From 0009df31cb51cb2be681f4eebd58a9776d75a580 Mon Sep 17 00:00:00 2001 From: Christian Schoenebeck Date: Mon, 14 Mar 2022 19:58:11 +0100 Subject: [PATCH 1/7] 9pfs: fix inode sequencing in 'synth' driver The 'synth' driver's root node and the 'synth' driver's first subdirectory node falsely share the same inode number (zero), which makes it impossible for 9p clients (i.e. 9p test cases) to distinguish root node and first subdirectory from each other by comparing their QIDs (which are derived by 9p server from driver's inode numbers). Fix this issue by using prefix-increment instead of postfix-increment operator while generating new inode numbers for subdirectories and files. Link: https://lore.kernel.org/qemu-devel/3859307.hTDP4D0zbi@silver/ Signed-off-by: Christian Schoenebeck Reviewed-by: Greg Kurz Message-Id: --- hw/9pfs/9p-synth.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/9pfs/9p-synth.c b/hw/9pfs/9p-synth.c index d99d263985..1c5813e4dd 100644 --- a/hw/9pfs/9p-synth.c +++ b/hw/9pfs/9p-synth.c @@ -92,7 +92,7 @@ int qemu_v9fs_synth_mkdir(V9fsSynthNode *parent, int mode, } } /* Add the name */ - node = v9fs_add_dir_node(parent, mode, name, NULL, synth_node_count++); + node = v9fs_add_dir_node(parent, mode, name, NULL, ++synth_node_count); v9fs_add_dir_node(node, parent->attr->mode, "..", parent->attr, parent->attr->inode); v9fs_add_dir_node(node, node->attr->mode, ".", @@ -130,7 +130,7 @@ int qemu_v9fs_synth_add_file(V9fsSynthNode *parent, int mode, mode = ((mode & 0777) | S_IFREG); node = g_new0(V9fsSynthNode, 1); node->attr = &node->actual_attr; - node->attr->inode = synth_node_count++; + node->attr->inode = ++synth_node_count; node->attr->nlink = 1; node->attr->read = read; node->attr->write = write; From 096af171274cc76c51bf11366ae257391ddfed2a Mon Sep 17 00:00:00 2001 From: Christian Schoenebeck Date: Fri, 29 Apr 2022 12:25:05 +0200 Subject: [PATCH 2/7] 9pfs: fix qemu_mknodat(S_IFREG) on macOS mknod() on macOS does not support creating regular files, so divert to openat_file() if S_IFREG is passed with mode argument. Furthermore, 'man 2 mknodat' on Linux says: "Zero file type is equivalent to type S_IFREG". Link: https://lore.kernel.org/qemu-devel/17933734.zYzKuhC07K@silver/ Signed-off-by: Christian Schoenebeck Reviewed-by: Will Cohen Reviewed-by: Greg Kurz Reviewed-by: Akihiko Odaki Message-Id: <3102ca936f88bc1f79d2a325e5bc68f48f54e6e3.1651228000.git.qemu_oss@crudebyte.com> --- hw/9pfs/9p-util-darwin.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/hw/9pfs/9p-util-darwin.c b/hw/9pfs/9p-util-darwin.c index bec0253474..e24d09763a 100644 --- a/hw/9pfs/9p-util-darwin.c +++ b/hw/9pfs/9p-util-darwin.c @@ -77,6 +77,15 @@ int fsetxattrat_nofollow(int dirfd, const char *filename, const char *name, int qemu_mknodat(int dirfd, const char *filename, mode_t mode, dev_t dev) { int preserved_errno, err; + + if (S_ISREG(mode) || !(mode & S_IFMT)) { + int fd = openat_file(dirfd, filename, O_CREAT, mode); + if (fd == -1) { + return fd; + } + close(fd); + return 0; + } if (!pthread_fchdir_np) { error_report_once("pthread_fchdir_np() not available on this version of macOS"); return -ENOTSUP; From 055ab89327bab83f1bd07e9de07f7628643d3d8d Mon Sep 17 00:00:00 2001 From: Christian Schoenebeck Date: Fri, 29 Apr 2022 12:25:11 +0200 Subject: [PATCH 3/7] 9pfs: fix qemu_mknodat(S_IFSOCK) on macOS mknod() on macOS does not support creating sockets, so divert to call sequence socket(), bind() and fchmodat() respectively if S_IFSOCK was passed with mode argument. Link: https://lore.kernel.org/qemu-devel/17933734.zYzKuhC07K@silver/ Signed-off-by: Christian Schoenebeck Reviewed-by: Greg Kurz Reviewed-by: Akihiko Odaki Message-Id: <2e7b5ecd7a6d83a538db4e8a22d8fb03e9e0f06e.1651228001.git.qemu_oss@crudebyte.com> [C.S. - Use AT_SYMLINK_NOFOLLOW instead of AT_SYMLINK_NOFOLLOW_ANY. ] Link: https://lore.kernel.org/qemu-devel/3704033.BMyLRrx2Jx@silver/ --- hw/9pfs/9p-util-darwin.c | 42 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) diff --git a/hw/9pfs/9p-util-darwin.c b/hw/9pfs/9p-util-darwin.c index e24d09763a..bd2dd81548 100644 --- a/hw/9pfs/9p-util-darwin.c +++ b/hw/9pfs/9p-util-darwin.c @@ -74,6 +74,42 @@ int fsetxattrat_nofollow(int dirfd, const char *filename, const char *name, */ #if defined CONFIG_PTHREAD_FCHDIR_NP +static int create_socket_file_at_cwd(const char *filename, mode_t mode) { + int fd, err; + struct sockaddr_un addr = { + .sun_family = AF_UNIX + }; + + err = snprintf(addr.sun_path, sizeof(addr.sun_path), "./%s", filename); + if (err < 0 || err >= sizeof(addr.sun_path)) { + errno = ENAMETOOLONG; + return -1; + } + fd = socket(PF_UNIX, SOCK_DGRAM, 0); + if (fd == -1) { + return fd; + } + err = bind(fd, (struct sockaddr *) &addr, sizeof(addr)); + if (err == -1) { + goto out; + } + /* + * FIXME: Should rather be using descriptor-based fchmod() on the + * socket file descriptor above (preferably before bind() call), + * instead of path-based fchmodat(), to prevent concurrent transient + * state issues between creating the named FIFO file at bind() and + * delayed adjustment of permissions at fchmodat(). However currently + * macOS (12.x) does not support such operations on socket file + * descriptors yet. + * + * Filed report with Apple: FB9997731 + */ + err = fchmodat(AT_FDCWD, filename, mode, AT_SYMLINK_NOFOLLOW); +out: + close_preserve_errno(fd); + return err; +} + int qemu_mknodat(int dirfd, const char *filename, mode_t mode, dev_t dev) { int preserved_errno, err; @@ -93,7 +129,11 @@ int qemu_mknodat(int dirfd, const char *filename, mode_t mode, dev_t dev) if (pthread_fchdir_np(dirfd) < 0) { return -1; } - err = mknod(filename, mode, dev); + if (S_ISSOCK(mode)) { + err = create_socket_file_at_cwd(filename, mode); + } else { + err = mknod(filename, mode, dev); + } preserved_errno = errno; /* Stop using the thread-local cwd */ pthread_fchdir_np(-1); From e5c88e2264ebd0bfe35b347b8cdca1e3af784d84 Mon Sep 17 00:00:00 2001 From: Christian Schoenebeck Date: Fri, 29 Apr 2022 12:25:15 +0200 Subject: [PATCH 4/7] 9pfs: fix wrong encoding of rdev field in Rgetattr on macOS The 'rdev' field in 9p reponse 'Rgetattr' is of type dev_t, which is actually a system dependant type and therefore both the size and encoding of dev_t differ between macOS and Linux. So far we have sent 'rdev' to guest in host's dev_t format as-is, which caused devices to appear with wrong device numbers on guests running on macOS hosts, eventually leading to various misbehaviours on guest in conjunction with device files. This patch fixes this issue by converting the device number from host's dev_t format to Linux dev_t format. As 9p request 'Tgettattr' is exclusive to protocol version 9p2000.L, it should be fair to assume that 'rdev' field is assumed to be in Linux dev_t format by client as well. Signed-off-by: Christian Schoenebeck Link: https://lore.kernel.org/qemu-devel/20220421093056.5ab1e7ed@bahia/ Reviewed-by: Greg Kurz Reviewed-by: Akihiko Odaki Message-Id: --- hw/9pfs/9p-util.h | 39 +++++++++++++++++++++++++++++++++++++++ hw/9pfs/9p.c | 2 +- 2 files changed, 40 insertions(+), 1 deletion(-) diff --git a/hw/9pfs/9p-util.h b/hw/9pfs/9p-util.h index 97e681e167..2cc9a5dbfb 100644 --- a/hw/9pfs/9p-util.h +++ b/hw/9pfs/9p-util.h @@ -19,6 +19,45 @@ #define O_PATH_9P_UTIL 0 #endif +#if !defined(CONFIG_LINUX) + +/* + * Generates a Linux device number (a.k.a. dev_t) for given device major + * and minor numbers. + * + * To be more precise: it generates a device number in glibc's format + * (MMMM_Mmmm_mmmM_MMmm, 64 bits) actually, which is compatible with + * Linux's format (mmmM_MMmm, 32 bits), as described in . + */ +static inline uint64_t makedev_dotl(uint32_t