4 files changed, 107 insertions, 19 deletions

diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index d71dc44e21ed..cb329edc925b 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -166,6 +166,75 @@ test_page_region(
 }
 
 /*
+ *      Mapping of multi-page buffers into contiguous virtual space
+ */
+
+typedef struct a_list {
+        void            *vm_addr;
+        struct a_list   *next;
+} a_list_t;
+
+static a_list_t         *as_free_head;
+static int              as_list_len;
+static DEFINE_SPINLOCK(as_lock);
+
+/*
+ *      Try to batch vunmaps because they are costly.
+ */
+STATIC void
+free_address(
+        void            *addr)
+{
+        a_list_t        *aentry;
+
+#ifdef CONFIG_XEN
+        /*
+         * Xen needs to be able to make sure it can get an exclusive
+         * RO mapping of pages it wants to turn into a pagetable.  If
+         * a newly allocated page is also still being vmap()ed by xfs,
+         * it will cause pagetable construction to fail.  This is a
+         * quick workaround to always eagerly unmap pages so that Xen
+         * is happy.
+         */
+        vunmap(addr);
+        return;
+#endif
+
+        aentry = kmalloc(sizeof(a_list_t), GFP_NOWAIT);
+        if (likely(aentry)) {
+                spin_lock(&as_lock);
+                aentry->next = as_free_head;
+                aentry->vm_addr = addr;
+                as_free_head = aentry;
+                as_list_len++;
+                spin_unlock(&as_lock);
+        } else {
+                vunmap(addr);
+        }
+}
+
+STATIC void
+purge_addresses(void)
+{
+        a_list_t        *aentry, *old;
+
+        if (as_free_head == NULL)
+                return;
+
+        spin_lock(&as_lock);
+        aentry = as_free_head;
+        as_free_head = NULL;
+        as_list_len = 0;
+        spin_unlock(&as_lock);
+
+        while ((old = aentry) != NULL) {
+                vunmap(aentry->vm_addr);
+                aentry = aentry->next;
+                kfree(old);
+        }
+}
+
+/*
  *      Internal xfs_buf_t object manipulation
  */
 
@@ -264,7 +333,7 @@ xfs_buf_free(
                 uint            i;
 
                 if ((bp->b_flags & XBF_MAPPED) && (bp->b_page_count > 1))
-                       vm_unmap_ram(bp->b_addr - bp->b_offset, bp->b_page_count);
+                        free_address(bp->b_addr - bp->b_offset);
 
                 for (i = 0; i < bp->b_page_count; i++) {
                         struct page     *page = bp->b_pages[i];
@@ -386,8 +455,10 @@ _xfs_buf_map_pages(
                 bp->b_addr = page_address(bp->b_pages[0]) + bp->b_offset;
                 bp->b_flags |= XBF_MAPPED;
         } else if (flags & XBF_MAPPED) {
-               bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count,
-                                       -1, PAGE_KERNEL);
+                if (as_list_len > 64)
+                        purge_addresses();
+                bp->b_addr = vmap(bp->b_pages, bp->b_page_count,
+                                        VM_MAP, PAGE_KERNEL);
                 if (unlikely(bp->b_addr == NULL))
                         return -ENOMEM;
                 bp->b_addr += bp->b_offset;
@@ -1672,6 +1743,8 @@ xfsbufd(
                         count++;
                 }
 
+                if (as_list_len > 0)
+                        purge_addresses();
                 if (count)
                         blk_run_address_space(target->bt_mapping);
 
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 2ed035354c26..a608e72fa405 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -371,7 +371,11 @@ xfs_quiesce_attr(
         /* flush inodes and push all remaining buffers out to disk */
         xfs_quiesce_fs(mp);
 
-        ASSERT_ALWAYS(atomic_read(&mp->m_active_trans) == 0);
+        /*
+         * Just warn here till VFS can correctly support
+         * read-only remount without racing.
+         */
+        WARN_ON(atomic_read(&mp->m_active_trans) != 0);
 
         /* Push the superblock and write an unmount record */
         error = xfs_log_sbcount(mp, 1);
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index b4c1ee713492..f8278cfcc1d3 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -55,17 +55,11 @@ xfs_swapext(
         struct file     *file, *target_file;
         int             error = 0;
 
-        sxp = kmem_alloc(sizeof(xfs_swapext_t), KM_MAYFAIL);
-        if (!sxp) {
-                error = XFS_ERROR(ENOMEM);
-                goto out;
-        }
-
         /* Pull information for the target fd */
         file = fget((int)sxp->sx_fdtarget);
         if (!file) {
                 error = XFS_ERROR(EINVAL);
-                goto out_free_sxp;
+                goto out;
         }
 
         if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND)) {
@@ -109,8 +103,6 @@ xfs_swapext(
         fput(target_file);
  out_put_file:
         fput(file);
- out_free_sxp:
-        kmem_free(sxp);
  out:
         return error;
 }
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 35cca98bd94c..b1047de2fffd 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -70,16 +70,21 @@ STATIC void	xlog_recover_check_summary(xlog_t *);
 xfs_buf_t *
 xlog_get_bp(
         xlog_t          *log,
-        int             num_bblks)
+        int             nbblks)
 {
-        ASSERT(num_bblks > 0);
+        if (nbblks <= 0 || nbblks > log->l_logBBsize) {
+                xlog_warn("XFS: Invalid block length (0x%x) given for buffer", nbblks);
+                XFS_ERROR_REPORT("xlog_get_bp(1)",
+                                 XFS_ERRLEVEL_HIGH, log->l_mp);
+                return NULL;
+        }
 
         if (log->l_sectbb_log) {
-                if (num_bblks > 1)
-                        num_bblks += XLOG_SECTOR_ROUNDUP_BBCOUNT(log, 1);
-                num_bblks = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, num_bblks);
+                if (nbblks > 1)
+                        nbblks += XLOG_SECTOR_ROUNDUP_BBCOUNT(log, 1);
+                nbblks = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, nbblks);
         }
-        return xfs_buf_get_noaddr(BBTOB(num_bblks), log->l_mp->m_logdev_targp);
+        return xfs_buf_get_noaddr(BBTOB(nbblks), log->l_mp->m_logdev_targp);
 }
 
 void
@@ -102,6 +107,13 @@ xlog_bread(
 {
         int             error;
 
+        if (nbblks <= 0 || nbblks > log->l_logBBsize) {
+                xlog_warn("XFS: Invalid block length (0x%x) given for buffer", nbblks);
+                XFS_ERROR_REPORT("xlog_bread(1)",
+                                 XFS_ERRLEVEL_HIGH, log->l_mp);
+                return EFSCORRUPTED;
+        }
+
         if (log->l_sectbb_log) {
                 blk_no = XLOG_SECTOR_ROUNDDOWN_BLKNO(log, blk_no);
                 nbblks = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, nbblks);
@@ -139,6 +151,13 @@ xlog_bwrite(
 {
         int             error;
 
+        if (nbblks <= 0 || nbblks > log->l_logBBsize) {
+                xlog_warn("XFS: Invalid block length (0x%x) given for buffer", nbblks);
+                XFS_ERROR_REPORT("xlog_bwrite(1)",
+                                 XFS_ERRLEVEL_HIGH, log->l_mp);
+                return EFSCORRUPTED;
+        }
+
         if (log->l_sectbb_log) {
                 blk_no = XLOG_SECTOR_ROUNDDOWN_BLKNO(log, blk_no);
                 nbblks = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, nbblks);