btrfs: enable large data folio support under CONFIG_BTRFS_EXPERIMENTAL

With all the preparation patches already merged, it's pretty easy to
enable large data folios:

- Remove the ASSERT() on folio size in btrfs_end_repair_bio()

- Add a helper to properly set the max folio order
  Currently due to several call sites that are fetching the bitmap
  content directly into an unsigned long, we can only support
  BITS_PER_LONG blocks for each bitmap.

- Call the helper when reading/creating an inode

The support has the following limitations:

- No large folios for data reloc inode
  The relocation code still requires page sized folio.
  But it's not that hot nor common compared to regular buffered ios.

  Will be improved in the future.

- Requires CONFIG_BTRFS_EXPERIMENTAL

- Will require all folio related operations to check if it needs the
  extra btrfs_subpage structure
  Now any folio larger than block size will need btrfs_subpage structure
  handling.

Unfortunately I do not have a physical machine for performance test, but
if everything goes like XFS/EXT4, it should mostly bring single digits
percentage performance improvement in the real world.

Although I believe there are still quite some optimizations to be done,
let's focus on testing the current large data folio support first.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index c352f3ae0385c7ba25181b7dd84d48c5ad3fa31a..ea95c90c847489a475f0ef6494dcfece92718d74 100644 (file)
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -114,6 +114,8 @@ config BTRFS_EXPERIMENTAL
 
          - extent tree v2 - complex rework of extent tracking
 
+         - large folio support
+
          If unsure, say N.
 
 config BTRFS_FS_REF_VERIFY

diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index e7d436c6aec2b311363c2e78ccf7e83f3b1cd34d..00d274ed2b1fa209668b415c2eca843c2cf8accf 100644 (file)
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -165,12 +165,6 @@ static void btrfs_end_repair_bio(struct btrfs_bio *repair_bbio,
        struct bio_vec *bv = bio_first_bvec_all(&repair_bbio->bio);
        int mirror = repair_bbio->mirror_num;
 
-       /*
-        * We can only trigger this for data bio, which doesn't support larger
-        * folios yet.
-        */
-       ASSERT(folio_order(page_folio(bv->bv_page)) == 0);
-
        if (repair_bbio->bio.bi_status ||
            !btrfs_data_csum_ok(repair_bbio, dev, 0, bv)) {
                bio_reset(&repair_bbio->bio, NULL, REQ_OP_READ);

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index a79fa0726f1d9ce54e4de3203a82b7fbedcde902..7545a1fa599792e7bc615772916ef5acaf5a1854 100644 (file)
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -525,6 +525,23 @@ static inline void btrfs_update_inode_mapping_flags(struct btrfs_inode *inode)
                mapping_set_stable_writes(inode->vfs_inode.i_mapping);
 }
 
+static inline void btrfs_set_inode_mapping_order(struct btrfs_inode *inode)
+{
+       /* Metadata inode should not reach here. */
+       ASSERT(is_data_inode(inode));
+
+       /* For data reloc inode, it still requires page sized folio. */
+       if (unlikely(btrfs_is_data_reloc_root(inode->root)))
+               return;
+
+       /* We only allow BITS_PER_LONGS blocks for each bitmap. */
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+       mapping_set_folio_order_range(inode->vfs_inode.i_mapping, 0,
+                       ilog2(((BITS_PER_LONG << inode->root->fs_info->sectorsize_bits)
+                               >> PAGE_SHIFT)));
+#endif
+}
+
 /* Array of bytes with variable length, hexadecimal format 0x1234 */
 #define CSUM_FMT                               "0x%*phN"
 #define CSUM_FMT_VALUE(size, bytes)            size, bytes

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index cbc95bceb7ff177c9e864f37643330c9d80dd418..b66eee5ab5d851e117429a428bd4bbd28b4875be 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3946,6 +3946,7 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path
        btrfs_inode_split_flags(btrfs_inode_flags(leaf, inode_item),
                                &inode->flags, &inode->ro_flags);
        btrfs_update_inode_mapping_flags(inode);
+       btrfs_set_inode_mapping_order(inode);
 
 cache_index:
        /*
@@ -6463,6 +6464,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
                        BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW |
                                BTRFS_INODE_NODATASUM;
                btrfs_update_inode_mapping_flags(BTRFS_I(inode));
+               btrfs_set_inode_mapping_order(BTRFS_I(inode));
        }
 
        ret = btrfs_insert_inode_locked(inode);

diff --git a/fs/btrfs/subpage.h b/fs/btrfs/subpage.h
index b6e40a678d738703b604ca8c057201cc25785bdb..ee0710eb13fd0abc00485643285ea64130975d69 100644 (file)
--- a/fs/btrfs/subpage.h
+++ b/fs/btrfs/subpage.h
@@ -92,7 +92,6 @@ enum btrfs_folio_type {
        BTRFS_SUBPAGE_DATA,
 };
 
-#if PAGE_SIZE > BTRFS_MIN_BLOCKSIZE
 /*
  * Subpage support for metadata is more complex, as we can have dummy extent
  * buffers, where folios have no mapping to determine the owning inode.
@@ -113,19 +112,6 @@ static inline bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info,
                ASSERT(is_data_inode(BTRFS_I(folio->mapping->host)));
        return fs_info->sectorsize < folio_size(folio);
 }
-#else
-static inline bool btrfs_meta_is_subpage(const struct btrfs_fs_info *fs_info)
-{
-       return false;
-}
-static inline bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info,
-                                   struct folio *folio)
-{
-       if (folio->mapping && folio->mapping->host)
-               ASSERT(is_data_inode(BTRFS_I(folio->mapping->host)));
-       return false;
-}
-#endif
 
 int btrfs_attach_folio_state(const struct btrfs_fs_info *fs_info,
                             struct folio *folio, enum btrfs_folio_type type);