From: Brian Vazquez <brianvv@google.com>
To: Brian Vazquez <brianvv.kernel@gmail.com>,
Brian Vazquez <brianvv@google.com>,
Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
"David S . Miller" <davem@davemloft.net>
Cc: Yonghong Song <yhs@fb.com>, Stanislav Fomichev <sdf@google.com>,
Petar Penkov <ppenkov@google.com>,
Willem de Bruijn <willemb@google.com>,
linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
bpf@vger.kernel.org, John Fastabend <john.fastabend@gmail.com>
Subject: [PATCH v3 bpf-next 01/11] bpf: add bpf_map_{value_size,update_value,map_copy_value} functions
Date: Wed, 11 Dec 2019 14:33:34 -0800 [thread overview]
Message-ID: <20191211223344.165549-2-brianvv@google.com> (raw)
In-Reply-To: <20191211223344.165549-1-brianvv@google.com>
This commit moves reusable code from map_lookup_elem and map_update_elem
to avoid code duplication in kernel/bpf/syscall.c.
Signed-off-by: Brian Vazquez <brianvv@google.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
---
kernel/bpf/syscall.c | 275 ++++++++++++++++++++++++-------------------
1 file changed, 151 insertions(+), 124 deletions(-)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 66b90eaf99fe8..2530266fa6477 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -129,6 +129,153 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
return map;
}
+static u32 bpf_map_value_size(struct bpf_map *map)
+{
+ 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 ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
+ return round_up(map->value_size, 8) * num_possible_cpus();
+ else if (IS_FD_MAP(map))
+ return sizeof(u32);
+ else
+ return map->value_size;
+}
+
+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();
+}
+
+static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key,
+ void *value, __u64 flags)
+{
+ int err;
+ /* Need to create a kthread, thus must support schedule */
+ if (bpf_map_is_dev_bound(map)) {
+ return bpf_map_offload_update_elem(map, key, value, flags);
+ } else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
+ map->map_type == BPF_MAP_TYPE_SOCKHASH ||
+ map->map_type == BPF_MAP_TYPE_SOCKMAP) {
+ return map->ops->map_update_elem(map, key, value, flags);
+ }
+
+ /* 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, flags);
+ } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
+ err = bpf_percpu_array_update(map, key, value, flags);
+ } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
+ err = bpf_percpu_cgroup_storage_update(map, key, value,
+ flags);
+ } else if (IS_FD_ARRAY(map)) {
+ rcu_read_lock();
+ err = bpf_fd_array_map_update_elem(map, f.file, key, value,
+ 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,
+ 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,
+ flags);
+ } else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
+ map->map_type == BPF_MAP_TYPE_STACK) {
+ err = map->ops->map_push_elem(map, value, flags);
+ } else {
+ rcu_read_lock();
+ err = map->ops->map_update_elem(map, key, value, flags);
+ rcu_read_unlock();
+ }
+ __this_cpu_dec(bpf_prog_active);
+ preempt_enable();
+ maybe_wait_bpf_programs(map);
+
+ return err;
+}
+
+static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
+ __u64 flags, bool do_delete)
+{
+ void *ptr;
+ int err;
+
+
+ if (bpf_map_is_dev_bound(map)) {
+ err = bpf_map_offload_lookup_elem(map, key, value);
+
+ if (!err && do_delete)
+ err = bpf_map_offload_delete_elem(map, key);
+
+ return err;
+ }
+
+ 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_PERCPU_CGROUP_STORAGE) {
+ err = bpf_percpu_cgroup_storage_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 if (map->map_type == BPF_MAP_TYPE_QUEUE ||
+ map->map_type == BPF_MAP_TYPE_STACK) {
+ err = map->ops->map_peek_elem(map, 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 (IS_ERR(ptr)) {
+ err = PTR_ERR(ptr);
+ } else if (!ptr) {
+ err = -ENOENT;
+ } else {
+ err = 0;
+ if (flags & BPF_F_LOCK)
+ /* lock 'ptr' and copy everything but lock */
+ copy_map_value_locked(map, value, ptr, true);
+ else
+ copy_map_value(map, value, ptr);
+ /* mask lock, since value wasn't zero inited */
+ check_and_init_map_lock(map, value);
+ }
+ rcu_read_unlock();
+ }
+ if (do_delete)
+ err = err ? err : map->ops->map_delete_elem(map, key);
+
+ this_cpu_dec(bpf_prog_active);
+ preempt_enable();
+ maybe_wait_bpf_programs(map);
+
+ return err;
+}
+
static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
{
/* We really just want to fail instead of triggering OOM killer
@@ -816,7 +963,7 @@ static int map_lookup_elem(union bpf_attr *attr)
void __user *uvalue = u64_to_user_ptr(attr->value);
int ufd = attr->map_fd;
struct bpf_map *map;
- void *key, *value, *ptr;
+ void *key, *value;
u32 value_size;
struct fd f;
