summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-06-24 06:33:54 +0800
committerLinus Torvalds <torvalds@linux-foundation.org>2018-06-24 06:33:54 +0800
commit77072ca59fddcb8cefd2cbf5382cfa39c5a10442 (patch)
tree3c88a0674264726f6667a19b3f2242c932d906bd
parent2dd3f7c904cce0d4b0e4684a62ce8b9024f8efda (diff)
parentf5e350f021e04ea41d2e5d58487c33b05ba3d25b (diff)
downloadlinux-77072ca59fddcb8cefd2cbf5382cfa39c5a10442.tar.bz2
Merge tag 'for-linus-20180623' of git://git.kernel.dk/linux-block
Pull block fixes from Jens Axboe: - Further timeout fixes. We aren't quite there yet, so expect another round of fixes for that to completely close some of the IRQ vs completion races. (Christoph/Bart) - Set of NVMe fixes from the usual suspects, mostly error handling - Two off-by-one fixes (Dan) - Another bdi race fix (Jan) - Fix nbd reconfigure with NBD_DISCONNECT_ON_CLOSE (Doron) * tag 'for-linus-20180623' of git://git.kernel.dk/linux-block: blk-mq: Fix timeout handling in case the timeout handler returns BLK_EH_DONE bdi: Fix another oops in wb_workfn() lightnvm: Remove depends on HAS_DMA in case of platform dependency nvme-pci: limit max IO size and segments to avoid high order allocations nvme-pci: move nvme_kill_queues to nvme_remove_dead_ctrl nvme-fc: release io queues to allow fast fail nbd: Add the nbd NBD_DISCONNECT_ON_CLOSE config flag. block: sed-opal: Fix a couple off by one bugs blk-mq-debugfs: Off by one in blk_mq_rq_state_name() nvmet: reset keep alive timer in controller enable nvme-rdma: don't override opts->queue_size nvme-rdma: Fix command completion race at error recovery nvme-rdma: fix possible free of a non-allocated async event buffer nvme-rdma: fix possible double free condition when failing to create a controller Revert "block: Add warning for bi_next not NULL in bio_endio()" block: fix timeout changes for legacy request drivers
-rw-r--r--block/bio.c3
-rw-r--r--block/blk-core.c8
-rw-r--r--block/blk-mq-debugfs.c2
-rw-r--r--block/blk-mq.c1
-rw-r--r--block/blk-softirq.c1
-rw-r--r--block/blk-timeout.c1
-rw-r--r--block/sed-opal.c4
-rw-r--r--drivers/block/nbd.c42
-rw-r--r--drivers/block/null_blk.c2
-rw-r--r--drivers/lightnvm/Kconfig2
-rw-r--r--drivers/nvme/host/core.c1
-rw-r--r--drivers/nvme/host/fc.c6
-rw-r--r--drivers/nvme/host/nvme.h1
-rw-r--r--drivers/nvme/host/pci.c44
-rw-r--r--drivers/nvme/host/rdma.c73
-rw-r--r--drivers/nvme/target/core.c8
-rw-r--r--drivers/scsi/scsi_transport_fc.c2
-rw-r--r--include/linux/backing-dev-defs.h2
-rw-r--r--include/uapi/linux/nbd.h3
-rw-r--r--mm/backing-dev.c20
20 files changed, 142 insertions, 84 deletions
diff --git a/block/bio.c b/block/bio.c
index 9710e275f230..67eff5eddc49 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1807,9 +1807,6 @@ again:
if (!bio_integrity_endio(bio))
return;
- if (WARN_ONCE(bio->bi_next, "driver left bi_next not NULL"))
- bio->bi_next = NULL;
-
/*
* Need to have a real endio function for chained bios, otherwise
* various corner cases will break (like stacking block devices that
diff --git a/block/blk-core.c b/block/blk-core.c
index cf0ee764b908..afd2596ea3d3 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -273,10 +273,6 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
bio_advance(bio, nbytes);
/* don't actually finish bio if it's part of flush sequence */
- /*
- * XXX this code looks suspicious - it's not consistent with advancing
- * req->bio in caller
- */
if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
bio_endio(bio);
}
@@ -3081,10 +3077,8 @@ bool blk_update_request(struct request *req, blk_status_t error,
struct bio *bio = req->bio;
unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
- if (bio_bytes == bio->bi_iter.bi_size) {
+ if (bio_bytes == bio->bi_iter.bi_size)
req->bio = bio->bi_next;
- bio->bi_next = NULL;
