1 files changed, 202 insertions, 66 deletions

diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 8b6c9e807efb..e79b56b4bca6 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -44,6 +44,8 @@
 #include "xfs_quota.h"
 #include "xfs_fsops.h"
 #include "xfs_utils.h"
+#include "xfs_trace.h"
+
 
 STATIC void     xfs_unmountfs_wait(xfs_mount_t *);
 
@@ -199,6 +201,38 @@ xfs_uuid_unmount(
 
 
 /*
+ * Reference counting access wrappers to the perag structures.
+ */
+struct xfs_perag *
+xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno)
+{
+        struct xfs_perag        *pag;
+        int                     ref = 0;
+
+        spin_lock(&mp->m_perag_lock);
+        pag = radix_tree_lookup(&mp->m_perag_tree, agno);
+        if (pag) {
+                ASSERT(atomic_read(&pag->pag_ref) >= 0);
+                /* catch leaks in the positive direction during testing */
+                ASSERT(atomic_read(&pag->pag_ref) < 1000);
+                ref = atomic_inc_return(&pag->pag_ref);
+        }
+        spin_unlock(&mp->m_perag_lock);
+        trace_xfs_perag_get(mp, agno, ref, _RET_IP_);
+        return pag;
+}
+
+void
+xfs_perag_put(struct xfs_perag *pag)
+{
+        int     ref;
+
+        ASSERT(atomic_read(&pag->pag_ref) > 0);
+        ref = atomic_dec_return(&pag->pag_ref);
+        trace_xfs_perag_put(pag->pag_mount, pag->pag_agno, ref, _RET_IP_);
+}
+
+/*
  * Free up the resources associated with a mount structure.  Assume that
  * the structure was initially zeroed, so we can tell which fields got
  * initialized.
@@ -207,13 +241,16 @@ STATIC void
 xfs_free_perag(
         xfs_mount_t     *mp)
 {
-        if (mp->m_perag) {
-                int     agno;
+        xfs_agnumber_t  agno;
+        struct xfs_perag *pag;
 
-                for (agno = 0; agno < mp->m_maxagi; agno++)
-                        if (mp->m_perag[agno].pagb_list)
-                                kmem_free(mp->m_perag[agno].pagb_list);
-                kmem_free(mp->m_perag);
+        for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
+                spin_lock(&mp->m_perag_lock);
+                pag = radix_tree_delete(&mp->m_perag_tree, agno);
+                ASSERT(pag);
+                ASSERT(atomic_read(&pag->pag_ref) == 0);
+                spin_unlock(&mp->m_perag_lock);
+                kmem_free(pag);
         }
 }
 
@@ -387,22 +424,57 @@ xfs_initialize_perag_icache(
         }
 }
 
-xfs_agnumber_t
+int
 xfs_initialize_perag(
         xfs_mount_t     *mp,
-        xfs_agnumber_t  agcount)
+        xfs_agnumber_t  agcount,
+        xfs_agnumber_t  *maxagi)
 {
         xfs_agnumber_t  index, max_metadata;
+        xfs_agnumber_t  first_initialised = 0;
         xfs_perag_t     *pag;
         xfs_agino_t     agino;
         xfs_ino_t       ino;
         xfs_sb_t        *sbp = &mp->m_sb;
         xfs_ino_t       max_inum = XFS_MAXINUMBER_32;
+        int             error = -ENOMEM;
 
         /* Check to see if the filesystem can overflow 32 bit inodes */
         agino = XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks - 1, 0);
         ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino);
 
+        /*
+         * Walk the current per-ag tree so we don't try to initialise AGs
+         * that already exist (growfs case). Allocate and insert all the
+         * AGs we don't find ready for initialisation.
+         */
+        for (index = 0; index < agcount; index++) {
+                pag = xfs_perag_get(mp, index);
+                if (pag) {
+                        xfs_perag_put(pag);
+                        continue;
+                }
+                if (!first_initialised)
+                        first_initialised = index;
+                pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL);
+                if (!pag)
+                        goto out_unwind;
+                if (radix_tree_preload(GFP_NOFS))
+                        goto out_unwind;
+                spin_lock(&mp->m_perag_lock);
+                if (radix_tree_insert(&mp->m_perag_tree, index, pag)) {
+                        BUG();
+                        spin_unlock(&mp->m_perag_lock);
+                        radix_tree_preload_end();
+                        error = -EEXIST;
+                        goto out_unwind;
+                }
+                pag->pag_agno = index;
+                pag->pag_mount = mp;
+                spin_unlock(&mp->m_perag_lock);
+                radix_tree_preload_end();
+        }
+
         /* Clear the mount flag if no inode can overflow 32 bits
          * on this filesystem, or if specifically requested..
          */
@@ -436,21 +508,33 @@ xfs_initialize_perag(
                         }
 
                         /* This ag is preferred for inodes */
-                        pag = &mp->m_perag[index];
+                        pag = xfs_perag_get(mp, index);
                         pag->pagi_inodeok = 1;
                         if (index < max_metadata)
                                 pag->pagf_metadata = 1;
                         xfs_initialize_perag_icache(pag);
+                        xfs_perag_put(pag);
                 }
         } else {
                 /* Setup default behavior for smaller filesystems */
                 for (index = 0; index < agcount; index++) {
-                        pag = &mp->m_perag[index];
+                        pag = xfs_perag_get(mp, index);
                         pag->pagi_inodeok = 1;
                         xfs_initialize_perag_icache(pag);
+                        xfs_perag_put(pag);
                 }
         }
-        return index;
+        if (maxagi)
+                *maxagi = index;
+        return 0;
+
+out_unwind:
+        kmem_free(pag);
+        for (; index > first_initialised; index--) {
+                pag = radix_tree_delete(&mp->m_perag_tree, index);
+                kmem_free(pag);
+        }
+        return error;
 }
 
 void
@@ -581,10 +665,10 @@ xfs_readsb(xfs_mount_t *mp, int flags)
          * access to the superblock.
          */
         sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
-        extra_flags = XFS_BUF_LOCK | XFS_BUF_MANAGE | XFS_BUF_MAPPED;
+        extra_flags = XBF_LOCK | XBF_FS_MANAGED | XBF_MAPPED;
 
-        bp = xfs_buf_read_flags(mp->m_ddev_targp, XFS_SB_DADDR,
-                                BTOBB(sector_size), extra_flags);
+        bp = xfs_buf_read(mp->m_ddev_targp, XFS_SB_DADDR, BTOBB(sector_size),
+                          extra_flags);
         if (!bp || XFS_BUF_ISERROR(bp)) {
                 xfs_fs_mount_cmn_err(flags, "SB read failed");
                 error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM;
@@ -624,8 +708,8 @@ xfs_readsb(xfs_mount_t *mp, int flags)
                 XFS_BUF_UNMANAGE(bp);
                 xfs_buf_relse(bp);
                 sector_size = mp->m_sb.sb_sectsize;
-                bp = xfs_buf_read_flags(mp->m_ddev_targp, XFS_SB_DADDR,
-                                        BTOBB(sector_size), extra_flags);
+                bp = xfs_buf_read(mp->m_ddev_targp, XFS_SB_DADDR,
+                                  BTOBB(sector_size), extra_flags);
                 if (!bp || XFS_BUF_ISERROR(bp)) {
                         xfs_fs_mount_cmn_err(flags, "SB re-read failed");
                         error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM;
@@ -729,12 +813,13 @@ xfs_initialize_perag_data(xfs_mount_t *mp, xfs_agnumber_t agcount)
                 error = xfs_ialloc_pagi_init(mp, NULL, index);
                 if (error)
                         return error;
-                pag = &mp->m_perag[index];
+                pag = xfs_perag_get(mp, index);
                 ifree += pag->pagi_freecount;
                 ialloc += pag->pagi_count;
                 bfree += pag->pagf_freeblks;
                 bfreelst += pag->pagf_flcount;
                 btree += pag->pagf_btreeblks;
+                xfs_perag_put(pag);
         }
         /*
          * Overwrite incore superblock counters with just-read data
@@ -1006,6 +1091,24 @@ xfs_mount_reset_sbqflags(
         return xfs_trans_commit(tp, 0);
 }
 
+__uint64_t
+xfs_default_resblks(xfs_mount_t *mp)
+{
+        __uint64_t resblks;
+
+        /*
+         * We default to 5% or 8192 fsbs of space reserved, whichever is
+         * smaller.  This is intended to cover concurrent allocation
+         * transactions when we initially hit enospc. These each require a 4
+         * block reservation. Hence by default we cover roughly 2000 concurrent
+         * allocation reservations.
+         */
+        resblks = mp->m_sb.sb_dblocks;
+        do_div(resblks, 20);
+        resblks = min_t(__uint64_t, resblks, 8192);
+        return resblks;
+}
+
 /*
  * This function does the following on an initial mount of a file system:
  *      - reads the superblock from disk and init the mount struct
@@ -1150,13 +1253,13 @@ xfs_mountfs(
         /*
          * Allocate and initialize the per-ag data.
          */
-        init_rwsem(&mp->m_peraglock);
-        mp->m_perag = kmem_zalloc(sbp->sb_agcount * sizeof(xfs_perag_t),
-                                  KM_MAYFAIL);
-        if (!mp->m_perag)
+        spin_lock_init(&mp->m_perag_lock);
+        INIT_RADIX_TREE(&mp->m_perag_tree, GFP_NOFS);
+        error = xfs_initialize_perag(mp, sbp->sb_agcount, &mp->m_maxagi);
+        if (error) {
+                cmn_err(CE_WARN, "XFS: Failed per-ag init: %d", error);
                 goto out_remove_uuid;
-
-        mp->m_maxagi = xfs_initialize_perag(mp, sbp->sb_agcount);
+        }
 
