From 01a69402cf9d38ff180345d55c2ee51c7e89fbc7 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sat, 18 May 2024 20:50:03 +0200 Subject: Adding upstream version 6.8.9. Signed-off-by: Daniel Baumann --- arch/s390/Kconfig | 10 ++-- arch/s390/boot/vmem.c | 2 +- arch/s390/configs/compat.config | 3 + arch/s390/configs/debug_defconfig | 9 +-- arch/s390/configs/defconfig | 10 +--- arch/s390/configs/zfcpdump_defconfig | 3 +- arch/s390/crypto/chacha-glue.c | 2 +- arch/s390/include/asm/ap.h | 21 ++++--- arch/s390/include/asm/ctlreg.h | 24 ++++---- arch/s390/include/asm/facility.h | 6 ++ arch/s390/include/asm/fpu/api.h | 35 +++++++----- arch/s390/include/asm/fpu/internal.h | 10 +++- arch/s390/include/asm/kvm_host.h | 2 +- arch/s390/include/asm/pgtable.h | 5 +- arch/s390/include/asm/processor.h | 34 ++++++++--- arch/s390/include/asm/setup.h | 2 - arch/s390/include/asm/sysinfo.h | 4 ++ arch/s390/kernel/Makefile | 2 +- arch/s390/kernel/compat_signal.c | 16 +++--- arch/s390/kernel/crash_dump.c | 5 +- arch/s390/kernel/early.c | 12 +--- arch/s390/kernel/entry.S | 1 + arch/s390/kernel/facility.c | 21 +++++++ arch/s390/kernel/fpu.c | 13 ++--- arch/s390/kernel/machine_kexec.c | 2 +- arch/s390/kernel/nmi.c | 10 ++-- arch/s390/kernel/perf_pai_crypto.c | 86 ++++++++++++++++------------ arch/s390/kernel/perf_pai_ext.c | 85 +++++++++++++++------------ arch/s390/kernel/perf_regs.c | 6 +- arch/s390/kernel/process.c | 2 +- arch/s390/kernel/processor.c | 7 +-- arch/s390/kernel/ptrace.c | 35 ++++++------ arch/s390/kernel/setup.c | 25 ++------ arch/s390/kernel/signal.c | 13 ++--- arch/s390/kernel/smp.c | 6 +- arch/s390/kernel/syscalls/syscall.tbl | 5 ++ arch/s390/kernel/sysinfo.c | 10 ++++ arch/s390/kernel/traps.c | 15 ++++- arch/s390/kernel/vmlinux.lds.S | 1 + arch/s390/kvm/Kconfig | 5 +- arch/s390/kvm/guestdbg.c | 4 +- arch/s390/kvm/interrupt.c | 2 +- arch/s390/kvm/kvm-s390.c | 22 +++---- arch/s390/kvm/priv.c | 8 ++- arch/s390/kvm/vsie.c | 19 +++++- arch/s390/lib/test_unwind.c | 6 +- arch/s390/mm/fault.c | 4 +- arch/s390/mm/gmap.c | 2 +- arch/s390/mm/hugetlbpage.c | 4 +- arch/s390/mm/pageattr.c | 2 +- arch/s390/mm/pgtable.c | 31 ++++------ arch/s390/mm/vmem.c | 6 +- arch/s390/net/bpf_jit_comp.c | 105 ++++++++++++++++++---------------- arch/s390/tools/gen_facilities.c | 1 + 54 files changed, 432 insertions(+), 349 deletions(-) create mode 100644 arch/s390/configs/compat.config create mode 100644 arch/s390/kernel/facility.c (limited to 'arch/s390') diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index d5d8f99d1f..fe565f3a3a 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -123,7 +123,6 @@ config S390 select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_USE_SYM_ANNOTATIONS - select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANTS_NO_INSTR select ARCH_WANT_DEFAULT_BPF_JIT select ARCH_WANT_IPC_PARSE_VERSION @@ -146,7 +145,7 @@ config S390 select GENERIC_TIME_VSYSCALL select GENERIC_VDSO_TIME_NS select GENERIC_IOREMAP if PCI - select HAVE_ALIGNED_STRUCT_PAGE if SLUB + select HAVE_ALIGNED_STRUCT_PAGE select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_JUMP_LABEL_RELATIVE @@ -217,7 +216,6 @@ config S390 select HAVE_VIRT_CPU_ACCOUNTING_IDLE select IOMMU_HELPER if PCI select IOMMU_SUPPORT if PCI - select KEXEC select MMU_GATHER_MERGE_VMAS select MMU_GATHER_NO_GATHER select MMU_GATHER_RCU_TABLE_FREE @@ -444,7 +442,7 @@ config COMMAND_LINE_SIZE line. config COMPAT - def_bool y + def_bool n prompt "Kernel support for 31 bit emulation" select ARCH_WANT_OLD_COMPAT_IPC select COMPAT_OLD_SIGACTION @@ -455,7 +453,9 @@ config COMPAT Select this option if you want to enable your system kernel to handle system-calls from ELF binaries for 31 bit ESA. This option (and some other stuff like libraries and such) is needed for - executing 31 bit applications. It is safe to say "Y". + executing 31 bit applications. + + If unsure say N. config SMP def_bool y diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index e3a4500a5a..47e1f54c58 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -366,7 +366,7 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e } pmd = boot_crst_alloc(_SEGMENT_ENTRY_EMPTY); pud_populate(&init_mm, pud, pmd); - } else if (pud_large(*pud)) { + } else if (pud_leaf(*pud)) { continue; } pgtable_pmd_populate(pud, addr, next, mode); diff --git a/arch/s390/configs/compat.config b/arch/s390/configs/compat.config new file mode 100644 index 0000000000..6fd051453a --- /dev/null +++ b/arch/s390/configs/compat.config @@ -0,0 +1,3 @@ +# Help: Enable compat support +CONFIG_COMPAT=y +CONFIG_COMPAT_32BIT_TIME=y diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 6de44ede4e..c924be0d7e 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -40,6 +40,7 @@ CONFIG_SCHED_AUTOGROUP=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set CONFIG_PROFILING=y +CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y CONFIG_CRASH_DUMP=y @@ -117,7 +118,6 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m -CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y CONFIG_IP_MULTICAST=y @@ -436,9 +436,6 @@ CONFIG_SCSI_DH_ALUA=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y # CONFIG_MD_BITMAP_FILE is not set -CONFIG_MD_LINEAR=m -CONFIG_MD_MULTIPATH=m -CONFIG_MD_FAULTY=m CONFIG_MD_CLUSTER=m CONFIG_BCACHE=m CONFIG_BLK_DEV_DM=y @@ -638,7 +635,7 @@ CONFIG_CUSE=m CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m CONFIG_NETFS_STATS=y -CONFIG_FSCACHE=m +CONFIG_FSCACHE=y CONFIG_CACHEFILES=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y @@ -708,7 +705,6 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" -CONFIG_INIT_STACK_NONE=y CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set @@ -738,7 +734,6 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index bcae47da6b..c8f0c9fe40 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -38,6 +38,7 @@ CONFIG_SCHED_AUTOGROUP=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set CONFIG_PROFILING=y +CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y CONFIG_CRASH_DUMP=y @@ -108,7 +109,6 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m -CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y CONFIG_IP_MULTICAST=y @@ -426,9 +426,6 @@ CONFIG_SCSI_DH_ALUA=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y # CONFIG_MD_BITMAP_FILE is not set -CONFIG_MD_LINEAR=m -CONFIG_MD_MULTIPATH=m -CONFIG_MD_FAULTY=m CONFIG_MD_CLUSTER=m CONFIG_BCACHE=m CONFIG_BLK_DEV_DM=y @@ -623,7 +620,7 @@ CONFIG_CUSE=m CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m CONFIG_NETFS_STATS=y -CONFIG_FSCACHE=m +CONFIG_FSCACHE=y CONFIG_CACHEFILES=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y @@ -692,7 +689,6 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" -CONFIG_INIT_STACK_NONE=y CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m @@ -723,11 +719,9 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_AEGIS128=m CONFIG_CRYPTO_CHACHA20POLY1305=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 47028450ee..c51f3ec4eb 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -8,9 +8,9 @@ CONFIG_BPF_SYSCALL=y # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y CONFIG_MARCH_Z13=y -# CONFIG_COMPAT is not set CONFIG_NR_CPUS=2 CONFIG_HZ_100=y # CONFIG_CHSC_SCH is not set @@ -65,7 +65,6 @@ CONFIG_ZFCP=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_LSM="yama,loadpin,safesetid,integrity" -CONFIG_INIT_STACK_NONE=y # CONFIG_ZLIB_DFLTCC is not set CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y diff --git a/arch/s390/crypto/chacha-glue.c b/arch/s390/crypto/chacha-glue.c index 5fae187f94..ed9959e6f7 100644 --- a/arch/s390/crypto/chacha-glue.c +++ b/arch/s390/crypto/chacha-glue.c @@ -82,7 +82,7 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, * it cannot handle a block of data or less, but otherwise * it can handle data of arbitrary size */ - if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20 || !MACHINE_HAS_VX) + if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20 || !cpu_has_vx()) chacha_crypt_generic(state, dst, src, bytes, nrounds); else chacha20_crypt_s390(state, dst, src, bytes, diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index 40c2b82f08..43ac4a64f4 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -88,7 +88,7 @@ static inline bool ap_instructions_available(void) } /* TAPQ register GR2 response struct */ -struct ap_tapq_gr2 { +struct ap_tapq_hwinfo { union { unsigned long value; struct { @@ -96,11 +96,13 @@ struct ap_tapq_gr2 { unsigned int apinfo : 32; /* ap type, ... */ }; struct { - unsigned int s : 1; /* APSC */ - unsigned int m : 1; /* AP4KM */ - unsigned int c : 1; /* AP4KC */ - unsigned int mode : 3; - unsigned int n : 1; /* APXA */ + unsigned int apsc : 1; /* APSC */ + unsigned int mex4k : 1; /* AP4KM */ + unsigned int crt4k : 1; /* AP4KC */ + unsigned int cca : 1; /* D */ + unsigned int accel : 1; /* A */ + unsigned int ep11 : 1; /* X */ + unsigned int apxa : 1; /* APXA */ unsigned int : 1; unsigned int class : 8; unsigned int bs : 2; /* SE bind/assoc */ @@ -126,11 +128,12 @@ struct ap_tapq_gr2 { /** * ap_tapq(): Test adjunct processor queue. * @qid: The AP queue number - * @info: Pointer to queue descriptor + * @info: Pointer to tapq hwinfo struct * * Returns AP queue status structure. */ -static inline struct ap_queue_status ap_tapq(ap_qid_t qid, struct ap_tapq_gr2 *info) +static inline struct ap_queue_status ap_tapq(ap_qid_t qid, + struct ap_tapq_hwinfo *info) { union ap_queue_status_reg reg1; unsigned long reg2; @@ -158,7 +161,7 @@ static inline struct ap_queue_status ap_tapq(ap_qid_t qid, struct ap_tapq_gr2 *i * Returns AP queue status structure. */ static inline struct ap_queue_status ap_test_queue(ap_qid_t qid, int tbit, - struct ap_tapq_gr2 *info) + struct ap_tapq_hwinfo *info) { if (tbit) qid |= 1UL << 23; /* set T bit*/ diff --git a/arch/s390/include/asm/ctlreg.h b/arch/s390/include/asm/ctlreg.h index 6d4b85f2b5..72a9556d04 100644 --- a/arch/s390/include/asm/ctlreg.h +++ b/arch/s390/include/asm/ctlreg.h @@ -141,22 +141,26 @@ static __always_inline void local_ctl_store(unsigned int cr, struct ctlreg *reg) : [cr] "i" (cr)); } -static __always_inline void local_ctl_set_bit(unsigned int cr, unsigned int bit) +static __always_inline struct ctlreg local_ctl_set_bit(unsigned int cr, unsigned int bit) { - struct ctlreg reg; + struct ctlreg new, old; - local_ctl_store(cr, ®); - reg.val |= 1UL << bit; - local_ctl_load(cr, ®); + local_ctl_store(cr, &old); + new = old; + new.val |= 1UL << bit; + local_ctl_load(cr, &new); + return old; } -static __always_inline void local_ctl_clear_bit(unsigned int cr, unsigned int bit) +static __always_inline struct ctlreg local_ctl_clear_bit(unsigned int cr, unsigned int bit) { - struct ctlreg reg; + struct ctlreg new, old; - local_ctl_store(cr, ®); - reg.val &= ~(1UL << bit); - local_ctl_load(cr, ®); + local_ctl_store(cr, &old); + new = old; + new.val &= ~(1UL << bit); + local_ctl_load(cr, &new); + return old; } struct lowcore; diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h index 94b6919026..796007125d 100644 --- a/arch/s390/include/asm/facility.h +++ b/arch/s390/include/asm/facility.h @@ -111,4 +111,10 @@ static inline void stfle(u64 *stfle_fac_list, int size) preempt_enable(); } +/** + * stfle_size - Actual size of the facility list as specified by stfle + * (number of double words) + */ +unsigned int stfle_size(void); + #endif /* __ASM_FACILITY_H */ diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h index 9acf48e53a..d6ca8bc6ca 100644 --- a/arch/s390/include/asm/fpu/api.h +++ b/arch/s390/include/asm/fpu/api.h @@ -46,26 +46,33 @@ #include #include +#include void save_fpu_regs(void); void load_fpu_regs(void); void __load_fpu_regs(void); -static inline int test_fp_ctl(u32 fpc) +/** + * sfpc_safe - Set floating point control register safely. + * @fpc: new value for floating point control register + * + * Set floating point control register. This may lead to an exception, + * since a saved value may have been modified by user space (ptrace, + * signal return, kvm registers) to an invalid value. In such a case + * set the floating point control register to zero. + */ +static inline void sfpc_safe(u32 fpc) { - u32 orig_fpc; - int rc; - - asm volatile( - " efpc %1\n" - " sfpc %2\n" - "0: sfpc %1\n" - " la %0,0\n" - "1:\n" - EX_TABLE(0b,1b) - : "=d" (rc), "=&d" (orig_fpc) - : "d" (fpc), "0" (-EINVAL)); - return rc; + asm volatile("\n" + "0: sfpc %[fpc]\n" + "1: nopr %%r7\n" + ".pushsection .fixup, \"ax\"\n" + "2: lghi %[fpc],0\n" + " jg 0b\n" + ".popsection\n" + EX_TABLE(1b, 2b) + : [fpc] "+d" (fpc) + : : "memory"); } #define KERNEL_FPC 1 diff --git a/arch/s390/include/asm/fpu/internal.h b/arch/s390/include/asm/fpu/internal.h index 8634581b90..d511c4cf5a 100644 --- a/arch/s390/include/asm/fpu/internal.h +++ b/arch/s390/include/asm/fpu/internal.h @@ -10,8 +10,14 @@ #define _ASM_S390_FPU_INTERNAL_H #include +#include #include +static inline bool cpu_has_vx(void) +{ + return likely(test_facility(129)); +} + static inline void save_vx_regs(__vector128 *vxrs) { asm volatile( @@ -41,7 +47,7 @@ static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) { fpregs->pad = 0; fpregs->fpc = fpu->fpc; - if (MACHINE_HAS_VX) + if (cpu_has_vx()) convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs); else memcpy((freg_t *)&fpregs->fprs, fpu->fprs, @@ -51,7 +57,7 @@ static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu) { fpu->fpc = fpregs->fpc; - if (MACHINE_HAS_VX) + if (cpu_has_vx()) convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs); else memcpy(fpu->fprs, (freg_t *)&fpregs->fprs, diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 67a298b6cf..52664105a4 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -818,7 +818,7 @@ struct s390_io_adapter { struct kvm_s390_cpu_model { /* facility mask supported by kvm & hosting machine */ - __u64 fac_mask[S390_ARCH_FAC_LIST_SIZE_U64]; + __u64 fac_mask[S390_ARCH_FAC_MASK_SIZE_U64]; struct kvm_s390_vm_cpu_subfunc subfuncs; /* facility list requested by guest (in dma page) */ __u64 *fac_list; diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 601e87fa8a..12a7b86789 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -730,7 +730,7 @@ static inline int pud_bad(pud_t pud) { unsigned long type = pud_val(pud) & _REGION_ENTRY_TYPE_MASK; - if (type > _REGION_ENTRY_TYPE_R3 || pud_large(pud)) + if (type > _REGION_ENTRY_TYPE_R3 || pud_leaf(pud)) return 1; if (type < _REGION_ENTRY_TYPE_R3) return 0; @@ -770,6 +770,7 @@ static inline int pud_write(pud_t pud) return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0; } +#define pmd_dirty pmd_dirty static inline int pmd_dirty(pmd_t pmd) { return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0; @@ -1397,7 +1398,7 @@ static inline unsigned long pud_deref(pud_t pud) unsigned long origin_mask; origin_mask = _REGION_ENTRY_ORIGIN; - if (pud_large(pud)) + if (pud_leaf(pud)) origin_mask = _REGION3_ENTRY_ORIGIN_LARGE; return (unsigned long)__va(pud_val(pud) & origin_mask); } diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index c15eadbb99..c0b6e74d89 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -184,11 +184,7 @@ struct thread_struct { struct gs_cb *gs_cb; /* Current guarded storage cb */ struct gs_cb *gs_bc_cb; /* Broadcast guarded storage cb */ struct pgm_tdb trap_tdb; /* Transaction abort diagnose block */ - /* - * Warning: 'fpu' is dynamically-sized. It *MUST* be at - * the end. - */ - struct fpu fpu; /* FP and VX register save area */ + struct fpu fpu; /* FP and VX register save area */ }; /* Flag to disable transactions. */ @@ -331,14 +327,36 @@ static inline unsigned long __extract_psw(void) return (((unsigned long) reg1) << 32) | ((unsigned long) reg2); } -static inline void local_mcck_enable(void) +static inline unsigned long __local_mcck_save(void) { - __load_psw_mask(__extract_psw() | PSW_MASK_MCHECK); + unsigned long mask = __extract_psw(); + + __load_psw_mask(mask & ~PSW_MASK_MCHECK); + return mask & PSW_MASK_MCHECK; +} + +#define local_mcck_save(mflags) \ +do { \ + typecheck(unsigned long, mflags); \ + mflags = __local_mcck_save(); \ +} while (0) + +static inline void local_mcck_restore(unsigned long mflags) +{ + unsigned long mask = __extract_psw(); + + mask &= ~PSW_MASK_MCHECK; + __load_psw_mask(mask | mflags); } static inline void local_mcck_disable(void) { - __load_psw_mask(__extract_psw() & ~PSW_MASK_MCHECK); + __local_mcck_save(); +} + +static inline void local_mcck_enable(void) +{ + __load_psw_mask(__extract_psw() | PSW_MASK_MCHECK); } /* diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index df316436d2..03bcaa8eff 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -28,7 +28,6 @@ #define MACHINE_FLAG_TOPOLOGY BIT(10) #define MACHINE_FLAG_TE BIT(11) #define MACHINE_FLAG_TLB_LC BIT(12) -#define MACHINE_FLAG_VX BIT(13) #define MACHINE_FLAG_TLB_GUEST BIT(14) #define MACHINE_FLAG_NX BIT(15) #define MACHINE_FLAG_GS BIT(16) @@ -90,7 +89,6 @@ extern unsigned long mio_wb_bit_mask; #define MACHINE_HAS_TOPOLOGY (S390_lowcore.machine_flags & MACHINE_FLAG_TOPOLOGY) #define MACHINE_HAS_TE (S390_lowcore.machine_flags & MACHINE_FLAG_TE) #define MACHINE_HAS_TLB_LC (S390_lowcore.machine_flags & MACHINE_FLAG_TLB_LC) -#define MACHINE_HAS_VX (S390_lowcore.machine_flags & MACHINE_FLAG_VX) #define MACHINE_HAS_TLB_GUEST (S390_lowcore.machine_flags & MACHINE_FLAG_TLB_GUEST) #define MACHINE_HAS_NX (S390_lowcore.machine_flags & MACHINE_FLAG_NX) #define MACHINE_HAS_GS (S390_lowcore.machine_flags & MACHINE_FLAG_GS) diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h index ab1c631605..edca5a751d 100644 --- a/arch/s390/include/asm/sysinfo.h +++ b/arch/s390/include/asm/sysinfo.h @@ -40,6 +40,10 @@ struct sysinfo_1_1_1 { unsigned int ncr; unsigned int npr; unsigned int ntr; + char reserved_3[4]; + char model_var_cap[16]; + unsigned int model_var_cap_rating; + unsigned int nvr; }; struct sysinfo_1_2_1 { diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 353def9397..7a562b4199 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -41,7 +41,7 @@ obj-y += sysinfo.o lgr.o os_info.o ctlreg.o obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o obj-y += entry.o reipl.o kdebugfs.o alternative.o obj-y += nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o -obj-y += smp.o text_amode31.o stacktrace.o abs_lowcore.o +obj-y += smp.o text_amode31.o stacktrace.o abs_lowcore.o facility.o extra-y += vmlinux.lds diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index cecedd01d4..f8fc6c25d0 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -29,6 +29,7 @@ #include #include #include +#include #include "compat_linux.h" #include "compat_ptrace.h" #include "entry.h" @@ -98,10 +99,6 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs) if (!is_ri_task(current) && (user_sregs.regs.psw.mask & PSW32_MASK_RI)) return -EINVAL; - /* Test the floating-point-control word. */ - if (test_fp_ctl(user_sregs.fpregs.fpc)) - return -EINVAL; - /* Use regs->psw.mask instead of PSW_USER_BITS to preserve PER bit. */ regs->psw.mask = (regs->psw.mask & ~(PSW_MASK_USER | PSW_MASK_RI)) | (__u64)(user_sregs.regs.psw.mask & PSW32_MASK_USER) << 32 | @@ -137,7 +134,7 @@ static int save_sigregs_ext32(struct pt_regs *regs, return -EFAULT; /* Save vector registers to signal stack */ - if (MACHINE_HAS_VX) { + if (cpu_has_vx()) { for (i = 0; i < __NUM_VXRS_LOW; i++) vxrs[i] = current->thread.fpu.vxrs[i].low; if (__copy_to_user(&sregs_ext->vxrs_low, vxrs, @@ -165,7 +162,7 @@ static int restore_sigregs_ext32(struct pt_regs *regs, *(__u32 *)®s->gprs[i] = gprs_high[i]; /* Restore vector registers from signal stack */ - if (MACHINE_HAS_VX) { + if (cpu_has_vx()) { if (__copy_from_user(vxrs, &sregs_ext->vxrs_low, sizeof(sregs_ext->vxrs_low)) || __copy_from_user(current->thread.fpu.vxrs + __NUM_VXRS_LOW, @@ -265,7 +262,7 @@ static int setup_frame32(struct ksignal *ksig, sigset_t *set, * the machine supports it */ frame_size = sizeof(*frame) - sizeof(frame->sregs_ext.__reserved); - if (!MACHINE_HAS_VX) + if (!cpu_has_vx()) frame_size -= sizeof(frame->sregs_ext.vxrs_low) + sizeof(frame->sregs_ext.vxrs_high); frame = get_sigframe(&ksig->ka, regs, frame_size); @@ -348,11 +345,12 @@ static int setup_rt_frame32(struct ksignal *ksig, sigset_t *set, * the machine supports it */ uc_flags = UC_GPRS_HIGH; - if (MACHINE_HAS_VX) { + if (cpu_has_vx()) { uc_flags |= UC_VXRS; - } else + } else { frame_size -= sizeof(frame->uc.uc_mcontext_ext.vxrs_low) + sizeof(frame->uc.uc_mcontext_ext.vxrs_high); + } frame = get_sigframe(&ksig->ka, regs, frame_size); if (frame == (void __user *) -1UL) return -EFAULT; diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index 514feadd4c..5c46c26593 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -22,6 +22,7 @@ #include #include #include +#include #define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y))) #define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y))) @@ -319,7 +320,7 @@ static void *fill_cpu_elf_notes(void *ptr, int cpu, struct save_area *sa) ptr = nt_init(ptr, NT_S390_TODPREG, &sa->todpreg, sizeof(sa->todpreg)); ptr = nt_init(ptr, NT_S390_CTRS, &sa->ctrs, sizeof(sa->ctrs)); ptr = nt_init(ptr, NT_S390_PREFIX, &sa->prefix, sizeof(sa->prefix)); - if (MACHINE_HAS_VX) { + if (cpu_has_vx()) { ptr = nt_init(ptr, NT_S390_VXRS_HIGH, &sa->vxrs_high, sizeof(sa->vxrs_high)); ptr = nt_init(ptr, NT_S390_VXRS_LOW, @@ -343,7 +344,7 @@ static size_t get_cpu_elf_notes_size(void) size += nt_size(NT_S390_TODPREG, sizeof(sa->todpreg)); size += nt_size(NT_S390_CTRS, sizeof(sa->ctrs)); size += nt_size(NT_S390_PREFIX, sizeof(sa->prefix)); - if (MACHINE_HAS_VX) { + if (cpu_has_vx()) { size += nt_size(NT_S390_VXRS_HIGH, sizeof(sa->vxrs_high)); size += nt_size(NT_S390_VXRS_LOW, sizeof(sa->vxrs_low)); } diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index eb43e5922a..2345ea332b 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -229,10 +229,8 @@ static __init void detect_machine_facilities(void) } if (test_facility(51)) S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_LC; - if (test_facility(129)) { - S390_lowcore.machine_flags |= MACHINE_FLAG_VX; + if (test_facility(129)) system_ctl_set_bit(0, CR0_VECTOR_BIT); - } if (test_facility(130)) S390_lowcore.machine_flags |= MACHINE_FLAG_NX; if (test_facility(133)) @@ -271,14 +269,6 @@ static inline void setup_access_registers(void) restore_access_regs(acrs); } -static int __init disable_vector_extension(char *str) -{ - S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX; - system_ctl_clear_bit(0, CR0_VECTOR_BIT); - return 0; -} -early_param("novx", disable_vector_extension); - char __bootdata(early_command_line)[COMMAND_LINE_SIZE]; static void __init setup_boot_command_line(void) { diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 49a11f6dd7..26c08ee877 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -653,6 +653,7 @@ SYM_DATA_START_LOCAL(daton_psw) SYM_DATA_END(daton_psw) .section .rodata, "a" + .balign 8 #define SYSCALL(esame,emu) .quad __s390x_ ## esame SYM_DATA_START(sys_call_table) #include "asm/syscall_table.h" diff --git a/arch/s390/kernel/facility.c b/arch/s390/kernel/facility.c new file mode 100644 index 0000000000..f02127219a --- /dev/null +++ b/arch/s390/kernel/facility.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright IBM Corp. 2023 + */ + +#include + +unsigned int stfle_size(void) +{ + static unsigned int size; + unsigned int r; + u64 dummy; + + r = READ_ONCE(size); + if (!r) { + r = __stfle_asm(&dummy, 1) + 1; + WRITE_ONCE(size, r); + } + return r; +} +EXPORT_SYMBOL(stfle_size); diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c index 4666b29ac8..a4f3449cc8 100644 --- a/arch/s390/kernel/fpu.c +++ b/arch/s390/kernel/fpu.c @@ -24,7 +24,7 @@ void __kernel_fpu_begin(struct kernel_fpu *state, u32 flags) /* Save floating point control */ asm volatile("stfpc %0" : "=Q" (state->fpc)); - if (!MACHINE_HAS_VX) { + if (!cpu_has_vx()) { if (flags & KERNEL_VXR_V0V7) { /* Save floating-point registers */ asm volatile("std 0,%0" : "=Q" (state->fprs[0])); @@ -106,7 +106,7 @@ void __kernel_fpu_end(struct kernel_fpu *state, u32 flags) /* Restore floating-point controls */ asm volatile("lfpc %0" : : "Q" (state->fpc)); - if (!MACHINE_HAS_VX) { + if (!cpu_has_vx()) { if (flags & KERNEL_VXR_V0V7) { /* Restore floating-point registers */ asm volatile("ld 0,%0" : : "Q" (state->fprs[0])); @@ -177,11 +177,11 @@ EXPORT_SYMBOL(__kernel_fpu_end); void __load_fpu_regs(void) { - struct fpu *state = ¤t->thread.fpu; unsigned long *regs = current->thread.fpu.regs; + struct fpu *state = ¤t->thread.fpu; - asm volatile("lfpc %0" : : "Q" (state->fpc)); - if (likely(MACHINE_HAS_VX)) { + sfpc_safe(state->fpc); + if (likely(cpu_has_vx())) { asm volatile("lgr 1,%0\n" "VLM 0,15,0,1\n" "VLM 16,31,256,1\n" @@ -208,7 +208,6 @@ void __load_fpu_regs(void) } clear_cpu_flag(CIF_FPU); } -EXPORT_SYMBOL(__load_fpu_regs); void load_fpu_regs(void) { @@ -232,7 +231,7 @@ void save_fpu_regs(void) regs = current->thread.fpu.regs; asm volatile("stfpc %0" : "=Q" (state->fpc)); - if (likely(MACHINE_HAS_VX)) { + if (likely(cpu_has_vx())) { asm volatile("lgr 1,%0\n" "VSTM 0,15,0,1\n" "VSTM 16,31,256,1\n" diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index bb0d4d68fc..aa22ffc16b 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -91,7 +91,7 @@ static noinline void __machine_kdump(void *image) } /* Store status of the boot CPU */ mcesa = __va(S390_lowcore.mcesad & MCESA_ORIGIN_MASK); - if (MACHINE_HAS_VX) + if (cpu_has_vx()) save_vx_regs((__vector128 *) mcesa->vector_save_area); if (MACHINE_HAS_GS) { local_ctl_store(2, &cr2_old.reg); diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 0daf0f1cdf..9ad44c26d1 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -32,6 +32,7 @@ #include #include #include +#include struct mcck_struct { unsigned int kill_task : 1; @@ -45,7 +46,7 @@ static DEFINE_PER_CPU(struct mcck_struct, cpu_mcck); static inline int nmi_needs_mcesa(void) { - return MACHINE_HAS_VX || MACHINE_HAS_GS; + return cpu_has_vx() || MACHINE_HAS_GS; } /* @@ -159,16 +160,17 @@ NOKPROBE_SYMBOL(s390_handle_damage); void s390_handle_mcck(void) { struct mcck_struct mcck; + unsigned long mflags; /* * Disable machine checks and get the current state of accumulated * machine checks. Afterwards delete the old state and enable machine * checks again. */ - local_mcck_disable(); + local_mcck_save(mflags); mcck = *this_cpu_ptr(&cpu_mcck); memset(this_cpu_ptr(&cpu_mcck), 0, sizeof(mcck)); - local_mcck_enable(); + local_mcck_restore(mflags); if (mcck.channel_report) crw_handle_channel_report(); @@ -234,7 +236,7 @@ static int notrace s390_validate_registers(union mci mci) } mcesa = __va(S390_lowcore.mcesad & MCESA_ORIGIN_MASK); - if (!MACHINE_HAS_VX) { + if (!cpu_has_vx()) { /* Validate floating point registers */ asm volatile( " ld 0,0(%0)\n" diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c index fc2dff1e4f..335e3f5d71 100644 --- a/arch/s390/kernel/perf_pai_crypto.c +++ b/arch/s390/kernel/perf_pai_crypto.c @@ -90,7 +90,6 @@ static void paicrypt_event_destroy(struct perf_event *event) event->cpu); struct paicrypt_map *cpump = mp->mapptr; - cpump->event = NULL; static_branch_dec(&pai_key); mutex_lock(&pai_reserve_mutex); debug_sprintf_event(cfm_dbg, 5, "%s event %#llx cpu %d users %d" @@ -111,11 +110,11 @@ static void paicrypt_event_destroy(struct perf_event *event) mutex_unlock(&pai_reserve_mutex); } -static u64 paicrypt_getctr(struct paicrypt_map *cpump, int nr, bool kernel) +static u64 paicrypt_getctr(unsigned long *page, int nr, bool kernel) { if (kernel) nr += PAI_CRYPTO_MAXCTR; - return cpump->page[nr]; + return page[nr]; } /* Read the counter values. Return value from location in CMP. For event @@ -129,13 +128,13 @@ static u64 paicrypt_getdata(struct perf_event *event, bool kernel) int i; if (event->attr.config != PAI_CRYPTO_BASE) { - return paicrypt_getctr(cpump, + return paicrypt_getctr(cpump->page, event->attr.config - PAI_CRYPTO_BASE, kernel); } for (i = 1; i <= paicrypt_cnt; i++) { - u64 val = paicrypt_getctr(cpump, i, kernel); + u64 val = paicrypt_getctr(cpump->page, i, kernel); if (!val) continue; @@ -317,10 +316,14 @@ static void paicrypt_start(struct perf_event *event, int flags) * Events are added, deleted and re-added when 2 or more events * are active at the same time. */ - if (!event->hw.last_tag) { - event->hw.last_tag = 1; - sum = paicrypt_getall(event); /* Get current value */ - local64_set(&event->hw.prev_count, sum); + if (!event->attr.sample_period) { /* Counting */ + if (!event->hw.last_tag) { + event->hw.last_tag = 1; + sum = paicrypt_getall(event); /* Get current value */ + local64_set(&event->hw.prev_count, sum); + } + } else { /* Sampling */ + perf_sched_cb_inc(event->pmu); } } @@ -336,19 +339,23 @@ static int paicrypt_add(struct perf_event *event, int flags) local_ctl_set_bit(0, CR0_CRYPTOGRAPHY_COUNTER_BIT); } cpump->event = event; - if (flags & PERF_EF_START && !event->attr.sample_period) { - /* Only counting needs initial counter value */ + if (flags & PERF_EF_START) paicrypt_start(event, PERF_EF_RELOAD); - } event->hw.state = 0; - if (event->attr.sample_period) - perf_sched_cb_inc(event->pmu); return 0; } static void paicrypt_stop(struct perf_event *event, int flags) { - paicrypt_read(event); + struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr); + struct paicrypt_map *cpump = mp->mapptr; + + if (!event->attr.sample_period) { /* Counting */ + paicrypt_read(event); + } else { /* Sampling */ + perf_sched_cb_dec(event->pmu); + cpump->event = NULL; + } event->hw.state = PERF_HES_STOPPED; } @@ -357,11 +364,7 @@ static void paicrypt_del(struct perf_event *event, int flags) struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr); struct paicrypt_map *cpump = mp->mapptr; - if (event->attr.sample_period) - perf_sched_cb_dec(event->pmu); - if (!event->attr.sample_period) - /* Only counting needs to read counter */ - paicrypt_stop(event, PERF_EF_UPDATE); + paicrypt_stop(event, PERF_EF_UPDATE); if (--cpump->active_events == 0) { local_ctl_clear_bit(0, CR0_CRYPTOGRAPHY_COUNTER_BIT); WRITE_ONCE(S390_lowcore.ccd, 0); @@ -373,8 +376,7 @@ static void paicrypt_del(struct perf_event *event, int flags) * 2 bytes: Number of counter * 8 bytes: Value of counter */ -static size_t paicrypt_copy(struct pai_userdata *userdata, - struct paicrypt_map *cpump, +static size_t paicrypt_copy(struct pai_userdata *userdata, unsigned long *page, bool exclude_user, bool exclude_kernel) { int i, outidx = 0; @@ -383,9 +385,9 @@ static size_t paicrypt_copy(struct pai_userdata *userdata, u64 val = 0; if (!exclude_kernel) - val += paicrypt_getctr(cpump, i, true); + val += paicrypt_getctr(page, i, true); if (!exclude_user) - val += paicrypt_getctr(cpump, i, false); + val += paicrypt_getctr(page, i, false); if (val) { userdata[outidx].num = i; userdata[outidx].value = val; @@ -395,25 +397,14 @@ static size_t paicrypt_copy(struct pai_userdata *userdata, return outidx * sizeof(struct pai_userdata); } -static int paicrypt_push_sample(void) +static int paicrypt_push_sample(size_t rawsize, struct paicrypt_map *cpump, + struct perf_event *event) { - struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr); - struct paicrypt_map *cpump = mp->mapptr; - struct perf_event *event = cpump->event; struct perf_sample_data data; struct perf_raw_record raw; struct pt_regs regs; - size_t rawsize; int overflow; - if (!cpump->event) /* No event active */ - return 0; - rawsize = paicrypt_copy(cpump->save, cpump, - cpump->event->attr.exclude_user, - cpump->event->attr.exclude_kernel); - if (!rawsize) /* No incremented counters */ - return 0; - /* Setup perf sample */ memset(®s, 0, sizeof(regs)); memset(&raw, 0, sizeof(raw)); @@ -444,6 +435,25 @@ static int paicrypt_push_sample(void) return overflow; } +/* Check if there is data to be saved on schedule out of a task. */ +static int paicrypt_have_sample(void) +{ + struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr); + struct paicrypt_map *cpump = mp->mapptr; + struct perf_event *event = cpump->event; + size_t rawsize; + int rc = 0; + + if (!event) /* No event active */ + return 0; + rawsize = paicrypt_copy(cpump->save, cpump->page, + cpump->event->attr.exclude_user, + cpump->event->attr.exclude_kernel); + if (rawsize) /* No incremented counters */ + rc = paicrypt_push_sample(rawsize, cpump, event); + return rc; +} + /* Called on schedule-in and schedule-out. No access to event structure, * but for sampling only event CRYPTO_ALL is allowed. */ @@ -453,7 +463,7 @@ static void paicrypt_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sch * results on schedule_out and if page was dirty, clear values. */ if (!sched_in) - paicrypt_push_sample(); + paicrypt_have_sample(); } /* Attribute definitions for paicrypt interface. As with other CPU diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c index 32b467c300..db37c38ddc 100644 --- a/arch/s390/kernel/perf_pai_ext.c +++ b/arch/s390/kernel/perf_pai_ext.c @@ -121,7 +121,6 @@ static void paiext_event_destroy(struct perf_event *event) struct paiext_map *cpump = mp->mapptr; mutex_lock(&paiext_reserve_mutex); - cpump->event = NULL; if (refcount_dec_and_test(&cpump->refcnt)) /* Last reference gone */ paiext_free(mp); paiext_root_free(); @@ -276,9 +275,9 @@ static int paiext_event_init(struct perf_event *event) return 0; } -static u64 paiext_getctr(struct paiext_map *cpump, int nr) +static u64 paiext_getctr(unsigned long *area, int nr) { - return cpump->area[nr]; + return area[nr]; } /* Read the counter values. Return value from location in buffer. For event @@ -292,10 +291,11 @@ static u64 paiext_getdata(struct perf_event *event) int i; if (event->attr.config != PAI_NNPA_BASE) - return paiext_getctr(cpump, event->attr.config - PAI_NNPA_BASE); + return paiext_getctr(cpump->area, + event->attr.config - PAI_NNPA_BASE); for (i = 1; i <= paiext_cnt; i++) - sum += paiext_getctr(cpump, i); + sum += paiext_getctr(cpump->area, i); return sum; } @@ -320,11 +320,15 @@ static void paiext_start(struct perf_event *event, int flags) { u64 sum; - if (event->hw.last_tag) - return; - event->hw.last_tag = 1; - sum = paiext_getall(event); /* Get current value */ - local64_set(&event->hw.prev_count, sum); + if (!event->attr.sample_period) { /* Counting */ + if (!event->hw.last_tag) { + event->hw.last_tag = 1; + sum = paiext_getall(event); /* Get current value */ + local64_set(&event->hw.prev_count, sum); + } + } else { /* Sampling */ + perf_sched_cb_inc(event->pmu); + } } static int paiext_add(struct perf_event *event, int flags) @@ -341,21 +345,24 @@ static int paiext_add(struct perf_event *event, int flags) debug_sprintf_event(paiext_dbg, 4, "%s 1508 %llx acc %llx\n", __func__, S390_lowcore.aicd, pcb->acc); } - if (flags & PERF_EF_START && !event->attr.sample_period) { - /* Only counting needs initial counter value */ + cpump->event = event; + if (flags & PERF_EF_START) paiext_start(event, PERF_EF_RELOAD); - } event->hw.state = 0; - if (event->attr.sample_period) { - cpump->event = event; - perf_sched_cb_inc(event->pmu); - } return 0; } static void paiext_stop(struct perf_event *event, int flags) { - paiext_read(event); + struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr); + struct paiext_map *cpump = mp->mapptr; + + if (!event->attr.sample_period) { /* Counting */ + paiext_read(event); + } else { /* Sampling */ + perf_sched_cb_dec(event->pmu); + cpump->event = NULL; + } event->hw.state = PERF_HES_STOPPED; } @@ -365,12 +372,7 @@ static void paiext_del(struct perf_event *event, int flags) struct paiext_map *cpump = mp->mapptr; struct paiext_cb *pcb = cpump->paiext_cb; - if (event->attr.sample_period) - perf_sched_cb_dec(event->pmu); - if (!event->attr.sample_period) { - /* Only counting needs to read counter */ - paiext_stop(event, PERF_EF_UPDATE); - } + paiext_stop(event, PERF_EF_UPDATE); if (--cpump->active_events == 0) { /* Disable CPU instruction lookup for PAIE1 control block */ local_ctl_clear_bit(0, CR0_PAI_EXTENSION_BIT); @@ -386,13 +388,12 @@ static void paiext_del(struct perf_event *event, int flags) * 2 bytes: Number of counter * 8 bytes: Value of counter */ -static size_t paiext_copy(struct paiext_map *cpump) +static size_t paiext_copy(struct pai_userdata *userdata, unsigned long *area) { - struct pai_userdata *userdata = cpump->save; int i, outidx = 0; for (i = 1; i <= paiext_cnt; i++) { - u64 val = paiext_getctr(cpump, i); + u64 val = paiext_getctr(area, i); if (val) { userdata[outidx].num = i; @@ -418,21 +419,14 @@ static size_t paiext_copy(struct paiext_map *cpump) * sched_task() callback. That callback is not active after paiext_del() * returns and has deleted the event on that CPU. */ -static int paiext_push_sample(void) +static int paiext_push_sample(size_t rawsize, struct paiext_map *cpump, + struct perf_event *event) { - struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr); - struct paiext_map *cpump = mp->mapptr; - struct perf_event *event = cpump->event; struct perf_sample_data data; struct perf_raw_record raw; struct pt_regs regs; - size_t rawsize; int overflow; - rawsize = paiext_copy(cpump); - if (!rawsize) /* No incremented counters */ - return 0; - /* Setup perf sample */ memset(®s, 0, sizeof(regs)); memset(&raw, 0, sizeof(raw)); @@ -461,6 +455,23 @@ static int paiext_push_sample(void) return overflow; } +/* Check if there is data to be saved on schedule out of a task. */ +static int paiext_have_sample(void) +{ + struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr); + struct paiext_map *cpump = mp->mapptr; + struct perf_event *event = cpump->event; + size_t rawsize; + int rc = 0; + + if (!event) + return 0; + rawsize = paiext_copy(cpump->save, cpump->area); + if (rawsize) /* Incremented counters */ + rc = paiext_push_sample(rawsize, cpump, event); + return rc; +} + /* Called on schedule-in and schedule-out. No access to event structure, * but for sampling only event NNPA_ALL is allowed. */ @@ -470,7 +481,7 @@ static void paiext_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched * results on schedule_out and if page was dirty, clear values. */ if (!sched_in) - paiext_push_sample(); + paiext_have_sample(); } /* Attribute definitions for pai extension1 interface. As with other CPU diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c index 6e9e5d5e92..3d93656bd9 100644 --- a/arch/s390/kernel/perf_regs.c +++ b/arch/s390/kernel/perf_regs.c @@ -20,8 +20,10 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) return 0; idx -= PERF_REG_S390_FP0; - fp = MACHINE_HAS_VX ? *(freg_t *)(current->thread.fpu.vxrs + idx) - : current->thread.fpu.fprs[idx]; + if (cpu_has_vx()) + fp = *(freg_t *)(current->thread.fpu.vxrs + idx); + else + fp = current->thread.fpu.fprs[idx]; return fp.ui; } diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 2580004177..4e3b366589 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -89,7 +89,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) */ save_fpu_regs(); - memcpy(dst, src, arch_task_struct_size); + *dst = *src; dst->thread.fpu.regs = dst->thread.fpu.fprs; /* diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 0a999c8226..65c1464eea 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -201,11 +201,8 @@ static int __init setup_hwcaps(void) if (MACHINE_HAS_TE) elf_hwcap |= HWCAP_TE; - /* - * Vector extension can be disabled with the "novx" parameter. - * Use MACHINE_HAS_VX instead of facility bit 129. - */ - if (MACHINE_HAS_VX) { + /* vector */ + if (test_facility(129)) { elf_hwcap |= HWCAP_VXRS; if (test_facility(134)) elf_hwcap |= HWCAP_VXRS_BCD; diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index c7ed302a6b..f1897a8bb2 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -30,6 +30,7 @@ #include #include #include +#include #include "entry.h" @@ -254,7 +255,7 @@ static unsigned long __peek_user(struct task_struct *child, addr_t addr) * or the child->thread.fpu.vxrs array */ offset = addr - offsetof(struct user, regs.fp_regs.fprs); - if (MACHINE_HAS_VX) + if (cpu_has_vx()) tmp = *(addr_t *) ((addr_t) child->thread.fpu.vxrs + 2*offset); else @@ -392,9 +393,7 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) /* * floating point control reg. is in the thread structure */ - save_fpu_regs(); - if ((unsigned int) data != 0 || - test_fp_ctl(data >> (BITS_PER_LONG - 32))) + if ((unsigned int)data != 0) return -EINVAL; child->thread.fpu.fpc = data >> (BITS_PER_LONG - 32); @@ -404,7 +403,7 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) * or the child->thread.fpu.vxrs array */ offset = addr - offsetof(struct user, regs.fp_regs.fprs); - if (MACHINE_HAS_VX) + if (cpu_has_vx()) *(addr_t *)((addr_t) child->thread.fpu.vxrs + 2*offset) = data; else @@ -631,7 +630,7 @@ static u32 __peek_user_compat(struct task_struct *child, addr_t addr) * or the child->thread.fpu.vxrs array */ offset = addr - offsetof(struct compat_user, regs.fp_regs.fprs); - if (MACHINE_HAS_VX) + if (cpu_has_vx()) tmp = *(__u32 *) ((addr_t) child->thread.fpu.vxrs + 2*offset); else @@ -749,9 +748,6 @@ static int __poke_user_compat(struct task_struct *child, /* * floating point control reg. is in the thread structure */ - save_fpu_regs(); - if (test_fp_ctl(tmp)) - return -EINVAL; child->thread.fpu.fpc = data; } else if (addr < offsetof(struct compat_user, regs.fp_regs) + sizeof(s390_fp_regs)) { @@ -760,7 +756,7 @@ static int __poke_user_compat(struct task_struct *child, * or the child->thread.fpu.vxrs array */ offset = addr - offsetof(struct compat_user, regs.fp_regs.fprs); - if (MACHINE_HAS_VX) + if (cpu_has_vx()) *(__u32 *)((addr_t) child->thread.fpu.vxrs + 2*offset) = tmp; else @@ -913,20 +909,21 @@ static int s390_fpregs_set(struct task_struct *target, int rc = 0; freg_t fprs[__NUM_FPRS]; - save_fpu_regs(); - if (MACHINE_HAS_VX) + if (target == current) + save_fpu_regs(); + + if (cpu_has_vx()) convert_vx_to_fp(fprs, target->thread.fpu.vxrs); else memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs)); - /* If setting FPC, must validate it first. */ if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) { u32 ufpc[2] = { target->thread.fpu.fpc, 0 }; rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ufpc, 0, offsetof(s390_fp_regs, fprs)); if (rc) return rc; - if (ufpc[1] != 0 || test_fp_ctl(ufpc[0])) + if (ufpc[1] != 0) return -EINVAL; target->thread.fpu.fpc = ufpc[0]; } @@ -937,7 +934,7 @@ static int s390_fpregs_set(struct task_struct *target, if (rc) return rc; - if (MACHINE_HAS_VX) + if (cpu_has_vx()) convert_fp_to_vx(target->thread.fpu.vxrs, fprs); else memcpy(target->thread.fpu.fprs, &fprs, sizeof(fprs)); @@ -988,7 +985,7 @@ static int s390_vxrs_low_get(struct task_struct *target, __u64 vxrs[__NUM_VXRS_LOW]; int i; - if (!MACHINE_HAS_VX) + if (!cpu_has_vx()) return -ENODEV; if (target == current) save_fpu_regs(); @@ -1005,7 +1002,7 @@ static int s390_vxrs_low_set(struct task_struct *target, __u64 vxrs[__NUM_VXRS_LOW]; int i, rc; - if (!MACHINE_HAS_VX) + if (!cpu_has_vx()) return -ENODEV; if (target == current) save_fpu_regs(); @@ -1025,7 +1022,7 @@ static int s390_vxrs_high_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { - if (!MACHINE_HAS_VX) + if (!cpu_has_vx()) return -ENODEV; if (target == current) save_fpu_regs(); @@ -1040,7 +1037,7 @@ static int s390_vxrs_high_set(struct task_struct *target, { int rc; - if (!MACHINE_HAS_VX) + if (!cpu_has_vx()) return -ENODEV; if (target == current) save_fpu_regs(); diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 5701356f4f..d1f3b56e7a 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -408,15 +408,15 @@ static void __init setup_lowcore(void) lc->restart_psw.mask = PSW_KERNEL_BITS & ~PSW_MASK_DAT; lc->restart_psw.addr = __pa(restart_int_handler); - lc->external_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK; + lc->external_new_psw.mask = PSW_KERNEL_BITS; lc->external_new_psw.addr = (unsigned long) ext_int_handler; - lc->svc_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK; + lc->svc_new_psw.mask = PSW_KERNEL_BITS; lc->svc_new_psw.addr = (unsigned long) system_call; - lc->program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK; + lc->program_new_psw.mask = PSW_KERNEL_BITS; lc->program_new_psw.addr = (unsigned long) pgm_check_handler; lc->mcck_new_psw.mask = PSW_KERNEL_BITS; lc->mcck_new_psw.addr = (unsigned long) mcck_int_handler; - lc->io_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK; + lc->io_new_psw.mask = PSW_KERNEL_BITS; lc->io_new_psw.addr = (unsigned long) io_int_handler; lc->clock_comparator = clock_comparator_max; lc->current_task = (unsigned long)&init_task; @@ -819,22 +819,6 @@ static void __init setup_randomness(void) static_branch_enable(&s390_arch_random_available); } -/* - * Find the correct size for the task_struct. This depends on - * the size of the struct fpu at the end of the thread_struct - * which is embedded in the task_struct. - */ -static void __init setup_task_size(void) -{ - int task_size = sizeof(struct task_struct); - - if (!MACHINE_HAS_VX) { - task_size -= sizeof(__vector128) * __NUM_VXRS; - task_size += sizeof(freg_t) * __NUM_FPRS; - } - arch_task_struct_size = task_size; -} - /* * Issue diagnose 318 to set the control program name and * version codes. @@ -927,7 +911,6 @@ void __init setup_arch(char **cmdline_p) os_info_init(); setup_ipl(); - setup_task_size(); setup_control_program_code(); /* Do some memory reservations *before* memory is added to memblock */ diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index d63557d386..43e9661cd7 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -12,6 +12,7 @@ #include #include +#include #include #include #include @@ -149,10 +150,6 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs) if (!is_ri_task(current) && (user_sregs.regs.psw.mask & PSW_MASK_RI)) return -EINVAL; - /* Test the floating-point-control word. */ - if (test_fp_ctl(user_sregs.fpregs.fpc)) - return -EINVAL; - /* Use regs->psw.mask instead of PSW_USER_BITS to preserve PER bit. */ regs->psw.mask = (regs->psw.mask & ~(PSW_MASK_USER | PSW_MASK_RI)) | (user_sregs.regs.psw.mask & (PSW_MASK_USER | PSW_MASK_RI)); @@ -182,7 +179,7 @@ static int save_sigregs_ext(struct pt_regs *regs, int i; /* Save vector registers to signal stack */ - if (MACHINE_HAS_VX) { + if (cpu_has_vx()) { for (i = 0; i < __NUM_VXRS_LOW; i++) vxrs[i] = current->thread.fpu.vxrs[i].low; if (__copy_to_user(&sregs_ext->vxrs_low, vxrs, @@ -202,7 +199,7 @@ static int restore_sigregs_ext(struct pt_regs *regs, int i; /* Restore vector registers from signal stack */ - if (MACHINE_HAS_VX) { + if (cpu_has_vx()) { if (__copy_from_user(vxrs, &sregs_ext->vxrs_low, sizeof(sregs_ext->vxrs_low)) || __copy_from_user(current->thread.fpu.vxrs + __NUM_VXRS_LOW, @@ -300,7 +297,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, * included in the signal frame on a 31-bit system. */ frame_size = sizeof(*frame) - sizeof(frame->sregs_ext); - if (MACHINE_HAS_VX) + if (cpu_has_vx()) frame_size += sizeof(frame->sregs_ext); frame = get_sigframe(ka, regs, frame_size); if (frame == (void __user *) -1UL) @@ -377,7 +374,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, * included in the signal frame on a 31-bit system. */ uc_flags = 0; - if (MACHINE_HAS_VX) { + if (cpu_has_vx()) { frame_size += sizeof(_sigregs_ext); uc_flags |= UC_VXRS; } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index f7fcfff09a..c39d9f0d4b 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -582,7 +582,7 @@ int smp_store_status(int cpu) if (__pcpu_sigp_relax(pcpu->address, SIGP_STORE_STATUS_AT_ADDRESS, pa) != SIGP_CC_ORDER_CODE_ACCEPTED) return -EIO; - if (!MACHINE_HAS_VX && !MACHINE_HAS_GS) + if (!cpu_has_vx() && !MACHINE_HAS_GS) return 0; pa = lc->mcesad & MCESA_ORIGIN_MASK; if (MACHINE_HAS_GS) @@ -638,7 +638,7 @@ void __init smp_save_dump_ipl_cpu(void) copy_oldmem_kernel(regs, __LC_FPREGS_SAVE_AREA, 512); save_area_add_regs(sa, regs); memblock_free(regs, 512); - if (MACHINE_HAS_VX) + if (cpu_has_vx()) save_area_add_vxrs(sa, boot_cpu_vector_save_area); } @@ -671,7 +671,7 @@ void __init smp_save_dump_secondary_cpus(void) panic("could not allocate memory for save area\n"); __pcpu_sigp_relax(addr, SIGP_STORE_STATUS_AT_ADDRESS, __pa(page)); save_area_add_regs(sa, page); - if (MACHINE_HAS_VX) { + if (cpu_has_vx()) { __pcpu_sigp_relax(addr, SIGP_STORE_ADDITIONAL_STATUS, __pa(page)); save_area_add_vxrs(sa, page); } diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 86fec9b080..095bb86339 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -459,3 +459,8 @@ 454 common futex_wake sys_futex_wake sys_futex_wake 455 common futex_wait sys_futex_wait sys_futex_wait 456 common futex_requeue sys_futex_requeue sys_futex_requeue +457 common statmount sys_statmount sys_statmount +458 common listmount sys_listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules sys_lsm_list_modules diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c index b5e364358c..f6f8f498c9 100644 --- a/arch/s390/kernel/sysinfo.c +++ b/arch/s390/kernel/sysinfo.c @@ -81,10 +81,12 @@ static bool convert_ext_name(unsigned char encoding, char *name, size_t len) static void stsi_1_1_1(struct seq_file *m, struct sysinfo_1_1_1 *info) { + bool has_var_cap; int i; if (stsi(info, 1, 1, 1)) return; + has_var_cap = !!info->model_var_cap[0]; EBCASC(info->manufacturer, sizeof(info->manufacturer)); EBCASC(info->type, sizeof(info->type)); EBCASC(info->model, sizeof(info->model)); @@ -93,6 +95,8 @@ static void stsi_1_1_1(struct seq_file *m, struct sysinfo_1_1_1 *info) EBCASC(info->model_capacity, sizeof(info->model_capacity)); EBCASC(info->model_perm_cap, sizeof(info->model_perm_cap)); EBCASC(info->model_temp_cap, sizeof(info->model_temp_cap)); + if (has_var_cap) + EBCASC(info->model_var_cap, sizeof(info->model_var_cap)); seq_printf(m, "Manufacturer: %-16.16s\n", info->manufacturer); seq_printf(m, "Type: %-4.4s\n", info->type); if (info->lic) @@ -120,12 +124,18 @@ static void stsi_1_1_1(struct seq_file *m, struct sysinfo_1_1_1 *info) seq_printf(m, "Model Temp. Capacity: %-16.16s %08u\n", info->model_temp_cap, info->model_temp_cap_rating); + if (has_var_cap && info->model_var_cap_rating) + seq_printf(m, "Model Var. Capacity: %-16.16s %08u\n", + info->model_var_cap, + info->model_var_cap_rating); if (info->ncr) seq_printf(m, "Nominal Cap. Rating: %08u\n", info->ncr); if (info->npr) seq_printf(m, "Nominal Perm. Rating: %08u\n", info->npr); if (info->ntr) seq_printf(m, "Nominal Temp. Rating: %08u\n", info->ntr); + if (has_var_cap && info->nvr) + seq_printf(m, "Nominal Var. Rating: %08u\n", info->nvr); if (info->cai) { seq_printf(m, "Capacity Adj. Ind.: %d\n", info->cai); seq_printf(m, "Capacity Ch. Reason: %d\n", info->ccr); diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 1d2aa448d1..46dac4540c 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -43,10 +43,12 @@ static inline void __user *get_trap_ip(struct pt_regs *regs) return (void __user *) (address - (regs->int_code >> 16)); } +#ifdef CONFIG_GENERIC_BUG int is_valid_bugaddr(unsigned long addr) { return 1; } +#endif void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str) { @@ -193,7 +195,7 @@ static void vector_exception(struct pt_regs *regs) { int si_code, vic; - if (!MACHINE_HAS_VX) { + if (!cpu_has_vx()) { do_trap(regs, SIGILL, ILL_ILLOPN, "illegal operation"); return; } @@ -286,6 +288,17 @@ static void __init test_monitor_call(void) void __init trap_init(void) { + unsigned long flags; + struct ctlreg cr0; + + local_irq_save(flags); + cr0 = local_ctl_clear_bit(0, CR0_LOW_ADDRESS_PROTECTION_BIT); + psw_bits(S390_lowcore.external_new_psw).mcheck = 1; + psw_bits(S390_lowcore.program_new_psw).mcheck = 1; + psw_bits(S390_lowcore.svc_new_psw).mcheck = 1; + psw_bits(S390_lowcore.io_new_psw).mcheck = 1; + local_ctl_load(0, &cr0); + local_irq_restore(flags); local_mcck_enable(); test_monitor_call(); } diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 2ae201ebf9..e32ef446f4 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -52,6 +52,7 @@ SECTIONS SOFTIRQENTRY_TEXT FTRACE_HOTPATCH_TRAMPOLINES_TEXT *(.text.