OpenE2K
/
qemu-e2k
13
4
Fork 0
Code Issues 4 Pull Requests Projects 2 Releases Activity

9pfs: introduce macOS host support and cleanup 

* Add support for Darwin (a.k.a. macOS) hosts.
 
 * Code cleanup (move qemu_dirent_dup() from osdep -> 9p-util).
 
 * API doc cleanup (convert Doxygen -> kerneldoc format).
 -----BEGIN PGP SIGNATURE-----
 
 iQJLBAABCgA1FiEEltjREM96+AhPiFkBNMK1h2Wkc5UFAmIl6SUXHHFlbXVfb3Nz
 QGNydWRlYnl0ZS5jb20ACgkQNMK1h2Wkc5WIAg//fAigCqLTYGL1MzOILppRXfJa
 3XBdCogLT8m0y+DFoCXgwQx4VU05xPj69633e6nmm4tuyhqMqiIjVQl8EZfH89wD
 vK3NlMJxevkK8soiOB91iyUD0LifrsdS7RwLF4XQmQ+tQbu6p+zLBjDBHYQScyUh
 Tms0YD5A+ubWb5s8fZ0NS+zi3GXUAKhnxtypHQjelsL492uXBOdVs+F3a/gCHzhq
 SyRJn0rdJ+MWZP4QYTpAeOC1YkYd4D52nuuLE4SY/lf3XdHIcUSVAKdWkEuJUAQC
 u7miCqmkXAjfiiu4/vIGeL2nSwApF6hNAckIoaH6jt3xZEeINmw612oO6uG5Ra3R
 AqAT1wNASf4e36Ee26pIwcbHVk0fTBjpmaTmlwb9ts1kSaCW5clopvQSkQuER9cz
 zqGZqD6uWSkfOFaGuLc6ai4/jkxeaM+7liALcXsm68/AnF/5zWPLsF73OrZDjA1H
 VXVg43+686HRBaHez1eLGmM4dJxlglgVEO35+rPeuztRtwL81v+RhBDcQWsjsxY1
 FO5V9LddpfvXgPNlcFNd3+PQnNzy7t4Oz1GKbRZ/bM9hv5+XiObUq+GuO4FvvrLj
 tmICJ7RYmV91H7MK5bFG1HA1qkdJkXu1GvW6x/knjnSKo6RhEAudDQZhrdjVGjVD
 vfDxPB4jHm0tKbIbtuU=
 =Fikk
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/cschoenebeck/tags/pull-9p-20220307' into staging

9pfs: introduce macOS host support and cleanup

* Add support for Darwin (a.k.a. macOS) hosts.

* Code cleanup (move qemu_dirent_dup() from osdep -> 9p-util).

* API doc cleanup (convert Doxygen -> kerneldoc format).

# gpg: Signature made Mon 07 Mar 2022 11:14:45 GMT
# gpg:                using RSA key 96D8D110CF7AF8084F88590134C2B58765A47395
# gpg:                issuer "qemu_oss@crudebyte.com"
# gpg: Good signature from "Christian Schoenebeck <qemu_oss@crudebyte.com>" [unknown]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: ECAB 1A45 4014 1413 BA38  4926 30DB 47C3 A012 D5F4
#      Subkey fingerprint: 96D8 D110 CF7A F808 4F88  5901 34C2 B587 65A4 7395

* remotes/cschoenebeck/tags/pull-9p-20220307:
  fsdev/p9array.h: convert Doxygen -> kerneldoc format
  9pfs/coth.h: drop Doxygen format on v9fs_co_run_in_worker()
  9pfs/9p-util.h: convert Doxygen -> kerneldoc format
  9pfs/9p.c: convert Doxygen -> kerneldoc format
  9pfs/codir.c: convert Doxygen -> kerneldoc format
  9pfs/9p.h: convert Doxygen -> kerneldoc format
  9pfs: drop Doxygen format from qemu_dirent_dup() API comment
  9pfs: move qemu_dirent_dup() from osdep -> 9p-util
  9p: darwin: meson: Allow VirtFS on Darwin
  9p: darwin: Adjust assumption on virtio-9p-test
  9p: darwin: Implement compatibility for mknodat
  9p: darwin: Compatibility for f/l*xattr
  9p: darwin: *xattr_nofollow implementations
  9p: darwin: Move XATTR_SIZE_MAX->P9_XATTR_SIZE_MAX
  9p: darwin: Ignore O_{NOATIME, DIRECT}
  9p: darwin: Handle struct dirent differences
  9p: darwin: Handle struct stat(fs) differences
  9p: Rename 9p-util -> 9p-util-linux
  9p: linux: Fix a couple Linux assumptions

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Peter Maydell 2022-03-08 09:06:57 +00:00
parent 99c4a9e68e 35b6466459
commit f45cc81911
19 changed files with 404 additions and 128 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
fsdev/file-op-9p.h
View File

@ -16,10 +16,17 @@
#include <dirent.h>
#include <utime.h>
#include <sys/vfs.h>
#include "qemu-fsdev-throttle.h"
#include "p9array.h"
#ifdef CONFIG_LINUX
# include <sys/vfs.h>
#endif
#ifdef CONFIG_DARWIN
# include <sys/param.h>
# include <sys/mount.h>
#endif
#define SM_LOCAL_MODE_BITS 0600
#define SM_LOCAL_DIR_MODE_BITS 0700

1
fsdev/meson.build
View File

@ -7,6 +7,7 @@ fsdev_ss.add(when: ['CONFIG_FSDEV_9P'], if_true: files(
'qemu-fsdev.c',
), if_false: files('qemu-fsdev-dummy.c'))
softmmu_ss.add_all(when: 'CONFIG_LINUX', if_true: fsdev_ss)
softmmu_ss.add_all(when: 'CONFIG_DARWIN', if_true: fsdev_ss)
if have_virtfs_proxy_helper
executable('virtfs-proxy-helper',

