summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Merge branch 'for-3.19/drivers' of git://git.kernel.dk/linux-blockLinus Torvalds2014-12-1320-1199/+1009
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull block layer driver updates from Jens Axboe: - NVMe updates: - The blk-mq conversion from Matias (and others) - A stack of NVMe bug fixes from the nvme tree, mostly from Keith. - Various bug fixes from me, fixing issues in both the blk-mq conversion and generic bugs. - Abort and CPU online fix from Sam. - Hot add/remove fix from Indraneel. - A couple of drbd fixes from the drbd team (Andreas, Lars, Philipp) - With the generic IO stat accounting from 3.19/core, converting md, bcache, and rsxx to use those. From Gu Zheng. - Boundary check for queue/irq mode for null_blk from Matias. Fixes cases where invalid values could be given, causing the device to hang. - The xen blkfront pull request, with two bug fixes from Vitaly. * 'for-3.19/drivers' of git://git.kernel.dk/linux-block: (56 commits) NVMe: fix race condition in nvme_submit_sync_cmd() NVMe: fix retry/error logic in nvme_queue_rq() NVMe: Fix FS mount issue (hot-remove followed by hot-add) NVMe: fix error return checking from blk_mq_alloc_request() NVMe: fix freeing of wrong request in abort path xen/blkfront: remove redundant flush_op xen/blkfront: improve protection against issuing unsupported REQ_FUA NVMe: Fix command setup on IO retry null_blk: boundary check queue_mode and irqmode block/rsxx: use generic io stats accounting functions to simplify io stat accounting md: use generic io stats accounting functions to simplify io stat accounting drbd: use generic io stats accounting functions to simplify io stat accounting md/bcache: use generic io stats accounting functions to simplify io stat accounting NVMe: Update module version major number NVMe: fail pci initialization if the device doesn't have any BARs NVMe: add ->exit_hctx() hook NVMe: make setup work for devices that don't do INTx NVMe: enable IO stats by default NVMe: nvme_submit_async_admin_req() must use atomic rq allocation NVMe: replace blk_put_request() with blk_mq_free_request() ...
| * NVMe: fix race condition in nvme_submit_sync_cmd()Jens Axboe2014-12-121-4/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If we have a race between the schedule timing out and the command completing, we could have the task issuing the command exit nvme_submit_sync_cmd() while the irq is running sync_completion(). If that happens, we could be corrupting memory, since the stack that held 'cmdinfo' is no longer valid. Fix this by always calling nvme_abort_cmd_info(). Once that call completes, we know that we have either run sync_completion() if the completion came in, or that we will never run it since we now have special_completion() as the command callback handler. Acked-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * NVMe: fix retry/error logic in nvme_queue_rq()Jens Axboe2014-12-111-23/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The logic around retrying and erroring IO in nvme_queue_rq() is broken in a few ways: - If we fail allocating dma memory for a discard, we return retry. We have the 'iod' stored in ->special, but we free the 'iod'. - For a normal request, if we fail dma mapping of setting up prps, we have the same iod situation. Additionally, we haven't set the callback for the request yet, so we also potentially leak IOMMU resources. Get rid of the ->special 'iod' store. The retry is uncommon enough that it's not worth optimizing for or holding on to resources to attempt to speed it up. Additionally, it's usually best practice to free any request related resources when doing retries. Acked-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * NVMe: Fix FS mount issue (hot-remove followed by hot-add)Indraneel M2014-12-111-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | After Hot-remove of a device with a mounted partition, when the device is hot-added again, the new node reappears as nvme0n1. Mounting this new node fails with the error: mount: mount /dev/nvme0n1p1 on /mnt failed: File exists. The old nodes's FS entries still exist and the kernel can't re-create procfs and sysfs entries for the new node with the same name. The patch fixes this issue. Acked-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Indraneel M <indraneel.m@samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * Merge branch 'for-jens-3.19' of ↵Jens Axboe2014-12-101-26/+39
| |\ | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen into for-3.19/drivers Konrad writes: These are two fixes for Xen blkfront. They harden how it deals with broken backends.
| | * xen/blkfront: remove redundant flush_opVitaly Kuznetsov2014-12-101-20/+31
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | flush_op is unambiguously defined by feature_flush: REQ_FUA | REQ_FLUSH -> BLKIF_OP_WRITE_BARRIER REQ_FLUSH -> BLKIF_OP_FLUSH_DISKCACHE 0 -> 0 and thus can be removed. This is just a cleanup. The patch was suggested by Boris Ostrovsky. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
| | * xen/blkfront: improve protection against issuing unsupported REQ_FUAVitaly Kuznetsov2014-12-101-6/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Guard against issuing unsupported REQ_FUA and REQ_FLUSH was introduced in d11e61583 and was factored out into blkif_request_flush_valid() in 0f1ca65ee. However: 1) This check in incomplete. In case we negotiated to feature_flush = REQ_FLUSH and flush_op = BLKIF_OP_FLUSH_DISKCACHE (so FUA is unsupported) FUA request will still pass the check. 2) blkif_request_flush_valid() is misnamed. It is bool but returns true when the request is invalid. 3) When blkif_request_flush_valid() fails -EIO is being returned. It seems that -EOPNOTSUPP is more appropriate here. Fix all of the above issues. This patch is based on the original patch by Laszlo Ersek and a comment by Jeff Moyer. Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Reviewed-by: Laszlo Ersek <lersek@redhat.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
| * | NVMe: fix error return checking from blk_mq_alloc_request()Jens Axboe2014-12-101-6/+6
| | | | | | | | | | | | | | | | | | | | | We return an error pointer or the request, not NULL. Half the call paths got it right, the others didn't. Fix those up. Signed-off-by: Jens Axboe <axboe@fb.com>
| * | NVMe: fix freeing of wrong request in abort pathSam Bradshaw2014-12-101-1/+1
| |/ | | | | | | | | | | | | | | We allocate 'abort_req', but free 'req' in case of an error submitting the IO. Signed-off-by: Sam Bradshaw <sbradshaw@micron.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * NVMe: Fix command setup on IO retryKeith Busch2014-12-031-2/+1
| | | | | | | | | | | | | | | | | | On retry, the req->special is pointing to an already setup IOD, but we still need to setup the command context and callback, otherwise you'll see false twice completed errors and leak requests. Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * null_blk: boundary check queue_mode and irqmodeMatias Bjorling2014-11-261-2/+40
| | | | | | | | | | | | | | | | | | | | | | | | | | When either queue_mode or irq_mode parameter is set outside its boundaries, the driver will not complete requests. This stalls driver initialization when partitions are probed. Fix by setting out of bound values to the parameters default. Signed-off-by: Matias Bjørling <m@bjorling.me> Updated by me to have the parse+check in just one function. Signed-off-by: Jens Axboe <axboe@fb.com>
| * block/rsxx: use generic io stats accounting functions to simplify io stat ↵Gu Zheng2014-11-241-25/+4
| | | | | | | | | | | | | | | | | | | | accounting Use generic io stats accounting help functions (generic_{start,end}_io_acct) to simplify io stat accounting. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * md: use generic io stats accounting functions to simplify io stat accountingGu Zheng2014-11-242-15/+4
| | | | | | | | | | | | | | | | Use generic io stats accounting help functions (generic_{start,end}_io_acct) to simplify io stat accounting. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * drbd: use generic io stats accounting functions to simplify io stat accountingGu Zheng2014-11-241-18/+4
| | | | | | | | | | | | | | | | Use generic io stats accounting help functions (generic_{start,end}_io_acct) to simplify io stat accounting. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * md/bcache: use generic io stats accounting functions to simplify io stat ↵Gu Zheng2014-11-241-17/+6
| | | | | | | | | | | | | | | | | | | | | | accounting Use generic io stats accounting help functions (generic_{start,end}_io_acct) to simplify io stat accounting. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Acked-by: Kent Overstreet <kmo@datera.io> Signed-off-by: Jens Axboe <axboe@fb.com>
| * Merge branch 'for-3.19/core' into for-3.19/driversJens Axboe2014-11-244-23/+52
| |\
| * | NVMe: Update module version major numberKeith Busch2014-11-211-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | It's already near impossible to tell what bits someone is running based on a 'modinfo nvme', and I don't want to try guessing if someone is running blk-mq or bio-based. Let's make it obvious with the module version that the blk-mq conversion is a major change. Future bio-based versions can increment to 0.10 in a fork if revisions occur. Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | NVMe: fail pci initialization if the device doesn't have any BARsJens Axboe2014-11-201-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The PCI init of NVMe doesn't check for valid bars before proceeding to map and use BAR 0. If the device is hosed (or firmware is), then we should catch this case and give up early. This fixes a: [ 1662.035778] WARNING: CPU: 0 PID: 4 at arch/x86/mm/ioremap.c:63 __ioremap_check_ram+0xa7/0xc0() and later badness on such a device. Acked-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | NVMe: add ->exit_hctx() hookJens Axboe2014-11-201-0/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | If we do teardown and setup of the queue and block related parts of the driver, then we should clear nvmeq->hctx once we kill the hardware queue. Acked-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | NVMe: make setup work for devices that don't do INTxJens Axboe2014-11-191-0/+19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The setup/probe part currently relies on INTx being there and working, that's not always the case. For devices that don't advertise INTx, enable a single MSIx vector early on and disable it again before we ask for our full range of queue vecs. Acked-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | Merge branch 'master' into for-3.19/driversJens Axboe2014-11-181339-9571/+22704
