summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/kernel/cpu/perf_event.h6
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c78
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c203
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_lbr.c29
4 files changed, 215 insertions, 101 deletions
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index cc16faae0538..fd00bb29425d 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -164,6 +164,11 @@ struct cpu_hw_events {
struct perf_guest_switch_msr guest_switch_msrs[X86_PMC_IDX_MAX];
/*
+ * Intel checkpoint mask
+ */
+ u64 intel_cp_status;
+
+ /*
* manage shared (per-core, per-cpu) registers
* used on Intel NHM/WSM/SNB
*/
@@ -440,6 +445,7 @@ struct x86_pmu {
int lbr_nr; /* hardware stack size */
u64 lbr_sel_mask; /* LBR_SELECT valid bits */
const int *lbr_sel_map; /* lbr_select mappings */
+ bool lbr_double_abort; /* duplicated lbr aborts */
/*
* Extra registers for events
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index f31a1655d1ff..0fa4f242f050 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -190,9 +190,9 @@ static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
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");
+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");
struct attribute *nhm_events_attrs[] = {
EVENT_PTR(mem_ld_nhm),
@@ -1184,6 +1184,11 @@ static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
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;
@@ -1197,6 +1202,7 @@ static void intel_pmu_disable_event(struct perf_event *event)
cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
+ cpuc->intel_cp_status &= ~(1ull << hwc->idx);
/*
* must disable before any actual event
@@ -1271,6 +1277,9 @@ static void intel_pmu_enable_event(struct perf_event *event)
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);
+
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_enable_fixed(hwc);
return;
@@ -1289,6 +1298,17 @@ static void intel_pmu_enable_event(struct perf_event *event)
int intel_pmu_save_and_restart(struct perf_event *event)
{
x86_perf_event_update(event);
+ /*
+ * For a checkpointed counter always reset back to 0. This
+ * avoids a situation where the counter overflows, aborts the
+ * transaction and is then set back to shortly before the
+ * overflow, and overflows and aborts again.
+ */
+ if (unlikely(event_is_checkpointed(event))) {
+ /* No race with NMIs because the counter should not be armed */
+ wrmsrl(event->hw.event_base, 0);
+ local64_set(&event->hw.prev_count, 0);
+ }
return x86_perf_event_set_period(event);
}
@@ -1372,6 +1392,13 @@ again:
x86_pmu.drain_pebs(regs);
}
+ /*
+ * 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];
@@ -1837,6 +1864,20 @@ static int hsw_hw_config(struct perf_event *event)
event->attr.precise_ip > 0))
return -EOPNOTSUPP;
+ if (event_is_checkpointed(event)) {
+ /*
+ * Sampling of checkpointed events can cause situations where
+ * the CPU constantly aborts because of a overflow, which is
+ * then checkpointed back and ignored. Forbid checkpointing
+ * for sampling.
+ *
+ * But still allow a long sampling period, so that perf stat
+ * from KVM works.
+ */
+ if (event->attr.sample_period > 0 &&
+ event->attr.sample_period < 0x7fffffff)
+ return -EOPNOTSUPP;
+ }
return 0;
}
@@ -2182,10 +2223,36 @@ static __init void intel_nehalem_quirk(void)
}
}
-EVENT_ATTR_STR(mem-loads, mem_ld_hsw, "event=0xcd,umask=0x1,ldlat=3");
-EVENT_ATTR_STR(mem-stores, mem_st_hsw, "event=0xd0,umask=0x82")
+EVENT_ATTR_STR(mem-loads, mem_ld_hsw, "event=0xcd,umask=0x1,ldlat=3");
+EVENT_ATTR_STR(mem-stores, mem_st_hsw, "event=0xd0,umask=0x82")
+
+/* Haswell special events */
+EVENT_ATTR_STR(tx-start, tx_start, "event=0xc9,umask=0x1");
+EVENT_ATTR_STR(tx-commit, tx_commit, "event=0xc9,umask=0x2");
+EVENT_ATTR_STR(tx-abort, tx_abort, "event=0xc9,umask=0x4");
+EVENT_ATTR_STR(tx-capacity, tx_capacity, "event=0x54,umask=0x2");
+EVENT_ATTR_STR(tx-conflict, tx_conflict, "event=0x54,umask=0x1");
+EVENT_ATTR_STR(el-start, el_start, "event=0xc8,umask=0x1");
+EVENT_ATTR_STR(el-commit, el_commit, "event=0xc8,umask=0x2");
+EVENT_ATTR_STR(el-abort, el_abort, "event=0xc8,umask=0x4");
+EVENT_ATTR_STR(el-capacity, el_capacity, "event=0x54,umask=0x2");
+EVENT_ATTR_STR(el-conflict, el_conflict, "event=0x54,umask=0x1");
+EVENT_ATTR_STR(cycles-t, cycles_t, "event=0x3c,in_tx=1");
+EVENT_ATTR_STR(cycles-ct, cycles_ct, "event=0x3c,in_tx=1,in_tx_cp=1");
static struct attribute *hsw_events_attrs[] = {
+ EVENT_PTR(tx_start),
+ EVENT_PTR(tx_commit),
+ EVENT_PTR(tx_abort),
+ EVENT_PTR(tx_capacity),
+ EVENT_PTR(tx_conflict),
+ EVENT_PTR(el_start),
+ EVENT_PTR(el_commit),
+ EVENT_PTR(el_abort),
+ EVENT_PTR(el_capacity),
+ EVENT_PTR(el_conflict),
+ EVENT_PTR(cycles_t),
+ EVENT_PTR(cycles_ct),
EVENT_PTR(mem_ld_hsw),
EVENT_PTR(mem_st_hsw),
NULL
@@ -2452,6 +2519,7 @@ __init int intel_pmu_init(void)
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
x86_pmu.cpu_events = hsw_events_attrs;
+ x86_pmu.lbr_double_abort = true;
pr_cont("Haswell events, ");
break;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index ab3ba1c1b7dd..c1760ff3c757 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -12,6 +12,7 @@
#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
#define PEBS_BUFFER_SIZE PAGE_SIZE
+#define PEBS_FIXUP_SIZE PAGE_SIZE
/*
* pebs_record_32 for p4 and core not supported
@@ -182,18 +183,32 @@ struct pebs_record_nhm {
* Same as pebs_record_nhm, with two additional fields.
*/
struct pebs_record_hsw {
- struct pebs_record_nhm nhm;
- /*
- * Real IP of the event. In the Intel documentation this
- * is called eventingrip.
- */
- u64 real_ip;
- /*
- * TSX tuning information field: abort cycles and abort flags.
- */
- u64 tsx_tuning;
+ u64 flags, ip;
+ u64 ax, bx, cx, dx;
+ u64 si, di, bp, sp;
+ u64 r8, r9, r10, r11;
+ u64 r12, r13, r14, r15;
+ u64 status, dla, dse, lat;
+ u64 real_ip, tsx_tuning;
+};
+
+union hsw_tsx_tuning {
+ struct {
+ u32 cycles_last_block : 32,
+ hle_abort : 1,
+ rtm_abort : 1,
+ instruction_abort : 1,
+ non_instruction_abort : 1,
+ retry : 1,
+ data_conflict : 1,
+ capacity_writes : 1,
+ capacity_reads : 1;
+ };
+ u64 value;
};
+#define PEBS_HSW_TSX_FLAGS 0xff00000000ULL
+
void init_debug_store_on_cpu(int cpu)
{
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
@@ -214,12 +229,14 @@ void fini_debug_store_on_cpu(int cpu)
wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
}
+static DEFINE_PER_CPU(void *, insn_buffer);
+
static int alloc_pebs_buffer(int cpu)
{
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
int node = cpu_to_node(cpu);
int max, thresh = 1; /* always use a single PEBS record */
- void *buffer;
+ void *buffer, *ibuffer;
if (!x86_pmu.pebs)
return 0;
@@ -228,6 +245,19 @@ static int alloc_pebs_buffer(int cpu)
if (unlikely(!buffer))
return -ENOMEM;
+ /*
+ * HSW+ already provides us the eventing ip; no need to allocate this
+ * buffer then.
