summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/powerpc/perf/core-book3s.c36
-rw-r--r--arch/powerpc/perf/hv-24x7.c166
-rw-r--r--arch/powerpc/perf/power8-pmu.c3
-rw-r--r--arch/s390/kernel/perf_cpum_cf.c35
-rw-r--r--arch/sparc/kernel/perf_event.c32
-rw-r--r--arch/x86/kernel/cpu/Makefile1
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c8
-rw-r--r--arch/x86/kernel/cpu/perf_event.c39
-rw-r--r--arch/x86/kernel/cpu/perf_event.h2
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_bts.c13
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_cstate.c694
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c40
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_lbr.c8
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_pt.c7
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c61
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.h12
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c16
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c34
-rw-r--r--arch/x86/kernel/tsc.c35
-rw-r--r--arch/x86/lib/x86-opcode-map.txt24
20 files changed, 1190 insertions, 76 deletions
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index b0382f3f1095..d1e65ce545b3 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -48,7 +48,7 @@ struct cpu_hw_events {
unsigned long amasks[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
unsigned long avalues[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES];
- unsigned int group_flag;
+ unsigned int txn_flags;
int n_txn_start;
/* BHRB bits */
@@ -1441,7 +1441,7 @@ static int power_pmu_add(struct perf_event *event, int ef_flags)
* skip the schedulability test here, it will be performed
* at commit time(->commit_txn) as a whole
*/
- if (cpuhw->group_flag & PERF_EVENT_TXN)
+ if (cpuhw->txn_flags & PERF_PMU_TXN_ADD)
goto nocheck;
if (check_excludes(cpuhw->event, cpuhw->flags, n0, 1))
@@ -1586,13 +1586,22 @@ static void power_pmu_stop(struct perf_event *event, int ef_flags)
* Start group events scheduling transaction
* Set the flag to make pmu::enable() not perform the
* schedulability test, it will be performed at commit time
+ *
+ * We only support PERF_PMU_TXN_ADD transactions. Save the
+ * transaction flags but otherwise ignore non-PERF_PMU_TXN_ADD
+ * transactions.
*/
-static void power_pmu_start_txn(struct pmu *pmu)
+static void power_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags)
{
struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+ WARN_ON_ONCE(cpuhw->txn_flags); /* txn already in flight */
+
+ cpuhw->txn_flags = txn_flags;
+ if (txn_flags & ~PERF_PMU_TXN_ADD)
+ return;
+
perf_pmu_disable(pmu);
- cpuhw->group_flag |= PERF_EVENT_TXN;
cpuhw->n_txn_start = cpuhw->n_events;
}
@@ -1604,8 +1613,15 @@ static void power_pmu_start_txn(struct pmu *pmu)
static void power_pmu_cancel_txn(struct pmu *pmu)
{
struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+ unsigned int txn_flags;
+
+ WARN_ON_ONCE(!cpuhw->txn_flags); /* no txn in flight */
+
+ txn_flags = cpuhw->txn_flags;
+ cpuhw->txn_flags = 0;
+ if (txn_flags & ~PERF_PMU_TXN_ADD)
+ return;
- cpuhw->group_flag &= ~PERF_EVENT_TXN;
perf_pmu_enable(pmu);
}
@@ -1621,7 +1637,15 @@ static int power_pmu_commit_txn(struct pmu *pmu)
if (!ppmu)
return -EAGAIN;
+
cpuhw = this_cpu_ptr(&cpu_hw_events);
+ WARN_ON_ONCE(!cpuhw->txn_flags); /* no txn in flight */
+
+ if (cpuhw->txn_flags & ~PERF_PMU_TXN_ADD) {
+ cpuhw->txn_flags = 0;
+ return 0;
+ }
+
n = cpuhw->n_events;
if (check_excludes(cpuhw->event, cpuhw->flags, 0, n))
return -EAGAIN;
@@ -1632,7 +1656,7 @@ static int power_pmu_commit_txn(struct pmu *pmu)
for (i = cpuhw->n_txn_start; i < n; ++i)
cpuhw->event[i]->hw.config = cpuhw->events[i];
- cpuhw->group_flag &= ~PERF_EVENT_TXN;
+ cpuhw->txn_flags = 0;
perf_pmu_enable(pmu);
return 0;
}
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 527c8b98e97e..9f9dfda9ed2c 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -142,6 +142,15 @@ static struct attribute_group event_long_desc_group = {
static struct kmem_cache *hv_page_cache;
+DEFINE_PER_CPU(int, hv_24x7_txn_flags);
+DEFINE_PER_CPU(int, hv_24x7_txn_err);
+
+struct hv_24x7_hw {
+ struct perf_event *events[255];
+};
+
+DEFINE_PER_CPU(struct hv_24x7_hw, hv_24x7_hw);
+
/*
* request_buffer and result_buffer are not required to be 4k aligned,
* but are not allowed to cross any 4k boundary. Aligning them to 4k is
@@ -1231,9 +1240,48 @@ static void update_event_count(struct perf_event *event, u64 now)
static void h_24x7_event_read(struct perf_event *event)
{
u64 now;
+ struct hv_24x7_request_buffer *request_buffer;
+ struct hv_24x7_hw *h24x7hw;
+ int txn_flags;
+
+ txn_flags = __this_cpu_read(hv_24x7_txn_flags);
+
+ /*
+ * If in a READ transaction, add this counter to the list of
+ * counters to read during the next HCALL (i.e commit_txn()).
+ * If not in a READ transaction, go ahead and make the HCALL
+ * to read this counter by itself.
+ */
+
+ if (txn_flags & PERF_PMU_TXN_READ) {
+ int i;
+ int ret;
- now = h_24x7_get_value(event);
- update_event_count(event, now);
+ if (__this_cpu_read(hv_24x7_txn_err))
+ return;
+
+ request_buffer = (void *)get_cpu_var(hv_24x7_reqb);
+
+ ret = add_event_to_24x7_request(event, request_buffer);
+ if (ret) {
+ __this_cpu_write(hv_24x7_txn_err, ret);
+ } else {
+ /*
+ * Assoicate the event with the HCALL request index,
+ * so ->commit_txn() can quickly find/update count.
+ */
+ i = request_buffer->num_requests - 1;
+
+ h24x7hw = &get_cpu_var(hv_24x7_hw);
+ h24x7hw->events[i] = event;
+ put_cpu_var(h24x7hw);
+ }
+
+ put_cpu_var(hv_24x7_reqb);
+ } else {
+ now = h_24x7_get_value(event);
+ update_event_count(event, now);
+ }
}
static void h_24x7_event_start(struct perf_event *event, int flags)
@@ -1255,6 +1303,117 @@ static int h_24x7_event_add(struct perf_event *event, int flags)
return 0;
}
+/*
+ * 24x7 counters only support READ transactions. They are
+ * always counting and dont need/support ADD transactions.
+ * Cache the flags, but otherwise ignore transactions that
+ * are not PERF_PMU_TXN_READ.
+ */
+static void h_24x7_event_start_txn(struct pmu *pmu, unsigned int flags)
+{
+ struct hv_24x7_request_buffer *request_buffer;
+ struct hv_24x7_data_result_buffer *result_buffer;
+
+ /* We should not be called if we are already in a txn */
+ WARN_ON_ONCE(__this_cpu_read(hv_24x7_txn_flags));
+
+ __this_cpu_write(hv_24x7_txn_flags, flags);
+ if (flags & ~PERF_PMU_TXN_READ)
+ return;
+
+ request_buffer = (void *)get_cpu_var(hv_24x7_reqb);
+ result_buffer = (void *)get_cpu_var(hv_24x7_resb);
+
+ init_24x7_request(request_buffer, result_buffer);
+
+ put_cpu_var(hv_24x7_resb);
+ put_cpu_var(hv_24x7_reqb);
+}
+
+/*
+ * Clean up transaction state.
