bpf-next-for-netdev

-----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQTFp0I1jqZrAX+hPRXbK58LschIgwUCZuH9UQAKCRDbK58LschI
 g0/zAP99WOcCBp1M/jSTUOba230+eiol7l5RirDEA6wu7TqY2QEAuvMG0KfCCpTI
 I0WqStrK1QMbhwKPodJC1k+17jArKgw=
 =jfMU
 -----END PGP SIGNATURE-----

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

Daniel Borkmann says:

====================
pull-request: bpf-next 2024-09-11

We've added 12 non-merge commits during the last 16 day(s) which contain
a total of 20 files changed, 228 insertions(+), 30 deletions(-).

There's a minor merge conflict in drivers/net/netkit.c:
  00d066a4d4 ("netdev_features: convert NETIF_F_LLTX to dev->lltx")
  d966087948 ("netkit: Disable netpoll support")

The main changes are:

1) Enable bpf_dynptr_from_skb for tp_btf such that this can be used
   to easily parse skbs in BPF programs attached to tracepoints,
   from Philo Lu.

2) Add a cond_resched() point in BPF's sock_hash_free() as there have
   been several syzbot soft lockup reports recently, from Eric Dumazet.

3) Fix xsk_buff_can_alloc() to account for queue_empty_descs which
   got noticed when zero copy ice driver started to use it,
   from Maciej Fijalkowski.

4) Move the xdp:xdp_cpumap_kthread tracepoint before cpumap pushes skbs
   up via netif_receive_skb_list() to better measure latencies,
   from Daniel Xu.

5) Follow-up to disable netpoll support from netkit, from Daniel Borkmann.

6) Improve xsk selftests to not assume a fixed MAX_SKB_FRAGS of 17 but
   instead gather the actual value via /proc/sys/net/core/max_skb_frags,
   also from Maciej Fijalkowski.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next:
  sock_map: Add a cond_resched() in sock_hash_free()
  selftests/bpf: Expand skb dynptr selftests for tp_btf
  bpf: Allow bpf_dynptr_from_skb() for tp_btf
  tcp: Use skb__nullable in trace_tcp_send_reset
  selftests/bpf: Add test for __nullable suffix in tp_btf
  bpf: Support __nullable argument suffix for tp_btf
  bpf, cpumap: Move xdp:xdp_cpumap_kthread tracepoint before rcv
  selftests/xsk: Read current MAX_SKB_FRAGS from sysctl knob
  xsk: Bump xsk_queue::queue_empty_descs in xp_can_alloc()
  tcp_bpf: Remove an unused parameter for bpf_tcp_ingress()
  bpf, sockmap: Correct spelling skmsg.c
  netkit: Disable netpoll support

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
====================

Link: https://patch.msgid.link/20240911211525.13834-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/netkit.c

@@ -255,6 +255,7 @@ static void netkit_setup(struct net_device *dev)
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	dev->priv_flags |= IFF_PHONY_HEADROOM;
 	dev->priv_flags |= IFF_NO_QUEUE;
+	dev->priv_flags |= IFF_DISABLE_NETPOLL;
 	dev->lltx = true;
 
 	dev->ethtool_ops = &netkit_ethtool_ops;

include/trace/events/tcp.h

@@ -91,10 +91,10 @@ DEFINE_RST_REASON(FN, FN)
 TRACE_EVENT(tcp_send_reset,
 
 	TP_PROTO(const struct sock *sk,
-		 const struct sk_buff *skb,
+		 const struct sk_buff *skb__nullable,
 		 const enum sk_rst_reason reason),
 
-	TP_ARGS(sk, skb, reason),
+	TP_ARGS(sk, skb__nullable, reason),
 
 	TP_STRUCT__entry(
 		__field(const void *, skbaddr)
@@ -106,7 +106,7 @@ TRACE_EVENT(tcp_send_reset,
 	),
 
 	TP_fast_assign(
-		__entry->skbaddr = skb;
+		__entry->skbaddr = skb__nullable;
 		__entry->skaddr = sk;
 		/* Zero means unknown state. */
 		__entry->state = sk ? sk->sk_state : 0;
@@ -118,13 +118,13 @@ TRACE_EVENT(tcp_send_reset,
 			const struct inet_sock *inet = inet_sk(sk);
 
 			TP_STORE_ADDR_PORTS(__entry, inet, sk);
-		} else if (skb) {
-			const struct tcphdr *th = (const struct tcphdr *)skb->data;
+		} else if (skb__nullable) {
+			const struct tcphdr *th = (const struct tcphdr *)skb__nullable->data;
 			/*
 			 * We should reverse the 4-tuple of skb, so later
 			 * it can print the right flow direction of rst.
 			 */
-			TP_STORE_ADDR_PORTS_SKB(skb, th, entry->daddr, entry->saddr);
+			TP_STORE_ADDR_PORTS_SKB(skb__nullable, th, entry->daddr, entry->saddr);
 		}
 		__entry->reason = reason;
 	),

kernel/bpf/btf.c

@@ -6525,6 +6525,9 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	if (prog_args_trusted(prog))
 		info->reg_type |= PTR_TRUSTED;
 
+	if (btf_param_match_suffix(btf, &args[arg], "__nullable"))
+		info->reg_type |= PTR_MAYBE_NULL;
+
 	if (tgt_prog) {
 		enum bpf_prog_type tgt_type;
 

kernel/bpf/cpumap.c

@@ -354,12 +354,14 @@ static int cpu_map_kthread_run(void *data)
 
 			list_add_tail(&skb->list, &list);
 		}
-		netif_receive_skb_list(&list);
 
-		/* Feedback loop via tracepoint */
+		/* Feedback loop via tracepoint.
+		 * NB: keep before recv to allow measuring enqueue/dequeue latency.
+		 */
 		trace_xdp_cpumap_kthread(rcpu->map_id, n, kmem_alloc_drops,
 					 sched, &stats);
 
+		netif_receive_skb_list(&list);
 		local_bh_enable(); /* resched point, may call do_softirq() */
 	}
 	__set_current_state(TASK_RUNNING);

kernel/bpf/verifier.c

@@ -28,6 +28,8 @@
 #include <linux/cpumask.h>
 #include <linux/bpf_mem_alloc.h>
 #include <net/xdp.h>
+#include <linux/trace_events.h>
+#include <linux/kallsyms.h>
 
 #include "disasm.h"
 
@@ -21154,11 +21156,13 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 {
 	bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
 	bool prog_tracing = prog->type == BPF_PROG_TYPE_TRACING;
+	char trace_symbol[KSYM_SYMBOL_LEN];
 	const char prefix[] = "btf_trace_";
+	struct bpf_raw_event_map *btp;
 	int ret = 0, subprog = -1, i;
 	const struct btf_type *t;
 	bool conservative = true;
-	const char *tname;
+	const char *tname, *fname;
 	struct btf *btf;
 	long addr = 0;
 	struct module *mod = NULL;
@@ -21289,10 +21293,34 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 			return -EINVAL;
 		}
 		tname += sizeof(prefix) - 1;
+
+		/* The func_proto of "btf_trace_##tname" is generated from typedef without argument
+		 * names. Thus using bpf_raw_event_map to get argument names.
+		 */
+		btp = bpf_get_raw_tracepoint(tname);
+		if (!btp)
+			return -EINVAL;
+		fname = kallsyms_lookup((unsigned long)btp->bpf_func, NULL, NULL, NULL,
+					trace_symbol);
+		bpf_put_raw_tracepoint(btp);
+
+		if (fname)
+			ret = btf_find_by_name_kind(btf, fname, BTF_KIND_FUNC);
+
+		if (!fname || ret < 0) {
+			bpf_log(log, "Cannot find btf of tracepoint template, fall back to %s%s.\n",
+				prefix, tname);
 			t = btf_type_by_id(btf, t->type);
 			if (!btf_type_is_ptr(t))
 				/* should never happen in valid vmlinux build */
 				return -EINVAL;
+		} else {
+			t = btf_type_by_id(btf, ret);
+			if (!btf_type_is_func(t))
+				/* should never happen in valid vmlinux build */
+				return -EINVAL;
+		}
+
 		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_func_proto(t))
 			/* should never happen in valid vmlinux build */

net/core/filter.c

@@ -12063,7 +12063,7 @@ int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
 }
 
 BTF_KFUNCS_START(bpf_kfunc_check_set_skb)
-BTF_ID_FLAGS(func, bpf_dynptr_from_skb)
+BTF_ID_FLAGS(func, bpf_dynptr_from_skb, KF_TRUSTED_ARGS)
 BTF_KFUNCS_END(bpf_kfunc_check_set_skb)
 
 BTF_KFUNCS_START(bpf_kfunc_check_set_xdp)
@@ -12112,6 +12112,7 @@ static int __init bpf_kfunc_init(void)
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_XMIT, &bpf_kfunc_set_skb);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_NETFILTER, &bpf_kfunc_set_skb);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_kfunc_set_skb);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
 					       &bpf_kfunc_set_sock_addr);

net/core/skmsg.c

@@ -293,7 +293,7 @@ out:
 	/* If we trim data a full sg elem before curr pointer update
 	 * copybreak and current so that any future copy operations
 	 * start at new copy location.
-	 * However trimed data that has not yet been used in a copy op
+	 * However trimmed data that has not yet been used in a copy op
 	 * does not require an update.
 	 */
 	if (!msg->sg.size) {

net/core/sock_map.c

@@ -1183,6 +1183,7 @@ static void sock_hash_free(struct bpf_map *map)
 			sock_put(elem->sk);
 			sock_hash_free_elem(htab, elem);
 		}
+		cond_resched();
 	}
 
 	/* wait for psock readers accessing its map link */

net/ipv4/tcp_bpf.c

@@ -30,7 +30,7 @@ void tcp_eat_skb(struct sock *sk, struct sk_buff *skb)
 }
 
 static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
-			   struct sk_msg *msg, u32 apply_bytes, int flags)
+			   struct sk_msg *msg, u32 apply_bytes)
 {
 	bool apply = apply_bytes;
 	struct scatterlist *sge;
@@ -167,7 +167,7 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress,
 	if (unlikely(!psock))
 		return -EPIPE;
 
-	ret = ingress ? bpf_tcp_ingress(sk, psock, msg, bytes, flags) :
+	ret = ingress ? bpf_tcp_ingress(sk, psock, msg, bytes) :
 			tcp_bpf_push_locked(sk, msg, bytes, flags, false);
 	sk_psock_put(sk, psock);
 	return ret;

net/xdp/xsk_buff_pool.c

@@ -661,9 +661,17 @@ EXPORT_SYMBOL(xp_alloc_batch);
 
 bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count)
 {
+	u32 req_count, avail_count;
+
 	if (pool->free_list_cnt >= count)
 		return true;
-	return xskq_cons_has_entries(pool->fq, count - pool->free_list_cnt);
+
+	req_count = count - pool->free_list_cnt;
+	avail_count = xskq_cons_nb_entries(pool->fq, req_count);
+	if (!avail_count)
+		pool->fq->queue_empty_descs++;
+
+	return avail_count >= req_count;
 }
 EXPORT_SYMBOL(xp_can_alloc);
 

net/xdp/xsk_queue.h

@@ -306,11 +306,6 @@ static inline u32 xskq_cons_nb_entries(struct xsk_queue *q, u32 max)
 	return entries >= max ? max : entries;
 }
 
-static inline bool xskq_cons_has_entries(struct xsk_queue *q, u32 cnt)
-{
-	return xskq_cons_nb_entries(q, cnt) >= cnt;
-}
-
 static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr)
 {
 	if (q->cached_prod == q->cached_cons)

tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h

@@ -34,6 +34,12 @@ DECLARE_TRACE(bpf_testmod_test_write_bare,
 	TP_ARGS(task, ctx)
 );
 
+/* Used in bpf_testmod_test_read() to test __nullable suffix */
+DECLARE_TRACE(bpf_testmod_test_nullable_bare,
+	TP_PROTO(struct bpf_testmod_test_read_ctx *ctx__nullable),
+	TP_ARGS(ctx__nullable)
+);
+
 #undef BPF_TESTMOD_DECLARE_TRACE
 #ifdef DECLARE_TRACE_WRITABLE
 #define BPF_TESTMOD_DECLARE_TRACE(call, proto, args, size) \

tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c

@@ -356,6 +356,8 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 	if (bpf_testmod_loop_test(101) > 100)
 		trace_bpf_testmod_test_read(current, &ctx);
 
+	trace_bpf_testmod_test_nullable_bare(NULL);
+
 	/* Magic number to enable writable tp */
 	if (len == 64) {
 		struct bpf_testmod_test_writable_ctx writable = {

tools/testing/selftests/bpf/prog_tests/dynptr.c

@@ -9,6 +9,7 @@
 enum test_setup_type {
 	SETUP_SYSCALL_SLEEP,
 	SETUP_SKB_PROG,
+	SETUP_SKB_PROG_TP,
 };
 
 static struct {
@@ -28,6 +29,7 @@ static struct {
 	{"test_dynptr_clone", SETUP_SKB_PROG},
 	{"test_dynptr_skb_no_buff", SETUP_SKB_PROG},
 	{"test_dynptr_skb_strcmp", SETUP_SKB_PROG},
+	{"test_dynptr_skb_tp_btf", SETUP_SKB_PROG_TP},
 };
 
 static void verify_success(const char *prog_name, enum test_setup_type setup_type)
@@ -87,6 +89,37 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ
 
 		break;
 	}
+	case SETUP_SKB_PROG_TP:
+	{
+		struct __sk_buff skb = {};
+		struct bpf_object *obj;
+		int aux_prog_fd;
+
+		/* Just use its test_run to trigger kfree_skb tracepoint */
+		err = bpf_prog_test_load("./test_pkt_access.bpf.o", BPF_PROG_TYPE_SCHED_CLS,
+					 &obj, &aux_prog_fd);
+		if (!ASSERT_OK(err, "prog_load sched cls"))
+			goto cleanup;
+
+		LIBBPF_OPTS(bpf_test_run_opts, topts,
+			    .data_in = &pkt_v4,
+			    .data_size_in = sizeof(pkt_v4),
+			    .ctx_in = &skb,
+			    .ctx_size_in = sizeof(skb),
+		);
+
+		link = bpf_program__attach(prog);
+		if (!ASSERT_OK_PTR(link, "bpf_program__attach"))
+			goto cleanup;
+
+		err = bpf_prog_test_run_opts(aux_prog_fd, &topts);
+		bpf_link__destroy(link);
+
+		if (!ASSERT_OK(err, "test_run"))
+			goto cleanup;
+
+		break;
+	}
 	}
 
 	ASSERT_EQ(skel->bss->err, 0, "err");

tools/testing/selftests/bpf/prog_tests/tp_btf_nullable.c

@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "test_tp_btf_nullable.skel.h"
+
+void test_tp_btf_nullable(void)
+{
+	if (!env.has_testmod) {
+		test__skip();
+		return;
+	}
+
+	RUN_TESTS(test_tp_btf_nullable);
+}

tools/testing/selftests/bpf/progs/dynptr_fail.c

@@ -6,6 +6,7 @@
 #include <stdbool.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 #include <linux/if_ether.h>
 #include "bpf_misc.h"
 #include "bpf_kfuncs.h"
@@ -1254,6 +1255,30 @@ int skb_invalid_ctx(void *ctx)
 	return 0;
 }
 
+SEC("fentry/skb_tx_error")
+__failure __msg("must be referenced or trusted")
+int BPF_PROG(skb_invalid_ctx_fentry, void *skb)
+{
+	struct bpf_dynptr ptr;
+
+	/* this should fail */
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	return 0;
+}
+
+SEC("fexit/skb_tx_error")
+__failure __msg("must be referenced or trusted")
+int BPF_PROG(skb_invalid_ctx_fexit, void *skb)
+{
+	struct bpf_dynptr ptr;
+
+	/* this should fail */
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	return 0;
+}
+
 /* Reject writes to dynptr slot for uninit arg */
 SEC("?raw_tp")
 __failure __msg("potential write to dynptr at off=-16")

tools/testing/selftests/bpf/progs/dynptr_success.c

@@ -5,6 +5,7 @@
 #include <stdbool.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 #include "bpf_misc.h"
 #include "bpf_kfuncs.h"
 #include "errno.h"
@@ -544,3 +545,25 @@ int test_dynptr_skb_strcmp(struct __sk_buff *skb)
 
