Introduce CAP_PERFMON to secure system performance monitoring and observability
Subsystems (15)
v8 cover Introduce CAP_PERFMON to secure system performance monitoring and observability
Changes in v8:
- added Acked-by and Reviewed-by tags acquired so far
- rebased on the top of tip perf/core repository:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip perf/core
sha1: 629b3df7ecb01fddfdf71cb5d3c563d143117c33
Changes in v7:
- updated and extended kernel.rst and perf-security.rst documentation files with the information about CAP_PERFMON capability and its use cases
- documented the case of double audit logging of CAP_PERFMON and CAP_SYS_ADMIN capabilities on a SELinux enabled system
Changes in v6:
- avoided noaudit checks in perfmon_capable() to explicitly advertise CAP_PERFMON usage thru audit logs to secure system performance monitoring and observability
Changes in v5:
- renamed CAP_SYS_PERFMON to CAP_PERFMON
- extended perfmon_capable() with noaudit checks
Changes in v4:
- converted perfmon_capable() into an inline function
- made perf_events kprobes, uprobes, hw breakpoints and namespaces data available to CAP_SYS_PERFMON privileged processes
- applied perfmon_capable() to drivers/perf and drivers/oprofile
- extended __cmd_ftrace() with support of CAP_SYS_PERFMON
Changes in v3:
- implemented perfmon_capable() macros aggregating required capabilities checks
Changes in v2:
- made perf_events trace points available to CAP_SYS_PERFMON privileged processes
- made perf_event_paranoid_check() treat CAP_SYS_PERFMON equally to CAP_SYS_ADMIN
- applied CAP_SYS_PERFMON to i915_perf, bpf_trace, powerpc and parisc system performance monitoring and observability related subsystems
Currently access to perf_events, i915_perf and other performance monitoring and observability subsystems of the kernel is open only for a privileged process [1] with CAP_SYS_ADMIN capability enabled in the process effective set [2].
This patch set introduces CAP_PERFMON capability designed to secure system performance monitoring and observability operations so that CAP_PERFMON would assist CAP_SYS_ADMIN capability in its governing role for performance monitoring and observability subsystems of the kernel.
CAP_PERFMON intends to harden system security and integrity during performance monitoring and observability operations by decreasing attack surface that is available to a CAP_SYS_ADMIN privileged process [2]. Providing the access to performance monitoring and observability operations under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes the operation more secure. Thus, CAP_PERFMON implements the principal of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e: 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
CAP_PERFMON intends to meet the demand to secure system performance monitoring and observability operations for adoption in security sensitive, restricted, multiuser production environments (e.g. HPC clusters, cloud and virtual compute environments), where root or CAP_SYS_ADMIN credentials are not available to mass users of a system, and securely unblock accessibility of system performance monitoring and observability operations beyond root and CAP_SYS_ADMIN use cases.
CAP_PERFMON intends to take over CAP_SYS_ADMIN credentials related to system performance monitoring and observability operations and balance amount of CAP_SYS_ADMIN credentials following the recommendations in the capabilities man page [2] for CAP_SYS_ADMIN: "Note: this capability is overloaded; see Notes to kernel developers, below." For backward compatibility reasons access to system performance monitoring and observability subsystems of the kernel remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN capability usage for secure system performance monitoring and observability operations is discouraged with respect to the designed CAP_PERFMON capability.
Possible alternative solution to this system security hardening, capabilities balancing task of making performance monitoring and observability operations more secure and accessible could be to use the existing CAP_SYS_PTRACE capability to govern system performance monitoring and observability subsystems. However CAP_SYS_PTRACE capability still provides users with more credentials than are required for secure performance monitoring and observability operations and this excess is avoided by the designed CAP_PERFMON.
Although software running under CAP_PERFMON can not ensure avoidance of related hardware issues, the software can still mitigate those issues following the official hardware issues mitigation procedure [3]. The bugs in the software itself can be fixed following the standard kernel development process [4] to maintain and harden security of system performance monitoring and observability operations. Finally, the patch set is shaped in the way that simplifies backtracking procedure of possible induced issues [5] as much as possible.
---
Alexey Budankov (12):
capabilities: introduce CAP_PERFMON to kernel and user space perf/core: open access to the core for CAP_PERFMON privileged process perf/core: open access to probes for CAP_PERFMON privileged process perf tool: extend Perf tool with CAP_PERFMON capability support drm/i915/perf: open access for CAP_PERFMON privileged process trace/bpf_trace: open access for CAP_PERFMON privileged process powerpc/perf: open access for CAP_PERFMON privileged process parisc/perf: open access for CAP_PERFMON privileged process drivers/perf: open access for CAP_PERFMON privileged process drivers/oprofile: open access for CAP_PERFMON privileged process doc/admin-guide: update perf-security.rst with CAP_PERFMON information doc/admin-guide: update kernel.rst with CAP_PERFMON information
Documentation/admin-guide/perf-security.rst | 65 +++++++++++++-------- Documentation/admin-guide/sysctl/kernel.rst | 16 +++-- arch/parisc/kernel/perf.c | 2 +- arch/powerpc/perf/imc-pmu.c | 4 +- drivers/gpu/drm/i915/i915_perf.c | 13 ++--- drivers/oprofile/event_buffer.c | 2 +- drivers/perf/arm_spe_pmu.c | 4 +- include/linux/capability.h | 4 ++ include/linux/perf_event.h | 6 +- include/uapi/linux/capability.h | 8 ++- kernel/events/core.c | 6 +- kernel/trace/bpf_trace.c | 2 +- security/selinux/include/classmap.h | 4 +- tools/perf/builtin-ftrace.c | 5 +- tools/perf/design.txt | 3 +- tools/perf/util/cap.h | 4 ++ tools/perf/util/evsel.c | 10 ++-- tools/perf/util/util.c | 1 + 18 files changed, 98 insertions(+), 61 deletions(-)
---
Validation (Intel Skylake, 8 cores, Fedora 29, 5.5.0-rc3+, x86_64):
libcap library [6], [7], [8] and Perf tool can be used to apply CAP_PERFMON capability for secure system performance monitoring and observability beyond the scope permitted by the system wide perf_event_paranoid kernel setting [9] and below are the steps for evaluation:
- patch, build and boot the kernel
- patch, build Perf tool e.g. to /home/user/perf
...
# git clone git://git.kernel.org/pub/scm/libs/libcap/libcap.git libcap
# pushd libcap
# patch libcap/include/uapi/linux/capabilities.h with [PATCH 1]
# make
# pushd progs
# ./setcap "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" /home/user/perf
# ./setcap -v "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" /home/user/perf
/home/user/perf: OK
# ./getcap /home/user/perf
/home/user/perf = cap_sys_ptrace,cap_syslog,cap_perfmon+ep
# echo 2 > /proc/sys/kernel/perf_event_paranoid
# cat /proc/sys/kernel/perf_event_paranoid
2
...
$ /home/user/perf top
... works as expected ...
$ cat /proc/`pidof perf`/status
Name: perf
Umask: 0002
State: S (sleeping)
Tgid: 2958
Ngid: 0
Pid: 2958
PPid: 9847
TracerPid: 0
Uid: 500 500 500 500
Gid: 500 500 500 500
FDSize: 256
...
CapInh: 0000000000000000
CapPrm: 0000004400080000
CapEff: 0000004400080000 => 01000100 00000000 00001000 00000000 00000000
cap_perfmon,cap_sys_ptrace,cap_syslog
CapBnd: 0000007fffffffff
CapAmb: 0000000000000000
NoNewPrivs: 0
Seccomp: 0
Speculation_Store_Bypass: thread vulnerable
Cpus_allowed: ff
Cpus_allowed_list: 0-7
...Usage of cap_perfmon effectively avoids unused credentials excess:
- with cap_sys_admin:
CapEff: 0000007fffffffff => 01111111 11111111 11111111 11111111 11111111
- with cap_perfmon:
CapEff: 0000004400080000 => 01000100 00000000 00001000 00000000 00000000
38 34 19
perfmon syslog sys_ptrace---
[1] https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html
[2] http://man7.org/linux/man-pages/man7/capabilities.7.html
[3] https://www.kernel.org/doc/html/latest/process/embargoed-hardware-issues.html
[4] https://www.kernel.org/doc/html/latest/admin-guide/security-bugs.html
[5] https://www.kernel.org/doc/html/latest/process/management-style.html#decisions
[6] http://man7.org/linux/man-pages/man8/setcap.8.html
[7] https://git.kernel.org/pub/scm/libs/libcap/libcap.git
[8] https://sites.google.com/site/fullycapable/, posix_1003.1e-990310.pdf
[9] http://man7.org/linux/man-pages/man2/perf_event_open.2.html
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
PATCH v8 1/12 capabilities: introduce CAP_PERFMON to kernel and user space
Introduce CAP_PERFMON capability designed to secure system performance monitoring and observability operations so that CAP_PERFMON would assist CAP_SYS_ADMIN capability in its governing role for performance monitoring and observability subsystems.
CAP_PERFMON hardens system security and integrity during performance monitoring and observability operations by decreasing attack surface that is available to a CAP_SYS_ADMIN privileged process [2]. Providing the access to system performance monitoring and observability operations under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes the operation more secure. Thus, CAP_PERFMON implements the principal of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e: 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
CAP_PERFMON meets the demand to secure system performance monitoring and observability operations for adoption in security sensitive, restricted, multiuser production environments (e.g. HPC clusters, cloud and virtual compute environments), where root or CAP_SYS_ADMIN credentials are not available to mass users of a system, and securely unblocks applicability and scalability of system performance monitoring and observability operations beyond root and CAP_SYS_ADMIN use cases.
CAP_PERFMON takes over CAP_SYS_ADMIN credentials related to system performance monitoring and observability operations and balances amount of CAP_SYS_ADMIN credentials following the recommendations in the capabilities man page [1] for CAP_SYS_ADMIN: "Note: this capability is overloaded; see Notes to kernel developers, below." For backward compatibility reasons access to system performance monitoring and observability subsystems of the kernel remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN capability usage for secure system performance monitoring and observability operations is discouraged with respect to the designed CAP_PERFMON capability.
Although the software running under CAP_PERFMON can not ensure avoidance of related hardware issues, the software can still mitigate these issues following the official hardware issues mitigation procedure [2]. The bugs in the software itself can be fixed following the standard kernel development process [3] to maintain and harden security of system performance monitoring and observability operations.
[1] http://man7.org/linux/man-pages/man7/capabilities.7.html
[2] https://www.kernel.org/doc/html/latest/process/embargoed-hardware-issues.html
[3] https://www.kernel.org/doc/html/latest/admin-guide/security-bugs.html
--- include/linux/capability.h | 4 ++++ include/uapi/linux/capability.h | 8 +++++++- security/selinux/include/classmap.h | 4 ++-- 3 files changed, 13 insertions(+), 3 deletions(-)
include/linux/capability.h +4 -0
@@ -251,6 +251,10 @@ extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const structextern bool capable_wrt_inode_uidgid (const struct inode *inode,int cap);extern bool file_ns_capable (const struct file *file,struct user_namespace *ns,int cap);extern bool ptracer_capable (struct task_struct *tsk,struct user_namespace *ns); +static inline bool perfmon_capable (void ) +{ +return capable (CAP_PERFMON ) ||capable (CAP_SYS_ADMIN ); +}/* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk (const struct dentry *dentry,struct cpu_vfs_cap_data *cpu_caps);
include/uapi/linux/capability.h +7 -1
@@ -367,8 +367,14 @@ struct vfs_ns_cap_data {#define CAP_AUDIT_READ 37 +/* +* Allow system performance and observability privileged operations +* using perf_events, i915_perf and other kernel subsystems +*/ + +#define CAP_PERFMON 38 -#define CAP_LAST_CAP CAP_AUDIT_READ +#define CAP_LAST_CAP CAP_PERFMON#define cap_valid (x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
security/selinux/include/classmap.h +2 -2
@@ -27,9 +27,9 @@ "audit_control", "setfcap"#define COMMON_CAP2_PERMS "mac_override", "mac_admin", "syslog", \ - "wake_alarm", "block_suspend", "audit_read" + "wake_alarm", "block_suspend", "audit_read", "perfmon" -#if CAP_LAST_CAP >CAP_AUDIT_READ +#if CAP_LAST_CAP >CAP_PERFMON #error New capability defined, please update COMMON_CAP2_PERMS.#endif
Signature · 1 line
2.24.1
[tip: perf/core] capabilities: Introduce CAP_PERFMON to kernel and user space
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 980737282232b752bb14dab96d77665c15889c36 Gitweb: https://git.kernel.org/tip/980737282232b752bb14dab96d77665c15889c36 Author: Alexey Budankov <[email protected]> AuthorDate: Thu, 02 Apr 2020 11:45:31 +03:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Thu, 16 Apr 2020 12:19:06 -03:00
capabilities: Introduce CAP_PERFMON to kernel and user space
Introduce the CAP_PERFMON capability designed to secure system performance monitoring and observability operations so that CAP_PERFMON can assist CAP_SYS_ADMIN capability in its governing role for performance monitoring and observability subsystems.
CAP_PERFMON hardens system security and integrity during performance monitoring and observability operations by decreasing attack surface that is available to a CAP_SYS_ADMIN privileged process [2]. Providing the access to system performance monitoring and observability operations under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes the operation more secure.
Thus, CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e:
2.2.2.39 principle of least privilege: A security design principle that
states that a process or program be granted only those privileges
(e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
CAP_PERFMON meets the demand to secure system performance monitoring and observability operations for adoption in security sensitive, restricted, multiuser production environments (e.g. HPC clusters, cloud and virtual compute environments), where root or CAP_SYS_ADMIN credentials are not available to mass users of a system, and securely unblocks applicability and scalability of system performance monitoring and observability operations beyond root and CAP_SYS_ADMIN use cases.
CAP_PERFMON takes over CAP_SYS_ADMIN credentials related to system performance monitoring and observability operations and balances amount of CAP_SYS_ADMIN credentials following the recommendations in the capabilities man page [1] for CAP_SYS_ADMIN: "Note: this capability is overloaded; see Notes to kernel developers, below." For backward compatibility reasons access to system performance monitoring and observability subsystems of the kernel remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN capability usage for secure system performance monitoring and observability operations is discouraged with respect to the designed CAP_PERFMON capability.
Although the software running under CAP_PERFMON can not ensure avoidance of related hardware issues, the software can still mitigate these issues following the official hardware issues mitigation procedure [2]. The bugs in the software itself can be fixed following the standard kernel development process [3] to maintain and harden security of system performance monitoring and observability operations.
[1] http://man7.org/linux/man-pages/man7/capabilities.7.html
[2] https://www.kernel.org/doc/html/latest/process/embargoed-hardware-issues.html
[3] https://www.kernel.org/doc/html/latest/admin-guide/security-bugs.html
--- include/linux/capability.h | 4 ++++ include/uapi/linux/capability.h | 8 +++++++- security/selinux/include/classmap.h | 4 ++-- 3 files changed, 13 insertions(+), 3 deletions(-)
include/linux/capability.h +4 -0
@@ -251,6 +251,10 @@ extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const structextern bool capable_wrt_inode_uidgid (const struct inode *inode,int cap);extern bool file_ns_capable (const struct file *file,struct user_namespace *ns,int cap);extern bool ptracer_capable (struct task_struct *tsk,struct user_namespace *ns); +static inline bool perfmon_capable (void ) +{ +return capable (CAP_PERFMON ) ||capable (CAP_SYS_ADMIN ); +}/* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk (const struct dentry *dentry,struct cpu_vfs_cap_data *cpu_caps);
include/uapi/linux/capability.h +7 -1
@@ -367,8 +367,14 @@ struct vfs_ns_cap_data {#define CAP_AUDIT_READ 37 +/* +* Allow system performance and observability privileged operations +* using perf_events, i915_perf and other kernel subsystems +*/ + +#define CAP_PERFMON 38 -#define CAP_LAST_CAP CAP_AUDIT_READ +#define CAP_LAST_CAP CAP_PERFMON#define cap_valid (x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
security/selinux/include/classmap.h +2 -2
@@ -27,9 +27,9 @@ "audit_control", "setfcap"#define COMMON_CAP2_PERMS "mac_override", "mac_admin", "syslog", \ - "wake_alarm", "block_suspend", "audit_read" + "wake_alarm", "block_suspend", "audit_read", "perfmon" -#if CAP_LAST_CAP >CAP_AUDIT_READ +#if CAP_LAST_CAP >CAP_PERFMON #error New capability defined, please update COMMON_CAP2_PERMS.#endif
PATCH v8 2/12 perf/core: open access to the core for CAP_PERFMON privileged process
In reply to Alexey BudankovOpen access to monitoring of kernel code, cpus, tracepoints and namespaces data for a CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
CAP_PERFMON implements the principal of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to perf_events subsystem remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure perf_events monitoring is discouraged with respect to CAP_PERFMON capability.
--- include/linux/perf_event.h | 6 +++--- kernel/events/core.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-)
include/linux/perf_event.h +3 -3
@@ -1304,7 +1304,7 @@ static inline int perf_is_paranoid(void)static inline int perf_allow_kernel (struct perf_event_attr *attr) { -if (sysctl_perf_event_paranoid >1 && !capable (CAP_SYS_ADMIN )) +if (sysctl_perf_event_paranoid >1 && !perfmon_capable ())return -EACCES ;return security_perf_event_open (attr,PERF_SECURITY_KERNEL );
@@ -1312,7 +1312,7 @@ static inline int perf_allow_kernel(struct perf_event_attr *attr)static inline int perf_allow_cpu (struct perf_event_attr *attr) { -if (sysctl_perf_event_paranoid >0 && !capable (CAP_SYS_ADMIN )) +if (sysctl_perf_event_paranoid >0 && !perfmon_capable ())return -EACCES ;return security_perf_event_open (attr,PERF_SECURITY_CPU );
@@ -1320,7 +1320,7 @@ static inline int perf_allow_cpu(struct perf_event_attr *attr)static inline int perf_allow_tracepoint (struct perf_event_attr *attr) { -if (sysctl_perf_event_paranoid >-1 && !capable (CAP_SYS_ADMIN )) +if (sysctl_perf_event_paranoid >-1 && !perfmon_capable ())return -EPERM ;return security_perf_event_open (attr,PERF_SECURITY_TRACEPOINT );
kernel/events/core.c +1 -1
@@ -11360,7 +11360,7 @@ SYSCALL_DEFINE5(perf_event_open, }if (attr.namespaces) { -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EACCES ; }
Signature · 1 line
2.24.1
[tip: perf/core] perf/core: Open access to the core for CAP_PERFMON privileged process
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 18aa18566218d4a46d940049b835314d2b071cc2 Gitweb: https://git.kernel.org/tip/18aa18566218d4a46d940049b835314d2b071cc2 Author: Alexey Budankov <[email protected]> AuthorDate: Thu, 02 Apr 2020 11:46:24 +03:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Thu, 16 Apr 2020 12:19:08 -03:00
perf/core: Open access to the core for CAP_PERFMON privileged process
Open access to monitoring of kernel code, CPUs, tracepoints and namespaces data for a CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons the access to perf_events subsystem remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure perf_events monitoring is discouraged with respect to CAP_PERFMON capability.
--- include/linux/perf_event.h | 6 +++--- kernel/events/core.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-)
include/linux/perf_event.h +3 -3
@@ -1305,7 +1305,7 @@ static inline int perf_is_paranoid(void)static inline int perf_allow_kernel (struct perf_event_attr *attr) { -if (sysctl_perf_event_paranoid >1 && !capable (CAP_SYS_ADMIN )) +if (sysctl_perf_event_paranoid >1 && !perfmon_capable ())return -EACCES ;return security_perf_event_open (attr,PERF_SECURITY_KERNEL );
@@ -1313,7 +1313,7 @@ static inline int perf_allow_kernel(struct perf_event_attr *attr)static inline int perf_allow_cpu (struct perf_event_attr *attr) { -if (sysctl_perf_event_paranoid >0 && !capable (CAP_SYS_ADMIN )) +if (sysctl_perf_event_paranoid >0 && !perfmon_capable ())return -EACCES ;return security_perf_event_open (attr,PERF_SECURITY_CPU );
@@ -1321,7 +1321,7 @@ static inline int perf_allow_cpu(struct perf_event_attr *attr)static inline int perf_allow_tracepoint (struct perf_event_attr *attr) { -if (sysctl_perf_event_paranoid >-1 && !capable (CAP_SYS_ADMIN )) +if (sysctl_perf_event_paranoid >-1 && !perfmon_capable ())return -EPERM ;return security_perf_event_open (attr,PERF_SECURITY_TRACEPOINT );
kernel/events/core.c +1 -1
@@ -11504,7 +11504,7 @@ SYSCALL_DEFINE5(perf_event_open, }if (attr.namespaces) { -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EACCES ; }
PATCH v8 3/12 perf/core: open access to probes for CAP_PERFMON privileged process
In reply to Alexey BudankovOpen access to monitoring via kprobes and uprobes and eBPF tracing for CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
perf kprobes and uprobes are used by ftrace and eBPF. perf probe uses ftrace to define new kprobe events, and those events are treated as tracepoint events. eBPF defines new probes via perf_event_open interface and then the probes are used in eBPF tracing.
CAP_PERFMON implements the principal of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to perf_events subsystem remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure perf_events monitoring is discouraged with respect to CAP_PERFMON capability.
--- kernel/events/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
kernel/events/core.c +2 -2
@@ -9259,7 +9259,7 @@ static int perf_kprobe_event_init(struct perf_event *event)if (event->attr.type != perf_kprobe.type)return -ENOENT ; -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EACCES ;/*
@@ -9319,7 +9319,7 @@ static int perf_uprobe_event_init(struct perf_event *event)if (event->attr.type != perf_uprobe.type)return -ENOENT ; -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EACCES ;/*
Signature · 7 lines
2.24.1 _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
[tip: perf/core] perf/core: open access to probes for CAP_PERFMON privileged process
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: c9e0924e5c2b59365f9c0d43ff8722e79ecf4088 Gitweb: https://git.kernel.org/tip/c9e0924e5c2b59365f9c0d43ff8722e79ecf4088 Author: Alexey Budankov <[email protected]> AuthorDate: Thu, 02 Apr 2020 11:47:01 +03:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Thu, 16 Apr 2020 12:19:08 -03:00
perf/core: open access to probes for CAP_PERFMON privileged process
Open access to monitoring via kprobes and uprobes and eBPF tracing for CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
perf kprobes and uprobes are used by ftrace and eBPF. perf probe uses ftrace to define new kprobe events, and those events are treated as tracepoint events. eBPF defines new probes via perf_event_open interface and then the probes are used in eBPF tracing.
CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to perf_events subsystem remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure perf_events monitoring is discouraged with respect to CAP_PERFMON capability.
--- kernel/events/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
kernel/events/core.c +2 -2
@@ -9397,7 +9397,7 @@ static int perf_kprobe_event_init(struct perf_event *event)if (event->attr.type != perf_kprobe.type)return -ENOENT ; -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EACCES ;/*
@@ -9457,7 +9457,7 @@ static int perf_uprobe_event_init(struct perf_event *event)if (event->attr.type != perf_uprobe.type)return -ENOENT ; -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EACCES ;/*
PATCH v8 4/12 perf tool: extend Perf tool with CAP_PERFMON capability support
In reply to Alexey BudankovExtend error messages to mention CAP_PERFMON capability as an option to substitute CAP_SYS_ADMIN capability for secure system performance monitoring and observability operations. Make perf_event_paranoid_check() and __cmd_ftrace() to be aware of CAP_PERFMON capability.
CAP_PERFMON implements the principal of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to perf_events subsystem remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure perf_events monitoring is discouraged with respect to CAP_PERFMON capability.
