Message-Id: <20180615174737.4064-1-artem.blagodarenko@gmail.com>
Date:   Fri, 15 Jun 2018 20:47:37 +0300
From:   Artem Blagodarenko <artem.blagodarenko@...il.com>
To:     linux-ext4@...r.kernel.org
Cc:     adilger.kernel@...ger.ca, alexey.lyashkov@...il.com,
        Andreas Dilger <andreas.dilger@...el.com>,
        Jim Garlick <garlick@...l.gov>
Subject: [PATCH] e2fsck: allow deleting or zeroing shared blocks

From: Andreas Dilger <andreas.dilger@...el.com>

E2fsck fixes files that are found to be sharing blocks by cloning
the shared blocks and giving each file a private copy in pass 1D.

Allowing all files claiming the shared blocks to have copies can
inadvertantly bypass access restrictions.  Deleting all the files,
zeroing the cloned blocks, or placing the files in the /lost+found
directory after cloning may be preferable in some secure environments.

The following patches implement config file and command line options
in e2fsck that allow pass 1D behavior to be tuned according to site
policy.  It adds two extended options and config file counterparts.
On the command line:

 -E clone=dup|zero

    Select the block cloning method.  "dup" is old behavior,
    and is the default.  "zero" is a new method that substitutes
    zero-filled blocks for the shared blocks in all the files
    that claim them.

 -E shared=preserve|lost+found|delete

    Select the disposition of files containing shared blocks.
    "preserve" is the old behavior which remains the default.
    "lost+found" causes files to be unlinked after cloning so
    they will be reconnected to /lost+found in pass 3.
    "delete" skips cloning entirely and simply deletes the files.

In the config file:
  [options]
      clone=dup|zero
      shared=preserve|lost+found|delete

Signed-off-by: Jim Garlick <garlick@...l.gov>
Signed-off-by: Andreas Dilger <andreas.dilger@...el.com>
---
 e2fsck/e2fsck.8.in      | 13 +++++++++
 e2fsck/e2fsck.conf.5.in | 13 +++++++++
 e2fsck/e2fsck.h         | 13 +++++++++
 e2fsck/pass1b.c         | 48 +++++++++++++++++++++++++------
 e2fsck/problem.c        |  8 ++++++
 e2fsck/problem.h        |  6 ++++
 e2fsck/unix.c           | 76 +++++++++++++++++++++++++++++++++++++++++++++++++
 7 files changed, 168 insertions(+), 9 deletions(-)

diff --git a/e2fsck/e2fsck.8.in b/e2fsck/e2fsck.8.in
index 1a3bd468..ec6427ee 100644
--- a/e2fsck/e2fsck.8.in
+++ b/e2fsck/e2fsck.8.in
@@ -198,6 +198,19 @@ separated, and may take an argument using the equals ('=') sign.  The
 following options are supported:
 .RS 1.2i
 .TP
+.BI clone= dup|zero
+Resolve files with shared blocks in pass 1D by giving each file a private
+copy of the blocks (dup);
+or replacing the shared blocks with private, zero-filled blocks (zero).
+The default is dup.
+.TP
+.BI shared= preserve|lost+found|delete
+Files with shared blocks discovered in pass 1D are cloned and then left
+in place (preserve);
+cloned and then disconnected from their parent directory,
+then reconnected to /lost+found in pass 3 (lost+found);
+or simply deleted (delete).  The default is preserve.
+.TP
 .BI ea_ver= extended_attribute_version
 Set the version of the extended attribute blocks which
 .B e2fsck
diff --git a/e2fsck/e2fsck.conf.5.in b/e2fsck/e2fsck.conf.5.in
index 708e2134..611ff7cb 100644
--- a/e2fsck/e2fsck.conf.5.in
+++ b/e2fsck/e2fsck.conf.5.in
@@ -147,6 +147,19 @@ will offer to clear
 the test_fs flag if the ext4 filesystem is available on the system.  It
 defaults to true.
 .TP
+.I clone
+This string relation controls the default handling of shared blocks in pass 1D.
+It can be set to dup or zero.  See the
+.I "-E clone"
+option description in e2fsck(8).
+.TP
+.I shared
+This string relation controls the default disposition of files discovered to
+have shared blocks in pass 1D.  It can be set to preserve, lost+found,
+or delete.  See the
+.I "-E shared"
+option description in e2fsck(8).
+.TP
 .I defer_check_on_battery
 This boolean relation controls whether or not the interval between
 filesystem checks (either based on time or number of mounts) should
diff --git a/e2fsck/e2fsck.h b/e2fsck/e2fsck.h
index 5269650f..0014fc2c 100644
--- a/e2fsck/e2fsck.h
+++ b/e2fsck/e2fsck.h
@@ -209,6 +209,17 @@ struct resource_track {
 #define E2F_PASS_5	5
 #define E2F_PASS_1B	6
 
+enum shared_opt {
+	E2F_SHARED_PRESERVE = 0,
+	E2F_SHARED_DELETE,
+	E2F_SHARED_LPF
+};
+
+enum clone_opt {
+	E2F_CLONE_DUP = 0,
+	E2F_CLONE_ZERO
+};
+
 /*
  * Define the extended attribute refcount structure
  */
@@ -383,6 +394,8 @@ struct e2fsck_struct {
 	time_t now;
 	time_t time_fudge;	/* For working around buggy init scripts */
 	int ext_attr_ver;
+	enum shared_opt shared;
+	enum clone_opt clone;
 	profile_t	profile;
 	int blocks_per_page;
 	ext2_u32_list encrypted_dirs;
diff --git a/e2fsck/pass1b.c b/e2fsck/pass1b.c
index 392ff2c6..e63fb083 100644
--- a/e2fsck/pass1b.c
+++ b/e2fsck/pass1b.c
@@ -523,6 +523,9 @@ static void pass1d(e2fsck_t ctx, char *block_buf)
 			q = (struct dup_cluster *) dnode_get(m);
 			if (q->num_bad > 1)
 				file_ok = 0;
+			if (q->num_bad == 1 && (ctx->clone == E2F_CLONE_ZERO ||
+			    ctx->shared != E2F_SHARED_PRESERVE))
+				file_ok = 0;
 			if (check_if_fs_cluster(ctx, s->cluster)) {
 				file_ok = 0;
 				meta_data = 1;
@@ -582,13 +585,26 @@ static void pass1d(e2fsck_t ctx, char *block_buf)
 			fix_problem(ctx, PR_1D_DUP_BLOCKS_DEALT, &pctx);
 			continue;
 		}
-		if (fix_problem(ctx, PR_1D_CLONE_QUESTION, &pctx)) {
+		if (ctx->shared != E2F_SHARED_DELETE &&
+		    fix_problem(ctx, PR_1D_CLONE_QUESTION, &pctx)) {
 			pctx.errcode = clone_file(ctx, ino, p, block_buf);
-			if (pctx.errcode)
+			if (pctx.errcode) {
 				fix_problem(ctx, PR_1D_CLONE_ERROR, &pctx);
-			else
-				continue;
+				goto delete;
+			}
+			if (ctx->shared == E2F_SHARED_LPF &&
+			    fix_problem(ctx, PR_1D_DISCONNECT_QUESTION, &pctx)) {
+				pctx.errcode = ext2fs_unlink(fs, p->dir,
+							     NULL, ino, 0);
+				if (pctx.errcode) {
+					fix_problem(ctx, PR_1D_DISCONNECT_ERROR,
+						    &pctx);
+					goto delete;
+				}
+			}
+			continue;
 		}
+delete:
 		if (fix_problem(ctx, PR_1D_DELETE_QUESTION, &pctx))
 			delete_file(ctx, ino, p, block_buf);
 		else
@@ -606,7 +622,8 @@ static void decrement_badcount(e2fsck_t ctx, blk64_t block,
 {
 	p->num_bad--;
 	if (p->num_bad <= 0 ||
-	    (p->num_bad == 1 && !check_if_fs_block(ctx, block))) {
+	    (p->num_bad == 1 && !check_if_fs_block(ctx, block) &&
+	    ctx->clone == E2F_CLONE_DUP)) {
 		if (check_if_fs_cluster(ctx, EXT2FS_B2C(ctx->fs, block)))
 			return;
 		ext2fs_unmark_block_bitmap2(ctx->block_dup_map, block);
@@ -799,6 +816,14 @@ static int clone_file_block(ext2_filsys fs,
 
 		p = (struct dup_cluster *) dnode_get(n);
 
