/*
* Performance events x86 architecture header
*
* Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
* Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
* Copyright (C) 2009 Jaswinder Singh Rajput
* Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
* Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
* Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
* Copyright (C) 2009 Google, Inc., Stephane Eranian
*
* For licencing details see kernel-base/COPYING
*/
#include <linux/perf_event.h>
#include <asm/intel_ds.h>
/* To enable MSR tracing please use the generic trace points. */
/*
* | NHM/WSM | SNB |
* register -------------------------------
* | HT | no HT | HT | no HT |
*-----------------------------------------
* offcore | core | core | cpu | core |
* lbr_sel | core | core | cpu | core |
* ld_lat | cpu | core | cpu | core |
*-----------------------------------------
*
* Given that there is a small number of shared regs,
* we can pre-allocate their slot in the per-cpu
* per-core reg tables.
*/
enum extra_reg_type {
EXTRA_REG_NONE = -1, /* not used */
EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */
EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */
EXTRA_REG_LBR = 2, /* lbr_select */
EXTRA_REG_LDLAT = 3, /* ld_lat_threshold */
EXTRA_REG_FE = 4, /* fe_* */
EXTRA_REG_MAX /* number of entries needed */
};
struct event_constraint {
union {
unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
u64 idxmsk64;
};
u64 code;
u64 cmask;
int weight;
int overlap;
int flags;
unsigned int size;
};
static inline bool constraint_match(struct event_constraint *c, u64 ecode)
{
return ((ecode & c->cmask) - c->code) <= (u64)c->size;
}
/*
* struct hw_perf_event.flags flags
*/
#define PERF_X86_EVENT_PEBS_LDLAT 0x0001 /* ld+ldlat data address sampling */
#define PERF_X86_EVENT_PEBS_ST 0x0002 /* st data address sampling */
#define PERF_X86_EVENT_PEBS_ST_HSW 0x0004 /* haswell style datala, store */
#define PERF_X86_EVENT_PEBS_LD_HSW 0x0008 /* haswell style datala, load */
#define PERF_X86_EVENT_PEBS_NA_HSW 0x0010 /* haswell style datala, unknown */
#define PERF_X86_EVENT_EXCL 0x0020 /* HT exclusivity on counter */
#define PERF_X86_EVENT_DYNAMIC 0x0040 /* dynamic alloc'd constraint */
#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0080 /* grant rdpmc permission */
#define PERF_X86_EVENT_EXCL_ACCT 0x0100 /* accounted EXCL event */
#define PERF_X86_EVENT_AUTO_RELOAD 0x0200 /* use PEBS auto-reload */
#define PERF_X86_EVENT_LARGE_PEBS 0x0400 /* use large PEBS */
#define PERF_X86_EVENT_PEBS_VIA_PT 0x0800 /* use PT buffer for PEBS */
#define PERF_X86_EVENT_PAIR 0x1000 /* Large Increment per Cycle */
#define PERF_X86_EVENT_LBR_SELECT 0x2000 /* Save/Restore MSR_LBR_SELECT */
struct amd_nb {
int nb_id; /* NorthBridge id */
int refcnt; /* reference count */
struct perf_event *owners[X86_PMC_IDX_MAX];
struct event_constraint event_constraints[X86_PMC_IDX_MAX];
};
#define PEBS_COUNTER_MASK ((1ULL << MAX_PEBS_EVENTS) - 1)
#define PEBS_PMI_AFTER_EACH_RECORD BIT_ULL(60)
#define PEBS_OUTPUT_OFFSET 61
#define PEBS_OUTPUT_MASK (3ull << PEBS_OUTPUT_OFFSET)
#define PEBS_OUTPUT_PT (1ull << PEBS_OUTPUT_OFFSET)
#define PEBS_VIA_PT_MASK (PEBS_OUTPUT_PT | PEBS_PMI_AFTER_EACH_RECORD)
/*
* Flags PEBS can handle without an PMI.
*
* TID can only be handled by flushing at context switch.
* REGS_USER can be handled for events limited to ring 3.
*
*/
#define LARGE_PEBS_FLAGS \
(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \
PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
PERF_SAMPLE_PERIOD)
#define PEBS_GP_REGS \
((1ULL << PERF_REG_X86_AX) | \
(1ULL << PERF_REG_X86_BX) | \
(1ULL << PERF_REG_X86_CX) | \
(1ULL << PERF_REG_X86_DX) | \
(1ULL << PERF_REG_X86_DI) | \
(1ULL << PERF_REG_X86_SI) | \
(1ULL << PERF_REG_X86_SP) | \
(1ULL << PERF_REG_X86_BP) | \
(1ULL << PERF_REG_X86_IP) | \
(1ULL << PERF_REG_X86_FLAGS) | \
(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))
/*
* Per register state.
*/
struct er_account {
raw_spinlock_t lock; /* per-core: protect structure */
u64 config; /* extra MSR config */
u64 reg; /* extra MSR number */
atomic_t ref; /* reference count */
};
/*
* Per core/cpu state
*
* Used to coordinate shared registers between HT threads or
* among events on a single PMU.
*/
struct intel_shared_regs {
struct er_account regs[EXTRA_REG_MAX