OpenCloudOS-Kernel/block/blk-lib.c

194 lines
4.5 KiB
C
Raw Normal View History

/*
* Functions related to generic helpers functions
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/scatterlist.h>
#include "blk.h"
struct bio_batch {
atomic_t done;
unsigned long flags;
struct completion *wait;
};
static void bio_batch_end_io(struct bio *bio, int err)
{
struct bio_batch *bb = bio->bi_private;
if (err && (err != -EOPNOTSUPP))
clear_bit(BIO_UPTODATE, &bb->flags);
if (atomic_dec_and_test(&bb->done))
complete(bb->wait);
bio_put(bio);
}
/**
* blkdev_issue_discard - queue a discard
* @bdev: blockdev to issue discard for
* @sector: start sector
* @nr_sects: number of sectors to discard
* @gfp_mask: memory allocation flags (for bio_alloc)
* @flags: BLKDEV_IFL_* flags to control behaviour
*
* Description:
* Issue a discard request for the sectors in question.
*/
int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
{
DECLARE_COMPLETION_ONSTACK(wait);
struct request_queue *q = bdev_get_queue(bdev);
int type = REQ_WRITE | REQ_DISCARD;
unsigned int max_discard_sectors;
unsigned int granularity, alignment, mask;
struct bio_batch bb;
struct bio *bio;
int ret = 0;
if (!q)
return -ENXIO;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
/* Zero-sector (unknown) and one-sector granularities are the same. */
granularity = max(q->limits.discard_granularity >> 9, 1U);
mask = granularity - 1;
alignment = (bdev_discard_alignment(bdev) >> 9) & mask;
/*
* Ensure that max_discard_sectors is of the proper
* granularity, so that requests stay aligned after a split.
*/
max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
max_discard_sectors = round_down(max_discard_sectors, granularity);
if (unlikely(!max_discard_sectors)) {
/* Avoid infinite loop below. Being cautious never hurts. */
return -EOPNOTSUPP;
}
if (flags & BLKDEV_DISCARD_SECURE) {
if (!blk_queue_secdiscard(q))
return -EOPNOTSUPP;
type |= REQ_SECURE;
}
atomic_set(&bb.done, 1);
bb.flags = 1 << BIO_UPTODATE;
bb.wait = &wait;
while (nr_sects) {
unsigned int req_sects;
sector_t end_sect;
bio = bio_alloc(gfp_mask, 1);
if (!bio) {
ret = -ENOMEM;
break;
}
req_sects = min_t(sector_t, nr_sects, max_discard_sectors);
/*
* If splitting a request, and the next starting sector would be
* misaligned, stop the discard at the previous aligned sector.
*/
end_sect = sector + req_sects;
if (req_sects < nr_sects && (end_sect & mask) != alignment) {
end_sect =
round_down(end_sect - alignment, granularity)
+ alignment;
req_sects = end_sect - sector;
}
bio->bi_sector = sector;
bio->bi_end_io = bio_batch_end_io;
bio->bi_bdev = bdev;
bio->bi_private = &bb;
bio->bi_size = req_sects << 9;
nr_sects -= req_sects;
sector = end_sect;
atomic_inc(&bb.done);
submit_bio(type, bio);
}
/* Wait for bios in-flight */
if (!atomic_dec_and_test(&bb.done))
wait_for_completion(&wait);
if (!test_bit(BIO_UPTODATE, &bb.flags))
ret = -EIO;
return ret;
}
EXPORT_SYMBOL(blkdev_issue_discard);
/**
* blkdev_issue_zeroout - generate number of zero filed write bios
* @bdev: blockdev to issue
* @sector: start sector
* @nr_sects: number of sectors to write
* @gfp_mask: memory allocation flags (for bio_alloc)
*
* Description:
* Generate and issue number of bios with zerofiled pages.