*_indirect_*) + *(.fixup) *(.gnu.warning) . = ALIGN(PAGE_SIZE); _etext = .; /* End of text section */ diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 45fdf2a9b2..72e9b7dcdf 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -20,19 +20,16 @@ config KVM def_tristate y prompt "Kernel-based Virtual Machine (KVM) support" depends on HAVE_KVM - select PREEMPT_NOTIFIERS select HAVE_KVM_CPU_RELAX_INTERCEPT select HAVE_KVM_VCPU_ASYNC_IOCTL - select HAVE_KVM_EVENTFD select KVM_ASYNC_PF select KVM_ASYNC_PF_SYNC + select KVM_COMMON select HAVE_KVM_IRQCHIP - select HAVE_KVM_IRQFD select HAVE_KVM_IRQ_ROUTING select HAVE_KVM_INVALID_WAKEUPS select HAVE_KVM_NO_POLL select KVM_VFIO - select INTERVAL_TREE select MMU_NOTIFIER help Support hosting paravirtualized guest machines using the SIE diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c index 3765c4223b..80879fc73c 100644 --- a/arch/s390/kvm/guestdbg.c +++ b/arch/s390/kvm/guestdbg.c @@ -213,8 +213,8 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu, else if (dbg->arch.nr_hw_bp > MAX_BP_COUNT) return -EINVAL; - bp_data = memdup_user(dbg->arch.hw_bp, - sizeof(*bp_data) * dbg->arch.nr_hw_bp); + bp_data = memdup_array_user(dbg->arch.hw_bp, dbg->arch.nr_hw_bp, + sizeof(*bp_data)); if (IS_ERR(bp_data)) return PTR_ERR(bp_data); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index efaebba5ee..fc4007cc06 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -639,7 +639,7 @@ static int __write_machine_check(struct kvm_vcpu *vcpu, rc |= put_guest_lc(vcpu, mci.val, (u64 __user *) __LC_MCCK_CODE); /* Register-save areas */ - if (MACHINE_HAS_VX) { + if (cpu_has_vx()) { convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs); rc |= write_guest_lc(vcpu, __LC_FPREGS_SAVE_AREA, fprs, 128); } else { diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 16e3217480..ea63ac7698 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -563,7 +563,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ENABLE_CAP: case KVM_CAP_S390_CSS_SUPPORT: case KVM_CAP_IOEVENTFD: - case KVM_CAP_DEVICE_CTRL: case KVM_CAP_S390_IRQCHIP: case KVM_CAP_VM_ATTRIBUTES: case KVM_CAP_MP_STATE: @@ -618,7 +617,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = MACHINE_HAS_ESOP; break; case KVM_CAP_S390_VECTOR_REGISTERS: - r = MACHINE_HAS_VX; + r = test_facility(129); break; case KVM_CAP_S390_RI: r = test_facility(64); @@ -767,7 +766,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) mutex_lock(&kvm->lock); if (kvm->created_vcpus) { r = -EBUSY; - } else if (MACHINE_HAS_VX) { + } else if (cpu_has_vx()) { set_kvm_facility(kvm->arch.model.fac_mask, 129); set_kvm_facility(kvm->arch.model.fac_list, 129); if (test_facility(134)) { @@ -3962,9 +3961,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) if (test_kvm_facility(vcpu->kvm, 156)) vcpu->run->kvm_valid_regs |= KVM_SYNC_ETOKEN; /* fprs can be synchronized via vrs, even if the guest has no vx. With - * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format. + * cpu_has_vx(), (load|store)_fpu_regs() will work with vrs format. */ - if (MACHINE_HAS_VX) + if (cpu_has_vx()) vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS; else vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS; @@ -4317,7 +4316,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) vcpu_load(vcpu); vcpu->run->s.regs.fpc = fpu->fpc; - if (MACHINE_HAS_VX) + if (cpu_has_vx()) convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs, (freg_t *) fpu->fprs); else @@ -4331,9 +4330,7 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { vcpu_load(vcpu); - /* make sure we have the latest values */ - save_fpu_regs(); - if (MACHINE_HAS_VX) + if (cpu_has_vx()) convert_vx_to_fp((freg_t *) fpu->fprs, (__vector128 *) vcpu->run->s.regs.vrs); else @@ -4958,14 +4955,11 @@ static void sync_regs(struct kvm_vcpu *vcpu) save_fpu_regs(); vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc; vcpu->arch.host_fpregs.regs = current->thread.fpu.regs; - if (MACHINE_HAS_VX) + if (cpu_has_vx()) current->thread.fpu.regs = vcpu->run->s.regs.vrs; else current->thread.fpu.regs = vcpu->run->s.regs.fprs; current->thread.fpu.fpc = vcpu->run->s.regs.fpc; - if (test_fp_ctl(current->thread.fpu.fpc)) - /* User space provided an invalid FPC, let's clear it */ - current->thread.fpu.fpc = 0; /* Sync fmt2 only data */ if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) { @@ -5140,7 +5134,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) gpa -= __LC_FPREGS_SAVE_AREA; /* manually convert vector registers if necessary */ - if (MACHINE_HAS_VX) { + if (cpu_has_vx()) { convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs); rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, fprs, 128); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 621a17fd1a..f875a404a0 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -676,8 +676,12 @@ static int handle_pqap(struct kvm_vcpu *vcpu) if (vcpu->kvm->arch.crypto.pqap_hook) { pqap_hook = *vcpu->kvm->arch.crypto.pqap_hook; ret = pqap_hook(vcpu); - if (!ret && vcpu->run->s.regs.gprs[1] & 0x00ff0000) - kvm_s390_set_psw_cc(vcpu, 3); + if (!ret) { + if (vcpu->run->s.regs.gprs[1] & 0x00ff0000) + kvm_s390_set_psw_cc(vcpu, 3); + else + kvm_s390_set_psw_cc(vcpu, 0); + } up_read(&vcpu->kvm->arch.crypto.pqap_hook_rwsem); return ret; } diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index db9a180de6..3af3bd20ac 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -19,6 +19,7 @@ #include #include #include +#include #include "kvm-s390.h" #include "gaccess.h" @@ -984,12 +985,26 @@ static void retry_vsie_icpt(struct vsie_page *vsie_page) static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; - __u32 fac = READ_ONCE(vsie_page->scb_o->fac) & 0x7ffffff8U; + __u32 fac = READ_ONCE(vsie_page->scb_o->fac); + /* + * Alternate-STFLE-Interpretive-Execution facilities are not supported + * -> format-0 flcb + */ if (fac && test_kvm_facility(vcpu->kvm, 7)) { retry_vsie_icpt(vsie_page); + /* + * The facility list origin (FLO) is in bits 1 - 28 of the FLD + * so we need to mask here before reading. + */ + fac = fac & 0x7ffffff8U; + /* + * format-0 -> size of nested guest's facility list == guest's size + * guest's size == host's size, since STFLE is interpretatively executed + * using a format-0 for the guest, too. + */ if (read_guest_real(vcpu, fac, &vsie_page->fac, - sizeof(vsie_page->fac))) + stfle_size() * sizeof(u64))) return set_validity_icpt(scb_s, 0x1090U); scb_s->fac = (__u32)(__u64) &vsie_page->fac; } diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c index 7231bf97b9..2848e3fb2f 100644 --- a/arch/s390/lib/test_unwind.c +++ b/arch/s390/lib/test_unwind.c @@ -350,15 +350,15 @@ static noinline int unwindme_func3(struct unwindme *u) /* This function must appear in the backtrace. */ static noinline int unwindme_func2(struct unwindme *u) { - unsigned long flags; + unsigned long flags, mflags; int rc; if (u->flags & UWM_SWITCH_STACK) { local_irq_save(flags); - local_mcck_disable(); + local_mcck_save(mflags); rc = call_on_stack(1, S390_lowcore.nodat_stack, int, unwindme_func3, struct unwindme *, u); - local_mcck_enable(); + local_mcck_restore(mflags); local_irq_restore(flags); return rc; } else { diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index ab4098886e..ac4c78546d 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -280,7 +280,6 @@ static void do_sigbus(struct pt_regs *regs) static void do_exception(struct pt_regs *regs, int access) { struct vm_area_struct *vma; - struct task_struct *tsk; unsigned long address; struct mm_struct *mm; enum fault_type type; @@ -289,7 +288,6 @@ static void do_exception(struct pt_regs *regs, int access) vm_fault_t fault; bool is_write; - tsk = current; /* * The instruction that caused the program check has * been nullified. Don't signal single step via SIGTRAP. @@ -297,7 +295,7 @@ static void do_exception(struct pt_regs *regs, int access) clear_thread_flag(TIF_PER_TRAP); if (kprobe_page_fault(regs, 14)) return; - mm = tsk->mm; + mm = current->mm; address = get_fault_address(regs); is_write = fault_is_write(regs); type = get_fault_type(regs); diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 8da39deb56..08a7eca03d 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -596,7 +596,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) pud = pud_offset(p4d, vmaddr); VM_BUG_ON(pud_none(*pud)); /* large puds cannot yet be handled */ - if (pud_large(*pud)) + if (pud_leaf(*pud)) return -EFAULT; pmd = pmd_offset(pud, vmaddr); VM_BUG_ON(pmd_none(*pmd)); diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 297a6d897d..5f64f3d0fa 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -224,7 +224,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, if (p4d_present(*p4dp)) { pudp = pud_offset(p4dp, addr); if (pud_present(*pudp)) { - if (pud_large(*pudp)) + if (pud_leaf(*pudp)) return (pte_t *) pudp; pmdp = pmd_offset(pudp, addr); } @@ -240,7 +240,7 @@ int pmd_huge(pmd_t pmd) int pud_huge(pud_t pud) { - return pud_large(pud); + return pud_leaf(pud); } bool __init arch_hugetlb_valid_size(unsigned long size) diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 631e3a4ee2..739185fc39 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -274,7 +274,7 @@ static int walk_pud_level(p4d_t *p4d, unsigned long addr, unsigned long end, if (pud_none(*pudp)) return -EINVAL; next = pud_addr_end(addr, end); - if (pud_large(*pudp)) { + if (pud_leaf(*pudp)) { need_split = !!(flags & SET_MEMORY_4K); need_split |= !!(addr & ~PUD_MASK); need_split |= !!(addr + PUD_SIZE > next); diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 5cb9294154..3ff07b6bcd 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -125,32 +125,23 @@ static inline pte_t ptep_flush_lazy(struct mm_struct *mm, static inline pgste_t pgste_get_lock(pte_t *ptep) { - unsigned long new = 0; + unsigned long value = 0; #ifdef CONFIG_PGSTE - unsigned long old; - - asm( - " lg %0,%2\n" - "0: lgr %1,%0\n" - " nihh %0,0xff7f\n" /* clear PCL bit in old */ - " oihh %1,0x0080\n" /* set PCL bit in new */ - " csg %0,%1,%2\n" - " jl 0b\n" - : "=&d" (old), "=&d" (new), "=Q" (ptep[PTRS_PER_PTE]) - : "Q" (ptep[PTRS_PER_PTE]) : "cc", "memory"); + unsigned long *ptr = (unsigned long *)(ptep + PTRS_PER_PTE); + + do { + value = __atomic64_or_barrier(PGSTE_PCL_BIT, ptr); + } while (value & PGSTE_PCL_BIT); + value |= PGSTE_PCL_BIT; #endif - return __pgste(new); + return __pgste(value); } static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste) { #ifdef CONFIG_PGSTE - asm( - " nihh %1,0xff7f\n" /* clear PCL bit */ - " stg %1,%0\n" - : "=Q" (ptep[PTRS_PER_PTE]) - : "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE]) - : "cc", "memory"); + barrier(); + WRITE_ONCE(*(unsigned long *)(ptep + PTRS_PER_PTE), pgste_val(pgste) & ~PGSTE_PCL_BIT); #endif } @@ -479,7 +470,7 @@ static int pmd_lookup(struct mm_struct *mm, unsigned long addr, pmd_t **pmdp) return -ENOENT; /* Large PUDs are not supported yet. */ - if (pud_large(*pud)) + if (pud_leaf(*pud)) return -EFAULT; *pmdp = pmd_offset(pud, addr); diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 186a020857..84e173c02a 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -323,7 +323,7 @@ static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end, if (!add) { if (pud_none(*pud)) continue; - if (pud_large(*pud)) { + if (pud_leaf(*pud)) { if (IS_ALIGNED(addr, PUD_SIZE) && IS_ALIGNED(next, PUD_SIZE)) { pud_clear(pud); @@ -344,7 +344,7 @@ static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end, if (!pmd) goto out; pud_populate(&init_mm, pud, pmd); - } else if (pud_large(*pud)) { + } else if (pud_leaf(*pud)) { continue; } ret = modify_pmd_table(pud, addr, next, add, direct); @@ -591,7 +591,7 @@ pte_t *vmem_get_alloc_pte(unsigned long addr, bool alloc) if (!pmd) goto out; pud_populate(&init_mm, pud, pmd); - } else if (WARN_ON_ONCE(pud_large(*pud))) { + } else if (WARN_ON_ONCE(pud_leaf(*pud))) { goto out; } pmd = pmd_offset(pud, addr); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index c7fbeedeb0..5af0402e94 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -516,11 +516,12 @@ static void bpf_skip(struct bpf_jit *jit, int size) * PLT for hotpatchable calls. The calling convention is the same as for the * ftrace hotpatch trampolines: %r0 is return address, %r1 is clobbered. */ -extern const char bpf_plt[]; -extern const char bpf_plt_ret[]; -extern const char bpf_plt_target[]; -extern const char bpf_plt_end[]; -#define BPF_PLT_SIZE 32 +struct bpf_plt { + char code[16]; + void *ret; + void *target; +} __packed; +extern const struct bpf_plt bpf_plt; asm( ".pushsection .rodata\n" " .balign 8\n" @@ -531,15 +532,14 @@ asm( " .balign 8\n" "bpf_plt_ret: .quad 0\n" "bpf_plt_target: .quad 0\n" - "bpf_plt_end:\n" " .popsection\n" ); -static void bpf_jit_plt(void *plt, void *ret, void *target) +static void bpf_jit_plt(struct bpf_plt *plt, void *ret, void *target) { - memcpy(plt, bpf_plt, BPF_PLT_SIZE); - *(void **)((char *)plt + (bpf_plt_ret - bpf_plt)) = ret; - *(void **)((char *)plt + (bpf_plt_target - bpf_plt)) = target ?: ret; + memcpy(plt, &bpf_plt, sizeof(*plt)); + plt->ret = ret; + plt->target = target; } /* @@ -662,9 +662,9 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth) jit->prg = ALIGN(jit->prg, 8); jit->prologue_plt = jit->prg; if (jit->prg_buf) - bpf_jit_plt(jit->prg_buf + jit->prg, + bpf_jit_plt((struct bpf_plt *)(jit->prg_buf + jit->prg), jit->prg_buf + jit->prologue_plt_ret, NULL); - jit->prg += BPF_PLT_SIZE; + jit->prg += sizeof(struct bpf_plt); } static int get_probe_mem_regno(const u8 *insn) @@ -2040,9 +2040,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) struct bpf_jit jit; int pass; - if (WARN_ON_ONCE(bpf_plt_end - bpf_plt != BPF_PLT_SIZE)) - return orig_fp; - if (!fp->jit_requested) return orig_fp; @@ -2148,14 +2145,11 @@ bool bpf_jit_supports_far_kfunc_call(void) int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *old_addr, void *new_addr) { + struct bpf_plt expected_plt, current_plt, new_plt, *plt; struct { u16 opc; s32 disp; } __packed insn; - char expected_plt[BPF_PLT_SIZE]; - char current_plt[BPF_PLT_SIZE]; - char new_plt[BPF_PLT_SIZE]; - char *plt; char *ret; int err; @@ -2174,18 +2168,18 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, */ } else { /* Verify the PLT. */ - plt = (char *)ip + (insn.disp << 1); - err = copy_from_kernel_nofault(current_plt, plt, BPF_PLT_SIZE); + plt = ip + (insn.disp << 1); + err = copy_from_kernel_nofault(¤t_plt, plt, + sizeof(current_plt)); if (err < 0) return err; ret = (char *)ip + 6; - bpf_jit_plt(expected_plt, ret, old_addr); - if (memcmp(current_plt, expected_plt, BPF_PLT_SIZE)) + bpf_jit_plt(&expected_plt, ret, old_addr); + if (memcmp(¤t_plt, &expected_plt, sizeof(current_plt))) return -EINVAL; /* Adjust the call address. */ - bpf_jit_plt(new_plt, ret, new_addr); - s390_kernel_write(plt + (bpf_plt_target - bpf_plt), - new_plt + (bpf_plt_target - bpf_plt), + bpf_jit_plt(&new_plt, ret, new_addr); + s390_kernel_write(&plt->target, &new_plt.target, sizeof(void *)); } @@ -2362,7 +2356,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, return -ENOTSUPP; /* Return to %r14, since func_addr and %r0 are not available. */ - if (!func_addr && !(flags & BPF_TRAMP_F_ORIG_STACK)) + if ((!func_addr && !(flags & BPF_TRAMP_F_ORIG_STACK)) || + (flags & BPF_TRAMP_F_INDIRECT)) flags |= BPF_TRAMP_F_SKIP_FRAME; /* @@ -2637,6 +2632,21 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, return 0; } +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *orig_call) +{ + struct bpf_tramp_image im; + struct bpf_tramp_jit tjit; + int ret; + + memset(&tjit, 0, sizeof(tjit)); + + ret = __arch_prepare_bpf_trampoline(&im, &tjit, m, flags, + tlinks, orig_call); + + return ret < 0 ? ret : tjit.common.prg; +} + int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, @@ -2644,30 +2654,27 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, { struct bpf_tramp_jit tjit; int ret; - int i; - for (i = 0; i < 2; i++) { - if (i == 0) { - /* Compute offsets, check whether the code fits. */ - memset(&tjit, 0, sizeof(tjit)); - } else { - /* Generate the code. */ - tjit.common.prg = 0; - tjit.common.prg_buf = image; - } - ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags, - tlinks, func_addr); - if (ret < 0) - return ret; - if (tjit.common.prg > (char *)image_end - (char *)image) - /* - * Use the same error code as for exceeding - * BPF_MAX_TRAMP_LINKS. - */ - return -E2BIG; - } + /* Compute offsets, check whether the code fits. */ + memset(&tjit, 0, sizeof(tjit)); + ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags, + tlinks, func_addr); + + if (ret < 0) + return ret; + if (tjit.common.prg > (char *)image_end - (char *)image) + /* + * Use the same error code as for exceeding + * BPF_MAX_TRAMP_LINKS. + */ + return -E2BIG; + + tjit.common.prg = 0; + tjit.common.prg_buf = image; + ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags, + tlinks, func_addr); - return tjit.common.prg; + return ret < 0 ? ret : tjit.common.prg; } bool bpf_jit_supports_subprog_tailcalls(void) diff --git a/arch/s390/tools/gen_facilities.c b/arch/s390/tools/gen_facilities.c index cb0aff5c01..68580cbea4 100644 --- a/arch/s390/tools/gen_facilities.c +++ b/arch/s390/tools/gen_facilities.c @@ -46,6 +46,7 @@ static struct facility_def facility_defs[] = { #endif #ifdef CONFIG_HAVE_MARCH_Z13_FEATURES 53, /* load-and-zero-rightmost-byte, etc. */ + 129, /* vector */ #endif #ifdef CONFIG_HAVE_MARCH_Z14_FEATURES 58, /* miscellaneous-instruction-extension 2 */ -- cgit v1.2.3