- Kernel - mailweb.openeuler.org

[PATCH OLK-6.6] net/mlx5e: Fix crash on profile change rollback failure
by Yi Yang 31 Jan '26

31 Jan '26

From: Saeed Mahameed <saeedm(a)nvidia.com> mainline inclusion from mainline-v6.19-rc6 commit 4dadc4077e3f77d6d31e199a925fc7a705e7adeb category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13511 CVE: CVE-2026-23000 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- mlx5e_netdev_change_profile can fail to attach a new profile and can fail to rollback to old profile, in such case, we could end up with a dangling netdev with a fully reset netdev_priv. A retry to change profile, e.g. another attempt to call mlx5e_netdev_change_profile via switchdev mode change, will crash trying to access the now NULL priv->mdev. This fix allows mlx5e_netdev_change_profile() to handle previous failures and an empty priv, by not assuming priv is valid. Pass netdev and mdev to all flows requiring mlx5e_netdev_change_profile() and avoid passing priv. In mlx5e_netdev_change_profile() check if current priv is valid, and if not, just attach the new profile without trying to access the old one. This fixes the following oops, when enabling switchdev mode for the 2nd time after first time failure: ## Enabling switchdev mode first time: mlx5_core 0012:03:00.1: E-Switch: Supported tc chains and prios offload workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR mlx5_core 0012:03:00.1: mlx5e_netdev_init_profile:6214:(pid 37199): mlx5e_priv_init failed, err=-12 mlx5_core 0012:03:00.1 gpu3rdma1: mlx5e_netdev_change_profile: new profile init failed, -12 workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR mlx5_core 0012:03:00.1: mlx5e_netdev_init_profile:6214:(pid 37199): mlx5e_priv_init failed, err=-12 mlx5_core 0012:03:00.1 gpu3rdma1: mlx5e_netdev_change_profile: failed to rollback to orig profile, -12 ^^^^^^^^ mlx5_core 0000:00:03.0: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0) ## retry: Enabling switchdev mode 2nd time: mlx5_core 0000:00:03.0: E-Switch: Supported tc chains and prios offload BUG: kernel NULL pointer dereference, address: 0000000000000038 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 13 UID: 0 PID: 520 Comm: devlink Not tainted 6.18.0-rc4+ #91 PREEMPT(voluntary) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-2.fc40 04/01/2014 RIP: 0010:mlx5e_detach_netdev+0x3c/0x90 Code: 50 00 00 f0 80 4f 78 02 48 8b bf e8 07 00 00 48 85 ff 74 16 48 8b 73 78 48 d1 ee 83 e6 01 83 f6 01 40 0f b6 f6 e8 c4 42 00 00 <48> 8b 45 38 48 85 c0 74 08 48 89 df e8 cc 47 40 1e 48 8b bb f0 07 RSP: 0018:ffffc90000673890 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff8881036a89c0 RCX: 0000000000000000 RDX: ffff888113f63800 RSI: ffffffff822fe720 RDI: 0000000000000000 RBP: 0000000000000000 R08: 0000000000002dcd R09: 0000000000000000 R10: ffffc900006738e8 R11: 00000000ffffffff R12: 0000000000000000 R13: 0000000000000000 R14: ffff8881036a89c0 R15: 0000000000000000 FS: 00007fdfb8384740(0000) GS:ffff88856a9d6000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000038 CR3: 0000000112ae0005 CR4: 0000000000370ef0 Call Trace: <TASK> mlx5e_netdev_change_profile+0x45/0xb0 mlx5e_vport_rep_load+0x27b/0x2d0 mlx5_esw_offloads_rep_load+0x72/0xf0 esw_offloads_enable+0x5d0/0x970 mlx5_eswitch_enable_locked+0x349/0x430 ? is_mp_supported+0x57/0xb0 mlx5_devlink_eswitch_mode_set+0x26b/0x430 devlink_nl_eswitch_set_doit+0x6f/0xf0 genl_family_rcv_msg_doit+0xe8/0x140 genl_rcv_msg+0x18b/0x290 ? __pfx_devlink_nl_pre_doit+0x10/0x10 ? __pfx_devlink_nl_eswitch_set_doit+0x10/0x10 ? __pfx_devlink_nl_post_doit+0x10/0x10 ? __pfx_genl_rcv_msg+0x10/0x10 netlink_rcv_skb+0x52/0x100 genl_rcv+0x28/0x40 netlink_unicast+0x282/0x3e0 ? __alloc_skb+0xd6/0x190 netlink_sendmsg+0x1f7/0x430 __sys_sendto+0x213/0x220 ? __sys_recvmsg+0x6a/0xd0 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x50/0x1f0 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7fdfb8495047 Fixes: c4d7eb57687f ("net/mxl5e: Add change profile method") Signed-off-by: Saeed Mahameed <saeedm(a)nvidia.com> Reviewed-by: Tariq Toukan <tariqt(a)nvidia.com> Link: https://patch.msgid.link/20260108212657.25090-2-saeed@kernel.org Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: drivers/net/ethernet/mellanox/mlx5/core/en.h drivers/net/ethernet/mellanox/mlx5/core/en_rep.c [Context conflicts.] Signed-off-by: Yi Yang <yiyang13(a)huawei.com> --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 9 ++-- .../net/ethernet/mellanox/mlx5/core/en_main.c | 48 +++++++++++++------ .../net/ethernet/mellanox/mlx5/core/en_rep.c | 11 ++--- 3 files changed, 44 insertions(+), 24 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 455d02b6500d..363809dcb4f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -1203,9 +1203,12 @@ mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *prof int mlx5e_attach_netdev(struct mlx5e_priv *priv); void mlx5e_detach_netdev(struct mlx5e_priv *priv); void mlx5e_destroy_netdev(struct mlx5e_priv *priv); -int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, - const struct mlx5e_profile *new_profile, void *new_ppriv); -void mlx5e_netdev_attach_nic_profile(struct mlx5e_priv *priv); +int mlx5e_netdev_change_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev, + const struct mlx5e_profile *new_profile, + void *new_ppriv); +void mlx5e_netdev_attach_nic_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev); void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv); void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu); void mlx5e_rx_dim_work(struct work_struct *work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index ec1b582cb9d5..c18512dd4a83 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5938,19 +5938,28 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde return err; } -int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, - const struct mlx5e_profile *new_profile, void *new_ppriv) +int mlx5e_netdev_change_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev, + const struct mlx5e_profile *new_profile, + void *new_ppriv) { - const struct mlx5e_profile *orig_profile = priv->profile; - struct net_device *netdev = priv->netdev; - struct mlx5_core_dev *mdev = priv->mdev; - void *orig_ppriv = priv->ppriv; + struct mlx5e_priv *priv = netdev_priv(netdev); + const struct mlx5e_profile *orig_profile; int err, rollback_err; + void *orig_ppriv; - /* cleanup old profile */ - mlx5e_detach_netdev(priv); - priv->profile->cleanup(priv); - mlx5e_priv_cleanup(priv); + orig_profile = priv->profile; + orig_ppriv = priv->ppriv; + + /* NULL could happen if previous change_profile failed to rollback */ + if (priv->profile) { + WARN_ON_ONCE(priv->mdev != mdev); + /* cleanup old profile */ + mlx5e_detach_netdev(priv); + priv->profile->cleanup(priv); + mlx5e_priv_cleanup(priv); + } + /* priv members are not valid from this point ... */ if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv); @@ -5967,16 +5976,25 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, return 0; rollback: + if (!orig_profile) { + netdev_warn(netdev, "no original profile to rollback to\n"); + priv->profile = NULL; + return err; + } + rollback_err = mlx5e_netdev_attach_profile(netdev, mdev, orig_profile, orig_ppriv); - if (rollback_err) - netdev_err(netdev, "%s: failed to rollback to orig profile, %d\n", - __func__, rollback_err); + if (rollback_err) { + netdev_err(netdev, "failed to rollback to orig profile, %d\n", + rollback_err); + priv->profile = NULL; + } return err; } -void mlx5e_netdev_attach_nic_profile(struct mlx5e_priv *priv) +void mlx5e_netdev_attach_nic_profile(struct net_device *netdev, + struct mlx5_core_dev *mdev) { - mlx5e_netdev_change_profile(priv, &mlx5e_nic_profile, NULL); + mlx5e_netdev_change_profile(netdev, mdev, &mlx5e_nic_profile, NULL); } void mlx5e_destroy_netdev(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 656a7b65f4c7..3708d57d757a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1450,17 +1450,16 @@ mlx5e_vport_uplink_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep * { struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); struct net_device *netdev; - struct mlx5e_priv *priv; int err; netdev = mlx5_uplink_netdev_get(dev); if (!netdev) return 0; - priv = netdev_priv(netdev); - rpriv->netdev = priv->netdev; - err = mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile, - rpriv); + /* must not use netdev_priv(netdev), it might not be initialized yet */ + rpriv->netdev = netdev; + err = mlx5e_netdev_change_profile(netdev, dev, + &mlx5e_uplink_rep_profile, rpriv); mlx5_uplink_netdev_put(dev, netdev); return err; } @@ -1473,7 +1472,7 @@ mlx5e_vport_uplink_rep_unload(struct mlx5e_rep_priv *rpriv) priv = netdev_priv(netdev); - mlx5e_netdev_attach_nic_profile(priv); + mlx5e_netdev_attach_nic_profile(netdev, priv->mdev); } static int -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] RDMA/mlx4: Prevent shift wrapping in set_user_sq_size()
by Yao Kai 31 Jan '26

