From f9118e5321a93f53be9b42ce1e2ba4609eb63d10 Mon Sep 17 00:00:00 2001 From: Jonathan Maple Date: Thu, 18 Sep 2025 11:23:37 -0400 Subject: [PATCH 1/5] scsi: lpfc: Use memcpy() for BIOS version jira VULN-72456 jira VULN-72455 cve CVE-2025-38332 commit-author Daniel Wagner commit ae82eaf4aeea060bb736c3e20c0568b67c701d7d The strlcat() with FORTIFY support is triggering a panic because it thinks the target buffer will overflow although the correct target buffer size is passed in. Anyway, instead of memset() with 0 followed by a strlcat(), just use memcpy() and ensure that the resulting buffer is NULL terminated. BIOSVersion is only used for the lpfc_printf_log() which expects a properly terminated string. Signed-off-by: Daniel Wagner Link: https://lore.kernel.org/r/20250409-fix-lpfc-bios-str-v1-1-05dac9e51e13@kernel.org Reviewed-by: Justin Tee Signed-off-by: Martin K. Petersen (cherry picked from commit ae82eaf4aeea060bb736c3e20c0568b67c701d7d) Signed-off-by: Jonathan Maple --- drivers/scsi/lpfc/lpfc_sli.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 1b8e83a8a5029..e9e2e1d05deac 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -5970,9 +5970,9 @@ lpfc_sli4_get_ctl_attr(struct lpfc_hba *phba) phba->sli4_hba.flash_id = bf_get(lpfc_cntl_attr_flash_id, cntl_attr); phba->sli4_hba.asic_rev = bf_get(lpfc_cntl_attr_asic_rev, cntl_attr); - memset(phba->BIOSVersion, 0, sizeof(phba->BIOSVersion)); - strlcat(phba->BIOSVersion, (char *)cntl_attr->bios_ver_str, + memcpy(phba->BIOSVersion, cntl_attr->bios_ver_str, sizeof(phba->BIOSVersion)); + phba->BIOSVersion[sizeof(phba->BIOSVersion) - 1] = '\0'; lpfc_printf_log(phba, KERN_INFO, LOG_SLI, "3086 lnk_type:%d, lnk_numb:%d, bios_ver:%s, " From f1751875e7b1b130187d82fea19a54ed5eb8f8be Mon Sep 17 00:00:00 2001 From: Jonathan Maple Date: Thu, 18 Sep 2025 11:23:43 -0400 Subject: [PATCH 2/5] idpf: convert control queue mutex to a spinlock jira VULN-136697 jira VULN-136696 cve CVE-2025-38392 commit-author Ahmed Zaki commit b2beb5bb2cd90d7939e470ed4da468683f41baa3 With VIRTCHNL2_CAP_MACFILTER enabled, the following warning is generated on module load: [ 324.701677] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:578 [ 324.701684] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1582, name: NetworkManager [ 324.701689] preempt_count: 201, expected: 0 [ 324.701693] RCU nest depth: 0, expected: 0 [ 324.701697] 2 locks held by NetworkManager/1582: [ 324.701702] #0: ffffffff9f7be770 (rtnl_mutex){....}-{3:3}, at: rtnl_newlink+0x791/0x21e0 [ 324.701730] #1: ff1100216c380368 (_xmit_ETHER){....}-{2:2}, at: __dev_open+0x3f0/0x870 [ 324.701749] Preemption disabled at: [ 324.701752] [] __dev_open+0x3dd/0x870 [ 324.701765] CPU: 30 UID: 0 PID: 1582 Comm: NetworkManager Not tainted 6.15.0-rc5+ #2 PREEMPT(voluntary) [ 324.701771] Hardware name: Intel Corporation M50FCP2SBSTD/M50FCP2SBSTD, BIOS SE5C741.86B.01.01.0001.2211140926 11/14/2022 [ 324.701774] Call Trace: [ 324.701777] [ 324.701779] dump_stack_lvl+0x5d/0x80 [ 324.701788] ? __dev_open+0x3dd/0x870 [ 324.701793] __might_resched.cold+0x1ef/0x23d <..> [ 324.701818] __mutex_lock+0x113/0x1b80 <..> [ 324.701917] idpf_ctlq_clean_sq+0xad/0x4b0 [idpf] [ 324.701935] ? kasan_save_track+0x14/0x30 [ 324.701941] idpf_mb_clean+0x143/0x380 [idpf] <..> [ 324.701991] idpf_send_mb_msg+0x111/0x720 [idpf] [ 324.702009] idpf_vc_xn_exec+0x4cc/0x990 [idpf] [ 324.702021] ? rcu_is_watching+0x12/0xc0 [ 324.702035] idpf_add_del_mac_filters+0x3ed/0xb50 [idpf] <..> [ 324.702122] __hw_addr_sync_dev+0x1cf/0x300 [ 324.702126] ? find_held_lock+0x32/0x90 [ 324.702134] idpf_set_rx_mode+0x317/0x390 [idpf] [ 324.702152] __dev_open+0x3f8/0x870 [ 324.702159] ? __pfx___dev_open+0x10/0x10 [ 324.702174] __dev_change_flags+0x443/0x650 <..> [ 324.702208] netif_change_flags+0x80/0x160 [ 324.702218] do_setlink.isra.0+0x16a0/0x3960 <..> [ 324.702349] rtnl_newlink+0x12fd/0x21e0 The sequence is as follows: rtnl_newlink()-> __dev_change_flags()-> __dev_open()-> dev_set_rx_mode() - > # disables BH and grabs "dev->addr_list_lock" idpf_set_rx_mode() -> # proceed only if VIRTCHNL2_CAP_MACFILTER is ON __dev_uc_sync() -> idpf_add_mac_filter -> idpf_add_del_mac_filters -> idpf_send_mb_msg() -> idpf_mb_clean() -> idpf_ctlq_clean_sq() # mutex_lock(cq_lock) Fix by converting cq_lock to a spinlock. All operations under the new lock are safe except freeing the DMA memory, which may use vunmap(). Fix by requesting a contiguous physical memory for the DMA mapping. Fixes: a251eee62133 ("idpf: add SRIOV support and other ndo_ops") Reviewed-by: Aleksandr Loktionov Signed-off-by: Ahmed Zaki Reviewed-by: Simon Horman Tested-by: Samuel Salin Signed-off-by: Tony Nguyen (cherry picked from commit b2beb5bb2cd90d7939e470ed4da468683f41baa3) Signed-off-by: Jonathan Maple --- .../net/ethernet/intel/idpf/idpf_controlq.c | 23 +++++++++---------- .../ethernet/intel/idpf/idpf_controlq_api.h | 2 +- drivers/net/ethernet/intel/idpf/idpf_lib.c | 12 ++++++---- 3 files changed, 20 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.c b/drivers/net/ethernet/intel/idpf/idpf_controlq.c index 4849590a5591f..f29f94a1d7f2b 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_controlq.c +++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.c @@ -96,7 +96,7 @@ static void idpf_ctlq_init_rxq_bufs(struct idpf_ctlq_info *cq) */ static void idpf_ctlq_shutdown(struct idpf_hw *hw, struct idpf_ctlq_info *cq) { - mutex_lock(&cq->cq_lock); + spin_lock(&cq->cq_lock); /* free ring buffers and the ring itself */ idpf_ctlq_dealloc_ring_res(hw, cq); @@ -104,8 +104,7 @@ static void idpf_ctlq_shutdown(struct idpf_hw *hw, struct idpf_ctlq_info *cq) /* Set ring_size to 0 to indicate uninitialized queue */ cq->ring_size = 0; - mutex_unlock(&cq->cq_lock); - mutex_destroy(&cq->cq_lock); + spin_unlock(&cq->cq_lock); } /** @@ -173,7 +172,7 @@ int idpf_ctlq_add(struct idpf_hw *hw, idpf_ctlq_init_regs(hw, cq, is_rxq); - mutex_init(&cq->cq_lock); + spin_lock_init(&cq->cq_lock); list_add(&cq->cq_list, &hw->cq_list_head); @@ -272,7 +271,7 @@ int idpf_ctlq_send(struct idpf_hw *hw, struct idpf_ctlq_info *cq, int err = 0; int i; - mutex_lock(&cq->cq_lock); + spin_lock(&cq->cq_lock); /* Ensure there are enough descriptors to send all messages */ num_desc_avail = IDPF_CTLQ_DESC_UNUSED(cq); @@ -332,7 +331,7 @@ int idpf_ctlq_send(struct idpf_hw *hw, struct idpf_ctlq_info *cq, wr32(hw, cq->reg.tail, cq->next_to_use); err_unlock: - mutex_unlock(&cq->cq_lock); + spin_unlock(&cq->cq_lock); return err; } @@ -364,7 +363,7 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count, if (*clean_count > cq->ring_size) return -EBADR; - mutex_lock(&cq->cq_lock); + spin_lock(&cq->cq_lock); ntc = cq->next_to_clean; @@ -394,7 +393,7 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count, cq->next_to_clean = ntc; - mutex_unlock(&cq->cq_lock); + spin_unlock(&cq->cq_lock); /* Return number of descriptors actually cleaned */ *clean_count = i; @@ -432,7 +431,7 @@ int idpf_ctlq_post_rx_buffs(struct idpf_hw *hw, struct idpf_ctlq_info *cq, if (*buff_count > 0) buffs_avail = true; - mutex_lock(&cq->cq_lock); + spin_lock(&cq->cq_lock); if (tbp >= cq->ring_size) tbp = 0; @@ -521,7 +520,7 @@ int idpf_ctlq_post_rx_buffs(struct idpf_hw *hw, struct idpf_ctlq_info *cq, wr32(hw, cq->reg.tail, cq->next_to_post); } - mutex_unlock(&cq->cq_lock); + spin_unlock(&cq->cq_lock); /* return the number of buffers that were not posted */ *buff_count = *buff_count - i; @@ -549,7 +548,7 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg, u16 i; /* take the lock before we start messing with the ring */ - mutex_lock(&cq->cq_lock); + spin_lock(&cq->cq_lock); ntc = cq->next_to_clean; @@ -608,7 +607,7 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg, cq->next_to_clean = ntc; - mutex_unlock(&cq->cq_lock); + spin_unlock(&cq->cq_lock); *num_q_msg = i; if (*num_q_msg == 0) diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h index e8e046ef2f0d7..5890d8adca4a8 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h +++ b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h @@ -99,7 +99,7 @@ struct idpf_ctlq_info { enum idpf_ctlq_type cq_type; int q_id; - struct mutex cq_lock; /* control queue lock */ + spinlock_t cq_lock; /* control queue lock */ /* used for interrupt processing */ u16 next_to_use; u16 next_to_clean; diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 5d3532c27d57f..e57e005ba1eb8 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -2369,8 +2369,12 @@ void *idpf_alloc_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem, u64 size) struct idpf_adapter *adapter = hw->back; size_t sz = ALIGN(size, 4096); - mem->va = dma_alloc_coherent(&adapter->pdev->dev, sz, - &mem->pa, GFP_KERNEL); + /* The control queue resources are freed under a spinlock, contiguous + * pages will avoid IOMMU remapping and the use vmap (and vunmap in + * dma_free_*() path. + */ + mem->va = dma_alloc_attrs(&adapter->pdev->dev, sz, &mem->pa, + GFP_KERNEL, DMA_ATTR_FORCE_CONTIGUOUS); mem->size = sz; return mem->va; @@ -2385,8 +2389,8 @@ void idpf_free_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem) { struct idpf_adapter *adapter = hw->back; - dma_free_coherent(&adapter->pdev->dev, mem->size, - mem->va, mem->pa); + dma_free_attrs(&adapter->pdev->dev, mem->size, + mem->va, mem->pa, DMA_ATTR_FORCE_CONTIGUOUS); mem->size = 0; mem->va = NULL; mem->pa = 0; From 325a6c52fc2fb9c29cd13ed6bc300e817e77a49d Mon Sep 17 00:00:00 2001 From: Jonathan Maple Date: Thu, 18 Sep 2025 11:23:55 -0400 Subject: [PATCH 3/5] tipc: Fix use-after-free in tipc_conn_close(). jira VULN-80316 jira VULN-80315 cve CVE-2025-38464 commit-author Kuniyuki Iwashima commit 667eeab4999e981c96b447a4df5f20bdf5c26f13 syzbot reported a null-ptr-deref in tipc_conn_close() during netns dismantle. [0] tipc_topsrv_stop() iterates tipc_net(net)->topsrv->conn_idr