summaryrefslogtreecommitdiff
path: root/drivers/nvme
AgeCommit message (Collapse)Author
2016-07-14nvme: Remove RCU namespace protectionKeith Busch
We can't sleep with RCU read lock held, but we need to do potentially blocking stuff to namespace queues when iterating the list. This patch removes the RCU locking and holds a mutex instead. To prevent deadlocks, this patch removes holding the mutex during namespace scanning and removal. The unlocked namespace scanning is made safe by holding a reference to the namespace being scanned. List iteration that does IO has to be unlocked to allow error recovery. The caller must ensure the list can not be manipulated during such an event, so this patch adds a comment explaining this requirement to the only function that iterates an unlocked list. All callers currently meet this requirement, so no further changes required. List iterations that do not do IO can safely use the lock since it couldn't block recovery from missing forced IO completions. Reported-by: Ming Lin <mlin at kernel.org> [fixes 0bf77e9 nvme: switch to RCU freeing the namespace] Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-06-09NVMe: Only release requested regionsJohannes Thumshirn
The NVMe driver only requests the PCIe device's memory regions but releases all possible regions (including eventual I/O regions). This leads to a stale warning entry in dmesg about freeing non existent resources. Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-17nvme/host: Add missing blk_integrity tag_size + flags assignmentsNicholas Bellinger
While doing recent bring-up of nvme/host with target-core T10-PI, I noticed /sys/block/nvme*/integrity/device_is_integrity_capable was false, and /sys/block/nvme*/integrity/tag_size contained a bogus value. AFAICT outside of blk_integrity_compare() for DM + MD these are informational values, but go ahead and add the missing assignments for nvme/host to match what SCSI does within sd_dif_config_host() for consistency's sake. Cc: Keith Busch <keith.busch@intel.com> Cc: Jay Freyensee <james.p.freyensee@intel.com> Cc: Martin K. Petersen <martin.petersen@oracle.com> Cc: Sagi Grimberg <sagig@grimberg.me> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org> Reviewed-by: Sagi Grimberg <sagi at grimberg.me> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-17NVMe: Add device ID's with stripe quirkKeith Busch
Adds two Intel controllers that have the "stripe" quirk. Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-17NVMe: Short-cut removal on surprise hot-unplugKeith Busch
This patch adds a new state that when set has the core automatically kill request queues prior to removing namespaces. If PCI device is not present at the time the nvme driver's remove is called, we can kill all IO queues immediately instead of waiting for the watchdog thread to do that at its polling interval. This improves scenarios where multiple hot plug events occur at the same time since it doesn't block the pci enumeration for as long. Signed-off-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-17NVMe: Allow user initiated rescanKeith Busch
This exposes ioctl and sysfs methods a user can invoke to request the driver rescan a controller and its namespaces. This is less harsh than doing a controller reset, which temporarilly halts all IO, just to surface a newly attached namespace. This is mainly useful for controllers that implement the namespace management command, but do not support the namespace notify change asynchronous event notification. Signed-off-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-17NVMe: Reduce driver log spammingKeith Busch
Reduce error logging when no corrective action is required. Suggessted-by: Chris Petersen <cpetersen@fb.com> Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-17NVMe: Unbind driver on failureKeith Busch
Instead of removing the PCI device from the kernel's topology on controller failure, this patch simply requests unbinding the device from the driver. This avoids concurrently running pci removal with the hot plug event, which has been reported to be problematic when multiple surprise events occur near simultaneously. The other benefit is that we will have PCI config and memory space available to poke around for debugging a failed controller, assuming the device was not physically removed. The down side occurs if the platform and/or kernel do not support any type of surprise hot removal. The device will remain visible through sysfs (and therefore lspci), and some manual work is necessary to get the logical topology corrected. But if your platform and/or kernel don't support surprise removal, you probably shouldn't be doing that anyway. Signed-off-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-17NVMe: Delete only created queuesKeith Busch