31 Jan '26

From: Dan Carpenter <error27(a)gmail.com> stable inclusion from stable-v4.19.283 commit 3d5ae269c4bd392ec1edbfb3bd031b8f42d7feff category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13202 CVE: CVE-2023-54168 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit d50b3c73f1ac20dabc53dc6e9d64ce9c79a331eb ] The ucmd->log_sq_bb_count variable is controlled by the user so this shift can wrap. Fix it by using check_shl_overflow() in the same way that it was done in commit 515f60004ed9 ("RDMA/hns: Prevent undefined behavior in hns_roce_set_user_sq_size()"). Fixes: 839041329fd3 ("IB/mlx4: Sanity check userspace send queue sizes") Signed-off-by: Dan Carpenter <error27(a)gmail.com> Link: https://lore.kernel.org/r/a8dfbd1d-c019-4556-930b-bab1ded73b10@kili.mountain Signed-off-by: Leon Romanovsky <leon(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yao Kai <yaokai34(a)huawei.com> --- drivers/infiniband/hw/mlx4/qp.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 6dd3cd2c2f80..e262389a05dc 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -436,9 +436,13 @@ static int set_user_sq_size(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, struct mlx4_ib_create_qp *ucmd) { + u32 cnt; + /* Sanity check SQ size before proceeding */ - if ((1 << ucmd->log_sq_bb_count) > dev->dev->caps.max_wqes || - ucmd->log_sq_stride > + if (check_shl_overflow(1, ucmd->log_sq_bb_count, &cnt) || + cnt > dev->dev->caps.max_wqes) + return -EINVAL; + if (ucmd->log_sq_stride > ilog2(roundup_pow_of_two(dev->dev->caps.max_sq_desc_sz)) || ucmd->log_sq_stride < MLX4_IB_MIN_SQ_STRIDE) return -EINVAL; -- 2.43.0

2 1

[PATCH OLK-6.6] net/mlx5e: Don't store mlx5e_priv in mlx5e_dev devlink priv
by Yi Yang 31 Jan '26