- }
/* Completion has already been traced */
bio_clear_flag(bio, BIO_TRACE_COMPLETION);
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index ffa622366922..1c4532e92938 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -356,7 +356,7 @@ static const char *const blk_mq_rq_state_name_array[] = {
static const char *blk_mq_rq_state_name(enum mq_rq_state rq_state)
{
- if (WARN_ON_ONCE((unsigned int)rq_state >
+ if (WARN_ON_ONCE((unsigned int)rq_state >=
ARRAY_SIZE(blk_mq_rq_state_name_array)))
return "(?)";
return blk_mq_rq_state_name_array[rq_state];
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 70c65bb6c013..b429d515b568 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -781,7 +781,6 @@ static void blk_mq_rq_timed_out(struct request *req, bool reserved)
WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER);
}
- req->rq_flags &= ~RQF_TIMED_OUT;
blk_add_timer(req);
}
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 01e2b353a2b9..15c1f5e12eb8 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -144,6 +144,7 @@ do_local:
local_irq_restore(flags);
}
+EXPORT_SYMBOL(__blk_complete_request);
/**
* blk_complete_request - end I/O on a request
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 4b8a48d48ba1..f2cfd56e1606 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -210,6 +210,7 @@ void blk_add_timer(struct request *req)
if (!req->timeout)
req->timeout = q->rq_timeout;
+ req->rq_flags &= ~RQF_TIMED_OUT;
blk_rq_set_deadline(req, jiffies + req->timeout);
/*
diff --git a/block/sed-opal.c b/block/sed-opal.c
index 945f4b8610e0..e0de4dd448b3 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -877,7 +877,7 @@ static size_t response_get_string(const struct parsed_resp *resp, int n,
return 0;
}
- if (n > resp->num) {
+ if (n >= resp->num) {
pr_debug("Response has %d tokens. Can't access %d\n",
resp->num, n);
return 0;
@@ -916,7 +916,7 @@ static u64 response_get_u64(const struct parsed_resp *resp, int n)
return 0;
}
- if (n > resp->num) {
+ if (n >= resp->num) {
pr_debug("Response has %d tokens. Can't access %d\n",
resp->num, n);
return 0;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 3b7083b8ecbb..74a05561b620 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -76,6 +76,7 @@ struct link_dead_args {
#define NBD_HAS_CONFIG_REF 4
#define NBD_BOUND 5
#define NBD_DESTROY_ON_DISCONNECT 6
+#define NBD_DISCONNECT_ON_CLOSE 7
struct nbd_config {
u32 flags;
@@ -138,6 +139,7 @@ static void nbd_config_put(struct nbd_device *nbd);
static void nbd_connect_reply(struct genl_info *info, int index);
static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info);
static void nbd_dead_link_work(struct work_struct *work);
+static void nbd_disconnect_and_put(struct nbd_device *nbd);
static inline struct device *nbd_to_dev(struct nbd_device *nbd)
{
@@ -1305,6 +1307,12 @@ out:
static void nbd_release(struct gendisk *disk, fmode_t mode)
{
struct nbd_device *nbd = disk->private_data;
+ struct block_device *bdev = bdget_disk(disk, 0);
+
+ if (test_bit(NBD_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) &&
+ bdev->bd_openers == 0)
+ nbd_disconnect_and_put(nbd);
+
nbd_config_put(nbd);
nbd_put(nbd);
}
@@ -1705,6 +1713,10 @@ again:
&config->runtime_flags);
put_dev = true;
}
+ if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) {
+ set_bit(NBD_DISCONNECT_ON_CLOSE,
+ &config->runtime_flags);
+ }
}
if (info->attrs[NBD_ATTR_SOCKETS]) {
@@ -1749,6 +1761,17 @@ out:
return ret;
}
+static void nbd_disconnect_and_put(struct nbd_device *nbd)
+{
+ mutex_lock(&nbd->config_lock);
+ nbd_disconnect(nbd);
+ nbd_clear_sock(nbd);
+ mutex_unlock(&nbd->config_lock);
+ if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
+ &nbd->config->runtime_flags))
+ nbd_config_put(nbd);
+}
+
