aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/events
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/events')
-rw-r--r--arch/x86/events/amd/core.c111
-rw-r--r--arch/x86/events/core.c95
-rw-r--r--arch/x86/events/intel/core.c306
-rw-r--r--arch/x86/events/intel/cstate.c2
-rw-r--r--arch/x86/events/intel/ds.c505
-rw-r--r--arch/x86/events/intel/lbr.c35
-rw-r--r--arch/x86/events/intel/pt.c3
-rw-r--r--arch/x86/events/intel/rapl.c2
-rw-r--r--arch/x86/events/intel/uncore.c6
-rw-r--r--arch/x86/events/intel/uncore.h1
-rw-r--r--arch/x86/events/intel/uncore_snb.c91
-rw-r--r--arch/x86/events/msr.c1
-rw-r--r--arch/x86/events/perf_event.h98
13 files changed, 1116 insertions, 140 deletions
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index d45f3fbd232e..f15441b07dad 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -116,6 +116,110 @@ static __initconst const u64 amd_hw_cache_event_ids
},
};
+static __initconst const u64 amd_hw_cache_event_ids_f17h
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+[C(L1D)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x0040, /* Data Cache Accesses */
+ [C(RESULT_MISS)] = 0xc860, /* L2$ access from DC Miss */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0xff5a, /* h/w prefetch DC Fills */
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x0080, /* Instruction cache fetches */
+ [C(RESULT_MISS)] = 0x0081, /* Instruction cache misses */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(DTLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0xff45, /* All L2 DTLB accesses */
+ [C(RESULT_MISS)] = 0xf045, /* L2 DTLB misses (PT walks) */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x0084, /* L1 ITLB misses, L2 ITLB hits */
+ [C(RESULT_MISS)] = 0xff85, /* L1 ITLB misses, L2 misses */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+},
+[C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x00c2, /* Retired Branch Instr. */
+ [C(RESULT_MISS)] = 0x00c3, /* Retired Mispredicted BI */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+},
+[C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+},
+};
+
/*
* AMD Performance Monitor K7 and later, up to and including Family 16h:
*/
@@ -865,9 +969,10 @@ __init int amd_pmu_init(void)
x86_pmu.amd_nb_constraints = 0;
}
- /* Events are common for all AMDs */
- memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
- sizeof(hw_cache_event_ids));
+ if (boot_cpu_data.x86 >= 0x17)
+ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids_f17h, sizeof(hw_cache_event_ids));
+ else
+ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids));
return 0;
}
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 81911e11a15d..f315425d8468 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -560,6 +560,21 @@ 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);
}
@@ -661,6 +676,10 @@ static inline int is_x86_event(struct perf_event *event)
return event->pmu == &pmu;
}
+struct pmu *x86_get_pmu(void)
+{
+ return &pmu;
+}
/*
* Event scheduler state:
*
@@ -849,18 +868,43 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
struct event_constraint *c;
unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
struct perf_event *e;
- int i, wmin, wmax, unsched = 0;
+ int n0, i, wmin, wmax, unsched = 0;
struct hw_perf_event *hwc;
bitmap_zero(used_mask, X86_PMC_IDX_MAX);
+ /*
+ * Compute the number of events already present; see x86_pmu_add(),
+ * validate_group() and x86_pmu_commit_txn(). For the former two
+ * cpuc->n_events hasn't been updated yet, while for the latter
+ * cpuc->n_txn contains the number of events added in the current
+ * transaction.
+ */
+ n0 = cpuc->n_events;
+ if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
+ n0 -= cpuc->n_txn;
+
if (x86_pmu.start_scheduling)
x86_pmu.start_scheduling(cpuc);
for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) {
- cpuc->event_constraint[i] = NULL;
- c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
- cpuc->event_constraint[i] = c;
+ c = cpuc->event_constraint[i];
+
+ /*
+ * Previously scheduled events should have a cached constraint,
+ * while new events should not have one.
+ */
+ WARN_ON_ONCE((c && i >= n0) || (!c && i < n0));
+
+ /*
+ * Request constraints for new events; or for those events that
+ * have a dynamic constraint -- for those the constraint can
+ * change due to external factors (sibling state, allow_tfa).
+ */
+ if (!c || (c->flags & PERF_X86_EVENT_DYNAMIC)) {
+ c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
+ cpuc->event_constraint[i] = c;
+ }
wmin = min(wmin, c->weight);
wmax = max(wmax, c->weight);
@@ -925,25 +969,20 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
if (!unsched && assign) {
for (i = 0; i < n; i++) {
e = cpuc->event_list[i];
- e->hw.flags |= PERF_X86_EVENT_COMMITTED;
if (x86_pmu.commit_scheduling)
x86_pmu.commit_scheduling(cpuc, i, assign[i]);
}
} else {
- for (i = 0; i < n; i++) {
+ for (i = n0; i < n; i++) {
e = cpuc->event_list[i];
- /*
- * do not put_constraint() on comitted events,
- * because they are good to go
- */
- if ((e->hw.flags & PERF_X86_EVENT_COMMITTED))
- continue;
/*
* release events that failed scheduling
*/
if (x86_pmu.put_event_constraints)
x86_pmu.put_event_constraints(cpuc, e);
+
+ cpuc->event_constraint[i] = NULL;
}
}
@@ -1373,11 +1412,6 @@ static void x86_pmu_del(struct perf_event *event, int flags)
int i;
/*
- * event is descheduled
- */
- event->hw.flags &= ~PERF_X86_EVENT_COMMITTED;
-
- /*
* If we're called during a txn, we only need to undo x86_pmu.add.
* The events never got scheduled and ->cancel_txn will truncate
* the event_list.
@@ -1413,6 +1447,7 @@ static void x86_pmu_del(struct perf_event *event, int flags)
cpuc->event_list[i-1] = cpuc->event_list[i];
cpuc->event_constraint[i-1] = cpuc->event_constraint[i];
}
+ cpuc->event_constraint[i-1] = NULL;
--cpuc->n_events;
perf_event_update_userpage(event);
@@ -2024,7 +2059,7 @@ static int validate_event(struct perf_event *event)
if (IS_ERR(fake_cpuc))
return PTR_ERR(fake_cpuc);
- c = x86_pmu.get_event_constraints(fake_cpuc, -1, event);
+ c = x86_pmu.get_event_constraints(fake_cpuc, 0, event);
if (!c || !c->weight)
ret = -EINVAL;
@@ -2072,8 +2107,7 @@ static int validate_group(struct perf_event *event)
if (n < 0)
goto out;
- fake_cpuc->n_events = n;
-
+ fake_cpuc->n_events = 0;
ret = x86_pmu.schedule_events(fake_cpuc, n, NULL);
out:
@@ -2348,6 +2382,15 @@ void arch_perf_update_userpage(struct perf_event *event,
cyc2ns_read_end();
}
+/*
+ * Determine whether the regs were taken from an irq/exception handler rather
+ * than from perf_arch_fetch_caller_regs().