int err;
@@ -848,72 +995,14 @@ static int map_lookup_elem(union bpf_attr *attr)
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 ||
- map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
- 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;
+ value_size = bpf_map_value_size(map);
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_PERCPU_CGROUP_STORAGE) {
- err = bpf_percpu_cgroup_storage_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) || IS_FD_PROG_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 if (map->map_type == BPF_MAP_TYPE_QUEUE ||
- map->map_type == BPF_MAP_TYPE_STACK) {
- err = map->ops->map_peek_elem(map, 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 (IS_ERR(ptr)) {
- err = PTR_ERR(ptr);
- } else if (!ptr) {
- err = -ENOENT;
- } else {
- err = 0;
- if (attr->flags & BPF_F_LOCK)
- /* lock 'ptr' and copy everything but lock */
- copy_map_value_locked(map, value, ptr, true);
- else
- copy_map_value(map, value, ptr);
- /* mask lock, since value wasn't zero inited */
- check_and_init_map_lock(map, value);
- }
- rcu_read_unlock();
- }
- this_cpu_dec(bpf_prog_active);
- preempt_enable();
-
-done:
+ err = bpf_map_copy_value(map, key, value, attr->flags, false);
if (err)
goto free_value;
@@ -932,16 +1021,6 @@ static int map_lookup_elem(union bpf_attr *attr)
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
@@ -997,60 +1076,8 @@ static int map_update_elem(union bpf_attr *attr)
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;
- } else if (IS_FD_PROG_ARRAY(map)) {
- err = bpf_fd_array_map_update_elem(map, f.file, key, value,
- attr->flags);
- goto out;
- }
+ err = bpf_map_update_value(map, f, key, value, attr->flags);
- /* 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 (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
- err = bpf_percpu_cgroup_storage_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 if (map->map_type == BPF_MAP_TYPE_QUEUE ||
- map->map_type == BPF_MAP_TYPE_STACK) {
- err = map->ops->map_push_elem(map, 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:
--
2.24.1.735.g03f4e72817-goog
next prev parent reply other threads:[~2019-12-11 22:34 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-12-11 22:33 [PATCH v3 bpf-next 00/11] add bpf batch ops to process more than 1 elem Brian Vazquez
2019-12-11 22:33 ` Brian Vazquez [this message]
2019-12-13 17:05 ` [PATCH v3 bpf-next 01/11] bpf: add bpf_map_{value_size,update_value,map_copy_value} functions Yonghong Song
2019-12-11 22:33 ` [PATCH v3 bpf-next 02/11] bpf: add generic support for lookup and lookup_and_delete batch ops Brian Vazquez
2019-12-13 17:26 ` Yonghong Song
2020-01-07 6:50 ` Brian Vazquez
2020-01-07 18:06 ` Yonghong Song
2019-12-11 22:33 ` [PATCH v3 bpf-next 03/11] bpf: add generic support for update and delete " Brian Vazquez
2019-12-13 17:38 ` Yonghong Song
2019-12-11 22:33 ` [PATCH v3 bpf-next 04/11] bpf: add lookup and updated batch ops to arraymap Brian Vazquez
2019-12-13 17:39 ` Yonghong Song
2019-12-11 22:33 ` [PATCH v3 bpf-next 05/11] bpf: add generic_batch_ops to lpm_trie map Brian Vazquez
2019-12-13 17:46 ` Yonghong Song
2020-01-07 6:39 ` Brian Vazquez
2020-01-07 17:57 ` Yonghong Song
2019-12-11 22:33 ` [PATCH v3 bpf-next 06/11] bpf: add batch ops to all htab bpf map Brian Vazquez
2019-12-13 18:14 ` Yonghong Song
2019-12-13 18:58 ` Yonghong Song
2020-01-07 7:02 ` Brian Vazquez
2020-01-07 18:18 ` Yonghong Song
2020-01-08 0:32 ` Brian Vazquez
2019-12-11 22:33 ` [PATCH v3 bpf-next 07/11] tools/bpf: sync uapi header bpf.h Brian Vazquez
2019-12-11 22:33 ` [PATCH v3 bpf-next 08/11] libbpf: add libbpf support to batch ops Brian Vazquez
2019-12-19 0:54 ` Andrii Nakryiko
2020-01-07 6:51 ` Brian Vazquez
2019-12-11 22:33 ` [PATCH v3 bpf-next 09/11] selftests/bpf: add batch ops testing for htab and htab_percpu map Brian Vazquez
2019-12-13 18:34 ` Yonghong Song
2019-12-13 18:40 ` Yonghong Song
2019-12-11 22:33 ` [PATCH v3 bpf-next 10/11] selftests/bpf: add batch ops testing to array bpf map Brian Vazquez
2019-12-11 22:33 ` [PATCH v3 bpf-next 11/11] selftests/bpf: add batch ops testing to lpm_trie " Brian Vazquez
2019-12-13 5:16 ` [PATCH v3 bpf-next 00/11] add bpf batch ops to process more than 1 elem Alexei Starovoitov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20191211223344.165549-2-brianvv@google.com \
--to=brianvv@google.com \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=brianvv.kernel@gmail.com \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=john.fastabend@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=ppenkov@google.com \
--cc=sdf@google.com \
--cc=willemb@google.com \
--cc=yhs@fb.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).