aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorKeith Busch <keith.busch@intel.com>2019-01-23 18:46:11 -0700
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2019-03-13 14:02:38 -0700
commit3cc6703d43f98131fc74def7599bb6cc240b0814 (patch)
tree896826e613417b78e6cb6ee0d6eae6e5799a80da
parente3aabe4c24671aea9e242819b001ab9d2beb1fc7 (diff)
downloadlinux-yocto-3cc6703d43f98131fc74def7599bb6cc240b0814.tar.gz
linux-yocto-3cc6703d43f98131fc74def7599bb6cc240b0814.tar.bz2
linux-yocto-3cc6703d43f98131fc74def7599bb6cc240b0814.zip
nvme-pci: fix rapid add remove sequence
[ Upstream commit 5c959d73dba6495ec01d04c206ee679d61ccb2b0 ] A surprise removal may fail to tear down request queues if it is racing with the initial asynchronous probe. If that happens, the remove path won't see the queue resources to tear down, and the controller reset path may create a new request queue on a removed device, but will not be able to make forward progress, deadlocking the pci removal. Protect setting up non-blocking resources from a shutdown by holding the same mutex, and transition to the CONNECTING state after these resources are initialized so the probe path may see the dead controller state before dispatching new IO. Link: https://bugzilla.kernel.org/show_bug.cgi?id=202081 Reported-by: Alex Gagniuc <Alex_Gagniuc@Dellteam.com> Signed-off-by: Keith Busch <keith.busch@intel.com> Tested-by: Alex Gagniuc <mr.nuke.me@gmail.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Sasha Levin <sashal@kernel.org>
-rw-r--r--drivers/nvme/host/pci.c22
1 files changed, 12 insertions, 10 deletions
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index f46313f441ec..6398ffbce6de 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2260,16 +2260,7 @@ static void nvme_reset_work(struct work_struct *work)
if (dev->ctrl.ctrl_config & NVME_CC_ENABLE)
nvme_dev_disable(dev, false);
- /*
- * Introduce CONNECTING state from nvme-fc/rdma transports to mark the
- * initializing procedure here.
- */
- if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) {
- dev_warn(dev->ctrl.device,
- "failed to mark controller CONNECTING\n");
- goto out;
- }
-
+ mutex_lock(&dev->shutdown_lock);
result = nvme_pci_enable(dev);
if (result)
goto out;
@@ -2288,6 +2279,17 @@ static void nvme_reset_work(struct work_struct *work)
*/
dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1;
dev->ctrl.max_segments = NVME_MAX_SEGS;
+ mutex_unlock(&dev->shutdown_lock);
+
+ /*
+ * Introduce CONNECTING state from nvme-fc/rdma transports to mark the
+ * initializing procedure here.
+ */
+ if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) {
+ dev_warn(dev->ctrl.device,
+ "failed to mark controller CONNECTING\n");
+ goto out;
+ }
result = nvme_init_identify(&dev->ctrl);
if (result)