summaryrefslogtreecommitdiff
path: root/arch/x86/events/intel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/events/intel')
-rw-r--r--arch/x86/events/intel/core.c34
-rw-r--r--arch/x86/events/intel/ds.c82
-rw-r--r--arch/x86/events/intel/lbr.c56
-rw-r--r--arch/x86/events/intel/uncore.h2
-rw-r--r--arch/x86/events/intel/uncore_snbep.c10
5 files changed, 128 insertions, 56 deletions
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 707b2a96e516..035c37481f57 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2041,15 +2041,15 @@ 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);
-
- if (unlikely(event->attr.precise_ip))
- intel_pmu_pebs_disable(event);
}
static void intel_pmu_del_event(struct perf_event *event)
@@ -2068,17 +2068,19 @@ static void intel_pmu_read_event(struct perf_event *event)
x86_perf_event_update(event);
}
-static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
+static void intel_pmu_enable_fixed(struct perf_event *event)
{
+ struct hw_perf_event *hwc = &event->hw;
int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
- u64 ctrl_val, bits, mask;
+ u64 ctrl_val, mask, bits = 0;
/*
- * Enable IRQ generation (0x8),
+ * Enable IRQ generation (0x8), if not PEBS,
* and enable ring-3 counting (0x2) and ring-0 counting (0x1)
* if requested:
*/
- bits = 0x8ULL;
+ if (!event->attr.precise_ip)
+ bits |= 0x8;
if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
bits |= 0x2;
if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
@@ -2120,14 +2122,14 @@ static void intel_pmu_enable_event(struct perf_event *event)
if (unlikely(event_is_checkpointed(event)))
cpuc->intel_cp_status |= (1ull << hwc->idx);
+ if (unlikely(event->attr.precise_ip))
+ intel_pmu_pebs_enable(event);
+
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
- intel_pmu_enable_fixed(hwc);
+ intel_pmu_enable_fixed(event);
return;
}
- if (unlikely(event->attr.precise_ip))
- intel_pmu_pebs_enable(event);
-
__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
}
@@ -2280,7 +2282,10 @@ again:
* counters from the GLOBAL_STATUS mask and we always process PEBS
* events via drain_pebs().
*/
- status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
+ if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+ status &= ~cpuc->pebs_enabled;
+ else
+ status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
/*
* PEBS overflow sets bit 62 in the global status register
@@ -2997,6 +3002,9 @@ static int intel_pmu_hw_config(struct perf_event *event)
}
if (x86_pmu.pebs_aliases)
x86_pmu.pebs_aliases(event);
+
+ if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+ event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY;
}
if (needs_branch_stack(event)) {
@@ -4069,7 +4077,6 @@ __init int intel_pmu_init(void)
intel_pmu_lbr_init_skl();
x86_pmu.event_constraints = intel_slm_event_constraints;
- x86_pmu.pebs_constraints = intel_glp_pebs_event_constraints;
x86_pmu.extra_regs = intel_glm_extra_regs;
/*
* It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
@@ -4079,6 +4086,7 @@ __init int intel_pmu_init(void)
x86_pmu.pebs_prec_dist = true;
x86_pmu.lbr_pt_coexist = true;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ x86_pmu.flags |= PMU_FL_PEBS_ALL;
x86_pmu.get_event_constraints = glp_get_event_constraints;
x86_pmu.cpu_events = glm_events_attrs;
/* Goldmont Plus has 4-wide pipeline */
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8a10a045b57b..b7b01d762d32 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -408,9 +408,11 @@ static int alloc_bts_buffer(int cpu)
ds->bts_buffer_base = (unsigned long) cea;
ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL);
ds->bts_index = ds->bts_buffer_base;
- max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE);
- ds->bts_absolute_maximum = ds->bts_buffer_base + max;
- ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16);
+ max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
+ ds->bts_absolute_maximum = ds->bts_buffer_base +
+ max * BTS_RECORD_SIZE;
+ ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
+ (max / 16) * BTS_RECORD_SIZE;
return 0;
}
@@ -711,12 +713,6 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
EVENT_CONSTRAINT_END
};
-struct event_constraint intel_glp_pebs_event_constraints[] = {
- /* Allow all events as PEBS with no flags */
- INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
- EVENT_CONSTRAINT_END
-};
-
struct event_constraint intel_nehalem_pebs_event_constraints[] = {
INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */
INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
@@ -869,6 +865,13 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
}
}
+ /*
+ * Extended PEBS support
+ * Makes the PEBS code search the normal constraints.
