bpf: avoid grabbing spin_locks of all cpus when no free elems

This patch use head->first in pcpu_freelist_head to check freelist
having free or not. If having, grab spin_lock, or check next cpu's
freelist.

Before patch: hash_map performance
./map_perf_test 1
0:hash_map_perf pre-alloc 1043397 events per sec
...
The average of the test results is around 1050000 events per sec.

hash_map the worst: no free
./run_bench_bpf_hashmap_full_update.sh
Setting up benchmark 'bpf-hashmap-ful-update'...
Benchmark 'bpf-hashmap-ful-update' started.
1:hash_map_full_perf 15687 events per sec
...
The average of the test results is around 16000 events per sec.

ftrace trace:
0) | htab_map_update_elem() {
0) | __pcpu_freelist_pop() {
0) | _raw_spin_lock()
0) | _raw_spin_unlock()
0) | ...
0) + 25.188 us | }
0) + 28.439 us | }

The test machine is 16C, trying to get spin_lock 17 times, in addition
to 16c, there is an extralist.

after patch: hash_map performance
./map_perf_test 1
0:hash_map_perf pre-alloc 1053298 events per sec
...
The average of the test results is around 1050000 events per sec.

hash_map worst: no free
./run_bench_bpf_hashmap_full_update.sh
Setting up benchmark 'bpf-hashmap-ful-update'...
Benchmark 'bpf-hashmap-ful-update' started.
1:hash_map_full_perf 555830 events per sec
...
The average of the test results is around 550000 events per sec.

ftrace trace:
0) | htab_map_update_elem() {
0) | alloc_htab_elem() {
0) 0.586 us | __pcpu_freelist_pop();
0) 0.945 us | }
0) 8.669 us | }

It can be seen that after adding this patch, the map performance is
almost not degraded, and when free=0, first check head->first instead of
directly acquiring spin_lock.

Co-developed-by: Chengming Zhou <[e-mail]>
Signed-off-by: Chengming Zhou <[e-mail]>
Signed-off-by: Feng Zhou <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Alexei Starovoitov <[e-mail]>

kernel/bpf/percpu_freelist.c

···
 					   struct pcpu_freelist_node *node)
 {
 	node->next = head->first;
-	head->first = node;
+	WRITE_ONCE(head->first, node);
 }
 
 static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head,
···
 	orig_cpu = cpu = raw_smp_processor_id();
 	while (1) {
 		head = per_cpu_ptr(s->freelist, cpu);
+		if (!READ_ONCE(head->first))
+			goto next_cpu;
 		raw_spin_lock(&head->lock);
 		node = head->first;
 		if (node) {
-			head->first = node->next;
+			WRITE_ONCE(head->first, node->next);
 			raw_spin_unlock(&head->lock);
 			return node;
 		}
 		raw_spin_unlock(&head->lock);
+next_cpu:
 		cpu = cpumask_next(cpu, cpu_possible_mask);
 		if (cpu >= nr_cpu_ids)
 			cpu = 0;
···
 	}
 
 	/* per cpu lists are all empty, try extralist */
+	if (!READ_ONCE(s->extralist.first))
+		return NULL;
 	raw_spin_lock(&s->extralist.lock);
 	node = s->extralist.first;
 	if (node)
-		s->extralist.first = node->next;
+		WRITE_ONCE(s->extralist.first, node->next);
 	raw_spin_unlock(&s->extralist.lock);
 	return node;
 }
···
 	orig_cpu = cpu = raw_smp_processor_id();
 	while (1) {
 		head = per_cpu_ptr(s->freelist, cpu);
+		if (!READ_ONCE(head->first))
+			goto next_cpu;
 		if (raw_spin_trylock(&head->lock)) {
 			node = head->first;
 			if (node) {
-				head->first = node->next;
+				WRITE_ONCE(head->first, node->next);
 				raw_spin_unlock(&head->lock);
 				return node;
 			}
 			raw_spin_unlock(&head->lock);
 		}
+next_cpu:
 		cpu = cpumask_next(cpu, cpu_possible_mask);
 		if (cpu >= nr_cpu_ids)
 			cpu = 0;
···
 	}
 
 	/* cannot pop from per cpu lists, try extralist */
-	if (!raw_spin_trylock(&s->extralist.lock))
+	if (!READ_ONCE(s->extralist.first) || !raw_spin_trylock(&s->extralist.lock))
 		return NULL;
 	node = s->extralist.first;
 	if (node)
-		s->extralist.first = node->next;
+		WRITE_ONCE(s->extralist.first, node->next);
 	raw_spin_unlock(&s->extralist.lock);
 	return node;
 }