From 4314a44564eb1565349fed7a4192344c5f46fc85 Mon Sep 17 00:00:00 2001 From: Yazhou Tang Date: Wed, 6 May 2026 17:47:12 +0800 Subject: bpf: Fix out-of-bounds read in bpf_patch_call_args() The interpreters_args array only accommodates stack depths up to MAX_BPF_STACK (512 bytes). However, do_misc_fixups() may allow a larger stack depth if JIT is requested. If JIT compilation later fails and falls back to the interpreter, the verifier invokes bpf_patch_call_args() with this oversized stack depth. This causes a load-time out-of-bounds (OOB) read when calculating the interpreter function pointer index. Fix this by changing bpf_patch_call_args() to return an int and explicitly rejecting the JIT fallback (returning -EINVAL) if the stack depth exceeds MAX_BPF_STACK. Fixes: 1ea47e01ad6e ("bpf: add support for bpf_call to interpreter") Co-developed-by: Tianci Cao Signed-off-by: Tianci Cao Co-developed-by: Shenghao Yuan Signed-off-by: Shenghao Yuan Signed-off-by: Yazhou Tang Acked-by: Xu Kuohai Link: https://lore.kernel.org/r/20260506094714.419842-2-tangyazhou@zju.edu.cn Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 01e203964892..52b30e9ea431 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2917,7 +2917,7 @@ int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size); #ifndef CONFIG_BPF_JIT_ALWAYS_ON -void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); +int bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); #endif struct btf *bpf_get_btf_vmlinux(void); -- cgit v1.2.3 From 58a8f3e2501dc14b8e00e883d6aaf0600a239da7 Mon Sep 17 00:00:00 2001 From: Yazhou Tang Date: Wed, 6 May 2026 17:47:13 +0800 Subject: bpf: Fix s16 truncation for large bpf-to-bpf call offsets Currently, the BPF instruction set allows bpf-to-bpf calls (or internal calls, pseudo calls) to use a 32-bit imm field to represent the relative jump offset. However, when JIT is disabled or falls back to the interpreter, the verifier invokes bpf_patch_call_args() to rewrite the call instruction. In this function, the 32-bit imm is downcast to s16 and stored in the off field. void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth) { stack_depth = max_t(u32, stack_depth, 1); insn->off = (s16) insn->imm; insn->imm = interpreters_args[(round_up(stack_depth, 32) / 32) - 1] - __bpf_call_base_args; insn->code = BPF_JMP | BPF_CALL_ARGS; } If the original imm exceeds the s16 range (i.e., a jump offset greater than 32767 instructions), this downcast silently truncates the offset, resulting in an incorrect call target. Fix this by: 1. In bpf_patch_call_args(), keeping the imm field unchanged and using the off field to store the index of the interpreter function. 2. In ___bpf_prog_run() for the JMP_CALL_ARGS case, retrieving the interpreter function pointer from the interpreters_args array using the off field as the index, and passing the original imm to calculate the last argument of the interpreter function. After these changes, the truncation issue is resolved, and __bpf_call_base_args is also no longer needed and can be removed, which makes the code cleaner. Performance: In ___bpf_prog_run() for the JMP_CALL_ARGS case, changing the retrieval of the interpreter function pointer from pointer addition to direct array indexing improves performance. The possible reason is that the latter has better instruction-level parallelism. See the v5 discussion [1] for more details. [1] https://lore.kernel.org/bpf/f120c3c4-6999-414a-b514-518bb64b4758@zju.edu.cn/ To avoid requiring bpftool changes, keep the new imm/off encoding internal and restore the legacy xlated dump layout in bpf_insn_prepare_dump(). For bpf-to-bpf call offsets that do not fit in s16, export off as 0 instead of a truncated and misleading value. Fixes: 1ea47e01ad6e ("bpf: add support for bpf_call to interpreter") Fixes: 7105e828c087 ("bpf: allow for correlation of maps and helpers in dump") Suggested-by: Xu Kuohai Suggested-by: Puranjay Mohan Co-developed-by: Tianci Cao Signed-off-by: Tianci Cao Co-developed-by: Shenghao Yuan Signed-off-by: Shenghao Yuan Signed-off-by: Yazhou Tang Link: https://lore.kernel.org/r/20260506094714.419842-3-tangyazhou@zju.edu.cn Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 ++++++ include/linux/filter.h | 3 --- kernel/bpf/core.c | 21 ++++++++++++++------- kernel/bpf/fixups.c | 6 +++--- kernel/bpf/syscall.c | 26 ++++++++++++++++++++++++++ 5 files changed, 49 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 52b30e9ea431..cd191c5fdb0a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2918,6 +2918,12 @@ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr, u32 ua #ifndef CONFIG_BPF_JIT_ALWAYS_ON int bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); +s32 bpf_call_args_imm(s16 idx); +#else +static inline s32 bpf_call_args_imm(s16 idx) +{ + return 0; +} #endif struct btf *bpf_get_btf_vmlinux(void); diff --git a/include/linux/filter.h b/include/linux/filter.h index 1ec6d5ba64cc..88a241aac36a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1151,9 +1151,6 @@ bool sk_filter_charge(struct sock *sk, struct sk_filter *fp); void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); -#define __bpf_call_base_args \ - ((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \ - (void *)__bpf_call_base) struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 63044ebe5721..6aa2a8b24030 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1771,6 +1771,9 @@ static u32 abs_s32(s32 x) return x >= 0 ? (u32)x : -(u32)x; } +static u64 (*interpreters_args[])(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, + const struct bpf_insn *insn); + /** * ___bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers @@ -2077,10 +2080,9 @@ select_insn: CONT; JMP_CALL_ARGS: - BPF_R0 = (__bpf_call_base_args + insn->imm)(BPF_R1, BPF_R2, - BPF_R3, BPF_R4, - BPF_R5, - insn + insn->off + 1); + BPF_R0 = interpreters_args[insn->off](BPF_R1, BPF_R2, BPF_R3, + BPF_R4, BPF_R5, + insn + insn->imm + 1); CONT; JMP_TAIL_CALL: { @@ -2400,12 +2402,17 @@ int bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth) /* Prevent out-of-bounds read to interpreters_args */ if (stack_depth > MAX_BPF_STACK) return -EINVAL; - insn->off = (s16) insn->imm; - insn->imm = interpreters_args[(round_up(stack_depth, 32) / 32) - 1] - - __bpf_call_base_args; + insn->off = (round_up(stack_depth, 32) / 32) - 1; insn->code = BPF_JMP | BPF_CALL_ARGS; return 0; } + +s32 bpf_call_args_imm(s16 idx) +{ + if (WARN_ON_ONCE(idx < 0 || idx >= ARRAY_SIZE(interpreters_args))) + return 0; + return BPF_CALL_IMM(interpreters_args[idx]); +} #endif #endif diff --git a/kernel/bpf/fixups.c b/kernel/bpf/fixups.c index df8f48091321..3692adf62558 100644 --- a/kernel/bpf/fixups.c +++ b/kernel/bpf/fixups.c @@ -1250,9 +1250,9 @@ static int jit_subprogs(struct bpf_verifier_env *env) } if (!bpf_pseudo_call(insn)) continue; - insn->off = env->insn_aux_data[i].call_imm; - subprog = bpf_find_subprog(env, i + insn->off + 1); - insn->imm = subprog; + insn->imm = env->insn_aux_data[i].call_imm; + subprog = bpf_find_subprog(env, i + insn->imm + 1); + insn->off = subprog; } prog->jited = 1; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a3c0214ca934..630d530782fe 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4919,6 +4919,29 @@ out: return map; } +static void prepare_dump_pseudo_call(struct bpf_insn *insn) +{ + s32 call_off = insn->imm; + + /* + * BPF_CALL_ARGS only exists for interpreter fallback. + * 1. For interpreter (BPF_CALL_ARGS): insn->off is the index of + * interpreters_args array, so here using bpf_call_args_imm() + * to get the real address offset. + * 2. For JIT (BPF_CALL): insn->off is the subprog id. + */ + if (insn->code == (BPF_JMP | BPF_CALL_ARGS)) + insn->imm = bpf_call_args_imm(insn->off); + else + insn->imm = insn->off; + + /* Avoid dumping a truncated and misleading pc-relative offset. */ + if (call_off > S16_MAX || call_off < S16_MIN) + insn->off = 0; + else + insn->off = call_off; +} + static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog, const struct cred *f_cred) { @@ -4944,6 +4967,9 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog, } if (code == (BPF_JMP | BPF_CALL) || code == (BPF_JMP | BPF_CALL_ARGS)) { + /* Restore the legacy xlated dump layout. */ + if (insns[i].src_reg == BPF_PSEUDO_CALL) + prepare_dump_pseudo_call(&insns[i]); if (code == (BPF_JMP | BPF_CALL_ARGS)) insns[i].code = BPF_JMP | BPF_CALL; if (!bpf_dump_raw_ok(f_cred)) -- cgit v1.2.3 From b5782e2d462c028096f922abca46318cec890670 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:40 +0100 Subject: netfs: Fix missing barriers when accessing stream->subrequests locklessly The list of subrequests attached to stream->subrequests is accessed without locks by netfs_collect_read_results() and netfs_collect_write_results(), and then they access subreq->flags without taking a barrier after getting the subreq pointer from the list. Relatedly, the functions that build the list don't use any sort of write barrier when constructing the list to make sure that the NETFS_SREQ_IN_PROGRESS flag is perceived to be set first if no lock is taken. Fix this by: (1) Add a new list_add_tail_release() function that uses a release barrier to set the pointer to the new member of the list. (2) Add a new list_first_entry_or_null_acquire() function that uses an acquire barrier to read the pointer to the first member in a list (or return NULL). (3) Use list_add_tail_release() when adding a subreq to ->subrequests. (4) Use list_first_entry_or_null_acquire() when initially accessing the front of the list (when an item is removed, the pointer to the new front iterm is obtained under the same lock). Fixes: e2d46f2ec332 ("netfs: Change the read result collector to only use one work item") Fixes: 288ace2f57c9 ("netfs: New writeback implementation") Link: https://sashiko.dev/#/patchset/20260326104544.509518-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-4-dhowells@redhat.com cc: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/buffered_read.c | 3 ++- fs/netfs/misc.c | 1 + fs/netfs/read_collect.c | 6 ++++-- fs/netfs/write_collect.c | 6 ++++-- fs/netfs/write_issue.c | 3 ++- include/linux/list.h | 37 +++++++++++++++++++++++++++++++++++++ 6 files changed, 50 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index a27ed501b6d4..15d73026ff64 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -168,7 +168,8 @@ void netfs_queue_read(struct netfs_io_request *rreq, * remove entries off of the front. */ spin_lock(&rreq->lock); - list_add_tail(&subreq->rreq_link, &stream->subrequests); + /* Write IN_PROGRESS before pointer to new subreq */ + list_add_tail_release(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { if (!stream->active) { stream->collected_to = subreq->start; diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 6df89c92b10b..21357907b7ee 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -356,6 +356,7 @@ void netfs_wait_for_in_progress_stream(struct netfs_io_request *rreq, DEFINE_WAIT(myself); list_for_each_entry(subreq, &stream->subrequests, rreq_link) { + smp_rmb(); /* Read ->next before IN_PROGRESS. */ if (!netfs_check_subreq_in_progress(subreq)) continue; diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index d2d902f46627..3c9b847885c2 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -205,8 +205,10 @@ reassess: * in progress. The issuer thread may be adding stuff to the tail * whilst we're doing this. */ - front = list_first_entry_or_null(&stream->subrequests, - struct netfs_io_subrequest, rreq_link); + front = list_first_entry_or_null_acquire(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); + /* Read first subreq pointer before IN_PROGRESS flag. */ + while (front) { size_t transferred; diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index b194447f4b11..7fbf50907a7f 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -228,8 +228,10 @@ reassess_streams: if (!smp_load_acquire(&stream->active)) continue; - front = list_first_entry_or_null(&stream->subrequests, - struct netfs_io_subrequest, rreq_link); + front = list_first_entry_or_null_acquire(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); + /* Read first subreq pointer before IN_PROGRESS flag. */ + while (front) { trace_netfs_collect_sreq(wreq, front); //_debug("sreq [%x] %llx %zx/%zx", diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 2db688f94125..b0e9690bb90c 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -204,7 +204,8 @@ void netfs_prepare_write(struct netfs_io_request *wreq, * remove entries off of the front. */ spin_lock(&wreq->lock); - list_add_tail(&subreq->rreq_link, &stream->subrequests); + /* Write IN_PROGRESS before pointer to new subreq */ + list_add_tail_release(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { if (!stream->active) { stream->collected_to = subreq->start; diff --git a/include/linux/list.h b/include/linux/list.h index 00ea8e5fb88b..09d979976b3b 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -191,6 +191,29 @@ static inline void list_add_tail(struct list_head *new, struct list_head *head) __list_add(new, head->prev, head); } +/** + * list_add_tail_release - add a new entry with release barrier + * @new: new entry to be added + * @head: list head to add it before + * + * Insert a new entry before the specified head, using a release barrier to set + * the ->next pointer that points to it. This is useful for implementing + * queues, in particular one that the elements will be walked through forwards + * locklessly. + */ +static inline void list_add_tail_release(struct list_head *new, + struct list_head *head) +{ + struct list_head *prev = head->prev; + + if (__list_add_valid(new, prev, head)) { + new->next = head; + new->prev = prev; + head->prev = new; + smp_store_release(&prev->next, new); + } +} + /* * Delete a list entry by making the prev/next entries * point to each other. @@ -644,6 +667,20 @@ static inline void list_splice_tail_init(struct list_head *list, pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ }) +/** + * list_first_entry_or_null_acquire - get the first element from a list with barrier + * @ptr: the list head to take the element from. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + * + * Note that if the list is empty, it returns NULL. + */ +#define list_first_entry_or_null_acquire(ptr, type, member) ({ \ + struct list_head *head__ = (ptr); \ + struct list_head *pos__ = smp_load_acquire(&head__->next); \ + pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ +}) + /** * list_last_entry_or_null - get the last element from a list * @ptr: the list head to take the element from. -- cgit v1.2.3 From 2c8f4742bb76117d735f92a3932d85239b16c494 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:42 +0100 Subject: netfs: Fix potential for tearing in ->remote_i_size and ->zero_point Fix potential tearing in using ->remote_i_size and ->zero_point by copying i_size_read() and i_size_write() and using the same seqcount as for i_size. We need to make sure that netfslib and the filesystems that use it always hold i_lock whilst updating any of the sizes to prevent i_size_seqcount from getting corrupted. Fixes: 4058f742105e ("netfs: Keep track of the actual remote file size") Fixes: 100ccd18bb41 ("netfs: Optimise away reads above the point at which there can be no data") Closes: https://sashiko.dev/#/patchset/20260414082004.3756080-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-6-dhowells@redhat.com cc: Paulo Alcantara cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- fs/9p/v9fs_vfs.h | 13 -- fs/9p/vfs_inode.c | 6 +- fs/9p/vfs_inode_dotl.c | 12 +- fs/afs/file.c | 24 +++- fs/afs/inode.c | 31 +++-- fs/afs/internal.h | 11 +- fs/afs/write.c | 2 +- fs/netfs/buffered_read.c | 6 +- fs/netfs/buffered_write.c | 2 +- fs/netfs/direct_write.c | 6 +- fs/netfs/misc.c | 32 +++-- fs/netfs/write_collect.c | 9 +- fs/smb/client/cifsfs.c | 38 ++++-- fs/smb/client/cifssmb.c | 3 +- fs/smb/client/file.c | 13 +- fs/smb/client/inode.c | 14 ++- fs/smb/client/readdir.c | 3 +- fs/smb/client/smb2ops.c | 42 ++++--- fs/smb/client/smb2pdu.c | 3 +- include/linux/netfs.h | 293 ++++++++++++++++++++++++++++++++++++++++++++-- 20 files changed, 450 insertions(+), 113 deletions(-) (limited to 'include/linux') diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index d3aefbec4de6..34c115d7c250 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -75,17 +75,4 @@ static inline void v9fs_invalidate_inode_attr(struct inode *inode) int v9fs_open_to_dotl_flags(int flags); -static inline void v9fs_i_size_write(struct inode *inode, loff_t i_size) -{ - /* - * 32-bit need the lock, concurrent updates could break the - * sequences and make i_size_read() loop forever. - * 64-bit updates are atomic and can skip the locking. - */ - if (sizeof(i_size) > sizeof(long)) - spin_lock(&inode->i_lock); - i_size_write(inode, i_size); - if (sizeof(i_size) > sizeof(long)) - spin_unlock(&inode->i_lock); -} #endif diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index d1508b1fe109..f468acb8ee7d 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1141,11 +1141,13 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; - v9inode->netfs.remote_i_size = stat->length; + spin_lock(&inode->i_lock); + netfs_write_remote_i_size(inode, stat->length); if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE)) - v9fs_i_size_write(inode, stat->length); + i_size_write(inode, stat->length); /* not real number of blocks, but 512 byte ones ... */ inode->i_blocks = (stat->length + 512 - 1) >> 9; + spin_unlock(&inode->i_lock); v9inode->cache_validity &= ~V9FS_INO_INVALID_ATTR; } diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 71796a89bcf4..141fb54db65d 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -634,10 +634,12 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; - v9inode->netfs.remote_i_size = stat->st_size; + spin_lock(&inode->i_lock); + netfs_write_remote_i_size(inode, stat->st_size); if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE)) - v9fs_i_size_write(inode, stat->st_size); + i_size_write(inode, stat->st_size); inode->i_blocks = stat->st_blocks; + spin_unlock(&inode->i_lock); } else { if (stat->st_result_mask & P9_STATS_ATIME) { inode_set_atime(inode, stat->st_atime_sec, @@ -662,13 +664,15 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; } + spin_lock(&inode->i_lock); if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE) && stat->st_result_mask & P9_STATS_SIZE) { - v9inode->netfs.remote_i_size = stat->st_size; - v9fs_i_size_write(inode, stat->st_size); + netfs_write_remote_i_size(inode, stat->st_size); + i_size_write(inode, stat->st_size); } if (stat->st_result_mask & P9_STATS_BLOCKS) inode->i_blocks = stat->st_blocks; + spin_unlock(&inode->i_lock); } if (stat->st_result_mask & P9_STATS_GEN) inode->i_generation = stat->st_gen; diff --git a/fs/afs/file.c b/fs/afs/file.c index 85696ac984cc..0467742bfeee 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -427,21 +427,35 @@ static void afs_free_request(struct netfs_io_request *rreq) afs_put_wb_key(rreq->netfs_priv2); } -static void afs_update_i_size(struct inode *inode, loff_t new_i_size) +/* + * Set the file size and block count, taking ->cb_lock and ->i_lock to maintain + * coherency and prevent 64-bit tearing on 32-bit arches. + * + * Also, estimate the number of 512 bytes blocks used, rounded up to nearest 1K + * for consistency with other AFS clients. + */ +void afs_set_i_size(struct afs_vnode *vnode, loff_t new_i_size) { - struct afs_vnode *vnode = AFS_FS_I(inode); + struct inode *inode = &vnode->netfs.inode; loff_t i_size; write_seqlock(&vnode->cb_lock); - i_size = i_size_read(&vnode->netfs.inode); + spin_lock(&inode->i_lock); + i_size = i_size_read(inode); if (new_i_size > i_size) { - i_size_write(&vnode->netfs.inode, new_i_size); - inode_set_bytes(&vnode->netfs.inode, new_i_size); + i_size_write(inode, new_i_size); + inode_set_bytes(inode, round_up(new_i_size, 1024)); } + spin_unlock(&inode->i_lock); write_sequnlock(&vnode->cb_lock); fscache_update_cookie(afs_vnode_cache(vnode), NULL, &new_i_size); } +static void afs_update_i_size(struct inode *inode, loff_t new_i_size) +{ + afs_set_i_size(AFS_FS_I(inode), new_i_size); +} + static void afs_netfs_invalidate_cache(struct netfs_io_request *wreq) { struct afs_vnode *vnode = AFS_FS_I(wreq->inode); diff --git a/fs/afs/inode.c b/fs/afs/inode.c index a5173434f786..19fe2e392885 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -224,7 +224,8 @@ static int afs_inode_init_from_status(struct afs_operation *op, return afs_protocol_error(NULL, afs_eproto_file_type); } - afs_set_i_size(vnode, status->size); + i_size_write(inode, status->size); + inode_set_bytes(inode, status->size); afs_set_netfs_context(vnode); vnode->invalid_before = status->data_version; @@ -253,7 +254,8 @@ static void afs_apply_status(struct afs_operation *op, { struct afs_file_status *status = &vp->scb.status; struct afs_vnode *vnode = vp->vnode; - struct inode *inode = &vnode->netfs.inode; + struct netfs_inode *ictx = &vnode->netfs; + struct inode *inode = &ictx->inode; struct timespec64 t; umode_t mode; bool unexpected_jump = false; @@ -336,6 +338,8 @@ static void afs_apply_status(struct afs_operation *op, } if (data_changed) { + unsigned long long zero_point, size = status->size; + inode_set_iversion_raw(inode, status->data_version); /* Only update the size if the data version jumped. If the @@ -343,16 +347,25 @@ static void afs_apply_status(struct afs_operation *op, * idea of what the size should be that's not the same as * what's on the server. */ - vnode->netfs.remote_i_size = status->size; - if (change_size || status->size > i_size_read(inode)) { - afs_set_i_size(vnode, status->size); + spin_lock(&inode->i_lock); + + if (change_size || size > i_size_read(inode)) { + /* We can read the sizes directly as we hold i_lock. */ + zero_point = ictx->_zero_point; + if (unexpected_jump) - vnode->netfs.zero_point = status->size; + zero_point = size; + netfs_write_sizes(inode, size, size, zero_point); + inode_set_bytes(inode, size); inode_set_ctime_to_ts(inode, t); inode_set_atime_to_ts(inode, t); + } else { + netfs_write_remote_i_size(inode, size); } + spin_unlock(&inode->i_lock); + if (op->ops == &afs_fetch_data_operation) - op->fetch.subreq->rreq->i_size = status->size; + op->fetch.subreq->rreq->i_size = size; } } @@ -709,7 +722,7 @@ int afs_getattr(struct mnt_idmap *idmap, const struct path *path, * it, but we need to give userspace the server's size. */ if (S_ISDIR(inode->i_mode)) - stat->size = vnode->netfs.remote_i_size; + stat->size = netfs_read_remote_i_size(inode); } while (read_seqretry(&vnode->cb_lock, seq)); return 0; @@ -889,7 +902,7 @@ int afs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, */ if (!(attr->ia_valid & (supported & ~ATTR_SIZE & ~ATTR_MTIME)) && attr->ia_size < i_size && - attr->ia_size > vnode->netfs.remote_i_size) { + attr->ia_size > netfs_read_remote_i_size(inode)) { truncate_setsize(inode, attr->ia_size); netfs_resize_file(&vnode->netfs, size, false); fscache_resize_cookie(afs_vnode_cache(vnode), diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 599353c33337..816dc848ea71 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -1157,6 +1157,7 @@ extern int afs_open(struct inode *, struct file *); extern int afs_release(struct inode *, struct file *); void afs_fetch_data_async_rx(struct work_struct *work); void afs_fetch_data_immediate_cancel(struct afs_call *call); +void afs_set_i_size(struct afs_vnode *vnode, loff_t new_i_size); /* * flock.c @@ -1758,16 +1759,6 @@ static inline void afs_update_dentry_version(struct afs_operation *op, (void *)(unsigned long)dir_vp->scb.status.data_version; } -/* - * Set the file size and block count. Estimate the number of 512 bytes blocks - * used, rounded up to nearest 1K for consistency with other AFS clients. - */ -static inline void afs_set_i_size(struct afs_vnode *vnode, u64 size) -{ - i_size_write(&vnode->netfs.inode, size); - vnode->netfs.inode.i_blocks = ((size + 1023) >> 10) << 1; -} - /* * Check for a conflicting operation on a directory that we just unlinked from. * If someone managed to sneak a link or an unlink in on the file we just diff --git a/fs/afs/write.c b/fs/afs/write.c index fcfed9d24e0a..7f34b939706a 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -142,7 +142,7 @@ static void afs_issue_write_worker(struct work_struct *work) afs_begin_vnode_operation(op); op->store.write_iter = &subreq->io_iter; - op->store.i_size = umax(pos + len, vnode->netfs.remote_i_size); + op->store.i_size = umax(pos + len, netfs_read_remote_i_size(&vnode->netfs.inode)); op->mtime = inode_get_mtime(&vnode->netfs.inode); afs_wait_for_operation(op); diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index fee0aebf5a3d..ebd84a6cc3f0 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -209,7 +209,6 @@ static void netfs_issue_read(struct netfs_io_request *rreq, static void netfs_read_to_pagecache(struct netfs_io_request *rreq, struct readahead_control *ractl) { - struct netfs_inode *ictx = netfs_inode(rreq->inode); unsigned long long start = rreq->start; ssize_t size = rreq->len; int ret = 0; @@ -233,7 +232,8 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, source = netfs_cache_prepare_read(rreq, subreq, rreq->i_size); subreq->source = source; if (source == NETFS_DOWNLOAD_FROM_SERVER) { - unsigned long long zp = umin(ictx->zero_point, rreq->i_size); + unsigned long long zero_point = netfs_read_zero_point(rreq->inode); + unsigned long long zp = umin(zero_point, rreq->i_size); size_t len = subreq->len; if (unlikely(rreq->origin == NETFS_READ_SINGLE)) @@ -249,7 +249,7 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, pr_err("ZERO-LEN READ: R=%08x[%x] l=%zx/%zx s=%llx z=%llx i=%llx", rreq->debug_id, subreq->debug_index, subreq->len, size, - subreq->start, ictx->zero_point, rreq->i_size); + subreq->start, zero_point, rreq->i_size); netfs_cancel_read(subreq, ret); break; } diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 05ea5b0cc0e8..b6ecd059dc4f 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -230,7 +230,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, * server would just return a block of zeros or a short read if * we try to read it. */ - if (fpos >= ctx->zero_point) { + if (fpos >= netfs_read_zero_point(inode)) { folio_zero_segment(folio, 0, offset); copied = copy_folio_from_iter_atomic(folio, offset, part, iter); if (unlikely(copied == 0)) diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index f9ab69de3e29..25f8ceb15fad 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -376,8 +376,10 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from) if (ret < 0) goto out; end = iocb->ki_pos + iov_iter_count(from); - if (end > ictx->zero_point) - ictx->zero_point = end; + spin_lock(&inode->i_lock); + if (end > ictx->_zero_point) + netfs_write_zero_point(inode, end); + spin_unlock(&inode->i_lock); fscache_invalidate(netfs_i_cookie(ictx), NULL, i_size_read(inode), FSCACHE_INVAL_DIO_WRITE); diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 21357907b7ee..bad661ff2bec 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -211,18 +211,25 @@ EXPORT_SYMBOL(netfs_clear_inode_writeback); void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length) { struct netfs_folio *finfo; - struct netfs_inode *ctx = netfs_inode(folio_inode(folio)); + struct inode *inode = folio_inode(folio); + struct netfs_inode *ctx = netfs_inode(inode); size_t flen = folio_size(folio); _enter("{%lx},%zx,%zx", folio->index, offset, length); if (offset == 0 && length == flen) { - unsigned long long i_size = i_size_read(&ctx->inode); + unsigned long long i_size, remote_i_size, zero_point; unsigned long long fpos = folio_pos(folio), end; + netfs_read_sizes(inode, &i_size, &remote_i_size, &zero_point); end = umin(fpos + flen, i_size); - if (fpos < i_size && end > ctx->zero_point) - ctx->zero_point = end; + if (fpos < i_size && end > zero_point) { + spin_lock(&inode->i_lock); + end = umin(fpos + flen, inode->i_size); + if (fpos < i_size && end > ctx->_zero_point) + netfs_write_zero_point(inode, end); + spin_unlock(&inode->i_lock); + } } folio_wait_private_2(folio); /* [DEPRECATED] */ @@ -292,15 +299,22 @@ EXPORT_SYMBOL(netfs_invalidate_folio); */ bool netfs_release_folio(struct folio *folio, gfp_t gfp) { - struct netfs_inode *ctx = netfs_inode(folio_inode(folio)); - unsigned long long end; + struct inode *inode = folio_inode(folio); + struct netfs_inode *ctx = netfs_inode(inode); + unsigned long long i_size, remote_i_size, zero_point, end; if (folio_test_dirty(folio)) return false; - end = umin(folio_next_pos(folio), i_size_read(&ctx->inode)); - if (end > ctx->zero_point) - ctx->zero_point = end; + netfs_read_sizes(inode, &i_size, &remote_i_size, &zero_point); + end = umin(folio_next_pos(folio), i_size); + if (end > zero_point) { + spin_lock(&inode->i_lock); + end = umin(folio_next_pos(folio), inode->i_size); + if (end > ctx->_zero_point) + netfs_write_zero_point(inode, end); + spin_unlock(&inode->i_lock); + } if (folio_test_private(folio)) return false; diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 7fbf50907a7f..24fc2bb2f8a4 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -57,7 +57,8 @@ static void netfs_dump_request(const struct netfs_io_request *rreq) int netfs_folio_written_back(struct folio *folio) { enum netfs_folio_trace why = netfs_folio_trace_clear; - struct netfs_inode *ictx = netfs_inode(folio->mapping->host); + struct inode *inode = folio_inode(folio); + struct netfs_inode *ictx = netfs_inode(inode); struct netfs_folio *finfo; struct netfs_group *group = NULL; int gcount = 0; @@ -69,8 +70,10 @@ int netfs_folio_written_back(struct folio *folio) unsigned long long fend; fend = folio_pos(folio) + finfo->dirty_offset + finfo->dirty_len; - if (fend > ictx->zero_point) - ictx->zero_point = fend; + spin_lock(&ictx->inode.i_lock); + if (fend > ictx->_zero_point) + netfs_write_zero_point(inode, fend); + spin_unlock(&ictx->inode.i_lock); folio_detach_private(folio); group = finfo->netfs_group; diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 9f76b0347fa9..feac491c5070 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -434,7 +434,8 @@ cifs_alloc_inode(struct super_block *sb) spin_lock_init(&cifs_inode->writers_lock); cifs_inode->writers = 0; cifs_inode->netfs.inode.i_blkbits = 14; /* 2**14 = CIFS_MAX_MSGSIZE */ - cifs_inode->netfs.remote_i_size = 0; + cifs_inode->netfs._remote_i_size = 0; + cifs_inode->netfs._zero_point = 0; cifs_inode->uniqueid = 0; cifs_inode->createtime = 0; cifs_inode->epoch = 0; @@ -1303,7 +1304,8 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, struct cifsFileInfo *smb_file_src = src_file->private_data; struct cifsFileInfo *smb_file_target = dst_file->private_data; struct cifs_tcon *target_tcon, *src_tcon; - unsigned long long destend, fstart, fend, old_size, new_size; + unsigned long long i_size, old_size, new_size, zero_point; + unsigned long long destend, fstart, fend; unsigned int xid; int rc; @@ -1347,7 +1349,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, * Advance the EOF marker after the flush above to the end of the range * if it's short of that. */ - if (src_cifsi->netfs.remote_i_size < off + len) { + if (netfs_read_remote_i_size(src_inode) < off + len) { rc = cifs_precopy_set_eof(src_inode, src_cifsi, src_tcon, xid, off + len); if (rc < 0) goto unlock; @@ -1368,16 +1370,18 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false); if (rc) goto unlock; - if (fend > target_cifsi->netfs.zero_point) - target_cifsi->netfs.zero_point = fend + 1; - old_size = target_cifsi->netfs.remote_i_size; + + spin_lock(&target_inode->i_lock); + if (fend > zero_point) + netfs_write_zero_point(target_inode, fend + 1); + i_size = target_inode->i_size; + spin_unlock(&target_inode->i_lock); /* Discard all the folios that overlap the destination region. */ cifs_dbg(FYI, "about to discard pages %llx-%llx\n", fstart, fend); truncate_inode_pages_range(&target_inode->i_data, fstart, fend); - fscache_invalidate(cifs_inode_cookie(target_inode), NULL, - i_size_read(target_inode), 0); + fscache_invalidate(cifs_inode_cookie(target_inode), NULL, i_size, 0); rc = -EOPNOTSUPP; if (target_tcon->ses->server->ops->duplicate_extents) { @@ -1402,8 +1406,12 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, rc = -EINVAL; } } - if (rc == 0 && new_size > target_cifsi->netfs.zero_point) - target_cifsi->netfs.zero_point = new_size; + if (rc == 0) { + spin_lock(&target_inode->i_lock); + if (new_size > target_cifsi->netfs._zero_point) + netfs_write_zero_point(target_inode, new_size); + spin_unlock(&target_inode->i_lock); + } } /* force revalidate of size and timestamps of target file now @@ -1474,7 +1482,7 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, * Advance the EOF marker after the flush above to the end of the range * if it's short of that. */ - if (src_cifsi->netfs.remote_i_size < off + len) { + if (netfs_read_remote_i_size(src_inode) < off + len) { rc = cifs_precopy_set_eof(src_inode, src_cifsi, src_tcon, xid, off + len); if (rc < 0) goto unlock; @@ -1502,8 +1510,12 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, fscache_resize_cookie(cifs_inode_cookie(target_inode), i_size_read(target_inode)); } - if (rc > 0 && destoff + rc > target_cifsi->netfs.zero_point) - target_cifsi->netfs.zero_point = destoff + rc; + if (rc > 0) { + spin_lock(&target_inode->i_lock); + if (destoff + rc > target_cifsi->netfs._zero_point) + netfs_write_zero_point(target_inode, destoff + rc); + spin_unlock(&target_inode->i_lock); + } } file_accessed(src_file); diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 3990a9012264..9e27bfa7376b 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1465,6 +1465,7 @@ cifs_readv_callback(struct TCP_Server_Info *server, struct mid_q_entry *mid) struct cifs_io_subrequest *rdata = mid->callback_data; struct netfs_inode *ictx = netfs_inode(rdata->rreq->inode); struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink); + struct inode *inode = &ictx->inode; struct smb_rqst rqst = { .rq_iov = rdata->iov, .rq_nvec = 1, .rq_iter = rdata->subreq.io_iter }; @@ -1538,7 +1539,7 @@ do_retry: } else { size_t trans = rdata->subreq.transferred + rdata->got_bytes; if (trans < rdata->subreq.len && - rdata->subreq.start + trans >= ictx->remote_i_size) { + rdata->subreq.start + trans >= netfs_read_remote_i_size(inode)) { rdata->result = 0; __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); } else if (rdata->got_bytes > 0) { diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 664a2c223089..b60344125f27 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -2517,18 +2517,23 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock) void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t result) { struct netfs_io_request *wreq = wdata->rreq; - struct netfs_inode *ictx = netfs_inode(wreq->inode); + struct inode *inode = wreq->inode; + struct netfs_inode *ictx = netfs_inode(inode); loff_t wrend; if (result > 0) { + spin_lock(&inode->i_lock); + wrend = wdata->subreq.start + wdata->subreq.transferred + result; - if (wrend > ictx->zero_point && + if (wrend > ictx->_zero_point && (wdata->rreq->origin == NETFS_UNBUFFERED_WRITE || wdata->rreq->origin == NETFS_DIO_WRITE)) - ictx->zero_point = wrend; - if (wrend > ictx->remote_i_size) + netfs_write_zero_point(inode, wrend); + if (wrend > ictx->_remote_i_size) netfs_resize_file(ictx, wrend, true); + + spin_unlock(&inode->i_lock); } netfs_write_subrequest_terminated(&wdata->subreq, result); diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 16a5310155d5..9472c0a6c187 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -119,7 +119,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr) fattr->cf_mtime = timestamp_truncate(fattr->cf_mtime, inode); mtime = inode_get_mtime(inode); if (timespec64_equal(&mtime, &fattr->cf_mtime) && - cifs_i->netfs.remote_i_size == fattr->cf_eof) { + netfs_read_remote_i_size(inode) == fattr->cf_eof) { cifs_dbg(FYI, "%s: inode %llu is unchanged\n", __func__, cifs_i->uniqueid); return; @@ -173,12 +173,12 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, CIFS_I(inode)->time = 0; /* force reval */ return -ESTALE; } - if (inode_state_read_once(inode) & I_NEW) - CIFS_I(inode)->netfs.zero_point = fattr->cf_eof; - cifs_revalidate_cache(inode, fattr); spin_lock(&inode->i_lock); + if (inode_state_read_once(inode) & I_NEW) + netfs_write_zero_point(inode, fattr->cf_eof); + fattr->cf_mtime = timestamp_truncate(fattr->cf_mtime, inode); fattr->cf_atime = timestamp_truncate(fattr->cf_atime, inode); fattr->cf_ctime = timestamp_truncate(fattr->cf_ctime, inode); @@ -212,7 +212,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, else clear_bit(CIFS_INO_DELETE_PENDING, &cifs_i->flags); - cifs_i->netfs.remote_i_size = fattr->cf_eof; + netfs_write_remote_i_size(inode, fattr->cf_eof); /* * Can't safely change the file size here if the client is writing to * it due to potential races. @@ -2772,7 +2772,9 @@ cifs_revalidate_mapping(struct inode *inode) if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_RW_CACHE) goto skip_invalidate; - cifs_inode->netfs.zero_point = cifs_inode->netfs.remote_i_size; + spin_lock(&inode->i_lock); + netfs_write_zero_point(inode, netfs_inode(inode)->_remote_i_size); + spin_unlock(&inode->i_lock); rc = filemap_invalidate_inode(inode, true, 0, LLONG_MAX); if (rc) { cifs_dbg(VFS, "%s: invalidate inode %p failed with rc %d\n", diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index be22bbc4a65a..e860fa08b5e3 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -143,7 +143,8 @@ retry: fattr->cf_rdev = inode->i_rdev; fattr->cf_uid = inode->i_uid; fattr->cf_gid = inode->i_gid; - fattr->cf_eof = CIFS_I(inode)->netfs.remote_i_size; + fattr->cf_eof = + netfs_read_remote_i_size(inode); fattr->cf_symlink_target = NULL; } else { CIFS_I(inode)->time = 0; diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index e6cb9b144530..0ea3ce1b94ea 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -3402,8 +3402,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, struct inode *inode = file_inode(file); struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifsFileInfo *cfile = file->private_data; - struct netfs_inode *ictx = netfs_inode(inode); - unsigned long long i_size, new_size, remote_size; + unsigned long long i_size, new_size, remote_i_size, zero_point; long rc; unsigned int xid; @@ -3414,9 +3413,8 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, filemap_invalidate_lock(inode->i_mapping); - i_size = i_size_read(inode); - remote_size = ictx->remote_i_size; - if (offset + len >= remote_size && offset < i_size) { + netfs_read_sizes(inode, &i_size, &remote_i_size, &zero_point); + if (offset + len >= remote_i_size && offset < i_size) { unsigned long long top = umin(offset + len, i_size); rc = filemap_write_and_wait_range(inode->i_mapping, offset, top - 1); @@ -3449,9 +3447,11 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, cfile->fid.volatile_fid, cfile->pid, new_size); if (rc >= 0) { truncate_setsize(inode, new_size); + spin_lock(&inode->i_lock); netfs_resize_file(&cifsi->netfs, new_size, true); - if (offset < cifsi->netfs.zero_point) - cifsi->netfs.zero_point = offset; + if (offset < cifsi->netfs._zero_point) + netfs_write_zero_point(inode, offset); + spin_unlock(&inode->i_lock); fscache_resize_cookie(cifs_inode_cookie(inode), new_size); } } @@ -3474,7 +3474,7 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, struct inode *inode = file_inode(file); struct cifsFileInfo *cfile = file->private_data; struct file_zero_data_information fsctl_buf; - unsigned long long end = offset + len, i_size, remote_i_size; + unsigned long long end = offset + len, i_size, remote_i_size, zero_point; long rc; unsigned int xid; __u8 set_sparse = 1; @@ -3516,14 +3516,17 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, * that we locally hole-punch the tail of the dirty data, the proposed * EOF update will end up in the wrong place. */ - i_size = i_size_read(inode); - remote_i_size = netfs_inode(inode)->remote_i_size; + netfs_read_sizes(inode, &i_size, &remote_i_size, &zero_point); + if (end > remote_i_size && i_size > remote_i_size) { unsigned long long extend_to = umin(end, i_size); rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, extend_to); - if (rc >= 0) - netfs_inode(inode)->remote_i_size = extend_to; + if (rc >= 0) { + spin_lock(&inode->i_lock); + netfs_write_remote_i_size(inode, extend_to); + spin_unlock(&inode->i_lock); + } } unlock: @@ -3787,7 +3790,6 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, struct inode *inode = file_inode(file); struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifsFileInfo *cfile = file->private_data; - struct netfs_inode *ictx = &cifsi->netfs; loff_t old_eof, new_eof; xid = get_xid(); @@ -3805,7 +3807,9 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, goto out_2; truncate_pagecache_range(inode, off, old_eof); - ictx->zero_point = old_eof; + spin_lock(&inode->i_lock); + netfs_write_zero_point(inode, old_eof); + spin_unlock(&inode->i_lock); netfs_wait_for_outstanding_io(inode); rc = smb2_copychunk_range(xid, cfile, cfile, off + len, @@ -3822,8 +3826,10 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, rc = 0; truncate_setsize(inode, new_eof); + spin_lock(&inode->i_lock); netfs_resize_file(&cifsi->netfs, new_eof, true); - ictx->zero_point = new_eof; + netfs_write_zero_point(inode, new_eof); + spin_unlock(&inode->i_lock); fscache_resize_cookie(cifs_inode_cookie(inode), new_eof); out_2: filemap_invalidate_unlock(inode->i_mapping); @@ -3866,13 +3872,17 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, goto out_2; truncate_setsize(inode, new_eof); + spin_lock(&inode->i_lock); netfs_resize_file(&cifsi->netfs, i_size_read(inode), true); + spin_unlock(&inode->i_lock); fscache_resize_cookie(cifs_inode_cookie(inode), i_size_read(inode)); rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len); if (rc < 0) goto out_2; - cifsi->netfs.zero_point = new_eof; + spin_lock(&inode->i_lock); + netfs_write_zero_point(inode, new_eof); + spin_unlock(&inode->i_lock); rc = smb3_zero_data(file, tcon, off, len, xid); if (rc < 0) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 995fcdd30681..3bd300347f16 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4608,6 +4608,7 @@ smb2_readv_callback(struct TCP_Server_Info *server, struct mid_q_entry *mid) struct netfs_inode *ictx = netfs_inode(rdata->rreq->inode); struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink); struct smb2_hdr *shdr = (struct smb2_hdr *)rdata->iov[0].iov_base; + struct inode *inode = &ictx->inode; struct cifs_credits credits = { .value = 0, .instance = 0, @@ -4721,7 +4722,7 @@ do_retry: } else { size_t trans = rdata->subreq.transferred + rdata->got_bytes; if (trans < rdata->subreq.len && - rdata->subreq.start + trans >= ictx->remote_i_size) { + rdata->subreq.start + trans >= netfs_read_remote_i_size(inode)) { __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; } diff --git a/include/linux/netfs.h b/include/linux/netfs.h index ba17ac5bf356..4fd1d796ad73 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -62,8 +62,8 @@ struct netfs_inode { struct fscache_cookie *cache; #endif struct mutex wb_lock; /* Writeback serialisation */ - loff_t remote_i_size; /* Size of the remote file */ - loff_t zero_point; /* Size after which we assume there's no data + loff_t _remote_i_size; /* Size of the remote file */ + loff_t _zero_point; /* Size after which we assume there's no data * on the server */ atomic_t io_count; /* Number of outstanding reqs */ unsigned long flags; @@ -474,6 +474,254 @@ static inline struct netfs_inode *netfs_inode(struct inode *inode) return container_of(inode, struct netfs_inode, inode); } +/** + * netfs_read_remote_i_size - Read remote_i_size safely + * @inode: The inode to access + * + * Read remote_i_size safely without the potential for tearing on 32-bit + * arches. + * + * NOTE: in a 32bit arch with a preemptable kernel and an UP compile the + * i_size_read/write must be atomic with respect to the local cpu (unlike with + * preempt disabled), but they don't need to be atomic with respect to other + * cpus like in true SMP (so they need either to either locally disable irq + * around the read or for example on x86 they can be still implemented as a + * cmpxchg8b without the need of the lock prefix). For SMP compiles and 64bit + * archs it makes no difference if preempt is enabled or not. + */ +static inline unsigned long long netfs_read_remote_i_size(const struct inode *inode) +{ + const struct netfs_inode *ictx = container_of(inode, struct netfs_inode, inode); + unsigned long long remote_i_size; + +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + unsigned int seq; + + do { + seq = read_seqcount_begin(&inode->i_size_seqcount); + remote_i_size = ictx->_remote_i_size; + } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) + preempt_disable(); + remote_i_size = ictx->_remote_i_size; + preempt_enable(); +#else + /* Pairs with smp_store_release() in netfs_write_remote_i_size() */ + remote_i_size = smp_load_acquire(&ictx->_remote_i_size); +#endif + return remote_i_size; +} + +/* + * netfs_write_remote_i_size - Set remote_i_size safely + * @inode: The inode to access + * @remote_i_size: The new value for the size of the file on the server + * + * Set remote_i_size safely without the potential for tearing on 32-bit arches. + * + * Context: The caller must hold inode->i_lock. + * + * NOTE: unlike netfs_read_remote_i_size(), netfs_write_remote_i_size() does + * need locking around it (normally i_rwsem), otherwise on 32bit/SMP an update + * of i_size_seqcount can be lost, resulting in subsequent i_size_read() calls + * spinning forever. + */ +static inline void netfs_write_remote_i_size(struct inode *inode, + unsigned long long remote_i_size) +{ + struct netfs_inode *ictx = netfs_inode(inode); + +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + write_seqcount_begin(&inode->i_size_seqcount); + ictx->_remote_i_size = remote_i_size; + write_seqcount_end(&inode->i_size_seqcount); +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) + preempt_disable(); + ictx->_remote_i_size = remote_i_size; + preempt_enable(); +#else + /* + * Pairs with smp_load_acquire() in netfs_read_remote_i_size() to + * ensure changes related to inode size (such as page contents) are + * visible before we see the changed inode size. + */ + smp_store_release(&ictx->_remote_i_size, remote_i_size); +#endif +} + +/** + * netfs_read_zero_point - Read zero_point safely + * @inode: The inode to access + * + * Read zero_point safely without the potential for tearing on 32-bit + * arches. + * + * NOTE: in a 32bit arch with a preemptable kernel and an UP compile the + * i_size_read/write must be atomic with respect to the local cpu (unlike with + * preempt disabled), but they don't need to be atomic with respect to other + * cpus like in true SMP (so they need either to either locally disable irq + * around the read or for example on x86 they can be still implemented as a + * cmpxchg8b without the need of the lock prefix). For SMP compiles and 64bit + * archs it makes no difference if preempt is enabled or not. + */ +static inline unsigned long long netfs_read_zero_point(const struct inode *inode) +{ + struct netfs_inode *ictx = container_of(inode, struct netfs_inode, inode); + unsigned long long zero_point; + +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + unsigned int seq; + + do { + seq = read_seqcount_begin(&inode->i_size_seqcount); + zero_point = ictx->_zero_point; + } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) + preempt_disable(); + zero_point = ictx->_zero_point; + preempt_enable(); +#else + /* Pairs with smp_store_release() in netfs_write_zero_point() */ + zero_point = smp_load_acquire(&ictx->_zero_point); +#endif + return zero_point; +} + +/* + * netfs_write_zero_point - Set zero_point safely + * @inode: The inode to access + * @zero_point: The new value for the point beyond which the server has no data + * + * Set zero_point safely without the potential for tearing on 32-bit arches. + * + * Context: The caller must hold inode->i_lock. + * + * NOTE: unlike netfs_read_zero_point(), netfs_write_zero_point() does need + * locking around it (normally i_rwsem), otherwise on 32bit/SMP an update of + * i_size_seqcount can be lost, resulting in subsequent read calls spinning + * forever. + */ +static inline void netfs_write_zero_point(struct inode *inode, + unsigned long long zero_point) +{ + struct netfs_inode *ictx = netfs_inode(inode); + +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + write_seqcount_begin(&inode->i_size_seqcount); + ictx->_zero_point = zero_point; + write_seqcount_end(&inode->i_size_seqcount); +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) + preempt_disable(); + ictx->_zero_point = zero_point; + preempt_enable(); +#else + /* + * Pairs with smp_load_acquire() in netfs_read_zero_point() to + * ensure changes related to inode size (such as page contents) are + * visible before we see the changed inode size. + */ + smp_store_release(&ictx->_zero_point, zero_point); +#endif +} + +/** + * netfs_read_sizes - Read remote_i_size and zero_point safely + * @inode: The inode to access + * @i_size: Where to return the local file size. + * @remote_i_size: Where to return the size of the file on the server + * @zero_point: Where to return the the point beyond which the server has no data + * + * Read remote_i_size and zero_point safely without the potential for tearing + * on 32-bit arches. + * + * NOTE: in a 32bit arch with a preemptable kernel and an UP compile the + * i_size_read/write must be atomic with respect to the local cpu (unlike with + * preempt disabled), but they don't need to be atomic with respect to other + * cpus like in true SMP (so they need either to either locally disable irq + * around the read or for example on x86 they can be still implemented as a + * cmpxchg8b without the need of the lock prefix). For SMP compiles and 64bit + * archs it makes no difference if preempt is enabled or not. + */ +static inline void netfs_read_sizes(const struct inode *inode, + unsigned long long *i_size, + unsigned long long *remote_i_size, + unsigned long long *zero_point) +{ + const struct netfs_inode *ictx = container_of(inode, struct netfs_inode, inode); +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + unsigned int seq; + + do { + seq = read_seqcount_begin(&inode->i_size_seqcount); + *i_size = inode->i_size; + *remote_i_size = ictx->_remote_i_size; + *zero_point = ictx->_zero_point; + } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) + preempt_disable(); + *i_size = inode->i_size; + *remote_i_size = ictx->_remote_i_size; + *zero_point = ictx->_zero_point; + preempt_enable(); +#else + /* Pairs with smp_store_release() in i_size_write() */ + *i_size = smp_load_acquire(&inode->i_size); + /* Pairs with smp_store_release() in netfs_write_remote_i_size() */ + *remote_i_size = smp_load_acquire(&ictx->_remote_i_size); + /* Pairs with smp_store_release() in netfs_write_zero_point() */ + *zero_point = smp_load_acquire(&ictx->_zero_point); +#endif +} + +/* + * netfs_write_sizes - Set i_size, remote_i_size and zero_point safely + * @inode: The inode to access + * @i_size: The new value for the local size of the file + * @remote_i_size: The new value for the size of the file on the server + * @zero_point: The new value for the point beyond which the server has no data + * + * Set both remote_i_size and zero_point safely without the potential for + * tearing on 32-bit arches. + * + * Context: The caller must hold inode->i_lock. + * + * NOTE: unlike netfs_read_zero_point(), netfs_write_zero_point() does need + * locking around it (normally i_rwsem), otherwise on 32bit/SMP an update of + * i_size_seqcount can be lost, resulting in subsequent read calls spinning + * forever. + */ +static inline void netfs_write_sizes(struct inode *inode, + unsigned long long i_size, + unsigned long long remote_i_size, + unsigned long long zero_point) +{ + struct netfs_inode *ictx = netfs_inode(inode); + +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + write_seqcount_begin(&inode->i_size_seqcount); + inode->i_size = i_size; + ictx->_remote_i_size = remote_i_size; + ictx->_zero_point = zero_point; + write_seqcount_end(&inode->i_size_seqcount); +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) + preempt_disable(); + inode->i_size = i_size; + ictx->_remote_i_size = remote_i_size; + ictx->_zero_point = zero_point; + preempt_enable(); +#else + /* + * Pairs with smp_load_acquire() in i_size_read(), + * netfs_read_remote_i_size() and netfs_read_zero_point() to ensure + * changes related to inode size (such as page contents) are visible + * before we see the changed inode size. + */ + smp_store_release(&inode->i_size, i_size); + smp_store_release(&ictx->_remote_i_size, remote_i_size); + smp_store_release(&ictx->_zero_point, zero_point); +#endif +} + /** * netfs_inode_init - Initialise a netfslib inode context * @ctx: The netfs inode to initialise @@ -488,8 +736,8 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, bool use_zero_point) { ctx->ops = ops; - ctx->remote_i_size = i_size_read(&ctx->inode); - ctx->zero_point = LLONG_MAX; + ctx->_remote_i_size = i_size_read(&ctx->inode); + ctx->_zero_point = LLONG_MAX; ctx->flags = 0; atomic_set(&ctx->io_count, 0); #if IS_ENABLED(CONFIG_FSCACHE) @@ -498,7 +746,7 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, mutex_init(&ctx->wb_lock); /* ->releasepage() drives zero_point */ if (use_zero_point) { - ctx->zero_point = ctx->remote_i_size; + ctx->_zero_point = ctx->_remote_i_size; mapping_set_release_always(ctx->inode.i_mapping); } } @@ -511,13 +759,40 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, * * Inform the netfs lib that a file got resized so that it can adjust its state. */ -static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size, +static inline void netfs_resize_file(struct netfs_inode *ictx, + unsigned long long new_i_size, bool changed_on_server) { +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + struct inode *inode = &ictx->inode; + + preempt_disable(); + write_seqcount_begin(&inode->i_size_seqcount); + if (changed_on_server) + ictx->_remote_i_size = new_i_size; + if (new_i_size < ictx->_zero_point) + ictx->_zero_point = new_i_size; + write_seqcount_end(&inode->i_size_seqcount); + preempt_enable(); +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) + preempt_disable(); if (changed_on_server) - ctx->remote_i_size = new_i_size; - if (new_i_size < ctx->zero_point) - ctx->zero_point = new_i_size; + ictx->_remote_i_size = new_i_size; + if (new_i_size < ictx->_zero_point) + ictx->_zero_point = new_i_size; + preempt_enable(); +#else + /* + * Pairs with smp_load_acquire() in netfs_read_remote_i_size and + * netfs_read_zero_point() to ensure changes related to inode size + * (such as page contents) are visible before we see the changed inode + * size. + */ + if (changed_on_server) + smp_store_release(&ictx->_remote_i_size, new_i_size); + if (new_i_size < ictx->_zero_point) + smp_store_release(&ictx->_zero_point, new_i_size); +#endif } /** -- cgit v1.2.3 From dbe556972100fabb8e5a1b3d2163831ff07b1e8e Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 12 May 2026 13:33:56 +0100 Subject: netfs: Fix potential UAF in netfs_unlock_abandoned_read_pages() netfs_unlock_abandoned_read_pages(rreq) accesses the index of the folios it is wanting to unlock and compares that to rreq->no_unlock_folio so that it doesn't unlock a folio being read for netfs_perform_write() or netfs_write_begin(). However, given that netfs_unlock_abandoned_read_pages() is called _after_ NETFS_RREQ_IN_PROGRESS is cleared, the one folio that it's not allowed to dereference is the one specified by ->no_unlock_folio as ownership immediately reverts to the caller. Fix this by storing the folio pointer instead and using that rather than the index. Also fix netfs_unlock_read_folio() where the same applies. Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading") Closes: https://sashiko.dev/#/patchset/20260414082004.3756080-1-dhowells%40redhat.com Signed-off-by: David Howells Link: https://patch.msgid.link/20260512123404.719402-20-dhowells@redhat.com cc: Paulo Alcantara cc: Viacheslav Dubeyko cc: Matthew Wilcox cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/buffered_read.c | 4 ++-- fs/netfs/read_collect.c | 2 +- fs/netfs/read_retry.c | 2 +- include/linux/netfs.h | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 004d426c02b4..83d0b8153e96 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -670,7 +670,7 @@ retry: ret = PTR_ERR(rreq); goto error; } - rreq->no_unlock_folio = folio->index; + rreq->no_unlock_folio = folio; __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); ret = netfs_begin_cache_read(rreq, ctx); @@ -736,7 +736,7 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio, goto error; } - rreq->no_unlock_folio = folio->index; + rreq->no_unlock_folio = folio; __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); ret = netfs_begin_cache_read(rreq, ctx); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 3c9b847885c2..23660a590124 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -83,7 +83,7 @@ static void netfs_unlock_read_folio(struct netfs_io_request *rreq, } just_unlock: - if (folio->index == rreq->no_unlock_folio && + if (folio == rreq->no_unlock_folio && test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) { _debug("no unlock"); } else { diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index e10eb5a07332..f59a70f3a086 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -292,7 +292,7 @@ void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq) struct folio *folio = folioq_folio(p, slot); if (folio && !folioq_is_marked2(p, slot)) { - if (folio->index == rreq->no_unlock_folio && + if (folio == rreq->no_unlock_folio && test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) { _debug("no unlock"); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 4fd1d796ad73..243c0f737938 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -252,7 +252,7 @@ struct netfs_io_request { unsigned long long collected_to; /* Point we've collected to */ unsigned long long cleaned_to; /* Position we've cleaned folios to */ unsigned long long abandon_to; /* Position to abandon folios to */ - pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ + const struct folio *no_unlock_folio; /* Don't unlock this folio after read */ unsigned int direct_bv_count; /* Number of elements in direct_bv[] */ unsigned int debug_id; unsigned int rsize; /* Maximum read size (0 for none) */ -- cgit v1.2.3 From 6a288a4ddb4a994490505ab5f41c445f8e6b6467 Mon Sep 17 00:00:00 2001 From: "David Hildenbrand (Arm)" Date: Tue, 21 Apr 2026 17:39:07 +0200 Subject: mm/page_alloc: fix initialization of tags of the huge zero folio with init_on_free __GFP_ZEROTAGS semantics are currently a bit weird, but effectively this flag is only ever set alongside __GFP_ZERO and __GFP_SKIP_KASAN. If we run with init_on_free, we will zero out pages during __free_pages_prepare(), to skip zeroing on the allocation path. However, when allocating with __GFP_ZEROTAG set, post_alloc_hook() will consequently not only skip clearing page content, but also skip clearing tag memory. Not clearing tags through __GFP_ZEROTAGS is irrelevant for most pages that will get mapped to user space through set_pte_at() later: set_pte_at() and friends will detect that the tags have not been initialized yet (PG_mte_tagged not set), and initialize them. However, for the huge zero folio, which will be mapped through a PMD marked as special, this initialization will not be performed, ending up exposing whatever tags were still set for the pages. The docs (Documentation/arch/arm64/memory-tagging-extension.rst) state that allocation tags are set to 0 when a page is first mapped to user space. That no longer holds with the huge zero folio when init_on_free is enabled. Fix it by decoupling __GFP_ZEROTAGS from __GFP_ZERO, passing to tag_clear_highpages() whether we want to also clear page content. Invert the meaning of the tag_clear_highpages() return value to have clearer semantics. Reproduced with the huge zero folio by modifying the check_buffer_fill arm64/mte selftest to use a 2 MiB area, after making sure that pages have a non-0 tag set when freeing (note that, during boot, we will not actually initialize tags, but only set KASAN_TAG_KERNEL in the page flags). $ ./check_buffer_fill 1..20 ... not ok 17 Check initial tags with private mapping, sync error mode and mmap memory not ok 18 Check initial tags with private mapping, sync error mode and mmap/mprotect memory ... This code needs more cleanups; we'll tackle that next, like decoupling __GFP_ZEROTAGS from __GFP_SKIP_KASAN. [akpm@linux-foundation.org: s/__GPF_ZERO/__GFP_ZERO/, per David] Link: https://lore.kernel.org/20260421-zerotags-v2-1-05cb1035482e@kernel.org Fixes: adfb6609c680 ("mm/huge_memory: initialise the tags of the huge zero folio") Signed-off-by: David Hildenbrand (Arm) Reviewed-by: Catalin Marinas Tested-by: Lance Yang Cc: Brendan Jackman Cc: Dev Jain Cc: Johannes Weiner Cc: Liam Howlett Cc: Lorenzo Stoakes (Oracle) Cc: Mark Brown Cc: Michal Hocko Cc: Mike Rapoport Cc: Ryan Roberts Cc: Suren Baghdasaryan Cc: Will Deacon Cc: Zi Yan Cc: Signed-off-by: Andrew Morton --- arch/arm64/include/asm/page.h | 2 +- arch/arm64/mm/fault.c | 11 +++++++---- include/linux/gfp_types.h | 10 +++++----- include/linux/highmem.h | 7 ++++--- mm/page_alloc.c | 8 ++++---- 5 files changed, 21 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h index e25d0d18f6d7..58200de8a221 100644 --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -33,7 +33,7 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr); #define vma_alloc_zeroed_movable_folio vma_alloc_zeroed_movable_folio -bool tag_clear_highpages(struct page *to, int numpages); +bool tag_clear_highpages(struct page *to, int numpages, bool clear_pages); #define __HAVE_ARCH_TAG_CLEAR_HIGHPAGES #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 0f3c5c7ca054..739800835920 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -1018,7 +1018,7 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, return vma_alloc_folio(flags, 0, vma, vaddr); } -bool tag_clear_highpages(struct page *page, int numpages) +bool tag_clear_highpages(struct page *page, int numpages, bool clear_pages) { /* * Check if MTE is supported and fall back to clear_highpage(). @@ -1026,13 +1026,16 @@ bool tag_clear_highpages(struct page *page, int numpages) * post_alloc_hook() will invoke tag_clear_highpages(). */ if (!system_supports_mte()) - return false; + return clear_pages; /* Newly allocated pages, shouldn't have been tagged yet */ for (int i = 0; i < numpages; i++, page++) { WARN_ON_ONCE(!try_page_mte_tagging(page)); - mte_zero_clear_page_tags(page_address(page)); + if (clear_pages) + mte_zero_clear_page_tags(page_address(page)); + else + mte_clear_page_tags(page_address(page)); set_page_mte_tagged(page); } - return true; + return false; } diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 6c75df30a281..cd4972a7c97c 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -273,11 +273,11 @@ enum { * * %__GFP_ZERO returns a zeroed page on success. * - * %__GFP_ZEROTAGS zeroes memory tags at allocation time if the memory itself - * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that - * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting - * memory tags at the same time as zeroing memory has minimal additional - * performance impact. + * %__GFP_ZEROTAGS zeroes memory tags at allocation time. Setting memory tags at + * the same time as zeroing memory (e.g., with __GFP_ZERO) has minimal + * additional performance impact. However, __GFP_ZEROTAGS also zeroes the tags + * even if memory is not getting zeroed at allocation time (e.g., + * with init_on_free). * * %__GFP_SKIP_KASAN makes KASAN skip unpoisoning on page allocation. * Used for userspace and vmalloc pages; the latter are unpoisoned by diff --git a/include/linux/highmem.h b/include/linux/highmem.h index af03db851a1d..d7aac9de1c8a 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -347,10 +347,11 @@ static inline void clear_highpage_kasan_tagged(struct page *page) #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGES -/* Return false to let people know we did not initialize the pages */ -static inline bool tag_clear_highpages(struct page *page, int numpages) +/* Returns true if the caller has to initialize the pages */ +static inline bool tag_clear_highpages(struct page *page, int numpages, + bool clear_pages) { - return false; + return clear_pages; } #endif diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 227d58dc3de6..23c7298d3be2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1808,9 +1808,9 @@ static inline bool should_skip_init(gfp_t flags) inline void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags) { + const bool zero_tags = gfp_flags & __GFP_ZEROTAGS; bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags) && !should_skip_init(gfp_flags); - bool zero_tags = init && (gfp_flags & __GFP_ZEROTAGS); int i; set_page_private(page, 0); @@ -1832,11 +1832,11 @@ inline void post_alloc_hook(struct page *page, unsigned int order, */ /* - * If memory tags should be zeroed - * (which happens only when memory should be initialized as well). + * Clearing tags can efficiently clear the memory for us as well, if + * required. */ if (zero_tags) - init = !tag_clear_highpages(page, 1 << order); + init = tag_clear_highpages(page, 1 << order, /* clear_pages= */init); if (!should_skip_kasan_unpoison(gfp_flags) && kasan_unpoison_pages(page, order, init)) { -- cgit v1.2.3 From 3d562d35a044ae798cab421c65a116f8cedfa5d4 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sun, 17 May 2026 09:55:28 +0200 Subject: bpf: Check global subprog exception paths Global subprogs are verified independently and are not descended into when their callers are symbolically executed. This means a caller can hold references or locks across a global subprog call that may throw, while the verifier only checks the non-exceptional return path at the call site. Record whether a subprog might throw in the CFG summary pass, alongside the existing might_sleep and packet-data-changing summaries, and propagate that effect through reachable callees. When a global subprog is marked as possibly throwing, push the normal continuation and validate the exceptional path immediately at the call site, avoiding a synthetic exception state and associated special case in the pruning checks. Fixes: f18b03fabaa9 ("bpf: Implement BPF exceptions") Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260517075530.3461166-2-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 2 ++ kernel/bpf/cfg.c | 13 ++++++++++++- kernel/bpf/verifier.c | 23 +++++++++++++++++------ 3 files changed, 31 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b148f816f25b..185b2aa43a42 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -729,6 +729,7 @@ struct bpf_subprog_info { */ s16 fastcall_stack_off; bool has_tail_call: 1; + bool might_throw: 1; bool tail_call_reachable: 1; bool has_ld_abs: 1; bool is_cb: 1; @@ -1308,6 +1309,7 @@ void bpf_fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask); bool bpf_subprog_is_global(const struct bpf_verifier_env *env, int subprog); int bpf_find_subprog(struct bpf_verifier_env *env, int off); +bool bpf_is_throw_kfunc(struct bpf_insn *insn); int bpf_compute_const_regs(struct bpf_verifier_env *env); int bpf_prune_dead_branches(struct bpf_verifier_env *env); int bpf_check_cfg(struct bpf_verifier_env *env); diff --git a/kernel/bpf/cfg.c b/kernel/bpf/cfg.c index 998f42a8189a..26d37066465f 100644 --- a/kernel/bpf/cfg.c +++ b/kernel/bpf/cfg.c @@ -64,11 +64,19 @@ static void mark_subprog_might_sleep(struct bpf_verifier_env *env, int off) subprog->might_sleep = true; } +static void mark_subprog_might_throw(struct bpf_verifier_env *env, int off) +{ + struct bpf_subprog_info *subprog; + + subprog = bpf_find_containing_subprog(env, off); + subprog->might_throw = true; +} + /* 't' is an index of a call-site. * 'w' is a callee entry point. * Eventually this function would be called when env->cfg.insn_state[w] == EXPLORED. * Rely on DFS traversal order and absence of recursive calls to guarantee that - * callee's change_pkt_data marks would be correct at that moment. + * callee's effect marks would be correct at that moment. */ static void merge_callee_effects(struct bpf_verifier_env *env, int t, int w) { @@ -78,6 +86,7 @@ static void merge_callee_effects(struct bpf_verifier_env *env, int t, int w) callee = bpf_find_containing_subprog(env, w); caller->changes_pkt_data |= callee->changes_pkt_data; caller->might_sleep |= callee->might_sleep; + caller->might_throw |= callee->might_throw; } enum { @@ -509,6 +518,8 @@ static int visit_insn(int t, struct bpf_verifier_env *env) mark_subprog_might_sleep(env, t); if (ret == 0 && bpf_is_kfunc_pkt_changing(&meta)) mark_subprog_changes_pkt_data(env, t); + if (ret == 0 && bpf_is_throw_kfunc(insn)) + mark_subprog_might_throw(env, t); } return visit_func_call_insn(t, insns, env, insn->src_reg == BPF_PSEUDO_CALL); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 88b40c979b56..7fb88e1cd7c4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -442,7 +442,6 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id) static bool is_sync_callback_calling_kfunc(u32 btf_id); static bool is_async_callback_calling_kfunc(u32 btf_id); static bool is_callback_calling_kfunc(u32 btf_id); -static bool is_bpf_throw_kfunc(struct bpf_insn *insn); static bool is_bpf_wq_set_callback_kfunc(u32 btf_id); static bool is_task_work_add_kfunc(u32 func_id); @@ -5405,7 +5404,7 @@ continue_func: if (bpf_pseudo_kfunc_call(insn + i) && !insn[i].off) { bool err = false; - if (!is_bpf_throw_kfunc(insn + i)) + if (!bpf_is_throw_kfunc(insn + i)) continue; for (tmp = idx; tmp >= 0 && !err; tmp = dinfo[tmp].caller) { if (subprog[tmp].is_cb) { @@ -9499,6 +9498,9 @@ static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *ins return 0; } +static int process_bpf_exit_full(struct bpf_verifier_env *env, + bool *do_print_state, bool exception_exit); + static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { @@ -9552,6 +9554,17 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; } + if (env->subprog_info[subprog].might_throw) { + struct bpf_verifier_state *branch; + + branch = push_stack(env, *insn_idx + 1, *insn_idx, false); + if (IS_ERR(branch)) { + verbose(env, "failed to push state for global subprog exception path\n"); + return PTR_ERR(branch); + } + return process_bpf_exit_full(env, NULL, true); + } + /* continue with next insn after call */ return 0; } @@ -11782,7 +11795,7 @@ static bool is_async_callback_calling_kfunc(u32 btf_id) is_task_work_add_kfunc(btf_id); } -static bool is_bpf_throw_kfunc(struct bpf_insn *insn) +bool bpf_is_throw_kfunc(struct bpf_insn *insn) { return bpf_pseudo_kfunc_call(insn) && insn->off == 0 && insn->imm == special_kfunc_list[KF_bpf_throw]; @@ -12972,8 +12985,6 @@ static int check_special_kfunc(struct bpf_verifier_env *env, struct bpf_kfunc_ca } static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name); -static int process_bpf_exit_full(struct bpf_verifier_env *env, - bool *do_print_state, bool exception_exit); static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) @@ -13354,7 +13365,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (meta.func_id == special_kfunc_list[KF_bpf_session_cookie]) env->prog->call_session_cookie = true; - if (is_bpf_throw_kfunc(insn)) + if (bpf_is_throw_kfunc(insn)) return process_bpf_exit_full(env, NULL, true); return 0; -- cgit v1.2.3 From f233124fb36cd57ef09f96d517a38ab4b902e15e Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 14 May 2026 09:39:01 +0200 Subject: ata: libata-scsi: do not use the deferred QC feature on PMPs with CBS When using Port Multipliers (PMPs) with Command-Based Switching (CBS), you can only issue commands to one link at a time. For PMPs with CBS, there is already code to handle commands being sent to different links in sata_pmp_qc_defer_cmd_switch() using ap->excl_link. sata_sil24 also makes use of ap->excl_link. A user on the list reported that commit 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") broke PMPs with CBS. The commit introduced code that stores a deferred qc in ap->deferred_qc, to later be issued via a workqueue. It turns out that this change is incompatible with the existing ap->excl_link handling used by PMPs with CBS. Thus, modify sata_pmp_qc_defer_cmd_switch() and sil24_qc_defer() to return ATA_DEFER_LINK_EXCL, and make sure that the deferred QC handling via workqueue is not used for this return value. This way, PMPs with CBS will work once again. Note that the starvation referenced in commit 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") can only happen on libsas ports, and libsas does not support Port Multipliers, thus there is no harm of reverting back to the previous way of deferring commands for PMPs with CBS. Non-libsas ports connected to anything but a PMP with CBS (e.g. a normal drive or a PMP with FBS) will continue using the deferred workqueue, since it does result in lower completion latencies for non-NCQ commands, even though the workqueue is not strictly needed to avoid starvation for non-libsas ports. If we want to modify the scope of the workqueue issuing to also handle PMPs with CBS, then we should ensure that we can save both NCQ and non-NCQ commands in ap->deferred_qc, while also removing the existing PMP CBS handling using ap->excl_link, such that we don't duplicate features. While at it, also add a comment explaining how the ap->excl_link mechanism works. Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") Tested-by: Tommy Kelly Reported-by: Tommy Kelly Closes: https://lore.kernel.org/linux-ide/ce09cc21-a8e9-4845-b205-35411e22fba9@tkel.ly/ Reviewed-by: Damien Le Moal Signed-off-by: Niklas Cassel --- drivers/ata/libata-pmp.c | 13 ++++++++++++- drivers/ata/libata-scsi.c | 8 ++++++++ drivers/ata/sata_sil24.c | 6 +++++- include/linux/libata.h | 1 + 4 files changed, 26 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c index e3adc008fed1..7e889534d73b 100644 --- a/drivers/ata/libata-pmp.c +++ b/drivers/ata/libata-pmp.c @@ -110,13 +110,24 @@ int sata_pmp_qc_defer_cmd_switch(struct ata_queued_cmd *qc) { struct ata_link *link = qc->dev->link; struct ata_port *ap = link->ap; + int ret; if (ap->excl_link == NULL || ap->excl_link == link) { if (ap->nr_active_links == 0 || ata_link_active(link)) { qc->flags |= ATA_QCFLAG_CLEAR_EXCL; - return ata_std_qc_defer(qc); + ret = ata_std_qc_defer(qc); + if (ret == ATA_DEFER_LINK) + return ATA_DEFER_LINK_EXCL; + return ret; } + /* + * Note: ap->excl_link contains the link that is next in line, + * i.e. implicit round robin. If there is only one link + * dispatching, ap->excl_link will be left unclaimed, allowing + * other links to set ap->excl_link, ensuring that the currently + * active link cannot queue any more. + */ ap->excl_link = link; } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index f03b6326ad2d..ca29744c57f9 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1787,6 +1787,14 @@ static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) case ATA_DEFER_LINK: ret = SCSI_MLQUEUE_DEVICE_BUSY; goto defer_qc; + case ATA_DEFER_LINK_EXCL: + /* + * Drivers making use of ap->excl_link cannot store the QC in + * ap->deferred_qc, because the ap->excl_link handling is + * incompatible with the ap->deferred_qc workqueue handling. + */ + ret = SCSI_MLQUEUE_DEVICE_BUSY; + goto free_qc; case ATA_DEFER_PORT: ret = SCSI_MLQUEUE_HOST_BUSY; goto free_qc; diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index d642ece9f07a..57f1081b86db 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -789,6 +789,7 @@ static int sil24_qc_defer(struct ata_queued_cmd *qc) struct ata_link *link = qc->dev->link; struct ata_port *ap = link->ap; u8 prot = qc->tf.protocol; + int ret; /* * There is a bug in the chip: @@ -826,7 +827,10 @@ static int sil24_qc_defer(struct ata_queued_cmd *qc) qc->flags |= ATA_QCFLAG_CLEAR_EXCL; } - return ata_std_qc_defer(qc); + ret = ata_std_qc_defer(qc); + if (ret == ATA_DEFER_LINK) + return ATA_DEFER_LINK_EXCL; + return ret; } static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc) diff --git a/include/linux/libata.h b/include/linux/libata.h index 5c085ef4eda7..360776016b50 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -371,6 +371,7 @@ enum { /* return values for ->qc_defer */ ATA_DEFER_LINK = 1, ATA_DEFER_PORT = 2, + ATA_DEFER_LINK_EXCL = 3, /* desc_len for ata_eh_info and context */ ATA_EH_DESC_LEN = 80, -- cgit v1.2.3 From 759e8756da00aa115d504a18155b1d1ee1cc12e8 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 14 May 2026 09:39:02 +0200 Subject: ata: libata-scsi: do not needlessly defer commands when using PMP with FBS The ACS specification does not allow a non-NCQ command to be issued while an NCQ command is outstanding. Commit 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") introduced a feature where a deferred non-NCQ command gets issued from a workqueue. The design stores a single non-NCQ command per port. However, when using Port Multipliers (PMPs), specifically PMPs that support FIS-Based Switching (FBS), non-NCQ and NCQ commands can be mixed on the same port, just not for the same link, see e.g. ata_std_qc_defer() which is, and always has operated on a per-link basis. Therefore, move the deferred_qc from struct ata_port to struct ata_link. This way, when using a PMP with FBS, we will not needlessly defer commands to all other links, just because one link issued a non-NCQ command while having an NCQ command outstanding. Only commands for that specific link will be deferred. This is in line with how PMPs with FBS worked before commit 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation"). Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation") Tested-by: Tommy Kelly Reviewed-by: Damien Le Moal Signed-off-by: Niklas Cassel --- drivers/ata/libata-core.c | 9 ++++++--- drivers/ata/libata-eh.c | 8 ++++---- drivers/ata/libata-pmp.c | 5 ++++- drivers/ata/libata-scsi.c | 43 +++++++++++++++++++++++++------------------ include/linux/libata.h | 6 +++--- 5 files changed, 42 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index e76d15411e2a..3d0027ec33c2 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5584,6 +5584,7 @@ void ata_link_init(struct ata_port *ap, struct ata_link *link, int pmp) link->pmp = pmp; link->active_tag = ATA_TAG_POISON; link->hw_sata_spd_limit = UINT_MAX; + INIT_WORK(&link->deferred_qc_work, ata_scsi_deferred_qc_work); /* can't use iterator, ap isn't initialized yet */ for (i = 0; i < ATA_MAX_DEVICES; i++) { @@ -5666,7 +5667,6 @@ struct ata_port *ata_port_alloc(struct ata_host *host) mutex_init(&ap->scsi_scan_mutex); INIT_DELAYED_WORK(&ap->hotplug_task, ata_scsi_hotplug); INIT_DELAYED_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan); - INIT_WORK(&ap->deferred_qc_work, ata_scsi_deferred_qc_work); INIT_LIST_HEAD(&ap->eh_done_q); init_waitqueue_head(&ap->eh_wait_q); init_completion(&ap->park_req_pending); @@ -6291,12 +6291,15 @@ static void ata_port_detach(struct ata_port *ap) /* It better be dead now and not have any remaining deferred qc. */ WARN_ON(!(ap->pflags & ATA_PFLAG_UNLOADED)); - WARN_ON(ap->deferred_qc); - cancel_work_sync(&ap->deferred_qc_work); cancel_delayed_work_sync(&ap->hotplug_task); cancel_delayed_work_sync(&ap->scsi_rescan_task); + ata_for_each_link(link, ap, PMP_FIRST) { + WARN_ON(link->deferred_qc); + cancel_work_sync(&link->deferred_qc_work); + } + /* Delete port multiplier link transport devices */ if (ap->pmp_link) { int i; diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 9a4b67b90b17..d623eb32ed8b 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -651,11 +651,11 @@ int ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, if (qc->scsicmd != scmd) continue; if ((qc->flags & ATA_QCFLAG_ACTIVE) || - qc == ap->deferred_qc) + qc == qc->dev->link->deferred_qc) break; } - if (i < ATA_MAX_QUEUE && qc == ap->deferred_qc) { + if (i < ATA_MAX_QUEUE && qc == qc->dev->link->deferred_qc) { /* * This is a deferred command that timed out while * waiting for the command queue to drain. Since the qc @@ -666,8 +666,8 @@ int ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, * deferred qc work from issuing this qc. */ WARN_ON_ONCE(qc->flags & ATA_QCFLAG_ACTIVE); - ap->deferred_qc = NULL; - cancel_work(&ap->deferred_qc_work); + qc->dev->link->deferred_qc = NULL; + cancel_work(&qc->dev->link->deferred_qc_work); set_host_byte(scmd, DID_TIME_OUT); scsi_eh_finish_cmd(scmd, &ap->eh_done_q); } else if (i < ATA_MAX_QUEUE) { diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c index 7e889534d73b..e8540931b4a1 100644 --- a/drivers/ata/libata-pmp.c +++ b/drivers/ata/libata-pmp.c @@ -582,8 +582,11 @@ static void sata_pmp_detach(struct ata_device *dev) if (ap->ops->pmp_detach) ap->ops->pmp_detach(ap); - ata_for_each_link(tlink, ap, EDGE) + ata_for_each_link(tlink, ap, EDGE) { + WARN_ON(tlink->deferred_qc); + cancel_work_sync(&tlink->deferred_qc_work); ata_eh_detach_dev(tlink->device); + } spin_lock_irqsave(ap->lock, flags); ap->nr_pmp_links = 0; diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index ca29744c57f9..d43207c6e467 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1664,8 +1664,9 @@ static void ata_scsi_qc_done(struct ata_queued_cmd *qc, bool set_result, void ata_scsi_deferred_qc_work(struct work_struct *work) { - struct ata_port *ap = - container_of(work, struct ata_port, deferred_qc_work); + struct ata_link *link = + container_of(work, struct ata_link, deferred_qc_work); + struct ata_port *ap = link->ap; struct ata_queued_cmd *qc; unsigned long flags; @@ -1676,10 +1677,10 @@ void ata_scsi_deferred_qc_work(struct work_struct *work) * such case, we should not need any more deferring the qc, so warn if * qc_defer() says otherwise. */ - qc = ap->deferred_qc; + qc = link->deferred_qc; if (qc && !ata_port_eh_scheduled(ap)) { WARN_ON_ONCE(ap->ops->qc_defer(qc)); - ap->deferred_qc = NULL; + link->deferred_qc = NULL; ata_qc_issue(qc); } @@ -1688,7 +1689,7 @@ void ata_scsi_deferred_qc_work(struct work_struct *work) void ata_scsi_requeue_deferred_qc(struct ata_port *ap) { - struct ata_queued_cmd *qc = ap->deferred_qc; + struct ata_link *link; lockdep_assert_held(ap->lock); @@ -1697,16 +1698,21 @@ void ata_scsi_requeue_deferred_qc(struct ata_port *ap) * do not try to be smart about what to do with this deferred command * and simply requeue it by completing it with DID_REQUEUE. */ - if (qc) { - ap->deferred_qc = NULL; - cancel_work(&ap->deferred_qc_work); - ata_scsi_qc_done(qc, true, DID_REQUEUE << 16); + ata_for_each_link(link, ap, PMP_FIRST) { + struct ata_queued_cmd *qc = link->deferred_qc; + + if (qc) { + link->deferred_qc = NULL; + cancel_work(&link->deferred_qc_work); + ata_scsi_qc_done(qc, true, DID_REQUEUE << 16); + } } } -static void ata_scsi_schedule_deferred_qc(struct ata_port *ap) +static void ata_scsi_schedule_deferred_qc(struct ata_link *link) { - struct ata_queued_cmd *qc = ap->deferred_qc; + struct ata_queued_cmd *qc = link->deferred_qc; + struct ata_port *ap = link->ap; lockdep_assert_held(ap->lock); @@ -1723,12 +1729,12 @@ static void ata_scsi_schedule_deferred_qc(struct ata_port *ap) return; } if (!ap->ops->qc_defer(qc)) - queue_work(system_highpri_wq, &ap->deferred_qc_work); + queue_work(system_highpri_wq, &link->deferred_qc_work); } static void ata_scsi_qc_complete(struct ata_queued_cmd *qc) { - struct ata_port *ap = qc->ap; + struct ata_link *link = qc->dev->link; struct scsi_cmnd *cmd = qc->scsicmd; u8 *cdb = cmd->cmnd; bool have_sense = qc->flags & ATA_QCFLAG_SENSE_VALID; @@ -1759,11 +1765,12 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc) ata_scsi_qc_done(qc, false, 0); - ata_scsi_schedule_deferred_qc(ap); + ata_scsi_schedule_deferred_qc(link); } static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) { + struct ata_link *link = qc->dev->link; int ret; if (!ap->ops->qc_defer) @@ -1774,7 +1781,7 @@ static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) * requeue and defer all incoming commands until the deferred qc is * processed, once all on-going commands complete. */ - if (ap->deferred_qc) { + if (link->deferred_qc) { ata_qc_free(qc); return SCSI_MLQUEUE_DEVICE_BUSY; } @@ -1790,8 +1797,8 @@ static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) case ATA_DEFER_LINK_EXCL: /* * Drivers making use of ap->excl_link cannot store the QC in - * ap->deferred_qc, because the ap->excl_link handling is - * incompatible with the ap->deferred_qc workqueue handling. + * link->deferred_qc, because the ap->excl_link handling is + * incompatible with the link->deferred_qc workqueue handling. */ ret = SCSI_MLQUEUE_DEVICE_BUSY; goto free_qc; @@ -1817,7 +1824,7 @@ defer_qc: * commands complete. */ if (!ata_is_ncq(qc->tf.protocol)) { - ap->deferred_qc = qc; + link->deferred_qc = qc; return 0; } diff --git a/include/linux/libata.h b/include/linux/libata.h index 360776016b50..127229fbd1a6 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -855,6 +855,9 @@ struct ata_link { unsigned int sata_spd; /* current SATA PHY speed */ enum ata_lpm_policy lpm_policy; + struct work_struct deferred_qc_work; + struct ata_queued_cmd *deferred_qc; + /* record runtime error info, protected by host_set lock */ struct ata_eh_info eh_info; /* EH context */ @@ -900,9 +903,6 @@ struct ata_port { u64 qc_active; int nr_active_links; /* #links with active qcs */ - struct work_struct deferred_qc_work; - struct ata_queued_cmd *deferred_qc; - struct ata_link link; /* host default link */ struct ata_link *slave_link; /* see ata_slave_link_init() */ -- cgit v1.2.3 From 8817005efbdfdf5d4e4814cb5dc52b53d12917d7 Mon Sep 17 00:00:00 2001 From: Qing Ming Date: Sat, 16 May 2026 15:08:49 +0800 Subject: cgroup/rstat: validate cpu before css_rstat_cpu() access css_rstat_updated() is exposed as a BPF kfunc and accepts a caller-provided cpu argument. The function uses cpu for per-cpu rstat lookups without checking whether it refers to a valid possible CPU. A BPF iter/cgroup program with CAP_BPF and CAP_PERFMON can pass an invalid cpu value. On an unfixed UBSCAN_BOUNDS test kernel, cpu == 0x7fffffff triggers: UBSAN: array-index-out-of-bounds in kernel/cgroup/rstat.c:31:9 index 2147483647 is out of range for type 'long unsigned int [64]' Call Trace: css_rstat_updated bpf_iter_run_prog cgroup_iter_seq_show bpf_seq_read Add cpu validation to the BPF-facing css_rstat_updated() kfunc and move the common implementation to __css_rstat_updated() for in-kernel callers. Fixes: a319185be9f5 ("cgroup: bpf: enable bpf programs to integrate with rstat") Signed-off-by: Qing Ming Signed-off-by: Tejun Heo --- block/blk-cgroup.c | 2 +- include/linux/cgroup.h | 1 + kernel/cgroup/rstat.c | 30 ++++++++++++++++++++---------- mm/memcontrol.c | 6 +++--- 4 files changed, 25 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 554c87bb4a86..bc63bd220865 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -2241,7 +2241,7 @@ void blk_cgroup_bio_start(struct bio *bio) } u64_stats_update_end_irqrestore(&bis->sync, flags); - css_rstat_updated(&blkcg->css, cpu); + __css_rstat_updated(&blkcg->css, cpu); put_cpu(); } diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index e52160e85af4..e011dc43fcf1 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -776,6 +776,7 @@ static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) /* * cgroup scalable recursive statistics. */ +void __css_rstat_updated(struct cgroup_subsys_state *css, int cpu); void css_rstat_updated(struct cgroup_subsys_state *css, int cpu); void css_rstat_flush(struct cgroup_subsys_state *css); diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 150e5871e66f..ed60ba119c68 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" +#include #include #include @@ -53,7 +54,7 @@ static inline struct llist_head *ss_lhead_cpu(struct cgroup_subsys *ss, int cpu) } /** - * css_rstat_updated - keep track of updated rstat_cpu + * __css_rstat_updated - keep track of updated rstat_cpu * @css: target cgroup subsystem state * @cpu: cpu on which rstat_cpu was updated * @@ -63,20 +64,17 @@ static inline struct llist_head *ss_lhead_cpu(struct cgroup_subsys *ss, int cpu) * * NOTE: if the user needs the guarantee that the updater either add itself in * the lockless list or the concurrent flusher flushes its updated stats, a - * memory barrier is needed before the call to css_rstat_updated() i.e. a + * memory barrier is needed before the call to __css_rstat_updated() i.e. a * barrier after updating the per-cpu stats and before calling - * css_rstat_updated(). + * __css_rstat_updated(). */ -__bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu) +void __css_rstat_updated(struct cgroup_subsys_state *css, int cpu) { struct llist_head *lhead; struct css_rstat_cpu *rstatc; struct llist_node *self; - /* - * Since bpf programs can call this function, prevent access to - * uninitialized rstat pointers. - */ + /* Prevent access to uninitialized rstat pointers. */ if (!css_uses_rstat(css)) return; @@ -125,6 +123,18 @@ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu) llist_add(&rstatc->lnode, lhead); } +/* + * BPF-facing wrapper for __css_rstat_updated(). Validate the caller-provided + * CPU before passing it to the internal rstat updater. + */ +__bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu) +{ + if (unlikely(cpu < 0 || cpu >= nr_cpu_ids || !cpu_possible(cpu))) + return; + + __css_rstat_updated(css, cpu); +} + static void __css_process_update_tree(struct cgroup_subsys_state *css, int cpu) { /* put @css and all ancestors on the corresponding updated lists */ @@ -170,7 +180,7 @@ static void css_process_update_tree(struct cgroup_subsys *ss, int cpu) * flusher flush the stats updated by the updater who have * observed that they are already on the list. The * corresponding barrier pair for this one should be before - * css_rstat_updated() by the user. + * __css_rstat_updated() by the user. * * For now, there aren't any such user, so not adding the * barrier here but if such a use-case arise, please add @@ -614,7 +624,7 @@ static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, unsigned long flags) { u64_stats_update_end_irqrestore(&rstatbc->bsync, flags); - css_rstat_updated(&cgrp->self, smp_processor_id()); + __css_rstat_updated(&cgrp->self, smp_processor_id()); put_cpu_ptr(rstatbc); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 051b82ebf371..c7e60f26013c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -579,7 +579,7 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val, if (!val) return; - css_rstat_updated(&memcg->css, cpu); + __css_rstat_updated(&memcg->css, cpu); statc_pcpu = memcg->vmstats_percpu; for (; statc_pcpu; statc_pcpu = statc->parent_pcpu) { statc = this_cpu_ptr(statc_pcpu); @@ -2608,7 +2608,7 @@ static inline void account_slab_nmi_safe(struct mem_cgroup *memcg, struct mem_cgroup_per_node *pn = memcg->nodeinfo[pgdat->node_id]; /* preemption is disabled in_nmi(). */ - css_rstat_updated(&memcg->css, smp_processor_id()); + __css_rstat_updated(&memcg->css, smp_processor_id()); if (idx == NR_SLAB_RECLAIMABLE_B) atomic_add(nr, &pn->slab_reclaimable); else @@ -2832,7 +2832,7 @@ static inline void account_kmem_nmi_safe(struct mem_cgroup *memcg, int val) mod_memcg_state(memcg, MEMCG_KMEM, val); } else { /* preemption is disabled in_nmi(). */ - css_rstat_updated(&memcg->css, smp_processor_id()); + __css_rstat_updated(&memcg->css, smp_processor_id()); atomic_add(val, &memcg->kmem_stat); } } -- cgit v1.2.3 From 8939562b16052c75b908d3c5f968bffb526fc6e9 Mon Sep 17 00:00:00 2001 From: Rong Tao Date: Mon, 18 May 2026 15:02:08 +0800 Subject: efi: efi.h: Remove extra semicolon Remove extra semicolons from comments. Signed-off-by: Rong Tao Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 72e76ec54641..ccbc35479684 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -61,7 +61,7 @@ typedef void *efi_handle_t; /* * The UEFI spec and EDK2 reference implementation both define EFI_GUID as - * struct { u32 a; u16; b; u16 c; u8 d[8]; }; and so the implied alignment + * struct { u32 a; u16 b; u16 c; u8 d[8]; }; and so the implied alignment * is 32 bits not 8 bits like our guid_t. In some cases (i.e., on 32-bit ARM), * this means that firmware services invoked by the kernel may assume that * efi_guid_t* arguments are 32-bit aligned, and use memory accessors that -- cgit v1.2.3 From 0cb5a74faa3bdcfa3b18735d554e12c0f615e35d Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Mon, 18 May 2026 15:44:57 +0200 Subject: net: airoha: Fix NPU RX DMA descriptor bits In an internal review from Airoha, it was notice that the RX DMA descriptor bits and mask are wrong. These values probably refer to an old NPU firmware never published. The previous value works correctly but it was reported that in some specific condition in mixed scenario with both Ethernet and WiFi offload it's possible that RX DMA descriptor signal wrong value with the problem to the RX ring or packets getting dropped. To handle these specific scenario, apply the new suggested bits mask from Airoha. Correct functionality of both AN7581 NPU and MT7996 variant were verified and confirmed working. Fixes: a7fc8c641cab ("net: airoha: Fix npu rx DMA definitions") Signed-off-by: Christian Marangi Acked-by: Lorenzo Bianconi Link: https://patch.msgid.link/20260518134530.3683-1-ansuelsmth@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/soc/airoha/airoha_offload.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/airoha/airoha_offload.h b/include/linux/soc/airoha/airoha_offload.h index d01ef4a6b3d7..7589fccfeef6 100644 --- a/include/linux/soc/airoha/airoha_offload.h +++ b/include/linux/soc/airoha/airoha_offload.h @@ -71,9 +71,9 @@ static inline void airoha_ppe_dev_check_skb(struct airoha_ppe_dev *dev, #define NPU_RX1_DESC_NUM 512 /* CTRL */ -#define NPU_RX_DMA_DESC_LAST_MASK BIT(27) -#define NPU_RX_DMA_DESC_LEN_MASK GENMASK(26, 14) -#define NPU_RX_DMA_DESC_CUR_LEN_MASK GENMASK(13, 1) +#define NPU_RX_DMA_DESC_LAST_MASK BIT(29) +#define NPU_RX_DMA_DESC_LEN_MASK GENMASK(28, 15) +#define NPU_RX_DMA_DESC_CUR_LEN_MASK GENMASK(14, 1) #define NPU_RX_DMA_DESC_DONE_MASK BIT(0) /* INFO */ #define NPU_RX_DMA_PKT_COUNT_MASK GENMASK(31, 29) -- cgit v1.2.3 From 215c90ee656114f5e8c32408228d97082f8e0eef Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 6 May 2026 13:57:00 +0200 Subject: device property: set fwnode->secondary to NULL in fwnode_init() If a firmware node is allocated on the stack (for instance: temporary software node whose life-time we control) or on the heap - but using a non-zeroing allocation function - and initialized using fwnode_init(), its secondary pointer will contain uninitalized memory which likely will be neither NULL nor IS_ERR() and so may end up being dereferenced (for example: in dev_to_swnode()). Set fwnode->secondary to NULL on initialization. Cc: stable Fixes: 01bb86b380a3 ("driver core: Add fwnode_init()") Signed-off-by: Bartosz Golaszewski Reviewed-by: Rafael J. Wysocki (Intel) Reviewed-by: Andy Shevchenko Reviewed-by: Sakari Ailus Link: https://patch.msgid.link/20260506115701.23035-1-bartosz.golaszewski@oss.qualcomm.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fwnode.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 80b38fbf2121..31df7608737e 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -208,6 +208,7 @@ struct fwnode_operations { static inline void fwnode_init(struct fwnode_handle *fwnode, const struct fwnode_operations *ops) { + fwnode->secondary = NULL; fwnode->ops = ops; INIT_LIST_HEAD(&fwnode->consumers); INIT_LIST_HEAD(&fwnode->suppliers); -- cgit v1.2.3