From eb1bf0e60d63200a79a328ec82b17c5de818f10c Mon Sep 17 00:00:00 2001 From: Ibrahim Hashimov Date: Sun, 12 Jul 2026 14:17:20 +0200 Subject: [PATCH 01/76] RDMA/rxe: Fix responder UAF on IB_QP_MAX_DEST_RD_ATOMIC modify_qp [ Upstream commit 6f7014237405e7f032b5c53a82d9eccf6161c291 ] rxe_qp_from_attr() handles IB_QP_MAX_DEST_RD_ATOMIC outside the IB_QP_STATE path, so it holds no state_lock and runs while the responder task rxe_receiver() (recv_task on rxe_wq) is live. A modify_qp() setting only that attribute calls free_rd_atomic_resources() then alloc_rd_atomic_resources(), swapping qp->resp.resources[] while rxe_prepare_res()/find_resource() walk it; free_rd_atomic_resources() also leaves the cached pointer qp->resp.res dangling. A local unprivileged user can race the free/realloc into a use-after-free in rxe_receiver() (local DoS). Drain recv_task around the swap with rxe_disable_task()/rxe_enable_task(), as rxe_qp_reset() already does when tearing this array down, re-enabling only after alloc_rd_atomic_resources() succeeds so the responder never resumes against a NULL qp->resp.resources on the ENOMEM path. Also clear qp->resp.res in free_rd_atomic_resources(), like the rxe_resp.c completion paths. Reproduced under KASAN; the slab-use-after-free in rxe_receiver() is gone. Fixes: 8700e3e7c485 ("Soft RoCE driver") Reviewed-by: Zhu Yanjun Signed-off-by: Ibrahim Hashimov Link: https://patch.msgid.link/20260712121720.78001-1-security@auditcode.ai Assisted-by: AuditCode-AI:2026.07 Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin (cherry picked from commit ffa4f0be69656be1755090f02db38d49816585c6) Signed-off-by: Wentao Guan --- drivers/infiniband/sw/rxe/rxe_qp.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 95f1c1c2949de..0af697c6469db 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -124,6 +124,7 @@ static void free_rd_atomic_resources(struct rxe_qp *qp) } kfree(qp->resp.resources); qp->resp.resources = NULL; + qp->resp.res = NULL; } } @@ -660,11 +661,23 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, qp->attr.max_dest_rd_atomic = max_dest_rd_atomic; + /* + * Not gated by IB_QP_STATE, so the responder task is live. + * Quiesce recv_task like rxe_qp_reset() before swapping the + * rd_atomic array, so rxe_receiver() cannot race the free/ + * realloc. + */ + rxe_disable_task(&qp->recv_task); free_rd_atomic_resources(qp); - err = alloc_rd_atomic_resources(qp, max_dest_rd_atomic); + /* + * On ENOMEM leave recv_task quiesced: qp->resp.resources is + * NULL and rxe_prepare_res()/find_resource() would deref it. + * Re-enable only after a fresh array is installed. + */ if (err) return err; + rxe_enable_task(&qp->recv_task); } if (mask & IB_QP_EN_SQD_ASYNC_NOTIFY) From 6d124fb587a4c8d356823943d18d3e66caf19a07 Mon Sep 17 00:00:00 2001 From: Peiyang He Date: Thu, 30 Jul 2026 10:28:27 +0800 Subject: [PATCH 02/76] RDMA/rxe: Fix OOB in free_rd_atomic_resources() [ Upstream commit de329533792a373186d79dca1ca120f8fa0afd05 ] free_rd_atomic_resources() iterates using qp->attr.max_dest_rd_atomic. Updating max_dest_rd_atomic before freeing the old array can make the free path walk past the old allocation and trigger a slab out-of-bounds write catched by KASAN: ================================================================== BUG: KASAN: slab-out-of-bounds in free_rd_atomic_resource drivers/infiniband/sw/rxe/rxe_qp.c:180 [inline] BUG: KASAN: slab-out-of-bounds in free_rd_atomic_resources drivers/infiniband/sw/rxe/rxe_qp.c:171 [inline] BUG: KASAN: slab-out-of-bounds in free_rd_atomic_resources drivers/infiniband/sw/rxe/rxe_qp.c:163 [inline] BUG: KASAN: slab-out-of-bounds in rxe_qp_from_attr+0x1e88/0x2150 drivers/infiniband/sw/rxe/rxe_qp.c:712 Write of size 4 at addr ffff88802b8dddb8 by task syz.3.451/11063 CPU: 0 UID: 0 PID: 11063 Comm: syz.3.451 Not tainted 7.1.0 #2 PREEMPT(full) Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps fix, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x10e/0x1f0 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xf7/0x600 mm/kasan/report.c:482 kasan_report+0xe4/0x120 mm/kasan/report.c:595 free_rd_atomic_resource drivers/infiniband/sw/rxe/rxe_qp.c:180 [inline] free_rd_atomic_resources drivers/infiniband/sw/rxe/rxe_qp.c:171 [inline] free_rd_atomic_resources drivers/infiniband/sw/rxe/rxe_qp.c:163 [inline] rxe_qp_from_attr+0x1e88/0x2150 drivers/infiniband/sw/rxe/rxe_qp.c:712 rxe_modify_qp+0x1e2/0x530 drivers/infiniband/sw/rxe/rxe_verbs.c:623 ib_security_modify_qp+0x223/0xfa0 drivers/infiniband/core/security.c:625 _ib_modify_qp+0x333/0xec0 drivers/infiniband/core/verbs.c:1915 modify_qp+0x13ca/0x1940 drivers/infiniband/core/uverbs_cmd.c:1932 ib_uverbs_modify_qp+0xcb/0x120 drivers/infiniband/core/uverbs_cmd.c:1958 ib_uverbs_write+0xb86/0x1030 drivers/infiniband/core/uverbs_main.c:680 vfs_write+0x2aa/0x1070 fs/read_write.c:686 ksys_write+0x1f8/0x250 fs/read_write.c:740 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x116/0x800 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fefc75a70cd Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fefc8495018 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 00007fefc7835fa0 RCX: 00007fefc75a70cd RDX: 0000000000000078 RSI: 0000200000000240 RDI: 0000000000000007 RBP: 00007fefc764f10f R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fefc7836038 R14: 00007fefc7835fa0 R15: 00007ffcf0586aa0 Allocated by task 11063: kasan_save_stack+0x33/0x60 mm/kasan/common.c:57 kasan_save_track+0x14/0x30 mm/kasan/common.c:78 poison_kmalloc_redzone mm/kasan/common.c:398 [inline] __kasan_kmalloc+0xaa/0xb0 mm/kasan/common.c:415 kasan_kmalloc include/linux/kasan.h:263 [inline] __do_kmalloc_node mm/slub.c:5296 [inline] __kmalloc_noprof+0x32a/0x850 mm/slub.c:5308 kmalloc_noprof include/linux/slab.h:954 [inline] kzalloc_noprof include/linux/slab.h:1188 [inline] alloc_rd_atomic_resources drivers/infiniband/sw/rxe/rxe_qp.c:155 [inline] rxe_qp_from_attr+0x3f8/0x2150 drivers/infiniband/sw/rxe/rxe_qp.c:714 rxe_modify_qp+0x1e2/0x530 drivers/infiniband/sw/rxe/rxe_verbs.c:623 ib_security_modify_qp+0x223/0xfa0 drivers/infiniband/core/security.c:625 _ib_modify_qp+0x333/0xec0 drivers/infiniband/core/verbs.c:1915 modify_qp+0x13ca/0x1940 drivers/infiniband/core/uverbs_cmd.c:1932 ib_uverbs_modify_qp+0xcb/0x120 drivers/infiniband/core/uverbs_cmd.c:1958 ib_uverbs_write+0xb86/0x1030 drivers/infiniband/core/uverbs_main.c:680 vfs_write+0x2aa/0x1070 fs/read_write.c:686 ksys_write+0x1f8/0x250 fs/read_write.c:740 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x116/0x800 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f The buggy address belongs to the object at ffff88802b8ddd80 which belongs to the cache kmalloc-64 of size 64 The buggy address is located 0 bytes to the right of allocated 56-byte region [ffff88802b8ddd80, ffff88802b8dddb8) The buggy address belongs to the physical page: page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x2b8dd flags: 0xfff00000000000(node=0|zone=1|lastcpupid=0x7ff) page_type: f5(slab) raw: 00fff00000000000 ffff888015c418c0 dead000000000100 dead000000000122 raw: 0000000000000000 0000000800200020 00000000f5000000 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 0, migratetype Unmovable, gfp_mask 0xd2c40(GFP_NOFS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 4651, tgid 4651 ((udev-worker)), ts 123427165316, free_ts 123425874255 set_page_owner include/linux/page_owner.h:32 [inline] post_alloc_hook+0xfc/0x120 mm/page_alloc.c:1853 prep_new_page mm/page_alloc.c:1861 [inline] get_page_from_freelist+0x75b/0x3220 mm/page_alloc.c:3941 __alloc_frozen_pages_noprof+0x27e/0x2b00 mm/page_alloc.c:5221 alloc_slab_page mm/slub.c:3278 [inline] allocate_slab mm/slub.c:3467 [inline] new_slab+0xa6/0x670 mm/slub.c:3525 refill_objects+0x278/0x420 mm/slub.c:7272 refill_sheaf mm/slub.c:2816 [inline] __pcs_replace_empty_main+0x2ed/0x640 mm/slub.c:4652 alloc_from_pcs mm/slub.c:4750 [inline] slab_alloc_node mm/slub.c:4884 [inline] __do_kmalloc_node mm/slub.c:5295 [inline] __kmalloc_noprof+0x68d/0x850 mm/slub.c:5308 kmalloc_noprof include/linux/slab.h:954 [inline] kzalloc_noprof include/linux/slab.h:1188 [inline] tomoyo_encode2+0x100/0x3e0 security/tomoyo/realpath.c:45 tomoyo_encode+0x29/0x50 security/tomoyo/realpath.c:80 tomoyo_realpath_from_path+0x18c/0x690 security/tomoyo/realpath.c:283 tomoyo_get_realpath security/tomoyo/file.c:151 [inline] tomoyo_check_open_permission+0x2ab/0x3c0 security/tomoyo/file.c:776 tomoyo_file_open+0x6b/0x90 security/tomoyo/tomoyo.c:334 security_file_open+0x7a/0x1b0 security/security.c:2739 do_dentry_open+0x57e/0x1690 fs/open.c:924 vfs_open+0x82/0x3f0 fs/open.c:1079 do_open fs/namei.c:4699 [inline] path_openat+0x218a/0x3190 fs/namei.c:4858 page last free pid 1 tgid 1 stack trace: reset_page_owner include/linux/page_owner.h:25 [inline] __free_pages_prepare mm/page_alloc.c:1397 [inline] __free_frozen_pages+0x763/0xfc0 mm/page_alloc.c:2938 selinux_genfs_get_sid security/selinux/hooks.c:1364 [inline] inode_doinit_with_dentry+0x903/0x1320 security/selinux/hooks.c:1563 selinux_d_instantiate+0x26/0x30 security/selinux/hooks.c:6658 security_d_instantiate+0x123/0x190 security/security.c:3704 d_splice_alias_ops+0x92/0x850 fs/dcache.c:3141 kernfs_iop_lookup+0x23f/0x2d0 fs/kernfs/dir.c:1289 lookup_open.isra.0+0x659/0x1080 fs/namei.c:4484 open_last_lookups fs/namei.c:4611 [inline] path_openat+0x17dd/0x3190 fs/namei.c:4855 do_file_open+0x20c/0x430 fs/namei.c:4887 do_sys_openat2+0x101/0x1d0 fs/open.c:1364 do_sys_open fs/open.c:1370 [inline] __do_sys_openat fs/open.c:1386 [inline] __se_sys_openat fs/open.c:1381 [inline] __x64_sys_openat+0x141/0x200 fs/open.c:1381 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x116/0x800 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f Memory state around the buggy address: ffff88802b8ddc80: 00 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc ffff88802b8ddd00: fa fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc >ffff88802b8ddd80: 00 00 00 00 00 00 00 fc fc fc fc fc fc fc fc fc ^ ffff88802b8dde00: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc ffff88802b8dde80: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc Fix the OOB by moving the assignment after free_rd_atomic_resources() so the old array is freed using the old bound. This matches the original ordering in commit 8700e3e7c485 ("Soft RoCE driver"). Closes: https://lore.kernel.org/all/365C68B4923F8214+30195a67-0b90-4b92-ab96-2ce41517793c@smail.nju.edu.cn/ Fixes: b6bbee0d2438 ("IB/rxe: Properly honor max IRD value for rd/atomic.") Cc: stable@vger.kernel.org Signed-off-by: Peiyang He Reviewed-by: Zhu Yanjun Signed-off-by: Leon Romanovsky Signed-off-by: Sasha Levin (cherry picked from commit bdf5deccfbf9f556a08d1d2ef52e9e48f969e53e) Signed-off-by: Wentao Guan --- drivers/infiniband/sw/rxe/rxe_qp.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 0af697c6469db..c31c0c9a53828 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -659,8 +659,6 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, int max_dest_rd_atomic = attr->max_dest_rd_atomic ? roundup_pow_of_two(attr->max_dest_rd_atomic) : 0; - qp->attr.max_dest_rd_atomic = max_dest_rd_atomic; - /* * Not gated by IB_QP_STATE, so the responder task is live. * Quiesce recv_task like rxe_qp_reset() before swapping the @@ -669,6 +667,7 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, */ rxe_disable_task(&qp->recv_task); free_rd_atomic_resources(qp); + qp->attr.max_dest_rd_atomic = max_dest_rd_atomic; err = alloc_rd_atomic_resources(qp, max_dest_rd_atomic); /* * On ENOMEM leave recv_task quiesced: qp->resp.resources is From a3894b5511a88000e4ab6618d405fec024c56840 Mon Sep 17 00:00:00 2001 From: Jinu Kim Date: Tue, 21 Jul 2026 19:35:11 +0900 Subject: [PATCH 03/76] KVM: x86/mmu: Check write tracking in all address spaces [ Upstream commit 0f38453cdb2e17566ccb7c0f3dabd5bd21caca26 ] kvm_gfn_is_write_tracked() checks only the supplied memslot, but page tracking is per-address-space and shadow pages are shared across all address spaces. With SMM, a GFN can therefore be write-tracked in one address space and appear untracked through the other. Check the supplied slot first, then the slot for the other address space. This ensures all callers honor write tracking regardless of the active address space. In particular, it prevents mmu_try_to_unsync_pages() from marking an upper-level shadow page unsync and eventually triggering the BUG in pte_list_remove(). Fixes: 699023e23965 ("KVM: x86: add SMM to the MMU role, support SMRAM address space") Assisted-by: Codex:GPT-5 Signed-off-by: Jinu Kim Message-ID: <20260721103512.2136240-2-kimjw04271234@gmail.com> [invert direction of the conditional. - Paolo] Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin (cherry picked from commit c0a9bd5fca0b5f2dea32b0fc31350e71e8648112) Signed-off-by: Wentao Guan --- arch/x86/kvm/mmu/page_track.c | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 1b17b12393a8c..7e8195a311bb0 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -130,13 +130,23 @@ void __kvm_write_track_remove_gfn(struct kvm *kvm, kvm_mmu_gfn_allow_lpage(slot, gfn); } -/* - * check if the corresponding access on the specified guest page is tracked. - */ +static bool __kvm_gfn_is_write_tracked(const struct kvm_memory_slot *slot, + gfn_t gfn) +{ + int index; + + if (!slot) + return false; + + index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K); + return !!READ_ONCE(slot->arch.gfn_write_track[index]); +} + +/* check if write access is tracked on the specified guest page. */ bool kvm_gfn_is_write_tracked(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn) { - int index; + const struct kvm_memory_slot *other_slot; if (!slot) return false; @@ -144,8 +154,18 @@ bool kvm_gfn_is_write_tracked(struct kvm *kvm, if (!kvm_page_track_write_tracking_enabled(kvm)) return false; - index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K); - return !!READ_ONCE(slot->arch.gfn_write_track[index]); + BUILD_BUG_ON(KVM_MAX_NR_ADDRESS_SPACES > 2); + + if (__kvm_gfn_is_write_tracked(slot, gfn)) + return true; + + if (kvm_arch_nr_memslot_as_ids(kvm) > 1) { + other_slot = __gfn_to_memslot(__kvm_memslots(kvm, slot->as_id ^ 1), gfn); + if (__kvm_gfn_is_write_tracked(other_slot, gfn)) + return true; + } + + return false; } #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING From 5641a80bdc43cd6c6426f6c08c96b9c41cdf3396 Mon Sep 17 00:00:00 2001 From: Dmitry Bogdanov Date: Thu, 27 Aug 2026 15:20:22 -0700 Subject: [PATCH 04/76] nvme-tcp: fix usage of page_frag_cache commit 36ac05f7cfd59d90c597071304b14e98090d5dd1 upstream. nvme uses page_frag_cache to preallocate PDU for each preallocated request of block device. Block devices are created in parallel threads, consequently page_frag_cache is used in not thread-safe manner. That leads to incorrect refcounting of backstore pages and premature free. That can be catched by !sendpage_ok inside network stack: WARNING: CPU: 7 PID: 467 at ../net/core/skbuff.c:6931 skb_splice_from_iter+0xfa/0x310. tcp_sendmsg_locked+0x782/0xce0 tcp_sendmsg+0x27/0x40 sock_sendmsg+0x8b/0xa0 nvme_tcp_try_send_cmd_pdu+0x149/0x2a0 Then random panic may occur. Fix that by serializing the usage of page_frag_cache. Fixes: 4e893ca81170 ("nvme_core: scan namespaces asynchronously") Signed-off-by: Dmitry Bogdanov Signed-off-by: Daniel Wagner Signed-off-by: Keith Busch [carlos.bilbao: adjust context in nvme_tcp_free_queue; branch predates 19bdb70c77d3 ("nvme-tcp: lockdep: use dynamic lockdep keys per socket instance")] Signed-off-by: Carlos Bilbao (Lambda) Signed-off-by: Sasha Levin (cherry picked from commit 64561afb42d8390695bf810d9bbd087cbca00291) Signed-off-by: Wentao Guan --- drivers/nvme/host/tcp.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index afdbcff3d4821..04c074ae8f7bb 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -145,6 +145,7 @@ struct nvme_tcp_queue { struct mutex queue_lock; struct mutex send_mutex; + struct mutex pf_cache_lock; struct llist_head req_list; struct list_head send_list; @@ -556,9 +557,11 @@ static int nvme_tcp_init_request(struct blk_mq_tag_set *set, struct nvme_tcp_queue *queue = &ctrl->queues[queue_idx]; u8 hdgst = nvme_tcp_hdgst_len(queue); + mutex_lock(&queue->pf_cache_lock); req->pdu = page_frag_alloc(&queue->pf_cache, sizeof(struct nvme_tcp_cmd_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); + mutex_unlock(&queue->pf_cache_lock); if (!req->pdu) return -ENOMEM; @@ -1423,9 +1426,11 @@ static int nvme_tcp_alloc_async_req(struct nvme_tcp_ctrl *ctrl) struct nvme_tcp_request *async = &ctrl->async_req; u8 hdgst = nvme_tcp_hdgst_len(queue); + mutex_lock(&queue->pf_cache_lock); async->pdu = page_frag_alloc(&queue->pf_cache, sizeof(struct nvme_tcp_cmd_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); + mutex_unlock(&queue->pf_cache_lock); if (!async->pdu) return -ENOMEM; @@ -1453,6 +1458,7 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) kfree(queue->pdu); mutex_destroy(&queue->send_mutex); mutex_destroy(&queue->queue_lock); + mutex_destroy(&queue->pf_cache_lock); } static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue) @@ -1775,6 +1781,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid, INIT_LIST_HEAD(&queue->send_list); mutex_init(&queue->send_mutex); INIT_WORK(&queue->io_work, nvme_tcp_io_work); + mutex_init(&queue->pf_cache_lock); if (qid > 0) queue->cmnd_capsule_len = nctrl->ioccsz * 16; @@ -1906,6 +1913,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid, err_destroy_mutex: mutex_destroy(&queue->send_mutex); mutex_destroy(&queue->queue_lock); + mutex_destroy(&queue->pf_cache_lock); return ret; } From d75081e00664d7d4f722ea2812491be649dd68e4 Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Wed, 31 Dec 2025 22:04:16 +0200 Subject: [PATCH 05/76] ASoC: nau8821: Cancel delayed work on component remove [ Upstream commit dbd3fd05cddfdeec1e49b0a66269881c09eebd17 ] Attempting to unload the driver while a jack detection work is pending would likely crash the kernel when it is eventually scheduled for execution: [ 1984.896308] BUG: unable to handle page fault for address: ffffffffc10c2a20 [...] [ 1984.896388] Hardware name: Valve Jupiter/Jupiter, BIOS F7A0131 01/30/2024 [ 1984.896396] Workqueue: events nau8821_jdet_work [snd_soc_nau8821] [ 1984.896414] RIP: 0010:__mutex_lock+0x9f/0x11d0 [...] [ 1984.896504] Call Trace: [ 1984.896511] [ 1984.896524] ? snd_soc_dapm_disable_pin+0x26/0x60 [snd_soc_core] [ 1984.896572] ? snd_soc_dapm_disable_pin+0x26/0x60 [snd_soc_core] [ 1984.896596] snd_soc_dapm_disable_pin+0x26/0x60 [snd_soc_core] [ 1984.896622] nau8821_jdet_work+0xeb/0x1e0 [snd_soc_nau8821] [ 1984.896636] process_one_work+0x211/0x590 [ 1984.896649] ? srso_return_thunk+0x5/0x5f [ 1984.896670] worker_thread+0x1cd/0x3a0 Cancel unscheduled jdet_work or wait for its execution to finish before the component driver gets removed. Fixes: aab1ad11d69f ("ASoC: nau8821: new driver") Fixes: ee70bacef1c6 ("ASoC: nau8821: Avoid unnecessary blocking in IRQ handler") Signed-off-by: Cristian Ciocaltea Link: https://patch.msgid.link/20251231-nau8821-cleanup-v1-2-6b0b76cbbb64@collabora.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin (cherry picked from commit 13d20517bee1c9b69c7750026c61e7ec021080a4) Signed-off-by: Wentao Guan --- sound/soc/codecs/nau8821.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/sound/soc/codecs/nau8821.c b/sound/soc/codecs/nau8821.c index dfb9630bffe29..8228cd396b9b3 100644 --- a/sound/soc/codecs/nau8821.c +++ b/sound/soc/codecs/nau8821.c @@ -1269,6 +1269,14 @@ static int nau8821_component_probe(struct snd_soc_component *component) return 0; } +static void nau8821_component_remove(struct snd_soc_component *component) +{ + struct nau8821 *nau8821 = snd_soc_component_get_drvdata(component); + + if (nau8821->jdet_active) + cancel_delayed_work_sync(&nau8821->jdet_work); +}; + /** * nau8821_calc_fll_param - Calculate FLL parameters. * @fll_in: external clock provided to codec. @@ -1627,6 +1635,7 @@ static int __maybe_unused nau8821_resume(struct snd_soc_component *component) static const struct snd_soc_component_driver nau8821_component_driver = { .probe = nau8821_component_probe, + .remove = nau8821_component_remove, .set_sysclk = nau8821_set_sysclk, .set_pll = nau8821_set_fll, .set_bias_level = nau8821_set_bias_level, From 9985ba73a34464adc61c8995d1cd43b1aec703cc Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Thu, 9 Apr 2026 10:37:32 +0800 Subject: [PATCH 06/76] bpf: Fix use-after-free in offloaded map/prog info fill [ Upstream commit a0c584fc18056709c8e047a82a6045d6c209f4ce ] When querying info for an offloaded BPF map or program, bpf_map_offload_info_fill_ns() and bpf_prog_offload_info_fill_ns() obtain the network namespace with get_net(dev_net(offmap->netdev)). However, the associated netdev's netns may be racing with teardown during netns destruction. If the netns refcount has already reached 0, get_net() performs a refcount_t increment on 0, triggering: refcount_t: addition on 0; use-after-free. Although rtnl_lock and bpf_devs_lock ensure the netdev pointer remains valid, they cannot prevent the netns refcount from reaching zero. Fix this by using maybe_get_net() instead of get_net(). maybe_get_net() uses refcount_inc_not_zero() and returns NULL if the refcount is already zero, which causes ns_get_path_cb() to fail and the caller to return -ENOENT -- the correct behavior when the netns is being destroyed. Fixes: 675fc275a3a2d ("bpf: offload: report device information for offloaded programs") Fixes: 52775b33bb507 ("bpf: offload: report device information about offloaded maps") Reported-by: Yinhao Hu Reported-by: Kaiyan Mei Reviewed-by: Dongliang Mu Closes: https://lore.kernel.org/bpf/f0aa3678-79c9-47ae-9e8c-02a3d1df160a@hust.edu.cn/ Signed-off-by: Jiayuan Chen Acked-by: Daniel Borkmann Link: https://lore.kernel.org/r/20260409023733.168050-1-jiayuan.chen@linux.dev Signed-off-by: Alexei Starovoitov Signed-off-by: Sasha Levin (cherry picked from commit 85dc711f742b192eb97c0e00b521312f5a7a415e) Signed-off-by: Wentao Guan --- kernel/bpf/offload.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 42ae8d595c2c2..a9a036547c960 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -445,9 +445,8 @@ static struct ns_common *bpf_prog_offload_info_fill_ns(void *private_data) if (aux->offload) { args->info->ifindex = aux->offload->netdev->ifindex; - net = dev_net(aux->offload->netdev); - get_net(net); - ns = &net->ns; + net = maybe_get_net(dev_net(aux->offload->netdev)); + ns = net ? &net->ns : NULL; } else { args->info->ifindex = 0; ns = NULL; @@ -657,9 +656,8 @@ static struct ns_common *bpf_map_offload_info_fill_ns(void *private_data) if (args->offmap->netdev) { args->info->ifindex = args->offmap->netdev->ifindex; - net = dev_net(args->offmap->netdev); - get_net(net); - ns = &net->ns; + net = maybe_get_net(dev_net(args->offmap->netdev)); + ns = net ? &net->ns : NULL; } else { args->info->ifindex = 0; ns = NULL; From 74dd8bc88629e3daf9616e08595632b893fa0fa9 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Fri, 1 May 2026 06:23:20 +0000 Subject: [PATCH 07/76] riscv: Fix register corruption from uninitialized cregs on error [ Upstream commit 6ebcbb53fc9bc30843054ed99fd60b8e542628f4 ] compat_riscv_gpr_set() calls cregs_to_regs() unconditionally, even when user_regset_copyin() fails. Since cregs is an uninitialized stack variable, a copyin failure causes uninitialized stack data to be written into the target task's pt_regs, corrupting its register state and potentially leaking kernel stack contents. compat_restore_sigcontext() has the same issue: it calls cregs_to_regs() even when __copy_from_user() fails, leading to the same corruption of the signal-returning task's register state on error. Only call cregs_to_regs() when the user copy succeeds. Fixes: 4608c159594f ("riscv: compat: ptrace: Add compat_arch_ptrace implement") Fixes: 7383ee05314b ("riscv: compat: signal: Add rt_frame implementation") Signed-off-by: Michael Neuling Assisted-by: Cursor:claude-4.6-opus-high-thinking Link: https://patch.msgid.link/20260501062320.2339562-1-mikey@neuling.org Signed-off-by: Paul Walmsley Signed-off-by: Sasha Levin (cherry picked from commit 0599aa23734c48de9bce36d043a9ec90c23945a1) Signed-off-by: Wentao Guan --- arch/riscv/kernel/compat_signal.c | 2 ++ arch/riscv/kernel/ptrace.c | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/riscv/kernel/compat_signal.c b/arch/riscv/kernel/compat_signal.c index 6ec4e34255a9a..cf3eb33a11e46 100644 --- a/arch/riscv/kernel/compat_signal.c +++ b/arch/riscv/kernel/compat_signal.c @@ -107,6 +107,8 @@ static long compat_restore_sigcontext(struct pt_regs *regs, /* sc_regs is structured the same as the start of pt_regs */ err = __copy_from_user(&cregs, &sc->sc_regs, sizeof(sc->sc_regs)); + if (unlikely(err)) + return err; cregs_to_regs(&cregs, regs); diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 8e86305831ea4..32cd48a4cebb8 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -372,8 +372,8 @@ static int compat_riscv_gpr_set(struct task_struct *target, struct compat_user_regs_struct cregs; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &cregs, 0, -1); - - cregs_to_regs(&cregs, task_pt_regs(target)); + if (!ret) + cregs_to_regs(&cregs, task_pt_regs(target)); return ret; } From f1cb4c44f6d62938a297093a7649116d66a34d97 Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Wed, 31 Dec 2025 22:04:17 +0200 Subject: [PATCH 08/76] ASoC: nau8821: Cancel pending work before suspend [ Upstream commit 7786b10688ac0ebeaff655923cbb2c7d34a98995 ] A jack detection work that is unscheduled or in progress while executing the suspend handler could trigger a race condition. Ensure state consistency by cancelling any pending work or wait for its execution to complete before processing the suspend. Since driver (re)enables both insert and eject interrupts on resume, there is no risk to miss the related jack events. Therefore, flush_delayed_work() is not required here. Fixes: aab1ad11d69f ("ASoC: nau8821: new driver") Fixes: ee70bacef1c6 ("ASoC: nau8821: Avoid unnecessary blocking in IRQ handler") Signed-off-by: Cristian Ciocaltea Link: https://patch.msgid.link/20251231-nau8821-cleanup-v1-3-6b0b76cbbb64@collabora.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin (cherry picked from commit caacbfb367210b3510ea081c21867d14dd7e9983) Signed-off-by: Wentao Guan --- sound/soc/codecs/nau8821.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/soc/codecs/nau8821.c b/sound/soc/codecs/nau8821.c index 8228cd396b9b3..53a38eb4eb0e1 100644 --- a/sound/soc/codecs/nau8821.c +++ b/sound/soc/codecs/nau8821.c @@ -1611,6 +1611,10 @@ static int __maybe_unused nau8821_suspend(struct snd_soc_component *component) if (nau8821->irq) disable_irq(nau8821->irq); + + if (nau8821->jdet_active) + cancel_delayed_work_sync(&nau8821->jdet_work); + snd_soc_component_force_bias_level(component, SND_SOC_BIAS_OFF); /* Power down codec power; don't support button wakeup */ snd_soc_component_disable_pin(component, "MICBIAS"); From ecb393d102fc119d222505e7a289861dad64f012 Mon Sep 17 00:00:00 2001 From: Stephen Smalley Date: Wed, 29 Apr 2026 15:18:40 -0400 Subject: [PATCH 09/76] selinux: switch two allocations to use kzalloc_objs() [ Upstream commit cf6a513f1937581eb012a217b29817e025a1a0ef ] These were the only two allocations in the policy loading logic that were not already using kzalloc_objs() for the policy data structures. Fix these to be consistent with the rest and to protect against ill-formed policy. Signed-off-by: Stephen Smalley Signed-off-by: Paul Moore Signed-off-by: Sasha Levin (cherry picked from commit 34aef83af724a8e65564b41a0acc827f61edb10b) Signed-off-by: Wentao Guan --- security/selinux/ss/conditional.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c index db30462ed6a32..280dc57df8d39 100644 --- a/security/selinux/ss/conditional.c +++ b/security/selinux/ss/conditional.c @@ -165,7 +165,7 @@ void cond_policydb_destroy(struct policydb *p) int cond_init_bool_indexes(struct policydb *p) { kfree(p->bool_val_to_struct); - p->bool_val_to_struct = kmalloc_array( + p->bool_val_to_struct = kcalloc( p->p_bools.nprim, sizeof(*p->bool_val_to_struct), GFP_KERNEL); if (!p->bool_val_to_struct) return -ENOMEM; @@ -706,9 +706,8 @@ static int duplicate_policydb_bools(struct policydb *newdb, struct cond_bool_datum **cond_bool_array; int rc; - cond_bool_array = kmalloc_array(orig->p_bools.nprim, - sizeof(*orig->bool_val_to_struct), - GFP_KERNEL); + cond_bool_array = kcalloc(orig->p_bools.nprim, + sizeof(*orig->bool_val_to_struct), GFP_KERNEL); if (!cond_bool_array) return -ENOMEM; From 2574a766e5e0f4b662d75bb24d3a153cc7d5c9f6 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 5 May 2026 15:21:53 +0200 Subject: [PATCH 10/76] veth: fix OOB txq access in veth_poll() with asymmetric queue counts [ Upstream commit 08f566e8f83bb70f04ad5aba5be352c490a01c8a ] XDP redirect into a veth device (via bpf_redirect()) calls veth_xdp_xmit(), which enqueues frames into the peer's ptr_ring using smp_processor_id() % peer->real_num_rx_queues as the ring index. With an asymmetric veth pair where the peer has fewer TX queues than RX queues, that index can exceed peer->real_num_tx_queues. veth_poll() then resolves peer_txq for the ring via: peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL; where queue_idx = rq->xdp_rxq.queue_index. When queue_idx exceeds peer_dev->real_num_tx_queues this is an out-of-bounds (OOB) access into the peer's netdev_queue array, triggering DEBUG_NET_WARN_ON_ONCE in netdev_get_tx_queue(). The normal ndo_start_xmit path is not affected: the stack clamps skb->queue_mapping via netdev_cap_txqueue() before invoking ndo_start_xmit, so rxq in veth_xmit() never exceeds real_num_tx_queues. Fix veth_poll() by clamping: only dereference peer_txq when queue_idx is within bounds, otherwise set it to NULL. The out-of-range rings are fed exclusively via XDP redirect (veth_xdp_xmit), never via ndo_start_xmit (veth_xmit), so the peer txq was never stopped and there is nothing to wake; NULL is the correct fallback. Reported-by: Sashiko Closes: https://lore.kernel.org/all/20260502071828.616C3C19425@smtp.kernel.org/ Fixes: dc82a33297fc ("veth: apply qdisc backpressure on full ptr_ring to reduce TX drops") Signed-off-by: Jesper Dangaard Brouer Link: https://patch.msgid.link/20260505132159.241305-2-hawk@kernel.org Signed-off-by: Paolo Abeni Signed-off-by: Sasha Levin (cherry picked from commit f2192741bdfc7d344d20fd13e315c64e4c83c848) Signed-off-by: Wentao Guan --- drivers/net/veth.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/veth.c b/drivers/net/veth.c index df276a646c451..56519b646cacd 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -978,7 +978,8 @@ static int veth_poll(struct napi_struct *napi, int budget) /* NAPI functions as RCU section */ peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held()); - peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL; + peer_txq = (peer_dev && queue_idx < peer_dev->real_num_tx_queues) ? + netdev_get_tx_queue(peer_dev, queue_idx) : NULL; xdp_set_return_frame_no_direct(); done = veth_xdp_rcv(rq, budget, &bq, &stats); From b434cde41c4f84150d84dbcfbad20cfacd9c9f82 Mon Sep 17 00:00:00 2001 From: Aboorva Devarajan Date: Fri, 8 May 2026 09:42:56 +0530 Subject: [PATCH 11/76] powerpc/hv-gpci: fix preempt count leak in sysfs show paths [ Upstream commit dbc30a57bd8e026995e9fa8e8c31cffd18542c01 ] Four sysfs show() callbacks in hv-gpci take get_cpu_var(hv_gpci_reqb) (which calls preempt_disable()) but only call the matching put_cpu_var() on the error path under the 'out:' label. Every successful read leaks one preempt_disable(): processor_bus_topology_show() processor_config_show() affinity_domain_via_virtual_processor_show() affinity_domain_via_domain_show() (affinity_domain_via_partition_show() was already correct.) On a CONFIG_PREEMPT=y kernel, repeated reads raise preempt_count and eventually return to userspace with preemption still disabled. The next user-mode page fault then hits faulthandler_disabled() == 1, gets forced to SIGSEGV, and the resulting coredump trips 'BUG: scheduling while atomic' in call_usermodehelper_exec -> wait_for_completion_state -> schedule: BUG: scheduling while atomic: //0x00000004 ... __schedule_bug+0x6c/0x90 __schedule+0x58c/0x13a0 schedule+0x48/0x1a0 schedule_timeout+0x104/0x170 wait_for_completion_state+0x16c/0x330 call_usermodehelper_exec+0x254/0x2d0 vfs_coredump+0x1050/0x2590 get_signal+0xb9c/0xc80 do_notify_resume+0xf8/0x470 Add an out_success label that calls put_cpu_var() before returning the byte count, mirroring affinity_domain_via_partition_show(). Fixes: 71f1c39647d8 ("powerpc/hv_gpci: Add sysfs file inside hv_gpci device to show processor bus topology information") Fixes: 1a160c2a13c6 ("powerpc/hv_gpci: Add sysfs file inside hv_gpci device to show processor config information") Fixes: 71a7ccb478fc ("powerpc/hv_gpci: Add sysfs file inside hv_gpci device to show affinity domain via virtual processor information") Fixes: a69a57cac1ec ("powerpc/hv_gpci: Add sysfs file inside hv_gpci device to show affinity domain via domain information") Signed-off-by: Aboorva Devarajan Reviewed-by: Ritesh Harjani (IBM) Signed-off-by: Madhavan Srinivasan Link: https://patch.msgid.link/20260508041256.3447113-1-aboorvad@linux.ibm.com Signed-off-by: Sasha Levin (cherry picked from commit b61ebb2826ca1852c2bbd92a676fb622c358cab4) Signed-off-by: Wentao Guan --- arch/powerpc/perf/hv-gpci.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 241551d1282f8..0ec0bd3110652 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -210,7 +210,7 @@ static ssize_t processor_bus_topology_show(struct device *dev, struct device_att 0, 0, buf, &n, arg); if (!ret) - return n; + goto out_success; if (ret != H_PARAMETER) goto out; @@ -244,12 +244,14 @@ static ssize_t processor_bus_topology_show(struct device *dev, struct device_att starting_index, 0, buf, &n, arg); if (!ret) - return n; + goto out_success; if (ret != H_PARAMETER) goto out; } +out_success: + put_cpu_var(hv_gpci_reqb); return n; out: @@ -278,7 +280,7 @@ static ssize_t processor_config_show(struct device *dev, struct device_attribute 0, 0, buf, &n, arg); if (!ret) - return n; + goto out_success; if (ret != H_PARAMETER) goto out; @@ -312,12 +314,14 @@ static ssize_t processor_config_show(struct device *dev, struct device_attribute starting_index, 0, buf, &n, arg); if (!ret) - return n; + goto out_success; if (ret != H_PARAMETER) goto out; } +out_success: + put_cpu_var(hv_gpci_reqb); return n; out: @@ -346,7 +350,7 @@ static ssize_t affinity_domain_via_virtual_processor_show(struct device *dev, 0, 0, buf, &n, arg); if (!ret) - return n; + goto out_success; if (ret != H_PARAMETER) goto out; @@ -382,12 +386,14 @@ static ssize_t affinity_domain_via_virtual_processor_show(struct device *dev, starting_index, secondary_index, buf, &n, arg); if (!ret) - return n; + goto out_success; if (ret != H_PARAMETER) goto out; } +out_success: + put_cpu_var(hv_gpci_reqb); return n; out: @@ -416,7 +422,7 @@ static ssize_t affinity_domain_via_domain_show(struct device *dev, struct device 0, 0, buf, &n, arg); if (!ret) - return n; + goto out_success; if (ret != H_PARAMETER) goto out; @@ -448,12 +454,14 @@ static ssize_t affinity_domain_via_domain_show(struct device *dev, struct device starting_index, 0, buf, &n, arg); if (!ret) - return n; + goto out_success; if (ret != H_PARAMETER) goto out; } +out_success: + put_cpu_var(hv_gpci_reqb); return n; out: From 77b60fe5216c481c354c2bb9ebacc89b20af3591 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 30 Jul 2026 06:50:47 -0600 Subject: [PATCH 12/76] io_uring/futex: only mark private futex waits as inflight commit 4d327bbd1cd2485783553b6b2b401aa475f90dd0 upstream. Inflight tracking of futex wait requests exists to ensure that do_exit() -> io_uring_files_cancel() cancels them before the mm goes away, as a private futex wait depends on the mm private futex hash staying alive for the duration of the request. Shared futexes have no such dependency. A FLAGS_SHARED request always resolves to either an inode based key or an mm-shared key, both of which fail futex_key_is_private() and hence always hash into the global futex hash, whose lifetime isn't tied to the mm. Only mark vectored futex waits as inflight if the futex is private. Cc: stable@vger.kernel.org Fixes: 079afb081c42 ("io_uring/futex: mark wait requests as inflight") Link: https://lore.kernel.org/io-uring/CANGjgdn=R_qyUdE=j9za+vkmqcxacbP-84OHXF4nZ4ho9qRyVg@mail.gmail.com/ Signed-off-by: Jens Axboe [ kept 6.18's `struct futex_vector *futexv` declaration and changed `ifd->futexv[i].w.flags` to `futexv[i].w.flags` since `struct io_futexv_data` is absent, retaining the `iof->futexv_owned = 0;` init ] Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 2b7c6b90ce8013455c0e41a9d525d3d1ed97f116) Signed-off-by: Wentao Guan --- io_uring/futex.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/io_uring/futex.c b/io_uring/futex.c index 57a17c6942219..cccd1244c4b46 100644 --- a/io_uring/futex.c +++ b/io_uring/futex.c @@ -149,14 +149,16 @@ int io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) int io_futex_wait_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { + struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); int ret; ret = io_futex_prep(req, sqe); if (unlikely(ret)) return ret; - /* Mark as inflight, so file exit cancelation will find it */ - io_req_track_inflight(req); + /* inflight tracking only needed for mm private hash */ + if (!(iof->futex_flags & FLAGS_SHARED)) + io_req_track_inflight(req); return 0; } @@ -179,6 +181,7 @@ int io_futexv_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex); struct futex_vector *futexv; + unsigned int i; int ret; /* No flags or mask supported for waitv */ @@ -202,8 +205,14 @@ int io_futexv_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return ret; } - /* Mark as inflight, so file exit cancelation will find it */ - io_req_track_inflight(req); + /* inflight tracking only needed for mm private hash */ + for (i = 0; i < iof->futex_nr; i++) { + if (!(futexv[i].w.flags & FLAGS_SHARED)) { + io_req_track_inflight(req); + break; + } + } + iof->futexv_owned = 0; iof->futexv_unqueued = 0; req->flags |= REQ_F_ASYNC_DATA; From 3a4493b1348a3f41f08ac956b61f76908b82fd35 Mon Sep 17 00:00:00 2001 From: Caleb Sander Mateos Date: Tue, 25 Aug 2026 15:47:42 -0400 Subject: [PATCH 13/76] io_uring: simplify IORING_SETUP_DEFER_TASKRUN && !SQPOLL check [ Upstream commit 7cb3a68376da0bc0afab8157223cb479c97de9ff ] io_uring_sanitise_params() already rejects flags that include both IORING_SETUP_SQPOLL and IORING_SETUP_DEFER_TASKRUN. So it's unnecessary to check IORING_SETUP_SQPOLL in io_uring_create() when IORING_SETUP_DEFER_TASKRUN has already been checked. Drop the !(ctx->flags & IORING_SETUP_SQPOLL) check for the task_complete case. Signed-off-by: Caleb Sander Mateos Signed-off-by: Jens Axboe Stable-dep-of: cd305ee3633a ("io_uring: defer eventfd signaling when queued from a wakeup handler") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman (cherry picked from commit e973a371d35a2ef6ebab5f5a569c7af8c67eff3d) Signed-off-by: Wentao Guan --- io_uring/io_uring.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 7f398c4a3a6eb..1dc160d86ea74 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3867,8 +3867,7 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, static_branch_deferred_inc(&io_key_has_sqarray); if ((ctx->flags & IORING_SETUP_DEFER_TASKRUN) && - !(ctx->flags & IORING_SETUP_IOPOLL) && - !(ctx->flags & IORING_SETUP_SQPOLL)) + !(ctx->flags & IORING_SETUP_IOPOLL)) ctx->task_complete = true; if (ctx->task_complete || (ctx->flags & IORING_SETUP_IOPOLL)) From bf1054e7d76917cefbf16a52be9f9836a5227243 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 25 Aug 2026 15:47:43 -0400 Subject: [PATCH 14/76] io_uring/rsrc: improve regbuf iov validation [ Upstream commit 2e02f9efdbc6c73544e315b7eb85e55a59776b6f ] Deduplicate io_buffer_validate() calls by moving the checks into io_sqe_buffer_register(). Now we also don't need special handling in io_buffer_validate() passing through buffer removal requests. I also was using it as a cleanup before some other changes. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe Stable-dep-of: cd305ee3633a ("io_uring: defer eventfd signaling when queued from a wakeup handler") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 0bcec5dda029ce9574260089a83aa12e992a0dff) Signed-off-by: Wentao Guan --- io_uring/rsrc.c | 31 ++++++++++--------------------- 1 file changed, 10 insertions(+), 21 deletions(-) diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index b6a070abbf997..8d28c6bfebb1e 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -94,20 +94,6 @@ int io_validate_user_buf_range(u64 uaddr, u64 ulen) return 0; } -static int io_buffer_validate(struct iovec *iov) -{ - /* - * Don't impose further limits on the size and buffer - * constraints here, we'll -EINVAL later when IO is - * submitted if they are wrong. - */ - if (!iov->iov_base) - return iov->iov_len ? -EFAULT : 0; - - return io_validate_user_buf_range((unsigned long)iov->iov_base, - iov->iov_len); -} - static void io_release_ubuf(void *priv) { struct io_mapped_ubuf *imu = priv; @@ -317,9 +303,6 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, err = -EFAULT; break; } - err = io_buffer_validate(iov); - if (err) - break; node = io_sqe_buffer_register(ctx, iov, &last_hpage); if (IS_ERR(node)) { err = PTR_ERR(node); @@ -788,8 +771,17 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx, struct io_imu_folio_data data; bool coalesced = false; - if (!iov->iov_base) + if (!iov->iov_base) { + if (iov->iov_len) + return ERR_PTR(-EFAULT); + /* remove the buffer without installing a new one */ return NULL; + } + + ret = io_validate_user_buf_range((unsigned long)iov->iov_base, + iov->iov_len); + if (ret) + return ERR_PTR(ret); node = io_rsrc_node_alloc(ctx, IORING_RSRC_BUFFER); if (!node) @@ -895,9 +887,6 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, ret = PTR_ERR(iov); break; } - ret = io_buffer_validate(iov); - if (ret) - break; if (ctx->compat) arg += sizeof(struct compat_iovec); else From f86a30cb3f1f2defa942645897c4416fc6e4e1d3 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 25 Aug 2026 15:47:44 -0400 Subject: [PATCH 15/76] io_uring: defer eventfd signaling when queued from a wakeup handler [ Upstream commit cd305ee3633a45fcf5f3a5d83f99f3cb77d87b6e ] io_req_local_work_add() signals the CQ ring eventfd inline when it is the one to push the first entry onto ->work_list. For DEFER_TASKRUN rings that add is frequently done from a waitqueue wakeup handler, where an arbitrary waitqueue lock is held. eventfd_signal_mask() only refuses to recurse when current->in_eventfd is set, but that bit is set by eventfd_signal_mask() itself. If the wake chain starts somewhere else, signal goes out inline and can feed back into epoll. Add IOU_F_TWQ_IN_WAKE, set it on the task_work add done from the three waitqueue callbacks, and use it to force io_eventfd_signal() down the existing call_rcu_hurry() deferral instead of signaling inline. Fixes: 21a091b970cd ("io_uring: signal registered eventfd to process deferred task work") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/20260813133843.2933127-1-4ncienth@gmail.com/ Signed-off-by: Jens Axboe [ Relocated the `io_req_local_work_add()` hunk into io_uring.c and kept 6.18's `ctx->has_evfd` and open-coded `io_pollfree_wake()` context due to missing tw.c split and `io_poll_remove_waitq()`. ] Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman (cherry picked from commit e22f4494cc9487d326e5e3067f33dea7c1e442b2) Signed-off-by: Wentao Guan --- include/linux/io_uring_types.h | 8 ++++++++ io_uring/eventfd.c | 8 ++++---- io_uring/eventfd.h | 2 +- io_uring/futex.c | 4 ++-- io_uring/io_uring.c | 4 ++-- io_uring/poll.c | 23 ++++++++++++----------- io_uring/waitid.c | 2 +- 7 files changed, 30 insertions(+), 21 deletions(-) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 2ee408d076b3f..d73556f10733c 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -17,6 +17,14 @@ enum { * It's also ignored unless IORING_SETUP_DEFER_TASKRUN is set. */ IOU_F_TWQ_LAZY_WAKE = 1, + + /* + * Set when task_work is queued from a waitqueue wakeup handler, where + * an arbitrary provider waitqueue lock is held. Signaling the CQ ring + * eventfd inline from there can recurse back into that lock through + * epoll, so the eventfd signal must be deferred. + */ + IOU_F_TWQ_IN_WAKE = 2, }; enum io_uring_cmd_flags { diff --git a/io_uring/eventfd.c b/io_uring/eventfd.c index ab789e1ebe91e..7a57dd88304a6 100644 --- a/io_uring/eventfd.c +++ b/io_uring/eventfd.c @@ -50,9 +50,9 @@ static void io_eventfd_do_signal(struct rcu_head *rcu) /* * Returns true if the caller should put the ev_fd reference, false if not. */ -static bool __io_eventfd_signal(struct io_ev_fd *ev_fd) +static bool __io_eventfd_signal(struct io_ev_fd *ev_fd, bool defer) { - if (eventfd_signal_allowed()) { + if (!defer && eventfd_signal_allowed()) { eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE); return true; } @@ -72,7 +72,7 @@ static bool io_eventfd_trigger(struct io_ev_fd *ev_fd) return !ev_fd->eventfd_async || io_wq_current_is_worker(); } -void io_eventfd_signal(struct io_ring_ctx *ctx, bool cqe_event) +void io_eventfd_signal(struct io_ring_ctx *ctx, bool cqe_event, bool defer) { bool skip = false; struct io_ev_fd *ev_fd; @@ -112,7 +112,7 @@ void io_eventfd_signal(struct io_ring_ctx *ctx, bool cqe_event) spin_unlock(&ctx->completion_lock); } - if (skip || __io_eventfd_signal(ev_fd)) + if (skip || __io_eventfd_signal(ev_fd, defer)) io_eventfd_put(ev_fd); } diff --git a/io_uring/eventfd.h b/io_uring/eventfd.h index e2f1985c2cf98..86c3c69eba1d7 100644 --- a/io_uring/eventfd.h +++ b/io_uring/eventfd.h @@ -4,4 +4,4 @@ int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg, unsigned int eventfd_async); int io_eventfd_unregister(struct io_ring_ctx *ctx); -void io_eventfd_signal(struct io_ring_ctx *ctx, bool cqe_event); +void io_eventfd_signal(struct io_ring_ctx *ctx, bool cqe_event, bool defer); diff --git a/io_uring/futex.c b/io_uring/futex.c index cccd1244c4b46..3e92c2a639602 100644 --- a/io_uring/futex.c +++ b/io_uring/futex.c @@ -174,7 +174,7 @@ static void io_futex_wakev_fn(struct wake_q_head *wake_q, struct futex_q *q) io_req_set_res(req, 0, 0); req->io_task_work.func = io_futexv_complete; - io_req_task_work_add(req); + __io_req_task_work_add(req, IOU_F_TWQ_IN_WAKE); } int io_futexv_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) @@ -230,7 +230,7 @@ static void io_futex_wake_fn(struct wake_q_head *wake_q, struct futex_q *q) io_req_set_res(req, 0, 0); req->io_task_work.func = io_futex_complete; - io_req_task_work_add(req); + __io_req_task_work_add(req, IOU_F_TWQ_IN_WAKE); } int io_futexv_wait(struct io_kiocb *req, unsigned int issue_flags) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 1dc160d86ea74..9784463fb718d 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -578,7 +578,7 @@ void __io_commit_cqring_flush(struct io_ring_ctx *ctx) if (ctx->off_timeout_used) io_flush_timeouts(ctx); if (ctx->has_evfd) - io_eventfd_signal(ctx, true); + io_eventfd_signal(ctx, true, false); } static inline void __io_cq_lock(struct io_ring_ctx *ctx) @@ -1312,7 +1312,7 @@ static void io_req_local_work_add(struct io_kiocb *req, unsigned flags) if (!head) { io_ctx_mark_taskrun(ctx); if (ctx->has_evfd) - io_eventfd_signal(ctx, false); + io_eventfd_signal(ctx, false, flags & IOU_F_TWQ_IN_WAKE); } nr_wait = atomic_read(&ctx->cq_wait_nr); diff --git a/io_uring/poll.c b/io_uring/poll.c index a5e78747e63ab..6745bbc963286 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -190,9 +190,9 @@ enum { IOU_POLL_REQUEUE = 4, }; -static void __io_poll_execute(struct io_kiocb *req, int mask) +static void __io_poll_execute(struct io_kiocb *req, int mask, unsigned tw_flags) { - unsigned flags = 0; + unsigned flags = tw_flags; io_req_set_res(req, mask, 0); req->io_task_work.func = io_poll_task_func; @@ -200,14 +200,15 @@ static void __io_poll_execute(struct io_kiocb *req, int mask) trace_io_uring_task_add(req, mask); if (!(req->flags & REQ_F_POLL_NO_LAZY)) - flags = IOU_F_TWQ_LAZY_WAKE; + flags |= IOU_F_TWQ_LAZY_WAKE; __io_req_task_work_add(req, flags); } -static inline void io_poll_execute(struct io_kiocb *req, int res) +static inline void io_poll_execute(struct io_kiocb *req, int res, + unsigned tw_flags) { if (io_poll_get_ownership(req)) - __io_poll_execute(req, res); + __io_poll_execute(req, res, tw_flags); } /* @@ -323,7 +324,7 @@ void io_poll_task_func(struct io_kiocb *req, io_tw_token_t tw) if (ret == IOU_POLL_NO_ACTION) { return; } else if (ret == IOU_POLL_REQUEUE) { - __io_poll_execute(req, 0); + __io_poll_execute(req, 0, 0); return; } io_poll_remove_entries(req); @@ -362,7 +363,7 @@ static void io_poll_cancel_req(struct io_kiocb *req) { io_poll_mark_cancelled(req); /* kick tw, which should complete the request */ - io_poll_execute(req, 0); + io_poll_execute(req, 0, 0); } #define IO_ASYNC_POLL_COMMON (EPOLLONESHOT | EPOLLPRI) @@ -371,7 +372,7 @@ static __cold int io_pollfree_wake(struct io_kiocb *req, struct io_poll *poll) { io_poll_mark_cancelled(req); /* we have to kick tw in case it's not already */ - io_poll_execute(req, 0); + io_poll_execute(req, 0, IOU_F_TWQ_IN_WAKE); /* * If the waitqueue is being freed early but someone is already @@ -426,7 +427,7 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, else req->flags &= ~REQ_F_SINGLE_POLL; } - __io_poll_execute(req, mask); + __io_poll_execute(req, mask, IOU_F_TWQ_IN_WAKE); } return 1; } @@ -614,7 +615,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req, if (mask && (poll->events & EPOLLET) && io_poll_can_finish_inline(req, ipt)) { - __io_poll_execute(req, mask); + __io_poll_execute(req, mask, 0); return 0; } io_napi_add(req); @@ -625,7 +626,7 @@ static int __io_arm_poll_handler(struct io_kiocb *req, * poll was waken up, queue up a tw, it'll deal with it. */ if (atomic_cmpxchg(&req->poll_refs, 1, 0) != 1) - __io_poll_execute(req, 0); + __io_poll_execute(req, 0, 0); } return 0; } diff --git a/io_uring/waitid.c b/io_uring/waitid.c index 921b4de3a31cb..97cce0bd2d50e 100644 --- a/io_uring/waitid.c +++ b/io_uring/waitid.c @@ -237,7 +237,7 @@ static int io_waitid_wait(struct wait_queue_entry *wait, unsigned mode, return 1; req->io_task_work.func = io_waitid_cb; - io_req_task_work_add(req); + __io_req_task_work_add(req, IOU_F_TWQ_IN_WAKE); return 1; } From 23474ec897cd8a1d278733dd596d6af5f9360a11 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jose=20Villase=C3=B1or=20Montfort?= Date: Wed, 26 Aug 2026 07:21:43 -0400 Subject: [PATCH 16/76] HID: magicmouse: prevent unbounded recursion in magicmouse_raw_event() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit db8d634128d2ba88d79c0b601e983ebe14bb0519 ] magicmouse_raw_event() handles DOUBLE_REPORT_ID (0xf7) packets, which pack two touch reports into one, by splitting the packet and calling itself on each half. The only guard against runaway recursion is a "size < 1" check, which stops zero-sized calls but does not bound the recursion depth. A malicious HID device that matches this driver can send a report starting with DOUBLE_REPORT_ID and filled with the sequence [0xf7, 0x00]. Each level consumes two bytes and recurses on the remainder, so an incoming report of up to HID_MAX_BUFFER_SIZE (16 KiB) drives roughly 8000 nested calls. That easily exhausts the 16 KiB kernel stack, leading to a stack overflow: a panic with CONFIG_VMAP_STACK, or memory corruption without it. A double report only ever wraps two normal reports; it is never legitimately nested. Refuse to re-enter the DOUBLE_REPORT_ID case from a recursive call so the recursion depth is bounded to two, while all valid packets keep being parsed exactly as before. Fixes: a462230e16ac ("HID: magicmouse: enable Magic Trackpad support") Link: https://lore.kernel.org/linux-input/20260706181347.700DB1F00A3F@smtp.kernel.org/ Cc: stable@vger.kernel.org Signed-off-by: Jose Villaseñor Montfort Reviewed-by: Alec Hall Tested-by: Alec Hall Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 70589b0c005db003f6d8ae4db3c4d54fed7b83e4) Signed-off-by: Wentao Guan --- drivers/hid/hid-magicmouse.c | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index ccdb29559fec2..0480e7d216bc4 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -383,8 +383,8 @@ static void magicmouse_emit_touch(struct magicmouse_sc *msc, int raw_id, u8 *tda } } -static int magicmouse_raw_event(struct hid_device *hdev, - struct hid_report *report, u8 *data, int size) +static int __magicmouse_raw_event(struct hid_device *hdev, + struct hid_report *report, u8 *data, int size, bool nested) { struct magicmouse_sc *msc = hid_get_drvdata(hdev); struct input_dev *input = msc->input; @@ -495,6 +495,15 @@ static int magicmouse_raw_event(struct hid_device *hdev, * packet. */ + /* + * A double report only ever wraps two normal reports, so it is + * never nested. Refuse to recurse a second time; otherwise a + * malicious device could chain DOUBLE_REPORT_ID packets to drive + * unbounded recursion and overflow the kernel stack. + */ + if (nested) + return 0; + /* Ensure that we have at least 2 elements (report type and size) */ if (size < 2) return 0; @@ -506,9 +515,9 @@ static int magicmouse_raw_event(struct hid_device *hdev, return 0; } - magicmouse_raw_event(hdev, report, data + 2, data[1]); - magicmouse_raw_event(hdev, report, data + 2 + data[1], - size - 2 - data[1]); + __magicmouse_raw_event(hdev, report, data + 2, data[1], true); + __magicmouse_raw_event(hdev, report, data + 2 + data[1], + size - 2 - data[1], true); return 0; default: return 0; @@ -534,6 +543,12 @@ static int magicmouse_raw_event(struct hid_device *hdev, return 1; } +static int magicmouse_raw_event(struct hid_device *hdev, + struct hid_report *report, u8 *data, int size) +{ + return __magicmouse_raw_event(hdev, report, data, size, false); +} + static int magicmouse_event(struct hid_device *hdev, struct hid_field *field, struct hid_usage *usage, __s32 value) { From 25b3861c40b19a02176c48913f3ceb62433fd786 Mon Sep 17 00:00:00 2001 From: Antheas Kapenekakis Date: Wed, 26 Aug 2026 09:46:55 -0400 Subject: [PATCH 17/76] HID: asus: simplify RGB init sequence MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 56d1b33e644cca1bedffbc73d28778ed4ae30f64 ] Currently, RGB initialization forks depending on whether a device is NKEY. However, in reality both initialization forks are the same, other than the NKEY initialization initializing the LED_REPORT_ID1, LED_REPORT_ID2 endpoints, and the non-NKEY initialization having a functionality check which is skipped for the NKEY path. Therefore, merge the if blocks, gate the ID1/ID2 initializations behind the NKEY quirk instead, and introduce the functionality check for NKEY devices (it is supported by them). There should be no functional change with this patch. Acked-by: Benjamin Tissoires Signed-off-by: Antheas Kapenekakis Link: https://patch.msgid.link/20260122075044.5070-2-lkml@antheas.dev Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen Stable-dep-of: 02bf61dfb44f ("HID: asus: fix missing hid_is_usb() check") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman (cherry picked from commit d0754db7883c81d340c8a0185ce8b0a2ba0e3cf4) Signed-off-by: Wentao Guan --- drivers/hid/hid-asus.c | 52 ++++++++++++++++++------------------------ 1 file changed, 22 insertions(+), 30 deletions(-) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 1746e8ea50ddf..e1ae518bfb217 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -638,13 +638,20 @@ static int asus_kbd_register_leds(struct hid_device *hdev) unsigned char kbd_func; int ret; - if (drvdata->quirks & QUIRK_ROG_NKEY_KEYBOARD) { - /* Initialize keyboard */ - ret = asus_kbd_init(hdev, FEATURE_KBD_REPORT_ID); - if (ret < 0) - return ret; + ret = asus_kbd_init(hdev, FEATURE_KBD_REPORT_ID); + if (ret < 0) + return ret; - /* The LED endpoint is initialised in two HID */ + /* Get keyboard functions */ + ret = asus_kbd_get_functions(hdev, &kbd_func, FEATURE_KBD_REPORT_ID); + if (ret < 0) + return ret; + + /* Check for backlight support */ + if (!(kbd_func & SUPPORT_KBD_BACKLIGHT)) + return -ENODEV; + + if (drvdata->quirks & QUIRK_ROG_NKEY_KEYBOARD) { ret = asus_kbd_init(hdev, FEATURE_KBD_LED_REPORT_ID1); if (ret < 0) return ret; @@ -652,34 +659,19 @@ static int asus_kbd_register_leds(struct hid_device *hdev) ret = asus_kbd_init(hdev, FEATURE_KBD_LED_REPORT_ID2); if (ret < 0) return ret; + } - if (dmi_match(DMI_PRODUCT_FAMILY, "ProArt P16")) { - ret = asus_kbd_disable_oobe(hdev); - if (ret < 0) - return ret; - } - - if (drvdata->quirks & QUIRK_ROG_ALLY_XPAD) { - intf = to_usb_interface(hdev->dev.parent); - udev = interface_to_usbdev(intf); - validate_mcu_fw_version(hdev, - le16_to_cpu(udev->descriptor.idProduct)); - } - - } else { - /* Initialize keyboard */ - ret = asus_kbd_init(hdev, FEATURE_KBD_REPORT_ID); - if (ret < 0) - return ret; - - /* Get keyboard functions */ - ret = asus_kbd_get_functions(hdev, &kbd_func, FEATURE_KBD_REPORT_ID); + if (dmi_match(DMI_PRODUCT_FAMILY, "ProArt P16")) { + ret = asus_kbd_disable_oobe(hdev); if (ret < 0) return ret; + } - /* Check for backlight support */ - if (!(kbd_func & SUPPORT_KBD_BACKLIGHT)) - return -ENODEV; + if (drvdata->quirks & QUIRK_ROG_ALLY_XPAD) { + intf = to_usb_interface(hdev->dev.parent); + udev = interface_to_usbdev(intf); + validate_mcu_fw_version(hdev, + le16_to_cpu(udev->descriptor.idProduct)); } drvdata->kbd_backlight = devm_kzalloc(&hdev->dev, From 12899f7e23d4e518d2849335deda1fb52e6f5cf4 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Wed, 26 Aug 2026 09:46:56 -0400 Subject: [PATCH 18/76] HID: asus: fix missing hid_is_usb() check [ Upstream commit 02bf61dfb44f17ec187d1da1a82495951bbd12df ] to_usb_interface() can only be used on a hid_device whose parent is really USB; uhid can create devices that identify as being on BUS_USB, but don't actually have a USB parent. Fix the use of to_usb_interface() without a hid_is_usb() check. I have verified that it is currently possible to trigger a kernel splat due to this bug in an ASAN build, and that this commit fixes the issue. Fixes: 00e005c952f7 ("hid-asus: check ROG Ally MCU version and warn") Cc: stable@vger.kernel.org Signed-off-by: Jann Horn Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 8b5debb6252cd1e2b6c7adf8f95761a0e743d2cf) Signed-off-by: Wentao Guan --- drivers/hid/hid-asus.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index e1ae518bfb217..185bcdb538f24 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -667,7 +667,7 @@ static int asus_kbd_register_leds(struct hid_device *hdev) return ret; } - if (drvdata->quirks & QUIRK_ROG_ALLY_XPAD) { + if ((drvdata->quirks & QUIRK_ROG_ALLY_XPAD) && hid_is_usb(hdev)) { intf = to_usb_interface(hdev->dev.parent); udev = interface_to_usbdev(intf); validate_mcu_fw_version(hdev, From 1b29fc408e9ebece446818a4a5208f7796209646 Mon Sep 17 00:00:00 2001 From: Michael Zaidman Date: Wed, 26 Aug 2026 11:11:24 -0400 Subject: [PATCH 19/76] HID: ft260: validate i2c input report length MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 80c4bbb2b38513e9c3d84805fa61a0ee16d79c45 ] Add two checks to ft260_raw_event() to prevent out-of-bounds reads from malicious or malfunctioning devices: First, reject reports shorter than the 2-byte header (report ID + length fields). Without this, even accessing xfer->length on a 1-byte report is an OOB read. Second, validate xfer->length against the actual data capacity of the received HID report. Each I2C data report ID (0xD0 through 0xDE) defines a different report size in the HID descriptor, so the available payload varies per report. A corrupted length field could cause memcpy to read beyond the report buffer. Reported-by: Sebastián Josué Alba Vives Signed-off-by: Michael Zaidman Signed-off-by: Jiri Kosina Stable-dep-of: bf3e39df3a39 ("HID: ft260: fix stack-use-after-return write in I2C read race") Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 30c37ac21a458262e014a3c649234dd46ef0ce75) Signed-off-by: Wentao Guan --- drivers/hid/hid-ft260.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-ft260.c b/drivers/hid/hid-ft260.c index 333341e80b0ec..70e2eedb465af 100644 --- a/drivers/hid/hid-ft260.c +++ b/drivers/hid/hid-ft260.c @@ -1068,10 +1068,22 @@ static int ft260_raw_event(struct hid_device *hdev, struct hid_report *report, struct ft260_device *dev = hid_get_drvdata(hdev); struct ft260_i2c_input_report *xfer = (void *)data; + if (size < offsetof(struct ft260_i2c_input_report, data)) { + hid_err(hdev, "short report %d\n", size); + return -1; + } + if (xfer->report >= FT260_I2C_REPORT_MIN && xfer->report <= FT260_I2C_REPORT_MAX) { - ft260_dbg("i2c resp: rep %#02x len %d\n", xfer->report, - xfer->length); + ft260_dbg("i2c resp: rep %#02x len %d size %d\n", + xfer->report, xfer->length, size); + + if (xfer->length > size - + offsetof(struct ft260_i2c_input_report, data)) { + hid_err(hdev, "report %#02x: length %d exceeds HID report size\n", + xfer->report, xfer->length); + return -1; + } if ((dev->read_buf == NULL) || (xfer->length > dev->read_len - dev->read_idx)) { From 5e1bbc950b9809c7fe199d89449bf2d2b8518eaf Mon Sep 17 00:00:00 2001 From: Raman Varabets Date: Wed, 26 Aug 2026 11:11:25 -0400 Subject: [PATCH 20/76] HID: ft260: fix stack-use-after-return write in I2C read race [ Upstream commit bf3e39df3a397fd82967a31d17c4e02c7feab221 ] ft260_i2c_read() points dev->read_buf at a caller-supplied buffer (often an on-stack variable), arms a completion and waits up to five seconds for the device to return the data. The HID input callback ft260_raw_event() runs in the input/IRQ path, independent of the dev->lock mutex held by the read path, and copies the device-supplied payload into dev->read_buf after a plain NULL check. These two paths share read_buf, read_idx and read_len with no serialization. If the device delays its response until the read times out, ft260_i2c_read() resets the controller, clears read_buf and returns, unwinding the stack frame the buffer lived in. A response that arrives at that moment lets ft260_raw_event() pass the NULL check and then memcpy() the device-controlled payload into the now-freed stack location, a bounded but attacker-influenced stack-use-after-return write triggerable by malicious or malfunctioning hardware. Add a dedicated spinlock that serializes every access to read_buf, read_idx and read_len. ft260_raw_event() now holds it across the NULL check, the memcpy and the index update, while the read path takes it when arming and when clearing the buffer, so the teardown can no longer slip between the check and the copy. Fixes: 6a82582d9fa4 ("HID: ft260: add usb hid to i2c host bridge driver") Cc: stable@vger.kernel.org Signed-off-by: Raman Varabets Reviewed-by: Michael Zaidman Signed-off-by: Jiri Kosina Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman (cherry picked from commit a8e1f970f9040294cfd9100c681c32af6c2aeec0) Signed-off-by: Wentao Guan --- drivers/hid/hid-ft260.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/drivers/hid/hid-ft260.c b/drivers/hid/hid-ft260.c index 70e2eedb465af..f479459544aee 100644 --- a/drivers/hid/hid-ft260.c +++ b/drivers/hid/hid-ft260.c @@ -240,6 +240,8 @@ struct ft260_device { struct mutex lock; u8 write_buf[FT260_REPORT_MAX_LENGTH]; unsigned long need_wakeup_at; + /* Protects read_buf, read_idx and read_len against ft260_raw_event() */ + spinlock_t read_lock; u8 *read_buf; u16 read_idx; u16 read_len; @@ -501,6 +503,7 @@ static int ft260_i2c_read(struct ft260_device *dev, u8 addr, u8 *data, int timeout, ret = 0; struct ft260_i2c_read_request_report rep; struct hid_device *hdev = dev->hdev; + unsigned long irqflags; u8 bus_busy = 0; if ((flag & FT260_FLAG_START_REPEATED) == FT260_FLAG_START_REPEATED) @@ -526,9 +529,11 @@ static int ft260_i2c_read(struct ft260_device *dev, u8 addr, u8 *data, reinit_completion(&dev->wait); + spin_lock_irqsave(&dev->read_lock, irqflags); dev->read_idx = 0; dev->read_buf = data; dev->read_len = rd_len; + spin_unlock_irqrestore(&dev->read_lock, irqflags); ret = ft260_hid_output_report(hdev, (u8 *)&rep, sizeof(rep)); if (ret < 0) { @@ -543,7 +548,9 @@ static int ft260_i2c_read(struct ft260_device *dev, u8 addr, u8 *data, goto ft260_i2c_read_exit; } + spin_lock_irqsave(&dev->read_lock, irqflags); dev->read_buf = NULL; + spin_unlock_irqrestore(&dev->read_lock, irqflags); if (flag & FT260_FLAG_STOP) bus_busy = FT260_I2C_STATUS_BUS_BUSY; @@ -562,7 +569,9 @@ static int ft260_i2c_read(struct ft260_device *dev, u8 addr, u8 *data, } while (len > 0); ft260_i2c_read_exit: + spin_lock_irqsave(&dev->read_lock, irqflags); dev->read_buf = NULL; + spin_unlock_irqrestore(&dev->read_lock, irqflags); return ret; } @@ -1018,6 +1027,7 @@ static int ft260_probe(struct hid_device *hdev, const struct hid_device_id *id) "FT260 usb-i2c bridge"); mutex_init(&dev->lock); + spin_lock_init(&dev->read_lock); init_completion(&dev->wait); ret = ft260_xfer_status(dev, FT260_I2C_STATUS_BUS_BUSY); @@ -1067,6 +1077,7 @@ static int ft260_raw_event(struct hid_device *hdev, struct hid_report *report, { struct ft260_device *dev = hid_get_drvdata(hdev); struct ft260_i2c_input_report *xfer = (void *)data; + unsigned long irqflags; if (size < offsetof(struct ft260_i2c_input_report, data)) { hid_err(hdev, "short report %d\n", size); @@ -1075,6 +1086,8 @@ static int ft260_raw_event(struct hid_device *hdev, struct hid_report *report, if (xfer->report >= FT260_I2C_REPORT_MIN && xfer->report <= FT260_I2C_REPORT_MAX) { + bool complete_read; + ft260_dbg("i2c resp: rep %#02x len %d size %d\n", xfer->report, xfer->length, size); @@ -1085,8 +1098,15 @@ static int ft260_raw_event(struct hid_device *hdev, struct hid_report *report, return -1; } + /* + * Hold read_lock so a timed-out ft260_i2c_read() cannot + * clear read_buf between the NULL check and the memcpy. + */ + spin_lock_irqsave(&dev->read_lock, irqflags); + if ((dev->read_buf == NULL) || (xfer->length > dev->read_len - dev->read_idx)) { + spin_unlock_irqrestore(&dev->read_lock, irqflags); hid_err(hdev, "unexpected report %#02x, length %d\n", xfer->report, xfer->length); return -1; @@ -1095,8 +1115,11 @@ static int ft260_raw_event(struct hid_device *hdev, struct hid_report *report, memcpy(&dev->read_buf[dev->read_idx], &xfer->data, xfer->length); dev->read_idx += xfer->length; + complete_read = dev->read_idx == dev->read_len; + + spin_unlock_irqrestore(&dev->read_lock, irqflags); - if (dev->read_idx == dev->read_len) + if (complete_read) complete(&dev->wait); } else { From d5c8767ac8ebdbbd5ada397e26f7d966a8f7ea78 Mon Sep 17 00:00:00 2001 From: DaeMyung Kang Date: Tue, 28 Apr 2026 23:08:55 +0900 Subject: [PATCH 21/76] ksmbd: harden file lifetime during session teardown commit a42896bebfcc287ed1e61d820a888e33b1eb80ce upstream. __close_file_table_ids() is the per-session teardown that closes every fp belonging to a session (or to one tree connect on that session) by walking the session's volatile-id idr. The current loop has three related problems on busy or racing workloads: * Sleeping under ft->lock. The session-teardown skip callback, session_fd_check(), already sleeps in ksmbd_vfs_copy_durable_owner() -> kstrdup(GFP_KERNEL) and down_write(&fp->f_ci->m_lock) (a rw_semaphore). Running the callback inside write_lock(&ft->lock) trips CONFIG_DEBUG_ATOMIC_SLEEP / CONFIG_PROVE_LOCKING on a durable-fd workload. * Refcount accounting blind to f_state. The unconditional atomic_dec_and_test(&fp->refcount) does not distinguish FP_INITED (idr-owned reference still intact) from FP_CLOSED (an earlier ksmbd_close_fd() already consumed the idr-owned reference while leaving fp in the idr because a holder kept refcount non-zero). When the latter races with teardown the same path over-decrements into a holder reference and ksmbd_fd_put() later UAFs that holder. * FP_NEW window. Between __open_id() publishing fp into the session idr and ksmbd_update_fstate(..., FP_INITED) committing the transition at the end of smb2_open(), an fp is in FP_NEW and an intervening teardown that takes a transient reference and unpublishes the volatile id leaves the original idr-owned reference orphaned -- the opener is unaware that fp has been unpublished, returns success to the client, and the fp leaks at refcount = 1. Refactor __close_file_table_ids() to take a transient reference on fp and unpublish fp from the session idr *under ft->lock* before calling skip() outside the lock. A transient ref protects lifetime but not concurrent field mutation, so the idr_remove() is what keeps __ksmbd_lookup_fd() through this session's idr from granting a new ksmbd_fp_get() reference to an fp whose fp->conn / fp->tcon / fp->volatile_id / op->conn / lock_list links are about to be rewritten by session_fd_check(). Durable reconnect is unaffected because it reaches fp through the global durable table (ksmbd_lookup_durable_fd -> global_ft). Decide n_to_drop together with any FP_INITED -> FP_CLOSED transition under ft->lock so teardown and ksmbd_close_fd() never both consume the idr-owned reference. See ksmbd_mark_fp_closed() for the per-state accounting. For the FP_NEW path to be safe, the opener has to learn that fp was unpublished: ksmbd_update_fstate() now returns -ENOENT when an FP_NEW -> FP_INITED transition finds f_state already advanced or the volatile id cleared (both committed by teardown under ft->lock); smb2_open() propagates that as STATUS_OBJECT_NAME_INVALID and drops the original reference via ksmbd_fd_put(). The list removal cannot be left for a deferred final putter because fp->volatile_id has already been cleared and __ksmbd_remove_fd() will intentionally skip both idr_remove() and list_del_init(). Move the m_fp_list unlink in __ksmbd_remove_fd() above the volatile-id check so that an FP_NEW fp that happened to be added to m_fp_list (smb2_open() adds fp->node before ksmbd_update_fstate() runs) is still cleaned up on the deferred putter path; list_del_init() on an empty node is a no-op and remains safe for fps that were never added. Add a defensive guard in session_fd_check() that refuses non-FP_INITED fps so that even if a teardown reaches an FP_NEW fp it falls into the close branch (where the n_to_drop = 1 accounting keeps the opener's reference alive) instead of the durable-preserve branch (which mutates fp->conn / fp->tcon). Validation on a debug kernel additionally built with CONFIG_DEBUG_LIST and CONFIG_DEBUG_OBJECTS_WORK used a same-session two-tcon workload (open/write storm on one tcon, 50 tree disconnects on the other) and reported no list-corruption, work_struct ODEBUG, sleep-in-atomic, lockdep or kmemleak reports. Reverting only the __close_file_table_ids() hunk while keeping a forced-is_reconnectable() harness produced the expected sleep-in-atomic at vfs_cache.c:1095, confirming the ft->lock-out-of-sleepable-skip discipline. KASAN-enabled direct SMB2 coverage with durable handles enabled exercised ksmbd_close_tree_conn_fds(), ksmbd_close_session_fds(), the FP_NEW failure path, tree_conn_fd_check(), and a non-zero session_fd_check() durable-preserve return. This produced no KASAN, DEBUG_LIST, ODEBUG, or WARNING reports. Fixes: f44158485826 ("cifsd: add file operations") Signed-off-by: DaeMyung Kang Acked-by: Namjae Jeon Signed-off-by: Steve French Signed-off-by: Namjae Jeon Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 6106fb7962a00ee990f7b6c8f212237c9a2bfc74) Signed-off-by: Wentao Guan --- fs/smb/server/smb2pdu.c | 6 +- fs/smb/server/vfs_cache.c | 179 +++++++++++++++++++++++++++++++++----- fs/smb/server/vfs_cache.h | 4 +- 3 files changed, 164 insertions(+), 25 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 7374422bfaf2c..fac188ab767b5 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3765,8 +3765,10 @@ int smb2_open(struct ksmbd_work *work) err_out2: if (!rc) { - ksmbd_update_fstate(&work->sess->file_table, fp, FP_INITED); - rc = ksmbd_iov_pin_rsp(work, (void *)rsp, iov_len); + rc = ksmbd_update_fstate(&work->sess->file_table, fp, + FP_INITED); + if (!rc) + rc = ksmbd_iov_pin_rsp(work, (void *)rsp, iov_len); } if (rc) { if (rc == -EINVAL) diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 51e37e89d1aa5..8b5f50ac61e2f 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -358,13 +358,13 @@ static void ksmbd_remove_durable_fd(struct ksmbd_file *fp) static void __ksmbd_remove_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp) { - if (!has_file_id(fp->volatile_id)) - return; - down_write(&fp->f_ci->m_lock); list_del_init(&fp->node); up_write(&fp->f_ci->m_lock); + if (!has_file_id(fp->volatile_id)) + return; + write_lock(&ft->lock); idr_remove(ft->idr, fp->volatile_id); write_unlock(&ft->lock); @@ -748,15 +748,58 @@ struct ksmbd_file *ksmbd_open_fd(struct ksmbd_work *work, struct file *filp) return ERR_PTR(ret); } -void ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, - unsigned int state) +/** + * ksmbd_update_fstate() - update an fp state under the file-table lock + * @ft: file table that publishes @fp's volatile id + * @fp: file pointer to update + * @state: new state + * + * Return: 0 on success. The FP_NEW -> FP_INITED transition is special: + * -ENOENT if teardown already unpublished @fp by advancing the state or + * clearing the volatile id. Other state updates preserve the historical + * fire-and-forget behavior. + */ +int ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, + unsigned int state) { + int ret; + if (!fp) - return; + return -ENOENT; write_lock(&ft->lock); - fp->f_state = state; + if (state == FP_INITED && + (fp->f_state != FP_NEW || !has_file_id(fp->volatile_id))) { + ret = -ENOENT; + } else { + fp->f_state = state; + ret = 0; + } write_unlock(&ft->lock); + + return ret; +} + +/* + * ksmbd_mark_fp_closed() - mark fp closed under ft->lock and return how many + * refs the teardown path owns. + * + * FP_INITED has a normal idr-owned reference, so teardown owns both that + * reference and the transient lookup reference. FP_NEW is still owned by the + * in-flight opener/reopener, which will drop the original reference after + * ksmbd_update_fstate(..., FP_INITED) observes the cleared volatile id. + * FP_CLOSED on entry means an earlier ksmbd_close_fd() already consumed the + * idr-owned ref. + */ +static int ksmbd_mark_fp_closed(struct ksmbd_file *fp) +{ + if (fp->f_state == FP_INITED) { + set_close_state_blocked_works(fp); + fp->f_state = FP_CLOSED; + return 2; + } + + return 1; } static int @@ -764,7 +807,8 @@ __close_file_table_ids(struct ksmbd_session *sess, struct ksmbd_tree_connect *tcon, bool (*skip)(struct ksmbd_tree_connect *tcon, struct ksmbd_file *fp, - struct ksmbd_user *user)) + struct ksmbd_user *user), + bool skip_preserves_fp) { struct ksmbd_file_table *ft = &sess->file_table; struct ksmbd_file *fp; @@ -772,32 +816,120 @@ __close_file_table_ids(struct ksmbd_session *sess, int num = 0; while (1) { + int n_to_drop; + write_lock(&ft->lock); fp = idr_get_next(ft->idr, &id); if (!fp) { write_unlock(&ft->lock); break; } - - if (skip(tcon, fp, sess->user) || - !atomic_dec_and_test(&fp->refcount)) { + if (!atomic_inc_not_zero(&fp->refcount)) { id++; write_unlock(&ft->lock); continue; } - set_close_state_blocked_works(fp); - idr_remove(ft->idr, fp->volatile_id); - fp->volatile_id = KSMBD_NO_FID; - write_unlock(&ft->lock); + if (skip_preserves_fp) { + /* + * Session teardown: skip() is session_fd_check(), + * which may sleep and mutates fp->conn / fp->tcon / + * fp->volatile_id when it chooses to preserve fp + * for durable reconnect. Unpublish fp from the + * session idr here, under ft->lock, so that + * __ksmbd_lookup_fd() through this session cannot + * grant a new ksmbd_fp_get() reference to an fp + * whose fields are about to be rewritten outside + * the lock. Durable reconnect still reaches fp via + * global_ft. + */ + idr_remove(ft->idr, id); + fp->volatile_id = KSMBD_NO_FID; + write_unlock(&ft->lock); + if (skip(tcon, fp, sess->user)) { + /* + * session_fd_check() has converted fp to + * durable-preserve state and cleared its + * per-conn fields. fp is already unpublished + * above; the original idr-owned ref keeps it + * alive for the durable scavenger. Drop only + * the transient ref. atomic_dec() is safe -- + * atomic_inc_not_zero() succeeded on a + * positive value and we added one more, so + * refcount cannot be zero here. + */ + atomic_dec(&fp->refcount); + id++; + continue; + } + + /* + * Keep the close-state decision under the same lock + * observed by ksmbd_update_fstate(), which is how an + * in-flight FP_NEW opener learns that teardown has + * cleared its volatile id. + */ + write_lock(&ft->lock); + n_to_drop = ksmbd_mark_fp_closed(fp); + write_unlock(&ft->lock); + } else { + /* + * Tree teardown: skip() is tree_conn_fd_check(), a + * cheap pointer compare that doesn't sleep and has + * no side effects, so keep the skip decision plus + * the unpublish-and-mark-closed sequence atomic + * under ft->lock. fps belonging to other tree + * connects (skip() == true) stay fully published in + * the session idr with no lock window. + */ + if (skip(tcon, fp, sess->user)) { + atomic_dec(&fp->refcount); + write_unlock(&ft->lock); + id++; + continue; + } + idr_remove(ft->idr, id); + fp->volatile_id = KSMBD_NO_FID; + n_to_drop = ksmbd_mark_fp_closed(fp); + write_unlock(&ft->lock); + } + + /* + * fp->volatile_id is already cleared to prevent stale idr + * removal from a deferred final close. Remove fp from + * m_fp_list here because __ksmbd_remove_fd() will skip the + * list unlink when volatile_id is KSMBD_NO_FID. + */ down_write(&fp->f_ci->m_lock); list_del_init(&fp->node); up_write(&fp->f_ci->m_lock); - __ksmbd_close_fd(ft, fp); - - num++; + /* + * Drop the references this iteration owns: + * + * n_to_drop == 2: we observed FP_INITED and committed + * the FP_CLOSED transition ourselves, so we own the + * transient (+1) and the still-intact idr-owned ref. + * + * n_to_drop == 1: either a prior ksmbd_close_fd() + * already consumed the idr-owned ref, or fp was still + * FP_NEW and the in-flight opener/reopener must keep + * the original reference until ksmbd_update_fstate() + * observes the cleared volatile id. + * + * If we end up as the final putter, finalize fp and + * account the open_files_count decrement via the caller's + * atomic_sub(num, ...). Otherwise the remaining user's + * ksmbd_fd_put() reaches __put_fd_final(), which does its + * own atomic_dec(&open_files_count), so we must not count + * this fp here -- doing so would double-decrement the + * connection-wide counter. + */ + if (atomic_sub_and_test(n_to_drop, &fp->refcount)) { + __ksmbd_close_fd(NULL, fp); + num++; + } id++; } @@ -1071,6 +1203,9 @@ static bool session_fd_check(struct ksmbd_tree_connect *tcon, if (!is_reconnectable(fp)) return false; + if (fp->f_state != FP_INITED) + return false; + if (WARN_ON_ONCE(!fp->conn)) return false; @@ -1122,7 +1257,8 @@ void ksmbd_close_tree_conn_fds(struct ksmbd_work *work) { int num = __close_file_table_ids(work->sess, work->tcon, - tree_conn_fd_check); + tree_conn_fd_check, + false); atomic_sub(num, &work->conn->stats.open_files_count); } @@ -1131,7 +1267,8 @@ void ksmbd_close_session_fds(struct ksmbd_work *work) { int num = __close_file_table_ids(work->sess, work->tcon, - session_fd_check); + session_fd_check, + true); atomic_sub(num, &work->conn->stats.open_files_count); } @@ -1271,7 +1408,7 @@ void ksmbd_destroy_file_table(struct ksmbd_session *sess) if (!ft->idr) return; - __close_file_table_ids(sess, NULL, session_fd_check); + __close_file_table_ids(sess, NULL, session_fd_check, true); idr_destroy(ft->idr); kfree(ft->idr); ft->idr = NULL; diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 10f4172ec8017..a3a9fda6de917 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -175,8 +175,8 @@ int ksmbd_close_inode_fds(struct ksmbd_work *work, struct inode *inode); int ksmbd_init_global_file_table(void); void ksmbd_free_global_file_table(void); void ksmbd_set_fd_limit(unsigned long limit); -void ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, - unsigned int state); +int ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, + unsigned int state); bool ksmbd_vfs_compare_durable_owner(struct ksmbd_file *fp, struct ksmbd_user *user); From aab12f62762c37e4ffead250ec066aaf2e83c908 Mon Sep 17 00:00:00 2001 From: Griffin Kroah-Hartman Date: Mon, 6 Jul 2026 16:58:21 +0200 Subject: [PATCH 22/76] fpga: dfl: fme: add error handling commit b5ba63e247075087ab8a6a087622c762dc4172e9 upstream. Add error handling to devm_kasprint in fme_perf_pmu_register(). Assisted-by: gkh_clanker_2000 Fixes: 724142f8c42a ("fpga: dfl: fme: add performance reporting support") Cc: stable@kernel.org Cc: Xu Yilun Cc: Tom Rix Cc: Moritz Fischer Signed-off-by: Griffin Kroah-Hartman Signed-off-by: Greg Kroah-Hartman [ Yilun: Fix stable tag, add Fixes tag ] Reviewed-by: Xu Yilun Link: https://lore.kernel.org/r/2026070620-unwired-clay-f6cc@gregkh Signed-off-by: Xu Yilun Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 8ec7271e05df7f7aef6ff8f1c8cb1848124d123f) Signed-off-by: Wentao Guan --- drivers/fpga/dfl-fme-perf.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/fpga/dfl-fme-perf.c b/drivers/fpga/dfl-fme-perf.c index 7422d2bc6f374..db56d52411efc 100644 --- a/drivers/fpga/dfl-fme-perf.c +++ b/drivers/fpga/dfl-fme-perf.c @@ -925,6 +925,8 @@ static int fme_perf_pmu_register(struct platform_device *pdev, PERF_PMU_CAP_NO_EXCLUDE; name = devm_kasprintf(priv->dev, GFP_KERNEL, "dfl_fme%d", pdev->id); + if (!name) + return -ENOMEM; ret = perf_pmu_register(pmu, name, -1); if (ret) From d4f8356d6723333676998e70b262ede9dc57acc7 Mon Sep 17 00:00:00 2001 From: Haoxiang Li Date: Mon, 1 Jun 2026 01:08:04 +0200 Subject: [PATCH 23/76] accessibility: speakup: unregister tty ldisc on later init failures commit a76acbaec9b8fd74413646984d2e3626d0543e39 upstream. The ldisc registration is intentionally non-fatal, since some synth drivers do not use tty/ldisc. However, once speakup_init() continues past the registration point and later fails, the init unwind path should mirror speakup_exit() and call spk_ttyio_unregister_ldisc(). Add the missing unregister call to the error path after synth_release(), matching the normal module exit cleanup order. Signed-off-by: Haoxiang Li Signed-off-by: Samuel Thibault Fixes: e23a9b439ce9 ("staging: speakup: safely register and unregister ldisc") Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260531230804.254962-16-samuel.thibault@ens-lyon.org Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 9786c42df8efbaa524955d5abc6ec72b74da446b) Signed-off-by: Wentao Guan --- drivers/accessibility/speakup/main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c index e68cf1d83787f..afd1bf9e3a840 100644 --- a/drivers/accessibility/speakup/main.c +++ b/drivers/accessibility/speakup/main.c @@ -2444,6 +2444,7 @@ static int __init speakup_init(void) mutex_lock(&spk_mutex); synth_release(); mutex_unlock(&spk_mutex); + spk_ttyio_unregister_ldisc(); speakup_kobj_exit(); error_kobjects: From 62203d8ce5a79228432ac3baea001e1fd0ed2266 Mon Sep 17 00:00:00 2001 From: Michal Pecio Date: Thu, 6 Aug 2026 17:21:13 +0300 Subject: [PATCH 24/76] usb: xhci: Handle bogus TRB pointers in Missed Service Error events commit 3d9eeb336131bc5a174367c384fa00c15c8744fd upstream. xHCI 1.0 allowed these pointers to be zero. Some Intel chipsets from the era usually set it to zero, but sometimes (apparently) to the next TRB after the one referenced by the previous transfer event on the endpoint. Usually that's indeed the missed TD, but it may also be the last TRB of a two-TRB TD already completed with Short Packet on its first TRB. Then the driver skips all pending TDs, failing to find a match. When handling Missed Service Error, scan TD list twice and only really skip TDs in the second pass if the first pass found a match. This won't catch bogus pointers to wrong TDs, but such a bug would be practically impossible to detect automatically and isn't known to exist. Reported-by: Bart Nagel Closes: https://lore.kernel.org/linux-usb/al_hchyOdPoPWKEo@spiral/ Suggested-by: Mathias Nyman Fixes: d0b619599e52 ("usb: xhci: Expedite skipping missed isoch TDs on modern HCs") Cc: stable@vger.kernel.org Signed-off-by: Michal Pecio Signed-off-by: Mathias Nyman Link: https://patch.msgid.link/20260806142113.2436238-18-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 56f20a406cc3b6159956c60f95d075ec2322ba36) Signed-off-by: Wentao Guan --- drivers/usb/host/xhci-ring.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 2bb7569c95054..58cd8967b3df5 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -2653,6 +2653,17 @@ static bool xhci_spurious_success_tx_event(struct xhci_hcd *xhci, } } +static struct xhci_td *find_td_by_dma(struct xhci_ring *ep_ring, dma_addr_t dma) +{ + struct xhci_td *td; + + if (dma) + list_for_each_entry(td, &ep_ring->td_list, td_list) + if (trb_in_td(td, dma)) + return td; + return NULL; +} + /* * If this function returns an error condition, it means it got a Transfer * event with a corrupted Slot ID, Endpoint ID, or TRB DMA address. @@ -2845,8 +2856,11 @@ static int handle_tx_event(struct xhci_hcd *xhci, xhci_dequeue_td(xhci, td, ep_ring, td->status); } - /* If the TRB pointer is NULL, missed TDs will be skipped on the next event */ - if (trb_comp_code == COMP_MISSED_SERVICE_ERROR && !ep_trb_dma) + /* + * We don't know how many TDs were missed when ep_trb_dma is zero (as permitted by + * xHCI 1.0) or bogus. Bail out leaving ep->skip set, next event will sort it out. + */ + if (trb_comp_code == COMP_MISSED_SERVICE_ERROR && !find_td_by_dma(ep_ring, ep_trb_dma)) return 0; if (list_empty(&ep_ring->td_list)) { From 32482472eab52f846433f1e75bb021c38858919b Mon Sep 17 00:00:00 2001 From: Semih Baskan Date: Thu, 6 Aug 2026 17:21:12 +0300 Subject: [PATCH 25/76] usb: xhci: Handle USB3 port events when there is one roothub commit 3e91ec3e7d80a327fb558207613c80415d3bf756 upstream. handle_port_status() drops every USB3 port event when xhci->shared_hcd is NULL. The check dates from a time when xhci-plat always created a shared hcd, so a NULL one could only mean the hcd had been removed. Since commit 4736ebd7fcaf ("usb: host: xhci-plat: omit shared hcd if either root hub has no ports") that is no longer true. A controller whose USB2 root hub has no ports gets a single roothub, the USB3 rhub is served by the main hcd, and shared_hcd stays NULL for the lifetime of the device. Every SuperSpeed port event is then thrown away as bogus behind a debug message, so devices never enumerate even though the port sees the device and its change bits stay set: 0x006a1203 Powered Connected Enabled Link:U0 PortSpeed:4 Change: CSC WRC PRC PLC Broadcom Northstar is such a controller. USB3 works there up to 5.15 and stops working from 5.19 onwards. Ask xhci_get_usb3_hcd() instead. It returns the shared hcd when there is one, the main hcd when the USB2 root hub has no ports, and NULL once the shared hcd is gone, which keeps the original meaning of the check. Tested on an Asus RT-N18U (BCM47081), which has a single roothub. Before the change nothing enumerates on the USB3 port; after it SuperSpeed devices enumerate normally over repeated connect and disconnect cycles, the change bits shown above clear, and USB2 is unaffected on both ports. Fixes: 4736ebd7fcaf ("usb: host: xhci-plat: omit shared hcd if either root hub has no ports") Cc: stable@vger.kernel.org Signed-off-by: Semih Baskan Signed-off-by: Mathias Nyman Link: https://patch.msgid.link/20260806142113.2436238-17-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 45dbddc389c59c0fc6cac45fea8fe816ffe040f5) Signed-off-by: Wentao Guan --- drivers/usb/host/xhci-ring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 58cd8967b3df5..26d72b4e11ce6 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -2026,7 +2026,7 @@ static void handle_port_status(struct xhci_hcd *xhci, union xhci_trb *event) vdev = xhci->devs[port->slot_id]; /* We might get interrupts after shared_hcd is removed */ - if (port->rhub == &xhci->usb3_rhub && xhci->shared_hcd == NULL) { + if (port->rhub == &xhci->usb3_rhub && xhci_get_usb3_hcd(xhci) == NULL) { xhci_dbg(xhci, "ignore port event for removed USB3 hcd\n"); bogus_port_status = true; goto cleanup; From 36c3d9134725de9327d97d42da560a4487716ae9 Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Thu, 6 Aug 2026 17:21:03 +0300 Subject: [PATCH 26/76] xhci: dbgtty: Fix unregister on tty_register_driver() failure commit a916fa66a43e10f63198b6ce978badffc678821a upstream. If tty_register_driver() fails, it drops the reference, but fails to set the global dbc_tty_driver to NULL, causing the unregister to be called again when module exits. On module unload dbc_tty_exit() only gates its cleanup on the driver pointer being non-NULL, so it operates on the already-freed driver: module_init(xhci_hcd_init) xhci_hcd_init() xhci_dbc_init() [return value ignored] dbc_tty_init() tty_register_driver() fails tty_driver_kref_put() -> driver freed (dbc_tty_driver left dangling) ... module_exit(xhci_hcd_fini) xhci_hcd_fini() xhci_dbc_exit() dbc_tty_exit() if (dbc_tty_driver) -> true (dangling) tty_unregister_driver() -> use-after-free Fixes: 4521f1613940 ("xhci: dbctty: split dbc tty driver registration and unregistration functions.") Cc: stable@vger.kernel.org # v5.10 Cc: Mathias Nyman Cc: Greg Kroah-Hartman Signed-off-by: Lucas De Marchi Signed-off-by: Mathias Nyman Link: https://patch.msgid.link/20260806142113.2436238-8-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 0d0faf3cc44c4d86fc6faf5cea972c0fbe00b922) Signed-off-by: Wentao Guan --- drivers/usb/host/xhci-dbgtty.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/host/xhci-dbgtty.c b/drivers/usb/host/xhci-dbgtty.c index 90282e51e23ec..d42535ef1978b 100644 --- a/drivers/usb/host/xhci-dbgtty.c +++ b/drivers/usb/host/xhci-dbgtty.c @@ -651,6 +651,7 @@ int dbc_tty_init(void) pr_err("Can't register dbc tty driver\n"); tty_driver_kref_put(dbc_tty_driver); idr_destroy(&dbc_tty_minors); + dbc_tty_driver = NULL; } return ret; From fd2d2e70597a6db44804372109e9c4570609e96c Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Thu, 6 Aug 2026 17:21:04 +0300 Subject: [PATCH 27/76] xhci: dbgtty: Fix unregister on tty_alloc_driver() failure commit 25b8dfc13495a6c1cf4abacc8ef20196c7f20e5c upstream. Make sure to set dbc_tty_driver to NULL to match the check in dbc_tty_exit(). For that, make detached error handling path common to the other branch in the same function. Fixes: 4521f1613940 ("xhci: dbctty: split dbc tty driver registration and unregistration functions.") Cc: stable@vger.kernel.org # v5.10 Cc: Mathias Nyman Cc: Greg Kroah-Hartman Signed-off-by: Lucas De Marchi Signed-off-by: Mathias Nyman Link: https://patch.msgid.link/20260806142113.2436238-9-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 0f127d522dbcb5f68b6bf09682eed1b92ea7b737) Signed-off-by: Wentao Guan --- drivers/usb/host/xhci-dbgtty.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/usb/host/xhci-dbgtty.c b/drivers/usb/host/xhci-dbgtty.c index d42535ef1978b..fda5ccaba27a9 100644 --- a/drivers/usb/host/xhci-dbgtty.c +++ b/drivers/usb/host/xhci-dbgtty.c @@ -628,8 +628,8 @@ int dbc_tty_init(void) dbc_tty_driver = tty_alloc_driver(64, TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV); if (IS_ERR(dbc_tty_driver)) { - idr_destroy(&dbc_tty_minors); - return PTR_ERR(dbc_tty_driver); + ret = PTR_ERR(dbc_tty_driver); + goto fail; } dbc_tty_driver->driver_name = "dbc_serial"; @@ -649,11 +649,17 @@ int dbc_tty_init(void) ret = tty_register_driver(dbc_tty_driver); if (ret) { pr_err("Can't register dbc tty driver\n"); - tty_driver_kref_put(dbc_tty_driver); - idr_destroy(&dbc_tty_minors); - dbc_tty_driver = NULL; + goto fail_put; } + return ret; + +fail_put: + tty_driver_kref_put(dbc_tty_driver); +fail: + idr_destroy(&dbc_tty_minors); + dbc_tty_driver = NULL; + return ret; } From 4df88bebd698108d41509491cd41636aa6d654c6 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Mon, 17 Aug 2026 23:18:00 +0800 Subject: [PATCH 28/76] fuse: fix invalidate lock leak on setattr writeback failure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 9afeca0d569c9fc89d758fe7a9339d1e8afb1546 upstream. fuse_do_setattr() takes filemap_invalidate_lock() for a DAX truncate (fault_blocked = true) and releases it at the out:/error: labels. But when a writeback flush is also needed, a write_inode_now() failure returns directly and leaks the lock, so any later fault or truncate on the file stalls on the stale rwsem. For example, truncate(2) on a setuid file reaches fuse_do_setattr() with both ATTR_SIZE and ATTR_MODE set: truncate(2) └─ do_truncate() ├─ dentry_needs_remove_privs() # S_ISUID └─ notify_change() # KILL_SUID -> ATTR_MODE └─ fuse_setattr() # no killpriv: │ # ia_valid |= ATTR_MODE └─ fuse_do_setattr() ├─ filemap_invalidate_lock() # IS_DAX && is_truncate └─ write_inode_now() # is_wb && ATTR_MODE └─ if (err) # e.g. daemon -> -EIO return err # <- lock leaked Fix this by adding an unlock label that releases the lock before returning the error, and use it for the fuse_dax_break_layouts() failure path as well. Fixes: 6ae330cad6ef ("virtiofs: serialize truncate/punch_hole and dax fault path") Cc: stable@vger.kernel.org # v5.10+ Signed-off-by: Baokun Li Signed-off-by: Miklos Szeredi Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 1758730d9eaa3c06cf415c3446d9f6eed9ed3eed) Signed-off-by: Wentao Guan --- fs/fuse/dir.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 1bc6982b5d6aa..a013fad843b2c 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1976,10 +1976,8 @@ int fuse_do_setattr(struct mnt_idmap *idmap, struct dentry *dentry, filemap_invalidate_lock(mapping); fault_blocked = true; err = fuse_dax_break_layouts(inode, 0, -1); - if (err) { - filemap_invalidate_unlock(mapping); - return err; - } + if (err) + goto unlock; } if (attr->ia_valid & ATTR_OPEN) { @@ -2006,7 +2004,7 @@ int fuse_do_setattr(struct mnt_idmap *idmap, struct dentry *dentry, ATTR_TIMES_SET)) { err = write_inode_now(inode, true); if (err) - return err; + goto unlock; fuse_set_nowrite(inode); fuse_release_nowrite(inode); @@ -2114,6 +2112,7 @@ int fuse_do_setattr(struct mnt_idmap *idmap, struct dentry *dentry, clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); +unlock: if (fault_blocked) filemap_invalidate_unlock(mapping); return err; From dc3d892dae30b79a8c038bdf3a216ae19e87ece0 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Mon, 17 Aug 2026 23:18:01 +0800 Subject: [PATCH 29/76] fuse: fix invalidate lock leak on open O_TRUNC DAX failure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit a927f1867e61b78f39f9da0bbba3c98c2ca151fe upstream. fuse_open() takes filemap_invalidate_lock() for a DAX truncate (dax_truncate = true) and releases it before the out_inode_unlock label. But when fuse_dax_break_layouts() fails, the goto out_inode_unlock skips the unlock and leaks the rwsem, so any later fault or truncate on the file stalls on the stale lock. fuse_dax_break_layouts() can fail with -ERESTARTSYS when a signal interrupts the wait for busy DAX pages to drain: open("file", O_RDWR | O_TRUNC) └─ fuse_open() ├─ filemap_invalidate_lock() # dax_truncate └─ fuse_dax_break_layouts() └─ dax_break_layout() └─ wait_page_idle() # TASK_INTERRUPTIBLE └─ fuse_wait_dax_page() # unlock, schedule, re-lock └─ signal → -ERESTARTSYS goto out_inode_unlock # <- lock leaked Fix this by moving filemap_invalidate_unlock() below the label so that all error paths release the lock, and rename the label to out_unlock as it now covers more than just the inode lock. Fixes: 2fdbb8dd0155 ("fuse: fix deadlock between atomic O_TRUNC and page invalidation") Cc: stable@vger.kernel.org # v6.0+ Signed-off-by: Baokun Li Signed-off-by: Miklos Szeredi Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 776e85fda752f9a15e0f82dec42ecacd12a9bd94) Signed-off-by: Wentao Guan --- fs/fuse/file.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 585dd90361b65..c581cd1df3e27 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -268,7 +268,7 @@ static int fuse_open(struct inode *inode, struct file *file) filemap_invalidate_lock(inode->i_mapping); err = fuse_dax_break_layouts(inode, 0, -1); if (err) - goto out_inode_unlock; + goto out_unlock; } if (is_wb_truncate || dax_truncate) @@ -292,9 +292,9 @@ static int fuse_open(struct inode *inode, struct file *file) else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) invalidate_inode_pages2(inode->i_mapping); } +out_unlock: if (dax_truncate) filemap_invalidate_unlock(inode->i_mapping); -out_inode_unlock: if (is_wb_truncate || dax_truncate) inode_unlock(inode); From 9eab59ea348e8d8b38fd0a948b06cb44fc6a4aad Mon Sep 17 00:00:00 2001 From: Aleksandr Nogikh Date: Thu, 6 Aug 2026 15:26:51 +0000 Subject: [PATCH 30/76] usb: usbtest: disable dynamic ID support commit 00e2071f6d5621a5ddea311a5e6b143ae6e474af upstream. The usbtest driver relies on the driver_info field of struct usb_device_id to point to a valid struct usbtest_info descriptor. This structure contains essential test configurations, such as endpoint addresses and test modes, which are required during probe. When a user dynamically adds a new device ID via the sysfs new_id interface without specifying a reference device, the USB core initializes driver_info to 0 (NULL). When a matching device is subsequently probed, usbtest_probe() unconditionally casts driver_info to a struct usbtest_info pointer and dereferences it, leading to a NULL pointer dereference crash: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] SMP KASAN NOPTI KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] RIP: 0010:usbtest_probe+0x3b9/0x1280 drivers/usb/misc/usbtest.c:2822 Because usbtest strictly requires pre-defined usbtest_info descriptors to function, dynamic ID binding via sysfs is fundamentally unsupported for this driver. Fix this by setting .no_dynamic_id = 1 on usbtest_driver. This instructs the USB core to skip creating the new_id and remove_id sysfs interfaces for usbtest, preventing invalid dynamic ID entries from being created. Cc: stable@vger.kernel.org Reported-by: syzbot+7e1e5911f9eac50bedc7@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=7e1e5911f9eac50bedc7 Signed-off-by: Aleksandr Nogikh Tested-by: syzbot@syzkaller.appspotmail.com Link: https://patch.msgid.link/20260806152651.2370795-1-nogikh@google.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 3f6face69034f56c3327c5e1087a187380eac922) Signed-off-by: Wentao Guan --- drivers/usb/misc/usbtest.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c index 5c92c8d8e2833..a015fbe4fc359 100644 --- a/drivers/usb/misc/usbtest.c +++ b/drivers/usb/misc/usbtest.c @@ -3054,6 +3054,7 @@ static struct usb_driver usbtest_driver = { .disconnect = usbtest_disconnect, .suspend = usbtest_suspend, .resume = usbtest_resume, + .no_dynamic_id = 1, }; /*-------------------------------------------------------------------------*/ From eb820aee1c5b0f606d5ce5b2f7ab8181bec4011c Mon Sep 17 00:00:00 2001 From: Shuangpeng Bai Date: Fri, 7 Aug 2026 02:07:33 -0400 Subject: [PATCH 31/76] usb: gadget: f_tcm: keep port count until LUN teardown completes commit c39d0916da47d94909391876c9e5bd429ea7b1b9 upstream. tcm_usbg_drop_nexus() permits session removal once tpg_port_count reaches zero. However, usbg_port_unlink() currently decrements that count from the fabric_pre_unlink() callback, before core_dev_del_lun() waits for active se_lun references to drain. If removal of the last LUN races a nexus removal, the latter can observe a zero port count and call target_remove_session(). This frees sess_cmd_map while an in-flight struct usbg_cmd, including its work item, can still be accessed. Overlapping the last-LUN unlink with nexus removal reproduces this lifetime violation as a DEBUG_OBJECTS "free active" warning for usbg_cmd_work, followed by a target-core BUG/Oops. The generic target-core unlink path has no callback after core_dev_del_lun() completes. Add an optional fabric_post_unlink() callback and use it for the f_tcm port count. The count now remains nonzero until core_dev_del_lun() has finished draining active LUN references, preventing nexus removal from freeing the session during command completion. Fixes: c52661d60f63 ("usb-gadget: Initial merge of target module for UASP + BOT") Cc: stable@vger.kernel.org Signed-off-by: Shuangpeng Bai Link: https://patch.msgid.link/20260807060733.3186624-1-shuangpeng.kernel@gmail.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 85aa61fedcb4eb13f3dc5db73f6dc359f41f5d95) Signed-off-by: Wentao Guan --- drivers/target/target_core_fabric_configfs.c | 8 ++++++++ drivers/usb/gadget/function/f_tcm.c | 2 +- include/target/target_core_fabric.h | 2 ++ 3 files changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index 7156a4dc1ca7d..15172e993be7c 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -690,6 +690,14 @@ static void target_fabric_port_unlink( } core_dev_del_lun(se_tpg, lun); + + if (tf->tf_ops->fabric_post_unlink) { + /* + * Allow fabrics to release state that must remain valid until + * core_dev_del_lun() has drained all active LUN references. + */ + tf->tf_ops->fabric_post_unlink(se_tpg, lun); + } } static void target_fabric_port_release(struct config_item *item) diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c index 5753c83f55784..09d72bb4f8550 100644 --- a/drivers/usb/gadget/function/f_tcm.c +++ b/drivers/usb/gadget/function/f_tcm.c @@ -2023,7 +2023,7 @@ static const struct target_core_fabric_ops usbg_ops = { .fabric_enable_tpg = usbg_enable_tpg, .fabric_drop_tpg = usbg_drop_tpg, .fabric_post_link = usbg_port_link, - .fabric_pre_unlink = usbg_port_unlink, + .fabric_post_unlink = usbg_port_unlink, .fabric_init_nodeacl = usbg_init_nodeacl, .tfc_wwn_attrs = usbg_wwn_attrs, diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index 3378ff9ee271c..7c85ca01c3f82 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -95,6 +95,8 @@ struct target_core_fabric_ops { struct se_lun *); void (*fabric_pre_unlink)(struct se_portal_group *, struct se_lun *); + void (*fabric_post_unlink)(struct se_portal_group *se_tpg, + struct se_lun *lun); struct se_tpg_np *(*fabric_make_np)(struct se_portal_group *, struct config_group *, const char *); void (*fabric_drop_np)(struct se_tpg_np *); From 48e166986f5bd3b93b8b3bb93184720ee5c68144 Mon Sep 17 00:00:00 2001 From: Pankaj Gupta Date: Wed, 15 Jul 2026 01:36:26 -0500 Subject: [PATCH 32/76] KVM: SEV: Drop FOLL_WRITE for encrypted region registration commit ee1a586dd1fa2f245b3b753a3e44d9263a49240b upstream. When pinning SEV guest memory, drop FOLL_WRITE and rely on FOLL_LONGTERM to break CoW, as *KVM* doesn't actually to the memory using the GUP'd pages. Omitting FOLL_WRITE fixes a regression when using file-backed guest memory that was introduced when KVM (correctly) added FOLL_LONG (e.g. to ensure anonymous memory is migrated out of MIGRATE_CMA/ZONE_MOVABLE before a long term pin). Unfortunately, as of commits: 8ac268436e6d ("mm/gup: disallow FOLL_LONGTERM GUP-nonfast writing to file-backed mappings") a6e79df92e4a ("mm/gup: disallow FOLL_LONGTERM GUP-fast writing to file-backed mappings") GUP uses FOLL_LONGTERM as a canary of sorts to detect pins that are likely to be problematic, and disallows WRITE+LONGTERM pins for file-backed memory. As a result, backing SEV+ guests with file-backed memory, e.g. virtio-pmem, fails due to the disallowed FOLL_LONGTERM+FOLL_WRITE combination. Note, in the past, FOLL_WRITE was required to trigger CoW unsharing, to prevent replacing the page in the (primary MMU's) page tables during a later write fault after already having pinned a (shared) page in MAP_PRIVATE mappings. FOLL_LONGTERM does that nowadays, even without FOLL_WRITE (see gup_must_unshare()). Fixes: 7e066cb9b71a ("KVM: SEV: Use long-term pin when registering encrypted memory regions") Cc: stable@vger.kernel.org Suggested-by: "David Hildenbrand (Arm)" Link: https://lore.kernel.org/all/ad784f05-b36c-4e91-9f17-4c5b826735d0@kernel.org/ Signed-off-by: Pankaj Gupta Acked-by: David Hildenbrand (Arm) Acked-by: Lorenzo Stoakes (ARM) Link: https://patch.msgid.link/20260715063626.65899-1-pankaj.gupta@amd.com [sean: massage changelog, add comment about CoW unsharing] Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman (cherry picked from commit dd1638c95163d394d69bda2d93f70d20ea6371c4) Signed-off-by: Wentao Guan --- arch/x86/kvm/svm/sev.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index ff07e31d175f7..6d4f5e6a937d8 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2844,8 +2844,12 @@ int sev_mem_enc_register_region(struct kvm *kvm, if (!region) return -ENOMEM; + /* + * Do NOT specify FOLL_WRITE, as KVM isn't using the pinned pages to + * write memory, and FOLL_LONGTERM itself triggers CoW unshare. + */ region->pages = sev_pin_memory(kvm, range->addr, range->size, ®ion->npages, - FOLL_WRITE | FOLL_LONGTERM); + FOLL_LONGTERM); if (IS_ERR(region->pages)) { ret = PTR_ERR(region->pages); goto e_free; From c86107fbc52370de165b14f45af43a99e4e0349f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 9 Jul 2026 13:49:31 -0700 Subject: [PATCH 33/76] KVM: SEV: Track the GPA of the guest-controlled VMSA used for SNP guests commit 42a39ad5d592aec87a70527a4e694f6210694482 upstream. Track the GPA of the guest-provided VMSA used after AP_CREATION events when running SNP guests, instead of simply tracking whether or not the vCPU is using a guest-provided VMSA. KVM needs to know the GPA of the VMSA that's actively being used so that it can react to MMU invalidation events, i.e. so that KVM can drop the VMSA if its backing guest_memfd page is punched out of existence. Opportunistically rename snp_vmsa_gpa to clarify that it tracks the pending VMSA GPA, whereas snp_guest_vmsa_gpa now tracks the in-use VMSA GPA. Note! Take care to track the GPA, not the GFN, as VALID_PAGE() won't behave correctly if an invalid GFN is converted to a GPA for checking. Note #2! Keep snp_has_guest_vmsa so that switching to a guest-provided VMSA is sticky, even if the guest-provided VMSA becomes invalid. No functional change intended. Cc: stable@vger.kernel.org # 6.12.x Reviewed-by: Michael Roth Link: https://patch.msgid.link/20260709204948.1988414-2-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 2de20fea620430da99f7326a7b02121d2aed3c02) Signed-off-by: Wentao Guan --- arch/x86/kvm/svm/sev.c | 14 +++++++++----- arch/x86/kvm/svm/svm.h | 3 ++- 2 files changed, 11 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 6d4f5e6a937d8..c4508b287178f 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -4227,6 +4227,7 @@ static void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) /* Clear use of the VMSA */ svm->vmcb->control.vmsa_pa = INVALID_PAGE; + svm->sev_es.snp_guest_vmsa_gpa = INVALID_PAGE; /* * When replacing the VMSA during SEV-SNP AP creation, @@ -4234,11 +4235,11 @@ static void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) */ vmcb_mark_all_dirty(svm->vmcb); - if (!VALID_PAGE(svm->sev_es.snp_vmsa_gpa)) + if (!VALID_PAGE(svm->sev_es.snp_pending_vmsa_gpa)) return; - gfn = gpa_to_gfn(svm->sev_es.snp_vmsa_gpa); - svm->sev_es.snp_vmsa_gpa = INVALID_PAGE; + gfn = gpa_to_gfn(svm->sev_es.snp_pending_vmsa_gpa); + svm->sev_es.snp_pending_vmsa_gpa = INVALID_PAGE; slot = gfn_to_memslot(vcpu->kvm, gfn); if (!slot) @@ -4263,6 +4264,7 @@ static void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) svm->sev_es.snp_has_guest_vmsa = true; /* Use the new VMSA */ + svm->sev_es.snp_guest_vmsa_gpa = gfn_to_gpa(gfn); svm->vmcb->control.vmsa_pa = pfn_to_hpa(pfn); /* Mark the vCPU as runnable */ @@ -4329,10 +4331,10 @@ static int sev_snp_ap_creation(struct vcpu_svm *svm) return -EINVAL; } - target_svm->sev_es.snp_vmsa_gpa = svm->vmcb->control.exit_info_2; + target_svm->sev_es.snp_pending_vmsa_gpa = svm->vmcb->control.exit_info_2; break; case SVM_VMGEXIT_AP_DESTROY: - target_svm->sev_es.snp_vmsa_gpa = INVALID_PAGE; + target_svm->sev_es.snp_pending_vmsa_gpa = INVALID_PAGE; break; default: vcpu_unimpl(vcpu, "vmgexit: invalid AP creation request [%#x] from guest\n", @@ -4926,6 +4928,8 @@ int sev_vcpu_create(struct kvm_vcpu *vcpu) } svm->sev_es.vmsa = page_address(vmsa_page); + svm->sev_es.snp_pending_vmsa_gpa = INVALID_PAGE; + svm->sev_es.snp_guest_vmsa_gpa = INVALID_PAGE; vcpu->arch.guest_tsc_protected = snp_is_secure_tsc_enabled(vcpu->kvm); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 1d0cc7c0552ec..72fcd1f09b9b0 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -248,7 +248,8 @@ struct vcpu_sev_es_state { u64 ghcb_registered_gpa; struct mutex snp_vmsa_mutex; /* Used to handle concurrent updates of VMSA. */ - gpa_t snp_vmsa_gpa; + gpa_t snp_pending_vmsa_gpa; + gpa_t snp_guest_vmsa_gpa; bool snp_ap_waiting_for_reset; bool snp_has_guest_vmsa; #ifdef CONFIG_HYGON_CSV From 78711cb60df1a6938f4a77eadf0b7670aa914ffe Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 9 Jul 2026 13:49:32 -0700 Subject: [PATCH 34/76] KVM: SEV: Extract loading of guest-provided VMSA to a separate helper commit 0060569e4f18a7dee2dd8728595e909f19a23c24 upstream. Extract the loading/retrieval of a guest-provided VMSA to a separate helper so that KVM can reuse the core logic when refreshing the VMSA after an MMU invalidation from guest_memfd. No functional change intended. Cc: stable@vger.kernel.org # 6.12.x Reviewed-by: Michael Roth Link: https://patch.msgid.link/20260709204948.1988414-3-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman (cherry picked from commit a3d45c2d645c6701e322ce7bb351b917d4436d9b) Signed-off-by: Wentao Guan --- arch/x86/kvm/svm/sev.c | 52 +++++++++++++++++++++++++----------------- 1 file changed, 31 insertions(+), 21 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index c4508b287178f..c51b7d6c291f2 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -4203,29 +4203,17 @@ static int snp_begin_psc(struct vcpu_svm *svm) BUG(); } -/* - * Invoked as part of svm_vcpu_reset() processing of an init event. - */ -static void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) +static void sev_snp_reload_vmsa(struct kvm_vcpu *vcpu, gpa_t gpa) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_memory_slot *slot; + gfn_t gfn = gpa_to_gfn(gpa); struct page *page; kvm_pfn_t pfn; - gfn_t gfn; - - guard(mutex)(&svm->sev_es.snp_vmsa_mutex); - - if (!svm->sev_es.snp_ap_waiting_for_reset) - return; - svm->sev_es.snp_ap_waiting_for_reset = false; - - /* Mark the vCPU as offline and not runnable */ - vcpu->arch.pv.pv_unhalted = false; - kvm_set_mp_state(vcpu, KVM_MP_STATE_HALTED); + lockdep_assert_held(&svm->sev_es.snp_vmsa_mutex); - /* Clear use of the VMSA */ + /* Clear use of the VMSA. */ svm->vmcb->control.vmsa_pa = INVALID_PAGE; svm->sev_es.snp_guest_vmsa_gpa = INVALID_PAGE; @@ -4235,12 +4223,9 @@ static void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) */ vmcb_mark_all_dirty(svm->vmcb); - if (!VALID_PAGE(svm->sev_es.snp_pending_vmsa_gpa)) + if (!VALID_PAGE(gpa)) return; - gfn = gpa_to_gfn(svm->sev_es.snp_pending_vmsa_gpa); - svm->sev_es.snp_pending_vmsa_gpa = INVALID_PAGE; - slot = gfn_to_memslot(vcpu->kvm, gfn); if (!slot) return; @@ -4264,7 +4249,7 @@ static void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) svm->sev_es.snp_has_guest_vmsa = true; /* Use the new VMSA */ - svm->sev_es.snp_guest_vmsa_gpa = gfn_to_gpa(gfn); + svm->sev_es.snp_guest_vmsa_gpa = gpa; svm->vmcb->control.vmsa_pa = pfn_to_hpa(pfn); /* Mark the vCPU as runnable */ @@ -4278,6 +4263,31 @@ static void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) kvm_release_page_clean(page); } +/* + * Invoked as part of svm_vcpu_reset() processing of an init event. + */ +static void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + gpa_t gpa; + + guard(mutex)(&svm->sev_es.snp_vmsa_mutex); + + if (!svm->sev_es.snp_ap_waiting_for_reset) + return; + + svm->sev_es.snp_ap_waiting_for_reset = false; + + /* Mark the vCPU as offline and not runnable */ + vcpu->arch.pv.pv_unhalted = false; + kvm_set_mp_state(vcpu, KVM_MP_STATE_HALTED); + + gpa = svm->sev_es.snp_pending_vmsa_gpa; + svm->sev_es.snp_pending_vmsa_gpa = INVALID_PAGE; + + sev_snp_reload_vmsa(vcpu, gpa); +} + static int sev_snp_ap_creation(struct vcpu_svm *svm) { struct kvm_sev_info *sev = to_kvm_sev_info(svm->vcpu.kvm); From 7cbfb9d0c319fc76f623f7fd5b7a2bc5acb4471c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 9 Jul 2026 13:49:33 -0700 Subject: [PATCH 35/76] KVM: SEV: Mark vCPU RUNNABLE after AP_CREATE, even if VMSA is unusable commit 98ade8c48c28c227fe2e80e545ff0c57cd4712a3 upstream. Always mark the vCPU as RUNNABLE after responding to AP_CREATE, even if the guest-specified VMSA is unusable, e.g. isn't backed by a memslot or doesn't have a backing guest_memfd page. If the VMSA is unusable, leaving the vCPU in a non-running state will effectively hang the vCPU instead of reporting an error to userspace. This will also allow retrying the VMSA load in the future, to fix a bug where KVM doesn't honor guest_memfd invalidation events, e.g. if AP_CREATION races with PUNCH_HOLE. Cc: stable@vger.kernel.org # 6.12.x Reviewed-by: Michael Roth Link: https://patch.msgid.link/20260709204948.1988414-4-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 9a45e7b0b140a8ea1ea2333130f07de285ace3fd) Signed-off-by: Wentao Guan --- arch/x86/kvm/svm/sev.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index c51b7d6c291f2..760f5bd8d073a 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -4252,9 +4252,6 @@ static void sev_snp_reload_vmsa(struct kvm_vcpu *vcpu, gpa_t gpa) svm->sev_es.snp_guest_vmsa_gpa = gpa; svm->vmcb->control.vmsa_pa = pfn_to_hpa(pfn); - /* Mark the vCPU as runnable */ - kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); - /* * gmem pages aren't currently migratable, but if this ever changes * then care should be taken to ensure svm->sev_es.vmsa is pinned @@ -4286,6 +4283,15 @@ static void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) svm->sev_es.snp_pending_vmsa_gpa = INVALID_PAGE; sev_snp_reload_vmsa(vcpu, gpa); + + /* + * Mark the vCPU as runnable for CREATE requests, indicated by a valid + * VMSA GPA, even if installing the VMSA failed, so that KVM_RUN will + * fail instead of blocking indefinitely and hanging the vCPU, e.g. if + * the backing guest_memfd page is unavailable. + */ + if (VALID_PAGE(gpa)) + kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE); } static int sev_snp_ap_creation(struct vcpu_svm *svm) From 75991211a2e5db27b75d32d4dda23a6a735cbf9e Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 9 Jul 2026 13:49:34 -0700 Subject: [PATCH 36/76] KVM: SEV: Wire up kvm_x86_ops.gmem_xxx() if and only if CONFIG_KVM_AMD_SEV=y commit 01a96ff30dde5127c37497f1e098e639e7ae152f upstream. Wire up the SEV-SNP guest_memfd kvm_x86_ops hooks if and only if SEV is actually enabled, and drop the now-unnecessary stubs. Leaving the hooks NULL allows the static call infrastructure to elide the CALL+RET, and more importantly, referencing the hooks if and only if SEV support is enabled will allow conditionally definining the hooks using their corresponding HAVE_KVM_ARCH_GMEM_XXX Kconfig. No functional change intended. Cc: stable@vger.kernel.org # 6.12.x Reviewed-by: Ackerley Tng Link: https://patch.msgid.link/20260709204948.1988414-5-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 0b0a668febb627b3eedb2c88729c4f9b65d89fc1) Signed-off-by: Wentao Guan --- arch/x86/kvm/svm/svm.c | 8 ++++---- arch/x86/kvm/svm/svm.h | 10 ---------- 2 files changed, 4 insertions(+), 14 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 4621ee5f38c6b..bd7fd016a0308 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -5301,6 +5301,10 @@ struct kvm_x86_ops svm_x86_ops __initdata = { .vm_copy_enc_context_from = sev_vm_copy_enc_context_from, .vm_move_enc_context_from = sev_vm_move_enc_context_from, + + .gmem_prepare = sev_gmem_prepare, + .gmem_invalidate = sev_gmem_invalidate, + .gmem_max_mapping_level = sev_gmem_max_mapping_level, #endif .check_emulate_instruction = svm_check_emulate_instruction, @@ -5312,10 +5316,6 @@ struct kvm_x86_ops svm_x86_ops __initdata = { .vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector, .vcpu_get_apicv_inhibit_reasons = avic_vcpu_get_apicv_inhibit_reasons, .alloc_apic_backing_page = svm_alloc_apic_backing_page, - - .gmem_prepare = sev_gmem_prepare, - .gmem_invalidate = sev_gmem_invalidate, - .gmem_max_mapping_level = sev_gmem_max_mapping_level, }; /* diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 72fcd1f09b9b0..7104c6a3140e7 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -912,16 +912,6 @@ static inline int sev_cpu_init(struct svm_cpu_data *sd) { return 0; } static inline int sev_dev_get_attr(u32 group, u64 attr, u64 *val) { return -ENXIO; } #define max_sev_asid 0 static inline void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code) {} -static inline int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order) -{ - return 0; -} -static inline void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) {} -static inline int sev_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, bool is_private) -{ - return 0; -} - static inline struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu) { return NULL; From bd45ab496b75e105c6de0b5f0913206f5ffd0285 Mon Sep 17 00:00:00 2001 From: Jiayuan Chen Date: Sun, 23 Aug 2026 16:47:56 +0800 Subject: [PATCH 37/76] tls: device: fix out-of-bounds write in tls_append_frag() commit b17cf742eaad70ae29ac558cefb3aa9bbeea03d4 upstream. Found with syzkaller and a local syzbot instance running on top of a netdevsim TLS offload emulation; tls_device.c is otherwise only reachable on a machine with a NIC that implements the offload. tls_push_data() only checks whether the open record still has room for another frag at the bottom of its loop, and the MSG_MORE early break skips that check. The record survives to the next syscall with the frag count it already had, and tls_append_frag() does not check either, so with TLS_TX_ZEROCOPY_RO every splice(SPLICE_F_MORE) of a byte or two adds a non-coalescing pipe page and num_frags walks off the end of tls_record_info.frags[MAX_SKB_FRAGS]. Once the record is pushed, tls_push_record() runs the same index over sg_tx_data[MAX_SKB_FRAGS] and the sg_set_page() writes land on the destruct_work that follows it, which the workqueue then calls. The byte limit is fine because copy drops to 0 and the loop falls through to the same check; the frag count has no such feedback. Push the record rather than keep a full one open, which is what a plain TCP socket does - tcp_sendmsg_locked() uses tcp_mark_push() and new_segment in both the copy and the MSG_SPLICE_PAGES paths, and tls_sw already sets full_record when the sk_msg ring fills up, MSG_MORE or not. BUG: KASAN: slab-out-of-bounds in tls_append_frag ( net/tls/tls_device.c:269) Write of size 8 at addr ffff8881104d1530 by task tls_oob/450 CPU: 2 UID: 0 PID: 450 Comm: tls_oob Not tainted 7.2.0-rc7+ #329 PREEMPT Call Trace: dump_stack_lvl (lib/dump_stack.c:94 lib/dump_stack.c:120) print_report (mm/kasan/report.c:378 mm/kasan/report.c:482) kasan_report (mm/kasan/report.c:595) tls_append_frag (net/tls/tls_device.c:269) tls_push_data (net/tls/tls_device.c:518) tls_device_sendmsg (net/tls/tls_device.c:583) inet_sendmsg (net/ipv4/af_inet.c:865) sock_sendmsg (net/socket.c:775 net/socket.c:790 net/socket.c:813) splice_to_socket (fs/splice.c:884) do_splice (fs/splice.c:936 fs/splice.c:1349) __do_splice (fs/splice.c:1431) __x64_sys_splice (fs/splice.c:1634 fs/splice.c:1616) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:121) and, once the record is pushed: UBSAN: array-index-out-of-bounds in net/tls/tls_device.c:300:24 index 18 is out of range for type 'skb_frag_t [17]' UBSAN: array-index-out-of-bounds in net/tls/tls_device.c:301:41 index 18 is out of range for type 'scatterlist [17]' UBSAN: array-index-out-of-bounds in net/tls/tls_device.c:302:39 index 18 is out of range for type 'scatterlist [17]' UBSAN: array-index-out-of-bounds in net/tls/tls_device.c:307:38 index 26 is out of range for type 'scatterlist [17]' kernel tried to execute NX-protected page - exploit attempt? (uid: 0) BUG: unable to handle page fault for address: ffffea000411a680 #PF: supervisor instruction fetch in kernel mode #PF: error_code(0x0011) - permissions violation Oops: Oops: 0011 [#1] SMP KASAN PTI Workqueue: ktls_device_destruct 0xffffea000411a680 RIP: 0010:0xffffea000411a680 Call Trace: worker_thread (kernel/workqueue.c:3405 kernel/workqueue.c:3486) kthread (kernel/kthread.c:436) ret_from_fork (arch/x86/kernel/process.c:158) ret_from_fork_asm (arch/x86/entry/entry_64.S:245) Fixes: e8f69799810c ("net/tls: Add generic NIC offload infrastructure") Cc: stable@vger.kernel.org Signed-off-by: Jiayuan Chen Link: https://patch.msgid.link/20260823084758.20936-1-jiayuan.chen@linux.dev Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman (cherry picked from commit fadbc1ed2a872a8649a44cf9e1cf9621fc58cd6e) Signed-off-by: Wentao Guan --- net/tls/tls_device.