qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Dr. David Alan Gilbert (git)" <dgilbert@redhat.com>
To: qemu-devel@nongnu.org, peterx@redhat.com, philmd@redhat.com,
	zhangjiachen.jaycee@bytedance.com, mreitz@redhat.com
Cc: stefanha@redhat.com, quintela@redhat.com
Subject: [PULL 09/12] virtiofsd: Add mount ID to the lo_inode key
Date: Mon,  2 Nov 2020 19:56:54 +0000	[thread overview]
Message-ID: <20201102195657.219501-10-dgilbert@redhat.com> (raw)
In-Reply-To: <20201102195657.219501-1-dgilbert@redhat.com>

From: Max Reitz <mreitz@redhat.com>

Using st_dev is not sufficient to uniquely identify a mount: You can
mount the same device twice, but those are still separate trees, and
e.g. by mounting something else inside one of them, they may differ.

Using statx(), we can get a mount ID that uniquely identifies a mount.
If that is available, add it to the lo_inode key.

Most of this patch is taken from Miklos's mail here:
https://marc.info/?l=fuse-devel&m=160062521827983
(virtiofsd-use-mount-id.patch attachment)

Suggested-by: Miklos Szeredi <mszeredi@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20201102161859.156603-5-mreitz@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
 tools/virtiofsd/passthrough_ll.c      | 95 ++++++++++++++++++++++++---
 tools/virtiofsd/passthrough_seccomp.c |  1 +
 2 files changed, 86 insertions(+), 10 deletions(-)

diff --git a/tools/virtiofsd/passthrough_ll.c b/tools/virtiofsd/passthrough_ll.c
index a0beb986f3..34d107975f 100644
--- a/tools/virtiofsd/passthrough_ll.c
+++ b/tools/virtiofsd/passthrough_ll.c
@@ -94,6 +94,7 @@ struct lo_map {
 struct lo_key {
     ino_t ino;
     dev_t dev;
+    uint64_t mnt_id;
 };
 
 struct lo_inode {
@@ -166,6 +167,7 @@ struct lo_data {
     int readdirplus_set;
     int readdirplus_clear;
     int allow_direct_io;
+    bool use_statx;
     struct lo_inode root;
     GHashTable *inodes; /* protected by lo->mutex */
     struct lo_map ino_map; /* protected by lo->mutex */
@@ -219,7 +221,8 @@ static struct {
 /* That we loaded cap-ng in the current thread from the saved */
 static __thread bool cap_loaded = 0;
 
-static struct lo_inode *lo_find(struct lo_data *lo, struct stat *st);
+static struct lo_inode *lo_find(struct lo_data *lo, struct stat *st,
+                                uint64_t mnt_id);
 
 static int is_dot_or_dotdot(const char *name)
 {
@@ -741,12 +744,14 @@ out_err:
     fuse_reply_err(req, saverr);
 }
 
-static struct lo_inode *lo_find(struct lo_data *lo, struct stat *st)
+static struct lo_inode *lo_find(struct lo_data *lo, struct stat *st,
+                                uint64_t mnt_id)
 {
     struct lo_inode *p;
     struct lo_key key = {
         .ino = st->st_ino,
         .dev = st->st_dev,
+        .mnt_id = mnt_id,
     };
 
     pthread_mutex_lock(&lo->mutex);
@@ -774,6 +779,60 @@ static void posix_locks_value_destroy(gpointer data)
     free(plock);
 }
 
