From: Sasha Levin <Alexander.Levin@microsoft.com>
To: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"stable@vger.kernel.org" <stable@vger.kernel.org>
Cc: Sagi Grimberg <sagi@grimberg.me>, Christoph Hellwig <hch@lst.de>,
"Sasha Levin" <Alexander.Levin@microsoft.com>
Subject: [PATCH AUTOSEL for 4.14 017/100] nvme-fabrics: introduce init command check for a queue that is not alive
Date: Wed, 24 Jan 2018 04:14:30 +0000 [thread overview]
Message-ID: <20180124041414.32065-17-alexander.levin@microsoft.com> (raw)
In-Reply-To: <20180124041414.32065-1-alexander.levin@microsoft.com>
From: Sagi Grimberg <sagi@grimberg.me>
[ Upstream commit 48832f8d58cfedb2f9bee11bbfbb657efb42e7e7 ]
When the fabrics queue is not alive and fully functional, no commands
should be allowed to pass but connect (which moves the queue to a fully
functional state). Any other command should be failed, with either
temporary status BLK_STS_RESOUCE or permanent status BLK_STS_IOERR.
This is shared across all fabrics, hence move the check to fabrics
library.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
---
drivers/nvme/host/fabrics.h | 30 ++++++++++++++++++++++++++++++
drivers/nvme/host/rdma.c | 32 ++++++--------------------------
2 files changed, 36 insertions(+), 26 deletions(-)
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index bf33663218cd..9ff8529a64a9 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -142,4 +142,34 @@ void nvmf_free_options(struct nvmf_ctrl_options *opts);
int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
+static inline blk_status_t nvmf_check_init_req(struct nvme_ctrl *ctrl,
+ struct request *rq)
+{
+ struct nvme_command *cmd = nvme_req(rq)->cmd;
+
+ /*
+ * We cannot accept any other command until the connect command has
+ * completed, so only allow connect to pass.
+ */
+ if (!blk_rq_is_passthrough(rq) ||
+ cmd->common.opcode != nvme_fabrics_command ||
+ cmd->fabrics.fctype != nvme_fabrics_type_connect) {
+ /*
+ * Reconnecting state means transport disruption, which can take
+ * a long time and even might fail permanently, fail fast to
+ * give upper layers a chance to failover.
+ * Deleting state means that the ctrl will never accept commands
+ * again, fail it permanently.
+ */
+ if (ctrl->state == NVME_CTRL_RECONNECTING ||
+ ctrl->state == NVME_CTRL_DELETING) {
+ nvme_req(rq)->status = NVME_SC_ABORT_REQ;
+ return BLK_STS_IOERR;
+ }
+ return BLK_STS_RESOURCE; /* try again later */
+ }
+
+ return BLK_STS_OK;
+}
+
#endif /* _NVME_FABRICS_H */
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 0ebb539f3bd3..6de163e6c9eb 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1603,31 +1603,11 @@ nvme_rdma_timeout(struct request *rq, bool reserved)
* We cannot accept any other command until the Connect command has completed.
*/
static inline blk_status_t
-nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue, struct request *rq)
-{
- if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags))) {
- struct nvme_command *cmd = nvme_req(rq)->cmd;
-
- if (!blk_rq_is_passthrough(rq) ||
- cmd->common.opcode != nvme_fabrics_command ||
- cmd->fabrics.fctype != nvme_fabrics_type_connect) {
- /*
- * reconnecting state means transport disruption, which
- * can take a long time and even might fail permanently,
- * fail fast to give upper layers a chance to failover.
- * deleting state means that the ctrl will never accept
- * commands again, fail it permanently.
