aboutsummaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/include/asm/traps.h7
-rw-r--r--arch/arm64/include/asm/traps.h7
-rw-r--r--arch/cris/arch-v32/mach-a3/arbiter.c4
-rw-r--r--arch/cris/arch-v32/mach-fs/arbiter.c4
-rw-r--r--arch/cris/kernel/traps.c6
-rw-r--r--arch/h8300/include/asm/traps.h6
-rw-r--r--arch/powerpc/perf/core-book3s.c3
-rw-r--r--arch/x86/entry/entry_64.S9
-rw-r--r--arch/x86/events/amd/uncore.c21
-rw-r--r--arch/x86/events/core.c57
-rw-r--r--arch/x86/events/intel/bts.c2
-rw-r--r--arch/x86/events/intel/core.c107
-rw-r--r--arch/x86/events/intel/ds.c58
-rw-r--r--arch/x86/events/intel/lbr.c52
-rw-r--r--arch/x86/events/intel/pt.c5
-rw-r--r--arch/x86/events/perf_event.h10
-rw-r--r--arch/x86/include/asm/cpufeatures.h2
-rw-r--r--arch/x86/kernel/kprobes/opt.c9
-rw-r--r--arch/x86/kernel/unwind_frame.c2
-rw-r--r--arch/xtensa/kernel/setup.c6
20 files changed, 283 insertions, 94 deletions
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
index f555bb3664dc..683d9230984a 100644
--- a/arch/arm/include/asm/traps.h
+++ b/arch/arm/include/asm/traps.h
@@ -18,7 +18,6 @@ struct undef_hook {
void register_undef_hook(struct undef_hook *hook);
void unregister_undef_hook(struct undef_hook *hook);
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static inline int __in_irqentry_text(unsigned long ptr)
{
extern char __irqentry_text_start[];
@@ -27,12 +26,6 @@ static inline int __in_irqentry_text(unsigned long ptr)
return ptr >= (unsigned long)&__irqentry_text_start &&
ptr < (unsigned long)&__irqentry_text_end;
}
-#else
-static inline int __in_irqentry_text(unsigned long ptr)
-{
- return 0;
-}
-#endif
static inline int in_exception_text(unsigned long ptr)
{
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 02e9035b0685..47a9066f7c86 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -37,18 +37,11 @@ void unregister_undef_hook(struct undef_hook *hook);
void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr);
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static inline int __in_irqentry_text(unsigned long ptr)
{
return ptr >= (unsigned long)&__irqentry_text_start &&
ptr < (unsigned long)&__irqentry_text_end;
}
-#else
-static inline int __in_irqentry_text(unsigned long ptr)
-{
- return 0;
-}
-#endif
static inline int in_exception_text(unsigned long ptr)
{
diff --git a/arch/cris/arch-v32/mach-a3/arbiter.c b/arch/cris/arch-v32/mach-a3/arbiter.c
index ab5c421a4de8..735a9b0abdb8 100644
--- a/arch/cris/arch-v32/mach-a3/arbiter.c
+++ b/arch/cris/arch-v32/mach-a3/arbiter.c
@@ -227,7 +227,7 @@ static void crisv32_arbiter_config(int arbiter, int region, int unused_slots)
}
}
-extern char _stext, _etext;
+extern char _stext[], _etext[];
static void crisv32_arbiter_init(void)
{
@@ -265,7 +265,7 @@ static void crisv32_arbiter_init(void)
#ifndef CONFIG_ETRAX_KGDB
/* Global watch for writes to kernel text segment. */
- crisv32_arbiter_watch(virt_to_phys(&_stext), &_etext - &_stext,
+ crisv32_arbiter_watch(virt_to_phys(_stext), _etext - _stext,
MARB_CLIENTS(arbiter_all_clients, arbiter_bar_all_clients),
arbiter_all_write, NULL);
#endif
diff --git a/arch/cris/arch-v32/mach-fs/arbiter.c b/arch/cris/arch-v32/mach-fs/arbiter.c
index c97f4d8120f9..047c70bdbb23 100644
--- a/arch/cris/arch-v32/mach-fs/arbiter.c
+++ b/arch/cris/arch-v32/mach-fs/arbiter.c
@@ -158,7 +158,7 @@ static void crisv32_arbiter_config(int region, int unused_slots)
}
}
-extern char _stext, _etext;
+extern char _stext[], _etext[];
static void crisv32_arbiter_init(void)
{
@@ -190,7 +190,7 @@ static void crisv32_arbiter_init(void)
#ifndef CONFIG_ETRAX_KGDB
/* Global watch for writes to kernel text segment. */
- crisv32_arbiter_watch(virt_to_phys(&_stext), &_etext - &_stext,
+ crisv32_arbiter_watch(virt_to_phys(_stext), _etext - _stext,
arbiter_all_clients, arbiter_all_write, NULL);
#endif
}
diff --git a/arch/cris/kernel/traps.c b/arch/cris/kernel/traps.c
index a01636a12a6e..d98131c45bb5 100644
--- a/arch/cris/kernel/traps.c
+++ b/arch/cris/kernel/traps.c
@@ -42,7 +42,7 @@ void (*nmi_handler)(struct pt_regs *);
void show_trace(unsigned long *stack)
{
unsigned long addr, module_start, module_end;
- extern char _stext, _etext;
+ extern char _stext[], _etext[];
int i;
pr_err("\nCall Trace: ");
@@ -69,8 +69,8 @@ void show_trace(unsigned long *stack)
* down the cause of the crash will be able to figure
* out the call path that was taken.
*/
- if (((addr >= (unsigned long)&_stext) &&
- (addr <= (unsigned long)&_etext)) ||
+ if (((addr >= (unsigned long)_stext) &&
+ (addr <= (unsigned long)_etext)) ||
((addr >= module_start) && (addr <= module_end))) {
#ifdef CONFIG_KALLSYMS
print_ip_sym(addr);
diff --git a/arch/h8300/include/asm/traps.h b/arch/h8300/include/asm/traps.h
index 15e701130b27..1c5a30ec2df8 100644
--- a/arch/h8300/include/asm/traps.h
+++ b/arch/h8300/include/asm/traps.h
@@ -33,9 +33,9 @@ extern unsigned long *_interrupt_redirect_table;
#define TRAP2_VEC 10
#define TRAP3_VEC 11
-extern char _start, _etext;
+extern char _start[], _etext[];
#define check_kernel_text(addr) \
- ((addr >= (unsigned long)(&_start)) && \
- (addr < (unsigned long)(&_etext)) && !(addr & 1))
+ ((addr >= (unsigned long)(_start)) && \
+ (addr < (unsigned long)(_etext)) && !(addr & 1))
#endif /* _H8300_TRAPS_H */
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 6c2d4168daec..2e3eb7431571 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2039,7 +2039,8 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
perf_sample_data_init(&data, ~0ULL, event->hw.last_period);
- if (event->attr.sample_type & PERF_SAMPLE_ADDR)
+ if (event->attr.sample_type &
+ (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
perf_get_data_addr(regs, &data.addr);
if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) {
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 6d078b89a5e8..ce8dc33dd640 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -675,13 +675,8 @@ apicinterrupt3 \num trace(\sym) smp_trace(\sym)
#endif
/* Make sure APIC interrupt handlers end up in the irqentry section: */
-#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
-# define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax"
-# define POP_SECTION_IRQENTRY .popsection
-#else
-# define PUSH_SECTION_IRQENTRY
-# define POP_SECTION_IRQENTRY
-#endif
+#define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax"
+#define POP_SECTION_IRQENTRY .popsection
.macro apicinterrupt num sym do_sym
PUSH_SECTION_IRQENTRY
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index ad44af0dd667..f5cbbba99283 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -400,11 +400,24 @@ static int amd_uncore_cpu_starting(unsigned int cpu)
if (amd_uncore_llc) {
unsigned int apicid = cpu_data(cpu).apicid;
- unsigned int nshared;
+ unsigned int nshared, subleaf, prev_eax = 0;
uncore = *per_cpu_ptr(amd_uncore_llc, cpu);
- cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx);
- nshared = ((eax >> 14) & 0xfff) + 1;
+ /*
+ * Iterate over Cache Topology Definition leaves until no
+ * more cache descriptions are available.
+ */
+ for (subleaf = 0; subleaf < 5; subleaf++) {
+ cpuid_count(0x8000001d, subleaf, &eax, &ebx, &ecx, &edx);
+
+ /* EAX[0:4] gives type of cache */
+ if (!(eax & 0x1f))
+ break;
+
+ prev_eax = eax;
+ }
+ nshared = ((prev_eax >> 14) & 0xfff) + 1;
+
uncore->id = apicid - (apicid % nshared);
uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc);
@@ -555,7 +568,7 @@ static int __init amd_uncore_init(void)
ret = 0;
}
- if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) {
+ if (boot_cpu_has(X86_FEATURE_PERFCTR_LLC)) {
amd_uncore_llc = alloc_percpu(struct amd_uncore *);
if (!amd_uncore_llc) {
ret = -ENOMEM;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 939050169d12..80534d3c2480 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -487,22 +487,28 @@ static inline int precise_br_compat(struct perf_event *event)
return m == b;
}
-int x86_pmu_hw_config(struct perf_event *event)
+int x86_pmu_max_precise(void)
{
- if (event->attr.precise_ip) {
- int precise = 0;
+ int precise = 0;
+
+ /* Support for constant skid */
+ if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) {
+ precise++;
- /* Support for constant skid */
- if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) {
+ /* Support for IP fixup */
+ if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2)
precise++;
- /* Support for IP fixup */
- if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2)
- precise++;
+ if (x86_pmu.pebs_prec_dist)
+ precise++;
+ }
+ return precise;
+}
- if (x86_pmu.pebs_prec_dist)
- precise++;
- }
+int x86_pmu_hw_config(struct perf_event *event)
+{
+ if (event->attr.precise_ip) {
+ int precise = x86_pmu_max_precise();
if (event->attr.precise_ip > precise)
return -EOPNOTSUPP;
@@ -1751,6 +1757,7 @@ ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event)
}
static struct attribute_group x86_pmu_attr_group;
+static struct attribute_group x86_pmu_caps_group;
static int __init init_hw_perf_events(void)
{
@@ -1799,6 +1806,14 @@ static int __init init_hw_perf_events(void)
x86_pmu_format_group.attrs = x86_pmu.format_attrs;
+ if (x86_pmu.caps_attrs) {
+ struct attribute **tmp;
+
+ tmp = merge_attr(x86_pmu_caps_group.attrs, x86_pmu.caps_attrs);
+ if (!WARN_ON(!tmp))
+ x86_pmu_caps_group.attrs = tmp;
+ }
+
if (x86_pmu.event_attrs)
x86_pmu_events_group.attrs = x86_pmu.event_attrs;
@@ -2213,10 +2228,30 @@ static struct attribute_group x86_pmu_attr_group = {
.attrs = x86_pmu_attrs,
};
+static ssize_t max_precise_show(struct device *cdev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%d\n", x86_pmu_max_precise());
+}
+
+static DEVICE_ATTR_RO(max_precise);
+
+static struct attribute *x86_pmu_caps_attrs[] = {
+ &dev_attr_max_precise.attr,
+ NULL
+};
+
+static struct attribute_group x86_pmu_caps_group = {
+ .name = "caps",
+ .attrs = x86_pmu_caps_attrs,
+};
+
static const struct attribute_group *x86_pmu_attr_groups[] = {
&x86_pmu_attr_group,
&x86_pmu_format_group,
&x86_pmu_events_group,
+ &x86_pmu_caps_group,
NULL,
};
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index ddd8d3516bfc..16076eb34699 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -268,7 +268,7 @@ static void bts_event_start(struct perf_event *event, int flags)
bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum;
bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold;
- event->hw.itrace_started = 1;
+ perf_event_itrace_started(event);
event->hw.state = 0;
