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

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-03-04

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Add AF_XDP support to libbpf. Rationale is to facilitate writing
   AF_XDP applications by offering higher-level APIs that hide many
   of the details of the AF_XDP uapi. Sample programs are converted
   over to this new interface as well, from Magnus.

2) Introduce a new cant_sleep() macro for annotation of functions
   that cannot sleep and use it in BPF_PROG_RUN() to assert that
   BPF programs run under preemption disabled context, from Peter.

3) Introduce per BPF prog stats in order to monitor the usage
   of BPF; this is controlled by kernel.bpf_stats_enabled sysctl
   knob where monitoring tools can make use of this to efficiently
   determine the average cost of programs, from Alexei.

4) Split up BPF selftest's test_progs similarly as we already
   did with test_verifier. This allows to further reduce merge
   conflicts in future and to get more structure into our
   quickly growing BPF selftest suite, from Stanislav.

5) Fix a bug in BTF's dedup algorithm which can cause an infinite
   loop in some circumstances; also various BPF doc fixes and
   improvements, from Andrii.

6) Various BPF sample cleanups and migration to libbpf in order
   to further isolate the old sample loader code (so we can get
   rid of it at some point), from Jakub.

7) Add a new BPF helper for BPF cgroup skb progs that allows
   to set ECN CE code point and a Host Bandwidth Manager (HBM)
   sample program for limiting the bandwidth used by v2 cgroups,
   from Lawrence.

8) Enable write access to skb->queue_mapping from tc BPF egress
   programs in order to let BPF pick TX queue, from Jesper.

9) Fix a bug in BPF spinlock handling for map-in-map which did
   not propagate spin_lock_off to the meta map, from Yonghong.

10) Fix a bug in the new per-CPU BPF prog counters to properly
    initialize stats for each CPU, from Eric.

11) Add various BPF helper prototypes to selftest's bpf_helpers.h,
    from Willem.

12) Fix various BPF samples bugs in XDP and tracing progs,
    from Toke, Daniel and Yonghong.

13) Silence preemption splat in test_bpf after BPF_PROG_RUN()
    enforces it now everywhere, from Anders.

14) Fix a signedness bug in libbpf's btf_dedup_ref_type() to
    get error handling working, from Dan.

15) Fix bpftool documentation and auto-completion with regards
    to stream_{verdict,parser} attach types, from Alban.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 51 insertions, 4 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index de18227b3d95..a2132e09dc1c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -16,6 +16,7 @@
 #include <linux/rbtree_latch.h>
 #include <linux/numa.h>
 #include <linux/wait.h>
+#include <linux/u64_stats_sync.h>
 
 struct bpf_verifier_env;
 struct perf_event;
@@ -340,6 +341,12 @@ enum bpf_cgroup_storage_type {
 
 #define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX
 
+struct bpf_prog_stats {
+	u64 cnt;
+	u64 nsecs;
+	struct u64_stats_sync syncp;
+};
+
 struct bpf_prog_aux {
 	atomic_t refcnt;
 	u32 used_map_cnt;
@@ -389,6 +396,7 @@ struct bpf_prog_aux {
 	 * main prog always has linfo_idx == 0
 	 */
 	u32 linfo_idx;
+	struct bpf_prog_stats __percpu *stats;
 	union {
 		struct work_struct work;
 		struct rcu_head	rcu;
@@ -559,6 +567,7 @@ void bpf_map_area_free(void *base);
 void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
 
 extern int sysctl_unprivileged_bpf_disabled;
+extern int sysctl_bpf_stats_enabled;
 
 int bpf_map_new_fd(struct bpf_map *map, int flags);
 int bpf_prog_new_fd(struct bpf_prog *prog);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 95e2d7ebdf21..7e5e3db11106 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -533,7 +533,24 @@ struct sk_filter {
 	struct bpf_prog	*prog;
 };
 
-#define BPF_PROG_RUN(filter, ctx)  (*(filter)->bpf_func)(ctx, (filter)->insnsi)
+DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
+
+#define BPF_PROG_RUN(prog, ctx)	({				\
+	u32 ret;						\
+	cant_sleep();						\
+	if (static_branch_unlikely(&bpf_stats_enabled_key)) {	\
+		struct bpf_prog_stats *stats;			\
+		u64 start = sched_clock();			\
+		ret = (*(prog)->bpf_func)(ctx, (prog)->insnsi);	\
+		stats = this_cpu_ptr(prog->aux->stats);		\
+		u64_stats_update_begin(&stats->syncp);		\
+		stats->cnt++;					\
+		stats->nsecs += sched_clock() - start;		\
+		u64_stats_update_end(&stats->syncp);		\
+	} else {						\
+		ret = (*(prog)->bpf_func)(ctx, (prog)->insnsi);	\
+	}							\
+	ret; })
 
 #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN
 
@@ -764,6 +781,7 @@ void bpf_prog_free_jited_linfo(struct bpf_prog *prog);
 void bpf_prog_free_unused_jited_linfo(struct bpf_prog *prog);
 
 struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags);
+struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags);
 struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 				  gfp_t gfp_extra_flags);
 void __bpf_prog_free(struct bpf_prog *fp);
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 8f0e68e250a7..a8868a32098c 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -245,8 +245,10 @@ extern int _cond_resched(void);
 #endif
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
-  void ___might_sleep(const char *file, int line, int preempt_offset);
-  void __might_sleep(const char *file, int line, int preempt_offset);
+extern void ___might_sleep(const char *file, int line, int preempt_offset);
+extern void __might_sleep(const char *file, int line, int preempt_offset);
+extern void __cant_sleep(const char *file, int line, int preempt_offset);
+
 /**
  * might_sleep - annotation for functions that can sleep
  *
@@ -259,6 +261,13 @@ extern int _cond_resched(void);
  */
 # define might_sleep() \
 	do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
+/**
+ * cant_sleep - annotation for functions that cannot sleep
+ *
+ * this macro will print a stack trace if it is executed with preemption enabled
+ */
+# define cant_sleep() \
+	do { __cant_sleep(__FILE__, __LINE__, 0); } while (0)
 # define sched_annotate_sleep()	(current->task_state_change = 0)
 #else
   static inline void ___might_sleep(const char *file, int line,
@@ -266,6 +275,7 @@ extern int _cond_resched(void);
   static inline void __might_sleep(const char *file, int line,
 				   int preempt_offset) { }
 # define might_sleep() do { might_resched(); } while (0)
+# define cant_sleep() do { } while (0)
 # define sched_annotate_sleep() do { } while (0)
 #endif
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index bcdd2474eee7..3c38ac9a92a7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2359,6 +2359,13 @@ union bpf_attr {
  *	Return
  *		A **struct bpf_tcp_sock** pointer on success, or NULL in
  *		case of failure.
+ *
+ * int bpf_skb_ecn_set_ce(struct sk_buf *skb)
+ *     Description
+ *             Sets ECN of IP header to ce (congestion encountered) if
+ *             current value is ect (ECN capable). Works with IPv6 and IPv4.
+ *     Return
+ *             1 if set, 0 if not set.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2457,7 +2464,8 @@ union bpf_attr {
 	FN(spin_lock),			\
 	FN(spin_unlock),		\
 	FN(sk_fullsock),		\
-	FN(tcp_sock),
+	FN(tcp_sock),			\
+	FN(skb_ecn_set_ce),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2813,6 +2821,8 @@ struct bpf_prog_info {
 	__u32 jited_line_info_rec_size;
 	__u32 nr_prog_tags;
 	__aligned_u64 prog_tags;
+	__u64 run_time_ns;
+	__u64 run_cnt;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {