kernel/linux.git/drivers/nvme/target, branch v4.14.85

nvme-loop: fix kernel oops in case of unhandled command

2018-11-21T08:24:17+00:00

commit 11d9ea6f2ca69237d35d6c55755beba3e006b106 upstream. When nvmet_req_init() fails, __nvmet_req_complete() is called to handle the target request via .queue_response(), so nvme_loop_queue_response() shouldn't be called again for handling the failure. This patch fixes this case by the following way: - move blk_mq_start_request() before nvmet_req_init(), so nvme_loop_queue_response() may work well to complete this host request - don't call nvme_cleanup_cmd() which is done in nvme_loop_complete_rq() - don't call nvme_loop_queue_response() which is done via .queue_response() Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig [trimmed changelog] Signed-off-by: Keith Busch Signed-off-by: Jens Axboe Signed-off-by: Sudip Mukherjee Signed-off-by: Greg Kroah-Hartman

nvmet-rdma: fix possible bogus dereference under heavy load

2018-10-10T06:54:24+00:00

[ Upstream commit 8407879c4e0d7731f6e7e905893cecf61a7762c7 ] Currently we always repost the recv buffer before we send a response capsule back to the host. Since ordering is not guaranteed for send and recv completions, it is posible that we will receive a new request from the host before we got a send completion for the response capsule. Today, we pre-allocate 2x rsps the length of the queue, but in reality, under heavy load there is nothing that is really preventing the gap to expand until we exhaust all our rsps. To fix this, if we don't have any pre-allocated rsps left, we dynamically allocate a rsp and make sure to free it when we are done. If under memory pressure we fail to allocate a rsp, we silently drop the command and wait for the host to retry. Reported-by: Steve Wise Tested-by: Steve Wise Signed-off-by: Sagi Grimberg [hch: dropped a superflous assignment] Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

nvme-fcloop: Fix dropped LS's to removed target port

2018-10-04T00:00:59+00:00

[ Upstream commit afd299ca996929f4f98ac20da0044c0cdc124879 ] When a targetport is removed from the config, fcloop will avoid calling the LS done() routine thinking the targetport is gone. This leaves the initiator reset/reconnect hanging as it waits for a status on the Create_Association LS for the reconnect. Change the filter in the LS callback path. If tport null (set when failed validation before "sending to remote port"), be sure to call done. This was the main bug. But, continue the logic that only calls done if tport was set but there is no remoteport (e.g. case where remoteport has been removed, thus host doesn't expect a completion). Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

nvmet: reset keep alive timer in controller enable

2018-08-24T11:09:02+00:00

[ Upstream commit d68a90e148f5a82aa67654c5012071e31c0e4baa ] Controllers that are not yet enabled should not really enforce keep alive timeouts, but we still want to track a timeout and cleanup in case a host died before it enabled the controller. Hence, simply reset the keep alive timer when the controller is enabled. Suggested-by: Max Gurtovoy Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

nvmet-fc: fix target sgl list on large transfers

2018-08-09T10:16:39+00:00

commit d082dc1562a2ff0947b214796f12faaa87e816a9 upstream. The existing code to carve up the sg list expected an sg element-per-page which can be very incorrect with iommu's remapping multiple memory pages to fewer bus addresses. To hit this error required a large io payload (greater than 256k) and a system that maps on a per-page basis. It's possible that large ios could get by fine if the system condensed the sgl list into the first 64 elements. This patch corrects the sg list handling by specifically walking the sg list element by element and attempting to divide the transfer up on a per-sg element boundary. While doing so, it still tries to keep sequences under 256k, but will exceed that rule if a single sg element is larger than 256k. Fixes: 48fa362b6c3f ("nvmet-fc: simplify sg list handling") Cc: # 4.14 Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Greg Kroah-Hartman

nvmet-rdma: depend on INFINIBAND_ADDR_TRANS

2018-06-20T19:02:50+00:00

[ Upstream commit d6fc6a22fc7d3df987666725496ed5dd2dd30f23 ] NVME_TARGET_RDMA code depends on INFINIBAND_ADDR_TRANS provided symbols. So declare the kconfig dependency. This is necessary to allow for enabling INFINIBAND without INFINIBAND_ADDR_TRANS. Signed-off-by: Greg Thelen Cc: Tarick Bedeir Signed-off-by: Doug Ledford Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

nvmet: fix PSDT field check in command format

2018-05-30T05:52:06+00:00

[ Upstream commit bffd2b61670feef18d2535e9b53364d270a1c991 ] PSDT field section according to NVM_Express-1.3: "This field specifies whether PRPs or SGLs are used for any data transfer associated with the command. PRPs shall be used for all Admin commands for NVMe over PCIe. SGLs shall be used for all Admin and I/O commands for NVMe over Fabrics. This field shall be set to 01b for NVMe over Fabrics 1.0 implementations. Suggested-by: Idan Burstein Signed-off-by: Max Gurtovoy Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

nvme_fcloop: fix abort race condition

2018-04-12T10:32:16+00:00

[ Upstream commit 278e096063f1914fccfc77a617be9fc8dbb31b0e ] A test case revealed a race condition of an i/o completing on a thread parallel to the delete_association generating the aborts for the outstanding ios on the controller. The i/o completion was freeing the target fcloop context, thus the abort task referenced the just-freed memory. Correct by clearing the target/initiator cross pointers in the io completion and abort tasks before calling the callbacks. On aborts that detect already finished io's, ensure the complete context is called. Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

nvme_fcloop: disassocate local port structs

2018-04-12T10:32:16+00:00

[ Upstream commit 6fda20283e55b9d288cd56822ce39fc8e64f2208 ] The current fcloop driver gets its lport structure from the private area co-allocated with the fc_localport. All is fine except the teardown path, which wants to wait on the completion, which is marked complete by the delete_localport callback performed after unregister_localport. The issue is, the nvme_fc transport frees the localport structure immediately after delete_localport is called, meaning the original routine is trying to wait on a complete that was just freed. Change such that a lport struct is allocated coincident with the addition and registration of a localport. The private area of the localport now contains just a backpointer to the real lport struct. Now, the completion can be waited for, and after completing, the new structure can be kfree'd. Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman

nvmet-fc: correct ref counting error when deferred rcv used

2018-02-03T16:38:59+00:00

[ Upstream commit 619c62dcc62b957d17cccde2081cad527b020883 ] Whenever a cmd is received a reference is taken while looking up the queue. The reference is removed after the cmd is done as the iod is returned for reuse. The fod may be reused for a deferred (recevied but no job context) cmd. Existing code removes the reference only if the fod is not reused for another command. Given the fod may be used for one or more ios, although a reference was taken per io, it won't be matched on the frees. Remove the reference on every fod free. This pairs the references to each io. Signed-off-by: James Smart Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman