LU-8465 e2fsck: serialize fix operations

Allow different threads to fix at the same time could
be dangerous and error-prone now, and most of time
parallel scanning and checking is important.

So this patch adds a mutex to serialize
fix operations during pass1.

And the good benefit of this, we don't need block
allocations and free, superblock updates protection
any more, since only fix operations during pass1
could touch them.

Change-Id: Id19a54db86820d7c50e4b84ad10b2e3cb9d1ff2b
Signed-off-by: Wang Shilong <wshilong@ddn.com>
Reviewed-on: https://review.whamcloud.com/37826
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>

diff --git a/e2fsck/e2fsck.h b/e2fsck/e2fsck.h
index b309558..2072cdc 100644 (file)
--- a/e2fsck/e2fsck.h
+++ b/e2fsck/e2fsck.h
@@ -495,6 +495,10 @@ struct e2fsck_struct {
        __u32                   fs_fragmented_dir;
        __u32                   large_files;
        __u32                   extent_depth_count[MAX_EXTENT_DEPTH_COUNT];
+#ifdef CONFIG_PFSCK
+       /* serialize fix operation for multiple threads */
+       pthread_mutex_t          fs_fix_mutex;
+#endif
 };
 
 #ifdef CONFIG_PFSCK
@@ -785,6 +789,8 @@ extern errcode_t e2fsck_allocate_subcluster_bitmap(ext2_filsys fs,
                                                   const char *profile_name,
                                                   ext2fs_block_bitmap *ret);
 unsigned long long get_memory_size(void);
+extern void e2fsck_pass1_fix_lock(e2fsck_t ctx);
+extern void e2fsck_pass1_fix_unlock(e2fsck_t ctx);
 
 /* unix.c */
 extern void e2fsck_clear_progbar(e2fsck_t ctx);

diff --git a/e2fsck/pass1.c b/e2fsck/pass1.c
index c94b5bc..87ce445 100644 (file)
--- a/e2fsck/pass1.c
+++ b/e2fsck/pass1.c
@@ -407,8 +407,10 @@ static problem_t check_large_ea_inode(e2fsck_t ctx,
                pctx->num = entry->e_value_inum;
                if (fix_problem(ctx, PR_1_ATTR_SET_EA_INODE_FL, pctx)) {
                        inode.i_flags |= EXT4_EA_INODE_FL;
+                       e2fsck_pass1_fix_lock(ctx);
                        ext2fs_write_inode(ctx->fs, entry->e_value_inum,
                                           &inode);
+                       e2fsck_pass1_fix_unlock(ctx);
                } else {
                        return PR_1_ATTR_NO_EA_INODE_FL;
                }
@@ -915,8 +917,11 @@ static errcode_t recheck_bad_inode_checksum(ext2_filsys fs, ext2_ino_t ino,
        if (!fix_problem(ctx, PR_1_INODE_ONLY_CSUM_INVALID, pctx))
                return 0;
 
+
+       e2fsck_pass1_fix_lock(ctx);
        retval = ext2fs_write_inode_full(fs, ino, (struct ext2_inode *)&inode,
                                         sizeof(inode));
+       e2fsck_pass1_fix_unlock(ctx);
        return retval;
 }
 
@@ -1070,15 +1075,19 @@ static void reserve_block_for_root_repair(e2fsck_t ctx)
        errcode_t       err;
        ext2_filsys     fs = ctx->fs;
 
+       e2fsck_pass1_fix_lock(ctx);
        ctx->root_repair_block = 0;
        if (ext2fs_test_inode_bitmap2(ctx->inode_used_map, EXT2_ROOT_INO))
-               return;
+               goto out;
 
        err = ext2fs_new_block2(fs, 0, ctx->block_found_map, &blk);
        if (err)
-               return;
+               goto out;
        ext2fs_mark_block_bitmap2(ctx->block_found_map, blk);
        ctx->root_repair_block = blk;
+out:
+       e2fsck_pass1_fix_unlock(ctx);
+       return;
 }
 
 static void reserve_block_for_lnf_repair(e2fsck_t ctx)
@@ -1089,15 +1098,19 @@ static void reserve_block_for_lnf_repair(e2fsck_t ctx)
        static const char name[] = "lost+found";
        ext2_ino_t      ino;
 
