From cf7905165fee15fe26ac4a91ee0a35b966249430 Mon Sep 17 00:00:00 2001
From: Alexey Budankov <alexey.budankov@linux.intel.com>
Date: Tue, 9 Oct 2018 17:36:24 +0300
Subject: perf record: Encode -k clockid frequency into Perf trace

Store -k clockid frequency into Perf trace to enable timestamps
derived metrics conversion into wall clock time on reporting stage.

Below is the example of perf report output:

  tools/perf/perf record -k raw -- ../../matrix/linux/matrix.gcc
  ...
  [ perf record: Captured and wrote 31.222 MB perf.data (818054 samples) ]

  tools/perf/perf report --header
  # ========
  ...
  # event : name = cycles:ppp, , size = 112, { sample_period, sample_freq } = 4000, sample_type = IP|TID|TIME|PERIOD, disabled = 1, inherit = 1, mmap = 1, comm = 1, freq = 1, enable_on_exec = 1, task = 1, precise_ip = 3, sample_id_all = 1, exclude_guest = 1, mmap2 = 1, comm_exec = 1, use_clockid = 1, clockid = 4
  ...
  # clockid frequency: 1000 MHz
  ...
  # ========

Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/23a4a1dc-b160-85a0-347d-40a2ed6d007b@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c | 24 ++++++++++++++++++++++--
 tools/perf/perf.h           |  1 +
 tools/perf/util/env.h       |  1 +
 tools/perf/util/header.c    | 23 +++++++++++++++++++++++
 tools/perf/util/header.h    |  1 +
 5 files changed, 48 insertions(+), 2 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0980dfe3396b..10cf889c6d75 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -592,6 +592,9 @@ static void record__init_features(struct record *rec)
 	if (!rec->opts.full_auxtrace)
 		perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
 
+	if (!(rec->opts.use_clockid && rec->opts.clockid_res_ns))
+		perf_header__clear_feat(&session->header, HEADER_CLOCKID);
+
 	perf_header__clear_feat(&session->header, HEADER_STAT);
 }
 
@@ -897,6 +900,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	record__init_features(rec);
 
+	if (rec->opts.use_clockid && rec->opts.clockid_res_ns)
+		session->header.env.clockid_res_ns = rec->opts.clockid_res_ns;
+
 	if (forks) {
 		err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
 						    argv, data->is_pipe,
@@ -1337,6 +1343,19 @@ static const struct clockid_map clockids[] = {
 	CLOCKID_END,
 };
 
+static int get_clockid_res(clockid_t clk_id, u64 *res_ns)
+{
+	struct timespec res;
+
+	*res_ns = 0;
+	if (!clock_getres(clk_id, &res))
+		*res_ns = res.tv_nsec + res.tv_sec * NSEC_PER_SEC;
+	else
+		pr_warning("WARNING: Failed to determine specified clock resolution.\n");
+
+	return 0;
+}
+
 static int parse_clockid(const struct option *opt, const char *str, int unset)
 {
 	struct record_opts *opts = (struct record_opts *)opt->value;
@@ -1360,7 +1379,7 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
 
 	/* if its a number, we're done */
 	if (sscanf(str, "%d", &opts->clockid) == 1)
-		return 0;
+		return get_clockid_res(opts->clockid, &opts->clockid_res_ns);
 
 	/* allow a "CLOCK_" prefix to the name */
 	if (!strncasecmp(str, "CLOCK_", 6))
@@ -1369,7 +1388,8 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
 	for (cm = clockids; cm->name; cm++) {
 		if (!strcasecmp(str, cm->name)) {
 			opts->clockid = cm->clockid;
-			return 0;
+			return get_clockid_res(opts->clockid,
+					       &opts->clockid_res_ns);
 		}
 	}
 
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 21bf7f5a3cf5..0ed4a34c74c4 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -81,6 +81,7 @@ struct record_opts {
 	unsigned     initial_delay;
 	bool         use_clockid;
 	clockid_t    clockid;
+	u64          clockid_res_ns;
 	unsigned int proc_map_timeout;
 };
 
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 1f3ccc368530..d01b8355f4ca 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -63,6 +63,7 @@ struct perf_env {
 	struct numa_node	*numa_nodes;
 	struct memory_node	*memory_nodes;
 	unsigned long long	 memory_bsize;
+	u64                     clockid_res_ns;
 };
 
 extern struct perf_env perf_env;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 1ec1d9bc2d63..4fd45be95a43 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1034,6 +1034,13 @@ static int write_auxtrace(struct feat_fd *ff,
 	return err;
 }
 
+static int write_clockid(struct feat_fd *ff,
+			 struct perf_evlist *evlist __maybe_unused)
+{
+	return do_write(ff, &ff->ph->env.clockid_res_ns,
+			sizeof(ff->ph->env.clockid_res_ns));
+}
+
 static int cpu_cache_level__sort(const void *a, const void *b)
 {
 	struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a;
@@ -1508,6 +1515,12 @@ static void print_cpu_topology(struct feat_fd *ff, FILE *fp)
 		fprintf(fp, "# Core ID and Socket ID information is not available\n");
 }
 
+static void print_clockid(struct feat_fd *ff, FILE *fp)
+{
+	fprintf(fp, "# clockid frequency: %"PRIu64" MHz\n",
+		ff->ph->env.clockid_res_ns * 1000);
+}
+
 static void free_event_desc(struct perf_evsel *events)
 {
 	struct perf_evsel *evsel;
@@ -2531,6 +2544,15 @@ out:
 	return ret;
 }
 
+static int process_clockid(struct feat_fd *ff,
+			   void *data __maybe_unused)
+{
+	if (do_read_u64(ff, &ff->ph->env.clockid_res_ns))
+		return -1;
+
+	return 0;
+}
+
 struct feature_ops {
 	int (*write)(struct feat_fd *ff, struct perf_evlist *evlist);
 	void (*print)(struct feat_fd *ff, FILE *fp);
@@ -2590,6 +2612,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPN(CACHE,		cache,		true),
 	FEAT_OPR(SAMPLE_TIME,	sample_time,	false),
 	FEAT_OPR(MEM_TOPOLOGY,	mem_topology,	true),
+	FEAT_OPR(CLOCKID,       clockid,        false)
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index e17903caa71d..0d553ddca0a3 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -38,6 +38,7 @@ enum {
 	HEADER_CACHE,
 	HEADER_SAMPLE_TIME,
 	HEADER_MEM_TOPOLOGY,
+	HEADER_CLOCKID,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
-- 
cgit v1.2.3-58-ga151


From 0ab41886648bb75b951bd41d8b5cecaca8e0ad66 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Tue, 16 Oct 2018 20:55:55 -0700
Subject: perf annotate: Add Sparc support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

E.g.:

  $ perf annotate --stdio2
  Samples: 7K of event 'cycles:ppp', 4000 Hz, Event count (approx.): 3086733887
  __gettimeofday  /lib32/libc-2.27.so [Percent: local period]
  Percent│
         │
         │
         │    Disassembly of section .text:
         │
         │    000a6fa0 <__gettimeofday@@GLIBC_2.0>:
    0.47 │      save   %sp, -96, %sp
    0.73 │      sethi  %hi(0xe9000), %l7
         │    → call   __frame_state_for@@GLIBC_2.0+0x480
    0.30 │      add    %l7, 0x58, %l7     ! e9058 <nftw64@@GLIBC_2.3.3+0x818>
    1.33 │      mov    %i0, %o0
         │      mov    %i1, %o1
    0.43 │      mov    0x74, %g1
         │      ta     0x10
   88.92 │    ↓ bcc    30
    2.95 │      clr    %g1
         │      neg    %o0
         │      mov    1, %g1
    0.31 │30:   cmp    %g1, 0
         │      bne,pn %icc, a6fe4 <__gettimeofday@@GLIBC_2.0+0x44>
         │      mov    %o0, %i0
    1.96 │    ← return %i7 + 8
    2.62 │      nop
         │      sethi  %hi(0), %g1
         │      neg    %o0, %g2
         │      add    %g1, 0x160, %g1
         │      ld     [ %l7 + %g1 ], %g1
         │      st     %g2, [ %g7 + %g1 ]
         │    ← return %i7 + 8
         │      mov    -1, %o0

Signed-off-by: David S. Miller <davem@davemloft.net>
Link: http://lkml.kernel.org/r/20181016.205555.1070918198627611771.davem@davemloft.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/sparc/annotate/instructions.c | 169 ++++++++++++++++++++++++++
 tools/perf/util/annotate.c                    |   8 ++
 2 files changed, 177 insertions(+)
 create mode 100644 tools/perf/arch/sparc/annotate/instructions.c

(limited to 'tools/perf')

diff --git a/tools/perf/arch/sparc/annotate/instructions.c b/tools/perf/arch/sparc/annotate/instructions.c
new file mode 100644
index 000000000000..2614c010c235
--- /dev/null
+++ b/tools/perf/arch/sparc/annotate/instructions.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+
+static int is_branch_cond(const char *cond)
+{
+	if (cond[0] == '\0')
+		return 1;
+
+	if (cond[0] == 'a' && cond[1] == '\0')
+		return 1;
+
+	if (cond[0] == 'c' &&
+	    (cond[1] == 'c' || cond[1] == 's') &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'e' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 'q' && cond[2] == '\0')))
+		return 1;
+
+	if (cond[0] == 'g' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 't' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == 'u' && cond[3] == '\0')))
+		return 1;
+
+	if (cond[0] == 'l' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 't' && cond[2] == '\0') ||
+	     (cond[1] == 'u' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == 'u' && cond[3] == '\0')))
+		return 1;
+
+	if (cond[0] == 'n' &&
+	    (cond[1] == '\0' ||
+	     (cond[1] == 'e' && cond[2] == '\0') ||
+	     (cond[1] == 'z' && cond[2] == '\0') ||
+	     (cond[1] == 'e' && cond[2] == 'g' && cond[3] == '\0')))
+		return 1;
+
+	if (cond[0] == 'b' &&
+	    cond[1] == 'p' &&
+	    cond[2] == 'o' &&
+	    cond[3] == 's' &&
+	    cond[4] == '\0')
+		return 1;
+
+	if (cond[0] == 'v' &&
+	    (cond[1] == 'c' || cond[1] == 's') &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'b' &&
+	    cond[1] == 'z' &&
+	    cond[2] == '\0')
+		return 1;
+
+	return 0;
+}
+
+static int is_branch_reg_cond(const char *cond)
+{
+	if ((cond[0] == 'n' || cond[0] == 'l') &&
+	    cond[1] == 'z' &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'z' &&
+	    cond[1] == '\0')
+		return 1;
+
+	if ((cond[0] == 'g' || cond[0] == 'l') &&
+	    cond[1] == 'e' &&
+	    cond[2] == 'z' &&
+	    cond[3] == '\0')
+		return 1;
+
+	if (cond[0] == 'g' &&
+	    cond[1] == 'z' &&
+	    cond[2] == '\0')
+		return 1;
+
+	return 0;
+}
+
+static int is_branch_float_cond(const char *cond)
+{
+	if (cond[0] == '\0')
+		return 1;
+
+	if ((cond[0] == 'a' || cond[0] == 'e' ||
+	     cond[0] == 'z' || cond[0] == 'g' ||
+	     cond[0] == 'l' || cond[0] == 'n' ||
+	     cond[0] == 'o' || cond[0] == 'u') &&
+	    cond[1] == '\0')
+		return 1;
+
+	if (((cond[0] == 'g' && cond[1] == 'e') ||
+	     (cond[0] == 'l' && (cond[1] == 'e' ||
+				 cond[1] == 'g')) ||
+	     (cond[0] == 'n' && (cond[1] == 'e' ||
+				 cond[1] == 'z')) ||
+	     (cond[0] == 'u' && (cond[1] == 'e' ||
+				 cond[1] == 'g' ||
+				 cond[1] == 'l'))) &&
+	    cond[2] == '\0')
+		return 1;
+
+	if (cond[0] == 'u' &&
+	    (cond[1] == 'g' || cond[1] == 'l') &&
+	    cond[2] == 'e' &&
+	    cond[3] == '\0')
+		return 1;
+
+	return 0;
+}
+
+static struct ins_ops *sparc__associate_instruction_ops(struct arch *arch, const char *name)
+{
+	struct ins_ops *ops = NULL;
+
+	if (!strcmp(name, "call") ||
+	    !strcmp(name, "jmp") ||
+	    !strcmp(name, "jmpl")) {
+		ops = &call_ops;
+	} else if (!strcmp(name, "ret") ||
+		   !strcmp(name, "retl") ||
+		   !strcmp(name, "return")) {
+		ops = &ret_ops;
+	} else if (!strcmp(name, "mov")) {
+		ops = &mov_ops;
+	} else {
+		if (name[0] == 'c' &&
+		    (name[1] == 'w' || name[1] == 'x'))
+			name += 2;
+
+		if (name[0] == 'b') {
+			const char *cond = name + 1;
+
+			if (cond[0] == 'r') {
+				if (is_branch_reg_cond(cond + 1))
+					ops = &jump_ops;
+			} else if (is_branch_cond(cond)) {
+				ops = &jump_ops;
+			}
+		} else if (name[0] == 'f' && name[1] == 'b') {
+			if (is_branch_float_cond(name + 2))
+				ops = &jump_ops;
+		}
+	}
+
+	if (ops)
+		arch__associate_ins_ops(arch, name, ops);
+
+	return ops;
+}
+
+static int sparc__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
+{
+	if (!arch->initialized) {
+		arch->initialized = true;
+		arch->associate_instruction_ops = sparc__associate_instruction_ops;
+		arch->objdump.comment_char = '#';
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 28cd6a17491b..6936daf89ddd 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -139,6 +139,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i
 #include "arch/x86/annotate/instructions.c"
 #include "arch/powerpc/annotate/instructions.c"
 #include "arch/s390/annotate/instructions.c"
+#include "arch/sparc/annotate/instructions.c"
 
 static struct arch architectures[] = {
 	{
@@ -170,6 +171,13 @@ static struct arch architectures[] = {
 			.comment_char = '#',
 		},
 	},
+	{
+		.name = "sparc",
+		.init = sparc__annotate_init,
+		.objdump = {
+			.comment_char = '#',
+		},
+	},
 };
 
 static void ins__delete(struct ins_operands *ops)
-- 
cgit v1.2.3-58-ga151


From d87b9790b3deb7601872d34fd05af3da78147583 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Tue, 16 Oct 2018 21:15:45 -0700
Subject: perf jitdump: Add Sparc support.

Signed-off-by: David S. Miller <davem@davemloft.net>
Link: http://lkml.kernel.org/r/20181016.211545.1487970139012324624.davem@davemloft.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/sparc/Makefile | 2 ++
 tools/perf/util/genelf.h       | 6 ++++++
 2 files changed, 8 insertions(+)

(limited to 'tools/perf')

diff --git a/tools/perf/arch/sparc/Makefile b/tools/perf/arch/sparc/Makefile
index 7fbca175099e..275dea7ff59a 100644
--- a/tools/perf/arch/sparc/Makefile
+++ b/tools/perf/arch/sparc/Makefile
@@ -1,3 +1,5 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
+
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index de322d51c7fe..b72440bf9a79 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -29,6 +29,12 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
 #elif defined(__powerpc__)
 #define GEN_ELF_ARCH	EM_PPC
 #define GEN_ELF_CLASS	ELFCLASS32
+#elif defined(__sparc__) && defined(__arch64__)
+#define GEN_ELF_ARCH	EM_SPARCV9
+#define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__sparc__)
+#define GEN_ELF_ARCH	EM_SPARC
+#define GEN_ELF_CLASS	ELFCLASS32
 #else
 #error "unsupported architecture"
 #endif
-- 
cgit v1.2.3-58-ga151


From d6afa561e1471ccfdaf7191230c0c59a37e45a5b Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Wed, 17 Oct 2018 12:08:59 -0700
Subject: perf symbols: Set PLT entry/header sizes properly on Sparc

Using the sh_entsize for both values isn't correct.  It happens to be
correct on x86...

For both 32-bit and 64-bit sparc, there are four PLT entries in the PLT
section.

Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexis Berlemont <alexis.berlemont@gmail.com>
Cc: David Tolnay <dtolnay@gmail.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Hemant Kumar <hemant@linux.vnet.ibm.com>
Cc: Li Bin <huawei.libin@huawei.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: zhangmengting@huawei.com
Fixes: b2f7605076d6 ("perf symbols: Fix plt entry calculation for ARM and AARCH64")
Link: http://lkml.kernel.org/r/20181017.120859.2268840244308635255.davem@davemloft.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/symbol-elf.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

(limited to 'tools/perf')

diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 29770ea61768..6e70cc00c161 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -324,7 +324,17 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss)
 			plt_entry_size = 16;
 			break;
 
-		default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/sparc/xtensa need to be checked */
+		case EM_SPARC:
+			plt_header_size = 48;
+			plt_entry_size = 12;
+			break;
+
+		case EM_SPARCV9:
+			plt_header_size = 128;
+			plt_entry_size = 32;
+			break;
+
+		default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/xtensa need to be checked */
 			plt_header_size = shdr_plt.sh_entsize;
 			plt_entry_size = shdr_plt.sh_entsize;
 			break;
-- 
cgit v1.2.3-58-ga151


From 389373d3306553896a9e218493e5b6175c844eb0 Mon Sep 17 00:00:00 2001
From: Hongxu Jia <hongxu.jia@windriver.com>
Date: Thu, 18 Oct 2018 16:26:13 +0800
Subject: perf arm64: Fix generate system call table failed with /tmp mounted
 with noexec
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When /tmp is mounted with noexec, mksyscalltbl fails.

  [snip]
  |perf-1.0/tools/perf/arch/arm64/entry/syscalls//mksyscalltbl:
  /tmp/create-table-6VGPSt: Permission denied
  [snip]

Add variable TMPDIR as prefix dir of the temporary file, if it is set,
replace default /tmp.

Signed-off-by: Hongxu Jia <hongxu.jia@windriver.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Sébastien Boisvert <sboisvert@gydle.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Fixes: 2b5882435606 ("perf arm64: Generate system call table from asm/unistd.h")
LPU-Reference: 1539851173-14959-1-git-send-email-hongxu.jia@windriver.com
Link: https://lkml.kernel.org/n/tip-1qrgq840ci0c5cy4oww957ge@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm64/entry/syscalls/mksyscalltbl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/perf')

diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
index 2dbb8cade048..c88fd32563eb 100755
--- a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
+++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
@@ -23,7 +23,7 @@ create_table_from_c()
 {
 	local sc nr last_sc
 
-	create_table_exe=`mktemp /tmp/create-table-XXXXXX`
+	create_table_exe=`mktemp ${TMPDIR:-/tmp}/create-table-XXXXXX`
 
 	{
 
-- 
cgit v1.2.3-58-ga151


From 5067a8cdd4ce3588fca2e0ee554f0f081650de8f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 18 Oct 2018 16:38:27 -0300
Subject: perf trace: Introduce --max-events
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Allow stopping tracing after a number of events take place, considering
strace-like syscalls formatting as one event per enter/exit pair or when
in a multi-process tracing session a syscall is interrupted and printed
ending with '...'.

Examples included in the documentation:

Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):

  $ perf trace -e open* --max-events 4
  [root@jouet perf]# trace -e open* --max-events 4
  2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
  2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
  3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
  4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
  $

Trace the first minor page fault when running a workload:

  # perf trace -F min --max-stack=7 --max-events 1 sleep 1
     0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
                                       __clear_user ([kernel.kallsyms])
                                       load_elf_binary ([kernel.kallsyms])
                                       search_binary_handler ([kernel.kallsyms])
                                       __do_execve_file.isra.33 ([kernel.kallsyms])
                                       __x64_sys_execve ([kernel.kallsyms])
                                       do_syscall_64 ([kernel.kallsyms])
                                       entry_SYSCALL_64 ([kernel.kallsyms])
  #

Trace the next min page page fault to take place on the first CPU:

  # perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
     0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
                                       js::gc::FreeSpan::initAsEmpty (inlined)
                                       js::gc::Arena::setAsNotAllocated (inlined)
                                       js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
                                       js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
                                       js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
                                       js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
                                       js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
                                       js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
                                       js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
                                       JSThinInlineString::new_<(js::AllowGC)1> (inlined)
                                       AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
                                       js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
                                       [0x18b26e6bc2bd] (/tmp/perf-17136.map)

Tracing the next four ext4 operations on a specific CPU:

  # perf trace -e ext4:*/call-graph=fp/ --max-events 4 --cpu 3
     0.000 mutt/3849 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 57277 lblk 0
                                       ext4_es_lookup_extent ([kernel.kallsyms])
                                       read (/usr/lib64/libc-2.26.so)
     0.097 mutt/3849 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 57277 found 0 [0/0) 0
                                       ext4_es_lookup_extent ([kernel.kallsyms])
                                       read (/usr/lib64/libc-2.26.so)
     0.141 mutt/3849 ext4:ext4_ext_map_blocks_enter:dev 253,2 ino 57277 lblk 0 len 1 flags
                                       ext4_ext_map_blocks ([kernel.kallsyms])
                                       read (/usr/lib64/libc-2.26.so)
     0.184 mutt/3849 ext4:ext4_ext_load_extent:dev 253,2 ino 57277 lblk 1516511 pblk 18446744071750013657
                                       __read_extent_tree_block ([kernel.kallsyms])
                                       __read_extent_tree_block ([kernel.kallsyms])
                                       ext4_find_extent ([kernel.kallsyms])
                                       ext4_ext_map_blocks ([kernel.kallsyms])
                                       ext4_map_blocks ([kernel.kallsyms])
                                       ext4_mpage_readpages ([kernel.kallsyms])
                                       read_pages ([kernel.kallsyms])
                                       __do_page_cache_readahead ([kernel.kallsyms])
                                       ondemand_readahead ([kernel.kallsyms])
                                       generic_file_read_iter ([kernel.kallsyms])
                                       __vfs_read ([kernel.kallsyms])
                                       vfs_read ([kernel.kallsyms])
                                       ksys_read ([kernel.kallsyms])
                                       do_syscall_64 ([kernel.kallsyms])
                                       entry_SYSCALL_64 ([kernel.kallsyms])
                                       read (/usr/lib64/libc-2.26.so)
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Rudá Moura <ruda.moura@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-sweh107bs7ol5bzls0m4tqdz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-trace.txt | 47 +++++++++++++++++++++++++++++++++
 tools/perf/builtin-trace.c              | 21 +++++++++++++++
 2 files changed, 68 insertions(+)

(limited to 'tools/perf')

diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 115db9e06ecd..0d1a1cd4d328 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -171,6 +171,11 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --kernel-syscall-graph::
 	 Show the kernel callchains on the syscall exit path.
 
+--max-events=N::
+	Stop after processing N events. Note that strace-like events are considered
+	only at exit time or when a syscall is interrupted, i.e. in those cases this
+	option is equivalent to the number of lines printed.
+
 --max-stack::
         Set the stack depth limit when parsing the callchain, anything
         beyond the specified depth will be ignored. Note that at this point
@@ -238,6 +243,48 @@ Trace syscalls, major and minor pagefaults:
   As you can see, there was major pagefault in python process, from
   CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so.
 
+Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
+
+  $ perf trace -e open* --max-events 4
+  [root@jouet perf]# trace -e open* --max-events 4
+  2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
+  2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
+  3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
+  4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
+  $
+
+Trace the first minor page fault when running a workload:
+
+  # perf trace -F min --max-stack=7 --max-events 1 sleep 1
+     0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
+                                       __clear_user ([kernel.kallsyms])
+                                       load_elf_binary ([kernel.kallsyms])
+                                       search_binary_handler ([kernel.kallsyms])
+                                       __do_execve_file.isra.33 ([kernel.kallsyms])
+                                       __x64_sys_execve ([kernel.kallsyms])
+                                       do_syscall_64 ([kernel.kallsyms])
+                                       entry_SYSCALL_64 ([kernel.kallsyms])
+  #
+
+Trace the next min page page fault to take place on the first CPU:
+
+  # perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
+     0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
+                                       js::gc::FreeSpan::initAsEmpty (inlined)
+                                       js::gc::Arena::setAsNotAllocated (inlined)
+                                       js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
+                                       js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
+                                       js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
+                                       js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
+                                       JSThinInlineString::new_<(js::AllowGC)1> (inlined)
+                                       AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
+                                       js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
+                                       [0x18b26e6bc2bd] (/tmp/perf-17136.map)
+  #
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script[1]
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 90289f31dd87..74638034861c 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -89,6 +89,8 @@ struct trace {
 	u64			base_time;
 	FILE			*output;
 	unsigned long		nr_events;
+	unsigned long		nr_events_printed;
+	unsigned long		max_events;
 	struct strlist		*ev_qualifier;
 	struct {
 		size_t		nr;
@@ -1664,6 +1666,8 @@ static int trace__printf_interrupted_entry(struct trace *trace)
 	printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str);
 	ttrace->entry_pending = false;
 
+	++trace->nr_events_printed;
+
 	return printed;
 }
 
@@ -1940,6 +1944,13 @@ errno_print: {
 
 	fputc('\n', trace->output);
 
+	/*
+	 * We only consider an 'event' for the sake of --max-events a non-filtered
+	 * sys_enter + sys_exit and other tracepoint events.
+	 */
+	if (++trace->nr_events_printed == trace->max_events && trace->max_events != ULONG_MAX)
+		interrupted = true;
+
 	if (callchain_ret > 0)
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
@@ -2072,6 +2083,7 @@ static void bpf_output__fprintf(struct trace *trace,
 {
 	binary__fprintf(sample->raw_data, sample->raw_size, 8,
 			bpf_output__printer, NULL, trace->output);
+	++trace->nr_events_printed;
 }
 
 static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
@@ -2127,6 +2139,7 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 			event_format__fprintf(evsel->tp_format, sample->cpu,
 					      sample->raw_data, sample->raw_size,
 					      trace->output);
+			++trace->nr_events_printed;
 		}
 	}
 
@@ -2225,6 +2238,8 @@ static int trace__pgfault(struct trace *trace,
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
 		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
+
+	++trace->nr_events_printed;
 out:
 	err = 0;
 out_put:
@@ -2402,6 +2417,9 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st
 		tracepoint_handler handler = evsel->handler;
 		handler(trace, evsel, event, sample);
 	}
+
+	if (trace->nr_events_printed >= trace->max_events && trace->max_events != ULONG_MAX)
+		interrupted = true;
 }
 
 static int trace__add_syscall_newtp(struct trace *trace)
@@ -3249,6 +3267,7 @@ int cmd_trace(int argc, const char **argv)
 		.trace_syscalls = false,
 		.kernel_syscallchains = false,
 		.max_stack = UINT_MAX,
+		.max_events = ULONG_MAX,
 	};
 	const char *output_name = NULL;
 	const struct option trace_options[] = {
@@ -3301,6 +3320,8 @@ int cmd_trace(int argc, const char **argv)
 		     &record_parse_callchain_opt),
 	OPT_BOOLEAN(0, "kernel-syscall-graph", &trace.kernel_syscallchains,
 		    "Show the kernel callchains on the syscall exit path"),
+	OPT_ULONG(0, "max-events", &trace.max_events,
+		"Set the maximum number of events to print, exit after that is reached. "),
 	OPT_UINTEGER(0, "min-stack", &trace.min_stack,
 		     "Set the minimum stack depth when parsing the callchain, "
 		     "anything below the specified depth will be ignored."),
-- 
cgit v1.2.3-58-ga151


From 2fda5ada07f36f6cde39a52e7f05d86ea8ffdc33 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 19 Oct 2018 15:47:34 -0300
Subject: perf evsel: Introduce per event max_events property

This simply adds the field to 'struct perf_evsel' and allows setting
it via the event parser, to test it lets trace trace:

First look at where in a function that receives an evsel we can put a probe
to read how evsel->max_events was setup:

  # perf probe -x ~/bin/perf -L trace__event_handler
  <trace__event_handler@/home/acme/git/perf/tools/perf/builtin-trace.c:0>
        0  static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
                                          union perf_event *event __maybe_unused,
                                          struct perf_sample *sample)
        3  {
        4         struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
        5         int callchain_ret = 0;

        7         if (sample->callchain) {
        8                 callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
        9                 if (callchain_ret == 0) {
       10                         if (callchain_cursor.nr < trace->min_stack)
       11                                 goto out;
       12                         callchain_ret = 1;
                          }
                  }

See what variables we can probe at line 7:

  # perf probe -x ~/bin/perf -V trace__event_handler:7
  Available variables at trace__event_handler:7
          @<trace__event_handler+89>
                  int     callchain_ret
                  struct perf_evsel*      evsel
                  struct perf_sample*     sample
                  struct thread*  thread
                  struct trace*   trace
                  union perf_event*       event

Add a probe at that line asking for evsel->max_events to be collected and named
as "max_events":

  # perf probe -x ~/bin/perf trace__event_handler:7 'max_events=evsel->max_events'
  Added new event:
    probe_perf:trace__event_handler (on trace__event_handler:7 in /home/acme/bin/perf with max_events=evsel->max_events)

  You can now use it in all perf tools, such as:

  	perf record -e probe_perf:trace__event_handler -aR sleep 1

Now use 'perf trace', here aliased to just 'trace' and trace trace, i.e.
the first 'trace' is tracing just that 'probe_perf:trace__event_handler' event,
while the traced trace is tracing all scheduler tracepoints, will stop at two
events (--max-events 2) and will just set evsel->max_events for all the sched
tracepoints to 9, we will see the output of both traces intermixed:

  # trace -e *perf:*event_handler trace --max-events 2 -e sched:*/nr=9/
       0.000 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=000
       0.009 :0/0 sched:sched_wakeup:comm=rcu_sched pid=10 prio=120 target_cpu=000
       0.000 trace/23949 probe_perf:trace__event_handler:(48c34a) max_events=0x9
       0.046 trace/23949 probe_perf:trace__event_handler:(48c34a) max_events=0x9
  #

Now, if the traced trace sends its output to /dev/null, we'll see just
what the first level trace outputs: that evsel->max_events is indeed
being set to 9:

  # trace -e *perf:*event_handler trace -o /dev/null --max-events 2 -e sched:*/nr=9/
       0.000 trace/23961 probe_perf:trace__event_handler:(48c34a) max_events=0x9
       0.030 trace/23961 probe_perf:trace__event_handler:(48c34a) max_events=0x9
  #

Now that we can set evsel->max_events, we can go to the next step, honour that
per-event property in 'perf trace'.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-og00yasj276joem6e14l1eas@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.c        | 4 ++++
 tools/perf/util/evsel.h        | 3 +++
 tools/perf/util/parse-events.c | 8 ++++++++
 tools/perf/util/parse-events.h | 1 +
 tools/perf/util/parse-events.l | 1 +
 5 files changed, 17 insertions(+)

(limited to 'tools/perf')

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 29d7b97f66fb..7e95ec1c19a8 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -232,6 +232,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->leader	   = evsel;
 	evsel->unit	   = "";
 	evsel->scale	   = 1.0;
+	evsel->max_events  = ULONG_MAX;
 	evsel->evlist	   = NULL;
 	evsel->bpf_fd	   = -1;
 	INIT_LIST_HEAD(&evsel->node);
@@ -793,6 +794,9 @@ static void apply_config_terms(struct perf_evsel *evsel,
 		case PERF_EVSEL__CONFIG_TERM_MAX_STACK:
 			max_stack = term->val.max_stack;
 			break;
+		case PERF_EVSEL__CONFIG_TERM_MAX_EVENTS:
+			evsel->max_events = term->val.max_events;
+			break;
 		case PERF_EVSEL__CONFIG_TERM_INHERIT:
 			/*
 			 * attr->inherit should has already been set by
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4107c39f4a54..ad5d615c6db6 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -46,6 +46,7 @@ enum term_type {
 	PERF_EVSEL__CONFIG_TERM_STACK_USER,
 	PERF_EVSEL__CONFIG_TERM_INHERIT,
 	PERF_EVSEL__CONFIG_TERM_MAX_STACK,
+	PERF_EVSEL__CONFIG_TERM_MAX_EVENTS,
 	PERF_EVSEL__CONFIG_TERM_OVERWRITE,
 	PERF_EVSEL__CONFIG_TERM_DRV_CFG,
 	PERF_EVSEL__CONFIG_TERM_BRANCH,
@@ -65,6 +66,7 @@ struct perf_evsel_config_term {
 		bool	inherit;
 		bool	overwrite;
 		char	*branch;
+		unsigned long max_events;
 	} val;
 	bool weak;
 };
@@ -99,6 +101,7 @@ struct perf_evsel {
 	struct perf_counts	*prev_raw_counts;
 	int			idx;
 	u32			ids;
+	unsigned long		max_events;
 	char			*name;
 	double			scale;
 	const char		*unit;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f8cd3e7c9186..59be3466d64d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -926,6 +926,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
 	[PARSE_EVENTS__TERM_TYPE_NOINHERIT]		= "no-inherit",
 	[PARSE_EVENTS__TERM_TYPE_INHERIT]		= "inherit",
 	[PARSE_EVENTS__TERM_TYPE_MAX_STACK]		= "max-stack",
+	[PARSE_EVENTS__TERM_TYPE_MAX_EVENTS]		= "nr",
 	[PARSE_EVENTS__TERM_TYPE_OVERWRITE]		= "overwrite",
 	[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]		= "no-overwrite",
 	[PARSE_EVENTS__TERM_TYPE_DRV_CFG]		= "driver-config",
@@ -1037,6 +1038,9 @@ do {									   \
 	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
 		CHECK_TYPE_VAL(NUM);
 		break;
+	case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+		CHECK_TYPE_VAL(NUM);
+		break;
 	default:
 		err->str = strdup("unknown term");
 		err->idx = term->err_term;
@@ -1084,6 +1088,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	case PARSE_EVENTS__TERM_TYPE_INHERIT:
 	case PARSE_EVENTS__TERM_TYPE_NOINHERIT:
 	case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
+	case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
 	case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
 	case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
 		return config_term_common(attr, term, err);
@@ -1162,6 +1167,9 @@ do {								\
 		case PARSE_EVENTS__TERM_TYPE_MAX_STACK:
 			ADD_CONFIG_TERM(MAX_STACK, max_stack, term->val.num);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
+			ADD_CONFIG_TERM(MAX_EVENTS, max_events, term->val.num);
+			break;
 		case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
 			ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 1 : 0);
 			break;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 4473dac27aee..5ed035cbcbb7 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -71,6 +71,7 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_NOINHERIT,
 	PARSE_EVENTS__TERM_TYPE_INHERIT,
 	PARSE_EVENTS__TERM_TYPE_MAX_STACK,
+	PARSE_EVENTS__TERM_TYPE_MAX_EVENTS,
 	PARSE_EVENTS__TERM_TYPE_NOOVERWRITE,
 	PARSE_EVENTS__TERM_TYPE_OVERWRITE,
 	PARSE_EVENTS__TERM_TYPE_DRV_CFG,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 5f761f3ed0f3..7805c71aaae2 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -269,6 +269,7 @@ time			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_TIME); }
 call-graph		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CALLGRAPH); }
 stack-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_STACKSIZE); }
 max-stack		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_STACK); }
+nr			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_EVENTS); }
 inherit			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_INHERIT); }
 no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); }
-- 
cgit v1.2.3-58-ga151


From b7e8452b860c299f342a012922bdd9ab8f2bb722 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sat, 20 Oct 2018 09:04:41 -0300
Subject: perf evsel: Mark a evsel as disabled when asking the kernel do
 disable it

Because there may be more such events in the ring buffer that should be
discarded when an app decides to stop considering them.

At some point we'll do this with eBPF, this way we stop them at origin,
before they are placed in the ring buffer.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-uzufuxws4hufigx07ue1dpv6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evlist.c |  2 +-
 tools/perf/util/evsel.c  | 23 +++++++++++++++++------
 tools/perf/util/evsel.h  |  1 +
 3 files changed, 19 insertions(+), 7 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index be440df29615..e88e6f9b1463 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -358,7 +358,7 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 	struct perf_evsel *pos;
 
 	evlist__for_each_entry(evlist, pos) {
-		if (!perf_evsel__is_group_leader(pos) || !pos->fd)
+		if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->fd)
 			continue;
 		perf_evsel__disable(pos);
 	}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7e95ec1c19a8..6d187059a373 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1207,16 +1207,27 @@ int perf_evsel__append_addr_filter(struct perf_evsel *evsel, const char *filter)
 
 int perf_evsel__enable(struct perf_evsel *evsel)
 {
-	return perf_evsel__run_ioctl(evsel,
-				     PERF_EVENT_IOC_ENABLE,
-				     0);
+	int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0);
+
+	if (!err)
+		evsel->disabled = false;
+
+	return err;
 }
 
 int perf_evsel__disable(struct perf_evsel *evsel)
 {
-	return perf_evsel__run_ioctl(evsel,
-				     PERF_EVENT_IOC_DISABLE,
-				     0);
+	int err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0);
+	/*
+	 * We mark it disabled here so that tools that disable a event can
+	 * ignore events after they disable it. I.e. the ring buffer may have
+	 * already a few more events queued up before the kernel got the stop
+	 * request.
+	 */
+	if (!err)
+		evsel->disabled = true;
+
+	return err;
 }
 
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index ad5d615c6db6..4ef50f157b50 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -122,6 +122,7 @@ struct perf_evsel {
 	bool			snapshot;
 	bool 			supported;
 	bool 			needs_swap;
+	bool 			disabled;
 	bool			no_aux_samples;
 	bool			immediate;
 	bool			system_wide;
-- 
cgit v1.2.3-58-ga151


From 4291bf5cb93918232f88a3a70d8f70a72fbb6ab0 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sat, 20 Oct 2018 09:18:50 -0300
Subject: perf trace: Drop addr_location refcounts

When we use machine__resolve() we grab a reference to
addr_location.thread (and in the future to other elements there) via
machine__findnew_thread(), so we must pair that with
addr_location__put(), else we'll never drop that thread when it exits
and no other remaining data structures have pointers to it. Fix it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ivg9hifzeuokb1f5jxc2wob4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 74638034861c..77b8748ad5ed 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1814,12 +1814,14 @@ static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evse
 	int max_stack = evsel->attr.sample_max_stack ?
 			evsel->attr.sample_max_stack :
 			trace->max_stack;
+	int err;
 
-	if (machine__resolve(trace->host, &al, sample) < 0 ||
-	    thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack))
+	if (machine__resolve(trace->host, &al, sample) < 0)
 		return -1;
 
-	return 0;
+	err = thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack);
+	addr_location__put(&al);
+	return err;
 }
 
 static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sample)
-- 
cgit v1.2.3-58-ga151


From a937c6658b8e77e1f65cde2be9970811752121bb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sat, 20 Oct 2018 09:27:52 -0300
Subject: perf trace: Drop thread refcount in trace__event_handler()

We must pair:

   thread = machine__findnew_thread();

with thread__put(thread). Fix it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: c4191e55b874 ("perf trace: Show comm and tid for tracepoint events")
Link: https://lkml.kernel.org/n/tip-dkxsb8cwg87rmkrzrbns1o4z@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/perf')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 77b8748ad5ed..589e0412652a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2152,8 +2152,8 @@ newline:
 		trace__fprintf_callchain(trace, sample);
 	else if (callchain_ret < 0)
 		pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
-	thread__put(thread);
 out:
+	thread__put(thread);
 	return 0;
 }
 
-- 
cgit v1.2.3-58-ga151


From cbb5df7e96070f1f728ff7885443646ebba703d4 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 22 Oct 2018 11:30:15 +0200
Subject: perf stat: Poll for monitored tasks being alive

Adding the check for tasks we monitor via -p/-t options, and finish stat
if there's no longer task to monitor.

Requested-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lkml.kernel.org/r/20181022093015.9106-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'tools/perf')

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index b86aba1c8028..d1028d7755bb 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -409,6 +409,28 @@ static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
 	return leader;
 }
 
+static bool is_target_alive(struct target *_target,
+			    struct thread_map *threads)
+{
+	struct stat st;
+	int i;
+
+	if (!target__has_task(_target))
+		return true;
+
+	for (i = 0; i < threads->nr; i++) {
+		char path[PATH_MAX];
+
+		scnprintf(path, PATH_MAX, "%s/%d", procfs__mountpoint(),
+			  threads->map[i].pid);
+
+		if (!stat(path, &st))
+			return true;
+	}
+
+	return false;
+}
+
 static int __run_perf_stat(int argc, const char **argv, int run_idx)
 {
 	int interval = stat_config.interval;
@@ -579,6 +601,8 @@ try_again:
 		enable_counters();
 		while (!done) {
 			nanosleep(&ts, NULL);
+			if (!is_target_alive(&target, evsel_list->threads))
+				break;
 			if (timeout)
 				break;
 			if (interval) {
-- 
cgit v1.2.3-58-ga151


From c1c9b9695cc8868048f45c7e2559f65bc0be7382 Mon Sep 17 00:00:00 2001
From: Milian Wolff <milian.wolff@kdab.com>
Date: Sun, 21 Oct 2018 21:14:23 +0200
Subject: perf script: Allow extended console debug output

The script tool isn't using a browser, yet use_browser wasn't set
explicitly to zero. This in turn lead to confusing output such as:

  ```
  $ perf script -vvv ...
  ...
  overlapping maps in /home/milian/foobar (disable tui for more info)
  ...
  ```

Explicitly set use_browser to 0 now, which gives us the extended
debug information now in perf script as expected.

Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lkml.kernel.org/r/20181021191424.16183-1-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'tools/perf')

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 4da5e32b9e03..bd468b90801b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3417,8 +3417,10 @@ int cmd_script(int argc, const char **argv)
 		exit(-1);
 	}
 
-	if (!script_name)
+	if (!script_name) {
 		setup_pager();
+		use_browser = 0;
+	}
 
 	session = perf_session__new(&data, false, &script.tool);
 	if (session == NULL)
-- 
cgit v1.2.3-58-ga151


From 7ee40678af935fb489b0c6cf0f75808175214cd7 Mon Sep 17 00:00:00 2001
From: Milian Wolff <milian.wolff@kdab.com>
Date: Sun, 21 Oct 2018 21:14:24 +0200
Subject: perf script: Flush output stream after events in verbose mode

When the perf script output is written to a terminal stream, the normal
output of `perf script` would get buffered, but its debug output would
be written directly. This made it quite hard to figure out where a given
debug output is coming from.

We can improve on this by flushing the output buffer after processing an
event. To see the value, compare the following output for a `perf script
-v` run:

Before this patch:
```
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
unwind: find_proc_info dso /usr/lib/ld-2.28.so
unwind: reg 6, val 0
unwind: _start:ip = 0x7faf7dfdc000 (0x2000)
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
unwind: find_proc_info dso /usr/lib/ld-2.28.so
unwind: reg 6, val 0
unwind: _start:ip = 0x7faf7dfdc000 (0x2000)
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
unwind: find_proc_info dso /usr/lib/ld-2.28.so
unwind: reg 6, val 0
unwind: _start:ip = 0x7faf7dfdc000 (0x2000)
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
... lots and lots of verbose debug output
cpp-inlining 24617 90229.122036534:          1 cycles:uppp:
            7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so)

cpp-inlining 24617 90229.122043974:          1 cycles:uppp:
            7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so)
...
```

After this patch:
```
...
unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
unwind: find_proc_info dso /usr/lib/ld-2.28.so
unwind: reg 6, val 0
unwind: _start:ip = 0x7faf7dfdc000 (0x2000)
cpp-inlining 24617 90229.122036534:          1 cycles:uppp:
            7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so)

unwind: reg 16, val 7faf7dfdc000
unwind: reg 7, val 7ffc80811e30
unwind: find_proc_info dso /usr/lib/ld-2.28.so
unwind: reg 6, val 0
unwind: _start:ip = 0x7faf7dfdc000 (0x2000)
cpp-inlining 24617 90229.122043974:          1 cycles:uppp:
            7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so)
...
```

This new output format makes it much easier to use perf script output
for debugging purposes, e.g. to investigate broken dwarf unwinding.

Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20181021191424.16183-2-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools/perf')

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index bd468b90801b..ca09b7d2adb7 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1737,6 +1737,9 @@ static void process_event(struct perf_script *script,
 
 	if (PRINT_FIELD(METRIC))
 		perf_sample__fprint_metric(script, thread, evsel, sample, fp);
+
+	if (verbose)
+		fflush(fp);
 }
 
 static struct scripting_ops	*scripting_ops;
-- 
cgit v1.2.3-58-ga151


From a9c5e6c1e9bff42ca5f01ceb3092a27a010755fb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 22 Oct 2018 14:14:16 -0300
Subject: perf trace: Introduce per-event maximum number of events property

Call it 'nr', as in this context it should be expressive enough, i.e.:

  # perf trace -e sched:*waking/nr=8,call-graph=fp/
     0.000 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001
                                       try_to_wake_up ([kernel.kallsyms])
                                       sched_clock ([kernel.kallsyms])
     3.933 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001
                                       try_to_wake_up ([kernel.kallsyms])
                                       sched_clock ([kernel.kallsyms])
     3.970 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
                                       try_to_wake_up ([kernel.kallsyms])
                                       __libc_write (/usr/lib64/libpthread-2.26.so)
    20.069 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
                                       try_to_wake_up ([kernel.kallsyms])
                                       __libc_write (/usr/lib64/libpthread-2.26.so)
    37.170 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
                                       try_to_wake_up ([kernel.kallsyms])
                                       __libc_write (/usr/lib64/libpthread-2.26.so)
    53.267 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
                                       try_to_wake_up ([kernel.kallsyms])
                                       __libc_write (/usr/lib64/libpthread-2.26.so)
    70.365 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
                                       try_to_wake_up ([kernel.kallsyms])
                                       __libc_write (/usr/lib64/libpthread-2.26.so)
    75.781 Web Content/3649 sched:sched_waking:comm=JS Helper pid=3670 prio=120 target_cpu=000
                                       try_to_wake_up ([kernel.kallsyms])
                                       try_to_wake_up ([kernel.kallsyms])
                                       wake_up_q ([kernel.kallsyms])
                                       futex_wake ([kernel.kallsyms])
                                       do_futex ([kernel.kallsyms])
                                       __x64_sys_futex ([kernel.kallsyms])
                                       do_syscall_64 ([kernel.kallsyms])
                                       entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
                                       pthread_cond_signal@@GLIBC_2.3.2 (/usr/lib64/libpthread-2.26.so)
  #

  # perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
     0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> trace:3367 [120]
     0.046 :0/0 sched:sched_switch:swapper/1:0 [120] S ==> kworker/u16:58:2722 [120]
   570.670 irq/50-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ef00 len=66
                                       __dev_queue_xmit ([kernel.kallsyms])
  1106.141 jbd2/dm-0-8/476 block:block_plug:[jbd2/dm-0-8]
  1106.175 jbd2/dm-0-8/476 block:block_unplug:[jbd2/dm-0-8] 1
  1618.088 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
  1810.000 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051ef00 len=52
                                       __dev_queue_xmit ([kernel.kallsyms])
  3857.974 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051f900 len=52
                                       __dev_queue_xmit ([kernel.kallsyms])
  4790.277 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
  4790.448 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
  #

The global --max-events has precendence:

  # trace --max-events 3 -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
     0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> qemu-system-x86:2252 [120]
     0.029 qemu-system-x8/2252 sched:sched_switch:qemu-system-x86:2252 [120] D ==> swapper/0:0 [120]
    58.047 DNS Res~er #14/31661 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff9346966af100 len=84
                                       __dev_queue_xmit ([kernel.kallsyms])
                                       __libc_send (/usr/lib64/libpthread-2.26.so)
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-s4jswltvh660ughvg9nwngah@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-trace.txt | 20 ++++++++++++++++++++
 tools/perf/builtin-trace.c              | 19 +++++++++++++++++--
 tools/perf/util/evsel.h                 |  1 +
 3 files changed, 38 insertions(+), 2 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 0d1a1cd4d328..e113450503d2 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -285,6 +285,26 @@ Trace the next min page page fault to take place on the first CPU:
                                        [0x18b26e6bc2bd] (/tmp/perf-17136.map)
   #
 
+Trace the next two sched:sched_switch events, four block:*_plug events, the
+next block:*_unplug and the next three net:*dev_queue events, this last one
+with a backtrace of at most 16 entries, system wide:
+
+  # perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
+     0.000 :0/0 sched:sched_switch:swapper/2:0 [120] S ==> rcu_sched:10 [120]
+     0.015 rcu_sched/10 sched:sched_switch:rcu_sched:10 [120] R ==> swapper/2:0 [120]
+   254.198 irq/50-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=66
+                                       __dev_queue_xmit ([kernel.kallsyms])
+   273.977 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=78
+                                       __dev_queue_xmit ([kernel.kallsyms])
+   274.007 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ff00 len=78
+                                       __dev_queue_xmit ([kernel.kallsyms])
+  2930.140 kworker/u16:58/2722 block:block_plug:[kworker/u16:58]
+  2930.162 kworker/u16:58/2722 block:block_unplug:[kworker/u16:58] 1
+  4466.094 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
+  8050.123 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
+  8050.271 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
+  #
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script[1]
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 589e0412652a..7081d7ea12e5 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2092,8 +2092,18 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 				union perf_event *event __maybe_unused,
 				struct perf_sample *sample)
 {
-	struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+	struct thread *thread;
 	int callchain_ret = 0;
+	/*
+	 * Check if we called perf_evsel__disable(evsel) due to, for instance,
+	 * this event's max_events having been hit and this is an entry coming
+	 * from the ring buffer that we should discard, since the max events
+	 * have already been considered/printed.
+	 */
+	if (evsel->disabled)
+		return 0;
+
+	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 
 	if (sample->callchain) {
 		callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
@@ -2142,6 +2152,11 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 					      sample->raw_data, sample->raw_size,
 					      trace->output);
 			++trace->nr_events_printed;
+
+			if (evsel->max_events != ULONG_MAX && ++evsel->nr_events_printed == evsel->max_events) {
+				perf_evsel__disable(evsel);
+				perf_evsel__close(evsel);
+			}
 		}
 	}
 
@@ -2726,7 +2741,7 @@ next_event:
 		int timeout = done ? 100 : -1;
 
 		if (!draining && perf_evlist__poll(evlist, timeout) > 0) {
-			if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP) == 0)
+			if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP | POLLNVAL) == 0)
 				draining = true;
 
 			goto again;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4ef50f157b50..3147ca76c6fc 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -102,6 +102,7 @@ struct perf_evsel {
 	int			idx;
 	u32			ids;
 	unsigned long		max_events;
+	unsigned long		nr_events_printed;
 	char			*name;
 	double			scale;
 	const char		*unit;
-- 
cgit v1.2.3-58-ga151


From 3e71c70c946b5d5e7b21397c621b14951e5c0fcf Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:35 +0300
Subject: perf scripts python: call-graph-from-sql.py: Use SPDX license
 identifier

Use SPDX license identifier in call-graph-from-sql.py.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-2-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index b494a67a1c67..ce1b91fcd6b8 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -1,15 +1,7 @@
 #!/usr/bin/python2
-# call-graph-from-sql.py: create call-graph from sql database
-# Copyright (c) 2014-2017, Intel Corporation.
-#
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-# more details.
+# SPDX-License-Identifier: GPL-2.0
+# exported-sql-viewer.py: view data from sql database
+# Copyright (c) 2014-2018, Intel Corporation.
 
 # To use this script you will need to have exported data using either the
 # export-to-sqlite.py or the export-to-postgresql.py script.  Refer to those
-- 
cgit v1.2.3-58-ga151


From 1d865c06f5715df94528f76d6bb7f6f98975e04e Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:36 +0300
Subject: perf scripts python: call-graph-from-sql.py: Provide better default
 column sizes

Set initial column sizes to improve initial display.

Committer testing:

Extended instructions on testing this, using the sqlite variant:

Make sure you have the SQLite glue for python+Qt installed, on fedora 27
I used:

  # dnf install python-pyside

Collect some PT samples, say 5-secs worth, system wide:

  # perf record -r 10 -e intel_pt//u -a sleep 5
  [ perf record: Woken up 49 times to write data ]
  [ perf record: Captured and wrote 96.131 MB perf.data ]

This results in this perf.data file:

  # ls -larth perf.data
  -rw-------. 1 root root 97M Oct 23 10:11 perf.data

With the following attributes:

  # perf evlist -v
  intel_pt//u: type: 8, size: 112, config: 0x300e601, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|IDENTIFIER, read_format: ID, disabled: 1, inherit: 1, exclude_kernel: 1, exclude_hv: 1, sample_id_all: 1
  dummy:u: type: 1, size: 112, config: 0x9, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|IDENTIFIER, read_format: ID, inherit: 1, exclude_kernel: 1, exclude_hv: 1, mmap: 1, comm: 1, task: 1, sample_id_all: 1, mmap2: 1, comm_exec: 1, context_switch: 1
  #

Then generate the "pt_example" tables using:

  # perf script -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py pt_example branches calls
  2018-10-23 10:56:59.177711 Creating database...
  2018-10-23 10:56:59.195842 Writing records...
   instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x263984516750 code 5: Failed to get instruction
   instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x7f26e116fd20 code 6: Trace doesn't match instruction
   instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x7f26e162c9ee code 6: Trace doesn't match instruction
   instruction trace error type 1 cpu 2 pid 1644 tid 1644 ip 0x7f26e9ce831a code 6: Trace doesn't match instruction
  <SNIP>
   instruction trace error type 1 cpu 0 pid 1644 tid 1644 ip 0x7f26e13d07b4 code 6: Trace doesn't match instruction
  Warning:
  132 instruction trace errors
  2018-10-23 11:25:25.015717 Adding indexes
  2018-10-23 11:25:28.788061 Done
  #

In my example, that perf.data file generated this db:

  # file pt_example
  pt_example: SQLite 3.x database, last written using SQLite version 3020001
  [root@seventh perf]# ls -lah pt_example
  -rw-r--r--. 1 root root 6.6G Oct 23 11:25 pt_example
  #

Then use this python script to use that db and provide a GUI:

  $ python tools/perf/scripts/python/call-graph-from-sql.py pt_example branches calls

I compared the column widths before this patch and after applying it,
the visual results match the patch intent.

The following patches will refer to this set of instructions in the "Committer
Testing" section.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index ce1b91fcd6b8..e1014f2628a7 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -280,6 +280,9 @@ class MainWindow(QMainWindow):
 		self.view = QTreeView()
 		self.view.setModel(self.model)
 
+		for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
+			self.view.setColumnWidth(c, w)
+
 		self.setCentralWidget(self.view)
 
 if __name__ == '__main__':
-- 
cgit v1.2.3-58-ga151


From 3c4ef451506897a15aff76ff141c995c6cd32f4d Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:37 +0300
Subject: perf scripts python: call-graph-from-sql.py: Set a minimum window
 size

Prevent weirdly small window size.

Committer testing:

Seems to work, but even before this patch, on my system, it always
started with:

xwininfo: Window id: 0x1e00002 "Call Graph: pt_example"
<SNIP>
  Width: 800
  Height: 600
<SNIP>

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-4-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index e1014f2628a7..68153fa1b4d1 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -274,6 +274,7 @@ class MainWindow(QMainWindow):
 		style = self.style()
 		icon = style.standardIcon(QStyle.SP_MessageBoxInformation)
 		self.setWindowIcon(icon);
+		self.setMinimumSize(200, 100)
 
 		self.model = TreeModel(db)
 
-- 
cgit v1.2.3-58-ga151


From 99a097c987c26c8c82293fcb92908d07009c925e Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:38 +0300
Subject: perf scripts python: call-graph-from-sql.py: Change icon

There are not many standard icons, but the computer icon looks slightly
better than the information icon.

Committer testing:

Noticed the change on the icon on the gnome menu right next to the
"Activities" menu, looks nicer indeed.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-5-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 68153fa1b4d1..2e33540f3de0 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -271,9 +271,7 @@ class MainWindow(QMainWindow):
 		self.setWindowTitle("Call Graph: " + dbname)
 		self.move(100, 100)
 		self.resize(800, 600)
-		style = self.style()
-		icon = style.standardIcon(QStyle.SP_MessageBoxInformation)
-		self.setWindowIcon(icon);
+		self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
 		self.setMinimumSize(200, 100)
 
 		self.model = TreeModel(db)
-- 
cgit v1.2.3-58-ga151


From 7e4fc93e2ade2b0c453a97e307203ffe3f930c98 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:39 +0300
Subject: perf scripts python: call-graph-from-sql.py: Make a "Main" function

Make a "Main" function so that the variables used do not pollute the global
namespace.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-6-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 2e33540f3de0..2b74b94eeccc 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -284,7 +284,9 @@ class MainWindow(QMainWindow):
 
 		self.setCentralWidget(self.view)
 
-if __name__ == '__main__':
+# Main
+
+def Main():
 	if (len(sys.argv) < 2):
 		print >> sys.stderr, "Usage is: call-graph-from-sql.py <database name>"
 		raise Exception("Too few arguments")
@@ -331,3 +333,6 @@ if __name__ == '__main__':
 	err = app.exec_()
 	db.close()
 	sys.exit(err)
+
+if __name__ == "__main__":
+	Main()
-- 
cgit v1.2.3-58-ga151


From b2556c46a69b4c0e6bbf690ac4ca2913cbe90e1e Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:40 +0300
Subject: perf scripts python: call-graph-from-sql.py: Separate the database
 details into a class

Separate the database details into a class that can provide different
connections using the same connection information.  That paves the way
for sub-processes that require their own connection.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-7-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 63 ++++++++++++++----------
 1 file changed, 38 insertions(+), 25 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 2b74b94eeccc..9d056deab2b1 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -284,6 +284,42 @@ class MainWindow(QMainWindow):
 
 		self.setCentralWidget(self.view)
 
+# Database reference
+
+class DBRef():
+
+	def __init__(self, is_sqlite3, dbname):
+		self.is_sqlite3 = is_sqlite3
+		self.dbname = dbname
+
+	def Open(self, connection_name):
+		dbname = self.dbname
+		if self.is_sqlite3:
+			db = QSqlDatabase.addDatabase("QSQLITE", connection_name)
+		else:
+			db = QSqlDatabase.addDatabase("QPSQL", connection_name)
+			opts = dbname.split()
+			for opt in opts:
+				if "=" in opt:
+					opt = opt.split("=")
+					if opt[0] == "hostname":
+						db.setHostName(opt[1])
+					elif opt[0] == "port":
+						db.setPort(int(opt[1]))
+					elif opt[0] == "username":
+						db.setUserName(opt[1])
+					elif opt[0] == "password":
+						db.setPassword(opt[1])
+					elif opt[0] == "dbname":
+						dbname = opt[1]
+				else:
+					dbname = opt
+
+		db.setDatabaseName(dbname)
+		if not db.open():
+			raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text())
+		return db, dbname
+
 # Main
 
 def Main():
@@ -302,31 +338,8 @@ def Main():
 	except:
 		pass
 
-	if is_sqlite3:
-		db = QSqlDatabase.addDatabase('QSQLITE')
-	else:
-		db = QSqlDatabase.addDatabase('QPSQL')
-		opts = dbname.split()
-		for opt in opts:
-			if '=' in opt:
-				opt = opt.split('=')
-				if opt[0] == 'hostname':
-					db.setHostName(opt[1])
-				elif opt[0] == 'port':
-					db.setPort(int(opt[1]))
-				elif opt[0] == 'username':
-					db.setUserName(opt[1])
-				elif opt[0] == 'password':
-					db.setPassword(opt[1])
-				elif opt[0] == 'dbname':
-					dbname = opt[1]
-			else:
-				dbname = opt
-
-	db.setDatabaseName(dbname)
-	if not db.open():
-		raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text())
-
+	dbref = DBRef(is_sqlite3, dbname)
+	db, dbname = dbref.Open("main")
 	app = QApplication(sys.argv)
 	window = MainWindow(db, dbname)
 	window.show()
-- 
cgit v1.2.3-58-ga151


From 5f9dfef1bb7fadfb2d001244ef23359982fedd06 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:41 +0300
Subject: perf scripts python: call-graph-from-sql.py: Add a class for global
 data

Keep global data in a single object that is easy to pass around as
needed, without polluting the global namespace.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-8-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 26 +++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 9d056deab2b1..0a4dc13d4818 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -264,17 +264,19 @@ class TreeModel(QAbstractItemModel):
 
 class MainWindow(QMainWindow):
 
-	def __init__(self, db, dbname, parent=None):
+	def __init__(self, glb, parent=None):
 		super(MainWindow, self).__init__(parent)
 
+		self.glb = glb
+
 		self.setObjectName("MainWindow")
-		self.setWindowTitle("Call Graph: " + dbname)
+		self.setWindowTitle("Call Graph: " + glb.dbname)
 		self.move(100, 100)
 		self.resize(800, 600)
 		self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
 		self.setMinimumSize(200, 100)
 
-		self.model = TreeModel(db)
+		self.model = TreeModel(glb.db)
 
 		self.view = QTreeView()
 		self.view.setModel(self.model)
@@ -284,6 +286,17 @@ class MainWindow(QMainWindow):
 
 		self.setCentralWidget(self.view)
 
+# Global data
+
+class Glb():
+
+	def __init__(self, dbref, db, dbname):
+		self.dbref = dbref
+		self.db = db
+		self.dbname = dbname
+		self.app = None
+		self.mainwindow = None
+
 # Database reference
 
 class DBRef():
@@ -340,9 +353,12 @@ def Main():
 
 	dbref = DBRef(is_sqlite3, dbname)
 	db, dbname = dbref.Open("main")
+	glb = Glb(dbref, db, dbname)
 	app = QApplication(sys.argv)
-	window = MainWindow(db, dbname)
-	window.show()
+	glb.app = app
+	mainwindow = MainWindow(glb)
+	glb.mainwindow = mainwindow
+	mainwindow.show()
 	err = app.exec_()
 	db.close()
 	sys.exit(err)
-- 
cgit v1.2.3-58-ga151


From e99ef8141a6d97abaf47647cfd0034769144d080 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:42 +0300
Subject: perf scripts python: call-graph-from-sql.py: Remove use of
 setObjectName()

The object name is never used, so don't bother setting it.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-9-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 1 -
 1 file changed, 1 deletion(-)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 0a4dc13d4818..65c18e351bc4 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -269,7 +269,6 @@ class MainWindow(QMainWindow):
 
 		self.glb = glb
 
-		self.setObjectName("MainWindow")
 		self.setWindowTitle("Call Graph: " + glb.dbname)
 		self.move(100, 100)
 		self.resize(800, 600)
-- 
cgit v1.2.3-58-ga151


From 70d831e85c1bdd87d193e85666bf3aa39aab7f21 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:43 +0300
Subject: perf scripts python: call-graph-from-sql.py: Factor out
 CallGraphModel from TreeModel

Factor out CallGraphModel from TreeModel, which paves the way to reuse
TreeModel in future reports.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-10-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 90 ++++++++++++++++--------
 1 file changed, 61 insertions(+), 29 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 65c18e351bc4..ada486048ad8 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -201,42 +201,47 @@ class TreeItem():
 			self.selectCalls()
 		return self.child_count
 
-	def columnCount(self):
-		return 7
-
-	def columnHeader(self, column):
-		headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
-		return headers[column]
+	def hasChildren(self):
+		if not self.query_done:
+			return True
+		return self.child_count > 0
 
 	def getData(self, column):
 		return self.data[column]
 
+# Tree data model
+
 class TreeModel(QAbstractItemModel):
 
-	def __init__(self, db, parent=None):
+	def __init__(self, root, parent=None):
 		super(TreeModel, self).__init__(parent)
-		self.db = db
-		self.root = TreeItem(db, 0, None)
+		self.root = root
+		self.last_row_read = 0
 
-	def columnCount(self, parent):
-		return self.root.columnCount()
-
-	def rowCount(self, parent):
+	def Item(self, parent):
 		if parent.isValid():
-			parent_item = parent.internalPointer()
+			return parent.internalPointer()
 		else:
-			parent_item = self.root
-		return parent_item.childCount()
+			return self.root
+
+	def rowCount(self, parent):
+		result = self.Item(parent).childCount()
+		if result < 0:
+			result = 0
+			self.dataChanged.emit(parent, parent)
+		return result
+
+	def hasChildren(self, parent):
+		return self.Item(parent).hasChildren()
 
 	def headerData(self, section, orientation, role):
 		if role == Qt.TextAlignmentRole:
-			if section > 1:
-				return Qt.AlignRight
+			return self.columnAlignment(section)
 		if role != Qt.DisplayRole:
 			return None
 		if orientation != Qt.Horizontal:
 			return None
-		return self.root.columnHeader(section)
+		return self.columnHeader(section)
 
 	def parent(self, child):
 		child_item = child.internalPointer()
@@ -246,21 +251,48 @@ class TreeModel(QAbstractItemModel):
 		return self.createIndex(parent_item.getRow(), 0, parent_item)
 
 	def index(self, row, column, parent):
-		if parent.isValid():
-			parent_item = parent.internalPointer()
-		else:
-			parent_item = self.root
-		child_item = parent_item.getChildItem(row)
+		child_item = self.Item(parent).getChildItem(row)
 		return self.createIndex(row, column, child_item)
 
+	def DisplayData(self, item, index):
+		return item.getData(index.column())
+
+	def columnAlignment(self, column):
+		return Qt.AlignLeft
+
+	def columnFont(self, column):
+		return None
+
 	def data(self, index, role):
 		if role == Qt.TextAlignmentRole:
-			if index.column() > 1:
-				return Qt.AlignRight
+			return self.columnAlignment(index.column())
+		if role == Qt.FontRole:
+			return self.columnFont(index.column())
 		if role != Qt.DisplayRole:
 			return None
-		index_item = index.internalPointer()
-		return index_item.getData(index.column())
+		item = index.internalPointer()
+		return self.DisplayData(item, index)
+
+# Context-sensitive call graph data model
+
+class CallGraphModel(TreeModel):
+
+	def __init__(self, glb, parent=None):
+		super(CallGraphModel, self).__init__(TreeItem(glb.db, 0, None), parent)
+		self.glb = glb
+
+	def columnCount(self, parent=None):
+		return 7
+
+	def columnHeader(self, column):
+		headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
+		return headers[column]
+
+	def columnAlignment(self, column):
+		alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
+		return alignment[column]
+
+# Main window
 
 class MainWindow(QMainWindow):
 
@@ -275,7 +307,7 @@ class MainWindow(QMainWindow):
 		self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
 		self.setMinimumSize(200, 100)
 
-		self.model = TreeModel(glb.db)
+		self.model = CallGraphModel(glb)
 
 		self.view = QTreeView()
 		self.view.setModel(self.model)
-- 
cgit v1.2.3-58-ga151


From 4be9ace7e1cdcb44c1fba1fb41ec2b92dda06732 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:44 +0300
Subject: perf scripts python: call-graph-from-sql.py: Add data helper
 functions

Add helper functions for a few common cases.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-11-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 54 +++++++++++++-----------
 1 file changed, 29 insertions(+), 25 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index ada486048ad8..7f2eabe7dacd 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -52,6 +52,28 @@ from PySide.QtGui import *
 from PySide.QtSql import *
 from decimal import *
 
+# Data formatting helpers
+
+def dsoname(name):
+	if name == "[kernel.kallsyms]":
+		return "[kernel]"
+	return name
+
+# Percent to one decimal place
+
+def PercentToOneDP(n, d):
+	if not d:
+		return "0.0"
+	x = (n * Decimal(100)) / d
+	return str(x.quantize(Decimal(".1"), rounding=ROUND_HALF_UP))
+
+# Helper for queries that must not fail
+
+def QueryExec(query, stmt):
+	ret = query.exec_(stmt)
+	if not ret:
+		raise Exception("Query failed: " + query.lastError().text())
+
 class TreeItem():
 
 	def __init__(self, db, row, parent_item):
@@ -73,9 +95,7 @@ class TreeItem():
 	def setUpRoot(self):
 		self.query_done = True
 		query = QSqlQuery(self.db)
-		ret = query.exec_('SELECT id, comm FROM comms')
-		if not ret:
-			raise Exception("Query failed: " + query.lastError().text())
+		QueryExec(query, 'SELECT id, comm FROM comms')
 		while query.next():
 			if not query.value(0):
 				continue
@@ -91,9 +111,7 @@ class TreeItem():
 		self.child_items = []
 		self.child_count = 0
 		query = QSqlQuery(self.db)
-		ret = query.exec_('SELECT thread_id, ( SELECT pid FROM threads WHERE id = thread_id ), ( SELECT tid FROM threads WHERE id = thread_id ) FROM comm_threads WHERE comm_id = ' + str(comm_id))
-		if not ret:
-			raise Exception("Query failed: " + query.lastError().text())
+		QueryExec(query, 'SELECT thread_id, ( SELECT pid FROM threads WHERE id = thread_id ), ( SELECT tid FROM threads WHERE id = thread_id ) FROM comm_threads WHERE comm_id = ' + str(comm_id))
 		while query.next():
 			child_item = TreeItem(self.db, self.child_count, self)
 			self.child_items.append(child_item)
@@ -114,18 +132,6 @@ class TreeItem():
 	def getRow(self):
 		return self.row
 
-	def timePercent(self, b):
-		if not self.time:
-			return "0.0"
-		x = (b * Decimal(100)) / self.time
-		return str(x.quantize(Decimal('.1'), rounding=ROUND_HALF_UP))
-
-	def branchPercent(self, b):
-		if not self.branch_count:
-			return "0.0"
-		x = (b * Decimal(100)) / self.branch_count
-		return str(x.quantize(Decimal('.1'), rounding=ROUND_HALF_UP))
-
 	def addChild(self, call_path_id, name, dso, count, time, branch_count):
 		child_item = TreeItem(self.db, self.child_count, self)
 		child_item.comm_id = self.comm_id
@@ -134,14 +140,12 @@ class TreeItem():
 		child_item.branch_count = branch_count
 		child_item.time = time
 		child_item.data[0] = name
-		if dso == "[kernel.kallsyms]":
-			dso = "[kernel]"
-		child_item.data[1] = dso
+		child_item.data[1] = dsoname(dso)
 		child_item.data[2] = str(count)
 		child_item.data[3] = str(time)
-		child_item.data[4] = self.timePercent(time)
+		child_item.data[4] = PercentToOneDP(time, self.time)
 		child_item.data[5] = str(branch_count)
-		child_item.data[6] = self.branchPercent(branch_count)
+		child_item.data[6] = PercentToOneDP(branch_count, self.branch_count)
 		self.child_items.append(child_item)
 		self.child_count += 1
 
@@ -189,12 +193,12 @@ class TreeItem():
 			self.branch_count = total_branch_count
 			if self.branch_count:
 				for child_item in self.child_items:
-					child_item.data[6] = self.branchPercent(child_item.branch_count)
+					child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
 		if total_time > self.time:
 			self.time = total_time
 			if self.time:
 				for child_item in self.child_items:
-					child_item.data[4] = self.timePercent(child_item.time)
+					child_item.data[4] = PercentToOneDP(child_item.time, self.time)
 
 	def childCount(self):
 		if not self.query_done:
-- 
cgit v1.2.3-58-ga151


From 341e73cbd3019d350d1271803b45d84af88f2408 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:45 +0300
Subject: perf scripts python: call-graph-from-sql.py: Refactor TreeItem class

class TreeItem represents items at all levels of the call-graph tree.
However, not all the levels represent the same data i.e. the top-level is
comms, the next level is threads, and subsequent levels are functions.
Consequently it is simpler to have separate classes for different levels
with commonality in a base class. Refactor TreeItem class accordingly.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-12-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/call-graph-from-sql.py | 273 +++++++++++------------
 1 file changed, 133 insertions(+), 140 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
index 7f2eabe7dacd..ee1085169a3e 100644
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ b/tools/perf/scripts/python/call-graph-from-sql.py
@@ -74,145 +74,6 @@ def QueryExec(query, stmt):
 	if not ret:
 		raise Exception("Query failed: " + query.lastError().text())
 
-class TreeItem():
-
-	def __init__(self, db, row, parent_item):
-		self.db = db
-		self.row = row
-		self.parent_item = parent_item
-		self.query_done = False;
-		self.child_count = 0
-		self.child_items = []
-		self.data = ["", "", "", "", "", "", ""]
-		self.comm_id = 0
-		self.thread_id = 0
-		self.call_path_id = 1
-		self.branch_count = 0
-		self.time = 0
-		if not parent_item:
-			self.setUpRoot()
-
-	def setUpRoot(self):
-		self.query_done = True
-		query = QSqlQuery(self.db)
-		QueryExec(query, 'SELECT id, comm FROM comms')
-		while query.next():
-			if not query.value(0):
-				continue
-			child_item = TreeItem(self.db, self.child_count, self)
-			self.child_items.append(child_item)
-			self.child_count += 1
-			child_item.setUpLevel1(query.value(0), query.value(1))
-
-	def setUpLevel1(self, comm_id, comm):
-		self.query_done = True;
-		self.comm_id = comm_id
-		self.data[0] = comm
-		self.child_items = []
-		self.child_count = 0
-		query = QSqlQuery(self.db)
-		QueryExec(query, 'SELECT thread_id, ( SELECT pid FROM threads WHERE id = thread_id ), ( SELECT tid FROM threads WHERE id = thread_id ) FROM comm_threads WHERE comm_id = ' + str(comm_id))
-		while query.next():
-			child_item = TreeItem(self.db, self.child_count, self)
-			self.child_items.append(child_item)
-			self.child_count += 1
-			child_item.setUpLevel2(comm_id, query.value(0), query.value(1), query.value(2))
-
-	def setUpLevel2(self, comm_id, thread_id, pid, tid):
-		self.comm_id = comm_id
-		self.thread_id = thread_id
-		self.data[0] = str(pid) + ":" + str(tid)
-
-	def getChildItem(self, row):
-		return self.child_items[row]
-
-	def getParentItem(self):
-		return self.parent_item
-
-	def getRow(self):
-		return self.row
-
-	def addChild(self, call_path_id, name, dso, count, time, branch_count):
-		child_item = TreeItem(self.db, self.child_count, self)
-		child_item.comm_id = self.comm_id
-		child_item.thread_id = self.thread_id
-		child_item.call_path_id = call_path_id
-		child_item.branch_count = branch_count
-		child_item.time = time
-		child_item.data[0] = name
-		child_item.data[1] = dsoname(dso)
-		child_item.data[2] = str(count)
-		child_item.data[3] = str(time)
-		child_item.data[4] = PercentToOneDP(time, self.time)
-		child_item.data[5] = str(branch_count)
-		child_item.data[6] = PercentToOneDP(branch_count, self.branch_count)
-		self.child_items.append(child_item)
-		self.child_count += 1
-
-	def selectCalls(self):
-		self.query_done = True;
-		query = QSqlQuery(self.db)
-		ret = query.exec_('SELECT id, call_path_id, branch_count, call_time, return_time, '
-				  '( SELECT name FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ), '
-				  '( SELECT short_name FROM dsos WHERE id = ( SELECT dso_id FROM symbols WHERE id = ( SELECT symbol_id FROM call_paths WHERE id = call_path_id ) ) ), '
-				  '( SELECT ip FROM call_paths where id = call_path_id ) '
-				  'FROM calls WHERE parent_call_path_id = ' + str(self.call_path_id) + ' AND comm_id = ' + str(self.comm_id) + ' AND thread_id = ' + str(self.thread_id) +
-				  ' ORDER BY call_path_id')
-		if not ret:
-			raise Exception("Query failed: " + query.lastError().text())
-		last_call_path_id = 0
-		name = ""
-		dso = ""
-		count = 0
-		branch_count = 0
-		total_branch_count = 0
-		time = 0
-		total_time = 0
-		while query.next():
-			if query.value(1) == last_call_path_id:
-				count += 1
-				branch_count += query.value(2)
-				time += query.value(4) - query.value(3)
-			else:
-				if count:
-					self.addChild(last_call_path_id, name, dso, count, time, branch_count)
-				last_call_path_id = query.value(1)
-				name = query.value(5)
-				dso = query.value(6)
-				count = 1
-				total_branch_count += branch_count
-				total_time += time
-				branch_count = query.value(2)
-				time = query.value(4) - query.value(3)
-		if count:
-			self.addChild(last_call_path_id, name, dso, count, time, branch_count)
-		total_branch_count += branch_count
-		total_time += time
-		# Top level does not have time or branch count, so fix that here
-		if total_branch_count > self.branch_count:
-			self.branch_count = total_branch_count
-			if self.branch_count:
-				for child_item in self.child_items:
-					child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
-		if total_time > self.time:
-			self.time = total_time
-			if self.time:
-				for child_item in self.child_items:
-					child_item.data[4] = PercentToOneDP(child_item.time, self.time)
-
-	def childCount(self):
-		if not self.query_done:
-			self.selectCalls()
-		return self.child_count
-
-	def hasChildren(self):
-		if not self.query_done:
-			return True
-		return self.child_count > 0
-
-	def getData(self, column):
-		return self.data[column]
-
 # Tree data model
 
 class TreeModel(QAbstractItemModel):
@@ -277,12 +138,144 @@ class TreeModel(QAbstractItemModel):
 		item = index.internalPointer()
 		return self.DisplayData(item, index)
 
+# Context-sensitive call graph data model item base
+
+class CallGraphLevelItemBase(object):
+
+	def __init__(self, glb, row, parent_item):
+		self.glb = glb
+		self.row = row
+		self.parent_item = parent_item
+		self.query_done = False;
+		self.child_count = 0
+		self.child_items = []
+
+	def getChildItem(self, row):
+		return self.child_items[row]
+
+	def getParentItem(self):
+		return self.parent_item
+
+	def getRow(self):
+		return self.row
+
+	def childCount(self):
+		if not self.query_done:
+			self.Select()
+			if not self.child_count:
+				return -1
+		return self.child_count
+
+	def hasChildren(self):
+		if not self.query_done:
+			return True
+		return self.child_count > 0
+
+	def getData(self, column):
+		return self.data[column]
+
+# Context-sensitive call graph data model level 2+ item base
+
+class CallGraphLevelTwoPlusItemBase(CallGraphLevelItemBase):
+
+	def __init__(self, glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item):
+		super(CallGraphLevelTwoPlusItemBase, self).__init__(glb, row, parent_item)
+		self.comm_id = comm_id
+		self.thread_id = thread_id
+		self.call_path_id = call_path_id
+		self.branch_count = branch_count
+		self.time = time
+
+	def Select(self):
+		self.query_done = True;
+		query = QSqlQuery(self.glb.db)
+		QueryExec(query, "SELECT call_path_id, name, short_name, COUNT(calls.id), SUM(return_time - call_time), SUM(branch_count)"
+					" FROM calls"
+					" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
+					" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
+					" INNER JOIN dsos ON symbols.dso_id = dsos.id"
+					" WHERE parent_call_path_id = " + str(self.call_path_id) +
+					" AND comm_id = " + str(self.comm_id) +
+					" AND thread_id = " + str(self.thread_id) +
+					" GROUP BY call_path_id, name, short_name"
+					" ORDER BY call_path_id")
+		while query.next():
+			child_item = CallGraphLevelThreeItem(self.glb, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), int(query.value(5)), self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+
+# Context-sensitive call graph data model level three item
+
+class CallGraphLevelThreeItem(CallGraphLevelTwoPlusItemBase):
+
+	def __init__(self, glb, row, comm_id, thread_id, call_path_id, name, dso, count, time, branch_count, parent_item):
+		super(CallGraphLevelThreeItem, self).__init__(glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item)
+		dso = dsoname(dso)
+		self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
+		self.dbid = call_path_id
+
+# Context-sensitive call graph data model level two item
+
+class CallGraphLevelTwoItem(CallGraphLevelTwoPlusItemBase):
+
+	def __init__(self, glb, row, comm_id, thread_id, pid, tid, parent_item):
+		super(CallGraphLevelTwoItem, self).__init__(glb, row, comm_id, thread_id, 1, 0, 0, parent_item)
+		self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
+		self.dbid = thread_id
+
+	def Select(self):
+		super(CallGraphLevelTwoItem, self).Select()
+		for child_item in self.child_items:
+			self.time += child_item.time
+			self.branch_count += child_item.branch_count
+		for child_item in self.child_items:
+			child_item.data[4] = PercentToOneDP(child_item.time, self.time)
+			child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
+
+# Context-sensitive call graph data model level one item
+
+class CallGraphLevelOneItem(CallGraphLevelItemBase):
+
+	def __init__(self, glb, row, comm_id, comm, parent_item):
+		super(CallGraphLevelOneItem, self).__init__(glb, row, parent_item)
+		self.data = [comm, "", "", "", "", "", ""]
+		self.dbid = comm_id
+
+	def Select(self):
+		self.query_done = True;
+		query = QSqlQuery(self.glb.db)
+		QueryExec(query, "SELECT thread_id, pid, tid"
+					" FROM comm_threads"
+					" INNER JOIN threads ON thread_id = threads.id"
+					" WHERE comm_id = " + str(self.dbid))
+		while query.next():
+			child_item = CallGraphLevelTwoItem(self.glb, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+
+# Context-sensitive call graph data model root item
+
+class CallGraphRootItem(CallGraphLevelItemBase):
+
+	def __init__(self, glb):
+		super(CallGraphRootItem, self).__init__(glb, 0, None)
+		self.dbid = 0
+		self.query_done = True;
+		query = QSqlQuery(glb.db)
+		QueryExec(query, "SELECT id, comm FROM comms")
+		while query.next():
+			if not query.value(0):
+				continue
+			child_item = CallGraphLevelOneItem(glb, self.child_count, query.value(0), query.value(1), self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+
 # Context-sensitive call graph data model
 
 class CallGraphModel(TreeModel):
 
 	def __init__(self, glb, parent=None):
-		super(CallGraphModel, self).__init__(TreeItem(glb.db, 0, None), parent)
+		super(CallGraphModel, self).__init__(CallGraphRootItem(glb), parent)
 		self.glb = glb
 
 	def columnCount(self, parent=None):
-- 
cgit v1.2.3-58-ga151


From 031c2a004ba75a4f8f2a6d0a7ca6f2fe5912de22 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:46 +0300
Subject: perf scripts python: call-graph-from-sql.py: Rename to
 exported-sql-viewer.py

Additional reports will be added to the script so rename to reflect the
more general purpose.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-13-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/intel-pt.txt             |   2 +-
 tools/perf/scripts/python/call-graph-from-sql.py  | 395 ----------------------
 tools/perf/scripts/python/export-to-postgresql.py |   2 +-
 tools/perf/scripts/python/export-to-sqlite.py     |   2 +-
 tools/perf/scripts/python/exported-sql-viewer.py  | 395 ++++++++++++++++++++++
 5 files changed, 398 insertions(+), 398 deletions(-)
 delete mode 100644 tools/perf/scripts/python/call-graph-from-sql.py
 create mode 100755 tools/perf/scripts/python/exported-sql-viewer.py

(limited to 'tools/perf')

diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index 76971d2e4164..115eaacc455f 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -106,7 +106,7 @@ in transaction, respectively.
 While it is possible to create scripts to analyze the data, an alternative
 approach is available to export the data to a sqlite or postgresql database.
 Refer to script export-to-sqlite.py or export-to-postgresql.py for more details,
-and to script call-graph-from-sql.py for an example of using the database.
+and to script exported-sql-viewer.py for an example of using the database.
 
