From b9a49520679e98700d3d89689cc91c08a1c88c1d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 19 Jan 2025 00:55:32 +0100 Subject: rcuref: Plug slowpath race in rcuref_put() Kernel test robot reported an "imbalanced put" in the rcuref_put() slow path, which turned out to be a false positive. Consider the following race: ref = 0 (via rcuref_init(ref, 1)) T1 T2 rcuref_put(ref) -> atomic_add_negative_release(-1, ref) # ref -> 0xffffffff -> rcuref_put_slowpath(ref) rcuref_get(ref) -> atomic_add_negative_relaxed(1, &ref->refcnt) -> return true; # ref -> 0 rcuref_put(ref) -> atomic_add_negative_release(-1, ref) # ref -> 0xffffffff -> rcuref_put_slowpath() -> cnt = atomic_read(&ref->refcnt); # cnt -> 0xffffffff / RCUREF_NOREF -> atomic_try_cmpxchg_release(&ref->refcnt, &cnt, RCUREF_DEAD)) # ref -> 0xe0000000 / RCUREF_DEAD -> return true -> cnt = atomic_read(&ref->refcnt); # cnt -> 0xe0000000 / RCUREF_DEAD -> if (cnt > RCUREF_RELEASED) # 0xe0000000 > 0xc0000000 -> WARN_ONCE(cnt >= RCUREF_RELEASED, "rcuref - imbalanced put()") The problem is the additional read in the slow path (after it decremented to RCUREF_NOREF) which can happen after the counter has been marked RCUREF_DEAD. Prevent this by reusing the return value of the decrement. Now every "final" put uses RCUREF_NOREF in the slow path and attempts the final cmpxchg() to RCUREF_DEAD. [ bigeasy: Add changelog ] Fixes: ee1ee6db07795 ("atomics: Provide rcuref - scalable reference counting") Reported-by: kernel test robot Debugged-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: stable@vger.kernel.org Closes: https://lore.kernel.org/oe-lkp/202412311453.9d7636a2-lkp@intel.com --- include/linux/rcuref.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcuref.h b/include/linux/rcuref.h index 2c8bfd0f1b6b..6322d8c1c6b4 100644 --- a/include/linux/rcuref.h +++ b/include/linux/rcuref.h @@ -71,27 +71,30 @@ static inline __must_check bool rcuref_get(rcuref_t *ref) return rcuref_get_slowpath(ref); } -extern __must_check bool rcuref_put_slowpath(rcuref_t *ref); +extern __must_check bool rcuref_put_slowpath(rcuref_t *ref, unsigned int cnt); /* * Internal helper. Do not invoke directly. */ static __always_inline __must_check bool __rcuref_put(rcuref_t *ref) { + int cnt; + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && preemptible(), "suspicious rcuref_put_rcusafe() usage"); /* * Unconditionally decrease the reference count. The saturation and * dead zones provide enough tolerance for this. */ - if (likely(!atomic_add_negative_release(-1, &ref->refcnt))) + cnt = atomic_sub_return_release(1, &ref->refcnt); + if (likely(cnt >= 0)) return false; /* * Handle the last reference drop and cases inside the saturation * and dead zones. */ - return rcuref_put_slowpath(ref); + return rcuref_put_slowpath(ref, cnt); } /** -- cgit v1.2.3 From 5bbd6e863b15a85221e49b9bdb2d5d8f0bb91f3d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 1 Feb 2025 15:00:02 -0500 Subject: SUNRPC: Prevent looping due to rpc_signal_task() races If rpc_signal_task() is called while a task is in an rpc_call_done() callback function, and the latter calls rpc_restart_call(), the task can end up looping due to the RPC_TASK_SIGNALLED flag being set without the tk_rpc_status being set. Removing the redundant mechanism for signalling the task fixes the looping behaviour. Reported-by: Li Lingfeng Fixes: 39494194f93b ("SUNRPC: Fix races with rpc_killall_tasks()") Signed-off-by: Trond Myklebust Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- include/linux/sunrpc/sched.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index fec1e8a1570c..eac57914dcf3 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -158,7 +158,6 @@ enum { RPC_TASK_NEED_XMIT, RPC_TASK_NEED_RECV, RPC_TASK_MSG_PIN_WAIT, - RPC_TASK_SIGNALLED, }; #define rpc_test_and_set_running(t) \ @@ -171,7 +170,7 @@ enum { #define RPC_IS_ACTIVATED(t) test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate) -#define RPC_SIGNALLED(t) test_bit(RPC_TASK_SIGNALLED, &(t)->tk_runstate) +#define RPC_SIGNALLED(t) (READ_ONCE(task->tk_rpc_status) == -ERESTARTSYS) /* * Task priorities. -- cgit v1.2.3 From b4c173dfbb6c78568578ff18f9e8822d7bd0e31b Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 20 Feb 2025 11:02:58 +0100 Subject: fuse: don't truncate cached, mutated symlink Fuse allows the value of a symlink to change and this property is exploited by some filesystems (e.g. CVMFS). It has been observed, that sometimes after changing the symlink contents, the value is truncated to the old size. This is caused by fuse_getattr() racing with