* [PATCH net-next 0/4] ulp: Generalize ULP infrastructure
From: Tom Herbert @ 2017-08-02 2:53 UTC (permalink / raw)
To: netdev; +Cc: rohit, davejwatson, Tom Herbert
Generalize the ULP infrastructure that was recently introduced to
support kTLS. This adds a SO_ULP socket option and creates new fields in
sock structure for ULP ops and ULP data. Also, the interface allows
additional per ULP parameters to be set so that a ULP can be pushed
and operations started in one shot.
This patch sets:
- Minor dependency fix in inet_common.h
- Implement ULP infrastructure as a socket mechanism
- Fixes TCP and TLS to use the new method (maintaining backwards
API compatibility)
- Adds a ulp.txt document
Tested: Ran simple ULP.
Tom Herbert (4):
inet: include net/sock.h in inet_common.h
sock: ULP infrastructure
tcp: Adjust TCP ULP to defer to sockets ULP
ulp: Documention for ULP infrastructure
Documentation/networking/tls.txt | 6 +-
Documentation/networking/ulp.txt | 82 ++++++++++++++
arch/alpha/include/uapi/asm/socket.h | 2 +
arch/frv/include/uapi/asm/socket.h | 2 +
arch/ia64/include/uapi/asm/socket.h | 2 +
arch/m32r/include/uapi/asm/socket.h | 2 +
arch/mips/include/uapi/asm/socket.h | 2 +
arch/mn10300/include/uapi/asm/socket.h | 2 +
arch/parisc/include/uapi/asm/socket.h | 2 +
arch/s390/include/uapi/asm/socket.h | 2 +
arch/sparc/include/uapi/asm/socket.h | 2 +
arch/xtensa/include/uapi/asm/socket.h | 2 +
include/linux/socket.h | 9 ++
include/net/inet_common.h | 2 +
include/net/inet_connection_sock.h | 4 -
include/net/sock.h | 5 +
include/net/tcp.h | 25 -----
include/net/tls.h | 4 +-
include/net/ulp_sock.h | 65 +++++++++++
include/uapi/asm-generic/socket.h | 2 +
net/Kconfig | 4 +
net/core/Makefile | 1 +
net/core/sock.c | 14 +++
net/core/sysctl_net_core.c | 25 +++++
net/core/ulp_sock.c | 194 +++++++++++++++++++++++++++++++++
net/ipv4/sysctl_net_ipv4.c | 9 +-
net/ipv4/tcp.c | 40 ++++---
net/ipv4/tcp_ipv4.c | 2 -
net/ipv4/tcp_ulp.c | 135 -----------------------
net/tls/Kconfig | 1 +
net/tls/tls_main.c | 21 ++--
31 files changed, 470 insertions(+), 200 deletions(-)
create mode 100644 Documentation/networking/ulp.txt
create mode 100644 include/net/ulp_sock.h
create mode 100644 net/core/ulp_sock.c
delete mode 100644 net/ipv4/tcp_ulp.c
--
2.11.0
^ permalink raw reply
* [PATCH net-next 1/4] inet: include net/sock.h in inet_common.h
From: Tom Herbert @ 2017-08-02 2:53 UTC (permalink / raw)
To: netdev; +Cc: rohit, davejwatson, Tom Herbert
In-Reply-To: <20170802025304.1862-1-tom@quantonium.net>
inet_common.h has a dependency on sock.h so it should include that.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
include/net/inet_common.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index f39ae697347f..df0119a317aa 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -1,6 +1,8 @@
#ifndef _INET_COMMON_H
#define _INET_COMMON_H
+#include <net/sock.h>
+
extern const struct proto_ops inet_stream_ops;
extern const struct proto_ops inet_dgram_ops;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 2/4] sock: ULP infrastructure
From: Tom Herbert @ 2017-08-02 2:53 UTC (permalink / raw)
To: netdev; +Cc: rohit, davejwatson, Tom Herbert
In-Reply-To: <20170802025304.1862-1-tom@quantonium.net>
Generalize the TCP ULP infrastructure recently introduced to support
kTLS. This adds a SO_ULP socket option and creates new fields in
sock structure for ULP ops and ULP data. Also, the interface allows
additional per ULP parameters to be set so that a ULP can be pushed
and operations started in one shot.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
arch/alpha/include/uapi/asm/socket.h | 2 +
arch/frv/include/uapi/asm/socket.h | 2 +
arch/ia64/include/uapi/asm/socket.h | 2 +
arch/m32r/include/uapi/asm/socket.h | 2 +
arch/mips/include/uapi/asm/socket.h | 2 +
arch/mn10300/include/uapi/asm/socket.h | 2 +
arch/parisc/include/uapi/asm/socket.h | 2 +
arch/s390/include/uapi/asm/socket.h | 2 +
arch/sparc/include/uapi/asm/socket.h | 2 +
arch/xtensa/include/uapi/asm/socket.h | 2 +
include/linux/socket.h | 9 ++
include/net/sock.h | 5 +
include/net/ulp_sock.h | 65 +++++++++++
include/uapi/asm-generic/socket.h | 2 +
net/Kconfig | 4 +
net/core/Makefile | 1 +
net/core/sock.c | 14 +++
net/core/sysctl_net_core.c | 25 +++++
net/core/ulp_sock.c | 194 +++++++++++++++++++++++++++++++++
19 files changed, 339 insertions(+)
create mode 100644 include/net/ulp_sock.h
create mode 100644 net/core/ulp_sock.c
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 7b285dd4fe05..885e8fca79b0 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -109,4 +109,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
index f1e3b20dce9f..8ba71f2a3bf3 100644
--- a/arch/frv/include/uapi/asm/socket.h
+++ b/arch/frv/include/uapi/asm/socket.h
@@ -102,5 +102,7 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index 5dd5c5d0d642..2de1c53f88b5 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -111,4 +111,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h
index f8f7b47e247f..b2d394381787 100644
--- a/arch/m32r/include/uapi/asm/socket.h
+++ b/arch/m32r/include/uapi/asm/socket.h
@@ -102,4 +102,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 882823bec153..d0bdf8c78220 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -120,4 +120,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
index c710db354ff2..686fbf497a13 100644
--- a/arch/mn10300/include/uapi/asm/socket.h
+++ b/arch/mn10300/include/uapi/asm/socket.h
@@ -102,4 +102,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index a0d4dc9f4eb2..d6e99deca976 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -101,4 +101,6 @@
#define SO_PEERGROUPS 0x4034
+#define SO_ULP 0x4035
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index 52a63f4175cb..6b52f162369a 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -108,4 +108,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 186fd8199f54..e765bf781107 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -98,6 +98,8 @@
#define SO_PEERGROUPS 0x003d
+#define SO_ULP 0x003e
+
/* Security levels - as per NRL IPv6 - don't actually do anything */
#define SO_SECURITY_AUTHENTICATION 0x5001
#define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index 3eed2761c149..8eaa2e9e27b6 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -113,4 +113,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _XTENSA_SOCKET_H */
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 8b13db5163cc..8f6e8c46a91e 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -156,6 +156,15 @@ struct ucred {
__u32 gid;
};
+/* ULP configuration for socket */
+
+#define ULP_NAME_MAX 16
+
+struct ulp_config {
+ char ulp_name[ULP_NAME_MAX];
+ __u8 ulp_params[0];
+};
+
/* Supported address families. */
#define AF_UNSPEC 0
#define AF_UNIX 1 /* Unix domain sockets */
diff --git a/include/net/sock.h b/include/net/sock.h
index 393c38e9f6aa..a1e5586aa767 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -72,6 +72,7 @@
#include <net/tcp_states.h>
#include <linux/net_tstamp.h>
#include <net/smc.h>
+#include <net/ulp_sock.h>
/*
* This structure really needs to be cleaned up.
