summaryrefslogtreecommitdiff
path: root/fs/libfs.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/libfs.c')
-rw-r--r--fs/libfs.c195
1 files changed, 98 insertions, 97 deletions
diff --git a/fs/libfs.c b/fs/libfs.c
index 748ac5923154..9ea0ecc325a8 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -245,9 +245,16 @@ const struct inode_operations simple_dir_inode_operations = {
};
EXPORT_SYMBOL(simple_dir_inode_operations);
-/* 0 is '.', 1 is '..', so always start with offset 2 or more */
+/* simple_offset_add() never assigns these to a dentry */
enum {
- DIR_OFFSET_MIN = 2,
+ DIR_OFFSET_FIRST = 2, /* Find first real entry */
+ DIR_OFFSET_EOD = S32_MAX,
+};
+
+/* simple_offset_add() allocation range */
+enum {
+ DIR_OFFSET_MIN = DIR_OFFSET_FIRST + 1,
+ DIR_OFFSET_MAX = DIR_OFFSET_EOD - 1,
};
static void offset_set(struct dentry *dentry, long offset)
@@ -291,9 +298,10 @@ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry)
return -EBUSY;
ret = mtree_alloc_cyclic(&octx->mt, &offset, dentry, DIR_OFFSET_MIN,
- LONG_MAX, &octx->next_offset, GFP_KERNEL);
- if (ret < 0)
- return ret;
+ DIR_OFFSET_MAX, &octx->next_offset,
+ GFP_KERNEL);
+ if (unlikely(ret < 0))
+ return ret == -EBUSY ? -ENOSPC : ret;
offset_set(dentry, offset);
return 0;
@@ -330,38 +338,6 @@ void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry)
}
/**
- * simple_offset_empty - Check if a dentry can be unlinked
- * @dentry: dentry to be tested
- *
- * Returns 0 if @dentry is a non-empty directory; otherwise returns 1.
- */
-int simple_offset_empty(struct dentry *dentry)
-{
- struct inode *inode = d_inode(dentry);
- struct offset_ctx *octx;
- struct dentry *child;
- unsigned long index;
- int ret = 1;
-
- if (!inode || !S_ISDIR(inode->i_mode))
- return ret;
-
- index = DIR_OFFSET_MIN;
- octx = inode->i_op->get_offset_ctx(inode);
- mt_for_each(&octx->mt, child, index, LONG_MAX) {
- spin_lock(&child->d_lock);
- if (simple_positive(child)) {
- spin_unlock(&child->d_lock);
- ret = 0;
- break;
- }
- spin_unlock(&child->d_lock);
- }
-
- return ret;
-}
-
-/**
* simple_offset_rename - handle directory offsets for rename
* @old_dir: parent directory of source entry
* @old_dentry: dentry of source entry
@@ -454,14 +430,6 @@ void simple_offset_destroy(struct offset_ctx *octx)
mtree_destroy(&octx->mt);
}
-static int offset_dir_open(struct inode *inode, struct file *file)
-{
- struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode);
-
- file->private_data = (void *)ctx->next_offset;
- return 0;
-}
-
/**
* offset_dir_llseek - Advance the read position of a directory descriptor
* @file: an open directory whose position is to be updated
@@ -475,9 +443,6 @@ static int offset_dir_open(struct inode *inode, struct file *file)
*/
static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence)
{
- struct inode *inode = file->f_inode;
- struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode);
-
switch (whence) {
case SEEK_CUR:
offset += file->f_pos;
@@ -490,62 +455,89 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence)
return -EINVAL;
}
- /* In this case, ->private_data is protected by f_pos_lock */
- if (!offset)
- file->private_data = (void *)ctx->next_offset;
return vfs_setpos(file, offset, LONG_MAX);
}
-static struct dentry *offset_find_next(struct offset_ctx *octx, loff_t offset)
+static struct dentry *find_positive_dentry(struct dentry *parent,
+ struct dentry *dentry,
+ bool next)
{
- MA_STATE(mas, &octx->mt, offset, offset);
+ struct dentry *found = NULL;
+
+ spin_lock(&parent->d_lock);
+ if (next)
+ dentry = d_next_sibling(dentry);
+ else if (!dentry)
+ dentry = d_first_child(parent);
+ hlist_for_each_entry_from(dentry, d_sib) {
+ if (!simple_positive(dentry))
+ continue;
+ spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+ if (simple_positive(dentry))
+ found = dget_dlock(dentry);
+ spin_unlock(&dentry->d_lock);
+ if (likely(found))
+ break;
+ }
+ spin_unlock(&parent->d_lock);
+ return found;
+}
+
+static noinline_for_stack struct dentry *
+offset_dir_lookup(struct dentry *parent, loff_t offset)
+{
+ struct inode *inode = d_inode(parent);
+ struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode);
struct dentry *child, *found = NULL;
- rcu_read_lock();
- child = mas_find(&mas, LONG_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();
+ MA_STATE(mas, &octx->mt, offset, offset);
+
+ if (offset == DIR_OFFSET_FIRST)
+ found = find_positive_dentry(parent, NULL, false);
+ else {
+ rcu_read_lock();
+ child = mas_find_rev(&mas, DIR_OFFSET_MIN);
+ found = find_positive_dentry(parent, child, false);
+ rcu_read_unlock();
+ }
return found;
}
static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
- long offset = dentry2offset(dentry);
- return ctx->actor(ctx, dentry->d_name.name, dentry->d_name.len, offset,
- inode->i_ino, fs_umode_to_dtype(inode->i_mode));
+ return dir_emit(ctx, dentry->d_name.name, dentry->d_name.len,
+ inode->i_ino, fs_umode_to_dtype(inode->i_mode));
}
-static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, long last_index)
+static void offset_iterate_dir(struct file *file, struct dir_context *ctx)
{
- struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode);
+ struct dentry *dir = file->f_path.dentry;
struct dentry *dentry;
+ dentry = offset_dir_lookup(dir, ctx->pos);
+ if (!dentry)
+ goto out_eod;
while (true) {
- dentry = offset_find_next(octx, ctx->pos);
- if (!dentry)
- return;
+ struct dentry *next;
- if (dentry2offset(dentry) >= last_index) {
- dput(dentry);
- return;
- }
-
- if (!offset_dir_emit(ctx, dentry)) {
- dput(dentry);
- return;
- }
+ ctx->pos = dentry2offset(dentry);
+ if (!offset_dir_emit(ctx, dentry))
+ break;
- ctx->pos = dentry2offset(dentry) + 1;
+ next = find_positive_dentry(dir, dentry, true);
dput(dentry);
+
+ if (!next)
+ goto out_eod;
+ dentry = next;
}
+ dput(dentry);
+ return;
+
+out_eod:
+ ctx->pos = DIR_OFFSET_EOD;
}
/**
@@ -565,6 +557,8 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, lon
*
* On return, @ctx->pos contains an offset that will read the next entry
* in this directory when offset_readdir() is called again with @ctx.
+ * Caller places this value in the d_off field of the last entry in the
+ * user's buffer.
*
* Return values:
* %0 - Complete
@@ -572,26 +566,24 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, lon
static int offset_readdir(struct file *file, struct dir_context *ctx)
{
struct dentry *dir = file->f_path.dentry;
- long last_index = (long)file->private_data;
lockdep_assert_held(&d_inode(dir)->i_rwsem);
if (!dir_emit_dots(file, ctx))
return 0;
-
- offset_iterate_dir(d_inode(dir), ctx, last_index);
+ if (ctx->pos != DIR_OFFSET_EOD)
+ offset_iterate_dir(file, ctx);
return 0;
}
const struct file_operations simple_offset_dir_operations = {
- .open = offset_dir_open,
.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 *find_next_child(struct dentry *parent, struct dentry *prev)
{
struct dentry *child = NULL, *d;
@@ -611,6 +603,7 @@ static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev
dput(prev);
return child;
}
+EXPORT_SYMBOL(find_next_child);
void simple_recursive_removal(struct dentry *dentry,
void (*callback)(struct dentry *))
@@ -673,6 +666,7 @@ static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc)
s->s_blocksize_bits = PAGE_SHIFT;
s->s_magic = ctx->magic;
s->s_op = ctx->ops ?: &simple_super_operations;
+ s->s_export_op = ctx->eops;
s->s_xattr = ctx->xattr;
s->s_time_gran = 1;
root = new_inode(s);
@@ -1654,10 +1648,16 @@ struct inode *alloc_anon_inode(struct super_block *s)
* that it already _is_ on the dirty list.
*/
inode->i_state = I_DIRTY;
- inode->i_mode = S_IRUSR | S_IWUSR;
+ /*
+ * Historically anonymous inodes didn't have a type at all and
+ * userspace has come to rely on this. Internally they're just
+ * regular files but S_IFREG is masked off when reporting
+ * information to userspace.
+ */
+ inode->i_mode = S_IFREG | S_IRUSR | S_IWUSR;
inode->i_uid = current_fsuid();
inode->i_gid = current_fsgid();
- inode->i_flags |= S_PRIVATE;
+ inode->i_flags |= S_PRIVATE | S_ANON_INODE;
simple_inode_init_ts(inode);
return inode;
}
@@ -1789,7 +1789,7 @@ int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
{
const struct dentry *parent;
const struct inode *dir;
- char strbuf[DNAME_INLINE_LEN];
+ union shortname_store strbuf;
struct qstr qstr;
/*
@@ -1809,22 +1809,23 @@ int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
if (!dir || !IS_CASEFOLDED(dir))
return 1;
+ qstr.len = len;
+ qstr.name = str;
/*
* If the dentry name is stored in-line, then it may be concurrently
* modified by a rename. If this happens, the VFS will eventually retry
* the lookup, so it doesn't matter what ->d_compare() returns.
* However, it's unsafe to call utf8_strncasecmp() with an unstable
* string. Therefore, we have to copy the name into a temporary buffer.
+ * As above, len is guaranteed to match str, so the shortname case
+ * is exactly when str points to ->d_shortname.
*/
- if (len <= DNAME_INLINE_LEN - 1) {
- memcpy(strbuf, str, len);
- strbuf[len] = 0;
- str = strbuf;
+ if (qstr.name == dentry->d_shortname.string) {
+ strbuf = dentry->d_shortname; // NUL is guaranteed to be in there
+ qstr.name = strbuf.string;
/* prevent compiler from optimizing out the temporary buffer */
barrier();
}
- qstr.len = len;
- qstr.name = str;
return utf8_strncasecmp(dentry->d_sb->s_encoding, name, &qstr);
}
@@ -2119,7 +2120,7 @@ struct timespec64 simple_inode_init_ts(struct inode *inode)
}
EXPORT_SYMBOL(simple_inode_init_ts);
-static inline struct dentry *get_stashed_dentry(struct dentry **stashed)
+struct dentry *stashed_dentry_get(struct dentry **stashed)
{
struct dentry *dentry;
@@ -2221,7 +2222,7 @@ int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data,
const struct stashed_operations *sops = mnt->mnt_sb->s_fs_info;
/* See if dentry can be reused. */
- path->dentry = get_stashed_dentry(stashed);
+ path->dentry = stashed_dentry_get(stashed);
if (path->dentry) {
sops->put_data(data);
goto out_path;