nvme-pci: fix multiple ctrl removal scheduling

Commit c5f6ce97c1210 tries to address multiple resets but fails as
work_busy doesn't involve any synchronization and can fail.  This is
reproducible easily as can be seen by WARNING below which is triggered
with line:

WARN_ON(dev->ctrl.state == NVME_CTRL_RESETTING)

Allowing multiple resets can result in multiple controller removal as
well if different conditions inside nvme_reset_work fail and which
might deadlock on device_release_driver.

[  480.327007] WARNING: CPU: 3 PID: 150 at drivers/nvme/host/pci.c:1900 nvme_reset_work+0x36c/0xec0
[  480.327008] Modules linked in: rfcomm fuse nf_conntrack_netbios_ns nf_conntrack_broadcast...
[  480.327044]  btusb videobuf2_core ghash_clmulni_intel snd_hwdep cfg80211 acer_wmi hci_uart..
[  480.327065] CPU: 3 PID: 150 Comm: kworker/u16:2 Not tainted 4.12.0-rc1+ #13
[  480.327065] Hardware name: Acer Predator G9-591/Mustang_SLS, BIOS V1.10 03/03/2016
[  480.327066] Workqueue: nvme nvme_reset_work
[  480.327067] task: ffff880498ad8000 task.stack: ffffc90002218000
[  480.327068] RIP: 0010:nvme_reset_work+0x36c/0xec0
[  480.327069] RSP: 0018:ffffc9000221bdb8 EFLAGS: 00010246
[  480.327070] RAX: 0000000000460000 RBX: ffff880498a98128 RCX: dead000000000200
[  480.327070] RDX: 0000000000000001 RSI: ffff8804b1028020 RDI: ffff880498a98128
[  480.327071] RBP: ffffc9000221be50 R08: 0000000000000000 R09: 0000000000000000
[  480.327071] R10: ffffc90001963ce8 R11: 000000000000020d R12: ffff880498a98000
[  480.327072] R13: ffff880498a53500 R14: ffff880498a98130 R15: ffff880498a98128
[  480.327072] FS:  0000000000000000(0000) GS:ffff8804c1cc0000(0000) knlGS:0000000000000000
[  480.327073] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  480.327074] CR2: 00007ffcf3c37f78 CR3: 0000000001e09000 CR4: 00000000003406e0
[  480.327074] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  480.327075] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  480.327075] Call Trace:
[  480.327079]  ? __switch_to+0x227/0x400
[  480.327081]  process_one_work+0x18c/0x3a0
[  480.327082]  worker_thread+0x4e/0x3b0
[  480.327084]  kthread+0x109/0x140
[  480.327085]  ? process_one_work+0x3a0/0x3a0
[  480.327087]  ? kthread_park+0x60/0x60
[  480.327102]  ret_from_fork+0x2c/0x40
[  480.327103] Code: e8 5a dc ff ff 85 c0 41 89 c1 0f.....

This patch addresses the problem by using state of controller to
decide whether reset should be queued or not as state change is
synchronizated using controller spinlock.  Also cancel_work_sync is
used to make sure remove cancels the reset_work and waits for it to
finish.  This patch also changes return value from -ENODEV to more
appropriate -EBUSY if nvme_reset fails to change state.

Fixes: c5f6ce97c1210 ("nvme: don't schedule multiple resets")
Signed-off-by: Rakesh Pandit <rakesh@tuxera.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>

1 files changed, 6 insertions, 7 deletions

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index d52701df7245..951042a375d6 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1367,7 +1367,7 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
 	bool nssro = dev->subsystem && (csts & NVME_CSTS_NSSRO);
 
 	/* If there is a reset ongoing, we shouldn't reset again. */
-	if (work_busy(&dev->reset_work))
+	if (dev->ctrl.state == NVME_CTRL_RESETTING)
 		return false;
 
 	/* We shouldn't reset unless the controller is on fatal error state
@@ -1903,7 +1903,7 @@ static void nvme_reset_work(struct work_struct *work)
 	bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
 	int result = -ENODEV;
 
-	if (WARN_ON(dev->ctrl.state == NVME_CTRL_RESETTING))
+	if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING))
 		goto out;
 
 	/*
@@ -1913,9 +1913,6 @@ static void nvme_reset_work(struct work_struct *work)
 	if (dev->ctrl.ctrl_config & NVME_CC_ENABLE)
 		nvme_dev_disable(dev, false);
 
-	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING))
-		goto out;
-
 	result = nvme_pci_enable(dev);
 	if (result)
 		goto out;
@@ -2009,8 +2006,8 @@ static int nvme_reset(struct nvme_dev *dev)
 {
 	if (!dev->ctrl.admin_q || blk_queue_dying(dev->ctrl.admin_q))
 		return -ENODEV;
-	if (work_busy(&dev->reset_work))
-		return -ENODEV;
+	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING))
+		return -EBUSY;
 	if (!queue_work(nvme_workq, &dev->reset_work))
 		return -EBUSY;
 	return 0;
@@ -2136,6 +2133,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (result)
 		goto release_pools;
 
+	nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING);
 	dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
 
 	queue_work(nvme_workq, &dev->reset_work);
@@ -2179,6 +2177,7 @@ static void nvme_remove(struct pci_dev *pdev)
 
 	nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
 
+	cancel_work_sync(&dev->reset_work);
 	pci_set_drvdata(pdev, NULL);
 
 	if (!pci_device_is_present(pdev)) {