__bts_event_start(event);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 98b0f0729527..829e89cfcee2 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3415,12 +3415,26 @@ static struct attribute *intel_arch3_formats_attr[] = {
&format_attr_any.attr,
&format_attr_inv.attr,
&format_attr_cmask.attr,
+ NULL,
+};
+
+static struct attribute *hsw_format_attr[] = {
&format_attr_in_tx.attr,
&format_attr_in_tx_cp.attr,
+ &format_attr_offcore_rsp.attr,
+ &format_attr_ldlat.attr,
+ NULL
+};
- &format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */
- &format_attr_ldlat.attr, /* PEBS load latency */
- NULL,
+static struct attribute *nhm_format_attr[] = {
+ &format_attr_offcore_rsp.attr,
+ &format_attr_ldlat.attr,
+ NULL
+};
+
+static struct attribute *slm_format_attr[] = {
+ &format_attr_offcore_rsp.attr,
+ NULL
};
static struct attribute *skl_format_attr[] = {
@@ -3781,6 +3795,36 @@ done:
static DEVICE_ATTR_RW(freeze_on_smi);
+static ssize_t branches_show(struct device *cdev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%d\n", x86_pmu.lbr_nr);
+}
+
+static DEVICE_ATTR_RO(branches);
+
+static struct attribute *lbr_attrs[] = {
+ &dev_attr_branches.attr,
+ NULL
+};
+
+static char pmu_name_str[30];
+
+static ssize_t pmu_name_show(struct device *cdev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%s\n", pmu_name_str);
+}
+
+static DEVICE_ATTR_RO(pmu_name);
+
+static struct attribute *intel_pmu_caps_attrs[] = {
+ &dev_attr_pmu_name.attr,
+ NULL
+};
+
static struct attribute *intel_pmu_attrs[] = {
&dev_attr_freeze_on_smi.attr,
NULL,
@@ -3795,6 +3839,8 @@ __init int intel_pmu_init(void)
unsigned int unused;
struct extra_reg *er;
int version, i;
+ struct attribute **extra_attr = NULL;
+ char *name;
if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
switch (boot_cpu_data.x86) {
@@ -3862,6 +3908,7 @@ __init int intel_pmu_init(void)
switch (boot_cpu_data.x86_model) {
case INTEL_FAM6_CORE_YONAH:
pr_cont("Core events, ");
+ name = "core";
break;
case INTEL_FAM6_CORE2_MEROM:
@@ -3877,6 +3924,7 @@ __init int intel_pmu_init(void)
x86_pmu.event_constraints = intel_core2_event_constraints;
x86_pmu.pebs_constraints = intel_core2_pebs_event_constraints;
pr_cont("Core2 events, ");
+ name = "core2";
break;
case INTEL_FAM6_NEHALEM:
@@ -3905,8 +3953,11 @@ __init int intel_pmu_init(void)
intel_pmu_pebs_data_source_nhm();
x86_add_quirk(intel_nehalem_quirk);
+ x86_pmu.pebs_no_tlb = 1;
+ extra_attr = nhm_format_attr;
pr_cont("Nehalem events, ");
+ name = "nehalem";
break;
case INTEL_FAM6_ATOM_PINEVIEW:
@@ -3923,6 +3974,7 @@ __init int intel_pmu_init(void)
x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints;
x86_pmu.pebs_aliases = intel_pebs_aliases_core2;
pr_cont("Atom events, ");
+ name = "bonnell";
break;
case INTEL_FAM6_ATOM_SILVERMONT1:
@@ -3940,7 +3992,9 @@ __init int intel_pmu_init(void)
x86_pmu.extra_regs = intel_slm_extra_regs;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.cpu_events = slm_events_attrs;
+ extra_attr = slm_format_attr;
pr_cont("Silvermont events, ");
+ name = "silvermont";
break;
case INTEL_FAM6_ATOM_GOLDMONT:
@@ -3965,7 +4019,9 @@ __init int intel_pmu_init(void)
x86_pmu.lbr_pt_coexist = true;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.cpu_events = glm_events_attrs;
+ extra_attr = slm_format_attr;
pr_cont("Goldmont events, ");
+ name = "goldmont";
break;
case INTEL_FAM6_ATOM_GEMINI_LAKE:
