xfs: add support for zoned space reservations

Source kernel commit: 0bb2193056b5969e4148fc0909e89a5362da873e

For zoned file systems garbage collection (GC) has to take the iolock
and mmaplock after moving data to a new place to synchronize with
readers.  This means waiting for garbage collection with the iolock can
deadlock.

To avoid this, the worst case required blocks have to be reserved before
taking the iolock, which is done using a new RTAVAILABLE counter that
tracks blocks that are free to write into and don't require garbage
collection.  The new helpers try to take these available blocks, and
if there aren't enough available it wakes and waits for GC.  This is
done using a list of on-stack reservations to ensure fairness.

Co-developed-by: Hans Holmberg <hans.holmberg@wdc.com>
Signed-off-by: Hans Holmberg <hans.holmberg@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>

diff --git a/libxfs/libxfs_priv.h b/libxfs/libxfs_priv.h
index 82952b0db62923af255748a15682bfd8d1e033fc..d5f7d28e08e268d25676a7e4122f05d438c67d05 100644 (file)
--- a/libxfs/libxfs_priv.h
+++ b/libxfs/libxfs_priv.h
@@ -471,6 +471,8 @@ static inline int retzero(void) { return 0; }
 #define xfs_sb_validate_fsb_count(sbp, nblks)          (0)
 #define xlog_calc_iovec_len(len)               roundup(len, sizeof(uint32_t))
 
+#define xfs_zoned_add_available(mp, rtxnum)    do { } while (0)
+
 /*
  * Prototypes for kernel static functions that are aren't in their
  * associated header files.

diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c
index c40cdf004ac9f5eb6de8d1f39f12eaebea51f4ba..3cb47c3c8707dbe12391bf1765043348808fffef 100644 (file)
--- a/libxfs/xfs_bmap.c
+++ b/libxfs/xfs_bmap.c
@@ -4783,12 +4783,18 @@ xfs_bmap_del_extent_delay(
        da_diff = da_old - da_new;
        fdblocks = da_diff;
 
-       if (bflags & XFS_BMAPI_REMAP)
+       if (bflags & XFS_BMAPI_REMAP) {
                ;
-       else if (isrt)
-               xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, del->br_blockcount));
-       else
+       } else if (isrt) {
+               xfs_rtbxlen_t   rtxlen;
+
+               rtxlen = xfs_blen_to_rtbxlen(mp, del->br_blockcount);
+               if (xfs_is_zoned_inode(ip))
+                       xfs_zoned_add_available(mp, rtxlen);
+               xfs_add_frextents(mp, rtxlen);
+       } else {
                fdblocks += del->br_blockcount;
+       }
 
        xfs_add_fdblocks(mp, fdblocks);
        xfs_mod_delalloc(ip, -(int64_t)del->br_blockcount, -da_diff);

diff --git a/libxfs/xfs_types.h b/libxfs/xfs_types.h
index dc1db15f0be521873cb05ae74e330382f9f667bf..f6f4f2d4b5dbf50012d0041cc6685421a3e2e07b 100644 (file)
--- a/libxfs/xfs_types.h
+++ b/libxfs/xfs_types.h
@@ -244,12 +244,22 @@ enum xfs_free_counter {
         */
        XC_FREE_RTEXTENTS,
 
+       /*
+        * Number of available for use RT extents.
+        *
+        * This counter only exists for zoned RT device and indicates the number
+        * of RT extents that can be directly used by writes.  XC_FREE_RTEXTENTS
+        * also includes blocks that have been written previously and freed, but
+        * sit in a rtgroup that still needs a zone reset.
+        */
+       XC_FREE_RTAVAILABLE,
        XC_FREE_NR,
 };
 
 #define XFS_FREECOUNTER_STR \
        { XC_FREE_BLOCKS,               "blocks" }, \
-       { XC_FREE_RTEXTENTS,            "rtextents" }
+       { XC_FREE_RTEXTENTS,            "rtextents" }, \
+       { XC_FREE_RTAVAILABLE,          "rtavailable" }
 
 /*
  * Type verifier functions