+ */
+ if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+ return NULL;
+
return &emptyconstraint;
}
@@ -894,10 +897,16 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
{
struct debug_store *ds = cpuc->ds;
u64 threshold;
+ int reserved;
+
+ if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+ reserved = x86_pmu.max_pebs_events + x86_pmu.num_counters_fixed;
+ else
+ reserved = x86_pmu.max_pebs_events;
if (cpuc->n_pebs == cpuc->n_large_pebs) {
threshold = ds->pebs_absolute_maximum -
- x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+ reserved * x86_pmu.pebs_record_size;
} else {
threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
}
@@ -961,7 +970,11 @@ void intel_pmu_pebs_enable(struct perf_event *event)
* This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
*/
if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
- ds->pebs_event_reset[hwc->idx] =
+ unsigned int idx = hwc->idx;
+
+ if (idx >= INTEL_PMC_IDX_FIXED)
+ idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED);
+ ds->pebs_event_reset[idx] =
(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
} else {
ds->pebs_event_reset[hwc->idx] = 0;
@@ -1184,16 +1197,20 @@ static void setup_pebs_sample_data(struct perf_event *event,
}
/*
+ * 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 happend between the record and
+ * PMI.
+ */
+ if (sample_type & PERF_SAMPLE_CALLCHAIN)
+ data->callchain = perf_callchain(event, iregs);
+
+ /*
* We use the interrupt regs as a base because the PEBS record does not
* contain a full regs set, specifically it seems to lack segment
* descriptors, which get used by things like user_mode().
*
* In the simple case fix up only the IP for PERF_SAMPLE_IP.
- *
- * We must however always use BP,SP from iregs for the unwinder to stay
- * sane; the record BP,SP can point into thin air when the record is
- * from a previous PMI context or an (I)RET happend between the record
- * and PMI.
*/
*regs = *iregs;
@@ -1212,15 +1229,8 @@ static void setup_pebs_sample_data(struct perf_event *event,
regs->si = pebs->si;
regs->di = pebs->di;
- /*
- * Per the above; only set BP,SP if we don't need callchains.
- *
- * XXX: does this make sense?
- */
- if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
- regs->bp = pebs->bp;
- regs->sp = pebs->sp;
- }
+ regs->bp = pebs->bp;
+ regs->sp = pebs->sp;
#ifndef CONFIG_X86_32
regs->r8 = pebs->r8;
@@ -1482,9 +1492,10 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
struct debug_store *ds = cpuc->ds;
struct perf_event *event;
void *base, *at, *top;
- short counts[MAX_PEBS_EVENTS] = {};
- short error[MAX_PEBS_EVENTS] = {};
- int bit, i;
+ short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+ short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+ int bit, i, size;
+ u64 mask;
if (!x86_pmu.pebs_active)
return;
@@ -1494,6 +1505,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
ds->pebs_index = ds->pebs_buffer_base;
+ mask = (1ULL << x86_pmu.max_pebs_events) - 1;
+ size = x86_pmu.max_pebs_events;
+ if (x86_pmu.flags & PMU_FL_PEBS_ALL) {
+ mask |= ((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)) {
/*
* The drain_pebs() could be called twice in a short period
@@ -1503,7 +1521,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
* update the event->count for this case.
*/
for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled,
- x86_pmu.max_pebs_events) {
+ size) {
event = cpuc->events[bit];
if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
intel_pmu_save_and_restart_reload(event, 0);
@@ -1516,12 +1534,12 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
u64 pebs_status;
pebs_status = p->status & cpuc->pebs_enabled;
- pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+ pebs_status &= mask;
/* PEBS v3 has more accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3) {
for_each_set_bit(bit, (unsigned long *)&pebs_status,
- x86_pmu.max_pebs_events)
+ size)
counts[bit]++;
continue;
@@ -1569,7 +1587,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
counts[bit]++;
}
- for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
+ for (bit = 0; bit < size; bit++) {
if ((counts[bit] == 0) && (error[bit] == 0))
continue;
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index cf372b90557e..f3e006bed9a7 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -216,6 +216,8 @@ static void intel_pmu_lbr_reset_64(void)
void intel_pmu_lbr_reset(void)
{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
if (!x86_pmu.lbr_nr)
