the IER then disable the interrupts + */ +- ier = serial_port_in(port, UART_IER); +- serial8250_clear_IER(up); ++ ier = serial8250_clear_IER(up); + + wait_for_xmitr(up, UART_LSR_BOTH_EMPTY); + /* +@@ -2188,7 +2234,7 @@ static void serial8250_put_poll_char(struct uart_port *port, + * and restore the IER + */ + wait_for_xmitr(up, UART_LSR_BOTH_EMPTY); +- serial_port_out(port, UART_IER, ier); ++ serial8250_set_IER(up, ier); + serial8250_rpm_put(up); + } + +@@ -2197,8 +2243,10 @@ static void serial8250_put_poll_char(struct uart_port *port, + int serial8250_do_startup(struct uart_port *port) + { + struct uart_8250_port *up = up_to_u8250p(port); ++ unsigned long cs_flags; + unsigned long flags; + unsigned char iir; ++ bool is_console; + int retval; + u16 lsr; + +@@ -2219,7 +2267,7 @@ int serial8250_do_startup(struct uart_port *port) + up->acr = 0; + serial_port_out(port, UART_LCR, UART_LCR_CONF_MODE_B); + serial_port_out(port, UART_EFR, UART_EFR_ECB); +- serial_port_out(port, UART_IER, 0); ++ serial8250_set_IER(up, 0); + serial_port_out(port, UART_LCR, 0); + serial_icr_write(up, UART_CSR, 0); /* Reset the UART */ + serial_port_out(port, UART_LCR, UART_LCR_CONF_MODE_B); +@@ -2229,7 +2277,7 @@ int serial8250_do_startup(struct uart_port *port) + + if (port->type == PORT_DA830) { + /* Reset the port */ +- serial_port_out(port, UART_IER, 0); ++ serial8250_set_IER(up, 0); + serial_port_out(port, UART_DA830_PWREMU_MGMT, 0); + mdelay(10); + +@@ -2328,6 +2376,8 @@ int serial8250_do_startup(struct uart_port *port) + if (retval) + goto out; + ++ is_console = uart_console(port); ++ + if (port->irq && !(up->port.flags & UPF_NO_THRE_TEST)) { + unsigned char iir1; + +@@ -2344,6 +2394,9 @@ int serial8250_do_startup(struct uart_port *port) + */ + spin_lock_irqsave(&port->lock, flags); + ++ if (is_console) ++ printk_cpu_sync_get_irqsave(cs_flags); ++ + wait_for_xmitr(up, UART_LSR_THRE); + serial_port_out_sync(port, UART_IER, UART_IER_THRI); + udelay(1); /* allow THRE to set */ +@@ -2354,6 +2407,9 @@ int serial8250_do_startup(struct uart_port *port) + iir = serial_port_in(port, UART_IIR); + serial_port_out(port, UART_IER, 0); + ++ if (is_console) ++ printk_cpu_sync_put_irqrestore(cs_flags); ++ + spin_unlock_irqrestore(&port->lock, flags); + + if (port->irqflags & IRQF_SHARED) +@@ -2408,10 +2464,14 @@ int serial8250_do_startup(struct uart_port *port) + * Do a quick test to see if we receive an interrupt when we enable + * the TX irq. + */ ++ if (is_console) ++ printk_cpu_sync_get_irqsave(cs_flags); + serial_port_out(port, UART_IER, UART_IER_THRI); + lsr = serial_port_in(port, UART_LSR); + iir = serial_port_in(port, UART_IIR); + serial_port_out(port, UART_IER, 0); ++ if (is_console) ++ printk_cpu_sync_put_irqrestore(cs_flags); + + if (lsr & UART_LSR_TEMT && iir & UART_IIR_NO_INT) { + if (!(up->bugs & UART_BUG_TXEN)) { +@@ -2443,7 +2503,7 @@ int serial8250_do_startup(struct uart_port *port) + if (up->dma) { + const char *msg = NULL; + +- if (uart_console(port)) ++ if (is_console) + msg = "forbid DMA for kernel console"; + else if (serial8250_request_dma(up)) + msg = "failed to request DMA"; +@@ -2494,7 +2554,7 @@ void serial8250_do_shutdown(struct uart_port *port) + */ + spin_lock_irqsave(&port->lock, flags); + up->ier = 0; +- serial_port_out(port, UART_IER, 0); ++ serial8250_set_IER(up, 0); + spin_unlock_irqrestore(&port->lock, flags); + + synchronize_irq(port->irq); +@@ -2856,7 +2916,7 @@ serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, + if (up->capabilities & UART_CAP_RTOIE) + up->ier |= UART_IER_RTOIE; + +- serial_port_out(port, UART_IER, up->ier); ++ serial8250_set_IER(up, up->ier); + + if (up->capabilities & UART_CAP_EFR) { + unsigned char efr = 0; +@@ -3321,7 +3381,7 @@ EXPORT_SYMBOL_GPL(serial8250_set_defaults); + + #ifdef CONFIG_SERIAL_8250_CONSOLE + +-static void serial8250_console_putchar(struct uart_port *port, unsigned char ch) ++static void serial8250_console_putchar_locked(struct uart_port *port, unsigned char ch) + { + struct uart_8250_port *up = up_to_u8250p(port); + +@@ -3329,6 +3389,18 @@ static void serial8250_console_putchar(struct uart_port *port, unsigned char ch) + serial_port_out(port, UART_TX, ch); + } + ++static void serial8250_console_putchar(struct uart_port *port, unsigned char ch) ++{ ++ struct uart_8250_port *up = up_to_u8250p(port); ++ unsigned long flags; ++ ++ wait_for_xmitr(up, UART_LSR_THRE); ++ ++ printk_cpu_sync_get_irqsave(flags); ++ serial8250_console_putchar_locked(port, ch); ++ printk_cpu_sync_put_irqrestore(flags); ++} ++ + /* + * Restore serial console when h/w power-off detected + */ +@@ -3355,6 +3427,32 @@ static void serial8250_console_restore(struct uart_8250_port *up) + serial8250_out_MCR(up, up->mcr | UART_MCR_DTR | UART_MCR_RTS); + } + ++void serial8250_console_write_atomic(struct uart_8250_port *up, ++ const char *s, unsigned int count) ++{ ++ struct uart_port *port = &up->port; ++ unsigned long flags; ++ unsigned int ier; ++ ++ printk_cpu_sync_get_irqsave(flags); ++ ++ touch_nmi_watchdog(); ++ ++ ier = serial8250_clear_IER(up); ++ ++ if (atomic_fetch_inc(&up->console_printing)) { ++ uart_console_write(port, "\n", 1, ++ serial8250_console_putchar_locked); ++ } ++ uart_console_write(port, s, count, serial8250_console_putchar_locked); ++ atomic_dec(&up->console_printing); ++ ++ wait_for_xmitr(up, UART_LSR_BOTH_EMPTY); ++ serial8250_set_IER(up, ier); ++ ++ printk_cpu_sync_put_irqrestore(flags); ++} ++ + /* + * Print a string to the serial port using the device FIFO + * +@@ -3400,20 +3498,15 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, + struct uart_port *port = &up->port; + unsigned long flags; + unsigned int ier, use_fifo; +- int locked = 1; + + touch_nmi_watchdog(); + +- if (oops_in_progress) +- locked = spin_trylock_irqsave(&port->lock, flags); +- else +- spin_lock_irqsave(&port->lock, flags); ++ spin_lock_irqsave(&port->lock, flags); + + /* + * First save the IER then disable the interrupts + */ +- ier = serial_port_in(port, UART_IER); +- serial8250_clear_IER(up); ++ ier = serial8250_clear_IER(up); + + /* check scratch reg to see if port powered off during system sleep */ + if (up->canary && (up->canary != serial_port_in(port, UART_SCR))) { +@@ -3447,10 +3540,12 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, + */ + !(up->port.flags & UPF_CONS_FLOW); + ++ atomic_inc(&up->console_printing); + if (likely(use_fifo)) + serial8250_console_fifo_write(up, s, count); + else + uart_console_write(port, s, count, serial8250_console_putchar); ++ atomic_dec(&up->console_printing); + + /* + * Finally, wait for transmitter to become empty +@@ -3463,8 +3558,7 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, + if (em485->tx_stopped) + up->rs485_stop_tx(up); + } +- +- serial_port_out(port, UART_IER, ier); ++ serial8250_set_IER(up, ier); + + /* + * The receive handling will happen properly because the +@@ -3476,8 +3570,7 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, + if (up->msr_saved_flags) + serial8250_modem_status(up); + +- if (locked) +- spin_unlock_irqrestore(&port->lock, flags); ++ spin_unlock_irqrestore(&port->lock, flags); + } + + static unsigned int probe_baud(struct uart_port *port) +@@ -3497,6 +3590,7 @@ static unsigned int probe_baud(struct uart_port *port) + + int serial8250_console_setup(struct uart_port *port, char *options, bool probe) + { ++ struct uart_8250_port *up = up_to_u8250p(port); + int baud = 9600; + int bits = 8; + int parity = 'n'; +@@ -3506,6 +3600,8 @@ int serial8250_console_setup(struct uart_port *port, char *options, bool probe) + if (!port->iobase && !port->membase) + return -ENODEV; + ++ atomic_set(&up->console_printing, 0); ++ + if (options) + uart_parse_options(options, &baud, &parity, &bits, &flow); + else if (probe) +diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig +index 583a340f9934..1f31320820a6 100644 +--- a/drivers/tty/serial/8250/Kconfig ++++ b/drivers/tty/serial/8250/Kconfig +@@ -9,6 +9,7 @@ config SERIAL_8250 + depends on !S390 + select SERIAL_CORE + select SERIAL_MCTRL_GPIO if GPIOLIB ++ select HAVE_ATOMIC_CONSOLE + help + This selects whether you want to include the driver for the standard + serial ports. The standard answer is Y. People who might say N +diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h +index 79b328861c5f..35f44352e641 100644 +--- a/include/linux/serial_8250.h ++++ b/include/linux/serial_8250.h +@@ -7,6 +7,7 @@ + #ifndef _LINUX_SERIAL_8250_H + #define _LINUX_SERIAL_8250_H + ++#include <linux/atomic.h> + #include <linux/serial_core.h> + #include <linux/serial_reg.h> + #include <linux/platform_device.h> +@@ -124,6 +125,8 @@ struct uart_8250_port { + #define MSR_SAVE_FLAGS UART_MSR_ANY_DELTA + unsigned char msr_saved_flags; + ++ atomic_t console_printing; ++ + struct uart_8250_dma *dma; + const struct uart_8250_ops *ops; + +@@ -179,6 +182,8 @@ void serial8250_init_port(struct uart_8250_port *up); + void serial8250_set_defaults(struct uart_8250_port *up); + void serial8250_console_write(struct uart_8250_port *up, const char *s, + unsigned int count); ++void serial8250_console_write_atomic(struct uart_8250_port *up, const char *s, ++ unsigned int count); + int serial8250_console_setup(struct uart_port *port, char *options, bool probe); + int serial8250_console_exit(struct uart_port *port); + +-- +2.43.0 + diff --git a/debian/patches-rt/0022-printk-avoid-preempt_disable-for-PREEMPT_RT.patch b/debian/patches-rt/0022-printk-avoid-preempt_disable-for-PREEMPT_RT.patch new file mode 100644 index 000000000..ff28f79d9 --- /dev/null +++ b/debian/patches-rt/0022-printk-avoid-preempt_disable-for-PREEMPT_RT.patch @@ -0,0 +1,96 @@ +From a549c0dff2a1a3b11b40abc969358d8cb367871d Mon Sep 17 00:00:00 2001 +From: John Ogness <john.ogness@linutronix.de> +Date: Fri, 4 Feb 2022 16:01:17 +0106 +Subject: [PATCH 22/62] printk: avoid preempt_disable() for PREEMPT_RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +During non-normal operation, printk() calls will attempt to +write the messages directly to the consoles. This involves +using console_trylock() to acquire @console_sem. + +Preemption is disabled while directly printing to the consoles +in order to ensure that the printing task is not scheduled away +while holding @console_sem, thus blocking all other printers +and causing delays in printing. + +Commit fd5f7cde1b85 ("printk: Never set console_may_schedule in +console_trylock()") specifically reverted a previous attempt at +allowing preemption while printing. + +However, on PREEMPT_RT systems, disabling preemption while +printing is not allowed because console drivers typically +acquire a spin lock (which under PREEMPT_RT is an rtmutex). +Since direct printing is only used during early boot and +non-panic dumps, the risks of delayed print output for these +scenarios will be accepted under PREEMPT_RT. + +Signed-off-by: John Ogness <john.ogness@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + kernel/printk/printk.c | 21 ++++++++++++++++++++- + 1 file changed, 20 insertions(+), 1 deletion(-) + +diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c +index 73b1727087c7..3d0ff49cca29 100644 +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -1981,6 +1981,7 @@ static int console_lock_spinning_disable_and_check(void) + return 1; + } + ++#if !IS_ENABLED(CONFIG_PREEMPT_RT) + /** + * console_trylock_spinning - try to get console_lock by busy waiting + * +@@ -2054,6 +2055,7 @@ static int console_trylock_spinning(void) + + return 1; + } ++#endif /* CONFIG_PREEMPT_RT */ + + /* + * Call the specified console driver, asking it to write out the specified +@@ -2393,6 +2395,18 @@ asmlinkage int vprintk_emit(int facility, int level, + + /* If called from the scheduler, we can not call up(). */ + if (!in_sched && allow_direct_printing()) { ++#if IS_ENABLED(CONFIG_PREEMPT_RT) ++ /* ++ * Use the non-spinning trylock since PREEMPT_RT does not ++ * support console lock handovers. ++ * ++ * Direct printing will most likely involve taking spinlocks. ++ * For PREEMPT_RT, this is only allowed if in a preemptible ++ * context. ++ */ ++ if (preemptible() && console_trylock()) ++ console_unlock(); ++#else + /* + * The caller may be holding system-critical or + * timing-sensitive locks. Disable preemption during direct +@@ -2410,6 +2424,7 @@ asmlinkage int vprintk_emit(int facility, int level, + if (console_trylock_spinning()) + console_unlock(); + preempt_enable(); ++#endif + } + + if (in_sched) +@@ -3119,8 +3134,12 @@ static bool console_emit_next_record_transferable(struct console *con, char *tex + /* + * Handovers are only supported if threaded printers are atomically + * blocked. The context taking over the console_lock may be atomic. ++ * ++ * PREEMPT_RT also does not support handovers because the spinning ++ * waiter can cause large latencies. + */ +- if (!console_kthreads_atomically_blocked()) { ++ if (!console_kthreads_atomically_blocked() || ++ IS_ENABLED(CONFIG_PREEMPT_RT)) { + *handover = false; + handover = NULL; + } +-- +2.43.0 + diff --git a/debian/patches-rt/0023-drm-i915-Use-preempt_disable-enable_rt-where-recomme.patch b/debian/patches-rt/0023-drm-i915-Use-preempt_disable-enable_rt-where-recomme.patch new file mode 100644 index 000000000..dcee3a6dc --- /dev/null +++ b/debian/patches-rt/0023-drm-i915-Use-preempt_disable-enable_rt-where-recomme.patch @@ -0,0 +1,62 @@ +From f99a0874dccc1ba9f9ead4473ba09603d10946b4 Mon Sep 17 00:00:00 2001 +From: Mike Galbraith <umgwanakikbuti@gmail.com> +Date: Sat, 27 Feb 2016 08:09:11 +0100 +Subject: [PATCH 23/62] drm/i915: Use preempt_disable/enable_rt() where + recommended +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Mario Kleiner suggest in commit + ad3543ede630f ("drm/intel: Push get_scanout_position() timestamping into kms driver.") + +a spots where preemption should be disabled on PREEMPT_RT. The +difference is that on PREEMPT_RT the intel_uncore::lock disables neither +preemption nor interrupts and so region remains preemptible. + +The area covers only register reads and writes. The part that worries me +is: +- __intel_get_crtc_scanline() the worst case is 100us if no match is + found. + +- intel_crtc_scanlines_since_frame_timestamp() not sure how long this + may take in the worst case. + +It was in the RT queue for a while and nobody complained. +Disable preemption on PREEPMPT_RT during timestamping. + +[bigeasy: patch description.] + +Cc: Mario Kleiner <mario.kleiner.de@gmail.com> +Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/gpu/drm/i915/i915_irq.c | 6 ++++-- + 1 file changed, 4 insertions(+), 2 deletions(-) + +diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c +index f93ffa6626a5..6e9d033cf808 100644 +--- a/drivers/gpu/drm/i915/i915_irq.c ++++ b/drivers/gpu/drm/i915/i915_irq.c +@@ -917,7 +917,8 @@ static bool i915_get_crtc_scanoutpos(struct drm_crtc *_crtc, + */ + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + +- /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ ++ if (IS_ENABLED(CONFIG_PREEMPT_RT)) ++ preempt_disable(); + + /* Get optional system timestamp before query. */ + if (stime) +@@ -981,7 +982,8 @@ static bool i915_get_crtc_scanoutpos(struct drm_crtc *_crtc, + if (etime) + *etime = ktime_get(); + +- /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ ++ if (IS_ENABLED(CONFIG_PREEMPT_RT)) ++ preempt_enable(); + + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); + +-- +2.43.0 + diff --git a/debian/patches-rt/0024-drm-i915-Don-t-disable-interrupts-on-PREEMPT_RT-duri.patch b/debian/patches-rt/0024-drm-i915-Don-t-disable-interrupts-on-PREEMPT_RT-duri.patch new file mode 100644 index 000000000..c05066850 --- /dev/null +++ b/debian/patches-rt/0024-drm-i915-Don-t-disable-interrupts-on-PREEMPT_RT-duri.patch @@ -0,0 +1,91 @@ +From 7540de1a42a1a7409b4367b67c76480f7e96d25b Mon Sep 17 00:00:00 2001 +From: Mike Galbraith <umgwanakikbuti@gmail.com> +Date: Sat, 27 Feb 2016 09:01:42 +0100 +Subject: [PATCH 24/62] drm/i915: Don't disable interrupts on PREEMPT_RT during + atomic updates +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Commit + 8d7849db3eab7 ("drm/i915: Make sprite updates atomic") + +started disabling interrupts across atomic updates. This breaks on PREEMPT_RT +because within this section the code attempt to acquire spinlock_t locks which +are sleeping locks on PREEMPT_RT. + +According to the comment the interrupts are disabled to avoid random delays and +not required for protection or synchronisation. +If this needs to happen with disabled interrupts on PREEMPT_RT, and the +whole section is restricted to register access then all sleeping locks +need to be acquired before interrupts are disabled and some function +maybe moved after enabling interrupts again. +This includes: +- prepare_to_wait() + finish_wait() due its wake queue. +- drm_crtc_vblank_put() -> vblank_disable_fn() drm_device::vbl_lock. +- skl_pfit_enable(), intel_update_plane(), vlv_atomic_update_fifo() and + maybe others due to intel_uncore::lock +- drm_crtc_arm_vblank_event() due to drm_device::event_lock and + drm_device::vblank_time_lock. + +Don't disable interrupts on PREEMPT_RT during atomic updates. + +[bigeasy: drop local locks, commit message] + +Signed-off-by: Mike Galbraith <umgwanakikbuti@gmail.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/gpu/drm/i915/display/intel_crtc.c | 15 ++++++++++----- + 1 file changed, 10 insertions(+), 5 deletions(-) + +diff --git a/drivers/gpu/drm/i915/display/intel_crtc.c b/drivers/gpu/drm/i915/display/intel_crtc.c +index 6792a9056f46..43cedfef104f 100644 +--- a/drivers/gpu/drm/i915/display/intel_crtc.c ++++ b/drivers/gpu/drm/i915/display/intel_crtc.c +@@ -521,7 +521,8 @@ void intel_pipe_update_start(struct intel_crtc_state *new_crtc_state) + */ + intel_psr_wait_for_idle_locked(new_crtc_state); + +- local_irq_disable(); ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ++ local_irq_disable(); + + crtc->debug.min_vbl = min; + crtc->debug.max_vbl = max; +@@ -546,11 +547,13 @@ void intel_pipe_update_start(struct intel_crtc_state *new_crtc_state) + break; + } + +- local_irq_enable(); ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ++ local_irq_enable(); + + timeout = schedule_timeout(timeout); + +- local_irq_disable(); ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ++ local_irq_disable(); + } + + finish_wait(wq, &wait); +@@ -583,7 +586,8 @@ void intel_pipe_update_start(struct intel_crtc_state *new_crtc_state) + return; + + irq_disable: +- local_irq_disable(); ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ++ local_irq_disable(); + } + + #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_VBLANK_EVADE) +@@ -684,7 +688,8 @@ void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state) + */ + intel_vrr_send_push(new_crtc_state); + +- local_irq_enable(); ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ++ local_irq_enable(); + + if (intel_vgpu_active(dev_priv)) + return; +-- +2.43.0 + diff --git a/debian/patches-rt/0025-drm-i915-Don-t-check-for-atomic-context-on-PREEMPT_R.patch b/debian/patches-rt/0025-drm-i915-Don-t-check-for-atomic-context-on-PREEMPT_R.patch new file mode 100644 index 000000000..2bbcdfed9 --- /dev/null +++ b/debian/patches-rt/0025-drm-i915-Don-t-check-for-atomic-context-on-PREEMPT_R.patch @@ -0,0 +1,36 @@ +From d9970290d810087f44a37de7ae6f3638ecddd3a0 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 25 Oct 2021 15:05:18 +0200 +Subject: [PATCH 25/62] drm/i915: Don't check for atomic context on PREEMPT_RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +The !in_atomic() check in _wait_for_atomic() triggers on PREEMPT_RT +because the uncore::lock is a spinlock_t and does not disable +preemption or interrupts. + +Changing the uncore:lock to a raw_spinlock_t doubles the worst case +latency on an otherwise idle testbox during testing. Therefore I'm +currently unsure about changing this. + +Link: https://lore.kernel.org/all/20211006164628.s2mtsdd2jdbfyf7g@linutronix.de/ +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/gpu/drm/i915/i915_utils.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h +index 6c14d13364bf..de58855e6926 100644 +--- a/drivers/gpu/drm/i915/i915_utils.h ++++ b/drivers/gpu/drm/i915/i915_utils.h +@@ -294,7 +294,7 @@ wait_remaining_ms_from_jiffies(unsigned long timestamp_jiffies, int to_wait_ms) + #define wait_for(COND, MS) _wait_for((COND), (MS) * 1000, 10, 1000) + + /* If CONFIG_PREEMPT_COUNT is disabled, in_atomic() always reports false. */ +-#if defined(CONFIG_DRM_I915_DEBUG) && defined(CONFIG_PREEMPT_COUNT) ++#if defined(CONFIG_DRM_I915_DEBUG) && defined(CONFIG_PREEMPT_COUNT) && !defined(CONFIG_PREEMPT_RT) + # define _WAIT_FOR_ATOMIC_CHECK(ATOMIC) WARN_ON_ONCE((ATOMIC) && !in_atomic()) + #else + # define _WAIT_FOR_ATOMIC_CHECK(ATOMIC) do { } while (0) +-- +2.43.0 + diff --git a/debian/patches-rt/0026-drm-i915-Disable-tracing-points-on-PREEMPT_RT.patch b/debian/patches-rt/0026-drm-i915-Disable-tracing-points-on-PREEMPT_RT.patch new file mode 100644 index 000000000..bcd36cace --- /dev/null +++ b/debian/patches-rt/0026-drm-i915-Disable-tracing-points-on-PREEMPT_RT.patch @@ -0,0 +1,51 @@ +From 05b1ad300df55e576476a0dee533c90068480372 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Thu, 6 Dec 2018 09:52:20 +0100 +Subject: [PATCH 26/62] drm/i915: Disable tracing points on PREEMPT_RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Luca Abeni reported this: +| BUG: scheduling while atomic: kworker/u8:2/15203/0x00000003 +| CPU: 1 PID: 15203 Comm: kworker/u8:2 Not tainted 4.19.1-rt3 #10 +| Call Trace: +| rt_spin_lock+0x3f/0x50 +| gen6_read32+0x45/0x1d0 [i915] +| g4x_get_vblank_counter+0x36/0x40 [i915] +| trace_event_raw_event_i915_pipe_update_start+0x7d/0xf0 [i915] + +The tracing events use trace_i915_pipe_update_start() among other events +use functions acquire spinlock_t locks which are transformed into +sleeping locks on PREEMPT_RT. A few trace points use +intel_get_crtc_scanline(), others use ->get_vblank_counter() wich also +might acquire a sleeping locks on PREEMPT_RT. +At the time the arguments are evaluated within trace point, preemption +is disabled and so the locks must not be acquired on PREEMPT_RT. + +Based on this I don't see any other way than disable trace points on +PREMPT_RT. + +Reported-by: Luca Abeni <lucabe72@gmail.com> +Cc: Steven Rostedt <rostedt@goodmis.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/gpu/drm/i915/i915_trace.h | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h +index 37b5c9e9d260..1434485cb536 100644 +--- a/drivers/gpu/drm/i915/i915_trace.h ++++ b/drivers/gpu/drm/i915/i915_trace.h +@@ -6,6 +6,10 @@ + #if !defined(_I915_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) + #define _I915_TRACE_H_ + ++#ifdef CONFIG_PREEMPT_RT ++#define NOTRACE ++#endif ++ + #include <linux/stringify.h> + #include <linux/types.h> + #include <linux/tracepoint.h> +-- +2.43.0 + diff --git a/debian/patches-rt/0027-drm-i915-skip-DRM_I915_LOW_LEVEL_TRACEPOINTS-with-NO.patch b/debian/patches-rt/0027-drm-i915-skip-DRM_I915_LOW_LEVEL_TRACEPOINTS-with-NO.patch new file mode 100644 index 000000000..77fa1b420 --- /dev/null +++ b/debian/patches-rt/0027-drm-i915-skip-DRM_I915_LOW_LEVEL_TRACEPOINTS-with-NO.patch @@ -0,0 +1,35 @@ +From 1fcbddeff5b9a56382a6ba0aba49578f8cdf9aa4 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 19 Dec 2018 10:47:02 +0100 +Subject: [PATCH 27/62] drm/i915: skip DRM_I915_LOW_LEVEL_TRACEPOINTS with + NOTRACE +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +The order of the header files is important. If this header file is +included after tracepoint.h was included then the NOTRACE here becomes a +nop. Currently this happens for two .c files which use the tracepoitns +behind DRM_I915_LOW_LEVEL_TRACEPOINTS. + +Cc: Steven Rostedt <rostedt@goodmis.org> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + drivers/gpu/drm/i915/i915_trace.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h +index 1434485cb536..73f29d8008f0 100644 +--- a/drivers/gpu/drm/i915/i915_trace.h ++++ b/drivers/gpu/drm/i915/i915_trace.h +@@ -327,7 +327,7 @@ DEFINE_EVENT(i915_request, i915_request_add, + TP_ARGS(rq) + ); + +-#if defined(CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS) ++#if defined(CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS) && !defined(NOTRACE) + DEFINE_EVENT(i915_request, i915_request_guc_submit, + TP_PROTO(struct i915_request *rq), + TP_ARGS(rq) +-- +2.43.0 + diff --git a/debian/patches-rt/0028-drm-i915-gt-Queue-and-wait-for-the-irq_work-item.patch b/debian/patches-rt/0028-drm-i915-gt-Queue-and-wait-for-the-irq_work-item.patch new file mode 100644 index 000000000..61bd48e8b --- /dev/null +++ b/debian/patches-rt/0028-drm-i915-gt-Queue-and-wait-for-the-irq_work-item.patch @@ -0,0 +1,48 @@ +From 6dfc680fe2808eaf10a9feed7e3116df60b6032f Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 8 Sep 2021 17:18:00 +0200 +Subject: [PATCH 28/62] drm/i915/gt: Queue and wait for the irq_work item. +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Disabling interrupts and invoking the irq_work function directly breaks +on PREEMPT_RT. +PREEMPT_RT does not invoke all irq_work from hardirq context because +some of the user have spinlock_t locking in the callback function. +These locks are then turned into a sleeping locks which can not be +acquired with disabled interrupts. + +Using irq_work_queue() has the benefit that the irqwork will be invoked +in the regular context. In general there is "no" delay between enqueuing +the callback and its invocation because the interrupt is raised right +away on architectures which support it (which includes x86). + +Use irq_work_queue() + irq_work_sync() instead invoking the callback +directly. + +Reported-by: Clark Williams <williams@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> +--- + drivers/gpu/drm/i915/gt/intel_breadcrumbs.c | 5 ++--- + 1 file changed, 2 insertions(+), 3 deletions(-) + +diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +index ecc990ec1b95..8d04b10681f0 100644 +--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c ++++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +@@ -312,10 +312,9 @@ void __intel_breadcrumbs_park(struct intel_breadcrumbs *b) + /* Kick the work once more to drain the signalers, and disarm the irq */ + irq_work_sync(&b->irq_work); + while (READ_ONCE(b->irq_armed) && !atomic_read(&b->active)) { +- local_irq_disable(); +- signal_irq_work(&b->irq_work); +- local_irq_enable(); ++ irq_work_queue(&b->irq_work); + cond_resched(); ++ irq_work_sync(&b->irq_work); + } + } + +-- +2.43.0 + diff --git a/debian/patches-rt/0029-drm-i915-gt-Use-spin_lock_irq-instead-of-local_irq_d.patch b/debian/patches-rt/0029-drm-i915-gt-Use-spin_lock_irq-instead-of-local_irq_d.patch new file mode 100644 index 000000000..d7696f54a --- /dev/null +++ b/debian/patches-rt/0029-drm-i915-gt-Use-spin_lock_irq-instead-of-local_irq_d.patch @@ -0,0 +1,95 @@ +From 6ca6d59038e0a61a7bb4904310525b1df57a2867 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 8 Sep 2021 19:03:41 +0200 +Subject: [PATCH 29/62] drm/i915/gt: Use spin_lock_irq() instead of + local_irq_disable() + spin_lock() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +execlists_dequeue() is invoked from a function which uses +local_irq_disable() to disable interrupts so the spin_lock() behaves +like spin_lock_irq(). +This breaks PREEMPT_RT because local_irq_disable() + spin_lock() is not +the same as spin_lock_irq(). + +execlists_dequeue_irq() and execlists_dequeue() has each one caller +only. If intel_engine_cs::active::lock is acquired and released with the +_irq suffix then it behaves almost as if execlists_dequeue() would be +invoked with disabled interrupts. The difference is the last part of the +function which is then invoked with enabled interrupts. +I can't tell if this makes a difference. From looking at it, it might +work to move the last unlock at the end of the function as I didn't find +anything that would acquire the lock again. + +Reported-by: Clark Williams <williams@redhat.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> +--- + .../drm/i915/gt/intel_execlists_submission.c | 17 +++++------------ + 1 file changed, 5 insertions(+), 12 deletions(-) + +diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +index f903ee1ce06e..f54059b63ea9 100644 +--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c ++++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +@@ -1302,7 +1302,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) + * and context switches) submission. + */ + +- spin_lock(&sched_engine->lock); ++ spin_lock_irq(&sched_engine->lock); + + /* + * If the queue is higher priority than the last +@@ -1402,7 +1402,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) + * Even if ELSP[1] is occupied and not worthy + * of timeslices, our queue might be. + */ +- spin_unlock(&sched_engine->lock); ++ spin_unlock_irq(&sched_engine->lock); + return; + } + } +@@ -1428,7 +1428,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) + + if (last && !can_merge_rq(last, rq)) { + spin_unlock(&ve->base.sched_engine->lock); +- spin_unlock(&engine->sched_engine->lock); ++ spin_unlock_irq(&engine->sched_engine->lock); + return; /* leave this for another sibling */ + } + +@@ -1590,7 +1590,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) + */ + sched_engine->queue_priority_hint = queue_prio(sched_engine); + i915_sched_engine_reset_on_empty(sched_engine); +- spin_unlock(&sched_engine->lock); ++ spin_unlock_irq(&sched_engine->lock); + + /* + * We can skip poking the HW if we ended up with exactly the same set +@@ -1616,13 +1616,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine) + } + } + +-static void execlists_dequeue_irq(struct intel_engine_cs *engine) +-{ +- local_irq_disable(); /* Suspend interrupts across request submission */ +- execlists_dequeue(engine); +- local_irq_enable(); /* flush irq_work (e.g. breadcrumb enabling) */ +-} +- + static void clear_ports(struct i915_request **ports, int count) + { + memset_p((void **)ports, NULL, count); +@@ -2476,7 +2469,7 @@ static void execlists_submission_tasklet(struct tasklet_struct *t) + } + + if (!engine->execlists.pending[0]) { +- execlists_dequeue_irq(engine); ++ execlists_dequeue(engine); + start_timeslice(engine); + } + +-- +2.43.0 + diff --git a/debian/patches-rt/0030-drm-i915-Drop-the-irqs_disabled-check.patch b/debian/patches-rt/0030-drm-i915-Drop-the-irqs_disabled-check.patch new file mode 100644 index 000000000..4d49e26f7 --- /dev/null +++ b/debian/patches-rt/0030-drm-i915-Drop-the-irqs_disabled-check.patch @@ -0,0 +1,45 @@ +From 6779399c1acfc91f6e9b0bd4dc4abb4f3cb30c78 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 1 Oct 2021 20:01:03 +0200 +Subject: [PATCH 30/62] drm/i915: Drop the irqs_disabled() check +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +The !irqs_disabled() check triggers on PREEMPT_RT even with +i915_sched_engine::lock acquired. The reason is the lock is transformed +into a sleeping lock on PREEMPT_RT and does not disable interrupts. + +There is no need to check for disabled interrupts. The lockdep +annotation below already check if the lock has been acquired by the +caller and will yell if the interrupts are not disabled. + +Remove the !irqs_disabled() check. + +Reported-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/gpu/drm/i915/i915_request.c | 2 -- + 1 file changed, 2 deletions(-) + +diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c +index 7ce126a01cbf..64a032dfaa90 100644 +--- a/drivers/gpu/drm/i915/i915_request.c ++++ b/drivers/gpu/drm/i915/i915_request.c +@@ -609,7 +609,6 @@ bool __i915_request_submit(struct i915_request *request) + + RQ_TRACE(request, "\n"); + +- GEM_BUG_ON(!irqs_disabled()); + lockdep_assert_held(&engine->sched_engine->lock); + + /* +@@ -718,7 +717,6 @@ void __i915_request_unsubmit(struct i915_request *request) + */ + RQ_TRACE(request, "\n"); + +- GEM_BUG_ON(!irqs_disabled()); + lockdep_assert_held(&engine->sched_engine->lock); + + /* +-- +2.43.0 + diff --git a/debian/patches-rt/0031-Revert-drm-i915-Depend-on-PREEMPT_RT.patch b/debian/patches-rt/0031-Revert-drm-i915-Depend-on-PREEMPT_RT.patch new file mode 100644 index 000000000..9ef52335e --- /dev/null +++ b/debian/patches-rt/0031-Revert-drm-i915-Depend-on-PREEMPT_RT.patch @@ -0,0 +1,29 @@ +From fe8c8e1f1ec5c61814ee0c4c90a2cef9d35ecad6 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Mon, 21 Feb 2022 17:59:14 +0100 +Subject: [PATCH 31/62] Revert "drm/i915: Depend on !PREEMPT_RT." +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Once the known issues are addressed, it should be safe to enable the +driver. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +--- + drivers/gpu/drm/i915/Kconfig | 1 - + 1 file changed, 1 deletion(-) + +diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig +index 6b10868ec72f..1fbdb7b4e6e1 100644 +--- a/drivers/gpu/drm/i915/Kconfig ++++ b/drivers/gpu/drm/i915/Kconfig +@@ -3,7 +3,6 @@ config DRM_I915 + tristate "Intel 8xx/9xx/G3x/G4x/HD Graphics" + depends on DRM + depends on X86 && PCI +- depends on !PREEMPT_RT + select INTEL_GTT if X86 + select INTERVAL_TREE + # we need shmfs for the swappable backing store, and in particular +-- +2.43.0 + diff --git a/debian/patches-rt/0032-sched-Add-support-for-lazy-preemption.patch b/debian/patches-rt/0032-sched-Add-support-for-lazy-preemption.patch new file mode 100644 index 000000000..54c21bbb9 --- /dev/null +++ b/debian/patches-rt/0032-sched-Add-support-for-lazy-preemption.patch @@ -0,0 +1,714 @@ +From 87194c420f8ef3b1a8b9b63ae640180e2414e8c4 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Fri, 26 Oct 2012 18:50:54 +0100 +Subject: [PATCH 32/62] sched: Add support for lazy preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +It has become an obsession to mitigate the determinism vs. throughput +loss of RT. Looking at the mainline semantics of preemption points +gives a hint why RT sucks throughput wise for ordinary SCHED_OTHER +tasks. One major issue is the wakeup of tasks which are right away +preempting the waking task while the waking task holds a lock on which +the woken task will block right after having preempted the wakee. In +mainline this is prevented due to the implicit preemption disable of +spin/rw_lock held regions. On RT this is not possible due to the fully +preemptible nature of sleeping spinlocks. + +Though for a SCHED_OTHER task preempting another SCHED_OTHER task this +is really not a correctness issue. RT folks are concerned about +SCHED_FIFO/RR tasks preemption and not about the purely fairness +driven SCHED_OTHER preemption latencies. + +So I introduced a lazy preemption mechanism which only applies to +SCHED_OTHER tasks preempting another SCHED_OTHER task. Aside of the +existing preempt_count each tasks sports now a preempt_lazy_count +which is manipulated on lock acquiry and release. This is slightly +incorrect as for lazyness reasons I coupled this on +migrate_disable/enable so some other mechanisms get the same treatment +(e.g. get_cpu_light). + +Now on the scheduler side instead of setting NEED_RESCHED this sets +NEED_RESCHED_LAZY in case of a SCHED_OTHER/SCHED_OTHER preemption and +therefor allows to exit the waking task the lock held region before +the woken task preempts. That also works better for cross CPU wakeups +as the other side can stay in the adaptive spinning loop. + +For RT class preemption there is no change. This simply sets +NEED_RESCHED and forgoes the lazy preemption counter. + + Initial test do not expose any observable latency increasement, but +history shows that I've been proven wrong before :) + +The lazy preemption mode is per default on, but with +CONFIG_SCHED_DEBUG enabled it can be disabled via: + + # echo NO_PREEMPT_LAZY >/sys/kernel/debug/sched_features + +and reenabled via + + # echo PREEMPT_LAZY >/sys/kernel/debug/sched_features + +The test results so far are very machine and workload dependent, but +there is a clear trend that it enhances the non RT workload +performance. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + include/linux/preempt.h | 54 ++++++++++++++++++++++-- + include/linux/sched.h | 37 +++++++++++++++++ + include/linux/thread_info.h | 12 +++++- + include/linux/trace_events.h | 10 ++++- + kernel/Kconfig.preempt | 6 +++ + kernel/sched/core.c | 79 +++++++++++++++++++++++++++++++++++- + kernel/sched/fair.c | 16 ++++---- + kernel/sched/features.h | 3 ++ + kernel/sched/sched.h | 9 ++++ + kernel/trace/trace.c | 50 ++++++++++++++--------- + kernel/trace/trace_events.c | 1 + + kernel/trace/trace_output.c | 18 +++++++- + 12 files changed, 260 insertions(+), 35 deletions(-) + +diff --git a/include/linux/preempt.h b/include/linux/preempt.h +index 8cfcc5d45451..9fc4c4bb320f 100644 +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -207,6 +207,20 @@ extern void preempt_count_sub(int val); + #define preempt_count_inc() preempt_count_add(1) + #define preempt_count_dec() preempt_count_sub(1) + ++#ifdef CONFIG_PREEMPT_LAZY ++#define add_preempt_lazy_count(val) do { preempt_lazy_count() += (val); } while (0) ++#define sub_preempt_lazy_count(val) do { preempt_lazy_count() -= (val); } while (0) ++#define inc_preempt_lazy_count() add_preempt_lazy_count(1) ++#define dec_preempt_lazy_count() sub_preempt_lazy_count(1) ++#define preempt_lazy_count() (current_thread_info()->preempt_lazy_count) ++#else ++#define add_preempt_lazy_count(val) do { } while (0) ++#define sub_preempt_lazy_count(val) do { } while (0) ++#define inc_preempt_lazy_count() do { } while (0) ++#define dec_preempt_lazy_count() do { } while (0) ++#define preempt_lazy_count() (0) ++#endif ++ + #ifdef CONFIG_PREEMPT_COUNT + + #define preempt_disable() \ +@@ -215,6 +229,12 @@ do { \ + barrier(); \ + } while (0) + ++#define preempt_lazy_disable() \ ++do { \ ++ inc_preempt_lazy_count(); \ ++ barrier(); \ ++} while (0) ++ + #define sched_preempt_enable_no_resched() \ + do { \ + barrier(); \ +@@ -246,6 +266,18 @@ do { \ + __preempt_schedule(); \ + } while (0) + ++/* ++ * open code preempt_check_resched() because it is not exported to modules and ++ * used by local_unlock() or bpf_enable_instrumentation(). ++ */ ++#define preempt_lazy_enable() \ ++do { \ ++ dec_preempt_lazy_count(); \ ++ barrier(); \ ++ if (should_resched(0)) \ ++ __preempt_schedule(); \ ++} while (0) ++ + #else /* !CONFIG_PREEMPTION */ + #define preempt_enable() \ + do { \ +@@ -253,6 +285,12 @@ do { \ + preempt_count_dec(); \ + } while (0) + ++#define preempt_lazy_enable() \ ++do { \ ++ dec_preempt_lazy_count(); \ ++ barrier(); \ ++} while (0) ++ + #define preempt_enable_notrace() \ + do { \ + barrier(); \ +@@ -293,6 +331,9 @@ do { \ + #define preempt_enable_notrace() barrier() + #define preemptible() 0 + ++#define preempt_lazy_disable() barrier() ++#define preempt_lazy_enable() barrier() ++ + #endif /* CONFIG_PREEMPT_COUNT */ + + #ifdef MODULE +@@ -311,7 +352,7 @@ do { \ + } while (0) + #define preempt_fold_need_resched() \ + do { \ +- if (tif_need_resched()) \ ++ if (tif_need_resched_now()) \ + set_preempt_need_resched(); \ + } while (0) + +@@ -427,8 +468,15 @@ extern void migrate_enable(void); + + #else + +-static inline void migrate_disable(void) { } +-static inline void migrate_enable(void) { } ++static inline void migrate_disable(void) ++{ ++ preempt_lazy_disable(); ++} ++ ++static inline void migrate_enable(void) ++{ ++ preempt_lazy_enable(); ++} + + #endif /* CONFIG_SMP */ + +diff --git a/include/linux/sched.h b/include/linux/sched.h +index 0cac69902ec5..67ec36dbfacf 100644 +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -2061,6 +2061,43 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) + return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++static inline void set_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ set_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline int test_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY)); ++} ++ ++static inline int need_resched_lazy(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline int need_resched_now(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED); ++} ++ ++#else ++static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) { } ++static inline int need_resched_lazy(void) { return 0; } ++ ++static inline int need_resched_now(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED); ++} ++ ++#endif ++ + /* + * cond_resched() and cond_resched_lock(): latency reduction via + * explicit rescheduling in places that are safe. The return +diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h +index 9f392ec76f2b..779e0e96b9cb 100644 +--- a/include/linux/thread_info.h ++++ b/include/linux/thread_info.h +@@ -177,7 +177,17 @@ static __always_inline unsigned long read_ti_thread_flags(struct thread_info *ti + clear_ti_thread_flag(task_thread_info(t), TIF_##fl) + #endif /* !CONFIG_GENERIC_ENTRY */ + +-#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) ++#ifdef CONFIG_PREEMPT_LAZY ++#define tif_need_resched() (test_thread_flag(TIF_NEED_RESCHED) || \ ++ test_thread_flag(TIF_NEED_RESCHED_LAZY)) ++#define tif_need_resched_now() (test_thread_flag(TIF_NEED_RESCHED)) ++#define tif_need_resched_lazy() test_thread_flag(TIF_NEED_RESCHED_LAZY) ++ ++#else ++#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) ++#define tif_need_resched_now() test_thread_flag(TIF_NEED_RESCHED) ++#define tif_need_resched_lazy() 0 ++#endif + + #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES + static inline int arch_within_stack_frames(const void * const stack, +diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h +index c8b5e9781d01..743b1183d184 100644 +--- a/include/linux/trace_events.h ++++ b/include/linux/trace_events.h +@@ -70,6 +70,7 @@ struct trace_entry { + unsigned char flags; + unsigned char preempt_count; + int pid; ++ unsigned char preempt_lazy_count; + }; + + #define TRACE_EVENT_TYPE_MAX \ +@@ -159,9 +160,10 @@ static inline void tracing_generic_entry_update(struct trace_entry *entry, + unsigned int trace_ctx) + { + entry->preempt_count = trace_ctx & 0xff; ++ entry->preempt_lazy_count = (trace_ctx >> 16) & 0xff; + entry->pid = current->pid; + entry->type = type; +- entry->flags = trace_ctx >> 16; ++ entry->flags = trace_ctx >> 24; + } + + unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status); +@@ -172,7 +174,13 @@ enum trace_flag_type { + TRACE_FLAG_NEED_RESCHED = 0x04, + TRACE_FLAG_HARDIRQ = 0x08, + TRACE_FLAG_SOFTIRQ = 0x10, ++#ifdef CONFIG_PREEMPT_LAZY ++ TRACE_FLAG_PREEMPT_RESCHED = 0x00, ++ TRACE_FLAG_NEED_RESCHED_LAZY = 0x20, ++#else ++ TRACE_FLAG_NEED_RESCHED_LAZY = 0x00, + TRACE_FLAG_PREEMPT_RESCHED = 0x20, ++#endif + TRACE_FLAG_NMI = 0x40, + TRACE_FLAG_BH_OFF = 0x80, + }; +diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt +index c2f1fd95a821..260c08efeb48 100644 +--- a/kernel/Kconfig.preempt ++++ b/kernel/Kconfig.preempt +@@ -1,5 +1,11 @@ + # SPDX-License-Identifier: GPL-2.0-only + ++config HAVE_PREEMPT_LAZY ++ bool ++ ++config PREEMPT_LAZY ++ def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT ++ + config PREEMPT_NONE_BUILD + bool + +diff --git a/kernel/sched/core.c b/kernel/sched/core.c +index 6bd06122850a..b72fc7d336e4 100644 +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1040,6 +1040,46 @@ void resched_curr(struct rq *rq) + trace_sched_wake_idle_without_ipi(cpu); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++ ++static int tsk_is_polling(struct task_struct *p) ++{ ++#ifdef TIF_POLLING_NRFLAG ++ return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG); ++#else ++ return 0; ++#endif ++} ++ ++void resched_curr_lazy(struct rq *rq) ++{ ++ struct task_struct *curr = rq->curr; ++ int cpu; ++ ++ if (!sched_feat(PREEMPT_LAZY)) { ++ resched_curr(rq); ++ return; ++ } ++ ++ if (test_tsk_need_resched(curr)) ++ return; ++ ++ if (test_tsk_need_resched_lazy(curr)) ++ return; ++ ++ set_tsk_need_resched_lazy(curr); ++ ++ cpu = cpu_of(rq); ++ if (cpu == smp_processor_id()) ++ return; ++ ++ /* NEED_RESCHED_LAZY must be visible before we test polling */ ++ smp_mb(); ++ if (!tsk_is_polling(curr)) ++ smp_send_reschedule(cpu); ++} ++#endif ++ + void resched_cpu(int cpu) + { + struct rq *rq = cpu_rq(cpu); +@@ -2224,6 +2264,7 @@ void migrate_disable(void) + preempt_disable(); + this_rq()->nr_pinned++; + p->migration_disabled = 1; ++ preempt_lazy_disable(); + preempt_enable(); + } + EXPORT_SYMBOL_GPL(migrate_disable); +@@ -2255,6 +2296,7 @@ void migrate_enable(void) + barrier(); + p->migration_disabled = 0; + this_rq()->nr_pinned--; ++ preempt_lazy_enable(); + preempt_enable(); + } + EXPORT_SYMBOL_GPL(migrate_enable); +@@ -4722,6 +4764,9 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) + p->on_cpu = 0; + #endif + init_task_preempt_count(p); ++#ifdef CONFIG_HAVE_PREEMPT_LAZY ++ task_thread_info(p)->preempt_lazy_count = 0; ++#endif + #ifdef CONFIG_SMP + plist_node_init(&p->pushable_tasks, MAX_PRIO); + RB_CLEAR_NODE(&p->pushable_dl_tasks); +@@ -6592,6 +6637,7 @@ static void __sched notrace __schedule(unsigned int sched_mode) + + next = pick_next_task(rq, prev, &rf); + clear_tsk_need_resched(prev); ++ clear_tsk_need_resched_lazy(prev); + clear_preempt_need_resched(); + #ifdef CONFIG_SCHED_DEBUG + rq->last_seen_need_resched_ns = 0; +@@ -6806,6 +6852,30 @@ static void __sched notrace preempt_schedule_common(void) + } while (need_resched()); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++/* ++ * If TIF_NEED_RESCHED is then we allow to be scheduled away since this is ++ * set by a RT task. Oterwise we try to avoid beeing scheduled out as long as ++ * preempt_lazy_count counter >0. ++ */ ++static __always_inline int preemptible_lazy(void) ++{ ++ if (test_thread_flag(TIF_NEED_RESCHED)) ++ return 1; ++ if (current_thread_info()->preempt_lazy_count) ++ return 0; ++ return 1; ++} ++ ++#else ++ ++static inline int preemptible_lazy(void) ++{ ++ return 1; ++} ++ ++#endif ++ + #ifdef CONFIG_PREEMPTION + /* + * This is the entry point to schedule() from in-kernel preemption +@@ -6819,6 +6889,8 @@ asmlinkage __visible void __sched notrace preempt_schedule(void) + */ + if (likely(!preemptible())) + return; ++ if (!preemptible_lazy()) ++ return; + preempt_schedule_common(); + } + NOKPROBE_SYMBOL(preempt_schedule); +@@ -6866,6 +6938,9 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) + if (likely(!preemptible())) + return; + ++ if (!preemptible_lazy()) ++ return; ++ + do { + /* + * Because the function tracer can trace preempt_count_sub() +@@ -9131,7 +9206,9 @@ void __init init_idle(struct task_struct *idle, int cpu) + + /* Set the preempt count _outside_ the spinlocks! */ + init_idle_preempt_count(idle, cpu); +- ++#ifdef CONFIG_HAVE_PREEMPT_LAZY ++ task_thread_info(idle)->preempt_lazy_count = 0; ++#endif + /* + * The idle tasks have their own, simple scheduling class: + */ +diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c +index 2558ab9033be..2dc35af7b5a6 100644 +--- a/kernel/sched/fair.c ++++ b/kernel/sched/fair.c +@@ -4914,7 +4914,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) + ideal_runtime = sched_slice(cfs_rq, curr); + delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; + if (delta_exec > ideal_runtime) { +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + /* + * The current task ran long enough, ensure it doesn't get + * re-elected due to buddy favours. +@@ -4938,7 +4938,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) + return; + + if (delta > ideal_runtime) +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + } + + static void +@@ -5084,7 +5084,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) + * validating it and just reschedule. + */ + if (queued) { +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + return; + } + /* +@@ -5233,7 +5233,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) + * hierarchy can be throttled + */ + if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + } + + static __always_inline +@@ -5984,7 +5984,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) + + if (delta < 0) { + if (task_current(rq, p)) +- resched_curr(rq); ++ resched_curr_lazy(rq); + return; + } + hrtick_start(rq, delta); +@@ -7712,7 +7712,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ + return; + + preempt: +- resched_curr(rq); ++ resched_curr_lazy(rq); + /* + * Only set the backward buddy when the current task is still + * on the rq. This can happen when a wakeup gets interleaved +@@ -11877,7 +11877,7 @@ static void task_fork_fair(struct task_struct *p) + * 'current' within the tree based on its new key value. + */ + swap(curr->vruntime, se->vruntime); +- resched_curr(rq); ++ resched_curr_lazy(rq); + } + + se->vruntime -= cfs_rq->min_vruntime; +@@ -11904,7 +11904,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) + */ + if (task_current(rq, p)) { + if (p->prio > oldprio) +- resched_curr(rq); ++ resched_curr_lazy(rq); + } else + check_preempt_curr(rq, p, 0); + } +diff --git a/kernel/sched/features.h b/kernel/sched/features.h +index ee7f23c76bd3..e13090e33f3c 100644 +--- a/kernel/sched/features.h ++++ b/kernel/sched/features.h +@@ -48,6 +48,9 @@ SCHED_FEAT(NONTASK_CAPACITY, true) + + #ifdef CONFIG_PREEMPT_RT + SCHED_FEAT(TTWU_QUEUE, false) ++# ifdef CONFIG_PREEMPT_LAZY ++SCHED_FEAT(PREEMPT_LAZY, true) ++# endif + #else + + /* +diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h +index b62d53d7c264..f2577f511a41 100644 +--- a/kernel/sched/sched.h ++++ b/kernel/sched/sched.h +@@ -2350,6 +2350,15 @@ extern void reweight_task(struct task_struct *p, int prio); + extern void resched_curr(struct rq *rq); + extern void resched_cpu(int cpu); + ++#ifdef CONFIG_PREEMPT_LAZY ++extern void resched_curr_lazy(struct rq *rq); ++#else ++static inline void resched_curr_lazy(struct rq *rq) ++{ ++ resched_curr(rq); ++} ++#endif ++ + extern struct rt_bandwidth def_rt_bandwidth; + extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); + extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq); +diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c +index 87eca95b57fb..462564d652be 100644 +--- a/kernel/trace/trace.c ++++ b/kernel/trace/trace.c +@@ -2616,11 +2616,19 @@ unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status) + if (softirq_count() >> (SOFTIRQ_SHIFT + 1)) + trace_flags |= TRACE_FLAG_BH_OFF; + +- if (tif_need_resched()) ++ if (tif_need_resched_now()) + trace_flags |= TRACE_FLAG_NEED_RESCHED; ++#ifdef CONFIG_PREEMPT_LAZY ++ /* Run out of bits. Share the LAZY and PREEMPT_RESCHED */ ++ if (need_resched_lazy()) ++ trace_flags |= TRACE_FLAG_NEED_RESCHED_LAZY; ++#else + if (test_preempt_need_resched()) + trace_flags |= TRACE_FLAG_PREEMPT_RESCHED; +- return (trace_flags << 16) | (min_t(unsigned int, pc & 0xff, 0xf)) | ++#endif ++ ++ return (trace_flags << 24) | (min_t(unsigned int, pc & 0xff, 0xf)) | ++ (preempt_lazy_count() & 0xff) << 16 | + (min_t(unsigned int, migration_disable_value(), 0xf)) << 4; + } + +@@ -4212,15 +4220,17 @@ unsigned long trace_total_entries(struct trace_array *tr) + + static void print_lat_help_header(struct seq_file *m) + { +- seq_puts(m, "# _------=> CPU# \n" +- "# / _-----=> irqs-off/BH-disabled\n" +- "# | / _----=> need-resched \n" +- "# || / _---=> hardirq/softirq \n" +- "# ||| / _--=> preempt-depth \n" +- "# |||| / _-=> migrate-disable \n" +- "# ||||| / delay \n" +- "# cmd pid |||||| time | caller \n" +- "# \\ / |||||| \\ | / \n"); ++ seq_puts(m, "# _--------=> CPU# \n" ++ "# / _-------=> irqs-off/BH-disabled\n" ++ "# | / _------=> need-resched \n" ++ "# || / _-----=> need-resched-lazy\n" ++ "# ||| / _----=> hardirq/softirq \n" ++ "# |||| / _---=> preempt-depth \n" ++ "# ||||| / _--=> preempt-lazy-depth\n" ++ "# |||||| / _-=> migrate-disable \n" ++ "# ||||||| / delay \n" ++ "# cmd pid |||||||| time | caller \n" ++ "# \\ / |||||||| \\ | / \n"); + } + + static void print_event_info(struct array_buffer *buf, struct seq_file *m) +@@ -4254,14 +4264,16 @@ static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file + + print_event_info(buf, m); + +- seq_printf(m, "# %.*s _-----=> irqs-off/BH-disabled\n", prec, space); +- seq_printf(m, "# %.*s / _----=> need-resched\n", prec, space); +- seq_printf(m, "# %.*s| / _---=> hardirq/softirq\n", prec, space); +- seq_printf(m, "# %.*s|| / _--=> preempt-depth\n", prec, space); +- seq_printf(m, "# %.*s||| / _-=> migrate-disable\n", prec, space); +- seq_printf(m, "# %.*s|||| / delay\n", prec, space); +- seq_printf(m, "# TASK-PID %.*s CPU# ||||| TIMESTAMP FUNCTION\n", prec, " TGID "); +- seq_printf(m, "# | | %.*s | ||||| | |\n", prec, " | "); ++ seq_printf(m, "# %.*s _-------=> irqs-off/BH-disabled\n", prec, space); ++ seq_printf(m, "# %.*s / _------=> need-resched\n", prec, space); ++ seq_printf(m, "# %.*s| / _-----=> need-resched-lazy\n", prec, space); ++ seq_printf(m, "# %.*s|| / _----=> hardirq/softirq\n", prec, space); ++ seq_printf(m, "# %.*s||| / _---=> preempt-depth\n", prec, space); ++ seq_printf(m, "# %.*s|||| / _--=> preempt-lazy-depth\n", prec, space); ++ seq_printf(m, "# %.*s||||| / _-=> migrate-disable\n", prec, space); ++ seq_printf(m, "# %.*s|||||| / delay\n", prec, space); ++ seq_printf(m, "# TASK-PID %.*s CPU# ||||||| TIMESTAMP FUNCTION\n", prec, " TGID "); ++ seq_printf(m, "# | | %.*s | ||||||| | |\n", prec, " | "); + } + + void +diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c +index a6d2f99f847d..493c3f9cf01a 100644 +--- a/kernel/trace/trace_events.c ++++ b/kernel/trace/trace_events.c +@@ -208,6 +208,7 @@ static int trace_define_common_fields(void) + /* Holds both preempt_count and migrate_disable */ + __common_field(unsigned char, preempt_count); + __common_field(int, pid); ++ __common_field(unsigned char, preempt_lazy_count); + + return ret; + } +diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c +index 5cd4fb656306..3c227e2843ae 100644 +--- a/kernel/trace/trace_output.c ++++ b/kernel/trace/trace_output.c +@@ -442,6 +442,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) + { + char hardsoft_irq; + char need_resched; ++ char need_resched_lazy; + char irqs_off; + int hardirq; + int softirq; +@@ -462,20 +463,27 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) + + switch (entry->flags & (TRACE_FLAG_NEED_RESCHED | + TRACE_FLAG_PREEMPT_RESCHED)) { ++#ifndef CONFIG_PREEMPT_LAZY + case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_PREEMPT_RESCHED: + need_resched = 'N'; + break; ++#endif + case TRACE_FLAG_NEED_RESCHED: + need_resched = 'n'; + break; ++#ifndef CONFIG_PREEMPT_LAZY + case TRACE_FLAG_PREEMPT_RESCHED: + need_resched = 'p'; + break; ++#endif + default: + need_resched = '.'; + break; + } + ++ need_resched_lazy = ++ (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.'; ++ + hardsoft_irq = + (nmi && hardirq) ? 'Z' : + nmi ? 'z' : +@@ -484,14 +492,20 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) + softirq ? 's' : + '.' ; + +- trace_seq_printf(s, "%c%c%c", +- irqs_off, need_resched, hardsoft_irq); ++ trace_seq_printf(s, "%c%c%c%c", ++ irqs_off, need_resched, need_resched_lazy, ++ hardsoft_irq); + + if (entry->preempt_count & 0xf) + trace_seq_printf(s, "%x", entry->preempt_count & 0xf); + else + trace_seq_putc(s, '.'); + ++ if (entry->preempt_lazy_count) ++ trace_seq_printf(s, "%x", entry->preempt_lazy_count); ++ else ++ trace_seq_putc(s, '.'); ++ + if (entry->preempt_count & 0xf0) + trace_seq_printf(s, "%x", entry->preempt_count >> 4); + else +-- +2.43.0 + diff --git a/debian/patches-rt/0033-x86-entry-Use-should_resched-in-idtentry_exit_cond_r.patch b/debian/patches-rt/0033-x86-entry-Use-should_resched-in-idtentry_exit_cond_r.patch new file mode 100644 index 000000000..69ddd41b3 --- /dev/null +++ b/debian/patches-rt/0033-x86-entry-Use-should_resched-in-idtentry_exit_cond_r.patch @@ -0,0 +1,36 @@ +From 37719a07083b68dad1449227e9fe66e8e6c9f2b6 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 30 Jun 2020 11:45:14 +0200 +Subject: [PATCH 33/62] x86/entry: Use should_resched() in + idtentry_exit_cond_resched() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +The TIF_NEED_RESCHED bit is inlined on x86 into the preemption counter. +By using should_resched(0) instead of need_resched() the same check can +be performed which uses the same variable as 'preempt_count()` which was +issued before. + +Use should_resched(0) instead need_resched(). + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/entry/common.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/kernel/entry/common.c b/kernel/entry/common.c +index be61332c66b5..97ff5faad4fb 100644 +--- a/kernel/entry/common.c ++++ b/kernel/entry/common.c +@@ -386,7 +386,7 @@ void raw_irqentry_exit_cond_resched(void) + rcu_irq_exit_check_preempt(); + if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) + WARN_ON_ONCE(!on_thread_stack()); +- if (need_resched()) ++ if (should_resched(0)) + preempt_schedule_irq(); + } + } +-- +2.43.0 + diff --git a/debian/patches-rt/0034-x86-Support-for-lazy-preemption.patch b/debian/patches-rt/0034-x86-Support-for-lazy-preemption.patch new file mode 100644 index 000000000..511fe0a01 --- /dev/null +++ b/debian/patches-rt/0034-x86-Support-for-lazy-preemption.patch @@ -0,0 +1,158 @@ +From 65ce5ba8ccb26e6de364e76228e645b2c02b921d Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 1 Nov 2012 11:03:47 +0100 +Subject: [PATCH 34/62] x86: Support for lazy preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Implement the x86 pieces for lazy preempt. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/x86/Kconfig | 1 + + arch/x86/include/asm/preempt.h | 33 +++++++++++++++++++++++++++++- + arch/x86/include/asm/thread_info.h | 7 +++++++ + include/linux/entry-common.h | 2 +- + kernel/entry/common.c | 2 +- + 5 files changed, 42 insertions(+), 3 deletions(-) + +diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig +index c9bed9c69423..f38bd8a5061e 100644 +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -251,6 +251,7 @@ config X86 + select HAVE_PCI + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP ++ select HAVE_PREEMPT_LAZY + select MMU_GATHER_RCU_TABLE_FREE if PARAVIRT + select MMU_GATHER_MERGE_VMAS + select HAVE_POSIX_CPU_TIMERS_TASK_WORK +diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h +index 5f6daea1ee24..cd20b4a5719a 100644 +--- a/arch/x86/include/asm/preempt.h ++++ b/arch/x86/include/asm/preempt.h +@@ -90,17 +90,48 @@ static __always_inline void __preempt_count_sub(int val) + * a decrement which hits zero means we have no preempt_count and should + * reschedule. + */ +-static __always_inline bool __preempt_count_dec_and_test(void) ++static __always_inline bool ____preempt_count_dec_and_test(void) + { + return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var])); + } + ++static __always_inline bool __preempt_count_dec_and_test(void) ++{ ++ if (____preempt_count_dec_and_test()) ++ return true; ++#ifdef CONFIG_PREEMPT_LAZY ++ if (preempt_count()) ++ return false; ++ if (current_thread_info()->preempt_lazy_count) ++ return false; ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++#else ++ return false; ++#endif ++} ++ + /* + * Returns true when we need to resched and can (barring IRQ state). + */ + static __always_inline bool should_resched(int preempt_offset) + { ++#ifdef CONFIG_PREEMPT_LAZY ++ u32 tmp; ++ tmp = raw_cpu_read_4(__preempt_count); ++ if (tmp == preempt_offset) ++ return true; ++ ++ /* preempt count == 0 ? */ ++ tmp &= ~PREEMPT_NEED_RESCHED; ++ if (tmp != preempt_offset) ++ return false; ++ /* XXX PREEMPT_LOCK_OFFSET */ ++ if (current_thread_info()->preempt_lazy_count) ++ return false; ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++#else + return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); ++#endif + } + + #ifdef CONFIG_PREEMPTION +diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h +index f0cb881c1d69..0da06a9b5f72 100644 +--- a/arch/x86/include/asm/thread_info.h ++++ b/arch/x86/include/asm/thread_info.h +@@ -57,6 +57,8 @@ struct thread_info { + unsigned long flags; /* low level flags */ + unsigned long syscall_work; /* SYSCALL_WORK_ flags */ + u32 status; /* thread synchronous flags */ ++ int preempt_lazy_count; /* 0 => lazy preemptable ++ <0 => BUG */ + #ifdef CONFIG_SMP + u32 cpu; /* current CPU */ + #endif +@@ -65,6 +67,7 @@ struct thread_info { + #define INIT_THREAD_INFO(tsk) \ + { \ + .flags = 0, \ ++ .preempt_lazy_count = 0, \ + } + + #else /* !__ASSEMBLY__ */ +@@ -92,6 +95,7 @@ struct thread_info { + #define TIF_NOCPUID 15 /* CPUID is not accessible in userland */ + #define TIF_NOTSC 16 /* TSC is not accessible in userland */ + #define TIF_NOTIFY_SIGNAL 17 /* signal notifications exist */ ++#define TIF_NEED_RESCHED_LAZY 19 /* lazy rescheduling necessary */ + #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ + #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ + #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ +@@ -115,6 +119,7 @@ struct thread_info { + #define _TIF_NOCPUID (1 << TIF_NOCPUID) + #define _TIF_NOTSC (1 << TIF_NOTSC) + #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) + #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) + #define _TIF_SPEC_FORCE_UPDATE (1 << TIF_SPEC_FORCE_UPDATE) +@@ -146,6 +151,8 @@ struct thread_info { + + #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) + ++#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) ++ + #define STACK_WARN (THREAD_SIZE/8) + + /* +diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h +index d95ab85f96ba..93cc1ae12125 100644 +--- a/include/linux/entry-common.h ++++ b/include/linux/entry-common.h +@@ -59,7 +59,7 @@ + + #define EXIT_TO_USER_MODE_WORK \ + (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ +- _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \ ++ _TIF_NEED_RESCHED_MASK | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \ + ARCH_EXIT_TO_USER_MODE_WORK) + + /** +diff --git a/kernel/entry/common.c b/kernel/entry/common.c +index 97ff5faad4fb..c6301e520d47 100644 +--- a/kernel/entry/common.c ++++ b/kernel/entry/common.c +@@ -155,7 +155,7 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, + + local_irq_enable_exit_to_user(ti_work); + +- if (ti_work & _TIF_NEED_RESCHED) ++ if (ti_work & _TIF_NEED_RESCHED_MASK) + schedule(); + + if (ti_work & _TIF_UPROBE) +-- +2.43.0 + diff --git a/debian/patches-rt/0035-entry-Fix-the-preempt-lazy-fallout.patch b/debian/patches-rt/0035-entry-Fix-the-preempt-lazy-fallout.patch new file mode 100644 index 000000000..27139e9bb --- /dev/null +++ b/debian/patches-rt/0035-entry-Fix-the-preempt-lazy-fallout.patch @@ -0,0 +1,49 @@ +From d37c604152cbded61a8e107918d3b9950725d897 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Tue, 13 Jul 2021 07:52:52 +0200 +Subject: [PATCH 35/62] entry: Fix the preempt lazy fallout +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Common code needs common defines.... + +Fixes: f2f9e496208c ("x86: Support for lazy preemption") +Reported-by: kernel test robot <lkp@intel.com> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/x86/include/asm/thread_info.h | 2 -- + include/linux/entry-common.h | 6 ++++++ + 2 files changed, 6 insertions(+), 2 deletions(-) + +diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h +index 0da06a9b5f72..fd8fb76f324f 100644 +--- a/arch/x86/include/asm/thread_info.h ++++ b/arch/x86/include/asm/thread_info.h +@@ -151,8 +151,6 @@ struct thread_info { + + #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) + +-#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) +- + #define STACK_WARN (THREAD_SIZE/8) + + /* +diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h +index 93cc1ae12125..3dc3704a3cdb 100644 +--- a/include/linux/entry-common.h ++++ b/include/linux/entry-common.h +@@ -57,6 +57,12 @@ + # define ARCH_EXIT_TO_USER_MODE_WORK (0) + #endif + ++#ifdef CONFIG_PREEMPT_LAZY ++# define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) ++#else ++# define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED) ++#endif ++ + #define EXIT_TO_USER_MODE_WORK \ + (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ + _TIF_NEED_RESCHED_MASK | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \ +-- +2.43.0 + diff --git a/debian/patches-rt/0036-arm-Add-support-for-lazy-preemption.patch b/debian/patches-rt/0036-arm-Add-support-for-lazy-preemption.patch new file mode 100644 index 000000000..8f76d13b0 --- /dev/null +++ b/debian/patches-rt/0036-arm-Add-support-for-lazy-preemption.patch @@ -0,0 +1,137 @@ +From f242fbbb3f85d6b9c8c8fc06ddbc83b9ca5a0511 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 31 Oct 2012 12:04:11 +0100 +Subject: [PATCH 36/62] arm: Add support for lazy preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Implement the arm pieces for lazy preempt. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/arm/Kconfig | 1 + + arch/arm/include/asm/thread_info.h | 6 +++++- + arch/arm/kernel/asm-offsets.c | 1 + + arch/arm/kernel/entry-armv.S | 19 ++++++++++++++++--- + arch/arm/kernel/signal.c | 3 ++- + 5 files changed, 25 insertions(+), 5 deletions(-) + +diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig +index 6d5afe2e6ba3..717e596dc13b 100644 +--- a/arch/arm/Kconfig ++++ b/arch/arm/Kconfig +@@ -115,6 +115,7 @@ config ARM + select HAVE_PERF_EVENTS + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP ++ select HAVE_PREEMPT_LAZY + select MMU_GATHER_RCU_TABLE_FREE if SMP && ARM_LPAE + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RSEQ +diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h +index 7f092cb55a41..ffcbf8ebed4b 100644 +--- a/arch/arm/include/asm/thread_info.h ++++ b/arch/arm/include/asm/thread_info.h +@@ -62,6 +62,7 @@ struct cpu_context_save { + struct thread_info { + unsigned long flags; /* low level flags */ + int preempt_count; /* 0 => preemptable, <0 => bug */ ++ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ + __u32 cpu; /* cpu */ + __u32 cpu_domain; /* cpu domain */ + struct cpu_context_save cpu_context; /* cpu context */ +@@ -129,6 +130,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, + #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ + #define TIF_UPROBE 3 /* breakpointed or singlestepping */ + #define TIF_NOTIFY_SIGNAL 4 /* signal notifications exist */ ++#define TIF_NEED_RESCHED_LAZY 5 + + #define TIF_USING_IWMMXT 17 + #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ +@@ -148,6 +150,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, + #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) + #define _TIF_SECCOMP (1 << TIF_SECCOMP) + #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_USING_IWMMXT (1 << TIF_USING_IWMMXT) + + /* Checks for any syscall work in entry-common.S */ +@@ -157,7 +160,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp *, + /* + * Change these and you break ASM code in entry-common.S + */ +-#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ ++#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | \ ++ _TIF_SIGPENDING | \ + _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ + _TIF_NOTIFY_SIGNAL) + +diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c +index 2c8d76fd7c66..c3bdec7d2df9 100644 +--- a/arch/arm/kernel/asm-offsets.c ++++ b/arch/arm/kernel/asm-offsets.c +@@ -43,6 +43,7 @@ int main(void) + BLANK(); + DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); + DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); ++ DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count)); + DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); + DEFINE(TI_CPU_DOMAIN, offsetof(struct thread_info, cpu_domain)); + DEFINE(TI_CPU_SAVE, offsetof(struct thread_info, cpu_context)); +diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S +index c39303e5c234..cfb4660e9fea 100644 +--- a/arch/arm/kernel/entry-armv.S ++++ b/arch/arm/kernel/entry-armv.S +@@ -222,11 +222,18 @@ ENDPROC(__dabt_svc) + + #ifdef CONFIG_PREEMPTION + ldr r8, [tsk, #TI_PREEMPT] @ get preempt count +- ldr r0, [tsk, #TI_FLAGS] @ get flags + teq r8, #0 @ if preempt count != 0 ++ bne 1f @ return from exeption ++ ldr r0, [tsk, #TI_FLAGS] @ get flags ++ tst r0, #_TIF_NEED_RESCHED @ if NEED_RESCHED is set ++ blne svc_preempt @ preempt! ++ ++ ldr r8, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count ++ teq r8, #0 @ if preempt lazy count != 0 + movne r0, #0 @ force flags to 0 +- tst r0, #_TIF_NEED_RESCHED ++ tst r0, #_TIF_NEED_RESCHED_LAZY + blne svc_preempt ++1: + #endif + + svc_exit r5, irq = 1 @ return from exception +@@ -241,8 +248,14 @@ ENDPROC(__irq_svc) + 1: bl preempt_schedule_irq @ irq en/disable is done inside + ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS + tst r0, #_TIF_NEED_RESCHED ++ bne 1b ++ tst r0, #_TIF_NEED_RESCHED_LAZY + reteq r8 @ go again +- b 1b ++ ldr r0, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count ++ teq r0, #0 @ if preempt lazy count != 0 ++ beq 1b ++ ret r8 @ go again ++ + #endif + + __und_fault: +diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c +index e07f359254c3..b50a3248e79f 100644 +--- a/arch/arm/kernel/signal.c ++++ b/arch/arm/kernel/signal.c +@@ -607,7 +607,8 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) + */ + trace_hardirqs_off(); + do { +- if (likely(thread_flags & _TIF_NEED_RESCHED)) { ++ if (likely(thread_flags & (_TIF_NEED_RESCHED | ++ _TIF_NEED_RESCHED_LAZY))) { + schedule(); + } else { + if (unlikely(!user_mode(regs))) +-- +2.43.0 + diff --git a/debian/patches-rt/0037-powerpc-Add-support-for-lazy-preemption.patch b/debian/patches-rt/0037-powerpc-Add-support-for-lazy-preemption.patch new file mode 100644 index 000000000..bf8022c6c --- /dev/null +++ b/debian/patches-rt/0037-powerpc-Add-support-for-lazy-preemption.patch @@ -0,0 +1,118 @@ +From 65e31d7b980c1413f19fcb84234387f97b09588f Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 1 Nov 2012 10:14:11 +0100 +Subject: [PATCH 37/62] powerpc: Add support for lazy preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Implement the powerpc pieces for lazy preempt. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/powerpc/Kconfig | 1 + + arch/powerpc/include/asm/thread_info.h | 8 ++++++++ + arch/powerpc/kernel/interrupt.c | 8 ++++++-- + 3 files changed, 15 insertions(+), 2 deletions(-) + +diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig +index 6050e6e10d32..0eff864d6ec3 100644 +--- a/arch/powerpc/Kconfig ++++ b/arch/powerpc/Kconfig +@@ -242,6 +242,7 @@ config PPC + select HAVE_PERF_EVENTS_NMI if PPC64 + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP ++ select HAVE_PREEMPT_LAZY + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RELIABLE_STACKTRACE + select HAVE_RSEQ +diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h +index af58f1ed3952..520864de8bb2 100644 +--- a/arch/powerpc/include/asm/thread_info.h ++++ b/arch/powerpc/include/asm/thread_info.h +@@ -53,6 +53,8 @@ + struct thread_info { + int preempt_count; /* 0 => preemptable, + <0 => BUG */ ++ int preempt_lazy_count; /* 0 => preemptable, ++ <0 => BUG */ + #ifdef CONFIG_SMP + unsigned int cpu; + #endif +@@ -77,6 +79,7 @@ struct thread_info { + #define INIT_THREAD_INFO(tsk) \ + { \ + .preempt_count = INIT_PREEMPT_COUNT, \ ++ .preempt_lazy_count = 0, \ + .flags = 0, \ + } + +@@ -102,6 +105,7 @@ void arch_setup_new_exec(void); + #define TIF_PATCH_PENDING 6 /* pending live patching update */ + #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ + #define TIF_SINGLESTEP 8 /* singlestepping active */ ++#define TIF_NEED_RESCHED_LAZY 9 /* lazy rescheduling necessary */ + #define TIF_SECCOMP 10 /* secure computing */ + #define TIF_RESTOREALL 11 /* Restore all regs (implies NOERROR) */ + #define TIF_NOERROR 12 /* Force successful syscall return */ +@@ -117,6 +121,7 @@ void arch_setup_new_exec(void); + #define TIF_POLLING_NRFLAG 19 /* true if poll_idle() is polling TIF_NEED_RESCHED */ + #define TIF_32BIT 20 /* 32 bit binary */ + ++ + /* as above, but as bit values */ + #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) + #define _TIF_SIGPENDING (1<<TIF_SIGPENDING) +@@ -128,6 +133,7 @@ void arch_setup_new_exec(void); + #define _TIF_PATCH_PENDING (1<<TIF_PATCH_PENDING) + #define _TIF_SYSCALL_AUDIT (1<<TIF_SYSCALL_AUDIT) + #define _TIF_SINGLESTEP (1<<TIF_SINGLESTEP) ++#define _TIF_NEED_RESCHED_LAZY (1<<TIF_NEED_RESCHED_LAZY) + #define _TIF_SECCOMP (1<<TIF_SECCOMP) + #define _TIF_RESTOREALL (1<<TIF_RESTOREALL) + #define _TIF_NOERROR (1<<TIF_NOERROR) +@@ -141,10 +147,12 @@ void arch_setup_new_exec(void); + _TIF_SYSCALL_EMU) + + #define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ ++ _TIF_NEED_RESCHED_LAZY | \ + _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ + _TIF_RESTORE_TM | _TIF_PATCH_PENDING | \ + _TIF_NOTIFY_SIGNAL) + #define _TIF_PERSYSCALL_MASK (_TIF_RESTOREALL|_TIF_NOERROR) ++#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) + + /* Bits in local_flags */ + /* Don't move TLF_NAPPING without adjusting the code in entry_32.S */ +diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c +index cf770d86c03c..2c454731c250 100644 +--- a/arch/powerpc/kernel/interrupt.c ++++ b/arch/powerpc/kernel/interrupt.c +@@ -186,7 +186,7 @@ interrupt_exit_user_prepare_main(unsigned long ret, struct pt_regs *regs) + ti_flags = read_thread_flags(); + while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) { + local_irq_enable(); +- if (ti_flags & _TIF_NEED_RESCHED) { ++ if (ti_flags & _TIF_NEED_RESCHED_MASK) { + schedule(); + } else { + /* +@@ -397,11 +397,15 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs) + /* Returning to a kernel context with local irqs enabled. */ + WARN_ON_ONCE(!(regs->msr & MSR_EE)); + again: +- if (IS_ENABLED(CONFIG_PREEMPT)) { ++ if (IS_ENABLED(CONFIG_PREEMPTION)) { + /* Return to preemptible kernel context */ + if (unlikely(read_thread_flags() & _TIF_NEED_RESCHED)) { + if (preempt_count() == 0) + preempt_schedule_irq(); ++ } else if (unlikely(current_thread_info()->flags & _TIF_NEED_RESCHED_LAZY)) { ++ if ((preempt_count() == 0) && ++ (current_thread_info()->preempt_lazy_count == 0)) ++ preempt_schedule_irq(); + } + } + +-- +2.43.0 + diff --git a/debian/patches-rt/0038-arch-arm64-Add-lazy-preempt-support.patch b/debian/patches-rt/0038-arch-arm64-Add-lazy-preempt-support.patch new file mode 100644 index 000000000..4df0c8a40 --- /dev/null +++ b/debian/patches-rt/0038-arch-arm64-Add-lazy-preempt-support.patch @@ -0,0 +1,146 @@ +From 12a36ad989490f5ae3ed6a50d764385e8e27e024 Mon Sep 17 00:00:00 2001 +From: Anders Roxell <anders.roxell@linaro.org> +Date: Thu, 14 May 2015 17:52:17 +0200 +Subject: [PATCH 38/62] arch/arm64: Add lazy preempt support +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +arm64 is missing support for PREEMPT_RT. The main feature which is +lacking is support for lazy preemption. The arch-specific entry code, +thread information structure definitions, and associated data tables +have to be extended to provide this support. Then the Kconfig file has +to be extended to indicate the support is available, and also to +indicate that support for full RT preemption is now available. + +Signed-off-by: Anders Roxell <anders.roxell@linaro.org> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/arm64/Kconfig | 1 + + arch/arm64/include/asm/preempt.h | 25 ++++++++++++++++++++++++- + arch/arm64/include/asm/thread_info.h | 8 +++++++- + arch/arm64/kernel/asm-offsets.c | 1 + + arch/arm64/kernel/signal.c | 2 +- + 5 files changed, 34 insertions(+), 3 deletions(-) + +diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig +index ea70eb960565..6e16670a7f43 100644 +--- a/arch/arm64/Kconfig ++++ b/arch/arm64/Kconfig +@@ -199,6 +199,7 @@ config ARM64 + select HAVE_PERF_USER_STACK_DUMP + select HAVE_PREEMPT_DYNAMIC_KEY + select HAVE_REGS_AND_STACK_ACCESS_API ++ select HAVE_PREEMPT_LAZY + select HAVE_POSIX_CPU_TIMERS_TASK_WORK + select HAVE_FUNCTION_ARG_ACCESS_API + select MMU_GATHER_RCU_TABLE_FREE +diff --git a/arch/arm64/include/asm/preempt.h b/arch/arm64/include/asm/preempt.h +index 0159b625cc7f..a5486918e5ee 100644 +--- a/arch/arm64/include/asm/preempt.h ++++ b/arch/arm64/include/asm/preempt.h +@@ -71,13 +71,36 @@ static inline bool __preempt_count_dec_and_test(void) + * interrupt occurring between the non-atomic READ_ONCE/WRITE_ONCE + * pair. + */ +- return !pc || !READ_ONCE(ti->preempt_count); ++ if (!pc || !READ_ONCE(ti->preempt_count)) ++ return true; ++#ifdef CONFIG_PREEMPT_LAZY ++ if ((pc & ~PREEMPT_NEED_RESCHED)) ++ return false; ++ if (current_thread_info()->preempt_lazy_count) ++ return false; ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++#else ++ return false; ++#endif + } + + static inline bool should_resched(int preempt_offset) + { ++#ifdef CONFIG_PREEMPT_LAZY ++ u64 pc = READ_ONCE(current_thread_info()->preempt_count); ++ if (pc == preempt_offset) ++ return true; ++ ++ if ((pc & ~PREEMPT_NEED_RESCHED) != preempt_offset) ++ return false; ++ ++ if (current_thread_info()->preempt_lazy_count) ++ return false; ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++#else + u64 pc = READ_ONCE(current_thread_info()->preempt_count); + return pc == preempt_offset; ++#endif + } + + #ifdef CONFIG_PREEMPTION +diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h +index 848739c15de8..4b7148fd5551 100644 +--- a/arch/arm64/include/asm/thread_info.h ++++ b/arch/arm64/include/asm/thread_info.h +@@ -26,6 +26,7 @@ struct thread_info { + #ifdef CONFIG_ARM64_SW_TTBR0_PAN + u64 ttbr0; /* saved TTBR0_EL1 */ + #endif ++ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ + union { + u64 preempt_count; /* 0 => preemptible, <0 => bug */ + struct { +@@ -68,6 +69,7 @@ int arch_dup_task_struct(struct task_struct *dst, + #define TIF_UPROBE 4 /* uprobe breakpoint or singlestep */ + #define TIF_MTE_ASYNC_FAULT 5 /* MTE Asynchronous Tag Check Fault */ + #define TIF_NOTIFY_SIGNAL 6 /* signal notifications exist */ ++#define TIF_NEED_RESCHED_LAZY 7 + #define TIF_SYSCALL_TRACE 8 /* syscall trace active */ + #define TIF_SYSCALL_AUDIT 9 /* syscall auditing */ + #define TIF_SYSCALL_TRACEPOINT 10 /* syscall tracepoint for ftrace */ +@@ -100,8 +102,10 @@ int arch_dup_task_struct(struct task_struct *dst, + #define _TIF_SVE (1 << TIF_SVE) + #define _TIF_MTE_ASYNC_FAULT (1 << TIF_MTE_ASYNC_FAULT) + #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + +-#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ ++#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | \ ++ _TIF_SIGPENDING | \ + _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \ + _TIF_UPROBE | _TIF_MTE_ASYNC_FAULT | \ + _TIF_NOTIFY_SIGNAL) +@@ -110,6 +114,8 @@ int arch_dup_task_struct(struct task_struct *dst, + _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ + _TIF_SYSCALL_EMU) + ++#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) ++ + #ifdef CONFIG_SHADOW_CALL_STACK + #define INIT_SCS \ + .scs_base = init_shadow_call_stack, \ +diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c +index 1197e7679882..e74c0415f67e 100644 +--- a/arch/arm64/kernel/asm-offsets.c ++++ b/arch/arm64/kernel/asm-offsets.c +@@ -32,6 +32,7 @@ int main(void) + DEFINE(TSK_TI_CPU, offsetof(struct task_struct, thread_info.cpu)); + DEFINE(TSK_TI_FLAGS, offsetof(struct task_struct, thread_info.flags)); + DEFINE(TSK_TI_PREEMPT, offsetof(struct task_struct, thread_info.preempt_count)); ++ DEFINE(TSK_TI_PREEMPT_LAZY, offsetof(struct task_struct, thread_info.preempt_lazy_count)); + #ifdef CONFIG_ARM64_SW_TTBR0_PAN + DEFINE(TSK_TI_TTBR0, offsetof(struct task_struct, thread_info.ttbr0)); + #endif +diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c +index 82f4572c8ddf..2a606c7bf025 100644 +--- a/arch/arm64/kernel/signal.c ++++ b/arch/arm64/kernel/signal.c +@@ -1108,7 +1108,7 @@ static void do_signal(struct pt_regs *regs) + void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) + { + do { +- if (thread_flags & _TIF_NEED_RESCHED) { ++ if (thread_flags & _TIF_NEED_RESCHED_MASK) { + /* Unmask Debug and SError for the next task */ + local_daif_restore(DAIF_PROCCTX_NOIRQ); + +-- +2.43.0 + diff --git a/debian/patches-rt/0039-arm-Disable-jump-label-on-PREEMPT_RT.patch b/debian/patches-rt/0039-arm-Disable-jump-label-on-PREEMPT_RT.patch new file mode 100644 index 000000000..ac47159c4 --- /dev/null +++ b/debian/patches-rt/0039-arm-Disable-jump-label-on-PREEMPT_RT.patch @@ -0,0 +1,42 @@ +From f1c0950a69e46ee1d45192bfae026622da60bdc8 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Wed, 8 Jul 2015 17:14:48 +0200 +Subject: [PATCH 39/62] arm: Disable jump-label on PREEMPT_RT. +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +jump-labels are used to efficiently switch between two possible code +paths. To achieve this, stop_machine() is used to keep the CPU in a +known state while the opcode is modified. The usage of stop_machine() +here leads to large latency spikes which can be observed on PREEMPT_RT. + +Jump labels may change the target during runtime and are not restricted +to debug or "configuration/ setup" part of a PREEMPT_RT system where +high latencies could be defined as acceptable. + +Disable jump-label support on a PREEMPT_RT system. + +[bigeasy: Patch description.] + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Link: https://lkml.kernel.org/r/20220613182447.112191-2-bigeasy@linutronix.de +--- + arch/arm/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig +index 717e596dc13b..f170f29e98ac 100644 +--- a/arch/arm/Kconfig ++++ b/arch/arm/Kconfig +@@ -71,7 +71,7 @@ config ARM + select HARDIRQS_SW_RESEND + select HAVE_ARCH_AUDITSYSCALL if AEABI && !OABI_COMPAT + select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 +- select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU ++ select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU && !PREEMPT_RT + select HAVE_ARCH_KFENCE if MMU && !XIP_KERNEL + select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU + select HAVE_ARCH_KASAN if MMU && !XIP_KERNEL +-- +2.43.0 + diff --git a/debian/patches-rt/0040-ARM-enable-irq-in-translation-section-permission-fau.patch b/debian/patches-rt/0040-ARM-enable-irq-in-translation-section-permission-fau.patch new file mode 100644 index 000000000..ee53f7bd6 --- /dev/null +++ b/debian/patches-rt/0040-ARM-enable-irq-in-translation-section-permission-fau.patch @@ -0,0 +1,97 @@ +From 802d6978bf4ebdec28d2ba4e715c2e414d9c7d06 Mon Sep 17 00:00:00 2001 +From: "Yadi.hu" <yadi.hu@windriver.com> +Date: Wed, 10 Dec 2014 10:32:09 +0800 +Subject: [PATCH 40/62] ARM: enable irq in translation/section permission fault + handlers +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Probably happens on all ARM, with +CONFIG_PREEMPT_RT +CONFIG_DEBUG_ATOMIC_SLEEP + +This simple program.... + +int main() { + *((char*)0xc0001000) = 0; +}; + +[ 512.742724] BUG: sleeping function called from invalid context at kernel/rtmutex.c:658 +[ 512.743000] in_atomic(): 0, irqs_disabled(): 128, pid: 994, name: a +[ 512.743217] INFO: lockdep is turned off. +[ 512.743360] irq event stamp: 0 +[ 512.743482] hardirqs last enabled at (0): [< (null)>] (null) +[ 512.743714] hardirqs last disabled at (0): [<c0426370>] copy_process+0x3b0/0x11c0 +[ 512.744013] softirqs last enabled at (0): [<c0426370>] copy_process+0x3b0/0x11c0 +[ 512.744303] softirqs last disabled at (0): [< (null)>] (null) +[ 512.744631] [<c041872c>] (unwind_backtrace+0x0/0x104) +[ 512.745001] [<c09af0c4>] (dump_stack+0x20/0x24) +[ 512.745355] [<c0462490>] (__might_sleep+0x1dc/0x1e0) +[ 512.745717] [<c09b6770>] (rt_spin_lock+0x34/0x6c) +[ 512.746073] [<c0441bf0>] (do_force_sig_info+0x34/0xf0) +[ 512.746457] [<c0442668>] (force_sig_info+0x18/0x1c) +[ 512.746829] [<c041d880>] (__do_user_fault+0x9c/0xd8) +[ 512.747185] [<c041d938>] (do_bad_area+0x7c/0x94) +[ 512.747536] [<c041d990>] (do_sect_fault+0x40/0x48) +[ 512.747898] [<c040841c>] (do_DataAbort+0x40/0xa0) +[ 512.748181] Exception stack(0xecaa1fb0 to 0xecaa1ff8) + +Oxc0000000 belongs to kernel address space, user task can not be +allowed to access it. For above condition, correct result is that +test case should receive a “segment fault” and exits but not stacks. + +the root cause is commit 02fe2845d6a8 ("avoid enabling interrupts in +prefetch/data abort handlers"),it deletes irq enable block in Data +abort assemble code and move them into page/breakpiont/alignment fault +handlers instead. But author does not enable irq in translation/section +permission fault handlers. ARM disables irq when it enters exception/ +interrupt mode, if kernel doesn't enable irq, it would be still disabled +during translation/section permission fault. + +We see the above splat because do_force_sig_info is still called with +IRQs off, and that code eventually does a: + + spin_lock_irqsave(&t->sighand->siglock, flags); + +As this is architecture independent code, and we've not seen any other +need for other arch to have the siglock converted to raw lock, we can +conclude that we should enable irq for ARM translation/section +permission exception. + + +Signed-off-by: Yadi.hu <yadi.hu@windriver.