Initial commit: Linux kernel 4.19 for Unplugged OS

kernel/bpf/Makefile

@@ -0,0 +1,29 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-y := core.o
+CFLAGS_core.o += $(call cc-disable-warning, override-init)
+
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
+obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
+obj-$(CONFIG_BPF_SYSCALL) += local_storage.o
+obj-$(CONFIG_BPF_SYSCALL) += disasm.o
+obj-$(CONFIG_BPF_SYSCALL) += btf.o
+ifeq ($(CONFIG_NET),y)
+obj-$(CONFIG_BPF_SYSCALL) += devmap.o
+obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
+ifeq ($(CONFIG_XDP_SOCKETS),y)
+obj-$(CONFIG_BPF_SYSCALL) += xskmap.o
+endif
+obj-$(CONFIG_BPF_SYSCALL) += offload.o
+ifeq ($(CONFIG_STREAM_PARSER),y)
+ifeq ($(CONFIG_INET),y)
+obj-$(CONFIG_BPF_SYSCALL) += sockmap.o
+endif
+endif
+endif
+ifeq ($(CONFIG_PERF_EVENTS),y)
+obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
+endif
+obj-$(CONFIG_CGROUP_BPF) += cgroup.o
+ifeq ($(CONFIG_INET),y)
+obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o
+endif

kernel/bpf/arraymap.c

@@ -0,0 +1,750 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2016,2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/filter.h>
+#include <linux/perf_event.h>
+#include <uapi/linux/btf.h>
+
+#include "map_in_map.h"
+
+#define ARRAY_CREATE_FLAG_MASK \
+	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
+static void bpf_array_free_percpu(struct bpf_array *array)
+{
+	int i;
+
+	for (i = 0; i < array->map.max_entries; i++) {
+		free_percpu(array->pptrs[i]);
+		cond_resched();
+	}
+}
+
+static int bpf_array_alloc_percpu(struct bpf_array *array)
+{
+	void __percpu *ptr;
+	int i;
+
+	for (i = 0; i < array->map.max_entries; i++) {
+		ptr = __alloc_percpu_gfp(array->elem_size, 8,
+					 GFP_USER | __GFP_NOWARN);
+		if (!ptr) {
+			bpf_array_free_percpu(array);
+			return -ENOMEM;
+		}
+		array->pptrs[i] = ptr;
+		cond_resched();
+	}
+
+	return 0;
+}
+
+/* Called from syscall */
+int array_map_alloc_check(union bpf_attr *attr)
+{
+	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
+	int numa_node = bpf_map_attr_numa_node(attr);
+
+	/* check sanity of attributes */
+	if (attr->max_entries == 0 || attr->key_size != 4 ||
+	    attr->value_size == 0 ||
+	    attr->map_flags & ~ARRAY_CREATE_FLAG_MASK ||
+	    (percpu && numa_node != NUMA_NO_NODE))
+		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.
+		 */
+		return -E2BIG;
+
+	return 0;
+}
+
+static struct bpf_map *array_map_alloc(union bpf_attr *attr)
+{
+	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
+	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;
+	struct bpf_array *array;
+
+	elem_size = round_up(attr->value_size, 8);
+
+	max_entries = attr->max_entries;
+
+	/* On 32 bit archs roundup_pow_of_two() with max_entries that has
+	 * upper most bit set in u32 space is undefined behavior due to
+	 * resulting 1U << 32, so do it manually here in u64 space.
+	 */
+	mask64 = fls_long(max_entries - 1);
+	mask64 = 1ULL << mask64;
+	mask64 -= 1;
+
+	index_mask = mask64;
+	if (unpriv) {
+		/* round up array size to nearest power of 2,
+		 * since cpu will speculate within index_mask limits
+		 */
+		max_entries = index_mask + 1;
+		/* Check for overflows. */
+		if (max_entries < attr->max_entries)
+			return ERR_PTR(-E2BIG);
+	}
+
+	array_size = sizeof(*array);
+	if (percpu)
+		array_size += (u64) max_entries * sizeof(void *);
+	else
+		array_size += (u64) max_entries * elem_size;
+
+	/* make sure there is no u32 overflow later in round_up() */
+	cost = array_size;
+	if (cost >= U32_MAX - PAGE_SIZE)
+		return ERR_PTR(-ENOMEM);
+	if (percpu) {
+		cost += (u64)attr->max_entries * elem_size * num_possible_cpus();
+		if (cost >= U32_MAX - PAGE_SIZE)
+			return ERR_PTR(-ENOMEM);
+	}
+	cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	ret = bpf_map_precharge_memlock(cost);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	/* allocate all map elements and zero-initialize them */
+	array = bpf_map_area_alloc(array_size, numa_node);
+	if (!array)
+		return ERR_PTR(-ENOMEM);
+	array->index_mask = index_mask;
+	array->map.unpriv_array = unpriv;
+
+	/* copy mandatory map attributes */
+	bpf_map_init_from_attr(&array->map, attr);
+	array->map.pages = cost;
+	array->elem_size = elem_size;
+
+	if (percpu && bpf_array_alloc_percpu(array)) {
+		bpf_map_area_free(array);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return &array->map;
+}
+
+/* Called from syscall or from eBPF program */
+static void *array_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u32 index = *(u32 *)key;
+
+	if (unlikely(index >= array->map.max_entries))
+		return NULL;
+
+	return array->value + array->elem_size * (index & array->index_mask);
+}
+
+/* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
+static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct bpf_insn *insn = insn_buf;
+	u32 elem_size = round_up(map->value_size, 8);
+	const int ret = BPF_REG_0;
+	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));
+	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
+	if (map->unpriv_array) {
+		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 4);
+		*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
+	} else {
+		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3);
+	}
+
+	if (is_power_of_2(elem_size)) {
+		*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
+	} else {
+		*insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size);
+	}
+	*insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr);
+	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
+	*insn++ = BPF_MOV64_IMM(ret, 0);
+	return insn - insn_buf;
+}
+
+/* Called from eBPF program */
+static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u32 index = *(u32 *)key;
+
+	if (unlikely(index >= array->map.max_entries))
+		return NULL;
+
+	return this_cpu_ptr(array->pptrs[index & array->index_mask]);
+}
+
+int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u32 index = *(u32 *)key;
+	void __percpu *pptr;
+	int cpu, off = 0;
+	u32 size;
+
+	if (unlikely(index >= array->map.max_entries))
+		return -ENOENT;
+
+	/* per_cpu areas are zero-filled and bpf programs can only
+	 * access 'value_size' of them, so copying rounded areas
+	 * will not leak any kernel data
+	 */
+	size = round_up(map->value_size, 8);
+	rcu_read_lock();
+	pptr = array->pptrs[index & array->index_mask];
+	for_each_possible_cpu(cpu) {
+		bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size);
+		off += size;
+	}
+	rcu_read_unlock();
+	return 0;
+}
+
+/* Called from syscall */
+static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u32 index = key ? *(u32 *)key : U32_MAX;
+	u32 *next = (u32 *)next_key;
+
+	if (index >= array->map.max_entries) {
+		*next = 0;
+		return 0;
+	}
+
+	if (index == array->map.max_entries - 1)
+		return -ENOENT;
+
+	*next = index + 1;
+	return 0;
+}
+
+/* Called from syscall or from eBPF program */
+static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
+				 u64 map_flags)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u32 index = *(u32 *)key;
+
+	if (unlikely(map_flags > BPF_EXIST))
+		/* unknown flags */
+		return -EINVAL;
+
+	if (unlikely(index >= array->map.max_entries))
+		/* all elements were pre-allocated, cannot insert a new one */
+		return -E2BIG;
+
+	if (unlikely(map_flags == BPF_NOEXIST))
+		/* all elements already exist */
+		return -EEXIST;
+
+	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+		memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]),
+		       value, map->value_size);
+	else
+		memcpy(array->value +
+		       array->elem_size * (index & array->index_mask),
+		       value, map->value_size);
+	return 0;
+}
+
+int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
+			    u64 map_flags)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u32 index = *(u32 *)key;
+	void __percpu *pptr;
+	int cpu, off = 0;
+	u32 size;
+
+	if (unlikely(map_flags > BPF_EXIST))
+		/* unknown flags */
+		return -EINVAL;
+
+	if (unlikely(index >= array->map.max_entries))
+		/* all elements were pre-allocated, cannot insert a new one */
+		return -E2BIG;
+
+	if (unlikely(map_flags == BPF_NOEXIST))
+		/* all elements already exist */
+		return -EEXIST;
+
+	/* the user space will provide round_up(value_size, 8) bytes that
+	 * will be copied into per-cpu area. bpf programs can only access
+	 * value_size of it. During lookup the same extra bytes will be
+	 * returned or zeros which were zero-filled by percpu_alloc,
+	 * so no kernel data leaks possible
+	 */
+	size = round_up(map->value_size, 8);
+	rcu_read_lock();
+	pptr = array->pptrs[index & array->index_mask];
+	for_each_possible_cpu(cpu) {
+		bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size);
+		off += size;
+	}
+	rcu_read_unlock();
+	return 0;
+}
+
+/* Called from syscall or from eBPF program */
+static int array_map_delete_elem(struct bpf_map *map, void *key)
+{
+	return -EINVAL;
+}
+
+/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
+static void array_map_free(struct bpf_map *map)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+
+	/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
+	 * so the programs (can be more than one that used this map) were
+	 * disconnected from events. Wait for outstanding programs to complete
+	 * and free the array
+	 */
+	synchronize_rcu();
+
+	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+		bpf_array_free_percpu(array);
+
+	bpf_map_area_free(array);
+}
+
+static void array_map_seq_show_elem(struct bpf_map *map, void *key,
+				    struct seq_file *m)
+{
+	void *value;
+
+	rcu_read_lock();
+
+	value = array_map_lookup_elem(map, key);
+	if (!value) {
+		rcu_read_unlock();
+		return;
+	}
+
+	seq_printf(m, "%u: ", *(u32 *)key);
+	btf_type_seq_show(map->btf, map->btf_value_type_id, value, m);
+	seq_puts(m, "\n");
+
+	rcu_read_unlock();
+}
+
+static int array_map_check_btf(const struct bpf_map *map,
+			       const struct btf_type *key_type,
+			       const struct btf_type *value_type)
+{
+	u32 int_data;
+
+	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
+		return -EINVAL;
+
+	int_data = *(u32 *)(key_type + 1);
+	/* bpf array can only take a u32 key. This check makes sure
+	 * that the btf matches the attr used during map_create.
+	 */
+	if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
+		return -EINVAL;
+
+	return 0;
+}
+
+const struct bpf_map_ops array_map_ops = {
+	.map_alloc_check = array_map_alloc_check,
+	.map_alloc = array_map_alloc,
+	.map_free = array_map_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = array_map_lookup_elem,
+	.map_update_elem = array_map_update_elem,
+	.map_delete_elem = array_map_delete_elem,
+	.map_gen_lookup = array_map_gen_lookup,
+	.map_seq_show_elem = array_map_seq_show_elem,
+	.map_check_btf = array_map_check_btf,
+};
+
+const struct bpf_map_ops percpu_array_map_ops = {
+	.map_alloc_check = array_map_alloc_check,
+	.map_alloc = array_map_alloc,
+	.map_free = array_map_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = percpu_array_map_lookup_elem,
+	.map_update_elem = array_map_update_elem,
+	.map_delete_elem = array_map_delete_elem,
+	.map_check_btf = array_map_check_btf,
+};
+
+static int fd_array_map_alloc_check(union bpf_attr *attr)
+{
+	/* only file descriptors can be stored in this type of map */
+	if (attr->value_size != sizeof(u32))
+		return -EINVAL;
+	return array_map_alloc_check(attr);
+}
+
+static void fd_array_map_free(struct bpf_map *map)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	int i;
+
+	synchronize_rcu();
+
+	/* make sure it's empty */
+	for (i = 0; i < array->map.max_entries; i++)
+		BUG_ON(array->ptrs[i] != NULL);
+
+	bpf_map_area_free(array);
+}
+
+static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	return NULL;
+}
+
+/* only called from syscall */
+int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value)
+{
+	void **elem, *ptr;
+	int ret =  0;
+
+	if (!map->ops->map_fd_sys_lookup_elem)
+		return -ENOTSUPP;
+
+	rcu_read_lock();
+	elem = array_map_lookup_elem(map, key);
+	if (elem && (ptr = READ_ONCE(*elem)))
+		*value = map->ops->map_fd_sys_lookup_elem(ptr);
+	else
+		ret = -ENOENT;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/* only called from syscall */
+int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
+				 void *key, void *value, u64 map_flags)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	void *new_ptr, *old_ptr;
+	u32 index = *(u32 *)key, ufd;
+
+	if (map_flags != BPF_ANY)
+		return -EINVAL;
+
+	if (index >= array->map.max_entries)
+		return -E2BIG;
+
+	ufd = *(u32 *)value;
+	new_ptr = map->ops->map_fd_get_ptr(map, map_file, ufd);
+	if (IS_ERR(new_ptr))
+		return PTR_ERR(new_ptr);
+
+	old_ptr = xchg(array->ptrs + index, new_ptr);
+	if (old_ptr)
+		map->ops->map_fd_put_ptr(old_ptr);
+
+	return 0;
+}
+
+static int fd_array_map_delete_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	void *old_ptr;
+	u32 index = *(u32 *)key;
+
+	if (index >= array->map.max_entries)
+		return -E2BIG;
+
+	old_ptr = xchg(array->ptrs + index, NULL);
+	if (old_ptr) {
+		map->ops->map_fd_put_ptr(old_ptr);
+		return 0;
+	} else {
+		return -ENOENT;
+	}
+}
+
+static void *prog_fd_array_get_ptr(struct bpf_map *map,
+				   struct file *map_file, int fd)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct bpf_prog *prog = bpf_prog_get(fd);
+
+	if (IS_ERR(prog))
+		return prog;
+
+	if (!bpf_prog_array_compatible(array, prog)) {
+		bpf_prog_put(prog);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return prog;
+}
+
+static void prog_fd_array_put_ptr(void *ptr)
+{
+	bpf_prog_put(ptr);
+}
+
+static u32 prog_fd_array_sys_lookup_elem(void *ptr)
+{
+	return ((struct bpf_prog *)ptr)->aux->id;
+}
+
+/* decrement refcnt of all bpf_progs that are stored in this map */
+static void bpf_fd_array_map_clear(struct bpf_map *map)
+{
+	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);
+}
+
+const struct bpf_map_ops prog_array_map_ops = {
+	.map_alloc_check = fd_array_map_alloc_check,
+	.map_alloc = array_map_alloc,
+	.map_free = fd_array_map_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = fd_array_map_lookup_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = prog_fd_array_get_ptr,
+	.map_fd_put_ptr = prog_fd_array_put_ptr,
+	.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
+	.map_release_uref = bpf_fd_array_map_clear,
+	.map_check_btf = map_check_no_btf,
+};
+
+static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
+						   struct file *map_file)
+{
+	struct bpf_event_entry *ee;
+
+	ee = kzalloc(sizeof(*ee), GFP_ATOMIC);
+	if (ee) {
+		ee->event = perf_file->private_data;
+		ee->perf_file = perf_file;
+		ee->map_file = map_file;
+	}
+
+	return ee;
+}
+
+static void __bpf_event_entry_free(struct rcu_head *rcu)
+{
+	struct bpf_event_entry *ee;
+
+	ee = container_of(rcu, struct bpf_event_entry, rcu);
+	fput(ee->perf_file);
+	kfree(ee);
+}
+
+static void bpf_event_entry_free_rcu(struct bpf_event_entry *ee)
+{
+	call_rcu(&ee->rcu, __bpf_event_entry_free);
+}
+
+static void *perf_event_fd_array_get_ptr(struct bpf_map *map,
+					 struct file *map_file, int fd)
+{
+	struct bpf_event_entry *ee;
+	struct perf_event *event;
+	struct file *perf_file;
+	u64 value;
+
+	perf_file = perf_event_get(fd);
+	if (IS_ERR(perf_file))
+		return perf_file;
+
+	ee = ERR_PTR(-EOPNOTSUPP);
+	event = perf_file->private_data;
+	if (perf_event_read_local(event, &value, NULL, NULL) == -EOPNOTSUPP)
+		goto err_out;
+
+	ee = bpf_event_entry_gen(perf_file, map_file);
+	if (ee)
+		return ee;
+	ee = ERR_PTR(-ENOMEM);
+err_out:
+	fput(perf_file);
+	return ee;
+}
+
+static void perf_event_fd_array_put_ptr(void *ptr)
+{
+	bpf_event_entry_free_rcu(ptr);
+}
+
+static void perf_event_fd_array_release(struct bpf_map *map,
+					struct file *map_file)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct bpf_event_entry *ee;
+	int i;
+
+	rcu_read_lock();
+	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);
+	}
+	rcu_read_unlock();
+}
+
+const struct bpf_map_ops perf_event_array_map_ops = {
+	.map_alloc_check = fd_array_map_alloc_check,
+	.map_alloc = array_map_alloc,
+	.map_free = fd_array_map_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = fd_array_map_lookup_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = perf_event_fd_array_get_ptr,
+	.map_fd_put_ptr = perf_event_fd_array_put_ptr,
+	.map_release = perf_event_fd_array_release,
+	.map_check_btf = map_check_no_btf,
+};
+
+#ifdef CONFIG_CGROUPS
+static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
+				     struct file *map_file /* not used */,
+				     int fd)
+{
+	return cgroup_get_from_fd(fd);
+}
+
+static void cgroup_fd_array_put_ptr(void *ptr)
+{
+	/* cgroup_put free cgrp after a rcu grace period */
+	cgroup_put(ptr);
+}
+
+static void cgroup_fd_array_free(struct bpf_map *map)
+{
+	bpf_fd_array_map_clear(map);
+	fd_array_map_free(map);
+}
+
+const struct bpf_map_ops cgroup_array_map_ops = {
+	.map_alloc_check = fd_array_map_alloc_check,
+	.map_alloc = array_map_alloc,
+	.map_free = cgroup_fd_array_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = fd_array_map_lookup_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = cgroup_fd_array_get_ptr,
+	.map_fd_put_ptr = cgroup_fd_array_put_ptr,
+	.map_check_btf = map_check_no_btf,
+};
+#endif
+
+static struct bpf_map *array_of_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_map *map, *inner_map_meta;
+
+	inner_map_meta = bpf_map_meta_alloc(attr->inner_map_fd);
+	if (IS_ERR(inner_map_meta))
+		return inner_map_meta;
+
+	map = array_map_alloc(attr);
+	if (IS_ERR(map)) {
+		bpf_map_meta_free(inner_map_meta);
+		return map;
+	}
+
+	map->inner_map_meta = inner_map_meta;
+
+	return map;
+}
+
+static void array_of_map_free(struct bpf_map *map)
+{
+	/* map->inner_map_meta is only accessed by syscall which
+	 * is protected by fdget/fdput.
+	 */
+	bpf_map_meta_free(map->inner_map_meta);
+	bpf_fd_array_map_clear(map);
+	fd_array_map_free(map);
+}
+
+static void *array_of_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_map **inner_map = array_map_lookup_elem(map, key);
+
+	if (!inner_map)
+		return NULL;
+
+	return READ_ONCE(*inner_map);
+}
+
+static u32 array_of_map_gen_lookup(struct bpf_map *map,
+				   struct bpf_insn *insn_buf)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u32 elem_size = round_up(map->value_size, 8);
+	struct bpf_insn *insn = insn_buf;
+	const int ret = BPF_REG_0;
+	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));
+	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
+	if (map->unpriv_array) {
+		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 6);
+		*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
+	} else {
+		*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
+	}
+	if (is_power_of_2(elem_size))
+		*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
+	else
+		*insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size);
+	*insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr);
+	*insn++ = BPF_LDX_MEM(BPF_DW, ret, ret, 0);
+	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
+	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
+	*insn++ = BPF_MOV64_IMM(ret, 0);
+
+	return insn - insn_buf;
+}
+
+const struct bpf_map_ops array_of_maps_map_ops = {
+	.map_alloc_check = fd_array_map_alloc_check,
+	.map_alloc = array_of_map_alloc,
+	.map_free = array_of_map_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = array_of_map_lookup_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = bpf_map_fd_get_ptr,
+	.map_fd_put_ptr = bpf_map_fd_put_ptr,
+	.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
+	.map_gen_lookup = array_of_map_gen_lookup,
+	.map_check_btf = map_check_no_btf,
+};

