bpf: Non-atomically allocate freelist during prefill

In internal testing of test_maps, we sometimes observed failures like:
  test_maps: test_maps.c:173: void test_hashmap_percpu(unsigned int, void *):
    Assertion `bpf_map_update_elem(fd, &key, value, BPF_ANY) == 0' failed.
where the errno is ENOMEM. After some troubleshooting and enabling
the warnings, we saw:
  [   91.304708] percpu: allocation failed, size=8 align=8 atomic=1, atomic alloc failed, no space left
  [   91.304716] CPU: 51 PID: 24145 Comm: test_maps Kdump: loaded Tainted: G                 N 6.1.38-smp-DEV #7
  [   91.304719] Hardware name: Google Astoria/astoria, BIOS 0.20230627.0-0 06/27/2023
  [   91.304721] Call Trace:
  [   91.304724]  <TASK>
  [   91.304730]  [<ffffffffa7ef83b9>] dump_stack_lvl+0x59/0x88
  [   91.304737]  [<ffffffffa7ef83f8>] dump_stack+0x10/0x18
  [   91.304738]  [<ffffffffa75caa0c>] pcpu_alloc+0x6fc/0x870
  [   91.304741]  [<ffffffffa75ca302>] __alloc_percpu_gfp+0x12/0x20
  [   91.304743]  [<ffffffffa756785e>] alloc_bulk+0xde/0x1e0
  [   91.304746]  [<ffffffffa7566c02>] bpf_mem_alloc_init+0xd2/0x2f0
  [   91.304747]  [<ffffffffa7547c69>] htab_map_alloc+0x479/0x650
  [   91.304750]  [<ffffffffa751d6e0>] map_create+0x140/0x2e0
  [   91.304752]  [<ffffffffa751d413>] __sys_bpf+0x5a3/0x6c0
  [   91.304753]  [<ffffffffa751c3ec>] __x64_sys_bpf+0x1c/0x30
  [   91.304754]  [<ffffffffa7ef847a>] do_syscall_64+0x5a/0x80
  [   91.304756]  [<ffffffffa800009b>] entry_SYSCALL_64_after_hwframe+0x63/0xcd

This makes sense, because in atomic context, percpu allocation would
not create new chunks; it would only create in non-atomic contexts.
And if during prefill all precpu chunks are full, -ENOMEM would
happen immediately upon next unit_alloc.

Prefill phase does not actually run in atomic context, so we can
use this fact to allocate non-atomically with GFP_KERNEL instead
of GFP_NOWAIT. This avoids the immediate -ENOMEM.

GFP_NOWAIT has to be used in unit_alloc when bpf program runs
in atomic context. Even if bpf program runs in non-atomic context,
in most cases, rcu read lock is enabled for the program so
GFP_NOWAIT is still needed. This is often also the case for
BPF_MAP_UPDATE_ELEM syscalls.

Signed-off-by: YiFei Zhu <zhuyifei@google.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20230728043359.3324347-1-zhuyifei@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 8 insertions, 4 deletions

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 14d9b1a9a4ca..9c49ae53deaf 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -201,12 +201,16 @@ static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj)
 }
 
 /* Mostly runs from irq_work except __init phase. */
-static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
+static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node, bool atomic)
 {
 	struct mem_cgroup *memcg = NULL, *old_memcg;
+	gfp_t gfp;
 	void *obj;
 	int i;
 
+	gfp = __GFP_NOWARN | __GFP_ACCOUNT;
+	gfp |= atomic ? GFP_NOWAIT : GFP_KERNEL;
+
 	for (i = 0; i < cnt; i++) {
 		/*
 		 * For every 'c' llist_del_first(&c->free_by_rcu_ttrace); is
@@ -238,7 +242,7 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
 		 * will allocate from the current numa node which is what we
 		 * want here.
 		 */
-		obj = __alloc(c, node, GFP_NOWAIT | __GFP_NOWARN | __GFP_ACCOUNT);
+		obj = __alloc(c, node, gfp);
 		if (!obj)
 			break;
 		add_obj_to_free_list(c, obj);
@@ -429,7 +433,7 @@ static void bpf_mem_refill(struct irq_work *work)
 		/* irq_work runs on this cpu and kmalloc will allocate
 		 * from the current numa node which is what we want here.
 		 */
-		alloc_bulk(c, c->batch, NUMA_NO_NODE);
+		alloc_bulk(c, c->batch, NUMA_NO_NODE, true);
 	else if (cnt > c->high_watermark)
 		free_bulk(c);
 
@@ -477,7 +481,7 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
 	 * prog won't be doing more than 4 map_update_elem from
 	 * irq disabled region
 	 */
-	alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu));
+	alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu), false);
 }
 
 /* When size != 0 bpf_mem_cache for each cpu.