Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 03cc59e..22066a6 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* 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>
@@ -23,7 +15,7 @@
#define HTAB_CREATE_FLAG_MASK \
(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \
- BPF_F_RDONLY | BPF_F_WRONLY)
+ BPF_F_ACCESS_MASK | BPF_F_ZERO_SEED)
struct bucket {
struct hlist_nulls_head head;
@@ -244,6 +236,7 @@
*/
bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
+ bool zero_seed = (attr->map_flags & BPF_F_ZERO_SEED);
int numa_node = bpf_map_attr_numa_node(attr);
BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
@@ -257,8 +250,12 @@
*/
return -EPERM;
- if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK)
- /* reserved bits should not be used */
+ if (zero_seed && !capable(CAP_SYS_ADMIN))
+ /* Guard against local DoS, and discourage production use. */
+ return -EPERM;
+
+ if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK ||
+ !bpf_map_flags_access_ok(attr->map_flags))
return -EINVAL;
if (!lru && percpu_lru)
@@ -355,14 +352,8 @@
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 map size is larger than memlock limit, reject it */
+ err = bpf_map_charge_init(&htab->map.memory, cost);
if (err)
goto free_htab;
@@ -371,9 +362,13 @@
sizeof(struct bucket),
htab->map.numa_node);
if (!htab->buckets)
- goto free_htab;
+ goto free_charge;
- htab->hashrnd = get_random_int();
+ if (htab->map.map_flags & BPF_F_ZERO_SEED)
+ htab->hashrnd = 0;
+ else
+ 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);
@@ -400,6 +395,8 @@
prealloc_destroy(htab);
free_buckets:
bpf_map_area_free(htab->buckets);
+free_charge:
+ bpf_map_charge_finish(&htab->map.memory);
free_htab:
kfree(htab);
return ERR_PTR(err);
@@ -518,18 +515,30 @@
return insn - insn_buf;
}
-static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key)
+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) {
- bpf_lru_node_set_ref(&l->lru_node);
+ 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)
{
@@ -677,7 +686,7 @@
}
if (htab_is_prealloc(htab)) {
- pcpu_freelist_push(&htab->freelist, &l->fnode);
+ __pcpu_freelist_push(&htab->freelist, &l->fnode);
} else {
atomic_dec(&htab->count);
l->htab = htab;
@@ -709,21 +718,12 @@
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);
+ u32 size = htab->map.value_size;
bool prealloc = htab_is_prealloc(htab);
struct htab_elem *l_new, **pl_new;
void __percpu *pptr;
@@ -739,7 +739,7 @@
} else {
struct pcpu_freelist_node *l;
- l = pcpu_freelist_pop(&htab->freelist);
+ l = __pcpu_freelist_pop(&htab->freelist);
if (!l)
return ERR_PTR(-E2BIG);
l_new = container_of(l, struct htab_elem, fnode);
@@ -761,10 +761,13 @@
l_new = ERR_PTR(-ENOMEM);
goto dec_count;
}
+ check_and_init_map_lock(&htab->map,
+ l_new->key + round_up(key_size, 8));
}
memcpy(l_new->key, key, key_size);
if (percpu) {
+ size = round_up(size, 8);
if (prealloc) {
pptr = htab_elem_get_ptr(l_new, key_size);
} else {
@@ -782,8 +785,13 @@
if (!prealloc)
htab_elem_set_ptr(l_new, key_size, pptr);
- } else {
+ } else if (fd_htab_map_needs_adjust(htab)) {
+ size = round_up(size, 8);
memcpy(l_new->key + round_up(key_size, 8), value, size);
+ } else {
+ copy_map_value(&htab->map,
+ l_new->key + round_up(key_size, 8),
+ value);
}
l_new->hash = hash;
@@ -796,11 +804,11 @@
static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
u64 map_flags)
{
- if (l_old && map_flags == BPF_NOEXIST)
+ if (l_old && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST)
/* elem already exists */
return -EEXIST;
- if (!l_old && map_flags == BPF_EXIST)
+ if (!l_old && (map_flags & ~BPF_F_LOCK) == BPF_EXIST)
/* elem doesn't exist, cannot update it */
return -ENOENT;
@@ -819,7 +827,7 @@
u32 key_size, hash;
int ret;
- if (unlikely(map_flags > BPF_EXIST))
+ if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST))
/* unknown flags */
return -EINVAL;
@@ -832,6 +840,28 @@
b = __select_bucket(htab, hash);
head = &b->head;
+ if (unlikely(map_flags & BPF_F_LOCK)) {
+ if (unlikely(!map_value_has_spin_lock(map)))
+ return -EINVAL;
+ /* find an element without taking the bucket lock */
+ l_old = lookup_nulls_elem_raw(head, hash, key, key_size,
+ htab->n_buckets);
+ ret = check_flags(htab, l_old, map_flags);
+ if (ret)
+ return ret;
+ if (l_old) {
+ /* grab the element lock and update value in place */
+ copy_map_value_locked(map,
+ l_old->key + round_up(key_size, 8),
+ value, false);
+ return 0;
+ }
+ /* fall through, grab the bucket lock and lookup again.