and calls tipc_conn_close() for each tipc_conn. The problem is that tipc_conn_close() is called after releasing the IDR lock. At the same time, there might be tipc_conn_recv_work() running and it could call tipc_conn_close() for the same tipc_conn and release its last ->kref. Once we release the IDR lock in tipc_topsrv_stop(), there is no guarantee that the tipc_conn is alive. Let's hold the ref before releasing the lock and put the ref after tipc_conn_close() in tipc_topsrv_stop(). [0]: BUG: KASAN: use-after-free in tipc_conn_close+0x122/0x140 net/tipc/topsrv.c:165 Read of size 8 at addr ffff888099305a08 by task kworker/u4:3/435 CPU: 0 PID: 435 Comm: kworker/u4:3 Not tainted 4.19.204-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: netns cleanup_net Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1fc/0x2ef lib/dump_stack.c:118 print_address_description.cold+0x54/0x219 mm/kasan/report.c:256 kasan_report_error.cold+0x8a/0x1b9 mm/kasan/report.c:354 kasan_report mm/kasan/report.c:412 [inline] __asan_report_load8_noabort+0x88/0x90 mm/kasan/report.c:433 tipc_conn_close+0x122/0x140 net/tipc/topsrv.c:165 tipc_topsrv_stop net/tipc/topsrv.c:701 [inline] tipc_topsrv_exit_net+0x27b/0x5c0 net/tipc/topsrv.c:722 ops_exit_list+0xa5/0x150 net/core/net_namespace.c:153 cleanup_net+0x3b4/0x8b0 net/core/net_namespace.c:553 process_one_work+0x864/0x1570 kernel/workqueue.c:2153 worker_thread+0x64c/0x1130 kernel/workqueue.c:2296 kthread+0x33f/0x460 kernel/kthread.c:259 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:415 Allocated by task 23: kmem_cache_alloc_trace+0x12f/0x380 mm/slab.c:3625 kmalloc include/linux/slab.h:515 [inline] kzalloc include/linux/slab.h:709 [inline] tipc_conn_alloc+0x43/0x4f0 net/tipc/topsrv.c:192 tipc_topsrv_accept+0x1b5/0x280 net/tipc/topsrv.c:470 process_one_work+0x864/0x1570 kernel/workqueue.c:2153 worker_thread+0x64c/0x1130 kernel/workqueue.c:2296 kthread+0x33f/0x460 kernel/kthread.c:259 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:415 Freed by task 23: __cache_free mm/slab.c:3503 [inline] kfree+0xcc/0x210 mm/slab.c:3822 tipc_conn_kref_release net/tipc/topsrv.c:150 [inline] kref_put include/linux/kref.h:70 [inline] conn_put+0x2cd/0x3a0 net/tipc/topsrv.c:155 process_one_work+0x864/0x1570 kernel/workqueue.c:2153 worker_thread+0x64c/0x1130 kernel/workqueue.c:2296 kthread+0x33f/0x460 kernel/kthread.c:259 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:415 The buggy address belongs to the object at ffff888099305a00 which belongs to the cache kmalloc-512 of size 512 The buggy address is located 8 bytes inside of 512-byte region [ffff888099305a00, ffff888099305c00) The buggy address belongs to the page: page:ffffea000264c140 count:1 mapcount:0 mapping:ffff88813bff0940 index:0x0 flags: 0xfff00000000100(slab) raw: 00fff00000000100 ffffea00028b6b88 ffffea0002cd2b08 ffff88813bff0940 raw: 0000000000000000 ffff888099305000 0000000100000006 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888099305900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888099305980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff888099305a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888099305a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888099305b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: c5fa7b3cf3cb ("tipc: introduce new TIPC server infrastructure") Reported-by: syzbot+d333febcf8f4bc5f6110@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=27169a847a70550d17be Signed-off-by: Kuniyuki Iwashima Reviewed-by: Tung Nguyen Link: https://patch.msgid.link/20250702014350.692213-1-kuniyu@google.com Signed-off-by: Jakub Kicinski (cherry picked from commit 667eeab4999e981c96b447a4df5f20bdf5c26f13) Signed-off-by: Jonathan Maple --- net/tipc/topsrv.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index ebd020c8b6e6d..a693b0b176550 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -700,8 +700,10 @@ static void tipc_topsrv_stop(struct net *net) for (id = 0; srv->idr_in_use; id++) { con = idr_find(&srv->conn_idr, id); if (con) { + conn_get(con); spin_unlock_bh(&srv->idr_lock); tipc_conn_close(con); + conn_put(con); spin_lock_bh(&srv->idr_lock); } } From c1bf8405c8505bc862f92de9b084cd8c33e56fe6 Mon Sep 17 00:00:00 2001 From: Jonathan Maple Date: Thu, 18 Sep 2025 11:24:00 -0400 Subject: [PATCH 4/5] net/sched: sch_qfq: Fix race condition on qfq_aggregate jira VULN-89290 jira VULN-89289 cve CVE-2025-38477 commit-author Xiang Mei commit 5e28d5a3f774f118896aec17a3a20a9c5c9dfc64 A race condition can occur when 'agg' is modified in qfq_change_agg (called during qfq_enqueue) while other threads access it concurrently. For example, qfq_dump_class may trigger a NULL dereference, and qfq_delete_class may cause a use-after-free. This patch addresses the issue by: 1. Moved qfq_destroy_class into the critical section. 2. Added sch_tree_lock protection to qfq_dump_class and qfq_dump_class_stats. Fixes: 462dbc9101ac ("pkt_sched: QFQ Plus: fair-queueing service at DRR cost") Signed-off-by: Xiang Mei Reviewed-by: Cong Wang Signed-off-by: David S. Miller (cherry picked from commit 5e28d5a3f774f118896aec17a3a20a9c5c9dfc64) Signed-off-by: Jonathan Maple --- net/sched/sch_qfq.c | 30 +++++++++++++++++++++--------- 1 file changed, 21 insertions(+), 9 deletions(-) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index cf1f585f2bc46..256a481245a65 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -412,7 +412,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, bool existing = false; struct nlattr *tb[TCA_QFQ_MAX + 1]; struct qfq_aggregate *new_agg = NULL; - u32 weight, lmax, inv_w; + u32 weight, lmax, inv_w, old_weight, old_lmax; int err; int delta_w; @@ -446,12 +446,16 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; - if (cl != NULL && - lmax == cl->agg->lmax && - weight == cl->agg->class_weight) - return 0; /* nothing to change */ + if (cl != NULL) { + sch_tree_lock(sch); + old_weight = cl->agg->class_weight; + old_lmax = cl->agg->lmax; + sch_tree_unlock(sch); + if (lmax == old_lmax && weight == old_weight) + return 0; /* nothing to change */ + } - delta_w = weight - (cl ? cl->agg->class_weight : 0); + delta_w = weight - (cl ? old_weight : 0); if (q->wsum + delta_w > QFQ_MAX_WSUM) { pr_notice("qfq: total weight out of range (%d + %u)\n", @@ -554,10 +558,10 @@ static int qfq_delete_class(struct Qdisc *sch, unsigned long arg, qdisc_purge_queue(cl->qdisc); qdisc_class_hash_remove(&q->clhash, &cl->common); + qfq_destroy_class(sch, cl); sch_tree_unlock(sch); - qfq_destroy_class(sch, cl); return 0; } @@ -624,6 +628,7 @@ static int qfq_dump_class(struct Qdisc *sch, unsigned long arg, { struct qfq_class *cl = (struct qfq_class *)arg; struct nlattr *nest; + u32 class_weight, lmax; tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle = cl->common.classid; @@ -632,8 +637,13 @@ static int qfq_dump_class(struct Qdisc *sch, unsigned long arg, nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; - if (nla_put_u32(skb, TCA_QFQ_WEIGHT, cl->agg->class_weight) || - nla_put_u32(skb, TCA_QFQ_LMAX, cl->agg->lmax)) + + sch_tree_lock(sch); + class_weight = cl->agg->class_weight; + lmax = cl->agg->lmax; + sch_tree_unlock(sch); + if (nla_put_u32(skb, TCA_QFQ_WEIGHT, class_weight) || + nla_put_u32(skb, TCA_QFQ_LMAX, lmax)) goto nla_put_failure; return nla_nest_end(skb, nest); @@ -650,8 +660,10 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg, memset(&xstats, 0, sizeof(xstats)); + sch_tree_lock(sch); xstats.weight = cl->agg->class_weight; xstats.lmax = cl->agg->lmax; + sch_tree_unlock(sch); if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || From 9a068aa4ddced96a698050699c0a66d12d3ff137 Mon Sep 17 00:00:00 2001 From: Jonathan Maple Date: Thu, 18 Sep 2025 16:13:34 -0400 Subject: [PATCH 5/5] net/sched: sch_qfq: Avoid triggering might_sleep in atomic context in qfq_delete_class jira VULN-89289 jira VULN-89290 cve-bf CVE-2025-38477 commit-author Xiang Mei commit cf074eca0065bc5142e6004ae236bb35a2687fdf might_sleep could be trigger in the atomic context in qfq_delete_class. qfq_destroy_class was moved into atomic context locked by sch_tree_lock to avoid a race condition bug on qfq_aggregate. However, might_sleep could be triggered by qfq_destroy_class, which introduced sleeping in atomic context (path: qfq_destroy_class->qdisc_put->__qdisc_destroy->lockdep_unregister_key ->might_sleep). Considering the race is on the qfq_aggregate objects, keeping qfq_rm_from_agg in the lock but moving the left part out can solve this issue. Fixes: 5e28d5a3f774 ("net/sched: sch_qfq: Fix race condition on qfq_aggregate") Reported-by: Dan Carpenter Signed-off-by: Xiang Mei Link: https://patch.msgid.link/4a04e0cc-a64b-44e7-9213-2880ed641d77@sabinyo.mountain Reviewed-by: Cong Wang Reviewed-by: Dan Carpenter Link: https://patch.msgid.link/20250717230128.159766-1-xmei5@asu.edu Signed-off-by: Paolo Abeni (cherry picked from commit cf074eca0065bc5142e6004ae236bb35a2687fdf) Signed-off-by: Jonathan Maple --- net/sched/sch_qfq.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 256a481245a65..0660200decc20 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -537,9 +537,6 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl) { - struct qfq_sched *q = qdisc_priv(sch); - - qfq_rm_from_agg(q, cl); gen_kill_estimator(&cl->rate_est); qdisc_put(cl->qdisc); kfree(cl); @@ -558,10 +555,11 @@ static int qfq_delete_class(struct Qdisc *sch, unsigned long arg, qdisc_purge_queue(cl->qdisc); qdisc_class_hash_remove(&q->clhash, &cl->common); - qfq_destroy_class(sch, cl); + qfq_rm_from_agg(q, cl); sch_tree_unlock(sch); + qfq_destroy_class(sch, cl); return 0; } @@ -1502,6 +1500,7 @@ static void qfq_destroy_qdisc(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], common.hnode) { + qfq_rm_from_agg(q, cl); qfq_destroy_class(sch, cl); } }