linux/block/blk-settings.c
Linus Torvalds ce8a79d560 for-6.2/block-2022-12-08
-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAmOScsgQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpi5ID/9pLXFYOq1+uDjU0KO/MdjMjK8Ukr34lCnk
 WkajRLheE8JBKOFDE54XJk56sQSZHX9bTWqziar0h1fioh7FlQR/tVvzsERCm2M9
 2y9THJNJygC68wgybStyiKlshFjl7TD7Kv5N9Y3xP3mkQygT+D6o8fXZk5xQbYyH
 YdFSoq4rJVHxRL03yzQiReGGIYdOUEQQh8l1FiLwLlKa3lXAey1KuxWIzksVN0KK
 aZB4QhiBpOiPgDHUVisq2XtyQjpZ2byoCImPzgrcqk9Jo4esvm/e6esrg4xlsvII
 LKFFkTmbVqjUZtFjqakFHmfuzVor4nU5f+xb90ZHExuuODYckkxWp5rWhf9QwqqI
 0ik6WYgI1/5vnHnX8f2DYzOFQf9qa/rLgg0CshyUODlD6RfHa9vntqYvlIFkmOBd
 Q7KblIoK8YTzUS1M+v7X8JQ7gDR2KwygH37Da2KJS+vgvfIb8kJGr1ZORuhJuJJ7
 Bl69gaNkHTHrqufp7UI64YXfueeuNu2J9z3zwzGoxeaFaofF/phDn0/2gCQE1fQI
 XBhsMw+ETqI6B2SPHMnzYDu2DM1S8ZTOYQlaD4G3uqgWnAM1tG707395uAy5yu4n
 D5azU1fVG4UocoNIyPujpaoSRs2zWZycEFEeUQkhyDDww/j4hlHi6H33eOnk0zsr
 wxzFGfvHfw==
 =k/vv
 -----END PGP SIGNATURE-----

Merge tag 'for-6.2/block-2022-12-08' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull requests via Christoph:
      - Support some passthrough commands without CAP_SYS_ADMIN (Kanchan
        Joshi)
      - Refactor PCIe probing and reset (Christoph Hellwig)
      - Various fabrics authentication fixes and improvements (Sagi
        Grimberg)
      - Avoid fallback to sequential scan due to transient issues (Uday
        Shankar)
      - Implement support for the DEAC bit in Write Zeroes (Christoph
        Hellwig)
      - Allow overriding the IEEE OUI and firmware revision in configfs
        for nvmet (Aleksandr Miloserdov)
      - Force reconnect when number of queue changes in nvmet (Daniel
        Wagner)
      - Minor fixes and improvements (Uros Bizjak, Joel Granados, Sagi
        Grimberg, Christoph Hellwig, Christophe JAILLET)
      - Fix and cleanup nvme-fc req allocation (Chaitanya Kulkarni)
      - Use the common tagset helpers in nvme-pci driver (Christoph
        Hellwig)
      - Cleanup the nvme-pci removal path (Christoph Hellwig)
      - Use kstrtobool() instead of strtobool (Christophe JAILLET)
      - Allow unprivileged passthrough of Identify Controller (Joel
        Granados)
      - Support io stats on the mpath device (Sagi Grimberg)
      - Minor nvmet cleanup (Sagi Grimberg)

 - MD pull requests via Song:
      - Code cleanups (Christoph)
      - Various fixes

 - Floppy pull request from Denis:
      - Fix a memory leak in the init error path (Yuan)

 - Series fixing some batch wakeup issues with sbitmap (Gabriel)

 - Removal of the pktcdvd driver that was deprecated more than 5 years
   ago, and subsequent removal of the devnode callback in struct
   block_device_operations as no users are now left (Greg)

 - Fix for partition read on an exclusively opened bdev (Jan)

 - Series of elevator API cleanups (Jinlong, Christoph)

 - Series of fixes and cleanups for blk-iocost (Kemeng)

 - Series of fixes and cleanups for blk-throttle (Kemeng)

 - Series adding concurrent support for sync queues in BFQ (Yu)

 - Series bringing drbd a bit closer to the out-of-tree maintained
   version (Christian, Joel, Lars, Philipp)

 - Misc drbd fixes (Wang)

 - blk-wbt fixes and tweaks for enable/disable (Yu)

 - Fixes for mq-deadline for zoned devices (Damien)

 - Add support for read-only and offline zones for null_blk
   (Shin'ichiro)

 - Series fixing the delayed holder tracking, as used by DM (Yu,
   Christoph)

 - Series enabling bio alloc caching for IRQ based IO (Pavel)

 - Series enabling userspace peer-to-peer DMA (Logan)

 - BFQ waker fixes (Khazhismel)

 - Series fixing elevator refcount issues (Christoph, Jinlong)

 - Series cleaning up references around queue destruction (Christoph)

 - Series doing quiesce by tagset, enabling cleanups in drivers
   (Christoph, Chao)

 - Series untangling the queue kobject and queue references (Christoph)

 - Misc fixes and cleanups (Bart, David, Dawei, Jinlong, Kemeng, Ye,
   Yang, Waiman, Shin'ichiro, Randy, Pankaj, Christoph)

* tag 'for-6.2/block-2022-12-08' of git://git.kernel.dk/linux: (247 commits)
  blktrace: Fix output non-blktrace event when blk_classic option enabled
  block: sed-opal: Don't include <linux/kernel.h>
  sed-opal: allow using IOC_OPAL_SAVE for locking too
  blk-cgroup: Fix typo in comment
  block: remove bio_set_op_attrs
  nvmet: don't open-code NVME_NS_ATTR_RO enumeration
  nvme-pci: use the tagset alloc/free helpers
  nvme: add the Apple shared tag workaround to nvme_alloc_io_tag_set
  nvme: only set reserved_tags in nvme_alloc_io_tag_set for fabrics controllers
  nvme: consolidate setting the tagset flags
  nvme: pass nr_maps explicitly to nvme_alloc_io_tag_set
  block: bio_copy_data_iter
  nvme-pci: split out a nvme_pci_ctrl_is_dead helper
  nvme-pci: return early on ctrl state mismatch in nvme_reset_work
  nvme-pci: rename nvme_disable_io_queues
  nvme-pci: cleanup nvme_suspend_queue
  nvme-pci: remove nvme_pci_disable
  nvme-pci: remove nvme_disable_admin_queue
  nvme: merge nvme_shutdown_ctrl into nvme_disable_ctrl
  nvme: use nvme_wait_ready in nvme_shutdown_ctrl
  ...
2022-12-13 10:43:59 -08:00

978 lines
30 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Functions related to setting various queue properties from drivers
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/pagemap.h>
#include <linux/backing-dev-defs.h>
#include <linux/gcd.h>
#include <linux/lcm.h>
#include <linux/jiffies.h>
#include <linux/gfp.h>
#include <linux/dma-mapping.h>
#include "blk.h"
#include "blk-wbt.h"
void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout)
{
q->rq_timeout = timeout;
}
EXPORT_SYMBOL_GPL(blk_queue_rq_timeout);
/**
* blk_set_default_limits - reset limits to default values
* @lim: the queue_limits structure to reset
*
* Description:
* Returns a queue_limit struct to its default state.
*/
void blk_set_default_limits(struct queue_limits *lim)
{
lim->max_segments = BLK_MAX_SEGMENTS;
lim->max_discard_segments = 1;
lim->max_integrity_segments = 0;
lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
lim->virt_boundary_mask = 0;
lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
lim->max_dev_sectors = 0;
lim->chunk_sectors = 0;
lim->max_write_zeroes_sectors = 0;
lim->max_zone_append_sectors = 0;
lim->max_discard_sectors = 0;
lim->max_hw_discard_sectors = 0;
lim->max_secure_erase_sectors = 0;
lim->discard_granularity = 0;
lim->discard_alignment = 0;
lim->discard_misaligned = 0;
lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
lim->bounce = BLK_BOUNCE_NONE;
lim->alignment_offset = 0;
lim->io_opt = 0;
lim->misaligned = 0;
lim->zoned = BLK_ZONED_NONE;
lim->zone_write_granularity = 0;
lim->dma_alignment = 511;
}
/**
* blk_set_stacking_limits - set default limits for stacking devices
* @lim: the queue_limits structure to reset
*
* Description:
* Returns a queue_limit struct to its default state. Should be used
* by stacking drivers like DM that have no internal limits.
*/
void blk_set_stacking_limits(struct queue_limits *lim)
{
blk_set_default_limits(lim);
/* Inherit limits from component devices */
lim->max_segments = USHRT_MAX;
lim->max_discard_segments = USHRT_MAX;
lim->max_hw_sectors = UINT_MAX;
lim->max_segment_size = UINT_MAX;
lim->max_sectors = UINT_MAX;
lim->max_dev_sectors = UINT_MAX;
lim->max_write_zeroes_sectors = UINT_MAX;
lim->max_zone_append_sectors = UINT_MAX;
}
EXPORT_SYMBOL(blk_set_stacking_limits);
/**
* blk_queue_bounce_limit - set bounce buffer limit for queue
* @q: the request queue for the device
* @bounce: bounce limit to enforce
*
* Description:
* Force bouncing for ISA DMA ranges or highmem.
*
* DEPRECATED, don't use in new code.
**/
void blk_queue_bounce_limit(struct request_queue *q, enum blk_bounce bounce)
{
q->limits.bounce = bounce;
}
EXPORT_SYMBOL(blk_queue_bounce_limit);
/**
* blk_queue_max_hw_sectors - set max sectors for a request for this queue
* @q: the request queue for the device
* @max_hw_sectors: max hardware sectors in the usual 512b unit
*
* Description:
* Enables a low level driver to set a hard upper limit,
* max_hw_sectors, on the size of requests. max_hw_sectors is set by
* the device driver based upon the capabilities of the I/O
* controller.
*
* max_dev_sectors is a hard limit imposed by the storage device for
* READ/WRITE requests. It is set by the disk driver.
*
* max_sectors is a soft limit imposed by the block layer for
* filesystem type requests. This value can be overridden on a
* per-device basis in /sys/block/<device>/queue/max_sectors_kb.
* The soft limit can not exceed max_hw_sectors.
**/
void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
{
struct queue_limits *limits = &q->limits;
unsigned int max_sectors;
if ((max_hw_sectors << 9) < PAGE_SIZE) {
max_hw_sectors = 1 << (PAGE_SHIFT - 9);
printk(KERN_INFO "%s: set to minimum %d\n",
__func__, max_hw_sectors);
}
max_hw_sectors = round_down(max_hw_sectors,
limits->logical_block_size >> SECTOR_SHIFT);
limits->max_hw_sectors = max_hw_sectors;
max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors);
max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS);
max_sectors = round_down(max_sectors,
limits->logical_block_size >> SECTOR_SHIFT);
limits->max_sectors = max_sectors;
if (!q->disk)
return;
q->disk->bdi->io_pages = max_sectors >> (PAGE_SHIFT - 9);
}
EXPORT_SYMBOL(blk_queue_max_hw_sectors);
/**
* blk_queue_chunk_sectors - set size of the chunk for this queue
* @q: the request queue for the device
* @chunk_sectors: chunk sectors in the usual 512b unit
*
* Description:
* If a driver doesn't want IOs to cross a given chunk size, it can set
* this limit and prevent merging across chunks. Note that the block layer
* must accept a page worth of data at any offset. So if the crossing of
* chunks is a hard limitation in the driver, it must still be prepared
* to split single page bios.
**/
void blk_queue_chunk_sectors(struct request_queue *q, unsigned int chunk_sectors)
{
q->limits.chunk_sectors = chunk_sectors;
}
EXPORT_SYMBOL(blk_queue_chunk_sectors);
/**
* blk_queue_max_discard_sectors - set max sectors for a single discard
* @q: the request queue for the device
* @max_discard_sectors: maximum number of sectors to discard
**/
void blk_queue_max_discard_sectors(struct request_queue *q,
unsigned int max_discard_sectors)
{
q->limits.max_hw_discard_sectors = max_discard_sectors;
q->limits.max_discard_sectors = max_discard_sectors;
}
EXPORT_SYMBOL(blk_queue_max_discard_sectors);
/**
* blk_queue_max_secure_erase_sectors - set max sectors for a secure erase
* @q: the request queue for the device
* @max_sectors: maximum number of sectors to secure_erase
**/
void blk_queue_max_secure_erase_sectors(struct request_queue *q,
unsigned int max_sectors)
{
q->limits.max_secure_erase_sectors = max_sectors;
}
EXPORT_SYMBOL(blk_queue_max_secure_erase_sectors);
/**
* blk_queue_max_write_zeroes_sectors - set max sectors for a single
* write zeroes
* @q: the request queue for the device
* @max_write_zeroes_sectors: maximum number of sectors to write per command
**/
void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
unsigned int max_write_zeroes_sectors)
{
q->limits.max_write_zeroes_sectors = max_write_zeroes_sectors;
}
EXPORT_SYMBOL(blk_queue_max_write_zeroes_sectors);
/**
* blk_queue_max_zone_append_sectors - set max sectors for a single zone append
* @q: the request queue for the device
* @max_zone_append_sectors: maximum number of sectors to write per command
**/
void blk_queue_max_zone_append_sectors(struct request_queue *q,
unsigned int max_zone_append_sectors)
{
unsigned int max_sectors;
if (WARN_ON(!blk_queue_is_zoned(q)))
return;
max_sectors = min(q->limits.max_hw_sectors, max_zone_append_sectors);
max_sectors = min(q->limits.chunk_sectors, max_sectors);
/*
* Signal eventual driver bugs resulting in the max_zone_append sectors limit
* being 0 due to a 0 argument, the chunk_sectors limit (zone size) not set,
* or the max_hw_sectors limit not set.
*/
WARN_ON(!max_sectors);
q->limits.max_zone_append_sectors = max_sectors;
}
EXPORT_SYMBOL_GPL(blk_queue_max_zone_append_sectors);
/**
* blk_queue_max_segments - set max hw segments for a request for this queue
* @q: the request queue for the device
* @max_segments: max number of segments
*
* Description:
* Enables a low level driver to set an upper limit on the number of
* hw data segments in a request.
**/
void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments)
{
if (!max_segments) {
max_segments = 1;
printk(KERN_INFO "%s: set to minimum %d\n",
__func__, max_segments);
}
q->limits.max_segments = max_segments;
}
EXPORT_SYMBOL(blk_queue_max_segments);
/**
* blk_queue_max_discard_segments - set max segments for discard requests
* @q: the request queue for the device
* @max_segments: max number of segments
*
* Description:
* Enables a low level driver to set an upper limit on the number of
* segments in a discard request.
**/
void blk_queue_max_discard_segments(struct request_queue *q,
unsigned short max_segments)
{
q->limits.max_discard_segments = max_segments;
}
EXPORT_SYMBOL_GPL(blk_queue_max_discard_segments);
/**
* blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
* @q: the request queue for the device
* @max_size: max size of segment in bytes
*
* Description:
* Enables a low level driver to set an upper limit on the size of a
* coalesced segment
**/
void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size)
{
if (max_size < PAGE_SIZE) {
max_size = PAGE_SIZE;
printk(KERN_INFO "%s: set to minimum %d\n",
__func__, max_size);
}
/* see blk_queue_virt_boundary() for the explanation */
WARN_ON_ONCE(q->limits.virt_boundary_mask);
q->limits.max_segment_size = max_size;
}
EXPORT_SYMBOL(blk_queue_max_segment_size);
/**
* blk_queue_logical_block_size - set logical block size for the queue
* @q: the request queue for the device
* @size: the logical block size, in bytes
*
* Description:
* This should be set to the lowest possible block size that the
* storage device can address. The default of 512 covers most
* hardware.
**/
void blk_queue_logical_block_size(struct request_queue *q, unsigned int size)
{
struct queue_limits *limits = &q->limits;
limits->logical_block_size = size;
if (limits->physical_block_size < size)
limits->physical_block_size = size;
if (limits->io_min < limits->physical_block_size)
limits->io_min = limits->physical_block_size;
limits->max_hw_sectors =
round_down(limits->max_hw_sectors, size >> SECTOR_SHIFT);
limits->max_sectors =
round_down(limits->max_sectors, size >> SECTOR_SHIFT);
}
EXPORT_SYMBOL(blk_queue_logical_block_size);
/**
* blk_queue_physical_block_size - set physical block size for the queue
* @q: the request queue for the device
* @size: the physical block size, in bytes
*
* Description:
* This should be set to the lowest possible sector size that the
* hardware can operate on without reverting to read-modify-write
* operations.
*/
void blk_queue_physical_block_size(struct request_queue *q, unsigned int size)
{
q->limits.physical_block_size = size;
if (q->limits.physical_block_size < q->limits.logical_block_size)
q->limits.physical_block_size = q->limits.logical_block_size;
if (q->limits.io_min < q->limits.physical_block_size)
q->limits.io_min = q->limits.physical_block_size;
}
EXPORT_SYMBOL(blk_queue_physical_block_size);
/**
* blk_queue_zone_write_granularity - set zone write granularity for the queue
* @q: the request queue for the zoned device
* @size: the zone write granularity size, in bytes
*
* Description:
* This should be set to the lowest possible size allowing to write in
* sequential zones of a zoned block device.
*/
void blk_queue_zone_write_granularity(struct request_queue *q,
unsigned int size)
{
if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
return;
q->limits.zone_write_granularity = size;
if (q->limits.zone_write_granularity < q->limits.logical_block_size)
q->limits.zone_write_granularity = q->limits.logical_block_size;
}
EXPORT_SYMBOL_GPL(blk_queue_zone_write_granularity);
/**
* blk_queue_alignment_offset - set physical block alignment offset
* @q: the request queue for the device
* @offset: alignment offset in bytes
*
* Description:
* Some devices are naturally misaligned to compensate for things like
* the legacy DOS partition table 63-sector offset. Low-level drivers
* should call this function for devices whose first sector is not
* naturally aligned.
*/
void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
{
q->limits.alignment_offset =
offset & (q->limits.physical_block_size - 1);
q->limits.misaligned = 0;
}
EXPORT_SYMBOL(blk_queue_alignment_offset);
void disk_update_readahead(struct gendisk *disk)
{
struct request_queue *q = disk->queue;
/*
* For read-ahead of large files to be effective, we need to read ahead
* at least twice the optimal I/O size.
*/
disk->bdi->ra_pages =
max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
disk->bdi->io_pages = queue_max_sectors(q) >> (PAGE_SHIFT - 9);
}
EXPORT_SYMBOL_GPL(disk_update_readahead);
/**
* blk_limits_io_min - set minimum request size for a device
* @limits: the queue limits
* @min: smallest I/O size in bytes
*
* Description:
* Some devices have an internal block size bigger than the reported
* hardware sector size. This function can be used to signal the
* smallest I/O the device can perform without incurring a performance
* penalty.
*/
void blk_limits_io_min(struct queue_limits *limits, unsigned int min)
{
limits->io_min = min;
if (limits->io_min < limits->logical_block_size)
limits->io_min = limits->logical_block_size;
if (limits->io_min < limits->physical_block_size)
limits->io_min = limits->physical_block_size;
}
EXPORT_SYMBOL(blk_limits_io_min);
/**
* blk_queue_io_min - set minimum request size for the queue
* @q: the request queue for the device
* @min: smallest I/O size in bytes
*
* Description:
* Storage devices may report a granularity or preferred minimum I/O
* size which is the smallest request the device can perform without
* incurring a performance penalty. For disk drives this is often the
* physical block size. For RAID arrays it is often the stripe chunk
* size. A properly aligned multiple of minimum_io_size is the
* preferred request size for workloads where a high number of I/O
* operations is desired.
*/
void blk_queue_io_min(struct request_queue *q, unsigned int min)
{
blk_limits_io_min(&q->limits, min);
}
EXPORT_SYMBOL(blk_queue_io_min);
/**
* blk_limits_io_opt - set optimal request size for a device
* @limits: the queue limits
* @opt: smallest I/O size in bytes
*
* Description:
* Storage devices may report an optimal I/O size, which is the
* device's preferred unit for sustained I/O. This is rarely reported
* for disk drives. For RAID arrays it is usually the stripe width or
* the internal track size. A properly aligned multiple of
* optimal_io_size is the preferred request size for workloads where
* sustained throughput is desired.
*/
void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt)
{
limits->io_opt = opt;
}
EXPORT_SYMBOL(blk_limits_io_opt);
/**
* blk_queue_io_opt - set optimal request size for the queue
* @q: the request queue for the device
* @opt: optimal request size in bytes
*
* Description:
* Storage devices may report an optimal I/O size, which is the
* device's preferred unit for sustained I/O. This is rarely reported
* for disk drives. For RAID arrays it is usually the stripe width or
* the internal track size. A properly aligned multiple of
* optimal_io_size is the preferred request size for workloads where
* sustained throughput is desired.
*/
void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
{
blk_limits_io_opt(&q->limits, opt);
