hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[PATCH] separate bdi congestion functions from queue congestion functions 

Separate out the concept of "queue congestion" from "backing-dev congestion".
Congestion is a backing-dev concept, not a queue concept.

The blk_* congestion functions are retained, as wrappers around the core
backing-dev congestion functions.

This proper layering is needed so that NFS can cleanly use the congestion
functions, and so that CONFIG_BLOCK=n actually links.

Cc: "Thomas Maier" <balagi@justmail.de>
Cc: "Jens Axboe" <jens.axboe@oracle.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: David Howells <dhowells@redhat.com>
Cc: Peter Osterlund <petero2@telia.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This commit is contained in:
Andrew Morton 2006-10-19 23:28:16 -07:00 committed by Linus Torvalds
parent 79e2de4bc5
commit 3fcfab16c5
17 changed files with 126 additions and 104 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
arch/i386/lib/usercopy.c
View File

@ -9,6 +9,7 @@
#include <linux/highmem.h>
#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <asm/uaccess.h>
#include <asm/mmx.h>
@ -741,7 +742,7 @@ survive:
if (retval == -ENOMEM && is_init(current)) {
up_read(&current->mm->mmap_sem);
blk_congestion_wait(WRITE, HZ/50);
congestion_wait(WRITE, HZ/50);
goto survive;
}

71
block/ll_rw_blk.c
View File

@ -56,11 +56,6 @@ static kmem_cache_t *requestq_cachep;
*/
static kmem_cache_t *iocontext_cachep;
static wait_queue_head_t congestion_wqh[2] = {
__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
};
/*
* Controlling structure to kblockd
*/
@ -112,37 +107,6 @@ static void blk_queue_congestion_threshold(struct request_queue *q)
q->nr_congestion_off = nr;
}
/*
* A queue has just exitted congestion. Note this in the global counter of
* congested queues, and wake up anyone who was waiting for requests to be
* put back.
*/
void blk_clear_queue_congested(request_queue_t *q, int rw)
{
enum bdi_state bit;
wait_queue_head_t *wqh = &congestion_wqh[rw];
bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
clear_bit(bit, &q->backing_dev_info.state);
smp_mb__after_clear_bit();
if (waitqueue_active(wqh))
wake_up(wqh);
}
EXPORT_SYMBOL(blk_clear_queue_congested);
/*
* A queue has just entered congestion. Flag that in the queue's VM-visible
* state flags and increment the global gounter of congested queues.
*/
void blk_set_queue_congested(request_queue_t *q, int rw)
{
enum bdi_state bit;
bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
set_bit(bit, &q->backing_dev_info.state);
}
EXPORT_SYMBOL(blk_set_queue_congested);
/**
* blk_get_backing_dev_info - get the address of a queue's backing_dev_info
* @bdev: device
@ -2755,41 +2719,6 @@ void blk_end_sync_rq(struct request *rq, int error)
}
EXPORT_SYMBOL(blk_end_sync_rq);
/**
* blk_congestion_wait - wait for a queue to become uncongested
* @rw: READ or WRITE
* @timeout: timeout in jiffies
*
* Waits for up to @timeout jiffies for a queue (any queue) to exit congestion.
* If no queues are congested then just wait for the next request to be
* returned.
*/
long blk_congestion_wait(int rw, long timeout)
{
long ret;
DEFINE_WAIT(wait);
wait_queue_head_t *wqh = &congestion_wqh[rw];
prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
ret = io_schedule_timeout(timeout);
finish_wait(wqh, &wait);
return ret;
}
EXPORT_SYMBOL(blk_congestion_wait);
/**
* blk_congestion_end - wake up sleepers on a congestion queue
* @rw: READ or WRITE
*/
void blk_congestion_end(int rw)
{
wait_queue_head_t *wqh = &congestion_wqh[rw];
if (waitqueue_active(wqh))
wake_up(wqh);
}
/*
* Has to be called with the request spinlock acquired
*/

3
drivers/md/dm-crypt.c
View File

@ -16,6 +16,7 @@
#include <linux/slab.h>
#include <linux/crypto.h>
#include <linux/workqueue.h>
#include <linux/backing-dev.h>
#include <asm/atomic.h>
#include <linux/scatterlist.h>
#include <asm/page.h>
@ -602,7 +603,7 @@ static void process_write(struct crypt_io *io)
/* out of memory -> run queues */
if (remaining)
blk_congestion_wait(bio_data_dir(clone), HZ/100);
congestion_wait(bio_data_dir(clone), HZ/100);
}
}

3
fs/fat/file.c
View File

@ -13,6 +13,7 @@
#include <linux/smp_lock.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/blkdev.h>
int fat_generic_ioctl(struct inode *inode, struct file *filp,
@ -118,7 +119,7 @@ static int fat_file_release(struct inode *inode, struct file *filp)
if ((filp->f_mode & FMODE_WRITE) &&
MSDOS_SB(inode->i_sb)->options.flush) {
fat_flush_inodes(inode->i_sb, inode, NULL);
blk_congestion_wait(WRITE, HZ/10);
congestion_wait(WRITE, HZ/10);
}
return 0;
}

4
fs/nfs/write.c
View File

@ -57,6 +57,8 @@
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/nfs_page.h>
#include <linux/backing-dev.h>
#include <asm/uaccess.h>
#include <linux/smp_lock.h>
@ -395,7 +397,7 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
out:
clear_bit(BDI_write_congested, &bdi->state);
wake_up_all(&nfs_write_congestion);
writeback_congestion_end();
congestion_end(WRITE);
return err;
}

3
fs/reiserfs/journal.c
View File

@ -53,6 +53,7 @@
#include <linux/workqueue.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
/* gets a struct reiserfs_journal_list * from a list head */
#define JOURNAL_LIST_ENTRY(h) (list_entry((h), struct reiserfs_journal_list, \
@ -970,7 +971,7 @@ int reiserfs_async_progress_wait(struct super_block *s)
DEFINE_WAIT(wait);
struct reiserfs_journal *j = SB_JOURNAL(s);
if (atomic_read(&j->j_async_throttle))
blk_congestion_wait(WRITE, HZ / 10);
congestion_wait(WRITE, HZ / 10);
return 0;
}

5
fs/xfs/linux-2.6/kmem.c
View File

@ -21,6 +21,7 @@
#include <linux/highmem.h>
#include <linux/swap.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include "time.h"
#include "kmem.h"
@ -53,7 +54,7 @@ kmem_alloc(size_t size, unsigned int __nocast flags)
printk(KERN_ERR "XFS: possible memory allocation "
"deadlock in %s (mode:0x%x)\n",
__FUNCTION__, lflags);
blk_congestion_wait(WRITE, HZ/50);
congestion_wait(WRITE, HZ/50);
} while (1);
}
@ -131,7 +132,7 @@ kmem_zone_alloc(kmem_zone_t *zone, unsigned int __nocast flags)
printk(KERN_ERR "XFS: possible memory allocation "
"deadlock in %s (mode:0x%x)\n",
__FUNCTION__, lflags);
blk_congestion_wait(WRITE, HZ/50);
congestion_wait(WRITE, HZ/50);
} while (1);
}

3
fs/xfs/linux-2.6/xfs_buf.c
View File

@ -30,6 +30,7 @@
#include <linux/hash.h>
#include <linux/kthread.h>
#include <linux/migrate.h>
#include <linux/backing-dev.h>
#include "xfs_linux.h"
STATIC kmem_zone_t *xfs_buf_zone;
@ -395,7 +396,7 @@ _xfs_buf_lookup_pages(
XFS_STATS_INC(xb_page_retries);
xfsbufd_wakeup(0, gfp_mask);
blk_congestion_wait(WRITE, HZ/50);
congestion_wait(WRITE, HZ/50);
goto retry;
}

7
include/linux/backing-dev.h
View File

@ -10,6 +10,8 @@
#include <asm/atomic.h>
struct page;
/*
* Bits in backing_dev_info.state
*/
@ -88,6 +90,11 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi)
(1 << BDI_write_congested));
}
void clear_bdi_congested(struct backing_dev_info *bdi, int rw);
void set_bdi_congested(struct backing_dev_info *bdi, int rw);
long congestion_wait(int rw, long timeout);
void congestion_end(int rw);
#define bdi_cap_writeback_dirty(bdi) \
(!((bdi)->capabilities & BDI_CAP_NO_WRITEBACK))

24
include/linux/blkdev.h
View File

@ -651,8 +651,26 @@ extern void blk_recount_segments(request_queue_t *, struct bio *);
extern int scsi_cmd_ioctl(struct file *, struct gendisk *, unsigned int, void __user *);
extern int sg_scsi_ioctl(struct file *, struct request_queue *,
struct gendisk *, struct scsi_ioctl_command __user *);
extern void blk_clear_queue_congested(request_queue_t *q, int rw);
extern void blk_set_queue_congested(request_queue_t *q, int rw);
/*
* A queue has just exitted congestion. Note this in the global counter of
* congested queues, and wake up anyone who was waiting for requests to be
* put back.
*/
static inline void blk_clear_queue_congested(request_queue_t *q, int rw)
{
clear_bdi_congested(&q->backing_dev_info, rw);
}
/*
* A queue has just entered congestion. Flag that in the queue's VM-visible
* state flags and increment the global gounter of congested queues.
*/
static inline void blk_set_queue_congested(request_queue_t *q, int rw)
{
set_bdi_congested(&q->backing_dev_info, rw);
}
extern void blk_start_queue(request_queue_t *q);
extern void blk_stop_queue(request_queue_t *q);
extern void blk_sync_queue(struct request_queue *q);
@ -767,10 +785,8 @@ extern int blk_queue_init_tags(request_queue_t *, int, struct blk_queue_tag *);
extern void blk_queue_free_tags(request_queue_t *);
extern int blk_queue_resize_tags(request_queue_t *, int);
extern void blk_queue_invalidate_tags(request_queue_t *);
extern long blk_congestion_wait(int rw, long timeout);
extern struct blk_queue_tag *blk_init_tags(int);
extern void blk_free_tags(struct blk_queue_tag *);
extern void blk_congestion_end(int rw);
static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
int tag)

1
include/linux/writeback.h
View File

@ -85,7 +85,6 @@ int wakeup_pdflush(long nr_pages);
void laptop_io_completion(void);
void laptop_sync_completion(void);
void throttle_vm_writeout(void);
void writeback_congestion_end(void);
/* These are exported to sysctl. */
extern int dirty_background_ratio;

3
mm/Makefile
View File

@ -10,7 +10,8 @@ mmu-$(CONFIG_MMU) := fremap.o highmem.o madvise.o memory.o mincore.o \
obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
page_alloc.o page-writeback.o pdflush.o \
readahead.o swap.o truncate.o vmscan.o \
prio_tree.o util.o mmzone.o vmstat.o $(mmu-y)
prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
$(mmu-y)
ifeq ($(CONFIG_MMU)$(CONFIG_BLOCK),yy)
obj-y += bounce.o

69
mm/backing-dev.c Normal file
View File

@ -0,0 +1,69 @@
#include <linux/wait.h>
#include <linux/backing-dev.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/module.h>
static wait_queue_head_t congestion_wqh[2] = {
__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
};
void clear_bdi_congested(struct backing_dev_info *bdi, int rw)
{
enum bdi_state bit;
wait_queue_head_t *wqh = &congestion_wqh[rw];
bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
clear_bit(bit, &bdi->state);
smp_mb__after_clear_bit();
if (waitqueue_active(wqh))
wake_up(wqh);
}
EXPORT_SYMBOL(clear_bdi_congested);
void set_bdi_congested(struct backing_dev_info *bdi, int rw)
{
enum bdi_state bit;
bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
set_bit(bit, &bdi->state);
}
EXPORT_SYMBOL(set_bdi_congested);
/**
* congestion_wait - wait for a backing_dev to become uncongested
* @rw: READ or WRITE
* @timeout: timeout in jiffies
*
* Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit
* write congestion. If no backing_devs are congested then just wait for the
* next write to be completed.
*/
long congestion_wait(int rw, long timeout)
{
long ret;
DEFINE_WAIT(wait);
wait_queue_head_t *wqh = &congestion_wqh[rw];
prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
ret = io_schedule_timeout(timeout);
finish_wait(wqh, &wait);
return ret;
}
EXPORT_SYMBOL(congestion_wait);
/**
* congestion_end - wake up sleepers on a congested backing_dev_info
* @rw: READ or WRITE
*/
void congestion_end(int rw)
{
wait_queue_head_t *wqh = &congestion_wqh[rw];
if (waitqueue_active(wqh))
wake_up(wqh);
}
EXPORT_SYMBOL(congestion_end);

17
mm/page-writeback.c
View File

@ -222,7 +222,7 @@ static void balance_dirty_pages(struct address_space *mapping)
if (pages_written >= write_chunk)
break; /* We've done our duty */
}
blk_congestion_wait(WRITE, HZ/10);
congestion_wait(WRITE, HZ/10);
}
if (nr_reclaimable + global_page_state(NR_WRITEBACK)
@ -314,7 +314,7 @@ void throttle_vm_writeout(void)
if (global_page_state(NR_UNSTABLE_NFS) +
global_page_state(NR_WRITEBACK) <= dirty_thresh)
break;
blk_congestion_wait(WRITE, HZ/10);
congestion_wait(WRITE, HZ/10);
}
}
@ -351,7 +351,7 @@ static void background_writeout(unsigned long _min_pages)
min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
/* Wrote less than expected */
blk_congestion_wait(WRITE, HZ/10);
congestion_wait(WRITE, HZ/10);
if (!wbc.encountered_congestion)
break;
}
@ -422,7 +422,7 @@ static void wb_kupdate(unsigned long arg)
writeback_inodes(&wbc);
if (wbc.nr_to_write > 0) {
if (wbc.encountered_congestion)
blk_congestion_wait(WRITE, HZ/10);
congestion_wait(WRITE, HZ/10);
else
break; /* All the old data is written */
}
@ -955,15 +955,6 @@ int test_set_page_writeback(struct page *page)
}
EXPORT_SYMBOL(test_set_page_writeback);
/*
* Wakes up tasks that are being throttled due to writeback congestion
*/
void writeback_congestion_end(void)
{
blk_congestion_end(WRITE);
}
EXPORT_SYMBOL(writeback_congestion_end);
/*
* Return true if any of the pages in the mapping are marged with the
* passed tag.

5
mm/page_alloc.c
View File

@ -39,6 +39,7 @@
#include <linux/stop_machine.h>
#include <linux/sort.h>
#include <linux/pfn.h>
#include <linux/backing-dev.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
@ -1050,7 +1051,7 @@ nofail_alloc:
if (page)
goto got_pg;
if (gfp_mask & __GFP_NOFAIL) {
blk_congestion_wait(WRITE, HZ/50);
congestion_wait(WRITE, HZ/50);
goto nofail_alloc;
}
}
@ -1113,7 +1114,7 @@ rebalance:
do_retry = 1;
}
if (do_retry) {
blk_congestion_wait(WRITE, HZ/50);
congestion_wait(WRITE, HZ/50);
goto rebalance;
}

3
mm/shmem.c
View File

@ -48,6 +48,7 @@
#include <linux/ctype.h>
#include <linux/migrate.h>
#include <linux/highmem.h>
#include <linux/backing-dev.h>
#include <asm/uaccess.h>
#include <asm/div64.h>
@ -1131,7 +1132,7 @@ repeat:
page_cache_release(swappage);
if (error == -ENOMEM) {
/* let kswapd refresh zone for GFP_ATOMICs */
blk_congestion_wait(WRITE, HZ/50);
congestion_wait(WRITE, HZ/50);
}
goto repeat;
}

6
mm/vmscan.c
View File

@ -1059,7 +1059,7 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
/* Take a nap, wait for some writeback to complete */
if (sc.nr_scanned && priority < DEF_PRIORITY - 2)
blk_congestion_wait(WRITE, HZ/10);
congestion_wait(WRITE, HZ/10);
}
/* top priority shrink_caches still had more to do? don't OOM, then */
if (!sc.all_unreclaimable)
@ -1214,7 +1214,7 @@ scan:
* another pass across the zones.
*/
if (total_scanned && priority < DEF_PRIORITY - 2)
blk_congestion_wait(WRITE, HZ/10);
congestion_wait(WRITE, HZ/10);
/*
* We do this so kswapd doesn't build up large priorities for
@ -1458,7 +1458,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
goto out;
if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
blk_congestion_wait(WRITE, HZ / 10);
congestion_wait(WRITE, HZ / 10);
}
lru_pages = 0;