summaryrefslogtreecommitdiffstats
path: root/drivers/block/drbd/drbd_nl.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/block/drbd/drbd_nl.c')
-rw-r--r--drivers/block/drbd/drbd_nl.c268
1 files changed, 130 insertions, 138 deletions
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 43747a1aae..5d65c9754d 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1189,9 +1189,31 @@ static int drbd_check_al_size(struct drbd_device *device, struct disk_conf *dc)
return 0;
}
-static void blk_queue_discard_granularity(struct request_queue *q, unsigned int granularity)
+static unsigned int drbd_max_peer_bio_size(struct drbd_device *device)
{
- q->limits.discard_granularity = granularity;
+ /*
+ * We may ignore peer limits if the peer is modern enough. From 8.3.8
+ * onwards the peer can use multiple BIOs for a single peer_request.
+ */
+ if (device->state.conn < C_WF_REPORT_PARAMS)
+ return device->peer_max_bio_size;
+
+ if (first_peer_device(device)->connection->agreed_pro_version < 94)
+ return min(device->peer_max_bio_size, DRBD_MAX_SIZE_H80_PACKET);
+
+ /*
+ * Correct old drbd (up to 8.3.7) if it believes it can do more than
+ * 32KiB.
+ */
+ if (first_peer_device(device)->connection->agreed_pro_version == 94)
+ return DRBD_MAX_SIZE_H80_PACKET;
+
+ /*
+ * drbd 8.3.8 onwards, before 8.4.0
+ */
+ if (first_peer_device(device)->connection->agreed_pro_version < 100)
+ return DRBD_MAX_BIO_SIZE_P95;
+ return DRBD_MAX_BIO_SIZE;
}
static unsigned int drbd_max_discard_sectors(struct drbd_connection *connection)
@@ -1204,149 +1226,119 @@ static unsigned int drbd_max_discard_sectors(struct drbd_connection *connection)
return AL_EXTENT_SIZE >> 9;
}
-static void decide_on_discard_support(struct drbd_device *device,
+static bool drbd_discard_supported(struct drbd_connection *connection,
struct drbd_backing_dev *bdev)
{
- struct drbd_connection *connection =
- first_peer_device(device)->connection;
- struct request_queue *q = device->rq_queue;
- unsigned int max_discard_sectors;
-
if (bdev && !bdev_max_discard_sectors(bdev->backing_bdev))
- goto not_supported;
+ return false;
if (connection->cstate >= C_CONNECTED &&
!(connection->agreed_features & DRBD_FF_TRIM)) {
drbd_info(connection,
"peer DRBD too old, does not support TRIM: disabling discards\n");
- goto not_supported;
+ return false;
}
- /*
- * We don't care for the granularity, really.
- *
- * Stacking limits below should fix it for the local device. Whether or
- * not it is a suitable granularity on the remote device is not our
- * problem, really. If you care, you need to use devices with similar
- * topology on all peers.
