Merge tag 'perf-core-for-mingo-4.17-20180215' of...

Merge tag 'perf-core-for-mingo-4.17-20180215' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/core fixes from Arnaldo Carvalho de Melo:

- perf_mmap overwrite mode fixes/overhaul, prep work to get 'perf top'
  using it, making it bearable to use it in large core count systems
  such as Knights Landing/Mill Intel systems (Kan Liang)

- s/390 now uses syscall.tbl, just like x86-64 to generate the syscall
  table id -> string tables used by 'perf trace' (Hendrik Brueckner)

- Use strtoull() instead of home grown function (Andy Shevchenko)

- Synchronize kernel ABI headers, v4.16-rc1 (Ingo Molnar)

- Document missing 'perf data --force' option (Sangwon Hong)

- Add perf vendor JSON metrics for ARM Cortex-A53 Processor (William Cohen)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

tools/arch/powerpc/include/uapi/asm/kvm.h

@@ -632,6 +632,8 @@ struct kvm_ppc_cpu_char {
 #define KVM_REG_PPC_TIDR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc)
 #define KVM_REG_PPC_PSSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
 
+#define KVM_REG_PPC_DEC_EXPIRY	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
  */

tools/arch/x86/include/asm/cpufeatures.h

@@ -210,6 +210,7 @@
 
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* "" Fill RSB on context switches */
+#define X86_FEATURE_SEV			( 7*32+20) /* AMD Secure Encrypted Virtualization */
 
 #define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
 

tools/include/uapi/drm/i915_drm.h

@@ -86,6 +86,62 @@ enum i915_mocs_table_index {
 	I915_MOCS_CACHED,
 };
 
+/*
+ * Different engines serve different roles, and there may be more than one
+ * engine serving each role. enum drm_i915_gem_engine_class provides a
+ * classification of the role of the engine, which may be used when requesting
+ * operations to be performed on a certain subset of engines, or for providing
+ * information about that group.
+ */
+enum drm_i915_gem_engine_class {
+	I915_ENGINE_CLASS_RENDER	= 0,
+	I915_ENGINE_CLASS_COPY		= 1,
+	I915_ENGINE_CLASS_VIDEO		= 2,
+	I915_ENGINE_CLASS_VIDEO_ENHANCE	= 3,
+
+	I915_ENGINE_CLASS_INVALID	= -1
+};
+
+/**
+ * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915
+ *
+ */
+
+enum drm_i915_pmu_engine_sample {
+	I915_SAMPLE_BUSY = 0,
+	I915_SAMPLE_WAIT = 1,
+	I915_SAMPLE_SEMA = 2
+};
+
+#define I915_PMU_SAMPLE_BITS (4)
+#define I915_PMU_SAMPLE_MASK (0xf)
+#define I915_PMU_SAMPLE_INSTANCE_BITS (8)
+#define I915_PMU_CLASS_SHIFT \
+	(I915_PMU_SAMPLE_BITS + I915_PMU_SAMPLE_INSTANCE_BITS)
+
+#define __I915_PMU_ENGINE(class, instance, sample) \
+	((class) << I915_PMU_CLASS_SHIFT | \
+	(instance) << I915_PMU_SAMPLE_BITS | \
+	(sample))
+
+#define I915_PMU_ENGINE_BUSY(class, instance) \
+	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_BUSY)
+
+#define I915_PMU_ENGINE_WAIT(class, instance) \
+	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_WAIT)
+
+#define I915_PMU_ENGINE_SEMA(class, instance) \
+	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA)
+
+#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x))
+
+#define I915_PMU_ACTUAL_FREQUENCY	__I915_PMU_OTHER(0)
+#define I915_PMU_REQUESTED_FREQUENCY	__I915_PMU_OTHER(1)
+#define I915_PMU_INTERRUPTS		__I915_PMU_OTHER(2)
+#define I915_PMU_RC6_RESIDENCY		__I915_PMU_OTHER(3)
+
+#define I915_PMU_LAST I915_PMU_RC6_RESIDENCY
+
 /* Each region is a minimum of 16k, and there are at most 255 of them.
  */
 #define I915_NR_TEX_REGIONS 255	/* table size 2k - maximum due to use
@@ -450,6 +506,27 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_HAS_EXEC_FENCE_ARRAY  49
 
+/*
+ * Query whether every context (both per-file default and user created) is
+ * isolated (insofar as HW supports). If this parameter is not true, then
+ * freshly created contexts may inherit values from an existing context,
+ * rather than default HW values. If true, it also ensures (insofar as HW
+ * supports) that all state set by this context will not leak to any other
+ * context.
+ *
+ * As not every engine across every gen support contexts, the returned
+ * value reports the support of context isolation for individual engines by
+ * returning a bitmask of each engine class set to true if that class supports
+ * isolation.
+ */
+#define I915_PARAM_HAS_CONTEXT_ISOLATION 50
+
+/* Frequency of the command streamer timestamps given by the *_TIMESTAMP
+ * registers. This used to be fixed per platform but from CNL onwards, this
+ * might vary depending on the parts.
+ */
+#define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51
+
 typedef struct drm_i915_getparam {
 	__s32 param;
 	/*

tools/include/uapi/linux/if_link.h

@@ -163,6 +163,7 @@ enum {
 	IFLA_IF_NETNSID,
 	IFLA_CARRIER_UP_COUNT,
 	IFLA_CARRIER_DOWN_COUNT,
+	IFLA_NEW_IFINDEX,
 	__IFLA_MAX
 };
 