kernel/bpf/bpf_lru_list.c

@@ -0,0 +1,698 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/cpumask.h>
+#include <linux/spinlock.h>
+#include <linux/percpu.h>
+
+#include "bpf_lru_list.h"
+
+#define LOCAL_FREE_TARGET		(128)
+#define LOCAL_NR_SCANS			LOCAL_FREE_TARGET
+
+#define PERCPU_FREE_TARGET		(4)
+#define PERCPU_NR_SCANS			PERCPU_FREE_TARGET
+
+/* Helpers to get the local list index */
+#define LOCAL_LIST_IDX(t)	((t) - BPF_LOCAL_LIST_T_OFFSET)
+#define LOCAL_FREE_LIST_IDX	LOCAL_LIST_IDX(BPF_LRU_LOCAL_LIST_T_FREE)
+#define LOCAL_PENDING_LIST_IDX	LOCAL_LIST_IDX(BPF_LRU_LOCAL_LIST_T_PENDING)
+#define IS_LOCAL_LIST_TYPE(t)	((t) >= BPF_LOCAL_LIST_T_OFFSET)
+
+static int get_next_cpu(int cpu)
+{
+	cpu = cpumask_next(cpu, cpu_possible_mask);
+	if (cpu >= nr_cpu_ids)
+		cpu = cpumask_first(cpu_possible_mask);
+	return cpu;
+}
+
+/* Local list helpers */
+static struct list_head *local_free_list(struct bpf_lru_locallist *loc_l)
+{
+	return &loc_l->lists[LOCAL_FREE_LIST_IDX];
+}
+
+static struct list_head *local_pending_list(struct bpf_lru_locallist *loc_l)
+{
+	return &loc_l->lists[LOCAL_PENDING_LIST_IDX];
+}
+
+/* bpf_lru_node helpers */
+static bool bpf_lru_node_is_ref(const struct bpf_lru_node *node)
+{
+	return node->ref;
+}
+
+static void bpf_lru_list_count_inc(struct bpf_lru_list *l,
+				   enum bpf_lru_list_type type)
+{
+	if (type < NR_BPF_LRU_LIST_COUNT)
+		l->counts[type]++;
+}
+
+static void bpf_lru_list_count_dec(struct bpf_lru_list *l,
+				   enum bpf_lru_list_type type)
+{
+	if (type < NR_BPF_LRU_LIST_COUNT)
+		l->counts[type]--;
+}
+
+static void __bpf_lru_node_move_to_free(struct bpf_lru_list *l,
+					struct bpf_lru_node *node,
+					struct list_head *free_list,
+					enum bpf_lru_list_type tgt_free_type)
+{
+	if (WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(node->type)))
+		return;
+
+	/* If the removing node is the next_inactive_rotation candidate,
+	 * move the next_inactive_rotation pointer also.
+	 */
+	if (&node->list == l->next_inactive_rotation)
+		l->next_inactive_rotation = l->next_inactive_rotation->prev;
+
+	bpf_lru_list_count_dec(l, node->type);
+
+	node->type = tgt_free_type;
+	list_move(&node->list, free_list);
+}
+
+/* Move nodes from local list to the LRU list */
+static void __bpf_lru_node_move_in(struct bpf_lru_list *l,
+				   struct bpf_lru_node *node,
+				   enum bpf_lru_list_type tgt_type)
+{
+	if (WARN_ON_ONCE(!IS_LOCAL_LIST_TYPE(node->type)) ||
+	    WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(tgt_type)))
+		return;
+
+	bpf_lru_list_count_inc(l, tgt_type);
+	node->type = tgt_type;
+	node->ref = 0;
+	list_move(&node->list, &l->lists[tgt_type]);
+}
+
+/* Move nodes between or within active and inactive list (like
+ * active to inactive, inactive to active or tail of active back to
+ * the head of active).
+ */
+static void __bpf_lru_node_move(struct bpf_lru_list *l,
+				struct bpf_lru_node *node,
+				enum bpf_lru_list_type tgt_type)
+{
+	if (WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(node->type)) ||
+	    WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(tgt_type)))
+		return;
+
+	if (node->type != tgt_type) {
+		bpf_lru_list_count_dec(l, node->type);
+		bpf_lru_list_count_inc(l, tgt_type);
+		node->type = tgt_type;
+	}
+	node->ref = 0;
+
+	/* If the moving node is the next_inactive_rotation candidate,
+	 * move the next_inactive_rotation pointer also.
+	 */
+	if (&node->list == l->next_inactive_rotation)
+		l->next_inactive_rotation = l->next_inactive_rotation->prev;
+
+	list_move(&node->list, &l->lists[tgt_type]);
+}
+
+static bool bpf_lru_list_inactive_low(const struct bpf_lru_list *l)
+{
+	return l->counts[BPF_LRU_LIST_T_INACTIVE] <
+		l->counts[BPF_LRU_LIST_T_ACTIVE];
+}
+
+/* Rotate the active list:
+ * 1. Start from tail
+ * 2. If the node has the ref bit set, it will be rotated
+ *    back to the head of active list with the ref bit cleared.
+ *    Give this node one more chance to survive in the active list.
+ * 3. If the ref bit is not set, move it to the head of the
+ *    inactive list.
+ * 4. It will at most scan nr_scans nodes
+ */
+static void __bpf_lru_list_rotate_active(struct bpf_lru *lru,
+					 struct bpf_lru_list *l)
+{
+	struct list_head *active = &l->lists[BPF_LRU_LIST_T_ACTIVE];
+	struct bpf_lru_node *node, *tmp_node, *first_node;
+	unsigned int i = 0;
+
+	first_node = list_first_entry(active, struct bpf_lru_node, list);
+	list_for_each_entry_safe_reverse(node, tmp_node, active, list) {
+		if (bpf_lru_node_is_ref(node))
+			__bpf_lru_node_move(l, node, BPF_LRU_LIST_T_ACTIVE);
+		else
+			__bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE);
+
+		if (++i == lru->nr_scans || node == first_node)
+			break;
+	}
+}
+
+/* Rotate the inactive list.  It starts from the next_inactive_rotation
+ * 1. If the node has ref bit set, it will be moved to the head
+ *    of active list with the ref bit cleared.
+ * 2. If the node does not have ref bit set, it will leave it
+ *    at its current location (i.e. do nothing) so that it can
+ *    be considered during the next inactive_shrink.
+ * 3. It will at most scan nr_scans nodes
+ */
+static void __bpf_lru_list_rotate_inactive(struct bpf_lru *lru,
+					   struct bpf_lru_list *l)
+{
+	struct list_head *inactive = &l->lists[BPF_LRU_LIST_T_INACTIVE];
+	struct list_head *cur, *last, *next = inactive;
+	struct bpf_lru_node *node;
+	unsigned int i = 0;
+
+	if (list_empty(inactive))
+		return;
+
+	last = l->next_inactive_rotation->next;
+	if (last == inactive)
+		last = last->next;
+
+	cur = l->next_inactive_rotation;
+	while (i < lru->nr_scans) {
+		if (cur == inactive) {
+			cur = cur->prev;
+			continue;
+		}
+
+		node = list_entry(cur, struct bpf_lru_node, list);
+		next = cur->prev;
+		if (bpf_lru_node_is_ref(node))
+			__bpf_lru_node_move(l, node, BPF_LRU_LIST_T_ACTIVE);
+		if (cur == last)
+			break;
+		cur = next;
+		i++;
+	}
+
+	l->next_inactive_rotation = next;
+}
+
+/* Shrink the inactive list.  It starts from the tail of the
+ * inactive list and only move the nodes without the ref bit
+ * set to the designated free list.
+ */
+static unsigned int
+__bpf_lru_list_shrink_inactive(struct bpf_lru *lru,
+			       struct bpf_lru_list *l,
+			       unsigned int tgt_nshrink,
+			       struct list_head *free_list,
+			       enum bpf_lru_list_type tgt_free_type)
+{
+	struct list_head *inactive = &l->lists[BPF_LRU_LIST_T_INACTIVE];
+	struct bpf_lru_node *node, *tmp_node;
+	unsigned int nshrinked = 0;
+	unsigned int i = 0;
+
+	list_for_each_entry_safe_reverse(node, tmp_node, inactive, list) {
+		if (bpf_lru_node_is_ref(node)) {
+			__bpf_lru_node_move(l, node, BPF_LRU_LIST_T_ACTIVE);
+		} else if (lru->del_from_htab(lru->del_arg, node)) {
+			__bpf_lru_node_move_to_free(l, node, free_list,
+						    tgt_free_type);
+			if (++nshrinked == tgt_nshrink)
+				break;
+		}
+
+		if (++i == lru->nr_scans)
+			break;
+	}
+
+	return nshrinked;
+}
+
+/* 1. Rotate the active list (if needed)
+ * 2. Always rotate the inactive list
+ */
+static void __bpf_lru_list_rotate(struct bpf_lru *lru, struct bpf_lru_list *l)
+{
+	if (bpf_lru_list_inactive_low(l))
+		__bpf_lru_list_rotate_active(lru, l);
+
+	__bpf_lru_list_rotate_inactive(lru, l);
+}
+
+/* Calls __bpf_lru_list_shrink_inactive() to shrink some
+ * ref-bit-cleared nodes and move them to the designated
+ * free list.
+ *
+ * If it cannot get a free node after calling
+ * __bpf_lru_list_shrink_inactive().  It will just remove
+ * one node from either inactive or active list without
+ * honoring the ref-bit.  It prefers inactive list to active
+ * list in this situation.
+ */
+static unsigned int __bpf_lru_list_shrink(struct bpf_lru *lru,
+					  struct bpf_lru_list *l,
+					  unsigned int tgt_nshrink,
+					  struct list_head *free_list,
+					  enum bpf_lru_list_type tgt_free_type)
+
+{
+	struct bpf_lru_node *node, *tmp_node;
+	struct list_head *force_shrink_list;
+	unsigned int nshrinked;
+
+	nshrinked = __bpf_lru_list_shrink_inactive(lru, l, tgt_nshrink,
+						   free_list, tgt_free_type);
+	if (nshrinked)
+		return nshrinked;
+
+	/* Do a force shrink by ignoring the reference bit */
+	if (!list_empty(&l->lists[BPF_LRU_LIST_T_INACTIVE]))
+		force_shrink_list = &l->lists[BPF_LRU_LIST_T_INACTIVE];
+	else
+		force_shrink_list = &l->lists[BPF_LRU_LIST_T_ACTIVE];
+
+	list_for_each_entry_safe_reverse(node, tmp_node, force_shrink_list,
+					 list) {
+		if (lru->del_from_htab(lru->del_arg, node)) {
+			__bpf_lru_node_move_to_free(l, node, free_list,
+						    tgt_free_type);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+/* Flush the nodes from the local pending list to the LRU list */
+static void __local_list_flush(struct bpf_lru_list *l,
+			       struct bpf_lru_locallist *loc_l)
+{
+	struct bpf_lru_node *node, *tmp_node;
+
+	list_for_each_entry_safe_reverse(node, tmp_node,
+					 local_pending_list(loc_l), list) {
+		if (bpf_lru_node_is_ref(node))
+			__bpf_lru_node_move_in(l, node, BPF_LRU_LIST_T_ACTIVE);
+		else
+			__bpf_lru_node_move_in(l, node,
+					       BPF_LRU_LIST_T_INACTIVE);
+	}
+}
+
+static void bpf_lru_list_push_free(struct bpf_lru_list *l,
+				   struct bpf_lru_node *node)
+{
+	unsigned long flags;
+
+	if (WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(node->type)))
+		return;
+
+	raw_spin_lock_irqsave(&l->lock, flags);
+	__bpf_lru_node_move(l, node, BPF_LRU_LIST_T_FREE);
+	raw_spin_unlock_irqrestore(&l->lock, flags);
+}
+
+static void bpf_lru_list_pop_free_to_local(struct bpf_lru *lru,
+					   struct bpf_lru_locallist *loc_l)
+{
+	struct bpf_lru_list *l = &lru->common_lru.lru_list;
+	struct bpf_lru_node *node, *tmp_node;
+	unsigned int nfree = 0;
+
+	raw_spin_lock(&l->lock);
+
+	__local_list_flush(l, loc_l);
+
+	__bpf_lru_list_rotate(lru, l);
+
+	list_for_each_entry_safe(node, tmp_node, &l->lists[BPF_LRU_LIST_T_FREE],
+				 list) {
+		__bpf_lru_node_move_to_free(l, node, local_free_list(loc_l),
+					    BPF_LRU_LOCAL_LIST_T_FREE);
+		if (++nfree == LOCAL_FREE_TARGET)
+			break;
+	}
+
+	if (nfree < LOCAL_FREE_TARGET)
+		__bpf_lru_list_shrink(lru, l, LOCAL_FREE_TARGET - nfree,
+				      local_free_list(loc_l),
+				      BPF_LRU_LOCAL_LIST_T_FREE);
+
+	raw_spin_unlock(&l->lock);
+}
+
+static void __local_list_add_pending(struct bpf_lru *lru,
+				     struct bpf_lru_locallist *loc_l,
+				     int cpu,
+				     struct bpf_lru_node *node,
+				     u32 hash)
+{
+	*(u32 *)((void *)node + lru->hash_offset) = hash;
+	node->cpu = cpu;
+	node->type = BPF_LRU_LOCAL_LIST_T_PENDING;
+	node->ref = 0;
+	list_add(&node->list, local_pending_list(loc_l));
+}
+
+static struct bpf_lru_node *
+__local_list_pop_free(struct bpf_lru_locallist *loc_l)
+{
+	struct bpf_lru_node *node;
+
+	node = list_first_entry_or_null(local_free_list(loc_l),
+					struct bpf_lru_node,
+					list);
+	if (node)
+		list_del(&node->list);
+
+	return node;
+}
+
+static struct bpf_lru_node *
+__local_list_pop_pending(struct bpf_lru *lru, struct bpf_lru_locallist *loc_l)
+{
+	struct bpf_lru_node *node;
+	bool force = false;
+
+ignore_ref:
+	/* Get from the tail (i.e. older element) of the pending list. */
+	list_for_each_entry_reverse(node, local_pending_list(loc_l),
+				    list) {
+		if ((!bpf_lru_node_is_ref(node) || force) &&
+		    lru->del_from_htab(lru->del_arg, node)) {
+			list_del(&node->list);
+			return node;
+		}
+	}
+
+	if (!force) {
+		force = true;
+		goto ignore_ref;
+	}
+
+	return NULL;
+}
+
+static struct bpf_lru_node *bpf_percpu_lru_pop_free(struct bpf_lru *lru,
+						    u32 hash)
+{
+	struct list_head *free_list;
+	struct bpf_lru_node *node = NULL;
+	struct bpf_lru_list *l;
+	unsigned long flags;
+	int cpu = raw_smp_processor_id();
+
+	l = per_cpu_ptr(lru->percpu_lru, cpu);
+
+	raw_spin_lock_irqsave(&l->lock, flags);
+
+	__bpf_lru_list_rotate(lru, l);
+
+	free_list = &l->lists[BPF_LRU_LIST_T_FREE];
+	if (list_empty(free_list))
+		__bpf_lru_list_shrink(lru, l, PERCPU_FREE_TARGET, free_list,
+				      BPF_LRU_LIST_T_FREE);
+
+	if (!list_empty(free_list)) {
+		node = list_first_entry(free_list, struct bpf_lru_node, list);
+		*(u32 *)((void *)node + lru->hash_offset) = hash;
+		node->ref = 0;
+		__bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE);
+	}
+
+	raw_spin_unlock_irqrestore(&l->lock, flags);
+
+	return node;
+}
+
+static struct bpf_lru_node *bpf_common_lru_pop_free(struct bpf_lru *lru,
+						    u32 hash)
+{
+	struct bpf_lru_locallist *loc_l, *steal_loc_l;
+	struct bpf_common_lru *clru = &lru->common_lru;
+	struct bpf_lru_node *node;
+	int steal, first_steal;
+	unsigned long flags;
+	int cpu = raw_smp_processor_id();
+
+	loc_l = per_cpu_ptr(clru->local_list, cpu);
+
+	raw_spin_lock_irqsave(&loc_l->lock, flags);
+
+	node = __local_list_pop_free(loc_l);
+	if (!node) {
+		bpf_lru_list_pop_free_to_local(lru, loc_l);
+		node = __local_list_pop_free(loc_l);
+	}
+
+	if (node)
+		__local_list_add_pending(lru, loc_l, cpu, node, hash);
+
+	raw_spin_unlock_irqrestore(&loc_l->lock, flags);
+
+	if (node)
+		return node;
+
+	/* No free nodes found from the local free list and
+	 * the global LRU list.
+	 *
+	 * Steal from the local free/pending list of the
+	 * current CPU and remote CPU in RR.  It starts
+	 * with the loc_l->next_steal CPU.
+	 */
+
+	first_steal = loc_l->next_steal;
+	steal = first_steal;
+	do {
+		steal_loc_l = per_cpu_ptr(clru->local_list, steal);
+
+		raw_spin_lock_irqsave(&steal_loc_l->lock, flags);
+
+		node = __local_list_pop_free(steal_loc_l);
+		if (!node)
+			node = __local_list_pop_pending(lru, steal_loc_l);
+
+		raw_spin_unlock_irqrestore(&steal_loc_l->lock, flags);
+
+		steal = get_next_cpu(steal);
+	} while (!node && steal != first_steal);
+
+	loc_l->next_steal = steal;
+
+	if (node) {
+		raw_spin_lock_irqsave(&loc_l->lock, flags);
+		__local_list_add_pending(lru, loc_l, cpu, node, hash);
+		raw_spin_unlock_irqrestore(&loc_l->lock, flags);
+	}
+
+	return node;
+}
+
+struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash)
+{
+	if (lru->percpu)
+		return bpf_percpu_lru_pop_free(lru, hash);
+	else
+		return bpf_common_lru_pop_free(lru, hash);
+}
+
+static void bpf_common_lru_push_free(struct bpf_lru *lru,
+				     struct bpf_lru_node *node)
+{
+	u8 node_type = READ_ONCE(node->type);
+	unsigned long flags;
+
+	if (WARN_ON_ONCE(node_type == BPF_LRU_LIST_T_FREE) ||
+	    WARN_ON_ONCE(node_type == BPF_LRU_LOCAL_LIST_T_FREE))
+		return;
+
+	if (node_type == BPF_LRU_LOCAL_LIST_T_PENDING) {
+		struct bpf_lru_locallist *loc_l;
+
+		loc_l = per_cpu_ptr(lru->common_lru.local_list, node->cpu);
+
+		raw_spin_lock_irqsave(&loc_l->lock, flags);
+
+		if (unlikely(node->type != BPF_LRU_LOCAL_LIST_T_PENDING)) {
+			raw_spin_unlock_irqrestore(&loc_l->lock, flags);
+			goto check_lru_list;
+		}
+
+		node->type = BPF_LRU_LOCAL_LIST_T_FREE;
+		node->ref = 0;
+		list_move(&node->list, local_free_list(loc_l));
+
+		raw_spin_unlock_irqrestore(&loc_l->lock, flags);
+		return;
+	}
+
+check_lru_list:
+	bpf_lru_list_push_free(&lru->common_lru.lru_list, node);
+}
+
+static void bpf_percpu_lru_push_free(struct bpf_lru *lru,
+				     struct bpf_lru_node *node)
+{
+	struct bpf_lru_list *l;
+	unsigned long flags;
+
+	l = per_cpu_ptr(lru->percpu_lru, node->cpu);
+
+	raw_spin_lock_irqsave(&l->lock, flags);
+
+	__bpf_lru_node_move(l, node, BPF_LRU_LIST_T_FREE);
+
+	raw_spin_unlock_irqrestore(&l->lock, flags);
+}
+
+void bpf_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node)
+{
+	if (lru->percpu)
+		bpf_percpu_lru_push_free(lru, node);
+	else
+		bpf_common_lru_push_free(lru, node);
+}
+
+static void bpf_common_lru_populate(struct bpf_lru *lru, void *buf,
+				    u32 node_offset, u32 elem_size,
+				    u32 nr_elems)
+{
+	struct bpf_lru_list *l = &lru->common_lru.lru_list;
+	u32 i;
+
+	for (i = 0; i < nr_elems; i++) {
+		struct bpf_lru_node *node;
+
+		node = (struct bpf_lru_node *)(buf + node_offset);
+		node->type = BPF_LRU_LIST_T_FREE;
+		node->ref = 0;
+		list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]);
+		buf += elem_size;
+	}
+}
+
+static void bpf_percpu_lru_populate(struct bpf_lru *lru, void *buf,
+				    u32 node_offset, u32 elem_size,
+				    u32 nr_elems)
+{
+	u32 i, pcpu_entries;
+	int cpu;
+	struct bpf_lru_list *l;
+
+	pcpu_entries = nr_elems / num_possible_cpus();
+
+	i = 0;
+
+	for_each_possible_cpu(cpu) {
+		struct bpf_lru_node *node;
+
+		l = per_cpu_ptr(lru->percpu_lru, cpu);
+again:
+		node = (struct bpf_lru_node *)(buf + node_offset);
+		node->cpu = cpu;
+		node->type = BPF_LRU_LIST_T_FREE;
+		node->ref = 0;
+		list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]);
+		i++;
+		buf += elem_size;
+		if (i == nr_elems)
+			break;
+		if (i % pcpu_entries)
+			goto again;
+	}
+}
+
+void bpf_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset,
+		      u32 elem_size, u32 nr_elems)
+{
+	if (lru->percpu)
+		bpf_percpu_lru_populate(lru, buf, node_offset, elem_size,
+					nr_elems);
+	else
+		bpf_common_lru_populate(lru, buf, node_offset, elem_size,
+					nr_elems);
+}
+
+static void bpf_lru_locallist_init(struct bpf_lru_locallist *loc_l, int cpu)
+{
+	int i;
+
+	for (i = 0; i < NR_BPF_LRU_LOCAL_LIST_T; i++)
+		INIT_LIST_HEAD(&loc_l->lists[i]);
+
+	loc_l->next_steal = cpu;
+
+	raw_spin_lock_init(&loc_l->lock);
+}
+
+static void bpf_lru_list_init(struct bpf_lru_list *l)
+{
+	int i;
+
+	for (i = 0; i < NR_BPF_LRU_LIST_T; i++)
+		INIT_LIST_HEAD(&l->lists[i]);
+
+	for (i = 0; i < NR_BPF_LRU_LIST_COUNT; i++)
+		l->counts[i] = 0;
+
+	l->next_inactive_rotation = &l->lists[BPF_LRU_LIST_T_INACTIVE];
+
+	raw_spin_lock_init(&l->lock);
+}
+
+int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset,
+		 del_from_htab_func del_from_htab, void *del_arg)
+{
+	int cpu;
+
+	if (percpu) {
+		lru->percpu_lru = alloc_percpu(struct bpf_lru_list);
+		if (!lru->percpu_lru)
+			return -ENOMEM;
+
+		for_each_possible_cpu(cpu) {
+			struct bpf_lru_list *l;
+
+			l = per_cpu_ptr(lru->percpu_lru, cpu);
+			bpf_lru_list_init(l);
+		}
+		lru->nr_scans = PERCPU_NR_SCANS;
+	} else {
+		struct bpf_common_lru *clru = &lru->common_lru;
+
+		clru->local_list = alloc_percpu(struct bpf_lru_locallist);
+		if (!clru->local_list)
+			return -ENOMEM;
+
+		for_each_possible_cpu(cpu) {
+			struct bpf_lru_locallist *loc_l;
+
+			loc_l = per_cpu_ptr(clru->local_list, cpu);
+			bpf_lru_locallist_init(loc_l, cpu);
+		}
+
+		bpf_lru_list_init(&clru->lru_list);
+		lru->nr_scans = LOCAL_NR_SCANS;
+	}
+
+	lru->percpu = percpu;
+	lru->del_from_htab = del_from_htab;
+	lru->del_arg = del_arg;
+	lru->hash_offset = hash_offset;
+
+	return 0;
+}
+
+void bpf_lru_destroy(struct bpf_lru *lru)
+{
+	if (lru->percpu)
+		free_percpu(lru->percpu_lru);
+	else
+		free_percpu(lru->common_lru.local_list);
+}

kernel/bpf/bpf_lru_list.h

@@ -0,0 +1,85 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef __BPF_LRU_LIST_H_
+#define __BPF_LRU_LIST_H_
+
+#include <linux/list.h>
+#include <linux/spinlock_types.h>
+
+#define NR_BPF_LRU_LIST_T	(3)
+#define NR_BPF_LRU_LIST_COUNT	(2)
+#define NR_BPF_LRU_LOCAL_LIST_T (2)
+#define BPF_LOCAL_LIST_T_OFFSET NR_BPF_LRU_LIST_T
+
+enum bpf_lru_list_type {
+	BPF_LRU_LIST_T_ACTIVE,
+	BPF_LRU_LIST_T_INACTIVE,
+	BPF_LRU_LIST_T_FREE,
+	BPF_LRU_LOCAL_LIST_T_FREE,
+	BPF_LRU_LOCAL_LIST_T_PENDING,
+};
+
+struct bpf_lru_node {
+	struct list_head list;
+	u16 cpu;
+	u8 type;
+	u8 ref;
+};
+
+struct bpf_lru_list {
+	struct list_head lists[NR_BPF_LRU_LIST_T];
+	unsigned int counts[NR_BPF_LRU_LIST_COUNT];
+	/* The next inacitve list rotation starts from here */
+	struct list_head *next_inactive_rotation;
+
+	raw_spinlock_t lock ____cacheline_aligned_in_smp;
+};
+
+struct bpf_lru_locallist {
+	struct list_head lists[NR_BPF_LRU_LOCAL_LIST_T];
+	u16 next_steal;
+	raw_spinlock_t lock;
+};
+
+struct bpf_common_lru {
+	struct bpf_lru_list lru_list;
+	struct bpf_lru_locallist __percpu *local_list;
+};
+
+typedef bool (*del_from_htab_func)(void *arg, struct bpf_lru_node *node);
+
+struct bpf_lru {
+	union {
+		struct bpf_common_lru common_lru;
+		struct bpf_lru_list __percpu *percpu_lru;
+	};
+	del_from_htab_func del_from_htab;
+	void *del_arg;
+	unsigned int hash_offset;
+	unsigned int nr_scans;
+	bool percpu;
+};
+
+static inline void bpf_lru_node_set_ref(struct bpf_lru_node *node)
+{
+	/* ref is an approximation on access frequency.  It does not
+	 * have to be very accurate.  Hence, no protection is used.
+	 */
+	if (!node->ref)
+		node->ref = 1;
+}
+
+int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset,
+		 del_from_htab_func del_from_htab, void *delete_arg);
+void bpf_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset,
+		      u32 elem_size, u32 nr_elems);
+void bpf_lru_destroy(struct bpf_lru *lru);
+struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash);
+void bpf_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node);
+void bpf_lru_promote(struct bpf_lru *lru, struct bpf_lru_node *node);
+
+#endif

kernel/bpf/cgroup.c

@@ -0,0 +1,724 @@
+/*
+ * Functions to manage eBPF programs attached to cgroups
+ *
+ * Copyright (c) 2016 Daniel Mack
+ *
+ * This file is subject to the terms and conditions of version 2 of the GNU
+ * General Public License.  See the file COPYING in the main directory of the
+ * Linux distribution for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/atomic.h>
+#include <linux/cgroup.h>
+#include <linux/slab.h>
+#include <linux/bpf.h>
+#include <linux/bpf-cgroup.h>
+#include <net/sock.h>
+
+DEFINE_STATIC_KEY_FALSE(cgroup_bpf_enabled_key);
+EXPORT_SYMBOL(cgroup_bpf_enabled_key);
+
+/**
+ * cgroup_bpf_put() - put references of all bpf programs
+ * @cgrp: the cgroup to modify
+ */
+void cgroup_bpf_put(struct cgroup *cgrp)
+{
+	unsigned int type;
+
+	for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) {
+		struct list_head *progs = &cgrp->bpf.progs[type];
+		struct bpf_prog_list *pl, *tmp;
+
+		list_for_each_entry_safe(pl, tmp, progs, node) {
+			list_del(&pl->node);
+			bpf_prog_put(pl->prog);
+			bpf_cgroup_storage_unlink(pl->storage);
+			bpf_cgroup_storage_free(pl->storage);
+			kfree(pl);
+			static_branch_dec(&cgroup_bpf_enabled_key);
+		}
+		bpf_prog_array_free(cgrp->bpf.effective[type]);
+	}
+}
+
+/* count number of elements in the list.
+ * it's slow but the list cannot be long
+ */
+static u32 prog_list_length(struct list_head *head)
+{
+	struct bpf_prog_list *pl;
+	u32 cnt = 0;
+
+	list_for_each_entry(pl, head, node) {
+		if (!pl->prog)
+			continue;
+		cnt++;
+	}
+	return cnt;
+}
+
+/* if parent has non-overridable prog attached,
+ * disallow attaching new programs to the descendent cgroup.
+ * if parent has overridable or multi-prog, allow attaching
+ */
+static bool hierarchy_allows_attach(struct cgroup *cgrp,
+				    enum bpf_attach_type type,
+				    u32 new_flags)
+{
+	struct cgroup *p;
+
+	p = cgroup_parent(cgrp);
+	if (!p)
+		return true;
+	do {
+		u32 flags = p->bpf.flags[type];
+		u32 cnt;
+
+		if (flags & BPF_F_ALLOW_MULTI)
+			return true;
+		cnt = prog_list_length(&p->bpf.progs[type]);
+		WARN_ON_ONCE(cnt > 1);
+		if (cnt == 1)
+			return !!(flags & BPF_F_ALLOW_OVERRIDE);
+		p = cgroup_parent(p);
+	} while (p);
+	return true;
+}
+
+/* compute a chain of effective programs for a given cgroup:
+ * start from the list of programs in this cgroup and add
+ * all parent programs.
+ * Note that parent's F_ALLOW_OVERRIDE-type program is yielding
+ * to programs in this cgroup
+ */
+static int compute_effective_progs(struct cgroup *cgrp,
+				   enum bpf_attach_type type,
+				   struct bpf_prog_array __rcu **array)
+{
+	struct bpf_prog_array *progs;
+	struct bpf_prog_list *pl;
+	struct cgroup *p = cgrp;
+	int cnt = 0;
+
+	/* count number of effective programs by walking parents */
+	do {
+		if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
+			cnt += prog_list_length(&p->bpf.progs[type]);
+		p = cgroup_parent(p);
+	} while (p);
+
+	progs = bpf_prog_array_alloc(cnt, GFP_KERNEL);
+	if (!progs)
+		return -ENOMEM;
+
+	/* populate the array with effective progs */
+	cnt = 0;
+	p = cgrp;
+	do {
+		if (cnt > 0 && !(p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
+			continue;
+
+		list_for_each_entry(pl, &p->bpf.progs[type], node) {
+			if (!pl->prog)
+				continue;
+
+			progs->items[cnt].prog = pl->prog;
+			progs->items[cnt].cgroup_storage = pl->storage;
+			cnt++;
+		}
+	} while ((p = cgroup_parent(p)));
+
+	rcu_assign_pointer(*array, progs);
+	return 0;
+}
+
+static void activate_effective_progs(struct cgroup *cgrp,
+				     enum bpf_attach_type type,
+				     struct bpf_prog_array __rcu *array)
+{
+	struct bpf_prog_array __rcu *old_array;
+
+	old_array = xchg(&cgrp->bpf.effective[type], array);
+	/* free prog array after grace period, since __cgroup_bpf_run_*()
+	 * might be still walking the array
+	 */
+	bpf_prog_array_free(old_array);
+}
+
+/**
+ * cgroup_bpf_inherit() - inherit effective programs from parent
+ * @cgrp: the cgroup to modify
+ */
+int cgroup_bpf_inherit(struct cgroup *cgrp)
+{
+/* has to use marco instead of const int, since compiler thinks
+ * that array below is variable length
+ */
+#define	NR ARRAY_SIZE(cgrp->bpf.effective)
+	struct bpf_prog_array __rcu *arrays[NR] = {};
+	int i;
+
+	for (i = 0; i < NR; i++)
+		INIT_LIST_HEAD(&cgrp->bpf.progs[i]);
+
+	for (i = 0; i < NR; i++)
+		if (compute_effective_progs(cgrp, i, &arrays[i]))
+			goto cleanup;
+
+	for (i = 0; i < NR; i++)
+		activate_effective_progs(cgrp, i, arrays[i]);
+
+	return 0;
+cleanup:
+	for (i = 0; i < NR; i++)
+		bpf_prog_array_free(arrays[i]);
+	return -ENOMEM;
+}
+
+static int update_effective_progs(struct cgroup *cgrp,
+				  enum bpf_attach_type type)
+{
+	struct cgroup_subsys_state *css;
+	int err;
+
+	/* allocate and recompute effective prog arrays */
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		struct cgroup *desc = container_of(css, struct cgroup, self);
+
+		err = compute_effective_progs(desc, type, &desc->bpf.inactive);
+		if (err)
+			goto cleanup;
+	}
+
+	/* all allocations were successful. Activate all prog arrays */
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		struct cgroup *desc = container_of(css, struct cgroup, self);
+
+		activate_effective_progs(desc, type, desc->bpf.inactive);
+		desc->bpf.inactive = NULL;
+	}
+
+	return 0;
+
+cleanup:
+	/* oom while computing effective. Free all computed effective arrays
+	 * since they were not activated
+	 */
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		struct cgroup *desc = container_of(css, struct cgroup, self);
+
+		bpf_prog_array_free(desc->bpf.inactive);
+		desc->bpf.inactive = NULL;
+	}
+
+	return err;
+}
+
+#define BPF_CGROUP_MAX_PROGS 64
+
+/**
+ * __cgroup_bpf_attach() - Attach the program to a cgroup, and
+ *                         propagate the change to descendants
+ * @cgrp: The cgroup which descendants to traverse
+ * @prog: A program to attach
+ * @type: Type of attach operation
+ *
+ * Must be called with cgroup_mutex held.
+ */
+int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+			enum bpf_attach_type type, u32 flags)
+{
+	struct list_head *progs = &cgrp->bpf.progs[type];
+	struct bpf_prog *old_prog = NULL;
+	struct bpf_cgroup_storage *storage, *old_storage = NULL;
+	struct bpf_prog_list *pl;
+	bool pl_was_allocated;
+	int err;
+
+	if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI))
+		/* invalid combination */
+		return -EINVAL;
+
+	if (!hierarchy_allows_attach(cgrp, type, flags))
+		return -EPERM;
+
+	if (!list_empty(progs) && cgrp->bpf.flags[type] != flags)
+		/* Disallow attaching non-overridable on top
+		 * of existing overridable in this cgroup.
+		 * Disallow attaching multi-prog if overridable or none
+		 */
+		return -EPERM;
+
+	if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS)
+		return -E2BIG;
+
+	storage = bpf_cgroup_storage_alloc(prog);
+	if (IS_ERR(storage))
+		return -ENOMEM;
+
+	if (flags & BPF_F_ALLOW_MULTI) {
+		list_for_each_entry(pl, progs, node) {
+			if (pl->prog == prog) {
+				/* disallow attaching the same prog twice */
+				bpf_cgroup_storage_free(storage);
+				return -EINVAL;
+			}
+		}
+
+		pl = kmalloc(sizeof(*pl), GFP_KERNEL);
+		if (!pl) {
+			bpf_cgroup_storage_free(storage);
+			return -ENOMEM;
+		}
+
+		pl_was_allocated = true;
+		pl->prog = prog;
+		pl->storage = storage;
+		list_add_tail(&pl->node, progs);
+	} else {
+		if (list_empty(progs)) {
+			pl = kmalloc(sizeof(*pl), GFP_KERNEL);
+			if (!pl) {
+				bpf_cgroup_storage_free(storage);
+				return -ENOMEM;
+			}
+			pl_was_allocated = true;
+			list_add_tail(&pl->node, progs);
+		} else {
+			pl = list_first_entry(progs, typeof(*pl), node);
+			old_prog = pl->prog;
+			old_storage = pl->storage;
+			bpf_cgroup_storage_unlink(old_storage);
+			pl_was_allocated = false;
+		}
+		pl->prog = prog;
+		pl->storage = storage;
+	}
+
+	cgrp->bpf.flags[type] = flags;
+
+	err = update_effective_progs(cgrp, type);
+	if (err)
+		goto cleanup;
+
+	static_branch_inc(&cgroup_bpf_enabled_key);
+	if (old_storage)
+		bpf_cgroup_storage_free(old_storage);
+	if (old_prog) {
+		bpf_prog_put(old_prog);
+		static_branch_dec(&cgroup_bpf_enabled_key);
+	}
+	bpf_cgroup_storage_link(storage, cgrp, type);
+	return 0;
+
+cleanup:
+	/* and cleanup the prog list */
+	pl->prog = old_prog;
+	bpf_cgroup_storage_free(pl->storage);
+	pl->storage = old_storage;
+	bpf_cgroup_storage_link(old_storage, cgrp, type);
+	if (pl_was_allocated) {
+		list_del(&pl->node);
+		kfree(pl);
+	}
+	return err;
+}
+
+/**
+ * __cgroup_bpf_detach() - Detach the program from a cgroup, and
+ *                         propagate the change to descendants
+ * @cgrp: The cgroup which descendants to traverse
+ * @prog: A program to detach or NULL
+ * @type: Type of detach operation
+ *
+ * Must be called with cgroup_mutex held.
+ */
+int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+			enum bpf_attach_type type, u32 unused_flags)
+{
+	struct list_head *progs = &cgrp->bpf.progs[type];
+	u32 flags = cgrp->bpf.flags[type];
+	struct bpf_prog *old_prog = NULL;
+	struct bpf_prog_list *pl;
+	int err;
+
+	if (flags & BPF_F_ALLOW_MULTI) {
+		if (!prog)
+			/* to detach MULTI prog the user has to specify valid FD
+			 * of the program to be detached
+			 */
+			return -EINVAL;
+	} else {
+		if (list_empty(progs))
+			/* report error when trying to detach and nothing is attached */
+			return -ENOENT;
+	}
+
+	if (flags & BPF_F_ALLOW_MULTI) {
+		/* find the prog and detach it */
+		list_for_each_entry(pl, progs, node) {
+			if (pl->prog != prog)
+				continue;
+			old_prog = prog;
+			/* mark it deleted, so it's ignored while
+			 * recomputing effective
+			 */
+			pl->prog = NULL;
+			break;
+		}
+		if (!old_prog)
+			return -ENOENT;
+	} else {
+		/* to maintain backward compatibility NONE and OVERRIDE cgroups
+		 * allow detaching with invalid FD (prog==NULL)
+		 */
+		pl = list_first_entry(progs, typeof(*pl), node);
+		old_prog = pl->prog;
+		pl->prog = NULL;
+	}
+
+	err = update_effective_progs(cgrp, type);
+	if (err)
+		goto cleanup;
+
+	/* now can actually delete it from this cgroup list */
+	list_del(&pl->node);
+	bpf_cgroup_storage_unlink(pl->storage);
+	bpf_cgroup_storage_free(pl->storage);
+	kfree(pl);
+	if (list_empty(progs))
+		/* last program was detached, reset flags to zero */
+		cgrp->bpf.flags[type] = 0;
+
+	bpf_prog_put(old_prog);
+	static_branch_dec(&cgroup_bpf_enabled_key);
+	return 0;
+
+cleanup:
+	/* and restore back old_prog */
+	pl->prog = old_prog;
+	return err;
+}
+
+/* Must be called with cgroup_mutex held to avoid races. */
+int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+		       union bpf_attr __user *uattr)
+{
+	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
+	enum bpf_attach_type type = attr->query.attach_type;
+	struct list_head *progs = &cgrp->bpf.progs[type];
+	u32 flags = cgrp->bpf.flags[type];
+	int cnt, ret = 0, i;
+
+	if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE)
+		cnt = bpf_prog_array_length(cgrp->bpf.effective[type]);
+	else
+		cnt = prog_list_length(progs);
+
+	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
+		return -EFAULT;
+	if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt)))
+		return -EFAULT;
+	if (attr->query.prog_cnt == 0 || !prog_ids || !cnt)
+		/* return early if user requested only program count + flags */
+		return 0;
+	if (attr->query.prog_cnt < cnt) {
+		cnt = attr->query.prog_cnt;
+		ret = -ENOSPC;
+	}
+
+	if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) {
+		return bpf_prog_array_copy_to_user(cgrp->bpf.effective[type],
+						   prog_ids, cnt);
+	} else {
+		struct bpf_prog_list *pl;
+		u32 id;
+
+		i = 0;
+		list_for_each_entry(pl, progs, node) {
+			id = pl->prog->aux->id;
+			if (copy_to_user(prog_ids + i, &id, sizeof(id)))
+				return -EFAULT;
+			if (++i == cnt)
+				break;
+		}
+	}
+	return ret;
+}
+
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+			   enum bpf_prog_type ptype, struct bpf_prog *prog)
+{
+	struct cgroup *cgrp;
+	int ret;
+
+	cgrp = cgroup_get_from_fd(attr->target_fd);
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+
+	ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+				attr->attach_flags);
+	cgroup_put(cgrp);
+	return ret;
+}
+
+int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
+{
+	struct bpf_prog *prog;
+	struct cgroup *cgrp;
+	int ret;
+
+	cgrp = cgroup_get_from_fd(attr->target_fd);
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+
+	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+	if (IS_ERR(prog))
+		prog = NULL;
+
+	ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
+	if (prog)
+		bpf_prog_put(prog);
+
+	cgroup_put(cgrp);
+	return ret;
+}
+
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+			  union bpf_attr __user *uattr)
+{
+	struct cgroup *cgrp;
+	int ret;
+
+	cgrp = cgroup_get_from_fd(attr->query.target_fd);
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+
+	ret = cgroup_bpf_query(cgrp, attr, uattr);
+
+	cgroup_put(cgrp);
+	return ret;
+}
+
+/**
+ * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
+ * @sk: The socket sending or receiving traffic
+ * @skb: The skb that is being sent or received
+ * @type: The type of program to be exectuted
+ *
+ * If no socket is passed, or the socket is not of type INET or INET6,
+ * this function does nothing and returns 0.
+ *
+ * The program type passed in via @type must be suitable for network
+ * filtering. No further check is performed to assert that.
+ *
+ * This function will return %-EPERM if any if an attached program was found
+ * and if it returned != 1 during execution. In all other cases, 0 is returned.
+ */
+int __cgroup_bpf_run_filter_skb(struct sock *sk,
+				struct sk_buff *skb,
+				enum bpf_attach_type type)
+{
+	unsigned int offset = skb->data - skb_network_header(skb);
+	struct sock *save_sk;
+	struct cgroup *cgrp;
+	int ret;
+
+	if (!sk || !sk_fullsock(sk))
+		return 0;
+
+	if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
+		return 0;
+
+	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	save_sk = skb->sk;
+	skb->sk = sk;
+	__skb_push(skb, offset);
+	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb,
+				 bpf_prog_run_save_cb);
+	__skb_pull(skb, offset);
+	skb->sk = save_sk;
+	return ret == 1 ? 0 : -EPERM;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);
+
+/**
+ * __cgroup_bpf_run_filter_sk() - Run a program on a sock
+ * @sk: sock structure to manipulate
+ * @type: The type of program to be exectuted
+ *
+ * socket is passed is expected to be of type INET or INET6.
+ *
+ * The program type passed in via @type must be suitable for sock
+ * filtering. No further check is performed to assert that.
+ *
+ * This function will return %-EPERM if any if an attached program was found
+ * and if it returned != 1 during execution. In all other cases, 0 is returned.
+ */
+int __cgroup_bpf_run_filter_sk(struct sock *sk,
+			       enum bpf_attach_type type)
+{
+	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	int ret;
+
+	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sk, BPF_PROG_RUN);
+	return ret == 1 ? 0 : -EPERM;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
+
+/**
+ * __cgroup_bpf_run_filter_sock_addr() - Run a program on a sock and
+ *                                       provided by user sockaddr
+ * @sk: sock struct that will use sockaddr
+ * @uaddr: sockaddr struct provided by user
+ * @type: The type of program to be exectuted
+ * @t_ctx: Pointer to attach type specific context
+ *
+ * socket is expected to be of type INET or INET6.
+ *
+ * This function will return %-EPERM if an attached program is found and
+ * returned value != 1 during execution. In all other cases, 0 is returned.
+ */
+int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
+				      struct sockaddr *uaddr,
+				      enum bpf_attach_type type,
+				      void *t_ctx)
+{
+	struct bpf_sock_addr_kern ctx = {
+		.sk = sk,
+		.uaddr = uaddr,
+		.t_ctx = t_ctx,
+	};
+	struct sockaddr_storage unspec;
+	struct cgroup *cgrp;
+	int ret;
+
+	/* Check socket family since not all sockets represent network
+	 * endpoint (e.g. AF_UNIX).
+	 */
+	if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
+		return 0;
+
+	if (!ctx.uaddr) {
+		memset(&unspec, 0, sizeof(unspec));
+		ctx.uaddr = (struct sockaddr *)&unspec;
+	}
+
+	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN);
+
+	return ret == 1 ? 0 : -EPERM;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);
+
+/**
+ * __cgroup_bpf_run_filter_sock_ops() - Run a program on a sock
+ * @sk: socket to get cgroup from
+ * @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains
+ * sk with connection information (IP addresses, etc.) May not contain
+ * cgroup info if it is a req sock.
+ * @type: The type of program to be exectuted
+ *
+ * socket passed is expected to be of type INET or INET6.
+ *
+ * The program type passed in via @type must be suitable for sock_ops
+ * filtering. No further check is performed to assert that.
+ *
+ * This function will return %-EPERM if any if an attached program was found
+ * and if it returned != 1 during execution. In all other cases, 0 is returned.
+ */
+int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
+				     struct bpf_sock_ops_kern *sock_ops,
+				     enum bpf_attach_type type)
+{
+	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	int ret;
+
+	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sock_ops,
+				 BPF_PROG_RUN);
+	return ret == 1 ? 0 : -EPERM;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops);
+
+int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
+				      short access, enum bpf_attach_type type)
+{
+	struct cgroup *cgrp;
+	struct bpf_cgroup_dev_ctx ctx = {
+		.access_type = (access << 16) | dev_type,
+		.major = major,
+		.minor = minor,
+	};
+	int allow = 1;
+
+	rcu_read_lock();
+	cgrp = task_dfl_cgroup(current);
+	allow = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx,
+				   BPF_PROG_RUN);
+	rcu_read_unlock();
+
+	return !allow;
+}
+EXPORT_SYMBOL(__cgroup_bpf_check_dev_permission);
+
+static const struct bpf_func_proto *
+cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	switch (func_id) {
+	case BPF_FUNC_map_lookup_elem:
+		return &bpf_map_lookup_elem_proto;
+	case BPF_FUNC_map_update_elem:
+		return &bpf_map_update_elem_proto;
+	case BPF_FUNC_map_delete_elem:
+		return &bpf_map_delete_elem_proto;
+	case BPF_FUNC_get_current_uid_gid:
+		return &bpf_get_current_uid_gid_proto;
+	case BPF_FUNC_get_local_storage:
+		return &bpf_get_local_storage_proto;
+	case BPF_FUNC_trace_printk:
+		if (capable(CAP_SYS_ADMIN))
+			return bpf_get_trace_printk_proto();
+	default:
+		return NULL;
+	}
+}
+
+static bool cgroup_dev_is_valid_access(int off, int size,
+				       enum bpf_access_type type,
+				       const struct bpf_prog *prog,
+				       struct bpf_insn_access_aux *info)
+{
+	const int size_default = sizeof(__u32);
+
+	if (type == BPF_WRITE)
+		return false;
+
+	if (off < 0 || off + size > sizeof(struct bpf_cgroup_dev_ctx))
+		return false;
+	/* The verifier guarantees that size > 0. */
+	if (off % size != 0)
+		return false;
+
+	switch (off) {
+	case bpf_ctx_range(struct bpf_cgroup_dev_ctx, access_type):
+		bpf_ctx_record_field_size(info, size_default);
+		if (!bpf_ctx_narrow_access_ok(off, size, size_default))
+			return false;
+		break;
+	default:
+		if (size != size_default)
+			return false;
+	}
+
+	return true;
+}
+
+const struct bpf_prog_ops cg_dev_prog_ops = {
+};
+
+const struct bpf_verifier_ops cg_dev_verifier_ops = {
+	.get_func_proto		= cgroup_dev_func_proto,
+	.is_valid_access	= cgroup_dev_is_valid_access,
+};

kernel/bpf/cpumap.c

@@ -0,0 +1,682 @@
+/* bpf/cpumap.c
+ *
+ * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
+ * Released under terms in GPL version 2.  See COPYING.
+ */
+
+/* The 'cpumap' is primarily used as a backend map for XDP BPF helper
+ * call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'.
+ *
+ * Unlike devmap which redirects XDP frames out another NIC device,
+ * this map type redirects raw XDP frames to another CPU.  The remote
+ * CPU will do SKB-allocation and call the normal network stack.
+ *
+ * This is a scalability and isolation mechanism, that allow
+ * separating the early driver network XDP layer, from the rest of the
+ * netstack, and assigning dedicated CPUs for this stage.  This
+ * basically allows for 10G wirespeed pre-filtering via bpf.
+ */
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/ptr_ring.h>
+#include <net/xdp.h>
+
+#include <linux/sched.h>
+#include <linux/workqueue.h>
+#include <linux/kthread.h>
+#include <linux/capability.h>
+#include <trace/events/xdp.h>
+
+#include <linux/netdevice.h>   /* netif_receive_skb_core */
+#include <linux/etherdevice.h> /* eth_type_trans */
+
+/* General idea: XDP packets getting XDP redirected to another CPU,
+ * will maximum be stored/queued for one driver ->poll() call.  It is
+ * guaranteed that setting flush bit and flush operation happen on
+ * same CPU.  Thus, cpu_map_flush operation can deduct via this_cpu_ptr()
+ * which queue in bpf_cpu_map_entry contains packets.
+ */
+
+#define CPU_MAP_BULK_SIZE 8  /* 8 == one cacheline on 64-bit archs */
+struct xdp_bulk_queue {
+	void *q[CPU_MAP_BULK_SIZE];
+	unsigned int count;
+};
+
+/* Struct for every remote "destination" CPU in map */
+struct bpf_cpu_map_entry {
+	u32 cpu;    /* kthread CPU and map index */
+	int map_id; /* Back reference to map */
+	u32 qsize;  /* Queue size placeholder for map lookup */
+
+	/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
+	struct xdp_bulk_queue __percpu *bulkq;
+
+	/* Queue with potential multi-producers, and single-consumer kthread */
+	struct ptr_ring *queue;
+	struct task_struct *kthread;
+	struct work_struct kthread_stop_wq;
+
+	atomic_t refcnt; /* Control when this struct can be free'ed */
+	struct rcu_head rcu;
+};
+
+struct bpf_cpu_map {
+	struct bpf_map map;
+	/* Below members specific for map type */
+	struct bpf_cpu_map_entry **cpu_map;
+	unsigned long __percpu *flush_needed;
+};
+
+static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
+			     struct xdp_bulk_queue *bq, bool in_napi_ctx);
+
+static u64 cpu_map_bitmap_size(const union bpf_attr *attr)
+{
+	return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long);
+}
+
+static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_cpu_map *cmap;
+	int err = -ENOMEM;
+	u64 cost;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	/* check sanity of attributes */
+	if (attr->max_entries == 0 || attr->key_size != 4 ||
+	    attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+		return ERR_PTR(-EINVAL);
+
+	cmap = kzalloc(sizeof(*cmap), GFP_USER);
+	if (!cmap)
+		return ERR_PTR(-ENOMEM);
+
+	bpf_map_init_from_attr(&cmap->map, attr);
+
+	/* Pre-limit array size based on NR_CPUS, not final CPU check */
+	if (cmap->map.max_entries > NR_CPUS) {
+		err = -E2BIG;
+		goto free_cmap;
+	}
+
+	/* make sure page count doesn't overflow */
+	cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *);
+	cost += cpu_map_bitmap_size(attr) * num_possible_cpus();
+	if (cost >= U32_MAX - PAGE_SIZE)
+		goto free_cmap;
+	cmap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	/* Notice returns -EPERM on if map size is larger than memlock limit */
+	ret = bpf_map_precharge_memlock(cmap->map.pages);
+	if (ret) {
+		err = ret;
+		goto free_cmap;
+	}
+
+	/* A per cpu bitfield with a bit per possible CPU in map  */
+	cmap->flush_needed = __alloc_percpu(cpu_map_bitmap_size(attr),
+					    __alignof__(unsigned long));
+	if (!cmap->flush_needed)
+		goto free_cmap;
+
+	/* Alloc array for possible remote "destination" CPUs */
+	cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries *
+					   sizeof(struct bpf_cpu_map_entry *),
+					   cmap->map.numa_node);
+	if (!cmap->cpu_map)
+		goto free_percpu;
+
+	return &cmap->map;
+free_percpu:
+	free_percpu(cmap->flush_needed);
+free_cmap:
+	kfree(cmap);
+	return ERR_PTR(err);
+}
+
+static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
+{
+	atomic_inc(&rcpu->refcnt);
+}
+
+/* called from workqueue, to workaround syscall using preempt_disable */
+static void cpu_map_kthread_stop(struct work_struct *work)
+{
+	struct bpf_cpu_map_entry *rcpu;
+
+	rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
+
+	/* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
+	 * as it waits until all in-flight call_rcu() callbacks complete.
+	 */
+	rcu_barrier();
+
+	/* kthread_stop will wake_up_process and wait for it to complete */
+	kthread_stop(rcpu->kthread);
+}
+
+static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
+					 struct xdp_frame *xdpf)
+{
+	unsigned int hard_start_headroom;
+	unsigned int frame_size;
+	void *pkt_data_start;
+	struct sk_buff *skb;
+
+	/* Part of headroom was reserved to xdpf */
+	hard_start_headroom = sizeof(struct xdp_frame) +  xdpf->headroom;
+
+	/* build_skb need to place skb_shared_info after SKB end, and
+	 * also want to know the memory "truesize".  Thus, need to
+	 * know the memory frame size backing xdp_buff.
+	 *
+	 * XDP was designed to have PAGE_SIZE frames, but this
+	 * assumption is not longer true with ixgbe and i40e.  It
+	 * would be preferred to set frame_size to 2048 or 4096
+	 * depending on the driver.
+	 *   frame_size = 2048;
+	 *   frame_len  = frame_size - sizeof(*xdp_frame);
+	 *
+	 * Instead, with info avail, skb_shared_info in placed after
+	 * packet len.  This, unfortunately fakes the truesize.
+	 * Another disadvantage of this approach, the skb_shared_info
+	 * is not at a fixed memory location, with mixed length
+	 * packets, which is bad for cache-line hotness.
+	 */
+	frame_size = SKB_DATA_ALIGN(xdpf->len + hard_start_headroom) +
+		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+	pkt_data_start = xdpf->data - hard_start_headroom;
+	skb = build_skb(pkt_data_start, frame_size);
+	if (!skb)
+		return NULL;
+
+	skb_reserve(skb, hard_start_headroom);
+	__skb_put(skb, xdpf->len);
+	if (xdpf->metasize)
+		skb_metadata_set(skb, xdpf->metasize);
+
+	/* Essential SKB info: protocol and skb->dev */
+	skb->protocol = eth_type_trans(skb, xdpf->dev_rx);
+
+	/* Optional SKB info, currently missing:
+	 * - HW checksum info		(skb->ip_summed)
+	 * - HW RX hash			(skb_set_hash)
+	 * - RX ring dev queue index	(skb_record_rx_queue)
+	 */
+
+	/* Allow SKB to reuse area used by xdp_frame */
+	xdp_scrub_frame(xdpf);
+
+	return skb;
+}
+
+static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
+{
+	/* The tear-down procedure should have made sure that queue is
+	 * empty.  See __cpu_map_entry_replace() and work-queue
+	 * invoked cpu_map_kthread_stop(). Catch any broken behaviour
+	 * gracefully and warn once.
+	 */
+	struct xdp_frame *xdpf;
+
+	while ((xdpf = ptr_ring_consume(ring)))
+		if (WARN_ON_ONCE(xdpf))
+			xdp_return_frame(xdpf);
+}
+
+static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
+{
+	if (atomic_dec_and_test(&rcpu->refcnt)) {
+		/* The queue should be empty at this point */
+		__cpu_map_ring_cleanup(rcpu->queue);
+		ptr_ring_cleanup(rcpu->queue, NULL);
+		kfree(rcpu->queue);
+		kfree(rcpu);
+	}
+}
+
+static int cpu_map_kthread_run(void *data)
+{
+	struct bpf_cpu_map_entry *rcpu = data;
+
+	set_current_state(TASK_INTERRUPTIBLE);
+
+	/* When kthread gives stop order, then rcpu have been disconnected
+	 * from map, thus no new packets can enter. Remaining in-flight
+	 * per CPU stored packets are flushed to this queue.  Wait honoring
+	 * kthread_stop signal until queue is empty.
+	 */
+	while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
+		unsigned int processed = 0, drops = 0, sched = 0;
+		struct xdp_frame *xdpf;
+
+		/* Release CPU reschedule checks */
+		if (__ptr_ring_empty(rcpu->queue)) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			/* Recheck to avoid lost wake-up */
+			if (__ptr_ring_empty(rcpu->queue)) {
+				schedule();
+				sched = 1;
+			} else {
+				__set_current_state(TASK_RUNNING);
+			}
+		} else {
+			sched = cond_resched();
+		}
+
+		/* Process packets in rcpu->queue */
+		local_bh_disable();
+		/*
+		 * The bpf_cpu_map_entry is single consumer, with this
+		 * kthread CPU pinned. Lockless access to ptr_ring
+		 * consume side valid as no-resize allowed of queue.
+		 */
+		while ((xdpf = __ptr_ring_consume(rcpu->queue))) {
+			struct sk_buff *skb;
+			int ret;
+
+			skb = cpu_map_build_skb(rcpu, xdpf);
+			if (!skb) {
+				xdp_return_frame(xdpf);
+				continue;
+			}
+
+			/* Inject into network stack */
+			ret = netif_receive_skb_core(skb);
+			if (ret == NET_RX_DROP)
+				drops++;
+
+			/* Limit BH-disable period */
+			if (++processed == 8)
+				break;
+		}
+		/* Feedback loop via tracepoint */
+		trace_xdp_cpumap_kthread(rcpu->map_id, processed, drops, sched);
+
+		local_bh_enable(); /* resched point, may call do_softirq() */
+	}
+	__set_current_state(TASK_RUNNING);
+
+	put_cpu_map_entry(rcpu);
+	return 0;
+}
+
+static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
+						       int map_id)
+{
+	gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
+	struct bpf_cpu_map_entry *rcpu;
+	int numa, err;
+
+	/* Have map->numa_node, but choose node of redirect target CPU */
+	numa = cpu_to_node(cpu);
+
+	rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa);
+	if (!rcpu)
+		return NULL;
+
+	/* Alloc percpu bulkq */
+	rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq),
+					 sizeof(void *), gfp);
+	if (!rcpu->bulkq)
+		goto free_rcu;
+
+	/* Alloc queue */
+	rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa);
+	if (!rcpu->queue)
+		goto free_bulkq;
+
+	err = ptr_ring_init(rcpu->queue, qsize, gfp);
+	if (err)
+		goto free_queue;
+
+	rcpu->cpu    = cpu;
+	rcpu->map_id = map_id;
+	rcpu->qsize  = qsize;
+
+	/* Setup kthread */
+	rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
+					       "cpumap/%d/map:%d", cpu, map_id);
+	if (IS_ERR(rcpu->kthread))
+		goto free_ptr_ring;
+
+	get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */
+	get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */
+
+	/* Make sure kthread runs on a single CPU */
+	kthread_bind(rcpu->kthread, cpu);
+	wake_up_process(rcpu->kthread);
+
+	return rcpu;
+
+free_ptr_ring:
+	ptr_ring_cleanup(rcpu->queue, NULL);
+free_queue:
+	kfree(rcpu->queue);
+free_bulkq:
+	free_percpu(rcpu->bulkq);
+free_rcu:
+	kfree(rcpu);
+	return NULL;
+}
+
+static void __cpu_map_entry_free(struct rcu_head *rcu)
+{
+	struct bpf_cpu_map_entry *rcpu;
+	int cpu;
+
+	/* This cpu_map_entry have been disconnected from map and one
+	 * RCU graze-period have elapsed.  Thus, XDP cannot queue any
+	 * new packets and cannot change/set flush_needed that can
+	 * find this entry.
+	 */
+	rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu);
+
+	/* Flush remaining packets in percpu bulkq */
+	for_each_online_cpu(cpu) {
+		struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu);
+
+		/* No concurrent bq_enqueue can run at this point */
+		bq_flush_to_queue(rcpu, bq, false);
+	}
+	free_percpu(rcpu->bulkq);
+	/* Cannot kthread_stop() here, last put free rcpu resources */
+	put_cpu_map_entry(rcpu);
+}
+
+/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to
+ * ensure any driver rcu critical sections have completed, but this
+ * does not guarantee a flush has happened yet. Because driver side
+ * rcu_read_lock/unlock only protects the running XDP program.  The
+ * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a
+ * pending flush op doesn't fail.
+ *
+ * The bpf_cpu_map_entry is still used by the kthread, and there can
+ * still be pending packets (in queue and percpu bulkq).  A refcnt
+ * makes sure to last user (kthread_stop vs. call_rcu) free memory
+ * resources.
+ *
+ * The rcu callback __cpu_map_entry_free flush remaining packets in
+ * percpu bulkq to queue.  Due to caller map_delete_elem() disable
+ * preemption, cannot call kthread_stop() to make sure queue is empty.
+ * Instead a work_queue is started for stopping kthread,
+ * cpu_map_kthread_stop, which waits for an RCU graze period before
+ * stopping kthread, emptying the queue.
+ */
+static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
+				    u32 key_cpu, struct bpf_cpu_map_entry *rcpu)
+{
+	struct bpf_cpu_map_entry *old_rcpu;
+
+	old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu);
+	if (old_rcpu) {
+		call_rcu(&old_rcpu->rcu, __cpu_map_entry_free);
+		INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop);
+		schedule_work(&old_rcpu->kthread_stop_wq);
+	}
+}
+
+static int cpu_map_delete_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	u32 key_cpu = *(u32 *)key;
+
+	if (key_cpu >= map->max_entries)
+		return -EINVAL;
+
+	/* notice caller map_delete_elem() use preempt_disable() */
+	__cpu_map_entry_replace(cmap, key_cpu, NULL);
+	return 0;
+}
+
+static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
+			       u64 map_flags)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	struct bpf_cpu_map_entry *rcpu;
+
+	/* Array index key correspond to CPU number */
+	u32 key_cpu = *(u32 *)key;
+	/* Value is the queue size */
+	u32 qsize = *(u32 *)value;
+
+	if (unlikely(map_flags > BPF_EXIST))
+		return -EINVAL;
+	if (unlikely(key_cpu >= cmap->map.max_entries))
+		return -E2BIG;
+	if (unlikely(map_flags == BPF_NOEXIST))
+		return -EEXIST;
+	if (unlikely(qsize > 16384)) /* sanity limit on qsize */
+		return -EOVERFLOW;
+
+	/* Make sure CPU is a valid possible cpu */
+	if (key_cpu >= nr_cpumask_bits || !cpu_possible(key_cpu))
+		return -ENODEV;
+
+	if (qsize == 0) {
+		rcpu = NULL; /* Same as deleting */
+	} else {
+		/* Updating qsize cause re-allocation of bpf_cpu_map_entry */
+		rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id);
+		if (!rcpu)
+			return -ENOMEM;
+	}
+	rcu_read_lock();
+	__cpu_map_entry_replace(cmap, key_cpu, rcpu);
+	rcu_read_unlock();
+	return 0;
+}
+
+static void cpu_map_free(struct bpf_map *map)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	int cpu;
+	u32 i;
+
+	/* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
+	 * so the bpf programs (can be more than one that used this map) were
+	 * disconnected from events. Wait for outstanding critical sections in
+	 * these programs to complete. The rcu critical section only guarantees
+	 * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map.
+	 * It does __not__ ensure pending flush operations (if any) are
+	 * complete.
+	 */
+
+	bpf_clear_redirect_map(map);
+	synchronize_rcu();
+
+	/* To ensure all pending flush operations have completed wait for flush
+	 * bitmap to indicate all flush_needed bits to be zero on _all_ cpus.
+	 * Because the above synchronize_rcu() ensures the map is disconnected
+	 * from the program we can assume no new bits will be set.
+	 */
+	for_each_online_cpu(cpu) {
+		unsigned long *bitmap = per_cpu_ptr(cmap->flush_needed, cpu);
+
+		while (!bitmap_empty(bitmap, cmap->map.max_entries))
+			cond_resched();
+	}
+
+	/* For cpu_map the remote CPUs can still be using the entries
+	 * (struct bpf_cpu_map_entry).
+	 */
+	for (i = 0; i < cmap->map.max_entries; i++) {
+		struct bpf_cpu_map_entry *rcpu;
+
+		rcpu = READ_ONCE(cmap->cpu_map[i]);
+		if (!rcpu)
+			continue;
+
+		/* bq flush and cleanup happens after RCU graze-period */
+		__cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */
+	}
+	free_percpu(cmap->flush_needed);
+	bpf_map_area_free(cmap->cpu_map);
+	kfree(cmap);
+}
+
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	struct bpf_cpu_map_entry *rcpu;
+
+	if (key >= map->max_entries)
+		return NULL;
+
+	rcpu = READ_ONCE(cmap->cpu_map[key]);
+	return rcpu;
+}
+
+static void *cpu_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_cpu_map_entry *rcpu =
+		__cpu_map_lookup_elem(map, *(u32 *)key);
+
+	return rcpu ? &rcpu->qsize : NULL;
+}
+
+static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	u32 index = key ? *(u32 *)key : U32_MAX;
+	u32 *next = next_key;
+
+	if (index >= cmap->map.max_entries) {
+		*next = 0;
+		return 0;
+	}
+
+	if (index == cmap->map.max_entries - 1)
+		return -ENOENT;
+	*next = index + 1;
+	return 0;
+}
+
+const struct bpf_map_ops cpu_map_ops = {
+	.map_alloc		= cpu_map_alloc,
+	.map_free		= cpu_map_free,
+	.map_delete_elem	= cpu_map_delete_elem,
+	.map_update_elem	= cpu_map_update_elem,
+	.map_lookup_elem	= cpu_map_lookup_elem,
+	.map_get_next_key	= cpu_map_get_next_key,
+	.map_check_btf		= map_check_no_btf,
+};
+
+static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
+			     struct xdp_bulk_queue *bq, bool in_napi_ctx)
+{
+	unsigned int processed = 0, drops = 0;
+	const int to_cpu = rcpu->cpu;
+	struct ptr_ring *q;
+	int i;
+
+	if (unlikely(!bq->count))
+		return 0;
+
+	q = rcpu->queue;
+	spin_lock(&q->producer_lock);
+
+	for (i = 0; i < bq->count; i++) {
+		struct xdp_frame *xdpf = bq->q[i];
+		int err;
+
+		err = __ptr_ring_produce(q, xdpf);
+		if (err) {
+			drops++;
+			if (likely(in_napi_ctx))
+				xdp_return_frame_rx_napi(xdpf);
+			else
+				xdp_return_frame(xdpf);
+		}
+		processed++;
+	}
+	bq->count = 0;
+	spin_unlock(&q->producer_lock);
+
+	/* Feedback loop via tracepoints */
+	trace_xdp_cpumap_enqueue(rcpu->map_id, processed, drops, to_cpu);
+	return 0;
+}
+
+/* Runs under RCU-read-side, plus in softirq under NAPI protection.
+ * Thus, safe percpu variable access.
+ */
+static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
+{
+	struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
+
+	if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
+		bq_flush_to_queue(rcpu, bq, true);
+
+	/* Notice, xdp_buff/page MUST be queued here, long enough for
+	 * driver to code invoking us to finished, due to driver
+	 * (e.g. ixgbe) recycle tricks based on page-refcnt.
+	 *
+	 * Thus, incoming xdp_frame is always queued here (else we race
+	 * with another CPU on page-refcnt and remaining driver code).
+	 * Queue time is very short, as driver will invoke flush
+	 * operation, when completing napi->poll call.
+	 */
+	bq->q[bq->count++] = xdpf;
+	return 0;
+}
+
+int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
+		    struct net_device *dev_rx)
+{
+	struct xdp_frame *xdpf;
+
+	xdpf = convert_to_xdp_frame(xdp);
+	if (unlikely(!xdpf))
+		return -EOVERFLOW;
+
+	/* Info needed when constructing SKB on remote CPU */
+	xdpf->dev_rx = dev_rx;
+
+	bq_enqueue(rcpu, xdpf);
+	return 0;
+}
+
+void __cpu_map_insert_ctx(struct bpf_map *map, u32 bit)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed);
+
+	__set_bit(bit, bitmap);
+}
+
+void __cpu_map_flush(struct bpf_map *map)
+{
+	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed);
+	u32 bit;
+
+	/* The napi->poll softirq makes sure __cpu_map_insert_ctx()
+	 * and __cpu_map_flush() happen on same CPU. Thus, the percpu
+	 * bitmap indicate which percpu bulkq have packets.
+	 */
+	for_each_set_bit(bit, bitmap, map->max_entries) {
+		struct bpf_cpu_map_entry *rcpu = READ_ONCE(cmap->cpu_map[bit]);
+		struct xdp_bulk_queue *bq;
+
+		/* This is possible if entry is removed by user space
+		 * between xdp redirect and flush op.
+		 */
+		if (unlikely(!rcpu))
+			continue;
+
+		__clear_bit(bit, bitmap);
+
+		/* Flush all frames in bulkq to real queue */
+		bq = this_cpu_ptr(rcpu->bulkq);
+		bq_flush_to_queue(rcpu, bq, true);
+
+		/* If already running, costs spin_lock_irqsave + smb_mb */
+		wake_up_process(rcpu->kthread);
+	}
+}

