perf tooling updates

201 lines not on this page · raw message

index f3aa9d02a5ab..d340d2e42776 100644
@@ -68,7 +68,7 @@ struct c2c_hist_entry {
 	struct hist_entry	he;
 };
 
-static char const *coalesce_default = "pid,iaddr";
+static char const *coalesce_default = "iaddr";
 
 struct perf_c2c {
 	struct perf_tool	tool;

@@ -1878,7 +1878,7 @@ static int c2c_hists__reinit(struct c2c_hists *c2c_hists,
 	return hpp_list__parse(&c2c_hists->list, output, sort);
 }
 
-#define DISPLAY_LINE_LIMIT  0.0005
+#define DISPLAY_LINE_LIMIT  0.001
 
 static bool he__display(struct hist_entry *he, struct c2c_stats *stats)
 {

index 3728b50e52e2..d079f36d342d 100644
@@ -1073,9 +1073,18 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 
 	/*
 	 * Print final block upto sample
+	 *
+	 * Due to pipeline delays the LBRs might be missing a branch
+	 * or two, which can result in very large or negative blocks
+	 * between final branch and sample. When this happens just
+	 * continue walking after the last TO until we hit a branch.
 	 */
 	start = br->entries[0].to;
 	end = sample->ip;
+	if (end < start) {
+		/* Missing jump. Scan 128 bytes for the next branch */
+		end = start + 128;
+	}
 	len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true);
 	printed += ip__fprintf_sym(start, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
 	if (len <= 0) {

@@ -1084,7 +1093,6 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 			      machine, thread, &x.is64bit, &x.cpumode, false);
 		if (len <= 0)
 			goto out;
-
 		printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", sample->ip,
 			dump_insn(&x, sample->ip, buffer, len, NULL));
 		if (PRINT_FIELD(SRCCODE))

@@ -1096,6 +1104,13 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 				   dump_insn(&x, start + off, buffer + off, len - off, &ilen));
 		if (ilen == 0)
 			break;
+		if (arch_is_branch(buffer + off, len - off, x.is64bit) && start + off != sample->ip) {
+			/*
+			 * Hit a missing branch. Just stop.
+			 */
+			printed += fprintf(fp, "\t... not reaching sample ...\n");
+			break;
+		}
 		if (PRINT_FIELD(SRCCODE))
 			print_srccode(thread, x.cpumode, start + off);
 	}

@@ -1167,7 +1182,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 					   struct addr_location *al, FILE *fp)
 {
 	struct perf_event_attr *attr = &evsel->attr;
-	size_t depth = thread_stack__depth(thread);
+	size_t depth = thread_stack__depth(thread, sample->cpu);
 	const char *name = NULL;
 	static int spacing;
 	int len = 0;

@@ -1701,7 +1716,7 @@ static bool show_event(struct perf_sample *sample,
 		       struct thread *thread,
 		       struct addr_location *al)
 {
-	int depth = thread_stack__depth(thread);
+	int depth = thread_stack__depth(thread, sample->cpu);
 
 	if (!symbol_conf.graph_function)
 		return true;

257 lines not on this page · raw message

index 83c5b202e00e..139d485a6f16 100644
@@ -32,6 +32,13 @@ size_t strarray__scnprintf_flags(struct strarray *sa, char *bf, size_t size, boo
 struct trace;
 struct thread;
 
+struct file {
+	char *pathname;
+	int  dev_maj;
+};
+
+struct file *thread__files_entry(struct thread *thread, int fd);
+
 struct strarrays {
 	int		nr_entries;
 	struct strarray **entries;

index 9efeb6a936c2..620350d41209 100644
@@ -112,6 +112,17 @@ static size_t ioctl__scnprintf_perf_cmd(int nr, int dir, char *bf, size_t size)
 	return scnprintf(bf, size, "(%#x, %#x, %#x)", 0xAE, nr, dir);
 }
 
+static size_t ioctl__scnprintf_usbdevfs_cmd(int nr, int dir, char *bf, size_t size)
+{
+#include "trace/beauty/generated/ioctl/usbdevfs_ioctl_array.c"
+	static DEFINE_STRARRAY(usbdevfs_ioctl_cmds, "");
+
+	if (nr < strarray__usbdevfs_ioctl_cmds.nr_entries && strarray__usbdevfs_ioctl_cmds.entries[nr] != NULL)
+		return scnprintf(bf, size, "USBDEVFS_%s", strarray__usbdevfs_ioctl_cmds.entries[nr]);
+
+	return scnprintf(bf, size, "(%c, %#x, %#x)", 'U', nr, dir);
+}
+
 static size_t ioctl__scnprintf_cmd(unsigned long cmd, char *bf, size_t size, bool show_prefix)
 {
 	const char *prefix = "_IOC_";

@@ -157,9 +168,20 @@ static size_t ioctl__scnprintf_cmd(unsigned long cmd, char *bf, size_t size, boo
 	return printed + scnprintf(bf + printed, size - printed, ", %#x, %#x, %#x)", type, nr, sz);
 }
 
+#ifndef USB_DEVICE_MAJOR
+#define USB_DEVICE_MAJOR 189
+#endif // USB_DEVICE_MAJOR
+
 size_t syscall_arg__scnprintf_ioctl_cmd(char *bf, size_t size, struct syscall_arg *arg)
 {
 	unsigned long cmd = arg->val;
+	unsigned int fd = syscall_arg__val(arg, 0);
+	struct file *file = thread__files_entry(arg->thread, fd);
+
+	if (file != NULL) {
+		if (file->dev_maj == USB_DEVICE_MAJOR)
+			return ioctl__scnprintf_usbdevfs_cmd(_IOC_NR(cmd), _IOC_DIR(cmd), bf, size);
+	}
 
 	return ioctl__scnprintf_cmd(cmd, bf, size, arg->show_string_prefix);
 }

index eb31089790e3..859a8a9db2c6 100644
@@ -18,8 +18,8 @@ static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 	}
 
 	P_MMAP_PROT(READ);
-	P_MMAP_PROT(EXEC);
 	P_MMAP_PROT(WRITE);
+	P_MMAP_PROT(EXEC);
 	P_MMAP_PROT(SEM);
 	P_MMAP_PROT(GROWSDOWN);
 	P_MMAP_PROT(GROWSUP);

index 4600c28a3cfe..637722e2796b 100644
@@ -9,7 +9,7 @@
 static size_t syscall_arg__scnprintf_seccomp_op(char *bf, size_t size, struct syscall_arg *arg)
 {
 	bool show_prefix = arg->show_string_prefix;
-	const char *prefix = "SECOMP_SET_MODE_";
+	const char *prefix = "SECCOMP_SET_MODE_";
 	int op = arg->val;
 	size_t printed = 0;
 

@@ -34,7 +34,7 @@ static size_t syscall_arg__scnprintf_seccomp_flags(char *bf, size_t size,
 						   struct syscall_arg *arg)
 {
 	bool show_prefix = arg->show_string_prefix;
-	const char *prefix = "SECOMP_FILTER_FLAG_";
+	const char *prefix = "SECCOMP_FILTER_FLAG_";
 	int printed = 0, flags = arg->val;
 
 #define	P_FLAG(n) \

index 10988d3de7ce..2bd8585db93c 100644
@@ -13,3 +13,11 @@ const char *dump_insn(struct perf_insn *x __maybe_unused,
 		*lenp = 0;
 	return "?";
 }
+
+__weak
+int arch_is_branch(const unsigned char *buf __maybe_unused,
+		   size_t len __maybe_unused,
+		   int x86_64 __maybe_unused)
+{
+	return 0;
+}

index 0e06280a8860..650125061530 100644
@@ -20,4 +20,6 @@ struct perf_insn {
 
 const char *dump_insn(struct perf_insn *x, u64 ip,
 		      u8 *inbuf, int inlen, int *lenp);
+int arch_is_branch(const unsigned char *buf, size_t len, int x86_64);
+
 #endif

index 7b27d77306c2..ee6ca65f81f4 100644
@@ -451,7 +451,7 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
 			continue;
 		intel_bts_get_branch_type(btsq, branch);
 		if (btsq->bts->synth_opts.thread_stack)
-			thread_stack__event(thread, btsq->sample_flags,
+			thread_stack__event(thread, btsq->cpu, btsq->sample_flags,
 					    le64_to_cpu(branch->from),
 					    le64_to_cpu(branch->to),
 					    btsq->intel_pt_insn.length,