+ * 99.9% chance that the element won't be found,
+ * but second lookup under lock has to be done.
+ */
+ }
+
/* bpf_map_update_elem() can be called in_irq() */
raw_spin_lock_irqsave(&b->lock, flags);
@@ -841,6 +871,20 @@
if (ret)
goto err;
+ if (unlikely(l_old && (map_flags & BPF_F_LOCK))) {
+ /* first lookup without the bucket lock didn't find the element,
+ * but second lookup with the bucket lock found it.
+ * This case is highly unlikely, but has to be dealt with:
+ * grab the element lock in addition to the bucket lock
+ * and update element in place
+ */
+ copy_map_value_locked(map,
+ l_old->key + round_up(key_size, 8),
+ value, false);
+ ret = 0;
+ goto err;
+ }
+
l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false,
l_old);
if (IS_ERR(l_new)) {
@@ -1206,6 +1250,7 @@
.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,
@@ -1237,7 +1282,6 @@
int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
{
- struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
struct htab_elem *l;
void __percpu *pptr;
int ret = -ENOENT;
@@ -1253,8 +1297,9 @@
l = __htab_map_lookup_elem(map, key);
if (!l)
goto out;
- if (htab_is_lru(htab))
- bpf_lru_node_set_ref(&l->lru_node);
+ /* 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,
@@ -1285,6 +1330,35 @@
return ret;
}
+static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key,
+ struct seq_file *m)
+{
+ struct htab_elem *l;
+ void __percpu *pptr;
+ int cpu;
+
+ rcu_read_lock();
+
+ l = __htab_map_lookup_elem(map, key);
+ if (!l) {
+ rcu_read_unlock();
+ return;
+ }
+
+ btf_type_seq_show(map->btf, map->btf_key_type_id, key, m);
+ seq_puts(m, ": {\n");
+ pptr = htab_elem_get_ptr(l, map->key_size);
+ for_each_possible_cpu(cpu) {
+ seq_printf(m, "\tcpu%d: ", cpu);
+ btf_type_seq_show(map->btf, map->btf_value_type_id,
+ per_cpu_ptr(pptr, cpu), m);
+ seq_puts(m, "\n");
+ }
+ seq_puts(m, "}\n");
+
+ rcu_read_unlock();
+}
+
const struct bpf_map_ops htab_percpu_map_ops = {
.map_alloc_check = htab_map_alloc_check,
.map_alloc = htab_map_alloc,
@@ -1293,6 +1367,7 @@
.map_lookup_elem = htab_percpu_map_lookup_elem,
.map_update_elem = htab_percpu_map_update_elem,
.map_delete_elem = htab_map_delete_elem,
+ .map_seq_show_elem = htab_percpu_map_seq_show_elem,
};
const struct bpf_map_ops htab_lru_percpu_map_ops = {
@@ -1303,6 +1378,7 @@
.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,
+ .map_seq_show_elem = htab_percpu_map_seq_show_elem,
};
static int fd_htab_map_alloc_check(union bpf_attr *attr)