[RFC,bpf-next,v2,04/11] bpf: Implement devtx hook points

Commit Message

Stanislav Fomichev June 21, 2023, 5:02 p.m. UTC

devtx is a lightweight set of hooks before and after packet transmission.
The hook is supposed to work for both skb and xdp paths by exposing
a light-weight packet wrapper via devtx_frame (header portion + frags).

devtx is implemented as a tracing program which has access to the
XDP-metadata-like kfuncs. The initial set of kfuncs is implemented
in the next patch, but the idea is similar to XDP metadata:
the kfuncs have netdev-specific implementation, but common
interface. Upon loading, the kfuncs are resolved to direct
calls against per-netdev implementation. This can be achieved
by marking devtx-tracing programs as dev-bound (largely
reusing xdp-dev-bound program infrastructure).

Cc: [e-mail]
Signed-off-by: Stanislav Fomichev <[e-mail]>
---
 MAINTAINERS          |  2 ++
 include/net/devtx.h  | 71 +++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/offload.c | 15 +++++++++
 net/core/Makefile    |  1 +
 net/core/dev.c       |  1 +
 net/core/devtx.c     | 76 ++++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 166 insertions(+)
 create mode 100644 include/net/devtx.h
 create mode 100644 net/core/devtx.c

Patch

diff --git a/MAINTAINERS b/MAINTAINERS
index c904dba1733b..516529b42e66 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22976,11 +22976,13 @@  L:	[e-mail]
 S:	Supported
 F:	drivers/net/ethernet/*/*/*/*/*xdp*
 F:	drivers/net/ethernet/*/*/*xdp*
+F:	include/net/devtx.h
 F:	include/net/xdp.h
 F:	include/net/xdp_priv.h
 F:	include/trace/events/xdp.h
 F:	kernel/bpf/cpumap.c
 F:	kernel/bpf/devmap.c
+F:	net/core/devtx.c
 F:	net/core/xdp.c
 F:	samples/bpf/xdp*
 F:	tools/testing/selftests/bpf/*/*xdp*
diff --git a/include/net/devtx.h b/include/net/devtx.h
new file mode 100644
index 000000000000..d1c75fd9b377
--- /dev/null
+++ b/include/net/devtx.h
@@ -0,0 +1,71 @@ 
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __LINUX_NET_DEVTX_H__
+#define __LINUX_NET_DEVTX_H__
+
+#include <linux/jump_label.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/btf_ids.h>
+#include <net/xdp.h>
+
+struct devtx_frame {
+	void *data;
+	u16 len;
+	u8 meta_len;
+	struct skb_shared_info *sinfo; /* for frags */
+	struct net_device *netdev;
+};
+
+#ifdef CONFIG_NET
+void devtx_hooks_enable(void);
+void devtx_hooks_disable(void);
+bool devtx_hooks_match(u32 attach_btf_id, const struct xdp_metadata_ops *xmo);
+int devtx_hooks_register(struct btf_id_set8 *set, const struct xdp_metadata_ops *xmo);
+void devtx_hooks_unregister(struct btf_id_set8 *set);
+
+static inline void devtx_frame_from_skb(struct devtx_frame *ctx, struct sk_buff *skb,
+					struct net_device *netdev)
+{
+	ctx->data = skb->data;
+	ctx->len = skb_headlen(skb);
+	ctx->meta_len = skb_metadata_len(skb);
+	ctx->sinfo = skb_shinfo(skb);
+	ctx->netdev = netdev;
+}
+
+static inline void devtx_frame_from_xdp(struct devtx_frame *ctx, struct xdp_frame *xdpf,
+					struct net_device *netdev)
+{
+	ctx->data = xdpf->data;
+	ctx->len = xdpf->len;
+	ctx->meta_len = xdpf->metasize & 0xff;
+	ctx->sinfo = xdp_frame_has_frags(xdpf) ? xdp_get_shared_info_from_frame(xdpf) : NULL;
+	ctx->netdev = netdev;
+}
+
+DECLARE_STATIC_KEY_FALSE(devtx_enabled_key);
+
+static inline bool devtx_enabled(void)
+{
+	return static_branch_unlikely(&devtx_enabled_key);
+}
+#else
+static inline void devtx_hooks_enable(void) {}
+static inline void devtx_hooks_disable(void) {}
+static inline bool devtx_hooks_match(u32 attach_btf_id, const struct xdp_metadata_ops *xmo) {}
+static inline int devtx_hooks_register(struct btf_id_set8 *set,
+				       const struct xdp_metadata_ops *xmo) {}
+static inline void devtx_hooks_unregister(struct btf_id_set8 *set) {}
+
+static inline void devtx_frame_from_skb(struct devtx_frame *ctx, struct sk_buff *skb,
+					struct net_device *netdev) {}
+static inline void devtx_frame_from_xdp(struct devtx_frame *ctx, struct xdp_frame *xdpf,
+					struct net_device *netdev) {}
+
+static inline bool devtx_enabled(void)
+{
+	return false;
+}
+#endif
+
+#endif /* __LINUX_NET_DEVTX_H__ */
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 235d81f7e0ed..f01a1aa0f627 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -25,6 +25,7 @@ 
 #include <linux/rhashtable.h>
 #include <linux/rtnetlink.h>
 #include <linux/rwsem.h>
+#include <net/devtx.h>
 