dev_major, uint32_t dev_minor) +{ + uint64_t dev; + + // from glibc sysmacros.h: + dev = (((uint64_t) (dev_major & 0x00000fffu)) << 8); + dev |= (((uint64_t) (dev_major & 0xfffff000u)) << 32); + dev |= (((uint64_t) (dev_minor & 0x000000ffu)) << 0); + dev |= (((uint64_t) (dev_minor & 0xffffff00u)) << 12); + return dev; +} + +#endif + +/* + * Converts given device number from host's device number format to Linux + * device number format. As both the size of type dev_t and encoding of + * dev_t is system dependant, we have to convert them for Linux guests if + * host is not running Linux. + */ +static inline uint64_t host_dev_to_dotl_dev(dev_t dev) +{ +#ifdef CONFIG_LINUX + return dev; +#else + return makedev_dotl(major(dev), minor(dev)); +#endif +} + #ifdef CONFIG_DARWIN #define qemu_fgetxattr(...) fgetxattr(__VA_ARGS__, 0, 0) #define qemu_lgetxattr(...) getxattr(__VA_ARGS__, 0, XATTR_NOFOLLOW) diff --git a/hw/9pfs/9p.c b/hw/9pfs/9p.c index 225f31fc31..4a296a0b94 100644 --- a/hw/9pfs/9p.c +++ b/hw/9pfs/9p.c @@ -1327,7 +1327,7 @@ static int stat_to_v9stat_dotl(V9fsPDU *pdu, const struct stat *stbuf, 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_rdev = host_dev_to_dotl_dev(stbuf->st_rdev); v9lstat->st_size = stbuf->st_size; v9lstat->st_blksize = stat_to_iounit(pdu, stbuf); v9lstat->st_blocks = stbuf->st_blocks; From 951fe2f89f46f5d51eead066556edc7369e23915 Mon Sep 17 00:00:00 2001 From: Christian Schoenebeck Date: Fri, 29 Apr 2022 12:25:18 +0200 Subject: [PATCH 5/7] 9pfs: fix wrong errno being sent to Linux client on macOS host Linux and macOS only share some errno definitions with equal macro name and value. In fact most mappings for errno are completely different on the two systems. This patch converts some important errno values from macOS host to corresponding Linux errno values before eventually sending such error codes along with 'Rlerror' replies (if 9p2000.L is used that is). Not having translated errnos before violated the 9p2000.L protocol spec, which says: " size[4] Rlerror tag[2] ecode[4] ... ecode is a numerical Linux errno. " https://github.com/chaos/diod/wiki/protocol#lerror----return-error-code This patch fixes a bunch of misbehaviours when running a Linux client on macOS host. For instance this patch fixes: mount -t 9p -o posixacl ... on Linux guest if security_mode=mapped was used for 9p server, which refused to mount successfully, because macOS returned ENOATTR==93 when client tried to retrieve POSIX ACL xattrs, because errno 93 is defined as EPROTONOSUPPORT==93 on Linux, so Linux client believed that xattrs were not supported by filesystem on host in general. Signed-off-by: Christian Schoenebeck Link: https://lore.kernel.org/qemu-devel/20220421124835.3e664669@bahia/ Reviewed-by: Greg Kurz Reviewed-by: Akihiko Odaki Message-Id: --- hw/9pfs/9p-util.h | 30 ++++++++++++++++++++++++++++++ hw/9pfs/9p.c | 2 ++ 2 files changed, 32 insertions(+) diff --git a/hw/9pfs/9p-util.h b/hw/9pfs/9p-util.h index 2cc9a5dbfb..c3526144c9 100644 --- a/hw/9pfs/9p-util.h +++ b/hw/9pfs/9p-util.h @@ -58,6 +58,36 @@ static inline uint64_t host_dev_to_dotl_dev(dev_t dev) #endif } +/* Translates errno from host -> Linux if needed */ +static inline int errno_to_dotl(int err) { +#if defined(CONFIG_LINUX) + /* nothing to translate (Linux -> Linux) */ +#elif defined(CONFIG_DARWIN) + /* + * translation mandatory for macOS hosts + * + * FIXME: Only most important errnos translated here yet, this should be + * extended to as many errnos being translated as possible in future. + */ + if (err == ENAMETOOLONG) { + err = 36; /* ==ENAMETOOLONG on Linux */ + } else if (err == ENOTEMPTY) { + err = 39; /* ==ENOTEMPTY on Linux */ + } else if (err == ELOOP) { + err = 40; /* ==ELOOP on Linux */ + } else if (err == ENOATTR) { + err = 61; /* ==ENODATA on Linux */ + } else if (err == ENOTSUP) { + err = 95; /* ==EOPNOTSUPP on Linux */ + } else if (err == EOPNOTSUPP) { + err = 95; /* ==EOPNOTSUPP on Linux */ + } +#else +#error Missing errno translation to Linux for this host system +#endif + return err; +} + #ifdef CONFIG_DARWIN #define qemu_fgetxattr(...) fgetxattr(__VA_ARGS__, 0, 0) #define qemu_lgetxattr(...) getxattr(__VA_ARGS__, 0, XATTR_NOFOLLOW) diff --git a/hw/9pfs/9p.c b/hw/9pfs/9p.c index 4a296a0b94..0cd0c14c2a 100644 --- a/hw/9pfs/9p.c +++ b/hw/9pfs/9p.c @@ -1054,6 +1054,8 @@ static void coroutine_fn pdu_complete(V9fsPDU *pdu, ssize_t len) } len += ret; id = P9_RERROR; + } else { + err = errno_to_dotl(err); } ret = pdu_marshal(pdu, len, "d", err); From 9ea3164611a63e898a979f2da24caa1abd29d906 Mon Sep 17 00:00:00 2001 From: Christian Schoenebeck Date: Fri, 29 Apr 2022 12:25:22 +0200 Subject: [PATCH 6/7] 9pfs: fix removing non-existent POSIX ACL xattr on macOS host When mapped POSIX ACL is used, we are ignoring errors when trying to remove a POSIX ACL xattr that does not exist. On Linux hosts we would get ENODATA in such cases, on macOS hosts however we get ENOATTR instead. As we can be sure that ENOATTR is defined as being identical on Linux hosts (at least by qemu/xattr.h), it is safe to fix this issue by simply comparing against ENOATTR instead of ENODATA. This patch fixes e.g. a command on Linux guest like: cp --preserve=mode old new Signed-off-by: Christian Schoenebeck Link: https://lore.kernel.org/qemu-devel/2866993.yOYK24bMf6@silver/ Reviewed-by: Greg Kurz Reviewed-by: Akihiko Odaki Message-Id: <34f81e9bffd7a3e65fb7aab5b56c107bd0aac960.1651228001.git.qemu_oss@crudebyte.com> --- hw/9pfs/9p-posix-acl.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/hw/9pfs/9p-posix-acl.c b/hw/9pfs/9p-posix-acl.c index eadae270dd..4b2cb3c66c 100644 --- a/hw/9pfs/9p-posix-acl.c +++ b/hw/9pfs/9p-posix-acl.c @@ -65,7 +65,11 @@ static int mp_pacl_removexattr(FsContext *ctx, int ret; ret = local_removexattr_nofollow(ctx, path, MAP_ACL_ACCESS); - if (ret == -1 && errno == ENODATA) { + /* + * macOS returns ENOATTR (!=ENODATA on macOS), whereas Linux returns + * ENODATA (==ENOATTR on Linux), so checking for ENOATTR is fine + */ + if (ret == -1 && errno == ENOATTR) { /* * We don't get ENODATA error when trying to remove a * posix acl that is not present. So don't throw the error @@ -115,7 +119,11 @@ static int mp_dacl_removexattr(FsContext *ctx, int ret; ret = local_removexattr_nofollow(ctx, path, MAP_ACL_DEFAULT); - if (ret == -1 && errno == ENODATA) { + /* + * macOS returns ENOATTR (!=ENODATA on macOS), whereas Linux returns + * ENODATA (==ENOATTR on Linux), so checking for ENOATTR is fine + */ + if (ret == -1 && errno == ENOATTR) { /* * We don't get ENODATA error when trying to remove a * posix acl that is not present. So don't throw the error From 063c75db2e03938b2fadb052c4661adae36e352c Mon Sep 17 00:00:00 2001 From: Christian Schoenebeck Date: Fri, 29 Apr 2022 12:25:29 +0200 Subject: [PATCH 7/7] 9pfs: fix qemu_mknodat() to always return -1 on error on macOS host qemu_mknodat() is expected to behave according to its POSIX API, and therefore should always return exactly -1 on any error, and errno should be set for the actual error code. Signed-off-by: Christian Schoenebeck Reviewed-by: Greg Kurz Reviewed-by: Akihiko Odaki Message-Id: --- hw/9pfs/9p-util-darwin.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/9pfs/9p-util-darwin.c b/hw/9pfs/9p-util-darwin.c index bd2dd81548..95146e7354 100644 --- a/hw/9pfs/9p-util-darwin.c +++ b/hw/9pfs/9p-util-darwin.c @@ -124,7 +124,8 @@ int qemu_mknodat(int dirfd, const char *filename, mode_t mode, dev_t dev) } if (!pthread_fchdir_np) { error_report_once("pthread_fchdir_np() not available on this version of macOS"); - return -ENOTSUP; + errno = ENOTSUP; + return -1; } if (pthread_fchdir_np(dirfd) < 0) { return -1;