summaryrefslogtreecommitdiff
path: root/drivers/block/rbd.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/block/rbd.c')
-rw-r--r--drivers/block/rbd.c149
1 files changed, 94 insertions, 55 deletions
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 07dc5419bd63..af354047ac4b 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -424,7 +424,7 @@ static struct workqueue_struct *rbd_wq;
* single-major requires >= 0.75 version of userspace rbd utility.
*/
static bool single_major = true;
-module_param(single_major, bool, S_IRUGO);
+module_param(single_major, bool, 0444);
MODULE_PARM_DESC(single_major, "Use a single major number for all rbd devices (default: true)");
static ssize_t rbd_add(struct bus_type *bus, const char *buf,
@@ -468,11 +468,11 @@ static ssize_t rbd_supported_features_show(struct bus_type *bus, char *buf)
return sprintf(buf, "0x%llx\n", RBD_FEATURES_SUPPORTED);
}
-static BUS_ATTR(add, S_IWUSR, NULL, rbd_add);
-static BUS_ATTR(remove, S_IWUSR, NULL, rbd_remove);
-static BUS_ATTR(add_single_major, S_IWUSR, NULL, rbd_add_single_major);
-static BUS_ATTR(remove_single_major, S_IWUSR, NULL, rbd_remove_single_major);
-static BUS_ATTR(supported_features, S_IRUGO, rbd_supported_features_show, NULL);
+static BUS_ATTR(add, 0200, NULL, rbd_add);
+static BUS_ATTR(remove, 0200, NULL, rbd_remove);
+static BUS_ATTR(add_single_major, 0200, NULL, rbd_add_single_major);
+static BUS_ATTR(remove_single_major, 0200, NULL, rbd_remove_single_major);
+static BUS_ATTR(supported_features, 0444, rbd_supported_features_show, NULL);
static struct attribute *rbd_bus_attrs[] = {
&bus_attr_add.attr,
@@ -732,6 +732,7 @@ static struct rbd_client *rbd_client_find(struct ceph_options *ceph_opts)
*/
enum {
Opt_queue_depth,
+ Opt_lock_timeout,
Opt_last_int,
/* int args above */
Opt_last_string,
@@ -740,11 +741,13 @@ enum {
Opt_read_write,
Opt_lock_on_read,
Opt_exclusive,
+ Opt_notrim,
Opt_err
};
static match_table_t rbd_opts_tokens = {
{Opt_queue_depth, "queue_depth=%d"},
+ {Opt_lock_timeout, "lock_timeout=%d"},
/* int args above */
/* string args above */
{Opt_read_only, "read_only"},
@@ -753,20 +756,25 @@ static match_table_t rbd_opts_tokens = {
{Opt_read_write, "rw"}, /* Alternate spelling */
{Opt_lock_on_read, "lock_on_read"},
{Opt_exclusive, "exclusive"},
+ {Opt_notrim, "notrim"},
{Opt_err, NULL}
};
struct rbd_options {
int queue_depth;
+ unsigned long lock_timeout;
bool read_only;
bool lock_on_read;
bool exclusive;
+ bool trim;
};
#define RBD_QUEUE_DEPTH_DEFAULT BLKDEV_MAX_RQ
+#define RBD_LOCK_TIMEOUT_DEFAULT 0 /* no timeout */
#define RBD_READ_ONLY_DEFAULT false
#define RBD_LOCK_ON_READ_DEFAULT false
#define RBD_EXCLUSIVE_DEFAULT false
+#define RBD_TRIM_DEFAULT true
static int parse_rbd_opts_token(char *c, void *private)
{
@@ -796,6 +804,14 @@ static int parse_rbd_opts_token(char *c, void *private)
}
rbd_opts->queue_depth = intval;
break;
+ case Opt_lock_timeout:
+ /* 0 is "wait forever" (i.e. infinite timeout) */
+ if (intval < 0 || intval > INT_MAX / 1000) {
+ pr_err("lock_timeout out of range\n");
+ return -EINVAL;
+ }
+ rbd_opts->lock_timeout = msecs_to_jiffies(intval * 1000);
+ break;
case Opt_read_only:
rbd_opts->read_only = true;
break;
@@ -808,6 +824,9 @@ static int parse_rbd_opts_token(char *c, void *private)
case Opt_exclusive:
rbd_opts->exclusive = true;
break;
+ case Opt_notrim:
+ rbd_opts->trim = false;
+ break;
default:
/* libceph prints "bad option" msg */
return -EINVAL;
@@ -1392,7 +1411,7 @@ static bool rbd_img_is_write(struct rbd_img_request *img_req)
case OBJ_OP_DISCARD:
return true;
default:
- rbd_assert(0);
+ BUG();
}
}
@@ -2347,7 +2366,9 @@ static int rbd_obj_issue_copyup(struct rbd_obj_request *obj_req, u32 bytes)
osd_req_op_cls_init(obj_req->osd_req, 0, CEPH_OSD_OP_CALL, "rbd",
"copyup");
osd_req_op_cls_request_data_bvecs(obj_req->osd_req, 0,
- obj_req->copyup_bvecs, bytes);
+ obj_req->copyup_bvecs,
+ obj_req->copyup_bvec_count,
+ bytes);
switch (obj_req->img_request->op_type) {
case OBJ_OP_WRITE:
@@ -2466,7 +2487,7 @@ again:
}
return false;
default:
- rbd_assert(0);
+ BUG();
}
}
@@ -2494,7 +2515,7 @@ static bool __rbd_obj_handle_request(struct rbd_obj_request *obj_req)
}
return false;
default:
- rbd_assert(0);
+ BUG();
}
}
@@ -3533,9 +3554,22 @@ static int rbd_obj_method_sync(struct rbd_device *rbd_dev,
/*
* lock_rwsem must be held for read
*/
-static void rbd_wait_state_locked(struct rbd_device *rbd_dev)
+static int rbd_wait_state_locked(struct rbd_device *rbd_dev, bool may_acquire)
{
DEFINE_WAIT(wait);
+ unsigned long timeout;
+ int ret = 0;
+
+ if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags))
+ return -EBLACKLISTED;
+
+ if (rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED)
+ return 0;
+
+ if (!may_acquire) {
+ rbd_warn(rbd_dev, "exclusive lock required");
+ return -EROFS;
+ }
do {
/*
@@ -3547,12 +3581,22 @@ static void rbd_wait_state_locked(struct rbd_device *rbd_dev)
prepare_to_wait_exclusive(&rbd_dev->lock_waitq, &wait,
TASK_UNINTERRUPTIBLE);
up_read(&rbd_dev->lock_rwsem);
- schedule();
+ timeout = schedule_timeout(ceph_timeout_jiffies(
+ rbd_dev->opts->lock_timeout));
down_read(&rbd_dev->lock_rwsem);
- } while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
- !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags));
+ if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
+ ret = -EBLACKLISTED;
+ break;
+ }
+ if (!timeout) {
+ rbd_warn(rbd_dev, "timed out waiting for lock");
+ ret = -ETIMEDOUT;
+ break;
+ }
+ } while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED);
finish_wait(&rbd_dev->lock_waitq, &wait);
+ return ret;
}
static void rbd_queue_workfn(struct work_struct *work)
@@ -3638,19 +3682,10 @@ static void rbd_queue_workfn(struct work_struct *work)
(op_type != OBJ_OP_READ || rbd_dev->opts->lock_on_read);
if (must_be_locked) {
down_read(&rbd_dev->lock_rwsem);
- if (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
- !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
- if (rbd_dev->opts->exclusive) {
- rbd_warn(rbd_dev, "exclusive lock required");
- result = -EROFS;
- goto err_unlock;
- }
- rbd_wait_state_locked(rbd_dev);
- }
- if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
- result = -EBLACKLISTED;
+ result = rbd_wait_state_locked(rbd_dev,
+ !rbd_dev->opts->exclusive);
+ if (result)
goto err_unlock;
- }
}
img_request = rbd_img_request_create(rbd_dev, op_type, snapc);
@@ -3902,7 +3937,8 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
{
struct gendisk *disk;
struct request_queue *q;
- u64 segment_size;
+ unsigned int objset_bytes =
+ rbd_dev->layout.object_size * rbd_dev->layout.stripe_count;
int err;
/* create gendisk info */
@@ -3942,20 +3978,19 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
/* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */
- /* set io sizes to object size */
- segment_size = rbd_obj_bytes(&rbd_dev->header);
- blk_queue_max_hw_sectors(q, segment_size / SECTOR_SIZE);
+ blk_queue_max_hw_sectors(q, objset_bytes >> SECTOR_SHIFT);
q->limits.max_sectors = queue_max_hw_sectors(q);
blk_queue_max_segments(q, USHRT_MAX);
blk_queue_max_segment_size(q, UINT_MAX);
- blk_queue_io_min(q, segment_size);
- blk_queue_io_opt(q, segment_size);
+ blk_queue_io_min(q, objset_bytes);
+ blk_queue_io_opt(q, objset_bytes);
- /* enable the discard support */
- blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
- q->limits.discard_granularity = segment_size;
- blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE);
