linux-stable/block/bio.c

1808 lines
49 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2001 Jens Axboe <axboe@kernel.dk>
*/
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/uio.h>
block: implement bio_associate_current() IO scheduling and cgroup are tied to the issuing task via io_context and cgroup of %current. Unfortunately, there are cases where IOs need to be routed via a different task which makes scheduling and cgroup limit enforcement applied completely incorrectly. For example, all bios delayed by blk-throttle end up being issued by a delayed work item and get assigned the io_context of the worker task which happens to serve the work item and dumped to the default block cgroup. This is double confusing as bios which aren't delayed end up in the correct cgroup and makes using blk-throttle and cfq propio together impossible. Any code which punts IO issuing to another task is affected which is getting more and more common (e.g. btrfs). As both io_context and cgroup are firmly tied to task including userland visible APIs to manipulate them, it makes a lot of sense to match up tasks to bios. This patch implements bio_associate_current() which associates the specified bio with %current. The bio will record the associated ioc and blkcg at that point and block layer will use the recorded ones regardless of which task actually ends up issuing the bio. bio release puts the associated ioc and blkcg. It grabs and remembers ioc and blkcg instead of the task itself because task may already be dead by the time the bio is issued making ioc and blkcg inaccessible and those are all block layer cares about. elevator_set_req_fn() is updated such that the bio elvdata is being allocated for is available to the elevator. This doesn't update block cgroup policies yet. Further patches will implement the support. -v2: #ifdef CONFIG_BLK_CGROUP added around bio->bi_ioc dereference in rq_ioc() to fix build breakage. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Kent Overstreet <koverstreet@google.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2012-03-05 21:15:27 +00:00
#include <linux/iocontext.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/mempool.h>
#include <linux/workqueue.h>
block: implement bio_associate_current() IO scheduling and cgroup are tied to the issuing task via io_context and cgroup of %current. Unfortunately, there are cases where IOs need to be routed via a different task which makes scheduling and cgroup limit enforcement applied completely incorrectly. For example, all bios delayed by blk-throttle end up being issued by a delayed work item and get assigned the io_context of the worker task which happens to serve the work item and dumped to the default block cgroup. This is double confusing as bios which aren't delayed end up in the correct cgroup and makes using blk-throttle and cfq propio together impossible. Any code which punts IO issuing to another task is affected which is getting more and more common (e.g. btrfs). As both io_context and cgroup are firmly tied to task including userland visible APIs to manipulate them, it makes a lot of sense to match up tasks to bios. This patch implements bio_associate_current() which associates the specified bio with %current. The bio will record the associated ioc and blkcg at that point and block layer will use the recorded ones regardless of which task actually ends up issuing the bio. bio release puts the associated ioc and blkcg. It grabs and remembers ioc and blkcg instead of the task itself because task may already be dead by the time the bio is issued making ioc and blkcg inaccessible and those are all block layer cares about. elevator_set_req_fn() is updated such that the bio elvdata is being allocated for is available to the elevator. This doesn't update block cgroup policies yet. Further patches will implement the support. -v2: #ifdef CONFIG_BLK_CGROUP added around bio->bi_ioc dereference in rq_ioc() to fix build breakage. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Kent Overstreet <koverstreet@google.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2012-03-05 21:15:27 +00:00
#include <linux/cgroup.h>
#include <linux/highmem.h>
#include <linux/sched/sysctl.h>
block: Inline encryption support for blk-mq We must have some way of letting a storage device driver know what encryption context it should use for en/decrypting a request. However, it's the upper layers (like the filesystem/fscrypt) that know about and manages encryption contexts. As such, when the upper layer submits a bio to the block layer, and this bio eventually reaches a device driver with support for inline encryption, the device driver will need to have been told the encryption context for that bio. We want to communicate the encryption context from the upper layer to the storage device along with the bio, when the bio is submitted to the block layer. To do this, we add a struct bio_crypt_ctx to struct bio, which can represent an encryption context (note that we can't use the bi_private field in struct bio to do this because that field does not function to pass information across layers in the storage stack). We also introduce various functions to manipulate the bio_crypt_ctx and make the bio/request merging logic aware of the bio_crypt_ctx. We also make changes to blk-mq to make it handle bios with encryption contexts. blk-mq can merge many bios into the same request. These bios need to have contiguous data unit numbers (the necessary changes to blk-merge are also made to ensure this) - as such, it suffices to keep the data unit number of just the first bio, since that's all a storage driver needs to infer the data unit number to use for each data block in each bio in a request. blk-mq keeps track of the encryption context to be used for all the bios in a request with the request's rq_crypt_ctx. When the first bio is added to an empty request, blk-mq will program the encryption context of that bio into the request_queue's keyslot manager, and store the returned keyslot in the request's rq_crypt_ctx. All the functions to operate on encryption contexts are in blk-crypto.c. Upper layers only need to call bio_crypt_set_ctx with the encryption key, algorithm and data_unit_num; they don't have to worry about getting a keyslot for each encryption context, as blk-mq/blk-crypto handles that. Blk-crypto also makes it possible for request-based layered devices like dm-rq to make use of inline encryption hardware by cloning the rq_crypt_ctx and programming a keyslot in the new request_queue when necessary. Note that any user of the block layer can submit bios with an encryption context, such as filesystems, device-mapper targets, etc. Signed-off-by: Satya Tangirala <satyat@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-05-14 00:37:18 +00:00
#include <linux/blk-crypto.h>
#include <linux/xarray.h>
tracing/events: convert block trace points to TRACE_EVENT() TRACE_EVENT is a more generic way to define tracepoints. Doing so adds these new capabilities to this tracepoint: - zero-copy and per-cpu splice() tracing - binary tracing without printf overhead - structured logging records exposed under /debug/tracing/events - trace events embedded in function tracer output and other plugins - user-defined, per tracepoint filter expressions ... Cons: - no dev_t info for the output of plug, unplug_timer and unplug_io events. no dev_t info for getrq and sleeprq events if bio == NULL. no dev_t info for rq_abort,...,rq_requeue events if rq->rq_disk == NULL. This is mainly because we can't get the deivce from a request queue. But this may change in the future. - A packet command is converted to a string in TP_assign, not TP_print. While blktrace do the convertion just before output. Since pc requests should be rather rare, this is not a big issue. - In blktrace, an event can have 2 different print formats, but a TRACE_EVENT has a unique format, which means we have some unused data in a trace entry. The overhead is minimized by using __dynamic_array() instead of __array(). I've benchmarked the ioctl blktrace vs the splice based TRACE_EVENT tracing: dd dd + ioctl blktrace dd + TRACE_EVENT (splice) 1 7.36s, 42.7 MB/s 7.50s, 42.0 MB/s 7.41s, 42.5 MB/s 2 7.43s, 42.3 MB/s 7.48s, 42.1 MB/s 7.43s, 42.4 MB/s 3 7.38s, 42.6 MB/s 7.45s, 42.2 MB/s 7.41s, 42.5 MB/s So the overhead of tracing is very small, and no regression when using those trace events vs blktrace. And the binary output of TRACE_EVENT is much smaller than blktrace: # ls -l -h -rw-r--r-- 1 root root 8.8M 06-09 13:24 sda.blktrace.0 -rw-r--r-- 1 root root 195K 06-09 13:24 sda.blktrace.1 -rw-r--r-- 1 root root 2.7M 06-09 13:25 trace_splice.out Following are some comparisons between TRACE_EVENT and blktrace: plug: kjournald-480 [000] 303.084981: block_plug: [kjournald] kjournald-480 [000] 303.084981: 8,0 P N [kjournald] unplug_io: kblockd/0-118 [000] 300.052973: block_unplug_io: [kblockd/0] 1 kblockd/0-118 [000] 300.052974: 8,0 U N [kblockd/0] 1 remap: kjournald-480 [000] 303.085042: block_remap: 8,0 W 102736992 + 8 <- (8,8) 33384 kjournald-480 [000] 303.085043: 8,0 A W 102736992 + 8 <- (8,8) 33384 bio_backmerge: kjournald-480 [000] 303.085086: block_bio_backmerge: 8,0 W 102737032 + 8 [kjournald] kjournald-480 [000] 303.085086: 8,0 M W 102737032 + 8 [kjournald] getrq: kjournald-480 [000] 303.084974: block_getrq: 8,0 W 102736984 + 8 [kjournald] kjournald-480 [000] 303.084975: 8,0 G W 102736984 + 8 [kjournald] bash-2066 [001] 1072.953770: 8,0 G N [bash] bash-2066 [001] 1072.953773: block_getrq: 0,0 N 0 + 0 [bash] rq_complete: konsole-2065 [001] 300.053184: block_rq_complete: 8,0 W () 103669040 + 16 [0] konsole-2065 [001] 300.053191: 8,0 C W 103669040 + 16 [0] ksoftirqd/1-7 [001] 1072.953811: 8,0 C N (5a 00 08 00 00 00 00 00 24 00) [0] ksoftirqd/1-7 [001] 1072.953813: block_rq_complete: 0,0 N (5a 00 08 00 00 00 00 00 24 00) 0 + 0 [0] rq_insert: kjournald-480 [000] 303.084985: block_rq_insert: 8,0 W 0 () 102736984 + 8 [kjournald] kjournald-480 [000] 303.084986: 8,0 I W 102736984 + 8 [kjournald] Changelog from v2 -> v3: - use the newly introduced __dynamic_array(). Changelog from v1 -> v2: - use __string() instead of __array() to minimize the memory required to store hex dump of rq->cmd(). - support large pc requests. - add missing blk_fill_rwbs_rq() in block_rq_requeue TRACE_EVENT. - some cleanups. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> LKML-Reference: <4A2DF669.5070905@cn.fujitsu.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-09 05:43:05 +00:00
#include <trace/events/block.h>
blk-throttle: add a simple idle detection A cgroup gets assigned a low limit, but the cgroup could never dispatch enough IO to cross the low limit. In such case, the queue state machine will remain in LIMIT_LOW state and all other cgroups will be throttled according to low limit. This is unfair for other cgroups. We should treat the cgroup idle and upgrade the state machine to lower state. We also have a downgrade logic. If the state machine upgrades because of cgroup idle (real idle), the state machine will downgrade soon as the cgroup is below its low limit. This isn't what we want. A more complicated case is cgroup isn't idle when queue is in LIMIT_LOW. But when queue gets upgraded to lower state, other cgroups could dispatch more IO and this cgroup can't dispatch enough IO, so the cgroup is below its low limit and looks like idle (fake idle). In this case, the queue should downgrade soon. The key to determine if we should do downgrade is to detect if cgroup is truely idle. Unfortunately it's very hard to determine if a cgroup is real idle. This patch uses the 'think time check' idea from CFQ for the purpose. Please note, the idea doesn't work for all workloads. For example, a workload with io depth 8 has disk utilization 100%, hence think time is 0, eg, not idle. But the workload can run higher bandwidth with io depth 16. Compared to io depth 16, the io depth 8 workload is idle. We use the idea to roughly determine if a cgroup is idle. We treat a cgroup idle if its think time is above a threshold (by default 1ms for SSD and 100ms for HD). The idea is think time above the threshold will start to harm performance. HD is much slower so a longer think time is ok. The patch (and the latter patches) uses 'unsigned long' to track time. We convert 'ns' to 'us' with 'ns >> 10'. This is fast but loses precision, should not a big deal. Signed-off-by: Shaohua Li <shli@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-27 17:51:41 +00:00
#include "blk.h"
#include "blk-rq-qos.h"
#include "blk-cgroup.h"
#define ALLOC_CACHE_THRESHOLD 16
#define ALLOC_CACHE_MAX 256
struct bio_alloc_cache {
struct bio *free_list;
struct bio *free_list_irq;
unsigned int nr;
unsigned int nr_irq;
};
static struct biovec_slab {
int nr_vecs;
char *name;
struct kmem_cache *slab;
} bvec_slabs[] __read_mostly = {
{ .nr_vecs = 16, .name = "biovec-16" },
{ .nr_vecs = 64, .name = "biovec-64" },
{ .nr_vecs = 128, .name = "biovec-128" },
{ .nr_vecs = BIO_MAX_VECS, .name = "biovec-max" },
};
static struct biovec_slab *biovec_slab(unsigned short nr_vecs)
{
switch (nr_vecs) {
/* smaller bios use inline vecs */
case 5 ... 16:
return &bvec_slabs[0];
case 17 ... 64:
return &bvec_slabs[1];
case 65 ... 128:
return &bvec_slabs[2];
case 129 ... BIO_MAX_VECS:
return &bvec_slabs[3];
default:
BUG();
return NULL;
}
}
/*
* fs_bio_set is the bio_set containing bio and iovec memory pools used by
* IO code that does not need private memory pools.
