- Kernel - mailweb.openeuler.org

[PATCH OLK-6.6 0/2] net: Fix CVE-2026-45859
by superdcc97＠163.com 22 Jun '26

22 Jun '26

From: Dong Chenchen <dongchenchen2(a)huawei.com> Fix CVE-2026-45859 Florian Westphal (1): netfilter: nfnetlink_queue: do shared-unconfirmed check before segmentation Dong Chenchen (1): net: Fix kabi breakage of struct nf_queue_entry include/net/netfilter/nf_queue.h | 1 + net/netfilter/nfnetlink_queue.c | 122 +++++++++++++++++++------------ 2 files changed, 75 insertions(+), 48 deletions(-) -- 2.43.0

2 3

[PATCH OLK-6.6] perf: arm_pmuv3: Use BR_RETIRED for HW branch event if enabled
by Yushan Wang 22 Jun '26

22 Jun '26

From: Ilkka Koskinen <ilkka(a)os.amperecomputing.com> mainline inclusion from mainline-v6.12-rc1 commit 5967a19f1c2ffb530f5d4589ddc4b4afbb6c7bd4 category: feature bugzilla: https://atomgit.com/openeuler/kernel/issues/9455 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ----------------------------------------------- The PMU driver attempts to use PC_WRITE_RETIRED for the HW branch event, if enabled. However, PC_WRITE_RETIRED counts only taken branches, whereas BR_RETIRED counts also non-taken ones. Furthermore, perf uses HW branch event to calculate branch misses ratio, implying BR_RETIRED is the correct event to count. We keep PC_WRITE_RETIRED still as an option in case BR_RETIRED isn't implemented. Signed-off-by: Ilkka Koskinen <ilkka(a)os.amperecomputing.com> Signed-off-by: Yushan Wang <wangyushan12(a)huawei.com> Signed-off-by: Ying Jiang <jiangying44(a)h-partners.com> --- drivers/perf/arm_pmuv3.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c index 5d750678a70e..d112d904c8c9 100644 --- a/drivers/perf/arm_pmuv3.c +++ b/drivers/perf/arm_pmuv3.c @@ -1419,14 +1419,14 @@ static int __armv8_pmuv3_map_event_id(struct arm_pmu *armpmu, if (event->attr.type == PERF_TYPE_HARDWARE && event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) { - if (test_bit(ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED, - armpmu->pmceid_bitmap)) - return ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED; - if (test_bit(ARMV8_PMUV3_PERFCTR_BR_RETIRED, armpmu->pmceid_bitmap)) return ARMV8_PMUV3_PERFCTR_BR_RETIRED; + if (test_bit(ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED, + armpmu->pmceid_bitmap)) + return ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED; + return HW_OP_UNSUPPORTED; } -- 2.43.0

2 1

[PATCH OLK-6.6] netfilter: nf_tables: use list_del_rcu for netlink hooks
by superdcc97＠163.com 22 Jun '26

22 Jun '26

From: Florian Westphal <fw(a)strlen.de> mainline inclusion from mainline-v7.1-rc2 commit f3224ee463f8f6f6ced7dcdf6081add4f8128527 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/15588 CVE: CVE-2026-46324 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- nft_netdev_unregister_hooks and __nft_unregister_flowtable_net_hooks need to use list_del_rcu(), this list can be walked by concurrent dumpers. Add a new helper and use it consistently. Fixes: f9a43007d3f7 ("netfilter: nf_tables: double hook unregistration in netns path") Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Conflicts: net/netfilter/nf_tables_api.c [commit 73319a8ee18b ("netfilter: nf_tables: Have a list of nf_hook_ops in nft_hook") introduced the ops_list structure and __nft_netdev_hook_free_rcu() helper which are not present in OLK-6.6. Adapted to use the single hook->ops and existing kfree_rcu()-based nft_netdev_hook_free_rcu() helper instead.] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/netfilter/nf_tables_api.c | 38 +++++++++++++++-------------------- 1 file changed, 16 insertions(+), 22 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 919be34ac7a0..8602dc3dfe08 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -333,6 +333,12 @@ static void nft_netdev_hook_free_rcu(struct nft_hook *hook) kfree_rcu(hook, rcu); } +static void nft_netdev_hook_unlink_free_rcu(struct nft_hook *hook) +{ + list_del_rcu(&hook->list); + nft_netdev_hook_free_rcu(hook); +} + static void nft_netdev_unregister_hooks(struct net *net, struct list_head *hook_list, bool release_netdev) @@ -341,10 +347,8 @@ static void nft_netdev_unregister_hooks(struct net *net, list_for_each_entry_safe(hook, next, hook_list, list) { nf_unregister_net_hook(net, &hook->ops); - if (release_netdev) { - list_del(&hook->list); - nft_netdev_hook_free_rcu(hook); - } + if (release_netdev) + nft_netdev_hook_unlink_free_rcu(hook); } } @@ -2106,10 +2110,8 @@ void nf_tables_chain_destroy(struct nft_chain *chain) if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) { list_for_each_entry_safe(hook, next, - &basechain->hook_list, list) { - list_del_rcu(&hook->list); - nft_netdev_hook_free_rcu(hook); - } + &basechain->hook_list, list) + nft_netdev_hook_unlink_free_rcu(hook); } module_put(basechain->type->owner); if (rcu_access_pointer(basechain->stats)) { @@ -2784,6 +2786,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, list_for_each_entry_safe(h, next, &hook.list, list) { if (unregister) nf_unregister_net_hook(ctx->net, &h->ops); + /* hook.list is on stack, no need for list_del_rcu() */ list_del(&h->list); nft_netdev_hook_free_rcu(h); } @@ -8495,10 +8498,8 @@ static void __nft_unregister_flowtable_net_hooks(struct net *net, nf_unregister_net_hook(net, &hook->ops); flowtable->data.type->setup(&flowtable->data, hook->ops.dev, FLOW_BLOCK_UNBIND); - if (release_netdev) { - list_del(&hook->list); - nft_netdev_hook_free_rcu(hook); - } + if (release_netdev) + nft_netdev_hook_unlink_free_rcu(hook); } } @@ -8557,8 +8558,7 @@ static int nft_register_flowtable_net_hooks(struct net *net, break; nft_unregister_flowtable_hook(net, flowtable, hook); - list_del_rcu(&hook->list); - nft_netdev_hook_free_rcu(hook); + nft_netdev_hook_unlink_free_rcu(hook); } return err; @@ -8655,8 +8655,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, list_for_each_entry_safe(hook, next, &flowtable_hook.list, list) { if (unregister) nft_unregister_flowtable_hook(ctx->net, flowtable, hook); - list_del_rcu(&hook->list); - nft_netdev_hook_free_rcu(hook); + nft_netdev_hook_unlink_free_rcu(hook); } return err; @@ -9149,13 +9148,8 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) { - struct nft_hook *hook, *next; - flowtable->data.type->free(&flowtable->data); - list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { - list_del_rcu(&hook->list); - nft_netdev_hook_free_rcu(hook); - } + nft_hooks_destroy(&flowtable->hook_list); kfree(flowtable->name); module_put(flowtable->data.type->owner); kfree(flowtable); -- 2.43.0

