From 2a42754b3104d78a2bc7a2ad8844427411c76ca6 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 3 Feb 2025 23:32:04 +0100 Subject: [PATCH 01/16] fsnotify: disable notification by default for all pseudo files Most pseudo files are not applicable for fsnotify events at all, let alone to the new pre-content events. Disable notifications to all files allocated with alloc_file_pseudo() and enable legacy inotify events for the specific cases of pipe and socket, which have known users of inotify events. Pre-content events are also kept disabled for sockets and pipes. Fixes: 20bf82a898b6 ("mm: don't allow huge faults for files with pre content watches") Reported-by: Alex Williamson Closes: https://lore.kernel.org/linux-fsdevel/20250131121703.1e4d00a7.alex.williamson@redhat.com/ Suggested-by: Linus Torvalds Link: https://lore.kernel.org/linux-fsdevel/CAHk-=wi2pThSVY=zhO=ZKxViBj5QCRX-=AS2+rVknQgJnHXDFg@mail.gmail.com/ Tested-by: Alex Williamson Signed-off-by: Amir Goldstein Link: https://lore.kernel.org/r/20250203223205.861346-3-amir73il@gmail.com Signed-off-by: Christian Brauner --- fs/file_table.c | 11 +++++++++++ fs/open.c | 4 ++-- fs/pipe.c | 6 ++++++ net/socket.c | 5 +++++ 4 files changed, 24 insertions(+), 2 deletions(-) diff --git a/fs/file_table.c b/fs/file_table.c index f0291a66f9db..35b93da6c5cb 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -375,7 +375,13 @@ struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, if (IS_ERR(file)) { ihold(inode); path_put(&path); + return file; } + /* + * Disable all fsnotify events for pseudo files by default. + * They may be enabled by caller with file_set_fsnotify_mode(). + */ + file_set_fsnotify_mode(file, FMODE_NONOTIFY); return file; } EXPORT_SYMBOL(alloc_file_pseudo); @@ -400,6 +406,11 @@ struct file *alloc_file_pseudo_noaccount(struct inode *inode, return file; } file_init_path(file, &path, fops); + /* + * Disable all fsnotify events for pseudo files by default. + * They may be enabled by caller with file_set_fsnotify_mode(). + */ + file_set_fsnotify_mode(file, FMODE_NONOTIFY); return file; } EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount); diff --git a/fs/open.c b/fs/open.c index 3fcbfff8aede..1be20de9f283 100644 --- a/fs/open.c +++ b/fs/open.c @@ -936,8 +936,8 @@ static int do_dentry_open(struct file *f, /* * Set FMODE_NONOTIFY_* bits according to existing permission watches. - * If FMODE_NONOTIFY was already set for an fanotify fd, this doesn't - * change anything. + * If FMODE_NONOTIFY mode was already set for an fanotify fd or for a + * pseudo file, this call will not change the mode. */ file_set_fsnotify_mode_from_watchers(f); error = fsnotify_open_perm(f); diff --git a/fs/pipe.c b/fs/pipe.c index 94b59045ab44..ce1af7592780 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -960,6 +960,12 @@ int create_pipe_files(struct file **res, int flags) res[1] = f; stream_open(inode, res[0]); stream_open(inode, res[1]); + /* + * Disable permission and pre-content events, but enable legacy + * inotify events for legacy users. + */ + file_set_fsnotify_mode(res[0], FMODE_NONOTIFY_PERM); + file_set_fsnotify_mode(res[1], FMODE_NONOTIFY_PERM); return 0; } diff --git a/net/socket.c b/net/socket.c index 262a28b59c7f..28bae5a94234 100644 --- a/net/socket.c +++ b/net/socket.c @@ -479,6 +479,11 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) sock->file = file; file->private_data = sock; stream_open(SOCK_INODE(sock), file); + /* + * Disable permission and pre-content events, but enable legacy + * inotify events for legacy users. + */ + file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM); return file; } EXPORT_SYMBOL(sock_alloc_file); -- 2.50.1 From 2cc02059fbc79306b53a44b1f1a4444aa3c76598 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 29 Jan 2025 17:06:41 +0100 Subject: [PATCH 02/16] selftests: always check mask returned by statmount(2) STATMOUNT_MNT_OPTS can actually be missing if there are no options. This is a change of behavior since 75ead69a7173 ("fs: don't let statmount return empty strings"). The other checks shouldn't actually trigger, but add them for correctness and for easier debugging if the test fails. Signed-off-by: Miklos Szeredi Link: https://lore.kernel.org/r/20250129160641.35485-1-mszeredi@redhat.com Signed-off-by: Christian Brauner --- .../filesystems/statmount/statmount_test.c | 22 ++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test.c b/tools/testing/selftests/filesystems/statmount/statmount_test.c index 8eb6aa606a0d..46d289611ce8 100644 --- a/tools/testing/selftests/filesystems/statmount/statmount_test.c +++ b/tools/testing/selftests/filesystems/statmount/statmount_test.c @@ -383,6 +383,10 @@ static void test_statmount_mnt_point(void) return; } + if (!(sm->mask & STATMOUNT_MNT_POINT)) { + ksft_test_result_fail("missing STATMOUNT_MNT_POINT in mask\n"); + return; + } if (strcmp(sm->str + sm->mnt_point, "/") != 0) { ksft_test_result_fail("unexpected mount point: '%s' != '/'\n", sm->str + sm->mnt_point); @@ -408,6 +412,10 @@ static void test_statmount_mnt_root(void) strerror(errno)); return; } + if (!(sm->mask & STATMOUNT_MNT_ROOT)) { + ksft_test_result_fail("missing STATMOUNT_MNT_ROOT in mask\n"); + return; + } mnt_root = sm->str + sm->mnt_root; last_root = strrchr(mnt_root, '/'); if (last_root) @@ -437,6 +445,10 @@ static void test_statmount_fs_type(void) strerror(errno)); return; } + if (!(sm->mask & STATMOUNT_FS_TYPE)) { + ksft_test_result_fail("missing STATMOUNT_FS_TYPE in mask\n"); + return; + } fs_type = sm->str + sm->fs_type; for (s = known_fs; s != NULL; s++) { if (strcmp(fs_type, *s) == 0) @@ -464,6 +476,11 @@ static void test_statmount_mnt_opts(void) return; } + if (!(sm->mask & STATMOUNT_MNT_BASIC)) { + ksft_test_result_fail("missing STATMOUNT_MNT_BASIC in mask\n"); + return; + } + while (getline(&line, &len, f_mountinfo) != -1) { int i; char *p, *p2; @@ -514,7 +531,10 @@ static void test_statmount_mnt_opts(void) if (p2) *p2 = '\0'; - statmount_opts = sm->str + sm->mnt_opts; + if (sm->mask & STATMOUNT_MNT_OPTS) + statmount_opts = sm->str + sm->mnt_opts; + else + statmount_opts = ""; if (strcmp(statmount_opts, p) != 0) ksft_test_result_fail( "unexpected mount options: '%s' != '%s'\n", -- 2.50.1 From 711f9b8fbe4f4936302804e246e206f0829f628f Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 3 Feb 2025 23:32:05 +0100 Subject: [PATCH 03/16] fsnotify: disable pre-content and permission events by default After introducing pre-content events, we had a regression related to disabling huge faults on files that should never have pre-content events enabled. This happened because the default f_mode of allocated files (0) does not disable pre-content events. Pre-content events are disabled in file_set_fsnotify_mode_by_watchers() but internal files may not get to call this helper. Initialize f_mode to disable permission and pre-content events for all files and if needed they will be enabled for the callers of file_set_fsnotify_mode_by_watchers(). Fixes: 20bf82a898b6 ("mm: don't allow huge faults for files with pre content watches") Reported-by: Alex Williamson Closes: https://lore.kernel.org/linux-fsdevel/20250131121703.1e4d00a7.alex.williamson@redhat.com/ Tested-by: Alex Williamson Signed-off-by: Amir Goldstein Link: https://lore.kernel.org/r/20250203223205.861346-4-amir73il@gmail.com Signed-off-by: Christian Brauner --- fs/file_table.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/file_table.c b/fs/file_table.c index 35b93da6c5cb..5c00dc38558d 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -194,6 +194,11 @@ static int init_file(struct file *f, int flags, const struct cred *cred) * refcount bumps we should reinitialize the reused file first. */ file_ref_init(&f->f_ref, 1); + /* + * Disable permission and pre-content events for all files by default. + * They may be enabled later by file_set_fsnotify_mode_from_watchers(). + */ + file_set_fsnotify_mode(f, FMODE_NONOTIFY_PERM); return 0; } -- 2.50.1 From 091ee63e36e8289f9067f659a48d497911e49d6f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 4 Feb 2025 14:51:20 +0100 Subject: [PATCH 04/16] pidfs: improve ioctl handling Pidfs supports extensible and non-extensible ioctls. The extensible ioctls need to check for the ioctl number itself not just the ioctl command otherwise both backward- and forward compatibility are broken. The pidfs ioctl handler also needs to look at the type of the ioctl command to guard against cases where "[...] a daemon receives some random file descriptor from a (potentially less privileged) client and expects the FD to be of some specific type, it might call ioctl() on this FD with some type-specific command and expect the call to fail if the FD is of the wrong type; but due to the missing type check, the kernel instead performs some action that userspace didn't expect." (cf. [1]] Link: https://lore.kernel.org/r/20250204-work-pidfs-ioctl-v1-1-04987d239575@kernel.org Link: https://lore.kernel.org/r/CAG48ez2K9A5GwtgqO31u9ZL292we8ZwAA=TJwwEv7wRuJ3j4Lw@mail.gmail.com [1] Fixes: 8ce352818820 ("pidfs: check for valid ioctl commands") Acked-by: Luca Boccassi Reported-by: Jann Horn Cc: stable@vger.kernel.org # v6.13; please backport with 8ce352818820 ("pidfs: check for valid ioctl commands") Signed-off-by: Christian Brauner --- fs/pidfs.