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.
Rasmus Villemoes also pointed out that systemd uses SYS_kcmp to deduplicate the per-service file descriptor store.
Note that some distributions such as Ubuntu are already enabling CHECKPOINT_RESTORE in their configs and so, by extension, SYS_kcmp.
References: https://gitlab.freedesktop.org/drm/intel/-/issues/3046 Signed-off-by: Chris Wilson chris@chris-wilson.co.uk Cc: Kees Cook keescook@chromium.org Cc: Andy Lutomirski luto@amacapital.net Cc: Will Drewry wad@chromium.org Cc: Andrew Morton akpm@linux-foundation.org Cc: Dave Airlie airlied@gmail.com Cc: Daniel Vetter daniel@ffwll.ch Cc: Lucas Stach l.stach@pengutronix.de Cc: Rasmus Villemoes linux@rasmusvillemoes.dk Cc: Cyrill Gorcunov gorcunov@gmail.com Cc: stable@vger.kernel.org Acked-by: Daniel Vetter daniel.vetter@ffwll.ch # DRM depends on kcmp Acked-by: Rasmus Villemoes linux@rasmusvillemoes.dk # systemd uses kcmp
--- v2: - Default n. - Borrrow help message from man kcmp. - Export get_epoll_tfile_raw_ptr() for CONFIG_KCMP v3: - Select KCMP for CONFIG_DRM --- drivers/gpu/drm/Kconfig | 3 +++ fs/eventpoll.c | 4 ++-- include/linux/eventpoll.h | 2 +- init/Kconfig | 11 +++++++++++ kernel/Makefile | 2 +- tools/testing/selftests/seccomp/seccomp_bpf.c | 2 +- 6 files changed, 19 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 0973f408d75f..af6c6d214d91 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -15,6 +15,9 @@ menuconfig DRM select I2C_ALGOBIT select DMA_SHARED_BUFFER select SYNC_FILE +# gallium uses SYS_kcmp for os_same_file_description() to de-duplicate +# device and dmabuf fd. Let's make sure that is available for our userspace. + select KCMP help Kernel-level support for the Direct Rendering Infrastructure (DRI) introduced in XFree86 4.0. If you say Y here, you need to select 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..9cc7436b2f73 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 +1738,16 @@ config ARCH_HAS_MEMBARRIER_CALLBACKS config ARCH_HAS_MEMBARRIER_SYNC_CORE bool
+config KCMP + bool "Enable kcmp() system call" if EXPERT + 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)
On Fri, Feb 05, 2021 at 10:00:12PM +0000, 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.
... Reviewed-by: Cyrill Gorcunov gorcunov@gmail.com
On Fri, Feb 05, 2021 at 10:00:12PM +0000, 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.
Rasmus Villemoes also pointed out that systemd uses SYS_kcmp to deduplicate the per-service file descriptor store.
Note that some distributions such as Ubuntu are already enabling CHECKPOINT_RESTORE in their configs and so, by extension, SYS_kcmp.
References: https://gitlab.freedesktop.org/drm/intel/-/issues/3046 Signed-off-by: Chris Wilson chris@chris-wilson.co.uk
Thanks!
Reviewed-by: Kees Cook keescook@chromium.org
-Kees
Cc: Kees Cook keescook@chromium.org Cc: Andy Lutomirski luto@amacapital.net Cc: Will Drewry wad@chromium.org Cc: Andrew Morton akpm@linux-foundation.org Cc: Dave Airlie airlied@gmail.com Cc: Daniel Vetter daniel@ffwll.ch Cc: Lucas Stach l.stach@pengutronix.de Cc: Rasmus Villemoes linux@rasmusvillemoes.dk Cc: Cyrill Gorcunov gorcunov@gmail.com Cc: stable@vger.kernel.org Acked-by: Daniel Vetter daniel.vetter@ffwll.ch # DRM depends on kcmp Acked-by: Rasmus Villemoes linux@rasmusvillemoes.dk # systemd uses kcmp
v2:
- Default n.
