Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull Ext4 updates from Theodore Ts'o:
 "The major new feature added in this update is Darrick J Wong's
  metadata checksum feature, which adds crc32 checksums to ext4's
  metadata fields.

  There is also the usual set of cleanups and bug fixes."

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (44 commits)
  ext4: hole-punch use truncate_pagecache_range
  jbd2: use kmem_cache_zalloc wrapper instead of flag
  ext4: remove mb_groups before tearing down the buddy_cache
  ext4: add ext4_mb_unload_buddy in the error path
  ext4: don't trash state flags in EXT4_IOC_SETFLAGS
  ext4: let getattr report the right blocks in delalloc+bigalloc
  ext4: add missing save_error_info() to ext4_error()
  ext4: add debugging trigger for ext4_error()
  ext4: protect group inode free counting with group lock
  ext4: use consistent ssize_t type in ext4_file_write()
  ext4: fix format flag in ext4_ext_binsearch_idx()
  ext4: cleanup in ext4_discard_allocated_blocks()
  ext4: return ENOMEM when mounts fail due to lack of memory
  ext4: remove redundundant "(char *) bh->b_data" casts
  ext4: disallow hard-linked directory in ext4_lookup
  ext4: fix potential integer overflow in alloc_flex_gd()
  ext4: remove needs_recovery in ext4_mb_init()
  ext4: force ro mount if ext4_setup_super() fails
  ext4: fix potential NULL dereference in ext4_free_inodes_counts()
  ext4/jbd2: add metadata checksumming to the list of supported features
  ...

2 files changed, 58 insertions, 3 deletions

diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 912c30a8ddb1..f334c7fab967 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -31,6 +31,7 @@
 #include <linux/mutex.h>
 #include <linux/timer.h>
 #include <linux/slab.h>
+#include <crypto/hash.h>
 #endif
 
 #define journal_oom_retry 1
@@ -147,12 +148,24 @@ typedef struct journal_header_s
 #define JBD2_CRC32_CHKSUM   1
 #define JBD2_MD5_CHKSUM     2
 #define JBD2_SHA1_CHKSUM    3
+#define JBD2_CRC32C_CHKSUM  4
 
 #define JBD2_CRC32_CHKSUM_SIZE 4
 
 #define JBD2_CHECKSUM_BYTES (32 / sizeof(u32))
 /*
  * Commit block header for storing transactional checksums:
+ *
+ * NOTE: If FEATURE_COMPAT_CHECKSUM (checksum v1) is set, the h_chksum*
+ * fields are used to store a checksum of the descriptor and data blocks.
+ *
+ * If FEATURE_INCOMPAT_CSUM_V2 (checksum v2) is set, then the h_chksum
+ * field is used to store crc32c(uuid+commit_block).  Each journal metadata
+ * block gets its own checksum, and data block checksums are stored in
+ * journal_block_tag (in the descriptor).  The other h_chksum* fields are
+ * not used.
+ *
+ * Checksum v1 and v2 are mutually exclusive features.
  */
 struct commit_header {
         __be32          h_magic;
@@ -175,13 +188,19 @@ struct commit_header {
 typedef struct journal_block_tag_s
 {
         __be32          t_blocknr;      /* The on-disk block number */
-        __be32          t_flags;        /* See below */
+        __be16          t_checksum;     /* truncated crc32c(uuid+seq+block) */
+        __be16          t_flags;        /* See below */
         __be32          t_blocknr_high; /* most-significant high 32bits. */
 } journal_block_tag_t;
 
 #define JBD2_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high))
 #define JBD2_TAG_SIZE64 (sizeof(journal_block_tag_t))
 
+/* Tail of descriptor block, for checksumming */
+struct jbd2_journal_block_tail {
+        __be32          t_checksum;     /* crc32c(uuid+descr_block) */
+};
+
 /*
  * The revoke descriptor: used on disk to describe a series of blocks to
  * be revoked from the log
@@ -192,6 +211,10 @@ typedef struct jbd2_journal_revoke_header_s
         __be32           r_count;       /* Count of bytes used in the block */
 } jbd2_journal_revoke_header_t;
 