31 Jan '26

From: Saeed Mahameed <saeedm(a)nvidia.com> mainline inclusion from mainline-v6.19-rc6 commit 123eda2e5b1638e298e3a66bb1e64a8da92de5e1 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13507 CVE: CVE-2026-22996 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- mlx5e_priv is an unstable structure that can be memset(0) if profile attaching fails, mlx5e_priv in mlx5e_dev devlink private is used to reference the netdev and mdev associated with that struct. Instead, store netdev directly into mlx5e_dev and get mdev from the containing mlx5_adev aux device structure. This fixes a kernel oops in mlx5e_remove when switchdev mode fails due to change profile failure. $ devlink dev eswitch set pci/0000:00:03.0 mode switchdev Error: mlx5_core: Failed setting eswitch to offloads. dmesg: workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR mlx5_core 0012:03:00.1: mlx5e_netdev_init_profile:6214:(pid 37199): mlx5e_priv_init failed, err=-12 mlx5_core 0012:03:00.1 gpu3rdma1: mlx5e_netdev_change_profile: new profile init failed, -12 workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR mlx5_core 0012:03:00.1: mlx5e_netdev_init_profile:6214:(pid 37199): mlx5e_priv_init failed, err=-12 mlx5_core 0012:03:00.1 gpu3rdma1: mlx5e_netdev_change_profile: failed to rollback to orig profile, -12 $ devlink dev reload pci/0000:00:03.0 ==> oops BUG: kernel NULL pointer dereference, address: 0000000000000520 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 3 UID: 0 PID: 521 Comm: devlink Not tainted 6.18.0-rc5+ #117 PREEMPT(voluntary) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-2.fc40 04/01/2014 RIP: 0010:mlx5e_remove+0x68/0x130 RSP: 0018:ffffc900034838f0 EFLAGS: 00010246 RAX: ffff88810283c380 RBX: ffff888101874400 RCX: ffffffff826ffc45 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: ffff888102d789c0 R08: ffff8881007137f0 R09: ffff888100264e10 R10: ffffc90003483898 R11: ffffc900034838a0 R12: ffff888100d261a0 R13: ffff888100d261a0 R14: ffff8881018749a0 R15: ffff888101874400 FS: 00007f8565fea740(0000) GS:ffff88856a759000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000520 CR3: 000000010b11a004 CR4: 0000000000370ef0 Call Trace: <TASK> device_release_driver_internal+0x19c/0x200 bus_remove_device+0xc6/0x130 device_del+0x160/0x3d0 ? devl_param_driverinit_value_get+0x2d/0x90 mlx5_detach_device+0x89/0xe0 mlx5_unload_one_devl_locked+0x3a/0x70 mlx5_devlink_reload_down+0xc8/0x220 devlink_reload+0x7d/0x260 devlink_nl_reload_doit+0x45b/0x5a0 genl_family_rcv_msg_doit+0xe8/0x140 Fixes: ee75f1fc44dd ("net/mlx5e: Create separate devlink instance for ethernet auxiliary device") Fixes: c4d7eb57687f ("net/mxl5e: Add change profile method") Signed-off-by: Saeed Mahameed <saeedm(a)nvidia.com> Link: https://patch.msgid.link/20260108212657.25090-3-saeed@kernel.org Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: drivers/net/ethernet/mellanox/mlx5/core/en_main.c [Commit 381978d28317 ("net/mlx5e: Create single netdev per SD group") was not merged.] Signed-off-by: Yi Yang <yiyang13(a)huawei.com> --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +- .../net/ethernet/mellanox/mlx5/core/en_main.c | 18 ++++++++++-------- 2 files changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 455d02b6500d..ee671e16f344 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -945,7 +945,7 @@ struct mlx5e_priv { }; struct mlx5e_dev { - struct mlx5e_priv *priv; + struct net_device *netdev; struct devlink_port dl_port; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index ec1b582cb9d5..0dd817780a2e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5991,8 +5991,8 @@ static int mlx5e_resume(struct auxiliary_device *adev) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); - struct mlx5e_priv *priv = mlx5e_dev->priv; - struct net_device *netdev = priv->netdev; + struct mlx5e_priv *priv = netdev_priv(mlx5e_dev->netdev); + struct net_device *netdev = mlx5e_dev->netdev; struct mlx5_core_dev *mdev = edev->mdev; int err; @@ -6014,10 +6014,11 @@ static int mlx5e_resume(struct auxiliary_device *adev) static int _mlx5e_suspend(struct auxiliary_device *adev, bool pre_netdev_reg) { + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); - struct mlx5e_priv *priv = mlx5e_dev->priv; - struct net_device *netdev = priv->netdev; - struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_priv *priv = netdev_priv(mlx5e_dev->netdev); + struct net_device *netdev = mlx5e_dev->netdev; + struct mlx5_core_dev *mdev = edev->mdev; if (!pre_netdev_reg && !netif_device_present(netdev)) { if (test_bit(MLX5E_STATE_DESTROYING, &priv->state)) @@ -6063,11 +6064,11 @@ static int _mlx5e_probe(struct auxiliary_device *adev) goto err_devlink_port_unregister; } SET_NETDEV_DEVLINK_PORT(netdev, &mlx5e_dev->dl_port); + mlx5e_dev->netdev = netdev; mlx5e_build_nic_netdev(netdev); priv = netdev_priv(netdev); - mlx5e_dev->priv = priv; priv->profile = profile; priv->ppriv = NULL; @@ -6117,11 +6118,12 @@ static int mlx5e_probe(struct auxiliary_device *adev, static void mlx5e_remove(struct auxiliary_device *adev) { struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); - struct mlx5e_priv *priv = mlx5e_dev->priv; + struct net_device *netdev = mlx5e_dev->netdev; + struct mlx5e_priv *priv = netdev_priv(netdev); mlx5_core_uplink_netdev_set(priv->mdev, NULL); mlx5e_dcbnl_delete_app(priv); - unregister_netdev(priv->netdev); + unregister_netdev(netdev); _mlx5e_suspend(adev, false); /* Avoid cleanup if profile rollback failed. */ if (priv->profile) -- 2.25.1

