qemu-e2k/hw/9pfs/9p.h

435 lines
10 KiB
C
Raw Normal View History

#ifndef QEMU_9P_H
#define QEMU_9P_H
#include <dirent.h>
#include <utime.h>
#include <sys/resource.h>
#include "fsdev/file-op-9p.h"
#include "fsdev/9p-iov-marshal.h"
#include "qemu/thread.h"
#include "qemu/coroutine.h"
9p: Added virtfs option 'multidevs=remap|forbid|warn' 'warn' (default): Only log an error message (once) on host if more than one device is shared by same export, except of that just ignore this config error though. This is the default behaviour for not breaking existing installations implying that they really know what they are doing. 'forbid': Like 'warn', but except of just logging an error this also denies access of guest to additional devices. 'remap': Allows to share more than one device per export by remapping inodes from host to guest appropriately. To support multiple devices on the 9p share, and avoid qid path collisions we take the device id as input to generate a unique QID path. The lowest 48 bits of the path will be set equal to the file inode, and the top bits will be uniquely assigned based on the top 16 bits of the inode and the device id. Signed-off-by: Antonios Motakis <antonios.motakis@huawei.com> [CS: - Rebased to https://github.com/gkurz/qemu/commits/9p-next (SHA1 7fc4c49e91). - Added virtfs option 'multidevs', original patch simply did the inode remapping without being asked. - Updated hash calls to new xxhash API. - Updated docs for new option 'multidevs'. - Fixed v9fs_do_readdir() not having remapped inodes. - Log error message when running out of prefixes in qid_path_prefixmap(). - Fixed definition of QPATH_INO_MASK. - Wrapped qpp_table initialization to dedicated qpp_table_init() function. - Dropped unnecessary parantheses in qpp_lookup_func(). - Dropped unnecessary g_malloc0() result checks. ] Signed-off-by: Christian Schoenebeck <qemu_oss@crudebyte.com> [groug: - Moved "multidevs" parsing to the local backend. - Added hint to invalid multidevs option error. - Turn "remap" into "x-remap". ] Signed-off-by: Greg Kurz <groug@kaod.org>
2019-10-10 11:36:05 +02:00
#include "qemu/qht.h"
enum {
P9_TLERROR = 6,
P9_RLERROR,
P9_TSTATFS = 8,
P9_RSTATFS,
P9_TLOPEN = 12,
P9_RLOPEN,
P9_TLCREATE = 14,
P9_RLCREATE,
P9_TSYMLINK = 16,
P9_RSYMLINK,
P9_TMKNOD = 18,
P9_RMKNOD,
P9_TRENAME = 20,
P9_RRENAME,
P9_TREADLINK = 22,
P9_RREADLINK,
P9_TGETATTR = 24,
P9_RGETATTR,
P9_TSETATTR = 26,
P9_RSETATTR,
P9_TXATTRWALK = 30,
P9_RXATTRWALK,
P9_TXATTRCREATE = 32,
P9_RXATTRCREATE,
P9_TREADDIR = 40,
P9_RREADDIR,
P9_TFSYNC = 50,
P9_RFSYNC,
P9_TLOCK = 52,
P9_RLOCK,
P9_TGETLOCK = 54,
P9_RGETLOCK,
P9_TLINK = 70,
P9_RLINK,
P9_TMKDIR = 72,
P9_RMKDIR,
P9_TRENAMEAT = 74,
P9_RRENAMEAT,
P9_TUNLINKAT = 76,
P9_RUNLINKAT,
P9_TVERSION = 100,
P9_RVERSION,
