From: Shay Drory shayd@nvidia.com

mainline inclusion from mainline-v6.10-rc1 commit 3d5918477f94e4c2f064567875c475468e264644 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA6S7G CVE: CVE-2024-38608

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

---------------------------

mlx5e_suspend cleans resources only if netif_device_present() returns true. However, mlx5e_resume changes the state of netif, via mlx5e_nic_enable, only if reg_state == NETREG_REGISTERED. In the below case, the above leads to NULL-ptr Oops[1] and memory leaks:

mlx5e_probe _mlx5e_resume mlx5e_attach_netdev mlx5e_nic_enable <-- netdev not reg, not calling netif_device_attach() register_netdev <-- failed for some reason. ERROR_FLOW: _mlx5e_suspend <-- netif_device_present return false, resources aren't freed :(

Hence, clean resources in this case as well.

[1] BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 0 P4D 0 Oops: 0010 [#1] SMP CPU: 2 PID: 9345 Comm: test-ovs-ct-gen Not tainted 6.5.0_for_upstream_min_debug_2023_09_05_16_01 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:0x0 Code: Unable to access opcode bytes at0xffffffffffffffd6. RSP: 0018:ffff888178aaf758 EFLAGS: 00010246 Call Trace: <TASK> ? __die+0x20/0x60 ? page_fault_oops+0x14c/0x3c0 ? exc_page_fault+0x75/0x140 ? asm_exc_page_fault+0x22/0x30 notifier_call_chain+0x35/0xb0 blocking_notifier_call_chain+0x3d/0x60 mlx5_blocking_notifier_call_chain+0x22/0x30 [mlx5_core] mlx5_core_uplink_netdev_event_replay+0x3e/0x60 [mlx5_core] mlx5_mdev_netdev_track+0x53/0x60 [mlx5_ib] mlx5_ib_roce_init+0xc3/0x340 [mlx5_ib] __mlx5_ib_add+0x34/0xd0 [mlx5_ib] mlx5r_probe+0xe1/0x210 [mlx5_ib] ? auxiliary_match_id+0x6a/0x90 auxiliary_bus_probe+0x38/0x80 ? driver_sysfs_add+0x51/0x80 really_probe+0xc9/0x3e0 ? driver_probe_device+0x90/0x90 __driver_probe_device+0x80/0x160 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 bus_for_each_drv+0x80/0xd0 __device_attach+0xbc/0x1f0 bus_probe_device+0x86/0xa0 device_add+0x637/0x840 __auxiliary_device_add+0x3b/0xa0 add_adev+0xc9/0x140 [mlx5_core] mlx5_rescan_drivers_locked+0x22a/0x310 [mlx5_core] mlx5_register_device+0x53/0xa0 [mlx5_core] mlx5_init_one_devl_locked+0x5c4/0x9c0 [mlx5_core] mlx5_init_one+0x3b/0x60 [mlx5_core] probe_one+0x44c/0x730 [mlx5_core] local_pci_probe+0x3e/0x90 pci_device_probe+0xbf/0x210 ? kernfs_create_link+0x5d/0xa0 ? sysfs_do_create_link_sd+0x60/0xc0 really_probe+0xc9/0x3e0 ? driver_probe_device+0x90/0x90 __driver_probe_device+0x80/0x160 driver_probe_device+0x1e/0x90 __device_attach_driver+0x7d/0x100 bus_for_each_drv+0x80/0xd0 __device_attach+0xbc/0x1f0 pci_bus_add_device+0x54/0x80 pci_iov_add_virtfn+0x2e6/0x320 sriov_enable+0x208/0x420 mlx5_core_sriov_configure+0x9e/0x200 [mlx5_core] sriov_numvfs_store+0xae/0x1a0 kernfs_fop_write_iter+0x10c/0x1a0 vfs_write+0x291/0x3c0 ksys_write+0x5f/0xe0 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 CR2: 0000000000000000 ---[ end trace 0000000000000000 ]---

Fixes: 2c3b5beec46a ("net/mlx5e: More generic netdev management API") Signed-off-by: Shay Drory shayd@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Reviewed-by: Simon Horman horms@kernel.org Link: https://lore.kernel.org/r/20240509112951.590184-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org

Conflicts: drivers/net/ethernet/mellanox/mlx5/core/en_main.c [Did not backport 912cebf420c2.] Signed-off-by: Liu Jian liujian56@huawei.com --- v1->v2: update bugzilla. drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5673a4113253..160ab564d641 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5578,7 +5578,7 @@ static int mlx5e_attach(struct mlx5_core_dev *mdev, void *vpriv) return 0; }

-static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv) +static void __mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv, bool pre_netdev_reg) { struct mlx5e_priv *priv = vpriv; struct net_device *netdev = priv->netdev; @@ -5588,13 +5588,18 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv) return; #endif

- if (!netif_device_present(netdev)) + if (!pre_netdev_reg && !netif_device_present(netdev)) return;

mlx5e_detach_netdev(priv); mlx5e_destroy_mdev_resources(mdev); }

+static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv) +{ + __mlx5e_detach(mdev, vpriv, false); +} + static void *mlx5e_add(struct mlx5_core_dev *mdev) { struct net_device *netdev; @@ -5642,7 +5647,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev) return priv;

err_detach: - mlx5e_detach(mdev, priv); + __mlx5e_detach(mdev, priv, true); err_destroy_netdev: mlx5e_destroy_netdev(priv); return NULL;