summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2009-09-24 08:32:11 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2009-09-24 08:32:11 -0700
commit6c5daf012c9155aafd2c7973e4278766c30dfad0 (patch)
tree33959d7b36d03e1610615641a2940cb2de5e8603 /mm
parent6d39b27f0ac7e805ae3bd9efa51d7da04bec0360 (diff)
parentc08d3b0e33edce28e9cfa7b64f7fe5bdeeb29248 (diff)
downloadlinux-6c5daf012c9155aafd2c7973e4278766c30dfad0.tar.bz2
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: truncate: use new helpers truncate: new helpers fs: fix overflow in sys_mount() for in-kernel calls fs: Make unload_nls() NULL pointer safe freeze_bdev: grab active reference to frozen superblocks freeze_bdev: kill bd_mount_sem exofs: remove BKL from super operations fs/romfs: correct error-handling code vfs: seq_file: add helpers for data filling vfs: remove redundant position check in do_sendfile vfs: change sb->s_maxbytes to a loff_t vfs: explicitly cast s_maxbytes in fiemap_check_ranges libfs: return error code on failed attr set seq_file: return a negative error code when seq_path_root() fails. vfs: optimize touch_time() too vfs: optimization for touch_atime() vfs: split generic_forget_inode() so that hugetlbfs does not have to copy it fs/inode.c: add dev-id and inode number for debugging in init_special_inode() libfs: make simple_read_from_buffer conventional
Diffstat (limited to 'mm')
-rw-r--r--mm/filemap.c2
-rw-r--r--mm/memory.c62
-rw-r--r--mm/mremap.c4
-rw-r--r--mm/nommu.c40
-rw-r--r--mm/truncate.c64
5 files changed, 70 insertions, 102 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index c1fc205a92c6..6c84e598b4a9 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -58,7 +58,7 @@
/*
* 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 --git a/mm/memory.c b/mm/memory.c
index 987389a809e7..7e91b5f9f690 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -297,7 +297,8 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
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);
@@ -2408,7 +2409,7 @@ 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
@@ -2459,63 +2460,6 @@ void unmap_mapping_range(struct address_space *mapping,
}
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 --git a/mm/mremap.c b/mm/mremap.c
index 20a07dba6be0..97bff2547719 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -86,8 +86,8 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
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 --git a/mm/nommu.c b/mm/nommu.c
index 8d484241d034..56a446f05971 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -83,46 +83,6 @@ struct vm_operations_struct generic_file_vm_ops = {
};
/*
- * 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 --git a/mm/truncate.c b/mm/truncate.c
index a17b3977cfdf..450cebdabfc0 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -497,3 +497,67 @@ int invalidate_inode_pages2(struct address_space *mapping)
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);