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, 120 insertions, 80 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c8cc09013210..f4c16f19f83e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1103,7 +1103,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 /* an array of programs to be executed under rcu_lock.
  *
  * Typical usage:
- * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, BPF_PROG_RUN);
+ * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, bpf_prog_run);
  *
  * the structure returned by bpf_prog_array_alloc() should be populated
  * with program pointers and the last pointer must be NULL.
@@ -1114,7 +1114,10 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
  */
 struct bpf_prog_array_item {
 	struct bpf_prog *prog;
-	struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
+	union {
+		struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
+		u64 bpf_cookie;
+	};
 };
 
 struct bpf_prog_array {
@@ -1140,73 +1143,133 @@ int bpf_prog_array_copy_info(struct bpf_prog_array *array,
 int bpf_prog_array_copy(struct bpf_prog_array *old_array,
 			struct bpf_prog *exclude_prog,
 			struct bpf_prog *include_prog,
+			u64 bpf_cookie,
 			struct bpf_prog_array **new_array);
 
 struct bpf_run_ctx {};
 
 struct bpf_cg_run_ctx {
 	struct bpf_run_ctx run_ctx;
-	struct bpf_prog_array_item *prog_item;
+	const struct bpf_prog_array_item *prog_item;
+};
+
+struct bpf_trace_run_ctx {
+	struct bpf_run_ctx run_ctx;
+	u64 bpf_cookie;
 };
 
+static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx)
+{
+	struct bpf_run_ctx *old_ctx = NULL;
+
+#ifdef CONFIG_BPF_SYSCALL
+	old_ctx = current->bpf_ctx;
+	current->bpf_ctx = new_ctx;
+#endif
+	return old_ctx;
+}
+
+static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx)
+{
+#ifdef CONFIG_BPF_SYSCALL
+	current->bpf_ctx = old_ctx;
+#endif
+}
+
 /* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */
 #define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE			(1 << 0)
 /* BPF program asks to set CN on the packet. */
 #define BPF_RET_SET_CN						(1 << 0)
 
