This adds rcu protected access to nvme_queue to fix a race between a
surprise removal freeing the queue and a thread with open reference on
a NVMe block device using that queue.
The queues do not need to be rcu protected during the initialization or
shutdown parts, so I've added a helper function for raw deferencing
to get around the sparse errors.
There is still a hole in the IOCTL path for the same problem, which is
fixed in a subsequent patch.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
If an NVMe device becomes ready but fails to create IO queues, the driver
creates a character device handle so the device can be managed. The
device reference count needs to be initialized before creating the
character device.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Add CONFIG_PM_SLEEP to suspend/resume functions to fix the following
build warning when CONFIG_PM_SLEEP is not selected. This is because
sleep PM callbacks defined by SIMPLE_DEV_PM_OPS are only used when
the CONFIG_PM_SLEEP is enabled.
drivers/block/nvme-core.c:2541:12: warning: 'nvme_suspend' defined but not used [-Wunused-function]
drivers/block/nvme-core.c:2550:12: warning: 'nvme_resume' defined but not used [-Wunused-function]
Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Pull NVMe driver update from Matthew Wilcox:
"Looks like I missed the merge window ... but these are almost all
bugfixes anyway (the ones that aren't have been baking for months)"
* git://git.infradead.org/users/willy/linux-nvme:
NVMe: Namespace use after free on surprise removal
NVMe: Correct uses of INIT_WORK
NVMe: Include device and queue numbers in interrupt name
NVMe: Add a pci_driver shutdown method
NVMe: Disable admin queue on init failure
NVMe: Dynamically allocate partition numbers
NVMe: Async IO queue deletion
NVMe: Surprise removal handling
NVMe: Abort timed out commands
NVMe: Schedule reset for failed controllers
NVMe: Device resume error handling
NVMe: Cache dev->pci_dev in a local pointer
NVMe: Fix lockdep warnings
NVMe: compat SG_IO ioctl
NVMe: remove deprecated IRQF_DISABLED
NVMe: Avoid shift operation when writing cq head doorbell
An nvme block device may have open references when the device is
removed. New commands may still be sent on the removed device, so we
need to ref count the opens, return errors for new commands, and not
free the namespace and nvme_dev until all references are closed.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
We need to initialise the work_struct when we initialise the rest of the
struct nvme_dev, otherwise we'll hit a lockdep warning when we remove
the device. Use PREPARE_WORK to change the function pointer instead
of INIT_WORK.
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
On larger systems with many drives, it may help debugging to know which
queue is tied to which interrupt, just by looking at /proc/interrupts.
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
We need to shut down the device cleanly when the system is being shut down.
This was in an earlier patch but was inadvertently lost during a rewrite.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Disable the admin queue if device fails during initialization so the
queue's irq is freed.
Signed-off-by: Keith Busch <keith.busch@intel.com>
[rewritten to use nvme_free_queues]
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Some users need more than 64 partitions per device. Rather than simply
increasing the number of partitions, switch to the dynamic partition
allocation scheme.
This means that minor numbers are not stable across boots, but since major
numbers aren't either, I cannot see this being a significant problem.
Tested-by: Matias Bjørling <m@bjorling.me>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
This attempts to delete all IO queues at the same time asynchronously on
shutdown. This is necessary for a present device that is not responding;
a shutdown operation previously would take 2 minutes per queue-pair
to timeout before moving on to the next queue, making a device removal
appear to take a very long time or "hung" as reported by users.
In the previous worst case, a removal may be stuck forever until a kill
signal is given if there are more than 32 queue pairs since it would run
out of admin command IDs after over an hour of timed out sync commands
(admin queue depth is 64).
This patch will wait for the admin command timeout for all commands to
complete, so the worst case now for an unresponsive controller is 60
seconds, though that still seems like a long time.
Since this adds another way to take queues offline, some duplicate code
resulted so I moved these into more convienient functions.
Signed-off-by: Keith Busch <keith.busch@intel.com>
[make functions static, correct line length and whitespace issues]
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
This adds checks to see if the nvme pci device was removed. The check
reads the status register for the value of -1, which it should never be
unless the device is no longer present.
If a user performs a surprise removal on an nvme device, the driver will
be notified either by the pci driver remove callback if the platform's
slot is capable of this event, or via reading the device BAR status
register, which will indicate controller failure and trigger a reset.
Either way, the device is not present so all outstanding commands would
timeout. This will not send queue deletion commands to a drive that
isn't present and fail after ioremap, significantly speeding up surprise
removal; previously this took over 2 minutes per IO queue pair created,
but this will complete removing the device within a few seconds.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Send nvme abort command to io requests that have timed out on an
initialized device. If the command is not returned after another timeout,
schedule the controller for reset.
Signed-off-by: Keith Busch <keith.busch@intel.com>
[fix endianness issues]
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Schedules a controller reset when it indicates it has a failed status. If
the device does not become ready after a reset, the pci device will be
scheduled for removal.
Signed-off-by: Keith Busch <keith.busch@intel.com>
[fixed checkpatch issue]
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Adds controller error handling on resume power management. If the device
fails to initialize, the device is queued for a reset. If the reset fails,
a thread is spawned to remove the pci device.
If the device resumes as "busy", the device is responding to admin
commands but will not create IO queues. In this case, we need to remove
the gendisks and free the IO queues since they can't be used and may be
holding bios in their lists.
From testing, the dma pools require a pci device so this had to change
the pci driver 'remove' to release the dma resources in line with that
call instead of after all references to the device are released.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
During the initialisation path, the queue lock is taken without interrupt
protection. It's perfectly safe to do so, because the interrupt handler
can't run at this point, but it confuses lockdep.
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
For 32-bit versions of sg3-utils running on a 64-bit system. This is
mostly a copy from the relevent portions of fs/compat_ioctl.c, with
slight modifications for going through block_device_operations.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Vishal Verma <vishal.l.verma@linux.intel.com>
[fixed up CONFIG_COMPAT=n build problems]
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
The new bio_split() can split arbitrary bios - it's not restricted to
single page bios, like the old bio_split() (previously renamed to
bio_pair_split()). It also has different semantics - it doesn't allocate
a struct bio_pair, leaving it up to the caller to handle completions.
Then convert the existing bio_pair_split() users to the new bio_split()
- and also nvme, which was open coding bio splitting.
(We have to take that BUG_ON() out of bio_integrity_trim() because this
bio_split() needs to use it, and there's no reason it has to be used on
bios marked as cloned; BIO_CLONED doesn't seem to have clearly
documented semantics anyways.)
Signed-off-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Neil Brown <neilb@suse.de>
More prep work for immutable biovecs - with immutable bvecs drivers
won't be able to use the biovec directly, they'll need to use helpers
that take into account bio->bi_iter.bi_bvec_done.
This updates callers for the new usage without changing the
implementation yet.
Signed-off-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Ed L. Cashin" <ecashin@coraid.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Paul Clements <Paul.Clements@steeleye.com>
Cc: Jim Paris <jim@jtan.com>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Yehuda Sadeh <yehuda@inktank.com>
Cc: Sage Weil <sage@inktank.com>
Cc: Alex Elder <elder@inktank.com>
Cc: ceph-devel@vger.kernel.org
Cc: Joshua Morris <josh.h.morris@us.ibm.com>
Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Neil Brown <neilb@suse.de>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: linux390@de.ibm.com
Cc: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com>
Cc: Sreekanth Reddy <Sreekanth.Reddy@lsi.com>
Cc: support@lsi.com
Cc: "James E.J. Bottomley" <JBottomley@parallels.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Guo Chao <yan@linux.vnet.ibm.com>
Cc: Asai Thambi S P <asamymuthupa@micron.com>
Cc: Selvan Mani <smani@micron.com>
Cc: Sam Bradshaw <sbradshaw@micron.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: Quoc-Son Anh <quoc-sonx.anh@intel.com>
Cc: Sebastian Ott <sebott@linux.vnet.ibm.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: "Darrick J. Wong" <darrick.wong@oracle.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Jan Kara <jack@suse.cz>
Cc: linux-m68k@lists.linux-m68k.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: drbd-user@lists.linbit.com
Cc: nbd-general@lists.sourceforge.net
Cc: cbe-oss-dev@lists.ozlabs.org
Cc: xen-devel@lists.xensource.com
Cc: virtualization@lists.linux-foundation.org
Cc: linux-raid@vger.kernel.org
Cc: linux-s390@vger.kernel.org
Cc: DL-MPTFusionLinux@lsi.com
Cc: linux-scsi@vger.kernel.org
Cc: devel@driverdev.osuosl.org
Cc: linux-fsdevel@vger.kernel.org
Cc: cluster-devel@redhat.com
Cc: linux-mm@kvack.org
Acked-by: Geoff Levand <geoff@infradead.org>
This patch proposes to remove the use of the IRQF_DISABLED flag
It's a NOOP since 2.6.35 and it will be removed one day.
Signed-off-by: Michael Opdenacker <michael.opdenacker@free-electrons.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Changes the type of dev->db_stride to unsigned and changes the value
stored there to be 1 << the current value. Then there is less
calculation to be done at completion time.
Signed-off-by: Haiyan Hu <huhaiyan@huawei.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Replace the following sequence:
dma_set_mask(dev, mask);
dma_set_coherent_mask(dev, mask);
with a call to the new helper dma_set_mask_and_coherent().
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
A recent patch made it possible to bring up the character handle when the
device is responsive but not accepting a set-features command. Another
recent patch moved the initialization that requires we move where the
checks for this condition occur. This patch merges these two ideas so
it works much as before.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Decrement the number of queues required for doorbell remapping until
the memory is successfully mapped for that size.
Additional checks are done so that we don't call free_irq if it has
already been freed.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Used for going in and out of low power states. Resuming reuses the IO
queues from the previous initialization, freeing any allocated queues
that are no longer usable.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
The NVMe spec recommends using the shutdown normal sequence when safely
taking the controller offline instead of hitting CC.EN on the next
start-up to reset the controller. The spec recommends a minimum of 1
second for the shutdown complete. This patch waits 2 seconds to be on
the safe side.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
This combines the controller initialization into one function, removing
IO queue setup from namespace discovery, and creates symetric functions
for device removal. The controller start and shutdown functions can now
be called from resume/suspend context as well as probe/remove.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
This separates nvme queue allocation from creation, and queue deletion
from freeing. This is so that we may in the future temporarily disable
queues and reuse the same memory when bringing them back online, like
coming back from suspend state.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
This will make it easier to reuse these outside probe/remove.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Flush and discard requests would previously mess up the accounting.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
This patch creates the character device as long as a device's admin queues
are usable so a user has an opprotunity to perform administration tasks.
A device may be in a state that does not allow IO and setting the queue
count feature in such a state returns an error. Previously the driver
would bail and the controller would be unusable.
Signed-off-by: Keith Busch <keith.busch@intel.com>
The 'Number of Namespaces' read from the device was being treated as
signed, which would cause us to not scan any namespaces for a device
with more than 2 billion namespaces. That led to noticing that the
namespace ID was also being treated as signed, which could lead to the
result from NVME_IOCTL_ID being treated as an error code.
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Since we have the queue locked, it makes sense to check if there are
any completion queue entries on the queue before we release the lock.
If there are, it may save an interrupt and reduce latency for the I/Os
that happened to complete. This happens fairly often for some workloads.
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
I was originally intending to log the fact that the kthread had done
some work since it might help us find interrupt handling problems, but
that hasn't been done yet, and spamming the logs with this message is
just rude.
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
The interrupt handler currently reports whether it found any new
completion queue entries. If the completion queue is primarily being
processed by a method other than the interrupt handler, it may return
IRQ_NONE so often that Linux thinks that the interrupt is being falsely
triggered.
To solve this problem, report whether any completion queue entries have
been seen since the last interrupt was received for this queue.
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Add io stats accounting for bio requests so nvme block devices show
useful disk stats.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
The current code copies 'nr_io_queues' into 'q_count', modifies
'nr_io_queues' during MSI-X setup, then resets 'nr_io_queues' for
MSI setup. Instead, copy 'nr_io_queues' into 'vecs' and modify 'vecs'
during both MSI-X and MSI setup.
This lets us simplify the for-loops that set up MSI-X and MSI, and opens
the possibility of using more I/O queues than we have interrupt vectors,
should future benchmarking prove that to be a useful feature.
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Some devices only have support for MSI, not MSI-X. While MSI is more
limited, it still provides better performance than line-based interrupts.
Signed-off-by: Ramachandra Gajula <rama@fastorsystems.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
In some circumstances setting a 64-bit DMA mask can fail, as explained
in Documentation/DMA-API-HOWTO.txt. Use the recommended code sequence
to set a 32-bit DMA mask if setting a 64-bit DMA mask fails.
Reported-by: Chayan Biswas <Chayan.Biswas@sandisk.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
We copy the result to user if the command is completed from the
controller even if it completes with failure (non-zero) status.
A return status of < 0 indicates the command was not completed
by the controller. The user application may expect the error code
in the result field in case of failure.
Signed-off-by: Chayan Biswas <Chayan.Biswas@sandisk.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cancelling an already cancelled command does not do anything, so check
the command context before cancelling it, continuing if had already been
cancelled so we do not log the same problem every second if a device
stops responding.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
nvme_submit_flush_data() might overwrite the initialisation of the
return value with 0, so move the -ENOMEM setting close to the usage.
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
You need to have CAP_SYS_ADMIN to trigger this overflow but it makes the
static checkers complain so we should fix it. The worry is that
"length" comes from copy_from_user() so we need to check that "length +
offset" can't overflow.
I also changed the min_t() cast to be unsigned instead of signed. Now
that we cap "length" to INT_MAX it doesn't make a difference, but it's a
little easier for reviewers to know that large values aren't cast to
negative.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Many of the bits in the Controller Configuration register may only be
modified when the Enable bit is clear. Clearing them at the same time
as the Enable bit might be OK, but let's play it safe and only touch the
Enable bit.
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Reviewed-by: Keith Busch <keith.busch@intel.com>
A recent update to the specification makes it clear that the host
is expected to wait for the device to acknowledge the Enable bit
transitioning to 0 as well as waiting for the device to acknowledge a
transition to 1.
Reported-by: Khosrow Panah <Khosrow.Panah@idt.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Schedule a timeout on sync commands in case the command times out and
the device is not being polled for timeouts. This prevents device removal
from hanging forever if the device has stopped responding.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Keith Busch