@@ -312,6 +313,8 @@ struct sock_common {
* @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
* @sk_reuseport_cb: reuseport group container
* @sk_rcu: used during RCU grace period
+ * @sk_ulp_ops: pluggable ULP control hook
+ * @sk_ulp_data: ULP private data
*/
struct sock {
/*
@@ -415,6 +418,8 @@ struct sock {
unsigned int sk_gso_max_size;
gfp_t sk_allocation;
__u32 sk_txhash;
+ const struct ulp_ops *sk_ulp_ops;
+ void *sk_ulp_data;
/*
* Because of non atomicity rules, all
diff --git a/include/net/ulp_sock.h b/include/net/ulp_sock.h
new file mode 100644
index 000000000000..c085c36a6433
--- /dev/null
+++ b/include/net/ulp_sock.h
@@ -0,0 +1,65 @@
+#ifndef __NET_ULP_SOCK_H
+#define __NET_ULP_SOCK_H
+
+#include <linux/socket.h>
+
+#define ULP_MAX 128
+#define ULP_BUF_MAX (ULP_NAME_MAX * ULP_MAX)
+
+struct ulp_ops {
+ struct list_head list;
+
+ /* initialize ulp */
+ int (*init)(struct sock *sk, char __user *optval, int len);
+
+ /* cleanup ulp */
+ void (*release)(struct sock *sk);
+
+ /* Get ULP specific parameters in getsockopt */
+ int (*get_params)(struct sock *sk, char __user *optval, int *optlen);
+
+ char name[ULP_NAME_MAX];
+ struct module *owner;
+};
+
+#ifdef CONFIG_ULP_SOCK
+
+int ulp_register(struct ulp_ops *type);
+void ulp_unregister(struct ulp_ops *type);
+int ulp_set(struct sock *sk, char __user *optval, int len);
+int ulp_get_config(struct sock *sk, char __user *optval, int *optlen);
+void ulp_get_available(char *buf, size_t len);
+void ulp_cleanup(struct sock *sk);
+
+#else
+
+static inline int ulp_register(struct ulp_ops *type)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void ulp_unregister(struct ulp_ops *type)
+{
+}
+
+int ulp_set(struct sock *sk, char __user *optval, int len)
+{
+ return -EOPNOTSUPP;
+}
+
+int ulp_get(struct sock *sk, char __user *optval, int *optlen);
+{
+ return -EOPNOTSUPP;
+}
+
+void ulp_get_available(char *buf, size_t len);
+{
+}
+
+void ulp_cleanup(struct sock *sk);
+{
+}
+
+#endif
+
+#endif /* __NET_ULP_SOCK_H */
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 9861be8da65e..bf15ae98f3b2 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -104,4 +104,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/net/Kconfig b/net/Kconfig
index 7d57ef34b79c..2b8d2d88bc2b 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -419,6 +419,10 @@ config GRO_CELLS
bool
default n
+config ULP_SOCK
+ bool
+ default n
+
config NET_DEVLINK
tristate "Network physical/parent device Netlink interface"
help
diff --git a/net/core/Makefile b/net/core/Makefile
index d501c4278015..fcfd29ef9926 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -28,3 +28,4 @@ obj-$(CONFIG_DST_CACHE) += dst_cache.o
obj-$(CONFIG_HWBM) += hwbm.o
obj-$(CONFIG_NET_DEVLINK) += devlink.o
obj-$(CONFIG_GRO_CELLS) += gro_cells.o
+obj-$(CONFIG_ULP_SOCK) += ulp_sock.o
diff --git a/net/core/sock.c b/net/core/sock.c
index 742f68c9c84a..cb03af11b536 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1055,6 +1055,11 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
if (val == 1)
dst_negative_advice(sk);
break;
+
+ case SO_ULP:
+ ret = ulp_set(sk, optval, optlen);
+ break;
+
default:
ret = -ENOPROTOOPT;
break;
@@ -1383,6 +1388,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val64 = sock_gen_cookie(sk);
break;
+ case SO_ULP:
+ return ulp_get_config(sk, optval, optlen);
+
default:
/* We implement the SO_SNDLOWAT etc to not be settable
* (1003.1g 7).