--- tools/perf/builtin-ftrace.c | 5 +++-- tools/perf/design.txt | 3 ++- tools/perf/util/cap.h | 4 ++++ tools/perf/util/evsel.c | 10 +++++----- tools/perf/util/util.c | 1 + 5 files changed, 15 insertions(+), 8 deletions(-)
tools/perf/builtin-ftrace.c +3 -2
@@ -284,10 +284,11 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) .events = POLLIN, }; - if (!perf_cap__capable(CAP_SYS_ADMIN)) { + if (!(perf_cap__capable(CAP_PERFMON) || + perf_cap__capable(CAP_SYS_ADMIN))) { pr_err("ftrace only works for %s!\n", #ifdef HAVE_LIBCAP_SUPPORT - "users with the SYS_ADMIN capability" + "users with the CAP_PERFMON or CAP_SYS_ADMIN capability" #else "root" #endif
tools/perf/design.txt +2 -1
@@ -258,7 +258,8 @@ gets schedule to. Per task counters can be created by any user, for their own tasks. A 'pid == -1' and 'cpu == x' counter is a per CPU counter that counts -all events on CPU-x. Per CPU counters need CAP_SYS_ADMIN privilege. +all events on CPU-x. Per CPU counters need CAP_PERFMON or CAP_SYS_ADMIN +privilege. The 'flags' parameter is currently unused and must be zero.
tools/perf/util/cap.h +4 -0
@@ -29,4 +29,8 @@ static inline bool perf_cap__capable(int cap __maybe_unused)#define CAP_SYSLOG 34#endif +#ifndef CAP_PERFMON +#define CAP_PERFMON 38 +#endif +#endif /* __PERF_CAP_H */
tools/perf/util/evsel.c +5 -5
@@ -2507,14 +2507,14 @@ int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,"You may not have permission to collect %sstats.\n\n" "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n" "which controls use of the performance events system by\n" -"unprivileged users (without CAP_SYS_ADMIN).\n\n" +"unprivileged users (without CAP_PERFMON or CAP_SYS_ADMIN).\n\n" "The current value is %d:\n\n" " -1: Allow use of (almost) all events by all users\n" " Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK\n" -">= 0: Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN\n" -" Disallow raw tracepoint access by users without CAP_SYS_ADMIN\n" -">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n" -">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n" +">= 0: Disallow ftrace function tracepoint by users without CAP_PERFMON or CAP_SYS_ADMIN\n" +" Disallow raw tracepoint access by users without CAP_SYS_PERFMON or CAP_SYS_ADMIN\n" +">= 1: Disallow CPU event access by users without CAP_PERFMON or CAP_SYS_ADMIN\n" +">= 2: Disallow kernel profiling by users without CAP_PERFMON or CAP_SYS_ADMIN\n\n" "To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n" " kernel.perf_event_paranoid = -1\n" , target->system_wide ? "system-wide " : "",
tools/perf/util/util.c +1 -0
@@ -290,6 +290,7 @@ int perf_event_paranoid(void)bool perf_event_paranoid_check (int max_level) {return perf_cap__capable (CAP_SYS_ADMIN ) || +perf_cap__capable (CAP_PERFMON ) ||perf_event_paranoid () <= max_level; }
Signature · 1 line
2.24.1
Re: [PATCH v8 04/12] perf tool: extend Perf tool with CAP_PERFMON capability support
Quoted 13 lines · Alexey Budankov
Extend error messages to mention
CAP_PERFMONcapability as an option to substituteCAP_SYS_ADMINcapability for secure system performance monitoring and observability operations. Makeperf_event_paranoid_check()and__cmd_ftrace()to be aware ofCAP_PERFMONcapability.
CAP_PERFMONimplements the principal of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
Quoted 7 lines
For backward compatibility reasons access to
perf_eventssubsystem remains open forCAP_SYS_ADMINprivileged processes butCAP_SYS_ADMINusage for secureperf_eventsmonitoring is discouraged with respect toCAP_PERFMONcapability.Signed-off-by Alexey Budankov <[email protected]>Reviewed-by James Morris <[email protected]>
thanks,
jirka
Quoted 92 lines
--- tools/perf/builtin-ftrace.c | 5 +++-- tools/perf/design.txt | 3 ++- tools/perf/util/cap.h | 4 ++++ tools/perf/util/evsel.c | 10 +++++----- tools/perf/util/util.c | 1 + 5 files changed, 15 insertions(+), 8 deletions(-)tools/perf/builtin-ftrace.c +3
-2@@ -284,10 +284,11 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) .events = POLLIN, }; - if (!perf_cap__capable(CAP_SYS_ADMIN)) { + if (!(perf_cap__capable(CAP_PERFMON) || + perf_cap__capable(CAP_SYS_ADMIN))) { pr_err("ftrace only works for %s!\n", #ifdef HAVE_LIBCAP_SUPPORT - "users with the SYS_ADMIN capability" + "users with the CAP_PERFMON or CAP_SYS_ADMIN capability" #else "root" #endiftools/perf/design.txt +2
-1@@ -258,7 +258,8 @@ gets schedule to. Per task counters can be created by any user, for their own tasks. A 'pid == -1' and 'cpu == x' counter is a per CPU counter that counts -all events on CPU-x. Per CPU counters need CAP_SYS_ADMIN privilege. +all events on CPU-x. Per CPU counters need CAP_PERFMON or CAP_SYS_ADMIN +privilege. The 'flags' parameter is currently unused and must be zero.tools/perf/util/cap.h +4
-0@@ -29,4 +29,8 @@ static inline bool perf_cap__capable(int cap __maybe_unused)#define CAP_SYSLOG 34#endif +#ifndef CAP_PERFMON +#define CAP_PERFMON 38 +#endif +#endif /* __PERF_CAP_H */ tools/perf/util/evsel.c +5
-5@@ -2507,14 +2507,14 @@ int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,"You may not have permission to collect %sstats.\n\n" "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n" "which controls use of the performance events system by\n" -"unprivileged users (without CAP_SYS_ADMIN).\n\n" +"unprivileged users (without CAP_PERFMON or CAP_SYS_ADMIN).\n\n" "The current value is %d:\n\n" " -1: Allow use of (almost) all events by all users\n" " Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK\n" -">= 0: Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN\n" -" Disallow raw tracepoint access by users without CAP_SYS_ADMIN\n" -">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n" -">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n" +">= 0: Disallow ftrace function tracepoint by users without CAP_PERFMON or CAP_SYS_ADMIN\n" +" Disallow raw tracepoint access by users without CAP_SYS_PERFMON or CAP_SYS_ADMIN\n" +">= 1: Disallow CPU event access by users without CAP_PERFMON or CAP_SYS_ADMIN\n" +">= 2: Disallow kernel profiling by users without CAP_PERFMON or CAP_SYS_ADMIN\n\n" "To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n" " kernel.perf_event_paranoid = -1\n" , target->system_wide ? "system-wide " : "",tools/perf/util/util.c +1
-0@@ -290,6 +290,7 @@ int perf_event_paranoid(void)bool perf_event_paranoid_check (int max_level) {return perf_cap__capable (CAP_SYS_ADMIN ) || +perf_cap__capable (CAP_PERFMON ) ||perf_event_paranoid () <= max_level; }Signature · 1 line
2.24.1
Re: [PATCH v8 04/12] perf tool: extend Perf tool with CAP_PERFMON capability support
Quoted 19 lines · Jiri Olsa
Quoted 18 lines · Alexey Budankov
Extend error messages to mention
CAP_PERFMONcapability as an option to substituteCAP_SYS_ADMINcapability for secure system performance monitoring and observability operations. Makeperf_event_paranoid_check()and__cmd_ftrace()to be aware ofCAP_PERFMONcapability.
CAP_PERFMONimplements the principal of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)For backward compatibility reasons access to
perf_eventssubsystem remains open forCAP_SYS_ADMINprivileged processes butCAP_SYS_ADMINusage for secureperf_eventsmonitoring is discouraged with respect toCAP_PERFMONcapability.
Quoted 4 lines
Quoted 2 lines
Signed-off-by Alexey Budankov <[email protected]>Reviewed-by James Morris <[email protected]>Acked-by Jiri Olsa <[email protected]>
Thanks! I appreciate you support.
~Alexey
Quoted 93 lines
thanks,
jirkaQuoted 89 lines
--- tools/perf/builtin-ftrace.c | 5 +++-- tools/perf/design.txt | 3 ++- tools/perf/util/cap.h | 4 ++++ tools/perf/util/evsel.c | 10 +++++----- tools/perf/util/util.c | 1 + 5 files changed, 15 insertions(+), 8 deletions(-)tools/perf/builtin-ftrace.c +3
-2@@ -284,10 +284,11 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) .events = POLLIN, }; - if (!perf_cap__capable(CAP_SYS_ADMIN)) { + if (!(perf_cap__capable(CAP_PERFMON) || + perf_cap__capable(CAP_SYS_ADMIN))) { pr_err("ftrace only works for %s!\n", #ifdef HAVE_LIBCAP_SUPPORT - "users with the SYS_ADMIN capability" + "users with the CAP_PERFMON or CAP_SYS_ADMIN capability" #else "root" #endiftools/perf/design.txt +2
-1@@ -258,7 +258,8 @@ gets schedule to. Per task counters can be created by any user, for their own tasks. A 'pid == -1' and 'cpu == x' counter is a per CPU counter that counts -all events on CPU-x. Per CPU counters need CAP_SYS_ADMIN privilege. +all events on CPU-x. Per CPU counters need CAP_PERFMON or CAP_SYS_ADMIN +privilege. The 'flags' parameter is currently unused and must be zero.tools/perf/util/cap.h +4
-0@@ -29,4 +29,8 @@ static inline bool perf_cap__capable(int cap __maybe_unused)#define CAP_SYSLOG 34#endif +#ifndef CAP_PERFMON +#define CAP_PERFMON 38 +#endif +#endif /* __PERF_CAP_H */ tools/perf/util/evsel.c +5
-5@@ -2507,14 +2507,14 @@ int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,"You may not have permission to collect %sstats.\n\n" "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n" "which controls use of the performance events system by\n" -"unprivileged users (without CAP_SYS_ADMIN).\n\n" +"unprivileged users (without CAP_PERFMON or CAP_SYS_ADMIN).\n\n" "The current value is %d:\n\n" " -1: Allow use of (almost) all events by all users\n" " Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK\n" -">= 0: Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN\n" -" Disallow raw tracepoint access by users without CAP_SYS_ADMIN\n" -">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n" -">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n" +">= 0: Disallow ftrace function tracepoint by users without CAP_PERFMON or CAP_SYS_ADMIN\n" +" Disallow raw tracepoint access by users without CAP_SYS_PERFMON or CAP_SYS_ADMIN\n" +">= 1: Disallow CPU event access by users without CAP_PERFMON or CAP_SYS_ADMIN\n" +">= 2: Disallow kernel profiling by users without CAP_PERFMON or CAP_SYS_ADMIN\n\n" "To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n" " kernel.perf_event_paranoid = -1\n" , target->system_wide ? "system-wide " : "",tools/perf/util/util.c +1
-0@@ -290,6 +290,7 @@ int perf_event_paranoid(void)bool perf_event_paranoid_check (int max_level) {return perf_cap__capable (CAP_SYS_ADMIN ) || +perf_cap__capable (CAP_PERFMON ) ||perf_event_paranoid () <= max_level; }
Quoted 4 lines
Quoted 3 lines
Signature · 1 line
2.24.1
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [PATCH v8 04/12] perf tool: extend Perf tool with CAP_PERFMON capability support
In reply to Alexey BudankovHello,
Quoted 14 lines · Alexey Budankov
Extend error messages to mention
CAP_PERFMONcapability as an option to substituteCAP_SYS_ADMINcapability for secure system performance monitoring and observability operations. Makeperf_event_paranoid_check()and__cmd_ftrace()to be aware ofCAP_PERFMONcapability.
CAP_PERFMONimplements the principal of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
Quoted 7 lines
For backward compatibility reasons access to
perf_eventssubsystem remains open forCAP_SYS_ADMINprivileged processes butCAP_SYS_ADMINusage for secureperf_eventsmonitoring is discouraged with respect toCAP_PERFMONcapability.Signed-off-by Alexey Budankov <[email protected]>Reviewed-by James Morris <[email protected]>
Thanks
Namhyung
Re: [PATCH v8 04/12] perf tool: extend Perf tool with CAP_PERFMON capability support
Hi Namhyung,
Quoted 23 lines · Namhyung Kim
Hello,
Quoted 19 lines · Alexey Budankov
Extend error messages to mention
CAP_PERFMONcapability as an option to substituteCAP_SYS_ADMINcapability for secure system performance monitoring and observability operations. Makeperf_event_paranoid_check()and__cmd_ftrace()to be aware ofCAP_PERFMONcapability.
CAP_PERFMONimplements the principal of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)For backward compatibility reasons access to
perf_eventssubsystem remains open forCAP_SYS_ADMINprivileged processes butCAP_SYS_ADMINusage for secureperf_eventsmonitoring is discouraged with respect toCAP_PERFMONcapability.
Quoted 4 lines
Quoted 2 lines
Signed-off-by Alexey Budankov <[email protected]>Reviewed-by James Morris <[email protected]>Acked-by Namhyung Kim <[email protected]>
Thanks! I appreciate you involvement and effort.
~Alexey
Quoted 4 lines
Thanks
Namhyung
[tip: perf/core] perf tools: Support CAP_PERFMON capability
In reply to Alexey BudankovThe following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 6b3e0e2e04615df128b2d38fa1dd1fcb84f2504c Gitweb: https://git.kernel.org/tip/6b3e0e2e04615df128b2d38fa1dd1fcb84f2504c Author: Alexey Budankov <[email protected]> AuthorDate: Thu, 02 Apr 2020 11:47:35 +03:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Thu, 16 Apr 2020 12:19:08 -03:00
perf tools: Support CAP_PERFMON capability
Extend error messages to mention CAP_PERFMON capability as an option to substitute CAP_SYS_ADMIN capability for secure system performance monitoring and observability operations. Make perf_event_paranoid_check() and __cmd_ftrace() to be aware of CAP_PERFMON capability.
CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to perf_events subsystem remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure perf_events monitoring is discouraged with respect to CAP_PERFMON capability.
Committer testing:
Using a libcap with this patch:
diff --git a/libcap/include/uapi/linux/capability.h b/libcap/include/uapi/linux/capability.h
index 78b2fd4c8a95..89b5b0279b60 100644
--- a/libcap/include/uapi/linux/capability.h
+++ b/libcap/include/uapi/linux/capability.h
@@ -366,8 +366,9 @@ struct vfs_ns_cap_data {#define CAP_AUDIT_READ 37
+#define CAP_PERFMON 38
-#define CAP_LAST_CAP CAP_AUDIT_READ
+#define CAP_LAST_CAP CAP_PERFMON
#define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
Note that using '38' in place of 'cap_perfmon' works to some degree with an old libcap, its only when cap_get_flag() is called that libcap performs an error check based on the maximum value known for capabilities that it will fail.
This makes determining the default of perf_event_attr.exclude_kernel to fail, as it can't determine if CAP_PERFMON is in place.
Using 'perf top -e cycles' avoids the default check and sets perf_event_attr.exclude_kernel to 1.
As root, with a libcap supporting CAP_PERFMON:
# groupadd perf_users # adduser perf -g perf_users # mkdir ~perf/bin # cp ~acme/bin/perf ~perf/bin/ # chgrp perf_users ~perf/bin/perf # setcap "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" ~perf/bin/perf # getcap ~perf/bin/perf /home/perf/bin/perf = cap_sys_ptrace,cap_syslog,cap_perfmon+ep # ls -la ~perf/bin/perf -rwxr-xr-x. 1 root perf_users 16968552 Apr 9 13:10 /home/perf/bin/perf
As the 'perf' user in the 'perf_users' group:
$ perf top -a --stdio Error: Failed to mmap with 1 (Operation not permitted) $
Either add the cap_ipc_lock capability to the perf binary or reduce the ring buffer size to some smaller value:
$ perf top -m10 -a --stdio rounding mmap pages size to 64K (16 pages) Error: Failed to mmap with 1 (Operation not permitted) $ perf top -m4 -a --stdio Error: Failed to mmap with 1 (Operation not permitted) $ perf top -m2 -a --stdio PerfTop: 762 irqs/sec kernel:49.7% exact: 100.0% lost: 0/0 drop: 0/0 [4000Hz cycles], (all, 4 CPUs) ------------------------------------------------------------------------------------------------------
9.83% perf [.] __symbols__insert
8.58% perf [.] rb_next
5.91% [kernel] [k] module_get_kallsym
5.66% [kernel] [k] kallsyms_expand_symbol.constprop.0
3.98% libc-2.29.so [.] __GI_____strtoull_l_internal
3.66% perf [.] rb_insert_color
2.34% [kernel] [k] vsnprintf
2.30% [kernel] [k] string_nocheck
2.16% libc-2.29.so [.] _IO_getdelim
2.15% [kernel] [k] number
2.13% [kernel] [k] format_decode
1.58% libc-2.29.so [.] _IO_feof
1.52% libc-2.29.so [.] __strcmp_avx2
1.50% perf [.] rb_set_parent_color
1.47% libc-2.29.so [.] __libc_calloc
1.24% [kernel] [k] do_syscall_64
1.17% [kernel] [k] __x86_indirect_thunk_rax $ perf record -a sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.552 MB perf.data (74 samples) ]
$ perf evlist
cycles
$ perf evlist -v
cycles: size: 120, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 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 | head -20
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 74 of event 'cycles'
# Event count (approx.): 15694834
#
# Overhead Command Shared Object Symbol
# ........ ............... .......................... ......................................
#
19.62% perf [kernel.vmlinux] [k] strnlen_user
13.88% swapper [kernel.vmlinux] [k] intel_idle
13.83% ksoftirqd/0 [kernel.vmlinux] [k] pfifo_fast_dequeue
13.51% swapper [kernel.vmlinux] [k] kmem_cache_free
6.31% gnome-shell [kernel.vmlinux] [k] kmem_cache_free
5.66% kworker/u8:3+ix [kernel.vmlinux] [k] delay_tsc
4.42% perf [kernel.vmlinux] [k] __set_cpus_allowed_ptr
3.45% kworker/2:1-eve [kernel.vmlinux] [k] shmem_truncate_range
2.29% gnome-shell libgobject-2.0.so.0.6000.7 [.] g_closure_ref
$--- tools/perf/builtin-ftrace.c | 5 +++-- tools/perf/design.txt | 3 ++- tools/perf/util/cap.h | 4 ++++ tools/perf/util/evsel.c | 10 +++++----- tools/perf/util/util.c | 1 + 5 files changed, 15 insertions(+), 8 deletions(-)
tools/perf/builtin-ftrace.c +3 -2
@@ -284,10 +284,11 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) .events = POLLIN, }; - if (!perf_cap__capable(CAP_SYS_ADMIN)) { + if (!(perf_cap__capable(CAP_PERFMON) || + perf_cap__capable(CAP_SYS_ADMIN))) { pr_err("ftrace only works for %s!\n", #ifdef HAVE_LIBCAP_SUPPORT - "users with the SYS_ADMIN capability" + "users with the CAP_PERFMON or CAP_SYS_ADMIN capability" #else "root" #endif
tools/perf/design.txt +2 -1
@@ -258,7 +258,8 @@ gets schedule to. Per task counters can be created by any user, for their own tasks. A 'pid == -1' and 'cpu == x' counter is a per CPU counter that counts -all events on CPU-x. Per CPU counters need CAP_SYS_ADMIN privilege. +all events on CPU-x. Per CPU counters need CAP_PERFMON or CAP_SYS_ADMIN +privilege. The 'flags' parameter is currently unused and must be zero.
tools/perf/util/cap.h +4 -0
@@ -29,4 +29,8 @@ static inline bool perf_cap__capable(int cap __maybe_unused)#define CAP_SYSLOG 34#endif +#ifndef CAP_PERFMON +#define CAP_PERFMON 38 +#endif +#endif /* __PERF_CAP_H */
tools/perf/util/evsel.c +5 -5
@@ -2523,14 +2523,14 @@ int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,"You may not have permission to collect %sstats.\n\n" "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n" "which controls use of the performance events system by\n" -"unprivileged users (without CAP_SYS_ADMIN).\n\n" +"unprivileged users (without CAP_PERFMON or CAP_SYS_ADMIN).\n\n" "The current value is %d:\n\n" " -1: Allow use of (almost) all events by all users\n" " Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK\n" -">= 0: Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN\n" -" Disallow raw tracepoint access by users without CAP_SYS_ADMIN\n" -">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n" -">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n" +">= 0: Disallow ftrace function tracepoint by users without CAP_PERFMON or CAP_SYS_ADMIN\n" +" Disallow raw tracepoint access by users without CAP_SYS_PERFMON or CAP_SYS_ADMIN\n" +">= 1: Disallow CPU event access by users without CAP_PERFMON or CAP_SYS_ADMIN\n" +">= 2: Disallow kernel profiling by users without CAP_PERFMON or CAP_SYS_ADMIN\n\n" "To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n" " kernel.perf_event_paranoid = -1\n" , target->system_wide ? "system-wide " : "",
tools/perf/util/util.c +1 -0
@@ -290,6 +290,7 @@ int perf_event_paranoid(void)bool perf_event_paranoid_check (int max_level) {return perf_cap__capable (CAP_SYS_ADMIN ) || +perf_cap__capable (CAP_PERFMON ) ||perf_event_paranoid () <= max_level; }
PATCH v8 5/12 drm/i915/perf: open access for CAP_PERFMON privileged process
In reply to Alexey BudankovOpen access to i915_perf monitoring for CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
CAP_PERFMON implements the principal of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to i915_events subsystem remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure i915_events monitoring is discouraged with respect to CAP_PERFMON capability.
--- drivers/gpu/drm/i915/i915_perf.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/i915_perf.c +6 -7
@@ -3402,10 +3402,10 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,/* Similar to perf's kernel.perf_paranoid_cpu sysctl option * we check a dev.i915.perf_stream_paranoid sysctl option * to determine if it's ok to access system wide OA counters -* without CAP_SYS_ADMIN privileges. +* without CAP_PERFMON or CAP_SYS_ADMIN privileges. */ if (privileged_op && - i915_perf_stream_paranoid && !capable (CAP_SYS_ADMIN )) { + i915_perf_stream_paranoid && !perfmon_capable ()) {DRM_DEBUG ("Insufficient privileges to open i915 perf stream\n" ); ret = -EACCES ; goto err_ctx;
@@ -3598,9 +3598,8 @@ static int read_properties_unlocked(struct i915_perf *perf, }else oa_freq_hz =0 ; -if (oa_freq_hz > i915_oa_max_sample_rate && - !capable (CAP_SYS_ADMIN )) { -DRM_DEBUG ("OA exponent would exceed the max sampling frequency (sysctl dev.i915.oa_max_sample_rate) %uHz without root privileges\n" , +if (oa_freq_hz > i915_oa_max_sample_rate && !perfmon_capable ()) { +DRM_DEBUG ("OA exponent would exceed the max sampling frequency (sysctl dev.i915.oa_max_sample_rate) %uHz without CAP_PERFMON or CAP_SYS_ADMIN privileges\n" , i915_oa_max_sample_rate);return -EACCES ; }
@@ -4021,7 +4020,7 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,return -EINVAL ; } -if (i915_perf_stream_paranoid && !capable (CAP_SYS_ADMIN )) { +if (i915_perf_stream_paranoid && !perfmon_capable ()) {DRM_DEBUG ("Insufficient privileges to add i915 OA config\n" );return -EACCES ; }
@@ -4168,7 +4167,7 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,return -ENOTSUPP ; } -if (i915_perf_stream_paranoid && !capable (CAP_SYS_ADMIN )) { +if (i915_perf_stream_paranoid && !perfmon_capable ()) {DRM_DEBUG ("Insufficient privileges to remove i915 OA config\n" );return -EACCES ; }
Signature · 1 line
2.24.1
[tip: perf/core] drm/i915/perf: Open access for CAP_PERFMON privileged process
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 4e3d3456b78fa5a70e65de0d7c5309b814281ae3 Gitweb: https://git.kernel.org/tip/4e3d3456b78fa5a70e65de0d7c5309b814281ae3 Author: Alexey Budankov <[email protected]> AuthorDate: Thu, 02 Apr 2020 11:48:15 +03:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Thu, 16 Apr 2020 12:19:08 -03:00
drm/i915/perf: Open access for CAP_PERFMON privileged process
Open access to i915_perf monitoring for CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to i915_events subsystem remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure i915_events monitoring is discouraged with respect to CAP_PERFMON capability.
--- drivers/gpu/drm/i915/i915_perf.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/i915_perf.c +6 -7
@@ -3433,10 +3433,10 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,/* Similar to perf's kernel.perf_paranoid_cpu sysctl option * we check a dev.i915.perf_stream_paranoid sysctl option * to determine if it's ok to access system wide OA counters -* without CAP_SYS_ADMIN privileges. +* without CAP_PERFMON or CAP_SYS_ADMIN privileges. */ if (privileged_op && - i915_perf_stream_paranoid && !capable (CAP_SYS_ADMIN )) { + i915_perf_stream_paranoid && !perfmon_capable ()) {DRM_DEBUG ("Insufficient privileges to open i915 perf stream\n" ); ret = -EACCES ; goto err_ctx;
@@ -3629,9 +3629,8 @@ static int read_properties_unlocked(struct i915_perf *perf, }else oa_freq_hz =0 ; -if (oa_freq_hz > i915_oa_max_sample_rate && - !capable (CAP_SYS_ADMIN )) { -DRM_DEBUG ("OA exponent would exceed the max sampling frequency (sysctl dev.i915.oa_max_sample_rate) %uHz without root privileges\n" , +if (oa_freq_hz > i915_oa_max_sample_rate && !perfmon_capable ()) { +DRM_DEBUG ("OA exponent would exceed the max sampling frequency (sysctl dev.i915.oa_max_sample_rate) %uHz without CAP_PERFMON or CAP_SYS_ADMIN privileges\n" , i915_oa_max_sample_rate);return -EACCES ; }
@@ -4052,7 +4051,7 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,return -EINVAL ; } -if (i915_perf_stream_paranoid && !capable (CAP_SYS_ADMIN )) { +if (i915_perf_stream_paranoid && !perfmon_capable ()) {DRM_DEBUG ("Insufficient privileges to add i915 OA config\n" );return -EACCES ; }
@@ -4199,7 +4198,7 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,return -ENOTSUPP ; } -if (i915_perf_stream_paranoid && !capable (CAP_SYS_ADMIN )) { +if (i915_perf_stream_paranoid && !perfmon_capable ()) {DRM_DEBUG ("Insufficient privileges to remove i915 OA config\n" );return -EACCES ; }
PATCH v8 6/12 trace/bpf_trace: open access for CAP_PERFMON privileged process
In reply to Alexey BudankovOpen access to bpf_trace monitoring for CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
CAP_PERFMON implements the principal of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to bpf_trace monitoring remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure bpf_trace monitoring is discouraged with respect to CAP_PERFMON capability.
--- kernel/trace/bpf_trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/trace/bpf_trace.c +1 -1
@@ -1416,7 +1416,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)u32 *ids, prog_cnt, ids_len;int ret; -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EPERM ;if (event->attr.type !=PERF_TYPE_TRACEPOINT )return -EINVAL ;
Signature · 7 lines
2.24.1 _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
[tip: perf/core] trace/bpf_trace: Open access for CAP_PERFMON privileged process
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 031258da05956646c5606023ab0abe10a7e68ea1 Gitweb: https://git.kernel.org/tip/031258da05956646c5606023ab0abe10a7e68ea1 Author: Alexey Budankov <[email protected]> AuthorDate: Thu, 02 Apr 2020 11:48:54 +03:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Thu, 16 Apr 2020 12:19:08 -03:00
trace/bpf_trace: Open access for CAP_PERFMON privileged process
Open access to bpf_trace monitoring for CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to bpf_trace monitoring remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure bpf_trace monitoring is discouraged with respect to CAP_PERFMON capability.
--- kernel/trace/bpf_trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/trace/bpf_trace.c +1 -1
@@ -1468,7 +1468,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)u32 *ids, prog_cnt, ids_len;int ret; -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EPERM ;if (event->attr.type !=PERF_TYPE_TRACEPOINT )return -EINVAL ;
PATCH v8 7/12 powerpc/perf: open access for CAP_PERFMON privileged process
In reply to Alexey BudankovOpen access to monitoring for CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
CAP_PERFMON implements the principal of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to the monitoring remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure monitoring is discouraged with respect to CAP_PERFMON capability.
--- arch/powerpc/perf/imc-pmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
arch/powerpc/perf/imc-pmu.c +2 -2
@@ -898,7 +898,7 @@ static int thread_imc_event_init(struct perf_event *event)if (event->attr.type != event->pmu->type)return -ENOENT ; -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EACCES ;/* Sampling not supported */
@@ -1307,7 +1307,7 @@ static int trace_imc_event_init(struct perf_event *event)if (event->attr.type != event->pmu->type)return -ENOENT ; -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EACCES ;/* Return if this is a couting event */
Signature · 6 lines
2.24.1 _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
[tip: perf/core] powerpc/perf: open access for CAP_PERFMON privileged process
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: ff46758313e688fca7d762b3e6ead32843999511 Gitweb: https://git.kernel.org/tip/ff46758313e688fca7d762b3e6ead32843999511 Author: Alexey Budankov <[email protected]> AuthorDate: Thu, 02 Apr 2020 11:49:36 +03:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Thu, 16 Apr 2020 12:19:08 -03:00
powerpc/perf: open access for CAP_PERFMON privileged process
Open access to monitoring for CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to the monitoring remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure monitoring is discouraged with respect to CAP_PERFMON capability.
--- arch/powerpc/perf/imc-pmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
arch/powerpc/perf/imc-pmu.c +2 -2
@@ -976,7 +976,7 @@ static int thread_imc_event_init(struct perf_event *event)if (event->attr.type != event->pmu->type)return -ENOENT ; -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EACCES ;/* Sampling not supported */
@@ -1412,7 +1412,7 @@ static int trace_imc_event_init(struct perf_event *event)if (event->attr.type != event->pmu->type)return -ENOENT ; -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EACCES ;/* Return if this is a couting event */
PATCH v8 8/12 parisc/perf: open access for CAP_PERFMON privileged process
In reply to Alexey BudankovOpen access to monitoring for CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
CAP_PERFMON implements the principal of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to the monitoring remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure monitoring is discouraged with respect to CAP_PERFMON capability.
--- arch/parisc/kernel/perf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/parisc/kernel/perf.c +1 -1
@@ -300,7 +300,7 @@ static ssize_t perf_write(struct file *file, const char __user *buf,else return -EFAULT ; -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EACCES ;if (count !=sizeof (uint32_t ))
Signature · 1 line
2.24.1
[tip: perf/core] parisc/perf: open access for CAP_PERFMON privileged process
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: cf91baf3f7f39a0cd29072e21ed0e4bb1ab3b382 Gitweb: https://git.kernel.org/tip/cf91baf3f7f39a0cd29072e21ed0e4bb1ab3b382 Author: Alexey Budankov <[email protected]> AuthorDate: Thu, 02 Apr 2020 11:50:15 +03:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Thu, 16 Apr 2020 12:19:08 -03:00
parisc/perf: open access for CAP_PERFMON privileged process
Open access to monitoring for CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to the monitoring remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure monitoring is discouraged with respect to CAP_PERFMON capability.
--- arch/parisc/kernel/perf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/parisc/kernel/perf.c +1 -1
@@ -300,7 +300,7 @@ static ssize_t perf_write(struct file *file, const char __user *buf,else return -EFAULT ; -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EACCES ;if (count !=sizeof (uint32_t ))
PATCH v8 9/12 drivers/perf: open access for CAP_PERFMON privileged process
In reply to Alexey BudankovOpen access to monitoring for CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
CAP_PERFMON implements the principal of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to the monitoring remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure monitoring is discouraged with respect to CAP_PERFMON capability.
--- drivers/perf/arm_spe_pmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/perf/arm_spe_pmu.c +2 -2
@@ -274,7 +274,7 @@ static u64 arm_spe_event_to_pmscr(struct perf_event *event)if (!attr->exclude_kernel) reg |=BIT (SYS_PMSCR_EL1_E1SPE_SHIFT ); -if (IS_ENABLED (CONFIG_PID_IN_CONTEXTIDR ) &&capable (CAP_SYS_ADMIN )) +if (IS_ENABLED (CONFIG_PID_IN_CONTEXTIDR ) &&perfmon_capable ()) reg |=BIT (SYS_PMSCR_EL1_CX_SHIFT );return reg;
@@ -700,7 +700,7 @@ static int arm_spe_pmu_event_init(struct perf_event *event)return -EOPNOTSUPP ; reg =arm_spe_event_to_pmscr (event); -if (!capable (CAP_SYS_ADMIN ) && +if (!perfmon_capable () && (reg & (BIT (SYS_PMSCR_EL1_PA_SHIFT ) |BIT (SYS_PMSCR_EL1_CX_SHIFT ) |BIT (SYS_PMSCR_EL1_PCT_SHIFT ))))
Signature · 6 lines
2.24.1 _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
[tip: perf/core] drivers/perf: Open access for CAP_PERFMON privileged process
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: cea7d0d4a59b4efd0e1fe067130b4c06ab4d412f Gitweb: https://git.kernel.org/tip/cea7d0d4a59b4efd0e1fe067130b4c06ab4d412f Author: Alexey Budankov <[email protected]> AuthorDate: Thu, 02 Apr 2020 11:51:21 +03:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Thu, 16 Apr 2020 12:19:09 -03:00
drivers/perf: Open access for CAP_PERFMON privileged process
Open access to monitoring for CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to the monitoring remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure monitoring is discouraged with respect to CAP_PERFMON capability.
--- drivers/perf/arm_spe_pmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/perf/arm_spe_pmu.c +2 -2
@@ -274,7 +274,7 @@ static u64 arm_spe_event_to_pmscr(struct perf_event *event)if (!attr->exclude_kernel) reg |=BIT (SYS_PMSCR_EL1_E1SPE_SHIFT ); -if (IS_ENABLED (CONFIG_PID_IN_CONTEXTIDR ) &&capable (CAP_SYS_ADMIN )) +if (IS_ENABLED (CONFIG_PID_IN_CONTEXTIDR ) &&perfmon_capable ()) reg |=BIT (SYS_PMSCR_EL1_CX_SHIFT );return reg;
@@ -700,7 +700,7 @@ static int arm_spe_pmu_event_init(struct perf_event *event)return -EOPNOTSUPP ; reg =arm_spe_event_to_pmscr (event); -if (!capable (CAP_SYS_ADMIN ) && +if (!perfmon_capable () && (reg & (BIT (SYS_PMSCR_EL1_PA_SHIFT ) |BIT (SYS_PMSCR_EL1_CX_SHIFT ) |BIT (SYS_PMSCR_EL1_PCT_SHIFT ))))
PATCH v8 10/12 drivers/oprofile: open access for CAP_PERFMON privileged process
In reply to Alexey BudankovOpen access to monitoring for CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
CAP_PERFMON implements the principal of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to the monitoring remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure monitoring is discouraged with respect to CAP_PERFMON capability.
--- drivers/oprofile/event_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/oprofile/event_buffer.c +1 -1
@@ -113,7 +113,7 @@ static int event_buffer_open(struct inode *inode, struct file *file) {int err = -EPERM ; -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EPERM ;if (test_and_set_bit_lock (0 , &buffer_opened))
Signature · 6 lines
2.24.1 _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
[tip: perf/core] drivers/oprofile: Open access for CAP_PERFMON privileged process
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: ab76878bb720cbd35a05ae868387f4373a58c949 Gitweb: https://git.kernel.org/tip/ab76878bb720cbd35a05ae868387f4373a58c949 Author: Alexey Budankov <[email protected]> AuthorDate: Thu, 02 Apr 2020 11:53:07 +03:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Thu, 16 Apr 2020 12:19:09 -03:00
drivers/oprofile: Open access for CAP_PERFMON privileged process
Open access to monitoring for CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure.
CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required)
For backward compatibility reasons access to the monitoring remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure monitoring is discouraged with respect to CAP_PERFMON capability.
--- drivers/oprofile/event_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/oprofile/event_buffer.c +1 -1
@@ -113,7 +113,7 @@ static int event_buffer_open(struct inode *inode, struct file *file) {int err = -EPERM ; -if (!capable (CAP_SYS_ADMIN )) +if (!perfmon_capable ())return -EPERM ;if (test_and_set_bit_lock (0 , &buffer_opened))
PATCH v8 11/12 doc/admin-guide: update perf-security.rst with CAP_PERFMON information
In reply to Alexey BudankovUpdate perf-security.rst documentation file with the information related to usage of CAP_PERFMON capability to secure performance monitoring and observability operations in system.
--- Documentation/admin-guide/perf-security.rst | 65 +++++++++++++-------- 1 file changed, 40 insertions(+), 25 deletions(-)
Documentation/admin-guide/perf-security.rst +40 -25
@@ -1,6 +1,6 @@ .. _perf_security: -Perf Events and tool security +Perf events and tool security ============================= Overview
@@ -42,11 +42,11 @@ categories: Data that belong to the fourth category can potentially contain sensitive process data. If PMUs in some monitoring modes capture values of execution context registers or data from process memory then access -to such monitoring capabilities requires to be ordered and secured -properly. So, perf_events/Perf performance monitoring is the subject for -security access control management [5]_ . +to such monitoring modes requires to be ordered and secured properly. +So, perf_events performance monitoring and observability operations is +the subject for security access control management [5]_ . -perf_events/Perf access control +perf_events access control ------------------------------- To perform security checks, the Linux implementation splits processes
@@ -66,11 +66,25 @@ into distinct units, known as capabilities [6]_ , which can be independently enabled and disabled on per-thread basis for processes and files of unprivileged users. -Unprivileged processes with enabled CAP_SYS_ADMIN capability are treated +Unprivileged processes with enabled CAP_PERFMON capability are treated as privileged processes with respect to perf_events performance -monitoring and bypass *scope* permissions checks in the kernel. - -Unprivileged processes using perf_events system call API is also subject +monitoring and observability operations, thus, bypass *scope* permissions +checks in the kernel. CAP_PERFMON implements the principal of least +privilege [13]_ (POSIX 1003.1e: 2.2.2.39) for performance monitoring and +observability operations in the kernel and provides secure approach to +perfomance monitoring and observability in the system. + +For backward compatibility reasons access to perf_events monitoring and +observability operations is also open for CAP_SYS_ADMIN privileged +processes but CAP_SYS_ADMIN usage for secure monitoring and observability +use cases is discouraged with respect to CAP_PERFMON capability. +If system audit records [14]_ for a process using perf_events system call +API contain denial records of acquiring both CAP_PERFMON and CAP_SYS_ADMIN +capabilities then providing the process with CAP_PERFMON capability singly +is recommended as the preferred secure approach to resolve double access +denial logging related to usage of performance monitoring and observability. + +Unprivileged processes using perf_events system call are also subject for PTRACE_MODE_READ_REALCREDS ptrace access mode check [7]_ , whose outcome determines whether monitoring is permitted. So unprivileged processes provided with CAP_SYS_PTRACE capability are effectively
@@ -82,14 +96,14 @@ performance analysis of monitored processes or a system. For example, CAP_SYSLOG capability permits reading kernel space memory addresses from /proc/kallsyms file. -perf_events/Perf privileged users +Privileged Perf users groups --------------------------------- Mechanisms of capabilities, privileged capability-dumb files [6]_ and -file system ACLs [10]_ can be used to create a dedicated group of -perf_events/Perf privileged users who are permitted to execute -performance monitoring without scope limits. The following steps can be -taken to create such a group of privileged Perf users. +file system ACLs [10]_ can be used to create dedicated groups of +privileged Perf users who are permitted to execute performance monitoring +and observability without scope limits. The following steps can be +taken to create such groups of privileged Perf users. 1. Create perf_users group of privileged Perf users, assign perf_users group to Perf tool executable and limit access to the executable for
@@ -108,30 +122,30 @@ taken to create such a group of privileged Perf users. -rwxr-x--- 2 root perf_users 11M Oct 19 15:12 perf 2. Assign the required capabilities to the Perf tool executable file and - enable members of perf_users group with performance monitoring + enable members of perf_users group with monitoring and observability privileges [6]_ : :: - # setcap "cap_sys_admin,cap_sys_ptrace,cap_syslog=ep" perf - # setcap -v "cap_sys_admin,cap_sys_ptrace,cap_syslog=ep" perf + # setcap "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" perf + # setcap -v "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" perf perf: OK # getcap perf - perf = cap_sys_ptrace,cap_sys_admin,cap_syslog+ep + perf = cap_sys_ptrace,cap_syslog,cap_perfmon+ep As a result, members of perf_users group are capable of conducting -performance monitoring by using functionality of the configured Perf -tool executable that, when executes, passes perf_events subsystem scope -checks. +performance monitoring and observability by using functionality of the +configured Perf tool executable that, when executes, passes perf_events +subsystem scope checks. This specific access control management is only available to superuser or root running processes with CAP_SETPCAP, CAP_SETFCAP [6]_ capabilities. -perf_events/Perf unprivileged users +Unprivileged users ----------------------------------- -perf_events/Perf *scope* and *access* control for unprivileged processes +perf_events *scope* and *access* control for unprivileged processes is governed by perf_event_paranoid [2]_ setting: -1:
@@ -166,7 +180,7 @@ is governed by perf_event_paranoid [2]_ setting: perf_event_mlock_kb locking limit is imposed but ignored for unprivileged processes with CAP_IPC_LOCK capability. -perf_events/Perf resource control +Resource control --------------------------------- Open file descriptors
@@ -227,4 +241,5 @@ Bibliography .. [10] `<http://man7.org/linux/man-pages/man5/acl.5.html>`_ .. [11] `<http://man7.org/linux/man-pages/man2/getrlimit.2.html>`_ .. [12] `<http://man7.org/linux/man-pages/man5/limits.conf.5.html>`_ - +.. [13] `<https://sites.google.com/site/fullycapable>`_ +.. [14] `<http://man7.org/linux/man-pages/man8/auditd.8.html>`_
Signature · 7 lines
2.24.1 _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
[tip: perf/core] doc/admin-guide: Update perf-security.rst with CAP_PERFMON information
The following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 902a8dcc5ba6c5dc3332e8806b01be2f0f7ef2e4 Gitweb: https://git.kernel.org/tip/902a8dcc5ba6c5dc3332e8806b01be2f0f7ef2e4 Author: Alexey Budankov <[email protected]> AuthorDate: Thu, 02 Apr 2020 11:54:01 +03:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Thu, 16 Apr 2020 12:19:10 -03:00
doc/admin-guide: Update perf-security.rst with CAP_PERFMON information
Update perf-security.rst documentation file with the information related to usage of CAP_PERFMON capability to secure performance monitoring and observability operations in system.
Committer notes:
While testing 'perf top' under cap_perfmon I noticed that it needs some more capability and Alexey pointed out cap_ipc_lock, as needed by this kernel chunk:
kernel/events/core.c: 6101
if ((locked > lock_limit) && perf_is_paranoid() &&
!capable(CAP_IPC_LOCK)) {
ret = -EPERM;
goto unlock;
}So I added it to the documentation, and also mentioned that if the libcap version doesn't yet supports 'cap_perfmon', its numeric value can be used instead, i.e. if:
# setcap "cap_perfmon,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf
Fails, try:
# setcap "38,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf
I also added a paragraph stating that using an unpatched libcap will fail the check for CAP_PERFMON, as it checks the cap number against a maximum to see if it is valid, which makes it use as the default the 'cycles:u' event, even tho a cap_perfmon capable perf binary can get kernel samples, to workaround that just use, e.g.:
# perf top -e cycles # perf record -e cycles
And it will sample kernel and user modes.
--- Documentation/admin-guide/perf-security.rst | 86 ++++++++++++++------ 1 file changed, 61 insertions(+), 25 deletions(-)
Documentation/admin-guide/perf-security.rst +61 -25
@@ -1,6 +1,6 @@ .. _perf_security: -Perf Events and tool security +Perf events and tool security ============================= Overview
@@ -42,11 +42,11 @@ categories: Data that belong to the fourth category can potentially contain sensitive process data. If PMUs in some monitoring modes capture values of execution context registers or data from process memory then access -to such monitoring capabilities requires to be ordered and secured -properly. So, perf_events/Perf performance monitoring is the subject for -security access control management [5]_ . +to such monitoring modes requires to be ordered and secured properly. +So, perf_events performance monitoring and observability operations are +the subject for security access control management [5]_ . -perf_events/Perf access control +perf_events access control ------------------------------- To perform security checks, the Linux implementation splits processes
@@ -66,11 +66,25 @@ into distinct units, known as capabilities [6]_ , which can be independently enabled and disabled on per-thread basis for processes and files of unprivileged users. -Unprivileged processes with enabled CAP_SYS_ADMIN capability are treated +Unprivileged processes with enabled CAP_PERFMON capability are treated as privileged processes with respect to perf_events performance -monitoring and bypass *scope* permissions checks in the kernel. - -Unprivileged processes using perf_events system call API is also subject +monitoring and observability operations, thus, bypass *scope* permissions +checks in the kernel. CAP_PERFMON implements the principle of least +privilege [13]_ (POSIX 1003.1e: 2.2.2.39) for performance monitoring and +observability operations in the kernel and provides a secure approach to +perfomance monitoring and observability in the system. + +For backward compatibility reasons the access to perf_events monitoring and +observability operations is also open for CAP_SYS_ADMIN privileged +processes but CAP_SYS_ADMIN usage for secure monitoring and observability +use cases is discouraged with respect to the CAP_PERFMON capability. +If system audit records [14]_ for a process using perf_events system call +API contain denial records of acquiring both CAP_PERFMON and CAP_SYS_ADMIN +capabilities then providing the process with CAP_PERFMON capability singly +is recommended as the preferred secure approach to resolve double access +denial logging related to usage of performance monitoring and observability. + +Unprivileged processes using perf_events system call are also subject for PTRACE_MODE_READ_REALCREDS ptrace access mode check [7]_ , whose outcome determines whether monitoring is permitted. So unprivileged processes provided with CAP_SYS_PTRACE capability are effectively
@@ -82,14 +96,14 @@ performance analysis of monitored processes or a system. For example, CAP_SYSLOG capability permits reading kernel space memory addresses from /proc/kallsyms file. -perf_events/Perf privileged users +Privileged Perf users groups --------------------------------- Mechanisms of capabilities, privileged capability-dumb files [6]_ and -file system ACLs [10]_ can be used to create a dedicated group of -perf_events/Perf privileged users who are permitted to execute -performance monitoring without scope limits. The following steps can be -taken to create such a group of privileged Perf users. +file system ACLs [10]_ can be used to create dedicated groups of +privileged Perf users who are permitted to execute performance monitoring +and observability without scope limits. The following steps can be +taken to create such groups of privileged Perf users. 1. Create perf_users group of privileged Perf users, assign perf_users group to Perf tool executable and limit access to the executable for
@@ -108,30 +122,51 @@ taken to create such a group of privileged Perf users. -rwxr-x--- 2 root perf_users 11M Oct 19 15:12 perf 2. Assign the required capabilities to the Perf tool executable file and - enable members of perf_users group with performance monitoring + enable members of perf_users group with monitoring and observability privileges [6]_ : :: - # setcap "cap_sys_admin,cap_sys_ptrace,cap_syslog=ep" perf - # setcap -v "cap_sys_admin,cap_sys_ptrace,cap_syslog=ep" perf + # setcap "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" perf + # setcap -v "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" perf perf: OK # getcap perf - perf = cap_sys_ptrace,cap_sys_admin,cap_syslog+ep + perf = cap_sys_ptrace,cap_syslog,cap_perfmon+ep + +If the libcap installed doesn't yet support "cap_perfmon", use "38" instead, +i.e.: + +:: + + # setcap "38,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf + +Note that you may need to have 'cap_ipc_lock' in the mix for tools such as +'perf top', alternatively use 'perf top -m N', to reduce the memory that +it uses for the perf ring buffer, see the memory allocation section below. + +Using a libcap without support for CAP_PERFMON will make cap_get_flag(caps, 38, +CAP_EFFECTIVE, &val) fail, which will lead the default event to be 'cycles:u', +so as a workaround explicitly ask for the 'cycles' event, i.e.: + +:: + + # perf top -e cycles + +To get kernel and user samples with a perf binary with just CAP_PERFMON. As a result, members of perf_users group are capable of conducting -performance monitoring by using functionality of the configured Perf -tool executable that, when executes, passes perf_events subsystem scope -checks. +performance monitoring and observability by using functionality of the +configured Perf tool executable that, when executes, passes perf_events +subsystem scope checks. This specific access control management is only available to superuser or root running processes with CAP_SETPCAP, CAP_SETFCAP [6]_ capabilities. -perf_events/Perf unprivileged users +Unprivileged users ----------------------------------- -perf_events/Perf *scope* and *access* control for unprivileged processes +perf_events *scope* and *access* control for unprivileged processes is governed by perf_event_paranoid [2]_ setting: -1:
@@ -166,7 +201,7 @@ is governed by perf_event_paranoid [2]_ setting: perf_event_mlock_kb locking limit is imposed but ignored for unprivileged processes with CAP_IPC_LOCK capability. -perf_events/Perf resource control +Resource control --------------------------------- Open file descriptors
@@ -227,4 +262,5 @@ Bibliography .. [10] `<http://man7.org/linux/man-pages/man5/acl.5.html>`_ .. [11] `<http://man7.org/linux/man-pages/man2/getrlimit.2.html>`_ .. [12] `<http://man7.org/linux/man-pages/man5/limits.conf.5.html>`_ - +.. [13] `<https://sites.google.com/site/fullycapable>`_ +.. [14] `<http://man7.org/linux/man-pages/man8/auditd.8.html>`_
PATCH v8 12/12 doc/admin-guide: update kernel.rst with CAP_PERFMON information
In reply to Alexey BudankovUpdate kernel.rst documentation file with the information related to usage of CAP_PERFMON capability to secure performance monitoring and observability operations in system.
--- Documentation/admin-guide/sysctl/kernel.rst | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)
Documentation/admin-guide/sysctl/kernel.rst +11 -5
@@ -720,20 +720,26 @@ perf_event_paranoid: ==================== Controls use of the performance events system by unprivileged -users (without CAP_SYS_ADMIN). The default value is 2. +users (without CAP_PERFMON). The default value is 2. + +For backward compatibility reasons access to system performance +monitoring and observability remains open for CAP_SYS_ADMIN +privileged processes but CAP_SYS_ADMIN usage for secure system +performance monitoring and observability operations is discouraged +with respect to CAP_PERFMON use cases. === ================================================================== -1 Allow use of (almost) all events by all users Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK ->=0 Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN +>=0 Disallow ftrace function tracepoint by users without CAP_PERFMON - Disallow raw tracepoint access by users without CAP_SYS_ADMIN + Disallow raw tracepoint access by users without CAP_PERFMON ->=1 Disallow CPU event access by users without CAP_SYS_ADMIN +>=1 Disallow CPU event access by users without CAP_PERFMON ->=2 Disallow kernel profiling by users without CAP_SYS_ADMIN +>=2 Disallow kernel profiling by users without CAP_PERFMON === ==================================================================
Signature · 1 line
2.24.1
Re: [PATCH v8 12/12] doc/admin-guide: update kernel.rst with CAP_PERFMON information
Em Thu, Apr 02, 2020 at 11:54:39AM +0300, Alexey Budankov escreveu:
Quoted 4 lines
Update
kernel.rstdocumentation file with the information related to usage ofCAP_PERFMONcapability to secure performance monitoring and observability operations in system.
This one is failing in my perf/core branch, please take a look. I'm pushing my perf/core branch with this series applied, please check that everything is ok, I'll do some testing now, but it all seems ok.
Thanks,
- Arnaldo
Quoted 44 lines
Signed-off-by Alexey Budankov <[email protected]>--- Documentation/admin-guide/sysctl/kernel.rst | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)Documentation/admin-guide/sysctl/kernel.rst +11
-5@@ -720,20 +720,26 @@ perf_event_paranoid: ==================== Controls use of the performance events system by unprivileged -users (without CAP_SYS_ADMIN). The default value is 2. +users (without CAP_PERFMON). The default value is 2. + +For backward compatibility reasons access to system performance +monitoring and observability remains open for CAP_SYS_ADMIN +privileged processes but CAP_SYS_ADMIN usage for secure system +performance monitoring and observability operations is discouraged +with respect to CAP_PERFMON use cases. === ================================================================== -1 Allow use of (almost) all events by all users Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK ->=0 Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN +>=0 Disallow ftrace function tracepoint by users without CAP_PERFMON - Disallow raw tracepoint access by users without CAP_SYS_ADMIN + Disallow raw tracepoint access by users without CAP_PERFMON ->=1 Disallow CPU event access by users without CAP_SYS_ADMIN +>=1 Disallow CPU event access by users without CAP_PERFMON ->=2 Disallow kernel profiling by users without CAP_SYS_ADMIN +>=2 Disallow kernel profiling by users without CAP_PERFMON === ==================================================================Signature · 1 line
2.24.1
Signature · 1 line
- Arnaldo
Re: [PATCH v8 12/12] doc/admin-guide: update kernel.rst with CAP_PERFMON information
Quoted 7 lines · Arnaldo Carvalho de Melo
Em Thu, Apr 02, 2020 at 11:54:39AM +0300, Alexey Budankov escreveu:
Quoted 4 lines
Update
kernel.rstdocumentation file with the information related to usage ofCAP_PERFMONcapability to secure performance monitoring and observability operations in system.This one is failing in my perf/core branch, please take a look. I'm
Trying to reproduce right now. What kind of failure do you see? Please share some specifics so I could follow up properly.
Thanks,
Alexey
Quoted 52 lines
pushing my perf/core branch with this series applied, please check that everything is ok, I'll do some testing now, but it all seems ok.
Thanks,
- Arnaldo
Quoted 44 lines
Signed-off-by Alexey Budankov <[email protected]>--- Documentation/admin-guide/sysctl/kernel.rst | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)Documentation/admin-guide/sysctl/kernel.rst +11
-5@@ -720,20 +720,26 @@ perf_event_paranoid: ==================== Controls use of the performance events system by unprivileged -users (without CAP_SYS_ADMIN). The default value is 2. +users (without CAP_PERFMON). The default value is 2. + +For backward compatibility reasons access to system performance +monitoring and observability remains open for CAP_SYS_ADMIN +privileged processes but CAP_SYS_ADMIN usage for secure system +performance monitoring and observability operations is discouraged +with respect to CAP_PERFMON use cases. === ================================================================== -1 Allow use of (almost) all events by all users Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK ->=0 Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN +>=0 Disallow ftrace function tracepoint by users without CAP_PERFMON - Disallow raw tracepoint access by users without CAP_SYS_ADMIN + Disallow raw tracepoint access by users without CAP_PERFMON ->=1 Disallow CPU event access by users without CAP_SYS_ADMIN +>=1 Disallow CPU event access by users without CAP_PERFMON ->=2 Disallow kernel profiling by users without CAP_SYS_ADMIN +>=2 Disallow kernel profiling by users without CAP_PERFMON === ==================================================================Signature · 1 line
2.24.1
Re: [PATCH v8 12/12] doc/admin-guide: update kernel.rst with CAP_PERFMON information
Quoted 9 lines · Alexey Budankov
Quoted 7 lines · Arnaldo Carvalho de Melo
Em Thu, Apr 02, 2020 at 11:54:39AM +0300, Alexey Budankov escreveu:
Quoted 4 lines
Update
kernel.rstdocumentation file with the information related to usage ofCAP_PERFMONcapability to secure performance monitoring and observability operations in system.This one is failing in my perf/core branch, please take a look. I'm
Please try applying this:
--- Documentation/admin-guide/sysctl/kernel.rst | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)
Documentation/admin-guide/sysctl/kernel.rst +11 -6
@@ -709,7 +709,13 @@ perf_event_paranoid =================== Controls use of the performance events system by unprivileged -users (without CAP_SYS_ADMIN). The default value is 2. +users (without CAP_PERFMON). The default value is 2. + +For backward compatibility reasons access to system performance +monitoring and observability remains open for CAP_SYS_ADMIN +privileged processes but CAP_SYS_ADMIN usage for secure system +performance monitoring and observability operations is discouraged +with respect to CAP_PERFMON use cases. === ================================================================== -1 Allow use of (almost) all events by all users.
@@ -718,13 +724,13 @@ users (without CAP_SYS_ADMIN). The default value is 2. ``CAP_IPC_LOCK``. >=0 Disallow ftrace function tracepoint by users without - ``CAP_SYS_ADMIN``. + ``CAP_PERFMON``. - Disallow raw tracepoint access by users without ``CAP_SYS_ADMIN``. + Disallow raw tracepoint access by users without ``CAP_PERFMON``. ->=1 Disallow CPU event access by users without ``CAP_SYS_ADMIN``. +>=1 Disallow CPU event access by users without ``CAP_PERFMON``. ->=2 Disallow kernel profiling by users without ``CAP_SYS_ADMIN``. +>=2 Disallow kernel profiling by users without ``CAP_PERFMON``. === ================================================================== ---
Thanks,
Alexey
Quoted 59 lines
Trying to reproduce right now. What kind of failure do you see? Please share some specifics so I could follow up properly.
Thanks,
AlexeyQuoted 52 lines
pushing my perf/core branch with this series applied, please check that everything is ok, I'll do some testing now, but it all seems ok.
Thanks,
- Arnaldo
Quoted 44 lines
Signed-off-by Alexey Budankov <[email protected]>--- Documentation/admin-guide/sysctl/kernel.rst | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)Documentation/admin-guide/sysctl/kernel.rst +11
-5@@ -720,20 +720,26 @@ perf_event_paranoid: ==================== Controls use of the performance events system by unprivileged -users (without CAP_SYS_ADMIN). The default value is 2. +users (without CAP_PERFMON). The default value is 2. + +For backward compatibility reasons access to system performance +monitoring and observability remains open for CAP_SYS_ADMIN +privileged processes but CAP_SYS_ADMIN usage for secure system +performance monitoring and observability operations is discouraged +with respect to CAP_PERFMON use cases. === ================================================================== -1 Allow use of (almost) all events by all users Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK ->=0 Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN +>=0 Disallow ftrace function tracepoint by users without CAP_PERFMON - Disallow raw tracepoint access by users without CAP_SYS_ADMIN + Disallow raw tracepoint access by users without CAP_PERFMON ->=1 Disallow CPU event access by users without CAP_SYS_ADMIN +>=1 Disallow CPU event access by users without CAP_PERFMON ->=2 Disallow kernel profiling by users without CAP_SYS_ADMIN +>=2 Disallow kernel profiling by users without CAP_PERFMON === ==================================================================Signature · 1 line
2.24.1
Arnaldo Carvalho de Melo
AppliedRe: [PATCH v8 12/12] doc/admin-guide: update kernel.rst with CAP_PERFMON information
Em Sun, Apr 05, 2020 at 05:54:37PM +0300, Alexey Budankov escreveu:
Quoted 6 lines · Alexey Budankov
Quoted 4 lines · Arnaldo Carvalho de Melo
Quoted 2 lines
Em Thu, Apr 02, 2020 at 11:54:39AM +0300, Alexey Budankov escreveu:
Quoted 1 line
Quoted 7 lines
Quoted 5 lines
Quoted 5 lines
Quoted 3 lines
Update
kernel.rstdocumentation file with the information related to usage ofCAP_PERFMONcapability to secure performance monitoring and observability operations in system.This one is failing in my perf/core branch, please take a look. I'm
Please try applying this:
Thanks, applied with the original commit log message,
- Arnaldo
Quoted 104 lines
--- Documentation/admin-guide/sysctl/kernel.rst | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)Documentation/admin-guide/sysctl/kernel.rst +11
-6@@ -709,7 +709,13 @@ perf_event_paranoid =================== Controls use of the performance events system by unprivileged -users (without CAP_SYS_ADMIN). The default value is 2. +users (without CAP_PERFMON). The default value is 2. + +For backward compatibility reasons access to system performance +monitoring and observability remains open for CAP_SYS_ADMIN +privileged processes but CAP_SYS_ADMIN usage for secure system +performance monitoring and observability operations is discouraged +with respect to CAP_PERFMON use cases. === ================================================================== -1 Allow use of (almost) all events by all users.@@ -718,13 +724,13 @@ users (without CAP_SYS_ADMIN). The default value is 2. ``CAP_IPC_LOCK``. >=0 Disallow ftrace function tracepoint by users without - ``CAP_SYS_ADMIN``. + ``CAP_PERFMON``. - Disallow raw tracepoint access by users without ``CAP_SYS_ADMIN``. + Disallow raw tracepoint access by users without ``CAP_PERFMON``. ->=1 Disallow CPU event access by users without ``CAP_SYS_ADMIN``. +>=1 Disallow CPU event access by users without ``CAP_PERFMON``. ->=2 Disallow kernel profiling by users without ``CAP_SYS_ADMIN``. +>=2 Disallow kernel profiling by users without ``CAP_PERFMON``. === ================================================================== ---Thanks,
AlexeyQuoted 59 lines
Trying to reproduce right now. What kind of failure do you see? Please share some specifics so I could follow up properly.
Thanks,
AlexeyQuoted 52 lines
pushing my perf/core branch with this series applied, please check that everything is ok, I'll do some testing now, but it all seems ok.
Thanks,
- Arnaldo
Quoted 44 lines
Signed-off-by Alexey Budankov <[email protected]>--- Documentation/admin-guide/sysctl/kernel.rst | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)Documentation/admin-guide/sysctl/kernel.rst +11
-5@@ -720,20 +720,26 @@ perf_event_paranoid: ==================== Controls use of the performance events system by unprivileged -users (without CAP_SYS_ADMIN). The default value is 2. +users (without CAP_PERFMON). The default value is 2. + +For backward compatibility reasons access to system performance +monitoring and observability remains open for CAP_SYS_ADMIN +privileged processes but CAP_SYS_ADMIN usage for secure system +performance monitoring and observability operations is discouraged +with respect to CAP_PERFMON use cases. === ================================================================== -1 Allow use of (almost) all events by all users Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK ->=0 Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN +>=0 Disallow ftrace function tracepoint by users without CAP_PERFMON - Disallow raw tracepoint access by users without CAP_SYS_ADMIN + Disallow raw tracepoint access by users without CAP_PERFMON ->=1 Disallow CPU event access by users without CAP_SYS_ADMIN +>=1 Disallow CPU event access by users without CAP_PERFMON ->=2 Disallow kernel profiling by users without CAP_SYS_ADMIN +>=2 Disallow kernel profiling by users without CAP_PERFMON === ==================================================================Signature · 1 line
2.24.1
Signature · 1 line
- Arnaldo
Re: [PATCH v8 12/12] doc/admin-guide: update kernel.rst with CAP_PERFMON information
Quoted 11 lines · Arnaldo Carvalho de Melo
Em Sun, Apr 05, 2020 at 05:54:37PM +0300, Alexey Budankov escreveu:
Quoted 10 lines · Alexey Budankov
Quoted 8 lines · Arnaldo Carvalho de Melo
Quoted 6 lines
Em Thu, Apr 02, 2020 at 11:54:39AM +0300, Alexey Budankov escreveu:
Quoted 4 lines
Update
kernel.rstdocumentation file with the information related to usage ofCAP_PERFMONcapability to secure performance monitoring and observability operations in system.
Quoted 5 lines
Quoted 3 lines
Quoted 1 line
Quoted 1 line
This one is failing in my perf/core branch, please take a look. I'm
Please try applying this:
Thanks, applied with the original commit log message,
Thanks,
Alexey
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
[tip: perf/core] doc/admin-guide: update kernel.rst with CAP_PERFMON information
In reply to Alexey BudankovThe following commit has been merged into the perf/core branch of tip:
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 025b16f81dd7f51f29d0109399d669438c63b6ce Gitweb: https://git.kernel.org/tip/025b16f81dd7f51f29d0109399d669438c63b6ce Author: Alexey Budankov <[email protected]> AuthorDate: Thu, 02 Apr 2020 11:54:39 +03:00 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitterDate: Thu, 16 Apr 2020 12:19:12 -03:00
doc/admin-guide: update kernel.rst with CAP_PERFMON information
Update the kernel.rst documentation file with the information related to usage of CAP_PERFMON capability to secure performance monitoring and observability operations in system.
--- Documentation/admin-guide/sysctl/kernel.rst | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)
Documentation/admin-guide/sysctl/kernel.rst +11 -5
@@ -730,7 +730,13 @@ perf_event_paranoid =================== Controls use of the performance events system by unprivileged -users (without CAP_SYS_ADMIN). The default value is 2. +users (without CAP_PERFMON). The default value is 2. + +For backward compatibility reasons access to system performance +monitoring and observability remains open for CAP_SYS_ADMIN +privileged processes but CAP_SYS_ADMIN usage for secure system +performance monitoring and observability operations is discouraged +with respect to CAP_PERFMON use cases. === ================================================================== -1 Allow use of (almost) all events by all users.
@@ -739,13 +745,13 @@ users (without CAP_SYS_ADMIN). The default value is 2. ``CAP_IPC_LOCK``. >=0 Disallow ftrace function tracepoint by users without - ``CAP_SYS_ADMIN``. + ``CAP_PERFMON``. - Disallow raw tracepoint access by users without ``CAP_SYS_ADMIN``. + Disallow raw tracepoint access by users without ``CAP_PERFMON``. ->=1 Disallow CPU event access by users without ``CAP_SYS_ADMIN``. +>=1 Disallow CPU event access by users without ``CAP_PERFMON``. ->=2 Disallow kernel profiling by users without ``CAP_SYS_ADMIN``. +>=2 Disallow kernel profiling by users without ``CAP_PERFMON``. === ==================================================================
[Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Introduce CAP_PERFMON to secure system performance monitoring and observability (rev5)
In reply to Alexey Budankov== Series Details ==
== Series Details ==
Series: Introduce CAP_PERFMON to secure system performance monitoring and observability (rev5)
URL : https://patchwork.freedesktop.org/series/72273/
State : warning
== Summary ==
$ dim checkpatch origin/drm-tip c027b79d90c7 capabilities: introduce CAP_PERFMON to kernel and user space -:13: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #13: is available to a CAP_SYS_ADMIN privileged process [2]. Providing the access
total: 0 errors, 1 warnings, 0 checks, 36 lines checked72d47d8219d3 perf/core: open access to the core for CAP_PERFMON privileged process
-:9: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #9:CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials,
total: 0 errors, 1 warnings, 0 checks, 32 lines checked330862f4c392 perf/core: open access to probes for CAP_PERFMON privileged process
-:18: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #18:
monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle
total: 0 errors, 1 warnings, 0 checks, 16 lines checkedd6069cbc260a perf tool: extend Perf tool with CAP_PERFMON capability supportfaa4cad37f3f drm/i915/perf: open access for CAP_PERFMON privileged processb18034c782e2 trace/bpf_trace: open access for CAP_PERFMON privileged process27bbababcb71 powerpc/perf: open access for CAP_PERFMON privileged process
-:24: WARNING:BAD_SIGN_OFF: email address 'Anju T Sudhakar<[email protected]>' might be better as 'Anju T Sudhakar <[email protected]>' #24:
total: 0 errors, 1 warnings, 0 checks, 16 lines checked06a7ab2ee66f parisc/perf: open access for CAP_PERFMON privileged process c6b6bc12a6fa drivers/perf: open access for CAP_PERFMON privileged process f43a46c59baa drivers/oprofile: open access for CAP_PERFMON privileged process 00b49a09c154 doc/admin-guide: update perf-security.rst with CAP_PERFMON information 6f9e4a45e370 doc/admin-guide: update kernel.rst with CAP_PERFMON information
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Patchwork
CI[Intel-gfx] ✓ Fi.CI.BAT: success for Introduce CAP_PERFMON to secure system performance monitoring and observability (rev5)
In reply to Alexey Budankov== Series Details ==
== Series Details ==
Series: Introduce CAP_PERFMON to secure system performance monitoring and observability (rev5)
URL : https://patchwork.freedesktop.org/series/72273/
State : success
== Summary ==
CI Bug Log - changes from CI_DRM_8236 -> Patchwork_17177
====================================================
Summary
-------
**SUCCESS**
No regressions found.
External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/index.html
Known issues
------------
Here are the changes found in Patchwork_17177 that come from known issues:
### IGT changes ###
#### Warnings ####
* igt@kms_flip@basic-flip-vs-wf_vblank:
- fi-kbl-x1275: [DMESG-WARN][1] ([i915#62] / [i915#92]) -> [DMESG-WARN][2] ([i915#62] / [i915#92] / [i915#95]) +4 similar issues
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/fi-kbl-x1275/igt@kms_flip@basic-flip-vs-wf_vblank.html
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/fi-kbl-x1275/igt@kms_flip@basic-flip-vs-wf_vblank.html
* igt@kms_pipe_crc_basic@nonblocking-crc-pipe-a:
- fi-kbl-x1275: [DMESG-WARN][3] ([i915#62] / [i915#92] / [i915#95]) -> [DMESG-WARN][4] ([i915#62] / [i915#92]) +4 similar issues
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/fi-kbl-x1275/igt@[email protected]
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/fi-kbl-x1275/igt@[email protected]
{name}: This element is suppressed. This means it is ignored when computing
the status of the difference (SUCCESS, WARNING, or FAILURE).
[i915#1314]: https://gitlab.freedesktop.org/drm/intel/issues/1314
[i915#62]: https://gitlab.freedesktop.org/drm/intel/issues/62
[i915#92]: https://gitlab.freedesktop.org/drm/intel/issues/92
[i915#95]: https://gitlab.freedesktop.org/drm/intel/issues/95
Participating hosts (47 -> 43)
------------------------------
Additional (4): fi-hsw-peppy fi-skl-6770hq fi-skl-6600u fi-elk-e7500
Missing (8): fi-ilk-m540 fi-hsw-4200u fi-bsw-cyan fi-snb-2520m fi-ctg-p8600 fi-byt-clapper fi-bsw-nick fi-bdw-samus
Build changes
-------------
* CI: CI-20190529 -> None
* Linux: CI_DRM_8236 -> Patchwork_17177
CI-20190529: 20190529
CI_DRM_8236: 698ce59acca37b93bfcdee6899504be3eb113097 @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_5556: 311cb1b360b7ae00fab80b822cd34fd512f08ce9 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
Patchwork_17177: 6f9e4a45e370aafb38de338cb9d03bf46a825f18 @ git://anongit.freedesktop.org/gfx-ci/linux
== Linux commits ==
6f9e4a45e370 doc/admin-guide: update kernel.rst with CAP_PERFMON information 00b49a09c154 doc/admin-guide: update perf-security.rst with CAP_PERFMON information f43a46c59baa drivers/oprofile: open access for CAP_PERFMON privileged process c6b6bc12a6fa drivers/perf: open access for CAP_PERFMON privileged process 06a7ab2ee66f parisc/perf: open access for CAP_PERFMON privileged process 27bbababcb71 powerpc/perf: open access for CAP_PERFMON privileged process b18034c782e2 trace/bpf_trace: open access for CAP_PERFMON privileged process faa4cad37f3f drm/i915/perf: open access for CAP_PERFMON privileged process d6069cbc260a perf tool: extend Perf tool with CAP_PERFMON capability support 330862f4c392 perf/core: open access to probes for CAP_PERFMON privileged process 72d47d8219d3 perf/core: open access to the core for CAP_PERFMON privileged process c027b79d90c7 capabilities: introduce CAP_PERFMON to kernel and user space
== Logs ==
For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/index.html
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Patchwork
CI[Intel-gfx] ✗ Fi.CI.IGT: failure for Introduce CAP_PERFMON to secure system performance monitoring and observability (rev5)
In reply to Alexey Budankov== Series Details ==
== Series Details ==
Series: Introduce CAP_PERFMON to secure system performance monitoring and observability (rev5)
URL : https://patchwork.freedesktop.org/series/72273/
State : failure
== Summary ==
CI Bug Log - changes from CI_DRM_8236_full -> Patchwork_17177_full
====================================================
Summary
-------
**FAILURE**
Serious unknown changes coming with Patchwork_17177_full absolutely need to be verified manually.
If you think the reported changes have nothing to do with the changes introduced in Patchwork_17177_full, please notify your bug team to allow them to document this new failure mode, which will reduce false positives in CI.
