Upgrade to 4.4.50-rt62

[kvmfornfv.git] / kernel / fs / ext4 / mballoc.c

diff --git a/kernel/fs/ext4/mballoc.c b/kernel/fs/ext4/mballoc.c
index 61eaf74..b7a3957 100644 (file)
--- a/kernel/fs/ext4/mballoc.c
+++ b/kernel/fs/ext4/mballoc.c
@@ -669,7 +669,7 @@ static void ext4_mb_mark_free_simple(struct super_block *sb,
        ext4_grpblk_t min;
        ext4_grpblk_t max;
        ext4_grpblk_t chunk;
-       unsigned short border;
+       unsigned int border;
 
        BUG_ON(len > EXT4_CLUSTERS_PER_GROUP(sb));
 
@@ -815,7 +815,7 @@ static void mb_regenerate_buddy(struct ext4_buddy *e4b)
  * for this page; do not hold this lock when calling this routine!
  */
 
-static int ext4_mb_init_cache(struct page *page, char *incore)
+static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 {
        ext4_group_t ngroups;
        int blocksize;
@@ -848,7 +848,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
        /* allocate buffer_heads to read bitmaps */
        if (groups_per_page > 1) {
                i = sizeof(struct buffer_head *) * groups_per_page;
-               bh = kzalloc(i, GFP_NOFS);
+               bh = kzalloc(i, gfp);
                if (bh == NULL) {
                        err = -ENOMEM;
                        goto out;
@@ -983,7 +983,7 @@ out:
  * are on the same page e4b->bd_buddy_page is NULL and return value is 0.
  */
 static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
-               ext4_group_t group, struct ext4_buddy *e4b)
+               ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp)
 {
        struct inode *inode = EXT4_SB(sb)->s_buddy_cache;
        int block, pnum, poff;
@@ -1002,7 +1002,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
        block = group * 2;
        pnum = block / blocks_per_page;
        poff = block % blocks_per_page;
-       page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+       page = find_or_create_page(inode->i_mapping, pnum, gfp);
        if (!page)
                return -ENOMEM;
        BUG_ON(page->mapping != inode->i_mapping);
@@ -1016,7 +1016,7 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
 
        block++;
        pnum = block / blocks_per_page;
-       page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+       page = find_or_create_page(inode->i_mapping, pnum, gfp);
        if (!page)
                return -ENOMEM;
        BUG_ON(page->mapping != inode->i_mapping);
@@ -1042,7 +1042,7 @@ static void ext4_mb_put_buddy_page_lock(struct ext4_buddy *e4b)
  * calling this routine!
  */
 static noinline_for_stack
-int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
+int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp)
 {
 
        struct ext4_group_info *this_grp;
@@ -1062,7 +1062,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
         * The call to ext4_mb_get_buddy_page_lock will mark the
         * page accessed.
         */
-       ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b);
+       ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b, gfp);
        if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) {
                /*
                 * somebody initialized the group
@@ -1072,7 +1072,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
        }
 
        page = e4b.bd_bitmap_page;
-       ret = ext4_mb_init_cache(page, NULL);
+       ret = ext4_mb_init_cache(page, NULL, gfp);
        if (ret)
                goto err;
        if (!PageUptodate(page)) {
@@ -1091,7 +1091,7 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
        }
        /* init buddy cache */
        page = e4b.bd_buddy_page;
-       ret = ext4_mb_init_cache(page, e4b.bd_bitmap);
+       ret = ext4_mb_init_cache(page, e4b.bd_bitmap, gfp);
        if (ret)
                goto err;
        if (!PageUptodate(page)) {
@@ -1109,8 +1109,8 @@ err:
  * calling this routine!
  */
 static noinline_for_stack int
-ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
-                                       struct ext4_buddy *e4b)
+ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group,
+                      struct ext4_buddy *e4b, gfp_t gfp)
 {
        int blocks_per_page;
        int block;
@@ -1140,7 +1140,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
                 * we need full data about the group
                 * to make a good selection
                 */
-               ret = ext4_mb_init_group(sb, group);
+               ret = ext4_mb_init_group(sb, group, gfp);
                if (ret)
                        return ret;
        }
@@ -1168,11 +1168,11 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
                         * wait for it to initialize.
                         */
                        page_cache_release(page);
-               page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+               page = find_or_create_page(inode->i_mapping, pnum, gfp);
                if (page) {
                        BUG_ON(page->mapping != inode->i_mapping);
                        if (!PageUptodate(page)) {
-                               ret = ext4_mb_init_cache(page, NULL);
+                               ret = ext4_mb_init_cache(page, NULL, gfp);
                                if (ret) {
                                        unlock_page(page);
                                        goto err;
@@ -1204,11 +1204,12 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
        if (page == NULL || !PageUptodate(page)) {
                if (page)
                        page_cache_release(page);
-               page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
+               page = find_or_create_page(inode->i_mapping, pnum, gfp);
                if (page) {
                        BUG_ON(page->mapping != inode->i_mapping);
                        if (!PageUptodate(page)) {
-                               ret = ext4_mb_init_cache(page, e4b->bd_bitmap);
+                               ret = ext4_mb_init_cache(page, e4b->bd_bitmap,
+                                                        gfp);
                                if (ret) {
                                        unlock_page(page);
                                        goto err;
@@ -1247,6 +1248,12 @@ err:
        return ret;
 }
 
+static int ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
+                             struct ext4_buddy *e4b)
+{
+       return ext4_mb_load_buddy_gfp(sb, group, e4b, GFP_NOFS);
+}
+
 static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
 {
        if (e4b->bd_bitmap_page)
@@ -1259,6 +1266,7 @@ static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
 static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
 {
        int order = 1;
+       int bb_incr = 1 << (e4b->bd_blkbits - 1);
        void *bb;
 
        BUG_ON(e4b->bd_bitmap == e4b->bd_buddy);
@@ -1271,7 +1279,8 @@ static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
                        /* this block is part of buddy of order 'order' */
                        return order;
                }
-               bb += 1 << (e4b->bd_blkbits - order);
+               bb += bb_incr;
+               bb_incr >>= 1;
                order++;
        }
        return 0;
@@ -2045,7 +2054,7 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac,
 
        /* We only do this if the grp has never been initialized */
        if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
-               int ret = ext4_mb_init_group(ac->ac_sb, group);
+               int ret = ext4_mb_init_group(ac->ac_sb, group, GFP_NOFS);
                if (ret)
                        return ret;
        }
@@ -2278,7 +2287,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
        struct ext4_group_info *grinfo;
        struct sg {
                struct ext4_group_info info;
-               ext4_grpblk_t counters[16];
+               ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2];
        } sg;
 
        group--;
@@ -2576,7 +2585,7 @@ int ext4_mb_init(struct super_block *sb)
 {
        struct ext4_sb_info *sbi = EXT4_SB(sb);
        unsigned i, j;
-       unsigned offset;
+       unsigned offset, offset_incr;
        unsigned max;
        int ret;
 
@@ -2605,11 +2614,13 @@ int ext4_mb_init(struct super_block *sb)
 
        i = 1;
        offset = 0;
+       offset_incr = 1 << (sb->s_blocksize_bits - 1);
        max = sb->s_blocksize << 2;
        do {
                sbi->s_mb_offsets[i] = offset;
                sbi->s_mb_maxs[i] = max;
-               offset += 1 << (sb->s_blocksize_bits - i);
+               offset += offset_incr;
+               offset_incr = offset_incr >> 1;
                max = max >> 1;
                i++;
        } while (i <= sb->s_blocksize_bits + 1);
@@ -2928,7 +2939,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
                ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
                           "fs metadata", block, block+len);
                /* File system mounted not to panic on error
-                * Fix the bitmap and repeat the block allocation
+                * Fix the bitmap and return EFSCORRUPTED
                 * We leak some of the blocks here.
                 */
                ext4_lock_group(sb, ac->ac_b_ex.fe_group);
@@ -2937,7 +2948,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
                ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
                err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
                if (!err)
-                       err = -EAGAIN;
+                       err = -EFSCORRUPTED;
                goto out_err;
        }
 
@@ -4502,18 +4513,7 @@ repeat:
        }
        if (likely(ac->ac_status == AC_STATUS_FOUND)) {
                *errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs);
-               if (*errp == -EAGAIN) {
-                       /*
-                        * drop the reference that we took
-                        * in ext4_mb_use_best_found
-                        */
-                       ext4_mb_release_context(ac);
-                       ac->ac_b_ex.fe_group = 0;
-                       ac->ac_b_ex.fe_start = 0;
-                       ac->ac_b_ex.fe_len = 0;
-                       ac->ac_status = AC_STATUS_CONTINUE;
-                       goto repeat;
-               } else if (*errp) {
+               if (*errp) {
                        ext4_discard_allocated_blocks(ac);
                        goto errout;
                } else {
@@ -4815,7 +4815,9 @@ do_more:
 #endif
        trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters);
 
-       err = ext4_mb_load_buddy(sb, block_group, &e4b);
+       /* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */
+       err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b,
+                                    GFP_NOFS|__GFP_NOFAIL);
        if (err)
                goto error_return;
 
@@ -5217,7 +5219,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
                grp = ext4_get_group_info(sb, group);
                /* We only do this if the grp has never been initialized */
                if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
-                       ret = ext4_mb_init_group(sb, group);
+                       ret = ext4_mb_init_group(sb, group, GFP_NOFS);
                        if (ret)
                                break;
                }