 	return 1;
 }
+
+SEC("tp_btf/kfree_skb")
+int BPF_PROG(test_dynptr_skb_tp_btf, void *skb, void *location)
+{
+	__u8 write_data[2] = {1, 2};
+	struct bpf_dynptr ptr;
+	int ret;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr)) {
+		err = 1;
+		return 1;
+	}
+
+	/* since tp_btf skbs are read only, writes should fail */
+	ret = bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0);
+	if (ret != -EINVAL) {
+		err = 2;
+		return 1;
+	}
+
+	return 1;
+}

tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c

@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../bpf_testmod/bpf_testmod.h"
+#include "bpf_misc.h"
+
+SEC("tp_btf/bpf_testmod_test_nullable_bare")
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
+int BPF_PROG(handle_tp_btf_nullable_bare1, struct bpf_testmod_test_read_ctx *nullable_ctx)
+{
+	return nullable_ctx->len;
+}
+
+SEC("tp_btf/bpf_testmod_test_nullable_bare")
+int BPF_PROG(handle_tp_btf_nullable_bare2, struct bpf_testmod_test_read_ctx *nullable_ctx)
+{
+	if (nullable_ctx)
+		return nullable_ctx->len;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/xskxceiver.c

@@ -324,6 +324,25 @@ out:
 	return zc_avail;
 }
 
+#define MAX_SKB_FRAGS_PATH "/proc/sys/net/core/max_skb_frags"
+static unsigned int get_max_skb_frags(void)
+{
+	unsigned int max_skb_frags = 0;
+	FILE *file;
+
+	file = fopen(MAX_SKB_FRAGS_PATH, "r");
+	if (!file) {
+		ksft_print_msg("Error opening %s\n", MAX_SKB_FRAGS_PATH);
+		return 0;
+	}
+
+	if (fscanf(file, "%u", &max_skb_frags) != 1)
+		ksft_print_msg("Error reading %s\n", MAX_SKB_FRAGS_PATH);
+
+	fclose(file);
+	return max_skb_frags;
+}
+
 static struct option long_options[] = {
 	{"interface", required_argument, 0, 'i'},
 	{"busy-poll", no_argument, 0, 'b'},
@@ -2244,13 +2263,24 @@ static int testapp_poll_rxq_tmout(struct test_spec *test)
 
 static int testapp_too_many_frags(struct test_spec *test)
 {
-	struct pkt pkts[2 * XSK_DESC__MAX_SKB_FRAGS + 2] = {};
+	struct pkt *pkts;
 	u32 max_frags, i;
+	int ret;
 
-	if (test->mode == TEST_MODE_ZC)
+	if (test->mode == TEST_MODE_ZC) {
 		max_frags = test->ifobj_tx->xdp_zc_max_segs;
-	else
-		max_frags = XSK_DESC__MAX_SKB_FRAGS;
+	} else {
+		max_frags = get_max_skb_frags();
+		if (!max_frags) {
+			ksft_print_msg("Couldn't retrieve MAX_SKB_FRAGS from system, using default (17) value\n");
+			max_frags = 17;
+		}
+		max_frags += 1;
+	}
+
+	pkts = calloc(2 * max_frags + 2, sizeof(struct pkt));
+	if (!pkts)
+		return TEST_FAILURE;
 
 	test->mtu = MAX_ETH_JUMBO_SIZE;
 
@@ -2280,7 +2310,10 @@ static int testapp_too_many_frags(struct test_spec *test)
 	pkts[2 * max_frags + 1].valid = true;
 
 	pkt_stream_generate_custom(test, pkts, 2 * max_frags + 2);
-	return testapp_validate_traffic(test);
+	ret = testapp_validate_traffic(test);
+
+	free(pkts);
+	return ret;
 }
 
 static int xsk_load_xdp_programs(struct ifobject *ifobj)

tools/testing/selftests/bpf/xskxceiver.h

@@ -55,7 +55,6 @@
 #define XSK_UMEM__LARGE_FRAME_SIZE (3 * 1024)
 #define XSK_UMEM__MAX_FRAME_SIZE (4 * 1024)
 #define XSK_DESC__INVALID_OPTION (0xffff)
-#define XSK_DESC__MAX_SKB_FRAGS 18
 #define HUGEPAGE_SIZE (2 * 1024 * 1024)
 #define PKT_DUMP_NB_TO_PRINT 16
 #define RUN_ALL_TESTS UINT_MAX