1 files changed, 84 insertions, 51 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 6e39895a91b8..5b0d2c7d5408 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -38,6 +38,7 @@
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
 #include <linux/aio.h>
+#include <linux/bitops.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -214,7 +215,7 @@ void ext4_evict_inode(struct inode *inode)
                         jbd2_complete_transaction(journal, commit_tid);
                         filemap_write_and_wait(&inode->i_data);
                 }
-                truncate_inode_pages(&inode->i_data, 0);
+                truncate_inode_pages_final(&inode->i_data);
 
                 WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
                 goto no_delete;
@@ -225,7 +226,7 @@ void ext4_evict_inode(struct inode *inode)
 
         if (ext4_should_order_data(inode))
                 ext4_begin_ordered_truncate(inode, 0);
-        truncate_inode_pages(&inode->i_data, 0);
+        truncate_inode_pages_final(&inode->i_data);
 
         WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
         if (is_bad_inode(inode))
@@ -503,6 +504,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 {
         struct extent_status es;
         int retval;
+        int ret = 0;
 #ifdef ES_AGGRESSIVE_TEST
         struct ext4_map_blocks orig_map;
 
@@ -514,6 +516,12 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
                   "logical block %lu\n", inode->i_ino, flags, map->m_len,
                   (unsigned long) map->m_lblk);
 
+        /*
+         * ext4_map_blocks returns an int, and m_len is an unsigned int
+         */
+        if (unlikely(map->m_len > INT_MAX))
+                map->m_len = INT_MAX;
+
         /* Lookup extent status tree firstly */
         if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
                 ext4_es_lru_add(inode);
@@ -552,7 +560,6 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
                                              EXT4_GET_BLOCKS_KEEP_SIZE);
         }
         if (retval > 0) {
-                int ret;
                 unsigned int status;
 
                 if (unlikely(retval != map->m_len)) {
@@ -579,7 +586,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 
 found:
         if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
-                int ret = check_block_validity(inode, map);
+                ret = check_block_validity(inode, map);
                 if (ret != 0)
                         return ret;
         }
@@ -596,7 +603,13 @@ found:
          * with buffer head unmapped.
          */
         if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
-                return retval;
+                /*
+                 * If we need to convert extent to unwritten
+                 * we continue and do the actual work in
+                 * ext4_ext_map_blocks()
+                 */
+                if (!(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN))
+                        return retval;
 
         /*
          * Here we clear m_flags because after allocating an new extent,
@@ -652,7 +665,6 @@ found:
                 ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
 
         if (retval > 0) {
-                int ret;
                 unsigned int status;
 
                 if (unlikely(retval != map->m_len)) {
@@ -687,7 +699,7 @@ found:
 has_zeroout:
         up_write((&EXT4_I(inode)->i_data_sem));
         if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
-                int ret = check_block_validity(inode, map);
+                ret = check_block_validity(inode, map);
                 if (ret != 0)
                         return ret;
         }
@@ -3312,33 +3324,13 @@ void ext4_set_aops(struct inode *inode)
 }
 
 /*
- * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
- * up to the end of the block which corresponds to `from'.
- * This required during truncate. We need to physically zero the tail end
- * of that block so it doesn't yield old data if the file is later grown.
- */
-int ext4_block_truncate_page(handle_t *handle,
-                struct address_space *mapping, loff_t from)
-{
-        unsigned offset = from & (PAGE_CACHE_SIZE-1);
-        unsigned length;
-        unsigned blocksize;
-        struct inode *inode = mapping->host;
-
-        blocksize = inode->i_sb->s_blocksize;
-        length = blocksize - (offset & (blocksize - 1));
-
-        return ext4_block_zero_page_range(handle, mapping, from, length);
-}
-
-/*
  * ext4_block_zero_page_range() zeros out a mapping of length 'length'
  * starting from file offset 'from'.  The range to be zero'd must
  * be contained with in one block.  If the specified range exceeds
  * the end of the block it will be shortened to end of the block
  * that cooresponds to 'from'
  */
-int ext4_block_zero_page_range(handle_t *handle,
+static int ext4_block_zero_page_range(handle_t *handle,
                 struct address_space *mapping, loff_t from, loff_t length)
 {
         ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
@@ -3428,6 +3420,26 @@ unlock:
         return err;
 }
 
+/*
+ * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
+ * up to the end of the block which corresponds to `from'.
+ * This required during truncate. We need to physically zero the tail end
+ * of that block so it doesn't yield old data if the file is later grown.
+ */
+int ext4_block_truncate_page(handle_t *handle,
+                struct address_space *mapping, loff_t from)
+{
+        unsigned offset = from & (PAGE_CACHE_SIZE-1);
+        unsigned length;
+        unsigned blocksize;
+        struct inode *inode = mapping->host;
+
+        blocksize = inode->i_sb->s_blocksize;
+        length = blocksize - (offset & (blocksize - 1));
+
+        return ext4_block_zero_page_range(handle, mapping, from, length);
+}
+
 int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
                              loff_t lstart, loff_t length)
 {
@@ -3501,7 +3513,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
         if (!S_ISREG(inode->i_mode))
                 return -EOPNOTSUPP;
 
-        trace_ext4_punch_hole(inode, offset, length);
+        trace_ext4_punch_hole(inode, offset, length, 0);
 
         /*
          * Write out all dirty pages to avoid race conditions
@@ -3608,6 +3620,12 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
         up_write(&EXT4_I(inode)->i_data_sem);
         if (IS_SYNC(inode))
                 ext4_handle_sync(handle);
+
+        /* Now release the pages again to reduce race window */
+        if (last_block_offset > first_block_offset)
+                truncate_pagecache_range(inode, first_block_offset,
+                                         last_block_offset);
+
         inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
         ext4_mark_inode_dirty(handle, inode);
 out_stop:
@@ -3681,7 +3699,7 @@ void ext4_truncate(struct inode *inode)
 
         /*
          * There is a possibility that we're either freeing the inode
-         * or it completely new indode. In those cases we might not
+         * or it's a completely new inode. In those cases we might not
          * have i_mutex locked because it's not necessary.
          */
         if (!(inode->i_state & (I_NEW|I_FREEING)))
@@ -3921,18 +3939,20 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
 void ext4_set_inode_flags(struct inode *inode)
 {
         unsigned int flags = EXT4_I(inode)->i_flags;
+        unsigned int new_fl = 0;
 
-        inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
         if (flags & EXT4_SYNC_FL)
-                inode->i_flags |= S_SYNC;
+                new_fl |= S_SYNC;
         if (flags & EXT4_APPEND_FL)
-                inode->i_flags |= S_APPEND;
+                new_fl |= S_APPEND;
         if (flags & EXT4_IMMUTABLE_FL)
-                inode->i_flags |= S_IMMUTABLE;
+                new_fl |= S_IMMUTABLE;
         if (flags & EXT4_NOATIME_FL)
-                inode->i_flags |= S_NOATIME;
+                new_fl |= S_NOATIME;
         if (flags & EXT4_DIRSYNC_FL)
-                inode->i_flags |= S_DIRSYNC;
+                new_fl |= S_DIRSYNC;
+        inode_set_flags(inode, new_fl,
+                        S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
 }
 
 /* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
@@ -4151,11 +4171,13 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
         EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode);
         EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
 
-        inode->i_version = le32_to_cpu(raw_inode->i_disk_version);
-        if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
-                if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
-                        inode->i_version |=
-                        (__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
+        if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
+                inode->i_version = le32_to_cpu(raw_inode->i_disk_version);
+                if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
+                        if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
+                                inode->i_version |=
+                    (__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
+                }
         }
 
         ret = 0;
@@ -4325,8 +4347,7 @@ static int ext4_do_update_inode(handle_t *handle,
                 goto out_brelse;
         raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
         raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF);
-        if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
-            cpu_to_le32(EXT4_OS_HURD))
+        if (likely(!test_opt2(inode->i_sb, HURD_COMPAT)))
                 raw_inode->i_file_acl_high =
                         cpu_to_le16(ei->i_file_acl >> 32);
         raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl);
@@ -4371,12 +4392,15 @@ static int ext4_do_update_inode(handle_t *handle,
                         raw_inode->i_block[block] = ei->i_data[block];
         }
 
-        raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
-        if (ei->i_extra_isize) {
-                if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
-                        raw_inode->i_version_hi =
-                        cpu_to_le32(inode->i_version >> 32);
-                raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
+        if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
+                raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
+                if (ei->i_extra_isize) {
+                        if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
+                                raw_inode->i_version_hi =
+                                        cpu_to_le32(inode->i_version >> 32);
+                        raw_inode->i_extra_isize =
+                                cpu_to_le16(ei->i_extra_isize);
+                }
         }
 
         ext4_inode_csum_set(inode, raw_inode, ei);
@@ -4443,7 +4467,12 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
                         return -EIO;
                 }
 
-                if (wbc->sync_mode != WB_SYNC_ALL)
+                /*
+                 * No need to force transaction in WB_SYNC_NONE mode. Also
+                 * ext4_sync_fs() will force the commit after everything is
+                 * written.
+                 */
+                if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync)
                         return 0;
 
                 err = ext4_force_commit(inode->i_sb);
@@ -4453,7 +4482,11 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
                 err = __ext4_get_inode_loc(inode, &iloc, 0);
                 if (err)
                         return err;
-                if (wbc->sync_mode == WB_SYNC_ALL)
+                /*
+                 * sync(2) will flush the whole buffer cache. No need to do
+                 * it here separately for each inode.
+                 */
+                if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
                         sync_dirty_buffer(iloc.bh);
                 if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
                         EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr,