commit 733e4b69d508d03c20adfdcf4bd27abc60fae9cc upstream
The namespace disk names must be unique for the lifetime of the subsystem. This was accomplished by using their parent subsystems' instances which were allocated independently from the controllers connected to that subsystem. This allowed name prefixes assigned to namespaces to match a controller from an unrelated subsystem, and has created confusion among users examining device nodes.
Ensure a namespace's subsystem instance never clashes with a controller instance of another subsystem by transferring the instance ownership to the parent subsystem from the first controller discovered in that subsystem.
Reviewed-by: Logan Gunthorpe logang@deltatee.com Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Minwoo Im minwoo.im@samsung.com Reviewed-by: Hannes Reinecke hare@suse.com Reviewed-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Keith Busch kbusch@kernel.org Signed-off-by: Sagi Grimberg sagi@grimberg.me --- drivers/nvme/host/core.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index ae0b01059fc6..cab4f368ef2d 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -88,7 +88,6 @@ EXPORT_SYMBOL_GPL(nvme_reset_wq); struct workqueue_struct *nvme_delete_wq; EXPORT_SYMBOL_GPL(nvme_delete_wq);
-static DEFINE_IDA(nvme_subsystems_ida); static LIST_HEAD(nvme_subsystems); static DEFINE_MUTEX(nvme_subsystems_lock);
@@ -2139,7 +2138,8 @@ static void nvme_init_subnqn(struct nvme_subsystem *subsys, struct nvme_ctrl *ct
static void __nvme_release_subsystem(struct nvme_subsystem *subsys) { - ida_simple_remove(&nvme_subsystems_ida, subsys->instance); + if (subsys->instance >= 0) + ida_simple_remove(&nvme_instance_ida, subsys->instance); kfree(subsys); }
@@ -2255,12 +2255,8 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) subsys = kzalloc(sizeof(*subsys), GFP_KERNEL); if (!subsys) return -ENOMEM; - ret = ida_simple_get(&nvme_subsystems_ida, 0, 0, GFP_KERNEL); - if (ret < 0) { - kfree(subsys); - return ret; - } - subsys->instance = ret; + + subsys->instance = -1; mutex_init(&subsys->lock); kref_init(&subsys->ref); INIT_LIST_HEAD(&subsys->ctrls); @@ -2275,7 +2271,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) subsys->dev.class = nvme_subsys_class; subsys->dev.release = nvme_release_subsystem; subsys->dev.groups = nvme_subsys_attrs_groups; - dev_set_name(&subsys->dev, "nvme-subsys%d", subsys->instance); + dev_set_name(&subsys->dev, "nvme-subsys%d", ctrl->instance); device_initialize(&subsys->dev);
mutex_lock(&nvme_subsystems_lock); @@ -2308,6 +2304,8 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) list_add_tail(&subsys->entry, &nvme_subsystems); }
+ if (!found) + subsys->instance = ctrl->instance; ctrl->subsys = subsys; mutex_unlock(&nvme_subsystems_lock);
@@ -2319,7 +2317,6 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) return -EINVAL; }
- mutex_lock(&subsys->lock); list_add_tail(&ctrl->subsys_entry, &subsys->ctrls); mutex_unlock(&subsys->lock);
@@ -3545,7 +3542,9 @@ static void nvme_free_ctrl(struct device *dev) container_of(dev, struct nvme_ctrl, ctrl_device); struct nvme_subsystem *subsys = ctrl->subsys;
- ida_simple_remove(&nvme_instance_ida, ctrl->instance); + if (subsys && ctrl->instance != subsys->instance) + ida_simple_remove(&nvme_instance_ida, ctrl->instance); + kfree(ctrl->effects); nvme_mpath_uninit(ctrl);
@@ -3775,7 +3774,6 @@ int __init nvme_core_init(void)
void nvme_core_exit(void) { - ida_destroy(&nvme_subsystems_ida); class_destroy(nvme_subsys_class); class_destroy(nvme_class); unregister_chrdev_region(nvme_chr_devt, NVME_MINORS);
On Thu, Oct 10, 2019 at 01:29:10AM +0900, Keith Busch wrote:
commit 733e4b69d508d03c20adfdcf4bd27abc60fae9cc upstream
The namespace disk names must be unique for the lifetime of the subsystem. This was accomplished by using their parent subsystems' instances which were allocated independently from the controllers connected to that subsystem. This allowed name prefixes assigned to namespaces to match a controller from an unrelated subsystem, and has created confusion among users examining device nodes.
Ensure a namespace's subsystem instance never clashes with a controller instance of another subsystem by transferring the instance ownership to the parent subsystem from the first controller discovered in that subsystem.
Reviewed-by: Logan Gunthorpe logang@deltatee.com Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Minwoo Im minwoo.im@samsung.com Reviewed-by: Hannes Reinecke hare@suse.com Reviewed-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Keith Busch kbusch@kernel.org Signed-off-by: Sagi Grimberg sagi@grimberg.me
What are your thoughts about taking the following for 4.19 instead?
733e4b69d508d nvme: Assign subsys instance from first ctrl e654dfd38c1ec nvme: fix memory leak caused by incorrect subsystem free 32fd90c407680 nvme: change locking for the per-subsystem controller list 092ff0520070f nvme: fix kernel paging oops cb5b7262b011c nvme: provide fallback for discard alloc failure
-- Thanks, Sasha
On Wed, Oct 09, 2019 at 05:55:04PM -0400, Sasha Levin wrote:
On Thu, Oct 10, 2019 at 01:29:10AM +0900, Keith Busch wrote:
commit 733e4b69d508d03c20adfdcf4bd27abc60fae9cc upstream
The namespace disk names must be unique for the lifetime of the subsystem. This was accomplished by using their parent subsystems' instances which were allocated independently from the controllers connected to that subsystem. This allowed name prefixes assigned to namespaces to match a controller from an unrelated subsystem, and has created confusion among users examining device nodes.
Ensure a namespace's subsystem instance never clashes with a controller instance of another subsystem by transferring the instance ownership to the parent subsystem from the first controller discovered in that subsystem.
Reviewed-by: Logan Gunthorpe logang@deltatee.com Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Minwoo Im minwoo.im@samsung.com Reviewed-by: Hannes Reinecke hare@suse.com Reviewed-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Keith Busch kbusch@kernel.org Signed-off-by: Sagi Grimberg sagi@grimberg.me
What are your thoughts about taking the following for 4.19 instead?
733e4b69d508d nvme: Assign subsys instance from first ctrl e654dfd38c1ec nvme: fix memory leak caused by incorrect subsystem free 32fd90c407680 nvme: change locking for the per-subsystem controller list 092ff0520070f nvme: fix kernel paging oops cb5b7262b011c nvme: provide fallback for discard alloc failure
Thank you for the suggestion. I have reviewed the proposed sequence, and I would prefer to use this for stable instead of this back-ported patch.
-- Thanks, Sasha
linux-stable-mirror@lists.linaro.org