kernel/bpf/devmap.c

@@ -0,0 +1,552 @@
+/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+/* Devmaps primary use is as a backend map for XDP BPF helper call
+ * bpf_redirect_map(). Because XDP is mostly concerned with performance we
+ * spent some effort to ensure the datapath with redirect maps does not use
+ * any locking. This is a quick note on the details.
+ *
+ * We have three possible paths to get into the devmap control plane bpf
+ * syscalls, bpf programs, and driver side xmit/flush operations. A bpf syscall
+ * will invoke an update, delete, or lookup operation. To ensure updates and
+ * deletes appear atomic from the datapath side xchg() is used to modify the
+ * netdev_map array. Then because the datapath does a lookup into the netdev_map
+ * array (read-only) from an RCU critical section we use call_rcu() to wait for
+ * an rcu grace period before free'ing the old data structures. This ensures the
+ * datapath always has a valid copy. However, the datapath does a "flush"
+ * operation that pushes any pending packets in the driver outside the RCU
+ * critical section. Each bpf_dtab_netdev tracks these pending operations using
+ * an atomic per-cpu bitmap. The bpf_dtab_netdev object will not be destroyed
+ * until all bits are cleared indicating outstanding flush operations have
+ * completed.
+ *
+ * BPF syscalls may race with BPF program calls on any of the update, delete
+ * or lookup operations. As noted above the xchg() operation also keep the
+ * netdev_map consistent in this case. From the devmap side BPF programs
+ * calling into these operations are the same as multiple user space threads
+ * making system calls.
+ *
+ * Finally, any of the above may race with a netdev_unregister notifier. The
+ * unregister notifier must search for net devices in the map structure that
+ * contain a reference to the net device and remove them. This is a two step
+ * process (a) dereference the bpf_dtab_netdev object in netdev_map and (b)
+ * check to see if the ifindex is the same as the net_device being removed.
+ * When removing the dev a cmpxchg() is used to ensure the correct dev is
+ * removed, in the case of a concurrent update or delete operation it is
+ * possible that the initially referenced dev is no longer in the map. As the
+ * notifier hook walks the map we know that new dev references can not be
+ * added by the user because core infrastructure ensures dev_get_by_index()
+ * calls will fail at this point.
+ */
+#include <linux/bpf.h>
+#include <net/xdp.h>
+#include <linux/filter.h>
+#include <trace/events/xdp.h>
+
+#define DEV_CREATE_FLAG_MASK \
+	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
+#define DEV_MAP_BULK_SIZE 16
+struct xdp_bulk_queue {
+	struct xdp_frame *q[DEV_MAP_BULK_SIZE];
+	struct net_device *dev_rx;
+	unsigned int count;
+};
+
+struct bpf_dtab_netdev {
+	struct net_device *dev; /* must be first member, due to tracepoint */
+	struct bpf_dtab *dtab;
+	unsigned int bit;
+	struct xdp_bulk_queue __percpu *bulkq;
+	struct rcu_head rcu;
+};
+
+struct bpf_dtab {
+	struct bpf_map map;
+	struct bpf_dtab_netdev **netdev_map;
+	unsigned long __percpu *flush_needed;
+	struct list_head list;
+};
+
+static DEFINE_SPINLOCK(dev_map_lock);
+static LIST_HEAD(dev_map_list);
+
+static u64 dev_map_bitmap_size(const union bpf_attr *attr)
+{
+	return BITS_TO_LONGS((u64) attr->max_entries) * sizeof(unsigned long);
+}
+
+static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_dtab *dtab;
+	int err = -EINVAL;
+	u64 cost;
+
+	if (!capable(CAP_NET_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	/* check sanity of attributes */
+	if (attr->max_entries == 0 || attr->key_size != 4 ||
+	    attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK)
+		return ERR_PTR(-EINVAL);
+
+	dtab = kzalloc(sizeof(*dtab), GFP_USER);
+	if (!dtab)
+		return ERR_PTR(-ENOMEM);
+
+	bpf_map_init_from_attr(&dtab->map, attr);
+
+	/* make sure page count doesn't overflow */
+	cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *);
+	cost += dev_map_bitmap_size(attr) * num_possible_cpus();
+	if (cost >= U32_MAX - PAGE_SIZE)
+		goto free_dtab;
+
+	dtab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	/* if map size is larger than memlock limit, reject it early */
+	err = bpf_map_precharge_memlock(dtab->map.pages);
+	if (err)
+		goto free_dtab;
+
+	err = -ENOMEM;
+
+	/* A per cpu bitfield with a bit per possible net device */
+	dtab->flush_needed = __alloc_percpu_gfp(dev_map_bitmap_size(attr),
+						__alignof__(unsigned long),
+						GFP_KERNEL | __GFP_NOWARN);
+	if (!dtab->flush_needed)
+		goto free_dtab;
+
+	dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries *
+					      sizeof(struct bpf_dtab_netdev *),
+					      dtab->map.numa_node);
+	if (!dtab->netdev_map)
+		goto free_dtab;
+
+	spin_lock(&dev_map_lock);
+	list_add_tail_rcu(&dtab->list, &dev_map_list);
+	spin_unlock(&dev_map_lock);
+
+	return &dtab->map;
+free_dtab:
+	free_percpu(dtab->flush_needed);
+	kfree(dtab);
+	return ERR_PTR(err);
+}
+
+static void dev_map_free(struct bpf_map *map)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	int i, cpu;
+
+	/* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
+	 * so the programs (can be more than one that used this map) were
+	 * disconnected from events. Wait for outstanding critical sections in
+	 * these programs to complete. The rcu critical section only guarantees
+	 * no further reads against netdev_map. It does __not__ ensure pending
+	 * flush operations (if any) are complete.
+	 */
+
+	spin_lock(&dev_map_lock);
+	list_del_rcu(&dtab->list);
+	spin_unlock(&dev_map_lock);
+
+	bpf_clear_redirect_map(map);
+	synchronize_rcu();
+
+	/* Make sure prior __dev_map_entry_free() have completed. */
+	rcu_barrier();
+
+	/* To ensure all pending flush operations have completed wait for flush
+	 * bitmap to indicate all flush_needed bits to be zero on _all_ cpus.
+	 * Because the above synchronize_rcu() ensures the map is disconnected
+	 * from the program we can assume no new bits will be set.
+	 */
+	for_each_online_cpu(cpu) {
+		unsigned long *bitmap = per_cpu_ptr(dtab->flush_needed, cpu);
+
+		while (!bitmap_empty(bitmap, dtab->map.max_entries))
+			cond_resched();
+	}
+
+	for (i = 0; i < dtab->map.max_entries; i++) {
+		struct bpf_dtab_netdev *dev;
+
+		dev = dtab->netdev_map[i];
+		if (!dev)
+			continue;
+
+		free_percpu(dev->bulkq);
+		dev_put(dev->dev);
+		kfree(dev);
+	}
+
+	free_percpu(dtab->flush_needed);
+	bpf_map_area_free(dtab->netdev_map);
+	kfree(dtab);
+}
+
+static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	u32 index = key ? *(u32 *)key : U32_MAX;
+	u32 *next = next_key;
+
+	if (index >= dtab->map.max_entries) {
+		*next = 0;
+		return 0;
+	}
+
+	if (index == dtab->map.max_entries - 1)
+		return -ENOENT;
+	*next = index + 1;
+	return 0;
+}
+
+void __dev_map_insert_ctx(struct bpf_map *map, u32 bit)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	unsigned long *bitmap = this_cpu_ptr(dtab->flush_needed);
+
+	__set_bit(bit, bitmap);
+}
+
+static int bq_xmit_all(struct bpf_dtab_netdev *obj,
+		       struct xdp_bulk_queue *bq, u32 flags,
+		       bool in_napi_ctx)
+{
+	struct net_device *dev = obj->dev;
+	int sent = 0, drops = 0, err = 0;
+	int i;
+
+	if (unlikely(!bq->count))
+		return 0;
+
+	for (i = 0; i < bq->count; i++) {
+		struct xdp_frame *xdpf = bq->q[i];
+
+		prefetch(xdpf);
+	}
+
+	sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, flags);
+	if (sent < 0) {
+		err = sent;
+		sent = 0;
+		goto error;
+	}
+	drops = bq->count - sent;
+out:
+	bq->count = 0;
+
+	trace_xdp_devmap_xmit(&obj->dtab->map, obj->bit,
+			      sent, drops, bq->dev_rx, dev, err);
+	bq->dev_rx = NULL;
+	return 0;
+error:
+	/* If ndo_xdp_xmit fails with an errno, no frames have been
+	 * xmit'ed and it's our responsibility to them free all.
+	 */
+	for (i = 0; i < bq->count; i++) {
+		struct xdp_frame *xdpf = bq->q[i];
+
+		/* RX path under NAPI protection, can return frames faster */
+		if (likely(in_napi_ctx))
+			xdp_return_frame_rx_napi(xdpf);
+		else
+			xdp_return_frame(xdpf);
+		drops++;
+	}
+	goto out;
+}
+
+/* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled
+ * from the driver before returning from its napi->poll() routine. The poll()
+ * routine is called either from busy_poll context or net_rx_action signaled
+ * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the
+ * net device can be torn down. On devmap tear down we ensure the ctx bitmap
+ * is zeroed before completing to ensure all flush operations have completed.
+ */
+void __dev_map_flush(struct bpf_map *map)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	unsigned long *bitmap = this_cpu_ptr(dtab->flush_needed);
+	u32 bit;
+
+	rcu_read_lock();
+	for_each_set_bit(bit, bitmap, map->max_entries) {
+		struct bpf_dtab_netdev *dev = READ_ONCE(dtab->netdev_map[bit]);
+		struct xdp_bulk_queue *bq;
+
+		/* This is possible if the dev entry is removed by user space
+		 * between xdp redirect and flush op.
+		 */
+		if (unlikely(!dev))
+			continue;
+
+		bq = this_cpu_ptr(dev->bulkq);
+		bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true);
+
+		__clear_bit(bit, bitmap);
+	}
+	rcu_read_unlock();
+}
+
+/* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or
+ * update happens in parallel here a dev_put wont happen until after reading the
+ * ifindex.
+ */
+struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	struct bpf_dtab_netdev *obj;
+
+	if (key >= map->max_entries)
+		return NULL;
+
+	obj = READ_ONCE(dtab->netdev_map[key]);
+	return obj;
+}
+
+/* Runs under RCU-read-side, plus in softirq under NAPI protection.
+ * Thus, safe percpu variable access.
+ */
+static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
+		      struct net_device *dev_rx)
+
+{
+	struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq);
+
+	if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
+		bq_xmit_all(obj, bq, 0, true);
+
+	/* Ingress dev_rx will be the same for all xdp_frame's in
+	 * bulk_queue, because bq stored per-CPU and must be flushed
+	 * from net_device drivers NAPI func end.
+	 */
+	if (!bq->dev_rx)
+		bq->dev_rx = dev_rx;
+
+	bq->q[bq->count++] = xdpf;
+	return 0;
+}
+
+int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
+		    struct net_device *dev_rx)
+{
+	struct net_device *dev = dst->dev;
+	struct xdp_frame *xdpf;
+	int err;
+
+	if (!dev->netdev_ops->ndo_xdp_xmit)
+		return -EOPNOTSUPP;
+
+	err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+	if (unlikely(err))
+		return err;
+
+	xdpf = convert_to_xdp_frame(xdp);
+	if (unlikely(!xdpf))
+		return -EOVERFLOW;
+
+	return bq_enqueue(dst, xdpf, dev_rx);
+}
+
+int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
+			     struct bpf_prog *xdp_prog)
+{
+	int err;
+
+	err = xdp_ok_fwd_dev(dst->dev, skb->len);
+	if (unlikely(err))
+		return err;
+	skb->dev = dst->dev;
+	generic_xdp_tx(skb, xdp_prog);
+
+	return 0;
+}
+
+static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
+	struct net_device *dev = obj ? obj->dev : NULL;
+
+	return dev ? &dev->ifindex : NULL;
+}
+
+static void dev_map_flush_old(struct bpf_dtab_netdev *dev)
+{
+	if (dev->dev->netdev_ops->ndo_xdp_xmit) {
+		struct xdp_bulk_queue *bq;
+		unsigned long *bitmap;
+
+		int cpu;
+
+		rcu_read_lock();
+		for_each_online_cpu(cpu) {
+			bitmap = per_cpu_ptr(dev->dtab->flush_needed, cpu);
+			__clear_bit(dev->bit, bitmap);
+
+			bq = per_cpu_ptr(dev->bulkq, cpu);
+			bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false);
+		}
+		rcu_read_unlock();
+	}
+}
+
+static void __dev_map_entry_free(struct rcu_head *rcu)
+{
+	struct bpf_dtab_netdev *dev;
+
+	dev = container_of(rcu, struct bpf_dtab_netdev, rcu);
+	dev_map_flush_old(dev);
+	free_percpu(dev->bulkq);
+	dev_put(dev->dev);
+	kfree(dev);
+}
+
+static int dev_map_delete_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	struct bpf_dtab_netdev *old_dev;
+	int k = *(u32 *)key;
+
+	if (k >= map->max_entries)
+		return -EINVAL;
+
+	/* Use call_rcu() here to ensure any rcu critical sections have
+	 * completed, but this does not guarantee a flush has happened
+	 * yet. Because driver side rcu_read_lock/unlock only protects the
+	 * running XDP program. However, for pending flush operations the
+	 * dev and ctx are stored in another per cpu map. And additionally,
+	 * the driver tear down ensures all soft irqs are complete before
+	 * removing the net device in the case of dev_put equals zero.
+	 */
+	old_dev = xchg(&dtab->netdev_map[k], NULL);
+	if (old_dev)
+		call_rcu(&old_dev->rcu, __dev_map_entry_free);
+	return 0;
+}
+
+static int dev_map_update_elem(struct bpf_map *map, void *key, void *value,
+				u64 map_flags)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	struct net *net = current->nsproxy->net_ns;
+	gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN;
+	struct bpf_dtab_netdev *dev, *old_dev;
+	u32 i = *(u32 *)key;
+	u32 ifindex = *(u32 *)value;
+
+	if (unlikely(map_flags > BPF_EXIST))
+		return -EINVAL;
+	if (unlikely(i >= dtab->map.max_entries))
+		return -E2BIG;
+	if (unlikely(map_flags == BPF_NOEXIST))
+		return -EEXIST;
+
+	if (!ifindex) {
+		dev = NULL;
+	} else {
+		dev = kmalloc_node(sizeof(*dev), gfp, map->numa_node);
+		if (!dev)
+			return -ENOMEM;
+
+		dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq),
+						sizeof(void *), gfp);
+		if (!dev->bulkq) {
+			kfree(dev);
+			return -ENOMEM;
+		}
+
+		dev->dev = dev_get_by_index(net, ifindex);
+		if (!dev->dev) {
+			free_percpu(dev->bulkq);
+			kfree(dev);
+			return -EINVAL;
+		}
+
+		dev->bit = i;
+		dev->dtab = dtab;
+	}
+
+	/* Use call_rcu() here to ensure rcu critical sections have completed
+	 * Remembering the driver side flush operation will happen before the
+	 * net device is removed.
+	 */
+	old_dev = xchg(&dtab->netdev_map[i], dev);
+	if (old_dev)
+		call_rcu(&old_dev->rcu, __dev_map_entry_free);
+
+	return 0;
+}
+
+const struct bpf_map_ops dev_map_ops = {
+	.map_alloc = dev_map_alloc,
+	.map_free = dev_map_free,
+	.map_get_next_key = dev_map_get_next_key,
+	.map_lookup_elem = dev_map_lookup_elem,
+	.map_update_elem = dev_map_update_elem,
+	.map_delete_elem = dev_map_delete_elem,
+	.map_check_btf = map_check_no_btf,
+};
+
+static int dev_map_notification(struct notifier_block *notifier,
+				ulong event, void *ptr)
+{
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+	struct bpf_dtab *dtab;
+	int i;
+
+	switch (event) {
+	case NETDEV_UNREGISTER:
+		/* This rcu_read_lock/unlock pair is needed because
+		 * dev_map_list is an RCU list AND to ensure a delete
+		 * operation does not free a netdev_map entry while we
+		 * are comparing it against the netdev being unregistered.
+		 */
+		rcu_read_lock();
+		list_for_each_entry_rcu(dtab, &dev_map_list, list) {
+			for (i = 0; i < dtab->map.max_entries; i++) {
+				struct bpf_dtab_netdev *dev, *odev;
+
+				dev = READ_ONCE(dtab->netdev_map[i]);
+				if (!dev || netdev != dev->dev)
+					continue;
+				odev = cmpxchg(&dtab->netdev_map[i], dev, NULL);
+				if (dev == odev)
+					call_rcu(&dev->rcu,
+						 __dev_map_entry_free);
+			}
+		}
+		rcu_read_unlock();
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block dev_map_notifier = {
+	.notifier_call = dev_map_notification,
+};
+
+static int __init dev_map_init(void)
+{
+	/* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */
+	BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) !=
+		     offsetof(struct _bpf_dtab_netdev, dev));
+	register_netdevice_notifier(&dev_map_notifier);
+	return 0;
+}
+
+subsys_initcall(dev_map_init);

kernel/bpf/disasm.c

@@ -0,0 +1,261 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/bpf.h>
+
+#include "disasm.h"
+
+#define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x)
+static const char * const func_id_str[] = {
+	__BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN)
+};
+#undef __BPF_FUNC_STR_FN
+
+static const char *__func_get_name(const struct bpf_insn_cbs *cbs,
+				   const struct bpf_insn *insn,
+				   char *buff, size_t len)
+{
+	BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID);
+
+	if (insn->src_reg != BPF_PSEUDO_CALL &&
+	    insn->imm >= 0 && insn->imm < __BPF_FUNC_MAX_ID &&
+	    func_id_str[insn->imm])
+		return func_id_str[insn->imm];
+
+	if (cbs && cbs->cb_call)
+		return cbs->cb_call(cbs->private_data, insn);
+
+	if (insn->src_reg == BPF_PSEUDO_CALL)
+		snprintf(buff, len, "%+d", insn->imm);
+
+	return buff;
+}
+
+static const char *__func_imm_name(const struct bpf_insn_cbs *cbs,
+				   const struct bpf_insn *insn,
+				   u64 full_imm, char *buff, size_t len)
+{
+	if (cbs && cbs->cb_imm)
+		return cbs->cb_imm(cbs->private_data, insn, full_imm);
+
+	snprintf(buff, len, "0x%llx", (unsigned long long)full_imm);
+	return buff;
+}
+
+const char *func_id_name(int id)
+{
+	if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id])
+		return func_id_str[id];
+	else
+		return "unknown";
+}
+
+const char *const bpf_class_string[8] = {
+	[BPF_LD]    = "ld",
+	[BPF_LDX]   = "ldx",
+	[BPF_ST]    = "st",
+	[BPF_STX]   = "stx",
+	[BPF_ALU]   = "alu",
+	[BPF_JMP]   = "jmp",
+	[BPF_RET]   = "BUG",
+	[BPF_ALU64] = "alu64",
+};
+
+const char *const bpf_alu_string[16] = {
+	[BPF_ADD >> 4]  = "+=",
+	[BPF_SUB >> 4]  = "-=",
+	[BPF_MUL >> 4]  = "*=",
+	[BPF_DIV >> 4]  = "/=",
+	[BPF_OR  >> 4]  = "|=",
+	[BPF_AND >> 4]  = "&=",
+	[BPF_LSH >> 4]  = "<<=",
+	[BPF_RSH >> 4]  = ">>=",
+	[BPF_NEG >> 4]  = "neg",
+	[BPF_MOD >> 4]  = "%=",
+	[BPF_XOR >> 4]  = "^=",
+	[BPF_MOV >> 4]  = "=",
+	[BPF_ARSH >> 4] = "s>>=",
+	[BPF_END >> 4]  = "endian",
+};
+
+static const char *const bpf_ldst_string[] = {
+	[BPF_W >> 3]  = "u32",
+	[BPF_H >> 3]  = "u16",
+	[BPF_B >> 3]  = "u8",
+	[BPF_DW >> 3] = "u64",
+};
+
+static const char *const bpf_jmp_string[16] = {
+	[BPF_JA >> 4]   = "jmp",
+	[BPF_JEQ >> 4]  = "==",
+	[BPF_JGT >> 4]  = ">",
+	[BPF_JLT >> 4]  = "<",
+	[BPF_JGE >> 4]  = ">=",
+	[BPF_JLE >> 4]  = "<=",
+	[BPF_JSET >> 4] = "&",
+	[BPF_JNE >> 4]  = "!=",
+	[BPF_JSGT >> 4] = "s>",
+	[BPF_JSLT >> 4] = "s<",
+	[BPF_JSGE >> 4] = "s>=",
+	[BPF_JSLE >> 4] = "s<=",
+	[BPF_CALL >> 4] = "call",
+	[BPF_EXIT >> 4] = "exit",
+};
+
+static void print_bpf_end_insn(bpf_insn_print_t verbose,
+			       void *private_data,
+			       const struct bpf_insn *insn)
+{
+	verbose(private_data, "(%02x) r%d = %s%d r%d\n",
+		insn->code, insn->dst_reg,
+		BPF_SRC(insn->code) == BPF_TO_BE ? "be" : "le",
+		insn->imm, insn->dst_reg);
+}
+
+void print_bpf_insn(const struct bpf_insn_cbs *cbs,
+		    const struct bpf_insn *insn,
+		    bool allow_ptr_leaks)
+{
+	const bpf_insn_print_t verbose = cbs->cb_print;
+	u8 class = BPF_CLASS(insn->code);
+
+	if (class == BPF_ALU || class == BPF_ALU64) {
+		if (BPF_OP(insn->code) == BPF_END) {
+			if (class == BPF_ALU64)
+				verbose(cbs->private_data, "BUG_alu64_%02x\n", insn->code);
+			else
+				print_bpf_end_insn(verbose, cbs->private_data, insn);
+		} else if (BPF_OP(insn->code) == BPF_NEG) {
+			verbose(cbs->private_data, "(%02x) r%d = %s-r%d\n",
+				insn->code, insn->dst_reg,
+				class == BPF_ALU ? "(u32) " : "",
+				insn->dst_reg);
+		} else if (BPF_SRC(insn->code) == BPF_X) {
+			verbose(cbs->private_data, "(%02x) %sr%d %s %sr%d\n",
+				insn->code, class == BPF_ALU ? "(u32) " : "",
+				insn->dst_reg,
+				bpf_alu_string[BPF_OP(insn->code) >> 4],
+				class == BPF_ALU ? "(u32) " : "",
+				insn->src_reg);
+		} else {
+			verbose(cbs->private_data, "(%02x) %sr%d %s %s%d\n",
+				insn->code, class == BPF_ALU ? "(u32) " : "",
+				insn->dst_reg,
+				bpf_alu_string[BPF_OP(insn->code) >> 4],
+				class == BPF_ALU ? "(u32) " : "",
+				insn->imm);
+		}
+	} else if (class == BPF_STX) {
+		if (BPF_MODE(insn->code) == BPF_MEM)
+			verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = r%d\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->dst_reg,
+				insn->off, insn->src_reg);
+		else if (BPF_MODE(insn->code) == BPF_XADD)
+			verbose(cbs->private_data, "(%02x) lock *(%s *)(r%d %+d) += r%d\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->dst_reg, insn->off,
+				insn->src_reg);
+		else
+			verbose(cbs->private_data, "BUG_%02x\n", insn->code);
+	} else if (class == BPF_ST) {
+		if (BPF_MODE(insn->code) != BPF_MEM) {
+			verbose(cbs->private_data, "BUG_st_%02x\n", insn->code);
+			return;
+		}
+		verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n",
+			insn->code,
+			bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+			insn->dst_reg,
+			insn->off, insn->imm);
+	} else if (class == BPF_LDX) {
+		if (BPF_MODE(insn->code) != BPF_MEM) {
+			verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code);
+			return;
+		}
+		verbose(cbs->private_data, "(%02x) r%d = *(%s *)(r%d %+d)\n",
+			insn->code, insn->dst_reg,
+			bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+			insn->src_reg, insn->off);
+	} else if (class == BPF_LD) {
+		if (BPF_MODE(insn->code) == BPF_ABS) {
+			verbose(cbs->private_data, "(%02x) r0 = *(%s *)skb[%d]\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->imm);
+		} else if (BPF_MODE(insn->code) == BPF_IND) {
+			verbose(cbs->private_data, "(%02x) r0 = *(%s *)skb[r%d + %d]\n",
+				insn->code,
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->src_reg, insn->imm);
+		} else if (BPF_MODE(insn->code) == BPF_IMM &&
+			   BPF_SIZE(insn->code) == BPF_DW) {
+			/* At this point, we already made sure that the second
+			 * part of the ldimm64 insn is accessible.
+			 */
+			u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
+			bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+			char tmp[64];
+
+			if (map_ptr && !allow_ptr_leaks)
+				imm = 0;
+
+			verbose(cbs->private_data, "(%02x) r%d = %s\n",
+				insn->code, insn->dst_reg,
+				__func_imm_name(cbs, insn, imm,
+						tmp, sizeof(tmp)));
+		} else {
+			verbose(cbs->private_data, "BUG_ld_%02x\n", insn->code);
+			return;
+		}
+	} else if (class == BPF_JMP) {
+		u8 opcode = BPF_OP(insn->code);
+
+		if (opcode == BPF_CALL) {
+			char tmp[64];
+
+			if (insn->src_reg == BPF_PSEUDO_CALL) {
+				verbose(cbs->private_data, "(%02x) call pc%s\n",
+					insn->code,
+					__func_get_name(cbs, insn,
+							tmp, sizeof(tmp)));
+			} else {
+				strcpy(tmp, "unknown");
+				verbose(cbs->private_data, "(%02x) call %s#%d\n", insn->code,
+					__func_get_name(cbs, insn,
+							tmp, sizeof(tmp)),
+					insn->imm);
+			}
+		} else if (insn->code == (BPF_JMP | BPF_JA)) {
+			verbose(cbs->private_data, "(%02x) goto pc%+d\n",
+				insn->code, insn->off);
+		} else if (insn->code == (BPF_JMP | BPF_EXIT)) {
+			verbose(cbs->private_data, "(%02x) exit\n", insn->code);
+		} else if (BPF_SRC(insn->code) == BPF_X) {
+			verbose(cbs->private_data, "(%02x) if r%d %s r%d goto pc%+d\n",
+				insn->code, insn->dst_reg,
+				bpf_jmp_string[BPF_OP(insn->code) >> 4],
+				insn->src_reg, insn->off);
+		} else {
+			verbose(cbs->private_data, "(%02x) if r%d %s 0x%x goto pc%+d\n",
+				insn->code, insn->dst_reg,
+				bpf_jmp_string[BPF_OP(insn->code) >> 4],
+				insn->imm, insn->off);
+		}
+	} else {
+		verbose(cbs->private_data, "(%02x) %s\n",
+			insn->code, bpf_class_string[class]);
+	}
+}

kernel/bpf/disasm.h

@@ -0,0 +1,48 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef __BPF_DISASM_H__
+#define __BPF_DISASM_H__
+
+#include <linux/bpf.h>
+#include <linux/kernel.h>
+#include <linux/stringify.h>
+#ifndef __KERNEL__
+#include <stdio.h>
+#include <string.h>
+#endif
+
+extern const char *const bpf_alu_string[16];
+extern const char *const bpf_class_string[8];
+
+const char *func_id_name(int id);
+
+typedef __printf(2, 3) void (*bpf_insn_print_t)(void *private_data,
+						const char *, ...);
+typedef const char *(*bpf_insn_revmap_call_t)(void *private_data,
+					      const struct bpf_insn *insn);
+typedef const char *(*bpf_insn_print_imm_t)(void *private_data,
+					    const struct bpf_insn *insn,
+					    __u64 full_imm);
+
+struct bpf_insn_cbs {
+	bpf_insn_print_t	cb_print;
+	bpf_insn_revmap_call_t	cb_call;
+	bpf_insn_print_imm_t	cb_imm;
+	void			*private_data;
+};
+
+void print_bpf_insn(const struct bpf_insn_cbs *cbs,
+		    const struct bpf_insn *insn,
+		    bool allow_ptr_leaks);
+#endif

kernel/bpf/helpers.c

@@ -0,0 +1,228 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/bpf.h>
+#include <linux/rcupdate.h>
+#include <linux/random.h>
+#include <linux/smp.h>
+#include <linux/topology.h>
+#include <linux/ktime.h>
+#include <linux/sched.h>
+#include <linux/uidgid.h>
+#include <linux/filter.h>
+
+/* If kernel subsystem is allowing eBPF programs to call this function,
+ * inside its own verifier_ops->get_func_proto() callback it should return
+ * bpf_map_lookup_elem_proto, so that verifier can properly check the arguments
+ *
+ * Different map implementations will rely on rcu in map methods
+ * lookup/update/delete, therefore eBPF programs must run under rcu lock
+ * if program is allowed to access maps, so check rcu_read_lock_held in
+ * all three functions.
+ */
+BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return (unsigned long) map->ops->map_lookup_elem(map, key);
+}
+
+const struct bpf_func_proto bpf_map_lookup_elem_proto = {
+	.func		= bpf_map_lookup_elem,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_MAP_KEY,
+};
+
+BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key,
+	   void *, value, u64, flags)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return map->ops->map_update_elem(map, key, value, flags);
+}
+
+const struct bpf_func_proto bpf_map_update_elem_proto = {
+	.func		= bpf_map_update_elem,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_MAP_KEY,
+	.arg3_type	= ARG_PTR_TO_MAP_VALUE,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return map->ops->map_delete_elem(map, key);
+}
+
+const struct bpf_func_proto bpf_map_delete_elem_proto = {
+	.func		= bpf_map_delete_elem,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_MAP_KEY,
+};
+
+const struct bpf_func_proto bpf_get_prandom_u32_proto = {
+	.func		= bpf_user_rnd_u32,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
+BPF_CALL_0(bpf_get_smp_processor_id)
+{
+	return smp_processor_id();
+}
+
+const struct bpf_func_proto bpf_get_smp_processor_id_proto = {
+	.func		= bpf_get_smp_processor_id,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
+BPF_CALL_0(bpf_get_numa_node_id)
+{
+	return numa_node_id();
+}
+
+const struct bpf_func_proto bpf_get_numa_node_id_proto = {
+	.func		= bpf_get_numa_node_id,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
+BPF_CALL_0(bpf_ktime_get_ns)
+{
+	/* NMI safe access to clock monotonic */
+	return ktime_get_mono_fast_ns();
+}
+
+const struct bpf_func_proto bpf_ktime_get_ns_proto = {
+	.func		= bpf_ktime_get_ns,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
+BPF_CALL_0(bpf_ktime_get_boot_ns)
+{
+	/* NMI safe access to clock boottime */
+	return ktime_get_boot_fast_ns();
+}
+
+const struct bpf_func_proto bpf_ktime_get_boot_ns_proto = {
+	.func		= bpf_ktime_get_boot_ns,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
+BPF_CALL_0(bpf_get_current_pid_tgid)
+{
+	struct task_struct *task = current;
+
+	if (unlikely(!task))
+		return -EINVAL;
+
+	return (u64) task->tgid << 32 | task->pid;
+}
+
+const struct bpf_func_proto bpf_get_current_pid_tgid_proto = {
+	.func		= bpf_get_current_pid_tgid,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
+BPF_CALL_0(bpf_get_current_uid_gid)
+{
+	struct task_struct *task = current;
+	kuid_t uid;
+	kgid_t gid;
+
+	if (unlikely(!task))
+		return -EINVAL;
+
+	current_uid_gid(&uid, &gid);
+	return (u64) from_kgid(&init_user_ns, gid) << 32 |
+		     from_kuid(&init_user_ns, uid);
+}
+
+const struct bpf_func_proto bpf_get_current_uid_gid_proto = {
+	.func		= bpf_get_current_uid_gid,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
+BPF_CALL_2(bpf_get_current_comm, char *, buf, u32, size)
+{
+	struct task_struct *task = current;
+
+	if (unlikely(!task))
+		goto err_clear;
+
+	strncpy(buf, task->comm, size);
+
+	/* Verifier guarantees that size > 0. For task->comm exceeding
+	 * size, guarantee that buf is %NUL-terminated. Unconditionally
+	 * done here to save the size test.
+	 */
+	buf[size - 1] = 0;
+	return 0;
+err_clear:
+	memset(buf, 0, size);
+	return -EINVAL;
+}
+
+const struct bpf_func_proto bpf_get_current_comm_proto = {
+	.func		= bpf_get_current_comm,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+};
+
+#ifdef CONFIG_CGROUPS
+BPF_CALL_0(bpf_get_current_cgroup_id)
+{
+	struct cgroup *cgrp = task_dfl_cgroup(current);
+
+	return cgrp->kn->id.id;
+}
+
+const struct bpf_func_proto bpf_get_current_cgroup_id_proto = {
+	.func		= bpf_get_current_cgroup_id,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
+DECLARE_PER_CPU(void*, bpf_cgroup_storage);
+
+BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
+{
+	/* map and flags arguments are not used now,
+	 * but provide an ability to extend the API
+	 * for other types of local storages.
+	 * verifier checks that their values are correct.
+	 */
+	return (unsigned long) this_cpu_read(bpf_cgroup_storage);
+}
+
+const struct bpf_func_proto bpf_get_local_storage_proto = {
+	.func		= bpf_get_local_storage,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MAP_VALUE,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_ANYTHING,
+};
+#endif

kernel/bpf/inode.c

@@ -0,0 +1,689 @@
+/*
+ * Minimal file system backend for holding eBPF maps and programs,
+ * used by bpf(2) object pinning.
+ *
+ * Authors:
+ *
+ *	Daniel Borkmann <daniel@iogearbox.net>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/magic.h>
+#include <linux/major.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/fs.h>
+#include <linux/kdev_t.h>
+#include <linux/parser.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
+
+enum bpf_type {
+	BPF_TYPE_UNSPEC	= 0,
+	BPF_TYPE_PROG,
+	BPF_TYPE_MAP,
+};
+
+static void *bpf_any_get(void *raw, enum bpf_type type)
+{
+	switch (type) {
+	case BPF_TYPE_PROG:
+		raw = bpf_prog_inc(raw);
+		break;
+	case BPF_TYPE_MAP:
+		raw = bpf_map_inc(raw, true);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	return raw;
+}
+
+static void bpf_any_put(void *raw, enum bpf_type type)
+{
+	switch (type) {
+	case BPF_TYPE_PROG:
+		bpf_prog_put(raw);
+		break;
+	case BPF_TYPE_MAP:
+		bpf_map_put_with_uref(raw);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+}
+
+static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type)
+{
+	void *raw;
+
+	*type = BPF_TYPE_MAP;
+	raw = bpf_map_get_with_uref(ufd);
+	if (IS_ERR(raw)) {
+		*type = BPF_TYPE_PROG;
+		raw = bpf_prog_get(ufd);
+	}
+
+	return raw;
+}
+
+static const struct inode_operations bpf_dir_iops;
+
+static const struct inode_operations bpf_prog_iops = { };
+static const struct inode_operations bpf_map_iops  = { };
+
+static struct inode *bpf_get_inode(struct super_block *sb,
+				   const struct inode *dir,
+				   umode_t mode)
+{
+	struct inode *inode;
+
+	switch (mode & S_IFMT) {
+	case S_IFDIR:
+	case S_IFREG:
+	case S_IFLNK:
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	inode = new_inode(sb);
+	if (!inode)
+		return ERR_PTR(-ENOSPC);
+
+	inode->i_ino = get_next_ino();
+	inode->i_atime = current_time(inode);
+	inode->i_mtime = inode->i_atime;
+	inode->i_ctime = inode->i_atime;
+
+	inode_init_owner(inode, dir, mode);
+
+	return inode;
+}
+
+static int bpf_inode_type(const struct inode *inode, enum bpf_type *type)
+{
+	*type = BPF_TYPE_UNSPEC;
+	if (inode->i_op == &bpf_prog_iops)
+		*type = BPF_TYPE_PROG;
+	else if (inode->i_op == &bpf_map_iops)
+		*type = BPF_TYPE_MAP;
+	else
+		return -EACCES;
+
+	return 0;
+}
+
+static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode,
+				struct inode *dir)
+{
+	d_instantiate(dentry, inode);
+	dget(dentry);
+
+	dir->i_mtime = current_time(dir);
+	dir->i_ctime = dir->i_mtime;
+}
+
+static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	struct inode *inode;
+
+	inode = bpf_get_inode(dir->i_sb, dir, mode | S_IFDIR);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+
+	inode->i_op = &bpf_dir_iops;
+	inode->i_fop = &simple_dir_operations;
+
+	inc_nlink(inode);
+	inc_nlink(dir);
+
+	bpf_dentry_finalize(dentry, inode, dir);
+	return 0;
+}
+
+struct map_iter {
+	void *key;
+	bool done;
+};
+
+static struct map_iter *map_iter(struct seq_file *m)
+{
+	return m->private;
+}
+
+static struct bpf_map *seq_file_to_map(struct seq_file *m)
+{
+	return file_inode(m->file)->i_private;
+}
+
+static void map_iter_free(struct map_iter *iter)
+{
+	if (iter) {
+		kfree(iter->key);
+		kfree(iter);
+	}
+}
+
+static struct map_iter *map_iter_alloc(struct bpf_map *map)
+{
+	struct map_iter *iter;
+
+	iter = kzalloc(sizeof(*iter), GFP_KERNEL | __GFP_NOWARN);
+	if (!iter)
+		goto error;
+
+	iter->key = kzalloc(map->key_size, GFP_KERNEL | __GFP_NOWARN);
+	if (!iter->key)
+		goto error;
+
+	return iter;
+
+error:
+	map_iter_free(iter);
+	return NULL;
+}
+
+static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct bpf_map *map = seq_file_to_map(m);
+	void *key = map_iter(m)->key;
+	void *prev_key;
+
+	(*pos)++;
+	if (map_iter(m)->done)
+		return NULL;
+
+	if (unlikely(v == SEQ_START_TOKEN))
+		prev_key = NULL;
+	else
+		prev_key = key;
+
+	rcu_read_lock();
+	if (map->ops->map_get_next_key(map, prev_key, key)) {
+		map_iter(m)->done = true;
+		key = NULL;
+	}
+	rcu_read_unlock();
+	return key;
+}
+
+static void *map_seq_start(struct seq_file *m, loff_t *pos)
+{
+	if (map_iter(m)->done)
+		return NULL;
+
+	return *pos ? map_iter(m)->key : SEQ_START_TOKEN;
+}
+
+static void map_seq_stop(struct seq_file *m, void *v)
+{
+}
+
+static int map_seq_show(struct seq_file *m, void *v)
+{
+	struct bpf_map *map = seq_file_to_map(m);
+	void *key = map_iter(m)->key;
+
+	if (unlikely(v == SEQ_START_TOKEN)) {
+		seq_puts(m, "# WARNING!! The output is for debug purpose only\n");
+		seq_puts(m, "# WARNING!! The output format will change\n");
+	} else {
+		map->ops->map_seq_show_elem(map, key, m);
+	}
+
+	return 0;
+}
+
+static const struct seq_operations bpffs_map_seq_ops = {
+	.start	= map_seq_start,
+	.next	= map_seq_next,
+	.show	= map_seq_show,
+	.stop	= map_seq_stop,
+};
+
+static int bpffs_map_open(struct inode *inode, struct file *file)
+{
+	struct bpf_map *map = inode->i_private;
+	struct map_iter *iter;
+	struct seq_file *m;
+	int err;
+
+	iter = map_iter_alloc(map);
+	if (!iter)
+		return -ENOMEM;
+
+	err = seq_open(file, &bpffs_map_seq_ops);
+	if (err) {
+		map_iter_free(iter);
+		return err;
+	}
+
+	m = file->private_data;
+	m->private = iter;
+
+	return 0;
+}
+
+static int bpffs_map_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *m = file->private_data;
+
+	map_iter_free(map_iter(m));
+
+	return seq_release(inode, file);
+}
+
+/* bpffs_map_fops should only implement the basic
+ * read operation for a BPF map.  The purpose is to
+ * provide a simple user intuitive way to do
+ * "cat bpffs/pathto/a-pinned-map".
+ *
+ * Other operations (e.g. write, lookup...) should be realized by
+ * the userspace tools (e.g. bpftool) through the
+ * BPF_OBJ_GET_INFO_BY_FD and the map's lookup/update
+ * interface.
+ */
+static const struct file_operations bpffs_map_fops = {
+	.open		= bpffs_map_open,
+	.read		= seq_read,
+	.release	= bpffs_map_release,
+};
+
+static int bpffs_obj_open(struct inode *inode, struct file *file)
+{
+	return -EIO;
+}
+
+static const struct file_operations bpffs_obj_fops = {
+	.open		= bpffs_obj_open,
+};
+
+static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw,
+			 const struct inode_operations *iops,
+			 const struct file_operations *fops)
+{
+	struct inode *dir = dentry->d_parent->d_inode;
+	struct inode *inode = bpf_get_inode(dir->i_sb, dir, mode);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+
+	inode->i_op = iops;
+	inode->i_fop = fops;
+	inode->i_private = raw;
+
+	bpf_dentry_finalize(dentry, inode, dir);
+	return 0;
+}
+
+static int bpf_mkprog(struct dentry *dentry, umode_t mode, void *arg)
+{
+	return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops,
+			     &bpffs_obj_fops);
+}
+
+static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg)
+{
+	struct bpf_map *map = arg;
+
+	return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops,
+			     bpf_map_support_seq_show(map) ?
+			     &bpffs_map_fops : &bpffs_obj_fops);
+}
+
+static struct dentry *
+bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags)
+{
+	/* Dots in names (e.g. "/sys/fs/bpf/foo.bar") are reserved for future
+	 * extensions.
+	 */
+	if (strchr(dentry->d_name.name, '.'))
+		return ERR_PTR(-EPERM);
+
+	return simple_lookup(dir, dentry, flags);
+}
+
+static int bpf_symlink(struct inode *dir, struct dentry *dentry,
+		       const char *target)
+{
+	char *link = kstrdup(target, GFP_USER | __GFP_NOWARN);
+	struct inode *inode;
+
+	if (!link)
+		return -ENOMEM;
+
+	inode = bpf_get_inode(dir->i_sb, dir, S_IRWXUGO | S_IFLNK);
+	if (IS_ERR(inode)) {
+		kfree(link);
+		return PTR_ERR(inode);
+	}
+
+	inode->i_op = &simple_symlink_inode_operations;
+	inode->i_link = link;
+
+	bpf_dentry_finalize(dentry, inode, dir);
+	return 0;
+}
+
+static const struct inode_operations bpf_dir_iops = {
+	.lookup		= bpf_lookup,
+	.mkdir		= bpf_mkdir,
+	.symlink	= bpf_symlink,
+	.rmdir		= simple_rmdir,
+	.rename		= simple_rename,
+	.link		= simple_link,
+	.unlink		= simple_unlink,
+};
+
+static int bpf_obj_do_pin(const struct filename *pathname, void *raw,
+			  enum bpf_type type)
+{
+	struct dentry *dentry;
+	struct inode *dir;
+	struct path path;
+	umode_t mode;
+	int ret;
+
+	dentry = kern_path_create(AT_FDCWD, pathname->name, &path, 0);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask());
+
+	ret = security_path_mknod(&path, dentry, mode, 0);
+	if (ret)
+		goto out;
+
+	dir = d_inode(path.dentry);
+	if (dir->i_op != &bpf_dir_iops) {
+		ret = -EPERM;
+		goto out;
+	}
+
+	switch (type) {
+	case BPF_TYPE_PROG:
+		ret = vfs_mkobj(dentry, mode, bpf_mkprog, raw);
+		break;
+	case BPF_TYPE_MAP:
+		ret = vfs_mkobj(dentry, mode, bpf_mkmap, raw);
+		break;
+	default:
+		ret = -EPERM;
+	}
+out:
+	done_path_create(&path, dentry);
+	return ret;
+}
+
+int bpf_obj_pin_user(u32 ufd, const char __user *pathname)
+{
+	struct filename *pname;
+	enum bpf_type type;
+	void *raw;
+	int ret;
+
+	pname = getname(pathname);
+	if (IS_ERR(pname))
+		return PTR_ERR(pname);
+
+	raw = bpf_fd_probe_obj(ufd, &type);
+	if (IS_ERR(raw)) {
+		ret = PTR_ERR(raw);
+		goto out;
+	}
+
+	ret = bpf_obj_do_pin(pname, raw, type);
+	if (ret != 0)
+		bpf_any_put(raw, type);
+out:
+	putname(pname);
+	return ret;
+}
+
+static void *bpf_obj_do_get(const struct filename *pathname,
+			    enum bpf_type *type, int flags)
+{
+	struct inode *inode;
+	struct path path;
+	void *raw;
+	int ret;
+
+	ret = kern_path(pathname->name, LOOKUP_FOLLOW, &path);
+	if (ret)
+		return ERR_PTR(ret);
+
+	inode = d_backing_inode(path.dentry);
+	ret = inode_permission(inode, ACC_MODE(flags));
+	if (ret)
+		goto out;
+
+	ret = bpf_inode_type(inode, type);
+	if (ret)
+		goto out;
+
+	raw = bpf_any_get(inode->i_private, *type);
+	if (!IS_ERR(raw))
+		touch_atime(&path);
+
+	path_put(&path);
+	return raw;
+out:
+	path_put(&path);
+	return ERR_PTR(ret);
+}
+
+int bpf_obj_get_user(const char __user *pathname, int flags)
+{
+	enum bpf_type type = BPF_TYPE_UNSPEC;
+	struct filename *pname;
+	int ret = -ENOENT;
+	int f_flags;
+	void *raw;
+
+	f_flags = bpf_get_file_flag(flags);
+	if (f_flags < 0)
+		return f_flags;
+
+	pname = getname(pathname);
+	if (IS_ERR(pname))
+		return PTR_ERR(pname);
+
+	raw = bpf_obj_do_get(pname, &type, f_flags);
+	if (IS_ERR(raw)) {
+		ret = PTR_ERR(raw);
+		goto out;
+	}
+
+	if (type == BPF_TYPE_PROG)
+		ret = bpf_prog_new_fd(raw);
+	else if (type == BPF_TYPE_MAP)
+		ret = bpf_map_new_fd(raw, f_flags);
+	else
+		goto out;
+
+	if (ret < 0)
+		bpf_any_put(raw, type);
+out:
+	putname(pname);
+	return ret;
+}
+
+static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type)
+{
+	struct bpf_prog *prog;
+	int ret = inode_permission(inode, MAY_READ);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (inode->i_op == &bpf_map_iops)
+		return ERR_PTR(-EINVAL);
+	if (inode->i_op != &bpf_prog_iops)
+		return ERR_PTR(-EACCES);
+
+	prog = inode->i_private;
+
+	ret = security_bpf_prog(prog);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	if (!bpf_prog_get_ok(prog, &type, false))
+		return ERR_PTR(-EINVAL);
+
+	return bpf_prog_inc(prog);
+}
+
+struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type)
+{
+	struct bpf_prog *prog;
+	struct path path;
+	int ret = kern_path(name, LOOKUP_FOLLOW, &path);
+	if (ret)
+		return ERR_PTR(ret);
+	prog = __get_prog_inode(d_backing_inode(path.dentry), type);
+	if (!IS_ERR(prog))
+		touch_atime(&path);
+	path_put(&path);
+	return prog;
+}
+EXPORT_SYMBOL(bpf_prog_get_type_path);
+
+/*
+ * Display the mount options in /proc/mounts.
+ */
+static int bpf_show_options(struct seq_file *m, struct dentry *root)
+{
+	umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX;
+
+	if (mode != S_IRWXUGO)
+		seq_printf(m, ",mode=%o", mode);
+	return 0;
+}
+
+static void bpf_destroy_inode_deferred(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	enum bpf_type type;
+
+	if (S_ISLNK(inode->i_mode))
+		kfree(inode->i_link);
+	if (!bpf_inode_type(inode, &type))
+		bpf_any_put(inode->i_private, type);
+	free_inode_nonrcu(inode);
+}
+
+static void bpf_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, bpf_destroy_inode_deferred);
+}
+
+static const struct super_operations bpf_super_ops = {
+	.statfs		= simple_statfs,
+	.drop_inode	= generic_delete_inode,
+	.show_options	= bpf_show_options,
+	.destroy_inode	= bpf_destroy_inode,
+};
+
+enum {
+	OPT_MODE,
+	OPT_ERR,
+};
+
+static const match_table_t bpf_mount_tokens = {
+	{ OPT_MODE, "mode=%o" },
+	{ OPT_ERR, NULL },
+};
+
+struct bpf_mount_opts {
+	umode_t mode;
+};
+
+static int bpf_parse_options(char *data, struct bpf_mount_opts *opts)
+{
+	substring_t args[MAX_OPT_ARGS];
+	int option, token;
+	char *ptr;
+
+	opts->mode = S_IRWXUGO;
+
+	while ((ptr = strsep(&data, ",")) != NULL) {
+		if (!*ptr)
+			continue;
+
+		token = match_token(ptr, bpf_mount_tokens, args);
+		switch (token) {
+		case OPT_MODE:
+			if (match_octal(&args[0], &option))
+				return -EINVAL;
+			opts->mode = option & S_IALLUGO;
+			break;
+		/* We might like to report bad mount options here, but
+		 * traditionally we've ignored all mount options, so we'd
+		 * better continue to ignore non-existing options for bpf.
+		 */
+		}
+	}
+
+	return 0;
+}
+
+static int bpf_fill_super(struct super_block *sb, void *data, int silent)
+{
+	static const struct tree_descr bpf_rfiles[] = { { "" } };
+	struct bpf_mount_opts opts;
+	struct inode *inode;
+	int ret;
+
+	ret = bpf_parse_options(data, &opts);
+	if (ret)
+		return ret;
+
+	ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles);
+	if (ret)
+		return ret;
+
+	sb->s_op = &bpf_super_ops;
+
+	inode = sb->s_root->d_inode;
+	inode->i_op = &bpf_dir_iops;
+	inode->i_mode &= ~S_IALLUGO;
+	inode->i_mode |= S_ISVTX | opts.mode;
+
+	return 0;
+}
+
+static struct dentry *bpf_mount(struct file_system_type *type, int flags,
+				const char *dev_name, void *data)
+{
+	return mount_nodev(type, flags, data, bpf_fill_super);
+}
+
+static struct file_system_type bpf_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "bpf",
+	.mount		= bpf_mount,
+	.kill_sb	= kill_litter_super,
+};
+
+static int __init bpf_init(void)
+{
+	int ret;
+
+	ret = sysfs_create_mount_point(fs_kobj, "bpf");
+	if (ret)
+		return ret;
+
+	ret = register_filesystem(&bpf_fs_type);
+	if (ret)
+		sysfs_remove_mount_point(fs_kobj, "bpf");
+
+	return ret;
+}
+fs_initcall(bpf_init);

kernel/bpf/local_storage.c

@@ -0,0 +1,383 @@
+//SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf-cgroup.h>
+#include <linux/bpf.h>
+#include <linux/bug.h>
+#include <linux/filter.h>
+#include <linux/mm.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+
+DEFINE_PER_CPU(void*, bpf_cgroup_storage);
+
+#ifdef CONFIG_CGROUP_BPF
+
+#define LOCAL_STORAGE_CREATE_FLAG_MASK					\
+	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
+struct bpf_cgroup_storage_map {
+	struct bpf_map map;
+
+	spinlock_t lock;
+	struct bpf_prog *prog;
+	struct rb_root root;
+	struct list_head list;
+};
+
+static struct bpf_cgroup_storage_map *map_to_storage(struct bpf_map *map)
+{
+	return container_of(map, struct bpf_cgroup_storage_map, map);
+}
+
+static int bpf_cgroup_storage_key_cmp(
+	const struct bpf_cgroup_storage_key *key1,
+	const struct bpf_cgroup_storage_key *key2)
+{
+	if (key1->cgroup_inode_id < key2->cgroup_inode_id)
+		return -1;
+	else if (key1->cgroup_inode_id > key2->cgroup_inode_id)
+		return 1;
+	else if (key1->attach_type < key2->attach_type)
+		return -1;
+	else if (key1->attach_type > key2->attach_type)
+		return 1;
+	return 0;
+}
+
+static struct bpf_cgroup_storage *cgroup_storage_lookup(
+	struct bpf_cgroup_storage_map *map, struct bpf_cgroup_storage_key *key,
+	bool locked)
+{
+	struct rb_root *root = &map->root;
+	struct rb_node *node;
+
+	if (!locked)
+		spin_lock_bh(&map->lock);
+
+	node = root->rb_node;
+	while (node) {
+		struct bpf_cgroup_storage *storage;
+
+		storage = container_of(node, struct bpf_cgroup_storage, node);
+
+		switch (bpf_cgroup_storage_key_cmp(key, &storage->key)) {
+		case -1:
+			node = node->rb_left;
+			break;
+		case 1:
+			node = node->rb_right;
+			break;
+		default:
+			if (!locked)
+				spin_unlock_bh(&map->lock);
+			return storage;
+		}
+	}
+
+	if (!locked)
+		spin_unlock_bh(&map->lock);
+
+	return NULL;
+}
+
+static int cgroup_storage_insert(struct bpf_cgroup_storage_map *map,
+				 struct bpf_cgroup_storage *storage)
+{
+	struct rb_root *root = &map->root;
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+	while (*new) {
+		struct bpf_cgroup_storage *this;
+
+		this = container_of(*new, struct bpf_cgroup_storage, node);
+
+		parent = *new;
+		switch (bpf_cgroup_storage_key_cmp(&storage->key, &this->key)) {
+		case -1:
+			new = &((*new)->rb_left);
+			break;
+		case 1:
+			new = &((*new)->rb_right);
+			break;
+		default:
+			return -EEXIST;
+		}
+	}
+
+	rb_link_node(&storage->node, parent, new);
+	rb_insert_color(&storage->node, root);
+
+	return 0;
+}
+
+static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *_key)
+{
+	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+	struct bpf_cgroup_storage_key *key = _key;
+	struct bpf_cgroup_storage *storage;
+
+	storage = cgroup_storage_lookup(map, key, false);
+	if (!storage)
+		return NULL;
+
+	return &READ_ONCE(storage->buf)->data[0];
+}
+
+static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
+				      void *value, u64 flags)
+{
+	struct bpf_cgroup_storage_key *key = _key;
+	struct bpf_cgroup_storage *storage;
+	struct bpf_storage_buffer *new;
+
+	if (flags != BPF_ANY && flags != BPF_EXIST)
+		return -EINVAL;
+
+	storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map,
+					key, false);
+	if (!storage)
+		return -ENOENT;
+
+	new = kmalloc_node(sizeof(struct bpf_storage_buffer) +
+			   map->value_size,
+			   __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN,
+			   map->numa_node);
+	if (!new)
+		return -ENOMEM;
+
+	memcpy(&new->data[0], value, map->value_size);
+
+	new = xchg(&storage->buf, new);
+	kfree_rcu(new, rcu);
+
+	return 0;
+}
+
+static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key,
+				       void *_next_key)
+{
+	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+	struct bpf_cgroup_storage_key *key = _key;
+	struct bpf_cgroup_storage_key *next = _next_key;
+	struct bpf_cgroup_storage *storage;
+
+	spin_lock_bh(&map->lock);
+
+	if (list_empty(&map->list))
+		goto enoent;
+
+	if (key) {
+		storage = cgroup_storage_lookup(map, key, true);
+		if (!storage)
+			goto enoent;
+
+		storage = list_next_entry(storage, list);
+		if (!storage)
+			goto enoent;
+	} else {
+		storage = list_first_entry(&map->list,
+					 struct bpf_cgroup_storage, list);
+	}
+
+	spin_unlock_bh(&map->lock);
+	next->attach_type = storage->key.attach_type;
+	next->cgroup_inode_id = storage->key.cgroup_inode_id;
+	return 0;
+
+enoent:
+	spin_unlock_bh(&map->lock);
+	return -ENOENT;
+}
+
+static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
+{
+	int numa_node = bpf_map_attr_numa_node(attr);
+	struct bpf_cgroup_storage_map *map;
+
+	if (attr->key_size != sizeof(struct bpf_cgroup_storage_key))
+		return ERR_PTR(-EINVAL);
+
+	if (attr->value_size == 0)
+		return ERR_PTR(-EINVAL);
+
+	if (attr->value_size > PAGE_SIZE)
+		return ERR_PTR(-E2BIG);
+
+	if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK)
+		/* reserved bits should not be used */
+		return ERR_PTR(-EINVAL);
+
+	if (attr->max_entries)
+		/* max_entries is not used and enforced to be 0 */
+		return ERR_PTR(-EINVAL);
+
+	map = kmalloc_node(sizeof(struct bpf_cgroup_storage_map),
+			   __GFP_ZERO | GFP_USER, numa_node);
+	if (!map)
+		return ERR_PTR(-ENOMEM);
+
+	map->map.pages = round_up(sizeof(struct bpf_cgroup_storage_map),
+				  PAGE_SIZE) >> PAGE_SHIFT;
+
+	/* copy mandatory map attributes */
+	bpf_map_init_from_attr(&map->map, attr);
+
+	spin_lock_init(&map->lock);
+	map->root = RB_ROOT;
+	INIT_LIST_HEAD(&map->list);
+
+	return &map->map;
+}
+
+static void cgroup_storage_map_free(struct bpf_map *_map)
+{
+	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+
+	WARN_ON(!RB_EMPTY_ROOT(&map->root));
+	WARN_ON(!list_empty(&map->list));
+
+	kfree(map);
+}
+
+static int cgroup_storage_delete_elem(struct bpf_map *map, void *key)
+{
+	return -EINVAL;
+}
+
+const struct bpf_map_ops cgroup_storage_map_ops = {
+	.map_alloc = cgroup_storage_map_alloc,
+	.map_free = cgroup_storage_map_free,
+	.map_get_next_key = cgroup_storage_get_next_key,
+	.map_lookup_elem = cgroup_storage_lookup_elem,
+	.map_update_elem = cgroup_storage_update_elem,
+	.map_delete_elem = cgroup_storage_delete_elem,
+	.map_check_btf = map_check_no_btf,
+};
+
+int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map)
+{
+	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+	int ret = -EBUSY;
+
+	spin_lock_bh(&map->lock);
+
+	if (map->prog && map->prog != prog)
+		goto unlock;
+	if (prog->aux->cgroup_storage && prog->aux->cgroup_storage != _map)
+		goto unlock;
+
+	map->prog = prog;
+	prog->aux->cgroup_storage = _map;
+	ret = 0;
+unlock:
+	spin_unlock_bh(&map->lock);
+
+	return ret;
+}
+
+void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map)
+{
+	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+
+	spin_lock_bh(&map->lock);
+	if (map->prog == prog) {
+		WARN_ON(prog->aux->cgroup_storage != _map);
+		map->prog = NULL;
+		prog->aux->cgroup_storage = NULL;
+	}
+	spin_unlock_bh(&map->lock);
+}
+
+struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog)
+{
+	struct bpf_cgroup_storage *storage;
+	struct bpf_map *map;
+	u32 pages;
+
+	map = prog->aux->cgroup_storage;
+	if (!map)
+		return NULL;
+
+	pages = round_up(sizeof(struct bpf_cgroup_storage) +
+			 sizeof(struct bpf_storage_buffer) +
+			 map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
+	if (bpf_map_charge_memlock(map, pages))
+		return ERR_PTR(-EPERM);
+
+	storage = kmalloc_node(sizeof(struct bpf_cgroup_storage),
+			       __GFP_ZERO | GFP_USER, map->numa_node);
+	if (!storage) {
+		bpf_map_uncharge_memlock(map, pages);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	storage->buf = kmalloc_node(sizeof(struct bpf_storage_buffer) +
+				    map->value_size, __GFP_ZERO | GFP_USER,
+				    map->numa_node);
+	if (!storage->buf) {
+		bpf_map_uncharge_memlock(map, pages);
+		kfree(storage);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	storage->map = (struct bpf_cgroup_storage_map *)map;
+
+	return storage;
+}
+
+void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage)
+{
+	u32 pages;
+	struct bpf_map *map;
+
+	if (!storage)
+		return;
+
+	map = &storage->map->map;
+	pages = round_up(sizeof(struct bpf_cgroup_storage) +
+			 sizeof(struct bpf_storage_buffer) +
+			 map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
+	bpf_map_uncharge_memlock(map, pages);
+
+	kfree_rcu(storage->buf, rcu);
+	kfree_rcu(storage, rcu);
+}
+
+void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
+			     struct cgroup *cgroup,
+			     enum bpf_attach_type type)
+{
+	struct bpf_cgroup_storage_map *map;
+
+	if (!storage)
+		return;
+
+	storage->key.attach_type = type;
+	storage->key.cgroup_inode_id = cgroup->kn->id.id;
+
+	map = storage->map;
+
+	spin_lock_bh(&map->lock);
+	WARN_ON(cgroup_storage_insert(map, storage));
+	list_add(&storage->list, &map->list);
+	spin_unlock_bh(&map->lock);
+}
+
+void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage)
+{
+	struct bpf_cgroup_storage_map *map;
+	struct rb_root *root;
+
+	if (!storage)
+		return;
+
+	map = storage->map;
+
+	spin_lock_bh(&map->lock);
+	root = &map->root;
+	rb_erase(&storage->node, root);
+
+	list_del(&storage->list);
+	spin_unlock_bh(&map->lock);
+}
+
+#endif

kernel/bpf/lpm_trie.c

@@ -0,0 +1,714 @@
+/*
+ * Longest prefix match list implementation
+ *
+ * Copyright (c) 2016,2017 Daniel Mack
+ * Copyright (c) 2016 David Herrmann
+ *
+ * This file is subject to the terms and conditions of version 2 of the GNU
+ * General Public License.  See the file COPYING in the main directory of the
+ * Linux distribution for more details.
+ */
+
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+#include <net/ipv6.h>
+#include <uapi/linux/btf.h>
+
+/* Intermediate node */
+#define LPM_TREE_NODE_FLAG_IM BIT(0)
+
+struct lpm_trie_node;
+
+struct lpm_trie_node {
+	struct rcu_head rcu;
+	struct lpm_trie_node __rcu	*child[2];
+	u32				prefixlen;
+	u32				flags;
+	u8				data[0];
+};
+
+struct lpm_trie {
+	struct bpf_map			map;
+	struct lpm_trie_node __rcu	*root;
+	size_t				n_entries;
+	size_t				max_prefixlen;
+	size_t				data_size;
+	raw_spinlock_t			lock;
+};
+
+/* This trie implements a longest prefix match algorithm that can be used to
+ * match IP addresses to a stored set of ranges.
+ *
+ * Data stored in @data of struct bpf_lpm_key and struct lpm_trie_node is
+ * interpreted as big endian, so data[0] stores the most significant byte.
+ *
+ * Match ranges are internally stored in instances of struct lpm_trie_node
+ * which each contain their prefix length as well as two pointers that may
+ * lead to more nodes containing more specific matches. Each node also stores
+ * a value that is defined by and returned to userspace via the update_elem
+ * and lookup functions.
+ *
+ * For instance, let's start with a trie that was created with a prefix length
+ * of 32, so it can be used for IPv4 addresses, and one single element that
+ * matches 192.168.0.0/16. The data array would hence contain
+ * [0xc0, 0xa8, 0x00, 0x00] in big-endian notation. This documentation will
+ * stick to IP-address notation for readability though.
+ *
+ * As the trie is empty initially, the new node (1) will be places as root
+ * node, denoted as (R) in the example below. As there are no other node, both
+ * child pointers are %NULL.
+ *
+ *              +----------------+
+ *              |       (1)  (R) |
+ *              | 192.168.0.0/16 |
+ *              |    value: 1    |
+ *              |   [0]    [1]   |
+ *              +----------------+
+ *
+ * Next, let's add a new node (2) matching 192.168.0.0/24. As there is already
+ * a node with the same data and a smaller prefix (ie, a less specific one),
+ * node (2) will become a child of (1). In child index depends on the next bit
+ * that is outside of what (1) matches, and that bit is 0, so (2) will be
+ * child[0] of (1):
+ *
+ *              +----------------+
+ *              |       (1)  (R) |
+ *              | 192.168.0.0/16 |
+ *              |    value: 1    |
+ *              |   [0]    [1]   |
+ *              +----------------+
+ *                   |
+ *    +----------------+
+ *    |       (2)      |
+ *    | 192.168.0.0/24 |
+ *    |    value: 2    |
+ *    |   [0]    [1]   |
+ *    +----------------+
+ *
+ * The child[1] slot of (1) could be filled with another node which has bit #17
+ * (the next bit after the ones that (1) matches on) set to 1. For instance,
+ * 192.168.128.0/24:
+ *
+ *              +----------------+
+ *              |       (1)  (R) |
+ *              | 192.168.0.0/16 |
+ *              |    value: 1    |
+ *              |   [0]    [1]   |
+ *              +----------------+
+ *                   |      |
+ *    +----------------+  +------------------+
+ *    |       (2)      |  |        (3)       |
+ *    | 192.168.0.0/24 |  | 192.168.128.0/24 |
+ *    |    value: 2    |  |     value: 3     |
+ *    |   [0]    [1]   |  |    [0]    [1]    |
+ *    +----------------+  +------------------+
+ *
+ * Let's add another node (4) to the game for 192.168.1.0/24. In order to place
+ * it, node (1) is looked at first, and because (4) of the semantics laid out
+ * above (bit #17 is 0), it would normally be attached to (1) as child[0].
+ * However, that slot is already allocated, so a new node is needed in between.
+ * That node does not have a value attached to it and it will never be
+ * returned to users as result of a lookup. It is only there to differentiate
+ * the traversal further. It will get a prefix as wide as necessary to
+ * distinguish its two children:
+ *
+ *                      +----------------+
+ *                      |       (1)  (R) |
+ *                      | 192.168.0.0/16 |
+ *                      |    value: 1    |
+ *                      |   [0]    [1]   |
+ *                      +----------------+
+ *                           |      |
+ *            +----------------+  +------------------+
+ *            |       (4)  (I) |  |        (3)       |
+ *            | 192.168.0.0/23 |  | 192.168.128.0/24 |
+ *            |    value: ---  |  |     value: 3     |
+ *            |   [0]    [1]   |  |    [0]    [1]    |
+ *            +----------------+  +------------------+
+ *                 |      |
+ *  +----------------+  +----------------+
+ *  |       (2)      |  |       (5)      |
+ *  | 192.168.0.0/24 |  | 192.168.1.0/24 |
+ *  |    value: 2    |  |     value: 5   |
+ *  |   [0]    [1]   |  |   [0]    [1]   |
+ *  +----------------+  +----------------+
+ *
+ * 192.168.1.1/32 would be a child of (5) etc.
+ *
+ * An intermediate node will be turned into a 'real' node on demand. In the
+ * example above, (4) would be re-used if 192.168.0.0/23 is added to the trie.
+ *
+ * A fully populated trie would have a height of 32 nodes, as the trie was
+ * created with a prefix length of 32.
+ *
+ * The lookup starts at the root node. If the current node matches and if there
+ * is a child that can be used to become more specific, the trie is traversed
+ * downwards. The last node in the traversal that is a non-intermediate one is
+ * returned.
+ */
+
+static inline int extract_bit(const u8 *data, size_t index)
+{
+	return !!(data[index / 8] & (1 << (7 - (index % 8))));
+}
+
+/**
+ * longest_prefix_match() - determine the longest prefix
+ * @trie:	The trie to get internal sizes from
+ * @node:	The node to operate on
+ * @key:	The key to compare to @node
+ *
+ * Determine the longest prefix of @node that matches the bits in @key.
+ */
+static size_t longest_prefix_match(const struct lpm_trie *trie,
+				   const struct lpm_trie_node *node,
+				   const struct bpf_lpm_trie_key *key)
+{
+	size_t prefixlen = 0;
+	size_t i;
+
+	for (i = 0; i < trie->data_size; i++) {
+		size_t b;
+
+		b = 8 - fls(node->data[i] ^ key->data[i]);
+		prefixlen += b;
+
+		if (prefixlen >= node->prefixlen || prefixlen >= key->prefixlen)
+			return min(node->prefixlen, key->prefixlen);
+
+		if (b < 8)
+			break;
+	}
+
+	return prefixlen;
+}
+
+/* Called from syscall or from eBPF program */
+static void *trie_lookup_elem(struct bpf_map *map, void *_key)
+{
+	struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
+	struct lpm_trie_node *node, *found = NULL;
+	struct bpf_lpm_trie_key *key = _key;
+
+	/* Start walking the trie from the root node ... */
+
+	for (node = rcu_dereference(trie->root); node;) {
+		unsigned int next_bit;
+		size_t matchlen;
+
+		/* Determine the longest prefix of @node that matches @key.
+		 * If it's the maximum possible prefix for this trie, we have
+		 * an exact match and can return it directly.
+		 */
+		matchlen = longest_prefix_match(trie, node, key);
+		if (matchlen == trie->max_prefixlen) {
+			found = node;
+			break;
+		}
+
+		/* If the number of bits that match is smaller than the prefix
+		 * length of @node, bail out and return the node we have seen
+		 * last in the traversal (ie, the parent).
+		 */
+		if (matchlen < node->prefixlen)
+			break;
+
+		/* Consider this node as return candidate unless it is an
+		 * artificially added intermediate one.
+		 */
+		if (!(node->flags & LPM_TREE_NODE_FLAG_IM))
+			found = node;
+
+		/* If the node match is fully satisfied, let's see if we can
+		 * become more specific. Determine the next bit in the key and
+		 * traverse down.
+		 */
+		next_bit = extract_bit(key->data, node->prefixlen);
+		node = rcu_dereference(node->child[next_bit]);
+	}
+
+	if (!found)
+		return NULL;
+
+	return found->data + trie->data_size;
+}
+
+static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie,
+						 const void *value)
+{
+	struct lpm_trie_node *node;
+	size_t size = sizeof(struct lpm_trie_node) + trie->data_size;
+
+	if (value)
+		size += trie->map.value_size;
+
+	node = kmalloc_node(size, GFP_ATOMIC | __GFP_NOWARN,
+			    trie->map.numa_node);
+	if (!node)
+		return NULL;
+
+	node->flags = 0;
+
+	if (value)
+		memcpy(node->data + trie->data_size, value,
+		       trie->map.value_size);
+
+	return node;
+}
+
+/* Called from syscall or from eBPF program */
+static int trie_update_elem(struct bpf_map *map,
+			    void *_key, void *value, u64 flags)
+{
+	struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
+	struct lpm_trie_node *node, *im_node = NULL, *new_node = NULL;
+	struct lpm_trie_node __rcu **slot;
+	struct bpf_lpm_trie_key *key = _key;
+	unsigned long irq_flags;
+	unsigned int next_bit;
+	size_t matchlen = 0;
+	int ret = 0;
+
+	if (unlikely(flags > BPF_EXIST))
+		return -EINVAL;
+
+	if (key->prefixlen > trie->max_prefixlen)
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&trie->lock, irq_flags);
+
+	/* Allocate and fill a new node */
+
+	if (trie->n_entries == trie->map.max_entries) {
+		ret = -ENOSPC;
+		goto out;
+	}
+
+	new_node = lpm_trie_node_alloc(trie, value);
+	if (!new_node) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	trie->n_entries++;
+
+	new_node->prefixlen = key->prefixlen;
+	RCU_INIT_POINTER(new_node->child[0], NULL);
+	RCU_INIT_POINTER(new_node->child[1], NULL);
+	memcpy(new_node->data, key->data, trie->data_size);
+
+	/* Now find a slot to attach the new node. To do that, walk the tree
+	 * from the root and match as many bits as possible for each node until
+	 * we either find an empty slot or a slot that needs to be replaced by
+	 * an intermediate node.
+	 */
+	slot = &trie->root;
+
+	while ((node = rcu_dereference_protected(*slot,
+					lockdep_is_held(&trie->lock)))) {
+		matchlen = longest_prefix_match(trie, node, key);
+
+		if (node->prefixlen != matchlen ||
+		    node->prefixlen == key->prefixlen ||
+		    node->prefixlen == trie->max_prefixlen)
+			break;
+
+		next_bit = extract_bit(key->data, node->prefixlen);
+		slot = &node->child[next_bit];
+	}
+
+	/* If the slot is empty (a free child pointer or an empty root),
+	 * simply assign the @new_node to that slot and be done.
+	 */
+	if (!node) {
+		rcu_assign_pointer(*slot, new_node);
+		goto out;
+	}
+
+	/* If the slot we picked already exists, replace it with @new_node
+	 * which already has the correct data array set.
+	 */
+	if (node->prefixlen == matchlen) {
+		new_node->child[0] = node->child[0];
+		new_node->child[1] = node->child[1];
+
+		if (!(node->flags & LPM_TREE_NODE_FLAG_IM))
+			trie->n_entries--;
+
+		rcu_assign_pointer(*slot, new_node);
+		kfree_rcu(node, rcu);
+
+		goto out;
+	}
+
+	/* If the new node matches the prefix completely, it must be inserted
+	 * as an ancestor. Simply insert it between @node and *@slot.
+	 */
+	if (matchlen == key->prefixlen) {
+		next_bit = extract_bit(node->data, matchlen);
+		rcu_assign_pointer(new_node->child[next_bit], node);
+		rcu_assign_pointer(*slot, new_node);
+		goto out;
+	}
+
+	im_node = lpm_trie_node_alloc(trie, NULL);
+	if (!im_node) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	im_node->prefixlen = matchlen;
+	im_node->flags |= LPM_TREE_NODE_FLAG_IM;
+	memcpy(im_node->data, node->data, trie->data_size);
+
+	/* Now determine which child to install in which slot */
+	if (extract_bit(key->data, matchlen)) {
+		rcu_assign_pointer(im_node->child[0], node);
+		rcu_assign_pointer(im_node->child[1], new_node);
+	} else {
+		rcu_assign_pointer(im_node->child[0], new_node);
+		rcu_assign_pointer(im_node->child[1], node);
+	}
+
+	/* Finally, assign the intermediate node to the determined spot */
+	rcu_assign_pointer(*slot, im_node);
+
+out:
+	if (ret) {
+		if (new_node)
+			trie->n_entries--;
+
+		kfree(new_node);
+		kfree(im_node);
+	}
+
+	raw_spin_unlock_irqrestore(&trie->lock, irq_flags);
+
+	return ret;
+}
+
+/* Called from syscall or from eBPF program */
+static int trie_delete_elem(struct bpf_map *map, void *_key)
+{
+	struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
+	struct bpf_lpm_trie_key *key = _key;
+	struct lpm_trie_node __rcu **trim, **trim2;
+	struct lpm_trie_node *node, *parent;
+	unsigned long irq_flags;
+	unsigned int next_bit;
+	size_t matchlen = 0;
+	int ret = 0;
+
+	if (key->prefixlen > trie->max_prefixlen)
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&trie->lock, irq_flags);
+
+	/* Walk the tree looking for an exact key/length match and keeping
+	 * track of the path we traverse.  We will need to know the node
+	 * we wish to delete, and the slot that points to the node we want
+	 * to delete.  We may also need to know the nodes parent and the
+	 * slot that contains it.
+	 */
+	trim = &trie->root;
+	trim2 = trim;
+	parent = NULL;
+	while ((node = rcu_dereference_protected(
+		       *trim, lockdep_is_held(&trie->lock)))) {
+		matchlen = longest_prefix_match(trie, node, key);
+
+		if (node->prefixlen != matchlen ||
+		    node->prefixlen == key->prefixlen)
+			break;
+
+		parent = node;
+		trim2 = trim;
+		next_bit = extract_bit(key->data, node->prefixlen);
+		trim = &node->child[next_bit];
+	}
+
+	if (!node || node->prefixlen != key->prefixlen ||
+	    node->prefixlen != matchlen ||
+	    (node->flags & LPM_TREE_NODE_FLAG_IM)) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	trie->n_entries--;
+
+	/* If the node we are removing has two children, simply mark it
+	 * as intermediate and we are done.
+	 */
+	if (rcu_access_pointer(node->child[0]) &&
+	    rcu_access_pointer(node->child[1])) {
+		node->flags |= LPM_TREE_NODE_FLAG_IM;
+		goto out;
+	}
+
+	/* If the parent of the node we are about to delete is an intermediate
+	 * node, and the deleted node doesn't have any children, we can delete
+	 * the intermediate parent as well and promote its other child
+	 * up the tree.  Doing this maintains the invariant that all
+	 * intermediate nodes have exactly 2 children and that there are no
+	 * unnecessary intermediate nodes in the tree.
+	 */
+	if (parent && (parent->flags & LPM_TREE_NODE_FLAG_IM) &&
+	    !node->child[0] && !node->child[1]) {
+		if (node == rcu_access_pointer(parent->child[0]))
+			rcu_assign_pointer(
+				*trim2, rcu_access_pointer(parent->child[1]));
+		else
+			rcu_assign_pointer(
+				*trim2, rcu_access_pointer(parent->child[0]));
+		kfree_rcu(parent, rcu);
+		kfree_rcu(node, rcu);
+		goto out;
+	}
+
+	/* The node we are removing has either zero or one child. If there
+	 * is a child, move it into the removed node's slot then delete
+	 * the node.  Otherwise just clear the slot and delete the node.
+	 */
+	if (node->child[0])
+		rcu_assign_pointer(*trim, rcu_access_pointer(node->child[0]));
+	else if (node->child[1])
+		rcu_assign_pointer(*trim, rcu_access_pointer(node->child[1]));
+	else
+		RCU_INIT_POINTER(*trim, NULL);
+	kfree_rcu(node, rcu);
+
+out:
+	raw_spin_unlock_irqrestore(&trie->lock, irq_flags);
+
+	return ret;
+}
+
+#define LPM_DATA_SIZE_MAX	256
+#define LPM_DATA_SIZE_MIN	1
+
+#define LPM_VAL_SIZE_MAX	(KMALLOC_MAX_SIZE - LPM_DATA_SIZE_MAX - \
+				 sizeof(struct lpm_trie_node))
+#define LPM_VAL_SIZE_MIN	1
+
+#define LPM_KEY_SIZE(X)		(sizeof(struct bpf_lpm_trie_key) + (X))
+#define LPM_KEY_SIZE_MAX	LPM_KEY_SIZE(LPM_DATA_SIZE_MAX)
+#define LPM_KEY_SIZE_MIN	LPM_KEY_SIZE(LPM_DATA_SIZE_MIN)
+
+#define LPM_CREATE_FLAG_MASK	(BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE |	\
+				 BPF_F_RDONLY | BPF_F_WRONLY)
+
+static struct bpf_map *trie_alloc(union bpf_attr *attr)
+{
+	struct lpm_trie *trie;
+	u64 cost = sizeof(*trie), cost_per_node;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	/* check sanity of attributes */
+	if (attr->max_entries == 0 ||
+	    !(attr->map_flags & BPF_F_NO_PREALLOC) ||
+	    attr->map_flags & ~LPM_CREATE_FLAG_MASK ||
+	    attr->key_size < LPM_KEY_SIZE_MIN ||
+	    attr->key_size > LPM_KEY_SIZE_MAX ||
+	    attr->value_size < LPM_VAL_SIZE_MIN ||
+	    attr->value_size > LPM_VAL_SIZE_MAX)
+		return ERR_PTR(-EINVAL);
+
+	trie = kzalloc(sizeof(*trie), GFP_USER | __GFP_NOWARN);
+	if (!trie)
+		return ERR_PTR(-ENOMEM);
+
+	/* copy mandatory map attributes */
+	bpf_map_init_from_attr(&trie->map, attr);
+	trie->data_size = attr->key_size -
+			  offsetof(struct bpf_lpm_trie_key, data);
+	trie->max_prefixlen = trie->data_size * 8;
+
+	cost_per_node = sizeof(struct lpm_trie_node) +
+			attr->value_size + trie->data_size;
+	cost += (u64) attr->max_entries * cost_per_node;
+	if (cost >= U32_MAX - PAGE_SIZE) {
+		ret = -E2BIG;
+		goto out_err;
+	}
+
+	trie->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	ret = bpf_map_precharge_memlock(trie->map.pages);
+	if (ret)
+		goto out_err;
+
+	raw_spin_lock_init(&trie->lock);
+
+	return &trie->map;
+out_err:
+	kfree(trie);
+	return ERR_PTR(ret);
+}
+
+static void trie_free(struct bpf_map *map)
+{
+	struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
+	struct lpm_trie_node __rcu **slot;
+	struct lpm_trie_node *node;
+
+	/* Wait for outstanding programs to complete
+	 * update/lookup/delete/get_next_key and free the trie.
+	 */
+	synchronize_rcu();
+
+	/* Always start at the root and walk down to a node that has no
+	 * children. Then free that node, nullify its reference in the parent
+	 * and start over.
+	 */
+
+	for (;;) {
+		slot = &trie->root;
+
+		for (;;) {
+			node = rcu_dereference_protected(*slot, 1);
+			if (!node)
+				goto out;
+
+			if (rcu_access_pointer(node->child[0])) {
+				slot = &node->child[0];
+				continue;
+			}
+
+			if (rcu_access_pointer(node->child[1])) {
+				slot = &node->child[1];
+				continue;
+			}
+
+			kfree(node);
+			RCU_INIT_POINTER(*slot, NULL);
+			break;
+		}
+	}
+
+out:
+	kfree(trie);
+}
+
+static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key)
+{
+	struct lpm_trie_node *node, *next_node = NULL, *parent, *search_root;
+	struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
+	struct bpf_lpm_trie_key *key = _key, *next_key = _next_key;
+	struct lpm_trie_node **node_stack = NULL;
+	int err = 0, stack_ptr = -1;
+	unsigned int next_bit;
+	size_t matchlen;
+
+	/* The get_next_key follows postorder. For the 4 node example in
+	 * the top of this file, the trie_get_next_key() returns the following
+	 * one after another:
+	 *   192.168.0.0/24
+	 *   192.168.1.0/24
+	 *   192.168.128.0/24
+	 *   192.168.0.0/16
+	 *
+	 * The idea is to return more specific keys before less specific ones.
+	 */
+
+	/* Empty trie */
+	search_root = rcu_dereference(trie->root);
+	if (!search_root)
+		return -ENOENT;
+
+	/* For invalid key, find the leftmost node in the trie */
+	if (!key || key->prefixlen > trie->max_prefixlen)
+		goto find_leftmost;
+
+	node_stack = kmalloc_array(trie->max_prefixlen,
+				   sizeof(struct lpm_trie_node *),
+				   GFP_ATOMIC | __GFP_NOWARN);
+	if (!node_stack)
+		return -ENOMEM;
+
+	/* Try to find the exact node for the given key */
+	for (node = search_root; node;) {
+		node_stack[++stack_ptr] = node;
+		matchlen = longest_prefix_match(trie, node, key);
+		if (node->prefixlen != matchlen ||
+		    node->prefixlen == key->prefixlen)
+			break;
+
+		next_bit = extract_bit(key->data, node->prefixlen);
+		node = rcu_dereference(node->child[next_bit]);
+	}
+	if (!node || node->prefixlen != key->prefixlen ||
+	    (node->flags & LPM_TREE_NODE_FLAG_IM))
+		goto find_leftmost;
+
+	/* The node with the exactly-matching key has been found,
+	 * find the first node in postorder after the matched node.
+	 */
+	node = node_stack[stack_ptr];
+	while (stack_ptr > 0) {
+		parent = node_stack[stack_ptr - 1];
+		if (rcu_dereference(parent->child[0]) == node) {
+			search_root = rcu_dereference(parent->child[1]);
+			if (search_root)
+				goto find_leftmost;
+		}
+		if (!(parent->flags & LPM_TREE_NODE_FLAG_IM)) {
+			next_node = parent;
+			goto do_copy;
+		}
+
+		node = parent;
+		stack_ptr--;
+	}
+
+	/* did not find anything */
+	err = -ENOENT;
+	goto free_stack;
+
+find_leftmost:
+	/* Find the leftmost non-intermediate node, all intermediate nodes
+	 * have exact two children, so this function will never return NULL.
+	 */
+	for (node = search_root; node;) {
+		if (node->flags & LPM_TREE_NODE_FLAG_IM) {
+			node = rcu_dereference(node->child[0]);
+		} else {
+			next_node = node;
+			node = rcu_dereference(node->child[0]);
+			if (!node)
+				node = rcu_dereference(next_node->child[1]);
+		}
+	}
+do_copy:
+	next_key->prefixlen = next_node->prefixlen;
+	memcpy((void *)next_key + offsetof(struct bpf_lpm_trie_key, data),
+	       next_node->data, trie->data_size);
+free_stack:
+	kfree(node_stack);
+	return err;
+}
+
+static int trie_check_btf(const struct bpf_map *map,
+			  const struct btf_type *key_type,
+			  const struct btf_type *value_type)
+{
+	/* Keys must have struct bpf_lpm_trie_key embedded. */
+	return BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ?
+	       -EINVAL : 0;
+}
+
+const struct bpf_map_ops trie_map_ops = {
+	.map_alloc = trie_alloc,
+	.map_free = trie_free,
+	.map_get_next_key = trie_get_next_key,
+	.map_lookup_elem = trie_lookup_elem,
+	.map_update_elem = trie_update_elem,
+	.map_delete_elem = trie_delete_elem,
+	.map_check_btf = trie_check_btf,
+};

kernel/bpf/map_in_map.c

@@ -0,0 +1,116 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/slab.h>
+#include <linux/bpf.h>
+
+#include "map_in_map.h"
+
+struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
+{
+	struct bpf_map *inner_map, *inner_map_meta;
+	u32 inner_map_meta_size;
+	struct fd f;
+
+	f = fdget(inner_map_ufd);
+	inner_map = __bpf_map_get(f);
+	if (IS_ERR(inner_map))
+		return inner_map;
+
+	/* prog_array->owner_prog_type and owner_jited
+	 * is a runtime binding.  Doing static check alone
+	 * in the verifier is not enough.
+	 */
+	if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
+	    inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE) {
+		fdput(f);
+		return ERR_PTR(-ENOTSUPP);
+	}
+
+	/* Does not support >1 level map-in-map */
+	if (inner_map->inner_map_meta) {
+		fdput(f);
+		return ERR_PTR(-EINVAL);
+	}
+
+	inner_map_meta_size = sizeof(*inner_map_meta);
+	/* In some cases verifier needs to access beyond just base map. */
+	if (inner_map->ops == &array_map_ops)
+		inner_map_meta_size = sizeof(struct bpf_array);
+
+	inner_map_meta = kzalloc(inner_map_meta_size, GFP_USER);
+	if (!inner_map_meta) {
+		fdput(f);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	inner_map_meta->map_type = inner_map->map_type;
+	inner_map_meta->key_size = inner_map->key_size;
+	inner_map_meta->value_size = inner_map->value_size;
+	inner_map_meta->map_flags = inner_map->map_flags;
+	inner_map_meta->max_entries = inner_map->max_entries;
+
+	/* Misc members not needed in bpf_map_meta_equal() check. */
+	inner_map_meta->ops = inner_map->ops;
+	if (inner_map->ops == &array_map_ops) {
+		inner_map_meta->unpriv_array = inner_map->unpriv_array;
+		container_of(inner_map_meta, struct bpf_array, map)->index_mask =
+		     container_of(inner_map, struct bpf_array, map)->index_mask;
+	}
+
+	fdput(f);
+	return inner_map_meta;
+}
+
+void bpf_map_meta_free(struct bpf_map *map_meta)
+{
+	kfree(map_meta);
+}
+
+bool bpf_map_meta_equal(const struct bpf_map *meta0,
+			const struct bpf_map *meta1)
+{
+	/* No need to compare ops because it is covered by map_type */
+	return meta0->map_type == meta1->map_type &&
+		meta0->key_size == meta1->key_size &&
+		meta0->value_size == meta1->value_size &&
+		meta0->map_flags == meta1->map_flags &&
+		meta0->max_entries == meta1->max_entries;
+}
+
+void *bpf_map_fd_get_ptr(struct bpf_map *map,
+			 struct file *map_file /* not used */,
+			 int ufd)
+{
+	struct bpf_map *inner_map;
+	struct fd f;
+
+	f = fdget(ufd);
+	inner_map = __bpf_map_get(f);
+	if (IS_ERR(inner_map))
+		return inner_map;
+
+	if (bpf_map_meta_equal(map->inner_map_meta, inner_map))
+		inner_map = bpf_map_inc(inner_map, false);
+	else
+		inner_map = ERR_PTR(-EINVAL);
+
+	fdput(f);
+	return inner_map;
+}
+
+void bpf_map_fd_put_ptr(void *ptr)
+{
+	/* ptr->ops->map_free() has to go through one
+	 * rcu grace period by itself.
+	 */
+	bpf_map_put(ptr);
+}
+
+u32 bpf_map_fd_sys_lookup_elem(void *ptr)
+{
+	return ((struct bpf_map *)ptr)->id;
+}

kernel/bpf/map_in_map.h

@@ -0,0 +1,24 @@
+/* Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef __MAP_IN_MAP_H__
+#define __MAP_IN_MAP_H__
+
+#include <linux/types.h>
+
+struct file;
+struct bpf_map;
+
+struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd);
+void bpf_map_meta_free(struct bpf_map *map_meta);
+bool bpf_map_meta_equal(const struct bpf_map *meta0,
+			const struct bpf_map *meta1);
+void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file,
+			 int ufd);
+void bpf_map_fd_put_ptr(void *ptr);
+u32 bpf_map_fd_sys_lookup_elem(void *ptr);
+
+#endif

kernel/bpf/offload.c

@@ -0,0 +1,671 @@
+/*
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
+ *
+ * This software is licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree.
+ *
+ * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
+ * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+ * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+ * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE
+ * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME
+ * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+ */
+
+#include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
+#include <linux/bug.h>
+#include <linux/kdev_t.h>
+#include <linux/list.h>
+#include <linux/lockdep.h>
+#include <linux/netdevice.h>
+#include <linux/printk.h>
+#include <linux/proc_ns.h>
+#include <linux/rhashtable.h>
+#include <linux/rtnetlink.h>
+#include <linux/rwsem.h>
+
+/* Protects offdevs, members of bpf_offload_netdev and offload members
+ * of all progs.
+ * RTNL lock cannot be taken when holding this lock.
+ */
+static DECLARE_RWSEM(bpf_devs_lock);
+
+struct bpf_offload_dev {
+	struct list_head netdevs;
+};
+
+struct bpf_offload_netdev {
+	struct rhash_head l;
+	struct net_device *netdev;
+	struct bpf_offload_dev *offdev;
+	struct list_head progs;
+	struct list_head maps;
+	struct list_head offdev_netdevs;
+};
+
+static const struct rhashtable_params offdevs_params = {
+	.nelem_hint		= 4,
+	.key_len		= sizeof(struct net_device *),
+	.key_offset		= offsetof(struct bpf_offload_netdev, netdev),
+	.head_offset		= offsetof(struct bpf_offload_netdev, l),
+	.automatic_shrinking	= true,
+};
+
+static struct rhashtable offdevs;
+static bool offdevs_inited;
+
+static int bpf_dev_offload_check(struct net_device *netdev)
+{
+	if (!netdev)
+		return -EINVAL;
+	if (!netdev->netdev_ops->ndo_bpf)
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static struct bpf_offload_netdev *
+bpf_offload_find_netdev(struct net_device *netdev)
+{
+	lockdep_assert_held(&bpf_devs_lock);
+
+	if (!offdevs_inited)
+		return NULL;
+	return rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
+}
+
+int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
+{
+	struct bpf_offload_netdev *ondev;
+	struct bpf_prog_offload *offload;
+	int err;
+
+	if (attr->prog_type != BPF_PROG_TYPE_SCHED_CLS &&
+	    attr->prog_type != BPF_PROG_TYPE_XDP)
+		return -EINVAL;
+
+	if (attr->prog_flags)
+		return -EINVAL;
+
+	offload = kzalloc(sizeof(*offload), GFP_USER);
+	if (!offload)
+		return -ENOMEM;
+
+	offload->prog = prog;
+
+	offload->netdev = dev_get_by_index(current->nsproxy->net_ns,
+					   attr->prog_ifindex);
+	err = bpf_dev_offload_check(offload->netdev);
+	if (err)
+		goto err_maybe_put;
+
+	down_write(&bpf_devs_lock);
+	ondev = bpf_offload_find_netdev(offload->netdev);
+	if (!ondev) {
+		err = -EINVAL;
+		goto err_unlock;
+	}
+	prog->aux->offload = offload;
+	list_add_tail(&offload->offloads, &ondev->progs);
+	dev_put(offload->netdev);
+	up_write(&bpf_devs_lock);
+
+	return 0;
+err_unlock:
+	up_write(&bpf_devs_lock);
+err_maybe_put:
+	if (offload->netdev)
+		dev_put(offload->netdev);
+	kfree(offload);
+	return err;
+}
+
+static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd,
+			     struct netdev_bpf *data)
+{
+	struct bpf_prog_offload *offload = prog->aux->offload;
+	struct net_device *netdev;
+
+	ASSERT_RTNL();
+
+	if (!offload)
+		return -ENODEV;
+	netdev = offload->netdev;
+
+	data->command = cmd;
+
+	return netdev->netdev_ops->ndo_bpf(netdev, data);
+}
+
+int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env)
+{
+	struct netdev_bpf data = {};
+	int err;
+
+	data.verifier.prog = env->prog;
+
+	rtnl_lock();
+	err = __bpf_offload_ndo(env->prog, BPF_OFFLOAD_VERIFIER_PREP, &data);
+	if (err)
+		goto exit_unlock;
+
+	env->prog->aux->offload->dev_ops = data.verifier.ops;
+	env->prog->aux->offload->dev_state = true;
+exit_unlock:
+	rtnl_unlock();
+	return err;
+}
+
+int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
+				 int insn_idx, int prev_insn_idx)
+{
+	struct bpf_prog_offload *offload;
+	int ret = -ENODEV;
+
+	down_read(&bpf_devs_lock);
+	offload = env->prog->aux->offload;
+	if (offload)
+		ret = offload->dev_ops->insn_hook(env, insn_idx, prev_insn_idx);
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+
+static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
+{
+	struct bpf_prog_offload *offload = prog->aux->offload;
+	struct netdev_bpf data = {};
+
+	data.offload.prog = prog;
+
+	if (offload->dev_state)
+		WARN_ON(__bpf_offload_ndo(prog, BPF_OFFLOAD_DESTROY, &data));
+
+	/* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */
+	bpf_prog_free_id(prog, true);
+
+	list_del_init(&offload->offloads);
+	kfree(offload);
+	prog->aux->offload = NULL;
+}
+
+void bpf_prog_offload_destroy(struct bpf_prog *prog)
+{
+	rtnl_lock();
+	down_write(&bpf_devs_lock);
+	if (prog->aux->offload)
+		__bpf_prog_offload_destroy(prog);
+	up_write(&bpf_devs_lock);
+	rtnl_unlock();
+}
+
+static int bpf_prog_offload_translate(struct bpf_prog *prog)
+{
+	struct netdev_bpf data = {};
+	int ret;
+
+	data.offload.prog = prog;
+
+	rtnl_lock();
+	ret = __bpf_offload_ndo(prog, BPF_OFFLOAD_TRANSLATE, &data);
+	rtnl_unlock();
+
+	return ret;
+}
+
+static unsigned int bpf_prog_warn_on_exec(const void *ctx,
+					  const struct bpf_insn *insn)
+{
+	WARN(1, "attempt to execute device eBPF program on the host!");
+	return 0;
+}
+
+int bpf_prog_offload_compile(struct bpf_prog *prog)
+{
+	prog->bpf_func = bpf_prog_warn_on_exec;
+
+	return bpf_prog_offload_translate(prog);
+}
+
+struct ns_get_path_bpf_prog_args {
+	struct bpf_prog *prog;
+	struct bpf_prog_info *info;
+};
+
+static struct ns_common *bpf_prog_offload_info_fill_ns(void *private_data)
+{
+	struct ns_get_path_bpf_prog_args *args = private_data;
+	struct bpf_prog_aux *aux = args->prog->aux;
+	struct ns_common *ns;
+	struct net *net;
+
+	rtnl_lock();
+	down_read(&bpf_devs_lock);
+
+	if (aux->offload) {
+		args->info->ifindex = aux->offload->netdev->ifindex;
+		net = dev_net(aux->offload->netdev);
+		get_net(net);
+		ns = &net->ns;
+	} else {
+		args->info->ifindex = 0;
+		ns = NULL;
+	}
+
+	up_read(&bpf_devs_lock);
+	rtnl_unlock();
+
+	return ns;
+}
+
+int bpf_prog_offload_info_fill(struct bpf_prog_info *info,
+			       struct bpf_prog *prog)
+{
+	struct ns_get_path_bpf_prog_args args = {
+		.prog	= prog,
+		.info	= info,
+	};
+	struct bpf_prog_aux *aux = prog->aux;
+	struct inode *ns_inode;
+	struct path ns_path;
+	char __user *uinsns;
+	void *res;
+	u32 ulen;
+
+	res = ns_get_path_cb(&ns_path, bpf_prog_offload_info_fill_ns, &args);
+	if (IS_ERR(res)) {
+		if (!info->ifindex)
+			return -ENODEV;
+		return PTR_ERR(res);
+	}
+
+	down_read(&bpf_devs_lock);
+
+	if (!aux->offload) {
+		up_read(&bpf_devs_lock);
+		return -ENODEV;
+	}
+
+	ulen = info->jited_prog_len;
+	info->jited_prog_len = aux->offload->jited_len;
+	if (info->jited_prog_len && ulen) {
+		uinsns = u64_to_user_ptr(info->jited_prog_insns);
+		ulen = min_t(u32, info->jited_prog_len, ulen);
+		if (copy_to_user(uinsns, aux->offload->jited_image, ulen)) {
+			up_read(&bpf_devs_lock);
+			return -EFAULT;
+		}
+	}
+
+	up_read(&bpf_devs_lock);
+
+	ns_inode = ns_path.dentry->d_inode;
+	info->netns_dev = new_encode_dev(ns_inode->i_sb->s_dev);
+	info->netns_ino = ns_inode->i_ino;
+	path_put(&ns_path);
+
+	return 0;
+}
+
+const struct bpf_prog_ops bpf_offload_prog_ops = {
+};
+
+static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap,
+			       enum bpf_netdev_command cmd)
+{
+	struct netdev_bpf data = {};
+	struct net_device *netdev;
+
+	ASSERT_RTNL();
+
+	data.command = cmd;
+	data.offmap = offmap;
+	/* Caller must make sure netdev is valid */
+	netdev = offmap->netdev;
+
+	return netdev->netdev_ops->ndo_bpf(netdev, &data);
+}
+
+struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct bpf_offload_netdev *ondev;
+	struct bpf_offloaded_map *offmap;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+	if (attr->map_type != BPF_MAP_TYPE_ARRAY &&
+	    attr->map_type != BPF_MAP_TYPE_HASH)
+		return ERR_PTR(-EINVAL);
+
+	offmap = kzalloc(sizeof(*offmap), GFP_USER);
+	if (!offmap)
+		return ERR_PTR(-ENOMEM);
+
+	bpf_map_init_from_attr(&offmap->map, attr);
+
+	rtnl_lock();
+	down_write(&bpf_devs_lock);
+	offmap->netdev = __dev_get_by_index(net, attr->map_ifindex);
+	err = bpf_dev_offload_check(offmap->netdev);
+	if (err)
+		goto err_unlock;
+
+	ondev = bpf_offload_find_netdev(offmap->netdev);
+	if (!ondev) {
+		err = -EINVAL;
+		goto err_unlock;
+	}
+
+	err = bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_ALLOC);
+	if (err)
+		goto err_unlock;
+
+	list_add_tail(&offmap->offloads, &ondev->maps);
+	up_write(&bpf_devs_lock);
+	rtnl_unlock();
+
+	return &offmap->map;
+
+err_unlock:
+	up_write(&bpf_devs_lock);
+	rtnl_unlock();
+	kfree(offmap);
+	return ERR_PTR(err);
+}
+
+static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap)
+{
+	WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE));
+	/* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */
+	bpf_map_free_id(&offmap->map, true);
+	list_del_init(&offmap->offloads);
+	offmap->netdev = NULL;
+}
+
+void bpf_map_offload_map_free(struct bpf_map *map)
+{
+	struct bpf_offloaded_map *offmap = map_to_offmap(map);
+
+	rtnl_lock();
+	down_write(&bpf_devs_lock);
+	if (offmap->netdev)
+		__bpf_map_offload_destroy(offmap);
+	up_write(&bpf_devs_lock);
+	rtnl_unlock();
+
+	kfree(offmap);
+}
+
+int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value)
+{
+	struct bpf_offloaded_map *offmap = map_to_offmap(map);
+	int ret = -ENODEV;
+
+	down_read(&bpf_devs_lock);
+	if (offmap->netdev)
+		ret = offmap->dev_ops->map_lookup_elem(offmap, key, value);
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+
+int bpf_map_offload_update_elem(struct bpf_map *map,
+				void *key, void *value, u64 flags)
+{
+	struct bpf_offloaded_map *offmap = map_to_offmap(map);
+	int ret = -ENODEV;
+
+	if (unlikely(flags > BPF_EXIST))
+		return -EINVAL;
+
+	down_read(&bpf_devs_lock);
+	if (offmap->netdev)
+		ret = offmap->dev_ops->map_update_elem(offmap, key, value,
+						       flags);
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+
+int bpf_map_offload_delete_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_offloaded_map *offmap = map_to_offmap(map);
+	int ret = -ENODEV;
+
+	down_read(&bpf_devs_lock);
+	if (offmap->netdev)
+		ret = offmap->dev_ops->map_delete_elem(offmap, key);
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+
+int bpf_map_offload_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	struct bpf_offloaded_map *offmap = map_to_offmap(map);
+	int ret = -ENODEV;
+
+	down_read(&bpf_devs_lock);
+	if (offmap->netdev)
+		ret = offmap->dev_ops->map_get_next_key(offmap, key, next_key);
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+
+struct ns_get_path_bpf_map_args {
+	struct bpf_offloaded_map *offmap;
+	struct bpf_map_info *info;
+};
+
+static struct ns_common *bpf_map_offload_info_fill_ns(void *private_data)
+{
+	struct ns_get_path_bpf_map_args *args = private_data;
+	struct ns_common *ns;
+	struct net *net;
+
+	rtnl_lock();
+	down_read(&bpf_devs_lock);
+
+	if (args->offmap->netdev) {
+		args->info->ifindex = args->offmap->netdev->ifindex;
+		net = dev_net(args->offmap->netdev);
+		get_net(net);
+		ns = &net->ns;
+	} else {
+		args->info->ifindex = 0;
+		ns = NULL;
+	}
+
+	up_read(&bpf_devs_lock);
+	rtnl_unlock();
+
+	return ns;
+}
+
+int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map)
+{
+	struct ns_get_path_bpf_map_args args = {
+		.offmap	= map_to_offmap(map),
+		.info	= info,
+	};
+	struct inode *ns_inode;
+	struct path ns_path;
+	void *res;
+
+	res = ns_get_path_cb(&ns_path, bpf_map_offload_info_fill_ns, &args);
+	if (IS_ERR(res)) {
+		if (!info->ifindex)
+			return -ENODEV;
+		return PTR_ERR(res);
+	}
+
+	ns_inode = ns_path.dentry->d_inode;
+	info->netns_dev = new_encode_dev(ns_inode->i_sb->s_dev);
+	info->netns_ino = ns_inode->i_ino;
+	path_put(&ns_path);
+
+	return 0;
+}
+
+static bool __bpf_offload_dev_match(struct bpf_prog *prog,
+				    struct net_device *netdev)
+{
+	struct bpf_offload_netdev *ondev1, *ondev2;
+	struct bpf_prog_offload *offload;
+
+	if (!bpf_prog_is_dev_bound(prog->aux))
+		return false;
+
+	offload = prog->aux->offload;
+	if (!offload)
+		return false;
+	if (offload->netdev == netdev)
+		return true;
+
+	ondev1 = bpf_offload_find_netdev(offload->netdev);
+	ondev2 = bpf_offload_find_netdev(netdev);
+
+	return ondev1 && ondev2 && ondev1->offdev == ondev2->offdev;
+}
+
+bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev)
+{
+	bool ret;
+
+	down_read(&bpf_devs_lock);
+	ret = __bpf_offload_dev_match(prog, netdev);
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_match);
+
+bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map)
+{
+	struct bpf_offloaded_map *offmap;
+	bool ret;
+
+	if (!bpf_map_is_dev_bound(map))
+		return bpf_map_offload_neutral(map);
+	offmap = map_to_offmap(map);
+
+	down_read(&bpf_devs_lock);
+	ret = __bpf_offload_dev_match(prog, offmap->netdev);
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+
+int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
+				    struct net_device *netdev)
+{
+	struct bpf_offload_netdev *ondev;
+	int err;
+
+	ondev = kzalloc(sizeof(*ondev), GFP_KERNEL);
+	if (!ondev)
+		return -ENOMEM;
+
+	ondev->netdev = netdev;
+	ondev->offdev = offdev;
+	INIT_LIST_HEAD(&ondev->progs);
+	INIT_LIST_HEAD(&ondev->maps);
+
+	down_write(&bpf_devs_lock);
+	err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params);
+	if (err) {
+		netdev_warn(netdev, "failed to register for BPF offload\n");
+		goto err_unlock_free;
+	}
+
+	list_add(&ondev->offdev_netdevs, &offdev->netdevs);
+	up_write(&bpf_devs_lock);
+	return 0;
+
+err_unlock_free:
+	up_write(&bpf_devs_lock);
+	kfree(ondev);
+	return err;
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register);
+
+void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
+				       struct net_device *netdev)
+{
+	struct bpf_offload_netdev *ondev, *altdev;
+	struct bpf_offloaded_map *offmap, *mtmp;
+	struct bpf_prog_offload *offload, *ptmp;
+
+	ASSERT_RTNL();
+
+	down_write(&bpf_devs_lock);
+	ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
+	if (WARN_ON(!ondev))
+		goto unlock;
+
+	WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params));
+	list_del(&ondev->offdev_netdevs);
+
+	/* Try to move the objects to another netdev of the device */
+	altdev = list_first_entry_or_null(&offdev->netdevs,
+					  struct bpf_offload_netdev,
+					  offdev_netdevs);
+	if (altdev) {
+		list_for_each_entry(offload, &ondev->progs, offloads)
+			offload->netdev = altdev->netdev;
+		list_splice_init(&ondev->progs, &altdev->progs);
+
+		list_for_each_entry(offmap, &ondev->maps, offloads)
+			offmap->netdev = altdev->netdev;
+		list_splice_init(&ondev->maps, &altdev->maps);
+	} else {
+		list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads)
+			__bpf_prog_offload_destroy(offload->prog);
+		list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads)
+			__bpf_map_offload_destroy(offmap);
+	}
+
+	WARN_ON(!list_empty(&ondev->progs));
+	WARN_ON(!list_empty(&ondev->maps));
+	kfree(ondev);
+unlock:
+	up_write(&bpf_devs_lock);
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister);
+
+struct bpf_offload_dev *bpf_offload_dev_create(void)
+{
+	struct bpf_offload_dev *offdev;
+	int err;
+
+	down_write(&bpf_devs_lock);
+	if (!offdevs_inited) {
+		err = rhashtable_init(&offdevs, &offdevs_params);
+		if (err) {
+			up_write(&bpf_devs_lock);
+			return ERR_PTR(err);
+		}
+		offdevs_inited = true;
+	}
+	up_write(&bpf_devs_lock);
+
+	offdev = kzalloc(sizeof(*offdev), GFP_KERNEL);
+	if (!offdev)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&offdev->netdevs);
+
+	return offdev;
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_create);
+
+void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev)
+{
+	WARN_ON(!list_empty(&offdev->netdevs));
+	kfree(offdev);
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_destroy);

kernel/bpf/percpu_freelist.c

@@ -0,0 +1,121 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include "percpu_freelist.h"
+
+int pcpu_freelist_init(struct pcpu_freelist *s)
+{
+	int cpu;
+
+	s->freelist = alloc_percpu(struct pcpu_freelist_head);
+	if (!s->freelist)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu) {
+		struct pcpu_freelist_head *head = per_cpu_ptr(s->freelist, cpu);
+
+		raw_spin_lock_init(&head->lock);
+		head->first = NULL;
+	}
+	return 0;
+}
+
+void pcpu_freelist_destroy(struct pcpu_freelist *s)
+{
+	free_percpu(s->freelist);
+}
+
+static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head,
+					 struct pcpu_freelist_node *node)
+{
+	raw_spin_lock(&head->lock);
+	node->next = head->first;
+	head->first = node;
+	raw_spin_unlock(&head->lock);
+}
+
+void __pcpu_freelist_push(struct pcpu_freelist *s,
+			struct pcpu_freelist_node *node)
+{
+	struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist);
+
+	___pcpu_freelist_push(head, node);
+}
+
+void pcpu_freelist_push(struct pcpu_freelist *s,
+			struct pcpu_freelist_node *node)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__pcpu_freelist_push(s, node);
+	local_irq_restore(flags);
+}
+
+void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
+			    u32 nr_elems)
+{
+	struct pcpu_freelist_head *head;
+	unsigned long flags;
+	int i, cpu, pcpu_entries;
+
+	pcpu_entries = nr_elems / num_possible_cpus() + 1;
+	i = 0;
+
+	/* disable irq to workaround lockdep false positive
+	 * in bpf usage pcpu_freelist_populate() will never race
+	 * with pcpu_freelist_push()
+	 */
+	local_irq_save(flags);
+	for_each_possible_cpu(cpu) {
+again:
+		head = per_cpu_ptr(s->freelist, cpu);
+		___pcpu_freelist_push(head, buf);
+		i++;
+		buf += elem_size;
+		if (i == nr_elems)
+			break;
+		if (i % pcpu_entries)
+			goto again;
+	}
+	local_irq_restore(flags);
+}
+
+struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s)
+{
+	struct pcpu_freelist_head *head;
+	struct pcpu_freelist_node *node;
+	int orig_cpu, cpu;
+
+	orig_cpu = cpu = raw_smp_processor_id();
+	while (1) {
+		head = per_cpu_ptr(s->freelist, cpu);
+		raw_spin_lock(&head->lock);
+		node = head->first;
+		if (node) {
+			head->first = node->next;
+			raw_spin_unlock(&head->lock);
+			return node;
+		}
+		raw_spin_unlock(&head->lock);
+		cpu = cpumask_next(cpu, cpu_possible_mask);
+		if (cpu >= nr_cpu_ids)
+			cpu = 0;
+		if (cpu == orig_cpu)
+			return NULL;
+	}
+}
+
+struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s)
+{
+	struct pcpu_freelist_node *ret;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	ret = __pcpu_freelist_pop(s);
+	local_irq_restore(flags);
+	return ret;
+}

kernel/bpf/percpu_freelist.h

@@ -0,0 +1,35 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef __PERCPU_FREELIST_H__
+#define __PERCPU_FREELIST_H__
+#include <linux/spinlock.h>
+#include <linux/percpu.h>
+
+struct pcpu_freelist_head {
+	struct pcpu_freelist_node *first;
+	raw_spinlock_t lock;
+};
+
+struct pcpu_freelist {
+	struct pcpu_freelist_head __percpu *freelist;
+};
+
+struct pcpu_freelist_node {
+	struct pcpu_freelist_node *next;
+};
+
+/* pcpu_freelist_* do spin_lock_irqsave. */
+void pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *);
+struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *);
+/* __pcpu_freelist_* do spin_lock only. caller must disable irqs. */
+void __pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *);
+struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *);
+void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
+			    u32 nr_elems);
+int pcpu_freelist_init(struct pcpu_freelist *);
+void pcpu_freelist_destroy(struct pcpu_freelist *s);
+#endif

kernel/bpf/reuseport_array.c

@@ -0,0 +1,363 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Facebook
+ */
+#include <linux/bpf.h>
+#include <linux/err.h>
+#include <linux/sock_diag.h>
+#include <net/sock_reuseport.h>
+
+struct reuseport_array {
+	struct bpf_map map;
+	struct sock __rcu *ptrs[];
+};
+
+static struct reuseport_array *reuseport_array(struct bpf_map *map)
+{
+	return (struct reuseport_array *)map;
+}
+
+/* The caller must hold the reuseport_lock */
+void bpf_sk_reuseport_detach(struct sock *sk)
+{
+	struct sock __rcu **socks;
+
+	write_lock_bh(&sk->sk_callback_lock);
+	socks = sk->sk_user_data;
+	if (socks) {
+		WRITE_ONCE(sk->sk_user_data, NULL);
+		/*
+		 * Do not move this NULL assignment outside of
+		 * sk->sk_callback_lock because there is
+		 * a race with reuseport_array_free()
+		 * which does not hold the reuseport_lock.
+		 */
+		RCU_INIT_POINTER(*socks, NULL);
+	}
+	write_unlock_bh(&sk->sk_callback_lock);
+}
+
+static int reuseport_array_alloc_check(union bpf_attr *attr)
+{
+	if (attr->value_size != sizeof(u32) &&
+	    attr->value_size != sizeof(u64))
+		return -EINVAL;
+
+	return array_map_alloc_check(attr);
+}
+
+static void *reuseport_array_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct reuseport_array *array = reuseport_array(map);
+	u32 index = *(u32 *)key;
+
+	if (unlikely(index >= array->map.max_entries))
+		return NULL;
+
+	return rcu_dereference(array->ptrs[index]);
+}
+
+/* Called from syscall only */
+static int reuseport_array_delete_elem(struct bpf_map *map, void *key)
+{
+	struct reuseport_array *array = reuseport_array(map);
+	u32 index = *(u32 *)key;
+	struct sock *sk;
+	int err;
+
+	if (index >= map->max_entries)
+		return -E2BIG;
+
+	if (!rcu_access_pointer(array->ptrs[index]))
+		return -ENOENT;
+
+	spin_lock_bh(&reuseport_lock);
+
+	sk = rcu_dereference_protected(array->ptrs[index],
+				       lockdep_is_held(&reuseport_lock));
+	if (sk) {
+		write_lock_bh(&sk->sk_callback_lock);
+		WRITE_ONCE(sk->sk_user_data, NULL);
+		RCU_INIT_POINTER(array->ptrs[index], NULL);
+		write_unlock_bh(&sk->sk_callback_lock);
+		err = 0;
+	} else {
+		err = -ENOENT;
+	}
+
+	spin_unlock_bh(&reuseport_lock);
+
+	return err;
+}
+
+static void reuseport_array_free(struct bpf_map *map)
+{
+	struct reuseport_array *array = reuseport_array(map);
+	struct sock *sk;
+	u32 i;
+
+	synchronize_rcu();
+
+	/*
+	 * ops->map_*_elem() will not be able to access this
+	 * array now. Hence, this function only races with
+	 * bpf_sk_reuseport_detach() which was triggerred by
+	 * close() or disconnect().
+	 *
+	 * This function and bpf_sk_reuseport_detach() are
+	 * both removing sk from "array".  Who removes it
+	 * first does not matter.
+	 *
+	 * The only concern here is bpf_sk_reuseport_detach()
+	 * may access "array" which is being freed here.
+	 * bpf_sk_reuseport_detach() access this "array"
+	 * through sk->sk_user_data _and_ with sk->sk_callback_lock
+	 * held which is enough because this "array" is not freed
+	 * until all sk->sk_user_data has stopped referencing this "array".
+	 *
+	 * Hence, due to the above, taking "reuseport_lock" is not
+	 * needed here.
+	 */
+
+	/*
+	 * Since reuseport_lock is not taken, sk is accessed under
+	 * rcu_read_lock()
+	 */
+	rcu_read_lock();
+	for (i = 0; i < map->max_entries; i++) {
+		sk = rcu_dereference(array->ptrs[i]);
+		if (sk) {
+			write_lock_bh(&sk->sk_callback_lock);
+			/*
+			 * No need for WRITE_ONCE(). At this point,
+			 * no one is reading it without taking the
+			 * sk->sk_callback_lock.
+			 */
+			sk->sk_user_data = NULL;
+			write_unlock_bh(&sk->sk_callback_lock);
+			RCU_INIT_POINTER(array->ptrs[i], NULL);
+		}
+	}
+	rcu_read_unlock();
+
+	/*
+	 * Once reaching here, all sk->sk_user_data is not
+	 * referenceing this "array".  "array" can be freed now.
+	 */
+	bpf_map_area_free(array);
+}
+
+static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr)
+{
+	int err, numa_node = bpf_map_attr_numa_node(attr);
+	struct reuseport_array *array;
+	u64 cost, array_size;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	array_size = sizeof(*array);
+	array_size += (u64)attr->max_entries * sizeof(struct sock *);
+
+	/* make sure there is no u32 overflow later in round_up() */
+	cost = array_size;
+	if (cost >= U32_MAX - PAGE_SIZE)
+		return ERR_PTR(-ENOMEM);
+	cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	err = bpf_map_precharge_memlock(cost);
+	if (err)
+		return ERR_PTR(err);
+
+	/* allocate all map elements and zero-initialize them */
+	array = bpf_map_area_alloc(array_size, numa_node);
+	if (!array)
+		return ERR_PTR(-ENOMEM);
+
+	/* copy mandatory map attributes */
+	bpf_map_init_from_attr(&array->map, attr);
+	array->map.pages = cost;
+
+	return &array->map;
+}
+
+int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
+				       void *value)
+{
+	struct sock *sk;
+	int err;
+
+	if (map->value_size != sizeof(u64))
+		return -ENOSPC;
+
+	rcu_read_lock();
+	sk = reuseport_array_lookup_elem(map, key);
+	if (sk) {
+		*(u64 *)value = sock_gen_cookie(sk);
+		err = 0;
+	} else {
+		err = -ENOENT;
+	}
+	rcu_read_unlock();
+
+	return err;
+}
+
+static int
+reuseport_array_update_check(const struct reuseport_array *array,
+			     const struct sock *nsk,
+			     const struct sock *osk,
+			     const struct sock_reuseport *nsk_reuse,
+			     u32 map_flags)
+{
+	if (osk && map_flags == BPF_NOEXIST)
+		return -EEXIST;
+
+	if (!osk && map_flags == BPF_EXIST)
+		return -ENOENT;
+
+	if (nsk->sk_protocol != IPPROTO_UDP && nsk->sk_protocol != IPPROTO_TCP)
+		return -ENOTSUPP;
+
+	if (nsk->sk_family != AF_INET && nsk->sk_family != AF_INET6)
+		return -ENOTSUPP;
+
+	if (nsk->sk_type != SOCK_STREAM && nsk->sk_type != SOCK_DGRAM)
+		return -ENOTSUPP;
+
+	/*
+	 * sk must be hashed (i.e. listening in the TCP case or binded
+	 * in the UDP case) and
+	 * it must also be a SO_REUSEPORT sk (i.e. reuse cannot be NULL).
+	 *
+	 * Also, sk will be used in bpf helper that is protected by
+	 * rcu_read_lock().
+	 */
+	if (!sock_flag(nsk, SOCK_RCU_FREE) || !sk_hashed(nsk) || !nsk_reuse)
+		return -EINVAL;
+
+	/* READ_ONCE because the sk->sk_callback_lock may not be held here */
+	if (READ_ONCE(nsk->sk_user_data))
+		return -EBUSY;
+
+	return 0;
+}
+
+/*
+ * Called from syscall only.
+ * The "nsk" in the fd refcnt.
+ * The "osk" and "reuse" are protected by reuseport_lock.
+ */
+int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
+				       void *value, u64 map_flags)
+{
+	struct reuseport_array *array = reuseport_array(map);
+	struct sock *free_osk = NULL, *osk, *nsk;
+	struct sock_reuseport *reuse;
+	u32 index = *(u32 *)key;
+	struct socket *socket;
+	int err, fd;
+
+	if (map_flags > BPF_EXIST)
+		return -EINVAL;
+
+	if (index >= map->max_entries)
+		return -E2BIG;
+
+	if (map->value_size == sizeof(u64)) {
+		u64 fd64 = *(u64 *)value;
+
+		if (fd64 > S32_MAX)
+			return -EINVAL;
+		fd = fd64;
+	} else {
+		fd = *(int *)value;
+	}
+
+	socket = sockfd_lookup(fd, &err);
+	if (!socket)
+		return err;
+
+	nsk = socket->sk;
+	if (!nsk) {
+		err = -EINVAL;
+		goto put_file;
+	}
+
+	/* Quick checks before taking reuseport_lock */
+	err = reuseport_array_update_check(array, nsk,
+					   rcu_access_pointer(array->ptrs[index]),
+					   rcu_access_pointer(nsk->sk_reuseport_cb),
+					   map_flags);
+	if (err)
+		goto put_file;
+
+	spin_lock_bh(&reuseport_lock);
+	/*
+	 * Some of the checks only need reuseport_lock
+	 * but it is done under sk_callback_lock also
+	 * for simplicity reason.
+	 */
+	write_lock_bh(&nsk->sk_callback_lock);
+
+	osk = rcu_dereference_protected(array->ptrs[index],
+					lockdep_is_held(&reuseport_lock));
+	reuse = rcu_dereference_protected(nsk->sk_reuseport_cb,
+					  lockdep_is_held(&reuseport_lock));
+	err = reuseport_array_update_check(array, nsk, osk, reuse, map_flags);
+	if (err)
+		goto put_file_unlock;
+
+	/* Ensure reuse->reuseport_id is set */
+	err = reuseport_get_id(reuse);
+	if (err < 0)
+		goto put_file_unlock;
+
+	WRITE_ONCE(nsk->sk_user_data, &array->ptrs[index]);
+	rcu_assign_pointer(array->ptrs[index], nsk);
+	free_osk = osk;
+	err = 0;
+
+put_file_unlock:
+	write_unlock_bh(&nsk->sk_callback_lock);
+
+	if (free_osk) {
+		write_lock_bh(&free_osk->sk_callback_lock);
+		WRITE_ONCE(free_osk->sk_user_data, NULL);
+		write_unlock_bh(&free_osk->sk_callback_lock);
+	}
+
+	spin_unlock_bh(&reuseport_lock);
+put_file:
+	fput(socket->file);
+	return err;
+}
+
+/* Called from syscall */
+static int reuseport_array_get_next_key(struct bpf_map *map, void *key,
+					void *next_key)
+{
+	struct reuseport_array *array = reuseport_array(map);
+	u32 index = key ? *(u32 *)key : U32_MAX;
+	u32 *next = (u32 *)next_key;
+
+	if (index >= array->map.max_entries) {
+		*next = 0;
+		return 0;
+	}
+
+	if (index == array->map.max_entries - 1)
+		return -ENOENT;
+
+	*next = index + 1;
+	return 0;
+}
+
+const struct bpf_map_ops reuseport_array_ops = {
+	.map_alloc_check = reuseport_array_alloc_check,
+	.map_alloc = reuseport_array_alloc,
+	.map_free = reuseport_array_free,
+	.map_lookup_elem = reuseport_array_lookup_elem,
+	.map_get_next_key = reuseport_array_get_next_key,
+	.map_delete_elem = reuseport_array_delete_elem,
+};

kernel/bpf/stackmap.c

@@ -0,0 +1,639 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/bpf.h>
+#include <linux/jhash.h>
+#include <linux/filter.h>
+#include <linux/stacktrace.h>
+#include <linux/perf_event.h>
+#include <linux/elf.h>
+#include <linux/pagemap.h>
+#include <linux/irq_work.h>
+#include "percpu_freelist.h"
+
+#define STACK_CREATE_FLAG_MASK					\
+	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY |	\
+	 BPF_F_STACK_BUILD_ID)
+
+struct stack_map_bucket {
+	struct pcpu_freelist_node fnode;
+	u32 hash;
+	u32 nr;
+	u64 data[];
+};
+
+struct bpf_stack_map {
+	struct bpf_map map;
+	void *elems;
+	struct pcpu_freelist freelist;
+	u32 n_buckets;
+	struct stack_map_bucket *buckets[];
+};
+
+/* irq_work to run up_read() for build_id lookup in nmi context */
+struct stack_map_irq_work {
+	struct irq_work irq_work;
+	struct rw_semaphore *sem;
+};
+
+static void do_up_read(struct irq_work *entry)
+{
+	struct stack_map_irq_work *work;
+
+	work = container_of(entry, struct stack_map_irq_work, irq_work);
+	up_read_non_owner(work->sem);
+	work->sem = NULL;
+}
+
+static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work);
+
+static inline bool stack_map_use_build_id(struct bpf_map *map)
+{
+	return (map->map_flags & BPF_F_STACK_BUILD_ID);
+}
+
+static inline int stack_map_data_size(struct bpf_map *map)
+{
+	return stack_map_use_build_id(map) ?
+		sizeof(struct bpf_stack_build_id) : sizeof(u64);
+}
+
+static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
+{
+	u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size;
+	int err;
+
+	smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries,
+					 smap->map.numa_node);
+	if (!smap->elems)
+		return -ENOMEM;
+
+	err = pcpu_freelist_init(&smap->freelist);
+	if (err)
+		goto free_elems;
+
+	pcpu_freelist_populate(&smap->freelist, smap->elems, elem_size,
+			       smap->map.max_entries);
+	return 0;
+
+free_elems:
+	bpf_map_area_free(smap->elems);
+	return err;
+}
+
+/* Called from syscall */
+static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
+{
+	u32 value_size = attr->value_size;
+	struct bpf_stack_map *smap;
+	u64 cost, n_buckets;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	if (attr->map_flags & ~STACK_CREATE_FLAG_MASK)
+		return ERR_PTR(-EINVAL);
+
+	/* check sanity of attributes */
+	if (attr->max_entries == 0 || attr->key_size != 4 ||
+	    value_size < 8 || value_size % 8)
+		return ERR_PTR(-EINVAL);
+
+	BUILD_BUG_ON(sizeof(struct bpf_stack_build_id) % sizeof(u64));
+	if (attr->map_flags & BPF_F_STACK_BUILD_ID) {
+		if (value_size % sizeof(struct bpf_stack_build_id) ||
+		    value_size / sizeof(struct bpf_stack_build_id)
+		    > sysctl_perf_event_max_stack)
+			return ERR_PTR(-EINVAL);
+	} else if (value_size / 8 > sysctl_perf_event_max_stack)
+		return ERR_PTR(-EINVAL);
+
+	/* hash table size must be power of 2 */
+	n_buckets = roundup_pow_of_two(attr->max_entries);
+	if (!n_buckets)
+		return ERR_PTR(-E2BIG);
+
+	cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap);
+	if (cost >= U32_MAX - PAGE_SIZE)
+		return ERR_PTR(-E2BIG);
+
+	smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr));
+	if (!smap)
+		return ERR_PTR(-ENOMEM);
+
+	err = -E2BIG;
+	cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
+	if (cost >= U32_MAX - PAGE_SIZE)
+		goto free_smap;
+
+	bpf_map_init_from_attr(&smap->map, attr);
+	smap->map.value_size = value_size;
+	smap->n_buckets = n_buckets;
+	smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	err = bpf_map_precharge_memlock(smap->map.pages);
+	if (err)
+		goto free_smap;
+
+	err = get_callchain_buffers(sysctl_perf_event_max_stack);
+	if (err)
+		goto free_smap;
+
+	err = prealloc_elems_and_freelist(smap);
+	if (err)
+		goto put_buffers;
+
+	return &smap->map;
+
+put_buffers:
+	put_callchain_buffers();
+free_smap:
+	bpf_map_area_free(smap);
+	return ERR_PTR(err);
+}
+
+#define BPF_BUILD_ID 3
+/*
+ * Parse build id from the note segment. This logic can be shared between
+ * 32-bit and 64-bit system, because Elf32_Nhdr and Elf64_Nhdr are
+ * identical.
+ */
+static inline int stack_map_parse_build_id(void *page_addr,
+					   unsigned char *build_id,
+					   void *note_start,
+					   Elf32_Word note_size)
+{
+	Elf32_Word note_offs = 0, new_offs;
+
+	/* check for overflow */
+	if (note_start < page_addr || note_start + note_size < note_start)
+		return -EINVAL;
+
+	/* only supports note that fits in the first page */
+	if (note_start + note_size > page_addr + PAGE_SIZE)
+		return -EINVAL;
+
+	while (note_offs + sizeof(Elf32_Nhdr) < note_size) {
+		Elf32_Nhdr *nhdr = (Elf32_Nhdr *)(note_start + note_offs);
+
+		if (nhdr->n_type == BPF_BUILD_ID &&
+		    nhdr->n_namesz == sizeof("GNU") &&
+		    nhdr->n_descsz > 0 &&
+		    nhdr->n_descsz <= BPF_BUILD_ID_SIZE) {
+			memcpy(build_id,
+			       note_start + note_offs +
+			       ALIGN(sizeof("GNU"), 4) + sizeof(Elf32_Nhdr),
+			       nhdr->n_descsz);
+			memset(build_id + nhdr->n_descsz, 0,
+			       BPF_BUILD_ID_SIZE - nhdr->n_descsz);
+			return 0;
+		}
+		new_offs = note_offs + sizeof(Elf32_Nhdr) +
+			ALIGN(nhdr->n_namesz, 4) + ALIGN(nhdr->n_descsz, 4);
+		if (new_offs <= note_offs)  /* overflow */
+			break;
+		note_offs = new_offs;
+	}
+	return -EINVAL;
+}
+
+/* Parse build ID from 32-bit ELF */
+static int stack_map_get_build_id_32(void *page_addr,
+				     unsigned char *build_id)
+{
+	Elf32_Ehdr *ehdr = (Elf32_Ehdr *)page_addr;
+	Elf32_Phdr *phdr;
+	int i;
+
+	/* only supports phdr that fits in one page */
+	if (ehdr->e_phnum >
+	    (PAGE_SIZE - sizeof(Elf32_Ehdr)) / sizeof(Elf32_Phdr))
+		return -EINVAL;
+
+	phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr));
+
+	for (i = 0; i < ehdr->e_phnum; ++i)
+		if (phdr[i].p_type == PT_NOTE)
+			return stack_map_parse_build_id(page_addr, build_id,
+					page_addr + phdr[i].p_offset,
+					phdr[i].p_filesz);
+	return -EINVAL;
+}
+
+/* Parse build ID from 64-bit ELF */
+static int stack_map_get_build_id_64(void *page_addr,
+				     unsigned char *build_id)
+{
+	Elf64_Ehdr *ehdr = (Elf64_Ehdr *)page_addr;
+	Elf64_Phdr *phdr;
+	int i;
+
+	/* only supports phdr that fits in one page */
+	if (ehdr->e_phnum >
+	    (PAGE_SIZE - sizeof(Elf64_Ehdr)) / sizeof(Elf64_Phdr))
+		return -EINVAL;
+
+	phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr));
+
+	for (i = 0; i < ehdr->e_phnum; ++i)
+		if (phdr[i].p_type == PT_NOTE)
+			return stack_map_parse_build_id(page_addr, build_id,
+					page_addr + phdr[i].p_offset,
+					phdr[i].p_filesz);
+	return -EINVAL;
+}
+
+/* Parse build ID of ELF file mapped to vma */
+static int stack_map_get_build_id(struct vm_area_struct *vma,
+				  unsigned char *build_id)
+{
+	Elf32_Ehdr *ehdr;
+	struct page *page;
+	void *page_addr;
+	int ret;
+
+	/* only works for page backed storage  */
+	if (!vma->vm_file)
+		return -EINVAL;
+
+	page = find_get_page(vma->vm_file->f_mapping, 0);
+	if (!page)
+		return -EFAULT;	/* page not mapped */
+
+	ret = -EINVAL;
+	page_addr = kmap_atomic(page);
+	ehdr = (Elf32_Ehdr *)page_addr;
+
+	/* compare magic x7f "ELF" */
+	if (memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0)
+		goto out;
+
+	/* only support executable file and shared object file */
+	if (ehdr->e_type != ET_EXEC && ehdr->e_type != ET_DYN)
+		goto out;
+
+	if (ehdr->e_ident[EI_CLASS] == ELFCLASS32)
+		ret = stack_map_get_build_id_32(page_addr, build_id);
+	else if (ehdr->e_ident[EI_CLASS] == ELFCLASS64)
+		ret = stack_map_get_build_id_64(page_addr, build_id);
+out:
+	kunmap_atomic(page_addr);
+	put_page(page);
+	return ret;
+}
+
+static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
+					  u64 *ips, u32 trace_nr, bool user)
+{
+	int i;
+	struct vm_area_struct *vma;
+	bool irq_work_busy = false;
+	struct stack_map_irq_work *work = NULL;
+
+	if (irqs_disabled()) {
+		work = this_cpu_ptr(&up_read_work);
+		if (work->irq_work.flags & IRQ_WORK_BUSY)
+			/* cannot queue more up_read, fallback */
+			irq_work_busy = true;
+	}
+
+	/*
+	 * We cannot do up_read() when the irq is disabled, because of
+	 * risk to deadlock with rq_lock. To do build_id lookup when the
+	 * irqs are disabled, we need to run up_read() in irq_work. We use
+	 * a percpu variable to do the irq_work. If the irq_work is
+	 * already used by another lookup, we fall back to report ips.
+	 *
+	 * Same fallback is used for kernel stack (!user) on a stackmap
+	 * with build_id.
+	 */
+	if (!user || !current || !current->mm || irq_work_busy ||
+	    down_read_trylock(&current->mm->mmap_sem) == 0) {
+		/* cannot access current->mm, fall back to ips */
+		for (i = 0; i < trace_nr; i++) {
+			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
+			id_offs[i].ip = ips[i];
+			memset(id_offs[i].build_id, 0, BPF_BUILD_ID_SIZE);
+		}
+		return;
+	}
+
+	for (i = 0; i < trace_nr; i++) {
+		vma = find_vma(current->mm, ips[i]);
+		if (!vma || stack_map_get_build_id(vma, id_offs[i].build_id)) {
+			/* per entry fall back to ips */
+			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
+			id_offs[i].ip = ips[i];
+			memset(id_offs[i].build_id, 0, BPF_BUILD_ID_SIZE);
+			continue;
+		}
+		id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ips[i]
+			- vma->vm_start;
+		id_offs[i].status = BPF_STACK_BUILD_ID_VALID;
+	}
+
+	if (!work) {
+		up_read(&current->mm->mmap_sem);
+	} else {
+		work->sem = &current->mm->mmap_sem;
+		irq_work_queue(&work->irq_work);
+		/*
+		 * The irq_work will release the mmap_sem with
+		 * up_read_non_owner(). The rwsem_release() is called
+		 * here to release the lock from lockdep's perspective.
+		 */
+		rwsem_release(&current->mm->mmap_sem.dep_map, 1, _RET_IP_);
+	}
+}
+
+BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
+	   u64, flags)
+{
+	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
+	struct perf_callchain_entry *trace;
+	struct stack_map_bucket *bucket, *new_bucket, *old_bucket;
+	u32 max_depth = map->value_size / stack_map_data_size(map);
+	/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
+	u32 init_nr = sysctl_perf_event_max_stack - max_depth;
+	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
+	u32 hash, id, trace_nr, trace_len;
+	bool user = flags & BPF_F_USER_STACK;
+	bool kernel = !user;
+	u64 *ips;
+	bool hash_matches;
+
+	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
+			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
+		return -EINVAL;
+
+	trace = get_perf_callchain(regs, init_nr, kernel, user,
+				   sysctl_perf_event_max_stack, false, false);
+
+	if (unlikely(!trace))
+		/* couldn't fetch the stack trace */
+		return -EFAULT;
+
+	/* get_perf_callchain() guarantees that trace->nr >= init_nr
+	 * and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth
+	 */
+	trace_nr = trace->nr - init_nr;
+
+	if (trace_nr <= skip)
+		/* skipping more than usable stack trace */
+		return -EFAULT;
+
+	trace_nr -= skip;
+	trace_len = trace_nr * sizeof(u64);
+	ips = trace->ip + skip + init_nr;
+	hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0);
+	id = hash & (smap->n_buckets - 1);
+	bucket = READ_ONCE(smap->buckets[id]);
+
+	hash_matches = bucket && bucket->hash == hash;
+	/* fast cmp */
+	if (hash_matches && flags & BPF_F_FAST_STACK_CMP)
+		return id;
+
+	if (stack_map_use_build_id(map)) {
+		/* for build_id+offset, pop a bucket before slow cmp */
+		new_bucket = (struct stack_map_bucket *)
+			pcpu_freelist_pop(&smap->freelist);
+		if (unlikely(!new_bucket))
+			return -ENOMEM;
+		new_bucket->nr = trace_nr;
+		stack_map_get_build_id_offset(
+			(struct bpf_stack_build_id *)new_bucket->data,
+			ips, trace_nr, user);
+		trace_len = trace_nr * sizeof(struct bpf_stack_build_id);
+		if (hash_matches && bucket->nr == trace_nr &&
+		    memcmp(bucket->data, new_bucket->data, trace_len) == 0) {
+			pcpu_freelist_push(&smap->freelist, &new_bucket->fnode);
+			return id;
+		}
+		if (bucket && !(flags & BPF_F_REUSE_STACKID)) {
+			pcpu_freelist_push(&smap->freelist, &new_bucket->fnode);
+			return -EEXIST;
+		}
+	} else {
+		if (hash_matches && bucket->nr == trace_nr &&
+		    memcmp(bucket->data, ips, trace_len) == 0)
+			return id;
+		if (bucket && !(flags & BPF_F_REUSE_STACKID))
+			return -EEXIST;
+
+		new_bucket = (struct stack_map_bucket *)
+			pcpu_freelist_pop(&smap->freelist);
+		if (unlikely(!new_bucket))
+			return -ENOMEM;
+		memcpy(new_bucket->data, ips, trace_len);
+	}
+
+	new_bucket->hash = hash;
+	new_bucket->nr = trace_nr;
+
+	old_bucket = xchg(&smap->buckets[id], new_bucket);
+	if (old_bucket)
+		pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
+	return id;
+}
+
+const struct bpf_func_proto bpf_get_stackid_proto = {
+	.func		= bpf_get_stackid,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
+	   u64, flags)
+{
+	u32 init_nr, trace_nr, copy_len, elem_size, num_elem;
+	bool user_build_id = flags & BPF_F_USER_BUILD_ID;
+	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
+	bool user = flags & BPF_F_USER_STACK;
+	struct perf_callchain_entry *trace;
+	bool kernel = !user;
+	int err = -EINVAL;
+	u64 *ips;
+
+	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
+			       BPF_F_USER_BUILD_ID)))
+		goto clear;
+	if (kernel && user_build_id)
+		goto clear;
+
+	elem_size = (user && user_build_id) ? sizeof(struct bpf_stack_build_id)
+					    : sizeof(u64);
+	if (unlikely(size % elem_size))
+		goto clear;
+
+	num_elem = size / elem_size;
+	if (sysctl_perf_event_max_stack < num_elem)
+		init_nr = 0;
+	else
+		init_nr = sysctl_perf_event_max_stack - num_elem;
+	trace = get_perf_callchain(regs, init_nr, kernel, user,
+				   sysctl_perf_event_max_stack, false, false);
+	if (unlikely(!trace))
+		goto err_fault;
+
+	trace_nr = trace->nr - init_nr;
+	if (trace_nr < skip)
+		goto err_fault;
+
+	trace_nr -= skip;
+	trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem;
+	copy_len = trace_nr * elem_size;
+	ips = trace->ip + skip + init_nr;
+	if (user && user_build_id)
+		stack_map_get_build_id_offset(buf, ips, trace_nr, user);
+	else
+		memcpy(buf, ips, copy_len);
+
+	if (size > copy_len)
+		memset(buf + copy_len, 0, size - copy_len);
+	return copy_len;
+
+err_fault:
+	err = -EFAULT;
+clear:
+	memset(buf, 0, size);
+	return err;
+}
+
+const struct bpf_func_proto bpf_get_stack_proto = {
+	.func		= bpf_get_stack,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+/* Called from eBPF program */
+static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	return NULL;
+}
+
+/* Called from syscall */
+int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
+{
+	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
+	struct stack_map_bucket *bucket, *old_bucket;
+	u32 id = *(u32 *)key, trace_len;
+
+	if (unlikely(id >= smap->n_buckets))
+		return -ENOENT;
+
+	bucket = xchg(&smap->buckets[id], NULL);
+	if (!bucket)
+		return -ENOENT;
+
+	trace_len = bucket->nr * stack_map_data_size(map);
+	memcpy(value, bucket->data, trace_len);
+	memset(value + trace_len, 0, map->value_size - trace_len);
+
+	old_bucket = xchg(&smap->buckets[id], bucket);
+	if (old_bucket)
+		pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
+	return 0;
+}
+
+static int stack_map_get_next_key(struct bpf_map *map, void *key,
+				  void *next_key)
+{
+	struct bpf_stack_map *smap = container_of(map,
+						  struct bpf_stack_map, map);
+	u32 id;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	if (!key) {
+		id = 0;
+	} else {
+		id = *(u32 *)key;
+		if (id >= smap->n_buckets || !smap->buckets[id])
+			id = 0;
+		else
+			id++;
+	}
+
+	while (id < smap->n_buckets && !smap->buckets[id])
+		id++;
+
+	if (id >= smap->n_buckets)
+		return -ENOENT;
+
+	*(u32 *)next_key = id;
+	return 0;
+}
+
+static int stack_map_update_elem(struct bpf_map *map, void *key, void *value,
+				 u64 map_flags)
+{
+	return -EINVAL;
+}
+
+/* Called from syscall or from eBPF program */
+static int stack_map_delete_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
+	struct stack_map_bucket *old_bucket;
+	u32 id = *(u32 *)key;
+
+	if (unlikely(id >= smap->n_buckets))
+		return -E2BIG;
+
+	old_bucket = xchg(&smap->buckets[id], NULL);
+	if (old_bucket) {
+		pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
+		return 0;
+	} else {
+		return -ENOENT;
+	}
+}
+
+/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
+static void stack_map_free(struct bpf_map *map)
+{
+	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
+
+	/* wait for bpf programs to complete before freeing stack map */
+	synchronize_rcu();
+
+	bpf_map_area_free(smap->elems);
+	pcpu_freelist_destroy(&smap->freelist);
+	bpf_map_area_free(smap);
+	put_callchain_buffers();
+}
+
+const struct bpf_map_ops stack_map_ops = {
+	.map_alloc = stack_map_alloc,
+	.map_free = stack_map_free,
+	.map_get_next_key = stack_map_get_next_key,
+	.map_lookup_elem = stack_map_lookup_elem,
+	.map_update_elem = stack_map_update_elem,
+	.map_delete_elem = stack_map_delete_elem,
+	.map_check_btf = map_check_no_btf,
+};
+
+static int __init stack_map_init(void)
+{
+	int cpu;
+	struct stack_map_irq_work *work;
+
+	for_each_possible_cpu(cpu) {
+		work = per_cpu_ptr(&up_read_work, cpu);
+		init_irq_work(&work->irq_work, do_up_read);
+	}
+	return 0;
+}
+subsys_initcall(stack_map_init);

kernel/bpf/tnum.c

@@ -0,0 +1,195 @@
+/* tnum: tracked (or tristate) numbers
+ *
+ * A tnum tracks knowledge about the bits of a value.  Each bit can be either
+ * known (0 or 1), or unknown (x).  Arithmetic operations on tnums will
+ * propagate the unknown bits such that the tnum result represents all the
+ * possible results for possible values of the operands.
+ */
+#include <linux/kernel.h>
+#include <linux/tnum.h>
+
+#define TNUM(_v, _m)	(struct tnum){.value = _v, .mask = _m}
+/* A completely unknown value */
+const struct tnum tnum_unknown = { .value = 0, .mask = -1 };
+
+struct tnum tnum_const(u64 value)
+{
+	return TNUM(value, 0);
+}
+
+struct tnum tnum_range(u64 min, u64 max)
+{
+	u64 chi = min ^ max, delta;
+	u8 bits = fls64(chi);
+
+	/* special case, needed because 1ULL << 64 is undefined */
+	if (bits > 63)
+		return tnum_unknown;
+	/* e.g. if chi = 4, bits = 3, delta = (1<<3) - 1 = 7.
+	 * if chi = 0, bits = 0, delta = (1<<0) - 1 = 0, so we return
+	 *  constant min (since min == max).
+	 */
+	delta = (1ULL << bits) - 1;
+	return TNUM(min & ~delta, delta);
+}
+
+struct tnum tnum_lshift(struct tnum a, u8 shift)
+{
+	return TNUM(a.value << shift, a.mask << shift);
+}
+
+struct tnum tnum_rshift(struct tnum a, u8 shift)
+{
+	return TNUM(a.value >> shift, a.mask >> shift);
+}
+
+struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness)
+{
+	/* if a.value is negative, arithmetic shifting by minimum shift
+	 * will have larger negative offset compared to more shifting.
+	 * If a.value is nonnegative, arithmetic shifting by minimum shift
+	 * will have larger positive offset compare to more shifting.
+	 */
+	if (insn_bitness == 32)
+		return TNUM((u32)(((s32)a.value) >> min_shift),
+			    (u32)(((s32)a.mask)  >> min_shift));
+	else
+		return TNUM((s64)a.value >> min_shift,
+			    (s64)a.mask  >> min_shift);
+}
+
+struct tnum tnum_add(struct tnum a, struct tnum b)
+{
+	u64 sm, sv, sigma, chi, mu;
+
+	sm = a.mask + b.mask;
+	sv = a.value + b.value;
+	sigma = sm + sv;
+	chi = sigma ^ sv;
+	mu = chi | a.mask | b.mask;
+	return TNUM(sv & ~mu, mu);
+}
+
+struct tnum tnum_sub(struct tnum a, struct tnum b)
+{
+	u64 dv, alpha, beta, chi, mu;
+
+	dv = a.value - b.value;
+	alpha = dv + a.mask;
+	beta = dv - b.mask;
+	chi = alpha ^ beta;
+	mu = chi | a.mask | b.mask;
+	return TNUM(dv & ~mu, mu);
+}
+
+struct tnum tnum_and(struct tnum a, struct tnum b)
+{
+	u64 alpha, beta, v;
+
+	alpha = a.value | a.mask;
+	beta = b.value | b.mask;
+	v = a.value & b.value;
+	return TNUM(v, alpha & beta & ~v);
+}
+
+struct tnum tnum_or(struct tnum a, struct tnum b)
+{
+	u64 v, mu;
+
+	v = a.value | b.value;
+	mu = a.mask | b.mask;
+	return TNUM(v, mu & ~v);
+}
+
+struct tnum tnum_xor(struct tnum a, struct tnum b)
+{
+	u64 v, mu;
+
+	v = a.value ^ b.value;
+	mu = a.mask | b.mask;
+	return TNUM(v & ~mu, mu);
+}
+
+/* half-multiply add: acc += (unknown * mask * value).
+ * An intermediate step in the multiply algorithm.
+ */
+static struct tnum hma(struct tnum acc, u64 value, u64 mask)
+{
+	while (mask) {
+		if (mask & 1)
+			acc = tnum_add(acc, TNUM(0, value));
+		mask >>= 1;
+		value <<= 1;
+	}
+	return acc;
+}
+
+struct tnum tnum_mul(struct tnum a, struct tnum b)
+{
+	struct tnum acc;
+	u64 pi;
+
+	pi = a.value * b.value;
+	acc = hma(TNUM(pi, 0), a.mask, b.mask | b.value);
+	return hma(acc, b.mask, a.value);
+}
+
+/* Note that if a and b disagree - i.e. one has a 'known 1' where the other has
+ * a 'known 0' - this will return a 'known 1' for that bit.
+ */
+struct tnum tnum_intersect(struct tnum a, struct tnum b)
+{
+	u64 v, mu;
+
+	v = a.value | b.value;
+	mu = a.mask & b.mask;
+	return TNUM(v & ~mu, mu);
+}
+
+struct tnum tnum_cast(struct tnum a, u8 size)
+{
+	a.value &= (1ULL << (size * 8)) - 1;
+	a.mask &= (1ULL << (size * 8)) - 1;
+	return a;
+}
+
+bool tnum_is_aligned(struct tnum a, u64 size)
+{
+	if (!size)
+		return true;
+	return !((a.value | a.mask) & (size - 1));
+}
+
+bool tnum_in(struct tnum a, struct tnum b)
+{
+	if (b.mask & ~a.mask)
+		return false;
+	b.value &= ~a.mask;
+	return a.value == b.value;
+}
+
+int tnum_strn(char *str, size_t size, struct tnum a)
+{
+	return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask);
+}
+EXPORT_SYMBOL_GPL(tnum_strn);
+
+int tnum_sbin(char *str, size_t size, struct tnum a)
+{
+	size_t n;
+
+	for (n = 64; n; n--) {
+		if (n < size) {
+			if (a.mask & 1)
+				str[n - 1] = 'x';
+			else if (a.value & 1)
+				str[n - 1] = '1';
+			else
+				str[n - 1] = '0';
+		}
+		a.mask >>= 1;
+		a.value >>= 1;
+	}
+	str[min(size - 1, (size_t)64)] = 0;
+	return 64;
+}

kernel/bpf/xskmap.c

@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0
+/* XSKMAP used for AF_XDP sockets
+ * Copyright(c) 2018 Intel Corporation.
+ */
+
+#include <linux/bpf.h>
+#include <linux/capability.h>
+#include <net/xdp_sock.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+
+struct xsk_map {
+	struct bpf_map map;
+	struct xdp_sock **xsk_map;
+	struct list_head __percpu *flush_list;
+};
+
+static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
+{
+	int cpu, err = -EINVAL;
+	struct xsk_map *m;
+	u64 cost;
+
+	if (!capable(CAP_NET_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	if (attr->max_entries == 0 || attr->key_size != 4 ||
+	    attr->value_size != 4 ||
+	    attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY))
+		return ERR_PTR(-EINVAL);
+
+	m = kzalloc(sizeof(*m), GFP_USER);
+	if (!m)
+		return ERR_PTR(-ENOMEM);
+
+	bpf_map_init_from_attr(&m->map, attr);
+
+	cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *);
+	cost += sizeof(struct list_head) * num_possible_cpus();
+	if (cost >= U32_MAX - PAGE_SIZE)
+		goto free_m;
+
+	m->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	/* Notice returns -EPERM on if map size is larger than memlock limit */
+	err = bpf_map_precharge_memlock(m->map.pages);
+	if (err)
+		goto free_m;
+
+	err = -ENOMEM;
+
+	m->flush_list = alloc_percpu(struct list_head);
+	if (!m->flush_list)
+		goto free_m;
+
+	for_each_possible_cpu(cpu)
+		INIT_LIST_HEAD(per_cpu_ptr(m->flush_list, cpu));
+
+	m->xsk_map = bpf_map_area_alloc(m->map.max_entries *
+					sizeof(struct xdp_sock *),
+					m->map.numa_node);
+	if (!m->xsk_map)
+		goto free_percpu;
+	return &m->map;
+
+free_percpu:
+	free_percpu(m->flush_list);
+free_m:
+	kfree(m);
+	return ERR_PTR(err);
+}
+
+static void xsk_map_free(struct bpf_map *map)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	int i;
+
+	bpf_clear_redirect_map(map);
+	synchronize_net();
+
+	for (i = 0; i < map->max_entries; i++) {
+		struct xdp_sock *xs;
+
+		xs = m->xsk_map[i];
+		if (!xs)
+			continue;
+
+		sock_put((struct sock *)xs);
+	}
+
+	free_percpu(m->flush_list);
+	bpf_map_area_free(m->xsk_map);
+	kfree(m);
+}
+
+static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	u32 index = key ? *(u32 *)key : U32_MAX;
+	u32 *next = next_key;
+
+	if (index >= m->map.max_entries) {
+		*next = 0;
+		return 0;
+	}
+
+	if (index == m->map.max_entries - 1)
+		return -ENOENT;
+	*next = index + 1;
+	return 0;
+}
+
+struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct xdp_sock *xs;
+
+	if (key >= map->max_entries)
+		return NULL;
+
+	xs = READ_ONCE(m->xsk_map[key]);
+	return xs;
+}
+
+int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
+		       struct xdp_sock *xs)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct list_head *flush_list = this_cpu_ptr(m->flush_list);
+	int err;
+
+	err = xsk_rcv(xs, xdp);
+	if (err)
+		return err;
+
+	if (!xs->flush_node.prev)
+		list_add(&xs->flush_node, flush_list);
+
+	return 0;
+}
+
+void __xsk_map_flush(struct bpf_map *map)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct list_head *flush_list = this_cpu_ptr(m->flush_list);
+	struct xdp_sock *xs, *tmp;
+
+	list_for_each_entry_safe(xs, tmp, flush_list, flush_node) {
+		xsk_flush(xs);
+		__list_del(xs->flush_node.prev, xs->flush_node.next);
+		xs->flush_node.prev = NULL;
+	}
+}
+
+static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	return NULL;
+}
+
+static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
+			       u64 map_flags)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	u32 i = *(u32 *)key, fd = *(u32 *)value;
+	struct xdp_sock *xs, *old_xs;
+	struct socket *sock;
+	int err;
+
+	if (unlikely(map_flags > BPF_EXIST))
+		return -EINVAL;
+	if (unlikely(i >= m->map.max_entries))
+		return -E2BIG;
+	if (unlikely(map_flags == BPF_NOEXIST))
+		return -EEXIST;
+
+	sock = sockfd_lookup(fd, &err);
+	if (!sock)
+		return err;
+
+	if (sock->sk->sk_family != PF_XDP) {
+		sockfd_put(sock);
+		return -EOPNOTSUPP;
+	}
+
+	xs = (struct xdp_sock *)sock->sk;
+
+	if (!xsk_is_setup_for_bpf_map(xs)) {
+		sockfd_put(sock);
+		return -EOPNOTSUPP;
+	}
+
+	sock_hold(sock->sk);
+
+	old_xs = xchg(&m->xsk_map[i], xs);
+	if (old_xs)
+		sock_put((struct sock *)old_xs);
+
+	sockfd_put(sock);
+	return 0;
+}
+
+static int xsk_map_delete_elem(struct bpf_map *map, void *key)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct xdp_sock *old_xs;
+	int k = *(u32 *)key;
+
+	if (k >= map->max_entries)
+		return -EINVAL;
+
+	old_xs = xchg(&m->xsk_map[k], NULL);
+	if (old_xs)
+		sock_put((struct sock *)old_xs);
+
+	return 0;
+}
+
+const struct bpf_map_ops xsk_map_ops = {
+	.map_alloc = xsk_map_alloc,
+	.map_free = xsk_map_free,
+	.map_get_next_key = xsk_map_get_next_key,
+	.map_lookup_elem = xsk_map_lookup_elem,
+	.map_update_elem = xsk_map_update_elem,
+	.map_delete_elem = xsk_map_delete_elem,
+	.map_check_btf = map_check_no_btf,
+};