+ *
+ * NOTE: Ignore state of request and result buffers for now.
+ * We will initialize them during the next read/txn.
+ */
+static void reset_txn(void)
+{
+ __this_cpu_write(hv_24x7_txn_flags, 0);
+ __this_cpu_write(hv_24x7_txn_err, 0);
+}
+
+/*
+ * 24x7 counters only support READ transactions. They are always counting
+ * and dont need/support ADD transactions. Clear ->txn_flags but otherwise
+ * ignore transactions that are not of type PERF_PMU_TXN_READ.
+ *
+ * For READ transactions, submit all pending 24x7 requests (i.e requests
+ * that were queued by h_24x7_event_read()), to the hypervisor and update
+ * the event counts.
+ */
+static int h_24x7_event_commit_txn(struct pmu *pmu)
+{
+ struct hv_24x7_request_buffer *request_buffer;
+ struct hv_24x7_data_result_buffer *result_buffer;
+ struct hv_24x7_result *resb;
+ struct perf_event *event;
+ u64 count;
+ int i, ret, txn_flags;
+ struct hv_24x7_hw *h24x7hw;
+
+ txn_flags = __this_cpu_read(hv_24x7_txn_flags);
+ WARN_ON_ONCE(!txn_flags);
+
+ ret = 0;
+ if (txn_flags & ~PERF_PMU_TXN_READ)
+ goto out;
+
+ ret = __this_cpu_read(hv_24x7_txn_err);
+ if (ret)
+ goto out;
+
+ request_buffer = (void *)get_cpu_var(hv_24x7_reqb);
+ result_buffer = (void *)get_cpu_var(hv_24x7_resb);
+
+ ret = make_24x7_request(request_buffer, result_buffer);
+ if (ret) {
+ log_24x7_hcall(request_buffer, result_buffer, ret);
+ goto put_reqb;
+ }
+
+ h24x7hw = &get_cpu_var(hv_24x7_hw);
+
+ /* Update event counts from hcall */
+ for (i = 0; i < request_buffer->num_requests; i++) {
+ resb = &result_buffer->results[i];
+ count = be64_to_cpu(resb->elements[0].element_data[0]);
+ event = h24x7hw->events[i];
+ h24x7hw->events[i] = NULL;
+ update_event_count(event, count);
+ }
+
+ put_cpu_var(hv_24x7_hw);
+
+put_reqb:
+ put_cpu_var(hv_24x7_resb);
+ put_cpu_var(hv_24x7_reqb);
+out:
+ reset_txn();
+ return ret;
+}
+
+/*
+ * 24x7 counters only support READ transactions. They are always counting
+ * and dont need/support ADD transactions. However, regardless of type
+ * of transaction, all we need to do is cleanup, so we don't have to check
+ * the type of transaction.
+ */
+static void h_24x7_event_cancel_txn(struct pmu *pmu)
+{
+ WARN_ON_ONCE(!__this_cpu_read(hv_24x7_txn_flags));
+ reset_txn();
+}
+
static struct pmu h_24x7_pmu = {
.task_ctx_nr = perf_invalid_context,
@@ -1266,6 +1425,9 @@ static struct pmu h_24x7_pmu = {
.start = h_24x7_event_start,
.stop = h_24x7_event_stop,
.read = h_24x7_event_read,
+ .start_txn = h_24x7_event_start_txn,
+ .commit_txn = h_24x7_event_commit_txn,
+ .cancel_txn = h_24x7_event_cancel_txn,
};
static int hv_24x7_init(void)
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index 396351db601b..7d5e295255b7 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -676,6 +676,9 @@ static u64 power8_bhrb_filter_map(u64 branch_sample_type)
if (branch_sample_type & PERF_SAMPLE_BRANCH_IND_CALL)
return -1;
+ if (branch_sample_type & PERF_SAMPLE_BRANCH_CALL)
+ return -1;
+
if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_CALL) {
pmu_bhrb_filter |= POWER8_MMCRA_IFM1;
return pmu_bhrb_filter;
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index a9563409c36e..929c147e07b4 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -72,6 +72,7 @@ struct cpu_hw_events {
atomic_t ctr_set[CPUMF_CTR_SET_MAX];
u64 state, tx_state;
unsigned int flags;
+ unsigned int txn_flags;
};
static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
.ctr_set = {
@@ -82,6 +83,7 @@ static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
},
.state = 0,
.flags = 0,
+ .txn_flags = 0,
};
static int get_counter_set(u64 event)
@@ -538,7 +540,7 @@ static int cpumf_pmu_add(struct perf_event *event, int flags)
* For group events transaction, the authorization check is
* done in cpumf_pmu_commit_txn().
*/
- if (!(cpuhw->flags & PERF_EVENT_TXN))
+ if (!(cpuhw->txn_flags & PERF_PMU_TXN_ADD))
if (validate_ctr_auth(&event->hw))
return -ENOENT;
@@ -576,13 +578,22 @@ static void cpumf_pmu_del(struct perf_event *event, int flags)
/*
* Start group events scheduling transaction.
* Set flags to perform a single test at commit time.
+ *
+ * We only support PERF_PMU_TXN_ADD transactions. Save the
+ * transaction flags but otherwise ignore non-PERF_PMU_TXN_ADD
+ * transactions.
*/
-static void cpumf_pmu_start_txn(struct pmu *pmu)
+static void cpumf_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags)
{
struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+ WARN_ON_ONCE(cpuhw->txn_flags); /* txn already in flight */
+
+ cpuhw->txn_flags = txn_flags;
+ if (txn_flags & ~PERF_PMU_TXN_ADD)
+ return;
+
perf_pmu_disable(pmu);
- cpuhw->flags |= PERF_EVENT_TXN;
cpuhw->tx_state = cpuhw->state;
}
@@ -593,11 +604,18 @@ static void cpumf_pmu_start_txn(struct pmu *pmu)
*/
static void cpumf_pmu_cancel_txn(struct pmu *pmu)
{
+ unsigned int txn_flags;
struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+ WARN_ON_ONCE(!cpuhw->txn_flags); /* no txn in flight */
+
+ txn_flags = cpuhw->txn_flags;
+ cpuhw->txn_flags = 0;
+ if (txn_flags & ~PERF_PMU_TXN_ADD)
+ return;
+
WARN_ON(cpuhw->tx_state != cpuhw->state);
- cpuhw->flags &= ~PERF_EVENT_TXN;
perf_pmu_enable(pmu);
}
@@ -611,13 +629,20 @@ static int cpumf_pmu_commit_txn(struct pmu *pmu)
struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
u64 state;
+ WARN_ON_ONCE(!cpuhw->txn_flags); /* no txn in flight */
+
+ if (cpuhw->txn_flags & ~PERF_PMU_TXN_ADD) {
+ cpuhw->txn_flags = 0;
+ return 0;
+ }
+
/* check if the updated state can be scheduled */
state = cpuhw->state & ~((1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1);
state >>= CPUMF_LCCTL_ENABLE_SHIFT;
if ((state & cpuhw->info.auth_ctl) != state)
return -ENOENT;
- cpuhw->flags &= ~PERF_EVENT_TXN;
+ cpuhw->txn_flags = 0;
perf_pmu_enable(pmu);
return 0;
}
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 689db65f8529..b0da5aedb336 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -108,7 +108,7 @@ struct cpu_hw_events {
/* Enabled/disable state. */
int enabled;
- unsigned int group_flag;
+ unsigned int txn_flags;
};
static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, };
@@ -1379,7 +1379,7 @@ static int sparc_pmu_add(struct perf_event *event, int ef_flags)
* skip the schedulability test here, it will be performed
* at commit time(->commit_txn) as a whole
*/
- if (cpuc->group_flag & PERF_EVENT_TXN)
+ if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
goto nocheck;
if (check_excludes(cpuc->event, n0, 1))
@@ -1494,12 +1494,17 @@ static int sparc_pmu_event_init(struct perf_event *event)
* Set the flag to make pmu::enable() not perform the
* schedulability test, it will be performed at commit time
*/
-static void sparc_pmu_start_txn(struct pmu *pmu)
+static void sparc_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags)
{
struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+ WARN_ON_ONCE(cpuhw->txn_flags); /* txn already in flight */
+
+ cpuhw->txn_flags = txn_flags;
+ if (txn_flags & ~PERF_PMU_TXN_ADD)
+ return;
+
perf_pmu_disable(pmu);
- cpuhw->group_flag |= PERF_EVENT_TXN;
}
/*
@@ -1510,8 +1515,15 @@ static void sparc_pmu_start_txn(struct pmu *pmu)
static void sparc_pmu_cancel_txn(struct pmu *pmu)
{
struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
+ unsigned int txn_flags;
+
+ WARN_ON_ONCE(!cpuhw->txn_flags); /* no txn in flight */
+
+ txn_flags = cpuhw->txn_flags;
+ cpuhw->txn_flags = 0;
+ if (txn_flags & ~PERF_PMU_TXN_ADD)
+ return;
- cpuhw->group_flag &= ~PERF_EVENT_TXN;
perf_pmu_enable(pmu);
}
@@ -1528,14 +1540,20 @@ static int sparc_pmu_commit_txn(struct pmu *pmu)
if (!sparc_pmu)
return -EINVAL;
- cpuc = this_cpu_ptr(&cpu_hw_events);
+ WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */
+
+ if (cpuc->txn_flags & ~PERF_PMU_TXN_ADD) {
+ cpuc->txn_flags = 0;
+ return 0;
+ }
+
n = cpuc->n_events;
if (check_excludes(cpuc->event, 0, n))
return -EINVAL;
if (sparc_check_constraints(cpuc->event, cpuc->events, n))
return -EAGAIN;
- cpuc->group_flag &= ~PERF_EVENT_TXN;
+ cpuc->txn_flags = 0;
perf_pmu_enable(pmu);
return 0;
}
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 4eb065c6bed2..58031303e304 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -41,6 +41,7 @@ obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o
obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_rapl.o perf_event_intel_cqm.o
obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_pt.o perf_event_intel_bts.o
+obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_cstate.o
obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += perf_event_intel_uncore.o \
perf_event_intel_uncore_snb.o \
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index be4febc58b94..e38d338a6447 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -157,7 +157,7 @@ struct _cpuid4_info_regs {
struct amd_northbridge *nb;
};
-unsigned short num_cache_leaves;
+static unsigned short num_cache_leaves;
/* AMD doesn't have CPUID4. Emulate it here to report the same
information to the user. This makes some assumptions about the machine:
@@ -326,7 +326,7 @@ static void amd_calc_l3_indices(struct amd_northbridge *nb)
*
* @returns: the disabled index if used or negative value if slot free.
*/
-int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned slot)
+static int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned slot)
{
unsigned int reg = 0;
@@ -403,8 +403,8 @@ static void amd_l3_disable_index(struct amd_northbridge *nb, int cpu,
*
* @return: 0 on success, error status on failure
*/
-int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu, unsigned slot,
- unsigned long index)
+static int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu,
+ unsigned slot, unsigned long index)
{
int ret = 0;
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 66dd3fe99b82..4562cf070c27 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1175,7 +1175,7 @@ static int x86_pmu_add(struct perf_event *event, int flags)
* skip the schedulability test here, it will be performed
* at commit time (->commit_txn) as a whole.
*/
- if (cpuc->group_flag & PERF_EVENT_TXN)
+ if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
goto done_collect;
ret = x86_pmu.schedule_events(cpuc, n, assign);
@@ -1326,7 +1326,7 @@ static void x86_pmu_del(struct perf_event *event, int flags)
* XXX assumes any ->del() called during a TXN will only be on
* an event added during that same TXN.
*/
- if (cpuc->group_flag & PERF_EVENT_TXN)
+ if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
return;
/*
@@ -1748,11 +1748,22 @@ static inline void x86_pmu_read(struct perf_event *event)
* Start group events scheduling transaction
* Set the flag to make pmu::enable() not perform the
* schedulability test, it will be performed at commit time
+ *
+ * We only support PERF_PMU_TXN_ADD transactions. Save the
+ * transaction flags but otherwise ignore non-PERF_PMU_TXN_ADD
+ * transactions.
*/
-static void x86_pmu_start_txn(struct pmu *pmu)
+static void x86_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags)
{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ WARN_ON_ONCE(cpuc->txn_flags); /* txn already in flight */
+
+ cpuc->txn_flags = txn_flags;
+ if (txn_flags & ~PERF_PMU_TXN_ADD)
+ return;
+
perf_pmu_disable(pmu);
- __this_cpu_or(cpu_hw_events.group_flag, PERF_EVENT_TXN);
__this_cpu_write(cpu_hw_events.n_txn, 0);
}
@@ -1763,7 +1774,16 @@ static void x86_pmu_start_txn(struct pmu *pmu)
*/
static void x86_pmu_cancel_txn(struct pmu *pmu)
{
- __this_cpu_and(cpu_hw_events.group_flag, ~PERF_EVENT_TXN);
+ unsigned int txn_flags;
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */
+
+ txn_flags = cpuc->txn_flags;
+ cpuc->txn_flags = 0;
+ if (txn_flags & ~PERF_PMU_TXN_ADD)
+ return;
+
/*
* Truncate collected array by the number of events added in this
* transaction. See x86_pmu_add() and x86_pmu_*_txn().
@@ -1786,6 +1806,13 @@ static int x86_pmu_commit_txn(struct pmu *pmu)
int assign[X86_PMC_IDX_MAX];
int n, ret;
+ WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */
+
+ if (cpuc->txn_flags & ~PERF_PMU_TXN_ADD) {
+ cpuc->txn_flags = 0;
+ return 0;
+ }
+
n = cpuc->n_events;
if (!x86_pmu_initialized())
@@ -1801,7 +1828,7 @@ static int x86_pmu_commit_txn(struct pmu *pmu)
*/
memcpy(cpuc->assign, assign, n*sizeof(int));
- cpuc->group_flag &= ~PERF_EVENT_TXN;
+ cpuc->txn_flags = 0;
perf_pmu_enable(pmu);
return 0;
}
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 165be83a7fa4..499f533dd3cc 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -196,7 +196,7 @@ struct cpu_hw_events {
int n_excl; /* the number of exclusive events */
- unsigned int group_flag;
+ unsigned int txn_flags;
int is_fake;
/*
diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c
index d1c0f254afbe..2cad71d1b14c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_bts.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c
@@ -495,6 +495,19 @@ static int bts_event_init(struct perf_event *event)
if (x86_add_exclusive(x86_lbr_exclusive_bts))
return -EBUSY;
+ /*
+ * BTS leaks kernel addresses even when CPL0 tracing is
+ * disabled, so disallow intel_bts driver for unprivileged
+ * users on paranoid systems since it provides trace data
+ * to the user in a zero-copy fashion.
+ *
+ * Note that the default paranoia setting permits unprivileged
+ * users to profile the kernel.
+ */
+ if (event->attr.exclude_kernel && perf_paranoid_kernel() &&
+ !capable(CAP_SYS_ADMIN))
+ return -EACCES;
+
ret = x86_reserve_hardware();
if (ret) {
x86_del_exclusive(x86_lbr_exclusive_bts);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cstate.c b/arch/x86/kernel/cpu/perf_event_intel_cstate.c
new file mode 100644
index 000000000000..75a38b5a2e26
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_cstate.c
@@ -0,0 +1,694 @@
+/*
+ * perf_event_intel_cstate.c: support cstate residency counters
+ *
+ * Copyright (C) 2015, Intel Corp.
+ * Author: Kan Liang (kan.liang@intel.com)
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Library General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * Library General Public License for more details.
+ *
+ */
+
+/*
+ * This file export cstate related free running (read-only) counters
+ * for perf. These counters may be use simultaneously by other tools,
+ * such as turbostat. However, it still make sense to implement them
+ * in perf. Because we can conveniently collect them together with
+ * other events, and allow to use them from tools without special MSR
+ * access code.
+ *
+ * The events only support system-wide mode counting. There is no
+ * sampling support because it is not supported by the hardware.
+ *
+ * According to counters' scope and category, two PMUs are registered
+ * with the perf_event core subsystem.
+ * - 'cstate_core': The counter is available for each physical core.
+ * The counters include CORE_C*_RESIDENCY.
+ * - 'cstate_pkg': The counter is available for each physical package.
+ * The counters include PKG_C*_RESIDENCY.
+ *
+ * All of these counters are specified in the Intel® 64 and IA-32
+ * Architectures Software Developer.s Manual Vol3b.
+ *
+ * Model specific counters:
+ * MSR_CORE_C1_RES: CORE C1 Residency Counter
+ * perf code: 0x00
+ * Available model: SLM,AMT
+ * Scope: Core (each processor core has a MSR)
+ * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
+ * perf code: 0x01
+ * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ * Scope: Core
+ * MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
+ * perf code: 0x02
+ * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ * Scope: Core
+ * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
+ * perf code: 0x03
+ * Available model: SNB,IVB,HSW,BDW,SKL
+ * Scope: Core
+ * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter.
+ * perf code: 0x00
+ * Available model: SNB,IVB,HSW,BDW,SKL
+ * Scope: Package (physical package)
+ * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter.
+ * perf code: 0x01
+ * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ * Scope: Package (physical package)
+ * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter.
+ * perf code: 0x02
+ * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ * Scope: Package (physical package)
+ * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter.
+ * perf code: 0x03
+ * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ * Scope: Package (physical package)
+ * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter.
+ * perf code: 0x04
+ * Available model: HSW ULT only
+ * Scope: Package (physical package)
+ * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter.
+ * perf code: 0x05
+ * Available model: HSW ULT only
+ * Scope: Package (physical package)
+ * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
+ * perf code: 0x06
+ * Available model: HSW ULT only
+ * Scope: Package (physical package)
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/perf_event.h>
+#include <asm/cpu_device_id.h>
+#include "perf_event.h"
+
+#define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \
+static ssize_t __cstate_##_var##_show(struct kobject *kobj, \
+ struct kobj_attribute *attr, \
+ char *page) \
+{ \
+ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
+ return sprintf(page, _format "\n"); \
+} \
+static struct kobj_attribute format_attr_##_var = \
+ __ATTR(_name, 0444, __cstate_##_var##_show, NULL)
+
+static ssize_t cstate_get_attr_cpumask(struct device *dev,
+ struct device_attribute *attr,
+ char *buf);
+
+struct perf_cstate_msr {
+ u64 msr;
+ struct perf_pmu_events_attr *attr;
+ bool (*test)(int idx);
+};
+
+
+/* cstate_core PMU */
+
+static struct pmu cstate_core_pmu;
+static bool has_cstate_core;
+
+enum perf_cstate_core_id {
+ /*
+ * cstate_core events
+ */
+ PERF_CSTATE_CORE_C1_RES = 0,
+ PERF_CSTATE_CORE_C3_RES,
+ PERF_CSTATE_CORE_C6_RES,
+ PERF_CSTATE_CORE_C7_RES,
+
+ PERF_CSTATE_CORE_EVENT_MAX,
+};
+
+bool test_core(int idx)
+{
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
+ boot_cpu_data.x86 != 6)
+ return false;
+
+ switch (boot_cpu_data.x86_model) {
+ case 30: /* 45nm Nehalem */
+ case 26: /* 45nm Nehalem-EP */
+ case 46: /* 45nm Nehalem-EX */
+
+ case 37: /* 32nm Westmere */
+ case 44: /* 32nm Westmere-EP */
+ case 47: /* 32nm Westmere-EX */
+ if (idx == PERF_CSTATE_CORE_C3_RES ||
+ idx == PERF_CSTATE_CORE_C6_RES)
+ return true;
+ break;
+ case 42: /* 32nm SandyBridge */
+ case 45: /* 32nm SandyBridge-E/EN/EP */
+
+ case 58: /* 22nm IvyBridge */
+ case 62: /* 22nm IvyBridge-EP/EX */
+
+ case 60: /* 22nm Haswell Core */
+ case 63: /* 22nm Haswell Server */
+ case 69: /* 22nm Haswell ULT */
+ case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
+
+ case 61: /* 14nm Broadwell Core-M */
+ case 86: /* 14nm Broadwell Xeon D */
+ case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */
+ case 79: /* 14nm Broadwell Server */
+
+ case 78: /* 14nm Skylake Mobile */
+ case 94: /* 14nm Skylake Desktop */
+ if (idx == PERF_CSTATE_CORE_C3_RES ||
+ idx == PERF_CSTATE_CORE_C6_RES ||
+ idx == PERF_CSTATE_CORE_C7_RES)
+ return true;
+ break;
+ case 55: /* 22nm Atom "Silvermont" */
+ case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
+ case 76: /* 14nm Atom "Airmont" */
+ if (idx == PERF_CSTATE_CORE_C1_RES ||
+ idx == PERF_CSTATE_CORE_C6_RES)
+ return true;
+ break;
+ }
+
+ return false;
+}
+
+PMU_EVENT_ATTR_STRING(c1-residency, evattr_cstate_core_c1, "event=0x00");
+PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_core_c3, "event=0x01");
+PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_core_c6, "event=0x02");
+PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_core_c7, "event=0x03");
+
+static struct perf_cstate_msr core_msr[] = {
+ [PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &evattr_cstate_core_c1, test_core, },
+ [PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &evattr_cstate_core_c3, test_core, },
+ [PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &evattr_cstate_core_c6, test_core, },
+ [PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &evattr_cstate_core_c7, test_core, },
+};
+
+static struct attribute *core_events_attrs[PERF_CSTATE_CORE_EVENT_MAX + 1] = {
+ NULL,
+};
+
+static struct attribute_group core_events_attr_group = {
+ .name = "events",
+ .attrs = core_events_attrs,
+};
+
+DEFINE_CSTATE_FORMAT_ATTR(core_event, event, "config:0-63");
+static struct attribute *core_format_attrs[] = {
+ &format_attr_core_event.attr,
+ NULL,
+};
+
+static struct attribute_group core_format_attr_group = {
+ .name = "format",
+ .attrs = core_format_attrs,
+};
+
+static cpumask_t cstate_core_cpu_mask;
+static DEVICE_ATTR(cpumask, S_IRUGO, cstate_get_attr_cpumask, NULL);
+
+static struct attribute *cstate_cpumask_attrs[] = {
+ &dev_attr_cpumask.attr,
+ NULL,
+};
+
+static struct attribute_group cpumask_attr_group = {
+ .attrs = cstate_cpumask_attrs,
+};
+
+static const struct attribute_group *core_attr_groups[] = {
+ &core_events_attr_group,
+ &core_format_attr_group,
+ &cpumask_attr_group,
+ NULL,
+};
+
+/* cstate_core PMU end */
+
+
+/* cstate_pkg PMU */
+
+static struct pmu cstate_pkg_pmu;
+static bool has_cstate_pkg;
+
+enum perf_cstate_pkg_id {
+ /*
+ * cstate_pkg events
+ */
+ PERF_CSTATE_PKG_C2_RES = 0,
+ PERF_CSTATE_PKG_C3_RES,
+ PERF_CSTATE_PKG_C6_RES,
+ PERF_CSTATE_PKG_C7_RES,
+ PERF_CSTATE_PKG_C8_RES,
+ PERF_CSTATE_PKG_C9_RES,
+ PERF_CSTATE_PKG_C10_RES,
+
+ PERF_CSTATE_PKG_EVENT_MAX,
+};
+
+bool test_pkg(int idx)
+{
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
+ boot_cpu_data.x86 != 6)
+ return false;
+
+ switch (boot_cpu_data.x86_model) {
+ case 30: /* 45nm Nehalem */
+ case 26: /* 45nm Nehalem-EP */
+ case 46: /* 45nm Nehalem-EX */
+
+ case 37: /* 32nm Westmere */
+ case 44: /* 32nm Westmere-EP */
+ case 47: /* 32nm Westmere-EX */
+ if (idx == PERF_CSTATE_CORE_C3_RES ||
+ idx == PERF_CSTATE_CORE_C6_RES ||
+ idx == PERF_CSTATE_CORE_C7_RES)
+ return true;
+ break;
+ case 42: /* 32nm SandyBridge */
+ case 45: /* 32nm SandyBridge-E/EN/EP */
+
+ case 58: /* 22nm IvyBridge */
+ case 62: /* 22nm IvyBridge-EP/EX */
+
+ case 60: /* 22nm Haswell Core */
+ case 63: /* 22nm Haswell Server */
+ case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
+
+ case 61: /* 14nm Broadwell Core-M */
+ case 86: /* 14nm Broadwell Xeon D */
+ case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */
+ case 79: /* 14nm Broadwell Server */
+
+ case 78: /* 14nm Skylake Mobile */
+ case 94: /* 14nm Skylake Desktop */
+ if (idx == PERF_CSTATE_PKG_C2_RES ||
+ idx == PERF_CSTATE_PKG_C3_RES ||
+ idx == PERF_CSTATE_PKG_C6_RES ||
+ idx == PERF_CSTATE_PKG_C7_RES)
+ return true;
+ break;
+ case 55: /* 22nm Atom "Silvermont" */
+ case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
+ case 76: /* 14nm Atom "Airmont" */
+ if (idx == PERF_CSTATE_CORE_C6_RES)
+ return true;
+ break;
+ case 69: /* 22nm Haswell ULT */
+ if (idx == PERF_CSTATE_PKG_C2_RES ||
+ idx == PERF_CSTATE_PKG_C3_RES ||
+ idx == PERF_CSTATE_PKG_C6_RES ||
+ idx == PERF_CSTATE_PKG_C7_RES ||
+ idx == PERF_CSTATE_PKG_C8_RES ||
+ idx == PERF_CSTATE_PKG_C9_RES ||
+ idx == PERF_CSTATE_PKG_C10_RES)
+ return true;
+ break;
+ }
+
+ return false;
+}
+
+PMU_EVENT_ATTR_STRING(c2-residency, evattr_cstate_pkg_c2, "event=0x00");
+PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_pkg_c3, "event=0x01");
+PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_pkg_c6, "event=0x02");
+PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_pkg_c7, "event=0x03");
+PMU_EVENT_ATTR_STRING(c8-residency, evattr_cstate_pkg_c8, "event=0x04");
+PMU_EVENT_ATTR_STRING(c9-residency, evattr_cstate_pkg_c9, "event=0x05");
+PMU_EVENT_ATTR_STRING(c10-residency, evattr_cstate_pkg_c10, "event=0x06");
+
+static struct perf_cstate_msr pkg_msr[] = {
+ [PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &evattr_cstate_pkg_c2, test_pkg, },
+ [PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &evattr_cstate_pkg_c3, test_pkg, },
+ [PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &evattr_cstate_pkg_c6, test_pkg, },
+ [PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &evattr_cstate_pkg_c7, test_pkg, },
+ [PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &evattr_cstate_pkg_c8, test_pkg, },
+ [PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &evattr_cstate_pkg_c9, test_pkg, },
+ [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &evattr_cstate_pkg_c10, test_pkg, },
+};
+
+static struct attribute *pkg_events_attrs[PERF_CSTATE_PKG_EVENT_MAX + 1] = {
+ NULL,
+};
+
+static struct attribute_group pkg_events_attr_group = {
+ .name = "events",
+ .attrs = pkg_events_attrs,
+};
+
+DEFINE_CSTATE_FORMAT_ATTR(pkg_event, event, "config:0-63");
+static struct attribute *pkg_format_attrs[] = {
+ &format_attr_pkg_event.attr,
+ NULL,
+};
+static struct attribute_group pkg_format_attr_group = {
+ .name = "format",
+ .attrs = pkg_format_attrs,
+};
+
+static cpumask_t cstate_pkg_cpu_mask;
+
+static const struct attribute_group *pkg_attr_groups[] = {
+ &pkg_events_attr_group,
+ &pkg_format_attr_group,
+ &cpumask_attr_group,
+ NULL,
+};
+
+/* cstate_pkg PMU end*/
+
+static ssize_t cstate_get_attr_cpumask(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct pmu *pmu = dev_get_drvdata(dev);
+
+ if (pmu == &cstate_core_pmu)
+ return cpumap_print_to_pagebuf(true, buf, &cstate_core_cpu_mask);
+ else if (pmu == &cstate_pkg_pmu)
+ return cpumap_print_to_pagebuf(true, buf, &cstate_pkg_cpu_mask);
+ else
+ return 0;
+}
+
+static int cstate_pmu_event_init(struct perf_event *event)
+{
+ u64 cfg = event->attr.config;
+ int ret = 0;
+
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
+
+ /* unsupported modes and filters */
+ if (event->attr.exclude_user ||
+ event->attr.exclude_kernel ||
+ event->attr.exclude_hv ||
+ event->attr.exclude_idle ||
+ event->attr.exclude_host ||
+ event->attr.exclude_guest ||
+ event->attr.sample_period) /* no sampling */
+ return -EINVAL;
+
+ if (event->pmu == &cstate_core_pmu) {
+ if (cfg >= PERF_CSTATE_CORE_EVENT_MAX)
+ return -EINVAL;
+ if (!core_msr[cfg].attr)
+ return -EINVAL;
+ event->hw.event_base = core_msr[cfg].msr;
+ } else if (event->pmu == &cstate_pkg_pmu) {
+ if (cfg >= PERF_CSTATE_PKG_EVENT_MAX)
+ return -EINVAL;
+ if (!pkg_msr[cfg].attr)
+ return -EINVAL;
+ event->hw.event_base = pkg_msr[cfg].msr;
+ } else
+ return -ENOENT;
+
+ /* must be done before validate_group */
+ event->hw.config = cfg;
+ event->hw.idx = -1;
+
+ return ret;
+}
+
+static inline u64 cstate_pmu_read_counter(struct perf_event *event)
+{
+ u64 val;
+
+ rdmsrl(event->hw.event_base, val);
+ return val;
+}
+
+static void cstate_pmu_event_update(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ u64 prev_raw_count, new_raw_count;
+
+again:
+ prev_raw_count = local64_read(&hwc->prev_count);
+ new_raw_count = cstate_pmu_read_counter(event);
+
+ if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+ new_raw_count) != prev_raw_count)
+ goto again;
+
+ local64_add(new_raw_count - prev_raw_count, &event->count);
+}
+
+static void cstate_pmu_event_start(struct perf_event *event, int mode)
+{
+ local64_set(&event->hw.prev_count, cstate_pmu_read_counter(event));
+}
+
+static void cstate_pmu_event_stop(struct perf_event *event, int mode)
+{
+ cstate_pmu_event_update(event);
+}
+
+static void cstate_pmu_event_del(struct perf_event *event, int mode)
+{
+ cstate_pmu_event_stop(event, PERF_EF_UPDATE);
+}
+
+static int cstate_pmu_event_add(struct perf_event *event, int mode)
+{
+ if (mode & PERF_EF_START)
+ cstate_pmu_event_start(event, mode);
+
+ return 0;
+}
+
+static void cstate_cpu_exit(int cpu)
+{
+ int i, id, target;
+
+ /* cpu exit for cstate core */
+ if (has_cstate_core) {
+ id = topology_core_id(cpu);
+ target = -1;
+
+ for_each_online_cpu(i) {
+ if (i == cpu)
+ continue;
+ if (id == topology_core_id(i)) {
+ target = i;
+ break;
+ }
+ }
+ if (cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask) && target >= 0)
+ cpumask_set_cpu(target, &cstate_core_cpu_mask);
+ WARN_ON(cpumask_empty(&cstate_core_cpu_mask));
+ if (target >= 0)
+ perf_pmu_migrate_context(&cstate_core_pmu, cpu, target);
+ }
+
+ /* cpu exit for cstate pkg */
+ if (has_cstate_pkg) {
+ id = topology_physical_package_id(cpu);
+ target = -1;
+
+ for_each_online_cpu(i) {
+ if (i == cpu)
+ continue;
+ if (id == topology_physical_package_id(i)) {
+ target = i;
+ break;
+ }
+ }
+ if (cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask) && target >= 0)
+ cpumask_set_cpu(target, &cstate_pkg_cpu_mask);
+ WARN_ON(cpumask_empty(&cstate_pkg_cpu_mask));
+ if (target >= 0)
+ perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target);
+ }
+}
+
+static void cstate_cpu_init(int cpu)
+{
+ int i, id;
+
+ /* cpu init for cstate core */
+ if (has_cstate_core) {
+ id = topology_core_id(cpu);
+ for_each_cpu(i, &cstate_core_cpu_mask) {
+ if (id == topology_core_id(i))
+ break;
+ }
+ if (i >= nr_cpu_ids)
+ cpumask_set_cpu(cpu, &cstate_core_cpu_mask);
+ }
+
+ /* cpu init for cstate pkg */
+ if (has_cstate_pkg) {
+ id = topology_physical_package_id(cpu);
+ for_each_cpu(i, &cstate_pkg_cpu_mask) {
+ if (id == topology_physical_package_id(i))
+ break;
+ }
+ if (i >= nr_cpu_ids)
+ cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask);
+ }
+}
+
+static int cstate_cpu_notifier(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ unsigned int cpu = (long)hcpu;
+
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_UP_PREPARE:
+ break;
+ case CPU_STARTING:
+ cstate_cpu_init(cpu);
+ break;
+ case CPU_UP_CANCELED:
+ case CPU_DYING:
+ break;
+ case CPU_ONLINE:
+ case CPU_DEAD:
+ break;
+ case CPU_DOWN_PREPARE:
+ cstate_cpu_exit(cpu);
+ break;
+ default:
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+/*
+ * Probe the cstate events and insert the available one into sysfs attrs
+ * Return false if there is no available events.
+ */
+static bool cstate_probe_msr(struct perf_cstate_msr *msr,
+ struct attribute **events_attrs,
+ int max_event_nr)
+{
+ int i, j = 0;
+ u64 val;
+
+ /* Probe the cstate events. */
+ for (i = 0; i < max_event_nr; i++) {
+ if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val))
+ msr[i].attr = NULL;
+ }
+
+ /* List remaining events in the sysfs attrs. */
+ for (i = 0; i < max_event_nr; i++) {
+ if (msr[i].attr)
+ events_attrs[j++] = &msr[i].attr->attr.attr;
+ }
+ events_attrs[j] = NULL;
+
+ return (j > 0) ? true : false;
+}
+
+static int __init cstate_init(void)
+{
+ /* SLM has different MSR for PKG C6 */
+ switch (boot_cpu_data.x86_model) {
+ case 55:
+ case 76:
+ case 77:
+ pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY;
+ }
+
+ if (cstate_probe_msr(core_msr, core_events_attrs, PERF_CSTATE_CORE_EVENT_MAX))
+ has_cstate_core = true;
+
+ if (cstate_probe_msr(pkg_msr, pkg_events_attrs, PERF_CSTATE_PKG_EVENT_MAX))
+ has_cstate_pkg = true;
+
+ return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV;
+}
+
+static void __init cstate_cpumask_init(void)
+{
+ int cpu;
+
+ cpu_notifier_register_begin();
+
+ for_each_online_cpu(cpu)
+ cstate_cpu_init(cpu);
+
+ __perf_cpu_notifier(cstate_cpu_notifier);
+
+ cpu_notifier_register_done();
+}
+
+static struct pmu cstate_core_pmu = {
+ .attr_groups = core_attr_groups,
+ .name = "cstate_core",
+ .task_ctx_nr = perf_invalid_context,
+ .event_init = cstate_pmu_event_init,
+ .add = cstate_pmu_event_add, /* must have */
+ .del = cstate_pmu_event_del, /* must have */
+ .start = cstate_pmu_event_start,
+ .stop = cstate_pmu_event_stop,
+ .read = cstate_pmu_event_update,
+ .capabilities = PERF_PMU_CAP_NO_INTERRUPT,
+};
+
+static struct pmu cstate_pkg_pmu = {
+ .attr_groups = pkg_attr_groups,
+ .name = "cstate_pkg",
+ .task_ctx_nr = perf_invalid_context,
+ .event_init = cstate_pmu_event_init,
+ .add = cstate_pmu_event_add, /* must have */
+ .del = cstate_pmu_event_del, /* must have */
+ .start = cstate_pmu_event_start,
+ .stop = cstate_pmu_event_stop,
+ .read = cstate_pmu_event_update,
+ .capabilities = PERF_PMU_CAP_NO_INTERRUPT,
+};
+
+static void __init cstate_pmus_register(void)
+{
+ int err;
+
+ if (has_cstate_core) {
+ err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1);
+ if (WARN_ON(err))
+ pr_info("Failed to register PMU %s error %d\n",
+ cstate_core_pmu.name, err);
+ }
+
+ if (has_cstate_pkg) {
+ err = perf_pmu_register(&cstate_pkg_pmu, cstate_pkg_pmu.name, -1);
+ if (WARN_ON(err))
+ pr_info("Failed to register PMU %s error %d\n",
+ cstate_pkg_pmu.name, err);
+ }
+}
+
+static int __init cstate_pmu_init(void)
+{
+ int err;
+
+ if (cpu_has_hypervisor)
+ return -ENODEV;
+
+ err = cstate_init();
+ if (err)
+ return err;
+
+ cstate_cpumask_init();
+
+ cstate_pmus_register();
+
+ return 0;
+}
+
+device_initcall(cstate_pmu_init);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 84f236ab96b0..5db1c7755548 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -510,10 +510,11 @@ int intel_pmu_drain_bts_buffer(void)
u64 flags;
};
struct perf_event *event = cpuc->events[INTEL_PMC_IDX_FIXED_BTS];
- struct bts_record *at, *top;
+ struct bts_record *at, *base, *top;
struct perf_output_handle handle;
struct perf_event_header header;
struct perf_sample_data data;
+ unsigned long skip = 0;
struct pt_regs regs;
if (!event)
@@ -522,10 +523,10 @@ int intel_pmu_drain_bts_buffer(void)
if (!x86_pmu.bts_active)
return 0;
- at = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
- top = (struct bts_record *)(unsigned long)ds->bts_index;
+ base = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
+ top = (struct bts_record *)(unsigned long)ds->bts_index;
- if (top <= at)
+ if (top <= base)
return 0;
memset(&regs, 0, sizeof(regs));
@@ -535,16 +536,43 @@ int intel_pmu_drain_bts_buffer(void)
perf_sample_data_init(&data, 0, event->hw.last_period);
/*
+ * BTS leaks kernel addresses in branches across the cpl boundary,
+ * such as traps or system calls, so unless the user is asking for
+ * kernel tracing (and right now it's not possible), we'd need to
+ * filter them out. But first we need to count how many of those we
+ * have in the current batch. This is an extra O(n) pass, however,
+ * it's much faster than the other one especially considering that
+ * n <= 2560 (BTS_BUFFER_SIZE / BTS_RECORD_SIZE * 15/16; see the
+ * alloc_bts_buffer()).
