summaryrefslogtreecommitdiff
path: root/drivers/nvme
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/nvme')
-rw-r--r--drivers/nvme/host/core.c46
-rw-r--r--drivers/nvme/host/fault_inject.c2
-rw-r--r--drivers/nvme/host/fc.c37
-rw-r--r--drivers/nvme/host/ioctl.c2
-rw-r--r--drivers/nvme/host/pci.c32
-rw-r--r--drivers/nvme/host/rdma.c3
-rw-r--r--drivers/nvme/host/sysfs.c2
-rw-r--r--drivers/nvme/host/tcp.c3
-rw-r--r--drivers/nvme/host/zns.c9
-rw-r--r--drivers/nvme/target/loop.c2
-rw-r--r--drivers/nvme/target/passthru.c4
11 files changed, 105 insertions, 37 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 47d7ba2827ff..f3a01b79148c 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3431,10 +3431,40 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info)
ret = nvme_global_check_duplicate_ids(ctrl->subsys, &info->ids);
if (ret) {
- dev_err(ctrl->device,
- "globally duplicate IDs for nsid %d\n", info->nsid);
+ /*
+ * We've found two different namespaces on two different
+ * subsystems that report the same ID. This is pretty nasty
+ * for anything that actually requires unique device
+ * identification. In the kernel we need this for multipathing,
+ * and in user space the /dev/disk/by-id/ links rely on it.
+ *
+ * If the device also claims to be multi-path capable back off
+ * here now and refuse the probe the second device as this is a
+ * recipe for data corruption. If not this is probably a
+ * cheap consumer device if on the PCIe bus, so let the user
+ * proceed and use the shiny toy, but warn that with changing
+ * probing order (which due to our async probing could just be
+ * device taking longer to startup) the other device could show
+ * up at any time.
+ */
nvme_print_device_info(ctrl);
- return ret;
+ if ((ns->ctrl->ops->flags & NVME_F_FABRICS) || /* !PCIe */
+ ((ns->ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) &&
+ info->is_shared)) {
+ dev_err(ctrl->device,
+ "ignoring nsid %d because of duplicate IDs\n",
+ info->nsid);
+ return ret;
+ }
+
+ dev_err(ctrl->device,
+ "clearing duplicate IDs for nsid %d\n", info->nsid);
+ dev_err(ctrl->device,
+ "use of /dev/disk/by-id/ may cause data corruption\n");
+ memset(&info->ids.nguid, 0, sizeof(info->ids.nguid));
+ memset(&info->ids.uuid, 0, sizeof(info->ids.uuid));
+ memset(&info->ids.eui64, 0, sizeof(info->ids.eui64));
+ ctrl->quirks |= NVME_QUIRK_BOGUS_NID;
}
mutex_lock(&ctrl->subsys->lock);
@@ -3903,6 +3933,12 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
*/
nvme_mpath_clear_ctrl_paths(ctrl);
+ /*
+ * Unquiesce io queues so any pending IO won't hang, especially
+ * those submitted from scan work
+ */
+ nvme_unquiesce_io_queues(ctrl);
+
/* prevent racing with ns scanning */
flush_work(&ctrl->scan_work);
@@ -3912,10 +3948,8 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
* removing the namespaces' disks; fail all the queues now to avoid
* potentially having to clean up the failed sync later.
*/
- if (ctrl->state == NVME_CTRL_DEAD) {
+ if (ctrl->state == NVME_CTRL_DEAD)
nvme_mark_namespaces_dead(ctrl);
- nvme_unquiesce_io_queues(ctrl);
- }
/* this is a no-op when called from the controller reset handler */
nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING_NOIO);
diff --git a/drivers/nvme/host/fault_inject.c b/drivers/nvme/host/fault_inject.c
index 83d2e6860d38..1ba10a5c656d 100644
--- a/drivers/nvme/host/fault_inject.c
+++ b/drivers/nvme/host/fault_inject.c
@@ -27,7 +27,7 @@ void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj,
/* create debugfs directory and attribute */
parent = debugfs_create_dir(dev_name, NULL);
- if (!parent) {
+ if (IS_ERR(parent)) {
pr_warn("%s: failed to create debugfs directory\n", dev_name);
return;
}
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 691f2df574ce..1cd2bf82319a 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2548,14 +2548,24 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
* the controller. Abort any ios on the association and let the
* create_association error path resolve things.
*/
- if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
- __nvme_fc_abort_outstanding_ios(ctrl, true);
+ enum nvme_ctrl_state state;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctrl->lock, flags);
+ state = ctrl->ctrl.state;
+ if (state == NVME_CTRL_CONNECTING) {
set_bit(ASSOC_FAILED, &ctrl->flags);
+ spin_unlock_irqrestore(&ctrl->lock, flags);
+ __nvme_fc_abort_outstanding_ios(ctrl, true);
+ dev_warn(ctrl->ctrl.device,
+ "NVME-FC{%d}: transport error during (re)connect\n",
+ ctrl->cnum);
return;
}
+ spin_unlock_irqrestore(&ctrl->lock, flags);
/* Otherwise, only proceed if in LIVE state - e.g. on first error */
- if (ctrl->ctrl.state != NVME_CTRL_LIVE)
+ if (state != NVME_CTRL_LIVE)
return;
dev_warn(ctrl->ctrl.device,
@@ -3110,7 +3120,9 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
*/
ret = nvme_enable_ctrl(&ctrl->ctrl);
- if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
+ if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
+ ret = -EIO;
+ if (ret)
goto out_disconnect_admin_queue;
ctrl->ctrl.max_segments = ctrl->lport->ops->max_sgl_segments;
@@ -3120,7 +3132,9 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
nvme_unquiesce_admin_queue(&ctrl->ctrl);
ret = nvme_init_ctrl_finish(&ctrl->ctrl, false);
- if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
+ if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
+ ret = -EIO;
+ if (ret)
goto out_disconnect_admin_queue;
/* sanity checks */
@@ -3165,10 +3179,16 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
else
ret = nvme_fc_recreate_io_queues(ctrl);
}
- if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
- goto out_term_aen_ops;
+ spin_lock_irqsave(&ctrl->lock, flags);
+ if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
+ ret = -EIO;
+ if (ret) {
+ spin_unlock_irqrestore(&ctrl->lock, flags);
+ goto out_term_aen_ops;
+ }
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+ spin_unlock_irqrestore(&ctrl->lock, flags);
ctrl->ctrl.nr_reconnects = 0;
@@ -3180,6 +3200,9 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
out_term_aen_ops:
nvme_fc_term_aen_ops(ctrl);
out_disconnect_admin_queue:
+ dev_warn(ctrl->ctrl.device,
+ "NVME-FC{%d}: create_assoc failed, assoc_id %llx ret %d\n",
+ ctrl->cnum, ctrl->association_id, ret);
/* send a Disconnect(association) LS to fc-nvme target */
nvme_fc_xmt_disconnect_assoc(ctrl);
spin_lock_irqsave(&ctrl->lock, flags);
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 5c3250f36ce7..d39f3219358b 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -786,11 +786,9 @@ int nvme_ns_chr_uring_cmd_iopoll(struct io_uring_cmd *ioucmd,
if (!(ioucmd->flags & IORING_URING_CMD_POLLED))
return 0;
- rcu_read_lock();
req = READ_ONCE(ioucmd->cookie);
if (req && blk_rq_is_poll(req))
ret = blk_rq_poll(req, iob, poll_flags);
- rcu_read_unlock();
return ret;
}
#ifdef CONFIG_NVME_MULTIPATH
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 72725729cb6c..2f57da12d983 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -967,7 +967,7 @@ static __always_inline void nvme_pci_unmap_rq(struct request *req)
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
dma_unmap_page(dev->dev, iod->meta_dma,
- rq_integrity_vec(req)->bv_len, rq_data_dir(req));
+ rq_integrity_vec(req)->bv_len, rq_dma_dir(req));
}
if (blk_rq_nr_phys_segments(req))
@@ -1298,9 +1298,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
*/
if (nvme_should_reset(dev, csts)) {
nvme_warn_reset(dev, csts);
- nvme_dev_disable(dev, false);
- nvme_reset_ctrl(&dev->ctrl);
- return BLK_EH_DONE;
+ goto disable;
}
/*
@@ -1351,10 +1349,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
"I/O %d QID %d timeout, reset controller\n",
req->tag, nvmeq->qid);
nvme_req(req)->flags |= NVME_REQ_CANCELLED;
- nvme_dev_disable(dev, false);
- nvme_reset_ctrl(&dev->ctrl);
-
- return BLK_EH_DONE;
+ goto disable;
}
if (atomic_dec_return(&dev->ctrl.abort_limit) < 0) {
@@ -1391,6 +1386,15 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
* as the device then is in a faulty state.
*/
return BLK_EH_RESET_TIMER;
+
+disable:
+ if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING))
+ return BLK_EH_DONE;
+
+ nvme_dev_disable(dev, false);
+ if (nvme_try_sched_reset(&dev->ctrl))
+ nvme_unquiesce_io_queues(&dev->ctrl);
+ return BLK_EH_DONE;
}
static void nvme_free_queue(struct nvme_queue *nvmeq)
@@ -3278,6 +3282,10 @@ static pci_ers_result_t nvme_error_detected(struct pci_dev *pdev,
case pci_channel_io_frozen:
dev_warn(dev->ctrl.device,
"frozen state error detected, reset controller\n");
+ if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING)) {
+ nvme_dev_disable(dev, true);
+ return PCI_ERS_RESULT_DISCONNECT;
+ }
nvme_dev_disable(dev, false);
return PCI_ERS_RESULT_NEED_RESET;
case pci_channel_io_perm_failure:
@@ -3294,7 +3302,8 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
dev_info(dev->ctrl.device, "restart after slot reset\n");
pci_restore_state(pdev);
- nvme_reset_ctrl(&dev->ctrl);
+ if (!nvme_try_sched_reset(&dev->ctrl))
+ nvme_unquiesce_io_queues(&dev->ctrl);
return PCI_ERS_RESULT_RECOVERED;
}
@@ -3393,9 +3402,12 @@ static const struct pci_device_id nvme_id_table[] = {
{ PCI_DEVICE(0x1d97, 0x2263), /* SPCC */
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x144d, 0xa80b), /* Samsung PM9B1 256G and 512G */
- .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES |
+ NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x144d, 0xa809), /* Samsung MZALQ256HBJD 256G */
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+ { PCI_DEVICE(0x144d, 0xa802), /* Samsung SM953 */
+ .driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1cc4, 0x6303), /* UMIS RPJTJ512MGE1QDY 512G */
.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
{ PCI_DEVICE(0x1cc4, 0x6302), /* UMIS RPJTJ256MGE1QDY 256G */
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index d433b2ec07a6..337a624a537c 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -883,6 +883,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
goto out_cleanup_tagset;
if (!new) {
+ nvme_start_freeze(&ctrl->ctrl);
nvme_unquiesce_io_queues(&ctrl->ctrl);
if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) {
/*
@@ -891,6 +892,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
* to be safe.
*/
ret = -ENODEV;
+ nvme_unfreeze(&ctrl->ctrl);
goto out_wait_freeze_timed_out;
}
blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
@@ -940,7 +942,6 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
if (ctrl->ctrl.queue_count > 1) {
- nvme_start_freeze(&ctrl->ctrl);
nvme_quiesce_io_queues(&ctrl->ctrl);
nvme_sync_io_queues(&ctrl->ctrl);
nvme_rdma_stop_io_queues(ctrl);
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index 45e91811f905..212e1b05d298 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -92,7 +92,7 @@ static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
* we have no UUID set
*/
if (uuid_is_null(&ids->uuid)) {
- dev_warn_ratelimited(dev,
+ dev_warn_once(dev,
"No UUID available providing old NGUID\n");
return sysfs_emit(buf, "%pU\n", ids->nguid);
}
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 9ce417cd32a7..5b332d9f87fc 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1868,6 +1868,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
goto out_cleanup_connect_q;
if (!new) {
+ nvme_start_freeze(ctrl);
nvme_unquiesce_io_queues(ctrl);
if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) {
/*
@@ -1876,6 +1877,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
* to be safe.
*/
ret = -ENODEV;
+ nvme_unfreeze(ctrl);
goto out_wait_freeze_timed_out;
}
blk_mq_update_nr_hw_queues(ctrl->tagset,
@@ -1980,7 +1982,6 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
if (ctrl->queue_count <= 1)
return;
nvme_quiesce_admin_queue(ctrl);
- nvme_start_freeze(ctrl);
nvme_quiesce_io_queues(ctrl);
nvme_sync_io_queues(ctrl);
nvme_tcp_stop_io_queues(ctrl);
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index 12316ab51bda..ec8557810c21 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -10,12 +10,11 @@
int nvme_revalidate_zones(struct nvme_ns *ns)
{
struct request_queue *q = ns->queue;
- int ret;
- ret = blk_revalidate_disk_zones(ns->disk, NULL);
- if (!ret)
- blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
- return ret;
+ blk_queue_chunk_sectors(q, ns->zsze);
+ blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
+
+ return blk_revalidate_disk_zones(ns->disk, NULL);
}
static int nvme_set_max_append(struct nvme_ctrl *ctrl)
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index f2d24b2d992f..48d5df054cd0 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -373,7 +373,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
goto out_cleanup_tagset;
ctrl->ctrl.max_hw_sectors =
- (NVME_LOOP_MAX_SEGMENTS - 1) << (PAGE_SHIFT - 9);
+ (NVME_LOOP_MAX_SEGMENTS - 1) << PAGE_SECTORS_SHIFT;
nvme_unquiesce_admin_queue(&ctrl->ctrl);
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index 71a9c1cc57f5..9fe07d7efa96 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -102,14 +102,14 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
* which depends on the host's memory fragementation. To solve this,
* ensure mdts is limited to the pages equal to the number of segments.
*/
- max_hw_sectors = min_not_zero(pctrl->max_segments << (PAGE_SHIFT - 9),
+ max_hw_sectors = min_not_zero(pctrl->max_segments << PAGE_SECTORS_SHIFT,
pctrl->max_hw_sectors);
/*
* nvmet_passthru_map_sg is limitted to using a single bio so limit
* the mdts based on BIO_MAX_VECS as well
*/
- max_hw_sectors = min_not_zero(BIO_MAX_VECS << (PAGE_SHIFT - 9),
+ max_hw_sectors = min_not_zero(BIO_MAX_VECS << PAGE_SECTORS_SHIFT,
max_hw_sectors);
page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;
generated by cgit v1.2.3 (git 2.39.0) at 2024-09-21 07:28:43 +0300