summaryrefslogtreecommitdiff
path: root/mm/fadvise.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/fadvise.c')
-rw-r--r--mm/fadvise.c188
1 files changed, 128 insertions, 60 deletions
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 3bcfd81db45e..67028e30aa91 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* mm/fadvise.c
*
@@ -13,7 +14,6 @@
#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>
@@ -21,36 +21,34 @@
#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.
*/
-SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
+
+int generic_fadvise(struct file *file, 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(file);
+ if (S_ISFIFO(inode->i_mode))
+ return -ESPIPE;
- if (S_ISFIFO(file_inode(f.file)->i_mode)) {
- ret = -ESPIPE;
- goto out;
- }
+ mapping = file->f_mapping;
+ if (!mapping || len < 0)
+ return -EINVAL;
- mapping = f.file->f_mapping;
- if (!mapping || len < 0) {
- ret = -EINVAL;
- goto out;
- }
+ bdi = inode_to_bdi(mapping->host);
- if (mapping->a_ops->get_xip_mem) {
+ if (IS_DAX(inode) || (bdi == &noop_backing_dev_info)) {
switch (advice) {
case POSIX_FADV_NORMAL:
case POSIX_FADV_RANDOM:
@@ -61,77 +59,110 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
/* no bad return value, but ignore advice */
break;
default:
- ret = -EINVAL;
+ return -EINVAL;
}
- goto out;
+ return 0;
}
- /* Careful about overflows. Len == 0 means "as much as possible" */
- endbyte = offset + len;
+ /*
+ * 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 = -1;
+ endbyte = LLONG_MAX;
else
endbyte--; /* inclusive */
- bdi = mapping->backing_dev_info;
-
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);
+ 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(&f.file->f_lock);
- f.file->f_mode |= FMODE_RANDOM;
- spin_unlock(&f.file->f_lock);
+ spin_lock(&file->f_lock);
+ file->f_mode |= FMODE_RANDOM;
+ spin_unlock(&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);
+ 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_CACHE_SHIFT;
- end_index = endbyte >> PAGE_CACHE_SHIFT;
+ 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;
- /*
- * 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);
+ 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:
- if (!bdi_write_congested(mapping->backing_dev_info))
- __filemap_fdatawrite_range(mapping, offset, endbyte,
- WB_SYNC_NONE);
+ filemap_flush_range(mapping, offset, endbyte);
- /* First and last FULL page! */
- start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
- end_index = (endbyte >> PAGE_CACHE_SHIFT);
+ /*
+ * 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 count = invalidate_mapping_pages(mapping,
- start_index, end_index);
+ unsigned long nr_failed = 0;
/*
- * 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.
+ * 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.
*/
- if (count < (end_index - start_index + 1)) {
+ 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);
@@ -139,18 +170,55 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
}
break;
default:
- ret = -EINVAL;
+ return -EINVAL;
}
-out:
- fdput(f);
- return ret;
+ 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)
+{
+ CLASS(fd, f)(fd);
+
+ if (fd_empty(f))
+ return -EBADF;
+
+ return vfs_fadvise(fd_file(f), offset, len, advice);
+}
+
+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 sys_fadvise64_64(fd, offset, len, 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
generated by cgit (git 2.34.1) at 2025-12-21 21:50:35 +0000