summaryrefslogtreecommitdiff
path: root/drivers/block
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/block')
-rw-r--r--drivers/block/nbd.c36
-rw-r--r--drivers/block/nvme-core.c24
-rw-r--r--drivers/block/rbd.c82
-rw-r--r--drivers/block/xen-blkfront.c3
4 files changed, 97 insertions, 48 deletions
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 293495a75d3d..1b87623381e2 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -60,6 +60,7 @@ struct nbd_device {
bool disconnect; /* a disconnect has been requested by user */
struct timer_list timeout_timer;
+ spinlock_t tasks_lock;
struct task_struct *task_recv;
struct task_struct *task_send;
@@ -140,21 +141,23 @@ static void sock_shutdown(struct nbd_device *nbd)
static void nbd_xmit_timeout(unsigned long arg)
{
struct nbd_device *nbd = (struct nbd_device *)arg;
- struct task_struct *task;
+ unsigned long flags;
if (list_empty(&nbd->queue_head))
return;
nbd->disconnect = true;
- task = READ_ONCE(nbd->task_recv);
- if (task)
- force_sig(SIGKILL, task);
+ spin_lock_irqsave(&nbd->tasks_lock, flags);
+
+ if (nbd->task_recv)
+ force_sig(SIGKILL, nbd->task_recv);
- task = READ_ONCE(nbd->task_send);
- if (task)
+ if (nbd->task_send)
force_sig(SIGKILL, nbd->task_send);
+ spin_unlock_irqrestore(&nbd->tasks_lock, flags);
+
dev_err(nbd_to_dev(nbd), "Connection timed out, killed receiver and sender, shutting down connection\n");
}
@@ -403,17 +406,24 @@ static int nbd_thread_recv(struct nbd_device *nbd)
{
struct request *req;
int ret;
+ unsigned long flags;
BUG_ON(nbd->magic != NBD_MAGIC);
sk_set_memalloc(nbd->sock->sk);
+ spin_lock_irqsave(&nbd->tasks_lock, flags);
nbd->task_recv = current;
+ spin_unlock_irqrestore(&nbd->tasks_lock, flags);
ret = device_create_file(disk_to_dev(nbd->disk), &pid_attr);
if (ret) {
dev_err(disk_to_dev(nbd->disk), "device_create_file failed!\n");
+
+ spin_lock_irqsave(&nbd->tasks_lock, flags);
nbd->task_recv = NULL;
+ spin_unlock_irqrestore(&nbd->tasks_lock, flags);
+
return ret;
}
@@ -429,7 +439,9 @@ static int nbd_thread_recv(struct nbd_device *nbd)
device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
+ spin_lock_irqsave(&nbd->tasks_lock, flags);
nbd->task_recv = NULL;
+ spin_unlock_irqrestore(&nbd->tasks_lock, flags);
if (signal_pending(current)) {
siginfo_t info;
@@ -534,8 +546,11 @@ static int nbd_thread_send(void *data)
{
struct nbd_device *nbd = data;
struct request *req;
+ unsigned long flags;
+ spin_lock_irqsave(&nbd->tasks_lock, flags);
nbd->task_send = current;
+ spin_unlock_irqrestore(&nbd->tasks_lock, flags);
set_user_nice(current, MIN_NICE);
while (!kthread_should_stop() || !list_empty(&nbd->waiting_queue)) {
@@ -572,7 +587,15 @@ static int nbd_thread_send(void *data)
nbd_handle_req(nbd, req);
}
+ spin_lock_irqsave(&nbd->tasks_lock, flags);
nbd->task_send = NULL;
+ spin_unlock_irqrestore(&nbd->tasks_lock, flags);
+
+ /* Clear maybe pending signals */
+ if (signal_pending(current)) {
+ siginfo_t info;
+ dequeue_signal_lock(current, &current->blocked, &info);
+ }
return 0;
}
@@ -1052,6 +1075,7 @@ static int __init nbd_init(void)
nbd_dev[i].magic = NBD_MAGIC;
INIT_LIST_HEAD(&nbd_dev[i].waiting_queue);
spin_lock_init(&nbd_dev[i].queue_lock);
+ spin_lock_init(&nbd_dev[i].tasks_lock);
INIT_LIST_HEAD(&nbd_dev[i].queue_head);
mutex_init(&nbd_dev[i].tx_lock);
init_timer(&nbd_dev[i].timeout_timer);
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index 6f04771f1019..ccc0c1f93daa 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -603,27 +603,31 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
struct nvme_iod *iod = ctx;
struct request *req = iod_get_private(iod);
struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
-
u16 status = le16_to_cpup(&cqe->status) >> 1;
+ bool requeue = false;
+ int error = 0;
if (unlikely(status)) {
if (!(status & NVME_SC_DNR || blk_noretry_request(req))
&& (jiffies - req->start_time) < req->timeout) {
unsigned long flags;
+ requeue = true;
blk_mq_requeue_request(req);
spin_lock_irqsave(req->q->queue_lock, flags);
if (!blk_queue_stopped(req->q))
blk_mq_kick_requeue_list(req->q);
spin_unlock_irqrestore(req->q->queue_lock, flags);
- return;
+ goto release_iod;
}
if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
if (cmd_rq->ctx == CMD_CTX_CANCELLED)
- status = -EINTR;
+ error = -EINTR;
+ else
+ error = status;
} else {
- status = nvme_error_status(status);
+ error = nvme_error_status(status);
}
}
@@ -635,8 +639,9 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
if (cmd_rq->aborted)
dev_warn(nvmeq->dev->dev,
"completing aborted command with status:%04x\n",
- status);
+ error);
+release_iod:
if (iod->nents) {
dma_unmap_sg(nvmeq->dev->dev, iod->sg, iod->nents,
rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
@@ -649,7 +654,8 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
}
nvme_free_iod(nvmeq->dev, iod);
- blk_mq_complete_request(req, status);
+ if (likely(!requeue))
+ blk_mq_complete_request(req, error);
}
/* length is in bytes. gfp flags indicates whether we may sleep. */
@@ -1804,7 +1810,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
length = (io.nblocks + 1) << ns->lba_shift;
meta_len = (io.nblocks + 1) * ns->ms;
- metadata = (void __user *)(unsigned long)io.metadata;
+ metadata = (void __user *)(uintptr_t)io.metadata;
write = io.opcode & 1;
if (ns->ext) {
@@ -1844,7 +1850,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
c.rw.metadata = cpu_to_le64(meta_dma);
status = __nvme_submit_sync_cmd(ns->queue, &c, NULL,
- (void __user *)io.addr, length, NULL, 0);
+ (void __user *)(uintptr_t)io.addr, length, NULL, 0);
unmap:
if (meta) {
if (status == NVME_SC_SUCCESS && !write) {
@@ -1886,7 +1892,7 @@ static int nvme_user_cmd(struct nvme_dev *dev, struct nvme_ns *ns,
timeout = msecs_to_jiffies(cmd.timeout_ms);
status = __nvme_submit_sync_cmd(ns ? ns->queue : dev->admin_q, &c,
- NULL, (void __user *)cmd.addr, cmd.data_len,
+ NULL, (void __user *)(uintptr_t)cmd.addr, cmd.data_len,
&cmd.result, timeout);
if (status >= 0) {
if (put_user(cmd.result, &ucmd->result))
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index d93a0372b37b..128e7df5b807 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -96,6 +96,8 @@ static int atomic_dec_return_safe(atomic_t *v)
#define RBD_MINORS_PER_MAJOR 256
#define RBD_SINGLE_MAJOR_PART_SHIFT 4
+#define RBD_MAX_PARENT_CHAIN_LEN 16
+
#define RBD_SNAP_DEV_NAME_PREFIX "snap_"
#define RBD_MAX_SNAP_NAME_LEN \
(NAME_MAX - (sizeof (RBD_SNAP_DEV_NAME_PREFIX) - 1))
@@ -426,7 +428,7 @@ static ssize_t rbd_add_single_major(struct bus_type *bus, const char *buf,
size_t count);
static ssize_t rbd_remove_single_major(struct bus_type *bus, const char *buf,
size_t count);
-static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping);
+static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth);
static void rbd_spec_put(struct rbd_spec *spec);
static int rbd_dev_id_to_minor(int dev_id)
@@ -1863,9 +1865,11 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
rbd_osd_read_callback(obj_request);
break;
case CEPH_OSD_OP_SETALLOCHINT:
- rbd_assert(osd_req->r_ops[1].op == CEPH_OSD_OP_WRITE);
+ rbd_assert(osd_req->r_ops[1].op == CEPH_OSD_OP_WRITE ||
+ osd_req->r_ops[1].op == CEPH_OSD_OP_WRITEFULL);
/* fall through */
case CEPH_OSD_OP_WRITE:
+ case CEPH_OSD_OP_WRITEFULL:
rbd_osd_write_callback(obj_request);
break;
case CEPH_OSD_OP_STAT:
@@ -2401,7 +2405,10 @@ static void rbd_img_obj_request_fill(struct rbd_obj_request *obj_request,
opcode = CEPH_OSD_OP_ZERO;
}
} else if (op_type == OBJ_OP_WRITE) {
- opcode = CEPH_OSD_OP_WRITE;
+ if (!offset && length == object_size)
+ opcode = CEPH_OSD_OP_WRITEFULL;
+ else
+ opcode = CEPH_OSD_OP_WRITE;
osd_req_op_alloc_hint_init(osd_request, num_ops,
object_size, object_size);
num_ops++;
@@ -3760,6 +3767,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
/* set io sizes to object size */
segment_size = rbd_obj_bytes(&rbd_dev->header);
blk_queue_max_hw_sectors(q, segment_size / SECTOR_SIZE);
+ q->limits.max_sectors = queue_max_hw_sectors(q);
blk_queue_max_segments(q, segment_size / SECTOR_SIZE);
blk_queue_max_segment_size(q, segment_size);
blk_queue_io_min(q, segment_size);
@@ -3772,6 +3780,9 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE);
q->limits.discard_zeroes_data = 1;
+ if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
+ q->backing_dev_info.capabilities |= BDI_CAP_STABLE_WRITES;
+
disk->queue = q;
q->queuedata = rbd_dev;
@@ -5125,44 +5136,51 @@ out_err:
return ret;
}
-static int rbd_dev_probe_parent(struct rbd_device *rbd_dev)
+/*
+ * @depth is rbd_dev_image_probe() -> rbd_dev_probe_parent() ->
+ * rbd_dev_image_probe() recursion depth, which means it's also the
+ * length of the already discovered part of the parent chain.
