Update vendor-sys/illumos/dist to illumos-gate 14046:6a5a2f4a47db
Illumos ZFS issues: 3742 zfs comments need cleaner, more consistent style
This commit is contained in:
parent
6ba2019d67
commit
7d8c721667
Notes:
svn2git
2020-12-20 02:59:44 +00:00
svn path=/vendor-sys/illumos/dist/; revision=251620
@ -58,11 +58,11 @@
|
||||
* tight.
|
||||
*
|
||||
* 3. The Megiddo and Modha model assumes a fixed page size. All
|
||||
* elements of the cache are therefor exactly the same size. So
|
||||
* elements of the cache are therefore exactly the same size. So
|
||||
* when adjusting the cache size following a cache miss, its simply
|
||||
* a matter of choosing a single page to evict. In our model, we
|
||||
* have variable sized cache blocks (rangeing from 512 bytes to
|
||||
* 128K bytes). We therefor choose a set of blocks to evict to make
|
||||
* 128K bytes). We therefore choose a set of blocks to evict to make
|
||||
* space for a cache miss that approximates as closely as possible
|
||||
* the space used by the new block.
|
||||
*
|
||||
@ -77,7 +77,7 @@
|
||||
* ways: 1) via a hash table lookup using the DVA as a key,
|
||||
* or 2) via one of the ARC lists. The arc_read() interface
|
||||
* uses method 1, while the internal arc algorithms for
|
||||
* adjusting the cache use method 2. We therefor provide two
|
||||
* adjusting the cache use method 2. We therefore provide two
|
||||
* types of locks: 1) the hash table lock array, and 2) the
|
||||
* arc list locks.
|
||||
*
|
||||
@ -385,7 +385,7 @@ static arc_stats_t arc_stats = {
|
||||
#define ARCSTAT(stat) (arc_stats.stat.value.ui64)
|
||||
|
||||
#define ARCSTAT_INCR(stat, val) \
|
||||
atomic_add_64(&arc_stats.stat.value.ui64, (val));
|
||||
atomic_add_64(&arc_stats.stat.value.ui64, (val))
|
||||
|
||||
#define ARCSTAT_BUMP(stat) ARCSTAT_INCR(stat, 1)
|
||||
#define ARCSTAT_BUMPDOWN(stat) ARCSTAT_INCR(stat, -1)
|
||||
@ -613,9 +613,7 @@ uint64_t zfs_crc64_table[256];
|
||||
#define l2arc_writes_sent ARCSTAT(arcstat_l2_writes_sent)
|
||||
#define l2arc_writes_done ARCSTAT(arcstat_l2_writes_done)
|
||||
|
||||
/*
|
||||
* L2ARC Performance Tunables
|
||||
*/
|
||||
/* L2ARC Performance Tunables */
|
||||
uint64_t l2arc_write_max = L2ARC_WRITE_SIZE; /* default max write size */
|
||||
uint64_t l2arc_write_boost = L2ARC_WRITE_SIZE; /* extra write during warmup */
|
||||
uint64_t l2arc_headroom = L2ARC_HEADROOM; /* number of dev writes */
|
||||
@ -3628,7 +3626,7 @@ arc_tempreserve_space(uint64_t reserve, uint64_t txg)
|
||||
|
||||
/*
|
||||
* Writes will, almost always, require additional memory allocations
|
||||
* in order to compress/encrypt/etc the data. We therefor need to
|
||||
* in order to compress/encrypt/etc the data. We therefore need to
|
||||
* make sure that there is sufficient available memory for this.
|
||||
*/
|
||||
if (error = arc_memory_throttle(reserve, anon_size, txg))
|
||||
|
@ -43,7 +43,7 @@
|
||||
* dsl_scan_sync. This allows the delete operation to finish without traversing
|
||||
* all the dataset's blocks.
|
||||
*
|
||||
* Note that while bt_begin and bt_end are only ever incremented in this code
|
||||
* Note that while bt_begin and bt_end are only ever incremented in this code,
|
||||
* they are effectively reset to 0 every time the entire bptree is freed because
|
||||
* the bptree's object is destroyed and re-created.
|
||||
*/
|
||||
|
@ -1803,14 +1803,16 @@ dnode_willuse_space(dnode_t *dn, int64_t space, dmu_tx_t *tx)
|
||||
}
|
||||
|
||||
/*
|
||||
* This function scans a block at the indicated "level" looking for
|
||||
* a hole or data (depending on 'flags'). If level > 0, then we are
|
||||
* scanning an indirect block looking at its pointers. If level == 0,
|
||||
* then we are looking at a block of dnodes. If we don't find what we
|
||||
* are looking for in the block, we return ESRCH. Otherwise, return
|
||||
* with *offset pointing to the beginning (if searching forwards) or
|
||||
* end (if searching backwards) of the range covered by the block
|
||||
* pointer we matched on (or dnode).
|
||||
* Scans a block at the indicated "level" looking for a hole or data,
|
||||
* depending on 'flags'.
|
||||
*
|
||||
* If level > 0, then we are scanning an indirect block looking at its
|
||||
* pointers. If level == 0, then we are looking at a block of dnodes.
|
||||
*
|
||||
* If we don't find what we are looking for in the block, we return ESRCH.
|
||||
* Otherwise, return with *offset pointing to the beginning (if searching
|
||||
* forwards) or end (if searching backwards) of the range covered by the
|
||||
* block pointer we matched on (or dnode).
|
||||
*
|
||||
* The basic search algorithm used below by dnode_next_offset() is to
|
||||
* use this function to search up the block tree (widen the search) until
|
||||
|
@ -302,7 +302,7 @@ free_children(dmu_buf_impl_t *db, uint64_t blkid, uint64_t nblks, int trunc,
|
||||
}
|
||||
|
||||
/*
|
||||
* free_range: Traverse the indicated range of the provided file
|
||||
* Traverse the indicated range of the provided file
|
||||
* and "free" all the blocks contained there.
|
||||
*/
|
||||
static void
|
||||
@ -370,7 +370,7 @@ dnode_sync_free_range(dnode_t *dn, uint64_t blkid, uint64_t nblks, dmu_tx_t *tx)
|
||||
}
|
||||
|
||||
/*
|
||||
* Try to kick all the dnodes dbufs out of the cache...
|
||||
* Try to kick all the dnode's dbufs out of the cache...
|
||||
*/
|
||||
void
|
||||
dnode_evict_dbufs(dnode_t *dn)
|
||||
|
@ -380,7 +380,7 @@ dsl_prop_predict(dsl_dir_t *dd, const char *propname,
|
||||
|
||||
/*
|
||||
* Unregister this callback. Return 0 on success, ENOENT if ddname is
|
||||
* invalid, ENOMSG if no matching callback registered.
|
||||
* invalid, or ENOMSG if no matching callback registered.
|
||||
*/
|
||||
int
|
||||
dsl_prop_unregister(dsl_dataset_t *ds, const char *propname,
|
||||
|
@ -111,6 +111,7 @@
|
||||
* location.
|
||||
*
|
||||
* Byteswap implications:
|
||||
*
|
||||
* Since the SA attributes are not entirely self describing we can't do
|
||||
* the normal byteswap processing. The special ZAP layout attribute and
|
||||
* attribute registration attributes define the byteswap function and the
|
||||
@ -189,7 +190,6 @@ sa_attr_reg_t sa_legacy_attrs[] = {
|
||||
};
|
||||
|
||||
/*
|
||||
* ZPL legacy layout
|
||||
* This is only used for objects of type DMU_OT_ZNODE
|
||||
*/
|
||||
sa_attr_type_t sa_legacy_zpl_layout[] = {
|
||||
@ -199,7 +199,6 @@ sa_attr_type_t sa_legacy_zpl_layout[] = {
|
||||
/*
|
||||
* Special dummy layout used for buffers with no attributes.
|
||||
*/
|
||||
|
||||
sa_attr_type_t sa_dummy_zpl_layout[] = { 0 };
|
||||
|
||||
static int sa_legacy_attr_count = 16;
|
||||
|
@ -4516,6 +4516,7 @@ spa_vdev_attach(spa_t *spa, uint64_t guid, nvlist_t *nvroot, int replacing)
|
||||
|
||||
/*
|
||||
* Detach a device from a mirror or replacing vdev.
|
||||
*
|
||||
* If 'replace_done' is specified, only detach if the parent
|
||||
* is a replacing vdev.
|
||||
*/
|
||||
@ -5170,11 +5171,9 @@ spa_vdev_remove_from_namespace(spa_t *spa, vdev_t *vd)
|
||||
* the spa_vdev_config_[enter/exit] functions which allow us to
|
||||
* grab and release the spa_config_lock while still holding the namespace
|
||||
* lock. During each step the configuration is synced out.