@@ -2943,6 +2951,12 @@ EXPORT_SYMBOL(compat_sock_common_setsockopt);
void sk_common_release(struct sock *sk)
{
+ /* Clean up ULP before destroying protocol socket since ULP might
+ * be dependent on transport (and not the other way around).
+ */
+
+ ulp_cleanup(sk);
+
if (sk->sk_prot->destroy)
sk->sk_prot->destroy(sk);
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index b7cd9aafe99e..9e14f91b57eb 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -21,6 +21,7 @@
#include <net/net_ratelimit.h>
#include <net/busy_poll.h>
#include <net/pkt_sched.h>
+#include <net/ulp_sock.h>
static int zero = 0;
static int one = 1;
@@ -249,6 +250,24 @@ static int proc_do_rss_key(struct ctl_table *table, int write,
return proc_dostring(&fake_table, write, buffer, lenp, ppos);
}
+static int proc_ulp_available(struct ctl_table *ctl,
+ int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ struct ctl_table tbl = { .maxlen = ULP_BUF_MAX, };
+ int ret;
+
+ tbl.data = kmalloc(tbl.maxlen, GFP_USER);
+ if (!tbl.data)
+ return -ENOMEM;
+ ulp_get_available(tbl.data, ULP_BUF_MAX);
+ ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+ kfree(tbl.data);
+
+ return ret;
+}
+
static struct ctl_table net_core_table[] = {
#ifdef CONFIG_NET
{
@@ -460,6 +479,12 @@ static struct ctl_table net_core_table[] = {
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
},
+ {
+ .procname = "ulp_available",
+ .maxlen = ULP_BUF_MAX,
+ .mode = 0444,
+ .proc_handler = proc_ulp_available,
+ },
{ }
};
diff --git a/net/core/ulp_sock.c b/net/core/ulp_sock.c
new file mode 100644
index 000000000000..0f49489b7eb6
--- /dev/null
+++ b/net/core/ulp_sock.c
@@ -0,0 +1,194 @@
+/*
+ * Pluggable upper layer protocol support in sockets.
+ *
+ * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved.
+ * Copyright (c) 2017, Tom Herbert <tom@quantonium.net>. All rights reserved.
+ *
+ */
+
+#include <linux/gfp.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <net/sock.h>
+#include <net/ulp_sock.h>
+
+static DEFINE_SPINLOCK(ulp_list_lock);
+static LIST_HEAD(ulp_list);
+
+/* Simple linear search, don't expect many entries! */
+static struct ulp_ops *ulp_find(const char *name)
+{
+ struct ulp_ops *e;
+
+ list_for_each_entry_rcu(e, &ulp_list, list) {
+ if (strcmp(e->name, name) == 0)
+ return e;
+ }
+
+ return NULL;
+}
+
+static const struct ulp_ops *__ulp_find_autoload(const char *name)
+{
+ const struct ulp_ops *ulp = NULL;
+
+ rcu_read_lock();
+ ulp = ulp_find(name);
+
+#ifdef CONFIG_MODULES
+ if (!ulp && capable(CAP_NET_ADMIN)) {
+ rcu_read_unlock();
+ request_module("%s", name);
+ rcu_read_lock();
+ ulp = ulp_find(name);
+ }
+#endif
+ if (!ulp || !try_module_get(ulp->owner))
+ ulp = NULL;
+
+ rcu_read_unlock();
+ return ulp;
+}
+
+/* Attach new upper layer protocol to the list
+ * of available protocols.
+ */
+int ulp_register(struct ulp_ops *ulp)
+{
+ int ret = 0;
+
+ spin_lock(&ulp_list_lock);
+ if (ulp_find(ulp->name)) {
+ pr_notice("%s already registered or non-unique name\n",
+ ulp->name);
+ ret = -EEXIST;
+ } else {
+ list_add_tail_rcu(&ulp->list, &ulp_list);
+ }
+ spin_unlock(&ulp_list_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ulp_register);
+
+void ulp_unregister(struct ulp_ops *ulp)
+{
+ spin_lock(&ulp_list_lock);
+ list_del_rcu(&ulp->list);
+ spin_unlock(&ulp_list_lock);
+
+ synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(ulp_unregister);
+
+/* Build string with list of available upper layer protocl values */
+void ulp_get_available(char *buf, size_t maxlen)
+{
+ struct ulp_ops *ulp_ops;
+ size_t offs = 0;
+
+ *buf = '\0';
+ rcu_read_lock();
+ list_for_each_entry_rcu(ulp_ops, &ulp_list, list) {
+ offs += snprintf(buf + offs, maxlen - offs,
+ "%s%s",
+ offs == 0 ? "" : " ", ulp_ops->name);
+ }
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(ulp_get_available);
+
+void ulp_cleanup(struct sock *sk)
+{
+ if (!sk->sk_ulp_ops)
+ return;
+
+ if (sk->sk_ulp_ops->release)
+ sk->sk_ulp_ops->release(sk);
+
+ module_put(sk->sk_ulp_ops->owner);
+}
+EXPORT_SYMBOL_GPL(ulp_cleanup);
+
+/* Change upper layer protocol for socket, Called from setsockopt. */
+int ulp_set(struct sock *sk, char __user *optval, int len)
+{
+ const struct ulp_ops *ulp_ops;
+ struct ulp_config ulpc;
+ int err = 0;
+
+ if (len < sizeof(ulpc))
+ return -EINVAL;
+
+ if (copy_from_user(&ulpc, optval, sizeof(ulpc)))
+ return -EFAULT;
+
+ if (sk->sk_ulp_ops)
+ return -EEXIST;
+
+ ulp_ops = __ulp_find_autoload(ulpc.ulp_name);
+ if (!ulp_ops)
+ return -ENOENT;
+
+ optval += sizeof(ulpc);
+ len -= sizeof(ulpc);
+
+ err = ulp_ops->init(sk, optval, len);
+ if (err)
+ return err;
+
+ sk->sk_ulp_ops = ulp_ops;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ulp_set);
+
+/* Get upper layer protocol for socket. Called from getsockopt. */
+int ulp_get_config(struct sock *sk, char __user *optval, int *optlen)
+{
+ struct ulp_config ulpc;
+ int len = *optlen;
+ int used_len;
+ int ret;
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+
+ if (len < sizeof(ulpc))
+ return -EINVAL;
+
+ if (!sk->sk_ulp_ops) {
+ if (put_user(0, optlen))
+ return -EFAULT;
+ return 0;
+ }
+
+ memcpy(ulpc.ulp_name, sk->sk_ulp_ops->name,
+ sizeof(ulpc.ulp_name));
+
+ if (copy_to_user(optval, &ulpc, sizeof(ulpc)))
+ return -EFAULT;
+
+ used_len = sizeof(ulpc);
+
+ if (sk->sk_ulp_ops->get_params) {
+ len -= sizeof(ulpc);
+ optval += sizeof(ulpc);
+
+ ret = sk->sk_ulp_ops->get_params(sk, optval, &len);
+ if (ret)
+ return ret;
+
+ used_len += len;
+ }
+
+ if (put_user(used_len, optlen))
+ return -EFAULT;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ulp_get_config);
+
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 3/4] tcp: Adjust TCP ULP to defer to sockets ULP
From: Tom Herbert @ 2017-08-02 2:53 UTC (permalink / raw)
To: netdev; +Cc: rohit, davejwatson, Tom Herbert
In-Reply-To: <20170802025304.1862-1-tom@quantonium.net>
Fix TCP and TLS to use the newer ULP infrastructure in sockets.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
Documentation/networking/tls.txt | 6 +-
include/net/inet_connection_sock.h | 4 --
include/net/tcp.h | 25 -------
include/net/tls.h | 4 +-
net/ipv4/sysctl_net_ipv4.c | 9 ++-
net/ipv4/tcp.c | 40 ++++++-----
net/ipv4/tcp_ipv4.c | 2 -
net/ipv4/tcp_ulp.c | 135 -------------------------------------
net/tls/Kconfig | 1 +
net/tls/tls_main.c | 21 +++---
10 files changed, 47 insertions(+), 200 deletions(-)
delete mode 100644 net/ipv4/tcp_ulp.c
diff --git a/Documentation/networking/tls.txt b/Documentation/networking/tls.txt
index 77ed00631c12..b70309df4709 100644
--- a/Documentation/networking/tls.txt
+++ b/Documentation/networking/tls.txt
@@ -12,8 +12,12 @@ Creating a TLS connection
First create a new TCP socket and set the TLS ULP.
+ struct ulp_config ulpc = {
+ .ulp_name = "tls",
+ };
+
sock = socket(AF_INET, SOCK_STREAM, 0);
- setsockopt(sock, SOL_TCP, TCP_ULP, "tls", sizeof("tls"));
+ setsockopt(sock, SOL_SOCKET, SO_ULP, &ulpc, sizeof(ulpc))
Setting the TLS ULP allows us to set/get TLS socket options. Currently
only the symmetric encryption is handled in the kernel. After the TLS
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 13e4c89a8231..c7a577976bec 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -75,8 +75,6 @@ struct inet_connection_sock_af_ops {
* @icsk_pmtu_cookie Last pmtu seen by socket
* @icsk_ca_ops Pluggable congestion control hook
* @icsk_af_ops Operations which are AF_INET{4,6} specific
- * @icsk_ulp_ops Pluggable ULP control hook
- * @icsk_ulp_data ULP private data
* @icsk_ca_state: Congestion control state
* @icsk_retransmits: Number of unrecovered [RTO] timeouts
* @icsk_pending: Scheduled timer event
@@ -99,8 +97,6 @@ struct inet_connection_sock {
__u32 icsk_pmtu_cookie;
const struct tcp_congestion_ops *icsk_ca_ops;
const struct inet_connection_sock_af_ops *icsk_af_ops;
- const struct tcp_ulp_ops *icsk_ulp_ops;
- void *icsk_ulp_data;
unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
__u8 icsk_ca_state:6,
icsk_ca_setsockopt:1,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index bb1881b4ce48..65c462da3740 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1968,31 +1968,6 @@ static inline void tcp_listendrop(const struct sock *sk)
enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer);
-/*
- * Interface for adding Upper Level Protocols over TCP
- */
-
-#define TCP_ULP_NAME_MAX 16
-#define TCP_ULP_MAX 128
-#define TCP_ULP_BUF_MAX (TCP_ULP_NAME_MAX*TCP_ULP_MAX)
-
-struct tcp_ulp_ops {
- struct list_head list;
-
- /* initialize ulp */
- int (*init)(struct sock *sk);
- /* cleanup ulp */
- void (*release)(struct sock *sk);
-
- char name[TCP_ULP_NAME_MAX];
- struct module *owner;
-};
-int tcp_register_ulp(struct tcp_ulp_ops *type);
-void tcp_unregister_ulp(struct tcp_ulp_ops *type);
-int tcp_set_ulp(struct sock *sk, const char *name);
-void tcp_get_available_ulp(char *buf, size_t len);
-void tcp_cleanup_ulp(struct sock *sk);
-
/* Call BPF_SOCK_OPS program that returns an int. If the return value
* is < 0, then the BPF op failed (for example if the loaded BPF
* program does not support the chosen operation or there is no BPF
diff --git a/include/net/tls.h b/include/net/tls.h
index b89d397dd62f..7d88a6e2f5a7 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -214,9 +214,7 @@ static inline void tls_fill_prepend(struct tls_context *ctx,
static inline struct tls_context *tls_get_ctx(const struct sock *sk)
{
- struct inet_connection_sock *icsk = inet_csk(sk);
-
- return icsk->icsk_ulp_data;
+ return sk->sk_ulp_data;
}
static inline struct tls_sw_context *tls_sw_ctx(
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 0d3c038d7b04..9ab0c278b7ba 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -21,6 +21,7 @@
#include <net/route.h>
#include <net/tcp.h>
#include <net/udp.h>
+#include <net/ulp_sock.h>
#include <net/cipso_ipv4.h>
#include <net/inet_frag.h>
#include <net/ping.h>
@@ -372,13 +373,15 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- struct ctl_table tbl = { .maxlen = TCP_ULP_BUF_MAX, };
+ struct ctl_table tbl = { .maxlen = ULP_BUF_MAX, };
int ret;
tbl.data = kmalloc(tbl.maxlen, GFP_USER);
if (!tbl.data)
return -ENOMEM;
- tcp_get_available_ulp(tbl.data, TCP_ULP_BUF_MAX);
+
+ /* Just return all ULPs for compatibility */
+ ulp_get_available(tbl.data, ULP_BUF_MAX);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
kfree(tbl.data);
@@ -709,7 +712,7 @@ static struct ctl_table ipv4_table[] = {
},
{
.procname = "tcp_available_ulp",
- .maxlen = TCP_ULP_BUF_MAX,
+ .maxlen = ULP_BUF_MAX,
.mode = 0444,
.proc_handler = proc_tcp_available_ulp,
},
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9dd6f4dba9b1..26f0d9821e6d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2404,24 +2404,24 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
release_sock(sk);
return err;
}
+
case TCP_ULP: {
- char name[TCP_ULP_NAME_MAX];
+ struct ulp_config ulpc;
if (optlen < 1)
return -EINVAL;
- val = strncpy_from_user(name, optval,
- min_t(long, TCP_ULP_NAME_MAX - 1,
+ val = strncpy_from_user(ulpc.ulp_name, optval,
+ min_t(long, ULP_NAME_MAX - 1,
optlen));
if (val < 0)
return -EFAULT;
- name[val] = 0;
+ ulpc.ulp_name[val] = 0;
- lock_sock(sk);
- err = tcp_set_ulp(sk, name);
- release_sock(sk);
- return err;
+ return kernel_setsockopt(sk->sk_socket, SOL_SOCKET, SO_ULP,
+ (char *)&ulpc, sizeof(ulpc));
}
+
default:
/* fallthru */
break;
@@ -2993,20 +2993,28 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
return -EFAULT;
return 0;
- case TCP_ULP:
+ case TCP_ULP: {
+ struct ulp_config ulpc;
+ int ulen, ret;
+
if (get_user(len, optlen))
return -EFAULT;
- len = min_t(unsigned int, len, TCP_ULP_NAME_MAX);
- if (!icsk->icsk_ulp_ops) {
- if (put_user(0, optlen))
- return -EFAULT;
- return 0;
- }
+ len = min_t(unsigned int, len, ULP_NAME_MAX);
+
+ ulen = sizeof(ulpc);
+
+ /* Backwards compatbility */
+ ret = kernel_getsockopt(sk->sk_socket, SOL_SOCKET, SO_ULP,
+ (char *)&ulpc, &ulen);
+ if (ret)
+ return ret;
+
if (put_user(len, optlen))
return -EFAULT;
- if (copy_to_user(optval, icsk->icsk_ulp_ops->name, len))
+ if (copy_to_user(optval, ulpc.ulp_name, len))
return -EFAULT;
return 0;
+ }
case TCP_THIN_LINEAR_TIMEOUTS:
val = tp->thin_lto;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 9b51663cd5a4..89fafd2c5d36 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1858,8 +1858,6 @@ void tcp_v4_destroy_sock(struct sock *sk)
tcp_cleanup_congestion_control(sk);
- tcp_cleanup_ulp(sk);
-
/* Cleanup up the write buffer. */
tcp_write_queue_purge(sk);
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
deleted file mode 100644
index 2417f55374c5..000000000000
--- a/net/ipv4/tcp_ulp.c
+++ /dev/null
@@ -1,135 +0,0 @@
-/*
- * Pluggable TCP upper layer protocol support.
- *
- * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved.
- *
- */
-
-#include<linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/gfp.h>
-#include <net/tcp.h>
-
-static DEFINE_SPINLOCK(tcp_ulp_list_lock);
-static LIST_HEAD(tcp_ulp_list);
-
-/* Simple linear search, don't expect many entries! */
-static struct tcp_ulp_ops *tcp_ulp_find(const char *name)
-{
- struct tcp_ulp_ops *e;
-
- list_for_each_entry_rcu(e, &tcp_ulp_list, list) {
- if (strcmp(e->name, name) == 0)
- return e;
- }
-
- return NULL;
-}
-
-static const struct tcp_ulp_ops *__tcp_ulp_find_autoload(const char *name)
-{
- const struct tcp_ulp_ops *ulp = NULL;
-
- rcu_read_lock();
- ulp = tcp_ulp_find(name);
-
-#ifdef CONFIG_MODULES
- if (!ulp && capable(CAP_NET_ADMIN)) {
- rcu_read_unlock();
- request_module("%s", name);
- rcu_read_lock();
- ulp = tcp_ulp_find(name);
- }
-#endif
- if (!ulp || !try_module_get(ulp->owner))
- ulp = NULL;
-
- rcu_read_unlock();
- return ulp;
-}
-
-/* Attach new upper layer protocol to the list
- * of available protocols.
