- 11 Feb, 2021 1 commit
-
-
Sagi Grimberg authored
write-zeros has a bio, but does not have any data buffers associated with it. Hence should not initialize the request iter for it (which attempts to reference the bi_io_vec (and crash). -- run blktests nvme/012 at 2021-02-05 21:53:34 BUG: kernel NULL pointer dereference, address: 0000000000000008 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP NOPTI CPU: 15 PID: 12069 Comm: kworker/15:2H Tainted: G S I 5.11.0-rc6+ #1 Hardware name: Dell Inc. PowerEdge R640/06NR82, BIOS 2.10.0 11/12/2020 Workqueue: kblockd blk_mq_run_work_fn RIP: 0010:nvme_tcp_init_iter+0x7d/0xd0 [nvme_tcp] RSP: 0018:ffffbd084447bd18 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffffa0bba9f3ce80 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000002000000 RBP: ffffa0ba8ac6fec0 R08: 0000000002000000 R09: 0000000000000000 R10: 0000000002800809 R11: 0000000000000000 R12: 0000000000000000 R13: ffffa0bba9f3cf90 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffffa0c9ff9c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 00000001c9c6c005 CR4: 00000000007706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: nvme_tcp_queue_rq+0xef/0x330 [nvme_tcp] blk_mq_dispatch_rq_list+0x11c/0x7c0 ? blk_mq_flush_busy_ctxs+0xf6/0x110 __blk_mq_sched_dispatch_requests+0x12b/0x170 blk_mq_sched_dispatch_requests+0x30/0x60 __blk_mq_run_hw_queue+0x2b/0x60 process_one_work+0x1cb/0x360 ? process_one_work+0x360/0x360 worker_thread+0x30/0x370 ? process_one_work+0x360/0x360 kthread+0x116/0x130 ? kthread_park+0x80/0x80 ret_from_fork+0x1f/0x30 -- Fixes: cb9b870f ("nvme-tcp: fix wrong setting of request iov_iter") Reported-by:
Yi Zhang <yi.zhang@redhat.com> Signed-off-by:
Sagi Grimberg <sagi@grimberg.me> Reviewed-by:
Keith Busch <kbusch@kernel.org> Reviewed-by:
Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Tested-by:
Christoph Hellwig <hch@lst.de>
-
- 10 Feb, 2021 27 commits
-
-
Filippo Sironi authored
Some Amazon NVMe controllers do not follow the NVMe specification and are limited to 48-bit DMA addresses. Add a quirk to force bounce buffering if needed and limit the IOVA allocation for these devices. This affects all current Amazon NVMe controllers that expose EBS volumes (0x0061, 0x0065, 0x8061) and local instance storage (0xcd00, 0xcd01, 0xcd02). Signed-off-by:
Filippo Sironi <sironi@amazon.de> Signed-off-by:
-
Hannes Reinecke authored
The original design to use device-managed resource allocation doesn't really work as the NVMe controller has a vastly different lifetime than the hwmon sysfs attributes, causing warning about duplicate sysfs entries upon reconnection. This patch reworks the hwmon allocation to avoid device-managed resource allocation, and uses the NVMe controller as parent for the sysfs attributes. Cc: Guenter Roeck <linux@roeck-us.net> Signed-off-by:
Hannes Reinecke <hare@suse.de> Tested-by:
Enzo Matsumiya <ematsumiya@suse.de> Tested-by:
Daniel Wagner <dwagner@suse.de> Signed-off-by:
-
Chaitanya Kulkarni authored
The function nvmet_parse_io_cmd() returns value from nvmet_file_parse_io_cmd() or nvmet_bdev_parse_io_cmd() based on which backend is set for the request. Remove the else and just return the value from nvmet_bdev_parse_io_cmd(). Signed-off-by:
-
Chaitanya Kulkarni authored
Just like what we have to get the passthru ctrl from the req, add an helper to get the subsystem associated with the nvmet_req() instead of open coding the chain of structures. Signed-off-by:
-
Chaitanya Kulkarni authored
In function __assign_req_name() instead of using the DEVICE_NAME_LEN in strncpy() use min of DISK_NAME_LEN and strlen(req->ns->device_path). This is needed to turn off the following warnings:- In file included from drivers/nvme/target/core.c:14: In function ‘__assign_req_name’, inlined from ‘trace_event_raw_event_nvmet_req_init’ at drivers/nvme/target/./trace.h:58:1: drivers/nvme/target/trace.h:52:3: warning: ‘strncpy’ specified bound 32 equals destination size [-Wstringop-truncation] strncpy(name, req->ns->device_path, DISK_NAME_LEN); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In function ‘__assign_req_name’, inlined from ‘perf_trace_nvmet_req_complete’ at drivers/nvme/target/./trace.h:100:1: drivers/nvme/target/trace.h:52:3: warning: ‘strncpy’ specified bound 32 equals destination size [-Wstringop-truncation] strncpy(name, req->ns->device_path, DISK_NAME_LEN); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In function ‘__assign_req_name’, inlined from ‘perf_trace_nvmet_req_init’ at drivers/nvme/target/./trace.h:58:1: drivers/nvme/target/trace.h:52:3: warning: ‘strncpy’ specified bound 32 equals destination size [-Wstringop-truncation] strncpy(name, req->ns->device_path, DISK_NAME_LEN); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In function ‘__assign_req_name’, inlined from ‘trace_event_raw_event_nvmet_req_complete’ at drivers/nvme/target/./trace.h:100:1: drivers/nvme/target/trace.h:52:3: warning: ‘strncpy’ specified bound 32 equals destination size [-Wstringop-truncation] strncpy(name, req->ns->device_path, DISK_NAME_LEN); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: -
Chaitanya Kulkarni authored
In the NVMeOF block device backend, file backend, and passthru backend we reject and report the commands if opcode is not handled. Use the previously introduced helper in the passthru backend to make the error message uniform. Signed-off-by:
-
Chaitanya Kulkarni authored
In the NVMeOF block device backend, file backend, and passthru backend we reject and report the commands if opcode is not handled. Use the previously introduced helper in file backend to reduce the duplicate code and make the error message uniform. Signed-off-by:
-
Chaitanya Kulkarni authored
In the NVMeOF block device backend, file backend, and passthru backend we reject and report the commands if opcode is not handled. Add an helper and use it in block device backend to keep the code and error message uniform. Signed-off-by:
-
Chaitanya Kulkarni authored
In nvmet_execute_identify_ns() local variable ctrl is accessed only in one place, remove that and directly use it from nvmet_req->sq->ctrl. Signed-off-by:
-
Chaitanya Kulkarni authored
The six callers of nvmet_find_namespace() duplicate the error log page update and status setting code for each call on failure. All callers are nvmet requests based functions, so we can pass req to the nvmet_find_namesapce() & derive ctrl from req, that'll allow us to update the error log page in nvmet_find_namespace(). Now that we pass the request we can also get rid of the local variable in nvmet_find_namespace() and use the req->ns and return the error code. Replace the ctrl parameter with nvmet_req for nvmet_find_namespace(), centralize the error log page update for non allocated namesapces, and return uniform error for non-allocated namespace. The nvmet_find_namespace() takes nsid parameter which is from NVMe commands structures such as get_log_page, identify, rw and common. All these commands have same offset for the nsid field. Derive nsid from req->cmd->common.nsid) & remove the extra parameter from the nvmet_find_namespace(). Lastly now we associate the ns to the req parameter that we pass to the nvmet_find_namespace(), rename nvmet_find_namespace() to nvmet_req_find_ns(). Signed-off-by:
-
Chaitanya Kulkarni authored
For nvmet_find_namespace() error case we have inconsistent error code mapping in the function nvmet_get_smart_log_nsid() and nvmet_set_feat_write_protect(). There is no point in retrying for the invalid namesapce from the host side. Set the error code to the NVME_SC_INVALID_NS | NVME_SC_DNR which matches what we have in nvmet_execute_identify_desclist(). Signed-off-by:
-
Chaitanya Kulkarni authored
For unallocated namespace in nvmet_execute_identify_ns() don't set the status to NVME_SC_INVALID_NS, set it to zero. Fixes: bffcd507 ("nvmet: set right status on error in id-ns handler") Signed-off-by:
-
Christoph Hellwig authored
Make sparse happy after the recent conversion to RCU lookups. Fixes: 4e2f02bf ("nvmet-fc: use RCU proctection for assoc_list") Signed-off-by:
James Smart <james.smart@broadcom.com>
-
Keith Busch authored
The bio based drivers only require the request_queue's nr_zones is set, so set this field in the head if the namespace path is zoned. Fixes: 240e6ee2 ("nvme: support for zoned namespaces") Reported-by:
Minwoo Im <minwoo.im.dev@gmail.com> Cc: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by:
-
Sagi Grimberg authored
When we accept a TCP connection and allocate an nvmet-tcp queue we should make sure not to fully establish it or reference it as the connection may be already closing, which triggers queue release work, which does not fence against queue establishment. In order to address such a race, we make sure to check the sk_state and contain the queue reference to be done underneath the sk_callback_lock such that the queue release work correctly fences against it. Fixes: 872d26a3 ("nvmet-tcp: add NVMe over TCP target driver") Reported-by:
Elad Grupi <elad.grupi@dell.com> Signed-off-by:
-
Sagi Grimberg authored
When a host sends multiple h2cdata PDUs for a single command, we should verify the data digest calculation per PDU and not per command. Fixes: 872d26a3 ("nvmet-tcp: add NVMe over TCP target driver") Reported-by:
Narayan Ayalasomayajula <Narayan.Ayalasomayajula@wdc.com> Tested-by:
-
Chao Leng authored
nvme_rdma_post_send failing is a path related error and should bounce to another path when using nvme-multipath. Call nvme_host_path_error when nvme_rdma_post_send returns -EIO to ensure nvme_complete_rq gets invoked to fail over to another path if there is one. Signed-off-by:
Chao Leng <lengchao@huawei.com> Signed-off-by:
-
Chao Leng authored
When reconnecting, the request may be completed with NVME_SC_HOST_PATH_ERROR in nvmf_fail_nonready_command, which currently set the state of the request to MQ_RQ_IN_FLIGHT before calling nvme_complete_rq. When this happens for a request that is freed by the caller, such as nvme_submit_user_cmd, in the worst case the request could be completed again in tear down process. Instead of calling blk_mq_start_request from nvmf_fail_nonready_command, just use the new nvme_host_path_error helper to complete the command without starting it. Signed-off-by:
-
Chao Leng authored
When using nvme native multipathing, if a path related error occurs during ->queue_rq, the request needs to be completed with NVME_SC_HOST_PATH_ERROR so that the request can be failed over. Introduce a helper to complete the command from ->queue_rq in a wait that invokes nvme_complete_rq. Signed-off-by:
-
Chao Leng authored
nvme drivers need to set the state of request to MQ_RQ_COMPLETE when directly complete request in queue_rq. So add blk_mq_set_request_complete. Signed-off-by:
-
Jiapeng Chong authored
Fix the following coccicheck warning: ./drivers/nvme/host/core.c:3580:8-16: WARNING: use scnprintf or sprintf. ./drivers/nvme/host/core.c:3570:8-16: WARNING: use scnprintf or sprintf. ./drivers/nvme/host/core.c:3560:8-16: WARNING: use scnprintf or sprintf. ./drivers/nvme/host/core.c:3526:8-16: WARNING: use scnprintf or sprintf. ./drivers/nvme/host/core.c:2833:8-16: WARNING: use scnprintf or sprintf. Reported-by: Abaci Robot<abaci@linux.alibaba.com> Signed-off-by:
Jiapeng Chong <jiapeng.chong@linux.alibaba.com> Reviewed-by:
-
Joe Perches authored
Use semicolons and braces. Signed-off-by:
Joe Perches <joe@perches.com> Signed-off-by:
Coly Li <colyli@suse.de> Signed-off-by:
Jens Axboe <axboe@kernel.dk>
-
Kai Krakow authored
This is potentially long running and not latency sensitive, let's get it out of the way of other latency sensitive events. As observed in the previous commit, the `system_wq` comes easily congested by bcache, and this fixes a few more stalls I was observing every once in a while. Let's not make this `WQ_MEM_RECLAIM` as it showed to reduce performance of boot and file system operations in my tests. Also, without `WQ_MEM_RECLAIM`, I no longer see desktop stalls. This matches the previous behavior as `system_wq` also does no memory reclaim: > // workqueue.c: > system_wq = alloc_workqueue("events", 0, 0); Cc: Coly Li <colyli@suse.de> Cc: stable@vger.kernel.org # 5.4+ Signed-off-by:Kai Krakow <kai@kaishome.de> Signed-off-by:
-
Kai Krakow authored
Before killing `btree_io_wq`, the queue was allocated using `create_singlethread_workqueue()` which has `WQ_MEM_RECLAIM`. After killing it, it no longer had this property but `system_wq` is not single threaded. Let's combine both worlds and make it multi threaded but able to reclaim memory. Cc: Coly Li <colyli@suse.de> Cc: stable@vger.kernel.org # 5.4+ Signed-off-by:
-
Kai Krakow authored
This reverts commit 56b30770. With the btree using the `system_wq`, I seem to see a lot more desktop latency than I should. After some more investigation, it looks like the original assumption of 56b30770 no longer is true, and bcache has a very high potential of congesting the `system_wq`. In turn, this introduces laggy desktop performance, IO stalls (at least with btrfs), and input events may be delayed. So let's revert this. It's important to note that the semantics of using `system_wq` previously mean that `btree_io_wq` should be created before and destroyed after other bcache wqs to keep the same assumptions. Cc: Coly Li <colyli@suse.de> Cc: stable@vger.kernel.org # 5.4+ Signed-off-by:
-
Kai Krakow authored
Should be `register_device_async`. Cc: Coly Li <colyli@suse.de> Signed-off-by:
-
dongdong tao authored
Current way to calculate the writeback rate only considered the dirty sectors, this usually works fine when the fragmentation is not high, but it will give us unreasonable small rate when we are under a situation that very few dirty sectors consumed a lot dirty buckets. In some case, the dirty bucekts can reached to CUTOFF_WRITEBACK_SYNC while the dirty data(sectors) not even reached the writeback_percent, the writeback rate will still be the minimum value (4k), thus it will cause all the writes to be stucked in a non-writeback mode because of the slow writeback. We accelerate the rate in 3 stages with different aggressiveness, the first stage starts when dirty buckets percent reach above BCH_WRITEBACK_FRAGMENT_THRESHOLD_LOW (50), the second is BCH_WRITEBACK_FRAGMENT_THRESHOLD_MID (57), the third is BCH_WRITEBACK_FRAGMENT_THRESHOLD_HIGH (64). By default the first stage tries to writeback the amount of dirty data in one bucket (on average) in (1 / (dirty_buckets_percent - 50)) second, the second stage tries to writeback the amount of dirty data in one bucket in (1 / (dirty_buckets_percent - 57)) * 100 millisecond, the third stage tries to writeback the amount of dirty data in one bucket in (1 / (dirty_buckets_percent - 64)) millisecond. the initial rate at each stage can be controlled by 3 configurable parameters writeback_rate_fp_term_{low|mid|high}, they are by default 1, 10, 1000, the hint of IO throughput that these values are trying to achieve is described by above paragraph, the reason that I choose those value as default is based on the testing and the production data, below is some details: A. When it comes to the low stage, there is still a bit far from the 70 threshold, so we only want to give it a little bit push by