Use the online queue count instead of the number of allocated queues. The controller should just return an invalid queue identifier error to the commands if a queue wasn't created. While it's not harmful, it's still not correct. Reported-by: Saar Gross <saar@annapurnalabs.com> Signed-off-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-17NVMe: Allocate queues only for online cpusKeith Busch
The driver previously requested allocating queues for the total possible number of CPUs so that blk-mq could rebalance these if CPUs were added after initialization. The number of hardware contexts can now be changed at runtime, so we only need to allocate the number of online queues since we can add more later. Suggested-by: Jeff Lien <jeff.lien@hgst.com> Signed-off-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-17Merge branch 'for-4.7/drivers' of git://git.kernel.dk/linux-blockLinus Torvalds
Pull block driver updates from Jens Axboe: "On top of the core pull request, this is the drivers pull request for this merge window. This contains: - Switch drivers to the new write back cache API, and kill off the flush flags. From me. - Kill the discard support for the STEC pci-e flash driver. It's trivially broken, and apparently unmaintained, so it's safer to just remove it. From Jeff Moyer. - A set of lightnvm updates from the usual suspects (Matias/Javier, and Simon), and fixes from Arnd, Jeff Mahoney, Sagi, and Wenwei Tao. - A set of updates for NVMe: - Turn the controller state management into a proper state machine. From Christoph. - Shuffling of code in preparation for NVMe-over-fabrics, also from Christoph. - Cleanup of the command prep part from Ming Lin. - Rewrite of the discard support from Ming Lin. - Deadlock fix for namespace removal from Ming Lin. - Use the now exported blk-mq tag helper for IO termination. From Sagi. - Various little fixes from Christoph, Guilherme, Keith, Ming Lin, Wang Sheng-Hui. - Convert mtip32xx to use the now exported blk-mq tag iter function, from Keith" * 'for-4.7/drivers' of git://git.kernel.dk/linux-block: (74 commits) lightnvm: reserved space calculation incorrect lightnvm: rename nr_pages to nr_ppas on nvm_rq lightnvm: add is_cached entry to struct ppa_addr lightnvm: expose gennvm_mark_blk to targets lightnvm: remove mgt targets on mgt removal lightnvm: pass dma address to hardware rather than pointer lightnvm: do not assume sequential lun alloc. nvme/lightnvm: Log using the ctrl named device lightnvm: rename dma helper functions lightnvm: enable metadata to be sent to device lightnvm: do not free unused metadata on rrpc lightnvm: fix out of bound ppa lun id on bb tbl lightnvm: refactor set_bb_tbl for accepting ppa list lightnvm: move responsibility for bad blk mgmt to target lightnvm: make nvm_set_rqd_ppalist() aware of vblks lightnvm: remove struct factory_blks lightnvm: refactor device ops->get_bb_tbl() lightnvm: introduce nvm_for_each_lun_ppa() macro lightnvm: refactor dev->online_target to global nvm_targets lightnvm: rename nvm_targets to nvm_tgt_type ...
2016-05-06lightnvm: rename nr_pages to nr_ppas on nvm_rqJavier González
The number of ppas contained on a request is not necessarily the number of pages that it maps to neither on the target nor on the device side. In order to avoid confusion, rename nr_pages to nr_ppas since it is what the variable actually contains. Signed-off-by: Javier González <javier@cnexlabs.com> Signed-off-by: Matias Bjørling <m@bjorling.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-06lightnvm: pass dma address to hardware rather than pointerArnd Bergmann
A recent change to lightnvm added code to pass a kernel pointer to the hardware, which gcc complained about: drivers/nvme/host/lightnvm.c: In function 'nvme_nvm_rqtocmd': drivers/nvme/host/lightnvm.c:472:32: error: cast from pointer to integer of different size [-Werror=pointer-to-int-cast] c->ph_rw.metadata = cpu_to_le64(rqd->meta_list); It looks like this has no way of working anyway, so this changes the code to pass the dma_address instead. This was most likely what was intended here. Neither of the two are currently ever written to, so the effect is the same for now. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Fixes: a34b1eb78e21 ("lightnvm: enable metadata to be sent to device") Signed-off-by: Matias Bjørling <m@bjorling.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-06nvme/lightnvm: Log using the ctrl named deviceSagi Grimberg
Align with the rest of the nvme subsystem. Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Matias Bjørling <m@bjorling.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-06lightnvm: rename dma helper functionsJavier González
Until now, the dma pool have been exclusively used to allocate the ppa list being sent to the device. In pblk (upcoming), we use these pools to allocate metadata too. Thus, we generalize the names of some variables on the dma helper functions to make the code more readable. Signed-off-by: Javier González <javier@cnexlabs.com> Signed-off-by: Matias Bjørling <m@bjorling.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-06lightnvm: enable metadata to be sent to deviceJavier González
Enable metadata buffer to be sent to the device through the metadata field on the physical rw nvme command. The size of the metadata buffer must follow dev->oob_size * # of PPAs. Signed-off-by: Javier González <javier@cnexlabs.com> Updated description. Signed-off-by: Matias Bjørling <m@bjorling.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-06lightnvm: refactor set_bb_tbl for accepting ppa listMatias Bjørling
The set_bb_tbl takes struct nvm_rq and only uses its ppa_list and nr_pages internally. Instead, make these two variables explicit. This allows a user to call it without initializing a struct nvm_rq first. Signed-off-by: Matias Bjørling <m@bjorling.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-06lightnvm: refactor device ops->get_bb_tbl()Matias Bjørling
The device ops->get_bb_tbl() takes a callback, that allows the caller to use its own callback function to update its data structures in the returning function. This makes it difficult to send parameters to the callback, and usually is circumvented by small private structures, that both carry the callers state and any flags needed to fulfill the update. Refactor ops->get_bb_tbl() to fill a data buffer with the status of the blocks returned, and let the user call the callback function manually. That will provide the necessary flags and data structures and simplify the logic around ops->get_bb_tbl(). Signed-off-by: Matias Bjørling <m@bjorling.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-06lightnvm: move block fold outside of get_bb_tbl()Matias Bjørling
The get block table command returns a list of blocks and planes with their associated state. Users, such as gennvm and sysblk, manages all planes as a single virtual block. It was therefore natural to fold the bad block list before it is returned. However, to allow users, which manages on a per-plane block level, to also use the interface, the get_bb_tbl interface is changed to not fold by default and instead let the caller fold if necessary. Reviewed by: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: Matias Bjørling <m@bjorling.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-03NVMe: Fix reset/remove raceKeith Busch
This fixes a scenario where device is present and being reset, but a request to unbind the driver occurs. A previous patch series addressing a device failure removal scenario flushed reset_work after controller disable to unblock reset_work waiting on a completion that wouldn't occur. This isn't safe as-is. The broken scenario can potentially be induced with: modprobe nvme && modprobe -r nvme To fix, the reset work is flushed immediately after setting the controller removing flag, and any subsequent reset will not proceed with controller initialization if the flag is set. The controller status must be polled while active, so the watchdog timer is also left active until the controller is disabled to cleanup requests that may be stuck during namespace removal. [Fixes: ff23a2a15a2117245b4599c1352343c8b8fb4c43] Signed-off-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-02nvme: fix nvme_ns_remove() deadlockMing Lin
On receipt of a namespace attribute changed AER, we acquire the namespace mutex lock before proceeding to scan and validate the namespace list. In case of namespace detach/delete command, nvme_ns_remove function deadlocks trying to acquire the already held lock. All callers, except nvme_remove_namespaces(), of nvme_ns_remove() already held namespaces_mutex. So we can simply fix the deadlock by not acquiring the mutex in nvme_ns_remove() and acquiring it in nvme_remove_namespaces(). Reported-by: Sunad Bhandary S <sunad.s@samsung.com> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Sagi Grimerg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-02nvme: switch to RCU freeing the namespaceMing Lin
Switch to RCU freeing the namespace structure so that nvme_start_queues, nvme_stop_queues and nvme_kill_queues would be able to get away with only a RCU read side critical section. Suggested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Sagi Grimerg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-02nvme: add helper nvme_cleanup_cmd()Ming Lin
This hides command cleanup into nvme.h and fabrics drivers will also use it. Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-02nvme: move AER handling to common codeChristoph Hellwig
The transport driver still needs to do the actual submission, but all the higher level code can be shared. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-02nvme: move namespace scanning to coreChristoph Hellwig
Move the scan work item and surrounding code to the common code. For now we need a new finish_scan method to allow the PCI driver to set the irq affinity hints, but I have plans in the works to obsolete this as well. Note that this moves the namespace scanning from nvme_wq to the system workqueue, but as we don't rely on namespace scanning to finish from reset or I/O this should be fine. Signed-off-by: Christoph Hellwig <hch@lst.de> Acked-by Jon Derrick: <jonathan.derrick@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-02nvme: tighten up state check for namespace scanningChristoph Hellwig
We only should be scanning namespaces if the controller is live. Currently we call the function just before setting it live, so fix the code up to move the call to nvme_queue_scan to just below the state change. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Acked-by Jon Derrick: <jonathan.derrick@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-02nvme: introduce a controller state machineChristoph Hellwig
Replace the adhoc flags in the PCI driver with a state machine in the core code. Based on code from Sagi Grimberg for the Fabrics driver. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Acked-by Jon Derrick: <jonathan.derrick@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-02nvme: remove the io_incapable methodChristoph Hellwig
It's unused since "NVMe: Move error handling to failed reset handler". Signed-off-by: Christoph Hellwig <hch@lst.de> Acked-by: Jon Derrick <jonathan.derrick@intel.com> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-02NVMe: nvme_core_exit() should do cleanup in the reverse order as ↵Wang Sheng-Hui
nvme_core_init does nvme_core_init does: 1) register_blkdev 2) __register_chrdev 3) class_create nvme_core_exit should do cleanup in the reverse order. Signed-off-by: Wang Sheng-Hui <shhuiw@foxmail.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-05-02NVMe: Fix check_flush_dependency warningKeith Busch
If the controller fails and is degraded after a reset, we need to kill off all requests queues before removing the inaccessble namespaces. This will prevent del_gendisk from syncing dirty data, which we can't due from a WQ_MEM_RECLAIM work queue. Signed-off-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-04-26NVMe: small typo in section BLK_DEV_NVME_SCSI of host/KconfigWang Sheng-Hui
"as well as " is miss typed "as well a " in section "config BLK_DEV_NVME_SCSI" Signed-off-by: Wang Sheng-Hui <shhuiw@foxmail.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-04-26nvme: fix cntlid typeChristoph Hellwig
Controller IDs in NVMe are unsigned 16-bit types. In the Fabrics driver we actually pass ctrl->id by reference, so we need it to have the correct type. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-04-14NVMe: Always use MSI/MSI-x interruptsKeith Busch
Multiple users have reported device initialization failure due the driver not receiving legacy PCI interrupts. This is not unique to any particular controller, but has been observed on multiple platforms. There have been no issues reported or observed when with message signaled interrupts, so this patch attempts to use MSI-x during initialization, falling back to MSI. If that fails, legacy would become the default. The setup_io_queues error handling had to change as a result: the admin queue's msix_entry used to be initialized to the legacy IRQ. The case where nr_io_queues is 0 would fail request_irq when setting up the admin queue's interrupt since re-enabling MSI-x fails with 0 vectors, leaving the admin queue's msix_entry invalid. Instead, return success immediately. Reported-by: Tim Muhlemmer <muhlemmer@gmail.com> Reported-by: Jon Derrick <jonathan.derrick@intel.com> Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-04-13nvme: Avoid reset work on watchdog timer function during error recoveryGuilherme G. Piccoli