tools/include/uapi/linux/kvm.h

@@ -1362,6 +1362,96 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_S390_CMMA_MIGRATION */
 #define KVM_S390_GET_CMMA_BITS      _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log)
 #define KVM_S390_SET_CMMA_BITS      _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log)
+/* Memory Encryption Commands */
+#define KVM_MEMORY_ENCRYPT_OP      _IOWR(KVMIO, 0xba, unsigned long)
+
+struct kvm_enc_region {
+	__u64 addr;
+	__u64 size;
+};
+
+#define KVM_MEMORY_ENCRYPT_REG_REGION    _IOR(KVMIO, 0xbb, struct kvm_enc_region)
+#define KVM_MEMORY_ENCRYPT_UNREG_REGION  _IOR(KVMIO, 0xbc, struct kvm_enc_region)
+
+/* Secure Encrypted Virtualization command */
+enum sev_cmd_id {
+	/* Guest initialization commands */
+	KVM_SEV_INIT = 0,
+	KVM_SEV_ES_INIT,
+	/* Guest launch commands */
+	KVM_SEV_LAUNCH_START,
+	KVM_SEV_LAUNCH_UPDATE_DATA,
+	KVM_SEV_LAUNCH_UPDATE_VMSA,
+	KVM_SEV_LAUNCH_SECRET,
+	KVM_SEV_LAUNCH_MEASURE,
+	KVM_SEV_LAUNCH_FINISH,
+	/* Guest migration commands (outgoing) */
+	KVM_SEV_SEND_START,
+	KVM_SEV_SEND_UPDATE_DATA,
+	KVM_SEV_SEND_UPDATE_VMSA,
+	KVM_SEV_SEND_FINISH,
+	/* Guest migration commands (incoming) */
+	KVM_SEV_RECEIVE_START,
+	KVM_SEV_RECEIVE_UPDATE_DATA,
+	KVM_SEV_RECEIVE_UPDATE_VMSA,
+	KVM_SEV_RECEIVE_FINISH,
+	/* Guest status and debug commands */
+	KVM_SEV_GUEST_STATUS,
+	KVM_SEV_DBG_DECRYPT,
+	KVM_SEV_DBG_ENCRYPT,
+	/* Guest certificates commands */
+	KVM_SEV_CERT_EXPORT,
+
+	KVM_SEV_NR_MAX,
+};
+
+struct kvm_sev_cmd {
+	__u32 id;
+	__u64 data;
+	__u32 error;
+	__u32 sev_fd;
+};
+
+struct kvm_sev_launch_start {
+	__u32 handle;
+	__u32 policy;
+	__u64 dh_uaddr;
+	__u32 dh_len;
+	__u64 session_uaddr;
+	__u32 session_len;
+};
+
+struct kvm_sev_launch_update_data {
+	__u64 uaddr;
+	__u32 len;
+};
+
+
+struct kvm_sev_launch_secret {
+	__u64 hdr_uaddr;
+	__u32 hdr_len;
+	__u64 guest_uaddr;
+	__u32 guest_len;
+	__u64 trans_uaddr;
+	__u32 trans_len;
+};
+
+struct kvm_sev_launch_measure {
+	__u64 uaddr;
+	__u32 len;
+};
+
+struct kvm_sev_guest_status {
+	__u32 handle;
+	__u32 policy;
+	__u32 state;
+};
+
+struct kvm_sev_dbg {
+	__u64 src_uaddr;
+	__u64 dst_uaddr;
+	__u32 len;
+};
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)

tools/perf/Documentation/perf-data.txt

@@ -30,6 +30,10 @@ OPTIONS for 'convert'
 -i::
 	Specify input perf data file path.
 
+-f::
+--force::
+	Don't complain, do it.
+
 -v::
 --verbose::
         Be more verbose (show counter open errors, etc).

tools/perf/arch/s390/Makefile

@@ -10,15 +10,19 @@ PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 
 out    := $(OUTPUT)arch/s390/include/generated/asm
 header := $(out)/syscalls_64.c
-sysdef := $(srctree)/tools/arch/s390/include/uapi/asm/unistd.h
-sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls/
+syskrn := $(srctree)/arch/s390/kernel/syscalls/syscall.tbl
+sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls
+sysdef := $(sysprf)/syscall.tbl
 systbl := $(sysprf)/mksyscalltbl
 
 # Create output directory if not already present
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 
 $(header): $(sysdef) $(systbl)
-	$(Q)$(SHELL) '$(systbl)' '$(CC)' $(sysdef) > $@
+	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
+        (diff -B $(sysdef) $(syskrn) >/dev/null) \
+        || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
+	$(Q)$(SHELL) '$(systbl)' $(sysdef) > $@
 
 clean::
 	$(call QUIET_CLEAN, s390) $(RM) $(header)

tools/perf/arch/s390/entry/syscalls/mksyscalltbl

@@ -3,25 +3,23 @@
 #
 # Generate system call table for perf
 #
-#
-# Copyright IBM Corp. 2017
+# Copyright IBM Corp. 2017, 2018
 # Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
 #
 
-gcc=$1
-input=$2
+SYSCALL_TBL=$1
 
-if ! test -r $input; then
+if ! test -r $SYSCALL_TBL; then
 	echo "Could not read input file" >&2
 	exit 1
 fi
 
 create_table()
 {
-	local max_nr
+	local max_nr nr abi sc discard
 
 	echo 'static const char *syscalltbl_s390_64[] = {'
-	while read sc nr; do
+	while read nr abi sc discard; do
 		printf '\t[%d] = "%s",\n' $nr $sc
 		max_nr=$nr
 	done
@@ -29,8 +27,6 @@ create_table()
 	echo "#define SYSCALLTBL_S390_64_MAX_ID $max_nr"
 }
 
