From 1231363aec86704a6b0467a12e3ca7bdf890e01d Mon Sep 17 00:00:00 2001 From: Juraj Pecigos Date: Sun, 26 Mar 2023 11:29:49 +0200 Subject: [PATCH 1/2] nvme-pci: mark Lexar NM760 as IGNORE_DEV_SUBNQN A system with more than one of these SSDs will only have one usable. The kernel fails to detect more than one nvme device due to duplicate cntlids. before: [ 9.395229] nvme 0000:01:00.0: platform quirk: setting simple suspend [ 9.395262] nvme nvme0: pci function 0000:01:00.0 [ 9.395282] nvme 0000:03:00.0: platform quirk: setting simple suspend [ 9.395305] nvme nvme1: pci function 0000:03:00.0 [ 9.409873] nvme nvme0: Duplicate cntlid 1 with nvme1, subsys nqn.2022-07.com.siliconmotion:nvm-subsystem-sn- , rejecting [ 9.409982] nvme nvme0: Removing after probe failure status: -22 [ 9.427487] nvme nvme1: allocated 64 MiB host memory buffer. [ 9.445088] nvme nvme1: 16/0/0 default/read/poll queues [ 9.449898] nvme nvme1: Ignoring bogus Namespace Identifiers after: [ 1.161890] nvme 0000:01:00.0: platform quirk: setting simple suspend [ 1.162660] nvme nvme0: pci function 0000:01:00.0 [ 1.162684] nvme 0000:03:00.0: platform quirk: setting simple suspend [ 1.162707] nvme nvme1: pci function 0000:03:00.0 [ 1.191354] nvme nvme0: allocated 64 MiB host memory buffer. [ 1.193378] nvme nvme1: allocated 64 MiB host memory buffer. [ 1.211044] nvme nvme1: 16/0/0 default/read/poll queues [ 1.211080] nvme nvme0: 16/0/0 default/read/poll queues [ 1.216145] nvme nvme0: Ignoring bogus Namespace Identifiers [ 1.216261] nvme nvme1: Ignoring bogus Namespace Identifiers Adding the NVME_QUIRK_IGNORE_DEV_SUBNQN quirk to resolves the issue. Signed-off-by: Juraj Pecigos Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index b615906263f3..282d808400c5 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3441,7 +3441,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(0x1d97, 0x1d97), /* Lexar NM620 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1d97, 0x2269), /* Lexar NM760 */ - .driver_data = NVME_QUIRK_BOGUS_NID, }, + .driver_data = NVME_QUIRK_BOGUS_NID | + NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065), From 88eaba80328b31ef81813a1207b4056efd7006a6 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 20 Mar 2023 15:33:34 +0200 Subject: [PATCH 2/2] nvme-tcp: fix a possible UAF when failing to allocate an io queue When we allocate a nvme-tcp queue, we set the data_ready callback before we actually need to use it. This creates the potential that if a stray controller sends us data on the socket before we connect, we can trigger the io_work and start consuming the socket. In this case reported: we failed to allocate one of the io queues, and as we start releasing the queues that we already allocated, we get a UAF [1] from the io_work which is running before it should really. Fix this by setting the socket ops callbacks only before we start the queue, so that we can't accidentally schedule the io_work in the initialization phase before the queue started. While we are at it, rename nvme_tcp_restore_sock_calls to pair with nvme_tcp_setup_sock_ops. [1]: [16802.107284] nvme nvme4: starting error recovery [16802.109166] nvme nvme4: Reconnecting in 10 seconds... [16812.173535] nvme nvme4: failed to connect socket: -111 [16812.173745] nvme nvme4: Failed reconnect attempt 1 [16812.173747] nvme nvme4: Reconnecting in 10 seconds... [16822.413555] nvme nvme4: failed to connect socket: -111 [16822.413762] nvme nvme4: Failed reconnect attempt 2 [16822.413765] nvme nvme4: Reconnecting in 10 seconds... [16832.661274] nvme nvme4: creating 32 I/O queues. [16833.919887] BUG: kernel NULL pointer dereference, address: 0000000000000088 [16833.920068] nvme nvme4: Failed reconnect attempt 3 [16833.920094] #PF: supervisor write access in kernel mode [16833.920261] nvme nvme4: Reconnecting in 10 seconds... [16833.920368] #PF: error_code(0x0002) - not-present page [16833.921086] Workqueue: nvme_tcp_wq nvme_tcp_io_work [nvme_tcp] [16833.921191] RIP: 0010:_raw_spin_lock_bh+0x17/0x30 ... [16833.923138] Call Trace: [16833.923271] [16833.923402] lock_sock_nested+0x1e/0x50 [16833.923545] nvme_tcp_try_recv+0x40/0xa0 [nvme_tcp] [16833.923685] nvme_tcp_io_work+0x68/0xa0 [nvme_tcp] [16833.923824] process_one_work+0x1e8/0x390 [16833.923969] worker_thread+0x53/0x3d0 [16833.924104] ? process_one_work+0x390/0x390 [16833.924240] kthread+0x124/0x150 [16833.924376] ? set_kthread_struct+0x50/0x50 [16833.924518] ret_from_fork+0x1f/0x30 [16833.924655] Reported-by: Yanjun Zhang Signed-off-by: Sagi Grimberg Tested-by: Yanjun Zhang Signed-off-by: Christoph Hellwig --- drivers/nvme/host/tcp.c | 46 +++++++++++++++++++++++------------------ 1 file changed, 26 insertions(+), 20 deletions(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 42c0598c31f2..49c9e7bc9116 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1620,22 +1620,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid) if (ret) goto err_init_connect; - queue->rd_enabled = true; set_bit(NVME_TCP_Q_ALLOCATED, &queue->flags); - nvme_tcp_init_recv_ctx(queue); - - write_lock_bh(&queue->sock->sk->sk_callback_lock); - queue->sock->sk->sk_user_data = queue; - queue->state_change = queue->sock->sk->sk_state_change; - queue->data_ready = queue->sock->sk->sk_data_ready; - queue->write_space = queue->sock->sk->sk_write_space; - queue->sock->sk->sk_data_ready = nvme_tcp_data_ready; - queue->sock->sk->sk_state_change = nvme_tcp_state_change; - queue->sock->sk->sk_write_space = nvme_tcp_write_space; -#ifdef CONFIG_NET_RX_BUSY_POLL - queue->sock->sk->sk_ll_usec = 1; -#endif - write_unlock_bh(&queue->sock->sk->sk_callback_lock); return 0; @@ -1655,7 +1640,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid) return ret; } -static void nvme_tcp_restore_sock_calls(struct nvme_tcp_queue *queue) +static void nvme_tcp_restore_sock_ops(struct nvme_tcp_queue *queue) { struct socket *sock = queue->sock; @@ -1670,7 +1655,7 @@ static void nvme_tcp_restore_sock_calls(struct nvme_tcp_queue *queue) static void __nvme_tcp_stop_queue(struct nvme_tcp_queue *queue) { kernel_sock_shutdown(queue->sock, SHUT_RDWR); - nvme_tcp_restore_sock_calls(queue); + nvme_tcp_restore_sock_ops(queue); cancel_work_sync(&queue->io_work); } @@ -1688,21 +1673,42 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid) mutex_unlock(&queue->queue_lock); } +static void nvme_tcp_setup_sock_ops(struct nvme_tcp_queue *queue) +{ + write_lock_bh(&queue->sock->sk->sk_callback_lock); + queue->sock->sk->sk_user_data = queue; + queue->state_change = queue->sock->sk->sk_state_change; + queue->data_ready = queue->sock->sk->sk_data_ready; + queue->write_space = queue->sock->sk->sk_write_space; + queue->sock->sk->sk_data_ready = nvme_tcp_data_ready; + queue->sock->sk->sk_state_change = nvme_tcp_state_change; + queue->sock->sk->sk_write_space = nvme_tcp_write_space; +#ifdef CONFIG_NET_RX_BUSY_POLL + queue->sock->sk->sk_ll_usec = 1; +#endif + write_unlock_bh(&queue->sock->sk->sk_callback_lock); +} + static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx) { struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); + struct nvme_tcp_queue *queue = &ctrl->queues[idx]; int ret; + queue->rd_enabled = true; + nvme_tcp_init_recv_ctx(queue); + nvme_tcp_setup_sock_ops(queue); + if (idx) ret = nvmf_connect_io_queue(nctrl, idx); else ret = nvmf_connect_admin_queue(nctrl); if (!ret) { - set_bit(NVME_TCP_Q_LIVE, &ctrl->queues[idx].flags); + set_bit(NVME_TCP_Q_LIVE, &queue->flags); } else { - if (test_bit(NVME_TCP_Q_ALLOCATED, &ctrl->queues[idx].flags)) - __nvme_tcp_stop_queue(&ctrl->queues[idx]); + if (test_bit(NVME_TCP_Q_ALLOCATED, &queue->flags)) + __nvme_tcp_stop_queue(queue); dev_err(nctrl->device, "failed to connect queue: %d ret=%d\n", idx, ret); }