bpf: rework memlock-based memory accounting for maps

In order to unify the existing memlock charging code with the
memcg-based memory accounting, which will be added later, let's
rework the current scheme.

Currently the following design is used:
  1) .alloc() callback optionally checks if the allocation will likely
     succeed using bpf_map_precharge_memlock()
  2) .alloc() performs actual allocations
  3) .alloc() callback calculates map cost and sets map.memory.pages
  4) map_create() calls bpf_map_init_memlock() which sets map.memory.user
     and performs actual charging; in case of failure the map is
     destroyed
  <map is in use>
  1) bpf_map_free_deferred() calls bpf_map_release_memlock(), which
     performs uncharge and releases the user
  2) .map_free() callback releases the memory

The scheme can be simplified and made more robust:
  1) .alloc() calculates map cost and calls bpf_map_charge_init()
  2) bpf_map_charge_init() sets map.memory.user and performs actual
    charge
  3) .alloc() performs actual allocations
  <map is in use>
  1) .map_free() callback releases the memory
  2) bpf_map_charge_finish() performs uncharge and releases the user

The new scheme also allows to reuse bpf_map_charge_init()/finish()
functions for memcg-based accounting. Because charges are performed
before actual allocations and uncharges after freeing the memory,
no bogus memory pressure can be created.

In cases when the map structure is not available (e.g. it's not
created yet, or is already destroyed), on-stack bpf_map_memory
structure is used. The charge can be transferred with the
bpf_map_charge_move() function.

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 17 insertions, 13 deletions

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 08d4efff73ac..8da24ca65d97 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -89,6 +89,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 {
 	u32 value_size = attr->value_size;
 	struct bpf_stack_map *smap;
+	struct bpf_map_memory mem;
 	u64 cost, n_buckets;
 	int err;
 
@@ -118,38 +119,41 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap);
 	if (cost >= U32_MAX - PAGE_SIZE)
 		return ERR_PTR(-E2BIG);
+	cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
+	if (cost >= U32_MAX - PAGE_SIZE)
+		return ERR_PTR(-E2BIG);
+
+	err = bpf_map_charge_init(&mem,
+				  round_up(cost, PAGE_SIZE) >> PAGE_SHIFT);
+	if (err)
+		return ERR_PTR(err);
 
 	smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr));
-	if (!smap)
+	if (!smap) {
+		bpf_map_charge_finish(&mem);
 		return ERR_PTR(-ENOMEM);
-
-	err = -E2BIG;
-	cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
-	if (cost >= U32_MAX - PAGE_SIZE)
-		goto free_smap;
+	}
 
 	bpf_map_init_from_attr(&smap->map, attr);
 	smap->map.value_size = value_size;
 	smap->n_buckets = n_buckets;
-	smap->map.memory.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
-
-	err = bpf_map_precharge_memlock(smap->map.memory.pages);
-	if (err)
-		goto free_smap;
 
 	err = get_callchain_buffers(sysctl_perf_event_max_stack);
 	if (err)
-		goto free_smap;
+		goto free_charge;
 
 	err = prealloc_elems_and_freelist(smap);
 	if (err)
 		goto put_buffers;
 
+	bpf_map_charge_move(&smap->map.memory, &mem);
+
 	return &smap->map;
 
 put_buffers:
 	put_callchain_buffers();
-free_smap:
+free_charge:
+	bpf_map_charge_finish(&mem);
 	bpf_map_area_free(smap);
 	return ERR_PTR(err);
 }