+		if (!is_meta) {
+			if (ctx->clone == E2F_CLONE_ZERO && p->num_bad == 0) {
+				ext2fs_unmark_block_bitmap2(ctx->block_found_map,
+							    *block_nr);
+				ext2fs_block_alloc_stats(fs, *block_nr, -1);
+			}
+		}
+
 		cs->dup_cluster = c;
 		/*
 		 * Let's try an implied cluster allocation.  If we get the same
@@ -838,10 +863,15 @@ cluster_alloc_ok:
  		printf("Cloning block #%lld from %llu to %llu\n",
 		       blockcnt, *block_nr, new_block);
 #endif
-		retval = io_channel_read_blk64(fs->io, *block_nr, 1, cs->buf);
-		if (retval) {
-			cs->errcode = retval;
-			return BLOCK_ABORT;
+		if (ctx->clone == E2F_CLONE_ZERO) {
+			memset(cs->buf, 0, fs->blocksize);
+		} else {
+			retval = io_channel_read_blk64(fs->io, *block_nr, 1,
+						       cs->buf);
+			if (retval) {
+				cs->errcode = retval;
+				return BLOCK_ABORT;
+			}
 		}
 		retval = io_channel_write_blk64(fs->io, new_block, 1, cs->buf);
 		if (retval) {
diff --git a/e2fsck/problem.c b/e2fsck/problem.c
index edc9d51f..4c1d8628 100644
--- a/e2fsck/problem.c
+++ b/e2fsck/problem.c
@@ -1264,6 +1264,14 @@ static struct e2fsck_problem problem_table[] = {
 	{ PR_1D_CLONE_ERROR,
 	  N_("Couldn't clone file: %m\n"), PROMPT_NONE, 0 },
 
+	/* File with shared blocks found */
+	{ PR_1D_DISCONNECT_QUESTION,
+	  N_("File with shared blocks found\n"), PROMPT_CONNECT, 0 },
+
+	/* Couldn't unlink file (error) */
+	{ PR_1D_DISCONNECT_ERROR,
+	  N_("Couldn't unlink file: %m\n"), PROMPT_NONE, 0 },
+
 	/* Pass 1E Extent tree optimization	*/
 
 	/* Pass 1E: Optimizing extent trees */
diff --git a/e2fsck/problem.h b/e2fsck/problem.h
index 482d111a..516cbc35 100644
--- a/e2fsck/problem.h
+++ b/e2fsck/problem.h
@@ -751,6 +751,12 @@ struct problem_context {
 /* Couldn't clone file (error) */
 #define PR_1D_CLONE_ERROR	0x013008
 
+/* File with shared blocks found */
+#define PR_1D_DISCONNECT_QUESTION 0x013009
+
+/* Couldn't unlink file (error) */
+#define PR_1D_DISCONNECT_ERROR	0x01300A
+
 /*
  * Pass 1e --- rebuilding extent trees
  */
diff --git a/e2fsck/unix.c b/e2fsck/unix.c
index 0294f5bd..e1de9060 100644
--- a/e2fsck/unix.c
+++ b/e2fsck/unix.c
@@ -649,6 +649,49 @@ static void signal_cancel(int sig EXT2FS_ATTR((unused)))
 }
 #endif
 
+static void initialize_profile_options(e2fsck_t ctx)
+{
+	char *tmp;
+
+	/* [options] shared=preserve|lost+found|delete */
+	tmp = NULL;
+	ctx->shared = E2F_SHARED_PRESERVE;
+	profile_get_string(ctx->profile, "options", "shared", 0,
+			   "preserve", &tmp);
+	if (tmp) {
+		if (strcmp(tmp, "preserve") == 0)
+			ctx->shared = E2F_SHARED_PRESERVE;
+		else if (strcmp(tmp, "delete") == 0)
+			ctx->shared = E2F_SHARED_DELETE;
+		else if (strcmp(tmp, "lost+found") == 0)
+			ctx->shared = E2F_SHARED_LPF;
+		else {
+			com_err(ctx->program_name, 0,
+				_("configuration error: 'shared=%s'"), tmp);
+			fatal_error(ctx, 0);
+		}
+		free(tmp);
+	}
+
+	/* [options] clone=dup|zero */
+	tmp = NULL;
+	ctx->clone = E2F_CLONE_DUP;
+	profile_get_string(ctx->profile, "options", "clone", 0,
+			   "dup", &tmp);
+	if (tmp) {
+		if (strcmp(tmp, "dup") == 0)
+			ctx->clone = E2F_CLONE_DUP;
+		else if (strcmp(tmp, "zero") == 0)
+			ctx->clone = E2F_CLONE_ZERO;
+		else {
+			com_err(ctx->program_name, 0,
+				_("configuration error: 'clone=%s'"), tmp);
+			fatal_error(ctx, 0);
+		}
+		free(tmp);
+	}
+}
+
 static void parse_extended_opts(e2fsck_t ctx, const char *opts)
 {
 	char	*buf, *token, *next, *p, *arg;
@@ -699,6 +742,36 @@ static void parse_extended_opts(e2fsck_t ctx, const char *opts)
 		} else if (strcmp(token, "fragcheck") == 0) {
 			ctx->options |= E2F_OPT_FRAGCHECK;
 			continue;
+		/* -E shared=preserve|lost+found|delete */
+		} else if (strcmp(token, "shared") == 0) {
+			if (!arg) {
+				extended_usage++;
+				continue;
+			}
+			if (strcmp(arg, "preserve") == 0) {
+				ctx->shared = E2F_SHARED_PRESERVE;
+			} else if (strcmp(arg, "lost+found") == 0) {
+				ctx->shared = E2F_SHARED_LPF;
+			} else if (strcmp(arg, "delete") == 0) {
+				ctx->shared = E2F_SHARED_DELETE;
+			} else {
+				extended_usage++;
+				continue;
+			}
+		/* -E clone=dup|zero */
+		} else if (strcmp(token, "clone") == 0) {
+			if (!arg) {
+				extended_usage++;
+				continue;
+			}
+			if (strcmp(arg, "dup") == 0) {
+				ctx->clone = E2F_CLONE_DUP;
+			} else if (strcmp(arg, "zero") == 0) {
+				ctx->clone = E2F_CLONE_ZERO;
+			} else {
+				extended_usage++;
+				continue;
+			}
 		} else if (strcmp(token, "journal_only") == 0) {
 			if (arg) {
 				extended_usage++;
@@ -760,6 +833,7 @@ static void parse_extended_opts(e2fsck_t ctx, const char *opts)
 		fputs(_("\treadahead_kb=<buffer size>\n"), stderr);
 		fputs("\tbmap2extent\n", stderr);
 		fputs("\tfixes_only\n", stderr);
+		fputs(("\tclone=<dup|zero>\n"), stderr);
 		fputc('\n', stderr);
 		exit(1);
 	}
@@ -844,6 +918,8 @@ static errcode_t PRS(int argc, char *argv[], e2fsck_t *ret_ctx)
 	if (c)
 		ctx->options |= E2F_OPT_ICOUNT_FULLMAP;
 
+	initialize_profile_options(ctx);
+
 	phys_mem_kb = get_memory_size() / 1024;
 	ctx->readahead_kb = ~0ULL;
 	while ((c = getopt(argc, argv, "panyrcC:B:dE:fvtFVM:b:I:j:P:l:L:N:SsDkz:")) != EOF)
-- 
2.14.3

Powered by blists - more mailing lists