-#define BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, ret_flags)		\
-	({								\
-		struct bpf_prog_array_item *_item;			\
-		struct bpf_prog *_prog;					\
-		struct bpf_prog_array *_array;				\
-		struct bpf_run_ctx *old_run_ctx;			\
-		struct bpf_cg_run_ctx run_ctx;				\
-		u32 _ret = 1;						\
-		u32 func_ret;						\
-		migrate_disable();					\
-		rcu_read_lock();					\
-		_array = rcu_dereference(array);			\
-		_item = &_array->items[0];				\
-		old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);	\
-		while ((_prog = READ_ONCE(_item->prog))) {		\
-			run_ctx.prog_item = _item;			\
-			func_ret = func(_prog, ctx);			\
-			_ret &= (func_ret & 1);				\
-			*(ret_flags) |= (func_ret >> 1);		\
-			_item++;					\
-		}							\
-		bpf_reset_run_ctx(old_run_ctx);				\
-		rcu_read_unlock();					\
-		migrate_enable();					\
-		_ret;							\
-	 })
-
-#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null, set_cg_storage)	\
-	({						\
-		struct bpf_prog_array_item *_item;	\
-		struct bpf_prog *_prog;			\
-		struct bpf_prog_array *_array;		\
-		struct bpf_run_ctx *old_run_ctx;	\
-		struct bpf_cg_run_ctx run_ctx;		\
-		u32 _ret = 1;				\
-		migrate_disable();			\
-		rcu_read_lock();			\
-		_array = rcu_dereference(array);	\
-		if (unlikely(check_non_null && !_array))\
-			goto _out;			\
-		_item = &_array->items[0];		\
-		old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);\
-		while ((_prog = READ_ONCE(_item->prog))) {	\
-			run_ctx.prog_item = _item;	\
-			_ret &= func(_prog, ctx);	\
-			_item++;			\
-		}					\
-		bpf_reset_run_ctx(old_run_ctx);		\
-_out:							\
-		rcu_read_unlock();			\
-		migrate_enable();			\
-		_ret;					\
-	 })
+typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx);
+
+static __always_inline u32
+BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu,
+			    const void *ctx, bpf_prog_run_fn run_prog,
+			    u32 *ret_flags)
+{
+	const struct bpf_prog_array_item *item;
+	const struct bpf_prog *prog;
+	const struct bpf_prog_array *array;
+	struct bpf_run_ctx *old_run_ctx;
+	struct bpf_cg_run_ctx run_ctx;
+	u32 ret = 1;
+	u32 func_ret;
+
+	migrate_disable();
+	rcu_read_lock();
+	array = rcu_dereference(array_rcu);
+	item = &array->items[0];
+	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
+	while ((prog = READ_ONCE(item->prog))) {
+		run_ctx.prog_item = item;
+		func_ret = run_prog(prog, ctx);
+		ret &= (func_ret & 1);
+		*(ret_flags) |= (func_ret >> 1);
+		item++;
+	}
+	bpf_reset_run_ctx(old_run_ctx);
+	rcu_read_unlock();
+	migrate_enable();
+	return ret;
+}
+
+static __always_inline u32
+BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu,
+		      const void *ctx, bpf_prog_run_fn run_prog)
+{
+	const struct bpf_prog_array_item *item;
+	const struct bpf_prog *prog;
+	const struct bpf_prog_array *array;
+	struct bpf_run_ctx *old_run_ctx;
+	struct bpf_cg_run_ctx run_ctx;
+	u32 ret = 1;
+
+	migrate_disable();
+	rcu_read_lock();
+	array = rcu_dereference(array_rcu);
+	item = &array->items[0];
+	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
+	while ((prog = READ_ONCE(item->prog))) {
+		run_ctx.prog_item = item;
+		ret &= run_prog(prog, ctx);
+		item++;
+	}
+	bpf_reset_run_ctx(old_run_ctx);
+	rcu_read_unlock();
+	migrate_enable();
+	return ret;
+}
+
+static __always_inline u32
+BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu,
+		   const void *ctx, bpf_prog_run_fn run_prog)
+{
+	const struct bpf_prog_array_item *item;
+	const struct bpf_prog *prog;
+	const struct bpf_prog_array *array;
+	struct bpf_run_ctx *old_run_ctx;
+	struct bpf_trace_run_ctx run_ctx;
+	u32 ret = 1;
+
+	migrate_disable();
+	rcu_read_lock();
+	array = rcu_dereference(array_rcu);
+	if (unlikely(!array))
+		goto out;
+	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
+	item = &array->items[0];
+	while ((prog = READ_ONCE(item->prog))) {
+		run_ctx.bpf_cookie = item->bpf_cookie;
+		ret &= run_prog(prog, ctx);
+		item++;
+	}
+	bpf_reset_run_ctx(old_run_ctx);
+out:
+	rcu_read_unlock();
+	migrate_enable();
+	return ret;
+}
 
 /* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs
  * so BPF programs can request cwr for TCP packets.
@@ -1235,7 +1298,7 @@ _out:							\
 		u32 _flags = 0;				\
 		bool _cn;				\
 		u32 _ret;				\
-		_ret = BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, &_flags); \
+		_ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \
 		_cn = _flags & BPF_RET_SET_CN;		\
 		if (_ret)				\
 			_ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS);	\
@@ -1244,12 +1307,6 @@ _out:							\
 		_ret;					\
 	})
 
-#define BPF_PROG_RUN_ARRAY(array, ctx, func)		\
-	__BPF_PROG_RUN_ARRAY(array, ctx, func, false, true)
-
-#define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func)	\
-	__BPF_PROG_RUN_ARRAY(array, ctx, func, true, false)
-
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
 extern struct mutex bpf_stats_enabled_mutex;
@@ -1284,20 +1341,6 @@ static inline void bpf_enable_instrumentation(void)
 	migrate_enable();
 }
 
-static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx)
-{
-	struct bpf_run_ctx *old_ctx;
-
-	old_ctx = current->bpf_ctx;
-	current->bpf_ctx = new_ctx;
-	return old_ctx;
-}
-
-static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx)
-{
-	current->bpf_ctx = old_ctx;
-}
-
 extern const struct file_operations bpf_map_fops;
 extern const struct file_operations bpf_prog_fops;
 extern const struct file_operations bpf_iter_fops;
@@ -2059,9 +2102,6 @@ extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto;
 extern const struct bpf_func_proto bpf_sk_setsockopt_proto;
 extern const struct bpf_func_proto bpf_sk_getsockopt_proto;
 
-const struct bpf_func_proto *bpf_tracing_func_proto(
-	enum bpf_func_id func_id, const struct bpf_prog *prog);
-
 const struct bpf_func_proto *tracing_prog_func_proto(
   enum bpf_func_id func_id, const struct bpf_prog *prog);