| |\ \
| * | | NVMe: enable IO stats by defaultJens Axboe2014-11-181-1/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Before the blk-mq conversion they were on by default, we should not change behavior there. Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | NVMe: nvme_submit_async_admin_req() must use atomic rq allocationJens Axboe2014-11-181-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We are called for async event notification issues, and the nvmeq lock is already held. If we fail the request allocation, we'll just retry next time. Reported-by: Julia Lawall <julia.lawall@lip6.fr> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | NVMe: replace blk_put_request() with blk_mq_free_request()Jens Axboe2014-11-171-7/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | No point in using blk_put_request(), since we know we are blk-mq. This only makes sense in core code where we could be dealing with either legacy or blk-mq drivers. Additionally, use blk_mq_free_hctx_request() for the request completion fast path, where we already know the mapping from request to hardware queue. Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | Merge branch 'for-3.19/core' into for-3.19/driversJens Axboe2014-11-174-22/+53
| |\ \ \
| * | | | drbd: Remove an useless copy of kernel_setsockopt()Philipp Reisner2014-11-101-25/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Old backward-compat cruft Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | drbd: Fix state change in case of connection timeoutPhilipp Reisner2014-11-101-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | A connection timeout affects all volumes of a resource! Under the following conditions: A resource with multiple volumes AND ko-count >=1 AND a write request triggers the timeout (ko-count * timeout) DRBD's internal state gets confused. That in turn may lead to very miss leading follow up failures. E.g. "BUG: scheduling while atomic" CC: stable@kernel.org # v3.17 Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | drbd: merge_bvec_fn: properly remap bvm->bi_bdevLars Ellenberg2014-11-101-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This was not noticed for many years. Affects operation if md raid is used a backing device for DRBD. CC: stable@kernel.org # v3.2+ Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | drbd: fix resync throttling initializationLars Ellenberg2014-11-103-3/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If for some reason DRBD resync was the only activity on a backend device, drbd_rs_c_min_rate_throttle() would mistakenly decide that it is still initialization time, and keep throttling the resync. This patch explicitly initializes ->rs_last_events to the current backend event counters, and drops the rs_last_events == 0 from the throttle condition. Reported-by: Mikhail Sugakov <msugakov@amazon.de> Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | drbd: fix race between role change and handshakePhilipp Reisner2014-11-103-8/+40
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Symptoms: If DRBD was "cleanly shut down" (all in sync, both Secondary before disconnect, identical data generation uuids), and then one side was promoted *during* the next connection handshake, the role change could confuse the handshake. The Primary would get stuck in WFBitmapS, the Secondary would log unexpected cstate (Connected) in receive_bitmap and get stuck in WFBitmapT. Fix: The test in is_valid_soft_transition wrong. It works because the not allowed actions (promote/attach) do not touch the cstate. The previous condition failed to demand a cstate change in one clause. In order to avoid deadlocks give up the state_mutex while waiting for the transient state to go away. Conflicts: drbd/drbd_state.c drbd/drbd_state.h drbd/drbd_wrappers.h Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | drbd: Only use drbd_msg_put_info() in drbd_nl.cAndreas Gruenbacher2014-11-103-16/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Avoid generic netlink calls in other parts of the code base. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | drbd: Minor cleanupsAndreas Gruenbacher2014-11-105-45/+35
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | . Update comments . drbd_set_{in,out_of}_sync(): Remove unused parameters . Move common code into adm_del_resource() . Redefine ERR_MINOR_EXISTS -> ERR_MINOR_OR_VOLUME_EXISTS Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: __nvme_submit_admin_cmd() can be statickbuild test robot2014-11-101-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | drivers/block/nvme-core.c:865:5: sparse: symbol '__nvme_submit_admin_cmd' was not declared. Should it be static? Signed-off-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: blk_mq_alloc_request() returns error pointersDan Carpenter2014-11-051-6/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We recently converted this to blk_mq but the error checks have to be updated to check for IS_ERR() instead of NULL. Fixes: a4aea5623d4a ('NVMe: Convert to blk-mq') Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: Convert to blk-mqMatias Bjørling2014-11-043-819/+570
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This converts the NVMe driver to a blk-mq request-based driver. The NVMe driver is currently bio-based and implements queue logic within itself. By using blk-mq, a lot of these responsibilities can be moved and simplified. The patch is divided into the following blocks: * Per-command data and cmdid have been moved into the struct request field. The cmdid_data can be retrieved using blk_mq_rq_to_pdu() and id maintenance are now handled by blk-mq through the rq->tag field. * The logic for splitting bio's has been moved into the blk-mq layer. The driver instead notifies the block layer about limited gap support in SG lists. * blk-mq handles timeouts and is reimplemented within nvme_timeout(). This both includes abort handling and command cancelation. * Assignment of nvme queues to CPUs are replaced with the blk-mq version. The current blk-mq strategy is to assign the number of mapped queues and CPUs to provide synergy, while the nvme driver assign as many nvme hw queues as possible. This can be implemented in blk-mq if needed. * NVMe queues are merged with the tags structure of blk-mq. * blk-mq takes care of setup/teardown of nvme queues and guards invalid accesses. Therefore, RCU-usage for nvme queues can be removed. * IO tracing and accounting are handled by blk-mq and therefore removed. * Queue suspension logic is replaced with the logic from the block layer. Contributions in this patch from: Sam Bradshaw <sbradshaw@micron.com> Jens Axboe <axboe@fb.com> Keith Busch <keith.busch@intel.com> Robert Nelson <rlnelson@google.com> Acked-by: Keith Busch <keith.busch@intel.com> Acked-by: Jens Axboe <axboe@fb.com> Updated for new ->queue_rq() prototype. Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: Do not over allocate for discard requestsKeith Busch2014-11-041-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Discard requests are often for very large ranges. The discard size is not representative of the data transfer size so we don't need to allocate for such a large prp list. This patch requests allocating only enough for the memory needed for the data transfer and saves a little over 8k of memory per max discard request. Signed-off-by: Keith Busch <keith.busch@intel.com> Reported-by: Paul Grabinar <paul.grabinar@ranbarg.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: Do not open disks that are being deletedKeith Busch2014-11-041-4/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | It is possible the block layer will request to open a block device after the driver deleted it. Subsequent releases will cause a double free, or the disk's private_data is pointing to freed memory. This patch protects the driver's freed disks from being opened and accessed: the nvme namespaces are freed only when the device's refcount is 0, so at that moment there were no active openers and no more should be allowed, and it is safe to clear the disk's private_data that is about to be freed. Signed-off-by: Keith Busch <keith.busch@intel.com> Reported-by: Henry Chow <henry.chow@oracle.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: Clear QUEUE_FLAG_STACKABLEKeith Busch2014-11-041-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The nvme namespace request_queue's flags are initialized to QUEUE_FLAG_DEFAULT, which currently sets QUEUE_FLAG_STACKABLE. The device-mapper indicates this flag means the block driver is requset based, though this driver is bio-based and problems will occur if an nvme namespace is used with a request based dm device. This patch clears the stackable flag. Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: Fix device probe waiting on kthreadKeith Busch2014-11-041-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If we ever do parallel device probing, we need to wake up all processes waiting for nvme kthread to start, not just one. This is currently serialized so the bug is not reachable today, but fixing this anyway in the hopes we implement parallel or asynchronous probe in the future. Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: Updates for 1.1 specKeith Busch2014-11-041-1/+26
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Updating commands and structures for NVMe 1.1 updates, mostly for nvme reservations. There are no additional in-kernel uses, but this is for the uapi. While doing this, I noticed that the software progress features was using the wrong value, so updating that value as well. Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: Passthrough IOCTL for IO commandsKeith Busch2014-11-042-6/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The NVME_IOCTL_SUBMIT_IO only works for IO commands with block data transfers and isn't usable for other NVMe commands like flush, data set management, or any sort of vendor unique command. The NVME_IOCTL_ADMIN_CMD, however, can easily be modified to accept arbitrary IO commands in addition to arbitrary admin commands without breaking backward compatibility. This patch just adds a new IOCTL to distinguish if the driver should submit the command on an IO or Admin queue. Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: Add revalidate_disk callbackKeith Busch2014-11-041-0/+30
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This adds a callback to revalidate the disk and change its block size and capacity if needed. Before, a user would have to remove + rescan an entire device if they changed the logical block size using an NVMe Format or other vendor specific command; now they can just run something that issues the BLKRRPART IOCTL, like # hdparm -z /dev/nvmeXnY This can also be used in response to the 1.2 Spec's Namespace Attribute Change asynchronous event. Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: Fix nvmeq waitqueue entry initializationKeith Busch2014-11-041-7/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We need to update the nvme queue's wait_queue_t entry during each initialization since the nvme_thread may be ended and restarted when the device is reset. If a device reset occurs during a large amount of buffered IO, it would take a lot longer to complete the outstanding requests due to the 1 second polling instead of waking up as completions occur. Fixes: b9afca3efb18a9b8392cb544a3e29e8b1168400c Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: Translate NVMe status to errnoKeith Busch2014-11-041-1/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This returns a more appropriate error for the "capacity exceeded" status. In case other NVMe statuses have a better errno, this patch adds a convience function to translate an NVMe status code to an errno for IO commands, defaulting to the current -EIO. Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: Fix SG_IO status valuesKeith Busch2014-11-041-0/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We've only been setting the sg_io_hdr status values on SCSI commands that require an nvme command to complete the translation. The fields in the struct are output parameters, so we have to set them, otherwise user space will see whatever was in memory from before. In the case of compat SG_IO, this would reveal kernel memory. This fixes the issue by initializing the sg_io_hdr with successful status. Signed-off-by: Keith Busch <keith.busch@intel.com> Acked-by: Vishal Verma <vishal.l.verma@linux.intel.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: Remove duplicate compat SG_IO codeKeith Busch2014-11-042-149/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We can return -ENOIOCTLCMD and the ioctl will be handled by fs/compat_ioctl.c instead. This removes a lot of duplicate code in the nvme driver. Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: Reference count pci deviceKeith Busch2014-11-041-2/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If an nvme device is removed but user space has an open reference, the nvme driver would have been holding an invalid reference to its pci device. You may get a general protection fault on x86 h/w when the driver uses that reference in dma_map_sg(), as is done in nvme_map_user_pages() from the IOCTL interface. This patch fixes the fault by taking a reference on the pci device and holding it even after device removal until all opens on the nvme device are closed. Signed-off-by: Keith Busch <keith.busch@intel.com> Reported-by: Nilesh Choudhury <nilesh.choudhury@oracle.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | nvme: Replace rcu_assign_pointer() with RCU_INIT_POINTER()Andreea-Cristina Bernat2014-11-041-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The use of "rcu_assign_pointer()" is NULLing out the pointer. According to RCU_INIT_POINTER()'s block comment: "1. This use of RCU_INIT_POINTER() is NULLing out the pointer" it is better to use it instead of rcu_assign_pointer() because it has a smaller overhead. The following Coccinelle semantic patch was used: @@ @@ - rcu_assign_pointer + RCU_INIT_POINTER (..., NULL) Signed-off-by: Andreea-Cristina Bernat <bernat.ada@gmail.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: Correctly handle IOCTL_SUBMIT_IO when cpus > online queuesSam Bradshaw2014-11-041-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | nvme_submit_io_cmd() uses smp_processor_id() to pick an IO queue index. This patch fixes the case where there are more cpus from which the ioctl call can originate than online queues, which can happen when a device supports or was allocated fewer interrupt vectors than exist cpu cores. Thanks to Keith Busch for the implementation suggestion. Signed-off-by: Sam Bradshaw <sbradshaw@micron.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
| * | | | NVMe: Fix filesystem sync deadlock on removalKeith Busch2014-11-041-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This changes the order of deleting the gendisks so it happens after the nvme IO queues are freed. If a device is removed while a filesystem has associated dirty data, the removal will wait on these to complete before proceeding from del_gendisk, which could have caused deadlock before. The implication of this is that an orderly removal of a responsive device won't necessarily wait for dirty data to be written, but we are not guaranteed the device is even going to respond at this point either. Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-09 20:30:13 +0000