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

Daniel Borkmann says:

====================
bpf-next 2021-08-31

We've added 116 non-merge commits during the last 17 day(s) which contain
a total of 126 files changed, 6813 insertions(+), 4027 deletions(-).

The main changes are:

1) Add opaque bpf_cookie to perf link which the program can read out again,
   to be used in libbpf-based USDT library, from Andrii Nakryiko.

2) Add bpf_task_pt_regs() helper to access userspace pt_regs, from Daniel Xu.

3) Add support for UNIX stream type sockets for BPF sockmap, from Jiang Wang.

4) Allow BPF TCP congestion control progs to call bpf_setsockopt() e.g. to switch
   to another congestion control algorithm during init, from Martin KaFai Lau.

5) Extend BPF iterator support for UNIX domain sockets, from Kuniyuki Iwashima.

6) Allow bpf_{set,get}sockopt() calls from setsockopt progs, from Prankur Gupta.

7) Add bpf_get_netns_cookie() helper for BPF_PROG_TYPE_{SOCK_OPS,CGROUP_SOCKOPT}
   progs, from Xu Liu and Stanislav Fomichev.

8) Support for __weak typed ksyms in libbpf, from Hao Luo.

9) Shrink struct cgroup_bpf by 504 bytes through refactoring, from Dave Marchevsky.

10) Fix a smatch complaint in verifier's narrow load handling, from Andrey Ignatov.

11) Fix BPF interpreter's tail call count limit, from Daniel Borkmann.

12) Big batch of improvements to BPF selftests, from Magnus Karlsson, Li Zhijian,
    Yucong Sun, Yonghong Song, Ilya Leoshkevich, Jussi Maki, Ilya Leoshkevich, others.

13) Another big batch to revamp XDP samples in order to give them consistent look
    and feel, from Kumar Kartikeya Dwivedi.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (116 commits)
  MAINTAINERS: Remove self from powerpc BPF JIT
  selftests/bpf: Fix potential unreleased lock
  samples: bpf: Fix uninitialized variable in xdp_redirect_cpu
  selftests/bpf: Reduce more flakyness in sockmap_listen
  bpf: Fix bpf-next builds without CONFIG_BPF_EVENTS
  bpf: selftests: Add dctcp fallback test
  bpf: selftests: Add connect_to_fd_opts to network_helpers
  bpf: selftests: Add sk_state to bpf_tcp_helpers.h
  bpf: tcp: Allow bpf-tcp-cc to call bpf_(get|set)sockopt
  selftests: xsk: Preface options with opt
  selftests: xsk: Make enums lower case
  selftests: xsk: Generate packets from specification
  selftests: xsk: Generate packet directly in umem
  selftests: xsk: Simplify cleanup of ifobjects
  selftests: xsk: Decrease sending speed
  selftests: xsk: Validate tx stats on tx thread
  selftests: xsk: Simplify packet validation in xsk tests
  selftests: xsk: Rename worker_* functions that are not thread entry points
  selftests: xsk: Disassociate umem size with packets sent
  selftests: xsk: Remove end-of-test packet
  ...
====================

Link: https://lore.kernel.org/r/20210830225618.11634-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 40 insertions, 26 deletions

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1797e8506929..7d248941ecea 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -600,25 +600,38 @@ struct sk_filter {
 
 DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
 
-#define __BPF_PROG_RUN(prog, ctx, dfunc)	({			\
-	u32 __ret;							\
-	cant_migrate();							\
-	if (static_branch_unlikely(&bpf_stats_enabled_key)) {		\
-		struct bpf_prog_stats *__stats;				\
-		u64 __start = sched_clock();				\
-		__ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func);	\
-		__stats = this_cpu_ptr(prog->stats);			\
-		u64_stats_update_begin(&__stats->syncp);		\
-		__stats->cnt++;						\
-		__stats->nsecs += sched_clock() - __start;		\
-		u64_stats_update_end(&__stats->syncp);			\
-	} else {							\
-		__ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func);	\
-	}								\
-	__ret; })
-
-#define BPF_PROG_RUN(prog, ctx)						\
-	__BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func)
+typedef unsigned int (*bpf_dispatcher_fn)(const void *ctx,
+					  const struct bpf_insn *insnsi,
+					  unsigned int (*bpf_func)(const void *,
+								   const struct bpf_insn *));
+
+static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog,
+					  const void *ctx,
+					  bpf_dispatcher_fn dfunc)
+{
+	u32 ret;
+
+	cant_migrate();
+	if (static_branch_unlikely(&bpf_stats_enabled_key)) {
+		struct bpf_prog_stats *stats;
+		u64 start = sched_clock();
+
+		ret = dfunc(ctx, prog->insnsi, prog->bpf_func);
+		stats = this_cpu_ptr(prog->stats);
+		u64_stats_update_begin(&stats->syncp);
+		stats->cnt++;
+		stats->nsecs += sched_clock() - start;
+		u64_stats_update_end(&stats->syncp);
+	} else {
+		ret = dfunc(ctx, prog->insnsi, prog->bpf_func);
+	}
+	return ret;
+}
+
+static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void *ctx)
+{
+	return __bpf_prog_run(prog, ctx, bpf_dispatcher_nop_func);
+}
 
 /*
  * Use in preemptible and therefore migratable context to make sure that
@@ -637,7 +650,7 @@ static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog,
 	u32 ret;
 
 	migrate_disable();
-	ret = __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func);
+	ret = bpf_prog_run(prog, ctx);
 	migrate_enable();
 	return ret;
 }
@@ -710,7 +723,7 @@ static inline void bpf_restore_data_end(
 	cb->data_end = saved_data_end;
 }
 
-static inline u8 *bpf_skb_cb(struct sk_buff *skb)
+static inline u8 *bpf_skb_cb(const struct sk_buff *skb)
 {
 	/* eBPF programs may read/write skb->cb[] area to transfer meta
 	 * data between tail calls. Since this also needs to work with
@@ -731,8 +744,9 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb)
 
 /* Must be invoked with migration disabled */
 static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog,
-					 struct sk_buff *skb)
+					 const void *ctx)
 {
+	const struct sk_buff *skb = ctx;
 	u8 *cb_data = bpf_skb_cb(skb);
 	u8 cb_saved[BPF_SKB_CB_LEN];
 	u32 res;
@@ -742,7 +756,7 @@ static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog,
 		memset(cb_data, 0, sizeof(cb_saved));
 	}
 
-	res = BPF_PROG_RUN(prog, skb);
+	res = bpf_prog_run(prog, skb);
 
 	if (unlikely(prog->cb_access))
 		memcpy(cb_data, cb_saved, sizeof(cb_saved));
@@ -787,7 +801,7 @@ static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog,
 	 * under local_bh_disable(), which provides the needed RCU protection
 	 * for accessing map entries.
 	 */
-	u32 act = __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp));
+	u32 act = __bpf_prog_run(prog, xdp, BPF_DISPATCHER_FUNC(xdp));
 
 	if (static_branch_unlikely(&bpf_master_redirect_enabled_key)) {
 		if (act == XDP_TX && netif_is_bond_slave(xdp->rxq->dev))
@@ -1440,7 +1454,7 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol,
 		};
 		u32 act;
 
-		act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN);
+		act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run);
 		if (act == SK_PASS) {
 			selected_sk = ctx.selected_sk;
 			no_reuseport = ctx.no_reuseport;
@@ -1478,7 +1492,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol,
 		};
 		u32 act;
 
-		act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN);
+		act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run);
 		if (act == SK_PASS) {
 			selected_sk = ctx.selected_sk;
 			no_reuseport = ctx.no_reuseport;