aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorAharon Landau <aharonl@nvidia.com>2021-06-10 10:34:26 +0300
committerJason Gunthorpe <jgg@nvidia.com>2021-06-10 08:59:34 -0300
commit6466f03fdf98dd78b9453deb8a7cb0d887c09fec (patch)
treeb4123f568362561cde2083990dc2133a693b1854
parent2adcb4c5a52a2623cd2b43efa7041e74d19f3a5e (diff)
downloadlinux-6466f03fdf98dd78b9453deb8a7cb0d887c09fec.tar.gz
RDMA/mlx5: Delete right entry from MR signature database
The value mr->sig is stored in the entry upon mr allocation, however, ibmr is wrongly entered here as "old", therefore, xa_cmpxchg() does not replace the entry with NULL, which leads to the following trace: WARNING: CPU: 28 PID: 2078 at drivers/infiniband/hw/mlx5/main.c:3643 mlx5_ib_stage_init_cleanup+0x4d/0x60 [mlx5_ib] Modules linked in: nvme_rdma nvme_fabrics nvme_core 8021q garp mrp bonding bridge stp llc rfkill rpcrdma sunrpc rdma_ucm ib_srpt ib_isert iscsi_tad CPU: 28 PID: 2078 Comm: reboot Tainted: G X --------- --- 5.13.0-0.rc2.19.el9.x86_64 #1 Hardware name: Dell Inc. PowerEdge R430/03XKDV, BIOS 2.9.1 12/07/2018 RIP: 0010:mlx5_ib_stage_init_cleanup+0x4d/0x60 [mlx5_ib] Code: 8d bb 70 1f 00 00 be 00 01 00 00 e8 9d 94 ce da 48 3d 00 01 00 00 75 02 5b c3 0f 0b 5b c3 0f 0b 48 83 bb b0 20 00 00 00 74 d5 <0f> 0b eb d1 4 RSP: 0018:ffffa8db06d33c90 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff97f890a44000 RCX: ffff97f900ec0160 RDX: 0000000000000000 RSI: 0000000080080001 RDI: ffff97f890a44000 RBP: ffffffffc0c189b8 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000300 R12: ffff97f890a44000 R13: ffffffffc0c36030 R14: 00000000fee1dead R15: 0000000000000000 FS: 00007f0d5a8a3b40(0000) GS:ffff98077fb80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000555acbf4f450 CR3: 00000002a6f56002 CR4: 00000000001706e0 Call Trace: mlx5r_remove+0x39/0x60 [mlx5_ib] auxiliary_bus_remove+0x1b/0x30 __device_release_driver+0x17a/0x230 device_release_driver+0x24/0x30 bus_remove_device+0xdb/0x140 device_del+0x18b/0x3e0 mlx5_detach_device+0x59/0x90 [mlx5_core] mlx5_unload_one+0x22/0x60 [mlx5_core] shutdown+0x31/0x3a [mlx5_core] pci_device_shutdown+0x34/0x60 device_shutdown+0x15b/0x1c0 __do_sys_reboot.cold+0x2f/0x5b ? vfs_writev+0xc7/0x140 ? handle_mm_fault+0xc5/0x290 ? do_writev+0x6b/0x110 do_syscall_64+0x40/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae Fixes: e6fb246ccafb ("RDMA/mlx5: Consolidate MR destruction to mlx5_ib_dereg_mr()") Link: https://lore.kernel.org/r/f3f585ea0db59c2a78f94f65eedeafc5a2374993.1623309971.git.leonro@nvidia.com Signed-off-by: Aharon Landau <aharonl@nvidia.com> Signed-off-by: Leon Romanovsky <leonro@nvidia.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
-rw-r--r--drivers/infiniband/hw/mlx5/mr.c4
1 files changed, 2 insertions, 2 deletions
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 9662cd39c7ffcb..425423dfac7245 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1940,8 +1940,8 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
mlx5r_deref_wait_odp_mkey(&mr->mmkey);
if (ibmr->type == IB_MR_TYPE_INTEGRITY) {
- xa_cmpxchg(&dev->sig_mrs, mlx5_base_mkey(mr->mmkey.key), ibmr,
- NULL, GFP_KERNEL);
+ xa_cmpxchg(&dev->sig_mrs, mlx5_base_mkey(mr->mmkey.key),
+ mr->sig, NULL, GFP_KERNEL);
if (mr->mtt_mr) {
rc = mlx5_ib_dereg_mr(&mr->mtt_mr->ibmr, NULL);