From: Leon Romanovsky leonro@nvidia.com
[ Upstream commit dc07628bd2bbc1da768e265192c28ebd301f509d ]
RXE is missing update of WQE status in LOCAL_WRITE failures. This caused the following kernel panic if someone sent an atomic operation with an explicitly wrong lkey.
[leonro@vm ~]$ mkt test test_atomic_invalid_lkey (tests.test_atomic.AtomicTest) ... WARNING: CPU: 5 PID: 263 at drivers/infiniband/sw/rxe/rxe_comp.c:740 rxe_completer+0x1a6d/0x2e30 [rdma_rxe] Modules linked in: crc32_generic rdma_rxe ip6_udp_tunnel udp_tunnel rdma_ucm rdma_cm ib_umad ib_ipoib iw_cm ib_cm mlx5_ib ib_uverbs ib_core mlx5_core ptp pps_core CPU: 5 PID: 263 Comm: python3 Not tainted 5.13.0-rc1+ #2936 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:rxe_completer+0x1a6d/0x2e30 [rdma_rxe] Code: 03 0f 8e 65 0e 00 00 3b 93 10 06 00 00 0f 84 82 0a 00 00 4c 89 ff 4c 89 44 24 38 e8 2d 74 a9 e1 4c 8b 44 24 38 e9 1c f5 ff ff <0f> 0b e9 0c e8 ff ff b8 05 00 00 00 41 bf 05 00 00 00 e9 ab e7 ff RSP: 0018:ffff8880158af090 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff888016a78000 RCX: ffffffffa0cf1652 RDX: 1ffff9200004b442 RSI: 0000000000000004 RDI: ffffc9000025a210 RBP: dffffc0000000000 R08: 00000000ffffffea R09: ffff88801617740b R10: ffffed1002c2ee81 R11: 0000000000000007 R12: ffff88800f3b63e8 R13: ffff888016a78008 R14: ffffc9000025a180 R15: 000000000000000c FS: 00007f88b622a740(0000) GS:ffff88806d540000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f88b5a1fa10 CR3: 000000000d848004 CR4: 0000000000370ea0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: rxe_do_task+0x130/0x230 [rdma_rxe] rxe_rcv+0xb11/0x1df0 [rdma_rxe] rxe_loopback+0x157/0x1e0 [rdma_rxe] rxe_responder+0x5532/0x7620 [rdma_rxe] rxe_do_task+0x130/0x230 [rdma_rxe] rxe_rcv+0x9c8/0x1df0 [rdma_rxe] rxe_loopback+0x157/0x1e0 [rdma_rxe] rxe_requester+0x1efd/0x58c0 [rdma_rxe] rxe_do_task+0x130/0x230 [rdma_rxe] rxe_post_send+0x998/0x1860 [rdma_rxe] ib_uverbs_post_send+0xd5f/0x1220 [ib_uverbs] ib_uverbs_write+0x847/0xc80 [ib_uverbs] vfs_write+0x1c5/0x840 ksys_write+0x176/0x1d0 do_syscall_64+0x3f/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae
Fixes: 8700e3e7c485 ("Soft RoCE driver") Link: https://lore.kernel.org/r/11e7b553f3a6f5371c6bb3f57c494bb52b88af99.162071173... Signed-off-by: Leon Romanovsky leonro@nvidia.com Acked-by: Zhu Yanjun zyjzyj2000@gmail.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/sw/rxe/rxe_comp.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index a612b335baa0..06b556169867 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -346,13 +346,15 @@ static inline enum comp_state do_read(struct rxe_qp *qp, ret = copy_data(qp->pd, IB_ACCESS_LOCAL_WRITE, &wqe->dma, payload_addr(pkt), payload_size(pkt), to_mr_obj, NULL); - if (ret) + if (ret) { + wqe->status = IB_WC_LOC_PROT_ERR; return COMPST_ERROR; + }
if (wqe->dma.resid == 0 && (pkt->mask & RXE_END_MASK)) return COMPST_COMP_ACK; - else - return COMPST_UPDATE_COMP; + + return COMPST_UPDATE_COMP; }
static inline enum comp_state do_atomic(struct rxe_qp *qp, @@ -366,10 +368,12 @@ static inline enum comp_state do_atomic(struct rxe_qp *qp, ret = copy_data(qp->pd, IB_ACCESS_LOCAL_WRITE, &wqe->dma, &atomic_orig, sizeof(u64), to_mr_obj, NULL); - if (ret) + if (ret) { + wqe->status = IB_WC_LOC_PROT_ERR; return COMPST_ERROR; - else - return COMPST_COMP_ACK; + } + + return COMPST_COMP_ACK; }
static void make_send_cqe(struct rxe_qp *qp, struct rxe_send_wqe *wqe,