![Andi Kleen](/assets/img/avatar_default.png)
The basic idea is that it does not make sense to list all PEBS events individually. The list is very long, sometimes outdated and the hardware doesn't need it. If an event does not support PEBS it will just not count, there is no security issue. We need to only list events that something special, like supporting load or store addresses. This vastly simplifies the PEBS event selection. It also speeds up the scheduling because the scheduler doesn't have to walk as many constraints. Bugs fixed: - We do not allow setting forbidden flags with PEBS anymore (SDM 18.9.4), except for the special cycle event. This is done using a new constraint macro that also matches on the event flags. - Correct DataLA and load/store/na flags reporting on Haswell [Requires a followon patch] - We did not allow all PEBS events on Haswell: We were missing some valid subevents in d1-d2 (MEM_LOAD_UOPS_RETIRED.*, MEM_LOAD_UOPS_RETIRED_L3_HIT_RETIRED.*) This includes the changes proposed by Stephane earlier and obsoletes his patchkit (except for some changes on pre Sandy Bridge/Silvermont CPUs) I only did Sandy Bridge and Silvermont and later so far, mostly because these are the parts I could directly confirm the hardware behavior with hardware architects. Also I do not believe the older CPUs have any missing events in their PEBS list, so there's no pressing need to change them. I did not implement the flag proposed by Peter to allow setting forbidden flags. If really needed this could be implemented on to of this patch. v2: Fix broken store events on SNB/IVB (Stephane Eranian) v3: More fixes. Rename some arguments (Stephane Eranian) v4: List most Haswell events individually again to report memory operation type correctly. Add new flags to describe load/store/na for datala. Update description. Signed-off-by: Andi Kleen <ak@linux.intel.com> Reviewed-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1407785233-32193-2-git-send-email-eranian@google.com Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com> Cc: Mark Davies <junk@eslaf.co.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> Cc: Yan, Zheng <zheng.z.yan@intel.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
288 lines
8 KiB
C
288 lines
8 KiB
C
#ifndef _ASM_X86_PERF_EVENT_H
|
|
#define _ASM_X86_PERF_EVENT_H
|
|
|
|
/*
|
|
* Performance event hw details:
|
|
*/
|
|
|
|
#define INTEL_PMC_MAX_GENERIC 32
|
|
#define INTEL_PMC_MAX_FIXED 3
|
|
#define INTEL_PMC_IDX_FIXED 32
|
|
|
|
#define X86_PMC_IDX_MAX 64
|
|
|
|
#define MSR_ARCH_PERFMON_PERFCTR0 0xc1
|
|
#define MSR_ARCH_PERFMON_PERFCTR1 0xc2
|
|
|
|
#define MSR_ARCH_PERFMON_EVENTSEL0 0x186
|
|
#define MSR_ARCH_PERFMON_EVENTSEL1 0x187
|
|
|
|
#define ARCH_PERFMON_EVENTSEL_EVENT 0x000000FFULL
|
|
#define ARCH_PERFMON_EVENTSEL_UMASK 0x0000FF00ULL
|
|
#define ARCH_PERFMON_EVENTSEL_USR (1ULL << 16)
|
|
#define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17)
|
|
#define ARCH_PERFMON_EVENTSEL_EDGE (1ULL << 18)
|
|
#define ARCH_PERFMON_EVENTSEL_PIN_CONTROL (1ULL << 19)
|
|
#define ARCH_PERFMON_EVENTSEL_INT (1ULL << 20)
|
|
#define ARCH_PERFMON_EVENTSEL_ANY (1ULL << 21)
|
|
#define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22)
|
|
#define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23)
|
|
#define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL
|
|
|
|
#define HSW_IN_TX (1ULL << 32)
|
|
#define HSW_IN_TX_CHECKPOINTED (1ULL << 33)
|
|
|
|
#define AMD64_EVENTSEL_INT_CORE_ENABLE (1ULL << 36)
|
|
#define AMD64_EVENTSEL_GUESTONLY (1ULL << 40)
|
|
#define AMD64_EVENTSEL_HOSTONLY (1ULL << 41)
|
|
|
|
#define AMD64_EVENTSEL_INT_CORE_SEL_SHIFT 37
|
|
#define AMD64_EVENTSEL_INT_CORE_SEL_MASK \
|
|
(0xFULL << AMD64_EVENTSEL_INT_CORE_SEL_SHIFT)
|
|
|
|
#define AMD64_EVENTSEL_EVENT \
|
|
(ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32))
|
|
#define INTEL_ARCH_EVENT_MASK \
|
|
(ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT)
|
|
|
|
#define X86_RAW_EVENT_MASK \
|
|
(ARCH_PERFMON_EVENTSEL_EVENT | \
|
|
ARCH_PERFMON_EVENTSEL_UMASK | \
|
|
ARCH_PERFMON_EVENTSEL_EDGE | \
|
|
ARCH_PERFMON_EVENTSEL_INV | \
|
|
ARCH_PERFMON_EVENTSEL_CMASK)
|
|
#define X86_ALL_EVENT_FLAGS \
|
|
(ARCH_PERFMON_EVENTSEL_EDGE | \
|
|
ARCH_PERFMON_EVENTSEL_INV | \
|
|
ARCH_PERFMON_EVENTSEL_CMASK | \
|
|
ARCH_PERFMON_EVENTSEL_ANY | \
|
|
ARCH_PERFMON_EVENTSEL_PIN_CONTROL | \
|
|
HSW_IN_TX | \
|
|
HSW_IN_TX_CHECKPOINTED)
|
|
#define AMD64_RAW_EVENT_MASK \
|
|
(X86_RAW_EVENT_MASK | \
|
|
AMD64_EVENTSEL_EVENT)
|
|
#define AMD64_RAW_EVENT_MASK_NB \
|
|
(AMD64_EVENTSEL_EVENT | \
|
|
ARCH_PERFMON_EVENTSEL_UMASK)
|
|
#define AMD64_NUM_COUNTERS 4
|
|
#define AMD64_NUM_COUNTERS_CORE 6
|
|
#define AMD64_NUM_COUNTERS_NB 4
|
|
|
|
#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c
|
|
#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8)
|
|
#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX 0
|
|
#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
|
|
(1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
|
|
|
|
#define ARCH_PERFMON_BRANCH_MISSES_RETIRED 6
|
|
#define ARCH_PERFMON_EVENTS_COUNT 7
|
|
|
|
/*
|
|
* Intel "Architectural Performance Monitoring" CPUID
|
|
* detection/enumeration details:
|
|
*/
|
|
union cpuid10_eax {
|
|
struct {
|
|
unsigned int version_id:8;
|
|
unsigned int num_counters:8;
|
|
unsigned int bit_width:8;
|
|
unsigned int mask_length:8;
|
|
} split;
|
|
unsigned int full;
|
|
};
|
|
|
|
union cpuid10_ebx {
|
|
struct {
|
|
unsigned int no_unhalted_core_cycles:1;
|
|
unsigned int no_instructions_retired:1;
|
|
unsigned int no_unhalted_reference_cycles:1;
|
|
unsigned int no_llc_reference:1;
|
|
unsigned int no_llc_misses:1;
|
|
unsigned int no_branch_instruction_retired:1;
|
|
unsigned int no_branch_misses_retired:1;
|
|
} split;
|
|
unsigned int full;
|
|
};
|
|
|
|
union cpuid10_edx {
|
|
struct {
|
|
unsigned int num_counters_fixed:5;
|
|
unsigned int bit_width_fixed:8;
|
|
unsigned int reserved:19;
|
|
} split;
|
|
unsigned int full;
|
|
};
|
|
|
|
struct x86_pmu_capability {
|
|
int version;
|
|
int num_counters_gp;
|
|
int num_counters_fixed;
|
|
int bit_width_gp;
|
|
int bit_width_fixed;
|
|
unsigned int events_mask;
|
|
int events_mask_len;
|
|
};
|
|
|
|
/*
|
|
* Fixed-purpose performance events:
|
|
*/
|
|
|
|
/*
|
|
* All 3 fixed-mode PMCs are configured via this single MSR:
|
|
*/
|
|
#define MSR_ARCH_PERFMON_FIXED_CTR_CTRL 0x38d
|
|
|
|
/*
|
|
* The counts are available in three separate MSRs:
|
|
*/
|
|
|
|
/* Instr_Retired.Any: */
|
|
#define MSR_ARCH_PERFMON_FIXED_CTR0 0x309
|
|
#define INTEL_PMC_IDX_FIXED_INSTRUCTIONS (INTEL_PMC_IDX_FIXED + 0)
|
|
|
|
/* CPU_CLK_Unhalted.Core: */
|
|
#define MSR_ARCH_PERFMON_FIXED_CTR1 0x30a
|
|
#define INTEL_PMC_IDX_FIXED_CPU_CYCLES (INTEL_PMC_IDX_FIXED + 1)
|
|
|
|
/* CPU_CLK_Unhalted.Ref: */
|
|
#define MSR_ARCH_PERFMON_FIXED_CTR2 0x30b
|
|
#define INTEL_PMC_IDX_FIXED_REF_CYCLES (INTEL_PMC_IDX_FIXED + 2)
|
|
#define INTEL_PMC_MSK_FIXED_REF_CYCLES (1ULL << INTEL_PMC_IDX_FIXED_REF_CYCLES)
|
|
|
|
/*
|
|
* We model BTS tracing as another fixed-mode PMC.
|
|
*
|
|
* We choose a value in the middle of the fixed event range, since lower
|
|
* values are used by actual fixed events and higher values are used
|
|
* to indicate other overflow conditions in the PERF_GLOBAL_STATUS msr.
|
|
*/
|
|
#define INTEL_PMC_IDX_FIXED_BTS (INTEL_PMC_IDX_FIXED + 16)
|
|
|
|
/*
|
|
* IBS cpuid feature detection
|
|
*/
|
|
|
|
#define IBS_CPUID_FEATURES 0x8000001b
|
|
|
|
/*
|
|
* Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but
|
|
* bit 0 is used to indicate the existence of IBS.