*/
struct bio_set fs_bio_set;
EXPORT_SYMBOL(fs_bio_set);
/*
* Our slab pool management
*/
struct bio_slab {
struct kmem_cache *slab;
unsigned int slab_ref;
unsigned int slab_size;
char name[8];
};
static DEFINE_MUTEX(bio_slab_lock);
static DEFINE_XARRAY(bio_slabs);
static struct bio_slab *create_bio_slab(unsigned int size)
{
struct bio_slab *bslab = kzalloc(sizeof(*bslab), GFP_KERNEL);
if (!bslab)
return NULL;
snprintf(bslab->name, sizeof(bslab->name), "bio-%d", size);
bslab->slab = kmem_cache_create(bslab->name, size,
ARCH_KMALLOC_MINALIGN,
SLAB_HWCACHE_ALIGN | SLAB_TYPESAFE_BY_RCU, NULL);
if (!bslab->slab)
goto fail_alloc_slab;
bslab->slab_ref = 1;
bslab->slab_size = size;
if (!xa_err(xa_store(&bio_slabs, size, bslab, GFP_KERNEL)))
return bslab;
kmem_cache_destroy(bslab->slab);
fail_alloc_slab:
kfree(bslab);
return NULL;
}
static inline unsigned int bs_bio_slab_size(struct bio_set *bs)
{
return bs->front_pad + sizeof(struct bio) + bs->back_pad;
}
static struct kmem_cache *bio_find_or_create_slab(struct bio_set *bs)
{
unsigned int size = bs_bio_slab_size(bs);
struct bio_slab *bslab;
mutex_lock(&bio_slab_lock);
bslab = xa_load(&bio_slabs, size);
if (bslab)
bslab->slab_ref++;
else
bslab = create_bio_slab(size);
mutex_unlock(&bio_slab_lock);
if (bslab)
return bslab->slab;
return NULL;
}
static void bio_put_slab(struct bio_set *bs)
{
struct bio_slab *bslab = NULL;
unsigned int slab_size = bs_bio_slab_size(bs);
mutex_lock(&bio_slab_lock);
bslab = xa_load(&bio_slabs, slab_size);
if (WARN(!bslab, KERN_ERR "bio: unable to find slab!\n"))
goto out;
WARN_ON_ONCE(bslab->slab != bs->bio_slab);
WARN_ON(!bslab->slab_ref);
if (--bslab->slab_ref)
goto out;
xa_erase(&bio_slabs, slab_size);
kmem_cache_destroy(bslab->slab);
kfree(bslab);
out:
mutex_unlock(&bio_slab_lock);
}
void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs)
{
BUG_ON(nr_vecs > BIO_MAX_VECS);
if (nr_vecs == BIO_MAX_VECS)
mempool_free(bv, pool);
else if (nr_vecs > BIO_INLINE_VECS)
kmem_cache_free(biovec_slab(nr_vecs)->slab, bv);
}
/*
* Make the first allocation restricted and don't dump info on allocation
* failures, since we'll fall back to the mempool in case of failure.
*/
static inline gfp_t bvec_alloc_gfp(gfp_t gfp)
{
return (gfp & ~(__GFP_DIRECT_RECLAIM | __GFP_IO)) |
__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
}
struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
gfp_t gfp_mask)
{
struct biovec_slab *bvs = biovec_slab(*nr_vecs);
if (WARN_ON_ONCE(!bvs))
return NULL;
/*
* Upgrade the nr_vecs request to take full advantage of the allocation.
* We also rely on this in the bvec_free path.
*/
*nr_vecs = bvs->nr_vecs;
/*
* Try a slab allocation first for all smaller allocations. If that
* fails and __GFP_DIRECT_RECLAIM is set retry with the mempool.
* The mempool is sized to handle up to BIO_MAX_VECS entries.
*/
if (*nr_vecs < BIO_MAX_VECS) {
struct bio_vec *bvl;
bvl = kmem_cache_alloc(bvs->slab, bvec_alloc_gfp(gfp_mask));
if (likely(bvl) || !(gfp_mask & __GFP_DIRECT_RECLAIM))
return bvl;
*nr_vecs = BIO_MAX_VECS;
}
return mempool_alloc(pool, gfp_mask);
}
block: provide bio_uninit() free freeing integrity/task associations Wen reports significant memory leaks with DIF and O_DIRECT: "With nvme devive + T10 enabled, On a system it has 256GB and started logging /proc/meminfo & /proc/slabinfo for every minute and in an hour it increased by 15968128 kB or ~15+GB.. Approximately 256 MB / minute leaking. /proc/meminfo | grep SUnreclaim... SUnreclaim: 6752128 kB SUnreclaim: 6874880 kB SUnreclaim: 7238080 kB .... SUnreclaim: 22307264 kB SUnreclaim: 22485888 kB SUnreclaim: 22720256 kB When testcases with T10 enabled call into __blkdev_direct_IO_simple, code doesn't free memory allocated by bio_integrity_alloc. The patch fixes the issue. HTX has been run with +60 hours without failure." Since __blkdev_direct_IO_simple() allocates the bio on the stack, it doesn't go through the regular bio free. This means that any ancillary data allocated with the bio through the stack is not freed. Hence, we can leak the integrity data associated with the bio, if the device is using DIF/DIX. Fix this by providing a bio_uninit() and export it, so that we can use it to free this data. Note that this is a minimal fix for this issue. Any current user of bio's that are allocated outside of bio_alloc_bioset() suffers from this issue, most notably some drivers. We will fix those in a more comprehensive patch for 4.13. This also means that the commit marked as being fixed by this isn't the real culprit, it's just the most obvious one out there. Fixes: 542ff7bf18c6 ("block: new direct I/O implementation") Reported-by: Wen Xiong <wenxiong@linux.vnet.ibm.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-06-28 21:30:13 +00:00
void bio_uninit(struct bio *bio)
{
#ifdef CONFIG_BLK_CGROUP
if (bio->bi_blkg) {
blkg_put(bio->bi_blkg);
bio->bi_blkg = NULL;
}
#endif
if (bio_integrity(bio))
bio_integrity_free(bio);
block: Inline encryption support for blk-mq We must have some way of letting a storage device driver know what encryption context it should use for en/decrypting a request. However, it's the upper layers (like the filesystem/fscrypt) that know about and manages encryption contexts. As such, when the upper layer submits a bio to the block layer, and this bio eventually reaches a device driver with support for inline encryption, the device driver will need to have been told the encryption context for that bio. We want to communicate the encryption context from the upper layer to the storage device along with the bio, when the bio is submitted to the block layer. To do this, we add a struct bio_crypt_ctx to struct bio, which can represent an encryption context (note that we can't use the bi_private field in struct bio to do this because that field does not function to pass information across layers in the storage stack). We also introduce various functions to manipulate the bio_crypt_ctx and make the bio/request merging logic aware of the bio_crypt_ctx. We also make changes to blk-mq to make it handle bios with encryption contexts. blk-mq can merge many bios into the same request. These bios need to have contiguous data unit numbers (the necessary changes to blk-merge are also made to ensure this) - as such, it suffices to keep the data unit number of just the first bio, since that's all a storage driver needs to infer the data unit number to use for each data block in each bio in a request. blk-mq keeps track of the encryption context to be used for all the bios in a request with the request's rq_crypt_ctx. When the first bio is added to an empty request, blk-mq will program the encryption context of that bio into the request_queue's keyslot manager, and store the returned keyslot in the request's rq_crypt_ctx. All the functions to operate on encryption contexts are in blk-crypto.c. Upper layers only need to call bio_crypt_set_ctx with the encryption key, algorithm and data_unit_num; they don't have to worry about getting a keyslot for each encryption context, as blk-mq/blk-crypto handles that. Blk-crypto also makes it possible for request-based layered devices like dm-rq to make use of inline encryption hardware by cloning the rq_crypt_ctx and programming a keyslot in the new request_queue when necessary. Note that any user of the block layer can submit bios with an encryption context, such as filesystems, device-mapper targets, etc. Signed-off-by: Satya Tangirala <satyat@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-05-14 00:37:18 +00:00
bio_crypt_free_ctx(bio);
}
block: provide bio_uninit() free freeing integrity/task associations Wen reports significant memory leaks with DIF and O_DIRECT: "With nvme devive + T10 enabled, On a system it has 256GB and started logging /proc/meminfo & /proc/slabinfo for every minute and in an hour it increased by 15968128 kB or ~15+GB.. Approximately 256 MB / minute leaking. /proc/meminfo | grep SUnreclaim... SUnreclaim: 6752128 kB SUnreclaim: 6874880 kB SUnreclaim: 7238080 kB .... SUnreclaim: 22307264 kB SUnreclaim: 22485888 kB SUnreclaim: 22720256 kB When testcases with T10 enabled call into __blkdev_direct_IO_simple, code doesn't free memory allocated by bio_integrity_alloc. The patch fixes the issue. HTX has been run with +60 hours without failure." Since __blkdev_direct_IO_simple() allocates the bio on the stack, it doesn't go through the regular bio free. This means that any ancillary data allocated with the bio through the stack is not freed. Hence, we can leak the integrity data associated with the bio, if the device is using DIF/DIX. Fix this by providing a bio_uninit() and export it, so that we can use it to free this data. Note that this is a minimal fix for this issue. Any current user of bio's that are allocated outside of bio_alloc_bioset() suffers from this issue, most notably some drivers. We will fix those in a more comprehensive patch for 4.13. This also means that the commit marked as being fixed by this isn't the real culprit, it's just the most obvious one out there. Fixes: 542ff7bf18c6 ("block: new direct I/O implementation") Reported-by: Wen Xiong <wenxiong@linux.vnet.ibm.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-06-28 21:30:13 +00:00
EXPORT_SYMBOL(bio_uninit);
static void bio_free(struct bio *bio)
{
struct bio_set *bs = bio->bi_pool;
void *p = bio;
WARN_ON_ONCE(!bs);
bio_uninit(bio);
bvec_free(&bs->bvec_pool, bio->bi_io_vec, bio->bi_max_vecs);
mempool_free(p - bs->front_pad, &bs->bio_pool);
}
block: provide bio_uninit() free freeing integrity/task associations Wen reports significant memory leaks with DIF and O_DIRECT: "With nvme devive + T10 enabled, On a system it has 256GB and started logging /proc/meminfo & /proc/slabinfo for every minute and in an hour it increased by 15968128 kB or ~15+GB.. Approximately 256 MB / minute leaking. /proc/meminfo | grep SUnreclaim... SUnreclaim: 6752128 kB SUnreclaim: 6874880 kB SUnreclaim: 7238080 kB .... SUnreclaim: 22307264 kB SUnreclaim: 22485888 kB SUnreclaim: 22720256 kB When testcases with T10 enabled call into __blkdev_direct_IO_simple, code doesn't free memory allocated by bio_integrity_alloc. The patch fixes the issue. HTX has been run with +60 hours without failure." Since __blkdev_direct_IO_simple() allocates the bio on the stack, it doesn't go through the regular bio free. This means that any ancillary data allocated with the bio through the stack is not freed. Hence, we can leak the integrity data associated with the bio, if the device is using DIF/DIX. Fix this by providing a bio_uninit() and export it, so that we can use it to free this data. Note that this is a minimal fix for this issue. Any current user of bio's that are allocated outside of bio_alloc_bioset() suffers from this issue, most notably some drivers. We will fix those in a more comprehensive patch for 4.13. This also means that the commit marked as being fixed by this isn't the real culprit, it's just the most obvious one out there. Fixes: 542ff7bf18c6 ("block: new direct I/O implementation") Reported-by: Wen Xiong <wenxiong@linux.vnet.ibm.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-06-28 21:30:13 +00:00
/*
* Users of this function have their own bio allocation. Subsequently,
* they must remember to pair any call to bio_init() with bio_uninit()
* when IO has completed, or when the bio is released.
*/
void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table,
unsigned short max_vecs, blk_opf_t opf)
{
bio->bi_next = NULL;
bio->bi_bdev = bdev;
bio->bi_opf = opf;
bio->bi_flags = 0;
bio->bi_ioprio = 0;
bio->bi_status = 0;
bio->bi_iter.bi_sector = 0;
bio->bi_iter.bi_size = 0;
bio->bi_iter.bi_idx = 0;
bio->bi_iter.bi_bvec_done = 0;
bio->bi_end_io = NULL;
bio->bi_private = NULL;
#ifdef CONFIG_BLK_CGROUP
bio->bi_blkg = NULL;
bio->bi_issue.value = 0;
if (bdev)
bio_associate_blkg(bio);
#ifdef CONFIG_BLK_CGROUP_IOCOST
bio->bi_iocost_cost = 0;
#endif
#endif
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
bio->bi_crypt_context = NULL;
#endif
#ifdef CONFIG_BLK_DEV_INTEGRITY
bio->bi_integrity = NULL;
#endif
bio->bi_vcnt = 0;
atomic_set(&bio->__bi_remaining, 1);
atomic_set(&bio->__bi_cnt, 1);
bio->bi_cookie = BLK_QC_T_NONE;
bio->bi_max_vecs = max_vecs;
bio->bi_io_vec = table;
bio->bi_pool = NULL;
}
EXPORT_SYMBOL(bio_init);
/**
* bio_reset - reinitialize a bio
* @bio: bio to reset
* @bdev: block device to use the bio for
* @opf: operation and flags for bio
*
* Description:
* After calling bio_reset(), @bio will be in the same state as a freshly
* allocated bio returned bio bio_alloc_bioset() - the only fields that are
* preserved are the ones that are initialized by bio_alloc_bioset(). See
* comment in struct bio.
*/
void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf)
{
block: provide bio_uninit() free freeing integrity/task associations Wen reports significant memory leaks with DIF and O_DIRECT: "With nvme devive + T10 enabled, On a system it has 256GB and started logging /proc/meminfo & /proc/slabinfo for every minute and in an hour it increased by 15968128 kB or ~15+GB.. Approximately 256 MB / minute leaking. /proc/meminfo | grep SUnreclaim... SUnreclaim: 6752128 kB SUnreclaim: 6874880 kB SUnreclaim: 7238080 kB .... SUnreclaim: 22307264 kB SUnreclaim: 22485888 kB SUnreclaim: 22720256 kB When testcases with T10 enabled call into __blkdev_direct_IO_simple, code doesn't free memory allocated by bio_integrity_alloc. The patch fixes the issue. HTX has been run with +60 hours without failure." Since __blkdev_direct_IO_simple() allocates the bio on the stack, it doesn't go through the regular bio free. This means that any ancillary data allocated with the bio through the stack is not freed. Hence, we can leak the integrity data associated with the bio, if the device is using DIF/DIX. Fix this by providing a bio_uninit() and export it, so that we can use it to free this data. Note that this is a minimal fix for this issue. Any current user of bio's that are allocated outside of bio_alloc_bioset() suffers from this issue, most notably some drivers. We will fix those in a more comprehensive patch for 4.13. This also means that the commit marked as being fixed by this isn't the real culprit, it's just the most obvious one out there. Fixes: 542ff7bf18c6 ("block: new direct I/O implementation") Reported-by: Wen Xiong <wenxiong@linux.vnet.ibm.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-06-28 21:30:13 +00:00
bio_uninit(bio);
memset(bio, 0, BIO_RESET_BYTES);
atomic_set(&bio->__bi_remaining, 1);
bio->bi_bdev = bdev;
if (bio->bi_bdev)
bio_associate_blkg(bio);
bio->bi_opf = opf;
}
EXPORT_SYMBOL(bio_reset);
static struct bio *__bio_chain_endio(struct bio *bio)
{
struct bio *parent = bio->bi_private;
block: only update parent bi_status when bio fail For multiple split bios, if one of the bio is fail, the whole should return error to application. But we found there is a race between bio_integrity_verify_fn and bio complete, which return io success to application after one of the bio fail. The race as following: split bio(READ) kworker nvme_complete_rq blk_update_request //split error=0 bio_endio bio_integrity_endio queue_work(kintegrityd_wq, &bip->bip_work); bio_integrity_verify_fn bio_endio //split bio __bio_chain_endio if (!parent->bi_status) <interrupt entry> nvme_irq blk_update_request //parent error=7 req_bio_endio bio->bi_status = 7 //parent bio <interrupt exit> parent->bi_status = 0 parent->bi_end_io() // return bi_status=0 The bio has been split as two: split and parent. When split bio completed, it depends on kworker to do endio, while bio_integrity_verify_fn have been interrupted by parent bio complete irq handler. Then, parent bio->bi_status which have been set in irq handler will overwrite by kworker. In fact, even without the above race, we also need to conside the concurrency beteen mulitple split bio complete and update the same parent bi_status. Normally, multiple split bios will be issued to the same hctx and complete from the same irq vector. But if we have updated queue map between multiple split bios, these bios may complete on different hw queue and different irq vector. Then the concurrency update parent bi_status may cause the final status error. Suggested-by: Keith Busch <kbusch@kernel.org> Signed-off-by: Yufen Yu <yuyufen@huawei.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/20210331115359.1125679-1-yuyufen@huawei.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-03-31 11:53:59 +00:00
if (bio->bi_status && !parent->bi_status)
parent->bi_status = bio->bi_status;
bio_put(bio);
return parent;
}
static void bio_chain_endio(struct bio *bio)
{
bio_endio(__bio_chain_endio(bio));
}
/**
* bio_chain - chain bio completions
* @bio: the target bio
* @parent: the parent bio of @bio
*
* The caller won't have a bi_end_io called when @bio completes - instead,
* @parent's bi_end_io won't be called until both @parent and @bio have
* completed; the chained bio will also be freed when it completes.
*
* The caller must not set bi_private or bi_end_io in @bio.
*/
void bio_chain(struct bio *bio, struct bio *parent)
{
BUG_ON(bio->bi_private || bio->bi_end_io);
bio->bi_private = parent;
bio->bi_end_io = bio_chain_endio;
bio_inc_remaining(parent);
}
EXPORT_SYMBOL(bio_chain);
struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
unsigned int nr_pages, blk_opf_t opf, gfp_t gfp)
{
struct bio *new = bio_alloc(bdev, nr_pages, opf, gfp);
if (bio) {
bio_chain(bio, new);
submit_bio(bio);
}
return new;
}
EXPORT_SYMBOL_GPL(blk_next_bio);
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-10 21:33:46 +00:00
static void bio_alloc_rescue(struct work_struct *work)
{
struct bio_set *bs = container_of(work, struct bio_set, rescue_work);
struct bio *bio;
while (1) {
spin_lock(&bs->rescue_lock);
bio = bio_list_pop(&bs->rescue_list);
spin_unlock(&bs->rescue_lock);
if (!bio)
break;
submit_bio_noacct(bio);
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-10 21:33:46 +00:00
}
}
static void punt_bios_to_rescuer(struct bio_set *bs)
{
struct bio_list punt, nopunt;
struct bio *bio;
if (WARN_ON_ONCE(!bs->rescue_workqueue))
return;
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-10 21:33:46 +00:00
/*
* In order to guarantee forward progress we must punt only bios that
* were allocated from this bio_set; otherwise, if there was a bio on
* there for a stacking driver higher up in the stack, processing it
* could require allocating bios from this bio_set, and doing that from
* our own rescuer would be bad.
*
* Since bio lists are singly linked, pop them all instead of trying to
* remove from the middle of the list:
*/
bio_list_init(&punt);
bio_list_init(&nopunt);
while ((bio = bio_list_pop(&current->bio_list[0])))
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-10 21:33:46 +00:00
bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
current->bio_list[0] = nopunt;
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-10 21:33:46 +00:00
bio_list_init(&nopunt);
while ((bio = bio_list_pop(&current->bio_list[1])))
bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
current->bio_list[1] = nopunt;
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-10 21:33:46 +00:00
spin_lock(&bs->rescue_lock);
bio_list_merge(&bs->rescue_list, &punt);
spin_unlock(&bs->rescue_lock);
queue_work(bs->rescue_workqueue, &bs->rescue_work);
}
static void bio_alloc_irq_cache_splice(struct bio_alloc_cache *cache)
{
unsigned long flags;
/* cache->free_list must be empty */
if (WARN_ON_ONCE(cache->free_list))
return;
local_irq_save(flags);
cache->free_list = cache->free_list_irq;
cache->free_list_irq = NULL;
cache->nr += cache->nr_irq;
cache->nr_irq = 0;
local_irq_restore(flags);
}
static struct bio *bio_alloc_percpu_cache(struct block_device *bdev,
unsigned short nr_vecs, blk_opf_t opf, gfp_t gfp,
struct bio_set *bs)
{
struct bio_alloc_cache *cache;
struct bio *bio;
cache = per_cpu_ptr(bs->cache, get_cpu());
if (!cache->free_list) {
if (READ_ONCE(cache->nr_irq) >= ALLOC_CACHE_THRESHOLD)
bio_alloc_irq_cache_splice(cache);
if (!cache->free_list) {
put_cpu();
return NULL;
}
}
bio = cache->free_list;
cache->free_list = bio->bi_next;
cache->nr--;
put_cpu();
bio_init(bio, bdev, nr_vecs ? bio->bi_inline_vecs : NULL, nr_vecs, opf);
bio->bi_pool = bs;
return bio;
}
/**
* bio_alloc_bioset - allocate a bio for I/O
* @bdev: block device to allocate the bio for (can be %NULL)
* @nr_vecs: number of bvecs to pre-allocate
* @opf: operation and flags for bio
* @gfp_mask: the GFP_* mask given to the slab allocator
* @bs: the bio_set to allocate from.
*
* Allocate a bio from the mempools in @bs.
*
* If %__GFP_DIRECT_RECLAIM is set then bio_alloc will always be able to
* allocate a bio. This is due to the mempool guarantees. To make this work,
* callers must never allocate more than 1 bio at a time from the general pool.
* Callers that need to allocate more than 1 bio must always submit the
* previously allocated bio for IO before attempting to allocate a new one.
* Failure to do so can cause deadlocks under memory pressure.
*
* Note that when running under submit_bio_noacct() (i.e. any block driver),
* bios are not submitted until after you return - see the code in
* submit_bio_noacct() that converts recursion into iteration, to prevent
* stack overflows.
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-10 21:33:46 +00:00
*
* This would normally mean allocating multiple bios under submit_bio_noacct()
* would be susceptible to deadlocks, but we have
* deadlock avoidance code that resubmits any blocked bios from a rescuer
* thread.
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-10 21:33:46 +00:00
*
* However, we do not guarantee forward progress for allocations from other
* mempools. Doing multiple allocations from the same mempool under
* submit_bio_noacct() should be avoided - instead, use bio_set's front_pad
* for per bio allocations.
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-10 21:33:46 +00:00
*
* Returns: Pointer to new bio on success, NULL on failure.
*/
struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
blk_opf_t opf, gfp_t gfp_mask,
struct bio_set *bs)
{
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-10 21:33:46 +00:00
gfp_t saved_gfp = gfp_mask;
struct bio *bio;
void *p;
/* should not use nobvec bioset for nr_vecs > 0 */
if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_vecs > 0))
return NULL;
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-10 21:33:46 +00:00
if (opf & REQ_ALLOC_CACHE) {
if (bs->cache && nr_vecs <= BIO_INLINE_VECS) {
bio = bio_alloc_percpu_cache(bdev, nr_vecs, opf,
gfp_mask, bs);
if (bio)
return bio;
/*
* No cached bio available, bio returned below marked with
* REQ_ALLOC_CACHE to particpate in per-cpu alloc cache.
*/
} else {
opf &= ~REQ_ALLOC_CACHE;
}
}
/*
* submit_bio_noacct() converts recursion to iteration; this means if
* we're running beneath it, any bios we allocate and submit will not be
* submitted (and thus freed) until after we return.
*
* This exposes us to a potential deadlock if we allocate multiple bios
* from the same bio_set() while running underneath submit_bio_noacct().
* If we were to allocate multiple bios (say a stacking block driver
* that was splitting bios), we would deadlock if we exhausted the
* mempool's reserve.
*
* We solve this, and guarantee forward progress, with a rescuer
* workqueue per bio_set. If we go to allocate and there are bios on
* current->bio_list, we first try the allocation without
* __GFP_DIRECT_RECLAIM; if that fails, we punt those bios we would be
* blocking to the rescuer workqueue before we retry with the original
* gfp_flags.
*/
if (current->bio_list &&
(!bio_list_empty(&current->bio_list[0]) ||
!bio_list_empty(&current->bio_list[1])) &&
bs->rescue_workqueue)
gfp_mask &= ~__GFP_DIRECT_RECLAIM;
p = mempool_alloc(&bs->bio_pool, gfp_mask);
if (!p && gfp_mask != saved_gfp) {
punt_bios_to_rescuer(bs);
gfp_mask = saved_gfp;
p = mempool_alloc(&bs->bio_pool, gfp_mask);
}
if (unlikely(!p))
return NULL;
if (!mempool_is_saturated(&bs->bio_pool))
opf &= ~REQ_ALLOC_CACHE;
bio = p + bs->front_pad;
if (nr_vecs > BIO_INLINE_VECS) {
struct bio_vec *bvl = NULL;
bvl = bvec_alloc(&bs->bvec_pool, &nr_vecs, gfp_mask);
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-10 21:33:46 +00:00
if (!bvl && gfp_mask != saved_gfp) {
punt_bios_to_rescuer(bs);
gfp_mask = saved_gfp;
bvl = bvec_alloc(&bs->bvec_pool, &nr_vecs, gfp_mask);
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-10 21:33:46 +00:00
}
if (unlikely(!bvl))
goto err_free;
bio_init(bio, bdev, bvl, nr_vecs, opf);
} else if (nr_vecs) {
bio_init(bio, bdev, bio->bi_inline_vecs, BIO_INLINE_VECS, opf);
} else {
bio_init(bio, bdev, NULL, 0, opf);
}
bio->bi_pool = bs;
return bio;
err_free:
mempool_free(p, &bs->bio_pool);
return NULL;
}
EXPORT_SYMBOL(bio_alloc_bioset);
/**
* bio_kmalloc - kmalloc a bio
* @nr_vecs: number of bio_vecs to allocate
* @gfp_mask: the GFP_* mask given to the slab allocator
*
* Use kmalloc to allocate a bio (including bvecs). The bio must be initialized
* using bio_init() before use. To free a bio returned from this function use
* kfree() after calling bio_uninit(). A bio returned from this function can
* be reused by calling bio_uninit() before calling bio_init() again.
*
* Note that unlike bio_alloc() or bio_alloc_bioset() allocations from this
* function are not backed by a mempool can fail. Do not use this function
* for allocations in the file system I/O path.
*
* Returns: Pointer to new bio on success, NULL on failure.
*/
struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask)
{
struct bio *bio;
if (nr_vecs > UIO_MAXIOV)
return NULL;
return kmalloc(struct_size(bio, bi_inline_vecs, nr_vecs), gfp_mask);
}
EXPORT_SYMBOL(bio_kmalloc);
void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start)
{
block: Convert bio_for_each_segment() to bvec_iter More prep work for immutable biovecs - with immutable bvecs drivers won't be able to use the biovec directly, they'll need to use helpers that take into account bio->bi_iter.bi_bvec_done. This updates callers for the new usage without changing the implementation yet. 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: Paul Clements <Paul.Clements@steeleye.com> Cc: Jim Paris <jim@jtan.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: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com> Cc: Sreekanth Reddy <Sreekanth.Reddy@lsi.com> Cc: support@lsi.com Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Tejun Heo <tj@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Quoc-Son Anh <quoc-sonx.anh@intel.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Seth Jennings <sjenning@linux.vnet.ibm.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Jan Kara <jack@suse.cz> Cc: linux-m68k@lists.linux-m68k.org Cc: linuxppc-dev@lists.ozlabs.org Cc: drbd-user@lists.linbit.com Cc: nbd-general@lists.sourceforge.net Cc: cbe-oss-dev@lists.ozlabs.org Cc: xen-devel@lists.xensource.com Cc: virtualization@lists.linux-foundation.org Cc: linux-raid@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: DL-MPTFusionLinux@lsi.com Cc: linux-scsi@vger.kernel.org Cc: devel@driverdev.osuosl.org Cc: linux-fsdevel@vger.kernel.org Cc: cluster-devel@redhat.com Cc: linux-mm@kvack.org Acked-by: Geoff Levand <geoff@infradead.org>
2013-11-24 01:19:00 +00:00
struct bio_vec bv;
struct bvec_iter iter;
__bio_for_each_segment(bv, bio, iter, start)
memzero_bvec(&bv);
}
EXPORT_SYMBOL(zero_fill_bio_iter);
/**
* bio_truncate - truncate the bio to small size of @new_size
* @bio: the bio to be truncated
* @new_size: new size for truncating the bio
*
* Description:
* Truncate the bio to new size of @new_size. If bio_op(bio) is
* REQ_OP_READ, zero the truncated part. This function should only
* be used for handling corner cases, such as bio eod.
*/
static void bio_truncate(struct bio *bio, unsigned new_size)
{
struct bio_vec bv;
struct bvec_iter iter;
unsigned int done = 0;
bool truncated = false;
if (new_size >= bio->bi_iter.bi_size)
return;
if (bio_op(bio) != REQ_OP_READ)
goto exit;
bio_for_each_segment(bv, bio, iter) {
if (done + bv.bv_len > new_size) {
unsigned offset;
if (!truncated)
offset = new_size - done;
else
offset = 0;
zero_user(bv.bv_page, bv.bv_offset + offset,
bv.bv_len - offset);
truncated = true;
}
done += bv.bv_len;
}
exit:
/*
* Don't touch bvec table here and make it really immutable, since
* fs bio user has to retrieve all pages via bio_for_each_segment_all
* in its .end_bio() callback.
*
* It is enough to truncate bio by updating .bi_size since we can make
* correct bvec with the updated .bi_size for drivers.
*/
bio->bi_iter.bi_size = new_size;
}
/**
* guard_bio_eod - truncate a BIO to fit the block device
* @bio: bio to truncate
*
* This allows us to do IO even on the odd last sectors of a device, even if the
* block size is some multiple of the physical sector size.
*
* We'll just truncate the bio to the size of the device, and clear the end of
* the buffer head manually. Truly out-of-range accesses will turn into actual
* I/O errors, this only handles the "we need to be able to do I/O at the final
* sector" case.
*/
void guard_bio_eod(struct bio *bio)
{
sector_t maxsector = bdev_nr_sectors(bio->bi_bdev);
if (!maxsector)
return;
/*
* If the *whole* IO is past the end of the device,
* let it through, and the IO layer will turn it into
* an EIO.
*/
if (unlikely(bio->bi_iter.bi_sector >= maxsector))
return;
maxsector -= bio->bi_iter.bi_sector;
if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
return;
bio_truncate(bio, maxsector << 9);
}
static int __bio_alloc_cache_prune(struct bio_alloc_cache *cache,
unsigned int nr)
{
unsigned int i = 0;
struct bio *bio;
while ((bio = cache->free_list) != NULL) {
cache->free_list = bio->bi_next;
cache->nr--;
bio_free(bio);
if (++i == nr)
break;
}
return i;
}
static void bio_alloc_cache_prune(struct bio_alloc_cache *cache,
unsigned int nr)
{
nr -= __bio_alloc_cache_prune(cache, nr);
if (!READ_ONCE(cache->free_list)) {
bio_alloc_irq_cache_splice(cache);
__bio_alloc_cache_prune(cache, nr);
}
}
static int bio_cpu_dead(unsigned int cpu, struct hlist_node *node)
{
struct bio_set *bs;
bs = hlist_entry_safe(node, struct bio_set, cpuhp_dead);
if (bs->cache) {
struct bio_alloc_cache *cache = per_cpu_ptr(bs->cache, cpu);
bio_alloc_cache_prune(cache, -1U);
}
return 0;
}
static void bio_alloc_cache_destroy(struct bio_set *bs)
{
int cpu;
if (!bs->cache)
return;
cpuhp_state_remove_instance_nocalls(CPUHP_BIO_DEAD, &bs->cpuhp_dead);
for_each_possible_cpu(cpu) {
struct bio_alloc_cache *cache;
cache = per_cpu_ptr(bs->cache, cpu);
bio_alloc_cache_prune(cache, -1U);
}
free_percpu(bs->cache);
bs->cache = NULL;
}
static inline void bio_put_percpu_cache(struct bio *bio)
{
struct bio_alloc_cache *cache;
cache = per_cpu_ptr(bio->bi_pool->cache, get_cpu());
if (READ_ONCE(cache->nr_irq) + cache->nr > ALLOC_CACHE_MAX) {
put_cpu();
bio_free(bio);
return;
}
bio_uninit(bio);
if ((bio->bi_opf & REQ_POLLED) && !WARN_ON_ONCE(in_interrupt())) {
bio->bi_next = cache->free_list;
bio->bi_bdev = NULL;
cache->free_list = bio;
cache->nr++;
} else {
unsigned long flags;
local_irq_save(flags);
bio->bi_next = cache->free_list_irq;
cache->free_list_irq = bio;
cache->nr_irq++;
local_irq_restore(flags);
}
put_cpu();
}
/**
* bio_put - release a reference to a bio
* @bio: bio to release reference to
*
* Description:
* Put a reference to a &struct bio, either one you have gotten with
* bio_alloc, bio_get or bio_clone_*. The last put of a bio will free it.
**/
void bio_put(struct bio *bio)
{
if (unlikely(bio_flagged(bio, BIO_REFFED))) {
BUG_ON(!atomic_read(&bio->__bi_cnt));
if (!atomic_dec_and_test(&bio->__bi_cnt))
return;
}
if (bio->bi_opf & REQ_ALLOC_CACHE)
bio_put_percpu_cache(bio);
else
bio_free(bio);
}
EXPORT_SYMBOL(bio_put);
static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp)
{
bio_set_flag(bio, BIO_CLONED);
bio->bi_ioprio = bio_src->bi_ioprio;
bio->bi_iter = bio_src->bi_iter;
if (bio->bi_bdev) {
if (bio->bi_bdev == bio_src->bi_bdev &&
bio_flagged(bio_src, BIO_REMAPPED))
bio_set_flag(bio, BIO_REMAPPED);
bio_clone_blkg_association(bio, bio_src);
}
if (bio_crypt_clone(bio, bio_src, gfp) < 0)
return -ENOMEM;
if (bio_integrity(bio_src) &&
bio_integrity_clone(bio, bio_src, gfp) < 0)
return -ENOMEM;
return 0;
}
/**
* bio_alloc_clone - clone a bio that shares the original bio's biovec
* @bdev: block_device to clone onto
* @bio_src: bio to clone from
* @gfp: allocation priority
* @bs: bio_set to allocate from
*
* Allocate a new bio that is a clone of @bio_src. The caller owns the returned
* bio, but not the actual data it points to.
