summaryrefslogtreecommitdiff
path: root/fs/kernfs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-08-28 19:55:25 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2023-08-28 19:55:25 +0300
commitecd7db20474c3859d4d01f34aaabf41bd28c7d84 (patch)
tree70d787f3138a907c3e6eb53c403beac3e2bf91c9 /fs/kernfs
parent615e95831ec3d428cc554ac12e9439e2d66038d3 (diff)
parent572a3d1e5d3a3e335b92e2c28a63c0b27944480c (diff)
downloadlinux-ecd7db20474c3859d4d01f34aaabf41bd28c7d84.tar.xz
Merge tag 'v6.6-vfs.tmpfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs
Pull libfs and tmpfs updates from Christian Brauner: "This cycle saw a lot of work for tmpfs that required changes to the vfs layer. Andrew, Hugh, and I decided to take tmpfs through vfs this cycle. Things will go back to mm next cycle. Features ======== - By far the biggest work is the quota support for tmpfs. New tmpfs quota infrastructure is added to support it and a new QFMT_SHMEM uapi option is exposed. This offers user and group quotas to tmpfs (project quotas will be added later). Similar to other filesystems tmpfs quota are not supported within user namespaces yet. - Add support for user xattrs. While tmpfs already supports security xattrs (security.*) and POSIX ACLs for a long time it lacked support for user xattrs (user.*). With this pull request tmpfs will be able to support a limited number of user xattrs. This is accompanied by a fix (see below) to limit persistent simple xattr allocations. - Add support for stable directory offsets. Currently tmpfs relies on the libfs provided cursor-based mechanism for readdir. This causes issues when a tmpfs filesystem is exported via NFS. NFS clients do not open directories. Instead, each server-side readdir operation opens the directory, reads it, and then closes it. Since the cursor state for that directory is associated with the opened file it is discarded after each readdir operation. Such directory offsets are not just cached by NFS clients but also various userspace libraries based on these clients. As it stands there is no way to invalidate the caches when directory offsets have changed and the whole application depends on unchanging directory offsets. At LSFMM we discussed how to solve this problem and decided to support stable directory offsets. libfs now allows filesystems like tmpfs to use an xarrary to map a directory offset to a dentry. This mechanism is currently only used by tmpfs but can be supported by others as well. Fixes ===== - Change persistent simple xattrs allocations in libfs from GFP_KERNEL to GPF_KERNEL_ACCOUNT so they're subject to memory cgroup limits. Since this is a change to libfs it affects both tmpfs and kernfs. - Correctly verify {g,u}id mount options. A new filesystem context is created via fsopen() which records the namespace that becomes the owning namespace of the superblock when fsconfig(FSCONFIG_CMD_CREATE) is called for filesystems that are mountable in namespaces. However, fsconfig() calls can occur in a namespace different from the namespace where fsopen() has been called. Currently, when fsconfig() is called to set {g,u}id mount options the requested {g,u}id is mapped into a k{g,u}id according to the namespace where fsconfig() was called from. The resulting k{g,u}id is not guaranteed to be resolvable in the namespace of the filesystem (the one that fsopen() was called in). This means it's possible for an unprivileged user to create files owned by any group in a tmpfs mount since it's possible to set the setid bits on the tmpfs directory. The contract for {g,u}id mount options and {g,u}id values in general set from userspace has always been that they are translated according to the caller's idmapping. In so far, tmpfs has been doing the correct thing. But since tmpfs is mountable in unprivileged contexts it is also necessary to verify that the resulting {k,g}uid is representable in the namespace of the superblock to avoid such bugs. The new mount api's cross-namespace delegation abilities are already widely used. Having talked to a bunch of