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/fs/pidfs.c b/fs/pidfs.c index 049352f973de..63f9699ebac3 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -287,7 +287,6 @@ static bool pidfs_ioctl_valid(unsigned int cmd) switch (cmd) { case FS_IOC_GETVERSION: case PIDFD_GET_CGROUP_NAMESPACE: - case PIDFD_GET_INFO: case PIDFD_GET_IPC_NAMESPACE: case PIDFD_GET_MNT_NAMESPACE: case PIDFD_GET_NET_NAMESPACE: @@ -300,6 +299,17 @@ static bool pidfs_ioctl_valid(unsigned int cmd) return true; } + /* Extensible ioctls require some more careful checks. */ + switch (_IOC_NR(cmd)) { + case _IOC_NR(PIDFD_GET_INFO): + /* + * Try to prevent performing a pidfd ioctl when someone + * erronously mistook the file descriptor for a pidfd. + * This is not perfect but will catch most cases. + */ + return (_IOC_TYPE(cmd) == _IOC_TYPE(PIDFD_GET_INFO)); + } + return false; } -- 2.50.1 From 37d11cfc63604b3886308e2111d845d148ced8bc Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Tue, 4 Feb 2025 22:32:07 +0100 Subject: [PATCH 05/16] vfs: sanity check the length passed to inode_set_cached_link() This costs a strlen() call when instatianating a symlink. Preferably it would be hidden behind VFS_WARN_ON (or compatible), but there is no such facility at the moment. With the facility in place the call can be patched out in production kernels. In the meantime, since the cost is being paid unconditionally, use the result to a fixup the bad caller. This is not expected to persist in the long run (tm). Sample splat: bad length passed for symlink [/tmp/syz-imagegen43743633/file0/file0] (got 131109, expected 37) [rest of WARN blurp goes here] Signed-off-by: Mateusz Guzik Link: https://lore.kernel.org/r/20250204213207.337980-1-mjguzik@gmail.com Signed-off-by: Christian Brauner --- include/linux/fs.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/include/linux/fs.h b/include/linux/fs.h index 7620547432a8..2c3b2f8a621f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -790,6 +790,19 @@ struct inode { static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen) { + int testlen; + + /* + * TODO: patch it into a debug-only check if relevant macros show up. + * In the meantime, since we are suffering strlen even on production kernels + * to find the right length, do a fixup if the wrong value got passed. + */ + testlen = strlen(link); + if (testlen != linklen) { + WARN_ONCE(1, "bad length passed for symlink [%s] (got %d, expected %d)", + link, linklen, testlen); + linklen = testlen; + } inode->i_link = link; inode->i_linklen = linklen; inode->i_opflags |= IOP_CACHED_LINK; -- 2.50.1 From 511121a48bbd12df4ae50a099a8936e833df8c46 Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Wed, 5 Feb 2025 19:42:01 +0100 Subject: [PATCH 06/16] MAINTAINERS: Move Pavel to kernel.org address I need to filter my emails better, switch to pavel@kernel.org address to help with that. Signed-off-by: Pavel Machek Signed-off-by: Linus Torvalds --- CREDITS | 6 ++---- MAINTAINERS | 10 +++++----- 2 files changed, 7 insertions(+), 9 deletions(-) diff --git a/CREDITS b/CREDITS index 1f9f0f078b4a..53d11a46fd69 100644 --- a/CREDITS +++ b/CREDITS @@ -2515,11 +2515,9 @@ D: SLS distribution D: Initial implementation of VC's, pty's and select() N: Pavel Machek -E: pavel@ucw.cz +E: pavel@kernel.org P: 4096R/92DFCE96 4FA7 9EEF FCD4 C44F C585 B8C7 C060 2241 92DF CE96 -D: Softcursor for vga, hypertech cdrom support, vcsa bugfix, nbd, -D: sun4/330 port, capabilities for elf, speedup for rm on ext2, USB, -D: work on suspend-to-ram/disk, killing duplicates from ioctl32, +D: NBD, Sun4/330 port, USB, work on suspend-to-ram/disk, D: Altera SoCFPGA and Nokia N900 support. S: Czech Republic diff --git a/MAINTAINERS b/MAINTAINERS index 873aa2cce4d7..157818de0b55 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9418,7 +9418,7 @@ F: fs/freevxfs/ FREEZER M: "Rafael J. Wysocki" -M: Pavel Machek +M: Pavel Machek L: linux-pm@vger.kernel.org S: Supported F: Documentation/power/freezing-of-tasks.rst @@ -10253,7 +10253,7 @@ F: drivers/video/fbdev/hgafb.c HIBERNATION (aka Software Suspend, aka swsusp) M: "Rafael J. Wysocki" -M: Pavel Machek +M: Pavel Machek L: linux-pm@vger.kernel.org S: Supported B: https://bugzilla.kernel.org @@ -13124,8 +13124,8 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/har F: scripts/leaking_addresses.pl LED SUBSYSTEM -M: Pavel Machek M: Lee Jones +M: Pavel Machek L: linux-leds@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/lee/leds.git @@ -16823,7 +16823,7 @@ F: include/linux/tick.h F: kernel/time/tick*.* NOKIA N900 CAMERA SUPPORT (ET8EK8 SENSOR, AD5820 FOCUS) -M: Pavel Machek +M: Pavel Machek M: Sakari Ailus L: linux-media@vger.kernel.org S: Maintained @@ -22849,7 +22849,7 @@ F: drivers/sh/ SUSPEND TO RAM M: "Rafael J. Wysocki" M: Len Brown -M: Pavel Machek +M: Pavel Machek L: linux-pm@vger.kernel.org S: Supported B: https://bugzilla.kernel.org -- 2.50.1 From 1b3291f00013c86a9bb349d6158a9a7a4f0334fe Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Fri, 7 Feb 2025 03:21:46 +0900 Subject: [PATCH 07/16] MAINTAINERS: Remove myself I no longer have any faith left in the kernel development process or community management approach. Apple/ARM platform development will continue downstream. If I feel like sending some patches upstream in the future myself for whatever subtree I may, or I may not. Anyone who feels like fighting the upstreaming fight themselves is welcome to do so. Signed-off-by: Hector Martin Signed-off-by: Linus Torvalds --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 157818de0b55..20c9e0871215 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2209,7 +2209,6 @@ F: sound/soc/codecs/cs42l84.* F: sound/soc/codecs/ssm3515.c ARM/APPLE MACHINE SUPPORT -M: Hector Martin M: Sven Peter R: Alyssa Rosenzweig L: asahi@lists.linux.dev -- 2.50.1 From f354fc88a72ae83dacd68370f6fa040e5733bcfe Mon Sep 17 00:00:00 2001 From: WangYuli Date: Fri, 7 Feb 2025 15:08:55 +0800 Subject: [PATCH 08/16] kbuild: install-extmod-build: add missing quotation marks for CC variable While attempting to build a Debian packages with CC="ccache gcc", I saw the following error as builddeb builds linux-headers-$KERNELVERSION: make HOSTCC=ccache gcc VPATH= srcroot=. -f ./scripts/Makefile.build obj=debian/linux-headers-6.14.0-rc1/usr/src/linux-headers-6.14.0-rc1/scripts make[6]: *** No rule to make target 'gcc'. Stop. Upon investigation, it seems that one instance of $(CC) variable reference in ./scripts/package/install-extmod-build was missing quotation marks, causing the above error. Add the missing quotation marks around $(CC) to fix build. Fixes: 5f73e7d0386d ("kbuild: refactor cross-compiling linux-headers package") Co-developed-by: Mingcong Bai Signed-off-by: Mingcong Bai Tested-by: WangYuli Signed-off-by: WangYuli Signed-off-by: Masahiro Yamada --- scripts/package/install-extmod-build | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build index bb6e23c1174e..b724626ea0ca 100755 --- a/scripts/package/install-extmod-build +++ b/scripts/package/install-extmod-build @@ -63,7 +63,7 @@ if [ "${CC}" != "${HOSTCC}" ]; then # Clear VPATH and srcroot because the source files reside in the output # directory. # shellcheck disable=SC2016 # $(MAKE), $(CC), and $(build) will be expanded by Make - "${MAKE}" run-command KBUILD_RUN_COMMAND='+$(MAKE) HOSTCC=$(CC) VPATH= srcroot=. $(build)='"${destdir}"/scripts + "${MAKE}" run-command KBUILD_RUN_COMMAND='+$(MAKE) HOSTCC="$(CC)" VPATH= srcroot=. $(build)='"${destdir}"/scripts rm -f "${destdir}/scripts/Kbuild" fi -- 2.50.1 From 8f6629c004b193d23612641c3607e785819e97ab Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 17 Oct 2024 10:09:22 -0700 Subject: [PATCH 09/16] kbuild: Move -Wenum-enum-conversion to W=2 -Wenum-enum-conversion was strengthened in clang-19 to warn for C, which caused the kernel to move it to W=1 in commit 75b5ab134bb5 ("kbuild: Move -Wenum-{compare-conditional,enum-conversion} into W=1") because there were numerous instances that would break builds with -Werror. Unfortunately, this is not a full solution, as more and more developers, subsystems, and distributors are building with W=1 as well, so they continue to see the numerous instances of this warning. Since the move to W=1, there have not been many new instances that have appeared through various build reports and the ones that have appeared seem to be following similar existing patterns, suggesting that most instances of this warning will not be real issues. The only alternatives for silencing this warning are adding casts (which is generally seen as an ugly practice) or refactoring the enums to macro defines or a unified enum (which may be undesirable because of type safety in other parts of the code). Move the warning to W=2, where warnings that occur frequently but may be relevant should reside. Cc: stable@vger.kernel.org Fixes: 75b5ab134bb5 ("kbuild: Move -Wenum-{compare-conditional,enum-conversion} into W=1") Link: https://lore.kernel.org/ZwRA9SOcOjjLJcpi@google.com/ Signed-off-by: Nathan Chancellor Acked-by: Arnd Bergmann Signed-off-by: Linus Torvalds --- scripts/Makefile.extrawarn | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index eb719f6d8d53..a7003c1e66c7 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -133,7 +133,6 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-to-enum-cast) KBUILD_CFLAGS += -Wno-tautological-constant-out-of-range-compare KBUILD_CFLAGS += $(call cc-disable-warning, unaligned-access) KBUILD_CFLAGS += -Wno-enum-compare-conditional -KBUILD_CFLAGS += -Wno-enum-enum-conversion endif endif @@ -157,6 +156,10 @@ KBUILD_CFLAGS += -Wno-missing-field-initializers KBUILD_CFLAGS += -Wno-type-limits KBUILD_CFLAGS += -Wno-shift-negative-value +ifdef CONFIG_CC_IS_CLANG +KBUILD_CFLAGS += -Wno-enum-enum-conversion +endif + ifdef CONFIG_CC_IS_GCC KBUILD_CFLAGS += -Wno-maybe-uninitialized endif -- 2.50.1 From c8c9b1d2d5b4377c72a979f5a26e842a869aefc9 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Sat, 8 Feb 2025 00:15:11 -0500 Subject: [PATCH 10/16] fgraph: Fix set_graph_notrace with setting TRACE_GRAPH_NOTRACE_BIT The code was restructured where the function graph notrace code, that would not trace a function and all its children is done by setting a NOTRACE flag when the function that is not to be traced is hit. There's a TRACE_GRAPH_NOTRACE_BIT which defines the bit in the flags and a TRACE_GRAPH_NOTRACE which is the mask with that bit set. But the restructuring used TRACE_GRAPH_NOTRACE_BIT when it should have used TRACE_GRAPH_NOTRACE. For example: # cd /sys/kernel/tracing # echo set_track_prepare stack_trace_save > set_graph_notrace # echo function_graph > current_tracer # cat trace [..] 0) | __slab_free() { 0) | free_to_partial_list() { 0) | arch_stack_walk() { 0) | __unwind_start() { 0) 0.501 us | get_stack_info(); Where a non filter trace looks like: # echo > set_graph_notrace # cat trace 0) | free_to_partial_list() { 0) | set_track_prepare() { 0) | stack_trace_save() { 0) | arch_stack_walk() { 0) | __unwind_start() { Where the filter should look like: # cat trace 0) | free_to_partial_list() { 0) | _raw_spin_lock_irqsave() { 0) 0.350 us | preempt_count_add(); 0) 0.351 us | do_raw_spin_lock(); 0) 2.440 us | } Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20250208001511.535be150@batman.local.home Fixes: b84214890a9bc ("function_graph: Move graph notrace bit to shadow stack global var") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_functions_graph.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 54d850997c0a..136c750b0b4d 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -198,7 +198,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace, * returning from the function. */ if (ftrace_graph_notrace_addr(trace->func)) { - *task_var |= TRACE_GRAPH_NOTRACE_BIT; + *task_var |= TRACE_GRAPH_NOTRACE; /* * Need to return 1 to have the return called * that will clear the NOTRACE bit. -- 2.50.1 From 7585946243d614bd2cd4e13377be2c711c9539e0 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 8 Feb 2025 18:54:28 +0100 Subject: [PATCH 11/16] PM: sleep: core: Restrict power.set_active propagation Commit 3775fc538f53 ("PM: sleep: core: Synchronize runtime PM status of parents and children") exposed an issue related to simple_pm_bus_pm_ops that uses pm_runtime_force_suspend() and pm_runtime_force_resume() as bus type PM callbacks for the noirq phases of system-wide suspend and resume. The problem is that pm_runtime_force_suspend() does not distinguish runtime-suspended devices from devices for which runtime PM has never been enabled, so if it sees a device with runtime PM status set to RPM_ACTIVE, it will assume that runtime PM is enabled for that device and so it will attempt to suspend it with the help of its runtime PM callbacks which may not be ready for that. As it turns out, this causes simple_pm_bus_runtime_suspend() to crash due to a NULL pointer dereference. Another problem related to the above commit and simple_pm_bus_pm_ops is that setting runtime PM status of a device handled by the latter to RPM_ACTIVE will actually prevent it from being resumed because pm_runtime_force_resume() only resumes devices with runtime PM status set to RPM_SUSPENDED. To mitigate these issues, do not allow power.set_active to propagate beyond the parent of the device with DPM_FLAG_SMART_SUSPEND set that will need to be resumed, which should be a sufficient stop-gap for the time being, but they will need to be properly addressed in the future because in general during system-wide resume it is necessary to resume all devices in a dependency chain in which at least one device is going to be resumed. Fixes: 3775fc538f53 ("PM: sleep: core: Synchronize runtime PM status of parents and children") Closes: https://lore.kernel.org/linux-pm/1c2433d4-7e0f-4395-b841-b8eac7c25651@nvidia.com/ Reported-by: Jon Hunter Tested-by: Johan Hovold Signed-off-by: Rafael J. Wysocki Link: https://patch.msgid.link/6137505.lOV4Wx5bFT@rjwysocki.net --- drivers/base/power/main.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index d497d448e4b2..40e1d8d8a589 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1191,24 +1191,18 @@ static pm_message_t resume_event(pm_message_t sleep_state) return PMSG_ON; } -static void dpm_superior_set_must_resume(struct device *dev, bool set_active) +static void dpm_superior_set_must_resume(struct device *dev) { struct device_link *link; int idx; - if (dev->parent) { + if (dev->parent) dev->parent->power.must_resume = true; - if (set_active) - dev->parent->power.set_active = true; - } idx = device_links_read_lock(); - list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node) { + list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node) link->supplier->power.must_resume = true; - if (set_active) - link->supplier->power.set_active = true; - } device_links_read_unlock(idx); } @@ -1287,9 +1281,12 @@ Skip: dev->power.must_resume = true; if (dev->power.must_resume) { - dev->power.set_active = dev->power.set_active || - dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND); - dpm_superior_set_must_resume(dev, dev->power.set_active); + if (dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND)) { + dev->power.set_active = true; + if (dev->parent && !dev->parent->power.ignore_children) + dev->parent->power.set_active = true; + } + dpm_superior_set_must_resume(dev); } Complete: -- 2.50.1 From a64dcfb451e254085a7daee5fe51bf22959d52d3 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 9 Feb 2025 12:45:03 -0800 Subject: [PATCH 12/16] Linux 6.14-rc2 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 9e0d63d9d94b..89628e354ca7 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Baby Opossum Posse # *DOCUMENTATION* -- 2.50.1 From fa1008e3df6220368b8ea3b004eca501ed546973 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Wed, 18 Dec 2024 22:54:12 +0800 Subject: [PATCH 13/16] ext4: remove unused ext4 journal callback Remove unused ext4 journal callback. Signed-off-by: Kemeng Shi Reviewed-by: Zhang Yi Reviewed-by: Jan Kara Link: https://patch.msgid.link/20241218145414.1422946-2-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/ext4_jbd2.h | 84 --------------------------------------------- fs/ext4/super.c | 14 -------- 2 files changed, 98 deletions(-) diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 0c77697d5e90..3f2596c9e5f2 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -122,90 +122,6 @@ #define EXT4_HT_EXT_CONVERT 11 #define EXT4_HT_MAX 12 -/** - * struct ext4_journal_cb_entry - Base structure for callback information. - * - * This struct is a 'seed' structure for a using with your own callback - * structs. If you are using callbacks you must allocate one of these - * or another struct of your own definition which has this struct - * as it's first element and pass it to ext4_journal_callback_add(). - */ -struct ext4_journal_cb_entry { - /* list information for other callbacks attached to the same handle */ - struct list_head jce_list; - - /* Function to call with this callback structure */ - void (*jce_func)(struct super_block *sb, - struct ext4_journal_cb_entry *jce, int error); - - /* user data goes here */ -}; - -/** - * ext4_journal_callback_add: add a function to call after transaction commit - * @handle: active journal transaction handle to register callback on - * @func: callback function to call after the transaction has committed: - * @sb: superblock of current filesystem for transaction - * @jce: returned journal callback data - * @rc: journal state at commit (0 = transaction committed properly) - * @jce: journal callback data (internal and function private data struct) - * - * The registered function will be called in the context of the journal thread - * after the transaction for which the handle was created has completed. - * - * No locks are held when the callback function is called, so it is safe to - * call blocking functions from within the callback, but the callback should - * not block or run for too long, or the filesystem will be blocked waiting for - * the next transaction to commit. No journaling functions can be used, or - * there is a risk of deadlock. - * - * There is no guaranteed calling order of multiple registered callbacks on - * the same transaction. - */ -static inline void _ext4_journal_callback_add(handle_t *handle, - struct ext4_journal_cb_entry *jce) -{ - /* Add the jce to transaction's private list */ - list_add_tail(&jce->jce_list, &handle->h_transaction->t_private_list); -} - -static inline void ext4_journal_callback_add(handle_t *handle, - void (*func)(struct super_block *sb, - struct ext4_journal_cb_entry *jce, - int rc), - struct ext4_journal_cb_entry *jce) -{ - struct ext4_sb_info *sbi = - EXT4_SB(handle->h_transaction->t_journal->j_private); - - /* Add the jce to transaction's private list */ - jce->jce_func = func; - spin_lock(&sbi->s_md_lock); - _ext4_journal_callback_add(handle, jce); - spin_unlock(&sbi->s_md_lock); -} - - -/** - * ext4_journal_callback_del: delete a registered callback - * @handle: active journal transaction handle on which callback was registered - * @jce: registered journal callback entry to unregister - * Return true if object was successfully removed - */ -static inline bool ext4_journal_callback_try_del(handle_t *handle, - struct ext4_journal_cb_entry *jce) -{ - bool deleted; - struct ext4_sb_info *sbi = - EXT4_SB(handle->h_transaction->t_journal->j_private); - - spin_lock(&sbi->s_md_lock); - deleted = !list_empty(&jce->jce_list); - list_del_init(&jce->jce_list); - spin_unlock(&sbi->s_md_lock); - return deleted; -} - int ext4_mark_iloc_dirty(handle_t *handle, struct inode *inode, diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a50e5c31b937..957b19b53d5b 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -502,25 +502,11 @@ static void ext4_maybe_update_superblock(struct super_block *sb) static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) { struct super_block *sb = journal->j_private; - struct ext4_sb_info *sbi = EXT4_SB(sb); - int error = is_journal_aborted(journal); - struct ext4_journal_cb_entry *jce; BUG_ON(txn->t_state == T_FINISHED); ext4_process_freed_data(sb, txn->t_tid); ext4_maybe_update_superblock(sb); - - spin_lock(&sbi->s_md_lock); - while (!list_empty(&txn->t_private_list)) { - jce = list_entry(txn->t_private_list.next, - struct ext4_journal_cb_entry, jce_list); - list_del_init(&jce->jce_list); - spin_unlock(&sbi->s_md_lock); - jce->jce_func(sb, jce, error); - spin_lock(&sbi->s_md_lock); - } - spin_unlock(&sbi->s_md_lock); } /* -- 2.50.1 From 06b9e91425b26b5e782f82a043a3f6c6354947c2 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Wed, 18 Dec 2024 22:54:13 +0800 Subject: [PATCH 14/16] jbd2: remove unused transaction->t_private_list After we remove ext4 journal callback, transaction->t_private_list is not used anymore. Just remove unused transaction->t_private_list. Signed-off-by: Kemeng Shi Reviewed-by: Zhang Yi Link: https://patch.msgid.link/20241218145414.1422946-3-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o --- Documentation/filesystems/journalling.rst | 4 +--- fs/jbd2/transaction.c | 1 - include/linux/jbd2.h | 6 ------ 3 files changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/filesystems/journalling.rst b/Documentation/filesystems/journalling.rst index 0254f7d57429..863e93e623f7 100644 --- a/Documentation/filesystems/journalling.rst +++ b/Documentation/filesystems/journalling.rst @@ -111,9 +111,7 @@ a callback function when the transaction is finally committed to disk, so that you can do some of your own management. You ask the journalling layer for calling the callback by simply setting ``journal->j_commit_callback`` function pointer and that function is -called after each transaction commit. You can also use -``transaction->t_private_list`` for attaching entries to a transaction -that need processing when the transaction commits. +called after each transaction commit. JBD2 also provides a way to block all transaction updates via jbd2_journal_lock_updates() / diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 66513c18ca29..9fe17e290c21 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -92,7 +92,6 @@ static void jbd2_get_transaction(journal_t *journal, atomic_set(&transaction->t_outstanding_revokes, 0); atomic_set(&transaction->t_handle_count, 0); INIT_LIST_HEAD(&transaction->t_inode_list); - INIT_LIST_HEAD(&transaction->t_private_list); /* Set up the commit timer for the new transaction. */ journal->j_commit_timer.expires = round_jiffies_up(transaction->t_expires); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 561025b4f3d9..053444f7a1d0 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -700,12 +700,6 @@ struct transaction_s /* Disk flush needs to be sent to fs partition [no locking] */ int t_need_data_flush; - - /* - * For use by the filesystem to store fs-specific data - * structures associated with the transaction - */ - struct list_head t_private_list; }; struct transaction_run_stats_s { -- 2.50.1 From 5e22ff3bc9358f994e65c870e2c4a8002ba81791 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Wed, 18 Dec 2024 22:54:14 +0800 Subject: [PATCH 15/16] ext4: remove unneeded forward declaration Remove unneeded forward declaration of ext4_destroy_lazyinit_thread(). Signed-off-by: Kemeng Shi Reviewed-by: Zhang Yi Reviewed-by: Jan Kara Link: https://patch.msgid.link/20241218145414.1422946-4-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 957b19b53d5b..a963ffda692a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -79,7 +79,6 @@ static int ext4_unfreeze(struct super_block *sb); static int ext4_freeze(struct super_block *sb); static inline int ext2_feature_set_ok(struct super_block *sb); static inline int ext3_feature_set_ok(struct super_block *sb); -static void ext4_destroy_lazyinit_thread(void); static void ext4_unregister_li_request(struct super_block *sb); static void ext4_clear_request_list(void); static struct inode *ext4_get_journal_inode(struct super_block *sb, -- 2.50.1 From 17207d0bb209e8b40f27d7f3f96e82a78af0bf2c Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Fri, 20 Dec 2024 09:16:28 +0800 Subject: [PATCH 16/16] ext4: remove writable userspace mappings before truncating page cache When zeroing a range of folios on the filesystem which block size is less than the page size, the file's mapped blocks within one page will be marked as unwritten, we should remove writable userspace mappings to ensure that ext4_page_mkwrite() can be called during subsequent write access to these partial folios. Otherwise, data written by subsequent mmap writes may not be saved to disk. $mkfs.ext4 -b 1024 /dev/vdb $mount /dev/vdb /mnt $xfs_io -t -f -c "pwrite -S 0x58 0 4096" -c "mmap -rw 0 4096" \ -c "mwrite -S 0x5a 2048 2048" -c "fzero 2048 2048" \ -c "mwrite -S 0x59 2048 2048" -c "close" /mnt/foo $od -Ax -t x1z /mnt/foo 000000 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 * 000800 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 * 001000 $umount /mnt && mount /dev/vdb /mnt $od -Ax -t x1z /mnt/foo 000000 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 * 000800 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 * 001000 Fix this by introducing ext4_truncate_page_cache_block_range() to remove writable userspace mappings when truncating a partial folio range. Additionally, move the journal data mode-specific handlers and truncate_pagecache_range() into this function, allowing it to serve as a common helper that correctly manages the page cache in preparation for block range manipulations. Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Reviewed-by: Ojaswin Mujoo Link: https://patch.msgid.link/20241220011637.1157197-2-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/ext4.h | 2 ++ fs/ext4/extents.c | 19 ++++---------- fs/ext4/inode.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 70 insertions(+), 14 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 4e7de7eaa374..902b7c00c240 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3001,6 +3001,8 @@ extern int ext4_inode_attach_jinode(struct inode *inode); extern int ext4_can_truncate(struct inode *inode); extern int ext4_truncate(struct inode *); extern int ext4_break_layouts(struct inode *); +extern int ext4_truncate_page_cache_block_range(struct inode *inode, + loff_t start, loff_t end); extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length); extern void ext4_set_inode_flags(struct inode *, bool init); extern int ext4_alloc_da_blocks(struct inode *inode); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index a07a98a4b97a..8dc6b4271b15 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4667,22 +4667,13 @@ static long ext4_zero_range(struct file *file, loff_t offset, goto out_mutex; } - /* - * For journalled data we need to write (and checkpoint) pages - * before discarding page cache to avoid inconsitent data on - * disk in case of crash before zeroing trans is committed. - */ - if (ext4_should_journal_data(inode)) { - ret = filemap_write_and_wait_range(mapping, start, - end - 1); - if (ret) { - filemap_invalidate_unlock(mapping); - goto out_mutex; - } + /* Now release the pages and zero block aligned part of pages */ + ret = ext4_truncate_page_cache_block_range(inode, start, end); + if (ret) { + filemap_invalidate_unlock(mapping); + goto out_mutex; } - /* Now release the pages and zero block aligned part of pages */ - truncate_pagecache_range(inode, start, end - 1); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7c54ae5fcbd4..a569b66103a3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -3902,6 +3903,68 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, return ret; } +static inline void ext4_truncate_folio(struct inode *inode, + loff_t start, loff_t end) +{ + unsigned long blocksize = i_blocksize(inode); + struct folio *folio; + + /* Nothing to be done if no complete block needs to be truncated. */ + if (round_up(start, blocksize) >= round_down(end, blocksize)) + return; + + folio = filemap_lock_folio(inode->i_mapping, start >> PAGE_SHIFT); + if (IS_ERR(folio)) + return; + + if (folio_mkclean(folio)) + folio_mark_dirty(folio); + folio_unlock(folio); + folio_put(folio); +} + +int ext4_truncate_page_cache_block_range(struct inode *inode, + loff_t start, loff_t end) +{ + unsigned long blocksize = i_blocksize(inode); + int ret; + + /* + * For journalled data we need to write (and checkpoint) pages + * before discarding page cache to avoid inconsitent data on disk + * in case of crash before freeing or unwritten converting trans + * is committed. + */ + if (ext4_should_journal_data(inode)) { + ret = filemap_write_and_wait_range(inode->i_mapping, start, + end - 1); + if (ret) + return ret; + goto truncate_pagecache; + } + + /* + * If the block size is less than the page size, the file's mapped + * blocks within one page could be freed or converted to unwritten. + * So it's necessary to remove writable userspace mappings, and then + * ext4_page_mkwrite() can be called during subsequent write access + * to these partial folios. + */ + if (!IS_ALIGNED(start | end, PAGE_SIZE) && + blocksize < PAGE_SIZE && start < inode->i_size) { + loff_t page_boundary = round_up(start, PAGE_SIZE); + + ext4_truncate_folio(inode, start, min(page_boundary, end)); + if (end > page_boundary) + ext4_truncate_folio(inode, + round_down(end, PAGE_SIZE), end); + } + +truncate_pagecache: + truncate_pagecache_range(inode, start, end - 1); + return 0; +} + static void ext4_wait_dax_page(struct inode *inode) { filemap_invalidate_unlock(inode->i_mapping); -- 2.50.1