The patch titled
fs: new truncate helpers
has been added to the -mm tree. Its filename is
fs-new-truncate-helpers.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: fs: new truncate helpers
From: Nick Piggin <npiggin@xxxxxxx>
Introduce new truncate helpers truncate_pagecache and inode_newsize_ok.
vmtruncate is also consolidated from mm/memory.c and mm/nommu.c and into
mm/truncate.c.
Signed-off-by: Nick Piggin <npiggin@xxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Dave Kleikamp <shaggy@xxxxxxxxxxxxxxxxxx>
Cc: Chris Mason <chris.mason@xxxxxxxxxx>
Cc: OGAWA Hirofumi <hirofumi@xxxxxxxxxxxxxxxxxx>
Cc: Hugh Dickins <hugh.dickins@xxxxxxxxxxxxx>
Cc: Miklos Szeredi <miklos@xxxxxxxxxx>
Cc: Trond Myklebust <trond.myklebust@xxxxxxxxxx>
Cc: Steven French <sfrench@xxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
Documentation/vm/locking | 2 -
fs/attr.c | 44 ++++++++++++++++++++++++-
include/linux/fs.h | 1
include/linux/mm.h | 5 +-
mm/filemap.c | 2 -
mm/memory.c | 62 +----------------------------------
mm/mremap.c | 4 +-
mm/nommu.c | 40 -----------------------
mm/truncate.c | 64 +++++++++++++++++++++++++++++++++++++
9 files changed, 118 insertions(+), 106 deletions(-)
diff -puN Documentation/vm/locking~fs-new-truncate-helpers Documentation/vm/locking
--- a/Documentation/vm/locking~fs-new-truncate-helpers
+++ a/Documentation/vm/locking
@@ -80,7 +80,7 @@ Note: PTL can also be used to guarantee
mm start up ... this is a loose form of stability on mm_users. For
example, it is used in copy_mm to protect against a racing tlb_gather_mmu
single address space optimization, so that the zap_page_range (from
-vmtruncate) does not lose sending ipi's to cloned threads that might
+truncate) does not lose sending ipi's to cloned threads that might
be spawned underneath it and go to user mode to drag in pte's into tlbs.
swap_lock
diff -puN fs/attr.c~fs-new-truncate-helpers fs/attr.c
--- a/fs/attr.c~fs-new-truncate-helpers
+++ a/fs/attr.c
@@ -60,9 +60,51 @@ fine:
error:
return retval;
}
-
EXPORT_SYMBOL(inode_change_ok);
+/**
+ * inode_newsize_ok - may this inode be truncated to a given size
+ * @inode: the inode to be truncated
+ * @offset: the new size to assign to the inode
+ * @Returns: 0 on success, -ve errno on failure
+ *
+ * inode_newsize_ok will check filesystem limits and ulimits to check that the
+ * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ
+ * when necessary. Caller must not proceed with inode size change if failure is
+ * returned. @inode must be a file (not directory), with appropriate
+ * permissions to allow truncate (inode_newsize_ok does NOT check these
+ * conditions).
+ *
+ * inode_newsize_ok must be called with i_mutex held.
+ */
+int inode_newsize_ok(struct inode *inode, loff_t offset)
+{
+ if (inode->i_size < offset) {
+ unsigned long limit;
+
+ limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
+ if (limit != RLIM_INFINITY && offset > limit)
+ goto out_sig;
+ if (offset > inode->i_sb->s_maxbytes)
+ goto out_big;
+ } else {
+ /*
+ * truncation of in-use swapfiles is disallowed - it would
+ * cause subsequent swapout to scribble on the now-freed
+ * blocks.
+ */
+ if (IS_SWAPFILE(inode))
+ return -ETXTBSY;
+ }
+
+ return 0;
+out_sig:
+ send_sig(SIGXFSZ, current, 0);
+out_big:
+ return -EFBIG;
+}
+EXPORT_SYMBOL(inode_newsize_ok);
+
int inode_setattr(struct inode * inode, struct iattr * attr)
{
unsigned int ia_valid = attr->ia_valid;
diff -puN include/linux/fs.h~fs-new-truncate-helpers include/linux/fs.h
--- a/include/linux/fs.h~fs-new-truncate-helpers
+++ a/include/linux/fs.h
@@ -2388,6 +2388,7 @@ extern int buffer_migrate_page(struct ad
#endif
extern int inode_change_ok(struct inode *, struct iattr *);
+extern int inode_newsize_ok(struct inode *, loff_t offset);
extern int __must_check inode_setattr(struct inode *, struct iattr *);
extern void file_update_time(struct file *file);
diff -puN include/linux/mm.h~fs-new-truncate-helpers include/linux/mm.h
--- a/include/linux/mm.h~fs-new-truncate-helpers
+++ a/include/linux/mm.h
@@ -791,8 +791,9 @@ static inline void unmap_shared_mapping_
unmap_mapping_range(mapping, holebegin, holelen, 0);
}
-extern int vmtruncate(struct inode * inode, loff_t offset);
-extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end);
+extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new);
+extern int vmtruncate(struct inode *inode, loff_t offset);
+extern int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end);
int truncate_inode_page(struct address_space *mapping, struct page *page);
int generic_error_remove_page(struct address_space *mapping, struct page *page);
diff -puN mm/filemap.c~fs-new-truncate-helpers mm/filemap.c
--- a/mm/filemap.c~fs-new-truncate-helpers
+++ a/mm/filemap.c
@@ -59,7 +59,7 @@
/*
* Lock ordering:
*
- * ->i_mmap_lock (vmtruncate)
+ * ->i_mmap_lock (truncate_pagecache)
* ->private_lock (__free_pte->__set_page_dirty_buffers)
* ->swap_lock (exclusive_swap_page, others)
* ->mapping->tree_lock
diff -puN mm/memory.c~fs-new-truncate-helpers mm/memory.c
--- a/mm/memory.c~fs-new-truncate-helpers
+++ a/mm/memory.c
@@ -283,7 +283,8 @@ void free_pgtables(struct mmu_gather *tl
unsigned long addr = vma->vm_start;
/*
- * Hide vma from rmap and vmtruncate before freeing pgtables
+ * Hide vma from rmap and truncate_pagecache before freeing
+ * pgtables
*/
anon_vma_unlink(vma);
unlink_file_vma(vma);
@@ -2360,7 +2361,7 @@ restart:
* @mapping: the address space containing mmaps to be unmapped.
* @holebegin: byte in first page to unmap, relative to the start of
* the underlying file. This will be rounded down to a PAGE_SIZE
- * boundary. Note that this is different from vmtruncate(), which
+ * boundary. Note that this is different from truncate_pagecache(), which
* must keep the partial page. In contrast, we must get rid of
* partial pages.
* @holelen: size of prospective hole in bytes. This will be rounded
@@ -2411,63 +2412,6 @@ void unmap_mapping_range(struct address_
}
EXPORT_SYMBOL(unmap_mapping_range);
-/**
- * vmtruncate - unmap mappings "freed" by truncate() syscall
- * @inode: inode of the file used
- * @offset: file offset to start truncating
- *
- * NOTE! We have to be ready to update the memory sharing
- * between the file and the memory map for a potential last
- * incomplete page. Ugly, but necessary.
- */
-int vmtruncate(struct inode * inode, loff_t offset)
-{
- if (inode->i_size < offset) {
- unsigned long limit;
-
- limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
- if (limit != RLIM_INFINITY && offset > limit)
- goto out_sig;
- if (offset > inode->i_sb->s_maxbytes)
- goto out_big;
- i_size_write(inode, offset);
- } else {
- struct address_space *mapping = inode->i_mapping;
-
- /*
- * truncation of in-use swapfiles is disallowed - it would
- * cause subsequent swapout to scribble on the now-freed
- * blocks.
- */
- if (IS_SWAPFILE(inode))
- return -ETXTBSY;
- i_size_write(inode, offset);
-
- /*
- * unmap_mapping_range is called twice, first simply for
- * efficiency so that truncate_inode_pages does fewer
- * single-page unmaps. However after this first call, and
- * before truncate_inode_pages finishes, it is possible for
- * private pages to be COWed, which remain after
- * truncate_inode_pages finishes, hence the second
- * unmap_mapping_range call must be made for correctness.
- */
- unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
- truncate_inode_pages(mapping, offset);
- unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
- }
-
- if (inode->i_op->truncate)
- inode->i_op->truncate(inode);
- return 0;
-
-out_sig:
- send_sig(SIGXFSZ, current, 0);
-out_big:
- return -EFBIG;
-}
-EXPORT_SYMBOL(vmtruncate);
-
int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
{
struct address_space *mapping = inode->i_mapping;
diff -puN mm/mremap.c~fs-new-truncate-helpers mm/mremap.c
--- a/mm/mremap.c~fs-new-truncate-helpers
+++ a/mm/mremap.c
@@ -85,8 +85,8 @@ static void move_ptes(struct vm_area_str
if (vma->vm_file) {
/*
* Subtle point from Rajesh Venkatasubramanian: before
- * moving file-based ptes, we must lock vmtruncate out,
- * since it might clean the dst vma before the src vma,
+ * moving file-based ptes, we must lock truncate_pagecache
+ * out, since it might clean the dst vma before the src vma,
* and we propagate stale pages into the dst afterward.
*/
mapping = vma->vm_file->f_mapping;
diff -puN mm/nommu.c~fs-new-truncate-helpers mm/nommu.c
--- a/mm/nommu.c~fs-new-truncate-helpers
+++ a/mm/nommu.c
@@ -83,46 +83,6 @@ struct vm_operations_struct generic_file
};
/*
- * Handle all mappings that got truncated by a "truncate()"
- * system call.
- *
- * NOTE! We have to be ready to update the memory sharing
- * between the file and the memory map for a potential last
- * incomplete page. Ugly, but necessary.
- */
-int vmtruncate(struct inode *inode, loff_t offset)
-{
- struct address_space *mapping = inode->i_mapping;
- unsigned long limit;
-
- if (inode->i_size < offset)
- goto do_expand;
- i_size_write(inode, offset);
-
- truncate_inode_pages(mapping, offset);
- goto out_truncate;
-
-do_expand:
- limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
- if (limit != RLIM_INFINITY && offset > limit)
- goto out_sig;
- if (offset > inode->i_sb->s_maxbytes)
- goto out;
- i_size_write(inode, offset);
-
-out_truncate:
- if (inode->i_op->truncate)
- inode->i_op->truncate(inode);
- return 0;
-out_sig:
- send_sig(SIGXFSZ, current, 0);
-out:
- return -EFBIG;
-}
-
-EXPORT_SYMBOL(vmtruncate);
-
-/*
* Return the total memory allocated for this pointer, not
* just what the caller asked for.
*
diff -puN mm/truncate.c~fs-new-truncate-helpers mm/truncate.c
--- a/mm/truncate.c~fs-new-truncate-helpers
+++ a/mm/truncate.c
@@ -497,3 +497,67 @@ int invalidate_inode_pages2(struct addre
return invalidate_inode_pages2_range(mapping, 0, -1);
}
EXPORT_SYMBOL_GPL(invalidate_inode_pages2);
+
+/**
+ * truncate_pagecache - unmap and remove pagecache that has been truncated
+ * @inode: inode
+ * @old: old file offset
+ * @new: new file offset
+ *
+ * inode's new i_size must already be written before truncate_pagecache
+ * is called.
+ *
+ * This function should typically be called before the filesystem
+ * releases resources associated with the freed range (eg. deallocates
+ * blocks). This way, pagecache will always stay logically coherent
+ * with on-disk format, and the filesystem would not have to deal with
+ * situations such as writepage being called for a page that has already
+ * had its underlying blocks deallocated.
+ */
+void truncate_pagecache(struct inode *inode, loff_t old, loff_t new)
+{
+ if (new < old) {
+ struct address_space *mapping = inode->i_mapping;
+
+ /*
+ * unmap_mapping_range is called twice, first simply for
+ * efficiency so that truncate_inode_pages does fewer
+ * single-page unmaps. However after this first call, and
+ * before truncate_inode_pages finishes, it is possible for
+ * private pages to be COWed, which remain after
+ * truncate_inode_pages finishes, hence the second
+ * unmap_mapping_range call must be made for correctness.
+ */
+ unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
+ truncate_inode_pages(mapping, new);
+ unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
+ }
+}
+EXPORT_SYMBOL(truncate_pagecache);
+
+/**
+ * vmtruncate - unmap mappings "freed" by truncate() syscall
+ * @inode: inode of the file used
+ * @offset: file offset to start truncating
+ *
+ * NOTE! We have to be ready to update the memory sharing
+ * between the file and the memory map for a potential last
+ * incomplete page. Ugly, but necessary.
+ */
+int vmtruncate(struct inode *inode, loff_t offset)
+{
+ loff_t oldsize;
+ int error;
+
+ error = inode_newsize_ok(inode, offset);
+ if (error)
+ return error;
+ oldsize = inode->i_size;
+ i_size_write(inode, offset);
+ truncate_pagecache(inode, oldsize, offset);
+ if (inode->i_op->truncate)
+ inode->i_op->truncate(inode);
+
+ return error;
+}
+EXPORT_SYMBOL(vmtruncate);
_
Patches currently in -mm which might be from npiggin@xxxxxxx are
origin.patch
linux-next.patch
fs-new-truncate-helpers.patch
fs-use-new-truncate-helpers.patch
fs-introduce-new-truncate-sequence.patch
fs-convert-simple-fs-to-new-truncate.patch
tmpfs-convert-to-use-the-new-truncate-convention.patch
ext2-convert-to-use-the-new-truncate-convention.patch
fat-convert-to-use-the-new-truncate-convention.patch
btrfs-convert-to-use-the-new-truncate-convention.patch
jfs-convert-to-use-the-new-truncate-convention.patch
udf-convert-to-use-the-new-truncate-convention.patch
minix-convert-to-use-the-new-truncate-convention.patch
ksm-no-debug-in-page_dup_rmap.patch
fs-turn-iprune_mutex-into-rwsem.patch
reiser4.patch
fs-symlink-write_begin-allocation-context-fix-reiser4-fix.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
