[PATCH 02/37] perf event: Check ref_reloc_sym before using it

[PATCH 02/37] perf event: Check ref_reloc_sym before using it

[Arnaldo Carvalho de Melo]

From: Igor Lubashev <ilubashe@akamai.com>

Check for ref_reloc_sym before using it instead of checking
symbol_conf.kptr_restrict and relying solely on that check.

Reported-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Signed-off-by: Igor Lubashev <ilubashe@akamai.com>
Tested-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: James Morris <jmorris@namei.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1566869956-7154-2-git-send-email-ilubashe@akamai.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/event.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 33616ea62a47..e33dd1a040cc 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -913,11 +913,13 @@ static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 	int err;
 	union perf_event *event;
 
-	if (symbol_conf.kptr_restrict)
-		return -1;
 	if (map == NULL)
 		return -1;
 
+	kmap = map__kmap(map);
+	if (!kmap->ref_reloc_sym)
+		return -1;
+
 	/*
 	 * We should get this from /sys/kernel/sections/.text, but till that is
 	 * available use this, and after it is use this as a fallback for older
@@ -940,7 +942,6 @@ static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 	}
 
-	kmap = map__kmap(map);
 	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
 			"%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1;
 	size = PERF_ALIGN(size, sizeof(u64));
-- 
2.21.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 03/37] perf tools: Use CAP_SYS_ADMIN with perf_event_paranoid checks

[Arnaldo Carvalho de Melo]

From: Igor Lubashev <ilubashe@akamai.com>

The kernel is using CAP_SYS_ADMIN instead of euid==0 to override
perf_event_paranoid check. Make perf do the same.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org> # coresight part
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: James Morris <jmorris@namei.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1566869956-7154-3-git-send-email-ilubashe@akamai.com
Signed-off-by: Igor Lubashev <ilubashe@akamai.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm/util/cs-etm.c    | 3 ++-
 tools/perf/arch/arm64/util/arm-spe.c | 3 ++-
 tools/perf/arch/x86/util/intel-bts.c | 3 ++-
 tools/perf/arch/x86/util/intel-pt.c  | 2 +-
 tools/perf/util/evsel.c              | 2 +-
 5 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index a185dab2d903..5d856edc412b 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -18,6 +18,7 @@
 #include "../../util/record.h"
 #include "../../util/auxtrace.h"
 #include "../../util/cpumap.h"
+#include "../../util/event.h"
 #include "../../util/evlist.h"
 #include "../../util/evsel.h"
 #include "../../util/pmu.h"
@@ -254,7 +255,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
 	struct evsel *evsel, *cs_etm_evsel = NULL;
 	struct perf_cpu_map *cpus = evlist->core.cpus;
-	bool privileged = (geteuid() == 0 || perf_event_paranoid() < 0);
+	bool privileged = perf_event_paranoid_check(-1);
 	int err = 0;
 
 	ptr->evlist = evlist;
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index cdd5c0c84183..c7b38f09260f 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -12,6 +12,7 @@
 #include <time.h>
 
 #include "../../util/cpumap.h"
+#include "../../util/event.h"
 #include "../../util/evsel.h"
 #include "../../util/evlist.h"
 #include "../../util/session.h"
@@ -67,7 +68,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 			container_of(itr, struct arm_spe_recording, itr);
 	struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
 	struct evsel *evsel, *arm_spe_evsel = NULL;
-	bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
+	bool privileged = perf_event_paranoid_check(-1);
 	struct evsel *tracking_evsel;
 	int err;
 
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 1f2cf612bc9c..16d26ea701ad 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -12,6 +12,7 @@
 #include <linux/zalloc.h>
 
 #include "../../util/cpumap.h"
+#include "../../util/event.h"
 #include "../../util/evsel.h"
 #include "../../util/evlist.h"
 #include "../../util/session.h"
@@ -108,7 +109,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 	struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu;
 	struct evsel *evsel, *intel_bts_evsel = NULL;
 	const struct perf_cpu_map *cpus = evlist->core.cpus;
-	bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
+	bool privileged = perf_event_paranoid_check(-1);
 
 	btsr->evlist = evlist;
 	btsr->snapshot_mode = opts->auxtrace_snapshot_mode;
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 44cfe72c1a4c..746981c82a16 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -579,7 +579,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	bool have_timing_info, need_immediate = false;
 	struct evsel *evsel, *intel_pt_evsel = NULL;
 	const struct perf_cpu_map *cpus = evlist->core.cpus;
-	bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
+	bool privileged = perf_event_paranoid_check(-1);
 	u64 tsc_bit;
 	int err;
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index fa676355559e..7c704b8f0e5c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -282,7 +282,7 @@ struct evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 
 static bool perf_event_can_profile_kernel(void)
 {
-	return geteuid() == 0 || perf_event_paranoid() == -1;
+	return perf_event_paranoid_check(-1);
 }
 
 struct evsel *perf_evsel__new_cycles(bool precise)
-- 
2.21.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 04/37] perf evsel: Kernel profiling is disallowed only when perf_event_paranoid > 1

[Arnaldo Carvalho de Melo]

From: Igor Lubashev <ilubashe@akamai.com>

Perf was too restrictive about sysctl kernel.perf_event_paranoid. The
kernel only disallows profiling when perf_event_paranoid > 1. Make perf
do the same.

Committer testing:

For a non-root user:

  $ id
  uid=1000(acme) gid=1000(acme) groups=1000(acme),10(wheel) context=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023
  $

Before:

We were restricting it to just userspace (:u suffix) even for a
workload started by the user:

  $ perf record sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.001 MB perf.data (8 samples) ]
  $ perf evlist
  cycles:u
  $ perf evlist -v
  cycles:u: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, read_format: ID, disabled: 1, inherit: 1, exclude_kernel: 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, ksymbol: 1, bpf_event: 1
  $ perf report --stdio
  # To display the perf.data header info, please use --header/--header-only options.
  #
  # Total Lost Samples: 0
  #
  # Samples: 8  of event 'cycles:u'
  # Event count (approx.): 1040396
  #
  # Overhead  Command  Shared Object     Symbol
  # ........  .......  ................  ......................
  #
      68.36%  sleep    libc-2.29.so      [.] _dl_addr
      27.33%  sleep    ld-2.29.so        [.] dl_main
       3.80%  sleep    ld-2.29.so        [.] _dl_setup_hash
  #
  # (Tip: Order by the overhead of source file name and line number: perf report -s srcline)
  #
  $
  $

After:

When the kernel allows profiling the kernel in that scenario:

  $ perf record sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.023 MB perf.data (11 samples) ]
  $ perf evlist
  cycles
  $ perf evlist -v
  cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, read_format: ID, 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, ksymbol: 1, bpf_event: 1
  $
  $ perf report --stdio
  # To display the perf.data header info, please use --header/--header-only options.
  #
  # Total Lost Samples: 0
  #
  # Samples: 11  of event 'cycles'
  # Event count (approx.): 1601964
  #
  # Overhead  Command  Shared Object     Symbol
  # ........  .......  ................  ..........................
  #
      28.14%  sleep    [kernel.vmlinux]  [k] __rb_erase_color
      27.21%  sleep    [kernel.vmlinux]  [k] unmap_page_range
      27.20%  sleep    ld-2.29.so        [.] __tunable_get_val
      15.24%  sleep    [kernel.vmlinux]  [k] thp_get_unmapped_area
       1.96%  perf     [kernel.vmlinux]  [k] perf_event_exec
       0.22%  perf     [kernel.vmlinux]  [k] native_sched_clock
       0.02%  perf     [kernel.vmlinux]  [k] intel_bts_enable_local
       0.00%  perf     [kernel.vmlinux]  [k] native_write_msr
  #
  # (Tip: Boolean options have negative forms, e.g.: perf report --no-children)
  #
  $

Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Igor Lubashev <ilubashe@akamai.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: James Morris <jmorris@namei.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1566869956-7154-4-git-send-email-ilubashe@akamai.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7c704b8f0e5c..d4540bfe4574 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -282,7 +282,7 @@ struct evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 
 static bool perf_event_can_profile_kernel(void)
 {
-	return perf_event_paranoid_check(-1);
+	return perf_event_paranoid_check(1);
 }
 
 struct evsel *perf_evsel__new_cycles(bool precise)
-- 
2.21.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 05/37] perf symbols: Use CAP_SYSLOG with kptr_restrict checks

[Arnaldo Carvalho de Melo]

From: Igor Lubashev <ilubashe@akamai.com>

The kernel is using CAP_SYSLOG capability instead of uid==0 and euid==0
when checking kptr_restrict. Make perf do the same.

Also, the kernel is a more restrictive than "no restrictions" in case of
kptr_restrict==0, so add the same logic to perf.

Signed-off-by: Igor Lubashev <ilubashe@akamai.com>
Tested-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: James Morris <jmorris@namei.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1566869956-7154-5-git-send-email-ilubashe@akamai.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/symbol.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 4efde7879474..035f2e75728c 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -4,6 +4,7 @@
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
+#include <linux/capability.h>
 #include <linux/kernel.h>
 #include <linux/mman.h>
 #include <linux/time64.h>
@@ -15,8 +16,10 @@
 #include <inttypes.h>
 #include "annotate.h"
 #include "build-id.h"
+#include "cap.h"
 #include "util.h"
 #include "debug.h"
+#include "event.h"
 #include "machine.h"
 #include "map.h"
 #include "symbol.h"
@@ -2195,13 +2198,19 @@ static bool symbol__read_kptr_restrict(void)
 		char line[8];
 
 		if (fgets(line, sizeof(line), fp) != NULL)
-			value = ((geteuid() != 0) || (getuid() != 0)) ?
-					(atoi(line) != 0) :
-					(atoi(line) == 2);
+			value = perf_cap__capable(CAP_SYSLOG) ?
+					(atoi(line) >= 2) :
+					(atoi(line) != 0);
 
 		fclose(fp);
 	}
 
+	/* Per kernel/kallsyms.c:
+	 * we also restrict when perf_event_paranoid > 1 w/o CAP_SYSLOG
+	 */
+	if (perf_event_paranoid() > 1 && !perf_cap__capable(CAP_SYSLOG))
+		value = true;
+
 	return value;
 }
 
-- 
2.21.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 06/37] perf tools: Warn that perf_event_paranoid can restrict kernel symbols

[Arnaldo Carvalho de Melo]

From: Igor Lubashev <ilubashe@akamai.com>

Warn that /proc/sys/kernel/perf_event_paranoid can also restrict kernel
symbols.

Signed-off-by: Igor Lubashev <ilubashe@akamai.com>
Tested-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: James Morris <jmorris@namei.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1566869956-7154-6-git-send-email-ilubashe@akamai.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c | 2 +-
 tools/perf/builtin-top.c    | 2 +-
 tools/perf/builtin-trace.c  | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 359bb8f33e57..afe558449677 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -2372,7 +2372,7 @@ int cmd_record(int argc, const char **argv)
 	if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(rec->evlist))
 		pr_warning(
 "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
-"check /proc/sys/kernel/kptr_restrict.\n\n"
+"check /proc/sys/kernel/kptr_restrict and /proc/sys/kernel/perf_event_paranoid.\n\n"
 "Samples in kernel functions may not be resolved if a suitable vmlinux\n"
 "file is not found in the buildid cache or in the vmlinux path.\n\n"
 "Samples in kernel modules won't be resolved at all.\n\n"
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 5970723cd55a..29e910fb2d9a 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -770,7 +770,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		if (!perf_evlist__exclude_kernel(top->session->evlist)) {
 			ui__warning(
 "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
-"Check /proc/sys/kernel/kptr_restrict.\n\n"
+"Check /proc/sys/kernel/kptr_restrict and /proc/sys/kernel/perf_event_paranoid.\n\n"
 "Kernel%s samples will not be resolved.\n",
 			  al.map && map__has_symbols(al.map) ?
 			  " modules" : "");
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 8ea62fd2591d..58a75dd3a571 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1382,7 +1382,7 @@ static char *trace__machine__resolve_kernel_addr(void *vmachine, unsigned long l
 
 	if (symbol_conf.kptr_restrict) {
 		pr_warning("Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
-			   "Check /proc/sys/kernel/kptr_restrict.\n\n"
+			   "Check /proc/sys/kernel/kptr_restrict and /proc/sys/kernel/perf_event_paranoid.\n\n"
 			   "Kernel samples will not be resolved.\n");
 		machine->kptr_restrict_warned = true;
 		return NULL;
-- 
2.21.0


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel