X-Git-Url: https://git.whamcloud.com/?a=blobdiff_plain;ds=inline;f=ldiskfs%2Fkernel_patches%2Fpatches%2Frhel8.3%2Fext4-mballoc-extra-checks.patch;fp=ldiskfs%2Fkernel_patches%2Fpatches%2Frhel8.3%2Fext4-mballoc-extra-checks.patch;h=2678de09dcf7c9eb16b00f26895b2f0c29d5eb6b;hb=cf48a2d23bca685e1076e45370c5d3763c9a9952;hp=0000000000000000000000000000000000000000;hpb=36c62df64b5f3e2a45ca36bef5b6f62c866c8d92;p=fs%2Flustre-release.git

diff --git a/ldiskfs/kernel_patches/patches/rhel8.3/ext4-mballoc-extra-checks.patch b/ldiskfs/kernel_patches/patches/rhel8.3/ext4-mballoc-extra-checks.patch
new file mode 100644
index 0000000..2678de0
--- /dev/null
+++ b/ldiskfs/kernel_patches/patches/rhel8.3/ext4-mballoc-extra-checks.patch
@@ -0,0 +1,301 @@
+Index: linux-4.18.0-80.1.2.el8_0/fs/ext4/ext4.h
+===================================================================
+--- linux-4.18.0-80.1.2.el8_0.orig/fs/ext4/ext4.h
++++ linux-4.18.0-80.1.2.el8_0/fs/ext4/ext4.h
+@@ -2881,6 +2881,7 @@ struct ext4_group_info {
+ 	ext4_grpblk_t	bb_fragments;	/* nr of freespace fragments */
+ 	ext4_grpblk_t	bb_largest_free_order;/* order of largest frag in BG */
+ 	struct          list_head bb_prealloc_list;
++	unsigned long   bb_prealloc_nr;
+ #ifdef DOUBLE_CHECK
+ 	void            *bb_bitmap;
+ #endif
+Index: linux-4.18.0-240.1.1.el8/fs/ext4/mballoc.c
+===================================================================
+--- linux-4.18.0-240.1.1.el8.orig/fs/ext4/mballoc.c
++++ linux-4.18.0-240.1.1.el8/fs/ext4/mballoc.c
+@@ -352,7 +352,7 @@ static const char * const ext4_groupinfo
+ 	"ext4_groupinfo_64k", "ext4_groupinfo_128k"
+ };
+ 
+-static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
++static int ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
+ 					ext4_group_t group);
+ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
+ 						ext4_group_t group);
+@@ -708,7 +708,7 @@ mb_set_largest_free_order(struct super_b
+ }
+ 
+ static noinline_for_stack
+-void ext4_mb_generate_buddy(struct super_block *sb,
++int ext4_mb_generate_buddy(struct super_block *sb,
+ 				void *buddy, void *bitmap, ext4_group_t group)
+ {
+ 	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+@@ -752,6 +752,7 @@ void ext4_mb_generate_buddy(struct super
+ 		grp->bb_free = free;
+ 		ext4_mark_group_bitmap_corrupted(sb, group,
+ 					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
++		return -EIO;
+ 	}
+ 	mb_set_largest_free_order(sb, grp);
+ 
+@@ -762,6 +763,8 @@ void ext4_mb_generate_buddy(struct super
+ 	sbi->s_mb_buddies_generated++;
+ 	sbi->s_mb_generation_time += period;
+ 	spin_unlock(&sbi->s_bal_lock);
++
++	return 0;
+ }
+ 
+ static void mb_regenerate_buddy(struct ext4_buddy *e4b)
+@@ -882,7 +885,7 @@ static int ext4_mb_init_cache(struct pag
+ 	}
+ 
+ 	first_block = page->index * blocks_per_page;
+-	for (i = 0; i < blocks_per_page; i++) {
++	for (i = 0; i < blocks_per_page && err == 0; i++) {
+ 		group = (first_block + i) >> 1;
+ 		if (group >= ngroups)
+ 			break;
+@@ -926,7 +929,7 @@ static int ext4_mb_init_cache(struct pag
+ 			ext4_lock_group(sb, group);
+ 			/* init the buddy */
+ 			memset(data, 0xff, blocksize);
+-			ext4_mb_generate_buddy(sb, data, incore, group);
++			err = ext4_mb_generate_buddy(sb, data, incore, group);
+ 			ext4_unlock_group(sb, group);
+ 			incore = NULL;
+ 		} else {
+@@ -941,7 +944,7 @@ static int ext4_mb_init_cache(struct pag
+ 			memcpy(data, bitmap, blocksize);
+ 
+ 			/* mark all preallocated blks used in in-core bitmap */
+-			ext4_mb_generate_from_pa(sb, data, group);
++			err = ext4_mb_generate_from_pa(sb, data, group);
+ 			ext4_mb_generate_from_freelist(sb, data, group);
+ 			ext4_unlock_group(sb, group);
+ 
+@@ -951,7 +954,8 @@ static int ext4_mb_init_cache(struct pag
+ 			incore = data;
+ 		}
+ 	}
+-	SetPageUptodate(page);
++	if (likely(err == 0))
++		SetPageUptodate(page);
+ 
+ out:
+ 	if (bh) {
+@@ -2280,9 +2284,11 @@ static void *ext4_mb_seq_groups_next(str
+ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
+ {
+ 	struct super_block *sb = PDE_DATA(file_inode(seq->file));
++	struct ext4_group_desc *gdp;
+ 	ext4_group_t group = (ext4_group_t) ((unsigned long) v);
+ 	int i;
+ 	int err, buddy_loaded = 0;
++	int free = 0;
+ 	struct ext4_buddy e4b;
+ 	struct ext4_group_info *grinfo;
+ 	unsigned char blocksize_bits = min_t(unsigned char,
+@@ -2295,7 +2301,7 @@ static int ext4_mb_seq_groups_show(struc
+ 
+ 	group--;
+ 	if (group == 0)
+-		seq_puts(seq, "#group: free  frags first ["
++		seq_puts(seq, "#group: bfree gfree frags first pa    ["
+ 			      " 2^0   2^1   2^2   2^3   2^4   2^5   2^6  "
+ 			      " 2^7   2^8   2^9   2^10  2^11  2^12  2^13  ]\n");
+ 
+@@ -2313,13 +2319,19 @@ static int ext4_mb_seq_groups_show(struc
+ 		buddy_loaded = 1;
+ 	}
+ 
++	gdp = ext4_get_group_desc(sb, group, NULL);
++	if (gdp != NULL)
++		free = ext4_free_group_clusters(sb, gdp);
++
+ 	memcpy(&sg, ext4_get_group_info(sb, group), i);
+ 
+ 	if (buddy_loaded)
+ 		ext4_mb_unload_buddy(&e4b);
+ 
+-	seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free,
+-			sg.info.bb_fragments, sg.info.bb_first_free);
++	seq_printf(seq, "#%-5lu: %-5u %-5u %-5u %-5u %-5lu [",
++			(long unsigned int)group, sg.info.bb_free, free,
++			sg.info.bb_fragments, sg.info.bb_first_free,
++			sg.info.bb_prealloc_nr);
+ 	for (i = 0; i <= 13; i++)
+ 		seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ?
+ 				sg.info.bb_counters[i] : 0);
+@@ -3635,22 +3647,71 @@ static void ext4_mb_generate_from_freeli
+ }
+ 
+ /*
++ * check free blocks in bitmap match free block in group descriptor
++ * do this before taking preallocated blocks into account to be able
++ * to detect on-disk corruptions. The group lock should be hold by the
++ * caller.
++ */
++int ext4_mb_check_ondisk_bitmap(struct super_block *sb, void *bitmap,
++				struct ext4_group_desc *gdp, int group)
++{
++	unsigned short max = EXT4_CLUSTERS_PER_GROUP(sb);
++	unsigned short i, first, free = 0;
++	unsigned short free_in_gdp = ext4_free_group_clusters(sb, gdp);
++
++	if (free_in_gdp == 0 && gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))
++		return 0;
++
++	i = mb_find_next_zero_bit(bitmap, max, 0);
++
++	while (i < max) {
++		first = i;
++		i = mb_find_next_bit(bitmap, max, i);
++		if (i > max)
++			i = max;
++		free += i - first;
++		if (i < max)
++			i = mb_find_next_zero_bit(bitmap, max, i);
++	}
++
++	if (free != free_in_gdp) {
++		ext4_error(sb, "on-disk bitmap for group %d"
++			"corrupted: %u blocks free in bitmap, %u - in gd\n",
++			group, free, free_in_gdp);
++		return -EIO;
++	}
++	return 0;
++}
++
++/*
+  * the function goes through all preallocation in this group and marks them
+  * used in in-core bitmap. buddy must be generated from this bitmap
+  * Need to be called with ext4 group lock held
+  */
+ static noinline_for_stack
+-void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
++int ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
+ 					ext4_group_t group)
+ {
+ 	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+ 	struct ext4_prealloc_space *pa;
++	struct ext4_group_desc *gdp;
+ 	struct list_head *cur;
+ 	ext4_group_t groupnr;
+ 	ext4_grpblk_t start;
+ 	int preallocated = 0;
++	int skip = 0, count = 0;
++	int err;
+ 	int len;
+ 
++	gdp = ext4_get_group_desc(sb, group, NULL);
++	if (gdp == NULL)
++		return -EIO;
++
++	/* before applying preallocations, check bitmap consistency */
++	err = ext4_mb_check_ondisk_bitmap(sb, bitmap, gdp, group);
++	if (err)
++		return err;
++
+ 	/* all form of preallocation discards first load group,
+ 	 * so the only competing code is preallocation use.
+ 	 * we don't need any locking here
+@@ -3666,13 +3727,23 @@ void ext4_mb_generate_from_pa(struct sup
+ 					     &groupnr, &start);
+ 		len = pa->pa_len;
+ 		spin_unlock(&pa->pa_lock);
+-		if (unlikely(len == 0))
++		if (unlikely(len == 0)) {
++			skip++;
+ 			continue;
++		}
+ 		BUG_ON(groupnr != group);
+ 		ext4_set_bits(bitmap, start, len);
+ 		preallocated += len;
++		count++;
++	}
++	if (count + skip != grp->bb_prealloc_nr) {
++		ext4_error(sb, "lost preallocations: "
++			   "count %d, bb_prealloc_nr %lu, skip %d\n",
++			   count, grp->bb_prealloc_nr, skip);
++		return -EIO;
+ 	}
+ 	mb_debug(1, "preallocated %u for group %u\n", preallocated, group);
++	return 0;
+ }
+ 
+ static void ext4_mb_pa_callback(struct rcu_head *head)
+@@ -3736,6 +3807,7 @@ static void ext4_mb_put_pa(struct ext4_a
+ 	 */
+ 	ext4_lock_group(sb, grp);
+ 	list_del(&pa->pa_group_list);
++	ext4_get_group_info(sb, grp)->bb_prealloc_nr--;
+ 	ext4_unlock_group(sb, grp);
+ 
+ 	spin_lock(pa->pa_obj_lock);
+@@ -3830,6 +3902,7 @@ ext4_mb_new_inode_pa(struct ext4_allocat
+ 
+ 	ext4_lock_group(sb, ac->ac_b_ex.fe_group);
+ 	list_add(&pa->pa_group_list, &grp->bb_prealloc_list);
++	grp->bb_prealloc_nr++;
+ 	ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
+ 
+ 	spin_lock(pa->pa_obj_lock);
+@@ -3891,6 +3964,7 @@ ext4_mb_new_group_pa(struct ext4_allocat
+ 
+ 	ext4_lock_group(sb, ac->ac_b_ex.fe_group);
+ 	list_add(&pa->pa_group_list, &grp->bb_prealloc_list);
++	grp->bb_prealloc_nr++;
+ 	ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
+ 
+ 	/*
+@@ -4063,6 +4137,8 @@ repeat:
+ 
+ 		spin_unlock(&pa->pa_lock);
+ 
++		BUG_ON(grp->bb_prealloc_nr == 0);
++		grp->bb_prealloc_nr--;
+ 		list_del(&pa->pa_group_list);
+ 		list_add(&pa->u.pa_tmp_list, &list);
+ 	}
+@@ -4193,7 +4269,7 @@ repeat:
+ 		if (err) {
+ 			ext4_error_err(sb, -err, "Error %d loading buddy information for %u",
+ 				       err, group);
+-			continue;
++			return;
+ 		}
+ 
+ 		bitmap_bh = ext4_read_block_bitmap(sb, group);
+@@ -4206,6 +4282,8 @@ repeat:
+ 		}
+ 
+ 		ext4_lock_group(sb, group);
++		BUG_ON(e4b.bd_info->bb_prealloc_nr == 0);
++		e4b.bd_info->bb_prealloc_nr--;
+ 		list_del(&pa->pa_group_list);
+ 		ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa);
+ 		ext4_unlock_group(sb, group);
+@@ -4467,6 +4545,7 @@ ext4_mb_discard_lg_preallocations(struct
+ 		}
+ 		ext4_lock_group(sb, group);
+ 		list_del(&pa->pa_group_list);
++		ext4_get_group_info(sb, group)->bb_prealloc_nr--;
+ 		ext4_mb_release_group_pa(&e4b, pa);
+ 		ext4_unlock_group(sb, group);
+ 
+Index: linux-4.18.0-80.1.2.el8_0/fs/ext4/mballoc.h
+===================================================================
+--- linux-4.18.0-80.1.2.el8_0.orig/fs/ext4/mballoc.h
++++ linux-4.18.0-80.1.2.el8_0/fs/ext4/mballoc.h
+@@ -70,7 +70,7 @@ do {									\
+ /*
+  * for which requests use 2^N search using buddies
+  */
+-#define MB_DEFAULT_ORDER2_REQS		2
++#define MB_DEFAULT_ORDER2_REQS		8
+ 
+ /*
+  * default group prealloc size 512 blocks