[PATCH v3 bpf-next 2/8] bpf: Compute program stats for sleepable programs

[Alexei Starovoitov <alexei.starovoitov@gmail.com>]

From: Alexei Starovoitov <ast@kernel.org>

In older non-RT kernels migrate_disable() was the same as preempt_disable().
Since commit 74d862b682f5 ("sched: Make migrate_disable/enable() independent of RT")
migrate_disable() is real and doesn't prevent sleeping.
Use it to efficiently compute execution stats for sleepable bpf programs.
migrate_disable() will also be used to enable per-cpu maps in sleepable programs
in the future patches.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c | 31 ++++++++++----------------
 include/linux/bpf.h         |  4 ++--
 kernel/bpf/trampoline.c     | 44 +++++++++++++++++++++++++------------
 3 files changed, 44 insertions(+), 35 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index a3dc3bd154ac..d11b9bcebbea 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1742,15 +1742,12 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	u8 *prog = *pprog;
 	int cnt = 0;
 
-	if (p->aux->sleepable) {
-		if (emit_call(&prog, __bpf_prog_enter_sleepable, prog))
+	if (emit_call(&prog,
+		      p->aux->sleepable ? __bpf_prog_enter_sleepable :
+		      __bpf_prog_enter, prog))
 			return -EINVAL;
-	} else {
-		if (emit_call(&prog, __bpf_prog_enter, prog))
-			return -EINVAL;
-		/* remember prog start time returned by __bpf_prog_enter */
-		emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
-	}
+	/* remember prog start time returned by __bpf_prog_enter */
+	emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
 
 	/* arg1: lea rdi, [rbp - stack_size] */
 	EMIT4(0x48, 0x8D, 0x7D, -stack_size);
@@ -1770,18 +1767,14 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	if (mod_ret)
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
 
-	if (p->aux->sleepable) {
-		if (emit_call(&prog, __bpf_prog_exit_sleepable, prog))
+	/* arg1: mov rdi, progs[i] */
+	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
+	/* arg2: mov rsi, rbx <- start time in nsec */
+	emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
+	if (emit_call(&prog,
+		      p->aux->sleepable ? __bpf_prog_exit_sleepable :
+		      __bpf_prog_exit, prog))
 			return -EINVAL;
-	} else {
-		/* arg1: mov rdi, progs[i] */
-		emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32,
-			       (u32) (long) p);
-		/* arg2: mov rsi, rbx <- start time in nsec */
-		emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
-		if (emit_call(&prog, __bpf_prog_exit, prog))
-			return -EINVAL;
-	}
 
 	*pprog = prog;
 	return 0;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 026fa8873c5d..2fa48439ef31 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -563,8 +563,8 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
 /* these two functions are called from generated trampoline */
 u64 notrace __bpf_prog_enter(void);
 void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
-void notrace __bpf_prog_enter_sleepable(void);
-void notrace __bpf_prog_exit_sleepable(void);
+u64 notrace __bpf_prog_enter_sleepable(void);
+void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start);
 
 struct bpf_ksym {
 	unsigned long		 start;
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 5be3beeedd74..48eb021e1421 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -381,55 +381,71 @@ void bpf_trampoline_put(struct bpf_trampoline *tr)
 	mutex_unlock(&trampoline_mutex);
 }
 
+#define NO_START_TIME 0
+static u64 notrace bpf_prog_start_time(void)
+{
+	u64 start = NO_START_TIME;
+
+	if (static_branch_unlikely(&bpf_stats_enabled_key))
+		start = sched_clock();
+	return start;
+}
+
 /* The logic is similar to BPF_PROG_RUN, but with an explicit
  * rcu_read_lock() and migrate_disable() which are required
  * for the trampoline. The macro is split into
- * call _bpf_prog_enter
+ * call __bpf_prog_enter
  * call prog->bpf_func
  * call __bpf_prog_exit
  */
 u64 notrace __bpf_prog_enter(void)
 	__acquires(RCU)
 {
-	u64 start = 0;
-
 	rcu_read_lock();
 	migrate_disable();
-	if (static_branch_unlikely(&bpf_stats_enabled_key))
-		start = sched_clock();
-	return start;
+	return bpf_prog_start_time();
 }
 
-void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start)
-	__releases(RCU)
+static void notrace update_prog_stats(struct bpf_prog *prog,
+				      u64 start)
 {
 	struct bpf_prog_stats *stats;
 
 	if (static_branch_unlikely(&bpf_stats_enabled_key) &&
-	    /* static_key could be enabled in __bpf_prog_enter
-	     * and disabled in __bpf_prog_exit.
+	    /* static_key could be enabled in __bpf_prog_enter*
+	     * and disabled in __bpf_prog_exit*.
 	     * And vice versa.
-	     * Hence check that 'start' is not zero.
+	     * Hence check that 'start' is valid.
 	     */
-	    start) {
+	    start > NO_START_TIME) {
 		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);
 	}
+}
+
+void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start)
+	__releases(RCU)
+{
+	update_prog_stats(prog, start);
 	migrate_enable();
 	rcu_read_unlock();
 }
 
-void notrace __bpf_prog_enter_sleepable(void)
+u64 notrace __bpf_prog_enter_sleepable(void)
 {
 	rcu_read_lock_trace();
+	migrate_disable();
 	might_fault();
+	return bpf_prog_start_time();
 }
 
-void notrace __bpf_prog_exit_sleepable(void)
+void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start)
 {
+	update_prog_stats(prog, start);
+	migrate_enable();
 	rcu_read_unlock_trace();
 }
 
-- 
2.24.1