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/arm/mm/fault.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c +index b0db85310331..77877dcb54ed 100644 +--- a/arch/arm/mm/fault.c ++++ b/arch/arm/mm/fault.c +@@ -400,6 +400,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr, + if (addr < TASK_SIZE) + return do_page_fault(addr, fsr, regs); + ++ if (interrupts_enabled(regs)) ++ local_irq_enable(); ++ + if (user_mode(regs)) + goto bad_area; + +@@ -470,6 +473,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr, + static int + do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) + { ++ if (interrupts_enabled(regs)) ++ local_irq_enable(); ++ + do_bad_area(addr, fsr, regs); + return 0; + } +-- +2.43.0 + diff --git a/debian/patches-rt/0041-tty-serial-omap-Make-the-locking-RT-aware.patch b/debian/patches-rt/0041-tty-serial-omap-Make-the-locking-RT-aware.patch new file mode 100644 index 000000000..b719f7f3b --- /dev/null +++ b/debian/patches-rt/0041-tty-serial-omap-Make-the-locking-RT-aware.patch @@ -0,0 +1,49 @@ +From 2a89ee21ea5c408b560839cc06bd0c13580fb3a4 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 28 Jul 2011 13:32:57 +0200 +Subject: [PATCH 41/62] tty/serial/omap: Make the locking RT aware +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +The lock is a sleeping lock and local_irq_save() is not the +optimsation we are looking for. Redo it to make it work on -RT and +non-RT. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + drivers/tty/serial/omap-serial.c | 12 ++++-------- + 1 file changed, 4 insertions(+), 8 deletions(-) + +diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c +index 7d0d2718ef59..aa216fdbcb1d 100644 +--- a/drivers/tty/serial/omap-serial.c ++++ b/drivers/tty/serial/omap-serial.c +@@ -1241,13 +1241,10 @@ serial_omap_console_write(struct console *co, const char *s, + unsigned int ier; + int locked = 1; + +- local_irq_save(flags); +- if (up->port.sysrq) +- locked = 0; +- else if (oops_in_progress) +- locked = spin_trylock(&up->port.lock); ++ if (up->port.sysrq || oops_in_progress) ++ locked = spin_trylock_irqsave(&up->port.lock, flags); + else +- spin_lock(&up->port.lock); ++ spin_lock_irqsave(&up->port.lock, flags); + + /* + * First save the IER then disable the interrupts +@@ -1274,8 +1271,7 @@ serial_omap_console_write(struct console *co, const char *s, + check_modem_status(up); + + if (locked) +- spin_unlock(&up->port.lock); +- local_irq_restore(flags); ++ spin_unlock_irqrestore(&up->port.lock, flags); + } + + static int __init +-- +2.43.0 + diff --git a/debian/patches-rt/0042-tty-serial-pl011-Make-the-locking-work-on-RT.patch b/debian/patches-rt/0042-tty-serial-pl011-Make-the-locking-work-on-RT.patch new file mode 100644 index 000000000..c80dc32de --- /dev/null +++ b/debian/patches-rt/0042-tty-serial-pl011-Make-the-locking-work-on-RT.patch @@ -0,0 +1,60 @@ +From 1db3dc8a6af68447b52efbbf8dbb4d210d23d57b Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Tue, 8 Jan 2013 21:36:51 +0100 +Subject: [PATCH 42/62] tty/serial/pl011: Make the locking work on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +The lock is a sleeping lock and local_irq_save() is not the optimsation +we are looking for. Redo it to make it work on -RT and non-RT. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + drivers/tty/serial/amba-pl011.c | 17 +++++++++++------ + 1 file changed, 11 insertions(+), 6 deletions(-) + +diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c +index c74eaf2552c3..38eb30b8491b 100644 +--- a/drivers/tty/serial/amba-pl011.c ++++ b/drivers/tty/serial/amba-pl011.c +@@ -2316,18 +2316,24 @@ pl011_console_write(struct console *co, const char *s, unsigned int count) + { + struct uart_amba_port *uap = amba_ports[co->index]; + unsigned int old_cr = 0, new_cr; +- unsigned long flags; ++ unsigned long flags = 0; + int locked = 1; + + clk_enable(uap->clk); + +- local_irq_save(flags); ++ /* ++ * local_irq_save(flags); ++ * ++ * This local_irq_save() is nonsense. If we come in via sysrq ++ * handling then interrupts are already disabled. Aside of ++ * that the port.sysrq check is racy on SMP regardless. ++ */ + if (uap->port.sysrq) + locked = 0; + else if (oops_in_progress) +- locked = spin_trylock(&uap->port.lock); ++ locked = spin_trylock_irqsave(&uap->port.lock, flags); + else +- spin_lock(&uap->port.lock); ++ spin_lock_irqsave(&uap->port.lock, flags); + + /* + * First save the CR then disable the interrupts +@@ -2353,8 +2359,7 @@ pl011_console_write(struct console *co, const char *s, unsigned int count) + pl011_write(old_cr, uap, REG_CR); + + if (locked) +- spin_unlock(&uap->port.lock); +- local_irq_restore(flags); ++ spin_unlock_irqrestore(&uap->port.lock, flags); + + clk_disable(uap->clk); + } +-- +2.43.0 + diff --git a/debian/patches-rt/0043-ARM-Allow-to-enable-RT.patch b/debian/patches-rt/0043-ARM-Allow-to-enable-RT.patch new file mode 100644 index 000000000..dd5a320a2 --- /dev/null +++ b/debian/patches-rt/0043-ARM-Allow-to-enable-RT.patch @@ -0,0 +1,37 @@ +From 47c9956482a592a16b58831ded27e3c0f62ec11d Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 11 Oct 2019 13:14:29 +0200 +Subject: [PATCH 43/62] ARM: Allow to enable RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Allow to select RT. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/arm/Kconfig | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig +index f170f29e98ac..d1f2e062ce0b 100644 +--- a/arch/arm/Kconfig ++++ b/arch/arm/Kconfig +@@ -33,6 +33,7 @@ config ARM + select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT if CPU_V7 + select ARCH_SUPPORTS_ATOMIC_RMW + select ARCH_SUPPORTS_HUGETLBFS if ARM_LPAE ++ select ARCH_SUPPORTS_RT if HAVE_POSIX_CPU_TIMERS_TASK_WORK + select ARCH_USE_BUILTIN_BSWAP + select ARCH_USE_CMPXCHG_LOCKREF + select ARCH_USE_MEMTEST +@@ -115,6 +116,7 @@ config ARM + select HAVE_PERF_EVENTS + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP ++ select HAVE_POSIX_CPU_TIMERS_TASK_WORK if !KVM + select HAVE_PREEMPT_LAZY + select MMU_GATHER_RCU_TABLE_FREE if SMP && ARM_LPAE + select HAVE_REGS_AND_STACK_ACCESS_API +-- +2.43.0 + diff --git a/debian/patches-rt/0044-ARM64-Allow-to-enable-RT.patch b/debian/patches-rt/0044-ARM64-Allow-to-enable-RT.patch new file mode 100644 index 000000000..478d2e7a8 --- /dev/null +++ b/debian/patches-rt/0044-ARM64-Allow-to-enable-RT.patch @@ -0,0 +1,29 @@ +From c71e1e0561e008bb2fe230ad7022c3e2483cd6c0 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 11 Oct 2019 13:14:35 +0200 +Subject: [PATCH 44/62] ARM64: Allow to enable RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Allow to select RT. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/arm64/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig +index 6e16670a7f43..0c617e48177c 100644 +--- a/arch/arm64/Kconfig ++++ b/arch/arm64/Kconfig +@@ -93,6 +93,7 @@ config ARM64 + select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 + select ARCH_SUPPORTS_NUMA_BALANCING + select ARCH_SUPPORTS_PAGE_TABLE_CHECK ++ select ARCH_SUPPORTS_RT + select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT + select ARCH_WANT_DEFAULT_BPF_JIT + select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT +-- +2.43.0 + diff --git a/debian/patches-rt/0045-powerpc-traps-Use-PREEMPT_RT.patch b/debian/patches-rt/0045-powerpc-traps-Use-PREEMPT_RT.patch new file mode 100644 index 000000000..76c18de22 --- /dev/null +++ b/debian/patches-rt/0045-powerpc-traps-Use-PREEMPT_RT.patch @@ -0,0 +1,40 @@ +From 4d7273bd07600b933e6d25807cd96df04e435cbe Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 26 Jul 2019 11:30:49 +0200 +Subject: [PATCH 45/62] powerpc: traps: Use PREEMPT_RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Add PREEMPT_RT to the backtrace if enabled. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/powerpc/kernel/traps.c | 7 ++++++- + 1 file changed, 6 insertions(+), 1 deletion(-) + +diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c +index 3956f32682c6..8e15205e51ef 100644 +--- a/arch/powerpc/kernel/traps.c ++++ b/arch/powerpc/kernel/traps.c +@@ -261,12 +261,17 @@ static char *get_mmu_str(void) + + static int __die(const char *str, struct pt_regs *regs, long err) + { ++ const char *pr = ""; ++ + printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter); + ++ if (IS_ENABLED(CONFIG_PREEMPTION)) ++ pr = IS_ENABLED(CONFIG_PREEMPT_RT) ? " PREEMPT_RT" : " PREEMPT"; ++ + printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s %s\n", + IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE", + PAGE_SIZE / 1024, get_mmu_str(), +- IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "", ++ pr, + IS_ENABLED(CONFIG_SMP) ? " SMP" : "", + IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "", + debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "", +-- +2.43.0 + diff --git a/debian/patches-rt/0046-powerpc-pseries-iommu-Use-a-locallock-instead-local_.patch b/debian/patches-rt/0046-powerpc-pseries-iommu-Use-a-locallock-instead-local_.patch new file mode 100644 index 000000000..9d6e8ab00 --- /dev/null +++ b/debian/patches-rt/0046-powerpc-pseries-iommu-Use-a-locallock-instead-local_.patch @@ -0,0 +1,118 @@ +From 1d20f49e62250211b43cbe18a087fdf19c313081 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 26 Mar 2019 18:31:54 +0100 +Subject: [PATCH 46/62] powerpc/pseries/iommu: Use a locallock instead + local_irq_save() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +The locallock protects the per-CPU variable tce_page. The function +attempts to allocate memory while tce_page is protected (by disabling +interrupts). + +Use local_irq_save() instead of local_irq_disable(). + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/powerpc/platforms/pseries/iommu.c | 31 +++++++++++++++++--------- + 1 file changed, 20 insertions(+), 11 deletions(-) + +diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c +index 97b026130c71..01b3d19be382 100644 +--- a/arch/powerpc/platforms/pseries/iommu.c ++++ b/arch/powerpc/platforms/pseries/iommu.c +@@ -24,6 +24,7 @@ + #include <linux/of.h> + #include <linux/iommu.h> + #include <linux/rculist.h> ++#include <linux/local_lock.h> + #include <asm/io.h> + #include <asm/prom.h> + #include <asm/rtas.h> +@@ -200,7 +201,13 @@ static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift, + return ret; + } + +-static DEFINE_PER_CPU(__be64 *, tce_page); ++struct tce_page { ++ __be64 * page; ++ local_lock_t lock; ++}; ++static DEFINE_PER_CPU(struct tce_page, tce_page) = { ++ .lock = INIT_LOCAL_LOCK(lock), ++}; + + static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, + long npages, unsigned long uaddr, +@@ -223,9 +230,10 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, + direction, attrs); + } + +- local_irq_save(flags); /* to protect tcep and the page behind it */ ++ /* to protect tcep and the page behind it */ ++ local_lock_irqsave(&tce_page.lock, flags); + +- tcep = __this_cpu_read(tce_page); ++ tcep = __this_cpu_read(tce_page.page); + + /* This is safe to do since interrupts are off when we're called + * from iommu_alloc{,_sg}() +@@ -234,12 +242,12 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, + tcep = (__be64 *)__get_free_page(GFP_ATOMIC); + /* If allocation fails, fall back to the loop implementation */ + if (!tcep) { +- local_irq_restore(flags); ++ local_unlock_irqrestore(&tce_page.lock, flags); + return tce_build_pSeriesLP(tbl->it_index, tcenum, + tceshift, + npages, uaddr, direction, attrs); + } +- __this_cpu_write(tce_page, tcep); ++ __this_cpu_write(tce_page.page, tcep); + } + + rpn = __pa(uaddr) >> tceshift; +@@ -269,7 +277,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, + tcenum += limit; + } while (npages > 0 && !rc); + +- local_irq_restore(flags); ++ local_unlock_irqrestore(&tce_page.lock, flags); + + if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) { + ret = (int)rc; +@@ -454,16 +462,17 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, + DMA_BIDIRECTIONAL, 0); + } + +- local_irq_disable(); /* to protect tcep and the page behind it */ +- tcep = __this_cpu_read(tce_page); ++ /* to protect tcep and the page behind it */ ++ local_lock_irq(&tce_page.lock); ++ tcep = __this_cpu_read(tce_page.page); + + if (!tcep) { + tcep = (__be64 *)__get_free_page(GFP_ATOMIC); + if (!tcep) { +- local_irq_enable(); ++ local_unlock_irq(&tce_page.lock); + return -ENOMEM; + } +- __this_cpu_write(tce_page, tcep); ++ __this_cpu_write(tce_page.page, tcep); + } + + proto_tce = TCE_PCI_READ | TCE_PCI_WRITE; +@@ -506,7 +515,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, + + /* error cleanup: caller will clear whole range */ + +- local_irq_enable(); ++ local_unlock_irq(&tce_page.lock); + return rc; + } + +-- +2.43.0 + diff --git a/debian/patches-rt/0047-powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch b/debian/patches-rt/0047-powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch new file mode 100644 index 000000000..937a75d99 --- /dev/null +++ b/debian/patches-rt/0047-powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch @@ -0,0 +1,46 @@ +From 34f52991170848510810b486dd6fe9a19cbe4c46 Mon Sep 17 00:00:00 2001 +From: Bogdan Purcareata <bogdan.purcareata@freescale.com> +Date: Fri, 24 Apr 2015 15:53:13 +0000 +Subject: [PATCH 47/62] powerpc/kvm: Disable in-kernel MPIC emulation for + PREEMPT_RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +While converting the openpic emulation code to use a raw_spinlock_t enables +guests to run on RT, there's still a performance issue. For interrupts sent in +directed delivery mode with a multiple CPU mask, the emulated openpic will loop +through all of the VCPUs, and for each VCPUs, it call IRQ_check, which will loop +through all the pending interrupts for that VCPU. This is done while holding the +raw_lock, meaning that in all this time the interrupts and preemption are +disabled on the host Linux. A malicious user app can max both these number and +cause a DoS. + +This temporary fix is sent for two reasons. First is so that users who want to +use the in-kernel MPIC emulation are aware of the potential latencies, thus +making sure that the hardware MPIC and their usage scenario does not involve +interrupts sent in directed delivery mode, and the number of possible pending +interrupts is kept small. Secondly, this should incentivize the development of a +proper openpic emulation that would be better suited for RT. + +Acked-by: Scott Wood <scottwood@freescale.com> +Signed-off-by: Bogdan Purcareata <bogdan.purcareata@freescale.com> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/powerpc/kvm/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig +index a9f57dad6d91..a0b528d4bb7c 100644 +--- a/arch/powerpc/kvm/Kconfig ++++ b/arch/powerpc/kvm/Kconfig +@@ -225,6 +225,7 @@ config KVM_E500MC + config KVM_MPIC + bool "KVM in-kernel MPIC emulation" + depends on KVM && PPC_E500 ++ depends on !PREEMPT_RT + select HAVE_KVM_IRQCHIP + select HAVE_KVM_IRQFD + select HAVE_KVM_IRQ_ROUTING +-- +2.43.0 + diff --git a/debian/patches-rt/0048-powerpc-stackprotector-work-around-stack-guard-init-.patch b/debian/patches-rt/0048-powerpc-stackprotector-work-around-stack-guard-init-.patch new file mode 100644 index 000000000..df6dbe080 --- /dev/null +++ b/debian/patches-rt/0048-powerpc-stackprotector-work-around-stack-guard-init-.patch @@ -0,0 +1,37 @@ +From d2e9a96e5570459dd886f87bf81c7714fb0a2108 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 26 Mar 2019 18:31:29 +0100 +Subject: [PATCH 48/62] powerpc/stackprotector: work around stack-guard init + from atomic +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +This is invoked from the secondary CPU in atomic context. On x86 we use +tsc instead. On Power we XOR it against mftb() so lets use stack address +as the initial value. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/powerpc/include/asm/stackprotector.h | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/arch/powerpc/include/asm/stackprotector.h b/arch/powerpc/include/asm/stackprotector.h +index 1c8460e23583..b1653c160bab 100644 +--- a/arch/powerpc/include/asm/stackprotector.h ++++ b/arch/powerpc/include/asm/stackprotector.h +@@ -24,7 +24,11 @@ static __always_inline void boot_init_stack_canary(void) + unsigned long canary; + + /* Try to get a semi random initial value. */ ++#ifdef CONFIG_PREEMPT_RT ++ canary = (unsigned long)&canary; ++#else + canary = get_random_canary(); ++#endif + canary ^= mftb(); + canary ^= LINUX_VERSION_CODE; + canary &= CANARY_MASK; +-- +2.43.0 + diff --git a/debian/patches-rt/0049-POWERPC-Allow-to-enable-RT.patch b/debian/patches-rt/0049-POWERPC-Allow-to-enable-RT.patch new file mode 100644 index 000000000..72ea26d09 --- /dev/null +++ b/debian/patches-rt/0049-POWERPC-Allow-to-enable-RT.patch @@ -0,0 +1,37 @@ +From 93941796079cb4515170adf454f9218adc89856d Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 11 Oct 2019 13:14:41 +0200 +Subject: [PATCH 49/62] POWERPC: Allow to enable RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Allow to select RT. + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + arch/powerpc/Kconfig | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig +index 0eff864d6ec3..df697d3f68cd 100644 +--- a/arch/powerpc/Kconfig ++++ b/arch/powerpc/Kconfig +@@ -151,6 +151,7 @@ config PPC + select ARCH_STACKWALK + select ARCH_SUPPORTS_ATOMIC_RMW + select ARCH_SUPPORTS_DEBUG_PAGEALLOC if PPC_BOOK3S || PPC_8xx || 40x ++ select ARCH_SUPPORTS_RT if HAVE_POSIX_CPU_TIMERS_TASK_WORK + select ARCH_USE_BUILTIN_BSWAP + select ARCH_USE_CMPXCHG_LOCKREF if PPC64 + select ARCH_USE_MEMTEST +@@ -245,6 +246,7 @@ config PPC + select HAVE_PREEMPT_LAZY + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RELIABLE_STACKTRACE ++ select HAVE_POSIX_CPU_TIMERS_TASK_WORK if !KVM + select HAVE_RSEQ + select HAVE_SETUP_PER_CPU_AREA if PPC64 + select HAVE_SOFTIRQ_ON_OWN_STACK +-- +2.43.0 + diff --git a/debian/patches-rt/0050-sysfs-Add-sys-kernel-realtime-entry.patch b/debian/patches-rt/0050-sysfs-Add-sys-kernel-realtime-entry.patch new file mode 100644 index 000000000..bebe5bd1b --- /dev/null +++ b/debian/patches-rt/0050-sysfs-Add-sys-kernel-realtime-entry.patch @@ -0,0 +1,55 @@ +From b2103f830327ab5d1e6f49134c22d3c5adfb52cc Mon Sep 17 00:00:00 2001 +From: Clark Williams <williams@redhat.com> +Date: Sat, 30 Jul 2011 21:55:53 -0500 +Subject: [PATCH 50/62] sysfs: Add /sys/kernel/realtime entry +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Add a /sys/kernel entry to indicate that the kernel is a +realtime kernel. + +Clark says that he needs this for udev rules, udev needs to evaluate +if its a PREEMPT_RT kernel a few thousand times and parsing uname +output is too slow or so. + +Are there better solutions? Should it exist and return 0 on !-rt? + +Signed-off-by: Clark Williams <williams@redhat.com> +Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + kernel/ksysfs.c | 12 ++++++++++++ + 1 file changed, 12 insertions(+) + +diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c +index 65dba9076f31..ab18048e2186 100644 +--- a/kernel/ksysfs.c ++++ b/kernel/ksysfs.c +@@ -142,6 +142,15 @@ KERNEL_ATTR_RO(vmcoreinfo); + + #endif /* CONFIG_CRASH_CORE */ + ++#if defined(CONFIG_PREEMPT_RT) ++static ssize_t realtime_show(struct kobject *kobj, ++ struct kobj_attribute *attr, char *buf) ++{ ++ return sprintf(buf, "%d\n", 1); ++} ++KERNEL_ATTR_RO(realtime); ++#endif ++ + /* whether file capabilities are enabled */ + static ssize_t fscaps_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +@@ -232,6 +241,9 @@ static struct attribute * kernel_attrs[] = { + #ifndef CONFIG_TINY_RCU + &rcu_expedited_attr.attr, + &rcu_normal_attr.attr, ++#endif ++#ifdef CONFIG_PREEMPT_RT ++ &realtime_attr.attr, + #endif + NULL + }; +-- +2.43.0 + diff --git a/debian/patches-rt/0051-Add-localversion-for-RT-release.patch b/debian/patches-rt/0051-Add-localversion-for-RT-release.patch new file mode 100644 index 000000000..f2ecbea44 --- /dev/null +++ b/debian/patches-rt/0051-Add-localversion-for-RT-release.patch @@ -0,0 +1,22 @@ +From 9c7d6e723acbbc184d1dd04811863378699134fb Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Fri, 8 Jul 2011 20:25:16 +0200 +Subject: [PATCH 51/62] Add localversion for -RT release +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +--- + localversion-rt | 1 + + 1 file changed, 1 insertion(+) + create mode 100644 localversion-rt + +diff --git a/localversion-rt b/localversion-rt +new file mode 100644 +index 000000000000..045478966e9f +--- /dev/null ++++ b/localversion-rt +@@ -0,0 +1 @@ ++-rt7 +-- +2.43.0 + diff --git a/debian/patches-rt/0052-Linux-6.1.46-rt13-REBASE.patch b/debian/patches-rt/0052-Linux-6.1.46-rt13-REBASE.patch new file mode 100644 index 000000000..3096368f3 --- /dev/null +++ b/debian/patches-rt/0052-Linux-6.1.46-rt13-REBASE.patch @@ -0,0 +1,21 @@ +From 3f783498b292a814f8f364bbfd0efbfc1be6d30f Mon Sep 17 00:00:00 2001 +From: Clark Williams <clrkwllms@kernel.org> +Date: Fri, 18 Aug 2023 10:45:35 -0500 +Subject: [PATCH 52/62] 'Linux 6.1.46-rt13 REBASE' +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Signed-off-by: Clark Williams <clrkwllms@kernel.org> +--- + localversion-rt | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/localversion-rt b/localversion-rt +index 045478966e9f..9f7d0bdbffb1 100644 +--- a/localversion-rt ++++ b/localversion-rt +@@ -1 +1 @@ +--rt7 ++-rt13 +-- +2.43.0 + diff --git a/debian/patches-rt/0053-io-mapping-don-t-disable-preempt-on-RT-in-io_mapping.patch b/debian/patches-rt/0053-io-mapping-don-t-disable-preempt-on-RT-in-io_mapping.patch new file mode 100644 index 000000000..b4b695541 --- /dev/null +++ b/debian/patches-rt/0053-io-mapping-don-t-disable-preempt-on-RT-in-io_mapping.patch @@ -0,0 +1,93 @@ +From 53c6a09e670e985d37ca05785a0155ab51b49cf4 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 10 Mar 2023 17:29:05 +0100 +Subject: [PATCH 53/62] io-mapping: don't disable preempt on RT in + io_mapping_map_atomic_wc(). +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +io_mapping_map_atomic_wc() disables preemption and pagefaults for +historical reasons. The conversion to io_mapping_map_local_wc(), which +only disables migration, cannot be done wholesale because quite some call +sites need to be updated to accommodate with the changed semantics. + +On PREEMPT_RT enabled kernels the io_mapping_map_atomic_wc() semantics are +problematic due to the implicit disabling of preemption which makes it +impossible to acquire 'sleeping' spinlocks within the mapped atomic +sections. + +PREEMPT_RT replaces the preempt_disable() with a migrate_disable() for +more than a decade. It could be argued that this is a justification to do +this unconditionally, but PREEMPT_RT covers only a limited number of +architectures and it disables some functionality which limits the coverage +further. + +Limit the replacement to PREEMPT_RT for now. This is also done +kmap_atomic(). + +Link: https://lkml.kernel.org/r/20230310162905.O57Pj7hh@linutronix.de +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Reported-by: Richard Weinberger <richard.weinberger@gmail.com> + Link: https://lore.kernel.org/CAFLxGvw0WMxaMqYqJ5WgvVSbKHq2D2xcXTOgMCpgq9nDC-MWTQ@mail.gmail.com +Cc: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Andrew Morton <akpm@linux-foundation.org> +(cherry picked from commit 7eb16f23b9a415f062db22739e59bb144e0b24ab) +Signed-off-by: Clark Williams <clark.williams@gmail.com> +--- + include/linux/io-mapping.h | 20 ++++++++++++++++---- + 1 file changed, 16 insertions(+), 4 deletions(-) + +diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h +index 66a774d2710e..b08532b8fba7 100644 +--- a/include/linux/io-mapping.h ++++ b/include/linux/io-mapping.h +@@ -69,7 +69,10 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping, + + BUG_ON(offset >= mapping->size); + phys_addr = mapping->base + offset; +- preempt_disable(); ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ++ preempt_disable(); ++ else ++ migrate_disable(); + pagefault_disable(); + return __iomap_local_pfn_prot(PHYS_PFN(phys_addr), mapping->prot); + } +@@ -79,7 +82,10 @@ io_mapping_unmap_atomic(void __iomem *vaddr) + { + kunmap_local_indexed((void __force *)vaddr); + pagefault_enable(); +- preempt_enable(); ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ++ preempt_enable(); ++ else ++ migrate_enable(); + } + + static inline void __iomem * +@@ -162,7 +168,10 @@ static inline void __iomem * + io_mapping_map_atomic_wc(struct io_mapping *mapping, + unsigned long offset) + { +- preempt_disable(); ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ++ preempt_disable(); ++ else ++ migrate_disable(); + pagefault_disable(); + return io_mapping_map_wc(mapping, offset, PAGE_SIZE); + } +@@ -172,7 +181,10 @@ io_mapping_unmap_atomic(void __iomem *vaddr) + { + io_mapping_unmap(vaddr); + pagefault_enable(); +- preempt_enable(); ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ++ preempt_enable(); ++ else ++ migrate_enable(); + } + + static inline void __iomem * +-- +2.43.0 + diff --git a/debian/patches-rt/0054-locking-rwbase-Mitigate-indefinite-writer-starvation.patch b/debian/patches-rt/0054-locking-rwbase-Mitigate-indefinite-writer-starvation.patch new file mode 100644 index 000000000..1940c66d7 --- /dev/null +++ b/debian/patches-rt/0054-locking-rwbase-Mitigate-indefinite-writer-starvation.patch @@ -0,0 +1,63 @@ +From 8785dde5198dc91cbb518044e1c6d301ef9a9857 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Tue, 21 Mar 2023 17:11:40 +0100 +Subject: [PATCH 54/62] locking/rwbase: Mitigate indefinite writer starvation +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +On PREEMPT_RT, rw_semaphore and rwlock_t locks are unfair to writers. +Readers can indefinitely acquire the lock unless the writer fully acquired +the lock, which might never happen if there is always a reader in the +critical section owning the lock. + +Mel Gorman reported that since LTP-20220121 the dio_truncate test case +went from having 1 reader to having 16 readers and that number of readers +is sufficient to prevent the down_write ever succeeding while readers +exist. Eventually the test is killed after 30 minutes as a failure. + +Mel proposed a timeout to limit how long a writer can be blocked until +the reader is forced into the slowpath. + +Thomas argued that there is no added value by providing this timeout. From +a PREEMPT_RT point of view, there are no critical rw_semaphore or rwlock_t +locks left where the reader must be preferred. + +Mitigate indefinite writer starvation by forcing the READER into the +slowpath once the WRITER attempts to acquire the lock. + +Reported-by: Mel Gorman <mgorman@techsingularity.net> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Ingo Molnar <mingo@kernel.org> +Acked-by: Mel Gorman <mgorman@techsingularity.net> +Link: https://lore.kernel.org/877cwbq4cq.ffs@tglx +Link: https://lore.kernel.org/r/20230321161140.HMcQEhHb@linutronix.de +Cc: Linus Torvalds <torvalds@linux-foundation.org> +(cherry picked from commit 286deb7ec03d941664ac3ffaff58814b454adf65) +Signed-off-by: Clark Williams <clark.williams@gmail.com> +--- + kernel/locking/rwbase_rt.c | 9 --------- + 1 file changed, 9 deletions(-) + +diff --git a/kernel/locking/rwbase_rt.c b/kernel/locking/rwbase_rt.c +index c201aadb9301..25ec0239477c 100644 +--- a/kernel/locking/rwbase_rt.c ++++ b/kernel/locking/rwbase_rt.c +@@ -72,15 +72,6 @@ static int __sched __rwbase_read_lock(struct rwbase_rt *rwb, + int ret; + + raw_spin_lock_irq(&rtm->wait_lock); +- /* +- * Allow readers, as long as the writer has not completely +- * acquired the semaphore for write. +- */ +- if (atomic_read(&rwb->readers) != WRITER_BIAS) { +- atomic_inc(&rwb->readers); +- raw_spin_unlock_irq(&rtm->wait_lock); +- return 0; +- } + + /* + * Call into the slow lock path with the rtmutex->wait_lock +-- +2.43.0 + diff --git a/debian/patches-rt/0055-revert-softirq-Let-ksoftirqd-do-its-job.patch b/debian/patches-rt/0055-revert-softirq-Let-ksoftirqd-do-its-job.patch new file mode 100644 index 000000000..c9ed7f6f6 --- /dev/null +++ b/debian/patches-rt/0055-revert-softirq-Let-ksoftirqd-do-its-job.patch @@ -0,0 +1,108 @@ +From fcdb9b29c6d58895a386ac23229564fad2c316b5 Mon Sep 17 00:00:00 2001 +From: Paolo Abeni <pabeni@redhat.com> +Date: Mon, 8 May 2023 08:17:44 +0200 +Subject: [PATCH 55/62] revert: "softirq: Let ksoftirqd do its job" +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Due to the mentioned commit, when the ksoftirqd processes take charge +of softirq processing, the system can experience high latencies. + +In the past a few workarounds have been implemented for specific +side-effects of the above: + +commit 1ff688209e2e ("watchdog: core: make sure the watchdog_worker is not deferred") +commit 8d5755b3f77b ("watchdog: softdog: fire watchdog even if softirqs do not get to run") +commit 217f69743681 ("net: busy-poll: allow preemption in sk_busy_loop()") +commit 3c53776e29f8 ("Mark HI and TASKLET softirq synchronous") + +but the latency problem still exists in real-life workloads, see the +link below. + +The reverted commit intended to solve a live-lock scenario that can now +be addressed with the NAPI threaded mode, introduced with commit +29863d41bb6e ("net: implement threaded-able napi poll loop support"), +and nowadays in a pretty stable status. + +While a complete solution to put softirq processing under nice resource +control would be preferable, that has proven to be a very hard task. In +the short term, remove the main pain point, and also simplify a bit the +current softirq implementation. + +Note that this change also reverts commit 3c53776e29f8 ("Mark HI and +TASKLET softirq synchronous") and commit 1342d8080f61 ("softirq: Don't +skip softirq execution when softirq thread is parking"), which are +direct follow-ups of the feature commit. A single change is preferred to +avoid known bad intermediate states introduced by a patch series +reverting them individually. + +Link: https://lore.kernel.org/netdev/305d7742212cbe98621b16be782b0562f1012cb6.camel@redhat.com/ +Signed-off-by: Paolo Abeni <pabeni@redhat.com> +Tested-by: Jason Xing <kerneljasonxing@gmail.com> +Reviewed-by: Jakub Kicinski <kuba@kernel.org> +Reviewed-by: Eric Dumazet <edumazet@google.com> +Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Link: https://lore.kernel.org/r/57e66b364f1b6f09c9bc0316742c3b14f4ce83bd.1683526542.git.pabeni@redhat.com +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +(cherry picked from commit b8a04a538ed4755dc97c403ee3b8dd882955c98c) +Signed-off-by: Clark Williams <clark.williams@gmail.com> +--- + kernel/softirq.c | 22 ++-------------------- + 1 file changed, 2 insertions(+), 20 deletions(-) + +diff --git a/kernel/softirq.c b/kernel/softirq.c +index 82f3e68fbe22..af9e879bbbf7 100644 +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -80,21 +80,6 @@ static void wakeup_softirqd(void) + wake_up_process(tsk); + } + +-/* +- * If ksoftirqd is scheduled, we do not want to process pending softirqs +- * right now. Let ksoftirqd handle this at its own rate, to get fairness, +- * unless we're doing some of the synchronous softirqs. +- */ +-#define SOFTIRQ_NOW_MASK ((1 << HI_SOFTIRQ) | (1 << TASKLET_SOFTIRQ)) +-static bool ksoftirqd_running(unsigned long pending) +-{ +- struct task_struct *tsk = __this_cpu_read(ksoftirqd); +- +- if (pending & SOFTIRQ_NOW_MASK) +- return false; +- return tsk && task_is_running(tsk) && !__kthread_should_park(tsk); +-} +- + #ifdef CONFIG_TRACE_IRQFLAGS + DEFINE_PER_CPU(int, hardirqs_enabled); + DEFINE_PER_CPU(int, hardirq_context); +@@ -236,7 +221,7 @@ void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) + goto out; + + pending = local_softirq_pending(); +- if (!pending || ksoftirqd_running(pending)) ++ if (!pending) + goto out; + + /* +@@ -432,9 +417,6 @@ static inline bool should_wake_ksoftirqd(void) + + static inline void invoke_softirq(void) + { +- if (ksoftirqd_running(local_softirq_pending())) +- return; +- + if (!force_irqthreads() || !__this_cpu_read(ksoftirqd)) { + #ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK + /* +@@ -468,7 +450,7 @@ asmlinkage __visible void do_softirq(void) + + pending = local_softirq_pending(); + +- if (pending && !ksoftirqd_running(pending)) ++ if (pending) + do_softirq_own_stack(); + + local_irq_restore(flags); +-- +2.43.0 + diff --git a/debian/patches-rt/0056-debugobjects-locking-Annotate-debug_object_fill_pool.patch b/debian/patches-rt/0056-debugobjects-locking-Annotate-debug_object_fill_pool.patch new file mode 100644 index 000000000..9528f771b --- /dev/null +++ b/debian/patches-rt/0056-debugobjects-locking-Annotate-debug_object_fill_pool.patch @@ -0,0 +1,177 @@ +From c082e5d28e56252dca01b53c553bba5cd152fec1 Mon Sep 17 00:00:00 2001 +From: Peter Zijlstra <peterz@infradead.org> +Date: Tue, 25 Apr 2023 17:03:13 +0200 +Subject: [PATCH 56/62] debugobjects,locking: Annotate debug_object_fill_pool() + wait type violation +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +There is an explicit wait-type violation in debug_object_fill_pool() +for PREEMPT_RT=n kernels which allows them to more easily fill the +object pool and reduce the chance of allocation failures. + +Lockdep's wait-type checks are designed to check the PREEMPT_RT +locking rules even for PREEMPT_RT=n kernels and object to this, so +create a lockdep annotation to allow this to stand. + +Specifically, create a 'lock' type that overrides the inner wait-type +while it is held -- allowing one to temporarily raise it, such that +the violation is hidden. + +Reported-by: Vlastimil Babka <vbabka@suse.cz> +Reported-by: Qi Zheng <zhengqi.arch@bytedance.com> +Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> +Tested-by: Qi Zheng <zhengqi.arch@bytedance.com> +Link: https://lkml.kernel.org/r/20230429100614.GA1489784@hirez.programming.kicks-ass.net +(cherry picked from commit 0cce06ba859a515bd06224085d3addb870608b6d) +Signed-off-by: Clark Williams <clark.williams@gmail.com> +--- + include/linux/lockdep.h | 14 ++++++++++++++ + include/linux/lockdep_types.h | 1 + + kernel/locking/lockdep.c | 28 +++++++++++++++++++++------- + lib/debugobjects.c | 15 +++++++++++++-- + 4 files changed, 49 insertions(+), 9 deletions(-) + +diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h +index 1023f349af71..a3329fb49b33 100644 +--- a/include/linux/lockdep.h ++++ b/include/linux/lockdep.h +@@ -339,6 +339,16 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); + #define lockdep_repin_lock(l,c) lock_repin_lock(&(l)->dep_map, (c)) + #define lockdep_unpin_lock(l,c) lock_unpin_lock(&(l)->dep_map, (c)) + ++/* ++ * Must use lock_map_aquire_try() with override maps to avoid ++ * lockdep thinking they participate in the block chain. ++ */ ++#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ ++ struct lockdep_map _name = { \ ++ .name = #_name "-wait-type-override", \ ++ .wait_type_inner = _wait_type, \ ++ .lock_type = LD_LOCK_WAIT_OVERRIDE, } ++ + #else /* !CONFIG_LOCKDEP */ + + static inline void lockdep_init_task(struct task_struct *task) +@@ -427,6 +437,9 @@ extern int lockdep_is_held(const void *); + #define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0) + #define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0) + ++#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ ++ struct lockdep_map __maybe_unused _name = {} ++ + #endif /* !LOCKDEP */ + + enum xhlock_context_t { +@@ -551,6 +564,7 @@ do { \ + #define rwsem_release(l, i) lock_release(l, i) + + #define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_) ++#define lock_map_acquire_try(l) lock_acquire_exclusive(l, 0, 1, NULL, _THIS_IP_) + #define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) + #define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_) + #define lock_map_release(l) lock_release(l, _THIS_IP_) +diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h +index d22430840b53..59f4fb1626ea 100644 +--- a/include/linux/lockdep_types.h ++++ b/include/linux/lockdep_types.h +@@ -33,6 +33,7 @@ enum lockdep_wait_type { + enum lockdep_lock_type { + LD_LOCK_NORMAL = 0, /* normal, catch all */ + LD_LOCK_PERCPU, /* percpu */ ++ LD_LOCK_WAIT_OVERRIDE, /* annotation */ + LD_LOCK_MAX, + }; + +diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c +index 3b38303ed27b..a046e03c7ead 100644 +--- a/kernel/locking/lockdep.c ++++ b/kernel/locking/lockdep.c +@@ -2245,6 +2245,9 @@ static inline bool usage_match(struct lock_list *entry, void *mask) + + static inline bool usage_skip(struct lock_list *entry, void *mask) + { ++ if (entry->class->lock_type == LD_LOCK_NORMAL) ++ return false; ++ + /* + * Skip local_lock() for irq inversion detection. + * +@@ -2271,14 +2274,16 @@ static inline bool usage_skip(struct lock_list *entry, void *mask) + * As a result, we will skip local_lock(), when we search for irq + * inversion bugs. + */ +- if (entry->class->lock_type == LD_LOCK_PERCPU) { +- if (DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG)) +- return false; ++ if (entry->class->lock_type == LD_LOCK_PERCPU && ++ DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG)) ++ return false; + +- return true; +- } ++ /* ++ * Skip WAIT_OVERRIDE for irq inversion detection -- it's not actually ++ * a lock and only used to override the wait_type. ++ */ + +- return false; ++ return true; + } + + /* +@@ -4745,7 +4750,8 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next) + + for (; depth < curr->lockdep_depth; depth++) { + struct held_lock *prev = curr->held_locks + depth; +- u8 prev_inner = hlock_class(prev)->wait_type_inner; ++ struct lock_class *class = hlock_class(prev); ++ u8 prev_inner = class->wait_type_inner; + + if (prev_inner) { + /* +@@ -4755,6 +4761,14 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next) + * Also due to trylocks. + */ + curr_inner = min(curr_inner, prev_inner); ++ ++ /* ++ * Allow override for annotations -- this is typically ++ * only valid/needed for code that only exists when ++ * CONFIG_PREEMPT_RT=n. ++ */ ++ if (unlikely(class->lock_type == LD_LOCK_WAIT_OVERRIDE)) ++ curr_inner = prev_inner; + } + } + +diff --git a/lib/debugobjects.c b/lib/debugobjects.c +index dacb80c22c4f..3c9e00e207dc 100644 +--- a/lib/debugobjects.c ++++ b/lib/debugobjects.c +@@ -600,10 +600,21 @@ static void debug_objects_fill_pool(void) + { + /* + * On RT enabled kernels the pool refill must happen in preemptible +- * context: ++ * context -- for !RT kernels we rely on the fact that spinlock_t and ++ * raw_spinlock_t are basically the same type and this lock-type ++ * inversion works just fine. + */ +- if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) { ++ /* ++ * Annotate away the spinlock_t inside raw_spinlock_t warning ++ * by temporarily raising the wait-type to WAIT_SLEEP, matching ++ * the preemptible() condition above. ++ */ ++ static DEFINE_WAIT_OVERRIDE_MAP(fill_pool_map, LD_WAIT_SLEEP); ++ lock_map_acquire_try(&fill_pool_map); + fill_pool(); ++ lock_map_release(&fill_pool_map); ++ } + } + + static void +-- +2.43.0 + diff --git a/debian/patches-rt/0057-sched-avoid-false-lockdep-splat-in-put_task_struct.patch b/debian/patches-rt/0057-sched-avoid-false-lockdep-splat-in-put_task_struct.patch new file mode 100644 index 000000000..9da36bc08 --- /dev/null +++ b/debian/patches-rt/0057-sched-avoid-false-lockdep-splat-in-put_task_struct.patch @@ -0,0 +1,52 @@ +From 5c27e6fdf46d68180a46fdf7944aa7e4668680c3 Mon Sep 17 00:00:00 2001 +From: Wander Lairson Costa <wander@redhat.com> +Date: Wed, 14 Jun 2023 09:23:22 -0300 +Subject: [PATCH 57/62] sched: avoid false lockdep splat in put_task_struct() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +In put_task_struct(), a spin_lock is indirectly acquired under the kernel +stock. When running the kernel in real-time (RT) configuration, the +operation is dispatched to a preemptible context call to ensure +guaranteed preemption. However, if PROVE_RAW_LOCK_NESTING is enabled +and __put_task_struct() is called while holding a raw_spinlock, lockdep +incorrectly reports an "Invalid lock context" in the stock kernel. + +This false splat occurs because lockdep is unaware of the different +route taken under RT. To address this issue, override the inner wait +type to prevent the false lockdep splat. + +Signed-off-by: Wander Lairson Costa <wander@redhat.com> +Suggested-by: Oleg Nesterov <oleg@redhat.com> +Suggested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Suggested-by: Peter Zijlstra <peterz@infradead.org> +Cc: Steven Rostedt <rostedt@goodmis.org> +Cc: Luis Goncalves <lgoncalv@redhat.com> +Link: https://lore.kernel.org/r/20230614122323.37957-3-wander@redhat.com +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +(cherry picked from commit a5e446e728e89d5f5c5e427cc919bc7813c64c28) +Signed-off-by: Clark Williams <clark.williams@gmail.com> +--- + include/linux/sched/task.h | 6 +++++- + 1 file changed, 5 insertions(+), 1 deletion(-) + +diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h +index 7291fb6399d2..de7ebd2bf3ba 100644 +--- a/include/linux/sched/task.h ++++ b/include/linux/sched/task.h +@@ -141,8 +141,12 @@ static inline void put_task_struct(struct task_struct *t) + */ + if (IS_ENABLED(CONFIG_PREEMPT_RT) && !preemptible()) + call_rcu(&t->rcu, __put_task_struct_rcu_cb); +- else ++ else { ++ static DEFINE_WAIT_OVERRIDE_MAP(put_task_map, LD_WAIT_SLEEP); ++ lock_map_acquire_try(&put_task_map); + __put_task_struct(t); ++ lock_map_release(&put_task_map); ++ } + } + + static inline void put_task_struct_many(struct task_struct *t, int nr) +-- +2.43.0 + diff --git a/debian/patches-rt/0058-mm-page_alloc-Use-write_seqlock_irqsave-instead-writ.patch b/debian/patches-rt/0058-mm-page_alloc-Use-write_seqlock_irqsave-instead-writ.patch new file mode 100644 index 000000000..68d9f5008 --- /dev/null +++ b/debian/patches-rt/0058-mm-page_alloc-Use-write_seqlock_irqsave-instead-writ.patch @@ -0,0 +1,97 @@ +From 9512a9467dec62e03f2df4f15af9a38332b8de58 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Fri, 23 Jun 2023 22:15:17 +0200 +Subject: [PATCH 58/62] mm/page_alloc: Use write_seqlock_irqsave() instead + write_seqlock() + local_irq_save(). +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +__build_all_zonelists() acquires zonelist_update_seq by first disabling +interrupts via local_irq_save() and then acquiring the seqlock with +write_seqlock(). This is troublesome and leads to problems on +PREEMPT_RT. The problem is that the inner spinlock_t becomes a sleeping +lock on PREEMPT_RT and must not be acquired with disabled interrupts. + +The API provides write_seqlock_irqsave() which does the right thing in +one step. +printk_deferred_enter() has to be invoked in non-migrate-able context to +ensure that deferred printing is enabled and disabled on the same CPU. +This is the case after zonelist_update_seq has been acquired. + +There was discussion on the first submission that the order should be: + local_irq_disable(); + printk_deferred_enter(); + write_seqlock(); + +to avoid pitfalls like having an unaccounted printk() coming from +write_seqlock_irqsave() before printk_deferred_enter() is invoked. The +only origin of such a printk() can be a lockdep splat because the +lockdep annotation happens after the sequence count is incremented. +This is exceptional and subject to change. + +It was also pointed that PREEMPT_RT can be affected by the printk +problem since its write_seqlock_irqsave() does not really disable +interrupts. This isn't the case because PREEMPT_RT's printk +implementation differs from the mainline implementation in two important +aspects: +- Printing happens in a dedicated threads and not at during the + invocation of printk(). +- In emergency cases where synchronous printing is used, a different + driver is used which does not use tty_port::lock. + +Acquire zonelist_update_seq with write_seqlock_irqsave() and then defer +printk output. + +Fixes: 1007843a91909 ("mm/page_alloc: fix potential deadlock on zonelist_update_seq seqlock") +Acked-by: Michal Hocko <mhocko@suse.com> +Reviewed-by: David Hildenbrand <david@redhat.com> +Link: https://lore.kernel.org/r/20230623201517.yw286Knb@linutronix.de +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +(cherry picked from commit 4d1139baae8bc4fff3728d1d204bdb04c13dbe10) +Signed-off-by: Clark Williams <clark.williams@gmail.com> +--- + mm/page_alloc.c | 15 ++++++--------- + 1 file changed, 6 insertions(+), 9 deletions(-) + +diff --git a/mm/page_alloc.c b/mm/page_alloc.c +index 4583f8a42d91..835b69a64f4f 100644 +--- a/mm/page_alloc.c ++++ b/mm/page_alloc.c +@@ -6588,19 +6588,17 @@ static void __build_all_zonelists(void *data) + unsigned long flags; + + /* +- * Explicitly disable this CPU's interrupts before taking seqlock +- * to prevent any IRQ handler from calling into the page allocator +- * (e.g. GFP_ATOMIC) that could hit zonelist_iter_begin and livelock. ++ * The zonelist_update_seq must be acquired with irqsave because the ++ * reader can be invoked from IRQ with GFP_ATOMIC. + */ +- local_irq_save(flags); ++ write_seqlock_irqsave(&zonelist_update_seq, flags); + /* +- * Explicitly disable this CPU's synchronous printk() before taking +- * seqlock to prevent any printk() from trying to hold port->lock, for ++ * Also disable synchronous printk() to prevent any printk() from ++ * trying to hold port->lock, for + * tty_insert_flip_string_and_push_buffer() on other CPU might be + * calling kmalloc(GFP_ATOMIC | __GFP_NOWARN) with port->lock held. + */ + printk_deferred_enter(); +- write_seqlock(&zonelist_update_seq); + + #ifdef CONFIG_NUMA + memset(node_load, 0, sizeof(node_load)); +@@ -6637,9 +6635,8 @@ static void __build_all_zonelists(void *data) + #endif + } + +- write_sequnlock(&zonelist_update_seq); + printk_deferred_exit(); +- local_irq_restore(flags); ++ write_sequnlock_irqrestore(&zonelist_update_seq, flags); + } + + static noinline void __init +-- +2.43.0 + diff --git a/debian/patches-rt/0059-bpf-Remove-in_atomic-from-bpf_link_put.patch b/debian/patches-rt/0059-bpf-Remove-in_atomic-from-bpf_link_put.patch new file mode 100644 index 000000000..8abf764af --- /dev/null +++ b/debian/patches-rt/0059-bpf-Remove-in_atomic-from-bpf_link_put.patch @@ -0,0 +1,120 @@ +From 05999b640eb04be872e5491a040701fcddc73349 Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Date: Wed, 14 Jun 2023 10:34:30 +0200 +Subject: [PATCH 59/62] bpf: Remove in_atomic() from bpf_link_put(). +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +bpf_free_inode() is invoked as a RCU callback. Usually RCU callbacks are +invoked within softirq context. By setting rcutree.use_softirq=0 boot +option the RCU callbacks will be invoked in a per-CPU kthread with +bottom halves disabled which implies a RCU read section. + +On PREEMPT_RT the context remains fully preemptible. The RCU read +section however does not allow schedule() invocation. The latter happens +in mutex_lock() performed by bpf_trampoline_unlink_prog() originated +from bpf_link_put(). + +It was pointed out that the bpf_link_put() invocation should not be +delayed if originated from close(). It was also pointed out that other +invocations from within a syscall should also avoid the workqueue. +Everyone else should use workqueue by default to remain safe in the +future (while auditing the code, every caller was preemptible except for +the RCU case). + +Let bpf_link_put() use the worker unconditionally. Add +bpf_link_put_direct() which will directly free the resources and is used +by close() and from within __sys_bpf(). + +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Signed-off-by: Andrii Nakryiko <andrii@kernel.org> +Link: https://lore.kernel.org/bpf/20230614083430.oENawF8f@linutronix.de +(cherry picked from commit ab5d47bd41b1db82c295b0e751e2b822b43a4b5a) +Signed-off-by: Clark Williams <clark.williams@gmail.com> +--- + kernel/bpf/syscall.c | 29 ++++++++++++++++------------- + 1 file changed, 16 insertions(+), 13 deletions(-) + +diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c +index c0915e2424f1..f8ba6e0a5c08 100644 +--- a/kernel/bpf/syscall.c ++++ b/kernel/bpf/syscall.c +@@ -2732,28 +2732,31 @@ static void bpf_link_put_deferred(struct work_struct *work) + bpf_link_free(link); + } + +-/* bpf_link_put can be called from atomic context, but ensures that resources +- * are freed from process context ++/* bpf_link_put might be called from atomic context. It needs to be called ++ * from sleepable context in order to acquire sleeping locks during the process. + */ + void bpf_link_put(struct bpf_link *link) + { + if (!atomic64_dec_and_test(&link->refcnt)) + return; + +- if (in_atomic()) { +- INIT_WORK(&link->work, bpf_link_put_deferred); +- schedule_work(&link->work); +- } else { +- bpf_link_free(link); +- } ++ INIT_WORK(&link->work, bpf_link_put_deferred); ++ schedule_work(&link->work); + } + EXPORT_SYMBOL(bpf_link_put); + ++static void bpf_link_put_direct(struct bpf_link *link) ++{ ++ if (!atomic64_dec_and_test(&link->refcnt)) ++ return; ++ bpf_link_free(link); ++} ++ + static int bpf_link_release(struct inode *inode, struct file *filp) + { + struct bpf_link *link = filp->private_data; + +- bpf_link_put(link); ++ bpf_link_put_direct(link); + return 0; + } + +@@ -4674,7 +4677,7 @@ static int link_update(union bpf_attr *attr) + if (ret) + bpf_prog_put(new_prog); + out_put_link: +- bpf_link_put(link); ++ bpf_link_put_direct(link); + return ret; + } + +@@ -4697,7 +4700,7 @@ static int link_detach(union bpf_attr *attr) + else + ret = -EOPNOTSUPP; + +- bpf_link_put(link); ++ bpf_link_put_direct(link); + return ret; + } + +@@ -4767,7 +4770,7 @@ static int bpf_link_get_fd_by_id(const union bpf_attr *attr) + + fd = bpf_link_new_fd(link); + if (fd < 0) +- bpf_link_put(link); ++ bpf_link_put_direct(link); + + return fd; + } +@@ -4844,7 +4847,7 @@ static int bpf_iter_create(union bpf_attr *attr) + return PTR_ERR(link); + + err = bpf_iter_new_fd(link); +- bpf_link_put(link); ++ bpf_link_put_direct(link); + + return err; + } +-- +2.43.0 + diff --git a/debian/patches-rt/0060-posix-timers-Ensure-timer-ID-search-loop-limit-is-va.patch b/debian/patches-rt/0060-posix-timers-Ensure-timer-ID-search-loop-limit-is-va.patch new file mode 100644 index 000000000..8b22f207c --- /dev/null +++ b/debian/patches-rt/0060-posix-timers-Ensure-timer-ID-search-loop-limit-is-va.patch @@ -0,0 +1,115 @@ +From a0d2c56749857956cb8ef1ccf2d982e2c1770f08 Mon Sep 17 00:00:00 2001 +From: Thomas Gleixner <tglx@linutronix.de> +Date: Thu, 1 Jun 2023 20:58:47 +0200 +Subject: [PATCH 60/62] posix-timers: Ensure timer ID search-loop limit is + valid +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +posix_timer_add() tries to allocate a posix timer ID by starting from the +cached ID which was stored by the last successful allocation. + +This is done in a loop searching the ID space for a free slot one by +one. The loop has to terminate when the search wrapped around to the +starting point. + +But that's racy vs. establishing the starting point. That is read out +lockless, which leads to the following problem: + +CPU0 CPU1 +posix_timer_add() + start = sig->posix_timer_id; + lock(hash_lock); + ... posix_timer_add() + if (++sig->posix_timer_id < 0) + start = sig->posix_timer_id; + sig->posix_timer_id = 0; + +So CPU1 can observe a negative start value, i.e. -1, and the loop break +never happens because the condition can never be true: + + if (sig->posix_timer_id == start) + break; + +While this is unlikely to ever turn into an endless loop as the ID space is +huge (INT_MAX), the racy read of the start value caught the attention of +KCSAN and Dmitry unearthed that incorrectness. + +Rewrite it so that all id operations are under the hash lock. + +Reported-by: syzbot+5c54bd3eb218bb595aa9@syzkaller.appspotmail.com +Reported-by: Dmitry Vyukov <dvyukov@google.com> +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Reviewed-by: Frederic Weisbecker <frederic@kernel.org> +Link: https://lore.kernel.org/r/87bkhzdn6g.ffs@tglx + +(cherry picked from commit 8ce8849dd1e78dadcee0ec9acbd259d239b7069f) +Signed-off-by: Clark Williams <clark.williams@gmail.com> +--- + include/linux/sched/signal.h | 2 +- + kernel/time/posix-timers.c | 31 ++++++++++++++++++------------- + 2 files changed, 19 insertions(+), 14 deletions(-) + +diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h +index 20099268fa25..669e8cff40c7 100644 +--- a/include/linux/sched/signal.h ++++ b/include/linux/sched/signal.h +@@ -135,7 +135,7 @@ struct signal_struct { + #ifdef CONFIG_POSIX_TIMERS + + /* POSIX.1b Interval Timers */ +- int posix_timer_id; ++ unsigned int next_posix_timer_id; + struct list_head posix_timers; + + /* ITIMER_REAL timer for the process */ +diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c +index ed3c4a954398..2d6cf93ca370 100644 +--- a/kernel/time/posix-timers.c ++++ b/kernel/time/posix-timers.c +@@ -140,25 +140,30 @@ static struct k_itimer *posix_timer_by_id(timer_t id) + static int posix_timer_add(struct k_itimer *timer) + { + struct signal_struct *sig = current->signal; +- int first_free_id = sig->posix_timer_id; + struct hlist_head *head; +- int ret = -ENOENT; ++ unsigned int cnt, id; + +- do { ++ /* ++ * FIXME: Replace this by a per signal struct xarray once there is ++ * a plan to handle the resulting CRIU regression gracefully. ++ */ ++ for (cnt = 0; cnt <= INT_MAX; cnt++) { + spin_lock(&hash_lock); +- head = &posix_timers_hashtable[hash(sig, sig->posix_timer_id)]; +- if (!__posix_timers_find(head, sig, sig->posix_timer_id)) { ++ id = sig->next_posix_timer_id; ++ ++ /* Write the next ID back. Clamp it to the positive space */ ++ sig->next_posix_timer_id = (id + 1) & INT_MAX; ++ ++ head = &posix_timers_hashtable[hash(sig, id)]; ++ if (!__posix_timers_find(head, sig, id)) { + hlist_add_head_rcu(&timer->t_hash, head); +- ret = sig->posix_timer_id; ++ spin_unlock(&hash_lock); ++ return id; + } +- if (++sig->posix_timer_id < 0) +- sig->posix_timer_id = 0; +- if ((sig->posix_timer_id == first_free_id) && (ret == -ENOENT)) +- /* Loop over all possible ids completed */ +- ret = -EAGAIN; + spin_unlock(&hash_lock); +- } while (ret == -ENOENT); +- return ret; ++ } ++ /* POSIX return code when no timer ID could be allocated */ ++ return -EAGAIN; + } + + static inline void unlock_timer(struct k_itimer *timr, unsigned long flags) +-- +2.43.0 + diff --git a/debian/patches-rt/0061-drm-i915-Do-not-disable-preemption-for-resets.patch b/debian/patches-rt/0061-drm-i915-Do-not-disable-preemption-for-resets.patch new file mode 100644 index 000000000..db8400741 --- /dev/null +++ b/debian/patches-rt/0061-drm-i915-Do-not-disable-preemption-for-resets.patch @@ -0,0 +1,110 @@ +From 1d651fe6c67cb3b355cc228f75289657496520ff Mon Sep 17 00:00:00 2001 +From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> +Date: Fri, 18 Aug 2023 22:45:25 -0400 +Subject: [PATCH 61/62] drm/i915: Do not disable preemption for resets +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +[commit 40cd2835ced288789a685aa4aa7bc04b492dcd45 in linux-rt-devel] + +Commit ade8a0f59844 ("drm/i915: Make all GPU resets atomic") added a +preempt disable section over the hardware reset callback to prepare the +driver for being able to reset from atomic contexts. + +In retrospect I can see that the work item at a time was about removing +the struct mutex from the reset path. Code base also briefly entertained +the idea of doing the reset under stop_machine in order to serialize +userspace mmap and temporary glitch in the fence registers (see +eb8d0f5af4ec ("drm/i915: Remove GPU reset dependence on struct_mutex"), +but that never materialized and was soon removed in 2caffbf11762 +("drm/i915: Revoke mmaps and prevent access to fence registers across +reset") and replaced with a SRCU based solution. + +As such, as far as I can see, today we still have a requirement that +resets must not sleep (invoked from submission tasklets), but no need to +support invoking them from a truly atomic context. + +Given that the preemption section is problematic on RT kernels, since the +uncore lock becomes a sleeping lock and so is invalid in such section, +lets try and remove it. Potential downside is that our short waits on GPU +to complete the reset may get extended if CPU scheduling interferes, but +in practice that probably isn't a deal breaker. + +In terms of mechanics, since the preemption disabled block is being +removed we just need to replace a few of the wait_for_atomic macros into +busy looping versions which will work (and not complain) when called from +non-atomic sections. + +Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> +Cc: Chris Wilson <chris.p.wilson@intel.com> +Cc: Paul Gortmaker <paul.gortmaker@windriver.com> +Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Link: https://lore.kernel.org/r/20230705093025.3689748-1-tvrtko.ursulin@linux.intel.com +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +[PG: backport from v6.4-rt ; minor context fixup caused by b7d70b8b06ed] +Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> +Signed-off-by: Clark Williams <williams@redhat.com> +--- + drivers/gpu/drm/i915/gt/intel_reset.c | 12 +++++------- + 1 file changed, 5 insertions(+), 7 deletions(-) + +diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c +index 10b930eaa8cb..6108a449cd19 100644 +--- a/drivers/gpu/drm/i915/gt/intel_reset.c ++++ b/drivers/gpu/drm/i915/gt/intel_reset.c +@@ -174,13 +174,13 @@ static int i915_do_reset(struct intel_gt *gt, + /* Assert reset for at least 20 usec, and wait for acknowledgement. */ + pci_write_config_byte(pdev, I915_GDRST, GRDOM_RESET_ENABLE); + udelay(50); +- err = wait_for_atomic(i915_in_reset(pdev), 50); ++ err = _wait_for_atomic(i915_in_reset(pdev), 50, 0); + + /* Clear the reset request. */ + pci_write_config_byte(pdev, I915_GDRST, 0); + udelay(50); + if (!err) +- err = wait_for_atomic(!i915_in_reset(pdev), 50); ++ err = _wait_for_atomic(!i915_in_reset(pdev), 50, 0); + + return err; + } +@@ -200,7 +200,7 @@ static int g33_do_reset(struct intel_gt *gt, + struct pci_dev *pdev = to_pci_dev(gt->i915->drm.dev); + + pci_write_config_byte(pdev, I915_GDRST, GRDOM_RESET_ENABLE); +- return wait_for_atomic(g4x_reset_complete(pdev), 50); ++ return _wait_for_atomic(g4x_reset_complete(pdev), 50, 0); + } + + static int g4x_do_reset(struct intel_gt *gt, +@@ -217,7 +217,7 @@ static int g4x_do_reset(struct intel_gt *gt, + + pci_write_config_byte(pdev, I915_GDRST, + GRDOM_MEDIA | GRDOM_RESET_ENABLE); +- ret = wait_for_atomic(g4x_reset_complete(pdev), 50); ++ ret = _wait_for_atomic(g4x_reset_complete(pdev), 50, 0); + if (ret) { + GT_TRACE(gt, "Wait for media reset failed\n"); + goto out; +@@ -225,7 +225,7 @@ static int g4x_do_reset(struct intel_gt *gt, + + pci_write_config_byte(pdev, I915_GDRST, + GRDOM_RENDER | GRDOM_RESET_ENABLE); +- ret = wait_for_atomic(g4x_reset_complete(pdev), 50); ++ ret = _wait_for_atomic(g4x_reset_complete(pdev), 50, 0); + if (ret) { + GT_TRACE(gt, "Wait for render reset failed\n"); + goto out; +@@ -718,9 +718,7 @@ int __intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask) + intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL); + for (retry = 0; ret == -ETIMEDOUT && retry < retries; retry++) { + GT_TRACE(gt, "engine_mask=%x\n", engine_mask); +- preempt_disable(); + ret = reset(gt, engine_mask, retry); +- preempt_enable(); + } + intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL); + +-- +2.43.0 + diff --git a/debian/patches-rt/0062-Linux-6.1.69-rt21-REBASE.patch b/debian/patches-rt/0062-Linux-6.1.69-rt21-REBASE.patch new file mode 100644 index 000000000..d5e736785 --- /dev/null +++ b/debian/patches-rt/0062-Linux-6.1.69-rt21-REBASE.patch @@ -0,0 +1,21 @@ +From 8aa6a280fc011cccf7cfcc0f5942e3ec6bdd73b4 Mon Sep 17 00:00:00 2001 +From: Clark Williams <clark.williams@gmail.com> +Date: Thu, 28 Dec 2023 23:45:11 -0600 +Subject: [PATCH 62/62] Linux 6.1.69-rt21 REBASE +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.69-rt21.tar.xz + +Signed-off-by: Clark Williams <clark.williams@gmail.com> +--- + localversion-rt | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/localversion-rt b/localversion-rt +index 9f7d0bdbffb1..6c6cde1c29e3 100644 +--- a/localversion-rt ++++ b/localversion-rt +@@ -1 +1 @@ +--rt13 ++-rt21 +-- +2.43.0 + diff --git a/debian/patches-rt/series b/debian/patches-rt/series new file mode 100644 index 000000000..a07ceae89 --- /dev/null +++ b/debian/patches-rt/series @@ -0,0 +1,62 @@ +0001-vduse-Remove-include-of-rwlock.h.patch +0002-signal-Don-t-disable-preemption-in-ptrace_stop-on-PR.patch +0003-sched-Consider-task_struct-saved_state-in-wait_task_.patch +0004-spi-Remove-the-obsolte-u64_stats_fetch_-_irq-users.patch +0005-net-Remove-the-obsolte-u64_stats_fetch_-_irq-users-d.patch +0006-net-Remove-the-obsolte-u64_stats_fetch_-_irq-users-n.patch +0007-bpf-Remove-the-obsolte-u64_stats_fetch_-_irq-users.patch +0008-u64_stat-Remove-the-obsolete-fetch_irq-variants.patch +0009-net-Avoid-the-IPI-to-free-the.patch +0010-x86-Allow-to-enable-RT.patch +0011-x86-Enable-RT-also-on-32bit.patch +0012-softirq-Use-a-dedicated-thread-for-timer-wakeups.patch +0013-rcutorture-Also-force-sched-priority-to-timersd-on-b.patch +0014-tick-Fix-timer-storm-since-introduction-of-timersd.patch +0015-softirq-Wake-ktimers-thread-also-in-softirq.patch +0016-tpm_tis-fix-stall-after-iowrite-s.patch +0017-zram-Replace-bit-spinlocks-with-spinlock_t-for-PREEM.patch +0018-locking-lockdep-Remove-lockdep_init_map_crosslock.patch +0019-printk-Bring-back-the-RT-bits.patch +0020-printk-add-infrastucture-for-atomic-consoles.patch +0021-serial-8250-implement-write_atomic.patch +0022-printk-avoid-preempt_disable-for-PREEMPT_RT.patch +0023-drm-i915-Use-preempt_disable-enable_rt-where-recomme.patch +0024-drm-i915-Don-t-disable-interrupts-on-PREEMPT_RT-duri.patch +0025-drm-i915-Don-t-check-for-atomic-context-on-PREEMPT_R.patch +0026-drm-i915-Disable-tracing-points-on-PREEMPT_RT.patch +0027-drm-i915-skip-DRM_I915_LOW_LEVEL_TRACEPOINTS-with-NO.patch +0028-drm-i915-gt-Queue-and-wait-for-the-irq_work-item.patch +0029-drm-i915-gt-Use-spin_lock_irq-instead-of-local_irq_d.patch +0030-drm-i915-Drop-the-irqs_disabled-check.patch +0031-Revert-drm-i915-Depend-on-PREEMPT_RT.patch +0032-sched-Add-support-for-lazy-preemption.patch +0033-x86-entry-Use-should_resched-in-idtentry_exit_cond_r.patch +0034-x86-Support-for-lazy-preemption.patch +0035-entry-Fix-the-preempt-lazy-fallout.patch +0036-arm-Add-support-for-lazy-preemption.patch +0037-powerpc-Add-support-for-lazy-preemption.patch +0038-arch-arm64-Add-lazy-preempt-support.patch +0039-arm-Disable-jump-label-on-PREEMPT_RT.patch +0040-ARM-enable-irq-in-translation-section-permission-fau.patch +0041-tty-serial-omap-Make-the-locking-RT-aware.patch +0042-tty-serial-pl011-Make-the-locking-work-on-RT.patch +0043-ARM-Allow-to-enable-RT.patch +0044-ARM64-Allow-to-enable-RT.patch +0045-powerpc-traps-Use-PREEMPT_RT.patch +0046-powerpc-pseries-iommu-Use-a-locallock-instead-local_.patch +0047-powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch +0048-powerpc-stackprotector-work-around-stack-guard-init-.patch +0049-POWERPC-Allow-to-enable-RT.patch +0050-sysfs-Add-sys-kernel-realtime-entry.patch +0051-Add-localversion-for-RT-release.patch +0052-Linux-6.1.46-rt13-REBASE.patch +0053-io-mapping-don-t-disable-preempt-on-RT-in-io_mapping.patch +0054-locking-rwbase-Mitigate-indefinite-writer-starvation.patch +0055-revert-softirq-Let-ksoftirqd-do-its-job.patch +0056-debugobjects-locking-Annotate-debug_object_fill_pool.patch +0057-sched-avoid-false-lockdep-splat-in-put_task_struct.patch +0058-mm-page_alloc-Use-write_seqlock_irqsave-instead-writ.patch +0059-bpf-Remove-in_atomic-from-bpf_link_put.patch +0060-posix-timers-Ensure-timer-ID-search-loop-limit-is-va.patch +0061-drm-i915-Do-not-disable-preemption-for-resets.patch +0062-Linux-6.1.69-rt21-REBASE.patch diff --git a/debian/patches/bugfix/all/cpupower-bump-soname-version.patch b/debian/patches/bugfix/all/cpupower-bump-soname-version.patch new file mode 100644 index 000000000..7e5f52eaa --- /dev/null +++ b/debian/patches/bugfix/all/cpupower-bump-soname-version.patch @@ -0,0 +1,27 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Thu, 9 Jun 2016 23:35:08 +0100 +Subject: cpupower: Bump soname version +Forwarded: http://mid.gmane.org/20160610005619.GQ7555@decadent.org.uk + +Several functions in the libcpupower API are renamed or removed in +Linux 4.7. This is an backward-incompatible ABI change, so the +library soname should change from libcpupower.so.0 to +libcpupower.so.1. + +Fixes: ac5a181d065d ("cpupower: Add cpuidle parts into library") +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- + tools/power/cpupower/Makefile | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/tools/power/cpupower/Makefile ++++ b/tools/power/cpupower/Makefile +@@ -53,7 +53,7 @@ DESTDIR ?= + + VERSION:= $(shell ./utils/version-gen.sh) + LIB_MAJ= 0.0.1 +-LIB_MIN= 0 ++LIB_MIN= 1 + + PACKAGE = cpupower + PACKAGE_BUGREPORT = linux-pm@vger.kernel.org diff --git a/debian/patches/bugfix/all/cpupower-fix-checks-for-cpu-existence.patch b/debian/patches/bugfix/all/cpupower-fix-checks-for-cpu-existence.patch new file mode 100644 index 000000000..5cce9b76a --- /dev/null +++ b/debian/patches/bugfix/all/cpupower-fix-checks-for-cpu-existence.patch @@ -0,0 +1,49 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Thu, 03 Nov 2016 15:25:26 -0600 +Subject: cpupower: Fix checks for CPU existence +Forwarded: https://marc.info/?l=linux-pm&m=149248268214265 + +Calls to cpufreq_cpu_exists(cpu) were converted to +cpupower_is_cpu_online(cpu) when libcpupower was introduced and the +former function was deleted. However, cpupower_is_cpu_online() does +not distinguish physically absent and offline CPUs, and does not set +errno. + +cpufreq-set has already been fixed (commit c25badc9ceb6). + +In cpufreq-bench, which prints an error message for offline CPUs, +properly distinguish and report the zero and negative cases. + +Fixes: ac5a181d065d ("cpupower: Add cpuidle parts into library") +Fixes: 53d1cd6b125f ("cpupowerutils: bench - Fix cpu online check") +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +[carnil: Update/Refresh patch for 4.14.17: The issue with the +incorrect check has been fixed with upstream commit 53d1cd6b125f. +Keep in the patch the distinction and report for the zero and +negative cases.] +--- +--- a/tools/power/cpupower/bench/system.c ++++ b/tools/power/cpupower/bench/system.c +@@ -58,12 +58,19 @@ long long int get_time() + + int set_cpufreq_governor(char *governor, unsigned int cpu) + { ++ int rc; + + dprintf("set %s as cpufreq governor\n", governor); + +- if (cpupower_is_cpu_online(cpu) != 1) { +- perror("cpufreq_cpu_exists"); +- fprintf(stderr, "error: cpu %u does not exist\n", cpu); ++ rc = cpupower_is_cpu_online(cpu); ++ if (rc != 1) { ++ if (rc < 0) ++ fprintf(stderr, "cpupower_is_cpu_online: %s\n", ++ strerror(-rc)); ++ else ++ fprintf(stderr, ++ "error: cpu %u is offline or does not exist\n", ++ cpu); + return -1; + } + diff --git a/debian/patches/bugfix/all/disable-some-marvell-phys.patch b/debian/patches/bugfix/all/disable-some-marvell-phys.patch new file mode 100644 index 000000000..9c4987116 --- /dev/null +++ b/debian/patches/bugfix/all/disable-some-marvell-phys.patch @@ -0,0 +1,91 @@ +From: Ian Campbell <ijc@hellion.org.uk> +Subject: phy/marvell: disable 4-port phys +Date: Wed, 20 Nov 2013 08:30:14 +0000 +Bug-Debian: https://bugs.debian.org/723177 +Forwarded: http://thread.gmane.org/gmane.linux.debian.devel.bugs.general/1107774/ + +The Marvell PHY was originally disabled because it can cause networking +failures on some systems. According to Lennert Buytenhek this is because some +of the variants added did not share the same register layout. Since the known +cases are all 4-ports disable those variants (indicated by a 4 in the +penultimate position of the model name) until they can be audited for +correctness. + +[bwh: Also #if-out the init functions for these PHYs to avoid + compiler warnings] + +--- a/drivers/net/phy/marvell.c ++++ b/drivers/net/phy/marvell.c +@@ -1262,6 +1262,7 @@ + return genphy_soft_reset(phydev); + } + ++#if 0 + static int m88e1149_config_init(struct phy_device *phydev) + { + int err; +@@ -1287,7 +1288,9 @@ + + return genphy_soft_reset(phydev); + } ++#endif + ++#if 0 + static int m88e1145_config_init_rgmii(struct phy_device *phydev) + { + int err; +@@ -1365,6 +1368,7 @@ + + return 0; + } ++#endif + + static int m88e1540_get_fld(struct phy_device *phydev, u8 *msecs) + { +@@ -2853,6 +2857,7 @@ + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, + }, ++#if 0 + { + .phy_id = MARVELL_PHY_ID_88E1145, + .phy_id_mask = MARVELL_PHY_ID_MASK, +@@ -2873,6 +2878,8 @@ + .get_tunable = m88e1111_get_tunable, + .set_tunable = m88e1111_set_tunable, + }, ++#endif ++#if 0 + { + .phy_id = MARVELL_PHY_ID_88E1149R, + .phy_id_mask = MARVELL_PHY_ID_MASK, +@@ -2891,6 +2898,8 @@ + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, + }, ++#endif ++#if 0 + { + .phy_id = MARVELL_PHY_ID_88E1240, + .phy_id_mask = MARVELL_PHY_ID_MASK, +@@ -2911,6 +2920,7 @@ + .get_tunable = m88e1011_get_tunable, + .set_tunable = m88e1011_set_tunable, + }, ++#endif + { + .phy_id = MARVELL_PHY_ID_88E1116R, + .phy_id_mask = MARVELL_PHY_ID_MASK, +@@ -3163,9 +3173,9 @@ + { MARVELL_PHY_ID_88E1111_FINISAR, MARVELL_PHY_ID_MASK }, + { MARVELL_PHY_ID_88E1118, MARVELL_PHY_ID_MASK }, + { MARVELL_PHY_ID_88E1121R, MARVELL_PHY_ID_MASK }, +- { MARVELL_PHY_ID_88E1145, MARVELL_PHY_ID_MASK }, +- { MARVELL_PHY_ID_88E1149R, MARVELL_PHY_ID_MASK }, +- { MARVELL_PHY_ID_88E1240, MARVELL_PHY_ID_MASK }, ++/* { MARVELL_PHY_ID_88E1145, MARVELL_PHY_ID_MASK }, */ ++/* { MARVELL_PHY_ID_88E1149R, MARVELL_PHY_ID_MASK }, */ ++/* { MARVELL_PHY_ID_88E1240, MARVELL_PHY_ID_MASK }, */ + { MARVELL_PHY_ID_88E1318S, MARVELL_PHY_ID_MASK }, + { MARVELL_PHY_ID_88E1116R, MARVELL_PHY_ID_MASK }, + { MARVELL_PHY_ID_88E1510, MARVELL_PHY_ID_MASK }, diff --git a/debian/patches/bugfix/all/firmware-remove-redundant-log-messages-from-drivers.patch b/debian/patches/bugfix/all/firmware-remove-redundant-log-messages-from-drivers.patch new file mode 100644 index 000000000..fc4cb5b33 --- /dev/null +++ b/debian/patches/bugfix/all/firmware-remove-redundant-log-messages-from-drivers.patch @@ -0,0 +1,2716 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Subject: firmware: Remove redundant log messages from drivers +Date: Sun, 09 Dec 2012 16:40:31 +0000 +Forwarded: no + +Now that firmware_class logs every success and failure consistently, +many other log messages can be removed from drivers. + +This will probably need to be split up into multiple patches prior to +upstream submission. + +Index: linux/arch/x86/kernel/cpu/microcode/amd.c +=================================================================== +--- linux.orig/arch/x86/kernel/cpu/microcode/amd.c ++++ linux/arch/x86/kernel/cpu/microcode/amd.c +@@ -907,10 +907,8 @@ static enum ucode_state request_microcod + if (c->x86 >= 0x15) + snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86); + +- if (request_firmware_direct(&fw, (const char *)fw_name, device)) { +- pr_debug("failed to load file %s\n", fw_name); ++ if (request_firmware_direct(&fw, (const char *)fw_name, device)) + goto out; +- } + + ret = UCODE_ERROR; + if (!verify_container(fw->data, fw->size, false)) +Index: linux/drivers/atm/fore200e.c +=================================================================== +--- linux.orig/drivers/atm/fore200e.c ++++ linux/drivers/atm/fore200e.c +@@ -2398,10 +2398,9 @@ static int fore200e_load_and_start_fw(st + int err; + + sprintf(buf, "%s%s", fore200e->bus->proc_name, FW_EXT); +- if ((err = request_firmware(&firmware, buf, fore200e->dev)) < 0) { +- printk(FORE200E "problem loading firmware image %s\n", fore200e->bus->model_name); ++ err = request_firmware(&firmware, buf, fore200e->dev); ++ if (err) + return err; +- } + + fw_data = (const __le32 *)firmware->data; + fw_size = firmware->size / sizeof(u32); +Index: linux/drivers/bluetooth/ath3k.c +=================================================================== +--- linux.orig/drivers/bluetooth/ath3k.c ++++ linux/drivers/bluetooth/ath3k.c +@@ -381,10 +381,8 @@ static int ath3k_load_patch(struct usb_d + le32_to_cpu(fw_version.rom_version)); + + ret = request_firmware(&firmware, filename, &udev->dev); +- if (ret < 0) { +- BT_ERR("Patch file not found %s", filename); ++ if (ret) + return ret; +- } + + pt_rom_version = get_unaligned_le32(firmware->data + + firmware->size - 8); +@@ -444,10 +442,8 @@ static int ath3k_load_syscfg(struct usb_ + le32_to_cpu(fw_version.rom_version), clk_value, ".dfu"); + + ret = request_firmware(&firmware, filename, &udev->dev); +- if (ret < 0) { +- BT_ERR("Configuration file not found %s", filename); ++ if (ret) + return ret; +- } + + ret = ath3k_load_fwfile(udev, firmware); + release_firmware(firmware); +Index: linux/drivers/bluetooth/bcm203x.c +=================================================================== +--- linux.orig/drivers/bluetooth/bcm203x.c ++++ linux/drivers/bluetooth/bcm203x.c +@@ -173,7 +173,6 @@ static int bcm203x_probe(struct usb_inte + return -ENOMEM; + + if (request_firmware(&firmware, "BCM2033-MD.hex", &udev->dev) < 0) { +- BT_ERR("Mini driver request failed"); + usb_free_urb(data->urb); + return -EIO; + } +@@ -198,7 +197,6 @@ static int bcm203x_probe(struct usb_inte + release_firmware(firmware); + + if (request_firmware(&firmware, "BCM2033-FW.bin", &udev->dev) < 0) { +- BT_ERR("Firmware request failed"); + usb_free_urb(data->urb); + kfree(data->buffer); + return -EIO; +Index: linux/drivers/bluetooth/bfusb.c +=================================================================== +--- linux.orig/drivers/bluetooth/bfusb.c ++++ linux/drivers/bluetooth/bfusb.c +@@ -639,10 +639,8 @@ static int bfusb_probe(struct usb_interf + skb_queue_head_init(&data->pending_q); + skb_queue_head_init(&data->completed_q); + +- if (request_firmware(&firmware, "bfubase.frm", &udev->dev) < 0) { +- BT_ERR("Firmware request failed"); ++ if (request_firmware(&firmware, "bfubase.frm", &udev->dev)) + goto done; +- } + + BT_DBG("firmware data %p size %zu", firmware->data, firmware->size); + +Index: linux/drivers/bluetooth/bt3c_cs.c +=================================================================== +--- linux.orig/drivers/bluetooth/bt3c_cs.c ++++ linux/drivers/bluetooth/bt3c_cs.c +@@ -569,10 +569,8 @@ static int bt3c_open(struct bt3c_info *i + + /* Load firmware */ + err = request_firmware(&firmware, "BT3CPCC.bin", &info->p_dev->dev); +- if (err < 0) { +- BT_ERR("Firmware request failed"); ++ if (err) + goto error; +- } + + err = bt3c_load_firmware(info, firmware->data, firmware->size); + +Index: linux/drivers/bluetooth/btmrvl_sdio.c +=================================================================== +--- linux.orig/drivers/bluetooth/btmrvl_sdio.c ++++ linux/drivers/bluetooth/btmrvl_sdio.c +@@ -470,8 +470,6 @@ static int btmrvl_sdio_download_helper(s + ret = request_firmware(&fw_helper, card->helper, + &card->func->dev); + if ((ret < 0) || !fw_helper) { +- BT_ERR("request_firmware(helper) failed, error code = %d", +- ret); + ret = -ENOENT; + goto done; + } +@@ -570,8 +568,6 @@ static int btmrvl_sdio_download_fw_w_hel + ret = request_firmware(&fw_firmware, card->firmware, + &card->func->dev); + if ((ret < 0) || !fw_firmware) { +- BT_ERR("request_firmware(firmware) failed, error code = %d", +- ret); + ret = -ENOENT; + goto done; + } +Index: linux/drivers/char/dsp56k.c +=================================================================== +--- linux.orig/drivers/char/dsp56k.c ++++ linux/drivers/char/dsp56k.c +@@ -140,11 +140,8 @@ static int dsp56k_upload(u_char __user * + } + err = request_firmware(&fw, fw_name, &pdev->dev); + platform_device_unregister(pdev); +- if (err) { +- printk(KERN_ERR "Failed to load image \"%s\" err %d\n", +- fw_name, err); ++ if (err) + return err; +- } + if (fw->size % 3) { + printk(KERN_ERR "Bogus length %d in image \"%s\"\n", + fw->size, fw_name); +Index: linux/drivers/dma/imx-sdma.c +=================================================================== +--- linux.orig/drivers/dma/imx-sdma.c ++++ linux/drivers/dma/imx-sdma.c +@@ -1910,11 +1910,8 @@ static void sdma_load_firmware(const str + const struct sdma_script_start_addrs *addr; + unsigned short *ram_code; + +- if (!fw) { +- dev_info(sdma->dev, "external firmware not found, using ROM firmware\n"); +- /* In this case we just use the ROM firmware. */ ++ if (!fw) + return; +- } + + if (fw->size < sizeof(*header)) + goto err_firmware; +Index: linux/drivers/gpu/drm/mga/mga_warp.c +=================================================================== +--- linux.orig/drivers/gpu/drm/mga/mga_warp.c ++++ linux/drivers/gpu/drm/mga/mga_warp.c +@@ -77,11 +77,8 @@ int mga_warp_install_microcode(drm_mga_p + } + rc = request_ihex_firmware(&fw, firmware_name, &pdev->dev); + platform_device_unregister(pdev); +- if (rc) { +- DRM_ERROR("mga: Failed to load microcode \"%s\"\n", +- firmware_name); ++ if (rc) + return rc; +- } + + size = 0; + where = 0; +Index: linux/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c +=================================================================== +--- linux.orig/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c ++++ linux/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c +@@ -2445,10 +2445,8 @@ gf100_gr_load_fw(struct gf100_gr *gr, co + if (ret) { + snprintf(f, sizeof(f), "nouveau/%s", name); + ret = request_firmware(&fw, f, device->dev); +- if (ret) { +- nvkm_error(subdev, "failed to load %s\n", name); ++ if (ret) + return ret; +- } + } + + blob->size = fw->size; +Index: linux/drivers/gpu/drm/r128/r128_cce.c +=================================================================== +--- linux.orig/drivers/gpu/drm/r128/r128_cce.c ++++ linux/drivers/gpu/drm/r128/r128_cce.c +@@ -161,11 +161,8 @@ static int r128_cce_load_microcode(drm_r + } + rc = request_firmware(&fw, FIRMWARE_NAME, &pdev->dev); + platform_device_unregister(pdev); +- if (rc) { +- pr_err("r128_cce: Failed to load firmware \"%s\"\n", +- FIRMWARE_NAME); ++ if (rc) + return rc; +- } + + if (fw->size != 256 * 8) { + pr_err("r128_cce: Bogus length %zu in firmware \"%s\"\n", +Index: linux/drivers/gpu/drm/radeon/ni.c +=================================================================== +--- linux.orig/drivers/gpu/drm/radeon/ni.c ++++ linux/drivers/gpu/drm/radeon/ni.c +@@ -820,9 +820,6 @@ int ni_init_microcode(struct radeon_devi + + out: + if (err) { +- if (err != -EINVAL) +- pr_err("ni_cp: Failed to load firmware \"%s\"\n", +- fw_name); + release_firmware(rdev->pfp_fw); + rdev->pfp_fw = NULL; + release_firmware(rdev->me_fw); +Index: linux/drivers/gpu/drm/radeon/r100.c +=================================================================== +--- linux.orig/drivers/gpu/drm/radeon/r100.c ++++ linux/drivers/gpu/drm/radeon/r100.c +@@ -1057,9 +1057,7 @@ static int r100_cp_init_microcode(struct + } + + err = request_firmware(&rdev->me_fw, fw_name, rdev->dev); +- if (err) { +- pr_err("radeon_cp: Failed to load firmware \"%s\"\n", fw_name); +- } else if (rdev->me_fw->size % 8) { ++ if (err == 0 && rdev->me_fw->size % 8) { + pr_err("radeon_cp: Bogus length %zu in firmware \"%s\"\n", + rdev->me_fw->size, fw_name); + err = -EINVAL; +Index: linux/drivers/gpu/drm/radeon/r600.c +=================================================================== +--- linux.orig/drivers/gpu/drm/radeon/r600.c ++++ linux/drivers/gpu/drm/radeon/r600.c +@@ -2600,9 +2600,6 @@ int r600_init_microcode(struct radeon_de + + out: + if (err) { +- if (err != -EINVAL) +- pr_err("r600_cp: Failed to load firmware \"%s\"\n", +- fw_name); + release_firmware(rdev->pfp_fw); + rdev->pfp_fw = NULL; + release_firmware(rdev->me_fw); +Index: linux/drivers/infiniband/hw/qib/qib_sd7220.c +=================================================================== +--- linux.orig/drivers/infiniband/hw/qib/qib_sd7220.c ++++ linux/drivers/infiniband/hw/qib/qib_sd7220.c +@@ -406,10 +406,8 @@ int qib_sd7220_init(struct qib_devdata * + } + + ret = request_firmware(&fw, SD7220_FW_NAME, &dd->pcidev->dev); +- if (ret) { +- qib_dev_err(dd, "Failed to load IB SERDES image\n"); ++ if (ret) + goto done; +- } + + /* Substitute our deduced value for was_reset */ + ret = qib_ibsd_ucode_loaded(dd->pport, fw); +Index: linux/drivers/input/touchscreen/atmel_mxt_ts.c +=================================================================== +--- linux.orig/drivers/input/touchscreen/atmel_mxt_ts.c ++++ linux/drivers/input/touchscreen/atmel_mxt_ts.c +@@ -2870,10 +2870,8 @@ static int mxt_load_fw(struct device *de + int ret; + + ret = request_firmware(&fw, fn, dev); +- if (ret) { +- dev_err(dev, "Unable to open firmware %s\n", fn); ++ if (ret) + return ret; +- } + + /* Check for incorrect enc file */ + ret = mxt_check_firmware_format(dev, fw); +Index: linux/drivers/isdn/hardware/mISDN/speedfax.c +=================================================================== +--- linux.orig/drivers/isdn/hardware/mISDN/speedfax.c ++++ linux/drivers/isdn/hardware/mISDN/speedfax.c +@@ -379,11 +379,8 @@ setup_instance(struct sfax_hw *card) + card->isar.owner = THIS_MODULE; + + err = request_firmware(&firmware, "isdn/ISAR.BIN", &card->pdev->dev); +- if (err < 0) { +- pr_info("%s: firmware request failed %d\n", +- card->name, err); ++ if (err) + goto error_fw; +- } + if (debug & DEBUG_HW) + pr_notice("%s: got firmware %zu bytes\n", + card->name, firmware->size); +Index: linux/drivers/media/common/siano/smscoreapi.c +=================================================================== +--- linux.orig/drivers/media/common/siano/smscoreapi.c ++++ linux/drivers/media/common/siano/smscoreapi.c +@@ -1152,10 +1152,8 @@ static int smscore_load_firmware_from_fi + return -EINVAL; + + rc = request_firmware(&fw, fw_filename, coredev->device); +- if (rc < 0) { +- pr_err("failed to open firmware file '%s'\n", fw_filename); ++ if (rc < 0) + return rc; +- } + pr_debug("read fw %s, buffer size=0x%zx\n", fw_filename, fw->size); + fw_buf = kmalloc(ALIGN(fw->size + sizeof(struct sms_firmware), + SMS_ALLOC_ALIGNMENT), GFP_KERNEL | coredev->gfp_buf_flags); +Index: linux/drivers/media/dvb-frontends/af9013.c +=================================================================== +--- linux.orig/drivers/media/dvb-frontends/af9013.c ++++ linux/drivers/media/dvb-frontends/af9013.c +@@ -1049,14 +1049,8 @@ static int af9013_download_firmware(stru + + /* Request the firmware, will block and timeout */ + ret = request_firmware(&firmware, name, &client->dev); +- if (ret) { +- dev_info(&client->dev, "firmware file '%s' not found %d\n", +- name, ret); ++ if (ret) + goto err; +- } +- +- dev_info(&client->dev, "downloading firmware from file '%s'\n", +- name); + + /* Write firmware checksum & size */ + for (i = 0; i < firmware->size; i++) +Index: linux/drivers/media/dvb-frontends/bcm3510.c +=================================================================== +--- linux.orig/drivers/media/dvb-frontends/bcm3510.c ++++ linux/drivers/media/dvb-frontends/bcm3510.c +@@ -636,10 +636,9 @@ static int bcm3510_download_firmware(str + int ret,i; + + deb_info("requesting firmware\n"); +- if ((ret = st->config->request_firmware(fe, &fw, BCM3510_DEFAULT_FIRMWARE)) < 0) { +- err("could not load firmware (%s): %d",BCM3510_DEFAULT_FIRMWARE,ret); ++ ret = st->config->request_firmware(fe, &fw, BCM3510_DEFAULT_FIRMWARE); ++ if (ret) + return ret; +- } + deb_info("got firmware: %zu\n", fw->size); + + b = fw->data; +Index: linux/drivers/media/dvb-frontends/cx24116.c +=================================================================== +--- linux.orig/drivers/media/dvb-frontends/cx24116.c ++++ linux/drivers/media/dvb-frontends/cx24116.c +@@ -479,13 +479,8 @@ static int cx24116_firmware_ondemand(str + __func__, CX24116_DEFAULT_FIRMWARE); + ret = request_firmware(&fw, CX24116_DEFAULT_FIRMWARE, + state->i2c->dev.parent); +- printk(KERN_INFO "%s: Waiting for firmware upload(2)...\n", +- __func__); +- if (ret) { +- printk(KERN_ERR "%s: No firmware uploaded (timeout or file not found?)\n", +- __func__); ++ if (ret) + return ret; +- } + + /* Make sure we don't recurse back through here + * during loading */ +Index: linux/drivers/media/dvb-frontends/drxd_hard.c +=================================================================== +--- linux.orig/drivers/media/dvb-frontends/drxd_hard.c ++++ linux/drivers/media/dvb-frontends/drxd_hard.c +@@ -891,10 +891,8 @@ static int load_firmware(struct drxd_sta + { + const struct firmware *fw; + +- if (request_firmware(&fw, fw_name, state->dev) < 0) { +- printk(KERN_ERR "drxd: firmware load failure [%s]\n", fw_name); ++ if (request_firmware(&fw, fw_name, state->dev)) + return -EIO; +- } + + state->microcode = kmemdup(fw->data, fw->size, GFP_KERNEL); + if (!state->microcode) { +Index: linux/drivers/media/dvb-frontends/drxk_hard.c +=================================================================== +--- linux.orig/drivers/media/dvb-frontends/drxk_hard.c ++++ linux/drivers/media/dvb-frontends/drxk_hard.c +@@ -6247,10 +6247,6 @@ static void load_firmware_cb(const struc + + dprintk(1, ": %s\n", fw ? "firmware loaded" : "firmware not loaded"); + if (!fw) { +- pr_err("Could not load firmware file %s.\n", +- state->microcode_name); +- pr_info("Copy %s to your hotplug directory!\n", +- state->microcode_name); + state->microcode_name = NULL; + + /* +Index: linux/drivers/media/dvb-frontends/ds3000.c +=================================================================== +--- linux.orig/drivers/media/dvb-frontends/ds3000.c ++++ linux/drivers/media/dvb-frontends/ds3000.c +@@ -348,12 +348,8 @@ static int ds3000_firmware_ondemand(stru + DS3000_DEFAULT_FIRMWARE); + ret = request_firmware(&fw, DS3000_DEFAULT_FIRMWARE, + state->i2c->dev.parent); +- printk(KERN_INFO "%s: Waiting for firmware upload(2)...\n", __func__); +- if (ret) { +- printk(KERN_ERR "%s: No firmware uploaded (timeout or file not found?)\n", +- __func__); ++ if (ret) + return ret; +- } + + ret = ds3000_load_firmware(fe, fw); + if (ret) +Index: linux/drivers/media/dvb-frontends/nxt200x.c +=================================================================== +--- linux.orig/drivers/media/dvb-frontends/nxt200x.c ++++ linux/drivers/media/dvb-frontends/nxt200x.c +@@ -861,12 +861,8 @@ static int nxt2002_init(struct dvb_front + __func__, NXT2002_DEFAULT_FIRMWARE); + ret = request_firmware(&fw, NXT2002_DEFAULT_FIRMWARE, + state->i2c->dev.parent); +- pr_debug("%s: Waiting for firmware upload(2)...\n", __func__); +- if (ret) { +- pr_err("%s: No firmware uploaded (timeout or file not found?)\n", +- __func__); ++ if (ret) + return ret; +- } + + ret = nxt2002_load_firmware(fe, fw); + release_firmware(fw); +@@ -928,12 +924,8 @@ static int nxt2004_init(struct dvb_front + __func__, NXT2004_DEFAULT_FIRMWARE); + ret = request_firmware(&fw, NXT2004_DEFAULT_FIRMWARE, + state->i2c->dev.parent); +- pr_debug("%s: Waiting for firmware upload(2)...\n", __func__); +- if (ret) { +- pr_err("%s: No firmware uploaded (timeout or file not found?)\n", +- __func__); ++ if (ret) + return ret; +- } + + ret = nxt2004_load_firmware(fe, fw); + release_firmware(fw); +Index: linux/drivers/media/dvb-frontends/or51132.c +=================================================================== +--- linux.orig/drivers/media/dvb-frontends/or51132.c ++++ linux/drivers/media/dvb-frontends/or51132.c +@@ -326,10 +326,8 @@ static int or51132_set_parameters(struct + printk("or51132: Waiting for firmware upload(%s)...\n", + fwname); + ret = request_firmware(&fw, fwname, state->i2c->dev.parent); +- if (ret) { +- printk(KERN_WARNING "or51132: No firmware uploaded(timeout or file not found?)\n"); ++ if (ret) + return ret; +- } + ret = or51132_load_firmware(fe, fw); + release_firmware(fw); + if (ret) { +Index: linux/drivers/media/dvb-frontends/or51211.c +=================================================================== +--- linux.orig/drivers/media/dvb-frontends/or51211.c ++++ linux/drivers/media/dvb-frontends/or51211.c +@@ -361,11 +361,8 @@ static int or51211_init(struct dvb_front + OR51211_DEFAULT_FIRMWARE); + ret = config->request_firmware(fe, &fw, + OR51211_DEFAULT_FIRMWARE); +- pr_info("Got Hotplug firmware\n"); +- if (ret) { +- pr_warn("No firmware uploaded (timeout or file not found?)\n"); ++ if (ret) + return ret; +- } + + ret = or51211_load_firmware(fe, fw); + release_firmware(fw); +Index: linux/drivers/media/dvb-frontends/sp887x.c +=================================================================== +--- linux.orig/drivers/media/dvb-frontends/sp887x.c ++++ linux/drivers/media/dvb-frontends/sp887x.c +@@ -525,10 +525,8 @@ static int sp887x_init(struct dvb_fronte + /* request the firmware, this will block until someone uploads it */ + printk("sp887x: waiting for firmware upload (%s)...\n", SP887X_DEFAULT_FIRMWARE); + ret = state->config->request_firmware(fe, &fw, SP887X_DEFAULT_FIRMWARE); +- if (ret) { +- printk("sp887x: no firmware upload (timeout or file not found?)\n"); ++ if (ret) + return ret; +- } + + ret = sp887x_initial_setup(fe, fw); + release_firmware(fw); +Index: linux/drivers/media/dvb-frontends/tda10048.c +=================================================================== +--- linux.orig/drivers/media/dvb-frontends/tda10048.c ++++ linux/drivers/media/dvb-frontends/tda10048.c +@@ -483,8 +483,6 @@ static int tda10048_firmware_upload(stru + ret = request_firmware(&fw, TDA10048_DEFAULT_FIRMWARE, + state->i2c->dev.parent); + if (ret) { +- printk(KERN_ERR "%s: Upload failed. (file not found?)\n", +- __func__); + return -EIO; + } else { + printk(KERN_INFO "%s: firmware read %zu bytes.\n", +Index: linux/drivers/media/dvb-frontends/tda1004x.c +=================================================================== +--- linux.orig/drivers/media/dvb-frontends/tda1004x.c ++++ linux/drivers/media/dvb-frontends/tda1004x.c +@@ -388,10 +388,8 @@ static int tda10045_fwupload(struct dvb_ + /* request the firmware, this will block until someone uploads it */ + printk(KERN_INFO "tda1004x: waiting for firmware upload (%s)...\n", TDA10045_DEFAULT_FIRMWARE); + ret = state->config->request_firmware(fe, &fw, TDA10045_DEFAULT_FIRMWARE); +- if (ret) { +- printk(KERN_ERR "tda1004x: no firmware upload (timeout or file not found?)\n"); ++ if (ret) + return ret; +- } + + /* reset chip */ + tda1004x_write_mask(state, TDA1004X_CONFC4, 0x10, 0); +@@ -532,7 +530,6 @@ static int tda10046_fwupload(struct dvb_ + /* remain compatible to old bug: try to load with tda10045 image name */ + ret = state->config->request_firmware(fe, &fw, TDA10045_DEFAULT_FIRMWARE); + if (ret) { +- printk(KERN_ERR "tda1004x: no firmware upload (timeout or file not found?)\n"); + return ret; + } else { + printk(KERN_INFO "tda1004x: please rename the firmware file to %s\n", +Index: linux/drivers/media/dvb-frontends/tda10071.c +=================================================================== +--- linux.orig/drivers/media/dvb-frontends/tda10071.c ++++ linux/drivers/media/dvb-frontends/tda10071.c +@@ -838,12 +838,8 @@ static int tda10071_init(struct dvb_fron + + /* request the firmware, this will block and timeout */ + ret = request_firmware(&fw, fw_file, &client->dev); +- if (ret) { +- dev_err(&client->dev, +- "did not find the firmware file '%s' (status %d). You can use <kernel_dir>/scripts/get_dvb_firmware to get the firmware\n", +- fw_file, ret); ++ if (ret) + goto error; +- } + + /* init */ + for (i = 0; i < ARRAY_SIZE(tab2); i++) { +Index: linux/drivers/media/i2c/cx25840/cx25840-firmware.c +=================================================================== +--- linux.orig/drivers/media/i2c/cx25840/cx25840-firmware.c ++++ linux/drivers/media/i2c/cx25840/cx25840-firmware.c +@@ -113,10 +113,8 @@ int cx25840_loadfw(struct i2c_client *cl + if (is_cx231xx(state) && max_buf_size > 16) + max_buf_size = 16; + +- if (request_firmware(&fw, fwname, FWDEV(client)) != 0) { +- v4l_err(client, "unable to open firmware %s\n", fwname); ++ if (request_firmware(&fw, fwname, FWDEV(client)) != 0) + return -EINVAL; +- } + + start_fw_load(client); + +Index: linux/drivers/media/pci/bt8xx/bttv-cards.c +=================================================================== +--- linux.orig/drivers/media/pci/bt8xx/bttv-cards.c ++++ linux/drivers/media/pci/bt8xx/bttv-cards.c +@@ -3904,10 +3904,8 @@ static int pvr_boot(struct bttv *btv) + int rc; + + rc = request_firmware(&fw_entry, "hcwamc.rbf", &btv->c.pci->dev); +- if (rc != 0) { +- pr_warn("%d: no altera firmware [via hotplug]\n", btv->c.nr); ++ if (rc != 0) + return rc; +- } + rc = pvr_altera_load(btv, fw_entry->data, fw_entry->size); + pr_info("%d: altera firmware upload %s\n", + btv->c.nr, (rc < 0) ? "failed" : "ok"); +Index: linux/drivers/media/pci/cx18/cx18-av-firmware.c +=================================================================== +--- linux.orig/drivers/media/pci/cx18/cx18-av-firmware.c ++++ linux/drivers/media/pci/cx18/cx18-av-firmware.c +@@ -70,10 +70,8 @@ int cx18_av_loadfw(struct cx18 *cx) + int i; + int retries1 = 0; + +- if (request_firmware(&fw, FWFILE, &cx->pci_dev->dev) != 0) { +- CX18_ERR_DEV(sd, "unable to open firmware %s\n", FWFILE); ++ if (request_firmware(&fw, FWFILE, &cx->pci_dev->dev) != 0) + return -EINVAL; +- } + + /* The firmware load often has byte errors, so allow for several + retries, both at byte level and at the firmware load level. */ +Index: linux/drivers/media/pci/cx18/cx18-dvb.c +=================================================================== +--- linux.orig/drivers/media/pci/cx18/cx18-dvb.c ++++ linux/drivers/media/pci/cx18/cx18-dvb.c +@@ -127,9 +127,7 @@ static int yuan_mpc718_mt352_reqfw(struc + int ret; + + ret = request_firmware(fw, fn, &cx->pci_dev->dev); +- if (ret) +- CX18_ERR("Unable to open firmware file %s\n", fn); +- else { ++ if (!ret) { + size_t sz = (*fw)->size; + if (sz < 2 || sz > 64 || (sz % 2) != 0) { + CX18_ERR("Firmware %s has a bad size: %lu bytes\n", +Index: linux/drivers/media/pci/cx18/cx18-firmware.c +=================================================================== +--- linux.orig/drivers/media/pci/cx18/cx18-firmware.c ++++ linux/drivers/media/pci/cx18/cx18-firmware.c +@@ -92,11 +92,8 @@ static int load_cpu_fw_direct(const char + u32 __iomem *dst = (u32 __iomem *)mem; + const u32 *src; + +- if (request_firmware(&fw, fn, &cx->pci_dev->dev)) { +- CX18_ERR("Unable to open firmware %s\n", fn); +- CX18_ERR("Did you put the firmware in the hotplug firmware directory?\n"); ++ if (request_firmware(&fw, fn, &cx->pci_dev->dev)) + return -ENOMEM; +- } + + src = (const u32 *)fw->data; + +@@ -137,8 +134,6 @@ static int load_apu_fw_direct(const char + int sz; + + if (request_firmware(&fw, fn, &cx->pci_dev->dev)) { +- CX18_ERR("unable to open firmware %s\n", fn); +- CX18_ERR("did you put the firmware in the hotplug firmware directory?\n"); + cx18_setup_page(cx, 0); + return -ENOMEM; + } +Index: linux/drivers/media/pci/cx23885/cx23885-417.c +=================================================================== +--- linux.orig/drivers/media/pci/cx23885/cx23885-417.c ++++ linux/drivers/media/pci/cx23885/cx23885-417.c +@@ -920,12 +920,8 @@ static int cx23885_load_firmware(struct + retval = request_firmware(&firmware, CX23885_FIRM_IMAGE_NAME, + &dev->pci->dev); + +- if (retval != 0) { +- pr_err("ERROR: Hotplug firmware request failed (%s).\n", +- CX23885_FIRM_IMAGE_NAME); +- pr_err("Please fix your hotplug setup, the board will not work without firmware loaded!\n"); ++ if (retval != 0) + return -1; +- } + + if (firmware->size != CX23885_FIRM_IMAGE_SIZE) { + pr_err("ERROR: Firmware size mismatch (have %zu, expected %d)\n", +Index: linux/drivers/media/pci/cx23885/cx23885-cards.c +=================================================================== +--- linux.orig/drivers/media/pci/cx23885/cx23885-cards.c ++++ linux/drivers/media/pci/cx23885/cx23885-cards.c +@@ -2480,10 +2480,7 @@ void cx23885_card_setup(struct cx23885_d + cinfo.rev, filename); + + ret = request_firmware(&fw, filename, &dev->pci->dev); +- if (ret != 0) +- pr_err("did not find the firmware file '%s'. You can use <kernel_dir>/scripts/get_dvb_firmware to get the firmware.", +- filename); +- else ++ if (ret == 0) + altera_init(&netup_config, fw); + + release_firmware(fw); +Index: linux/drivers/media/pci/cx88/cx88-blackbird.c +=================================================================== +--- linux.orig/drivers/media/pci/cx88/cx88-blackbird.c ++++ linux/drivers/media/pci/cx88/cx88-blackbird.c +@@ -462,12 +462,8 @@ static int blackbird_load_firmware(struc + retval = request_firmware(&firmware, CX2341X_FIRM_ENC_FILENAME, + &dev->pci->dev); + +- if (retval != 0) { +- pr_err("Hotplug firmware request failed (%s).\n", +- CX2341X_FIRM_ENC_FILENAME); +- pr_err("Please fix your hotplug setup, the board will not work without firmware loaded!\n"); ++ if (retval != 0) + return -EIO; +- } + + if (firmware->size != BLACKBIRD_FIRM_IMAGE_SIZE) { + pr_err("Firmware size mismatch (have %zd, expected %d)\n", +Index: linux/drivers/media/pci/ivtv/ivtv-firmware.c +=================================================================== +--- linux.orig/drivers/media/pci/ivtv/ivtv-firmware.c ++++ linux/drivers/media/pci/ivtv/ivtv-firmware.c +@@ -68,8 +68,6 @@ retry: + release_firmware(fw); + return size; + } +- IVTV_ERR("Unable to open firmware %s (must be %ld bytes)\n", fn, size); +- IVTV_ERR("Did you put the firmware in the hotplug firmware directory?\n"); + return -ENOMEM; + } + +Index: linux/drivers/media/pci/ngene/ngene-core.c +=================================================================== +--- linux.orig/drivers/media/pci/ngene/ngene-core.c ++++ linux/drivers/media/pci/ngene/ngene-core.c +@@ -1236,19 +1236,14 @@ static int ngene_load_firm(struct ngene + break; + } + +- if (request_firmware(&fw, fw_name, &dev->pci_dev->dev) < 0) { +- dev_err(pdev, "Could not load firmware file %s.\n", fw_name); +- dev_info(pdev, "Copy %s to your hotplug directory!\n", +- fw_name); ++ if (request_firmware(&fw, fw_name, &dev->pci_dev->dev)) + return -1; +- } + if (size == 0) + size = fw->size; + if (size != fw->size) { + dev_err(pdev, "Firmware %s has invalid size!", fw_name); + err = -1; + } else { +- dev_info(pdev, "Loading firmware file %s.\n", fw_name); + ngene_fw = (u8 *) fw->data; + err = ngene_command_load_firmware(dev, ngene_fw, size); + } +Index: linux/drivers/media/pci/saa7164/saa7164-fw.c +=================================================================== +--- linux.orig/drivers/media/pci/saa7164/saa7164-fw.c ++++ linux/drivers/media/pci/saa7164/saa7164-fw.c +@@ -406,11 +406,8 @@ int saa7164_downloadfirmware(struct saa7 + __func__, fwname); + + ret = request_firmware(&fw, fwname, &dev->pci->dev); +- if (ret) { +- printk(KERN_ERR "%s() Upload failed. (file not found?)\n", +- __func__); ++ if (ret) + return -ENOMEM; +- } + + printk(KERN_INFO "%s() firmware read %zu bytes.\n", + __func__, fw->size); +Index: linux/drivers/media/platform/samsung/s5p-mfc/s5p_mfc_ctrl.c +=================================================================== +--- linux.orig/drivers/media/platform/samsung/s5p-mfc/s5p_mfc_ctrl.c ++++ linux/drivers/media/platform/samsung/s5p-mfc/s5p_mfc_ctrl.c +@@ -65,10 +65,8 @@ int s5p_mfc_load_firmware(struct s5p_mfc + } + } + +- if (err != 0) { +- mfc_err("Firmware is not present in the /lib/firmware directory nor compiled in kernel\n"); ++ if (err != 0) + return -EINVAL; +- } + if (fw_blob->size > dev->fw_buf.size) { + mfc_err("MFC firmware is too big to be loaded\n"); + release_firmware(fw_blob); +Index: linux/drivers/media/radio/radio-wl1273.c +=================================================================== +--- linux.orig/drivers/media/radio/radio-wl1273.c ++++ linux/drivers/media/radio/radio-wl1273.c +@@ -502,11 +502,8 @@ static int wl1273_fm_upload_firmware_pat + * Uploading the firmware patch is not always necessary, + * so we only print an info message. + */ +- if (request_firmware(&fw_p, fw_name, dev)) { +- dev_info(dev, "%s - %s not found\n", __func__, fw_name); +- ++ if (request_firmware(&fw_p, fw_name, dev)) + return 0; +- } + + ptr = (__u8 *) fw_p->data; + packet_num = ptr[0]; +Index: linux/drivers/media/radio/wl128x/fmdrv_common.c +=================================================================== +--- linux.orig/drivers/media/radio/wl128x/fmdrv_common.c ++++ linux/drivers/media/radio/wl128x/fmdrv_common.c +@@ -1241,10 +1241,8 @@ static int fm_download_firmware(struct f + + ret = request_firmware(&fw_entry, fw_name, + &fmdev->radio_dev->dev); +- if (ret < 0) { +- fmerr("Unable to read firmware(%s) content\n", fw_name); ++ if (ret) + return ret; +- } + fmdbg("Firmware(%s) length : %zu bytes\n", fw_name, fw_entry->size); + + fw_data = (void *)fw_entry->data; +Index: linux/drivers/media/tuners/xc2028.c +=================================================================== +--- linux.orig/drivers/media/tuners/xc2028.c ++++ linux/drivers/media/tuners/xc2028.c +@@ -1366,7 +1366,6 @@ static void load_firmware_cb(const struc + + tuner_dbg("request_firmware_nowait(): %s\n", fw ? "OK" : "error"); + if (!fw) { +- tuner_err("Could not load firmware %s.\n", priv->fname); + priv->state = XC2028_NODEV; + return; + } +Index: linux/drivers/media/usb/cx231xx/cx231xx-417.c +=================================================================== +--- linux.orig/drivers/media/usb/cx231xx/cx231xx-417.c ++++ linux/drivers/media/usb/cx231xx/cx231xx-417.c +@@ -983,11 +983,6 @@ static int cx231xx_load_firmware(struct + dev->dev); + + if (retval != 0) { +- dev_err(dev->dev, +- "ERROR: Hotplug firmware request failed (%s).\n", +- CX231xx_FIRM_IMAGE_NAME); +- dev_err(dev->dev, +- "Please fix your hotplug setup, the board will not work without firmware loaded!\n"); + vfree(p_current_fw); + vfree(p_buffer); + return retval; +Index: linux/drivers/media/usb/dvb-usb/dib0700_devices.c +=================================================================== +--- linux.orig/drivers/media/usb/dvb-usb/dib0700_devices.c ++++ linux/drivers/media/usb/dvb-usb/dib0700_devices.c +@@ -2408,12 +2408,9 @@ static int stk9090m_frontend_attach(stru + + dib9000_i2c_enumeration(&adap->dev->i2c_adap, 1, 0x10, 0x80); + +- if (request_firmware(&state->frontend_firmware, "dib9090.fw", &adap->dev->udev->dev)) { +- deb_info("%s: Upload failed. (file not found?)\n", __func__); ++ if (request_firmware(&state->frontend_firmware, "dib9090.fw", &adap->dev->udev->dev)) + return -ENODEV; +- } else { +- deb_info("%s: firmware read %zu bytes.\n", __func__, state->frontend_firmware->size); +- } ++ deb_info("%s: firmware read %zu bytes.\n", __func__, state->frontend_firmware->size); + stk9090m_config.microcode_B_fe_size = state->frontend_firmware->size; + stk9090m_config.microcode_B_fe_buffer = state->frontend_firmware->data; + +@@ -2478,12 +2475,9 @@ static int nim9090md_frontend_attach(str + msleep(20); + dib0700_set_gpio(adap->dev, GPIO0, GPIO_OUT, 1); + +- if (request_firmware(&state->frontend_firmware, "dib9090.fw", &adap->dev->udev->dev)) { +- deb_info("%s: Upload failed. (file not found?)\n", __func__); ++ if (request_firmware(&state->frontend_firmware, "dib9090.fw", &adap->dev->udev->dev)) + return -EIO; +- } else { +- deb_info("%s: firmware read %zu bytes.\n", __func__, state->frontend_firmware->size); +- } ++ deb_info("%s: firmware read %zu bytes.\n", __func__, state->frontend_firmware->size); + nim9090md_config[0].microcode_B_fe_size = state->frontend_firmware->size; + nim9090md_config[0].microcode_B_fe_buffer = state->frontend_firmware->data; + nim9090md_config[1].microcode_B_fe_size = state->frontend_firmware->size; +Index: linux/drivers/media/usb/dvb-usb/dvb-usb-firmware.c +=================================================================== +--- linux.orig/drivers/media/usb/dvb-usb/dvb-usb-firmware.c ++++ linux/drivers/media/usb/dvb-usb/dvb-usb-firmware.c +@@ -90,13 +90,9 @@ int dvb_usb_download_firmware(struct usb + int ret; + const struct firmware *fw = NULL; + +- if ((ret = request_firmware(&fw, props->firmware, &udev->dev)) != 0) { +- err("did not find the firmware file '%s' (status %d). You can use <kernel_dir>/scripts/get_dvb_firmware to get the firmware", +- props->firmware,ret); ++ ret = request_firmware(&fw, props->firmware, &udev->dev); ++ if (ret) + return ret; +- } +- +- info("downloading firmware from file '%s'",props->firmware); + + switch (props->usb_ctrl) { + case CYPRESS_AN2135: +Index: linux/drivers/media/usb/dvb-usb/gp8psk.c +=================================================================== +--- linux.orig/drivers/media/usb/dvb-usb/gp8psk.c ++++ linux/drivers/media/usb/dvb-usb/gp8psk.c +@@ -131,19 +131,14 @@ static int gp8psk_load_bcm4500fw(struct + const u8 *ptr; + u8 *buf; + if ((ret = request_firmware(&fw, bcm4500_firmware, +- &d->udev->dev)) != 0) { +- err("did not find the bcm4500 firmware file '%s' (status %d). You can use <kernel_dir>/scripts/get_dvb_firmware to get the firmware", +- bcm4500_firmware,ret); ++ &d->udev->dev)) != 0) + return ret; +- } + + ret = -EINVAL; + + if (gp8psk_usb_out_op(d, LOAD_BCM4500,1,0,NULL, 0)) + goto out_rel_fw; + +- info("downloading bcm4500 firmware from file '%s'",bcm4500_firmware); +- + ptr = fw->data; + buf = kmalloc(64, GFP_KERNEL); + if (!buf) { +Index: linux/drivers/media/usb/dvb-usb/opera1.c +=================================================================== +--- linux.orig/drivers/media/usb/dvb-usb/opera1.c ++++ linux/drivers/media/usb/dvb-usb/opera1.c +@@ -455,8 +455,6 @@ static int opera1_xilinx_load_firmware(s + info("start downloading fpga firmware %s",filename); + + if ((ret = request_firmware(&fw, filename, &dev->dev)) != 0) { +- err("did not find the firmware file '%s'. You can use <kernel_dir>/scripts/get_dvb_firmware to get the firmware", +- filename); + return ret; + } else { + p = kmalloc(fw->size, GFP_KERNEL); +Index: linux/drivers/media/usb/go7007/go7007-driver.c +=================================================================== +--- linux.orig/drivers/media/usb/go7007/go7007-driver.c ++++ linux/drivers/media/usb/go7007/go7007-driver.c +@@ -84,10 +84,8 @@ static int go7007_load_encoder(struct go + u16 intr_val, intr_data; + + if (go->boot_fw == NULL) { +- if (request_firmware(&fw_entry, fw_name, go->dev)) { +- v4l2_err(go, "unable to load firmware from file \"%s\"\n", fw_name); ++ if (request_firmware(&fw_entry, fw_name, go->dev)) + return -1; +- } + if (fw_entry->size < 16 || memcmp(fw_entry->data, "WISGO7007FW", 11)) { + v4l2_err(go, "file \"%s\" does not appear to be go7007 firmware\n", fw_name); + release_firmware(fw_entry); +Index: linux/drivers/media/usb/go7007/go7007-fw.c +=================================================================== +--- linux.orig/drivers/media/usb/go7007/go7007-fw.c ++++ linux/drivers/media/usb/go7007/go7007-fw.c +@@ -1565,12 +1565,8 @@ int go7007_construct_fw_image(struct go7 + default: + return -1; + } +- if (request_firmware(&fw_entry, GO7007_FW_NAME, go->dev)) { +- dev_err(go->dev, +- "unable to load firmware from file \"%s\"\n", +- GO7007_FW_NAME); ++ if (request_firmware(&fw_entry, GO7007_FW_NAME, go->dev)) + return -1; +- } + code = kcalloc(codespace, 2, GFP_KERNEL); + if (code == NULL) + goto fw_failed; +Index: linux/drivers/media/usb/go7007/go7007-loader.c +=================================================================== +--- linux.orig/drivers/media/usb/go7007/go7007-loader.c ++++ linux/drivers/media/usb/go7007/go7007-loader.c +@@ -67,11 +67,8 @@ static int go7007_loader_probe(struct us + + dev_info(&interface->dev, "loading firmware %s\n", fw1); + +- if (request_firmware(&fw, fw1, &usbdev->dev)) { +- dev_err(&interface->dev, +- "unable to load firmware from file \"%s\"\n", fw1); ++ if (request_firmware(&fw, fw1, &usbdev->dev)) + goto failed2; +- } + ret = cypress_load_firmware(usbdev, fw, CYPRESS_FX2); + release_firmware(fw); + if (0 != ret) { +@@ -82,11 +79,8 @@ static int go7007_loader_probe(struct us + if (fw2 == NULL) + return 0; + +- if (request_firmware(&fw, fw2, &usbdev->dev)) { +- dev_err(&interface->dev, +- "unable to load firmware from file \"%s\"\n", fw2); ++ if (request_firmware(&fw, fw2, &usbdev->dev)) + goto failed2; +- } + ret = cypress_load_firmware(usbdev, fw, CYPRESS_FX2); + release_firmware(fw); + if (0 != ret) { +Index: linux/drivers/media/usb/gspca/vicam.c +=================================================================== +--- linux.orig/drivers/media/usb/gspca/vicam.c ++++ linux/drivers/media/usb/gspca/vicam.c +@@ -230,10 +230,8 @@ static int sd_init(struct gspca_dev *gsp + + ret = request_ihex_firmware(&fw, VICAM_FIRMWARE, + &gspca_dev->dev->dev); +- if (ret) { +- pr_err("Failed to load \"vicam/firmware.fw\": %d\n", ret); ++ if (ret) + return ret; +- } + + firmware_buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!firmware_buf) { +Index: linux/drivers/media/usb/pvrusb2/pvrusb2-hdw.c +=================================================================== +--- linux.orig/drivers/media/usb/pvrusb2/pvrusb2-hdw.c ++++ linux/drivers/media/usb/pvrusb2/pvrusb2-hdw.c +@@ -1370,25 +1370,6 @@ static int pvr2_locate_firmware(struct p + "request_firmware fatal error with code=%d",ret); + return ret; + } +- pvr2_trace(PVR2_TRACE_ERROR_LEGS, +- "***WARNING*** Device %s firmware seems to be missing.", +- fwtypename); +- pvr2_trace(PVR2_TRACE_ERROR_LEGS, +- "Did you install the pvrusb2 firmware files in their proper location?"); +- if (fwcount == 1) { +- pvr2_trace(PVR2_TRACE_ERROR_LEGS, +- "request_firmware unable to locate %s file %s", +- fwtypename,fwnames[0]); +- } else { +- pvr2_trace(PVR2_TRACE_ERROR_LEGS, +- "request_firmware unable to locate one of the following %s files:", +- fwtypename); +- for (idx = 0; idx < fwcount; idx++) { +- pvr2_trace(PVR2_TRACE_ERROR_LEGS, +- "request_firmware: Failed to find %s", +- fwnames[idx]); +- } +- } + return ret; + } + +Index: linux/drivers/media/usb/s2255/s2255drv.c +=================================================================== +--- linux.orig/drivers/media/usb/s2255/s2255drv.c ++++ linux/drivers/media/usb/s2255/s2255drv.c +@@ -2276,10 +2276,8 @@ static int s2255_probe(struct usb_interf + } + /* load the first chunk */ + if (request_firmware(&dev->fw_data->fw, +- FIRMWARE_FILE_NAME, &dev->udev->dev)) { +- dev_err(&interface->dev, "sensoray 2255 failed to get firmware\n"); ++ FIRMWARE_FILE_NAME, &dev->udev->dev)) + goto errorREQFW; +- } + /* check the firmware is valid */ + fw_size = dev->fw_data->fw->size; + pdata = (__le32 *) &dev->fw_data->fw->data[fw_size - 8]; +Index: linux/drivers/media/usb/ttusb-budget/dvb-ttusb-budget.c +=================================================================== +--- linux.orig/drivers/media/usb/ttusb-budget/dvb-ttusb-budget.c ++++ linux/drivers/media/usb/ttusb-budget/dvb-ttusb-budget.c +@@ -282,10 +282,8 @@ static int ttusb_boot_dsp(struct ttusb * + + err = request_firmware(&fw, "ttusb-budget/dspbootcode.bin", + &ttusb->dev->dev); +- if (err) { +- pr_err("failed to request firmware\n"); ++ if (err) + return err; +- } + + /* BootBlock */ + b[0] = 0xaa; +Index: linux/drivers/media/usb/ttusb-dec/ttusb_dec.c +=================================================================== +--- linux.orig/drivers/media/usb/ttusb-dec/ttusb_dec.c ++++ linux/drivers/media/usb/ttusb-dec/ttusb_dec.c +@@ -1317,11 +1317,8 @@ static int ttusb_dec_boot_dsp(struct ttu + dprintk("%s\n", __func__); + + result = request_firmware(&fw_entry, dec->firmware_name, &dec->udev->dev); +- if (result) { +- printk(KERN_ERR "%s: Firmware (%s) unavailable.\n", +- __func__, dec->firmware_name); ++ if (result) + return result; +- } + + firmware = fw_entry->data; + firmware_size = fw_entry->size; +Index: linux/drivers/misc/ti-st/st_kim.c +=================================================================== +--- linux.orig/drivers/misc/ti-st/st_kim.c ++++ linux/drivers/misc/ti-st/st_kim.c +@@ -295,11 +295,8 @@ static long download_firmware(struct kim + request_firmware(&kim_gdata->fw_entry, bts_scr_name, + &kim_gdata->kim_pdev->dev); + if (unlikely((err != 0) || (kim_gdata->fw_entry->data == NULL) || +- (kim_gdata->fw_entry->size == 0))) { +- pr_err(" request_firmware failed(errno %ld) for %s", err, +- bts_scr_name); ++ (kim_gdata->fw_entry->size == 0))) + return -EINVAL; +- } + ptr = (void *)kim_gdata->fw_entry->data; + len = kim_gdata->fw_entry->size; + /* +Index: linux/drivers/net/can/softing/softing_fw.c +=================================================================== +--- linux.orig/drivers/net/can/softing/softing_fw.c ++++ linux/drivers/net/can/softing/softing_fw.c +@@ -226,11 +226,8 @@ int softing_load_app_fw(const char *file + int8_t type_end = 0, type_entrypoint = 0; + + ret = request_firmware(&fw, file, &card->pdev->dev); +- if (ret) { +- dev_alert(&card->pdev->dev, "request_firmware(%s) got %i\n", +- file, ret); ++ if (ret) + return ret; +- } + dev_dbg(&card->pdev->dev, "firmware(%s) got %lu bytes\n", + file, (unsigned long)fw->size); + /* parse the firmware */ +Index: linux/drivers/net/ethernet/3com/typhoon.c +=================================================================== +--- linux.orig/drivers/net/ethernet/3com/typhoon.c ++++ linux/drivers/net/ethernet/3com/typhoon.c +@@ -1279,11 +1279,8 @@ typhoon_request_firmware(struct typhoon + return 0; + + err = request_firmware(&typhoon_fw, FIRMWARE_NAME, &tp->pdev->dev); +- if (err) { +- netdev_err(tp->dev, "Failed to load firmware \"%s\"\n", +- FIRMWARE_NAME); ++ if (err) + return err; +- } + + image_data = typhoon_fw->data; + remaining = typhoon_fw->size; +Index: linux/drivers/net/ethernet/adaptec/starfire.c +=================================================================== +--- linux.orig/drivers/net/ethernet/adaptec/starfire.c ++++ linux/drivers/net/ethernet/adaptec/starfire.c +@@ -1004,11 +1004,8 @@ static int netdev_open(struct net_device + #endif /* VLAN_SUPPORT */ + + retval = request_firmware(&fw_rx, FIRMWARE_RX, &np->pci_dev->dev); +- if (retval) { +- printk(KERN_ERR "starfire: Failed to load firmware \"%s\"\n", +- FIRMWARE_RX); ++ if (retval) + goto out_init; +- } + if (fw_rx->size % 4) { + printk(KERN_ERR "starfire: bogus length %zu in \"%s\"\n", + fw_rx->size, FIRMWARE_RX); +@@ -1016,11 +1013,8 @@ static int netdev_open(struct net_device + goto out_rx; + } + retval = request_firmware(&fw_tx, FIRMWARE_TX, &np->pci_dev->dev); +- if (retval) { +- printk(KERN_ERR "starfire: Failed to load firmware \"%s\"\n", +- FIRMWARE_TX); ++ if (retval) + goto out_rx; +- } + if (fw_tx->size % 4) { + printk(KERN_ERR "starfire: bogus length %zu in \"%s\"\n", + fw_tx->size, FIRMWARE_TX); +Index: linux/drivers/net/ethernet/alacritech/slicoss.c +=================================================================== +--- linux.orig/drivers/net/ethernet/alacritech/slicoss.c ++++ linux/drivers/net/ethernet/alacritech/slicoss.c +@@ -1051,11 +1051,8 @@ static int slic_load_rcvseq_firmware(str + file = (sdev->model == SLIC_MODEL_OASIS) ? SLIC_RCV_FIRMWARE_OASIS : + SLIC_RCV_FIRMWARE_MOJAVE; + err = request_firmware(&fw, file, &sdev->pdev->dev); +- if (err) { +- dev_err(&sdev->pdev->dev, +- "failed to load receive sequencer firmware %s\n", file); ++ if (err) + return err; +- } + /* Do an initial sanity check concerning firmware size now. A further + * check follows below. + */ +@@ -1126,10 +1123,8 @@ static int slic_load_firmware(struct sli + file = (sdev->model == SLIC_MODEL_OASIS) ? SLIC_FIRMWARE_OASIS : + SLIC_FIRMWARE_MOJAVE; + err = request_firmware(&fw, file, &sdev->pdev->dev); +- if (err) { +- dev_err(&sdev->pdev->dev, "failed to load firmware %s\n", file); ++ if (err) + return err; +- } + /* Do an initial sanity check concerning firmware size now. A further + * check follows below. + */ +Index: linux/drivers/net/ethernet/alteon/acenic.c +=================================================================== +--- linux.orig/drivers/net/ethernet/alteon/acenic.c ++++ linux/drivers/net/ethernet/alteon/acenic.c +@@ -2878,11 +2878,8 @@ static int ace_load_firmware(struct net_ + fw_name = "acenic/tg1.bin"; + + ret = request_firmware(&fw, fw_name, &ap->pdev->dev); +- if (ret) { +- printk(KERN_ERR "%s: Failed to load firmware \"%s\"\n", +- ap->name, fw_name); ++ if (ret) + return ret; +- } + + fw_data = (void *)fw->data; + +Index: linux/drivers/net/ethernet/broadcom/bnx2.c +=================================================================== +--- linux.orig/drivers/net/ethernet/broadcom/bnx2.c ++++ linux/drivers/net/ethernet/broadcom/bnx2.c +@@ -3712,16 +3712,13 @@ static int bnx2_request_uncached_firmwar + } + + rc = request_firmware(&bp->mips_firmware, mips_fw_file, &bp->pdev->dev); +- if (rc) { +- pr_err("Can't load firmware file \"%s\"\n", mips_fw_file); ++ if (rc) + goto out; +- } + + rc = request_firmware(&bp->rv2p_firmware, rv2p_fw_file, &bp->pdev->dev); +- if (rc) { +- pr_err("Can't load firmware file \"%s\"\n", rv2p_fw_file); ++ if (rc) + goto err_release_mips_firmware; +- } ++ + mips_fw = (const struct bnx2_mips_fw_file *) bp->mips_firmware->data; + rv2p_fw = (const struct bnx2_rv2p_fw_file *) bp->rv2p_firmware->data; + if (bp->mips_firmware->size < sizeof(*mips_fw) || +Index: linux/drivers/net/ethernet/broadcom/tg3.c +=================================================================== +--- linux.orig/drivers/net/ethernet/broadcom/tg3.c ++++ linux/drivers/net/ethernet/broadcom/tg3.c +@@ -11398,11 +11398,8 @@ static int tg3_request_firmware(struct t + { + const struct tg3_firmware_hdr *fw_hdr; + +- if (request_firmware(&tp->fw, tp->fw_needed, &tp->pdev->dev)) { +- netdev_err(tp->dev, "Failed to load firmware \"%s\"\n", +- tp->fw_needed); ++ if (request_firmware(&tp->fw, tp->fw_needed, &tp->pdev->dev)) + return -ENOENT; +- } + + fw_hdr = (struct tg3_firmware_hdr *)tp->fw->data; + +Index: linux/drivers/net/ethernet/brocade/bna/cna_fwimg.c +=================================================================== +--- linux.orig/drivers/net/ethernet/brocade/bna/cna_fwimg.c ++++ linux/drivers/net/ethernet/brocade/bna/cna_fwimg.c +@@ -24,10 +24,8 @@ cna_read_firmware(struct pci_dev *pdev, + const struct firmware *fw; + u32 n; + +- if (request_firmware(&fw, fw_name, &pdev->dev)) { +- dev_alert(&pdev->dev, "can't load firmware %s\n", fw_name); ++ if (request_firmware(&fw, fw_name, &pdev->dev)) + goto error; +- } + + *bfi_image = (u32 *)fw->data; + *bfi_image_size = fw->size/sizeof(u32); +Index: linux/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +=================================================================== +--- linux.orig/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c ++++ linux/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +@@ -1035,12 +1035,8 @@ int t3_get_edc_fw(struct cphy *phy, int + fw_name = get_edc_fw_name(edc_idx); + if (fw_name) + ret = request_firmware(&fw, fw_name, &adapter->pdev->dev); +- if (ret < 0) { +- dev_err(&adapter->pdev->dev, +- "could not upgrade firmware: unable to load %s\n", +- fw_name); ++ if (ret) + return ret; +- } + + /* check size, take checksum in account */ + if (fw->size > size + 4) { +@@ -1077,11 +1073,8 @@ static int upgrade_fw(struct adapter *ad + struct device *dev = &adap->pdev->dev; + + ret = request_firmware(&fw, FW_FNAME, dev); +- if (ret < 0) { +- dev_err(dev, "could not upgrade firmware: unable to load %s\n", +- FW_FNAME); ++ if (ret) + return ret; +- } + ret = t3_load_fw(adap, fw->data, fw->size); + release_firmware(fw); + +@@ -1126,11 +1119,8 @@ static int update_tpsram(struct adapter + snprintf(buf, sizeof(buf), TPSRAM_NAME, rev); + + ret = request_firmware(&tpsram, buf, dev); +- if (ret < 0) { +- dev_err(dev, "could not load TP SRAM: unable to load %s\n", +- buf); ++ if (ret) + return ret; +- } + + ret = t3_check_tpsram(adap, tpsram->data, tpsram->size); + if (ret) +Index: linux/drivers/net/ethernet/intel/e100.c +=================================================================== +--- linux.orig/drivers/net/ethernet/intel/e100.c ++++ linux/drivers/net/ethernet/intel/e100.c +@@ -1262,9 +1262,6 @@ static const struct firmware *e100_reque + + if (err) { + if (required) { +- netif_err(nic, probe, nic->netdev, +- "Failed to load firmware \"%s\": %d\n", +- fw_name, err); + return ERR_PTR(err); + } else { + netif_info(nic, probe, nic->netdev, +Index: linux/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +=================================================================== +--- linux.orig/drivers/net/ethernet/myricom/myri10ge/myri10ge.c ++++ linux/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +@@ -580,8 +580,6 @@ static int myri10ge_load_hotplug_firmwar + unsigned i; + + if (request_firmware(&fw, mgp->fw_name, dev) < 0) { +- dev_err(dev, "Unable to load %s firmware image via hotplug\n", +- mgp->fw_name); + status = -EINVAL; + goto abort_with_nothing; + } +Index: linux/drivers/net/ethernet/smsc/smc91c92_cs.c +=================================================================== +--- linux.orig/drivers/net/ethernet/smsc/smc91c92_cs.c ++++ linux/drivers/net/ethernet/smsc/smc91c92_cs.c +@@ -651,10 +651,8 @@ static int osi_load_firmware(struct pcmc + int i, err; + + err = request_firmware(&fw, FIRMWARE_NAME, &link->dev); +- if (err) { +- pr_err("Failed to load firmware \"%s\"\n", FIRMWARE_NAME); ++ if (err) + return err; +- } + + /* Download the Seven of Diamonds firmware */ + for (i = 0; i < fw->size; i++) { +Index: linux/drivers/net/ethernet/sun/cassini.c +=================================================================== +--- linux.orig/drivers/net/ethernet/sun/cassini.c ++++ linux/drivers/net/ethernet/sun/cassini.c +@@ -794,11 +794,8 @@ static void cas_saturn_firmware_init(str + return; + + err = request_firmware(&fw, fw_name, &cp->pdev->dev); +- if (err) { +- pr_err("Failed to load firmware \"%s\"\n", +- fw_name); ++ if (err) + return; +- } + if (fw->size < 2) { + pr_err("bogus length %zu in \"%s\"\n", + fw->size, fw_name); +Index: linux/drivers/net/hamradio/yam.c +=================================================================== +--- linux.orig/drivers/net/hamradio/yam.c ++++ linux/drivers/net/hamradio/yam.c +@@ -357,11 +357,8 @@ static unsigned char *add_mcs(unsigned c + } + err = request_firmware(&fw, fw_name[predef], &pdev->dev); + platform_device_unregister(pdev); +- if (err) { +- printk(KERN_ERR "Failed to load firmware \"%s\"\n", +- fw_name[predef]); ++ if (err) + return NULL; +- } + if (fw->size != YAM_FPGA_SIZE) { + printk(KERN_ERR "Bogus length %zu in firmware \"%s\"\n", + fw->size, fw_name[predef]); +Index: linux/drivers/net/usb/kaweth.c +=================================================================== +--- linux.orig/drivers/net/usb/kaweth.c ++++ linux/drivers/net/usb/kaweth.c +@@ -305,10 +305,8 @@ static int kaweth_download_firmware(stru + int ret; + + ret = request_firmware(&fw, fwname, &kaweth->dev->dev); +- if (ret) { +- dev_err(&kaweth->intf->dev, "Firmware request failed\n"); ++ if (ret) + return ret; +- } + + if (fw->size > KAWETH_FIRMWARE_BUF_SIZE) { + dev_err(&kaweth->intf->dev, "Firmware too big: %zu\n", +Index: linux/drivers/net/wireless/ath/ath9k/hif_usb.c +=================================================================== +--- linux.orig/drivers/net/wireless/ath/ath9k/hif_usb.c ++++ linux/drivers/net/wireless/ath/ath9k/hif_usb.c +@@ -1222,9 +1222,6 @@ static void ath9k_hif_usb_firmware_cb(co + if (!ret) + return; + +- dev_err(&hif_dev->udev->dev, +- "ath9k_htc: Failed to get firmware %s\n", +- hif_dev->fw_name); + goto err_fw; + } + +Index: linux/drivers/net/wireless/ath/carl9170/usb.c +=================================================================== +--- linux.orig/drivers/net/wireless/ath/carl9170/usb.c ++++ linux/drivers/net/wireless/ath/carl9170/usb.c +@@ -1029,7 +1029,6 @@ static void carl9170_usb_firmware_step2( + return; + } + +- dev_err(&ar->udev->dev, "firmware not found.\n"); + carl9170_usb_firmware_failed(ar); + } + +Index: linux/drivers/net/wireless/atmel/at76c50x-usb.c +=================================================================== +--- linux.orig/drivers/net/wireless/atmel/at76c50x-usb.c ++++ linux/drivers/net/wireless/atmel/at76c50x-usb.c +@@ -1616,13 +1616,8 @@ static struct fwentry *at76_load_firmwar + + at76_dbg(DBG_FW, "downloading firmware %s", fwe->fwname); + ret = request_firmware(&fwe->fw, fwe->fwname, &udev->dev); +- if (ret < 0) { +- dev_err(&udev->dev, "firmware %s not found!\n", +- fwe->fwname); +- dev_err(&udev->dev, +- "you may need to download the firmware from http://developer.berlios.de/projects/at76c503a/\n"); ++ if (ret) + goto exit; +- } + + at76_dbg(DBG_FW, "got it."); + fwh = (struct at76_fw_header *)(fwe->fw->data); +Index: linux/drivers/net/wireless/atmel/atmel.c +=================================================================== +--- linux.orig/drivers/net/wireless/atmel/atmel.c ++++ linux/drivers/net/wireless/atmel/atmel.c +@@ -3896,12 +3896,8 @@ static int reset_atmel_card(struct net_d + strcpy(priv->firmware_id, "atmel_at76c502.bin"); + } + err = request_firmware(&fw_entry, priv->firmware_id, priv->sys_dev); +- if (err != 0) { +- printk(KERN_ALERT +- "%s: firmware %s is missing, cannot continue.\n", +- dev->name, priv->firmware_id); ++ if (err != 0) + return err; +- } + } else { + int fw_index = 0; + int success = 0; +Index: linux/drivers/net/wireless/broadcom/b43/main.c +=================================================================== +--- linux.orig/drivers/net/wireless/broadcom/b43/main.c ++++ linux/drivers/net/wireless/broadcom/b43/main.c +@@ -2245,19 +2245,8 @@ int b43_do_request_fw(struct b43_request + } + err = request_firmware(&ctx->blob, ctx->fwname, + ctx->dev->dev->dev); +- if (err == -ENOENT) { +- snprintf(ctx->errors[ctx->req_type], +- sizeof(ctx->errors[ctx->req_type]), +- "Firmware file \"%s\" not found\n", +- ctx->fwname); ++ if (err) + return err; +- } else if (err) { +- snprintf(ctx->errors[ctx->req_type], +- sizeof(ctx->errors[ctx->req_type]), +- "Firmware file \"%s\" request failed (err=%d)\n", +- ctx->fwname, err); +- return err; +- } + fw_ready: + if (ctx->blob->size < sizeof(struct b43_fw_header)) + goto err_format; +Index: linux/drivers/net/wireless/broadcom/b43legacy/main.c +=================================================================== +--- linux.orig/drivers/net/wireless/broadcom/b43legacy/main.c ++++ linux/drivers/net/wireless/broadcom/b43legacy/main.c +@@ -1524,11 +1524,8 @@ static int do_request_fw(struct b43legac + } else { + err = request_firmware(fw, path, dev->dev->dev); + } +- if (err) { +- b43legacyerr(dev->wl, "Firmware file \"%s\" not found " +- "or load failed.\n", path); ++ if (err) + return err; +- } + if ((*fw)->size < sizeof(struct b43legacy_fw_header)) + goto err_format; + hdr = (struct b43legacy_fw_header *)((*fw)->data); +Index: linux/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c +=================================================================== +--- linux.orig/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c ++++ linux/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c +@@ -376,19 +376,13 @@ static int brcms_request_fw(struct brcms + sprintf(fw_name, "%s-%d.fw", brcms_firmwares[i], + UCODE_LOADER_API_VER); + status = request_firmware(&wl->fw.fw_bin[i], fw_name, device); +- if (status) { +- wiphy_err(wl->wiphy, "%s: fail to load firmware %s\n", +- KBUILD_MODNAME, fw_name); ++ if (status) + return status; +- } + sprintf(fw_name, "%s_hdr-%d.fw", brcms_firmwares[i], + UCODE_LOADER_API_VER); + status = request_firmware(&wl->fw.fw_hdr[i], fw_name, device); +- if (status) { +- wiphy_err(wl->wiphy, "%s: fail to load firmware %s\n", +- KBUILD_MODNAME, fw_name); ++ if (status) + return status; +- } + wl->fw.hdr_num_entries[i] = + wl->fw.fw_hdr[i]->size / (sizeof(struct firmware_hdr)); + } +Index: linux/drivers/net/wireless/intel/ipw2x00/ipw2100.c +=================================================================== +--- linux.orig/drivers/net/wireless/intel/ipw2x00/ipw2100.c ++++ linux/drivers/net/wireless/intel/ipw2x00/ipw2100.c +@@ -8370,12 +8370,8 @@ static int ipw2100_get_firmware(struct i + + rc = request_firmware(&fw->fw_entry, fw_name, &priv->pci_dev->dev); + +- if (rc < 0) { +- printk(KERN_ERR DRV_NAME ": " +- "%s: Firmware '%s' not available or load failed.\n", +- priv->net_dev->name, fw_name); ++ if (rc) + return rc; +- } + IPW_DEBUG_INFO("firmware data %p size %zd\n", fw->fw_entry->data, + fw->fw_entry->size); + +Index: linux/drivers/net/wireless/intel/ipw2x00/ipw2200.c +=================================================================== +--- linux.orig/drivers/net/wireless/intel/ipw2x00/ipw2200.c ++++ linux/drivers/net/wireless/intel/ipw2x00/ipw2200.c +@@ -3393,10 +3393,8 @@ static int ipw_get_fw(struct ipw_priv *p + + /* ask firmware_class module to get the boot firmware off disk */ + rc = request_firmware(raw, name, &priv->pci_dev->dev); +- if (rc < 0) { +- IPW_ERROR("%s request_firmware failed: Reason %d\n", name, rc); ++ if (rc) + return rc; +- } + + if ((*raw)->size < sizeof(*fw)) { + IPW_ERROR("%s is too small (%zd)\n", name, (*raw)->size); +Index: linux/drivers/net/wireless/intel/iwlegacy/3945-mac.c +=================================================================== +--- linux.orig/drivers/net/wireless/intel/iwlegacy/3945-mac.c ++++ linux/drivers/net/wireless/intel/iwlegacy/3945-mac.c +@@ -1835,7 +1835,6 @@ il3945_read_ucode(struct il_priv *il) + sprintf(buf, "%s%u%s", name_pre, idx, ".ucode"); + ret = request_firmware(&ucode_raw, buf, &il->pci_dev->dev); + if (ret < 0) { +- IL_ERR("%s firmware file req failed: %d\n", buf, ret); + if (ret == -ENOENT) + continue; + else +Index: linux/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +=================================================================== +--- linux.orig/drivers/net/wireless/intel/iwlwifi/iwl-drv.c ++++ linux/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +@@ -183,8 +183,6 @@ static int iwl_request_firmware(struct i + } + + if (drv->fw_index < cfg->ucode_api_min) { +- IWL_ERR(drv, "no suitable firmware found!\n"); +- + if (cfg->ucode_api_min == cfg->ucode_api_max) { + IWL_ERR(drv, "%s%d is required\n", cfg->fw_name_pre, + cfg->ucode_api_max); +Index: linux/drivers/net/wireless/intersil/orinoco/fw.c +=================================================================== +--- linux.orig/drivers/net/wireless/intersil/orinoco/fw.c ++++ linux/drivers/net/wireless/intersil/orinoco/fw.c +@@ -132,7 +132,6 @@ orinoco_dl_firmware(struct orinoco_priva + err = request_firmware(&fw_entry, firmware, priv->dev); + + if (err) { +- dev_err(dev, "Cannot find firmware %s\n", firmware); + err = -ENOENT; + goto free; + } +@@ -292,10 +291,8 @@ symbol_dl_firmware(struct orinoco_privat + const struct firmware *fw_entry; + + if (!orinoco_cached_fw_get(priv, true)) { +- if (request_firmware(&fw_entry, fw->pri_fw, priv->dev) != 0) { +- dev_err(dev, "Cannot find firmware: %s\n", fw->pri_fw); ++ if (request_firmware(&fw_entry, fw->pri_fw, priv->dev) != 0) + return -ENOENT; +- } + } else + fw_entry = orinoco_cached_fw_get(priv, true); + +@@ -311,10 +308,8 @@ symbol_dl_firmware(struct orinoco_privat + } + + if (!orinoco_cached_fw_get(priv, false)) { +- if (request_firmware(&fw_entry, fw->sta_fw, priv->dev) != 0) { +- dev_err(dev, "Cannot find firmware: %s\n", fw->sta_fw); ++ if (request_firmware(&fw_entry, fw->sta_fw, priv->dev) != 0) + return -ENOENT; +- } + } else + fw_entry = orinoco_cached_fw_get(priv, false); + +Index: linux/drivers/net/wireless/intersil/orinoco/orinoco_usb.c +=================================================================== +--- linux.orig/drivers/net/wireless/intersil/orinoco/orinoco_usb.c ++++ linux/drivers/net/wireless/intersil/orinoco/orinoco_usb.c +@@ -1708,7 +1708,6 @@ static int ezusb_probe(struct usb_interf + if (ezusb_firmware_download(upriv, &firmware) < 0) + goto error; + } else { +- err("No firmware to download"); + goto error; + } + +Index: linux/drivers/net/wireless/intersil/p54/p54pci.c +=================================================================== +--- linux.orig/drivers/net/wireless/intersil/p54/p54pci.c ++++ linux/drivers/net/wireless/intersil/p54/p54pci.c +@@ -502,7 +502,6 @@ static void p54p_firmware_step2(const st + int err; + + if (!fw) { +- dev_err(&pdev->dev, "Cannot find firmware (isl3886pci)\n"); + err = -ENOENT; + goto out; + } +Index: linux/drivers/net/wireless/intersil/p54/p54spi.c +=================================================================== +--- linux.orig/drivers/net/wireless/intersil/p54/p54spi.c ++++ linux/drivers/net/wireless/intersil/p54/p54spi.c +@@ -157,10 +157,8 @@ static int p54spi_request_firmware(struc + /* FIXME: should driver use it's own struct device? */ + ret = request_firmware(&priv->firmware, "3826.arm", &priv->spi->dev); + +- if (ret < 0) { +- dev_err(&priv->spi->dev, "request_firmware() failed: %d", ret); ++ if (ret) + return ret; +- } + + ret = p54_parse_firmware(dev, priv->firmware); + if (ret) { +Index: linux/drivers/net/wireless/intersil/p54/p54usb.c +=================================================================== +--- linux.orig/drivers/net/wireless/intersil/p54/p54usb.c ++++ linux/drivers/net/wireless/intersil/p54/p54usb.c +@@ -929,7 +929,6 @@ static void p54u_load_firmware_cb(const + err = p54u_start_ops(priv); + } else { + err = -ENOENT; +- dev_err(&udev->dev, "Firmware not found.\n"); + } + + complete(&priv->fw_wait_load); +Index: linux/drivers/net/wireless/marvell/libertas_tf/if_usb.c +=================================================================== +--- linux.orig/drivers/net/wireless/marvell/libertas_tf/if_usb.c ++++ linux/drivers/net/wireless/marvell/libertas_tf/if_usb.c +@@ -820,8 +820,6 @@ static int if_usb_prog_firmware(struct l + kernel_param_lock(THIS_MODULE); + ret = request_firmware(&cardp->fw, lbtf_fw_name, &cardp->udev->dev); + if (ret < 0) { +- pr_err("request_firmware() failed with %#x\n", ret); +- pr_err("firmware %s not found\n", lbtf_fw_name); + kernel_param_unlock(THIS_MODULE); + goto done; + } +Index: linux/drivers/net/wireless/marvell/mwifiex/main.c +=================================================================== +--- linux.orig/drivers/net/wireless/marvell/mwifiex/main.c ++++ linux/drivers/net/wireless/marvell/mwifiex/main.c +@@ -549,11 +549,8 @@ static int _mwifiex_fw_dpc(const struct + struct wireless_dev *wdev; + struct completion *fw_done = adapter->fw_done; + +- if (!firmware) { +- mwifiex_dbg(adapter, ERROR, +- "Failed to get firmware %s\n", adapter->fw_name); ++ if (!firmware) + goto err_dnld_fw; +- } + + memset(&fw, 0, sizeof(struct mwifiex_fw_image)); + adapter->firmware = firmware; +Index: linux/drivers/net/wireless/marvell/mwl8k.c +=================================================================== +--- linux.orig/drivers/net/wireless/marvell/mwl8k.c ++++ linux/drivers/net/wireless/marvell/mwl8k.c +@@ -5735,16 +5735,12 @@ static int mwl8k_firmware_load_success(s + static void mwl8k_fw_state_machine(const struct firmware *fw, void *context) + { + struct mwl8k_priv *priv = context; +- struct mwl8k_device_info *di = priv->device_info; + int rc; + + switch (priv->fw_state) { + case FW_STATE_INIT: +- if (!fw) { +- printk(KERN_ERR "%s: Error requesting helper fw %s\n", +- pci_name(priv->pdev), di->helper_image); ++ if (!fw) + goto fail; +- } + priv->fw_helper = fw; + rc = mwl8k_request_fw(priv, priv->fw_pref, &priv->fw_ucode, + true); +@@ -5779,11 +5775,8 @@ static void mwl8k_fw_state_machine(const + break; + + case FW_STATE_LOADING_ALT: +- if (!fw) { +- printk(KERN_ERR "%s: Error requesting alt fw %s\n", +- pci_name(priv->pdev), di->helper_image); ++ if (!fw) + goto fail; +- } + priv->fw_ucode = fw; + rc = mwl8k_firmware_load_success(priv); + if (rc) +@@ -5821,10 +5814,8 @@ retry: + + /* Ask userland hotplug daemon for the device firmware */ + rc = mwl8k_request_firmware(priv, fw_image, nowait); +- if (rc) { +- wiphy_err(hw->wiphy, "Firmware files not found\n"); ++ if (rc) + return rc; +- } + + if (nowait) + return rc; +Index: linux/drivers/net/wireless/ralink/rt2x00/rt2x00firmware.c +=================================================================== +--- linux.orig/drivers/net/wireless/ralink/rt2x00/rt2x00firmware.c ++++ linux/drivers/net/wireless/ralink/rt2x00/rt2x00firmware.c +@@ -38,10 +38,8 @@ static int rt2x00lib_request_firmware(st + rt2x00_info(rt2x00dev, "Loading firmware file '%s'\n", fw_name); + + retval = request_firmware(&fw, fw_name, device); +- if (retval) { +- rt2x00_err(rt2x00dev, "Failed to request Firmware\n"); ++ if (retval) + return retval; +- } + + if (!fw || !fw->size || !fw->data) { + rt2x00_err(rt2x00dev, "Failed to read Firmware\n"); +Index: linux/drivers/net/wireless/realtek/rtlwifi/core.c +=================================================================== +--- linux.orig/drivers/net/wireless/realtek/rtlwifi/core.c ++++ linux/drivers/net/wireless/realtek/rtlwifi/core.c +@@ -88,7 +88,6 @@ static void rtl_fw_do_work(const struct + if (!err) + goto found_alt; + } +- pr_err("Selected firmware is not available\n"); + rtlpriv->max_fw_size = 0; + goto exit; + } +Index: linux/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c +=================================================================== +--- linux.orig/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c ++++ linux/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c +@@ -63,13 +63,11 @@ static void rtl92se_fw_cb(const struct f + struct ieee80211_hw *hw = context; + struct rtl_priv *rtlpriv = rtl_priv(hw); + struct rt_firmware *pfirmware = NULL; +- char *fw_name = "rtlwifi/rtl8192sefw.bin"; + + rtl_dbg(rtlpriv, COMP_ERR, DBG_LOUD, + "Firmware callback routine entered!\n"); + complete(&rtlpriv->firmware_loading_complete); + if (!firmware) { +- pr_err("Firmware %s not available\n", fw_name); + rtlpriv->max_fw_size = 0; + return; + } +Index: linux/drivers/net/wireless/ti/wl1251/main.c +=================================================================== +--- linux.orig/drivers/net/wireless/ti/wl1251/main.c ++++ linux/drivers/net/wireless/ti/wl1251/main.c +@@ -57,10 +57,8 @@ static int wl1251_fetch_firmware(struct + + ret = request_firmware(&fw, WL1251_FW_NAME, dev); + +- if (ret < 0) { +- wl1251_error("could not get firmware: %d", ret); ++ if (ret) + return ret; +- } + + if (fw->size % 4) { + wl1251_error("firmware size is not multiple of 32 bits: %zu", +@@ -96,10 +94,8 @@ static int wl1251_fetch_nvs(struct wl125 + + ret = request_firmware(&fw, WL1251_NVS_NAME, dev); + +- if (ret < 0) { +- wl1251_error("could not get nvs file: %d", ret); ++ if (ret) + return ret; +- } + + if (fw->size % 4) { + wl1251_error("nvs size is not multiple of 32 bits: %zu", +Index: linux/drivers/net/wireless/ti/wlcore/main.c +=================================================================== +--- linux.orig/drivers/net/wireless/ti/wlcore/main.c ++++ linux/drivers/net/wireless/ti/wlcore/main.c +@@ -756,10 +756,8 @@ static int wl12xx_fetch_firmware(struct + + ret = request_firmware(&fw, fw_name, wl->dev); + +- if (ret < 0) { +- wl1271_error("could not get firmware %s: %d", fw_name, ret); ++ if (ret) + return ret; +- } + + if (fw->size % 4) { + wl1271_error("firmware size is not multiple of 32 bits: %zu", +Index: linux/drivers/net/wireless/zydas/zd1201.c +=================================================================== +--- linux.orig/drivers/net/wireless/zydas/zd1201.c ++++ linux/drivers/net/wireless/zydas/zd1201.c +@@ -62,8 +62,6 @@ static int zd1201_fw_upload(struct usb_d + + err = request_firmware(&fw_entry, fwfile, &dev->dev); + if (err) { +- dev_err(&dev->dev, "Failed to load %s firmware file!\n", fwfile); +- dev_err(&dev->dev, "Make sure the hotplug firmware loader is installed.\n"); + dev_err(&dev->dev, "Goto http://linux-lc100020.sourceforge.net for more info.\n"); + return err; + } +Index: linux/drivers/net/wireless/zydas/zd1211rw/zd_usb.c +=================================================================== +--- linux.orig/drivers/net/wireless/zydas/zd1211rw/zd_usb.c ++++ linux/drivers/net/wireless/zydas/zd1211rw/zd_usb.c +@@ -107,16 +107,9 @@ static void int_urb_complete(struct urb + static int request_fw_file( + const struct firmware **fw, const char *name, struct device *device) + { +- int r; +- + dev_dbg_f(device, "fw name %s\n", name); + +- r = request_firmware(fw, name, device); +- if (r) +- dev_err(device, +- "Could not load firmware file %s. Error number %d\n", +- name, r); +- return r; ++ return request_firmware(fw, name, device); + } + + static inline u16 get_bcdDevice(const struct usb_device *udev) +Index: linux/drivers/scsi/advansys.c +=================================================================== +--- linux.orig/drivers/scsi/advansys.c ++++ linux/drivers/scsi/advansys.c +@@ -4054,8 +4054,6 @@ static int AscInitAsc1000Driver(ASC_DVC_ + + err = request_firmware(&fw, fwname, asc_dvc->drv_ptr->dev); + if (err) { +- printk(KERN_ERR "Failed to load image \"%s\" err %d\n", +- fwname, err); + asc_dvc->err_code |= ASC_IERR_MCODE_CHKSUM; + return err; + } +@@ -4420,8 +4418,6 @@ static int AdvInitAsc3550Driver(ADV_DVC_ + + err = request_firmware(&fw, fwname, asc_dvc->drv_ptr->dev); + if (err) { +- printk(KERN_ERR "Failed to load image \"%s\" err %d\n", +- fwname, err); + asc_dvc->err_code = ASC_IERR_MCODE_CHKSUM; + return err; + } +@@ -4920,8 +4916,6 @@ static int AdvInitAsc38C0800Driver(ADV_D + + err = request_firmware(&fw, fwname, asc_dvc->drv_ptr->dev); + if (err) { +- printk(KERN_ERR "Failed to load image \"%s\" err %d\n", +- fwname, err); + asc_dvc->err_code = ASC_IERR_MCODE_CHKSUM; + return err; + } +@@ -5408,8 +5402,6 @@ static int AdvInitAsc38C1600Driver(ADV_D + + err = request_firmware(&fw, fwname, asc_dvc->drv_ptr->dev); + if (err) { +- printk(KERN_ERR "Failed to load image \"%s\" err %d\n", +- fwname, err); + asc_dvc->err_code = ASC_IERR_MCODE_CHKSUM; + return err; + } +Index: linux/drivers/scsi/aic94xx/aic94xx_init.c +=================================================================== +--- linux.orig/drivers/scsi/aic94xx/aic94xx_init.c ++++ linux/drivers/scsi/aic94xx/aic94xx_init.c +@@ -370,8 +370,6 @@ static ssize_t asd_store_update_bios(str + filename_ptr, + &asd_ha->pcidev->dev); + if (err) { +- asd_printk("Failed to load bios image file %s, error %d\n", +- filename_ptr, err); + err = FAIL_OPEN_BIOS_FILE; + goto out1; + } +Index: linux/drivers/scsi/aic94xx/aic94xx_seq.c +=================================================================== +--- linux.orig/drivers/scsi/aic94xx/aic94xx_seq.c ++++ linux/drivers/scsi/aic94xx/aic94xx_seq.c +@@ -1302,11 +1302,8 @@ int asd_init_seqs(struct asd_ha_struct * + + err = asd_request_firmware(asd_ha); + +- if (err) { +- asd_printk("Failed to load sequencer firmware file %s, error %d\n", +- SAS_RAZOR_SEQUENCER_FW_FILE, err); ++ if (err) + return err; +- } + + err = asd_seq_download_seqs(asd_ha); + if (err) { +Index: linux/drivers/scsi/bfa/bfad.c +=================================================================== +--- linux.orig/drivers/scsi/bfa/bfad.c ++++ linux/drivers/scsi/bfa/bfad.c +@@ -1743,7 +1743,6 @@ bfad_read_firmware(struct pci_dev *pdev, + const struct firmware *fw; + + if (request_firmware(&fw, fw_name, &pdev->dev)) { +- printk(KERN_ALERT "Can't locate firmware %s\n", fw_name); + *bfi_image = NULL; + goto out; + } +Index: linux/drivers/scsi/ipr.c +=================================================================== +--- linux.orig/drivers/scsi/ipr.c ++++ linux/drivers/scsi/ipr.c +@@ -4102,10 +4102,8 @@ static ssize_t ipr_store_update_fw(struc + if (endline) + *endline = '\0'; + +- if (request_firmware(&fw_entry, fname, &ioa_cfg->pdev->dev)) { +- dev_err(&ioa_cfg->pdev->dev, "Firmware file %s not found\n", fname); ++ if (request_firmware(&fw_entry, fname, &ioa_cfg->pdev->dev)) + return -EIO; +- } + + image_hdr = (struct ipr_ucode_image_header *)fw_entry->data; + +Index: linux/drivers/scsi/pm8001/pm8001_ctl.c +=================================================================== +--- linux.orig/drivers/scsi/pm8001/pm8001_ctl.c ++++ linux/drivers/scsi/pm8001/pm8001_ctl.c +@@ -846,9 +846,6 @@ static ssize_t pm8001_store_update_fw(st + pm8001_ha->dev); + + if (ret) { +- pm8001_dbg(pm8001_ha, FAIL, +- "Failed to load firmware image file %s, error %d\n", +- filename_ptr, ret); + pm8001_ha->fw_status = FAIL_OPEN_BIOS_FILE; + goto out; + } +Index: linux/drivers/scsi/qla1280.c +=================================================================== +--- linux.orig/drivers/scsi/qla1280.c ++++ linux/drivers/scsi/qla1280.c +@@ -1504,8 +1504,6 @@ qla1280_request_firmware(struct scsi_qla + err = request_firmware(&fw, fwname, &ha->pdev->dev); + + if (err) { +- printk(KERN_ERR "Failed to load image \"%s\" err %d\n", +- fwname, err); + fw = ERR_PTR(err); + goto unlock; + } +Index: linux/drivers/scsi/qla2xxx/qla_init.c +=================================================================== +--- linux.orig/drivers/scsi/qla2xxx/qla_init.c ++++ linux/drivers/scsi/qla2xxx/qla_init.c +@@ -8316,10 +8316,6 @@ qla2x00_load_risc(scsi_qla_host_t *vha, + /* Load firmware blob. */ + blob = qla2x00_request_firmware(vha); + if (!blob) { +- ql_log(ql_log_info, vha, 0x0083, +- "Firmware image unavailable.\n"); +- ql_log(ql_log_info, vha, 0x0084, +- "Firmware images can be retrieved from: "QLA_FW_URL ".\n"); + return QLA_FUNCTION_FAILED; + } + +@@ -8422,9 +8418,6 @@ qla24xx_load_risc_blob(scsi_qla_host_t * + + blob = qla2x00_request_firmware(vha); + if (!blob) { +- ql_log(ql_log_warn, vha, 0x0092, +- "-> Firmware file not found.\n"); +- + return QLA_FUNCTION_FAILED; + } + +Index: linux/drivers/scsi/qla2xxx/qla_nx.c +=================================================================== +--- linux.orig/drivers/scsi/qla2xxx/qla_nx.c ++++ linux/drivers/scsi/qla2xxx/qla_nx.c +@@ -2427,11 +2427,8 @@ try_blob_fw: + + /* Load firmware blob. */ + blob = ha->hablob = qla2x00_request_firmware(vha); +- if (!blob) { +- ql_log(ql_log_fatal, vha, 0x00a3, +- "Firmware image not present.\n"); ++ if (!blob) + goto fw_load_failed; +- } + + /* Validating firmware blob */ + if (qla82xx_validate_firmware_blob(vha, +Index: linux/drivers/scsi/qla2xxx/qla_os.c +=================================================================== +--- linux.orig/drivers/scsi/qla2xxx/qla_os.c ++++ linux/drivers/scsi/qla2xxx/qla_os.c +@@ -7651,8 +7651,6 @@ qla2x00_request_firmware(scsi_qla_host_t + goto out; + + if (request_firmware(&blob->fw, blob->name, &ha->pdev->dev)) { +- ql_log(ql_log_warn, vha, 0x0063, +- "Failed to load firmware image (%s).\n", blob->name); + blob->fw = NULL; + blob = NULL; + } +Index: linux/drivers/scsi/qlogicpti.c +=================================================================== +--- linux.orig/drivers/scsi/qlogicpti.c ++++ linux/drivers/scsi/qlogicpti.c +@@ -486,11 +486,8 @@ static int qlogicpti_load_firmware(struc + int i, timeout; + + err = request_firmware(&fw, fwname, &qpti->op->dev); +- if (err) { +- printk(KERN_ERR "Failed to load image \"%s\" err %d\n", +- fwname, err); ++ if (err) + return err; +- } + if (fw->size % 2) { + printk(KERN_ERR "Bogus length %zu in image \"%s\"\n", + fw->size, fwname); +Index: linux/drivers/staging/rtl8192u/r819xU_firmware.c +=================================================================== +--- linux.orig/drivers/staging/rtl8192u/r819xU_firmware.c ++++ linux/drivers/staging/rtl8192u/r819xU_firmware.c +@@ -240,10 +240,8 @@ bool init_firmware(struct net_device *de + */ + if (rst_opt == OPT_SYSTEM_RESET) { + rc = request_firmware(&fw_entry, fw_name[init_step], &priv->udev->dev); +- if (rc < 0) { +- RT_TRACE(COMP_ERR, "request firmware fail!\n"); ++ if (rc) + goto download_firmware_fail; +- } + + if (fw_entry->size > sizeof(pfirmware->firmware_buf)) { + RT_TRACE(COMP_ERR, "img file size exceed the container buffer fail!\n"); +Index: linux/drivers/staging/rtl8712/hal_init.c +=================================================================== +--- linux.orig/drivers/staging/rtl8712/hal_init.c ++++ linux/drivers/staging/rtl8712/hal_init.c +@@ -72,8 +72,6 @@ int rtl871x_load_fw(struct _adapter *pad + dev_info(dev, "r8712u: Loading firmware from \"%s\"\n", firmware_file); + rc = request_firmware_nowait(THIS_MODULE, 1, firmware_file, dev, + GFP_KERNEL, padapter, rtl871x_load_fw_cb); +- if (rc) +- dev_err(dev, "r8712u: Firmware request error %d\n", rc); + return rc; + } + MODULE_FIRMWARE("rtlwifi/rtl8712u.bin"); +Index: linux/drivers/staging/vt6656/main_usb.c +=================================================================== +--- linux.orig/drivers/staging/vt6656/main_usb.c ++++ linux/drivers/staging/vt6656/main_usb.c +@@ -107,11 +107,8 @@ static int vnt_download_firmware(struct + dev_dbg(dev, "---->Download firmware\n"); + + ret = request_firmware(&fw, FIRMWARE_NAME, dev); +- if (ret) { +- dev_err(dev, "firmware file %s request failed (%d)\n", +- FIRMWARE_NAME, ret); ++ if (ret) + goto end; +- } + + for (ii = 0; ii < fw->size; ii += FIRMWARE_CHUNK_SIZE) { + length = min_t(int, fw->size - ii, FIRMWARE_CHUNK_SIZE); +Index: linux/drivers/tty/moxa.c +=================================================================== +--- linux.orig/drivers/tty/moxa.c ++++ linux/drivers/tty/moxa.c +@@ -1154,13 +1154,8 @@ static int moxa_init_board(struct moxa_b + } + + ret = request_firmware(&fw, file, dev); +- if (ret) { +- printk(KERN_ERR "MOXA: request_firmware failed. Make sure " +- "you've placed '%s' file into your firmware " +- "loader directory (e.g. /lib/firmware)\n", +- file); ++ if (ret) + goto err_free; +- } + + ret = moxa_load_fw(brd, fw); + +Index: linux/drivers/tty/serial/icom.c +=================================================================== +--- linux.orig/drivers/tty/serial/icom.c ++++ linux/drivers/tty/serial/icom.c +@@ -621,7 +621,6 @@ static void load_code(struct icom_port * + + /* Load Call Setup into Adapter */ + if (request_firmware(&fw, "icom_call_setup.bin", &dev->dev) < 0) { +- dev_err(&dev->dev,"Unable to load icom_call_setup.bin firmware image\n"); + status = -1; + goto load_code_exit; + } +@@ -641,7 +640,6 @@ static void load_code(struct icom_port * + + /* Load Resident DCE portion of Adapter */ + if (request_firmware(&fw, "icom_res_dce.bin", &dev->dev) < 0) { +- dev_err(&dev->dev,"Unable to load icom_res_dce.bin firmware image\n"); + status = -1; + goto load_code_exit; + } +@@ -686,7 +684,6 @@ static void load_code(struct icom_port * + } + + if (request_firmware(&fw, "icom_asc.bin", &dev->dev) < 0) { +- dev_err(&dev->dev,"Unable to load icom_asc.bin firmware image\n"); + status = -1; + goto load_code_exit; + } +Index: linux/drivers/tty/serial/ucc_uart.c +=================================================================== +--- linux.orig/drivers/tty/serial/ucc_uart.c ++++ linux/drivers/tty/serial/ucc_uart.c +@@ -1151,10 +1151,8 @@ static void uart_firmware_cont(const str + struct device *dev = context; + int ret; + +- if (!fw) { +- dev_err(dev, "firmware not found\n"); ++ if (!fw) + return; +- } + + firmware = (struct qe_firmware *) fw->data; + +Index: linux/drivers/usb/atm/cxacru.c +=================================================================== +--- linux.orig/drivers/usb/atm/cxacru.c ++++ linux/drivers/usb/atm/cxacru.c +@@ -1084,8 +1084,6 @@ static int cxacru_find_firmware(struct c + return -ENOENT; + } + +- usb_info(usbatm, "found firmware %s\n", buf); +- + return 0; + } + +Index: linux/drivers/usb/atm/ueagle-atm.c +=================================================================== +--- linux.orig/drivers/usb/atm/ueagle-atm.c ++++ linux/drivers/usb/atm/ueagle-atm.c +@@ -606,10 +606,8 @@ static void uea_upload_pre_firmware(cons + int ret, size; + + uea_enters(usb); +- if (!fw_entry) { +- uea_err(usb, "firmware is not available\n"); ++ if (!fw_entry) + goto err; +- } + + pfw = fw_entry->data; + size = fw_entry->size; +@@ -704,10 +702,6 @@ static int uea_load_firmware(struct usb_ + ret = request_firmware_nowait(THIS_MODULE, 1, fw_name, &usb->dev, + GFP_KERNEL, usb, + uea_upload_pre_firmware); +- if (ret) +- uea_err(usb, "firmware %s is not available\n", fw_name); +- else +- uea_info(usb, "loading firmware %s\n", fw_name); + + uea_leaves(usb); + return ret; +@@ -869,12 +863,8 @@ static int request_dsp(struct uea_softc + } + + ret = request_firmware(&sc->dsp_firm, dsp_name, &sc->usb_dev->dev); +- if (ret < 0) { +- uea_err(INS_TO_USBDEV(sc), +- "requesting firmware %s failed with error %d\n", +- dsp_name, ret); ++ if (ret) + return ret; +- } + + if (UEA_CHIP_VERSION(sc) == EAGLE_IV) + ret = check_dsp_e4(sc->dsp_firm->data, sc->dsp_firm->size); +@@ -1587,12 +1577,8 @@ static int request_cmvs_old(struct uea_s + + cmvs_file_name(sc, cmv_name, 1); + ret = request_firmware(fw, cmv_name, &sc->usb_dev->dev); +- if (ret < 0) { +- uea_err(INS_TO_USBDEV(sc), +- "requesting firmware %s failed with error %d\n", +- cmv_name, ret); ++ if (ret) + return ret; +- } + + data = (u8 *) (*fw)->data; + size = (*fw)->size; +@@ -1629,9 +1615,6 @@ static int request_cmvs(struct uea_softc + "try to get older cmvs\n", cmv_name); + return request_cmvs_old(sc, cmvs, fw); + } +- uea_err(INS_TO_USBDEV(sc), +- "requesting firmware %s failed with error %d\n", +- cmv_name, ret); + return ret; + } + +@@ -1914,11 +1897,8 @@ static int load_XILINX_firmware(struct u + uea_enters(INS_TO_USBDEV(sc)); + + ret = request_firmware(&fw_entry, fw_name, &sc->usb_dev->dev); +- if (ret) { +- uea_err(INS_TO_USBDEV(sc), "firmware %s is not available\n", +- fw_name); ++ if (ret) + goto err0; +- } + + pfw = fw_entry->data; + size = fw_entry->size; +Index: linux/drivers/usb/misc/emi26.c +=================================================================== +--- linux.orig/drivers/usb/misc/emi26.c ++++ linux/drivers/usb/misc/emi26.c +@@ -85,21 +85,17 @@ static int emi26_load_firmware (struct u + + err = request_ihex_firmware(&loader_fw, "emi26/loader.fw", &dev->dev); + if (err) +- goto nofw; ++ goto wraperr; + + err = request_ihex_firmware(&bitstream_fw, "emi26/bitstream.fw", + &dev->dev); + if (err) +- goto nofw; ++ goto wraperr; + + err = request_ihex_firmware(&firmware_fw, "emi26/firmware.fw", + &dev->dev); +- if (err) { +- nofw: +- dev_err(&dev->dev, "%s - request_firmware() failed\n", +- __func__); ++ if (err) + goto wraperr; +- } + + /* Assert reset (stop the CPU in the EMI) */ + err = emi26_set_reset(dev,1); +Index: linux/drivers/usb/misc/ezusb.c +=================================================================== +--- linux.orig/drivers/usb/misc/ezusb.c ++++ linux/drivers/usb/misc/ezusb.c +@@ -64,12 +64,8 @@ static int ezusb_ihex_firmware_download( + const struct ihex_binrec *record; + + if (request_ihex_firmware(&firmware, firmware_path, +- &dev->dev)) { +- dev_err(&dev->dev, +- "%s - request \"%s\" failed\n", +- __func__, firmware_path); ++ &dev->dev)) + goto out; +- } + + ret = ezusb_set_reset(dev, fx.cpucs_reg, 0); + if (ret < 0) +Index: linux/drivers/usb/misc/isight_firmware.c +=================================================================== +--- linux.orig/drivers/usb/misc/isight_firmware.c ++++ linux/drivers/usb/misc/isight_firmware.c +@@ -45,7 +45,6 @@ static int isight_firmware_load(struct u + return -ENOMEM; + + if (request_firmware(&firmware, "isight.fw", &dev->dev) != 0) { +- printk(KERN_ERR "Unable to load isight firmware\n"); + ret = -ENODEV; + goto out; + } +Index: linux/drivers/usb/serial/io_edgeport.c +=================================================================== +--- linux.orig/drivers/usb/serial/io_edgeport.c ++++ linux/drivers/usb/serial/io_edgeport.c +@@ -332,11 +332,8 @@ static void update_edgeport_E2PROM(struc + + response = request_ihex_firmware(&fw, fw_name, + &edge_serial->serial->dev->dev); +- if (response) { +- dev_err(dev, "Failed to load image \"%s\" err %d\n", +- fw_name, response); ++ if (response) + return; +- } + + rec = (const struct ihex_binrec *)fw->data; + BootMajorVersion = rec->data[0]; +Index: linux/drivers/usb/serial/io_ti.c +=================================================================== +--- linux.orig/drivers/usb/serial/io_ti.c ++++ linux/drivers/usb/serial/io_ti.c +@@ -1009,8 +1009,6 @@ static int download_fw(struct edgeport_s + + status = request_firmware(&fw, fw_name, dev); + if (status) { +- dev_err(dev, "Failed to load image \"%s\" err %d\n", +- fw_name, status); + return status; + } + +Index: linux/drivers/usb/serial/ti_usb_3410_5052.c +=================================================================== +--- linux.orig/drivers/usb/serial/ti_usb_3410_5052.c ++++ linux/drivers/usb/serial/ti_usb_3410_5052.c +@@ -1631,10 +1631,8 @@ static int ti_download_firmware(struct t + } + + check_firmware: +- if (status) { +- dev_err(&dev->dev, "%s - firmware not found\n", __func__); ++ if (status) + return -ENOENT; +- } + if (fw_p->size > TI_FIRMWARE_BUF_SIZE) { + dev_err(&dev->dev, "%s - firmware too large %zu\n", __func__, fw_p->size); + release_firmware(fw_p); +Index: linux/drivers/video/fbdev/broadsheetfb.c +=================================================================== +--- linux.orig/drivers/video/fbdev/broadsheetfb.c ++++ linux/drivers/video/fbdev/broadsheetfb.c +@@ -743,10 +743,8 @@ static ssize_t broadsheet_loadstore_wave + return -EINVAL; + + err = request_firmware(&fw_entry, "broadsheet.wbf", dev); +- if (err < 0) { +- dev_err(dev, "Failed to get broadsheet waveform\n"); ++ if (err) + goto err_failed; +- } + + /* try to enforce reasonable min max on waveform */ + if ((fw_entry->size < 8*1024) || (fw_entry->size > 64*1024)) { +Index: linux/drivers/video/fbdev/metronomefb.c +=================================================================== +--- linux.orig/drivers/video/fbdev/metronomefb.c ++++ linux/drivers/video/fbdev/metronomefb.c +@@ -679,10 +679,8 @@ static int metronomefb_probe(struct plat + a) request the waveform file from userspace + b) process waveform and decode into metromem */ + retval = request_firmware(&fw_entry, "metronome.wbf", &dev->dev); +- if (retval < 0) { +- dev_err(&dev->dev, "Failed to get waveform\n"); ++ if (retval) + goto err_csum_table; +- } + + retval = load_waveform((u8 *) fw_entry->data, fw_entry->size, 3, 31, + par); +Index: linux/sound/drivers/vx/vx_hwdep.c +=================================================================== +--- linux.orig/sound/drivers/vx/vx_hwdep.c ++++ linux/sound/drivers/vx/vx_hwdep.c +@@ -58,10 +58,8 @@ int snd_vx_setup_firmware(struct vx_core + if (! fw_files[chip->type][i]) + continue; + sprintf(path, "vx/%s", fw_files[chip->type][i]); +- if (request_firmware(&fw, path, chip->dev)) { +- snd_printk(KERN_ERR "vx: can't load firmware %s\n", path); ++ if (request_firmware(&fw, path, chip->dev)) + return -ENOENT; +- } + err = chip->ops->load_dsp(chip, i, fw); + if (err < 0) { + release_firmware(fw); +Index: linux/sound/isa/msnd/msnd_pinnacle.c +=================================================================== +--- linux.orig/sound/isa/msnd/msnd_pinnacle.c ++++ linux/sound/isa/msnd/msnd_pinnacle.c +@@ -376,15 +376,11 @@ static int upload_dsp_code(struct snd_ca + outb(HPBLKSEL_0, chip->io + HP_BLKS); + + err = request_firmware(&init_fw, INITCODEFILE, card->dev); +- if (err < 0) { +- printk(KERN_ERR LOGNAME ": Error loading " INITCODEFILE); ++ if (err) + goto cleanup1; +- } + err = request_firmware(&perm_fw, PERMCODEFILE, card->dev); +- if (err < 0) { +- printk(KERN_ERR LOGNAME ": Error loading " PERMCODEFILE); ++ if (err) + goto cleanup; +- } + + memcpy_toio(chip->mappedbase, perm_fw->data, perm_fw->size); + if (snd_msnd_upload_host(chip, init_fw->data, init_fw->size) < 0) { +Index: linux/sound/isa/sscape.c +=================================================================== +--- linux.orig/sound/isa/sscape.c ++++ linux/sound/isa/sscape.c +@@ -520,10 +520,8 @@ static int sscape_upload_bootblock(struc + int ret; + + ret = request_firmware(&init_fw, "scope.cod", card->dev); +- if (ret < 0) { +- snd_printk(KERN_ERR "sscape: Error loading scope.cod"); ++ if (ret) + return ret; +- } + ret = upload_dma_data(sscape, init_fw->data, init_fw->size); + + release_firmware(init_fw); +@@ -560,11 +558,8 @@ static int sscape_upload_microcode(struc + snprintf(name, sizeof(name), "sndscape.co%d", version); + + err = request_firmware(&init_fw, name, card->dev); +- if (err < 0) { +- snd_printk(KERN_ERR "sscape: Error loading sndscape.co%d", +- version); ++ if (err) + return err; +- } + err = upload_dma_data(sscape, init_fw->data, init_fw->size); + if (err == 0) + snd_printk(KERN_INFO "sscape: MIDI firmware loaded %zu KBs\n", +Index: linux/sound/isa/wavefront/wavefront_synth.c +=================================================================== +--- linux.orig/sound/isa/wavefront/wavefront_synth.c ++++ linux/sound/isa/wavefront/wavefront_synth.c +@@ -1970,10 +1970,8 @@ wavefront_download_firmware (snd_wavefro + const struct firmware *firmware; + + err = request_firmware(&firmware, path, dev->card->dev); +- if (err < 0) { +- snd_printk(KERN_ERR "firmware (%s) download failed!!!\n", path); ++ if (err) + return 1; +- } + + len = 0; + buf = firmware->data; +Index: linux/sound/pci/asihpi/hpidspcd.c +=================================================================== +--- linux.orig/sound/pci/asihpi/hpidspcd.c ++++ linux/sound/pci/asihpi/hpidspcd.c +@@ -35,8 +35,6 @@ short hpi_dsp_code_open(u32 adapter, voi + err = request_firmware(&firmware, fw_name, &dev->dev); + + if (err || !firmware) { +- dev_err(&dev->dev, "%d, request_firmware failed for %s\n", +- err, fw_name); + goto error1; + } + if (firmware->size < sizeof(header)) { +Index: linux/sound/pci/cs46xx/cs46xx_lib.c +=================================================================== +--- linux.orig/sound/pci/cs46xx/cs46xx_lib.c ++++ linux/sound/pci/cs46xx/cs46xx_lib.c +@@ -3199,11 +3199,8 @@ int snd_cs46xx_start_dsp(struct snd_cs46 + #ifdef CONFIG_SND_CS46XX_NEW_DSP + for (i = 0; i < CS46XX_DSP_MODULES; i++) { + err = load_firmware(chip, &chip->modules[i], module_names[i]); +- if (err < 0) { +- dev_err(chip->card->dev, "firmware load error [%s]\n", +- module_names[i]); ++ if (err < 0) + return err; +- } + err = cs46xx_dsp_load_module(chip, chip->modules[i]); + if (err < 0) { + dev_err(chip->card->dev, "image download error [%s]\n", +Index: linux/sound/pci/echoaudio/echoaudio.c +=================================================================== +--- linux.orig/sound/pci/echoaudio/echoaudio.c ++++ linux/sound/pci/echoaudio/echoaudio.c +@@ -48,11 +48,8 @@ static int get_firmware(const struct fir + "firmware requested: %s\n", card_fw[fw_index].data); + snprintf(name, sizeof(name), "ea/%s", card_fw[fw_index].data); + err = request_firmware(fw_entry, name, &chip->pci->dev); +- if (err < 0) +- dev_err(chip->card->dev, +- "get_firmware(): Firmware not available (%d)\n", err); + #ifdef CONFIG_PM_SLEEP +- else ++ if (!err) + chip->fw_cache[fw_index] = *fw_entry; + #endif + return err; +Index: linux/sound/pci/emu10k1/emu10k1_main.c +=================================================================== +--- linux.orig/sound/pci/emu10k1/emu10k1_main.c ++++ linux/sound/pci/emu10k1/emu10k1_main.c +@@ -873,10 +873,8 @@ static int snd_emu10k1_emu1010_init(stru + dev_info(emu->card->dev, "emu1010: EMU_HANA_ID = 0x%x\n", reg); + + err = snd_emu1010_load_firmware(emu, 0, &emu->firmware); +- if (err < 0) { +- dev_info(emu->card->dev, "emu1010: Loading Firmware failed\n"); ++ if (err < 0) + return err; +- } + + /* ID, should read & 0x7f = 0x55 when FPGA programmed. */ + snd_emu1010_fpga_read(emu, EMU_HANA_ID, ®); +Index: linux/sound/pci/hda/hda_intel.c +=================================================================== +--- linux.orig/sound/pci/hda/hda_intel.c ++++ linux/sound/pci/hda/hda_intel.c +@@ -2017,8 +2017,6 @@ static void azx_firmware_cb(const struct + + if (fw) + chip->fw = fw; +- else +- dev_err(card->dev, "Cannot load firmware, continue without patching\n"); + if (!chip->disabled) { + /* continue probing */ + azx_probe_continue(chip); +Index: linux/sound/pci/korg1212/korg1212.c +=================================================================== +--- linux.orig/sound/pci/korg1212/korg1212.c ++++ linux/sound/pci/korg1212/korg1212.c +@@ -2258,7 +2258,6 @@ static int snd_korg1212_create(struct sn + + err = request_firmware(&dsp_code, "korg/k1212.dsp", &pci->dev); + if (err < 0) { +- snd_printk(KERN_ERR "firmware not available\n"); + return err; + } + +Index: linux/sound/pci/mixart/mixart_hwdep.c +=================================================================== +--- linux.orig/sound/pci/mixart/mixart_hwdep.c ++++ linux/sound/pci/mixart/mixart_hwdep.c +@@ -566,11 +566,8 @@ int snd_mixart_setup_firmware(struct mix + + for (i = 0; i < 3; i++) { + sprintf(path, "mixart/%s", fw_files[i]); +- if (request_firmware(&fw_entry, path, &mgr->pci->dev)) { +- dev_err(&mgr->pci->dev, +- "miXart: can't load firmware %s\n", path); ++ if (request_firmware(&fw_entry, path, &mgr->pci->dev)) + return -ENOENT; +- } + /* fake hwdep dsp record */ + err = mixart_dsp_load(mgr, i, fw_entry); + release_firmware(fw_entry); +Index: linux/sound/pci/pcxhr/pcxhr_hwdep.c +=================================================================== +--- linux.orig/sound/pci/pcxhr/pcxhr_hwdep.c ++++ linux/sound/pci/pcxhr/pcxhr_hwdep.c +@@ -375,12 +375,8 @@ int pcxhr_setup_firmware(struct pcxhr_mg + if (!fw_files[fw_set][i]) + continue; + sprintf(path, "pcxhr/%s", fw_files[fw_set][i]); +- if (request_firmware(&fw_entry, path, &mgr->pci->dev)) { +- dev_err(&mgr->pci->dev, +- "pcxhr: can't load firmware %s\n", +- path); ++ if (request_firmware(&fw_entry, path, &mgr->pci->dev)) + return -ENOENT; +- } + /* fake hwdep dsp record */ + err = pcxhr_dsp_load(mgr, i, fw_entry); + release_firmware(fw_entry); +Index: linux/sound/pci/riptide/riptide.c +=================================================================== +--- linux.orig/sound/pci/riptide/riptide.c ++++ linux/sound/pci/riptide/riptide.c +@@ -1222,11 +1222,8 @@ static int try_to_load_firmware(struct c + if (!chip->fw_entry) { + err = request_firmware(&chip->fw_entry, "riptide.hex", + &chip->pci->dev); +- if (err) { +- snd_printk(KERN_ERR +- "Riptide: Firmware not available %d\n", err); ++ if (err) + return -EIO; +- } + } + err = loadfirmware(cif, chip->fw_entry->data, chip->fw_entry->size); + if (err) { +Index: linux/sound/pci/rme9652/hdsp.c +=================================================================== +--- linux.orig/sound/pci/rme9652/hdsp.c ++++ linux/sound/pci/rme9652/hdsp.c +@@ -5201,11 +5201,8 @@ static int hdsp_request_fw_loader(struct + return -EINVAL; + } + +- if (request_firmware(&fw, fwfile, &hdsp->pci->dev)) { +- dev_err(hdsp->card->dev, +- "cannot load firmware %s\n", fwfile); ++ if (request_firmware(&fw, fwfile, &hdsp->pci->dev)) + return -ENOENT; +- } + if (fw->size < HDSP_FIRMWARE_SIZE) { + dev_err(hdsp->card->dev, + "too short firmware size %d (expected %d)\n", +Index: linux/sound/soc/codecs/wm2000.c +=================================================================== +--- linux.orig/sound/soc/codecs/wm2000.c ++++ linux/sound/soc/codecs/wm2000.c +@@ -891,10 +891,8 @@ static int wm2000_i2c_probe(struct i2c_c + } + + ret = request_firmware(&fw, filename, &i2c->dev); +- if (ret != 0) { +- dev_err(&i2c->dev, "Failed to acquire ANC data: %d\n", ret); ++ if (ret != 0) + goto err_supplies; +- } + + /* Pre-cook the concatenation of the register address onto the image */ + wm2000->anc_download_size = fw->size + 2; +Index: linux/sound/usb/6fire/firmware.c +=================================================================== +--- linux.orig/sound/usb/6fire/firmware.c ++++ linux/sound/usb/6fire/firmware.c +@@ -203,8 +203,6 @@ static int usb6fire_fw_ezusb_upload( + ret = request_firmware(&fw, fwname, &device->dev); + if (ret < 0) { + kfree(rec); +- dev_err(&intf->dev, +- "error requesting ezusb firmware %s.\n", fwname); + return ret; + } + ret = usb6fire_fw_ihex_init(fw, rec); +@@ -280,8 +278,6 @@ static int usb6fire_fw_fpga_upload( + + ret = request_firmware(&fw, fwname, &device->dev); + if (ret < 0) { +- dev_err(&intf->dev, "unable to get fpga firmware %s.\n", +- fwname); + kfree(buffer); + return -EIO; + } diff --git a/debian/patches/bugfix/all/firmware_class-log-every-success-and-failure.patch b/debian/patches/bugfix/all/firmware_class-log-every-success-and-failure.patch new file mode 100644 index 000000000..092a74496 --- /dev/null +++ b/debian/patches/bugfix/all/firmware_class-log-every-success-and-failure.patch @@ -0,0 +1,83 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Subject: firmware_class: Log every success and failure against given device +Date: Sun, 09 Dec 2012 16:02:00 +0000 +Forwarded: no + +The hundreds of users of request_firmware() have nearly as many +different log formats for reporting failures. They also have only the +vaguest hint as to what went wrong; only firmware_class really knows +that. Therefore, add specific log messages for the failure modes that +aren't currently logged. + +In case of a driver that tries multiple names, this may result in the +impression that it failed to initialise. Therefore, also log successes. + +This makes many error messages in drivers redundant, which will be +removed in later patches. + +This does not cover the case where we fall back to a user-mode helper +(which is no longer enabled in Debian). + +NOTE: hw-detect will depend on the "firmware: failed to load %s (%d)\n" +format to detect missing firmware. +--- + drivers/base/firmware_loader/fallback.c | 2 +- + drivers/base/firmware_loader/main.c | 17 ++++++++--------- + 2 files changed, 9 insertions(+), 10 deletions(-) + +--- a/drivers/base/firmware_loader/fallback.c ++++ b/drivers/base/firmware_loader/fallback.c +@@ -558,7 +558,7 @@ static int fw_load_from_user_helper(stru + if (opt_flags & FW_OPT_NOWAIT) { + timeout = usermodehelper_read_lock_wait(timeout); + if (!timeout) { +- dev_dbg(device, "firmware: %s loading timed out\n", ++ dev_err(device, "firmware: %s loading timed out\n", + name); + return -EBUSY; + } +--- a/drivers/base/firmware_loader/main.c ++++ b/drivers/base/firmware_loader/main.c +@@ -535,18 +535,15 @@ fw_get_filesystem_firmware(struct device + file_size_ptr, + READING_FIRMWARE); + if (rc < 0) { +- if (rc != -ENOENT) +- dev_warn(device, "loading %s failed with error %d\n", +- path, rc); +- else +- dev_dbg(device, "loading %s failed for no such file or directory.\n", +- path); ++ dev_dbg(device, "loading %s failed with error %d\n", ++ path, rc); + continue; + } + size = rc; + rc = 0; + +- dev_dbg(device, "Loading firmware from %s\n", path); ++ dev_info(device, "firmware: direct-loading firmware %s\n", ++ fw_priv->fw_name); + if (decompress) { + dev_dbg(device, "f/w decompressing %s\n", + fw_priv->fw_name); +@@ -559,8 +556,6 @@ fw_get_filesystem_firmware(struct device + continue; + } + } else { +- dev_dbg(device, "direct-loading %s\n", +- fw_priv->fw_name); + if (!fw_priv->data) + fw_priv->data = buffer; + fw_priv->size = size; +@@ -570,6 +565,10 @@ fw_get_filesystem_firmware(struct device + } + __putname(path); + ++ if (rc) ++ dev_err(device, "firmware: failed to load %s (%d)\n", ++ fw_priv->fw_name, rc); ++ + return rc; + } + diff --git a/debian/patches/bugfix/all/fs-add-module_softdep-declarations-for-hard-coded-cr.patch b/debian/patches/bugfix/all/fs-add-module_softdep-declarations-for-hard-coded-cr.patch new file mode 100644 index 000000000..35dacbf59 --- /dev/null +++ b/debian/patches/bugfix/all/fs-add-module_softdep-declarations-for-hard-coded-cr.patch @@ -0,0 +1,61 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Wed, 13 Apr 2016 21:48:06 +0100 +Subject: fs: Add MODULE_SOFTDEP declarations for hard-coded crypto drivers +Bug-Debian: https://bugs.debian.org/819725 +Forwarded: http://mid.gmane.org/20160517133631.GF7555@decadent.org.uk + +This helps initramfs builders and other tools to find the full +dependencies of a module. + +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +[Lukas Wunner: Forward-ported to 4.11: drop parts applied upstream] +--- + fs/btrfs/super.c | 2 +- + fs/ext4/super.c | 2 +- + fs/f2fs/super.c | 1 + + fs/jbd2/journal.c | 1 + + fs/nfsd/nfsctl.c | 3 +++ + 5 files changed, 7 insertions(+), 2 deletions(-) + +--- a/fs/btrfs/super.c ++++ b/fs/btrfs/super.c +@@ -2697,7 +2697,7 @@ + module_exit(exit_btrfs_fs) + + MODULE_LICENSE("GPL"); +-MODULE_SOFTDEP("pre: crc32c"); ++MODULE_SOFTDEP("pre: crypto-crc32c"); + MODULE_SOFTDEP("pre: xxhash64"); + MODULE_SOFTDEP("pre: sha256"); + MODULE_SOFTDEP("pre: blake2b-256"); +--- a/fs/ext4/super.c ++++ b/fs/ext4/super.c +@@ -6822,6 +6822,6 @@ + MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); + MODULE_DESCRIPTION("Fourth Extended Filesystem"); + MODULE_LICENSE("GPL"); +-MODULE_SOFTDEP("pre: crc32c"); ++MODULE_SOFTDEP("pre: crypto-crc32c"); + module_init(ext4_init_fs) + module_exit(ext4_exit_fs) +--- a/fs/jbd2/journal.c ++++ b/fs/jbd2/journal.c +@@ -3008,6 +3008,7 @@ + } + + MODULE_LICENSE("GPL"); ++MODULE_SOFTDEP("pre: crypto-crc32c"); + module_init(journal_init); + module_exit(journal_exit); + +--- a/fs/nfsd/nfsctl.c ++++ b/fs/nfsd/nfsctl.c +@@ -1579,5 +1579,8 @@ + + MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); + MODULE_LICENSE("GPL"); ++#ifdef CONFIG_NFSD_V4 ++MODULE_SOFTDEP("pre: crypto-md5"); ++#endif + module_init(init_nfsd) + module_exit(exit_nfsd) diff --git a/debian/patches/bugfix/all/kbuild-fix-recordmcount-dependency.patch b/debian/patches/bugfix/all/kbuild-fix-recordmcount-dependency.patch new file mode 100644 index 000000000..8f9c21f56 --- /dev/null +++ b/debian/patches/bugfix/all/kbuild-fix-recordmcount-dependency.patch @@ -0,0 +1,23 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Subject: kbuild: Fix recordmcount dependency for OOT modules +Date: Mon, 08 Sep 2014 18:31:24 +0100 +Forwarded: no + +We never rebuild anything in-tree when building an out-of-tree +modules, so external modules should not depend on the recordmcount +sources. + +--- a/scripts/Makefile.build ++++ b/scripts/Makefile.build +@@ -210,6 +210,11 @@ cmd_record_mcount = $(if $(findstring $( + $(sub_cmd_record_mcount)) + endif # CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT + ++# Don't require recordmcount source for an OOT build. ++ifdef KBUILD_EXTMOD ++recordmcount_source := ++endif ++ + # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory + # 'OBJECT_FILES_NON_STANDARD_foo.o := 'y': skip objtool checking for a file + # 'OBJECT_FILES_NON_STANDARD_foo.o := 'n': override directory skip for a file diff --git a/debian/patches/bugfix/all/libapi-define-_fortify_source-as-2-not-empty.patch b/debian/patches/bugfix/all/libapi-define-_fortify_source-as-2-not-empty.patch new file mode 100644 index 000000000..2c133d335 --- /dev/null +++ b/debian/patches/bugfix/all/libapi-define-_fortify_source-as-2-not-empty.patch @@ -0,0 +1,17 @@ +From: Ben Hutchings <benh@debian.org> +Date: Sat, 15 Jan 2022 22:30:49 +0100 +Subject: libapi: Define _FORTIFY_SOURCE as 2, not empty + +Signed-off-by: Ben Hutchings <benh@debian.org> +--- +--- a/tools/lib/api/Makefile ++++ b/tools/lib/api/Makefile +@@ -29,7 +29,7 @@ endif + endif + + ifeq ($(DEBUG),0) +- CFLAGS += -D_FORTIFY_SOURCE ++ CFLAGS += -D_FORTIFY_SOURCE=2 + endif + + # Treat warnings as errors unless directed not to diff --git a/debian/patches/bugfix/all/module-disable-matching-missing-version-crc.patch b/debian/patches/bugfix/all/module-disable-matching-missing-version-crc.patch new file mode 100644 index 000000000..8e0a7ee76 --- /dev/null +++ b/debian/patches/bugfix/all/module-disable-matching-missing-version-crc.patch @@ -0,0 +1,23 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Fri, 02 Dec 2016 23:06:18 +0000 +Subject: module: Disable matching missing version CRC +Forwarded: not-needed + +This partly reverts commit cd3caefb4663e3811d37cc2afad3cce642d60061. +We want to fail closed if a symbol version CRC is missing, as the +alternative may allow subverting module signing. +--- +--- a/kernel/module/version.c ++++ b/kernel/module/version.c +@@ -46,9 +46,8 @@ int check_version(const struct load_info + goto bad_version; + } + +- /* Broken toolchain. Warn once, then let it go.. */ +- pr_warn_once("%s: no symbol version for %s\n", info->name, symname); +- return 1; ++ pr_warn("%s: no symbol version for %s\n", info->name, symname); ++ return 0; + + bad_version: + pr_warn("%s: disagrees about version of symbol %s\n", info->name, symname); diff --git a/debian/patches/bugfix/all/radeon-amdgpu-firmware-is-required-for-drm-and-kms-on-r600-onward.patch b/debian/patches/bugfix/all/radeon-amdgpu-firmware-is-required-for-drm-and-kms-on-r600-onward.patch new file mode 100644 index 000000000..fe502df7e --- /dev/null +++ b/debian/patches/bugfix/all/radeon-amdgpu-firmware-is-required-for-drm-and-kms-on-r600-onward.patch @@ -0,0 +1,135 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Subject: radeon, amdgpu: Firmware is required for DRM and KMS on R600 onward +Date: Tue, 08 Jan 2013 03:25:52 +0000 +Bug-Debian: https://bugs.debian.org/607194 +Bug-Debian: https://bugs.debian.org/607471 +Bug-Debian: https://bugs.debian.org/610851 +Bug-Debian: https://bugs.debian.org/627497 +Bug-Debian: https://bugs.debian.org/632212 +Bug-Debian: https://bugs.debian.org/637943 +Bug-Debian: https://bugs.debian.org/649448 +Bug-Debian: https://bugs.debian.org/697229 +Forwarded: no + +radeon requires firmware/microcode for the GPU in all chips, but for +newer chips (apparently R600 'Evergreen' onward) it also expects +firmware for the memory controller and other sub-blocks. + +radeon attempts to gracefully fall back and disable some features if +the firmware is not available, but becomes unstable - the framebuffer +and/or system memory may be corrupted, or the display may stay black. + +Therefore, perform a basic check for the existence of +/lib/firmware/{radeon,amdgpu} when a device is probed, and abort if it +is missing, except for the pre-R600 case. + +--- + drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 29 ++++++++++++++++++++++++ + drivers/gpu/drm/radeon/radeon_drv.c | 30 +++++++++++++++++++++++++ + 2 files changed, 59 insertions(+) + +--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c ++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +@@ -39,6 +39,8 @@ + #include <linux/cc_platform.h> + #include <linux/fb.h> + #include <linux/dynamic_debug.h> ++#include <linux/namei.h> ++#include <linux/path.h> + + #include "amdgpu.h" + #include "amdgpu_irq.h" +@@ -2039,6 +2041,28 @@ static void amdgpu_get_secondary_funcs(s + } + } + ++/* Test that /lib/firmware/amdgpu is a directory (or symlink to a ++ * directory). We could try to match the udev search path, but let's ++ * keep it simple. ++ */ ++static bool amdgpu_firmware_installed(void) ++{ ++#if IS_BUILTIN(CONFIG_DRM_AMDGPU) ++ /* It may be too early to tell. Assume it's there. */ ++ return true; ++#else ++ struct path path; ++ ++ if (kern_path("/lib/firmware/amdgpu", LOOKUP_DIRECTORY | LOOKUP_FOLLOW, ++ &path) == 0) { ++ path_put(&path); ++ return true; ++ } ++ ++ return false; ++#endif ++} ++ + static int amdgpu_pci_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) + { +@@ -2122,6 +2146,11 @@ static int amdgpu_pci_probe(struct pci_d + } + #endif + ++ if (!amdgpu_firmware_installed()) { ++ DRM_ERROR("amdgpu requires firmware installed\n"); ++ return -ENODEV; ++ } ++ + adev = devm_drm_dev_alloc(&pdev->dev, &amdgpu_kms_driver, typeof(*adev), ddev); + if (IS_ERR(adev)) + return PTR_ERR(adev); +--- a/drivers/gpu/drm/radeon/radeon_drv.c ++++ b/drivers/gpu/drm/radeon/radeon_drv.c +@@ -48,6 +48,8 @@ + #include <drm/drm_probe_helper.h> + #include <drm/drm_vblank.h> + #include <drm/radeon_drm.h> ++#include <linux/namei.h> ++#include <linux/path.h> + + #include "radeon_drv.h" + #include "radeon.h" +@@ -284,6 +286,28 @@ MODULE_DEVICE_TABLE(pci, pciidlist); + + static const struct drm_driver kms_driver; + ++/* Test that /lib/firmware/radeon is a directory (or symlink to a ++ * directory). We could try to match the udev search path, but let's ++ * keep it simple. ++ */ ++static bool radeon_firmware_installed(void) ++{ ++#if IS_BUILTIN(CONFIG_DRM_RADEON) ++ /* It may be too early to tell. Assume it's there. */ ++ return true; ++#else ++ struct path path; ++ ++ if (kern_path("/lib/firmware/radeon", LOOKUP_DIRECTORY | LOOKUP_FOLLOW, ++ &path) == 0) { ++ path_put(&path); ++ return true; ++ } ++ ++ return false; ++#endif ++} ++ + static int radeon_pci_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) + { +@@ -324,6 +348,12 @@ static int radeon_pci_probe(struct pci_d + if (vga_switcheroo_client_probe_defer(pdev)) + return -EPROBE_DEFER; + ++ if ((ent->driver_data & RADEON_FAMILY_MASK) >= CHIP_R600 && ++ !radeon_firmware_installed()) { ++ DRM_ERROR("radeon kernel modesetting for R600 or later requires firmware installed\n"); ++ return -ENODEV; ++ } ++ + /* Get rid of things like offb */ + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &kms_driver); + if (ret) diff --git a/debian/patches/bugfix/all/tools-build-remove-bpf-run-time-check-at-build-time.patch b/debian/patches/bugfix/all/tools-build-remove-bpf-run-time-check-at-build-time.patch new file mode 100644 index 000000000..3818dbb17 --- /dev/null +++ b/debian/patches/bugfix/all/tools-build-remove-bpf-run-time-check-at-build-time.patch @@ -0,0 +1,27 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Sun, 21 Feb 2016 15:33:15 +0000 +Subject: tools/build: Remove bpf() run-time check at build time +Forwarded: no + +It is not correct to test that a syscall works on the build system's +kernel. We might be building on an earlier kernel version or with +security restrictions that block bpf(). + +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- +--- a/tools/build/feature/test-bpf.c ++++ b/tools/build/feature/test-bpf.c +@@ -35,8 +35,10 @@ int main(void) + attr.prog_flags = 0; + + /* +- * Test existence of __NR_bpf and BPF_PROG_LOAD. +- * This call should fail if we run the testcase. ++ * bwh: Don't use the bpf() syscall as we might be building on a ++ * much older kernel. Do "use" the attr structure here to avoid ++ * a "set but not used" warning. + */ +- return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); ++ (void)&attr; ++ return 0; + } diff --git a/debian/patches/bugfix/all/tools-perf-fix-missing-ldflags-for-some-programs.patch b/debian/patches/bugfix/all/tools-perf-fix-missing-ldflags-for-some-programs.patch new file mode 100644 index 000000000..2d8f29d25 --- /dev/null +++ b/debian/patches/bugfix/all/tools-perf-fix-missing-ldflags-for-some-programs.patch @@ -0,0 +1,17 @@ +From: Ben Hutchings <benh@debian.org> +Date: Sat, 15 Jan 2022 22:59:11 +0100 +Subject: tools/perf: Fix missing LDFLAGS for some programs + +Signed-off-by: Ben Hutchings <benh@debian.org> +--- +--- a/tools/perf/Makefile.perf ++++ b/tools/perf/Makefile.perf +@@ -785,7 +785,7 @@ $(OUTPUT)dlfilters/%.o: dlfilters/%.c in + .SECONDARY: $(DLFILTERS:.so=.o) + + $(OUTPUT)dlfilters/%.so: $(OUTPUT)dlfilters/%.o +- $(QUIET_LINK)$(CC) $(EXTRA_CFLAGS) -shared -o $@ $< ++ $(QUIET_LINK)$(CC) $(EXTRA_CFLAGS) $(LDFLAGS) -shared -o $@ $< + + ifndef NO_JVMTI + LIBJVMTI_IN := $(OUTPUT)jvmti/jvmti-in.o diff --git a/debian/patches/bugfix/all/tools-perf-man-date.patch b/debian/patches/bugfix/all/tools-perf-man-date.patch new file mode 100644 index 000000000..80a19b554 --- /dev/null +++ b/debian/patches/bugfix/all/tools-perf-man-date.patch @@ -0,0 +1,44 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Mon, 13 Jul 2015 20:29:20 +0100 +Subject: perf tools: Use $KBUILD_BUILD_TIMESTAMP as man page date +Forwarded: http://mid.gmane.org/20160517132809.GE7555@decadent.org.uk + +This allows man pages to be built reproducibly. + +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- + tools/perf/Documentation/Makefile | 3 +++ + tools/perf/Documentation/asciidoc.conf | 3 +++ + 2 files changed, 6 insertions(+) + +diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile +index adc5a7e44b98..2161b2e838b7 100644 +--- a/tools/perf/Documentation/Makefile ++++ b/tools/perf/Documentation/Makefile +@@ -132,6 +132,9 @@ endif + ifdef DOCBOOK_SUPPRESS_SP + XMLTO_EXTRA += -m manpage-suppress-sp.xsl + endif ++ifdef KBUILD_BUILD_TIMESTAMP ++ASCIIDOC_EXTRA += -a revdate=$(shell date -u -d '$(KBUILD_BUILD_TIMESTAMP)' +%Y-%m-%d) ++endif + + SHELL_PATH ?= $(SHELL) + # Shell quote; +diff --git a/tools/perf/Documentation/asciidoc.conf b/tools/perf/Documentation/asciidoc.conf +index 2b62ba1e72b7..82d3060177ba 100644 +--- a/tools/perf/Documentation/asciidoc.conf ++++ b/tools/perf/Documentation/asciidoc.conf +@@ -71,6 +71,9 @@ ifdef::backend-docbook[] + [header] + template::[header-declarations] + <refentry> ++<refentryinfo> ++template::[docinfo] ++</refentryinfo> + ifdef::perf_date[] + <refentryinfo><date>{perf_date}</date></refentryinfo> + endif::perf_date[] +-- +2.23.0 + diff --git a/debian/patches/bugfix/all/tools-perf-pmu-events-fix-reproducibility.patch b/debian/patches/bugfix/all/tools-perf-pmu-events-fix-reproducibility.patch new file mode 100644 index 000000000..cd4f5c5a3 --- /dev/null +++ b/debian/patches/bugfix/all/tools-perf-pmu-events-fix-reproducibility.patch @@ -0,0 +1,26 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Sun, 25 Aug 2019 13:49:41 +0100 +Subject: tools/perf: pmu-events: Fix reproducibility +Forwarded: https://lore.kernel.org/lkml/20190825131329.naqzd5kwg7mw5d3f@decadent.org.uk/T/#u + +jevents.py enumerates files and outputs the corresponding C structs in +the order they are found. This makes it sensitive to directory +ordering, so that the perf executable is not reproducible. + +To avoid this, sort the entries returned by os.scandir() before +processing them. + +References: https://tests.reproducible-builds.org/debian/dbdtxt/bullseye/i386/linux_4.19.37-6.diffoscope.txt.gz +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- +--- a/tools/perf/pmu-events/jevents.py ++++ b/tools/perf/pmu-events/jevents.py +@@ -663,7 +663,7 @@ def main() -> None: + def ftw(path: str, parents: Sequence[str], + action: Callable[[Sequence[str], os.DirEntry], None]) -> None: + """Replicate the directory/file walking behavior of C's file tree walk.""" +- for item in os.scandir(path): ++ for item in sorted(os.scandir(path), key=(lambda item: item.name)): + action(parents, item) + if item.is_dir(): + ftw(item.path, parents + [item.name], action) diff --git a/debian/patches/bugfix/all/tools-perf-remove-shebangs.patch b/debian/patches/bugfix/all/tools-perf-remove-shebangs.patch new file mode 100644 index 000000000..9766e0e4a --- /dev/null +++ b/debian/patches/bugfix/all/tools-perf-remove-shebangs.patch @@ -0,0 +1,39 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Fri, 25 Sep 2015 20:09:23 +0100 +Subject: tools/perf: Remove shebang lines from perf scripts +Forwarded: no + +perf scripts need to be invoked through perf, not directly through +perl (or other language interpreter). So including shebang lines in +them is useless and possibly misleading. + +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- +--- a/tools/perf/scripts/perl/rw-by-file.pl ++++ b/tools/perf/scripts/perl/rw-by-file.pl +@@ -1,4 +1,3 @@ +-#!/usr/bin/perl -w + # SPDX-License-Identifier: GPL-2.0-only + # (c) 2009, Tom Zanussi <tzanussi@gmail.com> + +--- a/tools/perf/scripts/perl/rw-by-pid.pl ++++ b/tools/perf/scripts/perl/rw-by-pid.pl +@@ -1,4 +1,3 @@ +-#!/usr/bin/perl -w + # SPDX-License-Identifier: GPL-2.0-only + # (c) 2009, Tom Zanussi <tzanussi@gmail.com> + +--- a/tools/perf/scripts/perl/rwtop.pl ++++ b/tools/perf/scripts/perl/rwtop.pl +@@ -1,4 +1,3 @@ +-#!/usr/bin/perl -w + # SPDX-License-Identifier: GPL-2.0-only + # (c) 2010, Tom Zanussi <tzanussi@gmail.com> + +--- a/tools/perf/scripts/perl/wakeup-latency.pl ++++ b/tools/perf/scripts/perl/wakeup-latency.pl +@@ -1,4 +1,3 @@ +-#!/usr/bin/perl -w + # SPDX-License-Identifier: GPL-2.0-only + # (c) 2009, Tom Zanussi <tzanussi@gmail.com> + diff --git a/debian/patches/bugfix/all/usbip-document-tcp-wrappers.patch b/debian/patches/bugfix/all/usbip-document-tcp-wrappers.patch new file mode 100644 index 000000000..d9d7b301d --- /dev/null +++ b/debian/patches/bugfix/all/usbip-document-tcp-wrappers.patch @@ -0,0 +1,29 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Sun, 24 Jun 2012 02:51:39 +0100 +Subject: usbip: Document TCP wrappers +Forwarded: no + +Add references to TCP wrappers configuration in the manual page. + +--- a/tools/usb/usbip/doc/usbipd.8 ++++ b/tools/usb/usbip/doc/usbipd.8 +@@ -14,7 +14,8 @@ Devices have to explicitly be exported u + before usbipd makes them available to other hosts. + + The daemon accepts connections from USB/IP clients +-on TCP port 3240 by default. ++on TCP port 3240 by default. The clients authorised to connect may be ++configured as documented in hosts_access(5). + + .SH OPTIONS + .HP +@@ -69,7 +70,8 @@ Show version. + + .B usbipd + offers no authentication or authorization for USB/IP. Any +-USB/IP client can connect and use exported devices. ++USB/IP client running on an authorised host can connect and ++use exported devices. + + .SH EXAMPLES + diff --git a/debian/patches/bugfix/all/wifi-mt76-do-not-run-mt76_unregister_device-on-unregistered-hw.patch b/debian/patches/bugfix/all/wifi-mt76-do-not-run-mt76_unregister_device-on-unregistered-hw.patch new file mode 100644 index 000000000..4635a6778 --- /dev/null +++ b/debian/patches/bugfix/all/wifi-mt76-do-not-run-mt76_unregister_device-on-unregistered-hw.patch @@ -0,0 +1,78 @@ +From: Lorenzo Bianconi <lorenzo@kernel.org> +Date: Thu, 23 Feb 2023 00:10:25 +0100 +Subject: wifi: mt76: do not run mt76_unregister_device() on unregistered hw +Origin: https://patchwork.kernel.org/project/linux-wireless/patch/be3457d82f4e44bb71a22b2b5db27b644a37b1e1.1677107277.git.lorenzo@kernel.org/ +Bug-Debian: https://bugs.debian.org/1029116 + +Trying to probe a mt7921e pci card without firmware results in a +successful probe where ieee80211_register_hw hasn't been called. When +removing the driver, ieee802111_unregister_hw is called unconditionally +leading to a kernel NULL pointer dereference. +Fix the issue running mt76_unregister_device routine just for registered +hw. + +Link: https://bugs.debian.org/1029116 +Link: https://bugs.kali.org/view.php?id=8140 +Reported-by: Stuart Hayhurst <stuart.a.hayhurst@gmail.com> +Fixes: 1c71e03afe4b ("mt76: mt7921: move mt7921_init_hw in a dedicated work") +Tested-by: Helmut Grohne <helmut@freexian.com> +Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org> + +Currently queued for review for the v6.3 release cycle, backported in +advance to prevent users from getting stuck in the installer. + +Signed-off-by: Cyril Brulebois <kibi@debian.org> + +--- + drivers/net/wireless/mediatek/mt76/mac80211.c | 8 ++++++++ + drivers/net/wireless/mediatek/mt76/mt76.h | 1 + + 2 files changed, 9 insertions(+) + +--- a/drivers/net/wireless/mediatek/mt76/mac80211.c ++++ b/drivers/net/wireless/mediatek/mt76/mac80211.c +@@ -522,6 +522,7 @@ int mt76_register_phy(struct mt76_phy *p + if (ret) + return ret; + ++ set_bit(MT76_STATE_REGISTERED, &phy->state); + phy->dev->phys[phy->band_idx] = phy; + + return 0; +@@ -532,6 +533,9 @@ void mt76_unregister_phy(struct mt76_phy + { + struct mt76_dev *dev = phy->dev; + ++ if (!test_bit(MT76_STATE_REGISTERED, &phy->state)) ++ return; ++ + mt76_tx_status_check(dev, true); + ieee80211_unregister_hw(phy->hw); + dev->phys[phy->band_idx] = NULL; +@@ -654,6 +658,7 @@ int mt76_register_device(struct mt76_dev + return ret; + + WARN_ON(mt76_worker_setup(hw, &dev->tx_worker, NULL, "tx")); ++ set_bit(MT76_STATE_REGISTERED, &phy->state); + sched_set_fifo_low(dev->tx_worker.task); + + return 0; +@@ -664,6 +669,9 @@ void mt76_unregister_device(struct mt76_ + { + struct ieee80211_hw *hw = dev->hw; + ++ if (!test_bit(MT76_STATE_REGISTERED, &dev->phy.state)) ++ return; ++ + if (IS_ENABLED(CONFIG_MT76_LEDS)) + mt76_led_cleanup(dev); + mt76_tx_status_check(dev, true); +--- a/drivers/net/wireless/mediatek/mt76/mt76.h ++++ b/drivers/net/wireless/mediatek/mt76/mt76.h +@@ -388,6 +388,7 @@ struct mt76_tx_cb { + + enum { + MT76_STATE_INITIALIZED, ++ MT76_STATE_REGISTERED, + MT76_STATE_RUNNING, + MT76_STATE_MCU_RUNNING, + MT76_SCANNING, diff --git a/debian/patches/bugfix/alpha/alpha-fix-missing-symbol-versions-for-str-n-cat-cpy.patch b/debian/patches/bugfix/alpha/alpha-fix-missing-symbol-versions-for-str-n-cat-cpy.patch new file mode 100644 index 000000000..3da69882e --- /dev/null +++ b/debian/patches/bugfix/alpha/alpha-fix-missing-symbol-versions-for-str-n-cat-cpy.patch @@ -0,0 +1,75 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Thu, 5 Jan 2023 17:04:40 +0100 +Subject: alpha: Fix missing symbol versions for str{,n}{cat,cpy} +Origin: https://marc.info/?l=linux-alpha&m=167364720725291&w=2 + +Now that modpost extracts symbol versions from *.cmd files, it can't +find the versions for these 4 symbols. This is due to the way we link +their objects together ahead of the full vmlinux link. genksyms puts +their symbol CRCs in .str{,n}{cat,cpy}.o.cmd, but modpost only reads +the .sty{,n}cpy.o.cmd files. + +Add assembly sources that bring the appropriate routines together with +include directives instead of using the linker for this. + +Reported-by: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> +Fixes: f292d875d0dc ("modpost: extract symbol versions from *.cmd files") +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- + arch/alpha/lib/Makefile | 14 -------------- + arch/alpha/lib/stycpy.S | 8 ++++++++ + arch/alpha/lib/styncpy.S | 8 ++++++++ + 3 files changed, 16 insertions(+), 14 deletions(-) + create mode 100644 arch/alpha/lib/stycpy.S + create mode 100644 arch/alpha/lib/styncpy.S + +diff --git a/arch/alpha/lib/Makefile b/arch/alpha/lib/Makefile +index 1cc74f7b50ef..8f1c32a25a40 100644 +--- a/arch/alpha/lib/Makefile ++++ b/arch/alpha/lib/Makefile +@@ -45,17 +45,3 @@ AFLAGS___remlu.o = -DREM -DINTSIZE + $(addprefix $(obj)/,__divqu.o __remqu.o __divlu.o __remlu.o): \ + $(src)/$(ev6-y)divide.S FORCE + $(call if_changed_rule,as_o_S) +- +-# There are direct branches between {str*cpy,str*cat} and stx*cpy. +-# Ensure the branches are within range by merging these objects. +- +-LDFLAGS_stycpy.o := -r +-LDFLAGS_styncpy.o := -r +- +-$(obj)/stycpy.o: $(obj)/strcpy.o $(obj)/$(ev67-y)strcat.o \ +- $(obj)/$(ev6-y)stxcpy.o FORCE +- $(call if_changed,ld) +- +-$(obj)/styncpy.o: $(obj)/strncpy.o $(obj)/$(ev67-y)strncat.o \ +- $(obj)/$(ev6-y)stxncpy.o FORCE +- $(call if_changed,ld) +diff --git a/arch/alpha/lib/stycpy.S b/arch/alpha/lib/stycpy.S +new file mode 100644 +index 000000000000..b4376834c91f +--- /dev/null ++++ b/arch/alpha/lib/stycpy.S +@@ -0,0 +1,8 @@ ++#include "strcpy.S" ++#ifdef CONFIG_ALPHA_EV6 ++#include "ev6-strcat.S" ++#include "ev6-stxcpy.S" ++#else ++#include "strcat.S" ++#include "stxcpy.S" ++#endif +diff --git a/arch/alpha/lib/styncpy.S b/arch/alpha/lib/styncpy.S +new file mode 100644 +index 000000000000..c393f816ff98 +--- /dev/null ++++ b/arch/alpha/lib/styncpy.S +@@ -0,0 +1,8 @@ ++#include "strncpy.S" ++#ifdef CONFIG_ALPHA_EV6 ++#include "ev6-strncat.S" ++#include "ev6-stxncpy.S" ++#else ++#include "strncat.S" ++#include "stxncpy.S" ++#endif diff --git a/debian/patches/bugfix/arm/arm-dts-kirkwood-fix-sata-pinmux-ing-for-ts419.patch b/debian/patches/bugfix/arm/arm-dts-kirkwood-fix-sata-pinmux-ing-for-ts419.patch new file mode 100644 index 000000000..9e6622fb0 --- /dev/null +++ b/debian/patches/bugfix/arm/arm-dts-kirkwood-fix-sata-pinmux-ing-for-ts419.patch @@ -0,0 +1,37 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Fri, 17 Feb 2017 01:30:30 +0000 +Subject: ARM: dts: kirkwood: Fix SATA pinmux-ing for TS419 +Forwarded: https://www.spinics.net/lists/arm-kernel/msg563610.html +Bug-Debian: https://bugs.debian.org/855017 + +The old board code for the TS419 assigns MPP pins 15 and 16 as SATA +activity signals (and none as SATA presence signals). Currently the +device tree assigns the SoC's default pinmux groups for SATA, which +conflict with the second Ethernet port. + +Reported-by: gmbh@gazeta.pl +Tested-by: gmbh@gazeta.pl +References: https://bugs.debian.org/855017 +Cc: stable@vger.kernel.org # 3.15+ +Fixes: 934b524b3f49 ("ARM: Kirkwood: Add DT description of QNAP 419") +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- + arch/arm/boot/dts/kirkwood-ts419.dtsi | 8 ++++++++ + 1 file changed, 8 insertions(+) + +diff --git a/arch/arm/boot/dts/kirkwood-ts419.dtsi b/arch/arm/boot/dts/kirkwood-ts419.dtsi +index 02bd53762705..532506cb0f4a 100644 +--- a/arch/arm/boot/dts/kirkwood-ts419.dtsi ++++ b/arch/arm/boot/dts/kirkwood-ts419.dtsi +@@ -73,3 +73,11 @@ + phy-handle = <ðphy1>; + }; + }; ++ ++&pmx_sata0 { ++ marvell,pins = "mpp15"; ++}; ++ ++&pmx_sata1 { ++ marvell,pins = "mpp16"; ++}; diff --git a/debian/patches/bugfix/arm/arm-mm-export-__sync_icache_dcache-for-xen-privcmd.patch b/debian/patches/bugfix/arm/arm-mm-export-__sync_icache_dcache-for-xen-privcmd.patch new file mode 100644 index 000000000..1bdd37fbe --- /dev/null +++ b/debian/patches/bugfix/arm/arm-mm-export-__sync_icache_dcache-for-xen-privcmd.patch @@ -0,0 +1,31 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Wed, 11 Jul 2018 23:40:55 +0100 +Subject: ARM: mm: Export __sync_icache_dcache() for xen-privcmd +Forwarded: https://marc.info/?l=linux-arm-kernel&m=153134944429241 + +The xen-privcmd driver, which can be modular, calls set_pte_at() +which in turn may call __sync_icache_dcache(). + +The call to __sync_icache_dcache() may be optimised out because it is +conditional on !pte_special(), and xen-privcmd calls pte_mkspecial(). +However, in a non-LPAE configuration there is no "special" bit and the +call is really unconditional. + +Fixes: 3ad0876554ca ("xen/privcmd: add IOCTL_PRIVCMD_MMAP_RESOURCE") +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- + arch/arm/mm/flush.c | 1 + + 1 file changed, 1 insertion(+) + +Index: debian-kernel/arch/arm/mm/flush.c +=================================================================== +--- debian-kernel.orig/arch/arm/mm/flush.c ++++ debian-kernel/arch/arm/mm/flush.c +@@ -292,6 +292,7 @@ void __sync_icache_dcache(pte_t pteval) + if (pte_exec(pteval)) + __flush_icache_all(); + } ++EXPORT_SYMBOL_GPL(__sync_icache_dcache); + #endif + + /* diff --git a/debian/patches/bugfix/arm64/arm64-acpi-Add-fixup-for-HPE-m400-quirks.patch b/debian/patches/bugfix/arm64/arm64-acpi-Add-fixup-for-HPE-m400-quirks.patch new file mode 100644 index 000000000..fc1e76a02 --- /dev/null +++ b/debian/patches/bugfix/arm64/arm64-acpi-Add-fixup-for-HPE-m400-quirks.patch @@ -0,0 +1,92 @@ +From: Geoff Levand <geoff@infradead.org> +Date: Wed, 13 Jun 2018 10:56:08 -0700 +Subject: arm64/acpi: Add fixup for HPE m400 quirks +Forwarded: https://patchwork.codeaurora.org/patch/547277/ + +Adds a new ACPI init routine acpi_fixup_m400_quirks that adds +a work-around for HPE ProLiant m400 APEI firmware problems. + +The work-around disables APEI when CONFIG_ACPI_APEI is set and +m400 firmware is detected. Without this fixup m400 systems +experience errors like these on startup: + + [Hardware Error]: Hardware error from APEI Generic Hardware Error Source: 2 + [Hardware Error]: event severity: fatal + [Hardware Error]: Error 0, type: fatal + [Hardware Error]: section_type: memory error + [Hardware Error]: error_status: 0x0000000000001300 + [Hardware Error]: error_type: 10, invalid address + Kernel panic - not syncing: Fatal hardware error! + +Signed-off-by: Geoff Levand <geoff@infradead.org> +[bwh: Adjust context to apply to Linux 4.19] +--- + arch/arm64/kernel/acpi.c | 40 ++++++++++++++++++++++++++++++++++++---- + 1 file changed, 36 insertions(+), 4 deletions(-) + +Index: linux/arch/arm64/kernel/acpi.c +=================================================================== +--- linux.orig/arch/arm64/kernel/acpi.c ++++ linux/arch/arm64/kernel/acpi.c +@@ -32,6 +32,8 @@ + #include <asm/daifflags.h> + #include <asm/smp_plat.h> + ++#include <acpi/apei.h> ++ + int acpi_noirq = 1; /* skip ACPI IRQ initialization */ + int acpi_disabled = 1; + EXPORT_SYMBOL(acpi_disabled); +@@ -178,6 +180,33 @@ out: + } + + /* ++ * acpi_fixup_m400_quirks - Work-around for HPE ProLiant m400 APEI firmware ++ * problems. ++ */ ++static void __init acpi_fixup_m400_quirks(void) ++{ ++ acpi_status status; ++ struct acpi_table_header *header; ++#if !defined(CONFIG_ACPI_APEI) ++ int hest_disable = HEST_DISABLED; ++#endif ++ ++ if (!IS_ENABLED(CONFIG_ACPI_APEI) || hest_disable != HEST_ENABLED) ++ return; ++ ++ status = acpi_get_table(ACPI_SIG_HEST, 0, &header); ++ ++ if (ACPI_SUCCESS(status) && !strncmp(header->oem_id, "HPE ", 6) && ++ !strncmp(header->oem_table_id, "ProLiant", 8) && ++ MIDR_IMPLEMENTOR(read_cpuid_id()) == ARM_CPU_IMP_APM) { ++ hest_disable = HEST_DISABLED; ++ pr_info("Disabled APEI for m400.\n"); ++ } ++ ++ acpi_put_table(header); ++} ++ ++/* + * acpi_boot_table_init() called from setup_arch(), always. + * 1. find RSDP and get its address, and then find XSDT + * 2. extract all tables and checksums them all +@@ -232,11 +261,14 @@ done: + if (acpi_disabled) { + if (earlycon_acpi_spcr_enable) + early_init_dt_scan_chosen_stdout(); +- } else { +- acpi_parse_spcr(earlycon_acpi_spcr_enable, true); +- if (IS_ENABLED(CONFIG_ACPI_BGRT)) +- acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); ++ return; + } ++ ++ acpi_parse_spcr(earlycon_acpi_spcr_enable, true); ++ if (IS_ENABLED(CONFIG_ACPI_BGRT)) ++ acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); ++ ++ acpi_fixup_m400_quirks(); + } + + static pgprot_t __acpi_get_writethrough_mem_attribute(void) diff --git a/debian/patches/bugfix/arm64/arm64-dts-rockchip-fix-spdif-fe460000-ordering-on-rk.patch b/debian/patches/bugfix/arm64/arm64-dts-rockchip-fix-spdif-fe460000-ordering-on-rk.patch new file mode 100644 index 000000000..e7ee12ead --- /dev/null +++ b/debian/patches/bugfix/arm64/arm64-dts-rockchip-fix-spdif-fe460000-ordering-on-rk.patch @@ -0,0 +1,63 @@ +From: Heiko Stuebner <heiko@sntech.de> +Date: Sun, 30 Oct 2022 20:34:42 +0100 +Subject: arm64: dts: rockchip: fix spdif@fe460000 ordering on rk356x +Origin: https://git.kernel.org/linus/d4eade428d22f2ac5f32b12ec183fdff84dc07a6 + +Move the node to its correct position, based on its +mmio-address. + +Link: https://lore.kernel.org/all/20221030193708.1671069-1-heiko@sntech.de +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + arch/arm64/boot/dts/rockchip/rk356x.dtsi | 28 ++++++++++++------------ + 1 file changed, 14 insertions(+), 14 deletions(-) + +diff --git a/arch/arm64/boot/dts/rockchip/rk356x.dtsi b/arch/arm64/boot/dts/rockchip/rk356x.dtsi +index 164708f1eb67..10e3a0862602 100644 +--- a/arch/arm64/boot/dts/rockchip/rk356x.dtsi ++++ b/arch/arm64/boot/dts/rockchip/rk356x.dtsi +@@ -1049,20 +1049,6 @@ + status = "disabled"; + }; + +- spdif: spdif@fe460000 { +- compatible = "rockchip,rk3568-spdif"; +- reg = <0x0 0xfe460000 0x0 0x1000>; +- interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>; +- clock-names = "mclk", "hclk"; +- clocks = <&cru MCLK_SPDIF_8CH>, <&cru HCLK_SPDIF_8CH>; +- dmas = <&dmac1 1>; +- dma-names = "tx"; +- pinctrl-names = "default"; +- pinctrl-0 = <&spdifm0_tx>; +- #sound-dai-cells = <0>; +- status = "disabled"; +- }; +- + i2s0_8ch: i2s@fe400000 { + compatible = "rockchip,rk3568-i2s-tdm"; + reg = <0x0 0xfe400000 0x0 0x1000>; +@@ -1142,6 +1128,20 @@ + status = "disabled"; + }; + ++ spdif: spdif@fe460000 { ++ compatible = "rockchip,rk3568-spdif"; ++ reg = <0x0 0xfe460000 0x0 0x1000>; ++ interrupts = <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>; ++ clock-names = "mclk", "hclk"; ++ clocks = <&cru MCLK_SPDIF_8CH>, <&cru HCLK_SPDIF_8CH>; ++ dmas = <&dmac1 1>; ++ dma-names = "tx"; ++ pinctrl-names = "default"; ++ pinctrl-0 = <&spdifm0_tx>; ++ #sound-dai-cells = <0>; ++ status = "disabled"; ++ }; ++ + dmac0: dma-controller@fe530000 { + compatible = "arm,pl330", "arm,primecell"; + reg = <0x0 0xfe530000 0x0 0x4000>; +-- +2.39.0 + diff --git a/debian/patches/bugfix/powerpc/fbdev-offb-Update-expected-device-name.patch b/debian/patches/bugfix/powerpc/fbdev-offb-Update-expected-device-name.patch new file mode 100644 index 000000000..d09035691 --- /dev/null +++ b/debian/patches/bugfix/powerpc/fbdev-offb-Update-expected-device-name.patch @@ -0,0 +1,46 @@ +From: Cyril Brulebois <cyril@debamax.com> +Date: Wed, 12 Apr 2023 11:55:08 +0200 +Subject: fbdev/offb: Update expected device name +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://git.kernel.org/pub/scm/linux/kernel/git/deller/linux-fbdev.git/commit?id=27c74ea74be805ccba1bc1a0a03cc79c51dca6ea + +Since commit 241d2fb56a18 ("of: Make OF framebuffer device names unique"), +as spotted by Frédéric Bonnard, the historical "of-display" device is +gone: the updated logic creates "of-display.0" instead, then as many +"of-display.N" as required. + +This means that offb no longer finds the expected device, which prevents +the Debian Installer from setting up its interface, at least on ppc64el. + +It might be better to iterate on all possible nodes, but updating the +hardcoded device from "of-display" to "of-display.0" is confirmed to fix +the Debian Installer at the very least. + +Link: https://bugzilla.kernel.org/show_bug.cgi?id=217328 +Link: https://bugs.debian.org/1033058 +Fixes: 241d2fb56a18 ("of: Make OF framebuffer device names unique") +Cc: stable@vger.kernel.org +Signed-off-by: Cyril Brulebois <cyril@debamax.com> +Signed-off-by: Helge Deller <deller@gmx.de> +--- + drivers/video/fbdev/offb.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/video/fbdev/offb.c b/drivers/video/fbdev/offb.c +index 0065a77b6dbc8..b5fdef2b74359 100644 +--- a/drivers/video/fbdev/offb.c ++++ b/drivers/video/fbdev/offb.c +@@ -696,7 +696,7 @@ MODULE_DEVICE_TABLE(of, offb_of_match_display); + + static struct platform_driver offb_driver_display = { + .driver = { +- .name = "of-display", ++ .name = "of-display.0", + .of_match_table = offb_of_match_display, + }, + .probe = offb_probe_display, +-- +2.30.2 + diff --git a/debian/patches/bugfix/powerpc/powerpc-boot-fix-missing-crc32poly.h-when-building-with-kernel_xz.patch b/debian/patches/bugfix/powerpc/powerpc-boot-fix-missing-crc32poly.h-when-building-with-kernel_xz.patch new file mode 100644 index 000000000..a00a2a485 --- /dev/null +++ b/debian/patches/bugfix/powerpc/powerpc-boot-fix-missing-crc32poly.h-when-building-with-kernel_xz.patch @@ -0,0 +1,39 @@ +From: Krzysztof Kozlowski <krzk@kernel.org> +Date: Wed, 29 Aug 2018 09:32:23 +0200 +Subject: powerpc/boot: Fix missing crc32poly.h when building with KERNEL_XZ +Origin: https://patchwork.ozlabs.org/patch/963258/ + +After commit faa16bc404d7 ("lib: Use existing define with +polynomial") the lib/xz/xz_crc32.c includes a header from include/linux +directory thus any other user of this code should define proper include +path. + +This fixes the build error on powerpc with CONFIG_KERNEL_XZ: + + In file included from ../arch/powerpc/boot/../../../lib/decompress_unxz.c:233:0, + from ../arch/powerpc/boot/decompress.c:42: + ../arch/powerpc/boot/../../../lib/xz/xz_crc32.c:18:29: fatal error: linux/crc32poly.h: No such file or directory + +Reported-by: Michal Kubecek <mkubecek@suse.cz> +Fixes: faa16bc404d7 ("lib: Use existing define with polynomial") +Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org> +Reported-by: kbuild test robot <lkp@intel.com> +Reported-by: Meelis Roos <mroos@linux.ee> +Tested-by: Michal Kubecek <mkubecek@suse.cz> +--- + arch/powerpc/boot/Makefile | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +Index: linux/arch/powerpc/boot/Makefile +=================================================================== +--- linux.orig/arch/powerpc/boot/Makefile ++++ linux/arch/powerpc/boot/Makefile +@@ -70,7 +70,7 @@ BOOTCFLAGS += -fno-stack-protector + endif + + BOOTCFLAGS += -include $(srctree)/include/linux/compiler_attributes.h +-BOOTCFLAGS += -I$(objtree)/$(obj) -I$(srctree)/$(obj) ++BOOTCFLAGS += -I$(objtree)/$(obj) -I$(srctree)/$(obj) -I$(srctree)/include + + DTC_FLAGS ?= -p 1024 + diff --git a/debian/patches/bugfix/sh/sh-boot-do-not-use-hyphen-in-exported-variable-name.patch b/debian/patches/bugfix/sh/sh-boot-do-not-use-hyphen-in-exported-variable-name.patch new file mode 100644 index 000000000..31eb2eb5d --- /dev/null +++ b/debian/patches/bugfix/sh/sh-boot-do-not-use-hyphen-in-exported-variable-name.patch @@ -0,0 +1,95 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Mon, 07 Feb 2022 00:00:26 +0100 +Subject: sh: Do not use hyphen in exported variable names + +arch/sh/Makefile defines and exports ld-bfd to be used by +arch/sh/boot/Makefile and arch/sh/boot/compressed/Makefile. However +some shells, including dash, will not pass through environment +variables whose name includes a hyphen. Usually GNU make does not use +a shell to recurse, but if e.g. $(srctree) contains '~' it will use a +shell here. + +Rename the variable to ld_bfd. + +(Another instance of this problem was fixed upstream by commit +82977af93a0d "sh: rename suffix-y to suffix_y".) + +References: https://buildd.debian.org/status/fetch.php?pkg=linux&arch=sh4&ver=4.13%7Erc5-1%7Eexp1&stamp=1502943967&raw=0 +Fixes: ef9b542fce00 ("sh: bzip2/lzma uImage support.") +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- + arch/sh/Makefile | 10 +++++----- + arch/sh/boot/compressed/Makefile | 4 ++-- + arch/sh/boot/romimage/Makefile | 4 ++-- + 3 files changed, 9 insertions(+), 9 deletions(-) + +Index: linux/arch/sh/Makefile +=================================================================== +--- linux.orig/arch/sh/Makefile ++++ linux/arch/sh/Makefile +@@ -102,16 +102,16 @@ UTS_MACHINE := sh + LDFLAGS_vmlinux += -e _stext + + ifdef CONFIG_CPU_LITTLE_ENDIAN +-ld-bfd := elf32-sh-linux +-LDFLAGS_vmlinux += --defsym jiffies=jiffies_64 --oformat $(ld-bfd) ++ld_bfd := elf32-sh-linux ++LDFLAGS_vmlinux += --defsym jiffies=jiffies_64 --oformat $(ld_bfd) + KBUILD_LDFLAGS += -EL + else +-ld-bfd := elf32-shbig-linux +-LDFLAGS_vmlinux += --defsym jiffies=jiffies_64+4 --oformat $(ld-bfd) ++ld_bfd := elf32-shbig-linux ++LDFLAGS_vmlinux += --defsym jiffies=jiffies_64+4 --oformat $(ld_bfd) + KBUILD_LDFLAGS += -EB + endif + +-export ld-bfd ++export ld_bfd + + # Mach groups + machdir-$(CONFIG_SOLUTION_ENGINE) += mach-se +Index: linux/arch/sh/boot/compressed/Makefile +=================================================================== +--- linux.orig/arch/sh/boot/compressed/Makefile ++++ linux/arch/sh/boot/compressed/Makefile +@@ -36,7 +36,7 @@ endif + + ccflags-remove-$(CONFIG_MCOUNT) += -pg + +-LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(IMAGE_OFFSET) -e startup \ ++LDFLAGS_vmlinux := --oformat $(ld_bfd) -Ttext $(IMAGE_OFFSET) -e startup \ + -T $(obj)/../../kernel/vmlinux.lds + + KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING +@@ -60,7 +60,7 @@ $(obj)/vmlinux.bin.lzo: $(obj)/vmlinux.b + + OBJCOPYFLAGS += -R .empty_zero_page + +-LDFLAGS_piggy.o := -r --format binary --oformat $(ld-bfd) -T ++LDFLAGS_piggy.o := -r --format binary --oformat $(ld_bfd) -T + + $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix_y) FORCE + $(call if_changed,ld) +Index: linux/arch/sh/boot/romimage/Makefile +=================================================================== +--- linux.orig/arch/sh/boot/romimage/Makefile ++++ linux/arch/sh/boot/romimage/Makefile +@@ -13,7 +13,7 @@ mmcif-obj-$(CONFIG_CPU_SUBTYPE_SH7724) : + load-$(CONFIG_ROMIMAGE_MMCIF) := $(mmcif-load-y) + obj-$(CONFIG_ROMIMAGE_MMCIF) := $(mmcif-obj-y) + +-LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(load-y) -e romstart \ ++LDFLAGS_vmlinux := --oformat $(ld_bfd) -Ttext $(load-y) -e romstart \ + -T $(obj)/../../kernel/vmlinux.lds + + $(obj)/vmlinux: $(obj)/head.o $(obj-y) $(obj)/piggy.o FORCE +@@ -24,7 +24,7 @@ OBJCOPYFLAGS += -j .empty_zero_page + $(obj)/zeropage.bin: vmlinux FORCE + $(call if_changed,objcopy) + +-LDFLAGS_piggy.o := -r --format binary --oformat $(ld-bfd) -T ++LDFLAGS_piggy.o := -r --format binary --oformat $(ld_bfd) -T + + $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/zeropage.bin arch/sh/boot/zImage FORCE + $(call if_changed,ld) diff --git a/debian/patches/bugfix/x86/perf-tools-fix-unwind-build-on-i386.patch b/debian/patches/bugfix/x86/perf-tools-fix-unwind-build-on-i386.patch new file mode 100644 index 000000000..f9baa7bd3 --- /dev/null +++ b/debian/patches/bugfix/x86/perf-tools-fix-unwind-build-on-i386.patch @@ -0,0 +1,35 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Sat, 22 Jul 2017 17:37:33 +0100 +Subject: perf tools: Fix unwind build on i386 +Forwarded: no + +EINVAL may not be defined when building unwind-libunwind.c with +REMOTE_UNWIND_LIBUNWIND, resulting in a compiler error in +LIBUNWIND__ARCH_REG_ID(). Its only caller, access_reg(), only checks +for a negative return value and doesn't care what it is. So change +-EINVAL to -1. + +Fixes: 52ffe0ff02fc ("Support x86(32-bit) cross platform callchain unwind.") +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- + +--- a/tools/perf/arch/x86/util/unwind-libunwind.c ++++ b/tools/perf/arch/x86/util/unwind-libunwind.c +@@ -66,7 +66,7 @@ int LIBUNWIND__ARCH_REG_ID(int regnum) + break; + default: + pr_err("unwind: invalid reg id %d\n", regnum); +- return -EINVAL; ++ return -1; + } + + return id; +@@ -106,7 +106,7 @@ int LIBUNWIND__ARCH_REG_ID(int regnum) + break; + default: + pr_err("unwind: invalid reg id %d\n", regnum); +- return -EINVAL; ++ return -1; + } + + return id; diff --git a/debian/patches/bugfix/x86/revert-perf-build-fix-libunwind-feature-detection-on.patch b/debian/patches/bugfix/x86/revert-perf-build-fix-libunwind-feature-detection-on.patch new file mode 100644 index 000000000..cfbf98e82 --- /dev/null +++ b/debian/patches/bugfix/x86/revert-perf-build-fix-libunwind-feature-detection-on.patch @@ -0,0 +1,22 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Fri, 25 Sep 2015 22:50:50 +0100 +Subject: Revert "perf build: Fix libunwind feature detection on 32-bit x86" +Forwarded: no + +This reverts commit 05b41775e2edd69a83f592e3534930c934d4038e. +It broke feature detection that was working just fine for us. +--- + tools/perf/Makefile.config | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/tools/perf/Makefile.config ++++ b/tools/perf/Makefile.config +@@ -38,7 +38,7 @@ ifeq ($(SRCARCH),x86) + LIBUNWIND_LIBS = -lunwind-x86_64 -lunwind -llzma + $(call detected,CONFIG_X86_64) + else +- LIBUNWIND_LIBS = -lunwind-x86 -llzma -lunwind ++ LIBUNWIND_LIBS = -lunwind -lunwind-x86 + endif + NO_PERF_REGS := 0 + endif diff --git a/debian/patches/bugfix/x86/viafb-autoload-on-olpc-xo1.5-only.patch b/debian/patches/bugfix/x86/viafb-autoload-on-olpc-xo1.5-only.patch new file mode 100644 index 000000000..62b4eb7de --- /dev/null +++ b/debian/patches/bugfix/x86/viafb-autoload-on-olpc-xo1.5-only.patch @@ -0,0 +1,34 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Sat, 20 Apr 2013 15:52:02 +0100 +Subject: viafb: Autoload on OLPC XO 1.5 only +Bug-Debian: https://bugs.debian.org/705788 +Forwarded: no + +It appears that viafb won't work automatically on all the boards for +which it has a PCI device ID match. Currently, it is blacklisted by +udev along with most other framebuffer drivers, so this doesn't matter +much. + +However, this driver is required for console support on the XO 1.5. +We need to allow it to be autoloaded on this model only, and then +un-blacklist it in udev. + +--- +--- a/drivers/video/fbdev/via/via-core.c ++++ b/drivers/video/fbdev/via/via-core.c +@@ -695,7 +695,14 @@ static const struct pci_device_id via_pc + .driver_data = UNICHROME_VX900 }, + { } + }; +-MODULE_DEVICE_TABLE(pci, via_pci_table); ++ ++static const struct pci_device_id via_pci_autoload_table[] __initconst = { ++ /* OLPC XO 1.5 */ ++ { PCI_DEVICE(PCI_VENDOR_ID_VIA, UNICHROME_VX855_DID), ++ .subvendor = 0x152d, .subdevice = 0x0833 }, ++ { } ++}; ++MODULE_DEVICE_TABLE(pci, via_pci_autoload_table); + + static const struct dev_pm_ops via_pm_ops = { + #ifdef CONFIG_PM_SLEEP diff --git a/debian/patches/debian/add-sysctl-to-disallow-unprivileged-CLONE_NEWUSER-by-default.patch b/debian/patches/debian/add-sysctl-to-disallow-unprivileged-CLONE_NEWUSER-by-default.patch new file mode 100644 index 000000000..205510d6b --- /dev/null +++ b/debian/patches/debian/add-sysctl-to-disallow-unprivileged-CLONE_NEWUSER-by-default.patch @@ -0,0 +1,101 @@ +From: Serge Hallyn <serge.hallyn@canonical.com> +Date: Fri, 31 May 2013 19:12:12 +0000 (+0100) +Subject: add sysctl to disallow unprivileged CLONE_NEWUSER by default +Origin: http://kernel.ubuntu.com/git?p=serge%2Fubuntu-saucy.git;a=commit;h=5c847404dcb2e3195ad0057877e1422ae90892b8 + +add sysctl to disallow unprivileged CLONE_NEWUSER by default + +This is a short-term patch. Unprivileged use of CLONE_NEWUSER +is certainly an intended feature of user namespaces. However +for at least saucy we want to make sure that, if any security +issues are found, we have a fail-safe. + +Signed-off-by: Serge Hallyn <serge.hallyn@ubuntu.com> +[bwh: Remove unneeded binary sysctl bits] +[bwh: Keep this sysctl, but change the default to enabled] +--- +Index: linux/kernel/fork.c +=================================================================== +--- linux.orig/kernel/fork.c ++++ linux/kernel/fork.c +@@ -108,6 +108,11 @@ + + #define CREATE_TRACE_POINTS + #include <trace/events/task.h> ++#ifdef CONFIG_USER_NS ++extern int unprivileged_userns_clone; ++#else ++#define unprivileged_userns_clone 0 ++#endif + + /* + * Minimum number of threads to boot the kernel +@@ -2008,6 +2013,10 @@ static __latent_entropy struct task_stru + if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) + return ERR_PTR(-EINVAL); + ++ if ((clone_flags & CLONE_NEWUSER) && !unprivileged_userns_clone) ++ if (!capable(CAP_SYS_ADMIN)) ++ return ERR_PTR(-EPERM); ++ + /* + * Thread groups must share signals as well, and detached threads + * can only be started up within the thread group. +@@ -3166,6 +3175,12 @@ int ksys_unshare(unsigned long unshare_f + if (unshare_flags & CLONE_NEWNS) + unshare_flags |= CLONE_FS; + ++ if ((unshare_flags & CLONE_NEWUSER) && !unprivileged_userns_clone) { ++ err = -EPERM; ++ if (!capable(CAP_SYS_ADMIN)) ++ goto bad_unshare_out; ++ } ++ + err = check_unshare_flags(unshare_flags); + if (err) + goto bad_unshare_out; +Index: linux/kernel/sysctl.c +=================================================================== +--- linux.orig/kernel/sysctl.c ++++ linux/kernel/sysctl.c +@@ -136,6 +136,10 @@ static enum sysctl_writes_mode sysctl_wr + int sysctl_legacy_va_layout; + #endif + ++#ifdef CONFIG_USER_NS ++extern int unprivileged_userns_clone; ++#endif ++ + #endif /* CONFIG_SYSCTL */ + + /* +@@ -1659,6 +1663,15 @@ static struct ctl_table kern_table[] = { + .mode = 0644, + .proc_handler = proc_dointvec, + }, ++#ifdef CONFIG_USER_NS ++ { ++ .procname = "unprivileged_userns_clone", ++ .data = &unprivileged_userns_clone, ++ .maxlen = sizeof(int), ++ .mode = 0644, ++ .proc_handler = proc_dointvec, ++ }, ++#endif + #ifdef CONFIG_PROC_SYSCTL + { + .procname = "tainted", +Index: linux/kernel/user_namespace.c +=================================================================== +--- linux.orig/kernel/user_namespace.c ++++ linux/kernel/user_namespace.c +@@ -22,6 +22,9 @@ + #include <linux/bsearch.h> + #include <linux/sort.h> + ++/* sysctl */ ++int unprivileged_userns_clone = 1; ++ + static struct kmem_cache *user_ns_cachep __read_mostly; + static DEFINE_MUTEX(userns_state_mutex); + diff --git a/debian/patches/debian/af_802154-Disable-auto-loading-as-mitigation-against.patch b/debian/patches/debian/af_802154-Disable-auto-loading-as-mitigation-against.patch new file mode 100644 index 000000000..3b33f845a --- /dev/null +++ b/debian/patches/debian/af_802154-Disable-auto-loading-as-mitigation-against.patch @@ -0,0 +1,29 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Fri, 19 Nov 2010 02:12:48 +0000 +Subject: [PATCH 2/3] af_802154: Disable auto-loading as mitigation against local exploits +Forwarded: not-needed + +Recent review has revealed several bugs in obscure protocol +implementations that can be exploited by local users for denial of +service or privilege escalation. We can mitigate the effect of any +remaining vulnerabilities in such protocols by preventing unprivileged +users from loading the modules, so that they are only exploitable on +systems where the administrator has chosen to load the protocol. + +The 'af_802154' (IEEE 802.15.4) protocol is not widely used, was +not present in the 'lenny' kernel, and seems to receive only sporadic +maintenance. Therefore disable auto-loading. + +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- + net/ieee802154/socket.c | 2 +- + 1 files changed, 1 insertions(+), 1 deletions(-) + +--- a/net/ieee802154/socket.c ++++ b/net/ieee802154/socket.c +@@ -1122,4 +1122,4 @@ module_init(af_ieee802154_init); + module_exit(af_ieee802154_remove); + + MODULE_LICENSE("GPL"); +-MODULE_ALIAS_NETPROTO(PF_IEEE802154); ++/* MODULE_ALIAS_NETPROTO(PF_IEEE802154); */ diff --git a/debian/patches/debian/android-enable-building-ashmem-and-binder-as-modules.patch b/debian/patches/debian/android-enable-building-ashmem-and-binder-as-modules.patch new file mode 100644 index 000000000..8a565c6c0 --- /dev/null +++ b/debian/patches/debian/android-enable-building-ashmem-and-binder-as-modules.patch @@ -0,0 +1,62 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Fri, 22 Jun 2018 17:27:00 +0100 +Subject: android: Enable building ashmem and binder as modules +Bug-Debian: https://bugs.debian.org/901492 + +We want to enable use of the Android ashmem and binder drivers to +support Anbox, but they should not be built-in as that would waste +resources and increase security attack surface on systems that don't +need them. + +- Add a MODULE_LICENSE declaration to ashmem +- Change the Makefiles to build each driver as an object with the + "_linux" suffix (which is what Anbox expects) +- Change config symbol types to tristate + +Update: +In upstream commit 721412ed3d titled "staging: remove ashmem" the ashmem +driver was removed entirely. Secondary commit message: +"The mainline replacement for ashmem is memfd, so remove the legacy +code from drivers/staging/" +Consequently, the ashmem part of this patch has been removed. +--- + drivers/android/Kconfig | 2 +- + drivers/android/Makefile | 7 ++++--- + drivers/android/binder_alloc.c | 2 +- + 3 files changed, 6 insertions(+), 5 deletions(-) + +--- a/drivers/android/Kconfig ++++ b/drivers/android/Kconfig +@@ -2,7 +2,7 @@ + menu "Android" + + config ANDROID_BINDER_IPC +- bool "Android Binder IPC Driver" ++ tristate "Android Binder IPC Driver" + depends on MMU + default n + help +--- a/drivers/android/Makefile ++++ b/drivers/android/Makefile +@@ -1,6 +1,7 @@ + # SPDX-License-Identifier: GPL-2.0-only + ccflags-y += -I$(src) # needed for trace events + +-obj-$(CONFIG_ANDROID_BINDERFS) += binderfs.o +-obj-$(CONFIG_ANDROID_BINDER_IPC) += binder.o binder_alloc.o +-obj-$(CONFIG_ANDROID_BINDER_IPC_SELFTEST) += binder_alloc_selftest.o ++obj-$(CONFIG_ANDROID_BINDER_IPC) += binder_linux.o ++binder_linux-y := binder.o binder_alloc.o ++binder_linux-$(CONFIG_ANDROID_BINDERFS) += binderfs.o ++binder_linux-$(CONFIG_ANDROID_BINDER_IPC_SELFTEST) += binder_alloc_selftest.o +--- a/drivers/android/binder_alloc.c ++++ b/drivers/android/binder_alloc.c +@@ -38,7 +38,7 @@ enum { + }; + static uint32_t binder_alloc_debug_mask = BINDER_DEBUG_USER_ERROR; + +-module_param_named(debug_mask, binder_alloc_debug_mask, ++module_param_named(alloc_debug_mask, binder_alloc_debug_mask, + uint, 0644); + + #define binder_alloc_debug(mask, x...) \ diff --git a/debian/patches/debian/arch-sh4-fix-uimage-build.patch b/debian/patches/debian/arch-sh4-fix-uimage-build.patch new file mode 100644 index 000000000..89e626b6b --- /dev/null +++ b/debian/patches/debian/arch-sh4-fix-uimage-build.patch @@ -0,0 +1,26 @@ +From: Nobuhiro Iwamatsu <iwamatsu@nigauri.org> +Subject: [sh4] Fix uImage build +Bug-Debian: https://bugs.debian.org/569034 +Forwarded: not-needed + +[bwh: This was added without a description, but I think it is done + only to avoid a build-dependency on u-boot-tools.] +--- + arch/sh/Makefile | 1 - + 1 file changed, 1 deletion(-) + +diff --git a/arch/sh/Makefile b/arch/sh/Makefile +index da9cf952f33c..974bbd9dcfcf 100644 +--- a/arch/sh/Makefile ++++ b/arch/sh/Makefile +@@ -85,7 +85,6 @@ OBJCOPYFLAGS := -O binary -R .note -R .note.gnu.build-id -R .comment \ + + # Give the various platforms the opportunity to set default image types + defaultimage-y := zImage +-defaultimage-$(CONFIG_SH_SH7785LCR) := uImage + defaultimage-$(CONFIG_SH_RSK) := uImage + defaultimage-$(CONFIG_SH_URQUELL) := uImage + defaultimage-$(CONFIG_SH_MIGOR) := uImage +-- +2.27.0 + diff --git a/debian/patches/debian/btrfs-warn-about-raid5-6-being-experimental-at-mount.patch b/debian/patches/debian/btrfs-warn-about-raid5-6-being-experimental-at-mount.patch new file mode 100644 index 000000000..9f21e0705 --- /dev/null +++ b/debian/patches/debian/btrfs-warn-about-raid5-6-being-experimental-at-mount.patch @@ -0,0 +1,35 @@ +From: Adam Borowski <kilobyte@angband.pl> +Date: Tue, 28 Mar 2017 16:55:05 +0200 +Subject: btrfs: warn about RAID5/6 being experimental at mount time +Bug-Debian: https://bugs.debian.org/863290 +Origin: https://bugs.debian.org/863290#5 + +Too many people come complaining about losing their data -- and indeed, +there's no warning outside a wiki and the mailing list tribal knowledge. +Message severity chosen for consistency with XFS -- "alert" makes dmesg +produce nice red background which should get the point across. + +Signed-off-by: Adam Borowski <kilobyte@angband.pl> +[bwh: Also add_taint() so this is flagged in bug reports] +--- + fs/btrfs/disk-io.c | 8 ++++++++ + 1 file changed, 8 insertions(+) + +--- a/fs/btrfs/disk-io.c ++++ b/fs/btrfs/disk-io.c +@@ -3060,6 +3060,15 @@ retry_root_backup: + btrfs_set_and_info(fs_info, SSD, "enabling ssd optimizations"); + } + ++ if ((fs_info->avail_data_alloc_bits | ++ fs_info->avail_metadata_alloc_bits | ++ fs_info->avail_system_alloc_bits) & ++ BTRFS_BLOCK_GROUP_RAID56_MASK) { ++ btrfs_alert(fs_info, ++ "btrfs RAID5/6 is EXPERIMENTAL and has known data-loss bugs"); ++ add_taint(TAINT_AUX, LOCKDEP_STILL_OK); ++ } ++ + /* + * Mount does not set all options immediately, we can do it now and do + * not have to wait for transaction commit diff --git a/debian/patches/debian/cdc_ncm-cdc_mbim-use-ncm-by-default.patch b/debian/patches/debian/cdc_ncm-cdc_mbim-use-ncm-by-default.patch new file mode 100644 index 000000000..70b446860 --- /dev/null +++ b/debian/patches/debian/cdc_ncm-cdc_mbim-use-ncm-by-default.patch @@ -0,0 +1,27 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Subject: cdc_ncm,cdc_mbim: Use NCM by default +Date: Sun, 31 Mar 2013 03:58:04 +0100 +Forwarded: not-needed + +Devices that support both NCM and MBIM modes should be kept in NCM +mode unless there is userland support for MBIM. + +Set the default value of cdc_ncm.prefer_mbim to false and leave it to +userland (modem-manager) to override this with a modprobe.conf file +once it's ready to speak MBIM. + +--- +--- a/drivers/net/usb/cdc_ncm.c ++++ b/drivers/net/usb/cdc_ncm.c +@@ -53,11 +53,7 @@ + #include <linux/usb/cdc.h> + #include <linux/usb/cdc_ncm.h> + +-#if IS_ENABLED(CONFIG_USB_NET_CDC_MBIM) +-static bool prefer_mbim = true; +-#else + static bool prefer_mbim; +-#endif + module_param(prefer_mbim, bool, 0644); + MODULE_PARM_DESC(prefer_mbim, "Prefer MBIM setting on dual NCM/MBIM functions"); + diff --git a/debian/patches/debian/dccp-disable-auto-loading-as-mitigation-against-local-exploits.patch b/debian/patches/debian/dccp-disable-auto-loading-as-mitigation-against-local-exploits.patch new file mode 100644 index 000000000..83583184e --- /dev/null +++ b/debian/patches/debian/dccp-disable-auto-loading-as-mitigation-against-local-exploits.patch @@ -0,0 +1,41 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Thu, 16 Feb 2017 19:09:17 +0000 +Subject: dccp: Disable auto-loading as mitigation against local exploits +Forwarded: not-needed + +We can mitigate the effect of vulnerabilities in obscure protocols by +preventing unprivileged users from loading the modules, so that they +are only exploitable on systems where the administrator has chosen to +load the protocol. + +The 'dccp' protocol is not actively maintained or widely used. +Therefore disable auto-loading. + +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- +--- a/net/dccp/ipv4.c ++++ b/net/dccp/ipv4.c +@@ -1071,8 +1071,8 @@ module_exit(dccp_v4_exit); + * values directly, Also cover the case where the protocol is not specified, + * i.e. net-pf-PF_INET-proto-0-type-SOCK_DCCP + */ +-MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 33, 6); +-MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 0, 6); ++/* MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 33, 6); */ ++/* MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 0, 6); */ + MODULE_LICENSE("GPL"); + MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>"); + MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol"); +--- a/net/dccp/ipv6.c ++++ b/net/dccp/ipv6.c +@@ -1125,8 +1125,8 @@ module_exit(dccp_v6_exit); + * values directly, Also cover the case where the protocol is not specified, + * i.e. net-pf-PF_INET6-proto-0-type-SOCK_DCCP + */ +-MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 33, 6); +-MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 0, 6); ++/* MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 33, 6); */ ++/* MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 0, 6); */ + MODULE_LICENSE("GPL"); + MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>"); + MODULE_DESCRIPTION("DCCPv6 - Datagram Congestion Controlled Protocol"); diff --git a/debian/patches/debian/dfsg/arch-powerpc-platforms-8xx-ucode-disable.patch b/debian/patches/debian/dfsg/arch-powerpc-platforms-8xx-ucode-disable.patch new file mode 100644 index 000000000..0e5176908 --- /dev/null +++ b/debian/patches/debian/dfsg/arch-powerpc-platforms-8xx-ucode-disable.patch @@ -0,0 +1,29 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Mon, 13 Apr 2009 17:34:00 +0100 +Subject: Remove microcode patches for mgsuvd (not enabled in Debian configs) +Forwarded: not-needed + +diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig +index 48a920a..81570b6 100644 +--- a/arch/powerpc/platforms/8xx/Kconfig ++++ b/arch/powerpc/platforms/8xx/Kconfig +@@ -160,16 +160,19 @@ config NO_UCODE_PATCH + + config USB_SOF_UCODE_PATCH + bool "USB SOF patch" ++ depends on BROKEN + help + Help not implemented yet, coming soon. + + config I2C_SPI_UCODE_PATCH + bool "I2C/SPI relocation patch" ++ depends on BROKEN + help + Help not implemented yet, coming soon. + + config I2C_SPI_SMC1_UCODE_PATCH + bool "I2C/SPI/SMC1 relocation patch" ++ depends on BROKEN + help + Help not implemented yet, coming soon. + diff --git a/debian/patches/debian/dfsg/documentation-fix-broken-link-to-cipso-draft.patch b/debian/patches/debian/dfsg/documentation-fix-broken-link-to-cipso-draft.patch new file mode 100644 index 000000000..840cf24d7 --- /dev/null +++ b/debian/patches/debian/dfsg/documentation-fix-broken-link-to-cipso-draft.patch @@ -0,0 +1,18 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Sat, 24 Aug 2019 19:00:41 +0100 +Subject: Documentation: Fix broken link to CIPSO draft +Forwarded: not-needed + +We exclude the CIPSO draft text as its licence is not DFSG compliant. +Link to the IETF's online version instead. + +--- +--- a/Documentation/netlabel/draft_ietf.rst ++++ b/Documentation/netlabel/draft_ietf.rst +@@ -1,5 +1,4 @@ + Draft IETF CIPSO IP Security + ---------------------------- + +- .. include:: draft-ietf-cipso-ipsecurity-01.txt +- :literal: ++https://tools.ietf.org/html/draft-ietf-cipso-ipsecurity-01 diff --git a/debian/patches/debian/dfsg/drivers-media-dvb-dvb-usb-af9005-disable.patch b/debian/patches/debian/dfsg/drivers-media-dvb-dvb-usb-af9005-disable.patch new file mode 100644 index 000000000..4e42da9a9 --- /dev/null +++ b/debian/patches/debian/dfsg/drivers-media-dvb-dvb-usb-af9005-disable.patch @@ -0,0 +1,15 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Mon, 17 Aug 2009 02:45:41 +0100 +Subject: dvb-usb-af9005: mark as broken +Forwarded: not-needed + +--- a/drivers/media/usb/dvb-usb/Kconfig ++++ b/drivers/media/usb/dvb-usb/Kconfig +@@ -227,6 +227,7 @@ config DVB_USB_OPERA1 + + config DVB_USB_AF9005 + tristate "Afatech AF9005 DVB-T USB1.1 support" ++ depends on BROKEN + depends on DVB_USB + select MEDIA_TUNER_MT2060 if MEDIA_SUBDRV_AUTOSELECT + select MEDIA_TUNER_QT1010 if MEDIA_SUBDRV_AUTOSELECT diff --git a/debian/patches/debian/dfsg/drivers-net-appletalk-cops.patch b/debian/patches/debian/dfsg/drivers-net-appletalk-cops.patch new file mode 100644 index 000000000..3bf7ca6b3 --- /dev/null +++ b/debian/patches/debian/dfsg/drivers-net-appletalk-cops.patch @@ -0,0 +1,55 @@ +From: Frederik Schüler <fs@debian.org> +Date: Fri, 05 Jan 2007 15:55:24 +0000 +Subject: Add removal patches for: 3c359, smctr, keyspan, cops +Forwarded: not-needed + +--- + drivers/net/appletalk/Kconfig | 26 -------------------------- + drivers/net/appletalk/Makefile | 1 - + 2 files changed, 27 deletions(-) + +--- a/drivers/net/appletalk/Kconfig ++++ b/drivers/net/appletalk/Kconfig +@@ -39,35 +39,6 @@ config DEV_APPLETALK + connect to the AppleTalk network, say Y. + + +-config COPS +- tristate "COPS LocalTalk PC support" +- depends on DEV_APPLETALK && ISA +- depends on NETDEVICES +- select NETDEV_LEGACY_INIT +- help +- This allows you to use COPS AppleTalk cards to connect to LocalTalk +- networks. You also need version 1.3.3 or later of the netatalk +- package. This driver is experimental, which means that it may not +- work. This driver will only work if you choose "AppleTalk DDP" +- networking support, above. +- Please read the file +- <file:Documentation/networking/device_drivers/appletalk/cops.rst>. +- +-config COPS_DAYNA +- bool "Dayna firmware support" +- depends on COPS +- help +- Support COPS compatible cards with Dayna style firmware (Dayna +- DL2000/ Daynatalk/PC (half length), COPS LT-95, Farallon PhoneNET PC +- III, Farallon PhoneNET PC II). +- +-config COPS_TANGENT +- bool "Tangent firmware support" +- depends on COPS +- help +- Support COPS compatible cards with Tangent style firmware (Tangent +- ATB_II, Novell NL-1000, Daystar Digital LT-200. +- + config IPDDP + tristate "Appletalk-IP driver support" + depends on DEV_APPLETALK && ATALK +--- a/drivers/net/appletalk/Makefile ++++ b/drivers/net/appletalk/Makefile +@@ -4,4 +4,3 @@ + # + + obj-$(CONFIG_IPDDP) += ipddp.o +-obj-$(CONFIG_COPS) += cops.o diff --git a/debian/patches/debian/dfsg/video-remove-nvidiafb-and-rivafb.patch b/debian/patches/debian/dfsg/video-remove-nvidiafb-and-rivafb.patch new file mode 100644 index 000000000..4adc90c2d --- /dev/null +++ b/debian/patches/debian/dfsg/video-remove-nvidiafb-and-rivafb.patch @@ -0,0 +1,128 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Sat, 2 Jun 2012 19:53:38 +0100 +Subject: video: Remove nvidiafb and rivafb +Bug-Debian: https://bugs.debian.org/383481 +Forwarded: no + +These drivers contain register programming code provided by the +hardware vendor that appears to have been deliberately obfuscated. +This is arguably not the preferred form for modification. + +These drivers are also largely redundant with nouveau. The RIVA 128 +(NV3) is not supported by nouveau but is about 15 years old and +probably discontinued 10 years ago. + +--- +--- a/drivers/video/fbdev/Kconfig ++++ b/drivers/video/fbdev/Kconfig +@@ -866,99 +866,6 @@ config FB_ATMEL + help + This enables support for the AT91 LCD Controller. + +-config FB_NVIDIA +- tristate "nVidia Framebuffer Support" +- depends on FB && PCI +- select FB_BACKLIGHT if FB_NVIDIA_BACKLIGHT +- select FB_MODE_HELPERS +- select FB_CFB_FILLRECT +- select FB_CFB_COPYAREA +- select FB_CFB_IMAGEBLIT +- select BITREVERSE +- select VGASTATE +- help +- This driver supports graphics boards with the nVidia chips, TNT +- and newer. For very old chipsets, such as the RIVA128, then use +- the rivafb. +- Say Y if you have such a graphics board. +- +- To compile this driver as a module, choose M here: the +- module will be called nvidiafb. +- +-config FB_NVIDIA_I2C +- bool "Enable DDC Support" +- depends on FB_NVIDIA +- select FB_DDC +- help +- This enables I2C support for nVidia Chipsets. This is used +- only for getting EDID information from the attached display +- allowing for robust video mode handling and switching. +- +- Because fbdev-2.6 requires that drivers must be able to +- independently validate video mode parameters, you should say Y +- here. +- +-config FB_NVIDIA_DEBUG +- bool "Lots of debug output" +- depends on FB_NVIDIA +- help +- Say Y here if you want the nVidia driver to output all sorts +- of debugging information to provide to the maintainer when +- something goes wrong. +- +-config FB_NVIDIA_BACKLIGHT +- bool "Support for backlight control" +- depends on FB_NVIDIA +- default y +- help +- Say Y here if you want to control the backlight of your display. +- +-config FB_RIVA +- tristate "nVidia Riva support" +- depends on FB && PCI +- select FB_BACKLIGHT if FB_RIVA_BACKLIGHT +- select FB_MODE_HELPERS +- select FB_CFB_FILLRECT +- select FB_CFB_COPYAREA +- select FB_CFB_IMAGEBLIT +- select BITREVERSE +- select VGASTATE +- help +- This driver supports graphics boards with the nVidia Riva/Geforce +- chips. +- Say Y if you have such a graphics board. +- +- To compile this driver as a module, choose M here: the +- module will be called rivafb. +- +-config FB_RIVA_I2C +- bool "Enable DDC Support" +- depends on FB_RIVA +- select FB_DDC +- help +- This enables I2C support for nVidia Chipsets. This is used +- only for getting EDID information from the attached display +- allowing for robust video mode handling and switching. +- +- Because fbdev-2.6 requires that drivers must be able to +- independently validate video mode parameters, you should say Y +- here. +- +-config FB_RIVA_DEBUG +- bool "Lots of debug output" +- depends on FB_RIVA +- help +- Say Y here if you want the Riva driver to output all sorts +- of debugging information to provide to the maintainer when +- something goes wrong. +- +-config FB_RIVA_BACKLIGHT +- bool "Support for backlight control" +- depends on FB_RIVA +- default y +- help +- Say Y here if you want to control the backlight of your display. +- + config FB_I740 + tristate "Intel740 support" + depends on FB && PCI +--- a/drivers/video/fbdev/Makefile ++++ b/drivers/video/fbdev/Makefile +@@ -21,8 +21,6 @@ obj-$(CONFIG_FB_PM3) += pm3fb.o + + obj-$(CONFIG_FB_I740) += i740fb.o + obj-$(CONFIG_FB_MATROX) += matrox/ +-obj-$(CONFIG_FB_RIVA) += riva/ +-obj-$(CONFIG_FB_NVIDIA) += nvidia/ + obj-$(CONFIG_FB_ATY) += aty/ macmodes.o + obj-$(CONFIG_FB_ATY128) += aty/ macmodes.o + obj-$(CONFIG_FB_RADEON) += aty/ diff --git a/debian/patches/debian/dfsg/vs6624-disable.patch b/debian/patches/debian/dfsg/vs6624-disable.patch new file mode 100644 index 000000000..182be87d3 --- /dev/null +++ b/debian/patches/debian/dfsg/vs6624-disable.patch @@ -0,0 +1,19 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Sun, 27 May 2012 01:56:58 +0100 +Subject: vs6624: mark as broken +Forwarded: not-needed + +--- + drivers/media/i2c/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +--- a/drivers/media/i2c/Kconfig ++++ b/drivers/media/i2c/Kconfig +@@ -754,6 +754,7 @@ config VIDEO_SR030PC30 + This driver supports SR030PC30 VGA camera from Siliconfile + + config VIDEO_VS6624 ++ depends on BROKEN + tristate "ST VS6624 sensor support" + depends on VIDEO_DEV && I2C + help diff --git a/debian/patches/debian/documentation-drop-sphinx-version-check.patch b/debian/patches/debian/documentation-drop-sphinx-version-check.patch new file mode 100644 index 000000000..14f0ee40b --- /dev/null +++ b/debian/patches/debian/documentation-drop-sphinx-version-check.patch @@ -0,0 +1,47 @@ +From 252aa79fdbd4ac2da09d9b98f81bf11f5e3e1870 Mon Sep 17 00:00:00 2001 +From: Bastian Blank <waldi@debian.org> +Date: Tue, 4 Aug 2020 09:44:19 +0000 +Subject: [PATCH 1/2] Documentation: Drop sphinx version check +Forwarded: not-needed + +--- + Documentation/Makefile | 5 ----- + 1 file changed, 5 deletions(-) + +--- a/Documentation/Makefile ++++ b/Documentation/Makefile +@@ -92,14 +92,12 @@ quiet_cmd_sphinx = SPHINX $@ --> file:/ + fi + + htmldocs: +- @$(srctree)/scripts/sphinx-pre-install --version-check + @+$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,html,$(var),,$(var))) + + linkcheckdocs: + @$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,linkcheck,$(var),,$(var))) + + latexdocs: +- @$(srctree)/scripts/sphinx-pre-install --version-check + @+$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,latex,$(var),latex,$(var))) + + ifeq ($(HAVE_PDFLATEX),0) +@@ -111,7 +109,6 @@ pdfdocs: + else # HAVE_PDFLATEX + + pdfdocs: latexdocs +- @$(srctree)/scripts/sphinx-pre-install --version-check + $(foreach var,$(SPHINXDIRS), \ + $(MAKE) PDFLATEX="$(PDFLATEX)" LATEXOPTS="$(LATEXOPTS)" -C $(BUILDDIR)/$(var)/latex || exit; \ + mkdir -p $(BUILDDIR)/$(var)/pdf; \ +@@ -121,11 +118,9 @@ pdfdocs: latexdocs + endif # HAVE_PDFLATEX + + epubdocs: +- @$(srctree)/scripts/sphinx-pre-install --version-check + @+$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,epub,$(var),epub,$(var))) + + xmldocs: +- @$(srctree)/scripts/sphinx-pre-install --version-check + @+$(foreach var,$(SPHINXDIRS),$(call loop_cmd,sphinx,xml,$(var),xml,$(var))) + + endif # HAVE_SPHINX diff --git a/debian/patches/debian/export-symbols-needed-by-android-drivers.patch b/debian/patches/debian/export-symbols-needed-by-android-drivers.patch new file mode 100644 index 000000000..860812230 --- /dev/null +++ b/debian/patches/debian/export-symbols-needed-by-android-drivers.patch @@ -0,0 +1,113 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Mon, 07 Sep 2020 02:51:53 +0100 +Subject: Export symbols needed by Android drivers +Bug-Debian: https://bugs.debian.org/901492 + +We want to enable use of the Android ashmem and binder drivers to +support Anbox, but they should not be built-in as that would waste +resources and increase security attack surface on systems that don't +need them. + +Export the currently un-exported symbols they depend on. + +--- + fs/file.c | 1 + + kernel/sched/core.c | 1 + + kernel/sched/wait.c | 1 + + kernel/task_work.c | 1 + + mm/memory.c | 1 + + mm/shmem.c | 1 + + security/security.c | 4 ++++ + 7 files changed, 10 insertions(+) + +--- a/fs/file.c ++++ b/fs/file.c +@@ -813,6 +813,7 @@ struct file *close_fd_get_file(unsigned + + return file; + } ++EXPORT_SYMBOL_GPL(close_fd_get_file); + + void do_close_on_exec(struct files_struct *files) + { +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7052,6 +7052,7 @@ static bool is_nice_reduction(const stru + + return (nice_rlim <= task_rlimit(p, RLIMIT_NICE)); + } ++EXPORT_SYMBOL_GPL(can_nice); + + /* + * can_nice - check if a task can reduce its nice value +--- a/kernel/sched/wait.c ++++ b/kernel/sched/wait.c +@@ -243,6 +243,7 @@ void __wake_up_pollfree(struct wait_queu + /* POLLFREE must have cleared the queue. */ + WARN_ON_ONCE(waitqueue_active(wq_head)); + } ++EXPORT_SYMBOL_GPL(__wake_up_pollfree); + + /* + * Note: we use "set_current_state()" _after_ the wait-queue add, +--- a/kernel/task_work.c ++++ b/kernel/task_work.c +@@ -73,6 +73,7 @@ int task_work_add(struct task_struct *ta + + return 0; + } ++EXPORT_SYMBOL_GPL(task_work_add); + + /** + * task_work_cancel_match - cancel a pending work added by task_work_add() +--- a/mm/memory.c ++++ b/mm/memory.c +@@ -1757,6 +1757,7 @@ void zap_page_range(struct vm_area_struc + mmu_notifier_invalidate_range_end(&range); + tlb_finish_mmu(&tlb); + } ++EXPORT_SYMBOL_GPL(zap_page_range); + + /** + * zap_page_range_single - remove user pages in a given range +--- a/mm/shmem.c ++++ b/mm/shmem.c +@@ -4245,6 +4245,7 @@ int shmem_zero_setup(struct vm_area_stru + + return 0; + } ++EXPORT_SYMBOL_GPL(shmem_zero_setup); + + /** + * shmem_read_mapping_page_gfp - read into page cache, using specified page allocation flags. +--- a/security/security.c ++++ b/security/security.c +@@ -752,24 +752,28 @@ int security_binder_set_context_mgr(cons + { + return call_int_hook(binder_set_context_mgr, 0, mgr); + } ++EXPORT_SYMBOL_GPL(security_binder_set_context_mgr); + + int security_binder_transaction(const struct cred *from, + const struct cred *to) + { + return call_int_hook(binder_transaction, 0, from, to); + } ++EXPORT_SYMBOL_GPL(security_binder_transaction); + + int security_binder_transfer_binder(const struct cred *from, + const struct cred *to) + { + return call_int_hook(binder_transfer_binder, 0, from, to); + } ++EXPORT_SYMBOL_GPL(security_binder_transfer_binder); + + int security_binder_transfer_file(const struct cred *from, + const struct cred *to, struct file *file) + { + return call_int_hook(binder_transfer_file, 0, from, to, file); + } ++EXPORT_SYMBOL_GPL(security_binder_transfer_file); + + int security_ptrace_access_check(struct task_struct *child, unsigned int mode) + { diff --git a/debian/patches/debian/fanotify-taint-on-use-of-fanotify_access_permissions.patch b/debian/patches/debian/fanotify-taint-on-use-of-fanotify_access_permissions.patch new file mode 100644 index 000000000..88a2b15b3 --- /dev/null +++ b/debian/patches/debian/fanotify-taint-on-use-of-fanotify_access_permissions.patch @@ -0,0 +1,29 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Subject: fanotify: Taint on use of FANOTIFY_ACCESS_PERMISSIONS +Date: Wed, 13 Jul 2016 01:37:22 +0100 +Forwarded: not-needed + +Various free and proprietary AV products use this feature and users +apparently want it. But punting access checks to userland seems like +an easy way to deadlock the system, and there will be nothing we can +do about that. So warn and taint the kernel if this feature is +actually used. + +--- +--- a/fs/notify/fanotify/fanotify_user.c ++++ b/fs/notify/fanotify/fanotify_user.c +@@ -1661,6 +1661,14 @@ static int do_fanotify_mark(int fanotify + umask = FANOTIFY_EVENT_FLAGS; + } + ++#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS ++ if (mask & FANOTIFY_PERM_EVENTS) { ++ pr_warn_once("%s (%d): Using fanotify permission checks may lead to deadlock; tainting kernel\n", ++ current->comm, current->pid); ++ add_taint(TAINT_AUX, LOCKDEP_STILL_OK); ++ } ++#endif ++ + f = fdget(fanotify_fd); + if (unlikely(!f.file)) + return -EBADF; diff --git a/debian/patches/debian/firmware_class-refer-to-debian-wiki-firmware-page.patch b/debian/patches/debian/firmware_class-refer-to-debian-wiki-firmware-page.patch new file mode 100644 index 000000000..27bc69903 --- /dev/null +++ b/debian/patches/debian/firmware_class-refer-to-debian-wiki-firmware-page.patch @@ -0,0 +1,52 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Mon, 12 Mar 2018 01:14:03 +0000 +Subject: firmware_class: Refer to Debian wiki page when logging missing firmware +Bug-Debian: https://bugs.debian.org/888405 +Forwarded: not-needed + +If firmware loading fails due to a missing file, log a second error +message referring to our wiki page about firmware. This will explain +why some firmware is in non-free, or can't be packaged at all. Only +do this once per boot. + +Do something similar in the radeon and amdgpu drivers, where we have +an early check to avoid failing at a point where we cannot display +anything. + +--- +--- a/drivers/base/firmware_loader/main.c ++++ b/drivers/base/firmware_loader/main.c +@@ -334,9 +334,12 @@ fw_get_filesystem_firmware(struct device + } + __putname(path); + +- if (rc) ++ if (rc) { + dev_err(device, "firmware: failed to load %s (%d)\n", + fw_priv->fw_name, rc); ++ if (rc == -ENOENT) ++ pr_err_once("See https://wiki.debian.org/Firmware for information about missing firmware\n"); ++ } + + return rc; + } +--- a/drivers/gpu/drm/radeon/radeon_drv.c ++++ b/drivers/gpu/drm/radeon/radeon_drv.c +@@ -367,6 +367,7 @@ static int radeon_pci_probe(struct pci_d + if ((ent->driver_data & RADEON_FAMILY_MASK) >= CHIP_R600 && + !radeon_firmware_installed()) { + DRM_ERROR("radeon kernel modesetting for R600 or later requires firmware installed\n"); ++ pr_err_once("See https://wiki.debian.org/Firmware for information about missing firmware\n"); + return -ENODEV; + } + +--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c ++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +@@ -626,6 +626,7 @@ static int amdgpu_pci_probe(struct pci_d + + if (!amdgpu_firmware_installed()) { + DRM_ERROR("amdgpu requires firmware installed\n"); ++ pr_err_once("See https://wiki.debian.org/Firmware for information about missing firmware\n"); + return -ENODEV; + } + diff --git a/debian/patches/debian/fjes-disable-autoload.patch b/debian/patches/debian/fjes-disable-autoload.patch new file mode 100644 index 000000000..873c6906e --- /dev/null +++ b/debian/patches/debian/fjes-disable-autoload.patch @@ -0,0 +1,26 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Sat, 18 Mar 2017 20:47:58 +0000 +Subject: fjes: Disable auto-loading +Bug-Debian: https://bugs.debian.org/853976 +Forwarded: no + +fjes matches a generic ACPI device ID, and relies on its probe +function to distinguish whether that really corresponds to a supported +device. Very few system will need the driver and it wastes memory on +all the other systems where the same device ID appears, so disable +auto-loading. + +--- +Index: linux/drivers/net/fjes/fjes_main.c +=================================================================== +--- linux.orig/drivers/net/fjes/fjes_main.c ++++ linux/drivers/net/fjes/fjes_main.c +@@ -36,7 +36,7 @@ static const struct acpi_device_id fjes_ + {ACPI_MOTHERBOARD_RESOURCE_HID, 0}, + {"", 0}, + }; +-MODULE_DEVICE_TABLE(acpi, fjes_acpi_ids); ++/* MODULE_DEVICE_TABLE(acpi, fjes_acpi_ids); */ + + static bool is_extended_socket_device(struct acpi_device *device) + { diff --git a/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch b/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch new file mode 100644 index 000000000..eab0e78ee --- /dev/null +++ b/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch @@ -0,0 +1,22 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Subject: fs: Enable link security restrictions by default +Date: Fri, 02 Nov 2012 05:32:06 +0000 +Bug-Debian: https://bugs.debian.org/609455 +Forwarded: not-needed + +This reverts commit 561ec64ae67ef25cac8d72bb9c4bfc955edfd415 +('VFS: don't do protected {sym,hard}links by default'). + +--- a/fs/namei.c ++++ b/fs/namei.c +@@ -1020,8 +1020,8 @@ static inline void put_link(struct namei + path_put(&last->link); + } + +-static int sysctl_protected_symlinks __read_mostly; +-static int sysctl_protected_hardlinks __read_mostly; ++static int sysctl_protected_symlinks __read_mostly = 1; ++static int sysctl_protected_hardlinks __read_mostly = 1; + static int sysctl_protected_fifos __read_mostly; + static int sysctl_protected_regular __read_mostly; + diff --git a/debian/patches/debian/gitignore.patch b/debian/patches/debian/gitignore.patch new file mode 100644 index 000000000..f98a51426 --- /dev/null +++ b/debian/patches/debian/gitignore.patch @@ -0,0 +1,52 @@ +From: Ian Campbell <ijc@hellion.org.uk> +Date: Thu, 17 Jan 2013 08:55:21 +0000 +Subject: Tweak gitignore for Debian pkg-kernel using git svn. +Forwarded: not-needed + +[bwh: Tweak further for pure git] + +Index: linux/.gitignore +=================================================================== +--- linux.orig/.gitignore ++++ linux/.gitignore +@@ -76,11 +76,6 @@ modules.order + /*.spec + + # +-# Debian directory (make deb-pkg) +-# +-/debian/ +- +-# + # Snap directory (make snap-pkg) + # + /snap/ +@@ -91,17 +86,6 @@ modules.order + /tar-install/ + + # +-# We don't want to ignore the following even if they are dot-files +-# +-!.clang-format +-!.cocciconfig +-!.get_maintainer.ignore +-!.gitattributes +-!.gitignore +-!.mailmap +-!.rustfmt.toml +- +-# + # Generated include files + # + /include/config/ +@@ -168,3 +152,10 @@ sphinx_*/ + + # Rust analyzer configuration + /rust-project.json ++ ++# ++# Debian packaging: ignore everything at the top level, since it isn't ++# included in our repository ++# ++/* ++!/debian/ diff --git a/debian/patches/debian/hamradio-disable-auto-loading-as-mitigation-against-local-exploits.patch b/debian/patches/debian/hamradio-disable-auto-loading-as-mitigation-against-local-exploits.patch new file mode 100644 index 000000000..b532d0054 --- /dev/null +++ b/debian/patches/debian/hamradio-disable-auto-loading-as-mitigation-against-local-exploits.patch @@ -0,0 +1,48 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Mon, 05 Aug 2019 00:29:11 +0100 +Subject: hamradio: Disable auto-loading as mitigation against local exploits +Forwarded: not-needed + +We can mitigate the effect of vulnerabilities in obscure protocols by +preventing unprivileged users from loading the modules, so that they +are only exploitable on systems where the administrator has chosen to +load the protocol. + +The 'ham' radio protocols (ax25, netrom, rose) are not actively +maintained or widely used. Therefore disable auto-loading. + +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- +--- a/net/ax25/af_ax25.c ++++ b/net/ax25/af_ax25.c +@@ -1986,7 +1986,7 @@ module_init(ax25_init); + MODULE_AUTHOR("Jonathan Naylor G4KLX <g4klx@g4klx.demon.co.uk>"); + MODULE_DESCRIPTION("The amateur radio AX.25 link layer protocol"); + MODULE_LICENSE("GPL"); +-MODULE_ALIAS_NETPROTO(PF_AX25); ++/* MODULE_ALIAS_NETPROTO(PF_AX25); */ + + static void __exit ax25_exit(void) + { +--- a/net/netrom/af_netrom.c ++++ b/net/netrom/af_netrom.c +@@ -1486,7 +1486,7 @@ MODULE_PARM_DESC(nr_ndevs, "number of NE + MODULE_AUTHOR("Jonathan Naylor G4KLX <g4klx@g4klx.demon.co.uk>"); + MODULE_DESCRIPTION("The amateur radio NET/ROM network and transport layer protocol"); + MODULE_LICENSE("GPL"); +-MODULE_ALIAS_NETPROTO(PF_NETROM); ++/* MODULE_ALIAS_NETPROTO(PF_NETROM); */ + + static void __exit nr_exit(void) + { +--- a/net/rose/af_rose.c ++++ b/net/rose/af_rose.c +@@ -1577,7 +1577,7 @@ MODULE_PARM_DESC(rose_ndevs, "number of + MODULE_AUTHOR("Jonathan Naylor G4KLX <g4klx@g4klx.demon.co.uk>"); + MODULE_DESCRIPTION("The amateur radio ROSE network layer protocol"); + MODULE_LICENSE("GPL"); +-MODULE_ALIAS_NETPROTO(PF_ROSE); ++/* MODULE_ALIAS_NETPROTO(PF_ROSE); */ + + static void __exit rose_exit(void) + { diff --git a/debian/patches/debian/i386-686-pae-pci-set-pci-nobios-by-default.patch b/debian/patches/debian/i386-686-pae-pci-set-pci-nobios-by-default.patch new file mode 100644 index 000000000..1b216d0d1 --- /dev/null +++ b/debian/patches/debian/i386-686-pae-pci-set-pci-nobios-by-default.patch @@ -0,0 +1,27 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Tue, 16 Feb 2016 02:45:42 +0000 +Subject: [i386/686-pae] PCI: Set pci=nobios by default +Forwarded: not-needed + +CONFIG_PCI_GOBIOS results in physical addresses 640KB-1MB being mapped +W+X, which is undesirable for security reasons and will result in a +warning at boot now that we enable CONFIG_DEBUG_WX. + +This can be overridden using the kernel parameter "pci=nobios", but we +want to disable W+X by default. Disable PCI BIOS probing by default; +it can still be enabled using "pci=bios". + +--- +--- a/arch/x86/pci/common.c ++++ b/arch/x86/pci/common.c +@@ -21,8 +21,8 @@ + #include <asm/setup.h> + #include <asm/irqdomain.h> + +-unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 | +- PCI_PROBE_MMCONF; ++unsigned int pci_probe = PCI_PROBE_CONF1 | PCI_PROBE_CONF2 | PCI_PROBE_MMCONF | ++ (IS_ENABLED(CONFIG_X86_64) || IS_ENABLED(CONFIG_X86_PAE) ? 0 : PCI_PROBE_BIOS); + + static int pci_bf_sort; + int pci_routeirq; diff --git a/debian/patches/debian/ia64-hardcode-arch-script-output.patch b/debian/patches/debian/ia64-hardcode-arch-script-output.patch new file mode 100644 index 000000000..56fdc4cb4 --- /dev/null +++ b/debian/patches/debian/ia64-hardcode-arch-script-output.patch @@ -0,0 +1,71 @@ +From: dann frazier <dannf@debian.org> +Subject: Hardcode arch script output +Date: Mon, 26 Mar 2007 16:30:51 -0600 +Bug-Debian: https://bugs.debian.org/392592 +Forwarded: not-needed + +Here's a patch that simply uses hardcoded definitions instead of +doing the dynamic tests that require architecture-specific scripts. + +I don't particularly like this approach because it restricts +portability and diverts from upstream. But, it is simpler, and this +really needs to be fixed somehow before etch (along with a rebuild of +linux-modules-extra-2.6), so I'm willing to live with it if my other +patch is deemed unacceptable. + +My primary concern is that, in the future, the output of these scripts +will change and we (or our successors) will either not notice or +forget to update the hardcoded values. + +Including the scripts in linux-kbuild will avoid this manual step +altogether, and allow for the possibility of other archs to provide +their own scripts in the future. +--- + arch/ia64/Makefile | 17 ++--------------- + 1 file changed, 2 insertions(+), 15 deletions(-) + +--- a/arch/ia64/Makefile ++++ b/arch/ia64/Makefile +@@ -26,16 +26,7 @@ cflags-y := -pipe $(EXTRA) -ffixed-r13 - + -falign-functions=32 -frename-registers -fno-optimize-sibling-calls + KBUILD_CFLAGS_KERNEL := -mconstant-gp + +-GAS_STATUS = $(shell $(srctree)/arch/ia64/scripts/check-gas "$(CC)" "$(OBJDUMP)") +-KBUILD_CPPFLAGS += $(shell $(srctree)/arch/ia64/scripts/toolchain-flags "$(CC)" "$(OBJDUMP)" "$(READELF)") +- +-ifeq ($(GAS_STATUS),buggy) +-$(error Sorry, you need a newer version of the assember, one that is built from \ +- a source-tree that post-dates 18-Dec-2002. You can find a pre-compiled \ +- static binary of such an assembler at: \ +- \ +- ftp://ftp.hpl.hp.com/pub/linux-ia64/gas-030124.tar.gz) +-endif ++KBUILD_CPPFLAGS += -DHAVE_WORKING_TEXT_ALIGN -DHAVE_MODEL_SMALL_ATTRIBUTE -DHAVE_SERIALIZE_DIRECTIVE + + quiet_cmd_gzip = GZIP $@ + cmd_gzip = cat $(real-prereqs) | $(KGZIP) -n -f -9 > $@ +@@ -52,7 +43,7 @@ drivers-y += arch/ia64/pci/ arch/ia64/ + + PHONY += compressed check + +-all: compressed unwcheck ++all: compressed + + compressed: vmlinux.gz + +@@ -64,9 +55,6 @@ vmlinux.gz: vmlinux.bin FORCE + vmlinux.bin: vmlinux FORCE + $(call if_changed,objcopy) + +-unwcheck: vmlinux +- -$(Q)READELF=$(READELF) $(PYTHON3) $(srctree)/arch/ia64/scripts/unwcheck.py $< +- + archheaders: + $(Q)$(MAKE) $(build)=arch/ia64/kernel/syscalls all + +@@ -78,5 +66,4 @@ install: vmlinux.gz + define archhelp + echo '* compressed - Build compressed kernel image' + echo ' install - Install compressed kernel image' +- echo '* unwcheck - Check vmlinux for invalid unwind info' + endef diff --git a/debian/patches/debian/iwlwifi-do-not-request-unreleased-firmware.patch b/debian/patches/debian/iwlwifi-do-not-request-unreleased-firmware.patch new file mode 100644 index 000000000..c8061436d --- /dev/null +++ b/debian/patches/debian/iwlwifi-do-not-request-unreleased-firmware.patch @@ -0,0 +1,26 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Subject: iwlwifi: Do not request unreleased firmware for IWL6000 +Bug-Debian: https://bugs.debian.org/689416 +Forwarded: not-needed + +The iwlwifi driver currently supports firmware API versions 4-6 for +these devices. It will request the file for the latest supported +version and then fall back to earlier versions. However, the latest +version that has actually been released is 4, so we expect the +requests for versions 6 and then 5 to fail. + +The installer appears to report any failed request, and it is probably +not easy to detect that this particular failure is harmless. So stop +requesting the unreleased firmware. + +--- a/drivers/net/wireless/intel/iwlwifi/cfg/6000.c ++++ b/drivers/net/wireless/intel/iwlwifi/cfg/6000.c +@@ -31,7 +31,7 @@ + #include "dvm/commands.h" /* needed for BT for now */ + + /* Highest firmware API version supported */ +-#define IWL6000_UCODE_API_MAX 6 ++#define IWL6000_UCODE_API_MAX 4 /* v5-6 are supported but not released */ + #define IWL6050_UCODE_API_MAX 5 + #define IWL6000G2_UCODE_API_MAX 6 + #define IWL6035_UCODE_API_MAX 6 diff --git a/debian/patches/debian/kbuild-abort-build-if-subdirs-used.patch b/debian/patches/debian/kbuild-abort-build-if-subdirs-used.patch new file mode 100644 index 000000000..ec23040d8 --- /dev/null +++ b/debian/patches/debian/kbuild-abort-build-if-subdirs-used.patch @@ -0,0 +1,37 @@ +From: Ben Hutchings <benh@debian.org> +Date: Mon, 26 Apr 2021 18:27:16 +0200 +Subject: kbuild: Abort build if SUBDIRS used +Forwarded: not-needed +Bug-Debian: https://bugs.debian.org/987575 + +DKMS and module-assistant both build OOT modules as root. If they +build an old OOT module that still use SUBDIRS this causes Kbuild +to try building a full kernel, which obviously fails but not before +deleting files from the installed headers package. + +To avoid such mishaps, detect this situation and abort the build. + +The error message is based on that used in commit 0126be38d988 +"kbuild: announce removal of SUBDIRS if used". +--- +--- a/Makefile ++++ b/Makefile +@@ -218,6 +218,18 @@ ifeq ("$(origin M)", "command line") + KBUILD_EXTMOD := $(M) + endif + ++# Old syntax make ... SUBDIRS=$PWD should be rejected to avoid mishaps ++# (see Debian bugs #982334, #987575) ++ifndef KBUILD_EXTMOD ++ ifdef SUBDIRS ++ $(warning =============== ERROR ==============) ++ $(warning 'SUBDIRS' was removed in Linux 5.3) ++ $(warning Use 'M=' or 'KBUILD_EXTMOD=' instead) ++ $(warning ====================================) ++ $(error .) ++ endif ++endif ++ + $(if $(word 2, $(KBUILD_EXTMOD)), \ + $(error building multiple external modules is not supported)) + diff --git a/debian/patches/debian/kbuild-look-for-module.lds-under-arch-directory-too.patch b/debian/patches/debian/kbuild-look-for-module.lds-under-arch-directory-too.patch new file mode 100644 index 000000000..f9a22d892 --- /dev/null +++ b/debian/patches/debian/kbuild-look-for-module.lds-under-arch-directory-too.patch @@ -0,0 +1,52 @@ +From: Ben Hutchings <benh@debian.org> +Date: Thu, 10 Dec 2020 17:31:39 +0100 +Subject: kbuild: Look for module.lds under arch directory too +Forwarded: not-needed +Bug-Debian: https://bugs.debian.org/975571 + +The module.lds linker script is now built under the scripts directory, +where previously it was under arch/$(SRCARCH). + +However, we package the scripts directory as linux-kbuild, which is +meant to be able to do support native and cross-builds. That means it +shouldn't contain files for a specific target architecture without a +wrapper to select between them, and it doesn't appear that linker +scripts are powerful enough to implement such a wrapper. + +Building module.lds in a different location would require relatively +large changes. Moving it in the package build rules can work, but we +need to support custom kernel builds from the same source so we can't +assume it's moved. + +Therefore, we move module.lds under the arch build directory in +rules.real and change Makefile.modfinal to look for it in both places. + +--- +Index: linux/scripts/Makefile.modfinal +=================================================================== +--- linux.orig/scripts/Makefile.modfinal ++++ linux/scripts/Makefile.modfinal +@@ -29,12 +29,13 @@ quiet_cmd_cc_o_c = CC [M] $@ + $(call if_changed_dep,cc_o_c) + + ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink) ++ARCH_MODULE_LDS := $(word 1,$(wildcard scripts/module.lds arch/$(SRCARCH)/module.lds)) + + quiet_cmd_ld_ko_o = LD [M] $@ + cmd_ld_ko_o += \ + $(LD) -r $(KBUILD_LDFLAGS) \ + $(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \ +- -T scripts/module.lds -o $@ $(filter %.o, $^); \ ++ -T $(ARCH_MODULE_LDS) -o $@ $(filter %.o, $^); \ + $(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true) + + quiet_cmd_btf_ko = BTF [M] $@ +@@ -57,7 +58,7 @@ if_changed_except = $(if $(call newer_pr + printf '%s\n' 'cmd_$@ := $(make-cmd)' > $(dot-target).cmd, @:) + + # Re-generate module BTFs if either module's .ko or vmlinux changed +-$(modules): %.ko: %.o %.mod.o scripts/module.lds $(and $(CONFIG_DEBUG_INFO_BTF_MODULES),$(KBUILD_BUILTIN),vmlinux) FORCE ++$(modules): %.ko: %.o %.mod.o $(ARCH_MODULE_LDS) $(and $(CONFIG_DEBUG_INFO_BTF_MODULES),$(KBUILD_BUILTIN),vmlinux) FORCE + +$(call if_changed_except,ld_ko_o,vmlinux) + ifdef CONFIG_DEBUG_INFO_BTF_MODULES + +$(if $(newer-prereqs),$(call cmd,btf_ko)) diff --git a/debian/patches/debian/kernelvariables.patch b/debian/patches/debian/kernelvariables.patch new file mode 100644 index 000000000..2196c8a43 --- /dev/null +++ b/debian/patches/debian/kernelvariables.patch @@ -0,0 +1,92 @@ +From: Bastian Blank <waldi@debian.org> +Subject: kbuild: Make the toolchain variables easily overwritable +Date: Sun, 22 Feb 2009 15:39:35 +0100 +Forwarded: not-needed + +Allow make variables to be overridden for each flavour by a file in +the build tree, .kernelvariables. + +We currently use this for ARCH, KERNELRELEASE, CC, and in some cases +also CROSS_COMPILE, KCFLAGS. + +This file can only be read after we establish the build tree, and all +use of $(ARCH) needs to be moved after this. + +[bwh: Updated for 5.3: include .kernelvariables from current directory + rather than using undefined $(obj).] +--- +--- a/Makefile ++++ b/Makefile +@@ -395,36 +395,6 @@ include $(srctree)/scripts/subarch.inclu + # Note: Some architectures assign CROSS_COMPILE in their arch/*/Makefile + ARCH ?= $(SUBARCH) + +-# Architecture as present in compile.h +-UTS_MACHINE := $(ARCH) +-SRCARCH := $(ARCH) +- +-# Additional ARCH settings for x86 +-ifeq ($(ARCH),i386) +- SRCARCH := x86 +-endif +-ifeq ($(ARCH),x86_64) +- SRCARCH := x86 +-endif +- +-# Additional ARCH settings for sparc +-ifeq ($(ARCH),sparc32) +- SRCARCH := sparc +-endif +-ifeq ($(ARCH),sparc64) +- SRCARCH := sparc +-endif +- +-# Additional ARCH settings for parisc +-ifeq ($(ARCH),parisc64) +- SRCARCH := parisc +-endif +- +-export cross_compiling := +-ifneq ($(SRCARCH),$(SUBARCH)) +-cross_compiling := 1 +-endif +- + KCONFIG_CONFIG ?= .config + export KCONFIG_CONFIG + +@@ -540,6 +510,35 @@ RUSTFLAGS_KERNEL = + AFLAGS_KERNEL = + LDFLAGS_vmlinux = + ++-include .kernelvariables ++ ++# Architecture as present in compile.h ++UTS_MACHINE := $(ARCH) ++SRCARCH := $(ARCH) ++ ++# Additional ARCH settings for x86 ++ifeq ($(ARCH),i386) ++ SRCARCH := x86 ++endif ++ifeq ($(ARCH),x86_64) ++ SRCARCH := x86 ++endif ++ ++# Additional ARCH settings for sparc ++ifeq ($(ARCH),sparc64) ++ SRCARCH := sparc ++endif ++ ++# Additional ARCH settings for parisc ++ifeq ($(ARCH),parisc64) ++ SRCARCH := parisc ++endif ++ ++# Additional ARCH settings for sh ++ifeq ($(ARCH),sh64) ++ SRCARCH := sh ++endif ++ + # Use USERINCLUDE when you must reference the UAPI directories only. + USERINCLUDE := \ + -I$(srctree)/arch/$(SRCARCH)/include/uapi \ diff --git a/debian/patches/debian/makefile-make-compiler-version-comparison-optional.patch b/debian/patches/debian/makefile-make-compiler-version-comparison-optional.patch new file mode 100644 index 000000000..f0d5c80d7 --- /dev/null +++ b/debian/patches/debian/makefile-make-compiler-version-comparison-optional.patch @@ -0,0 +1,31 @@ +From: Ben Hutchings <benh@debian.org> +Date: Thu, 15 Sep 2022 02:14:03 +0200 +Subject: Makefile: Make compiler version comparison optional +Forwarded: not-needed +Bug-Debian: https://bugs.debian.org/1019749 + +The top-level Makefile warns if the compiler version string changes at +all between the kernel build and an out-of-tree module build. + +We expect that major compiler version changes could introduce ABI +changes, and override the CC variable in out-of-tree module builds to +ensure that the same major compiler version is used. But minor +version changes should not make a difference, so this exact version +comparison produces false warnings. + +Since custom kernel packages don't have that, don't remove the version +comparison. Instead, skip it if $(DEBIAN_KERNEL_NO_CC_VERSION_CHECK) +is non-empty. + +--- +--- a/Makefile ++++ b/Makefile +@@ -1753,7 +1753,7 @@ PHONY += prepare + # now expand this into a simple variable to reduce the cost of shell evaluations + prepare: CC_VERSION_TEXT := $(CC_VERSION_TEXT) + prepare: +- @if [ "$(CC_VERSION_TEXT)" != "$(CONFIG_CC_VERSION_TEXT)" ]; then \ ++ @if [ -z "$(DEBIAN_KERNEL_NO_CC_VERSION_CHECK)" ] && [ "$(CC_VERSION_TEXT)" != "$(CONFIG_CC_VERSION_TEXT)" ]; then \ + echo >&2 "warning: the compiler differs from the one used to build the kernel"; \ + echo >&2 " The kernel was built by: $(CONFIG_CC_VERSION_TEXT)"; \ + echo >&2 " You are using: $(CC_VERSION_TEXT)"; \ diff --git a/debian/patches/debian/mips-boston-disable-its.patch b/debian/patches/debian/mips-boston-disable-its.patch new file mode 100644 index 000000000..ca4de2daa --- /dev/null +++ b/debian/patches/debian/mips-boston-disable-its.patch @@ -0,0 +1,22 @@ +From: YunQiang Su <syq@debian.org> +Date: Mon, 14 May 2018 16:16:18 +0800 +Subject: Disable uImage generation for mips generic +Forwarded: not-needed + +MIPS generic trys to generate uImage when build, which then ask for +u-boot-tools. + +[bwh: Updated for 5.17: + - zload-y is no longer assigned here and appears to default to empty + - Adjust context] + +--- a/arch/mips/generic/Platform ++++ b/arch/mips/generic/Platform +@@ -13,7 +13,6 @@ cflags-$(CONFIG_MACH_INGENIC_SOC) += -I$ + cflags-$(CONFIG_MIPS_GENERIC) += -I$(srctree)/arch/mips/include/asm/mach-generic + + load-$(CONFIG_MIPS_GENERIC) += 0xffffffff80100000 +-all-$(CONFIG_MIPS_GENERIC) += vmlinux.gz.itb + + its-y := vmlinux.its.S + its-$(CONFIG_FIT_IMAGE_FDT_BOSTON) += board-boston.its.S diff --git a/debian/patches/debian/mips-disable-werror.patch b/debian/patches/debian/mips-disable-werror.patch new file mode 100644 index 000000000..b8fe8b44c --- /dev/null +++ b/debian/patches/debian/mips-disable-werror.patch @@ -0,0 +1,23 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Mon, 13 Sep 2010 02:16:18 +0100 +Subject: [PATCH] Partially revert "MIPS: Add -Werror to arch/mips/Kbuild" +Forwarded: not-needed + +This reverts commits 66f9ba101f54bda63ab1db97f9e9e94763d0651b and +5373633cc9253ba82547473e899cab141c54133e. + +We really don't want to add -Werror anywhere. +--- +--- a/arch/mips/Kbuild ++++ b/arch/mips/Kbuild +@@ -1,10 +1,4 @@ + # SPDX-License-Identifier: GPL-2.0 +-# Fail on warnings - also for files referenced in subdirs +-# -Werror can be disabled for specific files using: +-# CFLAGS_<file.o> := -Wno-error +-ifeq ($(W),) +-subdir-ccflags-y := -Werror +-endif + + # platform specific definitions + include arch/mips/Kbuild.platforms diff --git a/debian/patches/debian/mips-ieee754-relaxed.patch b/debian/patches/debian/mips-ieee754-relaxed.patch new file mode 100644 index 000000000..20dff251c --- /dev/null +++ b/debian/patches/debian/mips-ieee754-relaxed.patch @@ -0,0 +1,32 @@ +From: YunQiang Su <syq@debian.org> +Date: Mon 16 Nov 2020 09:11:00 +0800 +Subject: Use RELAXED ieee754 mode for Loongson-3 as 3A 4000 is 2008-only +Forwarded: not-needed + +There are 2 mode of value of IEEE NaN hardcoded by CPU. +Currently, our mipsel/mips64el port is in so-called lagacy mode. +Loongson 3A 4000 is set as the so-called 2008 mode. + +To make Debian workable on Loongson 3A 4000, we need set the kerenl in +RELAXED mode. + +https://web.archive.org/web/20180830093617/https://dmz-portal.mips.com/wiki/MIPS_ABI_-_NaN_Interlinking + +diff --git a/arch/mips/kernel/fpu-probe.c b/arch/mips/kernel/fpu-probe.c +index e689d6a83..667226f94 100644 +--- a/arch/mips/kernel/fpu-probe.c ++++ b/arch/mips/kernel/fpu-probe.c +@@ -144,7 +144,12 @@ static void cpu_set_fpu_2008(struct cpuinfo_mips *c) + * IEEE 754 conformance mode to use. Affects the NaN encoding and the + * ABS.fmt/NEG.fmt execution mode. + */ +-static enum { STRICT, LEGACY, STD2008, RELAXED } ieee754 = STRICT; ++enum ieee754_mode { STRICT, LEGACY, STD2008, RELAXED }; ++#ifdef CONFIG_CPU_LOONGSON64 ++static enum ieee754_mode ieee754 = RELAXED; ++#else ++static enum ieee754_mode ieee754 = STRICT; ++#endif + + /* + * Set the IEEE 754 NaN encodings and the ABS.fmt/NEG.fmt execution modes diff --git a/debian/patches/debian/module-avoid-abi-changes-when-debug-info-is-disabled.patch b/debian/patches/debian/module-avoid-abi-changes-when-debug-info-is-disabled.patch new file mode 100644 index 000000000..3582f4ba3 --- /dev/null +++ b/debian/patches/debian/module-avoid-abi-changes-when-debug-info-is-disabled.patch @@ -0,0 +1,23 @@ +From: Ben Hutchings <benh@debian.org> +Date: Fri, 13 May 2022 21:08:08 +0200 +Subject: module: Avoid ABI changes when debug info is disabled +Forwarded: not-needed + +CI builds are done with debug info disabled, but this removes some +members from struct module. This causes builds to fail if there is an +ABI reference for the current ABI. + +Define these members unconditionally, so that there is no ABI change. + +--- +--- a/include/linux/module.h ++++ b/include/linux/module.h +@@ -471,7 +471,7 @@ struct module { + unsigned int num_bpf_raw_events; + struct bpf_raw_event_map *bpf_raw_events; + #endif +-#ifdef CONFIG_DEBUG_INFO_BTF_MODULES ++#if 1 + unsigned int btf_data_size; + void *btf_data; + #endif diff --git a/debian/patches/debian/ntfs-mark-it-as-broken.patch b/debian/patches/debian/ntfs-mark-it-as-broken.patch new file mode 100644 index 000000000..207f9751e --- /dev/null +++ b/debian/patches/debian/ntfs-mark-it-as-broken.patch @@ -0,0 +1,22 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Thu, 25 Apr 2019 15:31:33 +0100 +Subject: ntfs: mark it as broken + +NTFS has unfixed issues CVE-2018-12929, CVE-2018-12930, and +CVE-2018-12931. ntfs-3g is a better supported alternative. + +Make sure it can't be enabled even in custom kernels. + +--- +Index: debian-kernel/fs/ntfs/Kconfig +=================================================================== +--- debian-kernel.orig/fs/ntfs/Kconfig ++++ debian-kernel/fs/ntfs/Kconfig +@@ -1,6 +1,7 @@ + # SPDX-License-Identifier: GPL-2.0-only + config NTFS_FS + tristate "NTFS file system support" ++ depends on BROKEN + select NLS + help + NTFS is the file system of Microsoft Windows NT, 2000, XP and 2003. diff --git a/debian/patches/debian/perf-traceevent-support-asciidoctor-for-documentatio.patch b/debian/patches/debian/perf-traceevent-support-asciidoctor-for-documentatio.patch new file mode 100644 index 000000000..89df33ab0 --- /dev/null +++ b/debian/patches/debian/perf-traceevent-support-asciidoctor-for-documentatio.patch @@ -0,0 +1,54 @@ +From cd02fc78859ef9aefd7c92406f9523622da0b472 Mon Sep 17 00:00:00 2001 +From: Bastian Blank <waldi@debian.org> +Date: Tue, 4 Aug 2020 09:44:37 +0000 +Subject: [PATCH 2/2] perf/traceevent: Support asciidoctor for documentation +Forwarded: not-needed + +--- + tools/lib/perf/Documentation/Makefile | 2 +- + tools/lib/traceevent/Documentation/Makefile | 2 +- + tools/perf/Documentation/Makefile | 2 +- + 3 files changed, 3 insertions(+), 3 deletions(-) + +diff --git a/tools/lib/perf/Documentation/Makefile b/tools/lib/perf/Documentation/Makefile +index 972754082a85..272d06173a3e 100644 +--- a/tools/lib/perf/Documentation/Makefile ++++ b/tools/lib/perf/Documentation/Makefile +@@ -35,7 +35,7 @@ htmldir = $(docdir)/html + exdir = $(docdir)/examples + + ASCIIDOC = asciidoc +-ASCIIDOC_EXTRA = --unsafe -f asciidoc.conf ++ASCIIDOC_EXTRA = + ASCIIDOC_HTML = xhtml11 + MANPAGE_XSL = manpage-normal.xsl + XMLTO_EXTRA = +diff --git a/tools/lib/traceevent/Documentation/Makefile b/tools/lib/traceevent/Documentation/Makefile +index aa72ab96c3c1..f3a4ff3b8b0e 100644 +--- a/tools/lib/traceevent/Documentation/Makefile ++++ b/tools/lib/traceevent/Documentation/Makefile +@@ -28,7 +28,7 @@ mandir?=$(prefix)/share/man + man3dir=$(mandir)/man3 + + ASCIIDOC=asciidoc +-ASCIIDOC_EXTRA = --unsafe -f asciidoc.conf ++ASCIIDOC_EXTRA = + ASCIIDOC_HTML = xhtml11 + MANPAGE_XSL = manpage-normal.xsl + XMLTO_EXTRA = +diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile +index 6e54979c2124..7bfa6ae971ab 100644 +--- a/tools/perf/Documentation/Makefile ++++ b/tools/perf/Documentation/Makefile +@@ -48,7 +48,7 @@ man5dir=$(mandir)/man5 + man7dir=$(mandir)/man7 + + ASCIIDOC=asciidoc +-ASCIIDOC_EXTRA += --unsafe -f asciidoc.conf ++ASCIIDOC_EXTRA += + ASCIIDOC_HTML = xhtml11 + MANPAGE_XSL = manpage-normal.xsl + XMLTO_EXTRA = +-- +2.28.0 + diff --git a/debian/patches/debian/rds-Disable-auto-loading-as-mitigation-against-local.patch b/debian/patches/debian/rds-Disable-auto-loading-as-mitigation-against-local.patch new file mode 100644 index 000000000..3343aecac --- /dev/null +++ b/debian/patches/debian/rds-Disable-auto-loading-as-mitigation-against-local.patch @@ -0,0 +1,34 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Fri, 19 Nov 2010 02:12:48 +0000 +Subject: [PATCH 1/3] rds: Disable auto-loading as mitigation against local exploits +Forwarded: not-needed + +Recent review has revealed several bugs in obscure protocol +implementations that can be exploited by local users for denial of +service or privilege escalation. We can mitigate the effect of any +remaining vulnerabilities in such protocols by preventing unprivileged +users from loading the modules, so that they are only exploitable on +systems where the administrator has chosen to load the protocol. + +The 'rds' protocol is one such protocol that has been found to be +vulnerable, and which was not present in the 'lenny' kernel. +Therefore disable auto-loading. + +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- + net/rds/af_rds.c | 2 +- + 1 files changed, 1 insertions(+), 1 deletions(-) + +diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c +index 98e0538..d8d4525 100644 +--- a/net/rds/af_rds.c ++++ b/net/rds/af_rds.c +@@ -574,4 +574,4 @@ MODULE_DESCRIPTION("RDS: Reliable Datagram Sockets" + " v" DRV_VERSION " (" DRV_RELDATE ")"); + MODULE_VERSION(DRV_VERSION); + MODULE_LICENSE("Dual BSD/GPL"); +-MODULE_ALIAS_NETPROTO(PF_RDS); ++/* MODULE_ALIAS_NETPROTO(PF_RDS); */ +-- +1.7.2.3 + diff --git a/debian/patches/debian/sched-autogroup-disabled.patch b/debian/patches/debian/sched-autogroup-disabled.patch new file mode 100644 index 000000000..c616fa46e --- /dev/null +++ b/debian/patches/debian/sched-autogroup-disabled.patch @@ -0,0 +1,19 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Subject: sched: Do not enable autogrouping by default +Date: Wed, 16 Mar 2011 03:17:06 +0000 +Forwarded: not-needed + +We want to provide the option of autogrouping but without enabling +it by default yet. + +--- a/kernel/sched/autogroup.c ++++ b/kernel/sched/autogroup.c +@@ -4,7 +4,7 @@ + * Auto-group scheduling implementation: + */ + +-unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1; ++unsigned int __read_mostly sysctl_sched_autogroup_enabled = 0; + static struct autogroup autogroup_default; + static atomic_t autogroup_seq_nr; + diff --git a/debian/patches/debian/snd-pcsp-disable-autoload.patch b/debian/patches/debian/snd-pcsp-disable-autoload.patch new file mode 100644 index 000000000..e593f5144 --- /dev/null +++ b/debian/patches/debian/snd-pcsp-disable-autoload.patch @@ -0,0 +1,30 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Wed, 05 Feb 2014 23:01:30 +0000 +Subject: snd-pcsp: Disable autoload +Forwarded: not-needed +Bug-Debian: https://bugs.debian.org/697709 + +There are two drivers claiming the platform:pcspkr device: +- pcspkr creates an input(!) device that can only beep +- snd-pcsp creates an equivalent input device plus a PCM device that can + play barely recognisable renditions of sampled sound + +snd-pcsp is blacklisted by the alsa-base package, but not everyone +installs that. On PCs where no sound is wanted at all, both drivers +will still be loaded and one or other will complain that it couldn't +claim the relevant I/O range. + +In case anyone finds snd-pcsp useful, we continue to build it. But +remove the alias, to ensure it's not loaded where it's not wanted. + +--- a/sound/drivers/pcsp/pcsp.c ++++ b/sound/drivers/pcsp/pcsp.c +@@ -22,7 +22,7 @@ + MODULE_AUTHOR("Stas Sergeev <stsp@users.sourceforge.net>"); + MODULE_DESCRIPTION("PC-Speaker driver"); + MODULE_LICENSE("GPL"); +-MODULE_ALIAS("platform:pcspkr"); ++/*MODULE_ALIAS("platform:pcspkr");*/ + + static int index = SNDRV_DEFAULT_IDX1; /* Index 0-MAX */ + static char *id = SNDRV_DEFAULT_STR1; /* ID for this card */ diff --git a/debian/patches/debian/tools-perf-install-python-bindings.patch b/debian/patches/debian/tools-perf-install-python-bindings.patch new file mode 100644 index 000000000..c3f174741 --- /dev/null +++ b/debian/patches/debian/tools-perf-install-python-bindings.patch @@ -0,0 +1,26 @@ +From: Adriaan Schmidt <adriaan.schmidt@siemens.com> +Date: Mon, 4 Apr 2022 13:38:33 +0200 +Subject: tools: install perf python bindings +Bug-Debian: http://bugs.debian.org/860957 +Forwarded: not-needed + +--- + tools/perf/Makefile.perf | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf +index 80522bcfafe0..b011c7aae742 100644 +--- a/tools/perf/Makefile.perf ++++ b/tools/perf/Makefile.perf +@@ -1026,7 +1026,7 @@ install-bin: install-tools install-tests install-traceevent-plugins + install: install-bin try-install-man + + install-python_ext: +- $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)' ++ $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)' --install-layout=deb + + # 'make install-doc' should call 'make -C Documentation install' + $(INSTALL_DOC_TARGETS): +-- +2.30.2 + diff --git a/debian/patches/debian/tools-perf-perf-read-vdso-in-libexec.patch b/debian/patches/debian/tools-perf-perf-read-vdso-in-libexec.patch new file mode 100644 index 000000000..eacd9ce17 --- /dev/null +++ b/debian/patches/debian/tools-perf-perf-read-vdso-in-libexec.patch @@ -0,0 +1,32 @@ +From: Ben Hutchings <benh@debian.org> +Date: Mon, 11 May 2015 02:51:07 +0000 +Subject: linux-tools: Install perf-read-vdso{,x}32 in directory under /usr/lib + +--- a/tools/perf/Makefile.perf ++++ b/tools/perf/Makefile.perf +@@ -947,21 +947,21 @@ install-tools: all install-gtk + $(LN) '$(DESTDIR_SQ)$(bindir_SQ)/perf' '$(DESTDIR_SQ)$(bindir_SQ)/trace'; \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(includedir_SQ)/perf'; \ + $(INSTALL) -m 644 include/perf/perf_dlfilter.h -t '$(DESTDIR_SQ)$(includedir_SQ)/perf' ++ $(call QUIET_INSTALL, libexec) \ ++ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' + ifndef NO_PERF_READ_VDSO32 + $(call QUIET_INSTALL, perf-read-vdso32) \ +- $(INSTALL) $(OUTPUT)perf-read-vdso32 '$(DESTDIR_SQ)$(bindir_SQ)'; ++ $(INSTALL) $(OUTPUT)perf-read-vdso32 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'; + endif + ifndef NO_PERF_READ_VDSOX32 + $(call QUIET_INSTALL, perf-read-vdsox32) \ +- $(INSTALL) $(OUTPUT)perf-read-vdsox32 '$(DESTDIR_SQ)$(bindir_SQ)'; ++ $(INSTALL) $(OUTPUT)perf-read-vdsox32 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'; + endif + ifndef NO_JVMTI + $(call QUIET_INSTALL, $(LIBJVMTI)) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \ + $(INSTALL) $(OUTPUT)$(LIBJVMTI) '$(DESTDIR_SQ)$(libdir_SQ)'; + endif +- $(call QUIET_INSTALL, libexec) \ +- $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' + ifndef NO_LIBBPF + $(call QUIET_INSTALL, bpf-headers) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \ diff --git a/debian/patches/debian/uname-version-timestamp.patch b/debian/patches/debian/uname-version-timestamp.patch new file mode 100644 index 000000000..4be158e09 --- /dev/null +++ b/debian/patches/debian/uname-version-timestamp.patch @@ -0,0 +1,26 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Subject: Make mkcompile_h accept an alternate timestamp string +Date: Tue, 12 May 2015 19:29:22 +0100 +Forwarded: not-needed + +We want to include the Debian version in the utsname::version string +instead of a full timestamp string. However, we still need to provide +a standard timestamp string for gen_initramfs_list.sh to make the +kernel image reproducible. + +Make mkcompile_h use $KBUILD_BUILD_VERSION_TIMESTAMP in preference to +$KBUILD_BUILD_TIMESTAMP. + +Index: linux/init/Makefile +=================================================================== +--- linux.orig/init/Makefile ++++ linux/init/Makefile +@@ -29,7 +29,7 @@ preempt-flag-$(CONFIG_PREEMPT_DYNAMIC) : + preempt-flag-$(CONFIG_PREEMPT_RT) := PREEMPT_RT + + build-version = $(or $(KBUILD_BUILD_VERSION), $(build-version-auto)) +-build-timestamp = $(or $(KBUILD_BUILD_TIMESTAMP), $(build-timestamp-auto)) ++build-timestamp = $(or $(KBUILD_BUILD_VERSION_TIMESTAMP), $(KBUILD_BUILD_TIMESTAMP), $(build-timestamp-auto)) + + # Maximum length of UTS_VERSION is 64 chars + filechk_uts_version = \ diff --git a/debian/patches/debian/version.patch b/debian/patches/debian/version.patch new file mode 100644 index 000000000..1425f555a --- /dev/null +++ b/debian/patches/debian/version.patch @@ -0,0 +1,186 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Subject: Include package version along with kernel release in stack traces +Date: Tue, 24 Jul 2012 03:13:10 +0100 +Forwarded: not-needed + +For distribution binary packages we assume +$DISTRIBUTION_OFFICIAL_BUILD, $DISTRIBUTOR and $DISTRIBUTION_VERSION +are set. +--- + Makefile | 15 ++++++++++++++- + arch/ia64/kernel/process.c | 5 +++-- + arch/powerpc/kernel/process.c | 6 ++++-- + arch/x86/um/sysrq_64.c | 6 ++++-- + kernel/hung_task.c | 6 ++++-- + lib/dump_stack.c | 6 ++++-- + 6 files changed, 33 insertions(+), 11 deletions(-) + +Index: linux/Makefile +=================================================================== +--- linux.orig/Makefile ++++ linux/Makefile +@@ -1263,7 +1263,8 @@ PHONY += prepare archprepare + + archprepare: outputmakefile archheaders archscripts scripts include/config/kernel.release \ + asm-generic $(version_h) $(autoksyms_h) include/generated/utsrelease.h \ +- include/generated/compile.h include/generated/autoconf.h remove-stale-files ++ include/generated/compile.h include/generated/autoconf.h \ ++ include/generated/package.h remove-stale-files + + prepare0: archprepare + $(Q)$(MAKE) $(build)=scripts/mod +@@ -1321,6 +1322,16 @@ define filechk_version.h + echo \#define LINUX_VERSION_SUBLEVEL $(SUBLEVEL) + endef + ++ifneq ($(DISTRIBUTION_OFFICIAL_BUILD),) ++define filechk_package.h ++ echo \#define LINUX_PACKAGE_ID \" $(DISTRIBUTOR) $(DISTRIBUTION_VERSION)\" ++endef ++else ++define filechk_package.h ++ echo \#define LINUX_PACKAGE_ID \"\" ++endef ++endif ++ + $(version_h): PATCHLEVEL := $(or $(PATCHLEVEL), 0) + $(version_h): SUBLEVEL := $(or $(SUBLEVEL), 0) + $(version_h): FORCE +@@ -1335,6 +1346,9 @@ filechk_compile.h = $(srctree)/scripts/m + include/generated/compile.h: FORCE + $(call filechk,compile.h) + ++include/generated/package.h: $(srctree)/Makefile FORCE ++ $(call filechk,package.h) ++ + PHONY += headerdep + headerdep: + $(Q)find $(srctree)/include/ -name '*.h' | xargs --max-args 1 \ +Index: linux/arch/ia64/kernel/process.c +=================================================================== +--- linux.orig/arch/ia64/kernel/process.c ++++ linux/arch/ia64/kernel/process.c +@@ -35,6 +35,7 @@ + #include <linux/utsname.h> + #include <linux/resume_user_mode.h> + #include <linux/rcupdate.h> ++#include <generated/package.h> + + #include <asm/cpu.h> + #include <asm/delay.h> +@@ -102,9 +103,9 @@ show_regs (struct pt_regs *regs) + print_modules(); + printk("\n"); + show_regs_print_info(KERN_DEFAULT); +- printk("psr : %016lx ifs : %016lx ip : [<%016lx>] %s (%s)\n", ++ printk("psr : %016lx ifs : %016lx ip : [<%016lx>] %s (%s%s)\n", + regs->cr_ipsr, regs->cr_ifs, ip, print_tainted(), +- init_utsname()->release); ++ init_utsname()->release, LINUX_PACKAGE_ID); + printk("ip is at %pS\n", (void *)ip); + printk("unat: %016lx pfs : %016lx rsc : %016lx\n", + regs->ar_unat, regs->ar_pfs, regs->ar_rsc); +Index: linux/arch/powerpc/kernel/process.c +=================================================================== +--- linux.orig/arch/powerpc/kernel/process.c ++++ linux/arch/powerpc/kernel/process.c +@@ -38,6 +38,7 @@ + #include <linux/uaccess.h> + #include <linux/pkeys.h> + #include <linux/seq_buf.h> ++#include <generated/package.h> + + #include <asm/interrupt.h> + #include <asm/io.h> +@@ -1520,8 +1521,9 @@ static void __show_regs(struct pt_regs * + + printk("NIP: "REG" LR: "REG" CTR: "REG"\n", + regs->nip, regs->link, regs->ctr); +- printk("REGS: %px TRAP: %04lx %s (%s)\n", +- regs, regs->trap, print_tainted(), init_utsname()->release); ++ printk("REGS: %px TRAP: %04lx %s (%s%s)\n", ++ regs, regs->trap, print_tainted(), init_utsname()->release, ++ LINUX_PACKAGE_ID); + printk("MSR: "REG" ", regs->msr); + print_msr_bits(regs->msr); + pr_cont(" CR: %08lx XER: %08lx\n", regs->ccr, regs->xer); +Index: linux/arch/x86/um/sysrq_64.c +=================================================================== +--- linux.orig/arch/x86/um/sysrq_64.c ++++ linux/arch/x86/um/sysrq_64.c +@@ -9,6 +9,7 @@ + #include <linux/sched.h> + #include <linux/sched/debug.h> + #include <linux/utsname.h> ++#include <generated/package.h> + #include <asm/current.h> + #include <asm/ptrace.h> + #include <asm/sysrq.h> +@@ -17,8 +18,9 @@ void show_regs(struct pt_regs *regs) + { + printk("\n"); + print_modules(); +- printk(KERN_INFO "Pid: %d, comm: %.20s %s %s\n", task_pid_nr(current), +- current->comm, print_tainted(), init_utsname()->release); ++ printk(KERN_INFO "Pid: %d, comm: %.20s %s %s%s\n", task_pid_nr(current), ++ current->comm, print_tainted(), init_utsname()->release, ++ LINUX_PACKAGE_ID); + printk(KERN_INFO "RIP: %04lx:%pS\n", PT_REGS_CS(regs) & 0xffff, + (void *)PT_REGS_IP(regs)); + printk(KERN_INFO "RSP: %016lx EFLAGS: %08lx\n", PT_REGS_SP(regs), +Index: linux/kernel/hung_task.c +=================================================================== +--- linux.orig/kernel/hung_task.c ++++ linux/kernel/hung_task.c +@@ -24,6 +24,7 @@ + #include <linux/sched/sysctl.h> + + #include <trace/events/sched.h> ++#include <generated/package.h> + + /* + * The number of tasks checked: +@@ -131,10 +132,11 @@ static void check_hung_task(struct task_ + sysctl_hung_task_warnings--; + pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n", + t->comm, t->pid, (jiffies - t->last_switch_time) / HZ); +- pr_err(" %s %s %.*s\n", ++ pr_err(" %s %s %.*s%s\n", + print_tainted(), init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), +- init_utsname()->version); ++ init_utsname()->version, ++ LINUX_PACKAGE_ID); + pr_err("\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\"" + " disables this message.\n"); + sched_show_task(t); +Index: linux/lib/dump_stack.c +=================================================================== +--- linux.orig/lib/dump_stack.c ++++ linux/lib/dump_stack.c +@@ -14,6 +14,7 @@ + #include <linux/kexec.h> + #include <linux/utsname.h> + #include <linux/stop_machine.h> ++#include <generated/package.h> + + static char dump_stack_arch_desc_str[128]; + +@@ -54,13 +55,15 @@ void __init dump_stack_set_arch_desc(con + */ + void dump_stack_print_info(const char *log_lvl) + { +- printk("%sCPU: %d PID: %d Comm: %.20s %s%s %s %.*s" BUILD_ID_FMT "\n", ++ printk("%sCPU: %d PID: %d Comm: %.20s %s%s %s %.*s %s" BUILD_ID_FMT "\n", + log_lvl, raw_smp_processor_id(), current->pid, current->comm, + kexec_crash_loaded() ? "Kdump: loaded " : "", + print_tainted(), + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), +- init_utsname()->version, BUILD_ID_VAL); ++ init_utsname()->version, ++ LINUX_PACKAGE_ID, ++ BUILD_ID_VAL); + + if (dump_stack_arch_desc_str[0] != '\0') + printk("%sHardware name: %s\n", diff --git a/debian/patches/debian/wireless-add-debian-wireless-regdb-certificates.patch b/debian/patches/debian/wireless-add-debian-wireless-regdb-certificates.patch new file mode 100644 index 000000000..edbf8657f --- /dev/null +++ b/debian/patches/debian/wireless-add-debian-wireless-regdb-certificates.patch @@ -0,0 +1,1452 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Fri, 13 Apr 2018 20:10:28 +0100 +Subject: wireless: Add Debian wireless-regdb certificates +Forwarded: not-needed + +This hex dump is generated using: + +{ + for cert in debian/certs/wireless-regdb-*.pem; do + openssl x509 -in $cert -outform der; + done +} | hexdump -v -e '1/1 "0x%.2x," "\n"' > net/wireless/certs/debian.hex +--- + net/wireless/certs/debian.hex | 1426 +++++++++++++++++++++++++++++++++ + 1 file changed, 1426 insertions(+) + create mode 100644 net/wireless/certs/debian.hex + +diff --git a/net/wireless/certs/debian.hex b/net/wireless/certs/debian.hex +new file mode 100644 +index 000000000000..c5ab03f8c500 +--- /dev/null ++++ b/net/wireless/certs/debian.hex +@@ -0,0 +1,1426 @@ ++0x30, ++0x82, ++0x02, ++0xbd, ++0x30, ++0x82, ++0x01, ++0xa5, ++0x02, ++0x14, ++0x57, ++0x7e, ++0x02, ++0x1c, ++0xb9, ++0x80, ++0xe0, ++0xe8, ++0x20, ++0x82, ++0x1b, ++0xa7, ++0xb5, ++0x4b, ++0x49, ++0x61, ++0xb8, ++0xb4, ++0xfa, ++0xdf, ++0x30, ++0x0d, ++0x06, ++0x09, ++0x2a, ++0x86, ++0x48, ++0x86, ++0xf7, ++0x0d, ++0x01, ++0x01, ++0x0b, ++0x05, ++0x00, ++0x30, ++0x1a, ++0x31, ++0x18, ++0x30, ++0x16, ++0x06, ++0x03, ++0x55, ++0x04, ++0x03, ++0x0c, ++0x0f, ++0x62, ++0x65, ++0x6e, ++0x68, ++0x40, ++0x64, ++0x65, ++0x62, ++0x69, ++0x61, ++0x6e, ++0x2e, ++0x6f, ++0x72, ++0x67, ++0x30, ++0x20, ++0x17, ++0x0d, ++0x32, ++0x30, ++0x30, ++0x31, ++0x33, ++0x30, ++0x31, ++0x33, ++0x32, ++0x36, ++0x31, ++0x33, ++0x5a, ++0x18, ++0x0f, ++0x32, ++0x31, ++0x32, ++0x30, ++0x30, ++0x31, ++0x30, ++0x36, ++0x31, ++0x33, ++0x32, ++0x36, ++0x31, ++0x33, ++0x5a, ++0x30, ++0x1a, ++0x31, ++0x18, ++0x30, ++0x16, ++0x06, ++0x03, ++0x55, ++0x04, ++0x03, ++0x0c, ++0x0f, ++0x62, ++0x65, ++0x6e, ++0x68, ++0x40, ++0x64, ++0x65, ++0x62, ++0x69, ++0x61, ++0x6e, ++0x2e, ++0x6f, ++0x72, ++0x67, ++0x30, ++0x82, ++0x01, ++0x22, ++0x30, ++0x0d, ++0x06, ++0x09, ++0x2a, ++0x86, ++0x48, ++0x86, ++0xf7, ++0x0d, ++0x01, ++0x01, ++0x01, ++0x05, ++0x00, ++0x03, ++0x82, ++0x01, ++0x0f, ++0x00, ++0x30, ++0x82, ++0x01, ++0x0a, ++0x02, ++0x82, ++0x01, ++0x01, ++0x00, ++0x9d, ++0xe1, ++0x77, ++0xa0, ++0x24, ++0xa0, ++0xd5, ++0x79, ++0x65, ++0x3a, ++0x07, ++0x90, ++0xc9, ++0xf6, ++0xa5, ++0xa6, ++0x1f, ++0x84, ++0x1c, ++0x23, ++0x07, ++0x4b, ++0x4f, ++0xa5, ++0x03, ++0xc6, ++0x0f, ++0xf7, ++0x54, ++0xd5, ++0x8b, ++0x7e, ++0x79, ++0x81, ++0x00, ++0xd2, ++0xe9, ++0x3d, ++0xf4, ++0x97, ++0xfe, ++0x84, ++0xcd, ++0x55, ++0xbd, ++0xc9, ++0x8f, ++0x21, ++0x57, ++0x88, ++0x06, ++0x39, ++0x90, ++0x66, ++0x41, ++0x26, ++0x79, ++0x2c, ++0xca, ++0x3f, ++0x95, ++0x87, ++0x01, ++0x11, ++0x2f, ++0x2f, ++0xb0, ++0xe1, ++0x0b, ++0x43, ++0xfc, ++0x5f, ++0x2f, ++0x4f, ++0x67, ++0x04, ++0xdb, ++0x4d, ++0xb7, ++0x72, ++0x4d, ++0xd1, ++0xc5, ++0x76, ++0x73, ++0x4d, ++0x91, ++0x69, ++0xb0, ++0x71, ++0x17, ++0x36, ++0xea, ++0xab, ++0x0a, ++0x3a, ++0xcd, ++0x95, ++0x9b, ++0x76, ++0x1b, ++0x8e, ++0x21, ++0x17, ++0x8f, ++0xc5, ++0x02, ++0xbf, ++0x24, ++0xc7, ++0xc0, ++0x40, ++0xb1, ++0x3b, ++0xc4, ++0x80, ++0x7c, ++0x71, ++0xa5, ++0x51, ++0xdc, ++0xf7, ++0x3a, ++0x58, ++0x7f, ++0xb1, ++0x07, ++0x81, ++0x8a, ++0x10, ++0xd1, ++0xf6, ++0x93, ++0x17, ++0x71, ++0xe0, ++0xfa, ++0x51, ++0x79, ++0x15, ++0xd4, ++0xd7, ++0x8f, ++0xad, ++0xbd, ++0x6f, ++0x38, ++0xe1, ++0x26, ++0x7d, ++0xbc, ++0xf0, ++0x3e, ++0x80, ++0x89, ++0xb4, ++0xec, ++0x8e, ++0x69, ++0x90, ++0xdb, ++0x97, ++0x8a, ++0xf0, ++0x23, ++0x23, ++0x83, ++0x82, ++0x3b, ++0x6a, ++0xb1, ++0xac, ++0xeb, ++0xe7, ++0x99, ++0x74, ++0x2a, ++0x35, ++0x8e, ++0xa9, ++0x64, ++0xfd, ++0x46, ++0x9e, ++0xe8, ++0xe5, ++0x48, ++0x61, ++0x31, ++0x6e, ++0xe6, ++0xfc, ++0x19, ++0x18, ++0x54, ++0xc3, ++0x1b, ++0x4f, ++0xd6, ++0x00, ++0x44, ++0x87, ++0x1c, ++0x37, ++0x45, ++0xea, ++0xf5, ++0xc9, ++0xcb, ++0x0f, ++0x0c, ++0x55, ++0xec, ++0xcf, ++0x6a, ++0xc2, ++0x45, ++0x26, ++0x23, ++0xa2, ++0x31, ++0x52, ++0x4d, ++0xee, ++0x21, ++0x7d, ++0xfd, ++0x58, ++0x72, ++0xc2, ++0x28, ++0xc5, ++0x8e, ++0xa9, ++0xd0, ++0xee, ++0x01, ++0x77, ++0x08, ++0xa5, ++0xf0, ++0x22, ++0x2b, ++0x47, ++0x79, ++0x2b, ++0xcf, ++0x9a, ++0x46, ++0xb5, ++0x8f, ++0xfd, ++0x64, ++0xa2, ++0xb5, ++0xed, ++0x02, ++0x03, ++0x01, ++0x00, ++0x01, ++0x30, ++0x0d, ++0x06, ++0x09, ++0x2a, ++0x86, ++0x48, ++0x86, ++0xf7, ++0x0d, ++0x01, ++0x01, ++0x0b, ++0x05, ++0x00, ++0x03, ++0x82, ++0x01, ++0x01, ++0x00, ++0x20, ++0x44, ++0xfe, ++0xa9, ++0x9e, ++0xdd, ++0x9b, ++0xea, ++0xce, ++0x25, ++0x75, ++0x08, ++0xf0, ++0x2b, ++0x53, ++0xf7, ++0x5a, ++0x36, ++0x1c, ++0x4a, ++0x23, ++0x7f, ++0xd0, ++0x41, ++0x3c, ++0x12, ++0x2b, ++0xb9, ++0x80, ++0x4e, ++0x8a, ++0x15, ++0x5d, ++0x1f, ++0x40, ++0xa7, ++0x26, ++0x28, ++0x32, ++0xc3, ++0x5b, ++0x06, ++0x28, ++0x2d, ++0x3d, ++0x08, ++0x09, ++0x1e, ++0x01, ++0xe9, ++0x67, ++0xe3, ++0x33, ++0xe6, ++0x15, ++0x45, ++0x39, ++0xee, ++0x17, ++0x83, ++0xdb, ++0x42, ++0xff, ++0x7f, ++0x35, ++0xf4, ++0xac, ++0x16, ++0xdb, ++0xba, ++0xb8, ++0x1a, ++0x20, ++0x21, ++0x41, ++0xff, ++0xf3, ++0x92, ++0xff, ++0x65, ++0x6e, ++0x29, ++0x16, ++0xd0, ++0xbf, ++0x8d, ++0xdf, ++0x48, ++0x2c, ++0x73, ++0x36, ++0x7f, ++0x22, ++0xe6, ++0xee, ++0x78, ++0xb4, ++0x63, ++0x83, ++0x0e, ++0x39, ++0xeb, ++0xaf, ++0x10, ++0x2a, ++0x90, ++0xd3, ++0xfc, ++0xe6, ++0xc3, ++0x8f, ++0x97, ++0x5b, ++0x76, ++0xbf, ++0x9b, ++0xf5, ++0x98, ++0xd2, ++0x53, ++0x06, ++0x8b, ++0xf8, ++0xa4, ++0x04, ++0x9b, ++0x1b, ++0x62, ++0x6a, ++0x9d, ++0xac, ++0xe6, ++0x4b, ++0x0d, ++0xc9, ++0xd7, ++0x56, ++0x63, ++0x15, ++0x01, ++0x38, ++0x8c, ++0xbe, ++0xf1, ++0x44, ++0xc4, ++0x38, ++0x27, ++0xe0, ++0xcf, ++0x72, ++0xd6, ++0x3d, ++0xe4, ++0xf7, ++0x4b, ++0x3b, ++0xd2, ++0xb1, ++0x0c, ++0xd5, ++0x83, ++0x6d, ++0x1e, ++0x10, ++0x04, ++0x69, ++0x29, ++0x88, ++0x69, ++0xe0, ++0x7d, ++0xd7, ++0xdb, ++0xb4, ++0x59, ++0x72, ++0x8d, ++0x9d, ++0x3c, ++0x43, ++0xaf, ++0xc6, ++0x7d, ++0xb7, ++0x21, ++0x15, ++0x52, ++0x8a, ++0xe9, ++0x9b, ++0x6b, ++0x2e, ++0xe8, ++0x27, ++0x3c, ++0x3f, ++0x2d, ++0x84, ++0xfb, ++0x9a, ++0x22, ++0x0a, ++0x9f, ++0x6a, ++0x25, ++0xe6, ++0x39, ++0xe4, ++0x74, ++0x73, ++0xb6, ++0x2a, ++0x70, ++0xaa, ++0x1d, ++0xcb, ++0xcc, ++0xd4, ++0xa0, ++0x1b, ++0x26, ++0x71, ++0x63, ++0x04, ++0xc5, ++0x12, ++0x21, ++0x48, ++0xba, ++0x92, ++0x27, ++0x06, ++0xa8, ++0x3e, ++0x6d, ++0xa1, ++0x43, ++0xa5, ++0xd2, ++0x2a, ++0xf7, ++0xca, ++0xc4, ++0x26, ++0xe8, ++0x5b, ++0x1f, ++0xe4, ++0xdc, ++0x89, ++0xdc, ++0x1f, ++0x04, ++0x79, ++0x3f, ++0x30, ++0x82, ++0x02, ++0xcd, ++0x30, ++0x82, ++0x01, ++0xb5, ++0x02, ++0x14, ++0x3a, ++0xbb, ++0xc6, ++0xec, ++0x14, ++0x6e, ++0x09, ++0xd1, ++0xb6, ++0x01, ++0x6a, ++0xb9, ++0xd6, ++0xcf, ++0x71, ++0xdd, ++0x23, ++0x3f, ++0x03, ++0x28, ++0x30, ++0x0d, ++0x06, ++0x09, ++0x2a, ++0x86, ++0x48, ++0x86, ++0xf7, ++0x0d, ++0x01, ++0x01, ++0x0b, ++0x05, ++0x00, ++0x30, ++0x22, ++0x31, ++0x20, ++0x30, ++0x1e, ++0x06, ++0x03, ++0x55, ++0x04, ++0x03, ++0x0c, ++0x17, ++0x72, ++0x6f, ++0x6d, ++0x61, ++0x69, ++0x6e, ++0x2e, ++0x70, ++0x65, ++0x72, ++0x69, ++0x65, ++0x72, ++0x40, ++0x67, ++0x6d, ++0x61, ++0x69, ++0x6c, ++0x2e, ++0x63, ++0x6f, ++0x6d, ++0x30, ++0x20, ++0x17, ++0x0d, ++0x32, ++0x30, ++0x30, ++0x32, ++0x32, ++0x34, ++0x31, ++0x39, ++0x30, ++0x31, ++0x34, ++0x34, ++0x5a, ++0x18, ++0x0f, ++0x32, ++0x31, ++0x32, ++0x30, ++0x30, ++0x31, ++0x33, ++0x31, ++0x31, ++0x39, ++0x30, ++0x31, ++0x34, ++0x34, ++0x5a, ++0x30, ++0x22, ++0x31, ++0x20, ++0x30, ++0x1e, ++0x06, ++0x03, ++0x55, ++0x04, ++0x03, ++0x0c, ++0x17, ++0x72, ++0x6f, ++0x6d, ++0x61, ++0x69, ++0x6e, ++0x2e, ++0x70, ++0x65, ++0x72, ++0x69, ++0x65, ++0x72, ++0x40, ++0x67, ++0x6d, ++0x61, ++0x69, ++0x6c, ++0x2e, ++0x63, ++0x6f, ++0x6d, ++0x30, ++0x82, ++0x01, ++0x22, ++0x30, ++0x0d, ++0x06, ++0x09, ++0x2a, ++0x86, ++0x48, ++0x86, ++0xf7, ++0x0d, ++0x01, ++0x01, ++0x01, ++0x05, ++0x00, ++0x03, ++0x82, ++0x01, ++0x0f, ++0x00, ++0x30, ++0x82, ++0x01, ++0x0a, ++0x02, ++0x82, ++0x01, ++0x01, ++0x00, ++0xf0, ++0xb8, ++0x4f, ++0x3f, ++0x70, ++0x78, ++0xf8, ++0x74, ++0x45, ++0xa2, ++0x28, ++0xaf, ++0x04, ++0x75, ++0x04, ++0xa3, ++0xf3, ++0xa7, ++0xc7, ++0x04, ++0xac, ++0xb6, ++0xe1, ++0xfc, ++0xe1, ++0xc0, ++0x3d, ++0xe0, ++0x26, ++0x90, ++0x8a, ++0x45, ++0x60, ++0xc4, ++0x75, ++0xf3, ++0x1a, ++0x33, ++0x37, ++0x56, ++0x7d, ++0x30, ++0x07, ++0x75, ++0x0e, ++0xa6, ++0x79, ++0x06, ++0x95, ++0x9d, ++0x17, ++0x3c, ++0x09, ++0xa9, ++0x7f, ++0xab, ++0x95, ++0x5d, ++0xed, ++0xe0, ++0x75, ++0x26, ++0x2f, ++0x65, ++0x65, ++0xcd, ++0x61, ++0xb1, ++0x33, ++0x27, ++0x67, ++0x41, ++0xa1, ++0x01, ++0x13, ++0xe9, ++0x13, ++0x6a, ++0x6d, ++0x4e, ++0x98, ++0xe1, ++0x9e, ++0x7b, ++0x0b, ++0x5b, ++0x44, ++0xef, ++0x68, ++0x5a, ++0x6f, ++0x7d, ++0x97, ++0xa1, ++0x33, ++0x22, ++0x97, ++0x12, ++0x21, ++0x09, ++0x8f, ++0x90, ++0xe0, ++0x25, ++0x94, ++0xdd, ++0x8a, ++0x3a, ++0xf7, ++0x4a, ++0x60, ++0x04, ++0x26, ++0x6d, ++0x00, ++0x82, ++0xe4, ++0xcf, ++0x64, ++0x1c, ++0x79, ++0x15, ++0x24, ++0xf2, ++0x42, ++0x86, ++0xf5, ++0x10, ++0x86, ++0xac, ++0x20, ++0x88, ++0x90, ++0x87, ++0xdf, ++0x8c, ++0x37, ++0x7c, ++0xbf, ++0x35, ++0xd5, ++0x6f, ++0x9f, ++0x77, ++0xc3, ++0xcd, ++0x69, ++0x25, ++0x06, ++0xc2, ++0x65, ++0x51, ++0x71, ++0x89, ++0x7f, ++0x6e, ++0x4d, ++0xe5, ++0xd5, ++0x8a, ++0x36, ++0x1a, ++0xad, ++0xc1, ++0x18, ++0xd6, ++0x14, ++0x42, ++0x87, ++0xf0, ++0x93, ++0x83, ++0xf1, ++0x99, ++0x74, ++0xc4, ++0x13, ++0xaa, ++0x3b, ++0x66, ++0x85, ++0x6f, ++0xe0, ++0xbc, ++0x5f, ++0xb6, ++0x40, ++0xa6, ++0x41, ++0x06, ++0x0a, ++0xba, ++0x0e, ++0xe9, ++0x32, ++0x44, ++0x10, ++0x39, ++0x53, ++0xcd, ++0xbf, ++0xf3, ++0xd3, ++0x26, ++0xf6, ++0xb6, ++0x2b, ++0x40, ++0x2e, ++0xb9, ++0x88, ++0xc1, ++0xf4, ++0xe3, ++0xa0, ++0x28, ++0x77, ++0x4f, ++0xba, ++0xa8, ++0xca, ++0x9c, ++0x05, ++0xba, ++0x88, ++0x96, ++0x99, ++0x54, ++0x89, ++0xa2, ++0x8d, ++0xf3, ++0x73, ++0xa1, ++0x8c, ++0x4a, ++0xa8, ++0x71, ++0xee, ++0x2e, ++0xd2, ++0x83, ++0x14, ++0x48, ++0xbd, ++0x98, ++0xc6, ++0xce, ++0xdc, ++0xa8, ++0xa3, ++0x97, ++0x2e, ++0x40, ++0x16, ++0x2f, ++0x02, ++0x03, ++0x01, ++0x00, ++0x01, ++0x30, ++0x0d, ++0x06, ++0x09, ++0x2a, ++0x86, ++0x48, ++0x86, ++0xf7, ++0x0d, ++0x01, ++0x01, ++0x0b, ++0x05, ++0x00, ++0x03, ++0x82, ++0x01, ++0x01, ++0x00, ++0x76, ++0x5d, ++0x03, ++0x3d, ++0xb6, ++0x96, ++0x00, ++0x1b, ++0x6e, ++0x0c, ++0xdd, ++0xbb, ++0xc8, ++0xdf, ++0xbc, ++0xeb, ++0x6c, ++0x01, ++0x40, ++0x1a, ++0x2b, ++0x07, ++0x60, ++0xa1, ++0x1a, ++0xe1, ++0x43, ++0x57, ++0xfa, ++0xbe, ++0xde, ++0xbb, ++0x8f, ++0x73, ++0xf3, ++0x92, ++0xa2, ++0xaa, ++0x83, ++0x01, ++0xc1, ++0x17, ++0xe4, ++0x9d, ++0x09, ++0x41, ++0xe0, ++0x32, ++0x33, ++0x97, ++0x4b, ++0xf2, ++0xdc, ++0x0f, ++0x8b, ++0xa8, ++0xb8, ++0x5a, ++0x04, ++0x86, ++0xf6, ++0x71, ++0xa1, ++0x97, ++0xd0, ++0x54, ++0x56, ++0x10, ++0x8e, ++0x54, ++0x99, ++0x0d, ++0x2a, ++0xa9, ++0xaf, ++0x1b, ++0x55, ++0x59, ++0x06, ++0x2b, ++0xa4, ++0x5f, ++0xb1, ++0x54, ++0xa6, ++0xec, ++0xc7, ++0xd6, ++0x43, ++0xee, ++0x86, ++0x2c, ++0x9b, ++0x18, ++0x9d, ++0x8f, ++0x00, ++0x82, ++0xc1, ++0x88, ++0x61, ++0x16, ++0x85, ++0x3c, ++0x17, ++0x56, ++0xfe, ++0x6a, ++0xa0, ++0x7a, ++0x68, ++0xc5, ++0x7b, ++0x3d, ++0x3c, ++0xb6, ++0x13, ++0x18, ++0x99, ++0x6d, ++0x74, ++0x65, ++0x13, ++0x67, ++0xb7, ++0xfc, ++0x5a, ++0x44, ++0x48, ++0x72, ++0xa0, ++0x73, ++0xb8, ++0xff, ++0x02, ++0x9d, ++0x7c, ++0x5b, ++0xf9, ++0x7c, ++0x75, ++0x0a, ++0x3c, ++0x81, ++0x80, ++0x3c, ++0x41, ++0xf2, ++0xd5, ++0xfa, ++0x3d, ++0x1f, ++0xe3, ++0xda, ++0x8c, ++0xa5, ++0x17, ++0x1f, ++0x53, ++0x1a, ++0x75, ++0xad, ++0x4e, ++0x11, ++0x1c, ++0x07, ++0xec, ++0x0a, ++0x69, ++0xfd, ++0x33, ++0xfa, ++0x32, ++0x7e, ++0x66, ++0xf5, ++0x29, ++0xe8, ++0x4d, ++0x8a, ++0xfa, ++0x0d, ++0x4b, ++0x68, ++0xc3, ++0x95, ++0x11, ++0xba, ++0x6f, ++0x1e, ++0x07, ++0x8c, ++0x85, ++0xc7, ++0xc7, ++0xc9, ++0xc1, ++0x30, ++0xa3, ++0x70, ++0xb0, ++0xa1, ++0xe0, ++0xd5, ++0x85, ++0x15, ++0x94, ++0x77, ++0xc1, ++0x1c, ++0x91, ++0xf1, ++0x5f, ++0x50, ++0xcd, ++0x2c, ++0x57, ++0x4b, ++0x22, ++0x4f, ++0xee, ++0x95, ++0xd7, ++0xa7, ++0xa4, ++0x59, ++0x62, ++0xae, ++0xb9, ++0xbf, ++0xd7, ++0x63, ++0x5a, ++0x04, ++0xfc, ++0x24, ++0x11, ++0xae, ++0x34, ++0x4b, ++0xf4, ++0x0c, ++0x9f, ++0x0b, ++0x59, ++0x7d, ++0x27, ++0x39, ++0x54, ++0x69, ++0x4f, ++0xfd, ++0x6e, ++0x44, ++0x9f, ++0x21, +-- +2.25.1 + diff --git a/debian/patches/debian/yama-disable-by-default.patch b/debian/patches/debian/yama-disable-by-default.patch new file mode 100644 index 000000000..c33ac0c9d --- /dev/null +++ b/debian/patches/debian/yama-disable-by-default.patch @@ -0,0 +1,32 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Subject: yama: Disable by default +Date: Wed, 19 Jun 2013 04:35:28 +0100 +Bug-Debian: https://bugs.debian.org/712740 +Forwarded: not-needed + +--- + security/yama/yama_lsm.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c +index efac68556b45..95ff3e778a17 100644 +--- a/security/yama/yama_lsm.c ++++ b/security/yama/yama_lsm.c +@@ -28,7 +28,7 @@ + #define YAMA_SCOPE_CAPABILITY 2 + #define YAMA_SCOPE_NO_ATTACH 3 + +-static int ptrace_scope = YAMA_SCOPE_RELATIONAL; ++static int ptrace_scope = YAMA_SCOPE_DISABLED; + + /* describe a ptrace relationship for potential exception */ + struct ptrace_relation { +@@ -481,7 +481,7 @@ static inline void yama_init_sysctl(void) { } + + static int __init yama_init(void) + { +- pr_info("Yama: becoming mindful.\n"); ++ pr_info("Yama: disabled by default; enable with sysctl kernel.yama.*\n"); + security_add_hooks(yama_hooks, ARRAY_SIZE(yama_hooks), "yama"); + yama_init_sysctl(); + return 0; diff --git a/debian/patches/features/all/db-mok-keyring/0003-MODSIGN-checking-the-blacklisted-hash-before-loading-a-kernel-module.patch b/debian/patches/features/all/db-mok-keyring/0003-MODSIGN-checking-the-blacklisted-hash-before-loading-a-kernel-module.patch new file mode 100644 index 000000000..f2278ce63 --- /dev/null +++ b/debian/patches/features/all/db-mok-keyring/0003-MODSIGN-checking-the-blacklisted-hash-before-loading-a-kernel-module.patch @@ -0,0 +1,130 @@ +From: "Lee, Chun-Yi" <joeyli.kernel@gmail.com> +Date: Tue, 13 Mar 2018 18:38:02 +0800 +Subject: [PATCH 3/4] MODSIGN: checking the blacklisted hash before loading a + kernel module +Origin: https://lore.kernel.org/patchwork/patch/933175/ + +This patch adds the logic for checking the kernel module's hash +base on blacklist. The hash must be generated by sha256 and enrolled +to dbx/mokx. + +For example: + sha256sum sample.ko + mokutil --mokx --import-hash $HASH_RESULT + +Whether the signature on ko file is stripped or not, the hash can be +compared by kernel. + +Cc: David Howells <dhowells@redhat.com> +Cc: Josh Boyer <jwboyer@fedoraproject.org> +Cc: James Bottomley <James.Bottomley@HansenPartnership.com> +Signed-off-by: "Lee, Chun-Yi" <jlee@suse.com> +[Rebased by Luca Boccassi] +[bwh: Forward-ported to 5.19: + - The type parameter to is_hash_blacklisted() is now an enumeration + rather than a string + - Adjust filename, context] +--- + kernel/module/signing.c | 59 +++++++++++++++++++++++++++++++++++++++-- + 1 file changed, 57 insertions(+), 2 deletions(-) + +--- a/kernel/module/signing.c ++++ b/kernel/module/signing.c +@@ -13,6 +13,8 @@ + #include <linux/verification.h> + #include <linux/security.h> + #include <crypto/public_key.h> ++#include <crypto/hash.h> ++#include <keys/system_keyring.h> + #include <uapi/linux/module.h> + #include "internal.h" + +@@ -37,13 +39,60 @@ + sig_enforce = true; + } + ++static int mod_is_hash_blacklisted(const void *mod, size_t verifylen) ++{ ++ struct crypto_shash *tfm; ++ struct shash_desc *desc; ++ size_t digest_size, desc_size; ++ u8 *digest; ++ int ret; ++ ++ tfm = crypto_alloc_shash("sha256", 0, 0); ++ if (IS_ERR(tfm)) { ++ ret = PTR_ERR(tfm); ++ goto error_return; ++ } ++ ++ desc_size = crypto_shash_descsize(tfm) + sizeof(*desc); ++ digest_size = crypto_shash_digestsize(tfm); ++ digest = kzalloc(digest_size + desc_size, GFP_KERNEL); ++ if (!digest) { ++ pr_err("digest memory buffer allocate fail\n"); ++ ret = -ENOMEM; ++ goto error_digest; ++ } ++ desc = (void *)digest + digest_size; ++ desc->tfm = tfm; ++ ret = crypto_shash_init(desc); ++ if (ret < 0) ++ goto error_shash; ++ ++ ret = crypto_shash_finup(desc, mod, verifylen, digest); ++ if (ret < 0) ++ goto error_shash; ++ ++ pr_debug("%ld digest: %*phN\n", verifylen, (int) digest_size, digest); ++ ++ ret = is_hash_blacklisted(digest, digest_size, BLACKLIST_HASH_BINARY); ++ if (ret == -EKEYREJECTED) ++ pr_err("Module hash %*phN is blacklisted\n", ++ (int) digest_size, digest); ++ ++error_shash: ++ kfree(digest); ++error_digest: ++ crypto_free_shash(tfm); ++error_return: ++ return ret; ++} ++ + /* + * Verify the signature on a module. + */ + int mod_verify_sig(const void *mod, struct load_info *info) + { + struct module_signature ms; +- size_t sig_len, modlen = info->len; ++ size_t sig_len, modlen = info->len, wholelen; + int ret; + + pr_devel("==>%s(,%zu)\n", __func__, modlen); +@@ -51,6 +100,7 @@ + if (modlen <= sizeof(ms)) + return -EBADMSG; + ++ wholelen = modlen + sizeof(MODULE_SIG_STRING) - 1; + memcpy(&ms, mod + (modlen - sizeof(ms)), sizeof(ms)); + + ret = mod_check_sig(&ms, modlen, "module"); +@@ -61,10 +111,17 @@ + modlen -= sig_len + sizeof(ms); + info->len = modlen; + +- return verify_pkcs7_signature(mod, modlen, mod + modlen, sig_len, ++ ret = verify_pkcs7_signature(mod, modlen, mod + modlen, sig_len, + VERIFY_USE_SECONDARY_KEYRING, + VERIFYING_MODULE_SIGNATURE, + NULL, NULL); ++ pr_devel("verify_pkcs7_signature() = %d\n", ret); ++ ++ /* checking hash of module is in blacklist */ ++ if (!ret) ++ ret = mod_is_hash_blacklisted(mod, wholelen); ++ ++ return ret; + } + + int module_sig_check(struct load_info *info, int flags) diff --git a/debian/patches/features/all/db-mok-keyring/KEYS-Make-use-of-platform-keyring-for-module-signature.patch b/debian/patches/features/all/db-mok-keyring/KEYS-Make-use-of-platform-keyring-for-module-signature.patch new file mode 100644 index 000000000..e46aefe4d --- /dev/null +++ b/debian/patches/features/all/db-mok-keyring/KEYS-Make-use-of-platform-keyring-for-module-signature.patch @@ -0,0 +1,33 @@ +From: Robert Holmes <robeholmes@gmail.com> +Date: Tue, 23 Apr 2019 07:39:29 +0000 +Subject: [PATCH] KEYS: Make use of platform keyring for module signature + verify +Bug-Debian: https://bugs.debian.org/935945 +Bug-Debian: https://bugs.debian.org/1030200 +Origin: https://src.fedoraproject.org/rpms/kernel/raw/master/f/KEYS-Make-use-of-platform-keyring-for-module-signature.patch +Forwarded: https://lore.kernel.org/linux-modules/qvgp2il2co4iyxkzxvcs4p2bpyilqsbfgcprtpfrsajwae2etc@3z2s2o52i3xg/t/#u + +This allows a cert in DB to be used to sign modules, +in addition to certs in the MoK and built-in keyrings. + +Signed-off-by: Robert Holmes <robeholmes@gmail.com> +Signed-off-by: Jeremy Cline <jcline@redhat.com> +[bwh: Forward-ported to 5.19: adjust filename] +[наб: reinstate for 6.1, re-write description] +--- +--- a/kernel/module/signing.c ++++ b/kernel/module/signing.c +@@ -116,6 +116,13 @@ int mod_verify_sig(const void *mod, stru + VERIFYING_MODULE_SIGNATURE, + NULL, NULL); + pr_devel("verify_pkcs7_signature() = %d\n", ret); ++ if (ret == -ENOKEY && IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING)) { ++ ret = verify_pkcs7_signature(mod, modlen, mod + modlen, sig_len, ++ VERIFY_USE_PLATFORM_KEYRING, ++ VERIFYING_MODULE_SIGNATURE, ++ NULL, NULL); ++ pr_devel("verify_pkcs7_signature() = %d\n", ret); ++ } + + /* checking hash of module is in blacklist */ + if (!ret) diff --git a/debian/patches/features/all/db-mok-keyring/trust-machine-keyring-by-default.patch b/debian/patches/features/all/db-mok-keyring/trust-machine-keyring-by-default.patch new file mode 100644 index 000000000..7c32a018f --- /dev/null +++ b/debian/patches/features/all/db-mok-keyring/trust-machine-keyring-by-default.patch @@ -0,0 +1,16 @@ +Author: Luca Boccassi <bluca@debian.org> +Description: trust machine keyring (MoK) by default + Debian always trusted keys in MoK by default. Upstream made it conditional on + a new EFI variable being set. To keep backward compatibility skip this check. +--- a/security/integrity/platform_certs/machine_keyring.c ++++ b/security/integrity/platform_certs/machine_keyring.c +@@ -69,8 +69,7 @@ + if (!initialized) { + initialized = true; + +- if (uefi_check_trust_mok_keys()) +- trust_mok = true; ++ trust_mok = true; + } + + return trust_mok; diff --git a/debian/patches/features/all/drivers-media-dvb-usb-af9005-request_firmware.patch b/debian/patches/features/all/drivers-media-dvb-usb-af9005-request_firmware.patch new file mode 100644 index 000000000..a24ba17ef --- /dev/null +++ b/debian/patches/features/all/drivers-media-dvb-usb-af9005-request_firmware.patch @@ -0,0 +1,149 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Mon, 24 Aug 2009 23:19:58 +0100 +Subject: af9005: Use request_firmware() to load register init script +Forwarded: no + +Read the register init script from the Windows driver. This is sick +but should avoid the potential copyright infringement in distributing +a version of the script which is directly derived from the driver. +--- + drivers/media/dvb/dvb-usb/Kconfig | 2 +- + drivers/media/dvb/dvb-usb/af9005-fe.c | 66 ++++++++++++++++++++++++++------ + 2 files changed, 54 insertions(+), 14 deletions(-) + +Index: debian-kernel/drivers/media/usb/dvb-usb/Kconfig +=================================================================== +--- debian-kernel.orig/drivers/media/usb/dvb-usb/Kconfig ++++ debian-kernel/drivers/media/usb/dvb-usb/Kconfig +@@ -260,10 +260,10 @@ config DVB_USB_OPERA1 + + config DVB_USB_AF9005 + tristate "Afatech AF9005 DVB-T USB1.1 support" +- depends on BROKEN + depends on DVB_USB + select MEDIA_TUNER_MT2060 if MEDIA_SUBDRV_AUTOSELECT + select MEDIA_TUNER_QT1010 if MEDIA_SUBDRV_AUTOSELECT ++ select FW_LOADER + help + Say Y here to support the Afatech AF9005 based DVB-T USB1.1 receiver + and the TerraTec Cinergy T USB XE (Rev.1) +Index: debian-kernel/drivers/media/usb/dvb-usb/af9005-fe.c +=================================================================== +--- debian-kernel.orig/drivers/media/usb/dvb-usb/af9005-fe.c ++++ debian-kernel/drivers/media/usb/dvb-usb/af9005-fe.c +@@ -9,10 +9,26 @@ + * see Documentation/driver-api/media/drivers/dvb-usb.rst for more information + */ + #include "af9005.h" +-#include "af9005-script.h" + #include "mt2060.h" + #include "qt1010.h" + #include <asm/div64.h> ++#include <linux/firmware.h> ++ ++/* Register initialisation script to be extracted from the Windows driver */ ++ ++typedef struct { ++ __le16 reg; ++ u8 pos; ++ u8 len; ++ u8 val; ++ u8 pad; ++} __packed RegDesc; ++ ++#define WIN_DRV_NAME "AF05BDA.sys" ++#define WIN_DRV_VERSION "6.3.2.1" ++#define WIN_DRV_SIZE 133504 ++#define WIN_DRV_SCRIPT_OFFSET 88316 ++#define WIN_DRV_SCRIPT_SIZE 1110 + + struct af9005_fe_state { + struct dvb_usb_device *d; +@@ -804,6 +820,8 @@ static int af9005_fe_init(struct dvb_fro + { + struct af9005_fe_state *state = fe->demodulator_priv; + struct dvb_usb_adapter *adap = fe->dvb->priv; ++ const struct firmware *fw; ++ const RegDesc *script; + int ret, i, scriptlen; + u8 temp, temp0 = 0, temp1 = 0, temp2 = 0; + u8 buf[2]; +@@ -956,37 +974,55 @@ static int af9005_fe_init(struct dvb_fro + if ((ret = af9005_write_ofdm_register(state->d, 0xaefb, 0x01))) + return ret; + +- /* load init script */ +- deb_info("load init script\n"); +- scriptlen = sizeof(script) / sizeof(RegDesc); ++ /* load and validate init script */ ++ deb_info("load init script from Windows driver\n"); ++ ret = request_firmware(&fw, WIN_DRV_NAME, &state->d->udev->dev); ++ if (ret) ++ return ret; ++ BUILD_BUG_ON(sizeof(RegDesc) != 6); ++ if (fw->size != WIN_DRV_SIZE || ++ memcmp(fw->data + WIN_DRV_SCRIPT_OFFSET, ++ "\x80\xa1\x00\x08\x0a\x00", 6) || ++ memcmp(fw->data + WIN_DRV_SCRIPT_OFFSET + WIN_DRV_SCRIPT_SIZE - 6, ++ "\x49\xa3\x00\x06\x02\x00", 6)) { ++ err("%s is invalid - should be version %s, size %u bytes\n", ++ WIN_DRV_NAME, WIN_DRV_VERSION, WIN_DRV_SIZE); ++ ret = -EINVAL; ++ goto fail_release; ++ } ++ ++ script = (const RegDesc *)(fw->data + WIN_DRV_SCRIPT_OFFSET); ++ scriptlen = WIN_DRV_SCRIPT_SIZE / sizeof(RegDesc); + for (i = 0; i < scriptlen; i++) { ++ u16 reg = le16_to_cpu(script[i].reg); + if ((ret = +- af9005_write_register_bits(state->d, script[i].reg, ++ af9005_write_register_bits(state->d, reg, + script[i].pos, + script[i].len, script[i].val))) +- return ret; ++ goto fail_release; + /* save 3 bytes of original fcw */ +- if (script[i].reg == 0xae18) ++ if (reg == 0xae18) + temp2 = script[i].val; +- if (script[i].reg == 0xae19) ++ if (reg == 0xae19) + temp1 = script[i].val; +- if (script[i].reg == 0xae1a) ++ if (reg == 0xae1a) + temp0 = script[i].val; + + /* save original unplug threshold */ +- if (script[i].reg == xd_p_reg_unplug_th) ++ if (reg == xd_p_reg_unplug_th) + state->original_if_unplug_th = script[i].val; +- if (script[i].reg == xd_p_reg_unplug_rf_gain_th) ++ if (reg == xd_p_reg_unplug_rf_gain_th) + state->original_rf_unplug_th = script[i].val; +- if (script[i].reg == xd_p_reg_unplug_dtop_if_gain_th) ++ if (reg == xd_p_reg_unplug_dtop_if_gain_th) + state->original_dtop_if_unplug_th = script[i].val; +- if (script[i].reg == xd_p_reg_unplug_dtop_rf_gain_th) ++ if (reg == xd_p_reg_unplug_dtop_rf_gain_th) + state->original_dtop_rf_unplug_th = script[i].val; + + } + state->original_fcw = + ((u32) temp2 << 16) + ((u32) temp1 << 8) + (u32) temp0; + ++ release_firmware(fw); + + /* save original TOPs */ + deb_info("save original TOPs\n"); +@@ -1066,6 +1102,10 @@ static int af9005_fe_init(struct dvb_fro + + deb_info("profit!