+ */
+static bool perf_hw_regs(struct pt_regs *regs)
+{
+ return regs->flags & X86_EFLAGS_FIXED;
+}
+
void
perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
@@ -2359,11 +2402,15 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
return;
}
- if (perf_callchain_store(entry, regs->ip))
- return;
+ if (perf_hw_regs(regs)) {
+ if (perf_callchain_store(entry, regs->ip))
+ return;
+ unwind_start(&state, current, regs, NULL);
+ } else {
+ unwind_start(&state, current, NULL, (void *)regs->sp);
+ }
- for (unwind_start(&state, current, regs, NULL); !unwind_done(&state);
- unwind_next_frame(&state)) {
+ for (; !unwind_done(&state); unwind_next_frame(&state)) {
addr = unwind_get_return_address(&state);
if (!addr || perf_callchain_store(entry, addr))
return;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index f9451566cd9b..ef763f535e3a 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -239,6 +239,35 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = {
EVENT_EXTRA_END
};
+static struct event_constraint intel_icl_event_constraints[] = {
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ INTEL_UEVENT_CONSTRAINT(0x1c0, 0), /* INST_RETIRED.PREC_DIST */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */
+ INTEL_EVENT_CONSTRAINT_RANGE(0x03, 0x0a, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0x1f, 0x28, 0xf),
+ INTEL_EVENT_CONSTRAINT(0x32, 0xf), /* SW_PREFETCH_ACCESS.* */
+ INTEL_EVENT_CONSTRAINT_RANGE(0x48, 0x54, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0x60, 0x8b, 0xf),
+ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xff), /* CYCLE_ACTIVITY.STALLS_TOTAL */
+ INTEL_UEVENT_CONSTRAINT(0x10a3, 0xff), /* CYCLE_ACTIVITY.STALLS_MEM_ANY */
+ INTEL_EVENT_CONSTRAINT(0xa3, 0xf), /* CYCLE_ACTIVITY.* */
+ INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf),
+ EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg intel_icl_extra_regs[] __read_mostly = {
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff9fffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff9fffull, RSP_1),
+ INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+ INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
+ EVENT_EXTRA_END
+};
+
EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
@@ -1827,6 +1856,45 @@ static __initconst const u64 glp_hw_cache_extra_regs
},
};
+#define TNT_LOCAL_DRAM BIT_ULL(26)
+#define TNT_DEMAND_READ GLM_DEMAND_DATA_RD
+#define TNT_DEMAND_WRITE GLM_DEMAND_RFO
+#define TNT_LLC_ACCESS GLM_ANY_RESPONSE
+#define TNT_SNP_ANY (SNB_SNP_NOT_NEEDED|SNB_SNP_MISS| \
+ SNB_NO_FWD|SNB_SNP_FWD|SNB_HITM)
+#define TNT_LLC_MISS (TNT_SNP_ANY|SNB_NON_DRAM|TNT_LOCAL_DRAM)
+
+static __initconst const u64 tnt_hw_cache_extra_regs
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = TNT_DEMAND_READ|
+ TNT_LLC_ACCESS,
+ [C(RESULT_MISS)] = TNT_DEMAND_READ|
+ TNT_LLC_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = TNT_DEMAND_WRITE|
+ TNT_LLC_ACCESS,
+ [C(RESULT_MISS)] = TNT_DEMAND_WRITE|
+ TNT_LLC_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0x0,
+ [C(RESULT_MISS)] = 0x0,
+ },
+ },
+};
+
+static struct extra_reg intel_tnt_extra_regs[] __read_mostly = {
+ /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffffff9fffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xffffff9fffull, RSP_1),
+ EVENT_EXTRA_END
+};
+
#define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */
#define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */
#define KNL_MCDRAM_LOCAL BIT_ULL(21)
@@ -2015,7 +2083,7 @@ static void intel_tfa_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int
/*
* We're going to use PMC3, make sure TFA is set before we touch it.
*/
- if (cntr == 3 && !cpuc->is_fake)
+ if (cntr == 3)
intel_set_tfa(cpuc, true);
}
@@ -2091,15 +2159,19 @@ static void intel_pmu_disable_event(struct perf_event *event)
cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
cpuc->intel_cp_status &= ~(1ull << hwc->idx);
- if (unlikely(event->attr.precise_ip))
- intel_pmu_pebs_disable(event);
-
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_disable_fixed(hwc);
return;
}
x86_pmu_disable_event(event);
+
+ /*
+ * Needs to be called after x86_pmu_disable_event,
+ * so we don't trigger the event without PEBS bit set.
+ */
+ if (unlikely(event->attr.precise_ip))
+ intel_pmu_pebs_disable(event);
}
static void intel_pmu_del_event(struct perf_event *event)
@@ -2145,6 +2217,11 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
bits <<= (idx * 4);
mask = 0xfULL << (idx * 4);
+ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip) {
+ bits |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
+ mask |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
+ }
+
rdmsrl(hwc->config_base, ctrl_val);
ctrl_val &= ~mask;
ctrl_val |= bits;
@@ -2688,7 +2765,7 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
if (x86_pmu.event_constraints) {
for_each_event_constraint(c, x86_pmu.event_constraints) {
- if ((event->hw.config & c->cmask) == c->code) {
+ if (constraint_match(c, event->hw.config)) {
event->hw.flags |= c->flags;
return c;
}
@@ -2838,7 +2915,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
struct intel_excl_states *xlo;
int tid = cpuc->excl_thread_id;
- int is_excl, i;
+ int is_excl, i, w;
/*
* validating a group does not require
@@ -2894,36 +2971,40 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
* SHARED : sibling counter measuring non-exclusive event
* UNUSED : sibling counter unused
*/
+ w = c->weight;
for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) {
/*
* exclusive event in sibling counter
* our corresponding counter cannot be used
* regardless of our event
*/
- if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE)
+ if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) {
__clear_bit(i, c->idxmsk);
+ w--;
+ continue;
+ }
/*
* if measuring an exclusive event, sibling
* measuring non-exclusive, then counter cannot
* be used
*/
- if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED)
+ if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) {
__clear_bit(i, c->idxmsk);
+ w--;
+ continue;
+ }
}
/*
- * recompute actual bit weight for scheduling algorithm
- */
- c->weight = hweight64(c->idxmsk64);
-
- /*
* if we return an empty mask, then switch
* back to static empty constraint to avoid
* the cost of freeing later on
*/
- if (c->weight == 0)
+ if (!w)
c = &emptyconstraint;
+ c->weight = w;
+
return c;
}
@@ -2931,11 +3012,9 @@ static struct event_constraint *
intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
{
- struct event_constraint *c1 = NULL;
- struct event_constraint *c2;
+ struct event_constraint *c1, *c2;
- if (idx >= 0) /* fake does < 0 */
- c1 = cpuc->event_constraint[idx];
+ c1 = cpuc->event_constraint[idx];
/*
* first time only
@@ -2943,7 +3022,8 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
* - dynamic constraint: handled by intel_get_excl_constraints()
*/
c2 = __intel_get_event_constraints(cpuc, idx, event);
- if (c1 && (c1->flags & PERF_X86_EVENT_DYNAMIC)) {
+ if (c1) {
+ WARN_ON_ONCE(!(c1->flags & PERF_X86_EVENT_DYNAMIC));
bitmap_copy(c1->idxmsk, c2->idxmsk, X86_PMC_IDX_MAX);
c1->weight = c2->weight;
c2 = c1;
@@ -3366,6 +3446,12 @@ static struct event_constraint counter0_constraint =
static struct event_constraint counter2_constraint =
EVENT_CONSTRAINT(0, 0x4, 0);
+static struct event_constraint fixed0_constraint =
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0);
+
+static struct event_constraint fixed0_counter0_constraint =
+ INTEL_ALL_EVENT_CONSTRAINT(0, 0x100000001ULL);
+
static struct event_constraint *
hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
@@ -3385,6 +3471,21 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
}
static struct event_constraint *
+icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+ struct perf_event *event)
+{
+ /*
+ * Fixed counter 0 has less skid.
