btrfs: make page Ordered bit to be subpage compatible

This involves the following modification:

- Ordered extent creation
  This is done in process_one_page(), now PAGE_SET_ORDERED will call
  subpage helper to do the work.

- endio functions
  This is done in btrfs_mark_ordered_io_finished().

- btrfs_invalidatepage()

- btrfs_cleanup_ordered_extents()
  Use the subpage page helper, and add an extra branch to exit if the
  locked page have covered the full range.

Now the usage of page Ordered flag for ordered extent accounting is fully
subpage compatible.

Tested-by: Ritesh Harjani <riteshh@linux.ibm.com> # [ppc64]
Tested-by: Anand Jain <anand.jain@oracle.com> # [aarch64]
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 8cb51da0e16dd6e45677d02d2fa4292d4f7bf943..37a24b2e63ef16a8067d5b72cb14167d4027438a 100644 (file)
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1827,7 +1827,7 @@ static int process_one_page(struct btrfs_fs_info *fs_info,
        len = end + 1 - start;
 
        if (page_ops & PAGE_SET_ORDERED)
-               SetPageOrdered(page);
+               btrfs_page_clamp_set_ordered(fs_info, page, start, len);
 
        if (page == locked_page)
                return 1;

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2eedcf65b8aa9ea431eddcb9406ec986bc332f99..52f31d59a38e366cb89c0ccbb31612b2ec18fe4d 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -51,6 +51,7 @@
 #include "block-group.h"
 #include "space-info.h"
 #include "zoned.h"
+#include "subpage.h"
 
 struct btrfs_iget_args {
        u64 ino;
@@ -191,18 +192,22 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode,
                 * range, then __endio_write_update_ordered() will handle
                 * the ordered extent accounting for the range.
                 */
-               ClearPageOrdered(page);
+               btrfs_page_clamp_clear_ordered(inode->root->fs_info, page,
+                                              offset, bytes);
                put_page(page);
        }
 
+       /* The locked page covers the full range, nothing needs to be done */
+       if (bytes + offset <= page_offset(locked_page) + PAGE_SIZE)
+               return;
        /*
         * In case this page belongs to the delalloc range being instantiated
         * then skip it, since the first page of a range is going to be
         * properly cleaned up by the caller of run_delalloc_range
         */
        if (page_start >= offset && page_end <= (offset + bytes - 1)) {
-               offset += PAGE_SIZE;
-               bytes -= PAGE_SIZE;
+               bytes = offset + bytes - page_offset(locked_page) - PAGE_SIZE;
+               offset = page_offset(locked_page) + PAGE_SIZE;
        }
 
        return __endio_write_update_ordered(inode, offset, bytes, false);
@@ -8339,6 +8344,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
                                 unsigned int length)
 {
        struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
+       struct btrfs_fs_info *fs_info = inode->root->fs_info;
        struct extent_io_tree *tree = &inode->io_tree;
        struct extent_state *cached_state = NULL;
        u64 page_start = page_offset(page);
@@ -8374,6 +8380,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
                struct btrfs_ordered_extent *ordered;
                bool delete_states;
                u64 range_end;
+               u32 range_len;
 
                ordered = btrfs_lookup_first_ordered_range(inode, cur,
                                                           page_end + 1 - cur);
@@ -8400,7 +8407,9 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
 
                range_end = min(ordered->file_offset + ordered->num_bytes - 1,
                                page_end);
-               if (!PageOrdered(page)) {
+               ASSERT(range_end + 1 - cur < U32_MAX);
+               range_len = range_end + 1 - cur;
+               if (!btrfs_page_test_ordered(fs_info, page, cur, range_len)) {
                        /*
                         * If Ordered (Private2) is cleared, it means endio has
                         * already been executed for the range.
@@ -8410,7 +8419,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
                        delete_states = false;
                        goto next;
                }
-               ClearPageOrdered(page);
+               btrfs_page_clear_ordered(fs_info, page, cur, range_len);
 
                /*
                 * IO on this page will never be started, so we need to account

diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index b1b377ad99a048e7207b4e0636e5acf23d2f9894..6eb41b7c0c84395e7563ba11c98e92447571154f 100644 (file)
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -16,6 +16,7 @@
 #include "compression.h"
 #include "delalloc-space.h"
 #include "qgroup.h"
+#include "subpage.h"
 
 static struct kmem_cache *btrfs_ordered_extent_cache;
 
@@ -395,11 +396,11 @@ void btrfs_mark_ordered_io_finished(struct btrfs_inode *inode,
                         *
                         * If there's no such bit, we need to skip to next range.
                         */
-                       if (!PageOrdered(page)) {
+                       if (!btrfs_page_test_ordered(fs_info, page, cur, len)) {
                                cur += len;
                                continue;
                        }
-                       ClearPageOrdered(page);
+                       btrfs_page_clear_ordered(fs_info, page, cur, len);
                }
 
                /* Now we're fine to update the accounting */