+ */
+ for (at = base; at < top; at++) {
+ /*
+ * Note that right now *this* BTS code only works if
+ * attr::exclude_kernel is set, but let's keep this extra
+ * check here in case that changes.
+ */
+ if (event->attr.exclude_kernel &&
+ (kernel_ip(at->from) || kernel_ip(at->to)))
+ skip++;
+ }
+
+ /*
* Prepare a generic sample, i.e. fill in the invariant fields.
* We will overwrite the from and to address before we output
* the sample.
*/
perf_prepare_sample(&header, &data, event, &regs);
- if (perf_output_begin(&handle, event, header.size * (top - at)))
+ if (perf_output_begin(&handle, event, header.size *
+ (top - base - skip)))
return 1;
- for (; at < top; at++) {
+ for (at = base; at < top; at++) {
+ /* Filter out any records that contain kernel addresses. */
+ if (event->attr.exclude_kernel &&
+ (kernel_ip(at->from) || kernel_ip(at->to)))
+ continue;
+
data.ip = at->from;
data.addr = at->to;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index b2c9475b7ff2..bfd0b717e944 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -151,10 +151,10 @@ static void __intel_pmu_lbr_enable(bool pmi)
* No need to reprogram LBR_SELECT in a PMI, as it
* did not change.
*/
- if (cpuc->lbr_sel && !pmi) {
+ if (cpuc->lbr_sel)
lbr_select = cpuc->lbr_sel->config;
+ if (!pmi)
wrmsrl(MSR_LBR_SELECT, lbr_select);
- }
rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
orig_debugctl = debugctl;
@@ -555,6 +555,8 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP)
mask |= X86_BR_IND_JMP;
+ if (br_type & PERF_SAMPLE_BRANCH_CALL)
+ mask |= X86_BR_CALL | X86_BR_ZERO_CALL;
/*
* stash actual user request into reg, it may
* be used by fixup code for some CPU
@@ -890,6 +892,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL,
[PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC,
[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP,
+ [PERF_SAMPLE_BRANCH_CALL_SHIFT] = LBR_REL_CALL,
};
static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
@@ -905,6 +908,7 @@ static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] = LBR_REL_CALL | LBR_IND_CALL
| LBR_RETURN | LBR_CALL_STACK,
[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP,
+ [PERF_SAMPLE_BRANCH_CALL_SHIFT] = LBR_REL_CALL,
};
/* core */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
index 42169283448b..868e1194337f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -139,9 +139,6 @@ static int __init pt_pmu_hw_init(void)
long i;
attrs = NULL;
- ret = -ENODEV;
- if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_INTEL_PT))
- goto fail;
for (i = 0; i < PT_CPUID_LEAVES; i++) {
cpuid_count(20, i,
@@ -1130,6 +1127,10 @@ static __init int pt_init(void)
int ret, cpu, prior_warn = 0;
BUILD_BUG_ON(sizeof(struct topa) > PAGE_SIZE);
+
+ if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_INTEL_PT))
+ return -ENODEV;
+
get_online_cpus();
for_each_online_cpu(cpu) {
u64 ctl;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 560e5255b15e..61215a69b03d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -7,7 +7,8 @@ struct intel_uncore_type **uncore_pci_uncores = empty_uncore;
static bool pcidrv_registered;
struct pci_driver *uncore_pci_driver;
/* pci bus to socket mapping */
-int uncore_pcibus_to_physid[256] = { [0 ... 255] = -1, };
+DEFINE_RAW_SPINLOCK(pci2phy_map_lock);
+struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head);
struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
static DEFINE_RAW_SPINLOCK(uncore_box_lock);
@@ -20,6 +21,59 @@ static struct event_constraint uncore_constraint_fixed =
struct event_constraint uncore_constraint_empty =
EVENT_CONSTRAINT(0, 0, 0);
+int uncore_pcibus_to_physid(struct pci_bus *bus)
+{
+ struct pci2phy_map *map;
+ int phys_id = -1;
+
+ raw_spin_lock(&pci2phy_map_lock);
+ list_for_each_entry(map, &pci2phy_map_head, list) {
+ if (map->segment == pci_domain_nr(bus)) {
+ phys_id = map->pbus_to_physid[bus->number];
+ break;
+ }
+ }
+ raw_spin_unlock(&pci2phy_map_lock);
+
+ return phys_id;
+}
+
+struct pci2phy_map *__find_pci2phy_map(int segment)
+{
+ struct pci2phy_map *map, *alloc = NULL;
+ int i;
+
+ lockdep_assert_held(&pci2phy_map_lock);
+
+lookup:
+ list_for_each_entry(map, &pci2phy_map_head, list) {
+ if (map->segment == segment)
+ goto end;
+ }
+
+ if (!alloc) {
+ raw_spin_unlock(&pci2phy_map_lock);
+ alloc = kmalloc(sizeof(struct pci2phy_map), GFP_KERNEL);
+ raw_spin_lock(&pci2phy_map_lock);
+
+ if (!alloc)
+ return NULL;
+
+ goto lookup;
+ }
+
+ map = alloc;
+ alloc = NULL;
+ map->segment = segment;
+ for (i = 0; i < 256; i++)
+ map->pbus_to_physid[i] = -1;
+ list_add_tail(&map->list, &pci2phy_map_head);
+
+end:
+ kfree(alloc);
+ return map;
+}
+
ssize_t uncore_event_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
@@ -809,7 +863,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
int phys_id;
bool first_box = false;
- phys_id = uncore_pcibus_to_physid[pdev->bus->number];
+ phys_id = uncore_pcibus_to_physid(pdev->bus);
if (phys_id < 0)
return -ENODEV;
@@ -856,9 +910,10 @@ static void uncore_pci_remove(struct pci_dev *pdev)
{
struct intel_uncore_box *box = pci_get_drvdata(pdev);
struct intel_uncore_pmu *pmu;
- int i, cpu, phys_id = uncore_pcibus_to_physid[pdev->bus->number];
+ int i, cpu, phys_id;
bool last_box = false;
+ phys_id = uncore_pcibus_to_physid(pdev->bus);
box = pci_get_drvdata(pdev);
if (!box) {
for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 72c54c2e5b1a..2f0a4a98e16b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -117,6 +117,15 @@ struct uncore_event_desc {
const char *config;
};
+struct pci2phy_map {
+ struct list_head list;
+ int segment;
+ int pbus_to_physid[256];
+};
+
+int uncore_pcibus_to_physid(struct pci_bus *bus);
+struct pci2phy_map *__find_pci2phy_map(int segment);
+
ssize_t uncore_event_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf);
@@ -317,7 +326,8 @@ u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx);
extern struct intel_uncore_type **uncore_msr_uncores;
extern struct intel_uncore_type **uncore_pci_uncores;
extern struct pci_driver *uncore_pci_driver;
-extern int uncore_pcibus_to_physid[256];
+extern raw_spinlock_t pci2phy_map_lock;
+extern struct list_head pci2phy_map_head;
extern struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
extern struct event_constraint uncore_constraint_empty;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index f78574b3cb55..845256158a10 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -420,15 +420,25 @@ static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
static int snb_pci2phy_map_init(int devid)
{
struct pci_dev *dev = NULL;
- int bus;
+ struct pci2phy_map *map;
+ int bus, segment;
dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev);
if (!dev)
return -ENOTTY;
bus = dev->bus->number;
-
- uncore_pcibus_to_physid[bus] = 0;
+ segment = pci_domain_nr(dev->bus);
+
+ raw_spin_lock(&pci2phy_map_lock);
+ map = __find_pci2phy_map(segment);
+ if (!map) {
+ raw_spin_unlock(&pci2phy_map_lock);
+ pci_dev_put(dev);
+ return -ENOMEM;
+ }
+ map->pbus_to_physid[bus] = 0;
+ raw_spin_unlock(&pci2phy_map_lock);
pci_dev_put(dev);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index 694510a887dc..f0f4fcba252e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -1087,7 +1087,8 @@ static struct pci_driver snbep_uncore_pci_driver = {
static int snbep_pci2phy_map_init(int devid)
{
struct pci_dev *ubox_dev = NULL;
- int i, bus, nodeid;
+ int i, bus, nodeid, segment;
+ struct pci2phy_map *map;
int err = 0;
u32 config = 0;
@@ -1106,16 +1107,27 @@ static int snbep_pci2phy_map_init(int devid)
err = pci_read_config_dword(ubox_dev, 0x54, &config);
if (err)
break;
+
+ segment = pci_domain_nr(ubox_dev->bus);
+ raw_spin_lock(&pci2phy_map_lock);
+ map = __find_pci2phy_map(segment);
+ if (!map) {
+ raw_spin_unlock(&pci2phy_map_lock);
+ err = -ENOMEM;
+ break;
+ }
+
/*
* every three bits in the Node ID mapping register maps
* to a particular node.
