From ee930fffee469d076998274a2ca55e13dc1efb67 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 08:50:54 +0000
Subject: [PATCH] enable tun/tap/iptables
---
kernel/arch/x86/events/intel/core.c | 1517 +++++++++++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 1,281 insertions(+), 236 deletions(-)
diff --git a/kernel/arch/x86/events/intel/core.c b/kernel/arch/x86/events/intel/core.c
index 0fc0208..990d554 100644
--- a/kernel/arch/x86/events/intel/core.c
+++ b/kernel/arch/x86/events/intel/core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Per core/cpu state
*
@@ -17,7 +18,9 @@
#include <asm/cpufeature.h>
#include <asm/hardirq.h>
#include <asm/intel-family.h>
+#include <asm/intel_pt.h>
#include <asm/apic.h>
+#include <asm/cpu_device_id.h>
#include "../perf_event.h"
@@ -238,11 +241,46 @@
EVENT_EXTRA_END
};
+static struct event_constraint intel_icl_event_constraints[] = {
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ FIXED_EVENT_CONSTRAINT(0x01c0, 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 */
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_RETIRING, 0),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BAD_SPEC, 1),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FE_BOUND, 2),
+ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BE_BOUND, 3),
+ 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, 0x56, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0x60, 0x8b, 0xf),
+ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xff), /* CYCLE_ACTIVITY.STALLS_TOTAL */
+ INTEL_UEVENT_CONSTRAINT(0x10a3, 0xff), /* CYCLE_ACTIVITY.CYCLES_MEM_ANY */
+ INTEL_UEVENT_CONSTRAINT(0x14a3, 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(0xef, 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, 0x3fffffbfffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffffbfffull, 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");
-static struct attribute *nhm_events_attrs[] = {
+static struct attribute *nhm_mem_events_attrs[] = {
EVENT_PTR(mem_ld_nhm),
NULL,
};
@@ -277,9 +315,13 @@
EVENT_ATTR_STR_HT(topdown-recovery-bubbles.scale, td_recovery_bubbles_scale,
"4", "2");
+EVENT_ATTR_STR(slots, slots, "event=0x00,umask=0x4");
+EVENT_ATTR_STR(topdown-retiring, td_retiring, "event=0x00,umask=0x80");
+EVENT_ATTR_STR(topdown-bad-spec, td_bad_spec, "event=0x00,umask=0x81");
+EVENT_ATTR_STR(topdown-fe-bound, td_fe_bound, "event=0x00,umask=0x82");
+EVENT_ATTR_STR(topdown-be-bound, td_be_bound, "event=0x00,umask=0x83");
+
static struct attribute *snb_events_attrs[] = {
- EVENT_PTR(mem_ld_snb),
- EVENT_PTR(mem_st_snb),
EVENT_PTR(td_slots_issued),
EVENT_PTR(td_slots_retired),
EVENT_PTR(td_fetch_bubbles),
@@ -287,6 +329,12 @@
EVENT_PTR(td_total_slots_scale),
EVENT_PTR(td_recovery_bubbles),
EVENT_PTR(td_recovery_bubbles_scale),
+ NULL,
+};
+
+static struct attribute *snb_mem_events_attrs[] = {
+ EVENT_PTR(mem_ld_snb),
+ EVENT_PTR(mem_st_snb),
NULL,
};
@@ -1822,6 +1870,45 @@
},
};
+#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, 0x800ff0ffffff9fffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xff0ffffff9fffull, 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)
@@ -1870,6 +1957,14 @@
* intel_bts events don't coexist with intel PMU's BTS events because of
* x86_add_exclusive(x86_lbr_exclusive_lbr); there's no need to keep them
* disabled around intel PMU's event batching etc, only inside the PMI handler.
+ *
+ * Avoid PEBS_ENABLE MSR access in PMIs.
+ * The GLOBAL_CTRL has been disabled. All the counters do not count anymore.
+ * It doesn't matter if the PEBS is enabled or not.
+ * Usually, the PEBS status are not changed in PMIs. It's unnecessary to
+ * access PEBS_ENABLE MSR in disable_all()/enable_all().
+ * However, there are some cases which may change PEBS status, e.g. PMI
+ * throttle. The PEBS_ENABLE should be updated where the status changes.
*/
static void __intel_pmu_disable_all(void)
{
@@ -1879,13 +1974,12 @@
if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
intel_pmu_disable_bts();
-
- intel_pmu_pebs_disable_all();
}
static void intel_pmu_disable_all(void)
{
__intel_pmu_disable_all();
+ intel_pmu_pebs_disable_all();
intel_pmu_lbr_disable_all();
}
@@ -1893,7 +1987,6 @@
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- intel_pmu_pebs_enable_all();
intel_pmu_lbr_enable_all(pmi);
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL,
x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask);
@@ -1911,6 +2004,7 @@
static void intel_pmu_enable_all(int added)
{
+ intel_pmu_pebs_enable_all();
__intel_pmu_enable_all(added, false);
}
@@ -1926,7 +2020,7 @@
* in sequence on the same PMC or on different PMCs.
*
* In practise it appears some of these events do in fact count, and
- * we need to programm all 4 events.
+ * we need to program all 4 events.
*/
static void intel_pmu_nhm_workaround(void)
{
@@ -2010,7 +2104,7 @@
/*
* 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);
}
@@ -2028,6 +2122,18 @@
intel_pmu_enable_all(added);
}
+static void enable_counter_freeze(void)
+{
+ update_debugctlmsr(get_debugctlmsr() |
+ DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI);
+}
+
+static void disable_counter_freeze(void)
+{
+ update_debugctlmsr(get_debugctlmsr() &
+ ~DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI);
+}
+
static inline u64 intel_pmu_get_status(void)
{
u64 status;
@@ -2042,42 +2148,85 @@
wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
}
-static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
+static inline bool event_is_checkpointed(struct perf_event *event)
{
- int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
+ return unlikely(event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
+}
+
+static inline void intel_set_masks(struct perf_event *event, int idx)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ if (event->attr.exclude_host)
+ __set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
+ if (event->attr.exclude_guest)
+ __set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
+ if (event_is_checkpointed(event))
+ __set_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
+}
+
+static inline void intel_clear_masks(struct perf_event *event, int idx)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ __clear_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
+ __clear_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
+ __clear_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
+}
+
+static void intel_pmu_disable_fixed(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
u64 ctrl_val, mask;
+ int idx = hwc->idx;
- mask = 0xfULL << (idx * 4);
+ if (is_topdown_idx(idx)) {
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ /*
+ * When there are other active TopDown events,
+ * don't disable the fixed counter 3.
+ */
+ if (*(u64 *)cpuc->active_mask & INTEL_PMC_OTHER_TOPDOWN_BITS(idx))
+ return;
+ idx = INTEL_PMC_IDX_FIXED_SLOTS;
+ }
+
+ intel_clear_masks(event, idx);
+
+ mask = 0xfULL << ((idx - INTEL_PMC_IDX_FIXED) * 4);
rdmsrl(hwc->config_base, ctrl_val);
ctrl_val &= ~mask;
wrmsrl(hwc->config_base, ctrl_val);
}
-static inline bool event_is_checkpointed(struct perf_event *event)
-{
- return (event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
-}
-
static void intel_pmu_disable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int idx = hwc->idx;
- if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
+ switch (idx) {
+ case 0 ... INTEL_PMC_IDX_FIXED - 1:
+ intel_clear_masks(event, idx);
+ x86_pmu_disable_event(event);
+ break;
+ case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1:
+ case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END:
+ intel_pmu_disable_fixed(event);
+ break;
+ case INTEL_PMC_IDX_FIXED_BTS:
intel_pmu_disable_bts();
intel_pmu_drain_bts_buffer();
return;
+ case INTEL_PMC_IDX_FIXED_VLBR:
+ intel_clear_masks(event, idx);
+ break;
+ default:
+ intel_clear_masks(event, idx);
+ pr_warn("Failed to disable the event with invalid index %d\n",
+ idx);
+ return;
}
-
- cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
- cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
- cpuc->intel_cp_status &= ~(1ull << hwc->idx);
-
- if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL))
- intel_pmu_disable_fixed(hwc);
- else
- x86_pmu_disable_event(event);
/*
* Needs to be called after x86_pmu_disable_event,
@@ -2095,10 +2244,189 @@
intel_pmu_pebs_del(event);
}
+static int icl_set_topdown_event_period(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ s64 left = local64_read(&hwc->period_left);
+
+ /*
+ * The values in PERF_METRICS MSR are derived from fixed counter 3.
+ * Software should start both registers, PERF_METRICS and fixed
+ * counter 3, from zero.
+ * Clear PERF_METRICS and Fixed counter 3 in initialization.
+ * After that, both MSRs will be cleared for each read.
+ * Don't need to clear them again.
+ */
+ if (left == x86_pmu.max_period) {
+ wrmsrl(MSR_CORE_PERF_FIXED_CTR3, 0);
+ wrmsrl(MSR_PERF_METRICS, 0);
+ hwc->saved_slots = 0;
+ hwc->saved_metric = 0;
+ }
+
+ if ((hwc->saved_slots) && is_slots_event(event)) {
+ wrmsrl(MSR_CORE_PERF_FIXED_CTR3, hwc->saved_slots);
+ wrmsrl(MSR_PERF_METRICS, hwc->saved_metric);
+ }
+
+ perf_event_update_userpage(event);
+
+ return 0;
+}
+
+static inline u64 icl_get_metrics_event_value(u64 metric, u64 slots, int idx)
+{
+ u32 val;
+
+ /*
+ * The metric is reported as an 8bit integer fraction
+ * suming up to 0xff.
+ * slots-in-metric = (Metric / 0xff) * slots
+ */
+ val = (metric >> ((idx - INTEL_PMC_IDX_METRIC_BASE) * 8)) & 0xff;
+ return mul_u64_u32_div(slots, val, 0xff);
+}
+
+static u64 icl_get_topdown_value(struct perf_event *event,
+ u64 slots, u64 metrics)
+{
+ int idx = event->hw.idx;
+ u64 delta;
+
+ if (is_metric_idx(idx))
+ delta = icl_get_metrics_event_value(metrics, slots, idx);
+ else
+ delta = slots;
+
+ return delta;
+}
+
+static void __icl_update_topdown_event(struct perf_event *event,
+ u64 slots, u64 metrics,
+ u64 last_slots, u64 last_metrics)
+{
+ u64 delta, last = 0;
+
+ delta = icl_get_topdown_value(event, slots, metrics);
+ if (last_slots)
+ last = icl_get_topdown_value(event, last_slots, last_metrics);
+
+ /*
+ * The 8bit integer fraction of metric may be not accurate,
+ * especially when the changes is very small.
+ * For example, if only a few bad_spec happens, the fraction
+ * may be reduced from 1 to 0. If so, the bad_spec event value
+ * will be 0 which is definitely less than the last value.
+ * Avoid update event->count for this case.
+ */
+ if (delta > last) {
+ delta -= last;
+ local64_add(delta, &event->count);
+ }
+}
+
+static void update_saved_topdown_regs(struct perf_event *event,
+ u64 slots, u64 metrics)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct perf_event *other;
+ int idx;
+
+ event->hw.saved_slots = slots;
+ event->hw.saved_metric = metrics;
+
+ for_each_set_bit(idx, cpuc->active_mask, INTEL_PMC_IDX_TD_BE_BOUND + 1) {
+ if (!is_topdown_idx(idx))
+ continue;
+ other = cpuc->events[idx];
+ other->hw.saved_slots = slots;
+ other->hw.saved_metric = metrics;
+ }
+}
+
+/*
+ * Update all active Topdown events.
+ *
+ * The PERF_METRICS and Fixed counter 3 are read separately. The values may be
+ * modify by a NMI. PMU has to be disabled before calling this function.
+ */
+static u64 icl_update_topdown_event(struct perf_event *event)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct perf_event *other;
+ u64 slots, metrics;
+ bool reset = true;
+ int idx;
+
+ /* read Fixed counter 3 */
+ rdpmcl((3 | INTEL_PMC_FIXED_RDPMC_BASE), slots);
+ if (!slots)
+ return 0;
+
+ /* read PERF_METRICS */
+ rdpmcl(INTEL_PMC_FIXED_RDPMC_METRICS, metrics);
+
+ for_each_set_bit(idx, cpuc->active_mask, INTEL_PMC_IDX_TD_BE_BOUND + 1) {
+ if (!is_topdown_idx(idx))
+ continue;
+ other = cpuc->events[idx];
+ __icl_update_topdown_event(other, slots, metrics,
+ event ? event->hw.saved_slots : 0,
+ event ? event->hw.saved_metric : 0);
+ }
+
+ /*
+ * Check and update this event, which may have been cleared
+ * in active_mask e.g. x86_pmu_stop()
+ */
+ if (event && !test_bit(event->hw.idx, cpuc->active_mask)) {
+ __icl_update_topdown_event(event, slots, metrics,
+ event->hw.saved_slots,
+ event->hw.saved_metric);
+
+ /*
+ * In x86_pmu_stop(), the event is cleared in active_mask first,
+ * then drain the delta, which indicates context switch for
+ * counting.
+ * Save metric and slots for context switch.
+ * Don't need to reset the PERF_METRICS and Fixed counter 3.
+ * Because the values will be restored in next schedule in.
+ */
+ update_saved_topdown_regs(event, slots, metrics);
+ reset = false;
+ }
+
+ if (reset) {
+ /* The fixed counter 3 has to be written before the PERF_METRICS. */
+ wrmsrl(MSR_CORE_PERF_FIXED_CTR3, 0);
+ wrmsrl(MSR_PERF_METRICS, 0);
+ if (event)
+ update_saved_topdown_regs(event, 0, 0);
+ }
+
+ return slots;
+}
+
+static void intel_pmu_read_topdown_event(struct perf_event *event)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ /* Only need to call update_topdown_event() once for group read. */
+ if ((cpuc->txn_flags & PERF_PMU_TXN_READ) &&
+ !is_slots_event(event))
+ return;
+
+ perf_pmu_disable(event->pmu);
+ x86_pmu.update_topdown_event(event);
+ perf_pmu_enable(event->pmu);
+}
+
static void intel_pmu_read_event(struct perf_event *event)
{
if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
intel_pmu_auto_reload_read(event);
+ else if (is_topdown_count(event) && x86_pmu.update_topdown_event)
+ intel_pmu_read_topdown_event(event);
else
x86_perf_event_update(event);
}
@@ -2106,8 +2434,22 @@
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, mask, bits = 0;
+ int idx = hwc->idx;
+
+ if (is_topdown_idx(idx)) {
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ /*
+ * When there are other active TopDown events,
+ * don't enable the fixed counter 3 again.
+ */
+ if (*(u64 *)cpuc->active_mask & INTEL_PMC_OTHER_TOPDOWN_BITS(idx))
+ return;
+
+ idx = INTEL_PMC_IDX_FIXED_SLOTS;
+ }
+
+ intel_set_masks(event, idx);
/*
* Enable IRQ generation (0x8), if not PEBS,
@@ -2127,8 +2469,14 @@
if (x86_pmu.version > 2 && hwc->config & ARCH_PERFMON_EVENTSEL_ANY)
bits |= 0x4;
+ idx -= INTEL_PMC_IDX_FIXED;
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;
@@ -2139,33 +2487,32 @@
static void intel_pmu_enable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-
- if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
- if (!__this_cpu_read(cpu_hw_events.enabled))
- return;
-
- intel_pmu_enable_bts(hwc->config);
- return;
- }
-
- if (event->attr.exclude_host)
- cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
- if (event->attr.exclude_guest)
- cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx);
-
- if (unlikely(event_is_checkpointed(event)))
- cpuc->intel_cp_status |= (1ull << hwc->idx);
+ int idx = hwc->idx;
if (unlikely(event->attr.precise_ip))
intel_pmu_pebs_enable(event);
- if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+ switch (idx) {
+ case 0 ... INTEL_PMC_IDX_FIXED - 1:
+ intel_set_masks(event, idx);
+ __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+ break;
+ case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1:
+ case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END:
intel_pmu_enable_fixed(event);
- return;
+ break;
+ case INTEL_PMC_IDX_FIXED_BTS:
+ if (!__this_cpu_read(cpu_hw_events.enabled))
+ return;
+ intel_pmu_enable_bts(hwc->config);
+ break;
+ case INTEL_PMC_IDX_FIXED_VLBR:
+ intel_set_masks(event, idx);
+ break;
+ default:
+ pr_warn("Failed to enable the event with invalid index %d\n",
+ idx);
}
-
- __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
}
static void intel_pmu_add_event(struct perf_event *event)
@@ -2235,15 +2582,221 @@
local_irq_restore(flags);
}
+static int handle_pmi_common(struct pt_regs *regs, u64 status)
+{
+ struct perf_sample_data data;
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct perf_guest_info_callbacks *guest_cbs;
+ int bit;
+ int handled = 0;
+
+ inc_irq_stat(apic_perf_irqs);
+
+ /*
+ * Ignore a range of extra bits in status that do not indicate
+ * overflow by themselves.
+ */
+ status &= ~(GLOBAL_STATUS_COND_CHG |
+ GLOBAL_STATUS_ASIF |
+ GLOBAL_STATUS_LBRS_FROZEN);
+ if (!status)
+ return 0;
+ /*
+ * In case multiple PEBS events are sampled at the same time,
+ * it is possible to have GLOBAL_STATUS bit 62 set indicating
+ * PEBS buffer overflow and also seeing at most 3 PEBS counters
+ * having their bits set in the status register. This is a sign
+ * that there was at least one PEBS record pending at the time
+ * of the PMU interrupt. PEBS counters must only be processed
+ * via the drain_pebs() calls and not via the regular sample
+ * processing loop coming after that the function, otherwise
+ * phony regular samples may be generated in the sampling buffer
+ * not marked with the EXACT tag. Another possibility is to have
+ * one PEBS event and at least one non-PEBS event whic hoverflows
+ * while PEBS has armed. In this case, bit 62 of GLOBAL_STATUS will
+ * not be set, yet the overflow status bit for the PEBS counter will
+ * be on Skylake.
+ *
+ * To avoid this problem, we systematically ignore the PEBS-enabled
+ * counters from the GLOBAL_STATUS mask and we always process PEBS
+ * events via drain_pebs().
+ */
+ 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
+ */
+ if (__test_and_clear_bit(GLOBAL_STATUS_BUFFER_OVF_BIT, (unsigned long *)&status)) {
+ u64 pebs_enabled = cpuc->pebs_enabled;
+
+ handled++;
+ x86_pmu.drain_pebs(regs, &data);
+ status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
+
+ /*
+ * PMI throttle may be triggered, which stops the PEBS event.
+ * Although cpuc->pebs_enabled is updated accordingly, the
+ * MSR_IA32_PEBS_ENABLE is not updated. Because the
+ * cpuc->enabled has been forced to 0 in PMI.
+ * Update the MSR if pebs_enabled is changed.
+ */
+ if (pebs_enabled != cpuc->pebs_enabled)
+ wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+ }
+
+ /*
+ * Intel PT
+ */
+ if (__test_and_clear_bit(GLOBAL_STATUS_TRACE_TOPAPMI_BIT, (unsigned long *)&status)) {
+ handled++;
+
+ guest_cbs = perf_get_guest_cbs();
+ if (unlikely(guest_cbs && guest_cbs->is_in_guest() &&
+ guest_cbs->handle_intel_pt_intr))
+ guest_cbs->handle_intel_pt_intr();
+ else
+ intel_pt_interrupt();
+ }
+
+ /*
+ * Intel Perf mertrics
+ */
+ if (__test_and_clear_bit(GLOBAL_STATUS_PERF_METRICS_OVF_BIT, (unsigned long *)&status)) {
+ handled++;
+ if (x86_pmu.update_topdown_event)
+ x86_pmu.update_topdown_event(NULL);
+ }
+
+ /*
+ * Checkpointed counters can lead to 'spurious' PMIs because the
+ * rollback caused by the PMI will have cleared the overflow status
+ * bit. Therefore always force probe these counters.
+ */
+ status |= cpuc->intel_cp_status;
+
+ for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
+ struct perf_event *event = cpuc->events[bit];
+
+ handled++;
+
+ if (!test_bit(bit, cpuc->active_mask))
+ continue;
+
+ if (!intel_pmu_save_and_restart(event))
+ continue;
+
+ perf_sample_data_init(&data, 0, event->hw.last_period);
+
+ if (has_branch_stack(event))
+ data.br_stack = &cpuc->lbr_stack;
+
+ if (perf_event_overflow(event, &data, regs))
+ x86_pmu_stop(event, 0);
+ }
+
+ return handled;
+}
+
+static bool disable_counter_freezing = true;
+static int __init intel_perf_counter_freezing_setup(char *s)
+{
+ bool res;
+
+ if (kstrtobool(s, &res))
+ return -EINVAL;
+
+ disable_counter_freezing = !res;
+ return 1;
+}
+__setup("perf_v4_pmi=", intel_perf_counter_freezing_setup);
+
+/*
+ * Simplified handler for Arch Perfmon v4:
+ * - We rely on counter freezing/unfreezing to enable/disable the PMU.
+ * This is done automatically on PMU ack.
+ * - Ack the PMU only after the APIC.