- */
- blk_queue_discard_granularity(q, 512);
- max_discard_sectors = drbd_max_discard_sectors(connection);
- blk_queue_max_discard_sectors(q, max_discard_sectors);
- blk_queue_max_write_zeroes_sectors(q, max_discard_sectors);
- return;
-
-not_supported:
- blk_queue_discard_granularity(q, 0);
- blk_queue_max_discard_sectors(q, 0);
+ return true;
}
-static void fixup_write_zeroes(struct drbd_device *device, struct request_queue *q)
+/* This is the workaround for "bio would need to, but cannot, be split" */
+static unsigned int drbd_backing_dev_max_segments(struct drbd_device *device)
{
- /* Fixup max_write_zeroes_sectors after blk_stack_limits():
- * if we can handle "zeroes" efficiently on the protocol,
- * we want to do that, even if our backend does not announce
- * max_write_zeroes_sectors itself. */
- struct drbd_connection *connection = first_peer_device(device)->connection;
- /* If the peer announces WZEROES support, use it. Otherwise, rather
- * send explicit zeroes than rely on some discard-zeroes-data magic. */
- if (connection->agreed_features & DRBD_FF_WZEROES)
- q->limits.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS;
- else
- q->limits.max_write_zeroes_sectors = 0;
-}
+ unsigned int max_segments;
-static void fixup_discard_support(struct drbd_device *device, struct request_queue *q)
-{
- unsigned int max_discard = device->rq_queue->limits.max_discard_sectors;
- unsigned int discard_granularity =
- device->rq_queue->limits.discard_granularity >> SECTOR_SHIFT;
+ rcu_read_lock();
+ max_segments = rcu_dereference(device->ldev->disk_conf)->max_bio_bvecs;
+ rcu_read_unlock();
- if (discard_granularity > max_discard) {
- blk_queue_discard_granularity(q, 0);
- blk_queue_max_discard_sectors(q, 0);
- }
+ if (!max_segments)
+ return BLK_MAX_SEGMENTS;
+ return max_segments;
}
-static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backing_dev *bdev,
- unsigned int max_bio_size, struct o_qlim *o)
+void drbd_reconsider_queue_parameters(struct drbd_device *device,
+ struct drbd_backing_dev *bdev, struct o_qlim *o)
{
+ struct drbd_connection *connection =
+ first_peer_device(device)->connection;
struct request_queue * const q = device->rq_queue;
- unsigned int max_hw_sectors = max_bio_size >> 9;
- unsigned int max_segments = 0;
+ unsigned int now = queue_max_hw_sectors(q) << 9;
+ struct queue_limits lim;
struct request_queue *b = NULL;
- struct disk_conf *dc;
+ unsigned int new;
if (bdev) {
b = bdev->backing_bdev->bd_disk->queue;
- max_hw_sectors = min(queue_max_hw_sectors(b), max_bio_size >> 9);
- rcu_read_lock();
- dc = rcu_dereference(device->ldev->disk_conf);
- max_segments = dc->max_bio_bvecs;
- rcu_read_unlock();
-
- blk_set_stacking_limits(&q->limits);
+ device->local_max_bio_size =
+ queue_max_hw_sectors(b) << SECTOR_SHIFT;
}
- blk_queue_max_hw_sectors(q, max_hw_sectors);
- /* This is the workaround for "bio would need to, but cannot, be split" */
- blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS);
- blk_queue_segment_boundary(q, PAGE_SIZE-1);
- decide_on_discard_support(device, bdev);
-
- if (b) {
- blk_stack_limits(&q->limits, &b->limits, 0);
- disk_update_readahead(device->vdisk);
+ /*
+ * We may later detach and re-attach on a disconnected Primary. Avoid
+ * decreasing the value in this case.
+ *
+ * We want to store what we know the peer DRBD can handle, not what the
+ * peer IO backend can handle.
+ */
+ new = min3(DRBD_MAX_BIO_SIZE, device->local_max_bio_size,
+ max(drbd_max_peer_bio_size(device), device->peer_max_bio_size));
+ if (new != now) {
+ if (device->state.role == R_PRIMARY && new < now)
+ drbd_err(device, "ASSERT FAILED new < now; (%u < %u)\n",
+ new, now);
+ drbd_info(device, "max BIO size = %u\n", new);
}
- fixup_write_zeroes(device, q);
- fixup_discard_support(device, q);
-}
-
-void drbd_reconsider_queue_parameters(struct drbd_device *device, struct drbd_backing_dev *bdev, struct o_qlim *o)
-{
- unsigned int now, new, local, peer;
-
- now = queue_max_hw_sectors(device->rq_queue) << 9;
- local = device->local_max_bio_size; /* Eventually last known value, from volatile memory */
- peer = device->peer_max_bio_size; /* Eventually last known value, from meta data */
+ lim = queue_limits_start_update(q);
if (bdev) {
- local = queue_max_hw_sectors(bdev->backing_bdev->bd_disk->queue) << 9;
- device->local_max_bio_size = local;
+ blk_set_stacking_limits(&lim);
+ lim.max_segments = drbd_backing_dev_max_segments(device);
+ } else {
+ lim.max_segments = BLK_MAX_SEGMENTS;
}
- local = min(local, DRBD_MAX_BIO_SIZE);
- /* We may ignore peer limits if the peer is modern enough.
- Because new from 8.3.8 onwards the peer can use multiple
- BIOs for a single peer_request */
- if (device->state.conn >= C_WF_REPORT_PARAMS) {
- if (first_peer_device(device)->connection->agreed_pro_version < 94)
- peer = min(device->peer_max_bio_size, DRBD_MAX_SIZE_H80_PACKET);
- /* Correct old drbd (up to 8.3.7) if it believes it can do more than 32KiB */
- else if (first_peer_device(device)->connection->agreed_pro_version == 94)
- peer = DRBD_MAX_SIZE_H80_PACKET;
- else if (first_peer_device(device)->connection->agreed_pro_version < 100)
- peer = DRBD_MAX_BIO_SIZE_P95; /* drbd 8.3.8 onwards, before 8.4.0 */
- else
- peer = DRBD_MAX_BIO_SIZE;
+ lim.max_hw_sectors = new >> SECTOR_SHIFT;
+ lim.seg_boundary_mask = PAGE_SIZE - 1;
- /* We may later detach and re-attach on a disconnected Primary.
- * Avoid this setting to jump back in that case.
- * We want to store what we know the peer DRBD can handle,
- * not what the peer IO backend can handle. */
- if (peer > device->peer_max_bio_size)
- device->peer_max_bio_size = peer;
+ /*
+ * We don't care for the granularity, really.
+ *
+ * Stacking limits below should fix it for the local device. Whether or
+ * not it is a suitable granularity on the remote device is not our
+ * problem, really. If you care, you need to use devices with similar
+ * topology on all peers.
+ */
+ if (drbd_discard_supported(connection, bdev)) {
+ lim.discard_granularity = 512;
+ lim.max_hw_discard_sectors =
+ drbd_max_discard_sectors(connection);
+ } else {
+ lim.discard_granularity = 0;
+ lim.max_hw_discard_sectors = 0;
}
- new = min(local, peer);
- if (device->state.role == R_PRIMARY && new < now)
- drbd_err(device, "ASSERT FAILED new < now; (%u < %u)\n", new, now);
+ if (bdev)
+ blk_stack_limits(&lim, &b->limits, 0);
- if (new != now)
- drbd_info(device, "max BIO size = %u\n", new);
+ /*
+ * If we can handle "zeroes" efficiently on the protocol, we want to do
+ * that, even if our backend does not announce max_write_zeroes_sectors
+ * itself.
+ */
+ if (connection->agreed_features & DRBD_FF_WZEROES)
+ lim.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS;
+ else
+ lim.max_write_zeroes_sectors = 0;
+
+ if ((lim.discard_granularity >> SECTOR_SHIFT) >
+ lim.max_hw_discard_sectors) {
+ lim.discard_granularity = 0;
+ lim.max_hw_discard_sectors = 0;
+ }
- drbd_setup_queue_param(device, bdev, new, o);
+ if (queue_limits_commit_update(q, &lim))
+ drbd_err(device, "setting new queue limits failed\n");
}
/* Starts the worker thread */
@@ -1635,45 +1627,45 @@ success:
return 0;
}
-static struct bdev_handle *open_backing_dev(struct drbd_device *device,
+static struct file *open_backing_dev(struct drbd_device *device,
const char *bdev_path, void *claim_ptr, bool do_bd_link)
{
- struct bdev_handle *handle;
+ struct file *file;
int err = 0;
- handle = bdev_open_by_path(bdev_path, BLK_OPEN_READ | BLK_OPEN_WRITE,
- claim_ptr, NULL);
- if (IS_ERR(handle)) {
+ file = bdev_file_open_by_path(bdev_path, BLK_OPEN_READ | BLK_OPEN_WRITE,
+ claim_ptr, NULL);
+ if (IS_ERR(file)) {
drbd_err(device, "open(\"%s\") failed with %ld\n",
- bdev_path, PTR_ERR(handle));
- return handle;
+ bdev_path, PTR_ERR(file));
+ return file;
}