Possible new issues
-------------------
Here are the unknown changes that may have been introduced in Patchwork_17177_full:
### IGT changes ###
#### Possible regressions ####
* igt@gem_ctx_persistence@engines-hang@rcs0:
- shard-tglb: [PASS][1] -> [FAIL][2] +1 similar issue
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-tglb1/igt@gem_ctx_persistence@[email protected]
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-tglb7/igt@gem_ctx_persistence@[email protected]
* igt@gem_mmap_gtt@cpuset-medium-copy-xy:
- shard-skl: [PASS][3] -> [FAIL][4] +2 similar issues
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-skl2/igt@[email protected]
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-skl2/igt@[email protected]
* igt@gem_tiled_swapping@non-threaded:
- shard-glk: [PASS][5] -> [FAIL][6]
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-glk6/igt@[email protected]
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-glk4/igt@[email protected]
New tests
---------
New tests have been introduced between CI_DRM_8236_full and Patchwork_17177_full:
### New IGT tests (2) ###
* igt@perf_pmu@busy-hang:
- Statuses :
- Exec time: [None] s
* igt@perf_pmu@multi-client:
- Statuses :
- Exec time: [None] s
Known issues
------------
Here are the changes found in Patchwork_17177_full that come from known issues:
### IGT changes ###
#### Issues hit ####
* igt@gem_cs_tlb@vcs1:
- shard-iclb: [PASS][7] -> [SKIP][8] ([fdo#112080])
[7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-iclb2/igt@[email protected]
[8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-iclb5/igt@[email protected]
* igt@gem_exec_suspend@basic-s3:
- shard-apl: [PASS][9] -> [DMESG-WARN][10] ([i915#180])
[9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-apl4/igt@[email protected]
[10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-apl8/igt@[email protected]
* igt@i915_suspend@fence-restore-untiled:
- shard-kbl: [PASS][11] -> [DMESG-WARN][12] ([i915#180])
[11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-kbl1/igt@[email protected]
[12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-kbl7/igt@[email protected]
* igt@kms_draw_crc@draw-method-rgb565-mmap-gtt-untiled:
- shard-glk: [PASS][13] -> [FAIL][14] ([i915#52] / [i915#54])
[13]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-glk5/igt@[email protected]
[14]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-glk9/igt@[email protected]
* igt@kms_flip@flip-vs-expired-vblank:
- shard-skl: [PASS][15] -> [FAIL][16] ([i915#79])
[15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-skl1/igt@[email protected]
[16]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-skl10/igt@[email protected]
* igt@kms_hdr@bpc-switch-suspend:
- shard-skl: [PASS][17] -> [FAIL][18] ([i915#1188])
[17]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-skl3/igt@[email protected]
[18]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-skl6/igt@[email protected]
* igt@kms_plane_alpha_blend@pipe-b-coverage-7efc:
- shard-skl: [PASS][19] -> [FAIL][20] ([fdo#108145] / [i915#265])
[19]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-skl10/igt@[email protected]
[20]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-skl10/igt@[email protected]
* igt@kms_psr@no_drrs:
- shard-iclb: [PASS][21] -> [FAIL][22] ([i915#173])
[21]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-iclb4/igt@kms_psr@no_drrs.html
[22]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-iclb1/igt@kms_psr@no_drrs.html
* igt@kms_psr@psr2_cursor_render:
- shard-iclb: [PASS][23] -> [SKIP][24] ([fdo#109441]) +2 similar issues
[23]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-iclb2/igt@kms_psr@psr2_cursor_render.html
[24]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-iclb3/igt@kms_psr@psr2_cursor_render.html
* igt@kms_setmode@basic:
- shard-hsw: [PASS][25] -> [FAIL][26] ([i915#31])
[25]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-hsw6/igt@[email protected]
[26]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-hsw1/igt@[email protected]
* igt@prime_vgem@fence-wait-bsd2:
- shard-iclb: [PASS][27] -> [SKIP][28] ([fdo#109276]) +4 similar issues
[27]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-iclb2/igt@[email protected]
[28]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-iclb3/igt@[email protected]
#### Possible fixes ####
* igt@gem_mmap_gtt@cpuset-basic-small-copy-odd:
- shard-hsw: [FAIL][29] -> [PASS][30]
[29]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-hsw2/igt@[email protected]
[30]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-hsw1/igt@[email protected]
* igt@gem_tiled_swapping@non-threaded:
- shard-snb: [FAIL][31] -> [PASS][32]
[31]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-snb6/igt@[email protected]
[32]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-snb4/igt@[email protected]
* igt@kms_cursor_crc@pipe-a-cursor-256x256-offscreen:
- shard-apl: [FAIL][33] ([i915#54] / [i915#95]) -> [PASS][34]
[33]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-apl8/igt@[email protected]
[34]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-apl2/igt@[email protected]
* igt@kms_cursor_crc@pipe-a-cursor-suspend:
- shard-kbl: [DMESG-WARN][35] ([i915#180]) -> [PASS][36] +7 similar issues
[35]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-kbl7/igt@[email protected]
[36]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-kbl1/igt@[email protected]
* igt@kms_draw_crc@draw-method-rgb565-mmap-gtt-xtiled:
- shard-glk: [FAIL][37] ([i915#52] / [i915#54]) -> [PASS][38]
[37]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-glk7/igt@[email protected]
[38]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-glk2/igt@[email protected]
* igt@kms_flip@flip-vs-expired-vblank-interruptible:
- shard-skl: [FAIL][39] ([i915#79]) -> [PASS][40]
[39]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-skl2/igt@[email protected]
[40]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-skl2/igt@[email protected]
* igt@kms_flip@flip-vs-suspend:
- shard-skl: [INCOMPLETE][41] ([i915#221]) -> [PASS][42]
[41]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-skl4/igt@[email protected]
[42]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-skl4/igt@[email protected]
* igt@kms_flip@flip-vs-suspend-interruptible:
- shard-apl: [DMESG-WARN][43] ([i915#180]) -> [PASS][44] +2 similar issues
[43]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-apl7/igt@[email protected]
[44]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-apl1/igt@[email protected]
* igt@kms_hdr@bpc-switch-dpms:
- shard-skl: [FAIL][45] ([i915#1188]) -> [PASS][46]
[45]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-skl1/igt@[email protected]
[46]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-skl7/igt@[email protected]
* igt@kms_psr@psr2_cursor_mmap_cpu:
- shard-iclb: [SKIP][47] ([fdo#109441]) -> [PASS][48]
[47]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-iclb1/igt@kms_psr@psr2_cursor_mmap_cpu.html
[48]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-iclb2/igt@kms_psr@psr2_cursor_mmap_cpu.html
#### Warnings ####
* igt@i915_pm_dc@dc3co-vpb-simulation:
- shard-iclb: [SKIP][49] ([i915#588]) -> [SKIP][50] ([i915#658])
[49]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-iclb2/igt@[email protected]
[50]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-iclb5/igt@[email protected]
* igt@i915_pm_dc@dc6-psr:
- shard-tglb: [SKIP][51] ([i915#468]) -> [FAIL][52] ([i915#454])
[51]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8236/shard-tglb2/igt@[email protected]
[52]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/shard-tglb1/igt@[email protected]
{name}: This element is suppressed. This means it is ignored when computing
the status of the difference (SUCCESS, WARNING, or FAILURE).
[fdo#108145]: https://bugs.freedesktop.org/show_bug.cgi?id=108145
[fdo#109276]: https://bugs.freedesktop.org/show_bug.cgi?id=109276
[fdo#109441]: https://bugs.freedesktop.org/show_bug.cgi?id=109441
[fdo#112080]: https://bugs.freedesktop.org/show_bug.cgi?id=112080
[i915#1188]: https://gitlab.freedesktop.org/drm/intel/issues/1188
[i915#1542]: https://gitlab.freedesktop.org/drm/intel/issues/1542
[i915#173]: https://gitlab.freedesktop.org/drm/intel/issues/173
[i915#180]: https://gitlab.freedesktop.org/drm/intel/issues/180
[i915#221]: https://gitlab.freedesktop.org/drm/intel/issues/221
[i915#265]: https://gitlab.freedesktop.org/drm/intel/issues/265
[i915#31]: https://gitlab.freedesktop.org/drm/intel/issues/31
[i915#454]: https://gitlab.freedesktop.org/drm/intel/issues/454
[i915#468]: https://gitlab.freedesktop.org/drm/intel/issues/468
[i915#52]: https://gitlab.freedesktop.org/drm/intel/issues/52
[i915#54]: https://gitlab.freedesktop.org/drm/intel/issues/54
[i915#588]: https://gitlab.freedesktop.org/drm/intel/issues/588
[i915#658]: https://gitlab.freedesktop.org/drm/intel/issues/658
[i915#79]: https://gitlab.freedesktop.org/drm/intel/issues/79
[i915#95]: https://gitlab.freedesktop.org/drm/intel/issues/95
Participating hosts (10 -> 10)
------------------------------
No changes in participating hosts
Build changes
-------------
* CI: CI-20190529 -> None
* Linux: CI_DRM_8236 -> Patchwork_17177
CI-20190529: 20190529
CI_DRM_8236: 698ce59acca37b93bfcdee6899504be3eb113097 @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_5556: 311cb1b360b7ae00fab80b822cd34fd512f08ce9 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
Patchwork_17177: 6f9e4a45e370aafb38de338cb9d03bf46a825f18 @ git://anongit.freedesktop.org/gfx-ci/linux
piglit_4509: fdc5a4ca11124ab8413c7988896eec4c97336694 @ git://anongit.freedesktop.org/piglit
== Logs ==
For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17177/index.html
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Patchwork
CI[Intel-gfx] ✗ Fi.CI.BUILD: failure for Introduce CAP_PERFMON to secure system performance monitoring and observability (rev6)
In reply to Alexey Budankov== Series Details ==
== Series Details ==
Series: Introduce CAP_PERFMON to secure system performance monitoring and observability (rev6)
URL : https://patchwork.freedesktop.org/series/72273/
State : failure
== Summary ==
Applying: capabilities: introduce CAP_PERFMON to kernel and user space
Applying: perf/core: open access to the core for CAP_PERFMON privileged process
Applying: perf/core: open access to probes for CAP_PERFMON privileged process
Applying: perf tool: extend Perf tool with CAP_PERFMON capability support
Applying: drm/i915/perf: open access for CAP_PERFMON privileged process
Applying: trace/bpf_trace: open access for CAP_PERFMON privileged process
Applying: powerpc/perf: open access for CAP_PERFMON privileged process
Applying: parisc/perf: open access for CAP_PERFMON privileged process
Applying: drivers/perf: open access for CAP_PERFMON privileged process
Applying: drivers/oprofile: open access for CAP_PERFMON privileged process
Applying: doc/admin-guide: update perf-security.rst with CAP_PERFMON information
Applying: doc/admin-guide: update kernel.rst with CAP_PERFMON information
error: corrupt patch at line 106
error: could not build fake ancestor
hint: Use 'git am --show-current-patch=diff' to see the failed patch Patch failed at 0012 doc/admin-guide: update kernel.rst with CAP_PERFMON information When you have resolved this problem, run "git am --continue".
If you prefer to skip this patch, run "git am --skip" instead.
To restore the original branch and stop patching, run "git am --abort".
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Em Thu, Apr 02, 2020 at 11:42:05AM +0300, Alexey Budankov escreveu:
Quoted 4 lines
This patch set introduces
CAP_PERFMONcapability designed to secure system performance monitoring and observability operations so thatCAP_PERFMONwould assistCAP_SYS_ADMINcapability in its governing role for performance monitoring and observability subsystems of the kernel.
So, what am I doing wrong?
[perf@five ~]$ type perf
perf is hashed (/home/perf/bin/perf)
[perf@five ~]$
[perf@five ~]$ ls -lahF /home/perf/bin/perf
-rwxr-x---. 1 root perf_users 24M Apr 7 10:34 /home/perf/bin/perf* [perf@five ~]$
[perf@five ~]$ getcap /home/perf/bin/perf
[perf@five ~]$ perf top --stdio
Error:
You may not have permission to collect system-wide stats.
Consider tweaking /proc/sys/kernel/perf_event_paranoid, which controls use of the performance events system by unprivileged users (without CAP_PERFMON or CAP_SYS_ADMIN).
The current value is 2:
-1: Allow use of (almost) all events by all users
Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK
Quoted 1 line
= 0: Disallow ftrace function tracepoint by users without
CAP_PERFMONorCAP_SYS_ADMIN
Disallow raw tracepoint access by users without CAP_SYS_PERFMON or CAP_SYS_ADMIN
Quoted 2 lines
= 1: Disallow CPU event access by users without
CAP_PERFMONorCAP_SYS_ADMIN= 2: Disallow kernel profiling by users withoutCAP_PERFMONorCAP_SYS_ADMIN
To make this setting permanent, edit /etc/sysctl.conf too, e.g.:
kernel.perf_event_paranoid = -1
[perf@five ~]$
Ok, the message says I need to have CAP_PERFMON, lets do it, using an unpatched libcap that doesn't know about it but we can use 38, CAP_PERFMON value instead, and I tested this with a patched libcap as well, same results:
As root:
[root@five bin]# setcap "38,cap_sys_ptrace,cap_syslog=ep" perf [root@five bin]#
Back to the 'perf' user in the 'perf_users' group, ok, so now 'perf record -a' works for system wide sampling of cycles:u, i.e. only userspace samples, but 'perf top' is failing:
[perf@five ~]$ type perf
perf is hashed (/home/perf/bin/perf)
[perf@five ~]$ getcap /home/perf/bin/perf/home/perf/bin/perf = cap_sys_ptrace,cap_syslog,38+ep
[perf@five ~]$ groups
perf perf_users
[perf@five ~]$ id
uid=1002(perf) gid=1002(perf) groups=1002(perf),1003(perf_users) context=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 [perf@five ~]$ perf top --stdio
Error:
Failed to mmap with 1 (Operation not permitted)
[perf@five ~]$ perf record -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.177 MB perf.data (1552 samples) ]
[perf@five ~]$ perf evlist
cycles:u
[perf@five ~]$
- Arnaldo
Em Tue, Apr 07, 2020 at 11:30:14AM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 15 lines
[perf@five ~]$ type perf
perf is hashed (/home/perf/bin/perf)
[perf@five ~]$ getcap/home/perf/bin/perf/home/perf/bin/perf= cap_sys_ptrace,cap_syslog,38+ep
[perf@five ~]$ groups
perfperf_users
[perf@five ~]$ id
uid=1002(perf) gid=1002(perf) groups=1002(perf),1003(perf_users) context=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 [perf@five ~]$ perf top --stdio
Error:
Failed to mmap with 1 (Operation not permitted)
[perf@five ~]$ perf record -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.177 MB perf.data (1552 samples) ]
Quoted 3 lines
[perf@five ~]$ perf evlist
cycles:u
[perf@five ~]$
Humm, perf record falls back to cycles:u after initially trying cycles (i.e. kernel and userspace), lemme see trying 'perf top -e cycles:u', lemme test, humm not really:
[perf@five ~]$ perf top --stdio -e cycles:u
Error:
Failed to mmap with 1 (Operation not permitted) [perf@five ~]$ perf record -e cycles:u -a sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.123 MB perf.data (132 samples) ] [perf@five ~]$
Back to debugging this.
- Arnaldo
Quoted 32 lines · Arnaldo Carvalho de Melo
Em Tue, Apr 07, 2020 at 11:30:14AM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 15 lines
[perf@five ~]$ type perf
perf is hashed (/home/perf/bin/perf)
[perf@five ~]$ getcap/home/perf/bin/perf/home/perf/bin/perf= cap_sys_ptrace,cap_syslog,38+ep
[perf@five ~]$ groups
perfperf_users
[perf@five ~]$ id
uid=1002(perf) gid=1002(perf) groups=1002(perf),1003(perf_users) context=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 [perf@five ~]$ perf top --stdio
Error:
Failed to mmap with 1 (Operation not permitted)
[perf@five ~]$ perf record -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.177 MB perf.data (1552 samples) ]Quoted 3 lines
[perf@five ~]$ perf evlist
cycles:u
[perf@five ~]$Humm, perf record falls back to cycles:u after initially trying cycles (i.e. kernel and userspace), lemme see trying 'perf top -e cycles:u', lemme test, humm not really:
[perf@five ~]$ perf top --stdio -e cycles:u
Error:
Failed to mmap with 1 (Operation not permitted) [perf@five ~]$ perf record -e cycles:u -a sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.123 MB perf.data (132 samples) ] [perf@five ~]$
Quoted 1 line
Back to debugging this.
Could makes sense adding cap_ipc_lock to the binary to isolate from this:
kernel/events/core.c: 6101
if ((locked > lock_limit) && perf_is_paranoid() &&
!capable(CAP_IPC_LOCK)) {
ret = -EPERM;
goto unlock;
}~Alexey
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Em Tue, Apr 07, 2020 at 05:54:27PM +0300, Alexey Budankov escreveu:
Quoted 35 lines · Arnaldo Carvalho de Melo
Quoted 32 lines
Em Tue, Apr 07, 2020 at 11:30:14AM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 15 lines
[perf@five ~]$ type perf
perf is hashed (/home/perf/bin/perf)
[perf@five ~]$ getcap/home/perf/bin/perf/home/perf/bin/perf= cap_sys_ptrace,cap_syslog,38+ep
[perf@five ~]$ groups
perfperf_users
[perf@five ~]$ id
uid=1002(perf) gid=1002(perf) groups=1002(perf),1003(perf_users) context=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 [perf@five ~]$ perf top --stdio
Error:
Failed to mmap with 1 (Operation not permitted)
[perf@five ~]$ perf record -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.177 MB perf.data (1552 samples) ]Quoted 3 lines
[perf@five ~]$ perf evlist
cycles:u
[perf@five ~]$Humm, perf record falls back to cycles:u after initially trying cycles (i.e. kernel and userspace), lemme see trying 'perf top -e cycles:u', lemme test, humm not really:
[perf@five ~]$ perf top --stdio -e cycles:u
Error:
Failed to mmap with 1 (Operation not permitted) [perf@five ~]$ perf record -e cycles:u -a sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.123 MB perf.data (132 samples) ] [perf@five ~]$Quoted 1 line
Back to debugging this.
Quoted 8 lines
Could makes sense adding
cap_ipc_lockto the binary to isolate from this:
kernel/events/core.c: 6101if ((locked > lock_limit) && perf_is_paranoid() && !capable(CAP_IPC_LOCK)) { ret = -EPERM; goto unlock; }
That did the trick, I'll update the documentation and include in my "Committer testing" section:
[perf@five ~]$ groups
perf perf_users
[perf@five ~]$ ls -lahF bin/perf
-rwxr-x---. 1 root perf_users 24M Apr 7 10:34 bin/perf* [perf@five ~]$ getcap bin/perf
bin/perf = cap_ipc_lock,cap_sys_ptrace,cap_syslog,38+ep [perf@five ~]$
[perf@five ~]$ perf top --stdio
PerfTop: 652 irqs/sec kernel:73.8% exact: 99.7% lost: 0/0 drop: 0/0 [4000Hz cycles:u], (all, 12 CPUs)
---------------------------------------------------------------------------------------------------------------
13.03% [kernel] [k] module_get_kallsym
5.25% [kernel] [k] kallsyms_expand_symbol.constprop.0
5.00% libc-2.30.so [.] __GI_____strtoull_l_internal
4.41% [kernel] [k] memcpy
3.42% [kernel] [k] vsnprintf
2.98% perf [.] map__process_kallsym_symbol
2.86% [kernel] [k] format_decode
2.73% [kernel] [k] number
2.70% perf [.] rb_next
2.59% perf [.] maps__split_kallsyms
2.54% [kernel] [k] string_nocheck
1.90% libc-2.30.so [.] _IO_getdelim
1.86% [kernel] [k] __x86_indirect_thunk_rax
1.53% libc-2.30.so [.] _int_malloc
1.48% libc-2.30.so [.] __memmove_avx_unaligned_erms
1.40% [kernel] [k] clear_page_rep
1.07% perf [.] rb_insert_color
1.01% libc-2.30.so [.] _IO_feof
0.99% perf [.] __dso__load_kallsyms
0.98% [kernel] [k] s_next
0.96% perf [.] __rblist__findnew
0.95% [kernel] [k] strlen
0.95% perf [.] arch__symbols__fixup_end
0.94% libpixman-1.so.0.38.4 [.] 0x000000000006f4af
0.94% perf [.] symbol__new
0.89% libpixman-1.so.0.38.4 [.] 0x000000000006f4a0
0.86% [kernel] [k] seq_read
0.81% libpixman-1.so.0.38.4 [.] 0x000000000006f4ab
0.80% perf [.] __symbols__insert
0.73% libpixman-1.so.0.38.4 [.] 0x000000000006f4a7
0.67% [kernel] [k] s_show
0.66% libc-2.30.so [.] __libc_calloc
0.61% libpixman-1.so.0.38.4 [.] 0x000000000006f4bb
0.59% [kernel] [k] get_page_from_freelist
0.59% perf [.] memcpy@plt
0.58% perf [.] eprintfexiting.
[perf@five ~]$
There is still something strange in here, the event is cycles:u (see at the PerfTop line, but it is getting kernel samples :-\
- Arnaldo
Em Tue, Apr 07, 2020 at 01:36:54PM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 46 lines
Em Tue, Apr 07, 2020 at 05:54:27PM +0300, Alexey Budankov escreveu:
Quoted 35 lines · Arnaldo Carvalho de Melo
Quoted 32 lines
Em Tue, Apr 07, 2020 at 11:30:14AM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 15 lines
[perf@five ~]$ type perf
perf is hashed (/home/perf/bin/perf)
[perf@five ~]$ getcap/home/perf/bin/perf/home/perf/bin/perf= cap_sys_ptrace,cap_syslog,38+ep
[perf@five ~]$ groups
perfperf_users
[perf@five ~]$ id
uid=1002(perf) gid=1002(perf) groups=1002(perf),1003(perf_users) context=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 [perf@five ~]$ perf top --stdio
Error:
Failed to mmap with 1 (Operation not permitted)
[perf@five ~]$ perf record -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.177 MB perf.data (1552 samples) ]Quoted 3 lines
[perf@five ~]$ perf evlist
cycles:u
[perf@five ~]$Humm, perf record falls back to cycles:u after initially trying cycles (i.e. kernel and userspace), lemme see trying 'perf top -e cycles:u', lemme test, humm not really:
[perf@five ~]$ perf top --stdio -e cycles:u
Error:
Failed to mmap with 1 (Operation not permitted) [perf@five ~]$ perf record -e cycles:u -a sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.123 MB perf.data (132 samples) ] [perf@five ~]$Quoted 1 line
Back to debugging this.
Quoted 8 lines
Could makes sense adding
cap_ipc_lockto the binary to isolate from this:
kernel/events/core.c: 6101if ((locked > lock_limit) && perf_is_paranoid() && !capable(CAP_IPC_LOCK)) { ret = -EPERM; goto unlock; }
Quoted 2 lines
That did the trick, I'll update the documentation and include in my "Committer testing" section:
I ammended this to that patch, please check the wording:
- Arnaldo
Documentation/admin-guide/perf-security.rst +9 -2
@@ -127,12 +127,19 @@ taken to create such groups of privileged Perf users. :: - # setcap "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" perf - # setcap -v "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" perf + # setcap "cap_perfmon,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf + # setcap -v "cap_perfmon,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf perf: OK # getcap perf perf = cap_sys_ptrace,cap_syslog,cap_perfmon+ep +If the libcap installed doesn't yet support "cap_perfmon", use "38" instead, +i.e.: + +:: + + # setcap "38,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf + As a result, members of perf_users group are capable of conducting performance monitoring and observability by using functionality of the configured Perf tool executable that, when executes, passes perf_events
Quoted 71 lines · Arnaldo Carvalho de Melo
Em Tue, Apr 07, 2020 at 01:36:54PM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 46 lines
Em Tue, Apr 07, 2020 at 05:54:27PM +0300, Alexey Budankov escreveu:
Quoted 35 lines · Arnaldo Carvalho de Melo
Quoted 32 lines
Em Tue, Apr 07, 2020 at 11:30:14AM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 15 lines
[perf@five ~]$ type perf
perf is hashed (/home/perf/bin/perf)
[perf@five ~]$ getcap/home/perf/bin/perf/home/perf/bin/perf= cap_sys_ptrace,cap_syslog,38+ep
[perf@five ~]$ groups
perfperf_users
[perf@five ~]$ id
uid=1002(perf) gid=1002(perf) groups=1002(perf),1003(perf_users) context=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 [perf@five ~]$ perf top --stdio
Error:
Failed to mmap with 1 (Operation not permitted)
[perf@five ~]$ perf record -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.177 MB perf.data (1552 samples) ]Quoted 3 lines
[perf@five ~]$ perf evlist
cycles:u
[perf@five ~]$Humm, perf record falls back to cycles:u after initially trying cycles (i.e. kernel and userspace), lemme see trying 'perf top -e cycles:u', lemme test, humm not really:
[perf@five ~]$ perf top --stdio -e cycles:u
Error:
Failed to mmap with 1 (Operation not permitted) [perf@five ~]$ perf record -e cycles:u -a sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.123 MB perf.data (132 samples) ] [perf@five ~]$Quoted 1 line
Back to debugging this.
