linux/block/blk-settings.c

768 lines
24 KiB
C
Raw Normal View History

// 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/blk-integrity.h>
#include <linux/pagemap.h>
#include <linux/backing-dev-defs.h>
#include <linux/gcd.h>
#include <linux/lcm.h>
#include <linux/jiffies.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/gfp.h>
#include <linux/dma-mapping.h>
#include "blk.h"
#include "blk-rq-qos.h"
block: hook up writeback throttling Enable throttling of buffered writeback to make it a lot more smooth, and has way less impact on other system activity. Background writeback should be, by definition, background activity. The fact that we flush huge bundles of it at the time means that it potentially has heavy impacts on foreground workloads, which isn't ideal. We can't easily limit the sizes of writes that we do, since that would impact file system layout in the presence of delayed allocation. So just throttle back buffered writeback, unless someone is waiting for it. The algorithm for when to throttle takes its inspiration in the CoDel networking scheduling algorithm. Like CoDel, blk-wb monitors the minimum latencies of requests over a window of time. In that window of time, if the minimum latency of any request exceeds a given target, then a scale count is incremented and the queue depth is shrunk. The next monitoring window is shrunk accordingly. Unlike CoDel, if we hit a window that exhibits good behavior, then we simply increment the scale count and re-calculate the limits for that scale value. This prevents us from oscillating between a close-to-ideal value and max all the time, instead remaining in the windows where we get good behavior. Unlike CoDel, blk-wb allows the scale count to to negative. This happens if we primarily have writes going on. Unlike positive scale counts, this doesn't change the size of the monitoring window. When the heavy writers finish, blk-bw quickly snaps back to it's stable state of a zero scale count. The patch registers a sysfs entry, 'wb_lat_usec'. This sets the latency target to me met. It defaults to 2 msec for non-rotational storage, and 75 msec for rotational storage. Setting this value to '0' disables blk-wb. Generally, a user would not have to touch this setting. We don't enable WBT on devices that are managed with CFQ, and have a non-root block cgroup attached. If we have a proportional share setup on this particular disk, then the wbt throttling will interfere with that. We don't have a strong need for wbt for that case, since we will rely on CFQ doing that for us. Signed-off-by: Jens Axboe <axboe@fb.com>
2016-11-09 19:38:14 +00:00
#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_stacking_limits - set default limits for stacking devices
* @lim: the queue_limits structure to reset
*
* Prepare queue limits for applying limits from underlying devices using
* blk_stack_limits().
*/
void blk_set_stacking_limits(struct queue_limits *lim)
{
memset(lim, 0, sizeof(*lim));
lim->logical_block_size = SECTOR_SIZE;
lim->physical_block_size = SECTOR_SIZE;
lim->io_min = SECTOR_SIZE;
lim->discard_granularity = SECTOR_SIZE;
lim->dma_alignment = SECTOR_SIZE - 1;
lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
/* 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;
block/sd: Fix device-imposed transfer length limits Commit 4f258a46346c ("sd: Fix maximum I/O size for BLOCK_PC requests") had the unfortunate side-effect of removing an implicit clamp to BLK_DEF_MAX_SECTORS for REQ_TYPE_FS requests in the block layer code. This caused problems for some SMR drives. Debugging this issue revealed a few problems with the existing infrastructure since the block layer didn't know how to deal with device-imposed limits, only limits set by the I/O controller. - Introduce a new queue limit, max_dev_sectors, which is used by the ULD to signal the maximum sectors for a REQ_TYPE_FS request. - Ensure that max_dev_sectors is correctly stacked and taken into account when overriding max_sectors through sysfs. - Rework sd_read_block_limits() so it saves the max_xfer and opt_xfer values for later processing. - In sd_revalidate() set the queue's max_dev_sectors based on the MAXIMUM TRANSFER LENGTH value in the Block Limits VPD. If this value is not reported, fall back to a cap based on the CDB TRANSFER LENGTH field size. - In sd_revalidate(), use OPTIMAL TRANSFER LENGTH from the Block Limits VPD--if reported and sane--to signal the preferred device transfer size for FS requests. Otherwise use BLK_DEF_MAX_SECTORS. - blk_limits_max_hw_sectors() is no longer used and can be removed. Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=93581 Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: sweeneygj@gmx.com Tested-by: Arzeets <anatol.pomozov@gmail.com> Tested-by: David Eisner <david.eisner@oriel.oxon.org> Tested-by: Mario Kicherer <dev@kicherer.org> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2015-11-13 21:46:48 +00:00
lim->max_dev_sectors = UINT_MAX;
lim->max_write_zeroes_sectors = UINT_MAX;
block: Introduce REQ_OP_ZONE_APPEND Define REQ_OP_ZONE_APPEND to append-write sectors to a zone of a zoned block device. This is a no-merge write operation. A zone append write BIO must: * Target a zoned block device * Have a sector position indicating the start sector of the target zone * The target zone must be a sequential write zone * The BIO must not cross a zone boundary * The BIO size must not be split to ensure that a single range of LBAs is written with a single command. Implement these checks in generic_make_request_checks() using the helper function blk_check_zone_append(). To avoid write append BIO splitting, introduce the new max_zone_append_sectors queue limit attribute and ensure that a BIO size is always lower than this limit. Export this new limit through sysfs and check these limits in bio_full(). Also when a LLDD can't dispatch a request to a specific zone, it will return BLK_STS_ZONE_RESOURCE indicating this request needs to be delayed, e.g. because the zone it will be dispatched to is still write-locked. If this happens set the request aside in a local list to continue trying dispatching requests such as READ requests or a WRITE/ZONE_APPEND requests targetting other zones. This way we can still keep a high queue depth without starving other requests even if one request can't be served due to zone write-locking. Finally, make sure that the bio sector position indicates the actual write position as indicated by the device on completion. Signed-off-by: Keith Busch <kbusch@kernel.org> [ jth: added zone-append specific add_page and merge_page helpers ] Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-05-12 08:55:47 +00:00
lim->max_zone_append_sectors = UINT_MAX;
lim->max_user_discard_sectors = UINT_MAX;
}
EXPORT_SYMBOL(blk_set_stacking_limits);
void blk_apply_bdi_limits(struct backing_dev_info *bdi,
struct queue_limits *lim)
{
/*
* For read-ahead of large files to be effective, we need to read ahead
* at least twice the optimal I/O size.
