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: Igor Lubashev <[email protected]>
---
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 5cb07e8cb296..b87a1ca2968f 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -18,6 +18,7 @@
#include "../../perf.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 00915b8fd05b..29275a0544cd 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"
@@ -66,7 +67,7 @@ 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 7b23318ebd7b..56a76142e9fd 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"
@@ -107,7 +108,7 @@ 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 218a4e694618..43d5088ee824 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -558,7 +558,7 @@ 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 64bc32ed6dfa..eafc134bf17c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -279,7 +279,7 @@ 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)
--
2.7.4
Em Wed, Aug 07, 2019 at 10:44:15AM -0400, Igor Lubashev escreveu:
> +++ b/tools/perf/util/evsel.c
> @@ -279,7 +279,7 @@ 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);
> }
While looking at your changes I think the pre-existing code is wrong,
i.e. the check in sys_perf_event_open(), in the kernel is:
if (!attr.exclude_kernel) {
if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
return -EACCES;
}
And:
static inline bool perf_paranoid_kernel(void)
{
return sysctl_perf_event_paranoid > 1;
}
So we have to change that perf_event_paranoit_check(-1) to pass 1
instead?
bool perf_event_paranoid_check(int max_level)
{
return perf_cap__capable(CAP_SYS_ADMIN) ||
perf_event_paranoid() <= max_level;
}
Also you defined perf_cap__capable(anything) as:
#ifdef HAVE_LIBCAP_SUPPORT
#include <sys/capability.h>
bool perf_cap__capable(cap_value_t cap);
#else
static inline bool perf_cap__capable(int cap __maybe_unused)
{
return false;
}
#endif /* HAVE_LIBCAP_SUPPORT */
I think we should have:
#else
static inline bool perf_cap__capable(int cap __maybe_unused)
{
return geteuid() == 0;
}
#endif /* HAVE_LIBCAP_SUPPORT */
Right?
So I am removing the introduction of perf_cap__capable() from the first
patch you sent, leaving it with _only_ the feature detection part, using
that feature detection to do anything is then moved to a separate patch,
after we finish this discussion about what we should fallback to when
libcap-devel isn't available, i.e. we should use the previous checks,
etc.
- Arnaldo
Em Mon, Aug 12, 2019 at 05:01:34PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Wed, Aug 07, 2019 at 10:44:15AM -0400, Igor Lubashev escreveu:
> > +++ b/tools/perf/util/evsel.c
> > @@ -279,7 +279,7 @@ 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);
> > }
>
> While looking at your changes I think the pre-existing code is wrong,
> i.e. the check in sys_perf_event_open(), in the kernel is:
>
> if (!attr.exclude_kernel) {
> if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
> return -EACCES;
> }
>
> And:
>
> static inline bool perf_paranoid_kernel(void)
> {
> return sysctl_perf_event_paranoid > 1;
> }
>
> So we have to change that perf_event_paranoit_check(-1) to pass 1
> instead?
>
> bool perf_event_paranoid_check(int max_level)
> {
> return perf_cap__capable(CAP_SYS_ADMIN) ||
> perf_event_paranoid() <= max_level;
> }
>
> Also you defined perf_cap__capable(anything) as:
>
> #ifdef HAVE_LIBCAP_SUPPORT
>
> #include <sys/capability.h>
>
> bool perf_cap__capable(cap_value_t cap);
>
> #else
>
> static inline bool perf_cap__capable(int cap __maybe_unused)
> {
> return false;
> }
>
> #endif /* HAVE_LIBCAP_SUPPORT */
>
>
> I think we should have:
>
> #else
>
> static inline bool perf_cap__capable(int cap __maybe_unused)
> {
> return geteuid() == 0;
> }
>
> #endif /* HAVE_LIBCAP_SUPPORT */
>
> Right?
