mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-27 11:19:37 +00:00
![Tejun Heo](/assets/img/avatar_default.png)
In several places, bdi_congested() and its wrappers are used to determine whether more IOs should be issued. With cgroup writeback support, this question can't be answered solely based on the bdi (backing_dev_info). It's dependent on whether the filesystem and bdi support cgroup writeback and the blkcg the inode is associated with. This patch implements inode_congested() and its wrappers which take @inode and determines the congestion state considering cgroup writeback. The new functions replace bdi_*congested() calls in places where the query is about specific inode and task. There are several filesystem users which also fit this criteria but they should be updated when each filesystem implements cgroup writeback support. v2: Now that a given inode is associated with only one wb, congestion state can be determined independent from the asking task. Drop @task. Spotted by Vivek. Also, converted to take @inode instead of @mapping and renamed to inode_congested(). Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Jan Kara <jack@suse.cz> Cc: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <axboe@fb.com>
162 lines
3.7 KiB
C
162 lines
3.7 KiB
C
/*
|
|
* mm/fadvise.c
|
|
*
|
|
* Copyright (C) 2002, Linus Torvalds
|
|
*
|
|
* 11Jan2003 Andrew Morton
|
|
* Initial version.
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/file.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/backing-dev.h>
|
|
#include <linux/pagevec.h>
|
|
#include <linux/fadvise.h>
|
|
#include <linux/writeback.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/swap.h>
|
|
|
|
#include <asm/unistd.h>
|
|
|
|
/*
|
|
* POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could
|
|
* deactivate the pages and clear PG_Referenced.
|
|
*/
|
|
SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
|
|
{
|
|
struct fd f = fdget(fd);
|
|
struct inode *inode;
|
|
struct address_space *mapping;
|
|
struct backing_dev_info *bdi;
|
|
loff_t endbyte; /* inclusive */
|
|
pgoff_t start_index;
|
|
pgoff_t end_index;
|
|
unsigned long nrpages;
|
|
int ret = 0;
|
|
|
|
if (!f.file)
|
|
return -EBADF;
|
|
|
|
inode = file_inode(f.file);
|
|
if (S_ISFIFO(inode->i_mode)) {
|
|
ret = -ESPIPE;
|
|
goto out;
|
|
}
|
|
|
|
mapping = f.file->f_mapping;
|
|
if (!mapping || len < 0) {
|
|
ret = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
if (IS_DAX(inode)) {
|
|
switch (advice) {
|
|
case POSIX_FADV_NORMAL:
|
|
case POSIX_FADV_RANDOM:
|
|
case POSIX_FADV_SEQUENTIAL:
|
|
case POSIX_FADV_WILLNEED:
|
|
case POSIX_FADV_NOREUSE:
|
|
case POSIX_FADV_DONTNEED:
|
|
/* no bad return value, but ignore advice */
|
|
break;
|
|
default:
|
|
ret = -EINVAL;
|
|
}
|
|
goto out;
|
|
}
|
|
|
|
/* Careful about overflows. Len == 0 means "as much as possible" */
|
|
endbyte = offset + len;
|
|
if (!len || endbyte < len)
|
|
endbyte = -1;
|
|
else
|
|
endbyte--; /* inclusive */
|
|
|
|
bdi = inode_to_bdi(mapping->host);
|
|
|
|
switch (advice) {
|
|
case POSIX_FADV_NORMAL:
|
|
f.file->f_ra.ra_pages = bdi->ra_pages;
|
|
spin_lock(&f.file->f_lock);
|
|
f.file->f_mode &= ~FMODE_RANDOM;
|
|
spin_unlock(&f.file->f_lock);
|
|
break;
|
|
case POSIX_FADV_RANDOM:
|
|
spin_lock(&f.file->f_lock);
|
|
f.file->f_mode |= FMODE_RANDOM;
|
|
spin_unlock(&f.file->f_lock);
|
|
break;
|
|
case POSIX_FADV_SEQUENTIAL:
|
|
f.file->f_ra.ra_pages = bdi->ra_pages * 2;
|
|
spin_lock(&f.file->f_lock);
|
|
f.file->f_mode &= ~FMODE_RANDOM;
|
|
spin_unlock(&f.file->f_lock);
|
|
break;
|
|
case POSIX_FADV_WILLNEED:
|
|
/* First and last PARTIAL page! */
|
|
start_index = offset >> PAGE_CACHE_SHIFT;
|
|
end_index = endbyte >> PAGE_CACHE_SHIFT;
|
|
|
|
/* Careful about overflow on the "+1" */
|
|
nrpages = end_index - start_index + 1;
|
|
if (!nrpages)
|
|
nrpages = ~0UL;
|
|
|
|
/*
|
|
* Ignore return value because fadvise() shall return
|
|
* success even if filesystem can't retrieve a hint,
|
|
*/
|
|
force_page_cache_readahead(mapping, f.file, start_index,
|
|
nrpages);
|
|
break;
|
|
case POSIX_FADV_NOREUSE:
|
|
break;
|
|
case POSIX_FADV_DONTNEED:
|
|
if (!inode_write_congested(mapping->host))
|
|
__filemap_fdatawrite_range(mapping, offset, endbyte,
|
|
WB_SYNC_NONE);
|
|
|
|
/*
|
|
* First and last FULL page! Partial pages are deliberately
|
|
* preserved on the expectation that it is better to preserve
|
|
* needed memory than to discard unneeded memory.
|
|
*/
|
|
start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
|
|
end_index = (endbyte >> PAGE_CACHE_SHIFT);
|
|
|
|
if (end_index >= start_index) {
|
|
unsigned long count = invalidate_mapping_pages(mapping,
|
|
start_index, end_index);
|
|
|
|
/*
|
|
* If fewer pages were invalidated than expected then
|
|
* it is possible that some of the pages were on
|
|
* a per-cpu pagevec for a remote CPU. Drain all
|
|
* pagevecs and try again.
|
|
*/
|
|
if (count < (end_index - start_index + 1)) {
|
|
lru_add_drain_all();
|
|
invalidate_mapping_pages(mapping, start_index,
|
|
end_index);
|
|
}
|
|
}
|
|
break;
|
|
default:
|
|
ret = -EINVAL;
|
|
}
|
|
out:
|
|
fdput(f);
|
|
return ret;
|
|
}
|
|
|
|
#ifdef __ARCH_WANT_SYS_FADVISE64
|
|
|
|
SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice)
|
|
{
|
|
return sys_fadvise64_64(fd, offset, len, advice);
|
|
}
|
|
|
|
#endif
|