+ * Force instruction:ppp in Fixed counter 0
+ */
+ if ((event->attr.precise_ip == 3) &&
+ constraint_match(&fixed0_constraint, event->hw.config))
+ return &fixed0_constraint;
+
+ return hsw_get_event_constraints(cpuc, idx, event);
+}
+
+static struct event_constraint *
glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
{
@@ -3399,6 +3500,29 @@ glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
return c;
}
+static struct event_constraint *
+tnt_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+ struct perf_event *event)
+{
+ struct event_constraint *c;
+
+ /*
+ * :ppp means to do reduced skid PEBS,
+ * which is available on PMC0 and fixed counter 0.
+ */
+ if (event->attr.precise_ip == 3) {
+ /* Force instruction:ppp on PMC0 and Fixed counter 0 */
+ if (constraint_match(&fixed0_constraint, event->hw.config))
+ return &fixed0_counter0_constraint;
+
+ return &counter0_constraint;
+ }
+
+ c = intel_get_event_constraints(cpuc, idx, event);
+
+ return c;
+}
+
static bool allow_tsx_force_abort = true;
static struct event_constraint *
@@ -3410,7 +3534,7 @@ tfa_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
/*
* Without TFA we must not use PMC3.
*/
- if (!allow_tsx_force_abort && test_bit(3, c->idxmsk) && idx >= 0) {
+ if (!allow_tsx_force_abort && test_bit(3, c->idxmsk)) {
c = dyn_constraint(cpuc, c, idx);
c->idxmsk64 &= ~(1ULL << 3);
c->weight--;
@@ -3507,6 +3631,8 @@ static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu)
int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
{
+ cpuc->pebs_record_size = x86_pmu.pebs_record_size;
+
if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
cpuc->shared_regs = allocate_shared_regs(cpu);
if (!cpuc->shared_regs)
@@ -4114,6 +4240,42 @@ static struct attribute *hsw_tsx_events_attrs[] = {
NULL
};
+EVENT_ATTR_STR(tx-capacity-read, tx_capacity_read, "event=0x54,umask=0x80");
+EVENT_ATTR_STR(tx-capacity-write, tx_capacity_write, "event=0x54,umask=0x2");
+EVENT_ATTR_STR(el-capacity-read, el_capacity_read, "event=0x54,umask=0x80");
+EVENT_ATTR_STR(el-capacity-write, el_capacity_write, "event=0x54,umask=0x2");
+
+static struct attribute *icl_events_attrs[] = {
+ EVENT_PTR(mem_ld_hsw),
+ EVENT_PTR(mem_st_hsw),
+ NULL,
+};
+
+static struct attribute *icl_tsx_events_attrs[] = {
+ EVENT_PTR(tx_start),
+ EVENT_PTR(tx_abort),
+ EVENT_PTR(tx_commit),
+ EVENT_PTR(tx_capacity_read),
+ EVENT_PTR(tx_capacity_write),
+ EVENT_PTR(tx_conflict),
+ EVENT_PTR(el_start),
+ EVENT_PTR(el_abort),
+ EVENT_PTR(el_commit),
+ EVENT_PTR(el_capacity_read),
+ EVENT_PTR(el_capacity_write),
+ EVENT_PTR(el_conflict),
+ EVENT_PTR(cycles_t),
+ EVENT_PTR(cycles_ct),
+ NULL,
+};
+
+static __init struct attribute **get_icl_events_attrs(void)
+{
+ return boot_cpu_has(X86_FEATURE_RTM) ?
+ merge_attr(icl_events_attrs, icl_tsx_events_attrs) :
+ icl_events_attrs;
+}
+
static ssize_t freeze_on_smi_show(struct device *cdev,
struct device_attribute *attr,
char *buf)
@@ -4153,6 +4315,50 @@ done:
return count;
}
+static void update_tfa_sched(void *ignored)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ /*
+ * check if PMC3 is used
+ * and if so force schedule out for all event types all contexts
+ */
+ if (test_bit(3, cpuc->active_mask))
+ perf_pmu_resched(x86_get_pmu());
+}
+
+static ssize_t show_sysctl_tfa(struct device *cdev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return snprintf(buf, 40, "%d\n", allow_tsx_force_abort);
+}
+
+static ssize_t set_sysctl_tfa(struct device *cdev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ bool val;
+ ssize_t ret;
+
+ ret = kstrtobool(buf, &val);
+ if (ret)
+ return ret;
+
+ /* no change */
+ if (val == allow_tsx_force_abort)
+ return count;
+
+ allow_tsx_force_abort = val;
+
+ get_online_cpus();
+ on_each_cpu(update_tfa_sched, NULL, 1);
+ put_online_cpus();
+
+ return count;
+}
+
+
static DEVICE_ATTR_RW(freeze_on_smi);
static ssize_t branches_show(struct device *cdev,
@@ -4185,7 +4391,9 @@ static struct attribute *intel_pmu_caps_attrs[] = {
NULL
};
-static DEVICE_BOOL_ATTR(allow_tsx_force_abort, 0644, allow_tsx_force_abort);
+static DEVICE_ATTR(allow_tsx_force_abort, 0644,
+ show_sysctl_tfa,
+ set_sysctl_tfa);
static struct attribute *intel_pmu_attrs[] = {
&dev_attr_freeze_on_smi.attr,
@@ -4446,6 +4654,32 @@ __init int intel_pmu_init(void)
name = "goldmont_plus";
break;
+ case INTEL_FAM6_ATOM_TREMONT_X:
+ x86_pmu.late_ack = true;
+ memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs,
+ sizeof(hw_cache_extra_regs));
+ hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+
+ intel_pmu_lbr_init_skl();
+
+ x86_pmu.event_constraints = intel_slm_event_constraints;
+ x86_pmu.extra_regs = intel_tnt_extra_regs;
+ /*
+ * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
+ * for precise cycles.
