bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY

Add ability to memory-map contents of BPF array map. This is extremely useful
for working with BPF global data from userspace programs. It allows to avoid
typical bpf_map_{lookup,update}_elem operations, improving both performance
and usability.

There had to be special considerations for map freezing, to avoid having
writable memory view into a frozen map. To solve this issue, map freezing and
mmap-ing is happening under mutex now:
  - if map is already frozen, no writable mapping is allowed;
  - if map has writable memory mappings active (accounted in map->writecnt),
    map freezing will keep failing with -EBUSY;
  - once number of writable memory mappings drops to zero, map freezing can be
    performed again.

Only non-per-CPU plain arrays are supported right now. Maps with spinlocks
can't be memory mapped either.

For BPF_F_MMAPABLE array, memory allocation has to be done through vmalloc()
to be mmap()'able. We also need to make sure that array data memory is
page-sized and page-aligned, so we over-allocate memory in such a way that
struct bpf_array is at the end of a single page of memory with array->value
being aligned with the start of the second page. On deallocation we need to
accomodate this memory arrangement to free vmalloc()'ed memory correctly.

One important consideration regarding how memory-mapping subsystem functions.
Memory-mapping subsystem provides few optional callbacks, among them open()
and close().  close() is called for each memory region that is unmapped, so
that users can decrease their reference counters and free up resources, if
necessary. open() is *almost* symmetrical: it's called for each memory region
that is being mapped, **except** the very first one. So bpf_map_mmap does
initial refcnt bump, while open() will do any extra ones after that. Thus
number of close() calls is equal to number of open() calls plus one more.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lore.kernel.org/bpf/20191117172806.2195367-4-andriin@fb.com

3 files changed, 12 insertions, 3 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index fb606dc61a3a..e913dd5946ae 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -12,6 +12,7 @@
 #include <linux/err.h>
 #include <linux/rbtree_latch.h>
 #include <linux/numa.h>
+#include <linux/mm_types.h>
 #include <linux/wait.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/refcount.h>
@@ -68,6 +69,7 @@ struct bpf_map_ops {
 				     u64 *imm, u32 off);
 	int (*map_direct_value_meta)(const struct bpf_map *map,
 				     u64 imm, u32 *off);
+	int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma);
 };
 
 struct bpf_map_memory {
@@ -96,9 +98,10 @@ struct bpf_map {
 	u32 btf_value_type_id;
 	struct btf *btf;
 	struct bpf_map_memory memory;
+	char name[BPF_OBJ_NAME_LEN];
 	bool unpriv_array;
-	bool frozen; /* write-once */
-	/* 48 bytes hole */
+	bool frozen; /* write-once; write-protected by freeze_mutex */
+	/* 22 bytes hole */
 
 	/* The 3rd and 4th cacheline with misc members to avoid false sharing
 	 * particularly with refcounting.
@@ -106,7 +109,8 @@ struct bpf_map {
 	atomic64_t refcnt ____cacheline_aligned;
 	atomic64_t usercnt;
 	struct work_struct work;
-	char name[BPF_OBJ_NAME_LEN];
+	struct mutex freeze_mutex;
+	u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */
 };
 
 static inline bool map_value_has_spin_lock(const struct bpf_map *map)
@@ -795,6 +799,7 @@ void bpf_map_charge_finish(struct bpf_map_memory *mem);
 void bpf_map_charge_move(struct bpf_map_memory *dst,
 			 struct bpf_map_memory *src);
 void *bpf_map_area_alloc(size_t size, int numa_node);
+void *bpf_map_area_mmapable_alloc(size_t size, int numa_node);
 void bpf_map_area_free(void *base);
 void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
 
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 4e7809408073..b4c58a191eb1 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -93,6 +93,7 @@ extern void *vzalloc(unsigned long size);
 extern void *vmalloc_user(unsigned long size);
 extern void *vmalloc_node(unsigned long size, int node);
 extern void *vzalloc_node(unsigned long size, int node);
+extern void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags);
 extern void *vmalloc_exec(unsigned long size);
 extern void *vmalloc_32(unsigned long size);
 extern void *vmalloc_32_user(unsigned long size);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4842a134b202..dbbcf0b02970 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -348,6 +348,9 @@ enum bpf_attach_type {
 /* Clone map from listener for newly accepted socket */
 #define BPF_F_CLONE		(1U << 9)
 
+/* Enable memory-mapping BPF map */
+#define BPF_F_MMAPABLE		(1U << 10)
+
 /* flags for BPF_PROG_QUERY */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)