*/
bdi->ra_pages = max(lim->io_opt * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
bdi->io_pages = lim->max_sectors >> PAGE_SECTORS_SHIFT;
}
static int blk_validate_zoned_limits(struct queue_limits *lim)
{
if (!(lim->features & BLK_FEAT_ZONED)) {
if (WARN_ON_ONCE(lim->max_open_zones) ||
WARN_ON_ONCE(lim->max_active_zones) ||
WARN_ON_ONCE(lim->zone_write_granularity) ||
WARN_ON_ONCE(lim->max_zone_append_sectors))
return -EINVAL;
return 0;
}
if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED)))
return -EINVAL;
block: Improve checks on zone resource limits Make sure that the zone resource limits of a zoned block device are correct by checking that: (a) If the device has a max active zones limit, make sure that the max open zones limit is lower than the max active zones limit. (b) If the device has zone resource limits, check that the limits values are lower than the number of sequential zones of the device. If it is not, assume that the zoned device has no limits by setting the limits to 0. For (a), a check is added to blk_validate_zoned_limits() and an error returned if the max open zones limit exceeds the value of the max active zone limit (if there is one). For (b), given that we need the number of sequential zones of the zoned device, this check is added to disk_update_zone_resources(). This is safe to do as that function is executed with the disk queue frozen and the check executed after queue_limits_start_update() which takes the queue limits lock. Of note is that the early return in this function for zoned devices that do not use zone write plugging (e.g. DM devices using native zone append) is moved to after the new check and adjustment of the zone resource limits so that the check applies to any zoned device. Signed-off-by: Damien Le Moal <dlemoal@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Niklas Cassel <cassel@kernel.org> Reviewed-by: Benjamin Marzinski <bmarzins@redhat.com> Link: https://lore.kernel.org/r/20240611023639.89277-2-dlemoal@kernel.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-06-11 02:36:36 +00:00
/*
* Given that active zones include open zones, the maximum number of
* open zones cannot be larger than the maximum number of active zones.
*/
if (lim->max_active_zones &&
lim->max_open_zones > lim->max_active_zones)
return -EINVAL;
if (lim->zone_write_granularity < lim->logical_block_size)
lim->zone_write_granularity = lim->logical_block_size;
Revert "block: pre-calculate max_zone_append_sectors" This causes issue on, at least, nvme-mpath where my boot fails with: WARNING: CPU: 354 PID: 2729 at block/blk-settings.c:75 blk_validate_limits+0x356/0x380 Modules linked in: tg3(+) nvme usbcore scsi_mod ptp i2c_piix4 libphy nvme_core crc32c_intel scsi_common usb_common pps_core i2c_smbus CPU: 354 UID: 0 PID: 2729 Comm: kworker/u2061:1 Not tainted 6.12.0-rc6+ #181 Hardware name: Dell Inc. PowerEdge R7625/06444F, BIOS 1.8.3 04/02/2024 Workqueue: async async_run_entry_fn RIP: 0010:blk_validate_limits+0x356/0x380 Code: f6 47 01 04 75 28 83 bf 94 00 00 00 00 75 39 83 bf 98 00 00 00 00 75 34 83 7f 68 00 75 32 31 c0 83 7f 5c 00 0f 84 9b fd ff ff <0f> 0b eb 13 0f 0b eb 0f 48 c7 c0 74 12 58 92 48 89 c7 e8 13 76 46 RSP: 0018:ffffa8a1dfb93b30 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff9232829c8388 RCX: 0000000000000088 RDX: 0000000000000080 RSI: 0000000000000200 RDI: ffffa8a1dfb93c38 RBP: 000000000000000c R08: 00000000ffffffff R09: 000000000000ffff R10: 0000000000000000 R11: 0000000000000000 R12: ffff9232829b9000 R13: ffff9232829b9010 R14: ffffa8a1dfb93c38 R15: ffffa8a1dfb93c38 FS: 0000000000000000(0000) GS:ffff923867c80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055c1b92480a8 CR3: 0000002484ff0002 CR4: 0000000000370ef0 Call Trace: <TASK> ? __warn+0xca/0x1a0 ? blk_validate_limits+0x356/0x380 ? report_bug+0x11a/0x1a0 ? handle_bug+0x5e/0x90 ? exc_invalid_op+0x16/0x40 ? asm_exc_invalid_op+0x16/0x20 ? blk_validate_limits+0x356/0x380 blk_alloc_queue+0x7a/0x250 __blk_alloc_disk+0x39/0x80 nvme_mpath_alloc_disk+0x13d/0x1b0 [nvme_core] nvme_scan_ns+0xcc7/0x1010 [nvme_core] async_run_entry_fn+0x27/0x120 process_scheduled_works+0x1a0/0x360 worker_thread+0x2bc/0x350 ? pr_cont_work+0x1b0/0x1b0 kthread+0x111/0x120 ? kthread_unuse_mm+0x90/0x90 ret_from_fork+0x30/0x40 ? kthread_unuse_mm+0x90/0x90 ret_from_fork_asm+0x11/0x20 </TASK> ---[ end trace 0000000000000000 ]--- presumably due to max_zone_append_sectors not being cleared to zero, resulting in blk_validate_zoned_limits() complaining and failing. This reverts commit 2a8f6153e1c2db06a537a5c9d61102eb591776f1. Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-11-07 12:45:34 +00:00
if (lim->max_zone_append_sectors) {
/*
* The Zone Append size is limited by the maximum I/O size
* and the zone size given that it can't span zones.
*/
lim->max_zone_append_sectors =
min3(lim->max_hw_sectors,
lim->max_zone_append_sectors,
lim->chunk_sectors);
}
return 0;
}
static int blk_validate_integrity_limits(struct queue_limits *lim)
{
struct blk_integrity *bi = &lim->integrity;
if (!bi->tuple_size) {
if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE ||
bi->tag_size || ((bi->flags & BLK_INTEGRITY_REF_TAG))) {
pr_warn("invalid PI settings.\n");
return -EINVAL;
}
return 0;
}
if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) {
pr_warn("integrity support disabled.\n");
return -EINVAL;
}
if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE &&
(bi->flags & BLK_INTEGRITY_REF_TAG)) {
pr_warn("ref tag not support without checksum.\n");
return -EINVAL;
}
if (!bi->interval_exp)
bi->interval_exp = ilog2(lim->logical_block_size);
return 0;
}
block: Add core atomic write support Add atomic write support, as follows: - add helper functions to get request_queue atomic write limits - report request_queue atomic write support limits to sysfs and update Doc - support to safely merge atomic writes - deal with splitting atomic writes - misc helper functions - add a per-request atomic write flag New request_queue limits are added, as follows: - atomic_write_hw_max is set by the block driver and is the maximum length of an atomic write which the device may support. It is not necessarily a power-of-2. - atomic_write_max_sectors is derived from atomic_write_hw_max_sectors and max_hw_sectors. It is always a power-of-2. Atomic writes may be merged, and atomic_write_max_sectors would be the limit on a merged atomic write request size. This value is not capped at max_sectors, as the value in max_sectors can be controlled from userspace, and it would only cause trouble if userspace could limit atomic_write_unit_max_bytes and the other atomic write limits. - atomic_write_hw_unit_{min,max} are set by the block driver and are the min/max length of an atomic write unit which the device may support. They both must be a power-of-2. Typically atomic_write_hw_unit_max will hold the same value as atomic_write_hw_max. - atomic_write_unit_{min,max} are derived from atomic_write_hw_unit_{min,max}, max_hw_sectors, and block core limits. Both min and max values must be a power-of-2. - atomic_write_hw_boundary is set by the block driver. If non-zero, it indicates an LBA space boundary at which an atomic write straddles no longer is atomically executed by the disk. The value must be a power-of-2. Note that it would be acceptable to enforce a rule that atomic_write_hw_boundary_sectors is a multiple of atomic_write_hw_unit_max, but the resultant code would be more complicated. All atomic writes limits are by default set 0 to indicate no atomic write support. Even though it is assumed by Linux that a logical block can always be atomically written, we ignore this as it is not of particular interest. Stacked devices are just not supported either for now. An atomic write must always be submitted to the block driver as part of a single request. As such, only a single BIO must be submitted to the block layer for an atomic write. When a single atomic write BIO is submitted, it cannot be split. As such, atomic_write_unit_{max, min}_bytes are limited by the maximum guaranteed BIO size which will not be required to be split. This max size is calculated by request_queue max segments and the number of bvecs a BIO can fit, BIO_MAX_VECS. Currently we rely on userspace issuing a write with iovcnt=1 for pwritev2() - as such, we can rely on each segment containing PAGE_SIZE of data, apart from the first+last, which each can fit logical block size of data. The first+last will be LBS length/aligned as we rely on direct IO alignment rules also. New sysfs files are added to report the following atomic write limits: - atomic_write_unit_max_bytes - same as atomic_write_unit_max_sectors in bytes - atomic_write_unit_min_bytes - same as atomic_write_unit_min_sectors in bytes - atomic_write_boundary_bytes - same as atomic_write_hw_boundary_sectors in bytes - atomic_write_max_bytes - same as atomic_write_max_sectors in bytes Atomic writes may only be merged with other atomic writes and only under the following conditions: - total resultant request length <= atomic_write_max_bytes - the merged write does not straddle a boundary Helper function bdev_can_atomic_write() is added to indicate whether atomic writes may be issued to a bdev. If a bdev is a partition, the partition start must be aligned with both atomic_write_unit_min_sectors and atomic_write_hw_boundary_sectors. FSes will rely on the block layer to validate that an atomic write BIO submitted will be of valid size, so add blk_validate_atomic_write_op_size() for this purpose. Userspace expects an atomic write which is of invalid size to be rejected with -EINVAL, so add BLK_STS_INVAL for this. Also use BLK_STS_INVAL for when a BIO needs to be split, as this should mean an invalid size BIO. Flag REQ_ATOMIC is used for indicating an atomic write. Co-developed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Himanshu Madhani <himanshu.madhani@oracle.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: John Garry <john.g.garry@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Link: https://lore.kernel.org/r/20240620125359.2684798-6-john.g.garry@oracle.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-06-20 12:53:54 +00:00
/*
* Returns max guaranteed bytes which we can fit in a bio.
*
* We request that an atomic_write is ITER_UBUF iov_iter (so a single vector),
* so we assume that we can fit in at least PAGE_SIZE in a segment, apart from
* the first and last segments.