 There is also script intel-pt-events.py which provides an example of how to
 unpack the raw data for power events and PTWRITE.
diff --git a/tools/perf/scripts/python/call-graph-from-sql.py b/tools/perf/scripts/python/call-graph-from-sql.py
deleted file mode 100644
index ee1085169a3e..000000000000
--- a/tools/perf/scripts/python/call-graph-from-sql.py
+++ /dev/null
@@ -1,395 +0,0 @@
-#!/usr/bin/python2
-# SPDX-License-Identifier: GPL-2.0
-# exported-sql-viewer.py: view data from sql database
-# Copyright (c) 2014-2018, Intel Corporation.
-
-# To use this script you will need to have exported data using either the
-# export-to-sqlite.py or the export-to-postgresql.py script.  Refer to those
-# scripts for details.
-#
-# Following on from the example in the export scripts, a
-# call-graph can be displayed for the pt_example database like this:
-#
-#	python tools/perf/scripts/python/call-graph-from-sql.py pt_example
-#
-# Note that for PostgreSQL, this script supports connecting to remote databases
-# by setting hostname, port, username, password, and dbname e.g.
-#
-#	python tools/perf/scripts/python/call-graph-from-sql.py "hostname=myhost username=myuser password=mypassword dbname=pt_example"
-#
-# The result is a GUI window with a tree representing a context-sensitive
-# call-graph.  Expanding a couple of levels of the tree and adjusting column
-# widths to suit will display something like:
-#
-#                                         Call Graph: pt_example
-# Call Path                          Object      Count   Time(ns)  Time(%)  Branch Count   Branch Count(%)
-# v- ls
-#     v- 2638:2638
-#         v- _start                  ld-2.19.so    1     10074071   100.0         211135            100.0
-#           |- unknown               unknown       1        13198     0.1              1              0.0
-#           >- _dl_start             ld-2.19.so    1      1400980    13.9          19637              9.3
-#           >- _d_linit_internal     ld-2.19.so    1       448152     4.4          11094              5.3
-#           v-__libc_start_main@plt  ls            1      8211741    81.5         180397             85.4
-#              >- _dl_fixup          ld-2.19.so    1         7607     0.1            108              0.1
-#              >- __cxa_atexit       libc-2.19.so  1        11737     0.1             10              0.0
-#              >- __libc_csu_init    ls            1        10354     0.1             10              0.0
-#              |- _setjmp            libc-2.19.so  1            0     0.0              4              0.0
-#              v- main               ls            1      8182043    99.6         180254             99.9
-#
-# Points to note:
-#	The top level is a command name (comm)
-#	The next level is a thread (pid:tid)
-#	Subsequent levels are functions
-#	'Count' is the number of calls
-#	'Time' is the elapsed time until the function returns
-#	Percentages are relative to the level above
-#	'Branch Count' is the total number of branches for that function and all
-#       functions that it calls
-
-import sys
-from PySide.QtCore import *
-from PySide.QtGui import *
-from PySide.QtSql import *
-from decimal import *
-
-# Data formatting helpers
-
-def dsoname(name):
-	if name == "[kernel.kallsyms]":
-		return "[kernel]"
-	return name
-
-# Percent to one decimal place
-
-def PercentToOneDP(n, d):
-	if not d:
-		return "0.0"
-	x = (n * Decimal(100)) / d
-	return str(x.quantize(Decimal(".1"), rounding=ROUND_HALF_UP))
-
-# Helper for queries that must not fail
-
-def QueryExec(query, stmt):
-	ret = query.exec_(stmt)
-	if not ret:
-		raise Exception("Query failed: " + query.lastError().text())
-
-# Tree data model
-
-class TreeModel(QAbstractItemModel):
-
-	def __init__(self, root, parent=None):
-		super(TreeModel, self).__init__(parent)
-		self.root = root
-		self.last_row_read = 0
-
-	def Item(self, parent):
-		if parent.isValid():
-			return parent.internalPointer()
-		else:
-			return self.root
-
-	def rowCount(self, parent):
-		result = self.Item(parent).childCount()
-		if result < 0:
-			result = 0
-			self.dataChanged.emit(parent, parent)
-		return result
-
-	def hasChildren(self, parent):
-		return self.Item(parent).hasChildren()
-
-	def headerData(self, section, orientation, role):
-		if role == Qt.TextAlignmentRole:
-			return self.columnAlignment(section)
-		if role != Qt.DisplayRole:
-			return None
-		if orientation != Qt.Horizontal:
-			return None
-		return self.columnHeader(section)
-
-	def parent(self, child):
-		child_item = child.internalPointer()
-		if child_item is self.root:
-			return QModelIndex()
-		parent_item = child_item.getParentItem()
-		return self.createIndex(parent_item.getRow(), 0, parent_item)
-
-	def index(self, row, column, parent):
-		child_item = self.Item(parent).getChildItem(row)
-		return self.createIndex(row, column, child_item)
-
-	def DisplayData(self, item, index):
-		return item.getData(index.column())
-
-	def columnAlignment(self, column):
-		return Qt.AlignLeft
-
-	def columnFont(self, column):
-		return None
-
-	def data(self, index, role):
-		if role == Qt.TextAlignmentRole:
-			return self.columnAlignment(index.column())
-		if role == Qt.FontRole:
-			return self.columnFont(index.column())
-		if role != Qt.DisplayRole:
-			return None
-		item = index.internalPointer()
-		return self.DisplayData(item, index)
-
-# Context-sensitive call graph data model item base
-
-class CallGraphLevelItemBase(object):
-
-	def __init__(self, glb, row, parent_item):
-		self.glb = glb
-		self.row = row
-		self.parent_item = parent_item
-		self.query_done = False;
-		self.child_count = 0
-		self.child_items = []
-
-	def getChildItem(self, row):
-		return self.child_items[row]
-
-	def getParentItem(self):
-		return self.parent_item
-
-	def getRow(self):
-		return self.row
-
-	def childCount(self):
-		if not self.query_done:
-			self.Select()
-			if not self.child_count:
-				return -1
-		return self.child_count
-
-	def hasChildren(self):
-		if not self.query_done:
-			return True
-		return self.child_count > 0
-
-	def getData(self, column):
-		return self.data[column]
-
-# Context-sensitive call graph data model level 2+ item base
-
-class CallGraphLevelTwoPlusItemBase(CallGraphLevelItemBase):
-
-	def __init__(self, glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item):
-		super(CallGraphLevelTwoPlusItemBase, self).__init__(glb, row, parent_item)
-		self.comm_id = comm_id
-		self.thread_id = thread_id
-		self.call_path_id = call_path_id
-		self.branch_count = branch_count
-		self.time = time
-
-	def Select(self):
-		self.query_done = True;
-		query = QSqlQuery(self.glb.db)
-		QueryExec(query, "SELECT call_path_id, name, short_name, COUNT(calls.id), SUM(return_time - call_time), SUM(branch_count)"
-					" FROM calls"
-					" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
-					" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
-					" INNER JOIN dsos ON symbols.dso_id = dsos.id"
-					" WHERE parent_call_path_id = " + str(self.call_path_id) +
-					" AND comm_id = " + str(self.comm_id) +
-					" AND thread_id = " + str(self.thread_id) +
-					" GROUP BY call_path_id, name, short_name"
-					" ORDER BY call_path_id")
-		while query.next():
-			child_item = CallGraphLevelThreeItem(self.glb, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), int(query.value(5)), self)
-			self.child_items.append(child_item)
-			self.child_count += 1
-
-# Context-sensitive call graph data model level three item
-
-class CallGraphLevelThreeItem(CallGraphLevelTwoPlusItemBase):
-
-	def __init__(self, glb, row, comm_id, thread_id, call_path_id, name, dso, count, time, branch_count, parent_item):
-		super(CallGraphLevelThreeItem, self).__init__(glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item)
-		dso = dsoname(dso)
-		self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
-		self.dbid = call_path_id
-
-# Context-sensitive call graph data model level two item
-
-class CallGraphLevelTwoItem(CallGraphLevelTwoPlusItemBase):
-
-	def __init__(self, glb, row, comm_id, thread_id, pid, tid, parent_item):
-		super(CallGraphLevelTwoItem, self).__init__(glb, row, comm_id, thread_id, 1, 0, 0, parent_item)
-		self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
-		self.dbid = thread_id
-
-	def Select(self):
-		super(CallGraphLevelTwoItem, self).Select()
-		for child_item in self.child_items:
-			self.time += child_item.time
-			self.branch_count += child_item.branch_count
-		for child_item in self.child_items:
-			child_item.data[4] = PercentToOneDP(child_item.time, self.time)
-			child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
-
-# Context-sensitive call graph data model level one item
-
-class CallGraphLevelOneItem(CallGraphLevelItemBase):
-
-	def __init__(self, glb, row, comm_id, comm, parent_item):
-		super(CallGraphLevelOneItem, self).__init__(glb, row, parent_item)
-		self.data = [comm, "", "", "", "", "", ""]
-		self.dbid = comm_id
-
-	def Select(self):
-		self.query_done = True;
-		query = QSqlQuery(self.glb.db)
-		QueryExec(query, "SELECT thread_id, pid, tid"
-					" FROM comm_threads"
-					" INNER JOIN threads ON thread_id = threads.id"
-					" WHERE comm_id = " + str(self.dbid))
-		while query.next():
-			child_item = CallGraphLevelTwoItem(self.glb, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
-			self.child_items.append(child_item)
-			self.child_count += 1
-
-# Context-sensitive call graph data model root item
-
-class CallGraphRootItem(CallGraphLevelItemBase):
-
-	def __init__(self, glb):
-		super(CallGraphRootItem, self).__init__(glb, 0, None)
-		self.dbid = 0
-		self.query_done = True;
-		query = QSqlQuery(glb.db)
-		QueryExec(query, "SELECT id, comm FROM comms")
-		while query.next():
-			if not query.value(0):
-				continue
-			child_item = CallGraphLevelOneItem(glb, self.child_count, query.value(0), query.value(1), self)
-			self.child_items.append(child_item)
-			self.child_count += 1
-
-# Context-sensitive call graph data model
-
-class CallGraphModel(TreeModel):
-
-	def __init__(self, glb, parent=None):
-		super(CallGraphModel, self).__init__(CallGraphRootItem(glb), parent)
-		self.glb = glb
-
-	def columnCount(self, parent=None):
-		return 7
-
-	def columnHeader(self, column):
-		headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
-		return headers[column]
-
-	def columnAlignment(self, column):
-		alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
-		return alignment[column]
-
-# Main window
-
-class MainWindow(QMainWindow):
-
-	def __init__(self, glb, parent=None):
-		super(MainWindow, self).__init__(parent)
-
-		self.glb = glb
-
-		self.setWindowTitle("Call Graph: " + glb.dbname)
-		self.move(100, 100)
-		self.resize(800, 600)
-		self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
-		self.setMinimumSize(200, 100)
-
-		self.model = CallGraphModel(glb)
-
-		self.view = QTreeView()
-		self.view.setModel(self.model)
-
-		for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
-			self.view.setColumnWidth(c, w)
-
-		self.setCentralWidget(self.view)
-
-# Global data
-
-class Glb():
-
-	def __init__(self, dbref, db, dbname):
-		self.dbref = dbref
-		self.db = db
-		self.dbname = dbname
-		self.app = None
-		self.mainwindow = None
-
-# Database reference
-
-class DBRef():
-
-	def __init__(self, is_sqlite3, dbname):
-		self.is_sqlite3 = is_sqlite3
-		self.dbname = dbname
-
-	def Open(self, connection_name):
-		dbname = self.dbname
-		if self.is_sqlite3:
-			db = QSqlDatabase.addDatabase("QSQLITE", connection_name)
-		else:
-			db = QSqlDatabase.addDatabase("QPSQL", connection_name)
-			opts = dbname.split()
-			for opt in opts:
-				if "=" in opt:
-					opt = opt.split("=")
-					if opt[0] == "hostname":
-						db.setHostName(opt[1])
-					elif opt[0] == "port":
-						db.setPort(int(opt[1]))
-					elif opt[0] == "username":
-						db.setUserName(opt[1])
-					elif opt[0] == "password":
-						db.setPassword(opt[1])
-					elif opt[0] == "dbname":
-						dbname = opt[1]
-				else:
-					dbname = opt
-
-		db.setDatabaseName(dbname)
-		if not db.open():
-			raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text())
-		return db, dbname
-
-# Main
-
-def Main():
-	if (len(sys.argv) < 2):
-		print >> sys.stderr, "Usage is: call-graph-from-sql.py <database name>"
-		raise Exception("Too few arguments")
-
-	dbname = sys.argv[1]
-
-	is_sqlite3 = False
-	try:
-		f = open(dbname)
-		if f.read(15) == "SQLite format 3":
-			is_sqlite3 = True
-		f.close()
-	except:
-		pass
-
-	dbref = DBRef(is_sqlite3, dbname)
-	db, dbname = dbref.Open("main")
-	glb = Glb(dbref, db, dbname)
-	app = QApplication(sys.argv)
-	glb.app = app
-	mainwindow = MainWindow(glb)
-	glb.mainwindow = mainwindow
-	mainwindow.show()
-	err = app.exec_()
-	db.close()
-	sys.exit(err)
-
-if __name__ == "__main__":
-	Main()
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index e46f51b17513..0564dd7377f2 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -59,7 +59,7 @@ import datetime
 #	pt_example=# \q
 #
 # An example of using the database is provided by the script
-# call-graph-from-sql.py.  Refer to that script for details.
+# exported-sql-viewer.py.  Refer to that script for details.
 #
 # Tables:
 #
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index e4bb82c8aba9..245caf2643ed 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -40,7 +40,7 @@ import datetime
 #	sqlite> .quit
 #
 # An example of using the database is provided by the script
-# call-graph-from-sql.py.  Refer to that script for details.
+# exported-sql-viewer.py.  Refer to that script for details.
 #
 # The database structure is practically the same as created by the script
 # export-to-postgresql.py. Refer to that script for details.  A notable
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
new file mode 100755
index 000000000000..03e7a1de7f31
--- /dev/null
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -0,0 +1,395 @@
+#!/usr/bin/python2
+# SPDX-License-Identifier: GPL-2.0
+# exported-sql-viewer.py: view data from sql database
+# Copyright (c) 2014-2018, Intel Corporation.
+
+# To use this script you will need to have exported data using either the
+# export-to-sqlite.py or the export-to-postgresql.py script.  Refer to those
+# scripts for details.
+#
+# Following on from the example in the export scripts, a
+# call-graph can be displayed for the pt_example database like this:
+#
+#	python tools/perf/scripts/python/exported-sql-viewer.py pt_example
+#
+# Note that for PostgreSQL, this script supports connecting to remote databases
+# by setting hostname, port, username, password, and dbname e.g.
+#
+#	python tools/perf/scripts/python/exported-sql-viewer.py "hostname=myhost username=myuser password=mypassword dbname=pt_example"
+#
+# The result is a GUI window with a tree representing a context-sensitive
+# call-graph.  Expanding a couple of levels of the tree and adjusting column
+# widths to suit will display something like:
+#
+#                                         Call Graph: pt_example
+# Call Path                          Object      Count   Time(ns)  Time(%)  Branch Count   Branch Count(%)
+# v- ls
+#     v- 2638:2638
+#         v- _start                  ld-2.19.so    1     10074071   100.0         211135            100.0
+#           |- unknown               unknown       1        13198     0.1              1              0.0
+#           >- _dl_start             ld-2.19.so    1      1400980    13.9          19637              9.3
+#           >- _d_linit_internal     ld-2.19.so    1       448152     4.4          11094              5.3
+#           v-__libc_start_main@plt  ls            1      8211741    81.5         180397             85.4
+#              >- _dl_fixup          ld-2.19.so    1         7607     0.1            108              0.1
+#              >- __cxa_atexit       libc-2.19.so  1        11737     0.1             10              0.0
+#              >- __libc_csu_init    ls            1        10354     0.1             10              0.0
+#              |- _setjmp            libc-2.19.so  1            0     0.0              4              0.0
+#              v- main               ls            1      8182043    99.6         180254             99.9
+#
+# Points to note:
+#	The top level is a command name (comm)
+#	The next level is a thread (pid:tid)
+#	Subsequent levels are functions
+#	'Count' is the number of calls
+#	'Time' is the elapsed time until the function returns
+#	Percentages are relative to the level above
+#	'Branch Count' is the total number of branches for that function and all
+#       functions that it calls
+
+import sys
+from PySide.QtCore import *
+from PySide.QtGui import *
+from PySide.QtSql import *
+from decimal import *
+
+# Data formatting helpers
+
+def dsoname(name):
+	if name == "[kernel.kallsyms]":
+		return "[kernel]"
+	return name
+
+# Percent to one decimal place
+
+def PercentToOneDP(n, d):
+	if not d:
+		return "0.0"
+	x = (n * Decimal(100)) / d
+	return str(x.quantize(Decimal(".1"), rounding=ROUND_HALF_UP))
+
+# Helper for queries that must not fail
+
+def QueryExec(query, stmt):
+	ret = query.exec_(stmt)
+	if not ret:
+		raise Exception("Query failed: " + query.lastError().text())
+
+# Tree data model
+
+class TreeModel(QAbstractItemModel):
+
+	def __init__(self, root, parent=None):
+		super(TreeModel, self).__init__(parent)
+		self.root = root
+		self.last_row_read = 0
+
+	def Item(self, parent):
+		if parent.isValid():
+			return parent.internalPointer()
+		else:
+			return self.root
+
+	def rowCount(self, parent):
+		result = self.Item(parent).childCount()
+		if result < 0:
+			result = 0
+			self.dataChanged.emit(parent, parent)
+		return result
+
+	def hasChildren(self, parent):
+		return self.Item(parent).hasChildren()
+
+	def headerData(self, section, orientation, role):
+		if role == Qt.TextAlignmentRole:
+			return self.columnAlignment(section)
+		if role != Qt.DisplayRole:
+			return None
+		if orientation != Qt.Horizontal:
+			return None
+		return self.columnHeader(section)
+
+	def parent(self, child):
+		child_item = child.internalPointer()
+		if child_item is self.root:
+			return QModelIndex()
+		parent_item = child_item.getParentItem()
+		return self.createIndex(parent_item.getRow(), 0, parent_item)
+
+	def index(self, row, column, parent):
+		child_item = self.Item(parent).getChildItem(row)
+		return self.createIndex(row, column, child_item)
+
+	def DisplayData(self, item, index):
+		return item.getData(index.column())
+
+	def columnAlignment(self, column):
+		return Qt.AlignLeft
+
+	def columnFont(self, column):
+		return None
+
+	def data(self, index, role):
+		if role == Qt.TextAlignmentRole:
+			return self.columnAlignment(index.column())
+		if role == Qt.FontRole:
+			return self.columnFont(index.column())
+		if role != Qt.DisplayRole:
+			return None
+		item = index.internalPointer()
+		return self.DisplayData(item, index)
+
+# Context-sensitive call graph data model item base
+
+class CallGraphLevelItemBase(object):
+
+	def __init__(self, glb, row, parent_item):
+		self.glb = glb
+		self.row = row
+		self.parent_item = parent_item
+		self.query_done = False;
+		self.child_count = 0
+		self.child_items = []
+
+	def getChildItem(self, row):
+		return self.child_items[row]
+
+	def getParentItem(self):
+		return self.parent_item
+
+	def getRow(self):
+		return self.row
+
+	def childCount(self):
+		if not self.query_done:
+			self.Select()
+			if not self.child_count:
+				return -1
+		return self.child_count
+
+	def hasChildren(self):
+		if not self.query_done:
+			return True
+		return self.child_count > 0
+
+	def getData(self, column):
+		return self.data[column]
+
+# Context-sensitive call graph data model level 2+ item base
+
+class CallGraphLevelTwoPlusItemBase(CallGraphLevelItemBase):
+
+	def __init__(self, glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item):
+		super(CallGraphLevelTwoPlusItemBase, self).__init__(glb, row, parent_item)
+		self.comm_id = comm_id
+		self.thread_id = thread_id
+		self.call_path_id = call_path_id
+		self.branch_count = branch_count
+		self.time = time
+
+	def Select(self):
+		self.query_done = True;
+		query = QSqlQuery(self.glb.db)
+		QueryExec(query, "SELECT call_path_id, name, short_name, COUNT(calls.id), SUM(return_time - call_time), SUM(branch_count)"
+					" FROM calls"
+					" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
+					" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
+					" INNER JOIN dsos ON symbols.dso_id = dsos.id"
+					" WHERE parent_call_path_id = " + str(self.call_path_id) +
+					" AND comm_id = " + str(self.comm_id) +
+					" AND thread_id = " + str(self.thread_id) +
+					" GROUP BY call_path_id, name, short_name"
+					" ORDER BY call_path_id")
+		while query.next():
+			child_item = CallGraphLevelThreeItem(self.glb, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), int(query.value(5)), self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+
+# Context-sensitive call graph data model level three item
+
+class CallGraphLevelThreeItem(CallGraphLevelTwoPlusItemBase):
+
+	def __init__(self, glb, row, comm_id, thread_id, call_path_id, name, dso, count, time, branch_count, parent_item):
+		super(CallGraphLevelThreeItem, self).__init__(glb, row, comm_id, thread_id, call_path_id, time, branch_count, parent_item)
+		dso = dsoname(dso)
+		self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ]
+		self.dbid = call_path_id
+
+# Context-sensitive call graph data model level two item
+
+class CallGraphLevelTwoItem(CallGraphLevelTwoPlusItemBase):
+
+	def __init__(self, glb, row, comm_id, thread_id, pid, tid, parent_item):
+		super(CallGraphLevelTwoItem, self).__init__(glb, row, comm_id, thread_id, 1, 0, 0, parent_item)
+		self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""]
+		self.dbid = thread_id
+
+	def Select(self):
+		super(CallGraphLevelTwoItem, self).Select()
+		for child_item in self.child_items:
+			self.time += child_item.time
+			self.branch_count += child_item.branch_count
+		for child_item in self.child_items:
+			child_item.data[4] = PercentToOneDP(child_item.time, self.time)
+			child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count)
+
+# Context-sensitive call graph data model level one item
+
+class CallGraphLevelOneItem(CallGraphLevelItemBase):
+
+	def __init__(self, glb, row, comm_id, comm, parent_item):
+		super(CallGraphLevelOneItem, self).__init__(glb, row, parent_item)
+		self.data = [comm, "", "", "", "", "", ""]
+		self.dbid = comm_id
+
+	def Select(self):
+		self.query_done = True;
+		query = QSqlQuery(self.glb.db)
+		QueryExec(query, "SELECT thread_id, pid, tid"
+					" FROM comm_threads"
+					" INNER JOIN threads ON thread_id = threads.id"
+					" WHERE comm_id = " + str(self.dbid))
+		while query.next():
+			child_item = CallGraphLevelTwoItem(self.glb, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+
+# Context-sensitive call graph data model root item
+
+class CallGraphRootItem(CallGraphLevelItemBase):
+
+	def __init__(self, glb):
+		super(CallGraphRootItem, self).__init__(glb, 0, None)
+		self.dbid = 0
+		self.query_done = True;
+		query = QSqlQuery(glb.db)
+		QueryExec(query, "SELECT id, comm FROM comms")
+		while query.next():
+			if not query.value(0):
+				continue
+			child_item = CallGraphLevelOneItem(glb, self.child_count, query.value(0), query.value(1), self)
+			self.child_items.append(child_item)
+			self.child_count += 1
+
+# Context-sensitive call graph data model
+
+class CallGraphModel(TreeModel):
+
+	def __init__(self, glb, parent=None):
+		super(CallGraphModel, self).__init__(CallGraphRootItem(glb), parent)
+		self.glb = glb
+
+	def columnCount(self, parent=None):
+		return 7
+
+	def columnHeader(self, column):
+		headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "]
+		return headers[column]
+
+	def columnAlignment(self, column):
+		alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
+		return alignment[column]
+
+# Main window
+
+class MainWindow(QMainWindow):
+
+	def __init__(self, glb, parent=None):
+		super(MainWindow, self).__init__(parent)
+
+		self.glb = glb
+
+		self.setWindowTitle("Call Graph: " + glb.dbname)
+		self.move(100, 100)
+		self.resize(800, 600)
+		self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
+		self.setMinimumSize(200, 100)
+
+		self.model = CallGraphModel(glb)
+
+		self.view = QTreeView()
+		self.view.setModel(self.model)
+
+		for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
+			self.view.setColumnWidth(c, w)
+
+		self.setCentralWidget(self.view)
+
+# Global data
+
+class Glb():
+
+	def __init__(self, dbref, db, dbname):
+		self.dbref = dbref
+		self.db = db
+		self.dbname = dbname
+		self.app = None
+		self.mainwindow = None
+
+# Database reference
+
+class DBRef():
+
+	def __init__(self, is_sqlite3, dbname):
+		self.is_sqlite3 = is_sqlite3
+		self.dbname = dbname
+
+	def Open(self, connection_name):
+		dbname = self.dbname
+		if self.is_sqlite3:
+			db = QSqlDatabase.addDatabase("QSQLITE", connection_name)
+		else:
+			db = QSqlDatabase.addDatabase("QPSQL", connection_name)
+			opts = dbname.split()
+			for opt in opts:
+				if "=" in opt:
+					opt = opt.split("=")
+					if opt[0] == "hostname":
+						db.setHostName(opt[1])
+					elif opt[0] == "port":
+						db.setPort(int(opt[1]))
+					elif opt[0] == "username":
+						db.setUserName(opt[1])
+					elif opt[0] == "password":
+						db.setPassword(opt[1])
+					elif opt[0] == "dbname":
+						dbname = opt[1]
+				else:
+					dbname = opt
+
+		db.setDatabaseName(dbname)
+		if not db.open():
+			raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text())
+		return db, dbname
+
+# Main
+
+def Main():
+	if (len(sys.argv) < 2):
+		print >> sys.stderr, "Usage is: exported-sql-viewer.py <database name>"
+		raise Exception("Too few arguments")
+
+	dbname = sys.argv[1]
+
+	is_sqlite3 = False
+	try:
+		f = open(dbname)
+		if f.read(15) == "SQLite format 3":
+			is_sqlite3 = True
+		f.close()
+	except:
+		pass
+
+	dbref = DBRef(is_sqlite3, dbname)
+	db, dbname = dbref.Open("main")
+	glb = Glb(dbref, db, dbname)
+	app = QApplication(sys.argv)
+	glb.app = app
+	mainwindow = MainWindow(glb)
+	glb.mainwindow = mainwindow
+	mainwindow.show()
+	err = app.exec_()
+	db.close()
+	sys.exit(err)
+
+if __name__ == "__main__":
+	Main()
-- 
cgit v1.2.3-58-ga151


From 1beb5c7b07040b70975a2ae0e90b87d412fabf06 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:47 +0300
Subject: perf scripts python: exported-sql-viewer.py: Add support for multiple
 sub-windows

Use Qt MDI (multiple document interface) to support multiple sub-windows.
Put the data model in a cache so that each sub-window can share the same
data. This allows mutiple views of the call-graph at the same time and
paves the way to add more reports.

Committer testing:

Starts with a "File  Reports  Windows" main menu, from the "Reports" I
can get what was available up to now, the "Context-Sensitivi Call Graph"
option.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-14-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 182 +++++++++++++++++++++--
 1 file changed, 173 insertions(+), 9 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 03e7a1de7f31..c2f44351821e 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -47,6 +47,8 @@
 #       functions that it calls
 
 import sys
+import weakref
+import threading
 from PySide.QtCore import *
 from PySide.QtGui import *
 from PySide.QtSql import *
@@ -138,6 +140,23 @@ class TreeModel(QAbstractItemModel):
 		item = index.internalPointer()
 		return self.DisplayData(item, index)
 
+# Model cache
+
+model_cache = weakref.WeakValueDictionary()
+model_cache_lock = threading.Lock()
+
+def LookupCreateModel(model_name, create_fn):
+	model_cache_lock.acquire()
+	try:
+		model = model_cache[model_name]
+	except:
+		model = None
+	if model is None:
+		model = create_fn()
+		model_cache[model_name] = model
+	model_cache_lock.release()
+	return model
+
 # Context-sensitive call graph data model item base
 
 class CallGraphLevelItemBase(object):
@@ -289,6 +308,144 @@ class CallGraphModel(TreeModel):
 		alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
 		return alignment[column]
 
+# Context-sensitive call graph window
+
+class CallGraphWindow(QMdiSubWindow):
+
+	def __init__(self, glb, parent=None):
+		super(CallGraphWindow, self).__init__(parent)
+
+		self.model = LookupCreateModel("Context-Sensitive Call Graph", lambda x=glb: CallGraphModel(x))
+
+		self.view = QTreeView()
+		self.view.setModel(self.model)
+
+		for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
+			self.view.setColumnWidth(c, w)
+
+		self.setWidget(self.view)
+
+		AddSubWindow(glb.mainwindow.mdi_area, self, "Context-Sensitive Call Graph")
+
+# Action Definition
+
+def CreateAction(label, tip, callback, parent=None, shortcut=None):
+	action = QAction(label, parent)
+	if shortcut != None:
+		action.setShortcuts(shortcut)
+	action.setStatusTip(tip)
+	action.triggered.connect(callback)
+	return action
+
+# Typical application actions
+
+def CreateExitAction(app, parent=None):
+	return CreateAction("&Quit", "Exit the application", app.closeAllWindows, parent, QKeySequence.Quit)
+
+# Typical MDI actions
+
+def CreateCloseActiveWindowAction(mdi_area):
+	return CreateAction("Cl&ose", "Close the active window", mdi_area.closeActiveSubWindow, mdi_area)
+
+def CreateCloseAllWindowsAction(mdi_area):
+	return CreateAction("Close &All", "Close all the windows", mdi_area.closeAllSubWindows, mdi_area)
+
+def CreateTileWindowsAction(mdi_area):
+	return CreateAction("&Tile", "Tile the windows", mdi_area.tileSubWindows, mdi_area)
+
+def CreateCascadeWindowsAction(mdi_area):
+	return CreateAction("&Cascade", "Cascade the windows", mdi_area.cascadeSubWindows, mdi_area)
+
+def CreateNextWindowAction(mdi_area):
+	return CreateAction("Ne&xt", "Move the focus to the next window", mdi_area.activateNextSubWindow, mdi_area, QKeySequence.NextChild)
+
+def CreatePreviousWindowAction(mdi_area):
+	return CreateAction("Pre&vious", "Move the focus to the previous window", mdi_area.activatePreviousSubWindow, mdi_area, QKeySequence.PreviousChild)
+
+# Typical MDI window menu
+
+class WindowMenu():
+
+	def __init__(self, mdi_area, menu):
+		self.mdi_area = mdi_area
+		self.window_menu = menu.addMenu("&Windows")
+		self.close_active_window = CreateCloseActiveWindowAction(mdi_area)
+		self.close_all_windows = CreateCloseAllWindowsAction(mdi_area)
+		self.tile_windows = CreateTileWindowsAction(mdi_area)
+		self.cascade_windows = CreateCascadeWindowsAction(mdi_area)
+		self.next_window = CreateNextWindowAction(mdi_area)
+		self.previous_window = CreatePreviousWindowAction(mdi_area)
+		self.window_menu.aboutToShow.connect(self.Update)
+
+	def Update(self):
+		self.window_menu.clear()
+		sub_window_count = len(self.mdi_area.subWindowList())
+		have_sub_windows = sub_window_count != 0
+		self.close_active_window.setEnabled(have_sub_windows)
+		self.close_all_windows.setEnabled(have_sub_windows)
+		self.tile_windows.setEnabled(have_sub_windows)
+		self.cascade_windows.setEnabled(have_sub_windows)
+		self.next_window.setEnabled(have_sub_windows)
+		self.previous_window.setEnabled(have_sub_windows)
+		self.window_menu.addAction(self.close_active_window)
+		self.window_menu.addAction(self.close_all_windows)
+		self.window_menu.addSeparator()
+		self.window_menu.addAction(self.tile_windows)
+		self.window_menu.addAction(self.cascade_windows)
+		self.window_menu.addSeparator()
+		self.window_menu.addAction(self.next_window)
+		self.window_menu.addAction(self.previous_window)
+		if sub_window_count == 0:
+			return
+		self.window_menu.addSeparator()
+		nr = 1
+		for sub_window in self.mdi_area.subWindowList():
+			label = str(nr) + " " + sub_window.name
+			if nr < 10:
+				label = "&" + label
+			action = self.window_menu.addAction(label)
+			action.setCheckable(True)
+			action.setChecked(sub_window == self.mdi_area.activeSubWindow())
+			action.triggered.connect(lambda x=nr: self.setActiveSubWindow(x))
+			self.window_menu.addAction(action)
+			nr += 1
+
+	def setActiveSubWindow(self, nr):
+		self.mdi_area.setActiveSubWindow(self.mdi_area.subWindowList()[nr - 1])
+
+# Unique name for sub-windows
+
+def NumberedWindowName(name, nr):
+	if nr > 1:
+		name += " <" + str(nr) + ">"
+	return name
+
+def UniqueSubWindowName(mdi_area, name):
+	nr = 1
+	while True:
+		unique_name = NumberedWindowName(name, nr)
+		ok = True
+		for sub_window in mdi_area.subWindowList():
+			if sub_window.name == unique_name:
+				ok = False
+				break
+		if ok:
+			return unique_name
+		nr += 1
+
+# Add a sub-window
+
+def AddSubWindow(mdi_area, sub_window, name):
+	unique_name = UniqueSubWindowName(mdi_area, name)
+	sub_window.setMinimumSize(200, 100)
+	sub_window.resize(800, 600)
+	sub_window.setWindowTitle(unique_name)
+	sub_window.setAttribute(Qt.WA_DeleteOnClose)
+	sub_window.setWindowIcon(sub_window.style().standardIcon(QStyle.SP_FileIcon))
+	sub_window.name = unique_name
+	mdi_area.addSubWindow(sub_window)
+	sub_window.show()
+
 # Main window
 
 class MainWindow(QMainWindow):
@@ -298,21 +455,28 @@ class MainWindow(QMainWindow):
 
 		self.glb = glb
 
-		self.setWindowTitle("Call Graph: " + glb.dbname)
-		self.move(100, 100)
-		self.resize(800, 600)
+		self.setWindowTitle("Exported SQL Viewer: " + glb.dbname)
 		self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon))
 		self.setMinimumSize(200, 100)
 
-		self.model = CallGraphModel(glb)
+		self.mdi_area = QMdiArea()
+		self.mdi_area.setHorizontalScrollBarPolicy(Qt.ScrollBarAsNeeded)
+		self.mdi_area.setVerticalScrollBarPolicy(Qt.ScrollBarAsNeeded)
 
-		self.view = QTreeView()
-		self.view.setModel(self.model)
+		self.setCentralWidget(self.mdi_area)
 
-		for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
-			self.view.setColumnWidth(c, w)
+		menu = self.menuBar()
+
+		file_menu = menu.addMenu("&File")
+		file_menu.addAction(CreateExitAction(glb.app, self))
+
+		reports_menu = menu.addMenu("&Reports")
+		reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
+
+		self.window_menu = WindowMenu(self.mdi_area, menu)
 
-		self.setCentralWidget(self.view)
+	def NewCallGraph(self):
+		CallGraphWindow(self.glb, self)
 
 # Global data
 
-- 
cgit v1.2.3-58-ga151


From ebd70c7dc2f5f57315e19d959ddc9cb05e9d48e1 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:48 +0300
Subject: perf scripts python: exported-sql-viewer.py: Add ability to find
 symbols in the call-graph

Add a Find bar that appears at the bottom of the call-graph window.