static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
{
struct nbd_device *nbd;
@@ -1781,13 +1804,7 @@ static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
nbd_put(nbd);
return 0;
}
- mutex_lock(&nbd->config_lock);
- nbd_disconnect(nbd);
- nbd_clear_sock(nbd);
- mutex_unlock(&nbd->config_lock);
- if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
- &nbd->config->runtime_flags))
- nbd_config_put(nbd);
+ nbd_disconnect_and_put(nbd);
nbd_config_put(nbd);
nbd_put(nbd);
return 0;
@@ -1798,7 +1815,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
struct nbd_device *nbd = NULL;
struct nbd_config *config;
int index;
- int ret = -EINVAL;
+ int ret = 0;
bool put_dev = false;
if (!netlink_capable(skb, CAP_SYS_ADMIN))
@@ -1838,6 +1855,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
!nbd->task_recv) {
dev_err(nbd_to_dev(nbd),
"not configured, cannot reconfigure\n");
+ ret = -EINVAL;
goto out;
}
@@ -1862,6 +1880,14 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
&config->runtime_flags))
refcount_inc(&nbd->refs);
}
+
+ if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) {
+ set_bit(NBD_DISCONNECT_ON_CLOSE,
+ &config->runtime_flags);
+ } else {
+ clear_bit(NBD_DISCONNECT_ON_CLOSE,
+ &config->runtime_flags);
+ }
}
if (info->attrs[NBD_ATTR_SOCKETS]) {
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 7948049f6c43..042c778e5a4e 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -1365,7 +1365,7 @@ static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio)
static enum blk_eh_timer_return null_rq_timed_out_fn(struct request *rq)
{
pr_info("null: rq %p timed out\n", rq);
- blk_mq_complete_request(rq);
+ __blk_complete_request(rq);
return BLK_EH_DONE;
}
diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig
index 10c08982185a..9c03f35d9df1 100644
--- a/drivers/lightnvm/Kconfig
+++ b/drivers/lightnvm/Kconfig
@@ -4,7 +4,7 @@
menuconfig NVM
bool "Open-Channel SSD target support"
- depends on BLOCK && HAS_DMA && PCI
+ depends on BLOCK && PCI
select BLK_DEV_NVME
help
Say Y here to get to enable Open-channel SSDs.
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 21710a7460c8..46df030b2c3f 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1808,6 +1808,7 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
u32 max_segments =
(ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1;
+ max_segments = min_not_zero(max_segments, ctrl->max_segments);
blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
}
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index b528a2f5826c..41d45a1b5c62 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2790,6 +2790,9 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl)
/* re-enable the admin_q so anything new can fast fail */
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ /* resume the io queues so that things will fast fail */
+ nvme_start_queues(&ctrl->ctrl);
+
nvme_fc_ctlr_inactive_on_rport(ctrl);
}
@@ -2804,9 +2807,6 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl)
* waiting for io to terminate
*/
nvme_fc_delete_association(ctrl);
-
- /* resume the io queues so that things will fast fail */
- nvme_start_queues(nctrl);
}
static void
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 231807cbc849..0c4a33df3b2f 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -170,6 +170,7 @@ struct nvme_ctrl {
u64 cap;
u32 page_size;
u32 max_hw_sectors;
+ u32 max_segments;
u16 oncs;
u16 oacs;
u16 nssa;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index fc33804662e7..ba943f211687 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -38,6 +38,13 @@
#define SGES_PER_PAGE (PAGE_SIZE / sizeof(struct nvme_sgl_desc))
+/*
+ * These can be higher, but we need to ensure that any command doesn't
+ * require an sg allocation that needs more than a page of data.
+ */
+#define NVME_MAX_KB_SZ 4096
+#define NVME_MAX_SEGS 127
+
static int use_threaded_interrupts;
module_param(use_threaded_interrupts, int, 0);
@@ -100,6 +107,8 @@ struct nvme_dev {
struct nvme_ctrl ctrl;
struct completion ioq_wait;
+ mempool_t *iod_mempool;
+
/* shadow doorbell buffer support: */
u32 *dbbuf_dbs;
dma_addr_t dbbuf_dbs_dma_addr;
@@ -477,10 +486,7 @@ static blk_status_t nvme_init_iod(struct request *rq, struct nvme_dev *dev)
iod->use_sgl = nvme_pci_use_sgls(dev, rq);
if (nseg > NVME_INT_PAGES || size > NVME_INT_BYTES(dev)) {
- size_t alloc_size = nvme_pci_iod_alloc_size(dev, size, nseg,
- iod->use_sgl);
-
- iod->sg = kmalloc(alloc_size, GFP_ATOMIC);
+ iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC);
if (!iod->sg)
return BLK_STS_RESOURCE;
} else {
@@ -526,7 +532,7 @@ static void nvme_free_iod(struct nvme_dev *dev, struct request *req)
}
if (iod->sg != iod->inline_sg)
- kfree(iod->sg);
+ mempool_free(iod->sg, dev->iod_mempool);
}
#ifdef CONFIG_BLK_DEV_INTEGRITY
@@ -2280,6 +2286,7 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
blk_put_queue(dev->ctrl.admin_q);
kfree(dev->queues);
free_opal_dev(dev->ctrl.opal_dev);
+ mempool_destroy(dev->iod_mempool);
kfree(dev);
}
@@ -2289,6 +2296,7 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status)
nvme_get_ctrl(&dev->ctrl);
nvme_dev_disable(dev, false);
+ nvme_kill_queues(&dev->ctrl);
if (!queue_work(nvme_wq, &dev->remove_work))
nvme_put_ctrl(&dev->ctrl);
}
@@ -2333,6 +2341,13 @@ static void nvme_reset_work(struct work_struct *work)
if (result)
goto out;
+ /*
+ * Limit the max command size to prevent iod->sg allocations going
+ * over a single page.
+ */
+ dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1;
+ dev->ctrl.max_segments = NVME_MAX_SEGS;
+
result = nvme_init_identify(&dev->ctrl);
if (result)
goto out;
@@ -2405,7 +2420,6 @@ static void nvme_remove_dead_ctrl_work(struct work_struct *work)
struct nvme_dev *dev = container_of(work, struct nvme_dev, remove_work);
struct pci_dev *pdev = to_pci_dev(dev->dev);
- nvme_kill_queues(&dev->ctrl);
if (pci_get_drvdata(pdev))
device_release_driver(&pdev->dev);
nvme_put_ctrl(&dev->ctrl);
@@ -2509,6 +2523,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
int node, result = -ENOMEM;
struct nvme_dev *dev;
unsigned long quirks = id->driver_data;
+ size_t alloc_size;
node = dev_to_node(&pdev->dev);
if (node == NUMA_NO_NODE)
@@ -2546,6 +2561,23 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (result)
goto release_pools;
+ /*
+ * Double check that our mempool alloc size will cover the biggest
+ * command we support.
+ */
+ alloc_size = nvme_pci_iod_alloc_size(dev, NVME_MAX_KB_SZ,
+ NVME_MAX_SEGS, true);
+ WARN_ON_ONCE(alloc_size > PAGE_SIZE);
+
+ dev->iod_mempool = mempool_create_node(1, mempool_kmalloc,
+ mempool_kfree,
+ (void *) alloc_size,
+ GFP_KERNEL, node);
+ if (!dev->iod_mempool) {
+ result = -ENOMEM;
+ goto release_pools;
+ }
+
dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
nvme_get_ctrl(&dev->ctrl);
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index c9424da0d23e..9544625c0b7d 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -560,12 +560,6 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue)
if (!test_and_clear_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags))
return;
- if (nvme_rdma_queue_idx(queue) == 0) {
- nvme_rdma_free_qe(queue->device->dev,
- &queue->ctrl->async_event_sqe,
- sizeof(struct nvme_command), DMA_TO_DEVICE);
- }
-
nvme_rdma_destroy_queue_ib(queue);
rdma_destroy_id(queue->cm_id);
}
@@ -698,7 +692,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl,
set = &ctrl->tag_set;
memset(set, 0, sizeof(*set));
set->ops = &nvme_rdma_mq_ops;
- set->queue_depth = nctrl->opts->queue_size;
+ set->queue_depth = nctrl->sqsize + 1;
set->reserved_tags = 1; /* fabric connect */
set->numa_node = NUMA_NO_NODE;
set->flags = BLK_MQ_F_SHOULD_MERGE;
@@ -734,11 +728,12 @@ out:
static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
- nvme_rdma_stop_queue(&ctrl->queues[0]);
if (remove) {
blk_cleanup_queue(ctrl->ctrl.admin_q);
nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset);
}
+ nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+ sizeof(struct nvme_command), DMA_TO_DEVICE);
nvme_rdma_free_queue(&ctrl->queues[0]);
}
@@ -755,11 +750,16 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
ctrl->max_fr_pages = nvme_rdma_get_max_fr_pages(ctrl->device->dev);
+ error = nvme_rdma_alloc_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+ sizeof(struct nvme_command), DMA_TO_DEVICE);
+ if (error)
+ goto out_free_queue;
+
if (new) {
ctrl->ctrl.admin_tagset = nvme_rdma_alloc_tagset(&ctrl->ctrl, true);
if (IS_ERR(ctrl->ctrl.admin_tagset)) {
error = PTR_ERR(ctrl->ctrl.admin_tagset);
- goto out_free_queue;
+ goto out_free_async_qe;
}
ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
@@ -795,12 +795,6 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
if (error)
goto out_stop_queue;
- error = nvme_rdma_alloc_qe(ctrl->queues[0].device->dev,
- &ctrl->async_event_sqe, sizeof(struct nvme_command),
- DMA_TO_DEVICE);
- if (error)
- goto out_stop_queue;
-
return 0;
out_stop_queue:
@@ -811,6 +805,9 @@ out_cleanup_queue:
out_free_tagset:
if (new)
nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset);
+out_free_async_qe:
+ nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe,
+ sizeof(struct nvme_command), DMA_TO_DEVICE);
out_free_queue:
nvme_rdma_free_queue(&ctrl->queues[0]);
return error;
@@ -819,7 +816,6 @@ out_free_queue:
static void nvme_rdma_destroy_io_queues(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
- nvme_rdma_stop_io_queues(ctrl);
if (remove) {
blk_cleanup_queue(ctrl->ctrl.connect_q);
nvme_rdma_free_tagset(&ctrl->ctrl, ctrl->ctrl.tagset);
@@ -888,9 +884,9 @@ static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
list_del(&ctrl->list);
mutex_unlock(&nvme_rdma_ctrl_mutex);
- kfree(ctrl->queues);
nvmf_free_options(nctrl->opts);
free_ctrl:
+ kfree(ctrl->queues);
kfree(ctrl);
}
@@ -949,6 +945,7 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
return;
destroy_admin:
+ nvme_rdma_stop_queue(&ctrl->queues[0]);
nvme_rdma_destroy_admin_queue(ctrl, false);
requeue:
dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
@@ -965,12 +962,14 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
if (ctrl->ctrl.queue_count > 1) {
nvme_stop_queues(&ctrl->ctrl);
+ nvme_rdma_stop_io_queues(ctrl);
