xfs: add EOFBLOCKS inode tagging/untagging

Add the XFS_ICI_EOFBLOCKS_TAG inode tag to identify inodes with
speculatively preallocated blocks beyond EOF. An inode is tagged
when speculative preallocation occurs and untagged either via
truncate down or when post-EOF blocks are freed via release or
reclaim.

The tag management is intentionally not aggressive to prefer
simplicity over the complexity of handling all the corner cases
under which post-EOF blocks could be freed (i.e., forward
truncation, fallocate, write error conditions, etc.). This means
that a tagged inode may or may not have post-EOF blocks after a
period of time. The tag is eventually cleared when the inode is
released or reclaimed.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

7 files changed, 85 insertions, 0 deletions

diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h
index 44d65c1533c0..22bd4db011c8 100644
--- a/fs/xfs/xfs_ag.h
+++ b/fs/xfs/xfs_ag.h
@@ -233,6 +233,7 @@ typedef struct xfs_perag {
 #define XFS_ICI_NO_TAG          (-1)    /* special flag for an untagged lookup
                                            in xfs_inode_ag_iterator */
 #define XFS_ICI_RECLAIM_TAG     0       /* inode is to be reclaimed */
+#define XFS_ICI_EOFBLOCKS_TAG   1       /* inode has blocks beyond EOF */
 
 #define XFS_AG_MAXLEVELS(mp)            ((mp)->m_ag_maxlevels)
 #define XFS_MIN_FREELIST_RAW(bl,cl,mp)  \
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 9c8703b5cd72..f9afc5ff0482 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1128,3 +1128,65 @@ xfs_reclaim_inodes_count(
         return reclaimable;
 }
 
+void
+xfs_inode_set_eofblocks_tag(
+        xfs_inode_t     *ip)
+{
+        struct xfs_mount *mp = ip->i_mount;
+        struct xfs_perag *pag;
+        int tagged;
+
+        pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
+        spin_lock(&pag->pag_ici_lock);
+        trace_xfs_inode_set_eofblocks_tag(ip);
+
+        tagged = radix_tree_tagged(&pag->pag_ici_root,
+                                   XFS_ICI_EOFBLOCKS_TAG);
+        radix_tree_tag_set(&pag->pag_ici_root,
+                           XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
+                           XFS_ICI_EOFBLOCKS_TAG);
+        if (!tagged) {
+                /* propagate the eofblocks tag up into the perag radix tree */
+                spin_lock(&ip->i_mount->m_perag_lock);
+                radix_tree_tag_set(&ip->i_mount->m_perag_tree,
+                                   XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
+                                   XFS_ICI_EOFBLOCKS_TAG);
+                spin_unlock(&ip->i_mount->m_perag_lock);
+
+                trace_xfs_perag_set_eofblocks(ip->i_mount, pag->pag_agno,
+                                              -1, _RET_IP_);
+        }
+
+        spin_unlock(&pag->pag_ici_lock);
+        xfs_perag_put(pag);
+}
+
+void
+xfs_inode_clear_eofblocks_tag(
+        xfs_inode_t     *ip)
+{
+        struct xfs_mount *mp = ip->i_mount;
+        struct xfs_perag *pag;
+
+        pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
+        spin_lock(&pag->pag_ici_lock);
+        trace_xfs_inode_clear_eofblocks_tag(ip);
+
+        radix_tree_tag_clear(&pag->pag_ici_root,
+                             XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
+                             XFS_ICI_EOFBLOCKS_TAG);
+        if (!radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_EOFBLOCKS_TAG)) {
+                /* clear the eofblocks tag from the perag radix tree */
+                spin_lock(&ip->i_mount->m_perag_lock);
+                radix_tree_tag_clear(&ip->i_mount->m_perag_tree,
+                                     XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino),
+                                     XFS_ICI_EOFBLOCKS_TAG);
+                spin_unlock(&ip->i_mount->m_perag_lock);
+                trace_xfs_perag_clear_eofblocks(ip->i_mount, pag->pag_agno,
+                                               -1, _RET_IP_);
+        }
+
+        spin_unlock(&pag->pag_ici_lock);
+        xfs_perag_put(pag);
+}
+
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 222e22f16b4a..db3613075dc6 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -35,6 +35,9 @@ void xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
 
 void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
 
+void xfs_inode_set_eofblocks_tag(struct xfs_inode *ip);
+void xfs_inode_clear_eofblocks_tag(struct xfs_inode *ip);
+
 int xfs_sync_inode_grab(struct xfs_inode *ip);
 int xfs_inode_ag_iterator(struct xfs_mount *mp,
         int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag, int flags),
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index a066cf1766ab..add06b4e9a63 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -41,6 +41,7 @@
 #include "xfs_utils.h"
 #include "xfs_iomap.h"
 #include "xfs_trace.h"
+#include "xfs_icache.h"
 
 
 #define XFS_WRITEIO_ALIGN(mp,off)       (((off) >> mp->m_writeio_log) \
@@ -450,6 +451,13 @@ retry:
         if (!(imap[0].br_startblock || XFS_IS_REALTIME_INODE(ip)))
                 return xfs_alert_fsblock_zero(ip, &imap[0]);
 
+        /*
+         * Tag the inode as speculatively preallocated so we can reclaim this
+         * space on demand, if necessary.
+         */
+        if (prealloc)
+                xfs_inode_set_eofblocks_tag(ip);
+
         *ret_imap = imap[0];
         return 0;
 }
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 4e00cf091d2c..81f5c4953287 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -38,6 +38,7 @@
 #include "xfs_vnodeops.h"
 #include "xfs_inode_item.h"
 #include "xfs_trace.h"
+#include "xfs_icache.h"
 
 #include <linux/capability.h>
 #include <linux/xattr.h>
@@ -854,6 +855,9 @@ xfs_setattr_size(
                  * and do not wait the usual (long) time for writeout.
                  */
                 xfs_iflags_set(ip, XFS_ITRUNCATED);
+
+                /* A truncate down always removes post-EOF blocks. */
+                xfs_inode_clear_eofblocks_tag(ip);
         }
 
         if (mask & ATTR_CTIME) {
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 7d36ccf57f93..6f46e034b766 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -130,6 +130,8 @@ DEFINE_PERAG_REF_EVENT(xfs_perag_get_tag);
 DEFINE_PERAG_REF_EVENT(xfs_perag_put);
 DEFINE_PERAG_REF_EVENT(xfs_perag_set_reclaim);
 DEFINE_PERAG_REF_EVENT(xfs_perag_clear_reclaim);
+DEFINE_PERAG_REF_EVENT(xfs_perag_set_eofblocks);
+DEFINE_PERAG_REF_EVENT(xfs_perag_clear_eofblocks);
 
 TRACE_EVENT(xfs_attr_list_node_descend,
         TP_PROTO(struct xfs_attr_list_context *ctx,
@@ -585,6 +587,9 @@ DEFINE_INODE_EVENT(xfs_update_time);
 DEFINE_INODE_EVENT(xfs_dquot_dqalloc);
 DEFINE_INODE_EVENT(xfs_dquot_dqdetach);
 
+DEFINE_INODE_EVENT(xfs_inode_set_eofblocks_tag);
+DEFINE_INODE_EVENT(xfs_inode_clear_eofblocks_tag);
+
 DECLARE_EVENT_CLASS(xfs_iref_class,
         TP_PROTO(struct xfs_inode *ip, unsigned long caller_ip),
         TP_ARGS(ip, caller_ip),
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 2ee1f49da0aa..e6e1d11dfdf2 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -238,6 +238,8 @@ xfs_free_eofblocks(
                 } else {
                         error = xfs_trans_commit(tp,
                                                 XFS_TRANS_RELEASE_LOG_RES);
+                        if (!error)
+                                xfs_inode_clear_eofblocks_tag(ip);
                 }
 
                 xfs_iunlock(ip, XFS_ILOCK_EXCL);