From 76f9377cd2ab7a9220c25d33940d9ca20d368172 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Thu, 19 Mar 2026 17:51:45 -0700 Subject: writeback: don't block sync for filesystems with no data integrity guarantees Add a SB_I_NO_DATA_INTEGRITY superblock flag for filesystems that cannot guarantee data persistence on sync (eg fuse). For superblocks with this flag set, sync kicks off writeback of dirty inodes but does not wait for the flusher threads to complete the writeback. This replaces the per-inode AS_NO_DATA_INTEGRITY mapping flag added in commit f9a49aa302a0 ("fs/writeback: skip AS_NO_DATA_INTEGRITY mappings in wait_sb_inodes()"). The flag belongs at the superblock level because data integrity is a filesystem-wide property, not a per-inode one. Having this flag at the superblock level also allows us to skip having to iterate every dirty inode in wait_sb_inodes() only to skip each inode individually. Prior to this commit, mappings with no data integrity guarantees skipped waiting on writeback completion but still waited on the flusher threads to finish initiating the writeback. Waiting on the flusher threads is unnecessary. This commit kicks off writeback but does not wait on the flusher threads. This change properly addresses a recent report [1] for a suspend-to-RAM hang seen on fuse-overlayfs that was caused by waiting on the flusher threads to finish: Workqueue: pm_fs_sync pm_fs_sync_work_fn Call Trace: __schedule+0x457/0x1720 schedule+0x27/0xd0 wb_wait_for_completion+0x97/0xe0 sync_inodes_sb+0xf8/0x2e0 __iterate_supers+0xdc/0x160 ksys_sync+0x43/0xb0 pm_fs_sync_work_fn+0x17/0xa0 process_one_work+0x193/0x350 worker_thread+0x1a1/0x310 kthread+0xfc/0x240 ret_from_fork+0x243/0x280 ret_from_fork_asm+0x1a/0x30 On fuse this is problematic because there are paths that may cause the flusher thread to block (eg if systemd freezes the user session cgroups first, which freezes the fuse daemon, before invoking the kernel suspend. The kernel suspend triggers ->write_node() which on fuse issues a synchronous setattr request, which cannot be processed since the daemon is frozen. Or if the daemon is buggy and cannot properly complete writeback, initiating writeback on a dirty folio already under writeback leads to writeback_get_folio() -> folio_prepare_writeback() -> unconditional wait on writeback to finish, which will cause a hang). This commit restores fuse to its prior behavior before tmp folios were removed, where sync was essentially a no-op. [1] https://lore.kernel.org/linux-fsdevel/CAJnrk1a-asuvfrbKXbEwwDSctvemF+6zfhdnuzO65Pt8HsFSRw@mail.gmail.com/T/#m632c4648e9cafc4239299887109ebd880ac6c5c1 Fixes: 0c58a97f919c ("fuse: remove tmp folio for writebacks and internal rb tree") Reported-by: John Cc: stable@vger.kernel.org Signed-off-by: Joanne Koong Link: https://patch.msgid.link/20260320005145.2483161-2-joannelkoong@gmail.com Reviewed-by: Jan Kara Reviewed-by: David Hildenbrand (Arm) Signed-off-by: Christian Brauner --- include/linux/fs/super_types.h | 1 + include/linux/pagemap.h | 11 ----------- 2 files changed, 1 insertion(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h index fa7638b81246..383050e7fdf5 100644 --- a/include/linux/fs/super_types.h +++ b/include/linux/fs/super_types.h @@ -338,5 +338,6 @@ struct super_block { #define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ #define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ #define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */ +#define SB_I_NO_DATA_INTEGRITY 0x00008000 /* fs cannot guarantee data persistence on sync */ #endif /* _LINUX_FS_SUPER_TYPES_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ec442af3f886..31a848485ad9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -210,7 +210,6 @@ enum mapping_flags { AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9, AS_KERNEL_FILE = 10, /* mapping for a fake kernel file that shouldn't account usage to user cgroups */ - AS_NO_DATA_INTEGRITY = 11, /* no data integrity guarantees */ /* Bits 16-25 are used for FOLIO_ORDER */ AS_FOLIO_ORDER_BITS = 5, AS_FOLIO_ORDER_MIN = 16, @@ -346,16 +345,6 @@ static inline bool mapping_writeback_may_deadlock_on_reclaim(const struct addres return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); } -static inline void mapping_set_no_data_integrity(struct address_space *mapping) -{ - set_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); -} - -static inline bool mapping_no_data_integrity(const struct address_space *mapping) -{ - return test_bit(AS_NO_DATA_INTEGRITY, &mapping->flags); -} - static inline gfp_t mapping_gfp_mask(const struct address_space *mapping) { return mapping->gfp_mask; -- cgit v1.2.3 From a85b46db143fda5869e7d8df8f258ccef5fa1719 Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Fri, 13 Mar 2026 14:11:39 -0400 Subject: btrfs: tracepoints: get correct superblock from dentry in event btrfs_sync_file() If overlay is used on top of btrfs, dentry->d_sb translates to overlay's super block and fsid assignment will lead to a crash. Use file_inode(file)->i_sb to always get btrfs_sb. Reviewed-by: Boris Burkov Signed-off-by: Goldwyn Rodrigues Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 125bdc166bfe..0864700f76e0 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -769,12 +769,15 @@ TRACE_EVENT(btrfs_sync_file, ), TP_fast_assign( - const struct dentry *dentry = file->f_path.dentry; - const struct inode *inode = d_inode(dentry); + struct dentry *dentry = file_dentry(file); + struct inode *inode = file_inode(file); + struct dentry *parent = dget_parent(dentry); + struct inode *parent_inode = d_inode(parent); - TP_fast_assign_fsid(btrfs_sb(file->f_path.dentry->d_sb)); + dput(parent); + TP_fast_assign_fsid(btrfs_sb(inode->i_sb)); __entry->ino = btrfs_ino(BTRFS_I(inode)); - __entry->parent = btrfs_ino(BTRFS_I(d_inode(dentry->d_parent))); + __entry->parent = btrfs_ino(BTRFS_I(parent_inode)); __entry->datasync = datasync; __entry->root_objectid = btrfs_root_id(BTRFS_I(inode)->root); ), -- cgit v1.2.3 From cc34d77dd48708d810c12bfd6f5bf03304f6c824 Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Tue, 24 Mar 2026 01:59:15 +0100 Subject: spi: use generic driver_override infrastructure When a driver is probed through __driver_attach(), the bus' match() callback is called without the device lock held, thus accessing the driver_override field without a lock, which can cause a UAF. Fix this by using the driver-core driver_override infrastructure taking care of proper locking internally. Note that calling match() from __driver_attach() without the device lock held is intentional. [1] Also note that we do not enable the driver_override feature of struct bus_type, as SPI - in contrast to most other buses - passes "" to sysfs_emit() when the driver_override pointer is NULL. Thus, printing "\n" instead of "(null)\n". Link: https://lore.kernel.org/driver-core/DGRGTIRHA62X.3RY09D9SOK77P@kernel.org/ [1] Reported-by: Gui-Dong Han Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220789 Fixes: 5039563e7c25 ("spi: Add driver_override SPI device attribute") Signed-off-by: Danilo Krummrich Link: https://patch.msgid.link/20260324005919.2408620-12-dakr@kernel.org Signed-off-by: Mark Brown --- drivers/spi/spi.c | 19 +++++++------------ include/linux/spi/spi.h | 5 ----- 2 files changed, 7 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 53dee314d76a..4101c2803eb3 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -50,7 +50,6 @@ static void spidev_release(struct device *dev) struct spi_device *spi = to_spi_device(dev); spi_controller_put(spi->controller); - kfree(spi->driver_override); free_percpu(spi->pcpu_statistics); kfree(spi); } @@ -73,10 +72,9 @@ static ssize_t driver_override_store(struct device *dev, struct device_attribute *a, const char *buf, size_t count) { - struct spi_device *spi = to_spi_device(dev); int ret; - ret = driver_set_override(dev, &spi->driver_override, buf, count); + ret = __device_set_driver_override(dev, buf, count); if (ret) return ret; @@ -86,13 +84,8 @@ static ssize_t driver_override_store(struct device *dev, static ssize_t driver_override_show(struct device *dev, struct device_attribute *a, char *buf) { - const struct spi_device *spi = to_spi_device(dev); - ssize_t len; - - device_lock(dev); - len = sysfs_emit(buf, "%s\n", spi->driver_override ? : ""); - device_unlock(dev); - return len; + guard(spinlock)(&dev->driver_override.lock); + return sysfs_emit(buf, "%s\n", dev->driver_override.name ?: ""); } static DEVICE_ATTR_RW(driver_override); @@ -376,10 +369,12 @@ static int spi_match_device(struct device *dev, const struct device_driver *drv) { const struct spi_device *spi = to_spi_device(dev); const struct spi_driver *sdrv = to_spi_driver(drv); + int ret; /* Check override first, and if set, only use the named driver */ - if (spi->driver_override) - return strcmp(spi->driver_override, drv->name) == 0; + ret = device_match_driver_override(dev, drv); + if (ret >= 0) + return ret; /* Attempt an OF style match */ if (of_driver_match_device(dev, drv)) diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index af7cfee7b8f6..0dc671c07d3a 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -159,10 +159,6 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg, * @modalias: Name of the driver to use with this device, or an alias * for that name. This appears in the sysfs "modalias" attribute * for driver coldplugging, and in uevents used for hotplugging - * @driver_override: If the name of a driver is written to this attribute, then - * the device will bind to the named driver and only the named driver. - * Do not set directly, because core frees it; use driver_set_override() to - * set or clear it. * @pcpu_statistics: statistics for the spi_device * @word_delay: delay to be inserted between consecutive * words of a transfer @@ -224,7 +220,6 @@ struct spi_device { void *controller_state; void *controller_data; char modalias[SPI_NAME_SIZE]; - const char *driver_override; /* The statistics */ struct spi_statistics __percpu *pcpu_statistics; -- cgit v1.2.3 From 1b164b876c36c3eb5561dd9b37702b04401b0166 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 24 Mar 2026 10:21:25 -1000 Subject: cgroup: Wait for dying tasks to leave on rmdir a72f73c4dd9b ("cgroup: Don't expose dead tasks in cgroup") hid PF_EXITING tasks from cgroup.procs so that systemd doesn't see tasks that have already been reaped via waitpid(). However, the populated counter (nr_populated_csets) is only decremented when the task later passes through cgroup_task_dead() in finish_task_switch(). This means cgroup.procs can appear empty while the cgroup is still populated, causing rmdir to fail with -EBUSY. Fix this by making cgroup_rmdir() wait for dying tasks to fully leave. If the cgroup is populated but all remaining tasks have PF_EXITING set (the task iterator returns none due to the existing filter), wait for a kick from cgroup_task_dead() and retry. The wait is brief as tasks are removed from the cgroup's css_set between PF_EXITING assertion in do_exit() and cgroup_task_dead() in finish_task_switch(). v2: cgroup_is_populated() true to false transition happens under css_set_lock not cgroup_mutex, so retest under css_set_lock before sleeping to avoid missed wakeups (Sebastian). Fixes: a72f73c4dd9b ("cgroup: Don't expose dead tasks in cgroup") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202603222104.2c81684e-lkp@intel.com Reported-by: Sebastian Andrzej Siewior Signed-off-by: Tejun Heo Reviewed-by: Sebastian Andrzej Siewior Cc: Bert Karwatzki Cc: Michal Koutny Cc: cgroups@vger.kernel.org --- include/linux/cgroup-defs.h | 3 ++ kernel/cgroup/cgroup.c | 86 +++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 86 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index bb92f5c169ca..7f87399938fa 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -609,6 +609,9 @@ struct cgroup { /* used to wait for offlining of csses */ wait_queue_head_t offline_waitq; + /* used by cgroup_rmdir() to wait for dying tasks to leave */ + wait_queue_head_t dying_populated_waitq; + /* used to schedule release agent */ struct work_struct release_agent_work; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 01fc2a93f3ef..2163054e1aa6 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2126,6 +2126,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) #endif init_waitqueue_head(&cgrp->offline_waitq); + init_waitqueue_head(&cgrp->dying_populated_waitq); INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent); } @@ -6224,6 +6225,76 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) return 0; }; +/** + * cgroup_drain_dying - wait for dying tasks to leave before rmdir + * @cgrp: the cgroup being removed + * + * The PF_EXITING filter in css_task_iter_advance() hides exiting tasks from + * cgroup.procs so that userspace (e.g. systemd) doesn't see tasks that have + * already been reaped via waitpid(). However, the populated counter + * (nr_populated_csets) is only decremented when the task later passes through + * cgroup_task_dead() in finish_task_switch(). This creates a window where + * cgroup.procs appears empty but cgroup_is_populated() is still true, causing + * rmdir to fail with -EBUSY. + * + * This function bridges that gap. If the cgroup is populated but all remaining + * tasks have PF_EXITING set, we wait for cgroup_task_dead() to process them. + * Tasks are removed from the cgroup's css_set in cgroup_task_dead() called from + * finish_task_switch(). As the window between PF_EXITING and cgroup_task_dead() + * is short, the number of PF_EXITING tasks on the list is small and the wait + * is brief. + * + * Each cgroup_task_dead() kicks the waitqueue via cset->cgrp_links, and we + * retry the full check from scratch. + * + * Must be called with cgroup_mutex held. + */ +static int cgroup_drain_dying(struct cgroup *cgrp) + __releases(&cgroup_mutex) __acquires(&cgroup_mutex) +{ + struct css_task_iter it; + struct task_struct *task; + DEFINE_WAIT(wait); + + lockdep_assert_held(&cgroup_mutex); +retry: + if (!cgroup_is_populated(cgrp)) + return 0; + + /* Same iterator as cgroup.threads - if any task is visible, it's busy */ + css_task_iter_start(&cgrp->self, 0, &it); + task = css_task_iter_next(&it); + css_task_iter_end(&it); + + if (task) + return -EBUSY; + + /* + * All remaining tasks are PF_EXITING and will pass through + * cgroup_task_dead() shortly. Wait for a kick and retry. + * + * cgroup_is_populated() can't transition from false to true while + * we're holding cgroup_mutex, but the true to false transition + * happens under css_set_lock (via cgroup_task_dead()). We must + * retest and prepare_to_wait() under css_set_lock. Otherwise, the + * transition can happen between our first test and + * prepare_to_wait(), and we sleep with no one to wake us. + */ + spin_lock_irq(&css_set_lock); + if (!cgroup_is_populated(cgrp)) { + spin_unlock_irq(&css_set_lock); + return 0; + } + prepare_to_wait(&cgrp->dying_populated_waitq, &wait, + TASK_UNINTERRUPTIBLE); + spin_unlock_irq(&css_set_lock); + mutex_unlock(&cgroup_mutex); + schedule(); + finish_wait(&cgrp->dying_populated_waitq, &wait); + mutex_lock(&cgroup_mutex); + goto retry; +} + int cgroup_rmdir(struct kernfs_node *kn) { struct cgroup *cgrp; @@ -6233,9 +6304,12 @@ int cgroup_rmdir(struct kernfs_node *kn) if (!cgrp) return 0; - ret = cgroup_destroy_locked(cgrp); - if (!ret) - TRACE_CGROUP_PATH(rmdir, cgrp); + ret = cgroup_drain_dying(cgrp); + if (!ret) { + ret = cgroup_destroy_locked(cgrp); + if (!ret) + TRACE_CGROUP_PATH(rmdir, cgrp); + } cgroup_kn_unlock(kn); return ret; @@ -6995,6 +7069,7 @@ void cgroup_task_exit(struct task_struct *tsk) static void do_cgroup_task_dead(struct task_struct *tsk) { + struct cgrp_cset_link *link; struct css_set *cset; unsigned long flags; @@ -7008,6 +7083,11 @@ static void do_cgroup_task_dead(struct task_struct *tsk) if (thread_group_leader(tsk) && atomic_read(&tsk->signal->live)) list_add_tail(&tsk->cg_list, &cset->dying_tasks); + /* kick cgroup_drain_dying() waiters, see cgroup_rmdir() */ + list_for_each_entry(link, &cset->cgrp_links, cgrp_link) + if (waitqueue_active(&link->cgrp->dying_populated_waitq)) + wake_up(&link->cgrp->dying_populated_waitq); + if (dl_task(tsk)) dec_dl_tasks_cs(tsk); -- cgit v1.2.3 From c991ca3238410b611a2ce59adeca9b55850aff69 Mon Sep 17 00:00:00 2001 From: Shuming Fan Date: Wed, 25 Mar 2026 17:20:17 +0800 Subject: ASoC: SDCA: remove the max count of initialization table The number of the initialization table may exceed 2048. Therefore, this patch removes the limitation and allows the driver to allocate memory dynamically based on the size of the initialization table. Signed-off-by: Shuming Fan Reviewed-by: Charles Keepax Link: https://patch.msgid.link/20260325092017.3221640-1-shumingf@realtek.com Signed-off-by: Mark Brown --- include/sound/sdca_function.h | 5 ----- sound/soc/sdca/sdca_functions.c | 3 --- 2 files changed, 8 deletions(-) (limited to 'include') diff --git a/include/sound/sdca_function.h b/include/sound/sdca_function.h index 79bd5a7a0f88..0e871c786513 100644 --- a/include/sound/sdca_function.h +++ b/include/sound/sdca_function.h @@ -26,11 +26,6 @@ struct sdca_function_desc; */ #define SDCA_MAX_ENTITY_COUNT 128 -/* - * Sanity check on number of initialization writes, can be expanded if needed. - */ -#define SDCA_MAX_INIT_COUNT 2048 - /* * The Cluster IDs are 16-bit, so a maximum of 65535 Clusters per * function can be represented, however limit this to a slightly diff --git a/sound/soc/sdca/sdca_functions.c b/sound/soc/sdca/sdca_functions.c index e0ed593697ba..d27ffb25ad97 100644 --- a/sound/soc/sdca/sdca_functions.c +++ b/sound/soc/sdca/sdca_functions.c @@ -216,9 +216,6 @@ static int find_sdca_init_table(struct device *dev, } else if (num_init_writes % sizeof(*raw) != 0) { dev_err(dev, "%pfwP: init table size invalid\n", function_node); return -EINVAL; - } else if ((num_init_writes / sizeof(*raw)) > SDCA_MAX_INIT_COUNT) { - dev_err(dev, "%pfwP: maximum init table size exceeded\n", function_node); - return -EINVAL; } raw = kzalloc(num_init_writes, GFP_KERNEL); -- cgit v1.2.3 From 0e764b9d46071668969410ec5429be0e2f38c6d3 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 25 Mar 2026 08:20:17 +0000 Subject: netfs: Fix the handling of stream->front by removing it The netfs_io_stream::front member is meant to point to the subrequest currently being collected on a stream, but it isn't actually used this way by direct write (which mostly ignores it). However, there's a tracepoint which looks at it. Further, stream->front is actually redundant with stream->subrequests.next. Fix the potential problem in the direct code by just removing the member and using stream->subrequests.next instead, thereby also simplifying the code. Fixes: a0b4c7a49137 ("netfs: Fix unbuffered/DIO writes to dispatch subrequests in strict sequence") Reported-by: Paulo Alcantara Signed-off-by: David Howells Link: https://patch.msgid.link/4158599.1774426817@warthog.procyon.org.uk Reviewed-by: Paulo Alcantara (Red Hat) cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/buffered_read.c | 3 +-- fs/netfs/direct_read.c | 3 +-- fs/netfs/direct_write.c | 1 - fs/netfs/read_collect.c | 4 ++-- fs/netfs/read_single.c | 1 - fs/netfs/write_collect.c | 4 ++-- fs/netfs/write_issue.c | 3 +-- include/linux/netfs.h | 1 - include/trace/events/netfs.h | 8 ++++---- 9 files changed, 11 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 88a0d801525f..a8c0d86118c5 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -171,9 +171,8 @@ static void netfs_queue_read(struct netfs_io_request *rreq, spin_lock(&rreq->lock); list_add_tail(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { - stream->front = subreq; if (!stream->active) { - stream->collected_to = stream->front->start; + stream->collected_to = subreq->start; /* Store list pointers before active flag */ smp_store_release(&stream->active, true); } diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c index a498ee8d6674..f72e6da88cca 100644 --- a/fs/netfs/direct_read.c +++ b/fs/netfs/direct_read.c @@ -71,9 +71,8 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) spin_lock(&rreq->lock); list_add_tail(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { - stream->front = subreq; if (!stream->active) { - stream->collected_to = stream->front->start; + stream->collected_to = subreq->start; /* Store list pointers before active flag */ smp_store_release(&stream->active, true); } diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index 4d9760e36c11..f9ab69de3e29 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -111,7 +111,6 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) netfs_prepare_write(wreq, stream, wreq->start + wreq->transferred); subreq = stream->construct; stream->construct = NULL; - stream->front = NULL; } /* Check if (re-)preparation failed. */ diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 137f0e28a44c..e5f6665b3341 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -205,7 +205,8 @@ reassess: * in progress. The issuer thread may be adding stuff to the tail * whilst we're doing this. */ - front = READ_ONCE(stream->front); + front = list_first_entry_or_null(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); while (front) { size_t transferred; @@ -301,7 +302,6 @@ reassess: list_del_init(&front->rreq_link); front = list_first_entry_or_null(&stream->subrequests, struct netfs_io_subrequest, rreq_link); - stream->front = front; spin_unlock(&rreq->lock); netfs_put_subrequest(remove, notes & ABANDON_SREQ ? diff --git a/fs/netfs/read_single.c b/fs/netfs/read_single.c index 8e6264f62a8f..d0e23bc42445 100644 --- a/fs/netfs/read_single.c +++ b/fs/netfs/read_single.c @@ -107,7 +107,6 @@ static int netfs_single_dispatch_read(struct netfs_io_request *rreq) spin_lock(&rreq->lock); list_add_tail(&subreq->rreq_link, &stream->subrequests); trace_netfs_sreq(subreq, netfs_sreq_trace_added); - stream->front = subreq; /* Store list pointers before active flag */ smp_store_release(&stream->active, true); spin_unlock(&rreq->lock); diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 83eb3dc1adf8..b194447f4b11 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -228,7 +228,8 @@ reassess_streams: if (!smp_load_acquire(&stream->active)) continue; - front = stream->front; + front = list_first_entry_or_null(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); while (front) { trace_netfs_collect_sreq(wreq, front); //_debug("sreq [%x] %llx %zx/%zx", @@ -279,7 +280,6 @@ reassess_streams: list_del_init(&front->rreq_link); front = list_first_entry_or_null(&stream->subrequests, struct netfs_io_subrequest, rreq_link); - stream->front = front; spin_unlock(&wreq->lock); netfs_put_subrequest(remove, notes & SAW_FAILURE ? diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 437268f65640..2db688f94125 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -206,9 +206,8 @@ void netfs_prepare_write(struct netfs_io_request *wreq, spin_lock(&wreq->lock); list_add_tail(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { - stream->front = subreq; if (!stream->active) { - stream->collected_to = stream->front->start; + stream->collected_to = subreq->start; /* Write list pointers before active flag */ smp_store_release(&stream->active, true); } diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 72ee7d210a74..ba17ac5bf356 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -140,7 +140,6 @@ struct netfs_io_stream { void (*issue_write)(struct netfs_io_subrequest *subreq); /* Collection tracking */ struct list_head subrequests; /* Contributory I/O operations */ - struct netfs_io_subrequest *front; /* Op being collected */ unsigned long long collected_to; /* Position we've collected results to */ size_t transferred; /* The amount transferred from this stream */ unsigned short error; /* Aggregate error for the stream */ diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 2d366be46a1c..cbe28211106c 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -740,19 +740,19 @@ TRACE_EVENT(netfs_collect_stream, __field(unsigned int, wreq) __field(unsigned char, stream) __field(unsigned long long, collected_to) - __field(unsigned long long, front) + __field(unsigned long long, issued_to) ), TP_fast_assign( __entry->wreq = wreq->debug_id; __entry->stream = stream->stream_nr; __entry->collected_to = stream->collected_to; - __entry->front = stream->front ? stream->front->start : UINT_MAX; + __entry->issued_to = atomic64_read(&wreq->issued_to); ), - TP_printk("R=%08x[%x:] cto=%llx frn=%llx", + TP_printk("R=%08x[%x:] cto=%llx ito=%llx", __entry->wreq, __entry->stream, - __entry->collected_to, __entry->front) + __entry->collected_to, __entry->issued_to) ); TRACE_EVENT(netfs_folioq, -- cgit v1.2.3 From 190a8c48ff623c3d67cb295b4536a660db2012aa Mon Sep 17 00:00:00 2001 From: Hao-Yu Yang Date: Fri, 13 Mar 2026 20:47:56 +0800 Subject: futex: Fix UaF between futex_key_to_node_opt() and vma_replace_policy() During futex_key_to_node_opt() execution, vma->vm_policy is read under speculative mmap lock and RCU. Concurrently, mbind() may call vma_replace_policy() which frees the old mempolicy immediately via kmem_cache_free(). This creates a race where __futex_key_to_node() dereferences a freed mempolicy pointer, causing a use-after-free read of mpol->mode. [ 151.412631] BUG: KASAN: slab-use-after-free in __futex_key_to_node (kernel/futex/core.c:349) [ 151.414046] Read of size 2 at addr ffff888001c49634 by task e/87 [ 151.415969] Call Trace: [ 151.416732] __asan_load2 (mm/kasan/generic.c:271) [ 151.416777] __futex_key_to_node (kernel/futex/core.c:349) [ 151.416822] get_futex_key (kernel/futex/core.c:374 kernel/futex/core.c:386 kernel/futex/core.c:593) Fix by adding rcu to __mpol_put(). Fixes: c042c505210d ("futex: Implement FUTEX2_MPOL") Reported-by: Hao-Yu Yang Suggested-by: Eric Dumazet Signed-off-by: Hao-Yu Yang Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Eric Dumazet Acked-by: David Hildenbrand (Arm) Link: https://patch.msgid.link/20260324174418.GB1850007@noisy.programming.kicks-ass.net --- include/linux/mempolicy.h | 1 + kernel/futex/core.c | 2 +- mm/mempolicy.c | 10 ++++++++-- 3 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 0fe96f3ab3ef..65c732d440d2 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -55,6 +55,7 @@ struct mempolicy { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ } w; + struct rcu_head rcu; }; /* diff --git a/kernel/futex/core.c b/kernel/futex/core.c index cf7e610eac42..31e83a09789e 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -342,7 +342,7 @@ static int __futex_key_to_node(struct mm_struct *mm, unsigned long addr) if (!vma) return FUTEX_NO_NODE; - mpol = vma_policy(vma); + mpol = READ_ONCE(vma->vm_policy); if (!mpol) return FUTEX_NO_NODE; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 0e5175f1c767..cf92bd6a8226 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -487,7 +487,13 @@ void __mpol_put(struct mempolicy *pol) { if (!atomic_dec_and_test(&pol->refcnt)) return; - kmem_cache_free(policy_cache, pol); + /* + * Required to allow mmap_lock_speculative*() access, see for example + * futex_key_to_node_opt(). All accesses are serialized by mmap_lock, + * however the speculative lock section unbound by the normal lock + * boundaries, requiring RCU freeing. + */ + kfree_rcu(pol, rcu); } EXPORT_SYMBOL_FOR_MODULES(__mpol_put, "kvm"); @@ -1020,7 +1026,7 @@ static int vma_replace_policy(struct vm_area_struct *vma, } old = vma->vm_policy; - vma->vm_policy = new; /* protected by mmap_lock */ + WRITE_ONCE(vma->vm_policy, new); /* protected by mmap_lock */ mpol_put(old); return 0; -- cgit v1.2.3 From 629ec78ef8608d955ce217880cdc3e1873af3a15 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 24 Mar 2026 00:25:57 +0100 Subject: mpls: add seqcount to protect the platform_label{,s} pair The RCU-protected codepaths (mpls_forward, mpls_dump_routes) can have an inconsistent view of platform_labels vs platform_label in case of a concurrent resize (resize_platform_label_table, under platform_mutex). This can lead to OOB accesses. This patch adds a