+ */
+ x86_pmu.pebs_aliases = NULL;
+ x86_pmu.pebs_prec_dist = true;
+ x86_pmu.lbr_pt_coexist = true;
+ x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ x86_pmu.get_event_constraints = tnt_get_event_constraints;
+ extra_attr = slm_format_attr;
+ pr_cont("Tremont events, ");
+ name = "Tremont";
+ break;
+
case INTEL_FAM6_WESTMERE:
case INTEL_FAM6_WESTMERE_EP:
case INTEL_FAM6_WESTMERE_EX:
@@ -4694,13 +4928,41 @@ __init int intel_pmu_init(void)
x86_pmu.get_event_constraints = tfa_get_event_constraints;
x86_pmu.enable_all = intel_tfa_pmu_enable_all;
x86_pmu.commit_scheduling = intel_tfa_commit_scheduling;
- intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr.attr;
+ intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr;
}
pr_cont("Skylake events, ");
name = "skylake";
break;
+ case INTEL_FAM6_ICELAKE_MOBILE:
+ x86_pmu.late_ack = true;
+ memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+ hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+ intel_pmu_lbr_init_skl();
+
+ x86_pmu.event_constraints = intel_icl_event_constraints;
+ x86_pmu.pebs_constraints = intel_icl_pebs_event_constraints;
+ x86_pmu.extra_regs = intel_icl_extra_regs;
+ x86_pmu.pebs_aliases = NULL;
+ x86_pmu.pebs_prec_dist = true;
+ x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
+
+ x86_pmu.hw_config = hsw_hw_config;
+ x86_pmu.get_event_constraints = icl_get_event_constraints;
+ extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+ hsw_format_attr : nhm_format_attr;
+ extra_attr = merge_attr(extra_attr, skl_format_attr);
+ x86_pmu.cpu_events = get_icl_events_attrs();
+ x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
+ x86_pmu.lbr_pt_coexist = true;
+ intel_pmu_pebs_data_source_skl(false);
+ pr_cont("Icelake events, ");
+ name = "icelake";
+ break;
+
default:
switch (x86_pmu.version) {
case 1:
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index d41de9af7a39..6072f92cb8ea 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -578,6 +578,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_X, glm_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
+
+ X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_MOBILE, snb_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 10c99ce1fead..7a9f5dac5abe 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -849,6 +849,26 @@ struct event_constraint intel_skl_pebs_event_constraints[] = {
EVENT_CONSTRAINT_END
};
+struct event_constraint intel_icl_pebs_event_constraints[] = {
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x400000000ULL), /* SLOTS */
+
+ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */
+
+ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */
+
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */
+
+ /*
+ * Everything else is handled by PMU_FL_PEBS_ALL, because we
+ * need the full constraints from the main table.
+ */
+
+ EVENT_CONSTRAINT_END
+};
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event)
{
struct event_constraint *c;
@@ -858,7 +878,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
if (x86_pmu.pebs_constraints) {
for_each_event_constraint(c, x86_pmu.pebs_constraints) {
- if ((event->hw.config & c->cmask) == c->code) {
+ if (constraint_match(c, event->hw.config)) {
event->hw.flags |= c->flags;
return c;
}
@@ -906,17 +926,87 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
if (cpuc->n_pebs == cpuc->n_large_pebs) {
threshold = ds->pebs_absolute_maximum -
- reserved * x86_pmu.pebs_record_size;
+ reserved * cpuc->pebs_record_size;
} else {
- threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+ threshold = ds->pebs_buffer_base + cpuc->pebs_record_size;
}
ds->pebs_interrupt_threshold = threshold;
}
+static void adaptive_pebs_record_size_update(void)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ u64 pebs_data_cfg = cpuc->pebs_data_cfg;
+ int sz = sizeof(struct pebs_basic);
+
+ if (pebs_data_cfg & PEBS_DATACFG_MEMINFO)
+ sz += sizeof(struct pebs_meminfo);
+ if (pebs_data_cfg & PEBS_DATACFG_GP)
+ sz += sizeof(struct pebs_gprs);
+ if (pebs_data_cfg & PEBS_DATACFG_XMMS)
+ sz += sizeof(struct pebs_xmm);
+ if (pebs_data_cfg & PEBS_DATACFG_LBRS)
+ sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry);
+
+ cpuc->pebs_record_size = sz;
+}
+
+#define PERF_PEBS_MEMINFO_TYPE (PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC | \
+ PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \
+ PERF_SAMPLE_TRANSACTION)
+
+static u64 pebs_update_adaptive_cfg(struct perf_event *event)
+{
+ struct perf_event_attr *attr = &event->attr;
+ u64 sample_type = attr->sample_type;
+ u64 pebs_data_cfg = 0;
+ bool gprs, tsx_weight;
+
+ if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) &&
+ attr->precise_ip > 1)
+ return pebs_data_cfg;
+
+ if (sample_type & PERF_PEBS_MEMINFO_TYPE)
+ pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
+
+ /*
+ * We need GPRs when:
+ * + user requested them
+ * + precise_ip < 2 for the non event IP
+ * + For RTM TSX weight we need GPRs for the abort code.
+ */
+ gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr & PEBS_GP_REGS);
+
+ tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
+ ((attr->config & INTEL_ARCH_EVENT_MASK) ==
+ x86_pmu.rtm_abort_event);
+
+ if (gprs || (attr->precise_ip < 2) || tsx_weight)
+ pebs_data_cfg |= PEBS_DATACFG_GP;
+
+ if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr & PEBS_XMM_REGS))
+ pebs_data_cfg |= PEBS_DATACFG_XMMS;
+
+ if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+ /*
+ * For now always log all LBRs. Could configure this
+ * later.
+ */
+ pebs_data_cfg |= PEBS_DATACFG_LBRS |
+ ((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT);
+ }
+
+ return pebs_data_cfg;
+}
+
static void
-pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
+pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
+ struct perf_event *event, bool add)
{
+ struct pmu *pmu = event->ctx->pmu;
/*
* Make sure we get updated with the first PEBS
* event. It will trigger also during removal, but
@@ -933,6 +1023,29 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
update = true;
}
+ /*
+ * The PEBS record doesn't shrink on pmu::del(). Doing so would require
+ * iterating all remaining PEBS events to reconstruct the config.
+ */
+ if (x86_pmu.intel_cap.pebs_baseline && add) {
+ u64 pebs_data_cfg;
+
+ /* Clear pebs_data_cfg and pebs_record_size for first PEBS. */
+ if (cpuc->n_pebs == 1) {
+ cpuc->pebs_data_cfg = 0;
+ cpuc->pebs_record_size = sizeof(struct pebs_basic);
+ }
+
+ pebs_data_cfg = pebs_update_adaptive_cfg(event);
+
+ /* Update pebs_record_size if new event requires more data. */
+ if (pebs_data_cfg & ~cpuc->pebs_data_cfg) {
+ cpuc->pebs_data_cfg |= pebs_data_cfg;
+ adaptive_pebs_record_size_update();
+ update = true;
+ }
+ }
+
if (update)
pebs_update_threshold(cpuc);
}
@@ -947,7 +1060,7 @@ void intel_pmu_pebs_add(struct perf_event *event)
if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
cpuc->n_large_pebs++;
- pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+ pebs_update_state(needed_cb, cpuc, event, true);
}
void intel_pmu_pebs_enable(struct perf_event *event)
@@ -960,11 +1073,19 @@ void intel_pmu_pebs_enable(struct perf_event *event)
cpuc->pebs_enabled |= 1ULL << hwc->idx;
- if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+ if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && (x86_pmu.version < 5))
cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled |= 1ULL << 63;
+ if (x86_pmu.intel_cap.pebs_baseline) {
+ hwc->config |= ICL_EVENTSEL_ADAPTIVE;
+ if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) {
+ wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg);
+ cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg;
+ }
+ }
+
/*
* Use auto-reload if possible to save a MSR write in the PMI.
