BPF List
 help / color / mirror / Atom feed
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
Subject: [PATCH 25/26] fuse-bpf: Add userspace pre/post filters
Date: Mon, 26 Sep 2022 16:18:21 -0700	[thread overview]
Message-ID: <20220926231822.994383-26-drosen@google.com> (raw)
In-Reply-To: <20220926231822.994383-1-drosen@google.com>

This allows fuse-bpf to call out to userspace to handle pre and post
filters. Any of the inputs may be changed by the prefilter, so we must
handle up to 3 outputs. For the postfilter, our inputs include the
output arguments, so we must handle up to 5 inputs.

As long as you don't request both pre-filter and post-filter in
userspace, we will end up doing fewer round trips to userspace.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
---
 fs/fuse/backing.c        | 70 ++++++++++++++++++++++++++++++++++++++++
 fs/fuse/dev.c            |  2 ++
 fs/fuse/fuse_i.h         | 42 ++++++++++++++++++++++--
 include/linux/bpf_fuse.h |  1 +
 4 files changed, 113 insertions(+), 2 deletions(-)

diff --git a/fs/fuse/backing.c b/fs/fuse/backing.c
index 485b6f1e8503..7a3b1fdb2c56 100644
--- a/fs/fuse/backing.c
+++ b/fs/fuse/backing.c
@@ -2681,3 +2681,73 @@ void __exit fuse_bpf_cleanup(void)
 {
 	kmem_cache_destroy(fuse_bpf_aio_request_cachep);
 }
+
+static ssize_t fuse_bpf_simple_request(struct fuse_mount *fm, struct bpf_fuse_args *fa,
+				       unsigned short in_numargs, unsigned short out_numargs,
+				       struct bpf_fuse_arg *out_arg_array, bool add_out_to_in)
+{
+	int i;
+	uint32_t max_size;
+	ssize_t res;
+
+	struct fuse_args args = {
+		.nodeid = fa->nodeid,
+		.opcode = fa->opcode,
+		.error_in = fa->error_in,
+		.in_numargs = in_numargs,
+		.out_numargs = out_numargs,
+		.force = !!(fa->flags & FUSE_BPF_FORCE),
+		.out_argvar = !!(fa->flags & FUSE_BPF_OUT_ARGVAR),
+		.is_lookup = !!(fa->flags & FUSE_BPF_IS_LOOKUP),
+	};
+
+	/* Set in args */
+	for (i = 0; i < fa->in_numargs; ++i)
+		args.in_args[i] = (struct fuse_in_arg) {
+			.size = fa->in_args[i].size,
+			.value = fa->in_args[i].value,
+		};
+	if (add_out_to_in) {
+		for (i = 0; i < fa->out_numargs; ++i)
+			args.in_args[fa->in_numargs + i] = (struct fuse_in_arg) {
+				.size = fa->out_args[i].size,
+				.value = fa->out_args[i].value,
+			};
+	}
+
+	/* All out args must be writeable */
+	for (i = 0; i < out_numargs; ++i) {
+		max_size = out_arg_array[i].max_size ?: out_arg_array[i].size;
+		if (!bpf_fuse_get_writeable(&out_arg_array[i], max_size, true))
+			return -ENOMEM;
+	}
+
+	/* Set out args */
+	for (i = 0; i < out_numargs; ++i)
+		args.out_args[i] = (struct fuse_arg) {
+			.size = out_arg_array[i].size,
+			.value = out_arg_array[i].value,
+		};
+
+	res = fuse_simple_request(fm, &args);
+
+	/* update used areas of buffers */
+	for (i = 0; i < out_numargs; ++i)
+		if (out_arg_array[i].flags & BPF_FUSE_VARIABLE_SIZE)
+			out_arg_array[i].size = args.out_args[i].size;
+	fa->ret = args.ret;
+
+	return res;
+}
+
+ssize_t fuse_prefilter_simple_request(struct fuse_mount *fm, struct bpf_fuse_args *fa)
+{
+	return fuse_bpf_simple_request(fm, fa, fa->in_numargs, fa->in_numargs,
+				       fa->in_args, false);
+}
+
+ssize_t fuse_postfilter_simple_request(struct fuse_mount *fm, struct bpf_fuse_args *fa)
+{
+	return fuse_bpf_simple_request(fm, fa, fa->in_numargs + fa->out_numargs, fa->out_numargs,
+				       fa->out_args, true);
+}
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 626dbbf92874..765bc95bd560 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -520,6 +520,8 @@ ssize_t fuse_simple_request(struct fuse_mount *fm, struct fuse_args *args)
 		BUG_ON(args->out_numargs == 0);
 		ret = args->out_args[args->out_numargs - 1].size;
 	}
+	if (args->is_filter)
+		args->ret = req->out.h.error;
 	fuse_put_request(req);
 
 	return ret;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 07b50be2c6e4..a619c6eac6e5 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -305,6 +305,17 @@ struct fuse_page_desc {
 	unsigned int offset;
 };
 
+/* To deal with bpf pre and post filters in userspace calls, we must support
+ * passing the inputs and outputs as inputs, and we must have enough space in
+ * outputs to handle all of the inputs.
+ */
+#define FUSE_EXTENDED_MAX_ARGS_IN (FUSE_MAX_ARGS_IN + FUSE_MAX_ARGS_OUT)
+#if FUSE_MAX_ARGS_IN > FUSE_MAX_ARGS_OUT
+#define FUSE_EXTENDED_MAX_ARGS_OUT FUSE_MAX_ARGS_IN
+#else
+#define FUSE_EXTENDED_MAX_ARGS_OUT FUSE_MAX_ARGS_OUT
+#endif
+
 struct fuse_args {
 	uint64_t nodeid;
 	uint32_t opcode;
@@ -321,9 +332,11 @@ struct fuse_args {
 	bool page_zeroing:1;
 	bool page_replace:1;
 	bool may_block:1;
+	bool is_filter:1;
 	bool is_lookup:1;
-	struct fuse_in_arg in_args[3];
-	struct fuse_arg out_args[2];
+	uint32_t ret;
+	struct fuse_in_arg in_args[FUSE_EXTENDED_MAX_ARGS_IN];
+	struct fuse_arg out_args[FUSE_EXTENDED_MAX_ARGS_OUT];
 	void (*end)(struct fuse_mount *fm, struct fuse_args *args, int error);
 };
 
@@ -1936,6 +1949,9 @@ static inline void convert_fuse_statfs(struct kstatfs *stbuf, struct fuse_kstatf
 int __init fuse_bpf_init(void);
 void __exit fuse_bpf_cleanup(void);
 
+ssize_t fuse_prefilter_simple_request(struct fuse_mount *fm, struct bpf_fuse_args *args);
+ssize_t fuse_postfilter_simple_request(struct fuse_mount *fm, struct bpf_fuse_args *args);
+
 static inline void fuse_bpf_set_in_ends(struct bpf_fuse_args *fa)
 {
 	int i;
@@ -1994,9 +2010,11 @@ static inline void fuse_bpf_free_alloced(struct bpf_fuse_args *fa)
 			 backing, finalize, args...)			\
 ({									\
 	struct fuse_inode *fuse_inode = get_fuse_inode(inode);		\
+	struct fuse_mount *fm = get_fuse_mount(inode);			\
 	struct bpf_fuse_args fa = { 0 };				\
 	bool initialized = false;					\
 	bool handled = false;						\
+	bool locked;							\
 	ssize_t res;							\
 	int bpf_next;							\
 	io feo = { 0 };							\
@@ -2021,6 +2039,16 @@ static inline void fuse_bpf_free_alloced(struct bpf_fuse_args *fa)
 			break;						\
 		}							\
 									\
+		if (bpf_next == BPF_FUSE_USER_PREFILTER) {		\
+			locked = fuse_lock_inode(inode);		\
+			res = fuse_prefilter_simple_request(fm, &fa);	\
+			fuse_unlock_inode(inode, locked);		\
+			if (res < 0) {					\
+				error = res;				\
+				break;					\
+			}						\
+			bpf_next = fa.ret;				\
+		}							\
 		fuse_bpf_set_in_immutable(&fa);				\
 									\
 		error = initialize_out(&fa, &feo, args);		\
@@ -2051,6 +2079,16 @@ static inline void fuse_bpf_free_alloced(struct bpf_fuse_args *fa)
 			break;						\
 		}							\
 									\
+		if (!(bpf_next == BPF_FUSE_USER_POSTFILTER))		\
+			break;						\
+									\
+		locked = fuse_lock_inode(inode);			\
+		res = fuse_postfilter_simple_request(fm, &fa);		\
+		fuse_unlock_inode(inode, locked);			\
+		if (res < 0) {						\
+			error = res;					\
+			break;						\
+		}							\
 	} while (false);						\
 									\
 	if (initialized && handled) {					\
diff --git a/include/linux/bpf_fuse.h b/include/linux/bpf_fuse.h
index ef5c8fdaffee..2802ca71ddd1 100644
--- a/include/linux/bpf_fuse.h
+++ b/include/linux/bpf_fuse.h
@@ -40,6 +40,7 @@ struct bpf_fuse_args {
 	uint32_t in_numargs;
 	uint32_t out_numargs;
 	uint32_t flags;
+	uint32_t ret;
 	struct bpf_fuse_arg in_args[FUSE_MAX_ARGS_IN];
 	struct bpf_fuse_arg out_args[FUSE_MAX_ARGS_OUT];
 };
-- 
2.37.3.998.g577e59143f-goog


  parent reply	other threads:[~2022-09-26 23:21 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-26 23:17 [PATCH 00/26] FUSE BPF: A Stacked Filesystem Extension for FUSE Daniel Rosenberg
2022-09-26 23:17 ` [PATCH 01/26] bpf: verifier: Allow for multiple packets Daniel Rosenberg
2022-09-26 23:17 ` [PATCH 02/26] bpf: verifier: Allow single packet invalidation Daniel Rosenberg
2022-09-26 23:17 ` [PATCH 03/26] fuse-bpf: Update uapi for fuse-bpf Daniel Rosenberg
2022-09-27 18:19   ` Miklos Szeredi
2022-09-30 22:02     ` Paul Lawrence
2022-10-01  7:47       ` Amir Goldstein
2022-09-26 23:18 ` [PATCH 04/26] fuse-bpf: Add BPF supporting functions Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 05/26] fs: Generic function to convert iocb to rw flags Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 06/26] bpf: Export bpf_prog_fops Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 07/26] fuse-bpf: Prepare for fuse-bpf patch Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 08/26] fuse: Add fuse-bpf, a stacked fs extension for FUSE Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 09/26] fuse-bpf: Don't support export_operations Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 10/26] fuse-bpf: Partially add mapping support Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 11/26] fuse-bpf: Add lseek support Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 12/26] fuse-bpf: Add support for fallocate Daniel Rosenberg
2022-09-27 22:07   ` Dave Chinner
2022-09-27 23:36     ` Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 13/26] fuse-bpf: Support file/dir open/close Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 14/26] fuse-bpf: Support mknod/unlink/mkdir/rmdir Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 15/26] fuse-bpf: Add support for read/write iter Daniel Rosenberg
2022-10-01  6:53   ` Amir Goldstein
2022-09-26 23:18 ` [PATCH 16/26] fuse-bpf: support FUSE_READDIR Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 17/26] fuse-bpf: Add support for sync operations Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 18/26] fuse-bpf: Add Rename support Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 19/26] fuse-bpf: Add attr support Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 20/26] fuse-bpf: Add support for FUSE_COPY_FILE_RANGE Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 21/26] fuse-bpf: Add xattr support Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 22/26] fuse-bpf: Add symlink/link support Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 23/26] fuse-bpf: allow mounting with no userspace daemon Daniel Rosenberg
2022-09-26 23:18 ` [PATCH 24/26] fuse-bpf: Call bpf for pre/post filters Daniel Rosenberg
2022-09-26 23:18 ` Daniel Rosenberg [this message]
2022-09-28  6:41 ` [PATCH 00/26] FUSE BPF: A Stacked Filesystem Extension for FUSE Martin KaFai Lau
2022-09-28 12:31   ` Brian Foster
2022-10-01  0:47     ` Daniel Rosenberg
2022-10-01  0:05   ` Daniel Rosenberg
2022-10-01  0:24     ` Alexei Starovoitov
2022-10-06  1:58     ` Martin KaFai Lau

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220926231822.994383-26-drosen@google.com \
    --to=drosen@google.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=balsini@google.com \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=dvander@google.com \
    --cc=haoluo@google.com \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=kernel-team@android.com \
    --cc=kpsingh@kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=martin.lau@linux.dev \
    --cc=miklos@szeredi.hu \
    --cc=paullawrence@google.com \
    --cc=sdf@google.com \
    --cc=song@kernel.org \
    --cc=sspatil@google.com \
    --cc=yhs@fb.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox