[16/26] fuse-bpf: support FUSE_READDIR

Message ID	20220926231822.994383-17-drosen@google.com (mailing list archive)
State	Changes Requested
Delegated to:	BPF
Headers	show Return-Path: <bpf-owner@kernel.org> Date: Mon, 26 Sep 2022 16:18:12 -0700 In-Reply-To: <20220926231822.994383-1-drosen@google.com> Mime-Version: 1.0 References: <20220926231822.994383-1-drosen@google.com> Message-ID: <20220926231822.994383-17-drosen@google.com> Subject: [PATCH 16/26] fuse-bpf: support FUSE_READDIR From: Daniel Rosenberg <drosen@google.com> To: Miklos Szeredi <miklos@szeredi.hu>, Alexei Starovoitov <ast@kernel.org>, Daniel Borkmann <daniel@iogearbox.net>, John Fastabend <john.fastabend@gmail.com> Cc: Andrii Nakryiko <andrii@kernel.org>, Martin KaFai Lau <martin.lau@linux.dev>, Song Liu <song@kernel.org>, Yonghong Song <yhs@fb.com>, KP Singh <kpsingh@kernel.org>, Stanislav Fomichev <sdf@google.com>, Hao Luo <haoluo@google.com>, Jiri Olsa <jolsa@kernel.org>, Daniel Rosenberg <drosen@google.com>, Paul Lawrence <paullawrence@google.com>, Alessio Balsini <balsini@google.com>, David Anderson <dvander@google.com>, Sandeep Patil <sspatil@google.com>, linux-fsdevel@vger.kernel.org, bpf@vger.kernel.org, kernel-team@android.com Content-Type: text/plain; charset="UTF-8" Precedence: bulk
Series	FUSE BPF: A Stacked Filesystem Extension for FUSE \| expand [00/26] FUSE BPF: A Stacked Filesystem Extension for FUSE [01/26] bpf: verifier: Allow for multiple packets [02/26] bpf: verifier: Allow single packet invalidation [03/26] fuse-bpf: Update uapi for fuse-bpf [04/26] fuse-bpf: Add BPF supporting functions [05/26] fs: Generic function to convert iocb to rw flags [06/26] bpf: Export bpf_prog_fops [07/26] fuse-bpf: Prepare for fuse-bpf patch [08/26] fuse: Add fuse-bpf, a stacked fs extension for FUSE [09/26] fuse-bpf: Don't support export_operations [10/26] fuse-bpf: Partially add mapping support [11/26] fuse-bpf: Add lseek support [12/26] fuse-bpf: Add support for fallocate [13/26] fuse-bpf: Support file/dir open/close [14/26] fuse-bpf: Support mknod/unlink/mkdir/rmdir [15/26] fuse-bpf: Add support for read/write iter [16/26] fuse-bpf: support FUSE_READDIR [17/26] fuse-bpf: Add support for sync operations [18/26] fuse-bpf: Add Rename support [19/26] fuse-bpf: Add attr support [20/26] fuse-bpf: Add support for FUSE_COPY_FILE_RANGE [21/26] fuse-bpf: Add xattr support [22/26] fuse-bpf: Add symlink/link support [23/26] fuse-bpf: allow mounting with no userspace daemon [24/26] fuse-bpf: Call bpf for pre/post filters [25/26] fuse-bpf: Add userspace pre/post filters

Context	Check	Description
bpf/vmtest-bpf-PR	fail	PR summary
bpf/vmtest-bpf-VM_Test-1	pending	Logs for ${{ matrix.test }} on ${{ matrix.arch }} with ${{ matrix.toolchain }}
bpf/vmtest-bpf-VM_Test-2	fail	Logs for build for s390x with gcc
bpf/vmtest-bpf-VM_Test-3	fail	Logs for build for x86_64 with gcc
bpf/vmtest-bpf-VM_Test-4	fail	Logs for build for x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-5	success	Logs for llvm-toolchain
bpf/vmtest-bpf-VM_Test-6	success	Logs for set-matrix

