nvme: fix subsystem multiple controllers support check

There is a problem when another module (e.g. nvmet) takes a reference on
the nvme block device and the physical nvme drive is removed.  In that
case nvme_free_ctrl() will not be called and the controller state will be
"deleting" or "dead" unless nvmet module releases the block device.
Later on, the same nvme drive probes back and nvme_init_subsystem() will
be called and fail due to duplicate subnqn (if the nvme device doesn't
support subsystem with multiple controllers). This will cause a probe
failure.  This commit changes the check of multiple controllers support
at nvme_init_subsystem() by not counting all the controllers at "dead" or
"deleting" state (this is safe because controllers at this state will
never be active again).

Fixes: ab9e00cc72fa ("nvme: track subsystems")
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c8bcfe64e976ef13e85f935cd9273e439c6498a5..2bcd49584f710bfde39193fc92367e55b879b710 100644 (file)
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2069,6 +2069,22 @@ static const struct attribute_group *nvme_subsys_attrs_groups[] = {
        NULL,
 };
 
+static int nvme_active_ctrls(struct nvme_subsystem *subsys)
+{
+       int count = 0;
+       struct nvme_ctrl *ctrl;
+
+       mutex_lock(&subsys->lock);
+       list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+               if (ctrl->state != NVME_CTRL_DELETING &&
+                   ctrl->state != NVME_CTRL_DEAD)
+                       count++;
+       }
+       mutex_unlock(&subsys->lock);
+
+       return count;
+}
+
 static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 {
        struct nvme_subsystem *subsys, *found;
@@ -2107,7 +2123,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
                 * Verify that the subsystem actually supports multiple
                 * controllers, else bail out.
                 */
-               if (!(id->cmic & (1 << 1))) {
+               if (nvme_active_ctrls(found) && !(id->cmic & (1 << 1))) {
                        dev_err(ctrl->device,
                                "ignoring ctrl due to duplicate subnqn (%s).\n",
                                found->subnqn);