linux-stable.git/drivers/nvme, branch linux-4.8.y

nvmet: Fix possible infinite loop triggered on hot namespace removal

2017-01-06T10:16:23+00:00

commit e4fcf07cca6a3b6c4be00df16f08be894325eaa3 upstream.

When removing a namespace we delete it from the subsystem namespaces
list with list_del_init which allows us to know if it is enabled or
not.

The problem is that list_del_init initialize the list next and does
not respect the RCU list-traversal we do on the IO path for locating
a namespace. Instead we need to use list_del_rcu which is allowed to
run concurrently with the _rcu list-traversal primitives (keeps list
next intact) and guarantees concurrent nvmet_find_naespace forward
progress.

By changing that, we cannot rely on ns->dev_link for knowing if the
namspace is enabled, so add enabled indicator entry to nvmet_ns for
that.

Signed-off-by: Sagi Grimberg 
Signed-off-by: Solganik Alexander 
Signed-off-by: Greg Kroah-Hartman

nvme: Delete created IO queues on reset

2016-11-18T09:51:50+00:00

commit 7065906096273b39b90a512a7170a6697ed94b23 upstream.

The driver was decrementing the online_queues prior to attempting to
delete those IO queues, so the driver ended up not requesting the
controller delete any. This patch saves the online_queues prior to
suspending them, and adds that parameter for deleting io queues.

Fixes: c21377f8 ("nvme: Suspend all queues before deletion")
Signed-off-by: Keith Busch 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Jens Axboe 
Signed-off-by: Greg Kroah-Hartman

nvme-rdma: only clear queue flags after successful connect

2016-09-23T01:58:17+00:00

Otherwise, nvme_rdma_stop_and_clear_queue() will incorrectly
try to stop/free rdma qps/cm_ids that are already freed.

Fixes: e89ca58f9c90 ("nvme-rdma: add DELETING queue flag")
Reported-by: Steve Wise 
Tested-by: Steve Wise 
Signed-off-by: Sagi Grimberg 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Jens Axboe

Merge branch 'for-linus' of git://git.kernel.dk/linux-block

2016-09-15T20:22:59+00:00

Pull block fixes from Jens Axboe:
 "A set of fixes for the current series in the realm of block.

  Like the previous pull request, the meat of it are fixes for the nvme
  fabrics/target code.  Outside of that, just one fix from Gabriel for
  not doing a queue suspend if we didn't get the admin queue setup in
  the first place"

* 'for-linus' of git://git.kernel.dk/linux-block:
  nvme-rdma: add back dependency on CONFIG_BLOCK
  nvme-rdma: fix null pointer dereference on req->mr
  nvme-rdma: use ib_client API to detect device removal
  nvme-rdma: add DELETING queue flag
  nvme/quirk: Add a delay before checking device ready for memblaze device
  nvme: Don't suspend admin queue that wasn't created
  nvme-rdma: destroy nvme queue rdma resources on connect failure
  nvme_rdma: keep a ref on the ctrl during delete/flush
  iw_cxgb4: block module unload until all ep resources are released
  iw_cxgb4: call dev_put() on l2t allocation failure

Merge branch 'nvmf-4.8-rc' of git://git.infradead.org/nvme-fabrics into for-linus

2016-09-13T13:58:34+00:00

Sagi writes:

Here we have:
- Kconfig dependencies fix from Arnd
- nvme-rdma device removal fixes from Steve
- possible bad deref fix from Colin

nvme-rdma: add back dependency on CONFIG_BLOCK

2016-09-12T19:29:43+00:00

A recent change removed the dependency on BLK_DEV_NVME, which implies
the dependency on PCI and BLOCK. We don't need CONFIG_PCI, but without
CONFIG_BLOCK we get tons of build errors, e.g.

In file included from drivers/nvme/host/core.c:16:0:
linux/blk-mq.h:182:33: error: 'struct gendisk' declared inside parameter list will not be visible outside of this definition or declaration [-Werror]
drivers/nvme/host/core.c: In function 'nvme_setup_rw':
drivers/nvme/host/core.c:295:21: error: implicit declaration of function 'rq_data_dir' [-Werror=implicit-function-declaration]
drivers/nvme/host/nvme.h: In function 'nvme_map_len':
drivers/nvme/host/nvme.h:217:6: error: implicit declaration of function 'req_op' [-Werror=implicit-function-declaration]
drivers/nvme/host/scsi.c: In function 'nvme_trans_bdev_limits_page':
drivers/nvme/host/scsi.c:768:85: error: implicit declaration of function 'queue_max_hw_sectors' [-Werror=implicit-function-declaration]

This adds back the specific CONFIG_BLOCK dependency to avoid broken
configurations.

Signed-off-by: Arnd Bergmann 
Fixes: aa71987472a9 ("nvme: fabrics drivers don't need the nvme-pci driver")
Signed-off-by: Sagi Grimberg

nvme-rdma: fix null pointer dereference on req->mr

2016-09-12T19:29:42+00:00

If there is an error on req->mr, req->mr is set to null, however
the following statement sets req->mr->need_inval causing a null
pointer dereference.  Fix this by bailing out to label 'out' to
immediately return and hence skip over the offending null pointer
dereference.

Fixes: f5b7b559e1488 ("nvme-rdma: Get rid of duplicate variable")
Signed-off-by: Colin Ian King 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Sagi Grimberg

nvme-rdma: use ib_client API to detect device removal

2016-09-12T19:29:41+00:00

Change nvme-rdma to use the IB Client API to detect device removal.
This has the wonderful benefit of being able to blow away all the
ib/rdma_cm resources for the device being removed.  No craziness about
not destroying the cm_id handling the event.  No deadlocks due to broken
iw_cm/rdma_cm/iwarp dependencies.  And no need to have a bound cm_id
around during controller recovery/reconnect to catch device removal
events.

We don't use the device_add aspect of the ib_client service since we only
want to create resources for an IB device if we have a target utilizing
that device.

Reviewed-by: Christoph Hellwig 
Signed-off-by: Steve Wise 
Signed-off-by: Sagi Grimberg

nvme-rdma: add DELETING queue flag

2016-09-12T19:29:34+00:00

When we get a surprise disconnect from the target we queue a periodic
reconnect (which is the sane thing to do...).

We only move the queues out of CONNECTED when we retry to reconnect (after
10 seconds in the default case) but we stop the blk queues immediately
so we are not bothered with traffic from now on. If delete() is kicking
off in this period the queues are still in CONNECTED state.

Part of the delete sequence is trying to issue ctrl shutdown if the
admin queue is CONNECTED (which it is!). This request is issued but
stuck in blk-mq waiting for the queues to start again. This might be
the one preventing us from forward progress...

The patch separates the queue flags to CONNECTED and DELETING. Now we
will move out of CONNECTED as soon as error recovery kicks in (before
stopping the queues) and DELETING is on when we start the queue deletion.

Signed-off-by: Sagi Grimberg

nvme: make NVME_RDMA depend on BLOCK

2016-09-11T21:41:49+00:00

Commit aa71987472a9 ("nvme: fabrics drivers don't need the nvme-pci
driver") removed the dependency on BLK_DEV_NVME, but the cdoe does
depend on the block layer (which used to be an implicit dependency
through BLK_DEV_NVME).

Otherwise you get various errors from the kbuild test robot random
config testing when that happens to hit a configuration with BLOCK
device support disabled.

Cc: Christoph Hellwig 
Cc: Jay Freyensee 
Cc: Sagi Grimberg 
Signed-off-by: Linus Torvalds