/*
|
* GRUB -- GRand Unified Bootloader
|
* Copyright (C) 1999,2000,2001,2002,2003,2004 Free Software Foundation, Inc.
|
*
|
* SPDX-License-Identifier: GPL-2.0+
|
*/
|
/*
|
* Copyright (c) 2008, 2011, Oracle and/or its affiliates. All rights reserved.
|
*/
|
|
#ifndef ZFS_SPA_HEADER
|
#define ZFS_SPA_HEADER 1
|
|
|
/*
|
* General-purpose 32-bit and 64-bit bitfield encodings.
|
*/
|
#define BF32_DECODE(x, low, len) P2PHASE((x) >> (low), 1U << (len))
|
#define BF64_DECODE(x, low, len) P2PHASE((x) >> (low), 1ULL << (len))
|
#define BF32_ENCODE(x, low, len) (P2PHASE((x), 1U << (len)) << (low))
|
#define BF64_ENCODE(x, low, len) (P2PHASE((x), 1ULL << (len)) << (low))
|
|
#define BF32_GET(x, low, len) BF32_DECODE(x, low, len)
|
#define BF64_GET(x, low, len) BF64_DECODE(x, low, len)
|
|
#define BF32_SET(x, low, len, val) \
|
((x) ^= BF32_ENCODE((x >> low) ^ (val), low, len))
|
#define BF64_SET(x, low, len, val) \
|
((x) ^= BF64_ENCODE((x >> low) ^ (val), low, len))
|
|
#define BF32_GET_SB(x, low, len, shift, bias) \
|
((BF32_GET(x, low, len) + (bias)) << (shift))
|
#define BF64_GET_SB(x, low, len, shift, bias) \
|
((BF64_GET(x, low, len) + (bias)) << (shift))
|
|
#define BF32_SET_SB(x, low, len, shift, bias, val) \
|
BF32_SET(x, low, len, ((val) >> (shift)) - (bias))
|
#define BF64_SET_SB(x, low, len, shift, bias, val) \
|
BF64_SET(x, low, len, ((val) >> (shift)) - (bias))
|
|
/*
|
* We currently support nine block sizes, from 512 bytes to 128K.
|
* We could go higher, but the benefits are near-zero and the cost
|
* of COWing a giant block to modify one byte would become excessive.
|
*/
|
#define SPA_MINBLOCKSHIFT 9
|
#define SPA_MAXBLOCKSHIFT 17
|
#define SPA_MINBLOCKSIZE (1ULL << SPA_MINBLOCKSHIFT)
|
#define SPA_MAXBLOCKSIZE (1ULL << SPA_MAXBLOCKSHIFT)
|
|
#define SPA_BLOCKSIZES (SPA_MAXBLOCKSHIFT - SPA_MINBLOCKSHIFT + 1)
|
|
/*
|
* Size of block to hold the configuration data (a packed nvlist)
|
*/
|
#define SPA_CONFIG_BLOCKSIZE (1 << 14)
|
|
/*
|
* The DVA size encodings for LSIZE and PSIZE support blocks up to 32MB.
|
* The ASIZE encoding should be at least 64 times larger (6 more bits)
|
* to support up to 4-way RAID-Z mirror mode with worst-case gang block
|
* overhead, three DVAs per bp, plus one more bit in case we do anything
|
* else that expands the ASIZE.
|
*/
|
#define SPA_LSIZEBITS 16 /* LSIZE up to 32M (2^16 * 512) */
|
#define SPA_PSIZEBITS 16 /* PSIZE up to 32M (2^16 * 512) */
|
#define SPA_ASIZEBITS 24 /* ASIZE up to 64 times larger */
|
|
/*
|
* All SPA data is represented by 128-bit data virtual addresses (DVAs).
|
* The members of the dva_t should be considered opaque outside the SPA.
|
*/
|
typedef struct dva {
|
uint64_t dva_word[2];
|
} dva_t;
|
|
/*
|
* Each block has a 256-bit checksum -- strong enough for cryptographic hashes.
|
*/
|
typedef struct zio_cksum {
|
uint64_t zc_word[4];
|
} zio_cksum_t;
|
|
/*
|
* Each block is described by its DVAs, time of birth, checksum, etc.
|
* The word-by-word, bit-by-bit layout of the blkptr is as follows:
|
*
|
* 64 56 48 40 32 24 16 8 0
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* 0 | vdev1 | GRID | ASIZE |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* 1 |G| offset1 |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* 2 | vdev2 | GRID | ASIZE |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* 3 |G| offset2 |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* 4 | vdev3 | GRID | ASIZE |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* 5 |G| offset3 |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* 6 |BDX|lvl| type | cksum | comp | PSIZE | LSIZE |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* 7 | padding |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* 8 | padding |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* 9 | physical birth txg |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* a | logical birth txg |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* b | fill count |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* c | checksum[0] |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* d | checksum[1] |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* e | checksum[2] |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
* f | checksum[3] |
|
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
*
|
* Legend:
|
*
|
* vdev virtual device ID
|
* offset offset into virtual device
|
* LSIZE logical size
|
* PSIZE physical size (after compression)
|
* ASIZE allocated size (including RAID-Z parity and gang block headers)
|
* GRID RAID-Z layout information (reserved for future use)
|
* cksum checksum function
|
* comp compression function
|
* G gang block indicator
|
* B byteorder (endianness)
|
* D dedup
|
* X unused
|
* lvl level of indirection
|
* type DMU object type
|
* phys birth txg of block allocation; zero if same as logical birth txg
|
* log. birth transaction group in which the block was logically born
|
* fill count number of non-zero blocks under this bp
|
* checksum[4] 256-bit checksum of the data this bp describes
|
*/
|
#define SPA_BLKPTRSHIFT 7 /* blkptr_t is 128 bytes */
|
#define SPA_DVAS_PER_BP 3 /* Number of DVAs in a bp */
|
|
typedef struct blkptr {
|
dva_t blk_dva[SPA_DVAS_PER_BP]; /* Data Virtual Addresses */
|
uint64_t blk_prop; /* size, compression, type, etc */
|
uint64_t blk_pad[2]; /* Extra space for the future */
|
uint64_t blk_phys_birth; /* txg when block was allocated */
|
uint64_t blk_birth; /* transaction group at birth */
|
uint64_t blk_fill; /* fill count */
|
zio_cksum_t blk_cksum; /* 256-bit checksum */
|
} blkptr_t;
|
|
/*
|
* Macros to get and set fields in a bp or DVA.
|
*/
|
#define DVA_GET_ASIZE(dva) \
|
BF64_GET_SB((dva)->dva_word[0], 0, 24, SPA_MINBLOCKSHIFT, 0)
|
#define DVA_SET_ASIZE(dva, x) \
|
BF64_SET_SB((dva)->dva_word[0], 0, 24, SPA_MINBLOCKSHIFT, 0, x)
|
|
#define DVA_GET_GRID(dva) BF64_GET((dva)->dva_word[0], 24, 8)
|
#define DVA_SET_GRID(dva, x) BF64_SET((dva)->dva_word[0], 24, 8, x)
|
|
#define DVA_GET_VDEV(dva) BF64_GET((dva)->dva_word[0], 32, 32)
|
#define DVA_SET_VDEV(dva, x) BF64_SET((dva)->dva_word[0], 32, 32, x)
|
|
#define DVA_GET_GANG(dva) BF64_GET((dva)->dva_word[1], 63, 1)
|
#define DVA_SET_GANG(dva, x) BF64_SET((dva)->dva_word[1], 63, 1, x)
|
|
#define BP_GET_LSIZE(bp) \
|
BF64_GET_SB((bp)->blk_prop, 0, 16, SPA_MINBLOCKSHIFT, 1)
|
#define BP_SET_LSIZE(bp, x) \
|
BF64_SET_SB((bp)->blk_prop, 0, 16, SPA_MINBLOCKSHIFT, 1, x)
|
|
#define BP_GET_COMPRESS(bp) BF64_GET((bp)->blk_prop, 32, 8)
|
#define BP_SET_COMPRESS(bp, x) BF64_SET((bp)->blk_prop, 32, 8, x)
|
|
#define BP_GET_CHECKSUM(bp) BF64_GET((bp)->blk_prop, 40, 8)
|
#define BP_SET_CHECKSUM(bp, x) BF64_SET((bp)->blk_prop, 40, 8, x)
|
|
#define BP_GET_TYPE(bp) BF64_GET((bp)->blk_prop, 48, 8)
|
#define BP_SET_TYPE(bp, x) BF64_SET((bp)->blk_prop, 48, 8, x)
|
|
#define BP_GET_LEVEL(bp) BF64_GET((bp)->blk_prop, 56, 5)
|
#define BP_SET_LEVEL(bp, x) BF64_SET((bp)->blk_prop, 56, 5, x)
|
|
#define BP_GET_PROP_BIT_61(bp) BF64_GET((bp)->blk_prop, 61, 1)
|
#define BP_SET_PROP_BIT_61(bp, x) BF64_SET((bp)->blk_prop, 61, 1, x)
|
|
#define BP_GET_DEDUP(bp) BF64_GET((bp)->blk_prop, 62, 1)
|
#define BP_SET_DEDUP(bp, x) BF64_SET((bp)->blk_prop, 62, 1, x)
|
|
#define BP_GET_BYTEORDER(bp) (0 - BF64_GET((bp)->blk_prop, 63, 1))
|
#define BP_SET_BYTEORDER(bp, x) BF64_SET((bp)->blk_prop, 63, 1, x)
|
|
#define BP_PHYSICAL_BIRTH(bp) \
|
((bp)->blk_phys_birth ? (bp)->blk_phys_birth : (bp)->blk_birth)
|
|
#define BP_SET_BIRTH(bp, logical, physical) \
|
{ \
|
(bp)->blk_birth = (logical); \
|
(bp)->blk_phys_birth = ((logical) == (physical) ? 0 : (physical)); \
|
}
|
|
#define BP_GET_ASIZE(bp) \
|
(DVA_GET_ASIZE(&(bp)->blk_dva[0]) + DVA_GET_ASIZE(&(bp)->blk_dva[1]) + \
|
DVA_GET_ASIZE(&(bp)->blk_dva[2]))
|
|
#define BP_GET_UCSIZE(bp) \
|
((BP_GET_LEVEL(bp) > 0 || dmu_ot[BP_GET_TYPE(bp)].ot_metadata) ? \
|
BP_GET_PSIZE(bp) : BP_GET_LSIZE(bp));
|
|
#define BP_GET_NDVAS(bp) \
|
(!!DVA_GET_ASIZE(&(bp)->blk_dva[0]) + \
|
!!DVA_GET_ASIZE(&(bp)->blk_dva[1]) + \
|
!!DVA_GET_ASIZE(&(bp)->blk_dva[2]))
|
|
#define BP_COUNT_GANG(bp) \
|
(DVA_GET_GANG(&(bp)->blk_dva[0]) + \
|
DVA_GET_GANG(&(bp)->blk_dva[1]) + \
|
DVA_GET_GANG(&(bp)->blk_dva[2]))
|
|
#define DVA_EQUAL(dva1, dva2) \
|
((dva1)->dva_word[1] == (dva2)->dva_word[1] && \
|
(dva1)->dva_word[0] == (dva2)->dva_word[0])
|
|
#define BP_EQUAL(bp1, bp2) \
|
(BP_PHYSICAL_BIRTH(bp1) == BP_PHYSICAL_BIRTH(bp2) && \
|
DVA_EQUAL(&(bp1)->blk_dva[0], &(bp2)->blk_dva[0]) && \
|
DVA_EQUAL(&(bp1)->blk_dva[1], &(bp2)->blk_dva[1]) && \
|
DVA_EQUAL(&(bp1)->blk_dva[2], &(bp2)->blk_dva[2]))
|
|
#define ZIO_CHECKSUM_EQUAL(zc1, zc2) \
|
(0 == (((zc1).zc_word[0] - (zc2).zc_word[0]) | \
|
((zc1).zc_word[1] - (zc2).zc_word[1]) | \
|
((zc1).zc_word[2] - (zc2).zc_word[2]) | \
|
((zc1).zc_word[3] - (zc2).zc_word[3])))
|
|
#define DVA_IS_VALID(dva) (DVA_GET_ASIZE(dva) != 0)
|
|
#define ZIO_SET_CHECKSUM(zcp, w0, w1, w2, w3) \
|
{ \
|
(zcp)->zc_word[0] = w0; \
|
(zcp)->zc_word[1] = w1; \
|
(zcp)->zc_word[2] = w2; \
|
(zcp)->zc_word[3] = w3; \
|
}
|
|
#define BP_IDENTITY(bp) (&(bp)->blk_dva[0])
|
#define BP_IS_GANG(bp) DVA_GET_GANG(BP_IDENTITY(bp))
|
#define BP_IS_HOLE(bp) ((bp)->blk_birth == 0)
|
|
/* BP_IS_RAIDZ(bp) assumes no block compression */
|
#define BP_IS_RAIDZ(bp) (DVA_GET_ASIZE(&(bp)->blk_dva[0]) > \
|
BP_GET_PSIZE(bp))
|
|
#define BP_ZERO(bp) \
|
{ \
|
(bp)->blk_dva[0].dva_word[0] = 0; \
|
(bp)->blk_dva[0].dva_word[1] = 0; \
|
(bp)->blk_dva[1].dva_word[0] = 0; \
|
(bp)->blk_dva[1].dva_word[1] = 0; \
|
(bp)->blk_dva[2].dva_word[0] = 0; \
|
(bp)->blk_dva[2].dva_word[1] = 0; \
|
(bp)->blk_prop = 0; \
|
(bp)->blk_pad[0] = 0; \
|
(bp)->blk_pad[1] = 0; \
|
(bp)->blk_phys_birth = 0; \
|
(bp)->blk_birth = 0; \
|
(bp)->blk_fill = 0; \
|
ZIO_SET_CHECKSUM(&(bp)->blk_cksum, 0, 0, 0, 0); \
|
}
|
|
#define BP_SPRINTF_LEN 320
|
|
#endif /* ! ZFS_SPA_HEADER */
|