+static int do_statx(struct lo_data *lo, int dirfd, const char *pathname,
+                    struct stat *statbuf, int flags, uint64_t *mnt_id)
+{
+    int res;
+
+#if defined(CONFIG_STATX) && defined(STATX_MNT_ID)
+    if (lo->use_statx) {
+        struct statx statxbuf;
+
+        res = statx(dirfd, pathname, flags, STATX_BASIC_STATS | STATX_MNT_ID,
+                    &statxbuf);
+        if (!res) {
+            memset(statbuf, 0, sizeof(*statbuf));
+            statbuf->st_dev = makedev(statxbuf.stx_dev_major,
+                                      statxbuf.stx_dev_minor);
+            statbuf->st_ino = statxbuf.stx_ino;
+            statbuf->st_mode = statxbuf.stx_mode;
+            statbuf->st_nlink = statxbuf.stx_nlink;
+            statbuf->st_uid = statxbuf.stx_uid;
+            statbuf->st_gid = statxbuf.stx_gid;
+            statbuf->st_rdev = makedev(statxbuf.stx_rdev_major,
+                                       statxbuf.stx_rdev_minor);
+            statbuf->st_size = statxbuf.stx_size;
+            statbuf->st_blksize = statxbuf.stx_blksize;
+            statbuf->st_blocks = statxbuf.stx_blocks;
+            statbuf->st_atim.tv_sec = statxbuf.stx_atime.tv_sec;
+            statbuf->st_atim.tv_nsec = statxbuf.stx_atime.tv_nsec;
+            statbuf->st_mtim.tv_sec = statxbuf.stx_mtime.tv_sec;
+            statbuf->st_mtim.tv_nsec = statxbuf.stx_mtime.tv_nsec;
+            statbuf->st_ctim.tv_sec = statxbuf.stx_ctime.tv_sec;
+            statbuf->st_ctim.tv_nsec = statxbuf.stx_ctime.tv_nsec;
+
+            if (statxbuf.stx_mask & STATX_MNT_ID) {
+                *mnt_id = statxbuf.stx_mnt_id;
+            } else {
+                *mnt_id = 0;
+            }
+            return 0;
+        } else if (errno != ENOSYS) {
+            return -1;
+        }
+        lo->use_statx = false;
+        /* fallback */
+    }
+#endif
+    res = fstatat(dirfd, pathname, statbuf, flags);
+    if (res == -1) {
+        return -1;
+    }
+    *mnt_id = 0;
+
+    return 0;
+}
+
 /*
  * Increments nlookup and caller must release refcount using
  * lo_inode_put(&parent).
@@ -784,6 +843,7 @@ static int lo_do_lookup(fuse_req_t req, fuse_ino_t parent, const char *name,
     int newfd;
     int res;
     int saverr;
+    uint64_t mnt_id;
     struct lo_data *lo = lo_data(req);
     struct lo_inode *inode = NULL;
     struct lo_inode *dir = lo_inode(req, parent);
@@ -811,12 +871,13 @@ static int lo_do_lookup(fuse_req_t req, fuse_ino_t parent, const char *name,
         goto out_err;
     }
 
-    res = fstatat(newfd, "", &e->attr, AT_EMPTY_PATH | AT_SYMLINK_NOFOLLOW);
+    res = do_statx(lo, newfd, "", &e->attr, AT_EMPTY_PATH | AT_SYMLINK_NOFOLLOW,
+                   &mnt_id);
     if (res == -1) {
         goto out_err;
     }
 
-    inode = lo_find(lo, &e->attr);
+    inode = lo_find(lo, &e->attr, mnt_id);
     if (inode) {
         close(newfd);
     } else {
@@ -838,6 +899,7 @@ static int lo_do_lookup(fuse_req_t req, fuse_ino_t parent, const char *name,
         inode->fd = newfd;
         inode->key.ino = e->attr.st_ino;
         inode->key.dev = e->attr.st_dev;
+        inode->key.mnt_id = mnt_id;
         pthread_mutex_init(&inode->plock_mutex, NULL);
         inode->posix_locks = g_hash_table_new_full(
             g_direct_hash, g_direct_equal, NULL, posix_locks_value_destroy);
@@ -1090,15 +1152,23 @@ static struct lo_inode *lookup_name(fuse_req_t req, fuse_ino_t parent,
                                     const char *name)
 {
     int res;
+    uint64_t mnt_id;
     struct stat attr;
+    struct lo_data *lo = lo_data(req);
+    struct lo_inode *dir = lo_inode(req, parent);
 
-    res = fstatat(lo_fd(req, parent), name, &attr,
-                  AT_EMPTY_PATH | AT_SYMLINK_NOFOLLOW);
+    if (!dir) {
+        return NULL;
+    }
+
+    res = do_statx(lo, dir->fd, name, &attr,
+                   AT_EMPTY_PATH | AT_SYMLINK_NOFOLLOW, &mnt_id);
+    lo_inode_put(lo, &dir);
     if (res == -1) {
         return NULL;
     }
 
-    return lo_find(lo_data(req), &attr);
+    return lo_find(lo, &attr, mnt_id);
 }
 
 static void lo_rmdir(fuse_req_t req, fuse_ino_t parent, const char *name)
@@ -3266,6 +3336,7 @@ static void setup_root(struct lo_data *lo, struct lo_inode *root)
 {
     int fd, res;
     struct stat stat;
+    uint64_t mnt_id;
 
     fd = open("/", O_PATH);
     if (fd == -1) {
@@ -3273,7 +3344,8 @@ static void setup_root(struct lo_data *lo, struct lo_inode *root)
         exit(1);
     }
 