\n"); + return 0; ++ ++fail_release: ++ release_firmware(fw); ++ return ret; + } + + static int af9005_fe_sleep(struct dvb_frontend *fe) diff --git a/debian/patches/features/all/ethernet-microsoft/0001-net-Remove-the-obsolte-u64_stats_fetch_-_irq-users-d.patch b/debian/patches/features/all/ethernet-microsoft/0001-net-Remove-the-obsolte-u64_stats_fetch_-_irq-users-d.patch new file mode 100644 index 000000000..f17692d6c --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0001-net-Remove-the-obsolte-u64_stats_fetch_-_irq-users-d.patch @@ -0,0 +1,89 @@ +From 7c765fdf86fc9089b75d15ee33cdf30d9d9115d6 Mon Sep 17 00:00:00 2001 +From: Bastian Blank <waldi@debian.org> +Date: Wed, 12 Jul 2023 14:13:14 +0000 +Subject: [PATCH 01/23] net: Remove the obsolte u64_stats_fetch_*_irq() users + (drivers). + +Now that the 32bit UP oddity is gone and 32bit uses always a sequence +count, there is no need for the fetch_irq() variants anymore. + +Convert to the regular interface. + +Signed-off-by: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> +Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> +Signed-off-by: Jakub Kicinski <kuba@kernel.org> +(cherry picked from commit 068c38ad88ccb09e5e966d4db5cedab0e02b3b95) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana_en.c | 8 ++++---- + drivers/net/ethernet/microsoft/mana/mana_ethtool.c | 8 ++++---- + 2 files changed, 8 insertions(+), 8 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index 27a0f3af8aab..aec4bab6be56 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -315,10 +315,10 @@ static void mana_get_stats64(struct net_device *ndev, + rx_stats = &apc->rxqs[q]->stats; + + do { +- start = u64_stats_fetch_begin_irq(&rx_stats->syncp); ++ start = u64_stats_fetch_begin(&rx_stats->syncp); + packets = rx_stats->packets; + bytes = rx_stats->bytes; +- } while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&rx_stats->syncp, start)); + + st->rx_packets += packets; + st->rx_bytes += bytes; +@@ -328,10 +328,10 @@ static void mana_get_stats64(struct net_device *ndev, + tx_stats = &apc->tx_qp[q].txq.stats; + + do { +- start = u64_stats_fetch_begin_irq(&tx_stats->syncp); ++ start = u64_stats_fetch_begin(&tx_stats->syncp); + packets = tx_stats->packets; + bytes = tx_stats->bytes; +- } while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&tx_stats->syncp, start)); + + st->tx_packets += packets; + st->tx_bytes += bytes; +diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +index c530db76880f..96d55c91c969 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +@@ -90,13 +90,13 @@ static void mana_get_ethtool_stats(struct net_device *ndev, + rx_stats = &apc->rxqs[q]->stats; + + do { +- start = u64_stats_fetch_begin_irq(&rx_stats->syncp); ++ start = u64_stats_fetch_begin(&rx_stats->syncp); + packets = rx_stats->packets; + bytes = rx_stats->bytes; + xdp_drop = rx_stats->xdp_drop; + xdp_tx = rx_stats->xdp_tx; + xdp_redirect = rx_stats->xdp_redirect; +- } while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&rx_stats->syncp, start)); + + data[i++] = packets; + data[i++] = bytes; +@@ -109,11 +109,11 @@ static void mana_get_ethtool_stats(struct net_device *ndev, + tx_stats = &apc->tx_qp[q].txq.stats; + + do { +- start = u64_stats_fetch_begin_irq(&tx_stats->syncp); ++ start = u64_stats_fetch_begin(&tx_stats->syncp); + packets = tx_stats->packets; + bytes = tx_stats->bytes; + xdp_xmit = tx_stats->xdp_xmit; +- } while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start)); ++ } while (u64_stats_fetch_retry(&tx_stats->syncp, start)); + + data[i++] = packets; + data[i++] = bytes; +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0002-net-mana-Assign-interrupts-to-CPUs-based-on-NUMA-nod.patch b/debian/patches/features/all/ethernet-microsoft/0002-net-mana-Assign-interrupts-to-CPUs-based-on-NUMA-nod.patch new file mode 100644 index 000000000..6fc9d9cc7 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0002-net-mana-Assign-interrupts-to-CPUs-based-on-NUMA-nod.patch @@ -0,0 +1,114 @@ +From 8bdc2e0b4963e7cfd41b43ed117e8f0dec13fe29 Mon Sep 17 00:00:00 2001 +From: Saurabh Sengar <ssengar@linux.microsoft.com> +Date: Mon, 31 Oct 2022 23:06:01 -0700 +Subject: [PATCH 02/23] net: mana: Assign interrupts to CPUs based on NUMA + nodes + +In large VMs with multiple NUMA nodes, network performance is usually +best if network interrupts are all assigned to the same virtual NUMA +node. This patch assigns online CPU according to a numa aware policy, +local cpus are returned first, followed by non-local ones, then it wraps +around. + +Signed-off-by: Saurabh Sengar <ssengar@linux.microsoft.com> +Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> +Link: https://lore.kernel.org/r/1667282761-11547-1-git-send-email-ssengar@linux.microsoft.com +Signed-off-by: Paolo Abeni <pabeni@redhat.com> +(cherry picked from commit 71fa6887eeca7b631528f9c7a39815498de8028c) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/gdma.h | 1 + + .../net/ethernet/microsoft/mana/gdma_main.c | 30 +++++++++++++++++-- + 2 files changed, 28 insertions(+), 3 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/gdma.h b/drivers/net/ethernet/microsoft/mana/gdma.h +index 48b0ab56bdb0..68684a8bcead 100644 +--- a/drivers/net/ethernet/microsoft/mana/gdma.h ++++ b/drivers/net/ethernet/microsoft/mana/gdma.h +@@ -356,6 +356,7 @@ struct gdma_context { + void __iomem *shm_base; + void __iomem *db_page_base; + u32 db_page_size; ++ int numa_node; + + /* Shared memory chanenl (used to bootstrap HWC) */ + struct shm_channel shm_channel; +diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c +index d674ebda2053..abe9888a40aa 100644 +--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c ++++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c +@@ -1208,8 +1208,10 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) + struct gdma_context *gc = pci_get_drvdata(pdev); + struct gdma_irq_context *gic; + unsigned int max_irqs; ++ u16 *cpus; ++ cpumask_var_t req_mask; + int nvec, irq; +- int err, i, j; ++ int err, i = 0, j; + + if (max_queues_per_port > MANA_MAX_NUM_QUEUES) + max_queues_per_port = MANA_MAX_NUM_QUEUES; +@@ -1228,7 +1230,21 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) + goto free_irq_vector; + } + ++ if (!zalloc_cpumask_var(&req_mask, GFP_KERNEL)) { ++ err = -ENOMEM; ++ goto free_irq; ++ } ++ ++ cpus = kcalloc(nvec, sizeof(*cpus), GFP_KERNEL); ++ if (!cpus) { ++ err = -ENOMEM; ++ goto free_mask; ++ } ++ for (i = 0; i < nvec; i++) ++ cpus[i] = cpumask_local_spread(i, gc->numa_node); ++ + for (i = 0; i < nvec; i++) { ++ cpumask_set_cpu(cpus[i], req_mask); + gic = &gc->irq_contexts[i]; + gic->handler = NULL; + gic->arg = NULL; +@@ -1243,13 +1259,17 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) + irq = pci_irq_vector(pdev, i); + if (irq < 0) { + err = irq; +- goto free_irq; ++ goto free_mask; + } + + err = request_irq(irq, mana_gd_intr, 0, gic->name, gic); + if (err) +- goto free_irq; ++ goto free_mask; ++ irq_set_affinity_and_hint(irq, req_mask); ++ cpumask_clear(req_mask); + } ++ free_cpumask_var(req_mask); ++ kfree(cpus); + + err = mana_gd_alloc_res_map(nvec, &gc->msix_resource); + if (err) +@@ -1260,6 +1280,9 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) + + return 0; + ++free_mask: ++ free_cpumask_var(req_mask); ++ kfree(cpus); + free_irq: + for (j = i - 1; j >= 0; j--) { + irq = pci_irq_vector(pdev, j); +@@ -1389,6 +1412,7 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) + if (!bar0_va) + goto free_gc; + ++ gc->numa_node = dev_to_node(&pdev->dev); + gc->is_pf = mana_is_pf(pdev->device); + gc->bar0_va = bar0_va; + gc->dev = &pdev->dev; +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0003-net-mana-Add-support-for-auxiliary-device.patch b/debian/patches/features/all/ethernet-microsoft/0003-net-mana-Add-support-for-auxiliary-device.patch new file mode 100644 index 000000000..a639b69c9 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0003-net-mana-Add-support-for-auxiliary-device.patch @@ -0,0 +1,178 @@ +From 63ea159035f1c00da99016a1c71380d90f156ad4 Mon Sep 17 00:00:00 2001 +From: Long Li <longli@microsoft.com> +Date: Thu, 3 Nov 2022 12:16:19 -0700 +Subject: [PATCH 03/23] net: mana: Add support for auxiliary device + +In preparation for supporting MANA RDMA driver, add support for auxiliary +device in the Ethernet driver. The RDMA device is modeled as an auxiliary +device to the Ethernet device. + +Reviewed-by: Dexuan Cui <decui@microsoft.com> +Signed-off-by: Long Li <longli@microsoft.com> +Link: https://lore.kernel.org/r/1667502990-2559-2-git-send-email-longli@linuxonhyperv.com +Acked-by: Haiyang Zhang <haiyangz@microsoft.com> +Signed-off-by: Leon Romanovsky <leonro@nvidia.com> +(cherry picked from commit a69839d4327d053b18d8e1b0e7ddeee78db78f4f) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/Kconfig | 1 + + drivers/net/ethernet/microsoft/mana/gdma.h | 2 + + .../ethernet/microsoft/mana/mana_auxiliary.h | 10 +++ + drivers/net/ethernet/microsoft/mana/mana_en.c | 83 ++++++++++++++++++- + 4 files changed, 95 insertions(+), 1 deletion(-) + create mode 100644 drivers/net/ethernet/microsoft/mana/mana_auxiliary.h + +--- a/drivers/net/ethernet/microsoft/Kconfig ++++ b/drivers/net/ethernet/microsoft/Kconfig +@@ -19,6 +19,7 @@ config MICROSOFT_MANA + tristate "Microsoft Azure Network Adapter (MANA) support" + depends on PCI_MSI && X86_64 + depends on PCI_HYPERV ++ select AUXILIARY_BUS + select PAGE_POOL + help + This driver supports Microsoft Azure Network Adapter (MANA). +--- a/drivers/net/ethernet/microsoft/mana/gdma.h ++++ b/drivers/net/ethernet/microsoft/mana/gdma.h +@@ -204,6 +204,8 @@ struct gdma_dev { + + /* GDMA driver specific pointer */ + void *driver_data; ++ ++ struct auxiliary_device *adev; + }; + + #define MINIMUM_SUPPORTED_PAGE_SIZE PAGE_SIZE +--- /dev/null ++++ b/drivers/net/ethernet/microsoft/mana/mana_auxiliary.h +@@ -0,0 +1,10 @@ ++/* SPDX-License-Identifier: GPL-2.0-only */ ++/* Copyright (c) 2022, Microsoft Corporation. */ ++ ++#include "mana.h" ++#include <linux/auxiliary_bus.h> ++ ++struct mana_adev { ++ struct auxiliary_device adev; ++ struct gdma_dev *mdev; ++}; +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -14,6 +14,19 @@ + #include <net/ip6_checksum.h> + + #include "mana.h" ++#include "mana_auxiliary.h" ++ ++static DEFINE_IDA(mana_adev_ida); ++ ++static int mana_adev_idx_alloc(void) ++{ ++ return ida_alloc(&mana_adev_ida, GFP_KERNEL); ++} ++ ++static void mana_adev_idx_free(int idx) ++{ ++ ida_free(&mana_adev_ida, idx); ++} + + /* Microsoft Azure Network Adapter (MANA) functions */ + +@@ -2145,6 +2158,69 @@ free_net: + return err; + } + ++static void adev_release(struct device *dev) ++{ ++ struct mana_adev *madev = container_of(dev, struct mana_adev, adev.dev); ++ ++ kfree(madev); ++} ++ ++static void remove_adev(struct gdma_dev *gd) ++{ ++ struct auxiliary_device *adev = gd->adev; ++ int id = adev->id; ++ ++ auxiliary_device_delete(adev); ++ auxiliary_device_uninit(adev); ++ ++ mana_adev_idx_free(id); ++ gd->adev = NULL; ++} ++ ++static int add_adev(struct gdma_dev *gd) ++{ ++ struct auxiliary_device *adev; ++ struct mana_adev *madev; ++ int ret; ++ ++ madev = kzalloc(sizeof(*madev), GFP_KERNEL); ++ if (!madev) ++ return -ENOMEM; ++ ++ adev = &madev->adev; ++ ret = mana_adev_idx_alloc(); ++ if (ret < 0) ++ goto idx_fail; ++ adev->id = ret; ++ ++ adev->name = "rdma"; ++ adev->dev.parent = gd->gdma_context->dev; ++ adev->dev.release = adev_release; ++ madev->mdev = gd; ++ ++ ret = auxiliary_device_init(adev); ++ if (ret) ++ goto init_fail; ++ ++ ret = auxiliary_device_add(adev); ++ if (ret) ++ goto add_fail; ++ ++ gd->adev = adev; ++ return 0; ++ ++add_fail: ++ auxiliary_device_uninit(adev); ++ ++init_fail: ++ mana_adev_idx_free(adev->id); ++ ++idx_fail: ++ kfree(madev); ++ ++ return ret; ++} ++ + int mana_probe(struct gdma_dev *gd, bool resuming) + { + struct gdma_context *gc = gd->gdma_context; +@@ -2212,6 +2288,8 @@ int mana_probe(struct gdma_dev *gd, bool + break; + } + } ++ ++ err = add_adev(gd); + out: + if (err) + mana_remove(gd, false); +@@ -2228,6 +2306,10 @@ void mana_remove(struct gdma_dev *gd, bo + int err; + int i; + ++ /* adev currently doesn't support suspending, always remove it */ ++ if (gd->adev) ++ remove_adev(gd); ++ + for (i = 0; i < ac->num_ports; i++) { + ndev = ac->ports[i]; + if (!ndev) { +@@ -2260,7 +2342,6 @@ void mana_remove(struct gdma_dev *gd, bo + } + + mana_destroy_eq(ac); +- + out: + mana_gd_deregister_device(gd); + diff --git a/debian/patches/features/all/ethernet-microsoft/0004-net-mana-Record-the-physical-address-for-doorbell-pa.patch b/debian/patches/features/all/ethernet-microsoft/0004-net-mana-Record-the-physical-address-for-doorbell-pa.patch new file mode 100644 index 000000000..21568f6aa --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0004-net-mana-Record-the-physical-address-for-doorbell-pa.patch @@ -0,0 +1,63 @@ +From 108ed3960c8f1e65ad64b22a4a073c4e42204132 Mon Sep 17 00:00:00 2001 +From: Long Li <longli@microsoft.com> +Date: Thu, 3 Nov 2022 12:16:20 -0700 +Subject: [PATCH 04/23] net: mana: Record the physical address for doorbell + page region + +For supporting RDMA device with multiple user contexts with their +individual doorbell pages, record the start address of doorbell page +region for use by the RDMA driver to allocate user context doorbell IDs. + +Reviewed-by: Dexuan Cui <decui@microsoft.com> +Signed-off-by: Long Li <longli@microsoft.com> +Link: https://lore.kernel.org/r/1667502990-2559-3-git-send-email-longli@linuxonhyperv.com +Acked-by: Haiyang Zhang <haiyangz@microsoft.com> +Signed-off-by: Leon Romanovsky <leonro@nvidia.com> +(cherry picked from commit f3dc096246091048677c45cfc0e24ad512927b52) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/gdma.h | 2 ++ + drivers/net/ethernet/microsoft/mana/gdma_main.c | 4 ++++ + 2 files changed, 6 insertions(+) + +diff --git a/drivers/net/ethernet/microsoft/mana/gdma.h b/drivers/net/ethernet/microsoft/mana/gdma.h +index df0ffe35db92..86d8a9e36005 100644 +--- a/drivers/net/ethernet/microsoft/mana/gdma.h ++++ b/drivers/net/ethernet/microsoft/mana/gdma.h +@@ -354,9 +354,11 @@ struct gdma_context { + u32 test_event_eq_id; + + bool is_pf; ++ phys_addr_t bar0_pa; + void __iomem *bar0_va; + void __iomem *shm_base; + void __iomem *db_page_base; ++ phys_addr_t phys_db_page_base; + u32 db_page_size; + int numa_node; + +diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c +index abe9888a40aa..a00bd88443d3 100644 +--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c ++++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c +@@ -44,6 +44,9 @@ static void mana_gd_init_vf_regs(struct pci_dev *pdev) + gc->db_page_base = gc->bar0_va + + mana_gd_r64(gc, GDMA_REG_DB_PAGE_OFFSET); + ++ gc->phys_db_page_base = gc->bar0_pa + ++ mana_gd_r64(gc, GDMA_REG_DB_PAGE_OFFSET); ++ + gc->shm_base = gc->bar0_va + mana_gd_r64(gc, GDMA_REG_SHM_OFFSET); + } + +@@ -1407,6 +1410,7 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) + + mutex_init(&gc->eq_test_event_mutex); + pci_set_drvdata(pdev, gc); ++ gc->bar0_pa = pci_resource_start(pdev, 0); + + bar0_va = pci_iomap(pdev, bar, 0); + if (!bar0_va) +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0005-net-mana-Handle-vport-sharing-between-devices.patch b/debian/patches/features/all/ethernet-microsoft/0005-net-mana-Handle-vport-sharing-between-devices.patch new file mode 100644 index 000000000..f02172221 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0005-net-mana-Handle-vport-sharing-between-devices.patch @@ -0,0 +1,150 @@ +From 35238c1a74198a73e35ed386a7a3992522de804d Mon Sep 17 00:00:00 2001 +From: Long Li <longli@microsoft.com> +Date: Thu, 3 Nov 2022 12:16:21 -0700 +Subject: [PATCH 05/23] net: mana: Handle vport sharing between devices + +For outgoing packets, the PF requires the VF to configure the vport with +corresponding protection domain and doorbell ID for the kernel or user +context. The vport can't be shared between different contexts. + +Implement the logic to exclusively take over the vport by either the +Ethernet device or RDMA device. + +Reviewed-by: Dexuan Cui <decui@microsoft.com> +Signed-off-by: Long Li <longli@microsoft.com> +Link: https://lore.kernel.org/r/1667502990-2559-4-git-send-email-longli@linuxonhyperv.com +Acked-by: Haiyang Zhang <haiyangz@microsoft.com> +Signed-off-by: Leon Romanovsky <leonro@nvidia.com> +(cherry picked from commit b5c1c9855be3b5b978fde975a63df3cabc273faa) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana.h | 7 +++ + drivers/net/ethernet/microsoft/mana/mana_en.c | 53 ++++++++++++++++++- + 2 files changed, 58 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana.h b/drivers/net/ethernet/microsoft/mana/mana.h +index d58be64374c8..2883a08dbfb5 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana.h ++++ b/drivers/net/ethernet/microsoft/mana/mana.h +@@ -380,6 +380,10 @@ struct mana_port_context { + mana_handle_t port_handle; + mana_handle_t pf_filter_handle; + ++ /* Mutex for sharing access to vport_use_count */ ++ struct mutex vport_mutex; ++ int vport_use_count; ++ + u16 port_idx; + + bool port_is_up; +@@ -631,4 +635,7 @@ struct mana_tx_package { + struct gdma_posted_wqe_info wqe_info; + }; + ++int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, ++ u32 doorbell_pg_id); ++void mana_uncfg_vport(struct mana_port_context *apc); + #endif /* _MANA_H */ +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index b9e2723ce167..c5ab5cb63cb7 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -646,13 +646,48 @@ static int mana_query_vport_cfg(struct mana_port_context *apc, u32 vport_index, + return 0; + } + +-static int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, +- u32 doorbell_pg_id) ++void mana_uncfg_vport(struct mana_port_context *apc) ++{ ++ mutex_lock(&apc->vport_mutex); ++ apc->vport_use_count--; ++ WARN_ON(apc->vport_use_count < 0); ++ mutex_unlock(&apc->vport_mutex); ++} ++EXPORT_SYMBOL_NS(mana_uncfg_vport, NET_MANA); ++ ++int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, ++ u32 doorbell_pg_id) + { + struct mana_config_vport_resp resp = {}; + struct mana_config_vport_req req = {}; + int err; + ++ /* This function is used to program the Ethernet port in the hardware ++ * table. It can be called from the Ethernet driver or the RDMA driver. ++ * ++ * For Ethernet usage, the hardware supports only one active user on a ++ * physical port. The driver checks on the port usage before programming ++ * the hardware when creating the RAW QP (RDMA driver) or exposing the ++ * device to kernel NET layer (Ethernet driver). ++ * ++ * Because the RDMA driver doesn't know in advance which QP type the ++ * user will create, it exposes the device with all its ports. The user ++ * may not be able to create RAW QP on a port if this port is already ++ * in used by the Ethernet driver from the kernel. ++ * ++ * This physical port limitation only applies to the RAW QP. For RC QP, ++ * the hardware doesn't have this limitation. The user can create RC ++ * QPs on a physical port up to the hardware limits independent of the ++ * Ethernet usage on the same port. ++ */ ++ mutex_lock(&apc->vport_mutex); ++ if (apc->vport_use_count > 0) { ++ mutex_unlock(&apc->vport_mutex); ++ return -EBUSY; ++ } ++ apc->vport_use_count++; ++ mutex_unlock(&apc->vport_mutex); ++ + mana_gd_init_req_hdr(&req.hdr, MANA_CONFIG_VPORT_TX, + sizeof(req), sizeof(resp)); + req.vport = apc->port_handle; +@@ -679,9 +714,16 @@ static int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, + + apc->tx_shortform_allowed = resp.short_form_allowed; + apc->tx_vp_offset = resp.tx_vport_offset; ++ ++ netdev_info(apc->ndev, "Configured vPort %llu PD %u DB %u\n", ++ apc->port_handle, protection_dom_id, doorbell_pg_id); + out: ++ if (err) ++ mana_uncfg_vport(apc); ++ + return err; + } ++EXPORT_SYMBOL_NS(mana_cfg_vport, NET_MANA); + + static int mana_cfg_vport_steering(struct mana_port_context *apc, + enum TRI_STATE rx, +@@ -742,6 +784,9 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc, + resp.hdr.status); + err = -EPROTO; + } ++ ++ netdev_info(ndev, "Configured steering vPort %llu entries %u\n", ++ apc->port_handle, num_entries); + out: + kfree(req); + return err; +@@ -1810,6 +1855,7 @@ static void mana_destroy_vport(struct mana_port_context *apc) + } + + mana_destroy_txq(apc); ++ mana_uncfg_vport(apc); + + if (gd->gdma_context->is_pf) + mana_pf_deregister_hw_vport(apc); +@@ -2082,6 +2128,9 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, + apc->pf_filter_handle = INVALID_MANA_HANDLE; + apc->port_idx = port_idx; + ++ mutex_init(&apc->vport_mutex); ++ apc->vport_use_count = 0; ++ + ndev->netdev_ops = &mana_devops; + ndev->ethtool_ops = &mana_ethtool_ops; + ndev->mtu = ETH_DATA_LEN; +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0006-net-mana-Set-the-DMA-device-max-segment-size.patch b/debian/patches/features/all/ethernet-microsoft/0006-net-mana-Set-the-DMA-device-max-segment-size.patch new file mode 100644 index 000000000..6ac8249d0 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0006-net-mana-Set-the-DMA-device-max-segment-size.patch @@ -0,0 +1,40 @@ +From 09b5391c16655893159fe8a58c8b7e31499ef107 Mon Sep 17 00:00:00 2001 +From: Ajay Sharma <sharmaajay@microsoft.com> +Date: Thu, 3 Nov 2022 12:16:22 -0700 +Subject: [PATCH 06/23] net: mana: Set the DMA device max segment size + +MANA hardware doesn't have any restrictions on the DMA segment size, set it +to the max allowed value. + +Signed-off-by: Ajay Sharma <sharmaajay@microsoft.com> +Reviewed-by: Dexuan Cui <decui@microsoft.com> +Signed-off-by: Long Li <longli@microsoft.com> +Link: https://lore.kernel.org/r/1667502990-2559-5-git-send-email-longli@linuxonhyperv.com +Acked-by: Haiyang Zhang <haiyangz@microsoft.com> +Signed-off-by: Leon Romanovsky <leonro@nvidia.com> +(cherry picked from commit 6fe254160bd033a1e62dbad9b734183b31144678) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/gdma_main.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c +index a00bd88443d3..bc00a7d07232 100644 +--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c ++++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c +@@ -1403,6 +1403,12 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) + if (err) + goto release_region; + ++ err = dma_set_max_seg_size(&pdev->dev, UINT_MAX); ++ if (err) { ++ dev_err(&pdev->dev, "Failed to set dma device segment size\n"); ++ goto release_region; ++ } ++ + err = -ENOMEM; + gc = vzalloc(sizeof(*gc)); + if (!gc) +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0007-net-mana-Export-Work-Queue-functions-for-use-by-RDMA.patch b/debian/patches/features/all/ethernet-microsoft/0007-net-mana-Export-Work-Queue-functions-for-use-by-RDMA.patch new file mode 100644 index 000000000..c846badc8 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0007-net-mana-Export-Work-Queue-functions-for-use-by-RDMA.patch @@ -0,0 +1,100 @@ +From 8334d5a28eb711b8f464e0bd3ec0f76b0594bf95 Mon Sep 17 00:00:00 2001 +From: Long Li <longli@microsoft.com> +Date: Thu, 3 Nov 2022 12:16:23 -0700 +Subject: [PATCH 07/23] net: mana: Export Work Queue functions for use by RDMA + driver + +RDMA device may need to create Ethernet device queues for use by Queue +Pair type RAW. This allows a user-mode context accesses Ethernet hardware +queues. Export the supporting functions for use by the RDMA driver. + +Reviewed-by: Dexuan Cui <decui@microsoft.com> +Signed-off-by: Long Li <longli@microsoft.com> +Link: https://lore.kernel.org/r/1667502990-2559-6-git-send-email-longli@linuxonhyperv.com +Acked-by: Haiyang Zhang <haiyangz@microsoft.com> +Signed-off-by: Leon Romanovsky <leonro@nvidia.com> +(cherry picked from commit 4c0ff7a106e16ab63e0b597557255c012f179578) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/gdma_main.c | 1 + + drivers/net/ethernet/microsoft/mana/mana.h | 9 +++++++++ + drivers/net/ethernet/microsoft/mana/mana_en.c | 16 +++++++++------- + 3 files changed, 19 insertions(+), 7 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c +index bc00a7d07232..d9be0f3044ea 100644 +--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c ++++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c +@@ -152,6 +152,7 @@ int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req, + + return mana_hwc_send_request(hwc, req_len, req, resp_len, resp); + } ++EXPORT_SYMBOL_NS(mana_gd_send_request, NET_MANA); + + int mana_gd_alloc_memory(struct gdma_context *gc, unsigned int length, + struct gdma_mem_info *gmi) +diff --git a/drivers/net/ethernet/microsoft/mana/mana.h b/drivers/net/ethernet/microsoft/mana/mana.h +index 2883a08dbfb5..6e9e86fb4c02 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana.h ++++ b/drivers/net/ethernet/microsoft/mana/mana.h +@@ -635,6 +635,15 @@ struct mana_tx_package { + struct gdma_posted_wqe_info wqe_info; + }; + ++int mana_create_wq_obj(struct mana_port_context *apc, ++ mana_handle_t vport, ++ u32 wq_type, struct mana_obj_spec *wq_spec, ++ struct mana_obj_spec *cq_spec, ++ mana_handle_t *wq_obj); ++ ++void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, ++ mana_handle_t wq_obj); ++ + int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, + u32 doorbell_pg_id); + void mana_uncfg_vport(struct mana_port_context *apc); +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index c5ab5cb63cb7..a526657f4edb 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -792,11 +792,11 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc, + return err; + } + +-static int mana_create_wq_obj(struct mana_port_context *apc, +- mana_handle_t vport, +- u32 wq_type, struct mana_obj_spec *wq_spec, +- struct mana_obj_spec *cq_spec, +- mana_handle_t *wq_obj) ++int mana_create_wq_obj(struct mana_port_context *apc, ++ mana_handle_t vport, ++ u32 wq_type, struct mana_obj_spec *wq_spec, ++ struct mana_obj_spec *cq_spec, ++ mana_handle_t *wq_obj) + { + struct mana_create_wqobj_resp resp = {}; + struct mana_create_wqobj_req req = {}; +@@ -845,9 +845,10 @@ static int mana_create_wq_obj(struct mana_port_context *apc, + out: + return err; + } ++EXPORT_SYMBOL_NS(mana_create_wq_obj, NET_MANA); + +-static void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, +- mana_handle_t wq_obj) ++void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, ++ mana_handle_t wq_obj) + { + struct mana_destroy_wqobj_resp resp = {}; + struct mana_destroy_wqobj_req req = {}; +@@ -872,6 +873,7 @@ static void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, + netdev_err(ndev, "Failed to destroy WQ object: %d, 0x%x\n", err, + resp.hdr.status); + } ++EXPORT_SYMBOL_NS(mana_destroy_wq_obj, NET_MANA); + + static void mana_destroy_eq(struct mana_context *ac) + { +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0008-net-mana-Record-port-number-in-netdev.patch b/debian/patches/features/all/ethernet-microsoft/0008-net-mana-Record-port-number-in-netdev.patch new file mode 100644 index 000000000..11a680a25 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0008-net-mana-Record-port-number-in-netdev.patch @@ -0,0 +1,34 @@ +From 026293abc2d3962ebd7d9a4bc9375fa1bddc2995 Mon Sep 17 00:00:00 2001 +From: Long Li <longli@microsoft.com> +Date: Thu, 3 Nov 2022 12:16:24 -0700 +Subject: [PATCH 08/23] net: mana: Record port number in netdev + +The port number is useful for user-mode application to identify this +net device based on port index. Set to the correct value in ndev. + +Reviewed-by: Dexuan Cui <decui@microsoft.com> +Signed-off-by: Long Li <longli@microsoft.com> +Link: https://lore.kernel.org/r/1667502990-2559-7-git-send-email-longli@linuxonhyperv.com +Acked-by: Haiyang Zhang <haiyangz@microsoft.com> +Signed-off-by: Leon Romanovsky <leonro@nvidia.com> +(cherry picked from commit d44089e555ffe63a49cc6e94d0c03d933e413059) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana_en.c | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index a526657f4edb..5b7aae9bf983 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -2139,6 +2139,7 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, + ndev->max_mtu = ndev->mtu; + ndev->min_mtu = ndev->mtu; + ndev->needed_headroom = MANA_HEADROOM; ++ ndev->dev_port = port_idx; + SET_NETDEV_DEV(ndev, gc->dev); + + netif_carrier_off(ndev); +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0009-net-mana-Move-header-files-to-a-common-location.patch b/debian/patches/features/all/ethernet-microsoft/0009-net-mana-Move-header-files-to-a-common-location.patch new file mode 100644 index 000000000..e83e38049 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0009-net-mana-Move-header-files-to-a-common-location.patch @@ -0,0 +1,152 @@ +From 36187c02914640d8c2e2ef9f11213842b5082671 Mon Sep 17 00:00:00 2001 +From: Long Li <longli@microsoft.com> +Date: Thu, 3 Nov 2022 12:16:25 -0700 +Subject: [PATCH 09/23] net: mana: Move header files to a common location + +In preparation to add MANA RDMA driver, move all the required header files +to a common location for use by both Ethernet and RDMA drivers. + +Reviewed-by: Dexuan Cui <decui@microsoft.com> +Signed-off-by: Long Li <longli@microsoft.com> +Link: https://lore.kernel.org/r/1667502990-2559-8-git-send-email-longli@linuxonhyperv.com +Acked-by: Haiyang Zhang <haiyangz@microsoft.com> +Signed-off-by: Leon Romanovsky <leonro@nvidia.com> +(cherry picked from commit fd325cd648f15eb9a8b32a68de3bafc72bcfe753) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + MAINTAINERS | 1 + + drivers/net/ethernet/microsoft/mana/gdma_main.c | 2 +- + drivers/net/ethernet/microsoft/mana/hw_channel.c | 4 ++-- + drivers/net/ethernet/microsoft/mana/mana_bpf.c | 2 +- + drivers/net/ethernet/microsoft/mana/mana_en.c | 4 ++-- + drivers/net/ethernet/microsoft/mana/mana_ethtool.c | 2 +- + drivers/net/ethernet/microsoft/mana/shm_channel.c | 2 +- + {drivers/net/ethernet/microsoft => include/net}/mana/gdma.h | 0 + .../net/ethernet/microsoft => include/net}/mana/hw_channel.h | 0 + {drivers/net/ethernet/microsoft => include/net}/mana/mana.h | 0 + .../ethernet/microsoft => include/net}/mana/mana_auxiliary.h | 0 + .../net/ethernet/microsoft => include/net}/mana/shm_channel.h | 0 + 12 files changed, 9 insertions(+), 8 deletions(-) + rename {drivers/net/ethernet/microsoft => include/net}/mana/gdma.h (100%) + rename {drivers/net/ethernet/microsoft => include/net}/mana/hw_channel.h (100%) + rename {drivers/net/ethernet/microsoft => include/net}/mana/mana.h (100%) + rename {drivers/net/ethernet/microsoft => include/net}/mana/mana_auxiliary.h (100%) + rename {drivers/net/ethernet/microsoft => include/net}/mana/shm_channel.h (100%) + +diff --git a/MAINTAINERS b/MAINTAINERS +index 379387e20a96..a923933bbe82 100644 +--- a/MAINTAINERS ++++ b/MAINTAINERS +@@ -9536,6 +9536,7 @@ F: include/asm-generic/hyperv-tlfs.h + F: include/asm-generic/mshyperv.h + F: include/clocksource/hyperv_timer.h + F: include/linux/hyperv.h ++F: include/net/mana + F: include/uapi/linux/hyperv.h + F: net/vmw_vsock/hyperv_transport.c + F: tools/hv/ +diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c +index d9be0f3044ea..b114c31d70ba 100644 +--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c ++++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c +@@ -6,7 +6,7 @@ + #include <linux/utsname.h> + #include <linux/version.h> + +-#include "mana.h" ++#include <net/mana/mana.h> + + static u32 mana_gd_r32(struct gdma_context *g, u64 offset) + { +diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c +index 543a5d5c304f..76829ab43d40 100644 +--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c ++++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c +@@ -1,8 +1,8 @@ + // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + /* Copyright (c) 2021, Microsoft Corporation. */ + +-#include "gdma.h" +-#include "hw_channel.h" ++#include <net/mana/gdma.h> ++#include <net/mana/hw_channel.h> + + static int mana_hwc_get_msg_index(struct hw_channel_context *hwc, u16 *msg_id) + { +diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c +index 421fd39ff3a8..3caea631229c 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c +@@ -8,7 +8,7 @@ + #include <linux/bpf_trace.h> + #include <net/xdp.h> + +-#include "mana.h" ++#include <net/mana/mana.h> + + void mana_xdp_tx(struct sk_buff *skb, struct net_device *ndev) + { +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index 5b7aae9bf983..c0421c4a80d4 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -12,8 +12,8 @@ + #include <net/checksum.h> + #include <net/ip6_checksum.h> + +-#include "mana.h" +-#include "mana_auxiliary.h" ++#include <net/mana/mana.h> ++#include <net/mana/mana_auxiliary.h> + + static DEFINE_IDA(mana_adev_ida); + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +index 96d55c91c969..5b776a33a817 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +@@ -5,7 +5,7 @@ + #include <linux/etherdevice.h> + #include <linux/ethtool.h> + +-#include "mana.h" ++#include <net/mana/mana.h> + + static const struct { + char name[ETH_GSTRING_LEN]; +diff --git a/drivers/net/ethernet/microsoft/mana/shm_channel.c b/drivers/net/ethernet/microsoft/mana/shm_channel.c +index da255da62176..5553af9c8085 100644 +--- a/drivers/net/ethernet/microsoft/mana/shm_channel.c ++++ b/drivers/net/ethernet/microsoft/mana/shm_channel.c +@@ -6,7 +6,7 @@ + #include <linux/io.h> + #include <linux/mm.h> + +-#include "shm_channel.h" ++#include <net/mana/shm_channel.h> + + #define PAGE_FRAME_L48_WIDTH_BYTES 6 + #define PAGE_FRAME_L48_WIDTH_BITS (PAGE_FRAME_L48_WIDTH_BYTES * 8) +diff --git a/drivers/net/ethernet/microsoft/mana/gdma.h b/include/net/mana/gdma.h +similarity index 100% +rename from drivers/net/ethernet/microsoft/mana/gdma.h +rename to include/net/mana/gdma.h +diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.h b/include/net/mana/hw_channel.h +similarity index 100% +rename from drivers/net/ethernet/microsoft/mana/hw_channel.h +rename to include/net/mana/hw_channel.h +diff --git a/drivers/net/ethernet/microsoft/mana/mana.h b/include/net/mana/mana.h +similarity index 100% +rename from drivers/net/ethernet/microsoft/mana/mana.h +rename to include/net/mana/mana.h +diff --git a/drivers/net/ethernet/microsoft/mana/mana_auxiliary.h b/include/net/mana/mana_auxiliary.h +similarity index 100% +rename from drivers/net/ethernet/microsoft/mana/mana_auxiliary.h +rename to include/net/mana/mana_auxiliary.h +diff --git a/drivers/net/ethernet/microsoft/mana/shm_channel.h b/include/net/mana/shm_channel.h +similarity index 100% +rename from drivers/net/ethernet/microsoft/mana/shm_channel.h +rename to include/net/mana/shm_channel.h +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0010-net-mana-Define-max-values-for-SGL-entries.patch b/debian/patches/features/all/ethernet-microsoft/0010-net-mana-Define-max-values-for-SGL-entries.patch new file mode 100644 index 000000000..25af5ac09 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0010-net-mana-Define-max-values-for-SGL-entries.patch @@ -0,0 +1,79 @@ +From 5e6b27eabf53e70c084cf61e3d3860cd6ed1c321 Mon Sep 17 00:00:00 2001 +From: Long Li <longli@microsoft.com> +Date: Thu, 3 Nov 2022 12:16:26 -0700 +Subject: [PATCH 10/23] net: mana: Define max values for SGL entries + +The number of maximum SGl entries should be computed from the maximum +WQE size for the intended queue type and the corresponding OOB data +size. This guarantees the hardware queue can successfully queue requests +up to the queue depth exposed to the upper layer. + +Reviewed-by: Dexuan Cui <decui@microsoft.com> +Signed-off-by: Long Li <longli@microsoft.com> +Link: https://lore.kernel.org/r/1667502990-2559-9-git-send-email-longli@linuxonhyperv.com +Acked-by: Haiyang Zhang <haiyangz@microsoft.com> +Signed-off-by: Leon Romanovsky <leonro@nvidia.com> +(cherry picked from commit aa56549792fb348892fbbae67f6f0c71bb750b65) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana_en.c | 2 +- + include/net/mana/gdma.h | 7 +++++++ + include/net/mana/mana.h | 4 +--- + 3 files changed, 9 insertions(+), 4 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index c0421c4a80d4..958e55c936b5 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -189,7 +189,7 @@ int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) + pkg.wqe_req.client_data_unit = 0; + + pkg.wqe_req.num_sge = 1 + skb_shinfo(skb)->nr_frags; +- WARN_ON_ONCE(pkg.wqe_req.num_sge > 30); ++ WARN_ON_ONCE(pkg.wqe_req.num_sge > MAX_TX_WQE_SGL_ENTRIES); + + if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) { + pkg.wqe_req.sgl = pkg.sgl_array; +diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h +index 86d8a9e36005..11fc1cc67c01 100644 +--- a/include/net/mana/gdma.h ++++ b/include/net/mana/gdma.h +@@ -431,6 +431,13 @@ struct gdma_wqe { + #define MAX_TX_WQE_SIZE 512 + #define MAX_RX_WQE_SIZE 256 + ++#define MAX_TX_WQE_SGL_ENTRIES ((GDMA_MAX_SQE_SIZE - \ ++ sizeof(struct gdma_sge) - INLINE_OOB_SMALL_SIZE) / \ ++ sizeof(struct gdma_sge)) ++ ++#define MAX_RX_WQE_SGL_ENTRIES ((GDMA_MAX_RQE_SIZE - \ ++ sizeof(struct gdma_sge)) / sizeof(struct gdma_sge)) ++ + struct gdma_cqe { + u32 cqe_data[GDMA_COMP_DATA_SIZE / 4]; + +diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h +index 6e9e86fb4c02..713a8f8cca9a 100644 +--- a/include/net/mana/mana.h ++++ b/include/net/mana/mana.h +@@ -265,8 +265,6 @@ struct mana_cq { + int budget; + }; + +-#define GDMA_MAX_RQE_SGES 15 +- + struct mana_recv_buf_oob { + /* A valid GDMA work request representing the data buffer. */ + struct gdma_wqe_request wqe_req; +@@ -276,7 +274,7 @@ struct mana_recv_buf_oob { + + /* SGL of the buffer going to be sent has part of the work request. */ + u32 num_sge; +- struct gdma_sge sgl[GDMA_MAX_RQE_SGES]; ++ struct gdma_sge sgl[MAX_RX_WQE_SGL_ENTRIES]; + + /* Required to store the result of mana_gd_post_work_request. + * gdma_posted_wqe_info.wqe_size_in_bu is required for progressing the +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0011-net-mana-Define-and-process-GDMA-response-code-GDMA_.patch b/debian/patches/features/all/ethernet-microsoft/0011-net-mana-Define-and-process-GDMA-response-code-GDMA_.patch new file mode 100644 index 000000000..539f450c0 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0011-net-mana-Define-and-process-GDMA-response-code-GDMA_.patch @@ -0,0 +1,52 @@ +From 71b611192d6e5c0aa276eba89c4ac0b15ca1851b Mon Sep 17 00:00:00 2001 +From: Ajay Sharma <sharmaajay@microsoft.com> +Date: Thu, 3 Nov 2022 12:16:27 -0700 +Subject: [PATCH 11/23] net: mana: Define and process GDMA response code + GDMA_STATUS_MORE_ENTRIES + +When doing memory registration, the PF may respond with +GDMA_STATUS_MORE_ENTRIES to indicate a follow request is needed. This is +not an error and should be processed as expected. + +Signed-off-by: Ajay Sharma <sharmaajay@microsoft.com> +Reviewed-by: Dexuan Cui <decui@microsoft.com> +Signed-off-by: Long Li <longli@microsoft.com> +Link: https://lore.kernel.org/r/1667502990-2559-10-git-send-email-longli@linuxonhyperv.com +Acked-by: Haiyang Zhang <haiyangz@microsoft.com> +Signed-off-by: Leon Romanovsky <leonro@nvidia.com> +(cherry picked from commit de372f2a9ca7ada2698ecac7df8f02407cd98fa0) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/hw_channel.c | 2 +- + include/net/mana/gdma.h | 2 ++ + 2 files changed, 3 insertions(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c +index 76829ab43d40..9d1507eba5b9 100644 +--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c ++++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c +@@ -836,7 +836,7 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, + goto out; + } + +- if (ctx->status_code) { ++ if (ctx->status_code && ctx->status_code != GDMA_STATUS_MORE_ENTRIES) { + dev_err(hwc->dev, "HWC: Failed hw_channel req: 0x%x\n", + ctx->status_code); + err = -EPROTO; +diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h +index 11fc1cc67c01..202ac405ab59 100644 +--- a/include/net/mana/gdma.h ++++ b/include/net/mana/gdma.h +@@ -9,6 +9,8 @@ + + #include "shm_channel.h" + ++#define GDMA_STATUS_MORE_ENTRIES 0x00000105 ++ + /* Structures labeled with "HW DATA" are exchanged with the hardware. All of + * them are naturally aligned and hence don't need __packed. + */ +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0012-net-mana-Define-data-structures-for-protection-domai.patch b/debian/patches/features/all/ethernet-microsoft/0012-net-mana-Define-data-structures-for-protection-domai.patch new file mode 100644 index 000000000..fb9a2a84d --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0012-net-mana-Define-data-structures-for-protection-domai.patch @@ -0,0 +1,353 @@ +From b6589e00fed6f5a53bd4ffd172b7e4d2d300447c Mon Sep 17 00:00:00 2001 +From: Ajay Sharma <sharmaajay@microsoft.com> +Date: Thu, 3 Nov 2022 12:16:29 -0700 +Subject: [PATCH 12/23] net: mana: Define data structures for protection domain + and memory registration + +The MANA hardware support protection domain and memory registration for use +in RDMA environment. Add those definitions and expose them for use by the +RDMA driver. + +Signed-off-by: Ajay Sharma <sharmaajay@microsoft.com> +Signed-off-by: Long Li <longli@microsoft.com> +Link: https://lore.kernel.org/r/1667502990-2559-12-git-send-email-longli@linuxonhyperv.com +Reviewed-by: Dexuan Cui <decui@microsoft.com> +Acked-by: Haiyang Zhang <haiyangz@microsoft.com> +Signed-off-by: Leon Romanovsky <leonro@nvidia.com> +(cherry picked from commit 28c66cfa45388af1126985d1114e0ed762eb2abd) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + .../net/ethernet/microsoft/mana/gdma_main.c | 27 ++-- + drivers/net/ethernet/microsoft/mana/mana_en.c | 18 +-- + include/net/mana/gdma.h | 121 +++++++++++++++++- + 3 files changed, 143 insertions(+), 23 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c +index b114c31d70ba..690691e3e86c 100644 +--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c ++++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c +@@ -198,7 +198,7 @@ static int mana_gd_create_hw_eq(struct gdma_context *gc, + req.type = queue->type; + req.pdid = queue->gdma_dev->pdid; + req.doolbell_id = queue->gdma_dev->doorbell; +- req.gdma_region = queue->mem_info.gdma_region; ++ req.gdma_region = queue->mem_info.dma_region_handle; + req.queue_size = queue->queue_size; + req.log2_throttle_limit = queue->eq.log2_throttle_limit; + req.eq_pci_msix_index = queue->eq.msix_index; +@@ -212,7 +212,7 @@ static int mana_gd_create_hw_eq(struct gdma_context *gc, + + queue->id = resp.queue_index; + queue->eq.disable_needed = true; +- queue->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; ++ queue->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION; + return 0; + } + +@@ -671,24 +671,30 @@ int mana_gd_create_hwc_queue(struct gdma_dev *gd, + return err; + } + +-static void mana_gd_destroy_dma_region(struct gdma_context *gc, u64 gdma_region) ++int mana_gd_destroy_dma_region(struct gdma_context *gc, ++ gdma_obj_handle_t dma_region_handle) + { + struct gdma_destroy_dma_region_req req = {}; + struct gdma_general_resp resp = {}; + int err; + +- if (gdma_region == GDMA_INVALID_DMA_REGION) +- return; ++ if (dma_region_handle == GDMA_INVALID_DMA_REGION) ++ return 0; + + mana_gd_init_req_hdr(&req.hdr, GDMA_DESTROY_DMA_REGION, sizeof(req), + sizeof(resp)); +- req.gdma_region = gdma_region; ++ req.dma_region_handle = dma_region_handle; + + err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp); +- if (err || resp.hdr.status) ++ if (err || resp.hdr.status) { + dev_err(gc->dev, "Failed to destroy DMA region: %d, 0x%x\n", + err, resp.hdr.status); ++ return -EPROTO; ++ } ++ ++ return 0; + } ++EXPORT_SYMBOL_NS(mana_gd_destroy_dma_region, NET_MANA); + + static int mana_gd_create_dma_region(struct gdma_dev *gd, + struct gdma_mem_info *gmi) +@@ -733,14 +739,15 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd, + if (err) + goto out; + +- if (resp.hdr.status || resp.gdma_region == GDMA_INVALID_DMA_REGION) { ++ if (resp.hdr.status || ++ resp.dma_region_handle == GDMA_INVALID_DMA_REGION) { + dev_err(gc->dev, "Failed to create DMA region: 0x%x\n", + resp.hdr.status); + err = -EPROTO; + goto out; + } + +- gmi->gdma_region = resp.gdma_region; ++ gmi->dma_region_handle = resp.dma_region_handle; + out: + kfree(req); + return err; +@@ -863,7 +870,7 @@ void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue) + return; + } + +- mana_gd_destroy_dma_region(gc, gmi->gdma_region); ++ mana_gd_destroy_dma_region(gc, gmi->dma_region_handle); + mana_gd_free_memory(gmi); + kfree(queue); + } +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index 958e55c936b5..9bce13714b25 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -1529,10 +1529,10 @@ static int mana_create_txq(struct mana_port_context *apc, + memset(&wq_spec, 0, sizeof(wq_spec)); + memset(&cq_spec, 0, sizeof(cq_spec)); + +- wq_spec.gdma_region = txq->gdma_sq->mem_info.gdma_region; ++ wq_spec.gdma_region = txq->gdma_sq->mem_info.dma_region_handle; + wq_spec.queue_size = txq->gdma_sq->queue_size; + +- cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region; ++ cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle; + cq_spec.queue_size = cq->gdma_cq->queue_size; + cq_spec.modr_ctx_id = 0; + cq_spec.attached_eq = cq->gdma_cq->cq.parent->id; +@@ -1547,8 +1547,10 @@ static int mana_create_txq(struct mana_port_context *apc, + txq->gdma_sq->id = wq_spec.queue_index; + cq->gdma_cq->id = cq_spec.queue_index; + +- txq->gdma_sq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; +- cq->gdma_cq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; ++ txq->gdma_sq->mem_info.dma_region_handle = ++ GDMA_INVALID_DMA_REGION; ++ cq->gdma_cq->mem_info.dma_region_handle = ++ GDMA_INVALID_DMA_REGION; + + txq->gdma_txq_id = txq->gdma_sq->id; + +@@ -1759,10 +1761,10 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, + + memset(&wq_spec, 0, sizeof(wq_spec)); + memset(&cq_spec, 0, sizeof(cq_spec)); +- wq_spec.gdma_region = rxq->gdma_rq->mem_info.gdma_region; ++ wq_spec.gdma_region = rxq->gdma_rq->mem_info.dma_region_handle; + wq_spec.queue_size = rxq->gdma_rq->queue_size; + +- cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region; ++ cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle; + cq_spec.queue_size = cq->gdma_cq->queue_size; + cq_spec.modr_ctx_id = 0; + cq_spec.attached_eq = cq->gdma_cq->cq.parent->id; +@@ -1775,8 +1777,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, + rxq->gdma_rq->id = wq_spec.queue_index; + cq->gdma_cq->id = cq_spec.queue_index; + +- rxq->gdma_rq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; +- cq->gdma_cq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; ++ rxq->gdma_rq->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION; ++ cq->gdma_cq->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION; + + rxq->gdma_id = rxq->gdma_rq->id; + cq->gdma_id = cq->gdma_cq->id; +diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h +index 202ac405ab59..aabc7cea8a49 100644 +--- a/include/net/mana/gdma.h ++++ b/include/net/mana/gdma.h +@@ -27,6 +27,10 @@ enum gdma_request_type { + GDMA_CREATE_DMA_REGION = 25, + GDMA_DMA_REGION_ADD_PAGES = 26, + GDMA_DESTROY_DMA_REGION = 27, ++ GDMA_CREATE_PD = 29, ++ GDMA_DESTROY_PD = 30, ++ GDMA_CREATE_MR = 31, ++ GDMA_DESTROY_MR = 32, + }; + + enum gdma_queue_type { +@@ -57,6 +61,8 @@ enum { + GDMA_DEVICE_MANA = 2, + }; + ++typedef u64 gdma_obj_handle_t; ++ + struct gdma_resource { + /* Protect the bitmap */ + spinlock_t lock; +@@ -190,7 +196,7 @@ struct gdma_mem_info { + u64 length; + + /* Allocated by the PF driver */ +- u64 gdma_region; ++ gdma_obj_handle_t dma_region_handle; + }; + + #define REGISTER_ATB_MST_MKEY_LOWER_SIZE 8 +@@ -605,7 +611,7 @@ struct gdma_create_queue_req { + u32 reserved1; + u32 pdid; + u32 doolbell_id; +- u64 gdma_region; ++ gdma_obj_handle_t gdma_region; + u32 reserved2; + u32 queue_size; + u32 log2_throttle_limit; +@@ -632,6 +638,28 @@ struct gdma_disable_queue_req { + u32 alloc_res_id_on_creation; + }; /* HW DATA */ + ++enum atb_page_size { ++ ATB_PAGE_SIZE_4K, ++ ATB_PAGE_SIZE_8K, ++ ATB_PAGE_SIZE_16K, ++ ATB_PAGE_SIZE_32K, ++ ATB_PAGE_SIZE_64K, ++ ATB_PAGE_SIZE_128K, ++ ATB_PAGE_SIZE_256K, ++ ATB_PAGE_SIZE_512K, ++ ATB_PAGE_SIZE_1M, ++ ATB_PAGE_SIZE_2M, ++ ATB_PAGE_SIZE_MAX, ++}; ++ ++enum gdma_mr_access_flags { ++ GDMA_ACCESS_FLAG_LOCAL_READ = BIT_ULL(0), ++ GDMA_ACCESS_FLAG_LOCAL_WRITE = BIT_ULL(1), ++ GDMA_ACCESS_FLAG_REMOTE_READ = BIT_ULL(2), ++ GDMA_ACCESS_FLAG_REMOTE_WRITE = BIT_ULL(3), ++ GDMA_ACCESS_FLAG_REMOTE_ATOMIC = BIT_ULL(4), ++}; ++ + /* GDMA_CREATE_DMA_REGION */ + struct gdma_create_dma_region_req { + struct gdma_req_hdr hdr; +@@ -658,14 +686,14 @@ struct gdma_create_dma_region_req { + + struct gdma_create_dma_region_resp { + struct gdma_resp_hdr hdr; +- u64 gdma_region; ++ gdma_obj_handle_t dma_region_handle; + }; /* HW DATA */ + + /* GDMA_DMA_REGION_ADD_PAGES */ + struct gdma_dma_region_add_pages_req { + struct gdma_req_hdr hdr; + +- u64 gdma_region; ++ gdma_obj_handle_t dma_region_handle; + + u32 page_addr_list_len; + u32 reserved3; +@@ -677,9 +705,88 @@ struct gdma_dma_region_add_pages_req { + struct gdma_destroy_dma_region_req { + struct gdma_req_hdr hdr; + +- u64 gdma_region; ++ gdma_obj_handle_t dma_region_handle; + }; /* HW DATA */ + ++enum gdma_pd_flags { ++ GDMA_PD_FLAG_INVALID = 0, ++}; ++ ++struct gdma_create_pd_req { ++ struct gdma_req_hdr hdr; ++ enum gdma_pd_flags flags; ++ u32 reserved; ++};/* HW DATA */ ++ ++struct gdma_create_pd_resp { ++ struct gdma_resp_hdr hdr; ++ gdma_obj_handle_t pd_handle; ++ u32 pd_id; ++ u32 reserved; ++};/* HW DATA */ ++ ++struct gdma_destroy_pd_req { ++ struct gdma_req_hdr hdr; ++ gdma_obj_handle_t pd_handle; ++};/* HW DATA */ ++ ++struct gdma_destory_pd_resp { ++ struct gdma_resp_hdr hdr; ++};/* HW DATA */ ++ ++enum gdma_mr_type { ++ /* Guest Virtual Address - MRs of this type allow access ++ * to memory mapped by PTEs associated with this MR using a virtual ++ * address that is set up in the MST ++ */ ++ GDMA_MR_TYPE_GVA = 2, ++}; ++ ++struct gdma_create_mr_params { ++ gdma_obj_handle_t pd_handle; ++ enum gdma_mr_type mr_type; ++ union { ++ struct { ++ gdma_obj_handle_t dma_region_handle; ++ u64 virtual_address; ++ enum gdma_mr_access_flags access_flags; ++ } gva; ++ }; ++}; ++ ++struct gdma_create_mr_request { ++ struct gdma_req_hdr hdr; ++ gdma_obj_handle_t pd_handle; ++ enum gdma_mr_type mr_type; ++ u32 reserved_1; ++ ++ union { ++ struct { ++ gdma_obj_handle_t dma_region_handle; ++ u64 virtual_address; ++ enum gdma_mr_access_flags access_flags; ++ } gva; ++ ++ }; ++ u32 reserved_2; ++};/* HW DATA */ ++ ++struct gdma_create_mr_response { ++ struct gdma_resp_hdr hdr; ++ gdma_obj_handle_t mr_handle; ++ u32 lkey; ++ u32 rkey; ++};/* HW DATA */ ++ ++struct gdma_destroy_mr_request { ++ struct gdma_req_hdr hdr; ++ gdma_obj_handle_t mr_handle; ++};/* HW DATA */ ++ ++struct gdma_destroy_mr_response { ++ struct gdma_resp_hdr hdr; ++};/* HW DATA */ ++ + int mana_gd_verify_vf_version(struct pci_dev *pdev); + + int mana_gd_register_device(struct gdma_dev *gd); +@@ -706,4 +813,8 @@ void mana_gd_free_memory(struct gdma_mem_info *gmi); + + int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req, + u32 resp_len, void *resp); ++ ++int mana_gd_destroy_dma_region(struct gdma_context *gc, ++ gdma_obj_handle_t dma_region_handle); ++ + #endif /* _GDMA_H */ +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0013-net-mana-Fix-return-type-of-mana_start_xmit.patch b/debian/patches/features/all/ethernet-microsoft/0013-net-mana-Fix-return-type-of-mana_start_xmit.patch new file mode 100644 index 000000000..8f966405a --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0013-net-mana-Fix-return-type-of-mana_start_xmit.patch @@ -0,0 +1,66 @@ +From 37ec026c96afe1091f91d40515a91463ea50c150 Mon Sep 17 00:00:00 2001 +From: Nathan Huckleberry <nhuck@google.com> +Date: Tue, 8 Nov 2022 17:26:30 -0700 +Subject: [PATCH 13/23] net: mana: Fix return type of mana_start_xmit() + +The ndo_start_xmit field in net_device_ops is expected to be of type +netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb, struct net_device *dev). + +The mismatched return type breaks forward edge kCFI since the underlying +function definition does not match the function hook definition. A new +warning in clang will catch this at compile time: + + drivers/net/ethernet/microsoft/mana/mana_en.c:382:21: error: incompatible function pointer types initializing 'netdev_tx_t (*)(struct sk_buff *, struct net_device *)' (aka 'enum netdev_tx (*)(struct sk_buff *, struct net_device *)') with an expression of type 'int (struct sk_buff *, struct net_device *)' [-Werror,-Wincompatible-function-pointer-types-strict] + .ndo_start_xmit = mana_start_xmit, + ^~~~~~~~~~~~~~~ + 1 error generated. + +The return type of mana_start_xmit should be changed from int to +netdev_tx_t. + +Reported-by: Dan Carpenter <error27@gmail.com> +Link: https://github.com/ClangBuiltLinux/linux/issues/1703 +Link: https://github.com/ClangBuiltLinux/linux/issues/1750 +Signed-off-by: Nathan Huckleberry <nhuck@google.com> +Reviewed-by: Dexuan Cui <decui@microsoft.com> +[nathan: Rebase on net-next and resolve conflicts + Add note about new clang warning] +Signed-off-by: Nathan Chancellor <nathan@kernel.org> +Link: https://lore.kernel.org/r/20221109002629.1446680-1-nathan@kernel.org +Signed-off-by: Paolo Abeni <pabeni@redhat.com> +(cherry picked from commit 0c9ef08a4d0fd6c5e6000597b506235d71a85a61) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana_en.c | 2 +- + include/net/mana/mana.h | 2 +- + 2 files changed, 2 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index 9bce13714b25..2f6a048dee90 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -141,7 +141,7 @@ static int mana_map_skb(struct sk_buff *skb, struct mana_port_context *apc, + return -ENOMEM; + } + +-int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) ++netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) + { + enum mana_tx_pkt_format pkt_fmt = MANA_SHORT_PKT_FMT; + struct mana_port_context *apc = netdev_priv(ndev); +diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h +index 713a8f8cca9a..575ea36ce606 100644 +--- a/include/net/mana/mana.h ++++ b/include/net/mana/mana.h +@@ -390,7 +390,7 @@ struct mana_port_context { + struct mana_ethtool_stats eth_stats; + }; + +-int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev); ++netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev); + int mana_config_rss(struct mana_port_context *ac, enum TRI_STATE rx, + bool update_hash, bool update_tab); + +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0014-net-mana-Fix-accessing-freed-irq-affinity_hint.patch b/debian/patches/features/all/ethernet-microsoft/0014-net-mana-Fix-accessing-freed-irq-affinity_hint.patch new file mode 100644 index 000000000..2aa627612 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0014-net-mana-Fix-accessing-freed-irq-affinity_hint.patch @@ -0,0 +1,135 @@ +From 1b71f96ff9b962c904cefc9a57500869fa0d1d44 Mon Sep 17 00:00:00 2001 +From: Haiyang Zhang <haiyangz@microsoft.com> +Date: Mon, 6 Feb 2023 13:28:49 -0800 +Subject: [PATCH 14/23] net: mana: Fix accessing freed irq affinity_hint + +After calling irq_set_affinity_and_hint(), the cpumask pointer is +saved in desc->affinity_hint, and will be used later when reading +/proc/irq/<num>/affinity_hint. So the cpumask variable needs to be +persistent. Otherwise, we are accessing freed memory when reading +the affinity_hint file. + +Also, need to clear affinity_hint before free_irq(), otherwise there +is a one-time warning and stack trace during module unloading: + + [ 243.948687] WARNING: CPU: 10 PID: 1589 at kernel/irq/manage.c:1913 free_irq+0x318/0x360 + ... + [ 243.948753] Call Trace: + [ 243.948754] <TASK> + [ 243.948760] mana_gd_remove_irqs+0x78/0xc0 [mana] + [ 243.948767] mana_gd_remove+0x3e/0x80 [mana] + [ 243.948773] pci_device_remove+0x3d/0xb0 + [ 243.948778] device_remove+0x46/0x70 + [ 243.948782] device_release_driver_internal+0x1fe/0x280 + [ 243.948785] driver_detach+0x4e/0xa0 + [ 243.948787] bus_remove_driver+0x70/0xf0 + [ 243.948789] driver_unregister+0x35/0x60 + [ 243.948792] pci_unregister_driver+0x44/0x90 + [ 243.948794] mana_driver_exit+0x14/0x3fe [mana] + [ 243.948800] __do_sys_delete_module.constprop.0+0x185/0x2f0 + +To fix the bug, use the persistent mask, cpumask_of(cpu#), and set +affinity_hint to NULL before freeing the IRQ, as required by free_irq(). + +Cc: stable@vger.kernel.org +Fixes: 71fa6887eeca ("net: mana: Assign interrupts to CPUs based on NUMA nodes") +Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> +Reviewed-by: Michael Kelley <mikelley@microsoft.com> +Reviewed-by: Leon Romanovsky <leonro@nvidia.com> +Link: https://lore.kernel.org/r/1675718929-19565-1-git-send-email-haiyangz@microsoft.com +Signed-off-by: Jakub Kicinski <kuba@kernel.org> +(cherry picked from commit 18a048370b06a3a521219e9e5b10bdc2178ef19c) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + .../net/ethernet/microsoft/mana/gdma_main.c | 37 ++++++------------- + 1 file changed, 11 insertions(+), 26 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c +index 690691e3e86c..5b7fddfc9ff1 100644 +--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c ++++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c +@@ -1218,9 +1218,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) + unsigned int max_queues_per_port = num_online_cpus(); + struct gdma_context *gc = pci_get_drvdata(pdev); + struct gdma_irq_context *gic; +- unsigned int max_irqs; +- u16 *cpus; +- cpumask_var_t req_mask; ++ unsigned int max_irqs, cpu; + int nvec, irq; + int err, i = 0, j; + +@@ -1241,21 +1239,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) + goto free_irq_vector; + } + +- if (!zalloc_cpumask_var(&req_mask, GFP_KERNEL)) { +- err = -ENOMEM; +- goto free_irq; +- } +- +- cpus = kcalloc(nvec, sizeof(*cpus), GFP_KERNEL); +- if (!cpus) { +- err = -ENOMEM; +- goto free_mask; +- } +- for (i = 0; i < nvec; i++) +- cpus[i] = cpumask_local_spread(i, gc->numa_node); +- + for (i = 0; i < nvec; i++) { +- cpumask_set_cpu(cpus[i], req_mask); + gic = &gc->irq_contexts[i]; + gic->handler = NULL; + gic->arg = NULL; +@@ -1270,17 +1254,16 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) + irq = pci_irq_vector(pdev, i); + if (irq < 0) { + err = irq; +- goto free_mask; ++ goto free_irq; + } + + err = request_irq(irq, mana_gd_intr, 0, gic->name, gic); + if (err) +- goto free_mask; +- irq_set_affinity_and_hint(irq, req_mask); +- cpumask_clear(req_mask); ++ goto free_irq; ++ ++ cpu = cpumask_local_spread(i, gc->numa_node); ++ irq_set_affinity_and_hint(irq, cpumask_of(cpu)); + } +- free_cpumask_var(req_mask); +- kfree(cpus); + + err = mana_gd_alloc_res_map(nvec, &gc->msix_resource); + if (err) +@@ -1291,13 +1274,12 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) + + return 0; + +-free_mask: +- free_cpumask_var(req_mask); +- kfree(cpus); + free_irq: + for (j = i - 1; j >= 0; j--) { + irq = pci_irq_vector(pdev, j); + gic = &gc->irq_contexts[j]; ++ ++ irq_update_affinity_hint(irq, NULL); + free_irq(irq, gic); + } + +@@ -1325,6 +1307,9 @@ static void mana_gd_remove_irqs(struct pci_dev *pdev) + continue; + + gic = &gc->irq_contexts[i]; ++ ++ /* Need to clear the hint before free_irq */ ++ irq_update_affinity_hint(irq, NULL); + free_irq(irq, gic); + } + +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0015-net-mana-Add-new-MANA-VF-performance-counters-for-ea.patch b/debian/patches/features/all/ethernet-microsoft/0015-net-mana-Add-new-MANA-VF-performance-counters-for-ea.patch new file mode 100644 index 000000000..0ada4dca6 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0015-net-mana-Add-new-MANA-VF-performance-counters-for-ea.patch @@ -0,0 +1,334 @@ +From fbefc731a4cc001fe7ce5786e08053d707dde85f Mon Sep 17 00:00:00 2001 +From: Shradha Gupta <shradhagupta@linux.microsoft.com> +Date: Wed, 15 Mar 2023 04:55:13 -0700 +Subject: [PATCH 15/23] net: mana: Add new MANA VF performance counters for + easier troubleshooting + +Extended performance counter stats in 'ethtool -S <interface>' output +for MANA VF to facilitate troubleshooting. + +Tested-on: Ubuntu22 +Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com> +Signed-off-by: David S. Miller <davem@davemloft.net> +(cherry picked from commit bd7fc6e1957c2102866f9e464c1f2302e891b7e9) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana_en.c | 62 ++++++++++++++++++- + .../ethernet/microsoft/mana/mana_ethtool.c | 52 +++++++++++++++- + include/net/mana/mana.h | 18 ++++++ + 3 files changed, 128 insertions(+), 4 deletions(-) + +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -157,6 +157,7 @@ netdev_tx_t mana_start_xmit(struct sk_bu + struct mana_txq *txq; + struct mana_cq *cq; + int err, len; ++ u16 ihs; + + if (unlikely(!apc->port_is_up)) + goto tx_drop; +@@ -167,6 +168,7 @@ netdev_tx_t mana_start_xmit(struct sk_bu + txq = &apc->tx_qp[txq_idx].txq; + gdma_sq = txq->gdma_sq; + cq = &apc->tx_qp[txq_idx].tx_cq; ++ tx_stats = &txq->stats; + + pkg.tx_oob.s_oob.vcq_num = cq->gdma_id; + pkg.tx_oob.s_oob.vsq_frame = txq->vsq_frame; +@@ -180,10 +182,17 @@ netdev_tx_t mana_start_xmit(struct sk_bu + + pkg.tx_oob.s_oob.pkt_fmt = pkt_fmt; + +- if (pkt_fmt == MANA_SHORT_PKT_FMT) ++ if (pkt_fmt == MANA_SHORT_PKT_FMT) { + pkg.wqe_req.inline_oob_size = sizeof(struct mana_tx_short_oob); +- else ++ u64_stats_update_begin(&tx_stats->syncp); ++ tx_stats->short_pkt_fmt++; ++ u64_stats_update_end(&tx_stats->syncp); ++ } else { + pkg.wqe_req.inline_oob_size = sizeof(struct mana_tx_oob); ++ u64_stats_update_begin(&tx_stats->syncp); ++ tx_stats->long_pkt_fmt++; ++ u64_stats_update_end(&tx_stats->syncp); ++ } + + pkg.wqe_req.inline_oob_data = &pkg.tx_oob; + pkg.wqe_req.flags = 0; +@@ -233,9 +242,35 @@ netdev_tx_t mana_start_xmit(struct sk_bu + &ipv6_hdr(skb)->daddr, 0, + IPPROTO_TCP, 0); + } ++ ++ if (skb->encapsulation) { ++ ihs = skb_inner_tcp_all_headers(skb); ++ u64_stats_update_begin(&tx_stats->syncp); ++ tx_stats->tso_inner_packets++; ++ tx_stats->tso_inner_bytes += skb->len - ihs; ++ u64_stats_update_end(&tx_stats->syncp); ++ } else { ++ if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { ++ ihs = skb_transport_offset(skb) + sizeof(struct udphdr); ++ } else { ++ ihs = skb_tcp_all_headers(skb); ++ if (ipv6_has_hopopt_jumbo(skb)) ++ ihs -= sizeof(struct hop_jumbo_hdr); ++ } ++ ++ u64_stats_update_begin(&tx_stats->syncp); ++ tx_stats->tso_packets++; ++ tx_stats->tso_bytes += skb->len - ihs; ++ u64_stats_update_end(&tx_stats->syncp); ++ } ++ + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + csum_type = mana_checksum_info(skb); + ++ u64_stats_update_begin(&tx_stats->syncp); ++ tx_stats->csum_partial++; ++ u64_stats_update_end(&tx_stats->syncp); ++ + if (csum_type == IPPROTO_TCP) { + pkg.tx_oob.s_oob.is_outer_ipv4 = ipv4; + pkg.tx_oob.s_oob.is_outer_ipv6 = ipv6; +@@ -255,8 +290,12 @@ netdev_tx_t mana_start_xmit(struct sk_bu + } + } + +- if (mana_map_skb(skb, apc, &pkg)) ++ if (mana_map_skb(skb, apc, &pkg)) { ++ u64_stats_update_begin(&tx_stats->syncp); ++ tx_stats->mana_map_err++; ++ u64_stats_update_end(&tx_stats->syncp); + goto free_sgl_ptr; ++ } + + skb_queue_tail(&txq->pending_skbs, skb); + +@@ -1039,6 +1078,8 @@ static void mana_poll_tx_cq(struct mana_ + if (comp_read < 1) + return; + ++ apc->eth_stats.tx_cqes = comp_read; ++ + for (i = 0; i < comp_read; i++) { + struct mana_tx_comp_oob *cqe_oob; + +@@ -1067,6 +1108,7 @@ static void mana_poll_tx_cq(struct mana_ + netdev_err(ndev, "TX: CQE error %d\n", + cqe_oob->cqe_hdr.cqe_type); + ++ apc->eth_stats.tx_cqe_err++; + break; + + default: +@@ -1077,6 +1119,7 @@ static void mana_poll_tx_cq(struct mana_ + netdev_err(ndev, "TX: unknown CQE type %d\n", + cqe_oob->cqe_hdr.cqe_type); + ++ apc->eth_stats.tx_cqe_unknown_type++; + break; + } + +@@ -1123,6 +1166,8 @@ static void mana_poll_tx_cq(struct mana_ + WARN_ON_ONCE(1); + + cq->work_done = pkt_transmitted; ++ ++ apc->eth_stats.tx_cqes -= pkt_transmitted; + } + + static void mana_post_pkt_rxq(struct mana_rxq *rxq) +@@ -1257,12 +1302,15 @@ static void mana_process_rx_cqe(struct m + struct gdma_context *gc = rxq->gdma_rq->gdma_dev->gdma_context; + struct net_device *ndev = rxq->ndev; + struct mana_recv_buf_oob *rxbuf_oob; ++ struct mana_port_context *apc; + struct device *dev = gc->dev; + void *new_buf, *old_buf; + struct page *new_page; + u32 curr, pktlen; + dma_addr_t da; + ++ apc = netdev_priv(ndev); ++ + switch (oob->cqe_hdr.cqe_type) { + case CQE_RX_OKAY: + break; +@@ -1275,6 +1323,7 @@ static void mana_process_rx_cqe(struct m + + case CQE_RX_COALESCED_4: + netdev_err(ndev, "RX coalescing is unsupported\n"); ++ apc->eth_stats.rx_coalesced_err++; + return; + + case CQE_RX_OBJECT_FENCE: +@@ -1284,6 +1333,7 @@ static void mana_process_rx_cqe(struct m + default: + netdev_err(ndev, "Unknown RX CQE type = %d\n", + oob->cqe_hdr.cqe_type); ++ apc->eth_stats.rx_cqe_unknown_type++; + return; + } + +@@ -1346,11 +1396,15 @@ static void mana_poll_rx_cq(struct mana_ + { + struct gdma_comp *comp = cq->gdma_comp_buf; + struct mana_rxq *rxq = cq->rxq; ++ struct mana_port_context *apc; + int comp_read, i; + ++ apc = netdev_priv(rxq->ndev); ++ + comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, CQE_POLLING_BUFFER); + WARN_ON_ONCE(comp_read > CQE_POLLING_BUFFER); + ++ apc->eth_stats.rx_cqes = comp_read; + rxq->xdp_flush = false; + + for (i = 0; i < comp_read; i++) { +@@ -1362,6 +1416,8 @@ static void mana_poll_rx_cq(struct mana_ + return; + + mana_process_rx_cqe(rxq, cq, &comp[i]); ++ ++ apc->eth_stats.rx_cqes--; + } + + if (rxq->xdp_flush) +--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +@@ -13,6 +13,15 @@ static const struct { + } mana_eth_stats[] = { + {"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)}, + {"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)}, ++ {"tx_cqes", offsetof(struct mana_ethtool_stats, tx_cqes)}, ++ {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, ++ {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, ++ tx_cqe_unknown_type)}, ++ {"rx_cqes", offsetof(struct mana_ethtool_stats, rx_cqes)}, ++ {"rx_coalesced_err", offsetof(struct mana_ethtool_stats, ++ rx_coalesced_err)}, ++ {"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, ++ rx_cqe_unknown_type)}, + }; + + static int mana_get_sset_count(struct net_device *ndev, int stringset) +@@ -23,7 +32,8 @@ static int mana_get_sset_count(struct ne + if (stringset != ETH_SS_STATS) + return -EINVAL; + +- return ARRAY_SIZE(mana_eth_stats) + num_queues * 8; ++ return ARRAY_SIZE(mana_eth_stats) + num_queues * ++ (MANA_STATS_RX_COUNT + MANA_STATS_TX_COUNT); + } + + static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data) +@@ -61,6 +71,22 @@ static void mana_get_strings(struct net_ + p += ETH_GSTRING_LEN; + sprintf(p, "tx_%d_xdp_xmit", i); + p += ETH_GSTRING_LEN; ++ sprintf(p, "tx_%d_tso_packets", i); ++ p += ETH_GSTRING_LEN; ++ sprintf(p, "tx_%d_tso_bytes", i); ++ p += ETH_GSTRING_LEN; ++ sprintf(p, "tx_%d_tso_inner_packets", i); ++ p += ETH_GSTRING_LEN; ++ sprintf(p, "tx_%d_tso_inner_bytes", i); ++ p += ETH_GSTRING_LEN; ++ sprintf(p, "tx_%d_long_pkt_fmt", i); ++ p += ETH_GSTRING_LEN; ++ sprintf(p, "tx_%d_short_pkt_fmt", i); ++ p += ETH_GSTRING_LEN; ++ sprintf(p, "tx_%d_csum_partial", i); ++ p += ETH_GSTRING_LEN; ++ sprintf(p, "tx_%d_mana_map_err", i); ++ p += ETH_GSTRING_LEN; + } + } + +@@ -78,6 +104,14 @@ static void mana_get_ethtool_stats(struc + u64 xdp_xmit; + u64 xdp_drop; + u64 xdp_tx; ++ u64 tso_packets; ++ u64 tso_bytes; ++ u64 tso_inner_packets; ++ u64 tso_inner_bytes; ++ u64 long_pkt_fmt; ++ u64 short_pkt_fmt; ++ u64 csum_partial; ++ u64 mana_map_err; + int q, i = 0; + + if (!apc->port_is_up) +@@ -113,11 +147,27 @@ static void mana_get_ethtool_stats(struc + packets = tx_stats->packets; + bytes = tx_stats->bytes; + xdp_xmit = tx_stats->xdp_xmit; ++ tso_packets = tx_stats->tso_packets; ++ tso_bytes = tx_stats->tso_bytes; ++ tso_inner_packets = tx_stats->tso_inner_packets; ++ tso_inner_bytes = tx_stats->tso_inner_bytes; ++ long_pkt_fmt = tx_stats->long_pkt_fmt; ++ short_pkt_fmt = tx_stats->short_pkt_fmt; ++ csum_partial = tx_stats->csum_partial; ++ mana_map_err = tx_stats->mana_map_err; + } while (u64_stats_fetch_retry(&tx_stats->syncp, start)); + + data[i++] = packets; + data[i++] = bytes; + data[i++] = xdp_xmit; ++ data[i++] = tso_packets; ++ data[i++] = tso_bytes; ++ data[i++] = tso_inner_packets; ++ data[i++] = tso_inner_bytes; ++ data[i++] = long_pkt_fmt; ++ data[i++] = short_pkt_fmt; ++ data[i++] = csum_partial; ++ data[i++] = mana_map_err; + } + } + +--- a/include/net/mana/mana.h ++++ b/include/net/mana/mana.h +@@ -48,6 +48,10 @@ enum TRI_STATE { + + #define MAX_PORTS_IN_MANA_DEV 256 + ++/* Update this count whenever the respective structures are changed */ ++#define MANA_STATS_RX_COUNT 5 ++#define MANA_STATS_TX_COUNT 11 ++ + struct mana_stats_rx { + u64 packets; + u64 bytes; +@@ -61,6 +65,14 @@ struct mana_stats_tx { + u64 packets; + u64 bytes; + u64 xdp_xmit; ++ u64 tso_packets; ++ u64 tso_bytes; ++ u64 tso_inner_packets; ++ u64 tso_inner_bytes; ++ u64 short_pkt_fmt; ++ u64 long_pkt_fmt; ++ u64 csum_partial; ++ u64 mana_map_err; + struct u64_stats_sync syncp; + }; + +@@ -331,6 +343,12 @@ struct mana_tx_qp { + struct mana_ethtool_stats { + u64 stop_queue; + u64 wake_queue; ++ u64 tx_cqes; ++ u64 tx_cqe_err; ++ u64 tx_cqe_unknown_type; ++ u64 rx_cqes; ++ u64 rx_coalesced_err; ++ u64 rx_cqe_unknown_type; + }; + + struct mana_context { diff --git a/debian/patches/features/all/ethernet-microsoft/0016-net-mana-Remove-redundant-pci_clear_master.patch b/debian/patches/features/all/ethernet-microsoft/0016-net-mana-Remove-redundant-pci_clear_master.patch new file mode 100644 index 000000000..c0bd34da8 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0016-net-mana-Remove-redundant-pci_clear_master.patch @@ -0,0 +1,54 @@ +From 0022db71934d56cc601cacee4c1e414d7f3cbb37 Mon Sep 17 00:00:00 2001 +From: Cai Huoqing <cai.huoqing@linux.dev> +Date: Thu, 23 Mar 2023 17:03:05 +0800 +Subject: [PATCH 16/23] net: mana: Remove redundant pci_clear_master + +Remove pci_clear_master to simplify the code, +the bus-mastering is also cleared in do_pci_disable_device, +like this: +./drivers/pci/pci.c:2197 +static void do_pci_disable_device(struct pci_dev *dev) +{ + u16 pci_command; + + pci_read_config_word(dev, PCI_COMMAND, &pci_command); + if (pci_command & PCI_COMMAND_MASTER) { + pci_command &= ~PCI_COMMAND_MASTER; + pci_write_config_word(dev, PCI_COMMAND, pci_command); + } + + pcibios_disable_device(dev); +}. +And dev->is_busmaster is set to 0 in pci_disable_device. + +Signed-off-by: Cai Huoqing <cai.huoqing@linux.dev> +Signed-off-by: David S. Miller <davem@davemloft.net> +(cherry picked from commit 2d59af8307526f2829fdec9c5c5898a857d55180) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/gdma_main.c | 2 -- + 1 file changed, 2 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c +index 5b7fddfc9ff1..97a1845c676a 100644 +--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c ++++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c +@@ -1440,7 +1440,6 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) + release_region: + pci_release_regions(pdev); + disable_dev: +- pci_clear_master(pdev); + pci_disable_device(pdev); + dev_err(&pdev->dev, "gdma probe failed: err = %d\n", err); + return err; +@@ -1459,7 +1458,6 @@ static void mana_gd_remove(struct pci_dev *pdev) + vfree(gc); + + pci_release_regions(pdev); +- pci_clear_master(pdev); + pci_disable_device(pdev); + } + +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0017-net-mana-Use-napi_build_skb-in-RX-path.patch b/debian/patches/features/all/ethernet-microsoft/0017-net-mana-Use-napi_build_skb-in-RX-path.patch new file mode 100644 index 000000000..c8f0f4588 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0017-net-mana-Use-napi_build_skb-in-RX-path.patch @@ -0,0 +1,33 @@ +From a8796c5278b15a55111d43ccd622b745945ca3d4 Mon Sep 17 00:00:00 2001 +From: Haiyang Zhang <haiyangz@microsoft.com> +Date: Wed, 12 Apr 2023 14:16:00 -0700 +Subject: [PATCH 17/23] net: mana: Use napi_build_skb in RX path + +Use napi_build_skb() instead of build_skb() to take advantage of the +NAPI percpu caches to obtain skbuff_head. + +Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> +Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com> +Signed-off-by: David S. Miller <davem@davemloft.net> +(cherry picked from commit ce518bc3e9ca342309995c9270c3ec4892963695) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana_en.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index 55bf40e5ee71..a1b7905ed2f7 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -1188,7 +1188,7 @@ static void mana_post_pkt_rxq(struct mana_rxq *rxq) + static struct sk_buff *mana_build_skb(void *buf_va, uint pkt_len, + struct xdp_buff *xdp) + { +- struct sk_buff *skb = build_skb(buf_va, PAGE_SIZE); ++ struct sk_buff *skb = napi_build_skb(buf_va, PAGE_SIZE); + + if (!skb) + return NULL; +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0018-net-mana-Refactor-RX-buffer-allocation-code-to-prepa.patch b/debian/patches/features/all/ethernet-microsoft/0018-net-mana-Refactor-RX-buffer-allocation-code-to-prepa.patch new file mode 100644 index 000000000..7c072d77c --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0018-net-mana-Refactor-RX-buffer-allocation-code-to-prepa.patch @@ -0,0 +1,289 @@ +From cf9f102448044cea851cb97666bf6e853c8963e3 Mon Sep 17 00:00:00 2001 +From: Haiyang Zhang <haiyangz@microsoft.com> +Date: Wed, 12 Apr 2023 14:16:01 -0700 +Subject: [PATCH 18/23] net: mana: Refactor RX buffer allocation code to + prepare for various MTU + +Move out common buffer allocation code from mana_process_rx_cqe() and +mana_alloc_rx_wqe() to helper functions. +Refactor related variables so they can be changed in one place, and buffer +sizes are in sync. + +Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> +Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com> +Signed-off-by: David S. Miller <davem@davemloft.net> +(cherry picked from commit a2917b23497e4205db32271e4e06e142a9f8a6aa) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana_en.c | 154 ++++++++++-------- + include/net/mana/mana.h | 6 +- + 2 files changed, 91 insertions(+), 69 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index a1b7905ed2f7..af0c0ee95d87 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -1282,14 +1282,64 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe, + u64_stats_update_end(&rx_stats->syncp); + + drop: +- WARN_ON_ONCE(rxq->xdp_save_page); +- rxq->xdp_save_page = virt_to_page(buf_va); ++ WARN_ON_ONCE(rxq->xdp_save_va); ++ /* Save for reuse */ ++ rxq->xdp_save_va = buf_va; + + ++ndev->stats.rx_dropped; + + return; + } + ++static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, ++ dma_addr_t *da, bool is_napi) ++{ ++ struct page *page; ++ void *va; ++ ++ /* Reuse XDP dropped page if available */ ++ if (rxq->xdp_save_va) { ++ va = rxq->xdp_save_va; ++ rxq->xdp_save_va = NULL; ++ } else { ++ page = dev_alloc_page(); ++ if (!page) ++ return NULL; ++ ++ va = page_to_virt(page); ++ } ++ ++ *da = dma_map_single(dev, va + XDP_PACKET_HEADROOM, rxq->datasize, ++ DMA_FROM_DEVICE); ++ ++ if (dma_mapping_error(dev, *da)) { ++ put_page(virt_to_head_page(va)); ++ return NULL; ++ } ++ ++ return va; ++} ++ ++/* Allocate frag for rx buffer, and save the old buf */ ++static void mana_refill_rxoob(struct device *dev, struct mana_rxq *rxq, ++ struct mana_recv_buf_oob *rxoob, void **old_buf) ++{ ++ dma_addr_t da; ++ void *va; ++ ++ va = mana_get_rxfrag(rxq, dev, &da, true); ++ ++ if (!va) ++ return; ++ ++ dma_unmap_single(dev, rxoob->sgl[0].address, rxq->datasize, ++ DMA_FROM_DEVICE); ++ *old_buf = rxoob->buf_va; ++ ++ rxoob->buf_va = va; ++ rxoob->sgl[0].address = da; ++} ++ + static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, + struct gdma_comp *cqe) + { +@@ -1299,10 +1349,8 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, + struct mana_recv_buf_oob *rxbuf_oob; + struct mana_port_context *apc; + struct device *dev = gc->dev; +- void *new_buf, *old_buf; +- struct page *new_page; ++ void *old_buf = NULL; + u32 curr, pktlen; +- dma_addr_t da; + + apc = netdev_priv(ndev); + +@@ -1345,40 +1393,11 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, + rxbuf_oob = &rxq->rx_oobs[curr]; + WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1); + +- /* Reuse XDP dropped page if available */ +- if (rxq->xdp_save_page) { +- new_page = rxq->xdp_save_page; +- rxq->xdp_save_page = NULL; +- } else { +- new_page = alloc_page(GFP_ATOMIC); +- } +- +- if (new_page) { +- da = dma_map_page(dev, new_page, XDP_PACKET_HEADROOM, rxq->datasize, +- DMA_FROM_DEVICE); +- +- if (dma_mapping_error(dev, da)) { +- __free_page(new_page); +- new_page = NULL; +- } +- } +- +- new_buf = new_page ? page_to_virt(new_page) : NULL; +- +- if (new_buf) { +- dma_unmap_page(dev, rxbuf_oob->buf_dma_addr, rxq->datasize, +- DMA_FROM_DEVICE); +- +- old_buf = rxbuf_oob->buf_va; +- +- /* refresh the rxbuf_oob with the new page */ +- rxbuf_oob->buf_va = new_buf; +- rxbuf_oob->buf_dma_addr = da; +- rxbuf_oob->sgl[0].address = rxbuf_oob->buf_dma_addr; +- } else { +- old_buf = NULL; /* drop the packet if no memory */ +- } ++ mana_refill_rxoob(dev, rxq, rxbuf_oob, &old_buf); + ++ /* Unsuccessful refill will have old_buf == NULL. ++ * In this case, mana_rx_skb() will drop the packet. ++ */ + mana_rx_skb(old_buf, oob, rxq); + + drop: +@@ -1659,8 +1678,8 @@ static void mana_destroy_rxq(struct mana_port_context *apc, + + mana_deinit_cq(apc, &rxq->rx_cq); + +- if (rxq->xdp_save_page) +- __free_page(rxq->xdp_save_page); ++ if (rxq->xdp_save_va) ++ put_page(virt_to_head_page(rxq->xdp_save_va)); + + for (i = 0; i < rxq->num_rx_buf; i++) { + rx_oob = &rxq->rx_oobs[i]; +@@ -1668,10 +1687,10 @@ static void mana_destroy_rxq(struct mana_port_context *apc, + if (!rx_oob->buf_va) + continue; + +- dma_unmap_page(dev, rx_oob->buf_dma_addr, rxq->datasize, +- DMA_FROM_DEVICE); ++ dma_unmap_single(dev, rx_oob->sgl[0].address, ++ rx_oob->sgl[0].size, DMA_FROM_DEVICE); + +- free_page((unsigned long)rx_oob->buf_va); ++ put_page(virt_to_head_page(rx_oob->buf_va)); + rx_oob->buf_va = NULL; + } + +@@ -1681,6 +1700,26 @@ static void mana_destroy_rxq(struct mana_port_context *apc, + kfree(rxq); + } + ++static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key, ++ struct mana_rxq *rxq, struct device *dev) ++{ ++ dma_addr_t da; ++ void *va; ++ ++ va = mana_get_rxfrag(rxq, dev, &da, false); ++ ++ if (!va) ++ return -ENOMEM; ++ ++ rx_oob->buf_va = va; ++ ++ rx_oob->sgl[0].address = da; ++ rx_oob->sgl[0].size = rxq->datasize; ++ rx_oob->sgl[0].mem_key = mem_key; ++ ++ return 0; ++} ++ + #define MANA_WQE_HEADER_SIZE 16 + #define MANA_WQE_SGE_SIZE 16 + +@@ -1690,9 +1729,8 @@ static int mana_alloc_rx_wqe(struct mana_port_context *apc, + struct gdma_context *gc = apc->ac->gdma_dev->gdma_context; + struct mana_recv_buf_oob *rx_oob; + struct device *dev = gc->dev; +- struct page *page; +- dma_addr_t da; + u32 buf_idx; ++ int ret; + + WARN_ON(rxq->datasize == 0 || rxq->datasize > PAGE_SIZE); + +@@ -1703,25 +1741,12 @@ static int mana_alloc_rx_wqe(struct mana_port_context *apc, + rx_oob = &rxq->rx_oobs[buf_idx]; + memset(rx_oob, 0, sizeof(*rx_oob)); + +- page = alloc_page(GFP_KERNEL); +- if (!page) +- return -ENOMEM; +- +- da = dma_map_page(dev, page, XDP_PACKET_HEADROOM, rxq->datasize, +- DMA_FROM_DEVICE); +- +- if (dma_mapping_error(dev, da)) { +- __free_page(page); +- return -ENOMEM; +- } +- +- rx_oob->buf_va = page_to_virt(page); +- rx_oob->buf_dma_addr = da; +- + rx_oob->num_sge = 1; +- rx_oob->sgl[0].address = rx_oob->buf_dma_addr; +- rx_oob->sgl[0].size = rxq->datasize; +- rx_oob->sgl[0].mem_key = apc->ac->gdma_dev->gpa_mkey; ++ ++ ret = mana_fill_rx_oob(rx_oob, apc->ac->gdma_dev->gpa_mkey, rxq, ++ dev); ++ if (ret) ++ return ret; + + rx_oob->wqe_req.sgl = rx_oob->sgl; + rx_oob->wqe_req.num_sge = rx_oob->num_sge; +@@ -1780,9 +1805,10 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, + rxq->ndev = ndev; + rxq->num_rx_buf = RX_BUFFERS_PER_QUEUE; + rxq->rxq_idx = rxq_idx; +- rxq->datasize = ALIGN(MAX_FRAME_SIZE, 64); + rxq->rxobj = INVALID_MANA_HANDLE; + ++ rxq->datasize = ALIGN(ETH_FRAME_LEN, 64); ++ + err = mana_alloc_rx_wqe(apc, rxq, &rq_size, &cq_size); + if (err) + goto out; +diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h +index 343ace6de20e..da556246233e 100644 +--- a/include/net/mana/mana.h ++++ b/include/net/mana/mana.h +@@ -36,9 +36,6 @@ enum TRI_STATE { + + #define COMP_ENTRY_SIZE 64 + +-#define ADAPTER_MTU_SIZE 1500 +-#define MAX_FRAME_SIZE (ADAPTER_MTU_SIZE + 14) +- + #define RX_BUFFERS_PER_QUEUE 512 + + #define MAX_SEND_BUFFERS_PER_QUEUE 256 +@@ -282,7 +279,6 @@ struct mana_recv_buf_oob { + struct gdma_wqe_request wqe_req; + + void *buf_va; +- dma_addr_t buf_dma_addr; + + /* SGL of the buffer going to be sent has part of the work request. */ + u32 num_sge; +@@ -322,7 +318,7 @@ struct mana_rxq { + + struct bpf_prog __rcu *bpf_prog; + struct xdp_rxq_info xdp_rxq; +- struct page *xdp_save_page; ++ void *xdp_save_va; /* for reusing */ + bool xdp_flush; + int xdp_rc; /* XDP redirect return code */ + +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0019-net-mana-Enable-RX-path-to-handle-various-MTU-sizes.patch b/debian/patches/features/all/ethernet-microsoft/0019-net-mana-Enable-RX-path-to-handle-various-MTU-sizes.patch new file mode 100644 index 000000000..7fb93c495 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0019-net-mana-Enable-RX-path-to-handle-various-MTU-sizes.patch @@ -0,0 +1,147 @@ +From 8640f747acafd65c43be07bd7db9a431b5926db3 Mon Sep 17 00:00:00 2001 +From: Haiyang Zhang <haiyangz@microsoft.com> +Date: Wed, 12 Apr 2023 14:16:02 -0700 +Subject: [PATCH 19/23] net: mana: Enable RX path to handle various MTU sizes + +Update RX data path to allocate and use RX queue DMA buffers with +proper size based on potentially various MTU sizes. + +Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> +Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com> +Signed-off-by: David S. Miller <davem@davemloft.net> +(cherry picked from commit 2fbbd712baf1c60996554326728bbdbef5616e12) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana_en.c | 38 ++++++++++++++----- + include/net/mana/mana.h | 7 ++++ + 2 files changed, 35 insertions(+), 10 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index af0c0ee95d87..afbbe447de1d 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -1185,10 +1185,10 @@ static void mana_post_pkt_rxq(struct mana_rxq *rxq) + WARN_ON_ONCE(recv_buf_oob->wqe_inf.wqe_size_in_bu != 1); + } + +-static struct sk_buff *mana_build_skb(void *buf_va, uint pkt_len, +- struct xdp_buff *xdp) ++static struct sk_buff *mana_build_skb(struct mana_rxq *rxq, void *buf_va, ++ uint pkt_len, struct xdp_buff *xdp) + { +- struct sk_buff *skb = napi_build_skb(buf_va, PAGE_SIZE); ++ struct sk_buff *skb = napi_build_skb(buf_va, rxq->alloc_size); + + if (!skb) + return NULL; +@@ -1196,11 +1196,12 @@ static struct sk_buff *mana_build_skb(void *buf_va, uint pkt_len, + if (xdp->data_hard_start) { + skb_reserve(skb, xdp->data - xdp->data_hard_start); + skb_put(skb, xdp->data_end - xdp->data); +- } else { +- skb_reserve(skb, XDP_PACKET_HEADROOM); +- skb_put(skb, pkt_len); ++ return skb; + } + ++ skb_reserve(skb, rxq->headroom); ++ skb_put(skb, pkt_len); ++ + return skb; + } + +@@ -1233,7 +1234,7 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe, + if (act != XDP_PASS && act != XDP_TX) + goto drop_xdp; + +- skb = mana_build_skb(buf_va, pkt_len, &xdp); ++ skb = mana_build_skb(rxq, buf_va, pkt_len, &xdp); + + if (!skb) + goto drop; +@@ -1301,6 +1302,14 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, + if (rxq->xdp_save_va) { + va = rxq->xdp_save_va; + rxq->xdp_save_va = NULL; ++ } else if (rxq->alloc_size > PAGE_SIZE) { ++ if (is_napi) ++ va = napi_alloc_frag(rxq->alloc_size); ++ else ++ va = netdev_alloc_frag(rxq->alloc_size); ++ ++ if (!va) ++ return NULL; + } else { + page = dev_alloc_page(); + if (!page) +@@ -1309,7 +1318,7 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, + va = page_to_virt(page); + } + +- *da = dma_map_single(dev, va + XDP_PACKET_HEADROOM, rxq->datasize, ++ *da = dma_map_single(dev, va + rxq->headroom, rxq->datasize, + DMA_FROM_DEVICE); + + if (dma_mapping_error(dev, *da)) { +@@ -1732,7 +1741,7 @@ static int mana_alloc_rx_wqe(struct mana_port_context *apc, + u32 buf_idx; + int ret; + +- WARN_ON(rxq->datasize == 0 || rxq->datasize > PAGE_SIZE); ++ WARN_ON(rxq->datasize == 0); + + *rxq_size = 0; + *cq_size = 0; +@@ -1788,6 +1797,7 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, + struct gdma_dev *gd = apc->ac->gdma_dev; + struct mana_obj_spec wq_spec; + struct mana_obj_spec cq_spec; ++ unsigned int mtu = ndev->mtu; + struct gdma_queue_spec spec; + struct mana_cq *cq = NULL; + struct gdma_context *gc; +@@ -1807,7 +1817,15 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, + rxq->rxq_idx = rxq_idx; + rxq->rxobj = INVALID_MANA_HANDLE; + +- rxq->datasize = ALIGN(ETH_FRAME_LEN, 64); ++ rxq->datasize = ALIGN(mtu + ETH_HLEN, 64); ++ ++ if (mtu > MANA_XDP_MTU_MAX) { ++ rxq->alloc_size = mtu + MANA_RXBUF_PAD; ++ rxq->headroom = 0; ++ } else { ++ rxq->alloc_size = mtu + MANA_RXBUF_PAD + XDP_PACKET_HEADROOM; ++ rxq->headroom = XDP_PACKET_HEADROOM; ++ } + + err = mana_alloc_rx_wqe(apc, rxq, &rq_size, &cq_size); + if (err) +diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h +index da556246233e..42795849d68c 100644 +--- a/include/net/mana/mana.h ++++ b/include/net/mana/mana.h +@@ -291,6 +291,11 @@ struct mana_recv_buf_oob { + struct gdma_posted_wqe_info wqe_inf; + }; + ++#define MANA_RXBUF_PAD (SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) \ ++ + ETH_HLEN) ++ ++#define MANA_XDP_MTU_MAX (PAGE_SIZE - MANA_RXBUF_PAD - XDP_PACKET_HEADROOM) ++ + struct mana_rxq { + struct gdma_queue *gdma_rq; + /* Cache the gdma receive queue id */ +@@ -300,6 +305,8 @@ struct mana_rxq { + u32 rxq_idx; + + u32 datasize; ++ u32 alloc_size; ++ u32 headroom; + + mana_handle_t rxobj; + +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0020-net-mana-Add-support-for-jumbo-frame.patch b/debian/patches/features/all/ethernet-microsoft/0020-net-mana-Add-support-for-jumbo-frame.patch new file mode 100644 index 000000000..5a5a44d88 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0020-net-mana-Add-support-for-jumbo-frame.patch @@ -0,0 +1,423 @@ +From 2552a80c48dd33368d0e7a2b94e1eb72e3053b99 Mon Sep 17 00:00:00 2001 +From: Haiyang Zhang <haiyangz@microsoft.com> +Date: Wed, 12 Apr 2023 14:16:03 -0700 +Subject: [PATCH 20/23] net: mana: Add support for jumbo frame + +During probe, get the hardware-allowed max MTU by querying the device +configuration. Users can select MTU up to the device limit. +When XDP is in use, limit MTU settings so the buffer size is within +one page. And, when MTU is set to a too large value, XDP is not allowed +to run. +Also, to prevent changing MTU fails, and leaves the NIC in a bad state, +pre-allocate all buffers before starting the change. So in low memory +condition, it will return error, without affecting the NIC. + +Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> +Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com> +Signed-off-by: David S. Miller <davem@davemloft.net> +(cherry picked from commit 80f6215b450eb8e92d8b1f117abf5ecf867f963e) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + .../net/ethernet/microsoft/mana/mana_bpf.c | 22 +- + drivers/net/ethernet/microsoft/mana/mana_en.c | 217 ++++++++++++++++-- + include/net/mana/gdma.h | 4 + + include/net/mana/mana.h | 14 ++ + 4 files changed, 233 insertions(+), 24 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c +index 3caea631229c..23b1521c0df9 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c +@@ -133,12 +133,6 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, + return act; + } + +-static unsigned int mana_xdp_fraglen(unsigned int len) +-{ +- return SKB_DATA_ALIGN(len) + +- SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); +-} +- + struct bpf_prog *mana_xdp_get(struct mana_port_context *apc) + { + ASSERT_RTNL(); +@@ -179,17 +173,18 @@ static int mana_xdp_set(struct net_device *ndev, struct bpf_prog *prog, + { + struct mana_port_context *apc = netdev_priv(ndev); + struct bpf_prog *old_prog; +- int buf_max; ++ struct gdma_context *gc; ++ ++ gc = apc->ac->gdma_dev->gdma_context; + + old_prog = mana_xdp_get(apc); + + if (!old_prog && !prog) + return 0; + +- buf_max = XDP_PACKET_HEADROOM + mana_xdp_fraglen(ndev->mtu + ETH_HLEN); +- if (prog && buf_max > PAGE_SIZE) { +- netdev_err(ndev, "XDP: mtu:%u too large, buf_max:%u\n", +- ndev->mtu, buf_max); ++ if (prog && ndev->mtu > MANA_XDP_MTU_MAX) { ++ netdev_err(ndev, "XDP: mtu:%u too large, mtu_max:%lu\n", ++ ndev->mtu, MANA_XDP_MTU_MAX); + NL_SET_ERR_MSG_MOD(extack, "XDP: mtu too large"); + + return -EOPNOTSUPP; +@@ -206,6 +201,11 @@ static int mana_xdp_set(struct net_device *ndev, struct bpf_prog *prog, + if (apc->port_is_up) + mana_chn_setxdp(apc, prog); + ++ if (prog) ++ ndev->max_mtu = MANA_XDP_MTU_MAX; ++ else ++ ndev->max_mtu = gc->adapter_mtu - ETH_HLEN; ++ + return 0; + } + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index afbbe447de1d..34fa5c758b28 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -427,6 +427,192 @@ static u16 mana_select_queue(struct net_device *ndev, struct sk_buff *skb, + return txq; + } + ++/* Release pre-allocated RX buffers */ ++static void mana_pre_dealloc_rxbufs(struct mana_port_context *mpc) ++{ ++ struct device *dev; ++ int i; ++ ++ dev = mpc->ac->gdma_dev->gdma_context->dev; ++ ++ if (!mpc->rxbufs_pre) ++ goto out1; ++ ++ if (!mpc->das_pre) ++ goto out2; ++ ++ while (mpc->rxbpre_total) { ++ i = --mpc->rxbpre_total; ++ dma_unmap_single(dev, mpc->das_pre[i], mpc->rxbpre_datasize, ++ DMA_FROM_DEVICE); ++ put_page(virt_to_head_page(mpc->rxbufs_pre[i])); ++ } ++ ++ kfree(mpc->das_pre); ++ mpc->das_pre = NULL; ++ ++out2: ++ kfree(mpc->rxbufs_pre); ++ mpc->rxbufs_pre = NULL; ++ ++out1: ++ mpc->rxbpre_datasize = 0; ++ mpc->rxbpre_alloc_size = 0; ++ mpc->rxbpre_headroom = 0; ++} ++ ++/* Get a buffer from the pre-allocated RX buffers */ ++static void *mana_get_rxbuf_pre(struct mana_rxq *rxq, dma_addr_t *da) ++{ ++ struct net_device *ndev = rxq->ndev; ++ struct mana_port_context *mpc; ++ void *va; ++ ++ mpc = netdev_priv(ndev); ++ ++ if (!mpc->rxbufs_pre || !mpc->das_pre || !mpc->rxbpre_total) { ++ netdev_err(ndev, "No RX pre-allocated bufs\n"); ++ return NULL; ++ } ++ ++ /* Check sizes to catch unexpected coding error */ ++ if (mpc->rxbpre_datasize != rxq->datasize) { ++ netdev_err(ndev, "rxbpre_datasize mismatch: %u: %u\n", ++ mpc->rxbpre_datasize, rxq->datasize); ++ return NULL; ++ } ++ ++ if (mpc->rxbpre_alloc_size != rxq->alloc_size) { ++ netdev_err(ndev, "rxbpre_alloc_size mismatch: %u: %u\n", ++ mpc->rxbpre_alloc_size, rxq->alloc_size); ++ return NULL; ++ } ++ ++ if (mpc->rxbpre_headroom != rxq->headroom) { ++ netdev_err(ndev, "rxbpre_headroom mismatch: %u: %u\n", ++ mpc->rxbpre_headroom, rxq->headroom); ++ return NULL; ++ } ++ ++ mpc->rxbpre_total--; ++ ++ *da = mpc->das_pre[mpc->rxbpre_total]; ++ va = mpc->rxbufs_pre[mpc->rxbpre_total]; ++ mpc->rxbufs_pre[mpc->rxbpre_total] = NULL; ++ ++ /* Deallocate the array after all buffers are gone */ ++ if (!mpc->rxbpre_total) ++ mana_pre_dealloc_rxbufs(mpc); ++ ++ return va; ++} ++ ++/* Get RX buffer's data size, alloc size, XDP headroom based on MTU */ ++static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size, ++ u32 *headroom) ++{ ++ if (mtu > MANA_XDP_MTU_MAX) ++ *headroom = 0; /* no support for XDP */ ++ else ++ *headroom = XDP_PACKET_HEADROOM; ++ ++ *alloc_size = mtu + MANA_RXBUF_PAD + *headroom; ++ ++ *datasize = ALIGN(mtu + ETH_HLEN, MANA_RX_DATA_ALIGN); ++} ++ ++static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu) ++{ ++ struct device *dev; ++ struct page *page; ++ dma_addr_t da; ++ int num_rxb; ++ void *va; ++ int i; ++ ++ mana_get_rxbuf_cfg(new_mtu, &mpc->rxbpre_datasize, ++ &mpc->rxbpre_alloc_size, &mpc->rxbpre_headroom); ++ ++ dev = mpc->ac->gdma_dev->gdma_context->dev; ++ ++ num_rxb = mpc->num_queues * RX_BUFFERS_PER_QUEUE; ++ ++ WARN(mpc->rxbufs_pre, "mana rxbufs_pre exists\n"); ++ mpc->rxbufs_pre = kmalloc_array(num_rxb, sizeof(void *), GFP_KERNEL); ++ if (!mpc->rxbufs_pre) ++ goto error; ++ ++ mpc->das_pre = kmalloc_array(num_rxb, sizeof(dma_addr_t), GFP_KERNEL); ++ if (!mpc->das_pre) ++ goto error; ++ ++ mpc->rxbpre_total = 0; ++ ++ for (i = 0; i < num_rxb; i++) { ++ if (mpc->rxbpre_alloc_size > PAGE_SIZE) { ++ va = netdev_alloc_frag(mpc->rxbpre_alloc_size); ++ if (!va) ++ goto error; ++ } else { ++ page = dev_alloc_page(); ++ if (!page) ++ goto error; ++ ++ va = page_to_virt(page); ++ } ++ ++ da = dma_map_single(dev, va + mpc->rxbpre_headroom, ++ mpc->rxbpre_datasize, DMA_FROM_DEVICE); ++ ++ if (dma_mapping_error(dev, da)) { ++ put_page(virt_to_head_page(va)); ++ goto error; ++ } ++ ++ mpc->rxbufs_pre[i] = va; ++ mpc->das_pre[i] = da; ++ mpc->rxbpre_total = i + 1; ++ } ++ ++ return 0; ++ ++error: ++ mana_pre_dealloc_rxbufs(mpc); ++ return -ENOMEM; ++} ++ ++static int mana_change_mtu(struct net_device *ndev, int new_mtu) ++{ ++ struct mana_port_context *mpc = netdev_priv(ndev); ++ unsigned int old_mtu = ndev->mtu; ++ int err; ++ ++ /* Pre-allocate buffers to prevent failure in mana_attach later */ ++ err = mana_pre_alloc_rxbufs(mpc, new_mtu); ++ if (err) { ++ netdev_err(ndev, "Insufficient memory for new MTU\n"); ++ return err; ++ } ++ ++ err = mana_detach(ndev, false); ++ if (err) { ++ netdev_err(ndev, "mana_detach failed: %d\n", err); ++ goto out; ++ } ++ ++ ndev->mtu = new_mtu; ++ ++ err = mana_attach(ndev); ++ if (err) { ++ netdev_err(ndev, "mana_attach failed: %d\n", err); ++ ndev->mtu = old_mtu; ++ } ++ ++out: ++ mana_pre_dealloc_rxbufs(mpc); ++ return err; ++} ++ + static const struct net_device_ops mana_devops = { + .ndo_open = mana_open, + .ndo_stop = mana_close, +@@ -436,6 +622,7 @@ static const struct net_device_ops mana_devops = { + .ndo_get_stats64 = mana_get_stats64, + .ndo_bpf = mana_bpf, + .ndo_xdp_xmit = mana_xdp_xmit, ++ .ndo_change_mtu = mana_change_mtu, + }; + + static void mana_cleanup_port_context(struct mana_port_context *apc) +@@ -625,6 +812,9 @@ static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver, + + mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_DEV_CONFIG, + sizeof(req), sizeof(resp)); ++ ++ req.hdr.resp.msg_version = GDMA_MESSAGE_V2; ++ + req.proto_major_ver = proto_major_ver; + req.proto_minor_ver = proto_minor_ver; + req.proto_micro_ver = proto_micro_ver; +@@ -647,6 +837,11 @@ static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver, + + *max_num_vports = resp.max_num_vports; + ++ if (resp.hdr.response.msg_version == GDMA_MESSAGE_V2) ++ gc->adapter_mtu = resp.adapter_mtu; ++ else ++ gc->adapter_mtu = ETH_FRAME_LEN; ++ + return 0; + } + +@@ -1712,10 +1907,14 @@ static void mana_destroy_rxq(struct mana_port_context *apc, + static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key, + struct mana_rxq *rxq, struct device *dev) + { ++ struct mana_port_context *mpc = netdev_priv(rxq->ndev); + dma_addr_t da; + void *va; + +- va = mana_get_rxfrag(rxq, dev, &da, false); ++ if (mpc->rxbufs_pre) ++ va = mana_get_rxbuf_pre(rxq, &da); ++ else ++ va = mana_get_rxfrag(rxq, dev, &da, false); + + if (!va) + return -ENOMEM; +@@ -1797,7 +1996,6 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, + struct gdma_dev *gd = apc->ac->gdma_dev; + struct mana_obj_spec wq_spec; + struct mana_obj_spec cq_spec; +- unsigned int mtu = ndev->mtu; + struct gdma_queue_spec spec; + struct mana_cq *cq = NULL; + struct gdma_context *gc; +@@ -1817,15 +2015,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, + rxq->rxq_idx = rxq_idx; + rxq->rxobj = INVALID_MANA_HANDLE; + +- rxq->datasize = ALIGN(mtu + ETH_HLEN, 64); +- +- if (mtu > MANA_XDP_MTU_MAX) { +- rxq->alloc_size = mtu + MANA_RXBUF_PAD; +- rxq->headroom = 0; +- } else { +- rxq->alloc_size = mtu + MANA_RXBUF_PAD + XDP_PACKET_HEADROOM; +- rxq->headroom = XDP_PACKET_HEADROOM; +- } ++ mana_get_rxbuf_cfg(ndev->mtu, &rxq->datasize, &rxq->alloc_size, ++ &rxq->headroom); + + err = mana_alloc_rx_wqe(apc, rxq, &rq_size, &cq_size); + if (err) +@@ -2238,8 +2429,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, + ndev->netdev_ops = &mana_devops; + ndev->ethtool_ops = &mana_ethtool_ops; + ndev->mtu = ETH_DATA_LEN; +- ndev->max_mtu = ndev->mtu; +- ndev->min_mtu = ndev->mtu; ++ ndev->max_mtu = gc->adapter_mtu - ETH_HLEN; ++ ndev->min_mtu = ETH_MIN_MTU; + ndev->needed_headroom = MANA_HEADROOM; + ndev->dev_port = port_idx; + SET_NETDEV_DEV(ndev, gc->dev); +diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h +index aabc7cea8a49..b27bf852471b 100644 +--- a/include/net/mana/gdma.h ++++ b/include/net/mana/gdma.h +@@ -143,6 +143,7 @@ struct gdma_general_req { + }; /* HW DATA */ + + #define GDMA_MESSAGE_V1 1 ++#define GDMA_MESSAGE_V2 2 + + struct gdma_general_resp { + struct gdma_resp_hdr hdr; +@@ -352,6 +353,9 @@ struct gdma_context { + struct gdma_resource msix_resource; + struct gdma_irq_context *irq_contexts; + ++ /* L2 MTU */ ++ u16 adapter_mtu; ++ + /* This maps a CQ index to the queue structure. */ + unsigned int max_num_cqs; + struct gdma_queue **cq_table; +diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h +index 42795849d68c..4f19d73b66ae 100644 +--- a/include/net/mana/mana.h ++++ b/include/net/mana/mana.h +@@ -37,6 +37,7 @@ enum TRI_STATE { + #define COMP_ENTRY_SIZE 64 + + #define RX_BUFFERS_PER_QUEUE 512 ++#define MANA_RX_DATA_ALIGN 64 + + #define MAX_SEND_BUFFERS_PER_QUEUE 256 + +@@ -390,6 +391,14 @@ struct mana_port_context { + /* This points to an array of num_queues of RQ pointers. */ + struct mana_rxq **rxqs; + ++ /* pre-allocated rx buffer array */ ++ void **rxbufs_pre; ++ dma_addr_t *das_pre; ++ int rxbpre_total; ++ u32 rxbpre_datasize; ++ u32 rxbpre_alloc_size; ++ u32 rxbpre_headroom; ++ + struct bpf_prog *bpf_prog; + + /* Create num_queues EQs, SQs, SQ-CQs, RQs and RQ-CQs, respectively. */ +@@ -486,6 +495,11 @@ struct mana_query_device_cfg_resp { + u16 max_num_vports; + u16 reserved; + u32 max_num_eqs; ++ ++ /* response v2: */ ++ u16 adapter_mtu; ++ u16 reserved2; ++ u32 reserved3; + }; /* HW DATA */ + + /* Query vPort Configuration */ +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0021-net-mana-Check-if-netdev-napi_alloc_frag-returns-sin.patch b/debian/patches/features/all/ethernet-microsoft/0021-net-mana-Check-if-netdev-napi_alloc_frag-returns-sin.patch new file mode 100644 index 000000000..33ca4257b --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0021-net-mana-Check-if-netdev-napi_alloc_frag-returns-sin.patch @@ -0,0 +1,54 @@ +From e1541b0cdf147beef46101f2b9fa8aeb9793bd8d Mon Sep 17 00:00:00 2001 +From: Haiyang Zhang <haiyangz@microsoft.com> +Date: Fri, 21 Apr 2023 10:06:58 -0700 +Subject: [PATCH 21/23] net: mana: Check if netdev/napi_alloc_frag returns + single page + +netdev/napi_alloc_frag() may fall back to single page which is smaller +than the requested size. +Add error checking to avoid memory overwritten. + +Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> +Signed-off-by: Jakub Kicinski <kuba@kernel.org> +(cherry picked from commit df18f2da302f169e1a29098c6ca3b474f1b0269e) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana_en.c | 15 +++++++++++++++ + 1 file changed, 15 insertions(+) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index 34fa5c758b28..fc19e62c9c84 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -553,6 +553,14 @@ static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu) + va = netdev_alloc_frag(mpc->rxbpre_alloc_size); + if (!va) + goto error; ++ ++ page = virt_to_head_page(va); ++ /* Check if the frag falls back to single page */ ++ if (compound_order(page) < ++ get_order(mpc->rxbpre_alloc_size)) { ++ put_page(page); ++ goto error; ++ } + } else { + page = dev_alloc_page(); + if (!page) +@@ -1505,6 +1513,13 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, + + if (!va) + return NULL; ++ ++ page = virt_to_head_page(va); ++ /* Check if the frag falls back to single page */ ++ if (compound_order(page) < get_order(rxq->alloc_size)) { ++ put_page(page); ++ return NULL; ++ } + } else { + page = dev_alloc_page(); + if (!page) +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0022-net-mana-Fix-perf-regression-remove-rx_cqes-tx_cqes-.patch b/debian/patches/features/all/ethernet-microsoft/0022-net-mana-Fix-perf-regression-remove-rx_cqes-tx_cqes-.patch new file mode 100644 index 000000000..21a354cc8 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0022-net-mana-Fix-perf-regression-remove-rx_cqes-tx_cqes-.patch @@ -0,0 +1,121 @@ +From a6967df15a72ffd53963492b8cf52438cf0c27f7 Mon Sep 17 00:00:00 2001 +From: Haiyang Zhang <haiyangz@microsoft.com> +Date: Fri, 26 May 2023 08:38:57 -0700 +Subject: [PATCH 22/23] net: mana: Fix perf regression: remove rx_cqes, tx_cqes + counters + +The apc->eth_stats.rx_cqes is one per NIC (vport), and it's on the +frequent and parallel code path of all queues. So, r/w into this +single shared variable by many threads on different CPUs creates a +lot caching and memory overhead, hence perf regression. And, it's +not accurate due to the high volume concurrent r/w. + +For example, a workload is iperf with 128 threads, and with RPS +enabled. We saw perf regression of 25% with the previous patch +adding the counters. And this patch eliminates the regression. + +Since the error path of mana_poll_rx_cq() already has warnings, so +keeping the counter and convert it to a per-queue variable is not +necessary. So, just remove this counter from this high frequency +code path. + +Also, remove the tx_cqes counter for the same reason. We have +warnings & other counters for errors on that path, and don't need +to count every normal cqe processing. + +Cc: stable@vger.kernel.org +Fixes: bd7fc6e1957c ("net: mana: Add new MANA VF performance counters for easier troubleshooting") +Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> +Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com> +Reviewed-by: Jiri Pirko <jiri@nvidia.com> +Link: https://lore.kernel.org/r/1685115537-31675-1-git-send-email-haiyangz@microsoft.com +Signed-off-by: Paolo Abeni <pabeni@redhat.com> +(cherry picked from commit 1919b39fc6eabb9a6f9a51706ff6d03865f5df29) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana_en.c | 10 ---------- + drivers/net/ethernet/microsoft/mana/mana_ethtool.c | 2 -- + include/net/mana/mana.h | 2 -- + 3 files changed, 14 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index fc19e62c9c84..25b17213e54d 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -1280,8 +1280,6 @@ static void mana_poll_tx_cq(struct mana_cq *cq) + if (comp_read < 1) + return; + +- apc->eth_stats.tx_cqes = comp_read; +- + for (i = 0; i < comp_read; i++) { + struct mana_tx_comp_oob *cqe_oob; + +@@ -1364,8 +1362,6 @@ static void mana_poll_tx_cq(struct mana_cq *cq) + WARN_ON_ONCE(1); + + cq->work_done = pkt_transmitted; +- +- apc->eth_stats.tx_cqes -= pkt_transmitted; + } + + static void mana_post_pkt_rxq(struct mana_rxq *rxq) +@@ -1629,15 +1625,11 @@ static void mana_poll_rx_cq(struct mana_cq *cq) + { + struct gdma_comp *comp = cq->gdma_comp_buf; + struct mana_rxq *rxq = cq->rxq; +- struct mana_port_context *apc; + int comp_read, i; + +- apc = netdev_priv(rxq->ndev); +- + comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, CQE_POLLING_BUFFER); + WARN_ON_ONCE(comp_read > CQE_POLLING_BUFFER); + +- apc->eth_stats.rx_cqes = comp_read; + rxq->xdp_flush = false; + + for (i = 0; i < comp_read; i++) { +@@ -1649,8 +1641,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq) + return; + + mana_process_rx_cqe(rxq, cq, &comp[i]); +- +- apc->eth_stats.rx_cqes--; + } + + if (rxq->xdp_flush) +diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +index a64c81410dc1..0dc78679f620 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +@@ -13,11 +13,9 @@ static const struct { + } mana_eth_stats[] = { + {"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)}, + {"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)}, +- {"tx_cqes", offsetof(struct mana_ethtool_stats, tx_cqes)}, + {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, + {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, + tx_cqe_unknown_type)}, +- {"rx_cqes", offsetof(struct mana_ethtool_stats, rx_cqes)}, + {"rx_coalesced_err", offsetof(struct mana_ethtool_stats, + rx_coalesced_err)}, + {"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, +diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h +index 4f19d73b66ae..3abfce420594 100644 +--- a/include/net/mana/mana.h ++++ b/include/net/mana/mana.h +@@ -347,10 +347,8 @@ struct mana_tx_qp { + struct mana_ethtool_stats { + u64 stop_queue; + u64 wake_queue; +- u64 tx_cqes; + u64 tx_cqe_err; + u64 tx_cqe_unknown_type; +- u64 rx_cqes; + u64 rx_coalesced_err; + u64 rx_cqe_unknown_type; + }; +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0023-net-mana-Add-support-for-vlan-tagging.patch b/debian/patches/features/all/ethernet-microsoft/0023-net-mana-Add-support-for-vlan-tagging.patch new file mode 100644 index 000000000..74866c088 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0023-net-mana-Add-support-for-vlan-tagging.patch @@ -0,0 +1,67 @@ +From dc801500fea4fd5ddecc4007acffb5716a761f51 Mon Sep 17 00:00:00 2001 +From: Haiyang Zhang <haiyangz@microsoft.com> +Date: Fri, 9 Jun 2023 05:47:17 -0700 +Subject: [PATCH 23/23] net: mana: Add support for vlan tagging + +To support vlan, use MANA_LONG_PKT_FMT if vlan tag is present in TX +skb. Then extract the vlan tag from the skb struct, and save it to +tx_oob for the NIC to transmit. For vlan tags on the payload, they +are accepted by the NIC too. + +For RX, extract the vlan tag from CQE and put it into skb. + +Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> +Signed-off-by: David S. Miller <davem@davemloft.net> +(cherry picked from commit b803d1fded4085d268507a432dac8077ead68971) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana_en.c | 19 +++++++++++++++++-- + 1 file changed, 17 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index 25b17213e54d..808dbf55beef 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -179,6 +179,14 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) + pkg.tx_oob.s_oob.short_vp_offset = txq->vp_offset; + } + ++ if (skb_vlan_tag_present(skb)) { ++ pkt_fmt = MANA_LONG_PKT_FMT; ++ pkg.tx_oob.l_oob.inject_vlan_pri_tag = 1; ++ pkg.tx_oob.l_oob.pcp = skb_vlan_tag_get_prio(skb); ++ pkg.tx_oob.l_oob.dei = skb_vlan_tag_get_cfi(skb); ++ pkg.tx_oob.l_oob.vlan_id = skb_vlan_tag_get_id(skb); ++ } ++ + pkg.tx_oob.s_oob.pkt_fmt = pkt_fmt; + + if (pkt_fmt == MANA_SHORT_PKT_FMT) { +@@ -1458,6 +1466,12 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe, + skb_set_hash(skb, hash_value, PKT_HASH_TYPE_L3); + } + ++ if (cqe->rx_vlantag_present) { ++ u16 vlan_tci = cqe->rx_vlan_id; ++ ++ __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci); ++ } ++ + u64_stats_update_begin(&rx_stats->syncp); + rx_stats->packets++; + rx_stats->bytes += pkt_len; +@@ -2454,8 +2468,9 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, + ndev->hw_features |= NETIF_F_RXCSUM; + ndev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6; + ndev->hw_features |= NETIF_F_RXHASH; +- ndev->features = ndev->hw_features; +- ndev->vlan_features = 0; ++ ndev->features = ndev->hw_features | NETIF_F_HW_VLAN_CTAG_TX | ++ NETIF_F_HW_VLAN_CTAG_RX; ++ ndev->vlan_features = ndev->features; + + err = register_netdev(ndev); + if (err) { +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0024-RDMA-mana_ib-Use-v2-version-of-cfg_rx_steer_req-to-e.patch b/debian/patches/features/all/ethernet-microsoft/0024-RDMA-mana_ib-Use-v2-version-of-cfg_rx_steer_req-to-e.patch new file mode 100644 index 000000000..fb8020cdb --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0024-RDMA-mana_ib-Use-v2-version-of-cfg_rx_steer_req-to-e.patch @@ -0,0 +1,78 @@ +From 672aac0622254a8f1f5f9d2aa8cee2319654d083 Mon Sep 17 00:00:00 2001 +From: Long Li <longli@microsoft.com> +Date: Sat, 13 May 2023 23:18:15 -0700 +Subject: [PATCH 24/30] RDMA/mana_ib: Use v2 version of cfg_rx_steer_req to + enable RX coalescing + +With RX coalescing, one CQE entry can be used to indicate multiple packets +on the receive queue. This saves processing time and PCI bandwidth over +the CQ. + +The MANA Ethernet driver also uses the v2 version of the protocol. It +doesn't use RX coalescing and its behavior is not changed. + +Link: https://lore.kernel.org/r/1684045095-31228-1-git-send-email-longli@linuxonhyperv.com +Signed-off-by: Long Li <longli@microsoft.com> +Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> +(cherry picked from commit 2145328515c8fa9b8a9f7889250bc6c032f2a0e6) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana_en.c | 5 ++++- + include/net/mana/mana.h | 4 +++- + 2 files changed, 7 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index 808dbf55beef..7d82b8949a1e 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -981,7 +981,7 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc, + bool update_tab) + { + u16 num_entries = MANA_INDIRECT_TABLE_SIZE; +- struct mana_cfg_rx_steer_req *req = NULL; ++ struct mana_cfg_rx_steer_req_v2 *req; + struct mana_cfg_rx_steer_resp resp = {}; + struct net_device *ndev = apc->ndev; + mana_handle_t *req_indir_tab; +@@ -996,6 +996,8 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc, + mana_gd_init_req_hdr(&req->hdr, MANA_CONFIG_VPORT_RX, req_buf_size, + sizeof(resp)); + ++ req->hdr.req.msg_version = GDMA_MESSAGE_V2; ++ + req->vport = apc->port_handle; + req->num_indir_entries = num_entries; + req->indir_tab_offset = sizeof(*req); +@@ -1005,6 +1007,7 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc, + req->update_hashkey = update_key; + req->update_indir_tab = update_tab; + req->default_rxobj = apc->default_rxobj; ++ req->cqe_coalescing_enable = 0; + + if (update_key) + memcpy(&req->hashkey, apc->hashkey, MANA_HASH_KEY_SIZE); +diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h +index 3abfce420594..46b5769a5b6a 100644 +--- a/include/net/mana/mana.h ++++ b/include/net/mana/mana.h +@@ -576,7 +576,7 @@ struct mana_fence_rq_resp { + }; /* HW DATA */ + + /* Configure vPort Rx Steering */ +-struct mana_cfg_rx_steer_req { ++struct mana_cfg_rx_steer_req_v2 { + struct gdma_req_hdr hdr; + mana_handle_t vport; + u16 num_indir_entries; +@@ -589,6 +589,8 @@ struct mana_cfg_rx_steer_req { + u8 reserved; + mana_handle_t default_rxobj; + u8 hashkey[MANA_HASH_KEY_SIZE]; ++ u8 cqe_coalescing_enable; ++ u8 reserved2[7]; + }; /* HW DATA */ + + struct mana_cfg_rx_steer_resp { +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0025-net-mana-use-vmalloc_array-and-vcalloc.patch b/debian/patches/features/all/ethernet-microsoft/0025-net-mana-use-vmalloc_array-and-vcalloc.patch new file mode 100644 index 000000000..348583771 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0025-net-mana-use-vmalloc_array-and-vcalloc.patch @@ -0,0 +1,75 @@ +From 4a202b0bfd1b2f3509361e5d3f6040f7af90c2ec Mon Sep 17 00:00:00 2001 +From: Julia Lawall <Julia.Lawall@inria.fr> +Date: Tue, 27 Jun 2023 16:43:37 +0200 +Subject: [PATCH 25/30] net: mana: use vmalloc_array and vcalloc + +Use vmalloc_array and vcalloc to protect against +multiplication overflows. + +The changes were done using the following Coccinelle +semantic patch: + +// <smpl> +@initialize:ocaml@ +@@ + +let rename alloc = + match alloc with + "vmalloc" -> "vmalloc_array" + | "vzalloc" -> "vcalloc" + | _ -> failwith "unknown" + +@@ + size_t e1,e2; + constant C1, C2; + expression E1, E2, COUNT, x1, x2, x3; + typedef u8; + typedef __u8; + type t = {u8,__u8,char,unsigned char}; + identifier alloc = {vmalloc,vzalloc}; + fresh identifier realloc = script:ocaml(alloc) { rename alloc }; +@@ + +( + alloc(x1*x2*x3) +| + alloc(C1 * C2) +| + alloc((sizeof(t)) * (COUNT), ...) +| +- alloc((e1) * (e2)) ++ realloc(e1, e2) +| +- alloc((e1) * (COUNT)) ++ realloc(COUNT, e1) +| +- alloc((E1) * (E2)) ++ realloc(E1, E2) +) +// </smpl> + +Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr> +Link: https://lore.kernel.org/r/20230627144339.144478-23-Julia.Lawall@inria.fr +Signed-off-by: Jakub Kicinski <kuba@kernel.org> +(cherry picked from commit e9c74f8b8a31f77f8e9d7bbed5fc9f2eacbf32a5) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/hw_channel.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c +index 9d1507eba5b9..2bd1d74021f7 100644 +--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c ++++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c +@@ -627,7 +627,7 @@ static int mana_hwc_establish_channel(struct gdma_context *gc, u16 *q_depth, + if (WARN_ON(cq->id >= gc->max_num_cqs)) + return -EPROTO; + +- gc->cq_table = vzalloc(gc->max_num_cqs * sizeof(struct gdma_queue *)); ++ gc->cq_table = vcalloc(gc->max_num_cqs, sizeof(struct gdma_queue *)); + if (!gc->cq_table) + return -ENOMEM; + +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0026-net-mana-Batch-ringing-RX-queue-doorbell-on-receivin.patch b/debian/patches/features/all/ethernet-microsoft/0026-net-mana-Batch-ringing-RX-queue-doorbell-on-receivin.patch new file mode 100644 index 000000000..6f03091cd --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0026-net-mana-Batch-ringing-RX-queue-doorbell-on-receivin.patch @@ -0,0 +1,62 @@ +From ad96bbb0b221f0cc22fba13a28234636bf7fb9f5 Mon Sep 17 00:00:00 2001 +From: Long Li <longli@microsoft.com> +Date: Mon, 17 Jul 2023 12:35:38 -0700 +Subject: [PATCH 26/30] net: mana: Batch ringing RX queue doorbell on receiving + packets + +It's inefficient to ring the doorbell page every time a WQE is posted to +the received queue. Excessive MMIO writes result in CPU spending more +time waiting on LOCK instructions (atomic operations), resulting in +poor scaling performance. + +Move the code for ringing doorbell page to where after we have posted all +WQEs to the receive queue during a callback from napi_poll(). + +With this change, tests showed an improvement from 120G/s to 160G/s on a +200G physical link, with 16 or 32 hardware queues. + +Tests showed no regression in network latency benchmarks on single +connection. + +Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> +Reviewed-by: Dexuan Cui <decui@microsoft.com> +Signed-off-by: Long Li <longli@microsoft.com> +Link: https://lore.kernel.org/r/1689622539-5334-2-git-send-email-longli@linuxonhyperv.com +Signed-off-by: Jakub Kicinski <kuba@kernel.org> +(cherry picked from commit da4e8648079eb6f26f3a88d8c34270a057e2bfe6) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana_en.c | 10 ++++++++-- + 1 file changed, 8 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index 7d82b8949a1e..75c1f81ce64f 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -1387,8 +1387,8 @@ static void mana_post_pkt_rxq(struct mana_rxq *rxq) + + recv_buf_oob = &rxq->rx_oobs[curr_index]; + +- err = mana_gd_post_and_ring(rxq->gdma_rq, &recv_buf_oob->wqe_req, +- &recv_buf_oob->wqe_inf); ++ err = mana_gd_post_work_request(rxq->gdma_rq, &recv_buf_oob->wqe_req, ++ &recv_buf_oob->wqe_inf); + if (WARN_ON_ONCE(err)) + return; + +@@ -1660,6 +1660,12 @@ static void mana_poll_rx_cq(struct mana_cq *cq) + mana_process_rx_cqe(rxq, cq, &comp[i]); + } + ++ if (comp_read > 0) { ++ struct gdma_context *gc = rxq->gdma_rq->gdma_dev->gdma_context; ++ ++ mana_gd_wq_ring_doorbell(gc, rxq->gdma_rq); ++ } ++ + if (rxq->xdp_flush) + xdp_do_flush(); + } +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0027-net-mana-Use-the-correct-WQE-count-for-ringing-RQ-do.patch b/debian/patches/features/all/ethernet-microsoft/0027-net-mana-Use-the-correct-WQE-count-for-ringing-RQ-do.patch new file mode 100644 index 000000000..d0bb113fc --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0027-net-mana-Use-the-correct-WQE-count-for-ringing-RQ-do.patch @@ -0,0 +1,41 @@ +From ac7f97738c05e80f7de5e4ccbbf1ea82fdad956c Mon Sep 17 00:00:00 2001 +From: Long Li <longli@microsoft.com> +Date: Mon, 17 Jul 2023 12:35:39 -0700 +Subject: [PATCH 27/30] net: mana: Use the correct WQE count for ringing RQ + doorbell + +The hardware specification specifies that WQE_COUNT should set to 0 for +the Receive Queue. Although currently the hardware doesn't enforce the +check, in the future releases it may check on this value. + +Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> +Reviewed-by: Dexuan Cui <decui@microsoft.com> +Signed-off-by: Long Li <longli@microsoft.com> +Link: https://lore.kernel.org/r/1689622539-5334-3-git-send-email-longli@linuxonhyperv.com +Signed-off-by: Jakub Kicinski <kuba@kernel.org> +(cherry picked from commit f5e39b57124fd4715d7f0e2f841b8609b38f3e40) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/gdma_main.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c +index 97a1845c676a..6108a481edcb 100644 +--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c ++++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c +@@ -300,8 +300,11 @@ static void mana_gd_ring_doorbell(struct gdma_context *gc, u32 db_index, + + void mana_gd_wq_ring_doorbell(struct gdma_context *gc, struct gdma_queue *queue) + { ++ /* Hardware Spec specifies that software client should set 0 for ++ * wqe_cnt for Receive Queues. This value is not used in Send Queues. ++ */ + mana_gd_ring_doorbell(gc, queue->gdma_dev->doorbell, queue->type, +- queue->id, queue->head * GDMA_WQE_BU_SIZE, 1); ++ queue->id, queue->head * GDMA_WQE_BU_SIZE, 0); + } + + void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit) +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0028-net-mana-Configure-hwc-timeout-from-hardware.patch b/debian/patches/features/all/ethernet-microsoft/0028-net-mana-Configure-hwc-timeout-from-hardware.patch new file mode 100644 index 000000000..b5c24df16 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0028-net-mana-Configure-hwc-timeout-from-hardware.patch @@ -0,0 +1,217 @@ +From 4c91517cbcdd16c2a9aee0e21066f2f1aa193ece Mon Sep 17 00:00:00 2001 +From: Souradeep Chakrabarti <schakrabarti@linux.microsoft.com> +Date: Wed, 2 Aug 2023 04:07:40 -0700 +Subject: [PATCH 28/30] net: mana: Configure hwc timeout from hardware + +At present hwc timeout value is a fixed value. This patch sets the hwc +timeout from the hardware. It now uses a new hardware capability +GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG to query and set the value +in hwc_timeout. + +Signed-off-by: Souradeep Chakrabarti <schakrabarti@linux.microsoft.com> +Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com> +Signed-off-by: David S. Miller <davem@davemloft.net> +(cherry picked from commit 62c1bff593b7e30041d0273b835af9fd6f5ee737) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + .../net/ethernet/microsoft/mana/gdma_main.c | 30 ++++++++++++++++++- + .../net/ethernet/microsoft/mana/hw_channel.c | 24 ++++++++++++++- + include/net/mana/gdma.h | 20 ++++++++++++- + include/net/mana/hw_channel.h | 5 ++++ + 4 files changed, 76 insertions(+), 3 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c +index 6108a481edcb..4fa1901a2789 100644 +--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c ++++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c +@@ -106,6 +106,25 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev) + return 0; + } + ++static int mana_gd_query_hwc_timeout(struct pci_dev *pdev, u32 *timeout_val) ++{ ++ struct gdma_context *gc = pci_get_drvdata(pdev); ++ struct gdma_query_hwc_timeout_resp resp = {}; ++ struct gdma_query_hwc_timeout_req req = {}; ++ int err; ++ ++ mana_gd_init_req_hdr(&req.hdr, GDMA_QUERY_HWC_TIMEOUT, ++ sizeof(req), sizeof(resp)); ++ req.timeout_ms = *timeout_val; ++ err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp); ++ if (err || resp.hdr.status) ++ return err ? err : -EPROTO; ++ ++ *timeout_val = resp.timeout_ms; ++ ++ return 0; ++} ++ + static int mana_gd_detect_devices(struct pci_dev *pdev) + { + struct gdma_context *gc = pci_get_drvdata(pdev); +@@ -883,8 +902,10 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev) + struct gdma_context *gc = pci_get_drvdata(pdev); + struct gdma_verify_ver_resp resp = {}; + struct gdma_verify_ver_req req = {}; ++ struct hw_channel_context *hwc; + int err; + ++ hwc = gc->hwc.driver_data; + mana_gd_init_req_hdr(&req.hdr, GDMA_VERIFY_VF_DRIVER_VERSION, + sizeof(req), sizeof(resp)); + +@@ -911,7 +932,14 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev) + err, resp.hdr.status); + return err ? err : -EPROTO; + } +- ++ if (resp.pf_cap_flags1 & GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG) { ++ err = mana_gd_query_hwc_timeout(pdev, &hwc->hwc_timeout); ++ if (err) { ++ dev_err(gc->dev, "Failed to set the hwc timeout %d\n", err); ++ return err; ++ } ++ dev_dbg(gc->dev, "set the hwc timeout to %u\n", hwc->hwc_timeout); ++ } + return 0; + } + +diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c +index 2bd1d74021f7..9d1cd3bfcf66 100644 +--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c ++++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c +@@ -174,7 +174,25 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self, + complete(&hwc->hwc_init_eqe_comp); + break; + ++ case GDMA_EQE_HWC_SOC_RECONFIG_DATA: ++ type_data.as_uint32 = event->details[0]; ++ type = type_data.type; ++ val = type_data.value; ++ ++ switch (type) { ++ case HWC_DATA_CFG_HWC_TIMEOUT: ++ hwc->hwc_timeout = val; ++ break; ++ ++ default: ++ dev_warn(hwc->dev, "Received unknown reconfig type %u\n", type); ++ break; ++ } ++ ++ break; ++ + default: ++ dev_warn(hwc->dev, "Received unknown gdma event %u\n", event->type); + /* Ignore unknown events, which should never happen. */ + break; + } +@@ -696,6 +714,7 @@ int mana_hwc_create_channel(struct gdma_context *gc) + gd->driver_data = hwc; + hwc->gdma_dev = gd; + hwc->dev = gc->dev; ++ hwc->hwc_timeout = HW_CHANNEL_WAIT_RESOURCE_TIMEOUT_MS; + + /* HWC's instance number is always 0. */ + gd->dev_id.as_uint32 = 0; +@@ -770,6 +789,8 @@ void mana_hwc_destroy_channel(struct gdma_context *gc) + hwc->gdma_dev->doorbell = INVALID_DOORBELL; + hwc->gdma_dev->pdid = INVALID_PDID; + ++ hwc->hwc_timeout = 0; ++ + kfree(hwc); + gc->hwc.driver_data = NULL; + gc->hwc.gdma_context = NULL; +@@ -825,7 +846,8 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, + goto out; + } + +- if (!wait_for_completion_timeout(&ctx->comp_event, 30 * HZ)) { ++ if (!wait_for_completion_timeout(&ctx->comp_event, ++ (msecs_to_jiffies(hwc->hwc_timeout) * HZ))) { + dev_err(hwc->dev, "HWC: Request timed out!\n"); + err = -ETIMEDOUT; + goto out; +diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h +index b27bf852471b..102bb73c7a4f 100644 +--- a/include/net/mana/gdma.h ++++ b/include/net/mana/gdma.h +@@ -31,6 +31,7 @@ enum gdma_request_type { + GDMA_DESTROY_PD = 30, + GDMA_CREATE_MR = 31, + GDMA_DESTROY_MR = 32, ++ GDMA_QUERY_HWC_TIMEOUT = 84, /* 0x54 */ + }; + + enum gdma_queue_type { +@@ -53,6 +54,8 @@ enum gdma_eqe_type { + GDMA_EQE_HWC_INIT_EQ_ID_DB = 129, + GDMA_EQE_HWC_INIT_DATA = 130, + GDMA_EQE_HWC_INIT_DONE = 131, ++ GDMA_EQE_HWC_SOC_RECONFIG = 132, ++ GDMA_EQE_HWC_SOC_RECONFIG_DATA = 133, + }; + + enum { +@@ -529,10 +532,12 @@ enum { + * so the driver is able to reliably support features like busy_poll. + */ + #define GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX BIT(2) ++#define GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG BIT(3) + + #define GDMA_DRV_CAP_FLAGS1 \ + (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ +- GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX) ++ GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \ ++ GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG) + + #define GDMA_DRV_CAP_FLAGS2 0 + +@@ -642,6 +647,19 @@ struct gdma_disable_queue_req { + u32 alloc_res_id_on_creation; + }; /* HW DATA */ + ++/* GDMA_QUERY_HWC_TIMEOUT */ ++struct gdma_query_hwc_timeout_req { ++ struct gdma_req_hdr hdr; ++ u32 timeout_ms; ++ u32 reserved; ++}; ++ ++struct gdma_query_hwc_timeout_resp { ++ struct gdma_resp_hdr hdr; ++ u32 timeout_ms; ++ u32 reserved; ++}; ++ + enum atb_page_size { + ATB_PAGE_SIZE_4K, + ATB_PAGE_SIZE_8K, +diff --git a/include/net/mana/hw_channel.h b/include/net/mana/hw_channel.h +index 6a757a6e2732..3d3b5c881bc1 100644 +--- a/include/net/mana/hw_channel.h ++++ b/include/net/mana/hw_channel.h +@@ -23,6 +23,10 @@ + #define HWC_INIT_DATA_PF_DEST_RQ_ID 10 + #define HWC_INIT_DATA_PF_DEST_CQ_ID 11 + ++#define HWC_DATA_CFG_HWC_TIMEOUT 1 ++ ++#define HW_CHANNEL_WAIT_RESOURCE_TIMEOUT_MS 30000 ++ + /* Structures labeled with "HW DATA" are exchanged with the hardware. All of + * them are naturally aligned and hence don't need __packed. + */ +@@ -182,6 +186,7 @@ struct hw_channel_context { + + u32 pf_dest_vrq_id; + u32 pf_dest_vrcq_id; ++ u32 hwc_timeout; + + struct hwc_caller_ctx *caller_ctx; + }; +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0029-net-mana-Rename-mana_refill_rxoob-and-remove-some-em.patch b/debian/patches/features/all/ethernet-microsoft/0029-net-mana-Rename-mana_refill_rxoob-and-remove-some-em.patch new file mode 100644 index 000000000..a9f8249bd --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0029-net-mana-Rename-mana_refill_rxoob-and-remove-some-em.patch @@ -0,0 +1,67 @@ +From 609fba0ab4ebdde830c8c52ef0dcc2ea8f5e82fe Mon Sep 17 00:00:00 2001 +From: Haiyang Zhang <haiyangz@microsoft.com> +Date: Fri, 21 Apr 2023 10:06:57 -0700 +Subject: [PATCH 29/30] net: mana: Rename mana_refill_rxoob and remove some + empty lines + +Rename mana_refill_rxoob for naming consistency. +And remove some empty lines between function call and error +checking. + +Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> +Signed-off-by: Jakub Kicinski <kuba@kernel.org> +(cherry picked from commit 5c74064f43c291d9add2b436a2d70205b71a7cc7) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana_en.c | 9 +++------ + 1 file changed, 3 insertions(+), 6 deletions(-) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index 75c1f81ce64f..6aa273b68327 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -579,7 +579,6 @@ static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu) + + da = dma_map_single(dev, va + mpc->rxbpre_headroom, + mpc->rxbpre_datasize, DMA_FROM_DEVICE); +- + if (dma_mapping_error(dev, da)) { + put_page(virt_to_head_page(va)); + goto error; +@@ -1543,7 +1542,6 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, + + *da = dma_map_single(dev, va + rxq->headroom, rxq->datasize, + DMA_FROM_DEVICE); +- + if (dma_mapping_error(dev, *da)) { + put_page(virt_to_head_page(va)); + return NULL; +@@ -1553,14 +1551,13 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, + } + + /* Allocate frag for rx buffer, and save the old buf */ +-static void mana_refill_rxoob(struct device *dev, struct mana_rxq *rxq, +- struct mana_recv_buf_oob *rxoob, void **old_buf) ++static void mana_refill_rx_oob(struct device *dev, struct mana_rxq *rxq, ++ struct mana_recv_buf_oob *rxoob, void **old_buf) + { + dma_addr_t da; + void *va; + + va = mana_get_rxfrag(rxq, dev, &da, true); +- + if (!va) + return; + +@@ -1625,7 +1622,7 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, + rxbuf_oob = &rxq->rx_oobs[curr]; + WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1); + +- mana_refill_rxoob(dev, rxq, rxbuf_oob, &old_buf); ++ mana_refill_rx_oob(dev, rxq, rxbuf_oob, &old_buf); + + /* Unsuccessful refill will have old_buf == NULL. + * In this case, mana_rx_skb() will drop the packet. +-- +2.40.1 + diff --git a/debian/patches/features/all/ethernet-microsoft/0030-net-mana-Add-gdma-stats-to-ethtool-output-for-mana.patch b/debian/patches/features/all/ethernet-microsoft/0030-net-mana-Add-gdma-stats-to-ethtool-output-for-mana.patch new file mode 100644 index 000000000..07caff6a9 --- /dev/null +++ b/debian/patches/features/all/ethernet-microsoft/0030-net-mana-Add-gdma-stats-to-ethtool-output-for-mana.patch @@ -0,0 +1,232 @@ +From b7a5d522d26c84055bcc410b51b8cefc64fcdbca Mon Sep 17 00:00:00 2001 +From: Shradha Gupta <shradhagupta@linux.microsoft.com> +Date: Wed, 9 Aug 2023 21:15:22 -0700 +Subject: [PATCH 30/30] net: mana: Add gdma stats to ethtool output for mana + +Extended performance counter stats in 'ethtool -S <interface>' +for MANA VF to include GDMA tx LSO packets and bytes count. + +Tested-on: Ubuntu22 +Testcases: +1. LISA testcase: +PERF-NETWORK-TCP-THROUGHPUT-MULTICONNECTION-NTTTCP-Synthetic +2. LISA testcase: +PERF-NETWORK-TCP-THROUGHPUT-MULTICONNECTION-NTTTCP-SRIOV +3. Validated the GDMA stat packets and byte counters +Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com> +Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com> +Signed-off-by: David S. Miller <davem@davemloft.net> +(cherry picked from commit ac3899c6229649737b9d5cb86e417c98243883dc) +Signed-off-by: Bastian Blank <waldi@debian.org> +--- + drivers/net/ethernet/microsoft/mana/mana_en.c | 40 +++++++++ + .../ethernet/microsoft/mana/mana_ethtool.c | 15 ++++ + include/net/mana/mana.h | 87 +++++++++++++++++++ + 3 files changed, 142 insertions(+) + +diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c +index 6aa273b68327..a006bd69b26e 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_en.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c +@@ -2234,6 +2234,46 @@ int mana_config_rss(struct mana_port_context *apc, enum TRI_STATE rx, + return 0; + } + ++void mana_query_gf_stats(struct mana_port_context *apc) ++{ ++ struct mana_query_gf_stat_resp resp = {}; ++ struct mana_query_gf_stat_req req = {}; ++ struct net_device *ndev = apc->ndev; ++ int err; ++ ++ mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_GF_STAT, ++ sizeof(req), sizeof(resp)); ++ req.req_stats = STATISTICS_FLAGS_HC_TX_BYTES | ++ STATISTICS_FLAGS_HC_TX_UCAST_PACKETS | ++ STATISTICS_FLAGS_HC_TX_UCAST_BYTES | ++ STATISTICS_FLAGS_HC_TX_MCAST_PACKETS | ++ STATISTICS_FLAGS_HC_TX_MCAST_BYTES | ++ STATISTICS_FLAGS_HC_TX_BCAST_PACKETS | ++ STATISTICS_FLAGS_HC_TX_BCAST_BYTES; ++ ++ err = mana_send_request(apc->ac, &req, sizeof(req), &resp, ++ sizeof(resp)); ++ if (err) { ++ netdev_err(ndev, "Failed to query GF stats: %d\n", err); ++ return; ++ } ++ err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_GF_STAT, ++ sizeof(resp)); ++ if (err || resp.hdr.status) { ++ netdev_err(ndev, "Failed to query GF stats: %d, 0x%x\n", err, ++ resp.hdr.status); ++ return; ++ } ++ ++ apc->eth_stats.hc_tx_bytes = resp.hc_tx_bytes; ++ apc->eth_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts; ++ apc->eth_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes; ++ apc->eth_stats.hc_tx_bcast_pkts = resp.hc_tx_bcast_pkts; ++ apc->eth_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes; ++ apc->eth_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts; ++ apc->eth_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes; ++} ++ + static int mana_init_port(struct net_device *ndev) + { + struct mana_port_context *apc = netdev_priv(ndev); +diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +index 0dc78679f620..607150165ab4 100644 +--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c ++++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +@@ -13,6 +13,19 @@ static const struct { + } mana_eth_stats[] = { + {"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)}, + {"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)}, ++ {"hc_tx_bytes", offsetof(struct mana_ethtool_stats, hc_tx_bytes)}, ++ {"hc_tx_ucast_pkts", offsetof(struct mana_ethtool_stats, ++ hc_tx_ucast_pkts)}, ++ {"hc_tx_ucast_bytes", offsetof(struct mana_ethtool_stats, ++ hc_tx_ucast_bytes)}, ++ {"hc_tx_bcast_pkts", offsetof(struct mana_ethtool_stats, ++ hc_tx_bcast_pkts)}, ++ {"hc_tx_bcast_bytes", offsetof(struct mana_ethtool_stats, ++ hc_tx_bcast_bytes)}, ++ {"hc_tx_mcast_pkts", offsetof(struct mana_ethtool_stats, ++ hc_tx_mcast_pkts)}, ++ {"hc_tx_mcast_bytes", offsetof(struct mana_ethtool_stats, ++ hc_tx_mcast_bytes)}, + {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, + {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, + tx_cqe_unknown_type)}, +@@ -114,6 +127,8 @@ static void mana_get_ethtool_stats(struct net_device *ndev, + + if (!apc->port_is_up) + return; ++ /* we call mana function to update stats from GDMA */ ++ mana_query_gf_stats(apc); + + for (q = 0; q < ARRAY_SIZE(mana_eth_stats); q++) + data[i++] = *(u64 *)(eth_stats + mana_eth_stats[q].offset); +diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h +index 46b5769a5b6a..cc4502db2ced 100644 +--- a/include/net/mana/mana.h ++++ b/include/net/mana/mana.h +@@ -347,6 +347,13 @@ struct mana_tx_qp { + struct mana_ethtool_stats { + u64 stop_queue; + u64 wake_queue; ++ u64 hc_tx_bytes; ++ u64 hc_tx_ucast_pkts; ++ u64 hc_tx_ucast_bytes; ++ u64 hc_tx_bcast_pkts; ++ u64 hc_tx_bcast_bytes; ++ u64 hc_tx_mcast_pkts; ++ u64 hc_tx_mcast_bytes; + u64 tx_cqe_err; + u64 tx_cqe_unknown_type; + u64 rx_coalesced_err; +@@ -437,6 +444,7 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, + struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); + void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); + int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); ++void mana_query_gf_stats(struct mana_port_context *apc); + + extern const struct ethtool_ops mana_ethtool_ops; + +@@ -575,6 +583,49 @@ struct mana_fence_rq_resp { + struct gdma_resp_hdr hdr; + }; /* HW DATA */ + ++/* Query stats RQ */ ++struct mana_query_gf_stat_req { ++ struct gdma_req_hdr hdr; ++ u64 req_stats; ++}; /* HW DATA */ ++ ++struct mana_query_gf_stat_resp { ++ struct gdma_resp_hdr hdr; ++ u64 reported_stats; ++ /* rx errors/discards */ ++ u64 discard_rx_nowqe; ++ u64 err_rx_vport_disabled; ++ /* rx bytes/packets */ ++ u64 hc_rx_bytes; ++ u64 hc_rx_ucast_pkts; ++ u64 hc_rx_ucast_bytes; ++ u64 hc_rx_bcast_pkts; ++ u64 hc_rx_bcast_bytes; ++ u64 hc_rx_mcast_pkts; ++ u64 hc_rx_mcast_bytes; ++ /* tx errors */ ++ u64 err_tx_gf_disabled; ++ u64 err_tx_vport_disabled; ++ u64 err_tx_inval_vport_offset_pkt; ++ u64 err_tx_vlan_enforcement; ++ u64 err_tx_ethtype_enforcement; ++ u64 err_tx_SA_enforecement; ++ u64 err_tx_SQPDID_enforcement; ++ u64 err_tx_CQPDID_enforcement; ++ u64 err_tx_mtu_violation; ++ u64 err_tx_inval_oob; ++ /* tx bytes/packets */ ++ u64 hc_tx_bytes; ++ u64 hc_tx_ucast_pkts; ++ u64 hc_tx_ucast_bytes; ++ u64 hc_tx_bcast_pkts; ++ u64 hc_tx_bcast_bytes; ++ u64 hc_tx_mcast_pkts; ++ u64 hc_tx_mcast_bytes; ++ /* tx error */ ++ u64 err_tx_gdma; ++}; /* HW DATA */ ++ + /* Configure vPort Rx Steering */ + struct mana_cfg_rx_steer_req_v2 { + struct gdma_req_hdr hdr; +@@ -654,6 +705,42 @@ struct mana_deregister_filter_resp { + struct gdma_resp_hdr hdr; + }; /* HW DATA */ + ++/* Requested GF stats Flags */ ++/* Rx discards/Errors */ ++#define STATISTICS_FLAGS_RX_DISCARDS_NO_WQE 0x0000000000000001 ++#define STATISTICS_FLAGS_RX_ERRORS_VPORT_DISABLED 0x0000000000000002 ++/* Rx bytes/pkts */ ++#define STATISTICS_FLAGS_HC_RX_BYTES 0x0000000000000004 ++#define STATISTICS_FLAGS_HC_RX_UCAST_PACKETS 0x0000000000000008 ++#define STATISTICS_FLAGS_HC_RX_UCAST_BYTES 0x0000000000000010 ++#define STATISTICS_FLAGS_HC_RX_MCAST_PACKETS 0x0000000000000020 ++#define STATISTICS_FLAGS_HC_RX_MCAST_BYTES 0x0000000000000040 ++#define STATISTICS_FLAGS_HC_RX_BCAST_PACKETS 0x0000000000000080 ++#define STATISTICS_FLAGS_HC_RX_BCAST_BYTES 0x0000000000000100 ++/* Tx errors */ ++#define STATISTICS_FLAGS_TX_ERRORS_GF_DISABLED 0x0000000000000200 ++#define STATISTICS_FLAGS_TX_ERRORS_VPORT_DISABLED 0x0000000000000400 ++#define STATISTICS_FLAGS_TX_ERRORS_INVAL_VPORT_OFFSET_PACKETS \ ++ 0x0000000000000800 ++#define STATISTICS_FLAGS_TX_ERRORS_VLAN_ENFORCEMENT 0x0000000000001000 ++#define STATISTICS_FLAGS_TX_ERRORS_ETH_TYPE_ENFORCEMENT \ ++ 0x0000000000002000 ++#define STATISTICS_FLAGS_TX_ERRORS_SA_ENFORCEMENT 0x0000000000004000 ++#define STATISTICS_FLAGS_TX_ERRORS_SQPDID_ENFORCEMENT 0x0000000000008000 ++#define STATISTICS_FLAGS_TX_ERRORS_CQPDID_ENFORCEMENT 0x0000000000010000 ++#define STATISTICS_FLAGS_TX_ERRORS_MTU_VIOLATION 0x0000000000020000 ++#define STATISTICS_FLAGS_TX_ERRORS_INVALID_OOB 0x0000000000040000 ++/* Tx bytes/pkts */ ++#define STATISTICS_FLAGS_HC_TX_BYTES 0x0000000000080000 ++#define STATISTICS_FLAGS_HC_TX_UCAST_PACKETS 0x0000000000100000 ++#define STATISTICS_FLAGS_HC_TX_UCAST_BYTES 0x0000000000200000 ++#define STATISTICS_FLAGS_HC_TX_MCAST_PACKETS 0x0000000000400000 ++#define STATISTICS_FLAGS_HC_TX_MCAST_BYTES 0x0000000000800000 ++#define STATISTICS_FLAGS_HC_TX_BCAST_PACKETS 0x0000000001000000 ++#define STATISTICS_FLAGS_HC_TX_BCAST_BYTES 0x0000000002000000 ++/* Tx error */ ++#define STATISTICS_FLAGS_TX_ERRORS_GDMA_ERROR 0x0000000004000000 ++ + #define MANA_MAX_NUM_QUEUES 64 + + #define MANA_SHORT_VPORT_OFFSET_MAX ((1U << 8) - 1) +-- +2.40.1 + diff --git a/debian/patches/features/all/lockdown/arm64-add-kernel-config-option-to-lock-down-when.patch b/debian/patches/features/all/lockdown/arm64-add-kernel-config-option-to-lock-down-when.patch new file mode 100644 index 000000000..6f1ba8e5a --- /dev/null +++ b/debian/patches/features/all/lockdown/arm64-add-kernel-config-option-to-lock-down-when.patch @@ -0,0 +1,153 @@ +From: Linn Crosetto <linn@hpe.com> +Date: Tue, 30 Aug 2016 11:54:38 -0600 +Subject: arm64: add kernel config option to lock down when in Secure Boot mode +Bug-Debian: https://bugs.debian.org/831827 +Forwarded: no + +Add a kernel configuration option to lock down the kernel, to restrict +userspace's ability to modify the running kernel when UEFI Secure Boot is +enabled. Based on the x86 patch by Matthew Garrett. + +Determine the state of Secure Boot in the EFI stub and pass this to the +kernel using the FDT. + +Signed-off-by: Linn Crosetto <linn@hpe.com> +[bwh: Forward-ported to 4.10: adjust context] +[Lukas Wunner: Forward-ported to 4.11: drop parts applied upstream] +[bwh: Forward-ported to 4.15 and lockdown patch set: + - Pass result of efi_get_secureboot() in stub through to + efi_set_secure_boot() in main kernel + - Use lockdown API and naming] +[bwh: Forward-ported to 4.19.3: adjust context in update_fdt()] +[dannf: Moved init_lockdown() call after uefi_init(), fixing SB detection] +[bwh: Drop call to init_lockdown(), as efi_set_secure_boot() now calls this] +[bwh: Forward-ported to 5.6: efi_get_secureboot() no longer takes a + sys_table parameter] +[bwh: Forward-ported to 5.7: EFI initialisation from FDT was rewritten, so: + - Add Secure Boot mode to the parameter enumeration in fdtparams.c + - Add a parameter to efi_get_fdt_params() to return the Secure Boot mode + - Since Xen does not have a property name defined for Secure Boot mode, + change efi_get_fdt_prop() to handle a missing property name by clearing + the output variable] +[Salvatore Bonaccorso: Forward-ported to 5.10: f30f242fb131 ("efi: Rename +arm-init to efi-init common for all arch") renamed arm-init.c to efi-init.c] +--- + drivers/firmware/efi/efi-init.c | 5 ++++- + drivers/firmware/efi/fdtparams.c | 12 +++++++++++- + drivers/firmware/efi/libstub/fdt.c | 6 ++++++ + include/linux/efi.h | 3 ++- + 4 files changed, 23 insertions(+), 3 deletions(-) + +--- a/drivers/firmware/efi/efi-init.c ++++ b/drivers/firmware/efi/efi-init.c +@@ -210,9 +210,10 @@ void __init efi_init(void) + { + struct efi_memory_map_data data; + u64 efi_system_table; ++ u32 secure_boot; + + /* Grab UEFI information placed in FDT by stub */ +- efi_system_table = efi_get_fdt_params(&data); ++ efi_system_table = efi_get_fdt_params(&data, &secure_boot); + if (!efi_system_table) + return; + +@@ -234,6 +235,8 @@ void __init efi_init(void) + return; + } + ++ efi_set_secure_boot(secure_boot); ++ + reserve_regions(); + /* + * For memblock manipulation, the cap should come after the memblock_add(). +--- a/drivers/firmware/efi/fdtparams.c ++++ b/drivers/firmware/efi/fdtparams.c +@@ -16,6 +16,7 @@ enum { + MMSIZE, + DCSIZE, + DCVERS, ++ SBMODE, + + PARAMCOUNT + }; +@@ -26,6 +27,7 @@ static __initconst const char name[][22] + [MMSIZE] = "MemMap Size ", + [DCSIZE] = "MemMap Desc. Size ", + [DCVERS] = "MemMap Desc. Version ", ++ [SBMODE] = "Secure Boot Enabled ", + }; + + static __initconst const struct { +@@ -41,6 +43,7 @@ static __initconst const struct { + [MMSIZE] = "xen,uefi-mmap-size", + [DCSIZE] = "xen,uefi-mmap-desc-size", + [DCVERS] = "xen,uefi-mmap-desc-ver", ++ [SBMODE] = "", + } + }, { + #endif +@@ -51,6 +54,7 @@ static __initconst const struct { + [MMSIZE] = "linux,uefi-mmap-size", + [DCSIZE] = "linux,uefi-mmap-desc-size", + [DCVERS] = "linux,uefi-mmap-desc-ver", ++ [SBMODE] = "linux,uefi-secure-boot", + } + } + }; +@@ -62,6 +66,11 @@ static int __init efi_get_fdt_prop(const + int len; + u64 val; + ++ if (!pname[0]) { ++ memset(var, 0, size); ++ return 0; ++ } ++ + prop = fdt_getprop(fdt, node, pname, &len); + if (!prop) + return 1; +@@ -79,7 +88,7 @@ static int __init efi_get_fdt_prop(const + return 0; + } + +-u64 __init efi_get_fdt_params(struct efi_memory_map_data *mm) ++u64 __init efi_get_fdt_params(struct efi_memory_map_data *mm, u32 *secure_boot) + { + const void *fdt = initial_boot_params; + unsigned long systab; +@@ -93,6 +102,7 @@ u64 __init efi_get_fdt_params(struct efi + [MMSIZE] = { &mm->size, sizeof(mm->size) }, + [DCSIZE] = { &mm->desc_size, sizeof(mm->desc_size) }, + [DCVERS] = { &mm->desc_version, sizeof(mm->desc_version) }, ++ [SBMODE] = { secure_boot, sizeof(*secure_boot) }, + }; + + BUILD_BUG_ON(ARRAY_SIZE(target) != ARRAY_SIZE(name)); +--- a/drivers/firmware/efi/libstub/fdt.c ++++ b/drivers/firmware/efi/libstub/fdt.c +@@ -148,6 +148,12 @@ static efi_status_t update_fdt(void *ori + } + } + ++ fdt_val32 = cpu_to_fdt32(efi_get_secureboot()); ++ status = fdt_setprop(fdt, node, "linux,uefi-secure-boot", ++ &fdt_val32, sizeof(fdt_val32)); ++ if (status) ++ goto fdt_set_fail; ++ + /* Shrink the FDT back to its minimum size: */ + fdt_pack(fdt); + +--- a/include/linux/efi.h ++++ b/include/linux/efi.h +@@ -662,7 +662,8 @@ extern void efi_mem_reserve(phys_addr_t + extern int efi_mem_reserve_persistent(phys_addr_t addr, u64 size); + extern void efi_initialize_iomem_resources(struct resource *code_resource, + struct resource *data_resource, struct resource *bss_resource); +-extern u64 efi_get_fdt_params(struct efi_memory_map_data *data); ++extern u64 efi_get_fdt_params(struct efi_memory_map_data *data, ++ u32 *secure_boot); + extern struct kobject *efi_kobj; + + extern int efi_reboot_quirk_mode; diff --git a/debian/patches/features/all/lockdown/efi-add-an-efi_secure_boot-flag-to-indicate-secure-b.patch b/debian/patches/features/all/lockdown/efi-add-an-efi_secure_boot-flag-to-indicate-secure-b.patch new file mode 100644 index 000000000..b46698757 --- /dev/null +++ b/debian/patches/features/all/lockdown/efi-add-an-efi_secure_boot-flag-to-indicate-secure-b.patch @@ -0,0 +1,153 @@ +From: David Howells <dhowells@redhat.com> +Date: Mon, 18 Feb 2019 12:45:03 +0000 +Subject: [28/30] efi: Add an EFI_SECURE_BOOT flag to indicate secure boot mode +Origin: https://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs.git/commit?id=a5d70c55c603233c192b375f72116a395909da28 + +UEFI machines can be booted in Secure Boot mode. Add an EFI_SECURE_BOOT +flag that can be passed to efi_enabled() to find out whether secure boot is +enabled. + +Move the switch-statement in x86's setup_arch() that inteprets the +secure_boot boot parameter to generic code and set the bit there. + +Suggested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> +Signed-off-by: David Howells <dhowells@redhat.com> +Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> +cc: linux-efi@vger.kernel.org +[rperier: Forward-ported to 5.5: + - Use pr_warn() + - Adjust context] +[bwh: Forward-ported to 5.6: adjust context] +[bwh: Forward-ported to 5.7: + - Use the next available bit in efi.flags + - Adjust context] +--- + arch/x86/kernel/setup.c | 14 +---------- + drivers/firmware/efi/Makefile | 1 + + drivers/firmware/efi/secureboot.c | 39 +++++++++++++++++++++++++++++++ + include/linux/efi.h | 16 ++++++++----- + 4 files changed, 51 insertions(+), 19 deletions(-) + create mode 100644 drivers/firmware/efi/secureboot.c + +--- a/arch/x86/kernel/setup.c ++++ b/arch/x86/kernel/setup.c +@@ -1205,19 +1205,7 @@ void __init setup_arch(char **cmdline_p) + /* Allocate bigger log buffer */ + setup_log_buf(1); + +- if (efi_enabled(EFI_BOOT)) { +- switch (boot_params.secure_boot) { +- case efi_secureboot_mode_disabled: +- pr_info("Secure boot disabled\n"); +- break; +- case efi_secureboot_mode_enabled: +- pr_info("Secure boot enabled\n"); +- break; +- default: +- pr_info("Secure boot could not be determined\n"); +- break; +- } +- } ++ efi_set_secure_boot(boot_params.secure_boot); + + reserve_initrd(); + +--- a/drivers/firmware/efi/Makefile ++++ b/drivers/firmware/efi/Makefile +@@ -27,6 +27,7 @@ obj-$(CONFIG_EFI_FAKE_MEMMAP) += fake_m + obj-$(CONFIG_EFI_BOOTLOADER_CONTROL) += efibc.o + obj-$(CONFIG_EFI_TEST) += test/ + obj-$(CONFIG_EFI_DEV_PATH_PARSER) += dev-path-parser.o ++obj-$(CONFIG_EFI) += secureboot.o + obj-$(CONFIG_APPLE_PROPERTIES) += apple-properties.o + obj-$(CONFIG_EFI_RCI2_TABLE) += rci2-table.o + obj-$(CONFIG_EFI_EMBEDDED_FIRMWARE) += embedded-firmware.o +--- /dev/null ++++ b/drivers/firmware/efi/secureboot.c +@@ -0,0 +1,39 @@ ++ ++/* Core kernel secure boot support. ++ * ++ * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. ++ * Written by David Howells (dhowells@redhat.com) ++ * ++ * This program is free software; you can redistribute it and/or ++ * modify it under the terms of the GNU General Public Licence ++ * as published by the Free Software Foundation; either version ++ * 2 of the Licence, or (at your option) any later version. ++ */ ++ ++#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt ++ ++#include <linux/efi.h> ++#include <linux/kernel.h> ++#include <linux/printk.h> ++ ++/* ++ * Decide what to do when UEFI secure boot mode is enabled. ++ */ ++void __init efi_set_secure_boot(enum efi_secureboot_mode mode) ++{ ++ if (efi_enabled(EFI_BOOT)) { ++ switch (mode) { ++ case efi_secureboot_mode_disabled: ++ pr_info("Secure boot disabled\n"); ++ break; ++ case efi_secureboot_mode_enabled: ++ set_bit(EFI_SECURE_BOOT, &efi.flags); ++ pr_info("Secure boot enabled\n"); ++ break; ++ default: ++ pr_warn("Secure boot could not be determined (mode %u)\n", ++ mode); ++ break; ++ } ++ } ++} +--- a/include/linux/efi.h ++++ b/include/linux/efi.h +@@ -849,6 +849,14 @@ extern int __init efi_setup_pcdp_console + #define EFI_MEM_ATTR 10 /* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */ + #define EFI_MEM_NO_SOFT_RESERVE 11 /* Is the kernel configured to ignore soft reservations? */ + #define EFI_PRESERVE_BS_REGIONS 12 /* Are EFI boot-services memory segments available? */ ++#define EFI_SECURE_BOOT 13 /* Are we in Secure Boot mode? */ ++ ++enum efi_secureboot_mode { ++ efi_secureboot_mode_unset, ++ efi_secureboot_mode_unknown, ++ efi_secureboot_mode_disabled, ++ efi_secureboot_mode_enabled, ++}; + + #ifdef CONFIG_EFI + /* +@@ -873,6 +881,7 @@ static inline bool efi_rt_services_suppo + return (efi.runtime_supported_mask & mask) == mask; + } + extern void efi_find_mirror(void); ++extern void __init efi_set_secure_boot(enum efi_secureboot_mode mode); + #else + static inline bool efi_enabled(int feature) + { +@@ -892,6 +901,7 @@ static inline bool efi_rt_services_suppo + } + + static inline void efi_find_mirror(void) {} ++static inline void efi_set_secure_boot(enum efi_secureboot_mode mode) {} + #endif + + extern int efi_status_to_err(efi_status_t status); +@@ -1107,13 +1117,6 @@ static inline bool efi_runtime_disabled( + extern void efi_call_virt_check_flags(unsigned long flags, const char *call); + extern unsigned long efi_call_virt_save_flags(void); + +-enum efi_secureboot_mode { +- efi_secureboot_mode_unset, +- efi_secureboot_mode_unknown, +- efi_secureboot_mode_disabled, +- efi_secureboot_mode_enabled, +-}; +- + static inline + enum efi_secureboot_mode efi_get_secureboot_mode(efi_get_variable_t *get_var) + { diff --git a/debian/patches/features/all/lockdown/efi-lock-down-the-kernel-if-booted-in-secure-boot-mo.patch b/debian/patches/features/all/lockdown/efi-lock-down-the-kernel-if-booted-in-secure-boot-mo.patch new file mode 100644 index 000000000..9ec425871 --- /dev/null +++ b/debian/patches/features/all/lockdown/efi-lock-down-the-kernel-if-booted-in-secure-boot-mo.patch @@ -0,0 +1,131 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Tue, 10 Sep 2019 11:54:28 +0100 +Subject: efi: Lock down the kernel if booted in secure boot mode + +Based on an earlier patch by David Howells, who wrote the following +description: + +> UEFI Secure Boot provides a mechanism for ensuring that the firmware will +> only load signed bootloaders and kernels. Certain use cases may also +> require that all kernel modules also be signed. Add a configuration option +> that to lock down the kernel - which includes requiring validly signed +> modules - if the kernel is secure-booted. + +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +[Salvatore Bonaccorso: After fixing https://bugs.debian.org/956197 the +help text for LOCK_DOWN_IN_EFI_SECURE_BOOT needs to be adjusted to +mention that lockdown is triggered in integrity mode] +Signed-off-by: Salvatore Bonaccorso <carnil@debian.org> +--- + arch/x86/kernel/setup.c | 4 ++-- + drivers/firmware/efi/secureboot.c | 3 +++ + include/linux/security.h | 6 ++++++ + security/lockdown/Kconfig | 15 +++++++++++++++ + security/lockdown/lockdown.c | 2 +- + 5 files changed, 27 insertions(+), 3 deletions(-) + +Index: debian-kernel/arch/x86/kernel/setup.c +=================================================================== +--- debian-kernel.orig/arch/x86/kernel/setup.c ++++ debian-kernel/arch/x86/kernel/setup.c +@@ -979,6 +979,8 @@ void __init setup_arch(char **cmdline_p) + if (efi_enabled(EFI_BOOT)) + efi_init(); + ++ efi_set_secure_boot(boot_params.secure_boot); ++ + dmi_setup(); + + /* +@@ -1130,8 +1132,6 @@ void __init setup_arch(char **cmdline_p) + /* Allocate bigger log buffer */ + setup_log_buf(1); + +- efi_set_secure_boot(boot_params.secure_boot); +- + reserve_initrd(); + + acpi_table_upgrade(); +Index: debian-kernel/drivers/firmware/efi/secureboot.c +=================================================================== +--- debian-kernel.orig/drivers/firmware/efi/secureboot.c ++++ debian-kernel/drivers/firmware/efi/secureboot.c +@@ -15,6 +15,7 @@ + #include <linux/efi.h> + #include <linux/kernel.h> + #include <linux/printk.h> ++#include <linux/security.h> + + /* + * Decide what to do when UEFI secure boot mode is enabled. +@@ -28,6 +29,10 @@ void __init efi_set_secure_boot(enum efi + break; + case efi_secureboot_mode_enabled: + set_bit(EFI_SECURE_BOOT, &efi.flags); ++#ifdef CONFIG_LOCK_DOWN_IN_EFI_SECURE_BOOT ++ lock_kernel_down("EFI Secure Boot", ++ LOCKDOWN_INTEGRITY_MAX); ++#endif + pr_info("Secure boot enabled\n"); + break; + default: +Index: debian-kernel/include/linux/security.h +=================================================================== +--- debian-kernel.orig/include/linux/security.h ++++ debian-kernel/include/linux/security.h +@@ -451,6 +451,7 @@ int security_inode_notifysecctx(struct i + int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen); + int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen); + int security_locked_down(enum lockdown_reason what); ++int lock_kernel_down(const char *where, enum lockdown_reason level); + #else /* CONFIG_SECURITY */ + + static inline int call_blocking_lsm_notifier(enum lsm_event event, void *data) +@@ -1291,6 +1292,11 @@ static inline int security_locked_down(e + { + return 0; + } ++static inline int ++lock_kernel_down(const char *where, enum lockdown_reason level) ++{ ++ return -EOPNOTSUPP; ++} + #endif /* CONFIG_SECURITY */ + + #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE) +Index: debian-kernel/security/lockdown/Kconfig +=================================================================== +--- debian-kernel.orig/security/lockdown/Kconfig ++++ debian-kernel/security/lockdown/Kconfig +@@ -45,3 +45,18 @@ config LOCK_DOWN_KERNEL_FORCE_CONFIDENTI + disabled. + + endchoice ++ ++config LOCK_DOWN_IN_EFI_SECURE_BOOT ++ bool "Lock down the kernel in EFI Secure Boot mode" ++ default n ++ depends on SECURITY_LOCKDOWN_LSM ++ depends on EFI ++ select SECURITY_LOCKDOWN_LSM_EARLY ++ help ++ UEFI Secure Boot provides a mechanism for ensuring that the firmware ++ will only load signed bootloaders and kernels. Secure boot mode may ++ be determined from EFI variables provided by the system firmware if ++ not indicated by the boot parameters. ++ ++ Enabling this option results in kernel lockdown being ++ triggered in integrity mode if EFI Secure Boot is set. +Index: debian-kernel/security/lockdown/lockdown.c +=================================================================== +--- debian-kernel.orig/security/lockdown/lockdown.c ++++ debian-kernel/security/lockdown/lockdown.c +@@ -23,7 +23,7 @@ static const enum lockdown_reason lockdo + /* + * Put the kernel into lock-down mode. + */ +-static int lock_kernel_down(const char *where, enum lockdown_reason level) ++int lock_kernel_down(const char *where, enum lockdown_reason level) + { + if (kernel_locked_down >= level) + return -EPERM; diff --git a/debian/patches/features/all/lockdown/mtd-disable-slram-and-phram-when-locked-down.patch b/debian/patches/features/all/lockdown/mtd-disable-slram-and-phram-when-locked-down.patch new file mode 100644 index 000000000..c718e7e2f --- /dev/null +++ b/debian/patches/features/all/lockdown/mtd-disable-slram-and-phram-when-locked-down.patch @@ -0,0 +1,75 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Fri, 30 Aug 2019 15:54:24 +0100 +Subject: mtd: phram,slram: Disable when the kernel is locked down +Forwarded: https://lore.kernel.org/linux-security-module/20190830154720.eekfjt6c4jzvlbfz@decadent.org.uk/ + +These drivers allow mapping arbitrary memory ranges as MTD devices. +This should be disabled to preserve the kernel's integrity when it is +locked down. + +* Add the HWPARAM flag to the module parameters +* When slram is built-in, it uses __setup() to read kernel parameters, + so add an explicit check security_locked_down() check + +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +Cc: Matthew Garrett <mjg59@google.com> +Cc: David Howells <dhowells@redhat.com> +Cc: Joern Engel <joern@lazybastard.org> +Cc: linux-mtd@lists.infradead.org +--- + drivers/mtd/devices/phram.c | 6 +++++- + drivers/mtd/devices/slram.c | 9 ++++++++- + 2 files changed, 13 insertions(+), 2 deletions(-) + +--- a/drivers/mtd/devices/phram.c ++++ b/drivers/mtd/devices/phram.c +@@ -364,7 +364,11 @@ static int phram_param_call(const char * + #endif + } + +-module_param_call(phram, phram_param_call, NULL, NULL, 0200); ++static const struct kernel_param_ops phram_param_ops = { ++ .set = phram_param_call ++}; ++__module_param_call(MODULE_PARAM_PREFIX, phram, &phram_param_ops, NULL, ++ 0200, -1, KERNEL_PARAM_FL_HWPARAM | hwparam_iomem); + MODULE_PARM_DESC(phram, "Memory region to map. \"phram=<name>,<start>,<length>[,<erasesize>]\""); + + #ifdef CONFIG_OF +--- a/drivers/mtd/devices/slram.c ++++ b/drivers/mtd/devices/slram.c +@@ -43,6 +43,7 @@ + #include <linux/ioctl.h> + #include <linux/init.h> + #include <linux/io.h> ++#include <linux/security.h> + + #include <linux/mtd/mtd.h> + +@@ -65,7 +66,7 @@ typedef struct slram_mtd_list { + #ifdef MODULE + static char *map[SLRAM_MAX_DEVICES_PARAMS]; + +-module_param_array(map, charp, NULL, 0); ++module_param_hw_array(map, charp, iomem, NULL, 0); + MODULE_PARM_DESC(map, "List of memory regions to map. \"map=<name>, <start>, <length / end>\""); + #else + static char *map; +@@ -281,11 +282,17 @@ static int __init init_slram(void) + #ifndef MODULE + char *devstart; + char *devlength; ++ int ret; + + if (!map) { + E("slram: not enough parameters.\n"); + return(-EINVAL); + } ++ ++ ret = security_locked_down(LOCKDOWN_MODULE_PARAMETERS); ++ if (ret) ++ return ret; ++ + while (map) { + devname = devstart = devlength = NULL; + diff --git a/debian/patches/features/all/security-perf-allow-further-restriction-of-perf_event_open.patch b/debian/patches/features/all/security-perf-allow-further-restriction-of-perf_event_open.patch new file mode 100644 index 000000000..e58668ebe --- /dev/null +++ b/debian/patches/features/all/security-perf-allow-further-restriction-of-perf_event_open.patch @@ -0,0 +1,80 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Mon, 11 Jan 2016 15:23:55 +0000 +Subject: security,perf: Allow further restriction of perf_event_open +Forwarded: https://lkml.org/lkml/2016/1/11/587 + +When kernel.perf_event_open is set to 3 (or greater), disallow all +access to performance events by users without CAP_SYS_ADMIN. +Add a Kconfig symbol CONFIG_SECURITY_PERF_EVENTS_RESTRICT that +makes this value the default. + +This is based on a similar feature in grsecurity +(CONFIG_GRKERNSEC_PERF_HARDEN). This version doesn't include making +the variable read-only. It also allows enabling further restriction +at run-time regardless of whether the default is changed. + +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- + include/linux/perf_event.h | 5 +++++ + kernel/events/core.c | 8 ++++++++ + security/Kconfig | 9 +++++++++ + 3 files changed, 22 insertions(+) + +--- a/include/linux/perf_event.h ++++ b/include/linux/perf_event.h +@@ -1387,6 +1387,11 @@ int perf_cpu_time_max_percent_handler(st + int perf_event_max_stack_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); + ++static inline bool perf_paranoid_any(void) ++{ ++ return sysctl_perf_event_paranoid > 2; ++} ++ + /* Access to perf_event_open(2) syscall. */ + #define PERF_SECURITY_OPEN 0 + +--- a/kernel/events/core.c ++++ b/kernel/events/core.c +@@ -415,8 +415,13 @@ static struct kmem_cache *perf_event_cac + * 0 - disallow raw tracepoint access for unpriv + * 1 - disallow cpu events for unpriv + * 2 - disallow kernel profiling for unpriv ++ * 3 - disallow all unpriv perf event use + */ ++#ifdef CONFIG_SECURITY_PERF_EVENTS_RESTRICT ++int sysctl_perf_event_paranoid __read_mostly = 3; ++#else + int sysctl_perf_event_paranoid __read_mostly = 2; ++#endif + + /* Minimum for 512 kiB + 1 user control page */ + int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */ +@@ -12235,6 +12240,9 @@ SYSCALL_DEFINE5(perf_event_open, + if (err) + return err; + ++ if (perf_paranoid_any() && !capable(CAP_SYS_ADMIN)) ++ return -EACCES; ++ + /* Do we allow access to perf_event_open(2) ? */ + err = security_perf_event_open(&attr, PERF_SECURITY_OPEN); + if (err) +--- a/security/Kconfig ++++ b/security/Kconfig +@@ -19,6 +19,15 @@ config SECURITY_DMESG_RESTRICT + + If you are unsure how to answer this question, answer N. + ++config SECURITY_PERF_EVENTS_RESTRICT ++ bool "Restrict unprivileged use of performance events" ++ depends on PERF_EVENTS ++ help ++ If you say Y here, the kernel.perf_event_paranoid sysctl ++ will be set to 3 by default, and no unprivileged use of the ++ perf_event_open syscall will be permitted unless it is ++ changed. ++ + config SECURITY + bool "Enable different security models" + depends on SYSFS diff --git a/debian/patches/features/arm64/arm64-dts-rockchip-Add-Hardkernel-ODROID-M1-board.patch b/debian/patches/features/arm64/arm64-dts-rockchip-Add-Hardkernel-ODROID-M1-board.patch new file mode 100644 index 000000000..18b3218ee --- /dev/null +++ b/debian/patches/features/arm64/arm64-dts-rockchip-Add-Hardkernel-ODROID-M1-board.patch @@ -0,0 +1,454 @@ +From: Dongjin Kim <tobetter@gmail.com> +Date: Fri, 30 Sep 2022 07:12:35 +0200 +Subject: [02/13] arm64: dts: rockchip: Add Hardkernel ODROID-M1 board +Origin: https://git.kernel.org/linus/fd35832677032980df230f02509d6c016664cc89 + +This patch is to add a device tree for new board Hardkernel ODROID-M1 +based on Rockchip RK3568, includes basic peripherals - +uart/eMMC/uSD/i2c and on-board ethernet. + +Signed-off-by: Dongjin Kim <tobetter@gmail.com> +[aurelien@aurel32.net: addressed issues from initial review] +Signed-off-by: Aurelien Jarno <aurelien@aurel32.net> +Tested-by: Dan Johansen <strit@manjaro.org> +Link: https://lore.kernel.org/r/20220930051246.391614-3-aurelien@aurel32.net +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + arch/arm64/boot/dts/rockchip/Makefile | 1 + + .../boot/dts/rockchip/rk3568-odroid-m1.dts | 414 ++++++++++++++++++ + 2 files changed, 415 insertions(+) + create mode 100644 arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts + +diff --git a/arch/arm64/boot/dts/rockchip/Makefile b/arch/arm64/boot/dts/rockchip/Makefile +index a5a6262936f0..68cc720a623a 100644 +--- a/arch/arm64/boot/dts/rockchip/Makefile ++++ b/arch/arm64/boot/dts/rockchip/Makefile +@@ -72,4 +72,5 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-roc-pc.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-soquartz-cm4.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-bpi-r2-pro.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-evb1-v10.dtb ++dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-odroid-m1.