[PATCH v2 bpf-next 0/3] Add support for memory-mapping BPF array maps

[PATCH v2 bpf-next 0/3] Add support for memory-mapping BPF array maps

[Andrii Nakryiko]

This patch set adds ability to memory-map BPF array maps (single- and
multi-element). The primary use case is memory-mapping BPF array maps, created
to back global data variables, created by libbpf implicitly. This allows for
much better usability, along with avoiding syscalls to read or update data
completely.

Due to memory-mapping requirements, BPF array map that is supposed to be
memory-mapped, has to be created with special BPF_F_MMAPABLE attribute, which
triggers slightly different memory allocation strategy internally. See
patch 1 for details.

Libbpf is extended to detect kernel support for this flag, and if supported,
will specify it for all global data maps automatically.

v1->v2:
- fix map lookup code generation for BPF_F_MMAPABLE case;
- prevent BPF_F_MMAPABLE flag for all but plain array map type;
- centralize ref-counting in generic bpf_map_mmap();
- don't use uref counting (Alexei);
- use vfree() directly;
- print flags with %x (Song);
- extend tests to verify bpf_map_{lookup,update}_elem() logic as well.

Andrii Nakryiko (3):
  bpf: add mmap() support for BPF_MAP_TYPE_ARRAY
  libbpf: make global data internal arrays mmap()-able, if possible
  selftests/bpf: add BPF_TYPE_MAP_ARRAY mmap() tests

 include/linux/bpf.h                           |   9 +-
 include/uapi/linux/bpf.h                      |   3 +
 kernel/bpf/arraymap.c                         | 111 ++++++++++--
 kernel/bpf/syscall.c                          |  47 +++++
 tools/include/uapi/linux/bpf.h                |   3 +
 tools/lib/bpf/libbpf.c                        |  31 +++-
 .../selftests/bpf/prog_tests/core_reloc.c     |  45 +++--
 tools/testing/selftests/bpf/prog_tests/mmap.c | 170 ++++++++++++++++++
 tools/testing/selftests/bpf/progs/test_mmap.c |  41 +++++
 9 files changed, 426 insertions(+), 34 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/mmap.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_mmap.c

-- 
2.17.1

[PATCH v2 bpf-next 1/3] bpf: add mmap() support for BPF_MAP_TYPE_ARRAY

[Andrii Nakryiko]

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.

With BPF_F_MMAPABLE array allocating data in separate chunk of memory,
array_map_gen_lookup has to accomodate these changes. For non-memory-mapped
there are no changes and no extra instructions. For BPF_F_MMAPABLE case,
pointer to where array data is stored has to be dereferenced first.

Generated code for non-memory-mapped array:

; p = bpf_map_lookup_elem(&data_map, &zero);
  22: (18) r1 = map[id:19]
  24: (07) r1 += 408			/* array->inline_data offset */
  25: (61) r0 = *(u32 *)(r2 +0)
  26: (35) if r0 >= 0x3 goto pc+3
  27: (67) r0 <<= 3
  28: (0f) r0 += r1
  29: (05) goto pc+1
  30: (b7) r0 = 0

Generated code for memory-mapped array:

; p = bpf_map_lookup_elem(&data_map, &zero);
  22: (18) r1 = map[id:27]
  24: (07) r1 += 400			/* array->data offset */
  25: (79) r1 = *(u64 *)(r1 +0)		/* extra dereference */
  26: (61) r0 = *(u32 *)(r2 +0)
  27: (35) if r0 >= 0x3 goto pc+3
  28: (67) r0 <<= 3
  29: (0f) r0 += r1
  30: (05) goto pc+1
  31: (b7) r0 = 0

Cc: Rik van Riel <riel@surriel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
---
 include/linux/bpf.h            |   9 ++-
 include/uapi/linux/bpf.h       |   3 +
 kernel/bpf/arraymap.c          | 111 +++++++++++++++++++++++++++++----
 kernel/bpf/syscall.c           |  47 ++++++++++++++
 tools/include/uapi/linux/bpf.h |   3 +
 5 files changed, 159 insertions(+), 14 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7c7f518811a6..296332227959 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>
 
@@ -66,6 +67,7 @@ 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 {
@@ -95,7 +97,7 @@ struct bpf_map {
 	struct btf *btf;
 	struct bpf_map_memory memory;
 	bool unpriv_array;
-	bool frozen; /* write-once */
+	bool frozen; /* write-once; write-protected by freeze_mutex */
 	/* 48 bytes hole */
 
 	/* The 3rd and 4th cacheline with misc members to avoid false sharing
@@ -105,6 +107,8 @@ struct bpf_map {
 	atomic_t usercnt;
 	struct work_struct work;
 	char name[BPF_OBJ_NAME_LEN];
+	struct mutex freeze_mutex;
+	int writecnt; /* writable mmap cnt; protected by freeze_mutex */
 };
 
 static inline bool map_value_has_spin_lock(const struct bpf_map *map)
@@ -461,8 +465,9 @@ struct bpf_array {
 	 */
 	enum bpf_prog_type owner_prog_type;
 	bool owner_jited;
+	void *data;
 	union {
-		char value[0] __aligned(8);
+		char inline_data[0] __aligned(8);
 		void *ptrs[0] __aligned(8);
 		void __percpu *pptrs[0] __aligned(8);
 	};
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index df6809a76404..bb39b53622d9 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -346,6 +346,9 @@ 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)
 
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 1c65ce0098a9..275973b68bdd 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.
@@ -74,7 +78,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	int ret, numa_node = bpf_map_attr_numa_node(attr);
 	u32 elem_size, index_mask, max_entries;
 	bool unpriv = !capable(CAP_SYS_ADMIN);
-	u64 cost, array_size, mask64;
+	u64 cost, array_size, data_size, mask64;
 	struct bpf_map_memory mem;
 	struct bpf_array *array;
 
@@ -102,13 +106,20 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	}
 
 	array_size = sizeof(*array);
-	if (percpu)
+	data_size = 0;
+	if (percpu) {
 		array_size += (u64) max_entries * sizeof(void *);
-	else
-		array_size += (u64) max_entries * elem_size;
+	} else {
+		if (attr->map_flags & BPF_F_MMAPABLE) {
+			data_size = (u64) max_entries * elem_size;
+			data_size = round_up(data_size, PAGE_SIZE);
+		} else {
+			array_size += (u64) max_entries * elem_size;
+		}
+	}
 
 	/* make sure there is no u32 overflow later in round_up() */
-	cost = array_size;
+	cost = array_size + data_size;
 	if (percpu)
 		cost += (u64)attr->max_entries * elem_size * num_possible_cpus();
 
@@ -122,6 +133,19 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 		bpf_map_charge_finish(&mem);
 		return ERR_PTR(-ENOMEM);
 	}
+	array->data = (void *)&array->inline_data;
+
+	if (attr->map_flags & BPF_F_MMAPABLE) {
+		void *data = vzalloc_node(data_size, numa_node);
+
+		if (!data) {
+			bpf_map_charge_finish(&mem);
+			bpf_map_area_free(array);
+			return ERR_PTR(-ENOMEM);
+		}
+		array->data = data;
+	}
+
 	array->index_mask = index_mask;
 	array->map.unpriv_array = unpriv;
 
@@ -148,7 +172,7 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key)
 	if (unlikely(index >= array->map.max_entries))
 		return NULL;
 
-	return array->value + array->elem_size * (index & array->index_mask);
+	return array->data + array->elem_size * (index & array->index_mask);
 }
 
 static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm,
@@ -161,7 +185,7 @@ static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm,
 	if (off >= map->value_size)
 		return -EINVAL;
 
-	*imm = (unsigned long)array->value;
+	*imm = (unsigned long)array->data;
 	return 0;
 }
 
@@ -169,7 +193,7 @@ static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm,
 				       u32 *off)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
-	u64 base = (unsigned long)array->value;
+	u64 base = (unsigned long)array->data;
 	u64 range = array->elem_size;
 
 	if (map->max_entries != 1)
@@ -191,7 +215,15 @@ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 	const int map_ptr = BPF_REG_1;
 	const int index = BPF_REG_2;
 
-	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
+	if (map->map_flags & BPF_F_MMAPABLE) {
+		*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr,
+					offsetof(struct bpf_array, data));
+		*insn++ = BPF_LDX_MEM(bytes_to_bpf_size(sizeof(void *)),
+				      map_ptr, map_ptr, 0);
+	} else {
+		*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr,
+					offsetof(struct bpf_array, inline_data));
+	}
 	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
 	if (map->unpriv_array) {
 		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 4);
@@ -296,7 +328,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
 		memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]),
 		       value, map->value_size);
 	} else {
-		val = array->value +
+		val = array->data +
 			array->elem_size * (index & array->index_mask);
 		if (map_flags & BPF_F_LOCK)
 			copy_map_value_locked(map, val, value, false);
@@ -365,6 +397,8 @@ static void array_map_free(struct bpf_map *map)
 	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
 		bpf_array_free_percpu(array);
 
+	if (array->map.map_flags & BPF_F_MMAPABLE)
+		vfree(array->data);
 	bpf_map_area_free(array);
 }
 
@@ -444,6 +478,56 @@ static int array_map_check_btf(const struct bpf_map *map,
 	return 0;
 }
 
+void array_map_mmap_close(struct vm_area_struct *vma)
+{
+	struct bpf_array *array = vma->vm_file->private_data;
+
+	mutex_lock(&array->map.freeze_mutex);
+	if (vma->vm_flags & VM_WRITE)
+		array->map.writecnt--;
+	mutex_unlock(&array->map.freeze_mutex);
+
+	bpf_map_put(&array->map);
+}
+
+static vm_fault_t array_map_mmap_fault(struct vm_fault *vmf)
+{
+	struct bpf_array *array = vmf->vma->vm_file->private_data;
+	void *p = array->data + (vmf->pgoff << PAGE_SHIFT);
+
+	vmf->page = vmalloc_to_page(p);
+	/* bump page refcount, it will be decremented by kernel on unmap */
+	get_page(vmf->page);
+
+	return 0;
+}
+
+static const struct vm_operations_struct array_map_vmops = {
+	.close		= array_map_mmap_close,
+	.fault		= array_map_mmap_fault,
+};
+
+int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u64 data_size, vma_size;
+
+	if (!(map->map_flags & BPF_F_MMAPABLE))
+		return -EINVAL;
+
+	data_size = (u64)array->elem_size * map->max_entries;
+	data_size = round_up(data_size, PAGE_SIZE);
+	vma_size = vma->vm_end - vma->vm_start;
+	if (vma_size != data_size)
+		return -EINVAL;
+
+	vma->vm_ops = &array_map_vmops;
+	vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND;
+	vma->vm_private_data = array;
+
+	return 0;
+}
+
 const struct bpf_map_ops array_map_ops = {
 	.map_alloc_check = array_map_alloc_check,
 	.map_alloc = array_map_alloc,
@@ -455,6 +539,7 @@ 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,
 };
@@ -810,7 +895,9 @@ static u32 array_of_map_gen_lookup(struct bpf_map *map,
 	const int map_ptr = BPF_REG_1;
 	const int index = BPF_REG_2;
 
-	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
+	/* array of maps can't be BPF_F_MMAPABLE, so use inline_data */
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr,
+				offsetof(struct bpf_array, inline_data));
 	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
 	if (map->unpriv_array) {
 		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 6);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 6d9ce95e5a8d..c6ff1034c2f6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -425,6 +425,43 @@ static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf,
 	return -EINVAL;
 }
 
+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;
+	}
+
+	map = bpf_map_inc(map, false);
+	if (IS_ERR(map)) {
+		err = PTR_ERR(map);
+		goto out;
+	}
+
+	err = map->ops->map_mmap(map, vma);
+	if (err) {
+		bpf_map_put(map);
+		goto out;
+	}
+
+	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 +469,7 @@ 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 +615,7 @@ static int map_create(union bpf_attr *attr)
 
 	atomic_set(&map->refcnt, 1);
 	atomic_set(&map->usercnt, 1);
+	mutex_init(&map->freeze_mutex);
 
 	if (attr->btf_key_type_id || attr->btf_value_type_id) {
 		struct btf *btf;
@@ -1173,6 +1212,13 @@ 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;
@@ -1184,6 +1230,7 @@ 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;
 }
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index df6809a76404..bb39b53622d9 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -346,6 +346,9 @@ 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)
 
-- 
2.17.1

Re: [PATCH v2 bpf-next 1/3] bpf: add mmap() support for BPF_MAP_TYPE_ARRAY

[Song Liu]

> On Nov 9, 2019, at 12:06 AM, Andrii Nakryiko <andriin@fb.com> wrote:
> 
> 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.

[...]

> 
> Generated code for memory-mapped array:
> 
> ; p = bpf_map_lookup_elem(&data_map, &zero);
>  22: (18) r1 = map[id:27]
>  24: (07) r1 += 400			/* array->data offset */
>  25: (79) r1 = *(u64 *)(r1 +0)		/* extra dereference */
>  26: (61) r0 = *(u32 *)(r2 +0)
>  27: (35) if r0 >= 0x3 goto pc+3
>  28: (67) r0 <<= 3
>  29: (0f) r0 += r1
>  30: (05) goto pc+1
>  31: (b7) r0 = 0
> 
> Cc: Rik van Riel <riel@surriel.com>
> Cc: Johannes Weiner <hannes@cmpxchg.org>
> Signed-off-by: Andrii Nakryiko <andriin@fb.com>

Acked-by: Song Liu <songliubraving@fb.com>

Re: [PATCH v2 bpf-next 1/3] bpf: add mmap() support for BPF_MAP_TYPE_ARRAY

[Jakub Kicinski]

On Sat, 9 Nov 2019 00:06:30 -0800, Andrii Nakryiko wrote:
> With BPF_F_MMAPABLE array allocating data in separate chunk of memory,
> array_map_gen_lookup has to accomodate these changes. For non-memory-mapped
> there are no changes and no extra instructions. For BPF_F_MMAPABLE case,
> pointer to where array data is stored has to be dereferenced first.
> 
> Generated code for non-memory-mapped array:
> 
> ; p = bpf_map_lookup_elem(&data_map, &zero);
>   22: (18) r1 = map[id:19]
>   24: (07) r1 += 408			/* array->inline_data offset */
>   25: (61) r0 = *(u32 *)(r2 +0)
>   26: (35) if r0 >= 0x3 goto pc+3
>   27: (67) r0 <<= 3
>   28: (0f) r0 += r1
>   29: (05) goto pc+1
>   30: (b7) r0 = 0
> 
> Generated code for memory-mapped array:
> 
> ; p = bpf_map_lookup_elem(&data_map, &zero);
>   22: (18) r1 = map[id:27]
>   24: (07) r1 += 400			/* array->data offset */
>   25: (79) r1 = *(u64 *)(r1 +0)		/* extra dereference */
>   26: (61) r0 = *(u32 *)(r2 +0)
>   27: (35) if r0 >= 0x3 goto pc+3
>   28: (67) r0 <<= 3
>   29: (0f) r0 += r1
>   30: (05) goto pc+1
>   31: (b7) r0 = 0

Would it not be possible to overallocate the memory and align the start
of the bpf_map in case of BPF_F_MMAPABLE so that no extra dereference
is needed?

Re: [PATCH v2 bpf-next 1/3] bpf: add mmap() support for BPF_MAP_TYPE_ARRAY

[Andrii Nakryiko]

On Mon, Nov 11, 2019 at 10:37 AM Jakub Kicinski
<jakub.kicinski@netronome.com> wrote:
>
> On Sat, 9 Nov 2019 00:06:30 -0800, Andrii Nakryiko wrote:
> > With BPF_F_MMAPABLE array allocating data in separate chunk of memory,
> > array_map_gen_lookup has to accomodate these changes. For non-memory-mapped
> > there are no changes and no extra instructions. For BPF_F_MMAPABLE case,
> > pointer to where array data is stored has to be dereferenced first.
> >
> > Generated code for non-memory-mapped array:
> >
> > ; p = bpf_map_lookup_elem(&data_map, &zero);
> >   22: (18) r1 = map[id:19]
> >   24: (07) r1 += 408                  /* array->inline_data offset */
> >   25: (61) r0 = *(u32 *)(r2 +0)
> >   26: (35) if r0 >= 0x3 goto pc+3
> >   27: (67) r0 <<= 3
> >   28: (0f) r0 += r1
> >   29: (05) goto pc+1
> >   30: (b7) r0 = 0
> >
> > Generated code for memory-mapped array:
> >
> > ; p = bpf_map_lookup_elem(&data_map, &zero);
> >   22: (18) r1 = map[id:27]
> >   24: (07) r1 += 400                  /* array->data offset */
> >   25: (79) r1 = *(u64 *)(r1 +0)               /* extra dereference */
> >   26: (61) r0 = *(u32 *)(r2 +0)
> >   27: (35) if r0 >= 0x3 goto pc+3
> >   28: (67) r0 <<= 3
> >   29: (0f) r0 += r1
> >   30: (05) goto pc+1
> >   31: (b7) r0 = 0
>
> Would it not be possible to overallocate the memory and align the start
> of the bpf_map in case of BPF_F_MMAPABLE so that no extra dereference
> is needed?

So let's say if sizeof(struct bpf_array) is 300, then I'd have to either:

- somehow make sure that I allocate 4k (for data) + 300 (for struct
bpf_array) in such a way that those 4k of data are 4k-aligned. Is
there any way to do that?
- assuming there isn't, then another way would be to allocate entire
4k page for struct bpf_array itself, but put it at the end of that
page, so that 4k of data is 4k-aligned. While wasteful, the bigger
problem is that pointer to bpf_array is not a pointer to allocated
memory anymore, so we'd need to remember that and adjust address
before calling vfree().

Were you suggesting #2 as a solution? Or am I missing some other way to do this?

Re: [PATCH v2 bpf-next 1/3] bpf: add mmap() support for BPF_MAP_TYPE_ARRAY

[Jakub Kicinski]

On Mon, 11 Nov 2019 18:06:42 -0800, Andrii Nakryiko wrote:
> So let's say if sizeof(struct bpf_array) is 300, then I'd have to either:
> 
> - somehow make sure that I allocate 4k (for data) + 300 (for struct
> bpf_array) in such a way that those 4k of data are 4k-aligned. Is
> there any way to do that?
> - assuming there isn't, then another way would be to allocate entire
> 4k page for struct bpf_array itself, but put it at the end of that
> page, so that 4k of data is 4k-aligned. While wasteful, the bigger
> problem is that pointer to bpf_array is not a pointer to allocated
> memory anymore, so we'd need to remember that and adjust address
> before calling vfree().
> 
> Were you suggesting #2 as a solution? Or am I missing some other way to do this?

I am suggesting #2, that's the way to do it in the kernel.

You could make the assumption that if you're allocating memory aligned
to PAGE_SIZE, the address for vfree() is:

	addr = map;
	if (map->flags & MMAPABLE)
		addr = round_down(addr, PAGE_SIZE);
	vfree(addr);

Just make a note of the fact that we depend on vmalloc()s alignment in
bpf_map_area_alloc().

Re: [PATCH v2 bpf-next 1/3] bpf: add mmap() support for BPF_MAP_TYPE_ARRAY

[Andrii Nakryiko]

On Tue, Nov 12, 2019 at 11:17 AM Jakub Kicinski
<jakub.kicinski@netronome.com> wrote:
>
> On Mon, 11 Nov 2019 18:06:42 -0800, Andrii Nakryiko wrote:
> > So let's say if sizeof(struct bpf_array) is 300, then I'd have to either:
> >
> > - somehow make sure that I allocate 4k (for data) + 300 (for struct
> > bpf_array) in such a way that those 4k of data are 4k-aligned. Is
> > there any way to do that?
> > - assuming there isn't, then another way would be to allocate entire
> > 4k page for struct bpf_array itself, but put it at the end of that
> > page, so that 4k of data is 4k-aligned. While wasteful, the bigger
> > problem is that pointer to bpf_array is not a pointer to allocated
> > memory anymore, so we'd need to remember that and adjust address
> > before calling vfree().
> >
> > Were you suggesting #2 as a solution? Or am I missing some other way to do this?
>
> I am suggesting #2, that's the way to do it in the kernel.

So I'm concerned about this approach, because it feels like a bunch of
unnecessarily wasted memory. While there is no way around doing
round_up(PAGE_SIZE) for data itself, it certainly is not necessary to
waste almost entire page for struct bpf_array. And given this is going
to be used for BPF maps backing global variables, there most probably
will be at least 3 (.data, .bss, .rodata) per each program, and could
be more. Also, while on x86_64 page is 4k, on other architectures it
can be up to 64KB, so this seems wasteful.

What's your concern exactly with the way it's implemented in this patch?

>
> You could make the assumption that if you're allocating memory aligned
> to PAGE_SIZE, the address for vfree() is:
>
>         addr = map;
>         if (map->flags & MMAPABLE)
>                 addr = round_down(addr, PAGE_SIZE);
>         vfree(addr);
>
> Just make a note of the fact that we depend on vmalloc()s alignment in
> bpf_map_area_alloc().

will add comment for that

Re: [PATCH v2 bpf-next 1/3] bpf: add mmap() support for BPF_MAP_TYPE_ARRAY

[Jakub Kicinski]

On Tue, 12 Nov 2019 14:03:50 -0800, Andrii Nakryiko wrote:
> On Tue, Nov 12, 2019 at 11:17 AM Jakub Kicinski wrote:
> > On Mon, 11 Nov 2019 18:06:42 -0800, Andrii Nakryiko wrote:  
> > > So let's say if sizeof(struct bpf_array) is 300, then I'd have to either:
> > >
> > > - somehow make sure that I allocate 4k (for data) + 300 (for struct
> > > bpf_array) in such a way that those 4k of data are 4k-aligned. Is
> > > there any way to do that?
> > > - assuming there isn't, then another way would be to allocate entire
> > > 4k page for struct bpf_array itself, but put it at the end of that
> > > page, so that 4k of data is 4k-aligned. While wasteful, the bigger
> > > problem is that pointer to bpf_array is not a pointer to allocated
> > > memory anymore, so we'd need to remember that and adjust address
> > > before calling vfree().
> > >
> > > Were you suggesting #2 as a solution? Or am I missing some other way to do this?  
> >
> > I am suggesting #2, that's the way to do it in the kernel.  
> 
> So I'm concerned about this approach, because it feels like a bunch of
> unnecessarily wasted memory. While there is no way around doing
> round_up(PAGE_SIZE) for data itself, it certainly is not necessary to
> waste almost entire page for struct bpf_array. And given this is going
> to be used for BPF maps backing global variables, there most probably
> will be at least 3 (.data, .bss, .rodata) per each program, and could
> be more. Also, while on x86_64 page is 4k, on other architectures it
> can be up to 64KB, so this seems wasteful.

With the extra mutex and int you grew struct bpf_map from 192B to 256B,
that's for every map on the system, unconditionally, and array map has
an extra pointer even if it doesn't need it.

Increasing "wasted" space when an opt-in feature is selected doesn't
seem all that terrible to me, especially that the overhead of aligning
up map size to page size is already necessary.

> What's your concern exactly with the way it's implemented in this patch?

Judging by other threads we seem to care about performance of BPF
(rightly so). Doing an extra pointer deref for every static data access
seems like an obvious waste.

But then again, it's just an obvious suggestion, take it or leave it..

Re: [PATCH v2 bpf-next 1/3] bpf: add mmap() support for BPF_MAP_TYPE_ARRAY

[Andrii Nakryiko]

On Tue, Nov 12, 2019 at 2:38 PM Jakub Kicinski
<jakub.kicinski@netronome.com> wrote:
>
> On Tue, 12 Nov 2019 14:03:50 -0800, Andrii Nakryiko wrote:
> > On Tue, Nov 12, 2019 at 11:17 AM Jakub Kicinski wrote:
> > > On Mon, 11 Nov 2019 18:06:42 -0800, Andrii Nakryiko wrote:
> > > > So let's say if sizeof(struct bpf_array) is 300, then I'd have to either:
> > > >
> > > > - somehow make sure that I allocate 4k (for data) + 300 (for struct
> > > > bpf_array) in such a way that those 4k of data are 4k-aligned. Is
> > > > there any way to do that?
> > > > - assuming there isn't, then another way would be to allocate entire
> > > > 4k page for struct bpf_array itself, but put it at the end of that
> > > > page, so that 4k of data is 4k-aligned. While wasteful, the bigger
> > > > problem is that pointer to bpf_array is not a pointer to allocated
> > > > memory anymore, so we'd need to remember that and adjust address
> > > > before calling vfree().
> > > >
> > > > Were you suggesting #2 as a solution? Or am I missing some other way to do this?
> > >
> > > I am suggesting #2, that's the way to do it in the kernel.
> >
> > So I'm concerned about this approach, because it feels like a bunch of
> > unnecessarily wasted memory. While there is no way around doing
> > round_up(PAGE_SIZE) for data itself, it certainly is not necessary to
> > waste almost entire page for struct bpf_array. And given this is going
> > to be used for BPF maps backing global variables, there most probably
> > will be at least 3 (.data, .bss, .rodata) per each program, and could
> > be more. Also, while on x86_64 page is 4k, on other architectures it
> > can be up to 64KB, so this seems wasteful.
>
> With the extra mutex and int you grew struct bpf_map from 192B to 256B,
> that's for every map on the system, unconditionally, and array map has
> an extra pointer even if it doesn't need it.
>
> Increasing "wasted" space when an opt-in feature is selected doesn't
> seem all that terrible to me, especially that the overhead of aligning
> up map size to page size is already necessary.

Well, I've been talking about one more extra page for struct bpf_array
itself, on top of what we already potentially waste for mmap()'ing
array data. But I went ahead and posted v3 with layout we discussed
here, aligning array->value on page boundary. Let's see if you like it
better.

>
> > What's your concern exactly with the way it's implemented in this patch?
>
> Judging by other threads we seem to care about performance of BPF
> (rightly so). Doing an extra pointer deref for every static data access
> seems like an obvious waste.
>
> But then again, it's just an obvious suggestion, take it or leave it..

Re: [PATCH v2 bpf-next 1/3] bpf: add mmap() support for BPF_MAP_TYPE_ARRAY

[Jakub Kicinski]

On Sat, 9 Nov 2019 00:06:30 -0800, Andrii Nakryiko wrote:
> @@ -74,7 +78,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
>  	int ret, numa_node = bpf_map_attr_numa_node(attr);
>  	u32 elem_size, index_mask, max_entries;
>  	bool unpriv = !capable(CAP_SYS_ADMIN);
> -	u64 cost, array_size, mask64;
> +	u64 cost, array_size, data_size, mask64;
>  	struct bpf_map_memory mem;
>  	struct bpf_array *array;
>  

Please don't break reverse xmas tree where it exists.

Re: [PATCH v2 bpf-next 1/3] bpf: add mmap() support for BPF_MAP_TYPE_ARRAY

[Andrii Nakryiko]

On Mon, Nov 11, 2019 at 10:39 AM Jakub Kicinski
<jakub.kicinski@netronome.com> wrote:
>
> On Sat, 9 Nov 2019 00:06:30 -0800, Andrii Nakryiko wrote:
> > @@ -74,7 +78,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
> >       int ret, numa_node = bpf_map_attr_numa_node(attr);
> >       u32 elem_size, index_mask, max_entries;
> >       bool unpriv = !capable(CAP_SYS_ADMIN);
> > -     u64 cost, array_size, mask64;
> > +     u64 cost, array_size, data_size, mask64;
> >       struct bpf_map_memory mem;
> >       struct bpf_array *array;
> >
>
> Please don't break reverse xmas tree where it exists.

alright, will move it up

[PATCH v2 bpf-next 2/3] libbpf: make global data internal arrays mmap()-able, if possible

[Andrii Nakryiko]

Add detection of BPF_F_MMAPABLE flag support for arrays and add it as an extra
flag to internal global data maps, if supported by kernel. This allows users
to memory-map global data and use it without BPF map operations, greatly
simplifying user experience.

Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
---
 tools/lib/bpf/libbpf.c | 31 +++++++++++++++++++++++++++++--
 1 file changed, 29 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index fde6cb3e5d41..d32899e50f8a 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -142,6 +142,8 @@ struct bpf_capabilities {
 	__u32 btf_func:1;
 	/* BTF_KIND_VAR and BTF_KIND_DATASEC support */
 	__u32 btf_datasec:1;
+	/* BPF_F_MMAPABLE is supported for arrays */
+	__u32 array_mmap:1;
 };
 
 /*
@@ -855,8 +857,6 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 		pr_warn("failed to alloc map name\n");
 		return -ENOMEM;
 	}
-	pr_debug("map '%s' (global data): at sec_idx %d, offset %zu.\n",
-		 map_name, map->sec_idx, map->sec_offset);
 
 	def = &map->def;
 	def->type = BPF_MAP_TYPE_ARRAY;
@@ -864,6 +864,12 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 	def->value_size = data->d_size;
 	def->max_entries = 1;
 	def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0;
+	if (obj->caps.array_mmap)
+		def->map_flags |= BPF_F_MMAPABLE;
+
+	pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n",
+		 map_name, map->sec_idx, map->sec_offset, def->map_flags);
+
 	if (data_buff) {
 		*data_buff = malloc(data->d_size);
 		if (!*data_buff) {
@@ -2158,6 +2164,26 @@ static int bpf_object__probe_btf_datasec(struct bpf_object *obj)
 	return 0;
 }
 
+static int bpf_object__probe_array_mmap(struct bpf_object *obj)
+{
+	struct bpf_create_map_attr attr = {
+		.map_type = BPF_MAP_TYPE_ARRAY,
+		.map_flags = BPF_F_MMAPABLE,
+		.key_size = sizeof(int),
+		.value_size = sizeof(int),
+		.max_entries = 1,
+	};
+	int fd = bpf_create_map_xattr(&attr);
+
+	if (fd >= 0) {
+		obj->caps.array_mmap = 1;
+		close(fd);
+		return 1;
+	}
+
+	return 0;
+}
+
 static int
 bpf_object__probe_caps(struct bpf_object *obj)
 {
@@ -2166,6 +2192,7 @@ bpf_object__probe_caps(struct bpf_object *obj)
 		bpf_object__probe_global_data,
 		bpf_object__probe_btf_func,
 		bpf_object__probe_btf_datasec,
+		bpf_object__probe_array_mmap,
 	};
 	int i, ret;
 
-- 
2.17.1

Re: [PATCH v2 bpf-next 2/3] libbpf: make global data internal arrays mmap()-able, if possible

[Jakub Kicinski]

On Sat, 9 Nov 2019 00:06:31 -0800, Andrii Nakryiko wrote:
> +static int bpf_object__probe_array_mmap(struct bpf_object *obj)
> +{
> +	struct bpf_create_map_attr attr = {
> +		.map_type = BPF_MAP_TYPE_ARRAY,
> +		.map_flags = BPF_F_MMAPABLE,
> +		.key_size = sizeof(int),
> +		.value_size = sizeof(int),
> +		.max_entries = 1,
> +	};
> +	int fd = bpf_create_map_xattr(&attr);
> +
> +	if (fd >= 0) {

The point of the empty line between variable declarations and code in
the Linux coding style is to provide a visual separation between
variables and code.

If you call a complex function in variable init and then check for
errors in the code that really breaks that principle.

> +		obj->caps.array_mmap = 1;
> +		close(fd);
> +		return 1;
> +	}
> +
> +	return 0;
> +}

Re: [PATCH v2 bpf-next 2/3] libbpf: make global data internal arrays mmap()-able, if possible

[Andrii Nakryiko]

On Mon, Nov 11, 2019 at 10:41 AM Jakub Kicinski
<jakub.kicinski@netronome.com> wrote:
>
> On Sat, 9 Nov 2019 00:06:31 -0800, Andrii Nakryiko wrote:
> > +static int bpf_object__probe_array_mmap(struct bpf_object *obj)
> > +{
> > +     struct bpf_create_map_attr attr = {
> > +             .map_type = BPF_MAP_TYPE_ARRAY,
> > +             .map_flags = BPF_F_MMAPABLE,
> > +             .key_size = sizeof(int),
> > +             .value_size = sizeof(int),
> > +             .max_entries = 1,
> > +     };
> > +     int fd = bpf_create_map_xattr(&attr);
> > +
> > +     if (fd >= 0) {
>
> The point of the empty line between variable declarations and code in
> the Linux coding style is to provide a visual separation between
> variables and code.
>
> If you call a complex function in variable init and then check for
> errors in the code that really breaks that principle.

I'll split declaration and initialization, no problem

>
> > +             obj->caps.array_mmap = 1;
> > +             close(fd);
> > +             return 1;
> > +     }
> > +
> > +     return 0;
> > +}
>

[PATCH v2 bpf-next 3/3] selftests/bpf: add BPF_TYPE_MAP_ARRAY mmap() tests

[Andrii Nakryiko]

Add selftests validating mmap()-ing BPF array maps: both single-element and
multi-element ones. Check that plain bpf_map_update_elem() and
bpf_map_lookup_elem() work correctly with memory-mapped array. Also convert
CO-RE relocation tests to use memory-mapped views of global data.

Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
---
 .../selftests/bpf/prog_tests/core_reloc.c     |  45 +++--
 tools/testing/selftests/bpf/prog_tests/mmap.c | 170 ++++++++++++++++++
 tools/testing/selftests/bpf/progs/test_mmap.c |  41 +++++
 3 files changed, 238 insertions(+), 18 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/mmap.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_mmap.c

diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index f94bd071536b..ec9e2fdd6b89 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 #include "progs/core_reloc_types.h"
+#include <sys/mman.h>
 
 #define STRUCT_TO_CHAR_PTR(struct_name) (const char *)&(struct struct_name)
 
@@ -453,8 +454,15 @@ struct data {
 	char out[256];
 };
 
+static size_t roundup_page(size_t sz)
+{
+	long page_size = sysconf(_SC_PAGE_SIZE);
+	return (sz + page_size - 1) / page_size * page_size;
+}
+
 void test_core_reloc(void)
 {
+	const size_t mmap_sz = roundup_page(sizeof(struct data));
 	struct bpf_object_load_attr load_attr = {};
 	struct core_reloc_test_case *test_case;
 	const char *tp_name, *probe_name;
@@ -463,8 +471,8 @@ void test_core_reloc(void)
 	struct bpf_map *data_map;
 	struct bpf_program *prog;
 	struct bpf_object *obj;
-	const int zero = 0;
-	struct data data;
+	struct data *data;
+	void *mmap_data = NULL;
 
 	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
 		test_case = &test_cases[i];
@@ -476,8 +484,7 @@ void test_core_reloc(void)
 		);
 
 		obj = bpf_object__open_file(test_case->bpf_obj_file, &opts);
-		if (CHECK(IS_ERR_OR_NULL(obj), "obj_open",
-			  "failed to open '%s': %ld\n",
+		if (CHECK(IS_ERR(obj), "obj_open", "failed to open '%s': %ld\n",
 			  test_case->bpf_obj_file, PTR_ERR(obj)))
 			continue;
 
@@ -519,24 +526,22 @@ void test_core_reloc(void)
 		if (CHECK(!data_map, "find_data_map", "data map not found\n"))
 			goto cleanup;
 
-		memset(&data, 0, sizeof(data));
-		memcpy(data.in, test_case->input, test_case->input_len);
-
-		err = bpf_map_update_elem(bpf_map__fd(data_map),
-					  &zero, &data, 0);
-		if (CHECK(err, "update_data_map",
-			  "failed to update .data map: %d\n", err))
+		mmap_data = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE,
+				 MAP_SHARED, bpf_map__fd(data_map), 0);
+		if (CHECK(mmap_data == MAP_FAILED, "mmap",
+			  ".bss mmap failed: %d", errno)) {
+			mmap_data = NULL;
 			goto cleanup;
+		}
+		data = mmap_data;
+
+		memset(mmap_data, 0, sizeof(*data));
+		memcpy(data->in, test_case->input, test_case->input_len);
 
 		/* trigger test run */
 		usleep(1);
 
-		err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &data);
-		if (CHECK(err, "get_result",
-			  "failed to get output data: %d\n", err))
-			goto cleanup;
-
-		equal = memcmp(data.out, test_case->output,
+		equal = memcmp(data->out, test_case->output,
 			       test_case->output_len) == 0;
 		if (CHECK(!equal, "check_result",
 			  "input/output data don't match\n")) {
@@ -548,12 +553,16 @@ void test_core_reloc(void)
 			}
 			for (j = 0; j < test_case->output_len; j++) {
 				printf("output byte #%d: EXP 0x%02hhx GOT 0x%02hhx\n",
-				       j, test_case->output[j], data.out[j]);
+				       j, test_case->output[j], data->out[j]);
 			}
 			goto cleanup;
 		}
 
 cleanup:
+		if (mmap_data) {
+			CHECK_FAIL(munmap(mmap_data, mmap_sz));
+			mmap_data = NULL;
+		}
 		if (!IS_ERR_OR_NULL(link)) {
 			bpf_link__destroy(link);
 			link = NULL;
diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c
new file mode 100644
index 000000000000..ef3a4f926764
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/mmap.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <sys/mman.h>
+
+struct map_data {
+	__u64 val[3];
+};
+
+struct bss_data {
+	__u64 in_val;
+	__u64 out_val;
+};
+
+static size_t roundup_page(size_t sz)
+{
+	long page_size = sysconf(_SC_PAGE_SIZE);
+	return (sz + page_size - 1) / page_size * page_size;
+}
+
+void test_mmap(void)
+{
+	const char *file = "test_mmap.o";
+	const char *probe_name = "raw_tracepoint/sys_enter";
+	const char *tp_name = "sys_enter";
+	const size_t bss_sz = roundup_page(sizeof(struct bss_data));
+	const size_t map_sz = roundup_page(sizeof(struct map_data));
+	int err, duration = 0, i, data_map_fd, zero = 0, one = 1, two = 2;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	struct bpf_link *link = NULL;
+	struct bpf_map *data_map, *bss_map;
+	void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp_mmaped;
+	volatile struct bss_data *bss_data;
+	volatile struct map_data *map_data;
+	__u64 val = 0;
+
+	obj = bpf_object__open_file("test_mmap.o", NULL);
+	if (CHECK(IS_ERR(obj), "obj_open", "failed to open '%s': %ld\n",
+		  file, PTR_ERR(obj)))
+		return;
+	prog = bpf_object__find_program_by_title(obj, probe_name);
+	if (CHECK(!prog, "find_probe", "prog '%s' not found\n", probe_name))
+		goto cleanup;
+	err = bpf_object__load(obj);
+	if (CHECK(err, "obj_load", "failed to load prog '%s': %d\n",
+		  probe_name, err))
+		goto cleanup;
+
+	bss_map = bpf_object__find_map_by_name(obj, "test_mma.bss");
+	if (CHECK(!bss_map, "find_bss_map", ".bss map not found\n"))
+		goto cleanup;
+	data_map = bpf_object__find_map_by_name(obj, "data_map");
+	if (CHECK(!data_map, "find_data_map", "data_map map not found\n"))
+		goto cleanup;
+	data_map_fd = bpf_map__fd(data_map);
+
+	bss_mmaped = mmap(NULL, bss_sz, PROT_READ | PROT_WRITE, MAP_SHARED,
+			  bpf_map__fd(bss_map), 0);
+	if (CHECK(bss_mmaped == MAP_FAILED, "bss_mmap",
+		  ".bss mmap failed: %d\n", errno)) {
+		bss_mmaped = NULL;
+		goto cleanup;
+	}
+	/* map as R/W first */
+	map_mmaped = mmap(NULL, map_sz, PROT_READ | PROT_WRITE, MAP_SHARED,
+			  data_map_fd, 0);
+	if (CHECK(map_mmaped == MAP_FAILED, "data_mmap",
+		  "data_map mmap failed: %d\n", errno)) {
+		map_mmaped = NULL;
+		goto cleanup;
+	}
+
+	bss_data = bss_mmaped;
+	map_data = map_mmaped;
+
+	CHECK_FAIL(bss_data->in_val);
+	CHECK_FAIL(bss_data->out_val);
+	CHECK_FAIL(map_data->val[0]);
+	CHECK_FAIL(map_data->val[1]);
+	CHECK_FAIL(map_data->val[2]);
+
+	link = bpf_program__attach_raw_tracepoint(prog, tp_name);
+	if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link)))
+		goto cleanup;
+
+	bss_data->in_val = 123;
+	val = 111;
+	CHECK_FAIL(bpf_map_update_elem(data_map_fd, &zero, &val, 0));
+
+	usleep(1);
+
+	CHECK_FAIL(bss_data->in_val != 123);
+	CHECK_FAIL(bss_data->out_val != 123);
+	CHECK_FAIL(map_data->val[0] != 111);
+	CHECK_FAIL(map_data->val[1] != 222);
+	CHECK_FAIL(map_data->val[2] != 123);
+
+	CHECK_FAIL(bpf_map_lookup_elem(data_map_fd, &zero, &val));
+	CHECK_FAIL(val != 111);
+	CHECK_FAIL(bpf_map_lookup_elem(data_map_fd, &one, &val));
+	CHECK_FAIL(val != 222);
+	CHECK_FAIL(bpf_map_lookup_elem(data_map_fd, &two, &val));
+	CHECK_FAIL(val != 123);
+
+	/* data_map freeze should fail due to R/W mmap() */
+	err = bpf_map_freeze(data_map_fd);
+	if (CHECK(!err || errno != EBUSY, "no_freeze",
+		  "data_map freeze succeeded: err=%d, errno=%d\n", err, errno))
+		goto cleanup;
+
+	/* unmap R/W mapping */
+	err = munmap(map_mmaped, map_sz);
+	map_mmaped = NULL;
+	if (CHECK(err, "data_map_munmap", "data_map munmap failed: %d\n", errno))
+		goto cleanup;
+
+	/* re-map as R/O now */
+	map_mmaped = mmap(NULL, map_sz, PROT_READ, MAP_SHARED, data_map_fd, 0);
+	if (CHECK(map_mmaped == MAP_FAILED, "data_mmap",
+		  "data_map R/O mmap failed: %d\n", errno)) {
+		map_mmaped = NULL;
+		goto cleanup;
+	}
+	map_data = map_mmaped;
+
+	/* map/unmap in a loop to test ref counting */
+	for (i = 0; i < 10; i++) {
+		int flags = i % 2 ? PROT_READ : PROT_WRITE;
+		void *p;
+
+		p = mmap(NULL, map_sz, flags, MAP_SHARED, data_map_fd, 0);
+		if (CHECK_FAIL(p == MAP_FAILED))
+			goto cleanup;
+		err = munmap(p, map_sz);
+		if (CHECK_FAIL(err))
+			goto cleanup;
+	}
+
+	/* data_map freeze should now succeed due to no R/W mapping */
+	err = bpf_map_freeze(data_map_fd);
+	if (CHECK(err, "freeze", "data_map freeze failed: err=%d, errno=%d\n",
+		  err, errno))
+		goto cleanup;
+
+	/* mapping as R/W now should fail */
+	tmp_mmaped = mmap(NULL, map_sz, PROT_READ | PROT_WRITE, MAP_SHARED,
+			  data_map_fd, 0);
+	if (CHECK(tmp_mmaped != MAP_FAILED, "data_mmap",
+		  "data_map mmap succeeded\n")) {
+		munmap(tmp_mmaped, map_sz);
+		goto cleanup;
+	}
+
+	bss_data->in_val = 321;
+	usleep(1);
+	CHECK_FAIL(bss_data->in_val != 321);
+	CHECK_FAIL(bss_data->out_val != 321);
+	CHECK_FAIL(map_data->val[0] != 111);
+	CHECK_FAIL(map_data->val[1] != 222);
+	CHECK_FAIL(map_data->val[2] != 321);
+
+cleanup:
+	if (bss_mmaped)
+		CHECK_FAIL(munmap(bss_mmaped, bss_sz));
+	if (map_mmaped)
+		CHECK_FAIL(munmap(map_mmaped, map_sz));
+	if (!IS_ERR_OR_NULL(link))
+		bpf_link__destroy(link);
+	bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_mmap.c b/tools/testing/selftests/bpf/progs/test_mmap.c
new file mode 100644
index 000000000000..98e3ea36b88e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_mmap.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+#include <linux/bpf.h>
+#include <stdint.h>
+#include "bpf_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 3);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__type(key, __u32);
+	__type(value, __u64);
+} data_map SEC(".maps");
+
+static volatile __u64 in_val;
+static volatile __u64 out_val;
+
+SEC("raw_tracepoint/sys_enter")
+int test_mmap(void *ctx)
+{
+	int zero = 0, one = 1, two = 2;
+	__u64 val, *p;
+
+	out_val = in_val;
+
+	/* data_map[2] = in_val */
+	bpf_map_update_elem(&data_map, &two, (const void *)&in_val, 0);
+
+	/* data_map[1] = data_map[0] * 2; */
+	p = bpf_map_lookup_elem(&data_map, &zero);
+	if (p) {
+		val = (*p) * 2;
+		bpf_map_update_elem(&data_map, &one, &val, 0);
+	}
+
+	return 0;
+}
+
-- 
2.17.1