seqcount, so that we get a consistent snapshot. Note that mpls_label_ok is also susceptible to this, so the check against RTA_DST in rtm_to_route_config, done outside platform_mutex, is not sufficient. This value gets passed to mpls_label_ok once more in both mpls_route_add and mpls_route_del, so there is no issue, but that additional check must not be removed. Reported-by: Yuan Tan Reported-by: Yifan Wu Reported-by: Juefei Pu Reported-by: Xin Liu Fixes: 7720c01f3f590 ("mpls: Add a sysctl to control the size of the mpls label table") Fixes: dde1b38e873c ("mpls: Convert mpls_dump_routes() to RCU.") Signed-off-by: Sabrina Dubroca Link: https://patch.msgid.link/cd8fca15e3eb7e212b094064cd83652e20fd9d31.1774284088.git.sd@queasysnail.net Signed-off-by: Jakub Kicinski --- include/net/netns/mpls.h | 1 + net/mpls/af_mpls.c | 29 +++++++++++++++++++++++++---- 2 files changed, 26 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/netns/mpls.h b/include/net/netns/mpls.h index 6682e51513ef..2073cbac2afb 100644 --- a/include/net/netns/mpls.h +++ b/include/net/netns/mpls.h @@ -17,6 +17,7 @@ struct netns_mpls { size_t platform_labels; struct mpls_route __rcu * __rcu *platform_label; struct mutex platform_mutex; + seqcount_mutex_t platform_label_seq; struct ctl_table_header *ctl; }; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index d5417688f69e..18d3da8ab384 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -83,14 +83,30 @@ static struct mpls_route *mpls_route_input(struct net *net, unsigned int index) return mpls_dereference(net, platform_label[index]); } +static struct mpls_route __rcu **mpls_platform_label_rcu(struct net *net, size_t *platform_labels) +{ + struct mpls_route __rcu **platform_label; + unsigned int sequence; + + do { + sequence = read_seqcount_begin(&net->mpls.platform_label_seq); + platform_label = rcu_dereference(net->mpls.platform_label); + *platform_labels = net->mpls.platform_labels; + } while (read_seqcount_retry(&net->mpls.platform_label_seq, sequence)); + + return platform_label; +} + static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned int index) { struct mpls_route __rcu **platform_label; + size_t platform_labels; + + platform_label = mpls_platform_label_rcu(net, &platform_labels); - if (index >= net->mpls.platform_labels) + if (index >= platform_labels) return NULL; - platform_label = rcu_dereference(net->mpls.platform_label); return rcu_dereference(platform_label[index]); } @@ -2240,8 +2256,7 @@ static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb) if (index < MPLS_LABEL_FIRST_UNRESERVED) index = MPLS_LABEL_FIRST_UNRESERVED; - platform_label = rcu_dereference(net->mpls.platform_label); - platform_labels = net->mpls.platform_labels; + platform_label = mpls_platform_label_rcu(net, &platform_labels); if (filter.filter_set) flags |= NLM_F_DUMP_FILTERED; @@ -2645,8 +2660,12 @@ static int resize_platform_label_table(struct net *net, size_t limit) } /* Update the global pointers */ + local_bh_disable(); + write_seqcount_begin(&net->mpls.platform_label_seq); net->mpls.platform_labels = limit; rcu_assign_pointer(net->mpls.platform_label, labels); + write_seqcount_end(&net->mpls.platform_label_seq); + local_bh_enable(); mutex_unlock(&net->mpls.platform_mutex); @@ -2728,6 +2747,8 @@ static __net_init int mpls_net_init(struct net *net) int i; mutex_init(&net->mpls.platform_mutex); + seqcount_mutex_init(&net->mpls.platform_label_seq, &net->mpls.platform_mutex); + net->mpls.platform_labels = 0; net->mpls.platform_label = NULL; net->mpls.ip_ttl_propagate = 1; -- cgit v1.2.3 From 57a04a13aac1f247d171c3f3aef93efc69e6979e Mon Sep 17 00:00:00 2001 From: Qingfang Deng Date: Tue, 24 Mar 2026 22:08:56 +0800 Subject: netdevsim: fix build if SKB_EXTENSIONS=n __skb_ext_put() is not declared if SKB_EXTENSIONS is not enabled, which causes a build error: drivers/net/netdevsim/netdev.c: In function 'nsim_forward_skb': drivers/net/netdevsim/netdev.c:114:25: error: implicit declaration of function '__skb_ext_put'; did you mean 'skb_ext_put'? [-Werror=implicit-function-declaration] 114 | __skb_ext_put(psp_ext); | ^~~~~~~~~~~~~ | skb_ext_put cc1: some warnings being treated as errors Add a stub to fix the build. Fixes: 7d9351435ebb ("netdevsim: drop PSP ext ref on forward failure") Signed-off-by: Qingfang Deng Link: https://patch.msgid.link/20260324140857.783-1-dqfext@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index daa4e4944ce3..2f278ce376b7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -5097,6 +5097,7 @@ static inline bool skb_has_extensions(struct sk_buff *skb) return unlikely(skb->active_extensions); } #else +static inline void __skb_ext_put(struct skb_ext *ext) {} static inline void skb_ext_put(struct sk_buff *skb) {} static inline void skb_ext_reset(struct sk_buff *skb) {} static inline void skb_ext_del(struct sk_buff *skb, int unused) {} -- cgit v1.2.3 From 90c5def10bea574b101b7a520c015ca81742183f Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 2 Mar 2026 18:22:52 -0400 Subject: iommu: Do not call drivers for empty gathers An empty gather is coded with start=U64_MAX, end=0 and several drivers go on to convert that to a size with: end - start + 1 Which gives 2 for an empty gather. This then causes Weird Stuff to happen (for example an UBSAN splat in VT-d) that is hopefully harmless, but maybe not. Prevent drivers from being called right in iommu_iotlb_sync(). Auditing shows that AMD, Intel, Mediatek and RSIC-V drivers all do things on these empty gathers. Further, there are several callers that can trigger empty gathers, especially in unusual conditions. For example iommu_map_nosync() will call a 0 size unmap on some error paths. Also in VFIO, iommupt and other places. Cc: stable@vger.kernel.org Reported-by: Janusz Krzysztofik Closes: https://lore.kernel.org/r/11145826.aFP6jjVeTY@jkrzyszt-mobl2.ger.corp.intel.com Signed-off-by: Jason Gunthorpe Reviewed-by: Lu Baolu Reviewed-by: Samiullah Khawaja Reviewed-by: Robin Murphy Reviewed-by: Vasant Hegde Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 54b8b48c762e..555597b54083 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -980,7 +980,8 @@ static inline void iommu_flush_iotlb_all(struct iommu_domain *domain) static inline void iommu_iotlb_sync(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather) { - if (domain->ops->iotlb_sync) + if (domain->ops->iotlb_sync && + likely(iotlb_gather->start < iotlb_gather->end)) domain->ops->iotlb_sync(domain, iotlb_gather); iommu_iotlb_gather_init(iotlb_gather); -- cgit v1.2.3 From fffca572f9ca51607f180a37d0c898404c8f9112 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 26 Mar 2026 15:06:31 +0100 Subject: mpage: Provide variant of mpage_writepages() with own optional folio handler Some filesystems need to treat some folios specially (for example for inodes with inline data). Doing the handling in their .writepages method in a race-free manner results in duplicating some of the writeback internals. So provide generalized version of mpage_writepages() that allows filesystem to provide a handler called for each folio which can handle the folio in a special way. Reviewed-by: Christoph Hellwig Link: https://patch.msgid.link/20260326140635.15895-3-jack@suse.cz Signed-off-by: Jan Kara --- fs/mpage.c | 30 ++++++++++++++++++++++++------ include/linux/mpage.h | 11 +++++++++-- 2 files changed, 33 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/fs/mpage.c b/fs/mpage.c index 7dae5afc2b9e..b3d9f231a04a 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -646,17 +646,24 @@ out: } /** - * mpage_writepages - walk the list of dirty pages of the given address space & writepage() all of them + * __mpage_writepages - walk the list of dirty pages of the given address space + * & writepage() all of them * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @get_block: the filesystem's block mapper function. + * @write_folio: handler to call for each folio before calling + * mpage_write_folio() * * This is a library function, which implements the writepages() - * address_space_operation. + * address_space_operation. It calls @write_folio handler for each folio. If + * the handler returns value > 0, it calls mpage_write_folio() to do the + * folio writeback. */ int -mpage_writepages(struct address_space *mapping, - struct writeback_control *wbc, get_block_t get_block) +__mpage_writepages(struct address_space *mapping, + struct writeback_control *wbc, get_block_t get_block, + int (*write_folio)(struct folio *folio, + struct writeback_control *wbc)) { struct mpage_data mpd = { .get_block = get_block, @@ -666,11 +673,22 @@ mpage_writepages(struct address_space *mapping, int error; blk_start_plug(&plug); - while ((folio = writeback_iter(mapping, wbc, folio, &error))) + while ((folio = writeback_iter(mapping, wbc, folio, &error))) { + if (write_folio) { + error = write_folio(folio, wbc); + /* + * == 0 means folio is handled, < 0 means error. In + * both cases hand back control to writeback_iter() + */ + if (error <= 0) + continue; + /* Let mpage_write_folio() handle the folio. */ + } error = mpage_write_folio(wbc, folio, &mpd); + } if (mpd.bio) mpage_bio_submit_write(mpd.bio); blk_finish_plug(&plug); return error; } -EXPORT_SYMBOL(mpage_writepages); +EXPORT_SYMBOL(__mpage_writepages); diff --git a/include/linux/mpage.h b/include/linux/mpage.h index 1bdc39daac0a..358946990bfa 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -17,7 +17,14 @@ struct readahead_control; void mpage_readahead(struct readahead_control *, get_block_t get_block); int mpage_read_folio(struct folio *folio, get_block_t get_block); -int mpage_writepages(struct address_space *mapping, - struct writeback_control *wbc, get_block_t get_block); +int __mpage_writepages(struct address_space *mapping, + struct writeback_control *wbc, get_block_t get_block, + int (*write_folio)(struct folio *folio, + struct writeback_control *wbc)); +static inline int mpage_writepages(struct address_space *mapping, + struct writeback_control *wbc, get_block_t get_block) +{ + return __mpage_writepages(mapping, wbc, get_block, NULL); +} #endif -- cgit v1.2.3 From 4c5e7f0fcd592801c9cc18f29f80fbee84eb8669 Mon Sep 17 00:00:00 2001 From: Jinjiang Tu Date: Thu, 19 Mar 2026 09:25:41 +0800 Subject: mm/huge_memory: fix folio isn't locked in softleaf_to_folio() On arm64 server, we found folio that get from migration entry isn't locked in softleaf_to_folio(). This issue triggers when mTHP splitting and zap_nonpresent_ptes() races, and the root cause is lack of memory barrier in softleaf_to_folio(). The race is as follows: CPU0 CPU1 deferred_split_scan() zap_nonpresent_ptes() lock folio split_folio() unmap_folio() change ptes to migration entries __split_folio_to_order() softleaf_to_folio() set flags(including PG_locked) for tail pages folio = pfn_folio(softleaf_to_pfn(entry)) smp_wmb() VM_WARN_ON_ONCE(!folio_test_locked(folio)) prep_compound_page() for tail pages In __split_folio_to_order(), smp_wmb() guarantees page flags of tail pages are visible before the tail page becomes non-compound. smp_wmb() should be paired with smp_rmb() in softleaf_to_folio(), which is missed. As a result, if zap_nonpresent_ptes() accesses migration entry that stores tail pfn, softleaf_to_folio() may see the updated compound_head of tail page before page->flags. This issue will trigger VM_WARN_ON_ONCE() in pfn_swap_entry_folio() because of the race between folio split and zap_nonpresent_ptes() leading to a folio incorrectly undergoing modification without a folio lock being held. This is a BUG_ON() before commit 93976a20345b ("mm: eliminate further swapops predicates"), which in merged in v6.19-rc1. To fix it, add missing smp_rmb() if the softleaf entry is migration entry in softleaf_to_folio() and softleaf_to_page(). [tujinjiang@huawei.com: update function name and comments] Link: https://lkml.kernel.org/r/20260321075214.3305564-1-tujinjiang@huawei.com Link: https://lkml.kernel.org/r/20260319012541.4158561-1-tujinjiang@huawei.com Fixes: e9b61f19858a ("thp: reintroduce split_huge_page()") Signed-off-by: Jinjiang Tu Acked-by: David Hildenbrand (Arm) Reviewed-by: Lorenzo Stoakes (Oracle) Cc: Barry Song Cc: Kefeng Wang Cc: Liam Howlett Cc: Michal Hocko Cc: Mike Rapoport Cc: Nanyong Sun Cc: Ryan Roberts Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton --- include/linux/leafops.h | 32 +++++++++++++++++++++----------- 1 file changed, 21 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/leafops.h b/include/linux/leafops.h index a9ff94b744f2..05673d3529e7 100644 --- a/include/linux/leafops.h +++ b/include/linux/leafops.h @@ -363,6 +363,23 @@ static inline unsigned long softleaf_to_pfn(softleaf_t entry) return swp_offset(entry) & SWP_PFN_MASK; } +static inline void softleaf_migration_sync(softleaf_t entry, + struct folio *folio) +{ + /* + * Ensure we do not race with split, which might alter tail pages into new + * folios and thus result in observing an unlocked folio. + * This matches the write barrier in __split_folio_to_order(). + */ + smp_rmb(); + + /* + * Any use of migration entries may only occur while the + * corresponding page is locked + */ + VM_WARN_ON_ONCE(!folio_test_locked(folio)); +} + /** * softleaf_to_page() - Obtains struct page for PFN encoded within leaf entry. * @entry: Leaf entry, softleaf_has_pfn(@entry) must return true. @@ -374,11 +391,8 @@ static inline struct page *softleaf_to_page(softleaf_t entry) struct page *page = pfn_to_page(softleaf_to_pfn(entry)); VM_WARN_ON_ONCE(!softleaf_has_pfn(entry)); - /* - * Any use of migration entries may only occur while the - * corresponding page is locked - */ - VM_WARN_ON_ONCE(softleaf_is_migration(entry) && !PageLocked(page)); + if (softleaf_is_migration(entry)) + softleaf_migration_sync(entry, page_folio(page)); return page; } @@ -394,12 +408,8 @@ static inline struct folio *softleaf_to_folio(softleaf_t entry) struct folio *folio = pfn_folio(softleaf_to_pfn(entry)); VM_WARN_ON_ONCE(!softleaf_has_pfn(entry)); - /* - * Any use of migration entries may only occur while the - * corresponding folio is locked. - */ - VM_WARN_ON_ONCE(softleaf_is_migration(entry) && - !folio_test_locked(folio)); + if (softleaf_is_migration(entry)) + softleaf_migration_sync(entry, folio); return folio; } -- cgit v1.2.3 From b7e8590987aa94c9dc51518fad0e58cb887b1db5 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 30 Mar 2026 14:16:34 +0200 Subject: netfilter: ipset: use nla_strcmp for IPSET_ATTR_NAME attr IPSET_ATTR_NAME and IPSET_ATTR_NAMEREF are of NLA_STRING type, they cannot be treated like a c-string. They either have to be switched to NLA_NUL_STRING, or the compare operations need to use the nla functions. Fixes: f830837f0eed ("netfilter: ipset: list:set set type support") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 2 +- net/netfilter/ipset/ip_set_core.c | 4 ++-- net/netfilter/ipset/ip_set_list_set.c | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index e9f4f845d760..b98331572ad2 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -309,7 +309,7 @@ enum { /* register and unregister set references */ extern ip_set_id_t ip_set_get_byname(struct net *net, - const char *name, struct ip_set **set); + const struct nlattr *name, struct ip_set **set); extern void ip_set_put_byindex(struct net *net, ip_set_id_t index); extern void ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name); extern ip_set_id_t ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index a2fe711cb5e3..d0c9fe59c67d 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -821,7 +821,7 @@ EXPORT_SYMBOL_GPL(ip_set_del); * */ ip_set_id_t -ip_set_get_byname(struct net *net, const char *name, struct ip_set **set) +ip_set_get_byname(struct net *net, const struct nlattr *name, struct ip_set **set) { ip_set_id_t i, index = IPSET_INVALID_ID; struct ip_set *s; @@ -830,7 +830,7 @@ ip_set_get_byname(struct net *net, const char *name, struct ip_set **set) rcu_read_lock(); for (i = 0; i < inst->ip_set_max; i++) { s = rcu_dereference(inst->ip_set_list)[i]; - if (s && STRNCMP(s->name, name)) { + if (s && nla_strcmp(name, s->name) == 0) { __ip_set_get(s); index = i; *set = s; diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 98b91b34c314..1cef84f15e8c 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -367,7 +367,7 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[], ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; - e.id = ip_set_get_byname(map->net, nla_data(tb[IPSET_ATTR_NAME]), &s); + e.id = ip_set_get_byname(map->net, tb[IPSET_ATTR_NAME], &s); if (e.id == IPSET_INVALID_ID) return -IPSET_ERR_NAME; /* "Loop detection" */ @@ -389,7 +389,7 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_NAMEREF]) { e.refid = ip_set_get_byname(map->net, - nla_data(tb[IPSET_ATTR_NAMEREF]), + tb[IPSET_ATTR_NAMEREF], &s); if (e.refid == IPSET_INVALID_ID) { ret = -IPSET_ERR_NAMEREF; -- cgit v1.2.3