linux/drivers/md/dm-io.c

561 lines
14 KiB
C
Raw Normal View History

/*
* Copyright (C) 2003 Sistina Software
* Copyright (C) 2006 Red Hat GmbH
*
* This file is released under the GPL.
*/
#include "dm-core.h"
#include <linux/device-mapper.h>
#include <linux/bio.h>
#include <linux/completion.h>
#include <linux/mempool.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/dm-io.h>
#define DM_MSG_PREFIX "io"
#define DM_IO_MAX_REGIONS BITS_PER_LONG
struct dm_io_client {
mempool_t *pool;
struct bio_set *bios;
};
/*
* Aligning 'struct io' reduces the number of bits required to store
* its address. Refer to store_io_and_region_in_bio() below.
*/
struct io {
unsigned long error_bits;
atomic_t count;
struct dm_io_client *client;
io_notify_fn callback;
void *context;
void *vma_invalidate_address;
unsigned long vma_invalidate_size;
} __attribute__((aligned(DM_IO_MAX_REGIONS)));
static struct kmem_cache *_dm_io_cache;
/*
* Create a client with mempool and bioset.
*/
struct dm_io_client *dm_io_client_create(void)
{
struct dm_io_client *client;
unsigned min_ios = dm_get_reserved_bio_based_ios();
client = kmalloc(sizeof(*client), GFP_KERNEL);
if (!client)
return ERR_PTR(-ENOMEM);
client->pool = mempool_create_slab_pool(min_ios, _dm_io_cache);
if (!client->pool)
goto bad;
client->bios = bioset_create(min_ios, 0);
if (!client->bios)
goto bad;
return client;
bad:
mempool_destroy(client->pool);
kfree(client);
return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL(dm_io_client_create);
void dm_io_client_destroy(struct dm_io_client *client)
{
mempool_destroy(client->pool);
bioset_free(client->bios);
kfree(client);
}
EXPORT_SYMBOL(dm_io_client_destroy);
/*-----------------------------------------------------------------
* We need to keep track of which region a bio is doing io for.
* To avoid a memory allocation to store just 5 or 6 bits, we
* ensure the 'struct io' pointer is aligned so enough low bits are
* always zero and then combine it with the region number directly in
* bi_private.
*---------------------------------------------------------------*/
static void store_io_and_region_in_bio(struct bio *bio, struct io *io,
unsigned region)
{
if (unlikely(!IS_ALIGNED((unsigned long)io, DM_IO_MAX_REGIONS))) {
DMCRIT("Unaligned struct io pointer %p", io);
BUG();
}
bio->bi_private = (void *)((unsigned long)io | region);
}
static void retrieve_io_and_region_from_bio(struct bio *bio, struct io **io,
unsigned *region)
{
unsigned long val = (unsigned long)bio->bi_private;
*io = (void *)(val & -(unsigned long)DM_IO_MAX_REGIONS);
*region = val & (DM_IO_MAX_REGIONS - 1);
}
/*-----------------------------------------------------------------
* We need an io object to keep track of the number of bios that
* have been dispatched for a particular io.