Committer testing:

Using:

  python tools/perf/scripts/python/exported-sql-viewer.py pt_example branches calls

Using the database built in the first "Committer Testing" section in
this patch series I was able to:

  "Reports"
      "Context-Sensitive Call Graphs"
           Control+F or select "Edit" in the top menu then "Find"
                __poll<ENTER>

and find the first place where the "__poll" function appears, then
press the down arrow in the lower right corner and go to the next, etc.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-15-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 306 ++++++++++++++++++++++-
 1 file changed, 305 insertions(+), 1 deletion(-)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index c2f44351821e..0386a600ffc7 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -49,6 +49,7 @@
 import sys
 import weakref
 import threading
+import string
 from PySide.QtCore import *
 from PySide.QtGui import *
 from PySide.QtSql import *
@@ -76,6 +77,27 @@ def QueryExec(query, stmt):
 	if not ret:
 		raise Exception("Query failed: " + query.lastError().text())
 
+# Background thread
+
+class Thread(QThread):
+
+	done = Signal(object)
+
+	def __init__(self, task, param=None, parent=None):
+		super(Thread, self).__init__(parent)
+		self.task = task
+		self.param = param
+
+	def run(self):
+		while True:
+			if self.param is None:
+				done, result = self.task()
+			else:
+				done, result = self.task(self.param)
+			self.done.emit(result)
+			if done:
+				break
+
 # Tree data model
 
 class TreeModel(QAbstractItemModel):
@@ -157,6 +179,125 @@ def LookupCreateModel(model_name, create_fn):
 	model_cache_lock.release()
 	return model
 
+# Find bar
+
+class FindBar():
+
+	def __init__(self, parent, finder, is_reg_expr=False):
+		self.finder = finder
+		self.context = []
+		self.last_value = None
+		self.last_pattern = None
+
+		label = QLabel("Find:")
+		label.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.textbox = QComboBox()
+		self.textbox.setEditable(True)
+		self.textbox.currentIndexChanged.connect(self.ValueChanged)
+
+		self.progress = QProgressBar()
+		self.progress.setRange(0, 0)
+		self.progress.hide()
+
+		if is_reg_expr:
+			self.pattern = QCheckBox("Regular Expression")
+		else:
+			self.pattern = QCheckBox("Pattern")
+		self.pattern.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.next_button = QToolButton()
+		self.next_button.setIcon(parent.style().standardIcon(QStyle.SP_ArrowDown))
+		self.next_button.released.connect(lambda: self.NextPrev(1))
+
+		self.prev_button = QToolButton()
+		self.prev_button.setIcon(parent.style().standardIcon(QStyle.SP_ArrowUp))
+		self.prev_button.released.connect(lambda: self.NextPrev(-1))
+
+		self.close_button = QToolButton()
+		self.close_button.setIcon(parent.style().standardIcon(QStyle.SP_DockWidgetCloseButton))
+		self.close_button.released.connect(self.Deactivate)
+
+		self.hbox = QHBoxLayout()
+		self.hbox.setContentsMargins(0, 0, 0, 0)
+
+		self.hbox.addWidget(label)
+		self.hbox.addWidget(self.textbox)
+		self.hbox.addWidget(self.progress)
+		self.hbox.addWidget(self.pattern)
+		self.hbox.addWidget(self.next_button)
+		self.hbox.addWidget(self.prev_button)
+		self.hbox.addWidget(self.close_button)
+
+		self.bar = QWidget()
+		self.bar.setLayout(self.hbox);
+		self.bar.hide()
+
+	def Widget(self):
+		return self.bar
+
+	def Activate(self):
+		self.bar.show()
+		self.textbox.setFocus()
+
+	def Deactivate(self):
+		self.bar.hide()
+
+	def Busy(self):
+		self.textbox.setEnabled(False)
+		self.pattern.hide()
+		self.next_button.hide()
+		self.prev_button.hide()
+		self.progress.show()
+
+	def Idle(self):
+		self.textbox.setEnabled(True)
+		self.progress.hide()
+		self.pattern.show()
+		self.next_button.show()
+		self.prev_button.show()
+
+	def Find(self, direction):
+		value = self.textbox.currentText()
+		pattern = self.pattern.isChecked()
+		self.last_value = value
+		self.last_pattern = pattern
+		self.finder.Find(value, direction, pattern, self.context)
+
+	def ValueChanged(self):
+		value = self.textbox.currentText()
+		pattern = self.pattern.isChecked()
+		index = self.textbox.currentIndex()
+		data = self.textbox.itemData(index)
+		# Store the pattern in the combo box to keep it with the text value
+		if data == None:
+			self.textbox.setItemData(index, pattern)
+		else:
+			self.pattern.setChecked(data)
+		self.Find(0)
+
+	def NextPrev(self, direction):
+		value = self.textbox.currentText()
+		pattern = self.pattern.isChecked()
+		if value != self.last_value:
+			index = self.textbox.findText(value)
+			# Allow for a button press before the value has been added to the combo box
+			if index < 0:
+				index = self.textbox.count()
+				self.textbox.addItem(value, pattern)
+				self.textbox.setCurrentIndex(index)
+				return
+			else:
+				self.textbox.setItemData(index, pattern)
+		elif pattern != self.last_pattern:
+			# Keep the pattern recorded in the combo box up to date
+			index = self.textbox.currentIndex()
+			self.textbox.setItemData(index, pattern)
+		self.Find(direction)
+
+	def NotFound(self):
+		QMessageBox.information(self.bar, "Find", "'" + self.textbox.currentText() + "' not found")
+
 # Context-sensitive call graph data model item base
 
 class CallGraphLevelItemBase(object):
@@ -308,6 +449,123 @@ class CallGraphModel(TreeModel):
 		alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ]
 		return alignment[column]
 
+	def FindSelect(self, value, pattern, query):
+		if pattern:
+			# postgresql and sqlite pattern patching differences:
+			#   postgresql LIKE is case sensitive but sqlite LIKE is not
+			#   postgresql LIKE allows % and _ to be escaped with \ but sqlite LIKE does not
+			#   postgresql supports ILIKE which is case insensitive
+			#   sqlite supports GLOB (text only) which uses * and ? and is case sensitive
+			if not self.glb.dbref.is_sqlite3:
+				# Escape % and _
+				s = value.replace("%", "\%")
+				s = s.replace("_", "\_")
+				# Translate * and ? into SQL LIKE pattern characters % and _
+				trans = string.maketrans("*?", "%_")
+				match = " LIKE '" + str(s).translate(trans) + "'"
+			else:
+				match = " GLOB '" + str(value) + "'"
+		else:
+			match = " = '" + str(value) + "'"
+		QueryExec(query, "SELECT call_path_id, comm_id, thread_id"
+						" FROM calls"
+						" INNER JOIN call_paths ON calls.call_path_id = call_paths.id"
+						" INNER JOIN symbols ON call_paths.symbol_id = symbols.id"
+						" WHERE symbols.name" + match +
+						" GROUP BY comm_id, thread_id, call_path_id"
+						" ORDER BY comm_id, thread_id, call_path_id")
+
+	def FindPath(self, query):
+		# Turn the query result into a list of ids that the tree view can walk
+		# to open the tree at the right place.
+		ids = []
+		parent_id = query.value(0)
+		while parent_id:
+			ids.insert(0, parent_id)
+			q2 = QSqlQuery(self.glb.db)
+			QueryExec(q2, "SELECT parent_id"
+					" FROM call_paths"
+					" WHERE id = " + str(parent_id))
+			if not q2.next():
+				break
+			parent_id = q2.value(0)
+		# The call path root is not used
+		if ids[0] == 1:
+			del ids[0]
+		ids.insert(0, query.value(2))
+		ids.insert(0, query.value(1))
+		return ids
+
+	def Found(self, query, found):
+		if found:
+			return self.FindPath(query)
+		return []
+
+	def FindValue(self, value, pattern, query, last_value, last_pattern):
+		if last_value == value and pattern == last_pattern:
+			found = query.first()
+		else:
+			self.FindSelect(value, pattern, query)
+			found = query.next()
+		return self.Found(query, found)
+
+	def FindNext(self, query):
+		found = query.next()
+		if not found:
+			found = query.first()
+		return self.Found(query, found)
+
+	def FindPrev(self, query):
+		found = query.previous()
+		if not found:
+			found = query.last()
+		return self.Found(query, found)
+
+	def FindThread(self, c):
+		if c.direction == 0 or c.value != c.last_value or c.pattern != c.last_pattern:
+			ids = self.FindValue(c.value, c.pattern, c.query, c.last_value, c.last_pattern)
+		elif c.direction > 0:
+			ids = self.FindNext(c.query)
+		else:
+			ids = self.FindPrev(c.query)
+		return (True, ids)
+
+	def Find(self, value, direction, pattern, context, callback):
+		class Context():
+			def __init__(self, *x):
+				self.value, self.direction, self.pattern, self.query, self.last_value, self.last_pattern = x
+			def Update(self, *x):
+				self.value, self.direction, self.pattern, self.last_value, self.last_pattern = x + (self.value, self.pattern)
+		if len(context):
+			context[0].Update(value, direction, pattern)
+		else:
+			context.append(Context(value, direction, pattern, QSqlQuery(self.glb.db), None, None))
+		# Use a thread so the UI is not blocked during the SELECT
+		thread = Thread(self.FindThread, context[0])
+		thread.done.connect(lambda ids, t=thread, c=callback: self.FindDone(t, c, ids), Qt.QueuedConnection)
+		thread.start()
+
+	def FindDone(self, thread, callback, ids):
+		callback(ids)
+
+# Vertical widget layout
+
+class VBox():
+
+	def __init__(self, w1, w2, w3=None):
+		self.vbox = QWidget()
+		self.vbox.setLayout(QVBoxLayout());
+
+		self.vbox.layout().setContentsMargins(0, 0, 0, 0)
+
+		self.vbox.layout().addWidget(w1)
+		self.vbox.layout().addWidget(w2)
+		if w3:
+			self.vbox.layout().addWidget(w3)
+
+	def Widget(self):
+		return self.vbox
+
 # Context-sensitive call graph window
 
 class CallGraphWindow(QMdiSubWindow):
@@ -323,10 +581,45 @@ class CallGraphWindow(QMdiSubWindow):
 		for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)):
 			self.view.setColumnWidth(c, w)
 
-		self.setWidget(self.view)
+		self.find_bar = FindBar(self, self)
+
+		self.vbox = VBox(self.view, self.find_bar.Widget())
+
+		self.setWidget(self.vbox.Widget())
 
 		AddSubWindow(glb.mainwindow.mdi_area, self, "Context-Sensitive Call Graph")
 
+	def DisplayFound(self, ids):
+		if not len(ids):
+			return False
+		parent = QModelIndex()
+		for dbid in ids:
+			found = False
+			n = self.model.rowCount(parent)
+			for row in xrange(n):
+				child = self.model.index(row, 0, parent)
+				if child.internalPointer().dbid == dbid:
+					found = True
+					self.view.setCurrentIndex(child)
+					parent = child
+					break
+			if not found:
+				break
+		return found
+
+	def Find(self, value, direction, pattern, context):
+		self.view.setFocus()
+		self.find_bar.Busy()
+		self.model.Find(value, direction, pattern, context, self.FindDone)
+
+	def FindDone(self, ids):
+		found = True
+		if not self.DisplayFound(ids):
+			found = False
+		self.find_bar.Idle()
+		if not found:
+			self.find_bar.NotFound()
+
 # Action Definition
 
 def CreateAction(label, tip, callback, parent=None, shortcut=None):
@@ -470,11 +763,22 @@ class MainWindow(QMainWindow):
 		file_menu = menu.addMenu("&File")
 		file_menu.addAction(CreateExitAction(glb.app, self))
 
+		edit_menu = menu.addMenu("&Edit")
+		edit_menu.addAction(CreateAction("&Find...", "Find items", self.Find, self, QKeySequence.Find))
+
 		reports_menu = menu.addMenu("&Reports")
 		reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
 
 		self.window_menu = WindowMenu(self.mdi_area, menu)
 
+	def Find(self):
+		win = self.mdi_area.activeSubWindow()
+		if win:
+			try:
+				win.find_bar.Activate()
+			except:
+				pass
+
 	def NewCallGraph(self):
 		CallGraphWindow(self.glb, self)
 
-- 
cgit v1.2.3-58-ga151


From 82f68e2898e634b8b0efc7ddd57e037ef75ea114 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:49 +0300
Subject: perf scripts python: exported-sql-viewer.py: Add ability to shrink /
 enlarge font

Shrinking the font allows more information to display.

Committer testing:

Works, tested with the convenient Control+Shift+'+' and Control+'-' as
well with the more cumbersome top menu "Edit" + "Enlarge/Shrink font"
options.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-16-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 0386a600ffc7..310ba7147583 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -706,6 +706,20 @@ class WindowMenu():
 	def setActiveSubWindow(self, nr):
 		self.mdi_area.setActiveSubWindow(self.mdi_area.subWindowList()[nr - 1])
 
+# Font resize
+
+def ResizeFont(widget, diff):
+	font = widget.font()
+	sz = font.pointSize()
+	font.setPointSize(sz + diff)
+	widget.setFont(font)
+
+def ShrinkFont(widget):
+	ResizeFont(widget, -1)
+
+def EnlargeFont(widget):
+	ResizeFont(widget, 1)
+
 # Unique name for sub-windows
 
 def NumberedWindowName(name, nr):
@@ -765,6 +779,8 @@ class MainWindow(QMainWindow):
 
 		edit_menu = menu.addMenu("&Edit")
 		edit_menu.addAction(CreateAction("&Find...", "Find items", self.Find, self, QKeySequence.Find))
+		edit_menu.addAction(CreateAction("&Shrink Font", "Make text smaller", self.ShrinkFont, self, [QKeySequence("Ctrl+-")]))
+		edit_menu.addAction(CreateAction("&Enlarge Font", "Make text bigger", self.EnlargeFont, self, [QKeySequence("Ctrl++")]))
 
 		reports_menu = menu.addMenu("&Reports")
 		reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
@@ -779,6 +795,14 @@ class MainWindow(QMainWindow):
 			except:
 				pass
 
+	def ShrinkFont(self):
+		win = self.mdi_area.activeSubWindow()
+		ShrinkFont(win.view)
+
+	def EnlargeFont(self):
+		win = self.mdi_area.activeSubWindow()
+		EnlargeFont(win.view)
+
 	def NewCallGraph(self):
 		CallGraphWindow(self.glb, self)
 
-- 
cgit v1.2.3-58-ga151


From 8392b74b575c38fa5d50d1fe07fa9a4bcea93862 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 1 Oct 2018 09:28:50 +0300
Subject: perf scripts python: exported-sql-viewer.py: Add ability to display
 all the database tables

Displaying all the database tables can help make the database easier to
understand.

Committer testing:

Opened all the tables, even the sqlite master table, which I selected
everything and used control+C, lets see if it works...

  CREATE VIEW threads_view AS SELECT id,machine_id,(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,process_id,pid,tid FROM threads

Humm, nope, just one of the cells got copied, even with everything selected :-)

Anyway, works as advertised, useful for perusing the data.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181001062853.28285-17-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 694 +++++++++++++++++++++++
 1 file changed, 694 insertions(+)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 310ba7147583..ef822d850109 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -50,10 +50,15 @@ import sys
 import weakref
 import threading
 import string
+import cPickle
+import re
+import os
 from PySide.QtCore import *
 from PySide.QtGui import *
 from PySide.QtSql import *
 from decimal import *
+from ctypes import *
+from multiprocessing import Process, Array, Value, Event
 
 # Data formatting helpers
 
@@ -146,6 +151,68 @@ class TreeModel(QAbstractItemModel):
 	def DisplayData(self, item, index):
 		return item.getData(index.column())
 
+	def FetchIfNeeded(self, row):
+		if row > self.last_row_read:
+			self.last_row_read = row
+			if row + 10 >= self.root.child_count:
+				self.fetcher.Fetch(glb_chunk_sz)
+
+	def columnAlignment(self, column):
+		return Qt.AlignLeft
+
+	def columnFont(self, column):
+		return None
+
+	def data(self, index, role):
+		if role == Qt.TextAlignmentRole:
+			return self.columnAlignment(index.column())
+		if role == Qt.FontRole:
+			return self.columnFont(index.column())
+		if role != Qt.DisplayRole:
+			return None
+		item = index.internalPointer()
+		return self.DisplayData(item, index)
+
+# Table data model
+
+class TableModel(QAbstractTableModel):
+
+	def __init__(self, parent=None):
+		super(TableModel, self).__init__(parent)
+		self.child_count = 0
+		self.child_items = []
+		self.last_row_read = 0
+
+	def Item(self, parent):
+		if parent.isValid():
+			return parent.internalPointer()
+		else:
+			return self
+
+	def rowCount(self, parent):
+		return self.child_count
+
+	def headerData(self, section, orientation, role):
+		if role == Qt.TextAlignmentRole:
+			return self.columnAlignment(section)
+		if role != Qt.DisplayRole:
+			return None
+		if orientation != Qt.Horizontal:
+			return None
+		return self.columnHeader(section)
+
+	def index(self, row, column, parent):
+		return self.createIndex(row, column, self.child_items[row])
+
+	def DisplayData(self, item, index):
+		return item.getData(index.column())
+
+	def FetchIfNeeded(self, row):
+		if row > self.last_row_read:
+			self.last_row_read = row
+			if row + 10 >= self.child_count:
+				self.fetcher.Fetch(glb_chunk_sz)
+
 	def columnAlignment(self, column):
 		return Qt.AlignLeft
 
@@ -620,6 +687,601 @@ class CallGraphWindow(QMdiSubWindow):
 		if not found:
 			self.find_bar.NotFound()
 
+# Child data item  finder
+
+class ChildDataItemFinder():
+
+	def __init__(self, root):
+		self.root = root
+		self.value, self.direction, self.pattern, self.last_value, self.last_pattern = (None,) * 5
+		self.rows = []
+		self.pos = 0
+
+	def FindSelect(self):
+		self.rows = []
+		if self.pattern:
+			pattern = re.compile(self.value)
+			for child in self.root.child_items:
+				for column_data in child.data:
+					if re.search(pattern, str(column_data)) is not None:
+						self.rows.append(child.row)
+						break
+		else:
+			for child in self.root.child_items:
+				for column_data in child.data:
+					if self.value in str(column_data):
+						self.rows.append(child.row)
+						break
+
+	def FindValue(self):
+		self.pos = 0
+		if self.last_value != self.value or self.pattern != self.last_pattern:
+			self.FindSelect()
+		if not len(self.rows):
+			return -1
+		return self.rows[self.pos]
+
+	def FindThread(self):
+		if self.direction == 0 or self.value != self.last_value or self.pattern != self.last_pattern:
+			row = self.FindValue()
+		elif len(self.rows):
+			if self.direction > 0:
+				self.pos += 1
+				if self.pos >= len(self.rows):
+					self.pos = 0
+			else:
+				self.pos -= 1
+				if self.pos < 0:
+					self.pos = len(self.rows) - 1
+			row = self.rows[self.pos]
+		else:
+			row = -1
+		return (True, row)
+
+	def Find(self, value, direction, pattern, context, callback):
+		self.value, self.direction, self.pattern, self.last_value, self.last_pattern = (value, direction,pattern, self.value, self.pattern)
+		# Use a thread so the UI is not blocked
+		thread = Thread(self.FindThread)
+		thread.done.connect(lambda row, t=thread, c=callback: self.FindDone(t, c, row), Qt.QueuedConnection)
+		thread.start()
+
+	def FindDone(self, thread, callback, row):
+		callback(row)
+
+# Number of database records to fetch in one go
+
+glb_chunk_sz = 10000
+
+# size of pickled integer big enough for record size
+
+glb_nsz = 8
+
+# Background process for SQL data fetcher
+
+class SQLFetcherProcess():
+
+	def __init__(self, dbref, sql, buffer, head, tail, fetch_count, fetching_done, process_target, wait_event, fetched_event, prep):
+		# Need a unique connection name
+		conn_name = "SQLFetcher" + str(os.getpid())
+		self.db, dbname = dbref.Open(conn_name)
+		self.sql = sql
+		self.buffer = buffer
+		self.head = head
+		self.tail = tail
+		self.fetch_count = fetch_count
+		self.fetching_done = fetching_done
+		self.process_target = process_target
+		self.wait_event = wait_event
+		self.fetched_event = fetched_event
+		self.prep = prep
+		self.query = QSqlQuery(self.db)
+		self.query_limit = 0 if "$$last_id$$" in sql else 2
+		self.last_id = -1
+		self.fetched = 0
+		self.more = True
+		self.local_head = self.head.value
+		self.local_tail = self.tail.value
+
+	def Select(self):
+		if self.query_limit:
+			if self.query_limit == 1:
+				return
+			self.query_limit -= 1
+		stmt = self.sql.replace("$$last_id$$", str(self.last_id))
+		QueryExec(self.query, stmt)
+
+	def Next(self):
+		if not self.query.next():
+			self.Select()
+			if not self.query.next():
+				return None
+		self.last_id = self.query.value(0)
+		return self.prep(self.query)
+
+	def WaitForTarget(self):
+		while True:
+			self.wait_event.clear()
+			target = self.process_target.value
+			if target > self.fetched or target < 0:
+				break
+			self.wait_event.wait()
+		return target
+
+	def HasSpace(self, sz):
+		if self.local_tail <= self.local_head:
+			space = len(self.buffer) - self.local_head
+			if space > sz:
+				return True
+			if space >= glb_nsz:
+				# Use 0 (or space < glb_nsz) to mean there is no more at the top of the buffer
+				nd = cPickle.dumps(0, cPickle.HIGHEST_PROTOCOL)
+				self.buffer[self.local_head : self.local_head + len(nd)] = nd
+			self.local_head = 0
+		if self.local_tail - self.local_head > sz:
+			return True
+		return False
+
+	def WaitForSpace(self, sz):
+		if self.HasSpace(sz):
+			return
+		while True:
+			self.wait_event.clear()
+			self.local_tail = self.tail.value
+			if self.HasSpace(sz):
+				return
+			self.wait_event.wait()
+
+	def AddToBuffer(self, obj):
+		d = cPickle.dumps(obj, cPickle.HIGHEST_PROTOCOL)
+		n = len(d)
+		nd = cPickle.dumps(n, cPickle.HIGHEST_PROTOCOL)
+		sz = n + glb_nsz
+		self.WaitForSpace(sz)
+		pos = self.local_head
+		self.buffer[pos : pos + len(nd)] = nd
+		self.buffer[pos + glb_nsz : pos + sz] = d
+		self.local_head += sz
+
+	def FetchBatch(self, batch_size):
+		fetched = 0
+		while batch_size > fetched:
+			obj = self.Next()
+			if obj is None:
+				self.more = False
+				break
+			self.AddToBuffer(obj)
+			fetched += 1
+		if fetched:
+			self.fetched += fetched
+			with self.fetch_count.get_lock():
+				self.fetch_count.value += fetched
+			self.head.value = self.local_head
+			self.fetched_event.set()
+
+	def Run(self):
+		while self.more:
+			target = self.WaitForTarget()
+			if target < 0:
+				break
+			batch_size = min(glb_chunk_sz, target - self.fetched)
+			self.FetchBatch(batch_size)
+		self.fetching_done.value = True
+		self.fetched_event.set()
+
+def SQLFetcherFn(*x):
+	process = SQLFetcherProcess(*x)
+	process.Run()
+
+# SQL data fetcher
+
+class SQLFetcher(QObject):
+
+	done = Signal(object)
+
+	def __init__(self, glb, sql, prep, process_data, parent=None):
+		super(SQLFetcher, self).__init__(parent)
+		self.process_data = process_data
+		self.more = True
+		self.target = 0
+		self.last_target = 0
+		self.fetched = 0
+		self.buffer_size = 16 * 1024 * 1024
+		self.buffer = Array(c_char, self.buffer_size, lock=False)
+		self.head = Value(c_longlong)
+		self.tail = Value(c_longlong)
+		self.local_tail = 0
+		self.fetch_count = Value(c_longlong)
+		self.fetching_done = Value(c_bool)
+		self.last_count = 0
+		self.process_target = Value(c_longlong)
+		self.wait_event = Event()
+		self.fetched_event = Event()
+		glb.AddInstanceToShutdownOnExit(self)
+		self.process = Process(target=SQLFetcherFn, args=(glb.dbref, sql, self.buffer, self.head, self.tail, self.fetch_count, self.fetching_done, self.process_target, self.wait_event, self.fetched_event, prep))
+		self.process.start()
+		self.thread = Thread(self.Thread)
+		self.thread.done.connect(self.ProcessData, Qt.QueuedConnection)
+		self.thread.start()
+
+	def Shutdown(self):
+		# Tell the thread and process to exit
+		self.process_target.value = -1
+		self.wait_event.set()
+		self.more = False
+		self.fetching_done.value = True
+		self.fetched_event.set()
+
+	def Thread(self):
+		if not self.more:
+			return True, 0
+		while True:
+			self.fetched_event.clear()
+			fetch_count = self.fetch_count.value
+			if fetch_count != self.last_count:
+				break
+			if self.fetching_done.value:
+				self.more = False
+				return True, 0
+			self.fetched_event.wait()
+		count = fetch_count - self.last_count
+		self.last_count = fetch_count
+		self.fetched += count
+		return False, count
+
+	def Fetch(self, nr):
+		if not self.more:
+			# -1 inidcates there are no more
+			return -1
+		result = self.fetched
+		extra = result + nr - self.target
+		if extra > 0:
+			self.target += extra
+			# process_target < 0 indicates shutting down
+			if self.process_target.value >= 0:
+				self.process_target.value = self.target
+			self.wait_event.set()
+		return result
+
+	def RemoveFromBuffer(self):
+		pos = self.local_tail
+		if len(self.buffer) - pos < glb_nsz:
+			pos = 0
+		n = cPickle.loads(self.buffer[pos : pos + glb_nsz])
+		if n == 0:
+			pos = 0
+			n = cPickle.loads(self.buffer[0 : glb_nsz])
+		pos += glb_nsz
+		obj = cPickle.loads(self.buffer[pos : pos + n])
+		self.local_tail = pos + n
+		return obj
+
+	def ProcessData(self, count):
+		for i in xrange(count):
+			obj = self.RemoveFromBuffer()
+			self.process_data(obj)
+		self.tail.value = self.local_tail
+		self.wait_event.set()
+		self.done.emit(count)
+
+# Fetch more records bar
+
+class FetchMoreRecordsBar():
+
+	def __init__(self, model, parent):
+		self.model = model
+
+		self.label = QLabel("Number of records (x " + "{:,}".format(glb_chunk_sz) + ") to fetch:")
+		self.label.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.fetch_count = QSpinBox()
+		self.fetch_count.setRange(1, 1000000)
+		self.fetch_count.setValue(10)
+		self.fetch_count.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+
+		self.fetch = QPushButton("Go!")
+		self.fetch.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed)
+		self.fetch.released.connect(self.FetchMoreRecords)
+
+		self.progress = QProgressBar()
+		self.progress.setRange(0, 100)
+		self.progress.hide()
+
+		self.done_label = QLabel("All records fetched")
+		self.done_label.hide()
+
+		self.spacer = QLabel("")
+
+		self.close_button = QToolButton()
+		self.close_button.setIcon(parent.style().standardIcon(QStyle.SP_DockWidgetCloseButton))
+		self.close_button.released.connect(self.Deactivate)
+
+		self.hbox = QHBoxLayout()
+		self.hbox.setContentsMargins(0, 0, 0, 0)
+
+		self.hbox.addWidget(self.label)
+		self.hbox.addWidget(self.fetch_count)
+		self.hbox.addWidget(self.fetch)
+		self.hbox.addWidget(self.spacer)
+		self.hbox.addWidget(self.progress)
+		self.hbox.addWidget(self.done_label)
+		self.hbox.addWidget(self.close_button)
+
+		self.bar = QWidget()
+		self.bar.setLayout(self.hbox);
+		self.bar.show()
+
+		self.in_progress = False
+		self.model.progress.connect(self.Progress)
+
+		self.done = False
+
+		if not model.HasMoreRecords():
+			self.Done()
+
+	def Widget(self):
+		return self.bar
+
+	def Activate(self):
+		self.bar.show()
+		self.fetch.setFocus()
+
+	def Deactivate(self):
+		self.bar.hide()
+
+	def Enable(self, enable):
+		self.fetch.setEnabled(enable)
+		self.fetch_count.setEnabled(enable)
+
+	def Busy(self):
+		self.Enable(False)
+		self.fetch.hide()
+		self.spacer.hide()
+		self.progress.show()
+
+	def Idle(self):
+		self.in_progress = False
+		self.Enable(True)
+		self.progress.hide()
+		self.fetch.show()
+		self.spacer.show()
+
+	def Target(self):
+		return self.fetch_count.value() * glb_chunk_sz
+
+	def Done(self):
+		self.done = True
+		self.Idle()
+		self.label.hide()
+		self.fetch_count.hide()
+		self.fetch.hide()
+		self.spacer.hide()
+		self.done_label.show()
+
+	def Progress(self, count):
+		if self.in_progress:
+			if count:
+				percent = ((count - self.start) * 100) / self.Target()
+				if percent >= 100:
+					self.Idle()
+				else:
+					self.progress.setValue(percent)
+		if not count:
+			# Count value of zero means no more records
+			self.Done()
+
+	def FetchMoreRecords(self):
+		if self.done:
+			return
+		self.progress.setValue(0)
+		self.Busy()
+		self.in_progress = True
+		self.start = self.model.FetchMoreRecords(self.Target())
+
+# SQL data preparation
+
+def SQLTableDataPrep(query, count):
+	data = []
+	for i in xrange(count):
+		data.append(query.value(i))
+	return data
+
+# SQL table data model item
+
+class SQLTableItem():
+
+	def __init__(self, row, data):
+		self.row = row
+		self.data = data
+
+	def getData(self, column):
+		return self.data[column]
+
+# SQL table data model
+
+class SQLTableModel(TableModel):
+
+	progress = Signal(object)
+
+	def __init__(self, glb, sql, column_count, parent=None):
+		super(SQLTableModel, self).__init__(parent)
+		self.glb = glb
+		self.more = True
+		self.populated = 0
+		self.fetcher = SQLFetcher(glb, sql, lambda x, y=column_count: SQLTableDataPrep(x, y), self.AddSample)
+		self.fetcher.done.connect(self.Update)
+		self.fetcher.Fetch(glb_chunk_sz)
+
+	def DisplayData(self, item, index):
+		self.FetchIfNeeded(item.row)
+		return item.getData(index.column())
+
+	def AddSample(self, data):
+		child = SQLTableItem(self.populated, data)
+		self.child_items.append(child)
+		self.populated += 1
+
+	def Update(self, fetched):
+		if not fetched:
+			self.more = False
+			self.progress.emit(0)
+		child_count = self.child_count
+		count = self.populated - child_count
+		if count > 0:
+			parent = QModelIndex()
+			self.beginInsertRows(parent, child_count, child_count + count - 1)
+			self.insertRows(child_count, count, parent)
+			self.child_count += count
+			self.endInsertRows()
+			self.progress.emit(self.child_count)
+
+	def FetchMoreRecords(self, count):
+		current = self.child_count
+		if self.more:
+			self.fetcher.Fetch(count)
+		else:
+			self.progress.emit(0)
+		return current
+
+	def HasMoreRecords(self):
+		return self.more
+
+# SQL automatic table data model
+
+class SQLAutoTableModel(SQLTableModel):
+
+	def __init__(self, glb, table_name, parent=None):
+		sql = "SELECT * FROM " + table_name + " WHERE id > $$last_id$$ ORDER BY id LIMIT " + str(glb_chunk_sz)
+		if table_name == "comm_threads_view":
+			# For now, comm_threads_view has no id column
+			sql = "SELECT * FROM " + table_name + " WHERE comm_id > $$last_id$$ ORDER BY comm_id LIMIT " + str(glb_chunk_sz)
+		self.column_headers = []
+		query = QSqlQuery(glb.db)
+		if glb.dbref.is_sqlite3:
+			QueryExec(query, "PRAGMA table_info(" + table_name + ")")
+			while query.next():
+				self.column_headers.append(query.value(1))
+			if table_name == "sqlite_master":
+				sql = "SELECT * FROM " + table_name
+		else:
+			if table_name[:19] == "information_schema.":
+				sql = "SELECT * FROM " + table_name
+				select_table_name = table_name[19:]
+				schema = "information_schema"
+			else:
+				select_table_name = table_name
+				schema = "public"
+			QueryExec(query, "SELECT column_name FROM information_schema.columns WHERE table_schema = '" + schema + "' and table_name = '" + select_table_name + "'")
+			while query.next():
+				self.column_headers.append(query.value(0))
+		super(SQLAutoTableModel, self).__init__(glb, sql, len(self.column_headers), parent)
+
+	def columnCount(self, parent=None):
+		return len(self.column_headers)
+
+	def columnHeader(self, column):
+		return self.column_headers[column]
+
+# Base class for custom ResizeColumnsToContents
+
+class ResizeColumnsToContentsBase(QObject):
+
+	def __init__(self, parent=None):
+		super(ResizeColumnsToContentsBase, self).__init__(parent)
+
+	def ResizeColumnToContents(self, column, n):
+		# Using the view's resizeColumnToContents() here is extrememly slow
+		# so implement a crude alternative
+		font = self.view.font()
+		metrics = QFontMetrics(font)
+		max = 0
+		for row in xrange(n):
+			val = self.data_model.child_items[row].data[column]
+			len = metrics.width(str(val) + "MM")
+			max = len if len > max else max
+		val = self.data_model.columnHeader(column)
+		len = metrics.width(str(val) + "MM")
+		max = len if len > max else max
+		self.view.setColumnWidth(column, max)
+
+	def ResizeColumnsToContents(self):
+		n = min(self.data_model.child_count, 100)
+		if n < 1:
+			# No data yet, so connect a signal to notify when there is
+			self.data_model.rowsInserted.connect(self.UpdateColumnWidths)
+			return
+		columns = self.data_model.columnCount()
+		for i in xrange(columns):
+			self.ResizeColumnToContents(i, n)
+
+	def UpdateColumnWidths(self, *x):
+		# This only needs to be done once, so disconnect the signal now
+		self.data_model.rowsInserted.disconnect(self.UpdateColumnWidths)
+		self.ResizeColumnsToContents()
+
+# Table window
+
+class TableWindow(QMdiSubWindow, ResizeColumnsToContentsBase):
+
+	def __init__(self, glb, table_name, parent=None):
+		super(TableWindow, self).__init__(parent)
+
+		self.data_model = LookupCreateModel(table_name + " Table", lambda: SQLAutoTableModel(glb, table_name))
+
+		self.model = QSortFilterProxyModel()
+		self.model.setSourceModel(self.data_model)
+
+		self.view = QTableView()
+		self.view.setModel(self.model)
+		self.view.setEditTriggers(QAbstractItemView.NoEditTriggers)
+		self.view.verticalHeader().setVisible(False)
+		self.view.sortByColumn(-1, Qt.AscendingOrder)
+		self.view.setSortingEnabled(True)
+
+		self.ResizeColumnsToContents()
+
+		self.find_bar = FindBar(self, self, True)
+
+		self.finder = ChildDataItemFinder(self.data_model)
+
+		self.fetch_bar = FetchMoreRecordsBar(self.data_model, self)
+
+		self.vbox = VBox(self.view, self.find_bar.Widget(), self.fetch_bar.Widget())
+
+		self.setWidget(self.vbox.Widget())
+
+		AddSubWindow(glb.mainwindow.mdi_area, self, table_name + " Table")
+
+	def Find(self, value, direction, pattern, context):
+		self.view.setFocus()
+		self.find_bar.Busy()
+		self.finder.Find(value, direction, pattern, context, self.FindDone)
+
+	def FindDone(self, row):
+		self.find_bar.Idle()
+		if row >= 0:
+			self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex()))
+		else:
+			self.find_bar.NotFound()
+
+# Table list
+
+def GetTableList(glb):
+	tables = []
+	query = QSqlQuery(glb.db)
+	if glb.dbref.is_sqlite3:
+		QueryExec(query, "SELECT name FROM sqlite_master WHERE type IN ( 'table' , 'view' ) ORDER BY name")
+	else:
+		QueryExec(query, "SELECT table_name FROM information_schema.tables WHERE table_schema = 'public' AND table_type IN ( 'BASE TABLE' , 'VIEW' ) ORDER BY table_name")
+	while query.next():
+		tables.append(query.value(0))
+	if glb.dbref.is_sqlite3:
+		tables.append("sqlite_master")
+	else:
+		tables.append("information_schema.tables")
+		tables.append("information_schema.views")
+		tables.append("information_schema.columns")
+	return tables
+
 # Action Definition
 
 def CreateAction(label, tip, callback, parent=None, shortcut=None):
@@ -779,12 +1441,15 @@ class MainWindow(QMainWindow):
 
 		edit_menu = menu.addMenu("&Edit")
 		edit_menu.addAction(CreateAction("&Find...", "Find items", self.Find, self, QKeySequence.Find))
+		edit_menu.addAction(CreateAction("Fetch &more records...", "Fetch more records", self.FetchMoreRecords, self, [QKeySequence(Qt.Key_F8)]))
 		edit_menu.addAction(CreateAction("&Shrink Font", "Make text smaller", self.ShrinkFont, self, [QKeySequence("Ctrl+-")]))
 		edit_menu.addAction(CreateAction("&Enlarge Font", "Make text bigger", self.EnlargeFont, self, [QKeySequence("Ctrl++")]))
 
 		reports_menu = menu.addMenu("&Reports")
 		reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
 
+		self.TableMenu(GetTableList(glb), menu)
+
 		self.window_menu = WindowMenu(self.mdi_area, menu)
 
 	def Find(self):
@@ -795,6 +1460,14 @@ class MainWindow(QMainWindow):
 			except:
 				pass
 
+	def FetchMoreRecords(self):
+		win = self.mdi_area.activeSubWindow()
+		if win:
+			try:
+				win.fetch_bar.Activate()
+			except:
+				pass
+
 	def ShrinkFont(self):
 		win = self.mdi_area.activeSubWindow()
 		ShrinkFont(win.view)
@@ -803,9 +1476,17 @@ class MainWindow(QMainWindow):
 		win = self.mdi_area.activeSubWindow()
 		EnlargeFont(win.view)
 
+	def TableMenu(self, tables, menu):
+		table_menu = menu.addMenu("&Tables")
+		for table in tables:
+			table_menu.addAction(CreateAction(table, "Create a new window containing a table view", lambda t=table: self.NewTableView(t), self))
+
 	def NewCallGraph(self):
 		CallGraphWindow(self.glb, self)
 
+	def NewTableView(self, table_name):
+		TableWindow(self.glb, table_name, self)
+
 # Global data
 
 class Glb():
@@ -816,6 +1497,18 @@ class Glb():
 		self.dbname = dbname
 		self.app = None
 		self.mainwindow = None
+		self.instances_to_shutdown_on_exit = weakref.WeakSet()
+
+	def AddInstanceToShutdownOnExit(self, instance):
+		self.instances_to_shutdown_on_exit.add(instance)
+
+	# Shutdown any background processes or threads
+	def ShutdownInstances(self):
+		for x in self.instances_to_shutdown_on_exit:
+			try:
+				x.Shutdown()
+			except:
+				pass
 
 # Database reference
 
@@ -880,6 +1573,7 @@ def Main():
 	glb.mainwindow = mainwindow
 	mainwindow.show()
 	err = app.exec_()
+	glb.ShutdownInstances()
 	db.close()
 	sys.exit(err)
 
-- 
cgit v1.2.3-58-ga151


From 76099f98aea4606f7c96b8d2366b46840529d08f Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 23 Oct 2018 10:59:49 +0300
Subject: perf scripts python: exported-sql-viewer.py: Add All branches report

Add a report to display branches in a similar fashion to perf script. The
main purpose of this report is to display disassembly, however, presently,
the only supported disassembler is Intel XED, and additionally the object
code must be present in perf build ID cache.