         if (!sbp->sb_logblocks) {
                 cmn_err(CE_WARN, "XFS: no log defined");
@@ -1317,17 +1420,16 @@ xfs_mountfs(
          * attr, unwritten extent conversion at ENOSPC, etc. Data allocations
          * are not allowed to use this reserved space.
          *
-         * We default to 5% or 1024 fsbs of space reserved, whichever is smaller.
          * This may drive us straight to ENOSPC on mount, but that implies
          * we were already there on the last unmount. Warn if this occurs.
          */
-        resblks = mp->m_sb.sb_dblocks;
-        do_div(resblks, 20);
-        resblks = min_t(__uint64_t, resblks, 1024);
-        error = xfs_reserve_blocks(mp, &resblks, NULL);
-        if (error)
-                cmn_err(CE_WARN, "XFS: Unable to allocate reserve blocks. "
-                                "Continuing without a reserve pool.");
+        if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
+                resblks = xfs_default_resblks(mp);
+                error = xfs_reserve_blocks(mp, &resblks, NULL);
+                if (error)
+                        cmn_err(CE_WARN, "XFS: Unable to allocate reserve "
+                                "blocks. Continuing without a reserve pool.");
+        }
 
         return 0;
 
@@ -1370,8 +1472,19 @@ xfs_unmountfs(
          * push out the iclog we will never get that unlocked. hence we
          * need to force the log first.
          */
-        xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE | XFS_LOG_SYNC);
-        xfs_reclaim_inodes(mp, XFS_IFLUSH_ASYNC);
+        xfs_log_force(mp, XFS_LOG_SYNC);
+
+        /*
+         * Do a delwri reclaim pass first so that as many dirty inodes are
+         * queued up for IO as possible. Then flush the buffers before making
+         * a synchronous path to catch all the remaining inodes are reclaimed.
+         * This makes the reclaim process as quick as possible by avoiding
+         * synchronous writeout and blocking on inodes already in the delwri
+         * state as much as possible.
+         */
+        xfs_reclaim_inodes(mp, 0);
+        XFS_bflush(mp->m_ddev_targp);
+        xfs_reclaim_inodes(mp, SYNC_WAIT);
 
         xfs_qm_unmount(mp);
 
@@ -1380,7 +1493,7 @@ xfs_unmountfs(
          * that nothing is pinned.  This is important because bflush()
          * will skip pinned buffers.
          */
-        xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE | XFS_LOG_SYNC);
+        xfs_log_force(mp, XFS_LOG_SYNC);
 
         xfs_binval(mp->m_ddev_targp);
         if (mp->m_rtdev_targp) {
@@ -1471,7 +1584,7 @@ xfs_log_sbcount(
         if (!xfs_sb_version_haslazysbcount(&mp->m_sb))
                 return 0;
 
-        tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT);
+        tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT, KM_SLEEP);
         error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
                                         XFS_DEFAULT_LOG_COUNT);
         if (error) {
@@ -1546,15 +1659,14 @@ xfs_mod_sb(xfs_trans_t *tp, __int64_t fields)
         xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb, fields);
 
         /* find modified range */
+        f = (xfs_sb_field_t)xfs_highbit64((__uint64_t)fields);
+        ASSERT((1LL << f) & XFS_SB_MOD_BITS);
+        last = xfs_sb_info[f + 1].offset - 1;
 
         f = (xfs_sb_field_t)xfs_lowbit64((__uint64_t)fields);
         ASSERT((1LL << f) & XFS_SB_MOD_BITS);
         first = xfs_sb_info[f].offset;
 
-        f = (xfs_sb_field_t)xfs_highbit64((__uint64_t)fields);
-        ASSERT((1LL << f) & XFS_SB_MOD_BITS);
-        last = xfs_sb_info[f + 1].offset - 1;
-
         xfs_trans_log_buf(tp, bp, first, last);
 }
 
@@ -1618,26 +1730,30 @@ xfs_mod_incore_sb_unlocked(
                                 lcounter += rem;
                         }
                 } else {                                /* Taking blocks away */
-
                         lcounter += delta;
+                        if (lcounter >= 0) {
+                                mp->m_sb.sb_fdblocks = lcounter +
+                                                        XFS_ALLOC_SET_ASIDE(mp);
+                                return 0;
+                        }
 
-                /*
-                 * If were out of blocks, use any available reserved blocks if
-                 * were allowed to.
-                 */
+                        /*
+                         * We are out of blocks, use any available reserved
+                         * blocks if were allowed to.
+                         */
+                        if (!rsvd)
+                                return XFS_ERROR(ENOSPC);
 
-                        if (lcounter < 0) {
-                                if (rsvd) {
-                                        lcounter = (long long)mp->m_resblks_avail + delta;
-                                        if (lcounter < 0) {
-                                                return XFS_ERROR(ENOSPC);
-                                        }
-                                        mp->m_resblks_avail = lcounter;
-                                        return 0;
-                                } else {        /* not reserved */
-                                        return XFS_ERROR(ENOSPC);
-                                }
+                        lcounter = (long long)mp->m_resblks_avail + delta;
+                        if (lcounter >= 0) {
+                                mp->m_resblks_avail = lcounter;
+                                return 0;
                         }
+                        printk_once(KERN_WARNING
+                                "Filesystem \"%s\": reserve blocks depleted! "
+                                "Consider increasing reserve pool size.",
+                                mp->m_fsname);
+                        return XFS_ERROR(ENOSPC);
                 }
 
                 mp->m_sb.sb_fdblocks = lcounter + XFS_ALLOC_SET_ASIDE(mp);
@@ -1885,7 +2001,7 @@ xfs_getsb(
 
         ASSERT(mp->m_sb_bp != NULL);
         bp = mp->m_sb_bp;
-        if (flags & XFS_BUF_TRYLOCK) {
+        if (flags & XBF_TRYLOCK) {
                 if (!XFS_BUF_CPSEMA(bp)) {
                         return NULL;
                 }
@@ -1945,6 +2061,26 @@ xfs_mount_log_sb(
         return error;
 }
 
+/*
+ * If the underlying (data/log/rt) device is readonly, there are some
+ * operations that cannot proceed.
+ */
+int
+xfs_dev_is_read_only(
+        struct xfs_mount        *mp,
+        char                    *message)
+{
+        if (xfs_readonly_buftarg(mp->m_ddev_targp) ||
+            xfs_readonly_buftarg(mp->m_logdev_targp) ||
+            (mp->m_rtdev_targp && xfs_readonly_buftarg(mp->m_rtdev_targp))) {
+                cmn_err(CE_NOTE,
+                        "XFS: %s required on read-only device.", message);
+                cmn_err(CE_NOTE,
+                        "XFS: write access unavailable, cannot proceed.");
+                return EROFS;
+        }
+        return 0;
+}
 
 #ifdef HAVE_PERCPU_SB
 /*
@@ -2123,7 +2259,7 @@ xfs_icsb_destroy_counters(
         mutex_destroy(&mp->m_icsb_mutex);
 }
 
-STATIC_INLINE void
+STATIC void
 xfs_icsb_lock_cntr(
         xfs_icsb_cnts_t *icsbp)
 {
@@ -2132,7 +2268,7 @@ xfs_icsb_lock_cntr(
         }
 }
 
-STATIC_INLINE void
+STATIC void
 xfs_icsb_unlock_cntr(
         xfs_icsb_cnts_t *icsbp)
 {
@@ -2140,7 +2276,7 @@ xfs_icsb_unlock_cntr(
 }
 
 
-STATIC_INLINE void
+STATIC void
 xfs_icsb_lock_all_counters(
         xfs_mount_t     *mp)
 {
@@ -2153,7 +2289,7 @@ xfs_icsb_lock_all_counters(
         }
 }
 
-STATIC_INLINE void
+STATIC void
 xfs_icsb_unlock_all_counters(
         xfs_mount_t     *mp)
 {
@@ -2389,12 +2525,12 @@ xfs_icsb_modify_counters(
 {
         xfs_icsb_cnts_t *icsbp;
         long long       lcounter;       /* long counter for 64 bit fields */
-        int             cpu, ret = 0;
+        int             ret = 0;
 
         might_sleep();
 again:
-        cpu = get_cpu();
-        icsbp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, cpu);
+        preempt_disable();
+        icsbp = this_cpu_ptr(mp->m_sb_cnts);
 
         /*
          * if the counter is disabled, go to slow path
@@ -2438,11 +2574,11 @@ again:
                 break;
         }
         xfs_icsb_unlock_cntr(icsbp);
-        put_cpu();
+        preempt_enable();
         return 0;
 
 slow_path:
-        put_cpu();
+        preempt_enable();
 
         /*
          * serialise with a mutex so we don't burn lots of cpu on
@@ -2490,7 +2626,7 @@ slow_path:
 
 balance_counter:
         xfs_icsb_unlock_cntr(icsbp);
-        put_cpu();
+        preempt_enable();
 
         /*
          * We may have multiple threads here if multiple per-cpu