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, 33 insertions, 9 deletions

diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c
index 3505f3e5ae96..594a234f122b 100644
--- a/kernel/bpf/log.c
+++ b/kernel/bpf/log.c
@@ -539,6 +539,19 @@ static void verbose_snum(struct bpf_verifier_env *env, s64 num)
 		verbose(env, "%#llx", num);
 }
 
+int tnum_strn(char *str, size_t size, struct tnum a)
+{
+	/* print as a constant, if tnum is fully known */
+	if (a.mask == 0) {
+		if (is_unum_decimal(a.value))
+			return snprintf(str, size, "%llu", a.value);
+		else
+			return snprintf(str, size, "%#llx", a.value);
+	}
+	return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask);
+}
+EXPORT_SYMBOL_GPL(tnum_strn);
+
 static void print_scalar_ranges(struct bpf_verifier_env *env,
 				const struct bpf_reg_state *reg,
 				const char **sep)
@@ -615,6 +628,12 @@ static bool type_is_map_ptr(enum bpf_reg_type t) {
 	}
 }
 
+/*
+ * _a stands for append, was shortened to avoid multiline statements below.
+ * This macro is used to output a comma separated list of attributes.
+ */
+#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, ##__VA_ARGS__); sep = ","; })
+
 static void print_reg_state(struct bpf_verifier_env *env,
 			    const struct bpf_func_state *state,
 			    const struct bpf_reg_state *reg)
@@ -630,11 +649,6 @@ static void print_reg_state(struct bpf_verifier_env *env,
 		verbose_snum(env, reg->var_off.value + reg->off);
 		return;
 	}
-/*
- * _a stands for append, was shortened to avoid multiline statements below.
- * This macro is used to output a comma separated list of attributes.
- */
-#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, ##__VA_ARGS__); sep = ","; })
 
 	verbose(env, "%s", reg_type_str(env, t));
 	if (t == PTR_TO_STACK) {
@@ -669,6 +683,12 @@ static void print_reg_state(struct bpf_verifier_env *env,
 		verbose_a("r=");
 		verbose_unum(env, reg->range);
 	}
+	if (base_type(t) == PTR_TO_MEM) {
+		verbose_a("sz=");
+		verbose_unum(env, reg->mem_size);
+	}
+	if (t == CONST_PTR_TO_DYNPTR)
+		verbose_a("type=%s",  dynptr_type_str(reg->dynptr.type));
 	if (tnum_is_const(reg->var_off)) {
 		/* a pointer register with fixed offset */
 		if (reg->var_off.value) {
@@ -685,8 +705,6 @@ static void print_reg_state(struct bpf_verifier_env *env,
 		}
 	}
 	verbose(env, ")");
-
-#undef verbose_a
 }
 
 void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state,
@@ -710,6 +728,7 @@ void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_st
 	}
 	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
 		char types_buf[BPF_REG_SIZE + 1];
+		const char *sep = "";
 		bool valid = false;
 		u8 slot_type;
 		int j;
@@ -748,9 +767,14 @@ void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_st
 
 			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
 			print_liveness(env, reg->live);
-			verbose(env, "=dynptr_%s", dynptr_type_str(reg->dynptr.type));
+			verbose(env, "=dynptr_%s(", dynptr_type_str(reg->dynptr.type));
+			if (reg->id)
+				verbose_a("id=%d", reg->id);
 			if (reg->ref_obj_id)
-				verbose(env, "(ref_id=%d)", reg->ref_obj_id);
+				verbose_a("ref_id=%d", reg->ref_obj_id);
+			if (reg->dynptr_id)
+				verbose_a("dynptr_id=%d", reg->dynptr_id);
+			verbose(env, ")");
 			break;
 		case STACK_ITER:
 			/* only main slot has ref_obj_id set; skip others */