 /* Protects offdevs, members of bpf_offload_netdev and offload members
  * of all progs.
@@ -228,6 +229,7 @@  int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr)
 	int err;
 
 	if (attr->prog_type != BPF_PROG_TYPE_SCHED_CLS &&
+	    attr->prog_type != BPF_PROG_TYPE_TRACING &&
 	    attr->prog_type != BPF_PROG_TYPE_XDP)
 		return -EINVAL;
 
@@ -242,6 +244,15 @@  int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr)
 	if (!netdev)
 		return -EINVAL;
 
+	/* Make sure device-bound tracing programs are being attached
+	 * to the appropriate netdev.
+	 */
+	if (attr->prog_type == BPF_PROG_TYPE_TRACING &&
+	    !devtx_hooks_match(prog->aux->attach_btf_id, netdev->xdp_metadata_ops)) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	err = bpf_dev_offload_check(netdev);
 	if (err)
 		goto out;
@@ -252,6 +263,9 @@  int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr)
 	err = __bpf_prog_dev_bound_init(prog, netdev);
 	up_write(&bpf_devs_lock);
 
+	if (!err)
+		devtx_hooks_enable();
+
 out:
 	dev_put(netdev);
 	return err;
@@ -384,6 +398,7 @@  void bpf_prog_dev_bound_destroy(struct bpf_prog *prog)
 		ondev = bpf_offload_find_netdev(netdev);
 		if (!ondev->offdev && list_empty(&ondev->progs))
 			__bpf_offload_dev_netdev_unregister(NULL, netdev);
+		devtx_hooks_disable();
 	}
 	up_write(&bpf_devs_lock);
 	rtnl_unlock();
diff --git a/net/core/Makefile b/net/core/Makefile
index 8f367813bc68..c1db05ccfac7 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -39,4 +39,5 @@  obj-$(CONFIG_FAILOVER) += failover.o
 obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o
 obj-$(CONFIG_BPF_SYSCALL) += sock_map.o
 obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o
+obj-$(CONFIG_BPF_SYSCALL) += devtx.o
 obj-$(CONFIG_OF)	+= of_net.o
diff --git a/net/core/dev.c b/net/core/dev.c
index 3393c2f3dbe8..e2f4618ee1c5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -150,6 +150,7 @@ 
 #include <linux/pm_runtime.h>
 #include <linux/prandom.h>
 #include <linux/once_lite.h>
+#include <net/devtx.h>
 
 #include "dev.h"
 #include "net-sysfs.h"
diff --git a/net/core/devtx.c b/net/core/devtx.c
new file mode 100644
index 000000000000..bad694439ae3
--- /dev/null
+++ b/net/core/devtx.c
@@ -0,0 +1,76 @@ 
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <net/devtx.h>
+#include <linux/filter.h>
+
+DEFINE_STATIC_KEY_FALSE(devtx_enabled_key);
+EXPORT_SYMBOL_GPL(devtx_enabled_key);
+
+struct devtx_hook_entry {
+	struct list_head devtx_hooks;
+	struct btf_id_set8 *set;
+	const struct xdp_metadata_ops *xmo;
+};
+
+static LIST_HEAD(devtx_hooks);
+static DEFINE_MUTEX(devtx_hooks_lock);
+
+void devtx_hooks_enable(void)
+{
+	static_branch_inc(&devtx_enabled_key);
+}
+
+void devtx_hooks_disable(void)
+{
+	static_branch_dec(&devtx_enabled_key);
+}
+
+bool devtx_hooks_match(u32 attach_btf_id, const struct xdp_metadata_ops *xmo)
+{
+	struct devtx_hook_entry *entry, *tmp;
+	bool match = false;
+
+	mutex_lock(&devtx_hooks_lock);
+	list_for_each_entry_safe(entry, tmp, &devtx_hooks, devtx_hooks) {
+		if (btf_id_set8_contains(entry->set, attach_btf_id)) {
+			match = entry->xmo == xmo;
+			break;
+		}
+	}
+	mutex_unlock(&devtx_hooks_lock);
+
+	return match;
+}
+
+int devtx_hooks_register(struct btf_id_set8 *set, const struct xdp_metadata_ops *xmo)
+{
+	struct devtx_hook_entry *entry;
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->set = set;
+	entry->xmo = xmo;
+
+	mutex_lock(&devtx_hooks_lock);
+	list_add(&entry->devtx_hooks, &devtx_hooks);
+	mutex_unlock(&devtx_hooks_lock);
+
+	return 0;
+}
+
+void devtx_hooks_unregister(struct btf_id_set8 *set)
+{
+	struct devtx_hook_entry *entry, *tmp;
+
+	mutex_lock(&devtx_hooks_lock);
+	list_for_each_entry_safe(entry, tmp, &devtx_hooks, devtx_hooks) {
+		if (entry->set == set) {
+			list_del(&entry->devtx_hooks);
+			kfree(entry);
+			break;
+		}
+	}
+	mutex_unlock(&devtx_hooks_lock);
+}