1 files changed, 99 insertions, 51 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f9c642b22efa..4abd683b963d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -192,11 +192,24 @@ static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
  * so before we call here everything must be consistently dirtied against
  * this transaction.
  */
-static int ext4_journal_test_restart(handle_t *handle, struct inode *inode)
+ int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
+                                 int nblocks)
 {
+        int ret;
+
+        /*
+         * Drop i_data_sem to avoid deadlock with ext4_get_blocks At this
+         * moment, get_block can be called only for blocks inside i_size since
+         * page cache has been already dropped and writes are blocked by
+         * i_mutex. So we can safely drop the i_data_sem here.
+         */
         BUG_ON(EXT4_JOURNAL(inode) == NULL);
         jbd_debug(2, "restarting handle %p\n", handle);
-        return ext4_journal_restart(handle, blocks_for_truncate(inode));
+        up_write(&EXT4_I(inode)->i_data_sem);
+        ret = ext4_journal_restart(handle, blocks_for_truncate(inode));
+        down_write(&EXT4_I(inode)->i_data_sem);
+
+        return ret;
 }
 
 /*
@@ -341,9 +354,7 @@ static int ext4_block_to_path(struct inode *inode,
         int n = 0;
         int final = 0;
 
-        if (i_block < 0) {
-                ext4_warning(inode->i_sb, "ext4_block_to_path", "block < 0");
-        } else if (i_block < direct_blocks) {
+        if (i_block < direct_blocks) {
                 offsets[n++] = i_block;
                 final = direct_blocks;
         } else if ((i_block -= direct_blocks) < indirect_blocks) {
@@ -551,15 +562,21 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
  *
  *      Normally this function find the preferred place for block allocation,
  *      returns it.
+ *      Because this is only used for non-extent files, we limit the block nr
+ *      to 32 bits.
  */
 static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
                                    Indirect *partial)
 {
+        ext4_fsblk_t goal;
+
         /*
          * XXX need to get goal block from mballoc's data structures
          */
 
-        return ext4_find_near(inode, partial);
+        goal = ext4_find_near(inode, partial);
+        goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
+        return goal;
 }
 
 /**
@@ -640,6 +657,8 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
                 if (*err)
                         goto failed_out;
 
+                BUG_ON(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS);
+
                 target -= count;
                 /* allocate blocks for indirect blocks */
                 while (index < indirect_blks && count) {
@@ -674,6 +693,7 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
                 ar.flags = EXT4_MB_HINT_DATA;
 
         current_block = ext4_mb_new_blocks(handle, &ar, err);
+        BUG_ON(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS);
 
         if (*err && (target == blks)) {
                 /*
@@ -762,8 +782,9 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
                 BUFFER_TRACE(bh, "call get_create_access");
                 err = ext4_journal_get_create_access(handle, bh);
                 if (err) {
+                        /* Don't brelse(bh) here; it's done in
+                         * ext4_journal_forget() below */
                         unlock_buffer(bh);
-                        brelse(bh);
                         goto failed;
                 }
 
@@ -1109,16 +1130,15 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used)
                 ext4_discard_preallocations(inode);
 }
 
-static int check_block_validity(struct inode *inode, sector_t logical,
-                                sector_t phys, int len)
+static int check_block_validity(struct inode *inode, const char *msg,
+                                sector_t logical, sector_t phys, int len)
 {
         if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), phys, len)) {
-                ext4_error(inode->i_sb, "check_block_validity",
+                ext4_error(inode->i_sb, msg,
                            "inode #%lu logical block %llu mapped to %llu "
                            "(size %d)", inode->i_ino,
                            (unsigned long long) logical,
                            (unsigned long long) phys, len);
-                WARN_ON(1);
                 return -EIO;
         }
         return 0;
@@ -1170,8 +1190,8 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
         up_read((&EXT4_I(inode)->i_data_sem));
 
         if (retval > 0 && buffer_mapped(bh)) {
-                int ret = check_block_validity(inode, block,
-                                               bh->b_blocknr, retval);
+                int ret = check_block_validity(inode, "file system corruption",
+                                               block, bh->b_blocknr, retval);
                 if (ret != 0)
                         return ret;
         }
@@ -1235,8 +1255,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
                          * i_data's format changing.  Force the migrate
                          * to fail by clearing migrate flags
                          */
-                        EXT4_I(inode)->i_flags = EXT4_I(inode)->i_flags &
-                                                        ~EXT4_EXT_MIGRATE;
+                        EXT4_I(inode)->i_state &= ~EXT4_STATE_EXT_MIGRATE;
                 }
         }
 