P9_TAUTH = 102,
P9_RAUTH,
P9_TATTACH = 104,
P9_RATTACH,
P9_TERROR = 106,
P9_RERROR,
P9_TFLUSH = 108,
P9_RFLUSH,
P9_TWALK = 110,
P9_RWALK,
P9_TOPEN = 112,
P9_ROPEN,
P9_TCREATE = 114,
P9_RCREATE,
P9_TREAD = 116,
P9_RREAD,
P9_TWRITE = 118,
P9_RWRITE,
P9_TCLUNK = 120,
P9_RCLUNK,
P9_TREMOVE = 122,
P9_RREMOVE,
P9_TSTAT = 124,
P9_RSTAT,
P9_TWSTAT = 126,
P9_RWSTAT,
};
/* qid.types */
enum {
P9_QTDIR = 0x80,
P9_QTAPPEND = 0x40,
P9_QTEXCL = 0x20,
P9_QTMOUNT = 0x10,
P9_QTAUTH = 0x08,
P9_QTTMP = 0x04,
P9_QTSYMLINK = 0x02,
P9_QTLINK = 0x01,
P9_QTFILE = 0x00,
};
typedef enum P9ProtoVersion {
V9FS_PROTO_2000U = 0x01,
V9FS_PROTO_2000L = 0x02,
} P9ProtoVersion;
#define P9_NOTAG UINT16_MAX
#define P9_NOFID UINT32_MAX
#define P9_MAXWELEM 16
#define FID_REFERENCED 0x1
#define FID_NON_RECLAIMABLE 0x2
static inline char *rpath(FsContext *ctx, const char *path)
{
return g_strdup_printf("%s/%s", ctx->fs_root, path);
}
/*
* ample room for Twrite/Rread header
* size[4] Tread/Twrite tag[2] fid[4] offset[8] count[4]
*/
#define P9_IOHDRSZ 24
typedef struct V9fsPDU V9fsPDU;
typedef struct V9fsState V9fsState;
typedef struct V9fsTransport V9fsTransport;
typedef struct {
uint32_t size_le;
uint8_t id;
uint16_t tag_le;
} QEMU_PACKED P9MsgHeader;
/* According to the specification, 9p messages start with a 7-byte header.
* Since most of the code uses this header size in literal form, we must be
* sure this is indeed the case.
*/
QEMU_BUILD_BUG_ON(sizeof(P9MsgHeader) != 7);
struct V9fsPDU
{
uint32_t size;
uint16_t tag;
uint8_t id;
uint8_t cancelled;
CoQueue complete;
V9fsState *s;
QLIST_ENTRY(V9fsPDU) next;
uint32_t idx;
};
/* FIXME
* 1) change user needs to set groups and stuff
*/
#define MAX_REQ 128
#define MAX_TAG_LEN 32
#define BUG_ON(cond) assert(!(cond))
typedef struct V9fsFidState V9fsFidState;
enum {
P9_FID_NONE = 0,
P9_FID_FILE,
P9_FID_DIR,
P9_FID_XATTR,
};
typedef struct V9fsConf
{
/* tag name for the device */
char *tag;
char *fsdev_id;
} V9fsConf;
/* 9p2000.L xattr flags (matches Linux values) */
#define P9_XATTR_CREATE 1
#define P9_XATTR_REPLACE 2
typedef struct V9fsXattr
{
uint64_t copied_len;
uint64_t len;
void *value;
V9fsString name;
int flags;
bool xattrwalk_fid;
} V9fsXattr;
typedef struct V9fsDir {
DIR *stream;
QemuMutex readdir_mutex;
} V9fsDir;
static inline void v9fs_readdir_lock(V9fsDir *dir)
{
qemu_mutex_lock(&dir->readdir_mutex);
}
static inline void v9fs_readdir_unlock(V9fsDir *dir)
{
qemu_mutex_unlock(&dir->readdir_mutex);
}
static inline void v9fs_readdir_init(V9fsDir *dir)
{
qemu_mutex_init(&dir->readdir_mutex);
}
/*
* Filled by fs driver on open and other
* calls.
*/
union V9fsFidOpenState {
int fd;
V9fsDir dir;
V9fsXattr xattr;
/*
* private pointer for fs drivers, that
* have its own internal representation of
* open files.