*/
int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask)
{
int ret;
struct bio *bio;
struct bio_batch bb;
block: fix mis-synchronisation in blkdev_issue_zeroout() BZ29402 https://bugzilla.kernel.org/show_bug.cgi?id=29402 We can hit serious mis-synchronization in bio completion path of blkdev_issue_zeroout() leading to a panic. The problem is that when we are going to wait_for_completion() in blkdev_issue_zeroout() we check if the bb.done equals issued (number of submitted bios). If it does, we can skip the wait_for_completition() and just out of the function since there is nothing to wait for. However, there is a ordering problem because bio_batch_end_io() is calling atomic_inc(&bb->done) before complete(), hence it might seem to blkdev_issue_zeroout() that all bios has been completed and exit. At this point when bio_batch_end_io() is going to call complete(bb->wait), bb and wait does not longer exist since it was allocated on stack in blkdev_issue_zeroout() ==> panic! (thread 1) (thread 2) bio_batch_end_io() blkdev_issue_zeroout() if(bb) { ... if (bb->end_io) ... bb->end_io(bio, err); ... atomic_inc(&bb->done); ... ... while (issued != atomic_read(&bb.done)) ... (let issued == bb.done) ... (do the rest of the function) ... return ret; complete(bb->wait); ^^^^^^^^ panic We can fix this easily by simplifying bio_batch and completion counting. Also remove bio_end_io_t *end_io since it is not used. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Reported-by: Eric Whitney <eric.whitney@hp.com> Tested-by: Eric Whitney <eric.whitney@hp.com> Reviewed-by: Jeff Moyer <jmoyer@redhat.com> CC: Dmitry Monakhov <dmonakhov@openvz.org> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-11 17:23:53 +08:00
unsigned int sz;
DECLARE_COMPLETION_ONSTACK(wait);
block: fix mis-synchronisation in blkdev_issue_zeroout() BZ29402 https://bugzilla.kernel.org/show_bug.cgi?id=29402 We can hit serious mis-synchronization in bio completion path of blkdev_issue_zeroout() leading to a panic. The problem is that when we are going to wait_for_completion() in blkdev_issue_zeroout() we check if the bb.done equals issued (number of submitted bios). If it does, we can skip the wait_for_completition() and just out of the function since there is nothing to wait for. However, there is a ordering problem because bio_batch_end_io() is calling atomic_inc(&bb->done) before complete(), hence it might seem to blkdev_issue_zeroout() that all bios has been completed and exit. At this point when bio_batch_end_io() is going to call complete(bb->wait), bb and wait does not longer exist since it was allocated on stack in blkdev_issue_zeroout() ==> panic! (thread 1) (thread 2) bio_batch_end_io() blkdev_issue_zeroout() if(bb) { ... if (bb->end_io) ... bb->end_io(bio, err); ... atomic_inc(&bb->done); ... ... while (issued != atomic_read(&bb.done)) ... (let issued == bb.done) ... (do the rest of the function) ... return ret; complete(bb->wait); ^^^^^^^^ panic We can fix this easily by simplifying bio_batch and completion counting. Also remove bio_end_io_t *end_io since it is not used. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Reported-by: Eric Whitney <eric.whitney@hp.com> Tested-by: Eric Whitney <eric.whitney@hp.com> Reviewed-by: Jeff Moyer <jmoyer@redhat.com> CC: Dmitry Monakhov <dmonakhov@openvz.org> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-11 17:23:53 +08:00
atomic_set(&bb.done, 1);
bb.flags = 1 << BIO_UPTODATE;
bb.wait = &wait;
ret = 0;
while (nr_sects != 0) {
bio = bio_alloc(gfp_mask,
min(nr_sects, (sector_t)BIO_MAX_PAGES));
if (!bio) {
ret = -ENOMEM;
break;
}
bio->bi_sector = sector;
bio->bi_bdev = bdev;
bio->bi_end_io = bio_batch_end_io;
bio->bi_private = &bb;
while (nr_sects != 0) {
sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects);
ret = bio_add_page(bio, ZERO_PAGE(0), sz << 9, 0);
nr_sects -= ret >> 9;
sector += ret >> 9;
if (ret < (sz << 9))
break;
}
ret = 0;
block: fix mis-synchronisation in blkdev_issue_zeroout() BZ29402 https://bugzilla.kernel.org/show_bug.cgi?id=29402 We can hit serious mis-synchronization in bio completion path of blkdev_issue_zeroout() leading to a panic. The problem is that when we are going to wait_for_completion() in blkdev_issue_zeroout() we check if the bb.done equals issued (number of submitted bios). If it does, we can skip the wait_for_completition() and just out of the function since there is nothing to wait for. However, there is a ordering problem because bio_batch_end_io() is calling atomic_inc(&bb->done) before complete(), hence it might seem to blkdev_issue_zeroout() that all bios has been completed and exit. At this point when bio_batch_end_io() is going to call complete(bb->wait), bb and wait does not longer exist since it was allocated on stack in blkdev_issue_zeroout() ==> panic! (thread 1) (thread 2) bio_batch_end_io() blkdev_issue_zeroout() if(bb) { ... if (bb->end_io) ... bb->end_io(bio, err); ... atomic_inc(&bb->done); ... ... while (issued != atomic_read(&bb.done)) ... (let issued == bb.done) ... (do the rest of the function) ... return ret; complete(bb->wait); ^^^^^^^^ panic We can fix this easily by simplifying bio_batch and completion counting. Also remove bio_end_io_t *end_io since it is not used. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Reported-by: Eric Whitney <eric.whitney@hp.com> Tested-by: Eric Whitney <eric.whitney@hp.com> Reviewed-by: Jeff Moyer <jmoyer@redhat.com> CC: Dmitry Monakhov <dmonakhov@openvz.org> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-11 17:23:53 +08:00
atomic_inc(&bb.done);
submit_bio(WRITE, bio);
}
/* Wait for bios in-flight */
block: fix mis-synchronisation in blkdev_issue_zeroout() BZ29402 https://bugzilla.kernel.org/show_bug.cgi?id=29402 We can hit serious mis-synchronization in bio completion path of blkdev_issue_zeroout() leading to a panic. The problem is that when we are going to wait_for_completion() in blkdev_issue_zeroout() we check if the bb.done equals issued (number of submitted bios). If it does, we can skip the wait_for_completition() and just out of the function since there is nothing to wait for. However, there is a ordering problem because bio_batch_end_io() is calling atomic_inc(&bb->done) before complete(), hence it might seem to blkdev_issue_zeroout() that all bios has been completed and exit. At this point when bio_batch_end_io() is going to call complete(bb->wait), bb and wait does not longer exist since it was allocated on stack in blkdev_issue_zeroout() ==> panic! (thread 1) (thread 2) bio_batch_end_io() blkdev_issue_zeroout() if(bb) { ... if (bb->end_io) ... bb->end_io(bio, err); ... atomic_inc(&bb->done); ... ... while (issued != atomic_read(&bb.done)) ... (let issued == bb.done) ... (do the rest of the function) ... return ret; complete(bb->wait); ^^^^^^^^ panic We can fix this easily by simplifying bio_batch and completion counting. Also remove bio_end_io_t *end_io since it is not used. Signed-off-by: Lukas Czerner <lczerner@redhat.com> Reported-by: Eric Whitney <eric.whitney@hp.com> Tested-by: Eric Whitney <eric.whitney@hp.com> Reviewed-by: Jeff Moyer <jmoyer@redhat.com> CC: Dmitry Monakhov <dmonakhov@openvz.org> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-11 17:23:53 +08:00
if (!atomic_dec_and_test(&bb.done))
wait_for_completion(&wait);
if (!test_bit(BIO_UPTODATE, &bb.flags))
/* One of bios in the batch was completed with error.*/
ret = -EIO;
return ret;
}
EXPORT_SYMBOL(blkdev_issue_zeroout);