This patch adds a check on nvme_watchdog_timer() function to avoid the call to reset_work() when an error recovery process is ongoing on controller. The check is made by looking at pci_channel_offline() result. If we don't check for this on nvme_watchdog_timer(), error recovery mechanism can't recover well, because reset_work() won't be able to do its job (since we're in the middle of an error) and so the controller is removed from the system before error recovery mechanism can perform slot reset (which would allow the adapter to recover). In this patch we also have split the huge condition expression on nvme_watchdog_timer() by introducing an auxiliary function to help make the code more readable. Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: Guilherme G. Piccoli <gpiccoli@linux.vnet.ibm.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-04-12NVMe: silence warning about unused 'dev'Jens Axboe
Depending on options, we might not be using dev in nvme_cancel_io(): drivers/nvme/host/pci.c: In function ‘nvme_cancel_io’: drivers/nvme/host/pci.c:970:19: warning: unused variable ‘dev’ [-Wunused-variable] struct nvme_dev *dev = data; ^ So get rid of it, and just cast for the dev_dbg_ratelimited() call. Fixes: 82b4552b91c4 ("nvme: Use blk-mq helper for IO termination") Signed-off-by: Jens Axboe <axboe@fb.com>
2016-04-12NVMe: switch to using blk_queue_write_cache()Jens Axboe
Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-04-12nvme: Use blk-mq helper for IO terminationSagi Grimberg
blk-mq offers a tagset iterator so let's use that instead of using nvme_clear_queues. Note, we changed nvme_queue_cancel_ios name to nvme_cancel_io as there is no concept of a queue now in this function (we also lost the print). Signed-off-by: Sagi Grimberg <sagig@mellanox.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Acked-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-04-12NVMe: Skip async events for degraded controllersKeith Busch
If the controller is degraded, the driver should stay out of the way so the user can recover the drive. This patch skips driver initiated async event requests when the drive is in this state. Signed-off-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-04-12nvme: add helper nvme_setup_cmd()Ming Lin
This moves nvme_setup_{flush,discard,rw} calls into a common nvme_setup_cmd() helper. So we can eventually hide all the command setup in the core module and don't even need to update the fabrics drivers for any specific command type. Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-04-12nvme: rewrite discard supportMing Lin
This rewrites nvme_setup_discard() with blk_add_request_payload(). It allocates only the necessary amount(16 bytes) for the payload. Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-04-12nvme: add helper nvme_map_len()Ming Lin
The helper returns the number of bytes that need to be mapped using PRPs/SGL entries. Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-04-12nvme: add missing lock nesting notationMing Lin
When unloading driver, nvme_disable_io_queues() calls nvme_delete_queue() that sends nvme_admin_delete_cq command to admin sq. So when the command completed, the lock acquired by nvme_irq() actually belongs to admin queue. While the lock that nvme_del_cq_end() trying to acquire belongs to io queue. So it will not deadlock. This patch adds lock nesting notation to fix following report. [ 109.840952] ============================================= [ 109.846379] [ INFO: possible recursive locking detected ] [ 109.851806] 4.5.0+ #180 Tainted: G E [ 109.856533] --------------------------------------------- [ 109.861958] swapper/0/0 is trying to acquire lock: [ 109.866771] (&(&nvmeq->q_lock)->rlock){-.....}, at: [<ffffffffc0820bc6>] nvme_del_cq_end+0x26/0x70 [nvme] [ 109.876535] [ 109.876535] but task is already holding lock: [ 109.882398] (&(&nvmeq->q_lock)->rlock){-.....}, at: [<ffffffffc0820c2b>] nvme_irq+0x1b/0x50 [nvme] [ 109.891547] [ 109.891547] other info that might help us debug this: [ 109.898107] Possible unsafe locking scenario: [ 109.898107] [ 109.904056] CPU0 [ 109.906515] ---- [ 109.908974] lock(&(&nvmeq->q_lock)->rlock); [ 109.913381] lock(&(&nvmeq->q_lock)->rlock); [ 109.917787] [ 109.917787] *** DEADLOCK *** [ 109.917787] [ 109.923738] May be due to missing lock nesting notation [ 109.923738] [ 109.930558] 1 lock held by swapper/0/0: [ 109.934413] #0: (&(&nvmeq->q_lock)->rlock){-.....}, at: [<ffffffffc0820c2b>] nvme_irq+0x1b/0x50 [nvme] [ 109.944010] [ 109.944010] stack backtrace: [ 109.948389] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G E 4.5.0+ #180 [ 109.955734] Hardware name: Dell Inc. OptiPlex 7010/0YXT71, BIOS A15 08/12/2013 [ 109.962989] 0000000000000000 ffff88011e203c38 ffffffff81383d9c ffffffff81c13540 [ 109.970478] ffffffff826711d0 ffff88011e203ce8 ffffffff810bb429 0000000000000046 [ 109.977964] 0000000000000046 0000000000000000 0000000000b2e597 ffffffff81f4cb00 [ 109.985453] Call Trace: [ 109.987911] <IRQ> [<ffffffff81383d9c>] dump_stack+0x85/0xc9 [ 109.993711] [<ffffffff810bb429>] __lock_acquire+0x19b9/0x1c60 [ 109.999575] [<ffffffff810b6d1d>] ? trace_hardirqs_off+0xd/0x10 [ 110.005524] [<ffffffff810b386d>] ? complete+0x3d/0x50 [ 110.010688] [<ffffffff810bb760>] lock_acquire+0x90/0xf0 [ 110.016029] [<ffffffffc0820bc6>] ? nvme_del_cq_end+0x26/0x70 [nvme] [ 110.022418] [<ffffffff81772afb>] _raw_spin_lock_irqsave+0x4b/0x60 [ 110.028632] [<ffffffffc0820bc6>] ? nvme_del_cq_end+0x26/0x70 [nvme] [ 110.035019] [<ffffffffc0820bc6>] nvme_del_cq_end+0x26/0x70 [nvme] [ 110.041232] [<ffffffff8135b485>] blk_mq_end_request+0x35/0x60 [ 110.047095] [<ffffffffc0821ad8>] nvme_complete_rq+0x68/0x190 [nvme] [ 110.053481] [<ffffffff8135b53f>] __blk_mq_complete_request+0x8f/0x130 [ 110.060043] [<ffffffff8135b611>] blk_mq_complete_request+0x31/0x40 [ 110.066343] [<ffffffffc08209e3>] __nvme_process_cq+0x83/0x240 [nvme] [ 110.072818] [<ffffffffc0820c35>] nvme_irq+0x25/0x50 [nvme] [ 110.078419] [<ffffffff810cdb66>] handle_irq_event_percpu+0x36/0x110 [ 110.084804] [<ffffffff810cdc77>] handle_irq_event+0x37/0x60 [ 110.090491] [<ffffffff810d0ea3>] handle_edge_irq+0x93/0x150 [ 110.096180] [<ffffffff81012306>] handle_irq+0xa6/0x130 [ 110.101431] [<ffffffff81011abe>] do_IRQ+0x5e/0x120 [ 110.106333] [<ffffffff8177384c>] common_interrupt+0x8c/0x8c Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-04-12NVMe: Always use MSI/MSI-x interruptsKeith Busch
Multiple users have reported device initialization failure due the driver not receiving legacy PCI interrupts. This is not unique to any particular controller, but has been observed on multiple platforms. There have been no issues reported or observed when with message signaled interrupts, so this patch attempts to use MSI-x during initialization, falling back to MSI. If that fails, legacy would become the default. The setup_io_queues error handling had to change as a result: the admin queue's msix_entry used to be initialized to the legacy IRQ. The case where nr_io_queues is 0 would fail request_irq when setting up the admin queue's interrupt since re-enabling MSI-x fails with 0 vectors, leaving the admin queue's msix_entry invalid. Instead, return success immediately. Reported-by: Tim Muhlemmer <muhlemmer@gmail.com> Reported-by: Jon Derrick <jonathan.derrick@intel.com> Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-04-11NVMe: Fix reset/remove raceKeith Busch
This fixes a scenario where device is present and being reset, but a request to unbind the driver occurs. A previous patch series addressing a device failure removal scenario flushed reset_work after controller disable to unblock reset_work waiting on a completion that wouldn't occur. This isn't safe as-is. The broken scenario can potentially be induced with: modprobe nvme && modprobe -r nvme To fix, the reset work is flushed immediately after setting the controller removing flag, and any subsequent reset will not proceed with controller initialization if the flag is set. The controller status must be polled while active, so the watchdog timer is also left active until the controller is disabled to cleanup requests that may be stuck during namespace removal. [Fixes: ff23a2a15a2117245b4599c1352343c8b8fb4c43] Signed-off-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-03-22nvme: avoid cqe corruption when update at the same time as readMarta Rybczynska
Make sure the CQE phase (validity) is read before the rest of the structure. The phase bit is the highest address and the CQE read will happen on most platforms from lower to upper addresses and will be done by multiple non-atomic loads. If the structure is updated by PCI during the reads from the processor, the processor may get a corrupted copy. The addition of the new nvme_cqe_valid function that verifies the validity bit also allows refactoring of the other CQE read sequences. Signed-off-by: Marta Rybczynska <marta.rybczynska@kalray.eu> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-03-18nvme: lightnvm: return ppa completion statusMatias Bjorling