*/
for (i = 0; i < 8; i++) {
if (nodeid == ((config >> (3 * i)) & 0x7)) {
- uncore_pcibus_to_physid[bus] = i;
+ map->pbus_to_physid[bus] = i;
break;
}
}
+ raw_spin_unlock(&pci2phy_map_lock);
}
if (!err) {
@@ -1123,13 +1135,17 @@ static int snbep_pci2phy_map_init(int devid)
* For PCI bus with no UBOX device, find the next bus
* that has UBOX device and use its mapping.
*/
- i = -1;
- for (bus = 255; bus >= 0; bus--) {
- if (uncore_pcibus_to_physid[bus] >= 0)
- i = uncore_pcibus_to_physid[bus];
- else
- uncore_pcibus_to_physid[bus] = i;
+ raw_spin_lock(&pci2phy_map_lock);
+ list_for_each_entry(map, &pci2phy_map_head, list) {
+ i = -1;
+ for (bus = 255; bus >= 0; bus--) {
+ if (map->pbus_to_physid[bus] >= 0)
+ i = map->pbus_to_physid[bus];
+ else
+ map->pbus_to_physid[bus] = i;
+ }
}
+ raw_spin_unlock(&pci2phy_map_lock);
}
pci_dev_put(ubox_dev);
@@ -2444,7 +2460,7 @@ static struct intel_uncore_type *bdx_pci_uncores[] = {
NULL,
};
-static DEFINE_PCI_DEVICE_TABLE(bdx_uncore_pci_ids) = {
+static const struct pci_device_id bdx_uncore_pci_ids[] = {
{ /* Home Agent 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f30),
.driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 0),
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index c3f7602cd038..c7c4d9c51e99 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -168,21 +168,20 @@ static void cyc2ns_write_end(int cpu, struct cyc2ns_data *data)
* ns = cycles * cyc2ns_scale / SC
*
* And since SC is a constant power of two, we can convert the div
- * into a shift.
+ * into a shift. The larger SC is, the more accurate the conversion, but
+ * cyc2ns_scale needs to be a 32-bit value so that 32-bit multiplication
+ * (64-bit result) can be used.
*
- * We can use khz divisor instead of mhz to keep a better precision, since
- * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
+ * We can use khz divisor instead of mhz to keep a better precision.
* (mathieu.desnoyers@polymtl.ca)
*
* -johnstul@us.ibm.com "math is hard, lets go shopping!"
*/
-#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
-
static void cyc2ns_data_init(struct cyc2ns_data *data)
{
data->cyc2ns_mul = 0;
- data->cyc2ns_shift = CYC2NS_SCALE_FACTOR;
+ data->cyc2ns_shift = 0;
data->cyc2ns_offset = 0;
data->__count = 0;
}
@@ -216,14 +215,14 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
if (likely(data == tail)) {
ns = data->cyc2ns_offset;
- ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);
+ ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift);
} else {
data->__count++;
barrier();
ns = data->cyc2ns_offset;
- ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);
+ ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift);
barrier();
@@ -257,12 +256,22 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
* time function is continuous; see the comment near struct
* cyc2ns_data.
*/
- data->cyc2ns_mul =
- DIV_ROUND_CLOSEST(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR,
- cpu_khz);
- data->cyc2ns_shift = CYC2NS_SCALE_FACTOR;
+ clocks_calc_mult_shift(&data->cyc2ns_mul, &data->cyc2ns_shift, cpu_khz,
+ NSEC_PER_MSEC, 0);
+
+ /*
+ * cyc2ns_shift is exported via arch_perf_update_userpage() where it is
+ * not expected to be greater than 31 due to the original published
+ * conversion algorithm shifting a 32-bit value (now specifies a 64-bit
+ * value) - refer perf_event_mmap_page documentation in perf_event.h.
+ */
+ if (data->cyc2ns_shift == 32) {
+ data->cyc2ns_shift = 31;
+ data->cyc2ns_mul >>= 1;
+ }
+
data->cyc2ns_offset = ns_now -
- mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);
+ mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, data->cyc2ns_shift);
cyc2ns_write_end(cpu, data);
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 816488c0b97e..d388de72eaca 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -353,8 +353,12 @@ AVXcode: 1
17: vmovhps Mq,Vq (v1) | vmovhpd Mq,Vq (66),(v1)
18: Grp16 (1A)
19:
-1a: BNDCL Ev,Gv | BNDCU Ev,Gv | BNDMOV Gv,Ev | BNDLDX Gv,Ev,Gv
-1b: BNDCN Ev,Gv | BNDMOV Ev,Gv | BNDMK Gv,Ev | BNDSTX Ev,GV,Gv
+# Intel SDM opcode map does not list MPX instructions. For now using Gv for
+# bnd registers and Ev for everything else is OK because the instruction
+# decoder does not use the information except as an indication that there is
+# a ModR/M byte.
+1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev
+1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv
1c:
1d:
1e:
@@ -732,6 +736,12 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
# 0x0f 0x38 0xc0-0xff
+c8: sha1nexte Vdq,Wdq
+c9: sha1msg1 Vdq,Wdq
+ca: sha1msg2 Vdq,Wdq
+cb: sha256rnds2 Vdq,Wdq
+cc: sha256msg1 Vdq,Wdq
+cd: sha256msg2 Vdq,Wdq
db: VAESIMC Vdq,Wdq (66),(v1)
dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
@@ -790,6 +800,7 @@ AVXcode: 3
61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
+cc: sha1rnds4 Vdq,Wdq,Ib
df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
f0: RORX Gy,Ey,Ib (F2),(v)
EndTable
@@ -874,7 +885,7 @@ GrpTable: Grp7
2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B)
3: LIDT Ms
4: SMSW Mw/Rv
-5:
+5: rdpkru (110),(11B) | wrpkru (111),(11B)
6: LMSW Ew
7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B)
EndTable
@@ -888,6 +899,9 @@ EndTable
GrpTable: Grp9
1: CMPXCHG8B/16B Mq/Mdq
+3: xrstors
+4: xsavec
+5: xsaves
6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B)
EndTable
@@ -932,8 +946,8 @@ GrpTable: Grp15
3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
4: XSAVE
5: XRSTOR | lfence (11B)
-6: XSAVEOPT | mfence (11B)
-7: clflush | sfence (11B)
+6: XSAVEOPT | clwb (66) | mfence (11B)
+7: clflush | clflushopt (66) | sfence (11B) | pcommit (66),(11B)
EndTable
GrpTable: Grp16
generated by cgit v1.2.3 (git 2.39.1) at 2024-10-04 05:19:38 +0000