[PATCH net-next 12/22] dst: Metadata destinations
Introduces a new dst_metadata which enables to carry per packet metadata
between forwarding and processing elements via the skb-dst pointer.
The structure is set up to be a union. Thus, each separate type of
metadata requires its own dst instance. If demand arises to carry
multiple types of metadata concurrently, metadata dst entries can be
made stackable.
The metadata dst entry is refcnt'ed as expected for now but a non
reference counted use is possible if the reference is forced before
queueing the skb.
In order to allow allocating dsts with variable length, the existing
dst_alloc() is split into a dst_alloc() and dst_init() function. The
existing dst_init() function to initialize the subsystem is being
renamed to dst_subsys_init() to make it clear what is what.
The check before ip_route_input() is changed to ignore metadata dsts
and drop the dst inside the routing function thus allowing to interpret
metadata in a later commit.
Signed-off-by: Thomas Graf tg...@suug.ch
---
include/net/dst.h | 6 +++-
include/net/dst_metadata.h | 32 ++
net/core/dev.c | 2 +-
net/core/dst.c | 84 ++
net/ipv4/ip_input.c| 3 +-
net/ipv4/route.c | 2 ++
6 files changed, 112 insertions(+), 17 deletions(-)
create mode 100644 include/net/dst_metadata.h
diff --git a/include/net/dst.h b/include/net/dst.h
index 2bc73f8a..2578811 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -57,6 +57,7 @@ struct dst_entry {
#define DST_FAKE_RTABLE0x0040
#define DST_XFRM_TUNNEL0x0080
#define DST_XFRM_QUEUE 0x0100
+#define DST_METADATA 0x0200
unsigned short pending_confirm;
@@ -356,6 +357,9 @@ static inline int dst_discard(struct sk_buff *skb)
}
void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref,
int initial_obsolete, unsigned short flags);
+void dst_init(struct dst_entry *dst, struct dst_ops *ops,
+ struct net_device *dev, int initial_ref, int initial_obsolete,
+ unsigned short flags);
void __dst_free(struct dst_entry *dst);
struct dst_entry *dst_destroy(struct dst_entry *dst);
@@ -457,7 +461,7 @@ static inline struct dst_entry *dst_check(struct dst_entry
*dst, u32 cookie)
return dst;
}
-void dst_init(void);
+void dst_subsys_init(void);
/* Flags for xfrm_lookup flags argument. */
enum {
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
new file mode 100644
index 000..4f7694f
--- /dev/null
+++ b/include/net/dst_metadata.h
@@ -0,0 +1,32 @@
+#ifndef __NET_DST_METADATA_H
+#define __NET_DST_METADATA_H 1
+
+#include linux/skbuff.h
+#include net/ip_tunnels.h
+#include net/dst.h
+
+struct metadata_dst {
+ struct dst_entrydst;
+ size_t opts_len;
+};
+
+static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb)
+{
+ struct metadata_dst *md_dst = (struct metadata_dst *) skb_dst(skb);
+
+ if (md_dst md_dst-dst.flags DST_METADATA)
+ return md_dst;
+
+ return NULL;
+}
+
+static inline bool skb_valid_dst(const struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+
+ return dst !(dst-flags DST_METADATA);
+}
+
+struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags);
+
+#endif /* __NET_DST_METADATA_H */
diff --git a/net/core/dev.c b/net/core/dev.c
index 2ee15af..cb52cba 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7669,7 +7669,7 @@ static int __init net_dev_init(void)
open_softirq(NET_RX_SOFTIRQ, net_rx_action);
hotcpu_notifier(dev_cpu_callback, 0);
- dst_init();
+ dst_subsys_init();
rc = 0;
out:
return rc;
diff --git a/net/core/dst.c b/net/core/dst.c
index e956ce6..917364f 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -22,6 +22,7 @@
#include linux/prefetch.h
#include net/dst.h
+#include net/dst_metadata.h
/*
* Theory of operations:
@@ -158,19 +159,10 @@ const u32 dst_default_metrics[RTAX_MAX + 1] = {
[RTAX_MAX] = 0xdeadbeef,
};
-
-void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
- int initial_ref, int initial_obsolete, unsigned short flags)
+void dst_init(struct dst_entry *dst, struct dst_ops *ops,
+ struct net_device *dev, int initial_ref, int initial_obsolete,
+ unsigned short flags)
{
- struct dst_entry *dst;
-
- if (ops-gc dst_entries_get_fast(ops) ops-gc_thresh) {
- if (ops-gc(ops))
- return NULL;
- }
- dst = kmem_cache_alloc(ops-kmem_cachep, GFP_ATOMIC);
- if (!dst)
- return NULL;
dst-child = NULL;
dst-dev = dev;
if (dev)
@@ -200,6 +192,25 @@ void *dst_alloc(struct dst_ops *ops, struct net_device
*dev,
dst-next = NULL;
if (!(flags DST_NOCOUNT))
[PATCH net-next 12/22] dst: Metadata destinations
Introduces a new dst_metadata which enables to carry per packet metadata
between forwarding and processing elements via the skb-dst pointer.
The structure is set up to be a union. Thus, each separate type of
metadata requires its own dst instance. If demand arises to carry
multiple types of metadata concurrently, metadata dst entries can be
made stackable.
The metadata dst entry is refcnt'ed as expected for now but a non
reference counted use is possible if the reference is forced before
queueing the skb.
In order to allow allocating dsts with variable length, the existing
dst_alloc() is split into a dst_alloc() and dst_init() function. The
existing dst_init() function to initialize the subsystem is being
renamed to dst_subsys_init() to make it clear what is what.
The check before ip_route_input() is changed to ignore metadata dsts
and drop the dst inside the routing function thus allowing to interpret
metadata in a later commit.
Signed-off-by: Thomas Graf tg...@suug.ch
---
include/net/dst.h | 6 +++-
include/net/dst_metadata.h | 32 ++
net/core/dev.c | 2 +-
net/core/dst.c | 84 ++
net/ipv4/ip_input.c| 3 +-
net/ipv4/route.c | 2 ++
6 files changed, 112 insertions(+), 17 deletions(-)
create mode 100644 include/net/dst_metadata.h
diff --git a/include/net/dst.h b/include/net/dst.h
index 2bc73f8a..2578811 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -57,6 +57,7 @@ struct dst_entry {
#define DST_FAKE_RTABLE0x0040
#define DST_XFRM_TUNNEL0x0080
#define DST_XFRM_QUEUE 0x0100
+#define DST_METADATA 0x0200
unsigned short pending_confirm;
@@ -356,6 +357,9 @@ static inline int dst_discard(struct sk_buff *skb)
}
void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref,
int initial_obsolete, unsigned short flags);
+void dst_init(struct dst_entry *dst, struct dst_ops *ops,
+ struct net_device *dev, int initial_ref, int initial_obsolete,
+ unsigned short flags);
void __dst_free(struct dst_entry *dst);
struct dst_entry *dst_destroy(struct dst_entry *dst);
@@ -457,7 +461,7 @@ static inline struct dst_entry *dst_check(struct dst_entry
*dst, u32 cookie)
return dst;
}
-void dst_init(void);
+void dst_subsys_init(void);
/* Flags for xfrm_lookup flags argument. */
enum {
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
new file mode 100644
index 000..4f7694f
--- /dev/null
+++ b/include/net/dst_metadata.h
@@ -0,0 +1,32 @@
+#ifndef __NET_DST_METADATA_H
+#define __NET_DST_METADATA_H 1
+
+#include linux/skbuff.h
+#include net/ip_tunnels.h
+#include net/dst.h
+
+struct metadata_dst {
+ struct dst_entrydst;
+ size_t opts_len;
+};
+
+static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb)
+{
+ struct metadata_dst *md_dst = (struct metadata_dst *) skb_dst(skb);
+
+ if (md_dst md_dst-dst.flags DST_METADATA)
+ return md_dst;
+
+ return NULL;
+}
+
+static inline bool skb_valid_dst(const struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+
+ return dst !(dst-flags DST_METADATA);
+}
+
+struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags);
+
+#endif /* __NET_DST_METADATA_H */
diff --git a/net/core/dev.c b/net/core/dev.c
index 8810b6b..61e3dcb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7659,7 +7659,7 @@ static int __init net_dev_init(void)
open_softirq(NET_RX_SOFTIRQ, net_rx_action);
hotcpu_notifier(dev_cpu_callback, 0);
- dst_init();
+ dst_subsys_init();
rc = 0;
out:
return rc;
diff --git a/net/core/dst.c b/net/core/dst.c
index e956ce6..917364f 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -22,6 +22,7 @@
#include linux/prefetch.h
#include net/dst.h
+#include net/dst_metadata.h
/*
* Theory of operations:
@@ -158,19 +159,10 @@ const u32 dst_default_metrics[RTAX_MAX + 1] = {
[RTAX_MAX] = 0xdeadbeef,
};
-
-void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
- int initial_ref, int initial_obsolete, unsigned short flags)
+void dst_init(struct dst_entry *dst, struct dst_ops *ops,
+ struct net_device *dev, int initial_ref, int initial_obsolete,
+ unsigned short flags)
{
- struct dst_entry *dst;
-
- if (ops-gc dst_entries_get_fast(ops) ops-gc_thresh) {
- if (ops-gc(ops))
- return NULL;
- }
- dst = kmem_cache_alloc(ops-kmem_cachep, GFP_ATOMIC);
- if (!dst)
- return NULL;
dst-child = NULL;
dst-dev = dev;
if (dev)
@@ -200,6 +192,25 @@ void *dst_alloc(struct dst_ops *ops, struct net_device
*dev,
dst-next = NULL;
if (!(flags DST_NOCOUNT))
