summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-09-13 19:21:40 -1000
committerLinus Torvalds <torvalds@linux-foundation.org>2018-09-13 19:21:40 -1000
commit48751b562bce96c4284885571da1bdda7673f38e (patch)
treedbd845b16b7213cec7a42f6080193499a78cb850 /mm
parent4d8d9f540b780f7a3688a72275aecd8fd99c99e5 (diff)
parent8c25741aaad8be6fbe51510e917c740e0059cf83 (diff)
Merge tag 'ovl-fixes-4.19-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs
Pull overlayfs fixes from Miklos Szeredi: "This fixes a regression in the recent file stacking update, reported and fixed by Amir Goldstein. The fix is fairly trivial, but involves adding a fadvise() f_op and the associated churn in the vfs. As discussed on -fsdevel, there are other possible uses for this method, than allowing proper stacking for overlays. And there's one other fix for a syzkaller detected oops" * tag 'ovl-fixes-4.19-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs: ovl: fix oopses in ovl_fill_super() failure paths ovl: add ovl_fadvise() vfs: implement readahead(2) using POSIX_FADV_WILLNEED vfs: add the fadvise() file operation Documentation/filesystems: update documentation of file_operations ovl: fix GPF in swapfile_activate of file from overlayfs over xfs ovl: respect FIEMAP_FLAG_SYNC flag
Diffstat (limited to 'mm')
-rw-r--r--mm/Makefile3
-rw-r--r--mm/fadvise.c81
-rw-r--r--mm/readahead.c45
3 files changed, 66 insertions, 63 deletions
diff --git a/mm/Makefile b/mm/Makefile
index 8716bdabe1e6..26ef77a3883b 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -32,7 +32,7 @@ ifdef CONFIG_CROSS_MEMORY_ATTACH
mmu-$(CONFIG_MMU) += process_vm_access.o
endif
-obj-y := filemap.o mempool.o oom_kill.o \
+obj-y := filemap.o mempool.o oom_kill.o fadvise.o \
maccess.o page_alloc.o page-writeback.o \
readahead.o swap.o truncate.o vmscan.o shmem.o \
util.o mmzone.o vmstat.o backing-dev.o \
@@ -49,7 +49,6 @@ else
obj-y += bootmem.o
endif
-obj-$(CONFIG_ADVISE_SYSCALLS) += fadvise.o
ifdef CONFIG_MMU
obj-$(CONFIG_ADVISE_SYSCALLS) += madvise.o
endif
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 2d8376e3c640..467bcd032037 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -27,9 +27,9 @@
* deactivate the pages and clear PG_Referenced.
*/
-int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
+static 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;
@@ -37,22 +37,14 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
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;
- }
+ inode = file_inode(file);
+ if (S_ISFIFO(inode->i_mode))
+ return -ESPIPE;
- mapping = f.file->f_mapping;
- if (!mapping || len < 0) {
- ret = -EINVAL;
- goto out;
- }
+ mapping = file->f_mapping;
+ if (!mapping || len < 0)
+ return -EINVAL;
bdi = inode_to_bdi(mapping->host);
@@ -67,9 +59,9 @@ int ksys_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;
}
/*
@@ -85,21 +77,21 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
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;
+ 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! */
@@ -115,8 +107,7 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
* 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:
break;
@@ -183,9 +174,32 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
}
break;
default:
- ret = -EINVAL;
+ return -EINVAL;
}
-out:
+ return 0;
+}
+
+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 (!f.file)
+ return -EBADF;
+
+ ret = vfs_fadvise(f.file, offset, len, advice);
+
fdput(f);
return ret;
}
@@ -203,3 +217,4 @@ SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice)
}
#endif
+#endif
diff --git a/mm/readahead.c b/mm/readahead.c
index a59ea70527b9..4e630143a0ba 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -20,6 +20,7 @@
#include <linux/file.h>
#include <linux/mm_inline.h>
#include <linux/blk-cgroup.h>
+#include <linux/fadvise.h>
#include "internal.h"
@@ -575,24 +576,6 @@ page_cache_async_readahead(struct address_space *mapping,
}
EXPORT_SYMBOL_GPL(page_cache_async_readahead);
-static ssize_t
-do_readahead(struct address_space *mapping, struct file *filp,
- pgoff_t index, unsigned long nr)
-{
- if (!mapping || !mapping->a_ops)
- return -EINVAL;
-
- /*
- * Readahead doesn't make sense for DAX inodes, but we don't want it
- * to report a failure either. Instead, we just return success and
- * don't do any work.
- */
- if (dax_mapping(mapping))
- return 0;
-
- return force_page_cache_readahead(mapping, filp, index, nr);
-}
-
ssize_t ksys_readahead(int fd, loff_t offset, size_t count)
{
ssize_t ret;
@@ -600,16 +583,22 @@ ssize_t ksys_readahead(int fd, loff_t offset, size_t count)
ret = -EBADF;
f = fdget(fd);
- if (f.file) {
- if (f.file->f_mode & FMODE_READ) {
- struct address_space *mapping = f.file->f_mapping;
- pgoff_t start = offset >> PAGE_SHIFT;
- pgoff_t end = (offset + count - 1) >> PAGE_SHIFT;
- unsigned long len = end - start + 1;
- ret = do_readahead(mapping, f.file, start, len);
- }
- fdput(f);
- }
+ if (!f.file || !(f.file->f_mode & FMODE_READ))
+ goto out;
+
+ /*
+ * The readahead() syscall is intended to run only on files
+ * that can execute readahead. If readahead is not possible
+ * on this file, then we must return -EINVAL.
+ */
+ ret = -EINVAL;
+ if (!f.file->f_mapping || !f.file->f_mapping->a_ops ||
+ !S_ISREG(file_inode(f.file)->i_mode))
+ goto out;
+
+ ret = vfs_fadvise(f.file, offset, count, POSIX_FADV_WILLNEED);
+out:
+ fdput(f);
return ret;
}