@@ -3991,7 +4047,9 @@ __init int intel_pmu_init(void)
x86_pmu.cpu_events = 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_WESTMERE:
@@ -4020,7 +4078,9 @@ __init int intel_pmu_init(void)
X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1);
intel_pmu_pebs_data_source_nhm();
+ extra_attr = nhm_format_attr;
pr_cont("Westmere events, ");
+ name = "westmere";
break;
case INTEL_FAM6_SANDYBRIDGE:
@@ -4056,7 +4116,10 @@ __init int intel_pmu_init(void)
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
X86_CONFIG(.event=0xb1, .umask=0x01, .inv=1, .cmask=1);
+ extra_attr = nhm_format_attr;
+
pr_cont("SandyBridge events, ");
+ name = "sandybridge";
break;
case INTEL_FAM6_IVYBRIDGE:
@@ -4090,7 +4153,10 @@ __init int intel_pmu_init(void)
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
+ extra_attr = nhm_format_attr;
+
pr_cont("IvyBridge events, ");
+ name = "ivybridge";
break;
@@ -4118,7 +4184,10 @@ __init int intel_pmu_init(void)
x86_pmu.get_event_constraints = hsw_get_event_constraints;
x86_pmu.cpu_events = hsw_events_attrs;
x86_pmu.lbr_double_abort = true;
+ extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+ hsw_format_attr : nhm_format_attr;
pr_cont("Haswell events, ");
+ name = "haswell";
break;
case INTEL_FAM6_BROADWELL_CORE:
@@ -4154,7 +4223,10 @@ __init int intel_pmu_init(void)
x86_pmu.get_event_constraints = hsw_get_event_constraints;
x86_pmu.cpu_events = hsw_events_attrs;
x86_pmu.limit_period = bdw_limit_period;
+ extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+ hsw_format_attr : nhm_format_attr;
pr_cont("Broadwell events, ");
+ name = "broadwell";
break;
case INTEL_FAM6_XEON_PHI_KNL:
@@ -4172,8 +4244,9 @@ __init int intel_pmu_init(void)
/* all extra regs are per-cpu when HT is on */
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
-
+ extra_attr = slm_format_attr;
pr_cont("Knights Landing/Mill events, ");
+ name = "knights-landing";
break;
case INTEL_FAM6_SKYLAKE_MOBILE:
@@ -4203,11 +4276,14 @@ __init int intel_pmu_init(void)
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
- x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr,
- skl_format_attr);
- WARN_ON(!x86_pmu.format_attrs);
+ extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+ hsw_format_attr : nhm_format_attr;
+ extra_attr = merge_attr(extra_attr, skl_format_attr);
x86_pmu.cpu_events = hsw_events_attrs;
+ intel_pmu_pebs_data_source_skl(
+ boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
pr_cont("Skylake events, ");
+ name = "skylake";
break;
default:
@@ -4215,6 +4291,7 @@ __init int intel_pmu_init(void)
case 1:
x86_pmu.event_constraints = intel_v1_event_constraints;
pr_cont("generic architected perfmon v1, ");
+ name = "generic_arch_v1";
break;
default:
/*
@@ -4222,10 +4299,19 @@ __init int intel_pmu_init(void)
*/
x86_pmu.event_constraints = intel_gen_event_constraints;
pr_cont("generic architected perfmon, ");
+ name = "generic_arch_v2+";
break;
}
}
+ 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);
+ }
+
if (x86_pmu.num_counters > INTEL_PMC_MAX_GENERIC) {
WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC);
@@ -4272,8 +4358,13 @@ __init int intel_pmu_init(void)
x86_pmu.lbr_nr = 0;
}
- if (x86_pmu.lbr_nr)
+ 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);
pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr);
+ }
+
/*
* Access extra MSR may cause #GP under certain circumstances.
* E.g. KVM doesn't support offcore event
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index a322fed5f8ed..e1965e5ff570 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -49,34 +49,47 @@ union intel_x86_pebs_dse {
*/
#define P(a, b) PERF_MEM_S(a, b)
#define OP_LH (P(OP, LOAD) | P(LVL, HIT))
+#define LEVEL(x) P(LVLNUM, x)
+#define REM P(REMOTE, REMOTE)
#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
/* Version for Sandy Bridge and later */
static u64 pebs_data_source[] = {
- P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
- OP_LH | P(LVL, L1) | P(SNOOP, NONE), /* 0x01: L1 local */
- OP_LH | P(LVL, LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */
- OP_LH | P(LVL, L2) | P(SNOOP, NONE), /* 0x03: L2 hit */
- OP_LH | P(LVL, L3) | P(SNOOP, NONE), /* 0x04: L3 hit */
- OP_LH | P(LVL, L3) | P(SNOOP, MISS), /* 0x05: L3 hit, snoop miss */
- OP_LH | P(LVL, L3) | P(SNOOP, HIT), /* 0x06: L3 hit, snoop hit */
- OP_LH | P(LVL, L3) | P(SNOOP, HITM), /* 0x07: L3 hit, snoop hitm */
- OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HIT), /* 0x08: L3 miss snoop hit */
- OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HITM), /* 0x09: L3 miss snoop hitm*/
- OP_LH | P(LVL, LOC_RAM) | P(SNOOP, HIT), /* 0x0a: L3 miss, shared */
- OP_LH | P(LVL, REM_RAM1) | P(SNOOP, HIT), /* 0x0b: L3 miss, shared */
- OP_LH | P(LVL, LOC_RAM) | SNOOP_NONE_MISS,/* 0x0c: L3 miss, excl */
- OP_LH | P(LVL, REM_RAM1) | SNOOP_NONE_MISS,/* 0x0d: L3 miss, excl */
- OP_LH | P(LVL, IO) | P(SNOOP, NONE), /* 0x0e: I/O */
- OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */
+ P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
+ OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x01: L1 local */
+ OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */
+ OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* 0x03: L2 hit */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* 0x04: L3 hit */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, MISS), /* 0x05: L3 hit, snoop miss */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT), /* 0x06: L3 hit, snoop hit */
+ OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* 0x07: L3 hit, snoop hitm */
+ OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HIT), /* 0x08: L3 miss snoop hit */
+ OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM), /* 0x09: L3 miss snoop hitm*/
+ OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, HIT), /* 0x0a: L3 miss, shared */
+ OP_LH | P(LVL, REM_RAM1) | REM | LEVEL(L3) | P(SNOOP, HIT), /* 0x0b: L3 miss, shared */
+ OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | SNOOP_NONE_MISS, /* 0x0c: L3 miss, excl */
+ OP_LH | P(LVL, REM_RAM1) | LEVEL(RAM) | REM | SNOOP_NONE_MISS, /* 0x0d: L3 miss, excl */
+ OP_LH | P(LVL, IO) | LEVEL(NA) | P(SNOOP, NONE), /* 0x0e: I/O */
+ OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE), /* 0x0f: uncached */
};
/* Patch up minor differences in the bits */
void __init intel_pmu_pebs_data_source_nhm(void)
{
- pebs_data_source[0x05] = OP_LH | P(LVL, L3) | P(SNOOP, HIT);
- pebs_data_source[0x06] = OP_LH | P(LVL, L3) | P(SNOOP, HITM);
- pebs_data_source[0x07] = OP_LH | P(LVL, L3) | P(SNOOP, HITM);
+ pebs_data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT);
+ pebs_data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
+ pebs_data_source[0x07] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
+}
+
+void __init intel_pmu_pebs_data_source_skl(bool pmem)
+{
+ u64 pmem_or_l4 = pmem ? LEVEL(PMEM) : LEVEL(L4);
+
+ pebs_data_source[0x08] = OP_LH | pmem_or_l4 | P(SNOOP, HIT);
+ pebs_data_source[0x09] = OP_LH | pmem_or_l4 | REM | P(SNOOP, HIT);
+ pebs_data_source[0x0b] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE);
+ pebs_data_source[0x0c] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOPX, FWD);
+ pebs_data_source[0x0d] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOP, HITM);
}
static u64 precise_store_data(u64 status)
@@ -149,8 +162,6 @@ static u64 load_latency_data(u64 status)
{
union intel_x86_pebs_dse dse;
u64 val;
- int model = boot_cpu_data.x86_model;
- int fam = boot_cpu_data.x86;
dse.val = status;
@@ -162,8 +173,7 @@ static u64 load_latency_data(u64 status)
/*
* Nehalem models do not support TLB, Lock infos
*/
- if (fam == 0x6 && (model == 26 || model == 30
- || model == 31 || model == 46)) {
+ if (x86_pmu.pebs_no_tlb) {
val |= P(TLB, NA) | P(LOCK, NA);
return val;
}
@@ -1175,7 +1185,7 @@ static void setup_pebs_sample_data(struct perf_event *event,
else
regs->flags &= ~PERF_EFLAGS_EXACT;
- if ((sample_type & PERF_SAMPLE_ADDR) &&
+ if ((sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) &&
x86_pmu.intel_cap.pebs_format >= 1)
data->addr = pebs->dla;
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 955457a30197..8a6bbacd17dc 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -109,6 +109,9 @@ enum {
X86_BR_ZERO_CALL = 1 << 15,/* zero length call */
X86_BR_CALL_STACK = 1 << 16,/* call stack */
X86_BR_IND_JMP = 1 << 17,/* indirect jump */
+
+ X86_BR_TYPE_SAVE = 1 << 18,/* indicate to save branch type */
+
};
#define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
@@ -514,6 +517,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
cpuc->lbr_entries[i].in_tx = 0;
cpuc->lbr_entries[i].abort = 0;
cpuc->lbr_entries[i].cycles = 0;
+ cpuc->lbr_entries[i].type = 0;
cpuc->lbr_entries[i].reserved = 0;
}
cpuc->lbr_stack.nr = i;
@@ -600,6 +604,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
cpuc->lbr_entries[out].in_tx = in_tx;
cpuc->lbr_entries[out].abort = abort;
cpuc->lbr_entries[out].cycles = cycles;
+ cpuc->lbr_entries[out].type = 0;
cpuc->lbr_entries[out].reserved = 0;
out++;
}
@@ -677,6 +682,10 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
if (br_type & PERF_SAMPLE_BRANCH_CALL)
mask |= X86_BR_CALL | X86_BR_ZERO_CALL;
+
+ if (br_type & PERF_SAMPLE_BRANCH_TYPE_SAVE)
+ mask |= X86_BR_TYPE_SAVE;
+
/*
* stash actual user request into reg, it may
* be used by fixup code for some CPU
@@ -930,6 +939,43 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
return ret;
}
+#define X86_BR_TYPE_MAP_MAX 16
+
+static int branch_map[X86_BR_TYPE_MAP_MAX] = {
+ PERF_BR_CALL, /* X86_BR_CALL */
+ PERF_BR_RET, /* X86_BR_RET */
+ PERF_BR_SYSCALL, /* X86_BR_SYSCALL */
+ PERF_BR_SYSRET, /* X86_BR_SYSRET */
+ PERF_BR_UNKNOWN, /* X86_BR_INT */
+ PERF_BR_UNKNOWN, /* X86_BR_IRET */
+ PERF_BR_COND, /* X86_BR_JCC */
+ PERF_BR_UNCOND, /* X86_BR_JMP */
+ PERF_BR_UNKNOWN, /* X86_BR_IRQ */
+ PERF_BR_IND_CALL, /* X86_BR_IND_CALL */
+ PERF_BR_UNKNOWN, /* X86_BR_ABORT */
+ PERF_BR_UNKNOWN, /* X86_BR_IN_TX */
+ PERF_BR_UNKNOWN, /* X86_BR_NO_TX */
+ PERF_BR_CALL, /* X86_BR_ZERO_CALL */
+ PERF_BR_UNKNOWN, /* X86_BR_CALL_STACK */
+ PERF_BR_IND, /* X86_BR_IND_JMP */
+};
+
+static int
+common_branch_type(int type)
+{
+ int i;
+
+ type >>= 2; /* skip X86_BR_USER and X86_BR_KERNEL */
+
+ if (type) {
+ i = __ffs(type);
+ if (i < X86_BR_TYPE_MAP_MAX)
+ return branch_map[i];
+ }
+
+ return PERF_BR_UNKNOWN;
+}
+
/*
* implement actual branch filter based on user demand.
* Hardware may not exactly satisfy that request, thus
@@ -946,7 +992,8 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
bool compress = false;
/* if sampling all branches, then nothing to filter */
- if ((br_sel & X86_BR_ALL) == X86_BR_ALL)
+ if (((br_sel & X86_BR_ALL) == X86_BR_ALL) &&
+ ((br_sel & X86_BR_TYPE_SAVE) != X86_BR_TYPE_SAVE))
return;
for (i = 0; i < cpuc->lbr_stack.nr; i++) {
@@ -967,6 +1014,9 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
cpuc->lbr_entries[i].from = 0;
compress = true;
}
+
+ if ((br_sel & X86_BR_TYPE_SAVE) == X86_BR_TYPE_SAVE)
+ cpuc->lbr_entries[i].type = common_branch_type(type);
}
if (!compress)
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index ae8324d65e61..81fd41d5a0d9 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -471,8 +471,9 @@ static void pt_config(struct perf_event *event)
struct pt *pt = this_cpu_ptr(&pt_ctx);
u64 reg;
- if (!event->hw.itrace_started) {
- event->hw.itrace_started = 1;
+ /* First round: clear STATUS, in particular the PSB byte counter. */
+ if (!event->hw.config) {
+ perf_event_itrace_started(event);
wrmsrl(MSR_IA32_RTIT_STATUS, 0);
}
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 476aec3a4cab..4196f81ec0e1 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -91,7 +91,7 @@ struct amd_nb {
(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
- PERF_SAMPLE_TRANSACTION)
+ PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR)
/*
* A debug store configuration.
@@ -558,6 +558,7 @@ struct x86_pmu {
int attr_rdpmc;
struct attribute **format_attrs;
struct attribute **event_attrs;
+ struct attribute **caps_attrs;
ssize_t (*events_sysfs_show)(char *page, u64 config);
struct attribute **cpu_events;
@@ -591,7 +592,8 @@ struct x86_pmu {
pebs :1,
pebs_active :1,
pebs_broken :1,
- pebs_prec_dist :1;
+ pebs_prec_dist :1,
+ pebs_no_tlb :1;
int pebs_record_size;
int pebs_buffer_size;
void (*drain_pebs)(struct pt_regs *regs);
@@ -741,6 +743,8 @@ int x86_reserve_hardware(void);
void x86_release_hardware(void);
+int x86_pmu_max_precise(void);
+
void hw_perf_lbr_event_destroy(struct perf_event *event);
int x86_setup_perfctr(struct perf_event *event);
@@ -947,6 +951,8 @@ void intel_pmu_lbr_init_knl(void);
void intel_pmu_pebs_data_source_nhm(void);
+void intel_pmu_pebs_data_source_skl(bool pmem);
+
int intel_pmu_setup_lbr_filter(struct perf_event *event);
void intel_pt_interrupt(void);
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 5a28e8e55e36..8ea315a11fe0 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -177,7 +177,7 @@
#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */
#define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */
#define X86_FEATURE_PTSC ( 6*32+27) /* performance time-stamp counter */
-#define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */
+#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */
#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
/*
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 69ea0bc1cfa3..4f98aad38237 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -39,6 +39,7 @@
#include <asm/insn.h>
#include <asm/debugreg.h>
#include <asm/set_memory.h>
+#include <asm/sections.h>
#include "common.h"
@@ -251,10 +252,12 @@ static int can_optimize(unsigned long paddr)
/*
* Do not optimize in the entry code due to the unstable
- * stack handling.
+ * stack handling and registers setup.
*/
- if ((paddr >= (unsigned long)__entry_text_start) &&
- (paddr < (unsigned long)__entry_text_end))
+ if (((paddr >= (unsigned long)__entry_text_start) &&
+ (paddr < (unsigned long)__entry_text_end)) ||
+ ((paddr >= (unsigned long)__irqentry_text_start) &&
+ (paddr < (unsigned long)__irqentry_text_end)))
return 0;
/* Check there is enough space for a relative jump. */
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index b9389d72b2f7..c29e5bc7e9c9 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -91,10 +91,8 @@ static bool in_entry_code(unsigned long ip)
if (addr >= __entry_text_start && addr < __entry_text_end)
return true;
-#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
if (addr >= __irqentry_text_start && addr < __irqentry_text_end)
return true;
-#endif
return false;
}
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 33bfa5270d95..08175df7a69e 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -273,8 +273,8 @@ void __init init_arch(bp_tag_t *bp_start)
* Initialize system. Setup memory and reserve regions.
*/
-extern char _end;
-extern char _stext;
+extern char _end[];
+extern char _stext[];
extern char _WindowVectors_text_start;
extern char _WindowVectors_text_end;
extern char _DebugInterruptVector_literal_start;
@@ -333,7 +333,7 @@ void __init setup_arch(char **cmdline_p)
}
#endif
- mem_reserve(__pa(&_stext), __pa(&_end));
+ mem_reserve(__pa(_stext), __pa(_end));
#ifdef CONFIG_VECTORS_OFFSET
mem_reserve(__pa(&_WindowVectors_text_start),
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-06 14:16:39 +0000