return;
@@ -223,6 +225,9 @@ void intel_pmu_lbr_reset(void)
intel_pmu_lbr_reset_32();
else
intel_pmu_lbr_reset_64();
+
+ cpuc->last_task_ctx = NULL;
+ cpuc->last_log_id = 0;
}
/*
@@ -334,6 +339,7 @@ static inline u64 rdlbr_to(unsigned int idx)
static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int i;
unsigned lbr_idx, mask;
u64 tos;
@@ -344,9 +350,21 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
return;
}
- mask = x86_pmu.lbr_nr - 1;
tos = task_ctx->tos;
- for (i = 0; i < tos; i++) {
+ /*
+ * Does not restore the LBR registers, if
+ * - No one else touched them, and
+ * - Did not enter C6
+ */
+ if ((task_ctx == cpuc->last_task_ctx) &&
+ (task_ctx->log_id == cpuc->last_log_id) &&
+ rdlbr_from(tos)) {
+ task_ctx->lbr_stack_state = LBR_NONE;
+ return;
+ }
+
+ mask = x86_pmu.lbr_nr - 1;
+ for (i = 0; i < task_ctx->valid_lbrs; i++) {
lbr_idx = (tos - i) & mask;
wrlbr_from(lbr_idx, task_ctx->lbr_from[i]);
wrlbr_to (lbr_idx, task_ctx->lbr_to[i]);
@@ -354,14 +372,24 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
}
+
+ for (; i < x86_pmu.lbr_nr; i++) {
+ lbr_idx = (tos - i) & mask;
+ wrlbr_from(lbr_idx, 0);
+ wrlbr_to(lbr_idx, 0);
+ if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
+ wrmsrl(MSR_LBR_INFO_0 + lbr_idx, 0);
+ }
+
wrmsrl(x86_pmu.lbr_tos, tos);
task_ctx->lbr_stack_state = LBR_NONE;
}
static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
unsigned lbr_idx, mask;
- u64 tos;
+ u64 tos, from;
int i;
if (task_ctx->lbr_callstack_users == 0) {
@@ -371,15 +399,22 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
mask = x86_pmu.lbr_nr - 1;
tos = intel_pmu_lbr_tos();
- for (i = 0; i < tos; i++) {
+ for (i = 0; i < x86_pmu.lbr_nr; i++) {
lbr_idx = (tos - i) & mask;
- task_ctx->lbr_from[i] = rdlbr_from(lbr_idx);
+ from = rdlbr_from(lbr_idx);
+ if (!from)
+ break;
+ task_ctx->lbr_from[i] = from;
task_ctx->lbr_to[i] = rdlbr_to(lbr_idx);
if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
}
+ task_ctx->valid_lbrs = i;
task_ctx->tos = tos;
task_ctx->lbr_stack_state = LBR_VALID;
+
+ cpuc->last_task_ctx = task_ctx;
+ cpuc->last_log_id = ++task_ctx->log_id;
}
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
@@ -531,7 +566,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
*/
static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
{
- bool need_info = false;
+ bool need_info = false, call_stack = false;
unsigned long mask = x86_pmu.lbr_nr - 1;
int lbr_format = x86_pmu.intel_cap.lbr_format;
u64 tos = intel_pmu_lbr_tos();
@@ -542,7 +577,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
if (cpuc->lbr_sel) {
need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO);
if (cpuc->lbr_sel->config & LBR_CALL_STACK)
- num = tos;
+ call_stack = true;
}
for (i = 0; i < num; i++) {
@@ -555,6 +590,13 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
from = rdlbr_from(lbr_idx);
to = rdlbr_to(lbr_idx);
+ /*
+ * Read LBR call stack entries
+ * until invalid entry (0s) is detected.
+ */
+ if (call_stack && !from)
+ break;
+
if (lbr_format == LBR_FORMAT_INFO && need_info) {
u64 info;
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index c9e1e0bef3c3..e17ab885b1e9 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -28,7 +28,7 @@
#define UNCORE_PCI_DEV_TYPE(data) ((data >> 8) & 0xff)
#define UNCORE_PCI_DEV_IDX(data) (data & 0xff)
#define UNCORE_EXTRA_PCI_DEV 0xff
-#define UNCORE_EXTRA_PCI_DEV_MAX 3
+#define UNCORE_EXTRA_PCI_DEV_MAX 4
#define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 87dc0263a2e1..51d7c117e3c7 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1029,6 +1029,7 @@ void snbep_uncore_cpu_init(void)
enum {
SNBEP_PCI_QPI_PORT0_FILTER,
SNBEP_PCI_QPI_PORT1_FILTER,
+ BDX_PCI_QPI_PORT2_FILTER,
HSWEP_PCI_PCU_3,
};
@@ -3286,15 +3287,18 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = {
},
{ /* QPI Port 0 filter */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86),
- .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT0_FILTER),
},
{ /* QPI Port 1 filter */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96),
- .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT1_FILTER),
},
{ /* QPI Port 2 filter */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46),
- .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ BDX_PCI_QPI_PORT2_FILTER),
},
{ /* PCU.3 (for Capability registers) */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0),
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-24 22:02:08 +0300