- */
- if (queue->ctrl->ctrl.state == NVME_CTRL_RECONNECTING ||
- queue->ctrl->ctrl.state == NVME_CTRL_DELETING) {
- nvme_req(rq)->status = NVME_SC_ABORT_REQ;
- return BLK_STS_IOERR;
- }
- return BLK_STS_RESOURCE; /* try again later */
- }
- }
-
- return 0;
+nvme_rdma_is_ready(struct nvme_rdma_queue *queue, struct request *rq)
+{
+ if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags)))
+ return nvmf_check_init_req(&queue->ctrl->ctrl, rq);
+ return BLK_STS_OK;
}
static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
@@ -1646,7 +1626,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
WARN_ON_ONCE(rq->tag < 0);
- ret = nvme_rdma_queue_is_ready(queue, rq);
+ ret = nvme_rdma_is_ready(queue, rq);
if (unlikely(ret))
return ret;
--
2.11.0
next prev parent reply other threads:[~2018-01-24 5:03 UTC|newest]
Thread overview: 105+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-24 4:14 [PATCH AUTOSEL for 4.14 001/100] drm/vc4: Account for interrupts in flight Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 002/100] btrfs: Fix transaction abort during failure in btrfs_rm_dev_item Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 003/100] Btrfs: bail out gracefully rather than BUG_ON Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 004/100] cpupowerutils: bench - Fix cpu online check Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 005/100] cpupower : Fix cpupower working when cpu0 is offline Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 006/100] KVM: nVMX/nSVM: Don't intercept #UD when running L2 Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 007/100] KVM: x86: emulator: Return to user-mode on L1 CPL=0 emulation failure Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 008/100] KVM: x86: Don't re-execute instruction when not passing CR2 value Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 009/100] KVM: X86: Fix operand/address-size during instruction decoding Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 010/100] KVM: nVMX: Fix mmu context after VMLAUNCH/VMRESUME failure Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 011/100] KVM: x86: fix em_fxstor() sleeping while in atomic Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 012/100] KVM: x86: ioapic: Fix level-triggered EOI and IOAPIC reconfigure race Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 014/100] KVM: x86: ioapic: Preserve read-only values in the redirection table Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 013/100] KVM: x86: ioapic: Clear Remote IRR when entry is switched to edge-triggered Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 015/100] KVM: nVMX: Fix vmx_check_nested_events() return value in case an event was reinjected to L2 Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 016/100] KVM: x86: Fix CPUID function for word 6 (80000001_ECX) Sasha Levin
2018-01-24 4:14 ` Sasha Levin [this message]
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 018/100] nvme-fc: check if queue is ready in queue_rq Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 019/100] nvme-loop: " Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 020/100] nvme-pci: disable APST on Samsung SSD 960 EVO + ASUS PRIME B350M-A Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 022/100] nvmet-fc: correct ref counting error when deferred rcv used Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 021/100] nvme-pci: avoid hmb desc array idx out-of-bound when hmmaxd set Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 024/100] s390/zcrypt: Fix wrong comparison leading to strange load balancing Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 023/100] s390/topology: fix compile error in file arch/s390/kernel/smp.c Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 025/100] ACPI / bus: Leave modalias empty for devices which are not present Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 027/100] null_blk: fix dev->badblocks leak Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 026/100] cpufreq: Add Loongson machine dependencies Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 029/100] rxrpc: The mutex lock returned by rxrpc_accept_call() needs releasing Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 028/100] s390: fix alloc_pgste check in init_new_context again Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 031/100] rxrpc: Fix service endpoint expiry Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 030/100] rxrpc: Provide a different lockdep key for call->user_mutex for kernel calls Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 032/100] bcache: check return value of register_shrinker Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 034/100] drm/amdkfd: Fix SDMA ring buffer size calculation Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 033/100] drm/amdgpu: Fix SDMA load/unload sequence on HWS disabled mode Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 036/100] uapi: fix linux/kfd_ioctl.h userspace compilation errors Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 035/100] drm/amdkfd: Fix SDMA oversubsription handling Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 037/100] nvme-rdma: don't complete requests before a send work request has completed Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 038/100] openvswitch: fix the incorrect flow action alloc size Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 040/100] mac80211: use QoS NDP for AP probing Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 039/100] drm/rockchip: dw-mipi-dsi: fix possible un-balanced runtime PM enable Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 041/100] mac80211: fix the update of path metric for RANN frame Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 042/100] btrfs: fix deadlock when writing out space cache Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 043/100] sctp: only allow the asoc reset when the asoc outq is empty Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 045/100] sctp: set sender next_tsn for the old result with ctsn_ack_point plus 1 Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 044/100] sctp: avoid flushing unsent queue when doing asoc reset Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 046/100] reiserfs: remove unneeded i_version bump Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 047/100] KVM: X86: Fix softlockup when get the current kvmclock Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 048/100] KVM: VMX: Fix rflags cache during vCPU reset Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 050/100] KVM: Let KVM_SET_SIGNAL_MASK work as advertised Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 049/100] Btrfs: fix list_add corruption and soft lockups in fsync Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 052/100] xfs: log recovery should replay deferred ops in order Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 051/100] xfs: always free inline data before resetting inode fork during ifree Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 054/100] xen-netfront: remove warning when unloading module Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 053/100] i2c: i2c-boardinfo: fix memory leaks on devinfo Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 055/100] auxdisplay: img-ascii-lcd: Only build on archs that have IOMEM Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 056/100] nfsd: CLOSE SHOULD return the invalid special stateid for NFSv4.x (x>0) Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 057/100] nfsd: Ensure we don't recognise lock stateids after freeing them Sasha Levin
2018-01-24 15:47 ` J. Bruce Fields
2018-01-24 17:28 ` Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 058/100] nfsd: Ensure we check stateid validity in the seqid operation checks Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 059/100] grace: replace BUG_ON by WARN_ONCE in exit_net hook Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 060/100] nfsd: check for use of the closed special stateid Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 061/100] race of lockd inetaddr notifiers vs nlmsvc_rqst change Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 062/100] lockd: fix "list_add double add" caused by legacy signal interface Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 063/100] hwmon: (pmbus) Use 64bit math for DIRECT format values Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 064/100] quota: propagate error from __dquot_initialize Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 066/100] net: mvpp2: do not disable GMAC padding Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 065/100] net: mvpp2: fix the txq_init error path Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 067/100] net: phy: marvell10g: fix the PHY id mask Sasha Levin
2018-01-24 4:14 ` [PATCH AUTOSEL for 4.14 068/100] bnxt_en: Fix an error handling path in 'bnxt_get_module_eeprom()' Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 070/100] nvme-pci: fix NULL pointer dereference in nvme_free_host_mem() Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 069/100] Btrfs: incremental send, fix wrong unlink path after renaming file Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 072/100] drm/amdgpu: don't try to move pinned BOs Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 071/100] xfs: fortify xfs_alloc_buftarg error handling Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 073/100] net: ethernet: xilinx: Mark XILINX_LL_TEMAC broken on 64-bit Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 074/100] quota: Check for register_shrinker() failure Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 075/100] SUNRPC: Allow connect to return EHOSTUNREACH Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 077/100] fs/mbcache.c: make count_objects() more robust Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 076/100] scripts/faddr2line: extend usage on generic arch Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 078/100] kmemleak: add scheduling point to kmemleak_scan() Sasha Levin
2018-01-24 7:46 ` Yisheng Xie
2018-01-24 17:24 ` Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 079/100] drm/bridge: Fix lvds-encoder since the panel_bridge rework Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 080/100] drm/bridge: tc358767: do no fail on hi-res displays Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 082/100] drm/bridge: tc358767: fix DP0_MISC register set Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 081/100] drm/bridge: tc358767: filter out too high modes Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 084/100] drm/bridge: tc358767: fix AUXDATAn registers access Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 083/100] drm/bridge: tc358767: fix timing calculations Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 086/100] drm/omap: Fix error handling path in 'omap_dmm_probe()' Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 085/100] drm/bridge: tc358767: fix 1-lane behavior Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 088/100] xfs: ubsan fixes Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 087/100] drm/omap: displays: panel-dpi: add backlight dependency Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 089/100] xfs: Properly retry failed dquot items in case of error during buffer writeback Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 090/100] perf/core: Fix memory leak triggered by perf --namespace Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 091/100] scsi: aacraid: Prevent crash in case of free interrupt during scsi EH path Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 092/100] scsi: ufs: ufshcd: fix potential NULL pointer dereference in ufshcd_config_vreg Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 094/100] iwlwifi: fix access to prph when transport is stopped Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 093/100] iwlwifi: mvm: fix the TX queue hang timeout for MONITOR vif type Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 095/100] ARM: dts: NSP: Disable AHCI controller for HR NSP boards Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 096/100] ARM: dts: NSP: Fix PPI interrupt types Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 097/100] media: usbtv: add a new usbid Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 098/100] x86/xen: Support early interrupts in xen pv guests Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 099/100] usb: gadget: don't dereference g until after it has been null checked Sasha Levin
2018-01-24 4:15 ` [PATCH AUTOSEL for 4.14 100/100] staging: rtl8188eu: Fix incorrect response to SIOCGIWESSID Sasha Levin
2018-01-25 3:30 ` [PATCH AUTOSEL for 4.14 001/100] drm/vc4: Account for interrupts in flight Eric Anholt
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180124041414.32065-17-alexander.levin@microsoft.com \
--to=alexander.levin@microsoft.com \
--cc=hch@lst.de \
--cc=linux-kernel@vger.kernel.org \
--cc=sagi@grimberg.me \
--cc=stable@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox