Re: [PATCH v4 1/9] capabilities: introduce CAP_SYS_PERFMON to kernel and user space

On 12/18/19 4:24 AM, Alexey Budankov wrote:
> 
> Introduce CAP_SYS_PERFMON capability devoted to secure system performance
> monitoring and observability operations so that CAP_SYS_PERFMON would
> assist CAP_SYS_ADMIN capability in its governing role for perf_events,
> i915_perf and other subsystems of the kernel.
> 
> CAP_SYS_PERFMON intends to harden system security and integrity during
> system performance monitoring and observability operations by decreasing
> attack surface that is available to CAP_SYS_ADMIN privileged processes.
> 
> CAP_SYS_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 in accordance with the recommendations
> provided in the man page for CAP_SYS_ADMIN [1]: "Note: this capability
> is overloaded; see Notes to kernel developers, below."
> 
> [1] http://man7.org/linux/man-pages/man7/capabilities.7.html
> 
> Signed-off-by: Alexey Budankov <[email protected]>

Acked-by: Stephen Smalley <[email protected]>

Note for selinux developers: we will need to update the 
selinux-testsuite tests for perf_event when/if this change lands upstream.

> ---
>   include/linux/capability.h          | 4 ++++
>   include/uapi/linux/capability.h     | 8 +++++++-
>   security/selinux/include/classmap.h | 4 ++--
>   3 files changed, 13 insertions(+), 3 deletions(-)
> 
> diff --git a/include/linux/capability.h b/include/linux/capability.h
> index ecce0f43c73a..883c879baa4b 100644
> --- a/include/linux/capability.h
> +++ b/include/linux/capability.h
> @@ -251,6 +251,10 @@ extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct
>   extern 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_SYS_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);
> diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h
> index 240fdb9a60f6..98e03cc76c7c 100644
> --- a/include/uapi/linux/capability.h
> +++ b/include/uapi/linux/capability.h
> @@ -366,8 +366,14 @@ 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_SYS_PERFMON		38
>   
> -#define CAP_LAST_CAP         CAP_AUDIT_READ
> +#define CAP_LAST_CAP         CAP_SYS_PERFMON
>   
>   #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
>   
> diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
> index 7db24855e12d..bae602c623b0 100644
> --- a/security/selinux/include/classmap.h
> +++ b/security/selinux/include/classmap.h
> @@ -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", "sys_perfmon"
>   
> -#if CAP_LAST_CAP > CAP_AUDIT_READ
> +#if CAP_LAST_CAP > CAP_SYS_PERFMON
>   #error New capability defined, please update COMMON_CAP2_PERMS.
>   #endif
>   
>