fuse_reverse_inval_inode(). fuse_reverse_inval_inode() updates the fuse_inode's attr_version, which results in fuse_change_attributes() exiting before updating the cached attributes This is okay, as the cached attributes remain invalid and the next call to fuse_change_attributes() will likely update the inode with the correct values. The reason this causes problems is that cached symlinks will be returned through page_get_link(), which truncates the symlink to inode->i_size. This is correct for filesystems that don't mutate symlinks, but in this case it causes bad behavior. The solution is to just remove this truncation. This can cause a regression in a filesystem that relies on supplying a symlink larger than the file size, but this is unlikely. If that happens we'd need to make this behavior conditional. Reported-by: Laura Promberger Tested-by: Sam Lewis Signed-off-by: Miklos Szeredi Link: https://lore.kernel.org/r/20250220100258.793363-1-mszeredi@redhat.com Reviewed-by: Bernd Schubert Signed-off-by: Christian Brauner --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2c3b2f8a621f..9346adf28f7b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3452,6 +3452,8 @@ extern const struct file_operations generic_ro_fops; extern int readlink_copy(char __user *, int, const char *, int); extern int page_readlink(struct dentry *, char __user *, int); +extern const char *page_get_link_raw(struct dentry *, struct inode *, + struct delayed_call *); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); -- cgit v1.2.3 From 8510edf191d2df0822ea22d6226e4eef87562271 Mon Sep 17 00:00:00 2001 From: Jingbo Xu Date: Tue, 18 Feb 2025 20:02:08 +0800 Subject: mm/filemap: fix miscalculated file range for filemap_fdatawrite_range_kick() iocb->ki_pos has been updated with the number of written bytes since generic_perform_write(). Besides __filemap_fdatawrite_range() accepts the inclusive end of the data range. Fixes: 1d4457576570 ("mm: call filemap_fdatawrite_range_kick() after IOCB_DONTCACHE issue") Signed-off-by: Jingbo Xu Link: https://lore.kernel.org/r/20250218120209.88093-2-jefflexu@linux.alibaba.com Reviewed-by: Jens Axboe Signed-off-by: Christian Brauner --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9346adf28f7b..2788df98080f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2975,8 +2975,8 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) } else if (iocb->ki_flags & IOCB_DONTCACHE) { struct address_space *mapping = iocb->ki_filp->f_mapping; - filemap_fdatawrite_range_kick(mapping, iocb->ki_pos, - iocb->ki_pos + count); + filemap_fdatawrite_range_kick(mapping, iocb->ki_pos - count, + iocb->ki_pos - 1); } return count; -- cgit v1.2.3 From 889c57066ceee5e9172232da0608a8ac053bb6e5 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 25 Feb 2025 10:21:41 +0800 Subject: block: make segment size limit workable for > 4K PAGE_SIZE Using PAGE_SIZE as a minimum expected DMA segment size in consideration of devices which have a max DMA segment size of < 64k when used on 64k PAGE_SIZE systems leads to devices not being able to probe such as eMMC and Exynos UFS controller [0] [1] you can end up with a probe failure as follows: WARNING: CPU: 2 PID: 397 at block/blk-settings.c:339 blk_validate_limits+0x364/0x3c0 Ensure we use min(max_seg_size, seg_boundary_mask + 1) as the new min segment size when max segment size is < PAGE_SIZE for 16k and 64k base page size systems. If anyone need to backport this patch, the following commits are depended: commit 6aeb4f836480 ("block: remove bio_add_pc_page") commit 02ee5d69e3ba ("block: remove blk_rq_bio_prep") commit b7175e24d6ac ("block: add a dma mapping iterator") Link: https://lore.kernel.org/linux-block/20230612203314.17820-1-bvanassche@acm.org/ # [0] Link: https://lore.kernel.org/linux-block/1d55e942-5150-de4c-3a02-c3d066f87028@acm.org/ # [1] Cc: Yi Zhang Cc: John Garry Cc: Keith Busch Tested-by: Paul Bunyan Reviewed-by: Daniel Gomez Reviewed-by: Luis Chamberlain Reviewed-by: Bart Van Assche Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20250225022141.2154581-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 248416ecd01c..58ff5aca83b6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -367,6 +367,7 @@ struct queue_limits { unsigned int max_sectors; unsigned int max_user_sectors; unsigned int max_segment_size; + unsigned int min_segment_size; unsigned int physical_block_size; unsigned int logical_block_size; unsigned int alignment_offset; -- cgit v1.2.3 From 73cfc53cc3b6380eccf013049574485f64cb83ca Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 21 Feb 2025 14:57:07 +0100 Subject: objtool: Fix C jump