*---------------------------------------------------------------*/
static void complete_io(struct io *io)
{
unsigned long error_bits = io->error_bits;
io_notify_fn fn = io->callback;
void *context = io->context;
if (io->vma_invalidate_size)
invalidate_kernel_vmap_range(io->vma_invalidate_address,
io->vma_invalidate_size);
mempool_free(io, io->client->pool);
fn(error_bits, context);
}
static void dec_count(struct io *io, unsigned int region, int error)
{
if (error)
set_bit(region, &io->error_bits);
if (atomic_dec_and_test(&io->count))
complete_io(io);
}
static void endio(struct bio *bio)
{
struct io *io;
unsigned region;
block: don't access bio->bi_error after bio_put() Commit 4246a0b6 ("block: add a bi_error field to struct bio") has added a few dereferences of 'bio' after a call to bio_put(). This causes use-after-frees such as: [521120.719695] BUG: KASan: use after free in dio_bio_complete+0x2b3/0x320 at addr ffff880f36b38714 [521120.720638] Read of size 4 by task mount.ocfs2/9644 [521120.721212] ============================================================================= [521120.722056] BUG kmalloc-256 (Not tainted): kasan: bad access detected [521120.722968] ----------------------------------------------------------------------------- [521120.722968] [521120.723915] Disabling lock debugging due to kernel taint [521120.724539] INFO: Slab 0xffffea003cdace00 objects=32 used=25 fp=0xffff880f36b38600 flags=0x46fffff80004080 [521120.726037] INFO: Object 0xffff880f36b38700 @offset=1792 fp=0xffff880f36b38800 [521120.726037] [521120.726974] Bytes b4 ffff880f36b386f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.727898] Object ffff880f36b38700: 00 88 b3 36 0f 88 ff ff 00 00 d8 de 0b 88 ff ff ...6............ [521120.728822] Object ffff880f36b38710: 02 00 00 f0 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.729705] Object ffff880f36b38720: 01 00 00 00 00 00 00 00 00 00 00 00 01 00 00 00 ................ [521120.730623] Object ffff880f36b38730: 00 00 00 00 00 00 00 00 01 00 00 00 00 02 00 00 ................ [521120.731621] Object ffff880f36b38740: 00 02 00 00 01 00 00 00 d0 f7 87 ad ff ff ff ff ................ [521120.732776] Object ffff880f36b38750: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.733640] Object ffff880f36b38760: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.734508] Object ffff880f36b38770: 01 00 03 00 01 00 00 00 88 87 b3 36 0f 88 ff ff ...........6.... [521120.735385] Object ffff880f36b38780: 00 73 22 ad 02 88 ff ff 40 13 e0 3c 00 ea ff ff .s".....@..<.... [521120.736667] Object ffff880f36b38790: 00 02 00 00 00 04 00 00 00 00 00 00 00 00 00 00 ................ [521120.737596] Object ffff880f36b387a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.738524] Object ffff880f36b387b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.739388] Object ffff880f36b387c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.740277] Object ffff880f36b387d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.741187] Object ffff880f36b387e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.742233] Object ffff880f36b387f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.743229] CPU: 41 PID: 9644 Comm: mount.ocfs2 Tainted: G B 4.2.0-rc6-next-20150810-sasha-00039-gf909086 #2420 [521120.744274] ffff880f36b38000 ffff880d89c8f638 ffffffffb6e9ba8a ffff880101c0e5c0 [521120.745025] ffff880d89c8f668 ffffffffad76a313 ffff880101c0e5c0 ffffea003cdace00 [521120.745908] ffff880f36b38700 ffff880f36b38798 ffff880d89c8f690 ffffffffad772854 [521120.747063] Call Trace: [521120.747520] dump_stack (lib/dump_stack.c:52) [521120.748053] print_trailer (mm/slub.c:653) [521120.748582] object_err (mm/slub.c:660) [521120.749079] kasan_report_error (include/linux/kasan.h:20 mm/kasan/report.c:152 mm/kasan/report.c:194) [521120.750834] __asan_report_load4_noabort (mm/kasan/report.c:250) [521120.753580] dio_bio_complete (fs/direct-io.c:478) [521120.755752] do_blockdev_direct_IO (fs/direct-io.c:494 fs/direct-io.c:1291) [521120.759765] __blockdev_direct_IO (fs/direct-io.c:1322) [521120.761658] blkdev_direct_IO (fs/block_dev.c:162) [521120.762993] generic_file_read_iter (mm/filemap.c:1738) [521120.767405] blkdev_read_iter (fs/block_dev.c:1649) [521120.768556] __vfs_read (fs/read_write.c:423 fs/read_write.c:434) [521120.772126] vfs_read (fs/read_write.c:454) [521120.773118] SyS_pread64 (fs/read_write.c:607 fs/read_write.c:594) [521120.776062] entry_SYSCALL_64_fastpath (arch/x86/entry/entry_64.S:186) [521120.777375] Memory state around the buggy address: [521120.778118] ffff880f36b38600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.779211] ffff880f36b38680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.780315] >ffff880f36b38700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.781465] ^ [521120.782083] ffff880f36b38780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.783717] ffff880f36b38800: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [521120.784818] ================================================================== This patch fixes a few of those places that I caught while auditing the patch, but the original patch should be audited further for more occurences of this issue since I'm not too familiar with the code. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-08-11 01:05:18 +02:00
int error;
if (bio->bi_error && bio_data_dir(bio) == READ)
zero_fill_bio(bio);
/*
* The bio destructor in bio_put() may use the io object.
*/
retrieve_io_and_region_from_bio(bio, &io, &region);
block: don't access bio->bi_error after bio_put() Commit 4246a0b6 ("block: add a bi_error field to struct bio") has added a few dereferences of 'bio' after a call to bio_put(). This causes use-after-frees such as: [521120.719695] BUG: KASan: use after free in dio_bio_complete+0x2b3/0x320 at addr ffff880f36b38714 [521120.720638] Read of size 4 by task mount.ocfs2/9644 [521120.721212] ============================================================================= [521120.722056] BUG kmalloc-256 (Not tainted): kasan: bad access detected [521120.722968] ----------------------------------------------------------------------------- [521120.722968] [521120.723915] Disabling lock debugging due to kernel taint [521120.724539] INFO: Slab 0xffffea003cdace00 objects=32 used=25 fp=0xffff880f36b38600 flags=0x46fffff80004080 [521120.726037] INFO: Object 0xffff880f36b38700 @offset=1792 fp=0xffff880f36b38800 [521120.726037] [521120.726974] Bytes b4 ffff880f36b386f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.727898] Object ffff880f36b38700: 00 88 b3 36 0f 88 ff ff 00 00 d8 de 0b 88 ff ff ...6............ [521120.728822] Object ffff880f36b38710: 02 00 00 f0 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.729705] Object ffff880f36b38720: 01 00 00 00 00 00 00 00 00 00 00 00 01 00 00 00 ................ [521120.730623] Object ffff880f36b38730: 00 00 00 00 00 00 00 00 01 00 00 00 00 02 00 00 ................ [521120.731621] Object ffff880f36b38740: 00 02 00 00 01 00 00 00 d0 f7 87 ad ff ff ff ff ................ [521120.732776] Object ffff880f36b38750: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.733640] Object ffff880f36b38760: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.734508] Object ffff880f36b38770: 01 00 03 00 01 00 00 00 88 87 b3 36 0f 88 ff ff ...........6.... [521120.735385] Object ffff880f36b38780: 00 73 22 ad 02 88 ff ff 40 13 e0 3c 00 ea ff ff .s".....@..<.... [521120.736667] Object ffff880f36b38790: 00 02 00 00 00 04 00 00 00 00 00 00 00 00 00 00 ................ [521120.737596] Object ffff880f36b387a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.738524] Object ffff880f36b387b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.739388] Object ffff880f36b387c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.740277] Object ffff880f36b387d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.741187] Object ffff880f36b387e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.742233] Object ffff880f36b387f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.743229] CPU: 41 PID: 9644 Comm: mount.ocfs2 Tainted: G B 4.2.0-rc6-next-20150810-sasha-00039-gf909086 #2420 [521120.744274] ffff880f36b38000 ffff880d89c8f638 ffffffffb6e9ba8a ffff880101c0e5c0 [521120.745025] ffff880d89c8f668 ffffffffad76a313 ffff880101c0e5c0 ffffea003cdace00 [521120.745908] ffff880f36b38700 ffff880f36b38798 ffff880d89c8f690 ffffffffad772854 [521120.747063] Call Trace: [521120.747520] dump_stack (lib/dump_stack.c:52) [521120.748053] print_trailer (mm/slub.c:653) [521120.748582] object_err (mm/slub.c:660) [521120.749079] kasan_report_error (include/linux/kasan.h:20 mm/kasan/report.c:152 mm/kasan/report.c:194) [521120.750834] __asan_report_load4_noabort (mm/kasan/report.c:250) [521120.753580] dio_bio_complete (fs/direct-io.c:478) [521120.755752] do_blockdev_direct_IO (fs/direct-io.c:494 fs/direct-io.c:1291) [521120.759765] __blockdev_direct_IO (fs/direct-io.c:1322) [521120.761658] blkdev_direct_IO (fs/block_dev.c:162) [521120.762993] generic_file_read_iter (mm/filemap.c:1738) [521120.767405] blkdev_read_iter (fs/block_dev.c:1649) [521120.768556] __vfs_read (fs/read_write.c:423 fs/read_write.c:434) [521120.772126] vfs_read (fs/read_write.c:454) [521120.773118] SyS_pread64 (fs/read_write.c:607 fs/read_write.c:594) [521120.776062] entry_SYSCALL_64_fastpath (arch/x86/entry/entry_64.S:186) [521120.777375] Memory state around the buggy address: [521120.778118] ffff880f36b38600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.779211] ffff880f36b38680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.780315] >ffff880f36b38700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.781465] ^ [521120.782083] ffff880f36b38780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.783717] ffff880f36b38800: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [521120.784818] ================================================================== This patch fixes a few of those places that I caught while auditing the patch, but the original patch should be audited further for more occurences of this issue since I'm not too familiar with the code. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-08-11 01:05:18 +02:00
error = bio->bi_error;
bio_put(bio);
block: don't access bio->bi_error after bio_put() Commit 4246a0b6 ("block: add a bi_error field to struct bio") has added a few dereferences of 'bio' after a call to bio_put(). This causes use-after-frees such as: [521120.719695] BUG: KASan: use after free in dio_bio_complete+0x2b3/0x320 at addr ffff880f36b38714 [521120.720638] Read of size 4 by task mount.ocfs2/9644 [521120.721212] ============================================================================= [521120.722056] BUG kmalloc-256 (Not tainted): kasan: bad access detected [521120.722968] ----------------------------------------------------------------------------- [521120.722968] [521120.723915] Disabling lock debugging due to kernel taint [521120.724539] INFO: Slab 0xffffea003cdace00 objects=32 used=25 fp=0xffff880f36b38600 flags=0x46fffff80004080 [521120.726037] INFO: Object 0xffff880f36b38700 @offset=1792 fp=0xffff880f36b38800 [521120.726037] [521120.726974] Bytes b4 ffff880f36b386f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.727898] Object ffff880f36b38700: 00 88 b3 36 0f 88 ff ff 00 00 d8 de 0b 88 ff ff ...6............ [521120.728822] Object ffff880f36b38710: 02 00 00 f0 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.729705] Object ffff880f36b38720: 01 00 00 00 00 00 00 00 00 00 00 00 01 00 00 00 ................ [521120.730623] Object ffff880f36b38730: 00 00 00 00 00 00 00 00 01 00 00 00 00 02 00 00 ................ [521120.731621] Object ffff880f36b38740: 00 02 00 00 01 00 00 00 d0 f7 87 ad ff ff ff ff ................ [521120.732776] Object ffff880f36b38750: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.733640] Object ffff880f36b38760: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.734508] Object ffff880f36b38770: 01 00 03 00 01 00 00 00 88 87 b3 36 0f 88 ff ff ...........6.... [521120.735385] Object ffff880f36b38780: 00 73 22 ad 02 88 ff ff 40 13 e0 3c 00 ea ff ff .s".....@..<.... [521120.736667] Object ffff880f36b38790: 00 02 00 00 00 04 00 00 00 00 00 00 00 00 00 00 ................ [521120.737596] Object ffff880f36b387a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.738524] Object ffff880f36b387b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.739388] Object ffff880f36b387c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.740277] Object ffff880f36b387d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.741187] Object ffff880f36b387e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.742233] Object ffff880f36b387f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [521120.743229] CPU: 41 PID: 9644 Comm: mount.ocfs2 Tainted: G B 4.2.0-rc6-next-20150810-sasha-00039-gf909086 #2420 [521120.744274] ffff880f36b38000 ffff880d89c8f638 ffffffffb6e9ba8a ffff880101c0e5c0 [521120.745025] ffff880d89c8f668 ffffffffad76a313 ffff880101c0e5c0 ffffea003cdace00 [521120.745908] ffff880f36b38700 ffff880f36b38798 ffff880d89c8f690 ffffffffad772854 [521120.747063] Call Trace: [521120.747520] dump_stack (lib/dump_stack.c:52) [521120.748053] print_trailer (mm/slub.c:653) [521120.748582] object_err (mm/slub.c:660) [521120.749079] kasan_report_error (include/linux/kasan.h:20 mm/kasan/report.c:152 mm/kasan/report.c:194) [521120.750834] __asan_report_load4_noabort (mm/kasan/report.c:250) [521120.753580] dio_bio_complete (fs/direct-io.c:478) [521120.755752] do_blockdev_direct_IO (fs/direct-io.c:494 fs/direct-io.c:1291) [521120.759765] __blockdev_direct_IO (fs/direct-io.c:1322) [521120.761658] blkdev_direct_IO (fs/block_dev.c:162) [521120.762993] generic_file_read_iter (mm/filemap.c:1738) [521120.767405] blkdev_read_iter (fs/block_dev.c:1649) [521120.768556] __vfs_read (fs/read_write.c:423 fs/read_write.c:434) [521120.772126] vfs_read (fs/read_write.c:454) [521120.773118] SyS_pread64 (fs/read_write.c:607 fs/read_write.c:594) [521120.776062] entry_SYSCALL_64_fastpath (arch/x86/entry/entry_64.S:186) [521120.777375] Memory state around the buggy address: [521120.778118] ffff880f36b38600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.779211] ffff880f36b38680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.780315] >ffff880f36b38700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.781465] ^ [521120.782083] ffff880f36b38780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [521120.783717] ffff880f36b38800: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [521120.784818] ================================================================== This patch fixes a few of those places that I caught while auditing the patch, but the original patch should be audited further for more occurences of this issue since I'm not too familiar with the code. Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-08-11 01:05:18 +02:00
dec_count(io, region, error);
}
/*-----------------------------------------------------------------
* These little objects provide an abstraction for getting a new
* destination page for io.
*---------------------------------------------------------------*/
struct dpages {
void (*get_page)(struct dpages *dp,
struct page **p, unsigned long *len, unsigned *offset);
void (*next_page)(struct dpages *dp);
union {
unsigned context_u;
struct bvec_iter context_bi;
};
void *context_ptr;
void *vma_invalidate_address;
unsigned long vma_invalidate_size;
};
/*
* Functions for getting the pages from a list.
*/
static void list_get_page(struct dpages *dp,
struct page **p, unsigned long *len, unsigned *offset)
{
unsigned o = dp->context_u;
struct page_list *pl = (struct page_list *) dp->context_ptr;
*p = pl->page;
*len = PAGE_SIZE - o;
*offset = o;
}
static void list_next_page(struct dpages *dp)
{
struct page_list *pl = (struct page_list *) dp->context_ptr;
dp->context_ptr = pl->next;
dp->context_u = 0;
}
static void list_dp_init(struct dpages *dp, struct page_list *pl, unsigned offset)
{
dp->get_page = list_get_page;
dp->next_page = list_next_page;
dp->context_u = offset;
dp->context_ptr = pl;
}
/*
* Functions for getting the pages from a bvec.
*/
dm io: fix I/O to multiple destinations Commit 003b5c5719f159f4f4bf97511c4702a0638313dd ("block: Convert drivers to immutable biovecs") broke dm-mirror due to dm-io breakage. dm-io had three possible iterators (DM_IO_PAGE_LIST, DM_IO_BVEC, DM_IO_VMA) that iterate over pages where the I/O should be performed. The switch to immutable biovecs changed the DM_IO_BVEC iterator to DM_IO_BIO. Before this change the iterator stored the pointer to a bio vector in the dpages structure. The iterator incremented the pointer in the dpages structure as it advanced over the pages. After the immutable biovecs change, the DM_IO_BIO iterator stores a pointer to the bio in the dpages structure and uses bio_advance to change the bio as it advances. The problem is that the function dispatch_io stores the content of the dpages structure into the variable old_pages and restores it before issuing I/O to each of the devices. Before the change, the statement "*dp = old_pages;" restored the iterator to its starting position. After the change, struct dpages holds a pointer to the bio, thus the statement "*dp = old_pages;" doesn't restore the iterator. Consequently, in the context of dm-mirror: only the first mirror leg is written correctly, the kernel locks up when trying to write the other mirror legs because the number of sectors to write in the where->count variable doesn't match the number of sectors returned by the iterator. This patch fixes the bug by partially reverting the original patch - it changes the code so that struct dpages holds a pointer to the bio vector, so that the statement "*dp = old_pages;" restores the iterator correctly. The field "context_u" holds the offset from the beginning of the current bio vector entry, just like the "bio->bi_iter.bi_bvec_done" field. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2014-02-12 22:37:30 +01:00
static void bio_get_page(struct dpages *dp, struct page **p,
unsigned long *len, unsigned *offset)
{
struct bio_vec bvec = bvec_iter_bvec((struct bio_vec *)dp->context_ptr,
dp->context_bi);
*p = bvec.bv_page;
*len = bvec.bv_len;
*offset = bvec.bv_offset;
/* avoid figuring it out again in bio_next_page() */
dp->context_bi.bi_sector = (sector_t)bvec.bv_len;
}
static void bio_next_page(struct dpages *dp)
{
unsigned int len = (unsigned int)dp->context_bi.bi_sector;
bvec_iter_advance((struct bio_vec *)dp->context_ptr,
&dp->context_bi, len);
}
static void bio_dp_init(struct dpages *dp, struct bio *bio)
{
dp->get_page = bio_get_page;
dp->next_page = bio_next_page;
/*
* We just use bvec iterator to retrieve pages, so it is ok to
* access the bvec table directly here
*/
dp->context_ptr = bio->bi_io_vec;
dp->context_bi = bio->bi_iter;
}
/*
* Functions for getting the pages from a VMA.
*/
static void vm_get_page(struct dpages *dp,
struct page **p, unsigned long *len, unsigned *offset)
{
*p = vmalloc_to_page(dp->context_ptr);
*offset = dp->context_u;
*len = PAGE_SIZE - dp->context_u;
}
static void vm_next_page(struct dpages *dp)
{
dp->context_ptr += PAGE_SIZE - dp->context_u;
dp->context_u = 0;
}
static void vm_dp_init(struct dpages *dp, void *data)
{
dp->get_page = vm_get_page;
dp->next_page = vm_next_page;
dp->context_u = offset_in_page(data);
dp->context_ptr = data;
}
/*
* Functions for getting the pages from kernel memory.
*/
static void km_get_page(struct dpages *dp, struct page **p, unsigned long *len,
unsigned *offset)
{
*p = virt_to_page(dp->context_ptr);
*offset = dp->context_u;
*len = PAGE_SIZE - dp->context_u;
}
static void km_next_page(struct dpages *dp)
{
dp->context_ptr += PAGE_SIZE - dp->context_u;
dp->context_u = 0;
}
static void km_dp_init(struct dpages *dp, void *data)
{
dp->get_page = km_get_page;
dp->next_page = km_next_page;
dp->context_u = offset_in_page(data);
dp->context_ptr = data;
}
/*-----------------------------------------------------------------
* IO routines that accept a list of pages.
*---------------------------------------------------------------*/
static void do_region(int op, int op_flags, unsigned region,
struct dm_io_region *where, struct dpages *dp,
struct io *io)
{
struct bio *bio;
struct page *page;
unsigned long len;
unsigned offset;
unsigned num_bvecs;
sector_t remaining = where->count;
struct request_queue *q = bdev_get_queue(where->bdev);
unsigned short logical_block_size = queue_logical_block_size(q);
sector_t num_sectors;
unsigned int uninitialized_var(special_cmd_max_sectors);
/*
* Reject unsupported discard and write same requests.
*/
if (op == REQ_OP_DISCARD)
special_cmd_max_sectors = q->limits.max_discard_sectors;
else if (op == REQ_OP_WRITE_SAME)
special_cmd_max_sectors = q->limits.max_write_same_sectors;
if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_SAME) &&
special_cmd_max_sectors == 0) {
dec_count(io, region, -EOPNOTSUPP);
return;
}
/*
* where->count may be zero if op holds a flush and we need to
dm: implement REQ_FLUSH/FUA support for bio-based dm This patch converts bio-based dm to support REQ_FLUSH/FUA instead of now deprecated REQ_HARDBARRIER. * -EOPNOTSUPP handling logic dropped. * Preflush is handled as before but postflush is dropped and replaced with passing down REQ_FUA to member request_queues. This replaces one array wide cache flush w/ member specific FUA writes. * __split_and_process_bio() now calls __clone_and_map_flush() directly for flushes and guarantees all FLUSH bio's going to targets are zero ` length. * It's now guaranteed that all FLUSH bio's which are passed onto dm targets are zero length. bio_empty_barrier() tests are replaced with REQ_FLUSH tests. * Empty WRITE_BARRIERs are replaced with WRITE_FLUSHes. * Dropped unlikely() around REQ_FLUSH tests. Flushes are not unlikely enough to be marked with unlikely(). * Block layer now filters out REQ_FLUSH/FUA bio's if the request_queue doesn't support cache flushing. Advertise REQ_FLUSH | REQ_FUA capability. * Request based dm isn't converted yet. dm_init_request_based_queue() resets flush support to 0 for now. To avoid disturbing request based dm code, dm->flush_error is added for bio based dm while requested based dm continues to use dm->barrier_error. Lightly tested linear, stripe, raid1, snap and crypt targets. Please proceed with caution as I'm not familiar with the code base. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: dm-devel@redhat.com Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-09-03 11:56:19 +02:00
* send a zero-sized flush.
*/
do {
/*
* Allocate a suitably sized-bio.
*/
if ((op == REQ_OP_DISCARD) || (op == REQ_OP_WRITE_SAME))
num_bvecs = 1;
else
num_bvecs = min_t(int, BIO_MAX_PAGES,
dm_sector_div_up(remaining, (PAGE_SIZE >> SECTOR_SHIFT)));
bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, io->client->bios);
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-12 00:44:27 +02:00
bio->bi_iter.bi_sector = where->sector + (where->count - remaining);
bio->bi_bdev = where->bdev;
bio->bi_end_io = endio;
bio_set_op_attrs(bio, op, op_flags);
store_io_and_region_in_bio(bio, io, region);
if (op == REQ_OP_DISCARD) {
num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining);
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-12 00:44:27 +02:00
bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT;
remaining -= num_sectors;
} else if (op == REQ_OP_WRITE_SAME) {
/*
* WRITE SAME only uses a single page.
*/
dp->get_page(dp, &page, &len, &offset);
bio_add_page(bio, page, logical_block_size, offset);
num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining);
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-12 00:44:27 +02:00
bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT;
offset = 0;
remaining -= num_sectors;
dp->next_page(dp);
} else while (remaining) {
/*
* Try and add as many pages as possible.
*/
dp->get_page(dp, &page, &len, &offset);
len = min(len, to_bytes(remaining));
if (!bio_add_page(bio, page, len, offset))
break;
offset = 0;
remaining -= to_sector(len);
dp->next_page(dp);
}
atomic_inc(&io->count);
submit_bio(bio);
} while (remaining);
}
static void dispatch_io(int op, int op_flags, unsigned int num_regions,
struct dm_io_region *where, struct dpages *dp,
struct io *io, int sync)
{
int i;
struct dpages old_pages = *dp;
BUG_ON(num_regions > DM_IO_MAX_REGIONS);
if (sync)
op_flags |= REQ_SYNC;
/*
* For multiple regions we need to be careful to rewind
* the dp object for each call to do_region.
*/
for (i = 0; i < num_regions; i++) {
*dp = old_pages;
if (where[i].count || (op_flags & REQ_PREFLUSH))
do_region(op, op_flags, i, where + i, dp, io);
}
/*
* Drop the extra reference that we were holding to avoid
* the io being completed too early.
*/
dec_count(io, 0, 0);
}
struct sync_io {
unsigned long error_bits;
struct completion wait;
};
static void sync_io_complete(unsigned long error, void *context)
{
struct sync_io *sio = context;
sio->error_bits = error;
complete(&sio->wait);
}
static int sync_io(struct dm_io_client *client, unsigned int num_regions,
struct dm_io_region *where, int op, int op_flags,
struct dpages *dp, unsigned long *error_bits)
{
struct io *io;
struct sync_io sio;
if (num_regions > 1 && !op_is_write(op)) {
WARN_ON(1);
return -EIO;
}
init_completion(&sio.wait);
io = mempool_alloc(client->pool, GFP_NOIO);
io->error_bits = 0;
atomic_set(&io->count, 1); /* see dispatch_io() */
io->client = client;
io->callback = sync_io_complete;
io->context = &sio;
io->vma_invalidate_address = dp->vma_invalidate_address;
io->vma_invalidate_size = dp->vma_invalidate_size;
dispatch_io(op, op_flags, num_regions, where, dp, io, 1);
wait_for_completion_io(&sio.wait);
if (error_bits)
*error_bits = sio.error_bits;
return sio.error_bits ? -EIO : 0;
}
static int async_io(struct dm_io_client *client, unsigned int num_regions,
struct dm_io_region *where, int op, int op_flags,
struct dpages *dp, io_notify_fn fn, void *context)
{
struct io *io;
if (num_regions > 1 && !op_is_write(op)) {
WARN_ON(1);
fn(1, context);
return -EIO;
}
io = mempool_alloc(client->pool, GFP_NOIO);
io->error_bits = 0;
atomic_set(&io->count, 1); /* see dispatch_io() */
io->client = client;
io->callback = fn;
io->context = context;
io->vma_invalidate_address = dp->vma_invalidate_address;
io->vma_invalidate_size = dp->vma_invalidate_size;
dispatch_io(op, op_flags, num_regions, where, dp, io, 0);
return 0;
}
static int dp_init(struct dm_io_request *io_req, struct dpages *dp,
unsigned long size)
{
/* Set up dpages based on memory type */
dp->vma_invalidate_address = NULL;
dp->vma_invalidate_size = 0;
switch (io_req->mem.type) {
case DM_IO_PAGE_LIST:
list_dp_init(dp, io_req->mem.ptr.pl, io_req->mem.offset);
break;
case DM_IO_BIO:
bio_dp_init(dp, io_req->mem.ptr.bio);
break;
case DM_IO_VMA:
flush_kernel_vmap_range(io_req->mem.ptr.vma, size);
if (io_req->bi_op == REQ_OP_READ) {
dp->vma_invalidate_address = io_req->mem.ptr.vma;
dp->vma_invalidate_size = size;
}
vm_dp_init(dp, io_req->mem.ptr.vma);
break;
case DM_IO_KMEM:
km_dp_init(dp, io_req->mem.ptr.addr);
break;
default:
return -EINVAL;
}
return 0;
}
/*
dm: unplug queues in threads Remove an avoidable 3ms delay on some dm-raid1 and kcopyd I/O. It is specified that any submitted bio without BIO_RW_SYNC flag may plug the queue (i.e. block the requests from being dispatched to the physical device). The queue is unplugged when the caller calls blk_unplug() function. Usually, the sequence is that someone calls submit_bh to submit IO on a buffer. The IO plugs the queue and waits (to be possibly joined with other adjacent bios). Then, when the caller calls wait_on_buffer(), it unplugs the queue and submits the IOs to the disk. This was happenning: When doing O_SYNC writes, function fsync_buffers_list() submits a list of bios to dm_raid1, the bios are added to dm_raid1 write queue and kmirrord is woken up. fsync_buffers_list() calls wait_on_buffer(). That unplugs the queue, but there are no bios on the device queue as they are still in the dm_raid1 queue. wait_on_buffer() starts waiting until the IO is finished. kmirrord is scheduled, kmirrord takes bios and submits them to the devices. The submitted bio plugs the harddisk queue but there is no one to unplug it. (The process that called wait_on_buffer() is already sleeping.) So there is a 3ms timeout, after which the queues on the harddisks are unplugged and requests are processed. This 3ms timeout meant that in certain workloads (e.g. O_SYNC, 8kb writes), dm-raid1 is 10 times slower than md raid1. Every time we submit something asynchronously via dm_io, we must unplug the queue actually to send the request to the device. This patch adds an unplug call to kmirrord - while processing requests, it keeps the queue plugged (so that adjacent bios can be merged); when it finishes processing all the bios, it unplugs the queue to submit the bios. It also fixes kcopyd which has the same potential problem. All kcopyd requests are submitted with BIO_RW_SYNC. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com> Acked-by: Jens Axboe <jens.axboe@oracle.com>
2008-04-24 23:10:47 +02:00
* New collapsed (a)synchronous interface.
*
* If the IO is asynchronous (i.e. it has notify.fn), you must either unplug
* the queue with blk_unplug() some time later or set REQ_SYNC in
* io_req->bi_opf. If you fail to do one of these, the IO will be submitted to
* the disk after q->unplug_delay, which defaults to 3ms in blk-settings.c.
*/
int dm_io(struct dm_io_request *io_req, unsigned num_regions,
struct dm_io_region *where, unsigned long *sync_error_bits)
{
int r;
struct dpages dp;
r = dp_init(io_req, &dp, (unsigned long)where->count << SECTOR_SHIFT);
if (r)
return r;
if (!io_req->notify.fn)
return sync_io(io_req->client, num_regions, where,
io_req->bi_op, io_req->bi_op_flags, &dp,
sync_error_bits);
return async_io(io_req->client, num_regions, where, io_req->bi_op,
io_req->bi_op_flags, &dp, io_req->notify.fn,
io_req->notify.context);
}
EXPORT_SYMBOL(dm_io);
int __init dm_io_init(void)
{
_dm_io_cache = KMEM_CACHE(io, 0);
if (!_dm_io_cache)
return -ENOMEM;
return 0;
}
void dm_io_exit(void)
{
kmem_cache_destroy(_dm_io_cache);
_dm_io_cache = NULL;
}