- */
-int tcp_register_ulp(struct tcp_ulp_ops *ulp)
-{
- int ret = 0;
-
- spin_lock(&tcp_ulp_list_lock);
- if (tcp_ulp_find(ulp->name)) {
- pr_notice("%s already registered or non-unique name\n",
- ulp->name);
- ret = -EEXIST;
- } else {
- list_add_tail_rcu(&ulp->list, &tcp_ulp_list);
- }
- spin_unlock(&tcp_ulp_list_lock);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(tcp_register_ulp);
-
-void tcp_unregister_ulp(struct tcp_ulp_ops *ulp)
-{
- spin_lock(&tcp_ulp_list_lock);
- list_del_rcu(&ulp->list);
- spin_unlock(&tcp_ulp_list_lock);
-
- synchronize_rcu();
-}
-EXPORT_SYMBOL_GPL(tcp_unregister_ulp);
-
-/* Build string with list of available upper layer protocl values */
-void tcp_get_available_ulp(char *buf, size_t maxlen)
-{
- struct tcp_ulp_ops *ulp_ops;
- size_t offs = 0;
-
- *buf = '\0';
- rcu_read_lock();
- list_for_each_entry_rcu(ulp_ops, &tcp_ulp_list, list) {
- offs += snprintf(buf + offs, maxlen - offs,
- "%s%s",
- offs == 0 ? "" : " ", ulp_ops->name);
- }
- rcu_read_unlock();
-}
-
-void tcp_cleanup_ulp(struct sock *sk)
-{
- struct inet_connection_sock *icsk = inet_csk(sk);
-
- if (!icsk->icsk_ulp_ops)
- return;
-
- if (icsk->icsk_ulp_ops->release)
- icsk->icsk_ulp_ops->release(sk);
- module_put(icsk->icsk_ulp_ops->owner);
-}
-
-/* Change upper layer protocol for socket */
-int tcp_set_ulp(struct sock *sk, const char *name)
-{
- struct inet_connection_sock *icsk = inet_csk(sk);
- const struct tcp_ulp_ops *ulp_ops;
- int err = 0;
-
- if (icsk->icsk_ulp_ops)
- return -EEXIST;
-
- ulp_ops = __tcp_ulp_find_autoload(name);
- if (!ulp_ops)
- err = -ENOENT;
- else
- err = ulp_ops->init(sk);
-
- if (err)
- goto out;
-
- icsk->icsk_ulp_ops = ulp_ops;
- out:
- return err;
-}
diff --git a/net/tls/Kconfig b/net/tls/Kconfig
index eb583038c67e..60ae4e9b257e 100644
--- a/net/tls/Kconfig
+++ b/net/tls/Kconfig
@@ -7,6 +7,7 @@ config TLS
select CRYPTO
select CRYPTO_AES
select CRYPTO_GCM
+ select ULP_SOCK
default n
---help---
Enable kernel support for TLS protocol. This allows symmetric
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 60aff60e30ad..00ccbec96820 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -31,15 +31,15 @@
* SOFTWARE.
*/
-#include <linux/module.h>
-
-#include <net/tcp.h>
-#include <net/inet_common.h>
#include <linux/highmem.h>
+#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/sched/signal.h>
-
+#include <net/inet_common.h>
+#include <net/sock.h>
+#include <net/tcp.h>
#include <net/tls.h>
+#include <net/ulp_sock.h>
MODULE_AUTHOR("Mellanox Technologies");
MODULE_DESCRIPTION("Transport Layer Security Support");
@@ -438,9 +438,8 @@ static int tls_setsockopt(struct sock *sk, int level, int optname,
return do_tls_setsockopt(sk, optname, optval, optlen);
}
-static int tls_init(struct sock *sk)
+static int tls_init(struct sock *sk, char __user *optval, int len)
{
- struct inet_connection_sock *icsk = inet_csk(sk);
struct tls_context *ctx;
int rc = 0;
@@ -450,7 +449,7 @@ static int tls_init(struct sock *sk)
rc = -ENOMEM;
goto out;
}
- icsk->icsk_ulp_data = ctx;
+ sk->sk_ulp_data = ctx;
ctx->setsockopt = sk->sk_prot->setsockopt;
ctx->getsockopt = sk->sk_prot->getsockopt;
sk->sk_prot = &tls_base_prot;
@@ -458,7 +457,7 @@ static int tls_init(struct sock *sk)
return rc;
}
-static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = {
+static struct ulp_ops ulp_tls_ops __read_mostly = {
.name = "tls",
.owner = THIS_MODULE,
.init = tls_init,
@@ -475,14 +474,14 @@ static int __init tls_register(void)
tls_sw_prot.sendpage = tls_sw_sendpage;
tls_sw_prot.close = tls_sk_proto_close;
- tcp_register_ulp(&tcp_tls_ulp_ops);
+ ulp_register(&ulp_tls_ops);
return 0;
}
static void __exit tls_unregister(void)
{
- tcp_unregister_ulp(&tcp_tls_ulp_ops);
+ ulp_unregister(&ulp_tls_ops);
}
module_init(tls_register);
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 4/4] ulp: Documention for ULP infrastructure
From: Tom Herbert @ 2017-08-02 2:53 UTC (permalink / raw)
To: netdev; +Cc: rohit, davejwatson, Tom Herbert
In-Reply-To: <20170802025304.1862-1-tom@quantonium.net>
Add a doc in Documentation/networking
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
Documentation/networking/ulp.txt | 82 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 82 insertions(+)
create mode 100644 Documentation/networking/ulp.txt
diff --git a/Documentation/networking/ulp.txt b/Documentation/networking/ulp.txt
new file mode 100644
index 000000000000..4d830314b0ff
--- /dev/null
+++ b/Documentation/networking/ulp.txt
@@ -0,0 +1,82 @@
+Upper Layer Protocol (ULP) Infrastructure
+=========================================
+
+The ULP kernel infrastructure provides a means to hook upper layer
+protocol support on a socket. A module may register a ULP hook
+in the kernel. ULP processing is enabled by a setsockopt on a socket
+that specifies the name of the registered ULP to invoked. An
+initialization function is defined for each ULP that can change the
+function entry points of the socket (sendmsg, rcvmsg, etc.) or change
+the socket in other fundamental ways.
+
+Note, no synchronization is enforced between the setsockopt to enable
+a ULP and ongoing asynchronous operations on the socket (such as a
+blocked read). If synchronization is required this must be handled by
+the ULP and caller.
+
+User interface
+==============
+
+The structure for the socket SOL_ULP options is defined in socket.h.
+
+Example to enable "my_ulp" ULP on a socket:
+
+struct ulp_config ulpc = {
+ .ulp_name = "my_ulp",
+};
+
+setsockopt(sock, SOL_SOCKET, SO_ULP, &ulpc, sizeof(ulpc))
+
+The ulp_config includes a "__u8 ulp_params[0]" filled that may be used
+to refer ULP specific parameters being set.
+
+Kernel interface
+================
+
+The interface for ULP infrastructure is defined in net/ulp_sock.h.
