mirror_zfs/include/sys/abd.h
Matthew Ahrens e2af2acce3
allow callers to allocate and provide the abd_t struct
The `abd_get_offset_*()` routines create an abd_t that references
another abd_t, and doesn't allocate any pages/buffers of its own.  In
some workloads, these routines may be called frequently, to create many
abd_t's representing small pieces of a single large abd_t.  In
particular, the upcoming RAIDZ Expansion project makes heavy use of
these routines.

This commit adds the ability for the caller to allocate and provide the
abd_t struct to a variant of `abd_get_offset_*()`.  This eliminates the
cost of allocating the abd_t and performing the accounting associated
with it (`abdstat_struct_size`).  The RAIDZ/DRAID code uses this for
the `rc_abd`, which references the zio's abd.  The upcoming RAIDZ
Expansion project will leverage this infrastructure to increase
performance of reads post-expansion by around 50%.

Additionally, some of the interfaces around creating and destroying
abd_t's are cleaned up.  Most significantly, the distinction between
`abd_put()` and `abd_free()` is eliminated; all types of abd_t's are
now disposed of with `abd_free()`.

Reviewed-by: Brian Atkinson <batkinson@lanl.gov>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Issue #8853 
Closes #11439
2021-01-20 11:24:37 -08:00

220 lines
5.8 KiB
C

/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or http://www.opensolaris.org/os/licensing.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright (c) 2014 by Chunwei Chen. All rights reserved.
* Copyright (c) 2016, 2019 by Delphix. All rights reserved.
*/
#ifndef _ABD_H
#define _ABD_H
#include <sys/isa_defs.h>
#include <sys/debug.h>
#include <sys/zfs_refcount.h>
#include <sys/uio.h>
#ifdef __cplusplus
extern "C" {
#endif
typedef enum abd_flags {
ABD_FLAG_LINEAR = 1 << 0, /* is buffer linear (or scattered)? */
ABD_FLAG_OWNER = 1 << 1, /* does it own its data buffers? */
ABD_FLAG_META = 1 << 2, /* does this represent FS metadata? */
ABD_FLAG_MULTI_ZONE = 1 << 3, /* pages split over memory zones */
ABD_FLAG_MULTI_CHUNK = 1 << 4, /* pages split over multiple chunks */
ABD_FLAG_LINEAR_PAGE = 1 << 5, /* linear but allocd from page */
ABD_FLAG_GANG = 1 << 6, /* mult ABDs chained together */
ABD_FLAG_GANG_FREE = 1 << 7, /* gang ABD is responsible for mem */
ABD_FLAG_ZEROS = 1 << 8, /* ABD for zero-filled buffer */
ABD_FLAG_ALLOCD = 1 << 9, /* we allocated the abd_t */
} abd_flags_t;
typedef struct abd {
abd_flags_t abd_flags;
uint_t abd_size; /* excludes scattered abd_offset */
list_node_t abd_gang_link;
struct abd *abd_parent;
zfs_refcount_t abd_children;
kmutex_t abd_mtx;
union {
struct abd_scatter {
uint_t abd_offset;
#if defined(__FreeBSD__) && defined(_KERNEL)
uint_t abd_chunk_size;
void *abd_chunks[1]; /* actually variable-length */
#else
uint_t abd_nents;
struct scatterlist *abd_sgl;
#endif
} abd_scatter;
struct abd_linear {
void *abd_buf;
struct scatterlist *abd_sgl; /* for LINEAR_PAGE */
} abd_linear;
struct abd_gang {
list_t abd_gang_chain;
} abd_gang;
} abd_u;
} abd_t;
typedef int abd_iter_func_t(void *buf, size_t len, void *priv);
typedef int abd_iter_func2_t(void *bufa, void *bufb, size_t len, void *priv);
extern int zfs_abd_scatter_enabled;