if (!do_bd_link)
- return handle;
+ return file;
- err = bd_link_disk_holder(handle->bdev, device->vdisk);
+ err = bd_link_disk_holder(file_bdev(file), device->vdisk);
if (err) {
- bdev_release(handle);
+ fput(file);
drbd_err(device, "bd_link_disk_holder(\"%s\", ...) failed with %d\n",
bdev_path, err);
- handle = ERR_PTR(err);
+ file = ERR_PTR(err);
}
- return handle;
+ return file;
}
static int open_backing_devices(struct drbd_device *device,
struct disk_conf *new_disk_conf,
struct drbd_backing_dev *nbc)
{
- struct bdev_handle *handle;
+ struct file *file;
- handle = open_backing_dev(device, new_disk_conf->backing_dev, device,
+ file = open_backing_dev(device, new_disk_conf->backing_dev, device,
true);
- if (IS_ERR(handle))
+ if (IS_ERR(file))
return ERR_OPEN_DISK;
- nbc->backing_bdev = handle->bdev;
- nbc->backing_bdev_handle = handle;
+ nbc->backing_bdev = file_bdev(file);
+ nbc->backing_bdev_file = file;
/*
* meta_dev_idx >= 0: external fixed size, possibly multiple
@@ -1683,7 +1675,7 @@ static int open_backing_devices(struct drbd_device *device,
* should check it for you already; but if you don't, or
* someone fooled it, we need to double check here)
*/
- handle = open_backing_dev(device, new_disk_conf->meta_dev,
+ file = open_backing_dev(device, new_disk_conf->meta_dev,
/* claim ptr: device, if claimed exclusively; shared drbd_m_holder,
* if potentially shared with other drbd minors */
(new_disk_conf->meta_dev_idx < 0) ? (void*)device : (void*)drbd_m_holder,
@@ -1691,21 +1683,21 @@ static int open_backing_devices(struct drbd_device *device,
* as would happen with internal metadata. */
(new_disk_conf->meta_dev_idx != DRBD_MD_INDEX_FLEX_INT &&
new_disk_conf->meta_dev_idx != DRBD_MD_INDEX_INTERNAL));
- if (IS_ERR(handle))
+ if (IS_ERR(file))
return ERR_OPEN_MD_DISK;
- nbc->md_bdev = handle->bdev;
- nbc->md_bdev_handle = handle;
+ nbc->md_bdev = file_bdev(file);
+ nbc->f_md_bdev = file;
return NO_ERROR;
}
static void close_backing_dev(struct drbd_device *device,
- struct bdev_handle *handle, bool do_bd_unlink)
+ struct file *bdev_file, bool do_bd_unlink)
{
- if (!handle)
+ if (!bdev_file)
return;
if (do_bd_unlink)
- bd_unlink_disk_holder(handle->bdev, device->vdisk);
- bdev_release(handle);
+ bd_unlink_disk_holder(file_bdev(bdev_file), device->vdisk);
+ fput(bdev_file);
}
void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev *ldev)
@@ -1713,9 +1705,9 @@ void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev *
if (ldev == NULL)
return;
- close_backing_dev(device, ldev->md_bdev_handle,
+ close_backing_dev(device, ldev->f_md_bdev,
ldev->md_bdev != ldev->backing_bdev);
- close_backing_dev(device, ldev->backing_bdev_handle, true);
+ close_backing_dev(device, ldev->backing_bdev_file, true);
kfree(ldev->disk_conf);
kfree(ldev);
@@ -2131,9 +2123,9 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
fail:
conn_reconfig_done(connection);
if (nbc) {
- close_backing_dev(device, nbc->md_bdev_handle,
+ close_backing_dev(device, nbc->f_md_bdev,
nbc->md_bdev != nbc->backing_bdev);
- close_backing_dev(device, nbc->backing_bdev_handle, true);
+ close_backing_dev(device, nbc->backing_bdev_file, true);
kfree(nbc);
}
kfree(new_disk_conf);