[PATCH] introduce and use kzalloc

[pandora-kernel.git] / mm / filemap.c

diff --git a/mm/filemap.c b/mm/filemap.c
index 4a2fee2..8861192 100644 (file)
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -28,6 +28,7 @@
 #include <linux/blkdev.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
+#include "filemap.h"
 /*
  * FIXME: remove all knowledge of the buffer layer from the core VM
  */
@@ -53,9 +54,8 @@
  *
  *  ->i_mmap_lock              (vmtruncate)
  *    ->private_lock           (__free_pte->__set_page_dirty_buffers)
- *      ->swap_list_lock
- *        ->swap_device_lock   (exclusive_swap_page, others)
- *          ->mapping->tree_lock
+ *      ->swap_lock            (exclusive_swap_page, others)
+ *        ->mapping->tree_lock
  *
  *  ->i_sem
  *    ->i_mmap_lock            (truncate->unmap_mapping_range)
@@ -85,7 +85,7 @@
  *    ->page_table_lock                (anon_vma_prepare and various)
  *
  *  ->page_table_lock
- *    ->swap_device_lock       (try_to_unmap_one)
+ *    ->swap_lock              (try_to_unmap_one)
  *    ->private_lock           (try_to_unmap_one)
  *    ->tree_lock              (try_to_unmap_one)
  *    ->zone.lru_lock          (follow_page->mark_page_accessed)
@@ -1504,8 +1504,12 @@ repeat:
                return -EINVAL;
 
        page = filemap_getpage(file, pgoff, nonblock);
+
+       /* XXX: This is wrong, a filesystem I/O error may have happened. Fix that as
+        * done in shmem_populate calling shmem_getpage */
        if (!page && !nonblock)
                return -ENOMEM;
+
        if (page) {
                err = install_page(mm, vma, addr, page, prot);
                if (err) {
@@ -1513,6 +1517,9 @@ repeat:
                        return err;
                }
        } else {
+               /* No page was found just because we can't read it in now (being
+                * here implies nonblock != 0), but the page may exist, so set
+                * the PTE to fault it in later. */
                err = install_file_pte(mm, vma, addr, pgoff, prot);
                if (err)
                        return err;
@@ -1714,32 +1721,7 @@ int remove_suid(struct dentry *dentry)
 }
 EXPORT_SYMBOL(remove_suid);
 
-/*
- * Copy as much as we can into the page and return the number of bytes which
- * were sucessfully copied.  If a fault is encountered then clear the page
- * out to (offset+bytes) and return the number of bytes which were copied.
- */
-static inline size_t
-filemap_copy_from_user(struct page *page, unsigned long offset,
-                       const char __user *buf, unsigned bytes)
-{
-       char *kaddr;
-       int left;
-
-       kaddr = kmap_atomic(page, KM_USER0);
-       left = __copy_from_user_inatomic(kaddr + offset, buf, bytes);
-       kunmap_atomic(kaddr, KM_USER0);
-
-       if (left != 0) {
-               /* Do it the slow way */
-               kaddr = kmap(page);
-               left = __copy_from_user(kaddr + offset, buf, bytes);
-               kunmap(page);
-       }
-       return bytes - left;
-}
-
-static size_t
+size_t
 __filemap_copy_from_user_iovec(char *vaddr, 
                        const struct iovec *iov, size_t base, size_t bytes)
 {
@@ -1766,52 +1748,6 @@ __filemap_copy_from_user_iovec(char *vaddr,
        return copied - left;
 }
 
-/*
- * This has the same sideeffects and return value as filemap_copy_from_user().
- * The difference is that on a fault we need to memset the remainder of the
- * page (out to offset+bytes), to emulate filemap_copy_from_user()'s
- * single-segment behaviour.
- */
-static inline size_t
-filemap_copy_from_user_iovec(struct page *page, unsigned long offset,
-                       const struct iovec *iov, size_t base, size_t bytes)
-{
-       char *kaddr;
-       size_t copied;
-
-       kaddr = kmap_atomic(page, KM_USER0);
-       copied = __filemap_copy_from_user_iovec(kaddr + offset, iov,
-                                               base, bytes);
-       kunmap_atomic(kaddr, KM_USER0);
-       if (copied != bytes) {
-               kaddr = kmap(page);
-               copied = __filemap_copy_from_user_iovec(kaddr + offset, iov,
-                                                       base, bytes);
-               kunmap(page);
-       }
-       return copied;
-}
-
-static inline void
-filemap_set_next_iovec(const struct iovec **iovp, size_t *basep, size_t bytes)
-{
-       const struct iovec *iov = *iovp;
-       size_t base = *basep;
-
-       while (bytes) {
-               int copy = min(bytes, iov->iov_len - base);
-
-               bytes -= copy;
-               base += copy;
-               if (iov->iov_len == base) {
-                       iov++;
-                       base = 0;
-               }
-       }
-       *iovp = iov;
-       *basep = base;
-}
-
 /*
  * Performs necessary checks before doing a write
  *
@@ -1827,12 +1763,6 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i
         if (unlikely(*pos < 0))
                 return -EINVAL;
 
-        if (unlikely(file->f_error)) {
-                int err = file->f_error;
-                file->f_error = 0;
-                return err;
-        }
-
        if (!isblk) {
                /* FIXME: this is for backwards compatibility with 2.4 */
                if (file->f_flags & O_APPEND)
@@ -1927,8 +1857,11 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
         * i_sem is held, which protects generic_osync_inode() from
         * livelocking.
         */
-       if (written >= 0 && file->f_flags & O_SYNC)
-               generic_osync_inode(inode, mapping, OSYNC_METADATA);
+       if (written >= 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
+               int err = generic_osync_inode(inode, mapping, OSYNC_METADATA);
+               if (err < 0)
+                       written = err;
+       }
        if (written == count && !is_sync_kiocb(iocb))
                written = -EIOCBQUEUED;
        return written;
@@ -2027,7 +1960,9 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
                                if (unlikely(nr_segs > 1)) {
                                        filemap_set_next_iovec(&cur_iov,
                                                        &iov_base, status);
-                                       buf = cur_iov->iov_base + iov_base;
+                                       if (count)
+                                               buf = cur_iov->iov_base +
+                                                       iov_base;
                                } else {
                                        iov_base += status;
                                }