devtx is a lightweight set of hooks before and after packet transmission.
The hooks are 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).
Signed-off-by: Stanislav Fomichev <sdf@xxxxxxxxxx>
---
MAINTAINERS | 2 ++
include/net/devtx.h | 66 +++++++++++++++++++++++++++++++++++++
kernel/bpf/offload.c | 15 +++++++++
net/core/Makefile | 1 +
net/core/dev.c | 1 +
net/core/devtx.c | 78 ++++++++++++++++++++++++++++++++++++++++++++
6 files changed, 163 insertions(+)
create mode 100644 include/net/devtx.h
create mode 100644 net/core/devtx.c
diff --git a/MAINTAINERS b/MAINTAINERS
index acbe54087d1c..de6a2430d49a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -23063,11 +23063,13 @@ L: bpf@xxxxxxxxxxxxxxx
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..88127ca87b9a
--- /dev/null
+++ b/include/net/devtx.h
@@ -0,0 +1,66 @@
+/* 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_ctx {
+ struct net_device *netdev;
+ struct skb_shared_info *sinfo; /* for frags */
+};
+
+#define DECLARE_DEVTX_HOOKS(PREFIX) \
+void PREFIX ## _devtx_submit_skb(struct devtx_ctx *ctx, struct sk_buff *skb); \
+void PREFIX ## _devtx_complete_skb(struct devtx_ctx *ctx, struct sk_buff *skb); \
+void PREFIX ## _devtx_submit_xdp(struct devtx_ctx *ctx, struct xdp_frame *xdpf); \
+void PREFIX ## _devtx_complete_xdp(struct devtx_ctx *ctx, struct xdp_frame *xdpf)
+
+#define DEFINE_DEVTX_HOOKS(PREFIX) \
+__weak noinline void PREFIX ## _devtx_submit_skb(struct devtx_ctx *ctx, \
+ struct sk_buff *skb) {} \
+__weak noinline void PREFIX ## _devtx_complete_skb(struct devtx_ctx *ctx, \
+ struct sk_buff *skb) {} \
+__weak noinline void PREFIX ## _devtx_submit_xdp(struct devtx_ctx *ctx, \
+ struct xdp_frame *xdpf) {} \
+__weak noinline void PREFIX ## _devtx_complete_xdp(struct devtx_ctx *ctx, \
+ struct xdp_frame *xdpf) {} \
+\
+BTF_SET8_START(PREFIX ## _devtx_hook_ids) \
+BTF_ID_FLAGS(func, PREFIX ## _devtx_submit_skb) \
+BTF_ID_FLAGS(func, PREFIX ## _devtx_complete_skb) \
+BTF_ID_FLAGS(func, PREFIX ## _devtx_submit_xdp) \
+BTF_ID_FLAGS(func, PREFIX ## _devtx_complete_xdp) \
+BTF_SET8_END(PREFIX ## _devtx_hook_ids)
+
+#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);
+
+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 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 cec63c76dce5..a4423803b3dd 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 731db2eaa610..97b4d6703a77 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 69a3e544676c..b9500a722591 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..6ae1aecce2c5
--- /dev/null
+++ b/net/core/devtx.c
@@ -0,0 +1,78 @@
+// 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;
+}
+EXPORT_SYMBOL_GPL(devtx_hooks_register);
+
+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);
+}
+EXPORT_SYMBOL_GPL(devtx_hooks_unregister);
--
2.41.0.255.g8b1d071c50-goog
