Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-07-09

We've added 94 non-merge commits during the last 19 day(s) which contain
a total of 125 files changed, 5141 insertions(+), 6701 deletions(-).

The main changes are:

1) Add new way for performing BTF type queries to BPF, from Daniel Müller.

2) Add inlining of calls to bpf_loop() helper when its function callback is
   statically known, from Eduard Zingerman.

3) Implement BPF TCP CC framework usability improvements, from Jörn-Thorben Hinz.

4) Add LSM flavor for attaching per-cgroup BPF programs to existing LSM
   hooks, from Stanislav Fomichev.

5) Remove all deprecated libbpf APIs in prep for 1.0 release, from Andrii Nakryiko.

6) Add benchmarks around local_storage to BPF selftests, from Dave Marchevsky.

7) AF_XDP sample removal (given move to libxdp) and various improvements around AF_XDP
   selftests, from Magnus Karlsson & Maciej Fijalkowski.

8) Add bpftool improvements for memcg probing and bash completion, from Quentin Monnet.

9) Add arm64 JIT support for BPF-2-BPF coupled with tail calls, from Jakub Sitnicki.

10) Sockmap optimizations around throughput of UDP transmissions which have been
    improved by 61%, from Cong Wang.

11) Rework perf's BPF prologue code to remove deprecated functions, from Jiri Olsa.

12) Fix sockmap teardown path to avoid sleepable sk_psock_stop, from John Fastabend.

13) Fix libbpf's cleanup around legacy kprobe/uprobe on error case, from Chuang Wang.

14) Fix libbpf's bpf_helpers.h to work with gcc for the case of its sec/pragma
    macro, from James Hilliard.

15) Fix libbpf's pt_regs macros for riscv to use a0 for RC register, from Yixun Lan.

16) Fix bpftool to show the name of type BPF_OBJ_LINK, from Yafang Shao.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (94 commits)
  selftests/bpf: Fix xdp_synproxy build failure if CONFIG_NF_CONNTRACK=m/n
  bpf: Correctly propagate errors up from bpf_core_composites_match
  libbpf: Disable SEC pragma macro on GCC
  bpf: Check attach_func_proto more carefully in check_return_code
  selftests/bpf: Add test involving restrict type qualifier
  bpftool: Add support for KIND_RESTRICT to gen min_core_btf command
  MAINTAINERS: Add entry for AF_XDP selftests files
  selftests, xsk: Rename AF_XDP testing app
  bpf, docs: Remove deprecated xsk libbpf APIs description
  selftests/bpf: Add benchmark for local_storage RCU Tasks Trace usage
  libbpf, riscv: Use a0 for RC register
  libbpf: Remove unnecessary usdt_rel_ip assignments
  selftests/bpf: Fix few more compiler warnings
  selftests/bpf: Fix bogus uninitialized variable warning
  bpftool: Remove zlib feature test from Makefile
  libbpf: Cleanup the legacy uprobe_event on failed add/attach_event()
  libbpf: Fix wrong variable used in perf_event_uprobe_open_legacy()
  libbpf: Cleanup the legacy kprobe_event on failed add/attach_event()
  selftests/bpf: Add type match test against kernel's task_struct
  selftests/bpf: Add nested type to type based tests
  ...
====================

Link: https://lore.kernel.org/r/20220708233145.32365-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 226 insertions, 12 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a4012b35fdbd..328cfab3af60 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6153,7 +6153,8 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id)
 
 static bool allow_tail_call_in_subprogs(struct bpf_verifier_env *env)
 {
-	return env->prog->jit_requested && IS_ENABLED(CONFIG_X86_64);
+	return env->prog->jit_requested &&
+	       bpf_jit_supports_subprog_tailcalls();
 }
 
 static int check_map_func_compatibility(struct bpf_verifier_env *env,
@@ -7121,6 +7122,41 @@ static int check_get_func_ip(struct bpf_verifier_env *env)
 	return -ENOTSUPP;
 }
 
+static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
+{
+	return &env->insn_aux_data[env->insn_idx];
+}
+
+static bool loop_flag_is_zero(struct bpf_verifier_env *env)
+{
+	struct bpf_reg_state *regs = cur_regs(env);
+	struct bpf_reg_state *reg = &regs[BPF_REG_4];
+	bool reg_is_null = register_is_null(reg);
+
+	if (reg_is_null)
+		mark_chain_precision(env, BPF_REG_4);
+
+	return reg_is_null;
+}
+
+static void update_loop_inline_state(struct bpf_verifier_env *env, u32 subprogno)
+{
+	struct bpf_loop_inline_state *state = &cur_aux(env)->loop_inline_state;
+
+	if (!state->initialized) {
+		state->initialized = 1;
+		state->fit_for_inline = loop_flag_is_zero(env);
+		state->callback_subprogno = subprogno;
+		return;
+	}
+
+	if (!state->fit_for_inline)
+		return;
+
+	state->fit_for_inline = (loop_flag_is_zero(env) &&
+				 state->callback_subprogno == subprogno);
+}
+
 static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			     int *insn_idx_p)
 {
@@ -7273,6 +7309,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		err = check_bpf_snprintf_call(env, regs);
 		break;
 	case BPF_FUNC_loop:
+		update_loop_inline_state(env, meta.subprogno);
 		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
 					set_loop_callback_state);
 		break;
@@ -7282,6 +7319,18 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 				reg_type_str(env, regs[BPF_REG_1].type));
 			return -EACCES;
 		}
+		break;
+	case BPF_FUNC_set_retval:
+		if (env->prog->expected_attach_type == BPF_LSM_CGROUP) {
+			if (!env->prog->aux->attach_func_proto->type) {
+				/* Make sure programs that attach to void
+				 * hooks don't try to modify return value.
+				 */
+				verbose(env, "BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n");
+				return -EINVAL;
+			}
+		}
+		break;
 	}
 
 	if (err)
@@ -7679,11 +7728,6 @@ static bool check_reg_sane_offset(struct bpf_verifier_env *env,
 	return true;
 }
 
-static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
-{
-	return &env->insn_aux_data[env->insn_idx];
-}
-
 enum {
 	REASON_BOUNDS	= -1,
 	REASON_TYPE	= -2,
@@ -9054,7 +9098,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 
 	if (opcode == BPF_END || opcode == BPF_NEG) {
 		if (opcode == BPF_NEG) {
-			if (BPF_SRC(insn->code) != 0 ||
+			if (BPF_SRC(insn->code) != BPF_K ||
 			    insn->src_reg != BPF_REG_0 ||
 			    insn->off != 0 || insn->imm != 0) {
 				verbose(env, "BPF_NEG uses reserved fields\n");
@@ -10381,11 +10425,21 @@ static int check_return_code(struct bpf_verifier_env *env)
 	const bool is_subprog = frame->subprogno;
 
 	/* LSM and struct_ops func-ptr's return type could be "void" */
-	if (!is_subprog &&
-	    (prog_type == BPF_PROG_TYPE_STRUCT_OPS ||
-	     prog_type == BPF_PROG_TYPE_LSM) &&
-	    !prog->aux->attach_func_proto->type)
-		return 0;
+	if (!is_subprog) {
+		switch (prog_type) {
+		case BPF_PROG_TYPE_LSM:
+			if (prog->expected_attach_type == BPF_LSM_CGROUP)
+				/* See below, can be 0 or 0-1 depending on hook. */
+				break;
+			fallthrough;
+		case BPF_PROG_TYPE_STRUCT_OPS:
+			if (!prog->aux->attach_func_proto->type)
+				return 0;
+			break;
+		default:
+			break;
+		}
+	}
 