2 1

[PATCH OLK-6.6] PCI/AER: Fix NULL pointer access by aer_info
by Ziming Du 31 Jan '26

31 Jan '26

From: Vernon Yang <yanglincheng(a)kylinos.cn> stable inclusion from stable-v6.17.8 commit 6618243bcc3f60825f761a41ed65fef9fe97eb25 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/11501 CVE: CVE-2025-68309 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 0a27bdb14b028fed30a10cec2f945c38cb5ca4fa ] The kzalloc(GFP_KERNEL) may return NULL, so all accesses to aer_info->xxx will result in kernel panic. Fix it. Signed-off-by: Vernon Yang <yanglincheng(a)kylinos.cn> Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com> Link: https://patch.msgid.link/20250904182527.67371-1-vernon2gm@gmail.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: drivers/pci/pcie/aer.c [Ziming Du: context conflicts] Signed-off-by: Ziming Du <duziming2(a)huawei.com> --- drivers/pci/pcie/aer.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index 67d36680d834..fae1b96fdaab 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -373,6 +373,10 @@ void pci_aer_init(struct pci_dev *dev) return; dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL); + if (!dev->aer_stats) { + dev->aer_cap = 0; + return; + } /* * We save/restore PCI_ERR_UNCOR_MASK, PCI_ERR_UNCOR_SEVER, -- 2.43.0

2 1

[PATCH OLK-5.10 0/2] fix CVE-2026-22998
by Zheng Qixing 31 Jan '26

31 Jan '26

fix CVE-2026-22998 Maurizio Lombardi (1): nvmet-tcp: remove boilerplate code Shivam Kumar (1): nvme-tcp: fix NULL pointer dereferences in nvmet_tcp_build_pdu_iovec drivers/nvme/target/tcp.c | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) -- 2.39.2

2 3

[PATCH OLK-6.6 0/2] fix CVE-2026-22998
by Zheng Qixing 31 Jan '26

31 Jan '26

fix CVE-2026-22998 Maurizio Lombardi (1): nvmet-tcp: remove boilerplate code Shivam Kumar (1): nvme-tcp: fix NULL pointer dereferences in nvmet_tcp_build_pdu_iovec drivers/nvme/target/tcp.c | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) -- 2.39.2

2 3

[PATCH openEuler-1.0-LTS] md/raid10: fix memleak of md thread
by Zheng Qixing 31 Jan '26

31 Jan '26

From: Yu Kuai <yukuai3(a)huawei.com> stable inclusion from stable-v4.19.283 commit abf4d67060c8f63caff096e5fca1564bfef1e5d4 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13133 CVE: CVE-2023-54294 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------ [ Upstream commit f0ddb83da3cbbf8a1f9087a642c448ff52ee9abd ] In raid10_run(), if setup_conf() succeed and raid10_run() failed before setting 'mddev->thread', then in the error path 'conf->thread' is not freed. Fix the problem by setting 'mddev->thread' right after setup_conf(). Fixes: 43a521238aca ("md-cluster: choose correct label when clustered layout is not supported") Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Signed-off-by: Song Liu <song(a)kernel.org> Link: https://lore.kernel.org/r/20230310073855.1337560-7-yukuai1@huaweicloud.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: drivers/md/raid10.c [Context conflicts.] Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- drivers/md/raid10.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 8b7de02f5796..b46713e7e3c9 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -3824,6 +3824,9 @@ static int raid10_run(struct mddev *mddev) if (!conf) goto out; + mddev->thread = conf->thread; + conf->thread = NULL; + if (mddev_is_clustered(conf->mddev)) { int fc, fo; @@ -3836,9 +3839,6 @@ static int raid10_run(struct mddev *mddev) } } - mddev->thread = conf->thread; - conf->thread = NULL; - chunk_size = mddev->chunk_sectors << 9; if (mddev->queue) { blk_queue_max_discard_sectors(mddev->queue, -- 2.39.2

2 1

[PATCH OLK-6.6] scsi: target: Reset t_task_cdb pointer in error case
by Zheng Qixing 31 Jan '26

31 Jan '26

From: Andrey Vatoropin <a.vatoropin(a)crpt.ru> stable inclusion from stable-v6.6.120 commit 0260ad551b0815eb788d47f32899fbcd65d6f128 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13335 CVE: CVE-2025-68782 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------ commit 5053eab38a4c4543522d0c320c639c56a8b59908 upstream. If allocation of cmd->t_task_cdb fails, it remains NULL but is later dereferenced in the 'err' path. In case of error, reset NULL t_task_cdb value to point at the default fixed-size buffer. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 9e95fb805dc0 ("scsi: target: Fix NULL pointer dereference") Cc: stable(a)vger.kernel.org Signed-off-by: Andrey Vatoropin <a.vatoropin(a)crpt.ru> Reviewed-by: Mike Christie <michael.christie(a)oracle.com> Link: https://patch.msgid.link/20251118084014.324940-1-a.vatoropin@crpt.ru Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- drivers/target/target_core_transport.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index fb93d74c5d0b..b9a144a59dff 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1524,6 +1524,7 @@ target_cmd_init_cdb(struct se_cmd *cmd, unsigned char *cdb, gfp_t gfp) if (scsi_command_size(cdb) > sizeof(cmd->__t_task_cdb)) { cmd->t_task_cdb = kzalloc(scsi_command_size(cdb), gfp); if (!cmd->t_task_cdb) { + cmd->t_task_cdb = &cmd->__t_task_cdb[0]; pr_err("Unable to allocate cmd->t_task_cdb" " %u > sizeof(cmd->__t_task_cdb): %lu ops\n", scsi_command_size(cdb), -- 2.39.2

2 1

[PATCH OLK-6.6] scsi: Revert "scsi: qla2xxx: Perform lockless command completion in abort path"
by Zheng Qixing 31 Jan '26

31 Jan '26

From: Tony Battersby <tonyb(a)cybernetics.com> stable inclusion from stable-v6.6.120 commit e9e601b7df58ba0c667baf30263331df2c02ffe1 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13370 CVE: CVE-2025-68818 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------ commit b57fbc88715b6d18f379463f48a15b560b087ffe upstream. This reverts commit 0367076b0817d5c75dfb83001ce7ce5c64d803a9. The commit being reverted added code to __qla2x00_abort_all_cmds() to call sp->done() without holding a spinlock. But unlike the older code below it, this new code failed to check sp->cmd_type and just assumed TYPE_SRB, which results in a jump to an invalid pointer in target-mode with TYPE_TGT_CMD: qla2xxx [0000:65:00.0]-d034:8: qla24xx_do_nack_work create sess success 0000000009f7a79b qla2xxx [0000:65:00.0]-5003:8: ISP System Error - mbx1=1ff5h mbx2=10h mbx3=0h mbx4=0h mbx5=191h mbx6=0h mbx7=0h. qla2xxx [0000:65:00.0]-d01e:8: -> fwdump no buffer qla2xxx [0000:65:00.0]-f03a:8: qla_target(0): System error async event 0x8002 occurred qla2xxx [0000:65:00.0]-00af:8: Performing ISP error recovery - ha=0000000058183fda. BUG: kernel NULL pointer dereference, address: 0000000000000000 PF: supervisor instruction fetch in kernel mode PF: error_code(0x0010) - not-present page PGD 0 P4D 0 Oops: 0010 [#1] SMP CPU: 2 PID: 9446 Comm: qla2xxx_8_dpc Tainted: G O 6.1.133 #1 Hardware name: Supermicro Super Server/X11SPL-F, BIOS 4.2 12/15/2023 RIP: 0010:0x0 Code: Unable to access opcode bytes at 0xffffffffffffffd6. RSP: 0018:ffffc90001f93dc8 EFLAGS: 00010206 RAX: 0000000000000282 RBX: 0000000000000355 RCX: ffff88810d16a000 RDX: ffff88810dbadaa8 RSI: 0000000000080000 RDI: ffff888169dc38c0 RBP: ffff888169dc38c0 R08: 0000000000000001 R09: 0000000000000045 R10: ffffffffa034bdf0 R11: 0000000000000000 R12: ffff88810800bb40 R13: 0000000000001aa8 R14: ffff888100136610 R15: ffff8881070f7400 FS: 0000000000000000(0000) GS:ffff88bf80080000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffffffffd6 CR3: 000000010c8ff006 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> ? __die+0x4d/0x8b ? page_fault_oops+0x91/0x180 ? trace_buffer_unlock_commit_regs+0x38/0x1a0 ? exc_page_fault+0x391/0x5e0 ? asm_exc_page_fault+0x22/0x30 __qla2x00_abort_all_cmds+0xcb/0x3e0 [qla2xxx_scst] qla2x00_abort_all_cmds+0x50/0x70 [qla2xxx_scst] qla2x00_abort_isp_cleanup+0x3b7/0x4b0 [qla2xxx_scst] qla2x00_abort_isp+0xfd/0x860 [qla2xxx_scst] qla2x00_do_dpc+0x581/0xa40 [qla2xxx_scst] kthread+0xa8/0xd0 </TASK> Then commit 4475afa2646d ("scsi: qla2xxx: Complete command early within lock") added the spinlock back, because not having the lock caused a race and a crash. But qla2x00_abort_srb() in the switch below already checks for qla2x00_chip_is_down() and handles it the same way, so the code above the switch is now redundant and still buggy in target-mode. Remove it. Cc: stable(a)vger.kernel.org Signed-off-by: Tony Battersby <tonyb(a)cybernetics.com> Link: https://patch.msgid.link/3a8022dc-bcfd-4b01-9f9b-7a9ec61fa2a3@cybernetics.c… Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- drivers/scsi/qla2xxx/qla_os.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 91d12198cc6c..ef02ea87e415 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1874,12 +1874,6 @@ __qla2x00_abort_all_cmds(struct qla_qpair *qp, int res) for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) { sp = req->outstanding_cmds[cnt]; if (sp) { - if (qla2x00_chip_is_down(vha)) { - req->outstanding_cmds[cnt] = NULL; - sp->done(sp, res); - continue; - } - switch (sp->cmd_type) { case TYPE_SRB: qla2x00_abort_srb(qp, sp, res, &flags); -- 2.39.2