+ */
+
+static int intel_pmu_handle_irq_v4(struct pt_regs *regs)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int handled = 0;
+ bool bts = false;
+ u64 status;
+ int pmu_enabled = cpuc->enabled;
+ int loops = 0;
+
+ /* PMU has been disabled because of counter freezing */
+ cpuc->enabled = 0;
+ if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
+ bts = true;
+ intel_bts_disable_local();
+ handled = intel_pmu_drain_bts_buffer();
+ handled += intel_bts_interrupt();
+ }
+ status = intel_pmu_get_status();
+ if (!status)
+ goto done;
+again:
+ intel_pmu_lbr_read();
+ if (++loops > 100) {
+ static bool warned;
+
+ if (!warned) {
+ WARN(1, "perfevents: irq loop stuck!\n");
+ perf_event_print_debug();
+ warned = true;
+ }
+ intel_pmu_reset();
+ goto done;
+ }
+
+
+ handled += handle_pmi_common(regs, status);
+done:
+ /* Ack the PMI in the APIC */
+ apic_write(APIC_LVTPC, APIC_DM_NMI);
+
+ /*
+ * The counters start counting immediately while ack the status.
+ * Make it as close as possible to IRET. This avoids bogus
+ * freezing on Skylake CPUs.
+ */
+ if (status) {
+ intel_pmu_ack_status(status);
+ } else {
+ /*
+ * CPU may issues two PMIs very close to each other.
+ * When the PMI handler services the first one, the
+ * GLOBAL_STATUS is already updated to reflect both.
+ * When it IRETs, the second PMI is immediately
+ * handled and it sees clear status. At the meantime,
+ * there may be a third PMI, because the freezing bit
+ * isn't set since the ack in first PMI handlers.
+ * Double check if there is more work to be done.
+ */
+ status = intel_pmu_get_status();
+ if (status)
+ goto again;
+ }
+
+ if (bts)
+ intel_bts_enable_local();
+ cpuc->enabled = pmu_enabled;
+ return handled;
+}
+
/*
* This handler is triggered by the local APIC, so the APIC IRQ handling
* rules apply:
*/
static int intel_pmu_handle_irq(struct pt_regs *regs)
{
- struct perf_sample_data data;
struct cpu_hw_events *cpuc;
- int bit, loops;
+ int loops;
u64 status;
int handled;
int pmu_enabled;
@@ -2275,7 +2828,8 @@
intel_pmu_lbr_read();
intel_pmu_ack_status(status);
if (++loops > 100) {
- static bool warned = false;
+ static bool warned;
+
if (!warned) {
WARN(1, "perfevents: irq loop stuck!\n");
perf_event_print_debug();
@@ -2285,86 +2839,7 @@
goto done;
}
- inc_irq_stat(apic_perf_irqs);
-
-
- /*
- * Ignore a range of extra bits in status that do not indicate
- * overflow by themselves.
- */
- status &= ~(GLOBAL_STATUS_COND_CHG |
- GLOBAL_STATUS_ASIF |
- GLOBAL_STATUS_LBRS_FROZEN);
- if (!status)
- goto done;
- /*
- * In case multiple PEBS events are sampled at the same time,
- * it is possible to have GLOBAL_STATUS bit 62 set indicating
- * PEBS buffer overflow and also seeing at most 3 PEBS counters
- * having their bits set in the status register. This is a sign
- * that there was at least one PEBS record pending at the time
- * of the PMU interrupt. PEBS counters must only be processed
- * via the drain_pebs() calls and not via the regular sample
- * processing loop coming after that the function, otherwise
- * phony regular samples may be generated in the sampling buffer
- * not marked with the EXACT tag. Another possibility is to have
- * one PEBS event and at least one non-PEBS event whic hoverflows
- * while PEBS has armed. In this case, bit 62 of GLOBAL_STATUS will
- * not be set, yet the overflow status bit for the PEBS counter will
- * be on Skylake.
- *
- * To avoid this problem, we systematically ignore the PEBS-enabled
- * counters from the GLOBAL_STATUS mask and we always process PEBS
- * events via drain_pebs().
- */
- 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
- */
- if (__test_and_clear_bit(62, (unsigned long *)&status)) {
- handled++;
- x86_pmu.drain_pebs(regs);
- status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
- }
-
- /*
- * Intel PT
- */
- if (__test_and_clear_bit(55, (unsigned long *)&status)) {
- handled++;
- intel_pt_interrupt();
- }
-
- /*
- * Checkpointed counters can lead to 'spurious' PMIs because the
- * rollback caused by the PMI will have cleared the overflow status
- * bit. Therefore always force probe these counters.
- */
- status |= cpuc->intel_cp_status;
-
- for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
- struct perf_event *event = cpuc->events[bit];
-
- handled++;
-
- if (!test_bit(bit, cpuc->active_mask))
- continue;
-
- if (!intel_pmu_save_and_restart(event))
- continue;
-
- perf_sample_data_init(&data, 0, event->hw.last_period);
-
- if (has_branch_stack(event))
- data.br_stack = &cpuc->lbr_stack;
-
- if (perf_event_overflow(event, &data, regs))
- x86_pmu_stop(event, 0);
- }
+ handled += handle_pmi_common(regs, status);
/*
* Repeat if there is more work to be done:
@@ -2395,6 +2870,22 @@
{
if (unlikely(intel_pmu_has_bts(event)))
return &bts_constraint;
+
+ return NULL;
+}
+
+/*
+ * Note: matches a fake event, like Fixed2.
+ */
+static struct event_constraint *
+intel_vlbr_constraints(struct perf_event *event)
+{
+ struct event_constraint *c = &vlbr_constraint;
+
+ if (unlikely(constraint_match(c, event->hw.config))) {
+ event->hw.flags |= c->flags;
+ return c;
+ }
return NULL;
}
@@ -2573,7 +3064,7 @@
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;
}
@@ -2588,6 +3079,10 @@
struct perf_event *event)
{
struct event_constraint *c;
+
+ c = intel_vlbr_constraints(event);
+ if (c)
+ return c;
c = intel_bts_constraints(event);
if (c)
@@ -2723,7 +3218,7 @@
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
@@ -2779,35 +3274,39 @@
* 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;
}
@@ -2816,11 +3315,9 @@
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
@@ -2828,7 +3325,8 @@
* - 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;
@@ -3070,11 +3568,16 @@
return ret;
if (event->attr.precise_ip) {
+ if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT)
+ return -EINVAL;
+
if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) {
event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
if (!(event->attr.sample_type &
- ~intel_pmu_large_pebs_flags(event)))
+ ~intel_pmu_large_pebs_flags(event))) {
event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS;
+ event->attach_state |= PERF_ATTACH_SCHED_CB;
+ }
}
if (x86_pmu.pebs_aliases)
x86_pmu.pebs_aliases(event);
@@ -3087,6 +3590,7 @@
ret = intel_pmu_setup_lbr_filter(event);
if (ret)
return ret;
+ event->attach_state |= PERF_ATTACH_SCHED_CB;
/*
* BTS is set up earlier in this path, so don't account twice
@@ -3100,8 +3604,65 @@
}
}
+ if (event->attr.aux_output) {
+ if (!event->attr.precise_ip)
+ return -EINVAL;
+
+ event->hw.flags |= PERF_X86_EVENT_PEBS_VIA_PT;
+ }
+
if (event->attr.type != PERF_TYPE_RAW)
return 0;
+
+ /*
+ * Config Topdown slots and metric events
+ *
+ * The slots event on Fixed Counter 3 can support sampling,
+ * which will be handled normally in x86_perf_event_update().
+ *
+ * Metric events don't support sampling and require being paired
+ * with a slots event as group leader. When the slots event
+ * is used in a metrics group, it too cannot support sampling.
+ */
+ if (x86_pmu.intel_cap.perf_metrics && is_topdown_event(event)) {
+ if (event->attr.config1 || event->attr.config2)
+ return -EINVAL;
+
+ /*
+ * The TopDown metrics events and slots event don't
+ * support any filters.
+ */
+ if (event->attr.config & X86_ALL_EVENT_FLAGS)
+ return -EINVAL;
+
+ if (is_metric_event(event)) {
+ struct perf_event *leader = event->group_leader;
+
+ /* The metric events don't support sampling. */
+ if (is_sampling_event(event))
+ return -EINVAL;
+
+ /* The metric events require a slots group leader. */
+ if (!is_slots_event(leader))
+ return -EINVAL;
+
+ /*
+ * The leader/SLOTS must not be a sampling event for
+ * metric use; hardware requires it starts at 0 when used
+ * in conjunction with MSR_PERF_METRICS.
+ */
+ if (is_sampling_event(leader))
+ return -EINVAL;
+
+ event->event_caps |= PERF_EV_CAP_SIBLING;
+ /*
+ * Only once we have a METRICs sibling do we
+ * need TopDown magic.
+ */
+ leader->hw.flags |= PERF_X86_EVENT_TOPDOWN;
+ event->hw.flags |= PERF_X86_EVENT_TOPDOWN;
+ }
+ }
if (!(event->attr.config & ARCH_PERFMON_EVENTSEL_ANY))
return 0;
@@ -3118,8 +3679,19 @@
return 0;
}
+#ifdef CONFIG_RETPOLINE
+static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr);
+static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr);
+#endif
+
struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
{
+#ifdef CONFIG_RETPOLINE
+ if (x86_pmu.guest_get_msrs == intel_guest_get_msrs)
+ return intel_guest_get_msrs(nr);
+ else if (x86_pmu.guest_get_msrs == core_guest_get_msrs)
+ return core_guest_get_msrs(nr);
+#endif
if (x86_pmu.guest_get_msrs)
return x86_pmu.guest_get_msrs(nr);
*nr = 0;
@@ -3135,16 +3707,27 @@
arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
arr[0].host = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask;
arr[0].guest = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_host_mask;
- /*
- * If PMU counter has PEBS enabled it is not enough to disable counter
- * on a guest entry since PEBS memory write can overshoot guest entry
- * and corrupt guest memory. Disabling PEBS solves the problem.
- */
- arr[1].msr = MSR_IA32_PEBS_ENABLE;
- arr[1].host = cpuc->pebs_enabled;
- arr[1].guest = 0;
+ if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+ arr[0].guest &= ~cpuc->pebs_enabled;
+ else
+ arr[0].guest &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
+ *nr = 1;
- *nr = 2;
+ if (x86_pmu.pebs && x86_pmu.pebs_no_isolation) {
+ /*
+ * If PMU counter has PEBS enabled it is not enough to
+ * disable counter on a guest entry since PEBS memory
+ * write can overshoot guest entry and corrupt guest
+ * memory. Disabling PEBS solves the problem.
+ *
+ * Don't do this if the CPU already enforces it.
+ */
+ arr[1].msr = MSR_IA32_PEBS_ENABLE;
+ arr[1].host = cpuc->pebs_enabled;
+ arr[1].guest = 0;
+ *nr = 2;
+ }
+
return arr;
}
@@ -3241,6 +3824,12 @@
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)
@@ -3260,6 +3849,21 @@
}
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)
{
@@ -3268,6 +3872,29 @@
/* :ppp means to do reduced skid PEBS which is PMC0 only. */
if (event->attr.precise_ip == 3)
return &counter0_constraint;
+
+ c = intel_get_event_constraints(cpuc, idx, event);
+
+ 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);
@@ -3285,7 +3912,7 @@
/*
* 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--;
@@ -3387,6 +4014,8 @@
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)
@@ -3464,6 +4093,20 @@
if (x86_pmu.version > 1)
flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
+ if (x86_pmu.counter_freezing)
+ enable_counter_freeze();
+
+ /* Disable perf metrics if any added CPU doesn't support it. */
+ if (x86_pmu.intel_cap.perf_metrics) {
+ union perf_capabilities perf_cap;
+
+ rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_cap.capabilities);
+ if (!perf_cap.perf_metrics) {
+ x86_pmu.intel_cap.perf_metrics = 0;
+ x86_pmu.intel_ctrl &= ~(1ULL << GLOBAL_CTRL_EN_PERF_METRICS);
+ }
+ }
+
if (!cpuc->shared_regs)
return;
@@ -3523,6 +4166,9 @@
static void intel_pmu_cpu_dying(int cpu)
{
fini_debug_store_on_cpu(cpu);
+
+ if (x86_pmu.counter_freezing)
+ disable_counter_freeze();
}
void intel_cpuc_finish(struct cpu_hw_events *cpuc)
@@ -3551,9 +4197,23 @@
intel_pmu_lbr_sched_task(ctx, sched_in);
}
+static void intel_pmu_swap_task_ctx(struct perf_event_context *prev,
+ struct perf_event_context *next)
+{
+ intel_pmu_lbr_swap_task_ctx(prev, next);
+}
+
static int intel_pmu_check_period(struct perf_event *event, u64 value)
{
return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
+}
+
+static int intel_pmu_aux_output_match(struct perf_event *event)
+{
+ if (!x86_pmu.intel_cap.pebs_output_pt_available)
+ return 0;
+
+ return is_intel_pt_event(event);
}
PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
@@ -3638,9 +4298,12 @@
.cpu_dead = intel_pmu_cpu_dead,
.check_period = intel_pmu_check_period,
-};
-static struct attribute *intel_pmu_attrs[];
+ .lbr_reset = intel_pmu_lbr_reset_64,
+ .lbr_read = intel_pmu_lbr_read_64,
+ .lbr_save = intel_pmu_lbr_save,
+ .lbr_restore = intel_pmu_lbr_restore,
+};
static __initconst const struct x86_pmu intel_pmu = {
.name = "Intel",
@@ -3673,8 +4336,6 @@
.format_attrs = intel_arch3_formats_attr,
.events_sysfs_show = intel_event_sysfs_show,
- .attrs = intel_pmu_attrs,
-
.cpu_prepare = intel_pmu_cpu_prepare,
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
@@ -3682,8 +4343,29 @@
.guest_get_msrs = intel_guest_get_msrs,
.sched_task = intel_pmu_sched_task,
+ .swap_task_ctx = intel_pmu_swap_task_ctx,
.check_period = intel_pmu_check_period,
+
+ .aux_output_match = intel_pmu_aux_output_match,
+
+ .lbr_reset = intel_pmu_lbr_reset_64,
+ .lbr_read = intel_pmu_lbr_read_64,
+ .lbr_save = intel_pmu_lbr_save,
+ .lbr_restore = intel_pmu_lbr_restore,
+
+ /*
+ * SMM has access to all 4 rings and while traditionally SMM code only
+ * ran in CPL0, 2021-era firmware is starting to make use of CPL3 in SMM.
+ *
+ * Since the EVENTSEL.{USR,OS} CPL filtering makes no distinction
+ * between SMM or not, this results in what should be pure userspace
+ * counters including SMM data.
+ *
+ * This is a clear privilege issue, therefore globally disable
+ * counting SMM by default.
+ */
+ .attr_freeze_on_smi = 1,
};
static __init void intel_clovertown_quirk(void)
@@ -3712,36 +4394,66 @@
x86_pmu.pebs_constraints = NULL;
}
-static int intel_snb_pebs_broken(int cpu)
+static const struct x86_cpu_desc isolation_ucodes[] = {
+ INTEL_CPU_DESC(INTEL_FAM6_HASWELL, 3, 0x0000001f),
+ INTEL_CPU_DESC(INTEL_FAM6_HASWELL_L, 1, 0x0000001e),
+ INTEL_CPU_DESC(INTEL_FAM6_HASWELL_G, 1, 0x00000015),
+ INTEL_CPU_DESC(INTEL_FAM6_HASWELL_X, 2, 0x00000037),
+ INTEL_CPU_DESC(INTEL_FAM6_HASWELL_X, 4, 0x0000000a),
+ INTEL_CPU_DESC(INTEL_FAM6_BROADWELL, 4, 0x00000023),
+ INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_G, 1, 0x00000014),
+ INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 2, 0x00000010),
+ INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 3, 0x07000009),
+ INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 4, 0x0f000009),
+ INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 5, 0x0e000002),
+ INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_X, 1, 0x0b000014),
+ INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 3, 0x00000021),
+ INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 4, 0x00000000),
+ INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 5, 0x00000000),
+ INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 6, 0x00000000),
+ INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 7, 0x00000000),
+ INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 11, 0x00000000),
+ INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_L, 3, 0x0000007c),
+ INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE, 3, 0x0000007c),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 9, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 9, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 10, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 11, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 12, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 10, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 11, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 12, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 13, 0x0000004e),
+ {}
+};
+
+static void intel_check_pebs_isolation(void)
{
- u32 rev = UINT_MAX; /* default to broken for unknown models */
+ x86_pmu.pebs_no_isolation = !x86_cpu_has_min_microcode_rev(isolation_ucodes);
+}
- switch (cpu_data(cpu).x86_model) {
- case INTEL_FAM6_SANDYBRIDGE:
- rev = 0x28;
- break;
+static __init void intel_pebs_isolation_quirk(void)
+{
+ WARN_ON_ONCE(x86_pmu.check_microcode);
+ x86_pmu.check_microcode = intel_check_pebs_isolation;
+ intel_check_pebs_isolation();
+}
- case INTEL_FAM6_SANDYBRIDGE_X:
- switch (cpu_data(cpu).x86_stepping) {
- case 6: rev = 0x618; break;
- case 7: rev = 0x70c; break;
- }
- }
+static const struct x86_cpu_desc pebs_ucodes[] = {
+ INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE, 7, 0x00000028),
+ INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE_X, 6, 0x00000618),
+ INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE_X, 7, 0x0000070c),
+ {}
+};
- return (cpu_data(cpu).microcode < rev);
+static bool intel_snb_pebs_broken(void)
+{
+ return !x86_cpu_has_min_microcode_rev(pebs_ucodes);
}
static void intel_snb_check_microcode(void)
{
- int pebs_broken = 0;
- int cpu;
-
- for_each_online_cpu(cpu) {
- if ((pebs_broken = intel_snb_pebs_broken(cpu)))
- break;
- }
-
- if (pebs_broken == x86_pmu.pebs_broken)
+ if (intel_snb_pebs_broken() == x86_pmu.pebs_broken)
return;
/*
@@ -3770,6 +4482,13 @@
static bool check_msr(unsigned long msr, u64 mask)
{
u64 val_old, val_new, val_tmp;
+
+ /*
+ * Disable the check for real HW, so we don't
+ * mess with potentionaly enabled registers:
+ */
+ if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
+ return true;
/*
* Read the current value, change it and read it back to see if it
@@ -3858,6 +4577,39 @@
}
}
+static const struct x86_cpu_desc counter_freezing_ucodes[] = {
+ INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT, 2, 0x0000000e),
+ INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT, 9, 0x0000002e),
+ INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT, 10, 0x00000008),
+ INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_D, 1, 0x00000028),
+ INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_PLUS, 1, 0x00000028),
+ INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_PLUS, 8, 0x00000006),
+ {}
+};
+
+static bool intel_counter_freezing_broken(void)
+{
+ return !x86_cpu_has_min_microcode_rev(counter_freezing_ucodes);
+}
+
+static __init void intel_counter_freezing_quirk(void)
+{
+ /* Check if it's already disabled */
+ if (disable_counter_freezing)
+ return;
+
+ /*
+ * If the system starts with the wrong ucode, leave the
+ * counter-freezing feature permanently disabled.
+ */
+ if (intel_counter_freezing_broken()) {
+ pr_info("PMU counter freezing disabled due to CPU errata,"
+ "please upgrade microcode\n");
+ x86_pmu.counter_freezing = false;
+ x86_pmu.handle_irq = intel_pmu_handle_irq;
+ }
+}
+
/*
* enable software workaround for errata:
* SNB: BJ122
@@ -3897,8 +4649,6 @@
EVENT_ATTR_STR(cycles-ct, cycles_ct, "event=0x3c,in_tx=1,in_tx_cp=1");
static struct attribute *hsw_events_attrs[] = {
- EVENT_PTR(mem_ld_hsw),
- EVENT_PTR(mem_st_hsw),
EVENT_PTR(td_slots_issued),
EVENT_PTR(td_slots_retired),
EVENT_PTR(td_fetch_bubbles),
@@ -3907,6 +4657,12 @@
EVENT_PTR(td_recovery_bubbles),
EVENT_PTR(td_recovery_bubbles_scale),
NULL
+};
+
+static struct attribute *hsw_mem_events_attrs[] = {
+ EVENT_PTR(mem_ld_hsw),
+ EVENT_PTR(mem_st_hsw),
+ NULL,
};
static struct attribute *hsw_tsx_events_attrs[] = {
@@ -3925,12 +4681,43 @@
NULL
};
-static __init struct attribute **get_hsw_events_attrs(void)
-{
- return boot_cpu_has(X86_FEATURE_RTM) ?
- merge_attr(hsw_events_attrs, hsw_tsx_events_attrs) :
- hsw_events_attrs;
-}
+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_td_events_attrs[] = {
+ EVENT_PTR(slots),
+ EVENT_PTR(td_retiring),
+ EVENT_PTR(td_bad_spec),
+ EVENT_PTR(td_fe_bound),
+ EVENT_PTR(td_be_bound),
+ 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 ssize_t freeze_on_smi_show(struct device *cdev,
struct device_attribute *attr,
@@ -3971,6 +4758,50 @@
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(smp_processor_id()));
+}
+
+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,
@@ -4003,24 +4834,117 @@
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,
- NULL, /* &dev_attr_allow_tsx_force_abort.attr.attr */
+ &dev_attr_allow_tsx_force_abort.attr,
NULL,
};
+static umode_t
+tsx_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return boot_cpu_has(X86_FEATURE_RTM) ? attr->mode : 0;
+}
+
+static umode_t
+pebs_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return x86_pmu.pebs ? attr->mode : 0;
+}
+
+static umode_t
+lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return x86_pmu.lbr_nr ? attr->mode : 0;
+}
+
+static umode_t
+exra_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return x86_pmu.version >= 2 ? attr->mode : 0;
+}
+
+static umode_t
+default_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ if (attr == &dev_attr_allow_tsx_force_abort.attr)
+ return x86_pmu.flags & PMU_FL_TFA ? attr->mode : 0;
+
+ return attr->mode;
+}
+
+static struct attribute_group group_events_td = {
+ .name = "events",
+};
+
+static struct attribute_group group_events_mem = {
+ .name = "events",
+ .is_visible = pebs_is_visible,
+};
+
+static struct attribute_group group_events_tsx = {
+ .name = "events",
+ .is_visible = tsx_is_visible,
+};
+
+static struct attribute_group group_caps_gen = {
+ .name = "caps",
+ .attrs = intel_pmu_caps_attrs,
+};
+
+static struct attribute_group group_caps_lbr = {
+ .name = "caps",
+ .attrs = lbr_attrs,
+ .is_visible = lbr_is_visible,
+};
+
+static struct attribute_group group_format_extra = {
+ .name = "format",
+ .is_visible = exra_is_visible,
+};
+
+static struct attribute_group group_format_extra_skl = {
+ .name = "format",
+ .is_visible = exra_is_visible,
+};
+
+static struct attribute_group group_default = {
+ .attrs = intel_pmu_attrs,
+ .is_visible = default_is_visible,
+};
+
+static const struct attribute_group *attr_update[] = {
+ &group_events_td,
+ &group_events_mem,
+ &group_events_tsx,
+ &group_caps_gen,
+ &group_caps_lbr,
+ &group_format_extra,
+ &group_format_extra_skl,
+ &group_default,
+ NULL,
+};
+
+static struct attribute *empty_attrs;
+
__init int intel_pmu_init(void)
{
- struct attribute **extra_attr = NULL;
- struct attribute **to_free = NULL;
+ struct attribute **extra_skl_attr = &empty_attrs;
+ struct attribute **extra_attr = &empty_attrs;
+ struct attribute **td_attr = &empty_attrs;
+ struct attribute **mem_attr = &empty_attrs;
+ struct attribute **tsx_attr = &empty_attrs;
union cpuid10_edx edx;
union cpuid10_eax eax;
union cpuid10_ebx ebx;
struct event_constraint *c;
unsigned int unused;
struct extra_reg *er;
+ bool pmem = false;
int version, i;
char *name;
@@ -4071,6 +4995,9 @@
max((int)edx.split.num_counters_fixed, assume);
}
+ if (version >= 4)
+ x86_pmu.counter_freezing = !disable_counter_freezing;
+
if (boot_cpu_has(X86_FEATURE_PDCM)) {
u64 capabilities;
@@ -4078,9 +5005,23 @@
x86_pmu.intel_cap.capabilities = capabilities;
}
+ if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32) {
+ x86_pmu.lbr_reset = intel_pmu_lbr_reset_32;
+ x86_pmu.lbr_read = intel_pmu_lbr_read_32;
+ }
+
+ if (boot_cpu_has(X86_FEATURE_ARCH_LBR))
+ intel_pmu_arch_lbr_init();
+
intel_ds_init();
x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */
+
+ if (version >= 5) {
+ x86_pmu.intel_cap.anythread_deprecated = edx.split.anythread_deprecated;
+ if (x86_pmu.intel_cap.anythread_deprecated)
+ pr_cont(" AnyThread deprecated, ");
+ }
/*
* Install the hw-cache-events table:
@@ -4093,6 +5034,8 @@
case INTEL_FAM6_CORE2_MEROM:
x86_add_quirk(intel_clovertown_quirk);
+ fallthrough;
+
case INTEL_FAM6_CORE2_MEROM_L:
case INTEL_FAM6_CORE2_PENRYN:
case INTEL_FAM6_CORE2_DUNNINGTON:
@@ -4123,7 +5066,7 @@
x86_pmu.extra_regs = intel_nehalem_extra_regs;
x86_pmu.limit_period = nhm_limit_period;
- x86_pmu.cpu_events = nhm_events_attrs;
+ mem_attr = nhm_mem_events_attrs;
/* UOPS_ISSUED.STALLED_CYCLES */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4159,7 +5102,7 @@
break;
case INTEL_FAM6_ATOM_SILVERMONT:
- case INTEL_FAM6_ATOM_SILVERMONT_X:
+ case INTEL_FAM6_ATOM_SILVERMONT_D:
case INTEL_FAM6_ATOM_SILVERMONT_MID:
case INTEL_FAM6_ATOM_AIRMONT:
case INTEL_FAM6_ATOM_AIRMONT_MID:
@@ -4174,14 +5117,15 @@
x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
x86_pmu.extra_regs = intel_slm_extra_regs;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
- x86_pmu.cpu_events = slm_events_attrs;
+ td_attr = slm_events_attrs;
extra_attr = slm_format_attr;
pr_cont("Silvermont events, ");
name = "silvermont";
break;
case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_GOLDMONT_X:
+ case INTEL_FAM6_ATOM_GOLDMONT_D:
+ x86_add_quirk(intel_counter_freezing_quirk);
memcpy(hw_cache_event_ids, glm_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs,
@@ -4201,13 +5145,14 @@
x86_pmu.pebs_prec_dist = true;
x86_pmu.lbr_pt_coexist = true;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
- x86_pmu.cpu_events = glm_events_attrs;
+ td_attr = glm_events_attrs;
extra_attr = slm_format_attr;
pr_cont("Goldmont events, ");
name = "goldmont";
break;
case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+ x86_add_quirk(intel_counter_freezing_quirk);
memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs,
@@ -4227,12 +5172,40 @@
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;
+ td_attr = glm_events_attrs;
/* Goldmont Plus has 4-wide pipeline */
event_attr_td_total_slots_scale_glm.event_str = "4";
extra_attr = slm_format_attr;
pr_cont("Goldmont plus events, ");
name = "goldmont_plus";
+ break;
+
+ case INTEL_FAM6_ATOM_TREMONT_D:
+ case INTEL_FAM6_ATOM_TREMONT:
+ case INTEL_FAM6_ATOM_TREMONT_L:
+ 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:
@@ -4251,7 +5224,7 @@
x86_pmu.extra_regs = intel_westmere_extra_regs;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
- x86_pmu.cpu_events = nhm_events_attrs;
+ mem_attr = nhm_mem_events_attrs;
/* UOPS_ISSUED.STALLED_CYCLES */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4290,7 +5263,8 @@
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
- x86_pmu.cpu_events = snb_events_attrs;
+ td_attr = snb_events_attrs;
+ mem_attr = snb_mem_events_attrs;
/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4330,7 +5304,8 @@
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
- x86_pmu.cpu_events = snb_events_attrs;
+ td_attr = snb_events_attrs;
+ mem_attr = snb_mem_events_attrs;
/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4343,11 +5318,12 @@
break;
- case INTEL_FAM6_HASWELL_CORE:
+ case INTEL_FAM6_HASWELL:
case INTEL_FAM6_HASWELL_X:
- case INTEL_FAM6_HASWELL_ULT:
- case INTEL_FAM6_HASWELL_GT3E:
+ case INTEL_FAM6_HASWELL_L:
+ case INTEL_FAM6_HASWELL_G:
x86_add_quirk(intel_ht_bug);
+ x86_add_quirk(intel_pebs_isolation_quirk);
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -4365,18 +5341,21 @@
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
- x86_pmu.cpu_events = get_hsw_events_attrs();
x86_pmu.lbr_double_abort = true;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
+ td_attr = hsw_events_attrs;
+ mem_attr = hsw_mem_events_attrs;
+ tsx_attr = hsw_tsx_events_attrs;
pr_cont("Haswell events, ");
name = "haswell";
break;
- case INTEL_FAM6_BROADWELL_CORE:
- case INTEL_FAM6_BROADWELL_XEON_D:
- case INTEL_FAM6_BROADWELL_GT3E:
+ case INTEL_FAM6_BROADWELL:
+ case INTEL_FAM6_BROADWELL_D:
+ case INTEL_FAM6_BROADWELL_G:
case INTEL_FAM6_BROADWELL_X:
+ x86_add_quirk(intel_pebs_isolation_quirk);
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -4404,10 +5383,12 @@
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
- x86_pmu.cpu_events = get_hsw_events_attrs();
x86_pmu.limit_period = bdw_limit_period;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
+ td_attr = hsw_events_attrs;
+ mem_attr = hsw_mem_events_attrs;
+ tsx_attr = hsw_tsx_events_attrs;
pr_cont("Broadwell events, ");
name = "broadwell";
break;
@@ -4432,11 +5413,16 @@
name = "knights-landing";
break;
- case INTEL_FAM6_SKYLAKE_MOBILE:
- case INTEL_FAM6_SKYLAKE_DESKTOP:
case INTEL_FAM6_SKYLAKE_X:
- case INTEL_FAM6_KABYLAKE_MOBILE:
- case INTEL_FAM6_KABYLAKE_DESKTOP:
+ pmem = true;
+ fallthrough;
+ case INTEL_FAM6_SKYLAKE_L:
+ case INTEL_FAM6_SKYLAKE:
+ case INTEL_FAM6_KABYLAKE_L:
+ case INTEL_FAM6_KABYLAKE:
+ case INTEL_FAM6_COMETLAKE_L:
+ case INTEL_FAM6_COMETLAKE:
+ x86_add_quirk(intel_pebs_isolation_quirk);
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));
@@ -4461,22 +5447,60 @@
x86_pmu.get_event_constraints = hsw_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);
- to_free = extra_attr;
- x86_pmu.cpu_events = get_hsw_events_attrs();
- intel_pmu_pebs_data_source_skl(
- boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
+ extra_skl_attr = skl_format_attr;
+ td_attr = hsw_events_attrs;
+ mem_attr = hsw_mem_events_attrs;
+ tsx_attr = hsw_tsx_events_attrs;
+ intel_pmu_pebs_data_source_skl(pmem);
if (boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) {
x86_pmu.flags |= PMU_FL_TFA;
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;
}
pr_cont("Skylake events, ");
name = "skylake";
+ break;
+
+ case INTEL_FAM6_ICELAKE_X:
+ case INTEL_FAM6_ICELAKE_D:
+ pmem = true;
+ fallthrough;
+ case INTEL_FAM6_ICELAKE_L:
+ case INTEL_FAM6_ICELAKE:
+ case INTEL_FAM6_TIGERLAKE_L:
+ case INTEL_FAM6_TIGERLAKE:
+ 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_skl_attr = skl_format_attr;
+ mem_attr = icl_events_attrs;
+ td_attr = icl_td_events_attrs;
+ tsx_attr = icl_tsx_events_attrs;
+ x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xc9, .umask=0x04);
+ x86_pmu.lbr_pt_coexist = true;
+ intel_pmu_pebs_data_source_skl(pmem);
+ x86_pmu.update_topdown_event = icl_update_topdown_event;
+ x86_pmu.set_topdown_event_period = icl_set_topdown_event_period;
+ pr_cont("Icelake events, ");
+ name = "icelake";
break;
default:
@@ -4497,13 +5521,16 @@
}
}
- snprintf(pmu_name_str, sizeof pmu_name_str, "%s", name);
+ snprintf(pmu_name_str, sizeof(pmu_name_str), "%s", name);
- if (version >= 2 && extra_attr) {
- x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr,
- extra_attr);
- WARN_ON(!x86_pmu.format_attrs);
- }
+
+ group_events_td.attrs = td_attr;
+ group_events_mem.attrs = mem_attr;
+ group_events_tsx.attrs = tsx_attr;
+ group_format_extra.attrs = extra_attr;
+ group_format_extra_skl.attrs = extra_skl_attr;
+
+ x86_pmu.attr_update = attr_update;
if (x86_pmu.num_counters > INTEL_PMC_MAX_GENERIC) {
WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
@@ -4521,12 +5548,25 @@
x86_pmu.intel_ctrl |=
((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
+ /* AnyThread may be deprecated on arch perfmon v5 or later */
+ if (x86_pmu.intel_cap.anythread_deprecated)
+ x86_pmu.format_attrs = intel_arch_formats_attr;
+
if (x86_pmu.event_constraints) {
/*
* event on fixed counter2 (REF_CYCLES) only works on this
* counter, so do not extend mask to generic counters
*/
for_each_event_constraint(c, x86_pmu.event_constraints) {
+ /*
+ * Don't extend the topdown slots and metrics
+ * events to the generic counters.
+ */
+ if (c->idxmsk64 & INTEL_PMC_MSK_TOPDOWN) {
+ c->weight = hweight64(c->idxmsk64);
+ continue;
+ }
+
if (c->cmask == FIXED_EVENT_FLAGS
&& c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) {
c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
@@ -4543,7 +5583,7 @@
* Check all LBT MSR here.
* Disable LBR access if any LBR MSRs can not be accessed.
*/
- if (x86_pmu.lbr_nr && !check_msr(x86_pmu.lbr_tos, 0x3UL))
+ if (x86_pmu.lbr_tos && !check_msr(x86_pmu.lbr_tos, 0x3UL))
x86_pmu.lbr_nr = 0;
for (i = 0; i < x86_pmu.lbr_nr; i++) {
if (!(check_msr(x86_pmu.lbr_from + i, 0xffffUL) &&
@@ -4551,12 +5591,8 @@
x86_pmu.lbr_nr = 0;
}
- x86_pmu.caps_attrs = intel_pmu_caps_attrs;
-
- if (x86_pmu.lbr_nr) {
- x86_pmu.caps_attrs = merge_attr(x86_pmu.caps_attrs, lbr_attrs);
+ if (x86_pmu.lbr_nr)
pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr);
- }
/*
* Access extra MSR may cause #GP under certain circumstances.
@@ -4579,7 +5615,16 @@
pr_cont("full-width counters, ");
}
- kfree(to_free);
+ /*
+ * For arch perfmon 4 use counter freezing to avoid
+ * several MSR accesses in the PMI.
+ */
+ if (x86_pmu.counter_freezing)
+ x86_pmu.handle_irq = intel_pmu_handle_irq_v4;
+
+ if (x86_pmu.intel_cap.perf_metrics)
+ x86_pmu.intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
+
return 0;
}
--
Gitblit v1.6.2