From 3f1fe48a36b0b6722dc3fd421d93512bac138e9a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 2 Oct 2026 12:17:24 -0700 Subject: Merge tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux Pull io_uring fixes from Jens Axboe: - Fix a task_work add use-after-free with SQPOLL. The sqpoll thread could pop and complete the last request while io_req_normal_work_add() was still looking at them after the mpscq push. Use the same approach as DEFER_TASKRUN to protect from that, holding an RCU read lock across the add, and have exit wait for an RCU grace period for SQPOLL rings as well. - CQE32 ring fixes: correct the free entry check for 32b CQEs, zero the big_cqe for aux CQEs, and only post the dummy skip CQE on CQE_MIXED rings - Mark the source filter table as COW when cloning bpf filters, so registering another filter on the source doesn't modify the shared table in place - Initialize the task context before running the BPF loop - Requeue zcrx multishot receives stopped by a local resource - End a TX_TIMESTAMP multishot cmd when the CQ is full (lollipopkit) * tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: io_uring: fix task_work add use-after-free with SQPOLL io_uring/cmd_net: end TX_TIMESTAMP multishot when the CQ is full io_uring/zcrx: requeue multishot receives stopped by a local resource io_uring: initialize task context before running the BPF loop io_uring: zero big_cqe for aux CQEs on CQE32 rings io_uring: fix free entry check for 32b CQEs on CQE32 rings io_uring: only post the dummy skip CQE on CQE_MIXED rings io_uring/bpf_filter: mark source as COW when cloning filters --- fs/stack.c | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 76 insertions(+) create mode 100644 fs/stack.c (limited to 'fs/stack.c') diff --git a/fs/stack.c b/fs/stack.c new file mode 100644 index 000000000..d8c782e06 --- /dev/null +++ b/fs/stack.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include + +/* does _NOT_ require i_rwsem to be held. + * + * This function cannot be inlined since i_size_{read,write} is rather + * heavy-weight on 32-bit systems + */ +void fsstack_copy_inode_size(struct inode *dst, struct inode *src) +{ + loff_t i_size; + blkcnt_t i_blocks; + + /* + * i_size_read() includes its own seqlocking and protection from + * preemption (see include/linux/fs.h): we need nothing extra for + * that here, and prefer to avoid nesting locks than attempt to keep + * i_size and i_blocks in sync together. + */ + i_size = i_size_read(src); + + /* + * But on 32-bit, we ought to make an effort to keep the two halves of + * i_blocks in sync despite SMP or PREEMPTION - though stat's + * generic_fillattr() doesn't bother, and we won't be applying quotas + * (where i_blocks does become important) at the upper level. + * + * We don't actually know what locking is used at the lower level; + * but if it's a filesystem that supports quotas, it will be using + * i_lock as in inode_add_bytes(). + */ + if (sizeof(i_blocks) > sizeof(long)) + spin_lock(&src->i_lock); + i_blocks = src->i_blocks; + if (sizeof(i_blocks) > sizeof(long)) + spin_unlock(&src->i_lock); + + /* + * If CONFIG_SMP or CONFIG_PREEMPTION on 32-bit, it's vital for + * fsstack_copy_inode_size() to hold some lock around + * i_size_write(), otherwise i_size_read() may spin forever (see + * include/linux/fs.h). We don't necessarily hold i_rwsem when this + * is called, so take i_lock for that case. + * + * And if on 32-bit, continue our effort to keep the two halves of + * i_blocks in sync despite SMP or PREEMPTION: use i_lock for that case + * too, and do both at once by combining the tests. + * + * There is none of this locking overhead in the 64-bit case. + */ + if (sizeof(i_size) > sizeof(long) || sizeof(i_blocks) > sizeof(long)) + spin_lock(&dst->i_lock); + i_size_write(dst, i_size); + dst->i_blocks = i_blocks; + if (sizeof(i_size) > sizeof(long) || sizeof(i_blocks) > sizeof(long)) + spin_unlock(&dst->i_lock); +} +EXPORT_SYMBOL_GPL(fsstack_copy_inode_size); + +/* copy all attributes */ +void fsstack_copy_attr_all(struct inode *dest, const struct inode *src) +{ + dest->i_mode = src->i_mode; + dest->i_uid = src->i_uid; + dest->i_gid = src->i_gid; + dest->i_rdev = src->i_rdev; + inode_set_atime_to_ts(dest, inode_get_atime(src)); + inode_set_mtime_to_ts(dest, inode_get_mtime(src)); + inode_set_ctime_to_ts(dest, inode_get_ctime(src)); + dest->i_blkbits = src->i_blkbits; + dest->i_flags = src->i_flags; + set_nlink(dest, src->i_nlink); +} +EXPORT_SYMBOL_GPL(fsstack_copy_attr_all); -- cgit v1.3.1