|
||||
*/
|
||||
|
||||
/*
|
||||
* Remove a device from the pool. Currently, this supports removing only hot
|
||||
* spares, slogs, and level 2 ARC devices.
|
||||
*
|
||||
* Currently, this supports removing only hot spares, slogs, and level 2 ARC
|
||||
* devices.
|
||||
*/
|
||||
int
|
||||
spa_vdev_remove(spa_t *spa, uint64_t guid, boolean_t unspare)
|
||||
@ -5284,7 +5283,7 @@ spa_vdev_remove(spa_t *spa, uint64_t guid, boolean_t unspare)
|
||||
|
||||
/*
|
||||
* Find any device that's done replacing, or a vdev marked 'unspare' that's
|
||||
* current spared, so we can detach it.
|
||||
* currently spared, so we can detach it.
|
||||
*/
|
||||
static vdev_t *
|
||||
spa_vdev_resilver_done_hunt(vdev_t *vd)
|
||||
|
@ -317,6 +317,7 @@ spa_config_set(spa_t *spa, nvlist_t *config)
|
||||
|
||||
/*
|
||||
* Generate the pool's configuration based on the current in-core state.
|
||||
*
|
||||
* We infer whether to generate a complete config or just one top-level config
|
||||
* based on whether vd is the root vdev.
|
||||
*/
|
||||
|
@ -1334,7 +1334,7 @@ zfs_panic_recover(const char *fmt, ...)
|
||||
|
||||
/*
|
||||
* This is a stripped-down version of strtoull, suitable only for converting
|
||||
* lowercase hexidecimal numbers that don't overflow.
|
||||
* lowercase hexadecimal numbers that don't overflow.
|
||||
*/
|
||||
uint64_t
|
||||
strtonum(const char *str, char **nptr)
|
||||
|
@ -63,16 +63,15 @@ enum ddt_class {
|
||||
*/
|
||||
typedef struct ddt_key {
|
||||
zio_cksum_t ddk_cksum; /* 256-bit block checksum */
|
||||
uint64_t ddk_prop; /* LSIZE, PSIZE, compression */
|
||||
/*
|
||||
* Encoded with logical & physical size, and compression, as follows:
|
||||
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
||||
* | 0 | 0 | 0 | comp | PSIZE | LSIZE |
|
||||
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
||||
*/
|
||||
uint64_t ddk_prop;
|
||||
} ddt_key_t;
|
||||
|
||||
/*
|
||||
* ddk_prop layout:
|
||||
*
|
||||
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
||||
* | 0 | 0 | 0 | comp | PSIZE | LSIZE |
|
||||
* +-------+-------+-------+-------+-------+-------+-------+-------+
|
||||
*/
|
||||
#define DDK_GET_LSIZE(ddk) \
|
||||
BF64_GET_SB((ddk)->ddk_prop, 0, 16, SPA_MINBLOCKSHIFT, 1)
|
||||
#define DDK_SET_LSIZE(ddk, x) \
|
||||
|
@ -145,9 +145,8 @@ typedef struct dnode_phys {
|
||||
|
||||
typedef struct dnode {
|
||||
/*
|
||||
* dn_struct_rwlock protects the structure of the dnode,
|
||||
* including the number of levels of indirection (dn_nlevels),
|
||||
* dn_maxblkid, and dn_next_*
|
||||
* Protects the structure of the dnode, including the number of levels
|
||||
* of indirection (dn_nlevels), dn_maxblkid, and dn_next_*
|
||||
*/
|
||||
krwlock_t dn_struct_rwlock;
|
||||
|
||||
|
@ -110,6 +110,7 @@ typedef struct dsl_pool {
|
||||
|
||||
/*
|
||||
* Protects administrative changes (properties, namespace)
|
||||
*
|
||||
* It is only held for write in syncing context. Therefore
|
||||
* syncing context does not need to ever have it for read, since
|
||||
* nobody else could possibly have it for write.
|
||||
|
@ -150,6 +150,7 @@ struct sa_os {
|
||||
|
||||
/*
|
||||
* header for all bonus and spill buffers.
|
||||
*
|
||||
* The header has a fixed portion with a variable number
|
||||
* of "lengths" depending on the number of variable sized
|
||||
* attribues which are determined by the "layout number"
|
||||
@ -158,29 +159,27 @@ struct sa_os {
|
||||
#define SA_MAGIC 0x2F505A /* ZFS SA */
|
||||
typedef struct sa_hdr_phys {
|
||||
uint32_t sa_magic;
|
||||
uint16_t sa_layout_info; /* Encoded with hdrsize and layout number */
|
||||
/*
|
||||
* Encoded with hdrsize and layout number as follows:
|
||||
* 16 10 0
|
||||
* +--------+-------+
|
||||
* | hdrsz |layout |
|
||||
* +--------+-------+
|
||||
*
|
||||
* Bits 0-10 are the layout number
|
||||
* Bits 11-16 are the size of the header.
|
||||
* The hdrsize is the number * 8
|
||||
*
|
||||
* For example.
|
||||
* hdrsz of 1 ==> 8 byte header
|
||||
* 2 ==> 16 byte header
|
||||
*
|
||||
*/
|
||||
uint16_t sa_layout_info;
|
||||
uint16_t sa_lengths[1]; /* optional sizes for variable length attrs */
|
||||
/* ... Data follows the lengths. */
|
||||
} sa_hdr_phys_t;
|
||||
|
||||
/*
|
||||
* sa_hdr_phys -> sa_layout_info
|
||||
*
|
||||
* 16 10 0
|
||||
* +--------+-------+
|
||||
* | hdrsz |layout |
|
||||
* +--------+-------+
|
||||
*
|
||||
* Bits 0-10 are the layout number
|
||||
* Bits 11-16 are the size of the header.
|
||||
* The hdrsize is the number * 8
|
||||
*
|
||||
* For example.
|
||||
* hdrsz of 1 ==> 8 byte header
|
||||
* 2 ==> 16 byte header
|
||||
*
|
||||
*/
|
||||
|
||||
#define SA_HDR_LAYOUT_NUM(hdr) BF32_GET(hdr->sa_layout_info, 0, 10)
|
||||
#define SA_HDR_SIZE(hdr) BF32_GET_SB(hdr->sa_layout_info, 10, 6, 3, 0)
|
||||
#define SA_HDR_LAYOUT_INFO_ENCODE(x, num, size) \
|
||||
|
@ -239,7 +239,7 @@ struct spa {
|
||||
kmutex_t spa_iokstat_lock; /* protects spa_iokstat_* */
|
||||
struct kstat *spa_iokstat; /* kstat of io to this pool */
|
||||
/*
|
||||
* spa_refcnt & spa_config_lock must be the last elements
|
||||
* spa_refcount & spa_config_lock must be the last elements
|
||||
* because refcount_t changes size based on compilation options.
|
||||
* In order for the MDB module to function correctly, the other
|
||||
* fields must remain in the same location.
|
||||
|
@ -94,7 +94,6 @@ struct space_map_ops {
|
||||
* 63 62 60 59 50 49 0
|
||||
*
|
||||
*
|
||||
*
|
||||
* non-debug entry
|
||||
*
|
||||
* 1 47 1 15
|
||||
|
@ -26,8 +26,6 @@
|
||||
#ifndef _SYS_UNIQUE_H
|
||||
#define _SYS_UNIQUE_H
|
||||
|
||||
#pragma ident "%Z%%M% %I% %E% SMI"
|
||||
|
||||
#include <sys/zfs_context.h>
|
||||
|
||||
#ifdef __cplusplus
|
||||
@ -42,7 +40,7 @@ void unique_fini(void);
|
||||
|
||||
/*
|
||||
* Return a new unique value (which will not be uniquified against until
|
||||
* it is unique_insert()-ed.
|
||||
* it is unique_insert()-ed).
|
||||
*/
|
||||
uint64_t unique_create(void);
|
||||
|
||||
|
@ -245,12 +245,13 @@ typedef struct vdev_label {
|
||||
#define VDD_METASLAB 0x01
|
||||
#define VDD_DTL 0x02
|
||||
|
||||
/* Offset of embedded boot loader region on each label */
|
||||
#define VDEV_BOOT_OFFSET (2 * sizeof (vdev_label_t))
|
||||
/*
|
||||
* Size and offset of embedded boot loader region on each label.
|
||||
* Size of embedded boot loader region on each label.
|
||||
* The total size of the first two labels plus the boot area is 4MB.
|
||||
*/
|
||||
#define VDEV_BOOT_OFFSET (2 * sizeof (vdev_label_t))
|
||||
#define VDEV_BOOT_SIZE (7ULL << 19) /* 3.5M */
|
||||
#define VDEV_BOOT_SIZE (7ULL << 19) /* 3.5M */
|
||||
|
||||
/*
|
||||
* Size of label regions at the start and end of each leaf device.
|
||||
@ -317,8 +318,9 @@ extern uint64_t vdev_get_min_asize(vdev_t *vd);
|
||||
extern void vdev_set_min_asize(vdev_t *vd);
|
||||
|
||||
/*
|
||||
* zdb uses this tunable, so it must be declared here to make lint happy.
|
||||
* Global variables
|
||||
*/
|
||||
/* zdb uses this tunable, so it must be declared here to make lint happy. */
|
||||
extern int zfs_vdev_cache_size;
|
||||
|
||||
/*
|
||||
|
@ -86,18 +86,22 @@ extern "C" {
|
||||
#endif
|
||||
|
||||
/*
|
||||
* The matchtype specifies which entry will be accessed.
|
||||
* MT_EXACT: only find an exact match (non-normalized)
|
||||
* MT_FIRST: find the "first" normalized (case and Unicode
|
||||
* form) match; the designated "first" match will not change as long
|
||||
* as the set of entries with this normalization doesn't change
|
||||
* MT_BEST: if there is an exact match, find that, otherwise find the
|
||||
* first normalized match
|
||||
* Specifies matching criteria for ZAP lookups.
|
||||
*/
|
||||
typedef enum matchtype
|
||||
{
|
||||
/* Only find an exact match (non-normalized) */
|
||||
MT_EXACT,
|
||||
/*
|
||||
* If there is an exact match, find that, otherwise find the
|
||||
* first normalized match.
|
||||
*/
|
||||
MT_BEST,
|
||||
/*
|
||||
* Find the "first" normalized (case and Unicode form) match;
|
||||
* the designated "first" match will not change as long as the
|
||||
* set of entries with this normalization doesn't change.
|
||||
*/
|
||||
MT_FIRST
|
||||
} matchtype_t;
|
||||
|
||||
@ -174,16 +178,21 @@ int zap_destroy(objset_t *ds, uint64_t zapobj, dmu_tx_t *tx);
|
||||
* call will fail and return EINVAL.
|
||||
*
|
||||
* If 'integer_size' is equal to or larger than the attribute's integer
|
||||
* size, the call will succeed and return 0. * When converting to a
|
||||
* larger integer size, the integers will be treated as unsigned (ie. no
|
||||
* sign-extension will be performed).
|
||||
* size, the call will succeed and return 0.
|
||||
*
|
||||
* When converting to a larger integer size, the integers will be treated as
|
||||
* unsigned (ie. no sign-extension will be performed).
|
||||
*
|
||||
* 'num_integers' is the length (in integers) of 'buf'.
|
||||
*
|
||||
* If the attribute is longer than the buffer, as many integers as will
|
||||
* fit will be transferred to 'buf'. If the entire attribute was not
|
||||
* transferred, the call will return EOVERFLOW.
|
||||
*
|
||||
*/
|
||||
int zap_lookup(objset_t *ds, uint64_t zapobj, const char *name,
|
||||
uint64_t integer_size, uint64_t num_integers, void *buf);
|
||||
|
||||
/*
|
||||
* If rn_len is nonzero, realname will be set to the name of the found
|
||||
* entry (which may be different from the requested name if matchtype is
|
||||
* not MT_EXACT).
|
||||
@ -191,8 +200,6 @@ int zap_destroy(objset_t *ds, uint64_t zapobj, dmu_tx_t *tx);
|
||||
* If normalization_conflictp is not NULL, it will be set if there is
|
||||
* another name with the same case/unicode normalized form.
|
||||
*/
|
||||
int zap_lookup(objset_t *ds, uint64_t zapobj, const char *name,
|
||||
uint64_t integer_size, uint64_t num_integers, void *buf);
|
||||
int zap_lookup_norm(objset_t *ds, uint64_t zapobj, const char *name,
|
||||
uint64_t integer_size, uint64_t num_integers, void *buf,
|
||||
matchtype_t mt, char *realname, int rn_len,
|
||||
|
@ -101,6 +101,7 @@ typedef enum zap_chunk_type {
|
||||
*/
|
||||
typedef struct zap_leaf_phys {
|
||||
struct zap_leaf_header {
|
||||
/* Public to ZAP */
|
||||
uint64_t lh_block_type; /* ZBT_LEAF */
|
||||
uint64_t lh_pad1;
|
||||
uint64_t lh_prefix; /* hash prefix of this leaf */
|
||||
@ -109,8 +110,7 @@ typedef struct zap_leaf_phys {
|
||||
uint16_t lh_nentries; /* number of entries */
|
||||
uint16_t lh_prefix_len; /* num bits used to id this */
|
||||
|
||||
/* above is accessable to zap, below is zap_leaf private */
|
||||
|
||||
/* Private to zap_leaf */
|
||||
uint16_t lh_freelist; /* chunk head of free list */
|
||||
uint8_t lh_flags; /* ZLF_* flags */
|
||||
uint8_t lh_pad2[11];
|
||||
@ -161,13 +161,13 @@ typedef struct zap_leaf {
|
||||
|
||||
|
||||
typedef struct zap_entry_handle {
|
||||
/* below is set by zap_leaf.c and is public to zap.c */
|
||||
/* Set by zap_leaf and public to ZAP */
|
||||
uint64_t zeh_num_integers;
|
||||
uint64_t zeh_hash;
|
||||
uint32_t zeh_cd;
|
||||
uint8_t zeh_integer_size;
|
||||
|
||||
/* below is private to zap_leaf.c */
|
||||
/* Private to zap_leaf */
|
||||
uint16_t zeh_fakechunk;
|
||||
uint16_t *zeh_chunkp;
|
||||
zap_leaf_t *zeh_leaf;
|
||||
@ -202,7 +202,7 @@ extern int zap_entry_read_name(struct zap *zap, const zap_entry_handle_t *zeh,
|
||||
/*
|
||||
* Replace the value of an existing entry.
|
||||
*
|
||||
* zap_entry_update may fail if it runs out of space (ENOSPC).
|
||||
* May fail if it runs out of space (ENOSPC).
|
||||
*/
|
||||
extern int zap_entry_update(zap_entry_handle_t *zeh,
|
||||
uint8_t integer_size, uint64_t num_integers, const void *buf);
|
||||
@ -221,10 +221,7 @@ extern int zap_entry_create(zap_leaf_t *l, struct zap_name *zn, uint32_t cd,
|
||||
uint8_t integer_size, uint64_t num_integers, const void *buf,
|
||||
zap_entry_handle_t *zeh);
|
||||
|
||||
/*
|
||||
* Return true if there are additional entries with the same normalized
|
||||
* form.
|
||||
*/
|
||||
/* Determine whether there is another entry with the same normalized form. */
|
||||
extern boolean_t zap_entry_normalization_conflict(zap_entry_handle_t *zeh,
|
||||
struct zap_name *zn, const char *name, struct zap *zap);
|
||||
|
||||
|
@ -46,7 +46,8 @@ struct znode_phys;
|
||||
#define ZFS_ACL_VERSION ZFS_ACL_VERSION_FUID
|
||||
|
||||
/*
|
||||
* ZFS ACLs are store in various forms.
|
||||
* ZFS ACLs (Access Control Lists) are stored in various forms.
|
||||
*
|
||||
* Files created with ACL version ZFS_ACL_VERSION_INITIAL
|
||||
* will all be created with fixed length ACEs of type
|
||||
* zfs_oldace_t.
|
||||
@ -136,8 +137,8 @@ typedef struct acl_ops {
|
||||
size_t (*ace_size)(void *acep); /* how big is this ace */
|
||||
size_t (*ace_abstract_size)(void); /* sizeof abstract entry */
|
||||
int (*ace_mask_off)(void); /* off of access mask in ace */
|
||||
/* ptr to data if any */
|
||||
int (*ace_data)(void *acep, void **datap);
|
||||
/* ptr to data if any */
|
||||
} acl_ops_t;
|
||||
|
||||
/*
|
||||
|
@ -26,8 +26,6 @@
|
||||
#ifndef _SYS_FS_ZFS_RLOCK_H
|
||||
#define _SYS_FS_ZFS_RLOCK_H
|
||||
|
||||
#pragma ident "%Z%%M% %I% %E% SMI"
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
@ -57,16 +55,14 @@ typedef struct rl {
|
||||
} rl_t;
|
||||
|
||||
/*
|
||||
* Lock a range (offset, length) as either shared (READER)
|
||||
* or exclusive (WRITER or APPEND). APPEND is a special type that
|
||||
* is converted to WRITER that specified to lock from the start of the
|
||||
* end of file. zfs_range_lock() returns the range lock structure.
|
||||
* Lock a range (offset, length) as either shared (RL_READER)
|
||||
* or exclusive (RL_WRITER or RL_APPEND). RL_APPEND is a special type that
|
||||
* is converted to RL_WRITER that specified to lock from the start of the
|
||||
* end of file. Returns the range lock structure.
|
||||
*/
|
||||
rl_t *zfs_range_lock(znode_t *zp, uint64_t off, uint64_t len, rl_type_t type);
|
||||
|
||||
/*
|
||||
* Unlock range and destroy range lock structure.
|
||||
*/
|
||||
/* Unlock range and destroy range lock structure. */
|
||||
void zfs_range_unlock(rl_t *rl);
|
||||
|
||||
/*
|
||||
@ -76,7 +72,8 @@ void zfs_range_unlock(rl_t *rl);
|
||||
void zfs_range_reduce(rl_t *rl, uint64_t off, uint64_t len);
|
||||
|
||||
/*
|
||||
* AVL comparison function used to compare range locks
|
||||
* AVL comparison function used to order range locks
|
||||
* Locks are ordered on the start offset of the range.
|
||||
*/
|
||||
int zfs_range_compare(const void *arg1, const void *arg2);
|
||||
|
||||
|
@ -138,8 +138,9 @@ extern "C" {
|
||||
|
||||
#define ZFS_MAX_BLOCKSIZE (SPA_MAXBLOCKSIZE)
|
||||
|
||||
/* Path component length */
|
||||
/*
|
||||
* Path component length
|
||||
*
|
||||
* The generic fs code uses MAXNAMELEN to represent
|
||||
* what the largest component length is. Unfortunately,
|
||||
* this length includes the terminating NULL. ZFS needs
|
||||
@ -234,11 +235,7 @@ typedef struct znode {
|
||||
#define ZTOV(ZP) ((ZP)->z_vnode)
|
||||
#define VTOZ(VP) ((znode_t *)(VP)->v_data)
|
||||
|
||||
/*
|
||||
* ZFS_ENTER() is called on entry to each ZFS vnode and vfs operation.
|
||||
* ZFS_EXIT() must be called before exitting the vop.
|
||||
* ZFS_VERIFY_ZP() verifies the znode is valid.
|
||||
*/
|
||||
/* Called on entry to each ZFS vnode and vfs operation */
|
||||
#define ZFS_ENTER(zfsvfs) \
|
||||
{ \
|
||||
rrw_enter_read(&(zfsvfs)->z_teardown_lock, FTAG); \
|
||||
@ -248,8 +245,10 @@ typedef struct znode {
|
||||
} \
|
||||
}
|
||||
|
||||
/* Must be called before exiting the vop */
|
||||
#define ZFS_EXIT(zfsvfs) rrw_exit(&(zfsvfs)->z_teardown_lock, FTAG)
|
||||
|
||||
/* Verifies the znode is valid */
|
||||
#define ZFS_VERIFY_ZP(zp) \
|
||||
if ((zp)->z_sa_hdl == NULL) { \
|
||||
ZFS_EXIT((zp)->z_zfsvfs); \
|
||||
@ -269,15 +268,14 @@ typedef struct znode {
|
||||
#define ZFS_OBJ_HOLD_EXIT(zfsvfs, obj_num) \
|
||||
mutex_exit(ZFS_OBJ_MUTEX((zfsvfs), (obj_num)))
|
||||
|
||||
/*
|
||||
* Macros to encode/decode ZFS stored time values from/to struct timespec
|
||||
*/
|
||||
/* Encode ZFS stored time values from a struct timespec */
|
||||
#define ZFS_TIME_ENCODE(tp, stmp) \
|
||||
{ \
|
||||
(stmp)[0] = (uint64_t)(tp)->tv_sec; \
|
||||
(stmp)[1] = (uint64_t)(tp)->tv_nsec; \
|
||||
}
|
||||
|
||||
/* Decode ZFS stored time values to a struct timespec */
|
||||
#define ZFS_TIME_DECODE(tp, stmp) \
|
||||
{ \
|
||||
(tp)->tv_sec = (time_t)(stmp)[0]; \
|
||||
|
@ -242,6 +242,12 @@ typedef struct {
|
||||
* information needed for replaying the create. If the
|
||||
* file doesn't have any actual ACEs then the lr_aclcnt
|
||||
* would be zero.
|
||||
*
|
||||
* After lr_acl_flags, there are a lr_acl_bytes number of variable sized ace's.
|
||||
* If create is also setting xvattr's, then acl data follows xvattr.
|
||||
* If ACE FUIDs are needed then they will follow the xvattr_t. Following
|
||||
* the FUIDs will be the domain table information. The FUIDs for the owner
|
||||
* and group will be in lr_create. Name follows ACL data.
|
||||
*/
|
||||
typedef struct {
|
||||
lr_create_t lr_create; /* common create portion */
|
||||
@ -250,13 +256,6 @@ typedef struct {
|
||||
uint64_t lr_fuidcnt; /* number of real fuids */
|
||||
uint64_t lr_acl_bytes; /* number of bytes in ACL */
|
||||
uint64_t lr_acl_flags; /* ACL flags */
|
||||
/* lr_acl_bytes number of variable sized ace's follows */
|
||||
/* if create is also setting xvattr's, then acl data follows xvattr */
|
||||
/* if ACE FUIDs are needed then they will follow the xvattr_t */
|
||||
/* Following the FUIDs will be the domain table information. */
|
||||
/* The FUIDs for the owner and group will be in the lr_create */
|
||||
/* portion of the record. */
|
||||
/* name follows ACL data */
|
||||
} lr_acl_create_t;
|
||||
|
||||
typedef struct {
|
||||
|
@ -36,11 +36,10 @@
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
/*
|
||||
* Common signature for all zio compress/decompress functions.
|
||||
*/
|
||||
/* Common signature for all zio compress functions. */
|
||||
typedef size_t zio_compress_func_t(void *src, void *dst,
|
||||
size_t s_len, size_t d_len, int);
|
||||
/* Common signature for all zio decompress functions. */
|
||||
typedef int zio_decompress_func_t(void *src, void *dst,
|
||||
size_t s_len, size_t d_len, int);
|
||||
|
||||
|
@ -567,8 +567,8 @@ txg_quiesce_thread(dsl_pool_t *dp)
|
||||
|
||||
/*
|
||||
* Delay this thread by delay nanoseconds if we are still in the open
|
||||
* transaction group and there is already a waiting txg quiesing or quiesced.
|
||||
* Abort the delay if this txg stalls or enters the quiesing state.
|
||||
* transaction group and there is already a waiting txg quiescing or quiesced.
|
||||
* Abort the delay if this txg stalls or enters the quiescing state.
|
||||
*/
|
||||
void
|
||||
txg_delay(dsl_pool_t *dp, uint64_t txg, hrtime_t delay, hrtime_t resolution)
|
||||
@ -576,7 +576,7 @@ txg_delay(dsl_pool_t *dp, uint64_t txg, hrtime_t delay, hrtime_t resolution)
|
||||
tx_state_t *tx = &dp->dp_tx;
|
||||
hrtime_t start = gethrtime();
|
||||
|
||||
/* don't delay if this txg could transition to quiesing immediately */
|
||||
/* don't delay if this txg could transition to quiescing immediately */
|
||||
if (tx->tx_open_txg > txg ||
|
||||
tx->tx_syncing_txg == txg-1 || tx->tx_synced_txg == txg-1)
|
||||
return;
|
||||
|
@ -956,9 +956,11 @@ vdev_probe_done(zio_t *zio)
|
||||
}
|
||||
|
||||
/*
|
||||
* Determine whether this device is accessible by reading and writing
|
||||
* to several known locations: the pad regions of each vdev label
|
||||
* but the first (which we leave alone in case it contains a VTOC).
|
||||
* Determine whether this device is accessible.
|
||||
*
|
||||
* Read and write to several known locations: the pad regions of each
|
||||
* vdev label but the first, which we leave alone in case it contains
|
||||
* a VTOC.
|
||||
*/
|
||||
zio_t *
|
||||
vdev_probe(vdev_t *vd, zio_t *zio)
|
||||
@ -2179,10 +2181,12 @@ vdev_degrade(spa_t *spa, uint64_t guid, vdev_aux_t aux)
|
||||
}
|
||||
|
||||
/*
|
||||
* Online the given vdev. If 'unspare' is set, it implies two things. First,
|
||||
* any attached spare device should be detached when the device finishes
|
||||
* resilvering. Second, the online should be treated like a 'test' online case,
|
||||
* so no FMA events are generated if the device fails to open.
|
||||
* Online the given vdev.
|
||||
*
|
||||
* If 'ZFS_ONLINE_UNSPARE' is set, it implies two things. First, any attached
|
||||
* spare device should be detached when the device finishes resilvering.
|
||||
* Second, the online should be treated like a 'test' online case, so no FMA
|
||||
* events are generated if the device fails to open.
|
||||
*/
|
||||
int
|
||||
vdev_online(spa_t *spa, uint64_t guid, uint64_t flags, vdev_state_t *newstate)
|
||||
|
@ -36,13 +36,14 @@
|
||||
/*
|
||||
* These tunables are for performance analysis.
|
||||
*/
|
||||
/*
|
||||
* zfs_vdev_max_pending is the maximum number of i/os concurrently
|
||||
* pending to each device. zfs_vdev_min_pending is the initial number
|
||||
* of i/os pending to each device (before it starts ramping up to
|
||||
* max_pending).
|
||||
*/
|
||||
|
||||
/* The maximum number of I/Os concurrently pending to each device. */
|
||||
int zfs_vdev_max_pending = 10;
|
||||
|
||||
/*
|
||||
* The initial number of I/Os pending to each device, before it starts ramping
|
||||
* up to zfs_vdev_max_pending.
|
||||
*/
|
||||
int zfs_vdev_min_pending = 4;
|
||||
|
||||
/*
|
||||
|
@ -60,6 +60,7 @@
|
||||
* o addition (+) is represented by a bitwise XOR
|
||||
* o subtraction (-) is therefore identical to addition: A + B = A - B
|
||||
* o multiplication of A by 2 is defined by the following bitwise expression:
|
||||
*
|
||||
* (A * 2)_7 = A_6
|
||||
* (A * 2)_6 = A_5
|
||||
* (A * 2)_5 = A_4
|
||||
@ -118,7 +119,7 @@ typedef struct raidz_map {
|
||||
uint64_t rm_missingparity; /* Count of missing parity devices */
|
||||
uint64_t rm_firstdatacol; /* First data column/parity count */
|
||||
uint64_t rm_nskip; /* Skipped sectors for padding */
|
||||
uint64_t rm_skipstart; /* Column index of padding start */
|
||||
uint64_t rm_skipstart; /* Column index of padding start */
|
||||
void *rm_datacopy; /* rm_asize-buffer of copied data */
|
||||
uintptr_t rm_reports; /* # of referencing checksum reports */
|
||||
uint8_t rm_freed; /* map no longer has referencing ZIO */
|
||||
@ -158,10 +159,7 @@ typedef struct raidz_map {
|
||||
*/
|
||||
int vdev_raidz_default_to_general;
|
||||
|
||||
/*
|
||||
* These two tables represent powers and logs of 2 in the Galois field defined
|
||||
* above. These values were computed by repeatedly multiplying by 2 as above.
|
||||
*/
|
||||
/* Powers of 2 in the Galois field defined above. */
|
||||
static const uint8_t vdev_raidz_pow2[256] = {
|
||||
0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80,
|
||||
0x1d, 0x3a, 0x74, 0xe8, 0xcd, 0x87, 0x13, 0x26,
|
||||
@ -196,6 +194,7 @@ static const uint8_t vdev_raidz_pow2[256] = {
|
||||
0x2c, 0x58, 0xb0, 0x7d, 0xfa, 0xe9, 0xcf, 0x83,
|
||||
0x1b, 0x36, 0x6c, 0xd8, 0xad, 0x47, 0x8e, 0x01
|
||||
};
|
||||
/* Logs of 2 in the Galois field defined above. */
|
||||
static const uint8_t vdev_raidz_log2[256] = {
|
||||
0x00, 0x00, 0x01, 0x19, 0x02, 0x32, 0x1a, 0xc6,
|
||||
0x03, 0xdf, 0x33, 0xee, 0x1b, 0x68, 0xc7, 0x4b,
|
||||
|
@ -1362,7 +1362,8 @@ zfs_acl_chmod(vtype_t vtype, uint64_t mode, boolean_t trim, zfs_acl_t *aclp)
|
||||
zacep = (void *)((uintptr_t)zacep + abstract_size);
|
||||
new_count++;
|
||||
new_bytes += abstract_size;
|
||||
} if (masks.deny1) {
|
||||
}
|
||||
if (masks.deny1) {
|
||||
zfs_set_ace(aclp, zacep, masks.deny1, DENY, -1, ACE_OWNER);
|
||||
zacep = (void *)((uintptr_t)zacep + abstract_size);
|
||||
new_count++;
|
||||
@ -1766,7 +1767,7 @@ zfs_acl_ids_overquota(zfsvfs_t *zfsvfs, zfs_acl_ids_t *acl_ids)
|
||||
}
|
||||
|
||||
/*
|
||||
* Retrieve a files ACL
|
||||
* Retrieve a file's ACL
|
||||
*/
|
||||
int
|
||||
zfs_getacl(znode_t *zp, vsecattr_t *vsecp, boolean_t skipaclchk, cred_t *cr)
|
||||
@ -1921,7 +1922,7 @@ zfs_vsec_2_aclp(zfsvfs_t *zfsvfs, vtype_t obj_type,
|
||||
}
|
||||
|
||||
/*
|
||||
* Set a files ACL
|
||||
* Set a file's ACL
|
||||
*/
|
||||
int
|
||||
zfs_setacl(znode_t *zp, vsecattr_t *vsecp, boolean_t skipaclchk, cred_t *cr)
|
||||
@ -2342,6 +2343,7 @@ zfs_fastaccesschk_execute(znode_t *zdp, cred_t *cr)
|
||||
|
||||
/*
|
||||
* Determine whether Access should be granted/denied.
|
||||
*
|
||||
* The least priv subsytem is always consulted as a basic privilege
|
||||
* can define any form of access.
|
||||
*/
|
||||
@ -2537,7 +2539,6 @@ zfs_delete_final_check(znode_t *zp, znode_t *dzp,
|
||||
* Determine whether Access should be granted/deny, without
|
||||
* consulting least priv subsystem.
|
||||
*
|
||||
*
|
||||
* The following chart is the recommended NFSv4 enforcement for
|
||||
* ability to delete an object.
|
||||
*
|
||||
|
@ -1051,6 +1051,7 @@ zfsctl_shares_readdir(vnode_t *vp, uio_t *uiop, cred_t *cr, int *eofp,
|
||||
|
||||
/*
|
||||
* pvp is the '.zfs' directory (zfsctl_node_t).
|
||||
*
|
||||
* Creates vp, which is '.zfs/snapshot' (zfsctl_snapdir_t).
|
||||
*
|
||||
* This function is the callback to create a GFS vnode for '.zfs/snapshot'
|
||||
|
@ -323,9 +323,7 @@ zfs_is_bootfs(const char *name)
|
||||
}
|
||||
|
||||
/*
|
||||
* zfs_earlier_version
|
||||
*
|
||||
* Return non-zero if the spa version is less than requested version.
|
||||
* Return non-zero if the spa version is less than requested version.
|
||||
*/
|
||||
static int
|
||||
zfs_earlier_version(const char *name, int version)
|
||||
@ -343,8 +341,6 @@ zfs_earlier_version(const char *name, int version)
|
||||
}
|
||||
|
||||
/*
|
||||
* zpl_earlier_version
|
||||
*
|
||||
* Return TRUE if the ZPL version is less than requested version.
|
||||
*/
|
||||
static boolean_t
|
||||
@ -2955,10 +2951,10 @@ zfs_create_cb(objset_t *os, void *arg, cred_t *cr, dmu_tx_t *tx)
|
||||
|
||||
/*
|
||||
* inputs:
|
||||
* createprops list of properties requested by creator
|
||||
* default_zplver zpl version to use if unspecified in createprops
|
||||
* fuids_ok fuids allowed in this version of the spa?
|
||||
* os parent objset pointer (NULL if root fs)
|
||||
* fuids_ok fuids allowed in this version of the spa?
|
||||
* sa_ok SAs allowed in this version of the spa?
|
||||
* createprops list of properties requested by creator
|
||||
*
|
||||
* outputs:
|
||||
* zplprops values for the zplprops we attach to the master node object
|
||||
|
@ -211,9 +211,8 @@ zfs_log_fuid_domains(zfs_fuid_info_t *fuidp, void *start)
|
||||
}
|
||||
|
||||
/*
|
||||
* zfs_log_create() is used to handle TX_CREATE, TX_CREATE_ATTR, TX_MKDIR,
|
||||
* TX_MKDIR_ATTR and TX_MKXATTR
|
||||
* transactions.
|
||||
* Handles TX_CREATE, TX_CREATE_ATTR, TX_MKDIR, TX_MKDIR_ATTR and
|
||||
* TK_MKXATTR transactions.
|
||||
*
|
||||
* TX_CREATE and TX_MKDIR are standard creates, but they may have FUID
|
||||
* domain information appended prior to the name. In this case the
|
||||
@ -340,7 +339,7 @@ zfs_log_create(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
|
||||
}
|
||||
|
||||
/*
|
||||
* zfs_log_remove() handles both TX_REMOVE and TX_RMDIR transactions.
|
||||
* Handles both TX_REMOVE and TX_RMDIR transactions.
|
||||
*/
|
||||
void
|
||||
zfs_log_remove(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
|
||||
@ -364,7 +363,7 @@ zfs_log_remove(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
|
||||
}
|
||||
|
||||
/*
|
||||
* zfs_log_link() handles TX_LINK transactions.
|
||||
* Handles TX_LINK transactions.
|
||||
*/
|
||||
void
|
||||
zfs_log_link(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
|
||||
@ -387,7 +386,7 @@ zfs_log_link(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
|
||||
}
|
||||
|
||||
/*
|
||||
* zfs_log_symlink() handles TX_SYMLINK transactions.
|
||||
* Handles TX_SYMLINK transactions.
|
||||
*/
|
||||
void
|
||||
zfs_log_symlink(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
|
||||
@ -419,7 +418,7 @@ zfs_log_symlink(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
|
||||
}
|
||||
|
||||
/*
|
||||
* zfs_log_rename() handles TX_RENAME transactions.
|
||||
* Handles TX_RENAME transactions.
|
||||
*/
|
||||
void
|
||||
zfs_log_rename(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
|
||||
@ -445,7 +444,7 @@ zfs_log_rename(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype,
|
||||
}
|
||||
|
||||
/*
|
||||
* zfs_log_write() handles TX_WRITE transactions.
|
||||
* Handles TX_WRITE transactions.
|
||||
*/
|
||||
ssize_t zfs_immediate_write_sz = 32768;
|
||||
|
||||
@ -524,7 +523,7 @@ zfs_log_write(zilog_t *zilog, dmu_tx_t *tx, int txtype,
|
||||
}
|
||||
|
||||
/*
|
||||
* zfs_log_truncate() handles TX_TRUNCATE transactions.
|
||||
* Handles TX_TRUNCATE transactions.
|
||||
*/
|
||||
void
|
||||
zfs_log_truncate(zilog_t *zilog, dmu_tx_t *tx, int txtype,
|
||||
@ -547,7 +546,7 @@ zfs_log_truncate(zilog_t *zilog, dmu_tx_t *tx, int txtype,
|
||||
}
|
||||
|
||||
/*
|
||||
* zfs_log_setattr() handles TX_SETATTR transactions.
|
||||
* Handles TX_SETATTR transactions.
|
||||
*/
|
||||
void
|
||||
zfs_log_setattr(zilog_t *zilog, dmu_tx_t *tx, int txtype,
|
||||
@ -609,7 +608,7 @@ zfs_log_setattr(zilog_t *zilog, dmu_tx_t *tx, int txtype,
|
||||
}
|
||||
|
||||
/*
|
||||
* zfs_log_acl() handles TX_ACL transactions.
|
||||
* Handles TX_ACL transactions.
|
||||
*/
|
||||
void
|
||||
zfs_log_acl(zilog_t *zilog, dmu_tx_t *tx, znode_t *zp,
|
||||
|
@ -28,7 +28,7 @@
|
||||
|
||||
/*
|
||||
* This file contains the code to implement file range locking in
|
||||
* ZFS, although there isn't much specific to ZFS (all that comes to mind
|
||||
* ZFS, although there isn't much specific to ZFS (all that comes to mind is
|
||||
* support for growing the blocksize).
|
||||
*
|
||||
* Interface
|
||||
|
@ -187,7 +187,7 @@ zfs_sa_set_scanstamp(znode_t *zp, xvattr_t *xvap, dmu_tx_t *tx)
|
||||
/*
|
||||
* I'm not convinced we should do any of this upgrade.
|
||||
* since the SA code can read both old/new znode formats
|
||||
* with probably little to know performance difference.
|
||||
* with probably little to no performance difference.
|
||||
*
|
||||
* All new files will be created with the new format.
|
||||
*/
|
||||
|
@ -1348,13 +1348,12 @@ zfs_parse_bootfs(char *bpath, char *outpath)
|
||||
}
|
||||
|
||||
/*
|
||||
* zfs_check_global_label:
|
||||
* Check that the hex label string is appropriate for the dataset
|
||||
* being mounted into the global_zone proper.
|
||||
* Check that the hex label string is appropriate for the dataset being
|
||||
* mounted into the global_zone proper.
|
||||
*
|
||||
* Return an error if the hex label string is not default or
|
||||
* admin_low/admin_high. For admin_low labels, the corresponding
|
||||
* dataset must be readonly.
|
||||
* Return an error if the hex label string is not default or
|
||||
* admin_low/admin_high. For admin_low labels, the corresponding
|
||||
* dataset must be readonly.
|
||||
*/
|
||||
int
|
||||
zfs_check_global_label(const char *dsname, const char *hexsl)
|
||||
@ -1376,15 +1375,12 @@ zfs_check_global_label(const char *dsname, const char *hexsl)
|
||||
}
|
||||
|
||||
/*
|
||||
* zfs_mount_label_policy:
|
||||
* Determine whether the mount is allowed according to MAC check.
|
||||
* by comparing (where appropriate) label of the dataset against
|
||||
* the label of the zone being mounted into. If the dataset has
|
||||
* no label, create one.
|
||||
* Determine whether the mount is allowed according to MAC check.
|
||||
* by comparing (where appropriate) label of the dataset against
|
||||
* the label of the zone being mounted into. If the dataset has
|
||||
* no label, create one.
|
||||
*
|
||||
* Returns:
|
||||
* 0 : access allowed
|
||||
* >0 : error code, such as EACCES
|
||||
* Returns 0 if access allowed, error otherwise (e.g. EACCES)
|
||||
*/
|
||||
static int
|
||||
zfs_mount_label_policy(vfs_t *vfsp, char *osname)
|
||||
|
@ -91,11 +91,11 @@
|
||||
* The ordering of events is important to avoid deadlocks and references
|
||||
* to freed memory. The example below illustrates the following Big Rules:
|
||||
*
|
||||
* (1) A check must be made in each zfs thread for a mounted file system.
|
||||
* (1) A check must be made in each zfs thread for a mounted file system.
|
||||
* This is done avoiding races using ZFS_ENTER(zfsvfs).
|
||||
* A ZFS_EXIT(zfsvfs) is needed before all returns. Any znodes
|
||||
* must be checked with ZFS_VERIFY_ZP(zp). Both of these macros
|
||||
* can return EIO from the calling function.
|
||||
* A ZFS_EXIT(zfsvfs) is needed before all returns. Any znodes
|
||||
* must be checked with ZFS_VERIFY_ZP(zp). Both of these macros
|
||||
* can return EIO from the calling function.
|
||||
*
|
||||
* (2) VN_RELE() should always be the last thing except for zil_commit()
|
||||
* (if necessary) and ZFS_EXIT(). This is for 3 reasons:
|
||||
@ -127,7 +127,7 @@
|
||||
* (5) If the operation succeeded, generate the intent log entry for it
|
||||
* before dropping locks. This ensures that the ordering of events
|
||||
* in the intent log matches the order in which they actually occurred.
|
||||
* During ZIL replay the zfs_log_* functions will update the sequence
|
||||
* During ZIL replay the zfs_log_* functions will update the sequence
|
||||
* number to indicate the zil transaction has replayed.
|
||||
*
|
||||
* (6) At the end of each vnode op, the DMU tx must always commit,
|
||||
@ -384,7 +384,7 @@ update_pages(vnode_t *vp, int64_t start, int len, objset_t *os, uint64_t oid)
|
||||
* else we default from the dmu buffer.
|
||||
*
|
||||
* NOTE: We will always "break up" the IO into PAGESIZE uiomoves when
|
||||
* the file is memory mapped.
|
||||
* the file is memory mapped.
|
||||
*/
|
||||
static int
|
||||
mappedread(vnode_t *vp, int nbytes, uio_t *uio)
|
||||
@ -433,8 +433,7 @@ offset_t zfs_read_chunk_size = 1024 * 1024; /* Tunable */
|
||||
*
|
||||
* OUT: uio - updated offset and range, buffer filled.
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Side Effects:
|
||||
* vp - atime updated if byte count > 0
|
||||
@ -570,14 +569,14 @@ zfs_read(vnode_t *vp, uio_t *uio, int ioflag, cred_t *cr, caller_context_t *ct)
|
||||
* IN: vp - vnode of file to be written to.
|
||||
* uio - structure supplying write location, range info,
|
||||
* and data buffer.
|
||||
* ioflag - FAPPEND flag set if in append mode.
|
||||
* ioflag - FAPPEND, FSYNC, and/or FDSYNC. FAPPEND is
|
||||
* set if in append mode.
|
||||
* cr - credentials of caller.
|
||||
* ct - caller context (NFS/CIFS fem monitor only)
|
||||
*
|
||||
* OUT: uio - updated offset and range.
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Timestamps:
|
||||
* vp - ctime|mtime updated if byte count > 0
|
||||
@ -1148,8 +1147,7 @@ specvp_check(vnode_t **vpp, cred_t *cr)
|
||||
*
|
||||
* OUT: vpp - vnode of located entry, NULL if not found.
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Timestamps:
|
||||
* NA
|
||||
@ -1290,8 +1288,7 @@ zfs_lookup(vnode_t *dvp, char *nm, vnode_t **vpp, struct pathname *pnp,
|
||||
*
|
||||
* OUT: vpp - vnode of created or trunc'd entry.
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Timestamps:
|
||||
* dvp - ctime|mtime updated if new entry created
|
||||
@ -1541,8 +1538,7 @@ zfs_create(vnode_t *dvp, char *name, vattr_t *vap, vcexcl_t excl,
|
||||
* ct - caller context
|
||||
* flags - case flags
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Timestamps:
|
||||
* dvp - ctime|mtime
|
||||
@ -1772,12 +1768,12 @@ zfs_remove(vnode_t *dvp, char *name, cred_t *cr, caller_context_t *ct,
|
||||
* vap - attributes of new directory.
|
||||
* cr - credentials of caller.
|
||||
* ct - caller context
|
||||
* flags - case flags
|
||||
* vsecp - ACL to be set
|
||||
*
|
||||
* OUT: vpp - vnode of created directory.
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Timestamps:
|
||||
* dvp - ctime|mtime updated
|
||||
@ -1957,8 +1953,7 @@ zfs_mkdir(vnode_t *dvp, char *dirname, vattr_t *vap, vnode_t **vpp, cred_t *cr,
|
||||
* ct - caller context
|
||||
* flags - case flags
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Timestamps:
|
||||
* dvp - ctime|mtime updated
|
||||
@ -2076,7 +2071,7 @@ zfs_rmdir(vnode_t *dvp, char *name, vnode_t *cwd, cred_t *cr,
|
||||
/*
|
||||
* Read as many directory entries as will fit into the provided
|
||||
* buffer from the given directory cursor position (specified in
|
||||
* the uio structure.
|
||||
* the uio structure).
|
||||
*
|
||||
* IN: vp - vnode of directory to read.
|
||||
* uio - structure supplying read location, range info,
|
||||
@ -2088,8 +2083,7 @@ zfs_rmdir(vnode_t *dvp, char *name, vnode_t *cwd, cred_t *cr,
|
||||
* OUT: uio - updated offset and range, buffer filled.
|
||||
* eofp - set to true if end-of-file detected.
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Timestamps:
|
||||
* vp - atime updated
|
||||
@ -2408,7 +2402,7 @@ zfs_fsync(vnode_t *vp, int syncflag, cred_t *cr, caller_context_t *ct)
|
||||
*
|
||||
* OUT: vap - attribute values.
|
||||
*
|
||||
* RETURN: 0 (always succeeds)
|
||||
* RETURN: 0 (always succeeds).
|
||||
*/
|
||||
/* ARGSUSED */
|
||||
static int
|
||||
@ -2610,8 +2604,7 @@ zfs_getattr(vnode_t *vp, vattr_t *vap, int flags, cred_t *cr,
|
||||
* cr - credentials of caller.
|
||||
* ct - caller context
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Timestamps:
|
||||
* vp - ctime updated, mtime updated if size changed.
|
||||
@ -2619,7 +2612,7 @@ zfs_getattr(vnode_t *vp, vattr_t *vap, int flags, cred_t *cr,
|
||||
/* ARGSUSED */
|
||||
static int
|
||||
zfs_setattr(vnode_t *vp, vattr_t *vap, int flags, cred_t *cr,
|
||||
caller_context_t *ct)
|
||||
caller_context_t *ct)
|
||||
{
|
||||
znode_t *zp = VTOZ(vp);
|
||||
zfsvfs_t *zfsvfs = zp->z_zfsvfs;
|
||||
@ -3212,6 +3205,7 @@ zfs_setattr(vnode_t *vp, vattr_t *vap, int flags, cred_t *cr,
|
||||
|
||||
if (attrzp)
|
||||
VN_RELE(ZTOV(attrzp));
|
||||
|
||||
if (aclp)
|
||||
zfs_acl_free(aclp);
|
||||
|
||||
@ -3346,8 +3340,7 @@ zfs_rename_lock(znode_t *szp, znode_t *tdzp, znode_t *sdzp, zfs_zlock_t **zlpp)
|
||||
* ct - caller context
|
||||
* flags - case flags
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Timestamps:
|
||||
* sdvp,tdvp - ctime|mtime updated
|
||||
@ -3694,13 +3687,11 @@ zfs_rename(vnode_t *sdvp, char *snm, vnode_t *tdvp, char *tnm, cred_t *cr,
|
||||
* IN: dvp - Directory to contain new symbolic link.
|
||||
* link - Name for new symlink entry.
|
||||
* vap - Attributes of new entry.
|
||||
* target - Target path of new symlink.
|
||||
* cr - credentials of caller.
|
||||
* ct - caller context
|
||||
* flags - case flags
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Timestamps:
|
||||
* dvp - ctime|mtime updated
|
||||
@ -3846,14 +3837,13 @@ zfs_symlink(vnode_t *dvp, char *name, vattr_t *vap, char *link, cred_t *cr,
|
||||
* the symbolic path referred to by vp.
|
||||
*
|
||||
* IN: vp - vnode of symbolic link.
|
||||
* uoip - structure to contain the link path.
|
||||
* uio - structure to contain the link path.
|
||||
* cr - credentials of caller.
|
||||
* ct - caller context
|
||||
*
|
||||
* OUT: uio - structure to contain the link path.
|
||||
* OUT: uio - structure containing the link path.
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Timestamps:
|
||||
* vp - atime updated
|
||||
@ -3892,8 +3882,7 @@ zfs_readlink(vnode_t *vp, uio_t *uio, cred_t *cr, caller_context_t *ct)
|
||||
* cr - credentials of caller.
|
||||
* ct - caller context
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Timestamps:
|
||||
* tdvp - ctime|mtime updated
|
||||
@ -4061,8 +4050,7 @@ zfs_null_putapage(vnode_t *vp, page_t *pp, u_offset_t *offp,
|
||||
* OUT: offp - start of range pushed.
|
||||
* lenp - len of range pushed.
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* NOTE: callers must have locked the page to be pushed. On
|
||||
* exit, the page (and all other pages in the kluster) must be
|
||||
@ -4184,8 +4172,7 @@ zfs_putapage(vnode_t *vp, page_t *pp, u_offset_t *offp,
|
||||
* cr - credentials of caller.
|
||||
* ct - caller context.
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Timestamps:
|
||||
* vp - ctime|mtime updated
|
||||
@ -4350,8 +4337,7 @@ zfs_inactive(vnode_t *vp, cred_t *cr, caller_context_t *ct)
|
||||
* noffp - pointer to new file offset
|
||||
* ct - caller context
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* EINVAL if new offset invalid
|
||||
* RETURN: 0 on success, EINVAL if new offset invalid.
|
||||
*/
|
||||
/* ARGSUSED */
|
||||
static int
|
||||
@ -4487,8 +4473,7 @@ zfs_fillpage(vnode_t *vp, u_offset_t off, struct seg *seg,
|
||||
* OUT: protp - protection mode of created pages.
|
||||
* pl - list of pages created.
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Timestamps:
|
||||
* vp - atime updated
|
||||
@ -4496,8 +4481,8 @@ zfs_fillpage(vnode_t *vp, u_offset_t off, struct seg *seg,
|
||||
/* ARGSUSED */
|
||||
static int
|
||||
zfs_getpage(vnode_t *vp, offset_t off, size_t len, uint_t *protp,
|
||||
page_t *pl[], size_t plsz, struct seg *seg, caddr_t addr,
|
||||
enum seg_rw rw, cred_t *cr, caller_context_t *ct)
|
||||
page_t *pl[], size_t plsz, struct seg *seg, caddr_t addr,
|
||||
enum seg_rw rw, cred_t *cr, caller_context_t *ct)
|
||||
{
|
||||
znode_t *zp = VTOZ(vp);
|
||||
zfsvfs_t *zfsvfs = zp->z_zfsvfs;
|
||||
@ -4572,15 +4557,11 @@ zfs_getpage(vnode_t *vp, offset_t off, size_t len, uint_t *protp,
|
||||
* Request a memory map for a section of a file. This code interacts
|
||||
* with common code and the VM system as follows:
|
||||
*
|
||||
* common code calls mmap(), which ends up in smmap_common()
|
||||
*
|
||||
* this calls VOP_MAP(), which takes you into (say) zfs
|
||||
*
|
||||
* zfs_map() calls as_map(), passing segvn_create() as the callback
|
||||
*
|
||||
* segvn_create() creates the new segment and calls VOP_ADDMAP()
|
||||
*
|
||||
* zfs_addmap() updates z_mapcnt
|
||||
* - common code calls mmap(), which ends up in smmap_common()
|
||||
* - this calls VOP_MAP(), which takes you into (say) zfs
|
||||
* - zfs_map() calls as_map(), passing segvn_create() as the callback
|
||||
* - segvn_create() creates the new segment and calls VOP_ADDMAP()
|
||||
* - zfs_addmap() updates z_mapcnt
|
||||
*/
|
||||
/*ARGSUSED*/
|
||||
static int
|
||||
@ -4722,8 +4703,7 @@ zfs_delmap(vnode_t *vp, offset_t off, struct as *as, caddr_t addr,
|
||||
* cr - credentials of caller [UNUSED].
|
||||
* ct - caller context.
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure.
|
||||
*
|
||||
* Timestamps:
|
||||
* vp - ctime|mtime updated
|
||||
@ -4938,13 +4918,14 @@ zfs_setsecattr(vnode_t *vp, vsecattr_t *vsecp, int flag, cred_t *cr,
|
||||
}
|
||||
|
||||
/*
|
||||
* Tunable, both must be a power of 2.
|
||||
*
|
||||
* zcr_blksz_min: the smallest read we may consider to loan out an arcbuf
|
||||
* zcr_blksz_max: if set to less than the file block size, allow loaning out of
|
||||
* an arcbuf for a partial block read
|
||||
* The smallest read we may consider to loan out an arcbuf.
|
||||
* This must be a power of 2.
|
||||
*/
|
||||
int zcr_blksz_min = (1 << 10); /* 1K */
|
||||
/*
|
||||
* If set to less than the file block size, allow loaning out of an
|
||||
* arcbuf for a partial block read. This must be a power of 2.
|
||||
*/
|
||||
int zcr_blksz_max = (1 << 17); /* 128K */
|
||||
|
||||
/*ARGSUSED*/
|
||||
@ -5218,10 +5199,12 @@ const fs_operation_def_t zfs_sharevnodeops_template[] = {
|
||||
|
||||
/*
|
||||
* Extended attribute directory vnode operations template
|
||||
* This template is identical to the directory vnodes
|
||||
* operation template except for restricted operations:
|
||||
* VOP_MKDIR()
|
||||
* VOP_SYMLINK()
|
||||
*
|
||||
* This template is identical to the directory vnodes
|
||||
* operation template except for restricted operations:
|
||||
* VOP_MKDIR()
|
||||
* VOP_SYMLINK()
|
||||
*
|
||||
* Note that there are other restrictions embedded in:
|
||||
* zfs_create() - restrict type to VREG
|
||||
* zfs_link() - no links into/out of attribute space
|
||||
|
@ -1006,9 +1006,8 @@ zfs_mknode(znode_t *dzp, vattr_t *vap, dmu_tx_t *tx, cred_t *cr,
|
||||
}
|
||||
|
||||
/*
|
||||
* zfs_xvattr_set only updates the in-core attributes
|
||||
* it is assumed the caller will be doing an sa_bulk_update
|
||||
* to push the changes out
|
||||
* Update in-core attributes. It is assumed the caller will be doing an
|
||||
* sa_bulk_update to push the changes out.
|
||||
*/
|
||||
void
|
||||
zfs_xvattr_set(znode_t *zp, xvattr_t *xvap, dmu_tx_t *tx)
|
||||
@ -1447,8 +1446,7 @@ zfs_no_putpage(vnode_t *vp, page_t *pp, u_offset_t *offp, size_t *lenp,
|
||||
* IN: zp - znode of file to free data in.
|
||||
* end - new end-of-file
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure
|
||||
*/
|
||||
static int
|
||||
zfs_extend(znode_t *zp, uint64_t end)
|
||||
@ -1525,8 +1523,7 @@ zfs_extend(znode_t *zp, uint64_t end)
|
||||
* off - start of section to free.
|
||||
* len - length of section to free.
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure
|
||||
*/
|
||||
static int
|
||||
zfs_free_range(znode_t *zp, uint64_t off, uint64_t len)
|
||||
@ -1564,8 +1561,7 @@ zfs_free_range(znode_t *zp, uint64_t off, uint64_t len)
|
||||
* IN: zp - znode of file to free data in.
|
||||
* end - new end-of-file.
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure
|
||||
*/
|
||||
static int
|
||||
zfs_trunc(znode_t *zp, uint64_t end)
|
||||
@ -1663,8 +1659,7 @@ zfs_trunc(znode_t *zp, uint64_t end)
|
||||
* flag - current file open mode flags.
|
||||
* log - TRUE if this action should be logged
|
||||
*
|
||||
* RETURN: 0 if success
|
||||
* error code if failure
|
||||
* RETURN: 0 on success, error code on failure
|
||||
*/
|
||||
int
|
||||
zfs_freesp(znode_t *zp, uint64_t off, uint64_t len, int flag, boolean_t log)
|
||||
|
@ -66,9 +66,9 @@
|
||||
*/
|
||||
|
||||
/*
|
||||
* This global ZIL switch affects all pools
|
||||
* Disable intent logging replay. This global ZIL switch affects all pools.
|
||||
*/
|
||||
int zil_replay_disable = 0; /* disable intent logging replay */
|
||||
int zil_replay_disable = 0;
|
||||
|
||||
/*
|
||||
* Tunable parameter for debugging or performance analysis. Setting
|
||||
@ -879,6 +879,7 @@ zil_lwb_write_init(zilog_t *zilog, lwb_t *lwb)
|
||||
|
||||
/*
|
||||
* Define a limited set of intent log block sizes.
|
||||
*
|
||||
* These must be a multiple of 4KB. Note only the amount used (again
|
||||
* aligned to 4KB) actually gets written. However, we can't always just
|
||||
* allocate SPA_MAXBLOCKSIZE as the slog space could be exhausted.
|
||||
|
@ -1185,13 +1185,16 @@ zio_interrupt(zio_t *zio)
|
||||
|
||||
/*
|
||||
* Execute the I/O pipeline until one of the following occurs:
|
||||
* (1) the I/O completes; (2) the pipeline stalls waiting for
|
||||
* dependent child I/Os; (3) the I/O issues, so we're waiting
|
||||
* for an I/O completion interrupt; (4) the I/O is delegated by
|
||||
* vdev-level caching or aggregation; (5) the I/O is deferred
|
||||
* due to vdev-level queueing; (6) the I/O is handed off to
|
||||
* another thread. In all cases, the pipeline stops whenever
|
||||
* there's no CPU work; it never burns a thread in cv_wait().
|
||||
*
|
||||
* (1) the I/O completes
|
||||
* (2) the pipeline stalls waiting for dependent child I/Os
|
||||
* (3) the I/O issues, so we're waiting for an I/O completion interrupt
|
||||
* (4) the I/O is delegated by vdev-level caching or aggregation
|
||||
* (5) the I/O is deferred due to vdev-level queueing
|
||||
* (6) the I/O is handed off to another thread.
|
||||
*
|
||||
* In all cases, the pipeline stops whenever there's no CPU work; it never
|
||||
* burns a thread in cv_wait().
|
||||
*
|
||||
* There's no locking on io_stage because there's no legitimate way
|
||||
* for multiple threads to be attempting to process the same I/O.
|
||||
|
Loading…
Reference in New Issue
Block a user