2 1

[PATCH OLK-5.10] ext4: don't cache extent during splitting extent
by Long Li 18 Jun '26

18 Jun '26

From: Zhang Yi <yi.zhang(a)huawei.com> stable inclusion from stable-v5.10.251 commit 8302b5b4aacdbb378f7b1216bb2ee782b5142415 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/15152 CVE: CVE-2026-45912 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… -------------------------------- commit 8b4b19a2f96348d70bfa306ef7d4a13b0bcbea79 upstream. Caching extents during the splitting process is risky, as it may result in stale extents remaining in the status tree. Moreover, in most cases, the corresponding extent block entries are likely already cached before the split happens, making caching here not particularly useful. Assume we have an unwritten extent, and then DIO writes the first half. [UUUUUUUUUUUUUUUU] on-disk extent U: unwritten extent [UUUUUUUUUUUUUUUU] extent status tree |<- ->| ----> dio write this range First, when ext4_split_extent_at() splits this extent, it truncates the existing extent and then inserts a new one. During this process, this extent status entry may be shrunk, and calls to ext4_find_extent() and ext4_cache_extents() may occur, which could potentially insert the truncated range as a hole into the extent status tree. After the split is completed, this hole is not replaced with the correct status. [UUUUUUU|UUUUUUUU] on-disk extent U: unwritten extent [UUUUUUU|HHHHHHHH] extent status tree H: hole Then, the outer calling functions will not correct this remaining hole extent either. Finally, if we perform a delayed buffer write on this latter part, it will re-insert the delayed extent and cause an error in space accounting. In adition, if the unwritten extent cache is not shrunk during the splitting, ext4_cache_extents() also conflicts with existing extents when caching extents. In the future, we will add checks when caching extents, which will trigger a warning. Therefore, Do not cache extents that are being split. Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: Ojaswin Mujoo <ojaswin(a)linux.ibm.com> Reviewed-by: Baokun Li <libaokun1(a)huawei.com> Cc: stable(a)kernel.org Message-ID: <20251129103247.686136-6-yi.zhang(a)huaweicloud.com> Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Long Li <leo.lilong(a)huawei.com> --- fs/ext4/extents.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 89a43a8fa808..ac260a66b4d9 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3214,6 +3214,9 @@ static int ext4_split_extent_at(handle_t *handle, BUG_ON((split_flag & (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)) == (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)); + /* Do not cache extents that are in the process of being modified. */ + flags |= EXT4_EX_NOCACHE; + ext_debug(inode, "logical block %llu\n", (unsigned long long)split); ext4_ext_show_leaf(inode, path); @@ -3389,6 +3392,9 @@ static int ext4_split_extent(handle_t *handle, ee_len = ext4_ext_get_actual_len(ex); unwritten = ext4_ext_is_unwritten(ex); + /* Do not cache extents that are in the process of being modified. */ + flags |= EXT4_EX_NOCACHE; + if (map->m_lblk + map->m_len < ee_block + ee_len) { split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT; flags1 = flags | EXT4_GET_BLOCKS_PRE_IO; -- 2.52.0

2 1

[PATCH OLK-6.6] xfs: remove xfs_attr_leaf_hasname
by Long Li 18 Jun '26

18 Jun '26

From: Christoph Hellwig <hch(a)lst.de> mainline inclusion from mainline-v6.19-rc6 commit 3a65ea768b8094e4699e72f9ab420eb9e0f3f568 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/14700 CVE: CVE-2026-43153 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- mainline inclusion from mainline-v6.17-rc7 commit 3a65ea768b8094e4699e72f9ab420eb9e0f3f568 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/14700 CVE: CVE-2026-43153 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- The calling convention of xfs_attr_leaf_hasname() is problematic, because it returns a NULL buffer when xfs_attr3_leaf_read fails, a valid buffer when xfs_attr3_leaf_lookup_int returns -ENOATTR or -EEXIST, and a non-NULL buffer pointer for an already released buffer when xfs_attr3_leaf_lookup_int fails with other error values. Fix this by simply open coding xfs_attr_leaf_hasname in the callers, so that the buffer release code is done by each caller of xfs_attr3_leaf_read. Cc: stable(a)vger.kernel.org # v5.19+ Fixes: 07120f1abdff ("xfs: Add xfs_has_attr and subroutines") Reported-by: Mark Tinguely <mark.tinguely(a)oracle.com> Signed-off-by: Christoph Hellwig <hch(a)lst.de> Reviewed-by: Darrick J. Wong <djwong(a)kernel.org> Signed-off-by: Carlos Maiolino <cem(a)kernel.org> Conflicts: fs/xfs/libxfs/xfs_attr.c [Context conflicts] Signed-off-by: Long Li <leo.lilong(a)huawei.com> --- fs/xfs/libxfs/xfs_attr.c | 75 +++++++++++++--------------------------- 1 file changed, 24 insertions(+), 51 deletions(-) diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index 33edf047e0ad..1a2e69d89113 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -49,7 +49,6 @@ STATIC int xfs_attr_shortform_addname(xfs_da_args_t *args); */ STATIC int xfs_attr_leaf_get(xfs_da_args_t *args); STATIC int xfs_attr_leaf_removename(xfs_da_args_t *args); -STATIC int xfs_attr_leaf_hasname(struct xfs_da_args *args, struct xfs_buf **bp); STATIC int xfs_attr_leaf_try_add(struct xfs_da_args *args); /* @@ -866,11 +865,12 @@ xfs_attr_lookup( return xfs_attr_sf_findname(args, NULL, NULL); if (xfs_attr_is_leaf(dp)) { - error = xfs_attr_leaf_hasname(args, &bp); - - if (bp) - xfs_trans_brelse(args->trans, bp); - + error = xfs_attr3_leaf_read(args->trans, args->dp, + 0, &bp); + if (error) + return error; + error = xfs_attr3_leaf_lookup_int(bp, args); + xfs_trans_brelse(args->trans, bp); return error; } @@ -1246,27 +1246,6 @@ xfs_attr_leaf_try_add( return error; } -/* - * Return EEXIST if attr is found, or ENOATTR if not - */ -STATIC int -xfs_attr_leaf_hasname( - struct xfs_da_args *args, - struct xfs_buf **bp) -{ - int error = 0; - - error = xfs_attr3_leaf_read(args->trans, args->dp, 0, bp); - if (error) - return error; - - error = xfs_attr3_leaf_lookup_int(*bp, args); - if (error != -ENOATTR && error != -EEXIST) - xfs_trans_brelse(args->trans, *bp); - - return error; -} - /* * Remove a name from the leaf attribute list structure * @@ -1277,25 +1256,22 @@ STATIC int xfs_attr_leaf_removename( struct xfs_da_args *args) { - struct xfs_inode *dp; - struct xfs_buf *bp; + struct xfs_inode *dp = args->dp; int error, forkoff; + struct xfs_buf *bp; trace_xfs_attr_leaf_removename(args); - /* - * Remove the attribute. - */ - dp = args->dp; - - error = xfs_attr_leaf_hasname(args, &bp); - if (error == -ENOATTR) { + error = xfs_attr3_leaf_read(args->trans, args->dp, 0, &bp); + if (error) + return error; + error = xfs_attr3_leaf_lookup_int(bp, args); + if (error != -EEXIST) { xfs_trans_brelse(args->trans, bp); - if (args->op_flags & XFS_DA_OP_RECOVERY) + if (error == -ENOATTR && (args->op_flags & XFS_DA_OP_RECOVERY)) return 0; return error; - } else if (error != -EEXIST) - return error; + } xfs_attr3_leaf_remove(bp, args); @@ -1319,23 +1295,20 @@ xfs_attr_leaf_removename( * Returns 0 on successful retrieval, otherwise an error. */ STATIC int -xfs_attr_leaf_get(xfs_da_args_t *args) +xfs_attr_leaf_get( + struct xfs_da_args *args) { - struct xfs_buf *bp; - int error; + struct xfs_buf *bp; + int error; trace_xfs_attr_leaf_get(args); - error = xfs_attr_leaf_hasname(args, &bp); - - if (error == -ENOATTR) { - xfs_trans_brelse(args->trans, bp); + error = xfs_attr3_leaf_read(args->trans, args->dp, 0, &bp); + if (error) return error; - } else if (error != -EEXIST) - return error; - - - error = xfs_attr3_leaf_getvalue(bp, args); + error = xfs_attr3_leaf_lookup_int(bp, args); + if (error == -EEXIST) + error = xfs_attr3_leaf_getvalue(bp, args); xfs_trans_brelse(args->trans, bp); return error; } -- 2.52.0

2 1

[PATCH OLK-5.10] hfs: validate record offset in hfsplus_bmap_alloc
by Jinjiang Tu 18 Jun '26

18 Jun '26

From: Yang Chenzhi <yang.chenzhi(a)vivo.com> stable inclusion from stable-v5.10.246 commit 40dfe7a4215a1f20842561ffaf5a6f83a987e75b category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/11616 CVE: CVE-2025-40349 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 738d5a51864ed8d7a68600b8c0c63fe6fe5c4f20 ] hfsplus_bmap_alloc can trigger a crash if a record offset or length is larger than node_size [ 15.264282] BUG: KASAN: slab-out-of-bounds in hfsplus_bmap_alloc+0x887/0x8b0 [ 15.265192] Read of size 8 at addr ffff8881085ca188 by task test/183 [ 15.265949] [ 15.266163] CPU: 0 UID: 0 PID: 183 Comm: test Not tainted 6.17.0-rc2-gc17b750b3ad9 #14 PREEMPT(voluntary) [ 15.266165] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 15.266167] Call Trace: [ 15.266168] <TASK> [ 15.266169] dump_stack_lvl+0x53/0x70 [ 15.266173] print_report+0xd0/0x660 [ 15.266181] kasan_report+0xce/0x100 [ 15.266185] hfsplus_bmap_alloc+0x887/0x8b0 [ 15.266208] hfs_btree_inc_height.isra.0+0xd5/0x7c0 [ 15.266217] hfsplus_brec_insert+0x870/0xb00 [ 15.266222] __hfsplus_ext_write_extent+0x428/0x570 [ 15.266225] __hfsplus_ext_cache_extent+0x5e/0x910 [ 15.266227] hfsplus_ext_read_extent+0x1b2/0x200 [ 15.266233] hfsplus_file_extend+0x5a7/0x1000 [ 15.266237] hfsplus_get_block+0x12b/0x8c0 [ 15.266238] __block_write_begin_int+0x36b/0x12c0 [ 15.266251] block_write_begin+0x77/0x110 [ 15.266252] cont_write_begin+0x428/0x720 [ 15.266259] hfsplus_write_begin+0x51/0x100 [ 15.266262] cont_write_begin+0x272/0x720 [ 15.266270] hfsplus_write_begin+0x51/0x100 [ 15.266274] generic_perform_write+0x321/0x750 [ 15.266285] generic_file_write_iter+0xc3/0x310 [ 15.266289] __kernel_write_iter+0x2fd/0x800 [ 15.266296] dump_user_range+0x2ea/0x910 [ 15.266301] elf_core_dump+0x2a94/0x2ed0 [ 15.266320] vfs_coredump+0x1d85/0x45e0 [ 15.266349] get_signal+0x12e3/0x1990 [ 15.266357] arch_do_signal_or_restart+0x89/0x580 [ 15.266362] irqentry_exit_to_user_mode+0xab/0x110 [ 15.266364] asm_exc_page_fault+0x26/0x30 [ 15.266366] RIP: 0033:0x41bd35 [ 15.266367] Code: bc d1 f3 0f 7f 27 f3 0f 7f 6f 10 f3 0f 7f 77 20 f3 0f 7f 7f 30 49 83 c0 0f 49 29 d0 48 8d 7c 17 31 e9 9f 0b 00 00 66 0f ef c0 <f3> 0f 6f 0e f3 0f 6f 56 10 66 0f 74 c1 66 0f d7 d0 49 83 f8f [ 15.266369] RSP: 002b:00007ffc9e62d078 EFLAGS: 00010283 [ 15.266371] RAX: 00007ffc9e62d100 RBX: 0000000000000000 RCX: 0000000000000000 [ 15.266372] RDX: 00000000000000e0 RSI: 0000000000000000 RDI: 00007ffc9e62d100 [ 15.266373] RBP: 0000400000000040 R08: 00000000000000e0 R09: 0000000000000000 [ 15.266374] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 [ 15.266375] R13: 0000000000000000 R14: 0000000000000000 R15: 0000400000000000 [ 15.266376] </TASK> When calling hfsplus_bmap_alloc to allocate a free node, this function first retrieves the bitmap from header node and map node using node->page together with the offset and length from hfs_brec_lenoff ``` len = hfs_brec_lenoff(node, 2, &off16); off = off16; off += node->page_offset; pagep = node->page + (off >> PAGE_SHIFT); data = kmap_local_page(*pagep); ``` However, if the retrieved offset or length is invalid(i.e. exceeds node_size), the code may end up accessing pages outside the allocated range for this node. This patch adds proper validation of both offset and length before use, preventing out-of-bounds page access. Move is_bnode_offset_valid and check_and_correct_requested_length to hfsplus_fs.h, as they may be required by other functions. Reported-by: syzbot+356aed408415a56543cd(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/67bcb4a6.050a0220.bbfd1.008f.GAE@google.com/ Signed-off-by: Yang Chenzhi <yang.chenzhi(a)vivo.com> Reviewed-by: Viacheslav Dubeyko <slava(a)dubeyko.com> Signed-off-by: Viacheslav Dubeyko <slava(a)dubeyko.com> Link: https://lore.kernel.org/r/20250818141734.8559-2-yang.chenzhi@vivo.com Signed-off-by: Viacheslav Dubeyko <slava(a)dubeyko.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: fs/hfsplus/hfsplus_fs.h [Context conflicts.] Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- fs/hfsplus/bnode.c | 41 ---------------------------------------- fs/hfsplus/btree.c | 6 ++++++ fs/hfsplus/hfsplus_fs.h | 42 +++++++++++++++++++++++++++++++++++++++++ 3 files changed, 48 insertions(+), 41 deletions(-) diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c index c9c38fddf505..e566cea23827 100644 --- a/fs/hfsplus/bnode.c +++ b/fs/hfsplus/bnode.c @@ -18,47 +18,6 @@ #include "hfsplus_fs.h" #include "hfsplus_raw.h" -static inline -bool is_bnode_offset_valid(struct hfs_bnode *node, int off) -{ - bool is_valid = off < node->tree->node_size; - - if (!is_valid) { - pr_err("requested invalid offset: " - "NODE: id %u, type %#x, height %u, " - "node_size %u, offset %d\n", - node->this, node->type, node->height, - node->tree->node_size, off); - } - - return is_valid; -} - -static inline -int check_and_correct_requested_length(struct hfs_bnode *node, int off, int len) -{ - unsigned int node_size; - - if (!is_bnode_offset_valid(node, off)) - return 0; - - node_size = node->tree->node_size; - - if ((off + len) > node_size) { - int new_len = (int)node_size - off; - - pr_err("requested length has been corrected: " - "NODE: id %u, type %#x, height %u, " - "node_size %u, offset %d, " - "requested_len %d, corrected_len %d\n", - node->this, node->type, node->height, - node->tree->node_size, off, len, new_len); - - return new_len; - } - - return len; -} /* Copy a specified range of bytes from the raw data of a node */ void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len) diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c index 66774f4cb4fd..2211907537fe 100644 --- a/fs/hfsplus/btree.c +++ b/fs/hfsplus/btree.c @@ -392,6 +392,12 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) len = hfs_brec_lenoff(node, 2, &off16); off = off16; + if (!is_bnode_offset_valid(node, off)) { + hfs_bnode_put(node); + return ERR_PTR(-EIO); + } + len = check_and_correct_requested_length(node, off, len); + off += node->page_offset; pagep = node->page + (off >> PAGE_SHIFT); data = kmap(*pagep); diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index daf5a828eaaf..ff43287ba29a 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -562,6 +562,48 @@ static inline __be32 __hfsp_ut2mt(time64_t ut) return cpu_to_be32(lower_32_bits(ut) + HFSPLUS_UTC_OFFSET); } +static inline +bool is_bnode_offset_valid(struct hfs_bnode *node, int off) +{ + bool is_valid = off < node->tree->node_size; + + if (!is_valid) { + pr_err("requested invalid offset: " + "NODE: id %u, type %#x, height %u, " + "node_size %u, offset %d\n", + node->this, node->type, node->height, + node->tree->node_size, off); + } + + return is_valid; +} + +static inline +int check_and_correct_requested_length(struct hfs_bnode *node, int off, int len) +{ + unsigned int node_size; + + if (!is_bnode_offset_valid(node, off)) + return 0; + + node_size = node->tree->node_size; + + if ((off + len) > node_size) { + int new_len = (int)node_size - off; + + pr_err("requested length has been corrected: " + "NODE: id %u, type %#x, height %u, " + "node_size %u, offset %d, " + "requested_len %d, corrected_len %d\n", + node->this, node->type, node->height, + node->tree->node_size, off, len, new_len); + + return new_len; + } + + return len; +} + /* compatibility */ #define hfsp_mt2ut(t) (struct timespec64){ .tv_sec = __hfsp_mt2ut(t) } #define hfsp_ut2mt(t) __hfsp_ut2mt((t).tv_sec) -- 2.43.0