>
> So I am removing the introduction of perf_cap__capable() from the first
> patch you sent, leaving it with _only_ the feature detection part, using
> that feature detection to do anything is then moved to a separate patch,
> after we finish this discussion about what we should fallback to when
> libcap-devel isn't available, i.e. we should use the previous checks,
> etc.
So, please take a look at the tmp.perf/cap branch in my git repo:
https://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git/log/?h=tmp.perf/cap
I split the patch and made perf_cap__capable() fallback to 'return
geteuid() == 0;' when libcap-devel isn't available, i.e. keep the
checks made prior to your patchset.
Jiri, can I keep your Acked-by?
- Arnaldo
On Mon, August 12, 2019 at 4:16 PM Arnaldo Carvalho de Melo <[email protected]> wrote:
> Em Mon, Aug 12, 2019 at 05:01:34PM -0300, Arnaldo Carvalho de Melo
> escreveu:
> > Em Wed, Aug 07, 2019 at 10:44:15AM -0400, Igor Lubashev escreveu:
> > > +++ b/tools/perf/util/evsel.c
> > > @@ -279,7 +279,7 @@ 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);
> > > }
> >
> > While looking at your changes I think the pre-existing code is wrong,
> > i.e. the check in sys_perf_event_open(), in the kernel is:
> >
> > if (!attr.exclude_kernel) {
> > if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
> > return -EACCES;
> > }
> >
> > And:
> >
> > static inline bool perf_paranoid_kernel(void) {
> > return sysctl_perf_event_paranoid > 1; }
> >
> > So we have to change that perf_event_paranoit_check(-1) to pass 1
> > instead?
Indeed. This seems right. It was a pre-existing problem.
> > bool perf_event_paranoid_check(int max_level) {
> > return perf_cap__capable(CAP_SYS_ADMIN) ||
> > perf_event_paranoid() <= max_level; }
> >
> > Also you defined perf_cap__capable(anything) as:
> >
> > #ifdef HAVE_LIBCAP_SUPPORT
> >
> > #include <sys/capability.h>
> >
> > bool perf_cap__capable(cap_value_t cap);
> >
> > #else
> >
> > static inline bool perf_cap__capable(int cap __maybe_unused)
> > {
> > return false;
> > }
> >
> > #endif /* HAVE_LIBCAP_SUPPORT */
> >
> >
> > I think we should have:
> >
> > #else
> >
> > static inline bool perf_cap__capable(int cap __maybe_unused) {
> > return geteuid() == 0;
> > }
> >
> > #endif /* HAVE_LIBCAP_SUPPORT */
> >
> > Right?
You can have EUID==0 and not have CAP_SYS_ADMIN, though this would be rare in practice. I did not to use EUID in leu of libcap, since kernel does not do so, and therefore it seemed a bit misleading. But this is a slight matter of taste, and I do not see a problem with choosing to fall back to EUID -- the kernel will do the right thing anyway.
Now, if I were pedantic, I'd say that to use geteuid(), you need to #include <unistd.h> .
> > So I am removing the introduction of perf_cap__capable() from the
> > first patch you sent, leaving it with _only_ the feature detection
> > part, using that feature detection to do anything is then moved to a
> > separate patch, after we finish this discussion about what we should
> > fallback to when libcap-devel isn't available, i.e. we should use the
> > previous checks, etc.
>
> So, please take a look at the tmp.perf/cap branch in my git repo:
>
> https://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git/log/?h=tmp.p
> erf/cap
>
> I split the patch and made perf_cap__capable() fallback to 'return
> geteuid() == 0;' when libcap-devel isn't available, i.e. keep the checks made
> prior to your patchset.
Thank you. And thanks for updating "make_minimal".
>
> Jiri, can I keep your Acked-by?
>
> - Arnaldo
Em Mon, Aug 12, 2019 at 10:33:07PM +0000, Lubashev, Igor escreveu:
> On Mon, August 12, 2019 at 4:16 PM Arnaldo Carvalho de Melo <[email protected]> wrote:
> > Em Mon, Aug 12, 2019 at 05:01:34PM -0300, Arnaldo Carvalho de Melo
> > escreveu:
> > > Em Wed, Aug 07, 2019 at 10:44:15AM -0400, Igor Lubashev escreveu:
> > > > +++ b/tools/perf/util/evsel.c
> > > > @@ -279,7 +279,7 @@ 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);
> > > > }
> > >
> > > While looking at your changes I think the pre-existing code is wrong,
> > > i.e. the check in sys_perf_event_open(), in the kernel is:
> > >
> > > if (!attr.exclude_kernel) {
> > > if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
> > > return -EACCES;
> > > }
> > >
> > > And:
> > >
> > > static inline bool perf_paranoid_kernel(void) {
> > > return sysctl_perf_event_paranoid > 1; }
> > >
> > > So we have to change that perf_event_paranoit_check(-1) to pass 1
> > > instead?
>
> Indeed. This seems right. It was a pre-existing problem.
>
>
> > > bool perf_event_paranoid_check(int max_level) {
> > > return perf_cap__capable(CAP_SYS_ADMIN) ||
> > > perf_event_paranoid() <= max_level; }
> > >
> > > Also you defined perf_cap__capable(anything) as:
> > >
> > > #ifdef HAVE_LIBCAP_SUPPORT
> > >
> > > #include <sys/capability.h>
> > >
> > > bool perf_cap__capable(cap_value_t cap);
> > >
> > > #else
> > >
> > > static inline bool perf_cap__capable(int cap __maybe_unused)
> > > {
> > > return false;
> > > }
> > >
> > > #endif /* HAVE_LIBCAP_SUPPORT */
> > >
> > >
> > > I think we should have:
> > >
> > > #else
> > >
> > > static inline bool perf_cap__capable(int cap __maybe_unused) {
> > > return geteuid() == 0;
> > > }
> > >
> > > #endif /* HAVE_LIBCAP_SUPPORT */
> > >
> > > Right?
>
> You can have EUID==0 and not have CAP_SYS_ADMIN, though this would be rare in practice. I did not to use EUID in leu of libcap, since kernel does not do so, and therefore it seemed a bit misleading. But this is a slight matter of taste, and I do not see a problem with choosing to fall back to EUID -- the kernel will do the right thing anyway.
>
> Now, if I were pedantic, I'd say that to use geteuid(), you need to #include <unistd.h> .
Right, and that is how I did it :-)
[acme@seventh perf]$ cat tools/perf/util/cap.h
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __PERF_CAP_H
#define __PERF_CAP_H
#include <stdbool.h>
#include <linux/capability.h>
#include <linux/compiler.h>
#ifdef HAVE_LIBCAP_SUPPORT
#include <sys/capability.h>
bool perf_cap__capable(cap_value_t cap);
#else
#include <unistd.h>
#include <sys/types.h>
static inline bool perf_cap__capable(int cap __maybe_unused)
{
return geteuid() == 0;
}
#endif /* HAVE_LIBCAP_SUPPORT */
#endif /* __PERF_CAP_H */
[acme@seventh perf]$
>
> > > So I am removing the introduction of perf_cap__capable() from the
> > > first patch you sent, leaving it with _only_ the feature detection
> > > part, using that feature detection to do anything is then moved to a
> > > separate patch, after we finish this discussion about what we should
> > > fallback to when libcap-devel isn't available, i.e. we should use the
> > > previous checks, etc.
> >
> > So, please take a look at the tmp.perf/cap branch in my git repo:
> >
> > https://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git/log/?h=tmp.p
> > erf/cap
> >
> > I split the patch and made perf_cap__capable() fallback to 'return
> > geteuid() == 0;' when libcap-devel isn't available, i.e. keep the checks made
> > prior to your patchset.
>
> Thank you. And thanks for updating "make_minimal".
Ok!
> >
> > Jiri, can I keep your Acked-by?
> >
> > - Arnaldo
--
- Arnaldo