To use Intel XED, libxed.so must be present. To build and install
libxed.so:
	git clone https://github.com/intelxed/mbuild.git mbuild
	git clone https://github.com/intelxed/xed
	cd xed
	./mfile.py --share
	sudo ./mfile.py --prefix=/usr/local install
	sudo ldconfig

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20181023075949.18920-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/scripts/python/exported-sql-viewer.py | 547 +++++++++++++++++++++++
 1 file changed, 547 insertions(+)

(limited to 'tools/perf')

diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index ef822d850109..24cb0bd56afa 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -46,6 +46,48 @@
 #	'Branch Count' is the total number of branches for that function and all
 #       functions that it calls
 
+# There is also a "All branches" report, which displays branches and
+# possibly disassembly.  However, presently, the only supported disassembler is
+# Intel XED, and additionally the object code must be present in perf build ID
+# cache. To use Intel XED, libxed.so must be present. To build and install
+# libxed.so:
+#            git clone https://github.com/intelxed/mbuild.git mbuild
+#            git clone https://github.com/intelxed/xed
+#            cd xed
+#            ./mfile.py --share
+#            sudo ./mfile.py --prefix=/usr/local install
+#            sudo ldconfig
+#
+# Example report:
+#
+# Time           CPU  Command  PID    TID    Branch Type            In Tx  Branch
+# 8107675239590  2    ls       22011  22011  return from interrupt  No     ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea260 _start (ld-2.19.so)
+#                                                                              7fab593ea260 48 89 e7                                        mov %rsp, %rdi
+# 8107675239899  2    ls       22011  22011  hardware interrupt     No         7fab593ea260 _start (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel])
+# 8107675241900  2    ls       22011  22011  return from interrupt  No     ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea260 _start (ld-2.19.so)
+#                                                                              7fab593ea260 48 89 e7                                        mov %rsp, %rdi
+#                                                                              7fab593ea263 e8 c8 06 00 00                                  callq  0x7fab593ea930
+# 8107675241900  2    ls       22011  22011  call                   No         7fab593ea263 _start+0x3 (ld-2.19.so) -> 7fab593ea930 _dl_start (ld-2.19.so)
+#                                                                              7fab593ea930 55                                              pushq  %rbp
+#                                                                              7fab593ea931 48 89 e5                                        mov %rsp, %rbp
+#                                                                              7fab593ea934 41 57                                           pushq  %r15
+#                                                                              7fab593ea936 41 56                                           pushq  %r14
+#                                                                              7fab593ea938 41 55                                           pushq  %r13
+#                                                                              7fab593ea93a 41 54                                           pushq  %r12
+#                                                                              7fab593ea93c 53                                              pushq  %rbx
+#                                                                              7fab593ea93d 48 89 fb                                        mov %rdi, %rbx
+#                                                                              7fab593ea940 48 83 ec 68                                     sub $0x68, %rsp
+#                                                                              7fab593ea944 0f 31                                           rdtsc
+#                                                                              7fab593ea946 48 c1 e2 20                                     shl $0x20, %rdx
+#                                                                              7fab593ea94a 89 c0                                           mov %eax, %eax
+#                                                                              7fab593ea94c 48 09 c2                                        or %rax, %rdx
+#                                                                              7fab593ea94f 48 8b 05 1a 15 22 00                            movq  0x22151a(%rip), %rax
+# 8107675242232  2    ls       22011  22011  hardware interrupt     No         7fab593ea94f _dl_start+0x1f (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel])
+# 8107675242900  2    ls       22011  22011  return from interrupt  No     ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea94f _dl_start+0x1f (ld-2.19.so)
+#                                                                              7fab593ea94f 48 8b 05 1a 15 22 00                            movq  0x22151a(%rip), %rax
+#                                                                              7fab593ea956 48 89 15 3b 13 22 00                            movq  %rdx, 0x22133b(%rip)
+# 8107675243232  2    ls       22011  22011  hardware interrupt     No         7fab593ea956 _dl_start+0x26 (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel])
+
 import sys
 import weakref
 import threading
@@ -62,6 +104,16 @@ from multiprocessing import Process, Array, Value, Event
 
 # Data formatting helpers
 
+def tohex(ip):
+	if ip < 0:
+		ip += 1 << 64
+	return "%x" % ip
+
+def offstr(offset):
+	if offset:
+		return "+0x%x" % offset
+	return ""
+
 def dsoname(name):
 	if name == "[kernel.kallsyms]":
 		return "[kernel]"
@@ -1077,6 +1129,351 @@ class FetchMoreRecordsBar():
 		self.in_progress = True
 		self.start = self.model.FetchMoreRecords(self.Target())
 
+# Brance data model level two item
+
+class BranchLevelTwoItem():
+
+	def __init__(self, row, text, parent_item):
+		self.row = row
+		self.parent_item = parent_item
+		self.data = [""] * 8
+		self.data[7] = text
+		self.level = 2
+
+	def getParentItem(self):
+		return self.parent_item
+
+	def getRow(self):
+		return self.row
+
+	def childCount(self):
+		return 0
+
+	def hasChildren(self):
+		return False
+
+	def getData(self, column):
+		return self.data[column]
+
+# Brance data model level one item
+
+class BranchLevelOneItem():
+
+	def __init__(self, glb, row, data, parent_item):
+		self.glb = glb
+		self.row = row
+		self.parent_item = parent_item
+		self.child_count = 0
+		self.child_items = []
+		self.data = data[1:]
+		self.dbid = data[0]
+		self.level = 1
+		self.query_done = False
+
+	def getChildItem(self, row):
+		return self.child_items[row]
+
+	def getParentItem(self):
+		return self.parent_item
+
+	def getRow(self):
+		return self.row
+
+	def Select(self):
+		self.query_done = True
+
+		if not self.glb.have_disassembler:
+			return
+
+		query = QSqlQuery(self.glb.db)
+
+		QueryExec(query, "SELECT cpu, to_dso_id, to_symbol_id, to_sym_offset, short_name, long_name, build_id, sym_start, to_ip"
+				  " FROM samples"
+				  " INNER JOIN dsos ON samples.to_dso_id = dsos.id"
+				  " INNER JOIN symbols ON samples.to_symbol_id = symbols.id"
+				  " WHERE samples.id = " + str(self.dbid))
+		if not query.next():
+			return
+		cpu = query.value(0)
+		dso = query.value(1)
+		sym = query.value(2)
+		if dso == 0 or sym == 0:
+			return
+		off = query.value(3)
+		short_name = query.value(4)
+		long_name = query.value(5)
+		build_id = query.value(6)
+		sym_start = query.value(7)
+		ip = query.value(8)
+
+		QueryExec(query, "SELECT samples.dso_id, symbol_id, sym_offset, sym_start"
+				  " FROM samples"
+				  " INNER JOIN symbols ON samples.symbol_id = symbols.id"
+				  " WHERE samples.id > " + str(self.dbid) + " AND cpu = " + str(cpu) +
+				  " ORDER BY samples.id"
+				  " LIMIT 1")
+		if not query.next():
+			return
+		if query.value(0) != dso:
+			# Cannot disassemble from one dso to another
+			return
+		bsym = query.value(1)
+		boff = query.value(2)
+		bsym_start = query.value(3)
+		if bsym == 0:
+			return
+		tot = bsym_start + boff + 1 - sym_start - off
+		if tot <= 0 or tot > 16384:
+			return
+
+		inst = self.glb.disassembler.Instruction()
+		f = self.glb.FileFromNamesAndBuildId(short_name, long_name, build_id)
+		if not f:
+			return
+		mode = 0 if Is64Bit(f) else 1
+		self.glb.disassembler.SetMode(inst, mode)
+
+		buf_sz = tot + 16
+		buf = create_string_buffer(tot + 16)
+		f.seek(sym_start + off)
+		buf.value = f.read(buf_sz)
+		buf_ptr = addressof(buf)
+		i = 0
+		while tot > 0:
+			cnt, text = self.glb.disassembler.DisassembleOne(inst, buf_ptr, buf_sz, ip)
+			if cnt:
+				byte_str = tohex(ip).rjust(16)
+				for k in xrange(cnt):
+					byte_str += " %02x" % ord(buf[i])
+					i += 1
+				while k < 15:
+					byte_str += "   "
+					k += 1
+				self.child_items.append(BranchLevelTwoItem(0, byte_str + " " + text, self))
+				self.child_count += 1
+			else:
+				return
+			buf_ptr += cnt
+			tot -= cnt
+			buf_sz -= cnt
+			ip += cnt
+
+	def childCount(self):
+		if not self.query_done:
+			self.Select()
+			if not self.child_count:
+				return -1
+		return self.child_count
+
+	def hasChildren(self):
+		if not self.query_done:
+			return True
+		return self.child_count > 0
+
+	def getData(self, column):
+		return self.data[column]
+
+# Brance data model root item
+
+class BranchRootItem():
+
+	def __init__(self):
+		self.child_count = 0
+		self.child_items = []
+		self.level = 0
+
+	def getChildItem(self, row):
+		return self.child_items[row]
+
+	def getParentItem(self):
+		return None
+
+	def getRow(self):
+		return 0
+
+	def childCount(self):
+		return self.child_count
+
+	def hasChildren(self):
+		return self.child_count > 0
+
+	def getData(self, column):
+		return ""
+
+# Branch data preparation
+
+def BranchDataPrep(query):
+	data = []
+	for i in xrange(0, 8):
+		data.append(query.value(i))
+	data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) +
+			" (" + dsoname(query.value(11)) + ")" + " -> " +
+			tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) +
+			" (" + dsoname(query.value(15)) + ")")
+	return data
+
+# Branch data model
+
+class BranchModel(TreeModel):
+
+	progress = Signal(object)
+
+	def __init__(self, glb, event_id, where_clause, parent=None):
+		super(BranchModel, self).__init__(BranchRootItem(), parent)
+		self.glb = glb
+		self.event_id = event_id
+		self.more = True
+		self.populated = 0
+		sql = ("SELECT samples.id, time, cpu, comm, pid, tid, branch_types.name,"
+			" CASE WHEN in_tx = '0' THEN 'No' ELSE 'Yes' END,"
+			" ip, symbols.name, sym_offset, dsos.short_name,"
+			" to_ip, to_symbols.name, to_sym_offset, to_dsos.short_name"
+			" FROM samples"
+			" INNER JOIN comms ON comm_id = comms.id"
+			" INNER JOIN threads ON thread_id = threads.id"
+			" INNER JOIN branch_types ON branch_type = branch_types.id"
+			" INNER JOIN symbols ON symbol_id = symbols.id"
+			" INNER JOIN symbols to_symbols ON to_symbol_id = to_symbols.id"
+			" INNER JOIN dsos ON samples.dso_id = dsos.id"
+			" INNER JOIN dsos AS to_dsos ON samples.to_dso_id = to_dsos.id"
+			" WHERE samples.id > $$last_id$$" + where_clause +
+			" AND evsel_id = " + str(self.event_id) +
+			" ORDER BY samples.id"
+			" LIMIT " + str(glb_chunk_sz))
+		self.fetcher = SQLFetcher(glb, sql, BranchDataPrep, self.AddSample)
+		self.fetcher.done.connect(self.Update)
+		self.fetcher.Fetch(glb_chunk_sz)
+
+	def columnCount(self, parent=None):
+		return 8
+
+	def columnHeader(self, column):
+		return ("Time", "CPU", "Command", "PID", "TID", "Branch Type", "In Tx", "Branch")[column]
+
+	def columnFont(self, column):
+		if column != 7:
+			return None
+		return QFont("Monospace")
+
+	def DisplayData(self, item, index):
+		if item.level == 1:
+			self.FetchIfNeeded(item.row)
+		return item.getData(index.column())
+
+	def AddSample(self, data):
+		child = BranchLevelOneItem(self.glb, self.populated, data, self.root)
+		self.root.child_items.append(child)
+		self.populated += 1
+
+	def Update(self, fetched):
+		if not fetched:
+			self.more = False
+			self.progress.emit(0)
+		child_count = self.root.child_count
+		count = self.populated - child_count
+		if count > 0:
+			parent = QModelIndex()
+			self.beginInsertRows(parent, child_count, child_count + count - 1)
+			self.insertRows(child_count, count, parent)
+			self.root.child_count += count
+			self.endInsertRows()
+			self.progress.emit(self.root.child_count)
+
+	def FetchMoreRecords(self, count):
+		current = self.root.child_count
+		if self.more:
+			self.fetcher.Fetch(count)
+		else:
+			self.progress.emit(0)
+		return current
+
+	def HasMoreRecords(self):
+		return self.more
+
+# Branch window
+
+class BranchWindow(QMdiSubWindow):
+
+	def __init__(self, glb, event_id, name, where_clause, parent=None):
+		super(BranchWindow, self).__init__(parent)
+
+		model_name = "Branch Events " + str(event_id)
+		if len(where_clause):
+			model_name = where_clause + " " + model_name
+
+		self.model = LookupCreateModel(model_name, lambda: BranchModel(glb, event_id, where_clause))
+
+		self.view = QTreeView()
+		self.view.setUniformRowHeights(True)
+		self.view.setModel(self.model)
+
+		self.ResizeColumnsToContents()
+
+		self.find_bar = FindBar(self, self, True)
+
+		self.finder = ChildDataItemFinder(self.model.root)
+
+		self.fetch_bar = FetchMoreRecordsBar(self.model, self)
+
+		self.vbox = VBox(self.view, self.find_bar.Widget(), self.fetch_bar.Widget())
+
+		self.setWidget(self.vbox.Widget())
+
+		AddSubWindow(glb.mainwindow.mdi_area, self, name + " Branch Events")
+
+	def ResizeColumnToContents(self, column, n):
+		# Using the view's resizeColumnToContents() here is extrememly slow
+		# so implement a crude alternative
+		mm = "MM" if column else "MMMM"
+		font = self.view.font()
+		metrics = QFontMetrics(font)
+		max = 0
+		for row in xrange(n):
+			val = self.model.root.child_items[row].data[column]
+			len = metrics.width(str(val) + mm)
+			max = len if len > max else max
+		val = self.model.columnHeader(column)
+		len = metrics.width(str(val) + mm)
+		max = len if len > max else max
+		self.view.setColumnWidth(column, max)
+
+	def ResizeColumnsToContents(self):
+		n = min(self.model.root.child_count, 100)
+		if n < 1:
+			# No data yet, so connect a signal to notify when there is
+			self.model.rowsInserted.connect(self.UpdateColumnWidths)
+			return
+		columns = self.model.columnCount()
+		for i in xrange(columns):
+			self.ResizeColumnToContents(i, n)
+
+	def UpdateColumnWidths(self, *x):
+		# This only needs to be done once, so disconnect the signal now
+		self.model.rowsInserted.disconnect(self.UpdateColumnWidths)
+		self.ResizeColumnsToContents()
+
+	def Find(self, value, direction, pattern, context):
+		self.view.setFocus()
+		self.find_bar.Busy()
+		self.finder.Find(value, direction, pattern, context, self.FindDone)
+
+	def FindDone(self, row):
+		self.find_bar.Idle()
+		if row >= 0:
+			self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex()))
+		else:
+			self.find_bar.NotFound()
+
+# Event list
+
+def GetEventList(db):
+	events = []
+	query = QSqlQuery(db)
+	QueryExec(query, "SELECT name FROM selected_events WHERE id > 0 ORDER BY id")
+	while query.next():
+		events.append(query.value(0))
+	return events
+
 # SQL data preparation
 
 def SQLTableDataPrep(query, count):
@@ -1448,6 +1845,8 @@ class MainWindow(QMainWindow):
 		reports_menu = menu.addMenu("&Reports")
 		reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self))
 
+		self.EventMenu(GetEventList(glb.db), reports_menu)
+
 		self.TableMenu(GetTableList(glb), menu)
 
 		self.window_menu = WindowMenu(self.mdi_area, menu)
@@ -1476,6 +1875,20 @@ class MainWindow(QMainWindow):
 		win = self.mdi_area.activeSubWindow()
 		EnlargeFont(win.view)
 
+	def EventMenu(self, events, reports_menu):
+		branches_events = 0
+		for event in events:
+			event = event.split(":")[0]
+			if event == "branches":
+				branches_events += 1
+		dbid = 0
+		for event in events:
+			dbid += 1
+			event = event.split(":")[0]
+			if event == "branches":
+				label = "All branches" if branches_events == 1 else "All branches " + "(id=" + dbid + ")"
+				reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewBranchView(x), self))
+
 	def TableMenu(self, tables, menu):
 		table_menu = menu.addMenu("&Tables")
 		for table in tables:
@@ -1484,9 +1897,112 @@ class MainWindow(QMainWindow):
 	def NewCallGraph(self):
 		CallGraphWindow(self.glb, self)
 
+	def NewBranchView(self, event_id):
+		BranchWindow(self.glb, event_id, "", "", self)
+
 	def NewTableView(self, table_name):
 		TableWindow(self.glb, table_name, self)
 
+# XED Disassembler
+
+class xed_state_t(Structure):
+
+	_fields_ = [
+		("mode", c_int),
+		("width", c_int)
+	]
+
+class XEDInstruction():
+
+	def __init__(self, libxed):
+		# Current xed_decoded_inst_t structure is 192 bytes. Use 512 to allow for future expansion
+		xedd_t = c_byte * 512
+		self.xedd = xedd_t()
+		self.xedp = addressof(self.xedd)
+		libxed.xed_decoded_inst_zero(self.xedp)
+		self.state = xed_state_t()
+		self.statep = addressof(self.state)
+		# Buffer for disassembled instruction text
+		self.buffer = create_string_buffer(256)
+		self.bufferp = addressof(self.buffer)
+
+class LibXED():
+
+	def __init__(self):
+		self.libxed = CDLL("libxed.so")
+
+		self.xed_tables_init = self.libxed.xed_tables_init
+		self.xed_tables_init.restype = None
+		self.xed_tables_init.argtypes = []
+
+		self.xed_decoded_inst_zero = self.libxed.xed_decoded_inst_zero
+		self.xed_decoded_inst_zero.restype = None
+		self.xed_decoded_inst_zero.argtypes = [ c_void_p ]
+
+		self.xed_operand_values_set_mode = self.libxed.xed_operand_values_set_mode
+		self.xed_operand_values_set_mode.restype = None
+		self.xed_operand_values_set_mode.argtypes = [ c_void_p, c_void_p ]
+
+		self.xed_decoded_inst_zero_keep_mode = self.libxed.xed_decoded_inst_zero_keep_mode
+		self.xed_decoded_inst_zero_keep_mode.restype = None
+		self.xed_decoded_inst_zero_keep_mode.argtypes = [ c_void_p ]
+
+		self.xed_decode = self.libxed.xed_decode
+		self.xed_decode.restype = c_int
+		self.xed_decode.argtypes = [ c_void_p, c_void_p, c_uint ]
+
+		self.xed_format_context = self.libxed.xed_format_context
+		self.xed_format_context.restype = c_uint
+		self.xed_format_context.argtypes = [ c_int, c_void_p, c_void_p, c_int, c_ulonglong, c_void_p, c_void_p ]
+
+		self.xed_tables_init()
+
+	def Instruction(self):
+		return XEDInstruction(self)
+
+	def SetMode(self, inst, mode):
+		if mode:
+			inst.state.mode = 4 # 32-bit
+			inst.state.width = 4 # 4 bytes
+		else:
+			inst.state.mode = 1 # 64-bit
+			inst.state.width = 8 # 8 bytes
+		self.xed_operand_values_set_mode(inst.xedp, inst.statep)
+
+	def DisassembleOne(self, inst, bytes_ptr, bytes_cnt, ip):
+		self.xed_decoded_inst_zero_keep_mode(inst.xedp)
+		err = self.xed_decode(inst.xedp, bytes_ptr, bytes_cnt)
+		if err:
+			return 0, ""
+		# Use AT&T mode (2), alternative is Intel (3)
+		ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0)
+		if not ok:
+			return 0, ""
+		# Return instruction length and the disassembled instruction text
+		# For now, assume the length is in byte 166
+		return inst.xedd[166], inst.buffer.value
+
+def TryOpen(file_name):
+	try:
+		return open(file_name, "rb")
+	except:
+		return None
+
+def Is64Bit(f):
+	result = sizeof(c_void_p)
+	# ELF support only
+	pos = f.tell()
+	f.seek(0)
+	header = f.read(7)
+	f.seek(pos)
+	magic = header[0:4]
+	eclass = ord(header[4])
+	encoding = ord(header[5])
+	version = ord(header[6])
+	if magic == chr(127) + "ELF" and eclass > 0 and eclass < 3 and encoding > 0 and encoding < 3 and version == 1:
+		result = True if eclass == 2 else False
+	return result
+
 # Global data
 
 class Glb():
@@ -1495,9 +2011,40 @@ class Glb():
 		self.dbref = dbref
 		self.db = db
 		self.dbname = dbname
+		self.home_dir = os.path.expanduser("~")
+		self.buildid_dir = os.getenv("PERF_BUILDID_DIR")
+		if self.buildid_dir:
+			self.buildid_dir += "/.build-id/"
+		else:
+			self.buildid_dir = self.home_dir + "/.debug/.build-id/"
 		self.app = None
 		self.mainwindow = None
 		self.instances_to_shutdown_on_exit = weakref.WeakSet()
+		try:
+			self.disassembler = LibXED()
+			self.have_disassembler = True
+		except:
+			self.have_disassembler = False
+
+	def FileFromBuildId(self, build_id):
+		file_name = self.buildid_dir + build_id[0:2] + "/" + build_id[2:] + "/elf"
+		return TryOpen(file_name)
+
+	def FileFromNamesAndBuildId(self, short_name, long_name, build_id):
+		# Assume current machine i.e. no support for virtualization
+		if short_name[0:7] == "[kernel" and os.path.basename(long_name) == "kcore":
+			file_name = os.getenv("PERF_KCORE")
+			f = TryOpen(file_name) if file_name else None
+			if f:
+				return f
+			# For now, no special handling if long_name is /proc/kcore
+			f = TryOpen(long_name)
+			if f:
+				return f
+		f = self.FileFromBuildId(build_id)
+		if f:
+			return f
+		return None
 
 	def AddInstanceToShutdownOnExit(self, instance):
 		self.instances_to_shutdown_on_exit.add(instance)
-- 
cgit v1.2.3-58-ga151


From b585ebdb5912cf1438d4822f79aaebe36a2d123a Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Thu, 20 Sep 2018 11:05:36 -0700
Subject: perf script: Add --insn-trace for instruction decoding

Add a --insn-trace short hand option for decoding and disassembling
instruction streams for intel_pt. This automatically pipes the output
into the xed disassembler to generate disassembled instructions.  This
just makes this use model much nicer to use.

Before

  % perf record -e intel_pt// ...
  % perf script --itrace=i0ns --ns -F +insn,-event,-period | xed -F insn: -A -64
   swapper 0 [000] 17276.429606186: ffffffff81010486 pt_config ([kernel.kallsyms])    nopl  %eax, (%rax,%rax,1)
   swapper 0 [000] 17276.429606186: ffffffff8101048b pt_config ([kernel.kallsyms])    add $0x10, %rsp
   swapper 0 [000] 17276.429606186: ffffffff8101048f pt_config ([kernel.kallsyms])    popq  %rbx
   swapper 0 [000] 17276.429606186: ffffffff81010490 pt_config ([kernel.kallsyms])    popq  %rbp
   swapper 0 [000] 17276.429606186: ffffffff81010491 pt_config ([kernel.kallsyms])    popq  %r12
   swapper 0 [000] 17276.429606186: ffffffff81010493 pt_config ([kernel.kallsyms])    popq  %r13
   swapper 0 [000] 17276.429606186: ffffffff81010495 pt_config ([kernel.kallsyms])    popq  %r14
   swapper 0 [000] 17276.429606186: ffffffff81010497 pt_config ([kernel.kallsyms])    popq  %r15
   swapper 0 [000] 17276.429606186: ffffffff81010499 pt_config ([kernel.kallsyms])    retq
   swapper 0 [000] 17276.429606186: ffffffff8101063e pt_event_add ([kernel.kallsyms])         cmpl  $0x1, 0x1b0(%rbx)
   swapper 0 [000] 17276.429606186: ffffffff81010645 pt_event_add ([kernel.kallsyms])         mov $0xffffffea, %eax
   swapper 0 [000] 17276.429606186: ffffffff8101064a pt_event_add ([kernel.kallsyms])         mov $0x0, %edx
   swapper 0 [000] 17276.429606186: ffffffff8101064f pt_event_add ([kernel.kallsyms])         popq  %rbx
   swapper 0 [000] 17276.429606186: ffffffff81010650 pt_event_add ([kernel.kallsyms])         cmovnz %edx, %eax
   swapper 0 [000] 17276.429606186: ffffffff81010653 pt_event_add ([kernel.kallsyms])         jmp 0xffffffff81010635
   swapper 0 [000] 17276.429606186: ffffffff81010635 pt_event_add ([kernel.kallsyms])         retq
   swapper 0 [000] 17276.429606186: ffffffff8115e687 event_sched_in.isra.107 ([kernel.kallsyms])       test %eax, %eax

Now:

  % perf record -e intel_pt// ...
  % perf script --insn-trace --xed
  ... same output ...

XED needs to be installed with:

  $ git clone https://github.com/intelxed/mbuild.git mbuild
  $ git clone https://github.com/intelxed/xed
  $ cd xed
  $ ./mfile.py
  $ ./mfile.py examples
  $ sudo ./mfile.py --prefix=/usr/local install
  $ sudo cp obj/examples/xed /usr/local/bin
  $ xed | head -3
  ERROR: required argument(s) were missing
  Copyright (C) 2017, Intel Corporation. All rights reserved.
  XED version: [v10.0-328-g7d62c8c49b7b]
  $

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20180920180540.14039-2-andi@firstfloor.org
[ Fixed up whitespace damage, added the 'mfile.py examples + cp obj/examples/xed ... ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/build-xed.txt   | 19 +++++++++++++++++++
 tools/perf/Documentation/perf-script.txt |  7 +++++++
 tools/perf/builtin-script.c              | 23 +++++++++++++++++++++++
 3 files changed, 49 insertions(+)
 create mode 100644 tools/perf/Documentation/build-xed.txt

(limited to 'tools/perf')

diff --git a/tools/perf/Documentation/build-xed.txt b/tools/perf/Documentation/build-xed.txt
new file mode 100644
index 000000000000..6222c1e7231f
--- /dev/null
+++ b/tools/perf/Documentation/build-xed.txt
@@ -0,0 +1,19 @@
+
+For --xed the xed tool is needed. Here is how to install it:
+
+  $ git clone https://github.com/intelxed/mbuild.git mbuild
+  $ git clone https://github.com/intelxed/xed
+  $ cd xed
+  $ ./mfile.py --share
+  $ ./mfile.py examples
+  $ sudo ./mfile.py --prefix=/usr/local install
+  $ sudo ldconfig
+  $ sudo cp obj/examples/xed /usr/local/bin
+
+Basic xed testing:
+
+  $ xed | head -3
+  ERROR: required argument(s) were missing
+  Copyright (C) 2017, Intel Corporation. All rights reserved.
+  XED version: [v10.0-328-g7d62c8c49b7b]
+  $
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index afdafe2110a1..00c655ab4968 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -383,6 +383,13 @@ include::itrace.txt[]
 	will be printed. Each entry has function name and file/line. Enabled by
 	default, disable with --no-inline.
 
+--insn-trace::
+	Show instruction stream for intel_pt traces. Combine with --xed to
+	show disassembly.
+
+--xed::
+	Run xed disassembler on output. Requires installing the xed disassembler.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ca09b7d2adb7..411ea175bcaf 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -44,6 +44,7 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <unistd.h>
+#include <subcmd/pager.h>
 
 #include "sane_ctype.h"
 
@@ -3103,6 +3104,24 @@ static int perf_script__process_auxtrace_info(struct perf_session *session,
 #define perf_script__process_auxtrace_info 0
 #endif
 
+static int parse_insn_trace(const struct option *opt __maybe_unused,
+			    const char *str __maybe_unused,
+			    int unset __maybe_unused)
+{
+	parse_output_fields(NULL, "+insn,-event,-period", 0);
+	itrace_parse_synth_opts(opt, "i0ns", 0);
+	nanosecs = true;
+	return 0;
+}
+
+static int parse_xed(const struct option *opt __maybe_unused,
+		     const char *str __maybe_unused,
+		     int unset __maybe_unused)
+{
+	force_pager("xed -F insn: -A -64 | less");
+	return 0;
+}
+
 int cmd_script(int argc, const char **argv)
 {
 	bool show_full_info = false;
@@ -3187,6 +3206,10 @@ int cmd_script(int argc, const char **argv)
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
 		   "only consider these symbols"),
+	OPT_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, NULL,
+			"Decode instructions from itrace", parse_insn_trace),
+	OPT_CALLBACK_OPTARG(0, "xed", NULL, NULL, NULL,
+			"Run xed disassembler on output", parse_xed),
 	OPT_STRING(0, "stop-bt", &symbol_conf.bt_stop_list_str, "symbol[,symbol...]",
 		   "Stop display of callgraph at these symbols"),
 	OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
-- 
cgit v1.2.3-58-ga151


From 4eb068157121939f4bc16256a37bcd88f5554123 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Thu, 20 Sep 2018 11:05:37 -0700
Subject: perf script: Make itrace script default to all calls

By default 'perf script' for itrace outputs sampled instructions or
branches. In my experience this is confusing to users because it's hard
to correlate with real program behavior. The sampling makes sense for
tools like 'perf report' that actually sample to reduce the run time,
but run time is normally not a problem for 'perf script'.  It's better
to give an accurate representation of the program flow.

Default 'perf script' to output all calls for itrace. That's a much saner
default. The old behavior can be still requested with 'perf script'
--itrace=ibxwpe100000

v2: Fix ETM build failure
v3: Really fix ETM build failure (Kim Phillips)

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Leo Yan <leo.yan@linaro.org>
Link: http://lkml.kernel.org/r/20180920180540.14039-3-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/itrace.txt |  7 ++++---
 tools/perf/builtin-script.c         |  5 ++++-
 tools/perf/util/auxtrace.c          | 17 ++++++++++++-----
 tools/perf/util/auxtrace.h          |  5 ++++-
 tools/perf/util/cs-etm.c            |  3 ++-
 tools/perf/util/intel-bts.c         |  3 ++-
 tools/perf/util/intel-pt.c          |  3 ++-
 7 files changed, 30 insertions(+), 13 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index a3abe04c779d..c2182cbabde3 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -11,10 +11,11 @@
 		l	synthesize last branch entries (use with i or x)
 		s       skip initial number of events
 
-	The default is all events i.e. the same as --itrace=ibxwpe
+	The default is all events i.e. the same as --itrace=ibxwpe,
+	except for perf script where it is --itrace=ce
 
-	In addition, the period (default 100000) for instructions events
-	can be specified in units of:
+	In addition, the period (default 100000, except for perf script where it is 1)
+	for instructions events can be specified in units of:
 
 		i	instructions
 		t	ticks
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 411ea175bcaf..6099c722a679 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3131,7 +3131,10 @@ int cmd_script(int argc, const char **argv)
 	char *rec_script_path = NULL;
 	char *rep_script_path = NULL;
 	struct perf_session *session;
-	struct itrace_synth_opts itrace_synth_opts = { .set = false, };
+	struct itrace_synth_opts itrace_synth_opts = {
+		.set = false,
+		.default_no_sample = true,
+	};
 	char *script_path = NULL;
 	const char **__argv;
 	int i, j, err = 0;
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c4617bcfd521..72d5ba2479bf 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -962,16 +962,23 @@ s64 perf_event__process_auxtrace(struct perf_session *session,
 #define PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ	64
 #define PERF_ITRACE_MAX_LAST_BRANCH_SZ		1024
 
-void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
+				    bool no_sample)
 {
-	synth_opts->instructions = true;
 	synth_opts->branches = true;
 	synth_opts->transactions = true;
 	synth_opts->ptwrites = true;
 	synth_opts->pwr_events = true;
 	synth_opts->errors = true;
-	synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
-	synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	if (no_sample) {
+		synth_opts->period_type = PERF_ITRACE_PERIOD_INSTRUCTIONS;
+		synth_opts->period = 1;
+		synth_opts->calls = true;
+	} else {
+		synth_opts->instructions = true;
+		synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+		synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	}
 	synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
 	synth_opts->last_branch_sz = PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ;
 	synth_opts->initial_skip = 0;
@@ -999,7 +1006,7 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 	}
 
 	if (!str) {
-		itrace_synth_opts__set_default(synth_opts);
+		itrace_synth_opts__set_default(synth_opts, false);
 		return 0;
 	}
 
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index d88f6e9eb461..8e50f96d4b23 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -58,6 +58,7 @@ enum itrace_period_type {
 /**
  * struct itrace_synth_opts - AUX area tracing synthesis options.
  * @set: indicates whether or not options have been set
+ * @default_no_sample: Default to no sampling.
  * @inject: indicates the event (not just the sample) must be fully synthesized
  *          because 'perf inject' will write it out
  * @instructions: whether to synthesize 'instructions' events
@@ -82,6 +83,7 @@ enum itrace_period_type {
  */
 struct itrace_synth_opts {
 	bool			set;
+	bool			default_no_sample;
 	bool			inject;
 	bool			instructions;
 	bool			branches;
@@ -528,7 +530,8 @@ int perf_event__process_auxtrace_error(struct perf_session *session,
 				       union perf_event *event);
 int itrace_parse_synth_opts(const struct option *opt, const char *str,
 			    int unset);
-void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
+				    bool no_sample);
 
 size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp);
 void perf_session__auxtrace_error_inc(struct perf_session *session,
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 2ae640257fdb..3b37d66dc533 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1432,7 +1432,8 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
 		etm->synth_opts = *session->itrace_synth_opts;
 	} else {
-		itrace_synth_opts__set_default(&etm->synth_opts);
+		itrace_synth_opts__set_default(&etm->synth_opts,
+				session->itrace_synth_opts->default_no_sample);
 		etm->synth_opts.callchain = false;
 	}
 
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 7f0c83b6332b..3b3a3d55dca1 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -910,7 +910,8 @@ int intel_bts_process_auxtrace_info(union perf_event *event,
 	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
 		bts->synth_opts = *session->itrace_synth_opts;
 	} else {
-		itrace_synth_opts__set_default(&bts->synth_opts);
+		itrace_synth_opts__set_default(&bts->synth_opts,
+				session->itrace_synth_opts->default_no_sample);
 		if (session->itrace_synth_opts)
 			bts->synth_opts.thread_stack =
 				session->itrace_synth_opts->thread_stack;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 48c1d415c6b0..ffa385a029b3 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2559,7 +2559,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
 		pt->synth_opts = *session->itrace_synth_opts;
 	} else {
-		itrace_synth_opts__set_default(&pt->synth_opts);
+		itrace_synth_opts__set_default(&pt->synth_opts,
+				session->itrace_synth_opts->default_no_sample);
 		if (use_browser != -1) {
 			pt->synth_opts.branches = false;
 			pt->synth_opts.callchain = true;
-- 
cgit v1.2.3-58-ga151


From d1b1552e15d41297abcaf3812378e3391d44fa6b Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Thu, 20 Sep 2018 11:05:38 -0700
Subject: tools script: Add --call-trace and --call-ret-trace

Add short cut options to print PT call trace and call-ret-trace, for
calls and call and returns. Roughly corresponds to ftrace function
tracer and function graph tracer.

Just makes these common use cases nicer to use.

% perf record -a -e intel_pt// sleep 1
% perf script --call-trace
	    perf   900 [000] 194167.205652203: ([kernel.kallsyms])          perf_pmu_enable
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])          __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])          event_filter_match
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])          group_sched_in
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])              __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])              event_sched_in.isra.107
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  perf_event_set_state.part.71
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                      perf_event_update_time
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  perf_pmu_disable
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  perf_log_itrace_start
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                      perf_event_update_userpage

% perf script --call-ret-trace
	    perf   900 [000] 194167.205652203:   tr strt     ([unknown])        pt_config
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])            pt_config
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])            pt_event_add
            perf   900 [000] 194167.205652203:   call        ([kernel.kallsyms])            perf_pmu_enable
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])            perf_pmu_nop_void
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])            event_sched_in.isra.107
            perf   900 [000] 194167.205652203:   call        ([kernel.kallsyms])            __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])            perf_pmu_nop_int
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])            group_sched_in
            perf   900 [000] 194167.205652203:   call        ([kernel.kallsyms])            event_filter_match
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])            event_filter_match
            perf   900 [000] 194167.205652203:   call        ([kernel.kallsyms])            group_sched_in
            perf   900 [000] 194167.205652203:   call        ([kernel.kallsyms])                __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203:   return      ([kernel.kallsyms])                perf_pmu_nop_txn
            perf   900 [000] 194167.205652203:   call        ([kernel.kallsyms])                event_sched_in.isra.107
            perf   900 [000] 194167.205652203:   call        ([kernel.kallsyms])                    perf_event_set_state.part.71

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Kim Phillips <kim.phillips@arm.com>
Link: http://lkml.kernel.org/r/20180920180540.14039-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-script.txt |  7 +++++++
 tools/perf/builtin-script.c              | 24 ++++++++++++++++++++++++
 2 files changed, 31 insertions(+)

(limited to 'tools/perf')

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 00c655ab4968..805baabd238e 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -390,6 +390,13 @@ include::itrace.txt[]
 --xed::
 	Run xed disassembler on output. Requires installing the xed disassembler.
 
+--call-trace::
+	Show call stream for intel_pt traces. The CPUs are interleaved, but
+	can be filtered with -C.
+
+--call-ret-trace::
+	Show call and return stream for intel_pt traces.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 6099c722a679..566e1450898a 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3122,6 +3122,26 @@ static int parse_xed(const struct option *opt __maybe_unused,
 	return 0;
 }
 
+static int parse_call_trace(const struct option *opt __maybe_unused,
+			    const char *str __maybe_unused,
+			    int unset __maybe_unused)
+{
+	parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0);
+	itrace_parse_synth_opts(opt, "cewp", 0);
+	nanosecs = true;
+	return 0;
+}
+
+static int parse_callret_trace(const struct option *opt __maybe_unused,
+			    const char *str __maybe_unused,
+			    int unset __maybe_unused)
+{
+	parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent,+flags", 0);
+	itrace_parse_synth_opts(opt, "crewp", 0);
+	nanosecs = true;
+	return 0;
+}
+
 int cmd_script(int argc, const char **argv)
 {
 	bool show_full_info = false;
@@ -3213,6 +3233,10 @@ int cmd_script(int argc, const char **argv)
 			"Decode instructions from itrace", parse_insn_trace),
 	OPT_CALLBACK_OPTARG(0, "xed", NULL, NULL, NULL,
 			"Run xed disassembler on output", parse_xed),
+	OPT_CALLBACK_OPTARG(0, "call-trace", &itrace_synth_opts, NULL, NULL,
+			"Decode calls from from itrace", parse_call_trace),
+	OPT_CALLBACK_OPTARG(0, "call-ret-trace", &itrace_synth_opts, NULL, NULL,
+			"Decode calls and returns from itrace", parse_callret_trace),
 	OPT_STRING(0, "stop-bt", &symbol_conf.bt_stop_list_str, "symbol[,symbol...]",
 		   "Stop display of callgraph at these symbols"),
 	OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
-- 
cgit v1.2.3-58-ga151


From 99f753f048b3f02f31a56951781672021af6cd0d Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Thu, 20 Sep 2018 11:05:39 -0700
Subject: perf script: Implement --graph-function

Add a ftrace style --graph-function argument to 'perf script' that
allows to print itrace function calls only below a given function. This
makes it easier to find the code of interest in a large trace.

% perf record -e intel_pt//k -a sleep 1
% perf script --graph-function group_sched_in --call-trace
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])          group_sched_in
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])              __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])              event_sched_in.isra.107
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  perf_event_set_state.part.71
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                      perf_event_update_time
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  perf_pmu_disable
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  perf_log_itrace_start
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                      perf_event_update_userpage
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                          calc_timer_values
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                              sched_clock_cpu
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                          __x86_indirect_thunk_rax
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                          arch_perf_update_userpage
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                              __fentry__
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                              using_native_sched_clock
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                              sched_clock_stable
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])                  perf_pmu_enable
            perf   900 [000] 194167.205652203: ([kernel.kallsyms])              __x86_indirect_thunk_rax
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])          group_sched_in
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])              __x86_indirect_thunk_rax
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])              event_sched_in.isra.107
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                  perf_event_set_state.part.71
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                      perf_event_update_time
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                  perf_pmu_disable
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                  perf_log_itrace_start
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                  __x86_indirect_thunk_rax
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                      perf_event_update_userpage
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                          calc_timer_values
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                              sched_clock_cpu
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                          __x86_indirect_thunk_rax
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                          arch_perf_update_userpage
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                              __fentry__
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                              using_native_sched_clock
         swapper     0 [001] 194167.205660693: ([kernel.kallsyms])                              sched_clock_stable

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Leo Yan <leo.yan@linaro.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Kim Phillips <kim.phillips@arm.com>
Link: http://lkml.kernel.org/r/20180920180540.14039-5-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-script.txt |  4 ++
 tools/perf/builtin-script.c              | 96 ++++++++++++++++++++++++++------
 tools/perf/util/symbol.h                 |  3 +-
 tools/perf/util/thread.h                 |  2 +
 4 files changed, 86 insertions(+), 19 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 805baabd238e..a2b37ce48094 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -397,6 +397,10 @@ include::itrace.txt[]
 --call-ret-trace::
 	Show call and return stream for intel_pt traces.
 
+--graph-function::
+	For itrace only show specified functions and their callees for
+	itrace. Multiple functions can be separated by comma.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 566e1450898a..9d2249ea75e3 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1105,6 +1105,35 @@ out:
 	return printed;
 }
 
+static const char *resolve_branch_sym(struct perf_sample *sample,
+				      struct perf_evsel *evsel,
+				      struct thread *thread,
+				      struct addr_location *al,
+				      u64 *ip)
+{
+	struct addr_location addr_al;
+	struct perf_event_attr *attr = &evsel->attr;
+	const char *name = NULL;
+
+	if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
+		if (sample_addr_correlates_sym(attr)) {
+			thread__resolve(thread, &addr_al, sample);
+			if (addr_al.sym)
+				name = addr_al.sym->name;
+			else
+				*ip = sample->addr;
+		} else {
+			*ip = sample->addr;
+		}
+	} else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
+		if (al->sym)
+			name = al->sym->name;
+		else
+			*ip = sample->ip;
+	}
+	return name;
+}
+
 static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 					   struct perf_evsel *evsel,
 					   struct thread *thread,
@@ -1112,7 +1141,6 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	size_t depth = thread_stack__depth(thread);
-	struct addr_location addr_al;
 	const char *name = NULL;
 	static int spacing;
 	int len = 0;
@@ -1126,22 +1154,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 	if (thread->ts && sample->flags & PERF_IP_FLAG_RETURN)
 		depth += 1;
 
-	if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
-		if (sample_addr_correlates_sym(attr)) {
-			thread__resolve(thread, &addr_al, sample);
-			if (addr_al.sym)
-				name = addr_al.sym->name;
-			else
-				ip = sample->addr;
-		} else {
-			ip = sample->addr;
-		}
-	} else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
-		if (al->sym)
-			name = al->sym->name;
-		else
-			ip = sample->ip;
-	}
+	name = resolve_branch_sym(sample, evsel, thread, al, &ip);
 
 	if (PRINT_FIELD(DSO) && !(PRINT_FIELD(IP) || PRINT_FIELD(ADDR))) {
 		dlen += fprintf(fp, "(");
@@ -1647,6 +1660,47 @@ static void perf_sample__fprint_metric(struct perf_script *script,
 	}
 }
 
+static bool show_event(struct perf_sample *sample,
+		       struct perf_evsel *evsel,
+		       struct thread *thread,
+		       struct addr_location *al)
+{
+	int depth = thread_stack__depth(thread);
+
+	if (!symbol_conf.graph_function)
+		return true;
+
+	if (thread->filter) {
+		if (depth <= thread->filter_entry_depth) {
+			thread->filter = false;
+			return false;
+		}
+		return true;
+	} else {
+		const char *s = symbol_conf.graph_function;
+		u64 ip;
+		const char *name = resolve_branch_sym(sample, evsel, thread, al,
+				&ip);
+		unsigned nlen;
+
+		if (!name)
+			return false;
+		nlen = strlen(name);
+		while (*s) {
+			unsigned len = strcspn(s, ",");
+			if (nlen == len && !strncmp(name, s, len)) {
+				thread->filter = true;
+				thread->filter_entry_depth = depth;
+				return true;
+			}
+			s += len;
+			if (*s == ',')
+				s++;
+		}
+		return false;
+	}
+}
+
 static void process_event(struct perf_script *script,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
 			  struct addr_location *al,
@@ -1661,6 +1715,9 @@ static void process_event(struct perf_script *script,
 	if (output[type].fields == 0)
 		return;
 
+	if (!show_event(sample, evsel, thread, al))
+		return;
+
 	++es->samples;
 
 	perf_sample__fprintf_start(sample, thread, evsel,
@@ -3237,6 +3294,8 @@ int cmd_script(int argc, const char **argv)
 			"Decode calls from from itrace", parse_call_trace),
 	OPT_CALLBACK_OPTARG(0, "call-ret-trace", &itrace_synth_opts, NULL, NULL,
 			"Decode calls and returns from itrace", parse_callret_trace),
+	OPT_STRING(0, "graph-function", &symbol_conf.graph_function, "symbol[,symbol...]",
+			"Only print symbols and callees with --call-trace/--call-ret-trace"),
 	OPT_STRING(0, "stop-bt", &symbol_conf.bt_stop_list_str, "symbol[,symbol...]",
 		   "Stop display of callgraph at these symbols"),
 	OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
@@ -3494,7 +3553,8 @@ int cmd_script(int argc, const char **argv)
 	script.session = session;
 	script__setup_sample_type(&script);
 
-	if (output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT)
+	if ((output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT) ||
+	    symbol_conf.graph_function)
 		itrace_synth_opts.thread_stack = true;
 
 	session->itrace_synth_opts = &itrace_synth_opts;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index f25fae4b5743..d726a8a7bb1b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -123,7 +123,8 @@ struct symbol_conf {
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
-			*field_sep;
+			*field_sep,
+			*graph_function;
 	const char	*default_guest_vmlinux_name,
 			*default_guest_kallsyms,
 			*default_guest_modules;
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 07606aa6998d..36c09a9904e6 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -42,6 +42,8 @@ struct thread {
 	void				*addr_space;
 	struct unwind_libunwind_ops	*unwind_libunwind_ops;
 #endif
+	bool			filter;
+	int			filter_entry_depth;
 };
 
 struct machine;
-- 
cgit v1.2.3-58-ga151


From fe57120e18a1f9124ca758c89cc54f91333d1847 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Mon, 24 Sep 2018 10:07:32 -0700
Subject: perf script: Support total cycles count

For 'perf script' brstackinsn also print a running cycles count.  This
makes it easier to calculate cycle deltas for code sections measured
with LBRs.

% perf record -b -a sleep 1
% perf script -F +brstackinsn
...
        00007f73ecc41083        insn: 74 06                     # PRED 9 cycles [17] 1.11 IPC
        00007f73ecc4108b        insn: a8 10
        00007f73ecc4108d        insn: 74 71                     # PRED 1 cycles [18] 1.00 IPC
        00007f73ecc41100        insn: 48 8b 46 10
        00007f73ecc41104        insn: 4c 8b 38
        00007f73ecc41107        insn: 4d 85 ff
        00007f73ecc4110a        insn: 0f 84 b0 00 00 00
        00007f73ecc41110        insn: 83 43 58 01
        00007f73ecc41114        insn: 48 89 df
        00007f73ecc41117        insn: e8 94 73 04 00            # PRED 6 cycles [24] 1.00 IPC

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Link: http://lkml.kernel.org/r/20180924170732.GA28040@tassilo.jf.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9d2249ea75e3..b5bc85bd0bbe 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -913,7 +913,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
 
 static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 			    struct perf_insn *x, u8 *inbuf, int len,
-			    int insn, FILE *fp)
+			    int insn, FILE *fp, int *total_cycles)
 {
 	int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t#%s%s%s%s", ip,
 			      dump_insn(x, ip, inbuf, len, NULL),
@@ -922,7 +922,8 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 			      en->flags.in_tx ? " INTX" : "",
 			      en->flags.abort ? " ABORT" : "");
 	if (en->flags.cycles) {
-		printed += fprintf(fp, " %d cycles", en->flags.cycles);
+		*total_cycles += en->flags.cycles;
+		printed += fprintf(fp, " %d cycles [%d]", en->flags.cycles, *total_cycles);
 		if (insn)
 			printed += fprintf(fp, " %.2f IPC", (float)insn / en->flags.cycles);
 	}
@@ -979,6 +980,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 	u8 buffer[MAXBB];
 	unsigned off;
 	struct symbol *lastsym = NULL;
+	int total_cycles = 0;
 
 	if (!(br && br->nr))
 		return 0;
@@ -999,7 +1001,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 		printed += ip__fprintf_sym(br->entries[nr - 1].from, thread,
 					   x.cpumode, x.cpu, &lastsym, attr, fp);
 		printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
-					    &x, buffer, len, 0, fp);
+					    &x, buffer, len, 0, fp, &total_cycles);
 	}
 
 	/* Print all blocks */
@@ -1027,7 +1029,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 
 			printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
 			if (ip == end) {
-				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp);
+				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp,
+							    &total_cycles);
 				break;
 			} else {
 				printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip,
-- 
cgit v1.2.3-58-ga151


From f443f38c5789ece6ebe59ae21c27bf861e61c4e2 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 24 Oct 2018 14:31:12 -0300
Subject: tools include uapi: Grab a copy of linux/fs.h

We'll use it to create tables for the 'flags' argument to the 'mount'
and 'umount' syscalls.

Add it to check_headers.sh so that when a new protocol gets added we get
a notification during the build process.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-yacf9jvkwfwg2g95r2us3xb3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/fs.h | 393 ++++++++++++++++++++++++++++++++++++++++++
 tools/perf/check-headers.sh   |   1 +
 2 files changed, 394 insertions(+)
 create mode 100644 tools/include/uapi/linux/fs.h

(limited to 'tools/perf')

diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
new file mode 100644
index 000000000000..73e01918f996
--- /dev/null
+++ b/tools/include/uapi/linux/fs.h
@@ -0,0 +1,393 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_FS_H
+#define _UAPI_LINUX_FS_H
+
+/*
+ * This file has definitions for some important file table structures
+ * and constants and structures used by various generic file system
+ * ioctl's.  Please do not make any changes in this file before
+ * sending patches for review to linux-fsdevel@vger.kernel.org and
+ * linux-api@vger.kernel.org.
+ */
+
+#include <linux/limits.h>
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/*
+ * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
+ * the file limit at runtime and only root can increase the per-process
+ * nr_file rlimit, so it's safe to set up a ridiculously high absolute
+ * upper limit on files-per-process.
+ *
+ * Some programs (notably those using select()) may have to be 
+ * recompiled to take full advantage of the new limits..  
+ */
+
+/* Fixed constants first: */
+#undef NR_OPEN
+#define INR_OPEN_CUR 1024	/* Initial setting for nfile rlimits */
+#define INR_OPEN_MAX 4096	/* Hard limit for nfile rlimits */
+
+#define BLOCK_SIZE_BITS 10
+#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
+
+#define SEEK_SET	0	/* seek relative to beginning of file */
+#define SEEK_CUR	1	/* seek relative to current file position */
+#define SEEK_END	2	/* seek relative to end of file */
+#define SEEK_DATA	3	/* seek to the next data */
+#define SEEK_HOLE	4	/* seek to the next hole */
+#define SEEK_MAX	SEEK_HOLE
+
+#define RENAME_NOREPLACE	(1 << 0)	/* Don't overwrite target */
+#define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
+#define RENAME_WHITEOUT		(1 << 2)	/* Whiteout source */
+
+struct file_clone_range {
+	__s64 src_fd;
+	__u64 src_offset;
+	__u64 src_length;
+	__u64 dest_offset;
+};
+
+struct fstrim_range {
+	__u64 start;
+	__u64 len;
+	__u64 minlen;
+};
+
+/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
+#define FILE_DEDUPE_RANGE_SAME		0
+#define FILE_DEDUPE_RANGE_DIFFERS	1
+
+/* from struct btrfs_ioctl_file_extent_same_info */
+struct file_dedupe_range_info {
+	__s64 dest_fd;		/* in - destination file */
+	__u64 dest_offset;	/* in - start of extent in destination */
+	__u64 bytes_deduped;	/* out - total # of bytes we were able
+				 * to dedupe from this file. */
+	/* status of this dedupe operation:
+	 * < 0 for error
+	 * == FILE_DEDUPE_RANGE_SAME if dedupe succeeds
+	 * == FILE_DEDUPE_RANGE_DIFFERS if data differs
+	 */
+	__s32 status;		/* out - see above description */
+	__u32 reserved;		/* must be zero */
+};
+
+/* from struct btrfs_ioctl_file_extent_same_args */
+struct file_dedupe_range {
+	__u64 src_offset;	/* in - start of extent in source */
+	__u64 src_length;	/* in - length of extent */
+	__u16 dest_count;	/* in - total elements in info array */
+	__u16 reserved1;	/* must be zero */
+	__u32 reserved2;	/* must be zero */
+	struct file_dedupe_range_info info[0];
+};
+
+/* And dynamically-tunable limits and defaults: */
+struct files_stat_struct {
+	unsigned long nr_files;		/* read only */
+	unsigned long nr_free_files;	/* read only */
+	unsigned long max_files;		/* tunable */
+};
+
+struct inodes_stat_t {
+	long nr_inodes;
+	long nr_unused;
+	long dummy[5];		/* padding for sysctl ABI compatibility */
+};
+
+
+#define NR_FILE  8192	/* this can well be larger on a larger system */
+
+
+/*
+ * These are the fs-independent mount-flags: up to 32 flags are supported
+ */
+#define MS_RDONLY	 1	/* Mount read-only */
+#define MS_NOSUID	 2	/* Ignore suid and sgid bits */
+#define MS_NODEV	 4	/* Disallow access to device special files */
+#define MS_NOEXEC	 8	/* Disallow program execution */
+#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
+#define MS_REMOUNT	32	/* Alter flags of a mounted FS */
+#define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
+#define MS_DIRSYNC	128	/* Directory modifications are synchronous */
+#define MS_NOATIME	1024	/* Do not update access times. */
+#define MS_NODIRATIME	2048	/* Do not update directory access times */
+#define MS_BIND		4096
+#define MS_MOVE		8192
+#define MS_REC		16384
+#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
+				   MS_VERBOSE is deprecated. */
+#define MS_SILENT	32768
+#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
+#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
+#define MS_PRIVATE	(1<<18)	/* change to private */
+#define MS_SLAVE	(1<<19)	/* change to slave */
+#define MS_SHARED	(1<<20)	/* change to shared */
+#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
+#define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
+#define MS_I_VERSION	(1<<23) /* Update inode I_version field */
+#define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
+#define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
+
+/* These sb flags are internal to the kernel */
+#define MS_SUBMOUNT     (1<<26)
+#define MS_NOREMOTELOCK	(1<<27)
+#define MS_NOSEC	(1<<28)
+#define MS_BORN		(1<<29)
+#define MS_ACTIVE	(1<<30)
+#define MS_NOUSER	(1<<31)
+
+/*
+ * Superblock flags that can be altered by MS_REMOUNT
+ */
+#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
+			 MS_LAZYTIME)
+
+/*
+ * Old magic mount flag and mask
+ */
+#define MS_MGC_VAL 0xC0ED0000
+#define MS_MGC_MSK 0xffff0000
+
+/*
+ * Structure for FS_IOC_FSGETXATTR[A] and FS_IOC_FSSETXATTR.
+ */
+struct fsxattr {
+	__u32		fsx_xflags;	/* xflags field value (get/set) */
+	__u32		fsx_extsize;	/* extsize field value (get/set)*/
+	__u32		fsx_nextents;	/* nextents field value (get)	*/
+	__u32		fsx_projid;	/* project identifier (get/set) */
+	__u32		fsx_cowextsize;	/* CoW extsize field value (get/set)*/
+	unsigned char	fsx_pad[8];
+};
+
+/*
+ * Flags for the fsx_xflags field
+ */
+#define FS_XFLAG_REALTIME	0x00000001	/* data in realtime volume */
+#define FS_XFLAG_PREALLOC	0x00000002	/* preallocated file extents */
+#define FS_XFLAG_IMMUTABLE	0x00000008	/* file cannot be modified */
+#define FS_XFLAG_APPEND		0x00000010	/* all writes append */
+#define FS_XFLAG_SYNC		0x00000020	/* all writes synchronous */
+#define FS_XFLAG_NOATIME	0x00000040	/* do not update access time */
+#define FS_XFLAG_NODUMP		0x00000080	/* do not include in backups */
+#define FS_XFLAG_RTINHERIT	0x00000100	/* create with rt bit set */
+#define FS_XFLAG_PROJINHERIT	0x00000200	/* create with parents projid */
+#define FS_XFLAG_NOSYMLINKS	0x00000400	/* disallow symlink creation */
+#define FS_XFLAG_EXTSIZE	0x00000800	/* extent size allocator hint */
+#define FS_XFLAG_EXTSZINHERIT	0x00001000	/* inherit inode extent size */
+#define FS_XFLAG_NODEFRAG	0x00002000	/* do not defragment */
+#define FS_XFLAG_FILESTREAM	0x00004000	/* use filestream allocator */
+#define FS_XFLAG_DAX		0x00008000	/* use DAX for IO */
+#define FS_XFLAG_COWEXTSIZE	0x00010000	/* CoW extent size allocator hint */
+#define FS_XFLAG_HASATTR	0x80000000	/* no DIFLAG for this	*/
+
+/* the read-only stuff doesn't really belong here, but any other place is
+   probably as bad and I don't want to create yet another include file. */
+
+#define BLKROSET   _IO(0x12,93)	/* set device read-only (0 = read-write) */
+#define BLKROGET   _IO(0x12,94)	/* get read-only status (0 = read_write) */
+#define BLKRRPART  _IO(0x12,95)	/* re-read partition table */
+#define BLKGETSIZE _IO(0x12,96)	/* return device size /512 (long *arg) */
+#define BLKFLSBUF  _IO(0x12,97)	/* flush buffer cache */
+#define BLKRASET   _IO(0x12,98)	/* set read ahead for block device */
+#define BLKRAGET   _IO(0x12,99)	/* get current read ahead setting */
+#define BLKFRASET  _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */
+#define BLKFRAGET  _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */
+#define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */
+#define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */
+#define BLKSSZGET  _IO(0x12,104)/* get block device sector size */
+#if 0
+#define BLKPG      _IO(0x12,105)/* See blkpg.h */
+
+/* Some people are morons.  Do not use sizeof! */
+
+#define BLKELVGET  _IOR(0x12,106,size_t)/* elevator get */
+#define BLKELVSET  _IOW(0x12,107,size_t)/* elevator set */
+/* This was here just to show that the number is taken -
+   probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */
+#endif
+/* A jump here: 108-111 have been used for various private purposes. */
+#define BLKBSZGET  _IOR(0x12,112,size_t)
+#define BLKBSZSET  _IOW(0x12,113,size_t)
+#define BLKGETSIZE64 _IOR(0x12,114,size_t)	/* return device size in bytes (u64 *arg) */
+#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup)
+#define BLKTRACESTART _IO(0x12,116)
+#define BLKTRACESTOP _IO(0x12,117)
+#define BLKTRACETEARDOWN _IO(0x12,118)
+#define BLKDISCARD _IO(0x12,119)
+#define BLKIOMIN _IO(0x12,120)
+#define BLKIOOPT _IO(0x12,121)
+#define BLKALIGNOFF _IO(0x12,122)
+#define BLKPBSZGET _IO(0x12,123)
+#define BLKDISCARDZEROES _IO(0x12,124)
+#define BLKSECDISCARD _IO(0x12,125)
+#define BLKROTATIONAL _IO(0x12,126)
+#define BLKZEROOUT _IO(0x12,127)
+/*
+ * A jump here: 130-131 are reserved for zoned block devices
+ * (see uapi/linux/blkzoned.h)
+ */
+
+#define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
+#define FIBMAP	   _IO(0x00,1)	/* bmap access */
+#define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */
+#define FIFREEZE	_IOWR('X', 119, int)	/* Freeze */
+#define FITHAW		_IOWR('X', 120, int)	/* Thaw */
+#define FITRIM		_IOWR('X', 121, struct fstrim_range)	/* Trim */
+#define FICLONE		_IOW(0x94, 9, int)
+#define FICLONERANGE	_IOW(0x94, 13, struct file_clone_range)
+#define FIDEDUPERANGE	_IOWR(0x94, 54, struct file_dedupe_range)
+
+#define FSLABEL_MAX 256	/* Max chars for the interface; each fs may differ */
+
+#define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
+#define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
+#define	FS_IOC_GETVERSION		_IOR('v', 1, long)
+#define	FS_IOC_SETVERSION		_IOW('v', 2, long)
+#define FS_IOC_FIEMAP			_IOWR('f', 11, struct fiemap)
+#define FS_IOC32_GETFLAGS		_IOR('f', 1, int)
+#define FS_IOC32_SETFLAGS		_IOW('f', 2, int)
+#define FS_IOC32_GETVERSION		_IOR('v', 1, int)
+#define FS_IOC32_SETVERSION		_IOW('v', 2, int)
+#define FS_IOC_FSGETXATTR		_IOR('X', 31, struct fsxattr)
+#define FS_IOC_FSSETXATTR		_IOW('X', 32, struct fsxattr)
+#define FS_IOC_GETFSLABEL		_IOR(0x94, 49, char[FSLABEL_MAX])
+#define FS_IOC_SETFSLABEL		_IOW(0x94, 50, char[FSLABEL_MAX])
+
+/*
+ * File system encryption support
+ */
+/* Policy provided via an ioctl on the topmost directory */
+#define FS_KEY_DESCRIPTOR_SIZE	8
+
+#define FS_POLICY_FLAGS_PAD_4		0x00
+#define FS_POLICY_FLAGS_PAD_8		0x01
+#define FS_POLICY_FLAGS_PAD_16		0x02
+#define FS_POLICY_FLAGS_PAD_32		0x03
+#define FS_POLICY_FLAGS_PAD_MASK	0x03
+#define FS_POLICY_FLAGS_VALID		0x03
+
+/* Encryption algorithms */
+#define FS_ENCRYPTION_MODE_INVALID		0
+#define FS_ENCRYPTION_MODE_AES_256_XTS		1
+#define FS_ENCRYPTION_MODE_AES_256_GCM		2
+#define FS_ENCRYPTION_MODE_AES_256_CBC		3
+#define FS_ENCRYPTION_MODE_AES_256_CTS		4
+#define FS_ENCRYPTION_MODE_AES_128_CBC		5
+#define FS_ENCRYPTION_MODE_AES_128_CTS		6
+#define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7
+#define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8
+
+struct fscrypt_policy {
+	__u8 version;
+	__u8 contents_encryption_mode;
+	__u8 filenames_encryption_mode;
+	__u8 flags;
+	__u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
+};
+
+#define FS_IOC_SET_ENCRYPTION_POLICY	_IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_PWSALT	_IOW('f', 20, __u8[16])
+#define FS_IOC_GET_ENCRYPTION_POLICY	_IOW('f', 21, struct fscrypt_policy)
+
+/* Parameters for passing an encryption key into the kernel keyring */
+#define FS_KEY_DESC_PREFIX		"fscrypt:"
+#define FS_KEY_DESC_PREFIX_SIZE		8
+
+/* Structure that userspace passes to the kernel keyring */
+#define FS_MAX_KEY_SIZE			64
+
+struct fscrypt_key {
+	__u32 mode;
+	__u8 raw[FS_MAX_KEY_SIZE];
+	__u32 size;
+};
+
+/*
+ * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
+ *
+ * Note: for historical reasons, these flags were originally used and
+ * defined for use by ext2/ext3, and then other file systems started
+ * using these flags so they wouldn't need to write their own version
+ * of chattr/lsattr (which was shipped as part of e2fsprogs).  You
+ * should think twice before trying to use these flags in new
+ * contexts, or trying to assign these flags, since they are used both
+ * as the UAPI and the on-disk encoding for ext2/3/4.  Also, we are
+ * almost out of 32-bit flags.  :-)
+ *
+ * We have recently hoisted FS_IOC_FSGETXATTR / FS_IOC_FSSETXATTR from
+ * XFS to the generic FS level interface.  This uses a structure that
+ * has padding and hence has more room to grow, so it may be more
+ * appropriate for many new use cases.
+ *
+ * Please do not change these flags or interfaces before checking with
+ * linux-fsdevel@vger.kernel.org and linux-api@vger.kernel.org.
+ */
+#define	FS_SECRM_FL			0x00000001 /* Secure deletion */
+#define	FS_UNRM_FL			0x00000002 /* Undelete */
+#define	FS_COMPR_FL			0x00000004 /* Compress file */
+#define FS_SYNC_FL			0x00000008 /* Synchronous updates */
+#define FS_IMMUTABLE_FL			0x00000010 /* Immutable file */
+#define FS_APPEND_FL			0x00000020 /* writes to file may only append */
+#define FS_NODUMP_FL			0x00000040 /* do not dump file */
+#define FS_NOATIME_FL			0x00000080 /* do not update atime */
+/* Reserved for compression usage... */
+#define FS_DIRTY_FL			0x00000100
+#define FS_COMPRBLK_FL			0x00000200 /* One or more compressed clusters */
+#define FS_NOCOMP_FL			0x00000400 /* Don't compress */
+/* End compression flags --- maybe not all used */
+#define FS_ENCRYPT_FL			0x00000800 /* Encrypted file */
+#define FS_BTREE_FL			0x00001000 /* btree format dir */
+#define FS_INDEX_FL			0x00001000 /* hash-indexed directory */
+#define FS_IMAGIC_FL			0x00002000 /* AFS directory */
+#define FS_JOURNAL_DATA_FL		0x00004000 /* Reserved for ext3 */
+#define FS_NOTAIL_FL			0x00008000 /* file tail should not be merged */
+#define FS_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
+#define FS_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
+#define FS_HUGE_FILE_FL			0x00040000 /* Reserved for ext4 */
+#define FS_EXTENT_FL			0x00080000 /* Extents */
+#define FS_EA_INODE_FL			0x00200000 /* Inode used for large EA */
+#define FS_EOFBLOCKS_FL			0x00400000 /* Reserved for ext4 */
+#define FS_NOCOW_FL			0x00800000 /* Do not cow file */
+#define FS_INLINE_DATA_FL		0x10000000 /* Reserved for ext4 */
+#define FS_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
+#define FS_RESERVED_FL			0x80000000 /* reserved for ext2 lib */
+
+#define FS_FL_USER_VISIBLE		0x0003DFFF /* User visible flags */
+#define FS_FL_USER_MODIFIABLE		0x000380FF /* User modifiable flags */
+
+
+#define SYNC_FILE_RANGE_WAIT_BEFORE	1
+#define SYNC_FILE_RANGE_WRITE		2
+#define SYNC_FILE_RANGE_WAIT_AFTER	4
+
+/*
+ * Flags for preadv2/pwritev2:
+ */
+
+typedef int __bitwise __kernel_rwf_t;
+
+/* high priority request, poll if possible */
+#define RWF_HIPRI	((__force __kernel_rwf_t)0x00000001)
+
+/* per-IO O_DSYNC */
+#define RWF_DSYNC	((__force __kernel_rwf_t)0x00000002)
+
+/* per-IO O_SYNC */
+#define RWF_SYNC	((__force __kernel_rwf_t)0x00000004)
+
+/* per-IO, return -EAGAIN if operation would block */
+#define RWF_NOWAIT	((__force __kernel_rwf_t)0x00000008)
+
+/* per-IO O_APPEND */
+#define RWF_APPEND	((__force __kernel_rwf_t)0x00000010)
+
+/* mask of flags supported by the kernel */
+#define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
+			 RWF_APPEND)
+
+#endif /* _UAPI_LINUX_FS_H */
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index c72cc73a6b09..9531f7bd7d9b 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -5,6 +5,7 @@ HEADERS='
 include/uapi/drm/drm.h
 include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
+include/uapi/linux/fs.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
 include/uapi/linux/in.h
-- 
cgit v1.2.3-58-ga151


From ceaf8e5b49ce18e9e58d292130e92150d01a34e6 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 24 Oct 2018 14:54:55 -0300
Subject: perf beauty: Add a generator for MS_ mount/umount's flag constants

It'll use tools/include copy of linux/fs.h to generate a table to be
used by tools, initially by the 'mount' and 'umount' beautifiers in
'perf trace', but that could also be used to translate from a string
constant to the integer value to be used in a eBPF or tracefs tracepoint
filter.

When used without any args it produces:

  $ tools/perf/trace/beauty/mount_flags.sh
  static const char *mount_flags[] = {
	[1 ? (ilog2(1) + 1) : 0] = "RDONLY",
	[2 ? (ilog2(2) + 1) : 0] = "NOSUID",
	[4 ? (ilog2(4) + 1) : 0] = "NODEV",
	[8 ? (ilog2(8) + 1) : 0] = "NOEXEC",
	[16 ? (ilog2(16) + 1) : 0] = "SYNCHRONOUS",
	[32 ? (ilog2(32) + 1) : 0] = "REMOUNT",
	[64 ? (ilog2(64) + 1) : 0] = "MANDLOCK",
	[128 ? (ilog2(128) + 1) : 0] = "DIRSYNC",
	[1024 ? (ilog2(1024) + 1) : 0] = "NOATIME",
	[2048 ? (ilog2(2048) + 1) : 0] = "NODIRATIME",
	[4096 ? (ilog2(4096) + 1) : 0] = "BIND",
	[8192 ? (ilog2(8192) + 1) : 0] = "MOVE",
	[16384 ? (ilog2(16384) + 1) : 0] = "REC",
	[32768 ? (ilog2(32768) + 1) : 0] = "SILENT",
	[16 + 1] = "POSIXACL",
	[17 + 1] = "UNBINDABLE",
	[18 + 1] = "PRIVATE",
	[19 + 1] = "SLAVE",
	[20 + 1] = "SHARED",
	[21 + 1] = "RELATIME",
	[22 + 1] = "KERNMOUNT",
	[23 + 1] = "I_VERSION",
	[24 + 1] = "STRICTATIME",
	[25 + 1] = "LAZYTIME",
	[26 + 1] = "SUBMOUNT",
	[27 + 1] = "NOREMOTELOCK",
	[28 + 1] = "NOSEC",
	[29 + 1] = "BORN",
	[30 + 1] = "ACTIVE",
	[31 + 1] = "NOUSER",
  };
  $

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mgutbbkmip9gfnmd28ikg7xt@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/mount_flags.sh | 15 +++++++++++++++
 1 file changed, 15 insertions(+)
 create mode 100755 tools/perf/trace/beauty/mount_flags.sh

(limited to 'tools/perf')

diff --git a/tools/perf/trace/beauty/mount_flags.sh b/tools/perf/trace/beauty/mount_flags.sh
new file mode 100755
index 000000000000..45547573a1db
--- /dev/null
+++ b/tools/perf/trace/beauty/mount_flags.sh
@@ -0,0 +1,15 @@
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+
+printf "static const char *mount_flags[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
+egrep $regex ${header_dir}/fs.h | egrep -v '(MSK|VERBOSE|MGC_VAL)\>' | \
+	sed -r "s/$regex/\2 \2 \1/g" | sort -n | \
+	xargs printf "\t[%s ? (ilog2(%s) + 1) : 0] = \"%s\",\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+\(1<<([[:digit:]]+)\)[[:space:]]*.*'
+egrep $regex ${header_dir}/fs.h | \
+	sed -r "s/$regex/\2 \1/g" | \
+	xargs printf "\t[%s + 1] = \"%s\",\n"
+printf "};\n"
-- 
cgit v1.2.3-58-ga151


From 794f594e0c3be6199e0b3e2324280e8785806fb6 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 24 Oct 2018 15:54:23 -0300
Subject: perf beauty: Switch from GPL v2.0 to LGPL v2.1

The intention is to have this as a library, since it is not perf
specific at all.

I did the switch for the files where I'm the only contributor, with the
exception of a few lines changed by Jiri Olsa.

Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-a04q6chdyjknm1hr305ulx8h@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/clone.c                     | 3 +--
 tools/perf/trace/beauty/drm_ioctl.sh                | 1 +
 tools/perf/trace/beauty/eventfd.c                   | 2 +-
 tools/perf/trace/beauty/fcntl.c                     | 3 +--
 tools/perf/trace/beauty/flock.c                     | 2 +-
 tools/perf/trace/beauty/futex_op.c                  | 2 +-
 tools/perf/trace/beauty/futex_val3.c                | 2 +-
 tools/perf/trace/beauty/ioctl.c                     | 3 +--
 tools/perf/trace/beauty/kcmp.c                      | 3 +--
 tools/perf/trace/beauty/kcmp_type.sh                | 1 +
 tools/perf/trace/beauty/kvm_ioctl.sh                | 1 +
 tools/perf/trace/beauty/madvise_behavior.sh         | 1 +
 tools/perf/trace/beauty/mmap.c                      | 2 +-
 tools/perf/trace/beauty/mode_t.c                    | 2 +-
 tools/perf/trace/beauty/msg_flags.c                 | 2 +-
 tools/perf/trace/beauty/open_flags.c                | 2 +-
 tools/perf/trace/beauty/perf_event_open.c           | 2 +-
 tools/perf/trace/beauty/perf_ioctl.sh               | 1 +
 tools/perf/trace/beauty/pid.c                       | 3 ++-
 tools/perf/trace/beauty/pkey_alloc.c                | 3 +--
 tools/perf/trace/beauty/pkey_alloc_access_rights.sh | 1 +
 tools/perf/trace/beauty/prctl.c                     | 3 +--
 tools/perf/trace/beauty/prctl_option.sh             | 1 +
 tools/perf/trace/beauty/sched_policy.c              | 2 +-
 tools/perf/trace/beauty/seccomp.c                   | 2 +-
 tools/perf/trace/beauty/signum.c                    | 2 +-
 tools/perf/trace/beauty/sndrv_ctl_ioctl.sh          | 1 +
 tools/perf/trace/beauty/sndrv_pcm_ioctl.sh          | 1 +
 tools/perf/trace/beauty/sockaddr.c                  | 2 +-
 tools/perf/trace/beauty/socket.c                    | 2 +-
 tools/perf/trace/beauty/socket_ipproto.sh           | 1 +
 tools/perf/trace/beauty/socket_type.c               | 2 +-
 tools/perf/trace/beauty/statx.c                     | 3 +--
 tools/perf/trace/beauty/vhost_virtio_ioctl.sh       | 1 +
 tools/perf/trace/beauty/waitid_options.c            | 2 +-
 35 files changed, 36 insertions(+), 31 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c
index d64d049ab991..010406500c30 100644
--- a/tools/perf/trace/beauty/clone.c
+++ b/tools/perf/trace/beauty/clone.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/cone.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh
index 9d3816815e60..9aa94fd523a9 100755
--- a/tools/perf/trace/beauty/drm_ioctl.sh
+++ b/tools/perf/trace/beauty/drm_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/
 
diff --git a/tools/perf/trace/beauty/eventfd.c b/tools/perf/trace/beauty/eventfd.c
index 5d6a477a6400..db5b9b492113 100644
--- a/tools/perf/trace/beauty/eventfd.c
+++ b/tools/perf/trace/beauty/eventfd.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #ifndef EFD_SEMAPHORE
 #define EFD_SEMAPHORE		1
 #endif
diff --git a/tools/perf/trace/beauty/fcntl.c b/tools/perf/trace/beauty/fcntl.c
index 9e8900c13cb1..e6de31674e24 100644
--- a/tools/perf/trace/beauty/fcntl.c
+++ b/tools/perf/trace/beauty/fcntl.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/fcntl.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/flock.c b/tools/perf/trace/beauty/flock.c
index c4ff6ad30b06..cf02ae5f0ba6 100644
--- a/tools/perf/trace/beauty/flock.c
+++ b/tools/perf/trace/beauty/flock.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 
 #include "trace/beauty/beauty.h"
 #include <linux/kernel.h>
diff --git a/tools/perf/trace/beauty/futex_op.c b/tools/perf/trace/beauty/futex_op.c
index 61850fbc85ff..1136bde56406 100644
--- a/tools/perf/trace/beauty/futex_op.c
+++ b/tools/perf/trace/beauty/futex_op.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <linux/futex.h>
 
 #ifndef FUTEX_WAIT_BITSET
diff --git a/tools/perf/trace/beauty/futex_val3.c b/tools/perf/trace/beauty/futex_val3.c
index 26f6b3253511..138b7d588a70 100644
--- a/tools/perf/trace/beauty/futex_val3.c
+++ b/tools/perf/trace/beauty/futex_val3.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <linux/futex.h>
 
 #ifndef FUTEX_BITSET_MATCH_ANY
diff --git a/tools/perf/trace/beauty/ioctl.c b/tools/perf/trace/beauty/ioctl.c
index 1be3b4cf0827..5d2a7fd8d407 100644
--- a/tools/perf/trace/beauty/ioctl.c
+++ b/tools/perf/trace/beauty/ioctl.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/ioctl.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/kcmp.c b/tools/perf/trace/beauty/kcmp.c
index f62040eb9d5c..b276a274f203 100644
--- a/tools/perf/trace/beauty/kcmp.c
+++ b/tools/perf/trace/beauty/kcmp.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/kcmp.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh
index a3c304caa336..df8b17486d57 100755
--- a/tools/perf/trace/beauty/kcmp_type.sh
+++ b/tools/perf/trace/beauty/kcmp_type.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh
index c4699fd46bb6..4ce54f5bf756 100755
--- a/tools/perf/trace/beauty/kvm_ioctl.sh
+++ b/tools/perf/trace/beauty/kvm_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh
index 431639eb4d29..4527d290cdfc 100755
--- a/tools/perf/trace/beauty/madvise_behavior.sh
+++ b/tools/perf/trace/beauty/madvise_behavior.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 9f68077b241b..0605593552c6 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <uapi/linux/mman.h>
 
 static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
diff --git a/tools/perf/trace/beauty/mode_t.c b/tools/perf/trace/beauty/mode_t.c
index d929ad7dd97b..6879d36d3004 100644
--- a/tools/perf/trace/beauty/mode_t.c
+++ b/tools/perf/trace/beauty/mode_t.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c
index c064d6aae659..1b9d6306d274 100644
--- a/tools/perf/trace/beauty/msg_flags.c
+++ b/tools/perf/trace/beauty/msg_flags.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/socket.h>
 
diff --git a/tools/perf/trace/beauty/open_flags.c b/tools/perf/trace/beauty/open_flags.c
index 6aec6178a99d..cc673fec9184 100644
--- a/tools/perf/trace/beauty/open_flags.c
+++ b/tools/perf/trace/beauty/open_flags.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
diff --git a/tools/perf/trace/beauty/perf_event_open.c b/tools/perf/trace/beauty/perf_event_open.c
index 2bafd7c995ff..981185c1974b 100644
--- a/tools/perf/trace/beauty/perf_event_open.c
+++ b/tools/perf/trace/beauty/perf_event_open.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #ifndef PERF_FLAG_FD_NO_GROUP
 # define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
 #endif
diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh
index 6492c74df928..9aabd9743ef6 100755
--- a/tools/perf/trace/beauty/perf_ioctl.sh
+++ b/tools/perf/trace/beauty/perf_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/pid.c b/tools/perf/trace/beauty/pid.c
index 0313df342830..1a6acc46807b 100644
--- a/tools/perf/trace/beauty/pid.c
+++ b/tools/perf/trace/beauty/pid.c
@@ -1,4 +1,5 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
+
 size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg)
 {
 	int pid = arg->val;
diff --git a/tools/perf/trace/beauty/pkey_alloc.c b/tools/perf/trace/beauty/pkey_alloc.c
index 2ba784a3734a..d3e5188a9bef 100644
--- a/tools/perf/trace/beauty/pkey_alloc.c
+++ b/tools/perf/trace/beauty/pkey_alloc.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/pkey_alloc.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
index e0a51aeb20b2..f8f1b560cf8a 100755
--- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
+++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
diff --git a/tools/perf/trace/beauty/prctl.c b/tools/perf/trace/beauty/prctl.c
index 246130dad6c4..be7a5d395975 100644
--- a/tools/perf/trace/beauty/prctl.c
+++ b/tools/perf/trace/beauty/prctl.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/prctl.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
index f24722146ebe..d32f8f1124af 100755
--- a/tools/perf/trace/beauty/prctl_option.sh
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/sched_policy.c b/tools/perf/trace/beauty/sched_policy.c
index ba5096ae76b6..48f2b5c9aa3e 100644
--- a/tools/perf/trace/beauty/sched_policy.c
+++ b/tools/perf/trace/beauty/sched_policy.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sched.h>
 
 /*
diff --git a/tools/perf/trace/beauty/seccomp.c b/tools/perf/trace/beauty/seccomp.c
index b7097fd5fed9..e36156b19c70 100644
--- a/tools/perf/trace/beauty/seccomp.c
+++ b/tools/perf/trace/beauty/seccomp.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #ifndef SECCOMP_SET_MODE_STRICT
 #define SECCOMP_SET_MODE_STRICT 0
 #endif
diff --git a/tools/perf/trace/beauty/signum.c b/tools/perf/trace/beauty/signum.c
index bde18a53f090..587fec545b8a 100644
--- a/tools/perf/trace/beauty/signum.c
+++ b/tools/perf/trace/beauty/signum.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <signal.h>
 
 static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg)
diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
index eb511bb5fbd3..e0803b957593 100755
--- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
index 6818392968b2..7a464a7bf913 100755
--- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c
index 71a79f72d9d9..9410ad230f10 100644
--- a/tools/perf/trace/beauty/sockaddr.c
+++ b/tools/perf/trace/beauty/sockaddr.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 // Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c
index 65227269384b..d971a2596417 100644
--- a/tools/perf/trace/beauty/socket.c
+++ b/tools/perf/trace/beauty/socket.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/socket.c
  *
diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh
index a3cc24633bec..de0f2f29017f 100755
--- a/tools/perf/trace/beauty/socket_ipproto.sh
+++ b/tools/perf/trace/beauty/socket_ipproto.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/socket_type.c b/tools/perf/trace/beauty/socket_type.c
index bca26aef4a77..a63a9a332aa0 100644
--- a/tools/perf/trace/beauty/socket_type.c
+++ b/tools/perf/trace/beauty/socket_type.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/socket.h>
 
diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c
index 5643b692af4c..630f2760dd66 100644
--- a/tools/perf/trace/beauty/statx.c
+++ b/tools/perf/trace/beauty/statx.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/statx.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
index 0f6a5197d0be..439773daaf77 100755
--- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
+++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/waitid_options.c b/tools/perf/trace/beauty/waitid_options.c
index 8465281a093d..42ff58ad613b 100644
--- a/tools/perf/trace/beauty/waitid_options.c
+++ b/tools/perf/trace/beauty/waitid_options.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/wait.h>
 
-- 
cgit v1.2.3-58-ga151


From 579e5ff629b17744f62473f314768de8b6f1e66c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 25 Oct 2018 14:21:31 -0300
Subject: perf beauty: Introduce strarray__scnprintf_flags()

Generalizing pkey_alloc__scnprintf_access_rights(), so that we can use
it with other flags-like arguments, such as mount's mountflags argument.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-o3ymi3104m8moaz9865g09w9@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/beauty.h     |  1 +
 tools/perf/trace/beauty/pkey_alloc.c | 27 ++++++++++++++++-----------
 2 files changed, 17 insertions(+), 11 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 2570152d3909..a1806c4f3ccd 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -24,6 +24,7 @@ struct strarray {
 }
 
 size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const char *intfmt, int val);
+size_t strarray__scnprintf_flags(struct strarray *sa, char *bf, size_t size, unsigned long flags);
 
 struct trace;
 struct thread;
diff --git a/tools/perf/trace/beauty/pkey_alloc.c b/tools/perf/trace/beauty/pkey_alloc.c
index d3e5188a9bef..1b8ed4cac815 100644
--- a/tools/perf/trace/beauty/pkey_alloc.c
+++ b/tools/perf/trace/beauty/pkey_alloc.c
@@ -9,31 +9,28 @@
 #include <linux/kernel.h>
 #include <linux/log2.h>
 
-static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, size_t size)
+size_t strarray__scnprintf_flags(struct strarray *sa, char *bf, size_t size, unsigned long flags)
 {
 	int i, printed = 0;
 
-#include "trace/beauty/generated/pkey_alloc_access_rights_array.c"
-	static DEFINE_STRARRAY(pkey_alloc_access_rights);
-
-	if (access_rights == 0) {
-		const char *s = strarray__pkey_alloc_access_rights.entries[0];
+	if (flags == 0) {
+		const char *s = sa->entries[0];
 		if (s)
 			return scnprintf(bf, size, "%s", s);
 		return scnprintf(bf, size, "%d", 0);
 	}
 
-	for (i = 1; i < strarray__pkey_alloc_access_rights.nr_entries; ++i) {
-		int bit = 1 << (i - 1);
+	for (i = 1; i < sa->nr_entries; ++i) {
+		unsigned long bit = 1UL << (i - 1);
 
-		if (!(access_rights & bit))
+		if (!(flags & bit))
 			continue;
 
 		if (printed != 0)
 			printed += scnprintf(bf + printed, size - printed, "|");
 
-		if (strarray__pkey_alloc_access_rights.entries[i] != NULL)
-			printed += scnprintf(bf + printed, size - printed, "%s", strarray__pkey_alloc_access_rights.entries[i]);
+		if (sa->entries[i] != NULL)
+			printed += scnprintf(bf + printed, size - printed, "%s", sa->entries[i]);
 		else
 			printed += scnprintf(bf + printed, size - printed, "0x%#", bit);
 	}
@@ -41,6 +38,14 @@ static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, s
 	return printed;
 }
 
+static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, size_t size)
+{
+#include "trace/beauty/generated/pkey_alloc_access_rights_array.c"
+	static DEFINE_STRARRAY(pkey_alloc_access_rights);
+
+	return strarray__scnprintf_flags(&strarray__pkey_alloc_access_rights, bf, size, access_rights);
+}
+
 size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg)
 {
 	unsigned long cmd = arg->val;
-- 
cgit v1.2.3-58-ga151


From 496fd346b71ffa0ff35623e9ec79df0bad47bd66 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 25 Oct 2018 16:09:47 -0300
Subject: perf trace beauty: Allow syscalls to mask an argument before
 considering it

Take mount's 'flags' arg, to cope with this semantic, as defined in do_mount in fs/namespace.c:

  /*
   * Pre-0.97 versions of mount() didn't have a flags word.  When the
   * flags word was introduced its top half was required to have the
   * magic value 0xC0ED, and this remained so until 2.4.0-test9.
   * Therefore, if this magic number is present, it carries no
   * information and must be discarded.
   */

We need to mask this arg, and then see if it is zero, when we simply
don't print the arg name and value.

The next patch will use this for mount's 'flag' arg.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-btue14k5jemayuykfrwsnh85@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'tools/perf')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 7081d7ea12e5..14fb63e17de5 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -614,6 +614,7 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
 
 struct syscall_arg_fmt {
 	size_t	   (*scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
+	unsigned long (*mask_val)(struct syscall_arg *arg, unsigned long val);
 	void	   *parm;
 	const char *name;
 	bool	   show_zero;
@@ -1487,6 +1488,19 @@ static size_t syscall__scnprintf_name(struct syscall *sc, char *bf, size_t size,
 	return scnprintf(bf, size, "arg%d: ", arg->idx);
 }
 
+/*
+ * Check if the value is in fact zero, i.e. mask whatever needs masking, such
+ * as mount 'flags' argument that needs ignoring some magic flag, see comment
+ * in tools/perf/trace/beauty/mount_flags.c
+ */
+static unsigned long syscall__mask_val(struct syscall *sc, struct syscall_arg *arg, unsigned long val)
+{
+	if (sc->arg_fmt && sc->arg_fmt[arg->idx].mask_val)
+		return sc->arg_fmt[arg->idx].mask_val(arg, val);
+
+	return val;
+}
+
 static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size,
 				     struct syscall_arg *arg, unsigned long val)
 {
@@ -1535,6 +1549,11 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
 				continue;
 
 			val = syscall_arg__val(&arg, arg.idx);
+			/*
+			 * Some syscall args need some mask, most don't and
+			 * return val untouched.
+			 */
+			val = syscall__mask_val(sc, &arg, val);
 
 			/*
  			 * Suppress this argument if its value is zero and
-- 
cgit v1.2.3-58-ga151


From 73d141adcea66de656d0c8336811f2b0bbd9700c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 25 Oct 2018 15:18:06 -0300
Subject: perf trace beauty: Beautify mount/umount's 'flags' argument

  # trace -e mount mount -o ro -t debugfs nodev /mnt
     0.000 ( 1.040 ms): mount/27235 mount(dev_name: 0x5601cc8c64e0, dir_name: 0x5601cc8c6500, type: 0x5601cc8c6480, flags: RDONLY) = 0
  # trace -e mount mount -o remount,relatime -t debugfs nodev /mnt
     0.000 ( 2.946 ms): mount/27262 mount(dev_name: 0x55f4a73d64e0, dir_name: 0x55f4a73d6500, type: 0x55f4a73d6480, flags: REMOUNT|RELATIME) = 0
  # trace -e mount mount -o remount,strictatime -t debugfs nodev /mnt
     0.000 ( 2.934 ms): mount/27265 mount(dev_name: 0x5617f71d94e0, dir_name: 0x5617f71d9500, type: 0x5617f71d9480, flags: REMOUNT|STRICTATIME) = 0
  # trace -e mount mount -o remount,suid,silent -t debugfs nodev /mnt
     0.000 ( 0.049 ms): mount/27273 mount(dev_name: 0x55ad65df24e0, dir_name: 0x55ad65df2500, type: 0x55ad65df2480, flags: REMOUNT|SILENT) = 0
  # trace -e mount mount -o remount,rw,sync,lazytime -t debugfs nodev /mnt
     0.000 ( 2.684 ms): mount/27281 mount(dev_name: 0x561216055530, dir_name: 0x561216055550, type: 0x561216055510, flags: SYNCHRONOUS|REMOUNT|LAZYTIME) = 0
  # trace -e mount mount -o remount,dirsync -t debugfs nodev /mnt
     0.000 ( 3.512 ms): mount/27314 mount(dev_name: 0x55c4e7188480, dir_name: 0x55c4e7188530, type: 0x55c4e71884a0, flags: REMOUNT|DIRSYNC, data: 0x55c4e71884e0) = 0
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-i5ncao73c0bd02qprgrq6wb9@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf              |  8 +++++++
 tools/perf/builtin-trace.c            |  3 +++
 tools/perf/trace/beauty/Build         |  1 +
 tools/perf/trace/beauty/beauty.h      |  6 +++++
 tools/perf/trace/beauty/mount_flags.c | 43 +++++++++++++++++++++++++++++++++++
 5 files changed, 61 insertions(+)
 create mode 100644 tools/perf/trace/beauty/mount_flags.c

(limited to 'tools/perf')

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 2f3bf025e305..a31c5c29d53a 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -460,6 +460,12 @@ madvise_behavior_tbl := $(srctree)/tools/perf/trace/beauty/madvise_behavior.sh
 $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_tbl)
 	$(Q)$(SHELL) '$(madvise_behavior_tbl)' $(madvise_hdr_dir) > $@
 
+mount_flags_array := $(beauty_outdir)/mount_flags_array.c
+mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
+
+$(mount_flags_array): $(linux_uapi_dir)/fs.h $(mount_flags_tbl)
+	$(Q)$(SHELL) '$(mount_flags_tbl)' $(linux_uapi_dir) > $@
+
 prctl_option_array := $(beauty_outdir)/prctl_option_array.c
 prctl_hdr_dir := $(srctree)/tools/include/uapi/linux/
 prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh
@@ -577,6 +583,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(socket_ipproto_array) \
 	$(vhost_virtio_ioctl_array) \
 	$(madvise_behavior_array) \
+	$(mount_flags_array) \
 	$(perf_ioctl_array) \
 	$(prctl_option_array) \
 	$(arch_errno_name_array)
@@ -863,6 +870,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
 		$(OUTPUT)pmu-events/pmu-events.c \
 		$(OUTPUT)$(madvise_behavior_array) \
+		$(OUTPUT)$(mount_flags_array) \
 		$(OUTPUT)$(drm_ioctl_array) \
 		$(OUTPUT)$(pkey_alloc_access_rights_array) \
 		$(OUTPUT)$(sndrv_ctl_ioctl_array) \
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 14fb63e17de5..76c14c0129fc 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -726,6 +726,9 @@ static struct syscall_fmt {
 	  .arg = { [0] = { .scnprintf = SCA_HEX,	/* addr */ },
 		   [2] = { .scnprintf = SCA_MMAP_PROT,	/* prot */ },
 		   [3] = { .scnprintf = SCA_MMAP_FLAGS,	/* flags */ }, }, },
+	{ .name	    = "mount",
+	  .arg = { [3] = { .scnprintf = SCA_MOUNT_FLAGS, /* flags */
+			   .mask_val  = SCAMV_MOUNT_FLAGS, /* flags */ }, }, },
 	{ .name	    = "mprotect",
 	  .arg = { [0] = { .scnprintf = SCA_HEX,	/* start */ },
 		   [2] = { .scnprintf = SCA_MMAP_PROT,	/* prot */ }, }, },
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index c3b0afd67760..304313073242 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -5,6 +5,7 @@ ifeq ($(SRCARCH),$(filter $(SRCARCH),x86))
 libperf-y += ioctl.o
 endif
 libperf-y += kcmp.o
+libperf-y += mount_flags.o
 libperf-y += pkey_alloc.o
 libperf-y += prctl.o
 libperf-y += sockaddr.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index a1806c4f3ccd..039c29039b2c 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -123,6 +123,12 @@ size_t syscall_arg__scnprintf_kcmp_type(char *bf, size_t size, struct syscall_ar
 size_t syscall_arg__scnprintf_kcmp_idx(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_KCMP_IDX syscall_arg__scnprintf_kcmp_idx
 
+unsigned long syscall_arg__mask_val_mount_flags(struct syscall_arg *arg, unsigned long flags);
+#define SCAMV_MOUNT_FLAGS syscall_arg__mask_val_mount_flags
+
+size_t syscall_arg__scnprintf_mount_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_MOUNT_FLAGS syscall_arg__scnprintf_mount_flags
+
 size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PKEY_ALLOC_ACCESS_RIGHTS syscall_arg__scnprintf_pkey_alloc_access_rights
 
diff --git a/tools/perf/trace/beauty/mount_flags.c b/tools/perf/trace/beauty/mount_flags.c
new file mode 100644
index 000000000000..712935c6620a
--- /dev/null
+++ b/tools/perf/trace/beauty/mount_flags.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * trace/beauty/mount_flags.c
+ *
+ *  Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/log2.h>
+#include <sys/mount.h>
+
+static size_t mount__scnprintf_flags(unsigned long flags, char *bf, size_t size)
+{
+#include "trace/beauty/generated/mount_flags_array.c"
+	static DEFINE_STRARRAY(mount_flags);
+
+	return strarray__scnprintf_flags(&strarray__mount_flags, bf, size, flags);
+}
+
+unsigned long syscall_arg__mask_val_mount_flags(struct syscall_arg *arg __maybe_unused, unsigned long flags)
+{
+	// do_mount in fs/namespace.c:
+	/*
+	 * Pre-0.97 versions of mount() didn't have a flags word.  When the
+	 * flags word was introduced its top half was required to have the
+	 * magic value 0xC0ED, and this remained so until 2.4.0-test9.
+	 * Therefore, if this magic number is present, it carries no
+	 * information and must be discarded.
+	 */
+	if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
+		flags &= ~MS_MGC_MSK;
+
+	return flags;
+}
+
+size_t syscall_arg__scnprintf_mount_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+	unsigned long flags = arg->val;
+
+	return mount__scnprintf_flags(flags, bf, size);
+}
-- 
cgit v1.2.3-58-ga151


From f932184e282f574cfd34afee917a10b782fd3e76 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 25 Oct 2018 17:24:45 -0300
Subject: perf trace: Consider syscall aliases too

When trying to trace the 'umount' syscall on x86_64 I noticed that it
was failing:

  # trace -e umount umount /mnt
  event syntax error: 'umount'
                       \___ parser error
  Run 'perf list' for a list of valid events

   Usage: perf trace [<options>] [<command>]
      or: perf trace [<options>] -- <command> [<options>]
      or: perf trace record [<options>] [<command>]
      or: perf trace record [<options>] -- <command> [<options>]

      -e, --event <event>   event/syscall selector. use 'perf list' to list available events
  #

This is because in the x86-64 we have it just as 'umount2':

  $ grep umount arch/x86/entry/syscalls/syscall_64.tbl
  166	common	umount2			__x64_sys_umount
  $

So if the syscall name fails, try fallbacking to looking at the aliases
we have in the syscall_fmts table to then re-lookup, now:

  # trace -e umount umount -f /mnt
  umount: /mnt: not mounted.
     1.759 ( 0.004 ms): umount/18365 umount2(name: 0x55fbfcbc4480, flags: 1) = -1 EINVAL Invalid argument
  #

Time to beautify the flags arg :-)

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ukweodgzbmjd25lfkgryeft1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

(limited to 'tools/perf')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 76c14c0129fc..db8711061ca3 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -862,6 +862,18 @@ static struct syscall_fmt *syscall_fmt__find(const char *name)
 	return bsearch(name, syscall_fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp);
 }
 
+static struct syscall_fmt *syscall_fmt__find_by_alias(const char *alias)
+{
+	int i, nmemb = ARRAY_SIZE(syscall_fmts);
+
+	for (i = 0; i < nmemb; ++i) {
+		if (syscall_fmts[i].alias && strcmp(syscall_fmts[i].alias, alias) == 0)
+			return &syscall_fmts[i];
+	}
+
+	return NULL;
+}
+
 /*
  * is_exit: is this "exit" or "exit_group"?
  * is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter.
@@ -3195,6 +3207,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 	int len = strlen(str) + 1, err = -1, list, idx;
 	char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
 	char group_name[PATH_MAX];
+	struct syscall_fmt *fmt;
 
 	if (strace_groups_dir == NULL)
 		return -1;
@@ -3212,12 +3225,19 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 		if (syscalltbl__id(trace->sctbl, s) >= 0 ||
 		    syscalltbl__strglobmatch_first(trace->sctbl, s, &idx) >= 0) {
 			list = 1;
+			goto do_concat;
+		}
+
+		fmt = syscall_fmt__find_by_alias(s);
+		if (fmt != NULL) {
+			list = 1;
+			s = fmt->name;
 		} else {
 			path__join(group_name, sizeof(group_name), strace_groups_dir, s);
 			if (access(group_name, R_OK) == 0)
 				list = 1;
 		}
-
+do_concat:
 		if (lists[list]) {
 			sprintf(lists[list] + strlen(lists[list]), ",%s", s);
 		} else {
-- 
cgit v1.2.3-58-ga151


From 476c92cacf383c83584ba02d06c88cf18f062afb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 26 Oct 2018 13:23:25 -0300
Subject: perf trace: Beautify the umount's 'name' argument

By using the SCA_FILENAME beautifier, that works when either the
probe:vfs_getname probe is in place or with the eBPF program
tools/perf/examples/bpf/augmented_syscalls.c:

  # perf probe -l
  probe:vfs_getname (on getname_flags:73@acme/git/linux/fs/namei.c with pathname)
  # perf trace -e umount
  9630.332 ( 9.521 ms): umount/8082 umount2(name: /mnt) = 0
  #

The augmented syscalls one will be done in the next patch.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-hegbzlpd2nrn584l5jxn7sy2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'tools/perf')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index db8711061ca3..d286f73ef2e5 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -838,7 +838,8 @@ static struct syscall_fmt {
 	  .arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
 	{ .name	    = "tkill",
 	  .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
-	{ .name     = "umount2", .alias = "umount", },
+	{ .name     = "umount2", .alias = "umount",
+	  .arg = { [0] = { .scnprintf = SCA_FILENAME, /* name */ }, }, },
 	{ .name	    = "uname", .alias = "newuname", },
 	{ .name	    = "unlinkat",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
-- 
cgit v1.2.3-58-ga151


From 23c07a23cbed389d0b9c7a06486574621df8d1a4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 26 Oct 2018 13:51:45 -0300
Subject: perf trace: Beautify mount's first pathname arg

The pathname beautifiers so far support just one augmented pathname per
syscall, so do it just for mount's first arg, later this will get fixed.

With:

  # perf probe -l
  probe:vfs_getname    (on getname_flags:73@acme/git/linux/fs/namei.c with pathname)
  #

Later this will get added to augmented_syscalls.c (eBPF):

In one xterm:

  # perf trace -e mount,umount
  2687.331 ( 3.544 ms): mount/8892 mount(dev_name: /mnt, dir_name: 0x561f9ac184a0, type: 0x561f9ac1b170, flags: BIND) = 0
  3912.126 ( 8.807 ms): umount/8895 umount2(name: /mnt) = 0
  ^C#

In the other:

  $ sudo mount --bind /proc /mnt
  $ sudo umount /mnt

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-qsvhrm2es635cl4zicqjeth2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'tools/perf')

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d286f73ef2e5..dc8a6c4986ce 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -727,7 +727,8 @@ static struct syscall_fmt {
 		   [2] = { .scnprintf = SCA_MMAP_PROT,	/* prot */ },
 		   [3] = { .scnprintf = SCA_MMAP_FLAGS,	/* flags */ }, }, },
 	{ .name	    = "mount",
-	  .arg = { [3] = { .scnprintf = SCA_MOUNT_FLAGS, /* flags */
+	  .arg = { [0] = { .scnprintf = SCA_FILENAME, /* dev_name */ },
+		   [3] = { .scnprintf = SCA_MOUNT_FLAGS, /* flags */
 			   .mask_val  = SCAMV_MOUNT_FLAGS, /* flags */ }, }, },
 	{ .name	    = "mprotect",
 	  .arg = { [0] = { .scnprintf = SCA_HEX,	/* start */ },
-- 
cgit v1.2.3-58-ga151


From 4e303fbe2d95806c875f5ebfcb3d980e20b4bd83 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 26 Oct 2018 15:55:23 -0300
Subject: perf top: Allow disabling the overwrite mode

In ebebbf082357 ("perf top: Switch default mode to overwrite mode") we
forgot to leave a way to disable that new default, add a --overwrite
option that can be disabled using --no-overwrite, since the code already
in such a way that we can readily disable this mode.

This is useful when investigating bugs with this mode like the recent
report from David Miller where lots of unknown symbols appear due to
disabling the events while processing them which disables all record
types, not just PERF_RECORD_SAMPLE, which makes it impossible to resolve
maps when we lose PERF_RECORD_MMAP records.

This can be easily seen while building a kernel, when there are lots of
short lived processes.

Reported-by: David Miller <davem@davemloft.net>
Acked-by: Kan Liang <kan.liang@intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: ebebbf082357 ("perf top: Switch default mode to overwrite mode")
Link: https://lkml.kernel.org/n/tip-oqgsz2bq4kgrnnajrafcdhie@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-top.txt | 5 +++++
 tools/perf/builtin-top.c              | 2 ++
 2 files changed, 7 insertions(+)

(limited to 'tools/perf')

diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 114fda12aa49..d4be6061fe1c 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -242,6 +242,11 @@ Default is to monitor all CPUS.
 --hierarchy::
 	Enable hierarchy output.
 
+--overwrite::
+	This is the default, but for investigating problems with it or any other strange
+	behaviour like lots of unknown samples, we may want to disable this mode by using
+	--no-overwrite.
+
 --force::
 	Don't do ownership validation.
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index d21d8751e749..214fad747b04 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1372,6 +1372,8 @@ int cmd_top(int argc, const char **argv)
 		    "Show raw trace event output (do not use print fmt or plugins)"),
 	OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
 		    "Show entries in a hierarchy"),
+	OPT_BOOLEAN(0, "overwrite", &top.record_opts.overwrite,
+		    "Use a backward ring buffer, default: yes"),
 	OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"),
 	OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize,
 			"number of thread to run event synthesize"),
-- 
cgit v1.2.3-58-ga151


From 218d61110f69632974034b6e27686ce482a1c455 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 29 Oct 2018 09:47:00 -0300
Subject: perf top: Do not use overwrite mode by default

Enabling --overwrite mode allows us to to use just the most recent
records, which helps in high core count machines such as Knights
Landing/Mill, but right now is being disabled by default as the pausing
used in this technique is leading to loss of metadata events such as
PERF_RECORD_MMAP which makes 'perf top' unable to resolve samples,
leading to lots of unknown samples appearing on the UI.

Enabling this may be useful if you are in such machines and profiling a
workload that doesn't creates short lived threads and/or doesn't uses
many executable mmap operations.

Work is being planed to solve this situation, till then, this will
remain disabled by default.

Reported-by: David Miller <davem@davemloft.net>
Acked-by: Kan Liang <kan.liang@intel.com>
Link: https://lkml.kernel.org/r/4f84468f-37d9-cf1b-12c1-514ef74b6a48@linux.intel.com
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: ebebbf082357 ("perf top: Switch default mode to overwrite mode")
Link: https://lkml.kernel.org/n/tip-ehvf77vi1si9409r7p4wx788@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-top.txt | 11 ++++++++---
 tools/perf/builtin-top.c              | 11 +++++++++--
 2 files changed, 17 insertions(+), 5 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index d4be6061fe1c..808b664343c9 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -243,9 +243,14 @@ Default is to monitor all CPUS.
 	Enable hierarchy output.
 
 --overwrite::
-	This is the default, but for investigating problems with it or any other strange
-	behaviour like lots of unknown samples, we may want to disable this mode by using
-	--no-overwrite.
+	Enable this to use just the most recent records, which helps in high core count
+	machines such as Knights Landing/Mill, but right now is disabled by default as
+	the pausing used in this technique is leading to loss of metadata events such
+	as PERF_RECORD_MMAP which makes 'perf top' unable to resolve samples, leading
+	to lots of unknown samples appearing on the UI. Enable this if you are in such
+	machines and profiling a workload that doesn't creates short lived threads and/or
+	doesn't uses many executable mmap operations. Work is being planed to solve
+	this situation, till then, this will remain disabled by default.
 
 --force::
 	Don't do ownership validation.
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 214fad747b04..8e29e0cc8626 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1257,7 +1257,14 @@ int cmd_top(int argc, const char **argv)
 				.uses_mmap   = true,
 			},
 			.proc_map_timeout    = 500,
-			.overwrite	= 1,
+			/*
+			 * FIXME: This will lose PERF_RECORD_MMAP and other metadata
+			 * when we pause, fix that and reenable. Probably using a
+			 * separate evlist with a dummy event, i.e. a non-overwrite
+			 * ring buffer just for metadata events, while PERF_RECORD_SAMPLE
+			 * stays in overwrite mode. -acme
+			 * */
+			.overwrite	= 0,
 		},
 		.max_stack	     = sysctl__max_stack(),
 		.annotation_opts     = annotation__default_options,
@@ -1373,7 +1380,7 @@ int cmd_top(int argc, const char **argv)
 	OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
 		    "Show entries in a hierarchy"),
 	OPT_BOOLEAN(0, "overwrite", &top.record_opts.overwrite,
-		    "Use a backward ring buffer, default: yes"),
+		    "Use a backward ring buffer, default: no"),
 	OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"),
 	OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize,
 			"number of thread to run event synthesize"),
-- 
cgit v1.2.3-58-ga151


From 1fe627da30331024f453faef04d500079b901107 Mon Sep 17 00:00:00 2001
From: Milian Wolff <milian.wolff@kdab.com>
Date: Mon, 29 Oct 2018 15:16:44 +0100
Subject: perf unwind: Take pgoff into account when reporting elf to libdwfl

libdwfl parses an ELF file itself and creates mappings for the
individual sections. perf on the other hand sees raw mmap events which
represent individual sections. When we encounter an address pointing
into a mapping with pgoff != 0, we must take that into account and
report the file at the non-offset base address.

This fixes unwinding with libdwfl in some cases. E.g. for a file like:

```

using namespace std;

mutex g_mutex;

double worker()
{
    lock_guard<mutex> guard(g_mutex);
    uniform_real_distribution<double> uniform(-1E5, 1E5);
    default_random_engine engine;
    double s = 0;
    for (int i = 0; i < 1000; ++i) {
        s += norm(complex<double>(uniform(engine), uniform(engine)));
    }
    cout << s << endl;
    return s;
}

int main()
{
    vector<std::future<double>> results;
    for (int i = 0; i < 10000; ++i) {
        results.push_back(async(launch::async, worker));
    }
    return 0;
}
```

Compile it with `g++ -g -O2 -lpthread cpp-locking.cpp  -o cpp-locking`,
then record it with `perf record --call-graph dwarf -e
sched:sched_switch`.

When you analyze it with `perf script` and libunwind, you should see:

```
cpp-locking 20038 [005] 54830.236589: sched:sched_switch: prev_comm=cpp-locking prev_pid=20038 prev_prio=120 prev_state=T ==> next_comm=swapper/5 next_pid=0 next_prio=120
        ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1670208 schedule+0x28 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb16737cc rwsem_down_read_failed+0xec (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1665e04 call_rwsem_down_read_failed+0x14 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1672a03 down_read+0x13 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb106bd85 __do_page_fault+0x445 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb18015f5 page_fault+0x45 (/lib/modules/4.14.78-1-lts/build/vmlinux)
            7f38e4252591 new_heap+0x101 (/usr/lib/libc-2.28.so)
            7f38e4252d0b arena_get2.part.4+0x2fb (/usr/lib/libc-2.28.so)
            7f38e4255b1c tcache_init.part.6+0xec (/usr/lib/libc-2.28.so)
            7f38e42569e5 __GI___libc_malloc+0x115 (inlined)
            7f38e4241790 __GI__IO_file_doallocate+0x90 (inlined)
            7f38e424fbbf __GI__IO_doallocbuf+0x4f (inlined)
            7f38e424ee47 __GI__IO_file_overflow+0x197 (inlined)
            7f38e424df36 _IO_new_file_xsputn+0x116 (inlined)
            7f38e4242bfb __GI__IO_fwrite+0xdb (inlined)
            7f38e463fa6d std::basic_streambuf<char, std::char_traits<char> >::sputn(char const*, long)+0x1cd (inlined)
            7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> >::_M_put(char const*, long)+0x1cd (inlined)
            7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> > std::__write<char>(std::ostreambuf_iterator<char, std::char_traits<char> >, char const*, int)+0x1cd (inlined)
            7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> > std::num_put<char, std::ostreambuf_iterator<char, std::char_traits<char> > >::_M_insert_float<double>(std::ostreambuf_iterator<c>
            7f38e464bd70 std::num_put<char, std::ostreambuf_iterator<char, std::char_traits<char> > >::put(std::ostreambuf_iterator<char, std::char_traits<char> >, std::ios_base&, char, double) const+0x90 (inl>
            7f38e464bd70 std::ostream& std::ostream::_M_insert<double>(double)+0x90 (/usr/lib/libstdc++.so.6.0.25)
            563b9cb502f7 std::ostream::operator<<(double)+0xb7 (inlined)
            563b9cb502f7 worker()+0xb7 (/ssd/milian/projects/kdab/rnd/hotspot/build/tests/test-clients/cpp-locking/cpp-locking)
            563b9cb506fb double std::__invoke_impl<double, double (*)()>(std::__invoke_other, double (*&&)())+0x2b (inlined)
            563b9cb506fb std::__invoke_result<double (*)()>::type std::__invoke<double (*)()>(double (*&&)())+0x2b (inlined)
            563b9cb506fb decltype (__invoke((_S_declval<0ul>)())) std::thread::_Invoker<std::tuple<double (*)()> >::_M_invoke<0ul>(std::_Index_tuple<0ul>)+0x2b (inlined)
            563b9cb506fb std::thread::_Invoker<std::tuple<double (*)()> >::operator()()+0x2b (inlined)
            563b9cb506fb std::__future_base::_Task_setter<std::unique_ptr<std::__future_base::_Result<double>, std::__future_base::_Result_base::_Deleter>, std::thread::_Invoker<std::tuple<double (*)()> >, dou>
            563b9cb506fb std::_Function_handler<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> (), std::__future_base::_Task_setter<std::unique_ptr<std::__future_>
            563b9cb507e8 std::function<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> ()>::operator()() const+0x28 (inlined)
            563b9cb507e8 std::__future_base::_State_baseV2::_M_do_set(std::function<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> ()>*, bool*)+0x28 (/ssd/milian/>
            7f38e46d24fe __pthread_once_slow+0xbe (/usr/lib/libpthread-2.28.so)
            563b9cb51149 __gthread_once+0xe9 (inlined)
            563b9cb51149 void std::call_once<void (std::__future_base::_State_baseV2::*)(std::function<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> ()>*, bool*)>
            563b9cb51149 std::__future_base::_State_baseV2::_M_set_result(std::function<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> ()>, bool)+0xe9 (inlined)
            563b9cb51149 std::__future_base::_Async_state_impl<std::thread::_Invoker<std::tuple<double (*)()> >, double>::_Async_state_impl(std::thread::_Invoker<std::tuple<double (*)()> >&&)::{lambda()#1}::op>
            563b9cb51149 void std::__invoke_impl<void, std::__future_base::_Async_state_impl<std::thread::_Invoker<std::tuple<double (*)()> >, double>::_Async_state_impl(std::thread::_Invoker<std::tuple<double>
            563b9cb51149 std::__invoke_result<std::__future_base::_Async_state_impl<std::thread::_Invoker<std::tuple<double (*)()> >, double>::_Async_state_impl(std::thread::_Invoker<std::tuple<double (*)()> >>
            563b9cb51149 decltype (__invoke((_S_declval<0ul>)())) std::thread::_Invoker<std::tuple<std::__future_base::_Async_state_impl<std::thread::_Invoker<std::tuple<double (*)()> >, double>::_Async_state_>
            563b9cb51149 std::thread::_Invoker<std::tuple<std::__future_base::_Async_state_impl<std::thread::_Invoker<std::tuple<double (*)()> >, double>::_Async_state_impl(std::thread::_Invoker<std::tuple<dou>
            563b9cb51149 std::thread::_State_impl<std::thread::_Invoker<std::tuple<std::__future_base::_Async_state_impl<std::thread::_Invoker<std::tuple<double (*)()> >, double>::_Async_state_impl(std::thread>
            7f38e45f0062 execute_native_thread_routine+0x12 (/usr/lib/libstdc++.so.6.0.25)
            7f38e46caa9c start_thread+0xfc (/usr/lib/libpthread-2.28.so)
            7f38e42ccb22 __GI___clone+0x42 (inlined)
```

Before this patch, using libdwfl, you would see:

```
cpp-locking 20038 [005] 54830.236589: sched:sched_switch: prev_comm=cpp-locking prev_pid=20038 prev_prio=120 prev_state=T ==> next_comm=swapper/5 next_pid=0 next_prio=120
        ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1670208 schedule+0x28 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb16737cc rwsem_down_read_failed+0xec (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1665e04 call_rwsem_down_read_failed+0x14 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1672a03 down_read+0x13 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb106bd85 __do_page_fault+0x445 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb18015f5 page_fault+0x45 (/lib/modules/4.14.78-1-lts/build/vmlinux)
            7f38e4252591 new_heap+0x101 (/usr/lib/libc-2.28.so)
        a041161e77950c5c [unknown] ([unknown])
```

With this patch applied, we get a bit further in unwinding:

```
cpp-locking 20038 [005] 54830.236589: sched:sched_switch: prev_comm=cpp-locking prev_pid=20038 prev_prio=120 prev_state=T ==> next_comm=swapper/5 next_pid=0 next_prio=120
        ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb166fec5 __sched_text_start+0x545 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1670208 schedule+0x28 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb16737cc rwsem_down_read_failed+0xec (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1665e04 call_rwsem_down_read_failed+0x14 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb1672a03 down_read+0x13 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb106bd85 __do_page_fault+0x445 (/lib/modules/4.14.78-1-lts/build/vmlinux)
        ffffffffb18015f5 page_fault+0x45 (/lib/modules/4.14.78-1-lts/build/vmlinux)
            7f38e4252591 new_heap+0x101 (/usr/lib/libc-2.28.so)
            7f38e4252d0b arena_get2.part.4+0x2fb (/usr/lib/libc-2.28.so)
            7f38e4255b1c tcache_init.part.6+0xec (/usr/lib/libc-2.28.so)
            7f38e42569e5 __GI___libc_malloc+0x115 (inlined)
            7f38e4241790 __GI__IO_file_doallocate+0x90 (inlined)
            7f38e424fbbf __GI__IO_doallocbuf+0x4f (inlined)
            7f38e424ee47 __GI__IO_file_overflow+0x197 (inlined)
            7f38e424df36 _IO_new_file_xsputn+0x116 (inlined)
            7f38e4242bfb __GI__IO_fwrite+0xdb (inlined)
            7f38e463fa6d std::basic_streambuf<char, std::char_traits<char> >::sputn(char const*, long)+0x1cd (inlined)
            7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> >::_M_put(char const*, long)+0x1cd (inlined)
            7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> > std::__write<char>(std::ostreambuf_iterator<char, std::char_traits<char> >, char const*, int)+0x1cd (inlined)
            7f38e463fa6d std::ostreambuf_iterator<char, std::char_traits<char> > std::num_put<char, std::ostreambuf_iterator<char, std::char_traits<char> > >::_M_insert_float<double>(std::ostreambuf_iterator<c>
            7f38e464bd70 std::num_put<char, std::ostreambuf_iterator<char, std::char_traits<char> > >::put(std::ostreambuf_iterator<char, std::char_traits<char> >, std::ios_base&, char, double) const+0x90 (inl>
            7f38e464bd70 std::ostream& std::ostream::_M_insert<double>(double)+0x90 (/usr/lib/libstdc++.so.6.0.25)
            563b9cb502f7 std::ostream::operator<<(double)+0xb7 (inlined)
            563b9cb502f7 worker()+0xb7 (/ssd/milian/projects/kdab/rnd/hotspot/build/tests/test-clients/cpp-locking/cpp-locking)
        6eab825c1ee3e4ff [unknown] ([unknown])
```

Note that the backtrace is still stopping too early, when compared to
the nice results obtained via libunwind. It's unclear so far what the
reason for that is.

Committer note:

Further comment by Milian on the thread started on the Link: tag below:

 ---
The remaining issue is due to a bug in elfutils:

https://sourceware.org/ml/elfutils-devel/2018-q4/msg00089.html

With both patches applied, libunwind and elfutils produce the same output for
the above scenario.
 ---

Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20181029141644.3907-1-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/unwind-libdw.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 6f318b15950e..5eff9bfc5758 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -45,13 +45,13 @@ static int __report_module(struct addr_location *al, u64 ip,
 		Dwarf_Addr s;
 
 		dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
-		if (s != al->map->start)
+		if (s != al->map->start - al->map->pgoff)
 			mod = 0;
 	}
 
 	if (!mod)
 		mod = dwfl_report_elf(ui->dwfl, dso->short_name,
-				      (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start,
+				      (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start - al->map->pgoff,
 				      false);
 
 	return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1;
-- 
cgit v1.2.3-58-ga151


From d6c9c05fe1eb4b213b183d8a1e79416256dc833a Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Tue, 30 Oct 2018 15:18:28 +0800
Subject: perf cs-etm: Correct CPU mode for samples

Since commit edeb0c90df35 ("perf tools: Stop fallbacking to kallsyms for
vdso symbols lookup"), the kernel address cannot be properly parsed to
kernel symbol with command 'perf script -k vmlinux'.  The reason is
CoreSight samples is always to set CPU mode as PERF_RECORD_MISC_USER,
thus it fails to find corresponding map/dso in below flows:

  process_sample_event()
    `-> machine__resolve()
	  `-> thread__find_map(thread, sample->cpumode, sample->ip, al);

In this flow it needs to pass argument 'sample->cpumode' to tell what's
the CPU mode, before it always passed PERF_RECORD_MISC_USER but without
any failure until the commit edeb0c90df35 ("perf tools: Stop fallbacking
to kallsyms for vdso symbols lookup") has been merged.  The reason is
even with the wrong CPU mode the function thread__find_map() firstly
fails to find map but it will rollback to find kernel map for vdso
symbols lookup.  In the latest code it has removed the fallback code,
thus if CPU mode is PERF_RECORD_MISC_USER then it cannot find map
anymore with kernel address.

This patch is to correct samples CPU mode setting, it creates a new
helper function cs_etm__cpu_mode() to tell what's the CPU mode based on
the address with the info from machine structure; this patch has a bit
extension to check not only kernel and user mode, but also check for
host/guest and hypervisor mode.  Finally this patch uses the function in
instruction and branch samples and also apply in cs_etm__mem_access()
for a minor polishing.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Miller <davem@davemloft.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: stable@kernel.org # v4.19
Link: http://lkml.kernel.org/r/1540883908-17018-1-git-send-email-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cs-etm.c | 39 ++++++++++++++++++++++++++++++---------
 1 file changed, 30 insertions(+), 9 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 3b37d66dc533..73430b73570d 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -244,6 +244,27 @@ static void cs_etm__free(struct perf_session *session)
 	zfree(&aux);
 }
 
+static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address)
+{
+	struct machine *machine;
+
+	machine = etmq->etm->machine;
+
+	if (address >= etmq->etm->kernel_start) {
+		if (machine__is_host(machine))
+			return PERF_RECORD_MISC_KERNEL;
+		else
+			return PERF_RECORD_MISC_GUEST_KERNEL;
+	} else {
+		if (machine__is_host(machine))
+			return PERF_RECORD_MISC_USER;
+		else if (perf_guest)
+			return PERF_RECORD_MISC_GUEST_USER;
+		else
+			return PERF_RECORD_MISC_HYPERVISOR;
+	}
+}
+
 static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 			      size_t size, u8 *buffer)
 {
@@ -258,10 +279,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 		return -1;
 
 	machine = etmq->etm->machine;
-	if (address >= etmq->etm->kernel_start)
-		cpumode = PERF_RECORD_MISC_KERNEL;
-	else
-		cpumode = PERF_RECORD_MISC_USER;
+	cpumode = cs_etm__cpu_mode(etmq, address);
 
 	thread = etmq->thread;
 	if (!thread) {
@@ -653,7 +671,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	struct perf_sample sample = {.ip = 0,};
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
-	event->sample.header.misc = PERF_RECORD_MISC_USER;
+	event->sample.header.misc = cs_etm__cpu_mode(etmq, addr);
 	event->sample.header.size = sizeof(struct perf_event_header);
 
 	sample.ip = addr;
@@ -665,7 +683,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	sample.cpu = etmq->packet->cpu;
 	sample.flags = 0;
 	sample.insn_len = 1;
-	sample.cpumode = event->header.misc;
+	sample.cpumode = event->sample.header.misc;
 
 	if (etm->synth_opts.last_branch) {
 		cs_etm__copy_last_branch_rb(etmq);
@@ -706,12 +724,15 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 		u64			nr;
 		struct branch_entry	entries;
 	} dummy_bs;
+	u64 ip;
+
+	ip = cs_etm__last_executed_instr(etmq->prev_packet);
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
-	event->sample.header.misc = PERF_RECORD_MISC_USER;
+	event->sample.header.misc = cs_etm__cpu_mode(etmq, ip);
 	event->sample.header.size = sizeof(struct perf_event_header);
 
-	sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
+	sample.ip = ip;
 	sample.pid = etmq->pid;
 	sample.tid = etmq->tid;
 	sample.addr = cs_etm__first_executed_instr(etmq->packet);
@@ -720,7 +741,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 	sample.period = 1;
 	sample.cpu = etmq->packet->cpu;
 	sample.flags = 0;
-	sample.cpumode = PERF_RECORD_MISC_USER;
+	sample.cpumode = event->sample.header.misc;
 
 	/*
 	 * perf report cannot handle events without a branch stack
-- 
cgit v1.2.3-58-ga151


From e9024d519d892b38176cafd46f68a7cdddd77412 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 30 Oct 2018 12:12:26 -0300
Subject: perf callchain: Honour the ordering of PERF_CONTEXT_{USER,KERNEL,etc}

When processing using 'perf report -g caller', which is the default, we
ended up reverting the callchain entries received from the kernel, but
simply reverting throws away the information that tells that from a
point onwards the addresses are for userspace, kernel, guest kernel,
guest user, hypervisor.

The idea is that if we are walking backwards, for each cluster of
non-cpumode entries we have to first scan backwards for the next one and
use that for the cluster.

This seems silly and more expensive than it needs to be but it is enough
for a initial fix.

The code here is really complicated because it is intimately intertwined
with the lbr and branch handling, as well as this callchain order,
further fixes will be needed to properly take into account the cpumode
in those cases.

Another problem with ORDER_CALLER is that the NULL "0" IP that is at the
end of most callchains shows up at the top of the histogram because
every callchain contains it and with ORDER_CALLER it is the first entry.

Signed-off-by: David S. Miller <davem@davemloft.net>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Souvik Banerjee <souvik1997@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: stable@vger.kernel.org # 4.19
Link: https://lkml.kernel.org/n/tip-2wt3ayp6j2y2f2xowixa8y6y@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/machine.c | 35 ++++++++++++++++++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

(limited to 'tools/perf')

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 111ae858cbcb..8ee8ab39d8ac 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2140,6 +2140,27 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 	return 0;
 }
 
+static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
+			     struct callchain_cursor *cursor,
+			     struct symbol **parent,
+			     struct addr_location *root_al,
+			     u8 *cpumode, int ent)
+{
+	int err = 0;
+
+	while (--ent >= 0) {
+		u64 ip = chain->ips[ent];
+
+		if (ip >= PERF_CONTEXT_MAX) {
+			err = add_callchain_ip(thread, cursor, parent,
+					       root_al, cpumode, ip,
+					       false, NULL, NULL, 0);
+			break;
+		}
+	}
+	return err;
+}
+
 static int thread__resolve_callchain_sample(struct thread *thread,
 					    struct callchain_cursor *cursor,
 					    struct perf_evsel *evsel,
@@ -2246,6 +2267,12 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	}
 
 check_calls:
+	if (callchain_param.order != ORDER_CALLEE) {
+		err = find_prev_cpumode(chain, thread, cursor, parent, root_al,
+					&cpumode, chain->nr - first_call);
+		if (err)
+			return (err < 0) ? err : 0;
+	}
 	for (i = first_call, nr_entries = 0;
 	     i < chain_nr && nr_entries < max_stack; i++) {
 		u64 ip;
@@ -2260,9 +2287,15 @@ check_calls:
 			continue;
 #endif
 		ip = chain->ips[j];
-
 		if (ip < PERF_CONTEXT_MAX)
                        ++nr_entries;
+		else if (callchain_param.order != ORDER_CALLEE) {
+			err = find_prev_cpumode(chain, thread, cursor, parent,
+						root_al, &cpumode, j);
+			if (err)
+				return (err < 0) ? err : 0;
+			continue;
+		}
 
 		err = add_callchain_ip(thread, cursor, parent,
 				       root_al, &cpumode, ip,
-- 
cgit v1.2.3-58-ga151


From 80ee5668b8a755039ca6180c6272a6e8efee5aad Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 15:26:47 -0300
Subject: perf beauty: Add a generator for MAP_ mmap's flag constants

It'll use tools/{arch}/*,include copies of mman.h to generate a table to
be used by tools, initially by the 'mmap' beautifiers in 'perf trace',
but that could also be used to translate from a string constant to the
integer value to be used in a eBPF or tracefs tracepoint filter.

Tested for all archs using:

$ for arch in `ls tools/arch/` ; \
	do echo $arch ; tools/perf/trace/beauty/mmap_flags.sh $arch ; \
   done | less

Example for alpha, an oddball, doesn't include any header, defines all
its stuff:

  $ tools/perf/trace/beauty/mmap_flags.sh alpha
  static const char *mmap_flags[] = {
	[ilog2(0x10) + 1] = "ANONYMOUS",
	[ilog2(0x02000) + 1] = "DENYWRITE",
	[ilog2(0x04000) + 1] = "EXECUTABLE",
	[ilog2(0x100) + 1] = "FIXED",
	[ilog2(0x01000) + 1] = "GROWSDOWN",
	[ilog2(0x100000) + 1] = "HUGETLB",
	[ilog2(0x08000) + 1] = "LOCKED",
	[ilog2(0x40000) + 1] = "NONBLOCK",
	[ilog2(0x10000) + 1] = "NORESERVE",
	[ilog2(0x20000) + 1] = "POPULATE",
	[ilog2(0x02) + 1] = "PRIVATE",
	[ilog2(0x01) + 1] = "SHARED",
	[ilog2(0x80000) + 1] = "STACK",
  };
  $

Common case, my workstation, defines one entry (MAP_32BIT), then
includes mman.h, which gets it to include mman-common.h too:

  $ tools/perf/trace/beauty/mmap_flags.sh
  static const char *mmap_flags[] = {
	[ilog2(0x40) + 1] = "32BIT",
	[ilog2(0x01) + 1] = "SHARED",
	[ilog2(0x02) + 1] = "PRIVATE",
	[ilog2(0x10) + 1] = "FIXED",
	[ilog2(0x20) + 1] = "ANONYMOUS",
	[ilog2(0x100000) + 1] = "FIXED_NOREPLACE",
	[ilog2(0x0100) + 1] = "GROWSDOWN",
	[ilog2(0x0800) + 1] = "DENYWRITE",
	[ilog2(0x1000) + 1] = "EXECUTABLE",
	[ilog2(0x2000) + 1] = "LOCKED",
	[ilog2(0x4000) + 1] = "NORESERVE",
	[ilog2(0x8000) + 1] = "POPULATE",
	[ilog2(0x10000) + 1] = "NONBLOCK",
	[ilog2(0x20000) + 1] = "STACK",
	[ilog2(0x40000) + 1] = "HUGETLB",
	[ilog2(0x80000) + 1] = "SYNC",
  };
  $ uname -m
  x86_64
  $

Sparc, that defines a bunch then includes just mman-common.h:

  $ tools/perf/trace/beauty/mmap_flags.sh sparc
  static const char *mmap_flags[] = {
	[ilog2(0x0800) + 1] = "DENYWRITE",
	[ilog2(0x1000) + 1] = "EXECUTABLE",
	[ilog2(0x0200) + 1] = "GROWSDOWN",
	[ilog2(0x40000) + 1] = "HUGETLB",
	[ilog2(0x100) + 1] = "LOCKED",
	[ilog2(0x10000) + 1] = "NONBLOCK",
	[ilog2(0x40) + 1] = "NORESERVE",
	[ilog2(0x8000) + 1] = "POPULATE",
	[ilog2(0x20000) + 1] = "STACK",
	[ilog2(0x01) + 1] = "SHARED",
	[ilog2(0x02) + 1] = "PRIVATE",
	[ilog2(0x10) + 1] = "FIXED",
	[ilog2(0x20) + 1] = "ANONYMOUS",
	[ilog2(0x100000) + 1] = "FIXED_NOREPLACE",
  };
  [acme@jouet perf]$

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-xydeh491z8fkgglcmqnl5thj@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/mmap_flags.sh | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)
 create mode 100755 tools/perf/trace/beauty/mmap_flags.sh

(limited to 'tools/perf')

diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh
new file mode 100755
index 000000000000..22c3fdca8975
--- /dev/null
+++ b/tools/perf/trace/beauty/mmap_flags.sh
@@ -0,0 +1,32 @@
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+if [ $# -ne 2 ] ; then
+	[ $# -eq 1 ] && hostarch=$1 || hostarch=`uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/`
+	header_dir=tools/include/uapi/asm-generic
+	arch_header_dir=tools/arch/${hostarch}/include/uapi/asm
+else
+	header_dir=$1
+	arch_header_dir=$2
+fi
+
+arch_mman=${arch_header_dir}/mman.h
+
+# those in egrep -vw are flags, we want just the bits
+
+printf "static const char *mmap_flags[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MAP_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
+egrep -q $regex ${arch_mman} && \
+(egrep $regex ${arch_mman} | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman} &&
+(egrep $regex ${header_dir}/mman-common.h | \
+	egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.h>.*' ${arch_mman} &&
+(egrep $regex ${header_dir}/mman.h | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+printf "};\n"
-- 
cgit v1.2.3-58-ga151


From fbd7458db75790e37903c75be68513a4c087737c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 16:11:59 -0300
Subject: perf beauty: Wire up the mmap flags table generator to the Makefile

Now when we run 'make -C tools/perf O=/tmp/build/perf' we end up with:

  $ cat /tmp/build/perf/trace/beauty/generated/mmap_flags_array.c
  static const char *mmap_flags[] = {
	[ilog2(0x40) + 1] = "32BIT",
	[ilog2(0x01) + 1] = "SHARED",
	[ilog2(0x02) + 1] = "PRIVATE",
	[ilog2(0x10) + 1] = "FIXED",
	[ilog2(0x20) + 1] = "ANONYMOUS",
	[ilog2(0x100000) + 1] = "FIXED_NOREPLACE",
	[ilog2(0x0100) + 1] = "GROWSDOWN",
	[ilog2(0x0800) + 1] = "DENYWRITE",
	[ilog2(0x1000) + 1] = "EXECUTABLE",
	[ilog2(0x2000) + 1] = "LOCKED",
	[ilog2(0x4000) + 1] = "NORESERVE",
	[ilog2(0x8000) + 1] = "POPULATE",
	[ilog2(0x10000) + 1] = "NONBLOCK",
	[ilog2(0x20000) + 1] = "STACK",
	[ilog2(0x40000) + 1] = "HUGETLB",
	[ilog2(0x80000) + 1] = "SYNC",
  };
  $

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-t3fn7u3tjsupio6e6vkufx9m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'tools/perf')

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index a31c5c29d53a..3ccb4f0bf088 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -1,4 +1,5 @@
 include ../scripts/Makefile.include
+include ../scripts/Makefile.arch
 
 # The default target of this Makefile is...
 all:
@@ -385,6 +386,8 @@ export INSTALL SHELL_PATH
 SHELL = $(SHELL_PATH)
 
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
+asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
+arch_asm_uapi_dir := $(srctree)/tools/arch/$(ARCH)/include/uapi/asm/
 
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
@@ -460,6 +463,12 @@ madvise_behavior_tbl := $(srctree)/tools/perf/trace/beauty/madvise_behavior.sh
 $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_tbl)
 	$(Q)$(SHELL) '$(madvise_behavior_tbl)' $(madvise_hdr_dir) > $@
 
+mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c
+mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh
+
+$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(arch_asm_uapi_dir)/mman.h $(mmap_flags_tbl)
+	$(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
+
 mount_flags_array := $(beauty_outdir)/mount_flags_array.c
 mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
 
@@ -583,6 +592,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(socket_ipproto_array) \
 	$(vhost_virtio_ioctl_array) \
 	$(madvise_behavior_array) \
+	$(mmap_flags_array) \
 	$(mount_flags_array) \
 	$(perf_ioctl_array) \
 	$(prctl_option_array) \
@@ -870,6 +880,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
 		$(OUTPUT)pmu-events/pmu-events.c \
 		$(OUTPUT)$(madvise_behavior_array) \
+		$(OUTPUT)$(mmap_flags_array) \
 		$(OUTPUT)$(mount_flags_array) \
 		$(OUTPUT)$(drm_ioctl_array) \
 		$(OUTPUT)$(pkey_alloc_access_rights_array) \
-- 
cgit v1.2.3-58-ga151


From 2f967f1dbbc1f746ad0deda8352bcf563d59e1c7 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 30 Oct 2018 16:30:38 -0300
Subject: perf trace beauty: Use the mmap flags table generated from headers

Instead of requiring us to go on and edit sources to add new flag.

  # perf trace -e *mmap sleep 0.1
     0.025 ( 0.005 ms): sleep/29876 mmap(len: 163746, prot: READ, flags: PRIVATE, fd: 3) = 0x7faa68ad1000
     0.059 ( 0.004 ms): sleep/29876 mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS) = 0x7faa68acf000
     0.069 ( 0.006 ms): sleep/29876 mmap(len: 3889792, prot: EXEC|READ, flags: PRIVATE|DENYWRITE, fd: 3) = 0x7faa6851f000
     0.086 ( 0.009 ms): sleep/29876 mmap(addr: 0x7faa688cb000, len: 24576, prot: READ|WRITE, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 1753088) = 0x7faa688cb000
     0.101 ( 0.005 ms): sleep/29876 mmap(addr: 0x7faa688d1000, len: 14976, prot: READ|WRITE, flags: PRIVATE|FIXED|ANONYMOUS) = 0x7faa688d1000
     0.348 ( 0.005 ms): sleep/29876 mmap(len: 111950656, prot: READ, flags: PRIVATE, fd: 3) = 0x7faa61a5b000
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ggmoy6vxoygh5yim890ht0kf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/mmap.c | 48 ++++++++++--------------------------------
 1 file changed, 11 insertions(+), 37 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 0605593552c6..c534bd96ef5c 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: LGPL-2.1
 #include <uapi/linux/mman.h>
+#include <linux/log2.h>
 
 static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 					       struct syscall_arg *arg)
@@ -30,50 +31,23 @@ static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 
 #define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot
 
+static size_t mmap__scnprintf_flags(unsigned long flags, char *bf, size_t size)
+{
+#include "trace/beauty/generated/mmap_flags_array.c"
+       static DEFINE_STRARRAY(mmap_flags);
+
+       return strarray__scnprintf_flags(&strarray__mmap_flags, bf, size, flags);
+}
+
 static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 						struct syscall_arg *arg)
 {
-	int printed = 0, flags = arg->val;
+	unsigned long flags = arg->val;
 
 	if (flags & MAP_ANONYMOUS)
 		arg->mask |= (1 << 4) | (1 << 5); /* Mask 4th ('fd') and 5th ('offset') args, ignored */
 
-#define	P_MMAP_FLAG(n) \
-	if (flags & MAP_##n) { \
-		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
-		flags &= ~MAP_##n; \
-	}
-
-	P_MMAP_FLAG(SHARED);
-	P_MMAP_FLAG(PRIVATE);
-#ifdef MAP_32BIT
-	P_MMAP_FLAG(32BIT);
-#endif
-	P_MMAP_FLAG(ANONYMOUS);
-	P_MMAP_FLAG(DENYWRITE);
-	P_MMAP_FLAG(EXECUTABLE);
-	P_MMAP_FLAG(FILE);
-	P_MMAP_FLAG(FIXED);
-#ifdef MAP_FIXED_NOREPLACE
-	P_MMAP_FLAG(FIXED_NOREPLACE);
-#endif
-	P_MMAP_FLAG(GROWSDOWN);
-	P_MMAP_FLAG(HUGETLB);
-	P_MMAP_FLAG(LOCKED);
-	P_MMAP_FLAG(NONBLOCK);
-	P_MMAP_FLAG(NORESERVE);
-	P_MMAP_FLAG(POPULATE);
-	P_MMAP_FLAG(STACK);
-	P_MMAP_FLAG(UNINITIALIZED);
-#ifdef MAP_SYNC
-	P_MMAP_FLAG(SYNC);
-#endif
-#undef P_MMAP_FLAG
-
-	if (flags)
-		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
-	return printed;
+	return mmap__scnprintf_flags(flags, bf, size);
 }
 
 #define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
-- 
cgit v1.2.3-58-ga151


From ff27a06af6ffd3f49b9e193eb68f487ad76651e1 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Tue, 30 Oct 2018 22:30:03 -0700
Subject: perf top: Start display thread earlier

If events are coming in at a rate such that the event processing thread
can barely keep up, our initial run of the event ring will almost never
terminate and this delays the starting of the display thread.

The screen basically stays black until the event thread can get out of
it's endless loop.

Therefore, start the display thread before we start processing the ring
buffer.

This also make sure that we always have the user requested real time
setting engaged when processing the ring.

Signed-off-by: David S. Miller <davem@davemloft.net>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/20181030.223003.2242527041807905962.davem@davemloft.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-top.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 8e29e0cc8626..b2838de13de0 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1134,11 +1134,6 @@ static int __cmd_top(struct perf_top *top)
         if (!target__none(&opts->target))
                 perf_evlist__enable(top->evlist);
 
-	/* Wait for a minimal set of events before starting the snapshot */
-	perf_evlist__poll(top->evlist, 100);
-
-	perf_top__mmap_read(top);
-
 	ret = -1;
 	if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
 							    display_thread), top)) {
@@ -1156,6 +1151,11 @@ static int __cmd_top(struct perf_top *top)
 		}
 	}
 
+	/* Wait for a minimal set of events before starting the snapshot */
+	perf_evlist__poll(top->evlist, 100);
+
+	perf_top__mmap_read(top);
+
 	while (!done) {
 		u64 hits = top->samples;
 
-- 
cgit v1.2.3-58-ga151


From 4f8f382e635707ddaddf8269a116e4f8cc8835c0 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Tue, 30 Oct 2018 22:24:04 -0700
Subject: perf tools: Don't clone maps from parent when synthesizing forks

When synthesizing FORK events, we are trying to create thread objects
for the already running tasks on the machine.

Normally, for a kernel FORK event, we want to clone the parent's maps
because that is what the kernel just did.

But when synthesizing, this should not be done.  If we do, we end up
with overlapping maps as we process the sythesized MMAP2 events that
get delivered shortly thereafter.

Use the FORK event misc flags in an internal way to signal this
situation, so we can elide the map clone when appropriate.

Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joe Mario <jmario@redhat.com>
Link: http://lkml.kernel.org/r/20181030.222404.2085088822877051075.davem@davemloft.net
[ Added comment about flag use in machine__process_fork_event(),
  use ternary op in thread__clone_map_groups() as suggested by Jiri ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 include/uapi/linux/perf_event.h       |  2 ++
 tools/include/uapi/linux/perf_event.h |  2 ++
 tools/perf/util/event.c               |  1 +
 tools/perf/util/machine.c             | 19 ++++++++++++++++++-
 tools/perf/util/thread.c              | 13 +++++--------
 tools/perf/util/thread.h              |  2 +-
 6 files changed, 29 insertions(+), 10 deletions(-)

(limited to 'tools/perf')

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index f35eb72739c0..9de8780ac8d9 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -646,10 +646,12 @@ struct perf_event_mmap_page {
  *
  *   PERF_RECORD_MISC_MMAP_DATA  - PERF_RECORD_MMAP* events
  *   PERF_RECORD_MISC_COMM_EXEC  - PERF_RECORD_COMM event
+ *   PERF_RECORD_MISC_FORK_EXEC  - PERF_RECORD_FORK event (perf internal)
  *   PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
  */
 #define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
+#define PERF_RECORD_MISC_FORK_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
  * These PERF_RECORD_MISC_* flags below are safely reused
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index f35eb72739c0..9de8780ac8d9 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -646,10 +646,12 @@ struct perf_event_mmap_page {
  *
  *   PERF_RECORD_MISC_MMAP_DATA  - PERF_RECORD_MMAP* events
  *   PERF_RECORD_MISC_COMM_EXEC  - PERF_RECORD_COMM event
+ *   PERF_RECORD_MISC_FORK_EXEC  - PERF_RECORD_FORK event (perf internal)
  *   PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
  */
 #define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
+#define PERF_RECORD_MISC_FORK_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
  * These PERF_RECORD_MISC_* flags below are safely reused
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index bc646185f8d9..e9c108a6b1c3 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -308,6 +308,7 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
 	event->fork.pid  = tgid;
 	event->fork.tid  = pid;
 	event->fork.header.type = PERF_RECORD_FORK;
+	event->fork.header.misc = PERF_RECORD_MISC_FORK_EXEC;
 
 	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 8ee8ab39d8ac..8f36ce813bc5 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1708,6 +1708,7 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 	struct thread *parent = machine__findnew_thread(machine,
 							event->fork.ppid,
 							event->fork.ptid);
+	bool do_maps_clone = true;
 	int err = 0;
 
 	if (dump_trace)
@@ -1736,9 +1737,25 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 
 	thread = machine__findnew_thread(machine, event->fork.pid,
 					 event->fork.tid);
+	/*
+	 * When synthesizing FORK events, we are trying to create thread
+	 * objects for the already running tasks on the machine.
+	 *
+	 * Normally, for a kernel FORK event, we want to clone the parent's
+	 * maps because that is what the kernel just did.
+	 *
+	 * But when synthesizing, this should not be done.  If we do, we end up
+	 * with overlapping maps as we process the sythesized MMAP2 events that
+	 * get delivered shortly thereafter.
+	 *
+	 * Use the FORK event misc flags in an internal way to signal this
+	 * situation, so we can elide the map clone when appropriate.
+	 */
+	if (event->fork.header.misc & PERF_RECORD_MISC_FORK_EXEC)
+		do_maps_clone = false;
 
 	if (thread == NULL || parent == NULL ||
-	    thread__fork(thread, parent, sample->time) < 0) {
+	    thread__fork(thread, parent, sample->time, do_maps_clone) < 0) {
 		dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
 		err = -1;
 	}
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 2048d393ece6..3d9ed7d0e281 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -330,7 +330,8 @@ static int thread__prepare_access(struct thread *thread)
 }
 
 static int thread__clone_map_groups(struct thread *thread,
-				    struct thread *parent)
+				    struct thread *parent,
+				    bool do_maps_clone)
 {
 	/* This is new thread, we share map groups for process. */
 	if (thread->pid_ == parent->pid_)
@@ -341,15 +342,11 @@ static int thread__clone_map_groups(struct thread *thread,
 			 thread->pid_, thread->tid, parent->pid_, parent->tid);
 		return 0;
 	}
-
 	/* But this one is new process, copy maps. */
-	if (map_groups__clone(thread, parent->mg) < 0)
-		return -ENOMEM;
-
-	return 0;
+	return do_maps_clone ? map_groups__clone(thread, parent->mg) : 0;
 }
 
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone)
 {
 	if (parent->comm_set) {
 		const char *comm = thread__comm_str(parent);
@@ -362,7 +359,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 	}
 
 	thread->ppid = parent->tid;
-	return thread__clone_map_groups(thread, parent);
+	return thread__clone_map_groups(thread, parent, do_maps_clone);
 }
 
 void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 36c09a9904e6..30e2b4c165fe 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -89,7 +89,7 @@ struct comm *thread__comm(const struct thread *thread);
 struct comm *thread__exec_comm(const struct thread *thread);
 const char *thread__comm_str(const struct thread *thread);
 int thread__insert_map(struct thread *thread, struct map *map);
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
 struct thread *thread__main_thread(struct machine *machine, struct thread *thread);
-- 
cgit v1.2.3-58-ga151


From 242483068b4b9ad02f1653819b6e683577681e0e Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 31 Oct 2018 11:10:42 +0200
Subject: perf intel-pt: Insert callchain context into synthesized callchains

In the absence of a fallback, callchains must encode also the callchain
context. Do that now there is no fallback.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: stable@vger.kernel.org # 4.19
Link: http://lkml.kernel.org/r/100ea2ec-ed14-b56d-d810-e0a6d2f4b069@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-pt.c     |  6 ++++--
 tools/perf/util/thread-stack.c | 44 +++++++++++++++++++++++++++++++++---------
 tools/perf/util/thread-stack.h |  2 +-
 3 files changed, 40 insertions(+), 12 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index ffa385a029b3..60732213d16a 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -759,7 +759,8 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 	if (pt->synth_opts.callchain) {
 		size_t sz = sizeof(struct ip_callchain);
 
-		sz += pt->synth_opts.callchain_sz * sizeof(u64);
+		/* Add 1 to callchain_sz for callchain context */
+		sz += (pt->synth_opts.callchain_sz + 1) * sizeof(u64);
 		ptq->chain = zalloc(sz);
 		if (!ptq->chain)
 			goto out_free;
@@ -1160,7 +1161,8 @@ static void intel_pt_prep_sample(struct intel_pt *pt,
 
 	if (pt->synth_opts.callchain) {
 		thread_stack__sample(ptq->thread, ptq->chain,
-				     pt->synth_opts.callchain_sz, sample->ip);
+				     pt->synth_opts.callchain_sz + 1,
+				     sample->ip, pt->kernel_start);
 		sample->callchain = ptq->chain;
 	}
 
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index c091635bf7dc..61a4286a74dc 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -310,20 +310,46 @@ void thread_stack__free(struct thread *thread)
 	}
 }
 
+static inline u64 callchain_context(u64 ip, u64 kernel_start)
+{
+	return ip < kernel_start ? PERF_CONTEXT_USER : PERF_CONTEXT_KERNEL;
+}
+
 void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
-			  size_t sz, u64 ip)
+			  size_t sz, u64 ip, u64 kernel_start)
 {
-	size_t i;
+	u64 context = callchain_context(ip, kernel_start);
+	u64 last_context;
+	size_t i, j;
 
-	if (!thread || !thread->ts)
-		chain->nr = 1;
-	else
-		chain->nr = min(sz, thread->ts->cnt + 1);
+	if (sz < 2) {
+		chain->nr = 0;
+		return;
+	}
 
-	chain->ips[0] = ip;
+	chain->ips[0] = context;
+	chain->ips[1] = ip;
+
+	if (!thread || !thread->ts) {
+		chain->nr = 2;
+		return;
+	}
+
+	last_context = context;
+
+	for (i = 2, j = 1; i < sz && j <= thread->ts->cnt; i++, j++) {
+		ip = thread->ts->stack[thread->ts->cnt - j].ret_addr;
+		context = callchain_context(ip, kernel_start);
+		if (context != last_context) {
+			if (i >= sz - 1)
+				break;
+			chain->ips[i++] = context;
+			last_context = context;
+		}
+		chain->ips[i] = ip;
+	}
 
-	for (i = 1; i < chain->nr; i++)
-		chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
+	chain->nr = i;
 }
 
 struct call_return_processor *
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index b7e41c4ebfdd..f97c00a8c251 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -84,7 +84,7 @@ int thread_stack__event(struct thread *thread, 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,
-			  size_t sz, u64 ip);
+			  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);
-- 
cgit v1.2.3-58-ga151


From 5d4f0edaa3ac4f1844ed7c64cd2bae6f1912bac5 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 31 Oct 2018 11:10:43 +0200
Subject: perf intel-pt/bts: Calculate cpumode for synthesized samples

In the absence of a fallback, samples must provide a correct cpumode for
the 'ip'. Do that now there is no fallback.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: stable@vger.kernel.org # 4.19
Link: http://lkml.kernel.org/r/20181031091043.23465-6-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/intel-bts.c | 17 ++++++++++++-----
 tools/perf/util/intel-pt.c  | 22 +++++++++++++---------
 2 files changed, 25 insertions(+), 14 deletions(-)

(limited to 'tools/perf')

diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 3b3a3d55dca1..7b27d77306c2 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -269,6 +269,13 @@ static int intel_bts_do_fix_overlap(struct auxtrace_queue *queue,
 	return 0;
 }
 
+static inline u8 intel_bts_cpumode(struct intel_bts *bts, uint64_t ip)
+{
+	return machine__kernel_ip(bts->machine, ip) ?
+	       PERF_RECORD_MISC_KERNEL :
+	       PERF_RECORD_MISC_USER;
+}
+
 static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 					 struct branch *branch)
 {
@@ -281,12 +288,8 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	    bts->num_events++ <= bts->synth_opts.initial_skip)
 		return 0;
 
-	event.sample.header.type = PERF_RECORD_SAMPLE;
-	event.sample.header.misc = PERF_RECORD_MISC_USER;
-	event.sample.header.size = sizeof(struct perf_event_header);
-
-	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = le64_to_cpu(branch->from);
+	sample.cpumode = intel_bts_cpumode(bts, sample.ip);
 	sample.pid = btsq->pid;
 	sample.tid = btsq->tid;
 	sample.addr = le64_to_cpu(branch->to);
@@ -298,6 +301,10 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	sample.insn_len = btsq->intel_pt_insn.length;
 	memcpy(sample.insn, btsq->intel_pt_insn.buf, INTEL_PT_INSN_BUF_SZ);
 
+	event.sample.header.type = PERF_RECORD_SAMPLE;
+	event.sample.header.misc = sample.cpumode;
+	event.sample.header.size = sizeof(struct perf_event_header);
+
 	if (bts->synth_opts.inject) {
 		event.sample.header.size = bts->branches_event_size;
 		ret = perf_event__synthesize_sample(&event,
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 60732213d16a..86cc9a64e982 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -407,6 +407,13 @@ intel_pt_cache_lookup(struct dso *dso, struct machine *machine, u64 offset)
 	return auxtrace_cache__lookup(dso->auxtrace_cache, offset);
 }
 
+static inline u8 intel_pt_cpumode(struct intel_pt *pt, uint64_t ip)
+{
+	return ip >= pt->kernel_start ?
+	       PERF_RECORD_MISC_KERNEL :
+	       PERF_RECORD_MISC_USER;
+}
+
 static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 				   uint64_t *insn_cnt_ptr, uint64_t *ip,
 				   uint64_t to_ip, uint64_t max_insn_cnt,
@@ -429,10 +436,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 	if (to_ip && *ip == to_ip)
 		goto out_no_cache;
 
-	if (*ip >= ptq->pt->kernel_start)
-		cpumode = PERF_RECORD_MISC_KERNEL;
-	else
-		cpumode = PERF_RECORD_MISC_USER;
+	cpumode = intel_pt_cpumode(ptq->pt, *ip);
 
 	thread = ptq->thread;
 	if (!thread) {
@@ -1059,15 +1063,11 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
 				   union perf_event *event,
 				   struct perf_sample *sample)
 {
-	event->sample.header.type = PERF_RECORD_SAMPLE;
-	event->sample.header.misc = PERF_RECORD_MISC_USER;
-	event->sample.header.size = sizeof(struct perf_event_header);
-
 	if (!pt->timeless_decoding)
 		sample->time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
-	sample->cpumode = PERF_RECORD_MISC_USER;
 	sample->ip = ptq->state->from_ip;
+	sample->cpumode = intel_pt_cpumode(pt, sample->ip);
 	sample->pid = ptq->pid;
 	sample->tid = ptq->tid;
 	sample->addr = ptq->state->to_ip;
@@ -1076,6 +1076,10 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
 	sample->flags = ptq->flags;
 	sample->insn_len = ptq->insn_len;
 	memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
+
+	event->sample.header.type = PERF_RECORD_SAMPLE;
+	event->sample.header.misc = sample->cpumode;
+	event->sample.header.size = sizeof(struct perf_event_header);
 }
 
 static int intel_pt_inject_event(union perf_event *event,
-- 
cgit v1.2.3-58-ga151