*
* The caller must ensure that the return bio is not freed before @bio_src.
*/
struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src,
gfp_t gfp, struct bio_set *bs)
{
struct bio *bio;
bio = bio_alloc_bioset(bdev, 0, bio_src->bi_opf, gfp, bs);
if (!bio)
return NULL;
if (__bio_clone(bio, bio_src, gfp) < 0) {
bio_put(bio);
return NULL;
}
bio->bi_io_vec = bio_src->bi_io_vec;
return bio;
}
EXPORT_SYMBOL(bio_alloc_clone);
/**
* bio_init_clone - clone a bio that shares the original bio's biovec
* @bdev: block_device to clone onto
* @bio: bio to clone into
* @bio_src: bio to clone from
* @gfp: allocation priority
*
* Initialize a new bio in caller provided memory that is a clone of @bio_src.
* The caller owns the returned bio, but not the actual data it points to.
*
* The caller must ensure that @bio_src is not freed before @bio.
*/
int bio_init_clone(struct block_device *bdev, struct bio *bio,
struct bio *bio_src, gfp_t gfp)
{
int ret;
bio_init(bio, bdev, bio_src->bi_io_vec, 0, bio_src->bi_opf);
ret = __bio_clone(bio, bio_src, gfp);
if (ret)
bio_uninit(bio);
return ret;
}
EXPORT_SYMBOL(bio_init_clone);
/**
* bio_full - check if the bio is full
* @bio: bio to check
* @len: length of one segment to be added
*
* Return true if @bio is full and one segment with @len bytes can't be
* added to the bio, otherwise return false
*/
static inline bool bio_full(struct bio *bio, unsigned len)
{
if (bio->bi_vcnt >= bio->bi_max_vecs)
return true;
if (bio->bi_iter.bi_size > UINT_MAX - len)
return true;
return false;
}
static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page,
unsigned int len, unsigned int off, bool *same_page)
{
size_t bv_end = bv->bv_offset + bv->bv_len;
phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + bv_end - 1;
phys_addr_t page_addr = page_to_phys(page);
if (vec_end_addr + 1 != page_addr + off)
return false;
if (xen_domain() && !xen_biovec_phys_mergeable(bv, page))
return false;
if (!zone_device_pages_have_same_pgmap(bv->bv_page, page))
return false;
*same_page = ((vec_end_addr & PAGE_MASK) == page_addr);
if (!*same_page) {
if (IS_ENABLED(CONFIG_KMSAN))
return false;
if (bv->bv_page + bv_end / PAGE_SIZE != page + off / PAGE_SIZE)
return false;
}
bv->bv_len += len;
return true;
}
/*
* Try to merge a page into a segment, while obeying the hardware segment
* size limit. This is not for normal read/write bios, but for passthrough
* or Zone Append operations that we can't split.
*/
bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv,
struct page *page, unsigned len, unsigned offset,
bool *same_page)
{
unsigned long mask = queue_segment_boundary(q);
phys_addr_t addr1 = page_to_phys(bv->bv_page) + bv->bv_offset;
phys_addr_t addr2 = page_to_phys(page) + offset + len - 1;
if ((addr1 | mask) != (addr2 | mask))
return false;
if (bv->bv_len + len > queue_max_segment_size(q))
return false;
return bvec_try_merge_page(bv, page, len, offset, same_page);
}
/**
* bio_add_hw_page - attempt to add a page to a bio with hw constraints
* @q: the target queue
* @bio: destination bio
* @page: page to add
* @len: vec entry length
* @offset: vec entry offset
* @max_sectors: maximum number of sectors that can be added
* @same_page: return if the segment has been merged inside the same page
*
* Add a page to a bio while respecting the hardware max_sectors, max_segment
* and gap limitations.
*/
int bio_add_hw_page(struct request_queue *q, struct bio *bio,
struct page *page, unsigned int len, unsigned int offset,
unsigned int max_sectors, bool *same_page)
{
if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
return 0;
if (((bio->bi_iter.bi_size + len) >> SECTOR_SHIFT) > max_sectors)
return 0;
if (bio->bi_vcnt > 0) {
struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
if (bvec_try_merge_hw_page(q, bv, page, len, offset,
same_page)) {
bio->bi_iter.bi_size += len;
return len;
}
if (bio->bi_vcnt >=
min(bio->bi_max_vecs, queue_max_segments(q)))
return 0;
/*
* If the queue doesn't support SG gaps and adding this segment
* would create a gap, disallow it.
*/
if (bvec_gap_to_prev(&q->limits, bv, offset))
return 0;
}
bvec_set_page(&bio->bi_io_vec[bio->bi_vcnt], page, len, offset);
bio->bi_vcnt++;
bio->bi_iter.bi_size += len;
return len;
}
/**
* bio_add_pc_page - attempt to add page to passthrough bio
* @q: the target queue
* @bio: destination bio
* @page: page to add
* @len: vec entry length
* @offset: vec entry offset
*
* Attempt to add a page to the bio_vec maplist. This can fail for a
* number of reasons, such as the bio being full or target block device
* limitations. The target block device must allow bio's up to PAGE_SIZE,
* so it is always possible to add a single page to an empty bio.
*
* This should only be used by passthrough bios.
*/
int bio_add_pc_page(struct request_queue *q, struct bio *bio,
struct page *page, unsigned int len, unsigned int offset)
{
bool same_page = false;
return bio_add_hw_page(q, bio, page, len, offset,
queue_max_hw_sectors(q), &same_page);
}
EXPORT_SYMBOL(bio_add_pc_page);
/**
* bio_add_zone_append_page - attempt to add page to zone-append bio
* @bio: destination bio
* @page: page to add
* @len: vec entry length
* @offset: vec entry offset
*
* Attempt to add a page to the bio_vec maplist of a bio that will be submitted
* for a zone-append request. This can fail for a number of reasons, such as the
* bio being full or the target block device is not a zoned block device or
* other limitations of the target block device. The target block device must
* allow bio's up to PAGE_SIZE, so it is always possible to add a single page
* to an empty bio.
*
* Returns: number of bytes added to the bio, or 0 in case of a failure.
*/
int bio_add_zone_append_page(struct bio *bio, struct page *page,
unsigned int len, unsigned int offset)
{
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
bool same_page = false;
if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_ZONE_APPEND))
return 0;
if (WARN_ON_ONCE(!bdev_is_zoned(bio->bi_bdev)))
return 0;
return bio_add_hw_page(q, bio, page, len, offset,
queue_max_zone_append_sectors(q), &same_page);
}
EXPORT_SYMBOL_GPL(bio_add_zone_append_page);
/**
* __bio_add_page - add page(s) to a bio in a new segment
* @bio: destination bio
* @page: start page to add
* @len: length of the data to add, may cross pages
* @off: offset of the data relative to @page, may cross pages
*
* Add the data at @page + @off to @bio as a new bvec. The caller must ensure
* that @bio has space for another bvec.
*/
void __bio_add_page(struct bio *bio, struct page *page,
unsigned int len, unsigned int off)
{
WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
WARN_ON_ONCE(bio_full(bio, len));
bvec_set_page(&bio->bi_io_vec[bio->bi_vcnt], page, len, off);
bio->bi_iter.bi_size += len;
bio->bi_vcnt++;
}
EXPORT_SYMBOL_GPL(__bio_add_page);
/**
* bio_add_page - attempt to add page(s) to bio
* @bio: destination bio
* @page: start page to add
* @len: vec entry length, may cross pages
* @offset: vec entry offset relative to @page, may cross pages
*
* Attempt to add page(s) to the bio_vec maplist. This will only fail
* if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio.
*/
int bio_add_page(struct bio *bio, struct page *page,
unsigned int len, unsigned int offset)
{
bool same_page = false;
if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
return 0;
if (bio->bi_iter.bi_size > UINT_MAX - len)
return 0;
if (bio->bi_vcnt > 0 &&
bvec_try_merge_page(&bio->bi_io_vec[bio->bi_vcnt - 1],
page, len, offset, &same_page)) {
bio->bi_iter.bi_size += len;
return len;
}
if (bio->bi_vcnt >= bio->bi_max_vecs)
return 0;
__bio_add_page(bio, page, len, offset);
return len;
}
EXPORT_SYMBOL(bio_add_page);
void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len,
size_t off)
{
WARN_ON_ONCE(len > UINT_MAX);
WARN_ON_ONCE(off > UINT_MAX);
__bio_add_page(bio, &folio->page, len, off);
}
/**
* bio_add_folio - Attempt to add part of a folio to a bio.
* @bio: BIO to add to.
* @folio: Folio to add.
* @len: How many bytes from the folio to add.
* @off: First byte in this folio to add.
*
* Filesystems that use folios can call this function instead of calling
* bio_add_page() for each page in the folio. If @off is bigger than
* PAGE_SIZE, this function can create a bio_vec that starts in a page
* after the bv_page. BIOs do not support folios that are 4GiB or larger.
*
* Return: Whether the addition was successful.
*/
bool bio_add_folio(struct bio *bio, struct folio *folio, size_t len,
size_t off)
{
if (len > UINT_MAX || off > UINT_MAX)
return false;
return bio_add_page(bio, &folio->page, len, off) > 0;
}
EXPORT_SYMBOL(bio_add_folio);
void __bio_release_pages(struct bio *bio, bool mark_dirty)
{
struct bvec_iter_all iter_all;
struct bio_vec *bvec;
bio_for_each_segment_all(bvec, bio, iter_all) {
if (mark_dirty && !PageCompound(bvec->bv_page))
set_page_dirty_lock(bvec->bv_page);
bio_release_page(bio, bvec->bv_page);
}
}
EXPORT_SYMBOL_GPL(__bio_release_pages);
void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
{
size_t size = iov_iter_count(iter);
WARN_ON_ONCE(bio->bi_max_vecs);
if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
size_t max_sectors = queue_max_zone_append_sectors(q);
size = min(size, max_sectors << SECTOR_SHIFT);
}
bio->bi_vcnt = iter->nr_segs;
bio->bi_io_vec = (struct bio_vec *)iter->bvec;
bio->bi_iter.bi_bvec_done = iter->iov_offset;
bio->bi_iter.bi_size = size;
bio_set_flag(bio, BIO_CLONED);
}
static int bio_iov_add_page(struct bio *bio, struct page *page,
unsigned int len, unsigned int offset)
{
bool same_page = false;
if (WARN_ON_ONCE(bio->bi_iter.bi_size > UINT_MAX - len))
return -EIO;
if (bio->bi_vcnt > 0 &&
bvec_try_merge_page(&bio->bi_io_vec[bio->bi_vcnt - 1],
page, len, offset, &same_page)) {
bio->bi_iter.bi_size += len;
if (same_page)
bio_release_page(bio, page);
return 0;
}
__bio_add_page(bio, page, len, offset);
return 0;
}
static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
unsigned int len, unsigned int offset)
{
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
bool same_page = false;
if (bio_add_hw_page(q, bio, page, len, offset,
queue_max_zone_append_sectors(q), &same_page) != len)
return -EINVAL;
if (same_page)
bio_release_page(bio, page);
return 0;
}
#define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *))
/**
* __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
* @bio: bio to add pages to
* @iter: iov iterator describing the region to be mapped
*
* Extracts pages from *iter and appends them to @bio's bvec array. The pages
* will have to be cleaned up in the way indicated by the BIO_PAGE_PINNED flag.
* For a multi-segment *iter, this function only adds pages from the next
* non-empty segment of the iov iterator.
*/
static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
{
iov_iter_extraction_t extraction_flags = 0;
unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
struct page **pages = (struct page **)bv;
ssize_t size, left;
unsigned len, i = 0;
size_t offset;
int ret = 0;
/*
* Move page array up in the allocated memory for the bio vecs as far as
* possible so that we can start filling biovecs from the beginning
* without overwriting the temporary page array.
*/
BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
if (bio->bi_bdev && blk_queue_pci_p2pdma(bio->bi_bdev->bd_disk->queue))
extraction_flags |= ITER_ALLOW_P2PDMA;
/*
* Each segment in the iov is required to be a block size multiple.
* However, we may not be able to get the entire segment if it spans
* more pages than bi_max_vecs allows, so we have to ALIGN_DOWN the
* result to ensure the bio's total size is correct. The remainder of
* the iov data will be picked up in the next bio iteration.
*/
size = iov_iter_extract_pages(iter, &pages,
UINT_MAX - bio->bi_iter.bi_size,
nr_pages, extraction_flags, &offset);
if (unlikely(size <= 0))
return size ? size : -EFAULT;
nr_pages = DIV_ROUND_UP(offset + size, PAGE_SIZE);
if (bio->bi_bdev) {
size_t trim = size & (bdev_logical_block_size(bio->bi_bdev) - 1);
iov_iter_revert(iter, trim);
size -= trim;
}
if (unlikely(!size)) {
ret = -EFAULT;
goto out;
}
for (left = size, i = 0; left > 0; left -= len, i++) {
struct page *page = pages[i];
len = min_t(size_t, PAGE_SIZE - offset, left);
if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
ret = bio_iov_add_zone_append_page(bio, page, len,
offset);
if (ret)
break;
} else
bio_iov_add_page(bio, page, len, offset);
offset = 0;
}
iov_iter_revert(iter, left);
out:
while (i < nr_pages)
bio_release_page(bio, pages[i++]);
return ret;
}
/**
* bio_iov_iter_get_pages - add user or kernel pages to a bio
* @bio: bio to add pages to
* @iter: iov iterator describing the region to be added
*
* This takes either an iterator pointing to user memory, or one pointing to
* kernel pages (BVEC iterator). If we're adding user pages, we pin them and
* map them into the kernel. On IO completion, the caller should put those
* pages. For bvec based iterators bio_iov_iter_get_pages() uses the provided
* bvecs rather than copying them. Hence anyone issuing kiocb based IO needs
* to ensure the bvecs and pages stay referenced until the submitted I/O is
* completed by a call to ->ki_complete() or returns with an error other than
* -EIOCBQUEUED. The caller needs to check if the bio is flagged BIO_NO_PAGE_REF
* on IO completion. If it isn't, then pages should be released.
*
* The function tries, but does not guarantee, to pin as many pages as
* fit into the bio, or are requested in @iter, whatever is smaller. If
* MM encounters an error pinning the requested pages, it stops. Error
* is returned only if 0 pages could be pinned.
*/
int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
{
int ret = 0;
if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
return -EIO;
if (iov_iter_is_bvec(iter)) {
bio_iov_bvec_set(bio, iter);
iov_iter_advance(iter, bio->bi_iter.bi_size);
return 0;
}
if (iov_iter_extract_will_pin(iter))
bio_set_flag(bio, BIO_PAGE_PINNED);
do {
ret = __bio_iov_iter_get_pages(bio, iter);
} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
return bio->bi_vcnt ? 0 : ret;
}
EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
static void submit_bio_wait_endio(struct bio *bio)
{
complete(bio->bi_private);
}
/**
* submit_bio_wait - submit a bio, and wait until it completes
* @bio: The &struct bio which describes the I/O
*
* Simple wrapper around submit_bio(). Returns 0 on success, or the error from
* bio_endio() on failure.
*
* WARNING: Unlike to how submit_bio() is usually used, this function does not
* result in bio reference to be consumed. The caller must drop the reference
* on his own.
*/
int submit_bio_wait(struct bio *bio)
{
DECLARE_COMPLETION_ONSTACK_MAP(done,
bio->bi_bdev->bd_disk->lockdep_map);
unsigned long hang_check;
bio->bi_private = &done;
bio->bi_end_io = submit_bio_wait_endio;
bio->bi_opf |= REQ_SYNC;
submit_bio(bio);
/* Prevent hang_check timer from firing at us during very long I/O */
hang_check = sysctl_hung_task_timeout_secs;
if (hang_check)
while (!wait_for_completion_io_timeout(&done,
hang_check * (HZ/2)))
;
else
wait_for_completion_io(&done);
return blk_status_to_errno(bio->bi_status);
}
EXPORT_SYMBOL(submit_bio_wait);
void __bio_advance(struct bio *bio, unsigned bytes)
{
if (bio_integrity(bio))
bio_integrity_advance(bio, bytes);
block: Inline encryption support for blk-mq We must have some way of letting a storage device driver know what encryption context it should use for en/decrypting a request. However, it's the upper layers (like the filesystem/fscrypt) that know about and manages encryption contexts. As such, when the upper layer submits a bio to the block layer, and this bio eventually reaches a device driver with support for inline encryption, the device driver will need to have been told the encryption context for that bio. We want to communicate the encryption context from the upper layer to the storage device along with the bio, when the bio is submitted to the block layer. To do this, we add a struct bio_crypt_ctx to struct bio, which can represent an encryption context (note that we can't use the bi_private field in struct bio to do this because that field does not function to pass information across layers in the storage stack). We also introduce various functions to manipulate the bio_crypt_ctx and make the bio/request merging logic aware of the bio_crypt_ctx. We also make changes to blk-mq to make it handle bios with encryption contexts. blk-mq can merge many bios into the same request. These bios need to have contiguous data unit numbers (the necessary changes to blk-merge are also made to ensure this) - as such, it suffices to keep the data unit number of just the first bio, since that's all a storage driver needs to infer the data unit number to use for each data block in each bio in a request. blk-mq keeps track of the encryption context to be used for all the bios in a request with the request's rq_crypt_ctx. When the first bio is added to an empty request, blk-mq will program the encryption context of that bio into the request_queue's keyslot manager, and store the returned keyslot in the request's rq_crypt_ctx. All the functions to operate on encryption contexts are in blk-crypto.c. Upper layers only need to call bio_crypt_set_ctx with the encryption key, algorithm and data_unit_num; they don't have to worry about getting a keyslot for each encryption context, as blk-mq/blk-crypto handles that. Blk-crypto also makes it possible for request-based layered devices like dm-rq to make use of inline encryption hardware by cloning the rq_crypt_ctx and programming a keyslot in the new request_queue when necessary. Note that any user of the block layer can submit bios with an encryption context, such as filesystems, device-mapper targets, etc. Signed-off-by: Satya Tangirala <satyat@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-05-14 00:37:18 +00:00
bio_crypt_advance(bio, bytes);
bio_advance_iter(bio, &bio->bi_iter, bytes);
}
EXPORT_SYMBOL(__bio_advance);
void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
struct bio *src, struct bvec_iter *src_iter)
{
while (src_iter->bi_size && dst_iter->bi_size) {
struct bio_vec src_bv = bio_iter_iovec(src, *src_iter);
struct bio_vec dst_bv = bio_iter_iovec(dst, *dst_iter);
unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len);
void *src_buf = bvec_kmap_local(&src_bv);
void *dst_buf = bvec_kmap_local(&dst_bv);
memcpy(dst_buf, src_buf, bytes);
kunmap_local(dst_buf);
kunmap_local(src_buf);
bio_advance_iter_single(src, src_iter, bytes);
bio_advance_iter_single(dst, dst_iter, bytes);
}
}
EXPORT_SYMBOL(bio_copy_data_iter);
/**
* bio_copy_data - copy contents of data buffers from one bio to another
* @src: source bio
* @dst: destination bio
*
* Stops when it reaches the end of either @src or @dst - that is, copies
* min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of bios).
*/
void bio_copy_data(struct bio *dst, struct bio *src)
{
struct bvec_iter src_iter = src->bi_iter;
struct bvec_iter dst_iter = dst->bi_iter;
bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
}
EXPORT_SYMBOL(bio_copy_data);
void bio_free_pages(struct bio *bio)
{
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
bio_for_each_segment_all(bvec, bio, iter_all)
__free_page(bvec->bv_page);
}
EXPORT_SYMBOL(bio_free_pages);
/*
* bio_set_pages_dirty() and bio_check_pages_dirty() are support functions
* for performing direct-IO in BIOs.
*
* The problem is that we cannot run set_page_dirty() from interrupt context
* because the required locks are not interrupt-safe. So what we can do is to
* mark the pages dirty _before_ performing IO. And in interrupt context,
* check that the pages are still dirty. If so, fine. If not, redirty them
* in process context.
*
* We special-case compound pages here: normally this means reads into hugetlb
* pages. The logic in here doesn't really work right for compound pages
* because the VM does not uniformly chase down the head page in all cases.
* But dirtiness of compound pages is pretty meaningless anyway: the VM doesn't
* handle them at all. So we skip compound pages here at an early stage.
*
* Note that this code is very hard to test under normal circumstances because
* direct-io pins the pages with get_user_pages(). This makes
* is_page_cache_freeable return false, and the VM will not clean the pages.
* But other code (eg, flusher threads) could clean the pages if they are mapped
* pagecache.
*
* Simply disabling the call to bio_set_pages_dirty() is a good way to test the
* deferred bio dirtying paths.
*/
/*
* bio_set_pages_dirty() will mark all the bio's pages as dirty.
*/
void bio_set_pages_dirty(struct bio *bio)
{
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
bio_for_each_segment_all(bvec, bio, iter_all) {
if (!PageCompound(bvec->bv_page))
set_page_dirty_lock(bvec->bv_page);
}
}
EXPORT_SYMBOL_GPL(bio_set_pages_dirty);
/*
* bio_check_pages_dirty() will check that all the BIO's pages are still dirty.
* If they are, then fine. If, however, some pages are clean then they must
* have been written out during the direct-IO read. So we take another ref on
* the BIO and re-dirty the pages in process context.
*
* It is expected that bio_check_pages_dirty() will wholly own the BIO from
* here on. It will unpin each page and will run one bio_put() against the
* BIO.
*/
2006-11-22 14:55:48 +00:00
static void bio_dirty_fn(struct work_struct *work);
2006-11-22 14:55:48 +00:00
static DECLARE_WORK(bio_dirty_work, bio_dirty_fn);
static DEFINE_SPINLOCK(bio_dirty_lock);
static struct bio *bio_dirty_list;
/*
* This runs in process context
*/
2006-11-22 14:55:48 +00:00
static void bio_dirty_fn(struct work_struct *work)
{
struct bio *bio, *next;
spin_lock_irq(&bio_dirty_lock);
next = bio_dirty_list;
bio_dirty_list = NULL;
spin_unlock_irq(&bio_dirty_lock);
while ((bio = next) != NULL) {
next = bio->bi_private;
bio_release_pages(bio, true);
bio_put(bio);
}
}
void bio_check_pages_dirty(struct bio *bio)
{
struct bio_vec *bvec;
unsigned long flags;
struct bvec_iter_all iter_all;
bio_for_each_segment_all(bvec, bio, iter_all) {
if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page))
goto defer;
}
bio_release_pages(bio, false);
bio_put(bio);
return;
defer:
spin_lock_irqsave(&bio_dirty_lock, flags);
bio->bi_private = bio_dirty_list;
bio_dirty_list = bio;
spin_unlock_irqrestore(&bio_dirty_lock, flags);
schedule_work(&bio_dirty_work);
}
EXPORT_SYMBOL_GPL(bio_check_pages_dirty);
static inline bool bio_remaining_done(struct bio *bio)
{
/*
* If we're not chaining, then ->__bi_remaining is always 1 and
* we always end io on the first invocation.
*/
if (!bio_flagged(bio, BIO_CHAIN))
return true;
BUG_ON(atomic_read(&bio->__bi_remaining) <= 0);
block: remove management of bi_remaining when restoring original bi_end_io Commit c4cf5261 ("bio: skip atomic inc/dec of ->bi_remaining for non-chains") regressed all existing callers that followed this pattern: 1) saving a bio's original bi_end_io 2) wiring up an intermediate bi_end_io 3) restoring the original bi_end_io from intermediate bi_end_io 4) calling bio_endio() to execute the restored original bi_end_io The regression was due to BIO_CHAIN only ever getting set if bio_inc_remaining() is called. For the above pattern it isn't set until step 3 above (step 2 would've needed to establish BIO_CHAIN). As such the first bio_endio(), in step 2 above, never decremented __bi_remaining before calling the intermediate bi_end_io -- leaving __bi_remaining with the value 1 instead of 0. When bio_inc_remaining() occurred during step 3 it brought it to a value of 2. When the second bio_endio() was called, in step 4 above, it should've called the original bi_end_io but it didn't because there was an extra reference that wasn't dropped (due to atomic operations being optimized away since BIO_CHAIN wasn't set upfront). Fix this issue by removing the __bi_remaining management complexity for all callers that use the above pattern -- bio_chain() is the only interface that _needs_ to be concerned with __bi_remaining. For the above pattern callers just expect the bi_end_io they set to get called! Remove bio_endio_nodec() and also remove all bio_inc_remaining() calls that aren't associated with the bio_chain() interface. Also, the bio_inc_remaining() interface has been moved local to bio.c. Fixes: c4cf5261 ("bio: skip atomic inc/dec of ->bi_remaining for non-chains") Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-05-22 13:14:03 +00:00
if (atomic_dec_and_test(&bio->__bi_remaining)) {
bio_clear_flag(bio, BIO_CHAIN);
return true;
block: remove management of bi_remaining when restoring original bi_end_io Commit c4cf5261 ("bio: skip atomic inc/dec of ->bi_remaining for non-chains") regressed all existing callers that followed this pattern: 1) saving a bio's original bi_end_io 2) wiring up an intermediate bi_end_io 3) restoring the original bi_end_io from intermediate bi_end_io 4) calling bio_endio() to execute the restored original bi_end_io The regression was due to BIO_CHAIN only ever getting set if bio_inc_remaining() is called. For the above pattern it isn't set until step 3 above (step 2 would've needed to establish BIO_CHAIN). As such the first bio_endio(), in step 2 above, never decremented __bi_remaining before calling the intermediate bi_end_io -- leaving __bi_remaining with the value 1 instead of 0. When bio_inc_remaining() occurred during step 3 it brought it to a value of 2. When the second bio_endio() was called, in step 4 above, it should've called the original bi_end_io but it didn't because there was an extra reference that wasn't dropped (due to atomic operations being optimized away since BIO_CHAIN wasn't set upfront). Fix this issue by removing the __bi_remaining management complexity for all callers that use the above pattern -- bio_chain() is the only interface that _needs_ to be concerned with __bi_remaining. For the above pattern callers just expect the bi_end_io they set to get called! Remove bio_endio_nodec() and also remove all bio_inc_remaining() calls that aren't associated with the bio_chain() interface. Also, the bio_inc_remaining() interface has been moved local to bio.c. Fixes: c4cf5261 ("bio: skip atomic inc/dec of ->bi_remaining for non-chains") Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-05-22 13:14:03 +00:00
}
return false;
}
/**
* bio_endio - end I/O on a bio
* @bio: bio
*
* Description:
* bio_endio() will end I/O on the whole bio. bio_endio() is the preferred
* way to end I/O on a bio. No one should call bi_end_io() directly on a
* bio unless they own it and thus know that it has an end_io function.
block: trace completion of all bios. Currently only dm and md/raid5 bios trigger trace_block_bio_complete(). Now that we have bio_chain() and bio_inc_remaining(), it is not possible, in general, for a driver to know when the bio is really complete. Only bio_endio() knows that. So move the trace_block_bio_complete() call to bio_endio(). Now trace_block_bio_complete() pairs with trace_block_bio_queue(). Any bio for which a 'queue' event is traced, will subsequently generate a 'complete' event. There are a few cases where completion tracing is not wanted. 1/ If blk_update_request() has already generated a completion trace event at the 'request' level, there is no point generating one at the bio level too. In this case the bi_sector and bi_size will have changed, so the bio level event would be wrong 2/ If the bio hasn't actually been queued yet, but is being aborted early, then a trace event could be confusing. Some filesystems call bio_endio() but do not want tracing. 3/ The bio_integrity code interposes itself by replacing bi_end_io, then restoring it and calling bio_endio() again. This would produce two identical trace events if left like that. To handle these, we introduce a flag BIO_TRACE_COMPLETION and only produce the trace event when this is set. We address point 1 above by clearing the flag in blk_update_request(). We address point 2 above by only setting the flag when generic_make_request() is called. We address point 3 above by clearing the flag after generating a completion event. When bio_split() is used on a bio, particularly in blk_queue_split(), there is an extra complication. A new bio is split off the front, and may be handle directly without going through generic_make_request(). The old bio, which has been advanced, is passed to generic_make_request(), so it will trigger a trace event a second time. Probably the best result when a split happens is to see a single 'queue' event for the whole bio, then multiple 'complete' events - one for each component. To achieve this was can: - copy the BIO_TRACE_COMPLETION flag to the new bio in bio_split() - avoid generating a 'queue' event if BIO_TRACE_COMPLETION is already set. This way, the split-off bio won't create a queue event, the original won't either even if it re-submitted to generic_make_request(), but both will produce completion events, each for their own range. So if generic_make_request() is called (which generates a QUEUED event), then bi_endio() will create a single COMPLETE event for each range that the bio is split into, unless the driver has explicitly requested it not to. Signed-off-by: NeilBrown <neilb@suse.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-07 15:40:52 +00:00
*
* bio_endio() can be called several times on a bio that has been chained
* using bio_chain(). The ->bi_end_io() function will only be called the
* last time.
**/
void bio_endio(struct bio *bio)
{
again:
if (!bio_remaining_done(bio))
return;
if (!bio_integrity_endio(bio))
return;
block: fix rq-qos breakage from skipping rq_qos_done_bio() a647a524a467 ("block: don't call rq_qos_ops->done_bio if the bio isn't tracked") made bio_endio() skip rq_qos_done_bio() if BIO_TRACKED is not set. While this fixed a potential oops, it also broke blk-iocost by skipping the done_bio callback for merged bios. Before, whether a bio goes through rq_qos_throttle() or rq_qos_merge(), rq_qos_done_bio() would be called on the bio on completion with BIO_TRACKED distinguishing the former from the latter. rq_qos_done_bio() is not called for bios which wenth through rq_qos_merge(). This royally confuses blk-iocost as the merged bios never finish and are considered perpetually in-flight. One reliably reproducible failure mode is an intermediate cgroup geting stuck active preventing its children from being activated due to the leaf-only rule, leading to loss of control. The following is from resctl-bench protection scenario which emulates isolating a web server like workload from a memory bomb run on an iocost configuration which should yield a reasonable level of protection. # cat /sys/block/nvme2n1/device/model Samsung SSD 970 PRO 512GB # cat /sys/fs/cgroup/io.cost.model 259:0 ctrl=user model=linear rbps=834913556 rseqiops=93622 rrandiops=102913 wbps=618985353 wseqiops=72325 wrandiops=71025 # cat /sys/fs/cgroup/io.cost.qos 259:0 enable=1 ctrl=user rpct=95.00 rlat=18776 wpct=95.00 wlat=8897 min=60.00 max=100.00 # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=242u:336u/2.5m p90=794u:1.4m/7.5m p99=2.7m:8.0m/62.5m max=8.0m:36.4m/350m W p50=221u:323u/1.5m p90=709u:1.2m/5.5m p99=1.5m:2.5m/9.5m max=6.9m:35.9m/350m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 15.90 15.90 15.90 40.05 57.24 59.07 60.01 74.63 74.63 90.35 90.35 58.12 15.82 lat-imp% 0 0 0 0 0 4.55 14.68 15.54 233.5 548.1 548.1 53.88 143.6 Result: isol=58.12:15.82% lat_imp=53.88%:143.6 work_csv=100.0% missing=3.96% The isolation result of 58.12% is close to what this device would show without any IO control. Fix it by introducing a new flag BIO_QOS_MERGED to mark merged bios and calling rq_qos_done_bio() on them too. For consistency and clarity, rename BIO_TRACKED to BIO_QOS_THROTTLED. The flag checks are moved into rq_qos_done_bio() so that it's next to the code paths that set the flags. With the patch applied, the above same benchmark shows: # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=123u:84.4u/985u p90=322u:256u/2.5m p99=1.6m:1.4m/9.5m max=11.1m:36.0m/350m W p50=429u:274u/995u p90=1.7m:1.3m/4.5m p99=3.4m:2.7m/11.5m max=7.9m:5.9m/26.5m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 84.91 84.91 89.51 90.73 92.31 94.49 96.36 98.04 98.71 100.0 100.0 94.42 2.81 lat-imp% 0 0 0 0 0 2.81 5.73 11.11 13.92 17.53 22.61 4.10 4.68 Result: isol=94.42:2.81% lat_imp=4.10%:4.68 work_csv=58.34% missing=0% Signed-off-by: Tejun Heo <tj@kernel.org> Fixes: a647a524a467 ("block: don't call rq_qos_ops->done_bio if the bio isn't tracked") Cc: stable@vger.kernel.org # v5.15+ Cc: Ming Lei <ming.lei@redhat.com> Cc: Yu Kuai <yukuai3@huawei.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/Yi7rdrzQEHjJLGKB@slm.duckdns.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-03-14 07:15:02 +00:00
rq_qos_done_bio(bio);
if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio);
bio_clear_flag(bio, BIO_TRACE_COMPLETION);
}
/*
* Need to have a real endio function for chained bios, otherwise
* various corner cases will break (like stacking block devices that
* save/restore bi_end_io) - however, we want to avoid unbounded
* recursion and blowing the stack. Tail call optimization would
* handle this, but compiling with frame pointers also disables
* gcc's sibling call optimization.
*/
if (bio->bi_end_io == bio_chain_endio) {
bio = __bio_chain_endio(bio);
goto again;
}
blk-throttle: add a simple idle detection A cgroup gets assigned a low limit, but the cgroup could never dispatch enough IO to cross the low limit. In such case, the queue state machine will remain in LIMIT_LOW state and all other cgroups will be throttled according to low limit. This is unfair for other cgroups. We should treat the cgroup idle and upgrade the state machine to lower state. We also have a downgrade logic. If the state machine upgrades because of cgroup idle (real idle), the state machine will downgrade soon as the cgroup is below its low limit. This isn't what we want. A more complicated case is cgroup isn't idle when queue is in LIMIT_LOW. But when queue gets upgraded to lower state, other cgroups could dispatch more IO and this cgroup can't dispatch enough IO, so the cgroup is below its low limit and looks like idle (fake idle). In this case, the queue should downgrade soon. The key to determine if we should do downgrade is to detect if cgroup is truely idle. Unfortunately it's very hard to determine if a cgroup is real idle. This patch uses the 'think time check' idea from CFQ for the purpose. Please note, the idea doesn't work for all workloads. For example, a workload with io depth 8 has disk utilization 100%, hence think time is 0, eg, not idle. But the workload can run higher bandwidth with io depth 16. Compared to io depth 16, the io depth 8 workload is idle. We use the idea to roughly determine if a cgroup is idle. We treat a cgroup idle if its think time is above a threshold (by default 1ms for SSD and 100ms for HD). The idea is think time above the threshold will start to harm performance. HD is much slower so a longer think time is ok. The patch (and the latter patches) uses 'unsigned long' to track time. We convert 'ns' to 'us' with 'ns >> 10'. This is fast but loses precision, should not a big deal. Signed-off-by: Shaohua Li <shli@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-27 17:51:41 +00:00
blk_throtl_bio_endio(bio);
/* release cgroup info */
bio_uninit(bio);
if (bio->bi_end_io)
bio->bi_end_io(bio);
}
EXPORT_SYMBOL(bio_endio);
/**
* bio_split - split a bio
* @bio: bio to split
* @sectors: number of sectors to split from the front of @bio
* @gfp: gfp mask
* @bs: bio set to allocate from
*
* Allocates and returns a new bio which represents @sectors from the start of
* @bio, and updates @bio to represent the remaining sectors.
*
* Unless this is a discard request the newly allocated bio will point
* to @bio's bi_io_vec. It is the caller's responsibility to ensure that
* neither @bio nor @bs are freed before the split bio.
*/
struct bio *bio_split(struct bio *bio, int sectors,
gfp_t gfp, struct bio_set *bs)
{
struct bio *split;
BUG_ON(sectors <= 0);
BUG_ON(sectors >= bio_sectors(bio));
block: Introduce REQ_OP_ZONE_APPEND Define REQ_OP_ZONE_APPEND to append-write sectors to a zone of a zoned block device. This is a no-merge write operation. A zone append write BIO must: * Target a zoned block device * Have a sector position indicating the start sector of the target zone * The target zone must be a sequential write zone * The BIO must not cross a zone boundary * The BIO size must not be split to ensure that a single range of LBAs is written with a single command. Implement these checks in generic_make_request_checks() using the helper function blk_check_zone_append(). To avoid write append BIO splitting, introduce the new max_zone_append_sectors queue limit attribute and ensure that a BIO size is always lower than this limit. Export this new limit through sysfs and check these limits in bio_full(). Also when a LLDD can't dispatch a request to a specific zone, it will return BLK_STS_ZONE_RESOURCE indicating this request needs to be delayed, e.g. because the zone it will be dispatched to is still write-locked. If this happens set the request aside in a local list to continue trying dispatching requests such as READ requests or a WRITE/ZONE_APPEND requests targetting other zones. This way we can still keep a high queue depth without starving other requests even if one request can't be served due to zone write-locking. Finally, make sure that the bio sector position indicates the actual write position as indicated by the device on completion. Signed-off-by: Keith Busch <kbusch@kernel.org> [ jth: added zone-append specific add_page and merge_page helpers ] Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-05-12 08:55:47 +00:00
/* Zone append commands cannot be split */
if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND))
return NULL;
split = bio_alloc_clone(bio->bi_bdev, bio, gfp, bs);
if (!split)
return NULL;
split->bi_iter.bi_size = sectors << 9;
if (bio_integrity(split))
bio_integrity_trim(split);
bio_advance(bio, split->bi_iter.bi_size);
block: trace completion of all bios. Currently only dm and md/raid5 bios trigger trace_block_bio_complete(). Now that we have bio_chain() and bio_inc_remaining(), it is not possible, in general, for a driver to know when the bio is really complete. Only bio_endio() knows that. So move the trace_block_bio_complete() call to bio_endio(). Now trace_block_bio_complete() pairs with trace_block_bio_queue(). Any bio for which a 'queue' event is traced, will subsequently generate a 'complete' event. There are a few cases where completion tracing is not wanted. 1/ If blk_update_request() has already generated a completion trace event at the 'request' level, there is no point generating one at the bio level too. In this case the bi_sector and bi_size will have changed, so the bio level event would be wrong 2/ If the bio hasn't actually been queued yet, but is being aborted early, then a trace event could be confusing. Some filesystems call bio_endio() but do not want tracing. 3/ The bio_integrity code interposes itself by replacing bi_end_io, then restoring it and calling bio_endio() again. This would produce two identical trace events if left like that. To handle these, we introduce a flag BIO_TRACE_COMPLETION and only produce the trace event when this is set. We address point 1 above by clearing the flag in blk_update_request(). We address point 2 above by only setting the flag when generic_make_request() is called. We address point 3 above by clearing the flag after generating a completion event. When bio_split() is used on a bio, particularly in blk_queue_split(), there is an extra complication. A new bio is split off the front, and may be handle directly without going through generic_make_request(). The old bio, which has been advanced, is passed to generic_make_request(), so it will trigger a trace event a second time. Probably the best result when a split happens is to see a single 'queue' event for the whole bio, then multiple 'complete' events - one for each component. To achieve this was can: - copy the BIO_TRACE_COMPLETION flag to the new bio in bio_split() - avoid generating a 'queue' event if BIO_TRACE_COMPLETION is already set. This way, the split-off bio won't create a queue event, the original won't either even if it re-submitted to generic_make_request(), but both will produce completion events, each for their own range. So if generic_make_request() is called (which generates a QUEUED event), then bi_endio() will create a single COMPLETE event for each range that the bio is split into, unless the driver has explicitly requested it not to. Signed-off-by: NeilBrown <neilb@suse.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-07 15:40:52 +00:00
if (bio_flagged(bio, BIO_TRACE_COMPLETION))
bio_set_flag(split, BIO_TRACE_COMPLETION);
block: trace completion of all bios. Currently only dm and md/raid5 bios trigger trace_block_bio_complete(). Now that we have bio_chain() and bio_inc_remaining(), it is not possible, in general, for a driver to know when the bio is really complete. Only bio_endio() knows that. So move the trace_block_bio_complete() call to bio_endio(). Now trace_block_bio_complete() pairs with trace_block_bio_queue(). Any bio for which a 'queue' event is traced, will subsequently generate a 'complete' event. There are a few cases where completion tracing is not wanted. 1/ If blk_update_request() has already generated a completion trace event at the 'request' level, there is no point generating one at the bio level too. In this case the bi_sector and bi_size will have changed, so the bio level event would be wrong 2/ If the bio hasn't actually been queued yet, but is being aborted early, then a trace event could be confusing. Some filesystems call bio_endio() but do not want tracing. 3/ The bio_integrity code interposes itself by replacing bi_end_io, then restoring it and calling bio_endio() again. This would produce two identical trace events if left like that. To handle these, we introduce a flag BIO_TRACE_COMPLETION and only produce the trace event when this is set. We address point 1 above by clearing the flag in blk_update_request(). We address point 2 above by only setting the flag when generic_make_request() is called. We address point 3 above by clearing the flag after generating a completion event. When bio_split() is used on a bio, particularly in blk_queue_split(), there is an extra complication. A new bio is split off the front, and may be handle directly without going through generic_make_request(). The old bio, which has been advanced, is passed to generic_make_request(), so it will trigger a trace event a second time. Probably the best result when a split happens is to see a single 'queue' event for the whole bio, then multiple 'complete' events - one for each component. To achieve this was can: - copy the BIO_TRACE_COMPLETION flag to the new bio in bio_split() - avoid generating a 'queue' event if BIO_TRACE_COMPLETION is already set. This way, the split-off bio won't create a queue event, the original won't either even if it re-submitted to generic_make_request(), but both will produce completion events, each for their own range. So if generic_make_request() is called (which generates a QUEUED event), then bi_endio() will create a single COMPLETE event for each range that the bio is split into, unless the driver has explicitly requested it not to. Signed-off-by: NeilBrown <neilb@suse.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-07 15:40:52 +00:00
return split;
}
EXPORT_SYMBOL(bio_split);
/**
* bio_trim - trim a bio
* @bio: bio to trim
* @offset: number of sectors to trim from the front of @bio
* @size: size we want to trim @bio to, in sectors
*
* This function is typically used for bios that are cloned and submitted
* to the underlying device in parts.
*/
void bio_trim(struct bio *bio, sector_t offset, sector_t size)
{
if (WARN_ON_ONCE(offset > BIO_MAX_SECTORS || size > BIO_MAX_SECTORS ||
offset + size > bio_sectors(bio)))
return;
size <<= 9;
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
2013-10-11 22:44:27 +00:00
if (offset == 0 && size == bio->bi_iter.bi_size)
return;
bio_advance(bio, offset << 9);
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
2013-10-11 22:44:27 +00:00
bio->bi_iter.bi_size = size;
if (bio_integrity(bio))
bio_integrity_trim(bio);
}
EXPORT_SYMBOL_GPL(bio_trim);
/*
* create memory pools for biovec's in a bio_set.
* use the global biovec slabs created for general use.
*/
int biovec_init_pool(mempool_t *pool, int pool_entries)
{
struct biovec_slab *bp = bvec_slabs + ARRAY_SIZE(bvec_slabs) - 1;
return mempool_init_slab_pool(pool, pool_entries, bp->slab);
}
/*
* bioset_exit - exit a bioset initialized with bioset_init()
*
* May be called on a zeroed but uninitialized bioset (i.e. allocated with
* kzalloc()).
*/
void bioset_exit(struct bio_set *bs)
{
bio_alloc_cache_destroy(bs);
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-10 21:33:46 +00:00
if (bs->rescue_workqueue)
destroy_workqueue(bs->rescue_workqueue);
bs->rescue_workqueue = NULL;
block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet <koverstreet@google.com> CC: Jens Axboe <axboe@kernel.dk> Acked-by: Tejun Heo <tj@kernel.org> Reviewed-by: Muthukumar Ratty <muthur@gmail.com>
2012-09-10 21:33:46 +00:00
mempool_exit(&bs->bio_pool);
mempool_exit(&bs->bvec_pool);
bioset_integrity_free(bs);
if (bs->bio_slab)
bio_put_slab(bs);
bs->bio_slab = NULL;
}
EXPORT_SYMBOL(bioset_exit);
/**
* bioset_init - Initialize a bio_set
* @bs: pool to initialize
* @pool_size: Number of bio and bio_vecs to cache in the mempool
* @front_pad: Number of bytes to allocate in front of the returned bio
* @flags: Flags to modify behavior, currently %BIOSET_NEED_BVECS
* and %BIOSET_NEED_RESCUER
*
* Description:
* Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
* to ask for a number of bytes to be allocated in front of the bio.
* Front pad allocation is useful for embedding the bio inside
* another structure, to avoid allocating extra data to go with the bio.
* Note that the bio must be embedded at the END of that structure always,
* or things will break badly.
* If %BIOSET_NEED_BVECS is set in @flags, a separate pool will be allocated
* for allocating iovecs. This pool is not needed e.g. for bio_init_clone().
* If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used
* to dispatch queued requests when the mempool runs out of space.
*
*/
int bioset_init(struct bio_set *bs,
unsigned int pool_size,
unsigned int front_pad,
int flags)
{
bs->front_pad = front_pad;
if (flags & BIOSET_NEED_BVECS)
bs->back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec);
else
bs->back_pad = 0;
spin_lock_init(&bs->rescue_lock);
bio_list_init(&bs->rescue_list);
INIT_WORK(&bs->rescue_work, bio_alloc_rescue);
bs->bio_slab = bio_find_or_create_slab(bs);
if (!bs->bio_slab)
return -ENOMEM;
if (mempool_init_slab_pool(&bs->bio_pool, pool_size, bs->bio_slab))
goto bad;
if ((flags & BIOSET_NEED_BVECS) &&
biovec_init_pool(&bs->bvec_pool, pool_size))
goto bad;
if (flags & BIOSET_NEED_RESCUER) {
bs->rescue_workqueue = alloc_workqueue("bioset",
WQ_MEM_RECLAIM, 0);
if (!bs->rescue_workqueue)
goto bad;
}
if (flags & BIOSET_PERCPU_CACHE) {
bs->cache = alloc_percpu(struct bio_alloc_cache);
if (!bs->cache)
goto bad;
cpuhp_state_add_instance_nocalls(CPUHP_BIO_DEAD, &bs->cpuhp_dead);
}
return 0;
bad:
bioset_exit(bs);
return -ENOMEM;
}
EXPORT_SYMBOL(bioset_init);
static int __init init_bio(void)
{
int i;
BUILD_BUG_ON(BIO_FLAG_LAST > 8 * sizeof_field(struct bio, bi_flags));
bio_integrity_init();
for (i = 0; i < ARRAY_SIZE(bvec_slabs); i++) {
struct biovec_slab *bvs = bvec_slabs + i;
bvs->slab = kmem_cache_create(bvs->name,
bvs->nr_vecs * sizeof(struct bio_vec), 0,
SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
}
cpuhp_setup_state_multi(CPUHP_BIO_DEAD, "block/bio:dead", NULL,
bio_cpu_dead);
if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0,
BIOSET_NEED_BVECS | BIOSET_PERCPU_CACHE))
panic("bio: can't allocate bios\n");
if (bioset_integrity_create(&fs_bio_set, BIO_POOL_SIZE))
panic("bio: can't create integrity pool\n");
return 0;
}
subsys_initcall(init_bio);