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, 96 insertions, 3 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 52fe4bacb330..bac3becf9f90 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -127,7 +127,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 	return map;
 }
 
-void *bpf_map_area_alloc(size_t size, int numa_node)
+static void *__bpf_map_area_alloc(size_t size, int numa_node, bool mmapable)
 {
 	/* We really just want to fail instead of triggering OOM killer
 	 * under memory pressure, therefore we set __GFP_NORETRY to kmalloc,
@@ -142,18 +142,33 @@ void *bpf_map_area_alloc(size_t size, int numa_node)
 	const gfp_t flags = __GFP_NOWARN | __GFP_ZERO;
 	void *area;
 
-	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
+	/* kmalloc()'ed memory can't be mmap()'ed */
+	if (!mmapable && size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
 		area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags,
 				    numa_node);
 		if (area != NULL)
 			return area;
 	}
-
+	if (mmapable) {
+		BUG_ON(!PAGE_ALIGNED(size));
+		return vmalloc_user_node_flags(size, numa_node, GFP_KERNEL |
+					       __GFP_RETRY_MAYFAIL | flags);
+	}
 	return __vmalloc_node_flags_caller(size, numa_node,
 					   GFP_KERNEL | __GFP_RETRY_MAYFAIL |
 					   flags, __builtin_return_address(0));
 }
 
+void *bpf_map_area_alloc(size_t size, int numa_node)
+{
+	return __bpf_map_area_alloc(size, numa_node, false);
+}
+
+void *bpf_map_area_mmapable_alloc(size_t size, int numa_node)
+{
+	return __bpf_map_area_alloc(size, numa_node, true);
+}
+
 void bpf_map_area_free(void *area)
 {
 	kvfree(area);
@@ -425,6 +440,74 @@ static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf,
 	return -EINVAL;
 }
 
+/* called for any extra memory-mapped regions (except initial) */
+static void bpf_map_mmap_open(struct vm_area_struct *vma)
+{
+	struct bpf_map *map = vma->vm_file->private_data;
+
+	bpf_map_inc_with_uref(map);
+
+	if (vma->vm_flags & VM_WRITE) {
+		mutex_lock(&map->freeze_mutex);
+		map->writecnt++;
+		mutex_unlock(&map->freeze_mutex);
+	}
+}
+
+/* called for all unmapped memory region (including initial) */
+static void bpf_map_mmap_close(struct vm_area_struct *vma)
+{
+	struct bpf_map *map = vma->vm_file->private_data;
+
+	if (vma->vm_flags & VM_WRITE) {
+		mutex_lock(&map->freeze_mutex);
+		map->writecnt--;
+		mutex_unlock(&map->freeze_mutex);
+	}
+
+	bpf_map_put_with_uref(map);
+}
+
+static const struct vm_operations_struct bpf_map_default_vmops = {
+	.open		= bpf_map_mmap_open,
+	.close		= bpf_map_mmap_close,
+};
+
+static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct bpf_map *map = filp->private_data;
+	int err;
+
+	if (!map->ops->map_mmap || map_value_has_spin_lock(map))
+		return -ENOTSUPP;
+
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+
+	mutex_lock(&map->freeze_mutex);
+
+	if ((vma->vm_flags & VM_WRITE) && map->frozen) {
+		err = -EPERM;
+		goto out;
+	}
+
+	/* set default open/close callbacks */
+	vma->vm_ops = &bpf_map_default_vmops;
+	vma->vm_private_data = map;
+
+	err = map->ops->map_mmap(map, vma);
+	if (err)
+		goto out;
+
+	bpf_map_inc_with_uref(map);
+
+	if (vma->vm_flags & VM_WRITE)
+		map->writecnt++;
+out:
+	mutex_unlock(&map->freeze_mutex);
+	return err;
+}
+
 const struct file_operations bpf_map_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo	= bpf_map_show_fdinfo,
@@ -432,6 +515,7 @@ const struct file_operations bpf_map_fops = {
 	.release	= bpf_map_release,
 	.read		= bpf_dummy_read,
 	.write		= bpf_dummy_write,
+	.mmap		= bpf_map_mmap,
 };
 
 int bpf_map_new_fd(struct bpf_map *map, int flags)
@@ -577,6 +661,7 @@ static int map_create(union bpf_attr *attr)
 
 	atomic64_set(&map->refcnt, 1);
 	atomic64_set(&map->usercnt, 1);
+	mutex_init(&map->freeze_mutex);
 
 	if (attr->btf_key_type_id || attr->btf_value_type_id) {
 		struct btf *btf;
@@ -1163,6 +1248,13 @@ static int map_freeze(const union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+
+	mutex_lock(&map->freeze_mutex);
+
+	if (map->writecnt) {
+		err = -EBUSY;
+		goto err_put;
+	}
 	if (READ_ONCE(map->frozen)) {
 		err = -EBUSY;
 		goto err_put;
@@ -1174,6 +1266,7 @@ static int map_freeze(const union bpf_attr *attr)
 
 	WRITE_ONCE(map->frozen, true);
 err_put:
+	mutex_unlock(&map->freeze_mutex);
 	fdput(f);
 	return err;
 }