+/* Tail of revoke block, for checksumming */
+struct jbd2_journal_revoke_tail {
+        __be32          r_checksum;     /* crc32c(uuid+revoke_block) */
+};
 
 /* Definitions for the journal tag flags word: */
 #define JBD2_FLAG_ESCAPE                1       /* on-disk block is escaped */
@@ -241,7 +264,10 @@ typedef struct journal_superblock_s
         __be32  s_max_trans_data;       /* Limit of data blocks per trans. */
 
 /* 0x0050 */
-        __u32   s_padding[44];
+        __u8    s_checksum_type;        /* checksum type */
+        __u8    s_padding2[3];
+        __u32   s_padding[42];
+        __be32  s_checksum;             /* crc32c(superblock) */
 
 /* 0x0100 */
         __u8    s_users[16*48];         /* ids of all fs'es sharing the log */
@@ -263,13 +289,15 @@ typedef struct journal_superblock_s
 #define JBD2_FEATURE_INCOMPAT_REVOKE            0x00000001
 #define JBD2_FEATURE_INCOMPAT_64BIT             0x00000002
 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT      0x00000004
+#define JBD2_FEATURE_INCOMPAT_CSUM_V2           0x00000008
 
 /* Features known to this kernel version: */
 #define JBD2_KNOWN_COMPAT_FEATURES      JBD2_FEATURE_COMPAT_CHECKSUM
 #define JBD2_KNOWN_ROCOMPAT_FEATURES    0
 #define JBD2_KNOWN_INCOMPAT_FEATURES    (JBD2_FEATURE_INCOMPAT_REVOKE | \
                                         JBD2_FEATURE_INCOMPAT_64BIT | \
-                                        JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)
+                                        JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \
+                                        JBD2_FEATURE_INCOMPAT_CSUM_V2)
 
 #ifdef __KERNEL__
 
@@ -939,6 +967,12 @@ struct journal_s
          * superblock pointer here
          */
         void *j_private;
+
+        /* Reference to checksum algorithm driver via cryptoapi */
+        struct crypto_shash *j_chksum_driver;
+
+        /* Precomputed journal UUID checksum for seeding other checksums */
+        __u32 j_csum_seed;
 };
 
 /*
@@ -1268,6 +1302,25 @@ static inline int jbd_space_needed(journal_t *journal)
 
 extern int jbd_blocks_per_page(struct inode *inode);
 
+static inline u32 jbd2_chksum(journal_t *journal, u32 crc,
+                              const void *address, unsigned int length)
+{
+        struct {
+                struct shash_desc shash;
+                char ctx[crypto_shash_descsize(journal->j_chksum_driver)];
+        } desc;
+        int err;
+
+        desc.shash.tfm = journal->j_chksum_driver;
+        desc.shash.flags = 0;
+        *(u32 *)desc.ctx = crc;
+
+        err = crypto_shash_update(&desc.shash, address, length);
+        BUG_ON(err);
+
+        return *(u32 *)desc.ctx;
+}
+
 #ifdef __KERNEL__
 
 #define buffer_trace_init(bh)   do {} while (0)
diff --git a/include/linux/jbd_common.h b/include/linux/jbd_common.h
index 6230f8556a4e..6133679bc4c0 100644
--- a/include/linux/jbd_common.h
+++ b/include/linux/jbd_common.h
@@ -12,6 +12,7 @@ enum jbd_state_bits {
         BH_State,               /* Pins most journal_head state */
         BH_JournalHead,         /* Pins bh->b_private and jh->b_bh */
         BH_Unshadow,            /* Dummy bit, for BJ_Shadow wakeup filtering */
+        BH_Verified,            /* Metadata block has been verified ok */
         BH_JBDPrivateStart,     /* First bit available for private use by FS */
 };
 
@@ -24,6 +25,7 @@ TAS_BUFFER_FNS(Revoked, revoked)
 BUFFER_FNS(RevokeValid, revokevalid)
 TAS_BUFFER_FNS(RevokeValid, revokevalid)
 BUFFER_FNS(Freed, freed)
+BUFFER_FNS(Verified, verified)
 
 static inline struct buffer_head *jh2bh(struct journal_head *jh)
 {