|
|
*/
|
|
#define IBS_CAPS_AVAIL (1U<<0)
|
|
#define IBS_CAPS_FETCHSAM (1U<<1)
|
|
#define IBS_CAPS_OPSAM (1U<<2)
|
|
#define IBS_CAPS_RDWROPCNT (1U<<3)
|
|
#define IBS_CAPS_OPCNT (1U<<4)
|
|
#define IBS_CAPS_BRNTRGT (1U<<5)
|
|
#define IBS_CAPS_OPCNTEXT (1U<<6)
|
|
#define IBS_CAPS_RIPINVALIDCHK (1U<<7)
|
|
|
|
#define IBS_CAPS_DEFAULT (IBS_CAPS_AVAIL \
|
|
| IBS_CAPS_FETCHSAM \
|
|
| IBS_CAPS_OPSAM)
|
|
|
|
/*
|
|
* IBS APIC setup
|
|
*/
|
|
#define IBSCTL 0x1cc
|
|
#define IBSCTL_LVT_OFFSET_VALID (1ULL<<8)
|
|
#define IBSCTL_LVT_OFFSET_MASK 0x0F
|
|
|
|
/* ibs fetch bits/masks */
|
|
#define IBS_FETCH_RAND_EN (1ULL<<57)
|
|
#define IBS_FETCH_VAL (1ULL<<49)
|
|
#define IBS_FETCH_ENABLE (1ULL<<48)
|
|
#define IBS_FETCH_CNT 0xFFFF0000ULL
|
|
#define IBS_FETCH_MAX_CNT 0x0000FFFFULL
|
|
|
|
/* ibs op bits/masks */
|
|
/* lower 4 bits of the current count are ignored: */
|
|
#define IBS_OP_CUR_CNT (0xFFFF0ULL<<32)
|
|
#define IBS_OP_CNT_CTL (1ULL<<19)
|
|
#define IBS_OP_VAL (1ULL<<18)
|
|
#define IBS_OP_ENABLE (1ULL<<17)
|
|
#define IBS_OP_MAX_CNT 0x0000FFFFULL
|
|
#define IBS_OP_MAX_CNT_EXT 0x007FFFFFULL /* not a register bit mask */
|
|
#define IBS_RIP_INVALID (1ULL<<38)
|
|
|
|
#ifdef CONFIG_X86_LOCAL_APIC
|
|
extern u32 get_ibs_caps(void);
|
|
#else
|
|
static inline u32 get_ibs_caps(void) { return 0; }
|
|
#endif
|
|
|
|
#ifdef CONFIG_PERF_EVENTS
|
|
extern void perf_events_lapic_init(void);
|
|
|
|
/*
|
|
* Abuse bits {3,5} of the cpu eflags register. These flags are otherwise
|
|
* unused and ABI specified to be 0, so nobody should care what we do with
|
|
* them.
|
|
*
|
|
* EXACT - the IP points to the exact instruction that triggered the
|
|
* event (HW bugs exempt).
|
|
* VM - original X86_VM_MASK; see set_linear_ip().
|
|
*/
|
|
#define PERF_EFLAGS_EXACT (1UL << 3)
|
|
#define PERF_EFLAGS_VM (1UL << 5)
|
|
|
|
struct pt_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)
|
|
|
|
#include <asm/stacktrace.h>
|
|
|
|
/*
|
|
* We abuse bit 3 from flags to pass exact information, see perf_misc_flags
|
|
* and the comment with PERF_EFLAGS_EXACT.
|
|
*/
|
|
#define perf_arch_fetch_caller_regs(regs, __ip) { \
|
|
(regs)->ip = (__ip); \
|
|
(regs)->bp = caller_frame_pointer(); \
|
|
(regs)->cs = __KERNEL_CS; \
|
|
regs->flags = 0; \
|
|
asm volatile( \
|
|
_ASM_MOV "%%"_ASM_SP ", %0\n" \
|
|
: "=m" ((regs)->sp) \
|
|
:: "memory" \
|
|
); \
|
|
}
|
|
|
|
struct perf_guest_switch_msr {
|
|
unsigned msr;
|
|
u64 host, guest;
|
|
};
|
|
|
|
extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
|
|
extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
|
|
extern void perf_check_microcode(void);
|
|
#else
|
|
static inline struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
|
|
{
|
|
*nr = 0;
|
|
return NULL;
|
|
}
|
|
|
|
static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
|
|
{
|
|
memset(cap, 0, sizeof(*cap));
|
|
}
|
|
|
|
static inline void perf_events_lapic_init(void) { }
|
|
static inline void perf_check_microcode(void) { }
|
|
#endif
|
|
|
|
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
|
|
extern void amd_pmu_enable_virt(void);
|
|
extern void amd_pmu_disable_virt(void);
|
|
#else
|
|
static inline void amd_pmu_enable_virt(void) { }
|
|
static inline void amd_pmu_disable_virt(void) { }
|
|
#endif
|
|
|
|
#define arch_perf_out_copy_user copy_from_user_nmi
|
|
|
|
#endif /* _ASM_X86_PERF_EVENT_H */
|