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index d2e3870590c89..577fca23fe100 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -530,7 +530,8 @@ static int tls_push_data(struct sock *sk, if (!size) { last_record: tls_push_record_flags = flags; - if (flags & MSG_MORE) { + if ((flags & MSG_MORE) && + record->num_frags < MAX_SKB_FRAGS - 1) { more = true; break; } From e7c9e501a6671618bb5be2453db4c084c58bce80 Mon Sep 17 00:00:00 2001 From: Qing Ming Date: Tue, 18 Aug 2026 23:00:00 +0800 Subject: [PATCH 38/76] gtp: serialize PDP context updates commit 498386b6d402737db1e2eeed4c385acbf0ef9e34 upstream. PDP contexts can be deleted through GTP_CMD_DELPDP or while the GTP network device is being unregistered. The latter is serialized by RTNL, but the generic-netlink delete path only holds RCU. Running both paths concurrently can therefore make both paths delete the same PDP context. The issue was found through static analysis and reproduced on a KASAN-enabled kernel by a simple two-thread program racing GTP_CMD_DELPDP against RTM_DELLINK: Oops: general protection fault, probably for non-canonical address KASAN: maybe wild-memory-access in range [0xdead000000000120-0xdead000000000127] RIP: gtp_genl_del_pdp+0x1c1/0x420 [gtp] RBP: dead000000000122 The second deletion dereferenced the poisoned hlist pprev pointer. Serialize gtp_pdp_add(), gtp_genl_del_pdp(), and gtp_dellink() with a shared mutex. Keep the mutex held until the final use of a PDP context in the NEWPDP path, and keep the RCU read-side section around the complete PDP context use in the DELPDP path. Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)") Cc: stable@vger.kernel.org Signed-off-by: Qing Ming Link: https://patch.msgid.link/20260818150000.7670-1-a0yami@mailbox.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 3d950e98f74af9611925a5226edced02155f6ed1) Signed-off-by: Wentao Guan --- drivers/net/gtp.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 98614d0b390b8..af45118083ca2 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -12,6 +12,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include +#include #include #include #include @@ -108,6 +109,7 @@ struct gtp_net { }; static u32 gtp_h_initval; +static DEFINE_MUTEX(gtp_pdp_lock); static struct genl_family gtp_genl_family; @@ -151,7 +153,8 @@ static struct pdp_ctx *gtp0_pdp_find(struct gtp_dev *gtp, u64 tid, u16 family) head = >p->tid_hash[gtp0_hashfn(tid) % gtp->hash_size]; - hlist_for_each_entry_rcu(pdp, head, hlist_tid) { + hlist_for_each_entry_rcu(pdp, head, hlist_tid, + lockdep_is_held(>p_pdp_lock)) { if (pdp->af == family && pdp->gtp_version == GTP_V0 && pdp->u.v0.tid == tid) @@ -168,7 +171,8 @@ static struct pdp_ctx *gtp1_pdp_find(struct gtp_dev *gtp, u32 tid, u16 family) head = >p->tid_hash[gtp1u_hashfn(tid) % gtp->hash_size]; - hlist_for_each_entry_rcu(pdp, head, hlist_tid) { + hlist_for_each_entry_rcu(pdp, head, hlist_tid, + lockdep_is_held(>p_pdp_lock)) { if (pdp->af == family && pdp->gtp_version == GTP_V1 && pdp->u.v1.i_tei == tid) @@ -185,7 +189,8 @@ static struct pdp_ctx *ipv4_pdp_find(struct gtp_dev *gtp, __be32 ms_addr) head = >p->addr_hash[ipv4_hashfn(ms_addr) % gtp->hash_size]; - hlist_for_each_entry_rcu(pdp, head, hlist_addr) { + hlist_for_each_entry_rcu(pdp, head, hlist_addr, + lockdep_is_held(>p_pdp_lock)) { if (pdp->af == AF_INET && pdp->ms.addr.s_addr == ms_addr) return pdp; @@ -220,7 +225,8 @@ static struct pdp_ctx *ipv6_pdp_find(struct gtp_dev *gtp, head = >p->addr_hash[ipv6_hashfn(ms_addr) % gtp->hash_size]; - hlist_for_each_entry_rcu(pdp, head, hlist_addr) { + hlist_for_each_entry_rcu(pdp, head, hlist_addr, + lockdep_is_held(>p_pdp_lock)) { if (pdp->af == AF_INET6 && ipv6_pdp_addr_equal(&pdp->ms.addr6, ms_addr)) return pdp; @@ -1555,9 +1561,11 @@ static void gtp_dellink(struct net_device *dev, struct list_head *head) struct pdp_ctx *pctx; int i; + mutex_lock(>p_pdp_lock); for (i = 0; i < gtp->hash_size; i++) hlist_for_each_entry_safe(pctx, next, >p->tid_hash[i], hlist_tid) pdp_context_delete(pctx); + mutex_unlock(>p_pdp_lock); list_del(>p->list); unregister_netdevice_queue(dev, head); @@ -2053,6 +2061,7 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) goto out_unlock; } + mutex_lock(>p_pdp_lock); pctx = gtp_pdp_add(gtp, sk, info); if (IS_ERR(pctx)) { err = PTR_ERR(pctx); @@ -2060,6 +2069,7 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) gtp_tunnel_notify(pctx, GTP_CMD_NEWPDP, GFP_KERNEL); err = 0; } + mutex_unlock(>p_pdp_lock); out_unlock: rtnl_unlock(); @@ -2134,6 +2144,8 @@ static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[GTPA_VERSION]) return -EINVAL; + mutex_lock(>p_pdp_lock); + rcu_read_lock(); pctx = gtp_find_pdp(sock_net(skb->sk), info->attrs); @@ -2154,6 +2166,7 @@ static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info) out_unlock: rcu_read_unlock(); + mutex_unlock(>p_pdp_lock); return err; } From 2cb309e9aa67fa2306344f6e4cb04e04bad2c784 Mon Sep 17 00:00:00 2001 From: Pratik Vishwakarma Date: Wed, 29 Jul 2026 05:54:59 +0000 Subject: [PATCH 39/76] x86/CPU/AMD: Carve out a Zen5 models range commit 52075128273ace53e6254e37899a47d40d4baf45 upstream. Family 0x1a, model 0xd0..0xd7 belongs to the Zen5 generation. Carve it out from the larger, Zen6 range where former doesn't belong. [ bp: Rewrite commit message, add tags. ] Fixes: b5f53e6d3d32 ("x86/CPU/AMD: Add more Zen6 models") Signed-off-by: Pratik Vishwakarma [ bp: Backport only the Zen5 bits. ] Signed-off-by: Borislav Petkov (AMD) Cc: Link: https://patch.msgid.link/20260729055459.15904-1-Pratik.Vishwakarma@amd.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit b5d1534db32af0e5cb1bd978719e374f8f1d9d56) Signed-off-by: Wentao Guan --- arch/x86/kernel/cpu/amd.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 2c7b29a3333f5..46bd6ef754dc1 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -514,11 +514,13 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) case 0x00 ... 0x2f: case 0x40 ... 0x4f: case 0x60 ... 0x7f: + case 0xd0 ... 0xd7: setup_force_cpu_cap(X86_FEATURE_ZEN5); break; case 0x50 ... 0x5f: case 0x80 ... 0xaf: - case 0xc0 ... 0xef: + case 0xc0 ... 0xcf: + case 0xd8 ... 0xef: setup_force_cpu_cap(X86_FEATURE_ZEN6); break; default: From c585c33b5dd9def184b9a72a1a1a3689aab3fa38 Mon Sep 17 00:00:00 2001 From: Rastislav Szabo Date: Sat, 22 Aug 2026 22:11:18 +0200 Subject: [PATCH 40/76] net/tcp: fix TCP-AO key deletion in VRFs commit 94ad9e114a1c7b16ea418c1456ac3835e038ab3f upstream. TCP-AO keys with TCP_AO_KEYF_IFINDEX store the VRF L3 interface index in l3index. tcp_ao_del_cmd() validates the supplied ifindex, but does not assign it to its local l3index before matching keys. As a result, deleting a key scoped to a non-default VRF always fails with ENOENT because it is matched against l3index 0. Fixes: 248411b8cb89 ("net/tcp: Wire up l3index to TCP-AO") Cc: stable@vger.kernel.org Signed-off-by: Rastislav Szabo Reviewed-by: David Ahern Acked-by: Dmitry Safonov <0x7f454c46@gmail.com> Link: https://patch.msgid.link/20260822201119.272269-1-rastislav.szabo@isovalent.com Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 4527747760239fcc68d8036f5937d212961ef293) Signed-off-by: Wentao Guan --- net/ipv4/tcp_ao.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index a7b1fe194fb1e..31566faf34fcd 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -1854,6 +1854,9 @@ static int tcp_ao_del_cmd(struct sock *sk, unsigned short int family, if (cmd.ifindex && !(cmd.keyflags & TCP_AO_KEYF_IFINDEX)) return -EINVAL; + if (cmd.keyflags & TCP_AO_KEYF_IFINDEX) + l3index = cmd.ifindex; + ao_info = setsockopt_ao_info(sk); if (IS_ERR(ao_info)) return PTR_ERR(ao_info); From 7609bbb4a17fae6c1b192131f3b7c7e478312173 Mon Sep 17 00:00:00 2001 From: Qing Ming Date: Tue, 25 Aug 2026 15:20:33 +0800 Subject: [PATCH 41/76] tcp: fix AO info use-after-free in tcp_ao_connect_init() commit ea30dc5267e367b8a5e1e06cc074f813bcbf18b2 upstream. tcp_v4_connect() adds a SYN-SENT socket to the ehash before calling tcp_connect(). If TCP-AO is configured, tcp_connect() first verifies that a key matches the peer and the bound device's current L3 master. tcp_ao_connect_init() later resolves the L3 master again and removes keys which do not match it. The socket lock does not stabilize the bound device's VRF membership. Detaching the device from its VRF between the initial validation and the L3-master calculation in tcp_ao_connect_init() can therefore make the validation succeed while initialization observes the default L3 domain and removes the only key. The subsequent AO lookup then fails, so the no-key path clears tp->ao_info and frees it directly. The receive path can find the socket in the ehash and load tp->ao_info under RCU before acquiring the socket lock. A reader which loaded the old pointer can thus continue into tcp_inbound_ao_hash() after the direct free. The issue was found during a static audit of TCP-AO object lifetime. An unprivileged reproducer in self-created user and network namespaces raced connect() with detaching a veth from its VRF while sending TCP-AO segments. It triggered the same KASAN report on two fresh boots: BUG: KASAN: slab-use-after-free in tcp_inbound_ao_hash+0x585/0x19f0 Write of size 8 at addr ffff88800bf88128 by task tcp_ao_vrf_race/232 Call Trace: tcp_inbound_ao_hash+0x585/0x19f0 tcp_inbound_hash+0x677/0xa80 tcp_v4_rcv+0x1c3e/0x3ab0 Allocated by task 235: tcp_ao_alloc_info+0x43/0xf0 tcp_ao_add_cmd+0xdf7/0x13b0 do_tcp_setsockopt+0x168c/0x2640 Freed by task 235: kfree+0x1b8/0x550 tcp_connect+0x252/0x4f00 tcp_v4_connect+0x1114/0x1720 The bad address is 40 bytes inside the freed 128-byte object, matching the tcp_ao_info counters.key_not_found field. The two runs used 1000 attempts each, reached the no-key path 366 and 411 times, and produced one and two KASAN reports respectively. With this change, the same reproducer reached the no-key path 366 times in 1000 attempts without a KASAN report or oops. Use tcp_ao_destroy_sock() for the no-key path. It unpublishes the AO info, updates the socket memory and static-key accounting, and defers the free until after an RCU grace period. Also drop the WARN_ON_ONCE() and its stale comment. The VRF detach race makes the no-key state reachable during normal operation, so it is a handled condition rather than an impossible assertion. On panic_on_warn kernels the WARN would turn this handled race into a kernel panic. Fixes: 248411b8cb89 ("net/tcp: Wire up l3index to TCP-AO") Cc: stable@vger.kernel.org Assisted-by: Codex:gpt-5 Signed-off-by: Qing Ming Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20260825072033.6921-1-a0yami@mailbox.org Signed-off-by: Paolo Abeni Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 70051a57786d5b23f059fbaf5c8241eca14d42ed) Signed-off-by: Wentao Guan --- net/ipv4/tcp_ao.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 31566faf34fcd..d3196c94ba5f7 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -1147,12 +1147,7 @@ void tcp_ao_connect_init(struct sock *sk) ao_info->lisn = htonl(tp->write_seq); ao_info->snd_sne = 0; } else { - /* Can't happen: tcp_connect() verifies that there's - * at least one tcp-ao key that matches the remote peer. - */ - WARN_ON_ONCE(1); - rcu_assign_pointer(tp->ao_info, NULL); - kfree(ao_info); + tcp_ao_destroy_sock(sk, false); } } From f3816ec301481018a22954982932f7f1b749fe72 Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Mon, 17 Aug 2026 06:28:42 +0900 Subject: [PATCH 42/76] net/tcp-ao: fix use-after-free of current_key on reconnect to another peer commit da4471557f279d0f56605158a625bb6e49ef7d41 upstream. tcp_inbound_ao_hash() is called before bh_lock_sock_nested() is taken, with only rcu_read_lock() held. On the fast path for established sockets, if the rnext_keyid sent by the peer differs from current_key->sndid, the key the peer asked for is looked up and stored in current_key. The lookup is inside the RCU read side, but current_key outlives it. When the socket is disconnected and connect() is called again for another peer, tcp_ao_connect_init() unlinks every key that does not match the new peer and frees it with call_rcu(). If current_key points at such a key, it is cleared to NULL. The fast path reads sk_state only once on entry, so a softirq that got into it while the socket was still established can update current_key after that loop has already run. The update is inside the RCU read side, so it comes before the call_rcu() callback, and once the callback frees the key, current_key is left pointing at freed memory. The next transmission picks that pointer up in tcp_get_current_key(). tcp_ao_transmit_skb() then reads the traffic key from the freed object, which is the use-after-free. Wait for one grace period before unlinking, and only if a key is going to be removed. By the time tcp_connect() runs the socket is already in TCP_SYN_SENT, and TCP_AO_ESTABLISHED does not contain TCPF_SYN_SENT, so a softirq entering after the wait cannot reach the fast path, and the ones already in it have finished. The existing NULL handling in the loop is then enough. Fixes: 0a3a809089eb ("net/tcp: Verify inbound TCP-AO signed segments") Cc: stable@vger.kernel.org Signed-off-by: Hyunwoo Kim Reviewed-by: Simon Horman Acked-by: Paolo Abeni Link: https://patch.msgid.link/aoIriv3pHDgII2YR@v4bel Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 73fde8fe4469f4ed8f0afcc0b9d6413002a9e6b3) Signed-off-by: Wentao Guan --- net/ipv4/tcp_ao.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index d3196c94ba5f7..77352f720696f 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -1120,6 +1120,15 @@ void tcp_ao_connect_init(struct sock *sk) l3index = l3mdev_master_ifindex_by_index(sock_net(sk), sk->sk_bound_dev_if); + hlist_for_each_entry(key, &ao_info->head, node) { + if (tcp_ao_key_cmp(key, l3index, addr, key->prefixlen, + family, -1, -1)) { + /* pairs with tcp_inbound_ao_hash() */ + synchronize_rcu(); + break; + } + } + hlist_for_each_entry_safe(key, next, &ao_info->head, node) { if (!tcp_ao_key_cmp(key, l3index, addr, key->prefixlen, family, -1, -1)) continue; From c0c529f87d17ed5c588e600137591bc4eeb99e35 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Thu, 16 Jul 2026 22:54:59 +0200 Subject: [PATCH 43/76] xfrm: espintcp: fix UAF during close commit deb232e884877bf10b4ce2580909eedec986c284 upstream. ZDI reported and analyzed a race condition during close for espintcp sockets: espintcp_close() frees emsg->skb via kfree_skb() without holding any socket lock. Concurrently, the xfrm_trans_reinject work queue invokes esp_output_tcp_finish() -> espintcp_push_skb() -> espintcp_push_msgs() -> skb_send_sock_locked(), which reads the same skb as a data source. Fix this by adding a synchronize_rcu() call after resetting sk_prot, since esp_output_tcp_finish() runs under RCU and won't use a socket with sk_prot == &tcp_prot. Simply taking the socket lock in espintcp_close() could lead to leaks, if esp_output_tcp_finish() re-adds an skb in the slot we just freed. After this, the existing barrier() is no longer needed. Cc: stable@vger.kernel.org Fixes: e27cca96cd68 ("xfrm: add espintcp (RFC 8229)") Reported-by: zdi-disclosures@trendmicro.com Signed-off-by: Sabrina Dubroca Reviewed-by: Breno Leitao Signed-off-by: Steffen Klassert Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 24efebecf415ba264adba0f0491cec436463a14f) Signed-off-by: Wentao Guan --- net/xfrm/espintcp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index dd7a7dc027855..84e9412066b3b 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -518,7 +518,8 @@ static void espintcp_close(struct sock *sk, long timeout) strp_stop(&ctx->strp); sk->sk_prot = &tcp_prot; - barrier(); + + synchronize_rcu(); disable_work_sync(&ctx->work); strp_done(&ctx->strp); From 75293a594a8f10f69ee11a91da52bbda371b3b23 Mon Sep 17 00:00:00 2001 From: Zhiling Zou Date: Sat, 18 Jul 2026 15:12:50 +0800 Subject: [PATCH 44/76] xfrm: drop ESP-in-TCP packets with no ingress device commit e1d7c5ac1c246ce5775f604515de0a59fbf2116e upstream. ESP-in-TCP receives records through the TCP strparser. handle_esp() restores skb->dev from the saved skb_iif before passing the packet into the XFRM input path. Queued TCP data can be processed after the original ingress device has been removed, for example during veth or net namespace teardown. In that case dev_get_by_index_rcu() returns NULL. The XFRM IPv4 and IPv6 input paths both expect skb->dev to be valid while building the route lookup, so queued ESP-in-TCP data can dereference a NULL device. Drop the packet if the saved ingress device can no longer be resolved. Such a packet can no longer be routed through the normal XFRM receive path, and this preserves the existing behaviour for packets whose ingress device still exists. Fixes: e27cca96cd68 ("xfrm: add espintcp (RFC 8229)") Cc: stable@vger.kernel.org Reported-by: Vega Signed-off-by: Zhiling Zou Assisted-by: Codex:gpt-5.4 Reviewed-by: Ren Wei Signed-off-by: Steffen Klassert Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 328e40aa774b446969c69b654c52a051a95af8a1) Signed-off-by: Wentao Guan --- net/xfrm/espintcp.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index 84e9412066b3b..fb47c2f731040 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -40,6 +40,11 @@ static void handle_esp(struct sk_buff *skb, struct sock *sk) rcu_read_lock(); skb->dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); + if (!skb->dev) { + XFRM_INC_STATS(sock_net(sk), LINUX_MIB_XFRMINERROR); + kfree_skb(skb); + goto out; + } local_bh_disable(); #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) @@ -48,6 +53,7 @@ static void handle_esp(struct sk_buff *skb, struct sock *sk) #endif xfrm4_rcv_encap(skb, IPPROTO_ESP, 0, TCP_ENCAP_ESPINTCP); local_bh_enable(); +out: rcu_read_unlock(); } From 0e1f8e9f53767a6fa506781723213b9a269a38c0 Mon Sep 17 00:00:00 2001 From: Zihan Xi Date: Tue, 21 Jul 2026 23:25:42 +0800 Subject: [PATCH 45/76] xfrm: avoid lock inversion in nat keepalive work commit 763fe700b7c58ad64fe5202c5638848244dd4127 upstream. nat_keepalive_work() walks the state table while xfrm_state_walk() holds net->xfrm.xfrm_state_lock. Its callback then acquires x->lock, which conflicts with the delete path taking the same locks in reverse order via xfrm_state_delete() and __xfrm_state_delete(). This creates an AB-BA deadlock that is reported by lockdep when a NAT keepalive worker races with SA deletion. Fix this by splitting the keepalive walk into two phases. First, collect the candidate states while the walk holds xfrm_state_lock and take a reference on each state. Then, after the walk completes, process each collected state and acquire x->lock without nesting it under xfrm_state_lock. Fixes: f531d13bdfe3 ("xfrm: support sending NAT keepalives in ESP in UDP states") Cc: stable@vger.kernel.org Reported-by: Vega Assisted-by: Codex:gpt-5.4 Signed-off-by: Zihan Xi Signed-off-by: Ren Wei Signed-off-by: Steffen Klassert Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 5c86c895d1cac81a71ead3005084c6265cf6a7a5) Signed-off-by: Wentao Guan --- net/xfrm/xfrm_nat_keepalive.c | 57 +++++++++++++++++++++++++++++------ 1 file changed, 48 insertions(+), 9 deletions(-) diff --git a/net/xfrm/xfrm_nat_keepalive.c b/net/xfrm/xfrm_nat_keepalive.c index f50b1f48f2ed9..03e672d339dab 100644 --- a/net/xfrm/xfrm_nat_keepalive.c +++ b/net/xfrm/xfrm_nat_keepalive.c @@ -156,24 +156,51 @@ static void nat_keepalive_send(struct nat_keepalive *ka) } struct nat_keepalive_work_ctx { + struct list_head states; time64_t next_run; time64_t now; }; -static int nat_keepalive_work_single(struct xfrm_state *x, int count, void *ptr) +struct nat_keepalive_state { + struct list_head list; + struct xfrm_state *x; +}; + +static int nat_keepalive_work_collect(struct xfrm_state *x, int count, void *ptr) { struct nat_keepalive_work_ctx *ctx = ptr; + struct nat_keepalive_state *state; + + if (!READ_ONCE(x->nat_keepalive_interval)) + return 0; + + state = kmalloc_obj(*state, GFP_ATOMIC); + if (!state) + return -ENOMEM; + + xfrm_state_hold(x); + state->x = x; + list_add_tail(&state->list, &ctx->states); + return 0; +} + +static void nat_keepalive_work_single(struct xfrm_state *x, + struct nat_keepalive_work_ctx *ctx) +{ bool send_keepalive = false; struct nat_keepalive ka; - time64_t next_run; + time64_t next_run = 0; u32 interval; int delta; + spin_lock_bh(&x->lock); + + if (x->km.state == XFRM_STATE_DEAD) + goto out; + interval = x->nat_keepalive_interval; if (!interval) - return 0; - - spin_lock(&x->lock); + goto out; delta = (int)(ctx->now - x->lastused); if (delta < interval) { @@ -187,29 +214,41 @@ static int nat_keepalive_work_single(struct xfrm_state *x, int count, void *ptr) send_keepalive = true; } - spin_unlock(&x->lock); +out: + spin_unlock_bh(&x->lock); if (send_keepalive) nat_keepalive_send(&ka); - if (!ctx->next_run || next_run < ctx->next_run) + if (next_run && (!ctx->next_run || next_run < ctx->next_run)) ctx->next_run = next_run; - return 0; } static void nat_keepalive_work(struct work_struct *work) { + struct nat_keepalive_state *state, *tmp; struct nat_keepalive_work_ctx ctx; struct xfrm_state_walk walk; struct net *net; + int err; + INIT_LIST_HEAD(&ctx.states); ctx.next_run = 0; ctx.now = ktime_get_real_seconds(); net = container_of(work, struct net, xfrm.nat_keepalive_work.work); xfrm_state_walk_init(&walk, IPPROTO_ESP, NULL); - xfrm_state_walk(net, &walk, nat_keepalive_work_single, &ctx); + err = xfrm_state_walk(net, &walk, nat_keepalive_work_collect, &ctx); xfrm_state_walk_done(&walk, net); + list_for_each_entry_safe(state, tmp, &ctx.states, list) { + nat_keepalive_work_single(state->x, &ctx); + xfrm_state_put(state->x); + kfree(state); + } + if (err == -ENOMEM) { + schedule_delayed_work(&net->xfrm.nat_keepalive_work, 0); + return; + } if (ctx.next_run) schedule_delayed_work(&net->xfrm.nat_keepalive_work, (ctx.next_run - ctx.now) * HZ); From 154b327460827fcf280862dbc30fc220d31b6af3 Mon Sep 17 00:00:00 2001 From: Asim Viladi Oglu Manizada Date: Thu, 23 Jul 2026 09:35:48 +0000 Subject: [PATCH 46/76] xfrm: ah6: validate routing header segments_left commit 7bad4bda74dc4713f398d3b7624ff05478e3a568 upstream. AH6 rearranges routing-header addresses before computing or verifying the ICV. ipv6_rearrange_rthdr() assumes that segments_left is not larger than the number of addresses described by the routing header's hdrlen field. That assumption does not hold for raw IPv6 HDRINCL packets. A packet with hdrlen equal to 2 describes one address, but can carry an arbitrary segments_left value. With segments_left equal to 255, the function moves its address pointer 4,064 bytes backwards and passes a 4,064-byte length to memmove(), resulting in an out-of-bounds access. Validate the invariant locally before modifying the routing header or performing any address-pointer arithmetic, and propagate malformed-header errors to the existing AH6 input and output error paths. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Assisted-by: avom-custom-harness:gpt-5.5-qwen3.6-mod-mix Signed-off-by: Asim Viladi Oglu Manizada Signed-off-by: Steffen Klassert Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 6733ae71268a27d598cfb3f3339a3c950b9b656d) Signed-off-by: Wentao Guan --- net/ipv6/ah6.c | 29 ++++++++++++++++++----------- 1 file changed, 18 insertions(+), 11 deletions(-) diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index bf4e11614af25..188397b9a9db0 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -232,26 +232,28 @@ static void ipv6_rearrange_destopt(struct ipv6hdr *iph, struct ipv6_opt_hdr *des * Rearrange the destination address in @iph and the addresses in @rthdr * so that they appear in the order they will at the final destination. * See Appendix A2 of RFC 2402 for details. + * + * Return: 0 on success, -EINVAL if segments_left exceeds the number of + * addresses described by hdrlen. */ -static void ipv6_rearrange_rthdr(struct ipv6hdr *iph, struct ipv6_rt_hdr *rthdr) +static int ipv6_rearrange_rthdr(struct ipv6hdr *iph, struct ipv6_rt_hdr *rthdr) { - int segments, segments_left; + unsigned int segments, segments_left; struct in6_addr *addrs; struct in6_addr final_addr; segments_left = rthdr->segments_left; if (segments_left == 0) - return; - rthdr->segments_left = 0; + return 0; - /* The value of rthdr->hdrlen has been verified either by the system - * call if it is locally generated, or by ipv6_rthdr_rcv() for incoming - * packets. So we can assume that it is even and that segments is - * greater than or equal to segments_left. - * - * For the same reason we can assume that this option is of type 0. + /* Raw locally generated packets can reach AH6 without the invariant + * required by the rt0-style address rearrangement below. */ segments = rthdr->hdrlen >> 1; + if (segments_left > segments) + return -EINVAL; + + rthdr->segments_left = 0; addrs = ((struct rt0_hdr *)rthdr)->addr; final_addr = addrs[segments - 1]; @@ -261,6 +263,8 @@ static void ipv6_rearrange_rthdr(struct ipv6hdr *iph, struct ipv6_rt_hdr *rthdr) addrs[0] = iph->daddr; iph->daddr = final_addr; + + return 0; } static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) @@ -273,6 +277,7 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) } exthdr = { .iph = iph }; char *end = exthdr.raw + len; int nexthdr = iph->nexthdr; + int err; exthdr.iph++; @@ -292,7 +297,9 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) break; case NEXTHDR_ROUTING: - ipv6_rearrange_rthdr(iph, exthdr.rth); + err = ipv6_rearrange_rthdr(iph, exthdr.rth); + if (err) + return err; break; default: From c38649276ca97f3995ab29a60da8fcc6b2cf4f52 Mon Sep 17 00:00:00 2001 From: Zihan Xi Date: Tue, 28 Jul 2026 01:30:32 +0800 Subject: [PATCH 47/76] xfrm: fix xfrm_state_construct() auth-trunc leak commit c12cbf56320fb633484ee0ca1fb7d68d6b64b213 upstream. attach_auth_trunc() can allocate x->aalg while leaving x->props.aalgo at zero when the selected auth algorithm has no sadb_alg_id. One real case is cmac(aes). xfrm_state_construct() then treats !x->props.aalgo as "no auth algorithm attached yet" and calls attach_auth(). That overwrites x->aalg and loses the first allocation. Any later failure or teardown only frees the replacement pointer. Check whether x->aalg is already attached instead of inferring that state from x->props.aalgo. Fixes: 4447bb33f094 ("xfrm: Store aalg in xfrm_state with a user specified truncation length") Cc: stable@vger.kernel.org Reported-by: Vega Assisted-by: Codex:gpt-5.4 Signed-off-by: Zihan Xi Signed-off-by: Ren Wei Signed-off-by: Steffen Klassert Signed-off-by: Greg Kroah-Hartman (cherry picked from commit cf67361e78dca488d6e4df8396a53e6745a3a80e) Signed-off-by: Wentao Guan --- net/xfrm/xfrm_user.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 3641ccccbc415..0f0384b6a11d0 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -916,7 +916,7 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, if ((err = attach_auth_trunc(&x->aalg, &x->props.aalgo, attrs[XFRMA_ALG_AUTH_TRUNC], extack))) goto error; - if (!x->props.aalgo) { + if (!x->aalg) { if ((err = attach_auth(&x->aalg, &x->props.aalgo, attrs[XFRMA_ALG_AUTH], extack))) goto error; From 85b2fe1db71afb19124424d1b51ef68892f8fcbd Mon Sep 17 00:00:00 2001 From: Zihan Xi Date: Mon, 17 Aug 2026 19:09:56 +0000 Subject: [PATCH 48/76] xfrm: bound nat keepalive state collection commit 4e9442ce551ebd84b52ad649df721e2dc28af95a upstream. The v1 nat keepalive fix allocates a GFP_ATOMIC object for every state while collecting references for phase two. This makes the worker's temporary memory use depend on the number of states and lets -ENOMEM abort the scan. Replace the allocated list with a fixed-size batch. When the batch is full, return a private walk status so xfrm_state_walk() leaves a cursor; drain the references after the walk releases xfrm_state_lock and resume from the cursor. This bounds temporary memory use and avoids the allocation failure path. The v1 fix also moved nat_keepalive_send() out of the walk callback. Keep the phase-two drain BH-disabled, as required by local_lock_nested_bh() used by the keepalive sockets. Fixes: 763fe700b7c5 ("xfrm: avoid lock inversion in nat keepalive work") Cc: stable@vger.kernel.org Cc: Eyal Birger Reported-by: Vega Assisted-by: Codex:gpt-5.4 Signed-off-by: Zihan Xi Signed-off-by: Steffen Klassert Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 50229d334558aba80e6ffb296ab76f5de9269bed) Signed-off-by: Wentao Guan --- net/xfrm/xfrm_nat_keepalive.c | 46 ++++++++++++++++------------------- 1 file changed, 21 insertions(+), 25 deletions(-) diff --git a/net/xfrm/xfrm_nat_keepalive.c b/net/xfrm/xfrm_nat_keepalive.c index 03e672d339dab..22ca3dc1508b6 100644 --- a/net/xfrm/xfrm_nat_keepalive.c +++ b/net/xfrm/xfrm_nat_keepalive.c @@ -155,32 +155,30 @@ static void nat_keepalive_send(struct nat_keepalive *ka) } } +enum { + NAT_KEEPALIVE_BATCH_SIZE = 16, + NAT_KEEPALIVE_BATCH_FULL = 1, +}; + struct nat_keepalive_work_ctx { - struct list_head states; + struct xfrm_state *batch[NAT_KEEPALIVE_BATCH_SIZE]; + unsigned int nr; time64_t next_run; time64_t now; }; -struct nat_keepalive_state { - struct list_head list; - struct xfrm_state *x; -}; - static int nat_keepalive_work_collect(struct xfrm_state *x, int count, void *ptr) { struct nat_keepalive_work_ctx *ctx = ptr; - struct nat_keepalive_state *state; if (!READ_ONCE(x->nat_keepalive_interval)) return 0; - state = kmalloc_obj(*state, GFP_ATOMIC); - if (!state) - return -ENOMEM; + if (ctx->nr == ARRAY_SIZE(ctx->batch)) + return NAT_KEEPALIVE_BATCH_FULL; xfrm_state_hold(x); - state->x = x; - list_add_tail(&state->list, &ctx->states); + ctx->batch[ctx->nr++] = x; return 0; } @@ -226,29 +224,27 @@ static void nat_keepalive_work_single(struct xfrm_state *x, static void nat_keepalive_work(struct work_struct *work) { - struct nat_keepalive_state *state, *tmp; struct nat_keepalive_work_ctx ctx; struct xfrm_state_walk walk; struct net *net; - int err; + int err, i; - INIT_LIST_HEAD(&ctx.states); ctx.next_run = 0; ctx.now = ktime_get_real_seconds(); net = container_of(work, struct net, xfrm.nat_keepalive_work.work); xfrm_state_walk_init(&walk, IPPROTO_ESP, NULL); - err = xfrm_state_walk(net, &walk, nat_keepalive_work_collect, &ctx); + do { + ctx.nr = 0; + err = xfrm_state_walk(net, &walk, nat_keepalive_work_collect, &ctx); + local_bh_disable(); + for (i = 0; i < ctx.nr; i++) { + nat_keepalive_work_single(ctx.batch[i], &ctx); + xfrm_state_put(ctx.batch[i]); + } + local_bh_enable(); + } while (err == NAT_KEEPALIVE_BATCH_FULL); xfrm_state_walk_done(&walk, net); - list_for_each_entry_safe(state, tmp, &ctx.states, list) { - nat_keepalive_work_single(state->x, &ctx); - xfrm_state_put(state->x); - kfree(state); - } - if (err == -ENOMEM) { - schedule_delayed_work(&net->xfrm.nat_keepalive_work, 0); - return; - } if (ctx.next_run) schedule_delayed_work(&net->xfrm.nat_keepalive_work, (ctx.next_run - ctx.now) * HZ); From 95e856f26ba31ba283fca711f5c1731ce80c4e33 Mon Sep 17 00:00:00 2001 From: Norbert Szetei Date: Wed, 26 Aug 2026 11:12:27 +0200 Subject: [PATCH 49/76] net: bridge: mcast: fix use-after-free of a master VLAN's multicast context commit 50e5c6605cc9c2dd57bd2d1b3459674d19738983 upstream. br_multicast_toggle_one_vlan() clears BR_VLFLAG_MCAST_ENABLED under br->multicast_lock before stopping a VLAN's multicast context. That is the teardown handshake: lockless readers gate on the flag through br_multicast_ctx_should_use() -> br_multicast_ctx_vlan_disabled(), so once it is cleared under the lock no reader can arm the context again. For a master VLAN the handshake never runs. __vlan_del() clears BRIDGE_VLAN_INFO_BRENTRY before calling br_vlan_put_master(), so br_multicast_toggle_one_vlan(masterv, false) returns early on !br_vlan_is_brentry(vlan): the flag stays set and br->multicast_lock is never taken. br_vlan_put_master() then drains the context in br_multicast_ctx_deinit() and frees the VLAN through call_rcu(), while a reader still inside rcu_read_lock() sees the context as enabled and re-arms it. The port and port-VLAN branch of the function has no br_vlan_is_brentry() test and flips the flag under br->multicast_lock, so it is not affected. The reader is the bridge transmit path. For a master VLAN br_multicast_rcv() selects brmctx = &vlan->br_mcast_ctx with pmctx = NULL, so IGMP sent to the bridge device re-arms the context's timers after br_multicast_ctx_deinit() has already stopped them. BUG: KASAN: slab-use-after-free in detach_if_pending+0x412/0x4a0 Write of size 8 at addr ffff88810ac39918 by task brmc/601 __mod_timer+0x51a/0xc50 br_multicast_host_join+0x25b/0x390 __br_multicast_add_group+0x468/0x530 br_ip4_multicast_add_group+0x1a0/0x260 br_multicast_rcv+0x2cda/0x61e0 br_dev_xmit+0x6c4/0x1540 Allocated by task 610: br_vlan_add+0x111/0xb40 br_vlan_info+0x370/0x3e0 Freed by task 0: kfree+0x1a7/0x4f0 rcu_core+0x7dc/0x10a0 Only test br_vlan_is_brentry() when enabling, like the br_multicast_ctx_vlan_global_disabled() test next to it. Disabling then always clears BR_VLFLAG_MCAST_ENABLED under br->multicast_lock before br_multicast_ctx_deinit() drains the context. Fixes: 7b54aaaf53cb ("net: bridge: multicast: add vlan state initialization and control") Cc: stable@vger.kernel.org Signed-off-by: Norbert Szetei Acked-by: Nikolay Aleksandrov Link: https://patch.msgid.link/D400F6C7-543A-4B79-9E5B-D1D8974DE5C9@doyensec.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit c069f29da72324697aa4b7cab5b3647a7d24a575) Signed-off-by: Wentao Guan --- net/bridge/br_multicast.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index ce34881a9d96e..c2a5af45df204 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -4311,8 +4311,8 @@ void br_multicast_toggle_one_vlan(struct net_bridge_vlan *vlan, bool on) if (br_vlan_is_master(vlan)) { br = vlan->br; - if (!br_vlan_is_brentry(vlan) || - (on && + if (on && + (!br_vlan_is_brentry(vlan) || br_multicast_ctx_vlan_global_disabled(&vlan->br_mcast_ctx))) return; From ae8d197f93a8b12f5f004dfef58b540cab36b6be Mon Sep 17 00:00:00 2001 From: Kyle Zeng Date: Mon, 17 Aug 2026 08:58:38 +0000 Subject: [PATCH 50/76] ipv6: seg6: clear IPv4 control block on IPIP decapsulation commit 44930446dde45a7a90fe1446fa38eb0e2c561646 upstream. End.DX4 and End.DT4 decapsulate an IPv4 packet through decap_and_validate() and send it directly to IPv4 routing. The inner packet therefore bypasses ip_rcv_core(), which normally clears IPCB before IPv4 interprets skb->cb. The skb instead retains IP6CB data from the outer packet. IP6CB and IPCB use the same skb->cb storage, so IP6CB(skb)->lastopt overlaps IPCB(skb)->opt.optlen and srr, while IP6CB(skb)->nhoff overlaps rr and ts. The sender can make the stale optlen byte nonzero with a valid outer extension-header chain. The reproducers put an eight-byte Destination Options header immediately after the 40-byte IPv6 header and before the Segment Routing Header. ipv6_destopt_rcv() records the sender-controlled Destination Options offset in both lastopt and nhoff, setting them to 40. On the reproduced little-endian x86-64 kernel, IPv4 therefore sees optlen = 40 and rr = 40. Both tcp_v4_save_options() and __ip_options_echo() skip option copying when optlen is zero. Here optlen is 40, so the TCP SYN path allocates room for 40 bytes of option data and calls __ip_options_echo(). The stale rr value makes that function read inner packet byte 41 as the Record Route option length. The reproducers set that sender-controlled byte to 255, so __ip_options_echo() copies 255 bytes into the 40-byte option-data area. Separate End.DX4 and End.DT4 reproducers on the unpatched v7.2-rc5 kernel both produced: BUG: KASAN: slab-out-of-bounds in __ip_options_echo() Write of size 255 The relevant End.DX4 call path is: __ip_options_echo tcp_v4_route_req tcp_conn_request tcp_v4_conn_request tcp_rcv_state_process tcp_v4_do_rcv tcp_v4_rcv ip_protocol_deliver_rcu ip_local_deliver_finish ip_local_deliver input_action_end_dx4_finish input_action_end_dx4 The relevant End.DT4 call path is: __ip_options_echo tcp_v4_route_req tcp_conn_request tcp_v4_conn_request tcp_rcv_state_process tcp_v4_do_rcv tcp_v4_rcv ip_protocol_deliver_rcu ip_local_deliver_finish ip_local_deliver input_action_end_dt4 tcp_v4_save_options() is inlined into the tcp_v4_route_req() path, so it does not appear as a separate frame. When decap_and_validate() handles IPPROTO_IPIP, save the ingress interface from IP6CB, clear IPCB, and restore the saved value. Doing this in the common decapsulation path covers End.DX4, End.DT4, and End.DT46's IPv4 arm. Use IP6CB(skb)->iif rather than skb->skb_iif. These actions run after l3mdev processing, which can replace skb_iif with the L3 master; IP6CB iif still records the receiving interface set at IPv6 ingress. Fixes: 891ef8dd2a8d ("ipv6: sr: implement additional seg6local actions") Cc: stable@vger.kernel.org Suggested-by: Andrea Mayer Signed-off-by: Kyle Zeng Co-developed-by: David Lee Signed-off-by: David Lee Reviewed-by: Andrea Mayer Link: https://patch.msgid.link/20260817085839.946321-1-david.lee@trailofbits.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 3e4476e58343fb8f2fffced9e22d935376b17aaf) Signed-off-by: Wentao Guan --- net/ipv6/seg6_local.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 2b41e4c0dddd1..95ea0b62729ac 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -256,6 +256,13 @@ static bool decap_and_validate(struct sk_buff *skb, int proto) if (iptunnel_pull_offloads(skb)) return false; + if (proto == IPPROTO_IPIP) { + int iif = IP6CB(skb)->iif; + + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + IPCB(skb)->iif = iif; + } + return true; } From 9174215038f0a0828326717ad59e05f2e537a08a Mon Sep 17 00:00:00 2001 From: Kyle Zeng Date: Mon, 17 Aug 2026 08:49:54 +0000 Subject: [PATCH 51/76] batman-adv: reject unrepresentable multicast TVLV offsets commit f12c2de4f542e3220e17e0606f492110064f04cb upstream. The network and transport header fields in struct sk_buff are 16-bit offsets from skb->head, and U16_MAX is reserved as the unset transport header value. batadv_tvlv_call_handler() sets both fields from a received multicast TVLV without checking whether the TVLV end is representable. If the end offset exceeds the field's range, skb_set_transport_header() truncates it so that the transport header precedes the network header. The negative difference is then returned by skb_network_header_len() as a large u32. batadv_mcast_forw_packet() consequently accepts an oversized multicast tracker and accesses memory beyond the skb data. Add skb_set_transport_header_careful(), an offset-aware counterpart to skb_reset_transport_header_careful(), which validates the final head-relative offset before assigning it. Use the new helper in batadv_tvlv_call_handler() and reject unrepresentable TVLVs before setting the network header. Fixes: 07afe1ba288c ("batman-adv: mcast: implement multicast packet reception and forwarding") Cc: stable@vger.kernel.org Signed-off-by: Kyle Zeng Co-developed-by: David Lee Signed-off-by: David Lee Acked-by: Sven Eckelmann Link: https://patch.msgid.link/20260817084955.944189-1-david.lee@trailofbits.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 916ec741e65af072b98e475feaad98c063da1b7c) Signed-off-by: Wentao Guan --- include/linux/skbuff.h | 24 ++++++++++++++++++++++++ net/batman-adv/tvlv.c | 5 ++++- 2 files changed, 28 insertions(+), 1 deletion(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index def9cca948178..36a02653665ac 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3110,6 +3110,30 @@ static inline void skb_set_transport_header(struct sk_buff *skb, skb->transport_header += offset; } +/** + * skb_set_transport_header_careful - conditionally set transport header + * @skb: buffer to alter + * @offset: offset to add to skb->data + * + * Hardened version of skb_set_transport_header(). + * + * Returns: true if the operation was a success. + */ +static inline bool __must_check +skb_set_transport_header_careful(struct sk_buff *skb, const int offset) +{ + long thoff = skb->data - skb->head + offset; + + if (unlikely(thoff != (typeof(skb->transport_header))thoff)) + return false; + + if (unlikely(thoff == (typeof(skb->transport_header))~0U)) + return false; + + skb->transport_header = thoff; + return true; +} + static inline unsigned char *skb_network_header(const struct sk_buff *skb) { return skb->head + skb->network_header; diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index a91f1891747c0..0c405c5814d66 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -420,8 +420,11 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, return NET_RX_SUCCESS; tvlv_offset = (unsigned char *)tvlv_value - skb->data; + if (!skb_set_transport_header_careful(skb, + tvlv_offset + tvlv_value_len)) + return -EINVAL; + skb_set_network_header(skb, tvlv_offset); - skb_set_transport_header(skb, tvlv_offset + tvlv_value_len); return tvlv_handler->mcast_handler(bat_priv, skb); } From 42d8aa8ca63b54a60e29b2f694805b0ced3a6afa Mon Sep 17 00:00:00 2001 From: Kyle Zeng Date: Mon, 10 Aug 2026 14:41:14 +0000 Subject: [PATCH 52/76] vxlan: keep the last remote linked during FDB flush commit d5d4a7b538b52db63927773a8905fcd9f78a42e2 upstream. A non-nexthop FDB entry is expected to have at least one remote while it remains reachable through the FDB hash table. A filtered bulk flush violates this invariant when every remote matches: It unlinks the last remote in vxlan_fdb_dst_destroy() and only afterwards tells vxlan_flush() to destroy the parent FDB entry. An RCU reader can find the parent during this interval. first_remote_rcu() then applies list_entry_rcu() to the empty list head, producing an invalid remote pointer that the receive learning path can read from and write to. When a matching remote is the sole remaining remote, leave it linked and ask the caller to destroy the entire FDB entry. vxlan_fdb_destroy() keeps the remote attached while sending the deletion notification and removing the parent from the lookup structures. Fixes: c499fccb71cb ("vxlan: vxlan_core: Support FDB flushing by destination VNI") Cc: stable@vger.kernel.org Signed-off-by: Kyle Zeng Co-developed-by: David Lee Signed-off-by: David Lee Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/20260810144115.821654-1-david.lee@trailofbits.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit a8820c8a7718327e96849782033e7c85a0f6bcfe) Signed-off-by: Wentao Guan --- drivers/net/vxlan/vxlan_core.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 34976c13ba4b1..b6a1555ecf6be 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -3060,18 +3060,19 @@ vxlan_fdb_flush_match_remotes(struct vxlan_fdb *f, struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc, bool *p_destroy_fdb) { - bool remotes_flushed = false; struct vxlan_rdst *rd, *tmp; list_for_each_entry_safe(rd, tmp, &f->remotes, list) { if (!vxlan_fdb_flush_remote_matches(desc, rd)) continue; + if (list_is_singular(&f->remotes)) { + *p_destroy_fdb = true; + return; + } + vxlan_fdb_dst_destroy(vxlan, f, rd, true); - remotes_flushed = true; } - - *p_destroy_fdb = remotes_flushed && list_empty(&f->remotes); } /* Purge the forwarding table */ From 93e4d78ff9d814b1f67c8a4bf2132fed8350c5c5 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sat, 15 Aug 2026 13:57:50 -0700 Subject: [PATCH 53/76] netfilter: nft_set_pipapo_avx2: add missing vzeroupper commit 55dd20f0f4b1be5c9c8a0275d8d763c86563eac2 upstream. Since pipapo_get_avx2() uses YMM registers, execute vzeroupper before returning from it. This is needed to avoid degrading the performance of any later SSE code that may happen to be executed. Fixes: 7400b063969b ("nft_set_pipapo: Introduce AVX2-based lookup implementation") Cc: stable@vger.kernel.org Signed-off-by: Eric Biggers Reviewed-by: Stefano Brivio Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 07ee91e6b7b0a8ed9a24c48f2f07decf1033bdf4) Signed-off-by: Wentao Guan --- net/netfilter/nft_set_pipapo_avx2.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index 6395982e4d95c..29a548595857a 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1156,6 +1156,7 @@ struct nft_pipapo_elem *pipapo_get_avx2(const struct nft_pipapo_match *m, struct nft_pipapo_scratch *scratch; const struct nft_pipapo_field *f; unsigned long *res, *fill, *map; + struct nft_pipapo_elem *e; bool map_index; int i; @@ -1228,14 +1229,11 @@ struct nft_pipapo_elem *pipapo_get_avx2(const struct nft_pipapo_match *m, next_match: if (ret < 0) { scratch->map_index = map_index; - kernel_fpu_end(); - __local_unlock_nested_bh(&scratch->bh_lock); - return NULL; + e = NULL; + goto out; } if (last) { - struct nft_pipapo_elem *e; - e = f->mt[ret].e; if (unlikely(__nft_set_elem_expired(&e->ext, tstamp) || !nft_set_elem_active(&e->ext, genmask))) { @@ -1245,9 +1243,7 @@ struct nft_pipapo_elem *pipapo_get_avx2(const struct nft_pipapo_match *m, } scratch->map_index = map_index; - kernel_fpu_end(); - __local_unlock_nested_bh(&scratch->bh_lock); - return e; + goto out; } map_index = !map_index; @@ -1255,9 +1251,12 @@ struct nft_pipapo_elem *pipapo_get_avx2(const struct nft_pipapo_match *m, data += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); } + e = NULL; +out: + asm volatile("vzeroupper"); kernel_fpu_end(); __local_unlock_nested_bh(&scratch->bh_lock); - return NULL; + return e; } /** From 752a323e99beee07a3f74620c6847b8e1e22fb4d Mon Sep 17 00:00:00 2001 From: Fourie Zhang Date: Mon, 10 Aug 2026 19:35:01 +0800 Subject: [PATCH 54/76] netfilter: nf_tables: don't queue packet path object notifications commit 7904b94768e983bcb2be34a8d6d1f3450f5b838b upstream. All file:line references below are against v7.2-rc4 (ac5b0e5651b1). The trace was captured on 7.2.0-rc6-kasan72rc6 (075b74841bd0), where the same lines apply. nft_obj_notify() is exported and reached from the packet path. Its only in-tree caller is nft_quota_obj_eval() (net/netfilter/nft_quota.c:68), which notifies with GFP_ATOMIC while evaluating a rule for a transiting packet, holding no mutex. Since commit 67cc570edaa0 ("netfilter: nf_tables: coalesce multiple notifications into one skbuff") that notification is no longer sent immediately. __nft_obj_notify() queues it onto nft_net->notify_list via nft_notify_enqueue() (net/netfilter/nf_tables_api.c:1211), which is a bare list_add_tail(). notify_list has no lock of its own (include/net/netfilter/nf_tables.h:1951), it is serialised by commit_mutex: the six other enqueue sites all run inside a netlink transaction, and the drain in nft_commit_notify() (net/netfilter/nf_tables_api.c:10746) does list_del() + kfree_skb() from nf_tables_commit() with commit_mutex held. Sending packets through a chain that references a depleted quota object therefore races an unlocked list_add_tail() against list_del() + kfree_skb() on another CPU. The WRITE_ONCE(prev->next, new) in __list_add() then stores through an sk_buff that has already been freed: BUG: KASAN: slab-use-after-free in __nft_obj_notify+0x2c5/0x2d0 Write of size 8 at addr ff110001047183c0 by task poc/76 CPU: 0 UID: 1000 PID: 76 Comm: poc Tainted: G W 7.2.0-rc6-kasan72rc6 #4 Call Trace: __nft_obj_notify (include/linux/list.h:164 include/linux/list.h:191 net/netfilter/nf_tables_api.c:1211 net/netfilter/nf_tables_api.c:8743) nft_quota_obj_eval (net/netfilter/nft_quota.c:68) nft_do_chain_inet nf_hook_slow __ip_local_out ip_push_pending_frames udp_send_skb udp_sendmsg __x64_sys_sendto Allocated by task 77: __alloc_skb (net/core/skbuff.c:704) __nft_obj_notify (include/net/netlink.h:1055 net/netfilter/nf_tables_api.c:8731) nft_quota_obj_eval (net/netfilter/nft_quota.c:68) nft_do_chain Freed by task 79: nf_tables_commit (include/linux/skbuff.h:1332 net/netfilter/nf_tables_api.c:10759 net/netfilter/nf_tables_api.c:11185) nfnetlink_rcv_batch (net/netfilter/nfnetlink.c:574) netlink_unicast netlink_sendmsg The buggy address belongs to the cache skbuff_head_cache of size 232 Queueing from the packet path is wrong even leaving the race aside: notify_list is only drained by nft_commit_notify() from nf_tables_commit() (:11185), so a notification enqueued outside a transaction is not sent until some later netlink batch commits, if one ever does. The gfp argument that nft_obj_notify() still takes is a leftover of the pre-67cc570edaa0 behaviour, where this path called nfnetlink_send() directly. Restore that: split the message construction out into nft_obj_notify_alloc() and let each caller decide what to do with the skb. nft_obj_notify(), the exported one reached from the packet path, sends it straight away; nf_tables_obj_notify(), which runs under commit_mutex, keeps queueing it, so transaction notifications are still coalesced. Fixes: 67cc570edaa0 ("netfilter: nf_tables: coalesce multiple notifications into one skbuff") Cc: stable@kernel.org Reported-by: TencentOS Corvus AI Assisted-by: tencentos-corvus-ai:kimi-k3 Signed-off-by: Fourie Zhang Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 6fa88d11983c6fe693c13ed7c5b3b75ae9f39de6) Signed-off-by: Wentao Guan --- net/netfilter/nf_tables_api.c | 36 ++++++++++++++++++++++------------- 1 file changed, 23 insertions(+), 13 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index db939e1988009..d01f96d32f282 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8585,18 +8585,17 @@ static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, return nft_delobj(&ctx, obj); } -static void -__nft_obj_notify(struct net *net, const struct nft_table *table, - struct nft_object *obj, u32 portid, u32 seq, int event, - u16 flags, int family, int report, gfp_t gfp) +static struct sk_buff * +nft_obj_notify_alloc(struct net *net, const struct nft_table *table, + struct nft_object *obj, u32 portid, u32 seq, int event, + u16 flags, int family, int report, gfp_t gfp) { - struct nftables_pernet *nft_net = nft_pernet(net); struct sk_buff *skb; int err; if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) - return; + return NULL; skb = nlmsg_new(NLMSG_GOODSIZE, gfp); if (skb == NULL) @@ -8610,10 +8609,10 @@ __nft_obj_notify(struct net *net, const struct nft_table *table, goto err; } - nft_notify_enqueue(skb, report, &nft_net->notify_list); - return; + return skb; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); + return NULL; } void nft_obj_notify(struct net *net, const struct nft_table *table, @@ -8622,6 +8621,7 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, { char *buf = kasprintf(gfp, "%s:%u", table->name, nft_base_seq(net)); + struct sk_buff *skb; audit_log_nfcfg(buf, family, @@ -8632,17 +8632,27 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, gfp); kfree(buf); - __nft_obj_notify(net, table, obj, portid, seq, event, - flags, family, report, gfp); + /* Called from the packet path, holding no mutex: notify_list is + * serialised by commit_mutex, so send this notification directly. + */ + skb = nft_obj_notify_alloc(net, table, obj, portid, seq, event, + flags, family, report, gfp); + if (skb) + nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report, gfp); } EXPORT_SYMBOL_GPL(nft_obj_notify); static void nf_tables_obj_notify(const struct nft_ctx *ctx, struct nft_object *obj, int event) { - __nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, - ctx->seq, event, ctx->flags, ctx->family, - ctx->report, GFP_KERNEL); + struct nftables_pernet *nft_net = nft_pernet(ctx->net); + struct sk_buff *skb; + + skb = nft_obj_notify_alloc(ctx->net, ctx->table, obj, ctx->portid, + ctx->seq, event, ctx->flags, ctx->family, + ctx->report, GFP_KERNEL); + if (skb) + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); } /* From 7458ba03cb515469b937419b515aabd311e2bb88 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 3 Aug 2026 11:04:26 -0700 Subject: [PATCH 55/76] mm/swap: reject swapon() on filesystem-level encrypted files commit c310a8932a3107c9bc8f01d473e9d085f8aa9c98 upstream. ext4 and f2fs don't prevent filesystem-level encrypted files from being set up directly as swap files. In this case, encryption is bypassed. No one should be doing this, vs. the methods of encrypted swap that actually do work (such as swapping to a dm-crypt device, or swapping to a loopback device on top of a filesystem-level encrypted file). Nevertheless, to prevent user error, make swapon() explicitly reject this case. Document this behavior in fscrypt.rst as well. Link: https://lore.kernel.org/20260803180426.3123-1-ebiggers@kernel.org Fixes: 9bd8212f981e ("ext4 crypto: add encryption policy and password salt support") Fixes: f424f664f0e8 ("f2fs crypto: add encryption policy and password salt support") Signed-off-by: Eric Biggers Reviewed-by: Baoquan He Reviewed-by: Muhammad Usama Anjum Reviewed-by: "Darrick J. Wong" Cc: Barry Song Cc: Chris Li Cc: Kairui Song Cc: Kemeng Shi Cc: Nhat Pham Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 34f3c35dd13a3e2e0a0e5a7b8edd563572d67445) Signed-off-by: Wentao Guan --- Documentation/filesystems/fscrypt.rst | 4 ++++ mm/swapfile.c | 7 +++++++ 2 files changed, 11 insertions(+) diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index 696a5844bfa3b..480252ec8c781 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -1245,6 +1245,10 @@ astute users may notice some differences in behavior: - DAX (Direct Access) is not supported on encrypted files. +- Encrypted files cannot be used directly as swap files. To swap to + an encrypted file, set up a loopback device on top of it. + Alternatively, encrypted swap can use a dm-crypt device. + - The maximum length of an encrypted symlink is 2 bytes shorter than the maximum length of an unencrypted symlink. For example, on an EXT4 filesystem with a 4K block size, unencrypted symlinks can be up diff --git a/mm/swapfile.c b/mm/swapfile.c index e6a207c940707..4b6b694496584 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3458,6 +3458,13 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = -EBUSY; goto bad_swap_unlock_inode; } + if (IS_ENCRYPTED(inode)) { + pr_warn_once( + "Filesystem-level encrypted swapfile '%s' is unsupported. Create a loop device over it, or use dm-crypt\n", + name->name); + error = -EINVAL; + goto bad_swap_unlock_inode; + } /* * The swap subsystem needs a major overhaul to support this. From 16b3409b2d79b7917a52589caa77809cab603216 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 3 Aug 2026 11:18:41 -0700 Subject: [PATCH 56/76] kunit: irq: Continue increasing hrtimer interval for longer commit faa6c4c4e4ac69926564688a926105621295d613 upstream. Currently, kunit_irq_test_timer_func() stops increasing the hrtimer interval as soon as some forward progress is made in each of softirq and task context. Update it to use a more aggressive strategy: increase the interval as long as the hrtimer is running significantly faster than either context. This resolves an occasional hang in the CRC and crypto library tests under qemu-system-s390x. It was exposed by the change in the default preemption model on s390 from NONE to LAZY. That seems to have exposed the issue by allowing some forward progress to be made while the actual system timer tick is still starved, preventing jiffies from increasing or the task context from making much progress towards max_iterations. Fixes: 201ceb94aa1d ("kunit: irq: Ensure timer doesn't fire too frequently") Cc: stable@vger.kernel.org Reviewed-by: David Gow Acked-by: Ard Biesheuvel Link: https://patch.msgid.link/20260803181842.44648-1-ebiggers@kernel.org Signed-off-by: Eric Biggers Signed-off-by: Greg Kroah-Hartman (cherry picked from commit e90bc78125cd7a36d0ef166f681c62a584156fe5) Signed-off-by: Wentao Guan --- include/kunit/run-in-irq-context.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/include/kunit/run-in-irq-context.h b/include/kunit/run-in-irq-context.h index bfe60d6cf28d8..3802b6fb218ed 100644 --- a/include/kunit/run-in-irq-context.h +++ b/include/kunit/run-in-irq-context.h @@ -38,11 +38,13 @@ static enum hrtimer_restart kunit_irq_test_timer_func(struct hrtimer *timer) softirq_calls = atomic_read(&state->softirq_func_calls); /* - * If the timer is firing too often for the softirq or task to ever have - * a chance to run, increase the timer interval. This is needed on very - * slow systems. + * If the hrtimer is running much faster than the bh_work or the task, + * then it is firing too fast and might be starving those contexts as + * well as the actual system timer tick. Increase the interval. */ - if (hardirq_calls >= 20 && (softirq_calls == 0 || task_calls == 0)) + if (hardirq_calls >= 20 && + (hardirq_calls / 2 > softirq_calls || + hardirq_calls / 2 > task_calls)) state->interval = ktime_add_ns(state->interval, 250); if (!state->func(state->test_specific_state)) From 86f3ad886cab7866db1b763e71567cf51a92038d Mon Sep 17 00:00:00 2001 From: Bryam Vargas Date: Mon, 22 Jun 2026 01:52:15 -0500 Subject: [PATCH 57/76] crypto: virtio - bound the akcipher result length commit f77a956f6a19f9463ef1527c9d0cda50dded6b92 upstream. virtio_crypto_dataq_akcipher_callback() sets the result length from the device-reported response length without bounding it to the destination buffer, which was allocated for the original request length. sg_copy_from_buffer() then reads that many bytes from the destination buffer; a backend reporting a larger length over-reads adjacent kernel heap into the caller's scatterlist (an out-of-bounds read). Clamp the reported length to the originally requested destination length. A conforming device reports no more than that, so valid results are unaffected. Fixes: a36bd0ad9fbf ("virtio-crypto: adjust dst_len at ops callback") Cc: stable@vger.kernel.org Signed-off-by: Bryam Vargas Message-ID: <20260622-b4-disp-3a2c09a8-v2-1-d1a809281db4@proton.me> Signed-off-by: Michael S. Tsirkin Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 5545de5050cbc3594506d74f2c392b0716cf8bca) Signed-off-by: Wentao Guan --- drivers/crypto/virtio/virtio_crypto_akcipher_algs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c index 2e44915c9f239..090280af6b0cd 100644 --- a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c +++ b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c @@ -88,7 +88,8 @@ static void virtio_crypto_dataq_akcipher_callback(struct virtio_crypto_request * } /* actual length may be less than dst buffer */ - akcipher_req->dst_len = len - sizeof(vc_req->status); + akcipher_req->dst_len = min_t(unsigned int, len - sizeof(vc_req->status), + akcipher_req->dst_len); sg_copy_from_buffer(akcipher_req->dst, sg_nents(akcipher_req->dst), vc_akcipher_req->dst_buf, akcipher_req->dst_len); virtio_crypto_akcipher_finalize_req(vc_akcipher_req, akcipher_req, error); From 1ee4d6685dcfdd7a4ab3e040fe7daceaf2822490 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 8 Jun 2026 17:58:45 +0000 Subject: [PATCH 58/76] crypto: qcom-rng - Enable clock in hwrng case commit 0fd97bbda2842d7dcccee599ac2c0e9554bdddbc upstream. Fix qcom-rng.c to enable the clock before accessing the hardware. Fixes: f29cd5bb64c2 ("crypto: qcom-rng - Add hw_random interface support") Cc: stable@vger.kernel.org Reviewed-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 070b73019a53497c567f3456d97b344b755b93bf) Signed-off-by: Wentao Guan --- drivers/crypto/qcom-rng.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/crypto/qcom-rng.c b/drivers/crypto/qcom-rng.c index 0685ba122e8ac..921def6263ead 100644 --- a/drivers/crypto/qcom-rng.c +++ b/drivers/crypto/qcom-rng.c @@ -113,6 +113,13 @@ static int qcom_rng_seed(struct crypto_rng *tfm, const u8 *seed, return 0; } +static int qcom_hwrng_init(struct hwrng *hwrng) +{ + struct qcom_rng *qrng = container_of(hwrng, struct qcom_rng, hwrng); + + return clk_prepare_enable(qrng->clk); +} + static int qcom_hwrng_read(struct hwrng *hwrng, void *data, size_t max, bool wait) { struct qcom_rng *qrng = container_of(hwrng, struct qcom_rng, hwrng); @@ -120,6 +127,13 @@ static int qcom_hwrng_read(struct hwrng *hwrng, void *data, size_t max, bool wai return qcom_rng_read(qrng, data, max); } +static void qcom_hwrng_cleanup(struct hwrng *hwrng) +{ + struct qcom_rng *qrng = container_of(hwrng, struct qcom_rng, hwrng); + + clk_disable_unprepare(qrng->clk); +} + static int qcom_rng_enable(struct qcom_rng *rng) { u32 val; @@ -208,7 +222,9 @@ static int qcom_rng_probe(struct platform_device *pdev) if (rng->match_data->hwrng_support) { rng->hwrng.name = "qcom_hwrng"; + rng->hwrng.init = qcom_hwrng_init; rng->hwrng.read = qcom_hwrng_read; + rng->hwrng.cleanup = qcom_hwrng_cleanup; rng->hwrng.quality = QCOM_TRNG_QUALITY; ret = devm_hwrng_register(&pdev->dev, &rng->hwrng); if (ret) { From 7ce1ac0e0581d55ea3460bb58307602fdd726136 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 8 Jun 2026 17:58:47 +0000 Subject: [PATCH 59/76] crypto: qcom-rng - Remove crypto_rng interface commit 2ecdf5c9910e20f73639bc322f0518a3439d17c0 upstream. qcom-rng.c exposes the same hardware through two completely separate interfaces, crypto_rng and hwrng. However, the implementation of this is buggy because it permits generation operations from these interfaces to run concurrently with each other, accessing the same registers. That is, qcom_rng_generate() synchronizes with itself but not with qcom_hwrng_read(). This results in potential repetition of output from the RNG, output of non-random values, etc. Fortunately, there's actually no point in hardware RNG drivers implementing the crypto_rng interface. It's not actually used by anything besides the "rng" algorithm type of AF_ALG, which in turn is not actually used in practice. Other crypto_rng hardware drivers are likewise being phased out, leaving just the hwrng support. Thus, remove it to simplify the code and avoid conflict (and confusion) with the hwrng interface which is the one that actually matters. Fixes: f29cd5bb64c2 ("crypto: qcom-rng - Add hw_random interface support") Cc: stable@vger.kernel.org Signed-off-by: Eric Biggers Reviewed-by: Dmitry Baryshkov Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 14d9ee8286460a7b82f3b8610b5c7ebf4550b06b) Signed-off-by: Wentao Guan --- drivers/crypto/Kconfig | 1 - drivers/crypto/qcom-rng.c | 158 +++++--------------------------------- 2 files changed, 19 insertions(+), 140 deletions(-) diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index 43deeee1eae5b..0bc8aa27ab705 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -701,7 +701,6 @@ config CRYPTO_DEV_QCOM_RNG tristate "Qualcomm Random Number Generator Driver" depends on ARCH_QCOM || COMPILE_TEST depends on HW_RANDOM - select CRYPTO_RNG help This driver provides support for the Random Number Generator hardware found on Qualcomm SoCs. diff --git a/drivers/crypto/qcom-rng.c b/drivers/crypto/qcom-rng.c index 921def6263ead..4f1e83c2fdde0 100644 --- a/drivers/crypto/qcom-rng.c +++ b/drivers/crypto/qcom-rng.c @@ -3,10 +3,8 @@ // // Based on msm-rng.c and downstream driver -#include #include #include -#include #include #include #include @@ -32,24 +30,15 @@ #define QCOM_TRNG_QUALITY 1024 struct qcom_rng { - struct mutex lock; void __iomem *base; struct clk *clk; struct hwrng hwrng; - struct qcom_rng_match_data *match_data; -}; - -struct qcom_rng_ctx { - struct qcom_rng *rng; }; struct qcom_rng_match_data { - bool skip_init; bool hwrng_support; }; -static struct qcom_rng *qcom_rng_dev; - static int qcom_rng_read(struct qcom_rng *rng, u8 *data, unsigned int max) { unsigned int currsize = 0; @@ -82,37 +71,6 @@ static int qcom_rng_read(struct qcom_rng *rng, u8 *data, unsigned int max) return currsize; } -static int qcom_rng_generate(struct crypto_rng *tfm, - const u8 *src, unsigned int slen, - u8 *dstn, unsigned int dlen) -{ - struct qcom_rng_ctx *ctx = crypto_rng_ctx(tfm); - struct qcom_rng *rng = ctx->rng; - int ret; - - ret = clk_prepare_enable(rng->clk); - if (ret) - return ret; - - mutex_lock(&rng->lock); - - ret = qcom_rng_read(rng, dstn, dlen); - - mutex_unlock(&rng->lock); - clk_disable_unprepare(rng->clk); - - if (ret >= 0) - ret = 0; - - return ret; -} - -static int qcom_rng_seed(struct crypto_rng *tfm, const u8 *seed, - unsigned int slen) -{ - return 0; -} - static int qcom_hwrng_init(struct hwrng *hwrng) { struct qcom_rng *qrng = container_of(hwrng, struct qcom_rng, hwrng); @@ -134,74 +92,26 @@ static void qcom_hwrng_cleanup(struct hwrng *hwrng) clk_disable_unprepare(qrng->clk); } -static int qcom_rng_enable(struct qcom_rng *rng) -{ - u32 val; - int ret; - - ret = clk_prepare_enable(rng->clk); - if (ret) - return ret; - - /* Enable PRNG only if it is not already enabled */ - val = readl_relaxed(rng->base + PRNG_CONFIG); - if (val & PRNG_CONFIG_HW_ENABLE) - goto already_enabled; - - val = readl_relaxed(rng->base + PRNG_LFSR_CFG); - val &= ~PRNG_LFSR_CFG_MASK; - val |= PRNG_LFSR_CFG_CLOCKS; - writel(val, rng->base + PRNG_LFSR_CFG); - - val = readl_relaxed(rng->base + PRNG_CONFIG); - val |= PRNG_CONFIG_HW_ENABLE; - writel(val, rng->base + PRNG_CONFIG); - -already_enabled: - clk_disable_unprepare(rng->clk); - - return 0; -} - -static int qcom_rng_init(struct crypto_tfm *tfm) -{ - struct qcom_rng_ctx *ctx = crypto_tfm_ctx(tfm); - - ctx->rng = qcom_rng_dev; - - if (!ctx->rng->match_data->skip_init) - return qcom_rng_enable(ctx->rng); - - return 0; -} - -static struct rng_alg qcom_rng_alg = { - .generate = qcom_rng_generate, - .seed = qcom_rng_seed, - .seedsize = 0, - .base = { - .cra_name = "stdrng", - .cra_driver_name = "qcom-rng", - .cra_flags = CRYPTO_ALG_TYPE_RNG, - .cra_priority = 300, - .cra_ctxsize = sizeof(struct qcom_rng_ctx), - .cra_module = THIS_MODULE, - .cra_init = qcom_rng_init, - } -}; - static int qcom_rng_probe(struct platform_device *pdev) { + const struct qcom_rng_match_data *match_data; struct qcom_rng *rng; int ret; + match_data = device_get_match_data(&pdev->dev); + if (match_data == NULL || !match_data->hwrng_support) { + dev_info(&pdev->dev, "TRNG support not detected\n"); + /* + * In this case the driver does nothing except the dev_info(), + * but bind the device anyway to avoid effects on GCC state. + */ + return 0; + } + rng = devm_kzalloc(&pdev->dev, sizeof(*rng), GFP_KERNEL); if (!rng) return -ENOMEM; - platform_set_drvdata(pdev, rng); - mutex_init(&rng->lock); - rng->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(rng->base)) return PTR_ERR(rng->base); @@ -210,55 +120,26 @@ static int qcom_rng_probe(struct platform_device *pdev) if (IS_ERR(rng->clk)) return PTR_ERR(rng->clk); - rng->match_data = (struct qcom_rng_match_data *)device_get_match_data(&pdev->dev); - - qcom_rng_dev = rng; - ret = crypto_register_rng(&qcom_rng_alg); - if (ret) { - dev_err(&pdev->dev, "Register crypto rng failed: %d\n", ret); - qcom_rng_dev = NULL; - return ret; - } - - if (rng->match_data->hwrng_support) { - rng->hwrng.name = "qcom_hwrng"; - rng->hwrng.init = qcom_hwrng_init; - rng->hwrng.read = qcom_hwrng_read; - rng->hwrng.cleanup = qcom_hwrng_cleanup; - rng->hwrng.quality = QCOM_TRNG_QUALITY; - ret = devm_hwrng_register(&pdev->dev, &rng->hwrng); - if (ret) { - dev_err(&pdev->dev, "Register hwrng failed: %d\n", ret); - qcom_rng_dev = NULL; - goto fail; - } - } - - return ret; -fail: - crypto_unregister_rng(&qcom_rng_alg); + rng->hwrng.name = "qcom_hwrng"; + rng->hwrng.init = qcom_hwrng_init; + rng->hwrng.read = qcom_hwrng_read; + rng->hwrng.cleanup = qcom_hwrng_cleanup; + rng->hwrng.quality = QCOM_TRNG_QUALITY; + ret = devm_hwrng_register(&pdev->dev, &rng->hwrng); + if (ret) + dev_err(&pdev->dev, "Register hwrng failed: %d\n", ret); return ret; } -static void qcom_rng_remove(struct platform_device *pdev) -{ - crypto_unregister_rng(&qcom_rng_alg); - - qcom_rng_dev = NULL; -} - static struct qcom_rng_match_data qcom_prng_match_data = { - .skip_init = false, .hwrng_support = false, }; static struct qcom_rng_match_data qcom_prng_ee_match_data = { - .skip_init = true, .hwrng_support = false, }; static struct qcom_rng_match_data qcom_trng_match_data = { - .skip_init = true, .hwrng_support = true, }; @@ -278,7 +159,6 @@ MODULE_DEVICE_TABLE(of, qcom_rng_of_match); static struct platform_driver qcom_rng_driver = { .probe = qcom_rng_probe, - .remove = qcom_rng_remove, .driver = { .name = KBUILD_MODNAME, .of_match_table = of_match_ptr(qcom_rng_of_match), From c83eb47e4ac8a831d8fc3aa6392f9d0cb0d7b324 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 8 Jun 2026 17:58:46 +0000 Subject: [PATCH 60/76] crypto: qcom-rng - Allow zero as a random number commit 4ef04bdc0c9f98836d1638be516f6bf1bad55f69 upstream. Zero is a valid random number and needs to be allowed. Otherwise the output is distinguishable from random. Fixes: f29cd5bb64c2 ("crypto: qcom-rng - Add hw_random interface support") Cc: stable@vger.kernel.org Reviewed-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 4c0018320942003bfedd0a1c4cce3f036d363a7f) Signed-off-by: Wentao Guan --- drivers/crypto/qcom-rng.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/crypto/qcom-rng.c b/drivers/crypto/qcom-rng.c index 4f1e83c2fdde0..233aa226d994d 100644 --- a/drivers/crypto/qcom-rng.c +++ b/drivers/crypto/qcom-rng.c @@ -54,8 +54,6 @@ static int qcom_rng_read(struct qcom_rng *rng, u8 *data, unsigned int max) return ret; val = readl_relaxed(rng->base + PRNG_DATA_OUT); - if (!val) - return -EINVAL; if ((max - currsize) >= WORD_SZ) { memcpy(data, &val, WORD_SZ); From 390c375f1f078138fad1277cff0a5caa39465178 Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Thu, 11 Jun 2026 12:36:35 +0200 Subject: [PATCH 61/76] crypto: atmel-tdes - use scatterlist length before DMA mapping commit ba199bdaa80b09a7dd92f28751de7f3dbb06c510 upstream. Using sg_dma_len() is only valid after mapping the scatterlist with dma_map_sg(). However, atmel_tdes_crypt_start() uses it before mapping to compare input/output lengths and to compute the transfer count. Use the original scatterlist lengths before DMA mapping to avoid reading stale or uninitialized DMA lengths when CONFIG_NEED_SG_DMA_LENGTH=y. Drop the output scatterlist length in the fast path since it is equal to ->in_sg->length and does not change the transfer count. Fixes: 13802005d8f2 ("crypto: atmel - add Atmel DES/TDES driver") Fixes: 1f858040c2f7 ("crypto: atmel-tdes - add support for latest release of the IP (0x700)") Cc: stable@vger.kernel.org Signed-off-by: Thorsten Blum Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 302ecd1106065e88b64147b015ff87afa3d7e507) Signed-off-by: Wentao Guan --- drivers/crypto/atmel-tdes.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c index 643e507f9c020..d380f6741a2c5 100644 --- a/drivers/crypto/atmel-tdes.c +++ b/drivers/crypto/atmel-tdes.c @@ -463,14 +463,13 @@ static int atmel_tdes_crypt_start(struct atmel_tdes_dev *dd) IS_ALIGNED(dd->out_sg->length, dd->ctx->block_size); fast = in && out; - if (sg_dma_len(dd->in_sg) != sg_dma_len(dd->out_sg)) + if (dd->in_sg->length != dd->out_sg->length) fast = 0; } if (fast) { - count = min_t(size_t, dd->total, sg_dma_len(dd->in_sg)); - count = min_t(size_t, count, sg_dma_len(dd->out_sg)); + count = min_t(size_t, dd->total, dd->in_sg->length); err = dma_map_sg(dd->dev, dd->in_sg, 1, DMA_TO_DEVICE); if (!err) { From 243cf49571d31fc1aa560f8b7bddc4168a96d1f3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jan=20Sebastian=20G=C3=B6tte?= Date: Mon, 3 Aug 2026 21:26:21 +0200 Subject: [PATCH 62/76] crypto: krb5 - use kfree_sensitive() for derived key buffers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit f7d53dd3f267e46a784f219a75072f2f400d42b9 upstream. crypto_krb5_prepare_encryption() and crypto_krb5_prepare_checksum() free the buffer holding the freshly derived keys with plain kfree(), leaving the key material behind in the freed slab object. Fixes: 3936f02bf2d3 ("crypto/krb5: Implement Kerberos crypto core") Cc: stable@vger.kernel.org Signed-off-by: Jan Sebastian Götte Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 731a5b6fb4c1705f9405d9029dd64ea81e336207) Signed-off-by: Wentao Guan --- crypto/krb5/krb5_api.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/crypto/krb5/krb5_api.c b/crypto/krb5/krb5_api.c index 03395b89cc61e..b377f4f7558da 100644 --- a/crypto/krb5/krb5_api.c +++ b/crypto/krb5/krb5_api.c @@ -263,10 +263,10 @@ struct crypto_aead *crypto_krb5_prepare_encryption(const struct krb5_enctype *kr goto err; } - kfree(keys.data); + kfree_sensitive(keys.data); return ci; err: - kfree(keys.data); + kfree_sensitive(keys.data); return ERR_PTR(ret); } EXPORT_SYMBOL(crypto_krb5_prepare_encryption); @@ -333,10 +333,10 @@ struct crypto_shash *crypto_krb5_prepare_checksum(const struct krb5_enctype *krb goto err; } - kfree(keys.data); + kfree_sensitive(keys.data); return ci; err: - kfree(keys.data); + kfree_sensitive(keys.data); return ERR_PTR(ret); } EXPORT_SYMBOL(crypto_krb5_prepare_checksum); From e4fc670af8377fec12de9d5a7c5d4f61e244a6de Mon Sep 17 00:00:00 2001 From: Md Sadre Alam Date: Fri, 7 Aug 2026 12:24:54 +0530 Subject: [PATCH 63/76] crypto: qce - fix CCM AAD buffer underallocation commit 7f2345f47dd189625f657cd72437179ab4170ee1 upstream. The AAD buffer allocated in qce_aead_ccm_prepare_buf_assoclen() can be smaller than the length later programmed into the DMA scatterlist. The allocation size is currently calculated as: ALIGN(assoclen, 16) + MAX_CCM_ADATA_HEADER_LEN while the DMA length is set to: ALIGN(assoclen + adata_header_len, 16) Since ALIGN() does not distribute over addition, the allocation can be smaller than the DMA length. For example, when assoclen = 32 and adata_header_len = 2: allocation = ALIGN(32, 16) + 6 = 38 DMA length = ALIGN(32 + 2, 16) = 48 As a result, the QCE hardware can read beyond the allocated buffer while computing the CBC-MAC over the associated data. The extra bytes are folded into the authentication tag, resulting in an incorrect tag and causing CCM self-test failures such as: alg: aead: ccm-aes-qce encryption test failed (wrong result) on test vector 8 Fix the allocation by adding the maximum possible AAD header length before alignment: ALIGN(assoclen + MAX_CCM_ADATA_HEADER_LEN, 16) This guarantees that the allocated buffer is large enough for the fully padded AAD data for all supported header sizes. Cc: stable@vger.kernel.org Fixes: 9363efb4181c ("crypto: qce - Add support for AEAD algorithms") Signed-off-by: Md Sadre Alam Reviewed-by: Bartosz Golaszewski Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 2f65718b9c1095eef1ae9b374aa0384b1b083f3c) Signed-off-by: Wentao Guan --- drivers/crypto/qce/aead.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/qce/aead.c b/drivers/crypto/qce/aead.c index 97b56e92ea33f..0e5d9e1609d89 100644 --- a/drivers/crypto/qce/aead.c +++ b/drivers/crypto/qce/aead.c @@ -203,7 +203,7 @@ qce_aead_ccm_prepare_buf_assoclen(struct aead_request *req) /* Get the msg */ msg_sg = scatterwalk_ffwd(__sg, req->src, req->assoclen); - rctx->adata = kzalloc((ALIGN(assoclen, 16) + MAX_CCM_ADATA_HEADER_LEN) * + rctx->adata = kzalloc(ALIGN(assoclen + MAX_CCM_ADATA_HEADER_LEN, 16) * sizeof(unsigned char), GFP_ATOMIC); if (!rctx->adata) return -ENOMEM; From e8840af4917e4af5ccf7269d52b040cc079c5c31 Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Sun, 21 Jun 2026 21:26:16 +0200 Subject: [PATCH 64/76] crypto: mxs-dcp - fix source scatterlist length access commit c5bcb084a9871e5b62afb5f48b60adfa13b5d9f8 upstream. mxs_dcp_aes_block_crypt() uses sg_dma_len() without mapping the source scatterlist with dma_map_sg() first. Therefore, sg_dma_len() is invalid and could return zero or a stale DMA length, causing encryption and decryption to process the wrong number of bytes when CONFIG_NEED_SG_DMA_LENGTH=y. Use the original scatterlist length instead. Fixes: 15b59e7c3733 ("crypto: mxs - Add Freescale MXS DCP driver") Cc: stable@vger.kernel.org Signed-off-by: Thorsten Blum Reviewed-by: Frank Li Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 182f16a20d329a1c818d51dad57d9bf43d356c7c) Signed-off-by: Wentao Guan --- drivers/crypto/mxs-dcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/mxs-dcp.c b/drivers/crypto/mxs-dcp.c index 133ebc9982362..595b2fd84667e 100644 --- a/drivers/crypto/mxs-dcp.c +++ b/drivers/crypto/mxs-dcp.c @@ -353,7 +353,7 @@ static int mxs_dcp_aes_block_crypt(struct crypto_async_request *arq) for_each_sg(req->src, src, sg_nents(req->src), i) { src_buf = sg_virt(src); - len = sg_dma_len(src); + len = src->length; tlen += len; limit_hit = tlen > req->cryptlen; From 6e9ddb1cd9c6796addb7345cc1596d220eabb5d0 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 22 Jun 2026 15:18:09 +0200 Subject: [PATCH 65/76] crypto: qce - Remove unsafe/deprecated algorithms commit 7e28b0a5c4b7d075b98ce6d8f5290a9d3deb5b92 upstream. Remove algorithms that are either unsafe or deprecated and have no in-kernel users that cannot be served by the ARM CE implementations. AES-ECB reveals plaintext patterns (identical plaintext blocks produce identical ciphertext blocks) and should not be exposed as a hardware- accelerated primitive. DES, Triple DES and HMAC-SHA1 have been deprecated for years. Remove sha1, ecb(aes), ecb(des), cbc(des), ecb(des3_ede), cbc(des3_ede), hmac(sha1) and all AEAD variants built on these primitives as well as authenc(hmac(sha256),cbc(des)). Also clean up the - now dead - code, flags and constants. Cc: stable@vger.kernel.org Acked-by: Eric Biggers Tested-by: Kuldeep Singh Signed-off-by: Bartosz Golaszewski Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 545a6b9c91e2b68fc9c5c11a9ca935e916f70cca) Signed-off-by: Wentao Guan --- drivers/crypto/qce/aead.c | 56 +------------------- drivers/crypto/qce/common.c | 55 +++++--------------- drivers/crypto/qce/common.h | 16 ++---- drivers/crypto/qce/regs-v5.h | 4 -- drivers/crypto/qce/sha.c | 30 +---------- drivers/crypto/qce/sha.h | 1 - drivers/crypto/qce/skcipher.c | 97 +---------------------------------- 7 files changed, 20 insertions(+), 239 deletions(-) diff --git a/drivers/crypto/qce/aead.c b/drivers/crypto/qce/aead.c index 0e5d9e1609d89..d1f5b17b5313d 100644 --- a/drivers/crypto/qce/aead.c +++ b/drivers/crypto/qce/aead.c @@ -8,8 +8,6 @@ #include #include #include -#include -#include #include #include #include "aead.h" @@ -597,7 +595,6 @@ static int qce_aead_setkey(struct crypto_aead *tfm, const u8 *key, unsigned int struct qce_aead_ctx *ctx = crypto_aead_ctx(tfm); struct crypto_authenc_keys authenc_keys; unsigned long flags = to_aead_tmpl(tfm)->alg_flags; - u32 _key[6]; int err; err = crypto_authenc_extractkeys(&authenc_keys, key, keylen); @@ -608,26 +605,7 @@ static int qce_aead_setkey(struct crypto_aead *tfm, const u8 *key, unsigned int authenc_keys.authkeylen > QCE_MAX_KEY_SIZE) return -EINVAL; - if (IS_DES(flags)) { - err = verify_aead_des_key(tfm, authenc_keys.enckey, authenc_keys.enckeylen); - if (err) - return err; - } else if (IS_3DES(flags)) { - err = verify_aead_des3_key(tfm, authenc_keys.enckey, authenc_keys.enckeylen); - if (err) - return err; - /* - * The crypto engine does not support any two keys - * being the same for triple des algorithms. The - * verify_skcipher_des3_key does not check for all the - * below conditions. Schedule fallback in this case. - */ - memcpy(_key, authenc_keys.enckey, DES3_EDE_KEY_SIZE); - if (!((_key[0] ^ _key[2]) | (_key[1] ^ _key[3])) || - !((_key[2] ^ _key[4]) | (_key[3] ^ _key[5])) || - !((_key[0] ^ _key[4]) | (_key[1] ^ _key[5]))) - ctx->need_fallback = true; - } else if (IS_AES(flags)) { + if (IS_AES(flags)) { /* No random key sizes */ if (authenc_keys.enckeylen != AES_KEYSIZE_128 && authenc_keys.enckeylen != AES_KEYSIZE_192 && @@ -698,38 +676,6 @@ struct qce_aead_def { }; static const struct qce_aead_def aead_def[] = { - { - .flags = QCE_ALG_DES | QCE_MODE_CBC | QCE_HASH_SHA1_HMAC, - .name = "authenc(hmac(sha1),cbc(des))", - .drv_name = "authenc-hmac-sha1-cbc-des-qce", - .blocksize = DES_BLOCK_SIZE, - .ivsize = DES_BLOCK_SIZE, - .maxauthsize = SHA1_DIGEST_SIZE, - }, - { - .flags = QCE_ALG_3DES | QCE_MODE_CBC | QCE_HASH_SHA1_HMAC, - .name = "authenc(hmac(sha1),cbc(des3_ede))", - .drv_name = "authenc-hmac-sha1-cbc-3des-qce", - .blocksize = DES3_EDE_BLOCK_SIZE, - .ivsize = DES3_EDE_BLOCK_SIZE, - .maxauthsize = SHA1_DIGEST_SIZE, - }, - { - .flags = QCE_ALG_DES | QCE_MODE_CBC | QCE_HASH_SHA256_HMAC, - .name = "authenc(hmac(sha256),cbc(des))", - .drv_name = "authenc-hmac-sha256-cbc-des-qce", - .blocksize = DES_BLOCK_SIZE, - .ivsize = DES_BLOCK_SIZE, - .maxauthsize = SHA256_DIGEST_SIZE, - }, - { - .flags = QCE_ALG_3DES | QCE_MODE_CBC | QCE_HASH_SHA256_HMAC, - .name = "authenc(hmac(sha256),cbc(des3_ede))", - .drv_name = "authenc-hmac-sha256-cbc-3des-qce", - .blocksize = DES3_EDE_BLOCK_SIZE, - .ivsize = DES3_EDE_BLOCK_SIZE, - .maxauthsize = SHA256_DIGEST_SIZE, - }, { .flags = QCE_ALG_AES | QCE_MODE_CBC | QCE_HASH_SHA256_HMAC, .name = "authenc(hmac(sha256),cbc(aes))", diff --git a/drivers/crypto/qce/common.c b/drivers/crypto/qce/common.c index 04253a8d33409..0754a1bdd9d64 100644 --- a/drivers/crypto/qce/common.c +++ b/drivers/crypto/qce/common.c @@ -8,7 +8,6 @@ #include #include #include -#include #include #include "cipher.h" @@ -115,18 +114,16 @@ static u32 qce_auth_cfg(unsigned long flags, u32 key_size, u32 auth_size) cfg |= AUTH_KEY_SZ_AES256 << AUTH_KEY_SIZE_SHIFT; } - if (IS_SHA1(flags) || IS_SHA1_HMAC(flags)) - cfg |= AUTH_SIZE_SHA1 << AUTH_SIZE_SHIFT; - else if (IS_SHA256(flags) || IS_SHA256_HMAC(flags)) + if (IS_SHA256(flags) || IS_SHA256_HMAC(flags)) cfg |= AUTH_SIZE_SHA256 << AUTH_SIZE_SHIFT; else if (IS_CMAC(flags)) cfg |= AUTH_SIZE_ENUM_16_BYTES << AUTH_SIZE_SHIFT; else if (IS_CCM(flags)) cfg |= (auth_size - 1) << AUTH_SIZE_SHIFT; - if (IS_SHA1(flags) || IS_SHA256(flags)) + if (IS_SHA256(flags)) cfg |= AUTH_MODE_HASH << AUTH_MODE_SHIFT; - else if (IS_SHA1_HMAC(flags) || IS_SHA256_HMAC(flags)) + else if (IS_SHA256_HMAC(flags)) cfg |= AUTH_MODE_HMAC << AUTH_MODE_SHIFT; else if (IS_CCM(flags)) cfg |= AUTH_MODE_CCM << AUTH_MODE_SHIFT; @@ -191,7 +188,7 @@ static int qce_setup_regs_ahash(struct crypto_async_request *async_req) else qce_cpu_to_be32p_array(auth, rctx->digest, digestsize); - iv_words = (IS_SHA1(rctx->flags) || IS_SHA1_HMAC(rctx->flags)) ? 5 : 8; + iv_words = 8; qce_write_array(qce, REG_AUTH_IV0, (u32 *)auth, iv_words); if (rctx->first_blk) @@ -243,19 +240,8 @@ static u32 qce_encr_cfg(unsigned long flags, u32 aes_key_size) if (IS_AES(flags)) cfg |= ENCR_ALG_AES << ENCR_ALG_SHIFT; - else if (IS_DES(flags) || IS_3DES(flags)) - cfg |= ENCR_ALG_DES << ENCR_ALG_SHIFT; - - if (IS_DES(flags)) - cfg |= ENCR_KEY_SZ_DES << ENCR_KEY_SZ_SHIFT; - - if (IS_3DES(flags)) - cfg |= ENCR_KEY_SZ_3DES << ENCR_KEY_SZ_SHIFT; switch (flags & QCE_MODE_MASK) { - case QCE_MODE_ECB: - cfg |= ENCR_MODE_ECB << ENCR_MODE_SHIFT; - break; case QCE_MODE_CBC: cfg |= ENCR_MODE_CBC << ENCR_MODE_SHIFT; break; @@ -340,13 +326,7 @@ static int qce_setup_regs_skcipher(struct crypto_async_request *async_req) encr_cfg = qce_encr_cfg(flags, keylen); - if (IS_DES(flags)) { - enciv_words = 2; - enckey_words = 2; - } else if (IS_3DES(flags)) { - enciv_words = 2; - enckey_words = 6; - } else if (IS_AES(flags)) { + if (IS_AES(flags)) { if (IS_XTS(flags)) qce_xtskey(qce, ctx->enc_key, ctx->enc_keylen, rctx->cryptlen); @@ -357,14 +337,12 @@ static int qce_setup_regs_skcipher(struct crypto_async_request *async_req) qce_write_array(qce, REG_ENCR_KEY0, (u32 *)enckey, enckey_words); - if (!IS_ECB(flags)) { - if (IS_XTS(flags)) - qce_xts_swapiv(enciv, rctx->iv, ivsize); - else - qce_cpu_to_be32p_array(enciv, rctx->iv, ivsize); + if (IS_XTS(flags)) + qce_xts_swapiv(enciv, rctx->iv, ivsize); + else + qce_cpu_to_be32p_array(enciv, rctx->iv, ivsize); - qce_write_array(qce, REG_CNTR0_IV0, (u32 *)enciv, enciv_words); - } + qce_write_array(qce, REG_CNTR0_IV0, (u32 *)enciv, enciv_words); if (IS_ENCRYPT(flags)) encr_cfg |= BIT(ENCODE_SHIFT); @@ -393,10 +371,6 @@ static int qce_setup_regs_skcipher(struct crypto_async_request *async_req) #endif #ifdef CONFIG_CRYPTO_DEV_QCE_AEAD -static const u32 std_iv_sha1[SHA256_DIGEST_SIZE / sizeof(u32)] = { - SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4, 0, 0, 0 -}; - static const u32 std_iv_sha256[SHA256_DIGEST_SIZE / sizeof(u32)] = { SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3, SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7 @@ -473,13 +447,8 @@ static int qce_setup_regs_aead(struct crypto_async_request *async_req) /* Write initial authentication IV only for HMAC algorithms */ if (IS_SHA_HMAC(rctx->flags)) { /* Write default authentication iv */ - if (IS_SHA1_HMAC(rctx->flags)) { - auth_ivsize = SHA1_DIGEST_SIZE; - memcpy(authiv, std_iv_sha1, auth_ivsize); - } else if (IS_SHA256_HMAC(rctx->flags)) { - auth_ivsize = SHA256_DIGEST_SIZE; - memcpy(authiv, std_iv_sha256, auth_ivsize); - } + auth_ivsize = SHA256_DIGEST_SIZE; + memcpy(authiv, std_iv_sha256, auth_ivsize); authiv_words = auth_ivsize / sizeof(u32); qce_write_array(qce, REG_AUTH_IV0, (u32 *)authiv, authiv_words); } else if (IS_CCM(rctx->flags)) { diff --git a/drivers/crypto/qce/common.h b/drivers/crypto/qce/common.h index 02e63ad9f2455..9cd2e6ed8bbb0 100644 --- a/drivers/crypto/qce/common.h +++ b/drivers/crypto/qce/common.h @@ -22,7 +22,7 @@ /* IV length in bytes */ #define QCE_AES_IV_LENGTH AES_BLOCK_SIZE -/* max of AES_BLOCK_SIZE, DES3_EDE_BLOCK_SIZE */ +/* max of AES_BLOCK_SIZE */ #define QCE_MAX_IV_SIZE AES_BLOCK_SIZE /* maximum nonce bytes */ @@ -33,14 +33,10 @@ #define QCE_MAX_ALIGN_SIZE 64 /* cipher algorithms */ -#define QCE_ALG_DES BIT(0) -#define QCE_ALG_3DES BIT(1) #define QCE_ALG_AES BIT(2) /* hash and hmac algorithms */ -#define QCE_HASH_SHA1 BIT(3) #define QCE_HASH_SHA256 BIT(4) -#define QCE_HASH_SHA1_HMAC BIT(5) #define QCE_HASH_SHA256_HMAC BIT(6) #define QCE_HASH_AES_CMAC BIT(7) @@ -58,21 +54,15 @@ #define QCE_ENCRYPT BIT(30) #define QCE_DECRYPT BIT(31) -#define IS_DES(flags) (flags & QCE_ALG_DES) -#define IS_3DES(flags) (flags & QCE_ALG_3DES) #define IS_AES(flags) (flags & QCE_ALG_AES) -#define IS_SHA1(flags) (flags & QCE_HASH_SHA1) #define IS_SHA256(flags) (flags & QCE_HASH_SHA256) -#define IS_SHA1_HMAC(flags) (flags & QCE_HASH_SHA1_HMAC) #define IS_SHA256_HMAC(flags) (flags & QCE_HASH_SHA256_HMAC) #define IS_CMAC(flags) (flags & QCE_HASH_AES_CMAC) -#define IS_SHA(flags) (IS_SHA1(flags) || IS_SHA256(flags)) -#define IS_SHA_HMAC(flags) \ - (IS_SHA1_HMAC(flags) || IS_SHA256_HMAC(flags)) +#define IS_SHA(flags) IS_SHA256(flags) +#define IS_SHA_HMAC(flags) IS_SHA256_HMAC(flags) #define IS_CBC(mode) (mode & QCE_MODE_CBC) -#define IS_ECB(mode) (mode & QCE_MODE_ECB) #define IS_CTR(mode) (mode & QCE_MODE_CTR) #define IS_XTS(mode) (mode & QCE_MODE_XTS) #define IS_CCM(mode) (mode & QCE_MODE_CCM) diff --git a/drivers/crypto/qce/regs-v5.h b/drivers/crypto/qce/regs-v5.h index d59ed27989062..431a7db1a4e72 100644 --- a/drivers/crypto/qce/regs-v5.h +++ b/drivers/crypto/qce/regs-v5.h @@ -203,7 +203,6 @@ #define AUTH_SIZE_SHIFT 9 #define AUTH_SIZE_MASK GENMASK(13, 9) -#define AUTH_SIZE_SHA1 0 #define AUTH_SIZE_SHA256 1 #define AUTH_SIZE_ENUM_1_BYTES 0 #define AUTH_SIZE_ENUM_2_BYTES 1 @@ -284,15 +283,12 @@ #define ENCR_KEY_SZ_SHIFT 3 #define ENCR_KEY_SZ_MASK GENMASK(5, 3) -#define ENCR_KEY_SZ_DES 0 -#define ENCR_KEY_SZ_3DES 1 #define ENCR_KEY_SZ_AES128 0 #define ENCR_KEY_SZ_AES256 2 #define ENCR_ALG_SHIFT 0 #define ENCR_ALG_MASK GENMASK(2, 0) #define ENCR_ALG_NONE 0 -#define ENCR_ALG_DES 1 #define ENCR_ALG_AES 2 #define ENCR_ALG_KASUMI 4 #define ENCR_ALG_SNOW_3G 5 diff --git a/drivers/crypto/qce/sha.c b/drivers/crypto/qce/sha.c index 71b748183cfa8..fc2b891983628 100644 --- a/drivers/crypto/qce/sha.c +++ b/drivers/crypto/qce/sha.c @@ -24,10 +24,6 @@ struct qce_sha_saved_state { static LIST_HEAD(ahash_algs); -static const u32 std_iv_sha1[SHA256_DIGEST_SIZE / sizeof(u32)] = { - SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4, 0, 0, 0 -}; - static const u32 std_iv_sha256[SHA256_DIGEST_SIZE / sizeof(u32)] = { SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3, SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7 @@ -348,9 +344,7 @@ static int qce_ahash_hmac_setkey(struct crypto_ahash *tfm, const u8 *key, return 0; } - if (digestsize == SHA1_DIGEST_SIZE) - alg_name = "sha1-qce"; - else if (digestsize == SHA256_DIGEST_SIZE) + if (digestsize == SHA256_DIGEST_SIZE) alg_name = "sha256-qce"; else return -EINVAL; @@ -411,15 +405,6 @@ struct qce_ahash_def { }; static const struct qce_ahash_def ahash_def[] = { - { - .flags = QCE_HASH_SHA1, - .name = "sha1", - .drv_name = "sha1-qce", - .digestsize = SHA1_DIGEST_SIZE, - .blocksize = SHA1_BLOCK_SIZE, - .statesize = sizeof(struct qce_sha_saved_state), - .std_iv = std_iv_sha1, - }, { .flags = QCE_HASH_SHA256, .name = "sha256", @@ -429,15 +414,6 @@ static const struct qce_ahash_def ahash_def[] = { .statesize = sizeof(struct qce_sha_saved_state), .std_iv = std_iv_sha256, }, - { - .flags = QCE_HASH_SHA1_HMAC, - .name = "hmac(sha1)", - .drv_name = "hmac-sha1-qce", - .digestsize = SHA1_DIGEST_SIZE, - .blocksize = SHA1_BLOCK_SIZE, - .statesize = sizeof(struct qce_sha_saved_state), - .std_iv = std_iv_sha1, - }, { .flags = QCE_HASH_SHA256_HMAC, .name = "hmac(sha256)", @@ -475,9 +451,7 @@ static int qce_ahash_register_one(const struct qce_ahash_def *def, alg->halg.digestsize = def->digestsize; alg->halg.statesize = def->statesize; - if (IS_SHA1(def->flags)) - tmpl->hash_zero = sha1_zero_message_hash; - else if (IS_SHA256(def->flags)) + if (IS_SHA256(def->flags)) tmpl->hash_zero = sha256_zero_message_hash; base = &alg->halg.base; diff --git a/drivers/crypto/qce/sha.h b/drivers/crypto/qce/sha.h index a22695361f165..cb822fc334dc1 100644 --- a/drivers/crypto/qce/sha.h +++ b/drivers/crypto/qce/sha.h @@ -7,7 +7,6 @@ #define _SHA_H_ #include -#include #include #include "common.h" diff --git a/drivers/crypto/qce/skcipher.c b/drivers/crypto/qce/skcipher.c index ffb334eb5b346..61f6450bfd0aa 100644 --- a/drivers/crypto/qce/skcipher.c +++ b/drivers/crypto/qce/skcipher.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include "cipher.h" @@ -208,51 +207,6 @@ static int qce_skcipher_setkey(struct crypto_skcipher *ablk, const u8 *key, return ret; } -static int qce_des_setkey(struct crypto_skcipher *ablk, const u8 *key, - unsigned int keylen) -{ - struct qce_cipher_ctx *ctx = crypto_skcipher_ctx(ablk); - int err; - - err = verify_skcipher_des_key(ablk, key); - if (err) - return err; - - ctx->enc_keylen = keylen; - memcpy(ctx->enc_key, key, keylen); - return 0; -} - -static int qce_des3_setkey(struct crypto_skcipher *ablk, const u8 *key, - unsigned int keylen) -{ - struct qce_cipher_ctx *ctx = crypto_skcipher_ctx(ablk); - u32 _key[6]; - int err; - - err = verify_skcipher_des3_key(ablk, key); - if (err) - return err; - - /* - * The crypto engine does not support any two keys - * being the same for triple des algorithms. The - * verify_skcipher_des3_key does not check for all the - * below conditions. Return -ENOKEY in case any two keys - * are the same. Revisit to see if a fallback cipher - * is needed to handle this condition. - */ - memcpy(_key, key, DES3_EDE_KEY_SIZE); - if (!((_key[0] ^ _key[2]) | (_key[1] ^ _key[3])) || - !((_key[2] ^ _key[4]) | (_key[3] ^ _key[5])) || - !((_key[0] ^ _key[4]) | (_key[1] ^ _key[5]))) - return -ENOKEY; - - ctx->enc_keylen = keylen; - memcpy(ctx->enc_key, key, keylen); - return 0; -} - static int qce_skcipher_crypt(struct skcipher_request *req, int encrypt) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); @@ -275,7 +229,7 @@ static int qce_skcipher_crypt(struct skcipher_request *req, int encrypt) * ECB and CBC algorithms require message lengths to be * multiples of block size. */ - if (IS_ECB(rctx->flags) || IS_CBC(rctx->flags)) + if (IS_CBC(rctx->flags)) if (!IS_ALIGNED(req->cryptlen, blocksize)) return -EINVAL; @@ -358,15 +312,6 @@ struct qce_skcipher_def { }; static const struct qce_skcipher_def skcipher_def[] = { - { - .flags = QCE_ALG_AES | QCE_MODE_ECB, - .name = "ecb(aes)", - .drv_name = "ecb-aes-qce", - .blocksize = AES_BLOCK_SIZE, - .ivsize = 0, - .min_keysize = AES_MIN_KEY_SIZE, - .max_keysize = AES_MAX_KEY_SIZE, - }, { .flags = QCE_ALG_AES | QCE_MODE_CBC, .name = "cbc(aes)", @@ -395,42 +340,6 @@ static const struct qce_skcipher_def skcipher_def[] = { .min_keysize = AES_MIN_KEY_SIZE * 2, .max_keysize = AES_MAX_KEY_SIZE * 2, }, - { - .flags = QCE_ALG_DES | QCE_MODE_ECB, - .name = "ecb(des)", - .drv_name = "ecb-des-qce", - .blocksize = DES_BLOCK_SIZE, - .ivsize = 0, - .min_keysize = DES_KEY_SIZE, - .max_keysize = DES_KEY_SIZE, - }, - { - .flags = QCE_ALG_DES | QCE_MODE_CBC, - .name = "cbc(des)", - .drv_name = "cbc-des-qce", - .blocksize = DES_BLOCK_SIZE, - .ivsize = DES_BLOCK_SIZE, - .min_keysize = DES_KEY_SIZE, - .max_keysize = DES_KEY_SIZE, - }, - { - .flags = QCE_ALG_3DES | QCE_MODE_ECB, - .name = "ecb(des3_ede)", - .drv_name = "ecb-3des-qce", - .blocksize = DES3_EDE_BLOCK_SIZE, - .ivsize = 0, - .min_keysize = DES3_EDE_KEY_SIZE, - .max_keysize = DES3_EDE_KEY_SIZE, - }, - { - .flags = QCE_ALG_3DES | QCE_MODE_CBC, - .name = "cbc(des3_ede)", - .drv_name = "cbc-3des-qce", - .blocksize = DES3_EDE_BLOCK_SIZE, - .ivsize = DES3_EDE_BLOCK_SIZE, - .min_keysize = DES3_EDE_KEY_SIZE, - .max_keysize = DES3_EDE_KEY_SIZE, - }, }; static int qce_skcipher_register_one(const struct qce_skcipher_def *def, @@ -455,9 +364,7 @@ static int qce_skcipher_register_one(const struct qce_skcipher_def *def, alg->ivsize = def->ivsize; alg->min_keysize = def->min_keysize; alg->max_keysize = def->max_keysize; - alg->setkey = IS_3DES(def->flags) ? qce_des3_setkey : - IS_DES(def->flags) ? qce_des_setkey : - qce_skcipher_setkey; + alg->setkey = qce_skcipher_setkey; alg->encrypt = qce_skcipher_encrypt; alg->decrypt = qce_skcipher_decrypt; From 4b21e9500f1f1d5f6425ed2ac82a44ee2ab53d24 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 11 Aug 2026 17:37:36 +0200 Subject: [PATCH 66/76] KVM: s390: vsie: zero stale crypto bits commit 34d5b5b646c91cfb9338d7a12c955a70ffb8c66b upstream. When shadowing crypto access bits from a format0 apcb (crycb 0 or 1), the bits 64..255 are unchanged from whatever is in the vsie page in the crycb and thus in the apcb. This gives a nested guest potential access to a device no longer available. Zero out the remaining bits. Fixes: 6b79de4b056e ("KVM: s390: vsie: allow guest FORMAT-1 CRYCB on host FORMAT-2") Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger Reviewed-by: Claudio Imbrenda Signed-off-by: Claudio Imbrenda Message-ID: <20260811153738.206885-3-borntraeger@linux.ibm.com> Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 935eeba276012916c76243e5cbb843efd8fdb75d) Signed-off-by: Wentao Guan --- arch/s390/kvm/vsie.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 347268f89f2f1..56e82253bb7df 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -184,6 +184,7 @@ static int setup_apcb10(struct kvm_vcpu *vcpu, struct kvm_s390_apcb1 *apcb_s, sizeof(struct kvm_s390_apcb0))) return -EFAULT; + memset(apcb_s, 0, sizeof(*apcb_s)); apcb_s->apm[0] = apcb_h->apm[0] & tmp.apm[0]; apcb_s->aqm[0] = apcb_h->aqm[0] & tmp.aqm[0] & 0xffff000000000000UL; apcb_s->adm[0] = apcb_h->adm[0] & tmp.adm[0] & 0xffff000000000000UL; From 8868c928989230e832b64a0651f6fcf9ba72b217 Mon Sep 17 00:00:00 2001 From: Griffin Kroah-Hartman Date: Mon, 13 Jul 2026 17:43:53 +0200 Subject: [PATCH 67/76] usb: core: Add lock to usb_wakeup_notification() commit e263e18a9e7b1ff3e7301f0801c6ff87c31adfb6 upstream. Add a spin lock to usb_wakeup notification to prevent a race condition with dereferencing freed memory. This could be hit by the xHCI driver as it calls this function from an IRQ and could race with the hub_disconnect() function, which properly grabs this lock to protect the state of the device. Assisted-by: gkh_clanker_t1000 Signed-off-by: Griffin Kroah-Hartman Link: https://patch.msgid.link/20260713-usb_core_patches_1-v1-3-7721c2b33f53@kroah.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit d80b946804674069db7ce6657319a71cf8eeaa5a) Signed-off-by: Wentao Guan --- drivers/usb/core/hub.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 5bf1bd87afff7..c5ce8458cbf16 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -757,10 +757,12 @@ void usb_wakeup_notification(struct usb_device *hdev, { struct usb_hub *hub; struct usb_port *port_dev; + unsigned long flags; if (!hdev) return; + spin_lock_irqsave(&device_state_lock, flags); hub = usb_hub_to_struct_hub(hdev); if (hub) { port_dev = hub->ports[portnum - 1]; @@ -770,6 +772,7 @@ void usb_wakeup_notification(struct usb_device *hdev, set_bit(portnum, hub->wakeup_bits); kick_hub_wq(hub); } + spin_unlock_irqrestore(&device_state_lock, flags); } EXPORT_SYMBOL_GPL(usb_wakeup_notification); From 8ea9ac5d958bc2d3419ed8d848db15fdcc9a5ca1 Mon Sep 17 00:00:00 2001 From: Griffin Kroah-Hartman Date: Wed, 22 Jul 2026 10:17:39 +0200 Subject: [PATCH 68/76] usb: core: Strengthen error handling in hub_hub_status() commit a29496745aa335d97f617385809583241e118610 upstream. Add additional error handling after the call to get_hub_status() in hub_hub_status(). get_hub_status() uses usb_control_msg() which does not verify that the message is the correct length, substituting it for usb_control_msg_recv() would also solve this issue but increase memory allocations. Instead, error handling is copied from the method used in hub_ext_port_status(), which shares the same flow of logic as hub_hub_status(). Assisted-by: gkh_clanker_t1000 Signed-off-by: Griffin Kroah-Hartman Link: https://patch.msgid.link/20260722-usb_core_patches_2-v3-1-87622252bfdd@kroah.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 7eb02825b3684d2874eb68807fbc9cd89ace303f) Signed-off-by: Wentao Guan --- drivers/usb/core/hub.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index c5ce8458cbf16..f1d19165c735a 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -998,10 +998,12 @@ static int hub_hub_status(struct usb_hub *hub, mutex_lock(&hub->status_mutex); ret = get_hub_status(hub->hdev, &hub->status->hub); - if (ret < 0) { + if (ret < (int)sizeof(hub->status->hub)) { if (ret != -ENODEV) dev_err(hub->intfdev, "%s failed (err = %d)\n", __func__, ret); + if (ret >= 0) + ret = -EIO; } else { *status = le16_to_cpu(hub->status->hub.wHubStatus); *change = le16_to_cpu(hub->status->hub.wHubChange); From 072917121cf0b80d3e429dc3e279cea17f8e8ef2 Mon Sep 17 00:00:00 2001 From: Marouane El Moufid Date: Sun, 23 Aug 2026 13:55:48 +0000 Subject: [PATCH 69/76] ALSA: usb-audio: fix OOB write in snd_usbmidi_novation_output() commit 1035a8f63bae28e498b0e7b5ac91d749844a7158 upstream. snd_usbmidi_novation_output() lays out a two-byte header at transfer_buffer[0..1] and passes &transfer_buffer[2] together with a length of ep->max_transfer - 2 to snd_rawmidi_transmit(): count = snd_rawmidi_transmit(ep->ports[0].substream, &transfer_buffer[2], ep->max_transfer - 2); ep->max_transfer comes from the output endpoint's wMaxPacketSize via usb_maxpacket(). A malformed or malicious device can advertise a bulk OUT endpoint with a wMaxPacketSize of 1 - the USB core only clamps this value downwards - so ep->max_transfer becomes 1 and the count argument becomes -1. snd_rawmidi_transmit() passes the negative count on to __snd_rawmidi_transmit_peek(), where "if (count1 > count) count1 = count" leaves count1 negative; get_aligned_size() keeps it negative for a byte-stream substream, so the following memcpy(buffer, ..., count1) runs with a (size_t)-1 length and writes far past the transfer buffer, which was allocated with usb_alloc_coherent(ep->max_transfer). This is the same class of bug that was fixed for snd_usbmidi_akai_output() in commit 0970274613fb ("ALSA: usb-audio: fix OOB write in snd_usbmidi_akai_output()"); the novation output routine was left unguarded. Bail out when the endpoint cannot hold the two-byte header plus at least one payload byte. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Signed-off-by: Marouane El Moufid Link: https://patch.msgid.link/178749334830.543645.13722252148340572274@espilon.net Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 91919b3b99ab7ce3d7dbb39fcf7c6c742a663c0c) Signed-off-by: Wentao Guan --- sound/usb/midi.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/usb/midi.c b/sound/usb/midi.c index 01ed18b7b48a8..beb905e0946d2 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -871,6 +871,8 @@ static void snd_usbmidi_novation_output(struct snd_usb_midi_out_endpoint *ep, if (!ep->ports[0].active) return; + if (ep->max_transfer < 3) + return; transfer_buffer = urb->transfer_buffer; count = snd_rawmidi_transmit(ep->ports[0].substream, &transfer_buffer[2], From 6d318415d8dc9d2a165d49c8cbeadecbecda0ef6 Mon Sep 17 00:00:00 2001 From: Will Porter Date: Mon, 24 Aug 2026 17:57:57 -0500 Subject: [PATCH 70/76] ALSA: usb-audio: Complete cleanup after system-resume errors commit 1739a976312e110c93a8dee66a1cdf893a1b187e upstream. A failed system resume can leave the card unusable until reboot. usb_audio_resume() jumps to err_out when snd_usb_pcm_resume() or snd_usb_mixer_resume() fails. The error path skips the out: block, which restores D0 and decrements chip->num_suspended_intf. The card stays in SNDRV_CTL_POWER_D3hot, so later control access blocks in snd_power_ref_and_wait(). USB core logs an interface resume callback error. It does not retry that callback, so a later callback cannot complete the skipped cleanup. usb_audio_suspend() increments num_suspended_intf before returning success. A system-resume callback must consume the system-suspend count even if a component resume fails. Otherwise, the stranded count skews later suspend and resume cycles. Do not apply this cleanup to runtime-resume errors. Runtime PM can retry -EAGAIN or -EBUSY without another suspend callback. The count must continue to describe that suspended interface. Other runtime-resume errors latch runtime_error in the PM core and do not cause an immediate callback retry. Both parts of the system-resume error path are longstanding. Commit 88a8516a2128a ("ALSA: usbaudio: implement USB autosuspend") introduced err_out past the D0 restore. Commit 862b2509d157c ("ALSA: usb-audio: Fix inconsistent card PM state after resume") later moved num_suspended_intf-- into the out: block. The error path now skips both operations. No third-party code is needed to reach the error path. snd_usb_mixer_resume() ends in snd_usb_mixer_activate(), which returns the result of usb_submit_urb() for devices that have a mixer status URB. Its mixer->private_resume hook can also fail through scarlett2_init_notify(). snd_usb_pcm_resume() issues a SET_CUR request to a UAC3 power domain. It can return -EPIPE or -EIO when the device stalls the request. Route a component error through out: only when system_suspend is nonzero. Continue to return runtime-resume errors through err_out. Later component resume stages remain skipped. The original error still reaches USB core. A later transfer can fail if the device did not recover. I reproduced the system-resume failure on an Audient iD14 MkI with an out-of-tree diagnostic mixer resume hook. An injected -EIO on the unpatched core left control readers in uninterruptible sleep in snd_power_ref_and_wait() until a reboot. With this patch, the same failure restored control access. A second system suspend and resume also succeeded after I disabled fault injection. Assisted-by: Claude:claude-opus-5 Assisted-by: Antigravity:gemini-3.1-pro-high Assisted-by: Codex:gpt-5.6-sol Fixes: 88a8516a2128a ("ALSA: usbaudio: implement USB autosuspend") Fixes: 862b2509d157c ("ALSA: usb-audio: Fix inconsistent card PM state after resume") Cc: Signed-off-by: Will Porter Link: https://patch.msgid.link/20260824225757.26749-1-mrwillporter@gmail.com Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 6d3e202670b819c414076a5d07dffac8a39274ad) Signed-off-by: Wentao Guan --- sound/usb/card.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/sound/usb/card.c b/sound/usb/card.c index 270dad84d825e..85249606a6b18 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -1278,8 +1278,11 @@ static int usb_audio_resume(struct usb_interface *intf) list_for_each_entry(as, &chip->pcm_list, list) { err = snd_usb_pcm_resume(as); - if (err < 0) - goto err_out; + if (err < 0) { + if (!chip->system_suspend) + goto err_out; + goto out; + } } /* @@ -1288,8 +1291,11 @@ static int usb_audio_resume(struct usb_interface *intf) */ list_for_each_entry(mixer, &chip->mixer_list, list) { err = snd_usb_mixer_resume(mixer); - if (err < 0) - goto err_out; + if (err < 0) { + if (!chip->system_suspend) + goto err_out; + goto out; + } } list_for_each(p, &chip->midi_list) { From 3fe8acef1cfece0fabf81323c75d3dcc7af3cfc2 Mon Sep 17 00:00:00 2001 From: Jiale Yao Date: Sun, 26 Jul 2026 00:27:51 +0800 Subject: [PATCH 71/76] USB: serial: option: fix slab OOB read in interrupt URB callback commit 885d802f544ca7bfa8f3984d94233cce715bb6b3 upstream. The interrupt URB buffer is allocated in setup_port_interrupt_in() based on the endpoint's wMaxPacketSize: buffer_size = usb_endpoint_maxp(epd); port->interrupt_in_buffer = kmalloc(buffer_size, GFP_KERNEL); When a USB device declares wMaxPacketSize = 8 on its interrupt IN endpoint, the buffer is allocated from kmalloc-8 cache (exactly 8 bytes). If the device sends a short packet (actual_length < wMaxPacketSize), the URB completes with status == 0 and the callback proceeds to read: data[sizeof(struct usb_ctrlrequest)] which evaluates to data[8], accessing 1 byte beyond the allocated 8-byte buffer. This results in a slab out-of-bounds read. Fix this by adding the missing bounds check: first verify that the actual length is large enough to contain the struct usb_ctrlrequest header before accessing req_pkt->bRequestType and req_pkt->bRequest, and then verify that there is an additional byte for the modem signal state before reading data[sizeof(struct usb_ctrlrequest)] inside the conditional. Use sizeof(*req_pkt) instead of sizeof(struct usb_ctrlrequest) for consistency. Assisted-by: Claude:deepseek-v4-pro Signed-off-by: Jiale Yao Fixes: 58cfe9113e48 ("[PATCH] USB: add Option Card driver") Cc: stable@vger.kernel.org # v2.6.12 [ johan: use dev_err(); split signals declaration and initialisation ] Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 2ef5560387f2c0713cee975be2b24b281bd90f3e) Signed-off-by: Wentao Guan --- drivers/usb/serial/option.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 89624f38fec2e..5652155fc680b 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -2690,12 +2690,26 @@ static void option_instat_callback(struct urb *urb) dev_dbg(dev, "%s: NULL req_pkt\n", __func__); return; } + + if (urb->actual_length < sizeof(*req_pkt)) { + dev_err(dev, "%s: short packet: %u bytes\n", __func__, + urb->actual_length); + return; + } + if ((req_pkt->bRequestType == 0xA1) && (req_pkt->bRequest == 0x20)) { + unsigned char signals; int old_dcd_state; - unsigned char signals = *((unsigned char *) - urb->transfer_buffer + - sizeof(struct usb_ctrlrequest)); + + if (urb->actual_length < sizeof(*req_pkt) + 1) { + dev_err(dev, "%s: short interrupt transfer: %u bytes\n", + __func__, urb->actual_length); + return; + } + + signals = *((unsigned char *)urb->transfer_buffer + + sizeof(*req_pkt)); dev_dbg(dev, "%s: signal x%x\n", __func__, signals); From af2fb58b03271d0617aac4154dc8f5dedc943ec9 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 6 Aug 2026 15:52:48 +0200 Subject: [PATCH 72/76] USB: serial: spcp8x5: drop broken carrier detect support commit d37186bd95a07e334447f47274a38a311dad2172 upstream. The driver does not support modem status notifications and instead used to fetch the modem status once at open() and subsequently operate on and report stale state. As part of fixing this, a call to fetch the status was added to carrier_raised(), which does not work as that callback must not sleep (e.g. unlike tiocmget()). Drop the broken carrier detect support. Fixes: e1ed212d8593 ("USB: spcp8x5: add proper modem-status support") Cc: stable@vger.kernel.org # 3.10 Reported-by: syzbot+3b514b87202742f22c44@syzkaller.appspotmail.com Link: https://lore.kernel.org/all/6a73cea2.01d0871a.3a0d52.000d.GAE@google.com Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 683df50fff0f5fccecf96207f769b335e56d8ea8) Signed-off-by: Wentao Guan --- drivers/usb/serial/spcp8x5.c | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/drivers/usb/serial/spcp8x5.c b/drivers/usb/serial/spcp8x5.c index 11077beb7232a..aa8fe0dcb680e 100644 --- a/drivers/usb/serial/spcp8x5.c +++ b/drivers/usb/serial/spcp8x5.c @@ -237,18 +237,6 @@ static void spcp8x5_set_work_mode(struct usb_serial_port *port, u16 value, dev_err(&port->dev, "failed to set work mode: %d\n", ret); } -static int spcp8x5_carrier_raised(struct usb_serial_port *port) -{ - u8 msr; - int ret; - - ret = spcp8x5_get_msr(port, &msr); - if (ret || msr & MSR_STATUS_LINE_DCD) - return 1; - - return 0; -} - static void spcp8x5_dtr_rts(struct usb_serial_port *port, int on) { struct spcp8x5_private *priv = usb_get_serial_port_data(port); @@ -460,7 +448,6 @@ static struct usb_serial_driver spcp8x5_device = { .num_bulk_out = 1, .open = spcp8x5_open, .dtr_rts = spcp8x5_dtr_rts, - .carrier_raised = spcp8x5_carrier_raised, .set_termios = spcp8x5_set_termios, .init_termios = spcp8x5_init_termios, .tiocmget = spcp8x5_tiocmget, From 5aacf3ec89387308721a585adf4affcbd2ca5850 Mon Sep 17 00:00:00 2001 From: Shuangpeng Bai Date: Wed, 5 Aug 2026 21:35:02 -0400 Subject: [PATCH 73/76] USB: c67x00: fix use-after-free in c67x00_add_iso_urb() commit b1e24de475bf2d66fffc9103f3444b783527d55a upstream. When TD creation fails for the last packet of an isochronous URB, c67x00_add_iso_urb() gives the URB back before updating the endpoint scheduling state. c67x00_giveback_urb() frees the URB private data, and the completion callback may release the final URB reference. The following accesses to urbp->ep_data, urb->interval, and urbp->cnt can therefore use freed memory. Update next_frame and cnt before giving back the failed final packet, making the giveback the last operation that uses the URB and its private data. Fixes: e9b29ffc519b ("USB: add Cypress c67x00 OTG controller HCD driver") Cc: stable@vger.kernel.org Signed-off-by: Shuangpeng Bai Link: https://patch.msgid.link/20260806013502.322067-1-shuangpeng.kernel@gmail.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit b4cb8081cf80f82e48fbe9c021a8f6d0fa2ed421) Signed-off-by: Wentao Guan --- drivers/usb/c67x00/c67x00-sched.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/c67x00/c67x00-sched.c b/drivers/usb/c67x00/c67x00-sched.c index a09fa68a6ce74..346cdac1c1e23 100644 --- a/drivers/usb/c67x00/c67x00-sched.c +++ b/drivers/usb/c67x00/c67x00-sched.c @@ -761,13 +761,13 @@ static int c67x00_add_iso_urb(struct c67x00_hcd *c67x00, struct urb *urb) ret); urb->iso_frame_desc[urbp->cnt].actual_length = 0; urb->iso_frame_desc[urbp->cnt].status = ret; - if (urbp->cnt + 1 == urb->number_of_packets) - c67x00_giveback_urb(c67x00, urb, 0); } urbp->ep_data->next_frame = frame_add(urbp->ep_data->next_frame, urb->interval); urbp->cnt++; + if (ret && urbp->cnt == urb->number_of_packets) + c67x00_giveback_urb(c67x00, urb, 0); } return 0; } From d0f47245aa940628e63b0961fb49c2010607bbf7 Mon Sep 17 00:00:00 2001 From: Devin Wittmayer Date: Tue, 14 Jul 2026 19:33:48 -0700 Subject: [PATCH 74/76] wifi: mt76: mt7925: ensure tx headroom in usb_sdio_tx_prepare_skb commit ef3e34874d2332d0f63e72c2c35ce5c93568c125 upstream. mt7925_usb_sdio_tx_prepare_skb() pushes a TX descriptor and a USB header onto every skb and assumes the headroom for them is already there. That holds for locally generated traffic, where mac80211 reserves hw->extra_tx_headroom, but forwarded frames are sent through ieee80211_8023_xmit(), which does not reserve it. Bridge a wired interface to an mt7925u AP and the first forwarded frame that arrives short panics the kernel: skbuff: skb_under_panic: len:415 put:4 tail:0x19b end:0x640 dev:wlan1 kernel BUG at net/core/skbuff.c:212! Call trace: skb_panic+0x58/0x60 (P) skb_push+0x58/0x60 mt7925_usb_sdio_tx_prepare_skb+0xf8/0x1b8 [mt7925_common] mt76u_tx_queue_skb+0xa0/0x1f8 [mt76_usb] __mt76_tx_queue_skb+0x54/0xe8 [mt76] mt76_txq_schedule.part.0+0x204/0x478 [mt76] mt76_txq_schedule_all+0x50/0x80 [mt76] mt792x_tx_worker+0x68/0x100 [mt792x_lib] __mt76_worker_fn+0x84/0x150 [mt76] Whether a given setup hits it depends on how much headroom the ingress netdev leaves in its rx skbs. Reproduced on a Raspberry Pi 5 bridging onboard ethernet to a Netgear A9000; originally reported on an MT7986 router running OpenWrt. Nick Morrow's testing on a Pi 4 (bcmgenet), which leaves more headroom, helped narrow the trigger to the ingress path. The same bug was fixed on mt7921 by commit 98c4d0abf5c4 ("mt76: mt7921: don't assume adequate headroom for SDIO headers"), but mt7925 was copied from mt7921 without the fix. Add the same guard here. Fixes: c948b5da6bbe ("wifi: mt76: mt7925: add Mediatek Wi-Fi7 driver for mt7925 chips") Cc: stable@vger.kernel.org Link: https://github.com/morrownr/mt76/issues/52 Signed-off-by: Devin Wittmayer Link: https://patch.msgid.link/20260715023348.59506-1-lucid_duck@justthetip.ca Signed-off-by: Felix Fietkau Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 22edb6786127271aeba7abd30f152977c605c6a3) Signed-off-by: Wentao Guan --- drivers/net/wireless/mediatek/mt76/mt7925/mac.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c index be19fb748bb68..826e8648485bb 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c @@ -1434,6 +1434,10 @@ int mt7925_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, if (!wcid) wcid = &dev->mt76.global_wcid; + err = skb_cow_head(skb, MT_SDIO_TXD_SIZE + MT_SDIO_HDR_SIZE); + if (err) + return err; + if (sta) { struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv; From 524095caaf01f2dbdb83eaeb9090dd5fc7e3deea Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Miguel=20Pe=C3=B1aranda?= Date: Mon, 10 Aug 2026 14:12:09 +0200 Subject: [PATCH 75/76] usb: usbfs: fix use-after-free of usb_device in usbdev_release() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 0dd68b5d01d022fc9c5e71c82a82b0a94d3d0671 upstream. usbdev_release() drops its reference to the struct usb_device before draining the list of completed async URBs, but that drain path reads back through the same object: free_async() calls dec_usb_memory_use_count() for any URB whose buffer came from the usbfs mmap() region, and its first statement is bus_to_hcd(ps->dev->bus). After a disconnect the usbfs reference can be the last one, in which case usb_put_dev() frees the device and the subsequent loop reads offset 80 of freed memory and uses the result as a struct usb_hcd *, which hcd_buffer_free_pages() then dereferences. This is reachable by an unprivileged process that has read/write access to a /dev/bus/usb node: mmap() the fd, submit one URB with a buffer inside the mapping, wait for the device to be unplugged, then munmap() and close(). It reproduces on every attempt rather than being a race, because a live MAP_SHARED vma holds a reference on the struct file, so usbdev_release() cannot run until the last vma is gone and the freeing branch of dec_usb_memory_use_count() is always taken. BUG: KASAN: slab-use-after-free in dec_usb_memory_use_count+0x3ae/0x410 Read of size 8 at addr ffff8880122ee050 by task poc/769 CPU: 1 UID: 1000 PID: 769 Comm: poc Tainted: G B 6.12.94 #3 Call Trace: dec_usb_memory_use_count+0x3ae/0x410 free_async+0x2aa/0x4f0 usbdev_release+0x375/0x460 __fput+0x3ea/0xb50 __x64_sys_close+0x86/0x100 Allocated by task 11: usb_alloc_dev+0x55/0xd90 hub_event+0x2524/0x43d0 Freed by task 769: kfree+0x121/0x360 device_release+0xd2/0x280 usb_put_dev+0x23/0x30 usbdev_release+0x2d8/0x460 Release the device reference after the drain loop instead. Nothing between the two points requires it to have been dropped. Fixes: f7d34b445abc ("USB: Add support for usbfs zerocopy.") Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-5 Signed-off-by: Miguel Peñaranda Reviewed-by: Alan Stern Link: https://patch.msgid.link/20260810121209.795089-1-mig.penaranda07@gmail.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 5f08c45bdcfd28d1171de38c5ef29fc89a76eedc) Signed-off-by: Wentao Guan --- drivers/usb/core/devio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index f6ce6e26e0d45..53dcd0019e111 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -1113,7 +1113,6 @@ static int usbdev_release(struct inode *inode, struct file *file) if (!ps->suspend_allowed) usb_autosuspend_device(dev); usb_unlock_device(dev); - usb_put_dev(dev); put_pid(ps->disc_pid); put_cred(ps->cred); @@ -1122,6 +1121,7 @@ static int usbdev_release(struct inode *inode, struct file *file) free_async(as); as = async_getcompleted(ps); } + usb_put_dev(dev); kfree(ps); return 0; From 9ada2c286e27b25fcc86583e894841b4c44e48b4 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 2 Sep 2026 14:31:51 +0200 Subject: [PATCH 76/76] Linux 6.18.49 Link: https://lore.kernel.org/r/20260831133359.207714926@linuxfoundation.org Tested-by: Wentao Guan Tested-by: Brett A C Sheffield Tested-by: Peter Schneider Tested-by: Florian Fainelli Tested-by: Pavel Machek (CIP) Tested-by: Shuah Khan Tested-by: Miguel Ojeda Tested-by: Ron Economos Tested-by: Barry K. Nathan Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 1c732c6b94f0faee1526bd375add2fe10cba2e26) Signed-off-by: Wentao Guan --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index d430e829e3ae9..3a114c6e84251 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 18 -SUBLEVEL = 48 +SUBLEVEL = 49 EXTRAVERSION = NAME = Baby Opossum Posse