if (!q->disk)
return;
q->disk->bdi->ra_pages =
max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
}
EXPORT_SYMBOL(blk_queue_io_opt);
static int queue_limit_alignment_offset(const struct queue_limits *lim,
sector_t sector)
{
unsigned int granularity = max(lim->physical_block_size, lim->io_min);
unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT)
<< SECTOR_SHIFT;
return (granularity + lim->alignment_offset - alignment) % granularity;
}
static unsigned int queue_limit_discard_alignment(
const struct queue_limits *lim, sector_t sector)
{
unsigned int alignment, granularity, offset;
if (!lim->max_discard_sectors)
return 0;
/* Why are these in bytes, not sectors? */
alignment = lim->discard_alignment >> SECTOR_SHIFT;
granularity = lim->discard_granularity >> SECTOR_SHIFT;
if (!granularity)
return 0;
/* Offset of the partition start in 'granularity' sectors */
offset = sector_div(sector, granularity);
/* And why do we do this modulus *again* in blkdev_issue_discard()? */
offset = (granularity + alignment - offset) % granularity;
/* Turn it back into bytes, gaah */
return offset << SECTOR_SHIFT;
}
static unsigned int blk_round_down_sectors(unsigned int sectors, unsigned int lbs)
{
sectors = round_down(sectors, lbs >> SECTOR_SHIFT);
if (sectors < PAGE_SIZE >> SECTOR_SHIFT)
sectors = PAGE_SIZE >> SECTOR_SHIFT;
return sectors;
}
/**
* blk_stack_limits - adjust queue_limits for stacked devices
* @t: the stacking driver limits (top device)
* @b: the underlying queue limits (bottom, component device)
* @start: first data sector within component device
*
* Description:
* This function is used by stacking drivers like MD and DM to ensure
* that all component devices have compatible block sizes and
* alignments. The stacking driver must provide a queue_limits
* struct (top) and then iteratively call the stacking function for
* all component (bottom) devices. The stacking function will
* attempt to combine the values and ensure proper alignment.
*
* Returns 0 if the top and bottom queue_limits are compatible. The
* top device's block sizes and alignment offsets may be adjusted to
* ensure alignment with the bottom device. If no compatible sizes
* and alignments exist, -1 is returned and the resulting top
* queue_limits will have the misaligned flag set to indicate that
* the alignment_offset is undefined.
*/
int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
sector_t start)
{
unsigned int top, bottom, alignment, ret = 0;
t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors,
b->max_write_zeroes_sectors);
t->max_zone_append_sectors = min(t->max_zone_append_sectors,
b->max_zone_append_sectors);
t->bounce = max(t->bounce, b->bounce);
t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
b->seg_boundary_mask);
t->virt_boundary_mask = min_not_zero(t->virt_boundary_mask,
b->virt_boundary_mask);
t->max_segments = min_not_zero(t->max_segments, b->max_segments);
t->max_discard_segments = min_not_zero(t->max_discard_segments,
b->max_discard_segments);
t->max_integrity_segments = min_not_zero(t->max_integrity_segments,
b->max_integrity_segments);
t->max_segment_size = min_not_zero(t->max_segment_size,
b->max_segment_size);
t->misaligned |= b->misaligned;
alignment = queue_limit_alignment_offset(b, start);
/* Bottom device has different alignment. Check that it is
* compatible with the current top alignment.
*/
if (t->alignment_offset != alignment) {
top = max(t->physical_block_size, t->io_min)
+ t->alignment_offset;
bottom = max(b->physical_block_size, b->io_min) + alignment;
/* Verify that top and bottom intervals line up */
if (max(top, bottom) % min(top, bottom)) {
t->misaligned = 1;
ret = -1;
}
}
t->logical_block_size = max(t->logical_block_size,
b->logical_block_size);
t->physical_block_size = max(t->physical_block_size,
b->physical_block_size);
t->io_min = max(t->io_min, b->io_min);
t->io_opt = lcm_not_zero(t->io_opt, b->io_opt);
t->dma_alignment = max(t->dma_alignment, b->dma_alignment);
/* Set non-power-of-2 compatible chunk_sectors boundary */
if (b->chunk_sectors)
t->chunk_sectors = gcd(t->chunk_sectors, b->chunk_sectors);
/* Physical block size a multiple of the logical block size? */
if (t->physical_block_size & (t->logical_block_size - 1)) {
t->physical_block_size = t->logical_block_size;
t->misaligned = 1;
ret = -1;
}
/* Minimum I/O a multiple of the physical block size? */
if (t->io_min & (t->physical_block_size - 1)) {
t->io_min = t->physical_block_size;
t->misaligned = 1;
ret = -1;
}
/* Optimal I/O a multiple of the physical block size? */
if (t->io_opt & (t->physical_block_size - 1)) {
t->io_opt = 0;
t->misaligned = 1;
ret = -1;
}
/* chunk_sectors a multiple of the physical block size? */
if ((t->chunk_sectors << 9) & (t->physical_block_size - 1)) {
t->chunk_sectors = 0;
t->misaligned = 1;
ret = -1;
}
