diff options
author | Yang Zhang <yang.z.zhang@intel.com> | 2015-08-28 09:58:54 +0800 |
---|---|---|
committer | Yang Zhang <yang.z.zhang@intel.com> | 2015-09-01 12:44:00 +0800 |
commit | e44e3482bdb4d0ebde2d8b41830ac2cdb07948fb (patch) | |
tree | 66b09f592c55df2878107a468a91d21506104d3f /qemu/hw/9pfs | |
parent | 9ca8dbcc65cfc63d6f5ef3312a33184e1d726e00 (diff) |
Add qemu 2.4.0
Change-Id: Ic99cbad4b61f8b127b7dc74d04576c0bcbaaf4f5
Signed-off-by: Yang Zhang <yang.z.zhang@intel.com>
Diffstat (limited to 'qemu/hw/9pfs')
-rw-r--r-- | qemu/hw/9pfs/Makefile.objs | 9 | ||||
-rw-r--r-- | qemu/hw/9pfs/codir.c | 168 | ||||
-rw-r--r-- | qemu/hw/9pfs/cofile.c | 275 | ||||
-rw-r--r-- | qemu/hw/9pfs/cofs.c | 364 | ||||
-rw-r--r-- | qemu/hw/9pfs/coxattr.c | 107 | ||||
-rw-r--r-- | qemu/hw/9pfs/virtio-9p-coth.c | 82 | ||||
-rw-r--r-- | qemu/hw/9pfs/virtio-9p-coth.h | 107 | ||||
-rw-r--r-- | qemu/hw/9pfs/virtio-9p-device.c | 173 | ||||
-rw-r--r-- | qemu/hw/9pfs/virtio-9p-handle.c | 708 | ||||
-rw-r--r-- | qemu/hw/9pfs/virtio-9p-local.c | 1280 | ||||
-rw-r--r-- | qemu/hw/9pfs/virtio-9p-posix-acl.c | 185 | ||||
-rw-r--r-- | qemu/hw/9pfs/virtio-9p-proxy.c | 1219 | ||||
-rw-r--r-- | qemu/hw/9pfs/virtio-9p-proxy.h | 95 | ||||
-rw-r--r-- | qemu/hw/9pfs/virtio-9p-synth.c | 573 | ||||
-rw-r--r-- | qemu/hw/9pfs/virtio-9p-synth.h | 54 | ||||
-rw-r--r-- | qemu/hw/9pfs/virtio-9p-xattr-user.c | 128 | ||||
-rw-r--r-- | qemu/hw/9pfs/virtio-9p-xattr.c | 164 | ||||
-rw-r--r-- | qemu/hw/9pfs/virtio-9p-xattr.h | 120 | ||||
-rw-r--r-- | qemu/hw/9pfs/virtio-9p.c | 3300 | ||||
-rw-r--r-- | qemu/hw/9pfs/virtio-9p.h | 394 |
20 files changed, 9505 insertions, 0 deletions
diff --git a/qemu/hw/9pfs/Makefile.objs b/qemu/hw/9pfs/Makefile.objs new file mode 100644 index 000000000..1e9b595cb --- /dev/null +++ b/qemu/hw/9pfs/Makefile.objs @@ -0,0 +1,9 @@ +common-obj-y = virtio-9p.o +common-obj-y += virtio-9p-local.o virtio-9p-xattr.o +common-obj-y += virtio-9p-xattr-user.o virtio-9p-posix-acl.o +common-obj-y += virtio-9p-coth.o cofs.o codir.o cofile.o +common-obj-y += coxattr.o virtio-9p-synth.o +common-obj-$(CONFIG_OPEN_BY_HANDLE) += virtio-9p-handle.o +common-obj-y += virtio-9p-proxy.o + +obj-y += virtio-9p-device.o diff --git a/qemu/hw/9pfs/codir.c b/qemu/hw/9pfs/codir.c new file mode 100644 index 000000000..65ad3298b --- /dev/null +++ b/qemu/hw/9pfs/codir.c @@ -0,0 +1,168 @@ + +/* + * Virtio 9p backend + * + * Copyright IBM, Corp. 2011 + * + * Authors: + * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "fsdev/qemu-fsdev.h" +#include "qemu/thread.h" +#include "block/coroutine.h" +#include "virtio-9p-coth.h" + +int v9fs_co_readdir_r(V9fsPDU *pdu, V9fsFidState *fidp, struct dirent *dent, + struct dirent **result) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_co_run_in_worker( + { + errno = 0; + err = s->ops->readdir_r(&s->ctx, &fidp->fs, dent, result); + if (!*result && errno) { + err = -errno; + } else { + err = 0; + } + }); + return err; +} + +off_t v9fs_co_telldir(V9fsPDU *pdu, V9fsFidState *fidp) +{ + off_t err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_co_run_in_worker( + { + err = s->ops->telldir(&s->ctx, &fidp->fs); + if (err < 0) { + err = -errno; + } + }); + return err; +} + +void v9fs_co_seekdir(V9fsPDU *pdu, V9fsFidState *fidp, off_t offset) +{ + V9fsState *s = pdu->s; + if (v9fs_request_cancelled(pdu)) { + return; + } + v9fs_co_run_in_worker( + { + s->ops->seekdir(&s->ctx, &fidp->fs, offset); + }); +} + +void v9fs_co_rewinddir(V9fsPDU *pdu, V9fsFidState *fidp) +{ + V9fsState *s = pdu->s; + if (v9fs_request_cancelled(pdu)) { + return; + } + v9fs_co_run_in_worker( + { + s->ops->rewinddir(&s->ctx, &fidp->fs); + }); +} + +int v9fs_co_mkdir(V9fsPDU *pdu, V9fsFidState *fidp, V9fsString *name, + mode_t mode, uid_t uid, gid_t gid, struct stat *stbuf) +{ + int err; + FsCred cred; + V9fsPath path; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + cred_init(&cred); + cred.fc_mode = mode; + cred.fc_uid = uid; + cred.fc_gid = gid; + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->mkdir(&s->ctx, &fidp->path, name->data, &cred); + if (err < 0) { + err = -errno; + } else { + v9fs_path_init(&path); + err = v9fs_name_to_path(s, &fidp->path, name->data, &path); + if (!err) { + err = s->ops->lstat(&s->ctx, &path, stbuf); + if (err < 0) { + err = -errno; + } + } + v9fs_path_free(&path); + } + }); + v9fs_path_unlock(s); + return err; +} + +int v9fs_co_opendir(V9fsPDU *pdu, V9fsFidState *fidp) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->opendir(&s->ctx, &fidp->path, &fidp->fs); + if (err < 0) { + err = -errno; + } else { + err = 0; + } + }); + v9fs_path_unlock(s); + if (!err) { + total_open_fd++; + if (total_open_fd > open_fd_hw) { + v9fs_reclaim_fd(pdu); + } + } + return err; +} + +int v9fs_co_closedir(V9fsPDU *pdu, V9fsFidOpenState *fs) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_co_run_in_worker( + { + err = s->ops->closedir(&s->ctx, fs); + if (err < 0) { + err = -errno; + } + }); + if (!err) { + total_open_fd--; + } + return err; +} diff --git a/qemu/hw/9pfs/cofile.c b/qemu/hw/9pfs/cofile.c new file mode 100644 index 000000000..2efebf357 --- /dev/null +++ b/qemu/hw/9pfs/cofile.c @@ -0,0 +1,275 @@ + +/* + * Virtio 9p backend + * + * Copyright IBM, Corp. 2011 + * + * Authors: + * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "fsdev/qemu-fsdev.h" +#include "qemu/thread.h" +#include "block/coroutine.h" +#include "virtio-9p-coth.h" + +int v9fs_co_st_gen(V9fsPDU *pdu, V9fsPath *path, mode_t st_mode, + V9fsStatDotl *v9stat) +{ + int err = 0; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + if (s->ctx.exops.get_st_gen) { + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ctx.exops.get_st_gen(&s->ctx, path, st_mode, + &v9stat->st_gen); + if (err < 0) { + err = -errno; + } + }); + v9fs_path_unlock(s); + } + return err; +} + +int v9fs_co_lstat(V9fsPDU *pdu, V9fsPath *path, struct stat *stbuf) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->lstat(&s->ctx, path, stbuf); + if (err < 0) { + err = -errno; + } + }); + v9fs_path_unlock(s); + return err; +} + +int v9fs_co_fstat(V9fsPDU *pdu, V9fsFidState *fidp, struct stat *stbuf) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_co_run_in_worker( + { + err = s->ops->fstat(&s->ctx, fidp->fid_type, &fidp->fs, stbuf); + if (err < 0) { + err = -errno; + } + }); + /* + * Some FS driver (local:mapped-file) can't support fetching attributes + * using file descriptor. Use Path name in that case. + */ + if (err == -EOPNOTSUPP) { + err = v9fs_co_lstat(pdu, &fidp->path, stbuf); + if (err == -ENOENT) { + /* + * fstat on an unlinked file. Work with partial results + * returned from s->ops->fstat + */ + err = 0; + } + } + return err; +} + +int v9fs_co_open(V9fsPDU *pdu, V9fsFidState *fidp, int flags) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->open(&s->ctx, &fidp->path, flags, &fidp->fs); + if (err == -1) { + err = -errno; + } else { + err = 0; + } + }); + v9fs_path_unlock(s); + if (!err) { + total_open_fd++; + if (total_open_fd > open_fd_hw) { + v9fs_reclaim_fd(pdu); + } + } + return err; +} + +int v9fs_co_open2(V9fsPDU *pdu, V9fsFidState *fidp, V9fsString *name, gid_t gid, + int flags, int mode, struct stat *stbuf) +{ + int err; + FsCred cred; + V9fsPath path; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + cred_init(&cred); + cred.fc_mode = mode & 07777; + cred.fc_uid = fidp->uid; + cred.fc_gid = gid; + /* + * Hold the directory fid lock so that directory path name + * don't change. Read lock is fine because this fid cannot + * be used by any other operation. + */ + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->open2(&s->ctx, &fidp->path, + name->data, flags, &cred, &fidp->fs); + if (err < 0) { + err = -errno; + } else { + v9fs_path_init(&path); + err = v9fs_name_to_path(s, &fidp->path, name->data, &path); + if (!err) { + err = s->ops->lstat(&s->ctx, &path, stbuf); + if (err < 0) { + err = -errno; + s->ops->close(&s->ctx, &fidp->fs); + } else { + v9fs_path_copy(&fidp->path, &path); + } + } else { + s->ops->close(&s->ctx, &fidp->fs); + } + v9fs_path_free(&path); + } + }); + v9fs_path_unlock(s); + if (!err) { + total_open_fd++; + if (total_open_fd > open_fd_hw) { + v9fs_reclaim_fd(pdu); + } + } + return err; +} + +int v9fs_co_close(V9fsPDU *pdu, V9fsFidOpenState *fs) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_co_run_in_worker( + { + err = s->ops->close(&s->ctx, fs); + if (err < 0) { + err = -errno; + } + }); + if (!err) { + total_open_fd--; + } + return err; +} + +int v9fs_co_fsync(V9fsPDU *pdu, V9fsFidState *fidp, int datasync) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_co_run_in_worker( + { + err = s->ops->fsync(&s->ctx, fidp->fid_type, &fidp->fs, datasync); + if (err < 0) { + err = -errno; + } + }); + return err; +} + +int v9fs_co_link(V9fsPDU *pdu, V9fsFidState *oldfid, + V9fsFidState *newdirfid, V9fsString *name) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->link(&s->ctx, &oldfid->path, + &newdirfid->path, name->data); + if (err < 0) { + err = -errno; + } + }); + v9fs_path_unlock(s); + return err; +} + +int v9fs_co_pwritev(V9fsPDU *pdu, V9fsFidState *fidp, + struct iovec *iov, int iovcnt, int64_t offset) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_co_run_in_worker( + { + err = s->ops->pwritev(&s->ctx, &fidp->fs, iov, iovcnt, offset); + if (err < 0) { + err = -errno; + } + }); + return err; +} + +int v9fs_co_preadv(V9fsPDU *pdu, V9fsFidState *fidp, + struct iovec *iov, int iovcnt, int64_t offset) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_co_run_in_worker( + { + err = s->ops->preadv(&s->ctx, &fidp->fs, iov, iovcnt, offset); + if (err < 0) { + err = -errno; + } + }); + return err; +} diff --git a/qemu/hw/9pfs/cofs.c b/qemu/hw/9pfs/cofs.c new file mode 100644 index 000000000..42ee614e2 --- /dev/null +++ b/qemu/hw/9pfs/cofs.c @@ -0,0 +1,364 @@ + +/* + * Virtio 9p backend + * + * Copyright IBM, Corp. 2011 + * + * Authors: + * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "fsdev/qemu-fsdev.h" +#include "qemu/thread.h" +#include "block/coroutine.h" +#include "virtio-9p-coth.h" + +static ssize_t __readlink(V9fsState *s, V9fsPath *path, V9fsString *buf) +{ + ssize_t len, maxlen = PATH_MAX; + + buf->data = g_malloc(PATH_MAX); + for(;;) { + len = s->ops->readlink(&s->ctx, path, buf->data, maxlen); + if (len < 0) { + g_free(buf->data); + buf->data = NULL; + buf->size = 0; + break; + } else if (len == maxlen) { + /* + * We dodn't have space to put the NULL or we have more + * to read. Increase the size and try again + */ + maxlen *= 2; + g_free(buf->data); + buf->data = g_malloc(maxlen); + continue; + } + /* + * Null terminate the readlink output + */ + buf->data[len] = '\0'; + buf->size = len; + break; + } + return len; +} + +int v9fs_co_readlink(V9fsPDU *pdu, V9fsPath *path, V9fsString *buf) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = __readlink(s, path, buf); + if (err < 0) { + err = -errno; + } + }); + v9fs_path_unlock(s); + return err; +} + +int v9fs_co_statfs(V9fsPDU *pdu, V9fsPath *path, struct statfs *stbuf) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->statfs(&s->ctx, path, stbuf); + if (err < 0) { + err = -errno; + } + }); + v9fs_path_unlock(s); + return err; +} + +int v9fs_co_chmod(V9fsPDU *pdu, V9fsPath *path, mode_t mode) +{ + int err; + FsCred cred; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + cred_init(&cred); + cred.fc_mode = mode; + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->chmod(&s->ctx, path, &cred); + if (err < 0) { + err = -errno; + } + }); + v9fs_path_unlock(s); + return err; +} + +int v9fs_co_utimensat(V9fsPDU *pdu, V9fsPath *path, + struct timespec times[2]) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->utimensat(&s->ctx, path, times); + if (err < 0) { + err = -errno; + } + }); + v9fs_path_unlock(s); + return err; +} + +int v9fs_co_chown(V9fsPDU *pdu, V9fsPath *path, uid_t uid, gid_t gid) +{ + int err; + FsCred cred; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + cred_init(&cred); + cred.fc_uid = uid; + cred.fc_gid = gid; + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->chown(&s->ctx, path, &cred); + if (err < 0) { + err = -errno; + } + }); + v9fs_path_unlock(s); + return err; +} + +int v9fs_co_truncate(V9fsPDU *pdu, V9fsPath *path, off_t size) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->truncate(&s->ctx, path, size); + if (err < 0) { + err = -errno; + } + }); + v9fs_path_unlock(s); + return err; +} + +int v9fs_co_mknod(V9fsPDU *pdu, V9fsFidState *fidp, V9fsString *name, uid_t uid, + gid_t gid, dev_t dev, mode_t mode, struct stat *stbuf) +{ + int err; + V9fsPath path; + FsCred cred; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + cred_init(&cred); + cred.fc_uid = uid; + cred.fc_gid = gid; + cred.fc_mode = mode; + cred.fc_rdev = dev; + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->mknod(&s->ctx, &fidp->path, name->data, &cred); + if (err < 0) { + err = -errno; + } else { + v9fs_path_init(&path); + err = v9fs_name_to_path(s, &fidp->path, name->data, &path); + if (!err) { + err = s->ops->lstat(&s->ctx, &path, stbuf); + if (err < 0) { + err = -errno; + } + } + v9fs_path_free(&path); + } + }); + v9fs_path_unlock(s); + return err; +} + +/* Only works with path name based fid */ +int v9fs_co_remove(V9fsPDU *pdu, V9fsPath *path) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->remove(&s->ctx, path->data); + if (err < 0) { + err = -errno; + } + }); + v9fs_path_unlock(s); + return err; +} + +int v9fs_co_unlinkat(V9fsPDU *pdu, V9fsPath *path, V9fsString *name, int flags) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->unlinkat(&s->ctx, path, name->data, flags); + if (err < 0) { + err = -errno; + } + }); + v9fs_path_unlock(s); + return err; +} + +/* Only work with path name based fid */ +int v9fs_co_rename(V9fsPDU *pdu, V9fsPath *oldpath, V9fsPath *newpath) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_co_run_in_worker( + { + err = s->ops->rename(&s->ctx, oldpath->data, newpath->data); + if (err < 0) { + err = -errno; + } + }); + return err; +} + +int v9fs_co_renameat(V9fsPDU *pdu, V9fsPath *olddirpath, V9fsString *oldname, + V9fsPath *newdirpath, V9fsString *newname) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_co_run_in_worker( + { + err = s->ops->renameat(&s->ctx, olddirpath, oldname->data, + newdirpath, newname->data); + if (err < 0) { + err = -errno; + } + }); + return err; +} + +int v9fs_co_symlink(V9fsPDU *pdu, V9fsFidState *dfidp, V9fsString *name, + const char *oldpath, gid_t gid, struct stat *stbuf) +{ + int err; + FsCred cred; + V9fsPath path; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + cred_init(&cred); + cred.fc_uid = dfidp->uid; + cred.fc_gid = gid; + cred.fc_mode = 0777; + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->symlink(&s->ctx, oldpath, &dfidp->path, + name->data, &cred); + if (err < 0) { + err = -errno; + } else { + v9fs_path_init(&path); + err = v9fs_name_to_path(s, &dfidp->path, name->data, &path); + if (!err) { + err = s->ops->lstat(&s->ctx, &path, stbuf); + if (err < 0) { + err = -errno; + } + } + v9fs_path_free(&path); + } + }); + v9fs_path_unlock(s); + return err; +} + +/* + * For path name based fid we don't block. So we can + * directly call the fs driver ops. + */ +int v9fs_co_name_to_path(V9fsPDU *pdu, V9fsPath *dirpath, + const char *name, V9fsPath *path) +{ + int err; + V9fsState *s = pdu->s; + + if (s->ctx.export_flags & V9FS_PATHNAME_FSCONTEXT) { + err = s->ops->name_to_path(&s->ctx, dirpath, name, path); + if (err < 0) { + err = -errno; + } + } else { + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_co_run_in_worker( + { + err = s->ops->name_to_path(&s->ctx, dirpath, name, path); + if (err < 0) { + err = -errno; + } + }); + } + return err; +} diff --git a/qemu/hw/9pfs/coxattr.c b/qemu/hw/9pfs/coxattr.c new file mode 100644 index 000000000..18ee08df0 --- /dev/null +++ b/qemu/hw/9pfs/coxattr.c @@ -0,0 +1,107 @@ + +/* + * Virtio 9p backend + * + * Copyright IBM, Corp. 2011 + * + * Authors: + * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "fsdev/qemu-fsdev.h" +#include "qemu/thread.h" +#include "block/coroutine.h" +#include "virtio-9p-coth.h" + +int v9fs_co_llistxattr(V9fsPDU *pdu, V9fsPath *path, void *value, size_t size) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->llistxattr(&s->ctx, path, value, size); + if (err < 0) { + err = -errno; + } + }); + v9fs_path_unlock(s); + return err; +} + +int v9fs_co_lgetxattr(V9fsPDU *pdu, V9fsPath *path, + V9fsString *xattr_name, + void *value, size_t size) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->lgetxattr(&s->ctx, path, + xattr_name->data, + value, size); + if (err < 0) { + err = -errno; + } + }); + v9fs_path_unlock(s); + return err; +} + +int v9fs_co_lsetxattr(V9fsPDU *pdu, V9fsPath *path, + V9fsString *xattr_name, void *value, + size_t size, int flags) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->lsetxattr(&s->ctx, path, + xattr_name->data, value, + size, flags); + if (err < 0) { + err = -errno; + } + }); + v9fs_path_unlock(s); + return err; +} + +int v9fs_co_lremovexattr(V9fsPDU *pdu, V9fsPath *path, + V9fsString *xattr_name) +{ + int err; + V9fsState *s = pdu->s; + + if (v9fs_request_cancelled(pdu)) { + return -EINTR; + } + v9fs_path_read_lock(s); + v9fs_co_run_in_worker( + { + err = s->ops->lremovexattr(&s->ctx, path, xattr_name->data); + if (err < 0) { + err = -errno; + } + }); + v9fs_path_unlock(s); + return err; +} diff --git a/qemu/hw/9pfs/virtio-9p-coth.c b/qemu/hw/9pfs/virtio-9p-coth.c new file mode 100644 index 000000000..8185c533c --- /dev/null +++ b/qemu/hw/9pfs/virtio-9p-coth.c @@ -0,0 +1,82 @@ +/* + * Virtio 9p backend + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Harsh Prateek Bora <harsh@linux.vnet.ibm.com> + * Venkateswararao Jujjuri(JV) <jvrao@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "fsdev/qemu-fsdev.h" +#include "qemu/thread.h" +#include "qemu/event_notifier.h" +#include "block/coroutine.h" +#include "virtio-9p-coth.h" + +/* v9fs glib thread pool */ +static V9fsThPool v9fs_pool; + +void co_run_in_worker_bh(void *opaque) +{ + Coroutine *co = opaque; + g_thread_pool_push(v9fs_pool.pool, co, NULL); +} + +static void v9fs_qemu_process_req_done(EventNotifier *e) +{ + Coroutine *co; + + event_notifier_test_and_clear(e); + + while ((co = g_async_queue_try_pop(v9fs_pool.completed)) != NULL) { + qemu_coroutine_enter(co, NULL); + } +} + +static void v9fs_thread_routine(gpointer data, gpointer user_data) +{ + Coroutine *co = data; + + qemu_coroutine_enter(co, NULL); + + g_async_queue_push(v9fs_pool.completed, co); + + event_notifier_set(&v9fs_pool.e); +} + +int v9fs_init_worker_threads(void) +{ + int ret = 0; + V9fsThPool *p = &v9fs_pool; + sigset_t set, oldset; + + sigfillset(&set); + /* Leave signal handling to the iothread. */ + pthread_sigmask(SIG_SETMASK, &set, &oldset); + + p->pool = g_thread_pool_new(v9fs_thread_routine, p, -1, FALSE, NULL); + if (!p->pool) { + ret = -1; + goto err_out; + } + p->completed = g_async_queue_new(); + if (!p->completed) { + /* + * We are going to terminate. + * So don't worry about cleanup + */ + ret = -1; + goto err_out; + } + event_notifier_init(&p->e, 0); + + event_notifier_set_handler(&p->e, v9fs_qemu_process_req_done); +err_out: + pthread_sigmask(SIG_SETMASK, &oldset, NULL); + return ret; +} diff --git a/qemu/hw/9pfs/virtio-9p-coth.h b/qemu/hw/9pfs/virtio-9p-coth.h new file mode 100644 index 000000000..4f51b250d --- /dev/null +++ b/qemu/hw/9pfs/virtio-9p-coth.h @@ -0,0 +1,107 @@ +/* + * Virtio 9p backend + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Harsh Prateek Bora <harsh@linux.vnet.ibm.com> + * Venkateswararao Jujjuri(JV) <jvrao@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#ifndef _QEMU_VIRTIO_9P_COTH_H +#define _QEMU_VIRTIO_9P_COTH_H + +#include "qemu/thread.h" +#include "block/coroutine.h" +#include "virtio-9p.h" +#include <glib.h> + +typedef struct V9fsThPool { + EventNotifier e; + + GThreadPool *pool; + GAsyncQueue *completed; +} V9fsThPool; + +/* + * we want to use bottom half because we want to make sure the below + * sequence of events. + * + * 1. Yield the coroutine in the QEMU thread. + * 2. Submit the coroutine to a worker thread. + * 3. Enter the coroutine in the worker thread. + * we cannot swap step 1 and 2, because that would imply worker thread + * can enter coroutine while step1 is still running + */ +#define v9fs_co_run_in_worker(code_block) \ + do { \ + QEMUBH *co_bh; \ + co_bh = qemu_bh_new(co_run_in_worker_bh, \ + qemu_coroutine_self()); \ + qemu_bh_schedule(co_bh); \ + /* \ + * yield in qemu thread and re-enter back \ + * in glib worker thread \ + */ \ + qemu_coroutine_yield(); \ + qemu_bh_delete(co_bh); \ + code_block; \ + /* re-enter back to qemu thread */ \ + qemu_coroutine_yield(); \ + } while (0) + +extern void co_run_in_worker_bh(void *); +extern int v9fs_init_worker_threads(void); +extern int v9fs_co_readlink(V9fsPDU *, V9fsPath *, V9fsString *); +extern int v9fs_co_readdir_r(V9fsPDU *, V9fsFidState *, + struct dirent *, struct dirent **result); +extern off_t v9fs_co_telldir(V9fsPDU *, V9fsFidState *); +extern void v9fs_co_seekdir(V9fsPDU *, V9fsFidState *, off_t); +extern void v9fs_co_rewinddir(V9fsPDU *, V9fsFidState *); +extern int v9fs_co_statfs(V9fsPDU *, V9fsPath *, struct statfs *); +extern int v9fs_co_lstat(V9fsPDU *, V9fsPath *, struct stat *); +extern int v9fs_co_chmod(V9fsPDU *, V9fsPath *, mode_t); +extern int v9fs_co_utimensat(V9fsPDU *, V9fsPath *, struct timespec [2]); +extern int v9fs_co_chown(V9fsPDU *, V9fsPath *, uid_t, gid_t); +extern int v9fs_co_truncate(V9fsPDU *, V9fsPath *, off_t); +extern int v9fs_co_llistxattr(V9fsPDU *, V9fsPath *, void *, size_t); +extern int v9fs_co_lgetxattr(V9fsPDU *, V9fsPath *, + V9fsString *, void *, size_t); +extern int v9fs_co_mknod(V9fsPDU *, V9fsFidState *, V9fsString *, uid_t, + gid_t, dev_t, mode_t, struct stat *); +extern int v9fs_co_mkdir(V9fsPDU *, V9fsFidState *, V9fsString *, + mode_t, uid_t, gid_t, struct stat *); +extern int v9fs_co_remove(V9fsPDU *, V9fsPath *); +extern int v9fs_co_rename(V9fsPDU *, V9fsPath *, V9fsPath *); +extern int v9fs_co_unlinkat(V9fsPDU *, V9fsPath *, V9fsString *, int flags); +extern int v9fs_co_renameat(V9fsPDU *, V9fsPath *, V9fsString *, + V9fsPath *, V9fsString *); +extern int v9fs_co_fstat(V9fsPDU *, V9fsFidState *, struct stat *); +extern int v9fs_co_opendir(V9fsPDU *, V9fsFidState *); +extern int v9fs_co_open(V9fsPDU *, V9fsFidState *, int); +extern int v9fs_co_open2(V9fsPDU *, V9fsFidState *, V9fsString *, + gid_t, int, int, struct stat *); +extern int v9fs_co_lsetxattr(V9fsPDU *, V9fsPath *, V9fsString *, + void *, size_t, int); +extern int v9fs_co_lremovexattr(V9fsPDU *, V9fsPath *, V9fsString *); +extern int v9fs_co_closedir(V9fsPDU *, V9fsFidOpenState *); +extern int v9fs_co_close(V9fsPDU *, V9fsFidOpenState *); +extern int v9fs_co_fsync(V9fsPDU *, V9fsFidState *, int); +extern int v9fs_co_symlink(V9fsPDU *, V9fsFidState *, V9fsString *, + const char *, gid_t, struct stat *); +extern int v9fs_co_link(V9fsPDU *, V9fsFidState *, + V9fsFidState *, V9fsString *); +extern int v9fs_co_pwritev(V9fsPDU *, V9fsFidState *, + struct iovec *, int, int64_t); +extern int v9fs_co_preadv(V9fsPDU *, V9fsFidState *, + struct iovec *, int, int64_t); +extern int v9fs_co_name_to_path(V9fsPDU *, V9fsPath *, + const char *, V9fsPath *); +extern int v9fs_co_st_gen(V9fsPDU *pdu, V9fsPath *path, mode_t, + V9fsStatDotl *v9stat); + +#endif diff --git a/qemu/hw/9pfs/virtio-9p-device.c b/qemu/hw/9pfs/virtio-9p-device.c new file mode 100644 index 000000000..93a407c45 --- /dev/null +++ b/qemu/hw/9pfs/virtio-9p-device.c @@ -0,0 +1,173 @@ +/* + * Virtio 9p backend + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "hw/virtio/virtio.h" +#include "hw/virtio/virtio-9p.h" +#include "hw/i386/pc.h" +#include "qemu/sockets.h" +#include "virtio-9p.h" +#include "fsdev/qemu-fsdev.h" +#include "virtio-9p-xattr.h" +#include "virtio-9p-coth.h" +#include "hw/virtio/virtio-access.h" + +static uint64_t virtio_9p_get_features(VirtIODevice *vdev, uint64_t features, + Error **errp) +{ + virtio_add_feature(&features, VIRTIO_9P_MOUNT_TAG); + return features; +} + +static void virtio_9p_get_config(VirtIODevice *vdev, uint8_t *config) +{ + int len; + struct virtio_9p_config *cfg; + V9fsState *s = VIRTIO_9P(vdev); + + len = strlen(s->tag); + cfg = g_malloc0(sizeof(struct virtio_9p_config) + len); + virtio_stw_p(vdev, &cfg->tag_len, len); + /* We don't copy the terminating null to config space */ + memcpy(cfg->tag, s->tag, len); + memcpy(config, cfg, s->config_size); + g_free(cfg); +} + +static void virtio_9p_device_realize(DeviceState *dev, Error **errp) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + V9fsState *s = VIRTIO_9P(dev); + int i, len; + struct stat stat; + FsDriverEntry *fse; + V9fsPath path; + + virtio_init(vdev, "virtio-9p", VIRTIO_ID_9P, + sizeof(struct virtio_9p_config) + MAX_TAG_LEN); + + /* initialize pdu allocator */ + QLIST_INIT(&s->free_list); + QLIST_INIT(&s->active_list); + for (i = 0; i < (MAX_REQ - 1); i++) { + QLIST_INSERT_HEAD(&s->free_list, &s->pdus[i], next); + } + + s->vq = virtio_add_queue(vdev, MAX_REQ, handle_9p_output); + + v9fs_path_init(&path); + + fse = get_fsdev_fsentry(s->fsconf.fsdev_id); + + if (!fse) { + /* We don't have a fsdev identified by fsdev_id */ + error_setg(errp, "Virtio-9p device couldn't find fsdev with the " + "id = %s", + s->fsconf.fsdev_id ? s->fsconf.fsdev_id : "NULL"); + goto out; + } + + if (!s->fsconf.tag) { + /* we haven't specified a mount_tag */ + error_setg(errp, "fsdev with id %s needs mount_tag arguments", + s->fsconf.fsdev_id); + goto out; + } + + s->ctx.export_flags = fse->export_flags; + s->ctx.fs_root = g_strdup(fse->path); + s->ctx.exops.get_st_gen = NULL; + len = strlen(s->fsconf.tag); + if (len > MAX_TAG_LEN - 1) { + error_setg(errp, "mount tag '%s' (%d bytes) is longer than " + "maximum (%d bytes)", s->fsconf.tag, len, MAX_TAG_LEN - 1); + goto out; + } + + s->tag = g_strdup(s->fsconf.tag); + s->ctx.uid = -1; + + s->ops = fse->ops; + s->config_size = sizeof(struct virtio_9p_config) + len; + s->fid_list = NULL; + qemu_co_rwlock_init(&s->rename_lock); + + if (s->ops->init(&s->ctx) < 0) { + error_setg(errp, "Virtio-9p Failed to initialize fs-driver with id:%s" + " and export path:%s", s->fsconf.fsdev_id, s->ctx.fs_root); + goto out; + } + if (v9fs_init_worker_threads() < 0) { + error_setg(errp, "worker thread initialization failed"); + goto out; + } + + /* + * Check details of export path, We need to use fs driver + * call back to do that. Since we are in the init path, we don't + * use co-routines here. + */ + if (s->ops->name_to_path(&s->ctx, NULL, "/", &path) < 0) { + error_setg(errp, + "error in converting name to path %s", strerror(errno)); + goto out; + } + if (s->ops->lstat(&s->ctx, &path, &stat)) { + error_setg(errp, "share path %s does not exist", fse->path); + goto out; + } else if (!S_ISDIR(stat.st_mode)) { + error_setg(errp, "share path %s is not a directory", fse->path); + goto out; + } + v9fs_path_free(&path); + + return; +out: + g_free(s->ctx.fs_root); + g_free(s->tag); + virtio_cleanup(vdev); + v9fs_path_free(&path); +} + +/* virtio-9p device */ + +static Property virtio_9p_properties[] = { + DEFINE_PROP_STRING("mount_tag", V9fsState, fsconf.tag), + DEFINE_PROP_STRING("fsdev", V9fsState, fsconf.fsdev_id), + DEFINE_PROP_END_OF_LIST(), +}; + +static void virtio_9p_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); + + dc->props = virtio_9p_properties; + set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); + vdc->realize = virtio_9p_device_realize; + vdc->get_features = virtio_9p_get_features; + vdc->get_config = virtio_9p_get_config; +} + +static const TypeInfo virtio_device_info = { + .name = TYPE_VIRTIO_9P, + .parent = TYPE_VIRTIO_DEVICE, + .instance_size = sizeof(V9fsState), + .class_init = virtio_9p_class_init, +}; + +static void virtio_9p_register_types(void) +{ + type_register_static(&virtio_device_info); +} + +type_init(virtio_9p_register_types) diff --git a/qemu/hw/9pfs/virtio-9p-handle.c b/qemu/hw/9pfs/virtio-9p-handle.c new file mode 100644 index 000000000..13eabb98a --- /dev/null +++ b/qemu/hw/9pfs/virtio-9p-handle.c @@ -0,0 +1,708 @@ +/* + * Virtio 9p handle callback + * + * Copyright IBM, Corp. 2011 + * + * Authors: + * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "hw/virtio/virtio.h" +#include "virtio-9p.h" +#include "virtio-9p-xattr.h" +#include <arpa/inet.h> +#include <pwd.h> +#include <grp.h> +#include <sys/socket.h> +#include <sys/un.h> +#include "qemu/xattr.h" +#include <unistd.h> +#include <linux/fs.h> +#ifdef CONFIG_LINUX_MAGIC_H +#include <linux/magic.h> +#endif +#include <sys/ioctl.h> + +#ifndef XFS_SUPER_MAGIC +#define XFS_SUPER_MAGIC 0x58465342 +#endif +#ifndef EXT2_SUPER_MAGIC +#define EXT2_SUPER_MAGIC 0xEF53 +#endif +#ifndef REISERFS_SUPER_MAGIC +#define REISERFS_SUPER_MAGIC 0x52654973 +#endif +#ifndef BTRFS_SUPER_MAGIC +#define BTRFS_SUPER_MAGIC 0x9123683E +#endif + +struct handle_data { + int mountfd; + int handle_bytes; +}; + +static inline int name_to_handle(int dirfd, const char *name, + struct file_handle *fh, int *mnt_id, int flags) +{ + return name_to_handle_at(dirfd, name, fh, mnt_id, flags); +} + +static inline int open_by_handle(int mountfd, const char *fh, int flags) +{ + return open_by_handle_at(mountfd, (struct file_handle *)fh, flags); +} + +static int handle_update_file_cred(int dirfd, const char *name, FsCred *credp) +{ + int fd, ret; + fd = openat(dirfd, name, O_NONBLOCK | O_NOFOLLOW); + if (fd < 0) { + return fd; + } + ret = fchownat(fd, "", credp->fc_uid, credp->fc_gid, AT_EMPTY_PATH); + if (ret < 0) { + goto err_out; + } + ret = fchmod(fd, credp->fc_mode & 07777); +err_out: + close(fd); + return ret; +} + + +static int handle_lstat(FsContext *fs_ctx, V9fsPath *fs_path, + struct stat *stbuf) +{ + int fd, ret; + struct handle_data *data = (struct handle_data *)fs_ctx->private; + + fd = open_by_handle(data->mountfd, fs_path->data, O_PATH); + if (fd < 0) { + return fd; + } + ret = fstatat(fd, "", stbuf, AT_EMPTY_PATH); + close(fd); + return ret; +} + +static ssize_t handle_readlink(FsContext *fs_ctx, V9fsPath *fs_path, + char *buf, size_t bufsz) +{ + int fd, ret; + struct handle_data *data = (struct handle_data *)fs_ctx->private; + + fd = open_by_handle(data->mountfd, fs_path->data, O_PATH); + if (fd < 0) { + return fd; + } + ret = readlinkat(fd, "", buf, bufsz); + close(fd); + return ret; +} + +static int handle_close(FsContext *ctx, V9fsFidOpenState *fs) +{ + return close(fs->fd); +} + +static int handle_closedir(FsContext *ctx, V9fsFidOpenState *fs) +{ + return closedir(fs->dir); +} + +static int handle_open(FsContext *ctx, V9fsPath *fs_path, + int flags, V9fsFidOpenState *fs) +{ + struct handle_data *data = (struct handle_data *)ctx->private; + + fs->fd = open_by_handle(data->mountfd, fs_path->data, flags); + return fs->fd; +} + +static int handle_opendir(FsContext *ctx, + V9fsPath *fs_path, V9fsFidOpenState *fs) +{ + int ret; + ret = handle_open(ctx, fs_path, O_DIRECTORY, fs); + if (ret < 0) { + return -1; + } + fs->dir = fdopendir(ret); + if (!fs->dir) { + return -1; + } + return 0; +} + +static void handle_rewinddir(FsContext *ctx, V9fsFidOpenState *fs) +{ + rewinddir(fs->dir); +} + +static off_t handle_telldir(FsContext *ctx, V9fsFidOpenState *fs) +{ + return telldir(fs->dir); +} + +static int handle_readdir_r(FsContext *ctx, V9fsFidOpenState *fs, + struct dirent *entry, + struct dirent **result) +{ + return readdir_r(fs->dir, entry, result); +} + +static void handle_seekdir(FsContext *ctx, V9fsFidOpenState *fs, off_t off) +{ + seekdir(fs->dir, off); +} + +static ssize_t handle_preadv(FsContext *ctx, V9fsFidOpenState *fs, + const struct iovec *iov, + int iovcnt, off_t offset) +{ +#ifdef CONFIG_PREADV + return preadv(fs->fd, iov, iovcnt, offset); +#else + int err = lseek(fs->fd, offset, SEEK_SET); + if (err == -1) { + return err; + } else { + return readv(fs->fd, iov, iovcnt); + } +#endif +} + +static ssize_t handle_pwritev(FsContext *ctx, V9fsFidOpenState *fs, + const struct iovec *iov, + int iovcnt, off_t offset) +{ + ssize_t ret; +#ifdef CONFIG_PREADV + ret = pwritev(fs->fd, iov, iovcnt, offset); +#else + int err = lseek(fs->fd, offset, SEEK_SET); + if (err == -1) { + return err; + } else { + ret = writev(fs->fd, iov, iovcnt); + } +#endif +#ifdef CONFIG_SYNC_FILE_RANGE + if (ret > 0 && ctx->export_flags & V9FS_IMMEDIATE_WRITEOUT) { + /* + * Initiate a writeback. This is not a data integrity sync. + * We want to ensure that we don't leave dirty pages in the cache + * after write when writeout=immediate is sepcified. + */ + sync_file_range(fs->fd, offset, ret, + SYNC_FILE_RANGE_WAIT_BEFORE | SYNC_FILE_RANGE_WRITE); + } +#endif + return ret; +} + +static int handle_chmod(FsContext *fs_ctx, V9fsPath *fs_path, FsCred *credp) +{ + int fd, ret; + struct handle_data *data = (struct handle_data *)fs_ctx->private; + + fd = open_by_handle(data->mountfd, fs_path->data, O_NONBLOCK); + if (fd < 0) { + return fd; + } + ret = fchmod(fd, credp->fc_mode); + close(fd); + return ret; +} + +static int handle_mknod(FsContext *fs_ctx, V9fsPath *dir_path, + const char *name, FsCred *credp) +{ + int dirfd, ret; + struct handle_data *data = (struct handle_data *)fs_ctx->private; + + dirfd = open_by_handle(data->mountfd, dir_path->data, O_PATH); + if (dirfd < 0) { + return dirfd; + } + ret = mknodat(dirfd, name, credp->fc_mode, credp->fc_rdev); + if (!ret) { + ret = handle_update_file_cred(dirfd, name, credp); + } + close(dirfd); + return ret; +} + +static int handle_mkdir(FsContext *fs_ctx, V9fsPath *dir_path, + const char *name, FsCred *credp) +{ + int dirfd, ret; + struct handle_data *data = (struct handle_data *)fs_ctx->private; + + dirfd = open_by_handle(data->mountfd, dir_path->data, O_PATH); + if (dirfd < 0) { + return dirfd; + } + ret = mkdirat(dirfd, name, credp->fc_mode); + if (!ret) { + ret = handle_update_file_cred(dirfd, name, credp); + } + close(dirfd); + return ret; +} + +static int handle_fstat(FsContext *fs_ctx, int fid_type, + V9fsFidOpenState *fs, struct stat *stbuf) +{ + int fd; + + if (fid_type == P9_FID_DIR) { + fd = dirfd(fs->dir); + } else { + fd = fs->fd; + } + return fstat(fd, stbuf); +} + +static int handle_open2(FsContext *fs_ctx, V9fsPath *dir_path, const char *name, + int flags, FsCred *credp, V9fsFidOpenState *fs) +{ + int ret; + int dirfd, fd; + struct handle_data *data = (struct handle_data *)fs_ctx->private; + + dirfd = open_by_handle(data->mountfd, dir_path->data, O_PATH); + if (dirfd < 0) { + return dirfd; + } + fd = openat(dirfd, name, flags | O_NOFOLLOW, credp->fc_mode); + if (fd >= 0) { + ret = handle_update_file_cred(dirfd, name, credp); + if (ret < 0) { + close(fd); + fd = ret; + } else { + fs->fd = fd; + } + } + close(dirfd); + return fd; +} + + +static int handle_symlink(FsContext *fs_ctx, const char *oldpath, + V9fsPath *dir_path, const char *name, FsCred *credp) +{ + int fd, dirfd, ret; + struct handle_data *data = (struct handle_data *)fs_ctx->private; + + dirfd = open_by_handle(data->mountfd, dir_path->data, O_PATH); + if (dirfd < 0) { + return dirfd; + } + ret = symlinkat(oldpath, dirfd, name); + if (!ret) { + fd = openat(dirfd, name, O_PATH | O_NOFOLLOW); + if (fd < 0) { + ret = fd; + goto err_out; + } + ret = fchownat(fd, "", credp->fc_uid, credp->fc_gid, AT_EMPTY_PATH); + close(fd); + } +err_out: + close(dirfd); + return ret; +} + +static int handle_link(FsContext *ctx, V9fsPath *oldpath, + V9fsPath *dirpath, const char *name) +{ + int oldfd, newdirfd, ret; + struct handle_data *data = (struct handle_data *)ctx->private; + + oldfd = open_by_handle(data->mountfd, oldpath->data, O_PATH); + if (oldfd < 0) { + return oldfd; + } + newdirfd = open_by_handle(data->mountfd, dirpath->data, O_PATH); + if (newdirfd < 0) { + close(oldfd); + return newdirfd; + } + ret = linkat(oldfd, "", newdirfd, name, AT_EMPTY_PATH); + close(newdirfd); + close(oldfd); + return ret; +} + +static int handle_truncate(FsContext *ctx, V9fsPath *fs_path, off_t size) +{ + int fd, ret; + struct handle_data *data = (struct handle_data *)ctx->private; + + fd = open_by_handle(data->mountfd, fs_path->data, O_NONBLOCK | O_WRONLY); + if (fd < 0) { + return fd; + } + ret = ftruncate(fd, size); + close(fd); + return ret; +} + +static int handle_rename(FsContext *ctx, const char *oldpath, + const char *newpath) +{ + errno = EOPNOTSUPP; + return -1; +} + +static int handle_chown(FsContext *fs_ctx, V9fsPath *fs_path, FsCred *credp) +{ + int fd, ret; + struct handle_data *data = (struct handle_data *)fs_ctx->private; + + fd = open_by_handle(data->mountfd, fs_path->data, O_PATH); + if (fd < 0) { + return fd; + } + ret = fchownat(fd, "", credp->fc_uid, credp->fc_gid, AT_EMPTY_PATH); + close(fd); + return ret; +} + +static int handle_utimensat(FsContext *ctx, V9fsPath *fs_path, + const struct timespec *buf) +{ + int ret; +#ifdef CONFIG_UTIMENSAT + int fd; + struct handle_data *data = (struct handle_data *)ctx->private; + + fd = open_by_handle(data->mountfd, fs_path->data, O_NONBLOCK); + if (fd < 0) { + return fd; + } + ret = futimens(fd, buf); + close(fd); +#else + ret = -1; + errno = ENOSYS; +#endif + return ret; +} + +static int handle_remove(FsContext *ctx, const char *path) +{ + errno = EOPNOTSUPP; + return -1; +} + +static int handle_fsync(FsContext *ctx, int fid_type, + V9fsFidOpenState *fs, int datasync) +{ + int fd; + + if (fid_type == P9_FID_DIR) { + fd = dirfd(fs->dir); + } else { + fd = fs->fd; + } + + if (datasync) { + return qemu_fdatasync(fd); + } else { + return fsync(fd); + } +} + +static int handle_statfs(FsContext *ctx, V9fsPath *fs_path, + struct statfs *stbuf) +{ + int fd, ret; + struct handle_data *data = (struct handle_data *)ctx->private; + + fd = open_by_handle(data->mountfd, fs_path->data, O_NONBLOCK); + if (fd < 0) { + return fd; + } + ret = fstatfs(fd, stbuf); + close(fd); + return ret; +} + +static ssize_t handle_lgetxattr(FsContext *ctx, V9fsPath *fs_path, + const char *name, void *value, size_t size) +{ + int fd, ret; + struct handle_data *data = (struct handle_data *)ctx->private; + + fd = open_by_handle(data->mountfd, fs_path->data, O_NONBLOCK); + if (fd < 0) { + return fd; + } + ret = fgetxattr(fd, name, value, size); + close(fd); + return ret; +} + +static ssize_t handle_llistxattr(FsContext *ctx, V9fsPath *fs_path, + void *value, size_t size) +{ + int fd, ret; + struct handle_data *data = (struct handle_data *)ctx->private; + + fd = open_by_handle(data->mountfd, fs_path->data, O_NONBLOCK); + if (fd < 0) { + return fd; + } + ret = flistxattr(fd, value, size); + close(fd); + return ret; +} + +static int handle_lsetxattr(FsContext *ctx, V9fsPath *fs_path, const char *name, + void *value, size_t size, int flags) +{ + int fd, ret; + struct handle_data *data = (struct handle_data *)ctx->private; + + fd = open_by_handle(data->mountfd, fs_path->data, O_NONBLOCK); + if (fd < 0) { + return fd; + } + ret = fsetxattr(fd, name, value, size, flags); + close(fd); + return ret; +} + +static int handle_lremovexattr(FsContext *ctx, V9fsPath *fs_path, + const char *name) +{ + int fd, ret; + struct handle_data *data = (struct handle_data *)ctx->private; + + fd = open_by_handle(data->mountfd, fs_path->data, O_NONBLOCK); + if (fd < 0) { + return fd; + } + ret = fremovexattr(fd, name); + close(fd); + return ret; +} + +static int handle_name_to_path(FsContext *ctx, V9fsPath *dir_path, + const char *name, V9fsPath *target) +{ + char *buffer; + struct file_handle *fh; + int dirfd, ret, mnt_id; + struct handle_data *data = (struct handle_data *)ctx->private; + + /* "." and ".." are not allowed */ + if (!strcmp(name, ".") || !strcmp(name, "..")) { + errno = EINVAL; + return -1; + + } + if (dir_path) { + dirfd = open_by_handle(data->mountfd, dir_path->data, O_PATH); + } else { + /* relative to export root */ + buffer = rpath(ctx, "."); + dirfd = open(buffer, O_DIRECTORY); + g_free(buffer); + } + if (dirfd < 0) { + return dirfd; + } + fh = g_malloc(sizeof(struct file_handle) + data->handle_bytes); + fh->handle_bytes = data->handle_bytes; + /* add a "./" at the beginning of the path */ + buffer = g_strdup_printf("./%s", name); + /* flag = 0 imply don't follow symlink */ + ret = name_to_handle(dirfd, buffer, fh, &mnt_id, 0); + if (!ret) { + target->data = (char *)fh; + target->size = sizeof(struct file_handle) + data->handle_bytes; + } else { + g_free(fh); + } + close(dirfd); + g_free(buffer); + return ret; +} + +static int handle_renameat(FsContext *ctx, V9fsPath *olddir, + const char *old_name, V9fsPath *newdir, + const char *new_name) +{ + int olddirfd, newdirfd, ret; + struct handle_data *data = (struct handle_data *)ctx->private; + + olddirfd = open_by_handle(data->mountfd, olddir->data, O_PATH); + if (olddirfd < 0) { + return olddirfd; + } + newdirfd = open_by_handle(data->mountfd, newdir->data, O_PATH); + if (newdirfd < 0) { + close(olddirfd); + return newdirfd; + } + ret = renameat(olddirfd, old_name, newdirfd, new_name); + close(newdirfd); + close(olddirfd); + return ret; +} + +static int handle_unlinkat(FsContext *ctx, V9fsPath *dir, + const char *name, int flags) +{ + int dirfd, ret; + struct handle_data *data = (struct handle_data *)ctx->private; + int rflags; + + dirfd = open_by_handle(data->mountfd, dir->data, O_PATH); + if (dirfd < 0) { + return dirfd; + } + + rflags = 0; + if (flags & P9_DOTL_AT_REMOVEDIR) { + rflags |= AT_REMOVEDIR; + } + + ret = unlinkat(dirfd, name, rflags); + + close(dirfd); + return ret; +} + +static int handle_ioc_getversion(FsContext *ctx, V9fsPath *path, + mode_t st_mode, uint64_t *st_gen) +{ +#ifdef FS_IOC_GETVERSION + int err; + V9fsFidOpenState fid_open; + + /* + * Do not try to open special files like device nodes, fifos etc + * We can get fd for regular files and directories only + */ + if (!S_ISREG(st_mode) && !S_ISDIR(st_mode)) { + errno = ENOTTY; + return -1; + } + err = handle_open(ctx, path, O_RDONLY, &fid_open); + if (err < 0) { + return err; + } + err = ioctl(fid_open.fd, FS_IOC_GETVERSION, st_gen); + handle_close(ctx, &fid_open); + return err; +#else + errno = ENOTTY; + return -1; +#endif +} + +static int handle_init(FsContext *ctx) +{ + int ret, mnt_id; + struct statfs stbuf; + struct file_handle fh; + struct handle_data *data = g_malloc(sizeof(struct handle_data)); + + data->mountfd = open(ctx->fs_root, O_DIRECTORY); + if (data->mountfd < 0) { + ret = data->mountfd; + goto err_out; + } + ret = statfs(ctx->fs_root, &stbuf); + if (!ret) { + switch (stbuf.f_type) { + case EXT2_SUPER_MAGIC: + case BTRFS_SUPER_MAGIC: + case REISERFS_SUPER_MAGIC: + case XFS_SUPER_MAGIC: + ctx->exops.get_st_gen = handle_ioc_getversion; + break; + } + } + memset(&fh, 0, sizeof(struct file_handle)); + ret = name_to_handle(data->mountfd, ".", &fh, &mnt_id, 0); + if (ret && errno == EOVERFLOW) { + data->handle_bytes = fh.handle_bytes; + ctx->private = data; + ret = 0; + goto out; + } + /* we got 0 byte handle ? */ + ret = -1; + close(data->mountfd); +err_out: + g_free(data); +out: + return ret; +} + +static int handle_parse_opts(QemuOpts *opts, struct FsDriverEntry *fse) +{ + const char *sec_model = qemu_opt_get(opts, "security_model"); + const char *path = qemu_opt_get(opts, "path"); + + if (sec_model) { + fprintf(stderr, "Invalid argument security_model specified with handle fsdriver\n"); + return -1; + } + + if (!path) { + fprintf(stderr, "fsdev: No path specified.\n"); + return -1; + } + fse->path = g_strdup(path); + return 0; + +} + +FileOperations handle_ops = { + .parse_opts = handle_parse_opts, + .init = handle_init, + .lstat = handle_lstat, + .readlink = handle_readlink, + .close = handle_close, + .closedir = handle_closedir, + .open = handle_open, + .opendir = handle_opendir, + .rewinddir = handle_rewinddir, + .telldir = handle_telldir, + .readdir_r = handle_readdir_r, + .seekdir = handle_seekdir, + .preadv = handle_preadv, + .pwritev = handle_pwritev, + .chmod = handle_chmod, + .mknod = handle_mknod, + .mkdir = handle_mkdir, + .fstat = handle_fstat, + .open2 = handle_open2, + .symlink = handle_symlink, + .link = handle_link, + .truncate = handle_truncate, + .rename = handle_rename, + .chown = handle_chown, + .utimensat = handle_utimensat, + .remove = handle_remove, + .fsync = handle_fsync, + .statfs = handle_statfs, + .lgetxattr = handle_lgetxattr, + .llistxattr = handle_llistxattr, + .lsetxattr = handle_lsetxattr, + .lremovexattr = handle_lremovexattr, + .name_to_path = handle_name_to_path, + .renameat = handle_renameat, + .unlinkat = handle_unlinkat, +}; diff --git a/qemu/hw/9pfs/virtio-9p-local.c b/qemu/hw/9pfs/virtio-9p-local.c new file mode 100644 index 000000000..f1f2e2573 --- /dev/null +++ b/qemu/hw/9pfs/virtio-9p-local.c @@ -0,0 +1,1280 @@ +/* + * Virtio 9p Posix callback + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "hw/virtio/virtio.h" +#include "virtio-9p.h" +#include "virtio-9p-xattr.h" +#include "fsdev/qemu-fsdev.h" /* local_ops */ +#include <arpa/inet.h> +#include <pwd.h> +#include <grp.h> +#include <sys/socket.h> +#include <sys/un.h> +#include "qemu/xattr.h" +#include <libgen.h> +#include <linux/fs.h> +#ifdef CONFIG_LINUX_MAGIC_H +#include <linux/magic.h> +#endif +#include <sys/ioctl.h> + +#ifndef XFS_SUPER_MAGIC +#define XFS_SUPER_MAGIC 0x58465342 +#endif +#ifndef EXT2_SUPER_MAGIC +#define EXT2_SUPER_MAGIC 0xEF53 +#endif +#ifndef REISERFS_SUPER_MAGIC +#define REISERFS_SUPER_MAGIC 0x52654973 +#endif +#ifndef BTRFS_SUPER_MAGIC +#define BTRFS_SUPER_MAGIC 0x9123683E +#endif + +#define VIRTFS_META_DIR ".virtfs_metadata" + +static char *local_mapped_attr_path(FsContext *ctx, const char *path) +{ + int dirlen; + const char *name = strrchr(path, '/'); + if (name) { + dirlen = name - path; + ++name; + } else { + name = path; + dirlen = 0; + } + return g_strdup_printf("%s/%.*s/%s/%s", ctx->fs_root, + dirlen, path, VIRTFS_META_DIR, name); +} + +static FILE *local_fopen(const char *path, const char *mode) +{ + int fd, o_mode = 0; + FILE *fp; + int flags = O_NOFOLLOW; + /* + * only supports two modes + */ + if (mode[0] == 'r') { + flags |= O_RDONLY; + } else if (mode[0] == 'w') { + flags |= O_WRONLY | O_TRUNC | O_CREAT; + o_mode = S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH; + } else { + return NULL; + } + fd = open(path, flags, o_mode); + if (fd == -1) { + return NULL; + } + fp = fdopen(fd, mode); + if (!fp) { + close(fd); + } + return fp; +} + +#define ATTR_MAX 100 +static void local_mapped_file_attr(FsContext *ctx, const char *path, + struct stat *stbuf) +{ + FILE *fp; + char buf[ATTR_MAX]; + char *attr_path; + + attr_path = local_mapped_attr_path(ctx, path); + fp = local_fopen(attr_path, "r"); + g_free(attr_path); + if (!fp) { + return; + } + memset(buf, 0, ATTR_MAX); + while (fgets(buf, ATTR_MAX, fp)) { + if (!strncmp(buf, "virtfs.uid", 10)) { + stbuf->st_uid = atoi(buf+11); + } else if (!strncmp(buf, "virtfs.gid", 10)) { + stbuf->st_gid = atoi(buf+11); + } else if (!strncmp(buf, "virtfs.mode", 11)) { + stbuf->st_mode = atoi(buf+12); + } else if (!strncmp(buf, "virtfs.rdev", 11)) { + stbuf->st_rdev = atoi(buf+12); + } + memset(buf, 0, ATTR_MAX); + } + fclose(fp); +} + +static int local_lstat(FsContext *fs_ctx, V9fsPath *fs_path, struct stat *stbuf) +{ + int err; + char *buffer; + char *path = fs_path->data; + + buffer = rpath(fs_ctx, path); + err = lstat(buffer, stbuf); + if (err) { + goto err_out; + } + if (fs_ctx->export_flags & V9FS_SM_MAPPED) { + /* Actual credentials are part of extended attrs */ + uid_t tmp_uid; + gid_t tmp_gid; + mode_t tmp_mode; + dev_t tmp_dev; + if (getxattr(buffer, "user.virtfs.uid", &tmp_uid, sizeof(uid_t)) > 0) { + stbuf->st_uid = le32_to_cpu(tmp_uid); + } + if (getxattr(buffer, "user.virtfs.gid", &tmp_gid, sizeof(gid_t)) > 0) { + stbuf->st_gid = le32_to_cpu(tmp_gid); + } + if (getxattr(buffer, "user.virtfs.mode", + &tmp_mode, sizeof(mode_t)) > 0) { + stbuf->st_mode = le32_to_cpu(tmp_mode); + } + if (getxattr(buffer, "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) { + local_mapped_file_attr(fs_ctx, path, stbuf); + } + +err_out: + g_free(buffer); + return err; +} + +static int local_create_mapped_attr_dir(FsContext *ctx, const char *path) +{ + int err; + char *attr_dir; + char *tmp_path = g_strdup(path); + + attr_dir = g_strdup_printf("%s/%s/%s", + ctx->fs_root, dirname(tmp_path), VIRTFS_META_DIR); + + err = mkdir(attr_dir, 0700); + if (err < 0 && errno == EEXIST) { + err = 0; + } + g_free(attr_dir); + g_free(tmp_path); + return err; +} + +static int local_set_mapped_file_attr(FsContext *ctx, + const char *path, FsCred *credp) +{ + FILE *fp; + int ret = 0; + char buf[ATTR_MAX]; + char *attr_path; + int uid = -1, gid = -1, mode = -1, rdev = -1; + + attr_path = local_mapped_attr_path(ctx, path); + fp = local_fopen(attr_path, "r"); + if (!fp) { + goto create_map_file; + } + memset(buf, 0, ATTR_MAX); + while (fgets(buf, ATTR_MAX, fp)) { + if (!strncmp(buf, "virtfs.uid", 10)) { + uid = atoi(buf+11); + } else if (!strncmp(buf, "virtfs.gid", 10)) { + gid = atoi(buf+11); + } else if (!strncmp(buf, "virtfs.mode", 11)) { + mode = atoi(buf+12); + } else if (!strncmp(buf, "virtfs.rdev", 11)) { + rdev = atoi(buf+12); + } + memset(buf, 0, ATTR_MAX); + } + fclose(fp); + goto update_map_file; + +create_map_file: + ret = local_create_mapped_attr_dir(ctx, path); + if (ret < 0) { + goto err_out; + } + +update_map_file: + fp = local_fopen(attr_path, "w"); + if (!fp) { + ret = -1; + goto err_out; + } + + if (credp->fc_uid != -1) { + uid = credp->fc_uid; + } + if (credp->fc_gid != -1) { + gid = credp->fc_gid; + } + if (credp->fc_mode != -1) { + mode = credp->fc_mode; + } + if (credp->fc_rdev != -1) { + rdev = credp->fc_rdev; + } + + + if (uid != -1) { + fprintf(fp, "virtfs.uid=%d\n", uid); + } + if (gid != -1) { + fprintf(fp, "virtfs.gid=%d\n", gid); + } + if (mode != -1) { + fprintf(fp, "virtfs.mode=%d\n", mode); + } + if (rdev != -1) { + fprintf(fp, "virtfs.rdev=%d\n", rdev); + } + fclose(fp); + +err_out: + g_free(attr_path); + return ret; +} + +static int local_set_xattr(const char *path, FsCred *credp) +{ + int err; + + if (credp->fc_uid != -1) { + uint32_t tmp_uid = cpu_to_le32(credp->fc_uid); + err = setxattr(path, "user.virtfs.uid", &tmp_uid, sizeof(uid_t), 0); + if (err) { + return err; + } + } + if (credp->fc_gid != -1) { + uint32_t tmp_gid = cpu_to_le32(credp->fc_gid); + err = setxattr(path, "user.virtfs.gid", &tmp_gid, sizeof(gid_t), 0); + if (err) { + return err; + } + } + if (credp->fc_mode != -1) { + uint32_t tmp_mode = cpu_to_le32(credp->fc_mode); + err = setxattr(path, "user.virtfs.mode", &tmp_mode, sizeof(mode_t), 0); + if (err) { + return err; + } + } + if (credp->fc_rdev != -1) { + uint64_t tmp_rdev = cpu_to_le64(credp->fc_rdev); + err = setxattr(path, "user.virtfs.rdev", &tmp_rdev, sizeof(dev_t), 0); + if (err) { + return err; + } + } + return 0; +} + +static int local_post_create_passthrough(FsContext *fs_ctx, const char *path, + FsCred *credp) +{ + char *buffer; + + buffer = rpath(fs_ctx, path); + if (lchown(buffer, credp->fc_uid, credp->fc_gid) < 0) { + /* + * If we fail to change ownership and if we are + * using security model none. Ignore the error + */ + if ((fs_ctx->export_flags & V9FS_SEC_MASK) != V9FS_SM_NONE) { + goto err; + } + } + + if (chmod(buffer, credp->fc_mode & 07777) < 0) { + goto err; + } + + g_free(buffer); + return 0; +err: + g_free(buffer); + return -1; +} + +static ssize_t local_readlink(FsContext *fs_ctx, V9fsPath *fs_path, + char *buf, size_t bufsz) +{ + ssize_t tsize = -1; + char *buffer; + char *path = fs_path->data; + + if ((fs_ctx->export_flags & V9FS_SM_MAPPED) || + (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE)) { + int fd; + buffer = rpath(fs_ctx, path); + fd = open(buffer, O_RDONLY | O_NOFOLLOW); + g_free(buffer); + if (fd == -1) { + return -1; + } + do { + tsize = read(fd, (void *)buf, bufsz); + } while (tsize == -1 && errno == EINTR); + close(fd); + } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) || + (fs_ctx->export_flags & V9FS_SM_NONE)) { + buffer = rpath(fs_ctx, path); + tsize = readlink(buffer, buf, bufsz); + g_free(buffer); + } + return tsize; +} + +static int local_close(FsContext *ctx, V9fsFidOpenState *fs) +{ + return close(fs->fd); +} + +static int local_closedir(FsContext *ctx, V9fsFidOpenState *fs) +{ + return closedir(fs->dir); +} + +static int local_open(FsContext *ctx, V9fsPath *fs_path, + int flags, V9fsFidOpenState *fs) +{ + char *buffer; + char *path = fs_path->data; + + buffer = rpath(ctx, path); + fs->fd = open(buffer, flags | O_NOFOLLOW); + g_free(buffer); + return fs->fd; +} + +static int local_opendir(FsContext *ctx, + V9fsPath *fs_path, V9fsFidOpenState *fs) +{ + char *buffer; + char *path = fs_path->data; + + buffer = rpath(ctx, path); + fs->dir = opendir(buffer); + g_free(buffer); + if (!fs->dir) { + return -1; + } + return 0; +} + +static void local_rewinddir(FsContext *ctx, V9fsFidOpenState *fs) +{ + rewinddir(fs->dir); +} + +static off_t local_telldir(FsContext *ctx, V9fsFidOpenState *fs) +{ + return telldir(fs->dir); +} + +static int local_readdir_r(FsContext *ctx, V9fsFidOpenState *fs, + struct dirent *entry, + struct dirent **result) +{ + int ret; + +again: + ret = readdir_r(fs->dir, entry, result); + if (ctx->export_flags & V9FS_SM_MAPPED) { + entry->d_type = DT_UNKNOWN; + } else if (ctx->export_flags & V9FS_SM_MAPPED_FILE) { + if (!ret && *result != NULL && + !strcmp(entry->d_name, VIRTFS_META_DIR)) { + /* skp the meta data directory */ + goto again; + } + entry->d_type = DT_UNKNOWN; + } + return ret; +} + +static void local_seekdir(FsContext *ctx, V9fsFidOpenState *fs, off_t off) +{ + seekdir(fs->dir, off); +} + +static ssize_t local_preadv(FsContext *ctx, V9fsFidOpenState *fs, + const struct iovec *iov, + int iovcnt, off_t offset) +{ +#ifdef CONFIG_PREADV + return preadv(fs->fd, iov, iovcnt, offset); +#else + int err = lseek(fs->fd, offset, SEEK_SET); + if (err == -1) { + return err; + } else { + return readv(fs->fd, iov, iovcnt); + } +#endif +} + +static ssize_t local_pwritev(FsContext *ctx, V9fsFidOpenState *fs, + const struct iovec *iov, + int iovcnt, off_t offset) +{ + ssize_t ret +; +#ifdef CONFIG_PREADV + ret = pwritev(fs->fd, iov, iovcnt, offset); +#else + int err = lseek(fs->fd, offset, SEEK_SET); + if (err == -1) { + return err; + } else { + ret = writev(fs->fd, iov, iovcnt); + } +#endif +#ifdef CONFIG_SYNC_FILE_RANGE + if (ret > 0 && ctx->export_flags & V9FS_IMMEDIATE_WRITEOUT) { + /* + * Initiate a writeback. This is not a data integrity sync. + * We want to ensure that we don't leave dirty pages in the cache + * after write when writeout=immediate is sepcified. + */ + sync_file_range(fs->fd, offset, ret, + SYNC_FILE_RANGE_WAIT_BEFORE | SYNC_FILE_RANGE_WRITE); + } +#endif + return ret; +} + +static int local_chmod(FsContext *fs_ctx, V9fsPath *fs_path, FsCred *credp) +{ + char *buffer; + int ret = -1; + char *path = fs_path->data; + + if (fs_ctx->export_flags & V9FS_SM_MAPPED) { + buffer = rpath(fs_ctx, path); + ret = local_set_xattr(buffer, credp); + g_free(buffer); + } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) { + return local_set_mapped_file_attr(fs_ctx, path, credp); + } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) || + (fs_ctx->export_flags & V9FS_SM_NONE)) { + buffer = rpath(fs_ctx, path); + ret = chmod(buffer, credp->fc_mode); + g_free(buffer); + } + return ret; +} + +static int local_mknod(FsContext *fs_ctx, V9fsPath *dir_path, + const char *name, FsCred *credp) +{ + char *path; + int err = -1; + int serrno = 0; + V9fsString fullname; + char *buffer = NULL; + + v9fs_string_init(&fullname); + v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name); + path = fullname.data; + + /* Determine the security model */ + if (fs_ctx->export_flags & V9FS_SM_MAPPED) { + buffer = rpath(fs_ctx, path); + err = mknod(buffer, SM_LOCAL_MODE_BITS|S_IFREG, 0); + if (err == -1) { + goto out; + } + err = local_set_xattr(buffer, credp); + if (err == -1) { + serrno = errno; + goto err_end; + } + } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) { + + buffer = rpath(fs_ctx, path); + err = mknod(buffer, SM_LOCAL_MODE_BITS|S_IFREG, 0); + if (err == -1) { + goto out; + } + err = local_set_mapped_file_attr(fs_ctx, path, credp); + if (err == -1) { + serrno = errno; + goto err_end; + } + } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) || + (fs_ctx->export_flags & V9FS_SM_NONE)) { + buffer = rpath(fs_ctx, path); + err = mknod(buffer, credp->fc_mode, credp->fc_rdev); + if (err == -1) { + goto out; + } + err = local_post_create_passthrough(fs_ctx, path, credp); + if (err == -1) { + serrno = errno; + goto err_end; + } + } + goto out; + +err_end: + remove(buffer); + errno = serrno; +out: + g_free(buffer); + v9fs_string_free(&fullname); + return err; +} + +static int local_mkdir(FsContext *fs_ctx, V9fsPath *dir_path, + const char *name, FsCred *credp) +{ + char *path; + int err = -1; + int serrno = 0; + V9fsString fullname; + char *buffer = NULL; + + v9fs_string_init(&fullname); + v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name); + path = fullname.data; + + /* Determine the security model */ + if (fs_ctx->export_flags & V9FS_SM_MAPPED) { + buffer = rpath(fs_ctx, path); + err = mkdir(buffer, SM_LOCAL_DIR_MODE_BITS); + if (err == -1) { + goto out; + } + credp->fc_mode = credp->fc_mode|S_IFDIR; + err = local_set_xattr(buffer, credp); + if (err == -1) { + serrno = errno; + goto err_end; + } + } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) { + buffer = rpath(fs_ctx, path); + err = mkdir(buffer, SM_LOCAL_DIR_MODE_BITS); + if (err == -1) { + goto out; + } + credp->fc_mode = credp->fc_mode|S_IFDIR; + err = local_set_mapped_file_attr(fs_ctx, path, credp); + if (err == -1) { + serrno = errno; + goto err_end; + } + } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) || + (fs_ctx->export_flags & V9FS_SM_NONE)) { + buffer = rpath(fs_ctx, path); + err = mkdir(buffer, credp->fc_mode); + if (err == -1) { + goto out; + } + err = local_post_create_passthrough(fs_ctx, path, credp); + if (err == -1) { + serrno = errno; + goto err_end; + } + } + goto out; + +err_end: + remove(buffer); + errno = serrno; +out: + g_free(buffer); + v9fs_string_free(&fullname); + return err; +} + +static int local_fstat(FsContext *fs_ctx, int fid_type, + V9fsFidOpenState *fs, struct stat *stbuf) +{ + int err, fd; + + if (fid_type == P9_FID_DIR) { + fd = dirfd(fs->dir); + } else { + fd = fs->fd; + } + + err = fstat(fd, stbuf); + if (err) { + return err; + } + if (fs_ctx->export_flags & V9FS_SM_MAPPED) { + /* Actual credentials are part of extended attrs */ + uid_t tmp_uid; + gid_t tmp_gid; + mode_t tmp_mode; + dev_t tmp_dev; + + if (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) { + stbuf->st_gid = le32_to_cpu(tmp_gid); + } + if (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) { + stbuf->st_rdev = le64_to_cpu(tmp_dev); + } + } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) { + errno = EOPNOTSUPP; + return -1; + } + return err; +} + +static int local_open2(FsContext *fs_ctx, V9fsPath *dir_path, const char *name, + int flags, FsCred *credp, V9fsFidOpenState *fs) +{ + char *path; + int fd = -1; + int err = -1; + int serrno = 0; + V9fsString fullname; + char *buffer = NULL; + + /* + * Mark all the open to not follow symlinks + */ + flags |= O_NOFOLLOW; + + v9fs_string_init(&fullname); + v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name); + path = fullname.data; + + /* Determine the security model */ + if (fs_ctx->export_flags & V9FS_SM_MAPPED) { + buffer = rpath(fs_ctx, path); + fd = open(buffer, flags, SM_LOCAL_MODE_BITS); + if (fd == -1) { + err = fd; + goto out; + } + credp->fc_mode = credp->fc_mode|S_IFREG; + /* Set cleint credentials in xattr */ + err = local_set_xattr(buffer, credp); + if (err == -1) { + serrno = errno; + goto err_end; + } + } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) { + buffer = rpath(fs_ctx, path); + fd = open(buffer, flags, SM_LOCAL_MODE_BITS); + if (fd == -1) { + err = fd; + goto out; + } + credp->fc_mode = credp->fc_mode|S_IFREG; + /* Set client credentials in .virtfs_metadata directory files */ + err = local_set_mapped_file_attr(fs_ctx, path, credp); + if (err == -1) { + serrno = errno; + goto err_end; + } + } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) || + (fs_ctx->export_flags & V9FS_SM_NONE)) { + buffer = rpath(fs_ctx, path); + fd = open(buffer, flags, credp->fc_mode); + if (fd == -1) { + err = fd; + goto out; + } + err = local_post_create_passthrough(fs_ctx, path, credp); + if (err == -1) { + serrno = errno; + goto err_end; + } + } + err = fd; + fs->fd = fd; + goto out; + +err_end: + close(fd); + remove(buffer); + errno = serrno; +out: + g_free(buffer); + v9fs_string_free(&fullname); + return err; +} + + +static int local_symlink(FsContext *fs_ctx, const char *oldpath, + V9fsPath *dir_path, const char *name, FsCred *credp) +{ + int err = -1; + int serrno = 0; + char *newpath; + V9fsString fullname; + char *buffer = NULL; + + v9fs_string_init(&fullname); + v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name); + newpath = fullname.data; + + /* Determine the security model */ + if (fs_ctx->export_flags & V9FS_SM_MAPPED) { + int fd; + ssize_t oldpath_size, write_size; + buffer = rpath(fs_ctx, newpath); + fd = open(buffer, O_CREAT|O_EXCL|O_RDWR|O_NOFOLLOW, SM_LOCAL_MODE_BITS); + if (fd == -1) { + err = fd; + goto out; + } + /* Write the oldpath (target) to the file. */ + oldpath_size = strlen(oldpath); + do { + write_size = write(fd, (void *)oldpath, oldpath_size); + } while (write_size == -1 && errno == EINTR); + + if (write_size != oldpath_size) { + serrno = errno; + close(fd); + err = -1; + goto err_end; + } + close(fd); + /* Set cleint credentials in symlink's xattr */ + credp->fc_mode = credp->fc_mode|S_IFLNK; + err = local_set_xattr(buffer, credp); + if (err == -1) { + serrno = errno; + goto err_end; + } + } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) { + int fd; + ssize_t oldpath_size, write_size; + buffer = rpath(fs_ctx, newpath); + fd = open(buffer, O_CREAT|O_EXCL|O_RDWR|O_NOFOLLOW, SM_LOCAL_MODE_BITS); + if (fd == -1) { + err = fd; + goto out; + } + /* Write the oldpath (target) to the file. */ + oldpath_size = strlen(oldpath); + do { + write_size = write(fd, (void *)oldpath, oldpath_size); + } while (write_size == -1 && errno == EINTR); + + if (write_size != oldpath_size) { + serrno = errno; + close(fd); + err = -1; + goto err_end; + } + close(fd); + /* Set cleint credentials in symlink's xattr */ + credp->fc_mode = credp->fc_mode|S_IFLNK; + err = local_set_mapped_file_attr(fs_ctx, newpath, credp); + if (err == -1) { + serrno = errno; + goto err_end; + } + } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) || + (fs_ctx->export_flags & V9FS_SM_NONE)) { + buffer = rpath(fs_ctx, newpath); + err = symlink(oldpath, buffer); + if (err) { + goto out; + } + err = lchown(buffer, credp->fc_uid, credp->fc_gid); + if (err == -1) { + /* + * If we fail to change ownership and if we are + * using security model none. Ignore the error + */ + if ((fs_ctx->export_flags & V9FS_SEC_MASK) != V9FS_SM_NONE) { + serrno = errno; + goto err_end; + } else + err = 0; + } + } + goto out; + +err_end: + remove(buffer); + errno = serrno; +out: + g_free(buffer); + v9fs_string_free(&fullname); + return err; +} + +static int local_link(FsContext *ctx, V9fsPath *oldpath, + V9fsPath *dirpath, const char *name) +{ + int ret; + V9fsString newpath; + char *buffer, *buffer1; + + v9fs_string_init(&newpath); + v9fs_string_sprintf(&newpath, "%s/%s", dirpath->data, name); + + buffer = rpath(ctx, oldpath->data); + buffer1 = rpath(ctx, newpath.data); + ret = link(buffer, buffer1); + g_free(buffer); + g_free(buffer1); + + /* now link the virtfs_metadata files */ + if (!ret && (ctx->export_flags & V9FS_SM_MAPPED_FILE)) { + /* Link the .virtfs_metadata files. Create the metada directory */ + ret = local_create_mapped_attr_dir(ctx, newpath.data); + if (ret < 0) { + goto err_out; + } + buffer = local_mapped_attr_path(ctx, oldpath->data); + buffer1 = local_mapped_attr_path(ctx, newpath.data); + ret = link(buffer, buffer1); + g_free(buffer); + g_free(buffer1); + if (ret < 0 && errno != ENOENT) { + goto err_out; + } + } +err_out: + v9fs_string_free(&newpath); + return ret; +} + +static int local_truncate(FsContext *ctx, V9fsPath *fs_path, off_t size) +{ + char *buffer; + int ret; + char *path = fs_path->data; + + buffer = rpath(ctx, path); + ret = truncate(buffer, size); + g_free(buffer); + return ret; +} + +static int local_rename(FsContext *ctx, const char *oldpath, + const char *newpath) +{ + int err; + char *buffer, *buffer1; + + if (ctx->export_flags & V9FS_SM_MAPPED_FILE) { + err = local_create_mapped_attr_dir(ctx, newpath); + if (err < 0) { + return err; + } + /* rename the .virtfs_metadata files */ + buffer = local_mapped_attr_path(ctx, oldpath); + buffer1 = local_mapped_attr_path(ctx, newpath); + err = rename(buffer, buffer1); + g_free(buffer); + g_free(buffer1); + if (err < 0 && errno != ENOENT) { + return err; + } + } + + buffer = rpath(ctx, oldpath); + buffer1 = rpath(ctx, newpath); + err = rename(buffer, buffer1); + g_free(buffer); + g_free(buffer1); + return err; +} + +static int local_chown(FsContext *fs_ctx, V9fsPath *fs_path, FsCred *credp) +{ + char *buffer; + int ret = -1; + char *path = fs_path->data; + + if ((credp->fc_uid == -1 && credp->fc_gid == -1) || + (fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) || + (fs_ctx->export_flags & V9FS_SM_NONE)) { + buffer = rpath(fs_ctx, path); + ret = lchown(buffer, credp->fc_uid, credp->fc_gid); + g_free(buffer); + } else if (fs_ctx->export_flags & V9FS_SM_MAPPED) { + buffer = rpath(fs_ctx, path); + ret = local_set_xattr(buffer, credp); + g_free(buffer); + } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) { + return local_set_mapped_file_attr(fs_ctx, path, credp); + } + return ret; +} + +static int local_utimensat(FsContext *s, V9fsPath *fs_path, + const struct timespec *buf) +{ + char *buffer; + int ret; + char *path = fs_path->data; + + buffer = rpath(s, path); + ret = qemu_utimens(buffer, buf); + g_free(buffer); + return ret; +} + +static int local_remove(FsContext *ctx, const char *path) +{ + int err; + struct stat stbuf; + char *buffer; + + if (ctx->export_flags & V9FS_SM_MAPPED_FILE) { + buffer = rpath(ctx, path); + err = lstat(buffer, &stbuf); + g_free(buffer); + if (err) { + goto err_out; + } + /* + * If directory remove .virtfs_metadata contained in the + * directory + */ + if (S_ISDIR(stbuf.st_mode)) { + buffer = g_strdup_printf("%s/%s/%s", ctx->fs_root, + path, VIRTFS_META_DIR); + err = remove(buffer); + g_free(buffer); + if (err < 0 && errno != ENOENT) { + /* + * We didn't had the .virtfs_metadata file. May be file created + * in non-mapped mode ?. Ignore ENOENT. + */ + goto err_out; + } + } + /* + * Now remove the name from parent directory + * .virtfs_metadata directory + */ + buffer = local_mapped_attr_path(ctx, path); + err = remove(buffer); + g_free(buffer); + if (err < 0 && errno != ENOENT) { + /* + * We didn't had the .virtfs_metadata file. May be file created + * in non-mapped mode ?. Ignore ENOENT. + */ + goto err_out; + } + } + + buffer = rpath(ctx, path); + err = remove(buffer); + g_free(buffer); +err_out: + return err; +} + +static int local_fsync(FsContext *ctx, int fid_type, + V9fsFidOpenState *fs, int datasync) +{ + int fd; + + if (fid_type == P9_FID_DIR) { + fd = dirfd(fs->dir); + } else { + fd = fs->fd; + } + + if (datasync) { + return qemu_fdatasync(fd); + } else { + return fsync(fd); + } +} + +static int local_statfs(FsContext *s, V9fsPath *fs_path, struct statfs *stbuf) +{ + char *buffer; + int ret; + char *path = fs_path->data; + + buffer = rpath(s, path); + ret = statfs(buffer, stbuf); + g_free(buffer); + return ret; +} + +static ssize_t local_lgetxattr(FsContext *ctx, V9fsPath *fs_path, + const char *name, void *value, size_t size) +{ + char *path = fs_path->data; + + return v9fs_get_xattr(ctx, path, name, value, size); +} + +static ssize_t local_llistxattr(FsContext *ctx, V9fsPath *fs_path, + void *value, size_t size) +{ + char *path = fs_path->data; + + return v9fs_list_xattr(ctx, path, value, size); +} + +static int local_lsetxattr(FsContext *ctx, V9fsPath *fs_path, const char *name, + void *value, size_t size, int flags) +{ + char *path = fs_path->data; + + return v9fs_set_xattr(ctx, path, name, value, size, flags); +} + +static int local_lremovexattr(FsContext *ctx, V9fsPath *fs_path, + const char *name) +{ + char *path = fs_path->data; + + return v9fs_remove_xattr(ctx, path, name); +} + +static int local_name_to_path(FsContext *ctx, V9fsPath *dir_path, + const char *name, V9fsPath *target) +{ + if (dir_path) { + v9fs_string_sprintf((V9fsString *)target, "%s/%s", + dir_path->data, name); + } else { + v9fs_string_sprintf((V9fsString *)target, "%s", name); + } + /* Bump the size for including terminating NULL */ + target->size++; + return 0; +} + +static int local_renameat(FsContext *ctx, V9fsPath *olddir, + const char *old_name, V9fsPath *newdir, + const char *new_name) +{ + int ret; + V9fsString old_full_name, new_full_name; + + v9fs_string_init(&old_full_name); + v9fs_string_init(&new_full_name); + + v9fs_string_sprintf(&old_full_name, "%s/%s", olddir->data, old_name); + v9fs_string_sprintf(&new_full_name, "%s/%s", newdir->data, new_name); + + ret = local_rename(ctx, old_full_name.data, new_full_name.data); + v9fs_string_free(&old_full_name); + v9fs_string_free(&new_full_name); + return ret; +} + +static int local_unlinkat(FsContext *ctx, V9fsPath *dir, + const char *name, int flags) +{ + int ret; + V9fsString fullname; + char *buffer; + + v9fs_string_init(&fullname); + + v9fs_string_sprintf(&fullname, "%s/%s", dir->data, name); + if (ctx->export_flags & V9FS_SM_MAPPED_FILE) { + if (flags == AT_REMOVEDIR) { + /* + * If directory remove .virtfs_metadata contained in the + * directory + */ + buffer = g_strdup_printf("%s/%s/%s", ctx->fs_root, + fullname.data, VIRTFS_META_DIR); + ret = remove(buffer); + g_free(buffer); + if (ret < 0 && errno != ENOENT) { + /* + * We didn't had the .virtfs_metadata file. May be file created + * in non-mapped mode ?. Ignore ENOENT. + */ + goto err_out; + } + } + /* + * Now remove the name from parent directory + * .virtfs_metadata directory. + */ + buffer = local_mapped_attr_path(ctx, fullname.data); + ret = remove(buffer); + g_free(buffer); + if (ret < 0 && errno != ENOENT) { + /* + * We didn't had the .virtfs_metadata file. May be file created + * in non-mapped mode ?. Ignore ENOENT. + */ + goto err_out; + } + } + /* Remove the name finally */ + buffer = rpath(ctx, fullname.data); + ret = remove(buffer); + g_free(buffer); + +err_out: + v9fs_string_free(&fullname); + return ret; +} + +static int local_ioc_getversion(FsContext *ctx, V9fsPath *path, + mode_t st_mode, uint64_t *st_gen) +{ +#ifdef FS_IOC_GETVERSION + int err; + V9fsFidOpenState fid_open; + + /* + * Do not try to open special files like device nodes, fifos etc + * We can get fd for regular files and directories only + */ + if (!S_ISREG(st_mode) && !S_ISDIR(st_mode)) { + errno = ENOTTY; + return -1; + } + err = local_open(ctx, path, O_RDONLY, &fid_open); + if (err < 0) { + return err; + } + err = ioctl(fid_open.fd, FS_IOC_GETVERSION, st_gen); + local_close(ctx, &fid_open); + return err; +#else + errno = ENOTTY; + return -1; +#endif +} + +static int local_init(FsContext *ctx) +{ + int err = 0; + struct statfs stbuf; + + if (ctx->export_flags & V9FS_SM_PASSTHROUGH) { + ctx->xops = passthrough_xattr_ops; + } else if (ctx->export_flags & V9FS_SM_MAPPED) { + ctx->xops = mapped_xattr_ops; + } else if (ctx->export_flags & V9FS_SM_NONE) { + ctx->xops = none_xattr_ops; + } else if (ctx->export_flags & V9FS_SM_MAPPED_FILE) { + /* + * xattr operation for mapped-file and passthrough + * remain same. + */ + ctx->xops = passthrough_xattr_ops; + } + ctx->export_flags |= V9FS_PATHNAME_FSCONTEXT; +#ifdef FS_IOC_GETVERSION + /* + * use ioc_getversion only if the iocl is definied + */ + err = statfs(ctx->fs_root, &stbuf); + if (!err) { + switch (stbuf.f_type) { + case EXT2_SUPER_MAGIC: + case BTRFS_SUPER_MAGIC: + case REISERFS_SUPER_MAGIC: + case XFS_SUPER_MAGIC: + ctx->exops.get_st_gen = local_ioc_getversion; + break; + } + } +#endif + return err; +} + +static int local_parse_opts(QemuOpts *opts, struct FsDriverEntry *fse) +{ + const char *sec_model = qemu_opt_get(opts, "security_model"); + const char *path = qemu_opt_get(opts, "path"); + + if (!sec_model) { + fprintf(stderr, "security model not specified, " + "local fs needs security model\nvalid options are:" + "\tsecurity_model=[passthrough|mapped|none]\n"); + return -1; + } + + if (!strcmp(sec_model, "passthrough")) { + fse->export_flags |= V9FS_SM_PASSTHROUGH; + } else if (!strcmp(sec_model, "mapped") || + !strcmp(sec_model, "mapped-xattr")) { + fse->export_flags |= V9FS_SM_MAPPED; + } else if (!strcmp(sec_model, "none")) { + fse->export_flags |= V9FS_SM_NONE; + } else if (!strcmp(sec_model, "mapped-file")) { + fse->export_flags |= V9FS_SM_MAPPED_FILE; + } else { + fprintf(stderr, "Invalid security model %s specified, valid options are" + "\n\t [passthrough|mapped-xattr|mapped-file|none]\n", + sec_model); + return -1; + } + + if (!path) { + fprintf(stderr, "fsdev: No path specified.\n"); + return -1; + } + fse->path = g_strdup(path); + + return 0; +} + +FileOperations local_ops = { + .parse_opts = local_parse_opts, + .init = local_init, + .lstat = local_lstat, + .readlink = local_readlink, + .close = local_close, + .closedir = local_closedir, + .open = local_open, + .opendir = local_opendir, + .rewinddir = local_rewinddir, + .telldir = local_telldir, + .readdir_r = local_readdir_r, + .seekdir = local_seekdir, + .preadv = local_preadv, + .pwritev = local_pwritev, + .chmod = local_chmod, + .mknod = local_mknod, + .mkdir = local_mkdir, + .fstat = local_fstat, + .open2 = local_open2, + .symlink = local_symlink, + .link = local_link, + .truncate = local_truncate, + .rename = local_rename, + .chown = local_chown, + .utimensat = local_utimensat, + .remove = local_remove, + .fsync = local_fsync, + .statfs = local_statfs, + .lgetxattr = local_lgetxattr, + .llistxattr = local_llistxattr, + .lsetxattr = local_lsetxattr, + .lremovexattr = local_lremovexattr, + .name_to_path = local_name_to_path, + .renameat = local_renameat, + .unlinkat = local_unlinkat, +}; diff --git a/qemu/hw/9pfs/virtio-9p-posix-acl.c b/qemu/hw/9pfs/virtio-9p-posix-acl.c new file mode 100644 index 000000000..09dad071e --- /dev/null +++ b/qemu/hw/9pfs/virtio-9p-posix-acl.c @@ -0,0 +1,185 @@ +/* + * Virtio 9p system.posix* xattr callback + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include <sys/types.h> +#include "qemu/xattr.h" +#include "hw/virtio/virtio.h" +#include "virtio-9p.h" +#include "fsdev/file-op-9p.h" +#include "virtio-9p-xattr.h" + +#define MAP_ACL_ACCESS "user.virtfs.system.posix_acl_access" +#define MAP_ACL_DEFAULT "user.virtfs.system.posix_acl_default" +#define ACL_ACCESS "system.posix_acl_access" +#define ACL_DEFAULT "system.posix_acl_default" + +static ssize_t mp_pacl_getxattr(FsContext *ctx, const char *path, + const char *name, void *value, size_t size) +{ + char *buffer; + ssize_t ret; + + buffer = rpath(ctx, path); + ret = lgetxattr(buffer, MAP_ACL_ACCESS, value, size); + g_free(buffer); + return ret; +} + +static ssize_t mp_pacl_listxattr(FsContext *ctx, const char *path, + char *name, void *value, size_t osize) +{ + ssize_t len = sizeof(ACL_ACCESS); + + if (!value) { + return len; + } + + if (osize < len) { + errno = ERANGE; + return -1; + } + + /* len includes the trailing NUL */ + memcpy(value, ACL_ACCESS, len); + return 0; +} + +static int mp_pacl_setxattr(FsContext *ctx, const char *path, const char *name, + void *value, size_t size, int flags) +{ + char *buffer; + int ret; + + buffer = rpath(ctx, path); + ret = lsetxattr(buffer, MAP_ACL_ACCESS, value, size, flags); + g_free(buffer); + return ret; +} + +static int mp_pacl_removexattr(FsContext *ctx, + const char *path, const char *name) +{ + int ret; + char *buffer; + + buffer = rpath(ctx, path); + ret = lremovexattr(buffer, MAP_ACL_ACCESS); + if (ret == -1 && errno == ENODATA) { + /* + * We don't get ENODATA error when trying to remove a + * posix acl that is not present. So don't throw the error + * even in case of mapped security model + */ + errno = 0; + ret = 0; + } + g_free(buffer); + return ret; +} + +static ssize_t mp_dacl_getxattr(FsContext *ctx, const char *path, + const char *name, void *value, size_t size) +{ + char *buffer; + ssize_t ret; + + buffer = rpath(ctx, path); + ret = lgetxattr(buffer, MAP_ACL_DEFAULT, value, size); + g_free(buffer); + return ret; +} + +static ssize_t mp_dacl_listxattr(FsContext *ctx, const char *path, + char *name, void *value, size_t osize) +{ + ssize_t len = sizeof(ACL_DEFAULT); + + if (!value) { + return len; + } + + if (osize < len) { + errno = ERANGE; + return -1; + } + + /* len includes the trailing NUL */ + memcpy(value, ACL_DEFAULT, len); + return 0; +} + +static int mp_dacl_setxattr(FsContext *ctx, const char *path, const char *name, + void *value, size_t size, int flags) +{ + char *buffer; + int ret; + + buffer = rpath(ctx, path); + ret = lsetxattr(buffer, MAP_ACL_DEFAULT, value, size, flags); + g_free(buffer); + return ret; +} + +static int mp_dacl_removexattr(FsContext *ctx, + const char *path, const char *name) +{ + int ret; + char *buffer; + + buffer = rpath(ctx, path); + ret = lremovexattr(buffer, MAP_ACL_DEFAULT); + if (ret == -1 && errno == ENODATA) { + /* + * We don't get ENODATA error when trying to remove a + * posix acl that is not present. So don't throw the error + * even in case of mapped security model + */ + errno = 0; + ret = 0; + } + g_free(buffer); + return ret; +} + + +XattrOperations mapped_pacl_xattr = { + .name = "system.posix_acl_access", + .getxattr = mp_pacl_getxattr, + .setxattr = mp_pacl_setxattr, + .listxattr = mp_pacl_listxattr, + .removexattr = mp_pacl_removexattr, +}; + +XattrOperations mapped_dacl_xattr = { + .name = "system.posix_acl_default", + .getxattr = mp_dacl_getxattr, + .setxattr = mp_dacl_setxattr, + .listxattr = mp_dacl_listxattr, + .removexattr = mp_dacl_removexattr, +}; + +XattrOperations passthrough_acl_xattr = { + .name = "system.posix_acl_", + .getxattr = pt_getxattr, + .setxattr = pt_setxattr, + .listxattr = pt_listxattr, + .removexattr = pt_removexattr, +}; + +XattrOperations none_acl_xattr = { + .name = "system.posix_acl_", + .getxattr = notsup_getxattr, + .setxattr = notsup_setxattr, + .listxattr = notsup_listxattr, + .removexattr = notsup_removexattr, +}; diff --git a/qemu/hw/9pfs/virtio-9p-proxy.c b/qemu/hw/9pfs/virtio-9p-proxy.c new file mode 100644 index 000000000..1bc7881f0 --- /dev/null +++ b/qemu/hw/9pfs/virtio-9p-proxy.c @@ -0,0 +1,1219 @@ +/* + * Virtio 9p Proxy callback + * + * Copyright IBM, Corp. 2011 + * + * Authors: + * M. Mohan Kumar <mohan@in.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ +#include <sys/socket.h> +#include <sys/un.h> +#include "hw/virtio/virtio.h" +#include "virtio-9p.h" +#include "qemu/error-report.h" +#include "fsdev/qemu-fsdev.h" +#include "virtio-9p-proxy.h" + +typedef struct V9fsProxy { + int sockfd; + QemuMutex mutex; + struct iovec in_iovec; + struct iovec out_iovec; +} V9fsProxy; + +/* + * Return received file descriptor on success in *status. + * errno is also returned on *status (which will be < 0) + * return < 0 on transport error. + */ +static int v9fs_receivefd(int sockfd, int *status) +{ + struct iovec iov; + struct msghdr msg; + struct cmsghdr *cmsg; + int retval, data, fd; + union MsgControl msg_control; + + iov.iov_base = &data; + iov.iov_len = sizeof(data); + + memset(&msg, 0, sizeof(msg)); + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = &msg_control; + msg.msg_controllen = sizeof(msg_control); + + do { + retval = recvmsg(sockfd, &msg, 0); + } while (retval < 0 && errno == EINTR); + if (retval <= 0) { + return retval; + } + /* + * data is set to V9FS_FD_VALID, if ancillary data is sent. If this + * request doesn't need ancillary data (fd) or an error occurred, + * data is set to negative errno value. + */ + if (data != V9FS_FD_VALID) { + *status = data; + return 0; + } + /* + * File descriptor (fd) is sent in the ancillary data. Check if we + * indeed received it. One of the reasons to fail to receive it is if + * we exceeded the maximum number of file descriptors! + */ + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg; cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)) || + cmsg->cmsg_level != SOL_SOCKET || + cmsg->cmsg_type != SCM_RIGHTS) { + continue; + } + fd = *((int *)CMSG_DATA(cmsg)); + *status = fd; + return 0; + } + *status = -ENFILE; /* Ancillary data sent but not received */ + return 0; +} + +static ssize_t socket_read(int sockfd, void *buff, size_t size) +{ + ssize_t retval, total = 0; + + while (size) { + retval = read(sockfd, buff, size); + if (retval == 0) { + return -EIO; + } + if (retval < 0) { + if (errno == EINTR) { + continue; + } + return -errno; + } + size -= retval; + buff += retval; + total += retval; + } + return total; +} + +/* Converts proxy_statfs to VFS statfs structure */ +static void prstatfs_to_statfs(struct statfs *stfs, ProxyStatFS *prstfs) +{ + memset(stfs, 0, sizeof(*stfs)); + stfs->f_type = prstfs->f_type; + stfs->f_bsize = prstfs->f_bsize; + stfs->f_blocks = prstfs->f_blocks; + stfs->f_bfree = prstfs->f_bfree; + stfs->f_bavail = prstfs->f_bavail; + stfs->f_files = prstfs->f_files; + stfs->f_ffree = prstfs->f_ffree; + 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; +} + +/* Converts proxy_stat structure to VFS stat structure */ +static void prstat_to_stat(struct stat *stbuf, ProxyStat *prstat) +{ + memset(stbuf, 0, sizeof(*stbuf)); + stbuf->st_dev = prstat->st_dev; + stbuf->st_ino = prstat->st_ino; + stbuf->st_nlink = prstat->st_nlink; + stbuf->st_mode = prstat->st_mode; + stbuf->st_uid = prstat->st_uid; + stbuf->st_gid = prstat->st_gid; + stbuf->st_rdev = prstat->st_rdev; + 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_mtime = prstat->st_mtim_sec; + stbuf->st_mtim.tv_nsec = prstat->st_mtim_nsec; + stbuf->st_ctime = prstat->st_ctim_sec; + stbuf->st_ctim.tv_nsec = prstat->st_ctim_nsec; +} + +/* + * Response contains two parts + * {header, data} + * header.type == T_ERROR, data -> -errno + * header.type == T_SUCCESS, data -> response + * size of errno/response is given by header.size + * returns < 0, on transport error. response is + * valid only if status >= 0. + */ +static int v9fs_receive_response(V9fsProxy *proxy, int type, + int *status, void *response) +{ + int retval; + ProxyHeader header; + struct iovec *reply = &proxy->in_iovec; + + *status = 0; + reply->iov_len = 0; + retval = socket_read(proxy->sockfd, reply->iov_base, PROXY_HDR_SZ); + if (retval < 0) { + return retval; + } + reply->iov_len = PROXY_HDR_SZ; + proxy_unmarshal(reply, 0, "dd", &header.type, &header.size); + /* + * if response size > PROXY_MAX_IO_SZ, read the response but ignore it and + * return -ENOBUFS + */ + if (header.size > PROXY_MAX_IO_SZ) { + int count; + while (header.size > 0) { + count = MIN(PROXY_MAX_IO_SZ, header.size); + count = socket_read(proxy->sockfd, reply->iov_base, count); + if (count < 0) { + return count; + } + header.size -= count; + } + *status = -ENOBUFS; + return 0; + } + + retval = socket_read(proxy->sockfd, + reply->iov_base + PROXY_HDR_SZ, header.size); + if (retval < 0) { + return retval; + } + reply->iov_len += header.size; + /* there was an error during processing request */ + if (header.type == T_ERROR) { + int ret; + ret = proxy_unmarshal(reply, PROXY_HDR_SZ, "d", status); + if (ret < 0) { + *status = ret; + } + return 0; + } + + switch (type) { + case T_LSTAT: { + ProxyStat prstat; + retval = proxy_unmarshal(reply, PROXY_HDR_SZ, + "qqqdddqqqqqqqqqq", &prstat.st_dev, + &prstat.st_ino, &prstat.st_nlink, + &prstat.st_mode, &prstat.st_uid, + &prstat.st_gid, &prstat.st_rdev, + &prstat.st_size, &prstat.st_blksize, + &prstat.st_blocks, + &prstat.st_atim_sec, &prstat.st_atim_nsec, + &prstat.st_mtim_sec, &prstat.st_mtim_nsec, + &prstat.st_ctim_sec, &prstat.st_ctim_nsec); + prstat_to_stat(response, &prstat); + break; + } + case T_STATFS: { + ProxyStatFS prstfs; + retval = proxy_unmarshal(reply, PROXY_HDR_SZ, + "qqqqqqqqqqq", &prstfs.f_type, + &prstfs.f_bsize, &prstfs.f_blocks, + &prstfs.f_bfree, &prstfs.f_bavail, + &prstfs.f_files, &prstfs.f_ffree, + &prstfs.f_fsid[0], &prstfs.f_fsid[1], + &prstfs.f_namelen, &prstfs.f_frsize); + prstatfs_to_statfs(response, &prstfs); + break; + } + case T_READLINK: { + V9fsString target; + v9fs_string_init(&target); + retval = proxy_unmarshal(reply, PROXY_HDR_SZ, "s", &target); + strcpy(response, target.data); + v9fs_string_free(&target); + break; + } + case T_LGETXATTR: + case T_LLISTXATTR: { + V9fsString xattr; + v9fs_string_init(&xattr); + retval = proxy_unmarshal(reply, PROXY_HDR_SZ, "s", &xattr); + memcpy(response, xattr.data, xattr.size); + v9fs_string_free(&xattr); + break; + } + case T_GETVERSION: + proxy_unmarshal(reply, PROXY_HDR_SZ, "q", response); + break; + default: + return -1; + } + if (retval < 0) { + *status = retval; + } + return 0; +} + +/* + * return < 0 on transport error. + * *status is valid only if return >= 0 + */ +static int v9fs_receive_status(V9fsProxy *proxy, + struct iovec *reply, int *status) +{ + int retval; + ProxyHeader header; + + *status = 0; + reply->iov_len = 0; + retval = socket_read(proxy->sockfd, reply->iov_base, PROXY_HDR_SZ); + if (retval < 0) { + return retval; + } + reply->iov_len = PROXY_HDR_SZ; + proxy_unmarshal(reply, 0, "dd", &header.type, &header.size); + if (header.size != sizeof(int)) { + *status = -ENOBUFS; + return 0; + } + retval = socket_read(proxy->sockfd, + reply->iov_base + PROXY_HDR_SZ, header.size); + if (retval < 0) { + return retval; + } + reply->iov_len += header.size; + proxy_unmarshal(reply, PROXY_HDR_SZ, "d", status); + return 0; +} + +/* + * Proxy->header and proxy->request written to socket by QEMU process. + * This request read by proxy helper process + * returns 0 on success and -errno on error + */ +static int v9fs_request(V9fsProxy *proxy, int type, + void *response, const char *fmt, ...) +{ + dev_t rdev; + va_list ap; + int size = 0; + int retval = 0; + uint64_t offset; + ProxyHeader header = { 0, 0}; + struct timespec spec[2]; + int flags, mode, uid, gid; + V9fsString *name, *value; + V9fsString *path, *oldpath; + struct iovec *iovec = NULL, *reply = NULL; + + qemu_mutex_lock(&proxy->mutex); + + if (proxy->sockfd == -1) { + retval = -EIO; + goto err_out; + } + iovec = &proxy->out_iovec; + reply = &proxy->in_iovec; + va_start(ap, fmt); + switch (type) { + case T_OPEN: + path = va_arg(ap, V9fsString *); + flags = va_arg(ap, int); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "sd", path, flags); + if (retval > 0) { + header.size = retval; + header.type = T_OPEN; + } + break; + case T_CREATE: + path = va_arg(ap, V9fsString *); + flags = va_arg(ap, int); + mode = va_arg(ap, int); + uid = va_arg(ap, int); + gid = va_arg(ap, int); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "sdddd", path, + flags, mode, uid, gid); + if (retval > 0) { + header.size = retval; + header.type = T_CREATE; + } + break; + case T_MKNOD: + path = va_arg(ap, V9fsString *); + mode = va_arg(ap, int); + rdev = va_arg(ap, long int); + uid = va_arg(ap, int); + gid = va_arg(ap, int); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "ddsdq", + uid, gid, path, mode, rdev); + if (retval > 0) { + header.size = retval; + header.type = T_MKNOD; + } + break; + case T_MKDIR: + path = va_arg(ap, V9fsString *); + mode = va_arg(ap, int); + uid = va_arg(ap, int); + gid = va_arg(ap, int); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "ddsd", + uid, gid, path, mode); + if (retval > 0) { + header.size = retval; + header.type = T_MKDIR; + } + break; + case T_SYMLINK: + oldpath = va_arg(ap, V9fsString *); + path = va_arg(ap, V9fsString *); + uid = va_arg(ap, int); + gid = va_arg(ap, int); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "ddss", + uid, gid, oldpath, path); + if (retval > 0) { + header.size = retval; + header.type = T_SYMLINK; + } + break; + case T_LINK: + oldpath = va_arg(ap, V9fsString *); + path = va_arg(ap, V9fsString *); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "ss", + oldpath, path); + if (retval > 0) { + header.size = retval; + header.type = T_LINK; + } + break; + case T_LSTAT: + path = va_arg(ap, V9fsString *); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "s", path); + if (retval > 0) { + header.size = retval; + header.type = T_LSTAT; + } + break; + case T_READLINK: + path = va_arg(ap, V9fsString *); + size = va_arg(ap, int); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "sd", path, size); + if (retval > 0) { + header.size = retval; + header.type = T_READLINK; + } + break; + case T_STATFS: + path = va_arg(ap, V9fsString *); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "s", path); + if (retval > 0) { + header.size = retval; + header.type = T_STATFS; + } + break; + case T_CHMOD: + path = va_arg(ap, V9fsString *); + mode = va_arg(ap, int); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "sd", path, mode); + if (retval > 0) { + header.size = retval; + header.type = T_CHMOD; + } + break; + case T_CHOWN: + path = va_arg(ap, V9fsString *); + uid = va_arg(ap, int); + gid = va_arg(ap, int); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "sdd", path, uid, gid); + if (retval > 0) { + header.size = retval; + header.type = T_CHOWN; + } + break; + case T_TRUNCATE: + path = va_arg(ap, V9fsString *); + offset = va_arg(ap, uint64_t); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "sq", path, offset); + if (retval > 0) { + header.size = retval; + header.type = T_TRUNCATE; + } + break; + case T_UTIME: + path = va_arg(ap, V9fsString *); + spec[0].tv_sec = va_arg(ap, long); + spec[0].tv_nsec = va_arg(ap, long); + spec[1].tv_sec = va_arg(ap, long); + spec[1].tv_nsec = va_arg(ap, long); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "sqqqq", path, + spec[0].tv_sec, spec[1].tv_nsec, + spec[1].tv_sec, spec[1].tv_nsec); + if (retval > 0) { + header.size = retval; + header.type = T_UTIME; + } + break; + case T_RENAME: + oldpath = va_arg(ap, V9fsString *); + path = va_arg(ap, V9fsString *); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "ss", oldpath, path); + if (retval > 0) { + header.size = retval; + header.type = T_RENAME; + } + break; + case T_REMOVE: + path = va_arg(ap, V9fsString *); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "s", path); + if (retval > 0) { + header.size = retval; + header.type = T_REMOVE; + } + break; + case T_LGETXATTR: + size = va_arg(ap, int); + path = va_arg(ap, V9fsString *); + name = va_arg(ap, V9fsString *); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, + "dss", size, path, name); + if (retval > 0) { + header.size = retval; + header.type = T_LGETXATTR; + } + break; + case T_LLISTXATTR: + size = va_arg(ap, int); + path = va_arg(ap, V9fsString *); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "ds", size, path); + if (retval > 0) { + header.size = retval; + header.type = T_LLISTXATTR; + } + break; + case T_LSETXATTR: + path = va_arg(ap, V9fsString *); + name = va_arg(ap, V9fsString *); + value = va_arg(ap, V9fsString *); + size = va_arg(ap, int); + flags = va_arg(ap, int); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "sssdd", + path, name, value, size, flags); + if (retval > 0) { + header.size = retval; + header.type = T_LSETXATTR; + } + break; + case T_LREMOVEXATTR: + path = va_arg(ap, V9fsString *); + name = va_arg(ap, V9fsString *); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "ss", path, name); + if (retval > 0) { + header.size = retval; + header.type = T_LREMOVEXATTR; + } + break; + case T_GETVERSION: + path = va_arg(ap, V9fsString *); + retval = proxy_marshal(iovec, PROXY_HDR_SZ, "s", path); + if (retval > 0) { + header.size = retval; + header.type = T_GETVERSION; + } + break; + default: + error_report("Invalid type %d", type); + retval = -EINVAL; + break; + } + va_end(ap); + + if (retval < 0) { + goto err_out; + } + + /* marshal the header details */ + proxy_marshal(iovec, 0, "dd", header.type, header.size); + header.size += PROXY_HDR_SZ; + + retval = qemu_write_full(proxy->sockfd, iovec->iov_base, header.size); + if (retval != header.size) { + goto close_error; + } + + switch (type) { + case T_OPEN: + case T_CREATE: + /* + * A file descriptor is returned as response for + * T_OPEN,T_CREATE on success + */ + if (v9fs_receivefd(proxy->sockfd, &retval) < 0) { + goto close_error; + } + break; + case T_MKNOD: + case T_MKDIR: + case T_SYMLINK: + case T_LINK: + case T_CHMOD: + case T_CHOWN: + case T_RENAME: + case T_TRUNCATE: + case T_UTIME: + case T_REMOVE: + case T_LSETXATTR: + case T_LREMOVEXATTR: + if (v9fs_receive_status(proxy, reply, &retval) < 0) { + goto close_error; + } + break; + case T_LSTAT: + case T_READLINK: + case T_STATFS: + case T_GETVERSION: + if (v9fs_receive_response(proxy, type, &retval, response) < 0) { + goto close_error; + } + break; + case T_LGETXATTR: + case T_LLISTXATTR: + if (!size) { + if (v9fs_receive_status(proxy, reply, &retval) < 0) { + goto close_error; + } + } else { + if (v9fs_receive_response(proxy, type, &retval, response) < 0) { + goto close_error; + } + } + break; + } + +err_out: + qemu_mutex_unlock(&proxy->mutex); + return retval; + +close_error: + close(proxy->sockfd); + proxy->sockfd = -1; + qemu_mutex_unlock(&proxy->mutex); + return -EIO; +} + +static int proxy_lstat(FsContext *fs_ctx, V9fsPath *fs_path, struct stat *stbuf) +{ + int retval; + retval = v9fs_request(fs_ctx->private, T_LSTAT, stbuf, "s", fs_path); + if (retval < 0) { + errno = -retval; + return -1; + } + return retval; +} + +static ssize_t proxy_readlink(FsContext *fs_ctx, V9fsPath *fs_path, + char *buf, size_t bufsz) +{ + int retval; + retval = v9fs_request(fs_ctx->private, T_READLINK, buf, "sd", + fs_path, bufsz); + if (retval < 0) { + errno = -retval; + return -1; + } + return strlen(buf); +} + +static int proxy_close(FsContext *ctx, V9fsFidOpenState *fs) +{ + return close(fs->fd); +} + +static int proxy_closedir(FsContext *ctx, V9fsFidOpenState *fs) +{ + return closedir(fs->dir); +} + +static int proxy_open(FsContext *ctx, V9fsPath *fs_path, + int flags, V9fsFidOpenState *fs) +{ + fs->fd = v9fs_request(ctx->private, T_OPEN, NULL, "sd", fs_path, flags); + if (fs->fd < 0) { + errno = -fs->fd; + fs->fd = -1; + } + return fs->fd; +} + +static int proxy_opendir(FsContext *ctx, + V9fsPath *fs_path, V9fsFidOpenState *fs) +{ + int serrno, fd; + + fs->dir = NULL; + fd = v9fs_request(ctx->private, T_OPEN, NULL, "sd", fs_path, O_DIRECTORY); + if (fd < 0) { + errno = -fd; + return -1; + } + fs->dir = fdopendir(fd); + if (!fs->dir) { + serrno = errno; + close(fd); + errno = serrno; + return -1; + } + return 0; +} + +static void proxy_rewinddir(FsContext *ctx, V9fsFidOpenState *fs) +{ + rewinddir(fs->dir); +} + +static off_t proxy_telldir(FsContext *ctx, V9fsFidOpenState *fs) +{ + return telldir(fs->dir); +} + +static int proxy_readdir_r(FsContext *ctx, V9fsFidOpenState *fs, + struct dirent *entry, + struct dirent **result) +{ + return readdir_r(fs->dir, entry, result); +} + +static void proxy_seekdir(FsContext *ctx, V9fsFidOpenState *fs, off_t off) +{ + seekdir(fs->dir, off); +} + +static ssize_t proxy_preadv(FsContext *ctx, V9fsFidOpenState *fs, + const struct iovec *iov, + int iovcnt, off_t offset) +{ + ssize_t ret; +#ifdef CONFIG_PREADV + ret = preadv(fs->fd, iov, iovcnt, offset); +#else + ret = lseek(fs->fd, offset, SEEK_SET); + if (ret >= 0) { + ret = readv(fs->fd, iov, iovcnt); + } +#endif + return ret; +} + +static ssize_t proxy_pwritev(FsContext *ctx, V9fsFidOpenState *fs, + const struct iovec *iov, + int iovcnt, off_t offset) +{ + ssize_t ret; + +#ifdef CONFIG_PREADV + ret = pwritev(fs->fd, iov, iovcnt, offset); +#else + ret = lseek(fs->fd, offset, SEEK_SET); + if (ret >= 0) { + ret = writev(fs->fd, iov, iovcnt); + } +#endif +#ifdef CONFIG_SYNC_FILE_RANGE + if (ret > 0 && ctx->export_flags & V9FS_IMMEDIATE_WRITEOUT) { + /* + * Initiate a writeback. This is not a data integrity sync. + * We want to ensure that we don't leave dirty pages in the cache + * after write when writeout=immediate is sepcified. + */ + sync_file_range(fs->fd, offset, ret, + SYNC_FILE_RANGE_WAIT_BEFORE | SYNC_FILE_RANGE_WRITE); + } +#endif + return ret; +} + +static int proxy_chmod(FsContext *fs_ctx, V9fsPath *fs_path, FsCred *credp) +{ + int retval; + retval = v9fs_request(fs_ctx->private, T_CHMOD, NULL, "sd", + fs_path, credp->fc_mode); + if (retval < 0) { + errno = -retval; + } + return retval; +} + +static int proxy_mknod(FsContext *fs_ctx, V9fsPath *dir_path, + const char *name, FsCred *credp) +{ + int retval; + V9fsString fullname; + + v9fs_string_init(&fullname); + v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name); + + retval = v9fs_request(fs_ctx->private, T_MKNOD, NULL, "sdqdd", + &fullname, credp->fc_mode, credp->fc_rdev, + credp->fc_uid, credp->fc_gid); + v9fs_string_free(&fullname); + if (retval < 0) { + errno = -retval; + retval = -1; + } + return retval; +} + +static int proxy_mkdir(FsContext *fs_ctx, V9fsPath *dir_path, + const char *name, FsCred *credp) +{ + int retval; + V9fsString fullname; + + v9fs_string_init(&fullname); + v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name); + + retval = v9fs_request(fs_ctx->private, T_MKDIR, NULL, "sddd", &fullname, + credp->fc_mode, credp->fc_uid, credp->fc_gid); + v9fs_string_free(&fullname); + if (retval < 0) { + errno = -retval; + retval = -1; + } + v9fs_string_free(&fullname); + return retval; +} + +static int proxy_fstat(FsContext *fs_ctx, int fid_type, + V9fsFidOpenState *fs, struct stat *stbuf) +{ + int fd; + + if (fid_type == P9_FID_DIR) { + fd = dirfd(fs->dir); + } else { + fd = fs->fd; + } + return fstat(fd, stbuf); +} + +static int proxy_open2(FsContext *fs_ctx, V9fsPath *dir_path, const char *name, + int flags, FsCred *credp, V9fsFidOpenState *fs) +{ + V9fsString fullname; + + v9fs_string_init(&fullname); + v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name); + + fs->fd = v9fs_request(fs_ctx->private, T_CREATE, NULL, "sdddd", + &fullname, flags, credp->fc_mode, + credp->fc_uid, credp->fc_gid); + v9fs_string_free(&fullname); + if (fs->fd < 0) { + errno = -fs->fd; + fs->fd = -1; + } + return fs->fd; +} + +static int proxy_symlink(FsContext *fs_ctx, const char *oldpath, + V9fsPath *dir_path, const char *name, FsCred *credp) +{ + int retval; + V9fsString fullname, target; + + v9fs_string_init(&fullname); + v9fs_string_init(&target); + + v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name); + v9fs_string_sprintf(&target, "%s", oldpath); + + retval = v9fs_request(fs_ctx->private, T_SYMLINK, NULL, "ssdd", + &target, &fullname, credp->fc_uid, credp->fc_gid); + v9fs_string_free(&fullname); + v9fs_string_free(&target); + if (retval < 0) { + errno = -retval; + retval = -1; + } + return retval; +} + +static int proxy_link(FsContext *ctx, V9fsPath *oldpath, + V9fsPath *dirpath, const char *name) +{ + int retval; + V9fsString newpath; + + v9fs_string_init(&newpath); + v9fs_string_sprintf(&newpath, "%s/%s", dirpath->data, name); + + retval = v9fs_request(ctx->private, T_LINK, NULL, "ss", oldpath, &newpath); + v9fs_string_free(&newpath); + if (retval < 0) { + errno = -retval; + retval = -1; + } + return retval; +} + +static int proxy_truncate(FsContext *ctx, V9fsPath *fs_path, off_t size) +{ + int retval; + + retval = v9fs_request(ctx->private, T_TRUNCATE, NULL, "sq", fs_path, size); + if (retval < 0) { + errno = -retval; + return -1; + } + return 0; +} + +static int proxy_rename(FsContext *ctx, const char *oldpath, + const char *newpath) +{ + int retval; + V9fsString oldname, newname; + + v9fs_string_init(&oldname); + v9fs_string_init(&newname); + + v9fs_string_sprintf(&oldname, "%s", oldpath); + v9fs_string_sprintf(&newname, "%s", newpath); + retval = v9fs_request(ctx->private, T_RENAME, NULL, "ss", + &oldname, &newname); + v9fs_string_free(&oldname); + v9fs_string_free(&newname); + if (retval < 0) { + errno = -retval; + } + return retval; +} + +static int proxy_chown(FsContext *fs_ctx, V9fsPath *fs_path, FsCred *credp) +{ + int retval; + retval = v9fs_request(fs_ctx->private, T_CHOWN, NULL, "sdd", + fs_path, credp->fc_uid, credp->fc_gid); + if (retval < 0) { + errno = -retval; + } + return retval; +} + +static int proxy_utimensat(FsContext *s, V9fsPath *fs_path, + const struct timespec *buf) +{ + int retval; + retval = v9fs_request(s->private, T_UTIME, NULL, "sqqqq", + fs_path, + buf[0].tv_sec, buf[0].tv_nsec, + buf[1].tv_sec, buf[1].tv_nsec); + if (retval < 0) { + errno = -retval; + } + return retval; +} + +static int proxy_remove(FsContext *ctx, const char *path) +{ + int retval; + V9fsString name; + v9fs_string_init(&name); + v9fs_string_sprintf(&name, "%s", path); + retval = v9fs_request(ctx->private, T_REMOVE, NULL, "s", &name); + v9fs_string_free(&name); + if (retval < 0) { + errno = -retval; + } + return retval; +} + +static int proxy_fsync(FsContext *ctx, int fid_type, + V9fsFidOpenState *fs, int datasync) +{ + int fd; + + if (fid_type == P9_FID_DIR) { + fd = dirfd(fs->dir); + } else { + fd = fs->fd; + } + + if (datasync) { + return qemu_fdatasync(fd); + } else { + return fsync(fd); + } +} + +static int proxy_statfs(FsContext *s, V9fsPath *fs_path, struct statfs *stbuf) +{ + int retval; + retval = v9fs_request(s->private, T_STATFS, stbuf, "s", fs_path); + if (retval < 0) { + errno = -retval; + return -1; + } + return retval; +} + +static ssize_t proxy_lgetxattr(FsContext *ctx, V9fsPath *fs_path, + const char *name, void *value, size_t size) +{ + int retval; + V9fsString xname; + + v9fs_string_init(&xname); + v9fs_string_sprintf(&xname, "%s", name); + retval = v9fs_request(ctx->private, T_LGETXATTR, value, "dss", size, + fs_path, &xname); + v9fs_string_free(&xname); + if (retval < 0) { + errno = -retval; + } + return retval; +} + +static ssize_t proxy_llistxattr(FsContext *ctx, V9fsPath *fs_path, + void *value, size_t size) +{ + int retval; + retval = v9fs_request(ctx->private, T_LLISTXATTR, value, "ds", size, + fs_path); + if (retval < 0) { + errno = -retval; + } + return retval; +} + +static int proxy_lsetxattr(FsContext *ctx, V9fsPath *fs_path, const char *name, + void *value, size_t size, int flags) +{ + int retval; + V9fsString xname, xvalue; + + v9fs_string_init(&xname); + v9fs_string_sprintf(&xname, "%s", name); + + v9fs_string_init(&xvalue); + xvalue.size = size; + xvalue.data = g_malloc(size); + memcpy(xvalue.data, value, size); + + retval = v9fs_request(ctx->private, T_LSETXATTR, value, "sssdd", + fs_path, &xname, &xvalue, size, flags); + v9fs_string_free(&xname); + v9fs_string_free(&xvalue); + if (retval < 0) { + errno = -retval; + } + return retval; +} + +static int proxy_lremovexattr(FsContext *ctx, V9fsPath *fs_path, + const char *name) +{ + int retval; + V9fsString xname; + + v9fs_string_init(&xname); + v9fs_string_sprintf(&xname, "%s", name); + retval = v9fs_request(ctx->private, T_LREMOVEXATTR, NULL, "ss", + fs_path, &xname); + v9fs_string_free(&xname); + if (retval < 0) { + errno = -retval; + } + return retval; +} + +static int proxy_name_to_path(FsContext *ctx, V9fsPath *dir_path, + const char *name, V9fsPath *target) +{ + if (dir_path) { + v9fs_string_sprintf((V9fsString *)target, "%s/%s", + dir_path->data, name); + } else { + v9fs_string_sprintf((V9fsString *)target, "%s", name); + } + /* Bump the size for including terminating NULL */ + target->size++; + return 0; +} + +static int proxy_renameat(FsContext *ctx, V9fsPath *olddir, + const char *old_name, V9fsPath *newdir, + const char *new_name) +{ + int ret; + V9fsString old_full_name, new_full_name; + + v9fs_string_init(&old_full_name); + v9fs_string_init(&new_full_name); + + v9fs_string_sprintf(&old_full_name, "%s/%s", olddir->data, old_name); + v9fs_string_sprintf(&new_full_name, "%s/%s", newdir->data, new_name); + + ret = proxy_rename(ctx, old_full_name.data, new_full_name.data); + v9fs_string_free(&old_full_name); + v9fs_string_free(&new_full_name); + return ret; +} + +static int proxy_unlinkat(FsContext *ctx, V9fsPath *dir, + const char *name, int flags) +{ + int ret; + V9fsString fullname; + v9fs_string_init(&fullname); + + v9fs_string_sprintf(&fullname, "%s/%s", dir->data, name); + ret = proxy_remove(ctx, fullname.data); + v9fs_string_free(&fullname); + + return ret; +} + +static int proxy_ioc_getversion(FsContext *fs_ctx, V9fsPath *path, + mode_t st_mode, uint64_t *st_gen) +{ + int err; + + /* Do not try to open special files like device nodes, fifos etc + * we can get fd for regular files and directories only + */ + if (!S_ISREG(st_mode) && !S_ISDIR(st_mode)) { + errno = ENOTTY; + return -1; + } + err = v9fs_request(fs_ctx->private, T_GETVERSION, st_gen, "s", path); + if (err < 0) { + errno = -err; + err = -1; + } + return err; +} + +static int connect_namedsocket(const char *path) +{ + int sockfd, size; + struct sockaddr_un helper; + + if (strlen(path) >= sizeof(helper.sun_path)) { + fprintf(stderr, "Socket name too large\n"); + return -1; + } + sockfd = socket(AF_UNIX, SOCK_STREAM, 0); + if (sockfd < 0) { + fprintf(stderr, "failed to create socket: %s\n", strerror(errno)); + return -1; + } + strcpy(helper.sun_path, path); + helper.sun_family = AF_UNIX; + size = strlen(helper.sun_path) + sizeof(helper.sun_family); + if (connect(sockfd, (struct sockaddr *)&helper, size) < 0) { + fprintf(stderr, "failed to connect to %s: %s\n", path, strerror(errno)); + close(sockfd); + return -1; + } + + /* remove the socket for security reasons */ + unlink(path); + return sockfd; +} + +static int proxy_parse_opts(QemuOpts *opts, struct FsDriverEntry *fs) +{ + const char *socket = qemu_opt_get(opts, "socket"); + const char *sock_fd = qemu_opt_get(opts, "sock_fd"); + + if (!socket && !sock_fd) { + fprintf(stderr, "socket and sock_fd none of the option specified\n"); + return -1; + } + if (socket && sock_fd) { + fprintf(stderr, "Both socket and sock_fd options specified\n"); + return -1; + } + if (socket) { + fs->path = g_strdup(socket); + fs->export_flags = V9FS_PROXY_SOCK_NAME; + } else { + fs->path = g_strdup(sock_fd); + fs->export_flags = V9FS_PROXY_SOCK_FD; + } + return 0; +} + +static int proxy_init(FsContext *ctx) +{ + V9fsProxy *proxy = g_malloc(sizeof(V9fsProxy)); + int sock_id; + + if (ctx->export_flags & V9FS_PROXY_SOCK_NAME) { + sock_id = connect_namedsocket(ctx->fs_root); + } else { + sock_id = atoi(ctx->fs_root); + if (sock_id < 0) { + fprintf(stderr, "socket descriptor not initialized\n"); + } + } + if (sock_id < 0) { + g_free(proxy); + return -1; + } + g_free(ctx->fs_root); + ctx->fs_root = NULL; + + proxy->in_iovec.iov_base = g_malloc(PROXY_MAX_IO_SZ + PROXY_HDR_SZ); + proxy->in_iovec.iov_len = PROXY_MAX_IO_SZ + PROXY_HDR_SZ; + proxy->out_iovec.iov_base = g_malloc(PROXY_MAX_IO_SZ + PROXY_HDR_SZ); + proxy->out_iovec.iov_len = PROXY_MAX_IO_SZ + PROXY_HDR_SZ; + + ctx->private = proxy; + proxy->sockfd = sock_id; + qemu_mutex_init(&proxy->mutex); + + ctx->export_flags |= V9FS_PATHNAME_FSCONTEXT; + ctx->exops.get_st_gen = proxy_ioc_getversion; + return 0; +} + +FileOperations proxy_ops = { + .parse_opts = proxy_parse_opts, + .init = proxy_init, + .lstat = proxy_lstat, + .readlink = proxy_readlink, + .close = proxy_close, + .closedir = proxy_closedir, + .open = proxy_open, + .opendir = proxy_opendir, + .rewinddir = proxy_rewinddir, + .telldir = proxy_telldir, + .readdir_r = proxy_readdir_r, + .seekdir = proxy_seekdir, + .preadv = proxy_preadv, + .pwritev = proxy_pwritev, + .chmod = proxy_chmod, + .mknod = proxy_mknod, + .mkdir = proxy_mkdir, + .fstat = proxy_fstat, + .open2 = proxy_open2, + .symlink = proxy_symlink, + .link = proxy_link, + .truncate = proxy_truncate, + .rename = proxy_rename, + .chown = proxy_chown, + .utimensat = proxy_utimensat, + .remove = proxy_remove, + .fsync = proxy_fsync, + .statfs = proxy_statfs, + .lgetxattr = proxy_lgetxattr, + .llistxattr = proxy_llistxattr, + .lsetxattr = proxy_lsetxattr, + .lremovexattr = proxy_lremovexattr, + .name_to_path = proxy_name_to_path, + .renameat = proxy_renameat, + .unlinkat = proxy_unlinkat, +}; diff --git a/qemu/hw/9pfs/virtio-9p-proxy.h b/qemu/hw/9pfs/virtio-9p-proxy.h new file mode 100644 index 000000000..005c1ad75 --- /dev/null +++ b/qemu/hw/9pfs/virtio-9p-proxy.h @@ -0,0 +1,95 @@ +/* + * Virtio 9p Proxy callback + * + * Copyright IBM, Corp. 2011 + * + * Authors: + * M. Mohan Kumar <mohan@in.