2 1

[PATCH OLK-6.6] block: Use RCU in blk_mq_[un]quiesce_tagset() instead of set->tag_list_lock
by Zheng Qixing 31 Jan '26

31 Jan '26

From: Mohamed Khalfella <mkhalfella(a)purestorage.com> stable inclusion from stable-v6.6.120 commit ca8764c0ea1fb825f17f19704af55e9e02c9f768 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/13291 CVE: CVE-2025-68756 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------ [ Upstream commit 59e25ef2b413c72da6686d431e7759302cfccafa ] blk_mq_{add,del}_queue_tag_set() functions add and remove queues from tagset, the functions make sure that tagset and queues are marked as shared when two or more queues are attached to the same tagset. Initially a tagset starts as unshared and when the number of added queues reaches two, blk_mq_add_queue_tag_set() marks it as shared along with all the queues attached to it. When the number of attached queues drops to 1 blk_mq_del_queue_tag_set() need to mark both the tagset and the remaining queues as unshared. Both functions need to freeze current queues in tagset before setting on unsetting BLK_MQ_F_TAG_QUEUE_SHARED flag. While doing so, both functions hold set->tag_list_lock mutex, which makes sense as we do not want queues to be added or deleted in the process. This used to work fine until commit 98d81f0df70c ("nvme: use blk_mq_[un]quiesce_tagset") made the nvme driver quiesce tagset instead of quiscing individual queues. blk_mq_quiesce_tagset() does the job and quiesce the queues in set->tag_list while holding set->tag_list_lock also. This results in deadlock between two threads with these stacktraces: __schedule+0x47c/0xbb0 ? timerqueue_add+0x66/0xb0 schedule+0x1c/0xa0 schedule_preempt_disabled+0xa/0x10 __mutex_lock.constprop.0+0x271/0x600 blk_mq_quiesce_tagset+0x25/0xc0 nvme_dev_disable+0x9c/0x250 nvme_timeout+0x1fc/0x520 blk_mq_handle_expired+0x5c/0x90 bt_iter+0x7e/0x90 blk_mq_queue_tag_busy_iter+0x27e/0x550 ? __blk_mq_complete_request_remote+0x10/0x10 ? __blk_mq_complete_request_remote+0x10/0x10 ? __call_rcu_common.constprop.0+0x1c0/0x210 blk_mq_timeout_work+0x12d/0x170 process_one_work+0x12e/0x2d0 worker_thread+0x288/0x3a0 ? rescuer_thread+0x480/0x480 kthread+0xb8/0xe0 ? kthread_park+0x80/0x80 ret_from_fork+0x2d/0x50 ? kthread_park+0x80/0x80 ret_from_fork_asm+0x11/0x20 __schedule+0x47c/0xbb0 ? xas_find+0x161/0x1a0 schedule+0x1c/0xa0 blk_mq_freeze_queue_wait+0x3d/0x70 ? destroy_sched_domains_rcu+0x30/0x30 blk_mq_update_tag_set_shared+0x44/0x80 blk_mq_exit_queue+0x141/0x150 del_gendisk+0x25a/0x2d0 nvme_ns_remove+0xc9/0x170 nvme_remove_namespaces+0xc7/0x100 nvme_remove+0x62/0x150 pci_device_remove+0x23/0x60 device_release_driver_internal+0x159/0x200 unbind_store+0x99/0xa0 kernfs_fop_write_iter+0x112/0x1e0 vfs_write+0x2b1/0x3d0 ksys_write+0x4e/0xb0 do_syscall_64+0x5b/0x160 entry_SYSCALL_64_after_hwframe+0x4b/0x53 The top stacktrace is showing nvme_timeout() called to handle nvme command timeout. timeout handler is trying to disable the controller and as a first step, it needs to blk_mq_quiesce_tagset() to tell blk-mq not to call queue callback handlers. The thread is stuck waiting