bybrooklyn/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-04-18 06:44:00 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge tag 'for-6.9/block-20240310' of git://git.kernel.dk/linux

Browse Source 
Pull block updates from Jens Axboe:

 - MD pull requests via Song:
      - Cleanup redundant checks (Yu Kuai)
      - Remove deprecated headers (Marc Zyngier, Song Liu)
      - Concurrency fixes (Li Lingfeng)
      - Memory leak fix (Li Nan)
      - Refactor raid1 read_balance (Yu Kuai, Paul Luse)
      - Clean up and fix for md_ioctl (Li Nan)
      - Other small fixes (Gui-Dong Han, Heming Zhao)
      - MD atomic limits (Christoph)

 - NVMe pull request via Keith:
      - RDMA target enhancements (Max)
      - Fabrics fixes (Max, Guixin, Hannes)
      - Atomic queue_limits usage (Christoph)
      - Const use for class_register (Ricardo)
      - Identification error handling fixes (Shin'ichiro, Keith)

 - Improvement and cleanup for cached request handling (Christoph)

 - Moving towards atomic queue limits. Core changes and driver bits so
   far (Christoph)

 - Fix UAF issues in aoeblk (Chun-Yi)

 - Zoned fix and cleanups (Damien)

 - s390 dasd cleanups and fixes (Jan, Miroslav)

 - Block issue timestamp caching (me)

 - noio scope guarding for zoned IO (Johannes)

 - block/nvme PI improvements (Kanchan)

 - Ability to terminate long running discard loop (Keith)

 - bdev revalidation fix (Li)

 - Get rid of old nr_queues hack for kdump kernels (Ming)

 - Support for async deletion of ublk (Ming)

 - Improve IRQ bio recycling (Pavel)

 - Factor in CPU capacity for remote vs local completion (Qais)

 - Add shared_tags configfs entry for null_blk (Shin'ichiro

 - Fix for a regression in page refcounts introduced by the folio
   unification (Tony)

 - Misc fixes and cleanups (Arnd, Colin, John, Kunwu, Li, Navid,
   Ricardo, Roman, Tang, Uwe)

* tag 'for-6.9/block-20240310' of git://git.kernel.dk/linux: (221 commits)
  block: partitions: only define function mac_fix_string for CONFIG_PPC_PMAC
  block/swim: Convert to platform remove callback returning void
  cdrom: gdrom: Convert to platform remove callback returning void
  block: remove disk_stack_limits
  md: remove mddev->queue
  md: don't initialize queue limits
  md/raid10: use the atomic queue limit update APIs
  md/raid5: use the atomic queue limit update APIs
  md/raid1: use the atomic queue limit update APIs
  md/raid0: use the atomic queue limit update APIs
  md: add queue limit helpers
  md: add a mddev_is_dm helper
  md: add a mddev_add_trace_msg helper
  md: add a mddev_trace_remap helper
  bcache: move calculation of stripe_size and io_opt into bcache_device_init
  virtio_blk: Do not use disk_set_max_open/active_zones()
  aoe: fix the potential use-after-free problem in aoecmd_cfg_pkts
  block: move capacity validation to blkpg_do_ioctl()
  block: prevent division by zero in blk_rq_stat_sum()
  drbd: atomically update queue limits in drbd_reconsider_queue_parameters
  ...
This commit is contained in:
Linus Torvalds
2024-03-11 11:43:44 -07:00
parent d2c84bdce2 5205a4aa8f
commit 1ddeeb2a05
138 changed files with 3571 additions and 3298 deletions
Download Patch File Download Diff File Expand all files Collapse all files

232
drivers/block/drbd/drbd_nl.c
View File

@@ -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)
@@ -1204,24 +1226,81 @@ 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;
}
return true;
}
/* 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)
{
unsigned int max_segments;
rcu_read_lock();
max_segments = rcu_dereference(device->ldev->disk_conf)->max_bio_bvecs;
rcu_read_unlock();
if (!max_segments)
return BLK_MAX_SEGMENTS;
return max_segments;
}
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 now = queue_max_hw_sectors(q) << 9;
struct queue_limits lim;
struct request_queue *b = NULL;
unsigned int new;
if (bdev) {
b = bdev->backing_bdev->bd_disk->queue;
device->local_max_bio_size =
queue_max_hw_sectors(b) << SECTOR_SHIFT;
}
/*
* 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);
}
lim = queue_limits_start_update(q);
if (bdev) {
blk_set_stacking_limits(&lim);
lim.max_segments = drbd_backing_dev_max_segments(device);
} else {
lim.max_segments = BLK_MAX_SEGMENTS;
}
lim.max_hw_sectors = new >> SECTOR_SHIFT;
lim.seg_boundary_mask = PAGE_SIZE - 1;
/*
* We don't care for the granularity, really.
*
@@ -1230,123 +1309,36 @@ static void decide_on_discard_support(struct drbd_device *device,
* 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;
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;
}
not_supported:
blk_queue_discard_granularity(q, 0);
blk_queue_max_discard_sectors(q, 0);
}
if (bdev)
blk_stack_limits(&lim, &b->limits, 0);
static void fixup_write_zeroes(struct drbd_device *device, struct request_queue *q)
{
/* 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 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)
q->limits.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS;
lim.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS;
else
q->limits.max_write_zeroes_sectors = 0;
}
lim.max_write_zeroes_sectors = 0;
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;
if (discard_granularity > max_discard) {
blk_queue_discard_granularity(q, 0);
blk_queue_max_discard_sectors(q, 0);
}
}
static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backing_dev *bdev,
unsigned int max_bio_size, struct o_qlim *o)
{
struct request_queue * const q = device->rq_queue;
unsigned int max_hw_sectors = max_bio_size >> 9;
unsigned int max_segments = 0;
struct request_queue *b = NULL;
struct disk_conf *dc;
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);
if ((lim.discard_granularity >> SECTOR_SHIFT) >
lim.max_hw_discard_sectors) {
lim.discard_granularity = 0;
lim.max_hw_discard_sectors = 0;
}
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);
}
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 */
if (bdev) {
local = queue_max_hw_sectors(bdev->backing_bdev->bd_disk->queue) << 9;
device->local_max_bio_size = local;
}
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;
/* 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;
}
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 (new != now)
drbd_info(device, "max BIO size = %u\n", new);
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 */