-    res = fstatat(fd, "", &stat, AT_EMPTY_PATH | AT_SYMLINK_NOFOLLOW);
+    res = do_statx(lo, fd, "", &stat, AT_EMPTY_PATH | AT_SYMLINK_NOFOLLOW,
+                   &mnt_id);
     if (res == -1) {
         fuse_log(FUSE_LOG_ERR, "fstatat(%s): %m\n", lo->source);
         exit(1);
@@ -3283,6 +3355,7 @@ static void setup_root(struct lo_data *lo, struct lo_inode *root)
     root->fd = fd;
     root->key.ino = stat.st_ino;
     root->key.dev = stat.st_dev;
+    root->key.mnt_id = mnt_id;
     root->nlookup = 2;
     g_atomic_int_set(&root->refcount, 2);
 }
@@ -3291,7 +3364,7 @@ static guint lo_key_hash(gconstpointer key)
 {
     const struct lo_key *lkey = key;
 
-    return (guint)lkey->ino + (guint)lkey->dev;
+    return (guint)lkey->ino + (guint)lkey->dev + (guint)lkey->mnt_id;
 }
 
 static gboolean lo_key_equal(gconstpointer a, gconstpointer b)
@@ -3299,7 +3372,7 @@ static gboolean lo_key_equal(gconstpointer a, gconstpointer b)
     const struct lo_key *la = a;
     const struct lo_key *lb = b;
 
-    return la->ino == lb->ino && la->dev == lb->dev;
+    return la->ino == lb->ino && la->dev == lb->dev && la->mnt_id == lb->mnt_id;
 }
 
 static void fuse_lo_data_cleanup(struct lo_data *lo)
@@ -3445,6 +3518,8 @@ int main(int argc, char *argv[])
         exit(1);
     }
 
+    lo.use_statx = true;
+
     se = fuse_session_new(&args, &lo_oper, sizeof(lo_oper), &lo);
     if (se == NULL) {
         goto err_out1;
diff --git a/tools/virtiofsd/passthrough_seccomp.c b/tools/virtiofsd/passthrough_seccomp.c
index 672fb72a31..11623f56f2 100644
--- a/tools/virtiofsd/passthrough_seccomp.c
+++ b/tools/virtiofsd/passthrough_seccomp.c
@@ -76,6 +76,7 @@ static const int syscall_whitelist[] = {
     SCMP_SYS(mremap),
     SCMP_SYS(munmap),
     SCMP_SYS(newfstatat),
+    SCMP_SYS(statx),
     SCMP_SYS(open),
     SCMP_SYS(openat),
     SCMP_SYS(ppoll),
-- 
2.28.0



  parent reply	other threads:[~2020-11-02 20:10 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-02 19:56 [PULL 00/12] migration queue Dr. David Alan Gilbert (git)
2020-11-02 19:56 ` [PULL 01/12] migration: Unify reset of last_rb on destination node when recover Dr. David Alan Gilbert (git)
2020-11-02 19:56 ` [PULL 02/12] migration: Postpone the kick of the fault thread after recover Dr. David Alan Gilbert (git)
2020-11-02 19:56 ` [PULL 03/12] virtiofsd: Seccomp: Add 'send' for syslog Dr. David Alan Gilbert (git)
2020-11-02 19:56 ` [PULL 04/12] tools/virtiofsd: Check vu_init() return value (CID 1435958) Dr. David Alan Gilbert (git)
2020-11-02 19:56 ` [PULL 05/12] virtiofsd: Fix the help message of posix lock Dr. David Alan Gilbert (git)
2020-11-02 19:56 ` [PULL 06/12] virtiofsd: Check FUSE_SUBMOUNTS Dr. David Alan Gilbert (git)
2020-11-02 19:56 ` [PULL 07/12] virtiofsd: Add attr_flags to fuse_entry_param Dr. David Alan Gilbert (git)
2020-11-02 19:56 ` [PULL 08/12] meson.build: Check for statx() Dr. David Alan Gilbert (git)
2020-11-02 19:56 ` Dr. David Alan Gilbert (git) [this message]
2020-11-02 19:56 ` [PULL 10/12] virtiofsd: Announce sub-mount points Dr. David Alan Gilbert (git)
2020-11-03 10:24   ` Max Reitz
2020-11-03 10:29     ` Dr. David Alan Gilbert
2020-11-02 19:56 ` [PULL 11/12] tests/acceptance/boot_linux: Accept SSH pubkey Dr. David Alan Gilbert (git)
2020-11-02 19:56 ` [PULL 12/12] tests/acceptance: Add virtiofs_submounts.py Dr. David Alan Gilbert (git)
2020-11-03 10:37 ` [PULL 00/12] migration queue Peter Maydell

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20201102195657.219501-10-dgilbert@redhat.com \
    --to=dgilbert@redhat.com \
    --cc=mreitz@redhat.com \
    --cc=peterx@redhat.com \
    --cc=philmd@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=quintela@redhat.com \
    --cc=stefanha@redhat.com \
    --cc=zhangjiachen.jaycee@bytedance.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).