Merge branch 'bpf-misc-updates'

Daniel Borkmann says:

====================
Misc BPF updates

This set contains a couple of misc updates: stack usage reduction
for perf_sample_data in tracing progs, reduction of stale data in
verifier on register state transitions that I still had in my queue
and few selftest improvements as well as bpf_set_hash() helper for
tc programs.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

include/uapi/linux/bpf.h

@@ -513,6 +513,11 @@ union bpf_attr {
  *     Get the owner uid of the socket stored inside sk_buff.
  *     @skb: pointer to skb
  *     Return: uid of the socket owner on success or overflowuid if failed.
+ *
+ * u32 bpf_set_hash(skb, hash)
+ *     Set full skb->hash.
+ *     @skb: pointer to skb
+ *     @hash: hash to set
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -562,7 +567,8 @@ union bpf_attr {
 	FN(xdp_adjust_head),		\
 	FN(probe_read_str),		\
 	FN(get_socket_cookie),		\
-	FN(get_socket_uid),
+	FN(get_socket_uid),		\
+	FN(set_hash),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

kernel/bpf/verifier.c

@@ -1346,8 +1346,8 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
 		if (reg->type != PTR_TO_PACKET &&
 		    reg->type != PTR_TO_PACKET_END)
 			continue;
-		reg->type = UNKNOWN_VALUE;
-		reg->imm = 0;
+		__mark_reg_unknown_value(state->spilled_regs,
+					 i / BPF_REG_SIZE);
 	}
 }
 
@@ -1952,6 +1952,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			 */
 			regs[insn->dst_reg].type = CONST_IMM;
 			regs[insn->dst_reg].imm = insn->imm;
+			regs[insn->dst_reg].id = 0;
 			regs[insn->dst_reg].max_value = insn->imm;
 			regs[insn->dst_reg].min_value = insn->imm;
 			regs[insn->dst_reg].min_align = calc_align(insn->imm);
@@ -2409,6 +2410,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 
 		regs[insn->dst_reg].type = CONST_IMM;
 		regs[insn->dst_reg].imm = imm;
+		regs[insn->dst_reg].id = 0;
 		return 0;
 	}
 
@@ -2828,6 +2830,8 @@ static bool states_equal(struct bpf_verifier_env *env,
 			return false;
 		if (i % BPF_REG_SIZE)
 			continue;
+		if (old->stack_slot_type[i] != STACK_SPILL)
+			continue;
 		if (memcmp(&old->spilled_regs[i / BPF_REG_SIZE],
 			   &cur->spilled_regs[i / BPF_REG_SIZE],
 			   sizeof(old->spilled_regs[0])))

kernel/trace/bpf_trace.c

@@ -266,14 +266,16 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+static DEFINE_PER_CPU(struct perf_sample_data, bpf_sd);
+
 static __always_inline u64
 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 			u64 flags, struct perf_raw_record *raw)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct perf_sample_data *sd = this_cpu_ptr(&bpf_sd);
 	unsigned int cpu = smp_processor_id();
 	u64 index = flags & BPF_F_INDEX_MASK;
-	struct perf_sample_data sample_data;
 	struct bpf_event_entry *ee;
 	struct perf_event *event;
 
@@ -294,9 +296,9 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 	if (unlikely(event->oncpu != cpu))
 		return -EOPNOTSUPP;
 
-	perf_sample_data_init(&sample_data, 0, 0);
-	sample_data.raw = raw;
-	perf_event_output(event, &sample_data, regs);
+	perf_sample_data_init(sd, 0, 0);
+	sd->raw = raw;
+	perf_event_output(event, sd, regs);
 	return 0;
 }
 

net/core/filter.c

@@ -1874,6 +1874,24 @@ static const struct bpf_func_proto bpf_set_hash_invalid_proto = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_2(bpf_set_hash, struct sk_buff *, skb, u32, hash)
+{
+	/* Set user specified hash as L4(+), so that it gets returned
+	 * on skb_get_hash() call unless BPF prog later on triggers a
+	 * skb_clear_hash().
+	 */
+	__skb_set_sw_hash(skb, hash, true);
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_set_hash_proto = {
+	.func		= bpf_set_hash,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto,
 	   u16, vlan_tci)
 {
@@ -2744,6 +2762,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
 		return &bpf_get_hash_recalc_proto;
 	case BPF_FUNC_set_hash_invalid:
 		return &bpf_set_hash_invalid_proto;
+	case BPF_FUNC_set_hash:
+		return &bpf_set_hash_proto;
 	case BPF_FUNC_perf_event_output:
 		return &bpf_skb_event_output_proto;
 	case BPF_FUNC_get_smp_processor_id:
@@ -2774,12 +2794,6 @@ xdp_func_proto(enum bpf_func_id func_id)
 	}
 }
 
-static const struct bpf_func_proto *
-cg_skb_func_proto(enum bpf_func_id func_id)
-{
-	return sk_filter_func_proto(func_id);
-}
-
 static const struct bpf_func_proto *
 lwt_inout_func_proto(enum bpf_func_id func_id)
 {
@@ -3344,7 +3358,7 @@ const struct bpf_verifier_ops xdp_prog_ops = {
 };
 
 const struct bpf_verifier_ops cg_skb_prog_ops = {
-	.get_func_proto		= cg_skb_func_proto,
+	.get_func_proto		= sk_filter_func_proto,
 	.is_valid_access	= sk_filter_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
 	.test_run		= bpf_prog_test_run_skb,

tools/include/uapi/linux/bpf.h

@@ -513,6 +513,11 @@ union bpf_attr {
  *     Get the owner uid of the socket stored inside sk_buff.
  *     @skb: pointer to skb
  *     Return: uid of the socket owner on success or overflowuid if failed.
+ *
+ * u32 bpf_set_hash(skb, hash)
+ *     Set full skb->hash.
+ *     @skb: pointer to skb
+ *     @hash: hash to set
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -562,7 +567,8 @@ union bpf_attr {
 	FN(xdp_adjust_head),		\
 	FN(probe_read_str),		\
 	FN(get_socket_cookie),		\
-	FN(get_socket_uid),
+	FN(get_socket_uid),		\
+	FN(set_hash),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

tools/testing/selftests/bpf/test_align.c

@@ -9,6 +9,8 @@
 #include <stddef.h>
 #include <stdbool.h>
 
+#include <sys/resource.h>
+
 #include <linux/unistd.h>
 #include <linux/filter.h>
 #include <linux/bpf_perf_event.h>
@@ -432,6 +434,9 @@ static int do_test(unsigned int from, unsigned int to)
 int main(int argc, char **argv)
 {
 	unsigned int from = 0, to = ARRAY_SIZE(tests);
+	struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY };
+
+	setrlimit(RLIMIT_MEMLOCK, &rinf);
 
 	if (argc == 3) {
 		unsigned int l = atoi(argv[argc - 2]);

tools/testing/selftests/bpf/test_maps.c

@@ -239,6 +239,54 @@ static void test_hashmap_percpu(int task, void *data)
 	close(fd);
 }
 
+static void test_hashmap_walk(int task, void *data)
+{
+	int fd, i, max_entries = 100000;
+	long long key, value, next_key;
+	bool next_key_valid = true;
+
+	fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value),
+			    max_entries, map_flags);
+	if (fd < 0) {
+		printf("Failed to create hashmap '%s'!\n", strerror(errno));
+		exit(1);
+	}
+
+	for (i = 0; i < max_entries; i++) {
+		key = i; value = key;
+		assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == 0);
+	}
+
+	for (i = 0; bpf_map_get_next_key(fd, !i ? NULL : &key,
+					 &next_key) == 0; i++) {
+		key = next_key;
+		assert(bpf_map_lookup_elem(fd, &key, &value) == 0);
+	}
+
+	assert(i == max_entries);
+
+	assert(bpf_map_get_next_key(fd, NULL, &key) == 0);
+	for (i = 0; next_key_valid; i++) {
+		next_key_valid = bpf_map_get_next_key(fd, &key, &next_key) == 0;
+		assert(bpf_map_lookup_elem(fd, &key, &value) == 0);
+		value++;
+		assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) == 0);
+		key = next_key;
+	}
+
+	assert(i == max_entries);
+
+	for (i = 0; bpf_map_get_next_key(fd, !i ? NULL : &key,
+					 &next_key) == 0; i++) {
+		key = next_key;
+		assert(bpf_map_lookup_elem(fd, &key, &value) == 0);
+		assert(value - 1 == key);
+	}
+
+	assert(i == max_entries);
+	close(fd);
+}
+
 static void test_arraymap(int task, void *data)
 {
 	int key, next_key, fd;
@@ -464,6 +512,7 @@ static void test_map_stress(void)
 	run_parallel(100, test_hashmap, NULL);
 	run_parallel(100, test_hashmap_percpu, NULL);
 	run_parallel(100, test_hashmap_sizes, NULL);
+	run_parallel(100, test_hashmap_walk, NULL);
 
 	run_parallel(100, test_arraymap, NULL);
 	run_parallel(100, test_arraymap_percpu, NULL);
@@ -549,6 +598,7 @@ static void run_all_tests(void)
 {
 	test_hashmap(0, NULL);
 	test_hashmap_percpu(0, NULL);
+	test_hashmap_walk(0, NULL);
 
 	test_arraymap(0, NULL);
 	test_arraymap_percpu(0, NULL);