summaryrefslogtreecommitdiff
path: root/arch/x86/include
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-05-06 14:16:36 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-05-06 14:16:36 -0700
commit90489a72fba9529c85e051067ecb41183b8e982e (patch)
tree6c61660a380c3ddf25607b5892d173c3f4feb0d2 /arch/x86/include
parent007dc78fea62610bf06829e38f1d8c69b6ea5af6 (diff)
parentd15d356887e770c5f2dcf963b52c7cb510c9e42d (diff)
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar: "The main kernel changes were: - add support for Intel's "adaptive PEBS v4" - which embedds LBS data in PEBS records and can thus batch up and reduce the IRQ (NMI) rate significantly - reducing overhead and making call-graph profiling less intrusive. - add Intel CPU core and uncore support updates for Tremont, Icelake, - extend the x86 PMU constraints scheduler with 'constraint ranges' to better support Icelake hw constraints, - make x86 call-chain support work better with CONFIG_FRAME_POINTER=y - misc other changes Tooling changes: - updates to the main tools: 'perf record', 'perf trace', 'perf stat' - updated Intel and S/390 vendor events - libtraceevent updates - misc other updates and fixes" * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (69 commits) perf/x86: Make perf callchains work without CONFIG_FRAME_POINTER watchdog: Fix typo in comment perf/x86/intel: Add Tremont core PMU support perf/x86/intel/uncore: Add Intel Icelake uncore support perf/x86/msr: Add Icelake support perf/x86/intel/rapl: Add Icelake support perf/x86/intel/cstate: Add Icelake support perf/x86/intel: Add Icelake support perf/x86: Support constraint ranges perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them perf/x86/intel: Support adaptive PEBS v4 perf/x86/intel/ds: Extract code of event update in short period perf/x86/intel: Extract memory code PEBS parser for reuse perf/x86: Support outputting XMM registers perf/x86/intel: Force resched when TFA sysctl is modified perf/core: Add perf_pmu_resched() as global function perf/headers: Fix stale comment for struct perf_addr_filter perf/core: Make perf_swevent_init_cpu() static perf/x86: Add sanity checks to x86_schedule_events() perf/x86: Optimize x86_schedule_events() ...
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/intel_ds.h2
-rw-r--r--arch/x86/include/asm/msr-index.h1
-rw-r--r--arch/x86/include/asm/perf_event.h57
-rw-r--r--arch/x86/include/asm/stacktrace.h13
-rw-r--r--arch/x86/include/uapi/asm/perf_regs.h23
5 files changed, 74 insertions, 22 deletions
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
index ae26df1c2789..8380c3ddd4b2 100644
--- a/arch/x86/include/asm/intel_ds.h
+++ b/arch/x86/include/asm/intel_ds.h
@@ -8,7 +8,7 @@
/* The maximal number of PEBS events: */
#define MAX_PEBS_EVENTS 8
-#define MAX_FIXED_PEBS_EVENTS 3
+#define MAX_FIXED_PEBS_EVENTS 4
/*
* A debug store configuration.
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index ca5bc0eacb95..1378518cf63f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -116,6 +116,7 @@
#define LBR_INFO_CYCLES 0xffff
#define MSR_IA32_PEBS_ENABLE 0x000003f1
+#define MSR_PEBS_DATA_CFG 0x000003f2
#define MSR_IA32_DS_AREA 0x00000600
#define MSR_IA32_PERF_CAPABILITIES 0x00000345
#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8bdf74902293..1392d5e6e8d6 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -7,7 +7,7 @@
*/
#define INTEL_PMC_MAX_GENERIC 32
-#define INTEL_PMC_MAX_FIXED 3
+#define INTEL_PMC_MAX_FIXED 4
#define INTEL_PMC_IDX_FIXED 32
#define X86_PMC_IDX_MAX 64
@@ -32,6 +32,8 @@
#define HSW_IN_TX (1ULL << 32)
#define HSW_IN_TX_CHECKPOINTED (1ULL << 33)
+#define ICL_EVENTSEL_ADAPTIVE (1ULL << 34)
+#define ICL_FIXED_0_ADAPTIVE (1ULL << 32)
#define AMD64_EVENTSEL_INT_CORE_ENABLE (1ULL << 36)
#define AMD64_EVENTSEL_GUESTONLY (1ULL << 40)
@@ -87,6 +89,12 @@
#define ARCH_PERFMON_BRANCH_MISSES_RETIRED 6
#define ARCH_PERFMON_EVENTS_COUNT 7
+#define PEBS_DATACFG_MEMINFO BIT_ULL(0)
+#define PEBS_DATACFG_GP BIT_ULL(1)
+#define PEBS_DATACFG_XMMS BIT_ULL(2)
+#define PEBS_DATACFG_LBRS BIT_ULL(3)
+#define PEBS_DATACFG_LBR_SHIFT 24
+
/*
* Intel "Architectural Performance Monitoring" CPUID
* detection/enumeration details:
@@ -177,6 +185,41 @@ struct x86_pmu_capability {
#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55)
/*
+ * Adaptive PEBS v4
+ */
+
+struct pebs_basic {
+ u64 format_size;
+ u64 ip;
+ u64 applicable_counters;
+ u64 tsc;
+};
+
+struct pebs_meminfo {
+ u64 address;
+ u64 aux;
+ u64 latency;
+ u64 tsx_tuning;
+};
+
+struct pebs_gprs {
+ u64 flags, ip, ax, cx, dx, bx, sp, bp, si, di;
+ u64 r8, r9, r10, r11, r12, r13, r14, r15;
+};
+
+struct pebs_xmm {
+ u64 xmm[16*2]; /* two entries for each register */
+};
+
+struct pebs_lbr_entry {
+ u64 from, to, info;
+};
+
+struct pebs_lbr {
+ struct pebs_lbr_entry lbr[0]; /* Variable length */
+};
+
+/*
* IBS cpuid feature detection
*/
@@ -248,6 +291,11 @@ 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)
@@ -260,14 +308,9 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
*/
#define perf_arch_fetch_caller_regs(regs, __ip) { \
(regs)->ip = (__ip); \
- (regs)->bp = caller_frame_pointer(); \
+ (regs)->sp = (unsigned long)__builtin_frame_address(0); \
(regs)->cs = __KERNEL_CS; \
regs->flags = 0; \
- asm volatile( \
- _ASM_MOV "%%"_ASM_SP ", %0\n" \
- : "=m" ((regs)->sp) \
- :: "memory" \
- ); \
}
struct perf_guest_switch_msr {
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index f335aad404a4..beef7ad9e43a 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -98,19 +98,6 @@ struct stack_frame_ia32 {
u32 return_address;
};
-static inline unsigned long caller_frame_pointer(void)
-{
- struct stack_frame *frame;
-
- frame = __builtin_frame_address(0);
-
-#ifdef CONFIG_FRAME_POINTER
- frame = frame->next_frame;
-#endif
-
- return (unsigned long)frame;
-}
-
void show_opcodes(struct pt_regs *regs, const char *loglvl);
void show_ip(struct pt_regs *regs, const char *loglvl);
#endif /* _ASM_X86_STACKTRACE_H */
diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
index f3329cabce5c..ac67bbea10ca 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 */