* This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
@@ -991,7 +1112,7 @@ void intel_pmu_pebs_del(struct perf_event *event)
if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
cpuc->n_large_pebs--;
- pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+ pebs_update_state(needed_cb, cpuc, event, false);
}
void intel_pmu_pebs_disable(struct perf_event *event)
@@ -1004,7 +1125,8 @@ void intel_pmu_pebs_disable(struct perf_event *event)
cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
- if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+ if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) &&
+ (x86_pmu.version < 5))
cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32));
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled &= ~(1ULL << 63);
@@ -1125,34 +1247,57 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
return 0;
}
-static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_weight(u64 tsx_tuning)
{
- if (pebs->tsx_tuning) {
- union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning };
+ if (tsx_tuning) {
+ union hsw_tsx_tuning tsx = { .value = tsx_tuning };
return tsx.cycles_last_block;
}
return 0;
}
-static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_transaction(u64 tsx_tuning, u64 ax)
{
- u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
+ u64 txn = (tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
/* For RTM XABORTs also log the abort code from AX */
- if ((txn & PERF_TXN_TRANSACTION) && (pebs->ax & 1))
- txn |= ((pebs->ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
+ if ((txn & PERF_TXN_TRANSACTION) && (ax & 1))
+ txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
return txn;
}
-static void setup_pebs_sample_data(struct perf_event *event,
- struct pt_regs *iregs, void *__pebs,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+static inline u64 get_pebs_status(void *n)
{
+ if (x86_pmu.intel_cap.pebs_format < 4)
+ return ((struct pebs_record_nhm *)n)->status;
+ return ((struct pebs_basic *)n)->applicable_counters;
+}
+
#define PERF_X86_EVENT_PEBS_HSW_PREC \
(PERF_X86_EVENT_PEBS_ST_HSW | \
PERF_X86_EVENT_PEBS_LD_HSW | \
PERF_X86_EVENT_PEBS_NA_HSW)
+
+static u64 get_data_src(struct perf_event *event, u64 aux)
+{
+ u64 val = PERF_MEM_NA;
+ int fl = event->hw.flags;
+ bool fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+
+ if (fl & PERF_X86_EVENT_PEBS_LDLAT)
+ val = load_latency_data(aux);
+ else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
+ val = precise_datala_hsw(event, aux);
+ else if (fst)
+ val = precise_store_data(aux);
+ return val;
+}
+
+static void setup_pebs_fixed_sample_data(struct perf_event *event,
+ struct pt_regs *iregs, void *__pebs,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
/*
* We cast to the biggest pebs_record but are careful not to
* unconditionally access the 'extra' entries.
@@ -1160,17 +1305,13 @@ static void setup_pebs_sample_data(struct perf_event *event,
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct pebs_record_skl *pebs = __pebs;
u64 sample_type;
- int fll, fst, dsrc;
- int fl = event->hw.flags;
+ int fll;
if (pebs == NULL)
return;
sample_type = event->attr.sample_type;
- dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
-
- fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
- fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+ fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;
perf_sample_data_init(data, 0, event->hw.last_period);
@@ -1185,16 +1326,8 @@ static void setup_pebs_sample_data(struct perf_event *event,
/*
* data.data_src encodes the data source
*/
- if (dsrc) {
- u64 val = PERF_MEM_NA;
- if (fll)
- val = load_latency_data(pebs->dse);
- else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
- val = precise_datala_hsw(event, pebs->dse);
- else if (fst)
- val = precise_store_data(pebs->dse);
- data->data_src.val = val;
- }
+ if (sample_type & PERF_SAMPLE_DATA_SRC)
+ data->data_src.val = get_data_src(event, pebs->dse);
/*
* We must however always use iregs for the unwinder to stay sane; the
@@ -1281,10 +1414,11 @@ static void setup_pebs_sample_data(struct perf_event *event,
if (x86_pmu.intel_cap.pebs_format >= 2) {
/* Only set the TSX weight when no memory weight. */
if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
- data->weight = intel_hsw_weight(pebs);
+ data->weight = intel_get_tsx_weight(pebs->tsx_tuning);
if (sample_type & PERF_SAMPLE_TRANSACTION)
- data->txn = intel_hsw_transaction(pebs);
+ data->txn = intel_get_tsx_transaction(pebs->tsx_tuning,
+ pebs->ax);
}
/*
@@ -1301,6 +1435,140 @@ static void setup_pebs_sample_data(struct perf_event *event,
data->br_stack = &cpuc->lbr_stack;
}
+static void adaptive_pebs_save_regs(struct pt_regs *regs,
+ struct pebs_gprs *gprs)
+{
+ regs->ax = gprs->ax;
+ regs->bx = gprs->bx;
+ regs->cx = gprs->cx;
+ regs->dx = gprs->dx;
+ regs->si = gprs->si;
+ regs->di = gprs->di;
+ regs->bp = gprs->bp;
+ regs->sp = gprs->sp;
+#ifndef CONFIG_X86_32
+ regs->r8 = gprs->r8;
+ regs->r9 = gprs->r9;
+ regs->r10 = gprs->r10;
+ regs->r11 = gprs->r11;
+ regs->r12 = gprs->r12;
+ regs->r13 = gprs->r13;
+ regs->r14 = gprs->r14;
+ regs->r15 = gprs->r15;
+#endif
+}
+
+/*
+ * With adaptive PEBS the layout depends on what fields are configured.
+ */
+
+static void setup_pebs_adaptive_sample_data(struct perf_event *event,
+ struct pt_regs *iregs, void *__pebs,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct pebs_basic *basic = __pebs;
+ void *next_record = basic + 1;
+ u64 sample_type;
+ u64 format_size;
+ struct pebs_meminfo *meminfo = NULL;
+ struct pebs_gprs *gprs = NULL;
+ struct x86_perf_regs *perf_regs;
+
+ if (basic == NULL)
+ return;
+
+ perf_regs = container_of(regs, struct x86_perf_regs, regs);
+ perf_regs->xmm_regs = NULL;
+
+ sample_type = event->attr.sample_type;
+ format_size = basic->format_size;
+ perf_sample_data_init(data, 0, event->hw.last_period);
+ data->period = event->hw.last_period;
+
+ if (event->attr.use_clockid == 0)
+ data->time = native_sched_clock_from_tsc(basic->tsc);
+
+ /*
+ * We must however always use iregs for the unwinder to stay sane; the
+ * record BP,SP,IP can point into thin air when the record is from a
+ * previous PMI context or an (I)RET happened between the record and
+ * PMI.
+ */
+ if (sample_type & PERF_SAMPLE_CALLCHAIN)
+ data->callchain = perf_callchain(event, iregs);
+
+ *regs = *iregs;
+ /* The ip in basic is EventingIP */
+ set_linear_ip(regs, basic->ip);
+ regs->flags = PERF_EFLAGS_EXACT;
+
+ /*
+ * The record for MEMINFO is in front of GP
+ * But PERF_SAMPLE_TRANSACTION needs gprs->ax.
+ * Save the pointer here but process later.