2 1

[PATCH OLK-5.10] libceph: make decode_pool() more resilient against corrupted osdmaps
by Jinjiang Tu 18 Jun '26

18 Jun '26

From: Ilya Dryomov <idryomov(a)gmail.com> stable inclusion from stable-v5.10.248 commit d061be4c8040ffb1110d537654a038b8b6ad39d2 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13431 CVE: CVE-2025-71116 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 8c738512714e8c0aa18f8a10c072d5b01c83db39 upstream. If the osdmap is (maliciously) corrupted such that the encoded length of ceph_pg_pool envelope is less than what is expected for a particular encoding version, out-of-bounds reads may ensue because the only bounds check that is there is based on that length value. This patch adds explicit bounds checks for each field that is decoded or skipped. Cc: stable(a)vger.kernel.org Reported-by: ziming zhang <ezrakiez(a)gmail.com> Signed-off-by: Ilya Dryomov <idryomov(a)gmail.com> Reviewed-by: Xiubo Li <xiubli(a)redhat.com> Tested-by: ziming zhang <ezrakiez(a)gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Lin Yujun <linyujun809(a)h-partners.com> Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- net/ceph/osdmap.c | 116 +++++++++++++++++++++------------------------- 1 file changed, 52 insertions(+), 64 deletions(-) diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index fe6de7d72752..fe796775e3e9 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -790,51 +790,49 @@ static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) ceph_decode_need(p, end, len, bad); pool_end = *p + len; + ceph_decode_need(p, end, 4 + 4 + 4, bad); pi->type = ceph_decode_8(p); pi->size = ceph_decode_8(p); pi->crush_ruleset = ceph_decode_8(p); pi->object_hash = ceph_decode_8(p); - pi->pg_num = ceph_decode_32(p); pi->pgp_num = ceph_decode_32(p); - *p += 4 + 4; /* skip lpg* */ - *p += 4; /* skip last_change */ - *p += 8 + 4; /* skip snap_seq, snap_epoch */ + /* lpg*, last_change, snap_seq, snap_epoch */ + ceph_decode_skip_n(p, end, 8 + 4 + 8 + 4, bad); /* skip snaps */ - num = ceph_decode_32(p); + ceph_decode_32_safe(p, end, num, bad); while (num--) { - *p += 8; /* snapid key */ - *p += 1 + 1; /* versions */ - len = ceph_decode_32(p); - *p += len; + /* snapid key, pool snap (with versions) */ + ceph_decode_skip_n(p, end, 8 + 2, bad); + ceph_decode_skip_string(p, end, bad); } - /* skip removed_snaps */ - num = ceph_decode_32(p); - *p += num * (8 + 8); + /* removed_snaps */ + ceph_decode_skip_map(p, end, 64, 64, bad); + ceph_decode_need(p, end, 8 + 8 + 4, bad); *p += 8; /* skip auid */ pi->flags = ceph_decode_64(p); *p += 4; /* skip crash_replay_interval */ if (ev >= 7) - pi->min_size = ceph_decode_8(p); + ceph_decode_8_safe(p, end, pi->min_size, bad); else pi->min_size = pi->size - pi->size / 2; if (ev >= 8) - *p += 8 + 8; /* skip quota_max_* */ + /* quota_max_* */ + ceph_decode_skip_n(p, end, 8 + 8, bad); if (ev >= 9) { - /* skip tiers */ - num = ceph_decode_32(p); - *p += num * 8; + /* tiers */ + ceph_decode_skip_set(p, end, 64, bad); + ceph_decode_need(p, end, 8 + 1 + 8 + 8, bad); *p += 8; /* skip tier_of */ *p += 1; /* skip cache_mode */ - pi->read_tier = ceph_decode_64(p); pi->write_tier = ceph_decode_64(p); } else { @@ -842,86 +840,76 @@ static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) pi->write_tier = -1; } - if (ev >= 10) { - /* skip properties */ - num = ceph_decode_32(p); - while (num--) { - len = ceph_decode_32(p); - *p += len; /* key */ - len = ceph_decode_32(p); - *p += len; /* val */ - } - } + if (ev >= 10) + /* properties */ + ceph_decode_skip_map(p, end, string, string, bad); if (ev >= 11) { - /* skip hit_set_params */ - *p += 1 + 1; /* versions */ - len = ceph_decode_32(p); - *p += len; + /* hit_set_params (with versions) */ + ceph_decode_skip_n(p, end, 2, bad); + ceph_decode_skip_string(p, end, bad); - *p += 4; /* skip hit_set_period */ - *p += 4; /* skip hit_set_count */ + /* hit_set_period, hit_set_count */ + ceph_decode_skip_n(p, end, 4 + 4, bad); } if (ev >= 12) - *p += 4; /* skip stripe_width */ + /* stripe_width */ + ceph_decode_skip_32(p, end, bad); - if (ev >= 13) { - *p += 8; /* skip target_max_bytes */ - *p += 8; /* skip target_max_objects */ - *p += 4; /* skip cache_target_dirty_ratio_micro */ - *p += 4; /* skip cache_target_full_ratio_micro */ - *p += 4; /* skip cache_min_flush_age */ - *p += 4; /* skip cache_min_evict_age */ - } + if (ev >= 13) + /* target_max_*, cache_target_*, cache_min_* */ + ceph_decode_skip_n(p, end, 16 + 8 + 8, bad); - if (ev >= 14) { - /* skip erasure_code_profile */ - len = ceph_decode_32(p); - *p += len; - } + if (ev >= 14) + /* erasure_code_profile */ + ceph_decode_skip_string(p, end, bad); /* * last_force_op_resend_preluminous, will be overridden if the * map was encoded with RESEND_ON_SPLIT */ if (ev >= 15) - pi->last_force_request_resend = ceph_decode_32(p); + ceph_decode_32_safe(p, end, pi->last_force_request_resend, bad); else pi->last_force_request_resend = 0; if (ev >= 16) - *p += 4; /* skip min_read_recency_for_promote */ + /* min_read_recency_for_promote */ + ceph_decode_skip_32(p, end, bad); if (ev >= 17) - *p += 8; /* skip expected_num_objects */ + /* expected_num_objects */ + ceph_decode_skip_64(p, end, bad); if (ev >= 19) - *p += 4; /* skip cache_target_dirty_high_ratio_micro */ + /* cache_target_dirty_high_ratio_micro */ + ceph_decode_skip_32(p, end, bad); if (ev >= 20) - *p += 4; /* skip min_write_recency_for_promote */ + /* min_write_recency_for_promote */ + ceph_decode_skip_32(p, end, bad); if (ev >= 21) - *p += 1; /* skip use_gmt_hitset */ + /* use_gmt_hitset */ + ceph_decode_skip_8(p, end, bad); if (ev >= 22) - *p += 1; /* skip fast_read */ + /* fast_read */ + ceph_decode_skip_8(p, end, bad); - if (ev >= 23) { - *p += 4; /* skip hit_set_grade_decay_rate */ - *p += 4; /* skip hit_set_search_last_n */ - } + if (ev >= 23) + /* hit_set_grade_decay_rate, hit_set_search_last_n */ + ceph_decode_skip_n(p, end, 4 + 4, bad); if (ev >= 24) { - /* skip opts */ - *p += 1 + 1; /* versions */ - len = ceph_decode_32(p); - *p += len; + /* opts (with versions) */ + ceph_decode_skip_n(p, end, 2, bad); + ceph_decode_skip_string(p, end, bad); } if (ev >= 25) - pi->last_force_request_resend = ceph_decode_32(p); + ceph_decode_32_safe(p, end, pi->last_force_request_resend, bad); /* ignore the rest */ -- 2.43.0

2 1

[PATCH OLK-5.10] xfs: fix freemap adjustments when adding xattrs to leaf blocks
by Long Li 18 Jun '26

18 Jun '26

From: "Darrick J. Wong" <djwong(a)kernel.org> stable inclusion from stable-v5.10.251 commit d08976725355b9d54d8332fce223fa281cc304a5 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/14828 CVE: CVE-2026-43158 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… -------------------------------- [ Upstream commit 3eefc0c2b78444b64feeb3783c017d6adc3cd3ce ] xfs/592 and xfs/794 both trip this assertion in the leaf block freemap adjustment code after ~20 minutes of running on my test VMs: ASSERT(ichdr->firstused >= ichdr->count * sizeof(xfs_attr_leaf_entry_t) + xfs_attr3_leaf_hdr_size(leaf)); Upon enabling quite a lot more debugging code, I narrowed this down to fsstress trying to set a local extended attribute with namelen=3 and valuelen=71. This results in an entry size of 80 bytes. At the start of xfs_attr3_leaf_add_work, the freemap looks like this: i 0 base 448 size 0 rhs 448 count 46 i 1 base 388 size 132 rhs 448 count 46 i 2 base 2120 size 4 rhs 448 count 46 firstused = 520 where "rhs" is the first byte past the end of the leaf entry array. This is inconsistent -- the entries array ends at byte 448, but freemap[1] says there's free space starting at byte 388! By the end of the function, the freemap is in worse shape: i 0 base 456 size 0 rhs 456 count 47 i 1 base 388 size 52 rhs 456 count 47 i 2 base 2120 size 4 rhs 456 count 47 firstused = 440 Important note: 388 is not aligned with the entries array element size of 8 bytes. Based on the incorrect freemap, the name area starts at byte 440, which is below the end of the entries array! That's why the assertion triggers and the filesystem shuts down. How did we end up here? First, recall from the previous patch that the freemap array in an xattr leaf block is not intended to be a comprehensive map of all free space in the leaf block. In other words, it's perfectly legal to have a leaf block with: * 376 bytes in use by the entries array * freemap[0] has [base = 376, size = 8] * freemap[1] has [base = 388, size = 1500] * the space between 376 and 388 is free, but the freemap stopped tracking that some time ago If we add one xattr, the entries array grows to 384 bytes, and freemap[0] becomes [base = 384, size = 0]. So far, so good. But if we add a second xattr, the entries array grows to 392 bytes, and freemap[0] gets pushed up to [base = 392, size = 0]. This is bad, because freemap[1] hasn't been updated, and now the entries array and the free space claim the same space. The fix here is to adjust all freemap entries so that none of them collide with the entries array. Note that this fix relies on commit 2a2b5932db6758 ("xfs: fix attr leaf header freemap.size underflow") and the previous patch that resets zero length freemap entries to have base = 0. Cc: <stable(a)vger.kernel.org> # v2.6.12 Fixes: 1da177e4c3f415 ("Linux-2.6.12-rc2") Signed-off-by: "Darrick J. Wong" <djwong(a)kernel.org> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Lin Yujun <linyujun809(a)h-partners.com> Signed-off-by: Long Li <leo.lilong(a)huawei.com> --- fs/xfs/libxfs/xfs_attr_leaf.c | 36 +++++++++++++++++++++++++++-------- 1 file changed, 28 insertions(+), 8 deletions(-) diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 3954bf017c8d..3da4643b26cb 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -1472,6 +1472,7 @@ xfs_attr3_leaf_add_work( struct xfs_attr_leaf_name_local *name_loc; struct xfs_attr_leaf_name_remote *name_rmt; struct xfs_mount *mp; + int old_end, new_end; int tmp; int i; @@ -1563,17 +1564,36 @@ xfs_attr3_leaf_add_work( if (be16_to_cpu(entry->nameidx) < ichdr->firstused) ichdr->firstused = be16_to_cpu(entry->nameidx); - ASSERT(ichdr->firstused >= ichdr->count * sizeof(xfs_attr_leaf_entry_t) - + xfs_attr3_leaf_hdr_size(leaf)); - tmp = (ichdr->count - 1) * sizeof(xfs_attr_leaf_entry_t) - + xfs_attr3_leaf_hdr_size(leaf); + new_end = ichdr->count * sizeof(struct xfs_attr_leaf_entry) + + xfs_attr3_leaf_hdr_size(leaf); + old_end = new_end - sizeof(struct xfs_attr_leaf_entry); + + ASSERT(ichdr->firstused >= new_end); for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { - if (ichdr->freemap[i].base == tmp) { - ichdr->freemap[i].base += sizeof(xfs_attr_leaf_entry_t); + int diff = 0; + + if (ichdr->freemap[i].base == old_end) { + /* + * This freemap entry starts at the old end of the + * leaf entry array, so we need to adjust its base + * upward to accomodate the larger array. + */ + diff = sizeof(struct xfs_attr_leaf_entry); + } else if (ichdr->freemap[i].size > 0 && + ichdr->freemap[i].base < new_end) { + /* + * This freemap entry starts in the space claimed by + * the new leaf entry. Adjust its base upward to + * reflect that. + */ + diff = new_end - ichdr->freemap[i].base; + } + + if (diff) { + ichdr->freemap[i].base += diff; ichdr->freemap[i].size -= - min_t(uint16_t, ichdr->freemap[i].size, - sizeof(xfs_attr_leaf_entry_t)); + min_t(uint16_t, ichdr->freemap[i].size, diff); } /* -- 2.52.0

2 1

[PATCH OLK-6.6] nvmet-tcp: fix race between ICReq handling and queue teardown
by Long Li 18 Jun '26

18 Jun '26

From: Chaitanya Kulkarni <kch(a)nvidia.com> mainline inclusion from mainline-v7.0-rc3 commit 5293a8882c549fab4a878bc76b0b6c951f980a61 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/15382 CVE: CVE-2026-46135 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- nvmet_tcp_handle_icreq() updates queue->state after sending an Initialization Connection Response (ICResp), but it does so without serializing against target-side queue teardown. If an NVMe/TCP host sends an Initialization Connection Request (ICReq) and immediately closes the connection, target-side teardown may start in softirq context before io_work drains the already buffered ICReq. In that case, nvmet_tcp_schedule_release_queue() sets queue->state to NVMET_TCP_Q_DISCONNECTING and drops the queue reference under state_lock. If io_work later processes that ICReq, nvmet_tcp_handle_icreq() can still overwrite the state back to NVMET_TCP_Q_LIVE. That defeats the DISCONNECTING-state guard in nvmet_tcp_schedule_release_queue() and allows a later socket state change to re-enter teardown and issue a second kref_put() on an already released queue. The ICResp send failure path has the same problem. If teardown has already moved the queue to DISCONNECTING, a send error can still overwrite the state with NVMET_TCP_Q_FAILED, again reopening the window for a second teardown path to drop the queue reference. Fix this by serializing both post-send state transitions with state_lock and bailing out if teardown has already started. Use -ESHUTDOWN as an internal sentinel for that bail-out path rather than propagating it as a transport error like -ECONNRESET. Keep nvmet_tcp_socket_error() setting rcv_state to NVMET_TCP_RECV_ERR before honoring that sentinel so receive-side parsing stays quiesced until the existing release path completes. Fixes: c46a6465bac2 ("nvmet-tcp: add NVMe over TCP target driver") Cc: stable(a)vger.kernel.org Reported-by: Shivam Kumar <skumar47(a)syr.edu> Tested-by: Shivam Kumar <kumar.shivam43666(a)gmail.com> Signed-off-by: Chaitanya Kulkarni <kch(a)nvidia.com> Signed-off-by: Keith Busch <kbusch(a)kernel.org> Conflicts: drivers/nvme/target/tcp.c [not merge main commit 675b453e0241 ("nvmet-tcp: enable TLS handshake upcall")] Signed-off-by: Long Li <leo.lilong(a)huawei.com> --- drivers/nvme/target/tcp.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 5f85c4a812ab..6ec6912b2b47 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -389,6 +389,19 @@ static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue) static void nvmet_tcp_socket_error(struct nvmet_tcp_queue *queue, int status) { + /* + * Keep rcv_state at RECV_ERR even for the internal -ESHUTDOWN path. + * nvmet_tcp_handle_icreq() can return -ESHUTDOWN after the ICReq has + * already been consumed and queue teardown has started. + * + * If nvmet_tcp_data_ready() or nvmet_tcp_write_space() queues + * nvmet_tcp_io_work() again before nvmet_tcp_release_queue_work() + * cancels it, the queue must not keep that old receive state. + * Otherwise the next nvmet_tcp_io_work() run can reach + * nvmet_tcp_done_recv_pdu() and try to handle the same ICReq again. + * + * That is why queue->rcv_state needs to be updated before we return. + */ queue->rcv_state = NVMET_TCP_RECV_ERR; if (status == -EPIPE || status == -ECONNRESET) kernel_sock_shutdown(queue->sock, SHUT_RDWR); @@ -938,7 +951,14 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue) if (ret < 0) return ret; /* queue removal will cleanup */ + spin_lock_bh(&queue->state_lock); + if (queue->state == NVMET_TCP_Q_DISCONNECTING) { + spin_unlock_bh(&queue->state_lock); + /* Tell nvmet_tcp_socket_error() teardown is in progress. */ + return -ESHUTDOWN; + } queue->state = NVMET_TCP_Q_LIVE; + spin_unlock_bh(&queue->state_lock); nvmet_prepare_receive_pdu(queue); return 0; } -- 2.52.0

