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

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-10-27

The following pull-request contains BPF updates for your *net-next* tree.

We've added 52 non-merge commits during the last 11 day(s) which contain
a total of 65 files changed, 2604 insertions(+), 1100 deletions(-).

The main changes are:

 1) Revolutionize BPF tracing by using in-kernel BTF to type check BPF
    assembly code. The work here teaches BPF verifier to recognize
    kfree_skb()'s first argument as 'struct sk_buff *' in tracepoints
    such that verifier allows direct use of bpf_skb_event_output() helper
    used in tc BPF et al (w/o probing memory access) that dumps skb data
    into perf ring buffer. Also add direct loads to probe memory in order
    to speed up/replace bpf_probe_read() calls, from Alexei Starovoitov.

 2) Big batch of changes to improve libbpf and BPF kselftests. Besides
    others: generalization of libbpf's CO-RE relocation support to now
    also include field existence relocations, revamp the BPF kselftest
    Makefile to add test runner concept allowing to exercise various
    ways to build BPF programs, and teach bpf_object__open() and friends
    to automatically derive BPF program type/expected attach type from
    section names to ease their use, from Andrii Nakryiko.

 3) Fix deadlock in stackmap's build-id lookup on rq_lock(), from Song Liu.

 4) Allow to read BTF as raw data from bpftool. Most notable use case
    is to dump /sys/kernel/btf/vmlinux through this, from Jiri Olsa.

 5) Use bpf_redirect_map() helper in libbpf's AF_XDP helper prog which
    manages to improve "rx_drop" performance by ~4%., from Björn Töpel.

 6) Fix to restore the flow dissector after reattach BPF test and also
    fix error handling in bpf_helper_defs.h generation, from Jakub Sitnicki.

 7) Improve verifier's BTF ctx access for use outside of raw_tp, from
    Martin KaFai Lau.

 8) Improve documentation for AF_XDP with new sections and to reflect
    latest features, from Magnus Karlsson.

 9) Add back 'version' section parsing to libbpf for old kernels, from
    John Fastabend.

10) Fix strncat bounds error in libbpf's libbpf_prog_type_by_name(),
    from KP Singh.

11) Turn on -mattr=+alu32 in LLVM by default for BPF kselftests in order
    to improve insn coverage for built BPF progs, from Yonghong Song.

12) Misc minor cleanups and fixes, from various others.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 193 insertions, 18 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d3446f018b9a..c59778c0fc4d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -205,8 +205,11 @@ struct bpf_call_arg_meta {
 	u64 msize_umax_value;
 	int ref_obj_id;
 	int func_id;
+	u32 btf_id;
 };
 
+struct btf *btf_vmlinux;
+
 static DEFINE_MUTEX(bpf_verifier_lock);
 
 static const struct bpf_line_info *
@@ -243,6 +246,10 @@ void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt,
 	n = min(log->len_total - log->len_used - 1, n);
 	log->kbuf[n] = '\0';
 
+	if (log->level == BPF_LOG_KERNEL) {
+		pr_err("BPF:%s\n", log->kbuf);
+		return;
+	}
 	if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1))
 		log->len_used += n;
 	else
@@ -280,6 +287,19 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
 	va_end(args);
 }
 
+__printf(2, 3) void bpf_log(struct bpf_verifier_log *log,
+			    const char *fmt, ...)
+{
+	va_list args;
+
+	if (!bpf_verifier_log_needed(log))
+		return;
+
+	va_start(args, fmt);
+	bpf_verifier_vlog(log, fmt, args);
+	va_end(args);
+}
+
 static const char *ltrim(const char *s)
 {
 	while (isspace(*s))
@@ -400,6 +420,7 @@ static const char * const reg_type_str[] = {
 	[PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null",
 	[PTR_TO_TP_BUFFER]	= "tp_buffer",
 	[PTR_TO_XDP_SOCK]	= "xdp_sock",
+	[PTR_TO_BTF_ID]		= "ptr_",
 };
 
 static char slot_type_char[] = {
@@ -430,6 +451,12 @@ static struct bpf_func_state *func(struct bpf_verifier_env *env,
 	return cur->frame[reg->frameno];
 }
 
+const char *kernel_type_name(u32 id)
+{
+	return btf_name_by_offset(btf_vmlinux,
+				  btf_type_by_id(btf_vmlinux, id)->name_off);
+}
+
 static void print_verifier_state(struct bpf_verifier_env *env,
 				 const struct bpf_func_state *state)
 {
@@ -454,6 +481,8 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 			/* reg->off should be 0 for SCALAR_VALUE */
 			verbose(env, "%lld", reg->var_off.value + reg->off);
 		} else {
+			if (t == PTR_TO_BTF_ID)
+				verbose(env, "%s", kernel_type_name(reg->btf_id));
 			verbose(env, "(id=%d", reg->id);
 			if (reg_type_may_be_refcounted_or_null(t))
 				verbose(env, ",ref_obj_id=%d", reg->ref_obj_id);
@@ -2331,10 +2360,12 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
 