userspace this is the most faithful solution with minimal regression risks" * tag 'v6.6-vfs.tmpfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: tmpfs,xattr: GFP_KERNEL_ACCOUNT for simple xattrs mm: invalidation check mapping before folio_contains tmpfs: trivial support for direct IO tmpfs,xattr: enable limited user extended attributes tmpfs: track free_ispace instead of free_inodes xattr: simple_xattr_set() return old_xattr to be freed tmpfs: verify {g,u}id mount options correctly shmem: move spinlock into shmem_recalc_inode() to fix quota support libfs: Remove parent dentry locking in offset_iterate_dir() libfs: Add a lock class for the offset map's xa_lock shmem: stable directory offsets shmem: Refactor shmem_symlink() libfs: Add directory operations for stable offsets shmem: fix quota lock nesting in huge hole handling shmem: Add default quota limit mount options shmem: quota support shmem: prepare shmem quota infrastructure quota: Check presence of quota operation structures instead of ->quota_read and ->quota_write callbacks shmem: make shmem_get_inode() return ERR_PTR instead of NULL shmem: make shmem_inode_acct_block() return error
Diffstat (limited to 'fs/kernfs')
-rw-r--r--fs/kernfs/dir.c2
-rw-r--r--fs/kernfs/inode.c46
2 files changed, 30 insertions, 18 deletions
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 5a1a4af9d3d2..660995856a04 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -556,7 +556,7 @@ void kernfs_put(struct kernfs_node *kn)
kfree_const(kn->name);
if (kn->iattr) {
- simple_xattrs_free(&kn->iattr->xattrs);
+ simple_xattrs_free(&kn->iattr->xattrs, NULL);
kmem_cache_free(kernfs_iattrs_cache, kn->iattr);
}
spin_lock(&kernfs_idr_lock);
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index af37be68bf06..922719a343a7 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -305,11 +305,17 @@ int kernfs_xattr_get(struct kernfs_node *kn, const char *name,
int kernfs_xattr_set(struct kernfs_node *kn, const char *name,
const void *value, size_t size, int flags)
{
+ struct simple_xattr *old_xattr;
struct kernfs_iattrs *attrs = kernfs_iattrs(kn);
if (!attrs)
return -ENOMEM;
- return simple_xattr_set(&attrs->xattrs, name, value, size, flags, NULL);
+ old_xattr = simple_xattr_set(&attrs->xattrs, name, value, size, flags);
+ if (IS_ERR(old_xattr))
+ return PTR_ERR(old_xattr);
+
+ simple_xattr_free(old_xattr);
+ return 0;
}
static int kernfs_vfs_xattr_get(const struct xattr_handler *handler,
@@ -341,7 +347,7 @@ static int kernfs_vfs_user_xattr_add(struct kernfs_node *kn,
{
atomic_t *sz = &kn->iattr->user_xattr_size;
atomic_t *nr = &kn->iattr->nr_user_xattrs;
- ssize_t removed_size;
+ struct simple_xattr *old_xattr;
int ret;
if (atomic_inc_return(nr) > KERNFS_MAX_USER_XATTRS) {
@@ -354,13 +360,18 @@ static int kernfs_vfs_user_xattr_add(struct kernfs_node *kn,
goto dec_size_out;
}
- ret = simple_xattr_set(xattrs, full_name, value, size, flags,
- &removed_size);
-
- if (!ret && removed_size >= 0)
- size = removed_size;
- else if (!ret)
+ old_xattr = simple_xattr_set(xattrs, full_name, value, size, flags);
+ if (!old_xattr)
return 0;
+
+ if (IS_ERR(old_xattr)) {
+ ret = PTR_ERR(old_xattr);
+ goto dec_size_out;
+ }
+
+ ret = 0;
+ size = old_xattr->size;
+ simple_xattr_free(old_xattr);
dec_size_out:
atomic_sub(size, sz);
dec_count_out:
@@ -375,18 +386,19 @@ static int kernfs_vfs_user_xattr_rm(struct kernfs_node *kn,
{
atomic_t *sz = &kn->iattr->user_xattr_size;
atomic_t *nr = &kn->iattr->nr_user_xattrs;
- ssize_t removed_size;
- int ret;
+ struct simple_xattr *old_xattr;
- ret = simple_xattr_set(xattrs, full_name, value, size, flags,
- &removed_size);
+ old_xattr = simple_xattr_set(xattrs, full_name, value, size, flags);
+ if (!old_xattr)
+ return 0;
- if (removed_size >= 0) {
- atomic_sub(removed_size, sz);
- atomic_dec(nr);
- }
+ if (IS_ERR(old_xattr))
+ return PTR_ERR(old_xattr);
- return ret;
+ atomic_sub(old_xattr->size, sz);
+ atomic_dec(nr);
+ simple_xattr_free(old_xattr);
+ return 0;
}
static int kernfs_vfs_user_xattr_set(const struct xattr_handler *handler,