t->raid_partial_stripes_expensive =
max(t->raid_partial_stripes_expensive,
b->raid_partial_stripes_expensive);
/* Find lowest common alignment_offset */
t->alignment_offset = lcm_not_zero(t->alignment_offset, alignment)
% max(t->physical_block_size, t->io_min);
/* Verify that new alignment_offset is on a logical block boundary */
if (t->alignment_offset & (t->logical_block_size - 1)) {
t->misaligned = 1;
ret = -1;
}
t->max_sectors = blk_round_down_sectors(t->max_sectors, t->logical_block_size);
t->max_hw_sectors = blk_round_down_sectors(t->max_hw_sectors, t->logical_block_size);
t->max_dev_sectors = blk_round_down_sectors(t->max_dev_sectors, t->logical_block_size);
/* Discard alignment and granularity */
if (b->discard_granularity) {
alignment = queue_limit_discard_alignment(b, start);
if (t->discard_granularity != 0 &&
t->discard_alignment != alignment) {
top = t->discard_granularity + t->discard_alignment;
bottom = b->discard_granularity + alignment;
/* Verify that top and bottom intervals line up */
if ((max(top, bottom) % min(top, bottom)) != 0)
t->discard_misaligned = 1;
}
t->max_discard_sectors = min_not_zero(t->max_discard_sectors,
b->max_discard_sectors);
t->max_hw_discard_sectors = min_not_zero(t->max_hw_discard_sectors,
b->max_hw_discard_sectors);
t->discard_granularity = max(t->discard_granularity,
b->discard_granularity);
t->discard_alignment = lcm_not_zero(t->discard_alignment, alignment) %
t->discard_granularity;
}
t->max_secure_erase_sectors = min_not_zero(t->max_secure_erase_sectors,
b->max_secure_erase_sectors);
t->zone_write_granularity = max(t->zone_write_granularity,
b->zone_write_granularity);
t->zoned = max(t->zoned, b->zoned);
return ret;
}
EXPORT_SYMBOL(blk_stack_limits);
/**
* disk_stack_limits - adjust queue limits for stacked drivers
* @disk: MD/DM gendisk (top)
* @bdev: the underlying block device (bottom)
* @offset: offset to beginning of data within component device
*
* Description:
* Merges the limits for a top level gendisk and a bottom level
* block_device.
*/
void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
sector_t offset)
{
struct request_queue *t = disk->queue;
if (blk_stack_limits(&t->limits, &bdev_get_queue(bdev)->limits,
get_start_sect(bdev) + (offset >> 9)) < 0)
pr_notice("%s: Warning: Device %pg is misaligned\n",
disk->disk_name, bdev);
disk_update_readahead(disk);
}
EXPORT_SYMBOL(disk_stack_limits);
/**
* blk_queue_update_dma_pad - update pad mask
* @q: the request queue for the device
* @mask: pad mask
*
* Update dma pad mask.
*
* Appending pad buffer to a request modifies the last entry of a
* scatter list such that it includes the pad buffer.
**/
void blk_queue_update_dma_pad(struct request_queue *q, unsigned int mask)
{
if (mask > q->dma_pad_mask)
q->dma_pad_mask = mask;
}
EXPORT_SYMBOL(blk_queue_update_dma_pad);
/**
* blk_queue_segment_boundary - set boundary rules for segment merging
* @q: the request queue for the device
* @mask: the memory boundary mask
**/
void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask)
{
if (mask < PAGE_SIZE - 1) {
mask = PAGE_SIZE - 1;
printk(KERN_INFO "%s: set to minimum %lx\n",
__func__, mask);
}
q->limits.seg_boundary_mask = mask;
}
EXPORT_SYMBOL(blk_queue_segment_boundary);
/**
* blk_queue_virt_boundary - set boundary rules for bio merging
* @q: the request queue for the device
* @mask: the memory boundary mask
**/
void blk_queue_virt_boundary(struct request_queue *q, unsigned long mask)
{
q->limits.virt_boundary_mask = mask;
/*
* Devices that require a virtual boundary do not support scatter/gather
* I/O natively, but instead require a descriptor list entry for each
* page (which might not be idential to the Linux PAGE_SIZE). Because
* of that they are not limited by our notion of "segment size".
*/
if (mask)
q->limits.max_segment_size = UINT_MAX;
}
EXPORT_SYMBOL(blk_queue_virt_boundary);
/**
* blk_queue_dma_alignment - set dma length and memory alignment
* @q: the request queue for the device
* @mask: alignment mask
*
* description:
* set required memory and length alignment for direct dma transactions.
* this is used when building direct io requests for the queue.
*
**/
void blk_queue_dma_alignment(struct request_queue *q, int mask)
{
q->limits.dma_alignment = mask;
}
EXPORT_SYMBOL(blk_queue_dma_alignment);
/**
* blk_queue_update_dma_alignment - update dma length and memory alignment
* @q: the request queue for the device
* @mask: alignment mask
*
* description:
* update required memory and length alignment for direct dma transactions.
* If the requested alignment is larger than the current alignment, then
* the current queue alignment is updated to the new value, otherwise it
* is left alone. The design of this is to allow multiple objects
* (driver, device, transport etc) to set their respective
* alignments without having them interfere.
*
**/
void blk_queue_update_dma_alignment(struct request_queue *q, int mask)
{
BUG_ON(mask > PAGE_SIZE);
if (mask > q->limits.dma_alignment)
q->limits.dma_alignment = mask;
}
EXPORT_SYMBOL(blk_queue_update_dma_alignment);
/**
* blk_set_queue_depth - tell the block layer about the device queue depth
* @q: the request queue for the device
* @depth: queue depth
*
*/
void blk_set_queue_depth(struct request_queue *q, unsigned int depth)
{
q->queue_depth = depth;
rq_qos_queue_depth_changed(q);
}
EXPORT_SYMBOL(blk_set_queue_depth);
/**
* blk_queue_write_cache - configure queue's write cache
* @q: the request queue for the device
* @wc: write back cache on or off
* @fua: device supports FUA writes, if true
*
* Tell the block layer about the write cache of @q.
*/
void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
{
if (wc)
blk_queue_flag_set(QUEUE_FLAG_WC, q);
else
blk_queue_flag_clear(QUEUE_FLAG_WC, q);
if (fua)
blk_queue_flag_set(QUEUE_FLAG_FUA, q);
else
blk_queue_flag_clear(QUEUE_FLAG_FUA, q);
wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
}
EXPORT_SYMBOL_GPL(blk_queue_write_cache);
/**
* blk_queue_required_elevator_features - Set a queue required elevator features
* @q: the request queue for the target device
* @features: Required elevator features OR'ed together
*
* Tell the block layer that for the device controlled through @q, only the
* only elevators that can be used are those that implement at least the set of
* features specified by @features.
*/
void blk_queue_required_elevator_features(struct request_queue *q,
unsigned int features)
{
q->required_elevator_features = features;
}
EXPORT_SYMBOL_GPL(blk_queue_required_elevator_features);
/**
* blk_queue_can_use_dma_map_merging - configure queue for merging segments.
* @q: the request queue for the device
* @dev: the device pointer for dma
*
* Tell the block layer about merging the segments by dma map of @q.
*/
bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
struct device *dev)
{
unsigned long boundary = dma_get_merge_boundary(dev);
if (!boundary)
return false;
/* No need to update max_segment_size. see blk_queue_virt_boundary() */
blk_queue_virt_boundary(q, boundary);
return true;
}
EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging);
static bool disk_has_partitions(struct gendisk *disk)
{
unsigned long idx;
struct block_device *part;
bool ret = false;
rcu_read_lock();
xa_for_each(&disk->part_tbl, idx, part) {
if (bdev_is_partition(part)) {
ret = true;
break;
}
}
rcu_read_unlock();
return ret;
}
/**
* disk_set_zoned - configure the zoned model for a disk
* @disk: the gendisk of the queue to configure
* @model: the zoned model to set
*
* Set the zoned model of @disk to @model.
*
* When @model is BLK_ZONED_HM (host managed), this should be called only
* if zoned block device support is enabled (CONFIG_BLK_DEV_ZONED option).
* If @model specifies BLK_ZONED_HA (host aware), the effective model used
* depends on CONFIG_BLK_DEV_ZONED settings and on the existence of partitions
* on the disk.
*/
void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
{
struct request_queue *q = disk->queue;
switch (model) {
case BLK_ZONED_HM:
/*
* Host managed devices are supported only if
* CONFIG_BLK_DEV_ZONED is enabled.
*/
WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED));
break;
case BLK_ZONED_HA:
/*
* Host aware devices can be treated either as regular block
* devices (similar to drive managed devices) or as zoned block
* devices to take advantage of the zone command set, similarly
* to host managed devices. We try the latter if there are no
* partitions and zoned block device support is enabled, else
* we do nothing special as far as the block layer is concerned.
*/
if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) ||
disk_has_partitions(disk))
model = BLK_ZONED_NONE;
break;
case BLK_ZONED_NONE:
default:
if (WARN_ON_ONCE(model != BLK_ZONED_NONE))
model = BLK_ZONED_NONE;
break;
}
q->limits.zoned = model;
if (model != BLK_ZONED_NONE) {
/*
* Set the zone write granularity to the device logical block
* size by default. The driver can change this value if needed.
*/
blk_queue_zone_write_granularity(q,
queue_logical_block_size(q));
} else {
disk_clear_zone_settings(disk);
}
}
EXPORT_SYMBOL_GPL(disk_set_zoned);
int bdev_alignment_offset(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (q->limits.misaligned)
return -1;
if (bdev_is_partition(bdev))
return queue_limit_alignment_offset(&q->limits,
bdev->bd_start_sect);
return q->limits.alignment_offset;
}
EXPORT_SYMBOL_GPL(bdev_alignment_offset);
unsigned int bdev_discard_alignment(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (bdev_is_partition(bdev))
return queue_limit_discard_alignment(&q->limits,
bdev->bd_start_sect);
return q->limits.discard_alignment;
}
EXPORT_SYMBOL_GPL(bdev_discard_alignment);