This adds backing support for FUSE_READDIR Signed-off-by: Daniel Rosenberg <drosen@xxxxxxxxxx> Signed-off-by: Paul Lawrence <paullawrence@xxxxxxxxxx> --- fs/fuse/backing.c | 202 ++++++++++++++++++++++++++++++++++++++ fs/fuse/fuse_i.h | 6 ++ fs/fuse/readdir.c | 5 + include/uapi/linux/fuse.h | 6 ++ 4 files changed, 219 insertions(+) diff --git a/fs/fuse/backing.c b/fs/fuse/backing.c index c813237b6599..0182236c2735 100644 --- a/fs/fuse/backing.c +++ b/fs/fuse/backing.c @@ -1657,6 +1657,208 @@ int fuse_bpf_unlink(int *out, struct inode *dir, struct dentry *entry) dir, entry); } +struct fuse_read_args { + struct fuse_read_in in; + struct fuse_read_out out; + struct fuse_buffer buffer; +}; + +static int fuse_readdir_initialize_in(struct bpf_fuse_args *fa, struct fuse_read_args *args, + struct file *file, struct dir_context *ctx, + bool *force_again, bool *allow_force, bool is_continued) +{ + struct fuse_file *ff = file->private_data; + + *fa = (struct bpf_fuse_args) { + .info = (struct bpf_fuse_meta_info) { + .nodeid = ff->nodeid, + .opcode = FUSE_READDIR, + }, + .in_numargs = 1, + .in_args[0] = (struct bpf_fuse_arg) { + .size = sizeof(args->in), + .value = &args->in, + }, + }; + + args->in = (struct fuse_read_in) { + .fh = ff->fh, + .offset = ctx->pos, + .size = PAGE_SIZE, + }; + + *force_again = false; + *allow_force = true; + return 0; +} + +static int fuse_readdir_initialize_out(struct bpf_fuse_args *fa, struct fuse_read_args *args, + struct file *file, struct dir_context *ctx, + bool *force_again, bool *allow_force, bool is_continued) +{ + u8 *page = (u8 *)__get_free_page(GFP_KERNEL); + + if (!page) + return -ENOMEM; + + fa->flags = FUSE_BPF_OUT_ARGVAR; + fa->out_numargs = 2; + fa->out_args[0] = (struct bpf_fuse_arg) { + .size = sizeof(args->out), + .value = &args->out, + }; + fa->out_args[1] = (struct bpf_fuse_arg) { + .is_buffer = true, + .buffer = &args->buffer, + }; + args->out = (struct fuse_read_out) { + .again = 0, + .offset = 0, + }; + args->buffer = (struct fuse_buffer) { + .data = page, + .size = PAGE_SIZE, + .alloc_size = PAGE_SIZE, + .max_size = PAGE_SIZE, + .flags = BPF_FUSE_VARIABLE_SIZE, + }; + + return 0; +} + +struct fusebpf_ctx { + struct dir_context ctx; + u8 *addr; + size_t offset; +}; + +static bool filldir(struct dir_context *ctx, const char *name, int namelen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct fusebpf_ctx *ec = container_of(ctx, struct fusebpf_ctx, ctx); + struct fuse_dirent *fd = (struct fuse_dirent *)(ec->addr + ec->offset); + + if (ec->offset + sizeof(struct fuse_dirent) + namelen > PAGE_SIZE) + return false; + + *fd = (struct fuse_dirent) { + .ino = ino, + .off = offset, + .namelen = namelen, + .type = d_type, + }; + + memcpy(fd->name, name, namelen); + ec->offset += FUSE_DIRENT_SIZE(fd); + + return true; +} + +static int parse_dirfile(char *buf, size_t nbytes, struct dir_context *ctx, + loff_t next_offset) +{ + char *buf_start = buf; + + while (nbytes >= FUSE_NAME_OFFSET) { + struct fuse_dirent *dirent = (struct fuse_dirent *) buf; + size_t reclen = FUSE_DIRENT_SIZE(dirent); + + if (!dirent->namelen || dirent->namelen > FUSE_NAME_MAX) + return -EIO; + if (reclen > nbytes) + break; + if (memchr(dirent->name, '/', dirent->namelen) != NULL) + return -EIO; + + ctx->pos = dirent->off; + if (!dir_emit(ctx, dirent->name, dirent->namelen, dirent->ino, + dirent->type)) { + // If we can't make any progress, user buffer is too small + if (buf == buf_start) + return -EINVAL; + else + return 0; + } + + buf += reclen; + nbytes -= reclen; + } + ctx->pos = next_offset; + + return 0; +} + +static int fuse_readdir_backing(struct bpf_fuse_args *fa, int *out, + struct file *file, struct dir_context *ctx, + bool *force_again, bool *allow_force, bool is_continued) +{ + struct fuse_file *ff = file->private_data; + struct file *backing_dir = ff->backing_file; + struct