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ +#ifndef _QEMU_VIRTIO_9P_PROXY_H +#define _QEMU_VIRTIO_9P_PROXY_H + +#define PROXY_MAX_IO_SZ (64 * 1024) +#define V9FS_FD_VALID INT_MAX + +/* + * proxy iovec only support one element and + * marsha/unmarshal doesn't do little endian conversion. + */ +#define proxy_unmarshal(in_sg, offset, fmt, args...) \ + v9fs_unmarshal(in_sg, 1, offset, 0, fmt, ##args) +#define proxy_marshal(out_sg, offset, fmt, args...) \ + v9fs_marshal(out_sg, 1, offset, 0, fmt, ##args) + +union MsgControl { + struct cmsghdr cmsg; + char control[CMSG_SPACE(sizeof(int))]; +}; + +typedef struct { + uint32_t type; + uint32_t size; +} ProxyHeader; + +#define PROXY_HDR_SZ (sizeof(ProxyHeader)) + +enum { + T_SUCCESS = 0, + T_ERROR, + T_OPEN, + T_CREATE, + T_MKNOD, + T_MKDIR, + T_SYMLINK, + T_LINK, + T_LSTAT, + T_READLINK, + T_STATFS, + T_CHMOD, + T_CHOWN, + T_TRUNCATE, + T_UTIME, + T_RENAME, + T_REMOVE, + T_LGETXATTR, + T_LLISTXATTR, + T_LSETXATTR, + T_LREMOVEXATTR, + T_GETVERSION, +}; + +typedef struct { + uint64_t st_dev; + uint64_t st_ino; + uint64_t st_nlink; + uint32_t st_mode; + uint32_t st_uid; + uint32_t st_gid; + uint64_t st_rdev; + uint64_t st_size; + uint64_t st_blksize; + uint64_t st_blocks; + uint64_t st_atim_sec; + uint64_t st_atim_nsec; + uint64_t st_mtim_sec; + uint64_t st_mtim_nsec; + uint64_t st_ctim_sec; + uint64_t st_ctim_nsec; +} ProxyStat; + +typedef struct { + uint64_t f_type; + uint64_t f_bsize; + uint64_t f_blocks; + uint64_t f_bfree; + uint64_t f_bavail; + uint64_t f_files; + uint64_t f_ffree; + uint64_t f_fsid[2]; + uint64_t f_namelen; + uint64_t f_frsize; +} ProxyStatFS; +#endif diff --git a/qemu/hw/9pfs/virtio-9p-synth.c b/qemu/hw/9pfs/virtio-9p-synth.c new file mode 100644 index 000000000..a0ab9a86a --- /dev/null +++ b/qemu/hw/9pfs/virtio-9p-synth.c @@ -0,0 +1,573 @@ +/* + * Virtio 9p synthetic file system support + * + * Copyright IBM, Corp. 2011 + * + * Authors: + * Malahal Naineni <malahal@us.ibm.com> + * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "hw/virtio/virtio.h" +#include "virtio-9p.h" +#include "virtio-9p-xattr.h" +#include "fsdev/qemu-fsdev.h" +#include "virtio-9p-synth.h" +#include "qemu/rcu.h" +#include "qemu/rcu_queue.h" +#include <sys/stat.h> + +/* Root node for synth file system */ +static V9fsSynthNode v9fs_synth_root = { + .name = "/", + .actual_attr = { + .mode = 0555 | S_IFDIR, + .nlink = 1, + }, + .attr = &v9fs_synth_root.actual_attr, +}; + +static QemuMutex v9fs_synth_mutex; +static int v9fs_synth_node_count; +/* set to 1 when the synth fs is ready */ +static int v9fs_synth_fs; + +static V9fsSynthNode *v9fs_add_dir_node(V9fsSynthNode *parent, int mode, + const char *name, + V9fsSynthNodeAttr *attr, int inode) +{ + V9fsSynthNode *node; + + /* Add directory type and remove write bits */ + mode = ((mode & 0777) | S_IFDIR) & ~(S_IWUSR | S_IWGRP | S_IWOTH); + node = g_malloc0(sizeof(V9fsSynthNode)); + if (attr) { + /* We are adding .. or . entries */ + node->attr = attr; + node->attr->nlink++; + } else { + node->attr = &node->actual_attr; + node->attr->inode = inode; + node->attr->nlink = 1; + /* We don't allow write to directories */ + node->attr->mode = mode; + node->attr->write = NULL; + node->attr->read = NULL; + } + node->private = node; + pstrcpy(node->name, sizeof(node->name), name); + QLIST_INSERT_HEAD_RCU(&parent->child, node, sibling); + return node; +} + +int qemu_v9fs_synth_mkdir(V9fsSynthNode *parent, int mode, + const char *name, V9fsSynthNode **result) +{ + int ret; + V9fsSynthNode *node, *tmp; + + if (!v9fs_synth_fs) { + return EAGAIN; + } + if (!name || (strlen(name) >= NAME_MAX)) { + return EINVAL; + } + if (!parent) { + parent = &v9fs_synth_root; + } + qemu_mutex_lock(&v9fs_synth_mutex); + QLIST_FOREACH(tmp, &parent->child, sibling) { + if (!strcmp(tmp->name, name)) { + ret = EEXIST; + goto err_out; + } + } + /* Add the name */ + node = v9fs_add_dir_node(parent, mode, name, NULL, v9fs_synth_node_count++); + v9fs_add_dir_node(node, parent->attr->mode, "..", + parent->attr, parent->attr->inode); + v9fs_add_dir_node(node, node->attr->mode, ".", + node->attr, node->attr->inode); + *result = node; + ret = 0; +err_out: + qemu_mutex_unlock(&v9fs_synth_mutex); + return ret; +} + +int qemu_v9fs_synth_add_file(V9fsSynthNode *parent, int mode, + const char *name, v9fs_synth_read read, + v9fs_synth_write write, void *arg) +{ + int ret; + V9fsSynthNode *node, *tmp; + + if (!v9fs_synth_fs) { + return EAGAIN; + } + if (!name || (strlen(name) >= NAME_MAX)) { + return EINVAL; + } + if (!parent) { + parent = &v9fs_synth_root; + } + + qemu_mutex_lock(&v9fs_synth_mutex); + QLIST_FOREACH(tmp, &parent->child, sibling) { + if (!strcmp(tmp->name, name)) { + ret = EEXIST; + goto err_out; + } + } + /* Add file type and remove write bits */ + mode = ((mode & 0777) | S_IFREG); + node = g_malloc0(sizeof(V9fsSynthNode)); + node->attr = &node->actual_attr; + node->attr->inode = v9fs_synth_node_count++; + node->attr->nlink = 1; + node->attr->read = read; + node->attr->write = write; + node->attr->mode = mode; + node->private = arg; + pstrcpy(node->name, sizeof(node->name), name); + QLIST_INSERT_HEAD_RCU(&parent->child, node, sibling); + ret = 0; +err_out: + qemu_mutex_unlock(&v9fs_synth_mutex); + return ret; +} + +static void v9fs_synth_fill_statbuf(V9fsSynthNode *node, struct stat *stbuf) +{ + stbuf->st_dev = 0; + stbuf->st_ino = node->attr->inode; + stbuf->st_mode = node->attr->mode; + stbuf->st_nlink = node->attr->nlink; + stbuf->st_uid = 0; + stbuf->st_gid = 0; + stbuf->st_rdev = 0; + stbuf->st_size = 0; + stbuf->st_blksize = 0; + stbuf->st_blocks = 0; + stbuf->st_atime = 0; + stbuf->st_mtime = 0; + stbuf->st_ctime = 0; +} + +static int v9fs_synth_lstat(FsContext *fs_ctx, + V9fsPath *fs_path, struct stat *stbuf) +{ + V9fsSynthNode *node = *(V9fsSynthNode **)fs_path->data; + + v9fs_synth_fill_statbuf(node, stbuf); + return 0; +} + +static int v9fs_synth_fstat(FsContext *fs_ctx, int fid_type, + V9fsFidOpenState *fs, struct stat *stbuf) +{ + V9fsSynthOpenState *synth_open = fs->private; + v9fs_synth_fill_statbuf(synth_open->node, stbuf); + return 0; +} + +static int v9fs_synth_opendir(FsContext *ctx, + V9fsPath *fs_path, V9fsFidOpenState *fs) +{ + V9fsSynthOpenState *synth_open; + V9fsSynthNode *node = *(V9fsSynthNode **)fs_path->data; + + synth_open = g_malloc(sizeof(*synth_open)); + synth_open->node = node; + node->open_count++; + fs->private = synth_open; + return 0; +} + +static int v9fs_synth_closedir(FsContext *ctx, V9fsFidOpenState *fs) +{ + V9fsSynthOpenState *synth_open = fs->private; + V9fsSynthNode *node = synth_open->node; + + node->open_count--; + g_free(synth_open); + fs->private = NULL; + return 0; +} + +static off_t v9fs_synth_telldir(FsContext *ctx, V9fsFidOpenState *fs) +{ + V9fsSynthOpenState *synth_open = fs->private; + return synth_open->offset; +} + +static void v9fs_synth_seekdir(FsContext *ctx, V9fsFidOpenState *fs, off_t off) +{ + V9fsSynthOpenState *synth_open = fs->private; + synth_open->offset = off; +} + +static void v9fs_synth_rewinddir(FsContext *ctx, V9fsFidOpenState *fs) +{ + v9fs_synth_seekdir(ctx, fs, 0); +} + +static void v9fs_synth_direntry(V9fsSynthNode *node, + struct dirent *entry, off_t off) +{ + strcpy(entry->d_name, node->name); + entry->d_ino = node->attr->inode; + entry->d_off = off + 1; +} + +static int v9fs_synth_get_dentry(V9fsSynthNode *dir, struct dirent *entry, + struct dirent **result, off_t off) +{ + int i = 0; + V9fsSynthNode *node; + + rcu_read_lock(); + QLIST_FOREACH(node, &dir->child, sibling) { + /* This is the off child of the directory */ + if (i == off) { + break; + } + i++; + } + rcu_read_unlock(); + if (!node) { + /* end of directory */ + *result = NULL; + return 0; + } + v9fs_synth_direntry(node, entry, off); + *result = entry; + return 0; +} + +static int v9fs_synth_readdir_r(FsContext *ctx, V9fsFidOpenState *fs, + struct dirent *entry, struct dirent **result) +{ + int ret; + V9fsSynthOpenState *synth_open = fs->private; + V9fsSynthNode *node = synth_open->node; + ret = v9fs_synth_get_dentry(node, entry, result, synth_open->offset); + if (!ret && *result != NULL) { + synth_open->offset++; + } + return ret; +} + +static int v9fs_synth_open(FsContext *ctx, V9fsPath *fs_path, + int flags, V9fsFidOpenState *fs) +{ + V9fsSynthOpenState *synth_open; + V9fsSynthNode *node = *(V9fsSynthNode **)fs_path->data; + + synth_open = g_malloc(sizeof(*synth_open)); + synth_open->node = node; + node->open_count++; + fs->private = synth_open; + return 0; +} + +static int v9fs_synth_open2(FsContext *fs_ctx, V9fsPath *dir_path, + const char *name, int flags, + FsCred *credp, V9fsFidOpenState *fs) +{ + errno = ENOSYS; + return -1; +} + +static int v9fs_synth_close(FsContext *ctx, V9fsFidOpenState *fs) +{ + V9fsSynthOpenState *synth_open = fs->private; + V9fsSynthNode *node = synth_open->node; + + node->open_count--; + g_free(synth_open); + fs->private = NULL; + return 0; +} + +static ssize_t v9fs_synth_pwritev(FsContext *ctx, V9fsFidOpenState *fs, + const struct iovec *iov, + int iovcnt, off_t offset) +{ + int i, count = 0, wcount; + V9fsSynthOpenState *synth_open = fs->private; + V9fsSynthNode *node = synth_open->node; + if (!node->attr->write) { + errno = EPERM; + return -1; + } + for (i = 0; i < iovcnt; i++) { + wcount = node->attr->write(iov[i].iov_base, iov[i].iov_len, + offset, node->private); + offset += wcount; + count += wcount; + /* If we wrote less than requested. we are done */ + if (wcount < iov[i].iov_len) { + break; + } + } + return count; +} + +static ssize_t v9fs_synth_preadv(FsContext *ctx, V9fsFidOpenState *fs, + const struct iovec *iov, + int iovcnt, off_t offset) +{ + int i, count = 0, rcount; + V9fsSynthOpenState *synth_open = fs->private; + V9fsSynthNode *node = synth_open->node; + if (!node->attr->read) { + errno = EPERM; + return -1; + } + for (i = 0; i < iovcnt; i++) { + rcount = node->attr->read(iov[i].iov_base, iov[i].iov_len, + offset, node->private); + offset += rcount; + count += rcount; + /* If we read less than requested. we are done */ + if (rcount < iov[i].iov_len) { + break; + } + } + return count; +} + +static int v9fs_synth_truncate(FsContext *ctx, V9fsPath *path, off_t offset) +{ + errno = ENOSYS; + return -1; +} + +static int v9fs_synth_chmod(FsContext *fs_ctx, V9fsPath *path, FsCred *credp) +{ + errno = EPERM; + return -1; +} + +static int v9fs_synth_mknod(FsContext *fs_ctx, V9fsPath *path, + const char *buf, FsCred *credp) +{ + errno = EPERM; + return -1; +} + +static int v9fs_synth_mkdir(FsContext *fs_ctx, V9fsPath *path, + const char *buf, FsCred *credp) +{ + errno = EPERM; + return -1; +} + +static ssize_t v9fs_synth_readlink(FsContext *fs_ctx, V9fsPath *path, + char *buf, size_t bufsz) +{ + errno = ENOSYS; + return -1; +} + +static int v9fs_synth_symlink(FsContext *fs_ctx, const char *oldpath, + V9fsPath *newpath, const char *buf, FsCred *credp) +{ + errno = EPERM; + return -1; +} + +static int v9fs_synth_link(FsContext *fs_ctx, V9fsPath *oldpath, + V9fsPath *newpath, const char *buf) +{ + errno = EPERM; + return -1; +} + +static int v9fs_synth_rename(FsContext *ctx, const char *oldpath, + const char *newpath) +{ + errno = EPERM; + return -1; +} + +static int v9fs_synth_chown(FsContext *fs_ctx, V9fsPath *path, FsCred *credp) +{ + errno = EPERM; + return -1; +} + +static int v9fs_synth_utimensat(FsContext *fs_ctx, V9fsPath *path, + const struct timespec *buf) +{ + errno = EPERM; + return 0; +} + +static int v9fs_synth_remove(FsContext *ctx, const char *path) +{ + errno = EPERM; + return -1; +} + +static int v9fs_synth_fsync(FsContext *ctx, int fid_type, + V9fsFidOpenState *fs, int datasync) +{ + errno = ENOSYS; + return 0; +} + +static int v9fs_synth_statfs(FsContext *s, V9fsPath *fs_path, + struct statfs *stbuf) +{ + stbuf->f_type = 0xABCD; + stbuf->f_bsize = 512; + stbuf->f_blocks = 0; + stbuf->f_files = v9fs_synth_node_count; + stbuf->f_namelen = NAME_MAX; + return 0; +} + +static ssize_t v9fs_synth_lgetxattr(FsContext *ctx, V9fsPath *path, + const char *name, void *value, size_t size) +{ + errno = ENOTSUP; + return -1; +} + +static ssize_t v9fs_synth_llistxattr(FsContext *ctx, V9fsPath *path, + void *value, size_t size) +{ + errno = ENOTSUP; + return -1; +} + +static int v9fs_synth_lsetxattr(FsContext *ctx, V9fsPath *path, + const char *name, void *value, + size_t size, int flags) +{ + errno = ENOTSUP; + return -1; +} + +static int v9fs_synth_lremovexattr(FsContext *ctx, + V9fsPath *path, const char *name) +{ + errno = ENOTSUP; + return -1; +} + +static int v9fs_synth_name_to_path(FsContext *ctx, V9fsPath *dir_path, + const char *name, V9fsPath *target) +{ + V9fsSynthNode *node; + V9fsSynthNode *dir_node; + + /* "." and ".." are not allowed */ + if (!strcmp(name, ".") || !strcmp(name, "..")) { + errno = EINVAL; + return -1; + + } + if (!dir_path) { + dir_node = &v9fs_synth_root; + } else { + dir_node = *(V9fsSynthNode **)dir_path->data; + } + if (!strcmp(name, "/")) { + node = dir_node; + goto out; + } + /* search for the name in the childern */ + rcu_read_lock(); + QLIST_FOREACH(node, &dir_node->child, sibling) { + if (!strcmp(node->name, name)) { + break; + } + } + rcu_read_unlock(); + + if (!node) { + errno = ENOENT; + return -1; + } +out: + /* Copy the node pointer to fid */ + target->data = g_malloc(sizeof(void *)); + memcpy(target->data, &node, sizeof(void *)); + target->size = sizeof(void *); + return 0; +} + +static int v9fs_synth_renameat(FsContext *ctx, V9fsPath *olddir, + const char *old_name, V9fsPath *newdir, + const char *new_name) +{ + errno = EPERM; + return -1; +} + +static int v9fs_synth_unlinkat(FsContext *ctx, V9fsPath *dir, + const char *name, int flags) +{ + errno = EPERM; + return -1; +} + +static int v9fs_synth_init(FsContext *ctx) +{ + QLIST_INIT(&v9fs_synth_root.child); + qemu_mutex_init(&v9fs_synth_mutex); + + /* Add "." and ".." entries for root */ + v9fs_add_dir_node(&v9fs_synth_root, v9fs_synth_root.attr->mode, + "..", v9fs_synth_root.attr, v9fs_synth_root.attr->inode); + v9fs_add_dir_node(&v9fs_synth_root, v9fs_synth_root.attr->mode, + ".", v9fs_synth_root.attr, v9fs_synth_root.attr->inode); + + /* Mark the subsystem is ready for use */ + v9fs_synth_fs = 1; + return 0; +} + +FileOperations synth_ops = { + .init = v9fs_synth_init, + .lstat = v9fs_synth_lstat, + .readlink = v9fs_synth_readlink, + .close = v9fs_synth_close, + .closedir = v9fs_synth_closedir, + .open = v9fs_synth_open, + .opendir = v9fs_synth_opendir, + .rewinddir = v9fs_synth_rewinddir, + .telldir = v9fs_synth_telldir, + .readdir_r = v9fs_synth_readdir_r, + .seekdir = v9fs_synth_seekdir, + .preadv = v9fs_synth_preadv, + .pwritev = v9fs_synth_pwritev, + .chmod = v9fs_synth_chmod, + .mknod = v9fs_synth_mknod, + .mkdir = v9fs_synth_mkdir, + .fstat = v9fs_synth_fstat, + .open2 = v9fs_synth_open2, + .symlink = v9fs_synth_symlink, + .link = v9fs_synth_link, + .truncate = v9fs_synth_truncate, + .rename = v9fs_synth_rename, + .chown = v9fs_synth_chown, + .utimensat = v9fs_synth_utimensat, + .remove = v9fs_synth_remove, + .fsync = v9fs_synth_fsync, + .statfs = v9fs_synth_statfs, + .lgetxattr = v9fs_synth_lgetxattr, + .llistxattr = v9fs_synth_llistxattr, + .lsetxattr = v9fs_synth_lsetxattr, + .lremovexattr = v9fs_synth_lremovexattr, + .name_to_path = v9fs_synth_name_to_path, + .renameat = v9fs_synth_renameat, + .unlinkat = v9fs_synth_unlinkat, +}; diff --git a/qemu/hw/9pfs/virtio-9p-synth.h b/qemu/hw/9pfs/virtio-9p-synth.h new file mode 100644 index 000000000..ab05a8e78 --- /dev/null +++ b/qemu/hw/9pfs/virtio-9p-synth.h @@ -0,0 +1,54 @@ +/* + * Virtio 9p + * + * Copyright IBM, Corp. 2011 + * + * Authors: + * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ +#ifndef HW_9PFS_VIRTIO9P_SYNTH_H +#define HW_9PFS_VIRTIO9P_SYNTH_H 1 + +#include <unistd.h> +#include <sys/types.h> +#include <limits.h> + +typedef struct V9fsSynthNode V9fsSynthNode; +typedef ssize_t (*v9fs_synth_read)(void *buf, int len, off_t offset, + void *arg); +typedef ssize_t (*v9fs_synth_write)(void *buf, int len, off_t offset, + void *arg); +typedef struct V9fsSynthNodeAttr { + int mode; + int inode; + int nlink; + v9fs_synth_read read; + v9fs_synth_write write; +} V9fsSynthNodeAttr; + +struct V9fsSynthNode { + QLIST_HEAD(, V9fsSynthNode) child; + QLIST_ENTRY(V9fsSynthNode) sibling; + char name[NAME_MAX]; + V9fsSynthNodeAttr *attr; + V9fsSynthNodeAttr actual_attr; + void *private; + int open_count; +}; + +typedef struct V9fsSynthOpenState { + off_t offset; + V9fsSynthNode *node; +} V9fsSynthOpenState; + +extern int qemu_v9fs_synth_mkdir(V9fsSynthNode *parent, int mode, + const char *name, V9fsSynthNode **result); +extern int qemu_v9fs_synth_add_file(V9fsSynthNode *parent, int mode, + const char *name, v9fs_synth_read read, + v9fs_synth_write write, void *arg); + +#endif diff --git a/qemu/hw/9pfs/virtio-9p-xattr-user.c b/qemu/hw/9pfs/virtio-9p-xattr-user.c new file mode 100644 index 000000000..46133e06d --- /dev/null +++ b/qemu/hw/9pfs/virtio-9p-xattr-user.c @@ -0,0 +1,128 @@ +/* + * Virtio 9p user. xattr callback + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include <sys/types.h> +#include "hw/virtio/virtio.h" +#include "virtio-9p.h" +#include "fsdev/file-op-9p.h" +#include "virtio-9p-xattr.h" + + +static ssize_t mp_user_getxattr(FsContext *ctx, const char *path, + const char *name, void *value, size_t size) +{ + char *buffer; + ssize_t ret; + + if (strncmp(name, "user.virtfs.", 12) == 0) { + /* + * Don't allow fetch of user.virtfs namesapce + * in case of mapped security + */ + errno = ENOATTR; + return -1; + } + buffer = rpath(ctx, path); + ret = lgetxattr(buffer, name, value, size); + g_free(buffer); + return ret; +} + +static ssize_t mp_user_listxattr(FsContext *ctx, const char *path, + char *name, void *value, size_t size) +{ + int name_size = strlen(name) + 1; + if (strncmp(name, "user.virtfs.", 12) == 0) { + + /* check if it is a mapped posix acl */ + if (strncmp(name, "user.virtfs.system.posix_acl_", 29) == 0) { + /* adjust the name and size */ + name += 12; + name_size -= 12; + } else { + /* + * Don't allow fetch of user.virtfs namesapce + * in case of mapped security + */ + return 0; + } + } + if (!value) { + return name_size; + } + + if (size < name_size) { + errno = ERANGE; + return -1; + } + + /* name_size includes the trailing NUL. */ + memcpy(value, name, name_size); + return name_size; +} + +static int mp_user_setxattr(FsContext *ctx, const char *path, const char *name, + void *value, size_t size, int flags) +{ + char *buffer; + int ret; + + if (strncmp(name, "user.virtfs.", 12) == 0) { + /* + * Don't allow fetch of user.virtfs namesapce + * in case of mapped security + */ + errno = EACCES; + return -1; + } + buffer = rpath(ctx, path); + ret = lsetxattr(buffer, name, value, size, flags); + g_free(buffer); + return ret; +} + +static int mp_user_removexattr(FsContext *ctx, + const char *path, const char *name) +{ + char *buffer; + int ret; + + if (strncmp(name, "user.virtfs.", 12) == 0) { + /* + * Don't allow fetch of user.virtfs namesapce + * in case of mapped security + */ + errno = EACCES; + return -1; + } + buffer = rpath(ctx, path); + ret = lremovexattr(buffer, name); + g_free(buffer); + return ret; +} + +XattrOperations mapped_user_xattr = { + .name = "user.", + .getxattr = mp_user_getxattr, + .setxattr = mp_user_setxattr, + .listxattr = mp_user_listxattr, + .removexattr = mp_user_removexattr, +}; + +XattrOperations passthrough_user_xattr = { + .name = "user.", + .getxattr = pt_getxattr, + .setxattr = pt_setxattr, + .listxattr = pt_listxattr, + .removexattr = pt_removexattr, +}; diff --git a/qemu/hw/9pfs/virtio-9p-xattr.c b/qemu/hw/9pfs/virtio-9p-xattr.c new file mode 100644 index 000000000..07183887c --- /dev/null +++ b/qemu/hw/9pfs/virtio-9p-xattr.c @@ -0,0 +1,164 @@ +/* + * Virtio 9p xattr callback + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "hw/virtio/virtio.h" +#include "virtio-9p.h" +#include "fsdev/file-op-9p.h" +#include "virtio-9p-xattr.h" + + +static XattrOperations *get_xattr_operations(XattrOperations **h, + const char *name) +{ + XattrOperations *xops; + for (xops = *(h)++; xops != NULL; xops = *(h)++) { + if (!strncmp(name, xops->name, strlen(xops->name))) { + return xops; + } + } + return NULL; +} + +ssize_t v9fs_get_xattr(FsContext *ctx, const char *path, + const char *name, void *value, size_t size) +{ + XattrOperations *xops = get_xattr_operations(ctx->xops, name); + if (xops) { + return xops->getxattr(ctx, path, name, value, size); + } + errno = EOPNOTSUPP; + return -1; +} + +ssize_t pt_listxattr(FsContext *ctx, const char *path, + char *name, void *value, size_t size) +{ + int name_size = strlen(name) + 1; + if (!value) { + return name_size; + } + + if (size < name_size) { + errno = ERANGE; + return -1; + } + + /* no need for strncpy: name_size is strlen(name)+1 */ + memcpy(value, name, name_size); + return name_size; +} + + +/* + * Get the list and pass to each layer to find out whether + * to send the data or not + */ +ssize_t v9fs_list_xattr(FsContext *ctx, const char *path, + void *value, size_t vsize) +{ + ssize_t size = 0; + char *buffer; + void *ovalue = value; + XattrOperations *xops; + char *orig_value, *orig_value_start; + ssize_t xattr_len, parsed_len = 0, attr_len; + + /* Get the actual len */ + buffer = rpath(ctx, path); + xattr_len = llistxattr(buffer, value, 0); + if (xattr_len <= 0) { + g_free(buffer); + return xattr_len; + } + + /* Now fetch the xattr and find the actual size */ + orig_value = g_malloc(xattr_len); + xattr_len = llistxattr(buffer, orig_value, xattr_len); + g_free(buffer); + + /* store the orig pointer */ + orig_value_start = orig_value; + while (xattr_len > parsed_len) { + xops = get_xattr_operations(ctx->xops, orig_value); + if (!xops) { + goto next_entry; + } + + if (!value) { + size += xops->listxattr(ctx, path, orig_value, value, vsize); + } else { + size = xops->listxattr(ctx, path, orig_value, value, vsize); + if (size < 0) { + goto err_out; + } + value += size; + vsize -= size; + } +next_entry: + /* Got the next entry */ + attr_len = strlen(orig_value) + 1; + parsed_len += attr_len; + orig_value += attr_len; + } + if (value) { + size = value - ovalue; + } + +err_out: + g_free(orig_value_start); + return size; +} + +int v9fs_set_xattr(FsContext *ctx, const char *path, const char *name, + void *value, size_t size, int flags) +{ + XattrOperations *xops = get_xattr_operations(ctx->xops, name); + if (xops) { + return xops->setxattr(ctx, path, name, value, size, flags); + } + errno = EOPNOTSUPP; + return -1; + +} + +int v9fs_remove_xattr(FsContext *ctx, + const char *path, const char *name) +{ + XattrOperations *xops = get_xattr_operations(ctx->xops, name); + if (xops) { + return xops->removexattr(ctx, path, name); + } + errno = EOPNOTSUPP; + return -1; + +} + +XattrOperations *mapped_xattr_ops[] = { + &mapped_user_xattr, + &mapped_pacl_xattr, + &mapped_dacl_xattr, + NULL, +}; + +XattrOperations *passthrough_xattr_ops[] = { + &passthrough_user_xattr, + &passthrough_acl_xattr, + NULL, +}; + +/* for .user none model should be same as passthrough */ +XattrOperations *none_xattr_ops[] = { + &passthrough_user_xattr, + &none_acl_xattr, + NULL, +}; diff --git a/qemu/hw/9pfs/virtio-9p-xattr.h b/qemu/hw/9pfs/virtio-9p-xattr.h new file mode 100644 index 000000000..327b32b5a --- /dev/null +++ b/qemu/hw/9pfs/virtio-9p-xattr.h @@ -0,0 +1,120 @@ +/* + * Virtio 9p + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ +#ifndef _QEMU_VIRTIO_9P_XATTR_H +#define _QEMU_VIRTIO_9P_XATTR_H + +#include "qemu/xattr.h" + +typedef struct xattr_operations +{ + const char *name; + ssize_t (*getxattr)(FsContext *ctx, const char *path, + const char *name, void *value, size_t size); + ssize_t (*listxattr)(FsContext *ctx, const char *path, + char *name, void *value, size_t size); + int (*setxattr)(FsContext *ctx, const char *path, const char *name, + void *value, size_t size, int flags); + int (*removexattr)(FsContext *ctx, + const char *path, const char *name); +} XattrOperations; + + +extern XattrOperations mapped_user_xattr; +extern XattrOperations passthrough_user_xattr; + +extern XattrOperations mapped_pacl_xattr; +extern XattrOperations mapped_dacl_xattr; +extern XattrOperations passthrough_acl_xattr; +extern XattrOperations none_acl_xattr; + +extern XattrOperations *mapped_xattr_ops[]; +extern XattrOperations *passthrough_xattr_ops[]; +extern XattrOperations *none_xattr_ops[]; + +ssize_t v9fs_get_xattr(FsContext *ctx, const char *path, const char *name, + void *value, size_t size); +ssize_t v9fs_list_xattr(FsContext *ctx, const char *path, void *value, + size_t vsize); +int v9fs_set_xattr(FsContext *ctx, const char *path, const char *name, + void *value, size_t size, int flags); +int v9fs_remove_xattr(FsContext *ctx, const char *path, const char *name); +ssize_t pt_listxattr(FsContext *ctx, const char *path, char *name, void *value, + size_t size); + +static inline ssize_t pt_getxattr(FsContext *ctx, const char *path, + const char *name, void *value, size_t size) +{ + char *buffer; + ssize_t ret; + + buffer = rpath(ctx, path); + ret = lgetxattr(buffer, name, value, size); + g_free(buffer); + return ret; +} + +static inline int pt_setxattr(FsContext *ctx, const char *path, + const char *name, void *value, + size_t size, int flags) +{ + char *buffer; + int ret; + + buffer = rpath(ctx, path); + ret = lsetxattr(buffer, name, value, size, flags); + g_free(buffer); + return ret; +} + +static inline int pt_removexattr(FsContext *ctx, + const char *path, const char *name) +{ + char *buffer; + int ret; + + buffer = rpath(ctx, path); + ret = lremovexattr(path, name); + g_free(buffer); + return ret; +} + +static inline ssize_t notsup_getxattr(FsContext *ctx, const char *path, + const char *name, void *value, + size_t size) +{ + errno = ENOTSUP; + return -1; +} + +static inline int notsup_setxattr(FsContext *ctx, const char *path, + const char *name, void *value, + size_t size, int flags) +{ + errno = ENOTSUP; + return -1; +} + +static inline ssize_t notsup_listxattr(FsContext *ctx, const char *path, + char *name, void *value, size_t size) +{ + return 0; +} + +static inline int notsup_removexattr(FsContext *ctx, + const char *path, const char *name) +{ + errno = ENOTSUP; + return -1; +} + +#endif diff --git a/qemu/hw/9pfs/virtio-9p.c b/qemu/hw/9pfs/virtio-9p.c new file mode 100644 index 000000000..f972731f5 --- /dev/null +++ b/qemu/hw/9pfs/virtio-9p.c @@ -0,0 +1,3300 @@ +/* + * Virtio 9p backend + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "hw/virtio/virtio.h" +#include "hw/i386/pc.h" +#include "qemu/error-report.h" +#include "qemu/iov.h" +#include "qemu/sockets.h" +#include "virtio-9p.h" +#include "fsdev/qemu-fsdev.h" +#include "virtio-9p-xattr.h" +#include "virtio-9p-coth.h" +#include "trace.h" +#include "migration/migration.h" + +int open_fd_hw; +int total_open_fd; +static int open_fd_rc; + +enum { + Oread = 0x00, + Owrite = 0x01, + Ordwr = 0x02, + Oexec = 0x03, + Oexcl = 0x04, + Otrunc = 0x10, + Orexec = 0x20, + Orclose = 0x40, + Oappend = 0x80, +}; + +static int omode_to_uflags(int8_t mode) +{ + int ret = 0; + + switch (mode & 3) { + case Oread: + ret = O_RDONLY; + break; + case Ordwr: + ret = O_RDWR; + break; + case Owrite: + ret = O_WRONLY; + break; + case Oexec: + ret = O_RDONLY; + break; + } + + if (mode & Otrunc) { + ret |= O_TRUNC; + } + + if (mode & Oappend) { + ret |= O_APPEND; + } + + if (mode & Oexcl) { + ret |= O_EXCL; + } + + return ret; +} + +struct dotl_openflag_map { + int dotl_flag; + int open_flag; +}; + +static int dotl_to_open_flags(int flags) +{ + int i; + /* + * We have same bits for P9_DOTL_READONLY, P9_DOTL_WRONLY + * and P9_DOTL_NOACCESS + */ + int oflags = flags & O_ACCMODE; + + struct dotl_openflag_map dotl_oflag_map[] = { + { P9_DOTL_CREATE, O_CREAT }, + { P9_DOTL_EXCL, O_EXCL }, + { P9_DOTL_NOCTTY , O_NOCTTY }, + { P9_DOTL_TRUNC, O_TRUNC }, + { P9_DOTL_APPEND, O_APPEND }, + { P9_DOTL_NONBLOCK, O_NONBLOCK } , + { P9_DOTL_DSYNC, O_DSYNC }, + { P9_DOTL_FASYNC, FASYNC }, + { P9_DOTL_DIRECT, O_DIRECT }, + { 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 }, + }; + + for (i = 0; i < ARRAY_SIZE(dotl_oflag_map); i++) { + if (flags & dotl_oflag_map[i].dotl_flag) { + oflags |= dotl_oflag_map[i].open_flag; + } + } + + return oflags; +} + +void cred_init(FsCred *credp) +{ + credp->fc_uid = -1; + credp->fc_gid = -1; + credp->fc_mode = -1; + credp->fc_rdev = -1; +} + +static int get_dotl_openflags(V9fsState *s, int oflags) +{ + int flags; + /* + * Filter the client open flags + */ + flags = dotl_to_open_flags(oflags); + flags &= ~(O_NOCTTY | O_ASYNC | O_CREAT); + /* + * Ignore direct disk access hint until the server supports it. + */ + flags &= ~O_DIRECT; + return flags; +} + +void v9fs_path_init(V9fsPath *path) +{ + path->data = NULL; + path->size = 0; +} + +void v9fs_path_free(V9fsPath *path) +{ + g_free(path->data); + path->data = NULL; + path->size = 0; +} + +void v9fs_path_copy(V9fsPath *lhs, V9fsPath *rhs) +{ + v9fs_path_free(lhs); + lhs->data = g_malloc(rhs->size); + memcpy(lhs->data, rhs->data, rhs->size); + lhs->size = rhs->size; +} + +int v9fs_name_to_path(V9fsState *s, V9fsPath *dirpath, + const char *name, V9fsPath *path) +{ + int err; + err = s->ops->name_to_path(&s->ctx, dirpath, name, path); + if (err < 0) { + err = -errno; + } + return err; +} + +/* + * Return TRUE if s1 is an ancestor of s2. + * + * E.g. "a/b" is an ancestor of "a/b/c" but not of "a/bc/d". + * As a special case, We treat s1 as ancestor of s2 if they are same! + */ +static int v9fs_path_is_ancestor(V9fsPath *s1, V9fsPath *s2) +{ + if (!strncmp(s1->data, s2->data, s1->size - 1)) { + if (s2->data[s1->size - 1] == '\0' || s2->data[s1->size - 1] == '/') { + return 1; + } + } + return 0; +} + +static size_t v9fs_string_size(V9fsString *str) +{ + return str->size; +} + +/* + * returns 0 if fid got re-opened, 1 if not, < 0 on error */ +static int v9fs_reopen_fid(V9fsPDU *pdu, V9fsFidState *f) +{ + int err = 1; + if (f->fid_type == P9_FID_FILE) { + if (f->fs.fd == -1) { + do { + err = v9fs_co_open(pdu, f, f->open_flags); + } while (err == -EINTR && !pdu->cancelled); + } + } else if (f->fid_type == P9_FID_DIR) { + if (f->fs.dir == NULL) { + do { + err = v9fs_co_opendir(pdu, f); + } while (err == -EINTR && !pdu->cancelled); + } + } + return err; +} + +static V9fsFidState *get_fid(V9fsPDU *pdu, int32_t fid) +{ + int err; + V9fsFidState *f; + V9fsState *s = pdu->s; + + for (f = s->fid_list; f; f = f->next) { + BUG_ON(f->clunked); + if (f->fid == fid) { + /* + * Update the fid ref upfront so that + * we don't get reclaimed when we yield + * in open later. + */ + f->ref++; + /* + * check whether we need to reopen the + * file. We might have closed the fd + * while trying to free up some file + * descriptors. + */ + err = v9fs_reopen_fid(pdu, f); + if (err < 0) { + f->ref--; + return NULL; + } + /* + * Mark the fid as referenced so that the LRU + * reclaim won't close the file descriptor + */ + f->flags |= FID_REFERENCED; + return f; + } + } + return NULL; +} + +static V9fsFidState *alloc_fid(V9fsState *s, int32_t fid) +{ + V9fsFidState *f; + + for (f = s->fid_list; f; f = f->next) { + /* If fid is already there return NULL */ + BUG_ON(f->clunked); + if (f->fid == fid) { + return NULL; + } + } + f = g_malloc0(sizeof(V9fsFidState)); + f->fid = fid; + f->fid_type = P9_FID_NONE; + f->ref = 1; + /* + * Mark the fid as referenced so that the LRU + * reclaim won't close the file descriptor + */ + f->flags |= FID_REFERENCED; + f->next = s->fid_list; + s->fid_list = f; + + return f; +} + +static int v9fs_xattr_fid_clunk(V9fsPDU *pdu, V9fsFidState *fidp) +{ + int retval = 0; + + if (fidp->fs.xattr.copied_len == -1) { + /* getxattr/listxattr fid */ + goto free_value; + } + /* + * if this is fid for setxattr. clunk should + * result in setxattr localcall + */ + if (fidp->fs.xattr.len != fidp->fs.xattr.copied_len) { + /* clunk after partial write */ + retval = -EINVAL; + goto free_out; + } + if (fidp->fs.xattr.len) { + retval = v9fs_co_lsetxattr(pdu, &fidp->path, &fidp->fs.xattr.name, + fidp->fs.xattr.value, + fidp->fs.xattr.len, + fidp->fs.xattr.flags); + } else { + retval = v9fs_co_lremovexattr(pdu, &fidp->path, &fidp->fs.xattr.name); + } +free_out: + v9fs_string_free(&fidp->fs.xattr.name); +free_value: + g_free(fidp->fs.xattr.value); + return retval; +} + +static int free_fid(V9fsPDU *pdu, V9fsFidState *fidp) +{ + int retval = 0; + + if (fidp->fid_type == P9_FID_FILE) { + /* If we reclaimed the fd no need to close */ + if (fidp->fs.fd != -1) { + retval = v9fs_co_close(pdu, &fidp->fs); + } + } else if (fidp->fid_type == P9_FID_DIR) { + if (fidp->fs.dir != NULL) { + retval = v9fs_co_closedir(pdu, &fidp->fs); + } + } else if (fidp->fid_type == P9_FID_XATTR) { + retval = v9fs_xattr_fid_clunk(pdu, fidp); + } + v9fs_path_free(&fidp->path); + g_free(fidp); + return retval; +} + +static int put_fid(V9fsPDU *pdu, V9fsFidState *fidp) +{ + BUG_ON(!fidp->ref); + fidp->ref--; + /* + * Don't free the fid if it is in reclaim list + */ + if (!fidp->ref && fidp->clunked) { + if (fidp->fid == pdu->s->root_fid) { + /* + * if the clunked fid is root fid then we + * have unmounted the fs on the client side. + * delete the migration blocker. Ideally, this + * should be hooked to transport close notification + */ + if (pdu->s->migration_blocker) { + migrate_del_blocker(pdu->s->migration_blocker); + error_free(pdu->s->migration_blocker); + pdu->s->migration_blocker = NULL; + } + } + return free_fid(pdu, fidp); + } + return 0; +} + +static V9fsFidState *clunk_fid(V9fsState *s, int32_t fid) +{ + V9fsFidState **fidpp, *fidp; + + for (fidpp = &s->fid_list; *fidpp; fidpp = &(*fidpp)->next) { + if ((*fidpp)->fid == fid) { + break; + } + } + if (*fidpp == NULL) { + return NULL; + } + fidp = *fidpp; + *fidpp = fidp->next; + fidp->clunked = 1; + return fidp; +} + +void v9fs_reclaim_fd(V9fsPDU *pdu) +{ + int reclaim_count = 0; + V9fsState *s = pdu->s; + V9fsFidState *f, *reclaim_list = NULL; + + for (f = s->fid_list; f; f = f->next) { + /* + * Unlink fids cannot be reclaimed. Check + * for them and skip them. Also skip fids + * currently being operated on. + */ + if (f->ref || f->flags & FID_NON_RECLAIMABLE) { + continue; + } + /* + * if it is a recently referenced fid + * we leave the fid untouched and clear the + * reference bit. We come back to it later + * in the next iteration. (a simple LRU without + * moving list elements around) + */ + if (f->flags & FID_REFERENCED) { + f->flags &= ~FID_REFERENCED; + continue; + } + /* + * Add fids to reclaim list. + */ + if (f->fid_type == P9_FID_FILE) { + if (f->fs.fd != -1) { + /* + * Up the reference count so that + * a clunk request won't free this fid + */ + f->ref++; + f->rclm_lst = reclaim_list; + reclaim_list = f; + f->fs_reclaim.fd = f->fs.fd; + f->fs.fd = -1; + reclaim_count++; + } + } else if (f->fid_type == P9_FID_DIR) { + if (f->fs.dir != NULL) { + /* + * Up the reference count so that + * a clunk request won't free this fid + */ + f->ref++; + f->rclm_lst = reclaim_list; + reclaim_list = f; + f->fs_reclaim.dir = f->fs.dir; + f->fs.dir = NULL; + reclaim_count++; + } + } + if (reclaim_count >= open_fd_rc) { + break; + } + } + /* + * Now close the fid in reclaim list. Free them if they + * are already clunked. + */ + while (reclaim_list) { + f = reclaim_list; + reclaim_list = f->rclm_lst; + if (f->fid_type == P9_FID_FILE) { + v9fs_co_close(pdu, &f->fs_reclaim); + } else if (f->fid_type == P9_FID_DIR) { + v9fs_co_closedir(pdu, &f->fs_reclaim); + } + f->rclm_lst = NULL; + /* + * Now drop the fid reference, free it + * if clunked. + */ + put_fid(pdu, f); + } +} + +static int v9fs_mark_fids_unreclaim(V9fsPDU *pdu, V9fsPath *path) +{ + int err; + V9fsState *s = pdu->s; + V9fsFidState *fidp, head_fid; + + head_fid.next = s->fid_list; + for (fidp = s->fid_list; fidp; fidp = fidp->next) { + if (fidp->path.size != path->size) { + continue; + } + if (!memcmp(fidp->path.data, path->data, path->size)) { + /* Mark the fid non reclaimable. */ + fidp->flags |= FID_NON_RECLAIMABLE; + + /* reopen the file/dir if already closed */ + err = v9fs_reopen_fid(pdu, fidp); + if (err < 0) { + return -1; + } + /* + * Go back to head of fid list because + * the list could have got updated when + * switched to the worker thread + */ + if (err == 0) { + fidp = &head_fid; + } + } + } + return 0; +} + +static void virtfs_reset(V9fsPDU *pdu) +{ + V9fsState *s = pdu->s; + V9fsFidState *fidp = NULL; + + /* Free all fids */ + while (s->fid_list) { + fidp = s->fid_list; + s->fid_list = fidp->next; + + if (fidp->ref) { + fidp->clunked = 1; + } else { + free_fid(pdu, fidp); + } + } + if (fidp) { + /* One or more unclunked fids found... */ + error_report("9pfs:%s: One or more uncluncked fids " + "found during reset", __func__); + } +} + +#define P9_QID_TYPE_DIR 0x80 +#define P9_QID_TYPE_SYMLINK 0x02 + +#define P9_STAT_MODE_DIR 0x80000000 +#define P9_STAT_MODE_APPEND 0x40000000 +#define P9_STAT_MODE_EXCL 0x20000000 +#define P9_STAT_MODE_MOUNT 0x10000000 +#define P9_STAT_MODE_AUTH 0x08000000 +#define P9_STAT_MODE_TMP 0x04000000 +#define P9_STAT_MODE_SYMLINK 0x02000000 +#define P9_STAT_MODE_LINK 0x01000000 +#define P9_STAT_MODE_DEVICE 0x00800000 +#define P9_STAT_MODE_NAMED_PIPE 0x00200000 +#define P9_STAT_MODE_SOCKET 0x00100000 +#define P9_STAT_MODE_SETUID 0x00080000 +#define P9_STAT_MODE_SETGID 0x00040000 +#define P9_STAT_MODE_SETVTX 0x00010000 + +#define P9_STAT_MODE_TYPE_BITS (P9_STAT_MODE_DIR | \ + P9_STAT_MODE_SYMLINK | \ + P9_STAT_MODE_LINK | \ + P9_STAT_MODE_DEVICE | \ + P9_STAT_MODE_NAMED_PIPE | \ + P9_STAT_MODE_SOCKET) + +/* This is the algorithm from ufs in spfs */ +static void stat_to_qid(const struct stat *stbuf, V9fsQID *qidp) +{ + size_t size; + + memset(&qidp->path, 0, sizeof(qidp->path)); + size = MIN(sizeof(stbuf->st_ino), sizeof(qidp->path)); + memcpy(&qidp->path, &stbuf->st_ino, size); + qidp->version = stbuf->st_mtime ^ (stbuf->st_size << 8); + qidp->type = 0; + if (S_ISDIR(stbuf->st_mode)) { + qidp->type |= P9_QID_TYPE_DIR; + } + if (S_ISLNK(stbuf->st_mode)) { + qidp->type |= P9_QID_TYPE_SYMLINK; + } +} + +static int fid_to_qid(V9fsPDU *pdu, V9fsFidState *fidp, V9fsQID *qidp) +{ + struct stat stbuf; + int err; + + err = v9fs_co_lstat(pdu, &fidp->path, &stbuf); + if (err < 0) { + return err; + } + stat_to_qid(&stbuf, qidp); + return 0; +} + +static V9fsPDU *alloc_pdu(V9fsState *s) +{ + V9fsPDU *pdu = NULL; + + if (!QLIST_EMPTY(&s->free_list)) { + pdu = QLIST_FIRST(&s->free_list); + QLIST_REMOVE(pdu, next); + QLIST_INSERT_HEAD(&s->active_list, pdu, next); + } + return pdu; +} + +static void free_pdu(V9fsState *s, V9fsPDU *pdu) +{ + if (pdu) { + /* + * Cancelled pdu are added back to the freelist + * by flush request . + */ + if (!pdu->cancelled) { + QLIST_REMOVE(pdu, next); + QLIST_INSERT_HEAD(&s->free_list, pdu, next); + } + } +} + +/* + * We don't do error checking for pdu_marshal/unmarshal here + * because we always expect to have enough space to encode + * error details + */ +static void complete_pdu(V9fsState *s, V9fsPDU *pdu, ssize_t len) +{ + int8_t id = pdu->id + 1; /* Response */ + + if (len < 0) { + int err = -len; + len = 7; + + if (s->proto_version != V9FS_PROTO_2000L) { + V9fsString str; + + str.data = strerror(err); + str.size = strlen(str.data); + + len += pdu_marshal(pdu, len, "s", &str); + id = P9_RERROR; + } + + len += pdu_marshal(pdu, len, "d", err); + + if (s->proto_version == V9FS_PROTO_2000L) { + id = P9_RLERROR; + } + trace_v9fs_rerror(pdu->tag, pdu->id, err); /* Trace ERROR */ + } + + /* fill out the header */ + pdu_marshal(pdu, 0, "dbw", (int32_t)len, id, pdu->tag); + + /* keep these in sync */ + pdu->size = len; + pdu->id = id; + + /* push onto queue and notify */ + virtqueue_push(s->vq, &pdu->elem, len); + + /* FIXME: we should batch these completions */ + virtio_notify(VIRTIO_DEVICE(s), s->vq); + + /* Now wakeup anybody waiting in flush for this request */ + qemu_co_queue_next(&pdu->complete); + + free_pdu(s, pdu); +} + +static mode_t v9mode_to_mode(uint32_t mode, V9fsString *extension) +{ + mode_t ret; + + ret = mode & 0777; + if (mode & P9_STAT_MODE_DIR) { + ret |= S_IFDIR; + } + + if (mode & P9_STAT_MODE_SYMLINK) { + ret |= S_IFLNK; + } + if (mode & P9_STAT_MODE_SOCKET) { + ret |= S_IFSOCK; + } + if (mode & P9_STAT_MODE_NAMED_PIPE) { + ret |= S_IFIFO; + } + if (mode & P9_STAT_MODE_DEVICE) { + if (extension->size && extension->data[0] == 'c') { + ret |= S_IFCHR; + } else { + ret |= S_IFBLK; + } + } + + if (!(ret&~0777)) { + ret |= S_IFREG; + } + + if (mode & P9_STAT_MODE_SETUID) { + ret |= S_ISUID; + } + if (mode & P9_STAT_MODE_SETGID) { + ret |= S_ISGID; + } + if (mode & P9_STAT_MODE_SETVTX) { + ret |= S_ISVTX; + } + + return ret; +} + +static int donttouch_stat(V9fsStat *stat) +{ + if (stat->type == -1 && + stat->dev == -1 && + stat->qid.type == -1 && + stat->qid.version == -1 && + stat->qid.path == -1 && + stat->mode == -1 && + stat->atime == -1 && + stat->mtime == -1 && + stat->length == -1 && + !stat->name.size && + !stat->uid.size && + !stat->gid.size && + !stat->muid.size && + stat->n_uid == -1 && + stat->n_gid == -1 && + stat->n_muid == -1) { + return 1; + } + + return 0; +} + +static void v9fs_stat_init(V9fsStat *stat) +{ + v9fs_string_init(&stat->name); + v9fs_string_init(&stat->uid); + v9fs_string_init(&stat->gid); + v9fs_string_init(&stat->muid); + v9fs_string_init(&stat->extension); +} + +static void v9fs_stat_free(V9fsStat *stat) +{ + v9fs_string_free(&stat->name); + v9fs_string_free(&stat->uid); + v9fs_string_free(&stat->gid); + v9fs_string_free(&stat->muid); + v9fs_string_free(&stat->extension); +} + +static uint32_t stat_to_v9mode(const struct stat *stbuf) +{ + uint32_t mode; + + mode = stbuf->st_mode & 0777; + if (S_ISDIR(stbuf->st_mode)) { + mode |= P9_STAT_MODE_DIR; + } + + if (S_ISLNK(stbuf->st_mode)) { + mode |= P9_STAT_MODE_SYMLINK; + } + + if (S_ISSOCK(stbuf->st_mode)) { + mode |= P9_STAT_MODE_SOCKET; + } + + if (S_ISFIFO(stbuf->st_mode)) { + mode |= P9_STAT_MODE_NAMED_PIPE; + } + + if (S_ISBLK(stbuf->st_mode) || S_ISCHR(stbuf->st_mode)) { + mode |= P9_STAT_MODE_DEVICE; + } + + if (stbuf->st_mode & S_ISUID) { + mode |= P9_STAT_MODE_SETUID; + } + + if (stbuf->st_mode & S_ISGID) { + mode |= P9_STAT_MODE_SETGID; + } + + if (stbuf->st_mode & S_ISVTX) { + mode |= P9_STAT_MODE_SETVTX; + } + + return mode; +} + +static int stat_to_v9stat(V9fsPDU *pdu, V9fsPath *name, + const struct stat *stbuf, + V9fsStat *v9stat) +{ + int err; + const char *str; + + memset(v9stat, 0, sizeof(*v9stat)); + + stat_to_qid(stbuf, &v9stat->qid); + v9stat->mode = stat_to_v9mode(stbuf); + v9stat->atime = stbuf->st_atime; + v9stat->mtime = stbuf->st_mtime; + v9stat->length = stbuf->st_size; + + v9fs_string_null(&v9stat->uid); + v9fs_string_null(&v9stat->gid); + v9fs_string_null(&v9stat->muid); + + v9stat->n_uid = stbuf->st_uid; + v9stat->n_gid = stbuf->st_gid; + v9stat->n_muid = 0; + + v9fs_string_null(&v9stat->extension); + + if (v9stat->mode & P9_STAT_MODE_SYMLINK) { + err = v9fs_co_readlink(pdu, name, &v9stat->extension); + if (err < 0) { + return err; + } + } else if (v9stat->mode & P9_STAT_MODE_DEVICE) { + v9fs_string_sprintf(&v9stat->extension, "%c %u %u", + S_ISCHR(stbuf->st_mode) ? 'c' : 'b', + major(stbuf->st_rdev), minor(stbuf->st_rdev)); + } else if (S_ISDIR(stbuf->st_mode) || S_ISREG(stbuf->st_mode)) { + v9fs_string_sprintf(&v9stat->extension, "%s %lu", + "HARDLINKCOUNT", (unsigned long)stbuf->st_nlink); + } + + str = strrchr(name->data, '/'); + if (str) { + str += 1; + } else { + str = name->data; + } + + v9fs_string_sprintf(&v9stat->name, "%s", str); + + v9stat->size = 61 + + v9fs_string_size(&v9stat->name) + + v9fs_string_size(&v9stat->uid) + + v9fs_string_size(&v9stat->gid) + + v9fs_string_size(&v9stat->muid) + + v9fs_string_size(&v9stat->extension); + return 0; +} + +#define P9_STATS_MODE 0x00000001ULL +#define P9_STATS_NLINK 0x00000002ULL +#define P9_STATS_UID 0x00000004ULL +#define P9_STATS_GID 0x00000008ULL +#define P9_STATS_RDEV 0x00000010ULL +#define P9_STATS_ATIME 0x00000020ULL +#define P9_STATS_MTIME 0x00000040ULL +#define P9_STATS_CTIME 0x00000080ULL +#define P9_STATS_INO 0x00000100ULL +#define P9_STATS_SIZE 0x00000200ULL +#define P9_STATS_BLOCKS 0x00000400ULL + +#define P9_STATS_BTIME 0x00000800ULL +#define P9_STATS_GEN 0x00001000ULL +#define P9_STATS_DATA_VERSION 0x00002000ULL + +#define P9_STATS_BASIC 0x000007ffULL /* Mask for fields up to BLOCKS */ +#define P9_STATS_ALL 0x00003fffULL /* Mask for All fields above */ + + +static void stat_to_v9stat_dotl(V9fsState *s, const struct stat *stbuf, + V9fsStatDotl *v9lstat) +{ + memset(v9lstat, 0, sizeof(*v9lstat)); + + v9lstat->st_mode = stbuf->st_mode; + v9lstat->st_nlink = stbuf->st_nlink; + v9lstat->st_uid = stbuf->st_uid; + v9lstat->st_gid = stbuf->st_gid; + v9lstat->st_rdev = stbuf->st_rdev; + v9lstat->st_size = stbuf->st_size; + v9lstat->st_blksize = stbuf->st_blksize; + 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; + v9lstat->st_ctime_nsec = stbuf->st_ctim.tv_nsec; + /* Currently we only support BASIC fields in stat */ + v9lstat->st_result_mask = P9_STATS_BASIC; + + stat_to_qid(stbuf, &v9lstat->qid); +} + +static void print_sg(struct iovec *sg, int cnt) +{ + int i; + + printf("sg[%d]: {", cnt); + for (i = 0; i < cnt; i++) { + if (i) { + printf(", "); + } + printf("(%p, %zd)", sg[i].iov_base, sg[i].iov_len); + } + printf("}\n"); +} + +/* Will call this only for path name based fid */ +static void v9fs_fix_path(V9fsPath *dst, V9fsPath *src, int len) +{ + V9fsPath str; + v9fs_path_init(&str); + v9fs_path_copy(&str, dst); + v9fs_string_sprintf((V9fsString *)dst, "%s%s", src->data, str.data+len); + v9fs_path_free(&str); + /* +1 to include terminating NULL */ + dst->size++; +} + +static inline bool is_ro_export(FsContext *ctx) +{ + return ctx->export_flags & V9FS_RDONLY; +} + +static void v9fs_version(void *opaque) +{ + ssize_t err; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + V9fsString version; + size_t offset = 7; + + v9fs_string_init(&version); + err = pdu_unmarshal(pdu, offset, "ds", &s->msize, &version); + if (err < 0) { + offset = err; + goto out; + } + trace_v9fs_version(pdu->tag, pdu->id, s->msize, version.data); + + virtfs_reset(pdu); + + if (!strcmp(version.data, "9P2000.u")) { + s->proto_version = V9FS_PROTO_2000U; + } else if (!strcmp(version.data, "9P2000.L")) { + s->proto_version = V9FS_PROTO_2000L; + } else { + v9fs_string_sprintf(&version, "unknown"); + } + + err = pdu_marshal(pdu, offset, "ds", s->msize, &version); + if (err < 0) { + offset = err; + goto out; + } + offset += err; + trace_v9fs_version_return(pdu->tag, pdu->id, s->msize, version.data); +out: + complete_pdu(s, pdu, offset); + v9fs_string_free(&version); +} + +static void v9fs_attach(void *opaque) +{ + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + int32_t fid, afid, n_uname; + V9fsString uname, aname; + V9fsFidState *fidp; + size_t offset = 7; + V9fsQID qid; + ssize_t err; + + v9fs_string_init(&uname); + v9fs_string_init(&aname); + err = pdu_unmarshal(pdu, offset, "ddssd", &fid, + &afid, &uname, &aname, &n_uname); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_attach(pdu->tag, pdu->id, fid, afid, uname.data, aname.data); + + fidp = alloc_fid(s, fid); + if (fidp == NULL) { + err = -EINVAL; + goto out_nofid; + } + fidp->uid = n_uname; + err = v9fs_co_name_to_path(pdu, NULL, "/", &fidp->path); + if (err < 0) { + err = -EINVAL; + clunk_fid(s, fid); + goto out; + } + err = fid_to_qid(pdu, fidp, &qid); + if (err < 0) { + err = -EINVAL; + clunk_fid(s, fid); + goto out; + } + err = pdu_marshal(pdu, offset, "Q", &qid); + if (err < 0) { + clunk_fid(s, fid); + goto out; + } + err += offset; + trace_v9fs_attach_return(pdu->tag, pdu->id, + qid.type, qid.version, qid.path); + /* + * disable migration if we haven't done already. + * attach could get called multiple times for the same export. + */ + if (!s->migration_blocker) { + s->root_fid = fid; + error_setg(&s->migration_blocker, + "Migration is disabled when VirtFS export path '%s' is mounted in the guest using mount_tag '%s'", + s->ctx.fs_root ? s->ctx.fs_root : "NULL", s->tag); + migrate_add_blocker(s->migration_blocker); + } +out: + put_fid(pdu, fidp); +out_nofid: + complete_pdu(s, pdu, err); + v9fs_string_free(&uname); + v9fs_string_free(&aname); +} + +static void v9fs_stat(void *opaque) +{ + int32_t fid; + V9fsStat v9stat; + ssize_t err = 0; + size_t offset = 7; + struct stat stbuf; + V9fsFidState *fidp; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + err = pdu_unmarshal(pdu, offset, "d", &fid); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_stat(pdu->tag, pdu->id, fid); + + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -ENOENT; + goto out_nofid; + } + err = v9fs_co_lstat(pdu, &fidp->path, &stbuf); + if (err < 0) { + goto out; + } + err = stat_to_v9stat(pdu, &fidp->path, &stbuf, &v9stat); + if (err < 0) { + goto out; + } + err = pdu_marshal(pdu, offset, "wS", 0, &v9stat); + if (err < 0) { + v9fs_stat_free(&v9stat); + goto out; + } + trace_v9fs_stat_return(pdu->tag, pdu->id, v9stat.mode, + v9stat.atime, v9stat.mtime, v9stat.length); + err += offset; + v9fs_stat_free(&v9stat); +out: + put_fid(pdu, fidp); +out_nofid: + complete_pdu(s, pdu, err); +} + +static void v9fs_getattr(void *opaque) +{ + int32_t fid; + size_t offset = 7; + ssize_t retval = 0; + struct stat stbuf; + V9fsFidState *fidp; + uint64_t request_mask; + V9fsStatDotl v9stat_dotl; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + retval = pdu_unmarshal(pdu, offset, "dq", &fid, &request_mask); + if (retval < 0) { + goto out_nofid; + } + trace_v9fs_getattr(pdu->tag, pdu->id, fid, request_mask); + + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + retval = -ENOENT; + goto out_nofid; + } + /* + * Currently we only support BASIC fields in stat, so there is no + * need to look at request_mask. + */ + retval = v9fs_co_lstat(pdu, &fidp->path, &stbuf); + if (retval < 0) { + goto out; + } + stat_to_v9stat_dotl(s, &stbuf, &v9stat_dotl); + + /* fill st_gen if requested and supported by underlying fs */ + if (request_mask & P9_STATS_GEN) { + retval = v9fs_co_st_gen(pdu, &fidp->path, stbuf.st_mode, &v9stat_dotl); + switch (retval) { + case 0: + /* we have valid st_gen: update result mask */ + v9stat_dotl.st_result_mask |= P9_STATS_GEN; + break; + case -EINTR: + /* request cancelled, e.g. by Tflush */ + goto out; + default: + /* failed to get st_gen: not fatal, ignore */ + break; + } + } + retval = pdu_marshal(pdu, offset, "A", &v9stat_dotl); + if (retval < 0) { + goto out; + } + retval += offset; + trace_v9fs_getattr_return(pdu->tag, pdu->id, v9stat_dotl.st_result_mask, + v9stat_dotl.st_mode, v9stat_dotl.st_uid, + v9stat_dotl.st_gid); +out: + put_fid(pdu, fidp); +out_nofid: + complete_pdu(s, pdu, retval); +} + +/* Attribute flags */ +#define P9_ATTR_MODE (1 << 0) +#define P9_ATTR_UID (1 << 1) +#define P9_ATTR_GID (1 << 2) +#define P9_ATTR_SIZE (1 << 3) +#define P9_ATTR_ATIME (1 << 4) +#define P9_ATTR_MTIME (1 << 5) +#define P9_ATTR_CTIME (1 << 6) +#define P9_ATTR_ATIME_SET (1 << 7) +#define P9_ATTR_MTIME_SET (1 << 8) + +#define P9_ATTR_MASK 127 + +static void v9fs_setattr(void *opaque) +{ + int err = 0; + int32_t fid; + V9fsFidState *fidp; + size_t offset = 7; + V9fsIattr v9iattr; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + err = pdu_unmarshal(pdu, offset, "dI", &fid, &v9iattr); + if (err < 0) { + goto out_nofid; + } + + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -EINVAL; + goto out_nofid; + } + if (v9iattr.valid & P9_ATTR_MODE) { + err = v9fs_co_chmod(pdu, &fidp->path, v9iattr.mode); + if (err < 0) { + goto out; + } + } + if (v9iattr.valid & (P9_ATTR_ATIME | P9_ATTR_MTIME)) { + struct timespec times[2]; + if (v9iattr.valid & P9_ATTR_ATIME) { + if (v9iattr.valid & P9_ATTR_ATIME_SET) { + times[0].tv_sec = v9iattr.atime_sec; + times[0].tv_nsec = v9iattr.atime_nsec; + } else { + times[0].tv_nsec = UTIME_NOW; + } + } else { + times[0].tv_nsec = UTIME_OMIT; + } + if (v9iattr.valid & P9_ATTR_MTIME) { + if (v9iattr.valid & P9_ATTR_MTIME_SET) { + times[1].tv_sec = v9iattr.mtime_sec; + times[1].tv_nsec = v9iattr.mtime_nsec; + } else { + times[1].tv_nsec = UTIME_NOW; + } + } else { + times[1].tv_nsec = UTIME_OMIT; + } + err = v9fs_co_utimensat(pdu, &fidp->path, times); + if (err < 0) { + goto out; + } + } + /* + * If the only valid entry in iattr is ctime we can call + * chown(-1,-1) to update the ctime of the file + */ + if ((v9iattr.valid & (P9_ATTR_UID | P9_ATTR_GID)) || + ((v9iattr.valid & P9_ATTR_CTIME) + && !