lkml.org 
[lkml]   [2018]   [Mar]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[GIT pull] perf updates for 4.16
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

Another set of perf updates:

- Fix a Skylake Uncore event format declaration

- Prevent perf pipe mode from crahsing which was caused by a missing
buffer allocation

- Make the perf top popup message which tells the user that it uses
fallback mode on older kernels a debug message.

- Make perf context rescheduling work correcctly

- Robustify the jump error drawing in perf browser mode so it does not try
to create references to NULL initialized offset entries

- Make trigger_on() robust so it does not enable the trigger before
everything is set up correctly to handle it

- Make perf auxtrace respect the --no-itrace option so it does not try to
queue AUX data for decoding.

- Prevent having different number of field separators in CVS output lines
when a counter is not supported.

- Make the perf kallsyms man page usage behave like it does for all other
perf commands.

- Synchronize the kernel headers


Thanks,

tglx

------------------>
Adrian Hunter (2):
perf auxtrace: Prevent decoding when --no-itrace
perf tools: Fix trigger class trigger_on()

Arnaldo Carvalho de Melo (3):
perf annotate browser: Be more robust when drawing jump arrows
tools headers: Sync copy of kvm UAPI headers
tools headers: Sync x86's cpufeatures.h

Ilya Pronin (1):
perf stat: Fix CVS output format for non-supported counters

Jiri Olsa (1):
perf record: Fix crash in pipe mode

Kan Liang (2):
perf/x86/intel/uncore: Fix Skylake UPI event format
perf top: Fix annoying fallback message on older kernels

Sangwon Hong (1):
perf kallsyms: Fix the usage on the man page

Song Liu (1):
perf/core: Fix ctx_event_type in ctx_resched()


arch/x86/events/intel/uncore_snbep.c | 2 +-
kernel/events/core.c | 4 +++-
tools/arch/x86/include/asm/cpufeatures.h | 1 +
tools/include/uapi/linux/kvm.h | 2 ++
tools/perf/Documentation/perf-kallsyms.txt | 2 +-
tools/perf/builtin-record.c | 9 +++++++++
tools/perf/builtin-stat.c | 2 +-
tools/perf/builtin-top.c | 2 +-
tools/perf/perf.h | 1 +
tools/perf/ui/browsers/annotate.c | 25 +++++++++++++++++++++++++
tools/perf/util/auxtrace.c | 15 +++++++++------
tools/perf/util/record.c | 8 ++++++--
tools/perf/util/trigger.h | 9 +++++----
13 files changed, 65 insertions(+), 17 deletions(-)

diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 6d8044ab1060..22ec65bc033a 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3606,7 +3606,7 @@ static struct intel_uncore_type skx_uncore_imc = {
};

static struct attribute *skx_upi_uncore_formats_attr[] = {
- &format_attr_event_ext.attr,
+ &format_attr_event.attr,
&format_attr_umask_ext.attr,
&format_attr_edge.attr,
&format_attr_inv.attr,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 96db9ae5d5af..4b838470fac4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2246,7 +2246,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
struct perf_event_context *task_ctx,
enum event_type_t event_type)
{
- enum event_type_t ctx_event_type = event_type & EVENT_ALL;
+ enum event_type_t ctx_event_type;
bool cpu_event = !!(event_type & EVENT_CPU);

/*
@@ -2256,6 +2256,8 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
if (event_type & EVENT_PINNED)
event_type |= EVENT_FLEXIBLE;

+ ctx_event_type = event_type & EVENT_ALL;
+
perf_pmu_disable(cpuctx->ctx.pmu);
if (task_ctx)
task_ctx_sched_out(cpuctx, task_ctx, event_type);
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 0dfe4d3f74e2..f41079da38c5 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -213,6 +213,7 @@
#define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */

#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
+#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */

/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 0fb5ef939732..7b26d4b0b052 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -761,6 +761,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07
#define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08
#define KVM_GET_EMULATED_CPUID _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
+#define KVM_GET_MSR_FEATURE_INDEX_LIST _IOWR(KVMIO, 0x0a, struct kvm_msr_list)

/*
* Extension capability list.
@@ -934,6 +935,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_S390_AIS_MIGRATION 150
#define KVM_CAP_PPC_GET_CPU_CHAR 151
#define KVM_CAP_S390_BPB 152
+#define KVM_CAP_GET_MSR_FEATURES 153

#ifdef KVM_CAP_IRQ_ROUTING

diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt
index 954ea9e21236..cf9f4040ea5c 100644
--- a/tools/perf/Documentation/perf-kallsyms.txt
+++ b/tools/perf/Documentation/perf-kallsyms.txt
@@ -8,7 +8,7 @@ perf-kallsyms - Searches running kernel for symbols
SYNOPSIS
--------
[verse]
-'perf kallsyms <options> symbol_name[,symbol_name...]'
+'perf kallsyms' [<options>] symbol_name[,symbol_name...]