*/
void *private;
};
struct V9fsFidState
{
int fid_type;
int32_t fid;
V9fsPath path;
V9fsFidOpenState fs;
V9fsFidOpenState fs_reclaim;
int flags;
int open_flags;
uid_t uid;
int ref;
int clunked;
V9fsFidState *next;
V9fsFidState *rclm_lst;
};
9p: Use variable length suffixes for inode remapping Use variable length suffixes for inode remapping instead of the fixed 16 bit size prefixes before. With this change the inode numbers on guest will typically be much smaller (e.g. around >2^1 .. >2^7 instead of >2^48 with the previous fixed size inode remapping. Additionally this solution is more efficient, since inode numbers in practice can take almost their entire 64 bit range on guest as well, so there is less likely a need for generating and tracking additional suffixes, which might also be beneficial for nested virtualization where each level of virtualization would shift up the inode bits and increase the chance of expensive remapping actions. The "Exponential Golomb" algorithm is used as basis for generating the variable length suffixes. The algorithm has a parameter k which controls the distribution of bits on increasing indeces (minimum bits at low index vs. maximum bits at high index). With k=0 the generated suffixes look like: Index Dec/Bin -> Generated Suffix Bin 1 [1] -> [1] (1 bits) 2 [10] -> [010] (3 bits) 3 [11] -> [110] (3 bits) 4 [100] -> [00100] (5 bits) 5 [101] -> [10100] (5 bits) 6 [110] -> [01100] (5 bits) 7 [111] -> [11100] (5 bits) 8 [1000] -> [0001000] (7 bits) 9 [1001] -> [1001000] (7 bits) 10 [1010] -> [0101000] (7 bits) 11 [1011] -> [1101000] (7 bits) 12 [1100] -> [0011000] (7 bits) ... 65533 [1111111111111101] -> [1011111111111111000000000000000] (31 bits) 65534 [1111111111111110] -> [0111111111111111000000000000000] (31 bits) 65535 [1111111111111111] -> [1111111111111111000000000000000] (31 bits) Hence minBits=1 maxBits=31 And with k=5 they would look like: Index Dec/Bin -> Generated Suffix Bin 1 [1] -> [000001] (6 bits) 2 [10] -> [100001] (6 bits) 3 [11] -> [010001] (6 bits) 4 [100] -> [110001] (6 bits) 5 [101] -> [001001] (6 bits) 6 [110] -> [101001] (6 bits) 7 [111] -> [011001] (6 bits) 8 [1000] -> [111001] (6 bits) 9 [1001] -> [000101] (6 bits) 10 [1010] -> [100101] (6 bits) 11 [1011] -> [010101] (6 bits) 12 [1100] -> [110101] (6 bits) ... 65533 [1111111111111101] -> [0011100000000000100000000000] (28 bits) 65534 [1111111111111110] -> [1011100000000000100000000000] (28 bits) 65535 [1111111111111111] -> [0111100000000000100000000000] (28 bits) Hence minBits=6 maxBits=28 Signed-off-by: Christian Schoenebeck <qemu_oss@crudebyte.com> Signed-off-by: Greg Kurz <groug@kaod.org>
2019-10-07 17:02:45 +02:00
typedef enum AffixType_t {
AffixType_Prefix,
AffixType_Suffix, /* A.k.a. postfix. */
} AffixType_t;
/**
* @brief Unique affix of variable length.
*
* An affix is (currently) either a suffix or a prefix, which is either
* going to be prepended (prefix) or appended (suffix) with some other
* number for the goal to generate unique numbers. Accordingly the
* suffixes (or prefixes) we generate @b must all have the mathematical
* property of being suffix-free (or prefix-free in case of prefixes)
* so that no matter what number we concatenate the affix with, that we
* always reliably get unique numbers as result after concatenation.
*/
typedef struct VariLenAffix {
AffixType_t type; /* Whether this affix is a suffix or a prefix. */
uint64_t value; /* Actual numerical value of this affix. */
/*
* Lenght of the affix, that is how many (of the lowest) bits of @c value
* must be used for appending/prepending this affix to its final resulting,
* unique number.
*/
int bits;
} VariLenAffix;
/* See qid_inode_prefix_hash_bits(). */
typedef struct {
dev_t dev; /* FS device on host. */
/*
* How many (high) bits of the original inode number shall be used for
* hashing.
*/
int prefix_bits;
} QpdEntry;
9p: Added virtfs option 'multidevs=remap|forbid|warn' 'warn' (default): Only log an error message (once) on host if more than one device is shared by same export, except of that just ignore this config error though. This is the default behaviour for not breaking existing installations implying that they really know what they are doing. 'forbid': Like 'warn', but except of just logging an error this also denies access of guest to additional devices. 'remap': Allows to share more than one device per export by remapping inodes from host to guest appropriately. To support multiple devices on the 9p share, and avoid qid path collisions we take the device id as input to generate a unique QID path. The lowest 48 bits of the path will be set equal to the file inode, and the top bits will be uniquely assigned based on the top 16 bits of the inode and the device id. Signed-off-by: Antonios Motakis <antonios.motakis@huawei.com> [CS: - Rebased to https://github.com/gkurz/qemu/commits/9p-next (SHA1 7fc4c49e91). - Added virtfs option 'multidevs', original patch simply did the inode remapping without being asked. - Updated hash calls to new xxhash API. - Updated docs for new option 'multidevs'. - Fixed v9fs_do_readdir() not having remapped inodes. - Log error message when running out of prefixes in qid_path_prefixmap(). - Fixed definition of QPATH_INO_MASK. - Wrapped qpp_table initialization to dedicated qpp_table_init() function. - Dropped unnecessary parantheses in qpp_lookup_func(). - Dropped unnecessary g_malloc0() result checks. ] Signed-off-by: Christian Schoenebeck <qemu_oss@crudebyte.com> [groug: - Moved "multidevs" parsing to the local backend. - Added hint to invalid multidevs option error. - Turn "remap" into "x-remap". ] Signed-off-by: Greg Kurz <groug@kaod.org>
2019-10-10 11:36:05 +02:00
/* QID path prefix entry, see stat_to_qid */
typedef struct {
dev_t dev;
uint16_t ino_prefix;
9p: Use variable length suffixes for inode remapping Use variable length suffixes for inode remapping instead of the fixed 16 bit size prefixes before. With this change the inode numbers on guest will typically be much smaller (e.g. around >2^1 .. >2^7 instead of >2^48 with the previous fixed size inode remapping. Additionally this solution is more efficient, since inode numbers in practice can take almost their entire 64 bit range on guest as well, so there is less likely a need for generating and tracking additional suffixes, which might also be beneficial for nested virtualization where each level of virtualization would shift up the inode bits and increase the chance of expensive remapping actions. The "Exponential Golomb" algorithm is used as basis for generating the variable length suffixes. The algorithm has a parameter k which controls the distribution of bits on increasing indeces (minimum bits at low index vs. maximum bits at high index). With k=0 the generated suffixes look like: Index Dec/Bin -> Generated Suffix Bin 1 [1] -> [1] (1 bits) 2 [10] -> [010] (3 bits) 3 [11] -> [110] (3 bits) 4 [100] -> [00100] (5 bits) 5 [101] -> [10100] (5 bits) 6 [110] -> [01100] (5 bits) 7 [111] -> [11100] (5 bits) 8 [1000] -> [0001000] (7 bits) 9 [1001] -> [1001000] (7 bits) 10 [1010] -> [0101000] (7 bits) 11 [1011] -> [1101000] (7 bits) 12 [1100] -> [0011000] (7 bits) ... 65533 [1111111111111101] -> [1011111111111111000000000000000] (31 bits) 65534 [1111111111111110] -> [0111111111111111000000000000000] (31 bits) 65535 [1111111111111111] -> [1111111111111111000000000000000] (31 bits) Hence minBits=1 maxBits=31 And with k=5 they would look like: Index Dec/Bin -> Generated Suffix Bin 1 [1] -> [000001] (6 bits) 2 [10] -> [100001] (6 bits) 3 [11] -> [010001] (6 bits) 4 [100] -> [110001] (6 bits) 5 [101] -> [001001] (6 bits) 6 [110] -> [101001] (6 bits) 7 [111] -> [011001] (6 bits) 8 [1000] -> [111001] (6 bits) 9 [1001] -> [000101] (6 bits) 10 [1010] -> [100101] (6 bits) 11 [1011] -> [010101] (6 bits) 12 [1100] -> [110101] (6 bits) ... 65533 [1111111111111101] -> [0011100000000000100000000000] (28 bits) 65534 [1111111111111110] -> [1011100000000000100000000000] (28 bits) 65535 [1111111111111111] -> [0111100000000000100000000000] (28 bits) Hence minBits=6 maxBits=28 Signed-off-by: Christian Schoenebeck <qemu_oss@crudebyte.com> Signed-off-by: Greg Kurz <groug@kaod.org>
2019-10-07 17:02:45 +02:00
uint32_t qp_affix_index;
VariLenAffix qp_affix;
9p: Added virtfs option 'multidevs=remap|forbid|warn' 'warn' (default): Only log an error message (once) on host if more than one device is shared by same export, except of that just ignore this config error though. This is the default behaviour for not breaking existing installations implying that they really know what they are doing. 'forbid': Like 'warn', but except of just logging an error this also denies access of guest to additional devices. 'remap': Allows to share more than one device per export by remapping inodes from host to guest appropriately. To support multiple devices on the 9p share, and avoid qid path collisions we take the device id as input to generate a unique QID path. The lowest 48 bits of the path will be set equal to the file inode, and the top bits will be uniquely assigned based on the top 16 bits of the inode and the device id. Signed-off-by: Antonios Motakis <antonios.motakis@huawei.com> [CS: - Rebased to https://github.com/gkurz/qemu/commits/9p-next (SHA1 7fc4c49e91). - Added virtfs option 'multidevs', original patch simply did the inode remapping without being asked. - Updated hash calls to new xxhash API. - Updated docs for new option 'multidevs'. - Fixed v9fs_do_readdir() not having remapped inodes. - Log error message when running out of prefixes in qid_path_prefixmap(). - Fixed definition of QPATH_INO_MASK. - Wrapped qpp_table initialization to dedicated qpp_table_init() function. - Dropped unnecessary parantheses in qpp_lookup_func(). - Dropped unnecessary g_malloc0() result checks. ] Signed-off-by: Christian Schoenebeck <qemu_oss@crudebyte.com> [groug: - Moved "multidevs" parsing to the local backend. - Added hint to invalid multidevs option error. - Turn "remap" into "x-remap". ] Signed-off-by: Greg Kurz <groug@kaod.org>
2019-10-10 11:36:05 +02:00
} QppEntry;
/* QID path full entry, as above */
typedef struct {
dev_t dev;
ino_t ino;
uint64_t path;
} QpfEntry;
struct V9fsState
{
QLIST_HEAD(, V9fsPDU) free_list;
QLIST_HEAD(, V9fsPDU) active_list;
V9fsFidState *fid_list;
FileOperations *ops;
FsContext ctx;
char *tag;
P9ProtoVersion proto_version;
int32_t msize;
V9fsPDU pdus[MAX_REQ];
const V9fsTransport *transport;
/*
* lock ensuring atomic path update
* on rename.
*/
CoRwlock rename_lock;
int32_t root_fid;
Error *migration_blocker;
V9fsConf fsconf;
V9fsQID root_qid;
dev_t dev_id;
9p: Use variable length suffixes for inode remapping Use variable length suffixes for inode remapping instead of the fixed 16 bit size prefixes before. With this change the inode numbers on guest will typically be much smaller (e.g. around >2^1 .. >2^7 instead of >2^48 with the previous fixed size inode remapping. Additionally this solution is more efficient, since inode numbers in practice can take almost their entire 64 bit range on guest as well, so there is less likely a need for generating and tracking additional suffixes, which might also be beneficial for nested virtualization where each level of virtualization would shift up the inode bits and increase the chance of expensive remapping actions. The "Exponential Golomb" algorithm is used as basis for generating the variable length suffixes. The algorithm has a parameter k which controls the distribution of bits on increasing indeces (minimum bits at low index vs. maximum bits at high index). With k=0 the generated suffixes look like: Index Dec/Bin -> Generated Suffix Bin 1 [1] -> [1] (1 bits) 2 [10] -> [010] (3 bits) 3 [11] -> [110] (3 bits) 4 [100] -> [00100] (5 bits) 5 [101] -> [10100] (5 bits) 6 [110] -> [01100] (5 bits) 7 [111] -> [11100] (5 bits) 8 [1000] -> [0001000] (7 bits) 9 [1001] -> [1001000] (7 bits) 10 [1010] -> [0101000] (7 bits) 11 [1011] -> [1101000] (7 bits) 12 [1100] -> [0011000] (7 bits) ... 65533 [1111111111111101] -> [1011111111111111000000000000000] (31 bits) 65534 [1111111111111110] -> [0111111111111111000000000000000] (31 bits) 65535 [1111111111111111] -> [1111111111111111000000000000000] (31 bits) Hence minBits=1 maxBits=31 And with k=5 they would look like: Index Dec/Bin -> Generated Suffix Bin 1 [1] -> [000001] (6 bits) 2 [10] -> [100001] (6 bits) 3 [11] -> [010001] (6 bits) 4 [100] -> [110001] (6 bits) 5 [101] -> [001001] (6 bits) 6 [110] -> [101001] (6 bits) 7 [111] -> [011001] (6 bits) 8 [1000] -> [111001] (6 bits) 9 [1001] -> [000101] (6 bits) 10 [1010] -> [100101] (6 bits) 11 [1011] -> [010101] (6 bits) 12 [1100] -> [110101] (6 bits) ... 65533 [1111111111111101] -> [0011100000000000100000000000] (28 bits) 65534 [1111111111111110] -> [1011100000000000100000000000] (28 bits) 65535 [1111111111111111] -> [0111100000000000100000000000] (28 bits) Hence minBits=6 maxBits=28 Signed-off-by: Christian Schoenebeck <qemu_oss@crudebyte.com> Signed-off-by: Greg Kurz <groug@kaod.org>
2019-10-07 17:02:45 +02:00
struct qht qpd_table;
9p: Added virtfs option 'multidevs=remap|forbid|warn' 'warn' (default): Only log an error message (once) on host if more than one device is shared by same export, except of that just ignore this config error though. This is the default behaviour for not breaking existing installations implying that they really know what they are doing. 'forbid': Like 'warn', but except of just logging an error this also denies access of guest to additional devices. 'remap': Allows to share more than one device per export by remapping inodes from host to guest appropriately. To support multiple devices on the 9p share, and avoid qid path collisions we take the device id as input to generate a unique QID path. The lowest 48 bits of the path will be set equal to the file inode, and the top bits will be uniquely assigned based on the top 16 bits of the inode and the device id. Signed-off-by: Antonios Motakis <antonios.motakis@huawei.com> [CS: - Rebased to https://github.com/gkurz/qemu/commits/9p-next (SHA1 7fc4c49e91). - Added virtfs option 'multidevs', original patch simply did the inode remapping without being asked. - Updated hash calls to new xxhash API. - Updated docs for new option 'multidevs'. - Fixed v9fs_do_readdir() not having remapped inodes. - Log error message when running out of prefixes in qid_path_prefixmap(). - Fixed definition of QPATH_INO_MASK. - Wrapped qpp_table initialization to dedicated qpp_table_init() function. - Dropped unnecessary parantheses in qpp_lookup_func(). - Dropped unnecessary g_malloc0() result checks. ] Signed-off-by: Christian Schoenebeck <qemu_oss@crudebyte.com> [groug: - Moved "multidevs" parsing to the local backend. - Added hint to invalid multidevs option error. - Turn "remap" into "x-remap". ] Signed-off-by: Greg Kurz <groug@kaod.org>
2019-10-10 11:36:05 +02:00
struct qht qpp_table;
struct qht qpf_table;
9p: Use variable length suffixes for inode remapping Use variable length suffixes for inode remapping instead of the fixed 16 bit size prefixes before. With this change the inode numbers on guest will typically be much smaller (e.g. around >2^1 .. >2^7 instead of >2^48 with the previous fixed size inode remapping. Additionally this solution is more efficient, since inode numbers in practice can take almost their entire 64 bit range on guest as well, so there is less likely a need for generating and tracking additional suffixes, which might also be beneficial for nested virtualization where each level of virtualization would shift up the inode bits and increase the chance of expensive remapping actions. The "Exponential Golomb" algorithm is used as basis for generating the variable length suffixes. The algorithm has a parameter k which controls the distribution of bits on increasing indeces (minimum bits at low index vs. maximum bits at high index). With k=0 the generated suffixes look like: Index Dec/Bin -> Generated Suffix Bin 1 [1] -> [1] (1 bits) 2 [10] -> [010] (3 bits) 3 [11] -> [110] (3 bits) 4 [100] -> [00100] (5 bits) 5 [101] -> [10100] (5 bits) 6 [110] -> [01100] (5 bits) 7 [111] -> [11100] (5 bits) 8 [1000] -> [0001000] (7 bits) 9 [1001] -> [1001000] (7 bits) 10 [1010] -> [0101000] (7 bits) 11 [1011] -> [1101000] (7 bits) 12 [1100] -> [0011000] (7 bits) ... 65533 [1111111111111101] -> [1011111111111111000000000000000] (31 bits) 65534 [1111111111111110] -> [0111111111111111000000000000000] (31 bits) 65535 [1111111111111111] -> [1111111111111111000000000000000] (31 bits) Hence minBits=1 maxBits=31 And with k=5 they would look like: Index Dec/Bin -> Generated Suffix Bin 1 [1] -> [000001] (6 bits) 2 [10] -> [100001] (6 bits) 3 [11] -> [010001] (6 bits) 4 [100] -> [110001] (6 bits) 5 [101] -> [001001] (6 bits) 6 [110] -> [101001] (6 bits) 7 [111] -> [011001] (6 bits) 8 [1000] -> [111001] (6 bits) 9 [1001] -> [000101] (6 bits) 10 [1010] -> [100101] (6 bits) 11 [1011] -> [010101] (6 bits) 12 [1100] -> [110101] (6 bits) ... 65533 [1111111111111101] -> [0011100000000000100000000000] (28 bits) 65534 [1111111111111110] -> [1011100000000000100000000000] (28 bits) 65535 [1111111111111111] -> [0111100000000000100000000000] (28 bits) Hence minBits=6 maxBits=28 Signed-off-by: Christian Schoenebeck <qemu_oss@crudebyte.com> Signed-off-by: Greg Kurz <groug@kaod.org>
2019-10-07 17:02:45 +02:00
uint64_t qp_ndevices; /* Amount of entries in qpd_table. */
uint16_t qp_affix_next;
uint64_t qp_fullpath_next;
};
/* 9p2000.L open flags */
#define P9_DOTL_RDONLY 00000000
#define P9_DOTL_WRONLY 00000001
#define P9_DOTL_RDWR 00000002
#define P9_DOTL_NOACCESS 00000003
#define P9_DOTL_CREATE 00000100
#define P9_DOTL_EXCL 00000200
#define P9_DOTL_NOCTTY 00000400
#define P9_DOTL_TRUNC 00001000
#define P9_DOTL_APPEND 00002000
#define P9_DOTL_NONBLOCK 00004000
#define P9_DOTL_DSYNC 00010000
#define P9_DOTL_FASYNC 00020000
#define P9_DOTL_DIRECT 00040000
#define P9_DOTL_LARGEFILE 00100000
#define P9_DOTL_DIRECTORY 00200000
#define P9_DOTL_NOFOLLOW 00400000
#define P9_DOTL_NOATIME 01000000
#define P9_DOTL_CLOEXEC 02000000
#define P9_DOTL_SYNC 04000000
/* 9p2000.L at flags */
#define P9_DOTL_AT_REMOVEDIR 0x200
/* 9P2000.L lock type */
#define P9_LOCK_TYPE_RDLCK 0
#define P9_LOCK_TYPE_WRLCK 1
#define P9_LOCK_TYPE_UNLCK 2
#define P9_LOCK_SUCCESS 0
#define P9_LOCK_BLOCKED 1
#define P9_LOCK_ERROR 2
#define P9_LOCK_GRACE 3
#define P9_LOCK_FLAGS_BLOCK 1
#define P9_LOCK_FLAGS_RECLAIM 2
typedef struct V9fsFlock
{
uint8_t type;
uint32_t flags;
uint64_t start; /* absolute offset */
uint64_t length;
uint32_t proc_id;
V9fsString client_id;
} V9fsFlock;
typedef struct V9fsGetlock
{
uint8_t type;
uint64_t start; /* absolute offset */
uint64_t length;
uint32_t proc_id;
V9fsString client_id;
} V9fsGetlock;
extern int open_fd_hw;
extern int total_open_fd;
static inline void v9fs_path_write_lock(V9fsState *s)
{
if (s->ctx.export_flags & V9FS_PATHNAME_FSCONTEXT) {
qemu_co_rwlock_wrlock(&s->rename_lock);
}
}
static inline void v9fs_path_read_lock(V9fsState *s)
{
if (s->ctx.export_flags & V9FS_PATHNAME_FSCONTEXT) {
qemu_co_rwlock_rdlock(&s->rename_lock);
}
}
static inline void v9fs_path_unlock(V9fsState *s)
{
if (s->ctx.export_flags & V9FS_PATHNAME_FSCONTEXT) {
qemu_co_rwlock_unlock(&s->rename_lock);
}
}
static inline uint8_t v9fs_request_cancelled(V9fsPDU *pdu)
{
return pdu->cancelled;
}
void coroutine_fn v9fs_reclaim_fd(V9fsPDU *pdu);
void v9fs_path_init(V9fsPath *path);
void v9fs_path_free(V9fsPath *path);
void v9fs_path_sprintf(V9fsPath *path, const char *fmt, ...);
void v9fs_path_copy(V9fsPath *dst, const V9fsPath *src);
int v9fs_name_to_path(V9fsState *s, V9fsPath *dirpath,
const char *name, V9fsPath *path);
int v9fs_device_realize_common(V9fsState *s, const V9fsTransport *t,
Error **errp);
void v9fs_device_unrealize_common(V9fsState *s, Error **errp);
V9fsPDU *pdu_alloc(V9fsState *s);
void pdu_free(V9fsPDU *pdu);
void pdu_submit(V9fsPDU *pdu, P9MsgHeader *hdr);
virtio-9p: add reset handler Virtio devices should implement the VirtIODevice->reset() function to perform necessary cleanup actions and to bring the device to a quiescent state. In the case of the virtio-9p device, this means: - emptying the list of active PDUs (i.e. draining all in-flight I/O) - freeing all fids (i.e. close open file descriptors and free memory) That's what this patch does. The reset handler first waits for all active PDUs to complete. Since completion happens in the QEMU global aio context, we just have to loop around aio_poll() until the active list is empty. The freeing part involves some actions to be performed on the backend, like closing file descriptors or flushing extended attributes to the underlying filesystem. The virtfs_reset() function already does the job: it calls free_fid() for all open fids not involved in an ongoing I/O operation. We are sure this is the case since we have drained the PDU active list. The current code implements all backend accesses with coroutines, but we want to stay synchronous on the reset path. We can either change the current code to be able to run when not in coroutine context, or create a coroutine context and wait for virtfs_reset() to complete. This patch goes for the latter because it results in simpler code. Note that we also need to create a dummy PDU because it is also an API to pass the FsContext pointer to all backend callbacks. Signed-off-by: Greg Kurz <groug@kaod.org> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
2016-10-17 14:13:58 +02:00
void v9fs_reset(V9fsState *s);
struct V9fsTransport {
ssize_t (*pdu_vmarshal)(V9fsPDU *pdu, size_t offset, const char *fmt,
va_list ap);
ssize_t (*pdu_vunmarshal)(V9fsPDU *pdu, size_t offset, const char *fmt,
va_list ap);
void (*init_in_iov_from_pdu)(V9fsPDU *pdu, struct iovec **piov,
unsigned int *pniov, size_t *size);
void (*init_out_iov_from_pdu)(V9fsPDU *pdu, struct iovec **piov,
unsigned int *pniov, size_t size);
void (*push_and_notify)(V9fsPDU *pdu);
};
#endif