- 29 8月, 2017 12 次提交
-
-
由 Sagi Grimberg 提交于
If we move the queues from LIVE state, we might as well stop them (drain for rdma). Do it after we stop the request queues to prevent a stray request sneaking in .queue_rq after we stop the queue. Signed-off-by: NSagi Grimberg <sagi@grimberg.me> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
由 Sagi Grimberg 提交于
Make a symmetrical handling with admin queue. Signed-off-by: NSagi Grimberg <sagi@grimberg.me> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
由 Sagi Grimberg 提交于
No need to open-code it. Signed-off-by: NSagi Grimberg <sagi@grimberg.me> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
由 Sagi Grimberg 提交于
We're not supposed to do that. Signed-off-by: NSagi Grimberg <sagi@grimberg.me> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
由 Sagi Grimberg 提交于
Mimic the pci driver as a controller disable might be more lightweight than a shutdown. Signed-off-by: NSagi Grimberg <sagi@grimberg.me> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
由 Sagi Grimberg 提交于
We always pair tagset allocation with rdma device reference and it shares some code, centralize it with an argument if its an admin or IO tagset. Signed-off-by: NSagi Grimberg <sagi@grimberg.me> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
由 Sagi Grimberg 提交于
Will be used when we centralize control flows. Signed-off-by: NSagi Grimberg <sagi@grimberg.me> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
由 Sagi Grimberg 提交于
We will call it from other places so avoid having to forward declare it. Also move it next to nvme_rdma_destroy_admin_queue. Signed-off-by: NSagi Grimberg <sagi@grimberg.me> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
由 Johannes Thumshirn 提交于
NVME_RDMA_MAX_SEGMENT_SIZE is not used anywhere, zap it. Signed-off-by: NJohannes Thumshirn <jthumshirn@suse.de> Reviewed-by: NMax Gurtovoy <maxg@mellanox.com> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
由 Jon Derrick 提交于
NVME's Timestamp feature allows controllers to be aware of the epoch time in milliseconds. This patch adds the set features hook for various transports through the identify path, so that resets and resumes can update the controller as necessary. Signed-off-by: NJon Derrick <jonathan.derrick@intel.com> [hch: rebased on top of nvme-4.13 error handling changes, changed nvme_configure_timestamp to return the status] Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
由 Arnav Dawn 提交于
Define the constant "0xffffffff" (used as nsid for all namespaces) as NVME_NSID_ALL. Signed-off-by: NArnav Dawn <a.dawn@samsung.com> Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
-
由 Arnav Dawn 提交于
This patch adds support for handling Fw activation without reset On completion of FW-activation-starting AER, all queues are paused till CSTS.PP is cleared or timed out (exceeds max time for fw activtion MTFA). If device fails to clear CSTS.PP within MTFA, driver issues reset controller. Signed-off-by: NArnav Dawn <a.dawn@samsung.com> Reviewed-by: NKeith Busch <keith.busch@intel.com> Reviewed-by: NChristoph Hellwig <hch@lst.de> Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
-
- 24 8月, 2017 1 次提交
-
-
由 Christoph Hellwig 提交于
This way we don't need a block_device structure to submit I/O. The block_device has different life time rules from the gendisk and request_queue and is usually only available when the block device node is open. Other callers need to explicitly create one (e.g. the lightnvm passthrough code, or the new nvme multipathing code). For the actual I/O path all that we need is the gendisk, which exists once per block device. But given that the block layer also does partition remapping we additionally need a partition index, which is used for said remapping in generic_make_request. Note that all the block drivers generally want request_queue or sometimes the gendisk, so this removes a layer of indirection all over the stack. Signed-off-by: NChristoph Hellwig <hch@lst.de> Signed-off-by: NJens Axboe <axboe@kernel.dk>
-
- 18 8月, 2017 3 次提交
-
-
由 Bart Van Assche 提交于
Since blk_mq_ops.reinit_request is only called from inside blk_mq_reinit_tagset(), make this function pointer an argument of blk_mq_reinit_tagset() instead of a member of struct blk_mq_ops. This patch does not change any functionality but makes blk_mq_reinit_tagset() calls easier to read and to analyze. Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com> Reviewed-by: NHannes Reinecke <hare@suse.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Sagi Grimberg <sagi@grimberg.me> Cc: James Smart <james.smart@broadcom.com> Cc: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: NJens Axboe <axboe@kernel.dk>