DESCRIPTION
-----------
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index bf4ca749d1ac..a217623fec2e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -881,6 +881,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
}
}

+ /*
+ * If we have just single event and are sending data
+ * through pipe, we need to force the ids allocation,
+ * because we synthesize event name through the pipe
+ * and need the id for that.
+ */
+ if (data->is_pipe && rec->evlist->nr_entries == 1)
+ rec->opts.sample_id = true;
+
if (record__open(rec) != 0) {
err = -1;
goto out_child;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 98bf9d32f222..54a4c152edb3 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -917,7 +917,7 @@ static void print_metric_csv(void *ctx,
char buf[64], *vals, *ends;

if (unit == NULL || fmt == NULL) {
- fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep);
+ fprintf(out, "%s%s", csv_sep, csv_sep);
return;
}
snprintf(buf, sizeof(buf), fmt, val);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index b7c823ba8374..35ac016fcb98 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -991,7 +991,7 @@ static int perf_top_overwrite_fallback(struct perf_top *top,
evlist__for_each_entry(evlist, counter)
counter->attr.write_backward = false;
opts->overwrite = false;
- ui__warning("fall back to non-overwrite mode\n");
+ pr_debug2("fall back to non-overwrite mode\n");
return 1;
}

diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index cfe46236a5e5..57b9b342d533 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -61,6 +61,7 @@ struct record_opts {
bool tail_synthesize;
bool overwrite;
bool ignore_missing_thread;
+ bool sample_id;
unsigned int freq;
unsigned int mmap_pages;
unsigned int auxtrace_mmap_pages;
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 286427975112..fbf927cf775d 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -327,7 +327,32 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
if (!disasm_line__is_valid_jump(cursor, sym))
return;

+ /*
+ * This first was seen with a gcc function, _cpp_lex_token, that
+ * has the usual jumps:
+ *
+ * │1159e6c: ↓ jne 115aa32 <_cpp_lex_token@@Base+0xf92>
+ *
+ * I.e. jumps to a label inside that function (_cpp_lex_token), and
+ * those works, but also this kind:
+ *
+ * │1159e8b: ↓ jne c469be <cpp_named_operator2name@@Base+0xa72>
+ *
+ * I.e. jumps to another function, outside _cpp_lex_token, which
+ * are not being correctly handled generating as a side effect references
+ * to ab->offset[] entries that are set to NULL, so to make this code
+ * more robust, check that here.
+ *
+ * A proper fix for will be put in place, looking at the function
+ * name right after the '<' token and probably treating this like a
+ * 'call' instruction.
+ */
target = ab->offsets[cursor->ops.target.offset];
+ if (target == NULL) {
+ ui_helpline__printf("WARN: jump target inconsistency, press 'o', ab->offsets[%#x] = NULL\n",
+ cursor->ops.target.offset);
+ return;
+ }

bcursor = browser_line(&cursor->al);
btarget = browser_line(target);
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 9faf3b5367db..6470ea2aa25e 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -60,6 +60,12 @@
#include "sane_ctype.h"
#include "symbol/kallsyms.h"

+static bool auxtrace__dont_decode(struct perf_session *session)
+{
+ return !session->itrace_synth_opts ||
+ session->itrace_synth_opts->dont_decode;
+}
+
int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
struct auxtrace_mmap_params *mp,
void *userpg, int fd)
@@ -762,6 +768,9 @@ int auxtrace_queues__process_index(struct auxtrace_queues *queues,
size_t i;
int err;

+ if (auxtrace__dont_decode(session))
+ return 0;
+
list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) {
for (i = 0; i < auxtrace_index->nr; i++) {
ent = &auxtrace_index->entries[i];
@@ -892,12 +901,6 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
return err;
}

-static bool auxtrace__dont_decode(struct perf_session *session)
-{
- return !session->itrace_synth_opts ||
- session->itrace_synth_opts->dont_decode;
-}
-
int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_session *session)
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 1e97937b03a9..6f09e4962dad 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -137,6 +137,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
struct perf_evsel *evsel;
bool use_sample_identifier = false;
bool use_comm_exec;
+ bool sample_id = opts->sample_id;

/*
* Set the evsel leader links before we configure attributes,
@@ -163,8 +164,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
* match the id.
*/
use_sample_identifier = perf_can_sample_identifier();
- evlist__for_each_entry(evlist, evsel)
- perf_evsel__set_sample_id(evsel, use_sample_identifier);
+ sample_id = true;
} else if (evlist->nr_entries > 1) {
struct perf_evsel *first = perf_evlist__first(evlist);

@@ -174,6 +174,10 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
use_sample_identifier = perf_can_sample_identifier();
break;
}
+ sample_id = true;
+ }
+
+ if (sample_id) {
evlist__for_each_entry(evlist, evsel)
perf_evsel__set_sample_id(evsel, use_sample_identifier);
}
diff --git a/tools/perf/util/trigger.h b/tools/perf/util/trigger.h
index 370138e7e35c..88223bc7c82b 100644
--- a/tools/perf/util/trigger.h
+++ b/tools/perf/util/trigger.h
@@ -12,7 +12,7 @@
* States and transits:
*
*
- * OFF--(on)--> READY --(hit)--> HIT
+ * OFF--> ON --> READY --(hit)--> HIT
* ^ |
* | (ready)
* | |
@@ -27,8 +27,9 @@ struct trigger {
volatile enum {
TRIGGER_ERROR = -2,
TRIGGER_OFF = -1,
- TRIGGER_READY = 0,
- TRIGGER_HIT = 1,
+ TRIGGER_ON = 0,
+ TRIGGER_READY = 1,
+ TRIGGER_HIT = 2,
} state;
const char *name;
};
@@ -50,7 +51,7 @@ static inline bool trigger_is_error(struct trigger *t)
static inline void trigger_on(struct trigger *t)
{
TRIGGER_WARN_ONCE(t, TRIGGER_OFF);
- t->state = TRIGGER_READY;
+ t->state = TRIGGER_ON;
}

static inline void trigger_ready(struct trigger *t)
\
 
 \ /
  Last update: 2018-03-11 17:12    [W:0.042 / U:0.128 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site