[PATCH 03/10] perf db-export: Fix thread__exec_comm()

[PATCH 03/10] perf db-export: Fix thread__exec_comm()

[Arnaldo Carvalho de Melo]

From: Adrian Hunter <adrian.hunter@intel.com>

Threads synthesized from /proc have comms with a start time of zero, and
not marked as "exec". Currently, there can be 2 such comms. The first is
created by processing a synthesized fork event and is set to the
parent's comm string, and the second by processing a synthesized comm
event set to the thread's current comm string.

In the absence of an "exec" comm, thread__exec_comm() picks the last
(oldest) comm, which, in the case above, is the parent's comm string.
For a main thread, that is very probably wrong. Use the second-to-last
in that case.

This affects only db-export because it is the only user of
thread__exec_comm().

Example:

  $ sudo perf record -a -o pt-a-sleep-1 -e intel_pt//u -- sleep 1
  $ sudo chown ahunter pt-a-sleep-1

Before:

  $ perf script -i pt-a-sleep-1 --itrace=bep -s tools/perf/scripts/python/export-to-sqlite.py pt-a-sleep-1.db branches calls
  $ sqlite3 -header -column pt-a-sleep-1.db 'select * from comm_threads_view'
  comm_id     command     thread_id   pid         tid
  ----------  ----------  ----------  ----------  ----------
  1           swapper     1           0           0
  2           rcu_sched   2           10          10
  3           kthreadd    3           78          78
  5           sudo        4           15180       15180
  5           sudo        5           15180       15182
  7           kworker/4:  6           10335       10335
  8           kthreadd    7           55          55
  10          systemd     8           865         865
  10          systemd     9           865         875
  13          perf        10          15181       15181
  15          sleep       10          15181       15181
  16          kworker/3:  11          14179       14179
  17          kthreadd    12          29376       29376
  19          systemd     13          746         746
  21          systemd     14          401         401
  23          systemd     15          879         879
  23          systemd     16          879         945
  25          kthreadd    17          556         556
  27          kworker/u1  18          14136       14136
  28          kworker/u1  19          15021       15021
  29          kthreadd    20          509         509
  31          systemd     21          836         836
  31          systemd     22          836         967
  33          systemd     23          1148        1148
  33          systemd     24          1148        1163
  35          kworker/2:  25          17988       17988
  36          kworker/0:  26          13478       13478

After:

  $ perf script -i pt-a-sleep-1 --itrace=bep -s tools/perf/scripts/python/export-to-sqlite.py pt-a-sleep-1b.db branches calls
  $ sqlite3 -header -column pt-a-sleep-1b.db 'select * from comm_threads_view'
  comm_id     command     thread_id   pid         tid
  ----------  ----------  ----------  ----------  ----------
  1           swapper     1           0           0
  2           rcu_sched   2           10          10
  3           kswapd0     3           78          78
  4           perf        4           15180       15180
  4           perf        5           15180       15182
  6           kworker/4:  6           10335       10335
  7           kcompactd0  7           55          55
  8           accounts-d  8           865         865
  8           accounts-d  9           865         875
  10          perf        10          15181       15181
  12          sleep       10          15181       15181
  13          kworker/3:  11          14179       14179
  14          kworker/1:  12          29376       29376
  15          haveged     13          746         746
  16          systemd-jo  14          401         401
  17          NetworkMan  15          879         879
  17          NetworkMan  16          879         945
  19          irq/131-iw  17          556         556
  20          kworker/u1  18          14136       14136
  21          kworker/u1  19          15021       15021
  22          kworker/u1  20          509         509
  23          thermald    21          836         836
  23          thermald    22          836         967
  25          unity-sett  23          1148        1148
  25          unity-sett  24          1148        1163
  27          kworker/2:  25          17988       17988
  28          kworker/0:  26          13478       13478

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: stable@vger.kernel.org
Fixes: 65de51f93ebf ("perf tools: Identify which comms are from exec")
Link: http://lkml.kernel.org/r/20190808064823.14846-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/thread.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 873ab505ca80..590793cc5142 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -214,14 +214,24 @@ struct comm *thread__comm(const struct thread *thread)
 
 struct comm *thread__exec_comm(const struct thread *thread)
 {
-	struct comm *comm, *last = NULL;
+	struct comm *comm, *last = NULL, *second_last = NULL;
 
 	list_for_each_entry(comm, &thread->comm_list, list) {
 		if (comm->exec)
 			return comm;
+		second_last = last;
 		last = comm;
 	}
 
+	/*
+	 * 'last' with no start time might be the parent's comm of a synthesized
+	 * thread (created by processing a synthesized fork event). For a main
+	 * thread, that is very probably wrong. Prefer a later comm to avoid
+	 * that case.
+	 */
+	if (second_last && !last->start && thread->pid_ == thread->tid)
+		return second_last;
+
 	return last;
 }
 
-- 
2.21.0

[PATCH 08/10] perf record: Fix module size on s390

[Arnaldo Carvalho de Melo]

From: Thomas Richter <tmricht@linux.ibm.com>

On s390 the modules loaded in memory have the text segment located after
the GOT and Relocation table. This can be seen with this output:

  [root@m35lp76 perf]# fgrep qeth /proc/modules
  qeth 151552 1 qeth_l2, Live 0x000003ff800b2000
  ...
  [root@m35lp76 perf]# cat /sys/module/qeth/sections/.text
  0x000003ff800b3990
  [root@m35lp76 perf]#

There is an offset of 0x1990 bytes. The size of the qeth module is
151552 bytes (0x25000 in hex).

The location of the GOT/relocation table at the beginning of a module is
unique to s390.

commit 203d8a4aa6ed ("perf s390: Fix 'start' address of module's map")
adjusts the start address of a module in the map structures, but does
not adjust the size of the modules. This leads to overlapping of module
maps as this example shows:

[root@m35lp76 perf] # ./perf report -D
     0 0 0xfb0 [0xa0]: PERF_RECORD_MMAP -1/0: [0x3ff800b3990(0x25000)
          @ 0]:  x /lib/modules/.../qeth.ko.xz
     0 0 0x1050 [0xb0]: PERF_RECORD_MMAP -1/0: [0x3ff800d85a0(0x8000)
          @ 0]:  x /lib/modules/.../ip6_tables.ko.xz

The module qeth.ko has an adjusted start address modified to b3990, but
its size is unchanged and the module ends at 0x3ff800d8990.  This end
address overlaps with the next modules start address of 0x3ff800d85a0.

When the size of the leading GOT/Relocation table stored in the
beginning of the text segment (0x1990 bytes) is subtracted from module
qeth end address, there are no overlaps anymore:

   0x3ff800d8990 - 0x1990 = 0x0x3ff800d7000

which is the same as

   0x3ff800b2000 + 0x25000 = 0x0x3ff800d7000.

To fix this issue, also adjust the modules size in function
arch__fix_module_text_start(). Add another function parameter named size
and reduce the size of the module when the text segment start address is
changed.

Output after:
     0 0 0xfb0 [0xa0]: PERF_RECORD_MMAP -1/0: [0x3ff800b3990(0x23670)
          @ 0]:  x /lib/modules/.../qeth.ko.xz
     0 0 0x1050 [0xb0]: PERF_RECORD_MMAP -1/0: [0x3ff800d85a0(0x7a60)
          @ 0]:  x /lib/modules/.../ip6_tables.ko.xz

Reported-by: Stefan Liebler <stli@linux.ibm.com>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Hendrik Brueckner <brueckner@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: stable@vger.kernel.org
Fixes: 203d8a4aa6ed ("perf s390: Fix 'start' address of module's map")
Link: http://lkml.kernel.org/r/20190724122703.3996-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/s390/util/machine.c | 14 +++++++++++++-
 tools/perf/util/machine.c           |  3 ++-
 tools/perf/util/machine.h           |  2 +-
 3 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
index a19690a17291..de26b1441a48 100644
--- a/tools/perf/arch/s390/util/machine.c
+++ b/tools/perf/arch/s390/util/machine.c
@@ -7,7 +7,7 @@
 #include "api/fs/fs.h"
 #include "debug.h"
 
-int arch__fix_module_text_start(u64 *start, const char *name)
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name)
 {
 	u64 m_start = *start;
 	char path[PATH_MAX];
@@ -17,6 +17,18 @@ int arch__fix_module_text_start(u64 *start, const char *name)
 	if (sysfs__read_ull(path, (unsigned long long *)start) < 0) {
 		pr_debug2("Using module %s start:%#lx\n", path, m_start);
 		*start = m_start;
+	} else {
+		/* Successful read of the modules segment text start address.
+		 * Calculate difference between module start address
+		 * in memory and module text segment start address.
+		 * For example module load address is 0x3ff8011b000
+		 * (from /proc/modules) and module text segment start
+		 * address is 0x3ff8011b870 (from file above).
+		 *
+		 * Adjust the module size and subtract the GOT table
+		 * size located at the beginning of the module.
+		 */
+		*size -= (*start - m_start);
 	}
 
 	return 0;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index cf826eca3aaf..83b2fbbeeb90 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1378,6 +1378,7 @@ static int machine__set_modules_path(struct machine *machine)
 	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
 }
 int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
+				u64 *size __maybe_unused,
 				const char *name __maybe_unused)
 {
 	return 0;
@@ -1389,7 +1390,7 @@ static int machine__create_module(void *arg, const char *name, u64 start,
 	struct machine *machine = arg;
 	struct map *map;
 
-	if (arch__fix_module_text_start(&start, name) < 0)
+	if (arch__fix_module_text_start(&start, &size, name) < 0)
 		return -1;
 
 	map = machine__findnew_module_map(machine, start, name);
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index f70ab98a7bde..7aa38da26427 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -222,7 +222,7 @@ struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine,
 
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename);
-int arch__fix_module_text_start(u64 *start, const char *name);
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name);
 
 int machine__load_kallsyms(struct machine *machine, const char *filename);
 
-- 
2.21.0

[PATCH 09/10] perf annotate: Fix s390 gap between kernel end and module start

[Arnaldo Carvalho de Melo]

From: Thomas Richter <tmricht@linux.ibm.com>

During execution of command 'perf top' the error message:

   Not enough memory for annotating '__irf_end' symbol!)

is emitted from this call sequence:
  __cmd_top
    perf_top__mmap_read
      perf_top__mmap_read_idx
        perf_event__process_sample
          hist_entry_iter__add
            hist_iter__top_callback
              perf_top__record_precise_ip
                hist_entry__inc_addr_samples
                  symbol__inc_addr_samples
                    symbol__get_annotation
                      symbol__alloc_hist

In this function the size of symbol __irf_end is calculated. The size of
a symbol is the difference between its start and end address.

When the symbol was read the first time, its start and end was set to:

   symbol__new: __irf_end 0xe954d0-0xe954d0

which is correct and maps with /proc/kallsyms:

   root@s8360046:~/linux-4.15.0/tools/perf# fgrep _irf_end /proc/kallsyms
   0000000000e954d0 t __irf_end
   root@s8360046:~/linux-4.15.0/tools/perf#

In function symbol__alloc_hist() the end of symbol __irf_end is

  symbol__alloc_hist sym:__irf_end start:0xe954d0 end:0x3ff80045a8

which is identical with the first module entry in /proc/kallsyms

This results in a symbol size of __irf_req for histogram analyses of
70334140059072 bytes and a malloc() for this requested size fails.

The root cause of this is function
  __dso__load_kallsyms()
  +-> symbols__fixup_end()

Function symbols__fixup_end() enlarges the last symbol in the kallsyms
map:

   # fgrep __irf_end /proc/kallsyms
   0000000000e954d0 t __irf_end
   #

to the start address of the first module:
   # cat /proc/kallsyms | sort  | egrep ' [tT] '
   ....
   0000000000e952d0 T __security_initcall_end
   0000000000e954d0 T __initramfs_size
   0000000000e954d0 t __irf_end
   000003ff800045a8 T fc_get_event_number       [scsi_transport_fc]
   000003ff800045d0 t store_fc_vport_disable    [scsi_transport_fc]
   000003ff800046a8 T scsi_is_fc_rport  [scsi_transport_fc]
   000003ff800046d0 t fc_target_setup   [scsi_transport_fc]

On s390 the kernel is located around memory address 0x200, 0x10000 or
0x100000, depending on linux version. Modules however start some- where
around 0x3ff xxxx xxxx.

This is different than x86 and produces a large gap for which histogram
allocation fails.

Fix this by detecting the kernel's last symbol and do no adjustment for
it. Introduce a weak function and handle s390 specifics.

Reported-by: Klaus Theurich <klaus.theurich@de.ibm.com>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Hendrik Brueckner <brueckner@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/20190724122703.3996-2-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/s390/util/machine.c | 17 +++++++++++++++++
 tools/perf/util/symbol.c            |  7 ++++++-
 tools/perf/util/symbol.h            |  1 +
 3 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
index de26b1441a48..c8c86a0c9b79 100644
--- a/tools/perf/arch/s390/util/machine.c
+++ b/tools/perf/arch/s390/util/machine.c
@@ -6,6 +6,7 @@
 #include "machine.h"
 #include "api/fs/fs.h"
 #include "debug.h"
+#include "symbol.h"
 
 int arch__fix_module_text_start(u64 *start, u64 *size, const char *name)
 {
@@ -33,3 +34,19 @@ int arch__fix_module_text_start(u64 *start, u64 *size, const char *name)
 
 	return 0;
 }
+
+/* On s390 kernel text segment start is located at very low memory addresses,
+ * for example 0x10000. Modules are located at very high memory addresses,
+ * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment
+ * and beginning of first module's text segment is very big.
+ * Therefore do not fill this gap and do not assign it to the kernel dso map.
+ */
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
+		/* Last kernel symbol mapped to end of page */
+		p->end = roundup(p->end, page_size);
+	else
+		p->end = c->start;
+	pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end);
+}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 173f3378aaa0..4efde7879474 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -92,6 +92,11 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
+void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	p->end = c->start;
+}
+
 const char * __weak arch__normalize_symbol_name(const char *name)
 {
 	return name;
@@ -218,7 +223,7 @@ void symbols__fixup_end(struct rb_root_cached *symbols)
 		curr = rb_entry(nd, struct symbol, rb_node);
 
 		if (prev->end == prev->start && prev->end != curr->start)
-			prev->end = curr->start;
+			arch__symbols__fixup_end(prev, curr);
 	}
 
 	/* Last entry */
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 12755b42ea93..183f630cb5f1 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -288,6 +288,7 @@ const char *arch__normalize_symbol_name(const char *name);
 #define SYMBOL_A 0
 #define SYMBOL_B 1
 
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c);
 int arch__compare_symbol_names(const char *namea, const char *nameb);
 int arch__compare_symbol_names_n(const char *namea, const char *nameb,
 				 unsigned int n);
-- 
2.21.0