- Borrrow help message from man kcmp.
- Export get_epoll_tfile_raw_ptr() for CONFIG_KCMP
v3:
- Select KCMP for CONFIG_DRM
drivers/gpu/drm/Kconfig | 3 +++ fs/eventpoll.c | 4 ++-- include/linux/eventpoll.h | 2 +- init/Kconfig | 11 +++++++++++ kernel/Makefile | 2 +- tools/testing/selftests/seccomp/seccomp_bpf.c | 2 +- 6 files changed, 19 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 0973f408d75f..af6c6d214d91 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -15,6 +15,9 @@ menuconfig DRM select I2C_ALGOBIT select DMA_SHARED_BUFFER select SYNC_FILE +# gallium uses SYS_kcmp for os_same_file_description() to de-duplicate +# device and dmabuf fd. Let's make sure that is available for our userspace.
- select KCMP help Kernel-level support for the Direct Rendering Infrastructure (DRI) introduced in XFree86 4.0. If you say Y here, you need to select
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..9cc7436b2f73 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 +1738,16 @@ config ARCH_HAS_MEMBARRIER_CALLBACKS config ARCH_HAS_MEMBARRIER_SYNC_CORE bool +config KCMP
- bool "Enable kcmp() system call" if EXPERT
- help
Enable the kernel resource comparison system call. It providesuser-space with the ability to compare two processes to see if theyshare a common resource, such as a file descriptor or even virtualmemory 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) -- 2.20.1
On Mon, Feb 08, 2021 at 02:12:00PM -0800, Kees Cook wrote:
On Fri, Feb 05, 2021 at 10:00:12PM +0000, 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.
Rasmus Villemoes also pointed out that systemd uses SYS_kcmp to deduplicate the per-service file descriptor store.
Note that some distributions such as Ubuntu are already enabling CHECKPOINT_RESTORE in their configs and so, by extension, SYS_kcmp.
References: https://gitlab.freedesktop.org/drm/intel/-/issues/3046 Signed-off-by: Chris Wilson chris@chris-wilson.co.uk
Thanks!
Reviewed-by: Kees Cook keescook@chromium.org
Thanks for reviews&patch, I stuffed it into a topic branch and plan to send it to Linus later this week.
Cheers, Daniel
-Kees
Cc: Kees Cook keescook@chromium.org Cc: Andy Lutomirski luto@amacapital.net Cc: Will Drewry wad@chromium.org Cc: Andrew Morton akpm@linux-foundation.org Cc: Dave Airlie airlied@gmail.com Cc: Daniel Vetter daniel@ffwll.ch Cc: Lucas Stach l.stach@pengutronix.de Cc: Rasmus Villemoes linux@rasmusvillemoes.dk Cc: Cyrill Gorcunov gorcunov@gmail.com Cc: stable@vger.kernel.org Acked-by: Daniel Vetter daniel.vetter@ffwll.ch # DRM depends on kcmp Acked-by: Rasmus Villemoes linux@rasmusvillemoes.dk # systemd uses kcmp
v2:
- Default n.
- Borrrow help message from man kcmp.
- Export get_epoll_tfile_raw_ptr() for CONFIG_KCMP
v3:
- Select KCMP for CONFIG_DRM
drivers/gpu/drm/Kconfig | 3 +++ fs/eventpoll.c | 4 ++-- include/linux/eventpoll.h | 2 +- init/Kconfig | 11 +++++++++++ kernel/Makefile | 2 +- tools/testing/selftests/seccomp/seccomp_bpf.c | 2 +- 6 files changed, 19 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 0973f408d75f..af6c6d214d91 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -15,6 +15,9 @@ menuconfig DRM select I2C_ALGOBIT select DMA_SHARED_BUFFER select SYNC_FILE +# gallium uses SYS_kcmp for os_same_file_description() to de-duplicate +# device and dmabuf fd. Let's make sure that is available for our userspace.
- select KCMP help Kernel-level support for the Direct Rendering Infrastructure (DRI) introduced in XFree86 4.0. If you say Y here, you need to select
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..9cc7436b2f73 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 +1738,16 @@ config ARCH_HAS_MEMBARRIER_CALLBACKS config ARCH_HAS_MEMBARRIER_SYNC_CORE bool +config KCMP
- bool "Enable kcmp() system call" if EXPERT
- help
Enable the kernel resource comparison system call. It providesuser-space with the ability to compare two processes to see if theyshare a common resource, such as a file descriptor or even virtualmemory 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) -- 2.20.1
-- Kees Cook
On Fri, 5 Feb 2021 at 22:01, Chris Wilson chris@chris-wilson.co.uk 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)
As you rightfully point out, SYS_kcmp is a bit of a two edged sword. While you mention the CONFIG issue, there is also a portability aspect (mesa runs on more than just linux) and as well as sandbox filtering of the extra syscall.
Last time I looked, the latter was still an issue and mesa was using SYS_kcmp to compare device node fds. A far shorter and more portable solution is possible, so let me prepare a Mesa patch.
-Emil
On Friday, February 12th, 2021 at 1:57 PM, Emil Velikov emil.l.velikov@gmail.com wrote:
On Fri, 5 Feb 2021 at 22:01, Chris Wilson chris@chris-wilson.co.uk 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)
As you rightfully point out, SYS_kcmp is a bit of a two edged sword. While you mention the CONFIG issue, there is also a portability aspect (mesa runs on more than just linux) and as well as sandbox filtering of the extra syscall.
Last time I looked, the latter was still an issue and mesa was using SYS_kcmp to compare device node fds. A far shorter and more portable solution is possible, so let me prepare a Mesa patch.
Comparing two DMA-BUFs can be done with their inode number, I think.
Comparing two device FDs is more subtle, because of GEM handle ref'counting. You sometimes really want to check whether two FDs are backed by the same file *description*. See [1] for details.
[1]: https://gitlab.freedesktop.org/mesa/drm/-/merge_requests/110
On Fri, 12 Feb 2021 at 13:14, Simon Ser contact@emersion.fr wrote:
On Friday, February 12th, 2021 at 1:57 PM, Emil Velikov emil.l.velikov@gmail.com wrote:
On Fri, 5 Feb 2021 at 22:01, Chris Wilson chris@chris-wilson.co.uk 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)
As you rightfully point out, SYS_kcmp is a bit of a two edged sword. While you mention the CONFIG issue, there is also a portability aspect (mesa runs on more than just linux) and as well as sandbox filtering of the extra syscall.
Last time I looked, the latter was still an issue and mesa was using SYS_kcmp to compare device node fds. A far shorter and more portable solution is possible, so let me prepare a Mesa patch.
Comparing two DMA-BUFs can be done with their inode number, I think.
Comparing two device FDs is more subtle, because of GEM handle ref'counting. You sometimes really want to check whether two FDs are backed by the same file *description*. See [1] for details.
Thanks for the correction and the reference. Seems like I've short circuited file description table vs file descriptor.
Emil
On 2021-02-12 1:57 p.m., Emil Velikov wrote:
On Fri, 5 Feb 2021 at 22:01, Chris Wilson chris@chris-wilson.co.uk 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)
As you rightfully point out, SYS_kcmp is a bit of a two edged sword. While you mention the CONFIG issue, there is also a portability aspect (mesa runs on more than just linux) and as well as sandbox filtering of the extra syscall.
Last time I looked, the latter was still an issue and mesa was using SYS_kcmp to compare device node fds. A far shorter and more portable solution is possible, so let me prepare a Mesa patch.