*/
static unsigned int blk_queue_max_guaranteed_bio(struct queue_limits *lim)
block: Add core atomic write support Add atomic write support, as follows: - add helper functions to get request_queue atomic write limits - report request_queue atomic write support limits to sysfs and update Doc - support to safely merge atomic writes - deal with splitting atomic writes - misc helper functions - add a per-request atomic write flag New request_queue limits are added, as follows: - atomic_write_hw_max is set by the block driver and is the maximum length of an atomic write which the device may support. It is not necessarily a power-of-2. - atomic_write_max_sectors is derived from atomic_write_hw_max_sectors and max_hw_sectors. It is always a power-of-2. Atomic writes may be merged, and atomic_write_max_sectors would be the limit on a merged atomic write request size. This value is not capped at max_sectors, as the value in max_sectors can be controlled from userspace, and it would only cause trouble if userspace could limit atomic_write_unit_max_bytes and the other atomic write limits. - atomic_write_hw_unit_{min,max} are set by the block driver and are the min/max length of an atomic write unit which the device may support. They both must be a power-of-2. Typically atomic_write_hw_unit_max will hold the same value as atomic_write_hw_max. - atomic_write_unit_{min,max} are derived from atomic_write_hw_unit_{min,max}, max_hw_sectors, and block core limits. Both min and max values must be a power-of-2. - atomic_write_hw_boundary is set by the block driver. If non-zero, it indicates an LBA space boundary at which an atomic write straddles no longer is atomically executed by the disk. The value must be a power-of-2. Note that it would be acceptable to enforce a rule that atomic_write_hw_boundary_sectors is a multiple of atomic_write_hw_unit_max, but the resultant code would be more complicated. All atomic writes limits are by default set 0 to indicate no atomic write support. Even though it is assumed by Linux that a logical block can always be atomically written, we ignore this as it is not of particular interest. Stacked devices are just not supported either for now. An atomic write must always be submitted to the block driver as part of a single request. As such, only a single BIO must be submitted to the block layer for an atomic write. When a single atomic write BIO is submitted, it cannot be split. As such, atomic_write_unit_{max, min}_bytes are limited by the maximum guaranteed BIO size which will not be required to be split. This max size is calculated by request_queue max segments and the number of bvecs a BIO can fit, BIO_MAX_VECS. Currently we rely on userspace issuing a write with iovcnt=1 for pwritev2() - as such, we can rely on each segment containing PAGE_SIZE of data, apart from the first+last, which each can fit logical block size of data. The first+last will be LBS length/aligned as we rely on direct IO alignment rules also. New sysfs files are added to report the following atomic write limits: - atomic_write_unit_max_bytes - same as atomic_write_unit_max_sectors in bytes - atomic_write_unit_min_bytes - same as atomic_write_unit_min_sectors in bytes - atomic_write_boundary_bytes - same as atomic_write_hw_boundary_sectors in bytes - atomic_write_max_bytes - same as atomic_write_max_sectors in bytes Atomic writes may only be merged with other atomic writes and only under the following conditions: - total resultant request length <= atomic_write_max_bytes - the merged write does not straddle a boundary Helper function bdev_can_atomic_write() is added to indicate whether atomic writes may be issued to a bdev. If a bdev is a partition, the partition start must be aligned with both atomic_write_unit_min_sectors and atomic_write_hw_boundary_sectors. FSes will rely on the block layer to validate that an atomic write BIO submitted will be of valid size, so add blk_validate_atomic_write_op_size() for this purpose. Userspace expects an atomic write which is of invalid size to be rejected with -EINVAL, so add BLK_STS_INVAL for this. Also use BLK_STS_INVAL for when a BIO needs to be split, as this should mean an invalid size BIO. Flag REQ_ATOMIC is used for indicating an atomic write. Co-developed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Himanshu Madhani <himanshu.madhani@oracle.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: John Garry <john.g.garry@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Link: https://lore.kernel.org/r/20240620125359.2684798-6-john.g.garry@oracle.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-06-20 12:53:54 +00:00
{
unsigned int max_segments = min(BIO_MAX_VECS, lim->max_segments);
unsigned int length;
length = min(max_segments, 2) * lim->logical_block_size;
if (max_segments > 2)
length += (max_segments - 2) * PAGE_SIZE;
return length;
}
static void blk_atomic_writes_update_limits(struct queue_limits *lim)
{
unsigned int unit_limit = min(lim->max_hw_sectors << SECTOR_SHIFT,
blk_queue_max_guaranteed_bio(lim));
unit_limit = rounddown_pow_of_two(unit_limit);
lim->atomic_write_max_sectors =
min(lim->atomic_write_hw_max >> SECTOR_SHIFT,
lim->max_hw_sectors);
lim->atomic_write_unit_min =
min(lim->atomic_write_hw_unit_min, unit_limit);
lim->atomic_write_unit_max =
min(lim->atomic_write_hw_unit_max, unit_limit);
lim->atomic_write_boundary_sectors =
lim->atomic_write_hw_boundary >> SECTOR_SHIFT;
}
static void blk_validate_atomic_write_limits(struct queue_limits *lim)
{
unsigned int boundary_sectors;
if (!lim->atomic_write_hw_max)
goto unsupported;
boundary_sectors = lim->atomic_write_hw_boundary >> SECTOR_SHIFT;
if (boundary_sectors) {
/*
* A feature of boundary support is that it disallows bios to
* be merged which would result in a merged request which
* crosses either a chunk sector or atomic write HW boundary,
* even though chunk sectors may be just set for performance.
* For simplicity, disallow atomic writes for a chunk sector
* which is non-zero and smaller than atomic write HW boundary.
* Furthermore, chunk sectors must be a multiple of atomic
* write HW boundary. Otherwise boundary support becomes
* complicated.
* Devices which do not conform to these rules can be dealt
* with if and when they show up.
*/
if (WARN_ON_ONCE(lim->chunk_sectors % boundary_sectors))
block: Add core atomic write support Add atomic write support, as follows: - add helper functions to get request_queue atomic write limits - report request_queue atomic write support limits to sysfs and update Doc - support to safely merge atomic writes - deal with splitting atomic writes - misc helper functions - add a per-request atomic write flag New request_queue limits are added, as follows: - atomic_write_hw_max is set by the block driver and is the maximum length of an atomic write which the device may support. It is not necessarily a power-of-2. - atomic_write_max_sectors is derived from atomic_write_hw_max_sectors and max_hw_sectors. It is always a power-of-2. Atomic writes may be merged, and atomic_write_max_sectors would be the limit on a merged atomic write request size. This value is not capped at max_sectors, as the value in max_sectors can be controlled from userspace, and it would only cause trouble if userspace could limit atomic_write_unit_max_bytes and the other atomic write limits. - atomic_write_hw_unit_{min,max} are set by the block driver and are the min/max length of an atomic write unit which the device may support. They both must be a power-of-2. Typically atomic_write_hw_unit_max will hold the same value as atomic_write_hw_max. - atomic_write_unit_{min,max} are derived from atomic_write_hw_unit_{min,max}, max_hw_sectors, and block core limits. Both min and max values must be a power-of-2. - atomic_write_hw_boundary is set by the block driver. If non-zero, it indicates an LBA space boundary at which an atomic write straddles no longer is atomically executed by the disk. The value must be a power-of-2. Note that it would be acceptable to enforce a rule that atomic_write_hw_boundary_sectors is a multiple of atomic_write_hw_unit_max, but the resultant code would be more complicated. All atomic writes limits are by default set 0 to indicate no atomic write support. Even though it is assumed by Linux that a logical block can always be atomically written, we ignore this as it is not of particular interest. Stacked devices are just not supported either for now. An atomic write must always be submitted to the block driver as part of a single request. As such, only a single BIO must be submitted to the block layer for an atomic write. When a single atomic write BIO is submitted, it cannot be split. As such, atomic_write_unit_{max, min}_bytes are limited by the maximum guaranteed BIO size which will not be required to be split. This max size is calculated by request_queue max segments and the number of bvecs a BIO can fit, BIO_MAX_VECS. Currently we rely on userspace issuing a write with iovcnt=1 for pwritev2() - as such, we can rely on each segment containing PAGE_SIZE of data, apart from the first+last, which each can fit logical block size of data. The first+last will be LBS length/aligned as we rely on direct IO alignment rules also. New sysfs files are added to report the following atomic write limits: - atomic_write_unit_max_bytes - same as atomic_write_unit_max_sectors in bytes - atomic_write_unit_min_bytes - same as atomic_write_unit_min_sectors in bytes - atomic_write_boundary_bytes - same as atomic_write_hw_boundary_sectors in bytes - atomic_write_max_bytes - same as atomic_write_max_sectors in bytes Atomic writes may only be merged with other atomic writes and only under the following conditions: - total resultant request length <= atomic_write_max_bytes - the merged write does not straddle a boundary Helper function bdev_can_atomic_write() is added to indicate whether atomic writes may be issued to a bdev. If a bdev is a partition, the partition start must be aligned with both atomic_write_unit_min_sectors and atomic_write_hw_boundary_sectors. FSes will rely on the block layer to validate that an atomic write BIO submitted will be of valid size, so add blk_validate_atomic_write_op_size() for this purpose. Userspace expects an atomic write which is of invalid size to be rejected with -EINVAL, so add BLK_STS_INVAL for this. Also use BLK_STS_INVAL for when a BIO needs to be split, as this should mean an invalid size BIO. Flag REQ_ATOMIC is used for indicating an atomic write. Co-developed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Himanshu Madhani <himanshu.madhani@oracle.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: John Garry <john.g.garry@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Link: https://lore.kernel.org/r/20240620125359.2684798-6-john.g.garry@oracle.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-06-20 12:53:54 +00:00
goto unsupported;
/*
* The boundary size just needs to be a multiple of unit_max
* (and not necessarily a power-of-2), so this following check
* could be relaxed in future.
* Furthermore, if needed, unit_max could even be reduced so
* that it is compliant with a !power-of-2 boundary.
*/
if (!is_power_of_2(boundary_sectors))
goto unsupported;
}
blk_atomic_writes_update_limits(lim);
return;
unsupported:
lim->atomic_write_max_sectors = 0;
lim->atomic_write_boundary_sectors = 0;
lim->atomic_write_unit_min = 0;
lim->atomic_write_unit_max = 0;
}
/*
* Check that the limits in lim are valid, initialize defaults for unset
* values, and cap values based on others where needed.
*/
static int blk_validate_limits(struct queue_limits *lim)
{
unsigned int max_hw_sectors;
unsigned int logical_block_sectors;
int err;
/*
* Unless otherwise specified, default to 512 byte logical blocks and a
* physical block size equal to the logical block size.
*/
if (!lim->logical_block_size)
lim->logical_block_size = SECTOR_SIZE;
else if (blk_validate_block_size(lim->logical_block_size)) {
pr_warn("Invalid logical block size (%d)\n", lim->logical_block_size);
return -EINVAL;
}
if (lim->physical_block_size < lim->logical_block_size)
lim->physical_block_size = lim->logical_block_size;
/*
* The minimum I/O size defaults to the physical block size unless
* explicitly overridden.
*/
if (lim->io_min < lim->physical_block_size)
lim->io_min = lim->physical_block_size;
/*
* max_hw_sectors has a somewhat weird default for historical reason,
* but driver really should set their own instead of relying on this
* value.
*
* The block layer relies on the fact that every driver can
* handle at lest a page worth of data per I/O, and needs the value
* aligned to the logical block size.
*/
if (!lim->max_hw_sectors)
lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
if (WARN_ON_ONCE(lim->max_hw_sectors < PAGE_SECTORS))
return -EINVAL;
logical_block_sectors = lim->logical_block_size >> SECTOR_SHIFT;
if (WARN_ON_ONCE(logical_block_sectors > lim->max_hw_sectors))
return -EINVAL;
lim->max_hw_sectors = round_down(lim->max_hw_sectors,
logical_block_sectors);
/*
* The actual max_sectors value is a complex beast and also takes the
* max_dev_sectors value (set by SCSI ULPs) and a user configurable
* value into account. The ->max_sectors value is always calculated
* from these, so directly setting it won't have any effect.
*/
max_hw_sectors = min_not_zero(lim->max_hw_sectors,
lim->max_dev_sectors);
if (lim->max_user_sectors) {
if (lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE)
return -EINVAL;
lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors);
} else if (lim->io_opt > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) {
lim->max_sectors =
min(max_hw_sectors, lim->io_opt >> SECTOR_SHIFT);
} else if (lim->io_min > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) {
lim->max_sectors =
min(max_hw_sectors, lim->io_min >> SECTOR_SHIFT);
} else {
lim->max_sectors = min(max_hw_sectors, BLK_DEF_MAX_SECTORS_CAP);
}
lim->max_sectors = round_down(lim->max_sectors,
logical_block_sectors);
/*
* Random default for the maximum number of segments. Driver should not
* rely on this and set their own.
*/
if (!lim->max_segments)
lim->max_segments = BLK_MAX_SEGMENTS;
lim->max_discard_sectors =
min(lim->max_hw_discard_sectors, lim->max_user_discard_sectors);
if (!lim->max_discard_segments)
lim->max_discard_segments = 1;
if (lim->discard_granularity < lim->physical_block_size)
lim->discard_granularity = lim->physical_block_size;
/*
* By default there is no limit on the segment boundary alignment,
* but if there is one it can't be smaller than the page size as
* that would break all the normal I/O patterns.
*/
if (!lim->seg_boundary_mask)
lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
if (WARN_ON_ONCE(lim->seg_boundary_mask < PAGE_SIZE - 1))
return -EINVAL;
/*
* Stacking device may have both virtual boundary and max segment
* size limit, so allow this setting now, and long-term the two
* might need to move out of stacking limits since we have immutable
* bvec and lower layer bio splitting is supposed to handle the two
* correctly.
*/
if (lim->virt_boundary_mask) {
if (!lim->max_segment_size)
lim->max_segment_size = UINT_MAX;
} else {
/*
* The maximum segment size has an odd historic 64k default that
* drivers probably should override. Just like the I/O size we
* require drivers to at least handle a full page per segment.
*/
if (!lim->max_segment_size)
lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
if (WARN_ON_ONCE(lim->max_segment_size < PAGE_SIZE))
return -EINVAL;
}
/*
* We require drivers to at least do logical block aligned I/O, but
* historically could not check for that due to the separate calls
* to set the limits. Once the transition is finished the check
* below should be narrowed down to check the logical block size.
*/
if (!lim->dma_alignment)
lim->dma_alignment = SECTOR_SIZE - 1;
if (WARN_ON_ONCE(lim->dma_alignment > PAGE_SIZE))
return -EINVAL;
if (lim->alignment_offset) {
lim->alignment_offset &= (lim->physical_block_size - 1);
lim->flags &= ~BLK_FLAG_MISALIGNED;
}
if (!(lim->features & BLK_FEAT_WRITE_CACHE))
lim->features &= ~BLK_FEAT_FUA;
block: Add core atomic write support Add atomic write support, as follows: - add helper functions to get request_queue atomic write limits - report request_queue atomic write support limits to sysfs and update Doc - support to safely merge atomic writes - deal with splitting atomic writes - misc helper functions - add a per-request atomic write flag New request_queue limits are added, as follows: - atomic_write_hw_max is set by the block driver and is the maximum length of an atomic write which the device may support. It is not necessarily a power-of-2. - atomic_write_max_sectors is derived from atomic_write_hw_max_sectors and max_hw_sectors. It is always a power-of-2. Atomic writes may be merged, and atomic_write_max_sectors would be the limit on a merged atomic write request size. This value is not capped at max_sectors, as the value in max_sectors can be controlled from userspace, and it would only cause trouble if userspace could limit atomic_write_unit_max_bytes and the other atomic write limits. - atomic_write_hw_unit_{min,max} are set by the block driver and are the min/max length of an atomic write unit which the device may support. They both must be a power-of-2. Typically atomic_write_hw_unit_max will hold the same value as atomic_write_hw_max. - atomic_write_unit_{min,max} are derived from atomic_write_hw_unit_{min,max}, max_hw_sectors, and block core limits. Both min and max values must be a power-of-2. - atomic_write_hw_boundary is set by the block driver. If non-zero, it indicates an LBA space boundary at which an atomic write straddles no longer is atomically executed by the disk. The value must be a power-of-2. Note that it would be acceptable to enforce a rule that atomic_write_hw_boundary_sectors is a multiple of atomic_write_hw_unit_max, but the resultant code would be more complicated. All atomic writes limits are by default set 0 to indicate no atomic write support. Even though it is assumed by Linux that a logical block can always be atomically written, we ignore this as it is not of particular interest. Stacked devices are just not supported either for now. An atomic write must always be submitted to the block driver as part of a single request. As such, only a single BIO must be submitted to the block layer for an atomic write. When a single atomic write BIO is submitted, it cannot be split. As such, atomic_write_unit_{max, min}_bytes are limited by the maximum guaranteed BIO size which will not be required to be split. This max size is calculated by request_queue max segments and the number of bvecs a BIO can fit, BIO_MAX_VECS. Currently we rely on userspace issuing a write with iovcnt=1 for pwritev2() - as such, we can rely on each segment containing PAGE_SIZE of data, apart from the first+last, which each can fit logical block size of data. The first+last will be LBS length/aligned as we rely on direct IO alignment rules also. New sysfs files are added to report the following atomic write limits: - atomic_write_unit_max_bytes - same as atomic_write_unit_max_sectors in bytes - atomic_write_unit_min_bytes - same as atomic_write_unit_min_sectors in bytes - atomic_write_boundary_bytes - same as atomic_write_hw_boundary_sectors in bytes - atomic_write_max_bytes - same as atomic_write_max_sectors in bytes Atomic writes may only be merged with other atomic writes and only under the following conditions: - total resultant request length <= atomic_write_max_bytes - the merged write does not straddle a boundary Helper function bdev_can_atomic_write() is added to indicate whether atomic writes may be issued to a bdev. If a bdev is a partition, the partition start must be aligned with both atomic_write_unit_min_sectors and atomic_write_hw_boundary_sectors. FSes will rely on the block layer to validate that an atomic write BIO submitted will be of valid size, so add blk_validate_atomic_write_op_size() for this purpose. Userspace expects an atomic write which is of invalid size to be rejected with -EINVAL, so add BLK_STS_INVAL for this. Also use BLK_STS_INVAL for when a BIO needs to be split, as this should mean an invalid size BIO. Flag REQ_ATOMIC is used for indicating an atomic write. Co-developed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Himanshu Madhani <himanshu.madhani@oracle.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: John Garry <john.g.garry@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Link: https://lore.kernel.org/r/20240620125359.2684798-6-john.g.garry@oracle.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-06-20 12:53:54 +00:00
blk_validate_atomic_write_limits(lim);
err = blk_validate_integrity_limits(lim);
if (err)
return err;
return blk_validate_zoned_limits(lim);
}
/*
* Set the default limits for a newly allocated queue. @lim contains the
* initial limits set by the driver, which could be no limit in which case
* all fields are cleared to zero.