38
fsdev/p9array.h
View File

@ -81,11 +81,11 @@
*/
/**
* Declares an array type for the passed @a scalar_type.
* P9ARRAY_DECLARE_TYPE() - Declares an array type for the passed @scalar_type.
*
* @scalar_type: type of the individual array elements
*
* This is typically used from a shared header file.
*
* @param scalar_type - type of the individual array elements
*/
#define P9ARRAY_DECLARE_TYPE(scalar_type) \
typedef struct P9Array##scalar_type { \
@ -97,14 +97,14 @@
void p9array_auto_free_##scalar_type(scalar_type **auto_var); \
/**
* Defines an array type for the passed @a scalar_type and appropriate
* @a scalar_cleanup_func.
* P9ARRAY_DEFINE_TYPE() - Defines an array type for the passed @scalar_type
* and appropriate @scalar_cleanup_func.
*
* @scalar_type: type of the individual array elements
* @scalar_cleanup_func: appropriate function to free memory dynamically
* allocated by individual array elements before
*
* This is typically used from a C unit file.
*
* @param scalar_type - type of the individual array elements
* @param scalar_cleanup_func - appropriate function to free memory dynamically
* allocated by individual array elements before
*/
#define P9ARRAY_DEFINE_TYPE(scalar_type, scalar_cleanup_func) \
void p9array_new_##scalar_type(scalar_type **auto_var, size_t len) \
@ -132,23 +132,27 @@
} \
/**
* P9ARRAY_REF() - Declare a reference variable for an array.
*
* @scalar_type: type of the individual array elements
*
* Used to declare a reference variable (unique pointer) for an array. After
* leaving the scope of the reference variable, the associated array is
* automatically freed.
*
* @param scalar_type - type of the individual array elements
*/
#define P9ARRAY_REF(scalar_type) \
__attribute((__cleanup__(p9array_auto_free_##scalar_type))) scalar_type*
/**
* Allocates a new array of passed @a scalar_type with @a len number of array
* elements and assigns the created array to the reference variable
* @a auto_var.
* P9ARRAY_NEW() - Allocate a new array.
*
* @param scalar_type - type of the individual array elements
* @param auto_var - destination reference variable
* @param len - amount of array elements to be allocated immediately
* @scalar_type: type of the individual array elements
* @auto_var: destination reference variable
* @len: amount of array elements to be allocated immediately
*
* Allocates a new array of passed @scalar_type with @len number of array
* elements and assigns the created array to the reference variable
* @auto_var.
*/
#define P9ARRAY_NEW(scalar_type, auto_var, len) \
QEMU_BUILD_BUG_MSG( \

27
hw/9pfs/9p-local.c
View File

@ -32,10 +32,12 @@
#include "qemu/error-report.h"
#include "qemu/option.h"
#include <libgen.h>
#ifdef CONFIG_LINUX
#include <linux/fs.h>
#ifdef CONFIG_LINUX_MAGIC_H
#include <linux/magic.h>
#endif
#endif
#include <sys/ioctl.h>
#ifndef XFS_SUPER_MAGIC
@ -560,6 +562,15 @@ again:
if (!entry) {
return NULL;
}
#ifdef CONFIG_DARWIN
int off;
off = telldir(fs->dir.stream);
/* If telldir fails, fail the entire readdir call */
if (off < 0) {
return NULL;
}
entry->d_seekoff = off;
#endif
if (ctx->export_flags & V9FS_SM_MAPPED) {
entry->d_type = DT_UNKNOWN;
@ -671,7 +682,7 @@ static int local_mknod(FsContext *fs_ctx, V9fsPath *dir_path,
if (fs_ctx->export_flags & V9FS_SM_MAPPED ||
fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
err = mknodat(dirfd, name, fs_ctx->fmode | S_IFREG, 0);
err = qemu_mknodat(dirfd, name, fs_ctx->fmode | S_IFREG, 0);
if (err == -1) {
goto out;
}
@ -686,7 +697,7 @@ static int local_mknod(FsContext *fs_ctx, V9fsPath *dir_path,
}
} else if (fs_ctx->export_flags & V9FS_SM_PASSTHROUGH ||
fs_ctx->export_flags & V9FS_SM_NONE) {
err = mknodat(dirfd, name, credp->fc_mode, credp->fc_rdev);
err = qemu_mknodat(dirfd, name, credp->fc_mode, credp->fc_rdev);
if (err == -1) {
goto out;
}
@ -779,16 +790,20 @@ static int local_fstat(FsContext *fs_ctx, int fid_type,
mode_t tmp_mode;
dev_t tmp_dev;
if (fgetxattr(fd, "user.virtfs.uid", &tmp_uid, sizeof(uid_t)) > 0) {
if (qemu_fgetxattr(fd, "user.virtfs.uid",
&tmp_uid, sizeof(uid_t)) > 0) {
stbuf->st_uid = le32_to_cpu(tmp_uid);
}
if (fgetxattr(fd, "user.virtfs.gid", &tmp_gid, sizeof(gid_t)) > 0) {
if (qemu_fgetxattr(fd, "user.virtfs.gid",
&tmp_gid, sizeof(gid_t)) > 0) {
stbuf->st_gid = le32_to_cpu(tmp_gid);
}
if (fgetxattr(fd, "user.virtfs.mode", &tmp_mode, sizeof(mode_t)) > 0) {
if (qemu_fgetxattr(fd, "user.virtfs.mode",
&tmp_mode, sizeof(mode_t)) > 0) {
stbuf->st_mode = le32_to_cpu(tmp_mode);
}
if (fgetxattr(fd, "user.virtfs.rdev", &tmp_dev, sizeof(dev_t)) > 0) {
if (qemu_fgetxattr(fd, "user.virtfs.rdev",
&tmp_dev, sizeof(dev_t)) > 0) {
stbuf->st_rdev = le64_to_cpu(tmp_dev);
}
} else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {

40
hw/9pfs/9p-proxy.c
View File

@ -123,10 +123,16 @@ static void prstatfs_to_statfs(struct statfs *stfs, ProxyStatFS *prstfs)
stfs->f_bavail = prstfs->f_bavail;
stfs->f_files = prstfs->f_files;
stfs->f_ffree = prstfs->f_ffree;
#ifdef CONFIG_DARWIN
/* f_namelen and f_frsize do not exist on Darwin */
stfs->f_fsid.val[0] = prstfs->f_fsid[0] & 0xFFFFFFFFU;
stfs->f_fsid.val[1] = prstfs->f_fsid[1] >> 32 & 0xFFFFFFFFU;
#else
stfs->f_fsid.__val[0] = prstfs->f_fsid[0] & 0xFFFFFFFFU;
stfs->f_fsid.__val[1] = prstfs->f_fsid[1] >> 32 & 0xFFFFFFFFU;
stfs->f_namelen = prstfs->f_namelen;
stfs->f_frsize = prstfs->f_frsize;
#endif
}
/* Converts proxy_stat structure to VFS stat structure */
@ -143,12 +149,24 @@ static void prstat_to_stat(struct stat *stbuf, ProxyStat *prstat)
stbuf->st_size = prstat->st_size;
stbuf->st_blksize = prstat->st_blksize;
stbuf->st_blocks = prstat->st_blocks;
stbuf->st_atim.tv_sec = prstat->st_atim_sec;
stbuf->st_atim.tv_nsec = prstat->st_atim_nsec;
stbuf->st_atime = prstat->st_atim_sec;
stbuf->st_mtime = prstat->st_mtim_sec;
stbuf->st_mtim.tv_nsec = prstat->st_mtim_nsec;
stbuf->st_ctime = prstat->st_ctim_sec;
#ifdef CONFIG_DARWIN
stbuf->st_atimespec.tv_sec = prstat->st_atim_sec;
stbuf->st_mtimespec.tv_sec = prstat->st_mtim_sec;
stbuf->st_ctimespec.tv_sec = prstat->st_ctim_sec;
stbuf->st_atimespec.tv_nsec = prstat->st_atim_nsec;
stbuf->st_mtimespec.tv_nsec = prstat->st_mtim_nsec;
stbuf->st_ctimespec.tv_nsec = prstat->st_ctim_nsec;
#else
stbuf->st_atim.tv_sec = prstat->st_atim_sec;
stbuf->st_mtim.tv_sec = prstat->st_mtim_sec;
stbuf->st_ctim.tv_sec = prstat->st_ctim_sec;
stbuf->st_atim.tv_nsec = prstat->st_atim_nsec;
stbuf->st_mtim.tv_nsec = prstat->st_mtim_nsec;
stbuf->st_ctim.tv_nsec = prstat->st_ctim_nsec;
#endif
}
/*
@ -688,7 +706,21 @@ static off_t proxy_telldir(FsContext *ctx, V9fsFidOpenState *fs)
static struct dirent *proxy_readdir(FsContext *ctx, V9fsFidOpenState *fs)
{
return readdir(fs->dir.stream);
struct dirent *entry;
entry = readdir(fs->dir.stream);
#ifdef CONFIG_DARWIN
if (!entry) {
return NULL;
}
int td;
td = telldir(fs->dir.stream);
/* If telldir fails, fail the entire readdir call */
if (td < 0) {
return NULL;
}
entry->d_seekoff = td;
#endif
return entry;
}
static void proxy_seekdir(FsContext *ctx, V9fsFidOpenState *fs, off_t off)

6
hw/9pfs/9p-synth.c
View File

@ -234,7 +234,11 @@ static void synth_direntry(V9fsSynthNode *node,
offsetof(struct dirent, d_name) + sz);
memcpy(entry->d_name, node->name, sz);
entry->d_ino = node->attr->inode;
#ifdef CONFIG_DARWIN
entry->d_seekoff = off + 1;
#else
entry->d_off = off + 1;
#endif
}
static struct dirent *synth_get_dentry(V9fsSynthNode *dir,
@ -439,7 +443,9 @@ static int synth_statfs(FsContext *s, V9fsPath *fs_path,
stbuf->f_bsize = 512;
stbuf->f_blocks = 0;
stbuf->f_files = synth_node_count;
#ifndef CONFIG_DARWIN
stbuf->f_namelen = NAME_MAX;
#endif
return 0;
}

97
hw/9pfs/9p-util-darwin.c Normal file
View File

@ -0,0 +1,97 @@
/*
* 9p utilities (Darwin Implementation)
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "qemu/xattr.h"
#include "qapi/error.h"
#include "qemu/error-report.h"
#include "9p-util.h"
ssize_t fgetxattrat_nofollow(int dirfd, const char *filename, const char *name,
void *value, size_t size)
{
int ret;
int fd = openat_file(dirfd, filename,
O_RDONLY | O_PATH_9P_UTIL | O_NOFOLLOW, 0);
if (fd == -1) {
return -1;
}
ret = fgetxattr(fd, name, value, size, 0, 0);
close_preserve_errno(fd);
return ret;
}
ssize_t flistxattrat_nofollow(int dirfd, const char *filename,
char *list, size_t size)
{
int ret;
int fd = openat_file(dirfd, filename,
O_RDONLY | O_PATH_9P_UTIL | O_NOFOLLOW, 0);
if (fd == -1) {
return -1;
}
ret = flistxattr(fd, list, size, 0);
close_preserve_errno(fd);
return ret;
}
ssize_t fremovexattrat_nofollow(int dirfd, const char *filename,
const char *name)
{
int ret;
int fd = openat_file(dirfd, filename, O_PATH_9P_UTIL | O_NOFOLLOW, 0);
if (fd == -1) {
return -1;
}
ret = fremovexattr(fd, name, 0);
close_preserve_errno(fd);
return ret;
}
int fsetxattrat_nofollow(int dirfd, const char *filename, const char *name,
void *value, size_t size, int flags)
{
int ret;
int fd = openat_file(dirfd, filename, O_PATH_9P_UTIL | O_NOFOLLOW, 0);
if (fd == -1) {
return -1;
}
ret = fsetxattr(fd, name, value, size, 0, flags);
close_preserve_errno(fd);
return ret;
}
/*
* As long as mknodat is not available on macOS, this workaround
* using pthread_fchdir_np is needed.
*
* Radar filed with Apple for implementing mknodat:
* rdar://FB9862426 (https://openradar.appspot.com/FB9862426)
*/
#if defined CONFIG_PTHREAD_FCHDIR_NP
int qemu_mknodat(int dirfd, const char *filename, mode_t mode, dev_t dev)
{
int preserved_errno, err;
if (!pthread_fchdir_np) {
error_report_once("pthread_fchdir_np() not available on this version of macOS");
return -ENOTSUP;
}
if (pthread_fchdir_np(dirfd) < 0) {
return -1;
}
err = mknod(filename, mode, dev);
preserved_errno = errno;
/* Stop using the thread-local cwd */
pthread_fchdir_np(-1);
if (err < 0) {
errno = preserved_errno;
}
return err;
}
#endif

8
hw/9pfs/9p-util.c → hw/9pfs/9p-util-linux.c
View File

@ -1,5 +1,5 @@
/*
* 9p utilities
* 9p utilities (Linux Implementation)
*
* Copyright IBM, Corp. 2017
*
@ -61,4 +61,10 @@ int fsetxattrat_nofollow(int dirfd, const char *filename, const char *name,
ret = lsetxattr(proc_path, name, value, size, flags);
g_free(proc_path);
return ret;
}
int qemu_mknodat(int dirfd, const char *filename, mode_t mode, dev_t dev)
{
return mknodat(dirfd, filename, mode, dev);
}

78
hw/9pfs/9p-util.h
View File

@ -19,6 +19,23 @@
#define O_PATH_9P_UTIL 0
#endif
#ifdef CONFIG_DARWIN
#define qemu_fgetxattr(...) fgetxattr(__VA_ARGS__, 0, 0)
#define qemu_lgetxattr(...) getxattr(__VA_ARGS__, 0, XATTR_NOFOLLOW)
#define qemu_llistxattr(...) listxattr(__VA_ARGS__, XATTR_NOFOLLOW)
#define qemu_lremovexattr(...) removexattr(__VA_ARGS__, XATTR_NOFOLLOW)
static inline int qemu_lsetxattr(const char *path, const char *name,
const void *value, size_t size, int flags) {
return setxattr(path, name, value, size, 0, flags | XATTR_NOFOLLOW);
}
#else
#define qemu_fgetxattr fgetxattr
#define qemu_lgetxattr lgetxattr
#define qemu_llistxattr llistxattr
#define qemu_lremovexattr lremovexattr
#define qemu_lsetxattr lsetxattr
#endif
static inline void close_preserve_errno(int fd)
{
int serrno = errno;
@ -37,10 +54,13 @@ static inline int openat_file(int dirfd, const char *name, int flags,
{
int fd, serrno, ret;
#ifndef CONFIG_DARWIN
again:
#endif
fd = openat(dirfd, name, flags | O_NOFOLLOW | O_NOCTTY | O_NONBLOCK,
mode);
if (fd == -1) {
#ifndef CONFIG_DARWIN
if (errno == EPERM && (flags & O_NOATIME)) {
/*
* The client passed O_NOATIME but we lack permissions to honor it.
@ -53,6 +73,7 @@ again:
flags &= ~O_NOATIME;
goto again;
}
#endif
return -1;
}
@ -78,4 +99,61 @@ ssize_t flistxattrat_nofollow(int dirfd, const char *filename,
ssize_t fremovexattrat_nofollow(int dirfd, const char *filename,
const char *name);
/*
* Darwin has d_seekoff, which appears to function similarly to d_off.
* However, it does not appear to be supported on all file systems,
* so ensure it is manually injected earlier and call here when
* needed.
*/
static inline off_t qemu_dirent_off(struct dirent *dent)
{
#ifdef CONFIG_DARWIN
return dent->d_seekoff;
#else
return dent->d_off;
#endif
}
/**
* qemu_dirent_dup() - Duplicate directory entry @dent.
*
* @dent: original directory entry to be duplicated
* Return: duplicated directory entry which should be freed with g_free()
*
* It is highly recommended to use this function instead of open coding
* duplication of dirent objects, because the actual struct dirent
* size may be bigger or shorter than sizeof(struct dirent) and correct
* handling is platform specific (see gitlab issue #841).
*/
static inline struct dirent *qemu_dirent_dup(struct dirent *dent)
{
size_t sz = 0;
#if defined _DIRENT_HAVE_D_RECLEN
/* Avoid use of strlen() if platform supports d_reclen. */
sz = dent->d_reclen;
#endif
/*
* Test sz for zero even if d_reclen is available
* because some drivers may set d_reclen to zero.
*/
if (sz == 0) {
/* Fallback to the most portable way. */
sz = offsetof(struct dirent, d_name) +
strlen(dent->d_name) + 1;
}
return g_memdup(dent, sz);
}
/*
* As long as mknodat is not available on macOS, this workaround
* using pthread_fchdir_np is needed. qemu_mknodat is defined in
* os-posix.c. pthread_fchdir_np is weakly linked here as a guard
* in case it disappears in future macOS versions, because it is
* is a private API.
*/
#if defined CONFIG_DARWIN && defined CONFIG_PTHREAD_FCHDIR_NP
int pthread_fchdir_np(int fd) __attribute__((weak_import));
#endif
int qemu_mknodat(int dirfd, const char *filename, mode_t mode, dev_t dev);
#endif

104
hw/9pfs/9p.c
View File

@ -27,12 +27,17 @@
#include "virtio-9p.h"
#include "fsdev/qemu-fsdev.h"
#include "9p-xattr.h"
#include "9p-util.h"
#include "coth.h"
#include "trace.h"
#include "migration/blocker.h"
#include "qemu/xxhash.h"
#include <math.h>
#ifdef CONFIG_LINUX
#include <linux/limits.h>
#else
#include <limits.h>
#endif
int open_fd_hw;
int total_open_fd;
@ -133,11 +138,20 @@ static int dotl_to_open_flags(int flags)
{ P9_DOTL_NONBLOCK, O_NONBLOCK } ,
{ P9_DOTL_DSYNC, O_DSYNC },
{ P9_DOTL_FASYNC, FASYNC },
#ifndef CONFIG_DARWIN
{ P9_DOTL_NOATIME, O_NOATIME },
/*
* On Darwin, we could map to F_NOCACHE, which is
* similar, but doesn't quite have the same
* semantics. However, we don't support O_DIRECT
* even on linux at the moment, so we just ignore
* it here.
*/
{ P9_DOTL_DIRECT, O_DIRECT },
#endif
{ P9_DOTL_LARGEFILE, O_LARGEFILE },
{ P9_DOTL_DIRECTORY, O_DIRECTORY },
{ P9_DOTL_NOFOLLOW, O_NOFOLLOW },
{ P9_DOTL_NOATIME, O_NOATIME },
{ P9_DOTL_SYNC, O_SYNC },
};
@ -166,10 +180,12 @@ static int get_dotl_openflags(V9fsState *s, int oflags)
*/
flags = dotl_to_open_flags(oflags);
flags &= ~(O_NOCTTY | O_ASYNC | O_CREAT);
#ifndef CONFIG_DARWIN
/*
* Ignore direct disk access hint until the server supports it.
*/
flags &= ~O_DIRECT;
#endif
return flags;
}
@ -612,8 +628,8 @@ static inline uint64_t mirror64bit(uint64_t value)
((uint64_t)mirror8bit((value >> 56) & 0xff));
}
/**
* @brief Parameter k for the Exponential Golomb algorihm to be used.
/*
* Parameter k for the Exponential Golomb algorihm to be used.
*
* The smaller this value, the smaller the minimum bit count for the Exp.
* Golomb generated affixes will be (at lowest index) however for the
@ -626,28 +642,30 @@ static inline uint64_t mirror64bit(uint64_t value)
* should be small, for a large amount of devices k might be increased
* instead. The default of k=0 should be fine for most users though.
*
* @b IMPORTANT: In case this ever becomes a runtime parameter; the value of
* IMPORTANT: In case this ever becomes a runtime parameter; the value of
* k should not change as long as guest is still running! Because that would
* cause completely different inode numbers to be generated on guest.
*/
#define EXP_GOLOMB_K 0
/**
* @brief Exponential Golomb algorithm for arbitrary k (including k=0).
* expGolombEncode() - Exponential Golomb algorithm for arbitrary k
* (including k=0).
*
* The Exponential Golomb algorithm generates @b prefixes (@b not suffixes!)
* @n: natural number (or index) of the prefix to be generated
* (1, 2, 3, ...)
* @k: parameter k of Exp. Golomb algorithm to be used
* (see comment on EXP_GOLOMB_K macro for details about k)
* Return: prefix for given @n and @k
*
* The Exponential Golomb algorithm generates prefixes (NOT suffixes!)
* with growing length and with the mathematical property of being
* "prefix-free". The latter means the generated prefixes can be prepended
* in front of arbitrary numbers and the resulting concatenated numbers are
* guaranteed to be always unique.
*
* This is a minor adjustment to the original Exp. Golomb algorithm in the
* sense that lowest allowed index (@param n) starts with 1, not with zero.
*
* @param n - natural number (or index) of the prefix to be generated
* (1, 2, 3, ...)
* @param k - parameter k of Exp. Golomb algorithm to be used
* (see comment on EXP_GOLOMB_K macro for details about k)
* sense that lowest allowed index (@n) starts with 1, not with zero.
*/
static VariLenAffix expGolombEncode(uint64_t n, int k)
{
@ -661,7 +679,9 @@ static VariLenAffix expGolombEncode(uint64_t n, int k)
}
/**
* @brief Converts a suffix into a prefix, or a prefix into a suffix.
* invertAffix() - Converts a suffix into a prefix, or a prefix into a suffix.
* @affix: either suffix or prefix to be inverted
* Return: inversion of passed @affix
*
* Simply mirror all bits of the affix value, for the purpose to preserve
* respectively the mathematical "prefix-free" or "suffix-free" property
@ -685,16 +705,16 @@ static VariLenAffix invertAffix(const VariLenAffix *affix)
}
/**
* @brief Generates suffix numbers with "suffix-free" property.
* affixForIndex() - Generates suffix numbers with "suffix-free" property.
* @index: natural number (or index) of the suffix to be generated
* (1, 2, 3, ...)
* Return: Suffix suitable to assemble unique number.
*
* This is just a wrapper function on top of the Exp. Golomb algorithm.
*
* Since the Exp. Golomb algorithm generates prefixes, but we need suffixes,
* this function converts the Exp. Golomb prefixes into appropriate suffixes
* which are still suitable for generating unique numbers.
*
* @param n - natural number (or index) of the suffix to be generated
* (1, 2, 3, ...)
*/
static VariLenAffix affixForIndex(uint64_t index)
{