 	/* eBPF calling convention is such that R0 is used
 	 * to return the value from eBPF program.
@@ -10476,6 +10530,22 @@ static int check_return_code(struct bpf_verifier_env *env)
 	case BPF_PROG_TYPE_SK_LOOKUP:
 		range = tnum_range(SK_DROP, SK_PASS);
 		break;
+
+	case BPF_PROG_TYPE_LSM:
+		if (env->prog->expected_attach_type != BPF_LSM_CGROUP) {
+			/* Regular BPF_PROG_TYPE_LSM programs can return
+			 * any value.
+			 */
+			return 0;
+		}
+		if (!env->prog->aux->attach_func_proto->type) {
+			/* Make sure programs that attach to void
+			 * hooks don't try to modify return value.
+			 */
+			range = tnum_range(1, 1);
+		}
+		break;
+
 	case BPF_PROG_TYPE_EXT:
 		/* freplace program can return anything as its return value
 		 * depends on the to-be-replaced kernel func or bpf program.
@@ -10492,6 +10562,10 @@ static int check_return_code(struct bpf_verifier_env *env)
 
 	if (!tnum_in(range, reg->var_off)) {
 		verbose_invalid_scalar(env, reg, &range, "program exit", "R0");
+		if (prog->expected_attach_type == BPF_LSM_CGROUP &&
+		    prog_type == BPF_PROG_TYPE_LSM &&
+		    !prog->aux->attach_func_proto->type)
+			verbose(env, "Note, BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n");
 		return -EINVAL;
 	}
 
@@ -14296,6 +14370,142 @@ patch_call_imm:
 	return 0;
 }
 
+static struct bpf_prog *inline_bpf_loop(struct bpf_verifier_env *env,
+					int position,
+					s32 stack_base,
+					u32 callback_subprogno,
+					u32 *cnt)
+{
+	s32 r6_offset = stack_base + 0 * BPF_REG_SIZE;
+	s32 r7_offset = stack_base + 1 * BPF_REG_SIZE;
+	s32 r8_offset = stack_base + 2 * BPF_REG_SIZE;
+	int reg_loop_max = BPF_REG_6;
+	int reg_loop_cnt = BPF_REG_7;
+	int reg_loop_ctx = BPF_REG_8;
+
+	struct bpf_prog *new_prog;
+	u32 callback_start;
+	u32 call_insn_offset;
+	s32 callback_offset;
+
+	/* This represents an inlined version of bpf_iter.c:bpf_loop,
+	 * be careful to modify this code in sync.
+	 */
+	struct bpf_insn insn_buf[] = {
+		/* Return error and jump to the end of the patch if
+		 * expected number of iterations is too big.
+		 */
+		BPF_JMP_IMM(BPF_JLE, BPF_REG_1, BPF_MAX_LOOPS, 2),
+		BPF_MOV32_IMM(BPF_REG_0, -E2BIG),
+		BPF_JMP_IMM(BPF_JA, 0, 0, 16),
+		/* spill R6, R7, R8 to use these as loop vars */
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, r6_offset),
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_7, r7_offset),
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_8, r8_offset),
+		/* initialize loop vars */
+		BPF_MOV64_REG(reg_loop_max, BPF_REG_1),
+		BPF_MOV32_IMM(reg_loop_cnt, 0),
+		BPF_MOV64_REG(reg_loop_ctx, BPF_REG_3),
+		/* loop header,
+		 * if reg_loop_cnt >= reg_loop_max skip the loop body
+		 */
+		BPF_JMP_REG(BPF_JGE, reg_loop_cnt, reg_loop_max, 5),
+		/* callback call,
+		 * correct callback offset would be set after patching
+		 */
+		BPF_MOV64_REG(BPF_REG_1, reg_loop_cnt),
+		BPF_MOV64_REG(BPF_REG_2, reg_loop_ctx),
+		BPF_CALL_REL(0),
+		/* increment loop counter */
+		BPF_ALU64_IMM(BPF_ADD, reg_loop_cnt, 1),
+		/* jump to loop header if callback returned 0 */
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -6),
+		/* return value of bpf_loop,
+		 * set R0 to the number of iterations
+		 */
+		BPF_MOV64_REG(BPF_REG_0, reg_loop_cnt),
+		/* restore original values of R6, R7, R8 */
+		BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, r6_offset),
+		BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, r7_offset),
+		BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_10, r8_offset),
+	};
+
+	*cnt = ARRAY_SIZE(insn_buf);
+	new_prog = bpf_patch_insn_data(env, position, insn_buf, *cnt);
+	if (!new_prog)
+		return new_prog;
+
+	/* callback start is known only after patching */
+	callback_start = env->subprog_info[callback_subprogno].start;
+	/* Note: insn_buf[12] is an offset of BPF_CALL_REL instruction */
+	call_insn_offset = position + 12;
+	callback_offset = callback_start - call_insn_offset - 1;
+	new_prog->insnsi[call_insn_offset].imm = callback_offset;
+
+	return new_prog;
+}
+
+static bool is_bpf_loop_call(struct bpf_insn *insn)
+{
+	return insn->code == (BPF_JMP | BPF_CALL) &&
+		insn->src_reg == 0 &&
+		insn->imm == BPF_FUNC_loop;
+}
+
+/* For all sub-programs in the program (including main) check
+ * insn_aux_data to see if there are bpf_loop calls that require
+ * inlining. If such calls are found the calls are replaced with a
+ * sequence of instructions produced by `inline_bpf_loop` function and
+ * subprog stack_depth is increased by the size of 3 registers.
+ * This stack space is used to spill values of the R6, R7, R8.  These
+ * registers are used to store the loop bound, counter and context
+ * variables.
+ */
+static int optimize_bpf_loop(struct bpf_verifier_env *env)
+{
+	struct bpf_subprog_info *subprogs = env->subprog_info;
+	int i, cur_subprog = 0, cnt, delta = 0;
+	struct bpf_insn *insn = env->prog->insnsi;
+	int insn_cnt = env->prog->len;
+	u16 stack_depth = subprogs[cur_subprog].stack_depth;
+	u16 stack_depth_roundup = round_up(stack_depth, 8) - stack_depth;
+	u16 stack_depth_extra = 0;
+
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		struct bpf_loop_inline_state *inline_state =
+			&env->insn_aux_data[i + delta].loop_inline_state;
+
+		if (is_bpf_loop_call(insn) && inline_state->fit_for_inline) {
+			struct bpf_prog *new_prog;
+
+			stack_depth_extra = BPF_REG_SIZE * 3 + stack_depth_roundup;
+			new_prog = inline_bpf_loop(env,
+						   i + delta,
+						   -(stack_depth + stack_depth_extra),
+						   inline_state->callback_subprogno,
+						   &cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta     += cnt - 1;
+			env->prog  = new_prog;
+			insn       = new_prog->insnsi + i + delta;
+		}
+
+		if (subprogs[cur_subprog + 1].start == i + delta + 1) {
+			subprogs[cur_subprog].stack_depth += stack_depth_extra;
+			cur_subprog++;
+			stack_depth = subprogs[cur_subprog].stack_depth;
+			stack_depth_roundup = round_up(stack_depth, 8) - stack_depth;
+			stack_depth_extra = 0;
+		}
+	}
+
+	env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
+
+	return 0;
+}
+
 static void free_states(struct bpf_verifier_env *env)
 {
 	struct bpf_verifier_state_list *sl, *sln;
@@ -14715,6 +14925,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 		fallthrough;
 	case BPF_MODIFY_RETURN:
 	case BPF_LSM_MAC:
+	case BPF_LSM_CGROUP:
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
 		if (!btf_type_is_func(t)) {
@@ -15033,6 +15244,9 @@ skip_full_check:
 		ret = check_max_stack_depth(env);
 
 	/* instruction rewrites happen after this point */
+	if (ret == 0)
+		ret = optimize_bpf_loop(env);
+
 	if (is_priv) {
 		if (ret == 0)
 			opt_hard_wire_dead_code_branches(env);