On Wed, Dec 18, 2019 at 12:25:35PM +0300, Alexey Budankov wrote:
>
> Open access to perf_events monitoring for CAP_SYS_PERFMON privileged
> processes. 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_SYS_PERFMON capability.
>
> Signed-off-by: Alexey Budankov <[email protected]>
> ---
> include/linux/perf_event.h | 6 +++---
> kernel/events/core.c | 6 +++---
> 2 files changed, 6 insertions(+), 6 deletions(-)
>
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index 34c7c6910026..f46acd69425f 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -1285,7 +1285,7 @@ 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);
> @@ -1293,7 +1293,7 @@ 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);
> @@ -1301,7 +1301,7 @@ 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);
These are OK I suppose.
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 059ee7116008..d9db414f2197 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -9056,7 +9056,7 @@ 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;
>
> /*
This one only allows attaching to already extant kprobes, right? It does
not allow creation of kprobes.
> @@ -9116,7 +9116,7 @@ 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;
>
> /*
Idem, I presume.
> @@ -11157,7 +11157,7 @@ SYSCALL_DEFINE5(perf_event_open,
> }
>
> if (attr.namespaces) {
> - if (!capable(CAP_SYS_ADMIN))
> + if (!perfmon_capable())
> return -EACCES;
> }
And given we basically make the entire kernel observable with this CAP,
busting namespaces shoulnd't be a problem either.
So yeah, I suppose that works.
On 08.01.2020 19:07, Peter Zijlstra wrote:
> On Wed, Dec 18, 2019 at 12:25:35PM +0300, Alexey Budankov wrote:
>>
>> Open access to perf_events monitoring for CAP_SYS_PERFMON privileged
>> processes. 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_SYS_PERFMON capability.
>>
>> Signed-off-by: Alexey Budankov <[email protected]>
>> ---
>> include/linux/perf_event.h | 6 +++---
>> kernel/events/core.c | 6 +++---
>> 2 files changed, 6 insertions(+), 6 deletions(-)
>>
>> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
>> index 34c7c6910026..f46acd69425f 100644
>> --- a/include/linux/perf_event.h
>> +++ b/include/linux/perf_event.h
>> @@ -1285,7 +1285,7 @@ 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);
>> @@ -1293,7 +1293,7 @@ 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);
>> @@ -1301,7 +1301,7 @@ 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);
>
> These are OK I suppose.
>
>> diff --git a/kernel/events/core.c b/kernel/events/core.c
>> index 059ee7116008..d9db414f2197 100644
>> --- a/kernel/events/core.c
>> +++ b/kernel/events/core.c
>> @@ -9056,7 +9056,7 @@ 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;
>>
>> /*
>
> This one only allows attaching to already extant kprobes, right? It does
> not allow creation of kprobes.
This unblocks creation of local trace kprobes and uprobes by CAP_SYS_PERFMON
privileged process, exactly the same as for CAP_SYS_ADMIN privileged process.
>
>> @@ -9116,7 +9116,7 @@ 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;
>>
>> /*
>
> Idem, I presume.
>
>> @@ -11157,7 +11157,7 @@ SYSCALL_DEFINE5(perf_event_open,
>> }
>>
>> if (attr.namespaces) {
>> - if (!capable(CAP_SYS_ADMIN))
>> + if (!perfmon_capable())
>> return -EACCES;
>> }
>
> And given we basically make the entire kernel observable with this CAP,
> busting namespaces shoulnd't be a problem either.
>
> So yeah, I suppose that works.
>
Hi Peter,
On 08.01.2020 19:07, Peter Zijlstra wrote:
> On Wed, Dec 18, 2019 at 12:25:35PM +0300, Alexey Budankov wrote:
>>
>> Open access to perf_events monitoring for CAP_SYS_PERFMON privileged
>> processes. 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_SYS_PERFMON capability.
>>
>> Signed-off-by: Alexey Budankov <[email protected]>
>> ---
>> include/linux/perf_event.h | 6 +++---
>> kernel/events/core.c | 6 +++---
>> 2 files changed, 6 insertions(+), 6 deletions(-)
>>
>> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
>> index 34c7c6910026..f46acd69425f 100644
>> --- a/include/linux/perf_event.h
>> +++ b/include/linux/perf_event.h
>> @@ -1285,7 +1285,7 @@ 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);
>> @@ -1293,7 +1293,7 @@ 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);
>> @@ -1301,7 +1301,7 @@ 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);
>
> These are OK I suppose.
>
>> diff --git a/kernel/events/core.c b/kernel/events/core.c
>> index 059ee7116008..d9db414f2197 100644
>> --- a/kernel/events/core.c
>> +++ b/kernel/events/core.c
>> @@ -9056,7 +9056,7 @@ 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;
>>
>> /*
>
> This one only allows attaching to already extant kprobes, right? It does
> not allow creation of kprobes.
>
>> @@ -9116,7 +9116,7 @@ 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;
>>
>> /*
>
> Idem, I presume.
>
>> @@ -11157,7 +11157,7 @@ SYSCALL_DEFINE5(perf_event_open,
>> }
>>
>> if (attr.namespaces) {
>> - if (!capable(CAP_SYS_ADMIN))
>> + if (!perfmon_capable())
>> return -EACCES;
>> }
>
> And given we basically make the entire kernel observable with this CAP,
> busting namespaces shoulnd't be a problem either.
>
> So yeah, I suppose that works.
Could this have you explicit Reviewed-by or Acked-by tag
so the changes could be driven into the kernel?
Latest v7 is here:
https://lore.kernel.org/lkml/[email protected]/
Thanks,
Alexey
On 01.04.2020 23:49, Alexey Budankov wrote:
> Hi Peter,
>
> On 08.01.2020 19:07, Peter Zijlstra wrote:
>> On Wed, Dec 18, 2019 at 12:25:35PM +0300, Alexey Budankov wrote:
>>>
>>> Open access to perf_events monitoring for CAP_SYS_PERFMON privileged
>>> processes. 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_SYS_PERFMON capability.
>>>
>>> Signed-off-by: Alexey Budankov <[email protected]>
>>> ---
>>> include/linux/perf_event.h | 6 +++---
>>> kernel/events/core.c | 6 +++---
>>> 2 files changed, 6 insertions(+), 6 deletions(-)
>>>
>>> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
>>> index 34c7c6910026..f46acd69425f 100644
>>> --- a/include/linux/perf_event.h
>>> +++ b/include/linux/perf_event.h
>>> @@ -1285,7 +1285,7 @@ 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);
>>> @@ -1293,7 +1293,7 @@ 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);
>>> @@ -1301,7 +1301,7 @@ 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);
>>
>> These are OK I suppose.
>>
>>> diff --git a/kernel/events/core.c b/kernel/events/core.c
>>> index 059ee7116008..d9db414f2197 100644
>>> --- a/kernel/events/core.c
>>> +++ b/kernel/events/core.c
>>> @@ -9056,7 +9056,7 @@ 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;
>>>
>>> /*
>>
>> This one only allows attaching to already extant kprobes, right? It does
>> not allow creation of kprobes.
>>
>>> @@ -9116,7 +9116,7 @@ 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;
>>>
>>> /*
>>
>> Idem, I presume.
>>
>>> @@ -11157,7 +11157,7 @@ SYSCALL_DEFINE5(perf_event_open,
>>> }
>>>
>>> if (attr.namespaces) {
>>> - if (!capable(CAP_SYS_ADMIN))
>>> + if (!perfmon_capable())
>>> return -EACCES;
>>> }
>>
>> And given we basically make the entire kernel observable with this CAP,
>> busting namespaces shoulnd't be a problem either.
>>
>> So yeah, I suppose that works.
>
> Could this have you explicit Reviewed-by or Acked-by tag
> so the changes could be driven into the kernel?
> Latest v7 is here:
> https://lore.kernel.org/lkml/[email protected]/
Posted v8 with all acquired tags so far:
https://lore.kernel.org/lkml/[email protected]/
Thanks,
Alexey