-
-$gcc -m64 -E -dM -x c  $input	       \
-	|sed -ne 's/^#define __NR_//p' \
-	|sort -t' ' -k2 -nu	       \
+grep -E "^[[:digit:]]+[[:space:]]+(common|64)" $SYSCALL_TBL	\
+	|sort -k1 -n					\
 	|create_table

tools/perf/builtin-c2c.c

@@ -2245,7 +2245,7 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
 	c2c_browser__update_nr_entries(browser);
 
 	while (1) {
-		key = hist_browser__run(browser, "? - help");
+		key = hist_browser__run(browser, "? - help", true);
 
 		switch (key) {
 		case 's':
@@ -2314,7 +2314,7 @@ static int perf_c2c__hists_browse(struct hists *hists)
 	c2c_browser__update_nr_entries(browser);
 
 	while (1) {
-		key = hist_browser__run(browser, "? - help");
+		key = hist_browser__run(browser, "? - help", true);
 
 		switch (key) {
 		case 'q':

tools/perf/builtin-report.c

@@ -530,7 +530,8 @@ static int report__browse_hists(struct report *rep)
 	case 1:
 		ret = perf_evlist__tui_browse_hists(evlist, help, NULL,
 						    rep->min_percent,
-						    &session->header.env);
+						    &session->header.env,
+						    true);
 		/*
 		 * Usually "ret" is the last pressed key, and we only
 		 * care if the key notifies us to switch data file.

tools/perf/builtin-top.c

@@ -283,8 +283,9 @@ static void perf_top__print_sym_table(struct perf_top *top)
 
 	printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
 
-	if (hists->stats.nr_lost_warned !=
-	    hists->stats.nr_events[PERF_RECORD_LOST]) {
+	if (!top->record_opts.overwrite &&
+	    (hists->stats.nr_lost_warned !=
+	    hists->stats.nr_events[PERF_RECORD_LOST])) {
 		hists->stats.nr_lost_warned =
 			      hists->stats.nr_events[PERF_RECORD_LOST];
 		color_fprintf(stdout, PERF_COLOR_RED,
@@ -611,7 +612,8 @@ static void *display_thread_tui(void *arg)
 
 	perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
 				      top->min_percent,
-				      &top->session->header.env);
+				      &top->session->header.env,
+				      !top->record_opts.overwrite);
 
 	done = 1;
 	return NULL;
@@ -807,15 +809,23 @@ static void perf_event__process_sample(struct perf_tool *tool,
 
 static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 {
+	struct record_opts *opts = &top->record_opts;
+	struct perf_evlist *evlist = top->evlist;
 	struct perf_sample sample;
 	struct perf_evsel *evsel;
+	struct perf_mmap *md;
 	struct perf_session *session = top->session;
 	union perf_event *event;
 	struct machine *machine;
+	u64 end, start;
 	int ret;
 
-	while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) {
-		ret = perf_evlist__parse_sample(top->evlist, event, &sample);
+	md = opts->overwrite ? &evlist->overwrite_mmap[idx] : &evlist->mmap[idx];
+	if (perf_mmap__read_init(md, opts->overwrite, &start, &end) < 0)
+		return;
+
+	while ((event = perf_mmap__read_event(md, opts->overwrite, &start, end)) != NULL) {
+		ret = perf_evlist__parse_sample(evlist, event, &sample);
 		if (ret) {
 			pr_err("Can't parse sample, err = %d\n", ret);
 			goto next_event;
@@ -869,16 +879,120 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 		} else
 			++session->evlist->stats.nr_unknown_events;
 next_event:
-		perf_evlist__mmap_consume(top->evlist, idx);
+		perf_mmap__consume(md, opts->overwrite);
 	}
+
+	perf_mmap__read_done(md);
 }
 
 static void perf_top__mmap_read(struct perf_top *top)
 {
+	bool overwrite = top->record_opts.overwrite;
+	struct perf_evlist *evlist = top->evlist;
+	unsigned long long start, end;
 	int i;
 
+	start = rdclock();
+	if (overwrite)
+		perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING);
+
 	for (i = 0; i < top->evlist->nr_mmaps; i++)
 		perf_top__mmap_read_idx(top, i);
+
+	if (overwrite) {
+		perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
+		perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
+	}
+	end = rdclock();
+
+	if ((end - start) > (unsigned long long)top->delay_secs * NSEC_PER_SEC)
+		ui__warning("Too slow to read ring buffer.\n"
+			    "Please try increasing the period (-c) or\n"
+			    "decreasing the freq (-F) or\n"
+			    "limiting the number of CPUs (-C)\n");
+}
+
+/*
+ * Check per-event overwrite term.
+ * perf top should support consistent term for all events.
+ * - All events don't have per-event term
+ *   E.g. "cpu/cpu-cycles/,cpu/instructions/"
+ *   Nothing change, return 0.
+ * - All events have same per-event term
+ *   E.g. "cpu/cpu-cycles,no-overwrite/,cpu/instructions,no-overwrite/
+ *   Using the per-event setting to replace the opts->overwrite if
+ *   they are different, then return 0.
+ * - Events have different per-event term
+ *   E.g. "cpu/cpu-cycles,overwrite/,cpu/instructions,no-overwrite/"
+ *   Return -1
+ * - Some of the event set per-event term, but some not.
+ *   E.g. "cpu/cpu-cycles/,cpu/instructions,no-overwrite/"
+ *   Return -1
+ */
+static int perf_top__overwrite_check(struct perf_top *top)
+{
+	struct record_opts *opts = &top->record_opts;
+	struct perf_evlist *evlist = top->evlist;
+	struct perf_evsel_config_term *term;
+	struct list_head *config_terms;
+	struct perf_evsel *evsel;
+	int set, overwrite = -1;
+
+	evlist__for_each_entry(evlist, evsel) {
+		set = -1;
+		config_terms = &evsel->config_terms;
+		list_for_each_entry(term, config_terms, list) {
+			if (term->type == PERF_EVSEL__CONFIG_TERM_OVERWRITE)
+				set = term->val.overwrite ? 1 : 0;
+		}
+
+		/* no term for current and previous event (likely) */
+		if ((overwrite < 0) && (set < 0))
+			continue;
+
+		/* has term for both current and previous event, compare */
+		if ((overwrite >= 0) && (set >= 0) && (overwrite != set))
+			return -1;
+
+		/* no term for current event but has term for previous one */
+		if ((overwrite >= 0) && (set < 0))
+			return -1;
+
+		/* has term for current event */
+		if ((overwrite < 0) && (set >= 0)) {
+			/* if it's first event, set overwrite */
+			if (evsel == perf_evlist__first(evlist))
+				overwrite = set;
+			else
+				return -1;
+		}
+	}
+
+	if ((overwrite >= 0) && (opts->overwrite != overwrite))
+		opts->overwrite = overwrite;
+
+	return 0;
+}
+
+static int perf_top_overwrite_fallback(struct perf_top *top,
+				       struct perf_evsel *evsel)
+{
+	struct record_opts *opts = &top->record_opts;
+	struct perf_evlist *evlist = top->evlist;
+	struct perf_evsel *counter;
+
+	if (!opts->overwrite)
+		return 0;
+
+	/* only fall back when first event fails */
+	if (evsel != perf_evlist__first(evlist))
+		return 0;
+
+	evlist__for_each_entry(evlist, counter)
+		counter->attr.write_backward = false;
+	opts->overwrite = false;
+	ui__warning("fall back to non-overwrite mode\n");
+	return 1;
 }
 
 static int perf_top__start_counters(struct perf_top *top)
@@ -888,12 +1002,33 @@ static int perf_top__start_counters(struct perf_top *top)
 	struct perf_evlist *evlist = top->evlist;
 	struct record_opts *opts = &top->record_opts;
 
+	if (perf_top__overwrite_check(top)) {
+		ui__error("perf top only support consistent per-event "
+			  "overwrite setting for all events\n");
+		goto out_err;
+	}
+
 	perf_evlist__config(evlist, opts, &callchain_param);
 
 	evlist__for_each_entry(evlist, counter) {
 try_again:
 		if (perf_evsel__open(counter, top->evlist->cpus,
 				     top->evlist->threads) < 0) {
+
+			/*
+			 * Specially handle overwrite fall back.
+			 * Because perf top is the only tool which has
+			 * overwrite mode by default, support
+			 * both overwrite and non-overwrite mode, and
+			 * require consistent mode for all events.
+			 *
+			 * May move it to generic code with more tools
+			 * have similar attribute.
+			 */
+			if (perf_missing_features.write_backward &&
+			    perf_top_overwrite_fallback(top, counter))
+				goto try_again;
+
 			if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
 				if (verbose > 0)
 					ui__warning("%s\n", msg);
@@ -1033,7 +1168,7 @@ static int __cmd_top(struct perf_top *top)
 
 		perf_top__mmap_read(top);
 
-		if (hits == top->samples)
+		if (opts->overwrite || (hits == top->samples))
 			ret = perf_evlist__poll(top->evlist, 100);
 
 		if (resize) {
@@ -1127,6 +1262,7 @@ int cmd_top(int argc, const char **argv)
 				.uses_mmap   = true,
 			},
 			.proc_map_timeout    = 500,
+			.overwrite	= 1,
 		},
 		.max_stack	     = sysctl_perf_event_max_stack,
 		.sym_pcnt_filter     = 5,

tools/perf/check-headers.sh

@@ -33,7 +33,6 @@ arch/s390/include/uapi/asm/kvm.h
 arch/s390/include/uapi/asm/kvm_perf.h
 arch/s390/include/uapi/asm/ptrace.h
 arch/s390/include/uapi/asm/sie.h
-arch/s390/include/uapi/asm/unistd.h
 arch/arm/include/uapi/asm/kvm.h
 arch/arm64/include/uapi/asm/kvm.h
 arch/alpha/include/uapi/asm/errno.h

tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json

+[
+  {,
+    "EventCode": "0x7A",
+    "EventName": "BR_INDIRECT_SPEC",
+    "BriefDescription": "Branch speculatively executed - Indirect branch"
+  },
+  {,
+    "EventCode": "0xC9",
+    "EventName": "BR_COND",
+    "BriefDescription": "Conditional branch executed"
+  },
+  {,
+    "EventCode": "0xCA",
+    "EventName": "BR_INDIRECT_MISPRED",
+    "BriefDescription": "Indirect branch mispredicted"
+  },
+  {,
+    "EventCode": "0xCB",
+    "EventName": "BR_INDIRECT_MISPRED_ADDR",
+    "BriefDescription": "Indirect branch mispredicted because of address miscompare"
+  },
+  {,
+    "EventCode": "0xCC",
+    "EventName": "BR_COND_MISPRED",
+    "BriefDescription": "Conditional branch mispredicted"
+  }
+]

tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json

+[
+  {,
+    "EventCode": "0x60",
+    "EventName": "BUS_ACCESS_LD",
+    "BriefDescription": "Bus access - Read"
+  },
+  {,
+    "EventCode": "0x61",
+    "EventName": "BUS_ACCESS_ST",
+    "BriefDescription": "Bus access - Write"
+  },
+  {,
+    "EventCode": "0xC0",
+    "EventName": "EXT_MEM_REQ",
+    "BriefDescription": "External memory request"
+  },
+  {,
+    "EventCode": "0xC1",
+    "EventName": "EXT_MEM_REQ_NC",
+    "BriefDescription": "Non-cacheable external memory request"
+  }
+]

tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json

+[
+  {,
+    "EventCode": "0xC2",
+    "EventName": "PREFETCH_LINEFILL",
+    "BriefDescription": "Linefill because of prefetch"
+  },
+  {,
+    "EventCode": "0xC3",
+    "EventName": "PREFETCH_LINEFILL_DROP",
+    "BriefDescription": "Instruction Cache Throttle occurred"
+  },
+  {,
+    "EventCode": "0xC4",
+    "EventName": "READ_ALLOC_ENTER",
+    "BriefDescription": "Entering read allocate mode"
+  },
+  {,
+    "EventCode": "0xC5",
+    "EventName": "READ_ALLOC",
+    "BriefDescription": "Read allocate mode"
+  },
+  {,
+    "EventCode": "0xC8",
+    "EventName": "EXT_SNOOP",
+    "BriefDescription": "SCU Snooped data from another CPU for this CPU"
+  }
+]

tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json

+[
+  {,
+    "EventCode": "0x60",
+    "EventName": "BUS_ACCESS_LD",
+    "BriefDescription": "Bus access - Read"
+  },
+  {,
+    "EventCode": "0x61",
+    "EventName": "BUS_ACCESS_ST",
+    "BriefDescription": "Bus access - Write"
+  },
+  {,
+    "EventCode": "0xC0",
+    "EventName": "EXT_MEM_REQ",
+    "BriefDescription": "External memory request"
+  },
+  {,
+    "EventCode": "0xC1",
+    "EventName": "EXT_MEM_REQ_NC",
+    "BriefDescription": "Non-cacheable external memory request"
+  }
+]

tools/perf/pmu-events/arch/arm64/cortex-a53/other.json

+[
+  {,
+    "EventCode": "0x86",
+    "EventName": "EXC_IRQ",
+    "BriefDescription": "Exception taken, IRQ"
+  },
+  {,
+    "EventCode": "0x87",
+    "EventName": "EXC_FIQ",
+    "BriefDescription": "Exception taken, FIQ"
+  },
+  {,
+    "EventCode": "0xC6",
+    "EventName": "PRE_DECODE_ERR",
+    "BriefDescription": "Pre-decode error"
+  },
+  {,
+    "EventCode": "0xD0",
+    "EventName": "L1I_CACHE_ERR",
+    "BriefDescription": "L1 Instruction Cache (data or tag) memory error"
+  },
+  {,
+    "EventCode": "0xD1",
+    "EventName": "L1D_CACHE_ERR",
+    "BriefDescription": "L1 Data Cache (data, tag or dirty) memory error, correctable or non-correctable"
+  },
+  {,
+    "EventCode": "0xD2",
+    "EventName": "TLB_ERR",
+    "BriefDescription": "TLB memory error"
+  }
+]

tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json

+[
+  {,
+    "EventCode": "0xC7",
+    "EventName": "STALL_SB_FULL",
+    "BriefDescription": "Data Write operation that stalls the pipeline because the store buffer is full"
+  },
+  {,
+    "EventCode": "0xE0",
+    "EventName": "OTHER_IQ_DEP_STALL",
+    "BriefDescription": "Cycles that the DPU IQ is empty and that is not because of a recent micro-TLB miss, instruction cache miss or pre-decode error"
+  },
+  {,
+    "EventCode": "0xE1",
+    "EventName": "IC_DEP_STALL",
+    "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction cache miss being processed"
+  },
+  {,
+    "EventCode": "0xE2",
+    "EventName": "IUTLB_DEP_STALL",
+    "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction micro-TLB miss being processed"
+  },
+  {,
+    "EventCode": "0xE3",
+    "EventName": "DECODE_DEP_STALL",
+    "BriefDescription": "Cycles the DPU IQ is empty and there is a pre-decode error being processed"
+  },
+  {,
+    "EventCode": "0xE4",
+    "EventName": "OTHER_INTERLOCK_STALL",
+    "BriefDescription": "Cycles there is an interlock other than  Advanced SIMD/Floating-point instructions or load/store instruction"
+  },
+  {,
+    "EventCode": "0xE5",
+    "EventName": "AGU_DEP_STALL",
+    "BriefDescription": "Cycles there is an interlock for a load/store instruction waiting for data to calculate the address in the AGU"
+  },
+  {,
+    "EventCode": "0xE6",
+    "EventName": "SIMD_DEP_STALL",
+    "BriefDescription": "Cycles there is an interlock for an Advanced SIMD/Floating-point operation."
+  },
+  {,
+    "EventCode": "0xE7",
+    "EventName": "LD_DEP_STALL",
+    "BriefDescription": "Cycles there is a stall in the Wr stage because of a load miss"
+  },
+  {,
+    "EventCode": "0xE8",
+    "EventName": "ST_DEP_STALL",
+    "BriefDescription": "Cycles there is a stall in the Wr stage because of a store"
+  }
+]

tools/perf/pmu-events/arch/arm64/mapfile.csv

@@ -13,3 +13,4 @@
 #
 #Family-model,Version,Filename,EventType
 0x00000000420f5160,v1,cavium,core
+0x00000000410fd03[[:xdigit:]],v1,cortex-a53,core

tools/perf/tests/backward-ring-buffer.c

@@ -31,10 +31,12 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
 	int i;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
+		struct perf_mmap *map = &evlist->overwrite_mmap[i];
 		union perf_event *event;
+		u64 start, end;
 
-		perf_mmap__read_catchup(&evlist->overwrite_mmap[i]);
-		while ((event = perf_mmap__read_backward(&evlist->overwrite_mmap[i])) != NULL) {
+		perf_mmap__read_init(map, true, &start, &end);
+		while ((event = perf_mmap__read_event(map, true, &start, end)) != NULL) {
 			const u32 type = event->header.type;
 
 			switch (type) {
@@ -49,6 +51,7 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
 				return TEST_FAIL;
 			}
 		}
+		perf_mmap__read_done(map);
 	}
 	return TEST_OK;
 }

tools/perf/tests/shell/trace+probe_libc_inet_pton.sh

@@ -22,10 +22,23 @@ trace_libc_inet_pton_backtrace() {
 	expected[4]="rtt min.*"
 	expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)"
 	expected[6]=".*inet_pton[[:space:]]\($libc\)$"
-	expected[7]="getaddrinfo[[:space:]]\($libc\)$"
-	expected[8]=".*\(.*/bin/ping.*\)$"
-
-	perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do
+	case "$(uname -m)" in
+	s390x)
+		eventattr='call-graph=dwarf'
+		expected[7]="gaih_inet[[:space:]]\(inlined\)$"
+		expected[8]="__GI_getaddrinfo[[:space:]]\(inlined\)$"
+		expected[9]="main[[:space:]]\(.*/bin/ping.*\)$"
+		expected[10]="__libc_start_main[[:space:]]\($libc\)$"
+		expected[11]="_start[[:space:]]\(.*/bin/ping.*\)$"
+		;;
+	*)
+		eventattr='max-stack=3'
+		expected[7]="getaddrinfo[[:space:]]\($libc\)$"
+		expected[8]=".*\(.*/bin/ping.*\)$"
+		;;
+	esac
+
+	perf trace --no-syscalls -e probe_libc:inet_pton/$eventattr/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do
 		echo $line
 		echo "$line" | egrep -q "${expected[$idx]}"
 		if [ $? -ne 0 ] ; then
@@ -33,7 +46,7 @@ trace_libc_inet_pton_backtrace() {
 			exit 1
 		fi
 		let idx+=1
-		[ $idx -eq 9 ] && break
+		[ -z "${expected[$idx]}" ] && break
 	done
 }
 

tools/perf/ui/browsers/hists.c

@@ -608,7 +608,8 @@ static int hist_browser__title(struct hist_browser *browser, char *bf, size_t si
 	return browser->title ? browser->title(browser, bf, size) : 0;
 }
 
-int hist_browser__run(struct hist_browser *browser, const char *help)
+int hist_browser__run(struct hist_browser *browser, const char *help,
+		      bool warn_lost_event)
 {
 	int key;
 	char title[160];
@@ -638,8 +639,9 @@ int hist_browser__run(struct hist_browser *browser, const char *help)
 			nr_entries = hist_browser__nr_entries(browser);
 			ui_browser__update_nr_entries(&browser->b, nr_entries);
 
-			if (browser->hists->stats.nr_lost_warned !=
-			    browser->hists->stats.nr_events[PERF_RECORD_LOST]) {
+			if (warn_lost_event &&
+			    (browser->hists->stats.nr_lost_warned !=
+			    browser->hists->stats.nr_events[PERF_RECORD_LOST])) {
 				browser->hists->stats.nr_lost_warned =
 					browser->hists->stats.nr_events[PERF_RECORD_LOST];
 				ui_browser__warn_lost_events(&browser->b);
@@ -2763,7 +2765,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 				    bool left_exits,
 				    struct hist_browser_timer *hbt,
 				    float min_pcnt,
-				    struct perf_env *env)
+				    struct perf_env *env,
+				    bool warn_lost_event)
 {
 	struct hists *hists = evsel__hists(evsel);
 	struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env);
@@ -2844,7 +2847,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
 		nr_options = 0;
 
-		key = hist_browser__run(browser, helpline);
+		key = hist_browser__run(browser, helpline,
+					warn_lost_event);
 
 		if (browser->he_selection != NULL) {
 			thread = hist_browser__selected_thread(browser);
@@ -3184,7 +3188,8 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
 
 static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
 				int nr_events, const char *help,
-				struct hist_browser_timer *hbt)
+				struct hist_browser_timer *hbt,
+				bool warn_lost_event)
 {
 	struct perf_evlist *evlist = menu->b.priv;
 	struct perf_evsel *pos;
@@ -3203,7 +3208,9 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
 		case K_TIMER:
 			hbt->timer(hbt->arg);
 
-			if (!menu->lost_events_warned && menu->lost_events) {
+			if (!menu->lost_events_warned &&
+			    menu->lost_events &&
+			    warn_lost_event) {
 				ui_browser__warn_lost_events(&menu->b);
 				menu->lost_events_warned = true;
 			}
@@ -3224,7 +3231,8 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
 			key = perf_evsel__hists_browse(pos, nr_events, help,
 						       true, hbt,
 						       menu->min_pcnt,
-						       menu->env);
+						       menu->env,
+						       warn_lost_event);
 			ui_browser__show_title(&menu->b, title);
 			switch (key) {
 			case K_TAB:
@@ -3282,7 +3290,8 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
 					   int nr_entries, const char *help,
 					   struct hist_browser_timer *hbt,
 					   float min_pcnt,
-					   struct perf_env *env)
+					   struct perf_env *env,
+					   bool warn_lost_event)
 {
 	struct perf_evsel *pos;
 	struct perf_evsel_menu menu = {
@@ -3309,13 +3318,15 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
 			menu.b.width = line_len;
 	}
 
-	return perf_evsel_menu__run(&menu, nr_entries, help, hbt);
+	return perf_evsel_menu__run(&menu, nr_entries, help,
+				    hbt, warn_lost_event);
 }
 
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 				  struct hist_browser_timer *hbt,
 				  float min_pcnt,
-				  struct perf_env *env)
+				  struct perf_env *env,
+				  bool warn_lost_event)
 {
 	int nr_entries = evlist->nr_entries;
 
@@ -3325,7 +3336,7 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 
 		return perf_evsel__hists_browse(first, nr_entries, help,
 						false, hbt, min_pcnt,
-						env);
+						env, warn_lost_event);
 	}
 
 	if (symbol_conf.event_group) {
@@ -3342,5 +3353,6 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 	}
 
 	return __perf_evlist__tui_browse_hists(evlist, nr_entries, help,
-					       hbt, min_pcnt, env);
+					       hbt, min_pcnt, env,
+					       warn_lost_event);
 }

tools/perf/ui/browsers/hists.h

@@ -28,7 +28,8 @@ struct hist_browser {
 
 struct hist_browser *hist_browser__new(struct hists *hists);
 void hist_browser__delete(struct hist_browser *browser);
-int hist_browser__run(struct hist_browser *browser, const char *help);
+int hist_browser__run(struct hist_browser *browser, const char *help,
+		      bool warn_lost_event);
 void hist_browser__init(struct hist_browser *browser,
 			struct hists *hists);
 #endif /* _PERF_UI_BROWSER_HISTS_H_ */

tools/perf/util/evlist.c

@@ -715,28 +715,11 @@ union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int
 	return perf_mmap__read_forward(md);
 }
 
-union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
-{
-	struct perf_mmap *md = &evlist->mmap[idx];
-
-	/*
-	 * No need to check messup for backward ring buffer:
-	 * We can always read arbitrary long data from a backward
-	 * ring buffer unless we forget to pause it before reading.
-	 */
-	return perf_mmap__read_backward(md);
-}
-
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 {
 	return perf_evlist__mmap_read_forward(evlist, idx);
 }
 
-void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
-{
-	perf_mmap__read_catchup(&evlist->mmap[idx]);
-}
-
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 {
 	perf_mmap__consume(&evlist->mmap[idx], false);

tools/perf/util/evlist.h

@@ -133,10 +133,6 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx);
 
 union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist,
 						 int idx);
-union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist,
-						  int idx);
-void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx);
-
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
 
 int perf_evlist__open(struct perf_evlist *evlist);

tools/perf/util/evsel.c

@@ -41,17 +41,7 @@
 
 #include "sane_ctype.h"
 
-static struct {
-	bool sample_id_all;
-	bool exclude_guest;
-	bool mmap2;
-	bool cloexec;
-	bool clockid;
-	bool clockid_wrong;
-	bool lbr_flags;
-	bool write_backward;
-	bool group_read;
-} perf_missing_features;
+struct perf_missing_features perf_missing_features;
 
 static clockid_t clockid;
 

tools/perf/util/evsel.h

@@ -149,6 +149,20 @@ union u64_swap {
 	u32 val32[2];
 };
 
+struct perf_missing_features {
+	bool sample_id_all;
+	bool exclude_guest;
+	bool mmap2;
+	bool cloexec;
+	bool clockid;
+	bool clockid_wrong;
+	bool lbr_flags;
+	bool write_backward;
+	bool group_read;
+};
+
+extern struct perf_missing_features perf_missing_features;
+
 struct cpu_map;
 struct target;
 struct thread_map;

tools/perf/util/hist.h

@@ -430,7 +430,8 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 				  struct hist_browser_timer *hbt,
 				  float min_pcnt,
-				  struct perf_env *env);
+				  struct perf_env *env,
+				  bool warn_lost_event);
 int script_browse(const char *script_opt);
 #else
 static inline
@@ -438,7 +439,8 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
 				  const char *help __maybe_unused,
 				  struct hist_browser_timer *hbt __maybe_unused,
 				  float min_pcnt __maybe_unused,
-				  struct perf_env *env __maybe_unused)
+				  struct perf_env *env __maybe_unused,
+				  bool warn_lost_event __maybe_unused)
 {
 	return 0;
 }

tools/perf/util/mmap.c

@@ -22,29 +22,27 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map)
 
 /* When check_messup is true, 'end' must points to a good entry */
 static union perf_event *perf_mmap__read(struct perf_mmap *map,
-					 u64 start, u64 end, u64 *prev)
+					 u64 *startp, u64 end)
 {
 	unsigned char *data = map->base + page_size;
 	union perf_event *event = NULL;
-	int diff = end - start;
+	int diff = end - *startp;
 
 	if (diff >= (int)sizeof(event->header)) {
 		size_t size;
 
-		event = (union perf_event *)&data[start & map->mask];
+		event = (union perf_event *)&data[*startp & map->mask];
 		size = event->header.size;
 
-		if (size < sizeof(event->header) || diff < (int)size) {
-			event = NULL;
-			goto broken_event;
-		}
+		if (size < sizeof(event->header) || diff < (int)size)
+			return NULL;
 
 		/*
 		 * Event straddles the mmap boundary -- header should always
 		 * be inside due to u64 alignment of output.
 		 */
-		if ((start & map->mask) + size != ((start + size) & map->mask)) {
-			unsigned int offset = start;
+		if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) {
+			unsigned int offset = *startp;
 			unsigned int len = min(sizeof(*event), size), cpy;
 			void *dst = map->event_copy;
 
@@ -59,20 +57,19 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map,
 			event = (union perf_event *)map->event_copy;
 		}
 
-		start += size;
+		*startp += size;
 	}
 
-broken_event:
-	if (prev)
-		*prev = start;
-
 	return event;
 }
 
+/*
+ * legacy interface for mmap read.
+ * Don't use it. Use perf_mmap__read_event().
+ */
 union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
 {
 	u64 head;
-	u64 old = map->prev;
 
 	/*
 	 * Check if event was unmapped due to a POLLHUP/POLLERR.
@@ -82,13 +79,26 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
 
 	head = perf_mmap__read_head(map);
 
-	return perf_mmap__read(map, old, head, &map->prev);
+	return perf_mmap__read(map, &map->prev, head);
 }
 
-union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
+/*
+ * Read event from ring buffer one by one.
+ * Return one event for each call.
+ *
+ * Usage:
+ * perf_mmap__read_init()
+ * while(event = perf_mmap__read_event()) {
+ *	//process the event
+ *	perf_mmap__consume()
+ * }
+ * perf_mmap__read_done()
+ */
+union perf_event *perf_mmap__read_event(struct perf_mmap *map,
+					bool overwrite,
+					u64 *startp, u64 end)
 {
-	u64 head, end;
-	u64 start = map->prev;
+	union perf_event *event;
 
 	/*
 	 * Check if event was unmapped due to a POLLHUP/POLLERR.
@@ -96,40 +106,19 @@ union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
 	if (!refcount_read(&map->refcnt))
 		return NULL;
 
-	head = perf_mmap__read_head(map);
-	if (!head)
+	if (startp == NULL)
 		return NULL;
 
-	/*
-	 * 'head' pointer starts from 0. Kernel minus sizeof(record) form
-	 * it each time when kernel writes to it, so in fact 'head' is
-	 * negative. 'end' pointer is made manually by adding the size of
-	 * the ring buffer to 'head' pointer, means the validate data can
-	 * read is the whole ring buffer. If 'end' is positive, the ring
-	 * buffer has not fully filled, so we must adjust 'end' to 0.
-	 *
-	 * However, since both 'head' and 'end' is unsigned, we can't
-	 * simply compare 'end' against 0. Here we compare '-head' and
-	 * the size of the ring buffer, where -head is the number of bytes
-	 * kernel write to the ring buffer.
-	 */
-	if (-head < (u64)(map->mask + 1))
-		end = 0;
-	else
-		end = head + map->mask + 1;
-
-	return perf_mmap__read(map, start, end, &map->prev);
-}
+	/* non-overwirte doesn't pause the ringbuffer */
+	if (!overwrite)
+		end = perf_mmap__read_head(map);
 
-void perf_mmap__read_catchup(struct perf_mmap *map)
-{
-	u64 head;
+	event = perf_mmap__read(map, startp, end);
 
-	if (!refcount_read(&map->refcnt))
-		return;
+	if (!overwrite)
+		map->prev = *startp;
 
-	head = perf_mmap__read_head(map);
-	map->prev = head;
+	return event;
 }
 
 static bool perf_mmap__empty(struct perf_mmap *map)
@@ -267,41 +256,60 @@ static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u6
 	return -1;
 }
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite,
-		    void *to, int push(void *to, void *buf, size_t size))
+/*
+ * Report the start and end of the available data in ringbuffer
+ */
+int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
+			 u64 *startp, u64 *endp)
 {
 	u64 head = perf_mmap__read_head(md);
 	u64 old = md->prev;
-	u64 end = head, start = old;
 	unsigned char *data = md->base + page_size;
 	unsigned long size;
-	void *buf;
-	int rc = 0;
 
-	start = overwrite ? head : old;
-	end = overwrite ? old : head;
+	*startp = overwrite ? head : old;
+	*endp = overwrite ? old : head;
 
-	if (start == end)
-		return 0;
+	if (*startp == *endp)
+		return -EAGAIN;
 
-	size = end - start;
+	size = *endp - *startp;
 	if (size > (unsigned long)(md->mask) + 1) {
 		if (!overwrite) {
 			WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
 
 			md->prev = head;
 			perf_mmap__consume(md, overwrite);
-			return 0;
+			return -EAGAIN;
 		}
 
 		/*
 		 * Backward ring buffer is full. We still have a chance to read
 		 * most of data from it.
 		 */
-		if (overwrite_rb_find_range(data, md->mask, head, &start, &end))
-			return -1;
+		if (overwrite_rb_find_range(data, md->mask, head, startp, endp))
+			return -EINVAL;
 	}
 
+	return 0;
+}
+
+int perf_mmap__push(struct perf_mmap *md, bool overwrite,
+		    void *to, int push(void *to, void *buf, size_t size))
+{
+	u64 head = perf_mmap__read_head(md);
+	u64 end, start;
+	unsigned char *data = md->base + page_size;
+	unsigned long size;
+	void *buf;
+	int rc = 0;
+
+	rc = perf_mmap__read_init(md, overwrite, &start, &end);
+	if (rc < 0)
+		return (rc == -EAGAIN) ? 0 : -1;
+
+	size = end - start;
+
 	if ((start & md->mask) + size != (end & md->mask)) {
 		buf = &data[start & md->mask];
 		size = md->mask + 1 - (start & md->mask);
@@ -327,3 +335,14 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite,
 out:
 	return rc;
 }
+
+/*
+ * Mandatory for overwrite mode
+ * The direction of overwrite mode is backward.
+ * The last perf_mmap__read() will set tail to map->prev.
+ * Need to correct the map->prev to head which is the end of next read.
+ */
+void perf_mmap__read_done(struct perf_mmap *map)
+{
+	map->prev = perf_mmap__read_head(map);
+}

tools/perf/util/mmap.h

@@ -65,8 +65,6 @@ void perf_mmap__put(struct perf_mmap *map);
 
 void perf_mmap__consume(struct perf_mmap *map, bool overwrite);
 
-void perf_mmap__read_catchup(struct perf_mmap *md);
-
 static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
 {
 	struct perf_event_mmap_page *pc = mm->base;
@@ -87,11 +85,17 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
 }
 
 union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
-union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
+
+union perf_event *perf_mmap__read_event(struct perf_mmap *map,
+					bool overwrite,
+					u64 *startp, u64 end);
 
 int perf_mmap__push(struct perf_mmap *md, bool backward,
 		    void *to, int push(void *to, void *buf, size_t size));
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
 
+int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
+			 u64 *startp, u64 *endp);
+void perf_mmap__read_done(struct perf_mmap *map);
 #endif /*__PERF_MMAP_H */

tools/perf/util/util.c

@@ -340,35 +340,15 @@ size_t hex_width(u64 v)
 	return n;
 }
 
-static int hex(char ch)
-{
-	if ((ch >= '0') && (ch <= '9'))
-		return ch - '0';
-	if ((ch >= 'a') && (ch <= 'f'))
-		return ch - 'a' + 10;
-	if ((ch >= 'A') && (ch <= 'F'))
-		return ch - 'A' + 10;
-	return -1;
-}
-
 /*
  * While we find nice hex chars, build a long_val.
  * Return number of chars processed.
  */
 int hex2u64(const char *ptr, u64 *long_val)
 {
-	const char *p = ptr;
-	*long_val = 0;
-
-	while (*p) {
-		const int hex_val = hex(*p);
+	char *p;
 
-		if (hex_val < 0)
-			break;
-
-		*long_val = (*long_val << 4) | hex_val;
-		p++;
-	}
+	*long_val = strtoull(ptr, &p, 16);
 
 	return p - ptr;
 }