Merge branch 'bpf-introduce-new-vfs-based-bpf-kfuncs'

Matt Bobrowski says:

====================
bpf: introduce new VFS based BPF kfuncs

G'day!

A respin based off v3, which can be found here [0]. Original
motivations for introducing this suite of BPF kfuncs can be found here
[1].

The primary difference in this version of the patch series is that the
suite of VFS related BPF kfuncs added can be used from both sleepable
and non-sleepable BPF LSM program types. IOW, the KF_SLEEPABLE
annotation has been removed from all of them.

Changes sinve v3:

* KF_SLEEPABLE annotation has been dropped from all newly introduced
  VFS related BPF kfuncs. This includes bpf_get_task_exe_file(),
  bpf_put_file(), and bpf_path_d_path(). Both negative and positive
  selftests backing these new BPF kfuncs have also been updated
  accordingly.

* buf__sz conditional in bpf_path_d_path() has been updated from
  buf__sz <= 0, to !buf__sz.

* Syntax issues as reported so here [2] have been corrected.

[0] https://lore.kernel.org/bpf/20240726085604.2369469-1-mattbobrowski@google.com/
[1] https://lore.kernel.org/bpf/cover.1708377880.git.mattbobrowski@google.com/#t
[2] https://netdev.bots.linux.dev/static/nipa/874023/13742510/checkpatch/stdout
====================

Link: https://lore.kernel.org/r/20240731110833.1834742-1-mattbobrowski@google.comSigned-off-by: Alexei Starovoitov <ast@kernel.org>

fs/Makefile

@@ -129,3 +129,4 @@ obj-$(CONFIG_EFIVAR_FS)		+= efivarfs/
 obj-$(CONFIG_EROFS_FS)		+= erofs/
 obj-$(CONFIG_VBOXSF_FS)		+= vboxsf/
 obj-$(CONFIG_ZONEFS_FS)		+= zonefs/
+obj-$(CONFIG_BPF_LSM)		+= bpf_fs_kfuncs.o

fs/bpf_fs_kfuncs.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google LLC. */
+
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
+#include <linux/dcache.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+
+__bpf_kfunc_start_defs();
+
+/**
+ * bpf_get_task_exe_file - get a reference on the exe_file struct file member of
+ *                         the mm_struct that is nested within the supplied
+ *                         task_struct
+ * @task: task_struct of which the nested mm_struct exe_file member to get a
+ * reference on
+ *
+ * Get a reference on the exe_file struct file member field of the mm_struct
+ * nested within the supplied *task*. The referenced file pointer acquired by
+ * this BPF kfunc must be released using bpf_put_file(). Failing to call
+ * bpf_put_file() on the returned referenced struct file pointer that has been
+ * acquired by this BPF kfunc will result in the BPF program being rejected by
+ * the BPF verifier.
+ *
+ * This BPF kfunc may only be called from BPF LSM programs.
+ *
+ * Internally, this BPF kfunc leans on get_task_exe_file(), such that calling
+ * bpf_get_task_exe_file() would be analogous to calling get_task_exe_file()
+ * directly in kernel context.
+ *
+ * Return: A referenced struct file pointer to the exe_file member of the
+ * mm_struct that is nested within the supplied *task*. On error, NULL is
+ * returned.
+ */
+__bpf_kfunc struct file *bpf_get_task_exe_file(struct task_struct *task)
+{
+	return get_task_exe_file(task);
+}
+
+/**
+ * bpf_put_file - put a reference on the supplied file
+ * @file: file to put a reference on
+ *
+ * Put a reference on the supplied *file*. Only referenced file pointers may be
+ * passed to this BPF kfunc. Attempting to pass an unreferenced file pointer, or
+ * any other arbitrary pointer for that matter, will result in the BPF program
+ * being rejected by the BPF verifier.
+ *
+ * This BPF kfunc may only be called from BPF LSM programs.
+ */
+__bpf_kfunc void bpf_put_file(struct file *file)
+{
+	fput(file);
+}
+
+/**
+ * bpf_path_d_path - resolve the pathname for the supplied path
+ * @path: path to resolve the pathname for
+ * @buf: buffer to return the resolved pathname in
+ * @buf__sz: length of the supplied buffer
+ *
+ * Resolve the pathname for the supplied *path* and store it in *buf*. This BPF
+ * kfunc is the safer variant of the legacy bpf_d_path() helper and should be
+ * used in place of bpf_d_path() whenever possible. It enforces KF_TRUSTED_ARGS
+ * semantics, meaning that the supplied *path* must itself hold a valid
+ * reference, or else the BPF program will be outright rejected by the BPF
+ * verifier.
+ *
+ * This BPF kfunc may only be called from BPF LSM programs.
+ *
+ * Return: A positive integer corresponding to the length of the resolved
+ * pathname in *buf*, including the NUL termination character. On error, a
+ * negative integer is returned.
+ */
+__bpf_kfunc int bpf_path_d_path(struct path *path, char *buf, size_t buf__sz)
+{
+	int len;
+	char *ret;
+
+	if (!buf__sz)
+		return -EINVAL;
+
+	ret = d_path(path, buf, buf__sz);
+	if (IS_ERR(ret))
+		return PTR_ERR(ret);
+
+	len = buf + buf__sz - ret;
+	memmove(buf, ret, len);
+	return len;
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(bpf_fs_kfunc_set_ids)
+BTF_ID_FLAGS(func, bpf_get_task_exe_file,
+	     KF_ACQUIRE | KF_TRUSTED_ARGS | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_put_file, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_path_d_path, KF_TRUSTED_ARGS)
+BTF_KFUNCS_END(bpf_fs_kfunc_set_ids)
+
+static int bpf_fs_kfuncs_filter(const struct bpf_prog *prog, u32 kfunc_id)
+{
+	if (!btf_id_set8_contains(&bpf_fs_kfunc_set_ids, kfunc_id) ||
+	    prog->type == BPF_PROG_TYPE_LSM)
+		return 0;
+	return -EACCES;
+}
+
+static const struct btf_kfunc_id_set bpf_fs_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set = &bpf_fs_kfunc_set_ids,
+	.filter = bpf_fs_kfuncs_filter,
+};
+
+static int __init bpf_fs_kfuncs_init(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_LSM, &bpf_fs_kfunc_set);
+}
+
+late_initcall(bpf_fs_kfuncs_init);

tools/testing/selftests/bpf/bpf_experimental.h

@@ -195,6 +195,32 @@ extern void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) __ksym;
  */
 extern void bpf_throw(u64 cookie) __ksym;
 
+/* Description
+ *	Acquire a reference on the exe_file member field belonging to the
+ *	mm_struct that is nested within the supplied task_struct. The supplied
+ *	task_struct must be trusted/referenced.
+ * Returns
+ *	A referenced file pointer pointing to the exe_file member field of the
+ *	mm_struct nested in the supplied task_struct, or NULL.
+ */
+extern struct file *bpf_get_task_exe_file(struct task_struct *task) __ksym;
+
+/* Description
+ *	Release a reference on the supplied file. The supplied file must be
+ *	acquired.
+ */
+extern void bpf_put_file(struct file *file) __ksym;
+
+/* Description
+ *	Resolve a pathname for the supplied path and store it in the supplied
+ *	buffer. The supplied path must be trusted/referenced.
+ * Returns
+ *	A positive integer corresponding to the length of the resolved pathname,
+ *	including the NULL termination character, stored in the supplied
+ *	buffer. On error, a negative integer is returned.
+ */
+extern int bpf_path_d_path(struct path *path, char *buf, size_t buf__sz) __ksym;
+
 /* This macro must be used to mark the exception callback corresponding to the
  * main program. For example:
  *

tools/testing/selftests/bpf/prog_tests/verifier.c

@@ -85,6 +85,8 @@
 #include "verifier_value_or_null.skel.h"
 #include "verifier_value_ptr_arith.skel.h"
 #include "verifier_var_off.skel.h"
+#include "verifier_vfs_accept.skel.h"
+#include "verifier_vfs_reject.skel.h"
 #include "verifier_xadd.skel.h"
 #include "verifier_xdp.skel.h"
 #include "verifier_xdp_direct_packet_access.skel.h"
@@ -205,6 +207,8 @@ void test_verifier_value(void)                { RUN(verifier_value); }
 void test_verifier_value_illegal_alu(void)    { RUN(verifier_value_illegal_alu); }
 void test_verifier_value_or_null(void)        { RUN(verifier_value_or_null); }
 void test_verifier_var_off(void)              { RUN(verifier_var_off); }
+void test_verifier_vfs_accept(void)	      { RUN(verifier_vfs_accept); }
+void test_verifier_vfs_reject(void)	      { RUN(verifier_vfs_reject); }
 void test_verifier_xadd(void)                 { RUN(verifier_xadd); }
 void test_verifier_xdp(void)                  { RUN(verifier_xdp); }
 void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_packet_access); }

tools/testing/selftests/bpf/progs/verifier_vfs_accept.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google LLC. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+static char buf[64];
+
+SEC("lsm.s/file_open")
+__success
+int BPF_PROG(get_task_exe_file_and_put_kfunc_from_current_sleepable)
+{
+	struct file *acquired;
+
+	acquired = bpf_get_task_exe_file(bpf_get_current_task_btf());
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm/file_open")
+__success
+int BPF_PROG(get_task_exe_file_and_put_kfunc_from_current_non_sleepable, struct file *file)
+{
+	struct file *acquired;
+
+	acquired = bpf_get_task_exe_file(bpf_get_current_task_btf());
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm.s/task_alloc")
+__success
+int BPF_PROG(get_task_exe_file_and_put_kfunc_from_argument,
+	     struct task_struct *task)
+{
+	struct file *acquired;
+
+	acquired = bpf_get_task_exe_file(task);
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm.s/inode_getattr")
+__success
+int BPF_PROG(path_d_path_from_path_argument, struct path *path)
+{
+	int ret;
+
+	ret = bpf_path_d_path(path, buf, sizeof(buf));
+	__sink(ret);
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__success
+int BPF_PROG(path_d_path_from_file_argument, struct file *file)
+{
+	int ret;
+	struct path *path;
+
+	/* The f_path member is a path which is embedded directly within a
+	 * file. Therefore, a pointer to such embedded members are still
+	 * recognized by the BPF verifier as being PTR_TRUSTED as it's
+	 * essentially PTR_TRUSTED w/ a non-zero fixed offset.
+	 */
+	path = &file->f_path;
+	ret = bpf_path_d_path(path, buf, sizeof(buf));
+	__sink(ret);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/verifier_vfs_reject.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google LLC. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <linux/limits.h>
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+static char buf[PATH_MAX];
+
+SEC("lsm.s/file_open")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+int BPF_PROG(get_task_exe_file_kfunc_null)
+{
+	struct file *acquired;
+
+	/* Can't pass a NULL pointer to bpf_get_task_exe_file(). */
+	acquired = bpf_get_task_exe_file(NULL);
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm.s/inode_getxattr")
+__failure __msg("arg#0 pointer type STRUCT task_struct must point to scalar, or struct with scalar")
+int BPF_PROG(get_task_exe_file_kfunc_fp)
+{
+	u64 x;
+	struct file *acquired;
+	struct task_struct *task;
+
+	task = (struct task_struct *)&x;
+	/* Can't pass random frame pointer to bpf_get_task_exe_file(). */
+	acquired = bpf_get_task_exe_file(task);
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("R1 must be referenced or trusted")
+int BPF_PROG(get_task_exe_file_kfunc_untrusted)
+{
+	struct file *acquired;
+	struct task_struct *parent;
+
+	/* Walking a trusted struct task_struct returned from
+	 * bpf_get_current_task_btf() yields an untrusted pointer.
+	 */
+	parent = bpf_get_current_task_btf()->parent;
+	/* Can't pass untrusted pointer to bpf_get_task_exe_file(). */
+	acquired = bpf_get_task_exe_file(parent);
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("Unreleased reference")
+int BPF_PROG(get_task_exe_file_kfunc_unreleased)
+{
+	struct file *acquired;
+
+	acquired = bpf_get_task_exe_file(bpf_get_current_task_btf());
+	if (!acquired)
+		return 0;
+
+	/* Acquired but never released. */
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("release kernel function bpf_put_file expects")
+int BPF_PROG(put_file_kfunc_unacquired, struct file *file)
+{
+	/* Can't release an unacquired pointer. */
+	bpf_put_file(file);
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+int BPF_PROG(path_d_path_kfunc_null)
+{
+	/* Can't pass NULL value to bpf_path_d_path() kfunc. */
+	bpf_path_d_path(NULL, buf, sizeof(buf));
+	return 0;
+}
+
+SEC("lsm.s/task_alloc")
+__failure __msg("R1 must be referenced or trusted")
+int BPF_PROG(path_d_path_kfunc_untrusted_from_argument, struct task_struct *task)
+{
+	struct path *root;
+
+	/* Walking a trusted argument typically yields an untrusted
+	 * pointer. This is one example of that.
+	 */
+	root = &task->fs->root;
+	bpf_path_d_path(root, buf, sizeof(buf));
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("R1 must be referenced or trusted")
+int BPF_PROG(path_d_path_kfunc_untrusted_from_current)
+{
+	struct path *pwd;
+	struct task_struct *current;
+
+	current = bpf_get_current_task_btf();
+	/* Walking a trusted pointer returned from bpf_get_current_task_btf()
+	 * yields an untrusted pointer.
+	 */
+	pwd = &current->fs->pwd;
+	bpf_path_d_path(pwd, buf, sizeof(buf));
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("kernel function bpf_path_d_path args#0 expected pointer to STRUCT path but R1 has a pointer to STRUCT file")
+int BPF_PROG(path_d_path_kfunc_type_mismatch, struct file *file)
+{
+	bpf_path_d_path((struct path *)&file->f_task_work, buf, sizeof(buf));
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("invalid access to map value, value_size=4096 off=0 size=8192")
+int BPF_PROG(path_d_path_kfunc_invalid_buf_sz, struct file *file)
+{
+	/* bpf_path_d_path() enforces a constraint on the buffer size supplied
+	 * by the BPF LSM program via the __sz annotation. buf here is set to
+	 * PATH_MAX, so let's ensure that the BPF verifier rejects BPF_PROG_LOAD
+	 * attempts if the supplied size and the actual size of the buffer
+	 * mismatches.
+	 */
+	bpf_path_d_path(&file->f_path, buf, PATH_MAX * 2);
+	return 0;
+}
+
+SEC("fentry/vfs_open")
+__failure __msg("calling kernel function bpf_path_d_path is not allowed")
+int BPF_PROG(path_d_path_kfunc_non_lsm, struct path *path, struct file *f)
+{
+	/* Calling bpf_path_d_path() from a non-LSM BPF program isn't permitted.
+	 */
+	bpf_path_d_path(path, buf, sizeof(buf));
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";