@@ -523,7 +523,7 @@ static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
 	    !btsq->bts->synth_opts.thread_stack && thread &&
 	    (!old_buffer || btsq->bts->sampling_mode ||
 	     (btsq->bts->snapshot_mode && !buffer->consecutive)))
-		thread_stack__set_trace_nr(thread, buffer->buffer_nr + 1);
+		thread_stack__set_trace_nr(thread, btsq->cpu, buffer->buffer_nr + 1);
 
 	err = intel_bts_process_buffer(btsq, buffer, thread);
 

index 54818828023b..1c0e289f01e6 100644
@@ -180,6 +180,14 @@ int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64,
 	return 0;
 }
 
+int arch_is_branch(const unsigned char *buf, size_t len, int x86_64)
+{
+	struct intel_pt_insn in;
+	if (intel_pt_get_insn(buf, len, x86_64, &in) < 0)
+		return -1;
+	return in.branch != INTEL_PT_BR_NO_BRANCH;
+}
+
 const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused,
 		      u8 *inbuf, int inlen, int *lenp)
 {

index 149ff361ca78..2e72373ec6df 100644
@@ -1174,7 +1174,7 @@ static void intel_pt_prep_sample(struct intel_pt *pt,
 	intel_pt_prep_b_sample(pt, ptq, event, sample);
 
 	if (pt->synth_opts.callchain) {
-		thread_stack__sample(ptq->thread, ptq->chain,
+		thread_stack__sample(ptq->thread, ptq->cpu, ptq->chain,
 				     pt->synth_opts.callchain_sz + 1,
 				     sample->ip, pt->kernel_start);
 		sample->callchain = ptq->chain;

@@ -1526,11 +1526,11 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 		return 0;
 
 	if (pt->synth_opts.callchain || pt->synth_opts.thread_stack)
-		thread_stack__event(ptq->thread, ptq->flags, state->from_ip,
+		thread_stack__event(ptq->thread, ptq->cpu, ptq->flags, state->from_ip,
 				    state->to_ip, ptq->insn_len,
 				    state->trace_nr);
 	else
-		thread_stack__set_trace_nr(ptq->thread, state->trace_nr);
+		thread_stack__set_trace_nr(ptq->thread, ptq->cpu, state->trace_nr);
 
 	if (pt->sample_branches) {
 		err = intel_pt_synth_branch_sample(ptq);

index 47628e85c5eb..dda0ac978b1e 100644
@@ -939,7 +939,8 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist,
 
 		file = PyFile_FromFile(fp, "perf", "r", NULL);
 #else
-		file = PyFile_FromFd(evlist->pollfd.entries[i].fd, "perf", "r", -1, NULL, NULL, NULL, 1);
+		file = PyFile_FromFd(evlist->pollfd.entries[i].fd, "perf", "r", -1,
+				     NULL, NULL, NULL, 0);
 #endif
 		if (file == NULL)
 			goto free_list;

index 78a067777144..5456c84c7dd1 100644
@@ -1527,6 +1527,13 @@ struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
 	return machine__findnew_thread(&session->machines.host, -1, pid);
 }
 
+/*
+ * Threads are identified by pid and tid, and the idle task has pid == tid == 0.
+ * So here a single thread is created for that, but actually there is a separate
+ * idle task per cpu, so there should be one 'struct thread' per cpu, but there
+ * is only 1. That causes problems for some tools, requiring workarounds. For
+ * example get_idle_thread() in builtin-sched.c, or thread_stack__per_cpu().
+ */
 int perf_session__register_idle_thread(struct perf_session *session)
 {
 	struct thread *thread;

369 lines not on this page · raw message

index f97c00a8c251..1f626f4a1c40 100644
@@ -80,14 +80,14 @@ struct call_return_processor {
 	void *data;
 };
 
-int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
 			u64 to_ip, u16 insn_len, u64 trace_nr);
-void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
-void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+void thread_stack__set_trace_nr(struct thread *thread, int cpu, u64 trace_nr);
+void thread_stack__sample(struct thread *thread, int cpu, struct ip_callchain *chain,
 			  size_t sz, u64 ip, u64 kernel_start);
 int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
-size_t thread_stack__depth(struct thread *thread);
+size_t thread_stack__depth(struct thread *thread, int cpu);
 
 struct call_return_processor *
 call_return_processor__new(int (*process)(struct call_return *cr, void *data),