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

1 files changed, 52 insertions, 6 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 1c65ce0098a9..a42097c36b0c 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -14,7 +14,7 @@
 #include "map_in_map.h"
 
 #define ARRAY_CREATE_FLAG_MASK \
-	(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
+	(BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK)
 
 static void bpf_array_free_percpu(struct bpf_array *array)
 {
@@ -59,6 +59,10 @@ int array_map_alloc_check(union bpf_attr *attr)
 	    (percpu && numa_node != NUMA_NO_NODE))
 		return -EINVAL;
 
+	if (attr->map_type != BPF_MAP_TYPE_ARRAY &&
+	    attr->map_flags & BPF_F_MMAPABLE)
+		return -EINVAL;
+
 	if (attr->value_size > KMALLOC_MAX_SIZE)
 		/* if value_size is bigger, the user space won't be able to
 		 * access the elements.
@@ -102,10 +106,19 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	}
 
 	array_size = sizeof(*array);
-	if (percpu)
+	if (percpu) {
 		array_size += (u64) max_entries * sizeof(void *);
-	else
-		array_size += (u64) max_entries * elem_size;
+	} else {
+		/* rely on vmalloc() to return page-aligned memory and
+		 * ensure array->value is exactly page-aligned
+		 */
+		if (attr->map_flags & BPF_F_MMAPABLE) {
+			array_size = PAGE_ALIGN(array_size);
+			array_size += PAGE_ALIGN((u64) max_entries * elem_size);
+		} else {
+			array_size += (u64) max_entries * elem_size;
+		}
+	}
 
 	/* make sure there is no u32 overflow later in round_up() */
 	cost = array_size;
@@ -117,7 +130,20 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(ret);
 
 	/* allocate all map elements and zero-initialize them */
-	array = bpf_map_area_alloc(array_size, numa_node);
+	if (attr->map_flags & BPF_F_MMAPABLE) {
+		void *data;
+
+		/* kmalloc'ed memory can't be mmap'ed, use explicit vmalloc */
+		data = bpf_map_area_mmapable_alloc(array_size, numa_node);
+		if (!data) {
+			bpf_map_charge_finish(&mem);
+			return ERR_PTR(-ENOMEM);
+		}
+		array = data + PAGE_ALIGN(sizeof(struct bpf_array))
+			- offsetof(struct bpf_array, value);
+	} else {
+		array = bpf_map_area_alloc(array_size, numa_node);
+	}
 	if (!array) {
 		bpf_map_charge_finish(&mem);
 		return ERR_PTR(-ENOMEM);
@@ -350,6 +376,11 @@ static int array_map_delete_elem(struct bpf_map *map, void *key)
 	return -EINVAL;
 }
 
+static void *array_map_vmalloc_addr(struct bpf_array *array)
+{
+	return (void *)round_down((unsigned long)array, PAGE_SIZE);
+}
+
 /* Called when map->refcnt goes to zero, either from workqueue or from syscall */
 static void array_map_free(struct bpf_map *map)
 {
@@ -365,7 +396,10 @@ static void array_map_free(struct bpf_map *map)
 	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
 		bpf_array_free_percpu(array);
 
-	bpf_map_area_free(array);
+	if (array->map.map_flags & BPF_F_MMAPABLE)
+		bpf_map_area_free(array_map_vmalloc_addr(array));
+	else
+		bpf_map_area_free(array);
 }
 
 static void array_map_seq_show_elem(struct bpf_map *map, void *key,
@@ -444,6 +478,17 @@ static int array_map_check_btf(const struct bpf_map *map,
 	return 0;
 }
 
+int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	pgoff_t pgoff = PAGE_ALIGN(sizeof(*array)) >> PAGE_SHIFT;
+
+	if (!(map->map_flags & BPF_F_MMAPABLE))
+		return -EINVAL;
+
+	return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), pgoff);
+}
+
 const struct bpf_map_ops array_map_ops = {
 	.map_alloc_check = array_map_alloc_check,
 	.map_alloc = array_map_alloc,
@@ -455,6 +500,7 @@ const struct bpf_map_ops array_map_ops = {
 	.map_gen_lookup = array_map_gen_lookup,
 	.map_direct_value_addr = array_map_direct_value_addr,
 	.map_direct_value_meta = array_map_direct_value_meta,
+	.map_mmap = array_map_mmap,
 	.map_seq_show_elem = array_map_seq_show_elem,
 	.map_check_btf = array_map_check_btf,
 };