*/
int blk_set_default_limits(struct queue_limits *lim)
{
/*
* Most defaults are set by capping the bounds in blk_validate_limits,
* but max_user_discard_sectors is special and needs an explicit
* initialization to the max value here.
*/
lim->max_user_discard_sectors = UINT_MAX;
return blk_validate_limits(lim);
}
/**
* queue_limits_commit_update - commit an atomic update of queue limits
* @q: queue to update
* @lim: limits to apply
*
* Apply the limits in @lim that were obtained from queue_limits_start_update()
* and updated by the caller to @q.
*
* Returns 0 if successful, else a negative error code.
*/
int queue_limits_commit_update(struct request_queue *q,
struct queue_limits *lim)
{
int error;
error = blk_validate_limits(lim);
if (error)
goto out_unlock;
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
if (q->crypto_profile && lim->integrity.tag_size) {
pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together.\n");
error = -EINVAL;
goto out_unlock;
}
#endif
q->limits = *lim;
if (q->disk)
blk_apply_bdi_limits(q->disk->bdi, lim);
out_unlock:
mutex_unlock(&q->limits_lock);
return error;
}
EXPORT_SYMBOL_GPL(queue_limits_commit_update);
/**
* queue_limits_set - apply queue limits to queue
* @q: queue to update
* @lim: limits to apply
*
* Apply the limits in @lim that were freshly initialized to @q.
* To update existing limits use queue_limits_start_update() and
* queue_limits_commit_update() instead.
*
* Returns 0 if successful, else a negative error code.
*/
int queue_limits_set(struct request_queue *q, struct queue_limits *lim)
{
mutex_lock(&q->limits_lock);
return queue_limits_commit_update(q, lim);
}
EXPORT_SYMBOL_GPL(queue_limits_set);
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->features |= (b->features & BLK_FEAT_INHERIT_MASK);
/*
* Some feaures need to be supported both by the stacking driver and all
* underlying devices. The stacking driver sets these flags before
* stacking the limits, and this will clear the flags if any of the
* underlying devices does not support it.
*/
if (!(b->features & BLK_FEAT_NOWAIT))
t->features &= ~BLK_FEAT_NOWAIT;
if (!(b->features & BLK_FEAT_POLL))
t->features &= ~BLK_FEAT_POLL;
t->flags |= (b->flags & BLK_FLAG_MISALIGNED);
t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
t->max_user_sectors = min_not_zero(t->max_user_sectors,
b->max_user_sectors);
t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
block/sd: Fix device-imposed transfer length limits Commit 4f258a46346c ("sd: Fix maximum I/O size for BLOCK_PC requests") had the unfortunate side-effect of removing an implicit clamp to BLK_DEF_MAX_SECTORS for REQ_TYPE_FS requests in the block layer code. This caused problems for some SMR drives. Debugging this issue revealed a few problems with the existing infrastructure since the block layer didn't know how to deal with device-imposed limits, only limits set by the I/O controller. - Introduce a new queue limit, max_dev_sectors, which is used by the ULD to signal the maximum sectors for a REQ_TYPE_FS request. - Ensure that max_dev_sectors is correctly stacked and taken into account when overriding max_sectors through sysfs. - Rework sd_read_block_limits() so it saves the max_xfer and opt_xfer values for later processing. - In sd_revalidate() set the queue's max_dev_sectors based on the MAXIMUM TRANSFER LENGTH value in the Block Limits VPD. If this value is not reported, fall back to a cap based on the CDB TRANSFER LENGTH field size. - In sd_revalidate(), use OPTIMAL TRANSFER LENGTH from the Block Limits VPD--if reported and sane--to signal the preferred device transfer size for FS requests. Otherwise use BLK_DEF_MAX_SECTORS. - blk_limits_max_hw_sectors() is no longer used and can be removed. Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=93581 Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: sweeneygj@gmx.com Tested-by: Arzeets <anatol.pomozov@gmail.com> Tested-by: David Eisner <david.eisner@oriel.oxon.org> Tested-by: Mario Kicherer <dev@kicherer.org> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2015-11-13 21:46:48 +00:00
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);
Revert "block: pre-calculate max_zone_append_sectors" This causes issue on, at least, nvme-mpath where my boot fails with: WARNING: CPU: 354 PID: 2729 at block/blk-settings.c:75 blk_validate_limits+0x356/0x380 Modules linked in: tg3(+) nvme usbcore scsi_mod ptp i2c_piix4 libphy nvme_core crc32c_intel scsi_common usb_common pps_core i2c_smbus CPU: 354 UID: 0 PID: 2729 Comm: kworker/u2061:1 Not tainted 6.12.0-rc6+ #181 Hardware name: Dell Inc. PowerEdge R7625/06444F, BIOS 1.8.3 04/02/2024 Workqueue: async async_run_entry_fn RIP: 0010:blk_validate_limits+0x356/0x380 Code: f6 47 01 04 75 28 83 bf 94 00 00 00 00 75 39 83 bf 98 00 00 00 00 75 34 83 7f 68 00 75 32 31 c0 83 7f 5c 00 0f 84 9b fd ff ff <0f> 0b eb 13 0f 0b eb 0f 48 c7 c0 74 12 58 92 48 89 c7 e8 13 76 46 RSP: 0018:ffffa8a1dfb93b30 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff9232829c8388 RCX: 0000000000000088 RDX: 0000000000000080 RSI: 0000000000000200 RDI: ffffa8a1dfb93c38 RBP: 000000000000000c R08: 00000000ffffffff R09: 000000000000ffff R10: 0000000000000000 R11: 0000000000000000 R12: ffff9232829b9000 R13: ffff9232829b9010 R14: ffffa8a1dfb93c38 R15: ffffa8a1dfb93c38 FS: 0000000000000000(0000) GS:ffff923867c80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055c1b92480a8 CR3: 0000002484ff0002 CR4: 0000000000370ef0 Call Trace: <TASK> ? __warn+0xca/0x1a0 ? blk_validate_limits+0x356/0x380 ? report_bug+0x11a/0x1a0 ? handle_bug+0x5e/0x90 ? exc_invalid_op+0x16/0x40 ? asm_exc_invalid_op+0x16/0x20 ? blk_validate_limits+0x356/0x380 blk_alloc_queue+0x7a/0x250 __blk_alloc_disk+0x39/0x80 nvme_mpath_alloc_disk+0x13d/0x1b0 [nvme_core] nvme_scan_ns+0xcc7/0x1010 [nvme_core] async_run_entry_fn+0x27/0x120 process_scheduled_works+0x1a0/0x360 worker_thread+0x2bc/0x350 ? pr_cont_work+0x1b0/0x1b0 kthread+0x111/0x120 ? kthread_unuse_mm+0x90/0x90 ret_from_fork+0x30/0x40 ? kthread_unuse_mm+0x90/0x90 ret_from_fork_asm+0x11/0x20 </TASK> ---[ end trace 0000000000000000 ]--- presumably due to max_zone_append_sectors not being cleared to zero, resulting in blk_validate_zoned_limits() complaining and failing. This reverts commit 2a8f6153e1c2db06a537a5c9d61102eb591776f1. Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-11-07 12:45:34 +00:00
t->max_zone_append_sectors = min(queue_limits_max_zone_append_sectors(t),
queue_limits_max_zone_append_sectors(b));
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);
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->flags |= BLK_FLAG_MISALIGNED;
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->flags |= BLK_FLAG_MISALIGNED;
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->flags |= BLK_FLAG_MISALIGNED;
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->flags |= BLK_FLAG_MISALIGNED;
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->flags |= BLK_FLAG_MISALIGNED;
ret = -1;
}
/* 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->flags |= BLK_FLAG_MISALIGNED;
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);
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);
block: introduce zone_write_granularity limit Per ZBC and ZAC specifications, host-managed SMR hard-disks mandate that all writes into sequential write required zones be aligned to the device physical block size. However, NVMe ZNS does not have this constraint and allows write operations into sequential zones to be aligned to the device logical block size. This inconsistency does not help with software portability across device types. To solve this, introduce the zone_write_granularity queue limit to indicate the alignment constraint, in bytes, of write operations into zones of a zoned block device. This new limit is exported as a read-only sysfs queue attribute and the helper blk_queue_zone_write_granularity() introduced for drivers to set this limit. The function blk_queue_set_zoned() is modified to set this new limit to the device logical block size by default. NVMe ZNS devices as well as zoned nullb devices use this default value as is. The scsi disk driver is modified to execute the blk_queue_zone_write_granularity() helper to set the zone write granularity of host-managed SMR disks to the disk physical block size. The accessor functions queue_zone_write_granularity() and bdev_zone_write_granularity() are also introduced. Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@edc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-01-28 04:47:30 +00:00
t->zone_write_granularity = max(t->zone_write_granularity,
b->zone_write_granularity);
if (!(t->features & BLK_FEAT_ZONED)) {
t->zone_write_granularity = 0;
t->max_zone_append_sectors = 0;
}
return ret;
}
EXPORT_SYMBOL(blk_stack_limits);
/**
* queue_limits_stack_bdev - adjust queue_limits for stacked devices
* @t: the stacking driver limits (top device)
* @bdev: the underlying block device (bottom)
* @offset: offset to beginning of data within component device
* @pfx: prefix to use for warnings logged
*
* 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.
*/
void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
sector_t offset, const char *pfx)
{
if (blk_stack_limits(t, bdev_limits(bdev),
get_start_sect(bdev) + offset))
pr_notice("%s: Warning: Device %pg is misaligned\n",
pfx, bdev);
}
EXPORT_SYMBOL_GPL(queue_limits_stack_bdev);
/**
* queue_limits_stack_integrity - stack integrity profile
* @t: target queue limits
* @b: base queue limits
*
* Check if the integrity profile in the @b can be stacked into the
* target @t. Stacking is possible if either:
*
* a) does not have any integrity information stacked into it yet
* b) the integrity profile in @b is identical to the one in @t
*
* If @b can be stacked into @t, return %true. Else return %false and clear the
* integrity information in @t.
*/
bool queue_limits_stack_integrity(struct queue_limits *t,
struct queue_limits *b)
{
struct blk_integrity *ti = &t->integrity;
struct blk_integrity *bi = &b->integrity;
if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY))
return true;
if (!ti->tuple_size) {
/* inherit the settings from the first underlying device */
if (!(ti->flags & BLK_INTEGRITY_STACKED)) {
ti->flags = BLK_INTEGRITY_DEVICE_CAPABLE |
(bi->flags & BLK_INTEGRITY_REF_TAG);
ti->csum_type = bi->csum_type;
ti->tuple_size = bi->tuple_size;
ti->pi_offset = bi->pi_offset;
ti->interval_exp = bi->interval_exp;
ti->tag_size = bi->tag_size;
goto done;
}
if (!bi->tuple_size)
goto done;
}
if (ti->tuple_size != bi->tuple_size)
goto incompatible;
if (ti->interval_exp != bi->interval_exp)
goto incompatible;
if (ti->tag_size != bi->tag_size)
goto incompatible;
if (ti->csum_type != bi->csum_type)
goto incompatible;
if ((ti->flags & BLK_INTEGRITY_REF_TAG) !=
(bi->flags & BLK_INTEGRITY_REF_TAG))
goto incompatible;
done:
ti->flags |= BLK_INTEGRITY_STACKED;
return true;
incompatible:
memset(ti, 0, sizeof(*ti));
return false;
}
EXPORT_SYMBOL_GPL(queue_limits_stack_integrity);
/**
* 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);
int bdev_alignment_offset(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (q->limits.flags & BLK_FLAG_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);