summaryrefslogtreecommitdiffstats
path: root/kernel/bpf
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-06 01:02:30 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-06 01:02:30 +0000
commit76cb841cb886eef6b3bee341a2266c76578724ad (patch)
treef5892e5ba6cc11949952a6ce4ecbe6d516d6ce58 /kernel/bpf
parentInitial commit. (diff)
downloadlinux-76cb841cb886eef6b3bee341a2266c76578724ad.tar.xz
linux-76cb841cb886eef6b3bee341a2266c76578724ad.zip
Adding upstream version 4.19.249.upstream/4.19.249upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to '')
-rw-r--r--kernel/bpf/Makefile29
-rw-r--r--kernel/bpf/arraymap.c750
-rw-r--r--kernel/bpf/bpf_lru_list.c698
-rw-r--r--kernel/bpf/bpf_lru_list.h85
-rw-r--r--kernel/bpf/btf.c2441
-rw-r--r--kernel/bpf/cgroup.c724
-rw-r--r--kernel/bpf/core.c1945
-rw-r--r--kernel/bpf/cpumap.c682
-rw-r--r--kernel/bpf/devmap.c552
-rw-r--r--kernel/bpf/disasm.c263
-rw-r--r--kernel/bpf/disasm.h48
-rw-r--r--kernel/bpf/hashtab.c1451
-rw-r--r--kernel/bpf/helpers.c216
-rw-r--r--kernel/bpf/inode.c689
-rw-r--r--kernel/bpf/local_storage.c383
-rw-r--r--kernel/bpf/lpm_trie.c714
-rw-r--r--kernel/bpf/map_in_map.c116
-rw-r--r--kernel/bpf/map_in_map.h24
-rw-r--r--kernel/bpf/offload.c671
-rw-r--r--kernel/bpf/percpu_freelist.c121
-rw-r--r--kernel/bpf/percpu_freelist.h35
-rw-r--r--kernel/bpf/reuseport_array.c363
-rw-r--r--kernel/bpf/sockmap.c2631
-rw-r--r--kernel/bpf/stackmap.c640
-rw-r--r--kernel/bpf/syscall.c2479
-rw-r--r--kernel/bpf/tnum.c195
-rw-r--r--kernel/bpf/verifier.c6575
-rw-r--r--kernel/bpf/xskmap.c226
28 files changed, 25746 insertions, 0 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
new file mode 100644
index 000000000..ffc39a7e0
--- /dev/null
+++ b/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
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
new file mode 100644
index 000000000..0c17aab3c
--- /dev/null
+++ b/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,
+};
diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c
new file mode 100644
index 000000000..9b5eeff72
--- /dev/null
+++ b/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);
+}
diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h
new file mode 100644
index 000000000..7d4f89b7c
--- /dev/null
+++ b/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
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
new file mode 100644
index 000000000..471cc5c11
--- /dev/null
+++ b/kernel/bpf/btf.c
@@ -0,0 +1,2441 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Facebook */
+
+#include <uapi/linux/btf.h>
+#include <uapi/linux/types.h>
+#include <linux/seq_file.h>
+#include <linux/compiler.h>
+#include <linux/ctype.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/idr.h>
+#include <linux/sort.h>
+#include <linux/bpf_verifier.h>
+#include <linux/btf.h>
+
+/* BTF (BPF Type Format) is the meta data format which describes
+ * the data types of BPF program/map. Hence, it basically focus
+ * on the C programming language which the modern BPF is primary
+ * using.
+ *
+ * ELF Section:
+ * ~~~~~~~~~~~
+ * The BTF data is stored under the ".BTF" ELF section
+ *
+ * struct btf_type:
+ * ~~~~~~~~~~~~~~~
+ * Each 'struct btf_type' object describes a C data type.
+ * Depending on the type it is describing, a 'struct btf_type'
+ * object may be followed by more data. F.e.
+ * To describe an array, 'struct btf_type' is followed by
+ * 'struct btf_array'.
+ *
+ * 'struct btf_type' and any extra data following it are
+ * 4 bytes aligned.
+ *
+ * Type section:
+ * ~~~~~~~~~~~~~
+ * The BTF type section contains a list of 'struct btf_type' objects.
+ * Each one describes a C type. Recall from the above section
+ * that a 'struct btf_type' object could be immediately followed by extra
+ * data in order to desribe some particular C types.
+ *
+ * type_id:
+ * ~~~~~~~
+ * Each btf_type object is identified by a type_id. The type_id
+ * is implicitly implied by the location of the btf_type object in
+ * the BTF type section. The first one has type_id 1. The second
+ * one has type_id 2...etc. Hence, an earlier btf_type has
+ * a smaller type_id.
+ *
+ * A btf_type object may refer to another btf_type object by using
+ * type_id (i.e. the "type" in the "struct btf_type").
+ *
+ * NOTE that we cannot assume any reference-order.
+ * A btf_type object can refer to an earlier btf_type object
+ * but it can also refer to a later btf_type object.
+ *
+ * For example, to describe "const void *". A btf_type
+ * object describing "const" may refer to another btf_type
+ * object describing "void *". This type-reference is done
+ * by specifying type_id:
+ *
+ * [1] CONST (anon) type_id=2
+ * [2] PTR (anon) type_id=0
+ *
+ * The above is the btf_verifier debug log:
+ * - Each line started with "[?]" is a btf_type object
+ * - [?] is the type_id of the btf_type object.
+ * - CONST/PTR is the BTF_KIND_XXX
+ * - "(anon)" is the name of the type. It just
+ * happens that CONST and PTR has no name.
+ * - type_id=XXX is the 'u32 type' in btf_type
+ *
+ * NOTE: "void" has type_id 0
+ *
+ * String section:
+ * ~~~~~~~~~~~~~~
+ * The BTF string section contains the names used by the type section.
+ * Each string is referred by an "offset" from the beginning of the
+ * string section.
+ *
+ * Each string is '\0' terminated.
+ *
+ * The first character in the string section must be '\0'
+ * which is used to mean 'anonymous'. Some btf_type may not
+ * have a name.
+ */
+
+/* BTF verification:
+ *
+ * To verify BTF data, two passes are needed.
+ *
+ * Pass #1
+ * ~~~~~~~
+ * The first pass is to collect all btf_type objects to
+ * an array: "btf->types".
+ *
+ * Depending on the C type that a btf_type is describing,
+ * a btf_type may be followed by extra data. We don't know
+ * how many btf_type is there, and more importantly we don't
+ * know where each btf_type is located in the type section.
+ *
+ * Without knowing the location of each type_id, most verifications
+ * cannot be done. e.g. an earlier btf_type may refer to a later
+ * btf_type (recall the "const void *" above), so we cannot
+ * check this type-reference in the first pass.
+ *
+ * In the first pass, it still does some verifications (e.g.
+ * checking the name is a valid offset to the string section).
+ *
+ * Pass #2
+ * ~~~~~~~
+ * The main focus is to resolve a btf_type that is referring
+ * to another type.
+ *
+ * We have to ensure the referring type:
+ * 1) does exist in the BTF (i.e. in btf->types[])
+ * 2) does not cause a loop:
+ * struct A {
+ * struct B b;
+ * };
+ *
+ * struct B {
+ * struct A a;
+ * };
+ *
+ * btf_type_needs_resolve() decides if a btf_type needs
+ * to be resolved.
+ *
+ * The needs_resolve type implements the "resolve()" ops which
+ * essentially does a DFS and detects backedge.
+ *
+ * During resolve (or DFS), different C types have different
+ * "RESOLVED" conditions.
+ *
+ * When resolving a BTF_KIND_STRUCT, we need to resolve all its
+ * members because a member is always referring to another
+ * type. A struct's member can be treated as "RESOLVED" if
+ * it is referring to a BTF_KIND_PTR. Otherwise, the
+ * following valid C struct would be rejected:
+ *
+ * struct A {
+ * int m;
+ * struct A *a;
+ * };
+ *
+ * When resolving a BTF_KIND_PTR, it needs to keep resolving if
+ * it is referring to another BTF_KIND_PTR. Otherwise, we cannot
+ * detect a pointer loop, e.g.:
+ * BTF_KIND_CONST -> BTF_KIND_PTR -> BTF_KIND_CONST -> BTF_KIND_PTR +
+ * ^ |
+ * +-----------------------------------------+
+ *
+ */
+
+#define BITS_PER_U64 (sizeof(u64) * BITS_PER_BYTE)
+#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1)
+#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK)
+#define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3)
+#define BITS_ROUNDUP_BYTES(bits) \
+ (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits))
+
+#define BTF_INFO_MASK 0x0f00ffff
+#define BTF_INT_MASK 0x0fffffff
+#define BTF_TYPE_ID_VALID(type_id) ((type_id) <= BTF_MAX_TYPE)
+#define BTF_STR_OFFSET_VALID(name_off) ((name_off) <= BTF_MAX_NAME_OFFSET)
+
+/* 16MB for 64k structs and each has 16 members and
+ * a few MB spaces for the string section.
+ * The hard limit is S32_MAX.
+ */
+#define BTF_MAX_SIZE (16 * 1024 * 1024)
+
+#define for_each_member(i, struct_type, member) \
+ for (i = 0, member = btf_type_member(struct_type); \
+ i < btf_type_vlen(struct_type); \
+ i++, member++)
+
+#define for_each_member_from(i, from, struct_type, member) \
+ for (i = from, member = btf_type_member(struct_type) + from; \
+ i < btf_type_vlen(struct_type); \
+ i++, member++)
+
+static DEFINE_IDR(btf_idr);
+static DEFINE_SPINLOCK(btf_idr_lock);
+
+struct btf {
+ void *data;
+ struct btf_type **types;
+ u32 *resolved_ids;
+ u32 *resolved_sizes;
+ const char *strings;
+ void *nohdr_data;
+ struct btf_header hdr;
+ u32 nr_types;
+ u32 types_size;
+ u32 data_size;
+ refcount_t refcnt;
+ u32 id;
+ struct rcu_head rcu;
+};
+
+enum verifier_phase {
+ CHECK_META,
+ CHECK_TYPE,
+};
+
+struct resolve_vertex {
+ const struct btf_type *t;
+ u32 type_id;
+ u16 next_member;
+};
+
+enum visit_state {
+ NOT_VISITED,
+ VISITED,
+ RESOLVED,
+};
+
+enum resolve_mode {
+ RESOLVE_TBD, /* To Be Determined */
+ RESOLVE_PTR, /* Resolving for Pointer */
+ RESOLVE_STRUCT_OR_ARRAY, /* Resolving for struct/union
+ * or array
+ */
+};
+
+#define MAX_RESOLVE_DEPTH 32
+
+struct btf_sec_info {
+ u32 off;
+ u32 len;
+};
+
+struct btf_verifier_env {
+ struct btf *btf;
+ u8 *visit_states;
+ struct resolve_vertex stack[MAX_RESOLVE_DEPTH];
+ struct bpf_verifier_log log;
+ u32 log_type_id;
+ u32 top_stack;
+ enum verifier_phase phase;
+ enum resolve_mode resolve_mode;
+};
+
+static const char * const btf_kind_str[NR_BTF_KINDS] = {
+ [BTF_KIND_UNKN] = "UNKNOWN",
+ [BTF_KIND_INT] = "INT",
+ [BTF_KIND_PTR] = "PTR",
+ [BTF_KIND_ARRAY] = "ARRAY",
+ [BTF_KIND_STRUCT] = "STRUCT",
+ [BTF_KIND_UNION] = "UNION",
+ [BTF_KIND_ENUM] = "ENUM",
+ [BTF_KIND_FWD] = "FWD",
+ [BTF_KIND_TYPEDEF] = "TYPEDEF",
+ [BTF_KIND_VOLATILE] = "VOLATILE",
+ [BTF_KIND_CONST] = "CONST",
+ [BTF_KIND_RESTRICT] = "RESTRICT",
+};
+
+struct btf_kind_operations {
+ s32 (*check_meta)(struct btf_verifier_env *env,
+ const struct btf_type *t,
+ u32 meta_left);
+ int (*resolve)(struct btf_verifier_env *env,
+ const struct resolve_vertex *v);
+ int (*check_member)(struct btf_verifier_env *env,
+ const struct btf_type *struct_type,
+ const struct btf_member *member,
+ const struct btf_type *member_type);
+ void (*log_details)(struct btf_verifier_env *env,
+ const struct btf_type *t);
+ void (*seq_show)(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offsets,
+ struct seq_file *m);
+};
+
+static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS];
+static struct btf_type btf_void;
+
+static bool btf_type_is_modifier(const struct btf_type *t)
+{
+ /* Some of them is not strictly a C modifier
+ * but they are grouped into the same bucket
+ * for BTF concern:
+ * A type (t) that refers to another
+ * type through t->type AND its size cannot
+ * be determined without following the t->type.
+ *
+ * ptr does not fall into this bucket
+ * because its size is always sizeof(void *).
+ */
+ switch (BTF_INFO_KIND(t->info)) {
+ case BTF_KIND_TYPEDEF:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_CONST:
+ case BTF_KIND_RESTRICT:
+ return true;
+ }
+
+ return false;
+}
+
+static bool btf_type_is_void(const struct btf_type *t)
+{
+ /* void => no type and size info.
+ * Hence, FWD is also treated as void.
+ */
+ return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
+}
+
+static bool btf_type_is_void_or_null(const struct btf_type *t)
+{
+ return !t || btf_type_is_void(t);
+}
+
+/* union is only a special case of struct:
+ * all its offsetof(member) == 0
+ */
+static bool btf_type_is_struct(const struct btf_type *t)
+{
+ u8 kind = BTF_INFO_KIND(t->info);
+
+ return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
+}
+
+static bool btf_type_is_array(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY;
+}
+
+static bool btf_type_is_ptr(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info) == BTF_KIND_PTR;
+}
+
+static bool btf_type_is_int(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info) == BTF_KIND_INT;
+}
+
+/* What types need to be resolved?
+ *
+ * btf_type_is_modifier() is an obvious one.
+ *
+ * btf_type_is_struct() because its member refers to
+ * another type (through member->type).
+
+ * btf_type_is_array() because its element (array->type)
+ * refers to another type. Array can be thought of a
+ * special case of struct while array just has the same
+ * member-type repeated by array->nelems of times.
+ */
+static bool btf_type_needs_resolve(const struct btf_type *t)
+{
+ return btf_type_is_modifier(t) ||
+ btf_type_is_ptr(t) ||
+ btf_type_is_struct(t) ||
+ btf_type_is_array(t);
+}
+
+/* t->size can be used */
+static bool btf_type_has_size(const struct btf_type *t)
+{
+ switch (BTF_INFO_KIND(t->info)) {
+ case BTF_KIND_INT:
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION:
+ case BTF_KIND_ENUM:
+ return true;
+ }
+
+ return false;
+}
+
+static const char *btf_int_encoding_str(u8 encoding)
+{
+ if (encoding == 0)
+ return "(none)";
+ else if (encoding == BTF_INT_SIGNED)
+ return "SIGNED";
+ else if (encoding == BTF_INT_CHAR)
+ return "CHAR";
+ else if (encoding == BTF_INT_BOOL)
+ return "BOOL";
+ else
+ return "UNKN";
+}
+
+static u16 btf_type_vlen(const struct btf_type *t)
+{
+ return BTF_INFO_VLEN(t->info);
+}
+
+static u32 btf_type_int(const struct btf_type *t)
+{
+ return *(u32 *)(t + 1);
+}
+
+static const struct btf_array *btf_type_array(const struct btf_type *t)
+{
+ return (const struct btf_array *)(t + 1);
+}
+
+static const struct btf_member *btf_type_member(const struct btf_type *t)
+{
+ return (const struct btf_member *)(t + 1);
+}
+
+static const struct btf_enum *btf_type_enum(const struct btf_type *t)
+{
+ return (const struct btf_enum *)(t + 1);
+}
+
+static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t)
+{
+ return kind_ops[BTF_INFO_KIND(t->info)];
+}
+
+static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
+{
+ return BTF_STR_OFFSET_VALID(offset) &&
+ offset < btf->hdr.str_len;
+}
+
+/* Only C-style identifier is permitted. This can be relaxed if
+ * necessary.
+ */
+static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
+{
+ /* offset must be valid */
+ const char *src = &btf->strings[offset];
+ const char *src_limit;
+
+ if (!isalpha(*src) && *src != '_')
+ return false;
+
+ /* set a limit on identifier length */
+ src_limit = src + KSYM_NAME_LEN;
+ src++;
+ while (*src && src < src_limit) {
+ if (!isalnum(*src) && *src != '_')
+ return false;
+ src++;
+ }
+
+ return !*src;
+}
+
+static const char *btf_name_by_offset(const struct btf *btf, u32 offset)
+{
+ if (!offset)
+ return "(anon)";
+ else if (offset < btf->hdr.str_len)
+ return &btf->strings[offset];
+ else
+ return "(invalid-name-offset)";
+}
+
+static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
+{
+ if (type_id > btf->nr_types)
+ return NULL;
+
+ return btf->types[type_id];
+}
+
+/*
+ * Regular int is not a bit field and it must be either
+ * u8/u16/u32/u64.
+ */
+static bool btf_type_int_is_regular(const struct btf_type *t)
+{
+ u8 nr_bits, nr_bytes;
+ u32 int_data;
+
+ int_data = btf_type_int(t);
+ nr_bits = BTF_INT_BITS(int_data);
+ nr_bytes = BITS_ROUNDUP_BYTES(nr_bits);
+ if (BITS_PER_BYTE_MASKED(nr_bits) ||
+ BTF_INT_OFFSET(int_data) ||
+ (nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) &&
+ nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64))) {
+ return false;
+ }
+
+ return true;
+}
+
+__printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log,
+ const char *fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ bpf_verifier_vlog(log, fmt, args);
+ va_end(args);
+}
+
+__printf(2, 3) static void btf_verifier_log(struct btf_verifier_env *env,
+ const char *fmt, ...)
+{
+ struct bpf_verifier_log *log = &env->log;
+ va_list args;
+
+ if (!bpf_verifier_log_needed(log))
+ return;
+
+ va_start(args, fmt);
+ bpf_verifier_vlog(log, fmt, args);
+ va_end(args);
+}
+
+__printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env,
+ const struct btf_type *t,
+ bool log_details,
+ const char *fmt, ...)
+{
+ struct bpf_verifier_log *log = &env->log;
+ u8 kind = BTF_INFO_KIND(t->info);
+ struct btf *btf = env->btf;
+ va_list args;
+
+ if (!bpf_verifier_log_needed(log))
+ return;
+
+ __btf_verifier_log(log, "[%u] %s %s%s",
+ env->log_type_id,
+ btf_kind_str[kind],
+ btf_name_by_offset(btf, t->name_off),
+ log_details ? " " : "");
+
+ if (log_details)
+ btf_type_ops(t)->log_details(env, t);
+
+ if (fmt && *fmt) {
+ __btf_verifier_log(log, " ");
+ va_start(args, fmt);
+ bpf_verifier_vlog(log, fmt, args);
+ va_end(args);
+ }
+
+ __btf_verifier_log(log, "\n");
+}
+
+#define btf_verifier_log_type(env, t, ...) \
+ __btf_verifier_log_type((env), (t), true, __VA_ARGS__)
+#define btf_verifier_log_basic(env, t, ...) \
+ __btf_verifier_log_type((env), (t), false, __VA_ARGS__)
+
+__printf(4, 5)
+static void btf_verifier_log_member(struct btf_verifier_env *env,
+ const struct btf_type *struct_type,
+ const struct btf_member *member,
+ const char *fmt, ...)
+{
+ struct bpf_verifier_log *log = &env->log;
+ struct btf *btf = env->btf;
+ va_list args;
+
+ if (!bpf_verifier_log_needed(log))
+ return;
+
+ /* The CHECK_META phase already did a btf dump.
+ *
+ * If member is logged again, it must hit an error in
+ * parsing this member. It is useful to print out which
+ * struct this member belongs to.
+ */
+ if (env->phase != CHECK_META)
+ btf_verifier_log_type(env, struct_type, NULL);
+
+ __btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u",
+ btf_name_by_offset(btf, member->name_off),
+ member->type, member->offset);
+
+ if (fmt && *fmt) {
+ __btf_verifier_log(log, " ");
+ va_start(args, fmt);
+ bpf_verifier_vlog(log, fmt, args);
+ va_end(args);
+ }
+
+ __btf_verifier_log(log, "\n");
+}
+
+static void btf_verifier_log_hdr(struct btf_verifier_env *env,
+ u32 btf_data_size)
+{
+ struct bpf_verifier_log *log = &env->log;
+ const struct btf *btf = env->btf;
+ const struct btf_header *hdr;
+
+ if (!bpf_verifier_log_needed(log))
+ return;
+
+ hdr = &btf->hdr;
+ __btf_verifier_log(log, "magic: 0x%x\n", hdr->magic);
+ __btf_verifier_log(log, "version: %u\n", hdr->version);
+ __btf_verifier_log(log, "flags: 0x%x\n", hdr->flags);
+ __btf_verifier_log(log, "hdr_len: %u\n", hdr->hdr_len);
+ __btf_verifier_log(log, "type_off: %u\n", hdr->type_off);
+ __btf_verifier_log(log, "type_len: %u\n", hdr->type_len);
+ __btf_verifier_log(log, "str_off: %u\n", hdr->str_off);
+ __btf_verifier_log(log, "str_len: %u\n", hdr->str_len);
+ __btf_verifier_log(log, "btf_total_size: %u\n", btf_data_size);
+}
+
+static int btf_add_type(struct btf_verifier_env *env, struct btf_type *t)
+{
+ struct btf *btf = env->btf;
+
+ /* < 2 because +1 for btf_void which is always in btf->types[0].
+ * btf_void is not accounted in btf->nr_types because btf_void
+ * does not come from the BTF file.
+ */
+ if (btf->types_size - btf->nr_types < 2) {
+ /* Expand 'types' array */
+
+ struct btf_type **new_types;
+ u32 expand_by, new_size;
+
+ if (btf->types_size == BTF_MAX_TYPE) {
+ btf_verifier_log(env, "Exceeded max num of types");
+ return -E2BIG;
+ }
+
+ expand_by = max_t(u32, btf->types_size >> 2, 16);
+ new_size = min_t(u32, BTF_MAX_TYPE,
+ btf->types_size + expand_by);
+
+ new_types = kvcalloc(new_size, sizeof(*new_types),
+ GFP_KERNEL | __GFP_NOWARN);
+ if (!new_types)
+ return -ENOMEM;
+
+ if (btf->nr_types == 0)
+ new_types[0] = &btf_void;
+ else
+ memcpy(new_types, btf->types,
+ sizeof(*btf->types) * (btf->nr_types + 1));
+
+ kvfree(btf->types);
+ btf->types = new_types;
+ btf->types_size = new_size;
+ }
+
+ btf->types[++(btf->nr_types)] = t;
+
+ return 0;
+}
+
+static int btf_alloc_id(struct btf *btf)
+{
+ int id;
+
+ idr_preload(GFP_KERNEL);
+ spin_lock_bh(&btf_idr_lock);
+ id = idr_alloc_cyclic(&btf_idr, btf, 1, INT_MAX, GFP_ATOMIC);
+ if (id > 0)
+ btf->id = id;
+ spin_unlock_bh(&btf_idr_lock);
+ idr_preload_end();
+
+ if (WARN_ON_ONCE(!id))
+ return -ENOSPC;
+
+ return id > 0 ? 0 : id;
+}
+
+static void btf_free_id(struct btf *btf)
+{
+ unsigned long flags;
+
+ /*
+ * In map-in-map, calling map_delete_elem() on outer
+ * map will call bpf_map_put on the inner map.
+ * It will then eventually call btf_free_id()
+ * on the inner map. Some of the map_delete_elem()
+ * implementation may have irq disabled, so
+ * we need to use the _irqsave() version instead
+ * of the _bh() version.
+ */
+ spin_lock_irqsave(&btf_idr_lock, flags);
+ idr_remove(&btf_idr, btf->id);
+ spin_unlock_irqrestore(&btf_idr_lock, flags);
+}
+
+static void btf_free(struct btf *btf)
+{
+ kvfree(btf->types);
+ kvfree(btf->resolved_sizes);
+ kvfree(btf->resolved_ids);
+ kvfree(btf->data);
+ kfree(btf);
+}
+
+static void btf_free_rcu(struct rcu_head *rcu)
+{
+ struct btf *btf = container_of(rcu, struct btf, rcu);
+
+ btf_free(btf);
+}
+
+void btf_put(struct btf *btf)
+{
+ if (btf && refcount_dec_and_test(&btf->refcnt)) {
+ btf_free_id(btf);
+ call_rcu(&btf->rcu, btf_free_rcu);
+ }
+}
+
+static int env_resolve_init(struct btf_verifier_env *env)
+{
+ struct btf *btf = env->btf;
+ u32 nr_types = btf->nr_types;
+ u32 *resolved_sizes = NULL;
+ u32 *resolved_ids = NULL;
+ u8 *visit_states = NULL;
+
+ /* +1 for btf_void */
+ resolved_sizes = kvcalloc(nr_types + 1, sizeof(*resolved_sizes),
+ GFP_KERNEL | __GFP_NOWARN);
+ if (!resolved_sizes)
+ goto nomem;
+
+ resolved_ids = kvcalloc(nr_types + 1, sizeof(*resolved_ids),
+ GFP_KERNEL | __GFP_NOWARN);
+ if (!resolved_ids)
+ goto nomem;
+
+ visit_states = kvcalloc(nr_types + 1, sizeof(*visit_states),
+ GFP_KERNEL | __GFP_NOWARN);
+ if (!visit_states)
+ goto nomem;
+
+ btf->resolved_sizes = resolved_sizes;
+ btf->resolved_ids = resolved_ids;
+ env->visit_states = visit_states;
+
+ return 0;
+
+nomem:
+ kvfree(resolved_sizes);
+ kvfree(resolved_ids);
+ kvfree(visit_states);
+ return -ENOMEM;
+}
+
+static void btf_verifier_env_free(struct btf_verifier_env *env)
+{
+ kvfree(env->visit_states);
+ kfree(env);
+}
+
+static bool env_type_is_resolve_sink(const struct btf_verifier_env *env,
+ const struct btf_type *next_type)
+{
+ switch (env->resolve_mode) {
+ case RESOLVE_TBD:
+ /* int, enum or void is a sink */
+ return !btf_type_needs_resolve(next_type);
+ case RESOLVE_PTR:
+ /* int, enum, void, struct or array is a sink for ptr */
+ return !btf_type_is_modifier(next_type) &&
+ !btf_type_is_ptr(next_type);
+ case RESOLVE_STRUCT_OR_ARRAY:
+ /* int, enum, void or ptr is a sink for struct and array */
+ return !btf_type_is_modifier(next_type) &&
+ !btf_type_is_array(next_type) &&
+ !btf_type_is_struct(next_type);
+ default:
+ BUG();
+ }
+}
+
+static bool env_type_is_resolved(const struct btf_verifier_env *env,
+ u32 type_id)
+{
+ return env->visit_states[type_id] == RESOLVED;
+}
+
+static int env_stack_push(struct btf_verifier_env *env,
+ const struct btf_type *t, u32 type_id)
+{
+ struct resolve_vertex *v;
+
+ if (env->top_stack == MAX_RESOLVE_DEPTH)
+ return -E2BIG;
+
+ if (env->visit_states[type_id] != NOT_VISITED)
+ return -EEXIST;
+
+ env->visit_states[type_id] = VISITED;
+
+ v = &env->stack[env->top_stack++];
+ v->t = t;
+ v->type_id = type_id;
+ v->next_member = 0;
+
+ if (env->resolve_mode == RESOLVE_TBD) {
+ if (btf_type_is_ptr(t))
+ env->resolve_mode = RESOLVE_PTR;
+ else if (btf_type_is_struct(t) || btf_type_is_array(t))
+ env->resolve_mode = RESOLVE_STRUCT_OR_ARRAY;
+ }
+
+ return 0;
+}
+
+static void env_stack_set_next_member(struct btf_verifier_env *env,
+ u16 next_member)
+{
+ env->stack[env->top_stack - 1].next_member = next_member;
+}
+
+static void env_stack_pop_resolved(struct btf_verifier_env *env,
+ u32 resolved_type_id,
+ u32 resolved_size)
+{
+ u32 type_id = env->stack[--(env->top_stack)].type_id;
+ struct btf *btf = env->btf;
+
+ btf->resolved_sizes[type_id] = resolved_size;
+ btf->resolved_ids[type_id] = resolved_type_id;
+ env->visit_states[type_id] = RESOLVED;
+}
+
+static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env)
+{
+ return env->top_stack ? &env->stack[env->top_stack - 1] : NULL;
+}
+
+/* The input param "type_id" must point to a needs_resolve type */
+static const struct btf_type *btf_type_id_resolve(const struct btf *btf,
+ u32 *type_id)
+{
+ *type_id = btf->resolved_ids[*type_id];
+ return btf_type_by_id(btf, *type_id);
+}
+
+const struct btf_type *btf_type_id_size(const struct btf *btf,
+ u32 *type_id, u32 *ret_size)
+{
+ const struct btf_type *size_type;
+ u32 size_type_id = *type_id;
+ u32 size = 0;
+
+ size_type = btf_type_by_id(btf, size_type_id);
+ if (btf_type_is_void_or_null(size_type))
+ return NULL;
+
+ if (btf_type_has_size(size_type)) {
+ size = size_type->size;
+ } else if (btf_type_is_array(size_type)) {
+ size = btf->resolved_sizes[size_type_id];
+ } else if (btf_type_is_ptr(size_type)) {
+ size = sizeof(void *);
+ } else {
+ if (WARN_ON_ONCE(!btf_type_is_modifier(size_type)))
+ return NULL;
+
+ size = btf->resolved_sizes[size_type_id];
+ size_type_id = btf->resolved_ids[size_type_id];
+ size_type = btf_type_by_id(btf, size_type_id);
+ if (btf_type_is_void(size_type))
+ return NULL;
+ }
+
+ *type_id = size_type_id;
+ if (ret_size)
+ *ret_size = size;
+
+ return size_type;
+}
+
+static int btf_df_check_member(struct btf_verifier_env *env,
+ const struct btf_type *struct_type,
+ const struct btf_member *member,
+ const struct btf_type *member_type)
+{
+ btf_verifier_log_basic(env, struct_type,
+ "Unsupported check_member");
+ return -EINVAL;
+}
+
+static int btf_df_resolve(struct btf_verifier_env *env,
+ const struct resolve_vertex *v)
+{
+ btf_verifier_log_basic(env, v->t, "Unsupported resolve");
+ return -EINVAL;
+}
+
+static void btf_df_seq_show(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offsets,
+ struct seq_file *m)
+{
+ seq_printf(m, "<unsupported kind:%u>", BTF_INFO_KIND(t->info));
+}
+
+static int btf_int_check_member(struct btf_verifier_env *env,
+ const struct btf_type *struct_type,
+ const struct btf_member *member,
+ const struct btf_type *member_type)
+{
+ u32 int_data = btf_type_int(member_type);
+ u32 struct_bits_off = member->offset;
+ u32 struct_size = struct_type->size;
+ u32 nr_copy_bits;
+ u32 bytes_offset;
+
+ if (U32_MAX - struct_bits_off < BTF_INT_OFFSET(int_data)) {
+ btf_verifier_log_member(env, struct_type, member,
+ "bits_offset exceeds U32_MAX");
+ return -EINVAL;
+ }
+
+ struct_bits_off += BTF_INT_OFFSET(int_data);
+ bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
+ nr_copy_bits = BTF_INT_BITS(int_data) +
+ BITS_PER_BYTE_MASKED(struct_bits_off);
+
+ if (nr_copy_bits > BITS_PER_U64) {
+ btf_verifier_log_member(env, struct_type, member,
+ "nr_copy_bits exceeds 64");
+ return -EINVAL;
+ }
+
+ if (struct_size < bytes_offset ||
+ struct_size - bytes_offset < BITS_ROUNDUP_BYTES(nr_copy_bits)) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Member exceeds struct_size");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static s32 btf_int_check_meta(struct btf_verifier_env *env,
+ const struct btf_type *t,
+ u32 meta_left)
+{
+ u32 int_data, nr_bits, meta_needed = sizeof(int_data);
+ u16 encoding;
+
+ if (meta_left < meta_needed) {
+ btf_verifier_log_basic(env, t,
+ "meta_left:%u meta_needed:%u",
+ meta_left, meta_needed);
+ return -EINVAL;
+ }
+
+ if (btf_type_vlen(t)) {
+ btf_verifier_log_type(env, t, "vlen != 0");
+ return -EINVAL;
+ }
+
+ int_data = btf_type_int(t);
+ if (int_data & ~BTF_INT_MASK) {
+ btf_verifier_log_basic(env, t, "Invalid int_data:%x",
+ int_data);
+ return -EINVAL;
+ }
+
+ nr_bits = BTF_INT_BITS(int_data) + BTF_INT_OFFSET(int_data);
+
+ if (nr_bits > BITS_PER_U64) {
+ btf_verifier_log_type(env, t, "nr_bits exceeds %zu",
+ BITS_PER_U64);
+ return -EINVAL;
+ }
+
+ if (BITS_ROUNDUP_BYTES(nr_bits) > t->size) {
+ btf_verifier_log_type(env, t, "nr_bits exceeds type_size");
+ return -EINVAL;
+ }
+
+ /*
+ * Only one of the encoding bits is allowed and it
+ * should be sufficient for the pretty print purpose (i.e. decoding).
+ * Multiple bits can be allowed later if it is found
+ * to be insufficient.
+ */
+ encoding = BTF_INT_ENCODING(int_data);
+ if (encoding &&
+ encoding != BTF_INT_SIGNED &&
+ encoding != BTF_INT_CHAR &&
+ encoding != BTF_INT_BOOL) {
+ btf_verifier_log_type(env, t, "Unsupported encoding");
+ return -ENOTSUPP;
+ }
+
+ btf_verifier_log_type(env, t, NULL);
+
+ return meta_needed;
+}
+
+static void btf_int_log(struct btf_verifier_env *env,
+ const struct btf_type *t)
+{
+ int int_data = btf_type_int(t);
+
+ btf_verifier_log(env,
+ "size=%u bits_offset=%u nr_bits=%u encoding=%s",
+ t->size, BTF_INT_OFFSET(int_data),
+ BTF_INT_BITS(int_data),
+ btf_int_encoding_str(BTF_INT_ENCODING(int_data)));
+}
+
+static void btf_int_bits_seq_show(const struct btf *btf,
+ const struct btf_type *t,
+ void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ u16 left_shift_bits, right_shift_bits;
+ u32 int_data = btf_type_int(t);
+ u8 nr_bits = BTF_INT_BITS(int_data);
+ u8 total_bits_offset;
+ u8 nr_copy_bytes;
+ u8 nr_copy_bits;
+ u64 print_num;
+
+ /*
+ * bits_offset is at most 7.
+ * BTF_INT_OFFSET() cannot exceed 64 bits.
+ */
+ total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
+ data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
+ bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
+ nr_copy_bits = nr_bits + bits_offset;
+ nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
+
+ print_num = 0;
+ memcpy(&print_num, data, nr_copy_bytes);
+
+#ifdef __BIG_ENDIAN_BITFIELD
+ left_shift_bits = bits_offset;
+#else
+ left_shift_bits = BITS_PER_U64 - nr_copy_bits;
+#endif
+ right_shift_bits = BITS_PER_U64 - nr_bits;
+
+ print_num <<= left_shift_bits;
+ print_num >>= right_shift_bits;
+
+ seq_printf(m, "0x%llx", print_num);
+}
+
+static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ u32 int_data = btf_type_int(t);
+ u8 encoding = BTF_INT_ENCODING(int_data);
+ bool sign = encoding & BTF_INT_SIGNED;
+ u8 nr_bits = BTF_INT_BITS(int_data);
+
+ if (bits_offset || BTF_INT_OFFSET(int_data) ||
+ BITS_PER_BYTE_MASKED(nr_bits)) {
+ btf_int_bits_seq_show(btf, t, data, bits_offset, m);
+ return;
+ }
+
+ switch (nr_bits) {
+ case 64:
+ if (sign)
+ seq_printf(m, "%lld", *(s64 *)data);
+ else
+ seq_printf(m, "%llu", *(u64 *)data);
+ break;
+ case 32:
+ if (sign)
+ seq_printf(m, "%d", *(s32 *)data);
+ else
+ seq_printf(m, "%u", *(u32 *)data);
+ break;
+ case 16:
+ if (sign)
+ seq_printf(m, "%d", *(s16 *)data);
+ else
+ seq_printf(m, "%u", *(u16 *)data);
+ break;
+ case 8:
+ if (sign)
+ seq_printf(m, "%d", *(s8 *)data);
+ else
+ seq_printf(m, "%u", *(u8 *)data);
+ break;
+ default:
+ btf_int_bits_seq_show(btf, t, data, bits_offset, m);
+ }
+}
+
+static const struct btf_kind_operations int_ops = {
+ .check_meta = btf_int_check_meta,
+ .resolve = btf_df_resolve,
+ .check_member = btf_int_check_member,
+ .log_details = btf_int_log,
+ .seq_show = btf_int_seq_show,
+};
+
+static int btf_modifier_check_member(struct btf_verifier_env *env,
+ const struct btf_type *struct_type,
+ const struct btf_member *member,
+ const struct btf_type *member_type)
+{
+ const struct btf_type *resolved_type;
+ u32 resolved_type_id = member->type;
+ struct btf_member resolved_member;
+ struct btf *btf = env->btf;
+
+ resolved_type = btf_type_id_size(btf, &resolved_type_id, NULL);
+ if (!resolved_type) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Invalid member");
+ return -EINVAL;
+ }
+
+ resolved_member = *member;
+ resolved_member.type = resolved_type_id;
+
+ return btf_type_ops(resolved_type)->check_member(env, struct_type,
+ &resolved_member,
+ resolved_type);
+}
+
+static int btf_ptr_check_member(struct btf_verifier_env *env,
+ const struct btf_type *struct_type,
+ const struct btf_member *member,
+ const struct btf_type *member_type)
+{
+ u32 struct_size, struct_bits_off, bytes_offset;
+
+ struct_size = struct_type->size;
+ struct_bits_off = member->offset;
+ bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
+
+ if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Member is not byte aligned");
+ return -EINVAL;
+ }
+
+ if (struct_size - bytes_offset < sizeof(void *)) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Member exceeds struct_size");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int btf_ref_type_check_meta(struct btf_verifier_env *env,
+ const struct btf_type *t,
+ u32 meta_left)
+{
+ if (btf_type_vlen(t)) {
+ btf_verifier_log_type(env, t, "vlen != 0");
+ return -EINVAL;
+ }
+
+ if (!BTF_TYPE_ID_VALID(t->type)) {
+ btf_verifier_log_type(env, t, "Invalid type_id");
+ return -EINVAL;
+ }
+
+ /* typedef type must have a valid name, and other ref types,
+ * volatile, const, restrict, should have a null name.
+ */
+ if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF) {
+ if (!t->name_off ||
+ !btf_name_valid_identifier(env->btf, t->name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+ } else {
+ if (t->name_off) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+ }
+
+ btf_verifier_log_type(env, t, NULL);
+
+ return 0;
+}
+
+static int btf_modifier_resolve(struct btf_verifier_env *env,
+ const struct resolve_vertex *v)
+{
+ const struct btf_type *t = v->t;
+ const struct btf_type *next_type;
+ u32 next_type_id = t->type;
+ struct btf *btf = env->btf;
+ u32 next_type_size = 0;
+
+ next_type = btf_type_by_id(btf, next_type_id);
+ if (!next_type) {
+ btf_verifier_log_type(env, v->t, "Invalid type_id");
+ return -EINVAL;
+ }
+
+ /* "typedef void new_void", "const void"...etc */
+ if (btf_type_is_void(next_type))
+ goto resolved;
+
+ if (!env_type_is_resolve_sink(env, next_type) &&
+ !env_type_is_resolved(env, next_type_id))
+ return env_stack_push(env, next_type, next_type_id);
+
+ /* Figure out the resolved next_type_id with size.
+ * They will be stored in the current modifier's
+ * resolved_ids and resolved_sizes such that it can
+ * save us a few type-following when we use it later (e.g. in
+ * pretty print).
+ */
+ if (!btf_type_id_size(btf, &next_type_id, &next_type_size) &&
+ !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) {
+ btf_verifier_log_type(env, v->t, "Invalid type_id");
+ return -EINVAL;
+ }
+
+resolved:
+ env_stack_pop_resolved(env, next_type_id, next_type_size);
+
+ return 0;
+}
+
+static int btf_ptr_resolve(struct btf_verifier_env *env,
+ const struct resolve_vertex *v)
+{
+ const struct btf_type *next_type;
+ const struct btf_type *t = v->t;
+ u32 next_type_id = t->type;
+ struct btf *btf = env->btf;
+ u32 next_type_size = 0;
+
+ next_type = btf_type_by_id(btf, next_type_id);
+ if (!next_type) {
+ btf_verifier_log_type(env, v->t, "Invalid type_id");
+ return -EINVAL;
+ }
+
+ /* "void *" */
+ if (btf_type_is_void(next_type))
+ goto resolved;
+
+ if (!env_type_is_resolve_sink(env, next_type) &&
+ !env_type_is_resolved(env, next_type_id))
+ return env_stack_push(env, next_type, next_type_id);
+
+ /* If the modifier was RESOLVED during RESOLVE_STRUCT_OR_ARRAY,
+ * the modifier may have stopped resolving when it was resolved
+ * to a ptr (last-resolved-ptr).
+ *
+ * We now need to continue from the last-resolved-ptr to
+ * ensure the last-resolved-ptr will not referring back to
+ * the currenct ptr (t).
+ */
+ if (btf_type_is_modifier(next_type)) {
+ const struct btf_type *resolved_type;
+ u32 resolved_type_id;
+
+ resolved_type_id = next_type_id;
+ resolved_type = btf_type_id_resolve(btf, &resolved_type_id);
+
+ if (btf_type_is_ptr(resolved_type) &&
+ !env_type_is_resolve_sink(env, resolved_type) &&
+ !env_type_is_resolved(env, resolved_type_id))
+ return env_stack_push(env, resolved_type,
+ resolved_type_id);
+ }
+
+ if (!btf_type_id_size(btf, &next_type_id, &next_type_size) &&
+ !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) {
+ btf_verifier_log_type(env, v->t, "Invalid type_id");
+ return -EINVAL;
+ }
+
+resolved:
+ env_stack_pop_resolved(env, next_type_id, 0);
+
+ return 0;
+}
+
+static void btf_modifier_seq_show(const struct btf *btf,
+ const struct btf_type *t,
+ u32 type_id, void *data,
+ u8 bits_offset, struct seq_file *m)
+{
+ t = btf_type_id_resolve(btf, &type_id);
+
+ btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
+}
+
+static void btf_ptr_seq_show(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ /* It is a hashed value */
+ seq_printf(m, "%p", *(void **)data);
+}
+
+static void btf_ref_type_log(struct btf_verifier_env *env,
+ const struct btf_type *t)
+{
+ btf_verifier_log(env, "type_id=%u", t->type);
+}
+
+static struct btf_kind_operations modifier_ops = {
+ .check_meta = btf_ref_type_check_meta,
+ .resolve = btf_modifier_resolve,
+ .check_member = btf_modifier_check_member,
+ .log_details = btf_ref_type_log,
+ .seq_show = btf_modifier_seq_show,
+};
+
+static struct btf_kind_operations ptr_ops = {
+ .check_meta = btf_ref_type_check_meta,
+ .resolve = btf_ptr_resolve,
+ .check_member = btf_ptr_check_member,
+ .log_details = btf_ref_type_log,
+ .seq_show = btf_ptr_seq_show,
+};
+
+static s32 btf_fwd_check_meta(struct btf_verifier_env *env,
+ const struct btf_type *t,
+ u32 meta_left)
+{
+ if (btf_type_vlen(t)) {
+ btf_verifier_log_type(env, t, "vlen != 0");
+ return -EINVAL;
+ }
+
+ if (t->type) {
+ btf_verifier_log_type(env, t, "type != 0");
+ return -EINVAL;
+ }
+
+ /* fwd type must have a valid name */
+ if (!t->name_off ||
+ !btf_name_valid_identifier(env->btf, t->name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
+ btf_verifier_log_type(env, t, NULL);
+
+ return 0;
+}
+
+static struct btf_kind_operations fwd_ops = {
+ .check_meta = btf_fwd_check_meta,
+ .resolve = btf_df_resolve,
+ .check_member = btf_df_check_member,
+ .log_details = btf_ref_type_log,
+ .seq_show = btf_df_seq_show,
+};
+
+static int btf_array_check_member(struct btf_verifier_env *env,
+ const struct btf_type *struct_type,
+ const struct btf_member *member,
+ const struct btf_type *member_type)
+{
+ u32 struct_bits_off = member->offset;
+ u32 struct_size, bytes_offset;
+ u32 array_type_id, array_size;
+ struct btf *btf = env->btf;
+
+ if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Member is not byte aligned");
+ return -EINVAL;
+ }
+
+ array_type_id = member->type;
+ btf_type_id_size(btf, &array_type_id, &array_size);
+ struct_size = struct_type->size;
+ bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
+ if (struct_size - bytes_offset < array_size) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Member exceeds struct_size");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static s32 btf_array_check_meta(struct btf_verifier_env *env,
+ const struct btf_type *t,
+ u32 meta_left)
+{
+ const struct btf_array *array = btf_type_array(t);
+ u32 meta_needed = sizeof(*array);
+
+ if (meta_left < meta_needed) {
+ btf_verifier_log_basic(env, t,
+ "meta_left:%u meta_needed:%u",
+ meta_left, meta_needed);
+ return -EINVAL;
+ }
+
+ /* array type should not have a name */
+ if (t->name_off) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
+ if (btf_type_vlen(t)) {
+ btf_verifier_log_type(env, t, "vlen != 0");
+ return -EINVAL;
+ }
+
+ if (t->size) {
+ btf_verifier_log_type(env, t, "size != 0");
+ return -EINVAL;
+ }
+
+ /* Array elem type and index type cannot be in type void,
+ * so !array->type and !array->index_type are not allowed.
+ */
+ if (!array->type || !BTF_TYPE_ID_VALID(array->type)) {
+ btf_verifier_log_type(env, t, "Invalid elem");
+ return -EINVAL;
+ }
+
+ if (!array->index_type || !BTF_TYPE_ID_VALID(array->index_type)) {
+ btf_verifier_log_type(env, t, "Invalid index");
+ return -EINVAL;
+ }
+
+ btf_verifier_log_type(env, t, NULL);
+
+ return meta_needed;
+}
+
+static int btf_array_resolve(struct btf_verifier_env *env,
+ const struct resolve_vertex *v)
+{
+ const struct btf_array *array = btf_type_array(v->t);
+ const struct btf_type *elem_type, *index_type;
+ u32 elem_type_id, index_type_id;
+ struct btf *btf = env->btf;
+ u32 elem_size;
+
+ /* Check array->index_type */
+ index_type_id = array->index_type;
+ index_type = btf_type_by_id(btf, index_type_id);
+ if (btf_type_is_void_or_null(index_type)) {
+ btf_verifier_log_type(env, v->t, "Invalid index");
+ return -EINVAL;
+ }
+
+ if (!env_type_is_resolve_sink(env, index_type) &&
+ !env_type_is_resolved(env, index_type_id))
+ return env_stack_push(env, index_type, index_type_id);
+
+ index_type = btf_type_id_size(btf, &index_type_id, NULL);
+ if (!index_type || !btf_type_is_int(index_type) ||
+ !btf_type_int_is_regular(index_type)) {
+ btf_verifier_log_type(env, v->t, "Invalid index");
+ return -EINVAL;
+ }
+
+ /* Check array->type */
+ elem_type_id = array->type;
+ elem_type = btf_type_by_id(btf, elem_type_id);
+ if (btf_type_is_void_or_null(elem_type)) {
+ btf_verifier_log_type(env, v->t,
+ "Invalid elem");
+ return -EINVAL;
+ }
+
+ if (!env_type_is_resolve_sink(env, elem_type) &&
+ !env_type_is_resolved(env, elem_type_id))
+ return env_stack_push(env, elem_type, elem_type_id);
+
+ elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
+ if (!elem_type) {
+ btf_verifier_log_type(env, v->t, "Invalid elem");
+ return -EINVAL;
+ }
+
+ if (btf_type_is_int(elem_type) && !btf_type_int_is_regular(elem_type)) {
+ btf_verifier_log_type(env, v->t, "Invalid array of int");
+ return -EINVAL;
+ }
+
+ if (array->nelems && elem_size > U32_MAX / array->nelems) {
+ btf_verifier_log_type(env, v->t,
+ "Array size overflows U32_MAX");
+ return -EINVAL;
+ }
+
+ env_stack_pop_resolved(env, elem_type_id, elem_size * array->nelems);
+
+ return 0;
+}
+
+static void btf_array_log(struct btf_verifier_env *env,
+ const struct btf_type *t)
+{
+ const struct btf_array *array = btf_type_array(t);
+
+ btf_verifier_log(env, "type_id=%u index_type_id=%u nr_elems=%u",
+ array->type, array->index_type, array->nelems);
+}
+
+static void btf_array_seq_show(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ const struct btf_array *array = btf_type_array(t);
+ const struct btf_kind_operations *elem_ops;
+ const struct btf_type *elem_type;
+ u32 i, elem_size, elem_type_id;
+
+ elem_type_id = array->type;
+ elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
+ elem_ops = btf_type_ops(elem_type);
+ seq_puts(m, "[");
+ for (i = 0; i < array->nelems; i++) {
+ if (i)
+ seq_puts(m, ",");
+
+ elem_ops->seq_show(btf, elem_type, elem_type_id, data,
+ bits_offset, m);
+ data += elem_size;
+ }
+ seq_puts(m, "]");
+}
+
+static struct btf_kind_operations array_ops = {
+ .check_meta = btf_array_check_meta,
+ .resolve = btf_array_resolve,
+ .check_member = btf_array_check_member,
+ .log_details = btf_array_log,
+ .seq_show = btf_array_seq_show,
+};
+
+static int btf_struct_check_member(struct btf_verifier_env *env,
+ const struct btf_type *struct_type,
+ const struct btf_member *member,
+ const struct btf_type *member_type)
+{
+ u32 struct_bits_off = member->offset;
+ u32 struct_size, bytes_offset;
+
+ if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Member is not byte aligned");
+ return -EINVAL;
+ }
+
+ struct_size = struct_type->size;
+ bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
+ if (struct_size - bytes_offset < member_type->size) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Member exceeds struct_size");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static s32 btf_struct_check_meta(struct btf_verifier_env *env,
+ const struct btf_type *t,
+ u32 meta_left)
+{
+ bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION;
+ const struct btf_member *member;
+ u32 meta_needed, last_offset;
+ struct btf *btf = env->btf;
+ u32 struct_size = t->size;
+ u16 i;
+
+ meta_needed = btf_type_vlen(t) * sizeof(*member);
+ if (meta_left < meta_needed) {
+ btf_verifier_log_basic(env, t,
+ "meta_left:%u meta_needed:%u",
+ meta_left, meta_needed);
+ return -EINVAL;
+ }
+
+ /* struct type either no name or a valid one */
+ if (t->name_off &&
+ !btf_name_valid_identifier(env->btf, t->name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
+ btf_verifier_log_type(env, t, NULL);
+
+ last_offset = 0;
+ for_each_member(i, t, member) {
+ if (!btf_name_offset_valid(btf, member->name_off)) {
+ btf_verifier_log_member(env, t, member,
+ "Invalid member name_offset:%u",
+ member->name_off);
+ return -EINVAL;
+ }
+
+ /* struct member either no name or a valid one */
+ if (member->name_off &&
+ !btf_name_valid_identifier(btf, member->name_off)) {
+ btf_verifier_log_member(env, t, member, "Invalid name");
+ return -EINVAL;
+ }
+ /* A member cannot be in type void */
+ if (!member->type || !BTF_TYPE_ID_VALID(member->type)) {
+ btf_verifier_log_member(env, t, member,
+ "Invalid type_id");
+ return -EINVAL;
+ }
+
+ if (is_union && member->offset) {
+ btf_verifier_log_member(env, t, member,
+ "Invalid member bits_offset");
+ return -EINVAL;
+ }
+
+ /*
+ * ">" instead of ">=" because the last member could be
+ * "char a[0];"
+ */
+ if (last_offset > member->offset) {
+ btf_verifier_log_member(env, t, member,
+ "Invalid member bits_offset");
+ return -EINVAL;
+ }
+
+ if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) {
+ btf_verifier_log_member(env, t, member,
+ "Memmber bits_offset exceeds its struct size");
+ return -EINVAL;
+ }
+
+ btf_verifier_log_member(env, t, member, NULL);
+ last_offset = member->offset;
+ }
+
+ return meta_needed;
+}
+
+static int btf_struct_resolve(struct btf_verifier_env *env,
+ const struct resolve_vertex *v)
+{
+ const struct btf_member *member;
+ int err;
+ u16 i;
+
+ /* Before continue resolving the next_member,
+ * ensure the last member is indeed resolved to a
+ * type with size info.
+ */
+ if (v->next_member) {
+ const struct btf_type *last_member_type;
+ const struct btf_member *last_member;
+ u16 last_member_type_id;
+
+ last_member = btf_type_member(v->t) + v->next_member - 1;
+ last_member_type_id = last_member->type;
+ if (WARN_ON_ONCE(!env_type_is_resolved(env,
+ last_member_type_id)))
+ return -EINVAL;
+
+ last_member_type = btf_type_by_id(env->btf,
+ last_member_type_id);
+ err = btf_type_ops(last_member_type)->check_member(env, v->t,
+ last_member,
+ last_member_type);
+ if (err)
+ return err;
+ }
+
+ for_each_member_from(i, v->next_member, v->t, member) {
+ u32 member_type_id = member->type;
+ const struct btf_type *member_type = btf_type_by_id(env->btf,
+ member_type_id);
+
+ if (btf_type_is_void_or_null(member_type)) {
+ btf_verifier_log_member(env, v->t, member,
+ "Invalid member");
+ return -EINVAL;
+ }
+
+ if (!env_type_is_resolve_sink(env, member_type) &&
+ !env_type_is_resolved(env, member_type_id)) {
+ env_stack_set_next_member(env, i + 1);
+ return env_stack_push(env, member_type, member_type_id);
+ }
+
+ err = btf_type_ops(member_type)->check_member(env, v->t,
+ member,
+ member_type);
+ if (err)
+ return err;
+ }
+
+ env_stack_pop_resolved(env, 0, 0);
+
+ return 0;
+}
+
+static void btf_struct_log(struct btf_verifier_env *env,
+ const struct btf_type *t)
+{
+ btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
+}
+
+static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ const char *seq = BTF_INFO_KIND(t->info) == BTF_KIND_UNION ? "|" : ",";
+ const struct btf_member *member;
+ u32 i;
+
+ seq_puts(m, "{");
+ for_each_member(i, t, member) {
+ const struct btf_type *member_type = btf_type_by_id(btf,
+ member->type);
+ u32 member_offset = member->offset;
+ u32 bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset);
+ u8 bits8_offset = BITS_PER_BYTE_MASKED(member_offset);
+ const struct btf_kind_operations *ops;
+
+ if (i)
+ seq_puts(m, seq);
+
+ ops = btf_type_ops(member_type);
+ ops->seq_show(btf, member_type, member->type,
+ data + bytes_offset, bits8_offset, m);
+ }
+ seq_puts(m, "}");
+}
+
+static struct btf_kind_operations struct_ops = {
+ .check_meta = btf_struct_check_meta,
+ .resolve = btf_struct_resolve,
+ .check_member = btf_struct_check_member,
+ .log_details = btf_struct_log,
+ .seq_show = btf_struct_seq_show,
+};
+
+static int btf_enum_check_member(struct btf_verifier_env *env,
+ const struct btf_type *struct_type,
+ const struct btf_member *member,
+ const struct btf_type *member_type)
+{
+ u32 struct_bits_off = member->offset;
+ u32 struct_size, bytes_offset;
+
+ if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Member is not byte aligned");
+ return -EINVAL;
+ }
+
+ struct_size = struct_type->size;
+ bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
+ if (struct_size - bytes_offset < member_type->size) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Member exceeds struct_size");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static s32 btf_enum_check_meta(struct btf_verifier_env *env,
+ const struct btf_type *t,
+ u32 meta_left)
+{
+ const struct btf_enum *enums = btf_type_enum(t);
+ struct btf *btf = env->btf;
+ u16 i, nr_enums;
+ u32 meta_needed;
+
+ nr_enums = btf_type_vlen(t);
+ meta_needed = nr_enums * sizeof(*enums);
+
+ if (meta_left < meta_needed) {
+ btf_verifier_log_basic(env, t,
+ "meta_left:%u meta_needed:%u",
+ meta_left, meta_needed);
+ return -EINVAL;
+ }
+
+ if (t->size != sizeof(int)) {
+ btf_verifier_log_type(env, t, "Expected size:%zu",
+ sizeof(int));
+ return -EINVAL;
+ }
+
+ /* enum type either no name or a valid one */
+ if (t->name_off &&
+ !btf_name_valid_identifier(env->btf, t->name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
+ btf_verifier_log_type(env, t, NULL);
+
+ for (i = 0; i < nr_enums; i++) {
+ if (!btf_name_offset_valid(btf, enums[i].name_off)) {
+ btf_verifier_log(env, "\tInvalid name_offset:%u",
+ enums[i].name_off);
+ return -EINVAL;
+ }
+
+ /* enum member must have a valid name */
+ if (!enums[i].name_off ||
+ !btf_name_valid_identifier(btf, enums[i].name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
+
+ btf_verifier_log(env, "\t%s val=%d\n",
+ btf_name_by_offset(btf, enums[i].name_off),
+ enums[i].val);
+ }
+
+ return meta_needed;
+}
+
+static void btf_enum_log(struct btf_verifier_env *env,
+ const struct btf_type *t)
+{
+ btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
+}
+
+static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ const struct btf_enum *enums = btf_type_enum(t);
+ u32 i, nr_enums = btf_type_vlen(t);
+ int v = *(int *)data;
+
+ for (i = 0; i < nr_enums; i++) {
+ if (v == enums[i].val) {
+ seq_printf(m, "%s",
+ btf_name_by_offset(btf, enums[i].name_off));
+ return;
+ }
+ }
+
+ seq_printf(m, "%d", v);
+}
+
+static struct btf_kind_operations enum_ops = {
+ .check_meta = btf_enum_check_meta,
+ .resolve = btf_df_resolve,
+ .check_member = btf_enum_check_member,
+ .log_details = btf_enum_log,
+ .seq_show = btf_enum_seq_show,
+};
+
+static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = {
+ [BTF_KIND_INT] = &int_ops,
+ [BTF_KIND_PTR] = &ptr_ops,
+ [BTF_KIND_ARRAY] = &array_ops,
+ [BTF_KIND_STRUCT] = &struct_ops,
+ [BTF_KIND_UNION] = &struct_ops,
+ [BTF_KIND_ENUM] = &enum_ops,
+ [BTF_KIND_FWD] = &fwd_ops,
+ [BTF_KIND_TYPEDEF] = &modifier_ops,
+ [BTF_KIND_VOLATILE] = &modifier_ops,
+ [BTF_KIND_CONST] = &modifier_ops,
+ [BTF_KIND_RESTRICT] = &modifier_ops,
+};
+
+static s32 btf_check_meta(struct btf_verifier_env *env,
+ const struct btf_type *t,
+ u32 meta_left)
+{
+ u32 saved_meta_left = meta_left;
+ s32 var_meta_size;
+
+ if (meta_left < sizeof(*t)) {
+ btf_verifier_log(env, "[%u] meta_left:%u meta_needed:%zu",
+ env->log_type_id, meta_left, sizeof(*t));
+ return -EINVAL;
+ }
+ meta_left -= sizeof(*t);
+
+ if (t->info & ~BTF_INFO_MASK) {
+ btf_verifier_log(env, "[%u] Invalid btf_info:%x",
+ env->log_type_id, t->info);
+ return -EINVAL;
+ }
+
+ if (BTF_INFO_KIND(t->info) > BTF_KIND_MAX ||
+ BTF_INFO_KIND(t->info) == BTF_KIND_UNKN) {
+ btf_verifier_log(env, "[%u] Invalid kind:%u",
+ env->log_type_id, BTF_INFO_KIND(t->info));
+ return -EINVAL;
+ }
+
+ if (!btf_name_offset_valid(env->btf, t->name_off)) {
+ btf_verifier_log(env, "[%u] Invalid name_offset:%u",
+ env->log_type_id, t->name_off);
+ return -EINVAL;
+ }
+
+ var_meta_size = btf_type_ops(t)->check_meta(env, t, meta_left);
+ if (var_meta_size < 0)
+ return var_meta_size;
+
+ meta_left -= var_meta_size;
+
+ return saved_meta_left - meta_left;
+}
+
+static int btf_check_all_metas(struct btf_verifier_env *env)
+{
+ struct btf *btf = env->btf;
+ struct btf_header *hdr;
+ void *cur, *end;
+
+ hdr = &btf->hdr;
+ cur = btf->nohdr_data + hdr->type_off;
+ end = cur + hdr->type_len;
+
+ env->log_type_id = 1;
+ while (cur < end) {
+ struct btf_type *t = cur;
+ s32 meta_size;
+
+ meta_size = btf_check_meta(env, t, end - cur);
+ if (meta_size < 0)
+ return meta_size;
+
+ btf_add_type(env, t);
+ cur += meta_size;
+ env->log_type_id++;
+ }
+
+ return 0;
+}
+
+static int btf_resolve(struct btf_verifier_env *env,
+ const struct btf_type *t, u32 type_id)
+{
+ const struct resolve_vertex *v;
+ int err = 0;
+
+ env->resolve_mode = RESOLVE_TBD;
+ env_stack_push(env, t, type_id);
+ while (!err && (v = env_stack_peak(env))) {
+ env->log_type_id = v->type_id;
+ err = btf_type_ops(v->t)->resolve(env, v);
+ }
+
+ env->log_type_id = type_id;
+ if (err == -E2BIG)
+ btf_verifier_log_type(env, t,
+ "Exceeded max resolving depth:%u",
+ MAX_RESOLVE_DEPTH);
+ else if (err == -EEXIST)
+ btf_verifier_log_type(env, t, "Loop detected");
+
+ return err;
+}
+
+static bool btf_resolve_valid(struct btf_verifier_env *env,
+ const struct btf_type *t,
+ u32 type_id)
+{
+ struct btf *btf = env->btf;
+
+ if (!env_type_is_resolved(env, type_id))
+ return false;
+
+ if (btf_type_is_struct(t))
+ return !btf->resolved_ids[type_id] &&
+ !btf->resolved_sizes[type_id];
+
+ if (btf_type_is_modifier(t) || btf_type_is_ptr(t)) {
+ t = btf_type_id_resolve(btf, &type_id);
+ return t && !btf_type_is_modifier(t);
+ }
+
+ if (btf_type_is_array(t)) {
+ const struct btf_array *array = btf_type_array(t);
+ const struct btf_type *elem_type;
+ u32 elem_type_id = array->type;
+ u32 elem_size;
+
+ elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
+ return elem_type && !btf_type_is_modifier(elem_type) &&
+ (array->nelems * elem_size ==
+ btf->resolved_sizes[type_id]);
+ }
+
+ return false;
+}
+
+static int btf_check_all_types(struct btf_verifier_env *env)
+{
+ struct btf *btf = env->btf;
+ u32 type_id;
+ int err;
+
+ err = env_resolve_init(env);
+ if (err)
+ return err;
+
+ env->phase++;
+ for (type_id = 1; type_id <= btf->nr_types; type_id++) {
+ const struct btf_type *t = btf_type_by_id(btf, type_id);
+
+ env->log_type_id = type_id;
+ if (btf_type_needs_resolve(t) &&
+ !env_type_is_resolved(env, type_id)) {
+ err = btf_resolve(env, t, type_id);
+ if (err)
+ return err;
+ }
+
+ if (btf_type_needs_resolve(t) &&
+ !btf_resolve_valid(env, t, type_id)) {
+ btf_verifier_log_type(env, t, "Invalid resolve state");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+static int btf_parse_type_sec(struct btf_verifier_env *env)
+{
+ const struct btf_header *hdr = &env->btf->hdr;
+ int err;
+
+ /* Type section must align to 4 bytes */
+ if (hdr->type_off & (sizeof(u32) - 1)) {
+ btf_verifier_log(env, "Unaligned type_off");
+ return -EINVAL;
+ }
+
+ if (!hdr->type_len) {
+ btf_verifier_log(env, "No type found");
+ return -EINVAL;
+ }
+
+ err = btf_check_all_metas(env);
+ if (err)
+ return err;
+
+ return btf_check_all_types(env);
+}
+
+static int btf_parse_str_sec(struct btf_verifier_env *env)
+{
+ const struct btf_header *hdr;
+ struct btf *btf = env->btf;
+ const char *start, *end;
+
+ hdr = &btf->hdr;
+ start = btf->nohdr_data + hdr->str_off;
+ end = start + hdr->str_len;
+
+ if (end != btf->data + btf->data_size) {
+ btf_verifier_log(env, "String section is not at the end");
+ return -EINVAL;
+ }
+
+ if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET ||
+ start[0] || end[-1]) {
+ btf_verifier_log(env, "Invalid string section");
+ return -EINVAL;
+ }
+
+ btf->strings = start;
+
+ return 0;
+}
+
+static const size_t btf_sec_info_offset[] = {
+ offsetof(struct btf_header, type_off),
+ offsetof(struct btf_header, str_off),
+};
+
+static int btf_sec_info_cmp(const void *a, const void *b)
+{
+ const struct btf_sec_info *x = a;
+ const struct btf_sec_info *y = b;
+
+ return (int)(x->off - y->off) ? : (int)(x->len - y->len);
+}
+
+static int btf_check_sec_info(struct btf_verifier_env *env,
+ u32 btf_data_size)
+{
+ struct btf_sec_info secs[ARRAY_SIZE(btf_sec_info_offset)];
+ u32 total, expected_total, i;
+ const struct btf_header *hdr;
+ const struct btf *btf;
+
+ btf = env->btf;
+ hdr = &btf->hdr;
+
+ /* Populate the secs from hdr */
+ for (i = 0; i < ARRAY_SIZE(btf_sec_info_offset); i++)
+ secs[i] = *(struct btf_sec_info *)((void *)hdr +
+ btf_sec_info_offset[i]);
+
+ sort(secs, ARRAY_SIZE(btf_sec_info_offset),
+ sizeof(struct btf_sec_info), btf_sec_info_cmp, NULL);
+
+ /* Check for gaps and overlap among sections */
+ total = 0;
+ expected_total = btf_data_size - hdr->hdr_len;
+ for (i = 0; i < ARRAY_SIZE(btf_sec_info_offset); i++) {
+ if (expected_total < secs[i].off) {
+ btf_verifier_log(env, "Invalid section offset");
+ return -EINVAL;
+ }
+ if (total < secs[i].off) {
+ /* gap */
+ btf_verifier_log(env, "Unsupported section found");
+ return -EINVAL;
+ }
+ if (total > secs[i].off) {
+ btf_verifier_log(env, "Section overlap found");
+ return -EINVAL;
+ }
+ if (expected_total - total < secs[i].len) {
+ btf_verifier_log(env,
+ "Total section length too long");
+ return -EINVAL;
+ }
+ total += secs[i].len;
+ }
+
+ /* There is data other than hdr and known sections */
+ if (expected_total != total) {
+ btf_verifier_log(env, "Unsupported section found");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int btf_parse_hdr(struct btf_verifier_env *env)
+{
+ u32 hdr_len, hdr_copy, btf_data_size;
+ const struct btf_header *hdr;
+ struct btf *btf;
+ int err;
+
+ btf = env->btf;
+ btf_data_size = btf->data_size;
+
+ if (btf_data_size <
+ offsetof(struct btf_header, hdr_len) + sizeof(hdr->hdr_len)) {
+ btf_verifier_log(env, "hdr_len not found");
+ return -EINVAL;
+ }
+
+ hdr = btf->data;
+ hdr_len = hdr->hdr_len;
+ if (btf_data_size < hdr_len) {
+ btf_verifier_log(env, "btf_header not found");
+ return -EINVAL;
+ }
+
+ /* Ensure the unsupported header fields are zero */
+ if (hdr_len > sizeof(btf->hdr)) {
+ u8 *expected_zero = btf->data + sizeof(btf->hdr);
+ u8 *end = btf->data + hdr_len;
+
+ for (; expected_zero < end; expected_zero++) {
+ if (*expected_zero) {
+ btf_verifier_log(env, "Unsupported btf_header");
+ return -E2BIG;
+ }
+ }
+ }
+
+ hdr_copy = min_t(u32, hdr_len, sizeof(btf->hdr));
+ memcpy(&btf->hdr, btf->data, hdr_copy);
+
+ hdr = &btf->hdr;
+
+ if (hdr->hdr_len != hdr_len)
+ return -EINVAL;
+
+ btf_verifier_log_hdr(env, btf_data_size);
+
+ if (hdr->magic != BTF_MAGIC) {
+ btf_verifier_log(env, "Invalid magic");
+ return -EINVAL;
+ }
+
+ if (hdr->version != BTF_VERSION) {
+ btf_verifier_log(env, "Unsupported version");
+ return -ENOTSUPP;
+ }
+
+ if (hdr->flags) {
+ btf_verifier_log(env, "Unsupported flags");
+ return -ENOTSUPP;
+ }
+
+ if (btf_data_size == hdr->hdr_len) {
+ btf_verifier_log(env, "No data");
+ return -EINVAL;
+ }
+
+ err = btf_check_sec_info(env, btf_data_size);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size,
+ u32 log_level, char __user *log_ubuf, u32 log_size)
+{
+ struct btf_verifier_env *env = NULL;
+ struct bpf_verifier_log *log;
+ struct btf *btf = NULL;
+ u8 *data;
+ int err;
+
+ if (btf_data_size > BTF_MAX_SIZE)
+ return ERR_PTR(-E2BIG);
+
+ env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN);
+ if (!env)
+ return ERR_PTR(-ENOMEM);
+
+ log = &env->log;
+ if (log_level || log_ubuf || log_size) {
+ /* user requested verbose verifier output
+ * and supplied buffer to store the verification trace
+ */
+ log->level = log_level;
+ log->ubuf = log_ubuf;
+ log->len_total = log_size;
+
+ /* log attributes have to be sane */
+ if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
+ !log->level || !log->ubuf) {
+ err = -EINVAL;
+ goto errout;
+ }
+ }
+
+ btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN);
+ if (!btf) {
+ err = -ENOMEM;
+ goto errout;
+ }
+ env->btf = btf;
+
+ data = kvmalloc(btf_data_size, GFP_KERNEL | __GFP_NOWARN);
+ if (!data) {
+ err = -ENOMEM;
+ goto errout;
+ }
+
+ btf->data = data;
+ btf->data_size = btf_data_size;
+
+ if (copy_from_user(data, btf_data, btf_data_size)) {
+ err = -EFAULT;
+ goto errout;
+ }
+
+ err = btf_parse_hdr(env);
+ if (err)
+ goto errout;
+
+ btf->nohdr_data = btf->data + btf->hdr.hdr_len;
+
+ err = btf_parse_str_sec(env);
+ if (err)
+ goto errout;
+
+ err = btf_parse_type_sec(env);
+ if (err)
+ goto errout;
+
+ if (log->level && bpf_verifier_log_full(log)) {
+ err = -ENOSPC;
+ goto errout;
+ }
+
+ btf_verifier_env_free(env);
+ refcount_set(&btf->refcnt, 1);
+ return btf;
+
+errout:
+ btf_verifier_env_free(env);
+ if (btf)
+ btf_free(btf);
+ return ERR_PTR(err);
+}
+
+void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
+ struct seq_file *m)
+{
+ const struct btf_type *t = btf_type_by_id(btf, type_id);
+
+ btf_type_ops(t)->seq_show(btf, t, type_id, obj, 0, m);
+}
+
+static int btf_release(struct inode *inode, struct file *filp)
+{
+ btf_put(filp->private_data);
+ return 0;
+}
+
+const struct file_operations btf_fops = {
+ .release = btf_release,
+};
+
+static int __btf_new_fd(struct btf *btf)
+{
+ return anon_inode_getfd("btf", &btf_fops, btf, O_RDONLY | O_CLOEXEC);
+}
+
+int btf_new_fd(const union bpf_attr *attr)
+{
+ struct btf *btf;
+ int ret;
+
+ btf = btf_parse(u64_to_user_ptr(attr->btf),
+ attr->btf_size, attr->btf_log_level,
+ u64_to_user_ptr(attr->btf_log_buf),
+ attr->btf_log_size);
+ if (IS_ERR(btf))
+ return PTR_ERR(btf);
+
+ ret = btf_alloc_id(btf);
+ if (ret) {
+ btf_free(btf);
+ return ret;
+ }
+
+ /*
+ * The BTF ID is published to the userspace.
+ * All BTF free must go through call_rcu() from
+ * now on (i.e. free by calling btf_put()).
+ */
+
+ ret = __btf_new_fd(btf);
+ if (ret < 0)
+ btf_put(btf);
+
+ return ret;
+}
+
+struct btf *btf_get_by_fd(int fd)
+{
+ struct btf *btf;
+ struct fd f;
+
+ f = fdget(fd);
+
+ if (!f.file)
+ return ERR_PTR(-EBADF);
+
+ if (f.file->f_op != &btf_fops) {
+ fdput(f);
+ return ERR_PTR(-EINVAL);
+ }
+
+ btf = f.file->private_data;
+ refcount_inc(&btf->refcnt);
+ fdput(f);
+
+ return btf;
+}
+
+int btf_get_info_by_fd(const struct btf *btf,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_btf_info __user *uinfo;
+ struct bpf_btf_info info;
+ u32 info_copy, btf_copy;
+ void __user *ubtf;
+ u32 uinfo_len;
+
+ uinfo = u64_to_user_ptr(attr->info.info);
+ uinfo_len = attr->info.info_len;
+
+ info_copy = min_t(u32, uinfo_len, sizeof(info));
+ memset(&info, 0, sizeof(info));
+ if (copy_from_user(&info, uinfo, info_copy))
+ return -EFAULT;
+
+ info.id = btf->id;
+ ubtf = u64_to_user_ptr(info.btf);
+ btf_copy = min_t(u32, btf->data_size, info.btf_size);
+ if (copy_to_user(ubtf, btf->data, btf_copy))
+ return -EFAULT;
+ info.btf_size = btf->data_size;
+
+ if (copy_to_user(uinfo, &info, info_copy) ||
+ put_user(info_copy, &uattr->info.info_len))
+ return -EFAULT;
+
+ return 0;
+}
+
+int btf_get_fd_by_id(u32 id)
+{
+ struct btf *btf;
+ int fd;
+
+ rcu_read_lock();
+ btf = idr_find(&btf_idr, id);
+ if (!btf || !refcount_inc_not_zero(&btf->refcnt))
+ btf = ERR_PTR(-ENOENT);
+ rcu_read_unlock();
+
+ if (IS_ERR(btf))
+ return PTR_ERR(btf);
+
+ fd = __btf_new_fd(btf);
+ if (fd < 0)
+ btf_put(btf);
+
+ return fd;
+}
+
+u32 btf_id(const struct btf *btf)
+{
+ return btf->id;
+}
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
new file mode 100644
index 000000000..6a7d931bb
--- /dev/null
+++ b/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,
+};
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
new file mode 100644
index 000000000..4e5b5ae05
--- /dev/null
+++ b/kernel/bpf/core.c
@@ -0,0 +1,1945 @@
+/*
+ * Linux Socket Filter - Kernel level socket filtering
+ *
+ * Based on the design of the Berkeley Packet Filter. The new
+ * internal format has been designed by PLUMgrid:
+ *
+ * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com
+ *
+ * Authors:
+ *
+ * Jay Schulist <jschlst@samba.org>
+ * Alexei Starovoitov <ast@plumgrid.com>
+ * Daniel Borkmann <dborkman@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Andi Kleen - Fix a few bad bugs and races.
+ * Kris Katterjohn - Added many additional checks in bpf_check_classic()
+ */
+
+#include <linux/filter.h>
+#include <linux/skbuff.h>
+#include <linux/vmalloc.h>
+#include <linux/random.h>
+#include <linux/moduleloader.h>
+#include <linux/bpf.h>
+#include <linux/frame.h>
+#include <linux/rbtree_latch.h>
+#include <linux/kallsyms.h>
+#include <linux/rcupdate.h>
+#include <linux/perf_event.h>
+
+#include <asm/barrier.h>
+#include <asm/unaligned.h>
+
+/* Registers */
+#define BPF_R0 regs[BPF_REG_0]
+#define BPF_R1 regs[BPF_REG_1]
+#define BPF_R2 regs[BPF_REG_2]
+#define BPF_R3 regs[BPF_REG_3]
+#define BPF_R4 regs[BPF_REG_4]
+#define BPF_R5 regs[BPF_REG_5]
+#define BPF_R6 regs[BPF_REG_6]
+#define BPF_R7 regs[BPF_REG_7]
+#define BPF_R8 regs[BPF_REG_8]
+#define BPF_R9 regs[BPF_REG_9]
+#define BPF_R10 regs[BPF_REG_10]
+
+/* Named registers */
+#define DST regs[insn->dst_reg]
+#define SRC regs[insn->src_reg]
+#define FP regs[BPF_REG_FP]
+#define AX regs[BPF_REG_AX]
+#define ARG1 regs[BPF_REG_ARG1]
+#define CTX regs[BPF_REG_CTX]
+#define IMM insn->imm
+
+/* No hurry in this branch
+ *
+ * Exported for the bpf jit load helper.
+ */
+void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size)
+{
+ u8 *ptr = NULL;
+
+ if (k >= SKF_NET_OFF)
+ ptr = skb_network_header(skb) + k - SKF_NET_OFF;
+ else if (k >= SKF_LL_OFF)
+ ptr = skb_mac_header(skb) + k - SKF_LL_OFF;
+
+ if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb))
+ return ptr;
+
+ return NULL;
+}
+
+struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
+{
+ gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
+ struct bpf_prog_aux *aux;
+ struct bpf_prog *fp;
+
+ size = round_up(size, PAGE_SIZE);
+ fp = __vmalloc(size, gfp_flags, PAGE_KERNEL);
+ if (fp == NULL)
+ return NULL;
+
+ aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags);
+ if (aux == NULL) {
+ vfree(fp);
+ return NULL;
+ }
+
+ fp->pages = size / PAGE_SIZE;
+ fp->aux = aux;
+ fp->aux->prog = fp;
+ fp->jit_requested = ebpf_jit_enabled();
+
+ INIT_LIST_HEAD_RCU(&fp->aux->ksym_lnode);
+
+ return fp;
+}
+EXPORT_SYMBOL_GPL(bpf_prog_alloc);
+
+struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
+ gfp_t gfp_extra_flags)
+{
+ gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
+ struct bpf_prog *fp;
+ u32 pages, delta;
+ int ret;
+
+ BUG_ON(fp_old == NULL);
+
+ size = round_up(size, PAGE_SIZE);
+ pages = size / PAGE_SIZE;
+ if (pages <= fp_old->pages)
+ return fp_old;
+
+ delta = pages - fp_old->pages;
+ ret = __bpf_prog_charge(fp_old->aux->user, delta);
+ if (ret)
+ return NULL;
+
+ fp = __vmalloc(size, gfp_flags, PAGE_KERNEL);
+ if (fp == NULL) {
+ __bpf_prog_uncharge(fp_old->aux->user, delta);
+ } else {
+ memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE);
+ fp->pages = pages;
+ fp->aux->prog = fp;
+
+ /* We keep fp->aux from fp_old around in the new
+ * reallocated structure.
+ */
+ fp_old->aux = NULL;
+ __bpf_prog_free(fp_old);
+ }
+
+ return fp;
+}
+
+void __bpf_prog_free(struct bpf_prog *fp)
+{
+ kfree(fp->aux);
+ vfree(fp);
+}
+
+int bpf_prog_calc_tag(struct bpf_prog *fp)
+{
+ const u32 bits_offset = SHA_MESSAGE_BYTES - sizeof(__be64);
+ u32 raw_size = bpf_prog_tag_scratch_size(fp);
+ u32 digest[SHA_DIGEST_WORDS];
+ u32 ws[SHA_WORKSPACE_WORDS];
+ u32 i, bsize, psize, blocks;
+ struct bpf_insn *dst;
+ bool was_ld_map;
+ u8 *raw, *todo;
+ __be32 *result;
+ __be64 *bits;
+
+ raw = vmalloc(raw_size);
+ if (!raw)
+ return -ENOMEM;
+
+ sha_init(digest);
+ memset(ws, 0, sizeof(ws));
+
+ /* We need to take out the map fd for the digest calculation
+ * since they are unstable from user space side.
+ */
+ dst = (void *)raw;
+ for (i = 0, was_ld_map = false; i < fp->len; i++) {
+ dst[i] = fp->insnsi[i];
+ if (!was_ld_map &&
+ dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) &&
+ dst[i].src_reg == BPF_PSEUDO_MAP_FD) {
+ was_ld_map = true;
+ dst[i].imm = 0;
+ } else if (was_ld_map &&
+ dst[i].code == 0 &&
+ dst[i].dst_reg == 0 &&
+ dst[i].src_reg == 0 &&
+ dst[i].off == 0) {
+ was_ld_map = false;
+ dst[i].imm = 0;
+ } else {
+ was_ld_map = false;
+ }
+ }
+
+ psize = bpf_prog_insn_size(fp);
+ memset(&raw[psize], 0, raw_size - psize);
+ raw[psize++] = 0x80;
+
+ bsize = round_up(psize, SHA_MESSAGE_BYTES);
+ blocks = bsize / SHA_MESSAGE_BYTES;
+ todo = raw;
+ if (bsize - psize >= sizeof(__be64)) {
+ bits = (__be64 *)(todo + bsize - sizeof(__be64));
+ } else {
+ bits = (__be64 *)(todo + bsize + bits_offset);
+ blocks++;
+ }
+ *bits = cpu_to_be64((psize - 1) << 3);
+
+ while (blocks--) {
+ sha_transform(digest, todo, ws);
+ todo += SHA_MESSAGE_BYTES;
+ }
+
+ result = (__force __be32 *)digest;
+ for (i = 0; i < SHA_DIGEST_WORDS; i++)
+ result[i] = cpu_to_be32(digest[i]);
+ memcpy(fp->tag, result, sizeof(fp->tag));
+
+ vfree(raw);
+ return 0;
+}
+
+static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, u32 delta,
+ u32 curr, const bool probe_pass)
+{
+ const s64 imm_min = S32_MIN, imm_max = S32_MAX;
+ s64 imm = insn->imm;
+
+ if (curr < pos && curr + imm + 1 > pos)
+ imm += delta;
+ else if (curr > pos + delta && curr + imm + 1 <= pos + delta)
+ imm -= delta;
+ if (imm < imm_min || imm > imm_max)
+ return -ERANGE;
+ if (!probe_pass)
+ insn->imm = imm;
+ return 0;
+}
+
+static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, u32 delta,
+ u32 curr, const bool probe_pass)
+{
+ const s32 off_min = S16_MIN, off_max = S16_MAX;
+ s32 off = insn->off;
+
+ if (curr < pos && curr + off + 1 > pos)
+ off += delta;
+ else if (curr > pos + delta && curr + off + 1 <= pos + delta)
+ off -= delta;
+ if (off < off_min || off > off_max)
+ return -ERANGE;
+ if (!probe_pass)
+ insn->off = off;
+ return 0;
+}
+
+static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta,
+ const bool probe_pass)
+{
+ u32 i, insn_cnt = prog->len + (probe_pass ? delta : 0);
+ struct bpf_insn *insn = prog->insnsi;
+ int ret = 0;
+
+ for (i = 0; i < insn_cnt; i++, insn++) {
+ u8 code;
+
+ /* In the probing pass we still operate on the original,
+ * unpatched image in order to check overflows before we
+ * do any other adjustments. Therefore skip the patchlet.
+ */
+ if (probe_pass && i == pos) {
+ i += delta + 1;
+ insn++;
+ }
+ code = insn->code;
+ if (BPF_CLASS(code) != BPF_JMP ||
+ BPF_OP(code) == BPF_EXIT)
+ continue;
+ /* Adjust offset of jmps if we cross patch boundaries. */
+ if (BPF_OP(code) == BPF_CALL) {
+ if (insn->src_reg != BPF_PSEUDO_CALL)
+ continue;
+ ret = bpf_adj_delta_to_imm(insn, pos, delta, i,
+ probe_pass);
+ } else {
+ ret = bpf_adj_delta_to_off(insn, pos, delta, i,
+ probe_pass);
+ }
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
+ const struct bpf_insn *patch, u32 len)
+{
+ u32 insn_adj_cnt, insn_rest, insn_delta = len - 1;
+ const u32 cnt_max = S16_MAX;
+ struct bpf_prog *prog_adj;
+
+ /* Since our patchlet doesn't expand the image, we're done. */
+ if (insn_delta == 0) {
+ memcpy(prog->insnsi + off, patch, sizeof(*patch));
+ return prog;
+ }
+
+ insn_adj_cnt = prog->len + insn_delta;
+
+ /* Reject anything that would potentially let the insn->off
+ * target overflow when we have excessive program expansions.
+ * We need to probe here before we do any reallocation where
+ * we afterwards may not fail anymore.
+ */
+ if (insn_adj_cnt > cnt_max &&
+ bpf_adj_branches(prog, off, insn_delta, true))
+ return NULL;
+
+ /* Several new instructions need to be inserted. Make room
+ * for them. Likely, there's no need for a new allocation as
+ * last page could have large enough tailroom.
+ */
+ prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt),
+ GFP_USER);
+ if (!prog_adj)
+ return NULL;
+
+ prog_adj->len = insn_adj_cnt;
+
+ /* Patching happens in 3 steps:
+ *
+ * 1) Move over tail of insnsi from next instruction onwards,
+ * so we can patch the single target insn with one or more
+ * new ones (patching is always from 1 to n insns, n > 0).
+ * 2) Inject new instructions at the target location.
+ * 3) Adjust branch offsets if necessary.
+ */
+ insn_rest = insn_adj_cnt - off - len;
+
+ memmove(prog_adj->insnsi + off + len, prog_adj->insnsi + off + 1,
+ sizeof(*patch) * insn_rest);
+ memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len);
+
+ /* We are guaranteed to not fail at this point, otherwise
+ * the ship has sailed to reverse to the original state. An
+ * overflow cannot happen at this point.
+ */
+ BUG_ON(bpf_adj_branches(prog_adj, off, insn_delta, false));
+
+ return prog_adj;
+}
+
+void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
+{
+ int i;
+
+ for (i = 0; i < fp->aux->func_cnt; i++)
+ bpf_prog_kallsyms_del(fp->aux->func[i]);
+}
+
+void bpf_prog_kallsyms_del_all(struct bpf_prog *fp)
+{
+ bpf_prog_kallsyms_del_subprogs(fp);
+ bpf_prog_kallsyms_del(fp);
+}
+
+#ifdef CONFIG_BPF_JIT
+/* All BPF JIT sysctl knobs here. */
+int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
+int bpf_jit_harden __read_mostly;
+int bpf_jit_kallsyms __read_mostly;
+long bpf_jit_limit __read_mostly;
+long bpf_jit_limit_max __read_mostly;
+
+static __always_inline void
+bpf_get_prog_addr_region(const struct bpf_prog *prog,
+ unsigned long *symbol_start,
+ unsigned long *symbol_end)
+{
+ const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(prog);
+ unsigned long addr = (unsigned long)hdr;
+
+ WARN_ON_ONCE(!bpf_prog_ebpf_jited(prog));
+
+ *symbol_start = addr;
+ *symbol_end = addr + hdr->pages * PAGE_SIZE;
+}
+
+static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
+{
+ const char *end = sym + KSYM_NAME_LEN;
+
+ BUILD_BUG_ON(sizeof("bpf_prog_") +
+ sizeof(prog->tag) * 2 +
+ /* name has been null terminated.
+ * We should need +1 for the '_' preceding
+ * the name. However, the null character
+ * is double counted between the name and the
+ * sizeof("bpf_prog_") above, so we omit
+ * the +1 here.
+ */
+ sizeof(prog->aux->name) > KSYM_NAME_LEN);
+
+ sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_");
+ sym = bin2hex(sym, prog->tag, sizeof(prog->tag));
+ if (prog->aux->name[0])
+ snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name);
+ else
+ *sym = 0;
+}
+
+static __always_inline unsigned long
+bpf_get_prog_addr_start(struct latch_tree_node *n)
+{
+ unsigned long symbol_start, symbol_end;
+ const struct bpf_prog_aux *aux;
+
+ aux = container_of(n, struct bpf_prog_aux, ksym_tnode);
+ bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
+
+ return symbol_start;
+}
+
+static __always_inline bool bpf_tree_less(struct latch_tree_node *a,
+ struct latch_tree_node *b)
+{
+ return bpf_get_prog_addr_start(a) < bpf_get_prog_addr_start(b);
+}
+
+static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n)
+{
+ unsigned long val = (unsigned long)key;
+ unsigned long symbol_start, symbol_end;
+ const struct bpf_prog_aux *aux;
+
+ aux = container_of(n, struct bpf_prog_aux, ksym_tnode);
+ bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
+
+ if (val < symbol_start)
+ return -1;
+ if (val >= symbol_end)
+ return 1;
+
+ return 0;
+}
+
+static const struct latch_tree_ops bpf_tree_ops = {
+ .less = bpf_tree_less,
+ .comp = bpf_tree_comp,
+};
+
+static DEFINE_SPINLOCK(bpf_lock);
+static LIST_HEAD(bpf_kallsyms);
+static struct latch_tree_root bpf_tree __cacheline_aligned;
+
+static void bpf_prog_ksym_node_add(struct bpf_prog_aux *aux)
+{
+ WARN_ON_ONCE(!list_empty(&aux->ksym_lnode));
+ list_add_tail_rcu(&aux->ksym_lnode, &bpf_kallsyms);
+ latch_tree_insert(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops);
+}
+
+static void bpf_prog_ksym_node_del(struct bpf_prog_aux *aux)
+{
+ if (list_empty(&aux->ksym_lnode))
+ return;
+
+ latch_tree_erase(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops);
+ list_del_rcu(&aux->ksym_lnode);
+}
+
+static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp)
+{
+ return fp->jited && !bpf_prog_was_classic(fp);
+}
+
+static bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp)
+{
+ return list_empty(&fp->aux->ksym_lnode) ||
+ fp->aux->ksym_lnode.prev == LIST_POISON2;
+}
+
+void bpf_prog_kallsyms_add(struct bpf_prog *fp)
+{
+ if (!bpf_prog_kallsyms_candidate(fp) ||
+ !capable(CAP_SYS_ADMIN))
+ return;
+
+ spin_lock_bh(&bpf_lock);
+ bpf_prog_ksym_node_add(fp->aux);
+ spin_unlock_bh(&bpf_lock);
+}
+
+void bpf_prog_kallsyms_del(struct bpf_prog *fp)
+{
+ if (!bpf_prog_kallsyms_candidate(fp))
+ return;
+
+ spin_lock_bh(&bpf_lock);
+ bpf_prog_ksym_node_del(fp->aux);
+ spin_unlock_bh(&bpf_lock);
+}
+
+static struct bpf_prog *bpf_prog_kallsyms_find(unsigned long addr)
+{
+ struct latch_tree_node *n;
+
+ if (!bpf_jit_kallsyms_enabled())
+ return NULL;
+
+ n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops);
+ return n ?
+ container_of(n, struct bpf_prog_aux, ksym_tnode)->prog :
+ NULL;
+}
+
+const char *__bpf_address_lookup(unsigned long addr, unsigned long *size,
+ unsigned long *off, char *sym)
+{
+ unsigned long symbol_start, symbol_end;
+ struct bpf_prog *prog;
+ char *ret = NULL;
+
+ rcu_read_lock();
+ prog = bpf_prog_kallsyms_find(addr);
+ if (prog) {
+ bpf_get_prog_addr_region(prog, &symbol_start, &symbol_end);
+ bpf_get_prog_name(prog, sym);
+
+ ret = sym;
+ if (size)
+ *size = symbol_end - symbol_start;
+ if (off)
+ *off = addr - symbol_start;
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
+bool is_bpf_text_address(unsigned long addr)
+{
+ bool ret;
+
+ rcu_read_lock();
+ ret = bpf_prog_kallsyms_find(addr) != NULL;
+ rcu_read_unlock();
+
+ return ret;
+}
+
+int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+ char *sym)
+{
+ unsigned long symbol_start, symbol_end;
+ struct bpf_prog_aux *aux;
+ unsigned int it = 0;
+ int ret = -ERANGE;
+
+ if (!bpf_jit_kallsyms_enabled())
+ return ret;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(aux, &bpf_kallsyms, ksym_lnode) {
+ if (it++ != symnum)
+ continue;
+
+ bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
+ bpf_get_prog_name(aux->prog, sym);
+
+ *value = symbol_start;
+ *type = BPF_SYM_ELF_TYPE;
+
+ ret = 0;
+ break;
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
+static atomic_long_t bpf_jit_current;
+
+/* Can be overridden by an arch's JIT compiler if it has a custom,
+ * dedicated BPF backend memory area, or if neither of the two
+ * below apply.
+ */
+u64 __weak bpf_jit_alloc_exec_limit(void)
+{
+#if defined(MODULES_VADDR)
+ return MODULES_END - MODULES_VADDR;
+#else
+ return VMALLOC_END - VMALLOC_START;
+#endif
+}
+
+static int __init bpf_jit_charge_init(void)
+{
+ /* Only used as heuristic here to derive limit. */
+ bpf_jit_limit_max = bpf_jit_alloc_exec_limit();
+ bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 2,
+ PAGE_SIZE), LONG_MAX);
+ return 0;
+}
+pure_initcall(bpf_jit_charge_init);
+
+static int bpf_jit_charge_modmem(u32 pages)
+{
+ if (atomic_long_add_return(pages, &bpf_jit_current) >
+ (bpf_jit_limit >> PAGE_SHIFT)) {
+ if (!capable(CAP_SYS_ADMIN)) {
+ atomic_long_sub(pages, &bpf_jit_current);
+ return -EPERM;
+ }
+ }
+
+ return 0;
+}
+
+static void bpf_jit_uncharge_modmem(u32 pages)
+{
+ atomic_long_sub(pages, &bpf_jit_current);
+}
+
+struct bpf_binary_header *
+bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
+ unsigned int alignment,
+ bpf_jit_fill_hole_t bpf_fill_ill_insns)
+{
+ struct bpf_binary_header *hdr;
+ u32 size, hole, start, pages;
+
+ /* Most of BPF filters are really small, but if some of them
+ * fill a page, allow at least 128 extra bytes to insert a
+ * random section of illegal instructions.
+ */
+ size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE);
+ pages = size / PAGE_SIZE;
+
+ if (bpf_jit_charge_modmem(pages))
+ return NULL;
+ hdr = module_alloc(size);
+ if (!hdr) {
+ bpf_jit_uncharge_modmem(pages);
+ return NULL;
+ }
+
+ /* Fill space with illegal/arch-dep instructions. */
+ bpf_fill_ill_insns(hdr, size);
+
+ hdr->pages = pages;
+ hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
+ PAGE_SIZE - sizeof(*hdr));
+ start = (get_random_int() % hole) & ~(alignment - 1);
+
+ /* Leave a random number of instructions before BPF code. */
+ *image_ptr = &hdr->image[start];
+
+ return hdr;
+}
+
+void bpf_jit_binary_free(struct bpf_binary_header *hdr)
+{
+ u32 pages = hdr->pages;
+
+ module_memfree(hdr);
+ bpf_jit_uncharge_modmem(pages);
+}
+
+/* This symbol is only overridden by archs that have different
+ * requirements than the usual eBPF JITs, f.e. when they only
+ * implement cBPF JIT, do not set images read-only, etc.
+ */
+void __weak bpf_jit_free(struct bpf_prog *fp)
+{
+ if (fp->jited) {
+ struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
+
+ bpf_jit_binary_unlock_ro(hdr);
+ bpf_jit_binary_free(hdr);
+
+ WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp));
+ }
+
+ bpf_prog_unlock_free(fp);
+}
+
+static int bpf_jit_blind_insn(const struct bpf_insn *from,
+ const struct bpf_insn *aux,
+ struct bpf_insn *to_buff)
+{
+ struct bpf_insn *to = to_buff;
+ u32 imm_rnd = get_random_int();
+ s16 off;
+
+ BUILD_BUG_ON(BPF_REG_AX + 1 != MAX_BPF_JIT_REG);
+ BUILD_BUG_ON(MAX_BPF_REG + 1 != MAX_BPF_JIT_REG);
+
+ /* Constraints on AX register:
+ *
+ * AX register is inaccessible from user space. It is mapped in
+ * all JITs, and used here for constant blinding rewrites. It is
+ * typically "stateless" meaning its contents are only valid within
+ * the executed instruction, but not across several instructions.
+ * There are a few exceptions however which are further detailed
+ * below.
+ *
+ * Constant blinding is only used by JITs, not in the interpreter.
+ * In restricted circumstances, the verifier can also use the AX
+ * register for rewrites as long as they do not interfere with
+ * the above cases!
+ */
+ if (from->dst_reg == BPF_REG_AX || from->src_reg == BPF_REG_AX)
+ goto out;
+
+ if (from->imm == 0 &&
+ (from->code == (BPF_ALU | BPF_MOV | BPF_K) ||
+ from->code == (BPF_ALU64 | BPF_MOV | BPF_K))) {
+ *to++ = BPF_ALU64_REG(BPF_XOR, from->dst_reg, from->dst_reg);
+ goto out;
+ }
+
+ switch (from->code) {
+ case BPF_ALU | BPF_ADD | BPF_K:
+ case BPF_ALU | BPF_SUB | BPF_K:
+ case BPF_ALU | BPF_AND | BPF_K:
+ case BPF_ALU | BPF_OR | BPF_K:
+ case BPF_ALU | BPF_XOR | BPF_K:
+ case BPF_ALU | BPF_MUL | BPF_K:
+ case BPF_ALU | BPF_MOV | BPF_K:
+ case BPF_ALU | BPF_DIV | BPF_K:
+ case BPF_ALU | BPF_MOD | BPF_K:
+ *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
+ *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+ *to++ = BPF_ALU32_REG(from->code, from->dst_reg, BPF_REG_AX);
+ break;
+
+ case BPF_ALU64 | BPF_ADD | BPF_K:
+ case BPF_ALU64 | BPF_SUB | BPF_K:
+ case BPF_ALU64 | BPF_AND | BPF_K:
+ case BPF_ALU64 | BPF_OR | BPF_K:
+ case BPF_ALU64 | BPF_XOR | BPF_K:
+ case BPF_ALU64 | BPF_MUL | BPF_K:
+ case BPF_ALU64 | BPF_MOV | BPF_K:
+ case BPF_ALU64 | BPF_DIV | BPF_K:
+ case BPF_ALU64 | BPF_MOD | BPF_K:
+ *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
+ *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+ *to++ = BPF_ALU64_REG(from->code, from->dst_reg, BPF_REG_AX);
+ break;
+
+ case BPF_JMP | BPF_JEQ | BPF_K:
+ case BPF_JMP | BPF_JNE | BPF_K:
+ case BPF_JMP | BPF_JGT | BPF_K:
+ case BPF_JMP | BPF_JLT | BPF_K:
+ case BPF_JMP | BPF_JGE | BPF_K:
+ case BPF_JMP | BPF_JLE | BPF_K:
+ case BPF_JMP | BPF_JSGT | BPF_K:
+ case BPF_JMP | BPF_JSLT | BPF_K:
+ case BPF_JMP | BPF_JSGE | BPF_K:
+ case BPF_JMP | BPF_JSLE | BPF_K:
+ case BPF_JMP | BPF_JSET | BPF_K:
+ /* Accommodate for extra offset in case of a backjump. */
+ off = from->off;
+ if (off < 0)
+ off -= 2;
+ *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
+ *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+ *to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off);
+ break;
+
+ case BPF_LD | BPF_IMM | BPF_DW:
+ *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm);
+ *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+ *to++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32);
+ *to++ = BPF_ALU64_REG(BPF_MOV, aux[0].dst_reg, BPF_REG_AX);
+ break;
+ case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */
+ *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm);
+ *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+ *to++ = BPF_ALU64_REG(BPF_OR, aux[0].dst_reg, BPF_REG_AX);
+ break;
+
+ case BPF_ST | BPF_MEM | BPF_DW:
+ case BPF_ST | BPF_MEM | BPF_W:
+ case BPF_ST | BPF_MEM | BPF_H:
+ case BPF_ST | BPF_MEM | BPF_B:
+ *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm);
+ *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+ *to++ = BPF_STX_MEM(from->code, from->dst_reg, BPF_REG_AX, from->off);
+ break;
+ }
+out:
+ return to - to_buff;
+}
+
+static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other,
+ gfp_t gfp_extra_flags)
+{
+ gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;
+ struct bpf_prog *fp;
+
+ fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags, PAGE_KERNEL);
+ if (fp != NULL) {
+ /* aux->prog still points to the fp_other one, so
+ * when promoting the clone to the real program,
+ * this still needs to be adapted.
+ */
+ memcpy(fp, fp_other, fp_other->pages * PAGE_SIZE);
+ }
+
+ return fp;
+}
+
+static void bpf_prog_clone_free(struct bpf_prog *fp)
+{
+ /* aux was stolen by the other clone, so we cannot free
+ * it from this path! It will be freed eventually by the
+ * other program on release.
+ *
+ * At this point, we don't need a deferred release since
+ * clone is guaranteed to not be locked.
+ */
+ fp->aux = NULL;
+ __bpf_prog_free(fp);
+}
+
+void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other)
+{
+ /* We have to repoint aux->prog to self, as we don't
+ * know whether fp here is the clone or the original.
+ */
+ fp->aux->prog = fp;
+ bpf_prog_clone_free(fp_other);
+}
+
+struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog)
+{
+ struct bpf_insn insn_buff[16], aux[2];
+ struct bpf_prog *clone, *tmp;
+ int insn_delta, insn_cnt;
+ struct bpf_insn *insn;
+ int i, rewritten;
+
+ if (!bpf_jit_blinding_enabled(prog) || prog->blinded)
+ return prog;
+
+ clone = bpf_prog_clone_create(prog, GFP_USER);
+ if (!clone)
+ return ERR_PTR(-ENOMEM);
+
+ insn_cnt = clone->len;
+ insn = clone->insnsi;
+
+ for (i = 0; i < insn_cnt; i++, insn++) {
+ /* We temporarily need to hold the original ld64 insn
+ * so that we can still access the first part in the
+ * second blinding run.
+ */
+ if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW) &&
+ insn[1].code == 0)
+ memcpy(aux, insn, sizeof(aux));
+
+ rewritten = bpf_jit_blind_insn(insn, aux, insn_buff);
+ if (!rewritten)
+ continue;
+
+ tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten);
+ if (!tmp) {
+ /* Patching may have repointed aux->prog during
+ * realloc from the original one, so we need to
+ * fix it up here on error.
+ */
+ bpf_jit_prog_release_other(prog, clone);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ clone = tmp;
+ insn_delta = rewritten - 1;
+
+ /* Walk new program and skip insns we just inserted. */
+ insn = clone->insnsi + i + insn_delta;
+ insn_cnt += insn_delta;
+ i += insn_delta;
+ }
+
+ clone->blinded = 1;
+ return clone;
+}
+#endif /* CONFIG_BPF_JIT */
+
+/* Base function for offset calculation. Needs to go into .text section,
+ * therefore keeping it non-static as well; will also be used by JITs
+ * anyway later on, so do not let the compiler omit it. This also needs
+ * to go into kallsyms for correlation from e.g. bpftool, so naming
+ * must not change.
+ */
+noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ return 0;
+}
+EXPORT_SYMBOL_GPL(__bpf_call_base);
+
+/* All UAPI available opcodes. */
+#define BPF_INSN_MAP(INSN_2, INSN_3) \
+ /* 32 bit ALU operations. */ \
+ /* Register based. */ \
+ INSN_3(ALU, ADD, X), \
+ INSN_3(ALU, SUB, X), \
+ INSN_3(ALU, AND, X), \
+ INSN_3(ALU, OR, X), \
+ INSN_3(ALU, LSH, X), \
+ INSN_3(ALU, RSH, X), \
+ INSN_3(ALU, XOR, X), \
+ INSN_3(ALU, MUL, X), \
+ INSN_3(ALU, MOV, X), \
+ INSN_3(ALU, DIV, X), \
+ INSN_3(ALU, MOD, X), \
+ INSN_2(ALU, NEG), \
+ INSN_3(ALU, END, TO_BE), \
+ INSN_3(ALU, END, TO_LE), \
+ /* Immediate based. */ \
+ INSN_3(ALU, ADD, K), \
+ INSN_3(ALU, SUB, K), \
+ INSN_3(ALU, AND, K), \
+ INSN_3(ALU, OR, K), \
+ INSN_3(ALU, LSH, K), \
+ INSN_3(ALU, RSH, K), \
+ INSN_3(ALU, XOR, K), \
+ INSN_3(ALU, MUL, K), \
+ INSN_3(ALU, MOV, K), \
+ INSN_3(ALU, DIV, K), \
+ INSN_3(ALU, MOD, K), \
+ /* 64 bit ALU operations. */ \
+ /* Register based. */ \
+ INSN_3(ALU64, ADD, X), \
+ INSN_3(ALU64, SUB, X), \
+ INSN_3(ALU64, AND, X), \
+ INSN_3(ALU64, OR, X), \
+ INSN_3(ALU64, LSH, X), \
+ INSN_3(ALU64, RSH, X), \
+ INSN_3(ALU64, XOR, X), \
+ INSN_3(ALU64, MUL, X), \
+ INSN_3(ALU64, MOV, X), \
+ INSN_3(ALU64, ARSH, X), \
+ INSN_3(ALU64, DIV, X), \
+ INSN_3(ALU64, MOD, X), \
+ INSN_2(ALU64, NEG), \
+ /* Immediate based. */ \
+ INSN_3(ALU64, ADD, K), \
+ INSN_3(ALU64, SUB, K), \
+ INSN_3(ALU64, AND, K), \
+ INSN_3(ALU64, OR, K), \
+ INSN_3(ALU64, LSH, K), \
+ INSN_3(ALU64, RSH, K), \
+ INSN_3(ALU64, XOR, K), \
+ INSN_3(ALU64, MUL, K), \
+ INSN_3(ALU64, MOV, K), \
+ INSN_3(ALU64, ARSH, K), \
+ INSN_3(ALU64, DIV, K), \
+ INSN_3(ALU64, MOD, K), \
+ /* Call instruction. */ \
+ INSN_2(JMP, CALL), \
+ /* Exit instruction. */ \
+ INSN_2(JMP, EXIT), \
+ /* Jump instructions. */ \
+ /* Register based. */ \
+ INSN_3(JMP, JEQ, X), \
+ INSN_3(JMP, JNE, X), \
+ INSN_3(JMP, JGT, X), \
+ INSN_3(JMP, JLT, X), \
+ INSN_3(JMP, JGE, X), \
+ INSN_3(JMP, JLE, X), \
+ INSN_3(JMP, JSGT, X), \
+ INSN_3(JMP, JSLT, X), \
+ INSN_3(JMP, JSGE, X), \
+ INSN_3(JMP, JSLE, X), \
+ INSN_3(JMP, JSET, X), \
+ /* Immediate based. */ \
+ INSN_3(JMP, JEQ, K), \
+ INSN_3(JMP, JNE, K), \
+ INSN_3(JMP, JGT, K), \
+ INSN_3(JMP, JLT, K), \
+ INSN_3(JMP, JGE, K), \
+ INSN_3(JMP, JLE, K), \
+ INSN_3(JMP, JSGT, K), \
+ INSN_3(JMP, JSLT, K), \
+ INSN_3(JMP, JSGE, K), \
+ INSN_3(JMP, JSLE, K), \
+ INSN_3(JMP, JSET, K), \
+ INSN_2(JMP, JA), \
+ /* Store instructions. */ \
+ /* Register based. */ \
+ INSN_3(STX, MEM, B), \
+ INSN_3(STX, MEM, H), \
+ INSN_3(STX, MEM, W), \
+ INSN_3(STX, MEM, DW), \
+ INSN_3(STX, XADD, W), \
+ INSN_3(STX, XADD, DW), \
+ /* Immediate based. */ \
+ INSN_3(ST, MEM, B), \
+ INSN_3(ST, MEM, H), \
+ INSN_3(ST, MEM, W), \
+ INSN_3(ST, MEM, DW), \
+ /* Load instructions. */ \
+ /* Register based. */ \
+ INSN_3(LDX, MEM, B), \
+ INSN_3(LDX, MEM, H), \
+ INSN_3(LDX, MEM, W), \
+ INSN_3(LDX, MEM, DW), \
+ /* Immediate based. */ \
+ INSN_3(LD, IMM, DW)
+
+bool bpf_opcode_in_insntable(u8 code)
+{
+#define BPF_INSN_2_TBL(x, y) [BPF_##x | BPF_##y] = true
+#define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true
+ static const bool public_insntable[256] = {
+ [0 ... 255] = false,
+ /* Now overwrite non-defaults ... */
+ BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
+ /* UAPI exposed, but rewritten opcodes. cBPF carry-over. */
+ [BPF_LD | BPF_ABS | BPF_B] = true,
+ [BPF_LD | BPF_ABS | BPF_H] = true,
+ [BPF_LD | BPF_ABS | BPF_W] = true,
+ [BPF_LD | BPF_IND | BPF_B] = true,
+ [BPF_LD | BPF_IND | BPF_H] = true,
+ [BPF_LD | BPF_IND | BPF_W] = true,
+ };
+#undef BPF_INSN_3_TBL
+#undef BPF_INSN_2_TBL
+ return public_insntable[code];
+}
+
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+/**
+ * __bpf_prog_run - run eBPF program on a given context
+ * @ctx: is the data we are operating on
+ * @insn: is the array of eBPF instructions
+ *
+ * Decode and execute eBPF instructions.
+ */
+static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
+{
+#define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y
+#define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z
+ static const void *jumptable[256] = {
+ [0 ... 255] = &&default_label,
+ /* Now overwrite non-defaults ... */
+ BPF_INSN_MAP(BPF_INSN_2_LBL, BPF_INSN_3_LBL),
+ /* Non-UAPI available opcodes. */
+ [BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS,
+ [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL,
+ [BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC,
+ };
+#undef BPF_INSN_3_LBL
+#undef BPF_INSN_2_LBL
+ u32 tail_call_cnt = 0;
+ u64 tmp;
+
+#define CONT ({ insn++; goto select_insn; })
+#define CONT_JMP ({ insn++; goto select_insn; })
+
+select_insn:
+ goto *jumptable[insn->code];
+
+ /* ALU */
+#define ALU(OPCODE, OP) \
+ ALU64_##OPCODE##_X: \
+ DST = DST OP SRC; \
+ CONT; \
+ ALU_##OPCODE##_X: \
+ DST = (u32) DST OP (u32) SRC; \
+ CONT; \
+ ALU64_##OPCODE##_K: \
+ DST = DST OP IMM; \
+ CONT; \
+ ALU_##OPCODE##_K: \
+ DST = (u32) DST OP (u32) IMM; \
+ CONT;
+
+ ALU(ADD, +)
+ ALU(SUB, -)
+ ALU(AND, &)
+ ALU(OR, |)
+ ALU(LSH, <<)
+ ALU(RSH, >>)
+ ALU(XOR, ^)
+ ALU(MUL, *)
+#undef ALU
+ ALU_NEG:
+ DST = (u32) -DST;
+ CONT;
+ ALU64_NEG:
+ DST = -DST;
+ CONT;
+ ALU_MOV_X:
+ DST = (u32) SRC;
+ CONT;
+ ALU_MOV_K:
+ DST = (u32) IMM;
+ CONT;
+ ALU64_MOV_X:
+ DST = SRC;
+ CONT;
+ ALU64_MOV_K:
+ DST = IMM;
+ CONT;
+ LD_IMM_DW:
+ DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32;
+ insn++;
+ CONT;
+ ALU64_ARSH_X:
+ (*(s64 *) &DST) >>= SRC;
+ CONT;
+ ALU64_ARSH_K:
+ (*(s64 *) &DST) >>= IMM;
+ CONT;
+ ALU64_MOD_X:
+ div64_u64_rem(DST, SRC, &tmp);
+ DST = tmp;
+ CONT;
+ ALU_MOD_X:
+ tmp = (u32) DST;
+ DST = do_div(tmp, (u32) SRC);
+ CONT;
+ ALU64_MOD_K:
+ div64_u64_rem(DST, IMM, &tmp);
+ DST = tmp;
+ CONT;
+ ALU_MOD_K:
+ tmp = (u32) DST;
+ DST = do_div(tmp, (u32) IMM);
+ CONT;
+ ALU64_DIV_X:
+ DST = div64_u64(DST, SRC);
+ CONT;
+ ALU_DIV_X:
+ tmp = (u32) DST;
+ do_div(tmp, (u32) SRC);
+ DST = (u32) tmp;
+ CONT;
+ ALU64_DIV_K:
+ DST = div64_u64(DST, IMM);
+ CONT;
+ ALU_DIV_K:
+ tmp = (u32) DST;
+ do_div(tmp, (u32) IMM);
+ DST = (u32) tmp;
+ CONT;
+ ALU_END_TO_BE:
+ switch (IMM) {
+ case 16:
+ DST = (__force u16) cpu_to_be16(DST);
+ break;
+ case 32:
+ DST = (__force u32) cpu_to_be32(DST);
+ break;
+ case 64:
+ DST = (__force u64) cpu_to_be64(DST);
+ break;
+ }
+ CONT;
+ ALU_END_TO_LE:
+ switch (IMM) {
+ case 16:
+ DST = (__force u16) cpu_to_le16(DST);
+ break;
+ case 32:
+ DST = (__force u32) cpu_to_le32(DST);
+ break;
+ case 64:
+ DST = (__force u64) cpu_to_le64(DST);
+ break;
+ }
+ CONT;
+
+ /* CALL */
+ JMP_CALL:
+ /* Function call scratches BPF_R1-BPF_R5 registers,
+ * preserves BPF_R6-BPF_R9, and stores return value
+ * into BPF_R0.
+ */
+ BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3,
+ BPF_R4, BPF_R5);
+ CONT;
+
+ JMP_CALL_ARGS:
+ BPF_R0 = (__bpf_call_base_args + insn->imm)(BPF_R1, BPF_R2,
+ BPF_R3, BPF_R4,
+ BPF_R5,
+ insn + insn->off + 1);
+ CONT;
+
+ JMP_TAIL_CALL: {
+ struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2;
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+ struct bpf_prog *prog;
+ u32 index = BPF_R3;
+
+ if (unlikely(index >= array->map.max_entries))
+ goto out;
+ if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT))
+ goto out;
+
+ tail_call_cnt++;
+
+ prog = READ_ONCE(array->ptrs[index]);
+ if (!prog)
+ goto out;
+
+ /* ARG1 at this point is guaranteed to point to CTX from
+ * the verifier side due to the fact that the tail call is
+ * handeled like a helper, that is, bpf_tail_call_proto,
+ * where arg1_type is ARG_PTR_TO_CTX.
+ */
+ insn = prog->insnsi;
+ goto select_insn;
+out:
+ CONT;
+ }
+ /* JMP */
+ JMP_JA:
+ insn += insn->off;
+ CONT;
+ JMP_JEQ_X:
+ if (DST == SRC) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JEQ_K:
+ if (DST == IMM) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JNE_X:
+ if (DST != SRC) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JNE_K:
+ if (DST != IMM) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JGT_X:
+ if (DST > SRC) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JGT_K:
+ if (DST > IMM) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JLT_X:
+ if (DST < SRC) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JLT_K:
+ if (DST < IMM) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JGE_X:
+ if (DST >= SRC) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JGE_K:
+ if (DST >= IMM) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JLE_X:
+ if (DST <= SRC) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JLE_K:
+ if (DST <= IMM) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JSGT_X:
+ if (((s64) DST) > ((s64) SRC)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JSGT_K:
+ if (((s64) DST) > ((s64) IMM)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JSLT_X:
+ if (((s64) DST) < ((s64) SRC)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JSLT_K:
+ if (((s64) DST) < ((s64) IMM)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JSGE_X:
+ if (((s64) DST) >= ((s64) SRC)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JSGE_K:
+ if (((s64) DST) >= ((s64) IMM)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JSLE_X:
+ if (((s64) DST) <= ((s64) SRC)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JSLE_K:
+ if (((s64) DST) <= ((s64) IMM)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JSET_X:
+ if (DST & SRC) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_JSET_K:
+ if (DST & IMM) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ JMP_EXIT:
+ return BPF_R0;
+
+ /* ST, STX and LDX*/
+ ST_NOSPEC:
+ /* Speculation barrier for mitigating Speculative Store Bypass.
+ * In case of arm64, we rely on the firmware mitigation as
+ * controlled via the ssbd kernel parameter. Whenever the
+ * mitigation is enabled, it works for all of the kernel code
+ * with no need to provide any additional instructions here.
+ * In case of x86, we use 'lfence' insn for mitigation. We
+ * reuse preexisting logic from Spectre v1 mitigation that
+ * happens to produce the required code on x86 for v4 as well.
+ */
+#ifdef CONFIG_X86
+ barrier_nospec();
+#endif
+ CONT;
+#define LDST(SIZEOP, SIZE) \
+ STX_MEM_##SIZEOP: \
+ *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \
+ CONT; \
+ ST_MEM_##SIZEOP: \
+ *(SIZE *)(unsigned long) (DST + insn->off) = IMM; \
+ CONT; \
+ LDX_MEM_##SIZEOP: \
+ DST = *(SIZE *)(unsigned long) (SRC + insn->off); \
+ CONT;
+
+ LDST(B, u8)
+ LDST(H, u16)
+ LDST(W, u32)
+ LDST(DW, u64)
+#undef LDST
+ STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */
+ atomic_add((u32) SRC, (atomic_t *)(unsigned long)
+ (DST + insn->off));
+ CONT;
+ STX_XADD_DW: /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */
+ atomic64_add((u64) SRC, (atomic64_t *)(unsigned long)
+ (DST + insn->off));
+ CONT;
+
+ default_label:
+ /* If we ever reach this, we have a bug somewhere. Die hard here
+ * instead of just returning 0; we could be somewhere in a subprog,
+ * so execution could continue otherwise which we do /not/ want.
+ *
+ * Note, verifier whitelists all opcodes in bpf_opcode_in_insntable().
+ */
+ pr_warn("BPF interpreter: unknown opcode %02x\n", insn->code);
+ BUG_ON(1);
+ return 0;
+}
+STACK_FRAME_NON_STANDARD(___bpf_prog_run); /* jump table */
+
+#define PROG_NAME(stack_size) __bpf_prog_run##stack_size
+#define DEFINE_BPF_PROG_RUN(stack_size) \
+static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \
+{ \
+ u64 stack[stack_size / sizeof(u64)]; \
+ u64 regs[MAX_BPF_EXT_REG]; \
+\
+ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
+ ARG1 = (u64) (unsigned long) ctx; \
+ return ___bpf_prog_run(regs, insn, stack); \
+}
+
+#define PROG_NAME_ARGS(stack_size) __bpf_prog_run_args##stack_size
+#define DEFINE_BPF_PROG_RUN_ARGS(stack_size) \
+static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \
+ const struct bpf_insn *insn) \
+{ \
+ u64 stack[stack_size / sizeof(u64)]; \
+ u64 regs[MAX_BPF_EXT_REG]; \
+\
+ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
+ BPF_R1 = r1; \
+ BPF_R2 = r2; \
+ BPF_R3 = r3; \
+ BPF_R4 = r4; \
+ BPF_R5 = r5; \
+ return ___bpf_prog_run(regs, insn, stack); \
+}
+
+#define EVAL1(FN, X) FN(X)
+#define EVAL2(FN, X, Y...) FN(X) EVAL1(FN, Y)
+#define EVAL3(FN, X, Y...) FN(X) EVAL2(FN, Y)
+#define EVAL4(FN, X, Y...) FN(X) EVAL3(FN, Y)
+#define EVAL5(FN, X, Y...) FN(X) EVAL4(FN, Y)
+#define EVAL6(FN, X, Y...) FN(X) EVAL5(FN, Y)
+
+EVAL6(DEFINE_BPF_PROG_RUN, 32, 64, 96, 128, 160, 192);
+EVAL6(DEFINE_BPF_PROG_RUN, 224, 256, 288, 320, 352, 384);
+EVAL4(DEFINE_BPF_PROG_RUN, 416, 448, 480, 512);
+
+EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 32, 64, 96, 128, 160, 192);
+EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 224, 256, 288, 320, 352, 384);
+EVAL4(DEFINE_BPF_PROG_RUN_ARGS, 416, 448, 480, 512);
+
+#define PROG_NAME_LIST(stack_size) PROG_NAME(stack_size),
+
+static unsigned int (*interpreters[])(const void *ctx,
+ const struct bpf_insn *insn) = {
+EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192)
+EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384)
+EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
+};
+#undef PROG_NAME_LIST
+#define PROG_NAME_LIST(stack_size) PROG_NAME_ARGS(stack_size),
+static u64 (*interpreters_args[])(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5,
+ const struct bpf_insn *insn) = {
+EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192)
+EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384)
+EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
+};
+#undef PROG_NAME_LIST
+
+void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth)
+{
+ stack_depth = max_t(u32, stack_depth, 1);
+ insn->off = (s16) insn->imm;
+ insn->imm = interpreters_args[(round_up(stack_depth, 32) / 32) - 1] -
+ __bpf_call_base_args;
+ insn->code = BPF_JMP | BPF_CALL_ARGS;
+}
+
+#else
+static unsigned int __bpf_prog_ret0_warn(const void *ctx,
+ const struct bpf_insn *insn)
+{
+ /* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON
+ * is not working properly, so warn about it!
+ */
+ WARN_ON_ONCE(1);
+ return 0;
+}
+#endif
+
+bool bpf_prog_array_compatible(struct bpf_array *array,
+ const struct bpf_prog *fp)
+{
+ if (fp->kprobe_override)
+ return false;
+
+ if (!array->owner_prog_type) {
+ /* There's no owner yet where we could check for
+ * compatibility.
+ */
+ array->owner_prog_type = fp->type;
+ array->owner_jited = fp->jited;
+
+ return true;
+ }
+
+ return array->owner_prog_type == fp->type &&
+ array->owner_jited == fp->jited;
+}
+
+static int bpf_check_tail_call(const struct bpf_prog *fp)
+{
+ struct bpf_prog_aux *aux = fp->aux;
+ int i;
+
+ for (i = 0; i < aux->used_map_cnt; i++) {
+ struct bpf_map *map = aux->used_maps[i];
+ struct bpf_array *array;
+
+ if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
+ continue;
+
+ array = container_of(map, struct bpf_array, map);
+ if (!bpf_prog_array_compatible(array, fp))
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void bpf_prog_select_func(struct bpf_prog *fp)
+{
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+ u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+
+ fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
+#else
+ fp->bpf_func = __bpf_prog_ret0_warn;
+#endif
+}
+
+/**
+ * bpf_prog_select_runtime - select exec runtime for BPF program
+ * @fp: bpf_prog populated with internal BPF program
+ * @err: pointer to error variable
+ *
+ * Try to JIT eBPF program, if JIT is not available, use interpreter.
+ * The BPF program will be executed via BPF_PROG_RUN() macro.
+ */
+struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
+{
+ /* In case of BPF to BPF calls, verifier did all the prep
+ * work with regards to JITing, etc.
+ */
+ if (fp->bpf_func)
+ goto finalize;
+
+ bpf_prog_select_func(fp);
+
+ /* eBPF JITs can rewrite the program in case constant
+ * blinding is active. However, in case of error during
+ * blinding, bpf_int_jit_compile() must always return a
+ * valid program, which in this case would simply not
+ * be JITed, but falls back to the interpreter.
+ */
+ if (!bpf_prog_is_dev_bound(fp->aux)) {
+ fp = bpf_int_jit_compile(fp);
+#ifdef CONFIG_BPF_JIT_ALWAYS_ON
+ if (!fp->jited) {
+ *err = -ENOTSUPP;
+ return fp;
+ }
+#endif
+ } else {
+ *err = bpf_prog_offload_compile(fp);
+ if (*err)
+ return fp;
+ }
+
+finalize:
+ bpf_prog_lock_ro(fp);
+
+ /* The tail call compatibility check can only be done at
+ * this late stage as we need to determine, if we deal
+ * with JITed or non JITed program concatenations and not
+ * all eBPF JITs might immediately support all features.
+ */
+ *err = bpf_check_tail_call(fp);
+
+ return fp;
+}
+EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
+
+static unsigned int __bpf_prog_ret1(const void *ctx,
+ const struct bpf_insn *insn)
+{
+ return 1;
+}
+
+static struct bpf_prog_dummy {
+ struct bpf_prog prog;
+} dummy_bpf_prog = {
+ .prog = {
+ .bpf_func = __bpf_prog_ret1,
+ },
+};
+
+/* to avoid allocating empty bpf_prog_array for cgroups that
+ * don't have bpf program attached use one global 'empty_prog_array'
+ * It will not be modified the caller of bpf_prog_array_alloc()
+ * (since caller requested prog_cnt == 0)
+ * that pointer should be 'freed' by bpf_prog_array_free()
+ */
+static struct {
+ struct bpf_prog_array hdr;
+ struct bpf_prog *null_prog;
+} empty_prog_array = {
+ .null_prog = NULL,
+};
+
+struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
+{
+ if (prog_cnt)
+ return kzalloc(sizeof(struct bpf_prog_array) +
+ sizeof(struct bpf_prog_array_item) *
+ (prog_cnt + 1),
+ flags);
+
+ return &empty_prog_array.hdr;
+}
+
+void bpf_prog_array_free(struct bpf_prog_array __rcu *progs)
+{
+ if (!progs ||
+ progs == (struct bpf_prog_array __rcu *)&empty_prog_array.hdr)
+ return;
+ kfree_rcu(progs, rcu);
+}
+
+int bpf_prog_array_length(struct bpf_prog_array __rcu *array)
+{
+ struct bpf_prog_array_item *item;
+ u32 cnt = 0;
+
+ rcu_read_lock();
+ item = rcu_dereference(array)->items;
+ for (; item->prog; item++)
+ if (item->prog != &dummy_bpf_prog.prog)
+ cnt++;
+ rcu_read_unlock();
+ return cnt;
+}
+
+
+static bool bpf_prog_array_copy_core(struct bpf_prog_array __rcu *array,
+ u32 *prog_ids,
+ u32 request_cnt)
+{
+ struct bpf_prog_array_item *item;
+ int i = 0;
+
+ item = rcu_dereference_check(array, 1)->items;
+ for (; item->prog; item++) {
+ if (item->prog == &dummy_bpf_prog.prog)
+ continue;
+ prog_ids[i] = item->prog->aux->id;
+ if (++i == request_cnt) {
+ item++;
+ break;
+ }
+ }
+
+ return !!(item->prog);
+}
+
+int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *array,
+ __u32 __user *prog_ids, u32 cnt)
+{
+ unsigned long err = 0;
+ bool nospc;
+ u32 *ids;
+
+ /* users of this function are doing:
+ * cnt = bpf_prog_array_length();
+ * if (cnt > 0)
+ * bpf_prog_array_copy_to_user(..., cnt);
+ * so below kcalloc doesn't need extra cnt > 0 check, but
+ * bpf_prog_array_length() releases rcu lock and
+ * prog array could have been swapped with empty or larger array,
+ * so always copy 'cnt' prog_ids to the user.
+ * In a rare race the user will see zero prog_ids
+ */
+ ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN);
+ if (!ids)
+ return -ENOMEM;
+ rcu_read_lock();
+ nospc = bpf_prog_array_copy_core(array, ids, cnt);
+ rcu_read_unlock();
+ err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
+ kfree(ids);
+ if (err)
+ return -EFAULT;
+ if (nospc)
+ return -ENOSPC;
+ return 0;
+}
+
+void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *array,
+ struct bpf_prog *old_prog)
+{
+ struct bpf_prog_array_item *item = array->items;
+
+ for (; item->prog; item++)
+ if (item->prog == old_prog) {
+ WRITE_ONCE(item->prog, &dummy_bpf_prog.prog);
+ break;
+ }
+}
+
+int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
+ struct bpf_prog *exclude_prog,
+ struct bpf_prog *include_prog,
+ struct bpf_prog_array **new_array)
+{
+ int new_prog_cnt, carry_prog_cnt = 0;
+ struct bpf_prog_array_item *existing;
+ struct bpf_prog_array *array;
+ bool found_exclude = false;
+ int new_prog_idx = 0;
+
+ /* Figure out how many existing progs we need to carry over to
+ * the new array.
+ */
+ if (old_array) {
+ existing = old_array->items;
+ for (; existing->prog; existing++) {
+ if (existing->prog == exclude_prog) {
+ found_exclude = true;
+ continue;
+ }
+ if (existing->prog != &dummy_bpf_prog.prog)
+ carry_prog_cnt++;
+ if (existing->prog == include_prog)
+ return -EEXIST;
+ }
+ }
+
+ if (exclude_prog && !found_exclude)
+ return -ENOENT;
+
+ /* How many progs (not NULL) will be in the new array? */
+ new_prog_cnt = carry_prog_cnt;
+ if (include_prog)
+ new_prog_cnt += 1;
+
+ /* Do we have any prog (not NULL) in the new array? */
+ if (!new_prog_cnt) {
+ *new_array = NULL;
+ return 0;
+ }
+
+ /* +1 as the end of prog_array is marked with NULL */
+ array = bpf_prog_array_alloc(new_prog_cnt + 1, GFP_KERNEL);
+ if (!array)
+ return -ENOMEM;
+
+ /* Fill in the new prog array */
+ if (carry_prog_cnt) {
+ existing = old_array->items;
+ for (; existing->prog; existing++)
+ if (existing->prog != exclude_prog &&
+ existing->prog != &dummy_bpf_prog.prog) {
+ array->items[new_prog_idx++].prog =
+ existing->prog;
+ }
+ }
+ if (include_prog)
+ array->items[new_prog_idx++].prog = include_prog;
+ array->items[new_prog_idx].prog = NULL;
+ *new_array = array;
+ return 0;
+}
+
+int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
+ u32 *prog_ids, u32 request_cnt,
+ u32 *prog_cnt)
+{
+ u32 cnt = 0;
+
+ if (array)
+ cnt = bpf_prog_array_length(array);
+
+ *prog_cnt = cnt;
+
+ /* return early if user requested only program count or nothing to copy */
+ if (!request_cnt || !cnt)
+ return 0;
+
+ /* this function is called under trace/bpf_trace.c: bpf_event_mutex */
+ return bpf_prog_array_copy_core(array, prog_ids, request_cnt) ? -ENOSPC
+ : 0;
+}
+
+static void bpf_prog_free_deferred(struct work_struct *work)
+{
+ struct bpf_prog_aux *aux;
+ int i;
+
+ aux = container_of(work, struct bpf_prog_aux, work);
+ if (bpf_prog_is_dev_bound(aux))
+ bpf_prog_offload_destroy(aux->prog);
+#ifdef CONFIG_PERF_EVENTS
+ if (aux->prog->has_callchain_buf)
+ put_callchain_buffers();
+#endif
+ for (i = 0; i < aux->func_cnt; i++)
+ bpf_jit_free(aux->func[i]);
+ if (aux->func_cnt) {
+ kfree(aux->func);
+ bpf_prog_unlock_free(aux->prog);
+ } else {
+ bpf_jit_free(aux->prog);
+ }
+}
+
+/* Free internal BPF program */
+void bpf_prog_free(struct bpf_prog *fp)
+{
+ struct bpf_prog_aux *aux = fp->aux;
+
+ INIT_WORK(&aux->work, bpf_prog_free_deferred);
+ schedule_work(&aux->work);
+}
+EXPORT_SYMBOL_GPL(bpf_prog_free);
+
+/* RNG for unpriviledged user space with separated state from prandom_u32(). */
+static DEFINE_PER_CPU(struct rnd_state, bpf_user_rnd_state);
+
+void bpf_user_rnd_init_once(void)
+{
+ prandom_init_once(&bpf_user_rnd_state);
+}
+
+BPF_CALL_0(bpf_user_rnd_u32)
+{
+ /* Should someone ever have the rather unwise idea to use some
+ * of the registers passed into this function, then note that
+ * this function is called from native eBPF and classic-to-eBPF
+ * transformations. Register assignments from both sides are
+ * different, f.e. classic always sets fn(ctx, A, X) here.
+ */
+ struct rnd_state *state;
+ u32 res;
+
+ state = &get_cpu_var(bpf_user_rnd_state);
+ res = prandom_u32_state(state);
+ put_cpu_var(bpf_user_rnd_state);
+
+ return res;
+}
+
+/* Weak definitions of helper functions in case we don't have bpf syscall. */
+const struct bpf_func_proto bpf_map_lookup_elem_proto __weak;
+const struct bpf_func_proto bpf_map_update_elem_proto __weak;
+const struct bpf_func_proto bpf_map_delete_elem_proto __weak;
+
+const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
+const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
+const struct bpf_func_proto bpf_get_numa_node_id_proto __weak;
+const struct bpf_func_proto bpf_ktime_get_ns_proto __weak;
+
+const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
+const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
+const struct bpf_func_proto bpf_get_current_comm_proto __weak;
+const struct bpf_func_proto bpf_sock_map_update_proto __weak;
+const struct bpf_func_proto bpf_sock_hash_update_proto __weak;
+const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
+const struct bpf_func_proto bpf_get_local_storage_proto __weak;
+
+const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
+{
+ return NULL;
+}
+
+u64 __weak
+bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
+ void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy)
+{
+ return -ENOTSUPP;
+}
+EXPORT_SYMBOL_GPL(bpf_event_output);
+
+/* Always built-in helper functions. */
+const struct bpf_func_proto bpf_tail_call_proto = {
+ .func = NULL,
+ .gpl_only = false,
+ .ret_type = RET_VOID,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_ANYTHING,
+};
+
+/* Stub for JITs that only support cBPF. eBPF programs are interpreted.
+ * It is encouraged to implement bpf_int_jit_compile() instead, so that
+ * eBPF and implicitly also cBPF can get JITed!