blk_mq_tagset_busy_iter(&ctrl->tag_set,
nvme_cancel_request, &ctrl->ctrl);
nvme_rdma_destroy_io_queues(ctrl, false);
}
blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_rdma_stop_queue(&ctrl->queues[0]);
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_cancel_request, &ctrl->ctrl);
nvme_rdma_destroy_admin_queue(ctrl, false);
@@ -1736,6 +1735,7 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
{
if (ctrl->ctrl.queue_count > 1) {
nvme_stop_queues(&ctrl->ctrl);
+ nvme_rdma_stop_io_queues(ctrl);
blk_mq_tagset_busy_iter(&ctrl->tag_set,
nvme_cancel_request, &ctrl->ctrl);
nvme_rdma_destroy_io_queues(ctrl, shutdown);
@@ -1747,6 +1747,7 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
nvme_disable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_rdma_stop_queue(&ctrl->queues[0]);
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_cancel_request, &ctrl->ctrl);
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
@@ -1932,11 +1933,6 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
goto out_free_ctrl;
}
- ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
- 0 /* no quirks, we're perfect! */);
- if (ret)
- goto out_free_ctrl;
-
INIT_DELAYED_WORK(&ctrl->reconnect_work,
nvme_rdma_reconnect_ctrl_work);
INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work);
@@ -1950,14 +1946,19 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
ctrl->queues = kcalloc(ctrl->ctrl.queue_count, sizeof(*ctrl->queues),
GFP_KERNEL);
if (!ctrl->queues)
- goto out_uninit_ctrl;
+ goto out_free_ctrl;
+
+ ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
+ 0 /* no quirks, we're perfect! */);
+ if (ret)
+ goto out_kfree_queues;
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING);
WARN_ON_ONCE(!changed);
ret = nvme_rdma_configure_admin_queue(ctrl, true);
if (ret)
- goto out_kfree_queues;
+ goto out_uninit_ctrl;
/* sanity check icdoff */
if (ctrl->ctrl.icdoff) {
@@ -1974,20 +1975,19 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
goto out_remove_admin_queue;
}
- if (opts->queue_size > ctrl->ctrl.maxcmd) {
- /* warn if maxcmd is lower than queue_size */
- dev_warn(ctrl->ctrl.device,
- "queue_size %zu > ctrl maxcmd %u, clamping down\n",
- opts->queue_size, ctrl->ctrl.maxcmd);
- opts->queue_size = ctrl->ctrl.maxcmd;
- }
-
+ /* only warn if argument is too large here, will clamp later */
if (opts->queue_size > ctrl->ctrl.sqsize + 1) {
- /* warn if sqsize is lower than queue_size */
dev_warn(ctrl->ctrl.device,
"queue_size %zu > ctrl sqsize %u, clamping down\n",
opts->queue_size, ctrl->ctrl.sqsize + 1);
- opts->queue_size = ctrl->ctrl.sqsize + 1;
+ }
+
+ /* warn if maxcmd is lower than sqsize+1 */
+ if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
+ dev_warn(ctrl->ctrl.device,
+ "sqsize %u > ctrl maxcmd %u, clamping down\n",
+ ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd);
+ ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;
}
if (opts->nr_io_queues) {
@@ -2013,15 +2013,16 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
return &ctrl->ctrl;
out_remove_admin_queue:
+ nvme_rdma_stop_queue(&ctrl->queues[0]);
nvme_rdma_destroy_admin_queue(ctrl, true);
-out_kfree_queues:
- kfree(ctrl->queues);
out_uninit_ctrl:
nvme_uninit_ctrl(&ctrl->ctrl);
nvme_put_ctrl(&ctrl->ctrl);
if (ret > 0)
ret = -EIO;
return ERR_PTR(ret);
+out_kfree_queues:
+ kfree(ctrl->queues);
out_free_ctrl:
kfree(ctrl);
return ERR_PTR(ret);
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index a03da764ecae..74d4b785d2da 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -686,6 +686,14 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl)
}
ctrl->csts = NVME_CSTS_RDY;
+
+ /*
+ * Controllers that are not yet enabled should not really enforce the
+ * keep alive timeout, 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.
+ */
+ mod_delayed_work(system_wq, &ctrl->ka_work, ctrl->kato * HZ);
}
static void nvmet_clear_ctrl(struct nvmet_ctrl *ctrl)
diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index 1da3d71e9f61..13948102ca29 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -3592,7 +3592,7 @@ fc_bsg_job_timeout(struct request *req)
/* the blk_end_sync_io() doesn't check the error */
if (inflight)
- blk_mq_complete_request(req);
+ __blk_complete_request(req);
return BLK_EH_DONE;
}
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 0bd432a4d7bd..24251762c20c 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -22,7 +22,6 @@ struct dentry;
*/
enum wb_state {
WB_registered, /* bdi_register() was done */
- WB_shutting_down, /* wb_shutdown() in progress */
WB_writeback_running, /* Writeback is in progress */
WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */
WB_start_all, /* nr_pages == 0 (all) work pending */
@@ -189,6 +188,7 @@ struct backing_dev_info {
#ifdef CONFIG_CGROUP_WRITEBACK
struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
struct rb_root cgwb_congested_tree; /* their congested states */
+ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */
#else
struct bdi_writeback_congested *wb_congested;
#endif
diff --git a/include/uapi/linux/nbd.h b/include/uapi/linux/nbd.h
index 85a3fb65e40a..20d6cc91435d 100644
--- a/include/uapi/linux/nbd.h
+++ b/include/uapi/linux/nbd.h
@@ -53,6 +53,9 @@ enum {
/* These are client behavior specific flags. */
#define NBD_CFLAG_DESTROY_ON_DISCONNECT (1 << 0) /* delete the nbd device on
disconnect. */
+#define NBD_CFLAG_DISCONNECT_ON_CLOSE (1 << 1) /* disconnect the nbd device on
+ * close by last opener.
+ */
/* userspace doesn't need the nbd_device structure */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 347cc834c04a..2e5d3df0853d 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -359,15 +359,8 @@ static void wb_shutdown(struct bdi_writeback *wb)
spin_lock_bh(&wb->work_lock);
if (!test_and_clear_bit(WB_registered, &wb->state)) {
spin_unlock_bh(&wb->work_lock);
- /*
- * Wait for wb shutdown to finish if someone else is just
- * running wb_shutdown(). Otherwise we could proceed to wb /
- * bdi destruction before wb_shutdown() is finished.
- */
- wait_on_bit(&wb->state, WB_shutting_down, TASK_UNINTERRUPTIBLE);
return;
}
- set_bit(WB_shutting_down, &wb->state);
spin_unlock_bh(&wb->work_lock);
cgwb_remove_from_bdi_list(wb);
@@ -379,12 +372,6 @@ static void wb_shutdown(struct bdi_writeback *wb)
mod_delayed_work(bdi_wq, &wb->dwork, 0);
flush_delayed_work(&wb->dwork);
WARN_ON(!list_empty(&wb->work_list));
- /*
- * Make sure bit gets cleared after shutdown is finished. Matches with
- * the barrier provided by test_and_clear_bit() above.
- */
- smp_wmb();
- clear_and_wake_up_bit(WB_shutting_down, &wb->state);
}
static void wb_exit(struct bdi_writeback *wb)
@@ -508,10 +495,12 @@ static void cgwb_release_workfn(struct work_struct *work)
struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
release_work);
+ mutex_lock(&wb->bdi->cgwb_release_mutex);
wb_shutdown(wb);
css_put(wb->memcg_css);
css_put(wb->blkcg_css);
+ mutex_unlock(&wb->bdi->cgwb_release_mutex);
fprop_local_destroy_percpu(&wb->memcg_completions);
percpu_ref_exit(&wb->refcnt);
@@ -697,6 +686,7 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC);
bdi->cgwb_congested_tree = RB_ROOT;
+ mutex_init(&bdi->cgwb_release_mutex);
ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
if (!ret) {
@@ -717,7 +707,10 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi)
spin_lock_irq(&cgwb_lock);
radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0)
cgwb_kill(*slot);
+ spin_unlock_irq(&cgwb_lock);
+ mutex_lock(&bdi->cgwb_release_mutex);
+ spin_lock_irq(&cgwb_lock);
while (!list_empty(&bdi->wb_list)) {
wb = list_first_entry(&bdi->wb_list, struct bdi_writeback,
bdi_node);
@@ -726,6 +719,7 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi)
spin_lock_irq(&cgwb_lock);
}
spin_unlock_irq(&cgwb_lock);
+ mutex_unlock(&bdi->cgwb_release_mutex);
}
/**