* [GIT pull] perf fixes for 4.8
@ 2016-09-18 8:11 Thomas Gleixner
0 siblings, 0 replies; 4+ messages in thread
From: Thomas Gleixner @ 2016-09-18 8:11 UTC (permalink / raw)
To: Linus Torvalds; +Cc: LKML, Andrew Morton, Ingo Molnar, H. Peter Anvin
Linus,
please pull the latest perf-urgent-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus
A couple of small fixes to x86 perf drivers:
- Measure L2 for HW_CACHE* events on AMD
- Fix the address filter handling in the intel/pt driver
- Handle the BTS disabling at the proper place
Thanks,
tglx
------------------>
Alexander Shishkin (4):
perf/x86/intel: Don't disable "intel_bts" around "intel" event batching
perf/x86/intel/pt: Fix an off-by-one in address filter configuration
perf/x86/intel/pt: Fix kernel address filter's offset validation
perf/x86/intel/pt: Do validate the size of a kernel address filter
Matt Fleming (1):
perf/x86/amd: Make HW_CACHE_REFERENCES and HW_CACHE_MISSES measure L2
arch/x86/events/amd/core.c | 4 ++--
arch/x86/events/intel/core.c | 15 ++++++++-------
arch/x86/events/intel/pt.c | 18 ++++++++++++++----
arch/x86/kvm/pmu_amd.c | 4 ++--
4 files changed, 26 insertions(+), 15 deletions(-)
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index e07a22bb9308..f5f4b3fbbbc2 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -119,8 +119,8 @@ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
{
[PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
[PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
- [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0080,
- [PERF_COUNT_HW_CACHE_MISSES] = 0x0081,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x077e,
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
[PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2cbde2f449aa..4c9a79b9cd69 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1730,9 +1730,11 @@ static __initconst const u64 knl_hw_cache_extra_regs
* disabled state if called consecutively.
*
* During consecutive calls, the same disable value will be written to related
- * registers, so the PMU state remains unchanged. hw.state in
- * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive
- * calls.
+ * registers, so the PMU state remains unchanged.
+ *
+ * intel_bts events don't coexist with intel PMU's BTS events because of
+ * x86_add_exclusive(x86_lbr_exclusive_lbr); there's no need to keep them
+ * disabled around intel PMU's event batching etc, only inside the PMI handler.
*/
static void __intel_pmu_disable_all(void)
{
@@ -1742,8 +1744,6 @@ static void __intel_pmu_disable_all(void)
if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
intel_pmu_disable_bts();
- else
- intel_bts_disable_local();
intel_pmu_pebs_disable_all();
}
@@ -1771,8 +1771,7 @@ static void __intel_pmu_enable_all(int added, bool pmi)
return;
intel_pmu_enable_bts(event->hw.config);
- } else
- intel_bts_enable_local();
+ }
}
static void intel_pmu_enable_all(int added)
@@ -2073,6 +2072,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
*/
if (!x86_pmu.late_ack)
apic_write(APIC_LVTPC, APIC_DM_NMI);
+ intel_bts_disable_local();
__intel_pmu_disable_all();
handled = intel_pmu_drain_bts_buffer();
handled += intel_bts_interrupt();
@@ -2172,6 +2172,7 @@ done:
/* Only restore PMU state when it's active. See x86_pmu_disable(). */
if (cpuc->enabled)
__intel_pmu_enable_all(0, true);
+ intel_bts_enable_local();
/*
* Only unmask the NMI after the overflow counters
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 04bb5fb5a8d7..861a7d9cb60f 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1074,6 +1074,11 @@ static void pt_addr_filters_fini(struct perf_event *event)
event->hw.addr_filters = NULL;
}
+static inline bool valid_kernel_ip(unsigned long ip)
+{
+ return virt_addr_valid(ip) && kernel_ip(ip);
+}
+
static int pt_event_addr_filters_validate(struct list_head *filters)
{
struct perf_addr_filter *filter;
@@ -1081,11 +1086,16 @@ static int pt_event_addr_filters_validate(struct list_head *filters)
list_for_each_entry(filter, filters, entry) {
/* PT doesn't support single address triggers */
- if (!filter->range)
+ if (!filter->range || !filter->size)
return -EOPNOTSUPP;
- if (!filter->inode && !kernel_ip(filter->offset))
- return -EINVAL;
+ if (!filter->inode) {
+ if (!valid_kernel_ip(filter->offset))
+ return -EINVAL;
+
+ if (!valid_kernel_ip(filter->offset + filter->size))
+ return -EINVAL;
+ }
if (++range > pt_cap_get(PT_CAP_num_address_ranges))
return -EOPNOTSUPP;
@@ -1111,7 +1121,7 @@ static void pt_event_addr_filters_sync(struct perf_event *event)
} else {
/* apply the offset */
msr_a = filter->offset + offs[range];
- msr_b = filter->size + msr_a;
+ msr_b = filter->size + msr_a - 1;
}
filters->filter[range].msr_a = msr_a;
diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c
index 39b91127ef07..cd944435dfbd 100644
--- a/arch/x86/kvm/pmu_amd.c
+++ b/arch/x86/kvm/pmu_amd.c
@@ -23,8 +23,8 @@
static struct kvm_event_hw_type_mapping amd_event_mapping[] = {
[0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES },
[1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
- [2] = { 0x80, 0x00, PERF_COUNT_HW_CACHE_REFERENCES },
- [3] = { 0x81, 0x00, PERF_COUNT_HW_CACHE_MISSES },
+ [2] = { 0x7d, 0x07, PERF_COUNT_HW_CACHE_REFERENCES },
+ [3] = { 0x7e, 0x07, PERF_COUNT_HW_CACHE_MISSES },
[4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
[5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
[6] = { 0xd0, 0x00, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
^ permalink raw reply [flat|nested] 4+ messages in thread
* [GIT pull] perf fixes for 4.8
@ 2016-09-24 19:33 Thomas Gleixner
0 siblings, 0 replies; 4+ messages in thread
From: Thomas Gleixner @ 2016-09-24 19:33 UTC (permalink / raw)
To: Linus Torvalds; +Cc: LKML, Andrew Morton, Ingo Molnar, H. Peter Anvin
Linus,
please pull the latest perf-urgent-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus
Three fixlets for perf:
- Add a missing NULL pointer check in the intel BTS driver.
- Make BTS an exclusive PMU because BTS can only handle one event at a
time
- Ensure that exclusive events are limited to one PMU so that several
exclusive events can be scheduled on different PMU instances.
Thanks,
tglx
------------------>
Alexander Shishkin (2):
perf/x86/intel/bts: Make it an exclusive PMU
perf/core: Limit matching exclusive events to one PMU
Sebastian Andrzej Siewior (1):
perf/x86/intel/bts: Make sure debug store is valid
arch/x86/events/intel/bts.c | 5 +++--
kernel/events/core.c | 2 +-
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index bdcd6510992c..982c9e31daca 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -455,7 +455,7 @@ int intel_bts_interrupt(void)
* The only surefire way of knowing if this NMI is ours is by checking
* the write ptr against the PMI threshold.
*/
- if (ds->bts_index >= ds->bts_interrupt_threshold)
+ if (ds && (ds->bts_index >= ds->bts_interrupt_threshold))
handled = 1;
/*
@@ -584,7 +584,8 @@ static __init int bts_init(void)
if (!boot_cpu_has(X86_FEATURE_DTES64) || !x86_pmu.bts)
return -ENODEV;
- bts_pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE;
+ bts_pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE |
+ PERF_PMU_CAP_EXCLUSIVE;
bts_pmu.task_ctx_nr = perf_sw_context;
bts_pmu.event_init = bts_event_init;
bts_pmu.add = bts_event_add;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a54f2c2cdb20..fc9bb2225291 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3929,7 +3929,7 @@ static void exclusive_event_destroy(struct perf_event *event)
static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2)
{
- if ((e1->pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) &&
+ if ((e1->pmu == e2->pmu) &&
(e1->cpu == e2->cpu ||
e1->cpu == -1 ||
e2->cpu == -1))
^ permalink raw reply [flat|nested] 4+ messages in thread
* [GIT pull] perf fixes for 4.8
@ 2016-08-28 12:26 Thomas Gleixner
0 siblings, 0 replies; 4+ messages in thread
From: Thomas Gleixner @ 2016-08-28 12:26 UTC (permalink / raw)
To: Linus Torvalds; +Cc: LKML, Andrew Morton, Ingo Molnar, H. Peter Anvin
Linus,
please pull the latest perf-urgent-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus
A few fixes from the perf departement
- Prevent a imbalanced preemption disable in the events teardown code
- Prevent out of bound acces in perf userspace
- Make perf tools compile with UCLIBC again
- A fix for the userspace unwinder utility
Thanks,
tglx
------------------>
Arnaldo Carvalho de Melo (1):
perf evsel: Do not access outside hw cache name arrays
Milian Wolff (1):
perf unwind: Use addr_location::addr instead of ip for entries
Vineet Gupta (1):
tools lib: Reinstate strlcpy() header guard with __UCLIBC__
Will Deacon (1):
perf/core: Use this_cpu_ptr() when stopping AUX events
kernel/events/core.c | 2 +-
tools/include/linux/string.h | 6 +++++-
tools/perf/util/evsel.c | 6 +++---
tools/perf/util/unwind-libdw.c | 2 +-
tools/perf/util/unwind-libunwind-local.c | 2 +-
5 files changed, 11 insertions(+), 7 deletions(-)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5650f5317e0c..3cfabdf7b942 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6166,7 +6166,7 @@ static int __perf_pmu_output_stop(void *info)
{
struct perf_event *event = info;
struct pmu *pmu = event->pmu;
- struct perf_cpu_context *cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+ struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
struct remote_output ro = {
.rb = event->rb,
};
diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h
index b96879477311..f436d2420a18 100644
--- a/tools/include/linux/string.h
+++ b/tools/include/linux/string.h
@@ -8,7 +8,11 @@ void *memdup(const void *src, size_t len);
int strtobool(const char *s, bool *res);
-#ifdef __GLIBC__
+/*
+ * glibc based builds needs the extern while uClibc doesn't.
+ * However uClibc headers also define __GLIBC__ hence the hack below
+ */
+#if defined(__GLIBC__) && !defined(__UCLIBC__)
extern size_t strlcpy(char *dest, const char *src, size_t size);
#endif
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index d9b80ef881cd..21fd573106ed 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -507,17 +507,17 @@ static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size)
u8 op, result, type = (config >> 0) & 0xff;
const char *err = "unknown-ext-hardware-cache-type";
- if (type > PERF_COUNT_HW_CACHE_MAX)
+ if (type >= PERF_COUNT_HW_CACHE_MAX)
goto out_err;
op = (config >> 8) & 0xff;
err = "unknown-ext-hardware-cache-op";
- if (op > PERF_COUNT_HW_CACHE_OP_MAX)
+ if (op >= PERF_COUNT_HW_CACHE_OP_MAX)
goto out_err;
result = (config >> 16) & 0xff;
err = "unknown-ext-hardware-cache-result";
- if (result > PERF_COUNT_HW_CACHE_RESULT_MAX)
+ if (result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
goto out_err;
err = "invalid-cache";
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index cf5e250bc78e..783a53fb7a4e 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -66,7 +66,7 @@ static int entry(u64 ip, struct unwind_info *ui)
if (__report_module(&al, ip, ui))
return -1;
- e->ip = ip;
+ e->ip = al.addr;
e->map = al.map;
e->sym = al.sym;
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 97c0f8fc5561..20c2e5743903 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -542,7 +542,7 @@ static int entry(u64 ip, struct thread *thread,
thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
MAP__FUNCTION, ip, &al);
- e.ip = ip;
+ e.ip = al.addr;
e.map = al.map;
e.sym = al.sym;
^ permalink raw reply [flat|nested] 4+ messages in thread
* [GIT pull] perf fixes for 4.8
@ 2016-07-30 10:14 Thomas Gleixner
0 siblings, 0 replies; 4+ messages in thread
From: Thomas Gleixner @ 2016-07-30 10:14 UTC (permalink / raw)
To: Linus Torvalds; +Cc: LKML, Andrew Morton, Ingo Molnar, H. Peter Anvin
Linus,
please pull the latest perf-urgent-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus
This update contains:
- A fix for the bpf tools to use the new EM_BPF code
- A fix for the module parser of perf to retrieve the proper text start
address
- Add str_error_c to libapi to avoid linking against
tools/lib/str_error_r.o.
Thanks,
tglx
------------------>
Arnaldo Carvalho de Melo (1):
tools lib api: Add str_error_c to libapi
Song Shan Gong (1):
perf s390: Fix 'start' address of module's map
Wang Nan (1):
tools lib bpf: Use official ELF e_machine value
tools/lib/api/Build | 5 +++++
tools/lib/bpf/libbpf.c | 7 ++++++-
tools/perf/arch/s390/util/Build | 2 ++
tools/perf/arch/s390/util/machine.c | 19 +++++++++++++++++++
tools/perf/util/Build | 5 -----
tools/perf/util/machine.c | 8 ++++++++
tools/perf/util/machine.h | 1 +
tools/perf/util/python-ext-sources | 1 -
8 files changed, 41 insertions(+), 7 deletions(-)
create mode 100644 tools/perf/arch/s390/util/machine.c
diff --git a/tools/lib/api/Build b/tools/lib/api/Build
index 954c644f7ad9..6e2373db5598 100644
--- a/tools/lib/api/Build
+++ b/tools/lib/api/Build
@@ -2,3 +2,8 @@ libapi-y += fd/
libapi-y += fs/
libapi-y += cpu.o
libapi-y += debug.o
+libapi-y += str_error_r.o
+
+$(OUTPUT)str_error_r.o: ../str_error_r.c FORCE
+ $(call rule_mkdir)
+ $(call if_changed_dep,cc_o_c)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 32e6b6bc6f7d..b699aea9a025 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -37,6 +37,10 @@
#include "libbpf.h"
#include "bpf.h"
+#ifndef EM_BPF
+#define EM_BPF 247
+#endif
+
#define __printf(a, b) __attribute__((format(printf, a, b)))
__printf(1, 2)
@@ -439,7 +443,8 @@ static int bpf_object__elf_init(struct bpf_object *obj)
}
ep = &obj->efile.ehdr;
- if ((ep->e_type != ET_REL) || (ep->e_machine != 0)) {
+ /* Old LLVM set e_machine to EM_NONE */
+ if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) {
pr_warning("%s is not an eBPF object file\n",
obj->path);
err = -LIBBPF_ERRNO__FORMAT;
diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build
index 8a61372bb47a..5bd7b9260cc0 100644
--- a/tools/perf/arch/s390/util/Build
+++ b/tools/perf/arch/s390/util/Build
@@ -2,3 +2,5 @@ libperf-y += header.o
libperf-y += kvm-stat.o
libperf-$(CONFIG_DWARF) += dwarf-regs.o
+
+libperf-y += machine.o
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
new file mode 100644
index 000000000000..b9a95a1a8e69
--- /dev/null
+++ b/tools/perf/arch/s390/util/machine.c
@@ -0,0 +1,19 @@
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include "util.h"
+#include "machine.h"
+#include "api/fs/fs.h"
+
+int arch__fix_module_text_start(u64 *start, const char *name)
+{
+ char path[PATH_MAX];
+
+ snprintf(path, PATH_MAX, "module/%.*s/sections/.text",
+ (int)strlen(name) - 2, name + 1);
+
+ if (sysfs__read_ull(path, (unsigned long long *)start) < 0)
+ return -1;
+
+ return 0;
+}
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 2fa7d8b69873..91c5f6e1af59 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -70,7 +70,6 @@ libperf-y += stat.o
libperf-y += stat-shadow.o
libperf-y += record.o
libperf-y += srcline.o
-libperf-y += str_error_r.o
libperf-y += data.o
libperf-y += tsc.o
libperf-y += cloexec.o
@@ -176,10 +175,6 @@ $(OUTPUT)util/libstring.o: ../lib/string.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
-$(OUTPUT)util/str_error_r.o: ../lib/str_error_r.c FORCE
- $(call rule_mkdir)
- $(call if_changed_dep,cc_o_c)
-
$(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index bc2cdbd09a25..cb6388dbdd98 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1093,12 +1093,20 @@ static int machine__set_modules_path(struct machine *machine)
return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
}
+int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
+ const char *name __maybe_unused)
+{
+ return 0;
+}
static int machine__create_module(void *arg, const char *name, u64 start)
{
struct machine *machine = arg;
struct map *map;
+ if (arch__fix_module_text_start(&start, name) < 0)
+ return -1;
+
map = machine__findnew_module_map(machine, start, name);
if (map == NULL)
return -1;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 41ac9cfd416b..20739f746bc4 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -216,6 +216,7 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
struct map *machine__findnew_module_map(struct machine *machine, u64 start,
const char *filename);
+int arch__fix_module_text_start(u64 *start, const char *name);
int __machine__load_kallsyms(struct machine *machine, const char *filename,
enum map_type type, bool no_kcore, symbol_filter_t filter);
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 5065ec98049c..b7d4f4aeee61 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -13,7 +13,6 @@ util/cpumap.c
../lib/bitmap.c
../lib/find_bit.c
../lib/hweight.c
-../lib/str_error_r.c
../lib/vsprintf.c
util/thread_map.c
util/util.c
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2016-09-24 19:35 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2016-09-18 8:11 [GIT pull] perf fixes for 4.8 Thomas Gleixner
-- strict thread matches above, loose matches on Subject: below --
2016-09-24 19:33 Thomas Gleixner
2016-08-28 12:26 Thomas Gleixner
2016-07-30 10:14 Thomas Gleixner
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®