@ -794,8 +814,8 @@ static int qid_inode_prefix_hash_bits(V9fsPDU *pdu, dev_t dev)
return val->prefix_bits;
}
/**
* @brief Slow / full mapping host inode nr -> guest inode nr.
/*
* Slow / full mapping host inode nr -> guest inode nr.
*
* This function performs a slower and much more costly remapping of an
* original file inode number on host to an appropriate different inode
@ -807,7 +827,7 @@ static int qid_inode_prefix_hash_bits(V9fsPDU *pdu, dev_t dev)
* qid_path_suffixmap() failed. In practice this slow / full mapping is not
* expected ever to be used at all though.
*
* @see qid_path_suffixmap() for details
* See qid_path_suffixmap() for details
*
*/
static int qid_path_fullmap(V9fsPDU *pdu, const struct stat *stbuf,
@ -848,8 +868,8 @@ static int qid_path_fullmap(V9fsPDU *pdu, const struct stat *stbuf,
return 0;
}
/**
* @brief Quick mapping host inode nr -> guest inode nr.
/*
* Quick mapping host inode nr -> guest inode nr.
*
* This function performs quick remapping of an original file inode number
* on host to an appropriate different inode number on guest. This remapping
@ -1265,12 +1285,15 @@ static int coroutine_fn stat_to_v9stat(V9fsPDU *pdu, V9fsPath *path,
/**
* Convert host filesystem's block size into an appropriate block size for
* 9p client (guest OS side). The value returned suggests an "optimum" block
* size for 9p I/O, i.e. to maximize performance.
* blksize_to_iounit() - Block size exposed to 9p client.
* Return: block size
*
* @pdu: 9p client request
* @blksize: host filesystem's block size
*
* Convert host filesystem's block size into an appropriate block size for
* 9p client (guest OS side). The value returned suggests an "optimum" block
* size for 9p I/O, i.e. to maximize performance.
*/
static int32_t blksize_to_iounit(const V9fsPDU *pdu, int32_t blksize)
{
@ -1309,11 +1332,17 @@ static int stat_to_v9stat_dotl(V9fsPDU *pdu, const struct stat *stbuf,
v9lstat->st_blksize = stat_to_iounit(pdu, stbuf);
v9lstat->st_blocks = stbuf->st_blocks;
v9lstat->st_atime_sec = stbuf->st_atime;
v9lstat->st_atime_nsec = stbuf->st_atim.tv_nsec;
v9lstat->st_mtime_sec = stbuf->st_mtime;
v9lstat->st_mtime_nsec = stbuf->st_mtim.tv_nsec;
v9lstat->st_ctime_sec = stbuf->st_ctime;
#ifdef CONFIG_DARWIN
v9lstat->st_atime_nsec = stbuf->st_atimespec.tv_nsec;
v9lstat->st_mtime_nsec = stbuf->st_mtimespec.tv_nsec;
v9lstat->st_ctime_nsec = stbuf->st_ctimespec.tv_nsec;
#else
v9lstat->st_atime_nsec = stbuf->st_atim.tv_nsec;
v9lstat->st_mtime_nsec = stbuf->st_mtim.tv_nsec;
v9lstat->st_ctime_nsec = stbuf->st_ctim.tv_nsec;
#endif
/* Currently we only support BASIC fields in stat */
v9lstat->st_result_mask = P9_STATS_BASIC;
@ -2271,7 +2300,7 @@ static int coroutine_fn v9fs_do_readdir_with_stat(V9fsPDU *pdu,
count += len;
v9fs_stat_free(&v9stat);
v9fs_path_free(&path);
saved_dir_pos = dent->d_off;
saved_dir_pos = qemu_dirent_off(dent);
}
v9fs_readdir_unlock(&fidp->fs.dir);
@ -2376,10 +2405,11 @@ out_nofid:
}
/**
* Returns size required in Rreaddir response for the passed dirent @p name.
* v9fs_readdir_response_size() - Returns size required in Rreaddir response
* for the passed dirent @name.
*
* @param name - directory entry's name (i.e. file name, directory name)
* @returns required size in bytes
* @name: directory entry's name (i.e. file name, directory name)
* Return: required size in bytes
*/
size_t v9fs_readdir_response_size(V9fsString *name)
{
@ -2410,6 +2440,7 @@ static int coroutine_fn v9fs_do_readdir(V9fsPDU *pdu, V9fsFidState *fidp,
V9fsString name;
int len, err = 0;
int32_t count = 0;
off_t off;
struct dirent *dent;
struct stat *st;
struct V9fsDirEnt *entries = NULL;
@ -2470,12 +2501,13 @@ static int coroutine_fn v9fs_do_readdir(V9fsPDU *pdu, V9fsFidState *fidp,
qid.version = 0;
}
off = qemu_dirent_off(dent);
v9fs_string_init(&name);
v9fs_string_sprintf(&name, "%s", dent->d_name);
/* 11 = 7 + 4 (7 = start offset, 4 = space for storing count) */
len = pdu_marshal(pdu, 11 + count, "Qqbs",
&qid, dent->d_off,
&qid, off,
dent->d_type, &name);
v9fs_string_free(&name);
@ -3515,9 +3547,15 @@ static int v9fs_fill_statfs(V9fsState *s, V9fsPDU *pdu, struct statfs *stbuf)
f_bavail = stbuf->f_bavail / bsize_factor;
f_files = stbuf->f_files;
f_ffree = stbuf->f_ffree;
#ifdef CONFIG_DARWIN
fsid_val = (unsigned int)stbuf->f_fsid.val[0] |
(unsigned long long)stbuf->f_fsid.val[1] << 32;
f_namelen = NAME_MAX;
#else
fsid_val = (unsigned int) stbuf->f_fsid.__val[0] |
(unsigned long long)stbuf->f_fsid.__val[1] << 32;
f_namelen = stbuf->f_namelen;
#endif
return pdu_marshal(pdu, offset, "ddqqqqqqd",
f_type, f_bsize, f_blocks, f_bfree,
@ -3919,7 +3957,7 @@ static void coroutine_fn v9fs_xattrcreate(void *opaque)
rflags |= XATTR_REPLACE;
}
if (size > XATTR_SIZE_MAX) {
if (size > P9_XATTR_SIZE_MAX) {
err = -E2BIG;
goto out_nofid;
}

