1
linux/mm/fadvise.c
Al Viro 1da91ea87a introduce fd_file(), convert all accessors to it.
For any changes of struct fd representation we need to
turn existing accesses to fields into calls of wrappers.
Accesses to struct fd::flags are very few (3 in linux/file.h,
1 in net/socket.c, 3 in fs/overlayfs/file.c and 3 more in
explicit initializers).
	Those can be dealt with in the commit converting to
new layout; accesses to struct fd::file are too many for that.
	This commit converts (almost) all of f.file to
fd_file(f).  It's not entirely mechanical ('file' is used as
a member name more than just in struct fd) and it does not
even attempt to distinguish the uses in pointer context from
those in boolean context; the latter will be eventually turned
into a separate helper (fd_empty()).

	NOTE: mass conversion to fd_empty(), tempting as it
might be, is a bad idea; better do that piecewise in commit
that convert from fdget...() to CLASS(...).

[conflicts in fs/fhandle.c, kernel/bpf/syscall.c, mm/memcontrol.c
caught by git; fs/stat.c one got caught by git grep]
[fs/xattr.c conflict]

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2024-08-12 22:00:43 -04:00

230 lines
5.5 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* 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/fadvise.h>
#include <linux/writeback.h>
#include <linux/syscalls.h>
#include <linux/swap.h>
#include <asm/unistd.h>
#include "internal.h"
/*
* POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could
* deactivate the pages and clear PG_Referenced.
*/
int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
{
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;
inode = file_inode(file);
if (S_ISFIFO(inode->i_mode))
return -ESPIPE;
mapping = file->f_mapping;
if (!mapping || len < 0)
return -EINVAL;
bdi = inode_to_bdi(mapping->host);
if (IS_DAX(inode) || (bdi == &noop_backing_dev_info)) {
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:
return -EINVAL;
}
return 0;
}
/*
* Careful about overflows. Len == 0 means "as much as possible". Use
* unsigned math because signed overflows are undefined and UBSan
* complains.
*/
endbyte = (u64)offset + (u64)len;
if (!len || endbyte < len)
endbyte = LLONG_MAX;
else
endbyte--; /* inclusive */
switch (advice) {
case POSIX_FADV_NORMAL:
file->f_ra.ra_pages = bdi->ra_pages;
spin_lock(&file->f_lock);
file->f_mode &= ~(FMODE_RANDOM | FMODE_NOREUSE);
spin_unlock(&file->f_lock);
break;
case POSIX_FADV_RANDOM:
spin_lock(&file->f_lock);
file->f_mode |= FMODE_RANDOM;
spin_unlock(&file->f_lock);
break;
case POSIX_FADV_SEQUENTIAL:
file->f_ra.ra_pages = bdi->ra_pages * 2;
spin_lock(&file->f_lock);
file->f_mode &= ~FMODE_RANDOM;
spin_unlock(&file->f_lock);
break;
case POSIX_FADV_WILLNEED:
/* First and last PARTIAL page! */
start_index = offset >> PAGE_SHIFT;
end_index = endbyte >> PAGE_SHIFT;
/* Careful about overflow on the "+1" */
nrpages = end_index - start_index + 1;
if (!nrpages)
nrpages = ~0UL;
force_page_cache_readahead(mapping, file, start_index, nrpages);
break;
case POSIX_FADV_NOREUSE:
spin_lock(&file->f_lock);
file->f_mode |= FMODE_NOREUSE;
spin_unlock(&file->f_lock);
break;
case POSIX_FADV_DONTNEED:
__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_SIZE-1)) >> PAGE_SHIFT;
end_index = (endbyte >> PAGE_SHIFT);
/*
* The page at end_index will be inclusively discarded according
* by invalidate_mapping_pages(), so subtracting 1 from
* end_index means we will skip the last page. But if endbyte
* is page aligned or is at the end of file, we should not skip
* that page - discarding the last page is safe enough.
*/
if ((endbyte & ~PAGE_MASK) != ~PAGE_MASK &&
endbyte != inode->i_size - 1) {
/* First page is tricky as 0 - 1 = -1, but pgoff_t
* is unsigned, so the end_index >= start_index
* check below would be true and we'll discard the whole
* file cache which is not what was asked.
*/
if (end_index == 0)
break;
end_index--;
}
if (end_index >= start_index) {
unsigned long nr_failed = 0;
/*
* It's common to FADV_DONTNEED right after
* the read or write that instantiates the
* pages, in which case there will be some
* sitting on the local LRU cache. Try to
* avoid the expensive remote drain and the
* second cache tree walk below by flushing
* them out right away.
*/
lru_add_drain();
mapping_try_invalidate(mapping, start_index, end_index,
&nr_failed);
/*
* The failures may be due to the folio being
* in the LRU cache of a remote CPU. Drain all
* caches and try again.
*/
if (nr_failed) {
lru_add_drain_all();
invalidate_mapping_pages(mapping, start_index,
end_index);
}
}
break;
default:
return -EINVAL;
}
return 0;
}
EXPORT_SYMBOL(generic_fadvise);
int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
{
if (file->f_op->fadvise)
return file->f_op->fadvise(file, offset, len, advice);
return generic_fadvise(file, offset, len, advice);
}
EXPORT_SYMBOL(vfs_fadvise);
#ifdef CONFIG_ADVISE_SYSCALLS
int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
{
struct fd f = fdget(fd);
int ret;
if (!fd_file(f))
return -EBADF;
ret = vfs_fadvise(fd_file(f), offset, len, advice);
fdput(f);
return ret;
}
SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
{
return ksys_fadvise64_64(fd, offset, len, advice);
}
#ifdef __ARCH_WANT_SYS_FADVISE64
SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice)
{
return ksys_fadvise64_64(fd, offset, len, advice);
}
#endif
#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_FADVISE64_64)
COMPAT_SYSCALL_DEFINE6(fadvise64_64, int, fd, compat_arg_u64_dual(offset),
compat_arg_u64_dual(len), int, advice)
{
return ksys_fadvise64_64(fd, compat_arg_u64_glue(offset),
compat_arg_u64_glue(len), advice);
}
#endif
#endif