for set->tag_list_lock as it tries to walk the queues in set->tag_list. The lock is held by the second thread in the bottom stack which is waiting for one of queues to be frozen. The queue usage counter will drop to zero after nvme_timeout() finishes, and this will not happen because the thread will wait for this mutex forever. Given that [un]quiescing queue is an operation that does not need to sleep, update blk_mq_[un]quiesce_tagset() to use RCU instead of taking set->tag_list_lock, update blk_mq_{add,del}_queue_tag_set() to use RCU safe list operations. Also, delete INIT_LIST_HEAD(&q->tag_set_list) in blk_mq_del_queue_tag_set() because we can not re-initialize it while the list is being traversed under RCU. The deleted queue will not be added/deleted to/from a tagset and it will be freed in blk_free_queue() after the end of RCU grace period. Signed-off-by: Mohamed Khalfella <mkhalfella(a)purestorage.com> Fixes: 98d81f0df70c ("nvme: use blk_mq_[un]quiesce_tagset") Reviewed-by: Ming Lei <ming.lei(a)redhat.com> Reviewed-by: Bart Van Assche <bvanassche(a)acm.org> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- block/blk-mq.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 9281c00aa8a9..8b52aa4f371f 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -281,12 +281,12 @@ void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set) { struct request_queue *q; - mutex_lock(&set->tag_list_lock); - list_for_each_entry(q, &set->tag_list, tag_set_list) { + rcu_read_lock(); + list_for_each_entry_rcu(q, &set->tag_list, tag_set_list) { if (!blk_queue_skip_tagset_quiesce(q)) blk_mq_quiesce_queue_nowait(q); } - mutex_unlock(&set->tag_list_lock); + rcu_read_unlock(); blk_mq_wait_quiesce_done(set); } @@ -296,12 +296,12 @@ void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set) { struct request_queue *q; - mutex_lock(&set->tag_list_lock); - list_for_each_entry(q, &set->tag_list, tag_set_list) { + rcu_read_lock(); + list_for_each_entry_rcu(q, &set->tag_list, tag_set_list) { if (!blk_queue_skip_tagset_quiesce(q)) blk_mq_unquiesce_queue(q); } - mutex_unlock(&set->tag_list_lock); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blk_mq_unquiesce_tagset); @@ -4198,7 +4198,7 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q) struct blk_mq_tag_set *set = q->tag_set; mutex_lock(&set->tag_list_lock); - list_del(&q->tag_set_list); + list_del_rcu(&q->tag_set_list); if (list_is_singular(&set->tag_list)) { /* just transitioned to unshared */ set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; @@ -4206,7 +4206,6 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q) blk_mq_update_tag_set_shared(set, false); } mutex_unlock(&set->tag_list_lock); - INIT_LIST_HEAD(&q->tag_set_list); } static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, @@ -4226,7 +4225,7 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, } if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED) queue_set_hctx_shared(q, true); - list_add_tail(&q->tag_set_list, &set->tag_list); + list_add_tail_rcu(&q->tag_set_list, &set->tag_list); mutex_unlock(&set->tag_list_lock); } -- 2.39.2

2 1