PPAs sent to device is separately acknowledge in a 64bit status variable. The status is stored in DW0 and DW1 of the completion queue entry. Store this status inside the nvm_rq for further processing. This can later be used to implement retry techniques for failed writes and reads. Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Matias Bjørling <m@bjorling.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-03-18Merge branch 'for-4.6/drivers' of git://git.kernel.dk/linux-blockLinus Torvalds
Pull block driver updates from Jens Axboe: "This is the block driver pull request for this merge window. It sits on top of for-4.6/core, that was just sent out. This contains: - A set of fixes for lightnvm. One from Alan, fixing an overflow, and the rest from the usual suspects, Javier and Matias. - A set of fixes for nbd from Markus and Dan, and a fixup from Arnd for correct usage of the signed 64-bit divider. - A set of bug fixes for the Micron mtip32xx, from Asai. - A fix for the brd discard handling from Bart. - Update the maintainers entry for cciss, since that hardware has transferred ownership. - Three bug fixes for bcache from Eric Wheeler. - Set of fixes for xen-blk{back,front} from Jan and Konrad. - Removal of the cpqarray driver. It has been disabled in Kconfig since 2013, and we were initially scheduled to remove it in 3.15. - Various updates and fixes for NVMe, with the most important being: - Removal of the per-device NVMe thread, replacing that with a watchdog timer instead. From Christoph. - Exposing the namespace WWID through sysfs, from Keith. - Set of cleanups from Ming Lin. - Logging the controller device name instead of the underlying PCI device name, from Sagi. - And a bunch of fixes and optimizations from the usual suspects in this area" * 'for-4.6/drivers' of git://git.kernel.dk/linux-block: (49 commits) NVMe: Expose ns wwid through single sysfs entry drivers:block: cpqarray clean up brd: Fix discard request processing cpqarray: remove it from the kernel cciss: update MAINTAINERS NVMe: Remove unused sq_head read in completion path bcache: fix cache_set_flush() NULL pointer dereference on OOM bcache: cleaned up error handling around register_cache() bcache: fix race of writeback thread starting before complete initialization NVMe: Create discard zero quirk white list nbd: use correct div_s64 helper mtip32xx: remove unneeded variable in mtip_cmd_timeout() lightnvm: generalize rrpc ppa calculations lightnvm: remove struct nvm_dev->total_blocks lightnvm: rename ->nr_pages to ->nr_sects lightnvm: update closed list outside of intr context xen/blback: Fit the important information of the thread in 17 characters lightnvm: fold get bb tbl when using dual/quad plane mode lightnvm: fix up nonsensical configure overrun checking xen-blkback: advertise indirect segment support earlier ...
2016-03-16NVMe: Expose ns wwid through single sysfs entryKeith Busch
The method to uniquely identify a namespace depends on the controller's specification revision level and implemented capabilities. This patch has the driver figure this out and exports the unique string through a single 'wwid' attribute so the user doesn't have this burden. The longest namespace unique identifier is used if available. If not available, the driver will concat the controller's vendor, serial, and model with the namespace ID. The specification provides this as a unique indentifier. Signed-off-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-03-08NVMe: Remove unused sq_head read in completion pathJon Derrick
Signed-off-by: Jon Derrick <jonathan.derrick@intel.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-03-08NVMe: Create discard zero quirk white listKeith Busch
The NVMe specification does not require discarded blocks return zeroes on read, but provides that behavior as a possibility. Some applications more efficiently use an SSD if reads on discarded blocks were deterministically zero, based on the "discard_zeroes_data" queue attribute. There is no specification defined way to determine device behavior on discarded blocks, so the driver always left the queue setting disabled. We can only know behavior based on individual device models, so this patch adds a flag to the NVMe "quirk" list that vendors may set if they know their controller works that way. The patch also sets the new flag for one such known device. Signed-off-by: Keith Busch <keith.busch@intel.com> Suggested-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Jens Axboe <axboe@fb.com>