-
由 Keith Busch 提交于
Fixes: 920d13a8 ("nvme-pci: factor out the cqe reading mechanics from __nvme_process_cq") Reported-by: NJens Axboe <axboe@kernel.dk> Signed-off-by: NKeith Busch <keith.busch@intel.com> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
由 Christoph Hellwig 提交于
Only print the specified options that are not recognized, instead of the whole list of options. Signed-off-by: NChristoph Hellwig <hch@lst.de> Reviewed-by: NMax Gurtovoy <maxg@mellanox.com>
-
- 11 8月, 2017 2 次提交
-
-
由 Kwan (Hingkwan) Huen-SSI 提交于
The numd field of directive receive command takes number of dwords to transfer. This fix has the correct calculation for numd. Signed-off-by: NKwan (Hingkwan) Huen-SSI <kwan.huen@samsung.com> Reviewed-by: NJens Axboe <axboe@kernel.dk> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
由 Keith Busch 提交于
We need to return an error if a timeout occurs on any NVMe command during initialization. Without this, the nvme reset work will be stuck. A timeout will have a negative error code, meaning we need to stop initializing the controller. All postitive returns mean the controller is still usable. bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196325Signed-off-by: NKeith Busch <keith.busch@intel.com> Cc: Martin Peres <martin.peres@intel.com> [jth consolidated cleanup path ] Signed-off-by: NJohannes Thumshirn <jthumshirn@suse.de> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
- 10 8月, 2017 2 次提交
-
-
由 Max Gurtovoy 提交于
Currently we create the sysfs entry even if we fail mapping it. In that case, the unmapping will not remove the sysfs created file. There is no good reason to create a sysfs entry for a non working CMB and show his characteristics. Fixes: f63572df ("nvme: unmap CMB and remove sysfs file in reset path") Signed-off-by: NMax Gurtovoy <maxg@mellanox.com> Reviewed-by: NStephen Bates <sbates@raithlin.com> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
由 Martin Wilck 提交于
Some broken controllers (such as earlier Linux targets) pad model or serial fields with 0-bytes rather than spaces. The NVMe spec disallows 0 bytes in "ASCII" fields. Thus strip trailing 0-bytes, too. Also make sure that we get no underflow for pathological input. Signed-off-by: NMartin Wilck <mwilck@suse.com> Reviewed-by: NHannes Reinecke <hare@suse.de> Reviewed-by: NKeith Busch <keith.busch@intel.com> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
- 26 7月, 2017 3 次提交
-
-
由 Scott Bauer 提交于
With a misbehaving controller it's possible we'll never enter the live state and create an admin queue. When we fail out of reset work it's possible we failed out early enough without setting up the admin queue. We tear down queues after a failed reset, but needed to do some more sanitization. Fixes 443bd90f: "nvme: host: unquiesce queue in nvme_kill_queues()" [ 189.650995] nvme nvme1: pci function 0000:0b:00.0 [ 317.680055] nvme nvme0: Device not ready; aborting reset [ 317.680183] nvme nvme0: Removing after probe failure status: -19 [ 317.681258] kasan: GPF could be caused by NULL-ptr deref or user memory access [ 317.681397] general protection fault: 0000 [#1] SMP KASAN [ 317.682984] CPU: 3 PID: 477 Comm: kworker/3:2 Not tainted 4.13.0-rc1+ #5 [ 317.683112] Hardware name: Gigabyte Technology Co., Ltd. Z170X-UD5/Z170X-UD5-CF, BIOS F5 03/07/2016 [ 317.683284] Workqueue: events nvme_remove_dead_ctrl_work [nvme] [ 317.683398] task: ffff8803b0990000 task.stack: ffff8803c2ef0000 [ 317.683516] RIP: 0010:blk_mq_unquiesce_queue+0x2b/0xa0 [ 317.683614] RSP: 0018:ffff8803c2ef7d40 EFLAGS: 00010282 [ 317.683716] RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 1ffff1006fbdcde3 [ 317.683847] RDX: 0000000000000038 RSI: 1ffff1006f5a9245 RDI: 0000000000000000 [ 317.683978] RBP: ffff8803c2ef7d58 R08: 1ffff1007bcdc974 R09: 0000000000000000 [ 317.684108] R10: 1ffff1007bcdc975 R11: 0000000000000000 R12: 00000000000001c0 [ 317.684239] R13: ffff88037ad49228 R14: ffff88037ad492d0 R15: ffff88037ad492e0 [ 317.684371] FS: 0000000000000000(0000) GS:ffff8803de6c0000(0000) knlGS:0000000000000000 [ 317.684519] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 317.684627] CR2: 0000002d1860c000 CR3: 000000045b40d000 CR4: 00000000003406e0 [ 317.684758] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 317.684888] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 317.685018] Call Trace: [ 317.685084] nvme_kill_queues+0x4d/0x170 [nvme_core] [ 317.685185] nvme_remove_dead_ctrl_work+0x3a/0x90 [nvme] [ 317.685289] process_one_work+0x771/0x1170 [ 317.685372] worker_thread+0xde/0x11e0 [ 317.685452] ? pci_mmcfg_check_reserved+0x110/0x110 [ 317.685550] kthread+0x2d3/0x3d0 [ 317.685617] ? process_one_work+0x1170/0x1170 [ 317.685704] ? kthread_create_on_node+0xc0/0xc0 [ 317.685785] ret_from_fork+0x25/0x30 [ 317.685798] Code: 0f 1f 44 00 00 55 48 b8 00 00 00 00 00 fc ff df 48 89 e5 41 54 4c 8d a7 c0 01 00 00 53 48 89 fb 4c 89 e2 48 c1 ea 03 48 83 ec 08 <80> 3c 02 00 75 50 48 8b bb c0 01 00 00 e8 33 8a f9 00 0f ba b3 [ 317.685872] RIP: blk_mq_unquiesce_queue+0x2b/0xa0 RSP: ffff8803c2ef7d40 [ 317.685908] ---[ end trace a3f8704150b1e8b4 ]--- Signed-off-by: NScott Bauer <scott.bauer@intel.com> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
由 Christoph Hellwig 提交于
It's possible the preferred HMB size may not be a multiple of the chunk_size. This patch moves len to function scope and uses that in the for loop increment so the last iteration doesn't cause the total size to exceed the allocated HMB size. Based on an earlier patch from Keith Busch. Signed-off-by: NChristoph Hellwig <hch@lst.de> Reported-by: NDan Carpenter <dan.carpenter@oracle.com> Reviewed-by: NKeith Busch <keith.busch@intel.com> Fixes: 87ad72a5 ("nvme-pci: implement host memory buffer support")
-
由 James Smart 提交于
The FC-NVME spec hasn't locked down on the format string for TRADDR. Currently the spec is lobbying for "nn-<16hexdigits>:pn-<16hexdigits>" where the wwn's are hex values but not prefixed by 0x. Most implementations so far expect a string format of "nn-0x<16hexdigits>:pn-0x<16hexdigits>" to be used. The transport uses the match_u64 parser which requires a leading 0x prefix to set the base properly. If it's not there, a match will either fail or return a base 10 value. The resolution in T11 is pushing out. Therefore, to fix things now and to cover any eventuality and any implementations already in the field, this patch adds support for both formats. The change consists of replacing the token matching routine with a routine that validates the fixed string format, and then builds a local copy of the hex name with a 0x prefix before calling the system parser. Note: the same parser routine exists in both the initiator and target transports. Given this is about the only "shared" item, we chose to replicate rather than create an interdendency on some shared code. Signed-off-by: NJames Smart <james.smart@broadcom.com> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
- 25 7月, 2017 2 次提交
-
-
由 James Smart 提交于
There are cases where threads are in the process of submitting new io when the LLDD calls in to remove the remote port. In some cases, the next io actually goes to the LLDD, who knows the remoteport isn't present and rejects it. To properly recovery/restart these i/o's we don't want to hard fail them, we want to treat them as temporary resource errors in which a delayed retry will work. Add a couple more checks on remoteport connectivity and commonize the busy response handling when it's seen. Signed-off-by: NJames Smart <james.smart@broadcom.com> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
由 Johannes Thumshirn 提交于
The WWID sysfs attribute can provide multiple means of a World Wide ID for a NVMe device. It can either be a NGUID, a EUI-64 or a concatenation of VID, Serial Number, Model and the Namespace ID in this order of preference. If the target also sends us a UUID use the UUID for identification and give it the highest priority. This eases generation of /dev/disk/by-* symlinks. Signed-off-by: NJohannes Thumshirn <jthumshirn@suse.de> Signed-off-by: NChristoph Hellwig <hch@lst.de>
-
- 20 7月, 2017 4 次提交
-
-
由 Christophe JAILLET 提交于
Release resources in the correct order in order not to miss a 'put_device()' if 'nvme_dev_map()' fails. Fixes: b00a726a ("NVMe: Don't unmap controller registers on reset") Signed-off-by: NChristophe JAILLET <christophe.jaillet@wanadoo.fr> Reviewed-by: NKeith Busch <keith.busch@intel.com> Signed-off-by: NChristoph Hellwig <hch@lst.de> Signed-off-by: NJens Axboe <axboe@kernel.dk>
-
由 Keith Busch 提交于
This patch replaces the invalid nvme SGL kernel panic with a warning, and returns an appropriate error. The warning will occur only on the first occurance, and sgl details will be printed to help debug how the request was allowed to form. Signed-off-by: NKeith Busch <keith.busch@intel.com> Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de> Reviewed-by: NChristoph Hellwig <hch@lst.de> Signed-off-by: NSagi Grimberg <sagi@grimberg.me> Signed-off-by: NJens Axboe <axboe@kernel.dk>
-
由 David Wayne Fugate 提交于
Adds a fourth Intel controller which has the "stripe" quirk. Signed-off-by: NDavid Wayne Fugate <david.fugate@intel.com> Acked-by: NKeith Busch <keith.busch@intel.com> Acked-by: NChristoph Hellwig <hch@lst.de> Signed-off-by: NSagi Grimberg <sagi@grimberg.me> Signed-off-by: NJens Axboe <axboe@kernel.dk>
-
由 Christoph Hellwig 提交于
Signed-off-by: NChristoph Hellwig <hch@lst.de> Reviewed-by: NJens Axboe <axboe@kernel.dk> Signed-off-by: NJens Axboe <axboe@kernel.dk>
-
- 10 7月, 2017 2 次提交
-
-
由 weiping zhang 提交于
Adjust io queue depth more easily, and make sure io queue depth >= 2. Signed-off-by: Nweiping zhang <zhangweiping@didichuxing.com> Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
-
由 Dan Carpenter 提交于
"i" should be signed or it could cause a forever loop on the cleanup path. "size" can be used uninitialized. Fixes: 87ad72a5 ("nvme-pci: implement host memory buffer support") Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com> Reviewed-by: NChristoph Hellwig <hch@lst.de> Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
-
- 06 7月, 2017 7 次提交
-
-
由 Sagi Grimberg 提交于
When our RDMA queue-pair is torn down with high load of I/O traffic, we have no way of knowing if the memory region was actually registered by the reg_mr work request as it completion flushes with error (hw might have done it or not). So in order to not deal with all this uncertanty, we simply recycle the MR in reinit_request. Reviewed-by: NChristoph Hellwig <hch@lst.de> Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
-
由 Sagi Grimberg 提交于
Usually before we teardown the controller we want to: 1. complete/cancel any ctrl inflight works 2. remove ctrl namespaces (only for removal though, resets shouldn't remove any namespaces). but we do not want to destroy the controller device as we might use it for logging during the teardown stage. This patch adds nvme_start_ctrl() which queues inflight controller works (aen, ns scan, queue start and keep-alive if kato is set) and nvme_stop_ctrl() which cancels the works namespace removal is left to the callers to handle. Move nvme_uninit_ctrl after we are done with the controller device. Reviewed-by: NKeith Busch <keith.busch@intel.com> Reviewed-by: NChristoph Hellwig <hch@lst.de> Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
-
由 Sagi Grimberg 提交于
When we requeue a request, we can always insert the request back to the scheduler instead of doing it when restarting the queues and kicking the requeue work, so get rid of the requeue kick in nvme (core and drivers). Also, now there is no need start hw queues in nvme_kill_queues We don't stop the hw queues anymore, so no need to start them. Reviewed-by: NMing Lei <ming.lei@redhat.com> Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
-
由 Sagi Grimberg 提交于
unlike blk_mq_stop_hw_queues and blk_mq_start_stopped_hw_queues quiescing/unquiescing respects the submission path rcu grace. Reviewed-by: NMing Lei <ming.lei@redhat.com> Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
-
由 Sagi Grimberg 提交于
unlike blk_mq_stop_hw_queues and blk_mq_start_stopped_hw_queues quiescing/unquiescing respects the submission path rcu grace. Also, make sure to unquiesce before cleanup the admin queue. Reviewed-by: NMing Lei <ming.lei@redhat.com> Reviewed-By: NJames Smart <james.smart@broadcom.com> Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
-
由 Sagi Grimberg 提交于
unlike blk_mq_stop_hw_queues and blk_mq_start_stopped_hw_queues quiescing/unquiescing respects the submission path rcu grace. Also make sure to kick the requeue list when appropriate. Reviewed-by: NMing Lei <ming.lei@redhat.com> Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
-
由 Marta Rybczynska 提交于
This patch improves the way the RDMA IB signalling is done by using atomic operations for the signalling variable. This avoids race conditions on sig_count. The signalling interval changes slightly and is now the largest power of two not larger than queue depth / 2. ilog() usage idea by Bart Van Assche. Signed-off-by: NMarta Rybczynska <marta.rybczynska@kalray.eu> Reviewed-by: NSagi Grimberg <sagi@grimberg.me> Signed-off-by: NChristoph Hellwig <hch@lst.de> Cc: stable@vger.kernel.org
-
- 04 7月, 2017 2 次提交
-
-
由 Sagi Grimberg 提交于
Cc: James Smart <james.smart@broadcom.com> Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
-
由 Sagi Grimberg 提交于
We might have more/less queues once we reconnect/reset. For example due to cpu going online/offline or controller constraints. Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de> Reviewed-by: NChristoph Hellwig <hch@lst.de> Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
-