- blk_queue_max_write_zeroes_sectors(q, segment_size / SECTOR_SIZE);
+ if (rbd_dev->opts->trim) {
+ blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
+ q->limits.discard_granularity = objset_bytes;
+ blk_queue_max_discard_sectors(q, objset_bytes >> SECTOR_SHIFT);
+ blk_queue_max_write_zeroes_sectors(q, objset_bytes >> SECTOR_SHIFT);
+ }
if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
@@ -4169,22 +4204,22 @@ static ssize_t rbd_image_refresh(struct device *dev,
return size;
}
-static DEVICE_ATTR(size, S_IRUGO, rbd_size_show, NULL);
-static DEVICE_ATTR(features, S_IRUGO, rbd_features_show, NULL);
-static DEVICE_ATTR(major, S_IRUGO, rbd_major_show, NULL);
-static DEVICE_ATTR(minor, S_IRUGO, rbd_minor_show, NULL);
-static DEVICE_ATTR(client_addr, S_IRUGO, rbd_client_addr_show, NULL);
-static DEVICE_ATTR(client_id, S_IRUGO, rbd_client_id_show, NULL);
-static DEVICE_ATTR(cluster_fsid, S_IRUGO, rbd_cluster_fsid_show, NULL);
-static DEVICE_ATTR(config_info, S_IRUSR, rbd_config_info_show, NULL);
-static DEVICE_ATTR(pool, S_IRUGO, rbd_pool_show, NULL);
-static DEVICE_ATTR(pool_id, S_IRUGO, rbd_pool_id_show, NULL);
-static DEVICE_ATTR(name, S_IRUGO, rbd_name_show, NULL);
-static DEVICE_ATTR(image_id, S_IRUGO, rbd_image_id_show, NULL);
-static DEVICE_ATTR(refresh, S_IWUSR, NULL, rbd_image_refresh);
-static DEVICE_ATTR(current_snap, S_IRUGO, rbd_snap_show, NULL);
-static DEVICE_ATTR(snap_id, S_IRUGO, rbd_snap_id_show, NULL);
-static DEVICE_ATTR(parent, S_IRUGO, rbd_parent_show, NULL);
+static DEVICE_ATTR(size, 0444, rbd_size_show, NULL);
+static DEVICE_ATTR(features, 0444, rbd_features_show, NULL);
+static DEVICE_ATTR(major, 0444, rbd_major_show, NULL);
+static DEVICE_ATTR(minor, 0444, rbd_minor_show, NULL);
+static DEVICE_ATTR(client_addr, 0444, rbd_client_addr_show, NULL);
+static DEVICE_ATTR(client_id, 0444, rbd_client_id_show, NULL);
+static DEVICE_ATTR(cluster_fsid, 0444, rbd_cluster_fsid_show, NULL);
+static DEVICE_ATTR(config_info, 0400, rbd_config_info_show, NULL);
+static DEVICE_ATTR(pool, 0444, rbd_pool_show, NULL);
+static DEVICE_ATTR(pool_id, 0444, rbd_pool_id_show, NULL);
+static DEVICE_ATTR(name, 0444, rbd_name_show, NULL);
+static DEVICE_ATTR(image_id, 0444, rbd_image_id_show, NULL);
+static DEVICE_ATTR(refresh, 0200, NULL, rbd_image_refresh);
+static DEVICE_ATTR(current_snap, 0444, rbd_snap_show, NULL);
+static DEVICE_ATTR(snap_id, 0444, rbd_snap_id_show, NULL);
+static DEVICE_ATTR(parent, 0444, rbd_parent_show, NULL);
static struct attribute *rbd_attrs[] = {
&dev_attr_size.attr,
@@ -5179,8 +5214,10 @@ static int rbd_add_parse_args(const char *buf,
rbd_opts->read_only = RBD_READ_ONLY_DEFAULT;
rbd_opts->queue_depth = RBD_QUEUE_DEPTH_DEFAULT;
+ rbd_opts->lock_timeout = RBD_LOCK_TIMEOUT_DEFAULT;
rbd_opts->lock_on_read = RBD_LOCK_ON_READ_DEFAULT;
rbd_opts->exclusive = RBD_EXCLUSIVE_DEFAULT;
+ rbd_opts->trim = RBD_TRIM_DEFAULT;
copts = ceph_parse_options(options, mon_addrs,
mon_addrs + mon_addrs_size - 1,
@@ -5216,6 +5253,8 @@ static void rbd_dev_image_unlock(struct rbd_device *rbd_dev)
static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
{
+ int ret;
+
if (!(rbd_dev->header.features & RBD_FEATURE_EXCLUSIVE_LOCK)) {
rbd_warn(rbd_dev, "exclusive-lock feature is not enabled");
return -EINVAL;
@@ -5223,9 +5262,9 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
/* FIXME: "rbd map --exclusive" should be in interruptible */
down_read(&rbd_dev->lock_rwsem);
- rbd_wait_state_locked(rbd_dev);
+ ret = rbd_wait_state_locked(rbd_dev, true);
up_read(&rbd_dev->lock_rwsem);
- if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
+ if (ret) {
rbd_warn(rbd_dev, "failed to acquire exclusive lock");
return -EROFS;
}