- Kernel - mailweb.openeuler.org

[PATCH] scsi: bnx2fc: Flush destroy_work queue before calling bnx2fc_interface_put()
by Chen Jun 28 Jun '24

28 Jun '24

From: John Meneghini <jmeneghi(a)redhat.com> stable inclusion from stable-v4.19.228 commit de6336b17a1376db1c0f7a528cce8783db0881c0 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA72BN CVE: CVE-2022-48758 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 847f9ea4c5186fdb7b84297e3eeed9e340e83fce upstream. The bnx2fc_destroy() functions are removing the interface before calling destroy_work. This results multiple WARNings from sysfs_remove_group() as the controller rport device attributes are removed too early. Replace the fcoe_port's destroy_work queue. It's not needed. The problem is easily reproducible with the following steps. Example: $ dmesg -w & $ systemctl enable --now fcoe $ fipvlan -s -c ens2f1 $ fcoeadm -d ens2f1.802 [ 583.464488] host2: libfc: Link down on port (7500a1) [ 583.472651] bnx2fc: 7500a1 - rport not created Yet!! [ 583.490468] ------------[ cut here ]------------ [ 583.538725] sysfs group 'power' not found for kobject 'rport-2:0-0' [ 583.568814] WARNING: CPU: 3 PID: 192 at fs/sysfs/group.c:279 sysfs_remove_group+0x6f/0x80 [ 583.607130] Modules linked in: dm_service_time 8021q garp mrp stp llc bnx2fc cnic uio rpcsec_gss_krb5 auth_rpcgss nfsv4 ... [ 583.942994] CPU: 3 PID: 192 Comm: kworker/3:2 Kdump: loaded Not tainted 5.14.0-39.el9.x86_64 #1 [ 583.984105] Hardware name: HP ProLiant DL120 G7, BIOS J01 07/01/2013 [ 584.016535] Workqueue: fc_wq_2 fc_rport_final_delete [scsi_transport_fc] [ 584.050691] RIP: 0010:sysfs_remove_group+0x6f/0x80 [ 584.074725] Code: ff 5b 48 89 ef 5d 41 5c e9 ee c0 ff ff 48 89 ef e8 f6 b8 ff ff eb d1 49 8b 14 24 48 8b 33 48 c7 c7 ... [ 584.162586] RSP: 0018:ffffb567c15afdc0 EFLAGS: 00010282 [ 584.188225] RAX: 0000000000000000 RBX: ffffffff8eec4220 RCX: 0000000000000000 [ 584.221053] RDX: ffff8c1586ce84c0 RSI: ffff8c1586cd7cc0 RDI: ffff8c1586cd7cc0 [ 584.255089] RBP: 0000000000000000 R08: 0000000000000000 R09: ffffb567c15afc00 [ 584.287954] R10: ffffb567c15afbf8 R11: ffffffff8fbe7f28 R12: ffff8c1486326400 [ 584.322356] R13: ffff8c1486326480 R14: ffff8c1483a4a000 R15: 0000000000000004 [ 584.355379] FS: 0000000000000000(0000) GS:ffff8c1586cc0000(0000) knlGS:0000000000000000 [ 584.394419] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 584.421123] CR2: 00007fe95a6f7840 CR3: 0000000107674002 CR4: 00000000000606e0 [ 584.454888] Call Trace: [ 584.466108] device_del+0xb2/0x3e0 [ 584.481701] device_unregister+0x13/0x60 [ 584.501306] bsg_unregister_queue+0x5b/0x80 [ 584.522029] bsg_remove_queue+0x1c/0x40 [ 584.541884] fc_rport_final_delete+0xf3/0x1d0 [scsi_transport_fc] [ 584.573823] process_one_work+0x1e3/0x3b0 [ 584.592396] worker_thread+0x50/0x3b0 [ 584.609256] ? rescuer_thread+0x370/0x370 [ 584.628877] kthread+0x149/0x170 [ 584.643673] ? set_kthread_struct+0x40/0x40 [ 584.662909] ret_from_fork+0x22/0x30 [ 584.680002] ---[ end trace 53575ecefa942ece ]--- Link: https://lore.kernel.org/r/20220115040044.1013475-1-jmeneghi@redhat.com Fixes: 0cbf32e1681d ("[SCSI] bnx2fc: Avoid calling bnx2fc_if_destroy with unnecessary locks") Tested-by: Guangwu Zhang <guazhang(a)redhat.com> Co-developed-by: Maurizio Lombardi <mlombard(a)redhat.com> Signed-off-by: Maurizio Lombardi <mlombard(a)redhat.com> Signed-off-by: John Meneghini <jmeneghi(a)redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> --- drivers/scsi/bnx2fc/bnx2fc_fcoe.c | 20 +++++--------------- 1 file changed, 5 insertions(+), 15 deletions(-) diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index 66aac62f1238..ea2c601da8e1 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -80,7 +80,7 @@ static int bnx2fc_bind_pcidev(struct bnx2fc_hba *hba); static void bnx2fc_unbind_pcidev(struct bnx2fc_hba *hba); static struct fc_lport *bnx2fc_if_create(struct bnx2fc_interface *interface, struct device *parent, int npiv); -static void bnx2fc_destroy_work(struct work_struct *work); +static void bnx2fc_port_destroy(struct fcoe_port *port); static struct bnx2fc_hba *bnx2fc_hba_lookup(struct net_device *phys_dev); static struct bnx2fc_interface *bnx2fc_interface_lookup(struct net_device @@ -916,9 +916,6 @@ static void bnx2fc_indicate_netevent(void *context, unsigned long event, __bnx2fc_destroy(interface); } mutex_unlock(&bnx2fc_dev_lock); - - /* Ensure ALL destroy work has been completed before return */ - flush_workqueue(bnx2fc_wq); return; default: @@ -1225,8 +1222,8 @@ static int bnx2fc_vport_destroy(struct fc_vport *vport) mutex_unlock(&n_port->lp_mutex); bnx2fc_free_vport(interface->hba, port->lport); bnx2fc_port_shutdown(port->lport); + bnx2fc_port_destroy(port); bnx2fc_interface_put(interface); - queue_work(bnx2fc_wq, &port->destroy_work); return 0; } @@ -1535,7 +1532,6 @@ static struct fc_lport *bnx2fc_if_create(struct bnx2fc_interface *interface, port->lport = lport; port->priv = interface; port->get_netdev = bnx2fc_netdev; - INIT_WORK(&port->destroy_work, bnx2fc_destroy_work); /* Configure fcoe_port */ rc = bnx2fc_lport_config(lport); @@ -1663,8 +1659,8 @@ static void __bnx2fc_destroy(struct bnx2fc_interface *interface) bnx2fc_interface_cleanup(interface); bnx2fc_stop(interface); list_del(&interface->list); + bnx2fc_port_destroy(port); bnx2fc_interface_put(interface); - queue_work(bnx2fc_wq, &port->destroy_work); } /** @@ -1705,15 +1701,12 @@ static int bnx2fc_destroy(struct net_device *netdev) return rc; } -static void bnx2fc_destroy_work(struct work_struct *work) +static void bnx2fc_port_destroy(struct fcoe_port *port) { - struct fcoe_port *port; struct fc_lport *lport; - port = container_of(work, struct fcoe_port, destroy_work); lport = port->lport; - - BNX2FC_HBA_DBG(lport, "Entered bnx2fc_destroy_work\n"); + BNX2FC_HBA_DBG(lport, "Entered %s, destroying lport %p\n", __func__, lport); bnx2fc_if_destroy(lport); } @@ -2567,9 +2560,6 @@ static void bnx2fc_ulp_exit(struct cnic_dev *dev) __bnx2fc_destroy(interface); mutex_unlock(&bnx2fc_dev_lock); - /* Ensure ALL destroy work has been completed before return */ - flush_workqueue(bnx2fc_wq); - bnx2fc_ulp_stop(hba); /* unregister cnic device */ if (test_and_clear_bit(BNX2FC_CNIC_REGISTERED, &hba->reg_with_cnic)) -- 2.17.1

1 0

[PATCH openEuler-22.03-LTS-SP1] ext4: fix mb_cache_entry's e_refcnt leak in ext4_xattr_block_cache_find()
by Baokun Li 28 Jun '24

28 Jun '24

stable inclusion from stable-v5.10.219 commit 76dc776153a47372719d664e0fc50d6355791abb category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA8AER CVE: CVE-2024-39276 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 0c0b4a49d3e7f49690a6827a41faeffad5df7e21 upstream. Syzbot reports a warning as follows: ============================================ WARNING: CPU: 0 PID: 5075 at fs/mbcache.c:419 mb_cache_destroy+0x224/0x290 Modules linked in: CPU: 0 PID: 5075 Comm: syz-executor199 Not tainted 6.9.0-rc6-gb947cc5bf6d7 RIP: 0010:mb_cache_destroy+0x224/0x290 fs/mbcache.c:419 Call Trace: <TASK> ext4_put_super+0x6d4/0xcd0 fs/ext4/super.c:1375 generic_shutdown_super+0x136/0x2d0 fs/super.c:641 kill_block_super+0x44/0x90 fs/super.c:1675 ext4_kill_sb+0x68/0xa0 fs/ext4/super.c:7327 [...] ============================================ This is because when finding an entry in ext4_xattr_block_cache_find(), if ext4_sb_bread() returns -ENOMEM, the ce's e_refcnt, which has already grown in the __entry_find(), won't be put away, and eventually trigger the above issue in mb_cache_destroy() due to reference count leakage. So call mb_cache_entry_put() on the -ENOMEM error branch as a quick fix. Reported-by: syzbot+dd43bd0f7474512edc47(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=dd43bd0f7474512edc47 Fixes: fb265c9cb49e ("ext4: add ext4_sb_bread() to disambiguate ENOMEM cases") Cc: stable(a)kernel.org Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20240504075526.2254349-2-libaokun@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/xattr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index da7610ef1fa9..f9386cb80f70 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -3072,8 +3072,10 @@ ext4_xattr_block_cache_find(struct inode *inode, bh = ext4_sb_bread(inode->i_sb, ce->e_value, REQ_PRIO); if (IS_ERR(bh)) { - if (PTR_ERR(bh) == -ENOMEM) + if (PTR_ERR(bh) == -ENOMEM) { + mb_cache_entry_put(ea_block_cache, ce); return NULL; + } bh = NULL; EXT4_ERROR_INODE(inode, "block %lu read error", (unsigned long)ce->e_value); -- 2.31.1

2 1

[PATCH OLK-5.10] ext4: fix mb_cache_entry's e_refcnt leak in ext4_xattr_block_cache_find()
by Baokun Li 28 Jun '24

28 Jun '24

stable inclusion from stable-v5.10.219 commit 76dc776153a47372719d664e0fc50d6355791abb category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA8AER CVE: CVE-2024-39276 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 0c0b4a49d3e7f49690a6827a41faeffad5df7e21 upstream. Syzbot reports a warning as follows: ============================================ WARNING: CPU: 0 PID: 5075 at fs/mbcache.c:419 mb_cache_destroy+0x224/0x290 Modules linked in: CPU: 0 PID: 5075 Comm: syz-executor199 Not tainted 6.9.0-rc6-gb947cc5bf6d7 RIP: 0010:mb_cache_destroy+0x224/0x290 fs/mbcache.c:419 Call Trace: <TASK> ext4_put_super+0x6d4/0xcd0 fs/ext4/super.c:1375 generic_shutdown_super+0x136/0x2d0 fs/super.c:641 kill_block_super+0x44/0x90 fs/super.c:1675 ext4_kill_sb+0x68/0xa0 fs/ext4/super.c:7327 [...] ============================================ This is because when finding an entry in ext4_xattr_block_cache_find(), if ext4_sb_bread() returns -ENOMEM, the ce's e_refcnt, which has already grown in the __entry_find(), won't be put away, and eventually trigger the above issue in mb_cache_destroy() due to reference count leakage. So call mb_cache_entry_put() on the -ENOMEM error branch as a quick fix. Reported-by: syzbot+dd43bd0f7474512edc47(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=dd43bd0f7474512edc47 Fixes: fb265c9cb49e ("ext4: add ext4_sb_bread() to disambiguate ENOMEM cases") Cc: stable(a)kernel.org Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20240504075526.2254349-2-libaokun@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/xattr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index d223fb41ecec..caface6964e9 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -3068,8 +3068,10 @@ ext4_xattr_block_cache_find(struct inode *inode, bh = ext4_sb_bread(inode->i_sb, ce->e_value, REQ_PRIO); if (IS_ERR(bh)) { - if (PTR_ERR(bh) == -ENOMEM) + if (PTR_ERR(bh) == -ENOMEM) { + mb_cache_entry_put(ea_block_cache, ce); return NULL; + } bh = NULL; EXT4_ERROR_INODE(inode, "block %lu read error", (unsigned long)ce->e_value); -- 2.31.1

2 1

[PATCH OLK-5.10] ext4: fix mb_cache_entry's e_refcnt leak in ext4_xattr_block_cache_find()
by Baokun Li 28 Jun '24

28 Jun '24

stable inclusion from stable-v5.10.219 commit 76dc776153a47372719d664e0fc50d6355791abb category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA8AER CVE: CVE-2024-39276 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 0c0b4a49d3e7f49690a6827a41faeffad5df7e21 upstream. Syzbot reports a warning as follows: ============================================ WARNING: CPU: 0 PID: 5075 at fs/mbcache.c:419 mb_cache_destroy+0x224/0x290 Modules linked in: CPU: 0 PID: 5075 Comm: syz-executor199 Not tainted 6.9.0-rc6-gb947cc5bf6d7 RIP: 0010:mb_cache_destroy+0x224/0x290 fs/mbcache.c:419 Call Trace: <TASK> ext4_put_super+0x6d4/0xcd0 fs/ext4/super.c:1375 generic_shutdown_super+0x136/0x2d0 fs/super.c:641 kill_block_super+0x44/0x90 fs/super.c:1675 ext4_kill_sb+0x68/0xa0 fs/ext4/super.c:7327 [...] ============================================ This is because when finding an entry in ext4_xattr_block_cache_find(), if ext4_sb_bread() returns -ENOMEM, the ce's e_refcnt, which has already grown in the __entry_find(), won't be put away, and eventually trigger the above issue in mb_cache_destroy() due to reference count leakage. So call mb_cache_entry_put() on the -ENOMEM error branch as a quick fix. Reported-by: syzbot+dd43bd0f7474512edc47(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=dd43bd0f7474512edc47 Fixes: fb265c9cb49e ("ext4: add ext4_sb_bread() to disambiguate ENOMEM cases") Cc: stable(a)kernel.org Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20240504075526.2254349-2-libaokun@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/xattr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index d223fb41ecec..caface6964e9 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -3068,8 +3068,10 @@ ext4_xattr_block_cache_find(struct inode *inode, bh = ext4_sb_bread(inode->i_sb, ce->e_value, REQ_PRIO); if (IS_ERR(bh)) { - if (PTR_ERR(bh) == -ENOMEM) + if (PTR_ERR(bh) == -ENOMEM) { + mb_cache_entry_put(ea_block_cache, ce); return NULL; + } bh = NULL; EXT4_ERROR_INODE(inode, "block %lu read error", (unsigned long)ce->e_value); -- 2.31.1

2 2

[PATCH openEuler-1.0-LTS] net/mlx5e: Avoid field-overflowing memcpy()
by Yang Yingliang 28 Jun '24

28 Jun '24

From: Kees Cook <keescook(a)chromium.org> mainline inclusion from mainline-v5.17-rc3 commit ad5185735f7dab342fdd0dd41044da4c9ccfef67 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA72I4 CVE: CVE-2022-48744 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally writing across neighboring fields. Use flexible arrays instead of zero-element arrays (which look like they are always overflowing) and split the cross-field memcpy() into two halves that can be appropriately bounds-checked by the compiler. We were doing: #define ETH_HLEN 14 #define VLAN_HLEN 4 ... #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN) ... struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); ... struct mlx5_wqe_eth_seg *eseg = &wqe->eth; struct mlx5_wqe_data_seg *dseg = wqe->data; ... memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE); target is wqe->eth.inline_hdr.start (which the compiler sees as being 2 bytes in size), but copying 18, intending to write across start (really vlan_tci, 2 bytes). The remaining 16 bytes get written into wqe->data[0], covering byte_count (4 bytes), lkey (4 bytes), and addr (8 bytes). struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; /* 0 16 */ struct mlx5_wqe_eth_seg eth; /* 16 16 */ struct mlx5_wqe_data_seg data[]; /* 32 0 */ /* size: 32, cachelines: 1, members: 3 */ /* last cacheline: 32 bytes */ }; struct mlx5_wqe_eth_seg { u8 swp_outer_l4_offset; /* 0 1 */ u8 swp_outer_l3_offset; /* 1 1 */ u8 swp_inner_l4_offset; /* 2 1 */ u8 swp_inner_l3_offset; /* 3 1 */ u8 cs_flags; /* 4 1 */ u8 swp_flags; /* 5 1 */ __be16 mss; /* 6 2 */ __be32 flow_table_metadata; /* 8 4 */ union { struct { __be16 sz; /* 12 2 */ u8 start[2]; /* 14 2 */ } inline_hdr; /* 12 4 */ struct { __be16 type; /* 12 2 */ __be16 vlan_tci; /* 14 2 */ } insert; /* 12 4 */ __be32 trailer; /* 12 4 */ }; /* 12 4 */ /* size: 16, cachelines: 1, members: 9 */ /* last cacheline: 16 bytes */ }; struct mlx5_wqe_data_seg { __be32 byte_count; /* 0 4 */ __be32 lkey; /* 4 4 */ __be64 addr; /* 8 8 */ /* size: 16, cachelines: 1, members: 3 */ /* last cacheline: 16 bytes */ }; So, split the memcpy() so the compiler can reason about the buffer sizes. "pahole" shows no size nor member offset changes to struct mlx5e_tx_wqe nor struct mlx5e_umr_wqe. "objdump -d" shows no meaningful object code changes (i.e. only source line number induced differences and optimizations). Fixes: b5503b994ed5 ("net/mlx5e: XDP TX forwarding support") Signed-off-by: Kees Cook <keescook(a)chromium.org> Signed-off-by: Saeed Mahameed <saeedm(a)nvidia.com> Conflicts: drivers/net/ethernet/mellanox/mlx5/core/en.h [yyl: adjust context] Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 4 +++- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 6c06b5c3337f..0c5b62292ea0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -184,7 +184,7 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_eth_seg eth; - struct mlx5_wqe_data_seg data[0]; + struct mlx5_wqe_data_seg data[]; }; struct mlx5e_rx_wqe_ll { @@ -200,7 +200,7 @@ struct mlx5e_umr_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_umr_ctrl_seg uctrl; struct mlx5_mkey_seg mkc; - struct mlx5_mtt inline_mtts[0]; + DECLARE_FLEX_ARRAY(struct mlx5_mtt, inline_mtts); }; extern const char mlx5e_self_tests[][ETH_GSTRING_LEN]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 599114ab7821..12f3787b3048 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -159,8 +159,10 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi) /* copy the inline part if required */ if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) { - memcpy(eseg->inline_hdr.start, xdpf->data, MLX5E_XDP_MIN_INLINE); + memcpy(eseg->inline_hdr.start, xdpf->data, sizeof(eseg->inline_hdr.start)); eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE); + memcpy(dseg, xdpf->data + sizeof(eseg->inline_hdr.start), + MLX5E_XDP_MIN_INLINE - sizeof(eseg->inline_hdr.start)); dma_len -= MLX5E_XDP_MIN_INLINE; dma_addr += MLX5E_XDP_MIN_INLINE; dseg++; -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] net/mlx5e: Avoid field-overflowing memcpy()
by Yang Yingliang 28 Jun '24

28 Jun '24

From: Kees Cook <keescook(a)chromium.org> mainline inclusion from mainline-v5.17-rc3 commit ad5185735f7dab342fdd0dd41044da4c9ccfef67 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA72I4 CVE: CVE-2022-48744 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally writing across neighboring fields. Use flexible arrays instead of zero-element arrays (which look like they are always overflowing) and split the cross-field memcpy() into two halves that can be appropriately bounds-checked by the compiler. We were doing: #define ETH_HLEN 14 #define VLAN_HLEN 4 ... #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN) ... struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); ... struct mlx5_wqe_eth_seg *eseg = &wqe->eth; struct mlx5_wqe_data_seg *dseg = wqe->data; ... memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE); target is wqe->eth.inline_hdr.start (which the compiler sees as being 2 bytes in size), but copying 18, intending to write across start (really vlan_tci, 2 bytes). The remaining 16 bytes get written into wqe->data[0], covering byte_count (4 bytes), lkey (4 bytes), and addr (8 bytes). struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; /* 0 16 */ struct mlx5_wqe_eth_seg eth; /* 16 16 */ struct mlx5_wqe_data_seg data[]; /* 32 0 */ /* size: 32, cachelines: 1, members: 3 */ /* last cacheline: 32 bytes */ }; struct mlx5_wqe_eth_seg { u8 swp_outer_l4_offset; /* 0 1 */ u8 swp_outer_l3_offset; /* 1 1 */ u8 swp_inner_l4_offset; /* 2 1 */ u8 swp_inner_l3_offset; /* 3 1 */ u8 cs_flags; /* 4 1 */ u8 swp_flags; /* 5 1 */ __be16 mss; /* 6 2 */ __be32 flow_table_metadata; /* 8 4 */ union { struct { __be16 sz; /* 12 2 */ u8 start[2]; /* 14 2 */ } inline_hdr; /* 12 4 */ struct { __be16 type; /* 12 2 */ __be16 vlan_tci; /* 14 2 */ } insert; /* 12 4 */ __be32 trailer; /* 12 4 */ }; /* 12 4 */ /* size: 16, cachelines: 1, members: 9 */ /* last cacheline: 16 bytes */ }; struct mlx5_wqe_data_seg { __be32 byte_count; /* 0 4 */ __be32 lkey; /* 4 4 */ __be64 addr; /* 8 8 */ /* size: 16, cachelines: 1, members: 3 */ /* last cacheline: 16 bytes */ }; So, split the memcpy() so the compiler can reason about the buffer sizes. "pahole" shows no size nor member offset changes to struct mlx5e_tx_wqe nor struct mlx5e_umr_wqe. "objdump -d" shows no meaningful object code changes (i.e. only source line number induced differences and optimizations). Fixes: b5503b994ed5 ("net/mlx5e: XDP TX forwarding support") Signed-off-by: Kees Cook <keescook(a)chromium.org> Signed-off-by: Saeed Mahameed <saeedm(a)nvidia.com> Conflicts: drivers/net/ethernet/mellanox/mlx5/core/en.h [yyl: adjust context] Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 4 +++- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index b0229ceae234..bf711037f4c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -199,7 +199,7 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_eth_seg eth; - struct mlx5_wqe_data_seg data[0]; + struct mlx5_wqe_data_seg data[]; }; struct mlx5e_rx_wqe_ll { @@ -215,7 +215,7 @@ struct mlx5e_umr_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_umr_ctrl_seg uctrl; struct mlx5_mkey_seg mkc; - struct mlx5_mtt inline_mtts[0]; + DECLARE_FLEX_ARRAY(struct mlx5_mtt, inline_mtts); }; extern const char mlx5e_self_tests[][ETH_GSTRING_LEN]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index ae90d533a350..923e10d06f3d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -341,8 +341,10 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, /* copy the inline part if required */ if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) { - memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE); + memcpy(eseg->inline_hdr.start, xdptxd->data, sizeof(eseg->inline_hdr.start)); eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE); + memcpy(dseg, xdptxd->data + sizeof(eseg->inline_hdr.start), + MLX5E_XDP_MIN_INLINE - sizeof(eseg->inline_hdr.start)); dma_len -= MLX5E_XDP_MIN_INLINE; dma_addr += MLX5E_XDP_MIN_INLINE; dseg++; -- 2.25.1

2 1

[PATCH OLK-5.10] net/mlx5e: Avoid field-overflowing memcpy()
by Yang Yingliang 28 Jun '24

28 Jun '24

From: Kees Cook <keescook(a)chromium.org> mainline inclusion from mainline-v5.17-rc3 commit ad5185735f7dab342fdd0dd41044da4c9ccfef67 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA72I4 CVE: CVE-2022-48744 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally writing across neighboring fields. Use flexible arrays instead of zero-element arrays (which look like they are always overflowing) and split the cross-field memcpy() into two halves that can be appropriately bounds-checked by the compiler. We were doing: #define ETH_HLEN 14 #define VLAN_HLEN 4 ... #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN) ... struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); ... struct mlx5_wqe_eth_seg *eseg = &wqe->eth; struct mlx5_wqe_data_seg *dseg = wqe->data; ... memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE); target is wqe->eth.inline_hdr.start (which the compiler sees as being 2 bytes in size), but copying 18, intending to write across start (really vlan_tci, 2 bytes). The remaining 16 bytes get written into wqe->data[0], covering byte_count (4 bytes), lkey (4 bytes), and addr (8 bytes). struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; /* 0 16 */ struct mlx5_wqe_eth_seg eth; /* 16 16 */ struct mlx5_wqe_data_seg data[]; /* 32 0 */ /* size: 32, cachelines: 1, members: 3 */ /* last cacheline: 32 bytes */ }; struct mlx5_wqe_eth_seg { u8 swp_outer_l4_offset; /* 0 1 */ u8 swp_outer_l3_offset; /* 1 1 */ u8 swp_inner_l4_offset; /* 2 1 */ u8 swp_inner_l3_offset; /* 3 1 */ u8 cs_flags; /* 4 1 */ u8 swp_flags; /* 5 1 */ __be16 mss; /* 6 2 */ __be32 flow_table_metadata; /* 8 4 */ union { struct { __be16 sz; /* 12 2 */ u8 start[2]; /* 14 2 */ } inline_hdr; /* 12 4 */ struct { __be16 type; /* 12 2 */ __be16 vlan_tci; /* 14 2 */ } insert; /* 12 4 */ __be32 trailer; /* 12 4 */ }; /* 12 4 */ /* size: 16, cachelines: 1, members: 9 */ /* last cacheline: 16 bytes */ }; struct mlx5_wqe_data_seg { __be32 byte_count; /* 0 4 */ __be32 lkey; /* 4 4 */ __be64 addr; /* 8 8 */ /* size: 16, cachelines: 1, members: 3 */ /* last cacheline: 16 bytes */ }; So, split the memcpy() so the compiler can reason about the buffer sizes. "pahole" shows no size nor member offset changes to struct mlx5e_tx_wqe nor struct mlx5e_umr_wqe. "objdump -d" shows no meaningful object code changes (i.e. only source line number induced differences and optimizations). Fixes: b5503b994ed5 ("net/mlx5e: XDP TX forwarding support") Signed-off-by: Kees Cook <keescook(a)chromium.org> Signed-off-by: Saeed Mahameed <saeedm(a)nvidia.com> Conflicts: drivers/net/ethernet/mellanox/mlx5/core/en.h [yyl: adjust context] Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 4 +++- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index b0229ceae234..bf711037f4c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -199,7 +199,7 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_eth_seg eth; - struct mlx5_wqe_data_seg data[0]; + struct mlx5_wqe_data_seg data[]; }; struct mlx5e_rx_wqe_ll { @@ -215,7 +215,7 @@ struct mlx5e_umr_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_umr_ctrl_seg uctrl; struct mlx5_mkey_seg mkc; - struct mlx5_mtt inline_mtts[0]; + DECLARE_FLEX_ARRAY(struct mlx5_mtt, inline_mtts); }; extern const char mlx5e_self_tests[][ETH_GSTRING_LEN]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index ae90d533a350..923e10d06f3d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -341,8 +341,10 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, /* copy the inline part if required */ if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) { - memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE); + memcpy(eseg->inline_hdr.start, xdptxd->data, sizeof(eseg->inline_hdr.start)); eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE); + memcpy(dseg, xdptxd->data + sizeof(eseg->inline_hdr.start), + MLX5E_XDP_MIN_INLINE - sizeof(eseg->inline_hdr.start)); dma_len -= MLX5E_XDP_MIN_INLINE; dma_addr += MLX5E_XDP_MIN_INLINE; dseg++; -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] ext4: fix mb_cache_entry's e_refcnt leak in ext4_xattr_block_cache_find()
by Baokun Li 28 Jun '24

28 Jun '24

stable inclusion from stable-v4.19.316 commit 9ad75e78747b5a50dc5a52f0f8e92e920a653f16 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA8AER CVE: CVE-2024-39276 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 0c0b4a49d3e7f49690a6827a41faeffad5df7e21 upstream. Syzbot reports a warning as follows: ============================================ WARNING: CPU: 0 PID: 5075 at fs/mbcache.c:419 mb_cache_destroy+0x224/0x290 Modules linked in: CPU: 0 PID: 5075 Comm: syz-executor199 Not tainted 6.9.0-rc6-gb947cc5bf6d7 RIP: 0010:mb_cache_destroy+0x224/0x290 fs/mbcache.c:419 Call Trace: <TASK> ext4_put_super+0x6d4/0xcd0 fs/ext4/super.c:1375 generic_shutdown_super+0x136/0x2d0 fs/super.c:641 kill_block_super+0x44/0x90 fs/super.c:1675 ext4_kill_sb+0x68/0xa0 fs/ext4/super.c:7327 [...] ============================================ This is because when finding an entry in ext4_xattr_block_cache_find(), if ext4_sb_bread() returns -ENOMEM, the ce's e_refcnt, which has already grown in the __entry_find(), won't be put away, and eventually trigger the above issue in mb_cache_destroy() due to reference count leakage. So call mb_cache_entry_put() on the -ENOMEM error branch as a quick fix. Reported-by: syzbot+dd43bd0f7474512edc47(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=dd43bd0f7474512edc47 Fixes: fb265c9cb49e ("ext4: add ext4_sb_bread() to disambiguate ENOMEM cases") Cc: stable(a)kernel.org Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20240504075526.2254349-2-libaokun@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/ext4/xattr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index abb644b169cb..daef34f8bd21 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -3070,8 +3070,10 @@ ext4_xattr_block_cache_find(struct inode *inode, bh = ext4_sb_bread(inode->i_sb, ce->e_value, REQ_PRIO); if (IS_ERR(bh)) { - if (PTR_ERR(bh) == -ENOMEM) + if (PTR_ERR(bh) == -ENOMEM) { + mb_cache_entry_put(ea_block_cache, ce); return NULL; + } bh = NULL; EXT4_ERROR_INODE(inode, "block %lu read error", (unsigned long)ce->e_value); -- 2.31.1

2 1

[PATCH OLK-5.10] virtio: delete vq in vp_find_vqs_msix() when request_irq() fails
by Li Huafei 28 Jun '24