+ */
+ if (format_size & PEBS_DATACFG_MEMINFO) {
+ meminfo = next_record;
+ next_record = meminfo + 1;
+ }
+
+ if (format_size & PEBS_DATACFG_GP) {
+ gprs = next_record;
+ next_record = gprs + 1;
+
+ if (event->attr.precise_ip < 2) {
+ set_linear_ip(regs, gprs->ip);
+ regs->flags &= ~PERF_EFLAGS_EXACT;
+ }
+
+ if (sample_type & PERF_SAMPLE_REGS_INTR)
+ adaptive_pebs_save_regs(regs, gprs);
+ }
+
+ if (format_size & PEBS_DATACFG_MEMINFO) {
+ if (sample_type & PERF_SAMPLE_WEIGHT)
+ data->weight = meminfo->latency ?:
+ intel_get_tsx_weight(meminfo->tsx_tuning);
+
+ if (sample_type & PERF_SAMPLE_DATA_SRC)
+ data->data_src.val = get_data_src(event, meminfo->aux);
+
+ if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
+ data->addr = meminfo->address;
+
+ if (sample_type & PERF_SAMPLE_TRANSACTION)
+ data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning,
+ gprs ? gprs->ax : 0);
+ }
+
+ if (format_size & PEBS_DATACFG_XMMS) {
+ struct pebs_xmm *xmm = next_record;
+
+ next_record = xmm + 1;
+ perf_regs->xmm_regs = xmm->xmm;
+ }
+
+ if (format_size & PEBS_DATACFG_LBRS) {
+ struct pebs_lbr *lbr = next_record;
+ int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
+ & 0xff) + 1;
+ next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry);
+
+ if (has_branch_stack(event)) {
+ intel_pmu_store_pebs_lbrs(lbr);
+ data->br_stack = &cpuc->lbr_stack;
+ }
+ }
+
+ WARN_ONCE(next_record != __pebs + (format_size >> 48),
+ "PEBS record size %llu, expected %llu, config %llx\n",
+ format_size >> 48,
+ (u64)(next_record - __pebs),
+ basic->format_size);
+}
+
static inline void *
get_next_pebs_record_by_bit(void *base, void *top, int bit)
{
@@ -1318,19 +1586,19 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit)
if (base == NULL)
return NULL;
- for (at = base; at < top; at += x86_pmu.pebs_record_size) {
- struct pebs_record_nhm *p = at;
+ for (at = base; at < top; at += cpuc->pebs_record_size) {
+ unsigned long status = get_pebs_status(at);
- if (test_bit(bit, (unsigned long *)&p->status)) {
+ if (test_bit(bit, (unsigned long *)&status)) {
/* PEBS v3 has accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3)
return at;
- if (p->status == (1 << bit))
+ if (status == (1 << bit))
return at;
/* clear non-PEBS bit and re-check */
- pebs_status = p->status & cpuc->pebs_enabled;
+ pebs_status = status & cpuc->pebs_enabled;
pebs_status &= PEBS_COUNTER_MASK;
if (pebs_status == (1 << bit))
return at;
@@ -1410,11 +1678,18 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
static void __intel_pmu_pebs_event(struct perf_event *event,
struct pt_regs *iregs,
void *base, void *top,
- int bit, int count)
+ int bit, int count,
+ void (*setup_sample)(struct perf_event *,
+ struct pt_regs *,
+ void *,
+ struct perf_sample_data *,
+ struct pt_regs *))
{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
struct perf_sample_data data;
- struct pt_regs regs;
+ struct x86_perf_regs perf_regs;
+ struct pt_regs *regs = &perf_regs.regs;
void *at = get_next_pebs_record_by_bit(base, top, bit);
if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
@@ -1429,20 +1704,20 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
return;
while (count > 1) {
- setup_pebs_sample_data(event, iregs, at, &data, &regs);
- perf_event_output(event, &data, &regs);
- at += x86_pmu.pebs_record_size;
+ setup_sample(event, iregs, at, &data, regs);
+ perf_event_output(event, &data, regs);
+ at += cpuc->pebs_record_size;
at = get_next_pebs_record_by_bit(at, top, bit);
count--;
}
- setup_pebs_sample_data(event, iregs, at, &data, &regs);
+ setup_sample(event, iregs, at, &data, regs);
/*
* All but the last records are processed.
* The last one is left to be able to call the overflow handler.
*/
- if (perf_event_overflow(event, &data, &regs)) {
+ if (perf_event_overflow(event, &data, regs)) {
x86_pmu_stop(event, 0);
return;
}
@@ -1483,7 +1758,27 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
return;
}
- __intel_pmu_pebs_event(event, iregs, at, top, 0, n);
+ __intel_pmu_pebs_event(event, iregs, at, top, 0, n,
+ setup_pebs_fixed_sample_data);
+}
+
+static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
+{
+ struct perf_event *event;
+ int bit;
+
+ /*
+ * The drain_pebs() could be called twice in a short period
+ * for auto-reload event in pmu::read(). There are no
+ * overflows have happened in between.
+ * It needs to call intel_pmu_save_and_restart_reload() to
+ * update the event->count for this case.
+ */
+ for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) {
+ event = cpuc->events[bit];
+ if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
+ intel_pmu_save_and_restart_reload(event, 0);
+ }
}
static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
@@ -1513,19 +1808,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
}
if (unlikely(base >= top)) {
- /*
- * The drain_pebs() could be called twice in a short period
- * for auto-reload event in pmu::read(). There are no
- * overflows have happened in between.
- * It needs to call intel_pmu_save_and_restart_reload() to
- * update the event->count for this case.
- */
- for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled,
- size) {
- event = cpuc->events[bit];
- if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
- intel_pmu_save_and_restart_reload(event, 0);
- }
+ intel_pmu_pebs_event_update_no_drain(cpuc, size);
return;
}
@@ -1538,8 +1821,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
/* PEBS v3 has more accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3) {
- for_each_set_bit(bit, (unsigned long *)&pebs_status,
- size)
+ for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
counts[bit]++;
continue;
@@ -1578,8 +1860,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
* If collision happened, the record will be dropped.
