Merge branch 'bpf-fix-the-release-of-inner-map'

Hou Tao says:

====================
bpf: Fix the release of inner map

From: Hou Tao <houtao1@huawei.com>

Hi,

The patchset aims to fix the release of inner map in map array or map
htab. The release of inner map is different with normal map. For normal
map, the map is released after the bpf program which uses the map is
destroyed, because the bpf program tracks the used maps. However bpf
program can not track the used inner map because these inner map may be
updated or deleted dynamically, and for now the ref-counter of inner map
is decreased after the inner map is remove from outer map, so the inner
map may be freed before the bpf program, which is accessing the inner
map, exits and there will be use-after-free problem as demonstrated by
patch #6.

The patchset fixes the problem by deferring the release of inner map.
The freeing of inner map is deferred according to the sleepable
attributes of the bpf programs which own the outer map. Patch #1 fixes
the warning when running the newly-added selftest under interpreter
mode. Patch #2 adds more parameters to .map_fd_put_ptr() to prepare for
the fix. Patch #3 fixes the incorrect value of need_defer when freeing
the fd array. Patch #4 fixes the potential use-after-free problem by
using call_rcu_tasks_trace() and call_rcu() to wait for one tasks trace
RCU GP and one RCU GP unconditionally. Patch #5 optimizes the free of
inner map by removing the unnecessary RCU GP waiting. Patch #6 adds a
selftest to demonstrate the potential use-after-free problem. Patch #7
updates a selftest to update outer map in syscall bpf program.

Please see individual patches for more details. And comments are always
welcome.

Change Log:
v5:
 * patch #3: rename fd_array_map_delete_elem_with_deferred_free() to
             __fd_array_map_delete_elem() (Alexei)
 * patch #5: use atomic64_t instead of atomic_t to prevent potential
             overflow (Alexei)
 * patch #7: use ptr_to_u64() helper instead of force casting to initialize
             pointers in bpf_attr (Alexei)

v4: https://lore.kernel.org/bpf/20231130140120.1736235-1-houtao@huaweicloud.com
  * patch #2: don't use "deferred", use "need_defer" uniformly
  * patch #3: newly-added, fix the incorrect value of need_defer during
              fd array free.
  * patch #4: doesn't consider the case in which bpf map is not used by
              any bpf program and only use sleepable_refcnt to remove
	      unnecessary tasks trace RCU GP (Alexei)
  * patch #4: remove memory barriers added due to cautiousness (Alexei)

v3: https://lore.kernel.org/bpf/20231124113033.503338-1-houtao@huaweicloud.com
  * multiple variable renamings (Martin)
  * define BPF_MAP_RCU_GP/BPF_MAP_RCU_TT_GP as bit (Martin)
  * use call_rcu() and its variants instead of synchronize_rcu() (Martin)
  * remove unnecessary mask in bpf_map_free_deferred() (Martin)
  * place atomic_or() and the related smp_mb() together (Martin)
  * add patch #6 to demonstrate that updating outer map in syscall
    program is dead-lock free (Alexei)
  * update comments about the memory barrier in bpf_map_fd_put_ptr()
  * update commit message for patch #3 and #4 to describe more details

v2: https://lore.kernel.org/bpf/20231113123324.3914612-1-houtao@huaweicloud.com
  * defer the invocation of ops->map_free() instead of bpf_map_put() (Martin)
  * update selftest to make it being reproducible under JIT mode (Martin)
  * remove unnecessary preparatory patches

v1: https://lore.kernel.org/bpf/20231107140702.1891778-1-houtao@huaweicloud.com
====================

Link: https://lore.kernel.org/r/20231204140425.1480317-1-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 20 insertions, 13 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 2058e89b5ddd..4a4a67956e21 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -867,11 +867,11 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
 	}
 
 	if (old_ptr)
-		map->ops->map_fd_put_ptr(old_ptr);
+		map->ops->map_fd_put_ptr(map, old_ptr, true);
 	return 0;
 }
 
-static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
+static long __fd_array_map_delete_elem(struct bpf_map *map, void *key, bool need_defer)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	void *old_ptr;
@@ -890,13 +890,18 @@ static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
 	}
 
 	if (old_ptr) {
-		map->ops->map_fd_put_ptr(old_ptr);
+		map->ops->map_fd_put_ptr(map, old_ptr, need_defer);
 		return 0;
 	} else {
 		return -ENOENT;
 	}
 }
 
+static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
+{
+	return __fd_array_map_delete_elem(map, key, true);
+}
+
 static void *prog_fd_array_get_ptr(struct bpf_map *map,
 				   struct file *map_file, int fd)
 {
@@ -913,8 +918,9 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map,
 	return prog;
 }
 
-static void prog_fd_array_put_ptr(void *ptr)
+static void prog_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
+	/* bpf_prog is freed after one RCU or tasks trace grace period */
 	bpf_prog_put(ptr);
 }
 
@@ -924,13 +930,13 @@ static u32 prog_fd_array_sys_lookup_elem(void *ptr)
 }
 
 /* decrement refcnt of all bpf_progs that are stored in this map */
-static void bpf_fd_array_map_clear(struct bpf_map *map)
+static void bpf_fd_array_map_clear(struct bpf_map *map, bool need_defer)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
 
 	for (i = 0; i < array->map.max_entries; i++)
-		fd_array_map_delete_elem(map, &i);
+		__fd_array_map_delete_elem(map, &i, need_defer);
 }
 
 static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key,
@@ -1109,7 +1115,7 @@ static void prog_array_map_clear_deferred(struct work_struct *work)
 {
 	struct bpf_map *map = container_of(work, struct bpf_array_aux,
 					   work)->map;
-	bpf_fd_array_map_clear(map);
+	bpf_fd_array_map_clear(map, true);
 	bpf_map_put(map);
 }
 
@@ -1239,8 +1245,9 @@ err_out:
 	return ee;
 }
 
-static void perf_event_fd_array_put_ptr(void *ptr)
+static void perf_event_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
+	/* bpf_perf_event is freed after one RCU grace period */
 	bpf_event_entry_free_rcu(ptr);
 }
 
@@ -1258,7 +1265,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 	for (i = 0; i < array->map.max_entries; i++) {
 		ee = READ_ONCE(array->ptrs[i]);
 		if (ee && ee->map_file == map_file)
-			fd_array_map_delete_elem(map, &i);
+			__fd_array_map_delete_elem(map, &i, true);
 	}
 	rcu_read_unlock();
 }
@@ -1266,7 +1273,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 static void perf_event_fd_array_map_free(struct bpf_map *map)
 {
 	if (map->map_flags & BPF_F_PRESERVE_ELEMS)
-		bpf_fd_array_map_clear(map);
+		bpf_fd_array_map_clear(map, false);
 	fd_array_map_free(map);
 }
 
@@ -1294,7 +1301,7 @@ static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
 	return cgroup_get_from_fd(fd);
 }
 
-static void cgroup_fd_array_put_ptr(void *ptr)
+static void cgroup_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
 	/* cgroup_put free cgrp after a rcu grace period */
 	cgroup_put(ptr);
@@ -1302,7 +1309,7 @@ static void cgroup_fd_array_put_ptr(void *ptr)
 
 static void cgroup_fd_array_free(struct bpf_map *map)
 {
-	bpf_fd_array_map_clear(map);
+	bpf_fd_array_map_clear(map, false);
 	fd_array_map_free(map);
 }
 
@@ -1347,7 +1354,7 @@ static void array_of_map_free(struct bpf_map *map)
 	 * is protected by fdget/fdput.
 	 */
 	bpf_map_meta_free(map->inner_map_meta);
-	bpf_fd_array_map_clear(map);
+	bpf_fd_array_map_clear(map, false);
 	fd_array_map_free(map);
 }