summaryrefslogtreecommitdiffstats
path: root/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zio_checksum.c
diff options
context:
space:
mode:
authorpjd <pjd@FreeBSD.org>2011-02-27 19:41:40 +0000
committerpjd <pjd@FreeBSD.org>2011-02-27 19:41:40 +0000
commit1b03c5bf41222b723415638f03e00ed12cac076a (patch)
treeef515cadc08bf427e4d3f1360199ec9827b1596b /sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zio_checksum.c
parentc67d387baf03726323703774b1b320235fb1f24b (diff)
downloadFreeBSD-src-1b03c5bf41222b723415638f03e00ed12cac076a.zip
FreeBSD-src-1b03c5bf41222b723415638f03e00ed12cac076a.tar.gz
Finally... Import the latest open-source ZFS version - (SPA) 28.
Few new things available from now on: - Data deduplication. - Triple parity RAIDZ (RAIDZ3). - zfs diff. - zpool split. - Snapshot holds. - zpool import -F. Allows to rewind corrupted pool to earlier transaction group. - Possibility to import pool in read-only mode. MFC after: 1 month
Diffstat (limited to 'sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zio_checksum.c')
-rw-r--r--sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zio_checksum.c140
1 files changed, 104 insertions, 36 deletions
diff --git a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zio_checksum.c b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zio_checksum.c
index bf7fe73..c8fe20f2 100644
--- a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zio_checksum.c
+++ b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zio_checksum.c
@@ -19,14 +19,15 @@
* CDDL HEADER END
*/
/*
- * Copyright 2008 Sun Microsystems, Inc. All rights reserved.
- * Use is subject to license terms.
+ * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
*/
#include <sys/zfs_context.h>
#include <sys/spa.h>
#include <sys/zio.h>
#include <sys/zio_checksum.h>
+#include <sys/zil.h>
+#include <zfs_fletcher.h>
/*
* Checksum vectors.
@@ -49,13 +50,13 @@
* we want the ability to take advantage of that hardware.
*
* Of course, we don't want a checksum upgrade to invalidate existing
- * data, so we store the checksum *function* in five bits of the DVA.
- * This gives us room for up to 32 different checksum functions.
+ * data, so we store the checksum *function* in eight bits of the bp.
+ * This gives us room for up to 256 different checksum functions.
*
* When writing a block, we always checksum it with the latest-and-greatest
* checksum function of the appropriate strength. When reading a block,
* we compare the expected checksum against the actual checksum, which we
- * compute via the checksum function specified in the DVA encoding.
+ * compute via the checksum function specified by BP_GET_CHECKSUM(bp).
*/
/*ARGSUSED*/
@@ -66,19 +67,20 @@ zio_checksum_off(const void *buf, uint64_t size, zio_cksum_t *zcp)
}
zio_checksum_info_t zio_checksum_table[ZIO_CHECKSUM_FUNCTIONS] = {
- {{NULL, NULL}, 0, 0, "inherit"},
- {{NULL, NULL}, 0, 0, "on"},
- {{zio_checksum_off, zio_checksum_off}, 0, 0, "off"},
- {{zio_checksum_SHA256, zio_checksum_SHA256}, 1, 1, "label"},
- {{zio_checksum_SHA256, zio_checksum_SHA256}, 1, 1, "gang_header"},
- {{fletcher_2_native, fletcher_2_byteswap}, 0, 1, "zilog"},
- {{fletcher_2_native, fletcher_2_byteswap}, 0, 0, "fletcher2"},
- {{fletcher_4_native, fletcher_4_byteswap}, 1, 0, "fletcher4"},
- {{zio_checksum_SHA256, zio_checksum_SHA256}, 1, 0, "SHA256"},
+ {{NULL, NULL}, 0, 0, 0, "inherit"},
+ {{NULL, NULL}, 0, 0, 0, "on"},
+ {{zio_checksum_off, zio_checksum_off}, 0, 0, 0, "off"},
+ {{zio_checksum_SHA256, zio_checksum_SHA256}, 1, 1, 0, "label"},
+ {{zio_checksum_SHA256, zio_checksum_SHA256}, 1, 1, 0, "gang_header"},
+ {{fletcher_2_native, fletcher_2_byteswap}, 0, 1, 0, "zilog"},
+ {{fletcher_2_native, fletcher_2_byteswap}, 0, 0, 0, "fletcher2"},
+ {{fletcher_4_native, fletcher_4_byteswap}, 1, 0, 0, "fletcher4"},
+ {{zio_checksum_SHA256, zio_checksum_SHA256}, 1, 0, 1, "sha256"},
+ {{fletcher_4_native, fletcher_4_byteswap}, 0, 1, 0, "zilog2"},
};
-uint8_t
-zio_checksum_select(uint8_t child, uint8_t parent)
+enum zio_checksum
+zio_checksum_select(enum zio_checksum child, enum zio_checksum parent)
{
ASSERT(child < ZIO_CHECKSUM_FUNCTIONS);
ASSERT(parent < ZIO_CHECKSUM_FUNCTIONS);
@@ -93,6 +95,29 @@ zio_checksum_select(uint8_t child, uint8_t parent)
return (child);
}
+enum zio_checksum
+zio_checksum_dedup_select(spa_t *spa, enum zio_checksum child,
+ enum zio_checksum parent)
+{
+ ASSERT((child & ZIO_CHECKSUM_MASK) < ZIO_CHECKSUM_FUNCTIONS);
+ ASSERT((parent & ZIO_CHECKSUM_MASK) < ZIO_CHECKSUM_FUNCTIONS);
+ ASSERT(parent != ZIO_CHECKSUM_INHERIT && parent != ZIO_CHECKSUM_ON);
+
+ if (child == ZIO_CHECKSUM_INHERIT)
+ return (parent);
+
+ if (child == ZIO_CHECKSUM_ON)
+ return (spa_dedup_checksum(spa));
+
+ if (child == (ZIO_CHECKSUM_ON | ZIO_CHECKSUM_VERIFY))
+ return (spa_dedup_checksum(spa) | ZIO_CHECKSUM_VERIFY);
+
+ ASSERT(zio_checksum_table[child & ZIO_CHECKSUM_MASK].ci_dedup ||
+ (child & ZIO_CHECKSUM_VERIFY) || child == ZIO_CHECKSUM_OFF);
+
+ return (child);
+}
+
/*
* Set the external verifier for a gang block based on <vdev, offset, txg>,
* a tuple which is guaranteed to be unique for the life of the pool.
@@ -101,7 +126,7 @@ static void
zio_checksum_gang_verifier(zio_cksum_t *zcp, blkptr_t *bp)
{
dva_t *dva = BP_IDENTITY(bp);
- uint64_t txg = bp->blk_birth;
+ uint64_t txg = BP_PHYSICAL_BIRTH(bp);
ASSERT(BP_IS_GANG(bp));
@@ -128,47 +153,79 @@ zio_checksum_compute(zio_t *zio, enum zio_checksum checksum,
{
blkptr_t *bp = zio->io_bp;
uint64_t offset = zio->io_offset;
- zio_block_tail_t *zbt = (zio_block_tail_t *)((char *)data + size) - 1;
zio_checksum_info_t *ci = &zio_checksum_table[checksum];
- zio_cksum_t zbt_cksum;
+ zio_cksum_t cksum;
ASSERT((uint_t)checksum < ZIO_CHECKSUM_FUNCTIONS);
ASSERT(ci->ci_func[0] != NULL);
- if (ci->ci_zbt) {
+ if (ci->ci_eck) {
+ zio_eck_t *eck;
+
+ if (checksum == ZIO_CHECKSUM_ZILOG2) {
+ zil_chain_t *zilc = data;
+
+ size = P2ROUNDUP_TYPED(zilc->zc_nused, ZIL_MIN_BLKSZ,
+ uint64_t);
+ eck = &zilc->zc_eck;
+ } else {
+ eck = (zio_eck_t *)((char *)data + size) - 1;
+ }
if (checksum == ZIO_CHECKSUM_GANG_HEADER)
- zio_checksum_gang_verifier(&zbt->zbt_cksum, bp);
+ zio_checksum_gang_verifier(&eck->zec_cksum, bp);
