9 files changed, 69 insertions, 34 deletions

diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index ea79072f521..286e36e21da 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -440,12 +440,7 @@ _xfs_buf_find(
                 ASSERT(btp == bp->b_target);
                 if (bp->b_file_offset == range_base &&
                     bp->b_buffer_length == range_length) {
-                        /*
-                         * If we look at something, bring it to the
-                         * front of the list for next time.
-                         */
                         atomic_inc(&bp->b_hold);
-                        list_move(&bp->b_hash_list, &hash->bh_list);
                         goto found;
                 }
         }
@@ -1443,8 +1438,7 @@ xfs_alloc_bufhash(
 {
         unsigned int            i;
 
-        btp->bt_hashshift = external ? 3 : 8;   /* 8 or 256 buckets */
-        btp->bt_hashmask = (1 << btp->bt_hashshift) - 1;
+        btp->bt_hashshift = external ? 3 : 12;  /* 8 or 4096 buckets */
         btp->bt_hash = kmem_zalloc_large((1 << btp->bt_hashshift) *
                                          sizeof(xfs_bufhash_t));
         for (i = 0; i < (1 << btp->bt_hashshift); i++) {
@@ -1938,7 +1932,8 @@ xfs_buf_init(void)
         if (!xfs_buf_zone)
                 goto out;
 
-        xfslogd_workqueue = create_workqueue("xfslogd");
+        xfslogd_workqueue = alloc_workqueue("xfslogd",
+                                        WQ_RESCUER | WQ_HIGHPRI, 1);
         if (!xfslogd_workqueue)
                 goto out_free_buf_zone;
 
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index d072e5ff923..2a05614f0b9 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -137,7 +137,6 @@ typedef struct xfs_buftarg {
         size_t                  bt_smask;
 
         /* per device buffer hash table */
-        uint                    bt_hashmask;
         uint                    bt_hashshift;
         xfs_bufhash_t           *bt_hash;
 
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index 237f5ffb2ee..3b9e626f7cd 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -785,6 +785,8 @@ xfs_ioc_fsgetxattr(
 {
         struct fsxattr          fa;
 
+        memset(&fa, 0, sizeof(struct fsxattr));
+
         xfs_ilock(ip, XFS_ILOCK_SHARED);
         fa.fsx_xflags = xfs_ip2xflags(ip);
         fa.fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog;
@@ -907,6 +909,13 @@ xfs_ioctl_setattr(
                 return XFS_ERROR(EIO);
 
         /*
+         * Disallow 32bit project ids because on-disk structure
+         * is 16bit only.
+         */
+        if ((mask & FSX_PROJID) && (fa->fsx_projid > (__uint16_t)-1))
+                return XFS_ERROR(EINVAL);
+
+        /*
          * If disk quotas is on, we make sure that the dquots do exist on disk,
          * before we start any other transactions. Trying to do this later
          * is messy. We don't care to take a readlock to look at the ids
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 68be25dcd30..b1fc2a6bfe8 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -664,7 +664,7 @@ xfs_vn_fiemap(
                                         fieinfo->fi_extents_max + 1;
         bm.bmv_count = min_t(__s32, bm.bmv_count,
                              (PAGE_SIZE * 16 / sizeof(struct getbmapx)));
-        bm.bmv_iflags = BMV_IF_PREALLOC;
+        bm.bmv_iflags = BMV_IF_PREALLOC | BMV_IF_NO_HOLES;
         if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR)
                 bm.bmv_iflags |= BMV_IF_ATTRFORK;
         if (!(fieinfo->fi_flags & FIEMAP_FLAG_SYNC))
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 23f14e595c1..f90dadd5a96 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -5533,12 +5533,24 @@ xfs_getbmap(
                                         map[i].br_startblock))
                                 goto out_free_map;
 
-                        nexleft--;
                         bmv->bmv_offset =
                                 out[cur_ext].bmv_offset +
                                 out[cur_ext].bmv_length;
                         bmv->bmv_length =
                                 max_t(__int64_t, 0, bmvend - bmv->bmv_offset);
+
+                        /*
+                         * In case we don't want to return the hole,
+                         * don't increase cur_ext so that we can reuse
+                         * it in the next loop.
+                         */
+                        if ((iflags & BMV_IF_NO_HOLES) &&
+                            map[i].br_startblock == HOLESTARTBLOCK) {
+                                memset(&out[cur_ext], 0, sizeof(out[cur_ext]));
+                                continue;
+                        }
+
+                        nexleft--;
                         bmv->bmv_entries++;
                         cur_ext++;
                 }
diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h
index 7cf7220e7d5..87c2e9d0228 100644
--- a/fs/xfs/xfs_fs.h
+++ b/fs/xfs/xfs_fs.h
@@ -114,8 +114,10 @@ struct getbmapx {
 #define BMV_IF_NO_DMAPI_READ    0x2     /* Do not generate DMAPI read event  */
 #define BMV_IF_PREALLOC         0x4     /* rtn status BMV_OF_PREALLOC if req */
 #define BMV_IF_DELALLOC         0x8     /* rtn status BMV_OF_DELALLOC if req */
+#define BMV_IF_NO_HOLES         0x10    /* Do not return holes */
 #define BMV_IF_VALID    \
-        (BMV_IF_ATTRFORK|BMV_IF_NO_DMAPI_READ|BMV_IF_PREALLOC|BMV_IF_DELALLOC)
+        (BMV_IF_ATTRFORK|BMV_IF_NO_DMAPI_READ|BMV_IF_PREALLOC|  \
+         BMV_IF_DELALLOC|BMV_IF_NO_HOLES)
 
 /*      bmv_oflags values - returned for each non-header segment */
 #define BMV_OF_PREALLOC         0x1     /* segment = unwritten pre-allocation */
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index ed575fb4b49..7e206fc1fa3 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -405,9 +405,15 @@ xlog_cil_push(
         new_ctx = kmem_zalloc(sizeof(*new_ctx), KM_SLEEP|KM_NOFS);
         new_ctx->ticket = xlog_cil_ticket_alloc(log);
 
-        /* lock out transaction commit, but don't block on background push */
+        /*
+         * Lock out transaction commit, but don't block for background pushes
+         * unless we are well over the CIL space limit. See the definition of
+         * XLOG_CIL_HARD_SPACE_LIMIT() for the full explanation of the logic
+         * used here.
+         */
         if (!down_write_trylock(&cil->xc_ctx_lock)) {
-                if (!push_seq)
+                if (!push_seq &&
+                    cil->xc_ctx->space_used < XLOG_CIL_HARD_SPACE_LIMIT(log))
                         goto out_free_ticket;
                 down_write(&cil->xc_ctx_lock);
         }
@@ -422,7 +428,7 @@ xlog_cil_push(
                 goto out_skip;
 
         /* check for a previously pushed seqeunce */
-        if (push_seq < cil->xc_ctx->sequence)
+        if (push_seq && push_seq < cil->xc_ctx->sequence)
                 goto out_skip;
 
         /*
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index ced52b98b32..edcdfe01617 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -426,13 +426,13 @@ struct xfs_cil {
 };
 
 /*
- * The amount of log space we should the CIL to aggregate is difficult to size.
- * Whatever we chose we have to make we can get a reservation for the log space
- * effectively, that it is large enough to capture sufficient relogging to
- * reduce log buffer IO significantly, but it is not too large for the log or
- * induces too much latency when writing out through the iclogs. We track both
- * space consumed and the number of vectors in the checkpoint context, so we
- * need to decide which to use for limiting.
+ * The amount of log space we allow the CIL to aggregate is difficult to size.
+ * Whatever we choose, we have to make sure we can get a reservation for the
+ * log space effectively, that it is large enough to capture sufficient
+ * relogging to reduce log buffer IO significantly, but it is not too large for
+ * the log or induces too much latency when writing out through the iclogs. We
+ * track both space consumed and the number of vectors in the checkpoint
+ * context, so we need to decide which to use for limiting.
  *
  * Every log buffer we write out during a push needs a header reserved, which
  * is at least one sector and more for v2 logs. Hence we need a reservation of
@@ -459,16 +459,21 @@ struct xfs_cil {
  * checkpoint transaction ticket is specific to the checkpoint context, rather
  * than the CIL itself.
  *
- * With dynamic reservations, we can basically make up arbitrary limits for the
- * checkpoint size so long as they don't violate any other size rules.  Hence
- * the initial maximum size for the checkpoint transaction will be set to a
- * quarter of the log or 8MB, which ever is smaller. 8MB is an arbitrary limit
- * right now based on the latency of writing out a large amount of data through
- * the circular iclog buffers.
+ * With dynamic reservations, we can effectively make up arbitrary limits for
+ * the checkpoint size so long as they don't violate any other size rules.
+ * Recovery imposes a rule that no transaction exceed half the log, so we are
+ * limited by that.  Furthermore, the log transaction reservation subsystem
+ * tries to keep 25% of the log free, so we need to keep below that limit or we
+ * risk running out of free log space to start any new transactions.
+ *
+ * In order to keep background CIL push efficient, we will set a lower
+ * threshold at which background pushing is attempted without blocking current
+ * transaction commits.  A separate, higher bound defines when CIL pushes are
+ * enforced to ensure we stay within our maximum checkpoint size bounds.
+ * threshold, yet give us plenty of space for aggregation on large logs.
  */
-
-#define XLOG_CIL_SPACE_LIMIT(log)       \
-        (min((log->l_logsize >> 2), (8 * 1024 * 1024)))
+#define XLOG_CIL_SPACE_LIMIT(log)       (log->l_logsize >> 3)
+#define XLOG_CIL_HARD_SPACE_LIMIT(log)  (3 * (log->l_logsize >> 4))
 
 /*
  * The reservation head lsn is not made up of a cycle number and block number.
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 66d585c6917..4c7c7bfb2b2 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -2299,15 +2299,22 @@ xfs_alloc_file_space(
                         e = allocatesize_fsb;
                 }
 
+                /*
+                 * The transaction reservation is limited to a 32-bit block
+                 * count, hence we need to limit the number of blocks we are
+                 * trying to reserve to avoid an overflow. We can't allocate
+                 * more than @nimaps extents, and an extent is limited on disk
+                 * to MAXEXTLEN (21 bits), so use that to enforce the limit.
+                 */
+                resblks = min_t(xfs_fileoff_t, (e - s), (MAXEXTLEN * nimaps));
                 if (unlikely(rt)) {
-                        resrtextents = qblocks = (uint)(e - s);
+                        resrtextents = qblocks = resblks;
                         resrtextents /= mp->m_sb.sb_rextsize;
                         resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
                         quota_flag = XFS_QMOPT_RES_RTBLKS;
                 } else {
                         resrtextents = 0;
-                        resblks = qblocks = \
-                                XFS_DIOSTRAT_SPACE_RES(mp, (uint)(e - s));
+                        resblks = qblocks = XFS_DIOSTRAT_SPACE_RES(mp, resblks);
                         quota_flag = XFS_QMOPT_RES_REGBLKS;
                 }