Make sure to read my comments on https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6881 first. :)
On Fri, 12 Feb 2021 at 14:01, Michel Dänzer michel@daenzer.net wrote:
On 2021-02-12 1:57 p.m., Emil Velikov wrote:
On Fri, 5 Feb 2021 at 22:01, Chris Wilson chris@chris-wilson.co.uk 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)
As you rightfully point out, SYS_kcmp is a bit of a two edged sword. While you mention the CONFIG issue, there is also a portability aspect (mesa runs on more than just linux) and as well as sandbox filtering of the extra syscall.
Last time I looked, the latter was still an issue and mesa was using SYS_kcmp to compare device node fds. A far shorter and more portable solution is possible, so let me prepare a Mesa patch.
Make sure to read my comments on https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6881 first. :)
Much appreciated. I might have been "slightly" off - pardon for the noise o/
-Emil
Hi
Am 05.02.21 um 23:00 schrieb Chris Wilson:
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.
Rasmus Villemoes also pointed out that systemd uses SYS_kcmp to deduplicate the per-service file descriptor store.
This helps a lot with transactional programming in userspace system code. So FWIW
Acked-by: Thomas Zimmermann tzimmermann@suse.de
Note that some distributions such as Ubuntu are already enabling CHECKPOINT_RESTORE in their configs and so, by extension, SYS_kcmp.
References: https://gitlab.freedesktop.org/drm/intel/-/issues/3046 Signed-off-by: Chris Wilson chris@chris-wilson.co.uk Cc: Kees Cook keescook@chromium.org Cc: Andy Lutomirski luto@amacapital.net Cc: Will Drewry wad@chromium.org Cc: Andrew Morton akpm@linux-foundation.org Cc: Dave Airlie airlied@gmail.com Cc: Daniel Vetter daniel@ffwll.ch Cc: Lucas Stach l.stach@pengutronix.de Cc: Rasmus Villemoes linux@rasmusvillemoes.dk Cc: Cyrill Gorcunov gorcunov@gmail.com Cc: stable@vger.kernel.org Acked-by: Daniel Vetter daniel.vetter@ffwll.ch # DRM depends on kcmp Acked-by: Rasmus Villemoes linux@rasmusvillemoes.dk # systemd uses kcmp
v2:
- Default n.
- Borrrow help message from man kcmp.
- Export get_epoll_tfile_raw_ptr() for CONFIG_KCMP
v3:
- Select KCMP for CONFIG_DRM
drivers/gpu/drm/Kconfig | 3 +++ fs/eventpoll.c | 4 ++-- include/linux/eventpoll.h | 2 +- init/Kconfig | 11 +++++++++++ kernel/Makefile | 2 +- tools/testing/selftests/seccomp/seccomp_bpf.c | 2 +- 6 files changed, 19 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 0973f408d75f..af6c6d214d91 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -15,6 +15,9 @@ menuconfig DRM select I2C_ALGOBIT select DMA_SHARED_BUFFER select SYNC_FILE +# gallium uses SYS_kcmp for os_same_file_description() to de-duplicate +# device and dmabuf fd. Let's make sure that is available for our userspace.
- select KCMP help Kernel-level support for the Direct Rendering Infrastructure (DRI) introduced in XFree86 4.0. If you say Y here, you need to select
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..9cc7436b2f73 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 +1738,16 @@ config ARCH_HAS_MEMBARRIER_CALLBACKS config ARCH_HAS_MEMBARRIER_SYNC_CORE bool +config KCMP
- bool "Enable kcmp() system call" if EXPERT
- help
Enable the kernel resource comparison system call. It providesuser-space with the ability to compare two processes to see if theyshare a common resource, such as a file descriptor or even virtualmemory 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)
linux-stable-mirror@lists.linaro.org
-
Chris Wilson -
Cyrill Gorcunov -
Daniel Vetter -
Emil Velikov -
Kees Cook -
Michel Dänzer -
Simon Ser -
Thomas Zimmermann