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-rock-3a.dtb +diff --git a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +new file mode 100644 +index 000000000000..b3016437640b +--- /dev/null ++++ b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +@@ -0,0 +1,414 @@ ++// SPDX-License-Identifier: (GPL-2.0+ OR MIT) ++/* ++ * Copyright (c) 2022 Hardkernel Co., Ltd. ++ * ++ */ ++ ++/dts-v1/; ++#include <dt-bindings/gpio/gpio.h> ++#include <dt-bindings/leds/common.h> ++#include <dt-bindings/pinctrl/rockchip.h> ++#include "rk3568.dtsi" ++ ++/ { ++ model = "Hardkernel ODROID-M1"; ++ compatible = "rockchip,rk3568-odroid-m1", "rockchip,rk3568"; ++ ++ aliases { ++ ethernet0 = &gmac0; ++ i2c0 = &i2c3; ++ i2c3 = &i2c0; ++ mmc0 = &sdhci; ++ mmc1 = &sdmmc0; ++ serial0 = &uart1; ++ serial1 = &uart0; ++ }; ++ ++ chosen { ++ stdout-path = "serial2:1500000n8"; ++ }; ++ ++ dc_12v: dc-12v-regulator { ++ compatible = "regulator-fixed"; ++ regulator-name = "dc_12v"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <12000000>; ++ regulator-max-microvolt = <12000000>; ++ }; ++ ++ leds { ++ compatible = "gpio-leds"; ++ ++ led_power: led-0 { ++ gpios = <&gpio0 RK_PC6 GPIO_ACTIVE_HIGH>; ++ function = LED_FUNCTION_POWER; ++ color = <LED_COLOR_ID_RED>; ++ default-state = "keep"; ++ linux,default-trigger = "default-on"; ++ pinctrl-names = "default"; ++ pinctrl-0 = <&led_power_pin>; ++ }; ++ led_work: led-1 { ++ gpios = <&gpio0 RK_PB7 GPIO_ACTIVE_HIGH>; ++ function = LED_FUNCTION_HEARTBEAT; ++ color = <LED_COLOR_ID_BLUE>; ++ linux,default-trigger = "heartbeat"; ++ pinctrl-names = "default"; ++ pinctrl-0 = <&led_work_pin>; ++ }; ++ }; ++ ++ vcc3v3_sys: vcc3v3-sys-regulator { ++ compatible = "regulator-fixed"; ++ regulator-name = "vcc3v3_sys"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <3300000>; ++ regulator-max-microvolt = <3300000>; ++ vin-supply = <&dc_12v>; ++ }; ++}; ++ ++&cpu0 { ++ cpu-supply = <&vdd_cpu>; ++}; ++ ++&cpu1 { ++ cpu-supply = <&vdd_cpu>; ++}; ++ ++&cpu2 { ++ cpu-supply = <&vdd_cpu>; ++}; ++ ++&cpu3 { ++ cpu-supply = <&vdd_cpu>; ++}; ++ ++&gmac0 { ++ assigned-clocks = <&cru SCLK_GMAC0_RX_TX>, <&cru SCLK_GMAC0>; ++ assigned-clock-parents = <&cru SCLK_GMAC0_RGMII_SPEED>; ++ assigned-clock-rates = <0>, <125000000>; ++ clock_in_out = "output"; ++ phy-handle = <&rgmii_phy0>; ++ phy-mode = "rgmii"; ++ phy-supply = <&vcc3v3_sys>; ++ pinctrl-names = "default"; ++ pinctrl-0 = <&gmac0_miim ++ &gmac0_tx_bus2 ++ &gmac0_rx_bus2 ++ &gmac0_rgmii_clk ++ &gmac0_rgmii_bus>; ++ status = "okay"; ++ ++ tx_delay = <0x4f>; ++ rx_delay = <0x2d>; ++}; ++ ++&i2c0 { ++ status = "okay"; ++ ++ vdd_cpu: regulator@1c { ++ compatible = "tcs,tcs4525"; ++ reg = <0x1c>; ++ fcs,suspend-voltage-selector = <1>; ++ regulator-name = "vdd_cpu"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <800000>; ++ regulator-max-microvolt = <1150000>; ++ regulator-ramp-delay = <2300>; ++ vin-supply = <&vcc3v3_sys>; ++ ++ regulator-state-mem { ++ regulator-off-in-suspend; ++ }; ++ }; ++ ++ rk809: pmic@20 { ++ compatible = "rockchip,rk809"; ++ reg = <0x20>; ++ interrupt-parent = <&gpio0>; ++ interrupts = <RK_PA3 IRQ_TYPE_LEVEL_LOW>; ++ #clock-cells = <1>; ++ pinctrl-names = "default"; ++ pinctrl-0 = <&pmic_int_l>; ++ rockchip,system-power-controller; ++ vcc1-supply = <&vcc3v3_sys>; ++ vcc2-supply = <&vcc3v3_sys>; ++ vcc3-supply = <&vcc3v3_sys>; ++ vcc4-supply = <&vcc3v3_sys>; ++ vcc5-supply = <&vcc3v3_sys>; ++ vcc6-supply = <&vcc3v3_sys>; ++ vcc7-supply = <&vcc3v3_sys>; ++ vcc8-supply = <&vcc3v3_sys>; ++ vcc9-supply = <&vcc3v3_sys>; ++ wakeup-source; ++ ++ regulators { ++ vdd_logic: DCDC_REG1 { ++ regulator-name = "vdd_logic"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-init-microvolt = <900000>; ++ regulator-initial-mode = <0x2>; ++ regulator-min-microvolt = <500000>; ++ regulator-max-microvolt = <1350000>; ++ regulator-ramp-delay = <6001>; ++ ++ regulator-state-mem { ++ regulator-off-in-suspend; ++ }; ++ }; ++ ++ vdd_gpu: DCDC_REG2 { ++ regulator-name = "vdd_gpu"; ++ regulator-always-on; ++ regulator-init-microvolt = <900000>; ++ regulator-initial-mode = <0x2>; ++ regulator-min-microvolt = <500000>; ++ regulator-max-microvolt = <1350000>; ++ regulator-ramp-delay = <6001>; ++ ++ regulator-state-mem { ++ regulator-off-in-suspend; ++ }; ++ }; ++ ++ vcc_ddr: DCDC_REG3 { ++ regulator-name = "vcc_ddr"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-initial-mode = <0x2>; ++ ++ regulator-state-mem { ++ regulator-on-in-suspend; ++ }; ++ }; ++ ++ vdd_npu: DCDC_REG4 { ++ regulator-name = "vdd_npu"; ++ regulator-init-microvolt = <900000>; ++ regulator-initial-mode = <0x2>; ++ regulator-min-microvolt = <500000>; ++ regulator-max-microvolt = <1350000>; ++ regulator-ramp-delay = <6001>; ++ ++ regulator-state-mem { ++ regulator-off-in-suspend; ++ }; ++ }; ++ ++ vcc_1v8: DCDC_REG5 { ++ regulator-name = "vcc_1v8"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <1800000>; ++ regulator-max-microvolt = <1800000>; ++ ++ regulator-state-mem { ++ regulator-off-in-suspend; ++ }; ++ }; ++ ++ vdda0v9_image: LDO_REG1 { ++ regulator-name = "vdda0v9_image"; ++ regulator-always-on; ++ regulator-min-microvolt = <900000>; ++ regulator-max-microvolt = <900000>; ++ ++ regulator-state-mem { ++ regulator-off-in-suspend; ++ }; ++ }; ++ ++ vdda_0v9: LDO_REG2 { ++ regulator-name = "vdda_0v9"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <900000>; ++ regulator-max-microvolt = <900000>; ++ ++ regulator-state-mem { ++ regulator-off-in-suspend; ++ }; ++ }; ++ ++ vdda0v9_pmu: LDO_REG3 { ++ regulator-name = "vdda0v9_pmu"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <900000>; ++ regulator-max-microvolt = <900000>; ++ ++ regulator-state-mem { ++ regulator-on-in-suspend; ++ regulator-suspend-microvolt = <900000>; ++ }; ++ }; ++ ++ vccio_acodec: LDO_REG4 { ++ regulator-name = "vccio_acodec"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <3300000>; ++ regulator-max-microvolt = <3300000>; ++ ++ regulator-state-mem { ++ regulator-off-in-suspend; ++ }; ++ }; ++ ++ vccio_sd: LDO_REG5 { ++ regulator-name = "vccio_sd"; ++ regulator-min-microvolt = <1800000>; ++ regulator-max-microvolt = <3300000>; ++ ++ regulator-state-mem { ++ regulator-off-in-suspend; ++ }; ++ }; ++ ++ vcc3v3_pmu: LDO_REG6 { ++ regulator-name = "vcc3v3_pmu"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <3300000>; ++ regulator-max-microvolt = <3300000>; ++ ++ regulator-state-mem { ++ regulator-on-in-suspend; ++ regulator-suspend-microvolt = <3300000>; ++ }; ++ }; ++ ++ vcca_1v8: LDO_REG7 { ++ regulator-name = "vcca_1v8"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <1800000>; ++ regulator-max-microvolt = <1800000>; ++ ++ regulator-state-mem { ++ regulator-off-in-suspend; ++ }; ++ }; ++ ++ vcca1v8_pmu: LDO_REG8 { ++ regulator-name = "vcca1v8_pmu"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <1800000>; ++ regulator-max-microvolt = <1800000>; ++ ++ regulator-state-mem { ++ regulator-on-in-suspend; ++ regulator-suspend-microvolt = <1800000>; ++ }; ++ }; ++ ++ vcca1v8_image: LDO_REG9 { ++ regulator-name = "vcca1v8_image"; ++ regulator-always-on; ++ regulator-min-microvolt = <1800000>; ++ regulator-max-microvolt = <1800000>; ++ ++ regulator-state-mem { ++ regulator-off-in-suspend; ++ }; ++ }; ++ ++ vcc_3v3: SWITCH_REG1 { ++ regulator-name = "vcc_3v3"; ++ regulator-always-on; ++ regulator-boot-on; ++ ++ regulator-state-mem { ++ regulator-off-in-suspend; ++ }; ++ }; ++ ++ vcc3v3_sd: SWITCH_REG2 { ++ regulator-name = "vcc3v3_sd"; ++ ++ regulator-state-mem { ++ regulator-off-in-suspend; ++ }; ++ }; ++ }; ++ }; ++}; ++ ++&mdio0 { ++ rgmii_phy0: ethernet-phy@0 { ++ compatible = "ethernet-phy-ieee802.3-c22"; ++ reg = <0x0>; ++ reset-assert-us = <20000>; ++ reset-deassert-us = <100000>; ++ reset-gpios = <&gpio3 RK_PB7 GPIO_ACTIVE_LOW>; ++ }; ++}; ++ ++&pinctrl { ++ leds { ++ led_power_pin: led-power-pin { ++ rockchip,pins = <0 RK_PC6 RK_FUNC_GPIO &pcfg_pull_none>; ++ }; ++ led_work_pin: led-work-pin { ++ rockchip,pins = <0 RK_PB7 RK_FUNC_GPIO &pcfg_pull_none>; ++ }; ++ }; ++ ++ pmic { ++ pmic_int_l: pmic-int-l { ++ rockchip,pins = <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>; ++ }; ++ }; ++}; ++ ++&pmu_io_domains { ++ pmuio1-supply = <&vcc3v3_pmu>; ++ pmuio2-supply = <&vcc3v3_pmu>; ++ vccio1-supply = <&vccio_acodec>; ++ vccio2-supply = <&vcc_1v8>; ++ vccio3-supply = <&vccio_sd>; ++ vccio4-supply = <&vcc_1v8>; ++ vccio5-supply = <&vcc_3v3>; ++ vccio6-supply = <&vcc_3v3>; ++ vccio7-supply = <&vcc_3v3>; ++ status = "okay"; ++}; ++ ++&saradc { ++ vref-supply = <&vcca_1v8>; ++ status = "okay"; ++}; ++ ++&sdhci { ++ bus-width = <8>; ++ max-frequency = <200000000>; ++ non-removable; ++ pinctrl-names = "default"; ++ pinctrl-0 = <&emmc_bus8 &emmc_clk &emmc_cmd &emmc_datastrobe &emmc_rstnout>; ++ vmmc-supply = <&vcc_3v3>; ++ vqmmc-supply = <&vcc_1v8>; ++ status = "okay"; ++}; ++ ++&sdmmc0 { ++ bus-width = <4>; ++ cap-sd-highspeed; ++ cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; ++ disable-wp; ++ pinctrl-names = "default"; ++ pinctrl-0 = <&sdmmc0_bus4 &sdmmc0_clk &sdmmc0_cmd &sdmmc0_det>; ++ sd-uhs-sdr50; ++ vmmc-supply = <&vcc3v3_sd>; ++ vqmmc-supply = <&vccio_sd>; ++ status = "okay"; ++}; ++ ++&uart2 { ++ status = "okay"; ++}; +-- +2.35.1 + diff --git a/debian/patches/features/arm64/arm64-dts-rockchip-Add-IR-receiver-node-to-ODROID-M1.patch b/debian/patches/features/arm64/arm64-dts-rockchip-Add-IR-receiver-node-to-ODROID-M1.patch new file mode 100644 index 000000000..c94e717a5 --- /dev/null +++ b/debian/patches/features/arm64/arm64-dts-rockchip-Add-IR-receiver-node-to-ODROID-M1.patch @@ -0,0 +1,51 @@ +From: Aurelien Jarno <aurelien@aurel32.net> +Date: Fri, 30 Sep 2022 07:12:46 +0200 +Subject: [13/13] arm64: dts: rockchip: Add IR receiver node to ODROID-M1 +Origin: https://git.kernel.org/linus/d6882992fe8182e3122be34af3f491948a8b9069 + +Add the infrared receiver and its associated pinctrl entry. Note that +there is an external pullup to VCC3V3_SYS. + +Signed-off-by: Aurelien Jarno <aurelien@aurel32.net> +Tested-by: Dan Johansen <strit@manjaro.org> +Link: https://lore.kernel.org/r/20220930051246.391614-14-aurelien@aurel32.net +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts | 14 ++++++++++++++ + 1 file changed, 14 insertions(+) + +diff --git a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +index 2f685c606bb9..59ecf868dbd0 100644 +--- a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts ++++ b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +@@ -49,6 +49,13 @@ hdmi_con_in: endpoint { + }; + }; + ++ ir-receiver { ++ compatible = "gpio-ir-receiver"; ++ gpios = <&gpio0 RK_PC2 GPIO_ACTIVE_LOW>; ++ pinctrl-names = "default"; ++ pinctrl-0 = <&ir_receiver_pin>; ++ }; ++ + leds { + compatible = "gpio-leds"; + +@@ -519,6 +526,13 @@ fspi_dual_io_pins: fspi-dual-io-pins { + }; + }; + ++ ir-receiver { ++ ir_receiver_pin: ir-receiver-pin { ++ /* external pullup to VCC3V3_SYS */ ++ rockchip,pins = <0 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>; ++ }; ++ }; ++ + leds { + led_power_pin: led-power-pin { + rockchip,pins = <0 RK_PC6 RK_FUNC_GPIO &pcfg_pull_none>; +-- +2.35.1 + diff --git a/debian/patches/features/arm64/arm64-dts-rockchip-Add-NOR-flash-to-ODROID-M1.patch b/debian/patches/features/arm64/arm64-dts-rockchip-Add-NOR-flash-to-ODROID-M1.patch new file mode 100644 index 000000000..ebc21afec --- /dev/null +++ b/debian/patches/features/arm64/arm64-dts-rockchip-Add-NOR-flash-to-ODROID-M1.patch @@ -0,0 +1,100 @@ +From: Aurelien Jarno <aurelien@aurel32.net> +Date: Fri, 30 Sep 2022 07:12:37 +0200 +Subject: [04/13] arm64: dts: rockchip: Add NOR flash to ODROID-M1 +Origin: https://git.kernel.org/linus/9f96204b7dcf94d03cad41194447c665d10675b7 + +Enable the Rockchip Serial Flash Controller for the ODROID-M1 and add +the corresponding SPI NOR flash entry. The SFC is used in dual I/O mode +and not quad I/O mode, as the FSPI_D2 pin is shared with the EMMC_RSTn +pin. + +The partitions addresses and sizes are taken from the ODROID-M1 +Partition Table page on the ODROID wiki. + +Signed-off-by: Aurelien Jarno <aurelien@aurel32.net> +Tested-by: Dan Johansen <strit@manjaro.org> +Link: https://lore.kernel.org/r/20220930051246.391614-5-aurelien@aurel32.net +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + .../boot/dts/rockchip/rk3568-odroid-m1.dts | 58 +++++++++++++++++++ + 1 file changed, 58 insertions(+) + +diff --git a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +index 112c65af3f55..94e839c9afab 100644 +--- a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts ++++ b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +@@ -351,6 +351,20 @@ rgmii_phy0: ethernet-phy@0 { + }; + + &pinctrl { ++ fspi { ++ fspi_dual_io_pins: fspi-dual-io-pins { ++ rockchip,pins = ++ /* fspi_clk */ ++ <1 RK_PD0 1 &pcfg_pull_none>, ++ /* fspi_cs0n */ ++ <1 RK_PD3 1 &pcfg_pull_none>, ++ /* fspi_d0 */ ++ <1 RK_PD1 1 &pcfg_pull_none>, ++ /* fspi_d1 */ ++ <1 RK_PD2 1 &pcfg_pull_none>; ++ }; ++ }; ++ + leds { + led_power_pin: led-power-pin { + rockchip,pins = <0 RK_PC6 RK_FUNC_GPIO &pcfg_pull_none>; +@@ -409,6 +423,50 @@ &sdmmc0 { + status = "okay"; + }; + ++&sfc { ++ /* Dual I/O mode as the D2 pin conflicts with the eMMC */ ++ pinctrl-0 = <&fspi_dual_io_pins>; ++ pinctrl-names = "default"; ++ #address-cells = <1>; ++ #size-cells = <0>; ++ status = "okay"; ++ ++ flash@0 { ++ compatible = "jedec,spi-nor"; ++ reg = <0>; ++ spi-max-frequency = <100000000>; ++ spi-rx-bus-width = <2>; ++ spi-tx-bus-width = <1>; ++ ++ partitions { ++ compatible = "fixed-partitions"; ++ #address-cells = <1>; ++ #size-cells = <1>; ++ ++ partition@0 { ++ label = "SPL"; ++ reg = <0x0 0xe0000>; ++ }; ++ partition@e0000 { ++ label = "U-Boot Env"; ++ reg = <0xe0000 0x20000>; ++ }; ++ partition@100000 { ++ label = "U-Boot"; ++ reg = <0x100000 0x200000>; ++ }; ++ partition@300000 { ++ label = "splash"; ++ reg = <0x300000 0x100000>; ++ }; ++ partition@400000 { ++ label = "Filesystem"; ++ reg = <0x400000 0xc00000>; ++ }; ++ }; ++ }; ++}; ++ + &tsadc { + rockchip,hw-tshut-mode = <1>; + rockchip,hw-tshut-polarity = <0>; +-- +2.35.1 + diff --git a/debian/patches/features/arm64/arm64-dts-rockchip-Add-PCIEe-v3-nodes-to-ODROID-M1.patch b/debian/patches/features/arm64/arm64-dts-rockchip-Add-PCIEe-v3-nodes-to-ODROID-M1.patch new file mode 100644 index 000000000..94c7d7952 --- /dev/null +++ b/debian/patches/features/arm64/arm64-dts-rockchip-Add-PCIEe-v3-nodes-to-ODROID-M1.patch @@ -0,0 +1,77 @@ +From: Aurelien Jarno <aurelien@aurel32.net> +Date: Fri, 30 Sep 2022 07:12:45 +0200 +Subject: [12/13] arm64: dts: rockchip: Add PCIEe v3 nodes to ODROID-M1 +Origin: https://git.kernel.org/linus/35b28582aa3dfd7b6861b7ebc72798b0ff50ed41 + +Add nodes to ODROID-M1 to support PCIe v3 on the M2 slot. + +Signed-off-by: Aurelien Jarno <aurelien@aurel32.net> +Tested-by: Dan Johansen <strit@manjaro.org> +Link: https://lore.kernel.org/r/20220930051246.391614-13-aurelien@aurel32.net +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + .../boot/dts/rockchip/rk3568-odroid-m1.dts | 34 +++++++++++++++++++ + 1 file changed, 34 insertions(+) + +diff --git a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +index bd24ccf94e76..2f685c606bb9 100644 +--- a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts ++++ b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +@@ -96,6 +96,19 @@ simple-audio-card,codec { + }; + }; + ++ vcc3v3_pcie: vcc3v3-pcie-regulator { ++ compatible = "regulator-fixed"; ++ regulator-name = "vcc3v3_pcie"; ++ enable-active-high; ++ gpio = <&gpio4 RK_PA7 GPIO_ACTIVE_HIGH>; ++ pinctrl-names = "default"; ++ pinctrl-0 = <&vcc3v3_pcie_en_pin>; ++ regulator-min-microvolt = <3300000>; ++ regulator-max-microvolt = <3300000>; ++ startup-delay-us = <5000>; ++ vin-supply = <&vcc3v3_sys>; ++ }; ++ + vcc3v3_sys: vcc3v3-sys-regulator { + compatible = "regulator-fixed"; + regulator-name = "vcc3v3_sys"; +@@ -479,6 +492,18 @@ rgmii_phy0: ethernet-phy@0 { + }; + }; + ++&pcie30phy { ++ status = "okay"; ++}; ++ ++&pcie3x2 { ++ pinctrl-names = "default"; ++ pinctrl-0 = <&pcie_reset_pin>; ++ reset-gpios = <&gpio2 RK_PD6 GPIO_ACTIVE_HIGH>; ++ vpcie3v3-supply = <&vcc3v3_pcie>; ++ status = "okay"; ++}; ++ + &pinctrl { + fspi { + fspi_dual_io_pins: fspi-dual-io-pins { +@@ -503,6 +528,15 @@ led_work_pin: led-work-pin { + }; + }; + ++ pcie { ++ pcie_reset_pin: pcie-reset-pin { ++ rockchip,pins = <2 RK_PD6 RK_FUNC_GPIO &pcfg_pull_none>; ++ }; ++ vcc3v3_pcie_en_pin: vcc3v3-pcie-en-pin { ++ rockchip,pins = <4 RK_PA7 RK_FUNC_GPIO &pcfg_pull_none>; ++ }; ++ }; ++ + pmic { + pmic_int_l: pmic-int-l { + rockchip,pins = <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>; +-- +2.35.1 + diff --git a/debian/patches/features/arm64/arm64-dts-rockchip-Add-SATA-support-to-ODROID-M1.patch b/debian/patches/features/arm64/arm64-dts-rockchip-Add-SATA-support-to-ODROID-M1.patch new file mode 100644 index 000000000..2025079e1 --- /dev/null +++ b/debian/patches/features/arm64/arm64-dts-rockchip-Add-SATA-support-to-ODROID-M1.patch @@ -0,0 +1,45 @@ +From: Aurelien Jarno <aurelien@aurel32.net> +Date: Fri, 30 Sep 2022 07:12:44 +0200 +Subject: [11/13] arm64: dts: rockchip: Add SATA support to ODROID-M1 +Origin: https://git.kernel.org/linus/6a5a04d52ccc42e0e59ff69fca9c1db7e08ba44b + +Enable the Combo PHY and SATA nodes in ODROID-M1. + +Signed-off-by: Aurelien Jarno <aurelien@aurel32.net> +Tested-by: Dan Johansen <strit@manjaro.org> +Link: https://lore.kernel.org/r/20220930051246.391614-12-aurelien@aurel32.net +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts | 9 +++++++++ + 1 file changed, 9 insertions(+) + +diff --git a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +index 9a84a7e76d7a..bd24ccf94e76 100644 +--- a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts ++++ b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +@@ -153,6 +153,11 @@ &combphy1 { + status = "okay"; + }; + ++&combphy2 { ++ /* used for SATA */ ++ status = "okay"; ++}; ++ + &cpu0 { + cpu-supply = <&vdd_cpu>; + }; +@@ -538,6 +543,10 @@ &saradc { + status = "okay"; + }; + ++&sata2 { ++ status = "okay"; ++}; ++ + &sdhci { + bus-width = <8>; + max-frequency = <200000000>; +-- +2.35.1 + diff --git a/debian/patches/features/arm64/arm64-dts-rockchip-Add-analog-audio-on-ODROID-M1.patch b/debian/patches/features/arm64/arm64-dts-rockchip-Add-analog-audio-on-ODROID-M1.patch new file mode 100644 index 000000000..03cb99ff1 --- /dev/null +++ b/debian/patches/features/arm64/arm64-dts-rockchip-Add-analog-audio-on-ODROID-M1.patch @@ -0,0 +1,99 @@ +From: Aurelien Jarno <aurelien@aurel32.net> +Date: Fri, 30 Sep 2022 07:12:38 +0200 +Subject: [05/13] arm64: dts: rockchip: Add analog audio on ODROID-M1 +Origin: https://git.kernel.org/linus/78f858447cb78cac7259093d095fb783328b835c + +On the ODROID-M1, the I2S1 TDM controller is connected to the rk809 +codec in I2S mode. It is used to provide a stereo headphones output and +a mono speaker output. A GPIO with an external pullup is used as an +headphone detection input. + +Signed-off-by: Aurelien Jarno <aurelien@aurel32.net> +Tested-by: Dan Johansen <strit@manjaro.org> +Link: https://lore.kernel.org/r/20220930051246.391614-6-aurelien@aurel32.net +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + .../boot/dts/rockchip/rk3568-odroid-m1.dts | 43 ++++++++++++++++++- + 1 file changed, 42 insertions(+), 1 deletion(-) + +diff --git a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +index 94e839c9afab..634c1bd80b4e 100644 +--- a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts ++++ b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +@@ -59,6 +59,31 @@ led_work: led-1 { + }; + }; + ++ rk809-sound { ++ compatible = "simple-audio-card"; ++ pinctrl-names = "default"; ++ pinctrl-0 = <&hp_det_pin>; ++ simple-audio-card,name = "Analog RK817"; ++ simple-audio-card,format = "i2s"; ++ simple-audio-card,hp-det-gpio = <&gpio0 RK_PB0 GPIO_ACTIVE_HIGH>; ++ simple-audio-card,mclk-fs = <256>; ++ simple-audio-card,widgets = ++ "Headphone", "Headphones", ++ "Speaker", "Speaker"; ++ simple-audio-card,routing = ++ "Headphones", "HPOL", ++ "Headphones", "HPOR", ++ "Speaker", "SPKO"; ++ ++ simple-audio-card,cpu { ++ sound-dai = <&i2s1_8ch>; ++ }; ++ ++ simple-audio-card,codec { ++ sound-dai = <&rk809>; ++ }; ++ }; ++ + vcc3v3_sys: vcc3v3-sys-regulator { + compatible = "regulator-fixed"; + regulator-name = "vcc3v3_sys"; +@@ -131,10 +156,15 @@ rk809: pmic@20 { + reg = <0x20>; + interrupt-parent = <&gpio0>; + interrupts = <RK_PA3 IRQ_TYPE_LEVEL_LOW>; ++ assigned-clocks = <&cru I2S1_MCLKOUT_TX>; ++ assigned-clock-parents = <&cru CLK_I2S1_8CH_TX>; + #clock-cells = <1>; ++ clock-names = "mclk"; ++ clocks = <&cru I2S1_MCLKOUT_TX>; + pinctrl-names = "default"; +- pinctrl-0 = <&pmic_int_l>; ++ pinctrl-0 = <&pmic_int_l>, <&i2s1m0_mclk>; + rockchip,system-power-controller; ++ #sound-dai-cells = <0>; + vcc1-supply = <&vcc3v3_sys>; + vcc2-supply = <&vcc3v3_sys>; + vcc3-supply = <&vcc3v3_sys>; +@@ -340,6 +370,11 @@ regulator-state-mem { + }; + }; + ++&i2s1_8ch { ++ rockchip,trcm-sync-tx-only; ++ status = "okay"; ++}; ++ + &mdio0 { + rgmii_phy0: ethernet-phy@0 { + compatible = "ethernet-phy-ieee802.3-c22"; +@@ -379,6 +414,12 @@ pmic_int_l: pmic-int-l { + rockchip,pins = <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; ++ ++ rk809 { ++ hp_det_pin: hp-det-pin { ++ rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>; ++ }; ++ }; + }; + + &pmu_io_domains { +-- +2.35.1 + diff --git a/debian/patches/features/arm64/arm64-dts-rockchip-Enable-HDMI-audio-on-ODROID-M1.patch b/debian/patches/features/arm64/arm64-dts-rockchip-Enable-HDMI-audio-on-ODROID-M1.patch new file mode 100644 index 000000000..0dff4d2b7 --- /dev/null +++ b/debian/patches/features/arm64/arm64-dts-rockchip-Enable-HDMI-audio-on-ODROID-M1.patch @@ -0,0 +1,45 @@ +From: Aurelien Jarno <aurelien@aurel32.net> +Date: Fri, 30 Sep 2022 07:12:40 +0200 +Subject: [07/13] arm64: dts: rockchip: Enable HDMI audio on ODROID-M1. +Origin: https://git.kernel.org/linus/1ca7ddddf36494f0f6afd4f35d37827323271f39 + +This enables the i2s0 controller and the hdmi-sound node on the +ODROID-M1. + +Signed-off-by: Aurelien Jarno <aurelien@aurel32.net> +Tested-by: Dan Johansen <strit@manjaro.org> +Link: https://lore.kernel.org/r/20220930051246.391614-8-aurelien@aurel32.net +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts | 8 ++++++++ + 1 file changed, 8 insertions(+) + +diff --git a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +index 126b893048fe..ac4e94d18feb 100644 +--- a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts ++++ b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +@@ -161,6 +161,10 @@ hdmi_out_con: endpoint { + }; + }; + ++&hdmi_sound { ++ status = "okay"; ++}; ++ + &i2c0 { + status = "okay"; + +@@ -400,6 +404,10 @@ regulator-state-mem { + }; + }; + ++&i2s0_8ch { ++ status = "okay"; ++}; ++ + &i2s1_8ch { + rockchip,trcm-sync-tx-only; + status = "okay"; +-- +2.35.1 + diff --git a/debian/patches/features/arm64/arm64-dts-rockchip-Enable-the-GPU-on-ODROID-M1.patch b/debian/patches/features/arm64/arm64-dts-rockchip-Enable-the-GPU-on-ODROID-M1.patch new file mode 100644 index 000000000..faed83fca --- /dev/null +++ b/debian/patches/features/arm64/arm64-dts-rockchip-Enable-the-GPU-on-ODROID-M1.patch @@ -0,0 +1,34 @@ +From: Aurelien Jarno <aurelien@aurel32.net> +Date: Fri, 30 Sep 2022 07:12:41 +0200 +Subject: [08/13] arm64: dts: rockchip: Enable the GPU on ODROID-M1 +Origin: https://git.kernel.org/linus/cb80b3455c7cadc4c1157879930e919f607d557c + +Enable the GPU core on the Rockchip RK3568 ODROID-M1. + +Signed-off-by: Aurelien Jarno <aurelien@aurel32.net> +Tested-by: Dan Johansen <strit@manjaro.org> +Link: https://lore.kernel.org/r/20220930051246.391614-9-aurelien@aurel32.net +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts | 5 +++++ + 1 file changed, 5 insertions(+) + +diff --git a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +index ac4e94d18feb..e4b7699d3eea 100644 +--- a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts ++++ b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +@@ -143,6 +143,11 @@ &gmac0_rgmii_clk + rx_delay = <0x2d>; + }; + ++&gpu { ++ mali-supply = <&vdd_gpu>; ++ status = "okay"; ++}; ++ + &hdmi { + avdd-0v9-supply = <&vdda0v9_image>; + avdd-1v8-supply = <&vcca1v8_image>; +-- +2.35.1 + diff --git a/debian/patches/features/arm64/arm64-dts-rockchip-Enable-the-USB-2.0-ports-on-ODROI.patch b/debian/patches/features/arm64/arm64-dts-rockchip-Enable-the-USB-2.0-ports-on-ODROI.patch new file mode 100644 index 000000000..c27944417 --- /dev/null +++ b/debian/patches/features/arm64/arm64-dts-rockchip-Enable-the-USB-2.0-ports-on-ODROI.patch @@ -0,0 +1,108 @@ +From: Aurelien Jarno <aurelien@aurel32.net> +Date: Fri, 30 Sep 2022 07:12:42 +0200 +Subject: [09/13] arm64: dts: rockchip: Enable the USB 2.0 ports on ODROID-M1 +Origin: https://git.kernel.org/linus/4685d7b68aaac199ab0d950d2047405bf551f964 + +The Rockchip RK3568 has two USB OHCI/EHCI controllers connected to a PHY +providing one host-only port and one OTG port. On the ODROID-M1, they +are both used in host mode. The USB ports are powered by a DC/DC +converter providing 5V and named VCC5V0_SYS on the schematics, followed +by a power switch. + +Signed-off-by: Aurelien Jarno <aurelien@aurel32.net> +Tested-by: Dan Johansen <strit@manjaro.org> +Link: https://lore.kernel.org/r/20220930051246.391614-10-aurelien@aurel32.net +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + .../boot/dts/rockchip/rk3568-odroid-m1.dts | 61 +++++++++++++++++++ + 1 file changed, 61 insertions(+) + +diff --git a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +index e4b7699d3eea..2e4cc20bd676 100644 +--- a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts ++++ b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +@@ -105,6 +105,28 @@ vcc3v3_sys: vcc3v3-sys-regulator { + regulator-max-microvolt = <3300000>; + vin-supply = <&dc_12v>; + }; ++ ++ vcc5v0_sys: vcc5v0-sys-regulator { ++ compatible = "regulator-fixed"; ++ regulator-name = "vcc5v0_sys"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <5000000>; ++ regulator-max-microvolt = <5000000>; ++ vin-supply = <&dc_12v>; ++ }; ++ ++ vcc5v0_usb_host: vcc5v0-usb-host-regulator { ++ compatible = "regulator-fixed"; ++ regulator-name = "vcc5v0_usb_host"; ++ enable-active-high; ++ gpio = <&gpio0 RK_PA6 GPIO_ACTIVE_HIGH>; ++ pinctrl-names = "default"; ++ pinctrl-0 = <&vcc5v0_usb_host_en_pin>; ++ regulator-min-microvolt = <5000000>; ++ regulator-max-microvolt = <5000000>; ++ vin-supply = <&vcc5v0_sys>; ++ }; + }; + + &cpu0 { +@@ -463,6 +485,15 @@ hp_det_pin: hp-det-pin { + rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; ++ ++ usb { ++ vcc5v0_usb_host_en_pin: vcc5v0-usb-host-en-pin { ++ rockchip,pins = <0 RK_PA6 RK_FUNC_GPIO &pcfg_pull_none>; ++ }; ++ vcc5v0_usb_otg_en_pin: vcc5v0-usb-otg-en-pin { ++ rockchip,pins = <0 RK_PA5 RK_FUNC_GPIO &pcfg_pull_none>; ++ }; ++ }; + }; + + &pmu_io_domains { +@@ -561,6 +592,36 @@ &uart2 { + status = "okay"; + }; + ++&usb_host0_ehci { ++ status = "okay"; ++}; ++ ++&usb_host0_ohci { ++ status = "okay"; ++}; ++ ++&usb_host1_ehci { ++ status = "okay"; ++}; ++ ++&usb_host1_ohci { ++ status = "okay"; ++}; ++ ++&usb2phy1 { ++ status = "okay"; ++}; ++ ++&usb2phy1_host { ++ phy-supply = <&vcc5v0_usb_host>; ++ status = "okay"; ++}; ++ ++&usb2phy1_otg { ++ phy-supply = <&vcc5v0_usb_host>; ++ status = "okay"; ++}; ++ + &vop { + assigned-clocks = <&cru DCLK_VOP0>, <&cru DCLK_VOP1>; + assigned-clock-parents = <&pmucru PLL_HPLL>, <&cru PLL_VPLL>; +-- +2.35.1 + diff --git a/debian/patches/features/arm64/arm64-dts-rockchip-Enable-the-USB-3.0-ports-on-ODROI.patch b/debian/patches/features/arm64/arm64-dts-rockchip-Enable-the-USB-3.0-ports-on-ODROI.patch new file mode 100644 index 000000000..bfcf9c523 --- /dev/null +++ b/debian/patches/features/arm64/arm64-dts-rockchip-Enable-the-USB-3.0-ports-on-ODROI.patch @@ -0,0 +1,111 @@ +From: Aurelien Jarno <aurelien@aurel32.net> +Date: Fri, 30 Sep 2022 07:12:43 +0200 +Subject: [10/13] arm64: dts: rockchip: Enable the USB 3.0 ports on ODROID-M1 +Origin: https://git.kernel.org/linus/9984ef562653c8d0beb51021fc286706b6ec4802 + +The Rockchip RK3568 has two USB XHCI controllers. The USB 2.0 signals +are connected to a PHY providing one host-only port and one OTG port. +The USB 3.0 signals are connected to two USB3.0/PCIE/SATA combo PHY. + +The ODROID M1 has 2 type A USB 3.0 connectors, with the USB 3.0 signals +connected to the two combo PHYs. For the USB 2.0 signals, one connector +is connected to the host-only PHY and uses the same power switch as the +USB 2.0 ports. The other connector has its own power switch and is +connected to the OTG PHY, which is also connected to a device only +micro-USB connector. The purpose of this micro-USB connector is for +firmware update using the Rockusb vendor specific USB class. Therefore +it does not make sense to enable this port on Linux, and the PHY is +forced to host mode. + +Signed-off-by: Aurelien Jarno <aurelien@aurel32.net> +Tested-by: Dan Johansen <strit@manjaro.org> +Link: https://lore.kernel.org/r/20220930051246.391614-11-aurelien@aurel32.net +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + .../boot/dts/rockchip/rk3568-odroid-m1.dts | 49 ++++++++++++++++++- + 1 file changed, 48 insertions(+), 1 deletion(-) + +diff --git a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +index 2e4cc20bd676..9a84a7e76d7a 100644 +--- a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts ++++ b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +@@ -127,6 +127,30 @@ vcc5v0_usb_host: vcc5v0-usb-host-regulator { + regulator-max-microvolt = <5000000>; + vin-supply = <&vcc5v0_sys>; + }; ++ ++ vcc5v0_usb_otg: vcc5v0-usb-otg-regulator { ++ compatible = "regulator-fixed"; ++ regulator-name = "vcc5v0_usb_otg"; ++ enable-active-high; ++ gpio = <&gpio0 RK_PA5 GPIO_ACTIVE_HIGH>; ++ pinctrl-names = "default"; ++ pinctrl-0 = <&vcc5v0_usb_otg_en_pin>; ++ regulator-min-microvolt = <5000000>; ++ regulator-max-microvolt = <5000000>; ++ vin-supply = <&vcc5v0_sys>; ++ }; ++}; ++ ++&combphy0 { ++ /* Used for USB3 */ ++ phy-supply = <&vcc5v0_usb_host>; ++ status = "okay"; ++}; ++ ++&combphy1 { ++ /* Used for USB3 */ ++ phy-supply = <&vcc5v0_usb_otg>; ++ status = "okay"; + }; + + &cpu0 { +@@ -490,7 +514,7 @@ usb { + vcc5v0_usb_host_en_pin: vcc5v0-usb-host-en-pin { + rockchip,pins = <0 RK_PA6 RK_FUNC_GPIO &pcfg_pull_none>; + }; +- vcc5v0_usb_otg_en_pin: vcc5v0-usb-otg-en-pin { ++ vcc5v0_usb_otg_en_pin: vcc5v0-usb-dr-en-pin { + rockchip,pins = <0 RK_PA5 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; +@@ -600,6 +624,11 @@ &usb_host0_ohci { + status = "okay"; + }; + ++&usb_host0_xhci { ++ dr_mode = "host"; ++ status = "okay"; ++}; ++ + &usb_host1_ehci { + status = "okay"; + }; +@@ -608,6 +637,24 @@ &usb_host1_ohci { + status = "okay"; + }; + ++&usb_host1_xhci { ++ status = "okay"; ++}; ++ ++&usb2phy0 { ++ status = "okay"; ++}; ++ ++&usb2phy0_host { ++ phy-supply = <&vcc5v0_usb_host>; ++ status = "okay"; ++}; ++ ++&usb2phy0_otg { ++ phy-supply = <&vcc5v0_usb_otg>; ++ status = "okay"; ++}; ++ + &usb2phy1 { + status = "okay"; + }; +-- +2.35.1 + diff --git a/debian/patches/features/arm64/arm64-dts-rockchip-Enable-vop2-and-hdmi-tx-on-ODROID.patch b/debian/patches/features/arm64/arm64-dts-rockchip-Enable-vop2-and-hdmi-tx-on-ODROID.patch new file mode 100644 index 000000000..48d1b3642 --- /dev/null +++ b/debian/patches/features/arm64/arm64-dts-rockchip-Enable-vop2-and-hdmi-tx-on-ODROID.patch @@ -0,0 +1,94 @@ +From: Aurelien Jarno <aurelien@aurel32.net> +Date: Fri, 30 Sep 2022 07:12:39 +0200 +Subject: [06/13] arm64: dts: rockchip: Enable vop2 and hdmi tx on ODROID-M1 +Origin: https://git.kernel.org/linus/913404aa2e60610f9cae375069dae97e11d726ed + +Enable the RK356x Video Output Processor (VOP) 2 on ODROID M1. + +Signed-off-by: Aurelien Jarno <aurelien@aurel32.net> +Tested-by: Dan Johansen <strit@manjaro.org> +Link: https://lore.kernel.org/r/20220930051246.391614-7-aurelien@aurel32.net +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + .../boot/dts/rockchip/rk3568-odroid-m1.dts | 47 +++++++++++++++++++ + 1 file changed, 47 insertions(+) + +diff --git a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +index 634c1bd80b4e..126b893048fe 100644 +--- a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts ++++ b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +@@ -8,6 +8,7 @@ + #include <dt-bindings/gpio/gpio.h> + #include <dt-bindings/leds/common.h> + #include <dt-bindings/pinctrl/rockchip.h> ++#include <dt-bindings/soc/rockchip,vop2.h> + #include "rk3568.dtsi" + + / { +@@ -37,6 +38,17 @@ dc_12v: dc-12v-regulator { + regulator-max-microvolt = <12000000>; + }; + ++ hdmi-con { ++ compatible = "hdmi-connector"; ++ type = "a"; ++ ++ port { ++ hdmi_con_in: endpoint { ++ remote-endpoint = <&hdmi_out_con>; ++ }; ++ }; ++ }; ++ + leds { + compatible = "gpio-leds"; + +@@ -131,6 +143,24 @@ &gmac0_rgmii_clk + rx_delay = <0x2d>; + }; + ++&hdmi { ++ avdd-0v9-supply = <&vdda0v9_image>; ++ avdd-1v8-supply = <&vcca1v8_image>; ++ status = "okay"; ++}; ++ ++&hdmi_in { ++ hdmi_in_vp0: endpoint { ++ remote-endpoint = <&vp0_out_hdmi>; ++ }; ++}; ++ ++&hdmi_out { ++ hdmi_out_con: endpoint { ++ remote-endpoint = <&hdmi_con_in>; ++ }; ++}; ++ + &i2c0 { + status = "okay"; + +@@ -517,3 +547,20 @@ &tsadc { + &uart2 { + status = "okay"; + }; ++ ++&vop { ++ assigned-clocks = <&cru DCLK_VOP0>, <&cru DCLK_VOP1>; ++ assigned-clock-parents = <&pmucru PLL_HPLL>, <&cru PLL_VPLL>; ++ status = "okay"; ++}; ++ ++&vop_mmu { ++ status = "okay"; ++}; ++ ++&vp0 { ++ vp0_out_hdmi: endpoint@ROCKCHIP_VOP2_EP_HDMI0 { ++ reg = <ROCKCHIP_VOP2_EP_HDMI0>; ++ remote-endpoint = <&hdmi_in_vp0>; ++ }; ++}; +-- +2.35.1 + diff --git a/debian/patches/features/arm64/arm64-dts-rockchip-add-thermal-support-to-ODROID-M1.patch b/debian/patches/features/arm64/arm64-dts-rockchip-add-thermal-support-to-ODROID-M1.patch new file mode 100644 index 000000000..5e0970dba --- /dev/null +++ b/debian/patches/features/arm64/arm64-dts-rockchip-add-thermal-support-to-ODROID-M1.patch @@ -0,0 +1,35 @@ +From: Aurelien Jarno <aurelien@aurel32.net> +Date: Fri, 30 Sep 2022 07:12:36 +0200 +Subject: [03/13] arm64: dts: rockchip: add thermal support to ODROID-M1 +Origin: https://git.kernel.org/linus/f5511bd8498da222b6455038a0cf3e7d2b2dfc7e + +Add the thermal nodes for the ODROID-M1. + +Signed-off-by: Aurelien Jarno <aurelien@aurel32.net> +Tested-by: Dan Johansen <strit@manjaro.org> +Link: https://lore.kernel.org/r/20220930051246.391614-4-aurelien@aurel32.net +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts | 6 ++++++ + 1 file changed, 6 insertions(+) + +diff --git a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +index b3016437640b..112c65af3f55 100644 +--- a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts ++++ b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +@@ -409,6 +409,12 @@ &sdmmc0 { + status = "okay"; + }; + ++&tsadc { ++ rockchip,hw-tshut-mode = <1>; ++ rockchip,hw-tshut-polarity = <0>; ++ status = "okay"; ++}; ++ + &uart2 { + status = "okay"; + }; +-- +2.35.1 + diff --git a/debian/patches/features/arm64/dt-bindings-rockchip-Add-Hardkernel-ODROID-M1-board.patch b/debian/patches/features/arm64/dt-bindings-rockchip-Add-Hardkernel-ODROID-M1-board.patch new file mode 100644 index 000000000..54d0c6c20 --- /dev/null +++ b/debian/patches/features/arm64/dt-bindings-rockchip-Add-Hardkernel-ODROID-M1-board.patch @@ -0,0 +1,37 @@ +From: Dongjin Kim <tobetter@gmail.com> +Date: Fri, 30 Sep 2022 07:12:34 +0200 +Subject: [01/13] dt-bindings: rockchip: Add Hardkernel ODROID-M1 board +Origin: https://git.kernel.org/linus/19cc53eb2ce63c0e5adc2fd89494fb16f383ac10 + +Add device tree binding for Hardkernel ODROID-M1 board based on RK3568 +SoC. + +Signed-off-by: Dongjin Kim <tobetter@gmail.com> +Signed-off-by: Aurelien Jarno <aurelien@aurel32.net> +Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +Tested-by: Dan Johansen <strit@manjaro.org> +Link: https://lore.kernel.org/r/20220930051246.391614-2-aurelien@aurel32.net +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + Documentation/devicetree/bindings/arm/rockchip.yaml | 5 +++++ + 1 file changed, 5 insertions(+) + +diff --git a/Documentation/devicetree/bindings/arm/rockchip.yaml b/Documentation/devicetree/bindings/arm/rockchip.yaml +index eee1e6b3f9cb..72bf2fbfe99d 100644 +--- a/Documentation/devicetree/bindings/arm/rockchip.yaml ++++ b/Documentation/devicetree/bindings/arm/rockchip.yaml +@@ -468,6 +468,11 @@ properties: + - const: hardkernel,rk3326-odroid-go2 + - const: rockchip,rk3326 + ++ - description: Hardkernel Odroid M1 ++ items: ++ - const: rockchip,rk3568-odroid-m1 ++ - const: rockchip,rk3568 ++ + - description: Hugsun X99 TV Box + items: + - const: hugsun,x99 +-- +2.35.1 + diff --git a/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-Add-SOQuartz-Model-A-baseboard.patch b/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-Add-SOQuartz-Model-A-baseboard.patch new file mode 100644 index 000000000..ae644e05f --- /dev/null +++ b/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-Add-SOQuartz-Model-A-baseboard.patch @@ -0,0 +1,279 @@ +From: Andrew Powers-Holmes <aholmes@omnom.net> +Date: Wed, 16 Nov 2022 12:53:37 +0100 +Subject: [4/4] arm64: dts: rockchip: Add SOQuartz Model A baseboard +Origin: https://git.kernel.org/linus/afbaed737fb45bcae91e4606025fb31da71b9dfe + +This patch adds the device tree for the "Model A" baseboard for +the SOQuartz CM4 SoM, which is not to be confused with the +Quartz64 Model A, which is the same form factor and SoC, but is +not a CM4 carrier board. + +The board features a PCIe 2 x1 slot, USB 2 host ports, CSI/DSI +connectors, an eDP FFC connector, gigabit ethernet, HDMI, and a +12V DC barrel jack. Also present is a microSD card slot, 40-pin +GPIO, and a power and reset button. + +Signed-off-by: Andrew Powers-Holmes <aholmes@omnom.net> +[rebase, misc fixes, reword] +Signed-off-by: Nicolas Frattaroli <frattaroli.nicolas@gmail.com> +Link: https://lore.kernel.org/r/20221116115337.541601-5-frattaroli.nicolas@gmail.com +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + arch/arm64/boot/dts/rockchip/Makefile | 1 + + .../dts/rockchip/rk3566-soquartz-model-a.dts | 232 ++++++++++++++++++ + 2 files changed, 233 insertions(+) + create mode 100644 arch/arm64/boot/dts/rockchip/rk3566-soquartz-model-a.dts + +diff --git a/arch/arm64/boot/dts/rockchip/Makefile b/arch/arm64/boot/dts/rockchip/Makefile +index 071284a46bf7..0a76a2ebb5f6 100644 +--- a/arch/arm64/boot/dts/rockchip/Makefile ++++ b/arch/arm64/boot/dts/rockchip/Makefile +@@ -70,6 +70,7 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-quartz64-b.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-roc-pc.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-soquartz-blade.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-soquartz-cm4.dtb ++dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-soquartz-model-a.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-bpi-r2-pro.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-evb1-v10.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-odroid-m1.dtb +diff --git a/arch/arm64/boot/dts/rockchip/rk3566-soquartz-model-a.dts b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-model-a.dts +new file mode 100644 +index 000000000000..2208dbfb7f0a +--- /dev/null ++++ b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-model-a.dts +@@ -0,0 +1,232 @@ ++// SPDX-License-Identifier: (GPL-2.0+ OR MIT) ++ ++/dts-v1/; ++ ++#include "rk3566-soquartz.dtsi" ++ ++/ { ++ model = "PINE64 RK3566 SOQuartz on Model A carrier board"; ++ compatible = "pine64,soquartz-model-a", "pine64,soquartz", "rockchip,rk3566"; ++ ++ /* labeled DCIN_12V in schematic */ ++ vcc12v_dcin: vcc12v-dcin-regulator { ++ compatible = "regulator-fixed"; ++ regulator-name = "vcc12v_dcin"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <12000000>; ++ regulator-max-microvolt = <12000000>; ++ }; ++ ++ vcc5v0_usb: vcc5v0-usb-regulator { ++ compatible = "regulator-fixed"; ++ regulator-name = "vcc5v0_usb"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <5000000>; ++ regulator-max-microvolt = <5000000>; ++ vin-supply = <&vcc12v_dcin>; ++ }; ++ ++ /* ++ * Labelled VCC3V0_SD in schematic to not conflict with PMIC ++ * regulator, it's 3.3v in actuality ++ */ ++ vcc3v0_sd: vcc3v0-sd-regulator { ++ compatible = "regulator-fixed"; ++ regulator-name = "vcc3v0_sd"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <3300000>; ++ regulator-max-microvolt = <3300000>; ++ vin-supply = <&vcc3v3_sys>; ++ }; ++ ++ vcc3v3_pcie: vcc3v3-pcie-regulator { ++ compatible = "regulator-fixed"; ++ regulator-name = "vcc3v3_pcie"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <3300000>; ++ regulator-max-microvolt = <3300000>; ++ vin-supply = <&vcc12v_dcin>; ++ }; ++ ++ vcc12v_pcie: vcc12v-pcie-regulator { ++ compatible = "regulator-fixed"; ++ regulator-name = "vcc12v_pcie"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <12000000>; ++ regulator-max-microvolt = <12000000>; ++ vin-supply = <&vcc12v_dcin>; ++ }; ++}; ++ ++/* phy for pcie */ ++&combphy2 { ++ phy-supply = <&vcc3v3_sys>; ++ status = "okay"; ++}; ++ ++&gmac1 { ++ status = "okay"; ++}; ++ ++/* ++ * i2c1 is exposed on CM1 / Module1A ++ * pin 80 - SCL0 - i2c1_scl_m0, pullup to vcc3v3_pmu ++ * pin 82 - SDA0 - i2c1_sda_m0, pullup to vcc3v3_pmu ++ */ ++&i2c1 { ++ status = "okay"; ++ ++ /* ++ * the rtc interrupt is tied to PMIC_PWRON, ++ * it will force reset the board if triggered. ++ */ ++ pcf85063: rtc@51 { ++ compatible = "nxp,pcf85063"; ++ reg = <0x51>; ++ }; ++}; ++ ++/* ++ * i2c2 is exposed on CM1 / Module1A - to PI40 ++ * pin 56 - GPIO3 - i2c2_scl_m1, pullup to vcc_3v3, shared with i2s1_8ch ++ * pin 58 - GPIO2 - i2c2_sda_m1, pullup to vcc_3v3 ++ */ ++&i2c2 { ++ status = "disabled"; ++}; ++ ++/* ++ * i2c3 is exposed on CM1 / Module1A - to PI40 ++ * pin 35 - ID_SC(GPIO28) - i2c3_scl_m0, pullup to vcc_3v3 ++ * pin 36 - ID_SD(GPIO27) - i2c3_sda_m0, pullup to vcc_3v3 ++ */ ++&i2c3 { ++ status = "disabled"; ++}; ++ ++/* ++ * i2c4 is exposed on CM2 / Module1B - to PI40 ++ * pin 45 - GPIO24 - i2c4_scl_m1 ++ * pin 47 - GPIO23 - i2c4_sda_m1 ++ */ ++&i2c4 { ++ status = "disabled"; ++}; ++ ++/* ++ * i2s1_8ch is exposed on CM1 / Module1A - to PI40 ++ * pin 24 - GPIO26 - i2s1_sdi1_m1 ++ * pin 25 - GPIO21 - i2s1_sdo0_m1 ++ * pin 26 - GPIO19 - i2s1_lrck_tx_m1 ++ * pin 27 - GPIO20 - i2s1_sdi0_m1 ++ * pin 29 - GPIO16 - i2s1_sdi3_m1 ++ * pin 30 - GPIO6 - i2s1_sdi2_m1 ++ * pin 40 - GPIO9 - i2s1_sdo1_m1, shared with spi3 ++ * pin 41 - GPIO25 - i2s1_sdo2_m1 ++ * pin 49 - GPIO18 - i2s1_sclk_tx_m1 ++ * pin 50 - GPIO17 - i2s1_mclk_m1 ++ * pin 56 - GPIO3 - i2s1_sdo3_m1, shared with i2c2 ++ */ ++&i2s1_8ch { ++ status = "disabled"; ++}; ++ ++&led_diy { ++ status = "okay"; ++}; ++ ++&led_work { ++ status = "okay"; ++}; ++ ++&pcie2x1 { ++ vpcie3v3-supply = <&vcc3v3_pcie>; ++ status = "okay"; ++}; ++ ++&rgmii_phy1 { ++ status = "okay"; ++}; ++ ++&rgmii_phy1 { ++ status = "okay"; ++}; ++ ++/* ++ * saradc is exposed on CM1 / Module1A - to J2 ++ * pin 94 - AIN1 - saradc_vin3 ++ * pin 96 - AIN0 - saradc_vin2 ++ */ ++&saradc { ++ status = "disabled"; ++}; ++ ++/* ++ * vmmc-supply is vcc3v3_sd on v1.0 and vcc3v0_sd on v1.1+ ++ * the soquartz SoM has SDMMC_PWR (CM1 pin 75) hardwired to vcc3v3_sys, ++ * so we use vcc3v3_sd here to ensure the regulator is enabled on older boards. ++ */ ++&sdmmc0 { ++ vmmc-supply = <&vcc3v3_sd>; ++ status = "okay"; ++}; ++ ++/* ++ * spi3 is exposed on CM1 / Module1A - to PI40 ++ * pin 37 - GPIO7 - spi3_cs1_m0 ++ * pin 38 - GPIO11 - spi3_clk_m0 ++ * pin 39 - GPIO8 - spi3_cs0_m0 ++ * pin 40 - GPIO9 - spi3_miso_m0, shared with i2s1_8ch ++ * pin 44 - GPIO10 - spi3_mosi_m0 ++ */ ++&spi3 { ++ status = "disabled"; ++}; ++ ++/* ++ * uart2 is exposed on CM1 / Module1A - to PI40 ++ * pin 51 - GPIO15 - uart2_rx_m0 ++ * pin 55 - GPIO14 - uart2_tx_m0 ++ */ ++&uart2 { ++ status = "okay"; ++}; ++ ++/* ++ * uart7 is exposed on CM1 / Module1A - to PI40 ++ * pin 46 - GPIO22 - uart7_tx_m2 ++ * pin 47 - GPIO23 - uart7_rx_m2 ++ */ ++&uart7 { ++ status = "okay"; ++}; ++ ++&usb2phy0 { ++ status = "okay"; ++}; ++ ++&usb2phy0_otg { ++ phy-supply = <&vcc5v0_usb>; ++ status = "okay"; ++}; ++ ++&usb_host0_xhci { ++ status = "okay"; ++}; ++ ++&vbus { ++ vin-supply = <&vcc5v0_usb>; ++}; ++ ++&vcc3v3_sd { ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <3300000>; ++ regulator-max-microvolt = <3300000>; ++ status = "okay"; ++}; +-- +2.39.0 + diff --git a/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-Add-SOQuartz-blade-board.patch b/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-Add-SOQuartz-blade-board.patch new file mode 100644 index 000000000..246d62c12 --- /dev/null +++ b/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-Add-SOQuartz-blade-board.patch @@ -0,0 +1,242 @@ +From: Andrew Powers-Holmes <aholmes@omnom.net> +Date: Wed, 16 Nov 2022 12:53:35 +0100 +Subject: [2/4] arm64: dts: rockchip: Add SOQuartz blade board +Origin: https://git.kernel.org/linus/a5c826ecde5222f755e7d8a0c8d795189c5c1228 + +This adds a device tree for the PINE64 SOQuartz blade baseboard, +a 1U rack mountable baseboard for the CM4 form factor with PoE +support designed for the SOQuartz CM4 System-on-Module. + +The board takes power from either PoE or a 5V DC input, and allows +for mounting an M.2 SSD. + +The board also features one USB 2.0 host port, one HDMI output, +a 3.5mm jack for UART, and the aforementioned gigabit networking +port. + +Signed-off-by: Andrew Powers-Holmes <aholmes@omnom.net> +[rebase, squash, reword, misc fixes] +Signed-off-by: Nicolas Frattaroli <frattaroli.nicolas@gmail.com> +Link: https://lore.kernel.org/r/20221116115337.541601-3-frattaroli.nicolas@gmail.com +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + arch/arm64/boot/dts/rockchip/Makefile | 1 + + .../dts/rockchip/rk3566-soquartz-blade.dts | 194 ++++++++++++++++++ + 2 files changed, 195 insertions(+) + create mode 100644 arch/arm64/boot/dts/rockchip/rk3566-soquartz-blade.dts + +diff --git a/arch/arm64/boot/dts/rockchip/Makefile b/arch/arm64/boot/dts/rockchip/Makefile +index e14390277739..071284a46bf7 100644 +--- a/arch/arm64/boot/dts/rockchip/Makefile ++++ b/arch/arm64/boot/dts/rockchip/Makefile +@@ -68,6 +68,7 @@ dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-pinenote-v1.2.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-quartz64-a.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-quartz64-b.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-roc-pc.dtb ++dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-soquartz-blade.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3566-soquartz-cm4.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-bpi-r2-pro.dtb + dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3568-evb1-v10.dtb +diff --git a/arch/arm64/boot/dts/rockchip/rk3566-soquartz-blade.dts b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-blade.dts +new file mode 100644 +index 000000000000..4e49bebf548b +--- /dev/null ++++ b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-blade.dts +@@ -0,0 +1,194 @@ ++// SPDX-License-Identifier: (GPL-2.0+ OR MIT) ++ ++/dts-v1/; ++ ++#include <dt-bindings/gpio/gpio.h> ++#include <dt-bindings/input/input.h> ++#include <dt-bindings/leds/common.h> ++#include <dt-bindings/pinctrl/rockchip.h> ++ ++#include "rk3566-soquartz.dtsi" ++ ++/ { ++ model = "PINE64 RK3566 SOQuartz on Blade carrier board"; ++ compatible = "pine64,soquartz-blade", "pine64,soquartz", "rockchip,rk3566"; ++ ++ /* labeled VCC3V0_SD in schematic to not conflict with PMIC regulator */ ++ vcc3v0_sd: vcc3v0-sd-regulator { ++ compatible = "regulator-fixed"; ++ regulator-name = "vcc3v0_sd"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <3300000>; ++ regulator-max-microvolt = <3300000>; ++ vin-supply = <&vcc3v3_sys>; ++ }; ++ ++ /* labeled VCC_SSD in schematic */ ++ vcc3v3_pcie_p: vcc3v3-pcie-regulator { ++ compatible = "regulator-fixed"; ++ regulator-name = "vcc3v3_pcie_p"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <3300000>; ++ regulator-max-microvolt = <3300000>; ++ vin-supply = <&vbus>; ++ }; ++ ++ vcc5v_dcin: vcc5v-dcin-regulator { ++ compatible = "regulator-fixed"; ++ regulator-name = "vcc5v_dcin"; ++ regulator-always-on; ++ regulator-boot-on; ++ regulator-min-microvolt = <5000000>; ++ regulator-max-microvolt = <5000000>; ++ }; ++}; ++ ++&combphy2 { ++ phy-supply = <&vcc3v3_sys>; ++ status = "okay"; ++}; ++ ++&gmac1 { ++ status = "okay"; ++}; ++ ++/* ++ * i2c1 is exposed on CM1 / Module1A ++ * pin 80 - SCL0 - i2c1_scl_m0, pullup to vcc3v3_pmu ++ * pin 82 - SDA0 - i2c1_sda_m0, pullup to vcc3v3_pmu ++ */ ++&i2c1 { ++ status = "okay"; ++ ++}; ++ ++/* ++ * i2c2 is exposed on CM1 / Module1A - to PI40 ++ * pin 56 - GPIO3 - i2c2_scl_m1, pullup to vcc_3v3, shared with i2s1_8ch ++ * pin 58 - GPIO2 - i2c2_sda_m1, pullup to vcc_3v3 ++ */ ++&i2c2 { ++ status = "disabled"; ++}; ++ ++/* ++ * i2c3 is exposed on CM1 / Module1A - to PI40 ++ * pin 35 - ID_SC(GPIO28) - i2c3_scl_m0, pullup to vcc_3v3 ++ * pin 36 - ID_SD(GPIO27) - i2c3_sda_m0, pullup to vcc_3v3 ++ */ ++&i2c3 { ++ status = "disabled"; ++}; ++ ++/* ++ * i2c4 is exposed on CM2 / Module1B - to PI40 ++ * pin 45 - GPIO24 - i2c4_scl_m1 ++ * pin 47 - GPIO23 - i2c4_sda_m1 ++ */ ++&i2c4 { ++ status = "disabled"; ++}; ++ ++/* ++ * i2s1_8ch is exposed on CM1 / Module1A - to PI40 ++ * pin 24 - GPIO26 - i2s1_sdi1_m1 ++ * pin 25 - GPIO21 - i2s1_sdo0_m1 ++ * pin 26 - GPIO19 - i2s1_lrck_tx_m1 ++ * pin 27 - GPIO20 - i2s1_sdi0_m1 ++ * pin 29 - GPIO16 - i2s1_sdi3_m1 ++ * pin 30 - GPIO6 - i2s1_sdi2_m1 ++ * pin 40 - GPIO9 - i2s1_sdo1_m1, shared with spi3 ++ * pin 41 - GPIO25 - i2s1_sdo2_m1 ++ * pin 49 - GPIO18 - i2s1_sclk_tx_m1 ++ * pin 50 - GPIO17 - i2s1_mclk_m1 ++ * pin 56 - GPIO3 - i2s1_sdo3_m1, shared with i2c2 ++ */ ++&i2s1_8ch { ++ status = "disabled"; ++}; ++ ++&led_diy { ++ color = <LED_COLOR_ID_RED>; ++ function = LED_FUNCTION_DISK_ACTIVITY; ++ linux,default-trigger = "disk-activity"; ++ status = "okay"; ++}; ++ ++&led_work { ++ color = <LED_COLOR_ID_GREEN>; ++ function = LED_FUNCTION_STATUS; ++ linux,default-trigger = "heartbeat"; ++ status = "okay"; ++}; ++ ++&pcie2x1 { ++ vpcie3v3-supply = <&vcc3v3_pcie_p>; ++ status = "okay"; ++}; ++ ++&rgmii_phy1 { ++ status = "okay"; ++}; ++ ++/* ++ * saradc is exposed on CM1 / Module1A - to J2 ++ * pin 94 - AIN1 - saradc_vin3 ++ * pin 96 - AIN0 - saradc_vin2 ++ */ ++&saradc { ++ status = "disabled"; ++}; ++ ++&sdmmc0 { ++ vmmc-supply = <&vcc3v0_sd>; ++ status = "okay"; ++}; ++ ++/* ++ * spi3 is exposed on CM1 / Module1A - to PI40 ++ * pin 37 - GPIO7 - spi3_cs1_m0 ++ * pin 38 - GPIO11 - spi3_clk_m0 ++ * pin 39 - GPIO8 - spi3_cs0_m0 ++ * pin 40 - GPIO9 - spi3_miso_m0, shared with i2s1_8ch ++ * pin 44 - GPIO10 - spi3_mosi_m0 ++ */ ++&spi3 { ++ status = "disabled"; ++}; ++ ++/* ++ * uart2 is exposed on CM1 / Module1A - to PI40 ++ * pin 51 - GPIO15 - uart2_rx_m0 ++ * pin 55 - GPIO14 - uart2_tx_m0 ++ */ ++&uart2 { ++ status = "okay"; ++}; ++ ++/* ++ * uart7 is exposed on CM1 / Module1A - to PI40 ++ * pin 46 - GPIO22 - uart7_tx_m2 ++ * pin 47 - GPIO23 - uart7_rx_m2 ++ */ ++&uart7 { ++ status = "okay"; ++}; ++ ++&usb2phy0 { ++ status = "okay"; ++}; ++ ++&usb2phy0_otg { ++ phy-supply = <&vbus>; ++ status = "okay"; ++}; ++ ++&usb_host0_xhci { ++ status = "okay"; ++}; ++ ++&vbus { ++ vin-supply = <&vcc5v_dcin>; ++}; +-- +2.39.0 + diff --git a/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-Enable-HDMI-sound-on-SOQuartz.patch b/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-Enable-HDMI-sound-on-SOQuartz.patch new file mode 100644 index 000000000..d4df69e16 --- /dev/null +++ b/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-Enable-HDMI-sound-on-SOQuartz.patch @@ -0,0 +1,44 @@ +From: Nicolas Frattaroli <frattaroli.nicolas@gmail.com> +Date: Sat, 12 Nov 2022 17:04:00 +0100 +Subject: arm64: dts: rockchip: Enable HDMI sound on SOQuartz +Origin: https://git.kernel.org/linus/70b620c4ba919a87c607b8d98b08478b213877bd + +This patch enables the i2s0 node on SOQuartz, which is responsible +for hdmi audio, and adds an hdmi-sound node to enable said audio. + +Signed-off-by: Nicolas Frattaroli <frattaroli.nicolas@gmail.com> +Link: https://lore.kernel.org/r/20221112160404.70868-4-frattaroli.nicolas@gmail.com +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi | 8 ++++++++ + 1 file changed, 8 insertions(+) + +diff --git a/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi +index 0bfb0cea7d6b..1b975822effa 100644 +--- a/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi ++++ b/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi +@@ -178,6 +178,10 @@ + }; + }; + ++&hdmi_sound { ++ status = "okay"; ++}; ++ + &i2c0 { + status = "okay"; + +@@ -446,6 +450,10 @@ + status = "disabled"; + }; + ++&i2s0_8ch { ++ status = "okay"; ++}; ++ + /* + * i2s1_8ch is exposed on CM1 / Module1A + * pin 24 - i2s1_sdi1_m1 +-- +2.39.0 + diff --git a/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-Enable-PCIe-2-on-SOQuartz-CM4IO.patch b/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-Enable-PCIe-2-on-SOQuartz-CM4IO.patch new file mode 100644 index 000000000..1a8063e0f --- /dev/null +++ b/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-Enable-PCIe-2-on-SOQuartz-CM4IO.patch @@ -0,0 +1,82 @@ +From: Nicolas Frattaroli <frattaroli.nicolas@gmail.com> +Date: Sat, 12 Nov 2022 17:04:01 +0100 +Subject: arm64: dts: rockchip: Enable PCIe 2 on SOQuartz CM4IO +Origin: https://git.kernel.org/linus/3736aa7ecc4cd9b4abce30052bad00aba4f0362f + +This patch enables the PCIe2 on the CM4IO board when paired with +a SOQuartz CM4 System-on-Module board. combphy2 also needs to be +enabled in this case to make the PHY work for this. + +Signed-off-by: Nicolas Frattaroli <frattaroli.nicolas@gmail.com> +Link: https://lore.kernel.org/r/20221112160404.70868-5-frattaroli.nicolas@gmail.com +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + .../boot/dts/rockchip/rk3566-soquartz-cm4.dts | 11 +++++++++++ + arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi | 15 +++++++++++++++ + 2 files changed, 26 insertions(+) + +diff --git a/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts +index e00568a6be5c..263ce40770dd 100644 +--- a/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts ++++ b/arch/arm64/boot/dts/rockchip/rk3566-soquartz-cm4.dts +@@ -30,6 +30,12 @@ + }; + }; + ++/* phy for pcie */ ++&combphy2 { ++ phy-supply = <&vcc3v3_sys>; ++ status = "okay"; ++}; ++ + &gmac1 { + status = "okay"; + }; +@@ -105,6 +111,11 @@ + status = "okay"; + }; + ++&pcie2x1 { ++ vpcie3v3-supply = <&vcc_3v3>; ++ status = "okay"; ++}; ++ + &rgmii_phy1 { + status = "okay"; + }; +diff --git a/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi +index 1b975822effa..ce7165d7f1a1 100644 +--- a/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi ++++ b/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi +@@ -487,6 +487,12 @@ + }; + }; + ++&pcie2x1 { ++ pinctrl-names = "default"; ++ pinctrl-0 = <&pcie_reset_h>; ++ reset-gpios = <&gpio1 RK_PB2 GPIO_ACTIVE_HIGH>; ++}; ++ + &pinctrl { + bt { + bt_enable_h: bt-enable-h { +@@ -512,6 +518,15 @@ + }; + }; + ++ pcie { ++ pcie_clkreq_h: pcie-clkreq-h { ++ rockchip,pins = <1 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>; ++ }; ++ pcie_reset_h: pcie-reset-h { ++ rockchip,pins = <1 RK_PB2 RK_FUNC_GPIO &pcfg_pull_none>; ++ }; ++ }; ++ + pmic { + pmic_int_l: pmic-int-l { + rockchip,pins = <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>; +-- +2.39.0 + diff --git a/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-Enable-video-output-and-HDMI-on-S.patch b/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-Enable-video-output-and-HDMI-on-S.patch new file mode 100644 index 000000000..37cfbdb23 --- /dev/null +++ b/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-Enable-video-output-and-HDMI-on-S.patch @@ -0,0 +1,94 @@ +From: Nicolas Frattaroli <frattaroli.nicolas@gmail.com> +Date: Sat, 12 Nov 2022 17:03:59 +0100 +Subject: arm64: dts: rockchip: Enable video output and HDMI on SOQuartz +Origin: https://git.kernel.org/linus/36d7a605706d9648526a0574b8e7b0e02fa70c2a + +This patch adds and enables the necessary device tree nodes to +enable video output and HDMI functionality on the SOQuartz module. + +Signed-off-by: Nicolas Frattaroli <frattaroli.nicolas@gmail.com> +Link: https://lore.kernel.org/r/20221112160404.70868-3-frattaroli.nicolas@gmail.com +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + .../boot/dts/rockchip/rk3566-soquartz.dtsi | 47 +++++++++++++++++++ + 1 file changed, 47 insertions(+) + +diff --git a/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi +index 6e99f049501c..0bfb0cea7d6b 100644 +--- a/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi ++++ b/arch/arm64/boot/dts/rockchip/rk3566-soquartz.dtsi +@@ -4,6 +4,7 @@ + + #include <dt-bindings/gpio/gpio.h> + #include <dt-bindings/pinctrl/rockchip.h> ++#include <dt-bindings/soc/rockchip,vop2.h> + #include "rk3566.dtsi" + + / { +@@ -28,6 +29,17 @@ + #clock-cells = <0>; + }; + ++ hdmi-con { ++ compatible = "hdmi-connector"; ++ type = "a"; ++ ++ port { ++ hdmi_con_in: endpoint { ++ remote-endpoint = <&hdmi_out_con>; ++ }; ++ }; ++ }; ++ + leds { + compatible = "gpio-leds"; + +@@ -148,6 +160,24 @@ + status = "okay"; + }; + ++&hdmi { ++ avdd-0v9-supply = <&vdda0v9_image>; ++ avdd-1v8-supply = <&vcca1v8_image>; ++ status = "okay"; ++}; ++ ++&hdmi_in { ++ hdmi_in_vp0: endpoint { ++ remote-endpoint = <&vp0_out_hdmi>; ++ }; ++}; ++ ++&hdmi_out { ++ hdmi_out_con: endpoint { ++ remote-endpoint = <&hdmi_con_in>; ++ }; ++}; ++ + &i2c0 { + status = "okay"; + +@@ -619,3 +649,20 @@ + &usb_host0_xhci { + status = "disabled"; + }; ++ ++&vop { ++ assigned-clocks = <&cru DCLK_VOP0>, <&cru DCLK_VOP1>; ++ assigned-clock-parents = <&pmucru PLL_HPLL>, <&cru PLL_VPLL>; ++ status = "okay"; ++}; ++ ++&vop_mmu { ++ status = "okay"; ++}; ++ ++&vp0 { ++ vp0_out_hdmi: endpoint@ROCKCHIP_VOP2_EP_HDMI0 { ++ reg = <ROCKCHIP_VOP2_EP_HDMI0>; ++ remote-endpoint = <&hdmi_in_vp0>; ++ }; ++}; +-- +2.39.0 + diff --git a/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-RK356x-Add-I2S2-device-node.patch b/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-RK356x-Add-I2S2-device-node.patch new file mode 100644 index 000000000..55c6af80b --- /dev/null +++ b/debian/patches/features/arm64/quartz64/arm64-dts-rockchip-RK356x-Add-I2S2-device-node.patch @@ -0,0 +1,50 @@ +From: Shengyu Qu <wiagn233@outlook.com> +Date: Sun, 30 Oct 2022 01:09:04 +0800 +Subject: arm64: dts: rockchip: RK356x: Add I2S2 device node +Origin: https://git.kernel.org/linus/755f37010f3eac0bdfa41bdf2308e8380a93f10c + +This patch adds I2S2 device tree node for RK3566/RK3568. + +Signed-off-by: Shengyu Qu <wiagn233@outlook.com> +Link: https://lore.kernel.org/r/OS3P286MB259771C12F2B15A4DDF435FE98359@OS3P286MB2597.JPNP286.PROD.OUTLOOK.COM +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + arch/arm64/boot/dts/rockchip/rk356x.dtsi | 22 ++++++++++++++++++++++ + 1 file changed, 22 insertions(+) + +diff --git a/arch/arm64/boot/dts/rockchip/rk356x.dtsi b/arch/arm64/boot/dts/rockchip/rk356x.dtsi +index 10e3a0862602..5706c3e24f0a 100644 +--- a/arch/arm64/boot/dts/rockchip/rk356x.dtsi ++++ b/arch/arm64/boot/dts/rockchip/rk356x.dtsi +@@ -1091,6 +1091,28 @@ + status = "disabled"; + }; + ++ i2s2_2ch: i2s@fe420000 { ++ compatible = "rockchip,rk3568-i2s-tdm"; ++ reg = <0x0 0xfe420000 0x0 0x1000>; ++ interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>; ++ assigned-clocks = <&cru CLK_I2S2_2CH_SRC>; ++ assigned-clock-rates = <1188000000>; ++ clocks = <&cru MCLK_I2S2_2CH>, <&cru MCLK_I2S2_2CH>, <&cru HCLK_I2S2_2CH>; ++ clock-names = "mclk_tx", "mclk_rx", "hclk"; ++ dmas = <&dmac1 4>, <&dmac1 5>; ++ dma-names = "tx", "rx"; ++ resets = <&cru SRST_M_I2S2_2CH>; ++ reset-names = "m"; ++ rockchip,grf = <&grf>; ++ pinctrl-names = "default"; ++ pinctrl-0 = <&i2s2m0_sclktx ++ &i2s2m0_lrcktx ++ &i2s2m0_sdi ++ &i2s2m0_sdo>; ++ #sound-dai-cells = <0>; ++ status = "disabled"; ++ }; ++ + i2s3_2ch: i2s@fe430000 { + compatible = "rockchip,rk3568-i2s-tdm"; + reg = <0x0 0xfe430000 0x0 0x1000>; +-- +2.39.0 + diff --git a/debian/patches/features/arm64/quartz64/dt-bindings-arm-rockchip-Add-SOQuartz-Blade.patch b/debian/patches/features/arm64/quartz64/dt-bindings-arm-rockchip-Add-SOQuartz-Blade.patch new file mode 100644 index 000000000..52fdca25d --- /dev/null +++ b/debian/patches/features/arm64/quartz64/dt-bindings-arm-rockchip-Add-SOQuartz-Blade.patch @@ -0,0 +1,39 @@ +From: Nicolas Frattaroli <frattaroli.nicolas@gmail.com> +Date: Wed, 16 Nov 2022 12:53:34 +0100 +Subject: [1/4] dt-bindings: arm: rockchip: Add SOQuartz Blade +Origin: https://git.kernel.org/linus/8c84c2e51f3ee39b40e8078ebe3ad9c01fb17aff + +Add a compatible for the SOQuartz Blade base board to the rockchip +platforms binding. + +The SOQuartz Blade is a PoE-capable carrier board for the CM4 SoM +form factor, designed around the SOQuartz CM4 System-on-Module. + +The board features the usual connectivity (GPIO, USB, HDMI, +Ethernet) and an M.2 slot for SSDs. It may also be powered from +a 5V barrel jack input, and has a 3.5mm jack for UART debug +output. + +Signed-off-by: Nicolas Frattaroli <frattaroli.nicolas@gmail.com> +Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +Link: https://lore.kernel.org/r/20221116115337.541601-2-frattaroli.nicolas@gmail.com +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + Documentation/devicetree/bindings/arm/rockchip.yaml | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/Documentation/devicetree/bindings/arm/rockchip.yaml b/Documentation/devicetree/bindings/arm/rockchip.yaml +index 3f31115ee99a..42f33240ade8 100644 +--- a/Documentation/devicetree/bindings/arm/rockchip.yaml ++++ b/Documentation/devicetree/bindings/arm/rockchip.yaml +@@ -593,6 +593,7 @@ properties: + - description: Pine64 SoQuartz SoM + items: + - enum: ++ - pine64,soquartz-blade + - pine64,soquartz-cm4io + - const: pine64,soquartz + - const: rockchip,rk3566 +-- +2.39.0 + diff --git a/debian/patches/features/arm64/quartz64/dt-bindings-arm-rockchip-Add-SOQuartz-Model-A.patch b/debian/patches/features/arm64/quartz64/dt-bindings-arm-rockchip-Add-SOQuartz-Model-A.patch new file mode 100644 index 000000000..2983e8a88 --- /dev/null +++ b/debian/patches/features/arm64/quartz64/dt-bindings-arm-rockchip-Add-SOQuartz-Model-A.patch @@ -0,0 +1,39 @@ +From: Nicolas Frattaroli <frattaroli.nicolas@gmail.com> +Date: Wed, 16 Nov 2022 12:53:36 +0100 +Subject: [3/4] dt-bindings: arm: rockchip: Add SOQuartz Model A +Origin: https://git.kernel.org/linus/7441d8c437883581dddfb616a087b399338244f0 + +The SOQuartz Model A base board is a carrier board for the CM4 +form factor, designed around the PINE64 SOQuartz CM4 SoM. + +The board sports "Model A" dimensions like the Quartz64 Model A, +but is not to be confused with that. + +As for I/O, it features USB 2 ports, Gigabit Ethernet, a PCIe 2 +x1 slot, HDMI, a 40-pin GPIO header, CSI/DSI connectors, an eDP +flat-flex cable connector, a 12V DC barrel jack for power input +and power/reset buttons as well as a microSD card slot. + +Signed-off-by: Nicolas Frattaroli <frattaroli.nicolas@gmail.com> +Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +Link: https://lore.kernel.org/r/20221116115337.541601-4-frattaroli.nicolas@gmail.com +Signed-off-by: Heiko Stuebner <heiko@sntech.de> +--- + Documentation/devicetree/bindings/arm/rockchip.yaml | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/Documentation/devicetree/bindings/arm/rockchip.yaml b/Documentation/devicetree/bindings/arm/rockchip.yaml +index 42f33240ade8..88ff4422a8c1 100644 +--- a/Documentation/devicetree/bindings/arm/rockchip.yaml ++++ b/Documentation/devicetree/bindings/arm/rockchip.yaml +@@ -595,6 +595,7 @@ properties: + - enum: + - pine64,soquartz-blade + - pine64,soquartz-cm4io ++ - pine64,soquartz-model-a + - const: pine64,soquartz + - const: rockchip,rk3566 + +-- +2.39.0 + diff --git a/debian/patches/features/x86/intel-iommu-add-kconfig-option-to-exclude-igpu-by-default.patch b/debian/patches/features/x86/intel-iommu-add-kconfig-option-to-exclude-igpu-by-default.patch new file mode 100644 index 000000000..ff2fdadc4 --- /dev/null +++ b/debian/patches/features/x86/intel-iommu-add-kconfig-option-to-exclude-igpu-by-default.patch @@ -0,0 +1,76 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Wed, 21 Aug 2019 00:32:16 +0100 +Subject: intel-iommu: Add Kconfig option to exclude iGPU by default +Bug-Debian: https://bugs.debian.org/935270 +Bug-Kali: https://bugs.kali.org/view.php?id=5644 + +There is still laptop firmware that touches the integrated GPU behind +the operating system's back, and doesn't say so in the RMRR table. +Enabling the IOMMU for all devices causes breakage. + +Replace CONFIG_INTEL_IOMMU_DEFAULT_ON with a 3-way choice +corresponding to "on", "off", and "on,intgpu_off". + +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- +--- a/drivers/iommu/intel/Kconfig ++++ b/drivers/iommu/intel/Kconfig +@@ -56,14 +56,25 @@ config INTEL_IOMMU_SVM + to access DMA resources through process address space by + means of a Process Address Space ID (PASID). + +-config INTEL_IOMMU_DEFAULT_ON +- bool "Enable Intel DMA Remapping Devices by default" +- default y ++choice ++ prompt "Default state of Intel DMA Remapping Devices" ++ default INTEL_IOMMU_DEFAULT_ON + help +- Selecting this option will enable a DMAR device at boot time if +- one is found. If this option is not selected, DMAR support can +- be enabled by passing intel_iommu=on to the kernel. ++ Choose whether Intel DMA Remapping Devices should be enabled ++ by default. This can be overridden at boot time using the ++ intel_iommu= kernel parameter. ++ ++config INTEL_IOMMU_DEFAULT_ON ++ bool "Enable" ++ ++config INTEL_IOMMU_DEFAULT_ON_INTGPU_OFF ++ bool "Enable, excluding integrated GPU" ++ ++config INTEL_IOMMU_DEFAULT_OFF ++ bool "Disable" + ++endchoice ++ + config INTEL_IOMMU_BROKEN_GFX_WA + bool "Workaround broken graphics drivers (going away soon)" + depends on BROKEN && X86 +--- a/drivers/iommu/intel/iommu.c ++++ b/drivers/iommu/intel/iommu.c +@@ -282,14 +282,14 @@ static LIST_HEAD(dmar_satc_units); + + static void device_block_translation(struct device *dev); + +-int dmar_disabled = !IS_ENABLED(CONFIG_INTEL_IOMMU_DEFAULT_ON); ++int dmar_disabled = IS_ENABLED(CONFIG_INTEL_IOMMU_DEFAULT_OFF); + int intel_iommu_sm = IS_ENABLED(CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON); + + int intel_iommu_enabled = 0; + EXPORT_SYMBOL_GPL(intel_iommu_enabled); + + static int dmar_map_gfx = 1; +-static int dmar_map_intgpu = 1; ++static int dmar_map_intgpu = IS_ENABLED(CONFIG_INTEL_IOMMU_DEFAULT_ON); + static int intel_iommu_superpage = 1; + static int iommu_identity_mapping; + static int iommu_skip_te_disable; +@@ -327,6 +327,7 @@ static int __init intel_iommu_setup(char + while (*str) { + if (!strncmp(str, "on", 2)) { + dmar_disabled = 0; ++ dmar_map_intgpu = 1; + pr_info("IOMMU enabled\n"); + } else if (!strncmp(str, "off", 3)) { + dmar_disabled = 1; diff --git a/debian/patches/features/x86/intel-iommu-add-option-to-exclude-integrated-gpu-only.patch b/debian/patches/features/x86/intel-iommu-add-option-to-exclude-integrated-gpu-only.patch new file mode 100644 index 000000000..a3543d90e --- /dev/null +++ b/debian/patches/features/x86/intel-iommu-add-option-to-exclude-integrated-gpu-only.patch @@ -0,0 +1,90 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Wed, 21 Aug 2019 00:05:30 +0100 +Subject: intel-iommu: Add option to exclude integrated GPU only +Bug-Debian: https://bugs.debian.org/935270 +Bug-Kali: https://bugs.kali.org/view.php?id=5644 + +There is still laptop firmware that touches the integrated GPU behind +the operating system's back, and doesn't say so in the RMRR table. +Enabling the IOMMU for all devices causes breakage, but turning it off +for all graphics devices seems like a major weakness. + +Add an option, intel_iommu=intgpu_off, to exclude only integrated GPUs +from remapping. This is a narrower exclusion than igfx_off: it only +affects Intel devices on the root bus. Devices attached through an +external port (Thunderbolt or ExpressCard) won't be on the root bus. + +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- + Documentation/admin-guide/kernel-parameters.txt | 2 ++ + drivers/iommu/intel/iommu.c | 14 ++++++++++++++ + 2 files changed, 16 insertions(+) + +--- a/Documentation/admin-guide/kernel-parameters.txt ++++ b/Documentation/admin-guide/kernel-parameters.txt +@@ -2053,6 +2053,8 @@ + bypassed by not enabling DMAR with this option. In + this case, gfx device will use physical address for + DMA. ++ intgpu_off [Default Off] ++ Bypass the DMAR unit for an integrated GPU only. + strict [Default Off] + Deprecated, equivalent to iommu.strict=1. + sp_off [Default Off] +--- a/drivers/iommu/intel/iommu.c ++++ b/drivers/iommu/intel/iommu.c +@@ -35,6 +35,9 @@ + #define CONTEXT_SIZE VTD_PAGE_SIZE + + #define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY) ++#define IS_INTGPU_DEVICE(pdev) (IS_GFX_DEVICE(pdev) && \ ++ (pdev)->vendor == 0x8086 && \ ++ pci_is_root_bus((pdev)->bus)) + #define IS_USB_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_SERIAL_USB) + #define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA) + #define IS_AZALIA(pdev) ((pdev)->vendor == 0x8086 && (pdev)->device == 0x3a3e) +@@ -293,12 +296,14 @@ int intel_iommu_enabled = 0; + EXPORT_SYMBOL_GPL(intel_iommu_enabled); + + static int dmar_map_gfx = 1; ++static int dmar_map_intgpu = 1; + static int intel_iommu_superpage = 1; + static int iommu_identity_mapping; + static int iommu_skip_te_disable; + + #define IDENTMAP_GFX 2 + #define IDENTMAP_AZALIA 4 ++#define IDENTMAP_INTGPU 8 + + const struct iommu_ops intel_iommu_ops; + +@@ -337,6 +342,9 @@ static int __init intel_iommu_setup(char + } else if (!strncmp(str, "igfx_off", 8)) { + dmar_map_gfx = 0; + pr_info("Disable GFX device mapping\n"); ++ } else if (!strncmp(str, "intgpu_off", 10)) { ++ dmar_map_intgpu = 0; ++ pr_info("Disable integrated GPU device mapping\n"); + } else if (!strncmp(str, "forcedac", 8)) { + pr_warn("intel_iommu=forcedac deprecated; use iommu.forcedac instead\n"); + iommu_dma_forcedac = true; +@@ -2582,6 +2590,9 @@ static int device_def_domain_type(struct + + if ((iommu_identity_mapping & IDENTMAP_GFX) && IS_GFX_DEVICE(pdev)) + return IOMMU_DOMAIN_IDENTITY; ++ ++ if ((iommu_identity_mapping & IDENTMAP_INTGPU) && IS_INTGPU_DEVICE(pdev)) ++ return IOMMU_DOMAIN_IDENTITY; + } + + return 0; +@@ -2985,6 +2996,9 @@ static int __init init_dmars(void) + if (!dmar_map_gfx) + iommu_identity_mapping |= IDENTMAP_GFX; + ++ if (!dmar_map_intgpu) ++ iommu_identity_mapping |= IDENTMAP_INTGPU; ++ + check_tylersburg_isoch(); + + ret = si_domain_init(hw_pass_through); diff --git a/debian/patches/features/x86/x86-make-x32-syscall-support-conditional.patch b/debian/patches/features/x86/x86-make-x32-syscall-support-conditional.patch new file mode 100644 index 000000000..44dd25261 --- /dev/null +++ b/debian/patches/features/x86/x86-make-x32-syscall-support-conditional.patch @@ -0,0 +1,180 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Mon, 12 Feb 2018 23:59:26 +0000 +Subject: x86: Make x32 syscall support conditional on a kernel parameter +Bug-Debian: https://bugs.debian.org/708070 +Forwarded: https://lore.kernel.org/lkml/1415245982.3398.53.camel@decadent.org.uk/T/#u + +Enabling x32 in the standard amd64 kernel would increase its attack +surface while provide no benefit to the vast majority of its users. +No-one seems interested in regularly checking for vulnerabilities +specific to x32 (at least no-one with a white hat). + +Still, adding another flavour just to turn on x32 seems wasteful. And +the only differences on syscall entry are a few instructions that mask +out the x32 flag and compare the syscall number. + +Use a static key to control whether x32 syscalls are really enabled, a +Kconfig parameter to set its default value and a kernel parameter +"syscall.x32" to change it at boot time. + +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- + .../admin-guide/kernel-parameters.txt | 4 ++ + arch/x86/Kconfig | 8 ++++ + arch/x86/entry/common.c | 3 +- + arch/x86/entry/syscall_64.c | 46 +++++++++++++++++++ + arch/x86/include/asm/elf.h | 6 ++- + arch/x86/include/asm/syscall.h | 13 ++++++ + 6 files changed, 78 insertions(+), 2 deletions(-) + +--- a/Documentation/admin-guide/kernel-parameters.txt ++++ b/Documentation/admin-guide/kernel-parameters.txt +@@ -5768,6 +5768,10 @@ + later by a loaded module cannot be set this way. + Example: sysctl.vm.swappiness=40 + ++ syscall.x32= [KNL,x86_64] Enable/disable use of x32 syscalls on ++ an x86_64 kernel where CONFIG_X86_X32 is enabled. ++ Default depends on CONFIG_X86_X32_DISABLED. ++ + sysfs.deprecated=0|1 [KNL] + Enable/disable old style sysfs layout for old udev + on older distributions. When this option is enabled +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -2865,6 +2865,14 @@ config COMPAT_32 + select HAVE_UID16 + select OLD_SIGSUSPEND3 + ++config X86_X32_DISABLED ++ bool "x32 ABI disabled by default" ++ depends on X86_X32_ABI ++ default n ++ help ++ Disable the x32 ABI unless explicitly enabled using the ++ kernel paramter "syscall.x32=y". ++ + config COMPAT + def_bool y + depends on IA32_EMULATION || X86_X32_ABI +--- a/arch/x86/entry/common.c ++++ b/arch/x86/entry/common.c +@@ -62,7 +62,7 @@ static __always_inline bool do_syscall_x + */ + unsigned int xnr = nr - __X32_SYSCALL_BIT; + +- if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) { ++ if (IS_ENABLED(CONFIG_X86_X32_ABI) && unlikely(x32_enabled) && likely(xnr < X32_NR_syscalls)) { + xnr = array_index_nospec(xnr, X32_NR_syscalls); + regs->ax = x32_sys_call_table[xnr](regs); + return true; +--- a/arch/x86/entry/syscall_x32.c ++++ b/arch/x86/entry/syscall_x32.c +@@ -4,6 +4,9 @@ + #include <linux/linkage.h> + #include <linux/sys.h> + #include <linux/cache.h> ++#include <linux/moduleparam.h> ++#undef MODULE_PARAM_PREFIX ++#define MODULE_PARAM_PREFIX "syscall." + #include <linux/syscalls.h> + #include <asm/syscall.h> + +@@ -16,3 +19,46 @@ + asmlinkage const sys_call_ptr_t x32_sys_call_table[] = { + #include <asm/syscalls_x32.h> + }; ++ ++/* Maybe enable x32 syscalls */ ++ ++#if defined(CONFIG_X86_X32_DISABLED) ++DEFINE_STATIC_KEY_FALSE(x32_enabled_skey); ++#else ++DEFINE_STATIC_KEY_TRUE(x32_enabled_skey); ++#endif ++ ++static int __init x32_param_set(const char *val, const struct kernel_param *p) ++{ ++ bool enabled; ++ int ret; ++ ++ ret = kstrtobool(val, &enabled); ++ if (ret) ++ return ret; ++ if (IS_ENABLED(CONFIG_X86_X32_DISABLED)) { ++ if (enabled) { ++ static_key_enable(&x32_enabled_skey.key); ++ pr_info("Enabled x32 syscalls\n"); ++ } ++ } else { ++ if (!enabled) { ++ static_key_disable(&x32_enabled_skey.key); ++ pr_info("Disabled x32 syscalls\n"); ++ } ++ } ++ return 0; ++} ++ ++static int x32_param_get(char *buffer, const struct kernel_param *p) ++{ ++ return sprintf(buffer, "%c\n", ++ static_key_enabled(&x32_enabled_skey) ? 'Y' : 'N'); ++} ++ ++static const struct kernel_param_ops x32_param_ops = { ++ .set = x32_param_set, ++ .get = x32_param_get, ++}; ++ ++arch_param_cb(x32, &x32_param_ops, NULL, 0444); +--- a/arch/x86/include/asm/elf.h ++++ b/arch/x86/include/asm/elf.h +@@ -11,6 +11,9 @@ + #include <asm/user.h> + #include <asm/auxvec.h> + #include <asm/fsgsbase.h> ++#ifndef COMPILE_OFFSETS /* avoid a circular dependency on asm-offsets.h */ ++#include <asm/syscall.h> ++#endif + + typedef unsigned long elf_greg_t; + +@@ -161,7 +164,8 @@ do { \ + + #define compat_elf_check_arch(x) \ + (elf_check_arch_ia32(x) || \ +- (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64)) ++ (IS_ENABLED(CONFIG_X86_X32_ABI) && x32_enabled && \ ++ (x)->e_machine == EM_X86_64)) + + #if __USER32_DS != __USER_DS + # error "The following code assumes __USER32_DS == __USER_DS" +--- a/arch/x86/include/asm/syscall.h ++++ b/arch/x86/include/asm/syscall.h +@@ -13,6 +13,7 @@ + #include <uapi/linux/audit.h> + #include <linux/sched.h> + #include <linux/err.h> ++#include <linux/jump_label.h> + #include <asm/thread_info.h> /* for TS_COMPAT */ + #include <asm/unistd.h> + +@@ -30,6 +31,18 @@ extern const sys_call_ptr_t ia32_sys_cal + extern const sys_call_ptr_t x32_sys_call_table[]; + #endif + ++#if defined(CONFIG_X86_X32_ABI) ++#if defined(CONFIG_X86_X32_DISABLED) ++DECLARE_STATIC_KEY_FALSE(x32_enabled_skey); ++#define x32_enabled static_branch_unlikely(&x32_enabled_skey) ++#else ++DECLARE_STATIC_KEY_TRUE(x32_enabled_skey); ++#define x32_enabled static_branch_likely(&x32_enabled_skey) ++#endif ++#else ++#define x32_enabled 0 ++#endif ++ + /* + * Only the low 32 bits of orig_ax are meaningful, so we return int. + * This importantly ignores the high bits on 64-bit, so comparisons diff --git a/debian/patches/features/x86/x86-memtest-WARN-if-bad-RAM-found.patch b/debian/patches/features/x86/x86-memtest-WARN-if-bad-RAM-found.patch new file mode 100644 index 000000000..7a7952003 --- /dev/null +++ b/debian/patches/features/x86/x86-memtest-WARN-if-bad-RAM-found.patch @@ -0,0 +1,28 @@ +From: Ben Hutchings <ben@decadent.org.uk> +Date: Mon, 5 Dec 2011 04:00:58 +0000 +Subject: x86: memtest: WARN if bad RAM found +Bug-Debian: https://bugs.debian.org/613321 +Forwarded: http://thread.gmane.org/gmane.linux.kernel/1286471 + +Since this is not a particularly thorough test, if we find any bad +bits of RAM then there is a fair chance that there are other bad bits +we fail to detect. + +Signed-off-by: Ben Hutchings <ben@decadent.org.uk> +--- + mm/memtest.c | 2 ++ + 1 files changed, 2 insertions(+), 0 deletions(-) + +--- a/mm/memtest.c ++++ b/mm/memtest.c +@@ -26,6 +26,10 @@ static u64 patterns[] __initdata = { + + static void __init reserve_bad_mem(u64 pattern, phys_addr_t start_bad, phys_addr_t end_bad) + { ++#ifdef CONFIG_X86 ++ WARN_ONCE(1, "Bad RAM detected. Use memtest86+ to perform a thorough test\n" ++ "and the memmap= parameter to reserve the bad areas."); ++#endif + pr_info(" %016llx bad mem addr %pa - %pa reserved\n", + cpu_to_be64(pattern), &start_bad, &end_bad); + memblock_reserve(start_bad, end_bad - start_bad); diff --git a/debian/patches/series b/debian/patches/series new file mode 100644 index 000000000..f31b433c2 --- /dev/null +++ b/debian/patches/series @@ -0,0 +1,175 @@ +debian/gitignore.patch + +# Disable features broken by exclusion of upstream files +debian/dfsg/arch-powerpc-platforms-8xx-ucode-disable.patch +debian/dfsg/drivers-media-dvb-dvb-usb-af9005-disable.patch +debian/dfsg/vs6624-disable.patch +debian/dfsg/drivers-net-appletalk-cops.patch +debian/dfsg/video-remove-nvidiafb-and-rivafb.patch +debian/dfsg/documentation-fix-broken-link-to-cipso-draft.patch + +# Changes to support package build system +debian/version.patch +debian/uname-version-timestamp.patch +debian/kernelvariables.patch +debian/ia64-hardcode-arch-script-output.patch +debian/mips-disable-werror.patch +debian/mips-boston-disable-its.patch +debian/mips-ieee754-relaxed.patch +debian/arch-sh4-fix-uimage-build.patch +debian/tools-perf-perf-read-vdso-in-libexec.patch +debian/tools-perf-install-python-bindings.patch +debian/wireless-add-debian-wireless-regdb-certificates.patch +debian/export-symbols-needed-by-android-drivers.patch +debian/android-enable-building-ashmem-and-binder-as-modules.patch +debian/documentation-drop-sphinx-version-check.patch +debian/perf-traceevent-support-asciidoctor-for-documentatio.patch +debian/kbuild-look-for-module.lds-under-arch-directory-too.patch +debian/kbuild-abort-build-if-subdirs-used.patch +debian/module-avoid-abi-changes-when-debug-info-is-disabled.patch +debian/makefile-make-compiler-version-comparison-optional.patch + +# Fixes/improvements to firmware loading +features/all/drivers-media-dvb-usb-af9005-request_firmware.patch +debian/iwlwifi-do-not-request-unreleased-firmware.patch +bugfix/all/firmware_class-log-every-success-and-failure.patch +bugfix/all/firmware-remove-redundant-log-messages-from-drivers.patch +bugfix/all/radeon-amdgpu-firmware-is-required-for-drm-and-kms-on-r600-onward.patch +debian/firmware_class-refer-to-debian-wiki-firmware-page.patch +bugfix/all/wifi-mt76-do-not-run-mt76_unregister_device-on-unregistered-hw.patch + +# Change some defaults for security reasons +debian/af_802154-Disable-auto-loading-as-mitigation-against.patch +debian/rds-Disable-auto-loading-as-mitigation-against-local.patch +debian/dccp-disable-auto-loading-as-mitigation-against-local-exploits.patch +debian/hamradio-disable-auto-loading-as-mitigation-against-local-exploits.patch +debian/fs-enable-link-security-restrictions-by-default.patch + +# Set various features runtime-disabled by default +debian/sched-autogroup-disabled.patch +debian/yama-disable-by-default.patch +debian/add-sysctl-to-disallow-unprivileged-CLONE_NEWUSER-by-default.patch +features/all/security-perf-allow-further-restriction-of-perf_event_open.patch +features/x86/intel-iommu-add-option-to-exclude-integrated-gpu-only.patch +features/x86/intel-iommu-add-kconfig-option-to-exclude-igpu-by-default.patch + +# Disable autoloading/probing of various drivers by default +debian/cdc_ncm-cdc_mbim-use-ncm-by-default.patch +debian/snd-pcsp-disable-autoload.patch +bugfix/x86/viafb-autoload-on-olpc-xo1.5-only.patch +debian/fjes-disable-autoload.patch + +# Taint if dangerous features are used +debian/fanotify-taint-on-use-of-fanotify_access_permissions.patch +debian/btrfs-warn-about-raid5-6-being-experimental-at-mount.patch + +# Arch bug fixes +bugfix/arm/arm-dts-kirkwood-fix-sata-pinmux-ing-for-ts419.patch +bugfix/x86/perf-tools-fix-unwind-build-on-i386.patch +bugfix/sh/sh-boot-do-not-use-hyphen-in-exported-variable-name.patch +bugfix/arm/arm-mm-export-__sync_icache_dcache-for-xen-privcmd.patch +bugfix/powerpc/powerpc-boot-fix-missing-crc32poly.h-when-building-with-kernel_xz.patch +bugfix/arm64/arm64-acpi-Add-fixup-for-HPE-m400-quirks.patch +bugfix/alpha/alpha-fix-missing-symbol-versions-for-str-n-cat-cpy.patch + +# Arch features +features/arm64/dt-bindings-rockchip-Add-Hardkernel-ODROID-M1-board.patch +features/arm64/arm64-dts-rockchip-Add-Hardkernel-ODROID-M1-board.patch +features/arm64/arm64-dts-rockchip-add-thermal-support-to-ODROID-M1.patch +features/arm64/arm64-dts-rockchip-Add-NOR-flash-to-ODROID-M1.patch +features/arm64/arm64-dts-rockchip-Add-analog-audio-on-ODROID-M1.patch +features/arm64/arm64-dts-rockchip-Enable-vop2-and-hdmi-tx-on-ODROID.patch +features/arm64/arm64-dts-rockchip-Enable-HDMI-audio-on-ODROID-M1.patch +features/arm64/arm64-dts-rockchip-Enable-the-GPU-on-ODROID-M1.patch +features/arm64/arm64-dts-rockchip-Enable-the-USB-2.0-ports-on-ODROI.patch +features/arm64/arm64-dts-rockchip-Enable-the-USB-3.0-ports-on-ODROI.patch +features/arm64/arm64-dts-rockchip-Add-SATA-support-to-ODROID-M1.patch +features/arm64/arm64-dts-rockchip-Add-PCIEe-v3-nodes-to-ODROID-M1.patch +features/arm64/arm64-dts-rockchip-Add-IR-receiver-node-to-ODROID-M1.patch +features/x86/x86-memtest-WARN-if-bad-RAM-found.patch +features/x86/x86-make-x32-syscall-support-conditional.patch + +# Quartz64 bug fixes/patches +bugfix/arm64/arm64-dts-rockchip-fix-spdif-fe460000-ordering-on-rk.patch +features/arm64/quartz64/arm64-dts-rockchip-RK356x-Add-I2S2-device-node.patch +features/arm64/quartz64/arm64-dts-rockchip-Enable-video-output-and-HDMI-on-S.patch +features/arm64/quartz64/arm64-dts-rockchip-Enable-HDMI-sound-on-SOQuartz.patch +features/arm64/quartz64/arm64-dts-rockchip-Enable-PCIe-2-on-SOQuartz-CM4IO.patch +features/arm64/quartz64/dt-bindings-arm-rockchip-Add-SOQuartz-Blade.patch +features/arm64/quartz64/arm64-dts-rockchip-Add-SOQuartz-blade-board.patch +features/arm64/quartz64/dt-bindings-arm-rockchip-Add-SOQuartz-Model-A.patch +features/arm64/quartz64/arm64-dts-rockchip-Add-SOQuartz-Model-A-baseboard.patch + +# Miscellaneous bug fixes +bugfix/all/disable-some-marvell-phys.patch +bugfix/all/fs-add-module_softdep-declarations-for-hard-coded-cr.patch + +# Miscellaneous features + +# Lockdown missing pieces +features/all/lockdown/efi-add-an-efi_secure_boot-flag-to-indicate-secure-b.patch +features/all/lockdown/efi-lock-down-the-kernel-if-booted-in-secure-boot-mo.patch +features/all/lockdown/mtd-disable-slram-and-phram-when-locked-down.patch +features/all/lockdown/arm64-add-kernel-config-option-to-lock-down-when.patch + +# Improve integrity platform keyring for kernel modules verification +features/all/db-mok-keyring/0003-MODSIGN-checking-the-blacklisted-hash-before-loading-a-kernel-module.patch +features/all/db-mok-keyring/KEYS-Make-use-of-platform-keyring-for-module-signature.patch +features/all/db-mok-keyring/trust-machine-keyring-by-default.patch + +# Security fixes +debian/i386-686-pae-pci-set-pci-nobios-by-default.patch +debian/ntfs-mark-it-as-broken.patch + +# Fix exported symbol versions +bugfix/all/module-disable-matching-missing-version-crc.patch + +# Tools bug fixes +bugfix/all/usbip-document-tcp-wrappers.patch +bugfix/all/kbuild-fix-recordmcount-dependency.patch +bugfix/all/tools-perf-man-date.patch +bugfix/all/tools-perf-remove-shebangs.patch +bugfix/x86/revert-perf-build-fix-libunwind-feature-detection-on.patch +bugfix/all/tools-build-remove-bpf-run-time-check-at-build-time.patch +bugfix/all/cpupower-bump-soname-version.patch +bugfix/all/cpupower-fix-checks-for-cpu-existence.patch +bugfix/all/tools-perf-pmu-events-fix-reproducibility.patch +bugfix/all/libapi-define-_fortify_source-as-2-not-empty.patch +bugfix/all/tools-perf-fix-missing-ldflags-for-some-programs.patch + +# debian-installer fixes +bugfix/powerpc/fbdev-offb-Update-expected-device-name.patch + +# Backport of Microsoft Azure Network Adapter to 6.6 +features/all/ethernet-microsoft/0001-net-Remove-the-obsolte-u64_stats_fetch_-_irq-users-d.patch +features/all/ethernet-microsoft/0002-net-mana-Assign-interrupts-to-CPUs-based-on-NUMA-nod.patch +features/all/ethernet-microsoft/0003-net-mana-Add-support-for-auxiliary-device.patch +features/all/ethernet-microsoft/0004-net-mana-Record-the-physical-address-for-doorbell-pa.patch +features/all/ethernet-microsoft/0005-net-mana-Handle-vport-sharing-between-devices.patch +features/all/ethernet-microsoft/0006-net-mana-Set-the-DMA-device-max-segment-size.patch +features/all/ethernet-microsoft/0007-net-mana-Export-Work-Queue-functions-for-use-by-RDMA.patch +features/all/ethernet-microsoft/0008-net-mana-Record-port-number-in-netdev.patch +features/all/ethernet-microsoft/0009-net-mana-Move-header-files-to-a-common-location.patch +features/all/ethernet-microsoft/0010-net-mana-Define-max-values-for-SGL-entries.patch +features/all/ethernet-microsoft/0011-net-mana-Define-and-process-GDMA-response-code-GDMA_.patch +features/all/ethernet-microsoft/0012-net-mana-Define-data-structures-for-protection-domai.patch +features/all/ethernet-microsoft/0013-net-mana-Fix-return-type-of-mana_start_xmit.patch +features/all/ethernet-microsoft/0014-net-mana-Fix-accessing-freed-irq-affinity_hint.patch +features/all/ethernet-microsoft/0015-net-mana-Add-new-MANA-VF-performance-counters-for-ea.patch +features/all/ethernet-microsoft/0016-net-mana-Remove-redundant-pci_clear_master.patch +features/all/ethernet-microsoft/0017-net-mana-Use-napi_build_skb-in-RX-path.patch +features/all/ethernet-microsoft/0018-net-mana-Refactor-RX-buffer-allocation-code-to-prepa.patch +features/all/ethernet-microsoft/0019-net-mana-Enable-RX-path-to-handle-various-MTU-sizes.patch +features/all/ethernet-microsoft/0020-net-mana-Add-support-for-jumbo-frame.patch +features/all/ethernet-microsoft/0021-net-mana-Check-if-netdev-napi_alloc_frag-returns-sin.patch +features/all/ethernet-microsoft/0022-net-mana-Fix-perf-regression-remove-rx_cqes-tx_cqes-.patch +features/all/ethernet-microsoft/0023-net-mana-Add-support-for-vlan-tagging.patch +features/all/ethernet-microsoft/0024-RDMA-mana_ib-Use-v2-version-of-cfg_rx_steer_req-to-e.patch +features/all/ethernet-microsoft/0025-net-mana-use-vmalloc_array-and-vcalloc.patch +features/all/ethernet-microsoft/0026-net-mana-Batch-ringing-RX-queue-doorbell-on-receivin.patch +features/all/ethernet-microsoft/0027-net-mana-Use-the-correct-WQE-count-for-ringing-RQ-do.patch +features/all/ethernet-microsoft/0028-net-mana-Configure-hwc-timeout-from-hardware.patch +features/all/ethernet-microsoft/0029-net-mana-Rename-mana_refill_rxoob-and-remove-some-em.patch +features/all/ethernet-microsoft/0030-net-mana-Add-gdma-stats-to-ethtool-output-for-mana.patch + +# ABI maintenance |