2 1

[PATCH OLK-5.10] nvmet-tcp: fix race between ICReq handling and queue teardown
by Long Li 18 Jun '26

18 Jun '26

From: Chaitanya Kulkarni <kch(a)nvidia.com> mainline inclusion from mainline-v7.0-rc3 commit 5293a8882c549fab4a878bc76b0b6c951f980a61 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/15382 CVE: CVE-2026-46135 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- nvmet_tcp_handle_icreq() updates queue->state after sending an Initialization Connection Response (ICResp), but it does so without serializing against target-side queue teardown. If an NVMe/TCP host sends an Initialization Connection Request (ICReq) and immediately closes the connection, target-side teardown may start in softirq context before io_work drains the already buffered ICReq. In that case, nvmet_tcp_schedule_release_queue() sets queue->state to NVMET_TCP_Q_DISCONNECTING and drops the queue reference under state_lock. If io_work later processes that ICReq, nvmet_tcp_handle_icreq() can still overwrite the state back to NVMET_TCP_Q_LIVE. That defeats the DISCONNECTING-state guard in nvmet_tcp_schedule_release_queue() and allows a later socket state change to re-enter teardown and issue a second kref_put() on an already released queue. The ICResp send failure path has the same problem. If teardown has already moved the queue to DISCONNECTING, a send error can still overwrite the state with NVMET_TCP_Q_FAILED, again reopening the window for a second teardown path to drop the queue reference. Fix this by serializing both post-send state transitions with state_lock and bailing out if teardown has already started. Use -ESHUTDOWN as an internal sentinel for that bail-out path rather than propagating it as a transport error like -ECONNRESET. Keep nvmet_tcp_socket_error() setting rcv_state to NVMET_TCP_RECV_ERR before honoring that sentinel so receive-side parsing stays quiesced until the existing release path completes. Fixes: c46a6465bac2 ("nvmet-tcp: add NVMe over TCP target driver") Cc: stable(a)vger.kernel.org Reported-by: Shivam Kumar <skumar47(a)syr.edu> Tested-by: Shivam Kumar <kumar.shivam43666(a)gmail.com> Signed-off-by: Chaitanya Kulkarni <kch(a)nvidia.com> Signed-off-by: Keith Busch <kbusch(a)kernel.org> Conflicts: drivers/nvme/target/tcp.c [not merge main commit 675b453e0241 ("nvmet-tcp: enable TLS handshake upcall")] Signed-off-by: Long Li <leo.lilong(a)huawei.com> --- drivers/nvme/target/tcp.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 6b506783ea4f..1f048ad19f6a 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -354,6 +354,19 @@ static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue) static void nvmet_tcp_socket_error(struct nvmet_tcp_queue *queue, int status) { + /* + * Keep rcv_state at RECV_ERR even for the internal -ESHUTDOWN path. + * nvmet_tcp_handle_icreq() can return -ESHUTDOWN after the ICReq has + * already been consumed and queue teardown has started. + * + * If nvmet_tcp_data_ready() or nvmet_tcp_write_space() queues + * nvmet_tcp_io_work() again before nvmet_tcp_release_queue_work() + * cancels it, the queue must not keep that old receive state. + * Otherwise the next nvmet_tcp_io_work() run can reach + * nvmet_tcp_done_recv_pdu() and try to handle the same ICReq again. + * + * That is why queue->rcv_state needs to be updated before we return. + */ queue->rcv_state = NVMET_TCP_RECV_ERR; if (status == -EPIPE || status == -ECONNRESET) kernel_sock_shutdown(queue->sock, SHUT_RDWR); @@ -890,7 +903,14 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue) if (ret < 0) return ret; /* queue removal will cleanup */ + spin_lock_bh(&queue->state_lock); + if (queue->state == NVMET_TCP_Q_DISCONNECTING) { + spin_unlock_bh(&queue->state_lock); + /* Tell nvmet_tcp_socket_error() teardown is in progress. */ + return -ESHUTDOWN; + } queue->state = NVMET_TCP_Q_LIVE; + spin_unlock_bh(&queue->state_lock); nvmet_prepare_receive_pdu(queue); return 0; } -- 2.52.0

2 1