kcmp: Support selection of SYS_kcmp without CHECKPOINT_RESTORE

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
Reviewed-by: Cyrill Gorcunov <gorcunov@gmail.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210205220012.1983-1-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 0973f40..af6c6d2 100644 (file)
--- 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 a829af0..3196474 100644 (file)
--- 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 0350393..593322c 100644 (file)
--- 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 29ad683..b7d3c6a 100644 (file)
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1193,6 +1193,7 @@ 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.
@@ -1736,6 +1737,16 @@ 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 aa7368c..320f1f3 100644 (file)
--- 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 26c72f2..1b6c7d3 100644 (file)
--- 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)