*/
if (p->status != (1ULL << bit)) {
- for_each_set_bit(i, (unsigned long *)&pebs_status,
- x86_pmu.max_pebs_events)
+ for_each_set_bit(i, (unsigned long *)&pebs_status, size)
error[i]++;
continue;
}
@@ -1587,7 +1868,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
counts[bit]++;
}
- for (bit = 0; bit < size; bit++) {
+ for_each_set_bit(bit, (unsigned long *)&mask, size) {
if ((counts[bit] == 0) && (error[bit] == 0))
continue;
@@ -1608,11 +1889,66 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
if (counts[bit]) {
__intel_pmu_pebs_event(event, iregs, base,
- top, bit, counts[bit]);
+ top, bit, counts[bit],
+ setup_pebs_fixed_sample_data);
}
}
}
+static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs)
+{
+ short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct debug_store *ds = cpuc->ds;
+ struct perf_event *event;
+ void *base, *at, *top;
+ int bit, size;
+ u64 mask;
+
+ if (!x86_pmu.pebs_active)
+ return;
+
+ base = (struct pebs_basic *)(unsigned long)ds->pebs_buffer_base;
+ top = (struct pebs_basic *)(unsigned long)ds->pebs_index;
+
+ ds->pebs_index = ds->pebs_buffer_base;
+
+ mask = ((1ULL << x86_pmu.max_pebs_events) - 1) |
+ (((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED);
+ size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+
+ if (unlikely(base >= top)) {
+ intel_pmu_pebs_event_update_no_drain(cpuc, size);
+ return;
+ }
+
+ for (at = base; at < top; at += cpuc->pebs_record_size) {
+ u64 pebs_status;
+
+ pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
+ pebs_status &= mask;
+
+ for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
+ counts[bit]++;
+ }
+
+ for_each_set_bit(bit, (unsigned long *)&mask, size) {
+ if (counts[bit] == 0)
+ continue;
+
+ event = cpuc->events[bit];
+ if (WARN_ON_ONCE(!event))
+ continue;
+
+ if (WARN_ON_ONCE(!event->attr.precise_ip))
+ continue;
+
+ __intel_pmu_pebs_event(event, iregs, base,
+ top, bit, counts[bit],
+ setup_pebs_adaptive_sample_data);
+ }
+}
+
/*
* BTS, PEBS probe and setup
*/
@@ -1628,12 +1964,18 @@ 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)
+ if (x86_pmu.version <= 4) {
x86_pmu.pebs_no_isolation = 1;
+ x86_pmu.pebs_no_xmm_regs = 1;
+ }
if (x86_pmu.pebs) {
char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-';
+ char *pebs_qual = "";
int format = x86_pmu.intel_cap.pebs_format;
+ if (format < 4)
+ x86_pmu.intel_cap.pebs_baseline = 0;
+
switch (format) {
case 0:
pr_cont("PEBS fmt0%c, ", pebs_type);
@@ -1669,6 +2011,29 @@ void __init intel_ds_init(void)
x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
break;
+ case 4:
+ x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl;
+ x86_pmu.pebs_record_size = sizeof(struct pebs_basic);
+ if (x86_pmu.intel_cap.pebs_baseline) {
+ x86_pmu.large_pebs_flags |=
+ PERF_SAMPLE_BRANCH_STACK |
+ PERF_SAMPLE_TIME;
+ x86_pmu.flags |= PMU_FL_PEBS_ALL;
+ pebs_qual = "-baseline";
+ } else {
+ /* Only basic record supported */
+ x86_pmu.pebs_no_xmm_regs = 1;
+ x86_pmu.large_pebs_flags &=
+ ~(PERF_SAMPLE_ADDR |
+ PERF_SAMPLE_TIME |
+ PERF_SAMPLE_DATA_SRC |
+ PERF_SAMPLE_TRANSACTION |
+ PERF_SAMPLE_REGS_USER |
+ PERF_SAMPLE_REGS_INTR);
+ }
+ pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
+ break;
+
default:
pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
x86_pmu.pebs = 0;
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 580c1b91c454..6f814a27416b 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -488,6 +488,8 @@ void intel_pmu_lbr_add(struct perf_event *event)
* be 'new'. Conversely, a new event can get installed through the
* context switch path for the first time.
*/
+ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+ cpuc->lbr_pebs_users++;
perf_sched_cb_inc(event->ctx->pmu);
if (!cpuc->lbr_users++ && !event->total_time_running)
intel_pmu_lbr_reset();
@@ -507,8 +509,11 @@ void intel_pmu_lbr_del(struct perf_event *event)
task_ctx->lbr_callstack_users--;
}
+ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+ cpuc->lbr_pebs_users--;
cpuc->lbr_users--;
WARN_ON_ONCE(cpuc->lbr_users < 0);
+ WARN_ON_ONCE(cpuc->lbr_pebs_users < 0);
perf_sched_cb_dec(event->ctx->pmu);
}
@@ -658,7 +663,13 @@ void intel_pmu_lbr_read(void)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- if (!cpuc->lbr_users)
+ /*
+ * Don't read when all LBRs users are using adaptive PEBS.
+ *
+ * This could be smarter and actually check the event,
+ * but this simple approach seems to work for now.
+ */
+ if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users)
return;
if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
@@ -1080,6 +1091,28 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
}
}
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int i;
+
+ cpuc->lbr_stack.nr = x86_pmu.lbr_nr;
+ for (i = 0; i < x86_pmu.lbr_nr; i++) {
+ u64 info = lbr->lbr[i].info;
+ struct perf_branch_entry *e = &cpuc->lbr_entries[i];
+
+ e->from = lbr->lbr[i].from;
+ e->to = lbr->lbr[i].to;
+ e->mispred = !!(info & LBR_INFO_MISPRED);
+ e->predicted = !(info & LBR_INFO_MISPRED);
+ e->in_tx = !!(info & LBR_INFO_IN_TX);
+ e->abort = !!(info & LBR_INFO_ABORT);
+ e->cycles = info & LBR_INFO_CYCLES;
+ e->reserved = 0;
+ }
+ intel_pmu_lbr_filter(cpuc);
+}
+
/*
* Map interface branch filters onto LBR filters
*/
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index fb3a2f13fc70..339d7628080c 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1525,8 +1525,7 @@ static __init int pt_init(void)
}
if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
- pt_pmu.pmu.capabilities =
- PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF;
+ pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG;
pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE;
pt_pmu.pmu.attr_groups = pt_attr_groups;
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 94dc564146ca..37ebf6fc5415 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -775,6 +775,8 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init),
+
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, skl_rapl_init),
{},
};
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 9fe64c01a2e5..fc40a1473058 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1367,6 +1367,11 @@ static const struct intel_uncore_init_fun skx_uncore_init __initconst = {
.pci_init = skx_uncore_pci_init,
};
+static const struct intel_uncore_init_fun icl_uncore_init __initconst = {
+ .cpu_init = icl_uncore_cpu_init,
+ .pci_init = skl_uncore_pci_init,
+};
+
static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP, nhm_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM, nhm_uncore_init),
@@ -1393,6 +1398,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, icl_uncore_init),
{},
};
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 853a49a8ccf6..79eb2e21e4f0 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -512,6 +512,7 @@ int skl_uncore_pci_init(void);
void snb_uncore_cpu_init(void);
void nhm_uncore_cpu_init(void);
void skl_uncore_cpu_init(void);
+void icl_uncore_cpu_init(void);
int snb_pci2phy_map_init(int devid);
/* uncore_snbep.c */
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 13493f43b247..f8431819b3e1 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -34,6 +34,8 @@
#define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC 0x3e33
#define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC 0x3eca
#define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC 0x3e32
+#define PCI_DEVICE_ID_INTEL_ICL_U_IMC 0x8a02
+#define PCI_DEVICE_ID_INTEL_ICL_U2_IMC 0x8a12
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
@@ -93,6 +95,12 @@
#define SKL_UNC_PERF_GLOBAL_CTL 0xe01
#define SKL_UNC_GLOBAL_CTL_CORE_ALL ((1 << 5) - 1)
+/* ICL Cbo register */
+#define ICL_UNC_CBO_CONFIG 0x396
+#define ICL_UNC_NUM_CBO_MASK 0xf
+#define ICL_UNC_CBO_0_PER_CTR0 0x702
+#define ICL_UNC_CBO_MSR_OFFSET 0x8
+
DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
@@ -280,6 +288,70 @@ void skl_uncore_cpu_init(void)
snb_uncore_arb.ops = &skl_uncore_msr_ops;
}
+static struct intel_uncore_type icl_uncore_cbox = {
+ .name = "cbox",
+ .num_counters = 4,
+ .perf_ctr_bits = 44,
+ .perf_ctr = ICL_UNC_CBO_0_PER_CTR0,
+ .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0,
+ .event_mask = SNB_UNC_RAW_EVENT_MASK,
+ .msr_offset = ICL_UNC_CBO_MSR_OFFSET,
+ .ops = &skl_uncore_msr_ops,
+ .format_group = &snb_uncore_format_group,
+};
+
+static struct uncore_event_desc icl_uncore_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff"),
+ { /* end: all zeroes */ },
+};
+
+static struct attribute *icl_uncore_clock_formats_attr[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static struct attribute_group icl_uncore_clock_format_group = {
+ .name = "format",
+ .attrs = icl_uncore_clock_formats_attr,
+};
+
+static struct intel_uncore_type icl_uncore_clockbox = {
+ .name = "clock",
+ .num_counters = 1,
+ .num_boxes = 1,
+ .fixed_ctr_bits = 48,
+ .fixed_ctr = SNB_UNC_FIXED_CTR,
+ .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL,
+ .single_fixed = 1,
+ .event_mask = SNB_UNC_CTL_EV_SEL_MASK,
+ .format_group = &icl_uncore_clock_format_group,
+ .ops = &skl_uncore_msr_ops,
+ .event_descs = icl_uncore_events,
+};
+
+static struct intel_uncore_type *icl_msr_uncores[] = {
+ &icl_uncore_cbox,
+ &snb_uncore_arb,
+ &icl_uncore_clockbox,
+ NULL,
+};
+
+static int icl_get_cbox_num(void)
+{
+ u64 num_boxes;
+
+ rdmsrl(ICL_UNC_CBO_CONFIG, num_boxes);
+
+ return num_boxes & ICL_UNC_NUM_CBO_MASK;
+}
+
+void icl_uncore_cpu_init(void)
+{
+ uncore_msr_uncores = icl_msr_uncores;
+ icl_uncore_cbox.num_boxes = icl_get_cbox_num();
+ snb_uncore_arb.ops = &skl_uncore_msr_ops;
+}
+
enum {
SNB_PCI_UNCORE_IMC,
};
@@ -668,6 +740,18 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
{ /* end: all zeroes */ },
};
+static const struct pci_device_id icl_uncore_pci_ids[] = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U2_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
static struct pci_driver snb_uncore_pci_driver = {
.name = "snb_uncore",
.id_table = snb_uncore_pci_ids,
@@ -693,6 +777,11 @@ static struct pci_driver skl_uncore_pci_driver = {
.id_table = skl_uncore_pci_ids,
};
+static struct pci_driver icl_uncore_pci_driver = {
+ .name = "icl_uncore",
+ .id_table = icl_uncore_pci_ids,
+};
+
struct imc_uncore_pci_dev {
__u32 pci_id;
struct pci_driver *driver;
@@ -732,6 +821,8 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Server */
IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Server */
IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Server */
+ IMC_DEV(ICL_U_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
+ IMC_DEV(ICL_U2_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
{ /* end marker */ }
};
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index a878e6286e4a..f3f4c2263501 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -89,6 +89,7 @@ static bool test_intel(int idx)
case INTEL_FAM6_SKYLAKE_X:
case INTEL_FAM6_KABYLAKE_MOBILE:
case INTEL_FAM6_KABYLAKE_DESKTOP:
+ case INTEL_FAM6_ICELAKE_MOBILE:
if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
return true;
break;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 1e98a42b560a..07fc84bb85c1 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -49,28 +49,33 @@ struct event_constraint {
unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
u64 idxmsk64;
};
- u64 code;
- u64 cmask;
- int weight;
- int overlap;
- int flags;
+ 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_COMMITTED 0x0008 /* event passed commit_txn */
-#define PERF_X86_EVENT_PEBS_LD_HSW 0x0010 /* haswell style datala, load */
-#define PERF_X86_EVENT_PEBS_NA_HSW 0x0020 /* haswell style datala, unknown */
-#define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */
-#define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */
-#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */
-#define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */
-#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */
-#define PERF_X86_EVENT_LARGE_PEBS 0x0800 /* use large PEBS */
-
+#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 */
struct amd_nb {
int nb_id; /* NorthBridge id */
@@ -116,6 +121,24 @@ 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.
*/
@@ -207,10 +230,16 @@ struct cpu_hw_events {
int n_pebs;
int n_large_pebs;
+ /* Current super set of events hardware configuration */
+ u64 pebs_data_cfg;
+ u64 active_pebs_data_cfg;
+ int pebs_record_size;
+
/*
* Intel LBR bits
*/
int lbr_users;
+ int lbr_pebs_users;
struct perf_branch_stack lbr_stack;
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
struct er_account *lbr_sel;
@@ -257,18 +286,29 @@ struct cpu_hw_events {
void *kfree_on_online[X86_PERF_KFREE_MAX];
};
-#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\
+#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) { \
{ .idxmsk64 = (n) }, \
.code = (c), \
+ .size = (e) - (c), \
.cmask = (m), \
.weight = (w), \
.overlap = (o), \
.flags = f, \
}
+#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \
+ __EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f)
+
#define EVENT_CONSTRAINT(c, n, m) \
__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
+/*
+ * The constraint_match() function only works for 'simple' event codes
+ * and not for extended (AMD64_EVENTSEL_EVENT) events codes.
+ */
+#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \
+ __EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0)
+
#define INTEL_EXCLEVT_CONSTRAINT(c, n) \
__EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\
0, PERF_X86_EVENT_EXCL)
@@ -304,6 +344,12 @@ struct cpu_hw_events {
EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
/*
+ * Constraint on a range of Event codes
+ */
+#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n) \
+ EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT)
+
+/*
* Constraint on the Event code + UMask + fixed-mask
*
* filter mask to validate fixed counter events.
@@ -350,6 +396,9 @@ struct cpu_hw_events {
#define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n) \
+ EVENT_CONSTRAINT_RANGE(c, e, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+
/* Check only flags, but allow all event/umask */
#define INTEL_ALL_EVENT_CONSTRAINT(code, n) \
EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS)
@@ -366,6 +415,11 @@ struct cpu_hw_events {
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \
+ __EVENT_CONSTRAINT_RANGE(code, end, n, \
+ ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
+ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+
#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \
__EVENT_CONSTRAINT(code, n, \
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
@@ -473,6 +527,7 @@ union perf_capabilities {
* values > 32bit.
*/
u64 full_width_write:1;
+ u64 pebs_baseline:1;
};
u64 capabilities;
};
@@ -613,14 +668,16 @@ struct x86_pmu {
pebs_broken :1,
pebs_prec_dist :1,
pebs_no_tlb :1,
- pebs_no_isolation :1;
+ pebs_no_isolation :1,
+ pebs_no_xmm_regs :1;
int pebs_record_size;
int pebs_buffer_size;
+ int max_pebs_events;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
- int max_pebs_events;
unsigned long large_pebs_flags;
+ u64 rtm_abort_event;
/*
* Intel LBR
@@ -714,6 +771,7 @@ static struct perf_pmu_events_ht_attr event_attr_##v = { \
.event_str_ht = ht, \
}
+struct pmu *x86_get_pmu(void);
extern struct x86_pmu x86_pmu __read_mostly;
static inline bool x86_pmu_has_lbr_callstack(void)
@@ -941,6 +999,8 @@ extern struct event_constraint intel_bdw_pebs_event_constraints[];
extern struct event_constraint intel_skl_pebs_event_constraints[];
+extern struct event_constraint intel_icl_pebs_event_constraints[];
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event);
void intel_pmu_pebs_add(struct perf_event *event);
@@ -959,6 +1019,8 @@ void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
void intel_pmu_auto_reload_read(struct perf_event *event);
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr);
+
void intel_ds_init(void);
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.