+ */
+struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_prog *prog)
+{
+ return prog;
+}
+
+/* Stub for JITs that support eBPF. All cBPF code gets transformed into
+ * eBPF by the kernel and is later compiled by bpf_int_jit_compile().
+ */
+void __weak bpf_jit_compile(struct bpf_prog *prog)
+{
+}
+
+bool __weak bpf_helper_changes_pkt_data(void *func)
+{
+ return false;
+}
+
+/* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call
+ * skb_copy_bits(), so provide a weak definition of it for NET-less config.
+ */
+int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to,
+ int len)
+{
+ return -EFAULT;
+}
+
+/* All definitions of tracepoints related to BPF. */
+#define CREATE_TRACE_POINTS
+#include <linux/bpf_trace.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception);
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
new file mode 100644
index 000000000..61fbcae82
--- /dev/null
+++ b/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);
+ }
+}
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
new file mode 100644
index 000000000..1defea4b2
--- /dev/null
+++ b/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);
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
new file mode 100644
index 000000000..cbd75dd59
--- /dev/null
+++ b/kernel/bpf/disasm.c
@@ -0,0 +1,263 @@
+/* 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, "(%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 (BPF_MODE(insn->code) == 0xc0 /* BPF_NOSPEC, no UAPI */) {
+ verbose(cbs->private_data, "(%02x) nospec\n", insn->code);
+ } else {
+ verbose(cbs->private_data, "BUG_st_%02x\n", insn->code);
+ }
+ } 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]);
+ }
+}
diff --git a/kernel/bpf/disasm.h b/kernel/bpf/disasm.h
new file mode 100644
index 000000000..e1324a834
--- /dev/null
+++ b/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
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
new file mode 100644
index 000000000..3f3ed33bd
--- /dev/null
+++ b/kernel/bpf/hashtab.c
@@ -0,0 +1,1451 @@
+/* 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 <linux/btf.h>
+#include <linux/jhash.h>
+#include <linux/filter.h>
+#include <linux/rculist_nulls.h>
+#include <linux/random.h>
+#include <uapi/linux/btf.h>
+#include "percpu_freelist.h"
+#include "bpf_lru_list.h"
+#include "map_in_map.h"
+
+#define HTAB_CREATE_FLAG_MASK \
+ (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \
+ BPF_F_RDONLY | BPF_F_WRONLY)
+
+struct bucket {
+ struct hlist_nulls_head head;
+ raw_spinlock_t lock;
+};
+
+struct bpf_htab {
+ struct bpf_map map;
+ struct bucket *buckets;
+ void *elems;
+ union {
+ struct pcpu_freelist freelist;
+ struct bpf_lru lru;
+ };
+ struct htab_elem *__percpu *extra_elems;
+ atomic_t count; /* number of elements in this hashtable */
+ u32 n_buckets; /* number of hash buckets */
+ u32 elem_size; /* size of each element in bytes */
+ u32 hashrnd;
+};
+
+/* each htab element is struct htab_elem + key + value */
+struct htab_elem {
+ union {
+ struct hlist_nulls_node hash_node;
+ struct {
+ void *padding;
+ union {
+ struct bpf_htab *htab;
+ struct pcpu_freelist_node fnode;
+ };
+ };
+ };
+ union {
+ struct rcu_head rcu;
+ struct bpf_lru_node lru_node;
+ };
+ u32 hash;
+ char key[0] __aligned(8);
+};
+
+static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node);
+
+static bool htab_is_lru(const struct bpf_htab *htab)
+{
+ return htab->map.map_type == BPF_MAP_TYPE_LRU_HASH ||
+ htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
+}
+
+static bool htab_is_percpu(const struct bpf_htab *htab)
+{
+ return htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
+}
+
+static bool htab_is_prealloc(const struct bpf_htab *htab)
+{
+ return !(htab->map.map_flags & BPF_F_NO_PREALLOC);
+}
+
+static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size,
+ void __percpu *pptr)
+{
+ *(void __percpu **)(l->key + key_size) = pptr;
+}
+
+static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size)
+{
+ return *(void __percpu **)(l->key + key_size);
+}
+
+static void *fd_htab_map_get_ptr(const struct bpf_map *map, struct htab_elem *l)
+{
+ return *(void **)(l->key + roundup(map->key_size, 8));
+}
+
+static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i)
+{
+ return (struct htab_elem *) (htab->elems + i * htab->elem_size);
+}
+
+static void htab_free_elems(struct bpf_htab *htab)
+{
+ int i;
+
+ if (!htab_is_percpu(htab))
+ goto free_elems;
+
+ for (i = 0; i < htab->map.max_entries; i++) {
+ void __percpu *pptr;
+
+ pptr = htab_elem_get_ptr(get_htab_elem(htab, i),
+ htab->map.key_size);
+ free_percpu(pptr);
+ cond_resched();
+ }
+free_elems:
+ bpf_map_area_free(htab->elems);
+}
+
+static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
+ u32 hash)
+{
+ struct bpf_lru_node *node = bpf_lru_pop_free(&htab->lru, hash);
+ struct htab_elem *l;
+
+ if (node) {
+ l = container_of(node, struct htab_elem, lru_node);
+ memcpy(l->key, key, htab->map.key_size);
+ return l;
+ }
+
+ return NULL;
+}
+
+static int prealloc_init(struct bpf_htab *htab)
+{
+ u32 num_entries = htab->map.max_entries;
+ int err = -ENOMEM, i;
+
+ if (!htab_is_percpu(htab) && !htab_is_lru(htab))
+ num_entries += num_possible_cpus();
+
+ htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries,
+ htab->map.numa_node);
+ if (!htab->elems)
+ return -ENOMEM;
+
+ if (!htab_is_percpu(htab))
+ goto skip_percpu_elems;
+
+ for (i = 0; i < num_entries; i++) {
+ u32 size = round_up(htab->map.value_size, 8);
+ void __percpu *pptr;
+
+ pptr = __alloc_percpu_gfp(size, 8, GFP_USER | __GFP_NOWARN);
+ if (!pptr)
+ goto free_elems;
+ htab_elem_set_ptr(get_htab_elem(htab, i), htab->map.key_size,
+ pptr);
+ cond_resched();
+ }
+
+skip_percpu_elems:
+ if (htab_is_lru(htab))
+ err = bpf_lru_init(&htab->lru,
+ htab->map.map_flags & BPF_F_NO_COMMON_LRU,
+ offsetof(struct htab_elem, hash) -
+ offsetof(struct htab_elem, lru_node),
+ htab_lru_map_delete_node,
+ htab);
+ else
+ err = pcpu_freelist_init(&htab->freelist);
+
+ if (err)
+ goto free_elems;
+
+ if (htab_is_lru(htab))
+ bpf_lru_populate(&htab->lru, htab->elems,
+ offsetof(struct htab_elem, lru_node),
+ htab->elem_size, num_entries);
+ else
+ pcpu_freelist_populate(&htab->freelist,
+ htab->elems + offsetof(struct htab_elem, fnode),
+ htab->elem_size, num_entries);
+
+ return 0;
+
+free_elems:
+ htab_free_elems(htab);
+ return err;
+}
+
+static void prealloc_destroy(struct bpf_htab *htab)
+{
+ htab_free_elems(htab);
+
+ if (htab_is_lru(htab))
+ bpf_lru_destroy(&htab->lru);
+ else
+ pcpu_freelist_destroy(&htab->freelist);
+}
+
+static int alloc_extra_elems(struct bpf_htab *htab)
+{
+ struct htab_elem *__percpu *pptr, *l_new;
+ struct pcpu_freelist_node *l;
+ int cpu;
+
+ pptr = __alloc_percpu_gfp(sizeof(struct htab_elem *), 8,
+ GFP_USER | __GFP_NOWARN);
+ if (!pptr)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ l = pcpu_freelist_pop(&htab->freelist);
+ /* pop will succeed, since prealloc_init()
+ * preallocated extra num_possible_cpus elements
+ */
+ l_new = container_of(l, struct htab_elem, fnode);
+ *per_cpu_ptr(pptr, cpu) = l_new;
+ }
+ htab->extra_elems = pptr;
+ return 0;
+}
+
+/* Called from syscall */
+static int htab_map_alloc_check(union bpf_attr *attr)
+{
+ bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH);
+ bool lru = (attr->map_type == BPF_MAP_TYPE_LRU_HASH ||
+ attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH);
+ /* percpu_lru means each cpu has its own LRU list.
+ * it is different from BPF_MAP_TYPE_PERCPU_HASH where
+ * the map's value itself is percpu. percpu_lru has
+ * nothing to do with the map's value.
+ */
+ bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
+ bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
+ int numa_node = bpf_map_attr_numa_node(attr);
+
+ BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
+ offsetof(struct htab_elem, hash_node.pprev));
+ BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) !=
+ offsetof(struct htab_elem, hash_node.pprev));
+
+ if (lru && !capable(CAP_SYS_ADMIN))
+ /* LRU implementation is much complicated than other
+ * maps. Hence, limit to CAP_SYS_ADMIN for now.
+ */
+ return -EPERM;
+
+ if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK)
+ /* reserved bits should not be used */
+ return -EINVAL;
+
+ if (!lru && percpu_lru)
+ return -EINVAL;
+
+ if (lru && !prealloc)
+ return -ENOTSUPP;
+
+ if (numa_node != NUMA_NO_NODE && (percpu || percpu_lru))
+ return -EINVAL;
+
+ /* check sanity of attributes.
+ * value_size == 0 may be allowed in the future to use map as a set
+ */
+ if (attr->max_entries == 0 || attr->key_size == 0 ||
+ attr->value_size == 0)
+ return -EINVAL;
+
+ if (attr->key_size > MAX_BPF_STACK)
+ /* eBPF programs initialize keys on stack, so they cannot be
+ * larger than max stack size
+ */
+ return -E2BIG;
+
+ if (attr->value_size >= KMALLOC_MAX_SIZE -
+ MAX_BPF_STACK - sizeof(struct htab_elem))
+ /* if value_size is bigger, the user space won't be able to
+ * access the elements via bpf syscall. This check also makes
+ * sure that the elem_size doesn't overflow and it's
+ * kmalloc-able later in htab_map_update_elem()
+ */
+ return -E2BIG;
+
+ return 0;
+}
+
+static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
+{
+ bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH);
+ bool lru = (attr->map_type == BPF_MAP_TYPE_LRU_HASH ||
+ attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH);
+ /* percpu_lru means each cpu has its own LRU list.
+ * it is different from BPF_MAP_TYPE_PERCPU_HASH where
+ * the map's value itself is percpu. percpu_lru has
+ * nothing to do with the map's value.
+ */
+ bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
+ bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
+ struct bpf_htab *htab;
+ int err, i;
+ u64 cost;
+
+ htab = kzalloc(sizeof(*htab), GFP_USER);
+ if (!htab)
+ return ERR_PTR(-ENOMEM);
+
+ bpf_map_init_from_attr(&htab->map, attr);
+
+ if (percpu_lru) {
+ /* ensure each CPU's lru list has >=1 elements.
+ * since we are at it, make each lru list has the same
+ * number of elements.
+ */
+ htab->map.max_entries = roundup(attr->max_entries,
+ num_possible_cpus());
+ if (htab->map.max_entries < attr->max_entries)
+ htab->map.max_entries = rounddown(attr->max_entries,
+ num_possible_cpus());
+ }
+
+ /* hash table size must be power of 2 */
+ htab->n_buckets = roundup_pow_of_two(htab->map.max_entries);
+
+ htab->elem_size = sizeof(struct htab_elem) +
+ round_up(htab->map.key_size, 8);
+ if (percpu)
+ htab->elem_size += sizeof(void *);
+ else
+ htab->elem_size += round_up(htab->map.value_size, 8);
+
+ err = -E2BIG;
+ /* prevent zero size kmalloc and check for u32 overflow */
+ if (htab->n_buckets == 0 ||
+ htab->n_buckets > U32_MAX / sizeof(struct bucket))
+ goto free_htab;
+
+ cost = (u64) htab->n_buckets * sizeof(struct bucket) +
+ (u64) htab->elem_size * htab->map.max_entries;
+
+ if (percpu)
+ cost += (u64) round_up(htab->map.value_size, 8) *
+ num_possible_cpus() * htab->map.max_entries;
+ else
+ cost += (u64) htab->elem_size * num_possible_cpus();
+
+ if (cost >= U32_MAX - PAGE_SIZE)
+ /* make sure page count doesn't overflow */
+ goto free_htab;
+
+ htab->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(htab->map.pages);
+ if (err)
+ goto free_htab;
+
+ err = -ENOMEM;
+ htab->buckets = bpf_map_area_alloc(htab->n_buckets *
+ sizeof(struct bucket),
+ htab->map.numa_node);
+ if (!htab->buckets)
+ goto free_htab;
+
+ htab->hashrnd = get_random_int();
+ for (i = 0; i < htab->n_buckets; i++) {
+ INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
+ raw_spin_lock_init(&htab->buckets[i].lock);
+ }
+
+ if (prealloc) {
+ err = prealloc_init(htab);
+ if (err)
+ goto free_buckets;
+
+ if (!percpu && !lru) {
+ /* lru itself can remove the least used element, so
+ * there is no need for an extra elem during map_update.
+ */
+ err = alloc_extra_elems(htab);
+ if (err)
+ goto free_prealloc;
+ }
+ }
+
+ return &htab->map;
+
+free_prealloc:
+ prealloc_destroy(htab);
+free_buckets:
+ bpf_map_area_free(htab->buckets);
+free_htab:
+ kfree(htab);
+ return ERR_PTR(err);
+}
+
+static inline u32 htab_map_hash(const void *key, u32 key_len, u32 hashrnd)
+{
+ return jhash(key, key_len, hashrnd);
+}
+
+static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &htab->buckets[hash & (htab->n_buckets - 1)];
+}
+
+static inline struct hlist_nulls_head *select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &__select_bucket(htab, hash)->head;
+}
+
+/* this lookup function can only be called with bucket lock taken */
+static struct htab_elem *lookup_elem_raw(struct hlist_nulls_head *head, u32 hash,
+ void *key, u32 key_size)
+{
+ struct hlist_nulls_node *n;
+ struct htab_elem *l;
+
+ hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
+ if (l->hash == hash && !memcmp(&l->key, key, key_size))
+ return l;
+
+ return NULL;
+}
+
+/* can be called without bucket lock. it will repeat the loop in
+ * the unlikely event when elements moved from one bucket into another
+ * while link list is being walked
+ */
+static struct htab_elem *lookup_nulls_elem_raw(struct hlist_nulls_head *head,
+ u32 hash, void *key,
+ u32 key_size, u32 n_buckets)
+{
+ struct hlist_nulls_node *n;
+ struct htab_elem *l;
+
+again:
+ hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
+ if (l->hash == hash && !memcmp(&l->key, key, key_size))
+ return l;
+
+ if (unlikely(get_nulls_value(n) != (hash & (n_buckets - 1))))
+ goto again;
+
+ return NULL;
+}
+
+/* Called from syscall or from eBPF program directly, so
+ * arguments have to match bpf_map_lookup_elem() exactly.
+ * The return value is adjusted by BPF instructions
+ * in htab_map_gen_lookup().
+ */
+static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct hlist_nulls_head *head;
+ struct htab_elem *l;
+ u32 hash, key_size;
+
+ /* Must be called with rcu_read_lock. */
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ key_size = map->key_size;
+
+ hash = htab_map_hash(key, key_size, htab->hashrnd);
+
+ head = select_bucket(htab, hash);
+
+ l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets);
+
+ return l;
+}
+
+static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct htab_elem *l = __htab_map_lookup_elem(map, key);
+
+ if (l)
+ return l->key + round_up(map->key_size, 8);
+
+ return NULL;
+}
+
+/* inline bpf_map_lookup_elem() call.
+ * Instead of:
+ * bpf_prog
+ * bpf_map_lookup_elem
+ * map->ops->map_lookup_elem
+ * htab_map_lookup_elem
+ * __htab_map_lookup_elem
+ * do:
+ * bpf_prog
+ * __htab_map_lookup_elem
+ */
+static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+{
+ struct bpf_insn *insn = insn_buf;
+ const int ret = BPF_REG_0;
+
+ BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
+ (void *(*)(struct bpf_map *map, void *key))NULL));
+ *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem));
+ *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
+ *insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
+ offsetof(struct htab_elem, key) +
+ round_up(map->key_size, 8));
+ return insn - insn_buf;
+}
+
+static __always_inline void *__htab_lru_map_lookup_elem(struct bpf_map *map,
+ void *key, const bool mark)
+{
+ struct htab_elem *l = __htab_map_lookup_elem(map, key);
+
+ if (l) {
+ if (mark)
+ bpf_lru_node_set_ref(&l->lru_node);
+ return l->key + round_up(map->key_size, 8);
+ }
+
+ return NULL;
+}
+
+static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ return __htab_lru_map_lookup_elem(map, key, true);
+}
+
+static void *htab_lru_map_lookup_elem_sys(struct bpf_map *map, void *key)
+{
+ return __htab_lru_map_lookup_elem(map, key, false);
+}
+
+static u32 htab_lru_map_gen_lookup(struct bpf_map *map,
+ struct bpf_insn *insn_buf)
+{
+ struct bpf_insn *insn = insn_buf;
+ const int ret = BPF_REG_0;
+ const int ref_reg = BPF_REG_1;
+
+ BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
+ (void *(*)(struct bpf_map *map, void *key))NULL));
+ *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem));
+ *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4);
+ *insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret,
+ offsetof(struct htab_elem, lru_node) +
+ offsetof(struct bpf_lru_node, ref));
+ *insn++ = BPF_JMP_IMM(BPF_JNE, ref_reg, 0, 1);
+ *insn++ = BPF_ST_MEM(BPF_B, ret,
+ offsetof(struct htab_elem, lru_node) +
+ offsetof(struct bpf_lru_node, ref),
+ 1);
+ *insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
+ offsetof(struct htab_elem, key) +
+ round_up(map->key_size, 8));
+ return insn - insn_buf;
+}
+
+/* It is called from the bpf_lru_list when the LRU needs to delete
+ * older elements from the htab.
+ */
+static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
+{
+ struct bpf_htab *htab = (struct bpf_htab *)arg;
+ struct htab_elem *l = NULL, *tgt_l;
+ struct hlist_nulls_head *head;
+ struct hlist_nulls_node *n;
+ unsigned long flags;
+ struct bucket *b;
+
+ tgt_l = container_of(node, struct htab_elem, lru_node);
+ b = __select_bucket(htab, tgt_l->hash);
+ head = &b->head;
+
+ raw_spin_lock_irqsave(&b->lock, flags);
+
+ hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
+ if (l == tgt_l) {
+ hlist_nulls_del_rcu(&l->hash_node);
+ break;
+ }
+
+ raw_spin_unlock_irqrestore(&b->lock, flags);
+
+ return l == tgt_l;
+}
+
+/* Called from syscall */
+static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct hlist_nulls_head *head;
+ struct htab_elem *l, *next_l;
+ u32 hash, key_size;
+ int i = 0;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ key_size = map->key_size;
+
+ if (!key)
+ goto find_first_elem;
+
+ hash = htab_map_hash(key, key_size, htab->hashrnd);
+
+ head = select_bucket(htab, hash);
+
+ /* lookup the key */
+ l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets);
+
+ if (!l)
+ goto find_first_elem;
+
+ /* key was found, get next key in the same bucket */
+ next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_next_rcu(&l->hash_node)),
+ struct htab_elem, hash_node);
+
+ if (next_l) {
+ /* if next elem in this hash list is non-zero, just return it */
+ memcpy(next_key, next_l->key, key_size);
+ return 0;
+ }
+
+ /* no more elements in this hash list, go to the next bucket */
+ i = hash & (htab->n_buckets - 1);
+ i++;
+
+find_first_elem:
+ /* iterate over buckets */
+ for (; i < htab->n_buckets; i++) {
+ head = select_bucket(htab, i);
+
+ /* pick first element in the bucket */
+ next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_first_rcu(head)),
+ struct htab_elem, hash_node);
+ if (next_l) {
+ /* if it's not empty, just return it */
+ memcpy(next_key, next_l->key, key_size);
+ return 0;
+ }
+ }
+
+ /* iterated over all buckets and all elements */
+ return -ENOENT;
+}
+
+static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l)
+{
+ if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH)
+ free_percpu(htab_elem_get_ptr(l, htab->map.key_size));
+ kfree(l);
+}
+
+static void htab_elem_free_rcu(struct rcu_head *head)
+{
+ struct htab_elem *l = container_of(head, struct htab_elem, rcu);
+ struct bpf_htab *htab = l->htab;
+
+ htab_elem_free(htab, l);
+}
+
+static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l)
+{
+ struct bpf_map *map = &htab->map;
+ void *ptr;
+
+ if (map->ops->map_fd_put_ptr) {
+ ptr = fd_htab_map_get_ptr(map, l);
+ map->ops->map_fd_put_ptr(ptr);
+ }
+}
+
+static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
+{
+ htab_put_fd_value(htab, l);
+
+ if (htab_is_prealloc(htab)) {
+ __pcpu_freelist_push(&htab->freelist, &l->fnode);
+ } else {
+ atomic_dec(&htab->count);
+ l->htab = htab;
+ call_rcu(&l->rcu, htab_elem_free_rcu);
+ }
+}
+
+static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
+ void *value, bool onallcpus)
+{
+ if (!onallcpus) {
+ /* copy true value_size bytes */
+ memcpy(this_cpu_ptr(pptr), value, htab->map.value_size);
+ } else {
+ u32 size = round_up(htab->map.value_size, 8);
+ int off = 0, cpu;
+
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(per_cpu_ptr(pptr, cpu),
+ value + off, size);
+ off += size;
+ }
+ }
+}
+
+static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
+{
+ return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS &&
+ BITS_PER_LONG == 64;
+}
+
+static u32 htab_size_value(const struct bpf_htab *htab, bool percpu)
+{
+ u32 size = htab->map.value_size;
+
+ if (percpu || fd_htab_map_needs_adjust(htab))
+ size = round_up(size, 8);
+ return size;
+}
+
+static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
+ void *value, u32 key_size, u32 hash,
+ bool percpu, bool onallcpus,
+ struct htab_elem *old_elem)
+{
+ u32 size = htab_size_value(htab, percpu);
+ bool prealloc = htab_is_prealloc(htab);
+ struct htab_elem *l_new, **pl_new;
+ void __percpu *pptr;
+
+ if (prealloc) {
+ if (old_elem) {
+ /* if we're updating the existing element,
+ * use per-cpu extra elems to avoid freelist_pop/push
+ */
+ pl_new = this_cpu_ptr(htab->extra_elems);
+ l_new = *pl_new;
+ htab_put_fd_value(htab, old_elem);
+ *pl_new = old_elem;
+ } else {
+ struct pcpu_freelist_node *l;
+
+ l = __pcpu_freelist_pop(&htab->freelist);
+ if (!l)
+ return ERR_PTR(-E2BIG);
+ l_new = container_of(l, struct htab_elem, fnode);
+ }
+ } else {
+ if (atomic_inc_return(&htab->count) > htab->map.max_entries)
+ if (!old_elem) {
+ /* when map is full and update() is replacing
+ * old element, it's ok to allocate, since
+ * old element will be freed immediately.
+ * Otherwise return an error
+ */
+ l_new = ERR_PTR(-E2BIG);
+ goto dec_count;
+ }
+ l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
+ htab->map.numa_node);
+ if (!l_new) {
+ l_new = ERR_PTR(-ENOMEM);
+ goto dec_count;
+ }
+ }
+
+ memcpy(l_new->key, key, key_size);
+ if (percpu) {
+ if (prealloc) {
+ pptr = htab_elem_get_ptr(l_new, key_size);
+ } else {
+ /* alloc_percpu zero-fills */
+ pptr = __alloc_percpu_gfp(size, 8,
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (!pptr) {
+ kfree(l_new);
+ l_new = ERR_PTR(-ENOMEM);
+ goto dec_count;
+ }
+ }
+
+ pcpu_copy_value(htab, pptr, value, onallcpus);
+
+ if (!prealloc)
+ htab_elem_set_ptr(l_new, key_size, pptr);
+ } else {
+ memcpy(l_new->key + round_up(key_size, 8), value, size);
+ }
+
+ l_new->hash = hash;
+ return l_new;
+dec_count:
+ atomic_dec(&htab->count);
+ return l_new;
+}
+
+static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
+ u64 map_flags)
+{
+ if (l_old && map_flags == BPF_NOEXIST)
+ /* elem already exists */
+ return -EEXIST;
+
+ if (!l_old && map_flags == BPF_EXIST)
+ /* elem doesn't exist, cannot update it */
+ return -ENOENT;
+
+ return 0;
+}
+
+/* Called from syscall or from eBPF program */
+static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
+ u64 map_flags)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct htab_elem *l_new = NULL, *l_old;
+ struct hlist_nulls_head *head;
+ unsigned long flags;
+ struct bucket *b;
+ u32 key_size, hash;
+ int ret;
+
+ if (unlikely(map_flags > BPF_EXIST))
+ /* unknown flags */
+ return -EINVAL;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ key_size = map->key_size;
+
+ hash = htab_map_hash(key, key_size, htab->hashrnd);
+
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ /* bpf_map_update_elem() can be called in_irq() */
+ raw_spin_lock_irqsave(&b->lock, flags);
+
+ l_old = lookup_elem_raw(head, hash, key, key_size);
+
+ ret = check_flags(htab, l_old, map_flags);
+ if (ret)
+ goto err;
+
+ l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false,
+ l_old);
+ if (IS_ERR(l_new)) {
+ /* all pre-allocated elements are in use or memory exhausted */
+ ret = PTR_ERR(l_new);
+ goto err;
+ }
+
+ /* add new element to the head of the list, so that
+ * concurrent search will find it before old elem
+ */
+ hlist_nulls_add_head_rcu(&l_new->hash_node, head);
+ if (l_old) {
+ hlist_nulls_del_rcu(&l_old->hash_node);
+ if (!htab_is_prealloc(htab))
+ free_htab_elem(htab, l_old);
+ }
+ ret = 0;
+err:
+ raw_spin_unlock_irqrestore(&b->lock, flags);
+ return ret;
+}
+
+static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
+ u64 map_flags)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct htab_elem *l_new, *l_old = NULL;
+ struct hlist_nulls_head *head;
+ unsigned long flags;
+ struct bucket *b;
+ u32 key_size, hash;
+ int ret;
+
+ if (unlikely(map_flags > BPF_EXIST))
+ /* unknown flags */
+ return -EINVAL;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ key_size = map->key_size;
+
+ hash = htab_map_hash(key, key_size, htab->hashrnd);
+
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ /* For LRU, we need to alloc before taking bucket's
+ * spinlock because getting free nodes from LRU may need
+ * to remove older elements from htab and this removal
+ * operation will need a bucket lock.
+ */
+ l_new = prealloc_lru_pop(htab, key, hash);
+ if (!l_new)
+ return -ENOMEM;
+ memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size);
+
+ /* bpf_map_update_elem() can be called in_irq() */
+ raw_spin_lock_irqsave(&b->lock, flags);
+
+ l_old = lookup_elem_raw(head, hash, key, key_size);
+
+ ret = check_flags(htab, l_old, map_flags);
+ if (ret)
+ goto err;
+
+ /* add new element to the head of the list, so that
+ * concurrent search will find it before old elem
+ */
+ hlist_nulls_add_head_rcu(&l_new->hash_node, head);
+ if (l_old) {
+ bpf_lru_node_set_ref(&l_new->lru_node);
+ hlist_nulls_del_rcu(&l_old->hash_node);
+ }
+ ret = 0;
+
+err:
+ raw_spin_unlock_irqrestore(&b->lock, flags);
+
+ if (ret)
+ bpf_lru_push_free(&htab->lru, &l_new->lru_node);
+ else if (l_old)
+ bpf_lru_push_free(&htab->lru, &l_old->lru_node);
+
+ return ret;
+}
+
+static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags,
+ bool onallcpus)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct htab_elem *l_new = NULL, *l_old;
+ struct hlist_nulls_head *head;
+ unsigned long flags;
+ struct bucket *b;
+ u32 key_size, hash;
+ int ret;
+
+ if (unlikely(map_flags > BPF_EXIST))
+ /* unknown flags */
+ return -EINVAL;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ key_size = map->key_size;
+
+ hash = htab_map_hash(key, key_size, htab->hashrnd);
+
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ /* bpf_map_update_elem() can be called in_irq() */
+ raw_spin_lock_irqsave(&b->lock, flags);
+
+ l_old = lookup_elem_raw(head, hash, key, key_size);
+
+ ret = check_flags(htab, l_old, map_flags);
+ if (ret)
+ goto err;
+
+ if (l_old) {
+ /* per-cpu hash map can update value in-place */
+ pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
+ value, onallcpus);
+ } else {
+ l_new = alloc_htab_elem(htab, key, value, key_size,
+ hash, true, onallcpus, NULL);
+ if (IS_ERR(l_new)) {
+ ret = PTR_ERR(l_new);
+ goto err;
+ }
+ hlist_nulls_add_head_rcu(&l_new->hash_node, head);
+ }
+ ret = 0;
+err:
+ raw_spin_unlock_irqrestore(&b->lock, flags);
+ return ret;
+}
+
+static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags,
+ bool onallcpus)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct htab_elem *l_new = NULL, *l_old;
+ struct hlist_nulls_head *head;
+ unsigned long flags;
+ struct bucket *b;
+ u32 key_size, hash;
+ int ret;
+
+ if (unlikely(map_flags > BPF_EXIST))
+ /* unknown flags */
+ return -EINVAL;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ key_size = map->key_size;
+
+ hash = htab_map_hash(key, key_size, htab->hashrnd);
+
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ /* For LRU, we need to alloc before taking bucket's
+ * spinlock because LRU's elem alloc may need
+ * to remove older elem from htab and this removal
+ * operation will need a bucket lock.
+ */
+ if (map_flags != BPF_EXIST) {
+ l_new = prealloc_lru_pop(htab, key, hash);
+ if (!l_new)
+ return -ENOMEM;
+ }
+
+ /* bpf_map_update_elem() can be called in_irq() */
+ raw_spin_lock_irqsave(&b->lock, flags);
+
+ l_old = lookup_elem_raw(head, hash, key, key_size);
+
+ ret = check_flags(htab, l_old, map_flags);
+ if (ret)
+ goto err;
+
+ if (l_old) {
+ bpf_lru_node_set_ref(&l_old->lru_node);
+
+ /* per-cpu hash map can update value in-place */
+ pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
+ value, onallcpus);
+ } else {
+ pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size),
+ value, onallcpus);
+ hlist_nulls_add_head_rcu(&l_new->hash_node, head);
+ l_new = NULL;
+ }
+ ret = 0;
+err:
+ raw_spin_unlock_irqrestore(&b->lock, flags);
+ if (l_new)
+ bpf_lru_push_free(&htab->lru, &l_new->lru_node);
+ return ret;
+}
+
+static int htab_percpu_map_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags)
+{
+ return __htab_percpu_map_update_elem(map, key, value, map_flags, false);
+}
+
+static int htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags)
+{
+ return __htab_lru_percpu_map_update_elem(map, key, value, map_flags,
+ false);
+}
+
+/* Called from syscall or from eBPF program */
+static int htab_map_delete_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct hlist_nulls_head *head;
+ struct bucket *b;
+ struct htab_elem *l;
+ unsigned long flags;
+ u32 hash, key_size;
+ int ret = -ENOENT;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ key_size = map->key_size;
+
+ hash = htab_map_hash(key, key_size, htab->hashrnd);
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ raw_spin_lock_irqsave(&b->lock, flags);
+
+ l = lookup_elem_raw(head, hash, key, key_size);
+
+ if (l) {
+ hlist_nulls_del_rcu(&l->hash_node);
+ free_htab_elem(htab, l);
+ ret = 0;
+ }
+
+ raw_spin_unlock_irqrestore(&b->lock, flags);
+ return ret;
+}
+
+static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct hlist_nulls_head *head;
+ struct bucket *b;
+ struct htab_elem *l;
+ unsigned long flags;
+ u32 hash, key_size;
+ int ret = -ENOENT;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ key_size = map->key_size;
+
+ hash = htab_map_hash(key, key_size, htab->hashrnd);
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ raw_spin_lock_irqsave(&b->lock, flags);
+
+ l = lookup_elem_raw(head, hash, key, key_size);
+
+ if (l) {
+ hlist_nulls_del_rcu(&l->hash_node);
+ ret = 0;
+ }
+
+ raw_spin_unlock_irqrestore(&b->lock, flags);
+ if (l)
+ bpf_lru_push_free(&htab->lru, &l->lru_node);
+ return ret;
+}
+
+static void delete_all_elements(struct bpf_htab *htab)
+{
+ int i;
+
+ for (i = 0; i < htab->n_buckets; i++) {
+ struct hlist_nulls_head *head = select_bucket(htab, i);
+ struct hlist_nulls_node *n;
+ struct htab_elem *l;
+
+ hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
+ hlist_nulls_del_rcu(&l->hash_node);
+ htab_elem_free(htab, l);
+ }
+ }
+}
+
+/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
+static void htab_map_free(struct bpf_map *map)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, 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 critical sections in
+ * these programs to complete
+ */
+ synchronize_rcu();
+
+ /* some of free_htab_elem() callbacks for elements of this map may
+ * not have executed. Wait for them.
+ */
+ rcu_barrier();
+ if (!htab_is_prealloc(htab))
+ delete_all_elements(htab);
+ else
+ prealloc_destroy(htab);
+
+ free_percpu(htab->extra_elems);
+ bpf_map_area_free(htab->buckets);
+ kfree(htab);
+}
+
+static void htab_map_seq_show_elem(struct bpf_map *map, void *key,
+ struct seq_file *m)
+{
+ void *value;
+
+ rcu_read_lock();
+
+ value = htab_map_lookup_elem(map, key);
+ if (!value) {
+ rcu_read_unlock();
+ return;
+ }
+
+ btf_type_seq_show(map->btf, map->btf_key_type_id, key, m);
+ seq_puts(m, ": ");
+ btf_type_seq_show(map->btf, map->btf_value_type_id, value, m);
+ seq_puts(m, "\n");
+
+ rcu_read_unlock();
+}
+
+const struct bpf_map_ops htab_map_ops = {
+ .map_alloc_check = htab_map_alloc_check,
+ .map_alloc = htab_map_alloc,
+ .map_free = htab_map_free,
+ .map_get_next_key = htab_map_get_next_key,
+ .map_lookup_elem = htab_map_lookup_elem,
+ .map_update_elem = htab_map_update_elem,
+ .map_delete_elem = htab_map_delete_elem,
+ .map_gen_lookup = htab_map_gen_lookup,
+ .map_seq_show_elem = htab_map_seq_show_elem,
+};
+
+const struct bpf_map_ops htab_lru_map_ops = {
+ .map_alloc_check = htab_map_alloc_check,
+ .map_alloc = htab_map_alloc,
+ .map_free = htab_map_free,
+ .map_get_next_key = htab_map_get_next_key,
+ .map_lookup_elem = htab_lru_map_lookup_elem,
+ .map_lookup_elem_sys_only = htab_lru_map_lookup_elem_sys,
+ .map_update_elem = htab_lru_map_update_elem,
+ .map_delete_elem = htab_lru_map_delete_elem,
+ .map_gen_lookup = htab_lru_map_gen_lookup,
+ .map_seq_show_elem = htab_map_seq_show_elem,
+};
+
+/* Called from eBPF program */
+static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct htab_elem *l = __htab_map_lookup_elem(map, key);
+
+ if (l)
+ return this_cpu_ptr(htab_elem_get_ptr(l, map->key_size));
+ else
+ return NULL;
+}
+
+static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct htab_elem *l = __htab_map_lookup_elem(map, key);
+
+ if (l) {
+ bpf_lru_node_set_ref(&l->lru_node);
+ return this_cpu_ptr(htab_elem_get_ptr(l, map->key_size));
+ }
+
+ return NULL;
+}
+
+int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
+{
+ struct htab_elem *l;
+ void __percpu *pptr;
+ int ret = -ENOENT;
+ int cpu, off = 0;
+ u32 size;
+
+ /* 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();
+ l = __htab_map_lookup_elem(map, key);
+ if (!l)
+ goto out;
+ /* We do not mark LRU map element here in order to not mess up
+ * eviction heuristics when user space does a map walk.
+ */
+ pptr = htab_elem_get_ptr(l, map->key_size);
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(value + off,
+ per_cpu_ptr(pptr, cpu), size);
+ off += size;
+ }
+ ret = 0;
+out:
+ rcu_read_unlock();
+ return ret;
+}
+
+int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
+ u64 map_flags)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ int ret;
+
+ rcu_read_lock();
+ if (htab_is_lru(htab))
+ ret = __htab_lru_percpu_map_update_elem(map, key, value,
+ map_flags, true);
+ else
+ ret = __htab_percpu_map_update_elem(map, key, value, map_flags,
+ true);
+ rcu_read_unlock();
+
+ return ret;
+}
+
+const struct bpf_map_ops htab_percpu_map_ops = {
+ .map_alloc_check = htab_map_alloc_check,
+ .map_alloc = htab_map_alloc,
+ .map_free = htab_map_free,
+ .map_get_next_key = htab_map_get_next_key,
+ .map_lookup_elem = htab_percpu_map_lookup_elem,
+ .map_update_elem = htab_percpu_map_update_elem,
+ .map_delete_elem = htab_map_delete_elem,
+};
+
+const struct bpf_map_ops htab_lru_percpu_map_ops = {
+ .map_alloc_check = htab_map_alloc_check,
+ .map_alloc = htab_map_alloc,
+ .map_free = htab_map_free,
+ .map_get_next_key = htab_map_get_next_key,
+ .map_lookup_elem = htab_lru_percpu_map_lookup_elem,
+ .map_update_elem = htab_lru_percpu_map_update_elem,
+ .map_delete_elem = htab_lru_map_delete_elem,
+};
+
+static int fd_htab_map_alloc_check(union bpf_attr *attr)
+{
+ if (attr->value_size != sizeof(u32))
+ return -EINVAL;
+ return htab_map_alloc_check(attr);
+}
+
+static void fd_htab_map_free(struct bpf_map *map)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct hlist_nulls_node *n;
+ struct hlist_nulls_head *head;
+ struct htab_elem *l;
+ int i;
+
+ for (i = 0; i < htab->n_buckets; i++) {
+ head = select_bucket(htab, i);
+
+ hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
+ void *ptr = fd_htab_map_get_ptr(map, l);
+
+ map->ops->map_fd_put_ptr(ptr);
+ }
+ }
+
+ htab_map_free(map);
+}
+
+/* only called from syscall */
+int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value)
+{
+ void **ptr;
+ int ret = 0;
+
+ if (!map->ops->map_fd_sys_lookup_elem)
+ return -ENOTSUPP;
+
+ rcu_read_lock();
+ ptr = htab_map_lookup_elem(map, key);
+ if (ptr)
+ *value = map->ops->map_fd_sys_lookup_elem(READ_ONCE(*ptr));
+ else
+ ret = -ENOENT;
+ rcu_read_unlock();
+
+ return ret;
+}
+
+/* only called from syscall */
+int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
+ void *key, void *value, u64 map_flags)
+{
+ void *ptr;
+ int ret;
+ u32 ufd = *(u32 *)value;
+
+ ptr = map->ops->map_fd_get_ptr(map, map_file, ufd);
+ if (IS_ERR(ptr))
+ return PTR_ERR(ptr);
+
+ ret = htab_map_update_elem(map, key, &ptr, map_flags);
+ if (ret)
+ map->ops->map_fd_put_ptr(ptr);
+
+ return ret;
+}
+
+static struct bpf_map *htab_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 = htab_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 *htab_of_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_map **inner_map = htab_map_lookup_elem(map, key);
+
+ if (!inner_map)
+ return NULL;
+
+ return READ_ONCE(*inner_map);
+}
+
+static u32 htab_of_map_gen_lookup(struct bpf_map *map,
+ struct bpf_insn *insn_buf)
+{
+ struct bpf_insn *insn = insn_buf;
+ const int ret = BPF_REG_0;
+
+ BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
+ (void *(*)(struct bpf_map *map, void *key))NULL));
+ *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem));
+ *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 2);
+ *insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
+ offsetof(struct htab_elem, key) +
+ round_up(map->key_size, 8));
+ *insn++ = BPF_LDX_MEM(BPF_DW, ret, ret, 0);
+
+ return insn - insn_buf;
+}
+
+static void htab_of_map_free(struct bpf_map *map)
+{
+ bpf_map_meta_free(map->inner_map_meta);
+ fd_htab_map_free(map);
+}
+
+const struct bpf_map_ops htab_of_maps_map_ops = {
+ .map_alloc_check = fd_htab_map_alloc_check,
+ .map_alloc = htab_of_map_alloc,
+ .map_free = htab_of_map_free,
+ .map_get_next_key = htab_map_get_next_key,
+ .map_lookup_elem = htab_of_map_lookup_elem,
+ .map_delete_elem = htab_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 = htab_of_map_gen_lookup,
+ .map_check_btf = map_check_no_btf,
+};
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
new file mode 100644
index 000000000..1991466b8
--- /dev/null
+++ b/kernel/bpf/helpers.c
@@ -0,0 +1,216 @@
+/* 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 = true,
+ .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
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
new file mode 100644
index 000000000..11fade89c
--- /dev/null
+++ b/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);
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
new file mode 100644
index 000000000..fc1605aee
--- /dev/null
+++ b/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
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
new file mode 100644
index 000000000..1a8b208f6
--- /dev/null
+++ b/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,
+};
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
new file mode 100644
index 000000000..9670ee5ee
--- /dev/null
+++ b/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;
+}
diff --git a/kernel/bpf/map_in_map.h b/kernel/bpf/map_in_map.h
new file mode 100644
index 000000000..6183db9ec
--- /dev/null
+++ b/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
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
new file mode 100644
index 000000000..66e13aace
--- /dev/null
+++ b/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);
diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c
new file mode 100644
index 000000000..0c1b4ba9e
--- /dev/null
+++ b/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;
+}
diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h
new file mode 100644
index 000000000..c3960118e
--- /dev/null
+++ b/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
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
new file mode 100644
index 000000000..18e225de8
--- /dev/null
+++ b/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,
+};
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
new file mode 100644
index 000000000..0a0f2ec75
--- /dev/null
+++ b/kernel/bpf/sockmap.c
@@ -0,0 +1,2631 @@
+/* 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.
+ */
+
+/* A BPF sock_map is used to store sock objects. This is primarly used
+ * for doing socket redirect with BPF helper routines.
+ *
+ * A sock map may have BPF programs attached to it, currently a program
+ * used to parse packets and a program to provide a verdict and redirect
+ * decision on the packet are supported. Any programs attached to a sock
+ * map are inherited by sock objects when they are added to the map. If
+ * no BPF programs are attached the sock object may only be used for sock
+ * redirect.
+ *
+ * A sock object may be in multiple maps, but can only inherit a single
+ * parse or verdict program. If adding a sock object to a map would result
+ * in having multiple parsing programs the update will return an EBUSY error.
+ *
+ * For reference this program is similar to devmap used in XDP context
+ * reviewing these together may be useful. For an example please review
+ * ./samples/bpf/sockmap/.
+ */
+#include <linux/bpf.h>
+#include <net/sock.h>
+#include <linux/filter.h>
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/kernel.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/workqueue.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <net/strparser.h>
+#include <net/tcp.h>
+#include <linux/ptr_ring.h>
+#include <net/inet_common.h>
+#include <linux/sched/signal.h>
+
+#define SOCK_CREATE_FLAG_MASK \
+ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
+struct bpf_sock_progs {
+ struct bpf_prog *bpf_tx_msg;
+ struct bpf_prog *bpf_parse;
+ struct bpf_prog *bpf_verdict;
+};
+
+struct bpf_stab {
+ struct bpf_map map;
+ struct sock **sock_map;
+ struct bpf_sock_progs progs;
+ raw_spinlock_t lock;
+};
+
+struct bucket {
+ struct hlist_head head;
+ raw_spinlock_t lock;
+};
+
+struct bpf_htab {
+ struct bpf_map map;
+ struct bucket *buckets;
+ atomic_t count;
+ u32 n_buckets;
+ u32 elem_size;
+ struct bpf_sock_progs progs;
+ struct rcu_head rcu;
+};
+
+struct htab_elem {
+ struct rcu_head rcu;
+ struct hlist_node hash_node;
+ u32 hash;
+ struct sock *sk;
+ char key[0];
+};
+
+enum smap_psock_state {
+ SMAP_TX_RUNNING,
+};
+
+struct smap_psock_map_entry {
+ struct list_head list;
+ struct bpf_map *map;
+ struct sock **entry;
+ struct htab_elem __rcu *hash_link;
+};
+
+struct smap_psock {
+ struct rcu_head rcu;
+ refcount_t refcnt;
+
+ /* datapath variables */
+ struct sk_buff_head rxqueue;
+ bool strp_enabled;
+
+ /* datapath error path cache across tx work invocations */
+ int save_rem;
+ int save_off;
+ struct sk_buff *save_skb;
+
+ /* datapath variables for tx_msg ULP */
+ struct sock *sk_redir;
+ int apply_bytes;
+ int cork_bytes;
+ int sg_size;
+ int eval;
+ struct sk_msg_buff *cork;
+ struct list_head ingress;
+
+ struct strparser strp;
+ struct bpf_prog *bpf_tx_msg;
+ struct bpf_prog *bpf_parse;
+ struct bpf_prog *bpf_verdict;
+ struct list_head maps;
+ spinlock_t maps_lock;
+
+ /* Back reference used when sock callback trigger sockmap operations */
+ struct sock *sock;
+ unsigned long state;
+
+ struct work_struct tx_work;
+ struct work_struct gc_work;
+
+ struct proto *sk_proto;
+ void (*save_unhash)(struct sock *sk);
+ void (*save_close)(struct sock *sk, long timeout);
+ void (*save_data_ready)(struct sock *sk);
+ void (*save_write_space)(struct sock *sk);
+};
+
+static void smap_release_sock(struct smap_psock *psock, struct sock *sock);
+static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+ int nonblock, int flags, int *addr_len);
+static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
+static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
+ int offset, size_t size, int flags);
+static void bpf_tcp_unhash(struct sock *sk);
+static void bpf_tcp_close(struct sock *sk, long timeout);
+
+static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
+{
+ return rcu_dereference_sk_user_data(sk);
+}
+
+static bool bpf_tcp_stream_read(const struct sock *sk)
+{
+ struct smap_psock *psock;
+ bool empty = true;
+
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+ if (unlikely(!psock))
+ goto out;
+ empty = list_empty(&psock->ingress);
+out:
+ rcu_read_unlock();
+ return !empty;
+}
+
+enum {
+ SOCKMAP_IPV4,
+ SOCKMAP_IPV6,
+ SOCKMAP_NUM_PROTS,
+};
+
+enum {
+ SOCKMAP_BASE,
+ SOCKMAP_TX,
+ SOCKMAP_NUM_CONFIGS,
+};
+
+static struct proto *saved_tcpv6_prot __read_mostly;
+static DEFINE_SPINLOCK(tcpv6_prot_lock);
+static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS];
+static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS],
+ struct proto *base)
+{
+ prot[SOCKMAP_BASE] = *base;
+ prot[SOCKMAP_BASE].unhash = bpf_tcp_unhash;
+ prot[SOCKMAP_BASE].close = bpf_tcp_close;
+ prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg;
+ prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read;
+
+ prot[SOCKMAP_TX] = prot[SOCKMAP_BASE];
+ prot[SOCKMAP_TX].sendmsg = bpf_tcp_sendmsg;
+ prot[SOCKMAP_TX].sendpage = bpf_tcp_sendpage;
+}
+
+static void update_sk_prot(struct sock *sk, struct smap_psock *psock)
+{
+ int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4;
+ int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE;
+
+ sk->sk_prot = &bpf_tcp_prots[family][conf];
+}
+
+static int bpf_tcp_init(struct sock *sk)
+{
+ struct smap_psock *psock;
+
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+ if (unlikely(!psock)) {
+ rcu_read_unlock();
+ return -EINVAL;
+ }
+
+ if (unlikely(psock->sk_proto)) {
+ rcu_read_unlock();
+ return -EBUSY;
+ }
+
+ psock->save_unhash = sk->sk_prot->unhash;
+ psock->save_close = sk->sk_prot->close;
+ psock->sk_proto = sk->sk_prot;
+
+ /* Build IPv6 sockmap whenever the address of tcpv6_prot changes */
+ if (sk->sk_family == AF_INET6 &&
+ unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) {
+ spin_lock_bh(&tcpv6_prot_lock);
+ if (likely(sk->sk_prot != saved_tcpv6_prot)) {
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot);
+ smp_store_release(&saved_tcpv6_prot, sk->sk_prot);
+ }
+ spin_unlock_bh(&tcpv6_prot_lock);
+ }
+ update_sk_prot(sk, psock);
+ rcu_read_unlock();
+ return 0;
+}
+
+static void smap_release_sock(struct smap_psock *psock, struct sock *sock);
+static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge);
+
+static void bpf_tcp_release(struct sock *sk)
+{
+ struct smap_psock *psock;
+
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+ if (unlikely(!psock))
+ goto out;
+
+ if (psock->cork) {
+ free_start_sg(psock->sock, psock->cork, true);
+ kfree(psock->cork);
+ psock->cork = NULL;
+ }
+
+ if (psock->sk_proto) {
+ sk->sk_prot = psock->sk_proto;
+ psock->sk_proto = NULL;
+ }
+out:
+ rcu_read_unlock();
+}
+
+static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
+ u32 hash, void *key, u32 key_size)
+{
+ struct htab_elem *l;
+
+ hlist_for_each_entry_rcu(l, head, hash_node) {
+ if (l->hash == hash && !memcmp(&l->key, key, key_size))
+ return l;
+ }
+
+ return NULL;
+}
+
+static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &htab->buckets[hash & (htab->n_buckets - 1)];
+}
+
+static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &__select_bucket(htab, hash)->head;
+}
+
+static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
+{
+ atomic_dec(&htab->count);
+ kfree_rcu(l, rcu);
+}
+
+static struct smap_psock_map_entry *psock_map_pop(struct sock *sk,
+ struct smap_psock *psock)
+{
+ struct smap_psock_map_entry *e;
+
+ spin_lock_bh(&psock->maps_lock);
+ e = list_first_entry_or_null(&psock->maps,
+ struct smap_psock_map_entry,
+ list);
+ if (e)
+ list_del(&e->list);
+ spin_unlock_bh(&psock->maps_lock);
+ return e;
+}
+
+static void bpf_tcp_remove(struct sock *sk, struct smap_psock *psock)
+{
+ struct smap_psock_map_entry *e;
+ struct sk_msg_buff *md, *mtmp;
+ struct sock *osk;
+
+ if (psock->cork) {
+ free_start_sg(psock->sock, psock->cork, true);
+ kfree(psock->cork);
+ psock->cork = NULL;
+ }
+
+ list_for_each_entry_safe(md, mtmp, &psock->ingress, list) {
+ list_del(&md->list);
+ free_start_sg(psock->sock, md, true);
+ kfree(md);
+ }
+
+ e = psock_map_pop(sk, psock);
+ while (e) {
+ if (e->entry) {
+ struct bpf_stab *stab = container_of(e->map, struct bpf_stab, map);
+
+ raw_spin_lock_bh(&stab->lock);
+ osk = *e->entry;
+ if (osk == sk) {
+ *e->entry = NULL;
+ smap_release_sock(psock, sk);
+ }
+ raw_spin_unlock_bh(&stab->lock);
+ } else {
+ struct htab_elem *link = rcu_dereference(e->hash_link);
+ struct bpf_htab *htab = container_of(e->map, struct bpf_htab, map);
+ struct hlist_head *head;
+ struct htab_elem *l;
+ struct bucket *b;
+
+ b = __select_bucket(htab, link->hash);
+ head = &b->head;
+ raw_spin_lock_bh(&b->lock);
+ l = lookup_elem_raw(head,
+ link->hash, link->key,
+ htab->map.key_size);
+ /* If another thread deleted this object skip deletion.
+ * The refcnt on psock may or may not be zero.
+ */
+ if (l && l == link) {
+ hlist_del_rcu(&link->hash_node);
+ smap_release_sock(psock, link->sk);
+ free_htab_elem(htab, link);
+ }
+ raw_spin_unlock_bh(&b->lock);
+ }
+ kfree(e);
+ e = psock_map_pop(sk, psock);
+ }
+}
+
+static void bpf_tcp_unhash(struct sock *sk)
+{
+ void (*unhash_fun)(struct sock *sk);
+ struct smap_psock *psock;
+
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+ if (unlikely(!psock)) {
+ rcu_read_unlock();
+ if (sk->sk_prot->unhash)
+ sk->sk_prot->unhash(sk);
+ return;
+ }
+ unhash_fun = psock->save_unhash;
+ bpf_tcp_remove(sk, psock);
+ rcu_read_unlock();
+ unhash_fun(sk);
+}
+
+static void bpf_tcp_close(struct sock *sk, long timeout)
+{
+ void (*close_fun)(struct sock *sk, long timeout);
+ struct smap_psock *psock;
+
+ lock_sock(sk);
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+ if (unlikely(!psock)) {
+ rcu_read_unlock();
+ release_sock(sk);
+ return sk->sk_prot->close(sk, timeout);
+ }
+ close_fun = psock->save_close;
+ bpf_tcp_remove(sk, psock);
+ rcu_read_unlock();
+ release_sock(sk);
+ close_fun(sk, timeout);
+}
+
+enum __sk_action {
+ __SK_DROP = 0,
+ __SK_PASS,
+ __SK_REDIRECT,
+ __SK_NONE,
+};
+
+static struct tcp_ulp_ops bpf_tcp_ulp_ops __read_mostly = {
+ .name = "bpf_tcp",
+ .uid = TCP_ULP_BPF,
+ .user_visible = false,
+ .owner = NULL,
+ .init = bpf_tcp_init,
+ .release = bpf_tcp_release,
+};
+
+static int memcopy_from_iter(struct sock *sk,
+ struct sk_msg_buff *md,
+ struct iov_iter *from, int bytes)
+{
+ struct scatterlist *sg = md->sg_data;
+ int i = md->sg_curr, rc = -ENOSPC;
+
+ do {
+ int copy;
+ char *to;
+
+ if (md->sg_copybreak >= sg[i].length) {
+ md->sg_copybreak = 0;
+
+ if (++i == MAX_SKB_FRAGS)
+ i = 0;
+
+ if (i == md->sg_end)
+ break;
+ }
+
+ copy = sg[i].length - md->sg_copybreak;
+ to = sg_virt(&sg[i]) + md->sg_copybreak;
+ md->sg_copybreak += copy;
+
+ if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY)
+ rc = copy_from_iter_nocache(to, copy, from);
+ else
+ rc = copy_from_iter(to, copy, from);
+
+ if (rc != copy) {
+ rc = -EFAULT;
+ goto out;
+ }
+
+ bytes -= copy;
+ if (!bytes)
+ break;
+
+ md->sg_copybreak = 0;
+ if (++i == MAX_SKB_FRAGS)
+ i = 0;
+ } while (i != md->sg_end);
+out:
+ md->sg_curr = i;
+ return rc;
+}
+
+static int bpf_tcp_push(struct sock *sk, int apply_bytes,
+ struct sk_msg_buff *md,
+ int flags, bool uncharge)
+{
+ bool apply = apply_bytes;
+ struct scatterlist *sg;
+ int offset, ret = 0;
+ struct page *p;
+ size_t size;
+
+ while (1) {
+ sg = md->sg_data + md->sg_start;
+ size = (apply && apply_bytes < sg->length) ?
+ apply_bytes : sg->length;
+ offset = sg->offset;
+
+ tcp_rate_check_app_limited(sk);
+ p = sg_page(sg);
+retry:
+ ret = do_tcp_sendpages(sk, p, offset, size, flags);
+ if (ret != size) {
+ if (ret > 0) {
+ if (apply)
+ apply_bytes -= ret;
+
+ sg->offset += ret;
+ sg->length -= ret;
+ size -= ret;
+ offset += ret;
+ if (uncharge)
+ sk_mem_uncharge(sk, ret);
+ goto retry;
+ }
+
+ return ret;
+ }
+
+ if (apply)
+ apply_bytes -= ret;
+ sg->offset += ret;
+ sg->length -= ret;
+ if (uncharge)
+ sk_mem_uncharge(sk, ret);
+
+ if (!sg->length) {
+ put_page(p);
+ md->sg_start++;
+ if (md->sg_start == MAX_SKB_FRAGS)
+ md->sg_start = 0;
+ sg_init_table(sg, 1);
+
+ if (md->sg_start == md->sg_end)
+ break;
+ }
+
+ if (apply && !apply_bytes)
+ break;
+ }
+ return 0;
+}
+
+static inline void bpf_compute_data_pointers_sg(struct sk_msg_buff *md)
+{
+ struct scatterlist *sg = md->sg_data + md->sg_start;
+
+ if (md->sg_copy[md->sg_start]) {
+ md->data = md->data_end = 0;
+ } else {
+ md->data = sg_virt(sg);
+ md->data_end = md->data + sg->length;
+ }
+}
+
+static void return_mem_sg(struct sock *sk, int bytes, struct sk_msg_buff *md)
+{
+ struct scatterlist *sg = md->sg_data;
+ int i = md->sg_start;
+
+ do {
+ int uncharge = (bytes < sg[i].length) ? bytes : sg[i].length;
+
+ sk_mem_uncharge(sk, uncharge);
+ bytes -= uncharge;
+ if (!bytes)
+ break;
+ i++;
+ if (i == MAX_SKB_FRAGS)
+ i = 0;
+ } while (i != md->sg_end);
+}
+
+static void free_bytes_sg(struct sock *sk, int bytes,
+ struct sk_msg_buff *md, bool charge)
+{
+ struct scatterlist *sg = md->sg_data;
+ int i = md->sg_start, free;
+
+ while (bytes && sg[i].length) {
+ free = sg[i].length;
+ if (bytes < free) {
+ sg[i].length -= bytes;
+ sg[i].offset += bytes;
+ if (charge)
+ sk_mem_uncharge(sk, bytes);
+ break;
+ }
+
+ if (charge)
+ sk_mem_uncharge(sk, sg[i].length);
+ put_page(sg_page(&sg[i]));
+ bytes -= sg[i].length;
+ sg[i].length = 0;
+ sg[i].page_link = 0;
+ sg[i].offset = 0;
+ i++;
+
+ if (i == MAX_SKB_FRAGS)
+ i = 0;
+ }
+ md->sg_start = i;
+}
+
+static int free_sg(struct sock *sk, int start,
+ struct sk_msg_buff *md, bool charge)
+{
+ struct scatterlist *sg = md->sg_data;
+ int i = start, free = 0;
+
+ while (sg[i].length) {
+ free += sg[i].length;
+ if (charge)
+ sk_mem_uncharge(sk, sg[i].length);
+ if (!md->skb)
+ put_page(sg_page(&sg[i]));
+ sg[i].length = 0;
+ sg[i].page_link = 0;
+ sg[i].offset = 0;
+ i++;
+
+ if (i == MAX_SKB_FRAGS)
+ i = 0;
+ }
+ if (md->skb)
+ consume_skb(md->skb);
+
+ return free;
+}
+
+static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge)
+{
+ int free = free_sg(sk, md->sg_start, md, charge);
+
+ md->sg_start = md->sg_end;
+ return free;
+}
+
+static int free_curr_sg(struct sock *sk, struct sk_msg_buff *md)
+{
+ return free_sg(sk, md->sg_curr, md, true);
+}
+
+static int bpf_map_msg_verdict(int _rc, struct sk_msg_buff *md)
+{
+ return ((_rc == SK_PASS) ?
+ (md->sk_redir ? __SK_REDIRECT : __SK_PASS) :
+ __SK_DROP);
+}
+
+static unsigned int smap_do_tx_msg(struct sock *sk,
+ struct smap_psock *psock,
+ struct sk_msg_buff *md)
+{
+ struct bpf_prog *prog;
+ unsigned int rc, _rc;
+
+ preempt_disable();
+ rcu_read_lock();
+
+ /* If the policy was removed mid-send then default to 'accept' */
+ prog = READ_ONCE(psock->bpf_tx_msg);
+ if (unlikely(!prog)) {
+ _rc = SK_PASS;
+ goto verdict;
+ }
+
+ bpf_compute_data_pointers_sg(md);
+ md->sk = sk;
+ rc = (*prog->bpf_func)(md, prog->insnsi);
+ psock->apply_bytes = md->apply_bytes;
+
+ /* Moving return codes from UAPI namespace into internal namespace */
+ _rc = bpf_map_msg_verdict(rc, md);
+
+ /* The psock has a refcount on the sock but not on the map and because
+ * we need to drop rcu read lock here its possible the map could be
+ * removed between here and when we need it to execute the sock
+ * redirect. So do the map lookup now for future use.
+ */
+ if (_rc == __SK_REDIRECT) {
+ if (psock->sk_redir)
+ sock_put(psock->sk_redir);
+ psock->sk_redir = do_msg_redirect_map(md);
+ if (!psock->sk_redir) {
+ _rc = __SK_DROP;
+ goto verdict;
+ }
+ sock_hold(psock->sk_redir);
+ }
+verdict:
+ rcu_read_unlock();
+ preempt_enable();
+
+ return _rc;
+}
+
+static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
+ struct smap_psock *psock,
+ struct sk_msg_buff *md, int flags)
+{
+ bool apply = apply_bytes;
+ size_t size, copied = 0;
+ struct sk_msg_buff *r;
+ int err = 0, i;
+
+ r = kzalloc(sizeof(struct sk_msg_buff), __GFP_NOWARN | GFP_KERNEL);
+ if (unlikely(!r))
+ return -ENOMEM;
+
+ lock_sock(sk);
+ r->sg_start = md->sg_start;
+ i = md->sg_start;
+
+ do {
+ size = (apply && apply_bytes < md->sg_data[i].length) ?
+ apply_bytes : md->sg_data[i].length;
+
+ if (!sk_wmem_schedule(sk, size)) {
+ if (!copied)
+ err = -ENOMEM;
+ break;
+ }
+
+ sk_mem_charge(sk, size);
+ r->sg_data[i] = md->sg_data[i];
+ r->sg_data[i].length = size;
+ md->sg_data[i].length -= size;
+ md->sg_data[i].offset += size;
+ copied += size;
+
+ if (md->sg_data[i].length) {
+ get_page(sg_page(&r->sg_data[i]));
+ r->sg_end = (i + 1) == MAX_SKB_FRAGS ? 0 : i + 1;
+ } else {
+ i++;
+ if (i == MAX_SKB_FRAGS)
+ i = 0;
+ r->sg_end = i;
+ }
+
+ if (apply) {
+ apply_bytes -= size;
+ if (!apply_bytes)
+ break;
+ }
+ } while (i != md->sg_end);
+
+ md->sg_start = i;
+
+ if (!err) {
+ list_add_tail(&r->list, &psock->ingress);
+ sk->sk_data_ready(sk);
+ } else {
+ free_start_sg(sk, r, true);
+ kfree(r);
+ }
+
+ release_sock(sk);
+ return err;
+}
+
+static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
+ struct sk_msg_buff *md,
+ int flags)
+{
+ bool ingress = !!(md->flags & BPF_F_INGRESS);
+ struct smap_psock *psock;
+ int err = 0;
+
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+ if (unlikely(!psock))
+ goto out_rcu;
+
+ if (!refcount_inc_not_zero(&psock->refcnt))
+ goto out_rcu;
+
+ rcu_read_unlock();
+
+ if (ingress) {
+ err = bpf_tcp_ingress(sk, send, psock, md, flags);
+ } else {
+ lock_sock(sk);
+ err = bpf_tcp_push(sk, send, md, flags, false);
+ release_sock(sk);
+ }
+ smap_release_sock(psock, sk);
+ return err;
+out_rcu:
+ rcu_read_unlock();
+ return 0;
+}
+
+static inline void bpf_md_init(struct smap_psock *psock)
+{
+ if (!psock->apply_bytes) {
+ psock->eval = __SK_NONE;
+ if (psock->sk_redir) {
+ sock_put(psock->sk_redir);
+ psock->sk_redir = NULL;
+ }
+ }
+}
+
+static void apply_bytes_dec(struct smap_psock *psock, int i)
+{
+ if (psock->apply_bytes) {
+ if (psock->apply_bytes < i)
+ psock->apply_bytes = 0;
+ else
+ psock->apply_bytes -= i;
+ }
+}
+
+static int bpf_exec_tx_verdict(struct smap_psock *psock,
+ struct sk_msg_buff *m,
+ struct sock *sk,
+ int *copied, int flags)
+{
+ bool cork = false, enospc = (m->sg_start == m->sg_end);
+ struct sock *redir;
+ int err = 0;
+ int send;
+
+more_data:
+ if (psock->eval == __SK_NONE)
+ psock->eval = smap_do_tx_msg(sk, psock, m);
+
+ if (m->cork_bytes &&
+ m->cork_bytes > psock->sg_size && !enospc) {
+ psock->cork_bytes = m->cork_bytes - psock->sg_size;
+ if (!psock->cork) {
+ psock->cork = kcalloc(1,
+ sizeof(struct sk_msg_buff),
+ GFP_ATOMIC | __GFP_NOWARN);
+
+ if (!psock->cork) {
+ err = -ENOMEM;
+ goto out_err;
+ }
+ }
+ memcpy(psock->cork, m, sizeof(*m));
+ goto out_err;
+ }
+
+ send = psock->sg_size;
+ if (psock->apply_bytes && psock->apply_bytes < send)
+ send = psock->apply_bytes;
+
+ switch (psock->eval) {
+ case __SK_PASS:
+ err = bpf_tcp_push(sk, send, m, flags, true);
+ if (unlikely(err)) {
+ *copied -= free_start_sg(sk, m, true);
+ break;
+ }
+
+ apply_bytes_dec(psock, send);
+ psock->sg_size -= send;
+ break;
+ case __SK_REDIRECT:
+ redir = psock->sk_redir;
+ apply_bytes_dec(psock, send);
+
+ if (psock->cork) {
+ cork = true;
+ psock->cork = NULL;
+ }
+
+ return_mem_sg(sk, send, m);
+ release_sock(sk);
+
+ err = bpf_tcp_sendmsg_do_redirect(redir, send, m, flags);
+ lock_sock(sk);
+
+ if (unlikely(err < 0)) {
+ int free = free_start_sg(sk, m, false);
+
+ psock->sg_size = 0;
+ if (!cork)
+ *copied -= free;
+ } else {
+ psock->sg_size -= send;
+ }
+
+ if (cork) {
+ free_start_sg(sk, m, true);
+ psock->sg_size = 0;
+ kfree(m);
+ m = NULL;
+ err = 0;
+ }
+ break;
+ case __SK_DROP:
+ default:
+ free_bytes_sg(sk, send, m, true);
+ apply_bytes_dec(psock, send);
+ *copied -= send;
+ psock->sg_size -= send;
+ err = -EACCES;
+ break;
+ }
+
+ if (likely(!err)) {
+ bpf_md_init(psock);
+ if (m &&
+ m->sg_data[m->sg_start].page_link &&
+ m->sg_data[m->sg_start].length)
+ goto more_data;
+ }
+
+out_err:
+ return err;
+}
+
+static int bpf_wait_data(struct sock *sk,
+ struct smap_psock *psk, int flags,
+ long timeo, int *err)
+{
+ int rc;
+
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+ add_wait_queue(sk_sleep(sk), &wait);
+ sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ rc = sk_wait_event(sk, &timeo,
+ !list_empty(&psk->ingress) ||
+ !skb_queue_empty(&sk->sk_receive_queue),
+ &wait);
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ remove_wait_queue(sk_sleep(sk), &wait);
+
+ return rc;
+}
+
+static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+ int nonblock, int flags, int *addr_len)
+{
+ struct iov_iter *iter = &msg->msg_iter;
+ struct smap_psock *psock;
+ int copied = 0;
+
+ if (unlikely(flags & MSG_ERRQUEUE))
+ return inet_recv_error(sk, msg, len, addr_len);
+ if (!skb_queue_empty(&sk->sk_receive_queue))
+ return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+ if (unlikely(!psock))
+ goto out;
+
+ if (unlikely(!refcount_inc_not_zero(&psock->refcnt)))
+ goto out;
+ rcu_read_unlock();
+
+ lock_sock(sk);
+bytes_ready:
+ while (copied != len) {
+ struct scatterlist *sg;
+ struct sk_msg_buff *md;
+ int i;
+
+ md = list_first_entry_or_null(&psock->ingress,
+ struct sk_msg_buff, list);
+ if (unlikely(!md))
+ break;
+ i = md->sg_start;
+ do {
+ struct page *page;
+ int n, copy;
+
+ sg = &md->sg_data[i];
+ copy = sg->length;
+ page = sg_page(sg);
+
+ if (copied + copy > len)
+ copy = len - copied;
+
+ n = copy_page_to_iter(page, sg->offset, copy, iter);
+ if (n != copy) {
+ md->sg_start = i;
+ release_sock(sk);
+ smap_release_sock(psock, sk);
+ return -EFAULT;
+ }
+
+ copied += copy;
+ sg->offset += copy;
+ sg->length -= copy;
+ sk_mem_uncharge(sk, copy);
+
+ if (!sg->length) {
+ i++;
+ if (i == MAX_SKB_FRAGS)
+ i = 0;
+ if (!md->skb)
+ put_page(page);
+ }
+ if (copied == len)
+ break;
+ } while (i != md->sg_end);
+ md->sg_start = i;
+
+ if (!sg->length && md->sg_start == md->sg_end) {
+ list_del(&md->list);
+ if (md->skb)
+ consume_skb(md->skb);
+ kfree(md);
+ }
+ }
+
+ if (!copied) {
+ long timeo;
+ int data;
+ int err = 0;
+
+ timeo = sock_rcvtimeo(sk, nonblock);
+ data = bpf_wait_data(sk, psock, flags, timeo, &err);
+
+ if (data) {
+ if (!skb_queue_empty(&sk->sk_receive_queue)) {
+ release_sock(sk);
+ smap_release_sock(psock, sk);
+ copied = tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+ return copied;
+ }
+ goto bytes_ready;
+ }
+
+ if (err)
+ copied = err;
+ }
+
+ release_sock(sk);
+ smap_release_sock(psock, sk);
+ return copied;
+out:
+ rcu_read_unlock();
+ return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+}
+
+
+static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
+{
+ int flags = msg->msg_flags | MSG_NO_SHARED_FRAGS;
+ struct sk_msg_buff md = {0};
+ unsigned int sg_copy = 0;
+ struct smap_psock *psock;
+ int copied = 0, err = 0;
+ struct scatterlist *sg;
+ long timeo;
+
+ /* Its possible a sock event or user removed the psock _but_ the ops
+ * have not been reprogrammed yet so we get here. In this case fallback
+ * to tcp_sendmsg. Note this only works because we _only_ ever allow
+ * a single ULP there is no hierarchy here.
+ */
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+ if (unlikely(!psock)) {
+ rcu_read_unlock();
+ return tcp_sendmsg(sk, msg, size);
+ }
+
+ /* Increment the psock refcnt to ensure its not released while sending a
+ * message. Required because sk lookup and bpf programs are used in
+ * separate rcu critical sections. Its OK if we lose the map entry
+ * but we can't lose the sock reference.
+ */
+ if (!refcount_inc_not_zero(&psock->refcnt)) {
+ rcu_read_unlock();
+ return tcp_sendmsg(sk, msg, size);
+ }
+
+ sg = md.sg_data;
+ sg_init_marker(sg, MAX_SKB_FRAGS);
+ rcu_read_unlock();
+
+ lock_sock(sk);
+ timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
+
+ while (msg_data_left(msg)) {
+ struct sk_msg_buff *m = NULL;
+ bool enospc = false;
+ int copy;
+
+ if (sk->sk_err) {
+ err = -sk->sk_err;
+ goto out_err;
+ }
+
+ copy = msg_data_left(msg);
+ if (!sk_stream_memory_free(sk))
+ goto wait_for_sndbuf;
+
+ m = psock->cork_bytes ? psock->cork : &md;
+ m->sg_curr = m->sg_copybreak ? m->sg_curr : m->sg_end;
+ err = sk_alloc_sg(sk, copy, m->sg_data,
+ m->sg_start, &m->sg_end, &sg_copy,
+ m->sg_end - 1);
+ if (err) {
+ if (err != -ENOSPC)
+ goto wait_for_memory;
+ enospc = true;
+ copy = sg_copy;
+ }
+
+ err = memcopy_from_iter(sk, m, &msg->msg_iter, copy);
+ if (err < 0) {
+ free_curr_sg(sk, m);
+ goto out_err;
+ }
+
+ psock->sg_size += copy;
+ copied += copy;
+ sg_copy = 0;
+
+ /* When bytes are being corked skip running BPF program and
+ * applying verdict unless there is no more buffer space. In
+ * the ENOSPC case simply run BPF prorgram with currently
+ * accumulated data. We don't have much choice at this point
+ * we could try extending the page frags or chaining complex
+ * frags but even in these cases _eventually_ we will hit an
+ * OOM scenario. More complex recovery schemes may be
+ * implemented in the future, but BPF programs must handle
+ * the case where apply_cork requests are not honored. The
+ * canonical method to verify this is to check data length.
+ */
+ if (psock->cork_bytes) {
+ if (copy > psock->cork_bytes)
+ psock->cork_bytes = 0;
+ else
+ psock->cork_bytes -= copy;
+
+ if (psock->cork_bytes && !enospc)
+ goto out_cork;
+
+ /* All cork bytes accounted for re-run filter */
+ psock->eval = __SK_NONE;
+ psock->cork_bytes = 0;
+ }
+
+ err = bpf_exec_tx_verdict(psock, m, sk, &copied, flags);
+ if (unlikely(err < 0))
+ goto out_err;
+ continue;
+wait_for_sndbuf:
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+wait_for_memory:
+ err = sk_stream_wait_memory(sk, &timeo);
+ if (err) {
+ if (m && m != psock->cork)
+ free_start_sg(sk, m, true);
+ goto out_err;
+ }
+ }
+out_err:
+ if (err < 0)
+ err = sk_stream_error(sk, msg->msg_flags, err);
+out_cork:
+ release_sock(sk);
+ smap_release_sock(psock, sk);
+ return copied ? copied : err;
+}
+
+static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
+ int offset, size_t size, int flags)
+{
+ struct sk_msg_buff md = {0}, *m = NULL;
+ int err = 0, copied = 0;
+ struct smap_psock *psock;
+ struct scatterlist *sg;
+ bool enospc = false;
+
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+ if (unlikely(!psock))
+ goto accept;
+
+ if (!refcount_inc_not_zero(&psock->refcnt))
+ goto accept;
+ rcu_read_unlock();
+
+ lock_sock(sk);
+
+ if (psock->cork_bytes) {
+ m = psock->cork;
+ sg = &m->sg_data[m->sg_end];
+ } else {
+ m = &md;
+ sg = m->sg_data;
+ sg_init_marker(sg, MAX_SKB_FRAGS);
+ }
+
+ /* Catch case where ring is full and sendpage is stalled. */
+ if (unlikely(m->sg_end == m->sg_start &&
+ m->sg_data[m->sg_end].length))
+ goto out_err;
+
+ psock->sg_size += size;
+ sg_set_page(sg, page, size, offset);
+ get_page(page);
+ m->sg_copy[m->sg_end] = true;
+ sk_mem_charge(sk, size);
+ m->sg_end++;
+ copied = size;
+
+ if (m->sg_end == MAX_SKB_FRAGS)
+ m->sg_end = 0;
+
+ if (m->sg_end == m->sg_start)
+ enospc = true;
+
+ if (psock->cork_bytes) {
+ if (size > psock->cork_bytes)
+ psock->cork_bytes = 0;
+ else
+ psock->cork_bytes -= size;
+
+ if (psock->cork_bytes && !enospc)
+ goto out_err;
+
+ /* All cork bytes accounted for re-run filter */
+ psock->eval = __SK_NONE;
+ psock->cork_bytes = 0;
+ }
+
+ err = bpf_exec_tx_verdict(psock, m, sk, &copied, flags);
+out_err:
+ release_sock(sk);
+ smap_release_sock(psock, sk);
+ return copied ? copied : err;
+accept:
+ rcu_read_unlock();
+ return tcp_sendpage(sk, page, offset, size, flags);
+}
+
+static void bpf_tcp_msg_add(struct smap_psock *psock,
+ struct sock *sk,
+ struct bpf_prog *tx_msg)
+{
+ struct bpf_prog *orig_tx_msg;
+
+ orig_tx_msg = xchg(&psock->bpf_tx_msg, tx_msg);
+ if (orig_tx_msg)
+ bpf_prog_put(orig_tx_msg);
+}
+
+static int bpf_tcp_ulp_register(void)
+{
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot);
+ /* Once BPF TX ULP is registered it is never unregistered. It
+ * will be in the ULP list for the lifetime of the system. Doing
+ * duplicate registers is not a problem.
+ */
+ return tcp_register_ulp(&bpf_tcp_ulp_ops);
+}
+
+static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
+{
+ struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict);
+ int rc;
+
+ if (unlikely(!prog))
+ return __SK_DROP;
+
+ skb_orphan(skb);
+ /* We need to ensure that BPF metadata for maps is also cleared
+ * when we orphan the skb so that we don't have the possibility
+ * to reference a stale map.
+ */
+ TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
+ skb->sk = psock->sock;
+ bpf_compute_data_end_sk_skb(skb);
+ preempt_disable();
+ rc = (*prog->bpf_func)(skb, prog->insnsi);
+ preempt_enable();
+ skb->sk = NULL;
+
+ /* Moving return codes from UAPI namespace into internal namespace */
+ return rc == SK_PASS ?
+ (TCP_SKB_CB(skb)->bpf.sk_redir ? __SK_REDIRECT : __SK_PASS) :
+ __SK_DROP;
+}
+
+static int smap_do_ingress(struct smap_psock *psock, struct sk_buff *skb)
+{
+ struct sock *sk = psock->sock;
+ int copied = 0, num_sg;
+ struct sk_msg_buff *r;
+
+ r = kzalloc(sizeof(struct sk_msg_buff), __GFP_NOWARN | GFP_ATOMIC);
+ if (unlikely(!r))
+ return -EAGAIN;
+
+ if (!sk_rmem_schedule(sk, skb, skb->len)) {
+ kfree(r);
+ return -EAGAIN;
+ }
+
+ sg_init_table(r->sg_data, MAX_SKB_FRAGS);
+ num_sg = skb_to_sgvec(skb, r->sg_data, 0, skb->len);
+ if (unlikely(num_sg < 0)) {
+ kfree(r);
+ return num_sg;
+ }
+ sk_mem_charge(sk, skb->len);
+ copied = skb->len;
+ r->sg_start = 0;
+ r->sg_end = num_sg == MAX_SKB_FRAGS ? 0 : num_sg;
+ r->skb = skb;
+ list_add_tail(&r->list, &psock->ingress);
+ sk->sk_data_ready(sk);
+ return copied;
+}
+
+static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb)
+{
+ struct smap_psock *peer;
+ struct sock *sk;
+ __u32 in;
+ int rc;
+
+ rc = smap_verdict_func(psock, skb);
+ switch (rc) {
+ case __SK_REDIRECT:
+ sk = do_sk_redirect_map(skb);
+ if (!sk) {
+ kfree_skb(skb);
+ break;
+ }
+
+ peer = smap_psock_sk(sk);
+ in = (TCP_SKB_CB(skb)->bpf.flags) & BPF_F_INGRESS;
+
+ if (unlikely(!peer || sock_flag(sk, SOCK_DEAD) ||
+ !test_bit(SMAP_TX_RUNNING, &peer->state))) {
+ kfree_skb(skb);
+ break;
+ }
+
+ if (!in && sock_writeable(sk)) {
+ skb_set_owner_w(skb, sk);
+ skb_queue_tail(&peer->rxqueue, skb);
+ schedule_work(&peer->tx_work);
+ break;
+ } else if (in &&
+ atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) {
+ skb_queue_tail(&peer->rxqueue, skb);
+ schedule_work(&peer->tx_work);
+ break;
+ }
+ /* Fall through and free skb otherwise */
+ case __SK_DROP:
+ default:
+ kfree_skb(skb);
+ }
+}
+
+static void smap_report_sk_error(struct smap_psock *psock, int err)
+{
+ struct sock *sk = psock->sock;
+
+ sk->sk_err = err;
+ sk->sk_error_report(sk);
+}
+
+static void smap_read_sock_strparser(struct strparser *strp,
+ struct sk_buff *skb)
+{
+ struct smap_psock *psock;
+
+ rcu_read_lock();
+ psock = container_of(strp, struct smap_psock, strp);
+ smap_do_verdict(psock, skb);
+ rcu_read_unlock();
+}
+
+/* Called with lock held on socket */
+static void smap_data_ready(struct sock *sk)
+{
+ struct smap_psock *psock;
+
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+ if (likely(psock)) {
+ write_lock_bh(&sk->sk_callback_lock);
+ strp_data_ready(&psock->strp);
+ write_unlock_bh(&sk->sk_callback_lock);
+ }
+ rcu_read_unlock();
+}
+
+static void smap_tx_work(struct work_struct *w)
+{
+ struct smap_psock *psock;
+ struct sk_buff *skb;
+ int rem, off, n;
+
+ psock = container_of(w, struct smap_psock, tx_work);
+
+ /* lock sock to avoid losing sk_socket at some point during loop */
+ lock_sock(psock->sock);
+ if (psock->save_skb) {
+ skb = psock->save_skb;
+ rem = psock->save_rem;
+ off = psock->save_off;
+ psock->save_skb = NULL;
+ goto start;
+ }
+
+ while ((skb = skb_dequeue(&psock->rxqueue))) {
+ __u32 flags;
+
+ rem = skb->len;
+ off = 0;
+start:
+ flags = (TCP_SKB_CB(skb)->bpf.flags) & BPF_F_INGRESS;
+ do {
+ if (likely(psock->sock->sk_socket)) {
+ if (flags)
+ n = smap_do_ingress(psock, skb);
+ else
+ n = skb_send_sock_locked(psock->sock,
+ skb, off, rem);
+ } else {
+ n = -EINVAL;
+ }
+
+ if (n <= 0) {
+ if (n == -EAGAIN) {
+ /* Retry when space is available */
+ psock->save_skb = skb;
+ psock->save_rem = rem;
+ psock->save_off = off;
+ goto out;
+ }
+ /* Hard errors break pipe and stop xmit */
+ smap_report_sk_error(psock, n ? -n : EPIPE);
+ clear_bit(SMAP_TX_RUNNING, &psock->state);
+ kfree_skb(skb);
+ goto out;
+ }
+ rem -= n;
+ off += n;
+ } while (rem);
+
+ if (!flags)
+ kfree_skb(skb);
+ }
+out:
+ release_sock(psock->sock);
+}
+
+static void smap_write_space(struct sock *sk)
+{
+ struct smap_psock *psock;
+ void (*write_space)(struct sock *sk);
+
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+ if (likely(psock && test_bit(SMAP_TX_RUNNING, &psock->state)))
+ schedule_work(&psock->tx_work);
+ write_space = psock->save_write_space;
+ rcu_read_unlock();
+ write_space(sk);
+}
+
+static void smap_stop_sock(struct smap_psock *psock, struct sock *sk)
+{
+ if (!psock->strp_enabled)
+ return;
+ sk->sk_data_ready = psock->save_data_ready;
+ sk->sk_write_space = psock->save_write_space;
+ psock->save_data_ready = NULL;
+ psock->save_write_space = NULL;
+ strp_stop(&psock->strp);
+ psock->strp_enabled = false;
+}
+
+static void smap_destroy_psock(struct rcu_head *rcu)
+{
+ struct smap_psock *psock = container_of(rcu,
+ struct smap_psock, rcu);
+
+ /* Now that a grace period has passed there is no longer
+ * any reference to this sock in the sockmap so we can
+ * destroy the psock, strparser, and bpf programs. But,
+ * because we use workqueue sync operations we can not
+ * do it in rcu context
+ */
+ schedule_work(&psock->gc_work);
+}
+
+static bool psock_is_smap_sk(struct sock *sk)
+{
+ return inet_csk(sk)->icsk_ulp_ops == &bpf_tcp_ulp_ops;
+}
+
+static void smap_release_sock(struct smap_psock *psock, struct sock *sock)
+{
+ if (refcount_dec_and_test(&psock->refcnt)) {
+ if (psock_is_smap_sk(sock))
+ tcp_cleanup_ulp(sock);
+ write_lock_bh(&sock->sk_callback_lock);
+ smap_stop_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
+ clear_bit(SMAP_TX_RUNNING, &psock->state);
+ rcu_assign_sk_user_data(sock, NULL);
+ call_rcu_sched(&psock->rcu, smap_destroy_psock);
+ }
+}
+
+static int smap_parse_func_strparser(struct strparser *strp,
+ struct sk_buff *skb)
+{
+ struct smap_psock *psock;
+ struct bpf_prog *prog;
+ int rc;
+
+ rcu_read_lock();
+ psock = container_of(strp, struct smap_psock, strp);
+ prog = READ_ONCE(psock->bpf_parse);
+
+ if (unlikely(!prog)) {
+ rcu_read_unlock();
+ return skb->len;
+ }
+
+ /* Attach socket for bpf program to use if needed we can do this
+ * because strparser clones the skb before handing it to a upper
+ * layer, meaning skb_orphan has been called. We NULL sk on the
+ * way out to ensure we don't trigger a BUG_ON in skb/sk operations
+ * later and because we are not charging the memory of this skb to
+ * any socket yet.
+ */
+ skb->sk = psock->sock;
+ bpf_compute_data_end_sk_skb(skb);
+ rc = (*prog->bpf_func)(skb, prog->insnsi);
+ skb->sk = NULL;
+ rcu_read_unlock();
+ return rc;
+}
+
+static int smap_read_sock_done(struct strparser *strp, int err)
+{
+ return err;
+}
+
+static int smap_init_sock(struct smap_psock *psock,
+ struct sock *sk)
+{
+ static const struct strp_callbacks cb = {
+ .rcv_msg = smap_read_sock_strparser,
+ .parse_msg = smap_parse_func_strparser,
+ .read_sock_done = smap_read_sock_done,
+ };
+
+ return strp_init(&psock->strp, sk, &cb);
+}
+
+static void smap_init_progs(struct smap_psock *psock,
+ struct bpf_prog *verdict,
+ struct bpf_prog *parse)
+{
+ struct bpf_prog *orig_parse, *orig_verdict;
+
+ orig_parse = xchg(&psock->bpf_parse, parse);
+ orig_verdict = xchg(&psock->bpf_verdict, verdict);
+
+ if (orig_verdict)
+ bpf_prog_put(orig_verdict);
+ if (orig_parse)
+ bpf_prog_put(orig_parse);
+}
+
+static void smap_start_sock(struct smap_psock *psock, struct sock *sk)
+{
+ if (sk->sk_data_ready == smap_data_ready)
+ return;
+ psock->save_data_ready = sk->sk_data_ready;
+ psock->save_write_space = sk->sk_write_space;
+ sk->sk_data_ready = smap_data_ready;
+ sk->sk_write_space = smap_write_space;
+ psock->strp_enabled = true;
+}
+
+static void sock_map_remove_complete(struct bpf_stab *stab)
+{
+ bpf_map_area_free(stab->sock_map);
+ kfree(stab);
+}
+
+static void smap_gc_work(struct work_struct *w)
+{
+ struct smap_psock_map_entry *e, *tmp;
+ struct sk_msg_buff *md, *mtmp;
+ struct smap_psock *psock;
+
+ psock = container_of(w, struct smap_psock, gc_work);
+
+ /* no callback lock needed because we already detached sockmap ops */
+ if (psock->strp_enabled)
+ strp_done(&psock->strp);
+
+ cancel_work_sync(&psock->tx_work);
+ __skb_queue_purge(&psock->rxqueue);
+
+ /* At this point all strparser and xmit work must be complete */
+ if (psock->bpf_parse)
+ bpf_prog_put(psock->bpf_parse);
+ if (psock->bpf_verdict)
+ bpf_prog_put(psock->bpf_verdict);
+ if (psock->bpf_tx_msg)
+ bpf_prog_put(psock->bpf_tx_msg);
+
+ if (psock->cork) {
+ free_start_sg(psock->sock, psock->cork, true);
+ kfree(psock->cork);
+ }
+
+ list_for_each_entry_safe(md, mtmp, &psock->ingress, list) {
+ list_del(&md->list);
+ free_start_sg(psock->sock, md, true);
+ kfree(md);
+ }
+
+ list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ list_del(&e->list);
+ kfree(e);
+ }
+
+ if (psock->sk_redir)
+ sock_put(psock->sk_redir);
+
+ sock_put(psock->sock);
+ kfree(psock);
+}
+
+static struct smap_psock *smap_init_psock(struct sock *sock, int node)
+{
+ struct smap_psock *psock;
+
+ psock = kzalloc_node(sizeof(struct smap_psock),
+ GFP_ATOMIC | __GFP_NOWARN,
+ node);
+ if (!psock)
+ return ERR_PTR(-ENOMEM);
+
+ psock->eval = __SK_NONE;
+ psock->sock = sock;
+ skb_queue_head_init(&psock->rxqueue);
+ INIT_WORK(&psock->tx_work, smap_tx_work);
+ INIT_WORK(&psock->gc_work, smap_gc_work);
+ INIT_LIST_HEAD(&psock->maps);
+ INIT_LIST_HEAD(&psock->ingress);
+ refcount_set(&psock->refcnt, 1);
+ spin_lock_init(&psock->maps_lock);
+
+ rcu_assign_sk_user_data(sock, psock);
+ sock_hold(sock);
+ return psock;
+}
+
+static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
+{
+ struct bpf_stab *stab;
+ u64 cost;
+ int err;
+
+ 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 & ~SOCK_CREATE_FLAG_MASK)
+ return ERR_PTR(-EINVAL);
+
+ err = bpf_tcp_ulp_register();
+ if (err && err != -EEXIST)
+ return ERR_PTR(err);
+
+ stab = kzalloc(sizeof(*stab), GFP_USER);
+ if (!stab)
+ return ERR_PTR(-ENOMEM);
+
+ bpf_map_init_from_attr(&stab->map, attr);
+ raw_spin_lock_init(&stab->lock);
+
+ /* make sure page count doesn't overflow */
+ cost = (u64) stab->map.max_entries * sizeof(struct sock *);
+ err = -EINVAL;
+ if (cost >= U32_MAX - PAGE_SIZE)
+ goto free_stab;
+
+ stab->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(stab->map.pages);
+ if (err)
+ goto free_stab;
+
+ err = -ENOMEM;
+ stab->sock_map = bpf_map_area_alloc(stab->map.max_entries *
+ sizeof(struct sock *),
+ stab->map.numa_node);
+ if (!stab->sock_map)
+ goto free_stab;
+
+ return &stab->map;
+free_stab:
+ kfree(stab);
+ return ERR_PTR(err);
+}
+
+static void smap_list_map_remove(struct smap_psock *psock,
+ struct sock **entry)
+{
+ struct smap_psock_map_entry *e, *tmp;
+
+ spin_lock_bh(&psock->maps_lock);
+ list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ if (e->entry == entry) {
+ list_del(&e->list);
+ kfree(e);
+ }
+ }
+ spin_unlock_bh(&psock->maps_lock);
+}
+
+static void smap_list_hash_remove(struct smap_psock *psock,
+ struct htab_elem *hash_link)
+{
+ struct smap_psock_map_entry *e, *tmp;
+
+ spin_lock_bh(&psock->maps_lock);
+ list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ struct htab_elem *c = rcu_dereference(e->hash_link);
+
+ if (c == hash_link) {
+ list_del(&e->list);
+ kfree(e);
+ }
+ }
+ spin_unlock_bh(&psock->maps_lock);
+}
+
+static void sock_map_free(struct bpf_map *map)
+{
+ struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+ int i;
+
+ synchronize_rcu();
+
+ /* At this point no update, lookup or delete operations can happen.
+ * However, be aware we can still get a socket state event updates,
+ * and data ready callabacks that reference the psock from sk_user_data
+ * Also psock worker threads are still in-flight. So smap_release_sock
+ * will only free the psock after cancel_sync on the worker threads
+ * and a grace period expire to ensure psock is really safe to remove.
+ */
+ rcu_read_lock();
+ raw_spin_lock_bh(&stab->lock);
+ for (i = 0; i < stab->map.max_entries; i++) {
+ struct smap_psock *psock;
+ struct sock *sock;
+
+ sock = stab->sock_map[i];
+ if (!sock)
+ continue;
+ stab->sock_map[i] = NULL;
+ psock = smap_psock_sk(sock);
+ /* This check handles a racing sock event that can get the
+ * sk_callback_lock before this case but after xchg happens
+ * causing the refcnt to hit zero and sock user data (psock)
+ * to be null and queued for garbage collection.
+ */
+ if (likely(psock)) {
+ smap_list_map_remove(psock, &stab->sock_map[i]);
+ smap_release_sock(psock, sock);
+ }
+ }
+ raw_spin_unlock_bh(&stab->lock);
+ rcu_read_unlock();
+
+ sock_map_remove_complete(stab);
+}
+
+static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+ struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+ u32 i = key ? *(u32 *)key : U32_MAX;
+ u32 *next = (u32 *)next_key;
+
+ if (i >= stab->map.max_entries) {
+ *next = 0;
+ return 0;
+ }
+
+ if (i == stab->map.max_entries - 1)
+ return -ENOENT;
+
+ *next = i + 1;
+ return 0;
+}
+
+struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+ struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+
+ if (key >= map->max_entries)
+ return NULL;
+
+ return READ_ONCE(stab->sock_map[key]);
+}
+
+static int sock_map_delete_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+ struct smap_psock *psock;
+ int k = *(u32 *)key;
+ struct sock *sock;
+
+ if (k >= map->max_entries)
+ return -EINVAL;
+
+ raw_spin_lock_bh(&stab->lock);
+ sock = stab->sock_map[k];
+ stab->sock_map[k] = NULL;
+ raw_spin_unlock_bh(&stab->lock);
+ if (!sock)
+ return -EINVAL;
+
+ psock = smap_psock_sk(sock);
+ if (!psock)
+ return 0;
+ if (psock->bpf_parse) {
+ write_lock_bh(&sock->sk_callback_lock);
+ smap_stop_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
+ }
+ smap_list_map_remove(psock, &stab->sock_map[k]);
+ smap_release_sock(psock, sock);
+ return 0;
+}
+
+/* Locking notes: Concurrent updates, deletes, and lookups are allowed and are
+ * done inside rcu critical sections. This ensures on updates that the psock
+ * will not be released via smap_release_sock() until concurrent updates/deletes
+ * complete. All operations operate on sock_map using cmpxchg and xchg
+ * operations to ensure we do not get stale references. Any reads into the
+ * map must be done with READ_ONCE() because of this.
+ *
+ * A psock is destroyed via call_rcu and after any worker threads are cancelled
+ * and syncd so we are certain all references from the update/lookup/delete
+ * operations as well as references in the data path are no longer in use.
+ *
+ * Psocks may exist in multiple maps, but only a single set of parse/verdict
+ * programs may be inherited from the maps it belongs to. A reference count
+ * is kept with the total number of references to the psock from all maps. The
+ * psock will not be released until this reaches zero. The psock and sock
+ * user data data use the sk_callback_lock to protect critical data structures
+ * from concurrent access. This allows us to avoid two updates from modifying
+ * the user data in sock and the lock is required anyways for modifying
+ * callbacks, we simply increase its scope slightly.
+ *
+ * Rules to follow,
+ * - psock must always be read inside RCU critical section
+ * - sk_user_data must only be modified inside sk_callback_lock and read
+ * inside RCU critical section.
+ * - psock->maps list must only be read & modified inside sk_callback_lock
+ * - sock_map must use READ_ONCE and (cmp)xchg operations
+ * - BPF verdict/parse programs must use READ_ONCE and xchg operations
+ */
+
+static int __sock_map_ctx_update_elem(struct bpf_map *map,
+ struct bpf_sock_progs *progs,
+ struct sock *sock,
+ void *key)
+{
+ struct bpf_prog *verdict, *parse, *tx_msg;
+ struct smap_psock *psock;
+ bool new = false;
+ int err = 0;
+
+ /* 1. If sock map has BPF programs those will be inherited by the
+ * sock being added. If the sock is already attached to BPF programs
+ * this results in an error.
+ */
+ verdict = READ_ONCE(progs->bpf_verdict);
+ parse = READ_ONCE(progs->bpf_parse);
+ tx_msg = READ_ONCE(progs->bpf_tx_msg);
+
+ if (parse && verdict) {
+ /* bpf prog refcnt may be zero if a concurrent attach operation
+ * removes the program after the above READ_ONCE() but before
+ * we increment the refcnt. If this is the case abort with an
+ * error.
+ */
+ verdict = bpf_prog_inc_not_zero(verdict);
+ if (IS_ERR(verdict))
+ return PTR_ERR(verdict);
+
+ parse = bpf_prog_inc_not_zero(parse);
+ if (IS_ERR(parse)) {
+ bpf_prog_put(verdict);
+ return PTR_ERR(parse);
+ }
+ }
+
+ if (tx_msg) {
+ tx_msg = bpf_prog_inc_not_zero(tx_msg);
+ if (IS_ERR(tx_msg)) {
+ if (parse && verdict) {
+ bpf_prog_put(parse);
+ bpf_prog_put(verdict);
+ }
+ return PTR_ERR(tx_msg);
+ }
+ }
+
+ psock = smap_psock_sk(sock);
+
+ /* 2. Do not allow inheriting programs if psock exists and has
+ * already inherited programs. This would create confusion on
+ * which parser/verdict program is running. If no psock exists
+ * create one. Inside sk_callback_lock to ensure concurrent create
+ * doesn't update user data.
+ */
+ if (psock) {
+ if (!psock_is_smap_sk(sock)) {
+ err = -EBUSY;
+ goto out_progs;
+ }
+ if (READ_ONCE(psock->bpf_parse) && parse) {
+ err = -EBUSY;
+ goto out_progs;
+ }
+ if (READ_ONCE(psock->bpf_tx_msg) && tx_msg) {
+ err = -EBUSY;
+ goto out_progs;
+ }
+ if (!refcount_inc_not_zero(&psock->refcnt)) {
+ err = -EAGAIN;
+ goto out_progs;
+ }
+ } else {
+ psock = smap_init_psock(sock, map->numa_node);
+ if (IS_ERR(psock)) {
+ err = PTR_ERR(psock);
+ goto out_progs;
+ }
+
+ set_bit(SMAP_TX_RUNNING, &psock->state);
+ new = true;
+ }
+
+ /* 3. At this point we have a reference to a valid psock that is
+ * running. Attach any BPF programs needed.
+ */
+ if (tx_msg)
+ bpf_tcp_msg_add(psock, sock, tx_msg);
+ if (new) {
+ err = tcp_set_ulp_id(sock, TCP_ULP_BPF);
+ if (err)
+ goto out_free;
+ }
+
+ if (parse && verdict && !psock->strp_enabled) {
+ err = smap_init_sock(psock, sock);
+ if (err)
+ goto out_free;
+ smap_init_progs(psock, verdict, parse);
+ write_lock_bh(&sock->sk_callback_lock);
+ smap_start_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
+ }
+
+ return err;
+out_free:
+ smap_release_sock(psock, sock);
+out_progs:
+ if (parse && verdict) {
+ bpf_prog_put(parse);
+ bpf_prog_put(verdict);
+ }
+ if (tx_msg)
+ bpf_prog_put(tx_msg);
+ return err;
+}
+
+static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
+ struct bpf_map *map,
+ void *key, u64 flags)
+{
+ struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+ struct bpf_sock_progs *progs = &stab->progs;
+ struct sock *osock, *sock = skops->sk;
+ struct smap_psock_map_entry *e;
+ struct smap_psock *psock;
+ u32 i = *(u32 *)key;
+ int err;
+
+ if (unlikely(flags > BPF_EXIST))
+ return -EINVAL;
+ if (unlikely(i >= stab->map.max_entries))
+ return -E2BIG;
+
+ e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
+ if (!e)
+ return -ENOMEM;
+
+ err = __sock_map_ctx_update_elem(map, progs, sock, key);
+ if (err)
+ goto out;
+
+ /* psock guaranteed to be present. */
+ psock = smap_psock_sk(sock);
+ raw_spin_lock_bh(&stab->lock);
+ osock = stab->sock_map[i];
+ if (osock && flags == BPF_NOEXIST) {
+ err = -EEXIST;
+ goto out_unlock;
+ }
+ if (!osock && flags == BPF_EXIST) {
+ err = -ENOENT;
+ goto out_unlock;
+ }
+
+ e->entry = &stab->sock_map[i];
+ e->map = map;
+ spin_lock_bh(&psock->maps_lock);
+ list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
+
+ stab->sock_map[i] = sock;
+ if (osock) {
+ psock = smap_psock_sk(osock);
+ smap_list_map_remove(psock, &stab->sock_map[i]);
+ smap_release_sock(psock, osock);
+ }
+ raw_spin_unlock_bh(&stab->lock);
+ return 0;
+out_unlock:
+ smap_release_sock(psock, sock);
+ raw_spin_unlock_bh(&stab->lock);
+out:
+ kfree(e);
+ return err;
+}
+
+int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type)
+{
+ struct bpf_sock_progs *progs;
+ struct bpf_prog *orig;
+
+ if (map->map_type == BPF_MAP_TYPE_SOCKMAP) {
+ struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+
+ progs = &stab->progs;
+ } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH) {
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+
+ progs = &htab->progs;
+ } else {
+ return -EINVAL;
+ }
+
+ switch (type) {
+ case BPF_SK_MSG_VERDICT:
+ orig = xchg(&progs->bpf_tx_msg, prog);
+ break;
+ case BPF_SK_SKB_STREAM_PARSER:
+ orig = xchg(&progs->bpf_parse, prog);
+ break;
+ case BPF_SK_SKB_STREAM_VERDICT:
+ orig = xchg(&progs->bpf_verdict, prog);
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ if (orig)
+ bpf_prog_put(orig);
+
+ return 0;
+}
+
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+ struct bpf_prog *prog)
+{
+ int ufd = attr->target_fd;
+ struct bpf_map *map;
+ struct fd f;
+ int err;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ err = sock_map_prog(map, prog, attr->attach_type);
+ fdput(f);
+ return err;
+}
+
+static void *sock_map_lookup(struct bpf_map *map, void *key)
+{
+ return NULL;
+}
+
+static int sock_map_update_elem(struct bpf_map *map,
+ void *key, void *value, u64 flags)
+{
+ struct bpf_sock_ops_kern skops;
+ u32 fd = *(u32 *)value;
+ struct socket *socket;
+ int err;
+
+ socket = sockfd_lookup(fd, &err);
+ if (!socket)
+ return err;
+
+ skops.sk = socket->sk;
+ if (!skops.sk) {
+ fput(socket->file);
+ return -EINVAL;
+ }
+
+ /* ULPs are currently supported only for TCP sockets in ESTABLISHED
+ * state.
+ */
+ if (skops.sk->sk_type != SOCK_STREAM ||
+ skops.sk->sk_protocol != IPPROTO_TCP ||
+ skops.sk->sk_state != TCP_ESTABLISHED) {
+ fput(socket->file);
+ return -EOPNOTSUPP;
+ }
+
+ lock_sock(skops.sk);
+ preempt_disable();
+ rcu_read_lock();
+ err = sock_map_ctx_update_elem(&skops, map, key, flags);
+ rcu_read_unlock();
+ preempt_enable();
+ release_sock(skops.sk);
+ fput(socket->file);
+ return err;
+}
+
+static void sock_map_release(struct bpf_map *map)
+{
+ struct bpf_sock_progs *progs;
+ struct bpf_prog *orig;
+
+ if (map->map_type == BPF_MAP_TYPE_SOCKMAP) {
+ struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+
+ progs = &stab->progs;
+ } else {
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+
+ progs = &htab->progs;
+ }
+
+ orig = xchg(&progs->bpf_parse, NULL);
+ if (orig)
+ bpf_prog_put(orig);
+ orig = xchg(&progs->bpf_verdict, NULL);
+ if (orig)
+ bpf_prog_put(orig);
+
+ orig = xchg(&progs->bpf_tx_msg, NULL);
+ if (orig)
+ bpf_prog_put(orig);
+}
+
+static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
+{
+ struct bpf_htab *htab;
+ int i, err;
+ u64 cost;
+
+ if (!capable(CAP_NET_ADMIN))
+ return ERR_PTR(-EPERM);
+
+ /* check sanity of attributes */
+ if (attr->max_entries == 0 ||
+ attr->key_size == 0 ||
+ attr->value_size != 4 ||
+ attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
+ return ERR_PTR(-EINVAL);
+
+ if (attr->key_size > MAX_BPF_STACK)
+ /* eBPF programs initialize keys on stack, so they cannot be
+ * larger than max stack size
+ */
+ return ERR_PTR(-E2BIG);
+
+ err = bpf_tcp_ulp_register();
+ if (err && err != -EEXIST)
+ return ERR_PTR(err);
+
+ htab = kzalloc(sizeof(*htab), GFP_USER);
+ if (!htab)
+ return ERR_PTR(-ENOMEM);
+
+ bpf_map_init_from_attr(&htab->map, attr);
+
+ htab->n_buckets = roundup_pow_of_two(htab->map.max_entries);
+ htab->elem_size = sizeof(struct htab_elem) +
+ round_up(htab->map.key_size, 8);
+ err = -EINVAL;
+ if (htab->n_buckets == 0 ||
+ htab->n_buckets > U32_MAX / sizeof(struct bucket))
+ goto free_htab;
+
+ cost = (u64) htab->n_buckets * sizeof(struct bucket) +
+ (u64) htab->elem_size * htab->map.max_entries;
+
+ if (cost >= U32_MAX - PAGE_SIZE)
+ goto free_htab;
+
+ htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+ err = bpf_map_precharge_memlock(htab->map.pages);
+ if (err)
+ goto free_htab;
+
+ err = -ENOMEM;
+ htab->buckets = bpf_map_area_alloc(
+ htab->n_buckets * sizeof(struct bucket),
+ htab->map.numa_node);
+ if (!htab->buckets)
+ goto free_htab;
+
+ for (i = 0; i < htab->n_buckets; i++) {
+ INIT_HLIST_HEAD(&htab->buckets[i].head);
+ raw_spin_lock_init(&htab->buckets[i].lock);
+ }
+
+ return &htab->map;
+free_htab:
+ kfree(htab);
+ return ERR_PTR(err);
+}
+
+static void __bpf_htab_free(struct rcu_head *rcu)
+{
+ struct bpf_htab *htab;
+
+ htab = container_of(rcu, struct bpf_htab, rcu);
+ bpf_map_area_free(htab->buckets);
+ kfree(htab);
+}
+
+static void sock_hash_free(struct bpf_map *map)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ int i;
+
+ synchronize_rcu();
+
+ /* At this point no update, lookup or delete operations can happen.
+ * However, be aware we can still get a socket state event updates,
+ * and data ready callabacks that reference the psock from sk_user_data
+ * Also psock worker threads are still in-flight. So smap_release_sock
+ * will only free the psock after cancel_sync on the worker threads
+ * and a grace period expire to ensure psock is really safe to remove.
+ */
+ rcu_read_lock();
+ for (i = 0; i < htab->n_buckets; i++) {
+ struct bucket *b = __select_bucket(htab, i);
+ struct hlist_head *head;
+ struct hlist_node *n;
+ struct htab_elem *l;
+
+ raw_spin_lock_bh(&b->lock);
+ head = &b->head;
+ hlist_for_each_entry_safe(l, n, head, hash_node) {
+ struct sock *sock = l->sk;
+ struct smap_psock *psock;
+
+ hlist_del_rcu(&l->hash_node);
+ psock = smap_psock_sk(sock);
+ /* This check handles a racing sock event that can get
+ * the sk_callback_lock before this case but after xchg
+ * causing the refcnt to hit zero and sock user data
+ * (psock) to be null and queued for garbage collection.
+ */
+ if (likely(psock)) {
+ smap_list_hash_remove(psock, l);
+ smap_release_sock(psock, sock);
+ }
+ free_htab_elem(htab, l);
+ }
+ raw_spin_unlock_bh(&b->lock);
+ }
+ rcu_read_unlock();
+ call_rcu(&htab->rcu, __bpf_htab_free);
+}
+
+static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
+ void *key, u32 key_size, u32 hash,
+ struct sock *sk,
+ struct htab_elem *old_elem)
+{
+ struct htab_elem *l_new;
+
+ if (atomic_inc_return(&htab->count) > htab->map.max_entries) {
+ if (!old_elem) {
+ atomic_dec(&htab->count);
+ return ERR_PTR(-E2BIG);
+ }
+ }
+ l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
+ htab->map.numa_node);
+ if (!l_new) {
+ atomic_dec(&htab->count);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ memcpy(l_new->key, key, key_size);
+ l_new->sk = sk;
+ l_new->hash = hash;
+ return l_new;
+}
+
+static inline u32 htab_map_hash(const void *key, u32 key_len)
+{
+ return jhash(key, key_len, 0);
+}
+
+static int sock_hash_get_next_key(struct bpf_map *map,
+ void *key, void *next_key)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct htab_elem *l, *next_l;
+ struct hlist_head *h;
+ u32 hash, key_size;
+ int i = 0;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ key_size = map->key_size;
+ if (!key)
+ goto find_first_elem;
+ hash = htab_map_hash(key, key_size);
+ h = select_bucket(htab, hash);
+
+ l = lookup_elem_raw(h, hash, key, key_size);
+ if (!l)
+ goto find_first_elem;
+ next_l = hlist_entry_safe(
+ rcu_dereference_raw(hlist_next_rcu(&l->hash_node)),
+ struct htab_elem, hash_node);
+ if (next_l) {
+ memcpy(next_key, next_l->key, key_size);
+ return 0;
+ }
+
+ /* no more elements in this hash list, go to the next bucket */
+ i = hash & (htab->n_buckets - 1);
+ i++;
+
+find_first_elem:
+ /* iterate over buckets */
+ for (; i < htab->n_buckets; i++) {
+ h = select_bucket(htab, i);
+
+ /* pick first element in the bucket */
+ next_l = hlist_entry_safe(
+ rcu_dereference_raw(hlist_first_rcu(h)),
+ struct htab_elem, hash_node);
+ if (next_l) {
+ /* if it's not empty, just return it */
+ memcpy(next_key, next_l->key, key_size);
+ return 0;
+ }
+ }
+
+ /* iterated over all buckets and all elements */
+ return -ENOENT;
+}
+
+static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
+ struct bpf_map *map,
+ void *key, u64 map_flags)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct bpf_sock_progs *progs = &htab->progs;
+ struct htab_elem *l_new = NULL, *l_old;
+ struct smap_psock_map_entry *e = NULL;
+ struct hlist_head *head;
+ struct smap_psock *psock;
+ u32 key_size, hash;
+ struct sock *sock;
+ struct bucket *b;
+ int err;
+
+ sock = skops->sk;
+
+ if (sock->sk_type != SOCK_STREAM ||
+ sock->sk_protocol != IPPROTO_TCP)
+ return -EOPNOTSUPP;
+
+ if (unlikely(map_flags > BPF_EXIST))
+ return -EINVAL;
+
+ e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
+ if (!e)
+ return -ENOMEM;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ key_size = map->key_size;
+ hash = htab_map_hash(key, key_size);
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ err = __sock_map_ctx_update_elem(map, progs, sock, key);
+ if (err)
+ goto err;
+
+ /* psock is valid here because otherwise above *ctx_update_elem would
+ * have thrown an error. It is safe to skip error check.
+ */
+ psock = smap_psock_sk(sock);
+ raw_spin_lock_bh(&b->lock);
+ l_old = lookup_elem_raw(head, hash, key, key_size);
+ if (l_old && map_flags == BPF_NOEXIST) {
+ err = -EEXIST;
+ goto bucket_err;
+ }
+ if (!l_old && map_flags == BPF_EXIST) {
+ err = -ENOENT;
+ goto bucket_err;
+ }
+
+ l_new = alloc_sock_hash_elem(htab, key, key_size, hash, sock, l_old);
+ if (IS_ERR(l_new)) {
+ err = PTR_ERR(l_new);
+ goto bucket_err;
+ }
+
+ rcu_assign_pointer(e->hash_link, l_new);
+ e->map = map;
+ spin_lock_bh(&psock->maps_lock);
+ list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
+
+ /* add new element to the head of the list, so that
+ * concurrent search will find it before old elem
+ */
+ hlist_add_head_rcu(&l_new->hash_node, head);
+ if (l_old) {
+ psock = smap_psock_sk(l_old->sk);
+
+ hlist_del_rcu(&l_old->hash_node);
+ smap_list_hash_remove(psock, l_old);
+ smap_release_sock(psock, l_old->sk);
+ free_htab_elem(htab, l_old);
+ }
+ raw_spin_unlock_bh(&b->lock);
+ return 0;
+bucket_err:
+ smap_release_sock(psock, sock);
+ raw_spin_unlock_bh(&b->lock);
+err:
+ kfree(e);
+ return err;
+}
+
+static int sock_hash_update_elem(struct bpf_map *map,
+ void *key, void *value, u64 flags)
+{
+ struct bpf_sock_ops_kern skops;
+ u32 fd = *(u32 *)value;
+ struct socket *socket;
+ int err;
+
+ socket = sockfd_lookup(fd, &err);
+ if (!socket)
+ return err;
+
+ skops.sk = socket->sk;
+ if (!skops.sk) {
+ fput(socket->file);
+ return -EINVAL;
+ }
+
+ /* ULPs are currently supported only for TCP sockets in ESTABLISHED
+ * state.
+ */
+ if (skops.sk->sk_type != SOCK_STREAM ||
+ skops.sk->sk_protocol != IPPROTO_TCP ||
+ skops.sk->sk_state != TCP_ESTABLISHED) {
+ fput(socket->file);
+ return -EOPNOTSUPP;
+ }
+
+ lock_sock(skops.sk);
+ preempt_disable();
+ rcu_read_lock();
+ err = sock_hash_ctx_update_elem(&skops, map, key, flags);
+ rcu_read_unlock();
+ preempt_enable();
+ release_sock(skops.sk);
+ fput(socket->file);
+ return err;
+}
+
+static int sock_hash_delete_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct hlist_head *head;
+ struct bucket *b;
+ struct htab_elem *l;
+ u32 hash, key_size;
+ int ret = -ENOENT;
+
+ key_size = map->key_size;
+ hash = htab_map_hash(key, key_size);
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ raw_spin_lock_bh(&b->lock);
+ l = lookup_elem_raw(head, hash, key, key_size);
+ if (l) {
+ struct sock *sock = l->sk;
+ struct smap_psock *psock;
+
+ hlist_del_rcu(&l->hash_node);
+ psock = smap_psock_sk(sock);
+ /* This check handles a racing sock event that can get the
+ * sk_callback_lock before this case but after xchg happens
+ * causing the refcnt to hit zero and sock user data (psock)
+ * to be null and queued for garbage collection.
+ */
+ if (likely(psock)) {
+ smap_list_hash_remove(psock, l);
+ smap_release_sock(psock, sock);
+ }
+ free_htab_elem(htab, l);
+ ret = 0;
+ }
+ raw_spin_unlock_bh(&b->lock);
+ return ret;
+}
+
+struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct hlist_head *head;
+ struct htab_elem *l;
+ u32 key_size, hash;
+ struct bucket *b;
+ struct sock *sk;
+
+ key_size = map->key_size;
+ hash = htab_map_hash(key, key_size);
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ l = lookup_elem_raw(head, hash, key, key_size);
+ sk = l ? l->sk : NULL;
+ return sk;
+}
+
+const struct bpf_map_ops sock_map_ops = {
+ .map_alloc = sock_map_alloc,
+ .map_free = sock_map_free,
+ .map_lookup_elem = sock_map_lookup,
+ .map_get_next_key = sock_map_get_next_key,
+ .map_update_elem = sock_map_update_elem,
+ .map_delete_elem = sock_map_delete_elem,
+ .map_release_uref = sock_map_release,
+ .map_check_btf = map_check_no_btf,
+};
+
+const struct bpf_map_ops sock_hash_ops = {
+ .map_alloc = sock_hash_alloc,
+ .map_free = sock_hash_free,
+ .map_lookup_elem = sock_map_lookup,
+ .map_get_next_key = sock_hash_get_next_key,
+ .map_update_elem = sock_hash_update_elem,
+ .map_delete_elem = sock_hash_delete_elem,
+ .map_release_uref = sock_map_release,
+ .map_check_btf = map_check_no_btf,
+};
+
+static bool bpf_is_valid_sock_op(struct bpf_sock_ops_kern *ops)
+{
+ return ops->op == BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB ||
+ ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB;
+}
+BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
+ struct bpf_map *, map, void *, key, u64, flags)
+{
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ /* ULPs are currently supported only for TCP sockets in ESTABLISHED
+ * state. This checks that the sock ops triggering the update is
+ * one indicating we are (or will be soon) in an ESTABLISHED state.
+ */
+ if (!bpf_is_valid_sock_op(bpf_sock))
+ return -EOPNOTSUPP;
+ return sock_map_ctx_update_elem(bpf_sock, map, key, flags);
+}
+
+const struct bpf_func_proto bpf_sock_map_update_proto = {
+ .func = bpf_sock_map_update,
+ .gpl_only = false,
+ .pkt_access = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_PTR_TO_MAP_KEY,
+ .arg4_type = ARG_ANYTHING,
+};
+
+BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, bpf_sock,
+ struct bpf_map *, map, void *, key, u64, flags)
+{
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ if (!bpf_is_valid_sock_op(bpf_sock))
+ return -EOPNOTSUPP;
+ return sock_hash_ctx_update_elem(bpf_sock, map, key, flags);
+}
+
+const struct bpf_func_proto bpf_sock_hash_update_proto = {
+ .func = bpf_sock_hash_update,
+ .gpl_only = false,
+ .pkt_access = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_PTR_TO_MAP_KEY,
+ .arg4_type = ARG_ANYTHING,
+};
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
new file mode 100644
index 000000000..92310b07c
--- /dev/null
+++ b/kernel/bpf/stackmap.c
@@ -0,0 +1,640 @@
+/* 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)
+{
+ u64 elem_size = sizeof(struct stack_map_bucket) +
+ (u64)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);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
new file mode 100644
index 000000000..e940c1f65
--- /dev/null
+++ b/kernel/bpf/syscall.c
@@ -0,0 +1,2479 @@
+/* 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/bpf_trace.h>
+#include <linux/bpf_lirc.h>
+#include <linux/btf.h>
+#include <linux/syscalls.h>
+#include <linux/slab.h>
+#include <linux/sched/signal.h>
+#include <linux/vmalloc.h>
+#include <linux/mmzone.h>
+#include <linux/anon_inodes.h>
+#include <linux/fdtable.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/license.h>
+#include <linux/filter.h>
+#include <linux/version.h>
+#include <linux/kernel.h>
+#include <linux/idr.h>
+#include <linux/cred.h>
+#include <linux/timekeeping.h>
+#include <linux/ctype.h>
+#include <linux/btf.h>
+#include <linux/nospec.h>
+
+#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
+ (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
+ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
+ (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
+#define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
+#define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_HASH(map))
+
+#define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY)
+
+DEFINE_PER_CPU(int, bpf_prog_active);
+static DEFINE_IDR(prog_idr);
+static DEFINE_SPINLOCK(prog_idr_lock);
+static DEFINE_IDR(map_idr);
+static DEFINE_SPINLOCK(map_idr_lock);
+
+int sysctl_unprivileged_bpf_disabled __read_mostly =
+ IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0;
+
+static const struct bpf_map_ops * const bpf_map_types[] = {
+#define BPF_PROG_TYPE(_id, _ops)
+#define BPF_MAP_TYPE(_id, _ops) \
+ [_id] = &_ops,
+#include <linux/bpf_types.h>
+#undef BPF_PROG_TYPE
+#undef BPF_MAP_TYPE
+};
+
+/*
+ * If we're handed a bigger struct than we know of, ensure all the unknown bits
+ * are 0 - i.e. new user-space does not rely on any kernel feature extensions
+ * we don't know about yet.
+ *
+ * There is a ToCToU between this function call and the following
+ * copy_from_user() call. However, this is not a concern since this function is
+ * meant to be a future-proofing of bits.
+ */
+int bpf_check_uarg_tail_zero(void __user *uaddr,
+ size_t expected_size,
+ size_t actual_size)
+{
+ unsigned char __user *addr;
+ unsigned char __user *end;
+ unsigned char val;
+ int err;
+
+ if (unlikely(actual_size > PAGE_SIZE)) /* silly large */
+ return -E2BIG;
+
+ if (unlikely(!access_ok(VERIFY_READ, uaddr, actual_size)))
+ return -EFAULT;
+
+ if (actual_size <= expected_size)
+ return 0;
+
+ addr = uaddr + expected_size;
+ end = uaddr + actual_size;
+
+ for (; addr < end; addr++) {
+ err = get_user(val, addr);
+ if (err)
+ return err;
+ if (val)
+ return -E2BIG;
+ }
+
+ return 0;
+}
+
+const struct bpf_map_ops bpf_map_offload_ops = {
+ .map_alloc = bpf_map_offload_map_alloc,
+ .map_free = bpf_map_offload_map_free,
+ .map_check_btf = map_check_no_btf,
+};
+
+static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
+{
+ const struct bpf_map_ops *ops;
+ u32 type = attr->map_type;
+ struct bpf_map *map;
+ int err;
+
+ if (type >= ARRAY_SIZE(bpf_map_types))
+ return ERR_PTR(-EINVAL);
+ type = array_index_nospec(type, ARRAY_SIZE(bpf_map_types));
+ ops = bpf_map_types[type];
+ if (!ops)
+ return ERR_PTR(-EINVAL);
+
+ if (ops->map_alloc_check) {
+ err = ops->map_alloc_check(attr);
+ if (err)
+ return ERR_PTR(err);
+ }
+ if (attr->map_ifindex)
+ ops = &bpf_map_offload_ops;
+ map = ops->map_alloc(attr);
+ if (IS_ERR(map))
+ return map;
+ map->ops = ops;
+ map->map_type = type;
+ return map;
+}
+
+void *bpf_map_area_alloc(size_t size, int numa_node)
+{
+ /* We definitely need __GFP_NORETRY, so OOM killer doesn't
+ * trigger under memory pressure as we really just want to
+ * fail instead.
+ */
+ const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO;
+ void *area;
+
+ if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
+ area = kmalloc_node(size, GFP_USER | flags, numa_node);
+ if (area != NULL)
+ return area;
+ }
+
+ return __vmalloc_node_flags_caller(size, numa_node, GFP_KERNEL | flags,
+ __builtin_return_address(0));
+}
+
+void bpf_map_area_free(void *area)
+{
+ kvfree(area);
+}
+
+void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr)
+{
+ map->map_type = attr->map_type;
+ map->key_size = attr->key_size;
+ map->value_size = attr->value_size;
+ map->max_entries = attr->max_entries;
+ map->map_flags = attr->map_flags;
+ map->numa_node = bpf_map_attr_numa_node(attr);
+}
+
+int bpf_map_precharge_memlock(u32 pages)
+{
+ struct user_struct *user = get_current_user();
+ unsigned long memlock_limit, cur;
+
+ memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+ cur = atomic_long_read(&user->locked_vm);
+ free_uid(user);
+ if (cur + pages > memlock_limit)
+ return -EPERM;
+ return 0;
+}
+
+static int bpf_charge_memlock(struct user_struct *user, u32 pages)
+{
+ unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+
+ if (atomic_long_add_return(pages, &user->locked_vm) > memlock_limit) {
+ atomic_long_sub(pages, &user->locked_vm);
+ return -EPERM;
+ }
+ return 0;
+}
+
+static void bpf_uncharge_memlock(struct user_struct *user, u32 pages)
+{
+ atomic_long_sub(pages, &user->locked_vm);
+}
+
+static int bpf_map_init_memlock(struct bpf_map *map)
+{
+ struct user_struct *user = get_current_user();
+ int ret;
+
+ ret = bpf_charge_memlock(user, map->pages);
+ if (ret) {
+ free_uid(user);
+ return ret;
+ }
+ map->user = user;
+ return ret;
+}
+
+static void bpf_map_release_memlock(struct bpf_map *map)
+{
+ struct user_struct *user = map->user;
+ bpf_uncharge_memlock(user, map->pages);
+ free_uid(user);
+}
+
+int bpf_map_charge_memlock(struct bpf_map *map, u32 pages)
+{
+ int ret;
+
+ ret = bpf_charge_memlock(map->user, pages);
+ if (ret)
+ return ret;
+ map->pages += pages;
+ return ret;
+}
+
+void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages)
+{
+ bpf_uncharge_memlock(map->user, pages);
+ map->pages -= pages;
+}
+
+static int bpf_map_alloc_id(struct bpf_map *map)
+{
+ int id;
+
+ idr_preload(GFP_KERNEL);
+ spin_lock_bh(&map_idr_lock);
+ id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC);
+ if (id > 0)
+ map->id = id;
+ spin_unlock_bh(&map_idr_lock);
+ idr_preload_end();
+
+ if (WARN_ON_ONCE(!id))
+ return -ENOSPC;
+
+ return id > 0 ? 0 : id;
+}
+
+void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock)
+{
+ unsigned long flags;
+
+ /* Offloaded maps are removed from the IDR store when their device
+ * disappears - even if someone holds an fd to them they are unusable,
+ * the memory is gone, all ops will fail; they are simply waiting for
+ * refcnt to drop to be freed.
+ */
+ if (!map->id)
+ return;
+
+ if (do_idr_lock)
+ spin_lock_irqsave(&map_idr_lock, flags);
+ else
+ __acquire(&map_idr_lock);
+
+ idr_remove(&map_idr, map->id);
+ map->id = 0;
+
+ if (do_idr_lock)
+ spin_unlock_irqrestore(&map_idr_lock, flags);
+ else
+ __release(&map_idr_lock);
+}
+
+/* called from workqueue */
+static void bpf_map_free_deferred(struct work_struct *work)
+{
+ struct bpf_map *map = container_of(work, struct bpf_map, work);
+
+ bpf_map_release_memlock(map);
+ security_bpf_map_free(map);
+ /* implementation dependent freeing */
+ map->ops->map_free(map);
+}
+
+static void bpf_map_put_uref(struct bpf_map *map)
+{
+ if (atomic_dec_and_test(&map->usercnt)) {
+ if (map->ops->map_release_uref)
+ map->ops->map_release_uref(map);
+ }
+}
+
+/* decrement map refcnt and schedule it for freeing via workqueue
+ * (unrelying map implementation ops->map_free() might sleep)
+ */
+static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock)
+{
+ if (atomic_dec_and_test(&map->refcnt)) {
+ /* bpf_map_free_id() must be called first */
+ bpf_map_free_id(map, do_idr_lock);
+ btf_put(map->btf);
+ INIT_WORK(&map->work, bpf_map_free_deferred);
+ schedule_work(&map->work);
+ }
+}
+
+void bpf_map_put(struct bpf_map *map)
+{
+ __bpf_map_put(map, true);
+}
+EXPORT_SYMBOL_GPL(bpf_map_put);
+
+void bpf_map_put_with_uref(struct bpf_map *map)
+{
+ bpf_map_put_uref(map);
+ bpf_map_put(map);
+}
+
+static int bpf_map_release(struct inode *inode, struct file *filp)
+{
+ struct bpf_map *map = filp->private_data;
+
+ if (map->ops->map_release)
+ map->ops->map_release(map, filp);
+
+ bpf_map_put_with_uref(map);
+ return 0;
+}
+
+#ifdef CONFIG_PROC_FS
+static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
+{
+ const struct bpf_map *map = filp->private_data;
+ const struct bpf_array *array;
+ u32 owner_prog_type = 0;
+ u32 owner_jited = 0;
+
+ if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
+ array = container_of(map, struct bpf_array, map);
+ owner_prog_type = array->owner_prog_type;
+ owner_jited = array->owner_jited;
+ }
+
+ seq_printf(m,
+ "map_type:\t%u\n"
+ "key_size:\t%u\n"
+ "value_size:\t%u\n"
+ "max_entries:\t%u\n"
+ "map_flags:\t%#x\n"
+ "memlock:\t%llu\n"
+ "map_id:\t%u\n",
+ map->map_type,
+ map->key_size,
+ map->value_size,
+ map->max_entries,
+ map->map_flags,
+ map->pages * 1ULL << PAGE_SHIFT,
+ map->id);
+
+ if (owner_prog_type) {
+ seq_printf(m, "owner_prog_type:\t%u\n",
+ owner_prog_type);
+ seq_printf(m, "owner_jited:\t%u\n",
+ owner_jited);
+ }
+}
+#endif
+
+static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz,
+ loff_t *ppos)
+{
+ /* We need this handler such that alloc_file() enables
+ * f_mode with FMODE_CAN_READ.
+ */
+ return -EINVAL;
+}
+
+static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf,
+ size_t siz, loff_t *ppos)
+{
+ /* We need this handler such that alloc_file() enables
+ * f_mode with FMODE_CAN_WRITE.
+ */
+ return -EINVAL;
+}
+
+const struct file_operations bpf_map_fops = {
+#ifdef CONFIG_PROC_FS
+ .show_fdinfo = bpf_map_show_fdinfo,
+#endif
+ .release = bpf_map_release,
+ .read = bpf_dummy_read,
+ .write = bpf_dummy_write,
+};
+
+int bpf_map_new_fd(struct bpf_map *map, int flags)
+{
+ int ret;
+
+ ret = security_bpf_map(map, OPEN_FMODE(flags));
+ if (ret < 0)
+ return ret;
+
+ return anon_inode_getfd("bpf-map", &bpf_map_fops, map,
+ flags | O_CLOEXEC);
+}
+
+int bpf_get_file_flag(int flags)
+{
+ if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY))
+ return -EINVAL;
+ if (flags & BPF_F_RDONLY)
+ return O_RDONLY;
+ if (flags & BPF_F_WRONLY)
+ return O_WRONLY;
+ return O_RDWR;
+}
+
+/* helper macro to check that unused fields 'union bpf_attr' are zero */
+#define CHECK_ATTR(CMD) \
+ memchr_inv((void *) &attr->CMD##_LAST_FIELD + \
+ sizeof(attr->CMD##_LAST_FIELD), 0, \
+ sizeof(*attr) - \
+ offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
+ sizeof(attr->CMD##_LAST_FIELD)) != NULL
+
+/* dst and src must have at least BPF_OBJ_NAME_LEN number of bytes.
+ * Return 0 on success and < 0 on error.
+ */
+static int bpf_obj_name_cpy(char *dst, const char *src)
+{
+ const char *end = src + BPF_OBJ_NAME_LEN;
+
+ memset(dst, 0, BPF_OBJ_NAME_LEN);
+
+ /* Copy all isalnum() and '_' char */
+ while (src < end && *src) {
+ if (!isalnum(*src) && *src != '_')
+ return -EINVAL;
+ *dst++ = *src++;
+ }
+
+ /* No '\0' found in BPF_OBJ_NAME_LEN number of bytes */
+ if (src == end)
+ return -EINVAL;
+
+ return 0;
+}
+
+int map_check_no_btf(const struct bpf_map *map,
+ const struct btf_type *key_type,
+ const struct btf_type *value_type)
+{
+ return -ENOTSUPP;
+}
+
+static int map_check_btf(const struct bpf_map *map, const struct btf *btf,
+ u32 btf_key_id, u32 btf_value_id)
+{
+ const struct btf_type *key_type, *value_type;
+ u32 key_size, value_size;
+ int ret = 0;
+
+ key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
+ if (!key_type || key_size != map->key_size)
+ return -EINVAL;
+
+ value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
+ if (!value_type || value_size != map->value_size)
+ return -EINVAL;
+
+ if (map->ops->map_check_btf)
+ ret = map->ops->map_check_btf(map, key_type, value_type);
+
+ return ret;
+}
+
+#define BPF_MAP_CREATE_LAST_FIELD btf_value_type_id
+/* called via syscall */
+static int map_create(union bpf_attr *attr)
+{
+ int numa_node = bpf_map_attr_numa_node(attr);
+ struct bpf_map *map;
+ int f_flags;
+ int err;
+
+ err = CHECK_ATTR(BPF_MAP_CREATE);
+ if (err)
+ return -EINVAL;
+
+ f_flags = bpf_get_file_flag(attr->map_flags);
+ if (f_flags < 0)
+ return f_flags;
+
+ if (numa_node != NUMA_NO_NODE &&
+ ((unsigned int)numa_node >= nr_node_ids ||
+ !node_online(numa_node)))
+ return -EINVAL;
+
+ /* find map type and init map: hashtable vs rbtree vs bloom vs ... */
+ map = find_and_alloc_map(attr);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ err = bpf_obj_name_cpy(map->name, attr->map_name);
+ if (err)
+ goto free_map_nouncharge;
+
+ atomic_set(&map->refcnt, 1);
+ atomic_set(&map->usercnt, 1);
+
+ if (attr->btf_key_type_id || attr->btf_value_type_id) {
+ struct btf *btf;
+
+ if (!attr->btf_key_type_id || !attr->btf_value_type_id) {
+ err = -EINVAL;
+ goto free_map_nouncharge;
+ }
+
+ btf = btf_get_by_fd(attr->btf_fd);
+ if (IS_ERR(btf)) {
+ err = PTR_ERR(btf);
+ goto free_map_nouncharge;
+ }
+
+ err = map_check_btf(map, btf, attr->btf_key_type_id,
+ attr->btf_value_type_id);
+ if (err) {
+ btf_put(btf);
+ goto free_map_nouncharge;
+ }
+
+ map->btf = btf;
+ map->btf_key_type_id = attr->btf_key_type_id;
+ map->btf_value_type_id = attr->btf_value_type_id;
+ }
+
+ err = security_bpf_map_alloc(map);
+ if (err)
+ goto free_map_nouncharge;
+
+ err = bpf_map_init_memlock(map);
+ if (err)
+ goto free_map_sec;
+
+ err = bpf_map_alloc_id(map);
+ if (err)
+ goto free_map;
+
+ err = bpf_map_new_fd(map, f_flags);
+ if (err < 0) {
+ /* failed to allocate fd.
+ * bpf_map_put_with_uref() is needed because the above
+ * bpf_map_alloc_id() has published the map
+ * to the userspace and the userspace may
+ * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID.
+ */
+ bpf_map_put_with_uref(map);
+ return err;
+ }
+
+ return err;
+
+free_map:
+ bpf_map_release_memlock(map);
+free_map_sec:
+ security_bpf_map_free(map);
+free_map_nouncharge:
+ btf_put(map->btf);
+ map->ops->map_free(map);
+ return err;
+}
+
+/* if error is returned, fd is released.
+ * On success caller should complete fd access with matching fdput()
+ */
+struct bpf_map *__bpf_map_get(struct fd f)
+{
+ if (!f.file)
+ return ERR_PTR(-EBADF);
+ if (f.file->f_op != &bpf_map_fops) {
+ fdput(f);
+ return ERR_PTR(-EINVAL);
+ }
+
+ return f.file->private_data;
+}
+
+/* prog's and map's refcnt limit */
+#define BPF_MAX_REFCNT 32768
+
+struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref)
+{
+ if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) {
+ atomic_dec(&map->refcnt);
+ return ERR_PTR(-EBUSY);
+ }
+ if (uref)
+ atomic_inc(&map->usercnt);
+ return map;
+}
+EXPORT_SYMBOL_GPL(bpf_map_inc);
+
+struct bpf_map *bpf_map_get_with_uref(u32 ufd)
+{
+ struct fd f = fdget(ufd);
+ struct bpf_map *map;
+
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return map;
+
+ map = bpf_map_inc(map, true);
+ fdput(f);
+
+ return map;
+}
+
+/* map_idr_lock should have been held */
+static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map,
+ bool uref)
+{
+ int refold;
+
+ refold = atomic_fetch_add_unless(&map->refcnt, 1, 0);
+
+ if (refold >= BPF_MAX_REFCNT) {
+ __bpf_map_put(map, false);
+ return ERR_PTR(-EBUSY);
+ }
+
+ if (!refold)
+ return ERR_PTR(-ENOENT);
+
+ if (uref)
+ atomic_inc(&map->usercnt);
+
+ return map;
+}
+
+int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
+{
+ return -ENOTSUPP;
+}
+
+/* last field in 'union bpf_attr' used by this command */
+#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value
+
+static int map_lookup_elem(union bpf_attr *attr)
+{
+ void __user *ukey = u64_to_user_ptr(attr->key);
+ void __user *uvalue = u64_to_user_ptr(attr->value);
+ int ufd = attr->map_fd;
+ struct bpf_map *map;
+ void *key, *value, *ptr;
+ u32 value_size;
+ struct fd f;
+ int err;
+
+ if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
+ return -EINVAL;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ if (!(f.file->f_mode & FMODE_CAN_READ)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
+ key = memdup_user(ukey, map->key_size);
+ if (IS_ERR(key)) {
+ err = PTR_ERR(key);
+ goto err_put;
+ }
+
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ value_size = round_up(map->value_size, 8) * num_possible_cpus();
+ else if (IS_FD_MAP(map))
+ value_size = sizeof(u32);
+ else
+ value_size = map->value_size;
+
+ err = -ENOMEM;
+ value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
+ if (!value)
+ goto free_key;
+
+ if (bpf_map_is_dev_bound(map)) {
+ err = bpf_map_offload_lookup_elem(map, key, value);
+ goto done;
+ }
+
+ preempt_disable();
+ this_cpu_inc(bpf_prog_active);
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
+ err = bpf_percpu_hash_copy(map, key, value);
+ } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
+ err = bpf_percpu_array_copy(map, key, value);
+ } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
+ err = bpf_stackmap_copy(map, key, value);
+ } else if (IS_FD_ARRAY(map)) {
+ err = bpf_fd_array_map_lookup_elem(map, key, value);
+ } else if (IS_FD_HASH(map)) {
+ err = bpf_fd_htab_map_lookup_elem(map, key, value);
+ } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
+ err = bpf_fd_reuseport_array_lookup_elem(map, key, value);
+ } else {
+ rcu_read_lock();
+ if (map->ops->map_lookup_elem_sys_only)
+ ptr = map->ops->map_lookup_elem_sys_only(map, key);
+ else
+ ptr = map->ops->map_lookup_elem(map, key);
+ if (ptr)
+ memcpy(value, ptr, value_size);
+ rcu_read_unlock();
+ err = ptr ? 0 : -ENOENT;
+ }
+ this_cpu_dec(bpf_prog_active);
+ preempt_enable();
+
+done:
+ if (err)
+ goto free_value;
+
+ err = -EFAULT;
+ if (copy_to_user(uvalue, value, value_size) != 0)
+ goto free_value;
+
+ err = 0;
+
+free_value:
+ kfree(value);
+free_key:
+ kfree(key);
+err_put:
+ fdput(f);
+ return err;
+}
+
+static void maybe_wait_bpf_programs(struct bpf_map *map)
+{
+ /* Wait for any running BPF programs to complete so that
+ * userspace, when we return to it, knows that all programs
+ * that could be running use the new map value.
+ */
+ if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS ||
+ map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
+ synchronize_rcu();
+}
+
+#define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags
+
+static int map_update_elem(union bpf_attr *attr)
+{
+ void __user *ukey = u64_to_user_ptr(attr->key);
+ void __user *uvalue = u64_to_user_ptr(attr->value);
+ int ufd = attr->map_fd;
+ struct bpf_map *map;
+ void *key, *value;
+ u32 value_size;
+ struct fd f;
+ int err;
+
+ if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM))
+ return -EINVAL;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
+ key = memdup_user(ukey, map->key_size);
+ if (IS_ERR(key)) {
+ err = PTR_ERR(key);
+ goto err_put;
+ }
+
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ value_size = round_up(map->value_size, 8) * num_possible_cpus();
+ else
+ value_size = map->value_size;
+
+ err = -ENOMEM;
+ value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
+ if (!value)
+ goto free_key;
+
+ err = -EFAULT;
+ if (copy_from_user(value, uvalue, value_size) != 0)
+ goto free_value;
+
+ /* Need to create a kthread, thus must support schedule */
+ if (bpf_map_is_dev_bound(map)) {
+ err = bpf_map_offload_update_elem(map, key, value, attr->flags);
+ goto out;
+ } else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
+ map->map_type == BPF_MAP_TYPE_SOCKHASH ||
+ map->map_type == BPF_MAP_TYPE_SOCKMAP) {
+ err = map->ops->map_update_elem(map, key, value, attr->flags);
+ goto out;
+ }
+
+ /* must increment bpf_prog_active to avoid kprobe+bpf triggering from
+ * inside bpf map update or delete otherwise deadlocks are possible
+ */
+ preempt_disable();
+ __this_cpu_inc(bpf_prog_active);
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
+ err = bpf_percpu_hash_update(map, key, value, attr->flags);
+ } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
+ err = bpf_percpu_array_update(map, key, value, attr->flags);
+ } else if (IS_FD_ARRAY(map)) {
+ rcu_read_lock();
+ err = bpf_fd_array_map_update_elem(map, f.file, key, value,
+ attr->flags);
+ rcu_read_unlock();
+ } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+ rcu_read_lock();
+ err = bpf_fd_htab_map_update_elem(map, f.file, key, value,
+ attr->flags);
+ rcu_read_unlock();
+ } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
+ /* rcu_read_lock() is not needed */
+ err = bpf_fd_reuseport_array_update_elem(map, key, value,
+ attr->flags);
+ } else {
+ rcu_read_lock();
+ err = map->ops->map_update_elem(map, key, value, attr->flags);
+ rcu_read_unlock();
+ }
+ __this_cpu_dec(bpf_prog_active);
+ preempt_enable();
+ maybe_wait_bpf_programs(map);
+out:
+free_value:
+ kfree(value);
+free_key:
+ kfree(key);
+err_put:
+ fdput(f);
+ return err;
+}
+
+#define BPF_MAP_DELETE_ELEM_LAST_FIELD key
+
+static int map_delete_elem(union bpf_attr *attr)
+{
+ void __user *ukey = u64_to_user_ptr(attr->key);
+ int ufd = attr->map_fd;
+ struct bpf_map *map;
+ struct fd f;
+ void *key;
+ int err;
+
+ if (CHECK_ATTR(BPF_MAP_DELETE_ELEM))
+ return -EINVAL;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
+ key = memdup_user(ukey, map->key_size);
+ if (IS_ERR(key)) {
+ err = PTR_ERR(key);
+ goto err_put;
+ }
+
+ if (bpf_map_is_dev_bound(map)) {
+ err = bpf_map_offload_delete_elem(map, key);
+ goto out;
+ }
+
+ preempt_disable();
+ __this_cpu_inc(bpf_prog_active);
+ rcu_read_lock();
+ err = map->ops->map_delete_elem(map, key);
+ rcu_read_unlock();
+ __this_cpu_dec(bpf_prog_active);
+ preempt_enable();
+ maybe_wait_bpf_programs(map);
+out:
+ kfree(key);
+err_put:
+ fdput(f);
+ return err;
+}
+
+/* last field in 'union bpf_attr' used by this command */
+#define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key
+
+static int map_get_next_key(union bpf_attr *attr)
+{
+ void __user *ukey = u64_to_user_ptr(attr->key);
+ void __user *unext_key = u64_to_user_ptr(attr->next_key);
+ int ufd = attr->map_fd;
+ struct bpf_map *map;
+ void *key, *next_key;
+ struct fd f;
+ int err;
+
+ if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY))
+ return -EINVAL;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ if (!(f.file->f_mode & FMODE_CAN_READ)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
+ if (ukey) {
+ key = memdup_user(ukey, map->key_size);
+ if (IS_ERR(key)) {
+ err = PTR_ERR(key);
+ goto err_put;
+ }
+ } else {
+ key = NULL;
+ }
+
+ err = -ENOMEM;
+ next_key = kmalloc(map->key_size, GFP_USER);
+ if (!next_key)
+ goto free_key;
+
+ if (bpf_map_is_dev_bound(map)) {
+ err = bpf_map_offload_get_next_key(map, key, next_key);
+ goto out;
+ }
+
+ rcu_read_lock();
+ err = map->ops->map_get_next_key(map, key, next_key);
+ rcu_read_unlock();
+out:
+ if (err)
+ goto free_next_key;
+
+ err = -EFAULT;
+ if (copy_to_user(unext_key, next_key, map->key_size) != 0)
+ goto free_next_key;
+
+ err = 0;
+
+free_next_key:
+ kfree(next_key);
+free_key:
+ kfree(key);
+err_put:
+ fdput(f);
+ return err;
+}
+
+static const struct bpf_prog_ops * const bpf_prog_types[] = {
+#define BPF_PROG_TYPE(_id, _name) \
+ [_id] = & _name ## _prog_ops,
+#define BPF_MAP_TYPE(_id, _ops)
+#include <linux/bpf_types.h>
+#undef BPF_PROG_TYPE
+#undef BPF_MAP_TYPE
+};
+
+static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
+{
+ const struct bpf_prog_ops *ops;
+
+ if (type >= ARRAY_SIZE(bpf_prog_types))
+ return -EINVAL;
+ type = array_index_nospec(type, ARRAY_SIZE(bpf_prog_types));
+ ops = bpf_prog_types[type];
+ if (!ops)
+ return -EINVAL;
+
+ if (!bpf_prog_is_dev_bound(prog->aux))
+ prog->aux->ops = ops;
+ else
+ prog->aux->ops = &bpf_offload_prog_ops;
+ prog->type = type;
+ return 0;
+}
+
+/* drop refcnt on maps used by eBPF program and free auxilary data */
+static void free_used_maps(struct bpf_prog_aux *aux)
+{
+ int i;
+
+ if (aux->cgroup_storage)
+ bpf_cgroup_storage_release(aux->prog, aux->cgroup_storage);
+
+ for (i = 0; i < aux->used_map_cnt; i++)
+ bpf_map_put(aux->used_maps[i]);
+
+ kfree(aux->used_maps);
+}
+
+int __bpf_prog_charge(struct user_struct *user, u32 pages)
+{
+ unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+ unsigned long user_bufs;
+
+ if (user) {
+ user_bufs = atomic_long_add_return(pages, &user->locked_vm);
+ if (user_bufs > memlock_limit) {
+ atomic_long_sub(pages, &user->locked_vm);
+ return -EPERM;
+ }
+ }
+
+ return 0;
+}
+
+void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
+{
+ if (user)
+ atomic_long_sub(pages, &user->locked_vm);
+}
+
+static int bpf_prog_charge_memlock(struct bpf_prog *prog)
+{
+ struct user_struct *user = get_current_user();
+ int ret;
+
+ ret = __bpf_prog_charge(user, prog->pages);
+ if (ret) {
+ free_uid(user);
+ return ret;
+ }
+
+ prog->aux->user = user;
+ return 0;
+}
+
+static void bpf_prog_uncharge_memlock(struct bpf_prog *prog)
+{
+ struct user_struct *user = prog->aux->user;
+
+ __bpf_prog_uncharge(user, prog->pages);
+ free_uid(user);
+}
+
+static int bpf_prog_alloc_id(struct bpf_prog *prog)
+{
+ int id;
+
+ idr_preload(GFP_KERNEL);
+ spin_lock_bh(&prog_idr_lock);
+ id = idr_alloc_cyclic(&prog_idr, prog, 1, INT_MAX, GFP_ATOMIC);
+ if (id > 0)
+ prog->aux->id = id;
+ spin_unlock_bh(&prog_idr_lock);
+ idr_preload_end();
+
+ /* id is in [1, INT_MAX) */
+ if (WARN_ON_ONCE(!id))
+ return -ENOSPC;
+
+ return id > 0 ? 0 : id;
+}
+
+void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
+{
+ /* cBPF to eBPF migrations are currently not in the idr store.
+ * Offloaded programs are removed from the store when their device
+ * disappears - even if someone grabs an fd to them they are unusable,
+ * simply waiting for refcnt to drop to be freed.
+ */
+ if (!prog->aux->id)
+ return;
+
+ if (do_idr_lock)
+ spin_lock_bh(&prog_idr_lock);
+ else
+ __acquire(&prog_idr_lock);
+
+ idr_remove(&prog_idr, prog->aux->id);
+ prog->aux->id = 0;
+
+ if (do_idr_lock)
+ spin_unlock_bh(&prog_idr_lock);
+ else
+ __release(&prog_idr_lock);
+}
+
+static void __bpf_prog_put_rcu(struct rcu_head *rcu)
+{
+ struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
+
+ free_used_maps(aux);
+ bpf_prog_uncharge_memlock(aux->prog);
+ security_bpf_prog_free(aux);
+ bpf_prog_free(aux->prog);
+}
+
+static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
+{
+ if (atomic_dec_and_test(&prog->aux->refcnt)) {
+ /* bpf_prog_free_id() must be called first */
+ bpf_prog_free_id(prog, do_idr_lock);
+ bpf_prog_kallsyms_del_all(prog);
+
+ call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
+ }
+}
+
+void bpf_prog_put(struct bpf_prog *prog)
+{
+ __bpf_prog_put(prog, true);
+}
+EXPORT_SYMBOL_GPL(bpf_prog_put);
+
+static int bpf_prog_release(struct inode *inode, struct file *filp)
+{
+ struct bpf_prog *prog = filp->private_data;
+
+ bpf_prog_put(prog);
+ return 0;
+}
+
+#ifdef CONFIG_PROC_FS
+static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
+{
+ const struct bpf_prog *prog = filp->private_data;
+ char prog_tag[sizeof(prog->tag) * 2 + 1] = { };
+
+ bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
+ seq_printf(m,
+ "prog_type:\t%u\n"
+ "prog_jited:\t%u\n"
+ "prog_tag:\t%s\n"
+ "memlock:\t%llu\n"
+ "prog_id:\t%u\n",
+ prog->type,
+ prog->jited,
+ prog_tag,
+ prog->pages * 1ULL << PAGE_SHIFT,
+ prog->aux->id);
+}
+#endif
+
+const struct file_operations bpf_prog_fops = {
+#ifdef CONFIG_PROC_FS
+ .show_fdinfo = bpf_prog_show_fdinfo,
+#endif
+ .release = bpf_prog_release,
+ .read = bpf_dummy_read,
+ .write = bpf_dummy_write,
+};
+
+int bpf_prog_new_fd(struct bpf_prog *prog)
+{
+ int ret;
+
+ ret = security_bpf_prog(prog);
+ if (ret < 0)
+ return ret;
+
+ return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog,
+ O_RDWR | O_CLOEXEC);
+}
+
+static struct bpf_prog *____bpf_prog_get(struct fd f)
+{
+ if (!f.file)
+ return ERR_PTR(-EBADF);
+ if (f.file->f_op != &bpf_prog_fops) {
+ fdput(f);
+ return ERR_PTR(-EINVAL);
+ }
+
+ return f.file->private_data;
+}
+
+struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i)
+{
+ if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) {
+ atomic_sub(i, &prog->aux->refcnt);
+ return ERR_PTR(-EBUSY);
+ }
+ return prog;
+}
+EXPORT_SYMBOL_GPL(bpf_prog_add);
+
+void bpf_prog_sub(struct bpf_prog *prog, int i)
+{
+ /* Only to be used for undoing previous bpf_prog_add() in some
+ * error path. We still know that another entity in our call
+ * path holds a reference to the program, thus atomic_sub() can
+ * be safely used in such cases!
+ */
+ WARN_ON(atomic_sub_return(i, &prog->aux->refcnt) == 0);
+}
+EXPORT_SYMBOL_GPL(bpf_prog_sub);
+
+struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
+{
+ return bpf_prog_add(prog, 1);
+}
+EXPORT_SYMBOL_GPL(bpf_prog_inc);
+
+/* prog_idr_lock should have been held */
+struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
+{
+ int refold;
+
+ refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0);
+
+ if (refold >= BPF_MAX_REFCNT) {
+ __bpf_prog_put(prog, false);
+ return ERR_PTR(-EBUSY);
+ }
+
+ if (!refold)
+ return ERR_PTR(-ENOENT);
+
+ return prog;
+}
+EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero);
+
+bool bpf_prog_get_ok(struct bpf_prog *prog,
+ enum bpf_prog_type *attach_type, bool attach_drv)
+{
+ /* not an attachment, just a refcount inc, always allow */
+ if (!attach_type)
+ return true;
+
+ if (prog->type != *attach_type)
+ return false;
+ if (bpf_prog_is_dev_bound(prog->aux) && !attach_drv)
+ return false;
+
+ return true;
+}
+
+static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type,
+ bool attach_drv)
+{
+ struct fd f = fdget(ufd);
+ struct bpf_prog *prog;
+
+ prog = ____bpf_prog_get(f);
+ if (IS_ERR(prog))
+ return prog;
+ if (!bpf_prog_get_ok(prog, attach_type, attach_drv)) {
+ prog = ERR_PTR(-EINVAL);
+ goto out;
+ }
+
+ prog = bpf_prog_inc(prog);
+out:
+ fdput(f);
+ return prog;
+}
+
+struct bpf_prog *bpf_prog_get(u32 ufd)
+{
+ return __bpf_prog_get(ufd, NULL, false);
+}
+
+struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type,
+ bool attach_drv)
+{
+ return __bpf_prog_get(ufd, &type, attach_drv);
+}
+EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev);
+
+/* Initially all BPF programs could be loaded w/o specifying
+ * expected_attach_type. Later for some of them specifying expected_attach_type
+ * at load time became required so that program could be validated properly.
+ * Programs of types that are allowed to be loaded both w/ and w/o (for
+ * backward compatibility) expected_attach_type, should have the default attach
+ * type assigned to expected_attach_type for the latter case, so that it can be
+ * validated later at attach time.
+ *
+ * bpf_prog_load_fixup_attach_type() sets expected_attach_type in @attr if
+ * prog type requires it but has some attach types that have to be backward
+ * compatible.
+ */
+static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr)
+{
+ switch (attr->prog_type) {
+ case BPF_PROG_TYPE_CGROUP_SOCK:
+ /* Unfortunately BPF_ATTACH_TYPE_UNSPEC enumeration doesn't
+ * exist so checking for non-zero is the way to go here.
+ */
+ if (!attr->expected_attach_type)
+ attr->expected_attach_type =
+ BPF_CGROUP_INET_SOCK_CREATE;
+ break;
+ }
+}
+
+static int
+bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
+ enum bpf_attach_type expected_attach_type)
+{
+ switch (prog_type) {
+ case BPF_PROG_TYPE_CGROUP_SOCK:
+ switch (expected_attach_type) {
+ case BPF_CGROUP_INET_SOCK_CREATE:
+ case BPF_CGROUP_INET4_POST_BIND:
+ case BPF_CGROUP_INET6_POST_BIND:
+ return 0;
+ default:
+ return -EINVAL;
+ }
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ switch (expected_attach_type) {
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
+ case BPF_CGROUP_INET4_CONNECT:
+ case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_UDP4_SENDMSG:
+ case BPF_CGROUP_UDP6_SENDMSG:
+ case BPF_CGROUP_UDP4_RECVMSG:
+ case BPF_CGROUP_UDP6_RECVMSG:
+ return 0;
+ default:
+ return -EINVAL;
+ }
+ default:
+ return 0;
+ }
+}
+
+/* last field in 'union bpf_attr' used by this command */
+#define BPF_PROG_LOAD_LAST_FIELD expected_attach_type
+
+static int bpf_prog_load(union bpf_attr *attr)
+{
+ enum bpf_prog_type type = attr->prog_type;
+ struct bpf_prog *prog;
+ int err;
+ char license[128];
+ bool is_gpl;
+
+ if (CHECK_ATTR(BPF_PROG_LOAD))
+ return -EINVAL;
+
+ if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT))
+ return -EINVAL;
+
+ if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
+ (attr->prog_flags & BPF_F_ANY_ALIGNMENT) &&
+ !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ /* copy eBPF program license from user space */
+ if (strncpy_from_user(license, u64_to_user_ptr(attr->license),
+ sizeof(license) - 1) < 0)
+ return -EFAULT;
+ license[sizeof(license) - 1] = 0;
+
+ /* eBPF programs must be GPL compatible to use GPL-ed functions */
+ is_gpl = license_is_gpl_compatible(license);
+
+ if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS)
+ return -E2BIG;
+
+ if (type == BPF_PROG_TYPE_KPROBE &&
+ attr->kern_version != LINUX_VERSION_CODE)
+ return -EINVAL;
+
+ if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
+ type != BPF_PROG_TYPE_CGROUP_SKB &&
+ !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ bpf_prog_load_fixup_attach_type(attr);
+ if (bpf_prog_load_check_attach_type(type, attr->expected_attach_type))
+ return -EINVAL;
+
+ /* plain bpf_prog allocation */
+ prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER);
+ if (!prog)
+ return -ENOMEM;
+
+ prog->expected_attach_type = attr->expected_attach_type;
+
+ prog->aux->offload_requested = !!attr->prog_ifindex;
+
+ err = security_bpf_prog_alloc(prog->aux);
+ if (err)
+ goto free_prog_nouncharge;
+
+ err = bpf_prog_charge_memlock(prog);
+ if (err)
+ goto free_prog_sec;
+
+ prog->len = attr->insn_cnt;
+
+ err = -EFAULT;
+ if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns),
+ bpf_prog_insn_size(prog)) != 0)
+ goto free_prog;
+
+ prog->orig_prog = NULL;
+ prog->jited = 0;
+
+ atomic_set(&prog->aux->refcnt, 1);
+ prog->gpl_compatible = is_gpl ? 1 : 0;
+
+ if (bpf_prog_is_dev_bound(prog->aux)) {
+ err = bpf_prog_offload_init(prog, attr);
+ if (err)
+ goto free_prog;
+ }
+
+ /* find program type: socket_filter vs tracing_filter */
+ err = find_prog_type(type, prog);
+ if (err < 0)
+ goto free_prog;
+
+ prog->aux->load_time = ktime_get_boot_ns();
+ err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name);
+ if (err)
+ goto free_prog;
+
+ /* run eBPF verifier */
+ err = bpf_check(&prog, attr);
+ if (err < 0)
+ goto free_used_maps;
+
+ prog = bpf_prog_select_runtime(prog, &err);
+ if (err < 0)
+ goto free_used_maps;
+
+ err = bpf_prog_alloc_id(prog);
+ if (err)
+ goto free_used_maps;
+
+ /* Upon success of bpf_prog_alloc_id(), the BPF prog is
+ * effectively publicly exposed. However, retrieving via
+ * bpf_prog_get_fd_by_id() will take another reference,
+ * therefore it cannot be gone underneath us.
+ *
+ * Only for the time /after/ successful bpf_prog_new_fd()
+ * and before returning to userspace, we might just hold
+ * one reference and any parallel close on that fd could
+ * rip everything out. Hence, below notifications must
+ * happen before bpf_prog_new_fd().
+ *
+ * Also, any failure handling from this point onwards must
+ * be using bpf_prog_put() given the program is exposed.
+ */
+ bpf_prog_kallsyms_add(prog);
+
+ err = bpf_prog_new_fd(prog);
+ if (err < 0)
+ bpf_prog_put(prog);
+ return err;
+
+free_used_maps:
+ bpf_prog_kallsyms_del_subprogs(prog);
+ free_used_maps(prog->aux);
+free_prog:
+ bpf_prog_uncharge_memlock(prog);
+free_prog_sec:
+ security_bpf_prog_free(prog->aux);
+free_prog_nouncharge:
+ bpf_prog_free(prog);
+ return err;
+}
+
+#define BPF_OBJ_LAST_FIELD file_flags
+
+static int bpf_obj_pin(const union bpf_attr *attr)
+{
+ if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0)
+ return -EINVAL;
+
+ return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname));
+}
+
+static int bpf_obj_get(const union bpf_attr *attr)
+{
+ if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 ||
+ attr->file_flags & ~BPF_OBJ_FLAG_MASK)
+ return -EINVAL;
+
+ return bpf_obj_get_user(u64_to_user_ptr(attr->pathname),
+ attr->file_flags);
+}
+
+struct bpf_raw_tracepoint {
+ struct bpf_raw_event_map *btp;
+ struct bpf_prog *prog;
+};
+
+static int bpf_raw_tracepoint_release(struct inode *inode, struct file *filp)
+{
+ struct bpf_raw_tracepoint *raw_tp = filp->private_data;
+
+ if (raw_tp->prog) {
+ bpf_probe_unregister(raw_tp->btp, raw_tp->prog);
+ bpf_prog_put(raw_tp->prog);
+ }
+ kfree(raw_tp);
+ return 0;
+}
+
+static const struct file_operations bpf_raw_tp_fops = {
+ .release = bpf_raw_tracepoint_release,
+ .read = bpf_dummy_read,
+ .write = bpf_dummy_write,
+};
+
+#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd
+
+static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
+{
+ struct bpf_raw_tracepoint *raw_tp;
+ struct bpf_raw_event_map *btp;
+ struct bpf_prog *prog;
+ char tp_name[128];
+ int tp_fd, err;
+
+ if (strncpy_from_user(tp_name, u64_to_user_ptr(attr->raw_tracepoint.name),
+ sizeof(tp_name) - 1) < 0)
+ return -EFAULT;
+ tp_name[sizeof(tp_name) - 1] = 0;
+
+ btp = bpf_find_raw_tracepoint(tp_name);
+ if (!btp)
+ return -ENOENT;
+
+ raw_tp = kzalloc(sizeof(*raw_tp), GFP_USER);
+ if (!raw_tp)
+ return -ENOMEM;
+ raw_tp->btp = btp;
+
+ prog = bpf_prog_get_type(attr->raw_tracepoint.prog_fd,
+ BPF_PROG_TYPE_RAW_TRACEPOINT);
+ if (IS_ERR(prog)) {
+ err = PTR_ERR(prog);
+ goto out_free_tp;
+ }
+
+ err = bpf_probe_register(raw_tp->btp, prog);
+ if (err)
+ goto out_put_prog;
+
+ raw_tp->prog = prog;
+ tp_fd = anon_inode_getfd("bpf-raw-tracepoint", &bpf_raw_tp_fops, raw_tp,
+ O_CLOEXEC);
+ if (tp_fd < 0) {
+ bpf_probe_unregister(raw_tp->btp, prog);
+ err = tp_fd;
+ goto out_put_prog;
+ }
+ return tp_fd;
+
+out_put_prog:
+ bpf_prog_put(prog);
+out_free_tp:
+ kfree(raw_tp);
+ return err;
+}
+
+static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
+ enum bpf_attach_type attach_type)
+{
+ switch (prog->type) {
+ case BPF_PROG_TYPE_CGROUP_SOCK:
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
+ default:
+ return 0;
+ }
+}
+
+#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
+
+#define BPF_F_ATTACH_MASK \
+ (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
+
+static int bpf_prog_attach(const union bpf_attr *attr)
+{
+ enum bpf_prog_type ptype;
+ struct bpf_prog *prog;
+ int ret;
+
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (CHECK_ATTR(BPF_PROG_ATTACH))
+ return -EINVAL;
+
+ if (attr->attach_flags & ~BPF_F_ATTACH_MASK)
+ return -EINVAL;
+
+ switch (attr->attach_type) {
+ case BPF_CGROUP_INET_INGRESS:
+ case BPF_CGROUP_INET_EGRESS:
+ ptype = BPF_PROG_TYPE_CGROUP_SKB;
+ break;
+ case BPF_CGROUP_INET_SOCK_CREATE:
+ case BPF_CGROUP_INET4_POST_BIND:
+ case BPF_CGROUP_INET6_POST_BIND:
+ ptype = BPF_PROG_TYPE_CGROUP_SOCK;
+ break;
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
+ case BPF_CGROUP_INET4_CONNECT:
+ case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_UDP4_SENDMSG:
+ case BPF_CGROUP_UDP6_SENDMSG:
+ case BPF_CGROUP_UDP4_RECVMSG:
+ case BPF_CGROUP_UDP6_RECVMSG:
+ ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
+ break;
+ case BPF_CGROUP_SOCK_OPS:
+ ptype = BPF_PROG_TYPE_SOCK_OPS;
+ break;
+ case BPF_CGROUP_DEVICE:
+ ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
+ break;
+ case BPF_SK_MSG_VERDICT:
+ ptype = BPF_PROG_TYPE_SK_MSG;
+ break;
+ case BPF_SK_SKB_STREAM_PARSER:
+ case BPF_SK_SKB_STREAM_VERDICT:
+ ptype = BPF_PROG_TYPE_SK_SKB;
+ break;
+ case BPF_LIRC_MODE2:
+ ptype = BPF_PROG_TYPE_LIRC_MODE2;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
+ if (bpf_prog_attach_check_attach_type(prog, attr->attach_type)) {
+ bpf_prog_put(prog);
+ return -EINVAL;
+ }
+
+ switch (ptype) {
+ case BPF_PROG_TYPE_SK_SKB:
+ case BPF_PROG_TYPE_SK_MSG:
+ ret = sockmap_get_from_fd(attr, ptype, prog);
+ break;
+ case BPF_PROG_TYPE_LIRC_MODE2:
+ ret = lirc_prog_attach(attr, prog);
+ break;
+ default:
+ ret = cgroup_bpf_prog_attach(attr, ptype, prog);
+ }
+
+ if (ret)
+ bpf_prog_put(prog);
+ return ret;
+}
+
+#define BPF_PROG_DETACH_LAST_FIELD attach_type
+
+static int bpf_prog_detach(const union bpf_attr *attr)
+{
+ enum bpf_prog_type ptype;
+
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (CHECK_ATTR(BPF_PROG_DETACH))
+ return -EINVAL;
+
+ switch (attr->attach_type) {
+ case BPF_CGROUP_INET_INGRESS:
+ case BPF_CGROUP_INET_EGRESS:
+ ptype = BPF_PROG_TYPE_CGROUP_SKB;
+ break;
+ case BPF_CGROUP_INET_SOCK_CREATE:
+ case BPF_CGROUP_INET4_POST_BIND:
+ case BPF_CGROUP_INET6_POST_BIND:
+ ptype = BPF_PROG_TYPE_CGROUP_SOCK;
+ break;
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
+ case BPF_CGROUP_INET4_CONNECT:
+ case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_UDP4_SENDMSG:
+ case BPF_CGROUP_UDP6_SENDMSG:
+ case BPF_CGROUP_UDP4_RECVMSG:
+ case BPF_CGROUP_UDP6_RECVMSG:
+ ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
+ break;
+ case BPF_CGROUP_SOCK_OPS:
+ ptype = BPF_PROG_TYPE_SOCK_OPS;
+ break;
+ case BPF_CGROUP_DEVICE:
+ ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
+ break;
+ case BPF_SK_MSG_VERDICT:
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL);
+ case BPF_SK_SKB_STREAM_PARSER:
+ case BPF_SK_SKB_STREAM_VERDICT:
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL);
+ case BPF_LIRC_MODE2:
+ return lirc_prog_detach(attr);
+ default:
+ return -EINVAL;
+ }
+
+ return cgroup_bpf_prog_detach(attr, ptype);
+}
+
+#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt
+
+static int bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ if (CHECK_ATTR(BPF_PROG_QUERY))
+ return -EINVAL;
+ if (attr->query.query_flags & ~BPF_F_QUERY_EFFECTIVE)
+ return -EINVAL;
+
+ switch (attr->query.attach_type) {
+ case BPF_CGROUP_INET_INGRESS:
+ case BPF_CGROUP_INET_EGRESS:
+ case BPF_CGROUP_INET_SOCK_CREATE:
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
+ case BPF_CGROUP_INET4_POST_BIND:
+ case BPF_CGROUP_INET6_POST_BIND:
+ case BPF_CGROUP_INET4_CONNECT:
+ case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_UDP4_SENDMSG:
+ case BPF_CGROUP_UDP6_SENDMSG:
+ case BPF_CGROUP_UDP4_RECVMSG:
+ case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_SOCK_OPS:
+ case BPF_CGROUP_DEVICE:
+ break;
+ case BPF_LIRC_MODE2:
+ return lirc_prog_query(attr, uattr);
+ default:
+ return -EINVAL;
+ }
+
+ return cgroup_bpf_prog_query(attr, uattr);
+}
+
+#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
+
+static int bpf_prog_test_run(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_prog *prog;
+ int ret = -ENOTSUPP;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ if (CHECK_ATTR(BPF_PROG_TEST_RUN))
+ return -EINVAL;
+
+ prog = bpf_prog_get(attr->test.prog_fd);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
+ if (prog->aux->ops->test_run)
+ ret = prog->aux->ops->test_run(prog, attr, uattr);
+
+ bpf_prog_put(prog);
+ return ret;
+}
+
+#define BPF_OBJ_GET_NEXT_ID_LAST_FIELD next_id
+
+static int bpf_obj_get_next_id(const union bpf_attr *attr,
+ union bpf_attr __user *uattr,
+ struct idr *idr,
+ spinlock_t *lock)
+{
+ u32 next_id = attr->start_id;
+ int err = 0;
+
+ if (CHECK_ATTR(BPF_OBJ_GET_NEXT_ID) || next_id >= INT_MAX)
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ next_id++;
+ spin_lock_bh(lock);
+ if (!idr_get_next(idr, &next_id))
+ err = -ENOENT;
+ spin_unlock_bh(lock);
+
+ if (!err)
+ err = put_user(next_id, &uattr->next_id);
+
+ return err;
+}
+
+#define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id
+
+static int bpf_prog_get_fd_by_id(const union bpf_attr *attr)
+{
+ struct bpf_prog *prog;
+ u32 id = attr->prog_id;
+ int fd;
+
+ if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID))
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ spin_lock_bh(&prog_idr_lock);
+ prog = idr_find(&prog_idr, id);
+ if (prog)
+ prog = bpf_prog_inc_not_zero(prog);
+ else
+ prog = ERR_PTR(-ENOENT);
+ spin_unlock_bh(&prog_idr_lock);
+
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
+ fd = bpf_prog_new_fd(prog);
+ if (fd < 0)
+ bpf_prog_put(prog);
+
+ return fd;
+}
+
+#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD open_flags
+
+static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
+{
+ struct bpf_map *map;
+ u32 id = attr->map_id;
+ int f_flags;
+ int fd;
+
+ if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID) ||
+ attr->open_flags & ~BPF_OBJ_FLAG_MASK)
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ f_flags = bpf_get_file_flag(attr->open_flags);
+ if (f_flags < 0)
+ return f_flags;
+
+ spin_lock_bh(&map_idr_lock);
+ map = idr_find(&map_idr, id);
+ if (map)
+ map = bpf_map_inc_not_zero(map, true);
+ else
+ map = ERR_PTR(-ENOENT);
+ spin_unlock_bh(&map_idr_lock);
+
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ fd = bpf_map_new_fd(map, f_flags);
+ if (fd < 0)
+ bpf_map_put_with_uref(map);
+
+ return fd;
+}
+
+static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog,
+ unsigned long addr)
+{
+ int i;
+
+ for (i = 0; i < prog->aux->used_map_cnt; i++)
+ if (prog->aux->used_maps[i] == (void *)addr)
+ return prog->aux->used_maps[i];
+ return NULL;
+}
+
+static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog,
+ const struct cred *f_cred)
+{
+ const struct bpf_map *map;
+ struct bpf_insn *insns;
+ u64 imm;
+ int i;
+
+ insns = kmemdup(prog->insnsi, bpf_prog_insn_size(prog),
+ GFP_USER);
+ if (!insns)
+ return insns;
+
+ for (i = 0; i < prog->len; i++) {
+ if (insns[i].code == (BPF_JMP | BPF_TAIL_CALL)) {
+ insns[i].code = BPF_JMP | BPF_CALL;
+ insns[i].imm = BPF_FUNC_tail_call;
+ /* fall-through */
+ }
+ if (insns[i].code == (BPF_JMP | BPF_CALL) ||
+ insns[i].code == (BPF_JMP | BPF_CALL_ARGS)) {
+ if (insns[i].code == (BPF_JMP | BPF_CALL_ARGS))
+ insns[i].code = BPF_JMP | BPF_CALL;
+ if (!bpf_dump_raw_ok(f_cred))
+ insns[i].imm = 0;
+ continue;
+ }
+
+ if (insns[i].code != (BPF_LD | BPF_IMM | BPF_DW))
+ continue;
+
+ imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm;
+ map = bpf_map_from_imm(prog, imm);
+ if (map) {
+ insns[i].src_reg = BPF_PSEUDO_MAP_FD;
+ insns[i].imm = map->id;
+ insns[i + 1].imm = 0;
+ continue;
+ }
+
+ if (!bpf_dump_raw_ok(f_cred) &&
+ imm == (unsigned long)prog->aux) {
+ insns[i].imm = 0;
+ insns[i + 1].imm = 0;
+ continue;
+ }
+ }
+
+ return insns;
+}
+
+static int bpf_prog_get_info_by_fd(struct file *file,
+ struct bpf_prog *prog,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info);
+ struct bpf_prog_info info;
+ u32 info_len = attr->info.info_len;
+ char __user *uinsns;
+ u32 ulen;
+ int err;
+
+ err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+ if (err)
+ return err;
+ info_len = min_t(u32, sizeof(info), info_len);
+
+ memset(&info, 0, sizeof(info));
+ if (copy_from_user(&info, uinfo, info_len))
+ return -EFAULT;
+
+ info.type = prog->type;
+ info.id = prog->aux->id;
+ info.load_time = prog->aux->load_time;
+ info.created_by_uid = from_kuid_munged(current_user_ns(),
+ prog->aux->user->uid);
+ info.gpl_compatible = prog->gpl_compatible;
+
+ memcpy(info.tag, prog->tag, sizeof(prog->tag));
+ memcpy(info.name, prog->aux->name, sizeof(prog->aux->name));
+
+ ulen = info.nr_map_ids;
+ info.nr_map_ids = prog->aux->used_map_cnt;
+ ulen = min_t(u32, info.nr_map_ids, ulen);
+ if (ulen) {
+ u32 __user *user_map_ids = u64_to_user_ptr(info.map_ids);
+ u32 i;
+
+ for (i = 0; i < ulen; i++)
+ if (put_user(prog->aux->used_maps[i]->id,
+ &user_map_ids[i]))
+ return -EFAULT;
+ }
+
+ if (!capable(CAP_SYS_ADMIN)) {
+ info.jited_prog_len = 0;
+ info.xlated_prog_len = 0;
+ info.nr_jited_ksyms = 0;
+ info.nr_jited_func_lens = 0;
+ goto done;
+ }
+
+ ulen = info.xlated_prog_len;
+ info.xlated_prog_len = bpf_prog_insn_size(prog);
+ if (info.xlated_prog_len && ulen) {
+ struct bpf_insn *insns_sanitized;
+ bool fault;
+
+ if (prog->blinded && !bpf_dump_raw_ok(file->f_cred)) {
+ info.xlated_prog_insns = 0;
+ goto done;
+ }
+ insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred);
+ if (!insns_sanitized)
+ return -ENOMEM;
+ uinsns = u64_to_user_ptr(info.xlated_prog_insns);
+ ulen = min_t(u32, info.xlated_prog_len, ulen);
+ fault = copy_to_user(uinsns, insns_sanitized, ulen);
+ kfree(insns_sanitized);
+ if (fault)
+ return -EFAULT;
+ }
+
+ if (bpf_prog_is_dev_bound(prog->aux)) {
+ err = bpf_prog_offload_info_fill(&info, prog);
+ if (err)
+ return err;
+ goto done;
+ }
+
+ /* NOTE: the following code is supposed to be skipped for offload.
+ * bpf_prog_offload_info_fill() is the place to fill similar fields
+ * for offload.
+ */
+ ulen = info.jited_prog_len;
+ if (prog->aux->func_cnt) {
+ u32 i;
+
+ info.jited_prog_len = 0;
+ for (i = 0; i < prog->aux->func_cnt; i++)
+ info.jited_prog_len += prog->aux->func[i]->jited_len;
+ } else {
+ info.jited_prog_len = prog->jited_len;
+ }
+
+ if (info.jited_prog_len && ulen) {
+ if (bpf_dump_raw_ok(file->f_cred)) {
+ uinsns = u64_to_user_ptr(info.jited_prog_insns);
+ ulen = min_t(u32, info.jited_prog_len, ulen);
+
+ /* for multi-function programs, copy the JITed
+ * instructions for all the functions
+ */
+ if (prog->aux->func_cnt) {
+ u32 len, free, i;
+ u8 *img;
+
+ free = ulen;
+ for (i = 0; i < prog->aux->func_cnt; i++) {
+ len = prog->aux->func[i]->jited_len;
+ len = min_t(u32, len, free);
+ img = (u8 *) prog->aux->func[i]->bpf_func;
+ if (copy_to_user(uinsns, img, len))
+ return -EFAULT;
+ uinsns += len;
+ free -= len;
+ if (!free)
+ break;
+ }
+ } else {
+ if (copy_to_user(uinsns, prog->bpf_func, ulen))
+ return -EFAULT;
+ }
+ } else {
+ info.jited_prog_insns = 0;
+ }
+ }
+
+ ulen = info.nr_jited_ksyms;
+ info.nr_jited_ksyms = prog->aux->func_cnt;
+ if (info.nr_jited_ksyms && ulen) {
+ if (bpf_dump_raw_ok(file->f_cred)) {
+ u64 __user *user_ksyms;
+ ulong ksym_addr;
+ u32 i;
+
+ /* copy the address of the kernel symbol
+ * corresponding to each function
+ */
+ ulen = min_t(u32, info.nr_jited_ksyms, ulen);
+ user_ksyms = u64_to_user_ptr(info.jited_ksyms);
+ for (i = 0; i < ulen; i++) {
+ ksym_addr = (ulong) prog->aux->func[i]->bpf_func;
+ ksym_addr &= PAGE_MASK;
+ if (put_user((u64) ksym_addr, &user_ksyms[i]))
+ return -EFAULT;
+ }
+ } else {
+ info.jited_ksyms = 0;
+ }
+ }
+
+ ulen = info.nr_jited_func_lens;
+ info.nr_jited_func_lens = prog->aux->func_cnt;
+ if (info.nr_jited_func_lens && ulen) {
+ if (bpf_dump_raw_ok(file->f_cred)) {
+ u32 __user *user_lens;
+ u32 func_len, i;
+
+ /* copy the JITed image lengths for each function */
+ ulen = min_t(u32, info.nr_jited_func_lens, ulen);
+ user_lens = u64_to_user_ptr(info.jited_func_lens);
+ for (i = 0; i < ulen; i++) {
+ func_len = prog->aux->func[i]->jited_len;
+ if (put_user(func_len, &user_lens[i]))
+ return -EFAULT;
+ }
+ } else {
+ info.jited_func_lens = 0;
+ }
+ }
+
+done:
+ if (copy_to_user(uinfo, &info, info_len) ||
+ put_user(info_len, &uattr->info.info_len))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int bpf_map_get_info_by_fd(struct file *file,
+ struct bpf_map *map,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info);
+ struct bpf_map_info info;
+ u32 info_len = attr->info.info_len;
+ int err;
+
+ err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len);
+ if (err)
+ return err;
+ info_len = min_t(u32, sizeof(info), info_len);
+
+ memset(&info, 0, sizeof(info));
+ info.type = map->map_type;
+ info.id = map->id;
+ info.key_size = map->key_size;
+ info.value_size = map->value_size;
+ info.max_entries = map->max_entries;
+ info.map_flags = map->map_flags;
+ memcpy(info.name, map->name, sizeof(map->name));
+
+ if (map->btf) {
+ info.btf_id = btf_id(map->btf);
+ info.btf_key_type_id = map->btf_key_type_id;
+ info.btf_value_type_id = map->btf_value_type_id;
+ }
+
+ if (bpf_map_is_dev_bound(map)) {
+ err = bpf_map_offload_info_fill(&info, map);
+ if (err)
+ return err;
+ }
+
+ if (copy_to_user(uinfo, &info, info_len) ||
+ put_user(info_len, &uattr->info.info_len))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int bpf_btf_get_info_by_fd(struct file *file,
+ struct btf *btf,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_btf_info __user *uinfo = u64_to_user_ptr(attr->info.info);
+ u32 info_len = attr->info.info_len;
+ int err;
+
+ err = bpf_check_uarg_tail_zero(uinfo, sizeof(*uinfo), info_len);
+ if (err)
+ return err;
+
+ return btf_get_info_by_fd(btf, attr, uattr);
+}
+
+#define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info
+
+static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ int ufd = attr->info.bpf_fd;
+ struct fd f;
+ int err;
+
+ if (CHECK_ATTR(BPF_OBJ_GET_INFO_BY_FD))
+ return -EINVAL;
+
+ f = fdget(ufd);
+ if (!f.file)
+ return -EBADFD;
+
+ if (f.file->f_op == &bpf_prog_fops)
+ err = bpf_prog_get_info_by_fd(f.file, f.file->private_data, attr,
+ uattr);
+ else if (f.file->f_op == &bpf_map_fops)
+ err = bpf_map_get_info_by_fd(f.file, f.file->private_data, attr,
+ uattr);
+ else if (f.file->f_op == &btf_fops)
+ err = bpf_btf_get_info_by_fd(f.file, f.file->private_data, attr, uattr);
+ else
+ err = -EINVAL;
+
+ fdput(f);
+ return err;
+}
+
+#define BPF_BTF_LOAD_LAST_FIELD btf_log_level
+
+static int bpf_btf_load(const union bpf_attr *attr)
+{
+ if (CHECK_ATTR(BPF_BTF_LOAD))
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ return btf_new_fd(attr);
+}
+
+#define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id
+
+static int bpf_btf_get_fd_by_id(const union bpf_attr *attr)
+{
+ if (CHECK_ATTR(BPF_BTF_GET_FD_BY_ID))
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ return btf_get_fd_by_id(attr->btf_id);
+}
+
+static int bpf_task_fd_query_copy(const union bpf_attr *attr,
+ union bpf_attr __user *uattr,
+ u32 prog_id, u32 fd_type,
+ const char *buf, u64 probe_offset,
+ u64 probe_addr)
+{
+ char __user *ubuf = u64_to_user_ptr(attr->task_fd_query.buf);
+ u32 len = buf ? strlen(buf) : 0, input_len;
+ int err = 0;
+
+ if (put_user(len, &uattr->task_fd_query.buf_len))
+ return -EFAULT;
+ input_len = attr->task_fd_query.buf_len;
+ if (input_len && ubuf) {
+ if (!len) {
+ /* nothing to copy, just make ubuf NULL terminated */
+ char zero = '\0';
+
+ if (put_user(zero, ubuf))
+ return -EFAULT;
+ } else if (input_len >= len + 1) {
+ /* ubuf can hold the string with NULL terminator */
+ if (copy_to_user(ubuf, buf, len + 1))
+ return -EFAULT;
+ } else {
+ /* ubuf cannot hold the string with NULL terminator,
+ * do a partial copy with NULL terminator.
+ */
+ char zero = '\0';
+
+ err = -ENOSPC;
+ if (copy_to_user(ubuf, buf, input_len - 1))
+ return -EFAULT;
+ if (put_user(zero, ubuf + input_len - 1))
+ return -EFAULT;
+ }
+ }
+
+ if (put_user(prog_id, &uattr->task_fd_query.prog_id) ||
+ put_user(fd_type, &uattr->task_fd_query.fd_type) ||
+ put_user(probe_offset, &uattr->task_fd_query.probe_offset) ||
+ put_user(probe_addr, &uattr->task_fd_query.probe_addr))
+ return -EFAULT;
+
+ return err;
+}
+
+#define BPF_TASK_FD_QUERY_LAST_FIELD task_fd_query.probe_addr
+
+static int bpf_task_fd_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ pid_t pid = attr->task_fd_query.pid;
+ u32 fd = attr->task_fd_query.fd;
+ const struct perf_event *event;
+ struct files_struct *files;
+ struct task_struct *task;
+ struct file *file;
+ int err;
+
+ if (CHECK_ATTR(BPF_TASK_FD_QUERY))
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (attr->task_fd_query.flags != 0)
+ return -EINVAL;
+
+ task = get_pid_task(find_vpid(pid), PIDTYPE_PID);
+ if (!task)
+ return -ENOENT;
+
+ files = get_files_struct(task);
+ put_task_struct(task);
+ if (!files)
+ return -ENOENT;
+
+ err = 0;
+ spin_lock(&files->file_lock);
+ file = fcheck_files(files, fd);
+ if (!file)
+ err = -EBADF;
+ else
+ get_file(file);
+ spin_unlock(&files->file_lock);
+ put_files_struct(files);
+
+ if (err)
+ goto out;
+
+ if (file->f_op == &bpf_raw_tp_fops) {
+ struct bpf_raw_tracepoint *raw_tp = file->private_data;
+ struct bpf_raw_event_map *btp = raw_tp->btp;
+
+ err = bpf_task_fd_query_copy(attr, uattr,
+ raw_tp->prog->aux->id,
+ BPF_FD_TYPE_RAW_TRACEPOINT,
+ btp->tp->name, 0, 0);
+ goto put_file;
+ }
+
+ event = perf_get_event(file);
+ if (!IS_ERR(event)) {
+ u64 probe_offset, probe_addr;
+ u32 prog_id, fd_type;
+ const char *buf;
+
+ err = bpf_get_perf_event_info(event, &prog_id, &fd_type,
+ &buf, &probe_offset,
+ &probe_addr);
+ if (!err)
+ err = bpf_task_fd_query_copy(attr, uattr, prog_id,
+ fd_type, buf,
+ probe_offset,
+ probe_addr);
+ goto put_file;
+ }
+
+ err = -ENOTSUPP;
+put_file:
+ fput(file);
+out:
+ return err;
+}
+
+SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
+{
+ union bpf_attr attr;
+ int err;
+
+ if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size);
+ if (err)
+ return err;
+ size = min_t(u32, size, sizeof(attr));
+
+ /* copy attributes from user space, may be less than sizeof(bpf_attr) */
+ memset(&attr, 0, sizeof(attr));
+ if (copy_from_user(&attr, uattr, size) != 0)
+ return -EFAULT;
+
+ err = security_bpf(cmd, &attr, size);
+ if (err < 0)
+ return err;
+
+ switch (cmd) {
+ case BPF_MAP_CREATE:
+ err = map_create(&attr);
+ break;
+ case BPF_MAP_LOOKUP_ELEM:
+ err = map_lookup_elem(&attr);
+ break;
+ case BPF_MAP_UPDATE_ELEM:
+ err = map_update_elem(&attr);
+ break;
+ case BPF_MAP_DELETE_ELEM:
+ err = map_delete_elem(&attr);
+ break;
+ case BPF_MAP_GET_NEXT_KEY:
+ err = map_get_next_key(&attr);
+ break;
+ case BPF_PROG_LOAD:
+ err = bpf_prog_load(&attr);
+ break;
+ case BPF_OBJ_PIN:
+ err = bpf_obj_pin(&attr);
+ break;
+ case BPF_OBJ_GET:
+ err = bpf_obj_get(&attr);
+ break;
+ case BPF_PROG_ATTACH:
+ err = bpf_prog_attach(&attr);
+ break;
+ case BPF_PROG_DETACH:
+ err = bpf_prog_detach(&attr);
+ break;
+ case BPF_PROG_QUERY:
+ err = bpf_prog_query(&attr, uattr);
+ break;
+ case BPF_PROG_TEST_RUN:
+ err = bpf_prog_test_run(&attr, uattr);
+ break;
+ case BPF_PROG_GET_NEXT_ID:
+ err = bpf_obj_get_next_id(&attr, uattr,
+ &prog_idr, &prog_idr_lock);
+ break;
+ case BPF_MAP_GET_NEXT_ID:
+ err = bpf_obj_get_next_id(&attr, uattr,
+ &map_idr, &map_idr_lock);
+ break;
+ case BPF_PROG_GET_FD_BY_ID:
+ err = bpf_prog_get_fd_by_id(&attr);
+ break;
+ case BPF_MAP_GET_FD_BY_ID:
+ err = bpf_map_get_fd_by_id(&attr);
+ break;
+ case BPF_OBJ_GET_INFO_BY_FD:
+ err = bpf_obj_get_info_by_fd(&attr, uattr);
+ break;
+ case BPF_RAW_TRACEPOINT_OPEN:
+ err = bpf_raw_tracepoint_open(&attr);
+ break;
+ case BPF_BTF_LOAD:
+ err = bpf_btf_load(&attr);
+ break;
+ case BPF_BTF_GET_FD_BY_ID:
+ err = bpf_btf_get_fd_by_id(&attr);
+ break;
+ case BPF_TASK_FD_QUERY:
+ err = bpf_task_fd_query(&attr, uattr);
+ break;
+ default:
+ err = -EINVAL;
+ break;
+ }
+
+ return err;
+}
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
new file mode 100644
index 000000000..84984c0fc
--- /dev/null
+++ b/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;
+}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
new file mode 100644
index 000000000..30ac8ee82
--- /dev/null
+++ b/kernel/bpf/verifier.c
@@ -0,0 +1,6575 @@
+/* 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/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
+#include <linux/filter.h>
+#include <net/netlink.h>
+#include <linux/file.h>
+#include <linux/vmalloc.h>
+#include <linux/stringify.h>
+#include <linux/bsearch.h>
+#include <linux/sort.h>
+#include <linux/perf_event.h>
+
+#include "disasm.h"
+
+static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
+#define BPF_PROG_TYPE(_id, _name) \
+ [_id] = & _name ## _verifier_ops,
+#define BPF_MAP_TYPE(_id, _ops)
+#include <linux/bpf_types.h>
+#undef BPF_PROG_TYPE
+#undef BPF_MAP_TYPE
+};
+
+/* bpf_check() is a static code analyzer that walks eBPF program
+ * instruction by instruction and updates register/stack state.
+ * All paths of conditional branches are analyzed until 'bpf_exit' insn.
+ *
+ * The first pass is depth-first-search to check that the program is a DAG.
+ * It rejects the following programs:
+ * - larger than BPF_MAXINSNS insns
+ * - if loop is present (detected via back-edge)
+ * - unreachable insns exist (shouldn't be a forest. program = one function)
+ * - out of bounds or malformed jumps
+ * The second pass is all possible path descent from the 1st insn.
+ * Since it's analyzing all pathes through the program, the length of the
+ * analysis is limited to 64k insn, which may be hit even if total number of
+ * insn is less then 4K, but there are too many branches that change stack/regs.
+ * Number of 'branches to be analyzed' is limited to 1k
+ *
+ * On entry to each instruction, each register has a type, and the instruction
+ * changes the types of the registers depending on instruction semantics.
+ * If instruction is BPF_MOV64_REG(BPF_REG_1, BPF_REG_5), then type of R5 is
+ * copied to R1.
+ *
+ * All registers are 64-bit.
+ * R0 - return register
+ * R1-R5 argument passing registers
+ * R6-R9 callee saved registers
+ * R10 - frame pointer read-only
+ *
+ * At the start of BPF program the register R1 contains a pointer to bpf_context
+ * and has type PTR_TO_CTX.
+ *
+ * Verifier tracks arithmetic operations on pointers in case:
+ * BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ * BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -20),
+ * 1st insn copies R10 (which has FRAME_PTR) type into R1
+ * and 2nd arithmetic instruction is pattern matched to recognize
+ * that it wants to construct a pointer to some element within stack.
+ * So after 2nd insn, the register R1 has type PTR_TO_STACK
+ * (and -20 constant is saved for further stack bounds checking).
+ * Meaning that this reg is a pointer to stack plus known immediate constant.
+ *
+ * Most of the time the registers have SCALAR_VALUE type, which
+ * means the register has some value, but it's not a valid pointer.
+ * (like pointer plus pointer becomes SCALAR_VALUE type)
+ *
+ * When verifier sees load or store instructions the type of base register
+ * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK. These are three pointer
+ * types recognized by check_mem_access() function.
+ *
+ * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value'
+ * and the range of [ptr, ptr + map's value_size) is accessible.
+ *
+ * registers used to pass values to function calls are checked against
+ * function argument constraints.
+ *
+ * ARG_PTR_TO_MAP_KEY is one of such argument constraints.
+ * It means that the register type passed to this function must be
+ * PTR_TO_STACK and it will be used inside the function as
+ * 'pointer to map element key'
+ *
+ * For example the argument constraints for bpf_map_lookup_elem():
+ * .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
+ * .arg1_type = ARG_CONST_MAP_PTR,
+ * .arg2_type = ARG_PTR_TO_MAP_KEY,
+ *
+ * ret_type says that this function returns 'pointer to map elem value or null'
+ * function expects 1st argument to be a const pointer to 'struct bpf_map' and
+ * 2nd argument should be a pointer to stack, which will be used inside
+ * the helper function as a pointer to map element key.
+ *
+ * On the kernel side the helper function looks like:
+ * u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+ * {
+ * struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
+ * void *key = (void *) (unsigned long) r2;
+ * void *value;
+ *
+ * here kernel can access 'key' and 'map' pointers safely, knowing that
+ * [key, key + map->key_size) bytes are valid and were initialized on
+ * the stack of eBPF program.
+ * }
+ *
+ * Corresponding eBPF program may look like:
+ * BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), // after this insn R2 type is FRAME_PTR
+ * BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK
+ * BPF_LD_MAP_FD(BPF_REG_1, map_fd), // after this insn R1 type is CONST_PTR_TO_MAP
+ * BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ * here verifier looks at prototype of map_lookup_elem() and sees:
+ * .arg1_type == ARG_CONST_MAP_PTR and R1->type == CONST_PTR_TO_MAP, which is ok,
+ * Now verifier knows that this map has key of R1->map_ptr->key_size bytes
+ *
+ * Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far,
+ * Now verifier checks that [R2, R2 + map's key_size) are within stack limits
+ * and were initialized prior to this call.
+ * If it's ok, then verifier allows this BPF_CALL insn and looks at
+ * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets
+ * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function
+ * returns ether pointer to map value or NULL.
+ *
+ * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off'
+ * insn, the register holding that pointer in the true branch changes state to
+ * PTR_TO_MAP_VALUE and the same register changes state to CONST_IMM in the false
+ * branch. See check_cond_jmp_op().
+ *
+ * After the call R0 is set to return type of the function and registers R1-R5
+ * are set to NOT_INIT to indicate that they are no longer readable.
+ */
+
+/* verifier_state + insn_idx are pushed to stack when branch is encountered */
+struct bpf_verifier_stack_elem {
+ /* verifer state is 'st'
+ * before processing instruction 'insn_idx'
+ * and after processing instruction 'prev_insn_idx'
+ */
+ struct bpf_verifier_state st;
+ int insn_idx;
+ int prev_insn_idx;
+ struct bpf_verifier_stack_elem *next;
+};
+
+#define BPF_COMPLEXITY_LIMIT_INSNS 131072
+#define BPF_COMPLEXITY_LIMIT_STACK 1024
+#define BPF_COMPLEXITY_LIMIT_STATES 64
+
+#define BPF_MAP_PTR_UNPRIV 1UL
+#define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \
+ POISON_POINTER_DELTA))
+#define BPF_MAP_PTR(X) ((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV))
+
+static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux)
+{
+ return BPF_MAP_PTR(aux->map_state) == BPF_MAP_PTR_POISON;
+}
+
+static bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux)
+{
+ return aux->map_state & BPF_MAP_PTR_UNPRIV;
+}
+
+static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux,
+ const struct bpf_map *map, bool unpriv)
+{
+ BUILD_BUG_ON((unsigned long)BPF_MAP_PTR_POISON & BPF_MAP_PTR_UNPRIV);
+ unpriv |= bpf_map_ptr_unpriv(aux);
+ aux->map_state = (unsigned long)map |
+ (unpriv ? BPF_MAP_PTR_UNPRIV : 0UL);
+}
+
+struct bpf_call_arg_meta {
+ struct bpf_map *map_ptr;
+ bool raw_mode;
+ bool pkt_access;
+ int regno;
+ int access_size;
+ u64 msize_max_value;
+};
+
+static DEFINE_MUTEX(bpf_verifier_lock);
+
+void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt,
+ va_list args)
+{
+ unsigned int n;
+
+ n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args);
+
+ WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1,
+ "verifier log line truncated - local buffer too short\n");
+
+ n = min(log->len_total - log->len_used - 1, n);
+ log->kbuf[n] = '\0';
+
+ if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1))
+ log->len_used += n;
+ else
+ log->ubuf = NULL;
+}
+
+/* log_level controls verbosity level of eBPF verifier.
+ * bpf_verifier_log_write() is used to dump the verification trace to the log,
+ * so the user can figure out what's wrong with the program
+ */
+__printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
+ const char *fmt, ...)
+{
+ va_list args;
+
+ if (!bpf_verifier_log_needed(&env->log))
+ return;
+
+ va_start(args, fmt);
+ bpf_verifier_vlog(&env->log, fmt, args);
+ va_end(args);
+}
+EXPORT_SYMBOL_GPL(bpf_verifier_log_write);
+
+__printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
+{
+ struct bpf_verifier_env *env = private_data;
+ va_list args;
+
+ if (!bpf_verifier_log_needed(&env->log))
+ return;
+
+ va_start(args, fmt);
+ bpf_verifier_vlog(&env->log, fmt, args);
+ va_end(args);
+}
+
+static bool type_is_pkt_pointer(enum bpf_reg_type type)
+{
+ return type == PTR_TO_PACKET ||
+ type == PTR_TO_PACKET_META;
+}
+
+/* string representation of 'enum bpf_reg_type' */
+static const char * const reg_type_str[] = {
+ [NOT_INIT] = "?",
+ [SCALAR_VALUE] = "inv",
+ [PTR_TO_CTX] = "ctx",
+ [CONST_PTR_TO_MAP] = "map_ptr",
+ [PTR_TO_MAP_VALUE] = "map_value",
+ [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null",
+ [PTR_TO_STACK] = "fp",
+ [PTR_TO_PACKET] = "pkt",
+ [PTR_TO_PACKET_META] = "pkt_meta",
+ [PTR_TO_PACKET_END] = "pkt_end",
+};
+
+static void print_liveness(struct bpf_verifier_env *env,
+ enum bpf_reg_liveness live)
+{
+ if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN))
+ verbose(env, "_");
+ if (live & REG_LIVE_READ)
+ verbose(env, "r");
+ if (live & REG_LIVE_WRITTEN)
+ verbose(env, "w");
+}
+
+static struct bpf_func_state *func(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg)
+{
+ struct bpf_verifier_state *cur = env->cur_state;
+
+ return cur->frame[reg->frameno];
+}
+
+static void print_verifier_state(struct bpf_verifier_env *env,
+ const struct bpf_func_state *state)
+{
+ const struct bpf_reg_state *reg;
+ enum bpf_reg_type t;
+ int i;
+
+ if (state->frameno)
+ verbose(env, " frame%d:", state->frameno);
+ for (i = 0; i < MAX_BPF_REG; i++) {
+ reg = &state->regs[i];
+ t = reg->type;
+ if (t == NOT_INIT)
+ continue;
+ verbose(env, " R%d", i);
+ print_liveness(env, reg->live);
+ verbose(env, "=%s", reg_type_str[t]);
+ if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
+ tnum_is_const(reg->var_off)) {
+ /* reg->off should be 0 for SCALAR_VALUE */
+ verbose(env, "%lld", reg->var_off.value + reg->off);
+ if (t == PTR_TO_STACK)
+ verbose(env, ",call_%d", func(env, reg)->callsite);
+ } else {
+ verbose(env, "(id=%d", reg->id);
+ if (t != SCALAR_VALUE)
+ verbose(env, ",off=%d", reg->off);
+ if (type_is_pkt_pointer(t))
+ verbose(env, ",r=%d", reg->range);
+ else if (t == CONST_PTR_TO_MAP ||
+ t == PTR_TO_MAP_VALUE ||
+ t == PTR_TO_MAP_VALUE_OR_NULL)
+ verbose(env, ",ks=%d,vs=%d",
+ reg->map_ptr->key_size,
+ reg->map_ptr->value_size);
+ if (tnum_is_const(reg->var_off)) {
+ /* Typically an immediate SCALAR_VALUE, but
+ * could be a pointer whose offset is too big
+ * for reg->off
+ */
+ verbose(env, ",imm=%llx", reg->var_off.value);
+ } else {
+ if (reg->smin_value != reg->umin_value &&
+ reg->smin_value != S64_MIN)
+ verbose(env, ",smin_value=%lld",
+ (long long)reg->smin_value);
+ if (reg->smax_value != reg->umax_value &&
+ reg->smax_value != S64_MAX)
+ verbose(env, ",smax_value=%lld",
+ (long long)reg->smax_value);
+ if (reg->umin_value != 0)
+ verbose(env, ",umin_value=%llu",
+ (unsigned long long)reg->umin_value);
+ if (reg->umax_value != U64_MAX)
+ verbose(env, ",umax_value=%llu",
+ (unsigned long long)reg->umax_value);
+ if (!tnum_is_unknown(reg->var_off)) {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, ",var_off=%s", tn_buf);
+ }
+ }
+ verbose(env, ")");
+ }
+ }
+ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+ if (state->stack[i].slot_type[0] == STACK_SPILL) {
+ verbose(env, " fp%d",
+ (-i - 1) * BPF_REG_SIZE);
+ print_liveness(env, state->stack[i].spilled_ptr.live);
+ verbose(env, "=%s",
+ reg_type_str[state->stack[i].spilled_ptr.type]);
+ }
+ if (state->stack[i].slot_type[0] == STACK_ZERO)
+ verbose(env, " fp%d=0", (-i - 1) * BPF_REG_SIZE);
+ }
+ verbose(env, "\n");
+}
+
+static int copy_stack_state(struct bpf_func_state *dst,
+ const struct bpf_func_state *src)
+{
+ if (!src->stack)
+ return 0;
+ if (WARN_ON_ONCE(dst->allocated_stack < src->allocated_stack)) {
+ /* internal bug, make state invalid to reject the program */
+ memset(dst, 0, sizeof(*dst));
+ return -EFAULT;
+ }
+ memcpy(dst->stack, src->stack,
+ sizeof(*src->stack) * (src->allocated_stack / BPF_REG_SIZE));
+ return 0;
+}
+
+/* do_check() starts with zero-sized stack in struct bpf_verifier_state to
+ * make it consume minimal amount of memory. check_stack_write() access from
+ * the program calls into realloc_func_state() to grow the stack size.
+ * Note there is a non-zero parent pointer inside each reg of bpf_verifier_state
+ * which this function copies over. It points to corresponding reg in previous
+ * bpf_verifier_state which is never reallocated
+ */
+static int realloc_func_state(struct bpf_func_state *state, int size,
+ bool copy_old)
+{
+ u32 old_size = state->allocated_stack;
+ struct bpf_stack_state *new_stack;
+ int slot = size / BPF_REG_SIZE;
+
+ if (size <= old_size || !size) {
+ if (copy_old)
+ return 0;
+ state->allocated_stack = slot * BPF_REG_SIZE;
+ if (!size && old_size) {
+ kfree(state->stack);
+ state->stack = NULL;
+ }
+ return 0;
+ }
+ new_stack = kmalloc_array(slot, sizeof(struct bpf_stack_state),
+ GFP_KERNEL);
+ if (!new_stack)
+ return -ENOMEM;
+ if (copy_old) {
+ if (state->stack)
+ memcpy(new_stack, state->stack,
+ sizeof(*new_stack) * (old_size / BPF_REG_SIZE));
+ memset(new_stack + old_size / BPF_REG_SIZE, 0,
+ sizeof(*new_stack) * (size - old_size) / BPF_REG_SIZE);
+ }
+ state->allocated_stack = slot * BPF_REG_SIZE;
+ kfree(state->stack);
+ state->stack = new_stack;
+ return 0;
+}
+
+static void free_func_state(struct bpf_func_state *state)
+{
+ if (!state)
+ return;
+ kfree(state->stack);
+ kfree(state);
+}
+
+static void free_verifier_state(struct bpf_verifier_state *state,
+ bool free_self)
+{
+ int i;
+
+ for (i = 0; i <= state->curframe; i++) {
+ free_func_state(state->frame[i]);
+ state->frame[i] = NULL;
+ }
+ if (free_self)
+ kfree(state);
+}
+
+/* copy verifier state from src to dst growing dst stack space
+ * when necessary to accommodate larger src stack
+ */
+static int copy_func_state(struct bpf_func_state *dst,
+ const struct bpf_func_state *src)
+{
+ int err;
+
+ err = realloc_func_state(dst, src->allocated_stack, false);
+ if (err)
+ return err;
+ memcpy(dst, src, offsetof(struct bpf_func_state, allocated_stack));
+ return copy_stack_state(dst, src);
+}
+
+static int copy_verifier_state(struct bpf_verifier_state *dst_state,
+ const struct bpf_verifier_state *src)
+{
+ struct bpf_func_state *dst;
+ int i, err;
+
+ /* if dst has more stack frames then src frame, free them */
+ for (i = src->curframe + 1; i <= dst_state->curframe; i++) {
+ free_func_state(dst_state->frame[i]);
+ dst_state->frame[i] = NULL;
+ }
+ dst_state->speculative = src->speculative;
+ dst_state->curframe = src->curframe;
+ for (i = 0; i <= src->curframe; i++) {
+ dst = dst_state->frame[i];
+ if (!dst) {
+ dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+ if (!dst)
+ return -ENOMEM;
+ dst_state->frame[i] = dst;
+ }
+ err = copy_func_state(dst, src->frame[i]);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
+static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
+ int *insn_idx)
+{
+ struct bpf_verifier_state *cur = env->cur_state;
+ struct bpf_verifier_stack_elem *elem, *head = env->head;
+ int err;
+
+ if (env->head == NULL)
+ return -ENOENT;
+
+ if (cur) {
+ err = copy_verifier_state(cur, &head->st);
+ if (err)
+ return err;
+ }
+ if (insn_idx)
+ *insn_idx = head->insn_idx;
+ if (prev_insn_idx)
+ *prev_insn_idx = head->prev_insn_idx;
+ elem = head->next;
+ free_verifier_state(&head->st, false);
+ kfree(head);
+ env->head = elem;
+ env->stack_size--;
+ return 0;
+}
+
+static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
+ int insn_idx, int prev_insn_idx,
+ bool speculative)
+{
+ struct bpf_verifier_state *cur = env->cur_state;
+ struct bpf_verifier_stack_elem *elem;
+ int err;
+
+ elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL);
+ if (!elem)
+ goto err;
+
+ elem->insn_idx = insn_idx;
+ elem->prev_insn_idx = prev_insn_idx;
+ elem->next = env->head;
+ env->head = elem;
+ env->stack_size++;
+ err = copy_verifier_state(&elem->st, cur);
+ if (err)
+ goto err;
+ elem->st.speculative |= speculative;
+ if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) {
+ verbose(env, "BPF program is too complex\n");
+ goto err;
+ }
+ return &elem->st;
+err:
+ free_verifier_state(env->cur_state, true);
+ env->cur_state = NULL;
+ /* pop all elements and return */
+ while (!pop_stack(env, NULL, NULL));
+ return NULL;
+}
+
+#define CALLER_SAVED_REGS 6
+static const int caller_saved[CALLER_SAVED_REGS] = {
+ BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
+};
+
+static void __mark_reg_not_init(struct bpf_reg_state *reg);
+
+/* Mark the unknown part of a register (variable offset or scalar value) as
+ * known to have the value @imm.
+ */
+static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm)
+{
+ /* Clear id, off, and union(map_ptr, range) */
+ memset(((u8 *)reg) + sizeof(reg->type), 0,
+ offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type));
+ reg->var_off = tnum_const(imm);
+ reg->smin_value = (s64)imm;
+ reg->smax_value = (s64)imm;
+ reg->umin_value = imm;
+ reg->umax_value = imm;
+}
+
+/* Mark the 'variable offset' part of a register as zero. This should be
+ * used only on registers holding a pointer type.
+ */
+static void __mark_reg_known_zero(struct bpf_reg_state *reg)
+{
+ __mark_reg_known(reg, 0);
+}
+
+static void __mark_reg_const_zero(struct bpf_reg_state *reg)
+{
+ __mark_reg_known(reg, 0);
+ reg->type = SCALAR_VALUE;
+}
+
+static void mark_reg_known_zero(struct bpf_verifier_env *env,
+ struct bpf_reg_state *regs, u32 regno)
+{
+ if (WARN_ON(regno >= MAX_BPF_REG)) {
+ verbose(env, "mark_reg_known_zero(regs, %u)\n", regno);
+ /* Something bad happened, let's kill all regs */
+ for (regno = 0; regno < MAX_BPF_REG; regno++)
+ __mark_reg_not_init(regs + regno);
+ return;
+ }
+ __mark_reg_known_zero(regs + regno);
+}
+
+static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg)
+{
+ return type_is_pkt_pointer(reg->type);
+}
+
+static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg)
+{
+ return reg_is_pkt_pointer(reg) ||
+ reg->type == PTR_TO_PACKET_END;
+}
+
+/* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */
+static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg,
+ enum bpf_reg_type which)
+{
+ /* The register can already have a range from prior markings.
+ * This is fine as long as it hasn't been advanced from its
+ * origin.
+ */
+ return reg->type == which &&
+ reg->id == 0 &&
+ reg->off == 0 &&
+ tnum_equals_const(reg->var_off, 0);
+}
+
+/* Attempts to improve min/max values based on var_off information */
+static void __update_reg_bounds(struct bpf_reg_state *reg)
+{
+ /* min signed is max(sign bit) | min(other bits) */
+ reg->smin_value = max_t(s64, reg->smin_value,
+ reg->var_off.value | (reg->var_off.mask & S64_MIN));
+ /* max signed is min(sign bit) | max(other bits) */
+ reg->smax_value = min_t(s64, reg->smax_value,
+ reg->var_off.value | (reg->var_off.mask & S64_MAX));
+ reg->umin_value = max(reg->umin_value, reg->var_off.value);
+ reg->umax_value = min(reg->umax_value,
+ reg->var_off.value | reg->var_off.mask);
+}
+
+/* Uses signed min/max values to inform unsigned, and vice-versa */
+static void __reg_deduce_bounds(struct bpf_reg_state *reg)
+{
+ /* Learn sign from signed bounds.
+ * If we cannot cross the sign boundary, then signed and unsigned bounds
+ * are the same, so combine. This works even in the negative case, e.g.
+ * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
+ */
+ if (reg->smin_value >= 0 || reg->smax_value < 0) {
+ reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
+ reg->umin_value);
+ reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
+ reg->umax_value);
+ return;
+ }
+ /* Learn sign from unsigned bounds. Signed bounds cross the sign
+ * boundary, so we must be careful.
+ */
+ if ((s64)reg->umax_value >= 0) {
+ /* Positive. We can't learn anything from the smin, but smax
+ * is positive, hence safe.
+ */
+ reg->smin_value = reg->umin_value;
+ reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
+ reg->umax_value);
+ } else if ((s64)reg->umin_value < 0) {
+ /* Negative. We can't learn anything from the smax, but smin
+ * is negative, hence safe.
+ */
+ reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
+ reg->umin_value);
+ reg->smax_value = reg->umax_value;
+ }
+}
+
+/* Attempts to improve var_off based on unsigned min/max information */
+static void __reg_bound_offset(struct bpf_reg_state *reg)
+{
+ reg->var_off = tnum_intersect(reg->var_off,
+ tnum_range(reg->umin_value,
+ reg->umax_value));
+}
+
+/* Reset the min/max bounds of a register */
+static void __mark_reg_unbounded(struct bpf_reg_state *reg)
+{
+ reg->smin_value = S64_MIN;
+ reg->smax_value = S64_MAX;
+ reg->umin_value = 0;
+ reg->umax_value = U64_MAX;
+}
+
+/* Mark a register as having a completely unknown (scalar) value. */
+static void __mark_reg_unknown(struct bpf_reg_state *reg)
+{
+ /*
+ * Clear type, id, off, and union(map_ptr, range) and
+ * padding between 'type' and union
+ */
+ memset(reg, 0, offsetof(struct bpf_reg_state, var_off));
+ reg->type = SCALAR_VALUE;
+ reg->var_off = tnum_unknown;
+ reg->frameno = 0;
+ __mark_reg_unbounded(reg);
+}
+
+static void mark_reg_unknown(struct bpf_verifier_env *env,
+ struct bpf_reg_state *regs, u32 regno)
+{
+ if (WARN_ON(regno >= MAX_BPF_REG)) {
+ verbose(env, "mark_reg_unknown(regs, %u)\n", regno);
+ /* Something bad happened, let's kill all regs except FP */
+ for (regno = 0; regno < BPF_REG_FP; regno++)
+ __mark_reg_not_init(regs + regno);
+ return;
+ }
+ __mark_reg_unknown(regs + regno);
+}
+
+static void __mark_reg_not_init(struct bpf_reg_state *reg)
+{
+ __mark_reg_unknown(reg);
+ reg->type = NOT_INIT;
+}
+
+static void mark_reg_not_init(struct bpf_verifier_env *env,
+ struct bpf_reg_state *regs, u32 regno)
+{
+ if (WARN_ON(regno >= MAX_BPF_REG)) {
+ verbose(env, "mark_reg_not_init(regs, %u)\n", regno);
+ /* Something bad happened, let's kill all regs except FP */
+ for (regno = 0; regno < BPF_REG_FP; regno++)
+ __mark_reg_not_init(regs + regno);
+ return;
+ }
+ __mark_reg_not_init(regs + regno);
+}
+
+static void init_reg_state(struct bpf_verifier_env *env,
+ struct bpf_func_state *state)
+{
+ struct bpf_reg_state *regs = state->regs;
+ int i;
+
+ for (i = 0; i < MAX_BPF_REG; i++) {
+ mark_reg_not_init(env, regs, i);
+ regs[i].live = REG_LIVE_NONE;
+ regs[i].parent = NULL;
+ }
+
+ /* frame pointer */
+ regs[BPF_REG_FP].type = PTR_TO_STACK;
+ mark_reg_known_zero(env, regs, BPF_REG_FP);
+ regs[BPF_REG_FP].frameno = state->frameno;
+
+ /* 1st arg to a function */
+ regs[BPF_REG_1].type = PTR_TO_CTX;
+ mark_reg_known_zero(env, regs, BPF_REG_1);
+}
+
+#define BPF_MAIN_FUNC (-1)
+static void init_func_state(struct bpf_verifier_env *env,
+ struct bpf_func_state *state,
+ int callsite, int frameno, int subprogno)
+{
+ state->callsite = callsite;
+ state->frameno = frameno;
+ state->subprogno = subprogno;
+ init_reg_state(env, state);
+}
+
+enum reg_arg_type {
+ SRC_OP, /* register is used as source operand */
+ DST_OP, /* register is used as destination operand */
+ DST_OP_NO_MARK /* same as above, check only, don't mark */
+};
+
+static int cmp_subprogs(const void *a, const void *b)
+{
+ return ((struct bpf_subprog_info *)a)->start -
+ ((struct bpf_subprog_info *)b)->start;
+}
+
+static int find_subprog(struct bpf_verifier_env *env, int off)
+{
+ struct bpf_subprog_info *p;
+
+ p = bsearch(&off, env->subprog_info, env->subprog_cnt,
+ sizeof(env->subprog_info[0]), cmp_subprogs);
+ if (!p)
+ return -ENOENT;
+ return p - env->subprog_info;
+
+}
+
+static int add_subprog(struct bpf_verifier_env *env, int off)
+{
+ int insn_cnt = env->prog->len;
+ int ret;
+
+ if (off >= insn_cnt || off < 0) {
+ verbose(env, "call to invalid destination\n");
+ return -EINVAL;
+ }
+ ret = find_subprog(env, off);
+ if (ret >= 0)
+ return 0;
+ if (env->subprog_cnt >= BPF_MAX_SUBPROGS) {
+ verbose(env, "too many subprograms\n");
+ return -E2BIG;
+ }
+ env->subprog_info[env->subprog_cnt++].start = off;
+ sort(env->subprog_info, env->subprog_cnt,
+ sizeof(env->subprog_info[0]), cmp_subprogs, NULL);
+ return 0;
+}
+
+static int check_subprogs(struct bpf_verifier_env *env)
+{
+ int i, ret, subprog_start, subprog_end, off, cur_subprog = 0;
+ struct bpf_subprog_info *subprog = env->subprog_info;
+ struct bpf_insn *insn = env->prog->insnsi;
+ int insn_cnt = env->prog->len;
+
+ /* Add entry function. */
+ ret = add_subprog(env, 0);
+ if (ret < 0)
+ return ret;
+
+ /* determine subprog starts. The end is one before the next starts */
+ for (i = 0; i < insn_cnt; i++) {
+ if (insn[i].code != (BPF_JMP | BPF_CALL))
+ continue;
+ if (insn[i].src_reg != BPF_PSEUDO_CALL)
+ continue;
+ if (!env->allow_ptr_leaks) {
+ verbose(env, "function calls to other bpf functions are allowed for root only\n");
+ return -EPERM;
+ }
+ if (bpf_prog_is_dev_bound(env->prog->aux)) {
+ verbose(env, "function calls in offloaded programs are not supported yet\n");
+ return -EINVAL;
+ }
+ ret = add_subprog(env, i + insn[i].imm + 1);
+ if (ret < 0)
+ return ret;
+ }
+
+ /* Add a fake 'exit' subprog which could simplify subprog iteration
+ * logic. 'subprog_cnt' should not be increased.
+ */
+ subprog[env->subprog_cnt].start = insn_cnt;
+
+ if (env->log.level > 1)
+ for (i = 0; i < env->subprog_cnt; i++)
+ verbose(env, "func#%d @%d\n", i, subprog[i].start);
+
+ /* now check that all jumps are within the same subprog */
+ subprog_start = subprog[cur_subprog].start;
+ subprog_end = subprog[cur_subprog + 1].start;
+ for (i = 0; i < insn_cnt; i++) {
+ u8 code = insn[i].code;
+
+ if (BPF_CLASS(code) != BPF_JMP)
+ goto next;
+ if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
+ goto next;
+ off = i + insn[i].off + 1;
+ if (off < subprog_start || off >= subprog_end) {
+ verbose(env, "jump out of range from insn %d to %d\n", i, off);
+ return -EINVAL;
+ }
+next:
+ if (i == subprog_end - 1) {
+ /* to avoid fall-through from one subprog into another
+ * the last insn of the subprog should be either exit
+ * or unconditional jump back
+ */
+ if (code != (BPF_JMP | BPF_EXIT) &&
+ code != (BPF_JMP | BPF_JA)) {
+ verbose(env, "last insn is not an exit or jmp\n");
+ return -EINVAL;
+ }
+ subprog_start = subprog_end;
+ cur_subprog++;
+ if (cur_subprog < env->subprog_cnt)
+ subprog_end = subprog[cur_subprog + 1].start;
+ }
+ }
+ return 0;
+}
+
+/* Parentage chain of this register (or stack slot) should take care of all
+ * issues like callee-saved registers, stack slot allocation time, etc.
+ */
+static int mark_reg_read(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *state,
+ struct bpf_reg_state *parent)
+{
+ bool writes = parent == state->parent; /* Observe write marks */
+
+ while (parent) {
+ /* if read wasn't screened by an earlier write ... */
+ if (writes && state->live & REG_LIVE_WRITTEN)
+ break;
+ /* ... then we depend on parent's value */
+ parent->live |= REG_LIVE_READ;
+ state = parent;
+ parent = state->parent;
+ writes = true;
+ }
+ return 0;
+}
+
+static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
+ enum reg_arg_type t)
+{
+ struct bpf_verifier_state *vstate = env->cur_state;
+ struct bpf_func_state *state = vstate->frame[vstate->curframe];
+ struct bpf_reg_state *regs = state->regs;
+
+ if (regno >= MAX_BPF_REG) {
+ verbose(env, "R%d is invalid\n", regno);
+ return -EINVAL;
+ }
+
+ if (t == SRC_OP) {
+ /* check whether register used as source operand can be read */
+ if (regs[regno].type == NOT_INIT) {
+ verbose(env, "R%d !read_ok\n", regno);
+ return -EACCES;
+ }
+ /* We don't need to worry about FP liveness because it's read-only */
+ if (regno != BPF_REG_FP)
+ return mark_reg_read(env, &regs[regno],
+ regs[regno].parent);
+ } else {
+ /* check whether register used as dest operand can be written to */
+ if (regno == BPF_REG_FP) {
+ verbose(env, "frame pointer is read only\n");
+ return -EACCES;
+ }
+ regs[regno].live |= REG_LIVE_WRITTEN;
+ if (t == DST_OP)
+ mark_reg_unknown(env, regs, regno);
+ }
+ return 0;
+}
+
+static bool is_spillable_regtype(enum bpf_reg_type type)
+{
+ switch (type) {
+ case PTR_TO_MAP_VALUE:
+ case PTR_TO_MAP_VALUE_OR_NULL:
+ case PTR_TO_STACK:
+ case PTR_TO_CTX:
+ case PTR_TO_PACKET:
+ case PTR_TO_PACKET_META:
+ case PTR_TO_PACKET_END:
+ case CONST_PTR_TO_MAP:
+ return true;
+ default:
+ return false;
+ }
+}
+
+/* Does this register contain a constant zero? */
+static bool register_is_null(struct bpf_reg_state *reg)
+{
+ return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0);
+}
+
+static bool register_is_const(struct bpf_reg_state *reg)
+{
+ return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off);
+}
+
+static void save_register_state(struct bpf_func_state *state,
+ int spi, struct bpf_reg_state *reg)
+{
+ int i;
+
+ state->stack[spi].spilled_ptr = *reg;
+ state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
+
+ for (i = 0; i < BPF_REG_SIZE; i++)
+ state->stack[spi].slot_type[i] = STACK_SPILL;
+}
+
+/* check_stack_read/write functions track spill/fill of registers,
+ * stack boundary and alignment are checked in check_mem_access()
+ */
+static int check_stack_write(struct bpf_verifier_env *env,
+ struct bpf_func_state *state, /* func where register points to */
+ int off, int size, int value_regno, int insn_idx)
+{
+ struct bpf_func_state *cur; /* state of the current function */
+ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
+ struct bpf_reg_state *reg = NULL;
+
+ err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE),
+ true);
+ if (err)
+ return err;
+ /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
+ * so it's aligned access and [off, off + size) are within stack limits
+ */
+ if (!env->allow_ptr_leaks &&
+ state->stack[spi].slot_type[0] == STACK_SPILL &&
+ size != BPF_REG_SIZE) {
+ verbose(env, "attempt to corrupt spilled pointer on stack\n");
+ return -EACCES;
+ }
+
+ cur = env->cur_state->frame[env->cur_state->curframe];
+ if (value_regno >= 0)
+ reg = &cur->regs[value_regno];
+ if (!env->allow_ptr_leaks) {
+ bool sanitize = reg && is_spillable_regtype(reg->type);
+
+ for (i = 0; i < size; i++) {
+ if (state->stack[spi].slot_type[i] == STACK_INVALID) {
+ sanitize = true;
+ break;
+ }
+ }
+
+ if (sanitize)
+ env->insn_aux_data[insn_idx].sanitize_stack_spill = true;
+ }
+
+ if (reg && size == BPF_REG_SIZE && register_is_const(reg) &&
+ !register_is_null(reg) && env->allow_ptr_leaks) {
+ save_register_state(state, spi, reg);
+ } else if (reg && is_spillable_regtype(reg->type)) {
+ /* register containing pointer is being spilled into stack */
+ if (size != BPF_REG_SIZE) {
+ verbose(env, "invalid size of register spill\n");
+ return -EACCES;
+ }
+ if (state != cur && reg->type == PTR_TO_STACK) {
+ verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
+ return -EINVAL;
+ }
+ save_register_state(state, spi, reg);
+ } else {
+ u8 type = STACK_MISC;
+
+ /* regular write of data into stack destroys any spilled ptr */
+ state->stack[spi].spilled_ptr.type = NOT_INIT;
+ /* Mark slots as STACK_MISC if they belonged to spilled ptr. */
+ if (state->stack[spi].slot_type[0] == STACK_SPILL)
+ for (i = 0; i < BPF_REG_SIZE; i++)
+ state->stack[spi].slot_type[i] = STACK_MISC;
+
+ /* only mark the slot as written if all 8 bytes were written
+ * otherwise read propagation may incorrectly stop too soon
+ * when stack slots are partially written.
+ * This heuristic means that read propagation will be
+ * conservative, since it will add reg_live_read marks
+ * to stack slots all the way to first state when programs
+ * writes+reads less than 8 bytes
+ */
+ if (size == BPF_REG_SIZE)
+ state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
+
+ /* when we zero initialize stack slots mark them as such */
+ if (reg && register_is_null(reg))
+ type = STACK_ZERO;
+
+ /* Mark slots affected by this stack write. */
+ for (i = 0; i < size; i++)
+ state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
+ type;
+ }
+ return 0;
+}
+
+static int check_stack_read(struct bpf_verifier_env *env,
+ struct bpf_func_state *reg_state /* func where register points to */,
+ int off, int size, int value_regno)
+{
+ struct bpf_verifier_state *vstate = env->cur_state;
+ struct bpf_func_state *state = vstate->frame[vstate->curframe];
+ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
+ struct bpf_reg_state *reg;
+ u8 *stype;
+
+ if (reg_state->allocated_stack <= slot) {
+ verbose(env, "invalid read from stack off %d+0 size %d\n",
+ off, size);
+ return -EACCES;
+ }
+ stype = reg_state->stack[spi].slot_type;
+ reg = &reg_state->stack[spi].spilled_ptr;
+
+ if (stype[0] == STACK_SPILL) {
+ if (size != BPF_REG_SIZE) {
+ if (reg->type != SCALAR_VALUE) {
+ verbose(env, "invalid size of register fill\n");
+ return -EACCES;
+ }
+ if (value_regno >= 0) {
+ mark_reg_unknown(env, state->regs, value_regno);
+ state->regs[value_regno].live |= REG_LIVE_WRITTEN;
+ }
+ mark_reg_read(env, reg, reg->parent);
+ return 0;
+ }
+ for (i = 1; i < BPF_REG_SIZE; i++) {
+ if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) {
+ verbose(env, "corrupted spill memory\n");
+ return -EACCES;
+ }
+ }
+
+ if (value_regno >= 0) {
+ /* restore register state from stack */
+ state->regs[value_regno] = *reg;
+ /* mark reg as written since spilled pointer state likely
+ * has its liveness marks cleared by is_state_visited()
+ * which resets stack/reg liveness for state transitions
+ */
+ state->regs[value_regno].live |= REG_LIVE_WRITTEN;
+ }
+ mark_reg_read(env, reg, reg->parent);
+ } else {
+ int zeros = 0;
+
+ for (i = 0; i < size; i++) {
+ if (stype[(slot - i) % BPF_REG_SIZE] == STACK_MISC)
+ continue;
+ if (stype[(slot - i) % BPF_REG_SIZE] == STACK_ZERO) {
+ zeros++;
+ continue;
+ }
+ verbose(env, "invalid read from stack off %d+%d size %d\n",
+ off, i, size);
+ return -EACCES;
+ }
+ mark_reg_read(env, reg, reg->parent);
+ if (value_regno >= 0) {
+ if (zeros == size) {
+ /* any size read into register is zero extended,
+ * so the whole register == const_zero
+ */
+ __mark_reg_const_zero(&state->regs[value_regno]);
+ } else {
+ /* have read misc data from the stack */
+ mark_reg_unknown(env, state->regs, value_regno);
+ }
+ state->regs[value_regno].live |= REG_LIVE_WRITTEN;
+ }
+ }
+ return 0;
+}
+
+static int check_stack_access(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
+ int off, int size)
+{
+ /* Stack accesses must be at a fixed offset, so that we
+ * can determine what type of data were returned. See
+ * check_stack_read().
+ */
+ if (!tnum_is_const(reg->var_off)) {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "variable stack access var_off=%s off=%d size=%d\n",
+ tn_buf, off, size);
+ return -EACCES;
+ }
+
+ if (off >= 0 || off < -MAX_BPF_STACK) {
+ verbose(env, "invalid stack off=%d size=%d\n", off, size);
+ return -EACCES;
+ }
+
+ return 0;
+}
+
+/* check read/write into map element returned by bpf_map_lookup_elem() */
+static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
+ int size, bool zero_size_allowed)
+{
+ struct bpf_reg_state *regs = cur_regs(env);
+ struct bpf_map *map = regs[regno].map_ptr;
+
+ if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
+ off + size > map->value_size) {
+ verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n",
+ map->value_size, off, size);
+ return -EACCES;
+ }
+ return 0;
+}
+
+/* check read/write into a map element with possible variable offset */
+static int check_map_access(struct bpf_verifier_env *env, u32 regno,
+ int off, int size, bool zero_size_allowed)
+{
+ struct bpf_verifier_state *vstate = env->cur_state;
+ struct bpf_func_state *state = vstate->frame[vstate->curframe];
+ struct bpf_reg_state *reg = &state->regs[regno];
+ int err;
+
+ /* We may have adjusted the register to this map value, so we
+ * need to try adding each of min_value and max_value to off
+ * to make sure our theoretical access will be safe.
+ */
+ if (env->log.level)
+ print_verifier_state(env, state);
+
+ /* The minimum value is only important with signed
+ * comparisons where we can't assume the floor of a
+ * value is 0. If we are using signed variables for our
+ * index'es we need to make sure that whatever we use
+ * will have a set floor within our range.
+ */
+ if (reg->smin_value < 0 &&
+ (reg->smin_value == S64_MIN ||
+ (off + reg->smin_value != (s64)(s32)(off + reg->smin_value)) ||
+ reg->smin_value + off < 0)) {
+ verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
+ regno);
+ return -EACCES;
+ }
+ err = __check_map_access(env, regno, reg->smin_value + off, size,
+ zero_size_allowed);
+ if (err) {
+ verbose(env, "R%d min value is outside of the array range\n",
+ regno);
+ return err;
+ }
+
+ /* If we haven't set a max value then we need to bail since we can't be
+ * sure we won't do bad things.
+ * If reg->umax_value + off could overflow, treat that as unbounded too.
+ */
+ if (reg->umax_value >= BPF_MAX_VAR_OFF) {
+ verbose(env, "R%d unbounded memory access, make sure to bounds check any array access into a map\n",
+ regno);
+ return -EACCES;
+ }
+ err = __check_map_access(env, regno, reg->umax_value + off, size,
+ zero_size_allowed);
+ if (err)
+ verbose(env, "R%d max value is outside of the array range\n",
+ regno);
+ return err;
+}
+
+#define MAX_PACKET_OFF 0xffff
+
+static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
+ const struct bpf_call_arg_meta *meta,
+ enum bpf_access_type t)
+{
+ switch (env->prog->type) {
+ case BPF_PROG_TYPE_LWT_IN:
+ case BPF_PROG_TYPE_LWT_OUT:
+ case BPF_PROG_TYPE_LWT_SEG6LOCAL:
+ case BPF_PROG_TYPE_SK_REUSEPORT:
+ /* dst_input() and dst_output() can't write for now */
+ if (t == BPF_WRITE)
+ return false;
+ /* fallthrough */
+ case BPF_PROG_TYPE_SCHED_CLS:
+ case BPF_PROG_TYPE_SCHED_ACT:
+ case BPF_PROG_TYPE_XDP:
+ case BPF_PROG_TYPE_LWT_XMIT:
+ case BPF_PROG_TYPE_SK_SKB:
+ case BPF_PROG_TYPE_SK_MSG:
+ if (meta)
+ return meta->pkt_access;
+
+ env->seen_direct_write = true;
+ return true;
+ default:
+ return false;
+ }
+}
+
+static int __check_packet_access(struct bpf_verifier_env *env, u32 regno,
+ int off, int size, bool zero_size_allowed)
+{
+ struct bpf_reg_state *regs = cur_regs(env);
+ struct bpf_reg_state *reg = &regs[regno];
+
+ if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
+ (u64)off + size > reg->range) {
+ verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n",
+ off, size, regno, reg->id, reg->off, reg->range);
+ return -EACCES;
+ }
+ return 0;
+}
+
+static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
+ int size, bool zero_size_allowed)
+{
+ struct bpf_reg_state *regs = cur_regs(env);
+ struct bpf_reg_state *reg = &regs[regno];
+ int err;
+
+ /* We may have added a variable offset to the packet pointer; but any
+ * reg->range we have comes after that. We are only checking the fixed
+ * offset.
+ */
+
+ /* We don't allow negative numbers, because we aren't tracking enough
+ * detail to prove they're safe.
+ */
+ if (reg->smin_value < 0) {
+ verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
+ regno);
+ return -EACCES;
+ }
+ err = __check_packet_access(env, regno, off, size, zero_size_allowed);
+ if (err) {
+ verbose(env, "R%d offset is outside of the packet\n", regno);
+ return err;
+ }
+ return err;
+}
+
+/* check access to 'struct bpf_context' fields. Supports fixed offsets only */
+static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size,
+ enum bpf_access_type t, enum bpf_reg_type *reg_type)
+{
+ struct bpf_insn_access_aux info = {
+ .reg_type = *reg_type,
+ };
+
+ if (env->ops->is_valid_access &&
+ env->ops->is_valid_access(off, size, t, env->prog, &info)) {
+ /* A non zero info.ctx_field_size indicates that this field is a
+ * candidate for later verifier transformation to load the whole
+ * field and then apply a mask when accessed with a narrower
+ * access than actual ctx access size. A zero info.ctx_field_size
+ * will only allow for whole field access and rejects any other
+ * type of narrower access.
+ */
+ *reg_type = info.reg_type;
+
+ env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
+ /* remember the offset of last byte accessed in ctx */
+ if (env->prog->aux->max_ctx_offset < off + size)
+ env->prog->aux->max_ctx_offset = off + size;
+ return 0;
+ }
+
+ verbose(env, "invalid bpf_context access off=%d size=%d\n", off, size);
+ return -EACCES;
+}
+
+static bool __is_pointer_value(bool allow_ptr_leaks,
+ const struct bpf_reg_state *reg)
+{
+ if (allow_ptr_leaks)
+ return false;
+
+ return reg->type != SCALAR_VALUE;
+}
+
+static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
+{
+ return __is_pointer_value(env->allow_ptr_leaks, cur_regs(env) + regno);
+}
+
+static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
+{
+ const struct bpf_reg_state *reg = cur_regs(env) + regno;
+
+ return reg->type == PTR_TO_CTX;
+}
+
+static bool is_pkt_reg(struct bpf_verifier_env *env, int regno)
+{
+ const struct bpf_reg_state *reg = cur_regs(env) + regno;
+
+ return type_is_pkt_pointer(reg->type);
+}
+
+static int check_pkt_ptr_alignment(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
+ int off, int size, bool strict)
+{
+ struct tnum reg_off;
+ int ip_align;
+
+ /* Byte size accesses are always allowed. */
+ if (!strict || size == 1)
+ return 0;
+
+ /* For platforms that do not have a Kconfig enabling
+ * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS the value of
+ * NET_IP_ALIGN is universally set to '2'. And on platforms
+ * that do set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS, we get
+ * to this code only in strict mode where we want to emulate
+ * the NET_IP_ALIGN==2 checking. Therefore use an
+ * unconditional IP align value of '2'.
+ */
+ ip_align = 2;
+
+ reg_off = tnum_add(reg->var_off, tnum_const(ip_align + reg->off + off));
+ if (!tnum_is_aligned(reg_off, size)) {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env,
+ "misaligned packet access off %d+%s+%d+%d size %d\n",
+ ip_align, tn_buf, reg->off, off, size);
+ return -EACCES;
+ }
+
+ return 0;
+}
+
+static int check_generic_ptr_alignment(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
+ const char *pointer_desc,
+ int off, int size, bool strict)
+{
+ struct tnum reg_off;
+
+ /* Byte size accesses are always allowed. */
+ if (!strict || size == 1)
+ return 0;
+
+ reg_off = tnum_add(reg->var_off, tnum_const(reg->off + off));
+ if (!tnum_is_aligned(reg_off, size)) {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "misaligned %saccess off %s+%d+%d size %d\n",
+ pointer_desc, tn_buf, reg->off, off, size);
+ return -EACCES;
+ }
+
+ return 0;
+}
+
+static int check_ptr_alignment(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg, int off,
+ int size, bool strict_alignment_once)
+{
+ bool strict = env->strict_alignment || strict_alignment_once;
+ const char *pointer_desc = "";
+
+ switch (reg->type) {
+ case PTR_TO_PACKET:
+ case PTR_TO_PACKET_META:
+ /* Special case, because of NET_IP_ALIGN. Given metadata sits
+ * right in front, treat it the very same way.
+ */
+ return check_pkt_ptr_alignment(env, reg, off, size, strict);
+ case PTR_TO_MAP_VALUE:
+ pointer_desc = "value ";
+ break;
+ case PTR_TO_CTX:
+ pointer_desc = "context ";
+ break;
+ case PTR_TO_STACK:
+ pointer_desc = "stack ";
+ /* The stack spill tracking logic in check_stack_write()
+ * and check_stack_read() relies on stack accesses being
+ * aligned.
+ */
+ strict = true;
+ break;
+ default:
+ break;
+ }
+ return check_generic_ptr_alignment(env, reg, pointer_desc, off, size,
+ strict);
+}
+
+static int update_stack_depth(struct bpf_verifier_env *env,
+ const struct bpf_func_state *func,
+ int off)
+{
+ u16 stack = env->subprog_info[func->subprogno].stack_depth;
+
+ if (stack >= -off)
+ return 0;
+
+ /* update known max for given subprogram */
+ env->subprog_info[func->subprogno].stack_depth = -off;
+ return 0;
+}
+
+/* starting from main bpf function walk all instructions of the function
+ * and recursively walk all callees that given function can call.
+ * Ignore jump and exit insns.
+ * Since recursion is prevented by check_cfg() this algorithm
+ * only needs a local stack of MAX_CALL_FRAMES to remember callsites
+ */
+static int check_max_stack_depth(struct bpf_verifier_env *env)
+{
+ int depth = 0, frame = 0, idx = 0, i = 0, subprog_end;
+ struct bpf_subprog_info *subprog = env->subprog_info;
+ struct bpf_insn *insn = env->prog->insnsi;
+ int ret_insn[MAX_CALL_FRAMES];
+ int ret_prog[MAX_CALL_FRAMES];
+
+process_func:
+ /* round up to 32-bytes, since this is granularity
+ * of interpreter stack size
+ */
+ depth += round_up(max_t(u32, subprog[idx].stack_depth, 1), 32);
+ if (depth > MAX_BPF_STACK) {
+ verbose(env, "combined stack size of %d calls is %d. Too large\n",
+ frame + 1, depth);
+ return -EACCES;
+ }
+continue_func:
+ subprog_end = subprog[idx + 1].start;
+ for (; i < subprog_end; i++) {
+ if (insn[i].code != (BPF_JMP | BPF_CALL))
+ continue;
+ if (insn[i].src_reg != BPF_PSEUDO_CALL)
+ continue;
+ /* remember insn and function to return to */
+ ret_insn[frame] = i + 1;
+ ret_prog[frame] = idx;
+
+ /* find the callee */
+ i = i + insn[i].imm + 1;
+ idx = find_subprog(env, i);
+ if (idx < 0) {
+ WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
+ i);
+ return -EFAULT;
+ }
+ frame++;
+ if (frame >= MAX_CALL_FRAMES) {
+ WARN_ONCE(1, "verifier bug. Call stack is too deep\n");
+ return -EFAULT;
+ }
+ goto process_func;
+ }
+ /* end of for() loop means the last insn of the 'subprog'
+ * was reached. Doesn't matter whether it was JA or EXIT
+ */
+ if (frame == 0)
+ return 0;
+ depth -= round_up(max_t(u32, subprog[idx].stack_depth, 1), 32);
+ frame--;
+ i = ret_insn[frame];
+ idx = ret_prog[frame];
+ goto continue_func;
+}
+
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+static int get_callee_stack_depth(struct bpf_verifier_env *env,
+ const struct bpf_insn *insn, int idx)
+{
+ int start = idx + insn->imm + 1, subprog;
+
+ subprog = find_subprog(env, start);
+ if (subprog < 0) {
+ WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
+ start);
+ return -EFAULT;
+ }
+ return env->subprog_info[subprog].stack_depth;
+}
+#endif
+
+static int check_ctx_reg(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg, int regno)
+{
+ /* Access to ctx or passing it to a helper is only allowed in
+ * its original, unmodified form.
+ */
+
+ if (reg->off) {
+ verbose(env, "dereference of modified ctx ptr R%d off=%d disallowed\n",
+ regno, reg->off);
+ return -EACCES;
+ }
+
+ if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "variable ctx access var_off=%s disallowed\n", tn_buf);
+ return -EACCES;
+ }
+
+ return 0;
+}
+
+/* truncate register to smaller size (in bytes)
+ * must be called with size < BPF_REG_SIZE
+ */
+static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
+{
+ u64 mask;
+
+ /* clear high bits in bit representation */
+ reg->var_off = tnum_cast(reg->var_off, size);
+
+ /* fix arithmetic bounds */
+ mask = ((u64)1 << (size * 8)) - 1;
+ if ((reg->umin_value & ~mask) == (reg->umax_value & ~mask)) {
+ reg->umin_value &= mask;
+ reg->umax_value &= mask;
+ } else {
+ reg->umin_value = 0;
+ reg->umax_value = mask;
+ }
+ reg->smin_value = reg->umin_value;
+ reg->smax_value = reg->umax_value;
+}
+
+/* check whether memory at (regno + off) is accessible for t = (read | write)
+ * if t==write, value_regno is a register which value is stored into memory
+ * if t==read, value_regno is a register which will receive the value from memory
+ * if t==write && value_regno==-1, some unknown value is stored into memory
+ * if t==read && value_regno==-1, don't care what we read from memory
+ */
+static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno,
+ int off, int bpf_size, enum bpf_access_type t,
+ int value_regno, bool strict_alignment_once)
+{
+ struct bpf_reg_state *regs = cur_regs(env);
+ struct bpf_reg_state *reg = regs + regno;
+ struct bpf_func_state *state;
+ int size, err = 0;
+
+ size = bpf_size_to_bytes(bpf_size);
+ if (size < 0)
+ return size;
+
+ /* alignment checks will add in reg->off themselves */
+ err = check_ptr_alignment(env, reg, off, size, strict_alignment_once);
+ if (err)
+ return err;
+
+ /* for access checks, reg->off is just part of off */
+ off += reg->off;
+
+ if (reg->type == PTR_TO_MAP_VALUE) {
+ if (t == BPF_WRITE && value_regno >= 0 &&
+ is_pointer_value(env, value_regno)) {
+ verbose(env, "R%d leaks addr into map\n", value_regno);
+ return -EACCES;
+ }
+
+ err = check_map_access(env, regno, off, size, false);
+ if (!err && t == BPF_READ && value_regno >= 0)
+ mark_reg_unknown(env, regs, value_regno);
+
+ } else if (reg->type == PTR_TO_CTX) {
+ enum bpf_reg_type reg_type = SCALAR_VALUE;
+
+ if (t == BPF_WRITE && value_regno >= 0 &&
+ is_pointer_value(env, value_regno)) {
+ verbose(env, "R%d leaks addr into ctx\n", value_regno);
+ return -EACCES;
+ }
+
+ err = check_ctx_reg(env, reg, regno);
+ if (err < 0)
+ return err;
+
+ err = check_ctx_access(env, insn_idx, off, size, t, &reg_type);
+ if (!err && t == BPF_READ && value_regno >= 0) {
+ /* ctx access returns either a scalar, or a
+ * PTR_TO_PACKET[_META,_END]. In the latter
+ * case, we know the offset is zero.
+ */
+ if (reg_type == SCALAR_VALUE)
+ mark_reg_unknown(env, regs, value_regno);
+ else
+ mark_reg_known_zero(env, regs,
+ value_regno);
+ regs[value_regno].type = reg_type;
+ }
+
+ } else if (reg->type == PTR_TO_STACK) {
+ off += reg->var_off.value;
+ err = check_stack_access(env, reg, off, size);
+ if (err)
+ return err;
+
+ state = func(env, reg);
+ err = update_stack_depth(env, state, off);
+ if (err)
+ return err;
+
+ if (t == BPF_WRITE)
+ err = check_stack_write(env, state, off, size,
+ value_regno, insn_idx);
+ else
+ err = check_stack_read(env, state, off, size,
+ value_regno);
+ } else if (reg_is_pkt_pointer(reg)) {
+ if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) {
+ verbose(env, "cannot write into packet\n");
+ return -EACCES;
+ }
+ if (t == BPF_WRITE && value_regno >= 0 &&
+ is_pointer_value(env, value_regno)) {
+ verbose(env, "R%d leaks addr into packet\n",
+ value_regno);
+ return -EACCES;
+ }
+ err = check_packet_access(env, regno, off, size, false);
+ if (!err && t == BPF_READ && value_regno >= 0)
+ mark_reg_unknown(env, regs, value_regno);
+ } else {
+ verbose(env, "R%d invalid mem access '%s'\n", regno,
+ reg_type_str[reg->type]);
+ return -EACCES;
+ }
+
+ if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ &&
+ regs[value_regno].type == SCALAR_VALUE) {
+ /* b/h/w load zero-extends, mark upper bits as known 0 */
+ coerce_reg_to_size(&regs[value_regno], size);
+ }
+ return err;
+}
+
+static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn)
+{
+ int err;
+
+ if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) ||
+ insn->imm != 0) {
+ verbose(env, "BPF_XADD uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ /* check src1 operand */
+ err = check_reg_arg(env, insn->src_reg, SRC_OP);
+ if (err)
+ return err;
+
+ /* check src2 operand */
+ err = check_reg_arg(env, insn->dst_reg, SRC_OP);
+ if (err)
+ return err;
+
+ if (is_pointer_value(env, insn->src_reg)) {
+ verbose(env, "R%d leaks addr into mem\n", insn->src_reg);
+ return -EACCES;
+ }
+
+ if (is_ctx_reg(env, insn->dst_reg) ||
+ is_pkt_reg(env, insn->dst_reg)) {
+ verbose(env, "BPF_XADD stores into R%d %s is not allowed\n",
+ insn->dst_reg, is_ctx_reg(env, insn->dst_reg) ?
+ "context" : "packet");
+ return -EACCES;
+ }
+
+ /* check whether atomic_add can read the memory */
+ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
+ BPF_SIZE(insn->code), BPF_READ, -1, true);
+ if (err)
+ return err;
+
+ /* check whether atomic_add can write into the same memory */
+ return check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
+ BPF_SIZE(insn->code), BPF_WRITE, -1, true);
+}
+
+static int __check_stack_boundary(struct bpf_verifier_env *env, u32 regno,
+ int off, int access_size,
+ bool zero_size_allowed)
+{
+ struct bpf_reg_state *reg = cur_regs(env) + regno;
+
+ if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
+ access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
+ if (tnum_is_const(reg->var_off)) {
+ verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
+ regno, off, access_size);
+ } else {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "invalid stack type R%d var_off=%s access_size=%d\n",
+ regno, tn_buf, access_size);
+ }
+ return -EACCES;
+ }
+ return 0;
+}
+
+/* when register 'regno' is passed into function that will read 'access_size'
+ * bytes from that pointer, make sure that it's within stack boundary
+ * and all elements of stack are initialized.
+ * Unlike most pointer bounds-checking functions, this one doesn't take an
+ * 'off' argument, so it has to add in reg->off itself.
+ */
+static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
+ int access_size, bool zero_size_allowed,
+ struct bpf_call_arg_meta *meta)
+{
+ struct bpf_reg_state *reg = cur_regs(env) + regno;
+ struct bpf_func_state *state = func(env, reg);
+ int err, min_off, max_off, i, j, slot, spi;
+
+ if (reg->type != PTR_TO_STACK) {
+ /* Allow zero-byte read from NULL, regardless of pointer type */
+ if (zero_size_allowed && access_size == 0 &&
+ register_is_null(reg))
+ return 0;
+
+ verbose(env, "R%d type=%s expected=%s\n", regno,
+ reg_type_str[reg->type],
+ reg_type_str[PTR_TO_STACK]);
+ return -EACCES;
+ }
+
+ if (tnum_is_const(reg->var_off)) {
+ min_off = max_off = reg->var_off.value + reg->off;
+ err = __check_stack_boundary(env, regno, min_off, access_size,
+ zero_size_allowed);
+ if (err)
+ return err;
+ } else {
+ /* Variable offset is prohibited for unprivileged mode for
+ * simplicity since it requires corresponding support in
+ * Spectre masking for stack ALU.
+ * See also retrieve_ptr_limit().
+ */
+ if (!env->allow_ptr_leaks) {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "R%d indirect variable offset stack access prohibited for !root, var_off=%s\n",
+ regno, tn_buf);
+ return -EACCES;
+ }
+ /* Only initialized buffer on stack is allowed to be accessed
+ * with variable offset. With uninitialized buffer it's hard to
+ * guarantee that whole memory is marked as initialized on
+ * helper return since specific bounds are unknown what may
+ * cause uninitialized stack leaking.
+ */
+ if (meta && meta->raw_mode)
+ meta = NULL;
+
+ if (reg->smax_value >= BPF_MAX_VAR_OFF ||
+ reg->smax_value <= -BPF_MAX_VAR_OFF) {
+ verbose(env, "R%d unbounded indirect variable offset stack access\n",
+ regno);
+ return -EACCES;
+ }
+ min_off = reg->smin_value + reg->off;
+ max_off = reg->smax_value + reg->off;
+ err = __check_stack_boundary(env, regno, min_off, access_size,
+ zero_size_allowed);
+ if (err) {
+ verbose(env, "R%d min value is outside of stack bound\n",
+ regno);
+ return err;
+ }
+ err = __check_stack_boundary(env, regno, max_off, access_size,
+ zero_size_allowed);
+ if (err) {
+ verbose(env, "R%d max value is outside of stack bound\n",
+ regno);
+ return err;
+ }
+ }
+
+ if (meta && meta->raw_mode) {
+ meta->access_size = access_size;
+ meta->regno = regno;
+ return 0;
+ }
+
+ for (i = min_off; i < max_off + access_size; i++) {
+ u8 *stype;
+
+ slot = -i - 1;
+ spi = slot / BPF_REG_SIZE;
+ if (state->allocated_stack <= slot)
+ goto err;
+ stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
+ if (*stype == STACK_MISC)
+ goto mark;
+ if (*stype == STACK_ZERO) {
+ /* helper can write anything into the stack */
+ *stype = STACK_MISC;
+ goto mark;
+ }
+ if (state->stack[spi].slot_type[0] == STACK_SPILL &&
+ state->stack[spi].spilled_ptr.type == SCALAR_VALUE) {
+ __mark_reg_unknown(&state->stack[spi].spilled_ptr);
+ for (j = 0; j < BPF_REG_SIZE; j++)
+ state->stack[spi].slot_type[j] = STACK_MISC;
+ goto mark;
+ }
+
+err:
+ if (tnum_is_const(reg->var_off)) {
+ verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
+ min_off, i - min_off, access_size);
+ } else {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "invalid indirect read from stack var_off %s+%d size %d\n",
+ tn_buf, i - min_off, access_size);
+ }
+ return -EACCES;
+mark:
+ /* reading any byte out of 8-byte 'spill_slot' will cause
+ * the whole slot to be marked as 'read'
+ */
+ mark_reg_read(env, &state->stack[spi].spilled_ptr,
+ state->stack[spi].spilled_ptr.parent);
+ }
+ return update_stack_depth(env, state, min_off);
+}
+
+static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
+ int access_size, bool zero_size_allowed,
+ struct bpf_call_arg_meta *meta)
+{
+ struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
+
+ switch (reg->type) {
+ case PTR_TO_PACKET:
+ case PTR_TO_PACKET_META:
+ return check_packet_access(env, regno, reg->off, access_size,
+ zero_size_allowed);
+ case PTR_TO_MAP_VALUE:
+ return check_map_access(env, regno, reg->off, access_size,
+ zero_size_allowed);
+ default: /* scalar_value|ptr_to_stack or invalid ptr */
+ return check_stack_boundary(env, regno, access_size,
+ zero_size_allowed, meta);
+ }
+}
+
+static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
+{
+ return type == ARG_PTR_TO_MEM ||
+ type == ARG_PTR_TO_MEM_OR_NULL ||
+ type == ARG_PTR_TO_UNINIT_MEM;
+}
+
+static bool arg_type_is_mem_size(enum bpf_arg_type type)
+{
+ return type == ARG_CONST_SIZE ||
+ type == ARG_CONST_SIZE_OR_ZERO;
+}
+
+static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
+ enum bpf_arg_type arg_type,
+ struct bpf_call_arg_meta *meta)
+{
+ struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
+ enum bpf_reg_type expected_type, type = reg->type;
+ int err = 0;
+
+ if (arg_type == ARG_DONTCARE)
+ return 0;
+
+ err = check_reg_arg(env, regno, SRC_OP);
+ if (err)
+ return err;
+
+ if (arg_type == ARG_ANYTHING) {
+ if (is_pointer_value(env, regno)) {
+ verbose(env, "R%d leaks addr into helper function\n",
+ regno);
+ return -EACCES;
+ }
+ return 0;
+ }
+
+ if (type_is_pkt_pointer(type) &&
+ !may_access_direct_pkt_data(env, meta, BPF_READ)) {
+ verbose(env, "helper access to the packet is not allowed\n");
+ return -EACCES;
+ }
+
+ if (arg_type == ARG_PTR_TO_MAP_KEY ||
+ arg_type == ARG_PTR_TO_MAP_VALUE) {
+ expected_type = PTR_TO_STACK;
+ if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE &&
+ type != expected_type)
+ goto err_type;
+ } else if (arg_type == ARG_CONST_SIZE ||
+ arg_type == ARG_CONST_SIZE_OR_ZERO) {
+ expected_type = SCALAR_VALUE;
+ if (type != expected_type)
+ goto err_type;
+ } else if (arg_type == ARG_CONST_MAP_PTR) {
+ expected_type = CONST_PTR_TO_MAP;
+ if (type != expected_type)
+ goto err_type;
+ } else if (arg_type == ARG_PTR_TO_CTX) {
+ expected_type = PTR_TO_CTX;
+ if (type != expected_type)
+ goto err_type;
+ err = check_ctx_reg(env, reg, regno);
+ if (err < 0)
+ return err;
+ } else if (arg_type_is_mem_ptr(arg_type)) {
+ expected_type = PTR_TO_STACK;
+ /* One exception here. In case function allows for NULL to be
+ * passed in as argument, it's a SCALAR_VALUE type. Final test
+ * happens during stack boundary checking.
+ */
+ if (register_is_null(reg) &&
+ arg_type == ARG_PTR_TO_MEM_OR_NULL)
+ /* final test in check_stack_boundary() */;
+ else if (!type_is_pkt_pointer(type) &&
+ type != PTR_TO_MAP_VALUE &&
+ type != expected_type)
+ goto err_type;
+ meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM;
+ } else {
+ verbose(env, "unsupported arg_type %d\n", arg_type);
+ return -EFAULT;
+ }
+
+ if (arg_type == ARG_CONST_MAP_PTR) {
+ /* bpf_map_xxx(map_ptr) call: remember that map_ptr */
+ meta->map_ptr = reg->map_ptr;
+ } else if (arg_type == ARG_PTR_TO_MAP_KEY) {
+ /* bpf_map_xxx(..., map_ptr, ..., key) call:
+ * check that [key, key + map->key_size) are within
+ * stack limits and initialized
+ */
+ if (!meta->map_ptr) {
+ /* in function declaration map_ptr must come before
+ * map_key, so that it's verified and known before
+ * we have to check map_key here. Otherwise it means
+ * that kernel subsystem misconfigured verifier
+ */
+ verbose(env, "invalid map_ptr to access map->key\n");
+ return -EACCES;
+ }
+ err = check_helper_mem_access(env, regno,
+ meta->map_ptr->key_size, false,
+ NULL);
+ } else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
+ /* bpf_map_xxx(..., map_ptr, ..., value) call:
+ * check [value, value + map->value_size) validity
+ */
+ if (!meta->map_ptr) {
+ /* kernel subsystem misconfigured verifier */
+ verbose(env, "invalid map_ptr to access map->value\n");
+ return -EACCES;
+ }
+ err = check_helper_mem_access(env, regno,
+ meta->map_ptr->value_size, false,
+ NULL);
+ } else if (arg_type_is_mem_size(arg_type)) {
+ bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
+
+ /* remember the mem_size which may be used later
+ * to refine return values.
+ */
+ meta->msize_max_value = reg->umax_value;
+
+ /* The register is SCALAR_VALUE; the access check
+ * happens using its boundaries.
+ */
+ if (!tnum_is_const(reg->var_off))
+ /* For unprivileged variable accesses, disable raw
+ * mode so that the program is required to
+ * initialize all the memory that the helper could
+ * just partially fill up.
+ */
+ meta = NULL;
+
+ if (reg->smin_value < 0) {
+ verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n",
+ regno);
+ return -EACCES;
+ }
+
+ if (reg->umin_value == 0) {
+ err = check_helper_mem_access(env, regno - 1, 0,
+ zero_size_allowed,
+ meta);
+ if (err)
+ return err;
+ }
+
+ if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
+ verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n",
+ regno);
+ return -EACCES;
+ }
+ err = check_helper_mem_access(env, regno - 1,
+ reg->umax_value,
+ zero_size_allowed, meta);
+ }
+
+ return err;
+err_type:
+ verbose(env, "R%d type=%s expected=%s\n", regno,
+ reg_type_str[type], reg_type_str[expected_type]);
+ return -EACCES;
+}
+
+static int check_map_func_compatibility(struct bpf_verifier_env *env,
+ struct bpf_map *map, int func_id)
+{
+ if (!map)
+ return 0;
+
+ /* We need a two way check, first is from map perspective ... */
+ switch (map->map_type) {
+ case BPF_MAP_TYPE_PROG_ARRAY:
+ if (func_id != BPF_FUNC_tail_call)
+ goto error;
+ break;
+ case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+ if (func_id != BPF_FUNC_perf_event_read &&
+ func_id != BPF_FUNC_perf_event_output &&
+ func_id != BPF_FUNC_perf_event_read_value)
+ goto error;
+ break;
+ case BPF_MAP_TYPE_STACK_TRACE:
+ if (func_id != BPF_FUNC_get_stackid)
+ goto error;
+ break;
+ case BPF_MAP_TYPE_CGROUP_ARRAY:
+ if (func_id != BPF_FUNC_skb_under_cgroup &&
+ func_id != BPF_FUNC_current_task_under_cgroup)
+ goto error;
+ break;
+ case BPF_MAP_TYPE_CGROUP_STORAGE:
+ if (func_id != BPF_FUNC_get_local_storage)
+ goto error;
+ break;
+ /* devmap returns a pointer to a live net_device ifindex that we cannot
+ * allow to be modified from bpf side. So do not allow lookup elements
+ * for now.
+ */
+ case BPF_MAP_TYPE_DEVMAP:
+ if (func_id != BPF_FUNC_redirect_map)
+ goto error;
+ break;
+ /* Restrict bpf side of cpumap and xskmap, open when use-cases
+ * appear.
+ */
+ case BPF_MAP_TYPE_CPUMAP:
+ case BPF_MAP_TYPE_XSKMAP:
+ if (func_id != BPF_FUNC_redirect_map)
+ goto error;
+ break;
+ case BPF_MAP_TYPE_ARRAY_OF_MAPS:
+ case BPF_MAP_TYPE_HASH_OF_MAPS:
+ if (func_id != BPF_FUNC_map_lookup_elem)
+ goto error;
+ break;
+ case BPF_MAP_TYPE_SOCKMAP:
+ if (func_id != BPF_FUNC_sk_redirect_map &&
+ func_id != BPF_FUNC_sock_map_update &&
+ func_id != BPF_FUNC_map_delete_elem &&
+ func_id != BPF_FUNC_msg_redirect_map)
+ goto error;
+ break;
+ case BPF_MAP_TYPE_SOCKHASH:
+ if (func_id != BPF_FUNC_sk_redirect_hash &&
+ func_id != BPF_FUNC_sock_hash_update &&
+ func_id != BPF_FUNC_map_delete_elem &&
+ func_id != BPF_FUNC_msg_redirect_hash)
+ goto error;
+ break;
+ case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
+ if (func_id != BPF_FUNC_sk_select_reuseport)
+ goto error;
+ break;
+ default:
+ break;
+ }
+
+ /* ... and second from the function itself. */
+ switch (func_id) {
+ case BPF_FUNC_tail_call:
+ if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
+ goto error;
+ if (env->subprog_cnt > 1) {
+ verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n");
+ return -EINVAL;
+ }
+ break;
+ case BPF_FUNC_perf_event_read:
+ case BPF_FUNC_perf_event_output:
+ case BPF_FUNC_perf_event_read_value:
+ if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
+ goto error;
+ break;
+ case BPF_FUNC_get_stackid:
+ if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
+ goto error;
+ break;
+ case BPF_FUNC_current_task_under_cgroup:
+ case BPF_FUNC_skb_under_cgroup:
+ if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
+ goto error;
+ break;
+ case BPF_FUNC_redirect_map:
+ if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
+ map->map_type != BPF_MAP_TYPE_CPUMAP &&
+ map->map_type != BPF_MAP_TYPE_XSKMAP)
+ goto error;
+ break;
+ case BPF_FUNC_sk_redirect_map:
+ case BPF_FUNC_msg_redirect_map:
+ case BPF_FUNC_sock_map_update:
+ if (map->map_type != BPF_MAP_TYPE_SOCKMAP)
+ goto error;
+ break;
+ case BPF_FUNC_sk_redirect_hash:
+ case BPF_FUNC_msg_redirect_hash:
+ case BPF_FUNC_sock_hash_update:
+ if (map->map_type != BPF_MAP_TYPE_SOCKHASH)
+ goto error;
+ break;
+ case BPF_FUNC_get_local_storage:
+ if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
+ goto error;
+ break;
+ case BPF_FUNC_sk_select_reuseport:
+ if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY)
+ goto error;
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+error:
+ verbose(env, "cannot pass map_type %d into func %s#%d\n",
+ map->map_type, func_id_name(func_id), func_id);
+ return -EINVAL;
+}
+
+static bool check_raw_mode_ok(const struct bpf_func_proto *fn)
+{
+ int count = 0;
+
+ if (fn->arg1_type == ARG_PTR_TO_UNINIT_MEM)
+ count++;
+ if (fn->arg2_type == ARG_PTR_TO_UNINIT_MEM)
+ count++;
+ if (fn->arg3_type == ARG_PTR_TO_UNINIT_MEM)
+ count++;
+ if (fn->arg4_type == ARG_PTR_TO_UNINIT_MEM)
+ count++;
+ if (fn->arg5_type == ARG_PTR_TO_UNINIT_MEM)
+ count++;
+
+ /* We only support one arg being in raw mode at the moment,
+ * which is sufficient for the helper functions we have
+ * right now.
+ */
+ return count <= 1;
+}
+
+static bool check_args_pair_invalid(enum bpf_arg_type arg_curr,
+ enum bpf_arg_type arg_next)
+{
+ return (arg_type_is_mem_ptr(arg_curr) &&
+ !arg_type_is_mem_size(arg_next)) ||
+ (!arg_type_is_mem_ptr(arg_curr) &&
+ arg_type_is_mem_size(arg_next));
+}
+
+static bool check_arg_pair_ok(const struct bpf_func_proto *fn)
+{
+ /* bpf_xxx(..., buf, len) call will access 'len'
+ * bytes from memory 'buf'. Both arg types need
+ * to be paired, so make sure there's no buggy
+ * helper function specification.
+ */
+ if (arg_type_is_mem_size(fn->arg1_type) ||
+ arg_type_is_mem_ptr(fn->arg5_type) ||
+ check_args_pair_invalid(fn->arg1_type, fn->arg2_type) ||
+ check_args_pair_invalid(fn->arg2_type, fn->arg3_type) ||
+ check_args_pair_invalid(fn->arg3_type, fn->arg4_type) ||
+ check_args_pair_invalid(fn->arg4_type, fn->arg5_type))
+ return false;
+
+ return true;
+}
+
+static int check_func_proto(const struct bpf_func_proto *fn)
+{
+ return check_raw_mode_ok(fn) &&
+ check_arg_pair_ok(fn) ? 0 : -EINVAL;
+}
+
+/* Packet data might have moved, any old PTR_TO_PACKET[_META,_END]
+ * are now invalid, so turn them into unknown SCALAR_VALUE.
+ */
+static void __clear_all_pkt_pointers(struct bpf_verifier_env *env,
+ struct bpf_func_state *state)
+{
+ struct bpf_reg_state *regs = state->regs, *reg;
+ int i;
+
+ for (i = 0; i < MAX_BPF_REG; i++)
+ if (reg_is_pkt_pointer_any(&regs[i]))
+ mark_reg_unknown(env, regs, i);
+
+ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+ if (state->stack[i].slot_type[0] != STACK_SPILL)
+ continue;
+ reg = &state->stack[i].spilled_ptr;
+ if (reg_is_pkt_pointer_any(reg))
+ __mark_reg_unknown(reg);
+ }
+}
+
+static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
+{
+ struct bpf_verifier_state *vstate = env->cur_state;
+ int i;
+
+ for (i = 0; i <= vstate->curframe; i++)
+ __clear_all_pkt_pointers(env, vstate->frame[i]);
+}
+
+static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
+ int *insn_idx)
+{
+ struct bpf_verifier_state *state = env->cur_state;
+ struct bpf_func_state *caller, *callee;
+ int i, subprog, target_insn;
+
+ if (state->curframe + 1 >= MAX_CALL_FRAMES) {
+ verbose(env, "the call stack of %d frames is too deep\n",
+ state->curframe + 2);
+ return -E2BIG;
+ }
+
+ target_insn = *insn_idx + insn->imm;
+ subprog = find_subprog(env, target_insn + 1);
+ if (subprog < 0) {
+ verbose(env, "verifier bug. No program starts at insn %d\n",
+ target_insn + 1);
+ return -EFAULT;
+ }
+
+ caller = state->frame[state->curframe];
+ if (state->frame[state->curframe + 1]) {
+ verbose(env, "verifier bug. Frame %d already allocated\n",
+ state->curframe + 1);
+ return -EFAULT;
+ }
+
+ callee = kzalloc(sizeof(*callee), GFP_KERNEL);
+ if (!callee)
+ return -ENOMEM;
+ state->frame[state->curframe + 1] = callee;
+
+ /* callee cannot access r0, r6 - r9 for reading and has to write
+ * into its own stack before reading from it.
+ * callee can read/write into caller's stack
+ */
+ init_func_state(env, callee,
+ /* remember the callsite, it will be used by bpf_exit */
+ *insn_idx /* callsite */,
+ state->curframe + 1 /* frameno within this callchain */,
+ subprog /* subprog number within this prog */);
+
+ /* copy r1 - r5 args that callee can access. The copy includes parent
+ * pointers, which connects us up to the liveness chain
+ */
+ for (i = BPF_REG_1; i <= BPF_REG_5; i++)
+ callee->regs[i] = caller->regs[i];
+
+ /* after the call registers r0 - r5 were scratched */
+ for (i = 0; i < CALLER_SAVED_REGS; i++) {
+ mark_reg_not_init(env, caller->regs, caller_saved[i]);
+ check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
+ }
+
+ /* only increment it after check_reg_arg() finished */
+ state->curframe++;
+
+ /* and go analyze first insn of the callee */
+ *insn_idx = target_insn;
+
+ if (env->log.level) {
+ verbose(env, "caller:\n");
+ print_verifier_state(env, caller);
+ verbose(env, "callee:\n");
+ print_verifier_state(env, callee);
+ }
+ return 0;
+}
+
+static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
+{
+ struct bpf_verifier_state *state = env->cur_state;
+ struct bpf_func_state *caller, *callee;
+ struct bpf_reg_state *r0;
+
+ callee = state->frame[state->curframe];
+ r0 = &callee->regs[BPF_REG_0];
+ if (r0->type == PTR_TO_STACK) {
+ /* technically it's ok to return caller's stack pointer
+ * (or caller's caller's pointer) back to the caller,
+ * since these pointers are valid. Only current stack
+ * pointer will be invalid as soon as function exits,
+ * but let's be conservative
+ */
+ verbose(env, "cannot return stack pointer to the caller\n");
+ return -EINVAL;
+ }
+
+ state->curframe--;
+ caller = state->frame[state->curframe];
+ /* return to the caller whatever r0 had in the callee */
+ caller->regs[BPF_REG_0] = *r0;
+
+ *insn_idx = callee->callsite + 1;
+ if (env->log.level) {
+ verbose(env, "returning from callee:\n");
+ print_verifier_state(env, callee);
+ verbose(env, "to caller at %d:\n", *insn_idx);
+ print_verifier_state(env, caller);
+ }
+ /* clear everything in the callee */
+ free_func_state(callee);
+ state->frame[state->curframe + 1] = NULL;
+ return 0;
+}
+
+static int do_refine_retval_range(struct bpf_verifier_env *env,
+ struct bpf_reg_state *regs, int ret_type,
+ int func_id, struct bpf_call_arg_meta *meta)
+{
+ struct bpf_reg_state *ret_reg = &regs[BPF_REG_0];
+ struct bpf_reg_state tmp_reg = *ret_reg;
+ bool ret;
+
+ if (ret_type != RET_INTEGER ||
+ (func_id != BPF_FUNC_get_stack &&
+ func_id != BPF_FUNC_probe_read_str))
+ return 0;
+
+ /* Error case where ret is in interval [S32MIN, -1]. */
+ ret_reg->smin_value = S32_MIN;
+ ret_reg->smax_value = -1;
+
+ __reg_deduce_bounds(ret_reg);
+ __reg_bound_offset(ret_reg);
+ __update_reg_bounds(ret_reg);
+
+ ret = push_stack(env, env->insn_idx + 1, env->insn_idx, false);
+ if (!ret)
+ return -EFAULT;
+
+ *ret_reg = tmp_reg;
+
+ /* Success case where ret is in range [0, msize_max_value]. */
+ ret_reg->smin_value = 0;
+ ret_reg->smax_value = meta->msize_max_value;
+ ret_reg->umin_value = ret_reg->smin_value;
+ ret_reg->umax_value = ret_reg->smax_value;
+
+ __reg_deduce_bounds(ret_reg);
+ __reg_bound_offset(ret_reg);
+ __update_reg_bounds(ret_reg);
+
+ return 0;
+}
+
+static int
+record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
+ int func_id, int insn_idx)
+{
+ struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
+
+ if (func_id != BPF_FUNC_tail_call &&
+ func_id != BPF_FUNC_map_lookup_elem &&
+ func_id != BPF_FUNC_map_update_elem &&
+ func_id != BPF_FUNC_map_delete_elem)
+ return 0;
+
+ if (meta->map_ptr == NULL) {
+ verbose(env, "kernel subsystem misconfigured verifier\n");
+ return -EINVAL;
+ }
+
+ if (!BPF_MAP_PTR(aux->map_state))
+ bpf_map_ptr_store(aux, meta->map_ptr,
+ meta->map_ptr->unpriv_array);
+ else if (BPF_MAP_PTR(aux->map_state) != meta->map_ptr)
+ bpf_map_ptr_store(aux, BPF_MAP_PTR_POISON,
+ meta->map_ptr->unpriv_array);
+ return 0;
+}
+
+static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
+{
+ const struct bpf_func_proto *fn = NULL;
+ struct bpf_reg_state *regs;
+ struct bpf_call_arg_meta meta;
+ bool changes_data;
+ int i, err;
+
+ /* find function prototype */
+ if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) {
+ verbose(env, "invalid func %s#%d\n", func_id_name(func_id),
+ func_id);
+ return -EINVAL;
+ }
+
+ if (env->ops->get_func_proto)
+ fn = env->ops->get_func_proto(func_id, env->prog);
+ if (!fn) {
+ verbose(env, "unknown func %s#%d\n", func_id_name(func_id),
+ func_id);
+ return -EINVAL;
+ }
+
+ /* eBPF programs must be GPL compatible to use GPL-ed functions */
+ if (!env->prog->gpl_compatible && fn->gpl_only) {
+ verbose(env, "cannot call GPL-restricted function from non-GPL compatible program\n");
+ return -EINVAL;
+ }
+
+ /* With LD_ABS/IND some JITs save/restore skb from r1. */
+ changes_data = bpf_helper_changes_pkt_data(fn->func);
+ if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) {
+ verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n",
+ func_id_name(func_id), func_id);
+ return -EINVAL;
+ }
+
+ memset(&meta, 0, sizeof(meta));
+ meta.pkt_access = fn->pkt_access;
+
+ err = check_func_proto(fn);
+ if (err) {
+ verbose(env, "kernel subsystem misconfigured func %s#%d\n",
+ func_id_name(func_id), func_id);
+ return err;
+ }
+
+ /* check args */
+ err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta);
+ if (err)
+ return err;
+ err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta);
+ if (err)
+ return err;
+ err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta);
+ if (err)
+ return err;
+ err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &meta);
+ if (err)
+ return err;
+ err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &meta);
+ if (err)
+ return err;
+
+ err = record_func_map(env, &meta, func_id, insn_idx);
+ if (err)
+ return err;
+
+ /* Mark slots with STACK_MISC in case of raw mode, stack offset
+ * is inferred from register state.
+ */
+ for (i = 0; i < meta.access_size; i++) {
+ err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B,
+ BPF_WRITE, -1, false);
+ if (err)
+ return err;
+ }
+
+ regs = cur_regs(env);
+
+ /* check that flags argument in get_local_storage(map, flags) is 0,
+ * this is required because get_local_storage() can't return an error.
+ */
+ if (func_id == BPF_FUNC_get_local_storage &&
+ !register_is_null(&regs[BPF_REG_2])) {
+ verbose(env, "get_local_storage() doesn't support non-zero flags\n");
+ return -EINVAL;
+ }
+
+ /* reset caller saved regs */
+ for (i = 0; i < CALLER_SAVED_REGS; i++) {
+ mark_reg_not_init(env, regs, caller_saved[i]);
+ check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
+ }
+
+ /* update return register (already marked as written above) */
+ if (fn->ret_type == RET_INTEGER) {
+ /* sets type to SCALAR_VALUE */
+ mark_reg_unknown(env, regs, BPF_REG_0);
+ } else if (fn->ret_type == RET_VOID) {
+ regs[BPF_REG_0].type = NOT_INIT;
+ } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL ||
+ fn->ret_type == RET_PTR_TO_MAP_VALUE) {
+ if (fn->ret_type == RET_PTR_TO_MAP_VALUE)
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
+ else
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
+ /* There is no offset yet applied, variable or fixed */
+ mark_reg_known_zero(env, regs, BPF_REG_0);
+ /* remember map_ptr, so that check_map_access()
+ * can check 'value_size' boundary of memory access
+ * to map element returned from bpf_map_lookup_elem()
+ */
+ if (meta.map_ptr == NULL) {
+ verbose(env,
+ "kernel subsystem misconfigured verifier\n");
+ return -EINVAL;
+ }
+ regs[BPF_REG_0].map_ptr = meta.map_ptr;
+ regs[BPF_REG_0].id = ++env->id_gen;
+ } else {
+ verbose(env, "unknown return type %d of func %s#%d\n",
+ fn->ret_type, func_id_name(func_id), func_id);
+ return -EINVAL;
+ }
+
+ err = do_refine_retval_range(env, regs, fn->ret_type, func_id, &meta);
+ if (err)
+ return err;
+
+ err = check_map_func_compatibility(env, meta.map_ptr, func_id);
+ if (err)
+ return err;
+
+ if (func_id == BPF_FUNC_get_stack && !env->prog->has_callchain_buf) {
+ const char *err_str;
+
+#ifdef CONFIG_PERF_EVENTS
+ err = get_callchain_buffers(sysctl_perf_event_max_stack);
+ err_str = "cannot get callchain buffer for func %s#%d\n";
+#else
+ err = -ENOTSUPP;
+ err_str = "func %s#%d not supported without CONFIG_PERF_EVENTS\n";
+#endif
+ if (err) {
+ verbose(env, err_str, func_id_name(func_id), func_id);
+ return err;
+ }
+
+ env->prog->has_callchain_buf = true;
+ }
+
+ if (changes_data)
+ clear_all_pkt_pointers(env);
+ return 0;
+}
+
+static bool signed_add_overflows(s64 a, s64 b)
+{
+ /* Do the add in u64, where overflow is well-defined */
+ s64 res = (s64)((u64)a + (u64)b);
+
+ if (b < 0)
+ return res > a;
+ return res < a;
+}
+
+static bool signed_sub_overflows(s64 a, s64 b)
+{
+ /* Do the sub in u64, where overflow is well-defined */
+ s64 res = (s64)((u64)a - (u64)b);
+
+ if (b < 0)
+ return res < a;
+ return res > a;
+}
+
+static bool check_reg_sane_offset(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
+ enum bpf_reg_type type)
+{
+ bool known = tnum_is_const(reg->var_off);
+ s64 val = reg->var_off.value;
+ s64 smin = reg->smin_value;
+
+ if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) {
+ verbose(env, "math between %s pointer and %lld is not allowed\n",
+ reg_type_str[type], val);
+ return false;
+ }
+
+ if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) {
+ verbose(env, "%s pointer offset %d is not allowed\n",
+ reg_type_str[type], reg->off);
+ return false;
+ }
+
+ if (smin == S64_MIN) {
+ verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n",
+ reg_type_str[type]);
+ return false;
+ }
+
+ if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) {
+ verbose(env, "value %lld makes %s pointer be out of bounds\n",
+ smin, reg_type_str[type]);
+ return false;
+ }
+
+ return true;
+}
+
+static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
+{
+ return &env->insn_aux_data[env->insn_idx];
+}
+
+enum {
+ REASON_BOUNDS = -1,
+ REASON_TYPE = -2,
+ REASON_PATHS = -3,
+ REASON_LIMIT = -4,
+ REASON_STACK = -5,
+};
+
+static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
+ u32 *alu_limit, bool mask_to_left)
+{
+ u32 max = 0, ptr_limit = 0;
+
+ switch (ptr_reg->type) {
+ case PTR_TO_STACK:
+ /* Offset 0 is out-of-bounds, but acceptable start for the
+ * left direction, see BPF_REG_FP. Also, unknown scalar
+ * offset where we would need to deal with min/max bounds is
+ * currently prohibited for unprivileged.
+ */
+ max = MAX_BPF_STACK + mask_to_left;
+ ptr_limit = -(ptr_reg->var_off.value + ptr_reg->off);
+ break;
+ case PTR_TO_MAP_VALUE:
+ max = ptr_reg->map_ptr->value_size;
+ ptr_limit = (mask_to_left ?
+ ptr_reg->smin_value :
+ ptr_reg->umax_value) + ptr_reg->off;
+ break;
+ default:
+ return REASON_TYPE;
+ }
+
+ if (ptr_limit >= max)
+ return REASON_LIMIT;
+ *alu_limit = ptr_limit;
+ return 0;
+}
+
+static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env,
+ const struct bpf_insn *insn)
+{
+ return env->allow_ptr_leaks || BPF_SRC(insn->code) == BPF_K;
+}
+
+static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux,
+ u32 alu_state, u32 alu_limit)
+{
+ /* If we arrived here from different branches with different
+ * state or limits to sanitize, then this won't work.
+ */
+ if (aux->alu_state &&
+ (aux->alu_state != alu_state ||
+ aux->alu_limit != alu_limit))
+ return REASON_PATHS;
+
+ /* Corresponding fixup done in fixup_bpf_calls(). */
+ aux->alu_state = alu_state;
+ aux->alu_limit = alu_limit;
+ return 0;
+}
+
+static int sanitize_val_alu(struct bpf_verifier_env *env,
+ struct bpf_insn *insn)
+{
+ struct bpf_insn_aux_data *aux = cur_aux(env);
+
+ if (can_skip_alu_sanitation(env, insn))
+ return 0;
+
+ return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0);
+}
+
+static bool sanitize_needed(u8 opcode)
+{
+ return opcode == BPF_ADD || opcode == BPF_SUB;
+}
+
+struct bpf_sanitize_info {
+ struct bpf_insn_aux_data aux;
+ bool mask_to_left;
+};
+
+static struct bpf_verifier_state *
+sanitize_speculative_path(struct bpf_verifier_env *env,
+ const struct bpf_insn *insn,
+ u32 next_idx, u32 curr_idx)
+{
+ struct bpf_verifier_state *branch;
+ struct bpf_reg_state *regs;
+
+ branch = push_stack(env, next_idx, curr_idx, true);
+ if (branch && insn) {
+ regs = branch->frame[branch->curframe]->regs;
+ if (BPF_SRC(insn->code) == BPF_K) {
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ } else if (BPF_SRC(insn->code) == BPF_X) {
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ mark_reg_unknown(env, regs, insn->src_reg);
+ }
+ }
+ return branch;
+}
+
+static int sanitize_ptr_alu(struct bpf_verifier_env *env,
+ struct bpf_insn *insn,
+ const struct bpf_reg_state *ptr_reg,
+ const struct bpf_reg_state *off_reg,
+ struct bpf_reg_state *dst_reg,
+ struct bpf_sanitize_info *info,
+ const bool commit_window)
+{
+ struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : &info->aux;
+ struct bpf_verifier_state *vstate = env->cur_state;
+ bool off_is_imm = tnum_is_const(off_reg->var_off);
+ bool off_is_neg = off_reg->smin_value < 0;
+ bool ptr_is_dst_reg = ptr_reg == dst_reg;
+ u8 opcode = BPF_OP(insn->code);
+ u32 alu_state, alu_limit;
+ struct bpf_reg_state tmp;
+ bool ret;
+ int err;
+
+ if (can_skip_alu_sanitation(env, insn))
+ return 0;
+
+ /* We already marked aux for masking from non-speculative
+ * paths, thus we got here in the first place. We only care
+ * to explore bad access from here.
+ */
+ if (vstate->speculative)
+ goto do_sim;
+
+ if (!commit_window) {
+ if (!tnum_is_const(off_reg->var_off) &&
+ (off_reg->smin_value < 0) != (off_reg->smax_value < 0))
+ return REASON_BOUNDS;
+
+ info->mask_to_left = (opcode == BPF_ADD && off_is_neg) ||
+ (opcode == BPF_SUB && !off_is_neg);
+ }
+
+ err = retrieve_ptr_limit(ptr_reg, &alu_limit, info->mask_to_left);
+ if (err < 0)
+ return err;
+
+ if (commit_window) {
+ /* In commit phase we narrow the masking window based on
+ * the observed pointer move after the simulated operation.
+ */
+ alu_state = info->aux.alu_state;
+ alu_limit = abs(info->aux.alu_limit - alu_limit);
+ } else {
+ alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
+ alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0;
+ alu_state |= ptr_is_dst_reg ?
+ BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
+
+ /* Limit pruning on unknown scalars to enable deep search for
+ * potential masking differences from other program paths.
+ */
+ if (!off_is_imm)
+ env->explore_alu_limits = true;
+ }
+
+ err = update_alu_sanitation_state(aux, alu_state, alu_limit);
+ if (err < 0)
+ return err;
+do_sim:
+ /* If we're in commit phase, we're done here given we already
+ * pushed the truncated dst_reg into the speculative verification
+ * stack.
+ *
+ * Also, when register is a known constant, we rewrite register-based
+ * operation to immediate-based, and thus do not need masking (and as
+ * a consequence, do not need to simulate the zero-truncation either).
+ */
+ if (commit_window || off_is_imm)
+ return 0;
+
+ /* Simulate and find potential out-of-bounds access under
+ * speculative execution from truncation as a result of
+ * masking when off was not within expected range. If off
+ * sits in dst, then we temporarily need to move ptr there
+ * to simulate dst (== 0) +/-= ptr. Needed, for example,
+ * for cases where we use K-based arithmetic in one direction
+ * and truncated reg-based in the other in order to explore
+ * bad access.
+ */
+ if (!ptr_is_dst_reg) {
+ tmp = *dst_reg;
+ *dst_reg = *ptr_reg;
+ }
+ ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1,
+ env->insn_idx);
+ if (!ptr_is_dst_reg && ret)
+ *dst_reg = tmp;
+ return !ret ? REASON_STACK : 0;
+}
+
+static void sanitize_mark_insn_seen(struct bpf_verifier_env *env)
+{
+ struct bpf_verifier_state *vstate = env->cur_state;
+
+ /* If we simulate paths under speculation, we don't update the
+ * insn as 'seen' such that when we verify unreachable paths in
+ * the non-speculative domain, sanitize_dead_code() can still
+ * rewrite/sanitize them.
+ */
+ if (!vstate->speculative)
+ env->insn_aux_data[env->insn_idx].seen = true;
+}
+
+static int sanitize_err(struct bpf_verifier_env *env,
+ const struct bpf_insn *insn, int reason,
+ const struct bpf_reg_state *off_reg,
+ const struct bpf_reg_state *dst_reg)
+{
+ static const char *err = "pointer arithmetic with it prohibited for !root";
+ const char *op = BPF_OP(insn->code) == BPF_ADD ? "add" : "sub";
+ u32 dst = insn->dst_reg, src = insn->src_reg;
+
+ switch (reason) {
+ case REASON_BOUNDS:
+ verbose(env, "R%d has unknown scalar with mixed signed bounds, %s\n",
+ off_reg == dst_reg ? dst : src, err);
+ break;
+ case REASON_TYPE:
+ verbose(env, "R%d has pointer with unsupported alu operation, %s\n",
+ off_reg == dst_reg ? src : dst, err);
+ break;
+ case REASON_PATHS:
+ verbose(env, "R%d tried to %s from different maps, paths or scalars, %s\n",
+ dst, op, err);
+ break;
+ case REASON_LIMIT:
+ verbose(env, "R%d tried to %s beyond pointer bounds, %s\n",
+ dst, op, err);
+ break;
+ case REASON_STACK:
+ verbose(env, "R%d could not be pushed for speculative verification, %s\n",
+ dst, err);
+ break;
+ default:
+ verbose(env, "verifier internal error: unknown reason (%d)\n",
+ reason);
+ break;
+ }
+
+ return -EACCES;
+}
+
+static int sanitize_check_bounds(struct bpf_verifier_env *env,
+ const struct bpf_insn *insn,
+ const struct bpf_reg_state *dst_reg)
+{
+ u32 dst = insn->dst_reg;
+
+ /* For unprivileged we require that resulting offset must be in bounds
+ * in order to be able to sanitize access later on.
+ */
+ if (env->allow_ptr_leaks)
+ return 0;
+
+ switch (dst_reg->type) {
+ case PTR_TO_STACK:
+ if (check_stack_access(env, dst_reg, dst_reg->off +
+ dst_reg->var_off.value, 1)) {
+ verbose(env, "R%d stack pointer arithmetic goes out of range, "
+ "prohibited for !root\n", dst);
+ return -EACCES;
+ }
+ break;
+ case PTR_TO_MAP_VALUE:
+ if (check_map_access(env, dst, dst_reg->off, 1, false)) {
+ verbose(env, "R%d pointer arithmetic of map value goes out of range, "
+ "prohibited for !root\n", dst);
+ return -EACCES;
+ }
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+/* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off.
+ * Caller should also handle BPF_MOV case separately.
+ * If we return -EACCES, caller may want to try again treating pointer as a
+ * scalar. So we only emit a diagnostic if !env->allow_ptr_leaks.
+ */
+static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
+ struct bpf_insn *insn,
+ const struct bpf_reg_state *ptr_reg,
+ const struct bpf_reg_state *off_reg)
+{
+ struct bpf_verifier_state *vstate = env->cur_state;
+ struct bpf_func_state *state = vstate->frame[vstate->curframe];
+ struct bpf_reg_state *regs = state->regs, *dst_reg;
+ bool known = tnum_is_const(off_reg->var_off);
+ s64 smin_val = off_reg->smin_value, smax_val = off_reg->smax_value,
+ smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
+ u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value,
+ umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value;
+ struct bpf_sanitize_info info = {};
+ u8 opcode = BPF_OP(insn->code);
+ u32 dst = insn->dst_reg;
+ int ret;
+
+ dst_reg = &regs[dst];
+
+ if ((known && (smin_val != smax_val || umin_val != umax_val)) ||
+ smin_val > smax_val || umin_val > umax_val) {
+ /* Taint dst register if offset had invalid bounds derived from
+ * e.g. dead branches.
+ */
+ __mark_reg_unknown(dst_reg);
+ return 0;
+ }
+
+ if (BPF_CLASS(insn->code) != BPF_ALU64) {
+ /* 32-bit ALU ops on pointers produce (meaningless) scalars */
+ verbose(env,
+ "R%d 32-bit pointer arithmetic prohibited\n",
+ dst);
+ return -EACCES;
+ }
+
+ if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
+ verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n",
+ dst);
+ return -EACCES;
+ }
+ if (ptr_reg->type == CONST_PTR_TO_MAP) {
+ verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n",
+ dst);
+ return -EACCES;
+ }
+ if (ptr_reg->type == PTR_TO_PACKET_END) {
+ verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n",
+ dst);
+ return -EACCES;
+ }
+
+ /* In case of 'scalar += pointer', dst_reg inherits pointer type and id.
+ * The id may be overwritten later if we create a new variable offset.
+ */
+ dst_reg->type = ptr_reg->type;
+ dst_reg->id = ptr_reg->id;
+
+ if (!check_reg_sane_offset(env, off_reg, ptr_reg->type) ||
+ !check_reg_sane_offset(env, ptr_reg, ptr_reg->type))
+ return -EINVAL;
+
+ if (sanitize_needed(opcode)) {
+ ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg,
+ &info, false);
+ if (ret < 0)
+ return sanitize_err(env, insn, ret, off_reg, dst_reg);
+ }
+
+ switch (opcode) {
+ case BPF_ADD:
+ /* We can take a fixed offset as long as it doesn't overflow
+ * the s32 'off' field
+ */
+ if (known && (ptr_reg->off + smin_val ==
+ (s64)(s32)(ptr_reg->off + smin_val))) {
+ /* pointer += K. Accumulate it into fixed offset */
+ dst_reg->smin_value = smin_ptr;
+ dst_reg->smax_value = smax_ptr;
+ dst_reg->umin_value = umin_ptr;
+ dst_reg->umax_value = umax_ptr;
+ dst_reg->var_off = ptr_reg->var_off;
+ dst_reg->off = ptr_reg->off + smin_val;
+ dst_reg->raw = ptr_reg->raw;
+ break;
+ }
+ /* A new variable offset is created. Note that off_reg->off
+ * == 0, since it's a scalar.
+ * dst_reg gets the pointer type and since some positive
+ * integer value was added to the pointer, give it a new 'id'
+ * if it's a PTR_TO_PACKET.
+ * this creates a new 'base' pointer, off_reg (variable) gets
+ * added into the variable offset, and we copy the fixed offset
+ * from ptr_reg.
+ */
+ if (signed_add_overflows(smin_ptr, smin_val) ||
+ signed_add_overflows(smax_ptr, smax_val)) {
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ } else {
+ dst_reg->smin_value = smin_ptr + smin_val;
+ dst_reg->smax_value = smax_ptr + smax_val;
+ }
+ if (umin_ptr + umin_val < umin_ptr ||
+ umax_ptr + umax_val < umax_ptr) {
+ dst_reg->umin_value = 0;
+ dst_reg->umax_value = U64_MAX;
+ } else {
+ dst_reg->umin_value = umin_ptr + umin_val;
+ dst_reg->umax_value = umax_ptr + umax_val;
+ }
+ dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off);
+ dst_reg->off = ptr_reg->off;
+ dst_reg->raw = ptr_reg->raw;
+ if (reg_is_pkt_pointer(ptr_reg)) {
+ dst_reg->id = ++env->id_gen;
+ /* something was added to pkt_ptr, set range to zero */
+ dst_reg->raw = 0;
+ }
+ break;
+ case BPF_SUB:
+ if (dst_reg == off_reg) {
+ /* scalar -= pointer. Creates an unknown scalar */
+ verbose(env, "R%d tried to subtract pointer from scalar\n",
+ dst);
+ return -EACCES;
+ }
+ /* We don't allow subtraction from FP, because (according to
+ * test_verifier.c test "invalid fp arithmetic", JITs might not
+ * be able to deal with it.
+ */
+ if (ptr_reg->type == PTR_TO_STACK) {
+ verbose(env, "R%d subtraction from stack pointer prohibited\n",
+ dst);
+ return -EACCES;
+ }
+ if (known && (ptr_reg->off - smin_val ==
+ (s64)(s32)(ptr_reg->off - smin_val))) {
+ /* pointer -= K. Subtract it from fixed offset */
+ dst_reg->smin_value = smin_ptr;
+ dst_reg->smax_value = smax_ptr;
+ dst_reg->umin_value = umin_ptr;
+ dst_reg->umax_value = umax_ptr;
+ dst_reg->var_off = ptr_reg->var_off;
+ dst_reg->id = ptr_reg->id;
+ dst_reg->off = ptr_reg->off - smin_val;
+ dst_reg->raw = ptr_reg->raw;
+ break;
+ }
+ /* A new variable offset is created. If the subtrahend is known
+ * nonnegative, then any reg->range we had before is still good.
+ */
+ if (signed_sub_overflows(smin_ptr, smax_val) ||
+ signed_sub_overflows(smax_ptr, smin_val)) {
+ /* Overflow possible, we know nothing */
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ } else {
+ dst_reg->smin_value = smin_ptr - smax_val;
+ dst_reg->smax_value = smax_ptr - smin_val;
+ }
+ if (umin_ptr < umax_val) {
+ /* Overflow possible, we know nothing */
+ dst_reg->umin_value = 0;
+ dst_reg->umax_value = U64_MAX;
+ } else {
+ /* Cannot overflow (as long as bounds are consistent) */
+ dst_reg->umin_value = umin_ptr - umax_val;
+ dst_reg->umax_value = umax_ptr - umin_val;
+ }
+ dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off);
+ dst_reg->off = ptr_reg->off;
+ dst_reg->raw = ptr_reg->raw;
+ if (reg_is_pkt_pointer(ptr_reg)) {
+ dst_reg->id = ++env->id_gen;
+ /* something was added to pkt_ptr, set range to zero */
+ if (smin_val < 0)
+ dst_reg->raw = 0;
+ }
+ break;
+ case BPF_AND:
+ case BPF_OR:
+ case BPF_XOR:
+ /* bitwise ops on pointers are troublesome, prohibit. */
+ verbose(env, "R%d bitwise operator %s on pointer prohibited\n",
+ dst, bpf_alu_string[opcode >> 4]);
+ return -EACCES;
+ default:
+ /* other operators (e.g. MUL,LSH) produce non-pointer results */
+ verbose(env, "R%d pointer arithmetic with %s operator prohibited\n",
+ dst, bpf_alu_string[opcode >> 4]);
+ return -EACCES;
+ }
+
+ if (!check_reg_sane_offset(env, dst_reg, ptr_reg->type))
+ return -EINVAL;
+
+ __update_reg_bounds(dst_reg);
+ __reg_deduce_bounds(dst_reg);
+ __reg_bound_offset(dst_reg);
+
+ if (sanitize_check_bounds(env, insn, dst_reg) < 0)
+ return -EACCES;
+ if (sanitize_needed(opcode)) {
+ ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg,
+ &info, true);
+ if (ret < 0)
+ return sanitize_err(env, insn, ret, off_reg, dst_reg);
+ }
+
+ return 0;
+}
+
+/* WARNING: This function does calculations on 64-bit values, but the actual
+ * execution may occur on 32-bit values. Therefore, things like bitshifts
+ * need extra checks in the 32-bit case.
+ */
+static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
+ struct bpf_insn *insn,
+ struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state src_reg)
+{
+ struct bpf_reg_state *regs = cur_regs(env);
+ u8 opcode = BPF_OP(insn->code);
+ bool src_known, dst_known;
+ s64 smin_val, smax_val;
+ u64 umin_val, umax_val;
+ u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32;
+ int ret;
+
+ if (insn_bitness == 32) {
+ /* Relevant for 32-bit RSH: Information can propagate towards
+ * LSB, so it isn't sufficient to only truncate the output to
+ * 32 bits.
+ */
+ coerce_reg_to_size(dst_reg, 4);
+ coerce_reg_to_size(&src_reg, 4);
+ }
+
+ smin_val = src_reg.smin_value;
+ smax_val = src_reg.smax_value;
+ umin_val = src_reg.umin_value;
+ umax_val = src_reg.umax_value;
+ src_known = tnum_is_const(src_reg.var_off);
+ dst_known = tnum_is_const(dst_reg->var_off);
+
+ if ((src_known && (smin_val != smax_val || umin_val != umax_val)) ||
+ smin_val > smax_val || umin_val > umax_val) {
+ /* Taint dst register if offset had invalid bounds derived from
+ * e.g. dead branches.
+ */
+ __mark_reg_unknown(dst_reg);
+ return 0;
+ }
+
+ if (!src_known &&
+ opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) {
+ __mark_reg_unknown(dst_reg);
+ return 0;
+ }
+
+ if (sanitize_needed(opcode)) {
+ ret = sanitize_val_alu(env, insn);
+ if (ret < 0)
+ return sanitize_err(env, insn, ret, NULL, NULL);
+ }
+
+ switch (opcode) {
+ case BPF_ADD:
+ if (signed_add_overflows(dst_reg->smin_value, smin_val) ||
+ signed_add_overflows(dst_reg->smax_value, smax_val)) {
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ } else {
+ dst_reg->smin_value += smin_val;
+ dst_reg->smax_value += smax_val;
+ }
+ if (dst_reg->umin_value + umin_val < umin_val ||
+ dst_reg->umax_value + umax_val < umax_val) {
+ dst_reg->umin_value = 0;
+ dst_reg->umax_value = U64_MAX;
+ } else {
+ dst_reg->umin_value += umin_val;
+ dst_reg->umax_value += umax_val;
+ }
+ dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off);
+ break;
+ case BPF_SUB:
+ if (signed_sub_overflows(dst_reg->smin_value, smax_val) ||
+ signed_sub_overflows(dst_reg->smax_value, smin_val)) {
+ /* Overflow possible, we know nothing */
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ } else {
+ dst_reg->smin_value -= smax_val;
+ dst_reg->smax_value -= smin_val;
+ }
+ if (dst_reg->umin_value < umax_val) {
+ /* Overflow possible, we know nothing */
+ dst_reg->umin_value = 0;
+ dst_reg->umax_value = U64_MAX;
+ } else {
+ /* Cannot overflow (as long as bounds are consistent) */
+ dst_reg->umin_value -= umax_val;
+ dst_reg->umax_value -= umin_val;
+ }
+ dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off);
+ break;
+ case BPF_MUL:
+ dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off);
+ if (smin_val < 0 || dst_reg->smin_value < 0) {
+ /* Ain't nobody got time to multiply that sign */
+ __mark_reg_unbounded(dst_reg);
+ __update_reg_bounds(dst_reg);
+ break;
+ }
+ /* Both values are positive, so we can work with unsigned and
+ * copy the result to signed (unless it exceeds S64_MAX).
+ */
+ if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) {
+ /* Potential overflow, we know nothing */
+ __mark_reg_unbounded(dst_reg);
+ /* (except what we can learn from the var_off) */
+ __update_reg_bounds(dst_reg);
+ break;
+ }
+ dst_reg->umin_value *= umin_val;
+ dst_reg->umax_value *= umax_val;
+ if (dst_reg->umax_value > S64_MAX) {
+ /* Overflow possible, we know nothing */
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ } else {
+ dst_reg->smin_value = dst_reg->umin_value;
+ dst_reg->smax_value = dst_reg->umax_value;
+ }
+ break;
+ case BPF_AND:
+ if (src_known && dst_known) {
+ __mark_reg_known(dst_reg, dst_reg->var_off.value &
+ src_reg.var_off.value);
+ break;
+ }
+ /* We get our minimum from the var_off, since that's inherently
+ * bitwise. Our maximum is the minimum of the operands' maxima.
+ */
+ dst_reg->var_off = tnum_and(dst_reg->var_off, src_reg.var_off);
+ dst_reg->umin_value = dst_reg->var_off.value;
+ dst_reg->umax_value = min(dst_reg->umax_value, umax_val);
+ if (dst_reg->smin_value < 0 || smin_val < 0) {
+ /* Lose signed bounds when ANDing negative numbers,
+ * ain't nobody got time for that.
+ */
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ } else {
+ /* ANDing two positives gives a positive, so safe to
+ * cast result into s64.
+ */
+ dst_reg->smin_value = dst_reg->umin_value;
+ dst_reg->smax_value = dst_reg->umax_value;
+ }
+ /* We may learn something more from the var_off */
+ __update_reg_bounds(dst_reg);
+ break;
+ case BPF_OR:
+ if (src_known && dst_known) {
+ __mark_reg_known(dst_reg, dst_reg->var_off.value |
+ src_reg.var_off.value);
+ break;
+ }
+ /* We get our maximum from the var_off, and our minimum is the
+ * maximum of the operands' minima
+ */
+ dst_reg->var_off = tnum_or(dst_reg->var_off, src_reg.var_off);
+ dst_reg->umin_value = max(dst_reg->umin_value, umin_val);
+ dst_reg->umax_value = dst_reg->var_off.value |
+ dst_reg->var_off.mask;
+ if (dst_reg->smin_value < 0 || smin_val < 0) {
+ /* Lose signed bounds when ORing negative numbers,
+ * ain't nobody got time for that.
+ */
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ } else {
+ /* ORing two positives gives a positive, so safe to
+ * cast result into s64.
+ */
+ dst_reg->smin_value = dst_reg->umin_value;
+ dst_reg->smax_value = dst_reg->umax_value;
+ }
+ /* We may learn something more from the var_off */
+ __update_reg_bounds(dst_reg);
+ break;
+ case BPF_LSH:
+ if (umax_val >= insn_bitness) {
+ /* Shifts greater than 31 or 63 are undefined.
+ * This includes shifts by a negative number.
+ */
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ break;
+ }
+ /* We lose all sign bit information (except what we can pick
+ * up from var_off)
+ */
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ /* If we might shift our top bit out, then we know nothing */
+ if (dst_reg->umax_value > 1ULL << (63 - umax_val)) {
+ dst_reg->umin_value = 0;
+ dst_reg->umax_value = U64_MAX;
+ } else {
+ dst_reg->umin_value <<= umin_val;
+ dst_reg->umax_value <<= umax_val;
+ }
+ dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val);
+ /* We may learn something more from the var_off */
+ __update_reg_bounds(dst_reg);
+ break;
+ case BPF_RSH:
+ if (umax_val >= insn_bitness) {
+ /* Shifts greater than 31 or 63 are undefined.
+ * This includes shifts by a negative number.
+ */
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ break;
+ }
+ /* BPF_RSH is an unsigned shift. If the value in dst_reg might
+ * be negative, then either:
+ * 1) src_reg might be zero, so the sign bit of the result is
+ * unknown, so we lose our signed bounds
+ * 2) it's known negative, thus the unsigned bounds capture the
+ * signed bounds
+ * 3) the signed bounds cross zero, so they tell us nothing
+ * about the result
+ * If the value in dst_reg is known nonnegative, then again the
+ * unsigned bounts capture the signed bounds.
+ * Thus, in all cases it suffices to blow away our signed bounds
+ * and rely on inferring new ones from the unsigned bounds and
+ * var_off of the result.
+ */
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val);
+ dst_reg->umin_value >>= umax_val;
+ dst_reg->umax_value >>= umin_val;
+ /* We may learn something more from the var_off */
+ __update_reg_bounds(dst_reg);
+ break;
+ case BPF_ARSH:
+ if (umax_val >= insn_bitness) {
+ /* Shifts greater than 31 or 63 are undefined.
+ * This includes shifts by a negative number.
+ */
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ break;
+ }
+
+ /* Upon reaching here, src_known is true and
+ * umax_val is equal to umin_val.
+ */
+ if (insn_bitness == 32) {
+ dst_reg->smin_value = (u32)(((s32)dst_reg->smin_value) >> umin_val);
+ dst_reg->smax_value = (u32)(((s32)dst_reg->smax_value) >> umin_val);
+ } else {
+ dst_reg->smin_value >>= umin_val;
+ dst_reg->smax_value >>= umin_val;
+ }
+
+ dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val,
+ insn_bitness);
+
+ /* blow away the dst_reg umin_value/umax_value and rely on
+ * dst_reg var_off to refine the result.
+ */
+ dst_reg->umin_value = 0;
+ dst_reg->umax_value = U64_MAX;
+ __update_reg_bounds(dst_reg);
+ break;
+ default:
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ break;
+ }
+
+ if (BPF_CLASS(insn->code) != BPF_ALU64) {
+ /* 32-bit ALU ops are (32,32)->32 */
+ coerce_reg_to_size(dst_reg, 4);
+ }
+
+ __reg_deduce_bounds(dst_reg);
+ __reg_bound_offset(dst_reg);
+ return 0;
+}
+
+/* Handles ALU ops other than BPF_END, BPF_NEG and BPF_MOV: computes new min/max
+ * and var_off.
+ */
+static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
+ struct bpf_insn *insn)
+{
+ struct bpf_verifier_state *vstate = env->cur_state;
+ struct bpf_func_state *state = vstate->frame[vstate->curframe];
+ struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg;
+ struct bpf_reg_state *ptr_reg = NULL, off_reg = {0};
+ u8 opcode = BPF_OP(insn->code);
+
+ dst_reg = &regs[insn->dst_reg];
+ src_reg = NULL;
+ if (dst_reg->type != SCALAR_VALUE)
+ ptr_reg = dst_reg;
+ if (BPF_SRC(insn->code) == BPF_X) {
+ src_reg = &regs[insn->src_reg];
+ if (src_reg->type != SCALAR_VALUE) {
+ if (dst_reg->type != SCALAR_VALUE) {
+ /* Combining two pointers by any ALU op yields
+ * an arbitrary scalar. Disallow all math except
+ * pointer subtraction
+ */
+ if (opcode == BPF_SUB && env->allow_ptr_leaks) {
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ return 0;
+ }
+ verbose(env, "R%d pointer %s pointer prohibited\n",
+ insn->dst_reg,
+ bpf_alu_string[opcode >> 4]);
+ return -EACCES;
+ } else {
+ /* scalar += pointer
+ * This is legal, but we have to reverse our
+ * src/dest handling in computing the range
+ */
+ return adjust_ptr_min_max_vals(env, insn,
+ src_reg, dst_reg);
+ }
+ } else if (ptr_reg) {
+ /* pointer += scalar */
+ return adjust_ptr_min_max_vals(env, insn,
+ dst_reg, src_reg);
+ }
+ } else {
+ /* Pretend the src is a reg with a known value, since we only
+ * need to be able to read from this state.
+ */
+ off_reg.type = SCALAR_VALUE;
+ __mark_reg_known(&off_reg, insn->imm);
+ src_reg = &off_reg;
+ if (ptr_reg) /* pointer += K */
+ return adjust_ptr_min_max_vals(env, insn,
+ ptr_reg, src_reg);
+ }
+
+ /* Got here implies adding two SCALAR_VALUEs */
+ if (WARN_ON_ONCE(ptr_reg)) {
+ print_verifier_state(env, state);
+ verbose(env, "verifier internal error: unexpected ptr_reg\n");
+ return -EINVAL;
+ }
+ if (WARN_ON(!src_reg)) {
+ print_verifier_state(env, state);
+ verbose(env, "verifier internal error: no src_reg\n");
+ return -EINVAL;
+ }
+ return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg);
+}
+
+/* check validity of 32-bit and 64-bit arithmetic operations */
+static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
+{
+ struct bpf_reg_state *regs = cur_regs(env);
+ u8 opcode = BPF_OP(insn->code);
+ int err;
+
+ if (opcode == BPF_END || opcode == BPF_NEG) {
+ if (opcode == BPF_NEG) {
+ if (BPF_SRC(insn->code) != 0 ||
+ insn->src_reg != BPF_REG_0 ||
+ insn->off != 0 || insn->imm != 0) {
+ verbose(env, "BPF_NEG uses reserved fields\n");
+ return -EINVAL;
+ }
+ } else {
+ if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
+ (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
+ BPF_CLASS(insn->code) == BPF_ALU64) {
+ verbose(env, "BPF_END uses reserved fields\n");
+ return -EINVAL;
+ }
+ }
+
+ /* check src operand */
+ err = check_reg_arg(env, insn->dst_reg, SRC_OP);
+ if (err)
+ return err;
+
+ if (is_pointer_value(env, insn->dst_reg)) {
+ verbose(env, "R%d pointer arithmetic prohibited\n",
+ insn->dst_reg);
+ return -EACCES;
+ }
+
+ /* check dest operand */
+ err = check_reg_arg(env, insn->dst_reg, DST_OP);
+ if (err)
+ return err;
+
+ } else if (opcode == BPF_MOV) {
+
+ if (BPF_SRC(insn->code) == BPF_X) {
+ if (insn->imm != 0 || insn->off != 0) {
+ verbose(env, "BPF_MOV uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ /* check src operand */
+ err = check_reg_arg(env, insn->src_reg, SRC_OP);
+ if (err)
+ return err;
+ } else {
+ if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
+ verbose(env, "BPF_MOV uses reserved fields\n");
+ return -EINVAL;
+ }
+ }
+
+ /* check dest operand, mark as required later */
+ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
+ if (err)
+ return err;
+
+ if (BPF_SRC(insn->code) == BPF_X) {
+ struct bpf_reg_state *src_reg = regs + insn->src_reg;
+ struct bpf_reg_state *dst_reg = regs + insn->dst_reg;
+
+ if (BPF_CLASS(insn->code) == BPF_ALU64) {
+ /* case: R1 = R2
+ * copy register state to dest reg
+ */
+ *dst_reg = *src_reg;
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ } else {
+ /* R1 = (u32) R2 */
+ if (is_pointer_value(env, insn->src_reg)) {
+ verbose(env,
+ "R%d partial copy of pointer\n",
+ insn->src_reg);
+ return -EACCES;
+ } else if (src_reg->type == SCALAR_VALUE) {
+ *dst_reg = *src_reg;
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ } else {
+ mark_reg_unknown(env, regs,
+ insn->dst_reg);
+ }
+ coerce_reg_to_size(dst_reg, 4);
+ }
+ } else {
+ /* case: R = imm
+ * remember the value we stored into this reg
+ */
+ /* clear any state __mark_reg_known doesn't set */
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ regs[insn->dst_reg].type = SCALAR_VALUE;
+ if (BPF_CLASS(insn->code) == BPF_ALU64) {
+ __mark_reg_known(regs + insn->dst_reg,
+ insn->imm);
+ } else {
+ __mark_reg_known(regs + insn->dst_reg,
+ (u32)insn->imm);
+ }
+ }
+
+ } else if (opcode > BPF_END) {
+ verbose(env, "invalid BPF_ALU opcode %x\n", opcode);
+ return -EINVAL;
+
+ } else { /* all other ALU ops: and, sub, xor, add, ... */
+
+ if (BPF_SRC(insn->code) == BPF_X) {
+ if (insn->imm != 0 || insn->off != 0) {
+ verbose(env, "BPF_ALU uses reserved fields\n");
+ return -EINVAL;
+ }
+ /* check src1 operand */
+ err = check_reg_arg(env, insn->src_reg, SRC_OP);
+ if (err)
+ return err;
+ } else {
+ if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
+ verbose(env, "BPF_ALU uses reserved fields\n");
+ return -EINVAL;
+ }
+ }
+
+ /* check src2 operand */
+ err = check_reg_arg(env, insn->dst_reg, SRC_OP);
+ if (err)
+ return err;
+
+ if ((opcode == BPF_MOD || opcode == BPF_DIV) &&
+ BPF_SRC(insn->code) == BPF_K && insn->imm == 0) {
+ verbose(env, "div by zero\n");
+ return -EINVAL;
+ }
+
+ if (opcode == BPF_ARSH && BPF_CLASS(insn->code) != BPF_ALU64) {
+ verbose(env, "BPF_ARSH not supported for 32 bit ALU\n");
+ return -EINVAL;
+ }
+
+ if ((opcode == BPF_LSH || opcode == BPF_RSH ||
+ opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) {
+ int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;
+
+ if (insn->imm < 0 || insn->imm >= size) {
+ verbose(env, "invalid shift %d\n", insn->imm);
+ return -EINVAL;
+ }
+ }
+
+ /* check dest operand */
+ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
+ if (err)
+ return err;
+
+ return adjust_reg_min_max_vals(env, insn);
+ }
+
+ return 0;
+}
+
+static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
+ struct bpf_reg_state *dst_reg,
+ enum bpf_reg_type type,
+ bool range_right_open)
+{
+ struct bpf_func_state *state = vstate->frame[vstate->curframe];
+ struct bpf_reg_state *regs = state->regs, *reg;
+ u16 new_range;
+ int i, j;
+
+ if (dst_reg->off < 0 ||
+ (dst_reg->off == 0 && range_right_open))
+ /* This doesn't give us any range */
+ return;
+
+ if (dst_reg->umax_value > MAX_PACKET_OFF ||
+ dst_reg->umax_value + dst_reg->off > MAX_PACKET_OFF)
+ /* Risk of overflow. For instance, ptr + (1<<63) may be less
+ * than pkt_end, but that's because it's also less than pkt.
+ */
+ return;
+
+ new_range = dst_reg->off;
+ if (range_right_open)
+ new_range++;
+
+ /* Examples for register markings:
+ *
+ * pkt_data in dst register:
+ *
+ * r2 = r3;
+ * r2 += 8;
+ * if (r2 > pkt_end) goto <handle exception>
+ * <access okay>
+ *
+ * r2 = r3;
+ * r2 += 8;
+ * if (r2 < pkt_end) goto <access okay>
+ * <handle exception>
+ *
+ * Where:
+ * r2 == dst_reg, pkt_end == src_reg
+ * r2=pkt(id=n,off=8,r=0)
+ * r3=pkt(id=n,off=0,r=0)
+ *
+ * pkt_data in src register:
+ *
+ * r2 = r3;
+ * r2 += 8;
+ * if (pkt_end >= r2) goto <access okay>
+ * <handle exception>
+ *
+ * r2 = r3;
+ * r2 += 8;
+ * if (pkt_end <= r2) goto <handle exception>
+ * <access okay>
+ *
+ * Where:
+ * pkt_end == dst_reg, r2 == src_reg
+ * r2=pkt(id=n,off=8,r=0)
+ * r3=pkt(id=n,off=0,r=0)
+ *
+ * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8)
+ * or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8)
+ * and [r3, r3 + 8-1) respectively is safe to access depending on
+ * the check.
+ */
+
+ /* If our ids match, then we must have the same max_value. And we
+ * don't care about the other reg's fixed offset, since if it's too big
+ * the range won't allow anything.
+ * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16.
+ */
+ for (i = 0; i < MAX_BPF_REG; i++)
+ if (regs[i].type == type && regs[i].id == dst_reg->id)
+ /* keep the maximum range already checked */
+ regs[i].range = max(regs[i].range, new_range);
+
+ for (j = 0; j <= vstate->curframe; j++) {
+ state = vstate->frame[j];
+ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+ if (state->stack[i].slot_type[0] != STACK_SPILL)
+ continue;
+ reg = &state->stack[i].spilled_ptr;
+ if (reg->type == type && reg->id == dst_reg->id)
+ reg->range = max(reg->range, new_range);
+ }
+ }
+}
+
+/* compute branch direction of the expression "if (reg opcode val) goto target;"
+ * and return:
+ * 1 - branch will be taken and "goto target" will be executed
+ * 0 - branch will not be taken and fall-through to next insn
+ * -1 - unknown. Example: "if (reg < 5)" is unknown when register value range [0,10]
+ */
+static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
+{
+ if (__is_pointer_value(false, reg))
+ return -1;
+
+ switch (opcode) {
+ case BPF_JEQ:
+ if (tnum_is_const(reg->var_off))
+ return !!tnum_equals_const(reg->var_off, val);
+ break;
+ case BPF_JNE:
+ if (tnum_is_const(reg->var_off))
+ return !tnum_equals_const(reg->var_off, val);
+ break;
+ case BPF_JGT:
+ if (reg->umin_value > val)
+ return 1;
+ else if (reg->umax_value <= val)
+ return 0;
+ break;
+ case BPF_JSGT:
+ if (reg->smin_value > (s64)val)
+ return 1;
+ else if (reg->smax_value < (s64)val)
+ return 0;
+ break;
+ case BPF_JLT:
+ if (reg->umax_value < val)
+ return 1;
+ else if (reg->umin_value >= val)
+ return 0;
+ break;
+ case BPF_JSLT:
+ if (reg->smax_value < (s64)val)
+ return 1;
+ else if (reg->smin_value >= (s64)val)
+ return 0;
+ break;
+ case BPF_JGE:
+ if (reg->umin_value >= val)
+ return 1;
+ else if (reg->umax_value < val)
+ return 0;
+ break;
+ case BPF_JSGE:
+ if (reg->smin_value >= (s64)val)
+ return 1;
+ else if (reg->smax_value < (s64)val)
+ return 0;
+ break;
+ case BPF_JLE:
+ if (reg->umax_value <= val)
+ return 1;
+ else if (reg->umin_value > val)
+ return 0;
+ break;
+ case BPF_JSLE:
+ if (reg->smax_value <= (s64)val)
+ return 1;
+ else if (reg->smin_value > (s64)val)
+ return 0;
+ break;
+ }
+
+ return -1;
+}
+
+/* Adjusts the register min/max values in the case that the dst_reg is the
+ * variable register that we are working on, and src_reg is a constant or we're
+ * simply doing a BPF_K check.
+ * In JEQ/JNE cases we also adjust the var_off values.
+ */
+static void reg_set_min_max(struct bpf_reg_state *true_reg,
+ struct bpf_reg_state *false_reg, u64 val,
+ u8 opcode)
+{
+ /* If the dst_reg is a pointer, we can't learn anything about its
+ * variable offset from the compare (unless src_reg were a pointer into
+ * the same object, but we don't bother with that.
+ * Since false_reg and true_reg have the same type by construction, we
+ * only need to check one of them for pointerness.
+ */
+ if (__is_pointer_value(false, false_reg))
+ return;
+
+ switch (opcode) {
+ case BPF_JEQ:
+ /* If this is false then we know nothing Jon Snow, but if it is
+ * true then we know for sure.
+ */
+ __mark_reg_known(true_reg, val);
+ break;
+ case BPF_JNE:
+ /* If this is true we know nothing Jon Snow, but if it is false
+ * we know the value for sure;
+ */
+ __mark_reg_known(false_reg, val);
+ break;
+ case BPF_JGT:
+ false_reg->umax_value = min(false_reg->umax_value, val);
+ true_reg->umin_value = max(true_reg->umin_value, val + 1);
+ break;
+ case BPF_JSGT:
+ false_reg->smax_value = min_t(s64, false_reg->smax_value, val);
+ true_reg->smin_value = max_t(s64, true_reg->smin_value, val + 1);
+ break;
+ case BPF_JLT:
+ false_reg->umin_value = max(false_reg->umin_value, val);
+ true_reg->umax_value = min(true_reg->umax_value, val - 1);
+ break;
+ case BPF_JSLT:
+ false_reg->smin_value = max_t(s64, false_reg->smin_value, val);
+ true_reg->smax_value = min_t(s64, true_reg->smax_value, val - 1);
+ break;
+ case BPF_JGE:
+ false_reg->umax_value = min(false_reg->umax_value, val - 1);
+ true_reg->umin_value = max(true_reg->umin_value, val);
+ break;
+ case BPF_JSGE:
+ false_reg->smax_value = min_t(s64, false_reg->smax_value, val - 1);
+ true_reg->smin_value = max_t(s64, true_reg->smin_value, val);
+ break;
+ case BPF_JLE:
+ false_reg->umin_value = max(false_reg->umin_value, val + 1);
+ true_reg->umax_value = min(true_reg->umax_value, val);
+ break;
+ case BPF_JSLE:
+ false_reg->smin_value = max_t(s64, false_reg->smin_value, val + 1);
+ true_reg->smax_value = min_t(s64, true_reg->smax_value, val);
+ break;
+ default:
+ break;
+ }
+
+ __reg_deduce_bounds(false_reg);
+ __reg_deduce_bounds(true_reg);
+ /* We might have learned some bits from the bounds. */
+ __reg_bound_offset(false_reg);
+ __reg_bound_offset(true_reg);
+ /* Intersecting with the old var_off might have improved our bounds
+ * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
+ * then new var_off is (0; 0x7f...fc) which improves our umax.
+ */
+ __update_reg_bounds(false_reg);
+ __update_reg_bounds(true_reg);
+}
+
+/* Same as above, but for the case that dst_reg holds a constant and src_reg is
+ * the variable reg.
+ */
+static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
+ struct bpf_reg_state *false_reg, u64 val,
+ u8 opcode)
+{
+ if (__is_pointer_value(false, false_reg))
+ return;
+
+ switch (opcode) {
+ case BPF_JEQ:
+ /* If this is false then we know nothing Jon Snow, but if it is
+ * true then we know for sure.
+ */
+ __mark_reg_known(true_reg, val);
+ break;
+ case BPF_JNE:
+ /* If this is true we know nothing Jon Snow, but if it is false
+ * we know the value for sure;
+ */
+ __mark_reg_known(false_reg, val);
+ break;
+ case BPF_JGT:
+ true_reg->umax_value = min(true_reg->umax_value, val - 1);
+ false_reg->umin_value = max(false_reg->umin_value, val);
+ break;
+ case BPF_JSGT:
+ true_reg->smax_value = min_t(s64, true_reg->smax_value, val - 1);
+ false_reg->smin_value = max_t(s64, false_reg->smin_value, val);
+ break;
+ case BPF_JLT:
+ true_reg->umin_value = max(true_reg->umin_value, val + 1);
+ false_reg->umax_value = min(false_reg->umax_value, val);
+ break;
+ case BPF_JSLT:
+ true_reg->smin_value = max_t(s64, true_reg->smin_value, val + 1);
+ false_reg->smax_value = min_t(s64, false_reg->smax_value, val);
+ break;
+ case BPF_JGE:
+ true_reg->umax_value = min(true_reg->umax_value, val);
+ false_reg->umin_value = max(false_reg->umin_value, val + 1);
+ break;
+ case BPF_JSGE:
+ true_reg->smax_value = min_t(s64, true_reg->smax_value, val);
+ false_reg->smin_value = max_t(s64, false_reg->smin_value, val + 1);
+ break;
+ case BPF_JLE:
+ true_reg->umin_value = max(true_reg->umin_value, val);
+ false_reg->umax_value = min(false_reg->umax_value, val - 1);
+ break;
+ case BPF_JSLE:
+ true_reg->smin_value = max_t(s64, true_reg->smin_value, val);
+ false_reg->smax_value = min_t(s64, false_reg->smax_value, val - 1);
+ break;
+ default:
+ break;
+ }
+
+ __reg_deduce_bounds(false_reg);
+ __reg_deduce_bounds(true_reg);
+ /* We might have learned some bits from the bounds. */
+ __reg_bound_offset(false_reg);
+ __reg_bound_offset(true_reg);
+ /* Intersecting with the old var_off might have improved our bounds
+ * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
+ * then new var_off is (0; 0x7f...fc) which improves our umax.
+ */
+ __update_reg_bounds(false_reg);
+ __update_reg_bounds(true_reg);
+}
+
+/* Regs are known to be equal, so intersect their min/max/var_off */
+static void __reg_combine_min_max(struct bpf_reg_state *src_reg,
+ struct bpf_reg_state *dst_reg)
+{
+ src_reg->umin_value = dst_reg->umin_value = max(src_reg->umin_value,
+ dst_reg->umin_value);
+ src_reg->umax_value = dst_reg->umax_value = min(src_reg->umax_value,
+ dst_reg->umax_value);
+ src_reg->smin_value = dst_reg->smin_value = max(src_reg->smin_value,
+ dst_reg->smin_value);
+ src_reg->smax_value = dst_reg->smax_value = min(src_reg->smax_value,
+ dst_reg->smax_value);
+ src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off,
+ dst_reg->var_off);
+ /* We might have learned new bounds from the var_off. */
+ __update_reg_bounds(src_reg);
+ __update_reg_bounds(dst_reg);
+ /* We might have learned something about the sign bit. */
+ __reg_deduce_bounds(src_reg);
+ __reg_deduce_bounds(dst_reg);
+ /* We might have learned some bits from the bounds. */
+ __reg_bound_offset(src_reg);
+ __reg_bound_offset(dst_reg);
+ /* Intersecting with the old var_off might have improved our bounds
+ * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
+ * then new var_off is (0; 0x7f...fc) which improves our umax.
+ */
+ __update_reg_bounds(src_reg);
+ __update_reg_bounds(dst_reg);
+}
+
+static void reg_combine_min_max(struct bpf_reg_state *true_src,
+ struct bpf_reg_state *true_dst,
+ struct bpf_reg_state *false_src,
+ struct bpf_reg_state *false_dst,
+ u8 opcode)
+{
+ switch (opcode) {
+ case BPF_JEQ:
+ __reg_combine_min_max(true_src, true_dst);
+ break;
+ case BPF_JNE:
+ __reg_combine_min_max(false_src, false_dst);
+ break;
+ }
+}
+
+static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
+ bool is_null)
+{
+ struct bpf_reg_state *reg = &regs[regno];
+
+ if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) {
+ /* Old offset (both fixed and variable parts) should
+ * have been known-zero, because we don't allow pointer
+ * arithmetic on pointers that might be NULL.
+ */
+ if (WARN_ON_ONCE(reg->smin_value || reg->smax_value ||
+ !tnum_equals_const(reg->var_off, 0) ||
+ reg->off)) {
+ __mark_reg_known_zero(reg);
+ reg->off = 0;
+ }
+ if (is_null) {
+ reg->type = SCALAR_VALUE;
+ } else if (reg->map_ptr->inner_map_meta) {
+ reg->type = CONST_PTR_TO_MAP;
+ reg->map_ptr = reg->map_ptr->inner_map_meta;
+ } else {
+ reg->type = PTR_TO_MAP_VALUE;
+ }
+ /* We don't need id from this point onwards anymore, thus we
+ * should better reset it, so that state pruning has chances
+ * to take effect.
+ */
+ reg->id = 0;
+ }
+}
+
+/* The logic is similar to find_good_pkt_pointers(), both could eventually
+ * be folded together at some point.
+ */
+static void mark_map_regs(struct bpf_verifier_state *vstate, u32 regno,
+ bool is_null)
+{
+ struct bpf_func_state *state = vstate->frame[vstate->curframe];
+ struct bpf_reg_state *regs = state->regs;
+ u32 id = regs[regno].id;
+ int i, j;
+
+ for (i = 0; i < MAX_BPF_REG; i++)
+ mark_map_reg(regs, i, id, is_null);
+
+ for (j = 0; j <= vstate->curframe; j++) {
+ state = vstate->frame[j];
+ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+ if (state->stack[i].slot_type[0] != STACK_SPILL)
+ continue;
+ mark_map_reg(&state->stack[i].spilled_ptr, 0, id, is_null);
+ }
+ }
+}
+
+static bool try_match_pkt_pointers(const struct bpf_insn *insn,
+ struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg,
+ struct bpf_verifier_state *this_branch,
+ struct bpf_verifier_state *other_branch)
+{
+ if (BPF_SRC(insn->code) != BPF_X)
+ return false;
+
+ switch (BPF_OP(insn->code)) {
+ case BPF_JGT:
+ if ((dst_reg->type == PTR_TO_PACKET &&
+ src_reg->type == PTR_TO_PACKET_END) ||
+ (dst_reg->type == PTR_TO_PACKET_META &&
+ reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
+ /* pkt_data' > pkt_end, pkt_meta' > pkt_data */
+ find_good_pkt_pointers(this_branch, dst_reg,
+ dst_reg->type, false);
+ } else if ((dst_reg->type == PTR_TO_PACKET_END &&
+ src_reg->type == PTR_TO_PACKET) ||
+ (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
+ src_reg->type == PTR_TO_PACKET_META)) {
+ /* pkt_end > pkt_data', pkt_data > pkt_meta' */
+ find_good_pkt_pointers(other_branch, src_reg,
+ src_reg->type, true);
+ } else {
+ return false;
+ }
+ break;
+ case BPF_JLT:
+ if ((dst_reg->type == PTR_TO_PACKET &&
+ src_reg->type == PTR_TO_PACKET_END) ||
+ (dst_reg->type == PTR_TO_PACKET_META &&
+ reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
+ /* pkt_data' < pkt_end, pkt_meta' < pkt_data */
+ find_good_pkt_pointers(other_branch, dst_reg,
+ dst_reg->type, true);
+ } else if ((dst_reg->type == PTR_TO_PACKET_END &&
+ src_reg->type == PTR_TO_PACKET) ||
+ (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
+ src_reg->type == PTR_TO_PACKET_META)) {
+ /* pkt_end < pkt_data', pkt_data > pkt_meta' */
+ find_good_pkt_pointers(this_branch, src_reg,
+ src_reg->type, false);
+ } else {
+ return false;
+ }
+ break;
+ case BPF_JGE:
+ if ((dst_reg->type == PTR_TO_PACKET &&
+ src_reg->type == PTR_TO_PACKET_END) ||
+ (dst_reg->type == PTR_TO_PACKET_META &&
+ reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
+ /* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */
+ find_good_pkt_pointers(this_branch, dst_reg,
+ dst_reg->type, true);
+ } else if ((dst_reg->type == PTR_TO_PACKET_END &&
+ src_reg->type == PTR_TO_PACKET) ||
+ (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
+ src_reg->type == PTR_TO_PACKET_META)) {
+ /* pkt_end >= pkt_data', pkt_data >= pkt_meta' */
+ find_good_pkt_pointers(other_branch, src_reg,
+ src_reg->type, false);
+ } else {
+ return false;
+ }
+ break;
+ case BPF_JLE:
+ if ((dst_reg->type == PTR_TO_PACKET &&
+ src_reg->type == PTR_TO_PACKET_END) ||
+ (dst_reg->type == PTR_TO_PACKET_META &&
+ reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
+ /* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */
+ find_good_pkt_pointers(other_branch, dst_reg,
+ dst_reg->type, false);
+ } else if ((dst_reg->type == PTR_TO_PACKET_END &&
+ src_reg->type == PTR_TO_PACKET) ||
+ (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
+ src_reg->type == PTR_TO_PACKET_META)) {
+ /* pkt_end <= pkt_data', pkt_data <= pkt_meta' */
+ find_good_pkt_pointers(this_branch, src_reg,
+ src_reg->type, true);
+ } else {
+ return false;
+ }
+ break;
+ default:
+ return false;
+ }
+
+ return true;
+}
+
+static int check_cond_jmp_op(struct bpf_verifier_env *env,
+ struct bpf_insn *insn, int *insn_idx)
+{
+ struct bpf_verifier_state *this_branch = env->cur_state;
+ struct bpf_verifier_state *other_branch;
+ struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs;
+ struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL;
+ u8 opcode = BPF_OP(insn->code);
+ int pred = -1;
+ int err;
+
+ if (opcode > BPF_JSLE) {
+ verbose(env, "invalid BPF_JMP opcode %x\n", opcode);
+ return -EINVAL;
+ }
+
+ if (BPF_SRC(insn->code) == BPF_X) {
+ if (insn->imm != 0) {
+ verbose(env, "BPF_JMP uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ /* check src1 operand */
+ err = check_reg_arg(env, insn->src_reg, SRC_OP);
+ if (err)
+ return err;
+
+ if (is_pointer_value(env, insn->src_reg)) {
+ verbose(env, "R%d pointer comparison prohibited\n",
+ insn->src_reg);
+ return -EACCES;
+ }
+ src_reg = &regs[insn->src_reg];
+ } else {
+ if (insn->src_reg != BPF_REG_0) {
+ verbose(env, "BPF_JMP uses reserved fields\n");
+ return -EINVAL;
+ }
+ }
+
+ /* check src2 operand */
+ err = check_reg_arg(env, insn->dst_reg, SRC_OP);
+ if (err)
+ return err;
+
+ dst_reg = &regs[insn->dst_reg];
+
+ if (BPF_SRC(insn->code) == BPF_K)
+ pred = is_branch_taken(dst_reg, insn->imm, opcode);
+ else if (src_reg->type == SCALAR_VALUE &&
+ tnum_is_const(src_reg->var_off))
+ pred = is_branch_taken(dst_reg, src_reg->var_off.value,
+ opcode);
+
+ if (pred == 1) {
+ /* Only follow the goto, ignore fall-through. If needed, push
+ * the fall-through branch for simulation under speculative
+ * execution.
+ */
+ if (!env->allow_ptr_leaks &&
+ !sanitize_speculative_path(env, insn, *insn_idx + 1,
+ *insn_idx))
+ return -EFAULT;
+ *insn_idx += insn->off;
+ return 0;
+ } else if (pred == 0) {
+ /* Only follow the fall-through branch, since that's where the
+ * program will go. If needed, push the goto branch for
+ * simulation under speculative execution.
+ */
+ if (!env->allow_ptr_leaks &&
+ !sanitize_speculative_path(env, insn,
+ *insn_idx + insn->off + 1,
+ *insn_idx))
+ return -EFAULT;
+ return 0;
+ }
+
+ other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx,
+ false);
+ if (!other_branch)
+ return -EFAULT;
+ other_branch_regs = other_branch->frame[other_branch->curframe]->regs;
+
+ /* detect if we are comparing against a constant value so we can adjust
+ * our min/max values for our dst register.
+ * this is only legit if both are scalars (or pointers to the same
+ * object, I suppose, but we don't support that right now), because
+ * otherwise the different base pointers mean the offsets aren't
+ * comparable.
+ */
+ if (BPF_SRC(insn->code) == BPF_X) {
+ if (dst_reg->type == SCALAR_VALUE &&
+ regs[insn->src_reg].type == SCALAR_VALUE) {
+ if (tnum_is_const(regs[insn->src_reg].var_off))
+ reg_set_min_max(&other_branch_regs[insn->dst_reg],
+ dst_reg, regs[insn->src_reg].var_off.value,
+ opcode);
+ else if (tnum_is_const(dst_reg->var_off))
+ reg_set_min_max_inv(&other_branch_regs[insn->src_reg],
+ &regs[insn->src_reg],
+ dst_reg->var_off.value, opcode);
+ else if (opcode == BPF_JEQ || opcode == BPF_JNE)
+ /* Comparing for equality, we can combine knowledge */
+ reg_combine_min_max(&other_branch_regs[insn->src_reg],
+ &other_branch_regs[insn->dst_reg],
+ &regs[insn->src_reg],
+ &regs[insn->dst_reg], opcode);
+ }
+ } else if (dst_reg->type == SCALAR_VALUE) {
+ reg_set_min_max(&other_branch_regs[insn->dst_reg],
+ dst_reg, insn->imm, opcode);
+ }
+
+ /* detect if R == 0 where R is returned from bpf_map_lookup_elem() */
+ if (BPF_SRC(insn->code) == BPF_K &&
+ insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
+ dst_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
+ /* Mark all identical map registers in each branch as either
+ * safe or unknown depending R == 0 or R != 0 conditional.
+ */
+ mark_map_regs(this_branch, insn->dst_reg, opcode == BPF_JNE);
+ mark_map_regs(other_branch, insn->dst_reg, opcode == BPF_JEQ);
+ } else if (!try_match_pkt_pointers(insn, dst_reg, &regs[insn->src_reg],
+ this_branch, other_branch) &&
+ is_pointer_value(env, insn->dst_reg)) {
+ verbose(env, "R%d pointer comparison prohibited\n",
+ insn->dst_reg);
+ return -EACCES;
+ }
+ if (env->log.level)
+ print_verifier_state(env, this_branch->frame[this_branch->curframe]);
+ return 0;
+}
+
+/* return the map pointer stored inside BPF_LD_IMM64 instruction */
+static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn)
+{
+ u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32;
+
+ return (struct bpf_map *) (unsigned long) imm64;
+}
+
+/* verify BPF_LD_IMM64 instruction */
+static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
+{
+ struct bpf_reg_state *regs = cur_regs(env);
+ int err;
+
+ if (BPF_SIZE(insn->code) != BPF_DW) {
+ verbose(env, "invalid BPF_LD_IMM insn\n");
+ return -EINVAL;
+ }
+ if (insn->off != 0) {
+ verbose(env, "BPF_LD_IMM64 uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ err = check_reg_arg(env, insn->dst_reg, DST_OP);
+ if (err)
+ return err;
+
+ if (insn->src_reg == 0) {
+ u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
+
+ regs[insn->dst_reg].type = SCALAR_VALUE;
+ __mark_reg_known(&regs[insn->dst_reg], imm);
+ return 0;
+ }
+
+ /* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */
+ BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD);
+
+ regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
+ regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn);
+ return 0;
+}
+
+static bool may_access_skb(enum bpf_prog_type type)
+{
+ switch (type) {
+ case BPF_PROG_TYPE_SOCKET_FILTER:
+ case BPF_PROG_TYPE_SCHED_CLS:
+ case BPF_PROG_TYPE_SCHED_ACT:
+ return true;
+ default:
+ return false;
+ }
+}
+
+/* verify safety of LD_ABS|LD_IND instructions:
+ * - they can only appear in the programs where ctx == skb
+ * - since they are wrappers of function calls, they scratch R1-R5 registers,
+ * preserve R6-R9, and store return value into R0
+ *
+ * Implicit input:
+ * ctx == skb == R6 == CTX
+ *
+ * Explicit input:
+ * SRC == any register
+ * IMM == 32-bit immediate
+ *
+ * Output:
+ * R0 - 8/16/32-bit skb data converted to cpu endianness
+ */
+static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
+{
+ struct bpf_reg_state *regs = cur_regs(env);
+ static const int ctx_reg = BPF_REG_6;
+ u8 mode = BPF_MODE(insn->code);
+ int i, err;
+
+ if (!may_access_skb(env->prog->type)) {
+ verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n");
+ return -EINVAL;
+ }
+
+ if (!env->ops->gen_ld_abs) {
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EINVAL;
+ }
+
+ if (env->subprog_cnt > 1) {
+ /* when program has LD_ABS insn JITs and interpreter assume
+ * that r1 == ctx == skb which is not the case for callees
+ * that can have arbitrary arguments. It's problematic
+ * for main prog as well since JITs would need to analyze
+ * all functions in order to make proper register save/restore
+ * decisions in the main prog. Hence disallow LD_ABS with calls
+ */
+ verbose(env, "BPF_LD_[ABS|IND] instructions cannot be mixed with bpf-to-bpf calls\n");
+ return -EINVAL;
+ }
+
+ if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
+ BPF_SIZE(insn->code) == BPF_DW ||
+ (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
+ verbose(env, "BPF_LD_[ABS|IND] uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ /* check whether implicit source operand (register R6) is readable */
+ err = check_reg_arg(env, ctx_reg, SRC_OP);
+ if (err)
+ return err;
+
+ if (regs[ctx_reg].type != PTR_TO_CTX) {
+ verbose(env,
+ "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
+ return -EINVAL;
+ }
+
+ if (mode == BPF_IND) {
+ /* check explicit source operand */
+ err = check_reg_arg(env, insn->src_reg, SRC_OP);
+ if (err)
+ return err;
+ }
+
+ err = check_ctx_reg(env, &regs[ctx_reg], ctx_reg);
+ if (err < 0)
+ return err;
+
+ /* reset caller saved regs to unreadable */
+ for (i = 0; i < CALLER_SAVED_REGS; i++) {
+ mark_reg_not_init(env, regs, caller_saved[i]);
+ check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
+ }
+
+ /* mark destination R0 register as readable, since it contains
+ * the value fetched from the packet.
+ * Already marked as written above.
+ */
+ mark_reg_unknown(env, regs, BPF_REG_0);
+ return 0;
+}
+
+static int check_return_code(struct bpf_verifier_env *env)
+{
+ struct bpf_reg_state *reg;
+ struct tnum range = tnum_range(0, 1);
+
+ switch (env->prog->type) {
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
+ env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG)
+ range = tnum_range(1, 1);
+ case BPF_PROG_TYPE_CGROUP_SKB:
+ case BPF_PROG_TYPE_CGROUP_SOCK:
+ case BPF_PROG_TYPE_SOCK_OPS:
+ case BPF_PROG_TYPE_CGROUP_DEVICE:
+ break;
+ default:
+ return 0;
+ }
+
+ reg = cur_regs(env) + BPF_REG_0;
+ if (reg->type != SCALAR_VALUE) {
+ verbose(env, "At program exit the register R0 is not a known value (%s)\n",
+ reg_type_str[reg->type]);
+ return -EINVAL;
+ }
+
+ if (!tnum_in(range, reg->var_off)) {
+ char tn_buf[48];
+
+ verbose(env, "At program exit the register R0 ");
+ if (!tnum_is_unknown(reg->var_off)) {
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "has value %s", tn_buf);
+ } else {
+ verbose(env, "has unknown scalar value");
+ }
+ tnum_strn(tn_buf, sizeof(tn_buf), range);
+ verbose(env, " should have been in %s\n", tn_buf);
+ return -EINVAL;
+ }
+ return 0;
+}
+
+/* non-recursive DFS pseudo code
+ * 1 procedure DFS-iterative(G,v):
+ * 2 label v as discovered
+ * 3 let S be a stack
+ * 4 S.push(v)
+ * 5 while S is not empty
+ * 6 t <- S.pop()
+ * 7 if t is what we're looking for:
+ * 8 return t
+ * 9 for all edges e in G.adjacentEdges(t) do
+ * 10 if edge e is already labelled
+ * 11 continue with the next edge
+ * 12 w <- G.adjacentVertex(t,e)
+ * 13 if vertex w is not discovered and not explored
+ * 14 label e as tree-edge
+ * 15 label w as discovered
+ * 16 S.push(w)
+ * 17 continue at 5
+ * 18 else if vertex w is discovered
+ * 19 label e as back-edge
+ * 20 else
+ * 21 // vertex w is explored
+ * 22 label e as forward- or cross-edge
+ * 23 label t as explored
+ * 24 S.pop()
+ *
+ * convention:
+ * 0x10 - discovered
+ * 0x11 - discovered and fall-through edge labelled
+ * 0x12 - discovered and fall-through and branch edges labelled
+ * 0x20 - explored
+ */
+
+enum {
+ DISCOVERED = 0x10,
+ EXPLORED = 0x20,
+ FALLTHROUGH = 1,
+ BRANCH = 2,
+};
+
+#define STATE_LIST_MARK ((struct bpf_verifier_state_list *) -1L)
+
+static int *insn_stack; /* stack of insns to process */
+static int cur_stack; /* current stack index */
+static int *insn_state;
+
+/* t, w, e - match pseudo-code above:
+ * t - index of current instruction
+ * w - next instruction
+ * e - edge
+ */
+static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
+{
+ if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH))
+ return 0;
+
+ if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH))
+ return 0;
+
+ if (w < 0 || w >= env->prog->len) {
+ verbose(env, "jump out of range from insn %d to %d\n", t, w);
+ return -EINVAL;
+ }
+
+ if (e == BRANCH)
+ /* mark branch target for state pruning */
+ env->explored_states[w] = STATE_LIST_MARK;
+
+ if (insn_state[w] == 0) {
+ /* tree-edge */
+ insn_state[t] = DISCOVERED | e;
+ insn_state[w] = DISCOVERED;
+ if (cur_stack >= env->prog->len)
+ return -E2BIG;
+ insn_stack[cur_stack++] = w;
+ return 1;
+ } else if ((insn_state[w] & 0xF0) == DISCOVERED) {
+ verbose(env, "back-edge from insn %d to %d\n", t, w);
+ return -EINVAL;
+ } else if (insn_state[w] == EXPLORED) {
+ /* forward- or cross-edge */
+ insn_state[t] = DISCOVERED | e;
+ } else {
+ verbose(env, "insn state internal bug\n");
+ return -EFAULT;
+ }
+ return 0;
+}
+
+/* non-recursive depth-first-search to detect loops in BPF program
+ * loop == back-edge in directed graph
+ */
+static int check_cfg(struct bpf_verifier_env *env)
+{
+ struct bpf_insn *insns = env->prog->insnsi;
+ int insn_cnt = env->prog->len;
+ int ret = 0;
+ int i, t;
+
+ ret = check_subprogs(env);
+ if (ret < 0)
+ return ret;
+
+ insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+ if (!insn_state)
+ return -ENOMEM;
+
+ insn_stack = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+ if (!insn_stack) {
+ kfree(insn_state);
+ return -ENOMEM;
+ }
+
+ insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */
+ insn_stack[0] = 0; /* 0 is the first instruction */
+ cur_stack = 1;
+
+peek_stack:
+ if (cur_stack == 0)
+ goto check_state;
+ t = insn_stack[cur_stack - 1];
+
+ if (BPF_CLASS(insns[t].code) == BPF_JMP) {
+ u8 opcode = BPF_OP(insns[t].code);
+
+ if (opcode == BPF_EXIT) {
+ goto mark_explored;
+ } else if (opcode == BPF_CALL) {
+ ret = push_insn(t, t + 1, FALLTHROUGH, env);
+ if (ret == 1)
+ goto peek_stack;
+ else if (ret < 0)
+ goto err_free;
+ if (t + 1 < insn_cnt)
+ env->explored_states[t + 1] = STATE_LIST_MARK;
+ if (insns[t].src_reg == BPF_PSEUDO_CALL) {
+ env->explored_states[t] = STATE_LIST_MARK;
+ ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env);
+ if (ret == 1)
+ goto peek_stack;
+ else if (ret < 0)
+ goto err_free;
+ }
+ } else if (opcode == BPF_JA) {
+ if (BPF_SRC(insns[t].code) != BPF_K) {
+ ret = -EINVAL;
+ goto err_free;
+ }
+ /* unconditional jump with single edge */
+ ret = push_insn(t, t + insns[t].off + 1,
+ FALLTHROUGH, env);
+ if (ret == 1)
+ goto peek_stack;
+ else if (ret < 0)
+ goto err_free;
+ /* tell verifier to check for equivalent states
+ * after every call and jump
+ */
+ if (t + 1 < insn_cnt)
+ env->explored_states[t + 1] = STATE_LIST_MARK;
+ } else {
+ /* conditional jump with two edges */
+ env->explored_states[t] = STATE_LIST_MARK;
+ ret = push_insn(t, t + 1, FALLTHROUGH, env);
+ if (ret == 1)
+ goto peek_stack;
+ else if (ret < 0)
+ goto err_free;
+
+ ret = push_insn(t, t + insns[t].off + 1, BRANCH, env);
+ if (ret == 1)
+ goto peek_stack;
+ else if (ret < 0)
+ goto err_free;
+ }
+ } else {
+ /* all other non-branch instructions with single
+ * fall-through edge
+ */
+ ret = push_insn(t, t + 1, FALLTHROUGH, env);
+ if (ret == 1)
+ goto peek_stack;
+ else if (ret < 0)
+ goto err_free;
+ }
+
+mark_explored:
+ insn_state[t] = EXPLORED;
+ if (cur_stack-- <= 0) {
+ verbose(env, "pop stack internal bug\n");
+ ret = -EFAULT;
+ goto err_free;
+ }
+ goto peek_stack;
+
+check_state:
+ for (i = 0; i < insn_cnt; i++) {
+ if (insn_state[i] != EXPLORED) {
+ verbose(env, "unreachable insn %d\n", i);
+ ret = -EINVAL;
+ goto err_free;
+ }
+ }
+ ret = 0; /* cfg looks good */
+
+err_free:
+ kfree(insn_state);
+ kfree(insn_stack);
+ return ret;
+}
+
+/* check %cur's range satisfies %old's */
+static bool range_within(struct bpf_reg_state *old,
+ struct bpf_reg_state *cur)
+{
+ return old->umin_value <= cur->umin_value &&
+ old->umax_value >= cur->umax_value &&
+ old->smin_value <= cur->smin_value &&
+ old->smax_value >= cur->smax_value;
+}
+
+/* If in the old state two registers had the same id, then they need to have
+ * the same id in the new state as well. But that id could be different from
+ * the old state, so we need to track the mapping from old to new ids.
+ * Once we have seen that, say, a reg with old id 5 had new id 9, any subsequent
+ * regs with old id 5 must also have new id 9 for the new state to be safe. But
+ * regs with a different old id could still have new id 9, we don't care about
+ * that.
+ * So we look through our idmap to see if this old id has been seen before. If
+ * so, we require the new id to match; otherwise, we add the id pair to the map.
+ */
+static bool check_ids(u32 old_id, u32 cur_id, struct bpf_id_pair *idmap)
+{
+ unsigned int i;
+
+ for (i = 0; i < BPF_ID_MAP_SIZE; i++) {
+ if (!idmap[i].old) {
+ /* Reached an empty slot; haven't seen this id before */
+ idmap[i].old = old_id;
+ idmap[i].cur = cur_id;
+ return true;
+ }
+ if (idmap[i].old == old_id)
+ return idmap[i].cur == cur_id;
+ }
+ /* We ran out of idmap slots, which should be impossible */
+ WARN_ON_ONCE(1);
+ return false;
+}
+
+/* Returns true if (rold safe implies rcur safe) */
+static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
+ struct bpf_reg_state *rcur, struct bpf_id_pair *idmap)
+{
+ bool equal;
+
+ if (!(rold->live & REG_LIVE_READ))
+ /* explored state didn't use this */
+ return true;
+
+ equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, parent)) == 0;
+
+ if (rold->type == PTR_TO_STACK)
+ /* two stack pointers are equal only if they're pointing to
+ * the same stack frame, since fp-8 in foo != fp-8 in bar
+ */
+ return equal && rold->frameno == rcur->frameno;
+
+ if (equal)
+ return true;
+
+ if (rold->type == NOT_INIT)
+ /* explored state can't have used this */
+ return true;
+ if (rcur->type == NOT_INIT)
+ return false;
+ switch (rold->type) {
+ case SCALAR_VALUE:
+ if (env->explore_alu_limits)
+ return false;
+ if (rcur->type == SCALAR_VALUE) {
+ /* new val must satisfy old val knowledge */
+ return range_within(rold, rcur) &&
+ tnum_in(rold->var_off, rcur->var_off);
+ } else {
+ /* We're trying to use a pointer in place of a scalar.
+ * Even if the scalar was unbounded, this could lead to
+ * pointer leaks because scalars are allowed to leak
+ * while pointers are not. We could make this safe in
+ * special cases if root is calling us, but it's
+ * probably not worth the hassle.
+ */
+ return false;
+ }
+ case PTR_TO_MAP_VALUE:
+ /* If the new min/max/var_off satisfy the old ones and
+ * everything else matches, we are OK.
+ * We don't care about the 'id' value, because nothing
+ * uses it for PTR_TO_MAP_VALUE (only for ..._OR_NULL)
+ */
+ return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 &&
+ range_within(rold, rcur) &&
+ tnum_in(rold->var_off, rcur->var_off);
+ case PTR_TO_MAP_VALUE_OR_NULL:
+ /* a PTR_TO_MAP_VALUE could be safe to use as a
+ * PTR_TO_MAP_VALUE_OR_NULL into the same map.
+ * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL-
+ * checked, doing so could have affected others with the same
+ * id, and we can't check for that because we lost the id when
+ * we converted to a PTR_TO_MAP_VALUE.
+ */
+ if (rcur->type != PTR_TO_MAP_VALUE_OR_NULL)
+ return false;
+ if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)))
+ return false;
+ /* Check our ids match any regs they're supposed to */
+ return check_ids(rold->id, rcur->id, idmap);
+ case PTR_TO_PACKET_META:
+ case PTR_TO_PACKET:
+ if (rcur->type != rold->type)
+ return false;
+ /* We must have at least as much range as the old ptr
+ * did, so that any accesses which were safe before are
+ * still safe. This is true even if old range < old off,
+ * since someone could have accessed through (ptr - k), or
+ * even done ptr -= k in a register, to get a safe access.
+ */
+ if (rold->range > rcur->range)
+ return false;
+ /* If the offsets don't match, we can't trust our alignment;
+ * nor can we be sure that we won't fall out of range.
+ */
+ if (rold->off != rcur->off)
+ return false;
+ /* id relations must be preserved */
+ if (rold->id && !check_ids(rold->id, rcur->id, idmap))
+ return false;
+ /* new val must satisfy old val knowledge */
+ return range_within(rold, rcur) &&
+ tnum_in(rold->var_off, rcur->var_off);
+ case PTR_TO_CTX:
+ case CONST_PTR_TO_MAP:
+ case PTR_TO_PACKET_END:
+ /* Only valid matches are exact, which memcmp() above
+ * would have accepted
+ */
+ default:
+ /* Don't know what's going on, just say it's not safe */
+ return false;
+ }
+
+ /* Shouldn't get here; if we do, say it's not safe */
+ WARN_ON_ONCE(1);
+ return false;
+}
+
+static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
+ struct bpf_func_state *cur, struct bpf_id_pair *idmap)
+{
+ int i, spi;
+
+ /* if explored stack has more populated slots than current stack
+ * such stacks are not equivalent
+ */
+ if (old->allocated_stack > cur->allocated_stack)
+ return false;
+
+ /* walk slots of the explored stack and ignore any additional
+ * slots in the current stack, since explored(safe) state
+ * didn't use them
+ */
+ for (i = 0; i < old->allocated_stack; i++) {
+ spi = i / BPF_REG_SIZE;
+
+ if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ))
+ /* explored state didn't use this */
+ continue;
+
+ if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID)
+ continue;
+ /* if old state was safe with misc data in the stack
+ * it will be safe with zero-initialized stack.
+ * The opposite is not true
+ */
+ if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_MISC &&
+ cur->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_ZERO)
+ continue;
+ if (old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
+ cur->stack[spi].slot_type[i % BPF_REG_SIZE])
+ /* Ex: old explored (safe) state has STACK_SPILL in
+ * this stack slot, but current has has STACK_MISC ->
+ * this verifier states are not equivalent,
+ * return false to continue verification of this path
+ */
+ return false;
+ if (i % BPF_REG_SIZE)
+ continue;
+ if (old->stack[spi].slot_type[0] != STACK_SPILL)
+ continue;
+ if (!regsafe(env, &old->stack[spi].spilled_ptr,
+ &cur->stack[spi].spilled_ptr, idmap))
+ /* when explored and current stack slot are both storing
+ * spilled registers, check that stored pointers types
+ * are the same as well.
+ * Ex: explored safe path could have stored
+ * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -8}
+ * but current path has stored:
+ * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -16}
+ * such verifier states are not equivalent.
+ * return false to continue verification of this path
+ */
+ return false;
+ }
+ return true;
+}
+
+/* compare two verifier states
+ *
+ * all states stored in state_list are known to be valid, since
+ * verifier reached 'bpf_exit' instruction through them
+ *
+ * this function is called when verifier exploring different branches of
+ * execution popped from the state stack. If it sees an old state that has
+ * more strict register state and more strict stack state then this execution
+ * branch doesn't need to be explored further, since verifier already
+ * concluded that more strict state leads to valid finish.
+ *
+ * Therefore two states are equivalent if register state is more conservative
+ * and explored stack state is more conservative than the current one.
+ * Example:
+ * explored current
+ * (slot1=INV slot2=MISC) == (slot1=MISC slot2=MISC)
+ * (slot1=MISC slot2=MISC) != (slot1=INV slot2=MISC)
+ *
+ * In other words if current stack state (one being explored) has more
+ * valid slots than old one that already passed validation, it means
+ * the verifier can stop exploring and conclude that current state is valid too
+ *
+ * Similarly with registers. If explored state has register type as invalid
+ * whereas register type in current state is meaningful, it means that
+ * the current state will reach 'bpf_exit' instruction safely
+ */
+static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old,
+ struct bpf_func_state *cur)
+{
+ int i;
+
+ memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch));
+ for (i = 0; i < MAX_BPF_REG; i++)
+ if (!regsafe(env, &old->regs[i], &cur->regs[i],
+ env->idmap_scratch))
+ return false;
+
+ if (!stacksafe(env, old, cur, env->idmap_scratch))
+ return false;
+
+ return true;
+}
+
+static bool states_equal(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *old,
+ struct bpf_verifier_state *cur)
+{
+ int i;
+
+ if (old->curframe != cur->curframe)
+ return false;
+
+ /* Verification state from speculative execution simulation
+ * must never prune a non-speculative execution one.
+ */
+ if (old->speculative && !cur->speculative)
+ return false;
+
+ /* for states to be equal callsites have to be the same
+ * and all frame states need to be equivalent
+ */
+ for (i = 0; i <= old->curframe; i++) {
+ if (old->frame[i]->callsite != cur->frame[i]->callsite)
+ return false;
+ if (!func_states_equal(env, old->frame[i], cur->frame[i]))
+ return false;
+ }
+ return true;
+}
+
+/* A write screens off any subsequent reads; but write marks come from the
+ * straight-line code between a state and its parent. When we arrive at an
+ * equivalent state (jump target or such) we didn't arrive by the straight-line
+ * code, so read marks in the state must propagate to the parent regardless
+ * of the state's write marks. That's what 'parent == state->parent' comparison
+ * in mark_reg_read() is for.
+ */
+static int propagate_liveness(struct bpf_verifier_env *env,
+ const struct bpf_verifier_state *vstate,
+ struct bpf_verifier_state *vparent)
+{
+ int i, frame, err = 0;
+ struct bpf_func_state *state, *parent;
+
+ if (vparent->curframe != vstate->curframe) {
+ WARN(1, "propagate_live: parent frame %d current frame %d\n",
+ vparent->curframe, vstate->curframe);
+ return -EFAULT;
+ }
+ /* Propagate read liveness of registers... */
+ BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG);
+ /* We don't need to worry about FP liveness because it's read-only */
+ for (i = 0; i < BPF_REG_FP; i++) {
+ if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ)
+ continue;
+ if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) {
+ err = mark_reg_read(env, &vstate->frame[vstate->curframe]->regs[i],
+ &vparent->frame[vstate->curframe]->regs[i]);
+ if (err)
+ return err;
+ }
+ }
+
+ /* ... and stack slots */
+ for (frame = 0; frame <= vstate->curframe; frame++) {
+ state = vstate->frame[frame];
+ parent = vparent->frame[frame];
+ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE &&
+ i < parent->allocated_stack / BPF_REG_SIZE; i++) {
+ if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ)
+ continue;
+ if (state->stack[i].spilled_ptr.live & REG_LIVE_READ)
+ mark_reg_read(env, &state->stack[i].spilled_ptr,
+ &parent->stack[i].spilled_ptr);
+ }
+ }
+ return err;
+}
+
+static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
+{
+ struct bpf_verifier_state_list *new_sl;
+ struct bpf_verifier_state_list *sl;
+ struct bpf_verifier_state *cur = env->cur_state, *new;
+ int i, j, err, states_cnt = 0;
+
+ sl = env->explored_states[insn_idx];
+ if (!sl)
+ /* this 'insn_idx' instruction wasn't marked, so we will not
+ * be doing state search here
+ */
+ return 0;
+
+ while (sl != STATE_LIST_MARK) {
+ if (states_equal(env, &sl->state, cur)) {
+ /* reached equivalent register/stack state,
+ * prune the search.
+ * Registers read by the continuation are read by us.
+ * If we have any write marks in env->cur_state, they
+ * will prevent corresponding reads in the continuation
+ * from reaching our parent (an explored_state). Our
+ * own state will get the read marks recorded, but
+ * they'll be immediately forgotten as we're pruning
+ * this state and will pop a new one.
+ */
+ err = propagate_liveness(env, &sl->state, cur);
+ if (err)
+ return err;
+ return 1;
+ }
+ sl = sl->next;
+ states_cnt++;
+ }
+
+ if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
+ return 0;
+
+ /* there were no equivalent states, remember current one.
+ * technically the current state is not proven to be safe yet,
+ * but it will either reach outer most bpf_exit (which means it's safe)
+ * or it will be rejected. Since there are no loops, we won't be
+ * seeing this tuple (frame[0].callsite, frame[1].callsite, .. insn_idx)
+ * again on the way to bpf_exit
+ */
+ new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL);
+ if (!new_sl)
+ return -ENOMEM;
+
+ /* add new state to the head of linked list */
+ new = &new_sl->state;
+ err = copy_verifier_state(new, cur);
+ if (err) {
+ free_verifier_state(new, false);
+ kfree(new_sl);
+ return err;
+ }
+ new_sl->next = env->explored_states[insn_idx];
+ env->explored_states[insn_idx] = new_sl;
+ /* connect new state to parentage chain */
+ for (i = 0; i < BPF_REG_FP; i++)
+ cur_regs(env)[i].parent = &new->frame[new->curframe]->regs[i];
+ /* clear write marks in current state: the writes we did are not writes
+ * our child did, so they don't screen off its reads from us.
+ * (There are no read marks in current state, because reads always mark
+ * their parent and current state never has children yet. Only
+ * explored_states can get read marks.)
+ */
+ for (i = 0; i < BPF_REG_FP; i++)
+ cur->frame[cur->curframe]->regs[i].live = REG_LIVE_NONE;
+
+ /* all stack frames are accessible from callee, clear them all */
+ for (j = 0; j <= cur->curframe; j++) {
+ struct bpf_func_state *frame = cur->frame[j];
+ struct bpf_func_state *newframe = new->frame[j];
+
+ for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) {
+ frame->stack[i].spilled_ptr.live = REG_LIVE_NONE;
+ frame->stack[i].spilled_ptr.parent =
+ &newframe->stack[i].spilled_ptr;
+ }
+ }
+ return 0;
+}
+
+static int do_check(struct bpf_verifier_env *env)
+{
+ struct bpf_verifier_state *state;
+ struct bpf_insn *insns = env->prog->insnsi;
+ struct bpf_reg_state *regs;
+ int insn_cnt = env->prog->len, i;
+ int insn_processed = 0;
+ bool do_print_state = false;
+
+ state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
+ if (!state)
+ return -ENOMEM;
+ state->curframe = 0;
+ state->speculative = false;
+ state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
+ if (!state->frame[0]) {
+ kfree(state);
+ return -ENOMEM;
+ }
+ env->cur_state = state;
+ init_func_state(env, state->frame[0],
+ BPF_MAIN_FUNC /* callsite */,
+ 0 /* frameno */,
+ 0 /* subprogno, zero == main subprog */);
+
+ for (;;) {
+ struct bpf_insn *insn;
+ u8 class;
+ int err;
+
+ if (env->insn_idx >= insn_cnt) {
+ verbose(env, "invalid insn idx %d insn_cnt %d\n",
+ env->insn_idx, insn_cnt);
+ return -EFAULT;
+ }
+
+ insn = &insns[env->insn_idx];
+ class = BPF_CLASS(insn->code);
+
+ if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
+ verbose(env,
+ "BPF program is too large. Processed %d insn\n",
+ insn_processed);
+ return -E2BIG;
+ }
+
+ err = is_state_visited(env, env->insn_idx);
+ if (err < 0)
+ return err;
+ if (err == 1) {
+ /* found equivalent state, can prune the search */
+ if (env->log.level) {
+ if (do_print_state)
+ verbose(env, "\nfrom %d to %d%s: safe\n",
+ env->prev_insn_idx, env->insn_idx,
+ env->cur_state->speculative ?
+ " (speculative execution)" : "");
+ else
+ verbose(env, "%d: safe\n", env->insn_idx);
+ }
+ goto process_bpf_exit;
+ }
+
+ if (signal_pending(current))
+ return -EAGAIN;
+
+ if (need_resched())
+ cond_resched();
+
+ if (env->log.level > 1 || (env->log.level && do_print_state)) {
+ if (env->log.level > 1)
+ verbose(env, "%d:", env->insn_idx);
+ else
+ verbose(env, "\nfrom %d to %d%s:",
+ env->prev_insn_idx, env->insn_idx,
+ env->cur_state->speculative ?
+ " (speculative execution)" : "");
+ print_verifier_state(env, state->frame[state->curframe]);
+ do_print_state = false;
+ }
+
+ if (env->log.level) {
+ const struct bpf_insn_cbs cbs = {
+ .cb_print = verbose,
+ .private_data = env,
+ };
+
+ verbose(env, "%d: ", env->insn_idx);
+ print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
+ }
+
+ if (bpf_prog_is_dev_bound(env->prog->aux)) {
+ err = bpf_prog_offload_verify_insn(env, env->insn_idx,
+ env->prev_insn_idx);
+ if (err)
+ return err;
+ }
+
+ regs = cur_regs(env);
+ sanitize_mark_insn_seen(env);
+
+ if (class == BPF_ALU || class == BPF_ALU64) {
+ err = check_alu_op(env, insn);
+ if (err)
+ return err;
+
+ } else if (class == BPF_LDX) {
+ enum bpf_reg_type *prev_src_type, src_reg_type;
+
+ /* check for reserved fields is already done */
+
+ /* check src operand */
+ err = check_reg_arg(env, insn->src_reg, SRC_OP);
+ if (err)
+ return err;
+
+ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
+ if (err)
+ return err;
+
+ src_reg_type = regs[insn->src_reg].type;
+
+ /* check that memory (src_reg + off) is readable,
+ * the state of dst_reg will be updated by this func
+ */
+ err = check_mem_access(env, env->insn_idx, insn->src_reg,
+ insn->off, BPF_SIZE(insn->code),
+ BPF_READ, insn->dst_reg, false);
+ if (err)
+ return err;
+
+ prev_src_type = &env->insn_aux_data[env->insn_idx].ptr_type;
+
+ if (*prev_src_type == NOT_INIT) {
+ /* saw a valid insn
+ * dst_reg = *(u32 *)(src_reg + off)
+ * save type to validate intersecting paths
+ */
+ *prev_src_type = src_reg_type;
+
+ } else if (src_reg_type != *prev_src_type &&
+ (src_reg_type == PTR_TO_CTX ||
+ *prev_src_type == PTR_TO_CTX)) {
+ /* ABuser program is trying to use the same insn
+ * dst_reg = *(u32*) (src_reg + off)
+ * with different pointer types:
+ * src_reg == ctx in one branch and
+ * src_reg == stack|map in some other branch.
+ * Reject it.
+ */
+ verbose(env, "same insn cannot be used with different pointers\n");
+ return -EINVAL;
+ }
+
+ } else if (class == BPF_STX) {
+ enum bpf_reg_type *prev_dst_type, dst_reg_type;
+
+ if (BPF_MODE(insn->code) == BPF_XADD) {
+ err = check_xadd(env, env->insn_idx, insn);
+ if (err)
+ return err;
+ env->insn_idx++;
+ continue;
+ }
+
+ /* check src1 operand */
+ err = check_reg_arg(env, insn->src_reg, SRC_OP);
+ if (err)
+ return err;
+ /* check src2 operand */
+ err = check_reg_arg(env, insn->dst_reg, SRC_OP);
+ if (err)
+ return err;
+
+ dst_reg_type = regs[insn->dst_reg].type;
+
+ /* check that memory (dst_reg + off) is writeable */
+ err = check_mem_access(env, env->insn_idx, insn->dst_reg,
+ insn->off, BPF_SIZE(insn->code),
+ BPF_WRITE, insn->src_reg, false);
+ if (err)
+ return err;
+
+ prev_dst_type = &env->insn_aux_data[env->insn_idx].ptr_type;
+
+ if (*prev_dst_type == NOT_INIT) {
+ *prev_dst_type = dst_reg_type;
+ } else if (dst_reg_type != *prev_dst_type &&
+ (dst_reg_type == PTR_TO_CTX ||
+ *prev_dst_type == PTR_TO_CTX)) {
+ verbose(env, "same insn cannot be used with different pointers\n");
+ return -EINVAL;
+ }
+
+ } else if (class == BPF_ST) {
+ if (BPF_MODE(insn->code) != BPF_MEM ||
+ insn->src_reg != BPF_REG_0) {
+ verbose(env, "BPF_ST uses reserved fields\n");
+ return -EINVAL;
+ }
+ /* check src operand */
+ err = check_reg_arg(env, insn->dst_reg, SRC_OP);
+ if (err)
+ return err;
+
+ if (is_ctx_reg(env, insn->dst_reg)) {
+ verbose(env, "BPF_ST stores into R%d context is not allowed\n",
+ insn->dst_reg);
+ return -EACCES;
+ }
+
+ /* check that memory (dst_reg + off) is writeable */
+ err = check_mem_access(env, env->insn_idx, insn->dst_reg,
+ insn->off, BPF_SIZE(insn->code),
+ BPF_WRITE, -1, false);
+ if (err)
+ return err;
+
+ } else if (class == BPF_JMP) {
+ u8 opcode = BPF_OP(insn->code);
+
+ if (opcode == BPF_CALL) {
+ if (BPF_SRC(insn->code) != BPF_K ||
+ insn->off != 0 ||
+ (insn->src_reg != BPF_REG_0 &&
+ insn->src_reg != BPF_PSEUDO_CALL) ||
+ insn->dst_reg != BPF_REG_0) {
+ verbose(env, "BPF_CALL uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ if (insn->src_reg == BPF_PSEUDO_CALL)
+ err = check_func_call(env, insn, &env->insn_idx);
+ else
+ err = check_helper_call(env, insn->imm, env->insn_idx);
+ if (err)
+ return err;
+
+ } else if (opcode == BPF_JA) {
+ if (BPF_SRC(insn->code) != BPF_K ||
+ insn->imm != 0 ||
+ insn->src_reg != BPF_REG_0 ||
+ insn->dst_reg != BPF_REG_0) {
+ verbose(env, "BPF_JA uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ env->insn_idx += insn->off + 1;
+ continue;
+
+ } else if (opcode == BPF_EXIT) {
+ if (BPF_SRC(insn->code) != BPF_K ||
+ insn->imm != 0 ||
+ insn->src_reg != BPF_REG_0 ||
+ insn->dst_reg != BPF_REG_0) {
+ verbose(env, "BPF_EXIT uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ if (state->curframe) {
+ /* exit from nested function */
+ env->prev_insn_idx = env->insn_idx;
+ err = prepare_func_exit(env, &env->insn_idx);
+ if (err)
+ return err;
+ do_print_state = true;
+ continue;
+ }
+
+ /* eBPF calling convetion is such that R0 is used
+ * to return the value from eBPF program.
+ * Make sure that it's readable at this time
+ * of bpf_exit, which means that program wrote
+ * something into it earlier
+ */
+ err = check_reg_arg(env, BPF_REG_0, SRC_OP);
+ if (err)
+ return err;
+
+ if (is_pointer_value(env, BPF_REG_0)) {
+ verbose(env, "R0 leaks addr as return value\n");
+ return -EACCES;
+ }
+
+ err = check_return_code(env);
+ if (err)
+ return err;
+process_bpf_exit:
+ err = pop_stack(env, &env->prev_insn_idx,
+ &env->insn_idx);
+ if (err < 0) {
+ if (err != -ENOENT)
+ return err;
+ break;
+ } else {
+ do_print_state = true;
+ continue;
+ }
+ } else {
+ err = check_cond_jmp_op(env, insn, &env->insn_idx);
+ if (err)
+ return err;
+ }
+ } else if (class == BPF_LD) {
+ u8 mode = BPF_MODE(insn->code);
+
+ if (mode == BPF_ABS || mode == BPF_IND) {
+ err = check_ld_abs(env, insn);
+ if (err)
+ return err;
+
+ } else if (mode == BPF_IMM) {
+ err = check_ld_imm(env, insn);
+ if (err)
+ return err;
+
+ env->insn_idx++;
+ sanitize_mark_insn_seen(env);
+ } else {
+ verbose(env, "invalid BPF_LD mode\n");
+ return -EINVAL;
+ }
+ } else {
+ verbose(env, "unknown insn class %d\n", class);
+ return -EINVAL;
+ }
+
+ env->insn_idx++;
+ }
+
+ verbose(env, "processed %d insns (limit %d), stack depth ",
+ insn_processed, BPF_COMPLEXITY_LIMIT_INSNS);
+ for (i = 0; i < env->subprog_cnt; i++) {
+ u32 depth = env->subprog_info[i].stack_depth;
+
+ verbose(env, "%d", depth);
+ if (i + 1 < env->subprog_cnt)
+ verbose(env, "+");
+ }
+ verbose(env, "\n");
+ env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
+ return 0;
+}
+
+static int check_map_prealloc(struct bpf_map *map)
+{
+ return (map->map_type != BPF_MAP_TYPE_HASH &&
+ map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&
+ map->map_type != BPF_MAP_TYPE_HASH_OF_MAPS) ||
+ !(map->map_flags & BPF_F_NO_PREALLOC);
+}
+
+static int check_map_prog_compatibility(struct bpf_verifier_env *env,
+ struct bpf_map *map,
+ struct bpf_prog *prog)
+
+{
+ /* Make sure that BPF_PROG_TYPE_PERF_EVENT programs only use
+ * preallocated hash maps, since doing memory allocation
+ * in overflow_handler can crash depending on where nmi got
+ * triggered.
+ */
+ if (prog->type == BPF_PROG_TYPE_PERF_EVENT) {
+ if (!check_map_prealloc(map)) {
+ verbose(env, "perf_event programs can only use preallocated hash map\n");
+ return -EINVAL;
+ }
+ if (map->inner_map_meta &&
+ !check_map_prealloc(map->inner_map_meta)) {
+ verbose(env, "perf_event programs can only use preallocated inner hash map\n");
+ return -EINVAL;
+ }
+ }
+
+ if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
+ !bpf_offload_prog_map_match(prog, map)) {
+ verbose(env, "offload device mismatch between prog and map\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/* look for pseudo eBPF instructions that access map FDs and
+ * replace them with actual map pointers
+ */
+static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
+{
+ struct bpf_insn *insn = env->prog->insnsi;
+ int insn_cnt = env->prog->len;
+ int i, j, err;
+
+ err = bpf_prog_calc_tag(env->prog);
+ if (err)
+ return err;
+
+ for (i = 0; i < insn_cnt; i++, insn++) {
+ if (BPF_CLASS(insn->code) == BPF_LDX &&
+ (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) {
+ verbose(env, "BPF_LDX uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ if (BPF_CLASS(insn->code) == BPF_STX &&
+ ((BPF_MODE(insn->code) != BPF_MEM &&
+ BPF_MODE(insn->code) != BPF_XADD) || insn->imm != 0)) {
+ verbose(env, "BPF_STX uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
+ struct bpf_map *map;
+ struct fd f;
+
+ if (i == insn_cnt - 1 || insn[1].code != 0 ||
+ insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
+ insn[1].off != 0) {
+ verbose(env, "invalid bpf_ld_imm64 insn\n");
+ return -EINVAL;
+ }
+
+ if (insn->src_reg == 0)
+ /* valid generic load 64-bit imm */
+ goto next_insn;
+
+ if (insn->src_reg != BPF_PSEUDO_MAP_FD) {
+ verbose(env,
+ "unrecognized bpf_ld_imm64 insn\n");
+ return -EINVAL;
+ }
+
+ f = fdget(insn->imm);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map)) {
+ verbose(env, "fd %d is not pointing to valid bpf_map\n",
+ insn->imm);
+ return PTR_ERR(map);
+ }
+
+ err = check_map_prog_compatibility(env, map, env->prog);
+ if (err) {
+ fdput(f);
+ return err;
+ }
+
+ /* store map pointer inside BPF_LD_IMM64 instruction */
+ insn[0].imm = (u32) (unsigned long) map;
+ insn[1].imm = ((u64) (unsigned long) map) >> 32;
+
+ /* check whether we recorded this map already */
+ for (j = 0; j < env->used_map_cnt; j++)
+ if (env->used_maps[j] == map) {
+ fdput(f);
+ goto next_insn;
+ }
+
+ if (env->used_map_cnt >= MAX_USED_MAPS) {
+ fdput(f);
+ return -E2BIG;
+ }
+
+ /* hold the map. If the program is rejected by verifier,
+ * the map will be released by release_maps() or it
+ * will be used by the valid program until it's unloaded
+ * and all maps are released in free_used_maps()
+ */
+ map = bpf_map_inc(map, false);
+ if (IS_ERR(map)) {
+ fdput(f);
+ return PTR_ERR(map);
+ }
+ env->used_maps[env->used_map_cnt++] = map;
+
+ if (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE &&
+ bpf_cgroup_storage_assign(env->prog, map)) {
+ verbose(env,
+ "only one cgroup storage is allowed\n");
+ fdput(f);
+ return -EBUSY;
+ }
+
+ fdput(f);
+next_insn:
+ insn++;
+ i++;
+ continue;
+ }
+
+ /* Basic sanity check before we invest more work here. */
+ if (!bpf_opcode_in_insntable(insn->code)) {
+ verbose(env, "unknown opcode %02x\n", insn->code);
+ return -EINVAL;
+ }
+ }
+
+ /* now all pseudo BPF_LD_IMM64 instructions load valid
+ * 'struct bpf_map *' into a register instead of user map_fd.
+ * These pointers will be used later by verifier to validate map access.
+ */
+ return 0;
+}
+
+/* drop refcnt of maps used by the rejected program */
+static void release_maps(struct bpf_verifier_env *env)
+{
+ int i;
+
+ if (env->prog->aux->cgroup_storage)
+ bpf_cgroup_storage_release(env->prog,
+ env->prog->aux->cgroup_storage);
+
+ for (i = 0; i < env->used_map_cnt; i++)
+ bpf_map_put(env->used_maps[i]);
+}
+
+/* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */
+static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env)
+{
+ struct bpf_insn *insn = env->prog->insnsi;
+ int insn_cnt = env->prog->len;
+ int i;
+
+ for (i = 0; i < insn_cnt; i++, insn++)
+ if (insn->code == (BPF_LD | BPF_IMM | BPF_DW))
+ insn->src_reg = 0;
+}
+
+/* single env->prog->insni[off] instruction was replaced with the range
+ * insni[off, off + cnt). Adjust corresponding insn_aux_data by copying
+ * [0, off) and [off, end) to new locations, so the patched range stays zero
+ */
+static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len,
+ u32 off, u32 cnt)
+{
+ struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data;
+ bool old_seen = old_data[off].seen;
+ int i;
+
+ if (cnt == 1)
+ return 0;
+ new_data = vzalloc(array_size(prog_len,
+ sizeof(struct bpf_insn_aux_data)));
+ if (!new_data)
+ return -ENOMEM;
+ memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off);
+ memcpy(new_data + off + cnt - 1, old_data + off,
+ sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
+ for (i = off; i < off + cnt - 1; i++) {
+ /* Expand insni[off]'s seen count to the patched range. */
+ new_data[i].seen = old_seen;
+ }
+ env->insn_aux_data = new_data;
+ vfree(old_data);
+ return 0;
+}
+
+static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len)
+{
+ int i;
+
+ if (len == 1)
+ return;
+ /* NOTE: fake 'exit' subprog should be updated as well. */
+ for (i = 0; i <= env->subprog_cnt; i++) {
+ if (env->subprog_info[i].start <= off)
+ continue;
+ env->subprog_info[i].start += len - 1;
+ }
+}
+
+static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
+ const struct bpf_insn *patch, u32 len)
+{
+ struct bpf_prog *new_prog;
+
+ new_prog = bpf_patch_insn_single(env->prog, off, patch, len);
+ if (!new_prog)
+ return NULL;
+ if (adjust_insn_aux_data(env, new_prog->len, off, len))
+ return NULL;
+ adjust_subprog_starts(env, off, len);
+ return new_prog;
+}
+
+/* The verifier does more data flow analysis than llvm and will not
+ * explore branches that are dead at run time. Malicious programs can
+ * have dead code too. Therefore replace all dead at-run-time code
+ * with 'ja -1'.
+ *
+ * Just nops are not optimal, e.g. if they would sit at the end of the
+ * program and through another bug we would manage to jump there, then
+ * we'd execute beyond program memory otherwise. Returning exception
+ * code also wouldn't work since we can have subprogs where the dead
+ * code could be located.
+ */
+static void sanitize_dead_code(struct bpf_verifier_env *env)
+{
+ struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+ struct bpf_insn trap = BPF_JMP_IMM(BPF_JA, 0, 0, -1);
+ struct bpf_insn *insn = env->prog->insnsi;
+ const int insn_cnt = env->prog->len;
+ int i;
+
+ for (i = 0; i < insn_cnt; i++) {
+ if (aux_data[i].seen)
+ continue;
+ memcpy(insn + i, &trap, sizeof(trap));
+ }
+}
+
+/* convert load instructions that access fields of 'struct __sk_buff'
+ * into sequence of instructions that access fields of 'struct sk_buff'
+ */
+static int convert_ctx_accesses(struct bpf_verifier_env *env)
+{
+ const struct bpf_verifier_ops *ops = env->ops;
+ int i, cnt, size, ctx_field_size, delta = 0;
+ const int insn_cnt = env->prog->len;
+ struct bpf_insn insn_buf[16], *insn;
+ u32 target_size, size_default, off;
+ struct bpf_prog *new_prog;
+ enum bpf_access_type type;
+ bool is_narrower_load;
+
+ if (ops->gen_prologue) {
+ cnt = ops->gen_prologue(insn_buf, env->seen_direct_write,
+ env->prog);
+ if (cnt >= ARRAY_SIZE(insn_buf)) {
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EINVAL;
+ } else if (cnt) {
+ new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ env->prog = new_prog;
+ delta += cnt - 1;
+ }
+ }
+
+ if (!ops->convert_ctx_access || bpf_prog_is_dev_bound(env->prog->aux))
+ return 0;
+
+ insn = env->prog->insnsi + delta;
+
+ for (i = 0; i < insn_cnt; i++, insn++) {
+ bool ctx_access;
+
+ if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
+ insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
+ insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
+ insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) {
+ type = BPF_READ;
+ ctx_access = true;
+ } else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
+ insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
+ insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
+ insn->code == (BPF_STX | BPF_MEM | BPF_DW) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_B) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_H) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_W) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_DW)) {
+ type = BPF_WRITE;
+ ctx_access = BPF_CLASS(insn->code) == BPF_STX;
+ } else {
+ continue;
+ }
+
+ if (type == BPF_WRITE &&
+ env->insn_aux_data[i + delta].sanitize_stack_spill) {
+ struct bpf_insn patch[] = {
+ *insn,
+ BPF_ST_NOSPEC(),
+ };
+
+ cnt = ARRAY_SIZE(patch);
+ new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
+ if (!ctx_access)
+ continue;
+
+ if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
+ continue;
+
+ ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size;
+ size = BPF_LDST_BYTES(insn);
+
+ /* If the read access is a narrower load of the field,
+ * convert to a 4/8-byte load, to minimum program type specific
+ * convert_ctx_access changes. If conversion is successful,
+ * we will apply proper mask to the result.
+ */
+ is_narrower_load = size < ctx_field_size;
+ size_default = bpf_ctx_off_adjust_machine(ctx_field_size);
+ off = insn->off;
+ if (is_narrower_load) {
+ u8 size_code;
+
+ if (type == BPF_WRITE) {
+ verbose(env, "bpf verifier narrow ctx access misconfigured\n");
+ return -EINVAL;
+ }
+
+ size_code = BPF_H;
+ if (ctx_field_size == 4)
+ size_code = BPF_W;
+ else if (ctx_field_size == 8)
+ size_code = BPF_DW;
+
+ insn->off = off & ~(size_default - 1);
+ insn->code = BPF_LDX | BPF_MEM | size_code;
+ }
+
+ target_size = 0;
+ cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog,
+ &target_size);
+ if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) ||
+ (ctx_field_size && !target_size)) {
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EINVAL;
+ }
+
+ if (is_narrower_load && size < target_size) {
+ u8 shift = (off & (size_default - 1)) * 8;
+
+ if (ctx_field_size <= 4) {
+ if (shift)
+ insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH,
+ insn->dst_reg,
+ shift);
+ insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg,
+ (1 << size * 8) - 1);
+ } else {
+ if (shift)
+ insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH,
+ insn->dst_reg,
+ shift);
+ insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg,
+ (1ULL << size * 8) - 1);
+ }
+ }
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+
+ /* keep walking new program and skip insns we just inserted */
+ env->prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ }
+
+ return 0;
+}
+
+static int jit_subprogs(struct bpf_verifier_env *env)
+{
+ struct bpf_prog *prog = env->prog, **func, *tmp;
+ int i, j, subprog_start, subprog_end = 0, len, subprog;
+ struct bpf_insn *insn;
+ void *old_bpf_func;
+ int err = -ENOMEM;
+
+ if (env->subprog_cnt <= 1)
+ return 0;
+
+ for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
+ if (insn->code != (BPF_JMP | BPF_CALL) ||
+ insn->src_reg != BPF_PSEUDO_CALL)
+ continue;
+ /* Upon error here we cannot fall back to interpreter but
+ * need a hard reject of the program. Thus -EFAULT is
+ * propagated in any case.
+ */
+ subprog = find_subprog(env, i + insn->imm + 1);
+ if (subprog < 0) {
+ WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
+ i + insn->imm + 1);
+ return -EFAULT;
+ }
+ /* temporarily remember subprog id inside insn instead of
+ * aux_data, since next loop will split up all insns into funcs
+ */
+ insn->off = subprog;
+ /* remember original imm in case JIT fails and fallback
+ * to interpreter will be needed
+ */
+ env->insn_aux_data[i].call_imm = insn->imm;
+ /* point imm to __bpf_call_base+1 from JITs point of view */
+ insn->imm = 1;
+ }
+
+ func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL);
+ if (!func)
+ goto out_undo_insn;
+
+ for (i = 0; i < env->subprog_cnt; i++) {
+ subprog_start = subprog_end;
+ subprog_end = env->subprog_info[i + 1].start;
+
+ len = subprog_end - subprog_start;
+ func[i] = bpf_prog_alloc(bpf_prog_size(len), GFP_USER);
+ if (!func[i])
+ goto out_free;
+ memcpy(func[i]->insnsi, &prog->insnsi[subprog_start],
+ len * sizeof(struct bpf_insn));
+ func[i]->type = prog->type;
+ func[i]->len = len;
+ if (bpf_prog_calc_tag(func[i]))
+ goto out_free;
+ func[i]->is_func = 1;
+ /* Use bpf_prog_F_tag to indicate functions in stack traces.
+ * Long term would need debug info to populate names
+ */
+ func[i]->aux->name[0] = 'F';
+ func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
+ func[i]->jit_requested = 1;
+ func[i] = bpf_int_jit_compile(func[i]);
+ if (!func[i]->jited) {
+ err = -ENOTSUPP;
+ goto out_free;
+ }
+ cond_resched();
+ }
+ /* at this point all bpf functions were successfully JITed
+ * now populate all bpf_calls with correct addresses and
+ * run last pass of JIT
+ */
+ for (i = 0; i < env->subprog_cnt; i++) {
+ insn = func[i]->insnsi;
+ for (j = 0; j < func[i]->len; j++, insn++) {
+ if (insn->code != (BPF_JMP | BPF_CALL) ||
+ insn->src_reg != BPF_PSEUDO_CALL)
+ continue;
+ subprog = insn->off;
+ insn->imm = (u64 (*)(u64, u64, u64, u64, u64))
+ func[subprog]->bpf_func -
+ __bpf_call_base;
+ }
+
+ /* we use the aux data to keep a list of the start addresses
+ * of the JITed images for each function in the program
+ *
+ * for some architectures, such as powerpc64, the imm field
+ * might not be large enough to hold the offset of the start
+ * address of the callee's JITed image from __bpf_call_base
+ *
+ * in such cases, we can lookup the start address of a callee
+ * by using its subprog id, available from the off field of
+ * the call instruction, as an index for this list
+ */
+ func[i]->aux->func = func;
+ func[i]->aux->func_cnt = env->subprog_cnt;
+ }
+ for (i = 0; i < env->subprog_cnt; i++) {
+ old_bpf_func = func[i]->bpf_func;
+ tmp = bpf_int_jit_compile(func[i]);
+ if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
+ verbose(env, "JIT doesn't support bpf-to-bpf calls\n");
+ err = -ENOTSUPP;
+ goto out_free;
+ }
+ cond_resched();
+ }
+
+ /* finally lock prog and jit images for all functions and
+ * populate kallsysm
+ */
+ for (i = 0; i < env->subprog_cnt; i++) {
+ bpf_prog_lock_ro(func[i]);
+ bpf_prog_kallsyms_add(func[i]);
+ }
+
+ /* Last step: make now unused interpreter insns from main
+ * prog consistent for later dump requests, so they can
+ * later look the same as if they were interpreted only.
+ */
+ for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
+ if (insn->code != (BPF_JMP | BPF_CALL) ||
+ insn->src_reg != BPF_PSEUDO_CALL)
+ continue;
+ insn->off = env->insn_aux_data[i].call_imm;
+ subprog = find_subprog(env, i + insn->off + 1);
+ insn->imm = subprog;
+ }
+
+ prog->jited = 1;
+ prog->bpf_func = func[0]->bpf_func;
+ prog->aux->func = func;
+ prog->aux->func_cnt = env->subprog_cnt;
+ return 0;
+out_free:
+ for (i = 0; i < env->subprog_cnt; i++)
+ if (func[i])
+ bpf_jit_free(func[i]);
+ kfree(func);
+out_undo_insn:
+ /* cleanup main prog to be interpreted */
+ prog->jit_requested = 0;
+ for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
+ if (insn->code != (BPF_JMP | BPF_CALL) ||
+ insn->src_reg != BPF_PSEUDO_CALL)
+ continue;
+ insn->off = 0;
+ insn->imm = env->insn_aux_data[i].call_imm;
+ }
+ return err;
+}
+
+static int fixup_call_args(struct bpf_verifier_env *env)
+{
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+ struct bpf_prog *prog = env->prog;
+ struct bpf_insn *insn = prog->insnsi;
+ int i, depth;
+#endif
+ int err;
+
+ err = 0;
+ if (env->prog->jit_requested) {
+ err = jit_subprogs(env);
+ if (err == 0)
+ return 0;
+ if (err == -EFAULT)
+ return err;
+ }
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+ for (i = 0; i < prog->len; i++, insn++) {
+ if (insn->code != (BPF_JMP | BPF_CALL) ||
+ insn->src_reg != BPF_PSEUDO_CALL)
+ continue;
+ depth = get_callee_stack_depth(env, insn, i);
+ if (depth < 0)
+ return depth;
+ bpf_patch_call_args(insn, depth);
+ }
+ err = 0;
+#endif
+ return err;
+}
+
+/* fixup insn->imm field of bpf_call instructions
+ * and inline eligible helpers as explicit sequence of BPF instructions
+ *
+ * this function is called after eBPF program passed verification
+ */
+static int fixup_bpf_calls(struct bpf_verifier_env *env)
+{
+ struct bpf_prog *prog = env->prog;
+ struct bpf_insn *insn = prog->insnsi;
+ const struct bpf_func_proto *fn;
+ const int insn_cnt = prog->len;
+ const struct bpf_map_ops *ops;
+ struct bpf_insn_aux_data *aux;
+ struct bpf_insn insn_buf[16];
+ struct bpf_prog *new_prog;
+ struct bpf_map *map_ptr;
+ int i, cnt, delta = 0;
+
+ for (i = 0; i < insn_cnt; i++, insn++) {
+ if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) ||
+ insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) ||
+ insn->code == (BPF_ALU | BPF_MOD | BPF_X) ||
+ insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
+ bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
+ struct bpf_insn mask_and_div[] = {
+ BPF_MOV_REG(BPF_CLASS(insn->code), BPF_REG_AX, insn->src_reg),
+ /* [R,W]x div 0 -> 0 */
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, 2),
+ BPF_RAW_REG(*insn, insn->dst_reg, BPF_REG_AX),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_ALU_REG(BPF_CLASS(insn->code), BPF_XOR, insn->dst_reg, insn->dst_reg),
+ };
+ struct bpf_insn mask_and_mod[] = {
+ BPF_MOV_REG(BPF_CLASS(insn->code), BPF_REG_AX, insn->src_reg),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, 1 + (is64 ? 0 : 1)),
+ BPF_RAW_REG(*insn, insn->dst_reg, BPF_REG_AX),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_MOV32_REG(insn->dst_reg, insn->dst_reg),
+ };
+ struct bpf_insn *patchlet;
+
+ if (insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) ||
+ insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
+ patchlet = mask_and_div;
+ cnt = ARRAY_SIZE(mask_and_div);
+ } else {
+ patchlet = mask_and_mod;
+ cnt = ARRAY_SIZE(mask_and_mod) - (is64 ? 2 : 0);
+ }
+
+ new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
+ if (BPF_CLASS(insn->code) == BPF_LD &&
+ (BPF_MODE(insn->code) == BPF_ABS ||
+ BPF_MODE(insn->code) == BPF_IND)) {
+ cnt = env->ops->gen_ld_abs(insn, insn_buf);
+ if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EINVAL;
+ }
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
+ if (insn->code == (BPF_ALU64 | BPF_ADD | BPF_X) ||
+ insn->code == (BPF_ALU64 | BPF_SUB | BPF_X)) {
+ const u8 code_add = BPF_ALU64 | BPF_ADD | BPF_X;
+ const u8 code_sub = BPF_ALU64 | BPF_SUB | BPF_X;
+ struct bpf_insn insn_buf[16];
+ struct bpf_insn *patch = &insn_buf[0];
+ bool issrc, isneg, isimm;
+ u32 off_reg;
+
+ aux = &env->insn_aux_data[i + delta];
+ if (!aux->alu_state ||
+ aux->alu_state == BPF_ALU_NON_POINTER)
+ continue;
+
+ isneg = aux->alu_state & BPF_ALU_NEG_VALUE;
+ issrc = (aux->alu_state & BPF_ALU_SANITIZE) ==
+ BPF_ALU_SANITIZE_SRC;
+ isimm = aux->alu_state & BPF_ALU_IMMEDIATE;
+
+ off_reg = issrc ? insn->src_reg : insn->dst_reg;
+ if (isimm) {
+ *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit);
+ } else {
+ if (isneg)
+ *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
+ *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit);
+ *patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg);
+ *patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg);
+ *patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0);
+ *patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63);
+ *patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX, off_reg);
+ }
+ if (!issrc)
+ *patch++ = BPF_MOV64_REG(insn->dst_reg, insn->src_reg);
+ insn->src_reg = BPF_REG_AX;
+ if (isneg)
+ insn->code = insn->code == code_add ?
+ code_sub : code_add;
+ *patch++ = *insn;
+ if (issrc && isneg && !isimm)
+ *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
+ cnt = patch - insn_buf;
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
+ if (insn->code != (BPF_JMP | BPF_CALL))
+ continue;
+ if (insn->src_reg == BPF_PSEUDO_CALL)
+ continue;
+
+ if (insn->imm == BPF_FUNC_get_route_realm)
+ prog->dst_needed = 1;
+ if (insn->imm == BPF_FUNC_get_prandom_u32)
+ bpf_user_rnd_init_once();
+ if (insn->imm == BPF_FUNC_override_return)
+ prog->kprobe_override = 1;
+ if (insn->imm == BPF_FUNC_tail_call) {
+ /* If we tail call into other programs, we
+ * cannot make any assumptions since they can
+ * be replaced dynamically during runtime in
+ * the program array.
+ */
+ prog->cb_access = 1;
+ env->prog->aux->stack_depth = MAX_BPF_STACK;
+
+ /* mark bpf_tail_call as different opcode to avoid
+ * conditional branch in the interpeter for every normal
+ * call and to prevent accidental JITing by JIT compiler
+ * that doesn't support bpf_tail_call yet
+ */
+ insn->imm = 0;
+ insn->code = BPF_JMP | BPF_TAIL_CALL;
+
+ aux = &env->insn_aux_data[i + delta];
+ if (!bpf_map_ptr_unpriv(aux))
+ continue;
+
+ /* instead of changing every JIT dealing with tail_call
+ * emit two extra insns:
+ * if (index >= max_entries) goto out;
+ * index &= array->index_mask;
+ * to avoid out-of-bounds cpu speculation
+ */
+ if (bpf_map_ptr_poisoned(aux)) {
+ verbose(env, "tail_call abusing map_ptr\n");
+ return -EINVAL;
+ }
+
+ map_ptr = BPF_MAP_PTR(aux->map_state);
+ insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3,
+ map_ptr->max_entries, 2);
+ insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3,
+ container_of(map_ptr,
+ struct bpf_array,
+ map)->index_mask);
+ insn_buf[2] = *insn;
+ cnt = 3;
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
+ /* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup
+ * and other inlining handlers are currently limited to 64 bit
+ * only.
+ */
+ if (prog->jit_requested && BITS_PER_LONG == 64 &&
+ (insn->imm == BPF_FUNC_map_lookup_elem ||
+ insn->imm == BPF_FUNC_map_update_elem ||
+ insn->imm == BPF_FUNC_map_delete_elem)) {
+ aux = &env->insn_aux_data[i + delta];
+ if (bpf_map_ptr_poisoned(aux))
+ goto patch_call_imm;
+
+ map_ptr = BPF_MAP_PTR(aux->map_state);
+ ops = map_ptr->ops;
+ if (insn->imm == BPF_FUNC_map_lookup_elem &&
+ ops->map_gen_lookup) {
+ cnt = ops->map_gen_lookup(map_ptr, insn_buf);
+ if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EINVAL;
+ }
+
+ new_prog = bpf_patch_insn_data(env, i + delta,
+ insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
+ BUILD_BUG_ON(!__same_type(ops->map_lookup_elem,
+ (void *(*)(struct bpf_map *map, void *key))NULL));
+ BUILD_BUG_ON(!__same_type(ops->map_delete_elem,
+ (int (*)(struct bpf_map *map, void *key))NULL));
+ BUILD_BUG_ON(!__same_type(ops->map_update_elem,
+ (int (*)(struct bpf_map *map, void *key, void *value,
+ u64 flags))NULL));
+ switch (insn->imm) {
+ case BPF_FUNC_map_lookup_elem:
+ insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) -
+ __bpf_call_base;
+ continue;
+ case BPF_FUNC_map_update_elem:
+ insn->imm = BPF_CAST_CALL(ops->map_update_elem) -
+ __bpf_call_base;
+ continue;
+ case BPF_FUNC_map_delete_elem:
+ insn->imm = BPF_CAST_CALL(ops->map_delete_elem) -
+ __bpf_call_base;
+ continue;
+ }
+
+ goto patch_call_imm;
+ }
+
+patch_call_imm:
+ fn = env->ops->get_func_proto(insn->imm, env->prog);
+ /* all functions that have prototype and verifier allowed
+ * programs to call them, must be real in-kernel functions
+ */
+ if (!fn->func) {
+ verbose(env,
+ "kernel subsystem misconfigured func %s#%d\n",
+ func_id_name(insn->imm), insn->imm);
+ return -EFAULT;
+ }
+ insn->imm = fn->func - __bpf_call_base;
+ }
+
+ return 0;
+}
+
+static void free_states(struct bpf_verifier_env *env)
+{
+ struct bpf_verifier_state_list *sl, *sln;
+ int i;
+
+ if (!env->explored_states)
+ return;
+
+ for (i = 0; i < env->prog->len; i++) {
+ sl = env->explored_states[i];
+
+ if (sl)
+ while (sl != STATE_LIST_MARK) {
+ sln = sl->next;
+ free_verifier_state(&sl->state, false);
+ kfree(sl);
+ sl = sln;
+ }
+ }
+
+ kfree(env->explored_states);
+}
+
+int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
+{
+ struct bpf_verifier_env *env;
+ struct bpf_verifier_log *log;
+ int ret = -EINVAL;
+
+ /* no program is valid */
+ if (ARRAY_SIZE(bpf_verifier_ops) == 0)
+ return -EINVAL;
+
+ /* 'struct bpf_verifier_env' can be global, but since it's not small,
+ * allocate/free it every time bpf_check() is called
+ */
+ env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL);
+ if (!env)
+ return -ENOMEM;
+ log = &env->log;
+
+ env->insn_aux_data =
+ vzalloc(array_size(sizeof(struct bpf_insn_aux_data),
+ (*prog)->len));
+ ret = -ENOMEM;
+ if (!env->insn_aux_data)
+ goto err_free_env;
+ env->prog = *prog;
+ env->ops = bpf_verifier_ops[env->prog->type];
+
+ /* grab the mutex to protect few globals used by verifier */
+ mutex_lock(&bpf_verifier_lock);
+
+ if (attr->log_level || attr->log_buf || attr->log_size) {
+ /* user requested verbose verifier output
+ * and supplied buffer to store the verification trace
+ */
+ log->level = attr->log_level;
+ log->ubuf = (char __user *) (unsigned long) attr->log_buf;
+ log->len_total = attr->log_size;
+
+ ret = -EINVAL;
+ /* log attributes have to be sane */
+ if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
+ !log->level || !log->ubuf)
+ goto err_unlock;
+ }
+
+ env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
+ if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
+ env->strict_alignment = true;
+
+ if (attr->prog_flags & BPF_F_ANY_ALIGNMENT)
+ env->strict_alignment = false;
+
+ ret = replace_map_fd_with_map_ptr(env);
+ if (ret < 0)
+ goto skip_full_check;
+
+ if (bpf_prog_is_dev_bound(env->prog->aux)) {
+ ret = bpf_prog_offload_verifier_prep(env);
+ if (ret)
+ goto skip_full_check;
+ }
+
+ env->explored_states = kcalloc(env->prog->len,
+ sizeof(struct bpf_verifier_state_list *),
+ GFP_USER);
+ ret = -ENOMEM;
+ if (!env->explored_states)
+ goto skip_full_check;
+
+ env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);
+
+ ret = check_cfg(env);
+ if (ret < 0)
+ goto skip_full_check;
+
+ ret = do_check(env);
+ if (env->cur_state) {
+ free_verifier_state(env->cur_state, true);
+ env->cur_state = NULL;
+ }
+
+skip_full_check:
+ while (!pop_stack(env, NULL, NULL));
+ free_states(env);
+
+ if (ret == 0)
+ sanitize_dead_code(env);
+
+ if (ret == 0)
+ ret = check_max_stack_depth(env);
+
+ if (ret == 0)
+ /* program is valid, convert *(u32*)(ctx + off) accesses */
+ ret = convert_ctx_accesses(env);
+
+ if (ret == 0)
+ ret = fixup_bpf_calls(env);
+
+ if (ret == 0)
+ ret = fixup_call_args(env);
+
+ if (log->level && bpf_verifier_log_full(log))
+ ret = -ENOSPC;
+ if (log->level && !log->ubuf) {
+ ret = -EFAULT;
+ goto err_release_maps;
+ }
+
+ if (ret == 0 && env->used_map_cnt) {
+ /* if program passed verifier, update used_maps in bpf_prog_info */
+ env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt,
+ sizeof(env->used_maps[0]),
+ GFP_KERNEL);
+
+ if (!env->prog->aux->used_maps) {
+ ret = -ENOMEM;
+ goto err_release_maps;
+ }
+
+ memcpy(env->prog->aux->used_maps, env->used_maps,
+ sizeof(env->used_maps[0]) * env->used_map_cnt);
+ env->prog->aux->used_map_cnt = env->used_map_cnt;
+
+ /* program is valid. Convert pseudo bpf_ld_imm64 into generic
+ * bpf_ld_imm64 instructions
+ */
+ convert_pseudo_ld_imm64(env);
+ }
+
+err_release_maps:
+ if (!env->prog->aux->used_maps)
+ /* if we didn't copy map pointers into bpf_prog_info, release
+ * them now. Otherwise free_used_maps() will release them.
+ */
+ release_maps(env);
+ *prog = env->prog;
+err_unlock:
+ mutex_unlock(&bpf_verifier_lock);
+ vfree(env->insn_aux_data);
+err_free_env:
+ kfree(env);
+ return ret;
+}
diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c
new file mode 100644
index 000000000..47147c9e1
--- /dev/null
+++ b/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,
+};