else if (checksum == ZIO_CHECKSUM_LABEL)
- zio_checksum_label_verifier(&zbt->zbt_cksum, offset);
+ zio_checksum_label_verifier(&eck->zec_cksum, offset);
else
- bp->blk_cksum = zbt->zbt_cksum;
- zbt->zbt_magic = ZBT_MAGIC;
- ci->ci_func[0](data, size, &zbt_cksum);
- zbt->zbt_cksum = zbt_cksum;
+ bp->blk_cksum = eck->zec_cksum;
+ eck->zec_magic = ZEC_MAGIC;
+ ci->ci_func[0](data, size, &cksum);
+ eck->zec_cksum = cksum;
} else {
ci->ci_func[0](data, size, &bp->blk_cksum);
}
}
int
-zio_checksum_error(zio_t *zio)
+zio_checksum_error(zio_t *zio, zio_bad_cksum_t *info)
{
blkptr_t *bp = zio->io_bp;
uint_t checksum = (bp == NULL ? zio->io_prop.zp_checksum :
(BP_IS_GANG(bp) ? ZIO_CHECKSUM_GANG_HEADER : BP_GET_CHECKSUM(bp)));
int byteswap;
- void *data = zio->io_data;
+ int error;
uint64_t size = (bp == NULL ? zio->io_size :
(BP_IS_GANG(bp) ? SPA_GANGBLOCKSIZE : BP_GET_PSIZE(bp)));
uint64_t offset = zio->io_offset;
- zio_block_tail_t *zbt = (zio_block_tail_t *)((char *)data + size) - 1;
+ void *data = zio->io_data;
zio_checksum_info_t *ci = &zio_checksum_table[checksum];
zio_cksum_t actual_cksum, expected_cksum, verifier;
if (checksum >= ZIO_CHECKSUM_FUNCTIONS || ci->ci_func[0] == NULL)
return (EINVAL);
- if (ci->ci_zbt) {
+ if (ci->ci_eck) {
+ zio_eck_t *eck;
+
+ if (checksum == ZIO_CHECKSUM_ZILOG2) {
+ zil_chain_t *zilc = data;
+ uint64_t nused;
+
+ eck = &zilc->zc_eck;
+ if (eck->zec_magic == ZEC_MAGIC)
+ nused = zilc->zc_nused;
+ else if (eck->zec_magic == BSWAP_64(ZEC_MAGIC))
+ nused = BSWAP_64(zilc->zc_nused);
+ else
+ return (ECKSUM);
+
+ if (nused > size)
+ return (ECKSUM);
+
+ size = P2ROUNDUP_TYPED(nused, ZIL_MIN_BLKSZ, uint64_t);
+ } else {
+ eck = (zio_eck_t *)((char *)data + size) - 1;
+ }
+
if (checksum == ZIO_CHECKSUM_GANG_HEADER)
zio_checksum_gang_verifier(&verifier, bp);
else if (checksum == ZIO_CHECKSUM_LABEL)
@@ -176,15 +233,15 @@ zio_checksum_error(zio_t *zio)
else
verifier = bp->blk_cksum;
- byteswap = (zbt->zbt_magic == BSWAP_64(ZBT_MAGIC));
+ byteswap = (eck->zec_magic == BSWAP_64(ZEC_MAGIC));
if (byteswap)
byteswap_uint64_array(&verifier, sizeof (zio_cksum_t));
- expected_cksum = zbt->zbt_cksum;
- zbt->zbt_cksum = verifier;
+ expected_cksum = eck->zec_cksum;
+ eck->zec_cksum = verifier;
ci->ci_func[byteswap](data, size, &actual_cksum);
- zbt->zbt_cksum = expected_cksum;
+ eck->zec_cksum = expected_cksum;
if (byteswap)
byteswap_uint64_array(&expected_cksum,
@@ -196,11 +253,22 @@ zio_checksum_error(zio_t *zio)
ci->ci_func[byteswap](data, size, &actual_cksum);
}
+ info->zbc_expected = expected_cksum;
+ info->zbc_actual = actual_cksum;
+ info->zbc_checksum_name = ci->ci_name;
+ info->zbc_byteswapped = byteswap;
+ info->zbc_injected = 0;
+ info->zbc_has_cksum = 1;
+
if (!ZIO_CHECKSUM_EQUAL(actual_cksum, expected_cksum))
return (ECKSUM);
- if (zio_injection_enabled && !zio->io_error)
- return (zio_handle_fault_injection(zio, ECKSUM));
+ if (zio_injection_enabled && !zio->io_error &&
+ (error = zio_handle_fault_injection(zio, ECKSUM)) != 0) {
+
+ info->zbc_injected = 1;
+ return (error);
+ }
return (0);
}
OpenPOWER on IntegriCloud