From: Kan Liang kan.liang@linux.intel.com
mainline inclusion from mainline-v5.2-rc1 commit 878068ea270ea82767ff1d26c91583263c81fba0 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I47H3V CVE: NA
--------------------------------
commit 878068ea270ea82767ff1d26c91583263c81fba0 upstream.
Starting from Icelake, XMM registers can be collected in PEBS record. But current code only output the pt_regs.
Add a new struct x86_perf_regs for both pt_regs and xmm_regs. The xmm_regs will be used later to keep a pointer to PEBS record which has XMM information.
XMM registers are 128 bit. To simplify the code, they are handled like two different registers, which means setting two bits in the register bitmap. This also allows only sampling the lower 64bit bits in XMM.
The index of XMM registers starts from 32. There are 16 XMM registers. So all reserved space for regs are used. Remove REG_RESERVED.
Add PERF_REG_X86_XMM_MAX, which stands for the max number of all x86 regs including both GPRs and XMM.
Add REG_NOSUPPORT for 32bit to exclude unsupported registers.
Previous platforms can not collect XMM information in PEBS record. Adding pebs_no_xmm_regs to indicate the unsupported platforms.
The common code still validates the supported registers. However, it cannot check model specific registers, e.g. XMM. Add extra check in x86_pmu_hw_config() to reject invalid config of regs_user and regs_intr. The regs_user never supports XMM collection. The regs_intr only supports XMM collection when sampling PEBS event on icelake and later platforms.
Originally-by: Andi Kleen ak@linux.intel.com Suggested-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Kan Liang kan.liang@linux.intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Arnaldo Carvalho de Melo acme@redhat.com Cc: Jiri Olsa jolsa@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Cc: acme@kernel.org Cc: jolsa@kernel.org Link: https://lkml.kernel.org/r/20190402194509.2832-3-kan.liang@linux.intel.com Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Shen, Xiaochen xiaochen.shen@intel.com Signed-off-by: Jackie Liu liuyun01@kylinos.cn Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Reviewed-by: Yang Jihong yangjihong1@huawei.com Reviewed-by: Xie XiuQi xiexiuqi@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- arch/x86/events/core.c | 15 ++++++++++++ arch/x86/events/intel/ds.c | 2 ++ arch/x86/events/perf_event.h | 33 +++++++++++++++++++++------ arch/x86/include/asm/perf_event.h | 5 ++++ arch/x86/include/uapi/asm/perf_regs.h | 23 ++++++++++++++++++- arch/x86/kernel/perf_regs.c | 27 ++++++++++++++++------ 6 files changed, 90 insertions(+), 15 deletions(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 640f85da2b342..206ce31116b23 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -565,6 +565,21 @@ int x86_pmu_hw_config(struct perf_event *event) return -EINVAL; }
+ /* sample_regs_user never support XMM registers */ + if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS)) + return -EINVAL; + /* + * Besides the general purpose registers, XMM registers may + * be collected in PEBS on some platforms, e.g. Icelake + */ + if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) { + if (x86_pmu.pebs_no_xmm_regs) + return -EINVAL; + + if (!event->attr.precise_ip) + return -EINVAL; + } + return x86_setup_perfctr(event); }
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 2de55e1bef8ec..f62fd8f54ac14 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1651,6 +1651,8 @@ void __init intel_ds_init(void) x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS); x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS); x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE; + if (x86_pmu.version <= 4) + x86_pmu.pebs_no_xmm_regs = 1; if (x86_pmu.pebs) { char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-'; int format = x86_pmu.intel_cap.pebs_format; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index ad7290d51a3b1..97745c45334c2 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -123,6 +123,24 @@ struct amd_nb { (1ULL << PERF_REG_X86_R14) | \ (1ULL << PERF_REG_X86_R15))
+#define PEBS_XMM_REGS \ + ((1ULL << PERF_REG_X86_XMM0) | \ + (1ULL << PERF_REG_X86_XMM1) | \ + (1ULL << PERF_REG_X86_XMM2) | \ + (1ULL << PERF_REG_X86_XMM3) | \ + (1ULL << PERF_REG_X86_XMM4) | \ + (1ULL << PERF_REG_X86_XMM5) | \ + (1ULL << PERF_REG_X86_XMM6) | \ + (1ULL << PERF_REG_X86_XMM7) | \ + (1ULL << PERF_REG_X86_XMM8) | \ + (1ULL << PERF_REG_X86_XMM9) | \ + (1ULL << PERF_REG_X86_XMM10) | \ + (1ULL << PERF_REG_X86_XMM11) | \ + (1ULL << PERF_REG_X86_XMM12) | \ + (1ULL << PERF_REG_X86_XMM13) | \ + (1ULL << PERF_REG_X86_XMM14) | \ + (1ULL << PERF_REG_X86_XMM15)) + /* * Per register state. */ @@ -639,13 +657,14 @@ struct x86_pmu { /* * Intel DebugStore bits */ - unsigned int bts :1, - bts_active :1, - pebs :1, - pebs_active :1, - pebs_broken :1, - pebs_prec_dist :1, - pebs_no_tlb :1; + unsigned int bts :1, + bts_active :1, + pebs :1, + pebs_active :1, + pebs_broken :1, + pebs_prec_dist :1, + pebs_no_tlb :1, + pebs_no_xmm_regs :1; int pebs_record_size; int pebs_buffer_size; void (*drain_pebs)(struct pt_regs *regs); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 7a5ca63a3cca6..af66f97544a2a 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -252,6 +252,11 @@ extern void perf_events_lapic_init(void); #define PERF_EFLAGS_VM (1UL << 5)
struct pt_regs; +struct x86_perf_regs { + struct pt_regs regs; + u64 *xmm_regs; +}; + extern unsigned long perf_instruction_pointer(struct pt_regs *regs); extern unsigned long perf_misc_flags(struct pt_regs *regs); #define perf_misc_flags(regs) perf_misc_flags(regs) diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h index f3329cabce5c6..ac67bbea10cae 100644 --- a/arch/x86/include/uapi/asm/perf_regs.h +++ b/arch/x86/include/uapi/asm/perf_regs.h @@ -27,8 +27,29 @@ enum perf_event_x86_regs { PERF_REG_X86_R13, PERF_REG_X86_R14, PERF_REG_X86_R15, - + /* These are the limits for the GPRs. */ PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1, PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1, + + /* These all need two bits set because they are 128bit */ + PERF_REG_X86_XMM0 = 32, + PERF_REG_X86_XMM1 = 34, + PERF_REG_X86_XMM2 = 36, + PERF_REG_X86_XMM3 = 38, + PERF_REG_X86_XMM4 = 40, + PERF_REG_X86_XMM5 = 42, + PERF_REG_X86_XMM6 = 44, + PERF_REG_X86_XMM7 = 46, + PERF_REG_X86_XMM8 = 48, + PERF_REG_X86_XMM9 = 50, + PERF_REG_X86_XMM10 = 52, + PERF_REG_X86_XMM11 = 54, + PERF_REG_X86_XMM12 = 56, + PERF_REG_X86_XMM13 = 58, + PERF_REG_X86_XMM14 = 60, + PERF_REG_X86_XMM15 = 62, + + /* These include both GPRs and XMMX registers */ + PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2, }; #endif /* _ASM_X86_PERF_REGS_H */ diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index c06c4c16c6b69..07c30ee174254 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -59,18 +59,34 @@ static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = {
u64 perf_reg_value(struct pt_regs *regs, int idx) { + struct x86_perf_regs *perf_regs; + + if (idx >= PERF_REG_X86_XMM0 && idx < PERF_REG_X86_XMM_MAX) { + perf_regs = container_of(regs, struct x86_perf_regs, regs); + if (!perf_regs->xmm_regs) + return 0; + return perf_regs->xmm_regs[idx - PERF_REG_X86_XMM0]; + } + if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset))) return 0;
return regs_get_register(regs, pt_regs_offset[idx]); }
-#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL)) - #ifdef CONFIG_X86_32 +#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \ + (1ULL << PERF_REG_X86_R9) | \ + (1ULL << PERF_REG_X86_R10) | \ + (1ULL << PERF_REG_X86_R11) | \ + (1ULL << PERF_REG_X86_R12) | \ + (1ULL << PERF_REG_X86_R13) | \ + (1ULL << PERF_REG_X86_R14) | \ + (1ULL << PERF_REG_X86_R15)) + int perf_reg_validate(u64 mask) { - if (!mask || mask & REG_RESERVED) + if (!mask || (mask & REG_NOSUPPORT)) return -EINVAL;
return 0; @@ -96,10 +112,7 @@ void perf_get_regs_user(struct perf_regs *regs_user,
int perf_reg_validate(u64 mask) { - if (!mask || mask & REG_RESERVED) - return -EINVAL; - - if (mask & REG_NOSUPPORT) + if (!mask || (mask & REG_NOSUPPORT)) return -EINVAL;
return 0;