table annotations for Clang A C jump table (such as the one used by the BPF interpreter) is a const global array of absolute code addresses, and this means that the actual values in the table may not be known until the kernel is booted (e.g., when using KASLR or when the kernel VA space is sized dynamically). When using PIE codegen, the compiler will default to placing such const global objects in .data.rel.ro (which is annotated as writable), rather than .rodata (which is annotated as read-only). As C jump tables are explicitly emitted into .rodata, this used to result in warnings for LoongArch builds (which uses PIE codegen for the entire kernel) like Warning: setting incorrect section attributes for .rodata..c_jump_table due to the fact that the explicitly specified .rodata section inherited the read-write annotation that the compiler uses for such objects when using PIE codegen. This warning was suppressed by explicitly adding the read-only annotation to the __attribute__((section(""))) string, by commit c5b1184decc8 ("compiler.h: specify correct attribute for .rodata..c_jump_table") Unfortunately, this hack does not work on Clang's integrated assembler, which happily interprets the appended section type and permission specifiers as part of the section name, which therefore no longer matches the hard-coded pattern '.rodata..c_jump_table' that objtool expects, causing it to emit a warning kernel/bpf/core.o: warning: objtool: ___bpf_prog_run+0x20: sibling call from callable instruction with modified stack frame Work around this, by emitting C jump tables into .data.rel.ro instead, which is treated as .rodata by the linker script for all builds, not just PIE based ones. Fixes: c5b1184decc8 ("compiler.h: specify correct attribute for .rodata..c_jump_table") Tested-by: Tiezhu Yang # on LoongArch Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20250221135704.431269-6-ardb+git@google.com Signed-off-by: Josh Poimboeuf --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index b087de2f3e94..0c25f3e429bb 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -110,7 +110,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Unreachable code */ #ifdef CONFIG_OBJTOOL /* Annotate a C jump table to allow objtool to follow the code flow */ -#define __annotate_jump_table __section(".rodata..c_jump_table,\"a\",@progbits #") +#define __annotate_jump_table __section(".data.rel.ro.c_jump_table") #else /* !CONFIG_OBJTOOL */ #define __annotate_jump_table #endif /* CONFIG_OBJTOOL */ -- cgit v1.2.3 From 9084ed79ddaaaa1ec01cd304af9fb532c26252db Mon Sep 17 00:00:00 2001 From: Stephen Smalley Date: Thu, 20 Feb 2025 14:29:36 -0500 Subject: lsm,nfs: fix memory leak of lsm_context commit b530104f50e8 ("lsm: lsm_context in security_dentry_init_security") did not preserve the lsm id for subsequent release calls, which results in a memory leak. Fix it by saving the lsm id in the nfs4_label and providing it on the subsequent release call. Fixes: b530104f50e8 ("lsm: lsm_context in security_dentry_init_security") Signed-off-by: Stephen Smalley Acked-by: Paul Moore Acked-by: Casey Schaufler Signed-off-by: Anna Schumaker --- include/linux/nfs4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 71fbebfa43c7..9ac83ca88326 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -47,6 +47,7 @@ struct nfs4_acl { struct nfs4_label { uint32_t lfs; uint32_t pi; + u32 lsmid; u32 len; char *label; }; -- cgit v1.2.3 From 18912c520674ec4d920fe3826e7e4fefeecdf5ae Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 24 Feb 2025 09:44:01 -0800 Subject: tcp: devmem: don't write truncated dmabuf CMSGs to userspace Currently, we report -ETOOSMALL (err) only on the first iteration (!sent). When we get put_cmsg error after a bunch of successful put_cmsg calls, we don't signal the error at all. This might be confusing on the userspace side which will see truncated CMSGs but no MSG_CTRUNC signal. Consider the following case: - sizeof(struct cmsghdr) = 16 - sizeof(struct dmabuf_cmsg) = 24 - total cmsg size (CMSG_LEN) = 40 (16+24) When calling recvmsg with msg_controllen=60, the userspace will receive two(!) dmabuf_cmsg(s), the first one will be a valid one and the second one will be silently truncated. There is no easy way to discover the truncation besides doing something like "cm->cmsg_len != CMSG_LEN(sizeof(dmabuf_cmsg))". Introduce new put_devmem_cmsg wrapper that reports an error instead of doing the truncation. Mina suggests that it's the intended way this API should work. Note that we might now report MSG_CTRUNC when the users (incorrectly) call us with msg_control == NULL. Fixes: 8f0b3cc9a4c1 ("tcp: RX path for devmem TCP") Reviewed-by: Mina Almasry Signed-off-by: Stanislav Fomichev Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20250224174401.3582695-1-sdf@fomichev.me Signed-off-by: Jakub Kicinski --- include/linux/socket.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index d18cc47e89bd..c3322eb3d686 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -392,6 +392,8 @@ struct ucred { extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr); extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); +extern int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len, + void *data); struct timespec64; struct __kernel_timespec; -- cgit v1.2.3 From a6aa36e957a1bfb5341986dec32d013d23228fe1 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 14 Feb 2025 13:14:34 +0900 Subject: block: Remove zone write plugs when handling native zone append writes For devices that natively support zone append operations, REQ_OP_ZONE_APPEND BIOs are not processed through zone write plugging and are immediately issued to the zoned device. This means that there is no write pointer offset tracking done for these operations and that a zone write plug is not necessary. However, when receiving a zone append BIO, we may already have a zone write plug for the target zone if that zone was previously partially written using regular write operations. In such case, since the write pointer offset of the zone write plug is not incremented by the amount of sectors appended to the zone, 2 issues arise: 1) we risk leaving the plug in the disk hash table if the zone is fully written using zone append or regular write operations, because the write pointer offset will never reach the "zone full" state. 2) Regular write operations that are issued after zone append operations will always be failed by blk_zone_wplug_prepare_bio() as the write pointer alignment check will fail, even if the user correctly accounted for the zone append operations and issued the regular writes with a correct sector. Avoid these issues by immediately removing the zone write plug of zones that are the target of zone append operations when blk_zone_plug_bio() is called. The new function blk_zone_wplug_handle_native_zone_append() implements this for devices that natively support zone append. The removal of the zone write plug using disk_remove_zone_wplug() requires aborting all plugged regular write using disk_zone_wplug_abort() as otherwise the plugged write BIOs would never be executed (with the plug removed, the completion path will never see again the zone write plug as disk_get_zone_wplug() will return NULL). Rate-limited warnings are added to blk_zone_wplug_handle_native_zone_append() and to disk_zone_wplug_abort() to signal this. Since blk_zone_wplug_handle_native_zone_append() is called in the hot path for operations that will not be plugged, disk_get_zone_wplug() is optimized under the assumption that a user issuing zone append operations is not at the same time issuing regular writes and that there are no hashed zone write plugs. The struct gendisk atomic counter nr_zone_wplugs is added to check this, with this counter incremented in disk_insert_zone_wplug() and decremented in disk_remove_zone_wplug(). To be consistent with this fix, we do not need to fill the zone write plug hash table with zone write plugs for zones that are partially written for a device that supports native zone append operations. So modify blk_revalidate_seq_zone() to return early to avoid allocating and inserting a zone write plug for partially written sequential zones if the device natively supports zone append. Reported-by: Jorgen Hansen Fixes: 9b1ce7f0c6f8 ("block: Implement zone append emulation") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Tested-by: Jorgen Hansen Link: https://lore.kernel.org/r/20250214041434.82564-1-dlemoal@kernel.org Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 58ff5aca83b6..d37751789bf5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -196,10 +196,11 @@ struct gendisk { unsigned int zone_capacity; unsigned int last_zone_capacity; unsigned long __rcu *conv_zones_bitmap; - unsigned int zone_wplugs_hash_bits; - spinlock_t zone_wplugs_lock; + unsigned int zone_wplugs_hash_bits; + atomic_t nr_zone_wplugs; + spinlock_t zone_wplugs_lock; struct mempool_s *zone_wplugs_pool; - struct hlist_head *zone_wplugs_hash; + struct hlist_head *zone_wplugs_hash; struct workqueue_struct *zone_wplugs_wq; #endif /* CONFIG_BLK_DEV_ZONED */ -- cgit v1.2.3 From 02410ac72ac3707936c07ede66e94360d0d65319 Mon Sep 17 00:00:00 2001 From: Ryan