setting the term to 1, it means the initial rate will be 170 if the fragment is 6, it is calculated by bucket_size/fragment, this rate is very small, but still much reasonable than the minimum 8. For a production bcache with unheavy workload, if the cache device is bigger than 1 TB, it may take hours to consume 1% buckets, so it is very possible to reclaim enough dirty buckets in this stage, thus to avoid entering the next stage. B. If the dirty buckets ratio didn't turn around during the first stage, it comes to the mid stage, then it is necessary for mid stage to be more aggressive than low stage, so i choose the initial rate to be 10 times more than low stage, that means 1700 as the initial rate if the fragment is 6. This is some normal rate we usually see for a normal workload when writeback happens because of writeback_percent. C. If the dirty buckets ratio didn't turn around during the low and mid stages, it comes to the third stage, and it is the last chance that we can turn around to avoid the horrible cutoff writeback sync issue, then we choose 100 times more aggressive than the mid stage, that means 170000 as the initial rate if the fragment is 6. This is also inferred from a production bcache, I've got one week's writeback rate data from a production bcache which has quite heavy workloads, again, the writeback is triggered by the writeback percent, the highest rate area is around 100000 to 240000, so I believe this kind aggressiveness at this stage is reasonable for production. And it should be mostly enough because the hint is trying to reclaim 1000 bucket per second, and from that heavy production env, it is consuming 50 bucket per second on average in one week's data. Option writeback_consider_fragment is to control whether we want this feature to be on or off, it's on by default. Lastly, below is the performance data for all the testing result, including the data from production env: https://docs.google.com/document/d/1AmbIEa_2MhB9bqhC3rfga9tp7n9YX9PLn0jSUxscVW0/edit?usp=sharingSigned-off-by:dongdong tao <dongdong.tao@canonical.com> Signed-off-by:
-
- 04 Feb, 2021 5 commits
-
-
Damien Le Moal authored
The STEC S1220 PCIe SSD cards are EOL since 2014 and not supported by the vendor anymore. As the skd driver for this SSD is starting to cause problems with improvements to the block layer, stop supporting it in newer kernel versions. Signed-off-by:
Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by:
-
Jens Axboe authored
Merge branch 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-5.12/drivers Pull MD fix from Song. * 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md: md/raid5: cast chunk_sectors to sector_t value
-
https://github.com/evdenis/linux-floppyJens Axboe authored
Pull floppy fix from Denis: "Floppy patch for 5.12 - O_NDELAY/O_NONBLOCK fix for floppy from Jiri Kosina. libblkid is using O_NONBLOCK when probing devices. This leads to pollution of kernel log with error messages from floppy driver. Also the driver fails a mount prior to being opened without O_NONBLOCK at least once. The patch fixes the issues." Signed-off-by:
Denis Efremov <efremov@linux.com> * tag 'floppy-for-5.12' of https://github.com/evdenis/linux-floppy: floppy: reintroduce O_NDELAY fix
-
Jiri Kosina authored
This issue was originally fixed in 09954bad ("floppy: refactor open() flags handling"). The fix as a side-effect, however, introduce issue for open(O_ACCMODE) that is being used for ioctl-only open. I wrote a fix for that, but instead of it being merged, full revert of 09954bad was performed, re-introducing the O_NDELAY / O_NONBLOCK issue, and it strikes again. This is a forward-port of the original fix to current codebase; the original submission had the changelog below: ==== Commit 09954bad ("floppy: refactor open() flags handling"), as a side-effect, causes open(/dev/fdX, O_ACCMODE) to fail. It turns out that this is being used setfdprm userspace for ioctl-only open(). Reintroduce back the original behavior wrt !(FMODE_READ|FMODE_WRITE) modes, while still keeping the original O_NDELAY bug fixed. Link: https://lore.kernel.org/r/nycvar.YFH.7.76.2101221209060.5622@cbobk.fhfr.pm Cc: stable@vger.kernel.org Reported-by:
Wim Osterholt <wim@djo.tudelft.nl> Tested-by:
Kurt Garloff <kurt@garloff.de> Fixes: 09954bad ("floppy: refactor open() flags handling") Fixes: f2791e7e ("Revert "floppy: refactor open() flags handling"") Signed-off-by:
Jiri Kosina <jkosina@suse.cz> Signed-off-by:
-
Guoqing Jiang authored
Currently, raid5 calculates dev_sectors from chunk_sectors without proper cast, which is problematic. Signed-off-by:
Guoqing Jiang <guoqing.jiang@cloud.ionos.com> Signed-off-by:
Song Liu <songliubraving@fb.com>
-
- 02 Feb, 2021 7 commits
-
-
git://git.infradead.org/nvmeJens Axboe authored
Pull NVMe updates from Christoph: "nvme updates for 5.12: - failed reconnect fixes (Chao Leng) - various tracing improvements (Michal Krakowiak, Johannes Thumshirn) - switch the nvmet-fc assoc_list to use RCU protection (Leonid Ravich) - resync the status codes with the latest spec (Max Gurtovoy) - minor nvme-tcp improvements (Sagi Grimberg) - various cleanups (Rikard Falkeborn, Minwoo Im, Chaitanya Kulkarni, Israel Rukshin)" * tag 'nvme-5.21-2020-02-02' of git://git.infradead.org/nvme: (22 commits) nvme-tcp: use cancel tagset helper for tear down nvme-rdma: use cancel tagset helper for tear down nvme-tcp: add clean action for failed reconnection nvme-rdma: add clean action for failed reconnection nvme-core: add cancel tagset helpers nvme-core: get rid of the extra space nvme: add tracing of zns commands nvme: parse format nvm command details when tracing nvme: update enumerations for status codes nvmet: add lba to sect conversion helpers nvmet: remove extra variable in identify ns nvmet: remove extra variable in id-desclist nvmet: remove extra variable in smart log nsid nvme: refactor ns->ctrl by request nvme-tcp: pass multipage bvec to request iov_iter nvme-tcp: get rid of unused helper function nvme-tcp: fix wrong setting of request iov_iter nvme: support command retry delay for admin command nvme: constify static attribute_group structs nvmet-fc: use RCU proctection for assoc_list ...
-
Chao Leng authored
Use nvme_cancel_tagset and nvme_cancel_admin_tagset to clean code for tear down process. Signed-off-by:
-
Chao Leng authored
Use nvme_cancel_tagset and nvme_cancel_admin_tagset to clean code for tear down process. Signed-off-by:
-
Chao Leng authored
If reconnect failed after start io queues, the queues will be unquiesced and new requests continue to be delivered. Reconnection error handling process directly free queues without cancel suspend requests. The suppend request will time out, and then crash due to use the queue after free. Add sync queues and cancel suppend requests for reconnection error handling. Signed-off-by:
-
Chao Leng authored
A crash happens when inject failed reconnection. If reconnect failed after start io queues, the queues will be unquiesced and new requests continue to be delivered. Reconnection error handling process directly free queues without cancel suspend requests. The suppend request will time out, and then crash due to use the queue after free. Add sync queues and cancel suppend requests for reconnection error handling. Signed-off-by:
-
Chao Leng authored
Add nvme_cancel_tagset and nvme_cancel_admin_tagset for tear down and reconnection error handling. Signed-off-by:
-
Chaitanya Kulkarni authored
Remove the extra space in the nvme_free_cels() when calling xa_for_each loop which is not a common practice (except drivers/infiniband/core/ not sure why). Signed-off-by:
-