30
hw/9pfs/9p.h
View File

@ -100,8 +100,8 @@ typedef enum P9ProtoVersion {
V9FS_PROTO_2000L = 0x02,
} P9ProtoVersion;
/**
* @brief Minimum message size supported by this 9pfs server.
/*
* Minimum message size supported by this 9pfs server.
*
* A client establishes a session by sending a Tversion request along with a
* 'msize' parameter which suggests the server a maximum message size ever to be
@ -231,7 +231,7 @@ static inline void v9fs_readdir_init(P9ProtoVersion proto_version, V9fsDir *dir)
}
}
/**
/*
* Type for 9p fs drivers' (a.k.a. 9p backends) result of readdir requests,
* which is a chained list of directory entries.
*/
@ -289,8 +289,8 @@ typedef enum AffixType_t {
AffixType_Suffix, /* A.k.a. postfix. */
} AffixType_t;
/**
* @brief Unique affix of variable length.
/*
* 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
@ -304,7 +304,7 @@ 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
* Lenght of the affix, that is how many (of the lowest) bits of ``value``
* must be used for appending/prepending this affix to its final resulting,
* unique number.
*/
@ -479,4 +479,22 @@ struct V9fsTransport {
void (*push_and_notify)(V9fsPDU *pdu);
};
#if defined(XATTR_SIZE_MAX)
/* Linux */
#define P9_XATTR_SIZE_MAX XATTR_SIZE_MAX
#elif defined(CONFIG_DARWIN)
/*
* Darwin doesn't seem to define a maximum xattr size in its user
* space header, so manually configure it across platforms as 64k.
*
* Having no limit at all can lead to QEMU crashing during large g_malloc()
* calls. Because QEMU does not currently support macOS guests, the below
* preliminary solution only works due to its being a reflection of the limit of
* Linux guests.
*/
#define P9_XATTR_SIZE_MAX 65536
#else
#error Missing definition for P9_XATTR_SIZE_MAX for this host system
#endif
#endif

34
hw/9pfs/codir.c
View File

@ -22,6 +22,8 @@
#include "qemu/coroutine.h"
#include "qemu/main-loop.h"
#include "coth.h"
#include "9p-xattr.h"
#include "9p-util.h"
/*
* Intended to be called from bottom-half (e.g. background I/O thread)
@ -166,7 +168,7 @@ static int do_readdir_many(V9fsPDU *pdu, V9fsFidState *fidp,
}
size += len;
saved_dir_pos = dent->d_off;
saved_dir_pos = qemu_dirent_off(dent);
}
/* restore (last) saved position */
@ -182,14 +184,25 @@ out:
}
/**
* @brief Reads multiple directory entries in one rush.
* v9fs_co_readdir_many() - Reads multiple directory entries in one rush.
*
* @pdu: the causing 9p (T_readdir) client request
* @fidp: already opened directory where readdir shall be performed on
* @entries: output for directory entries (must not be NULL)
* @offset: initial position inside the directory the function shall
* seek to before retrieving the directory entries
* @maxsize: maximum result message body size (in bytes)
* @dostat: whether a stat() should be performed and returned for
* each directory entry
* Return: resulting response message body size (in bytes) on success,
* negative error code otherwise
*
* Retrieves the requested (max. amount of) directory entries from the fs
* driver. This function must only be called by the main IO thread (top half).
* Internally this function call will be dispatched to a background IO thread
* (bottom half) where it is eventually executed by the fs driver.
*
* @discussion Acquiring multiple directory entries in one rush from the fs
* Acquiring multiple directory entries in one rush from the fs
* driver, instead of retrieving each directory entry individually, is very
* beneficial from performance point of view. Because for every fs driver
* request latency is added, which in practice could lead to overall
@ -197,20 +210,9 @@ out:
* directory) if every directory entry was individually requested from fs
* driver.
*
* @note You must @b ALWAYS call @c v9fs_free_dirents(entries) after calling
* NOTE: You must ALWAYS call v9fs_free_dirents(entries) after calling
* v9fs_co_readdir_many(), both on success and on error cases of this
* function, to avoid memory leaks once @p entries are no longer needed.
*
* @param pdu - the causing 9p (T_readdir) client request
* @param fidp - already opened directory where readdir shall be performed on
* @param entries - output for directory entries (must not be NULL)
* @param offset - initial position inside the directory the function shall
* seek to before retrieving the directory entries
* @param maxsize - maximum result message body size (in bytes)
* @param dostat - whether a stat() should be performed and returned for
* each directory entry
* @returns resulting response message body size (in bytes) on success,
* negative error code otherwise
* function, to avoid memory leaks once @entries are no longer needed.
*/
int coroutine_fn v9fs_co_readdir_many(V9fsPDU *pdu, V9fsFidState *fidp,
struct V9fsDirEnt **entries,

4
hw/9pfs/coth.h
View File

@ -19,7 +19,7 @@
#include "qemu/coroutine.h"
#include "9p.h"
/**
/*
* we want to use bottom half because we want to make sure the below
* sequence of events.
*
@ -29,7 +29,7 @@
* we cannot swap step 1 and 2, because that would imply worker thread
* can enter coroutine while step1 is still running
*
* @b PERFORMANCE @b CONSIDERATIONS: As a rule of thumb, keep in mind
* PERFORMANCE CONSIDERATIONS: As a rule of thumb, keep in mind
* that hopping between threads adds @b latency! So when handling a
* 9pfs request, avoid calling v9fs_co_run_in_worker() too often, because
* this might otherwise sum up to a significant, huge overall latency for

3
hw/9pfs/meson.build
View File

@ -4,7 +4,6 @@ fs_ss.add(files(
'9p-posix-acl.c',
'9p-proxy.c',
'9p-synth.c',
'9p-util.c',
'9p-xattr-user.c',
'9p-xattr.c',
'9p.c',
@ -14,6 +13,8 @@ fs_ss.add(files(
'coth.c',
'coxattr.c',
))
fs_ss.add(when: 'CONFIG_LINUX', if_true: files('9p-util-linux.c'))
fs_ss.add(when: 'CONFIG_DARWIN', if_true: files('9p-util-darwin.c'))
fs_ss.add(when: 'CONFIG_XEN', if_true: files('xen-9p-backend.c'))
softmmu_ss.add_all(when: 'CONFIG_FSDEV_9P', if_true: fs_ss)

13
include/qemu/osdep.h
View File

@ -673,19 +673,6 @@ static inline int platform_does_not_support_system(const char *command)
}
#endif /* !HAVE_SYSTEM_FUNCTION */
/**
* Duplicate directory entry @dent.
*
* It is highly recommended to use this function instead of open coding
* duplication of @c dirent objects, because the actual @c struct @c dirent
* size may be bigger or shorter than @c sizeof(struct dirent) and correct
* handling is platform specific (see gitlab issue #841).
*
* @dent - original directory entry to be duplicated
* @returns duplicated directory entry which should be freed with g_free()
*/
struct dirent *qemu_dirent_dup(struct dirent *dent);
#ifdef __cplusplus
}
#endif

4
include/qemu/xattr.h
View File

@ -22,7 +22,9 @@
#ifdef CONFIG_LIBATTR
# include <attr/xattr.h>
#else
# define ENOATTR ENODATA
# if !defined(ENOATTR)
# define ENOATTR ENODATA
# endif
# include <sys/xattr.h>
#endif

13
meson.build
View File

@ -1462,14 +1462,16 @@ dbus_display = get_option('dbus_display') \
.allowed()
have_virtfs = get_option('virtfs') \
.require(targetos == 'linux',
error_message: 'virtio-9p (virtfs) requires Linux') \
.require(libattr.found() and libcap_ng.found(),
error_message: 'virtio-9p (virtfs) requires libcap-ng-devel and libattr-devel') \
.require(targetos == 'linux' or targetos == 'darwin',
error_message: 'virtio-9p (virtfs) requires Linux or macOS') \
.require(targetos == 'linux' or cc.has_function('pthread_fchdir_np'),
error_message: 'virtio-9p (virtfs) on macOS requires the presence of pthread_fchdir_np') \
.require(targetos == 'darwin' or (libattr.found() and libcap_ng.found()),
error_message: 'virtio-9p (virtfs) on Linux requires libcap-ng-devel and libattr-devel') \
.disable_auto_if(not have_tools and not have_system) \
.allowed()
have_virtfs_proxy_helper = have_virtfs and have_tools
have_virtfs_proxy_helper = targetos != 'darwin' and have_virtfs and have_tools
foreach k : get_option('trace_backends')
config_host_data.set('CONFIG_TRACE_' + k.to_upper(), true)
@ -1622,6 +1624,7 @@ config_host_data.set('CONFIG_POSIX_FALLOCATE', cc.has_function('posix_fallocate'
config_host_data.set('CONFIG_POSIX_MEMALIGN', cc.has_function('posix_memalign'))
config_host_data.set('CONFIG_PPOLL', cc.has_function('ppoll'))
config_host_data.set('CONFIG_PREADV', cc.has_function('preadv', prefix: '#include <sys/uio.h>'))
config_host_data.set('CONFIG_PTHREAD_FCHDIR_NP', cc.has_function('pthread_fchdir_np'))
config_host_data.set('CONFIG_SEM_TIMEDWAIT', cc.has_function('sem_timedwait', dependencies: threads))
config_host_data.set('CONFIG_SENDFILE', cc.has_function('sendfile'))
config_host_data.set('CONFIG_SETNS', cc.has_function('setns') and cc.has_function('unshare'))

2
tests/qtest/virtio-9p-test.c
View File

@ -1253,7 +1253,7 @@ static void fs_unlinkat_dir(void *obj, void *data, QGuestAllocator *t_alloc)
/* ... and is actually a directory */
g_assert((st.st_mode & S_IFMT) == S_IFDIR);
do_unlinkat(v9p, "/", "02", AT_REMOVEDIR);
do_unlinkat(v9p, "/", "02", P9_DOTL_AT_REMOVEDIR);
/* directory should be gone now */
g_assert(stat(new_dir, &st) != 0);
}

21
util/osdep.c
View File

@ -33,7 +33,6 @@
extern int madvise(char *, size_t, int);
#endif
#include <dirent.h>
#include "qemu-common.h"
#include "qemu/cutils.h"
#include "qemu/sockets.h"
@ -619,23 +618,3 @@ writev(int fd, const struct iovec *iov, int iov_cnt)
return readv_writev(fd, iov, iov_cnt, true);
}
#endif
struct dirent *
qemu_dirent_dup(struct dirent *dent)
{
size_t sz = 0;
#if defined _DIRENT_HAVE_D_RECLEN
/* Avoid use of strlen() if platform supports d_reclen. */
sz = dent->d_reclen;
#endif
/*
* Test sz for zero even if d_reclen is available
* because some drivers may set d_reclen to zero.
*/
if (sz == 0) {
/* Fallback to the most portable way. */
sz = offsetof(struct dirent, d_name) +
strlen(dent->d_name) + 1;
}
return g_memdup(dent, sz);
}