fuse_read_out *fro = fa->out_args[0].value; + struct fusebpf_ctx ec; + + ec = (struct fusebpf_ctx) { + .ctx.actor = filldir, + .ctx.pos = ctx->pos, + .addr = fa->out_args[1].buffer->data, + }; + + if (!ec.addr) + return -ENOMEM; + + if (!is_continued) + backing_dir->f_pos = file->f_pos; + + *out = iterate_dir(backing_dir, &ec.ctx); + if (ec.offset == 0) + *allow_force = false; + fa->out_args[1].buffer->size = ec.offset; + + fro->offset = ec.ctx.pos; + fro->again = false; + + return *out; +} + +static int fuse_readdir_finalize(struct bpf_fuse_args *fa, int *out, + struct file *file, struct dir_context *ctx, + bool *force_again, bool *allow_force, bool is_continued) +{ + struct fuse_read_out *fro = fa->out_args[0].value; + struct fuse_file *ff = file->private_data; + struct file *backing_dir = ff->backing_file; + + *out = parse_dirfile(fa->out_args[1].buffer->data, fa->out_args[1].buffer->size, ctx, fro->offset); + *force_again = !!fro->again; + if (*force_again && !*allow_force) + *out = -EINVAL; + + backing_dir->f_pos = ctx->pos; + + free_page((unsigned long)fa->out_args[1].buffer->data); + return *out; +} + +int fuse_bpf_readdir(int *out, struct inode *inode, struct file *file, struct dir_context *ctx) +{ + int ret; + bool allow_force; + bool force_again = false; + bool is_continued = false; + +again: + ret = bpf_fuse_backing(inode, struct fuse_read_args, out, + fuse_readdir_initialize_in, fuse_readdir_initialize_out, + fuse_readdir_backing, fuse_readdir_finalize, + file, ctx, &force_again, &allow_force, is_continued); + if (force_again && *out >= 0) { + is_continued = true; + goto again; + } + + return ret; +} + static int fuse_access_initialize_in(struct bpf_fuse_args *fa, struct fuse_access_in *in, struct inode *inode, int mask) { diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index bd187dbf20b2..ab52003de194 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -1452,6 +1452,7 @@ int fuse_bpf_file_read_iter(ssize_t *out, struct inode *inode, struct kiocb *ioc int fuse_bpf_file_write_iter(ssize_t *out, struct inode *inode, struct kiocb *iocb, struct iov_iter *from); int fuse_bpf_file_fallocate(int *out, struct inode *inode, struct file *file, int mode, loff_t offset, loff_t length); int fuse_bpf_lookup(struct dentry **out, struct inode *dir, struct dentry *entry, unsigned int flags); +int fuse_bpf_readdir(int *out, struct inode *inode, struct file *file, struct dir_context *ctx); int fuse_bpf_access(int *out, struct inode *inode, int mask); #else @@ -1522,6 +1523,11 @@ static inline int fuse_bpf_lookup(struct dentry **out, struct inode *dir, struct return 0; } +static inline int fuse_bpf_readdir(int *out, struct inode *inode, struct file *file, struct dir_context *ctx) +{ + return 0; +} + static inline int fuse_bpf_access(int *out, struct inode *inode, int mask) { return 0; diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index c66a54d6c7d3..53a1fd756772 100644 --- a/fs/fuse/readdir.c +++ b/fs/fuse/readdir.c @@ -20,6 +20,8 @@ static bool fuse_use_readdirplus(struct inode *dir, struct dir_context *ctx) if (!fc->do_readdirplus) return false; + if (fi->nodeid == 0) + return false; if (!fc->readdirplus_auto) return true; if (test_and_clear_bit(FUSE_I_ADVISE_RDPLUS, &fi->state)) @@ -592,6 +594,9 @@ int fuse_readdir(struct file *file, struct dir_context *ctx) if (fuse_is_bad(inode)) return -EIO; + if (fuse_bpf_readdir(&err, inode, file, ctx)) + return err; + mutex_lock(&ff->readdir.lock); err = UNCACHED; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 8efaa9eecc5f..3417717c1a55 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -811,6 +811,12 @@ struct fuse_read_in { uint32_t padding; }; +struct fuse_read_out { + uint64_t offset; + uint32_t again; + uint32_t padding; +}; + // This is likely not what we want struct fuse_read_iter_out { uint64_t ret; -- 2.44.0.478.gd926399ef9-goog