Commit 3b7dc700 authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

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:
  00d066a4 ("netdev_features: convert NETIF_F_LLTX to dev->lltx")
  d9660879 ("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: default avatarJakub Kicinski <kuba@kernel.org>
====================

Link: https://patch.msgid.link/20240911211525.13834-1-daniel@iogearbox.net


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents f1bcd486 b1339be9

drivers/net/netkit.c

+1 −0
Original line number Diff line number Diff line
@@ -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

+6 −6
Original line number Diff line number Diff line
@@ -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

+3 −0
Original line number Diff line number Diff line
@@ -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

+4 −2
Original line number Diff line number Diff line
@@ -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

+32 −4
Original line number Diff line number Diff line
@@ -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 */