@@ -1252,8 +1271,9 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
 
         up_write((&EXT4_I(inode)->i_data_sem));
         if (retval > 0 && buffer_mapped(bh)) {
-                int ret = check_block_validity(inode, block,
-                                               bh->b_blocknr, retval);
+                int ret = check_block_validity(inode, "file system "
+                                               "corruption after allocation",
+                                               block, bh->b_blocknr, retval);
                 if (ret != 0)
                         return ret;
         }
@@ -1863,18 +1883,6 @@ static void ext4_da_page_release_reservation(struct page *page,
  * Delayed allocation stuff
  */
 
-struct mpage_da_data {
-        struct inode *inode;
-        sector_t b_blocknr;             /* start block number of extent */
-        size_t b_size;                  /* size of extent */
-        unsigned long b_state;          /* state of the extent */
-        unsigned long first_page, next_page;    /* extent of pages */
-        struct writeback_control *wbc;
-        int io_done;
-        int pages_written;
-        int retval;
-};
-
 /*
  * mpage_da_submit_io - walks through extent of pages and try to write
  * them with writepage() call back
@@ -2737,6 +2745,7 @@ static int ext4_da_writepages(struct address_space *mapping,
         long pages_skipped;
         int range_cyclic, cycled = 1, io_done = 0;
         int needed_blocks, ret = 0, nr_to_writebump = 0;
+        loff_t range_start = wbc->range_start;
         struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 
         trace_ext4_da_writepages(inode, wbc);
@@ -2850,6 +2859,7 @@ retry:
                         mpd.io_done = 1;
                         ret = MPAGE_DA_EXTENT_TAIL;
                 }
+                trace_ext4_da_write_pages(inode, &mpd);
                 wbc->nr_to_write -= mpd.pages_written;
 
                 ext4_journal_stop(handle);
@@ -2905,6 +2915,7 @@ out_writepages:
         if (!no_nrwrite_index_update)
                 wbc->no_nrwrite_index_update = 0;
         wbc->nr_to_write -= nr_to_writebump;
+        wbc->range_start = range_start;
         trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
         return ret;
 }
@@ -3117,6 +3128,8 @@ out:
  */
 int ext4_alloc_da_blocks(struct inode *inode)
 {
+        trace_ext4_alloc_da_blocks(inode);
+
         if (!EXT4_I(inode)->i_reserved_data_blocks &&
             !EXT4_I(inode)->i_reserved_meta_blocks)
                 return 0;
@@ -3659,7 +3672,8 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
                         ext4_handle_dirty_metadata(handle, inode, bh);
                 }
                 ext4_mark_inode_dirty(handle, inode);
-                ext4_journal_test_restart(handle, inode);
+                ext4_truncate_restart_trans(handle, inode,
+                                            blocks_for_truncate(inode));
                 if (bh) {
                         BUFFER_TRACE(bh, "retaking write access");
                         ext4_journal_get_write_access(handle, bh);
@@ -3870,7 +3884,8 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
                                 return;
                         if (try_to_extend_transaction(handle, inode)) {
                                 ext4_mark_inode_dirty(handle, inode);
-                                ext4_journal_test_restart(handle, inode);
+                                ext4_truncate_restart_trans(handle, inode,
+                                            blocks_for_truncate(inode));
                         }
 
                         ext4_free_blocks(handle, inode, nr, 1, 1);
@@ -3958,8 +3973,7 @@ void ext4_truncate(struct inode *inode)
         if (!ext4_can_truncate(inode))
                 return;
 
