linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
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
Subject: [PATCH v3 bpf-next 03/11] bpf: add generic support for update and delete batch ops
Date: Wed, 11 Dec 2019 14:33:36 -0800	[thread overview]
Message-ID: <20191211223344.165549-4-brianvv@google.com> (raw)
In-Reply-To: <20191211223344.165549-1-brianvv@google.com>

This commit adds generic support for update and delete batch ops that
can be used for almost all the bpf maps. These commands share the same
UAPI attr that lookup and lookup_and_delete batch ops use and the
syscall commands are:

  BPF_MAP_UPDATE_BATCH
  BPF_MAP_DELETE_BATCH

The main difference between update/delete and lookup/lookup_and_delete
batch ops is that for update/delete keys/values must be specified for
userspace and because of that, neither in_batch nor out_batch are used.

Suggested-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Brian Vazquez <brianvv@google.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
---
 include/linux/bpf.h      |  10 ++++
 include/uapi/linux/bpf.h |   2 +
 kernel/bpf/syscall.c     | 117 ++++++++++++++++++++++++++++++++++++++-
 3 files changed, 128 insertions(+), 1 deletion(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a16f209255a59..851fb3ff084b0 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -48,6 +48,10 @@ struct bpf_map_ops {
 	int (*map_lookup_and_delete_batch)(struct bpf_map *map,
 					   const union bpf_attr *attr,
 					   union bpf_attr __user *uattr);
+	int (*map_update_batch)(struct bpf_map *map, const union bpf_attr *attr,
+				union bpf_attr __user *uattr);
+	int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr,
+				union bpf_attr __user *uattr);
 
 	/* funcs callable from userspace and from eBPF programs */
 	void *(*map_lookup_elem)(struct bpf_map *map, void *key);
@@ -849,6 +853,12 @@ int  generic_map_lookup_batch(struct bpf_map *map,
 int  generic_map_lookup_and_delete_batch(struct bpf_map *map,
 					 const union bpf_attr *attr,
 					 union bpf_attr __user *uattr);
+int  generic_map_update_batch(struct bpf_map *map,
+			      const union bpf_attr *attr,
+			      union bpf_attr __user *uattr);
+int  generic_map_delete_batch(struct bpf_map *map,
+			      const union bpf_attr *attr,
+			      union bpf_attr __user *uattr);
 
 extern int sysctl_unprivileged_bpf_disabled;
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 36d3b885ddedd..dab24a763e4bb 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -109,6 +109,8 @@ enum bpf_cmd {
 	BPF_BTF_GET_NEXT_ID,
 	BPF_MAP_LOOKUP_BATCH,
 	BPF_MAP_LOOKUP_AND_DELETE_BATCH,
+	BPF_MAP_UPDATE_BATCH,
+	BPF_MAP_DELETE_BATCH,
 };
 
 enum bpf_map_type {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 708aa89fe2308..8272e76183068 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1206,6 +1206,111 @@ static int map_get_next_key(union bpf_attr *attr)
 	return err;
 }
 
+int generic_map_delete_batch(struct bpf_map *map,
+			     const union bpf_attr *attr,
+			     union bpf_attr __user *uattr)
+{
+	void __user *keys = u64_to_user_ptr(attr->batch.keys);
+	u32 cp, max_count;
+	int err = 0;
+	void *key;
+
+	if (attr->batch.elem_flags & ~BPF_F_LOCK)
+		return -EINVAL;
+
+	if ((attr->batch.elem_flags & BPF_F_LOCK) &&
+	    !map_value_has_spin_lock(map)) {
+		return -EINVAL;
+	}
+
+	max_count = attr->batch.count;
+	if (!max_count)
+		return -EINVAL;
+
+	for (cp = 0; cp < max_count; cp++) {
+		key = __bpf_copy_key(keys + cp * map->key_size, map->key_size);
+		if (IS_ERR(key)) {
+			err = PTR_ERR(key);
+			break;
+		}
+
+		if (bpf_map_is_dev_bound(map)) {
+			err = bpf_map_offload_delete_elem(map, key);
+			break;
+		}
+
+		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);
+		if (err)
+			break;
+	}
+	if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp)))
+		err = -EFAULT;
+	return err;
+}
+
+int generic_map_update_batch(struct bpf_map *map,
+			     const union bpf_attr *attr,
+			     union bpf_attr __user *uattr)
+{
+	void __user *values = u64_to_user_ptr(attr->batch.values);
+	void __user *keys = u64_to_user_ptr(attr->batch.keys);
+	u32 value_size, cp, max_count;
+	int ufd = attr->map_fd;
+	void *key, *value;
+	struct fd f;
+	int err = 0;
+
+	f = fdget(ufd);
+	if (attr->batch.elem_flags & ~BPF_F_LOCK)
+		return -EINVAL;
+
+	if ((attr->batch.elem_flags & BPF_F_LOCK) &&
+	    !map_value_has_spin_lock(map)) {
+		return -EINVAL;
+	}
+
+	value_size = bpf_map_value_size(map);
+
+	max_count = attr->batch.count;
+	if (!max_count)
+		return 0;
+
+	value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
+	if (!value)
+		return -ENOMEM;
+
+	for (cp = 0; cp < max_count; cp++) {
+		key = __bpf_copy_key(keys + cp * map->key_size, map->key_size);
+		if (IS_ERR(key)) {
+			err = PTR_ERR(key);
+			break;
+		}
+		err = -EFAULT;
+		if (copy_from_user(value, values + cp * value_size, value_size))
+			break;
+
+		err = bpf_map_update_value(map, f, key, value,
+					   attr->batch.elem_flags);
+
+		if (err)
+			break;
+	}
+
+	if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp)))
+		err = -EFAULT;
+
+	kfree(value);
+	kfree(key);
+	return err;
+}
+
 #define MAP_LOOKUP_RETRIES 3
 
 static int __generic_map_lookup_batch(struct bpf_map *map,
@@ -3203,8 +3308,12 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 
 	if (cmd == BPF_MAP_LOOKUP_BATCH)
 		BPF_DO_BATCH(map->ops->map_lookup_batch);
-	else
+	else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH)
 		BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch);
+	else if (cmd == BPF_MAP_UPDATE_BATCH)
+		BPF_DO_BATCH(map->ops->map_update_batch);
+	else
+		BPF_DO_BATCH(map->ops->map_delete_batch);
 
 err_put:
 	fdput(f);
@@ -3315,6 +3424,12 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 		err = bpf_map_do_batch(&attr, uattr,
 				       BPF_MAP_LOOKUP_AND_DELETE_BATCH);
 		break;
+	case BPF_MAP_UPDATE_BATCH:
+		err = bpf_map_do_batch(&attr, uattr, BPF_MAP_UPDATE_BATCH);
+		break;
+	case BPF_MAP_DELETE_BATCH:
+		err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH);
+		break;
 	default:
 		err = -EINVAL;
 		break;
-- 
2.24.1.735.g03f4e72817-goog


  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 ` [PATCH v3 bpf-next 01/11] bpf: add bpf_map_{value_size,update_value,map_copy_value} functions Brian Vazquez
2019-12-13 17:05   ` 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 ` Brian Vazquez [this message]
2019-12-13 17:38   ` [PATCH v3 bpf-next 03/11] bpf: add generic support for update and delete " 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=20191211223344.165549-4-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=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).