 /* check access to 'struct bpf_context' fields.  Supports fixed offsets only */
 static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size,
-			    enum bpf_access_type t, enum bpf_reg_type *reg_type)
+			    enum bpf_access_type t, enum bpf_reg_type *reg_type,
+			    u32 *btf_id)
 {
 	struct bpf_insn_access_aux info = {
 		.reg_type = *reg_type,
+		.log = &env->log,
 	};
 
 	if (env->ops->is_valid_access &&
@@ -2348,7 +2379,10 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off,
 		 */
 		*reg_type = info.reg_type;
 
-		env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
+		if (*reg_type == PTR_TO_BTF_ID)
+			*btf_id = info.btf_id;
+		else
+			env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
 		/* remember the offset of last byte accessed in ctx */
 		if (env->prog->aux->max_ctx_offset < off + size)
 			env->prog->aux->max_ctx_offset = off + size;
@@ -2774,6 +2808,53 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
 	return 0;
 }
 
+static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
+				   struct bpf_reg_state *regs,
+				   int regno, int off, int size,
+				   enum bpf_access_type atype,
+				   int value_regno)
+{
+	struct bpf_reg_state *reg = regs + regno;
+	const struct btf_type *t = btf_type_by_id(btf_vmlinux, reg->btf_id);
+	const char *tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+	u32 btf_id;
+	int ret;
+
+	if (atype != BPF_READ) {
+		verbose(env, "only read is supported\n");
+		return -EACCES;
+	}
+
+	if (off < 0) {
+		verbose(env,
+			"R%d is ptr_%s invalid negative access: off=%d\n",
+			regno, tname, off);
+		return -EACCES;
+	}
+	if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
+		char tn_buf[48];
+
+		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+		verbose(env,
+			"R%d is ptr_%s invalid variable offset: off=%d, var_off=%s\n",
+			regno, tname, off, tn_buf);
+		return -EACCES;
+	}
+
+	ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id);
+	if (ret < 0)
+		return ret;
+
+	if (ret == SCALAR_VALUE) {
+		mark_reg_unknown(env, regs, value_regno);
+		return 0;
+	}
+	mark_reg_known_zero(env, regs, value_regno);
+	regs[value_regno].type = PTR_TO_BTF_ID;
+	regs[value_regno].btf_id = btf_id;
+	return 0;
+}
+
 /* check whether memory at (regno + off) is accessible for t = (read | write)
  * if t==write, value_regno is a register which value is stored into memory
  * if t==read, value_regno is a register which will receive the value from memory
@@ -2834,6 +2915,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		}
 	} else if (reg->type == PTR_TO_CTX) {
 		enum bpf_reg_type reg_type = SCALAR_VALUE;
+		u32 btf_id = 0;
 
 		if (t == BPF_WRITE && value_regno >= 0 &&
 		    is_pointer_value(env, value_regno)) {
@@ -2845,7 +2927,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		if (err < 0)
 			return err;
 
-		err = check_ctx_access(env, insn_idx, off, size, t, &reg_type);
+		err = check_ctx_access(env, insn_idx, off, size, t, &reg_type, &btf_id);
+		if (err)
+			verbose_linfo(env, insn_idx, "; ");
 		if (!err && t == BPF_READ && value_regno >= 0) {
 			/* ctx access returns either a scalar, or a
 			 * PTR_TO_PACKET[_META,_END]. In the latter
@@ -2864,6 +2948,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 				 * a sub-register.
 				 */
 				regs[value_regno].subreg_def = DEF_NOT_SUBREG;
+				if (reg_type == PTR_TO_BTF_ID)
+					regs[value_regno].btf_id = btf_id;
 			}
 			regs[value_regno].type = reg_type;
 		}
@@ -2923,6 +3009,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		err = check_tp_buffer_access(env, reg, regno, off, size);
 		if (!err && t == BPF_READ && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
+	} else if (reg->type == PTR_TO_BTF_ID) {
+		err = check_ptr_to_btf_access(env, regs, regno, off, size, t,
+					      value_regno);
 	} else {
 		verbose(env, "R%d invalid mem access '%s'\n", regno,
 			reg_type_str[reg->type]);
@@ -3351,6 +3440,22 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		expected_type = PTR_TO_SOCKET;
 		if (type != expected_type)
 			goto err_type;
+	} else if (arg_type == ARG_PTR_TO_BTF_ID) {
+		expected_type = PTR_TO_BTF_ID;
+		if (type != expected_type)
+			goto err_type;
+		if (reg->btf_id != meta->btf_id) {
+			verbose(env, "Helper has type %s got %s in R%d\n",
+				kernel_type_name(meta->btf_id),
+				kernel_type_name(reg->btf_id), regno);
+
+			return -EACCES;
+		}
+		if (!tnum_is_const(reg->var_off) || reg->var_off.value || reg->off) {
+			verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n",
+				regno);
+			return -EACCES;
+		}
 	} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
 		if (meta->func_id == BPF_FUNC_spin_lock) {
 			if (process_spin_lock(env, regno, true))
@@ -3498,6 +3603,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
 		if (func_id != BPF_FUNC_perf_event_read &&
 		    func_id != BPF_FUNC_perf_event_output &&
+		    func_id != BPF_FUNC_skb_output &&
 		    func_id != BPF_FUNC_perf_event_read_value)
 			goto error;
 		break;
@@ -3585,6 +3691,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_FUNC_perf_event_read:
 	case BPF_FUNC_perf_event_output:
 	case BPF_FUNC_perf_event_read_value:
+	case BPF_FUNC_skb_output:
 		if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
 			goto error;
 		break;
@@ -4039,21 +4146,16 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 
 	meta.func_id = func_id;
 	/* check args */
-	err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta);
-	if (err)
-		return err;
-	err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta);
-	if (err)
-		return err;
-	err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta);
-	if (err)
-		return err;
-	err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &meta);
-	if (err)
-		return err;
-	err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &meta);
-	if (err)
-		return err;
+	for (i = 0; i < 5; i++) {
+		if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID) {
+			if (!fn->btf_id[i])
+				fn->btf_id[i] = btf_resolve_helper_id(&env->log, fn->func, i);
+			meta.btf_id = fn->btf_id[i];
+		}
+		err = check_func_arg(env, BPF_REG_1 + i, fn->arg_type[i], &meta);
+		if (err)
+			return err;
+	}
 
 	err = record_func_map(env, &meta, func_id, insn_idx);
 	if (err)
@@ -7493,6 +7595,7 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type)
 	case PTR_TO_TCP_SOCK:
 	case PTR_TO_TCP_SOCK_OR_NULL:
 	case PTR_TO_XDP_SOCK:
+	case PTR_TO_BTF_ID:
 		return false;
 	default:
 		return true;
@@ -8634,6 +8737,14 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		case PTR_TO_XDP_SOCK:
 			convert_ctx_access = bpf_xdp_sock_convert_ctx_access;
 			break;
+		case PTR_TO_BTF_ID:
+			if (type == BPF_WRITE) {
+				verbose(env, "Writes through BTF pointers are not allowed\n");
+				return -EINVAL;
+			}
+			insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code);
+			env->prog->aux->num_exentries++;
+			continue;
 		default:
 			continue;
 		}
@@ -9261,6 +9372,52 @@ static void print_verification_stats(struct bpf_verifier_env *env)
 		env->peak_states, env->longest_mark_read_walk);
 }
 
+static int check_attach_btf_id(struct bpf_verifier_env *env)
+{
+	struct bpf_prog *prog = env->prog;
+	u32 btf_id = prog->aux->attach_btf_id;
+	const struct btf_type *t;
+	const char *tname;
+
+	if (prog->type == BPF_PROG_TYPE_RAW_TRACEPOINT && btf_id) {
+		const char prefix[] = "btf_trace_";
+
+		t = btf_type_by_id(btf_vmlinux, btf_id);
+		if (!t) {
+			verbose(env, "attach_btf_id %u is invalid\n", btf_id);
+			return -EINVAL;
+		}
+		if (!btf_type_is_typedef(t)) {
+			verbose(env, "attach_btf_id %u is not a typedef\n",
+				btf_id);
+			return -EINVAL;
+		}
+		tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+		if (!tname || strncmp(prefix, tname, sizeof(prefix) - 1)) {
+			verbose(env, "attach_btf_id %u points to wrong type name %s\n",
+				btf_id, tname);
+			return -EINVAL;
+		}
+		tname += sizeof(prefix) - 1;
+		t = btf_type_by_id(btf_vmlinux, t->type);
+		if (!btf_type_is_ptr(t))
+			/* should never happen in valid vmlinux build */
+			return -EINVAL;
+		t = btf_type_by_id(btf_vmlinux, t->type);
+		if (!btf_type_is_func_proto(t))
+			/* should never happen in valid vmlinux build */
+			return -EINVAL;
+
+		/* remember two read only pointers that are valid for
+		 * the life time of the kernel
+		 */
+		prog->aux->attach_func_name = tname;
+		prog->aux->attach_func_proto = t;
+		prog->aux->attach_btf_trace = true;
+	}
+	return 0;
+}
+
 int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	      union bpf_attr __user *uattr)
 {
@@ -9294,6 +9451,13 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	env->ops = bpf_verifier_ops[env->prog->type];
 	is_priv = capable(CAP_SYS_ADMIN);
 
+	if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) {
+		mutex_lock(&bpf_verifier_lock);
+		if (!btf_vmlinux)
+			btf_vmlinux = btf_parse_vmlinux();
+		mutex_unlock(&bpf_verifier_lock);
+	}
+
 	/* grab the mutex to protect few globals used by verifier */
 	if (!is_priv)
 		mutex_lock(&bpf_verifier_lock);
@@ -9313,6 +9477,17 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 			goto err_unlock;
 	}
 
+	if (IS_ERR(btf_vmlinux)) {
+		/* Either gcc or pahole or kernel are broken. */
+		verbose(env, "in-kernel BTF is malformed\n");
+		ret = PTR_ERR(btf_vmlinux);
+		goto skip_full_check;
+	}
+
+	ret = check_attach_btf_id(env);
+	if (ret)
+		goto skip_full_check;
+
 	env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
 		env->strict_alignment = true;