linux_dsm_epyc7002/block/blk-settings.c

873 lines
27 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/blkdev.h>
mm: remove include/linux/bootmem.h Move remaining definitions and declarations from include/linux/bootmem.h into include/linux/memblock.h and remove the redundant header. The includes were replaced with the semantic patch below and then semi-automated removal of duplicated '#include <linux/memblock.h> @@ @@ - #include <linux/bootmem.h> + #include <linux/memblock.h> [sfr@canb.auug.org.au: dma-direct: fix up for the removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181002185342.133d1680@canb.auug.org.au [sfr@canb.auug.org.au: powerpc: fix up for removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181005161406.73ef8727@canb.auug.org.au [sfr@canb.auug.org.au: x86/kaslr, ACPI/NUMA: fix for linux/bootmem.h removal] Link: http://lkml.kernel.org/r/20181008190341.5e396491@canb.auug.org.au Link: http://lkml.kernel.org/r/1536927045-23536-30-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Ingo Molnar <mingo@redhat.com> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Jonas Bonn <jonas@southpole.se> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ley Foon Tan <lftan@altera.com> Cc: Mark Salter <msalter@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: Paul Burton <paul.burton@mips.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Serge Semin <fancer.lancer@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-31 05:09:49 +07:00
#include <linux/memblock.h> /* for max_pfn/max_low_pfn */
#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 15:04:11 +07:00
#include <linux/gfp.h>
#include <linux/dma-mapping.h>
#include "blk.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>
2016-11-10 02:38:14 +07:00
#include "blk-wbt.h"
unsigned long blk_max_low_pfn;
EXPORT_SYMBOL(blk_max_low_pfn);
unsigned long blk_max_pfn;
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_same_sectors = 0;
lim->max_write_zeroes_sectors = 0;
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 15:55:47 +07:00
lim->max_zone_append_sectors = 0;
lim->max_discard_sectors = 0;
lim->max_hw_discard_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_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT);
lim->alignment_offset = 0;
lim->io_opt = 0;
lim->misaligned = 0;
lim->zoned = BLK_ZONED_NONE;
}
EXPORT_SYMBOL(blk_set_default_limits);
/**
* 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;
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>
2015-11-14 04:46:48 +07:00
lim->max_dev_sectors = UINT_MAX;
lim->max_write_same_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 15:55:47 +07:00
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
* @max_addr: the maximum address the device can handle
*
* Description:
* Different hardware can have different requirements as to what pages
* it can do I/O directly to. A low level driver can call
* blk_queue_bounce_limit to have lower memory pages allocated as bounce
* buffers for doing I/O to pages residing above @max_addr.
**/
void blk_queue_bounce_limit(struct request_queue *q, u64 max_addr)
{
unsigned long b_pfn = max_addr >> PAGE_SHIFT;
int dma = 0;
q->bounce_gfp = GFP_NOIO;
#if BITS_PER_LONG == 64
/*
* Assume anything <= 4GB can be handled by IOMMU. Actually
* some IOMMUs can handle everything, but I don't know of a
* way to test this here.
*/
if (b_pfn < (min_t(u64, 0xffffffffUL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
dma = 1;
q->limits.bounce_pfn = max(max_low_pfn, b_pfn);
#else
if (b_pfn < blk_max_low_pfn)
dma = 1;
q->limits.bounce_pfn = b_pfn;
#endif
if (dma) {
init_emergency_isa_pool();
q->bounce_gfp = GFP_NOIO | GFP_DMA;
q->limits.bounce_pfn = b_pfn;
}
}
EXPORT_SYMBOL(blk_queue_bounce_limit);
/**
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>
2015-11-14 04:46:48 +07:00
* 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.
*
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>
2015-11-14 04:46:48 +07:00
* 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.
**/
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>
2015-11-14 04:46:48 +07:00
void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int 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>
2015-11-14 04:46:48 +07:00
struct queue_limits *limits = &q->limits;
unsigned int max_sectors;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 19:29:47 +07:00
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);
}
limits->max_hw_sectors = 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>
2015-11-14 04:46:48 +07:00
max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors);
max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS);
limits->max_sectors = max_sectors;
q->backing_dev_info->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_write_same_sectors - set max sectors for a single write same
* @q: the request queue for the device
* @max_write_same_sectors: maximum number of sectors to write per command
**/
void blk_queue_max_write_same_sectors(struct request_queue *q,
unsigned int max_write_same_sectors)
{
q->limits.max_write_same_sectors = max_write_same_sectors;
}
EXPORT_SYMBOL(blk_queue_max_write_same_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);
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 15:55:47 +07:00
/**
* 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)
{
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 19:29:47 +07:00
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)
{
q->limits.logical_block_size = size;
if (q->limits.physical_block_size < size)
q->limits.physical_block_size = size;
if (q->limits.io_min < q->limits.physical_block_size)
q->limits.io_min = q->limits.physical_block_size;
}
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_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 blk_queue_update_readahead(struct request_queue *q)
{
/*
* For read-ahead of large files to be effective, we need to read ahead
* at least twice the optimal I/O size.
*/
q->backing_dev_info->ra_pages =
max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
q->backing_dev_info->io_pages =
queue_max_sectors(q) >> (PAGE_SHIFT - 9);
}
EXPORT_SYMBOL_GPL(blk_queue_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);
q->backing_dev_info->ra_pages =
max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
}
EXPORT_SYMBOL(blk_queue_io_opt);
/**
* 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);
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>
2015-11-14 04:46:48 +07:00
t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
t->max_write_same_sectors = min(t->max_write_same_sectors,
b->max_write_same_sectors);
t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors,
b->max_write_zeroes_sectors);
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 15:55:47 +07:00
t->max_zone_append_sectors = min(t->max_zone_append_sectors,
b->max_zone_append_sectors);
t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
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->chunk_sectors = lcm_not_zero(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;
}
/* 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->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) {
char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE];
disk_name(disk, 0, top);
bdevname(bdev, bottom);
printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n",
top, bottom);
}
blk_queue_update_readahead(disk->queue);
}
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)
{
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 19:29:47 +07:00
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->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->dma_alignment)
q->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);
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>
2016-11-10 02:38:14 +07:00
wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
}
EXPORT_SYMBOL_GPL(blk_queue_write_cache);
block: Introduce elevator features Introduce the definition of elevator features through the elevator_features flags in the elevator_type structure. Each flag can represent a feature supported by an elevator. The first feature defined by this patch is support for zoned block device sequential write constraint with the flag ELEVATOR_F_ZBD_SEQ_WRITE, which is implemented by the mq-deadline elevator using zone write locking. Other possible features are IO priorities, write hints, latency targets or single-LUN dual-actuator disks (for which the elevator could maintain one LBA ordered list per actuator). The required_elevator_features field is also added to the request_queue structure to allow a device driver to specify elevator feature flags that an elevator must support for the correct operation of the device (e.g. device drivers for zoned block devices can have the ELEVATOR_F_ZBD_SEQ_WRITE flag as a required feature). The helper function blk_queue_required_elevator_features() is defined for setting this new field. With these two new fields in place, the elevator functions elevator_match() and elevator_find() are modified to allow a user to set only an elevator with a set of features that satisfies the device required features. Elevators not matching the device requirements are not shown in the device sysfs queue/scheduler file to prevent their use. The "none" elevator can always be selected as before. Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-09-05 16:51:31 +07:00
/**
* 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);
/**
* blk_queue_set_zoned - configure a disk queue zoned model.
* @disk: the gendisk of the queue to configure
* @model: the zoned model to set
*
* Set the zoned model of the request queue of @disk according 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 blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
{
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;
}
disk->queue->limits.zoned = model;
}
EXPORT_SYMBOL_GPL(blk_queue_set_zoned);
static int __init blk_settings_init(void)
{
blk_max_low_pfn = max_low_pfn - 1;
blk_max_pfn = max_pfn - 1;
return 0;
}
subsys_initcall(blk_settings_init);