+ */
+static int rbd_dev_probe_parent(struct rbd_device *rbd_dev, int depth)
{
struct rbd_device *parent = NULL;
- struct rbd_spec *parent_spec;
- struct rbd_client *rbdc;
int ret;
if (!rbd_dev->parent_spec)
return 0;
- /*
- * We need to pass a reference to the client and the parent
- * spec when creating the parent rbd_dev. Images related by
- * parent/child relationships always share both.
- */
- parent_spec = rbd_spec_get(rbd_dev->parent_spec);
- rbdc = __rbd_get_client(rbd_dev->rbd_client);
- ret = -ENOMEM;
- parent = rbd_dev_create(rbdc, parent_spec, NULL);
- if (!parent)
+ if (++depth > RBD_MAX_PARENT_CHAIN_LEN) {
+ pr_info("parent chain is too long (%d)\n", depth);
+ ret = -EINVAL;
+ goto out_err;
+ }
+
+ parent = rbd_dev_create(rbd_dev->rbd_client, rbd_dev->parent_spec,
+ NULL);
+ if (!parent) {
+ ret = -ENOMEM;
goto out_err;
+ }
- ret = rbd_dev_image_probe(parent, false);
+ /*
+ * Images related by parent/child relationships always share
+ * rbd_client and spec/parent_spec, so bump their refcounts.
+ */
+ __rbd_get_client(rbd_dev->rbd_client);
+ rbd_spec_get(rbd_dev->parent_spec);
+
+ ret = rbd_dev_image_probe(parent, depth);
if (ret < 0)
goto out_err;
+
rbd_dev->parent = parent;
atomic_set(&rbd_dev->parent_ref, 1);
-
return 0;
+
out_err:
- if (parent) {
- rbd_dev_unparent(rbd_dev);
+ rbd_dev_unparent(rbd_dev);
+ if (parent)
rbd_dev_destroy(parent);
- } else {
- rbd_put_client(rbdc);
- rbd_spec_put(parent_spec);
- }
-
return ret;
}
@@ -5280,7 +5298,7 @@ static void rbd_dev_image_release(struct rbd_device *rbd_dev)
* parent), initiate a watch on its header object before using that
* object to get detailed information about the rbd image.
*/
-static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
+static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
{
int ret;
@@ -5298,7 +5316,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
if (ret)
goto err_out_format;
- if (mapping) {
+ if (!depth) {
ret = rbd_dev_header_watch_sync(rbd_dev);
if (ret) {
if (ret == -ENOENT)
@@ -5319,7 +5337,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
* Otherwise this is a parent image, identified by pool, image
* and snap ids - need to fill in names for those ids.
*/
- if (mapping)
+ if (!depth)
ret = rbd_spec_fill_snap_id(rbd_dev);
else
ret = rbd_spec_fill_names(rbd_dev);
@@ -5341,12 +5359,12 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
* Need to warn users if this image is the one being
* mapped and has a parent.
*/
- if (mapping && rbd_dev->parent_spec)
+ if (!depth && rbd_dev->parent_spec)
rbd_warn(rbd_dev,
"WARNING: kernel layering is EXPERIMENTAL!");
}
- ret = rbd_dev_probe_parent(rbd_dev);
+ ret = rbd_dev_probe_parent(rbd_dev, depth);
if (ret)
goto err_out_probe;
@@ -5357,7 +5375,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
err_out_probe:
rbd_dev_unprobe(rbd_dev);
err_out_watch:
- if (mapping)
+ if (!depth)
rbd_dev_header_unwatch_sync(rbd_dev);
out_header_name:
kfree(rbd_dev->header_name);
@@ -5420,7 +5438,7 @@ static ssize_t do_rbd_add(struct bus_type *bus,
spec = NULL; /* rbd_dev now owns this */
rbd_opts = NULL; /* rbd_dev now owns this */
- rc = rbd_dev_image_probe(rbd_dev, true);
+ rc = rbd_dev_image_probe(rbd_dev, 0);
if (rc < 0)
goto err_out_rbd_dev;
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 611170896b8c..a69c02dadec0 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1956,7 +1956,8 @@ static void blkback_changed(struct xenbus_device *dev,
break;
/* Missed the backend's Closing state -- fallthrough */
case XenbusStateClosing:
- blkfront_closing(info);
+ if (info)
+ blkfront_closing(info);
break;
}
}
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-23 17:09:42 +0300