+ */
+ if (x86_pmu.intel_cap.pebs_format < 2) {
+ ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
+ if (!ibuffer) {
+ kfree(buffer);
+ return -ENOMEM;
+ }
+ per_cpu(insn_buffer, cpu) = ibuffer;
+ }
+
max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
ds->pebs_buffer_base = (u64)(unsigned long)buffer;
@@ -248,6 +278,9 @@ static void release_pebs_buffer(int cpu)
if (!ds || !x86_pmu.pebs)
return;
+ kfree(per_cpu(insn_buffer, cpu));
+ per_cpu(insn_buffer, cpu) = NULL;
+
kfree((void *)(unsigned long)ds->pebs_buffer_base);
ds->pebs_buffer_base = 0;
}
@@ -715,6 +748,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
unsigned long old_to, to = cpuc->lbr_entries[0].to;
unsigned long ip = regs->ip;
int is_64bit = 0;
+ void *kaddr;
/*
* We don't need to fixup if the PEBS assist is fault like
@@ -738,7 +772,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
* unsigned math, either ip is before the start (impossible) or
* the basic block is larger than 1 page (sanity)
*/
- if ((ip - to) > PAGE_SIZE)
+ if ((ip - to) > PEBS_FIXUP_SIZE)
return 0;
/*
@@ -749,29 +783,33 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
return 1;
}
+ if (!kernel_ip(ip)) {
+ int size, bytes;
+ u8 *buf = this_cpu_read(insn_buffer);
+
+ size = ip - to; /* Must fit our buffer, see above */
+ bytes = copy_from_user_nmi(buf, (void __user *)to, size);
+ if (bytes != size)
+ return 0;
+
+ kaddr = buf;
+ } else {
+ kaddr = (void *)to;
+ }
+
do {
struct insn insn;
- u8 buf[MAX_INSN_SIZE];
- void *kaddr;
old_to = to;
- if (!kernel_ip(ip)) {
- int bytes, size = MAX_INSN_SIZE;
-
- bytes = copy_from_user_nmi(buf, (void __user *)to, size);
- if (bytes != size)
- return 0;
-
- kaddr = buf;
- } else
- kaddr = (void *)to;
#ifdef CONFIG_X86_64
is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32);
#endif
insn_init(&insn, kaddr, is_64bit);
insn_get_length(&insn);
+
to += insn.length;
+ kaddr += insn.length;
} while (to < ip);
if (to == ip) {
@@ -786,16 +824,34 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
return 0;
}
+static inline u64 intel_hsw_weight(struct pebs_record_hsw *pebs)
+{
+ if (pebs->tsx_tuning) {
+ union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning };
+ return tsx.cycles_last_block;
+ }
+ return 0;
+}
+
+static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs)
+{
+ u64 txn = (pebs->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;
+ return txn;
+}
+
static void __intel_pmu_pebs_event(struct perf_event *event,
struct pt_regs *iregs, void *__pebs)
{
/*
- * We cast to pebs_record_nhm to get the load latency data
- * if extra_reg MSR_PEBS_LD_LAT_THRESHOLD used
+ * We cast to the biggest pebs_record but are careful not to
+ * unconditionally access the 'extra' entries.
*/
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- struct pebs_record_nhm *pebs = __pebs;
- struct pebs_record_hsw *pebs_hsw = __pebs;
+ struct pebs_record_hsw *pebs = __pebs;
struct perf_sample_data data;
struct pt_regs regs;
u64 sample_type;
@@ -854,7 +910,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
regs.sp = pebs->sp;
if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
- regs.ip = pebs_hsw->real_ip;
+ regs.ip = pebs->real_ip;
regs.flags |= PERF_EFLAGS_EXACT;
} else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(&regs))
regs.flags |= PERF_EFLAGS_EXACT;
@@ -862,9 +918,18 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
regs.flags &= ~PERF_EFLAGS_EXACT;
if ((event->attr.sample_type & PERF_SAMPLE_ADDR) &&
- x86_pmu.intel_cap.pebs_format >= 1)
+ x86_pmu.intel_cap.pebs_format >= 1)
data.addr = pebs->dla;
+ if (x86_pmu.intel_cap.pebs_format >= 2) {
+ /* Only set the TSX weight when no memory weight. */
+ if ((event->attr.sample_type & PERF_SAMPLE_WEIGHT) && !fll)
+ data.weight = intel_hsw_weight(pebs);
+
+ if (event->attr.sample_type & PERF_SAMPLE_TRANSACTION)
+ data.txn = intel_hsw_transaction(pebs);
+ }
+
if (has_branch_stack(event))
data.br_stack = &cpuc->lbr_stack;
@@ -913,17 +978,34 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
__intel_pmu_pebs_event(event, iregs, at);
}
-static void __intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, void *at,
- void *top)
+static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
struct debug_store *ds = cpuc->ds;
struct perf_event *event = NULL;
+ void *at, *top;
u64 status = 0;
int bit;
+ if (!x86_pmu.pebs_active)
+ return;
+
+ at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
+ top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
+
ds->pebs_index = ds->pebs_buffer_base;
+ if (unlikely(at > top))
+ return;
+
+ /*
+ * Should not happen, we program the threshold at 1 and do not
+ * set a reset value.
+ */
+ WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size,
+ "Unexpected number of pebs records %ld\n",
+ (long)(top - at) / x86_pmu.pebs_record_size);
+
for (; at < top; at += x86_pmu.pebs_record_size) {
struct pebs_record_nhm *p = at;
@@ -951,61 +1033,6 @@ static void __intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, void *at,
}
}
-static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- struct debug_store *ds = cpuc->ds;
- struct pebs_record_nhm *at, *top;
- int n;
-
- if (!x86_pmu.pebs_active)
- return;
-
- at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
- top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
-
- ds->pebs_index = ds->pebs_buffer_base;
-
- n = top - at;
- if (n <= 0)
- return;
-
- /*
- * Should not happen, we program the threshold at 1 and do not
- * set a reset value.
- */
- WARN_ONCE(n > x86_pmu.max_pebs_events,
- "Unexpected number of pebs records %d\n", n);
-
- return __intel_pmu_drain_pebs_nhm(iregs, at, top);
-}
-
-static void intel_pmu_drain_pebs_hsw(struct pt_regs *iregs)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- struct debug_store *ds = cpuc->ds;
- struct pebs_record_hsw *at, *top;
- int n;
-
- if (!x86_pmu.pebs_active)
- return;
-
- at = (struct pebs_record_hsw *)(unsigned long)ds->pebs_buffer_base;
- top = (struct pebs_record_hsw *)(unsigned long)ds->pebs_index;
-
- n = top - at;
- if (n <= 0)
- return;
- /*
- * Should not happen, we program the threshold at 1 and do not
- * set a reset value.
- */
- WARN_ONCE(n > x86_pmu.max_pebs_events,
- "Unexpected number of pebs records %d\n", n);
-
- return __intel_pmu_drain_pebs_nhm(iregs, at, top);
-}
-
/*
* BTS, PEBS probe and setup
*/
@@ -1040,7 +1067,7 @@ void intel_ds_init(void)
case 2:
pr_cont("PEBS fmt2%c, ", pebs_type);
x86_pmu.pebs_record_size = sizeof(struct pebs_record_hsw);
- x86_pmu.drain_pebs = intel_pmu_drain_pebs_hsw;
+ x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
break;
default:
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index d5be06a5005e..90ee6c1d0542 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -284,6 +284,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
int lbr_format = x86_pmu.intel_cap.lbr_format;
u64 tos = intel_pmu_lbr_tos();
int i;
+ int out = 0;
for (i = 0; i < x86_pmu.lbr_nr; i++) {
unsigned long lbr_idx = (tos - i) & mask;
@@ -306,15 +307,27 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
}
from = (u64)((((s64)from) << skip) >> skip);
- cpuc->lbr_entries[i].from = from;
- cpuc->lbr_entries[i].to = to;
- cpuc->lbr_entries[i].mispred = mis;
- cpuc->lbr_entries[i].predicted = pred;
- cpuc->lbr_entries[i].in_tx = in_tx;
- cpuc->lbr_entries[i].abort = abort;
- cpuc->lbr_entries[i].reserved = 0;
+ /*
+ * Some CPUs report duplicated abort records,
+ * with the second entry not having an abort bit set.
+ * Skip them here. This loop runs backwards,
+ * so we need to undo the previous record.
+ * If the abort just happened outside the window
+ * the extra entry cannot be removed.
+ */
+ if (abort && x86_pmu.lbr_double_abort && out > 0)
+ out--;
+
+ cpuc->lbr_entries[out].from = from;
+ cpuc->lbr_entries[out].to = to;
+ cpuc->lbr_entries[out].mispred = mis;
+ cpuc->lbr_entries[out].predicted = pred;
+ cpuc->lbr_entries[out].in_tx = in_tx;
+ cpuc->lbr_entries[out].abort = abort;
+ cpuc->lbr_entries[out].reserved = 0;
+ out++;
}
- cpuc->lbr_stack.nr = i;
+ cpuc->lbr_stack.nr = out;
}
void intel_pmu_lbr_read(void)
generated by cgit v1.2.3-55-g7522 (git 2.39.0) at 2024-11-06 12:34:32 +0100