Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2023-12-18

This PR is larger than usual and contains changes in various parts
of the kernel.

The main changes are:

1) Fix kCFI bugs in BPF, from Peter Zijlstra.

End result: all forms of indirect calls from BPF into kernel
and from kernel into BPF work with CFI enabled. This allows BPF
to work with CONFIG_FINEIBT=y.

2) Introduce BPF token object, from Andrii Nakryiko.

It adds an ability to delegate a subset of BPF features from privileged
daemon (e.g., systemd) through special mount options for userns-bound
BPF FS to a trusted unprivileged application. The design accommodates
suggestions from Christian Brauner and Paul Moore.

Example:
$ sudo mkdir -p /sys/fs/bpf/token
$ sudo mount -t bpf bpffs /sys/fs/bpf/token \
             -o delegate_cmds=prog_load:MAP_CREATE \
             -o delegate_progs=kprobe \
             -o delegate_attachs=xdp

3) Various verifier improvements and fixes, from Andrii Nakryiko, Andrei Matei.

 - Complete precision tracking support for register spills
 - Fix verification of possibly-zero-sized stack accesses
 - Fix access to uninit stack slots
 - Track aligned STACK_ZERO cases as imprecise spilled registers.
   It improves the verifier "instructions processed" metric from single
   digit to 50-60% for some programs.
 - Fix verifier retval logic

4) Support for VLAN tag in XDP hints, from Larysa Zaremba.

5) Allocate BPF trampoline via bpf_prog_pack mechanism, from Song Liu.

End result: better memory utilization and lower I$ miss for calls to BPF
via BPF trampoline.

6) Fix race between BPF prog accessing inner map and parallel delete,
from Hou Tao.

7) Add bpf_xdp_get_xfrm_state() kfunc, from Daniel Xu.

It allows BPF interact with IPSEC infra. The intent is to support
software RSS (via XDP) for the upcoming ipsec pcpu work.
Experiments on AWS demonstrate single tunnel pcpu ipsec reaching
line rate on 100G ENA nics.

8) Expand bpf_cgrp_storage to support cgroup1 non-attach, from Yafang Shao.

9) BPF file verification via fsverity, from Song Liu.

It allows BPF progs get fsverity digest.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (164 commits)
  bpf: Ensure precise is reset to false in __mark_reg_const_zero()
  selftests/bpf: Add more uprobe multi fail tests
  bpf: Fail uprobe multi link with negative offset
  selftests/bpf: Test the release of map btf
  s390/bpf: Fix indirect trampoline generation
  selftests/bpf: Temporarily disable dummy_struct_ops test on s390
  x86/cfi,bpf: Fix bpf_exception_cb() signature
  bpf: Fix dtor CFI
  cfi: Add CFI_NOSEAL()
  x86/cfi,bpf: Fix bpf_struct_ops CFI
  x86/cfi,bpf: Fix bpf_callback_t CFI
  x86/cfi,bpf: Fix BPF JIT call
  cfi: Flip headers
  selftests/bpf: Add test for abnormal cnt during multi-kprobe attachment
  selftests/bpf: Don't use libbpf_get_error() in kprobe_multi_test
  selftests/bpf: Add test for abnormal cnt during multi-uprobe attachment
  bpf: Limit the number of kprobes when attaching program to multiple kprobes
  bpf: Limit the number of uprobes when attaching program to multiple uprobes
  bpf: xdp: Register generic_kfunc_set with XDP programs
  selftests/bpf: utilize string values for delegate_xxx mount options
  ...
====================

Link: https://lore.kernel.org/r/20231219000520.34178-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 81 insertions, 3 deletions

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index c284a4ad0315cf..492d60e9c48000 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -24,6 +24,7 @@
 #include <linux/key.h>
 #include <linux/verification.h>
 #include <linux/namei.h>
+#include <linux/fileattr.h>
 
 #include <net/bpf_sk_storage.h>
 
@@ -41,6 +42,9 @@
 #define bpf_event_rcu_dereference(p)					\
 	rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex))
 
+#define MAX_UPROBE_MULTI_CNT (1U << 20)
+#define MAX_KPROBE_MULTI_CNT (1U << 20)
+
 #ifdef CONFIG_MODULES
 struct bpf_trace_module {
 	struct module *module;
@@ -1431,6 +1435,72 @@ static int __init bpf_key_sig_kfuncs_init(void)
 late_initcall(bpf_key_sig_kfuncs_init);
 #endif /* CONFIG_KEYS */
 
+/* filesystem kfuncs */
+__bpf_kfunc_start_defs();
+
+/**
+ * bpf_get_file_xattr - get xattr of a file
+ * @file: file to get xattr from
+ * @name__str: name of the xattr
+ * @value_ptr: output buffer of the xattr value
+ *
+ * Get xattr *name__str* of *file* and store the output in *value_ptr*.
+ *
+ * For security reasons, only *name__str* with prefix "user." is allowed.
+ *
+ * Return: 0 on success, a negative value on error.
+ */
+__bpf_kfunc int bpf_get_file_xattr(struct file *file, const char *name__str,
+				   struct bpf_dynptr_kern *value_ptr)
+{
+	struct dentry *dentry;
+	u32 value_len;
+	void *value;
+	int ret;
+
+	if (strncmp(name__str, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))
+		return -EPERM;
+
+	value_len = __bpf_dynptr_size(value_ptr);
+	value = __bpf_dynptr_data_rw(value_ptr, value_len);
+	if (!value)
+		return -EINVAL;
+
+	dentry = file_dentry(file);
+	ret = inode_permission(&nop_mnt_idmap, dentry->d_inode, MAY_READ);
+	if (ret)
+		return ret;
+	return __vfs_getxattr(dentry, dentry->d_inode, name__str, value, value_len);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_SET8_START(fs_kfunc_set_ids)
+BTF_ID_FLAGS(func, bpf_get_file_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS)
+BTF_SET8_END(fs_kfunc_set_ids)
+
+static int bpf_get_file_xattr_filter(const struct bpf_prog *prog, u32 kfunc_id)
+{
+	if (!btf_id_set8_contains(&fs_kfunc_set_ids, kfunc_id))
+		return 0;
+
+	/* Only allow to attach from LSM hooks, to avoid recursion */
+	return prog->type != BPF_PROG_TYPE_LSM ? -EACCES : 0;
+}
+
+static const struct btf_kfunc_id_set bpf_fs_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set = &fs_kfunc_set_ids,
+	.filter = bpf_get_file_xattr_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);
+
 static const struct bpf_func_proto *
 bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1559,7 +1629,7 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_trace_vprintk:
 		return bpf_get_trace_vprintk_proto();
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
@@ -2903,6 +2973,8 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	cnt = attr->link_create.kprobe_multi.cnt;
 	if (!cnt)
 		return -EINVAL;
+	if (cnt > MAX_KPROBE_MULTI_CNT)
+		return -E2BIG;
 
 	size = cnt * sizeof(*addrs);
 	addrs = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL);
@@ -3277,6 +3349,8 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 
 	if (!upath || !uoffsets || !cnt)
 		return -EINVAL;
+	if (cnt > MAX_UPROBE_MULTI_CNT)
+		return -E2BIG;
 
 	uref_ctr_offsets = u64_to_user_ptr(attr->link_create.uprobe_multi.ref_ctr_offsets);
 	ucookies = u64_to_user_ptr(attr->link_create.uprobe_multi.cookies);
@@ -3317,15 +3391,19 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 		goto error_free;
 
 	for (i = 0; i < cnt; i++) {
-		if (ucookies && __get_user(uprobes[i].cookie, ucookies + i)) {
+		if (__get_user(uprobes[i].offset, uoffsets + i)) {
 			err = -EFAULT;
 			goto error_free;
 		}
+		if (uprobes[i].offset < 0) {
+			err = -EINVAL;
+			goto error_free;
+		}
 		if (uref_ctr_offsets && __get_user(uprobes[i].ref_ctr_offset, uref_ctr_offsets + i)) {
 			err = -EFAULT;
 			goto error_free;
 		}
-		if (__get_user(uprobes[i].offset, uoffsets + i)) {
+		if (ucookies && __get_user(uprobes[i].cookie, ucookies + i)) {
 			err = -EFAULT;
 			goto error_free;
 		}