/*
* Allocations and deallocations
*/
abd_t *abd_alloc(size_t, boolean_t);
abd_t *abd_alloc_linear(size_t, boolean_t);
abd_t *abd_alloc_gang(void);
abd_t *abd_alloc_for_io(size_t, boolean_t);
abd_t *abd_alloc_sametype(abd_t *, size_t);
void abd_gang_add(abd_t *, abd_t *, boolean_t);
void abd_free(abd_t *);
abd_t *abd_get_offset(abd_t *, size_t);
abd_t *abd_get_offset_size(abd_t *, size_t, size_t);
abd_t *abd_get_offset_struct(abd_t *, abd_t *, size_t, size_t);
abd_t *abd_get_zeros(size_t);
abd_t *abd_get_from_buf(void *, size_t);
void abd_cache_reap_now(void);
/*
* Conversion to and from a normal buffer
*/
void *abd_to_buf(abd_t *);
void *abd_borrow_buf(abd_t *, size_t);
void *abd_borrow_buf_copy(abd_t *, size_t);
void abd_return_buf(abd_t *, void *, size_t);
void abd_return_buf_copy(abd_t *, void *, size_t);
void abd_take_ownership_of_buf(abd_t *, boolean_t);
void abd_release_ownership_of_buf(abd_t *);
/*
* ABD operations
*/
int abd_iterate_func(abd_t *, size_t, size_t, abd_iter_func_t *, void *);
int abd_iterate_func2(abd_t *, abd_t *, size_t, size_t, size_t,
abd_iter_func2_t *, void *);
void abd_copy_off(abd_t *, abd_t *, size_t, size_t, size_t);
void abd_copy_from_buf_off(abd_t *, const void *, size_t, size_t);
void abd_copy_to_buf_off(void *, abd_t *, size_t, size_t);
int abd_cmp(abd_t *, abd_t *);
int abd_cmp_buf_off(abd_t *, const void *, size_t, size_t);
void abd_zero_off(abd_t *, size_t, size_t);
void abd_verify(abd_t *);
void abd_raidz_gen_iterate(abd_t **cabds, abd_t *dabd,
ssize_t csize, ssize_t dsize, const unsigned parity,
void (*func_raidz_gen)(void **, const void *, size_t, size_t));
void abd_raidz_rec_iterate(abd_t **cabds, abd_t **tabds,
ssize_t tsize, const unsigned parity,
void (*func_raidz_rec)(void **t, const size_t tsize, void **c,
const unsigned *mul),
const unsigned *mul);
/*
* Wrappers for calls with offsets of 0
*/
static inline void
abd_copy(abd_t *dabd, abd_t *sabd, size_t size)
{
abd_copy_off(dabd, sabd, 0, 0, size);
}
static inline void
abd_copy_from_buf(abd_t *abd, const void *buf, size_t size)
{
abd_copy_from_buf_off(abd, buf, 0, size);
}
static inline void
abd_copy_to_buf(void* buf, abd_t *abd, size_t size)
{
abd_copy_to_buf_off(buf, abd, 0, size);
}
static inline int
abd_cmp_buf(abd_t *abd, const void *buf, size_t size)
{
return (abd_cmp_buf_off(abd, buf, 0, size));
}
static inline void
abd_zero(abd_t *abd, size_t size)
{
abd_zero_off(abd, 0, size);
}
/*
* ABD type check functions
*/
static inline boolean_t
abd_is_linear(abd_t *abd)
{
return ((abd->abd_flags & ABD_FLAG_LINEAR) != 0);
}
static inline boolean_t
abd_is_linear_page(abd_t *abd)
{
return ((abd->abd_flags & ABD_FLAG_LINEAR_PAGE) != 0);
}
static inline boolean_t
abd_is_gang(abd_t *abd)
{
return ((abd->abd_flags & ABD_FLAG_GANG) != 0);
}
static inline uint_t
abd_get_size(abd_t *abd)
{
return (abd->abd_size);
}
/*
* Module lifecycle
* Defined in each specific OS's abd_os.c
*/
void abd_init(void);
void abd_fini(void);
/*
* Linux ABD bio functions
*/
#if defined(__linux__) && defined(_KERNEL)
unsigned int abd_bio_map_off(struct bio *, abd_t *, unsigned int, size_t);
unsigned long abd_nr_pages_off(abd_t *, unsigned int, size_t);
#endif
#ifdef __cplusplus
}
#endif
#endif /* _ABD_H */