From bb430b69422640891b0b8db762885730579a4145 Mon Sep 17 00:00:00 2001 From: Alyssa Ross Date: Mon, 20 Mar 2023 13:54:30 +0100 Subject: [PATCH 1/4] loop: LOOP_CONFIGURE: send uevents for partitions LOOP_CONFIGURE is, as far as I understand it, supposed to be a way to combine LOOP_SET_FD and LOOP_SET_STATUS64 into a single syscall. When using LOOP_SET_FD+LOOP_SET_STATUS64, a single uevent would be sent for each partition found on the loop device after the second ioctl(), but when using LOOP_CONFIGURE, no such uevent was being sent. In the old setup, uevents are disabled for LOOP_SET_FD, but not for LOOP_SET_STATUS64. This makes sense, as it prevents uevents being sent for a partially configured device during LOOP_SET_FD - they're only sent at the end of LOOP_SET_STATUS64. But for LOOP_CONFIGURE, uevents were disabled for the entire operation, so that final notification was never issued. To fix this, reduce the critical section to exclude the loop_reread_partitions() call, which causes the uevents to be issued, to after uevents are re-enabled, matching the behaviour of the LOOP_SET_FD+LOOP_SET_STATUS64 combination. I noticed this because Busybox's losetup program recently changed from using LOOP_SET_FD+LOOP_SET_STATUS64 to LOOP_CONFIGURE, and this broke my setup, for which I want a notification from the kernel any time a new partition becomes available. Signed-off-by: Alyssa Ross [hch: reduced the critical section] Signed-off-by: Christoph Hellwig Fixes: 3448914e8cc5 ("loop: Add LOOP_CONFIGURE ioctl") Link: https://lore.kernel.org/r/20230320125430.55367-1-hch@lst.de Signed-off-by: Jens Axboe --- drivers/block/loop.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 28eb59fd71ca..bc31bb7072a2 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1010,9 +1010,6 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); - /* suppress uevents while reconfiguring the device */ - dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1); - /* * If we don't hold exclusive handle for the device, upgrade to it * here to avoid changing device under exclusive owner. @@ -1067,6 +1064,9 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, } } + /* suppress uevents while reconfiguring the device */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1); + disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE); set_disk_ro(lo->lo_disk, (lo->lo_flags & LO_FLAGS_READ_ONLY) != 0); @@ -1109,17 +1109,17 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, if (partscan) clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state); + /* enable and uncork uevent now that we are done */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); + loop_global_unlock(lo, is_loop); if (partscan) loop_reread_partitions(lo); + if (!(mode & FMODE_EXCL)) bd_abort_claiming(bdev, loop_configure); - error = 0; -done: - /* enable and uncork uevent now that we are done */ - dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); - return error; + return 0; out_unlock: loop_global_unlock(lo, is_loop); @@ -1130,7 +1130,7 @@ out_putf: fput(file); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); - goto done; + return error; } static void __loop_clr_fd(struct loop_device *lo, bool release) From 1231363aec86704a6b0467a12e3ca7bdf890e01d Mon Sep 17 00:00:00 2001 From: Juraj Pecigos Date: Sun, 26 Mar 2023 11:29:49 +0200 Subject: [PATCH 2/4] 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 433279beba1d4872da10b7b60a539e0cb828b32b Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 28 Mar 2023 17:44:00 +0800 Subject: [PATCH 3/4] md: fix regression for null-ptr-deference in __md_stop() Commit 3e453522593d ("md: Free resources in __md_stop") tried to fix null-ptr-deference for 'active_io' by moving percpu_ref_exit() to __md_stop(), however, the commit also moving 'writes_pending' to __md_stop(), and this will cause mdadm tests broken: BUG: kernel NULL pointer dereference, address: 0000000000000038 Oops: 0000 [#1] PREEMPT SMP CPU: 15 PID: 17830 Comm: mdadm Not tainted 6.3.0-rc3-next-20230324-00009-g520d37 RIP: 0010:free_percpu+0x465/0x670 Call Trace: __percpu_ref_exit+0x48/0x70 percpu_ref_exit+0x1a/0x90 __md_stop+0xe9/0x170 do_md_stop+0x1e1/0x7b0 md_ioctl+0x90c/0x1aa0 blkdev_ioctl+0x19b/0x400 vfs_ioctl+0x20/0x50 __x64_sys_ioctl+0xba/0xe0 do_syscall_64+0x6c/0xe0 entry_SYSCALL_64_after_hwframe+0x63/0xcd And the problem can be reporduced 100% by following test: mdadm -CR /dev/md0 -l1 -n1 /dev/sda --force echo inactive > /sys/block/md0/md/array_state echo read-auto > /sys/block/md0/md/array_state echo inactive > /sys/block/md0/md/array_state Root cause: // start raid raid1_run mddev_init_writes_pending percpu_ref_init // inactive raid array_state_store do_md_stop __md_stop percpu_ref_exit // start raid again array_state_store do_md_run raid1_run mddev_init_writes_pending if (mddev->writes_pending.percpu_count_ptr) // won't reinit // inactive raid again ... percpu_ref_exit -> null-ptr-deference Before the commit, 'writes_pending' is exited when mddev is freed, and it's safe to restart raid because mddev_init_writes_pending() already make sure that 'writes_pending' will only be initialized once. Fix the prblem by moving 'writes_pending' back, it's a litter hard to find the relationship between alloc memory and free memory, however, code changes is much less and we lived with this for a long time already. Fixes: 3e453522593d ("md: Free resources in __md_stop") Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230328094400.1448955-1-yukuai1@huaweicloud.com --- drivers/md/md.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 39e49e5d7182..13321dbb5fbc 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6260,7 +6260,6 @@ static void __md_stop(struct mddev *mddev) module_put(pers->owner); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - percpu_ref_exit(&mddev->writes_pending); percpu_ref_exit(&mddev->active_io); bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); @@ -6273,6 +6272,7 @@ void md_stop(struct mddev *mddev) */ __md_stop_writes(mddev); __md_stop(mddev); + percpu_ref_exit(&mddev->writes_pending); } EXPORT_SYMBOL_GPL(md_stop); @@ -7843,6 +7843,7 @@ static void md_free_disk(struct gendisk *disk) { struct mddev *mddev = disk->private_data; + percpu_ref_exit(&mddev->writes_pending); mddev_free(mddev); } From 88eaba80328b31ef81813a1207b4056efd7006a6 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 20 Mar 2023 15:33:34 +0200 Subject: [PATCH 4/4] 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 @@ err_destroy_mutex: 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); }