((v9iattr.valid & P9_ATTR_MASK) & ~P9_ATTR_CTIME))) { + if (!(v9iattr.valid & P9_ATTR_UID)) { + v9iattr.uid = -1; + } + if (!(v9iattr.valid & P9_ATTR_GID)) { + v9iattr.gid = -1; + } + err = v9fs_co_chown(pdu, &fidp->path, v9iattr.uid, + v9iattr.gid); + if (err < 0) { + goto out; + } + } + if (v9iattr.valid & (P9_ATTR_SIZE)) { + err = v9fs_co_truncate(pdu, &fidp->path, v9iattr.size); + if (err < 0) { + goto out; + } + } + err = offset; +out: + put_fid(pdu, fidp); +out_nofid: + complete_pdu(s, pdu, err); +} + +static int v9fs_walk_marshal(V9fsPDU *pdu, uint16_t nwnames, V9fsQID *qids) +{ + int i; + ssize_t err; + size_t offset = 7; + + err = pdu_marshal(pdu, offset, "w", nwnames); + if (err < 0) { + return err; + } + offset += err; + for (i = 0; i < nwnames; i++) { + err = pdu_marshal(pdu, offset, "Q", &qids[i]); + if (err < 0) { + return err; + } + offset += err; + } + return offset; +} + +static void v9fs_walk(void *opaque) +{ + int name_idx; + V9fsQID *qids = NULL; + int i, err = 0; + V9fsPath dpath, path; + uint16_t nwnames; + struct stat stbuf; + size_t offset = 7; + int32_t fid, newfid; + V9fsString *wnames = NULL; + V9fsFidState *fidp; + V9fsFidState *newfidp = NULL; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + err = pdu_unmarshal(pdu, offset, "ddw", &fid, &newfid, &nwnames); + if (err < 0) { + complete_pdu(s, pdu, err); + return ; + } + offset += err; + + trace_v9fs_walk(pdu->tag, pdu->id, fid, newfid, nwnames); + + if (nwnames && nwnames <= P9_MAXWELEM) { + wnames = g_malloc0(sizeof(wnames[0]) * nwnames); + qids = g_malloc0(sizeof(qids[0]) * nwnames); + for (i = 0; i < nwnames; i++) { + err = pdu_unmarshal(pdu, offset, "s", &wnames[i]); + if (err < 0) { + goto out_nofid; + } + offset += err; + } + } else if (nwnames > P9_MAXWELEM) { + err = -EINVAL; + goto out_nofid; + } + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -ENOENT; + goto out_nofid; + } + v9fs_path_init(&dpath); + v9fs_path_init(&path); + /* + * Both dpath and path initially poin to fidp. + * Needed to handle request with nwnames == 0 + */ + v9fs_path_copy(&dpath, &fidp->path); + v9fs_path_copy(&path, &fidp->path); + for (name_idx = 0; name_idx < nwnames; name_idx++) { + err = v9fs_co_name_to_path(pdu, &dpath, wnames[name_idx].data, &path); + if (err < 0) { + goto out; + } + err = v9fs_co_lstat(pdu, &path, &stbuf); + if (err < 0) { + goto out; + } + stat_to_qid(&stbuf, &qids[name_idx]); + v9fs_path_copy(&dpath, &path); + } + if (fid == newfid) { + BUG_ON(fidp->fid_type != P9_FID_NONE); + v9fs_path_copy(&fidp->path, &path); + } else { + newfidp = alloc_fid(s, newfid); + if (newfidp == NULL) { + err = -EINVAL; + goto out; + } + newfidp->uid = fidp->uid; + v9fs_path_copy(&newfidp->path, &path); + } + err = v9fs_walk_marshal(pdu, nwnames, qids); + trace_v9fs_walk_return(pdu->tag, pdu->id, nwnames, qids); +out: + put_fid(pdu, fidp); + if (newfidp) { + put_fid(pdu, newfidp); + } + v9fs_path_free(&dpath); + v9fs_path_free(&path); +out_nofid: + complete_pdu(s, pdu, err); + if (nwnames && nwnames <= P9_MAXWELEM) { + for (name_idx = 0; name_idx < nwnames; name_idx++) { + v9fs_string_free(&wnames[name_idx]); + } + g_free(wnames); + g_free(qids); + } +} + +static int32_t get_iounit(V9fsPDU *pdu, V9fsPath *path) +{ + struct statfs stbuf; + int32_t iounit = 0; + V9fsState *s = pdu->s; + + /* + * iounit should be multiples of f_bsize (host filesystem block size + * and as well as less than (client msize - P9_IOHDRSZ)) + */ + if (!v9fs_co_statfs(pdu, path, &stbuf)) { + iounit = stbuf.f_bsize; + iounit *= (s->msize - P9_IOHDRSZ)/stbuf.f_bsize; + } + if (!iounit) { + iounit = s->msize - P9_IOHDRSZ; + } + return iounit; +} + +static void v9fs_open(void *opaque) +{ + int flags; + int32_t fid; + int32_t mode; + V9fsQID qid; + int iounit = 0; + ssize_t err = 0; + size_t offset = 7; + struct stat stbuf; + V9fsFidState *fidp; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + if (s->proto_version == V9FS_PROTO_2000L) { + err = pdu_unmarshal(pdu, offset, "dd", &fid, &mode); + } else { + uint8_t modebyte; + err = pdu_unmarshal(pdu, offset, "db", &fid, &modebyte); + mode = modebyte; + } + if (err < 0) { + goto out_nofid; + } + trace_v9fs_open(pdu->tag, pdu->id, fid, mode); + + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -ENOENT; + goto out_nofid; + } + BUG_ON(fidp->fid_type != P9_FID_NONE); + + err = v9fs_co_lstat(pdu, &fidp->path, &stbuf); + if (err < 0) { + goto out; + } + stat_to_qid(&stbuf, &qid); + if (S_ISDIR(stbuf.st_mode)) { + err = v9fs_co_opendir(pdu, fidp); + if (err < 0) { + goto out; + } + fidp->fid_type = P9_FID_DIR; + err = pdu_marshal(pdu, offset, "Qd", &qid, 0); + if (err < 0) { + goto out; + } + err += offset; + } else { + if (s->proto_version == V9FS_PROTO_2000L) { + flags = get_dotl_openflags(s, mode); + } else { + flags = omode_to_uflags(mode); + } + if (is_ro_export(&s->ctx)) { + if (mode & O_WRONLY || mode & O_RDWR || + mode & O_APPEND || mode & O_TRUNC) { + err = -EROFS; + goto out; + } + } + err = v9fs_co_open(pdu, fidp, flags); + if (err < 0) { + goto out; + } + fidp->fid_type = P9_FID_FILE; + fidp->open_flags = flags; + if (flags & O_EXCL) { + /* + * We let the host file system do O_EXCL check + * We should not reclaim such fd + */ + fidp->flags |= FID_NON_RECLAIMABLE; + } + iounit = get_iounit(pdu, &fidp->path); + err = pdu_marshal(pdu, offset, "Qd", &qid, iounit); + if (err < 0) { + goto out; + } + err += offset; + } + trace_v9fs_open_return(pdu->tag, pdu->id, + qid.type, qid.version, qid.path, iounit); +out: + put_fid(pdu, fidp); +out_nofid: + complete_pdu(s, pdu, err); +} + +static void v9fs_lcreate(void *opaque) +{ + int32_t dfid, flags, mode; + gid_t gid; + ssize_t err = 0; + ssize_t offset = 7; + V9fsString name; + V9fsFidState *fidp; + struct stat stbuf; + V9fsQID qid; + int32_t iounit; + V9fsPDU *pdu = opaque; + + v9fs_string_init(&name); + err = pdu_unmarshal(pdu, offset, "dsddd", &dfid, + &name, &flags, &mode, &gid); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_lcreate(pdu->tag, pdu->id, dfid, flags, mode, gid); + + fidp = get_fid(pdu, dfid); + if (fidp == NULL) { + err = -ENOENT; + goto out_nofid; + } + + flags = get_dotl_openflags(pdu->s, flags); + err = v9fs_co_open2(pdu, fidp, &name, gid, + flags | O_CREAT, mode, &stbuf); + if (err < 0) { + goto out; + } + fidp->fid_type = P9_FID_FILE; + fidp->open_flags = flags; + if (flags & O_EXCL) { + /* + * We let the host file system do O_EXCL check + * We should not reclaim such fd + */ + fidp->flags |= FID_NON_RECLAIMABLE; + } + iounit = get_iounit(pdu, &fidp->path); + stat_to_qid(&stbuf, &qid); + err = pdu_marshal(pdu, offset, "Qd", &qid, iounit); + if (err < 0) { + goto out; + } + err += offset; + trace_v9fs_lcreate_return(pdu->tag, pdu->id, + qid.type, qid.version, qid.path, iounit); +out: + put_fid(pdu, fidp); +out_nofid: + complete_pdu(pdu->s, pdu, err); + v9fs_string_free(&name); +} + +static void v9fs_fsync(void *opaque) +{ + int err; + int32_t fid; + int datasync; + size_t offset = 7; + V9fsFidState *fidp; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + err = pdu_unmarshal(pdu, offset, "dd", &fid, &datasync); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_fsync(pdu->tag, pdu->id, fid, datasync); + + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -ENOENT; + goto out_nofid; + } + err = v9fs_co_fsync(pdu, fidp, datasync); + if (!err) { + err = offset; + } + put_fid(pdu, fidp); +out_nofid: + complete_pdu(s, pdu, err); +} + +static void v9fs_clunk(void *opaque) +{ + int err; + int32_t fid; + size_t offset = 7; + V9fsFidState *fidp; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + err = pdu_unmarshal(pdu, offset, "d", &fid); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_clunk(pdu->tag, pdu->id, fid); + + fidp = clunk_fid(s, fid); + if (fidp == NULL) { + err = -ENOENT; + goto out_nofid; + } + /* + * Bump the ref so that put_fid will + * free the fid. + */ + fidp->ref++; + err = put_fid(pdu, fidp); + if (!err) { + err = offset; + } +out_nofid: + complete_pdu(s, pdu, err); +} + +static int v9fs_xattr_read(V9fsState *s, V9fsPDU *pdu, V9fsFidState *fidp, + uint64_t off, uint32_t max_count) +{ + ssize_t err; + size_t offset = 7; + int read_count; + int64_t xattr_len; + + xattr_len = fidp->fs.xattr.len; + read_count = xattr_len - off; + if (read_count > max_count) { + read_count = max_count; + } else if (read_count < 0) { + /* + * read beyond XATTR value + */ + read_count = 0; + } + err = pdu_marshal(pdu, offset, "d", read_count); + if (err < 0) { + return err; + } + offset += err; + err = v9fs_pack(pdu->elem.in_sg, pdu->elem.in_num, offset, + ((char *)fidp->fs.xattr.value) + off, + read_count); + if (err < 0) { + return err; + } + offset += err; + return offset; +} + +static int v9fs_do_readdir_with_stat(V9fsPDU *pdu, + V9fsFidState *fidp, uint32_t max_count) +{ + V9fsPath path; + V9fsStat v9stat; + int len, err = 0; + int32_t count = 0; + struct stat stbuf; + off_t saved_dir_pos; + struct dirent *dent, *result; + + /* save the directory position */ + saved_dir_pos = v9fs_co_telldir(pdu, fidp); + if (saved_dir_pos < 0) { + return saved_dir_pos; + } + + dent = g_malloc(sizeof(struct dirent)); + + while (1) { + v9fs_path_init(&path); + err = v9fs_co_readdir_r(pdu, fidp, dent, &result); + if (err || !result) { + break; + } + err = v9fs_co_name_to_path(pdu, &fidp->path, dent->d_name, &path); + if (err < 0) { + goto out; + } + err = v9fs_co_lstat(pdu, &path, &stbuf); + if (err < 0) { + goto out; + } + err = stat_to_v9stat(pdu, &path, &stbuf, &v9stat); + if (err < 0) { + goto out; + } + /* 11 = 7 + 4 (7 = start offset, 4 = space for storing count) */ + len = pdu_marshal(pdu, 11 + count, "S", &v9stat); + if ((len != (v9stat.size + 2)) || ((count + len) > max_count)) { + /* Ran out of buffer. Set dir back to old position and return */ + v9fs_co_seekdir(pdu, fidp, saved_dir_pos); + v9fs_stat_free(&v9stat); + v9fs_path_free(&path); + g_free(dent); + return count; + } + count += len; + v9fs_stat_free(&v9stat); + v9fs_path_free(&path); + saved_dir_pos = dent->d_off; + } +out: + g_free(dent); + v9fs_path_free(&path); + if (err < 0) { + return err; + } + return count; +} + +/* + * Create a QEMUIOVector for a sub-region of PDU iovecs + * + * @qiov: uninitialized QEMUIOVector + * @skip: number of bytes to skip from beginning of PDU + * @size: number of bytes to include + * @is_write: true - write, false - read + * + * The resulting QEMUIOVector has heap-allocated iovecs and must be cleaned up + * with qemu_iovec_destroy(). + */ +static void v9fs_init_qiov_from_pdu(QEMUIOVector *qiov, V9fsPDU *pdu, + size_t skip, size_t size, + bool is_write) +{ + QEMUIOVector elem; + struct iovec *iov; + unsigned int niov; + + if (is_write) { + iov = pdu->elem.out_sg; + niov = pdu->elem.out_num; + } else { + iov = pdu->elem.in_sg; + niov = pdu->elem.in_num; + } + + qemu_iovec_init_external(&elem, iov, niov); + qemu_iovec_init(qiov, niov); + qemu_iovec_concat(qiov, &elem, skip, size); +} + +static void v9fs_read(void *opaque) +{ + int32_t fid; + uint64_t off; + ssize_t err = 0; + int32_t count = 0; + size_t offset = 7; + uint32_t max_count; + V9fsFidState *fidp; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + err = pdu_unmarshal(pdu, offset, "dqd", &fid, &off, &max_count); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_read(pdu->tag, pdu->id, fid, off, max_count); + + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -EINVAL; + goto out_nofid; + } + if (fidp->fid_type == P9_FID_DIR) { + + if (off == 0) { + v9fs_co_rewinddir(pdu, fidp); + } + count = v9fs_do_readdir_with_stat(pdu, fidp, max_count); + if (count < 0) { + err = count; + goto out; + } + err = pdu_marshal(pdu, offset, "d", count); + if (err < 0) { + goto out; + } + err += offset + count; + } else if (fidp->fid_type == P9_FID_FILE) { + QEMUIOVector qiov_full; + QEMUIOVector qiov; + int32_t len; + + v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset + 4, max_count, false); + qemu_iovec_init(&qiov, qiov_full.niov); + do { + qemu_iovec_reset(&qiov); + qemu_iovec_concat(&qiov, &qiov_full, count, qiov_full.size - count); + if (0) { + print_sg(qiov.iov, qiov.niov); + } + /* Loop in case of EINTR */ + do { + len = v9fs_co_preadv(pdu, fidp, qiov.iov, qiov.niov, off); + if (len >= 0) { + off += len; + count += len; + } + } while (len == -EINTR && !pdu->cancelled); + if (len < 0) { + /* IO error return the error */ + err = len; + goto out; + } + } while (count < max_count && len > 0); + err = pdu_marshal(pdu, offset, "d", count); + if (err < 0) { + goto out; + } + err += offset + count; + qemu_iovec_destroy(&qiov); + qemu_iovec_destroy(&qiov_full); + } else if (fidp->fid_type == P9_FID_XATTR) { + err = v9fs_xattr_read(s, pdu, fidp, off, max_count); + } else { + err = -EINVAL; + } + trace_v9fs_read_return(pdu->tag, pdu->id, count, err); +out: + put_fid(pdu, fidp); +out_nofid: + complete_pdu(s, pdu, err); +} + +static size_t v9fs_readdir_data_size(V9fsString *name) +{ + /* + * Size of each dirent on the wire: size of qid (13) + size of offset (8) + * size of type (1) + size of name.size (2) + strlen(name.data) + */ + return 24 + v9fs_string_size(name); +} + +static int v9fs_do_readdir(V9fsPDU *pdu, + V9fsFidState *fidp, int32_t max_count) +{ + size_t size; + V9fsQID qid; + V9fsString name; + int len, err = 0; + int32_t count = 0; + off_t saved_dir_pos; + struct dirent *dent, *result; + + /* save the directory position */ + saved_dir_pos = v9fs_co_telldir(pdu, fidp); + if (saved_dir_pos < 0) { + return saved_dir_pos; + } + + dent = g_malloc(sizeof(struct dirent)); + + while (1) { + err = v9fs_co_readdir_r(pdu, fidp, dent, &result); + if (err || !result) { + break; + } + v9fs_string_init(&name); + v9fs_string_sprintf(&name, "%s", dent->d_name); + if ((count + v9fs_readdir_data_size(&name)) > max_count) { + /* Ran out of buffer. Set dir back to old position and return */ + v9fs_co_seekdir(pdu, fidp, saved_dir_pos); + v9fs_string_free(&name); + g_free(dent); + return count; + } + /* + * Fill up just the path field of qid because the client uses + * only that. To fill the entire qid structure we will have + * to stat each dirent found, which is expensive + */ + size = MIN(sizeof(dent->d_ino), sizeof(qid.path)); + memcpy(&qid.path, &dent->d_ino, size); + /* Fill the other fields with dummy values */ + qid.type = 0; + qid.version = 0; + + /* 11 = 7 + 4 (7 = start offset, 4 = space for storing count) */ + len = pdu_marshal(pdu, 11 + count, "Qqbs", + &qid, dent->d_off, + dent->d_type, &name); + if (len < 0) { + v9fs_co_seekdir(pdu, fidp, saved_dir_pos); + v9fs_string_free(&name); + g_free(dent); + return len; + } + count += len; + v9fs_string_free(&name); + saved_dir_pos = dent->d_off; + } + g_free(dent); + if (err < 0) { + return err; + } + return count; +} + +static void v9fs_readdir(void *opaque) +{ + int32_t fid; + V9fsFidState *fidp; + ssize_t retval = 0; + size_t offset = 7; + uint64_t initial_offset; + int32_t count; + uint32_t max_count; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + retval = pdu_unmarshal(pdu, offset, "dqd", &fid, + &initial_offset, &max_count); + if (retval < 0) { + goto out_nofid; + } + trace_v9fs_readdir(pdu->tag, pdu->id, fid, initial_offset, max_count); + + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + retval = -EINVAL; + goto out_nofid; + } + if (!fidp->fs.dir) { + retval = -EINVAL; + goto out; + } + if (initial_offset == 0) { + v9fs_co_rewinddir(pdu, fidp); + } else { + v9fs_co_seekdir(pdu, fidp, initial_offset); + } + count = v9fs_do_readdir(pdu, fidp, max_count); + if (count < 0) { + retval = count; + goto out; + } + retval = pdu_marshal(pdu, offset, "d", count); + if (retval < 0) { + goto out; + } + retval += count + offset; + trace_v9fs_readdir_return(pdu->tag, pdu->id, count, retval); +out: + put_fid(pdu, fidp); +out_nofid: + complete_pdu(s, pdu, retval); +} + +static int v9fs_xattr_write(V9fsState *s, V9fsPDU *pdu, V9fsFidState *fidp, + uint64_t off, uint32_t count, + struct iovec *sg, int cnt) +{ + int i, to_copy; + ssize_t err = 0; + int write_count; + int64_t xattr_len; + size_t offset = 7; + + + xattr_len = fidp->fs.xattr.len; + write_count = xattr_len - off; + if (write_count > count) { + write_count = count; + } else if (write_count < 0) { + /* + * write beyond XATTR value len specified in + * xattrcreate + */ + err = -ENOSPC; + goto out; + } + err = pdu_marshal(pdu, offset, "d", write_count); + if (err < 0) { + return err; + } + err += offset; + fidp->fs.xattr.copied_len += write_count; + /* + * Now copy the content from sg list + */ + for (i = 0; i < cnt; i++) { + if (write_count > sg[i].iov_len) { + to_copy = sg[i].iov_len; + } else { + to_copy = write_count; + } + memcpy((char *)fidp->fs.xattr.value + off, sg[i].iov_base, to_copy); + /* updating vs->off since we are not using below */ + off += to_copy; + write_count -= to_copy; + } +out: + return err; +} + +static void v9fs_write(void *opaque) +{ + ssize_t err; + int32_t fid; + uint64_t off; + uint32_t count; + int32_t len = 0; + int32_t total = 0; + size_t offset = 7; + V9fsFidState *fidp; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + QEMUIOVector qiov_full; + QEMUIOVector qiov; + + err = pdu_unmarshal(pdu, offset, "dqd", &fid, &off, &count); + if (err < 0) { + complete_pdu(s, pdu, err); + return; + } + offset += err; + v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset, count, true); + trace_v9fs_write(pdu->tag, pdu->id, fid, off, count, qiov_full.niov); + + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -EINVAL; + goto out_nofid; + } + if (fidp->fid_type == P9_FID_FILE) { + if (fidp->fs.fd == -1) { + err = -EINVAL; + goto out; + } + } else if (fidp->fid_type == P9_FID_XATTR) { + /* + * setxattr operation + */ + err = v9fs_xattr_write(s, pdu, fidp, off, count, + qiov_full.iov, qiov_full.niov); + goto out; + } else { + err = -EINVAL; + goto out; + } + qemu_iovec_init(&qiov, qiov_full.niov); + do { + qemu_iovec_reset(&qiov); + qemu_iovec_concat(&qiov, &qiov_full, total, qiov_full.size - total); + if (0) { + print_sg(qiov.iov, qiov.niov); + } + /* Loop in case of EINTR */ + do { + len = v9fs_co_pwritev(pdu, fidp, qiov.iov, qiov.niov, off); + if (len >= 0) { + off += len; + total += len; + } + } while (len == -EINTR && !pdu->cancelled); + if (len < 0) { + /* IO error return the error */ + err = len; + goto out_qiov; + } + } while (total < count && len > 0); + + offset = 7; + err = pdu_marshal(pdu, offset, "d", total); + if (err < 0) { + goto out; + } + err += offset; + trace_v9fs_write_return(pdu->tag, pdu->id, total, err); +out_qiov: + qemu_iovec_destroy(&qiov); +out: + put_fid(pdu, fidp); +out_nofid: + qemu_iovec_destroy(&qiov_full); + complete_pdu(s, pdu, err); +} + +static void v9fs_create(void *opaque) +{ + int32_t fid; + int err = 0; + size_t offset = 7; + V9fsFidState *fidp; + V9fsQID qid; + int32_t perm; + int8_t mode; + V9fsPath path; + struct stat stbuf; + V9fsString name; + V9fsString extension; + int iounit; + V9fsPDU *pdu = opaque; + + v9fs_path_init(&path); + v9fs_string_init(&name); + v9fs_string_init(&extension); + err = pdu_unmarshal(pdu, offset, "dsdbs", &fid, &name, + &perm, &mode, &extension); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_create(pdu->tag, pdu->id, fid, name.data, perm, mode); + + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -EINVAL; + goto out_nofid; + } + if (perm & P9_STAT_MODE_DIR) { + err = v9fs_co_mkdir(pdu, fidp, &name, perm & 0777, + fidp->uid, -1, &stbuf); + if (err < 0) { + goto out; + } + err = v9fs_co_name_to_path(pdu, &fidp->path, name.data, &path); + if (err < 0) { + goto out; + } + v9fs_path_copy(&fidp->path, &path); + err = v9fs_co_opendir(pdu, fidp); + if (err < 0) { + goto out; + } + fidp->fid_type = P9_FID_DIR; + } else if (perm & P9_STAT_MODE_SYMLINK) { + err = v9fs_co_symlink(pdu, fidp, &name, + extension.data, -1 , &stbuf); + if (err < 0) { + goto out; + } + err = v9fs_co_name_to_path(pdu, &fidp->path, name.data, &path); + if (err < 0) { + goto out; + } + v9fs_path_copy(&fidp->path, &path); + } else if (perm & P9_STAT_MODE_LINK) { + int32_t ofid = atoi(extension.data); + V9fsFidState *ofidp = get_fid(pdu, ofid); + if (ofidp == NULL) { + err = -EINVAL; + goto out; + } + err = v9fs_co_link(pdu, ofidp, fidp, &name); + put_fid(pdu, ofidp); + if (err < 0) { + goto out; + } + err = v9fs_co_name_to_path(pdu, &fidp->path, name.data, &path); + if (err < 0) { + fidp->fid_type = P9_FID_NONE; + goto out; + } + v9fs_path_copy(&fidp->path, &path); + err = v9fs_co_lstat(pdu, &fidp->path, &stbuf); + if (err < 0) { + fidp->fid_type = P9_FID_NONE; + goto out; + } + } else if (perm & P9_STAT_MODE_DEVICE) { + char ctype; + uint32_t major, minor; + mode_t nmode = 0; + + if (sscanf(extension.data, "%c %u %u", &ctype, &major, &minor) != 3) { + err = -errno; + goto out; + } + + switch (ctype) { + case 'c': + nmode = S_IFCHR; + break; + case 'b': + nmode = S_IFBLK; + break; + default: + err = -EIO; + goto out; + } + + nmode |= perm & 0777; + err = v9fs_co_mknod(pdu, fidp, &name, fidp->uid, -1, + makedev(major, minor), nmode, &stbuf); + if (err < 0) { + goto out; + } + err = v9fs_co_name_to_path(pdu, &fidp->path, name.data, &path); + if (err < 0) { + goto out; + } + v9fs_path_copy(&fidp->path, &path); + } else if (perm & P9_STAT_MODE_NAMED_PIPE) { + err = v9fs_co_mknod(pdu, fidp, &name, fidp->uid, -1, + 0, S_IFIFO | (perm & 0777), &stbuf); + if (err < 0) { + goto out; + } + err = v9fs_co_name_to_path(pdu, &fidp->path, name.data, &path); + if (err < 0) { + goto out; + } + v9fs_path_copy(&fidp->path, &path); + } else if (perm & P9_STAT_MODE_SOCKET) { + err = v9fs_co_mknod(pdu, fidp, &name, fidp->uid, -1, + 0, S_IFSOCK | (perm & 0777), &stbuf); + if (err < 0) { + goto out; + } + err = v9fs_co_name_to_path(pdu, &fidp->path, name.data, &path); + if (err < 0) { + goto out; + } + v9fs_path_copy(&fidp->path, &path); + } else { + err = v9fs_co_open2(pdu, fidp, &name, -1, + omode_to_uflags(mode)|O_CREAT, perm, &stbuf); + if (err < 0) { + goto out; + } + fidp->fid_type = P9_FID_FILE; + fidp->open_flags = omode_to_uflags(mode); + if (fidp->open_flags & O_EXCL) { + /* + * We let the host file system do O_EXCL check + * We should not reclaim such fd + */ + fidp->flags |= FID_NON_RECLAIMABLE; + } + } + iounit = get_iounit(pdu, &fidp->path); + stat_to_qid(&stbuf, &qid); + err = pdu_marshal(pdu, offset, "Qd", &qid, iounit); + if (err < 0) { + goto out; + } + err += offset; + trace_v9fs_create_return(pdu->tag, pdu->id, + qid.type, qid.version, qid.path, iounit); +out: + put_fid(pdu, fidp); +out_nofid: + complete_pdu(pdu->s, pdu, err); + v9fs_string_free(&name); + v9fs_string_free(&extension); + v9fs_path_free(&path); +} + +static void v9fs_symlink(void *opaque) +{ + V9fsPDU *pdu = opaque; + V9fsString name; + V9fsString symname; + V9fsFidState *dfidp; + V9fsQID qid; + struct stat stbuf; + int32_t dfid; + int err = 0; + gid_t gid; + size_t offset = 7; + + v9fs_string_init(&name); + v9fs_string_init(&symname); + err = pdu_unmarshal(pdu, offset, "dssd", &dfid, &name, &symname, &gid); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_symlink(pdu->tag, pdu->id, dfid, name.data, symname.data, gid); + + dfidp = get_fid(pdu, dfid); + if (dfidp == NULL) { + err = -EINVAL; + goto out_nofid; + } + err = v9fs_co_symlink(pdu, dfidp, &name, symname.data, gid, &stbuf); + if (err < 0) { + goto out; + } + stat_to_qid(&stbuf, &qid); + err = pdu_marshal(pdu, offset, "Q", &qid); + if (err < 0) { + goto out; + } + err += offset; + trace_v9fs_symlink_return(pdu->tag, pdu->id, + qid.type, qid.version, qid.path); +out: + put_fid(pdu, dfidp); +out_nofid: + complete_pdu(pdu->s, pdu, err); + v9fs_string_free(&name); + v9fs_string_free(&symname); +} + +static void v9fs_flush(void *opaque) +{ + ssize_t err; + int16_t tag; + size_t offset = 7; + V9fsPDU *cancel_pdu; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + err = pdu_unmarshal(pdu, offset, "w", &tag); + if (err < 0) { + complete_pdu(s, pdu, err); + return; + } + trace_v9fs_flush(pdu->tag, pdu->id, tag); + + QLIST_FOREACH(cancel_pdu, &s->active_list, next) { + if (cancel_pdu->tag == tag) { + break; + } + } + if (cancel_pdu) { + cancel_pdu->cancelled = 1; + /* + * Wait for pdu to complete. + */ + qemu_co_queue_wait(&cancel_pdu->complete); + cancel_pdu->cancelled = 0; + free_pdu(pdu->s, cancel_pdu); + } + complete_pdu(s, pdu, 7); +} + +static void v9fs_link(void *opaque) +{ + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + int32_t dfid, oldfid; + V9fsFidState *dfidp, *oldfidp; + V9fsString name; + size_t offset = 7; + int err = 0; + + v9fs_string_init(&name); + err = pdu_unmarshal(pdu, offset, "dds", &dfid, &oldfid, &name); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_link(pdu->tag, pdu->id, dfid, oldfid, name.data); + + dfidp = get_fid(pdu, dfid); + if (dfidp == NULL) { + err = -ENOENT; + goto out_nofid; + } + + oldfidp = get_fid(pdu, oldfid); + if (oldfidp == NULL) { + err = -ENOENT; + goto out; + } + err = v9fs_co_link(pdu, oldfidp, dfidp, &name); + if (!err) { + err = offset; + } +out: + put_fid(pdu, dfidp); +out_nofid: + v9fs_string_free(&name); + complete_pdu(s, pdu, err); +} + +/* Only works with path name based fid */ +static void v9fs_remove(void *opaque) +{ + int32_t fid; + int err = 0; + size_t offset = 7; + V9fsFidState *fidp; + V9fsPDU *pdu = opaque; + + err = pdu_unmarshal(pdu, offset, "d", &fid); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_remove(pdu->tag, pdu->id, fid); + + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -EINVAL; + goto out_nofid; + } + /* if fs driver is not path based, return EOPNOTSUPP */ + if (!(pdu->s->ctx.export_flags & V9FS_PATHNAME_FSCONTEXT)) { + err = -EOPNOTSUPP; + goto out_err; + } + /* + * IF the file is unlinked, we cannot reopen + * the file later. So don't reclaim fd + */ + err = v9fs_mark_fids_unreclaim(pdu, &fidp->path); + if (err < 0) { + goto out_err; + } + err = v9fs_co_remove(pdu, &fidp->path); + if (!err) { + err = offset; + } +out_err: + /* For TREMOVE we need to clunk the fid even on failed remove */ + clunk_fid(pdu->s, fidp->fid); + put_fid(pdu, fidp); +out_nofid: + complete_pdu(pdu->s, pdu, err); +} + +static void v9fs_unlinkat(void *opaque) +{ + int err = 0; + V9fsString name; + int32_t dfid, flags; + size_t offset = 7; + V9fsPath path; + V9fsFidState *dfidp; + V9fsPDU *pdu = opaque; + + v9fs_string_init(&name); + err = pdu_unmarshal(pdu, offset, "dsd", &dfid, &name, &flags); + if (err < 0) { + goto out_nofid; + } + dfidp = get_fid(pdu, dfid); + if (dfidp == NULL) { + err = -EINVAL; + goto out_nofid; + } + /* + * IF the file is unlinked, we cannot reopen + * the file later. So don't reclaim fd + */ + v9fs_path_init(&path); + err = v9fs_co_name_to_path(pdu, &dfidp->path, name.data, &path); + if (err < 0) { + goto out_err; + } + err = v9fs_mark_fids_unreclaim(pdu, &path); + if (err < 0) { + goto out_err; + } + err = v9fs_co_unlinkat(pdu, &dfidp->path, &name, flags); + if (!err) { + err = offset; + } +out_err: + put_fid(pdu, dfidp); + v9fs_path_free(&path); +out_nofid: + complete_pdu(pdu->s, pdu, err); + v9fs_string_free(&name); +} + + +/* Only works with path name based fid */ +static int v9fs_complete_rename(V9fsPDU *pdu, V9fsFidState *fidp, + int32_t newdirfid, V9fsString *name) +{ + char *end; + int err = 0; + V9fsPath new_path; + V9fsFidState *tfidp; + V9fsState *s = pdu->s; + V9fsFidState *dirfidp = NULL; + char *old_name, *new_name; + + v9fs_path_init(&new_path); + if (newdirfid != -1) { + dirfidp = get_fid(pdu, newdirfid); + if (dirfidp == NULL) { + err = -ENOENT; + goto out_nofid; + } + BUG_ON(dirfidp->fid_type != P9_FID_NONE); + v9fs_co_name_to_path(pdu, &dirfidp->path, name->data, &new_path); + } else { + old_name = fidp->path.data; + end = strrchr(old_name, '/'); + if (end) { + end++; + } else { + end = old_name; + } + new_name = g_malloc0(end - old_name + name->size + 1); + strncat(new_name, old_name, end - old_name); + strncat(new_name + (end - old_name), name->data, name->size); + v9fs_co_name_to_path(pdu, NULL, new_name, &new_path); + g_free(new_name); + } + err = v9fs_co_rename(pdu, &fidp->path, &new_path); + if (err < 0) { + goto out; + } + /* + * Fixup fid's pointing to the old name to + * start pointing to the new name + */ + for (tfidp = s->fid_list; tfidp; tfidp = tfidp->next) { + if (v9fs_path_is_ancestor(&fidp->path, &tfidp->path)) { + /* replace the name */ + v9fs_fix_path(&tfidp->path, &new_path, strlen(fidp->path.data)); + } + } +out: + if (dirfidp) { + put_fid(pdu, dirfidp); + } + v9fs_path_free(&new_path); +out_nofid: + return err; +} + +/* Only works with path name based fid */ +static void v9fs_rename(void *opaque) +{ + int32_t fid; + ssize_t err = 0; + size_t offset = 7; + V9fsString name; + int32_t newdirfid; + V9fsFidState *fidp; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + v9fs_string_init(&name); + err = pdu_unmarshal(pdu, offset, "dds", &fid, &newdirfid, &name); + if (err < 0) { + goto out_nofid; + } + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -ENOENT; + goto out_nofid; + } + BUG_ON(fidp->fid_type != P9_FID_NONE); + /* if fs driver is not path based, return EOPNOTSUPP */ + if (!(pdu->s->ctx.export_flags & V9FS_PATHNAME_FSCONTEXT)) { + err = -EOPNOTSUPP; + goto out; + } + v9fs_path_write_lock(s); + err = v9fs_complete_rename(pdu, fidp, newdirfid, &name); + v9fs_path_unlock(s); + if (!err) { + err = offset; + } +out: + put_fid(pdu, fidp); +out_nofid: + complete_pdu(s, pdu, err); + v9fs_string_free(&name); +} + +static void v9fs_fix_fid_paths(V9fsPDU *pdu, V9fsPath *olddir, + V9fsString *old_name, V9fsPath *newdir, + V9fsString *new_name) +{ + V9fsFidState *tfidp; + V9fsPath oldpath, newpath; + V9fsState *s = pdu->s; + + + v9fs_path_init(&oldpath); + v9fs_path_init(&newpath); + v9fs_co_name_to_path(pdu, olddir, old_name->data, &oldpath); + v9fs_co_name_to_path(pdu, newdir, new_name->data, &newpath); + + /* + * Fixup fid's pointing to the old name to + * start pointing to the new name + */ + for (tfidp = s->fid_list; tfidp; tfidp = tfidp->next) { + if (v9fs_path_is_ancestor(&oldpath, &tfidp->path)) { + /* replace the name */ + v9fs_fix_path(&tfidp->path, &newpath, strlen(oldpath.data)); + } + } + v9fs_path_free(&oldpath); + v9fs_path_free(&newpath); +} + +static int v9fs_complete_renameat(V9fsPDU *pdu, int32_t olddirfid, + V9fsString *old_name, int32_t newdirfid, + V9fsString *new_name) +{ + int err = 0; + V9fsState *s = pdu->s; + V9fsFidState *newdirfidp = NULL, *olddirfidp = NULL; + + olddirfidp = get_fid(pdu, olddirfid); + if (olddirfidp == NULL) { + err = -ENOENT; + goto out; + } + if (newdirfid != -1) { + newdirfidp = get_fid(pdu, newdirfid); + if (newdirfidp == NULL) { + err = -ENOENT; + goto out; + } + } else { + newdirfidp = get_fid(pdu, olddirfid); + } + + err = v9fs_co_renameat(pdu, &olddirfidp->path, old_name, + &newdirfidp->path, new_name); + if (err < 0) { + goto out; + } + if (s->ctx.export_flags & V9FS_PATHNAME_FSCONTEXT) { + /* Only for path based fid we need to do the below fixup */ + v9fs_fix_fid_paths(pdu, &olddirfidp->path, old_name, + &newdirfidp->path, new_name); + } +out: + if (olddirfidp) { + put_fid(pdu, olddirfidp); + } + if (newdirfidp) { + put_fid(pdu, newdirfidp); + } + return err; +} + +static void v9fs_renameat(void *opaque) +{ + ssize_t err = 0; + size_t offset = 7; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + int32_t olddirfid, newdirfid; + V9fsString old_name, new_name; + + v9fs_string_init(&old_name); + v9fs_string_init(&new_name); + err = pdu_unmarshal(pdu, offset, "dsds", &olddirfid, + &old_name, &newdirfid, &new_name); + if (err < 0) { + goto out_err; + } + + v9fs_path_write_lock(s); + err = v9fs_complete_renameat(pdu, olddirfid, + &old_name, newdirfid, &new_name); + v9fs_path_unlock(s); + if (!err) { + err = offset; + } + +out_err: + complete_pdu(s, pdu, err); + v9fs_string_free(&old_name); + v9fs_string_free(&new_name); +} + +static void v9fs_wstat(void *opaque) +{ + int32_t fid; + int err = 0; + int16_t unused; + V9fsStat v9stat; + size_t offset = 7; + struct stat stbuf; + V9fsFidState *fidp; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + v9fs_stat_init(&v9stat); + err = pdu_unmarshal(pdu, offset, "dwS", &fid, &unused, &v9stat); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_wstat(pdu->tag, pdu->id, fid, + v9stat.mode, v9stat.atime, v9stat.mtime); + + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -EINVAL; + goto out_nofid; + } + /* do we need to sync the file? */ + if (donttouch_stat(&v9stat)) { + err = v9fs_co_fsync(pdu, fidp, 0); + goto out; + } + if (v9stat.mode != -1) { + uint32_t v9_mode; + err = v9fs_co_lstat(pdu, &fidp->path, &stbuf); + if (err < 0) { + goto out; + } + v9_mode = stat_to_v9mode(&stbuf); + if ((v9stat.mode & P9_STAT_MODE_TYPE_BITS) != + (v9_mode & P9_STAT_MODE_TYPE_BITS)) { + /* Attempting to change the type */ + err = -EIO; + goto out; + } + err = v9fs_co_chmod(pdu, &fidp->path, + v9mode_to_mode(v9stat.mode, + &v9stat.extension)); + if (err < 0) { + goto out; + } + } + if (v9stat.mtime != -1 || v9stat.atime != -1) { + struct timespec times[2]; + if (v9stat.atime != -1) { + times[0].tv_sec = v9stat.atime; + times[0].tv_nsec = 0; + } else { + times[0].tv_nsec = UTIME_OMIT; + } + if (v9stat.mtime != -1) { + times[1].tv_sec = v9stat.mtime; + times[1].tv_nsec = 0; + } else { + times[1].tv_nsec = UTIME_OMIT; + } + err = v9fs_co_utimensat(pdu, &fidp->path, times); + if (err < 0) { + goto out; + } + } + if (v9stat.n_gid != -1 || v9stat.n_uid != -1) { + err = v9fs_co_chown(pdu, &fidp->path, v9stat.n_uid, v9stat.n_gid); + if (err < 0) { + goto out; + } + } + if (v9stat.name.size != 0) { + err = v9fs_complete_rename(pdu, fidp, -1, &v9stat.name); + if (err < 0) { + goto out; + } + } + if (v9stat.length != -1) { + err = v9fs_co_truncate(pdu, &fidp->path, v9stat.length); + if (err < 0) { + goto out; + } + } + err = offset; +out: + put_fid(pdu, fidp); +out_nofid: + v9fs_stat_free(&v9stat); + complete_pdu(s, pdu, err); +} + +static int v9fs_fill_statfs(V9fsState *s, V9fsPDU *pdu, struct statfs *stbuf) +{ + uint32_t f_type; + uint32_t f_bsize; + uint64_t f_blocks; + uint64_t f_bfree; + uint64_t f_bavail; + uint64_t f_files; + uint64_t f_ffree; + uint64_t fsid_val; + uint32_t f_namelen; + size_t offset = 7; + int32_t bsize_factor; + + /* + * compute bsize factor based on host file system block size + * and client msize + */ + bsize_factor = (s->msize - P9_IOHDRSZ)/stbuf->f_bsize; + if (!bsize_factor) { + bsize_factor = 1; + } + f_type = stbuf->f_type; + f_bsize = stbuf->f_bsize; + f_bsize *= bsize_factor; + /* + * f_bsize is adjusted(multiplied) by bsize factor, so we need to + * adjust(divide) the number of blocks, free blocks and available + * blocks by bsize factor + */ + f_blocks = stbuf->f_blocks/bsize_factor; + f_bfree = stbuf->f_bfree/bsize_factor; + f_bavail = stbuf->f_bavail/bsize_factor; + f_files = stbuf->f_files; + f_ffree = stbuf->f_ffree; + fsid_val = (unsigned int) stbuf->f_fsid.__val[0] | + (unsigned long long)stbuf->f_fsid.__val[1] << 32; + f_namelen = stbuf->f_namelen; + + return pdu_marshal(pdu, offset, "ddqqqqqqd", + f_type, f_bsize, f_blocks, f_bfree, + f_bavail, f_files, f_ffree, + fsid_val, f_namelen); +} + +static void v9fs_statfs(void *opaque) +{ + int32_t fid; + ssize_t retval = 0; + size_t offset = 7; + V9fsFidState *fidp; + struct statfs stbuf; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + retval = pdu_unmarshal(pdu, offset, "d", &fid); + if (retval < 0) { + goto out_nofid; + } + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + retval = -ENOENT; + goto out_nofid; + } + retval = v9fs_co_statfs(pdu, &fidp->path, &stbuf); + if (retval < 0) { + goto out; + } + retval = v9fs_fill_statfs(s, pdu, &stbuf); + if (retval < 0) { + goto out; + } + retval += offset; +out: + put_fid(pdu, fidp); +out_nofid: + complete_pdu(s, pdu, retval); +} + +static void v9fs_mknod(void *opaque) +{ + + int mode; + gid_t gid; + int32_t fid; + V9fsQID qid; + int err = 0; + int major, minor; + size_t offset = 7; + V9fsString name; + struct stat stbuf; + V9fsFidState *fidp; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + v9fs_string_init(&name); + err = pdu_unmarshal(pdu, offset, "dsdddd", &fid, &name, &mode, + &major, &minor, &gid); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_mknod(pdu->tag, pdu->id, fid, mode, major, minor); + + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -ENOENT; + goto out_nofid; + } + err = v9fs_co_mknod(pdu, fidp, &name, fidp->uid, gid, + makedev(major, minor), mode, &stbuf); + if (err < 0) { + goto out; + } + stat_to_qid(&stbuf, &qid); + err = pdu_marshal(pdu, offset, "Q", &qid); + if (err < 0) { + goto out; + } + err += offset; + trace_v9fs_mknod_return(pdu->tag, pdu->id, + qid.type, qid.version, qid.path); +out: + put_fid(pdu, fidp); +out_nofid: + complete_pdu(s, pdu, err); + v9fs_string_free(&name); +} + +/* + * Implement posix byte range locking code + * Server side handling of locking code is very simple, because 9p server in + * QEMU can handle only one client. And most of the lock handling + * (like conflict, merging) etc is done by the VFS layer itself, so no need to + * do any thing in * qemu 9p server side lock code path. + * So when a TLOCK request comes, always return success + */ +static void v9fs_lock(void *opaque) +{ + int8_t status; + V9fsFlock flock; + size_t offset = 7; + struct stat stbuf; + V9fsFidState *fidp; + int32_t fid, err = 0; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + status = P9_LOCK_ERROR; + v9fs_string_init(&flock.client_id); + err = pdu_unmarshal(pdu, offset, "dbdqqds", &fid, &flock.type, + &flock.flags, &flock.start, &flock.length, + &flock.proc_id, &flock.client_id); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_lock(pdu->tag, pdu->id, fid, + flock.type, flock.start, flock.length); + + + /* We support only block flag now (that too ignored currently) */ + if (flock.flags & ~P9_LOCK_FLAGS_BLOCK) { + err = -EINVAL; + goto out_nofid; + } + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -ENOENT; + goto out_nofid; + } + err = v9fs_co_fstat(pdu, fidp, &stbuf); + if (err < 0) { + goto out; + } + status = P9_LOCK_SUCCESS; +out: + put_fid(pdu, fidp); +out_nofid: + err = pdu_marshal(pdu, offset, "b", status); + if (err > 0) { + err += offset; + } + trace_v9fs_lock_return(pdu->tag, pdu->id, status); + complete_pdu(s, pdu, err); + v9fs_string_free(&flock.client_id); +} + +/* + * When a TGETLOCK request comes, always return success because all lock + * handling is done by client's VFS layer. + */ +static void v9fs_getlock(void *opaque) +{ + size_t offset = 7; + struct stat stbuf; + V9fsFidState *fidp; + V9fsGetlock glock; + int32_t fid, err = 0; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + v9fs_string_init(&glock.client_id); + err = pdu_unmarshal(pdu, offset, "dbqqds", &fid, &glock.type, + &glock.start, &glock.length, &glock.proc_id, + &glock.client_id); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_getlock(pdu->tag, pdu->id, fid, + glock.type, glock.start, glock.length); + + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -ENOENT; + goto out_nofid; + } + err = v9fs_co_fstat(pdu, fidp, &stbuf); + if (err < 0) { + goto out; + } + glock.type = P9_LOCK_TYPE_UNLCK; + err = pdu_marshal(pdu, offset, "bqqds", glock.type, + glock.start, glock.length, glock.proc_id, + &glock.client_id); + if (err < 0) { + goto out; + } + err += offset; + trace_v9fs_getlock_return(pdu->tag, pdu->id, glock.type, glock.start, + glock.length, glock.proc_id); +out: + put_fid(pdu, fidp); +out_nofid: + complete_pdu(s, pdu, err); + v9fs_string_free(&glock.client_id); +} + +static void v9fs_mkdir(void *opaque) +{ + V9fsPDU *pdu = opaque; + size_t offset = 7; + int32_t fid; + struct stat stbuf; + V9fsQID qid; + V9fsString name; + V9fsFidState *fidp; + gid_t gid; + int mode; + int err = 0; + + v9fs_string_init(&name); + err = pdu_unmarshal(pdu, offset, "dsdd", &fid, &name, &mode, &gid); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_mkdir(pdu->tag, pdu->id, fid, name.data, mode, gid); + + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -ENOENT; + goto out_nofid; + } + err = v9fs_co_mkdir(pdu, fidp, &name, mode, fidp->uid, gid, &stbuf); + if (err < 0) { + goto out; + } + stat_to_qid(&stbuf, &qid); + err = pdu_marshal(pdu, offset, "Q", &qid); + if (err < 0) { + goto out; + } + err += offset; + trace_v9fs_mkdir_return(pdu->tag, pdu->id, + qid.type, qid.version, qid.path, err); +out: + put_fid(pdu, fidp); +out_nofid: + complete_pdu(pdu->s, pdu, err); + v9fs_string_free(&name); +} + +static void v9fs_xattrwalk(void *opaque) +{ + int64_t size; + V9fsString name; + ssize_t err = 0; + size_t offset = 7; + int32_t fid, newfid; + V9fsFidState *file_fidp; + V9fsFidState *xattr_fidp = NULL; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + v9fs_string_init(&name); + err = pdu_unmarshal(pdu, offset, "dds", &fid, &newfid, &name); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_xattrwalk(pdu->tag, pdu->id, fid, newfid, name.data); + + file_fidp = get_fid(pdu, fid); + if (file_fidp == NULL) { + err = -ENOENT; + goto out_nofid; + } + xattr_fidp = alloc_fid(s, newfid); + if (xattr_fidp == NULL) { + err = -EINVAL; + goto out; + } + v9fs_path_copy(&xattr_fidp->path, &file_fidp->path); + if (name.data == NULL) { + /* + * listxattr request. Get the size first + */ + size = v9fs_co_llistxattr(pdu, &xattr_fidp->path, NULL, 0); + if (size < 0) { + err = size; + clunk_fid(s, xattr_fidp->fid); + goto out; + } + /* + * Read the xattr value + */ + xattr_fidp->fs.xattr.len = size; + xattr_fidp->fid_type = P9_FID_XATTR; + xattr_fidp->fs.xattr.copied_len = -1; + if (size) { + xattr_fidp->fs.xattr.value = g_malloc(size); + err = v9fs_co_llistxattr(pdu, &xattr_fidp->path, + xattr_fidp->fs.xattr.value, + xattr_fidp->fs.xattr.len); + if (err < 0) { + clunk_fid(s, xattr_fidp->fid); + goto out; + } + } + err = pdu_marshal(pdu, offset, "q", size); + if (err < 0) { + goto out; + } + err += offset; + } else { + /* + * specific xattr fid. We check for xattr + * presence also collect the xattr size + */ + size = v9fs_co_lgetxattr(pdu, &xattr_fidp->path, + &name, NULL, 0); + if (size < 0) { + err = size; + clunk_fid(s, xattr_fidp->fid); + goto out; + } + /* + * Read the xattr value + */ + xattr_fidp->fs.xattr.len = size; + xattr_fidp->fid_type = P9_FID_XATTR; + xattr_fidp->fs.xattr.copied_len = -1; + if (size) { + xattr_fidp->fs.xattr.value = g_malloc(size); + err = v9fs_co_lgetxattr(pdu, &xattr_fidp->path, + &name, xattr_fidp->fs.xattr.value, + xattr_fidp->fs.xattr.len); + if (err < 0) { + clunk_fid(s, xattr_fidp->fid); + goto out; + } + } + err = pdu_marshal(pdu, offset, "q", size); + if (err < 0) { + goto out; + } + err += offset; + } + trace_v9fs_xattrwalk_return(pdu->tag, pdu->id, size); +out: + put_fid(pdu, file_fidp); + if (xattr_fidp) { + put_fid(pdu, xattr_fidp); + } +out_nofid: + complete_pdu(s, pdu, err); + v9fs_string_free(&name); +} + +static void v9fs_xattrcreate(void *opaque) +{ + int flags; + int32_t fid; + int64_t size; + ssize_t err = 0; + V9fsString name; + size_t offset = 7; + V9fsFidState *file_fidp; + V9fsFidState *xattr_fidp; + V9fsPDU *pdu = opaque; + V9fsState *s = pdu->s; + + v9fs_string_init(&name); + err = pdu_unmarshal(pdu, offset, "dsqd", &fid, &name, &size, &flags); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_xattrcreate(pdu->tag, pdu->id, fid, name.data, size, flags); + + file_fidp = get_fid(pdu, fid); + if (file_fidp == NULL) { + err = -EINVAL; + goto out_nofid; + } + /* Make the file fid point to xattr */ + xattr_fidp = file_fidp; + xattr_fidp->fid_type = P9_FID_XATTR; + xattr_fidp->fs.xattr.copied_len = 0; + xattr_fidp->fs.xattr.len = size; + xattr_fidp->fs.xattr.flags = flags; + v9fs_string_init(&xattr_fidp->fs.xattr.name); + v9fs_string_copy(&xattr_fidp->fs.xattr.name, &name); + xattr_fidp->fs.xattr.value = g_malloc(size); + err = offset; + put_fid(pdu, file_fidp); +out_nofid: + complete_pdu(s, pdu, err); + v9fs_string_free(&name); +} + +static void v9fs_readlink(void *opaque) +{ + V9fsPDU *pdu = opaque; + size_t offset = 7; + V9fsString target; + int32_t fid; + int err = 0; + V9fsFidState *fidp; + + err = pdu_unmarshal(pdu, offset, "d", &fid); + if (err < 0) { + goto out_nofid; + } + trace_v9fs_readlink(pdu->tag, pdu->id, fid); + fidp = get_fid(pdu, fid); + if (fidp == NULL) { + err = -ENOENT; + goto out_nofid; + } + + v9fs_string_init(&target); + err = v9fs_co_readlink(pdu, &fidp->path, &target); + if (err < 0) { + goto out; + } + err = pdu_marshal(pdu, offset, "s", &target); + if (err < 0) { + v9fs_string_free(&target); + goto out; + } + err += offset; + trace_v9fs_readlink_return(pdu->tag, pdu->id, target.data); + v9fs_string_free(&target); +out: + put_fid(pdu, fidp); +out_nofid: + complete_pdu(pdu->s, pdu, err); +} + +static CoroutineEntry *pdu_co_handlers[] = { + [P9_TREADDIR] = v9fs_readdir, + [P9_TSTATFS] = v9fs_statfs, + [P9_TGETATTR] = v9fs_getattr, + [P9_TSETATTR] = v9fs_setattr, + [P9_TXATTRWALK] = v9fs_xattrwalk, + [P9_TXATTRCREATE] = v9fs_xattrcreate, + [P9_TMKNOD] = v9fs_mknod, + [P9_TRENAME] = v9fs_rename, + [P9_TLOCK] = v9fs_lock, + [P9_TGETLOCK] = v9fs_getlock, + [P9_TRENAMEAT] = v9fs_renameat, + [P9_TREADLINK] = v9fs_readlink, + [P9_TUNLINKAT] = v9fs_unlinkat, + [P9_TMKDIR] = v9fs_mkdir, + [P9_TVERSION] = v9fs_version, + [P9_TLOPEN] = v9fs_open, + [P9_TATTACH] = v9fs_attach, + [P9_TSTAT] = v9fs_stat, + [P9_TWALK] = v9fs_walk, + [P9_TCLUNK] = v9fs_clunk, + [P9_TFSYNC] = v9fs_fsync, + [P9_TOPEN] = v9fs_open, + [P9_TREAD] = v9fs_read, +#if 0 + [P9_TAUTH] = v9fs_auth, +#endif + [P9_TFLUSH] = v9fs_flush, + [P9_TLINK] = v9fs_link, + [P9_TSYMLINK] = v9fs_symlink, + [P9_TCREATE] = v9fs_create, + [P9_TLCREATE] = v9fs_lcreate, + [P9_TWRITE] = v9fs_write, + [P9_TWSTAT] = v9fs_wstat, + [P9_TREMOVE] = v9fs_remove, +}; + +static void v9fs_op_not_supp(void *opaque) +{ + V9fsPDU *pdu = opaque; + complete_pdu(pdu->s, pdu, -EOPNOTSUPP); +} + +static void v9fs_fs_ro(void *opaque) +{ + V9fsPDU *pdu = opaque; + complete_pdu(pdu->s, pdu, -EROFS); +} + +static inline bool is_read_only_op(V9fsPDU *pdu) +{ + switch (pdu->id) { + case P9_TREADDIR: + case P9_TSTATFS: + case P9_TGETATTR: + case P9_TXATTRWALK: + case P9_TLOCK: + case P9_TGETLOCK: + case P9_TREADLINK: + case P9_TVERSION: + case P9_TLOPEN: + case P9_TATTACH: + case P9_TSTAT: + case P9_TWALK: + case P9_TCLUNK: + case P9_TFSYNC: + case P9_TOPEN: + case P9_TREAD: + case P9_TAUTH: + case P9_TFLUSH: + return 1; + default: + return 0; + } +} + +static void submit_pdu(V9fsState *s, V9fsPDU *pdu) +{ + Coroutine *co; + CoroutineEntry *handler; + + if (pdu->id >= ARRAY_SIZE(pdu_co_handlers) || + (pdu_co_handlers[pdu->id] == NULL)) { + handler = v9fs_op_not_supp; + } else { + handler = pdu_co_handlers[pdu->id]; + } + + if (is_ro_export(&s->ctx) && !is_read_only_op(pdu)) { + handler = v9fs_fs_ro; + } + co = qemu_coroutine_create(handler); + qemu_coroutine_enter(co, pdu); +} + +void handle_9p_output(VirtIODevice *vdev, VirtQueue *vq) +{ + V9fsState *s = (V9fsState *)vdev; + V9fsPDU *pdu; + ssize_t len; + + while ((pdu = alloc_pdu(s)) && + (len = virtqueue_pop(vq, &pdu->elem)) != 0) { + struct { + uint32_t size_le; + uint8_t id; + uint16_t tag_le; + } QEMU_PACKED out; + int len; + + pdu->s = s; + BUG_ON(pdu->elem.out_num == 0 || pdu->elem.in_num == 0); + QEMU_BUILD_BUG_ON(sizeof out != 7); + + len = iov_to_buf(pdu->elem.out_sg, pdu->elem.out_num, 0, + &out, sizeof out); + BUG_ON(len != sizeof out); + + pdu->size = le32_to_cpu(out.size_le); + + pdu->id = out.id; + pdu->tag = le16_to_cpu(out.tag_le); + + qemu_co_queue_init(&pdu->complete); + submit_pdu(s, pdu); + } + free_pdu(s, pdu); +} + +static void __attribute__((__constructor__)) virtio_9p_set_fd_limit(void) +{ + struct rlimit rlim; + if (getrlimit(RLIMIT_NOFILE, &rlim) < 0) { + fprintf(stderr, "Failed to get the resource limit\n"); + exit(1); + } + open_fd_hw = rlim.rlim_cur - MIN(400, rlim.rlim_cur/3); + open_fd_rc = rlim.rlim_cur/2; +} diff --git a/qemu/hw/9pfs/virtio-9p.h b/qemu/hw/9pfs/virtio-9p.h new file mode 100644 index 000000000..2e7d48857 --- /dev/null +++ b/qemu/hw/9pfs/virtio-9p.h @@ -0,0 +1,394 @@ +#ifndef _QEMU_VIRTIO_9P_H +#define _QEMU_VIRTIO_9P_H + +#include <sys/types.h> +#include <dirent.h> +#include <sys/time.h> +#include <utime.h> +#include <sys/resource.h> +#include <glib.h> +#include "standard-headers/linux/virtio_9p.h" +#include "hw/virtio/virtio.h" +#include "hw/virtio/virtio-9p.h" +#include "fsdev/file-op-9p.h" +#include "fsdev/virtio-9p-marshal.h" +#include "qemu/thread.h" +#include "block/coroutine.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, +}; + +enum p9_proto_version { + V9FS_PROTO_2000U = 0x01, + V9FS_PROTO_2000L = 0x02, +}; + +#define P9_NOTAG (u16)(~0) +#define P9_NOFID (u32)(~0) +#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; +struct V9fsState; + +struct V9fsPDU +{ + uint32_t size; + uint16_t tag; + uint8_t id; + uint8_t cancelled; + CoQueue complete; + VirtQueueElement elem; + struct V9fsState *s; + QLIST_ENTRY(V9fsPDU) next; +}; + + +/* 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 V9fsXattr +{ + int64_t copied_len; + int64_t len; + void *value; + V9fsString name; + int flags; +} V9fsXattr; + +/* + * Filled by fs driver on open and other + * calls. + */ +union V9fsFidOpenState { + int fd; + DIR *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; +}; + +typedef struct V9fsState +{ + VirtIODevice parent_obj; + VirtQueue *vq; + V9fsPDU pdus[MAX_REQ]; + QLIST_HEAD(, V9fsPDU) free_list; + QLIST_HEAD(, V9fsPDU) active_list; + V9fsFidState *fid_list; + FileOperations *ops; + FsContext ctx; + char *tag; + size_t config_size; + enum p9_proto_version proto_version; + int32_t msize; + /* + * lock ensuring atomic path update + * on rename. + */ + CoRwlock rename_lock; + int32_t root_fid; + Error *migration_blocker; + V9fsConf fsconf; +} V9fsState; + +typedef struct V9fsStatState { + V9fsPDU *pdu; + size_t offset; + V9fsStat v9stat; + V9fsFidState *fidp; + struct stat stbuf; +} V9fsStatState; + +typedef struct V9fsOpenState { + V9fsPDU *pdu; + size_t offset; + int32_t mode; + V9fsFidState *fidp; + V9fsQID qid; + struct stat stbuf; + int iounit; +} V9fsOpenState; + +typedef struct V9fsReadState { + V9fsPDU *pdu; + size_t offset; + int32_t count; + int32_t total; + int64_t off; + V9fsFidState *fidp; + struct iovec iov[128]; /* FIXME: bad, bad, bad */ + struct iovec *sg; + off_t dir_pos; + struct dirent *dent; + struct stat stbuf; + V9fsString name; + V9fsStat v9stat; + int32_t len; + int32_t cnt; + int32_t max_count; +} V9fsReadState; + +typedef struct V9fsWriteState { + V9fsPDU *pdu; + size_t offset; + int32_t len; + int32_t count; + int32_t total; + int64_t off; + V9fsFidState *fidp; + struct iovec iov[128]; /* FIXME: bad, bad, bad */ + struct iovec *sg; + int cnt; +} V9fsWriteState; + +typedef struct V9fsMkState { + V9fsPDU *pdu; + size_t offset; + V9fsQID qid; + struct stat stbuf; + V9fsString name; + V9fsString fullname; +} V9fsMkState; + +/* 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; + +size_t pdu_packunpack(void *addr, struct iovec *sg, int sg_count, + size_t offset, size_t size, int pack); + +static inline size_t do_pdu_unpack(void *dst, struct iovec *sg, int sg_count, + size_t offset, size_t size) +{ + return pdu_packunpack(dst, sg, sg_count, offset, size, 0); +} + +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; +} + +extern void handle_9p_output(VirtIODevice *vdev, VirtQueue *vq); +extern void v9fs_reclaim_fd(V9fsPDU *pdu); +extern void v9fs_path_init(V9fsPath *path); +extern void v9fs_path_free(V9fsPath *path); +extern void v9fs_path_copy(V9fsPath *lhs, V9fsPath *rhs); +extern int v9fs_name_to_path(V9fsState *s, V9fsPath *dirpath, + const char *name, V9fsPath *path); + +#define pdu_marshal(pdu, offset, fmt, args...) \ + v9fs_marshal(pdu->elem.in_sg, pdu->elem.in_num, offset, 1, fmt, ##args) +#define pdu_unmarshal(pdu, offset, fmt, args...) \ + v9fs_unmarshal(pdu->elem.out_sg, pdu->elem.out_num, offset, 1, fmt, ##args) + +#define TYPE_VIRTIO_9P "virtio-9p-device" +#define VIRTIO_9P(obj) \ + OBJECT_CHECK(V9fsState, (obj), TYPE_VIRTIO_9P) + +#endif |