diff --git a/fs/fuse/backing.c b/fs/fuse/backing.c index cf4ad9f4fe10..a31199064dc7 100644 --- a/fs/fuse/backing.c +++ b/fs/fuse/backing.c @@ -1312,6 +1312,168 @@ int fuse_unlink_finalize(struct bpf_fuse_args *fa, int *out, return 0; } +int fuse_readdir_initialize_in(struct bpf_fuse_args *fa, struct fuse_read_io *frio, + 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) { + .nodeid = ff->nodeid, + .opcode = FUSE_READDIR, + .in_numargs = 1, + .in_args[0] = (struct bpf_fuse_arg) { + .size = sizeof(frio->fri), + .value = &frio->fri, + }, + }; + + frio->fri = (struct fuse_read_in) { + .fh = ff->fh, + .offset = ctx->pos, + .size = PAGE_SIZE, + }; + + *force_again = false; + *allow_force = true; + return 0; +} + +int fuse_readdir_initialize_out(struct bpf_fuse_args *fa, struct fuse_read_io *frio, + 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(frio->fro), + .value = &frio->fro, + }; + fa->out_args[1] = (struct bpf_fuse_arg) { + .size = PAGE_SIZE, + .max_size = PAGE_SIZE, + .flags = BPF_FUSE_VARIABLE_SIZE, + .value = page, + }; + frio->fro = (struct fuse_read_out) { + .again = 0, + .offset = 0, + }; + + return 0; +} + +struct extfuse_ctx { + struct dir_context ctx; + u8 *addr; + size_t offset; +}; + +static int filldir(struct dir_context *ctx, const char *name, int namelen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct extfuse_ctx *ec = container_of(ctx, struct extfuse_ctx, ctx); + struct fuse_dirent *fd = (struct fuse_dirent *)(ec->addr + ec->offset); + + if (ec->offset + sizeof(struct fuse_dirent) + namelen > PAGE_SIZE) + return -ENOMEM; + + *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 0; +} + +static int parse_dirfile(char *buf, size_t nbytes, struct dir_context *ctx) +{ + 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)) + break; + + buf += reclen; + nbytes -= reclen; + } + + return 0; +} + + +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 extfuse_ctx ec; + + ec = (struct extfuse_ctx) { + .ctx.actor = filldir, + .ctx.pos = ctx->pos, + .addr = fa->out_args[1].value, + }; + + 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].size = ec.offset; + + fro->offset = ec.ctx.pos; + fro->again = false; + + return *out; +} + +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].value, fa->out_args[1].size, ctx); + *force_again = !!fro->again; + if (*force_again && !*allow_force) + *out = -EINVAL; + + ctx->pos = fro->offset; + backing_dir->f_pos = fro->offset; + + free_page((unsigned long)fa->out_args[1].value); + return *out; +} + int fuse_access_initialize_in(struct bpf_fuse_args *fa, struct fuse_access_in *fai, struct inode *inode, int mask) { diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index f427a7bb367c..8780a50be244 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -1572,6 +1572,24 @@ int fuse_lookup_finalize(struct bpf_fuse_args *fa, struct dentry **out, struct inode *dir, struct dentry *entry, unsigned int flags); int fuse_revalidate_backing(struct dentry *entry, unsigned int flags); +struct fuse_read_io { + struct fuse_read_in fri; + struct fuse_read_out fro; +}; + +int fuse_readdir_initialize_in(struct bpf_fuse_args *fa, struct fuse_read_io *frio, + struct file *file, struct dir_context *ctx, + bool *force_again, bool *allow_force, bool is_continued); +int fuse_readdir_initialize_out(struct bpf_fuse_args *fa, struct fuse_read_io *frio, + struct file *file, struct dir_context *ctx, + bool *force_again, bool *allow_force, bool is_continued); +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); +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); + int fuse_access_initialize_in(struct bpf_fuse_args *fa, struct fuse_access_in *fai, struct inode *inode, int mask); int fuse_access_initialize_out(struct bpf_fuse_args *fa, struct fuse_access_in *fai, diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index b4e565711045..07da8570e337 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)) @@ -571,6 +573,26 @@ int fuse_readdir(struct file *file, struct dir_context *ctx) struct inode *inode = file_inode(file); int err; +#ifdef CONFIG_FUSE_BPF + bool bpf_ret = false; + bool allow_force; + bool force_again = false; + bool is_continued = false; + +again: + bpf_ret = fuse_bpf_backing(inode, struct fuse_read_io, err, + 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 && err >= 0) { + is_continued = true; + goto again; + } + + if (bpf_ret) + return err; +#endif + if (fuse_is_bad(inode)) return -EIO; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 8c80c146e69b..b7736cb4bdaf 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -701,6 +701,12 @@ struct fuse_read_in { uint32_t padding; }; +struct fuse_read_out { + uint64_t offset; + uint32_t again; + uint32_t padding; +}; + #define FUSE_COMPAT_WRITE_IN_SIZE 24 struct fuse_write_in {

[16/26] fuse-bpf: support FUSE_READDIR

Checks

Commit Message

Patch