+       e2fsck_pass1_fix_lock(ctx);
        ctx->lnf_repair_block = 0;
        if (!ext2fs_lookup(fs, EXT2_ROOT_INO, name, sizeof(name)-1, 0, &ino))
-               return;
+               goto out;
 
        err = ext2fs_new_block2(fs, 0, ctx->block_found_map, &blk);
        if (err)
-               return;
+               goto out;
        ext2fs_mark_block_bitmap2(ctx->block_found_map, blk);
        ctx->lnf_repair_block = blk;
+out:
+       e2fsck_pass1_fix_unlock(ctx);
+       return;
 }
 
 static errcode_t get_inline_data_ea_size(ext2_filsys fs, ext2_ino_t ino,
@@ -1744,8 +1757,10 @@ void e2fsck_pass1_run(e2fsck_t ctx)
                        pctx.errcode = get_inline_data_ea_size(fs, ino, &size);
                        if (!pctx.errcode &&
                            fix_problem(ctx, PR_1_INLINE_DATA_FEATURE, &pctx)) {
+                               e2fsck_pass1_fix_lock(ctx);
                                ext2fs_set_feature_inline_data(sb);
                                ext2fs_mark_super_dirty(fs);
+                               e2fsck_pass1_fix_unlock(ctx);
                                inlinedata_fs = 1;
                        } else if (fix_problem(ctx, PR_1_INLINE_DATA_SET, &pctx)) {
                                e2fsck_clear_inode(ctx, ino, inode, 0, "pass1");
@@ -1833,9 +1848,11 @@ void e2fsck_pass1_run(e2fsck_t ctx)
                        if ((ext2fs_extent_header_verify(inode->i_block,
                                                 sizeof(inode->i_block)) == 0) &&
                            fix_problem(ctx, PR_1_EXTENT_FEATURE, &pctx)) {
+                               e2fsck_pass1_fix_lock(ctx);
                                ext2fs_set_feature_extents(sb);
                                ext2fs_mark_super_dirty(fs);
                                extent_fs = 1;
+                               e2fsck_pass1_fix_unlock(ctx);
                        } else if (fix_problem(ctx, PR_1_EXTENTS_SET, &pctx)) {
                        clear_inode:
                                e2fsck_clear_inode(ctx, ino, inode, 0, "pass1");
@@ -2282,8 +2299,11 @@ void e2fsck_pass1_run(e2fsck_t ctx)
                ctx->ea_block_quota_inodes = 0;
        }
 
-       if (ctx->invalid_bitmaps)
+       if (ctx->invalid_bitmaps) {
+               e2fsck_pass1_fix_lock(ctx);
                handle_fs_bad_blocks(ctx);
+               e2fsck_pass1_fix_unlock(ctx);
+       }
 
        /* We don't need the block_ea_map any more */
        if (ctx->block_ea_map) {
@@ -2293,7 +2313,9 @@ void e2fsck_pass1_run(e2fsck_t ctx)
 
        if (ctx->flags & E2F_FLAG_RESIZE_INODE) {
                clear_problem_context(&pctx);
+               e2fsck_pass1_fix_lock(ctx);
                pctx.errcode = ext2fs_create_resize_inode(fs);
+               e2fsck_pass1_fix_unlock(ctx);
                if (pctx.errcode) {
                        if (!fix_problem(ctx, PR_1_RESIZE_INODE_CREATE,
                                         &pctx)) {
@@ -3129,6 +3151,7 @@ static void e2fsck_pass1_multithread(e2fsck_t global_ctx)
        int                              num_threads = 1;
        errcode_t                        retval;
 
+       pthread_mutex_init(&global_ctx->fs_fix_mutex, NULL);
        retval = e2fsck_pass1_threads_start(&infos, num_threads, global_ctx);
        if (retval) {
                com_err(global_ctx->program_name, retval,
@@ -3449,6 +3472,18 @@ static _INLINE_ void mark_blocks_used(e2fsck_t ctx, blk64_t block,
        }
 }
 
+static errcode_t _INLINE_ e2fsck_write_ext_attr3(e2fsck_t ctx, blk64_t block,
+                                                void *inbuf, ext2_ino_t inum)
+{
+       errcode_t retval;
+       ext2_filsys fs = ctx->fs;
+
+       e2fsck_pass1_fix_lock(ctx);
+       retval = ext2fs_write_ext_attr3(fs, block, inbuf, inum);
+       e2fsck_pass1_fix_unlock(ctx);
+
+       return retval;
+}
 /*
  * Adjust the extended attribute block's reference counts at the end
  * of pass 1, either by subtracting out references for EA blocks that
@@ -3491,7 +3526,7 @@ static void adjust_extattr_refcount(e2fsck_t ctx, ext2_refcount_t refcount,
                pctx.num = should_be;
                if (fix_problem(ctx, PR_1_EXTATTR_REFCOUNT, &pctx)) {
                        header->h_refcount = should_be;
-                       pctx.errcode = ext2fs_write_ext_attr3(fs, blk,
+                       pctx.errcode = e2fsck_write_ext_attr3(ctx, blk,
                                                             block_buf,
                                                             pctx.ino);
                        if (pctx.errcode) {
@@ -3723,7 +3758,7 @@ static int check_ext_attr(e2fsck_t ctx, struct problem_context *pctx,
         */
        if (failed_csum &&
            fix_problem(ctx, PR_1_EA_BLOCK_ONLY_CSUM_INVALID, pctx)) {
-               pctx->errcode = ext2fs_write_ext_attr3(fs, blk, block_buf,
+               pctx->errcode = e2fsck_write_ext_attr3(ctx, blk, block_buf,
                                                       pctx->ino);
                if (pctx->errcode)
                        return 0;
@@ -4007,10 +4042,12 @@ static void scan_extent_node(e2fsck_t ctx, struct problem_context *pctx,
                if (try_repairs && is_dir && problem == 0 &&
                    (extent.e_flags & EXT2_EXTENT_FLAGS_UNINIT) &&
                    fix_problem(ctx, PR_1_UNINIT_DBLOCK, pctx)) {
+                       e2fsck_pass1_fix_lock(ctx);
                        extent.e_flags &= ~EXT2_EXTENT_FLAGS_UNINIT;
                        pb->inode_modified = 1;
                        pctx->errcode = ext2fs_extent_replace(ehandle, 0,
                                                              &extent);
+                       e2fsck_pass1_fix_unlock(ctx);
                        if (pctx->errcode)
                                return;
                        failed_csum = 0;
@@ -4045,13 +4082,17 @@ report_problem:
                                }
                                e2fsck_read_bitmaps(ctx);
                                pb->inode_modified = 1;
+                               e2fsck_pass1_fix_lock(ctx);
                                pctx->errcode =
                                        ext2fs_extent_delete(ehandle, 0);
+                               e2fsck_pass1_fix_unlock(ctx);
                                if (pctx->errcode) {
                                        pctx->str = "ext2fs_extent_delete";
                                        return;
                                }
+                               e2fsck_pass1_fix_lock(ctx);
                                pctx->errcode = ext2fs_extent_fix_parents(ehandle);
+                               e2fsck_pass1_fix_unlock(ctx);
                                if (pctx->errcode &&
                                    pctx->errcode != EXT2_ET_NO_CURRENT_NODE) {
                                        pctx->str = "ext2fs_extent_fix_parents";
@@ -4115,9 +4156,11 @@ report_problem:
                                pctx->num = e_info.curr_level - 1;
                                problem = PR_1_EXTENT_INDEX_START_INVALID;
                                if (fix_problem(ctx, problem, pctx)) {
+                                       e2fsck_pass1_fix_lock(ctx);
                                        pb->inode_modified = 1;
                                        pctx->errcode =
                                                ext2fs_extent_fix_parents(ehandle);
+                                       e2fsck_pass1_fix_unlock(ctx);
                                        if (pctx->errcode) {
                                                pctx->str = "ext2fs_extent_fix_parents";
                                                return;
@@ -4181,15 +4224,19 @@ report_problem:
                        pctx->blk = extent.e_lblk;
                        pctx->blk2 = new_lblk;
                        if (fix_problem(ctx, PR_1_COLLAPSE_DBLOCK, pctx)) {
+                               e2fsck_pass1_fix_lock(ctx);
                                extent.e_lblk = new_lblk;
                                pb->inode_modified = 1;
                                pctx->errcode = ext2fs_extent_replace(ehandle,
                                                                0, &extent);
+                               e2fsck_pass1_fix_unlock(ctx);
                                if (pctx->errcode) {
                                        pctx->errcode = 0;
                                        goto alloc_later;
                                }
+                               e2fsck_pass1_fix_lock(ctx);
                                pctx->errcode = ext2fs_extent_fix_parents(ehandle);
+                               e2fsck_pass1_fix_unlock(ctx);
                                if (pctx->errcode)
                                        goto failed_add_dir_block;
                                pctx->errcode = ext2fs_extent_goto(ehandle,
@@ -4285,8 +4332,10 @@ alloc_later:
        /* Failed csum but passes checks?  Ask to fix checksum. */
        if (failed_csum &&
            fix_problem(ctx, PR_1_EXTENT_ONLY_CSUM_INVALID, pctx)) {
+               e2fsck_pass1_fix_lock(ctx);
                pb->inode_modified = 1;
                pctx->errcode = ext2fs_extent_replace(ehandle, 0, &extent);
+               e2fsck_pass1_fix_unlock(ctx);
                if (pctx->errcode)
                        return;
        }

diff --git a/e2fsck/util.c b/e2fsck/util.c
index 57aacd2..5ea84b3 100644 (file)
--- a/e2fsck/util.c
+++ b/e2fsck/util.c
@@ -42,6 +42,10 @@
 #include <sys/sysctl.h>
 #endif
 
+#ifdef CONFIG_PFSCK
+#include <pthread.h>
+#endif
+
 #include "e2fsck.h"
 
 extern e2fsck_t e2fsck_global_ctx;   /* Try your very best not to use this! */
@@ -565,13 +569,45 @@ void e2fsck_read_inode_full(e2fsck_t ctx, unsigned long ino,
        }
 }
 
+#ifdef CONFIG_PFSCK
+void e2fsck_pass1_fix_lock(e2fsck_t ctx)
+{
+       e2fsck_t global_ctx = ctx->global_ctx;
+       if (!global_ctx)
+               global_ctx = ctx;
+
+       pthread_mutex_lock(&global_ctx->fs_fix_mutex);
+}
+
+void e2fsck_pass1_fix_unlock(e2fsck_t ctx)
+{
+       e2fsck_t global_ctx = ctx->global_ctx;
+       if (!global_ctx)
+               global_ctx = ctx;
+
+       pthread_mutex_unlock(&global_ctx->fs_fix_mutex);
+}
+#else
+void e2fsck_pass1_fix_lock(e2fsck_t ctx)
+{
+
+}
+
+void e2fsck_pass1_fix_unlock(e2fsck_t ctx)
+{
+
+}
+#endif
+
 void e2fsck_write_inode_full(e2fsck_t ctx, unsigned long ino,
                             struct ext2_inode * inode, int bufsize,
                             const char *proc)
 {
        errcode_t retval;
 
+       e2fsck_pass1_fix_lock(ctx);
        retval = ext2fs_write_inode_full(ctx->fs, ino, inode, bufsize);
+       e2fsck_pass1_fix_unlock(ctx);
        if (retval) {
                com_err("ext2fs_write_inode", retval,
                        _("while writing inode %lu in %s"), ino, proc);
@@ -584,7 +620,9 @@ void e2fsck_write_inode(e2fsck_t ctx, unsigned long ino,
 {
        errcode_t retval;
 
+       e2fsck_pass1_fix_lock(ctx);
        retval = ext2fs_write_inode(ctx->fs, ino, inode);
+       e2fsck_pass1_fix_unlock(ctx);
        if (retval) {
                com_err("ext2fs_write_inode", retval,
                        _("while writing inode %lu in %s"), ino, proc);