[PATCH v2] kernel: Expose SYS_kcmp by default

[Rasmus Villemoes]

On 05/02/2021 22.06, Chris Wilson wrote:
> Userspace has discovered the functionality offered by SYS_kcmp and has
> started to depend upon it. In particular, Mesa uses SYS_kcmp for
> os_same_file_description() in order to identify when two fd (e.g. device
> or dmabuf) point to the same struct file. Since they depend on it for
> core functionality, lift SYS_kcmp out of the non-default
> CONFIG_CHECKPOINT_RESTORE into the selectable syscall category.
> 
> Note that some distributions such as Ubuntu are already enabling
> CHECKPOINT_RESTORE in their configs and so, by extension, SYS_kcmp.
> 

Looks a lot like
https://lore.kernel.org/lkml/20200710075632.14661-1-linux@rasmusvillemoes.dk/.
So FWIW, ack from me.

cc += Cyrill.

> References: https://gitlab.freedesktop.org/drm/intel/-/issues/3046
> Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> Cc: Kees Cook <keescook at chromium.org>
> Cc: Andy Lutomirski <luto at amacapital.net>
> Cc: Will Drewry <wad at chromium.org>
> Cc: Andrew Morton <akpm at linux-foundation.org>
> Cc: Dave Airlie <airlied at gmail.com>
> Cc: Daniel Vetter <daniel at ffwll.ch>
> Cc: Lucas Stach <l.stach at pengutronix.de>
> Acked-by: Daniel Vetter <daniel.vetter at ffwll.ch> # DRM depends on SYS_kcmp
> 
> ---
> v2:
>   - Default n.
>   - Borrrow help message from man kcmp.
>   - Export get_epoll_tfile_raw_ptr() for CONFIG_KCMP
> ---
>  fs/eventpoll.c                                |  4 ++--
>  include/linux/eventpoll.h                     |  2 +-
>  init/Kconfig                                  | 12 ++++++++++++
>  kernel/Makefile                               |  2 +-
>  tools/testing/selftests/seccomp/seccomp_bpf.c |  2 +-
>  5 files changed, 17 insertions(+), 5 deletions(-)
> 
> diff --git a/fs/eventpoll.c b/fs/eventpoll.c
> index a829af074eb5..3196474cbe24 100644
> --- a/fs/eventpoll.c
> +++ b/fs/eventpoll.c
> @@ -979,7 +979,7 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
>  	return epir;
>  }
>  
> -#ifdef CONFIG_CHECKPOINT_RESTORE
> +#ifdef CONFIG_KCMP
>  static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff)
>  {
>  	struct rb_node *rbp;
> @@ -1021,7 +1021,7 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
>  
>  	return file_raw;
>  }
> -#endif /* CONFIG_CHECKPOINT_RESTORE */
> +#endif /* CONFIG_KCMP */
>  
>  /**
>   * Adds a new entry to the tail of the list in a lockless way, i.e.
> diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h
> index 0350393465d4..593322c946e6 100644
> --- a/include/linux/eventpoll.h
> +++ b/include/linux/eventpoll.h
> @@ -18,7 +18,7 @@ struct file;
>  
>  #ifdef CONFIG_EPOLL
>  
> -#ifdef CONFIG_CHECKPOINT_RESTORE
> +#ifdef CONFIG_KCMP
>  struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff);
>  #endif
>  
> diff --git a/init/Kconfig b/init/Kconfig
> index b77c60f8b963..1b75141bc18b 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -1194,6 +1194,7 @@ endif # NAMESPACES
>  config CHECKPOINT_RESTORE
>  	bool "Checkpoint/restore support"
>  	select PROC_CHILDREN
> +	select KCMP
>  	default n
>  	help
>  	  Enables additional kernel features in a sake of checkpoint/restore.
> @@ -1737,6 +1738,17 @@ config ARCH_HAS_MEMBARRIER_CALLBACKS
>  config ARCH_HAS_MEMBARRIER_SYNC_CORE
>  	bool
>  
> +config KCMP
> +	bool "Enable kcmp() system call" if EXPERT
> +	default n
> +	help
> +	  Enable the kernel resource comparison system call. It provides
> +	  user-space with the ability to compare two processes to see if they
> +	  share a common resource, such as a file descriptor or even virtual
> +	  memory space.
> +
> +	  If unsure, say N.
> +
>  config RSEQ
>  	bool "Enable rseq() system call" if EXPERT
>  	default y
> diff --git a/kernel/Makefile b/kernel/Makefile
> index aa7368c7eabf..320f1f3941b7 100644
> --- a/kernel/Makefile
> +++ b/kernel/Makefile
> @@ -51,7 +51,7 @@ obj-y += livepatch/
>  obj-y += dma/
>  obj-y += entry/
>  
> -obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o
> +obj-$(CONFIG_KCMP) += kcmp.o
>  obj-$(CONFIG_FREEZER) += freezer.o
>  obj-$(CONFIG_PROFILING) += profile.o
>  obj-$(CONFIG_STACKTRACE) += stacktrace.o
> diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
> index 26c72f2b61b1..1b6c7d33c4ff 100644
> --- a/tools/testing/selftests/seccomp/seccomp_bpf.c
> +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
> @@ -315,7 +315,7 @@ TEST(kcmp)
>  	ret = __filecmp(getpid(), getpid(), 1, 1);
>  	EXPECT_EQ(ret, 0);
>  	if (ret != 0 && errno == ENOSYS)
> -		SKIP(return, "Kernel does not support kcmp() (missing CONFIG_CHECKPOINT_RESTORE?)");
> +		SKIP(return, "Kernel does not support kcmp() (missing CONFIG_KCMP?)");
>  }
>  
>  TEST(mode_strict_support)
>