Quoted 8 lines
Could makes sense adding
cap_ipc_lockto the binary to isolate from this:
kernel/events/core.c: 6101if ((locked > lock_limit) && perf_is_paranoid() && !capable(CAP_IPC_LOCK)) { ret = -EPERM; goto unlock; }Quoted 2 lines
That did the trick, I'll update the documentation and include in my "Committer testing" section:
I ammended this to that patch, please check the wording:
- Arnaldo
Documentation/admin-guide/perf-security.rst +2
-2@@ -127,12 +127,19 @@ taken to create such groups of privileged Perf users. :: - # setcap "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" perf - # setcap -v "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" perf + # setcap "cap_perfmon,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf + # setcap -v "cap_perfmon,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf perf: OK # getcap perf perf = cap_sys_ptrace,cap_syslog,cap_perfmon+ep
Documentation/admin-guide/perf-security.rst taken to create such groups of privileged Perf users. · line 145
Quoted 10 lines
Documentation/admin-guide/perf-security.rst +7
-0+If the libcap installed doesn't yet support "cap_perfmon", use "38" instead, +i.e.: + +:: + + # setcap "38,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf + As a result, members of perf_users group are capable of conducting performance monitoring and observability by using functionality of the configured Perf tool executable that, when executes, passes perf_events
Looks good to me. The paragraph just above should then also be extended to mention that perf_events subsystem memory limit is ignored due to usage of CAP_IPC_LOCK:
"As a result, members of perf_users group are capable of conducting
performance monitoring and observability by using functionality of the configured Perf tool executable that, when executes, passes perf_events subsystem scope and perf_event_mlock_kb locking limit checks."
~Alexey
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Quoted 4 lines · Arnaldo Carvalho de Melo
Em Tue, Apr 07, 2020 at 05:54:27PM +0300, Alexey Budankov escreveu:
Quoted 3 lines · Arnaldo Carvalho de Melo
Quoted 2 lines
Em Tue, Apr 07, 2020 at 11:30:14AM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 1 line
[perf@five ~]$ type perf
<SNIP>
Quoted 27 lines
Quoted 17 lines
Quoted 15 lines
Quoted 2 lines
perf is hashed (
/home/perf/bin/perf)
[perf@five ~]$Humm, perf record falls back to cycles:u after initially trying cycles (i.e. kernel and userspace), lemme see trying 'perf top -e cycles:u', lemme test, humm not really:
[perf@five ~]$ perf top --stdio -e cycles:u
Error:
Failed to mmap with 1 (Operation not permitted) [perf@five ~]$ perf record -e cycles:u -a sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.123 MB perf.data (132 samples) ] [perf@five ~]$Quoted 1 line
Back to debugging this.
Quoted 8 lines
Could makes sense adding
cap_ipc_lockto the binary to isolate from this:
kernel/events/core.c: 6101if ((locked > lock_limit) && perf_is_paranoid() && !capable(CAP_IPC_LOCK)) { ret = -EPERM; goto unlock; }
Quoted 2 lines
That did the trick, I'll update the documentation and include in my "Committer testing" section:
Looks like top mode somehow reaches perf mmap limit described here [1]. Using -m option solves the issue avoiding cap_ipc_lock on my 8 cores machine:
perf top -e cycles -m 1
~Alexey
[1] https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html#memory-allocation
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Em Tue, Apr 07, 2020 at 07:52:56PM +0300, Alexey Budankov escreveu:
Quoted 12 lines · Arnaldo Carvalho de Melo
Quoted 9 lines
Em Tue, Apr 07, 2020 at 05:54:27PM +0300, Alexey Budankov escreveu:
Quoted 8 lines
Could makes sense adding
cap_ipc_lockto the binary to isolate from this:
kernel/events/core.c: 6101if ((locked > lock_limit) && perf_is_paranoid() && !capable(CAP_IPC_LOCK)) { ret = -EPERM; goto unlock; }
Quoted 6 lines
Quoted 2 lines
That did the trick, I'll update the documentation and include in my "Committer testing" section:
Looks like top mode somehow reaches perf mmap limit described here [1]. Using -m option solves the issue avoiding
cap_ipc_lockon my 8 cores machine:
perf top -e cycles -m 1
So this would read better?
Documentation/admin-guide/perf-security.rst +6 -2
@@ -127,8 +127,8 @@ taken to create such groups of privileged Perf users. :: - # setcap "cap_perfmon,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf - # setcap -v "cap_perfmon,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf + # setcap "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" perf + # setcap -v "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" perf perf: OK # getcap perf perf = cap_sys_ptrace,cap_syslog,cap_perfmon+ep
@@ -140,6 +140,10 @@ i.e.: # setcap "38,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf +Note that you may need to have 'cap_ipc_lock' in the mix for tools such as +'perf top', alternatively use 'perf top -m N', to reduce the memory that +it uses for the perf ring buffer, see the memory allocation section below. + As a result, members of perf_users group are capable of conducting performance monitoring and observability by using functionality of the configured Perf tool executable that, when executes, passes perf_events
Quoted 38 lines · Arnaldo Carvalho de Melo
Em Tue, Apr 07, 2020 at 07:52:56PM +0300, Alexey Budankov escreveu:
Quoted 12 lines · Arnaldo Carvalho de Melo
Quoted 9 lines
Em Tue, Apr 07, 2020 at 05:54:27PM +0300, Alexey Budankov escreveu:
Quoted 8 lines
Could makes sense adding
cap_ipc_lockto the binary to isolate from this:
kernel/events/core.c: 6101if ((locked > lock_limit) && perf_is_paranoid() && !capable(CAP_IPC_LOCK)) { ret = -EPERM; goto unlock; }Quoted 6 lines
Quoted 2 lines
That did the trick, I'll update the documentation and include in my "Committer testing" section:
Looks like top mode somehow reaches perf mmap limit described here [1]. Using -m option solves the issue avoiding
cap_ipc_lockon my 8 cores machine:
perf top -e cycles -m 1So this would read better?
Documentation/admin-guide/perf-security.rst +2
-2@@ -127,8 +127,8 @@ taken to create such groups of privileged Perf users. :: - # setcap "cap_perfmon,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf - # setcap -v "cap_perfmon,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf + # setcap "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" perf + # setcap -v "cap_perfmon,cap_sys_ptrace,cap_syslog=ep" perf perf: OK # getcap perf perf = cap_sys_ptrace,cap_syslog,cap_perfmon+ep
Documentation/admin-guide/perf-security.rst i.e.: · line 146
Quoted 7 lines
Documentation/admin-guide/perf-security.rst +4
-0@@ -140,6 +140,10 @@ i.e.: # setcap "38,cap_ipc_lock,cap_sys_ptrace,cap_syslog=ep" perf +Note that you may need to have 'cap_ipc_lock' in the mix for tools such as +'perf top', alternatively use 'perf top -m N', to reduce the memory that +it uses for the perf ring buffer, see the memory allocation section below. +
Let's stay with the first variant of you addition to this patch and also extend the paragraph below as suggested in other mail in the thread.
Documentation/admin-guide/perf-security.rst i.e.: · line 149
Quoted 4 lines
Documentation/admin-guide/perf-security.rst +0
-0As a result, members of perf_users group are capable of conducting performance monitoring and observability by using functionality of the configured Perf tool executable that, when executes, passes perf_events
Thanks,
Alexey
Em Tue, Apr 07, 2020 at 01:36:54PM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 98 lines
Em Tue, Apr 07, 2020 at 05:54:27PM +0300, Alexey Budankov escreveu:
Quoted 35 lines · Arnaldo Carvalho de Melo
Quoted 32 lines
Em Tue, Apr 07, 2020 at 11:30:14AM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 15 lines
[perf@five ~]$ type perf
perf is hashed (/home/perf/bin/perf)
[perf@five ~]$ getcap/home/perf/bin/perf/home/perf/bin/perf= cap_sys_ptrace,cap_syslog,38+ep
[perf@five ~]$ groups
perfperf_users
[perf@five ~]$ id
uid=1002(perf) gid=1002(perf) groups=1002(perf),1003(perf_users) context=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 [perf@five ~]$ perf top --stdio
Error:
Failed to mmap with 1 (Operation not permitted)
[perf@five ~]$ perf record -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.177 MB perf.data (1552 samples) ]Quoted 3 lines
[perf@five ~]$ perf evlist
cycles:u
[perf@five ~]$Humm, perf record falls back to cycles:u after initially trying cycles (i.e. kernel and userspace), lemme see trying 'perf top -e cycles:u', lemme test, humm not really:
[perf@five ~]$ perf top --stdio -e cycles:u
Error:
Failed to mmap with 1 (Operation not permitted) [perf@five ~]$ perf record -e cycles:u -a sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.123 MB perf.data (132 samples) ] [perf@five ~]$Quoted 1 line
Back to debugging this.
Quoted 8 lines
Could makes sense adding
cap_ipc_lockto the binary to isolate from this:
kernel/events/core.c: 6101if ((locked > lock_limit) && perf_is_paranoid() && !capable(CAP_IPC_LOCK)) { ret = -EPERM; goto unlock; }That did the trick, I'll update the documentation and include in my "Committer testing" section:
[perf@five ~]$ groups
perfperf_users
[perf@five ~]$ ls -lahF bin/perf
-rwxr-x---. 1 rootperf_users24M Apr 7 10:34 bin/perf* [perf@five ~]$ getcap bin/perf
bin/perf = cap_ipc_lock,cap_sys_ptrace,cap_syslog,38+ep [perf@five ~]$
[perf@five ~]$ perf top --stdioPerfTop: 652 irqs/sec kernel:73.8% exact: 99.7% lost: 0/0 drop: 0/0 [4000Hz cycles:u], (all, 12 CPUs)---------------------------------------------------------------------------------------------------------------
13.03% [kernel] [k] module_get_kallsym 5.25% [kernel] [k] kallsyms_expand_symbol.constprop.0 5.00% libc-2.30.so [.] __GI_____strtoull_l_internal 4.41% [kernel] [k] memcpy 3.42% [kernel] [k] vsnprintf 2.98% perf [.] map__process_kallsym_symbol 2.86% [kernel] [k] format_decode 2.73% [kernel] [k] number 2.70% perf [.] rb_next 2.59% perf [.] maps__split_kallsyms 2.54% [kernel] [k] string_nocheck 1.90% libc-2.30.so [.] _IO_getdelim 1.86% [kernel] [k] __x86_indirect_thunk_rax 1.53% libc-2.30.so [.] _int_malloc 1.48% libc-2.30.so [.] __memmove_avx_unaligned_erms 1.40% [kernel] [k] clear_page_rep 1.07% perf [.] rb_insert_color 1.01% libc-2.30.so [.] _IO_feof 0.99% perf [.] __dso__load_kallsyms 0.98% [kernel] [k] s_next 0.96% perf [.] __rblist__findnew 0.95% [kernel] [k] strlen 0.95% perf [.] arch__symbols__fixup_end 0.94% libpixman-1.so.0.38.4 [.] 0x000000000006f4af 0.94% perf [.] symbol__new 0.89% libpixman-1.so.0.38.4 [.] 0x000000000006f4a0 0.86% [kernel] [k] seq_read 0.81% libpixman-1.so.0.38.4 [.] 0x000000000006f4ab 0.80% perf [.] __symbols__insert 0.73% libpixman-1.so.0.38.4 [.] 0x000000000006f4a7 0.67% [kernel] [k] s_show 0.66% libc-2.30.so [.] __libc_calloc 0.61% libpixman-1.so.0.38.4 [.] 0x000000000006f4bb 0.59% [kernel] [k] get_page_from_freelist 0.59% perf [.] memcpy@plt 0.58% perf [.] eprintf
Quoted 5 lines
exiting.
[perf@five ~]$There is still something strange in here, the event is cycles:u (see at the PerfTop line, but it is getting kernel samples :-\
So running with 'perf top --stdio -vv 2> /tmp/output' I see we try create three events, the first is some capability querying, then we try to determine the max precision level, but continue with attr.exclude_kernel=1, which shouldn't be the case, perhaps we're seeing that it is not the root in the tooling part, and end up setting that to 1 as, previously, we knew it would fail, so we should switch to checking if we have cap_perfmon too, will check that:
------------------------------------------------------------perf_event_attr:
type 1 size 120 config 0x9 watermark 1 sample_id_all 1 bpf_event 1
{ wakeup_events, wakeup_watermark } 1
------------------------------------------------------------
------------------------------------------------------------perf_event_attr:
size 120
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|CPU|PERIOD
read_format ID
disabled 1
inherit 1
exclude_kernel 1
mmap 1
comm 1
freq 1
task 1
precise_ip 3
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1
------------------------------------------------------------
------------------------------------------------------------
perf_event_attr:
size 120
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|CPU|PERIOD
read_format ID
disabled 1
inherit 1
exclude_kernel 1
mmap 1
comm 1
freq 1
task 1
precise_ip 2
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1------------------------------------------------------------
But then, even with that attr.exclude_kernel set to 1 we _still_ get kernel samples, which looks like another bug, now trying with strace, which leads us to another rabbit hole:
[perf@five ~]$ strace -e perf_event_open -o /tmp/out.put perf top --stdio Error:
You may not have permission to collect system-wide stats.
Consider tweaking /proc/sys/kernel/perf_event_paranoid, which controls use of the performance events system by unprivileged users (without CAP_PERFMON or CAP_SYS_ADMIN).
The current value is 2:
-1: Allow use of (almost) all events by all users
Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK
Quoted 1 line
= 0: Disallow ftrace function tracepoint by users without
CAP_PERFMONorCAP_SYS_ADMIN
Disallow raw tracepoint access by users without CAP_SYS_PERFMON or CAP_SYS_ADMIN
Quoted 2 lines
= 1: Disallow CPU event access by users without
CAP_PERFMONorCAP_SYS_ADMIN= 2: Disallow kernel profiling by users withoutCAP_PERFMONorCAP_SYS_ADMIN
To make this setting permanent, edit /etc/sysctl.conf too, e.g.:
kernel.perf_event_paranoid = -1
[perf@five ~]$
If I remove that strace -e ... from the front, 'perf top' is back working as a non-cap_sys_admin user, just with cap_perfmon.
- Arnaldo
Em Tue, Apr 07, 2020 at 01:56:43PM -0300, Arnaldo Carvalho de Melo escreveu:
Quoted 22 lines
But then, even with that attr.exclude_kernel set to 1 we _still_ get kernel samples, which looks like another bug, now trying with strace, which leads us to another rabbit hole:
[perf@five ~]$ strace -e
perf_event_open-o/tmp/out.putperf top --stdio Error:
You may not have permission to collect system-wide stats.Consider tweaking
/proc/sys/kernel/perf_event_paranoid, which controls use of the performance events system by unprivileged users (withoutCAP_PERFMONorCAP_SYS_ADMIN).The current value is 2:
-1: Allow use of (almost) all events by all users
Ignore mlock limit afterperf_event_mlock_kbwithoutCAP_IPC_LOCKQuoted 1 line
= 0: Disallow ftrace function tracepoint by users without
CAP_PERFMONorCAP_SYS_ADMINDisallow raw tracepoint access by users without
CAP_SYS_PERFMONorCAP_SYS_ADMINQuoted 2 lines
= 1: Disallow CPU event access by users without
CAP_PERFMONorCAP_SYS_ADMIN= 2: Disallow kernel profiling by users withoutCAP_PERFMONorCAP_SYS_ADMIN
Quoted 9 lines
To make this setting permanent, edit
/etc/sysctl.conftoo, e.g.:kernel.perf_event_paranoid = -1
[perf@five ~]$
If I remove that strace -e ... from the front, 'perf top' is back working as a non-cap_sys_admin user, just with
cap_perfmon.
So I couldn't figure it out so far why is that exclude_kernel is being set to 1, as perf-top when no event is passed defaults to this to find out what to use as a default event:
perf_evlist__add_default(top.evlist)
perf_evsel__new_cycles(true);
struct perf_event_attr attr = {
.type = PERF_TYPE_HARDWARE,
.config = PERF_COUNT_HW_CPU_CYCLES,
.exclude_kernel = !perf_event_can_profile_kernel(),
};
perf_event_paranoid_check(1);
return perf_cap__capable(CAP_SYS_ADMIN) ||
perf_cap__capable(CAP_PERFMON) ||
perf_event_paranoid() <= max_level;And then that second condition should hold true, it returns true, and then .exclude_kernel should be set to !true -> zero.o
Now the wallclock says I need to stop being a programmer and turn into a daycare provider for Pedro, cya!
- Arnaldo
Patchwork
CI[Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Introduce CAP_PERFMON to secure system performance monitoring and observability (rev18)
In reply to Alexey Budankov== Series Details ==
== Series Details ==
Series: Introduce CAP_PERFMON to secure system performance monitoring and observability (rev18)
URL : https://patchwork.freedesktop.org/series/72273/
State : warning
== Summary ==
$ dim checkpatch origin/drm-tip
f036c99151ab capabilities: Introduce CAP_PERFMON to kernel and user space
-:8: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit fatal: bad o ("96d77665c15889c36")'
#8:
Commit-ID: 980737282232b752bb14dab96d77665c15889c36-:9: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #9:
Gitweb: https://git.kernel.org/tip/980737282232b752bb14dab96d77665c15889c36
-:137: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'tip-bot2 for Alexey Budankov <[email protected]>'
total: 1 errors, 2 warnings, 0 checks, 36 lines checked64cddb3c59c7 perf/core: Open access to the core for CAP_PERFMON privileged process
-:9: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit fatal: bad o ("9b835314d2b071cc2")' #9:
Commit-ID: 18aa18566218d4a46d940049b835314d2b071cc2
-:10: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #10:
Gitweb: https://git.kernel.org/tip/18aa18566218d4a46d940049b835314d2b071cc2
-:100: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'tip-bot2 for Alexey Budankov <[email protected]>'
total: 1 errors, 2 warnings, 0 checks, 32 lines checked0bb591638827 perf/core: open access to probes for CAP_PERFMON privileged process
-:9: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit fatal: bad o ("3ff8722e79ecf4088")' #9:
Commit-ID: c9e0924e5c2b59365f9c0d43ff8722e79ecf4088
-:10: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #10:
Gitweb: https://git.kernel.org/tip/c9e0924e5c2b59365f9c0d43ff8722e79ecf4088
-:83: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'tip-bot2 for Alexey Budankov <[email protected]>'
total: 1 errors, 2 warnings, 0 checks, 16 lines checked9ded613d59ba perf tools: Support CAP_PERFMON capability
-:8: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit fatal: bad o ("fa1dd1fcb84f2504c")' #8:
Commit-ID: 6b3e0e2e04615df128b2d38fa1dd1fcb84f2504c
-:9: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #9:
Gitweb: https://git.kernel.org/tip/6b3e0e2e04615df128b2d38fa1dd1fcb84f2504c
-:41: ERROR:DIFF_IN_COMMIT_MSG: Avoid using diff content in the commit message - patch(1) might not work #41:
--- a/libcap/include/uapi/linux/capability.h
-:248: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'tip-bot2 for Alexey Budankov <[email protected]>'
total: 2 errors, 2 warnings, 0 checks, 56 lines checkedd2eaa8483797 drm/i915/perf: Open access for CAP_PERFMON privileged process
-:8: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit fatal: bad o ("d7c5309b814281ae3")' #8:
Commit-ID: 4e3d3456b78fa5a70e65de0d7c5309b814281ae3
-:9: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #9:
Gitweb: https://git.kernel.org/tip/4e3d3456b78fa5a70e65de0d7c5309b814281ae3
-:101: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'tip-bot2 for Alexey Budankov <[email protected]>'
total: 1 errors, 2 warnings, 0 checks, 39 lines checked14afa15c555f trace/bpf_trace: Open access for CAP_PERFMON privileged process
-:9: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit fatal: bad o ("3ab0abe10a7e68ea1")' #9:
Commit-ID: 031258da05956646c5606023ab0abe10a7e68ea1
-:10: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #10:
Gitweb: https://git.kernel.org/tip/031258da05956646c5606023ab0abe10a7e68ea1
-:67: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'tip-bot2 for Alexey Budankov <[email protected]>'
total: 1 errors, 2 warnings, 0 checks, 8 lines checked092f35fb8dec powerpc/perf: open access for CAP_PERFMON privileged process
-:8: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit fatal: bad o ("3e6ead32843999511")' #8:
Commit-ID: ff46758313e688fca7d762b3e6ead32843999511
-:9: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #9:
Gitweb: https://git.kernel.org/tip/ff46758313e688fca7d762b3e6ead32843999511
-:75: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'tip-bot2 for Alexey Budankov <[email protected]>'
total: 1 errors, 2 warnings, 0 checks, 16 lines checked2b530591caa3 parisc/perf: open access for CAP_PERFMON privileged process
-:8: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit fatal: bad o ("21ed0e4bb1ab3b382")' #8:
Commit-ID: cf91baf3f7f39a0cd29072e21ed0e4bb1ab3b382
-:9: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #9:
Gitweb: https://git.kernel.org/tip/cf91baf3f7f39a0cd29072e21ed0e4bb1ab3b382
-:66: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'tip-bot2 for Alexey Budankov <[email protected]>'
total: 1 errors, 2 warnings, 0 checks, 8 lines checked10e972d65247 drivers/perf: Open access for CAP_PERFMON privileged process
-:8: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit fatal: bad o ("7130b4c06ab4d412f")' #8:
Commit-ID: cea7d0d4a59b4efd0e1fe067130b4c06ab4d412f
-:9: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #9:
Gitweb: https://git.kernel.org/tip/cea7d0d4a59b4efd0e1fe067130b4c06ab4d412f
-:75: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'tip-bot2 for Alexey Budankov <[email protected]>'
total: 1 errors, 2 warnings, 0 checks, 16 lines checked33c94226c35f drivers/oprofile: Open access for CAP_PERFMON privileged process
-:9: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit fatal: bad o ("68387f4373a58c949")' #9:
Commit-ID: ab76878bb720cbd35a05ae868387f4373a58c949
-:10: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #10:
Gitweb: https://git.kernel.org/tip/ab76878bb720cbd35a05ae868387f4373a58c949
-:66: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'tip-bot2 for Alexey Budankov <[email protected]>'
total: 1 errors, 2 warnings, 0 checks, 8 lines checkedb3c0c8dc3225 doc/admin-guide: Update perf-security.rst with CAP_PERFMON information
-:9: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit fatal: bad o ("06b01be2f0f7ef2e4")' #9:
Commit-ID: 902a8dcc5ba6c5dc3332e8806b01be2f0f7ef2e4
-:10: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #10:
Gitweb: https://git.kernel.org/tip/902a8dcc5ba6c5dc3332e8806b01be2f0f7ef2e4
-:231: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'tip-bot2 for Alexey Budankov <[email protected]>'
total: 1 errors, 2 warnings, 0 checks, 144 lines checkedd13256e76cf3 doc/admin-guide: update kernel.rst with CAP_PERFMON information
-:9: ERROR:GIT_COMMIT_ID: Please use git commit description style 'commit <12+ chars of sha1> ("<title line>")' - ie: 'commit fatal: bad o ("399d669438c63b6ce")' #9:
Commit-ID: 025b16f81dd7f51f29d0109399d669438c63b6ce
-:10: WARNING:COMMIT_LOG_LONG_LINE: Possible unwrapped commit description (prefer a maximum 75 chars per line) #10:
Gitweb: https://git.kernel.org/tip/025b16f81dd7f51f29d0109399d669438c63b6ce
-:78: WARNING:NO_AUTHOR_SIGN_OFF: Missing Signed-off-by: line by nominal patch author 'tip-bot2 for Alexey Budankov <[email protected]>'
total: 1 errors, 2 warnings, 0 checks, 31 lines checked
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Patchwork
CI[Intel-gfx] ✗ Fi.CI.BAT: failure for Introduce CAP_PERFMON to secure system performance monitoring and observability (rev18)
In reply to Alexey Budankov== Series Details ==
== Series Details ==
Series: Introduce CAP_PERFMON to secure system performance monitoring and observability (rev18)
URL : https://patchwork.freedesktop.org/series/72273/
State : failure
== Summary ==
CI Bug Log - changes from CI_DRM_8350 -> Patchwork_17428
====================================================
Summary
-------
**FAILURE**
Serious unknown changes coming with Patchwork_17428 absolutely need to be verified manually.
If you think the reported changes have nothing to do with the changes introduced in Patchwork_17428, please notify your bug team to allow them to document this new failure mode, which will reduce false positives in CI.
External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17428/index.html
Possible new issues
-------------------
Here are the unknown changes that may have been introduced in Patchwork_17428:
### IGT changes ###
#### Possible regressions ####
* igt@i915_selftest@live@gt_engines:
- fi-byt-j1900: [PASS][1] -> [FAIL][2]
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/fi-byt-j1900/igt@i915_selftest@live@gt_engines.html
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17428/fi-byt-j1900/igt@i915_selftest@live@gt_engines.html
Known issues
------------
Here are the changes found in Patchwork_17428 that come from known issues:
### IGT changes ###
#### Issues hit ####
* igt@i915_selftest@live@coherency:
- fi-ivb-3770: [PASS][3] -> [FAIL][4] ([i915#1763])
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/fi-ivb-3770/igt@i915_selftest@[email protected]
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17428/fi-ivb-3770/igt@i915_selftest@[email protected]
#### Warnings ####
* igt@i915_pm_rpm@module-reload:
- fi-kbl-x1275: [FAIL][5] ([i915#62]) -> [SKIP][6] ([fdo#109271])
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8350/fi-kbl-x1275/igt@[email protected]
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17428/fi-kbl-x1275/igt@[email protected]
[fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271
[i915#1763]: https://gitlab.freedesktop.org/drm/intel/issues/1763
[i915#62]: https://gitlab.freedesktop.org/drm/intel/issues/62
Participating hosts (48 -> 42)
------------------------------
Additional (1): fi-icl-dsi
Missing (7): fi-cml-u2 fi-hsw-4200u fi-byt-squawks fi-bsw-cyan fi-kbl-7500u fi-byt-clapper fi-bdw-samus
Build changes
-------------
* CI: CI-20190529 -> None
* Linux: CI_DRM_8350 -> Patchwork_17428
CI-20190529: 20190529
CI_DRM_8350: 018bab6d1c4ac37bff9306384383fab59750e140 @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_5606: 678afb3954bec6227c8762756a0ad6d9946d49b2 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
Patchwork_17428: d13256e76cf361a2b4e954ce8790725c3021cc62 @ git://anongit.freedesktop.org/gfx-ci/linux
== Linux commits ==
d13256e76cf3 doc/admin-guide: update kernel.rst with CAP_PERFMON information b3c0c8dc3225 doc/admin-guide: Update perf-security.rst with CAP_PERFMON information 33c94226c35f drivers/oprofile: Open access for CAP_PERFMON privileged process 10e972d65247 drivers/perf: Open access for CAP_PERFMON privileged process 2b530591caa3 parisc/perf: open access for CAP_PERFMON privileged process 092f35fb8dec powerpc/perf: open access for CAP_PERFMON privileged process 14afa15c555f trace/bpf_trace: Open access for CAP_PERFMON privileged process d2eaa8483797 drm/i915/perf: Open access for CAP_PERFMON privileged process 9ded613d59ba perf tools: Support CAP_PERFMON capability0bb591638827 perf/core: open access to probes for CAP_PERFMON privileged process 64cddb3c59c7 perf/core: Open access to the core for CAP_PERFMON privileged process f036c99151ab capabilities: Introduce CAP_PERFMON to kernel and user space
== Logs ==
For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17428/index.html
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Hi Alexey,
Quoted 9 lines
Currently access to
perf_events,i915_perfand other performance monitoring and observability subsystems of the kernel is open only for a privileged process [1] withCAP_SYS_ADMINcapability enabled in the process effective set [2].This patch set introduces
CAP_PERFMONcapability designed to secure system performance monitoring and observability operations so thatCAP_PERFMONwould assistCAP_SYS_ADMINcapability in its governing role for performance monitoring and observability subsystems of the kernel.
I'm seeing an issue with CAP_PERFMON when I try to record data for a specific target. I don't know whether this is sort of a regression or an expected behavior.
Without setting CAP_PERFMON:
$ getcap ./perf
$ ./perf stat -a ls
Error:
Access to performance monitoring and observability operations is limited.
$ ./perf stat ls
Performance counter stats for 'ls': 2.06 msec task-clock:u # 0.418 CPUs utilized
0 context-switches:u # 0.000 K/sec
0 cpu-migrations:u # 0.000 K/secWith CAP_PERFMON:
$ getcap ./perf
./perf = cap_perfmon+ep
$ ./perf stat -a ls
Performance counter stats for 'system wide': 142.42 msec cpu-clock # 25.062 CPUs utilized
182 context-switches # 0.001 M/sec
48 cpu-migrations # 0.337 K/sec
$ ./perf stat ls
Error:
Access to performance monitoring and observability operations is limited.Am I missing something silly?
Analysis:
---------
A bit more analysis lead me to below kernel code fs/exec.c:
begin_new_exec()
{
...
if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP ||
!(uid_eq(current_euid(), current_uid()) &&
gid_eq(current_egid(), current_gid())))
set_dumpable(current->mm, suid_dumpable);
else
set_dumpable(current->mm, SUID_DUMP_USER); ...
commit_creds(bprm->cred);}
When I execute './perf stat ls', it's going into else condition and thus sets dumpable flag as SUID_DUMP_USER. Then in commit_creds():
int commit_creds(struct cred *new)
{
...
/* dumpability changes */
if (...
!cred_cap_issubset(old, new)) {
if (task->mm)
set_dumpable(task->mm, suid_dumpable);
}!cred_cap_issubset(old, new) fails for perf without any capability and thus it doesn't execute set_dumpable(). Whereas that condition passes for perf with CAP_PERFMON and thus it overwrites old value (SUID_DUMP_USER) with suid_dumpable in mm_flags. On an Ubuntu, suid_dumpable default value is SUID_DUMP_ROOT. On Fedora, it's SUID_DUMP_DISABLE. (/proc/sys/fs/suid_dumpable).
Now while opening an event:
perf_event_open()
ptrace_may_access()
__ptrace_may_access() {
...
if (mm &&
((get_dumpable(mm) != SUID_DUMP_USER) &&
!ptrace_has_cap(cred, mm->user_ns, mode)))
return -EPERM;
}This if condition passes for perf with CAP_PERFMON and thus it returns -EPERM. But it fails for perf without CAP_PERFMON and thus it goes ahead and returns success. So opening an event fails when perf has CAP_PREFMON and tries to open process specific event as normal user.
Workarounds:
------------
Based on above analysis, I found couple of workarounds (examples are on Ubuntu 18.04.4 powerpc):
Workaround1:
Setting SUID_DUMP_USER as default (in /proc/sys/fs/suid_dumpable) solves the issue.
# echo 1 > /proc/sys/fs/suid_dumpable
$ getcap ./perf
./perf = cap_perfmon+ep
$ ./perf stat ls
Performance counter stats for 'ls': 1.47 msec task-clock # 0.806 CPUs utilized
0 context-switches # 0.000 K/sec
0 cpu-migrations # 0.000 K/secWorkaround2:
Using CAP_SYS_PTRACE along with CAP_PERFMON solves the issue.
$ cat /proc/sys/fs/suid_dumpable
2
# setcap "cap_perfmon,cap_sys_ptrace=ep" ./perf
$ ./perf stat ls
Performance counter stats for 'ls': 1.41 msec task-clock # 0.826 CPUs utilized
0 context-switches # 0.000 K/sec
0 cpu-migrations # 0.000 K/secWorkaround3:
Adding CAP_PERFMON to parent of perf (/bin/bash) also solves the issue.
$ cat /proc/sys/fs/suid_dumpable
2
# setcap "cap_perfmon=ep" /bin/bash
# setcap "cap_perfmon=ep" ./perf
$ bash
$ ./perf stat ls
Performance counter stats for 'ls': 1.47 msec task-clock # 0.806 CPUs utilized
0 context-switches # 0.000 K/sec
0 cpu-migrations # 0.000 K/sec- Ravi
Hi Ravi,
Quoted 7 lines · Ravi Bangoria
Hi Alexey,
Quoted 5 lines
Currently access to
perf_events,i915_perfand other performance monitoring and observability subsystems of the kernel is open only for a privileged process [1] withCAP_SYS_ADMINcapability enabled in the process effective set [2].
Quoted 8 lines
Quoted 4 lines
This patch set introduces
CAP_PERFMONcapability designed to secure system performance monitoring and observability operations so thatCAP_PERFMONwould assistCAP_SYS_ADMINcapability in its governing role for performance monitoring and observability subsystems of the kernel.I'm seeing an issue with
CAP_PERFMONwhen I try to record data for a specific target. I don't know whether this is sort of a regression or an expected behavior.
Thanks for reporting and root causing this case. The behavior looks like kind of expected since currently CAP_PERFMON takes over the related part of CAP_SYS_ADMIN credentials only. Actually Perf security docs [1] say that access control is also subject to CAP_SYS_PTRACE credentials.
CAP_PERFMON could be used to extend and substitute ptrace_may_access() check in perf_events subsystem to simplify user experience at least in this specific case.
Alexei
[1] https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html
Quoted 126 lines
Without setting
CAP_PERFMON:$ getcap ./perf $ ./perf stat -a ls Error: Access to performance monitoring and observability operations is limited. $ ./perf stat ls Performance counter stats for 'ls': 2.06 msec task-clock:u # 0.418 CPUs utilized 0 context-switches:u # 0.000 K/sec 0 cpu-migrations:u # 0.000 K/secWith
CAP_PERFMON:$ getcap ./perf ./perf = cap_perfmon+ep $ ./perf stat -a ls Performance counter stats for 'system wide': 142.42 msec cpu-clock # 25.062 CPUs utilized 182 context-switches # 0.001 M/sec 48 cpu-migrations # 0.337 K/sec $ ./perf stat ls Error: Access to performance monitoring and observability operations is limited.Am I missing something silly?
Analysis:
---------
A bit more analysis lead me to below kernel codefs/exec.c:
begin_new_exec()
{
...
if (bprm->interp_flags&BINPRM_FLAGS_ENFORCE_NONDUMP|| !(uid_eq(current_euid(),current_uid()) &&gid_eq(current_egid(), current_gid())))set_dumpable(current->mm, suid_dumpable); else
set_dumpable(current->mm, SUID_DUMP_USER);...
commit_creds(bprm->cred);
}When I execute './perf stat ls', it's going into else condition and thus sets dumpable flag as
SUID_DUMP_USER. Then incommit_creds():int
commit_creds(struct cred *new)
{
...
/* dumpability changes */
if (...
!cred_cap_issubset(old, new)) {
if (task->mm)
set_dumpable(task->mm, suid_dumpable); }!cred_cap_issubset(old, new) fails for perf without any capability and thus it doesn't execute
set_dumpable(). Whereas that condition passes for perf withCAP_PERFMONand thus it overwrites old value (SUID_DUMP_USER) withsuid_dumpableinmm_flags. On an Ubuntu,suid_dumpabledefault value isSUID_DUMP_ROOT. On Fedora, it'sSUID_DUMP_DISABLE. (/proc/sys/fs/suid_dumpable).Now while opening an event:
perf_event_open()
ptrace_may_access()
__ptrace_may_access(){
...
if (mm &&
((get_dumpable(mm)!=SUID_DUMP_USER) && !ptrace_has_cap(cred,mm->user_ns, mode))) return-EPERM;
}This if condition passes for perf with
CAP_PERFMONand thus it returns-EPERM. But it fails for perf withoutCAP_PERFMONand thus it goes ahead and returns success. So opening an event fails when perf hasCAP_PREFMONand tries to open process specific event as normal user.Workarounds:
------------
Based on above analysis, I found couple of workarounds (examples are on Ubuntu 18.04.4 powerpc):Workaround1:
SettingSUID_DUMP_USERas default (in/proc/sys/fs/suid_dumpable) solves the issue.# echo 1 > /proc/sys/fs/suid_dumpable $ getcap ./perf ./perf = cap_perfmon+ep $ ./perf stat ls Performance counter stats for 'ls': 1.47 msec task-clock # 0.806 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/secWorkaround2:
UsingCAP_SYS_PTRACEalong withCAP_PERFMONsolves the issue.$ cat /proc/sys/fs/suid_dumpable 2 # setcap "cap_perfmon,cap_sys_ptrace=ep" ./perf $ ./perf stat ls Performance counter stats for 'ls': 1.41 msec task-clock # 0.826 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/secWorkaround3:
AddingCAP_PERFMONto parent of perf (/bin/bash) also solves the issue.$ cat /proc/sys/fs/suid_dumpable 2 # setcap "cap_perfmon=ep" /bin/bash # setcap "cap_perfmon=ep" ./perf $ bash $ ./perf stat ls Performance counter stats for 'ls': 1.47 msec task-clock # 0.806 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/sec
Quoted 1 line
- Ravi
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Arnaldo Carvalho de Melo
maintainerEm Fri, Jul 10, 2020 at 05:30:50PM +0300, Alexey Budankov escreveu:
Quoted 11 lines · Ravi Bangoria
Quoted 9 lines
Quoted 9 lines
Currently access to
perf_events,i915_perfand other performance monitoring and observability subsystems of the kernel is open only for a privileged process [1] withCAP_SYS_ADMINcapability enabled in the process effective set [2].This patch set introduces
CAP_PERFMONcapability designed to secure system performance monitoring and observability operations so thatCAP_PERFMONwould assistCAP_SYS_ADMINcapability in its governing role for performance monitoring and observability subsystems of the kernel.
Quoted 8 lines
Quoted 3 lines
I'm seeing an issue with
CAP_PERFMONwhen I try to record data for a specific target. I don't know whether this is sort of a regression or an expected behavior.Thanks for reporting and root causing this case. The behavior looks like kind of expected since currently
CAP_PERFMONtakes over the related part ofCAP_SYS_ADMINcredentials only. Actually Perf security docs [1] say that access control is also subject toCAP_SYS_PTRACEcredentials.
I think that stating that in the error message would be helpful, after all, who reads docs? 8-)
I.e., this:
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. $
Could become:
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. Right now only CAP_PERFMON is granted, you may need CAP_SYS_PTRACE. $
- Arnaldo
Quoted 135 lines
CAP_PERFMONcould be used to extend and substituteptrace_may_access()check inperf_eventssubsystem to simplify user experience at least in this specific case.Alexei
[1] https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html
Quoted 127 lines
Without setting
CAP_PERFMON:$ getcap ./perf $ ./perf stat -a ls Error: Access to performance monitoring and observability operations is limited. $ ./perf stat ls Performance counter stats for 'ls': 2.06 msec task-clock:u # 0.418 CPUs utilized 0 context-switches:u # 0.000 K/sec 0 cpu-migrations:u # 0.000 K/secWith
CAP_PERFMON:$ getcap ./perf ./perf = cap_perfmon+ep $ ./perf stat -a ls Performance counter stats for 'system wide': 142.42 msec cpu-clock # 25.062 CPUs utilized 182 context-switches # 0.001 M/sec 48 cpu-migrations # 0.337 K/sec $ ./perf stat ls Error: Access to performance monitoring and observability operations is limited.Am I missing something silly?
Analysis:
---------
A bit more analysis lead me to below kernel codefs/exec.c:
begin_new_exec()
{
...
if (bprm->interp_flags&BINPRM_FLAGS_ENFORCE_NONDUMP|| !(uid_eq(current_euid(),current_uid()) &&gid_eq(current_egid(), current_gid())))set_dumpable(current->mm, suid_dumpable); else
set_dumpable(current->mm, SUID_DUMP_USER);...
commit_creds(bprm->cred);
}When I execute './perf stat ls', it's going into else condition and thus sets dumpable flag as
SUID_DUMP_USER. Then incommit_creds():int
commit_creds(struct cred *new)
{
...
/* dumpability changes */
if (...
!cred_cap_issubset(old, new)) {
if (task->mm)
set_dumpable(task->mm, suid_dumpable); }!cred_cap_issubset(old, new) fails for perf without any capability and thus it doesn't execute
set_dumpable(). Whereas that condition passes for perf withCAP_PERFMONand thus it overwrites old value (SUID_DUMP_USER) withsuid_dumpableinmm_flags. On an Ubuntu,suid_dumpabledefault value isSUID_DUMP_ROOT. On Fedora, it'sSUID_DUMP_DISABLE. (/proc/sys/fs/suid_dumpable).Now while opening an event:
perf_event_open()
ptrace_may_access()
__ptrace_may_access(){
...
if (mm &&
((get_dumpable(mm)!=SUID_DUMP_USER) && !ptrace_has_cap(cred,mm->user_ns, mode))) return-EPERM;
}This if condition passes for perf with
CAP_PERFMONand thus it returns-EPERM. But it fails for perf withoutCAP_PERFMONand thus it goes ahead and returns success. So opening an event fails when perf hasCAP_PREFMONand tries to open process specific event as normal user.Workarounds:
------------
Based on above analysis, I found couple of workarounds (examples are on Ubuntu 18.04.4 powerpc):Workaround1:
SettingSUID_DUMP_USERas default (in/proc/sys/fs/suid_dumpable) solves the issue.# echo 1 > /proc/sys/fs/suid_dumpable $ getcap ./perf ./perf = cap_perfmon+ep $ ./perf stat ls Performance counter stats for 'ls': 1.47 msec task-clock # 0.806 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/secWorkaround2:
UsingCAP_SYS_PTRACEalong withCAP_PERFMONsolves the issue.$ cat /proc/sys/fs/suid_dumpable 2 # setcap "cap_perfmon,cap_sys_ptrace=ep" ./perf $ ./perf stat ls Performance counter stats for 'ls': 1.41 msec task-clock # 0.826 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/secWorkaround3:
AddingCAP_PERFMONto parent of perf (/bin/bash) also solves the issue.$ cat /proc/sys/fs/suid_dumpable 2 # setcap "cap_perfmon=ep" /bin/bash # setcap "cap_perfmon=ep" ./perf $ bash $ ./perf stat ls Performance counter stats for 'ls': 1.47 msec task-clock # 0.806 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/sec- Ravi
Signature · 1 line
- Arnaldo
Quoted 16 lines · Arnaldo Carvalho de Melo
Em Fri, Jul 10, 2020 at 05:30:50PM +0300, Alexey Budankov escreveu:
Quoted 14 lines · Ravi Bangoria
Quoted 13 lines
Quoted 9 lines
Currently access to
perf_events,i915_perfand other performance monitoring and observability subsystems of the kernel is open only for a privileged process [1] withCAP_SYS_ADMINcapability enabled in the process effective set [2].This patch set introduces
CAP_PERFMONcapability designed to secure system performance monitoring and observability operations so thatCAP_PERFMONwould assistCAP_SYS_ADMINcapability in its governing role for performance monitoring and observability subsystems of the kernel.I'm seeing an issue with
CAP_PERFMONwhen I try to record data for a specific target. I don't know whether this is sort of a regression or an expected behavior.
Quoted 7 lines
Quoted 4 lines
Thanks for reporting and root causing this case. The behavior looks like kind of expected since currently
CAP_PERFMONtakes over the related part ofCAP_SYS_ADMINcredentials only. Actually Perf security docs [1] say that access control is also subject toCAP_SYS_PTRACEcredentials.I think that stating that in the error message would be helpful, after all, who reads docs? 8-)
At least those who write it :D ...
Quoted 8 lines
I.e., this:
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. $
Quoted 7 lines
Could become:
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. Right now only CAP_PERFMON is granted, you may need CAP_SYS_PTRACE. $
It would better provide reference to perf security docs in the tool output. Looks like extending ptrace_may_access() check for perf_events with CAP_PERFMON makes monitoring simpler and even more secure to use since Perf tool need not to start/stop/single-step and read/write registers and memory and so on like a debugger or strace-like tool. What do you think?
Alexei
Quoted 139 lines
- Arnaldo
Quoted 135 lines
CAP_PERFMONcould be used to extend and substituteptrace_may_access()check inperf_eventssubsystem to simplify user experience at least in this specific case.Alexei
[1] https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html
Quoted 127 lines
Without setting
CAP_PERFMON:$ getcap ./perf $ ./perf stat -a ls Error: Access to performance monitoring and observability operations is limited. $ ./perf stat ls Performance counter stats for 'ls': 2.06 msec task-clock:u # 0.418 CPUs utilized 0 context-switches:u # 0.000 K/sec 0 cpu-migrations:u # 0.000 K/secWith
CAP_PERFMON:$ getcap ./perf ./perf = cap_perfmon+ep $ ./perf stat -a ls Performance counter stats for 'system wide': 142.42 msec cpu-clock # 25.062 CPUs utilized 182 context-switches # 0.001 M/sec 48 cpu-migrations # 0.337 K/sec $ ./perf stat ls Error: Access to performance monitoring and observability operations is limited.Am I missing something silly?
Analysis:
---------
A bit more analysis lead me to below kernel codefs/exec.c:
begin_new_exec()
{
...
if (bprm->interp_flags&BINPRM_FLAGS_ENFORCE_NONDUMP|| !(uid_eq(current_euid(),current_uid()) &&gid_eq(current_egid(), current_gid())))set_dumpable(current->mm, suid_dumpable); else
set_dumpable(current->mm, SUID_DUMP_USER);...
commit_creds(bprm->cred);
}When I execute './perf stat ls', it's going into else condition and thus sets dumpable flag as
SUID_DUMP_USER. Then incommit_creds():int
commit_creds(struct cred *new)
{
...
/* dumpability changes */
if (...
!cred_cap_issubset(old, new)) {
if (task->mm)
set_dumpable(task->mm, suid_dumpable); }!cred_cap_issubset(old, new) fails for perf without any capability and thus it doesn't execute
set_dumpable(). Whereas that condition passes for perf withCAP_PERFMONand thus it overwrites old value (SUID_DUMP_USER) withsuid_dumpableinmm_flags. On an Ubuntu,suid_dumpabledefault value isSUID_DUMP_ROOT. On Fedora, it'sSUID_DUMP_DISABLE. (/proc/sys/fs/suid_dumpable).Now while opening an event:
perf_event_open()
ptrace_may_access()
__ptrace_may_access(){
...
if (mm &&
((get_dumpable(mm)!=SUID_DUMP_USER) && !ptrace_has_cap(cred,mm->user_ns, mode))) return-EPERM;
}This if condition passes for perf with
CAP_PERFMONand thus it returns-EPERM. But it fails for perf withoutCAP_PERFMONand thus it goes ahead and returns success. So opening an event fails when perf hasCAP_PREFMONand tries to open process specific event as normal user.Workarounds:
------------
Based on above analysis, I found couple of workarounds (examples are on Ubuntu 18.04.4 powerpc):Workaround1:
SettingSUID_DUMP_USERas default (in/proc/sys/fs/suid_dumpable) solves the issue.# echo 1 > /proc/sys/fs/suid_dumpable $ getcap ./perf ./perf = cap_perfmon+ep $ ./perf stat ls Performance counter stats for 'ls': 1.47 msec task-clock # 0.806 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/secWorkaround2:
UsingCAP_SYS_PTRACEalong withCAP_PERFMONsolves the issue.$ cat /proc/sys/fs/suid_dumpable 2 # setcap "cap_perfmon,cap_sys_ptrace=ep" ./perf $ ./perf stat ls Performance counter stats for 'ls': 1.41 msec task-clock # 0.826 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/secWorkaround3:
AddingCAP_PERFMONto parent of perf (/bin/bash) also solves the issue.$ cat /proc/sys/fs/suid_dumpable 2 # setcap "cap_perfmon=ep" /bin/bash # setcap "cap_perfmon=ep" ./perf $ bash $ ./perf stat ls Performance counter stats for 'ls': 1.47 msec task-clock # 0.806 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/sec- Ravi
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Arnaldo Carvalho de Melo
maintainerEm Mon, Jul 13, 2020 at 12:48:25PM +0300, Alexey Budankov escreveu:
Quoted 23 lines · Arnaldo Carvalho de Melo
Quoted 20 lines
Em Fri, Jul 10, 2020 at 05:30:50PM +0300, Alexey Budankov escreveu:
Quoted 19 lines · Ravi Bangoria
Quoted 5 lines
Quoted 4 lines
Currently access to
perf_events,i915_perfand other performance monitoring and observability subsystems of the kernel is open only for a privileged process [1] withCAP_SYS_ADMINcapability enabled in the process effective set [2].Quoted 8 lines
Quoted 4 lines
This patch set introduces
CAP_PERFMONcapability designed to secure system performance monitoring and observability operations so thatCAP_PERFMONwould assistCAP_SYS_ADMINcapability in its governing role for performance monitoring and observability subsystems of the kernel.I'm seeing an issue with
CAP_PERFMONwhen I try to record data for a specific target. I don't know whether this is sort of a regression or an expected behavior.Thanks for reporting and root causing this case. The behavior looks like kind of expected since currently
CAP_PERFMONtakes over the related part ofCAP_SYS_ADMINcredentials only. Actually Perf security docs [1] say that access control is also subject toCAP_SYS_PTRACEcredentials.
Quoted 4 lines
Quoted 2 lines
I think that stating that in the error message would be helpful, after all, who reads docs? 8-)
At least those who write it :D ...
Everybody should read it, sure :-)
Quoted 9 lines
Quoted 9 lines
I.e., this:
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. $Could become:
Quoted 7 lines
Quoted 5 lines
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. Right now only CAP_PERFMON is granted, you may need CAP_SYS_PTRACE. $It would better provide reference to perf security docs in the tool output.
So add a 3rd line:
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. Right now only CAP_PERFMON is granted, you may need CAP_SYS_PTRACE. Please read the 'Perf events and tool security' document: https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html
Quoted 1 line
Looks like extending
ptrace_may_access()check forperf_eventswithCAP_PERFMON
You mean the following?
kernel/events/core.c +1 -1
@@ -11595,7 +11595,7 @@ SYSCALL_DEFINE5(perf_event_open,* perf_event_exit_task() that could imply). */ err = -EACCES ; -if (!ptrace_may_access (task,PTRACE_MODE_READ_REALCREDS )) +if (!perfmon_capable () && !ptrace_may_access (task,PTRACE_MODE_READ_REALCREDS )) goto err_cred; }
Quoted 3 lines
makes monitoring simpler and even more secure to use since Perf tool need not to start/stop/single-step and read/write registers and memory and so on like a debugger or strace-like tool. What do you think?
I tend to agree, Peter?
Quoted 141 lines
Alexei
Quoted 139 lines
- Arnaldo
Quoted 135 lines
CAP_PERFMONcould be used to extend and substituteptrace_may_access()check inperf_eventssubsystem to simplify user experience at least in this specific case.Alexei
[1] https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html
Quoted 127 lines
Without setting
CAP_PERFMON:$ getcap ./perf $ ./perf stat -a ls Error: Access to performance monitoring and observability operations is limited. $ ./perf stat ls Performance counter stats for 'ls': 2.06 msec task-clock:u # 0.418 CPUs utilized 0 context-switches:u # 0.000 K/sec 0 cpu-migrations:u # 0.000 K/secWith
CAP_PERFMON:$ getcap ./perf ./perf = cap_perfmon+ep $ ./perf stat -a ls Performance counter stats for 'system wide': 142.42 msec cpu-clock # 25.062 CPUs utilized 182 context-switches # 0.001 M/sec 48 cpu-migrations # 0.337 K/sec $ ./perf stat ls Error: Access to performance monitoring and observability operations is limited.Am I missing something silly?
Analysis:
---------
A bit more analysis lead me to below kernel codefs/exec.c:
begin_new_exec()
{
...
if (bprm->interp_flags&BINPRM_FLAGS_ENFORCE_NONDUMP|| !(uid_eq(current_euid(),current_uid()) &&gid_eq(current_egid(), current_gid())))set_dumpable(current->mm, suid_dumpable); else
set_dumpable(current->mm, SUID_DUMP_USER);...
commit_creds(bprm->cred);
}When I execute './perf stat ls', it's going into else condition and thus sets dumpable flag as
SUID_DUMP_USER. Then incommit_creds():int
commit_creds(struct cred *new)
{
...
/* dumpability changes */
if (...
!cred_cap_issubset(old, new)) {
if (task->mm)
set_dumpable(task->mm, suid_dumpable); }!cred_cap_issubset(old, new) fails for perf without any capability and thus it doesn't execute
set_dumpable(). Whereas that condition passes for perf withCAP_PERFMONand thus it overwrites old value (SUID_DUMP_USER) withsuid_dumpableinmm_flags. On an Ubuntu,suid_dumpabledefault value isSUID_DUMP_ROOT. On Fedora, it'sSUID_DUMP_DISABLE. (/proc/sys/fs/suid_dumpable).Now while opening an event:
perf_event_open()
ptrace_may_access()
__ptrace_may_access(){
...
if (mm &&
((get_dumpable(mm)!=SUID_DUMP_USER) && !ptrace_has_cap(cred,mm->user_ns, mode))) return-EPERM;
}This if condition passes for perf with
CAP_PERFMONand thus it returns-EPERM. But it fails for perf withoutCAP_PERFMONand thus it goes ahead and returns success. So opening an event fails when perf hasCAP_PREFMONand tries to open process specific event as normal user.Workarounds:
------------
Based on above analysis, I found couple of workarounds (examples are on Ubuntu 18.04.4 powerpc):Workaround1:
SettingSUID_DUMP_USERas default (in/proc/sys/fs/suid_dumpable) solves the issue.# echo 1 > /proc/sys/fs/suid_dumpable $ getcap ./perf ./perf = cap_perfmon+ep $ ./perf stat ls Performance counter stats for 'ls': 1.47 msec task-clock # 0.806 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/secWorkaround2:
UsingCAP_SYS_PTRACEalong withCAP_PERFMONsolves the issue.$ cat /proc/sys/fs/suid_dumpable 2 # setcap "cap_perfmon,cap_sys_ptrace=ep" ./perf $ ./perf stat ls Performance counter stats for 'ls': 1.41 msec task-clock # 0.826 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/secWorkaround3:
AddingCAP_PERFMONto parent of perf (/bin/bash) also solves the issue.$ cat /proc/sys/fs/suid_dumpable 2 # setcap "cap_perfmon=ep" /bin/bash # setcap "cap_perfmon=ep" ./perf $ bash $ ./perf stat ls Performance counter stats for 'ls': 1.47 msec task-clock # 0.806 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/sec- Ravi
Signature · 1 line
- Arnaldo
Quoted 48 lines · Arnaldo Carvalho de Melo
Em Mon, Jul 13, 2020 at 12:48:25PM +0300, Alexey Budankov escreveu:
Quoted 23 lines · Arnaldo Carvalho de Melo
Quoted 20 lines
Em Fri, Jul 10, 2020 at 05:30:50PM +0300, Alexey Budankov escreveu:
Quoted 19 lines · Ravi Bangoria
Quoted 5 lines
Quoted 4 lines
Currently access to
perf_events,i915_perfand other performance monitoring and observability subsystems of the kernel is open only for a privileged process [1] withCAP_SYS_ADMINcapability enabled in the process effective set [2].Quoted 8 lines
Quoted 4 lines
This patch set introduces
CAP_PERFMONcapability designed to secure system performance monitoring and observability operations so thatCAP_PERFMONwould assistCAP_SYS_ADMINcapability in its governing role for performance monitoring and observability subsystems of the kernel.I'm seeing an issue with
CAP_PERFMONwhen I try to record data for a specific target. I don't know whether this is sort of a regression or an expected behavior.Thanks for reporting and root causing this case. The behavior looks like kind of expected since currently
CAP_PERFMONtakes over the related part ofCAP_SYS_ADMINcredentials only. Actually Perf security docs [1] say that access control is also subject toCAP_SYS_PTRACEcredentials.Quoted 4 lines
Quoted 2 lines
I think that stating that in the error message would be helpful, after all, who reads docs? 8-)
At least those who write it :D ...
Everybody should read it, sure :-)
Quoted 9 lines
Quoted 9 lines
I.e., this:
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. $Could become:
Quoted 7 lines
Quoted 5 lines
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. Right now only CAP_PERFMON is granted, you may need CAP_SYS_PTRACE. $It would better provide reference to perf security docs in the tool output.
Quoted 8 lines
So add a 3rd line:
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. Right now only CAP_PERFMON is granted, you may need CAP_SYS_PTRACE. Please read the 'Perf events and tool security' document: https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html
If it had that patch below then message change would not be required. However this two sentences in the end of whole message would still add up:
"Please read the 'Perf events and tool security' document:
https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html"
Quoted 4 lines
Quoted 2 lines
Looks like extending
ptrace_may_access()check forperf_eventswithCAP_PERFMONYou mean the following?
Exactly that.
Quoted 18 lines
kernel/events/core.c +1
-1@@ -11595,7 +11595,7 @@ SYSCALL_DEFINE5(perf_event_open,* perf_event_exit_task() that could imply). */ err = -EACCES ; -if (!ptrace_may_access (task,PTRACE_MODE_READ_REALCREDS )) +if (!perfmon_capable () && !ptrace_may_access (task,PTRACE_MODE_READ_REALCREDS )) goto err_cred; }Quoted 3 lines
makes monitoring simpler and even more secure to use since Perf tool need not to start/stop/single-step and read/write registers and memory and so on like a debugger or strace-like tool. What do you think?
Quoted 6 lines
I tend to agree, Peter?
Quoted 4 lines
Alexei
Quoted 2 lines
- Arnaldo
Alexei
Arnaldo Carvalho de Melo
maintainerEm Mon, Jul 13, 2020 at 03:37:51PM +0300, Alexey Budankov escreveu:
Quoted 52 lines · Arnaldo Carvalho de Melo
Quoted 50 lines
Em Mon, Jul 13, 2020 at 12:48:25PM +0300, Alexey Budankov escreveu:
Quoted 23 lines · Arnaldo Carvalho de Melo
Quoted 20 lines
Em Fri, Jul 10, 2020 at 05:30:50PM +0300, Alexey Budankov escreveu:
Quoted 19 lines · Ravi Bangoria
Quoted 5 lines
Quoted 4 lines
Currently access to
perf_events,i915_perfand other performance monitoring and observability subsystems of the kernel is open only for a privileged process [1] withCAP_SYS_ADMINcapability enabled in the process effective set [2].Quoted 8 lines
Quoted 4 lines
This patch set introduces
CAP_PERFMONcapability designed to secure system performance monitoring and observability operations so thatCAP_PERFMONwould assistCAP_SYS_ADMINcapability in its governing role for performance monitoring and observability subsystems of the kernel.I'm seeing an issue with
CAP_PERFMONwhen I try to record data for a specific target. I don't know whether this is sort of a regression or an expected behavior.Thanks for reporting and root causing this case. The behavior looks like kind of expected since currently
CAP_PERFMONtakes over the related part ofCAP_SYS_ADMINcredentials only. Actually Perf security docs [1] say that access control is also subject toCAP_SYS_PTRACEcredentials.Quoted 4 lines
Quoted 2 lines
I think that stating that in the error message would be helpful, after all, who reads docs? 8-)
At least those who write it :D ...
Everybody should read it, sure :-)
Quoted 9 lines
Quoted 9 lines
I.e., this:
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. $Could become:
Quoted 7 lines
Quoted 5 lines
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. Right now only CAP_PERFMON is granted, you may need CAP_SYS_PTRACE. $It would better provide reference to perf security docs in the tool output.
So add a 3rd line:
Quoted 8 lines
Quoted 6 lines
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. Right now only CAP_PERFMON is granted, you may need CAP_SYS_PTRACE. Please read the 'Perf events and tool security' document: https://www.kernel.org/doc/html/latest/admin-guide/perf-security.htmlIf it had that patch below then message change would not be required.
Sure, but the tool should continue to work and provide useful messages when running on kernels without that change. Pointing to the document is valid and should be done, that is an agreed point. But the tool can do some checks, narrow down the possible causes for the error message and provide something that in most cases will make the user make progress.
Quoted 3 lines
However this two sentences in the end of whole message would still add up:
"Please read the 'Perf events and tool security' document:
https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html"
We're in violent agreement here. :-)
Quoted 6 lines
Quoted 4 lines
Quoted 2 lines
Looks like extending
ptrace_may_access()check forperf_eventswithCAP_PERFMONYou mean the following?
Exactly that.
Sure, lets then wait for others to chime in and then you can go ahead and submit that patch.
Peter?
- Arnaldo
Quoted 26 lines
Quoted 18 lines
kernel/events/core.c +1
-1@@ -11595,7 +11595,7 @@ SYSCALL_DEFINE5(perf_event_open,* perf_event_exit_task() that could imply). */ err = -EACCES ; -if (!ptrace_may_access (task,PTRACE_MODE_READ_REALCREDS )) +if (!perfmon_capable () && !ptrace_may_access (task,PTRACE_MODE_READ_REALCREDS )) goto err_cred; }Quoted 3 lines
makes monitoring simpler and even more secure to use since Perf tool need not to start/stop/single-step and read/write registers and memory and so on like a debugger or strace-like tool. What do you think?
Quoted 6 lines
I tend to agree, Peter?
Quoted 4 lines
Alexei
Quoted 2 lines
- Arnaldo
Alexei
Signature · 1 line
- Arnaldo
Peter Zijlstra
maintainerQuoted 13 lines · Arnaldo Carvalho de Melo
Quoted 13 lines
Quoted 13 lines
kernel/events/core.c +1
-1@@ -11595,7 +11595,7 @@ SYSCALL_DEFINE5(perf_event_open,* perf_event_exit_task() that could imply). */ err = -EACCES ; -if (!ptrace_may_access (task,PTRACE_MODE_READ_REALCREDS )) +if (!perfmon_capable () && !ptrace_may_access (task,PTRACE_MODE_READ_REALCREDS )) goto err_cred; }
Quoted 5 lines
Quoted 5 lines
Quoted 5 lines
Quoted 3 lines
makes monitoring simpler and even more secure to use since Perf tool need not to start/stop/single-step and read/write registers and memory and so on like a debugger or strace-like tool. What do you think?
I tend to agree, Peter?
So this basically says that if CAP_PERFMON, we don't care about the ptrace() permissions? Just like how CAP_SYS_PTRACE would always allow the ptrace checks?
I suppose that makes sense.
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Arnaldo Carvalho de Melo
maintainerEm Tue, Jul 14, 2020 at 12:59:34PM +0200, Peter Zijlstra escreveu:
Quoted 19 lines · Arnaldo Carvalho de Melo
Quoted 17 lines
Quoted 17 lines
Quoted 17 lines
kernel/events/core.c +1
-1@@ -11595,7 +11595,7 @@ SYSCALL_DEFINE5(perf_event_open,* perf_event_exit_task() that could imply). */ err = -EACCES ; -if (!ptrace_may_access (task,PTRACE_MODE_READ_REALCREDS )) +if (!perfmon_capable () && !ptrace_may_access (task,PTRACE_MODE_READ_REALCREDS )) goto err_cred; }Quoted 3 lines
makes monitoring simpler and even more secure to use since Perf tool need not to start/stop/single-step and read/write registers and memory and so on like a debugger or strace-like tool. What do you think?
Quoted 7 lines
Quoted 1 line
Quoted 1 line
Quoted 1 line
I tend to agree, Peter?
So this basically says that if
CAP_PERFMON, we don't care about theptrace()permissions? Just like howCAP_SYS_PTRACEwould always allow the ptrace checks?I suppose that makes sense.
Yeah, it in fact addresses the comment right above it:
if (task) {
err = mutex_lock_interruptible(&task->signal->exec_update_mutex);
if (err)
goto err_task;
/*
* Reuse ptrace permission checks for now.
*
* We must hold exec_update_mutex across this and any potential
* perf_install_in_context() call for this new event to
* serialize against exec() altering our credentials (and the
* perf_event_exit_task() that could imply).
*/
err = -EACCES;
if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
goto err_cred;
}that "for now" part :-)
Idea is to not require CAP_PTRACE for that, i.e. the attack surface for the perf binary is reduced.
- Arnaldo
Quoted 68 lines · Arnaldo Carvalho de Melo
Em Mon, Jul 13, 2020 at 03:37:51PM +0300, Alexey Budankov escreveu:
Quoted 52 lines · Arnaldo Carvalho de Melo
Quoted 50 lines
Em Mon, Jul 13, 2020 at 12:48:25PM +0300, Alexey Budankov escreveu:
Quoted 23 lines · Arnaldo Carvalho de Melo
Quoted 20 lines
Em Fri, Jul 10, 2020 at 05:30:50PM +0300, Alexey Budankov escreveu:
Quoted 19 lines · Ravi Bangoria
Quoted 5 lines
Quoted 4 lines
Currently access to
perf_events,i915_perfand other performance monitoring and observability subsystems of the kernel is open only for a privileged process [1] withCAP_SYS_ADMINcapability enabled in the process effective set [2].Quoted 8 lines
Quoted 4 lines
This patch set introduces
CAP_PERFMONcapability designed to secure system performance monitoring and observability operations so thatCAP_PERFMONwould assistCAP_SYS_ADMINcapability in its governing role for performance monitoring and observability subsystems of the kernel.I'm seeing an issue with
CAP_PERFMONwhen I try to record data for a specific target. I don't know whether this is sort of a regression or an expected behavior.Thanks for reporting and root causing this case. The behavior looks like kind of expected since currently
CAP_PERFMONtakes over the related part ofCAP_SYS_ADMINcredentials only. Actually Perf security docs [1] say that access control is also subject toCAP_SYS_PTRACEcredentials.Quoted 4 lines
Quoted 2 lines
I think that stating that in the error message would be helpful, after all, who reads docs? 8-)
At least those who write it :D ...
Everybody should read it, sure :-)
Quoted 9 lines
Quoted 9 lines
I.e., this:
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. $Could become:
Quoted 7 lines
Quoted 5 lines
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. Right now only CAP_PERFMON is granted, you may need CAP_SYS_PTRACE. $It would better provide reference to perf security docs in the tool output.
So add a 3rd line:
Quoted 8 lines
Quoted 6 lines
$ ./perf stat ls Error: Access to performance monitoring and observability operations is limited. Right now only CAP_PERFMON is granted, you may need CAP_SYS_PTRACE. Please read the 'Perf events and tool security' document: https://www.kernel.org/doc/html/latest/admin-guide/perf-security.htmlIf it had that patch below then message change would not be required.
Sure, but the tool should continue to work and provide useful messages when running on kernels without that change. Pointing to the document is valid and should be done, that is an agreed point. But the tool can do some checks, narrow down the possible causes for the error message and provide something that in most cases will make the user make progress.
Quoted 5 lines
Quoted 3 lines
However this two sentences in the end of whole message would still add up:
"Please read the 'Perf events and tool security' document:
https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html"We're in violent agreement here. :-)
Here is the message draft mentioning a) CAP_SYS_PTRACE, for kernels prior v5.8, and b) Perf security document link. The plan is to send a patch extending perf_events with CAP_PERFMON check [1] for ptrace_may_access() and extending the tool with this message.
"Access to performance monitoring and observability operations is limited.
Enforced MAC policy settings (SELinux) can limit access to performance monitoring and observability operations. Inspect system audit records for more perf_event access control information and adjusting the policy. Consider adjusting /proc/sys/kernel/perf_event_paranoid setting to open access to performance monitoring and observability operations for processes without CAP_PERFMON, CAP_SYS_PTRACE or CAP_SYS_ADMIN Linux capability. More information can be found at 'Perf events and tool security' document:
https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html
perf_event_paranoid setting is -1:
-1: Allow use of (almost) all events by all users
Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK
Quoted 3 lines
= 0: Disallow raw and ftrace function tracepoint access = 1: Disallow CPU event access
= 2: Disallow kernel profiling
To make the adjusted perf_event_paranoid setting permanent preserve it in /etc/sysctl.conf (e.g. kernel.perf_event_paranoid = <setting>)"
Alexei
[1] https://lore.kernel.org/lkml/[email protected]/
Quoted 42 lines
Quoted 7 lines
Quoted 5 lines
Quoted 3 lines
Looks like extending
ptrace_may_access()check forperf_eventswithCAP_PERFMONYou mean the following?
Exactly that.
Sure, lets then wait for others to chime in and then you can go ahead and submit that patch.
Peter?
- Arnaldo
Quoted 26 lines
Quoted 18 lines
kernel/events/core.c +1
-1@@ -11595,7 +11595,7 @@ SYSCALL_DEFINE5(perf_event_open,* perf_event_exit_task() that could imply). */ err = -EACCES ; -if (!ptrace_may_access (task,PTRACE_MODE_READ_REALCREDS )) +if (!perfmon_capable () && !ptrace_may_access (task,PTRACE_MODE_READ_REALCREDS )) goto err_cred; }Quoted 3 lines
makes monitoring simpler and even more secure to use since Perf tool need not to start/stop/single-step and read/write registers and memory and so on like a debugger or strace-like tool. What do you think?
Quoted 6 lines
I tend to agree, Peter?
Quoted 4 lines
Alexei
Quoted 2 lines
- Arnaldo
Alexei
Arnaldo Carvalho de Melo
maintainerEm Tue, Jul 21, 2020 at 04:06:34PM +0300, Alexey Budankov escreveu:
Quoted 37 lines · Arnaldo Carvalho de Melo
Quoted 12 lines
Em Mon, Jul 13, 2020 at 03:37:51PM +0300, Alexey Budankov escreveu:
Quoted 4 lines · Arnaldo Carvalho de Melo
Quoted 1 line
Em Mon, Jul 13, 2020 at 12:48:25PM +0300, Alexey Budankov escreveu:
If it had that patch below then message change would not be required.
Sure, but the tool should continue to work and provide useful messages when running on kernels without that change. Pointing to the document is valid and should be done, that is an agreed point. But the tool can do some checks, narrow down the possible causes for the error message and provide something that in most cases will make the user make progress.
Quoted 5 lines
Quoted 3 lines
However this two sentences in the end of whole message would still add up:
"Please read the 'Perf events and tool security' document:
https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html"We're in violent agreement here. :-)
Here is the message draft mentioning a)
CAP_SYS_PTRACE, for kernels prior v5.8, and b) Perf security document link. The plan is to send a patch extendingperf_eventswithCAP_PERFMONcheck [1] forptrace_may_access()and extending the tool with this message."Access to performance monitoring and observability operations is limited.
Enforced MAC policy settings (SELinux) can limit access to performance monitoring and observability operations. Inspect system audit records for moreperf_eventaccess control information and adjusting the policy. Consider adjusting/proc/sys/kernel/perf_event_paranoidsetting to open access to performance monitoring and observability operations for processes withoutCAP_PERFMON,CAP_SYS_PTRACEorCAP_SYS_ADMINLinux capability. More information can be found at 'Perf events and tool security' document:
https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html
perf_event_paranoidsetting is -1:
-1: Allow use of (almost) all events by all users
Ignore mlock limit afterperf_event_mlock_kbwithoutCAP_IPC_LOCK
Quoted 5 lines
Quoted 3 lines
= 0: Disallow raw and ftrace function tracepoint access = 1: Disallow CPU event access
= 2: Disallow kernel profilingTo make the adjusted
perf_event_paranoidsetting permanent preserve it in/etc/sysctl.conf(e.g. kernel.perf_event_paranoid = <setting>)"
Looks ok! Lots of knobs to control access as one needs.
- Arnaldo
Quoted 3 lines
Alexei