-        if (ei->i_disksize && inode->i_size == 0 &&
-            !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
+        if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
                 ei->i_state |= EXT4_STATE_DA_ALLOC_CLOSE;
 
         if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
@@ -4533,7 +4547,8 @@ static int ext4_inode_blocks_set(handle_t *handle,
  */
 static int ext4_do_update_inode(handle_t *handle,
                                 struct inode *inode,
-                                struct ext4_iloc *iloc)
+                                struct ext4_iloc *iloc,
+                                int do_sync)
 {
         struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
         struct ext4_inode_info *ei = EXT4_I(inode);
@@ -4581,8 +4596,7 @@ static int ext4_do_update_inode(handle_t *handle,
         if (ext4_inode_blocks_set(handle, raw_inode, ei))
                 goto out_brelse;
         raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
-        /* clear the migrate flag in the raw_inode */
-        raw_inode->i_flags = cpu_to_le32(ei->i_flags & ~EXT4_EXT_MIGRATE);
+        raw_inode->i_flags = cpu_to_le32(ei->i_flags);
         if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
             cpu_to_le32(EXT4_OS_HURD))
                 raw_inode->i_file_acl_high =
@@ -4635,10 +4649,22 @@ static int ext4_do_update_inode(handle_t *handle,
                 raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
         }
 
-        BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
-        rc = ext4_handle_dirty_metadata(handle, inode, bh);
-        if (!err)
-                err = rc;
+        /*
+         * If we're not using a journal and we were called from
+         * ext4_write_inode() to sync the inode (making do_sync true),
+         * we can just use sync_dirty_buffer() directly to do our dirty
+         * work.  Testing s_journal here is a bit redundant but it's
+         * worth it to avoid potential future trouble.
+         */
+        if (EXT4_SB(inode->i_sb)->s_journal == NULL && do_sync) {
+                BUFFER_TRACE(bh, "call sync_dirty_buffer");
+                sync_dirty_buffer(bh);
+        } else {
+                BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+                rc = ext4_handle_dirty_metadata(handle, inode, bh);
+                if (!err)
+                        err = rc;
+        }
         ei->i_state &= ~EXT4_STATE_NEW;
 
 out_brelse:
@@ -4684,19 +4710,32 @@ out_brelse:
  */
 int ext4_write_inode(struct inode *inode, int wait)
 {
+        int err;
+
         if (current->flags & PF_MEMALLOC)
                 return 0;
 
-        if (ext4_journal_current_handle()) {
-                jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n");
-                dump_stack();
-                return -EIO;
-        }
+        if (EXT4_SB(inode->i_sb)->s_journal) {
+                if (ext4_journal_current_handle()) {
+                        jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n");
+                        dump_stack();
+                        return -EIO;
+                }
 
-        if (!wait)
-                return 0;
+                if (!wait)
+                        return 0;
+
+                err = ext4_force_commit(inode->i_sb);
+        } else {
+                struct ext4_iloc iloc;
 
-        return ext4_force_commit(inode->i_sb);
+                err = ext4_get_inode_loc(inode, &iloc);
+                if (err)
+                        return err;
+                err = ext4_do_update_inode(EXT4_NOJOURNAL_HANDLE,
+                                           inode, &iloc, wait);
+        }
+        return err;
 }
 
 /*
@@ -4990,7 +5029,7 @@ int ext4_mark_iloc_dirty(handle_t *handle,
         get_bh(iloc->bh);
 
         /* ext4_do_update_inode() does jbd2_journal_dirty_metadata */
-        err = ext4_do_update_inode(handle, inode, iloc);
+        err = ext4_do_update_inode(handle, inode, iloc, 0);
         put_bh(iloc->bh);
         return err;
 }
@@ -5281,12 +5320,21 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
         else
                 len = PAGE_CACHE_SIZE;
 
+        lock_page(page);
+        /*
+         * return if we have all the buffers mapped. This avoid
+         * the need to call write_begin/write_end which does a
+         * journal_start/journal_stop which can block and take
+         * long time
+         */
         if (page_has_buffers(page)) {
-                /* return if we have all the buffers mapped */
                 if (!walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
-                                       ext4_bh_unmapped))
+                                        ext4_bh_unmapped)) {
+                        unlock_page(page);
                         goto out_unlock;
+                }
         }
+        unlock_page(page);
         /*
          * OK, we need to fill the hole... Do write_begin write_end
          * to do block allocation/reservation.We are not holding