Roberts Date: Wed, 26 Feb 2025 12:06:51 +0000 Subject: mm: hugetlb: Add huge page size param to huge_ptep_get_and_clear() In order to fix a bug, arm64 needs to be told the size of the huge page for which the huge_pte is being cleared in huge_ptep_get_and_clear(). Provide for this by adding an `unsigned long sz` parameter to the function. This follows the same pattern as huge_pte_clear() and set_huge_pte_at(). This commit makes the required interface modifications to the core mm as well as all arches that implement this function (arm64, loongarch, mips, parisc, powerpc, riscv, s390, sparc). The actual arm64 bug will be fixed in a separate commit. Cc: stable@vger.kernel.org Fixes: 66b3923a1a0f ("arm64: hugetlb: add support for PTE contiguous bit") Acked-by: David Hildenbrand Reviewed-by: Alexandre Ghiti # riscv Reviewed-by: Christophe Leroy Reviewed-by: Catalin Marinas Reviewed-by: Anshuman Khandual Signed-off-by: Ryan Roberts Acked-by: Alexander Gordeev # s390 Link: https://lore.kernel.org/r/20250226120656.2400136-2-ryan.roberts@arm.com Signed-off-by: Will Deacon --- include/linux/hugetlb.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ec8c0ccc8f95..bf5f7256bd28 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -1004,7 +1004,9 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm) static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { - return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); + unsigned long psize = huge_page_size(hstate_vma(vma)); + + return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize); } #endif -- cgit v1.2.3 From 916b7f42b3b3b539a71c204a9b49fdc4ca92cd82 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 27 Feb 2025 15:06:31 -0800 Subject: kvm: retry nx_huge_page_recovery_thread creation A VMM may send a non-fatal signal to its threads, including vCPU tasks, at any time, and thus may signal vCPU tasks during KVM_RUN. If a vCPU task receives the signal while its trying to spawn the huge page recovery vhost task, then KVM_RUN will fail due to copy_process() returning -ERESTARTNOINTR. Rework call_once() to mark the call complete if and only if the called function succeeds, and plumb the function's true error code back to the call_once() invoker. This provides userspace with the correct, non-fatal error code so that the VMM doesn't terminate the VM on -ENOMEM, and allows subsequent KVM_RUN a succeed by virtue of retrying creation of the NX huge page task. Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson [implemented the kvm user side] Signed-off-by: Keith Busch Message-ID: <20250227230631.303431-3-kbusch@meta.com> Signed-off-by: Paolo Bonzini --- include/linux/call_once.h | 47 ++++++++++++++++++++++++++++++++++------------- 1 file changed, 34 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/call_once.h b/include/linux/call_once.h index 6261aa0b3fb0..13cd6469e7e5 100644 --- a/include/linux/call_once.h +++ b/include/linux/call_once.h @@ -26,20 +26,41 @@ do { \ __once_init((once), #once, &__key); \ } while (0) -static inline void call_once(struct once *once, void (*cb)(struct once *)) +/* + * call_once - Ensure a function has been called exactly once + * + * @once: Tracking struct + * @cb: Function to be called + * + * If @once has never completed successfully before, call @cb and, if + * it returns a zero or positive value, mark @once as completed. Return + * the value returned by @cb + * + * If @once has completed succesfully before, return 0. + * + * The call to @cb is implicitly surrounded by a mutex, though for + * efficiency the * function avoids taking it after the first call. + */ +static inline int call_once(struct once *once, int (*cb)(struct once *)) { - /* Pairs with atomic_set_release() below. */ - if (atomic_read_acquire(&once->state) == ONCE_COMPLETED) - return; - - guard(mutex)(&once->lock); - WARN_ON(atomic_read(&once->state) == ONCE_RUNNING); - if (atomic_read(&once->state) != ONCE_NOT_STARTED) - return; - - atomic_set(&once->state, ONCE_RUNNING); - cb(once); - atomic_set_release(&once->state, ONCE_COMPLETED); + int r, state; + + /* Pairs with atomic_set_release() below. */ + if (atomic_read_acquire(&once->state) == ONCE_COMPLETED) + return 0; + + guard(mutex)(&once->lock); + state = atomic_read(&once->state); + if (unlikely(state != ONCE_NOT_STARTED)) + return WARN_ON_ONCE(state != ONCE_COMPLETED) ? -EINVAL : 0; + + atomic_set(&once->state, ONCE_RUNNING); + r = cb(once); + if (r < 0) + atomic_set(&once->state, ONCE_NOT_STARTED); + else + atomic_set_release(&once->state, ONCE_COMPLETED); + return r; } #endif /* _LINUX_CALL_ONCE_H */ -- cgit v1.2.3