28 Jun '24

From: Jiri Pirko <jiri(a)nvidia.com> stable inclusion from stable-v5.10.219 commit 7fbe54f02a5c77ff5dd65e8ed0b58e3bd8c43e9c category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA7D1Z CVE: CVE-2024-37353 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 89875151fccdd024d571aa884ea97a0128b968b6 ] When request_irq() fails, error path calls vp_del_vqs(). There, as vq is present in the list, free_irq() is called for the same vector. That causes following splat: [ 0.414355] Trying to free already-free IRQ 27 [ 0.414403] WARNING: CPU: 1 PID: 1 at kernel/irq/manage.c:1899 free_irq+0x1a1/0x2d0 [ 0.414510] Modules linked in: [ 0.414540] CPU: 1 PID: 1 Comm: swapper/0 Not tainted 6.9.0-rc4+ #27 [ 0.414540] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-1.fc39 04/01/2014 [ 0.414540] RIP: 0010:free_irq+0x1a1/0x2d0 [ 0.414540] Code: 1e 00 48 83 c4 08 48 89 e8 5b 5d 41 5c 41 5d 41 5e 41 5f c3 cc cc cc cc 90 8b 74 24 04 48 c7 c7 98 80 6c b1 e8 00 c9 f7 ff 90 <0f> 0b 90 90 48 89 ee 4c 89 ef e8 e0 20 b8 00 49 8b 47 40 48 8b 40 [ 0.414540] RSP: 0000:ffffb71480013ae0 EFLAGS: 00010086 [ 0.414540] RAX: 0000000000000000 RBX: ffffa099c2722000 RCX: 0000000000000000 [ 0.414540] RDX: 0000000000000000 RSI: ffffb71480013998 RDI: 0000000000000001 [ 0.414540] RBP: 0000000000000246 R08: 00000000ffffdfff R09: 0000000000000001 [ 0.414540] R10: 00000000ffffdfff R11: ffffffffb18729c0 R12: ffffa099c1c91760 [ 0.414540] R13: ffffa099c1c916a4 R14: ffffa099c1d2f200 R15: ffffa099c1c91600 [ 0.414540] FS: 0000000000000000(0000) GS:ffffa099fec40000(0000) knlGS:0000000000000000 [ 0.414540] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 0.414540] CR2: 0000000000000000 CR3: 0000000008e3e001 CR4: 0000000000370ef0 [ 0.414540] Call Trace: [ 0.414540] <TASK> [ 0.414540] ? __warn+0x80/0x120 [ 0.414540] ? free_irq+0x1a1/0x2d0 [ 0.414540] ? report_bug+0x164/0x190 [ 0.414540] ? handle_bug+0x3b/0x70 [ 0.414540] ? exc_invalid_op+0x17/0x70 [ 0.414540] ? asm_exc_invalid_op+0x1a/0x20 [ 0.414540] ? free_irq+0x1a1/0x2d0 [ 0.414540] vp_del_vqs+0xc1/0x220 [ 0.414540] vp_find_vqs_msix+0x305/0x470 [ 0.414540] vp_find_vqs+0x3e/0x1a0 [ 0.414540] vp_modern_find_vqs+0x1b/0x70 [ 0.414540] init_vqs+0x387/0x600 [ 0.414540] virtnet_probe+0x50a/0xc80 [ 0.414540] virtio_dev_probe+0x1e0/0x2b0 [ 0.414540] really_probe+0xc0/0x2c0 [ 0.414540] ? __pfx___driver_attach+0x10/0x10 [ 0.414540] __driver_probe_device+0x73/0x120 [ 0.414540] driver_probe_device+0x1f/0xe0 [ 0.414540] __driver_attach+0x88/0x180 [ 0.414540] bus_for_each_dev+0x85/0xd0 [ 0.414540] bus_add_driver+0xec/0x1f0 [ 0.414540] driver_register+0x59/0x100 [ 0.414540] ? __pfx_virtio_net_driver_init+0x10/0x10 [ 0.414540] virtio_net_driver_init+0x90/0xb0 [ 0.414540] do_one_initcall+0x58/0x230 [ 0.414540] kernel_init_freeable+0x1a3/0x2d0 [ 0.414540] ? __pfx_kernel_init+0x10/0x10 [ 0.414540] kernel_init+0x1a/0x1c0 [ 0.414540] ret_from_fork+0x31/0x50 [ 0.414540] ? __pfx_kernel_init+0x10/0x10 [ 0.414540] ret_from_fork_asm+0x1a/0x30 [ 0.414540] </TASK> Fix this by calling deleting the current vq when request_irq() fails. Fixes: 0b0f9dc52ed0 ("Revert "virtio_pci: use shared interrupts for virtqueues"") Signed-off-by: Jiri Pirko <jiri(a)nvidia.com> Message-Id: <20240426150845.3999481-1-jiri(a)resnulli.us> Signed-off-by: Michael S. Tsirkin <mst(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Li Huafei <lihuafei1(a)huawei.com> --- drivers/virtio/virtio_pci_common.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 1e890ef176873..a6f375417fd54 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -339,8 +339,10 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs, vring_interrupt, 0, vp_dev->msix_names[msix_vec], vqs[i]); - if (err) + if (err) { + vp_del_vq(vqs[i]); goto error_find; + } } return 0; -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] virtio: delete vq in vp_find_vqs_msix() when request_irq() fails
by Li Huafei 28 Jun '24

28 Jun '24

From: Jiri Pirko <jiri(a)nvidia.com> stable inclusion from stable-v4.19.316 commit cb7a7c8144b434e06aba99b13b045a7efe859587 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA7D1Z CVE: CVE-2024-37353 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 89875151fccdd024d571aa884ea97a0128b968b6 ] When request_irq() fails, error path calls vp_del_vqs(). There, as vq is present in the list, free_irq() is called for the same vector. That causes following splat: [ 0.414355] Trying to free already-free IRQ 27 [ 0.414403] WARNING: CPU: 1 PID: 1 at kernel/irq/manage.c:1899 free_irq+0x1a1/0x2d0 [ 0.414510] Modules linked in: [ 0.414540] CPU: 1 PID: 1 Comm: swapper/0 Not tainted 6.9.0-rc4+ #27 [ 0.414540] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-1.fc39 04/01/2014 [ 0.414540] RIP: 0010:free_irq+0x1a1/0x2d0 [ 0.414540] Code: 1e 00 48 83 c4 08 48 89 e8 5b 5d 41 5c 41 5d 41 5e 41 5f c3 cc cc cc cc 90 8b 74 24 04 48 c7 c7 98 80 6c b1 e8 00 c9 f7 ff 90 <0f> 0b 90 90 48 89 ee 4c 89 ef e8 e0 20 b8 00 49 8b 47 40 48 8b 40 [ 0.414540] RSP: 0000:ffffb71480013ae0 EFLAGS: 00010086 [ 0.414540] RAX: 0000000000000000 RBX: ffffa099c2722000 RCX: 0000000000000000 [ 0.414540] RDX: 0000000000000000 RSI: ffffb71480013998 RDI: 0000000000000001 [ 0.414540] RBP: 0000000000000246 R08: 00000000ffffdfff R09: 0000000000000001 [ 0.414540] R10: 00000000ffffdfff R11: ffffffffb18729c0 R12: ffffa099c1c91760 [ 0.414540] R13: ffffa099c1c916a4 R14: ffffa099c1d2f200 R15: ffffa099c1c91600 [ 0.414540] FS: 0000000000000000(0000) GS:ffffa099fec40000(0000) knlGS:0000000000000000 [ 0.414540] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 0.414540] CR2: 0000000000000000 CR3: 0000000008e3e001 CR4: 0000000000370ef0 [ 0.414540] Call Trace: [ 0.414540] <TASK> [ 0.414540] ? __warn+0x80/0x120 [ 0.414540] ? free_irq+0x1a1/0x2d0 [ 0.414540] ? report_bug+0x164/0x190 [ 0.414540] ? handle_bug+0x3b/0x70 [ 0.414540] ? exc_invalid_op+0x17/0x70 [ 0.414540] ? asm_exc_invalid_op+0x1a/0x20 [ 0.414540] ? free_irq+0x1a1/0x2d0 [ 0.414540] vp_del_vqs+0xc1/0x220 [ 0.414540] vp_find_vqs_msix+0x305/0x470 [ 0.414540] vp_find_vqs+0x3e/0x1a0 [ 0.414540] vp_modern_find_vqs+0x1b/0x70 [ 0.414540] init_vqs+0x387/0x600 [ 0.414540] virtnet_probe+0x50a/0xc80 [ 0.414540] virtio_dev_probe+0x1e0/0x2b0 [ 0.414540] really_probe+0xc0/0x2c0 [ 0.414540] ? __pfx___driver_attach+0x10/0x10 [ 0.414540] __driver_probe_device+0x73/0x120 [ 0.414540] driver_probe_device+0x1f/0xe0 [ 0.414540] __driver_attach+0x88/0x180 [ 0.414540] bus_for_each_dev+0x85/0xd0 [ 0.414540] bus_add_driver+0xec/0x1f0 [ 0.414540] driver_register+0x59/0x100 [ 0.414540] ? __pfx_virtio_net_driver_init+0x10/0x10 [ 0.414540] virtio_net_driver_init+0x90/0xb0 [ 0.414540] do_one_initcall+0x58/0x230 [ 0.414540] kernel_init_freeable+0x1a3/0x2d0 [ 0.414540] ? __pfx_kernel_init+0x10/0x10 [ 0.414540] kernel_init+0x1a/0x1c0 [ 0.414540] ret_from_fork+0x31/0x50 [ 0.414540] ? __pfx_kernel_init+0x10/0x10 [ 0.414540] ret_from_fork_asm+0x1a/0x30 [ 0.414540] </TASK> Fix this by calling deleting the current vq when request_irq() fails. Fixes: 0b0f9dc52ed0 ("Revert "virtio_pci: use shared interrupts for virtqueues"") Signed-off-by: Jiri Pirko <jiri(a)nvidia.com> Message-Id: <20240426150845.3999481-1-jiri(a)resnulli.us> Signed-off-by: Michael S. Tsirkin <mst(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Li Huafei <lihuafei1(a)huawei.com> --- drivers/virtio/virtio_pci_common.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index b7cc63f556eea..f26f9f4dc7239 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -343,8 +343,10 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs, vring_interrupt, 0, vp_dev->msix_names[msix_vec], vqs[i]); - if (err) + if (err) { + vp_del_vq(vqs[i]); goto error_find; + } } return 0; -- 2.25.1

2 1