summaryrefslogtreecommitdiff
path: root/fs/libfs.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-08-28 09:55:25 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2023-08-28 09:55:25 -0700
commitecd7db20474c3859d4d01f34aaabf41bd28c7d84 (patch)
tree70d787f3138a907c3e6eb53c403beac3e2bf91c9 /fs/libfs.c
parent615e95831ec3d428cc554ac12e9439e2d66038d3 (diff)
parent572a3d1e5d3a3e335b92e2c28a63c0b27944480c (diff)
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/libfs.c')
-rw-r--r--fs/libfs.c248
1 files changed, 248 insertions, 0 deletions
diff --git a/fs/libfs.c b/fs/libfs.c
index a61878469dcd..2263d353855d 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -239,6 +239,254 @@ const struct inode_operations simple_dir_inode_operations = {
};
EXPORT_SYMBOL(simple_dir_inode_operations);
+static void offset_set(struct dentry *dentry, u32 offset)
+{
+ dentry->d_fsdata = (void *)((uintptr_t)(offset));
+}
+
+static u32 dentry2offset(struct dentry *dentry)
+{
+ return (u32)((uintptr_t)(dentry->d_fsdata));
+}
+
+static struct lock_class_key simple_offset_xa_lock;
+
+/**
+ * simple_offset_init - initialize an offset_ctx
+ * @octx: directory offset map to be initialized
+ *
+ */
+void simple_offset_init(struct offset_ctx *octx)
+{
+ xa_init_flags(&octx->xa, XA_FLAGS_ALLOC1);
+ lockdep_set_class(&octx->xa.xa_lock, &simple_offset_xa_lock);
+
+ /* 0 is '.', 1 is '..', so always start with offset 2 */
+ octx->next_offset = 2;
+}
+
+/**
+ * simple_offset_add - Add an entry to a directory's offset map
+ * @octx: directory offset ctx to be updated
+ * @dentry: new dentry being added
+ *
+ * Returns zero on success. @so_ctx and the dentry offset are updated.
+ * Otherwise, a negative errno value is returned.
+ */
+int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry)
+{
+ static const struct xa_limit limit = XA_LIMIT(2, U32_MAX);
+ u32 offset;
+ int ret;
+
+ if (dentry2offset(dentry) != 0)
+ return -EBUSY;
+
+ ret = xa_alloc_cyclic(&octx->xa, &offset, dentry, limit,
+ &octx->next_offset, GFP_KERNEL);
+ if (ret < 0)
+ return ret;
+
+ offset_set(dentry, offset);
+ return 0;
+}
+
+/**
+ * simple_offset_remove - Remove an entry to a directory's offset map
+ * @octx: directory offset ctx to be updated
+ * @dentry: dentry being removed
+ *
+ */
+void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry)
+{
+ u32 offset;
+
+ offset = dentry2offset(dentry);
+ if (offset == 0)
+ return;
+
+ xa_erase(&octx->xa, offset);
+ offset_set(dentry, 0);
+}
+
+/**
+ * simple_offset_rename_exchange - exchange rename with directory offsets
+ * @old_dir: parent of dentry being moved
+ * @old_dentry: dentry being moved
+ * @new_dir: destination parent
+ * @new_dentry: destination dentry
+ *
+ * Returns zero on success. Otherwise a negative errno is returned and the
+ * rename is rolled back.
+ */
+int simple_offset_rename_exchange(struct inode *old_dir,
+ struct dentry *old_dentry,
+ struct inode *new_dir,
+ struct dentry *new_dentry)
+{
+ struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir);
+ struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir);
+ u32 old_index = dentry2offset(old_dentry);
+ u32 new_index = dentry2offset(new_dentry);
+ int ret;
+
+ simple_offset_remove(old_ctx, old_dentry);
+ simple_offset_remove(new_ctx, new_dentry);
+
+ ret = simple_offset_add(new_ctx, old_dentry);
+ if (ret)
+ goto out_restore;
+
+ ret = simple_offset_add(old_ctx, new_dentry);
+ if (ret) {
+ simple_offset_remove(new_ctx, old_dentry);
+ goto out_restore;
+ }
+
+ ret = simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry);
+ if (ret) {
+ simple_offset_remove(new_ctx, old_dentry);
+ simple_offset_remove(old_ctx, new_dentry);
+ goto out_restore;
+ }
+ return 0;
+
+out_restore:
+ offset_set(old_dentry, old_index);
+ xa_store(&old_ctx->xa, old_index, old_dentry, GFP_KERNEL);
+ offset_set(new_dentry, new_index);
+ xa_store(&new_ctx->xa, new_index, new_dentry, GFP_KERNEL);
+ return ret;
+}
+
+/**
+ * simple_offset_destroy - Release offset map
+ * @octx: directory offset ctx that is about to be destroyed
+ *
+ * During fs teardown (eg. umount), a directory's offset map might still
+ * contain entries. xa_destroy() cleans out anything that remains.
+ */
+void simple_offset_destroy(struct offset_ctx *octx)
+{
+ xa_destroy(&octx->xa);
+}
+
+/**
+ * offset_dir_llseek - Advance the read position of a directory descriptor
+ * @file: an open directory whose position is to be updated
+ * @offset: a byte offset
+ * @whence: enumerator describing the starting position for this update
+ *
+ * SEEK_END, SEEK_DATA, and SEEK_HOLE are not supported for directories.
+ *
+ * Returns the updated read position if successful; otherwise a
+ * negative errno is returned and the read position remains unchanged.
+ */
+static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+ switch (whence) {
+ case SEEK_CUR:
+ offset += file->f_pos;
+ fallthrough;
+ case SEEK_SET:
+ if (offset >= 0)
+ break;
+ fallthrough;
+ default:
+ return -EINVAL;
+ }
+
+ return vfs_setpos(file, offset, U32_MAX);
+}
+
+static struct dentry *offset_find_next(struct xa_state *xas)
+{
+ struct dentry *child, *found = NULL;
+
+ rcu_read_lock();
+ child = xas_next_entry(xas, U32_MAX);
+ if (!child)
+ goto out;
+ spin_lock(&child->d_lock);
+ if (simple_positive(child))
+ found = dget_dlock(child);
+ spin_unlock(&child->d_lock);
+out:
+ rcu_read_unlock();
+ return found;
+}
+
+static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry)
+{
+ u32 offset = dentry2offset(dentry);
+ struct inode *inode = d_inode(dentry);
+
+ return ctx->actor(ctx, dentry->d_name.name, dentry->d_name.len, offset,
+ inode->i_ino, fs_umode_to_dtype(inode->i_mode));
+}
+
+static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
+{
+ struct offset_ctx *so_ctx = inode->i_op->get_offset_ctx(inode);
+ XA_STATE(xas, &so_ctx->xa, ctx->pos);
+ struct dentry *dentry;
+
+ while (true) {
+ dentry = offset_find_next(&xas);
+ if (!dentry)
+ break;
+
+ if (!offset_dir_emit(ctx, dentry)) {
+ dput(dentry);
+ break;
+ }
+
+ dput(dentry);
+ ctx->pos = xas.xa_index + 1;
+ }
+}
+
+/**
+ * offset_readdir - Emit entries starting at offset @ctx->pos
+ * @file: an open directory to iterate over
+ * @ctx: directory iteration context
+ *
+ * Caller must hold @file's i_rwsem to prevent insertion or removal of
+ * entries during this call.
+ *
+ * On entry, @ctx->pos contains an offset that represents the first entry
+ * to be read from the directory.
+ *
+ * The operation continues until there are no more entries to read, or
+ * until the ctx->actor indicates there is no more space in the caller's
+ * output buffer.
+ *
+ * On return, @ctx->pos contains an offset that will read the next entry
+ * in this directory when offset_readdir() is called again with @ctx.
+ *
+ * Return values:
+ * %0 - Complete
+ */
+static int offset_readdir(struct file *file, struct dir_context *ctx)
+{
+ struct dentry *dir = file->f_path.dentry;
+
+ lockdep_assert_held(&d_inode(dir)->i_rwsem);
+
+ if (!dir_emit_dots(file, ctx))
+ return 0;
+
+ offset_iterate_dir(d_inode(dir), ctx);
+ return 0;
+}
+
+const struct file_operations simple_offset_dir_operations = {
+ .llseek = offset_dir_llseek,
+ .iterate_shared = offset_readdir,
+ .read = generic_read_dir,
+ .fsync = noop_fsync,
+};
+
static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev)
{
struct dentry *child = NULL;