+
+ULP registration functions
+--------------------------
+
+int ulp_register(struct ulp_ops *type)
+
+ Called to register a ULP. The ulp_ops structure is described below.
+
+void ulp_unregister(struct ulp_ops *type);
+
+ Called to unregister a ULP.
+
+ulp_ops structure
+-----------------
+
+int (*init)(struct sock *sk, char __user *optval, int len)
+
+ Initialization function for the ULP. This is called from setsockopt
+ when the ULP name in the ulp_config argument matches the registered
+ ULP. optval is a userspace pointer to the ULP specific parameters.
+ len is the length of the ULP specific parameters.
+
+void (*release)(struct sock *sk)
+
+ Called when socket is being destroyed. The ULP implementation
+ should cancel any asynchronous operations (such as timers) and
+ release any acquired resources.
+
+int (*get_params)(struct sock *sk, char __user *optval, int *optlen)
+
+ Get the ULP specific parameters previous set in the init function
+ for the ULP. Note that optlen is a pointer to kernel memory.
+
+char name[ULP_NAME_MAX]
+
+ Name of the ULP. Must be NULL terminated.
+
+struct module *owner
+
+ Corresponding owner for ref count.
+
+Author
+======
+
+Tom Herbert (tom@quantonium.net)
+
--
2.11.0
^ permalink raw reply related
* Re: [PATCH 1/2] [for 4.13] net: qcom/emac: disable flow control autonegotiation by default
From: Andrew Lunn @ 2017-08-02 2:58 UTC (permalink / raw)
To: Timur Tabi; +Cc: David S. Miller, netdev
In-Reply-To: <6a6ac2c1-eb78-d7fd-5721-49dd6a550913@codeaurora.org>
On Tue, Aug 01, 2017 at 07:56:31PM -0500, Timur Tabi wrote:
> On 8/1/17 6:15 PM, Andrew Lunn wrote:
> >Pause frames are something you can auto-negotiate at the PHY
> >level. Should you also be clearing some bits in the phydev, so the
> >peer knows pause frames are not supported?
>
> When pause frame autonegotiation is enabled in the driver, that only means
> that the driver looks at what the PHY has autonegotiated, and then
> configures the MAC to match that.
>
> The driver doesn't touch the PHY at all. It leaves all that to phylib.
>
> Now if autonegotiation is disabled in the driver, then it just hard-codes
> those TX/RX settings in the driver. Are you saying I should program the PHY
> at the point to disable autonegotiation on the PHY level? If so, then I
> don't know how to do that. I just assumed that the MAC never tells the PHY
> what to do.
Documentation/networking/phy.txt says:
Pause frames / flow control
The PHY does not participate directly in flow control/pause frames except by
making sure that the SUPPORTED_Pause and SUPPORTED_AsymPause bits are set in
MII_ADVERTISE to indicate towards the link partner that the Ethernet MAC
controller supports such a thing. Since flow control/pause frames generation
involves the Ethernet MAC driver, it is recommended that this driver takes care
of properly indicating advertisement and support for such features by setting
the SUPPORTED_Pause and SUPPORTED_AsymPause bits accordingly. This can be done
either before or after phy_connect() and/or as a result of implementing the
ethtool::set_pauseparam feature.
So just check if the MAC driver is setting SUPPORTED_Pause and
SUPPORTED_AsymPause.
Andrew
^ permalink raw reply
* [PATCH net-next v3 0/3] netvsc: transparent VF support
From: Stephen Hemminger @ 2017-08-02 2:58 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, corbet; +Cc: devel, linux-doc, netdev
This patch set changes how SR-IOV Virtual Function devices are managed
in the Hyper-V network driver. This version is rebased onto current net-next.
Background
In Hyper-V SR-IOV can be enabled (and disabled) by changing guest settings
on host. When SR-IOV is enabled a matching PCI device is hot plugged and
visible on guest. The VF device is an add-on to an existing netvsc
device, and has the same MAC address.
How is this different?
The original support of VF relied on using bonding driver in active
standby mode to handle the VF device.
With the new netvsc VF logic, the Linux hyper-V network
virtual driver will directly manage the link to SR-IOV VF device.
When VF device is detected (hot plug) it is automatically made a
slave device of the netvsc device. The VF device state reflects
the state of the netvsc device; i.e. if netvsc is set down, then
VF is set down. If netvsc is set up, then VF is brought up.
Packet flow is independent of VF status; all packets are sent and
received as if they were associated with the netvsc device. If VF is
removed or link is down then the synthetic VMBUS path is used.
What was wrong with using bonding script?
A lot of work went into getting the bonding script to work on all
distributions, but it was a major struggle. Linux network devices
can be configured many, many ways and there is no one solution from
userspace to make it all work. What is really hard is when
configuration is attached to synthetic device during boot (eth0) and
then the same addresses and firewall rules needs to also work later if
doing bonding. The new code gets around all of this.
How does VF work during initialization?
Since all packets are sent and received through the logical netvsc
device, initialization is much easier. Just configure the regular
netvsc Ethernet device; when/if SR-IOV is enabled it just
works. Provisioning and cloud init only need to worry about setting up
netvsc device (eth0). If SR-IOV is enabled (even as a later step), the
address and rules stay the same.
What devices show up?
Both netvsc and PCI devices are visible in the system. The netvsc
device is active and named in usual manner (eth0). The PCI device is
visible to Linux and gets renamed by udev to a persistent name
(enP2p3s0). The PCI device name is now irrelevant now.
The logic also sets the PCI VF device SLAVE flag on the network
device so network tools can see the relationship if they are smart
enough to understand how layered devices work.
This is a lot like how I see Windows working.
The VF device is visible in Device Manager, but is not configured.
Is there any performance impact?
There is no visible change in performance. The bonding
and netvsc driver both have equivalent steps.
Is it compatible with old bonding script?
It turns out that if you use the old bonding script, then everything
still works but in a sub-optimum manner. What happens is that bonding
is unable to steal the VF from the netvsc device so it creates a one
legged bond. Packet flow then is:
bond0 <--> eth0 <- -> VF (enP2p3s0).
In other words, if you get it wrong it still works, just
awkward and slower.
What if I add address or firewall rule onto the VF?
Same problems occur with now as already occur with bonding, bridging,
teaming on Linux if user incorrectly does configuration onto
an underlying slave device. It will sort of work, packets will come in
and out but the Linux kernel gets confused and things like ARP don’t
work right. There is no way to block manipulation of the slave
device, and I am sure someone will find some special use case where
they want it.
Stephen Hemminger (3):
netvsc: transparent VF management
netvsc: add documentation
netvsc: remove bonding setup script
Documentation/networking/netvsc.txt | 63 ++++++
MAINTAINERS | 1 +
drivers/net/hyperv/hyperv_net.h | 12 ++
drivers/net/hyperv/netvsc_drv.c | 419 ++++++++++++++++++++++++++++--------
tools/hv/bondvf.sh | 255 ----------------------
5 files changed, 406 insertions(+), 344 deletions(-)
create mode 100644 Documentation/networking/netvsc.txt
delete mode 100755 tools/hv/bondvf.sh
--
2.11.0
^ permalink raw reply
* [PATCH net-next v3 1/3] netvsc: transparent VF management
From: Stephen Hemminger @ 2017-08-02 2:58 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, corbet; +Cc: devel, netdev, linux-doc
In-Reply-To: <20170802025855.11521-1-sthemmin@microsoft.com>
This patch implements transparent fail over from synthetic NIC to
SR-IOV virtual function NIC in Hyper-V environment. It is a better
alternative to using bonding as is done now. Instead, the receive and
transmit fail over is done internally inside the driver.
Using bonding driver has lots of issues because it depends on the
script being run early enough in the boot process and with sufficient
information to make the association. This patch moves all that
functionality into the kernel.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
---
v3 - fix merge conflict (due to comment change)
drivers/net/hyperv/hyperv_net.h | 12 ++
drivers/net/hyperv/netvsc_drv.c | 419 +++++++++++++++++++++++++++++++---------
2 files changed, 342 insertions(+), 89 deletions(-)
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index f2cef5aaed1f..c701b059c5ac 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -680,6 +680,15 @@ struct netvsc_ethtool_stats {
unsigned long tx_busy;
};
+struct netvsc_vf_pcpu_stats {
+ u64 rx_packets;
+ u64 rx_bytes;
+ u64 tx_packets;
+ u64 tx_bytes;
+ struct u64_stats_sync syncp;
+ u32 tx_dropped;
+};
+
struct netvsc_reconfig {
struct list_head list;
u32 event;
@@ -713,6 +722,9 @@ struct net_device_context {
/* State to manage the associated VF interface. */
struct net_device __rcu *vf_netdev;
+ struct netvsc_vf_pcpu_stats __percpu *vf_stats;
+ struct work_struct vf_takeover;
+ struct work_struct vf_notify;
/* 1: allocated, serial number is valid. 0: not allocated */
u32 vf_alloc;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 9453eef6d09f..c71728d82049 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -34,6 +34,7 @@
#include <linux/in.h>
#include <linux/slab.h>
#include <linux/rtnetlink.h>
+#include <linux/netpoll.h>
#include <net/arp.h>
#include <net/route.h>
@@ -71,6 +72,7 @@ static void netvsc_set_multicast_list(struct net_device *net)
static int netvsc_open(struct net_device *net)
{
struct net_device_context *ndev_ctx = netdev_priv(net);
+ struct net_device *vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
struct netvsc_device *nvdev = rtnl_dereference(ndev_ctx->nvdev);
struct rndis_device *rdev;
int ret = 0;
@@ -87,15 +89,29 @@ static int netvsc_open(struct net_device *net)
netif_tx_wake_all_queues(net);
rdev = nvdev->extension;
- if (!rdev->link_state && !ndev_ctx->datapath)
+
+ if (!rdev->link_state)
netif_carrier_on(net);
- return ret;
+ if (vf_netdev) {
+ /* Setting synthetic device up transparently sets
+ * slave as up. If open fails, then slave will be
+ * still be offline (and not used).
+ */
+ ret = dev_open(vf_netdev);
+ if (ret)
+ netdev_warn(net,
+ "unable to open slave: %s: %d\n",
+ vf_netdev->name, ret);
+ }
+ return 0;
}
static int netvsc_close(struct net_device *net)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
+ struct net_device *vf_netdev
+ = rtnl_dereference(net_device_ctx->vf_netdev);
struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
int ret;
u32 aread, i, msec = 10, retry = 0, retry_max = 20;
@@ -141,6 +157,9 @@ static int netvsc_close(struct net_device *net)
ret = -ETIMEDOUT;
}
+ if (vf_netdev)
+ dev_close(vf_netdev);
+
return ret;
}
@@ -224,13 +243,11 @@ static inline int netvsc_get_tx_queue(struct net_device *ndev,
*
* TODO support XPS - but get_xps_queue not exported
*/
-static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
- void *accel_priv, select_queue_fallback_t fallback)
+static u16 netvsc_pick_tx(struct net_device *ndev, struct sk_buff *skb)
{
- unsigned int num_tx_queues = ndev->real_num_tx_queues;
int q_idx = sk_tx_queue_get(skb->sk);
- if (q_idx < 0 || skb->ooo_okay) {
+ if (q_idx < 0 || skb->ooo_okay || q_idx >= ndev->real_num_tx_queues) {
/* If forwarding a packet, we use the recorded queue when
* available for better cache locality.
*/
@@ -240,12 +257,33 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
q_idx = netvsc_get_tx_queue(ndev, skb, q_idx);
}
- while (unlikely(q_idx >= num_tx_queues))
- q_idx -= num_tx_queues;
-
return q_idx;
}
+static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
+ void *accel_priv,
+ select_queue_fallback_t fallback)
+{
+ struct net_device_context *ndc = netdev_priv(ndev);
+ struct net_device *vf_netdev;
+ u16 txq;
+
+ rcu_read_lock();
+ vf_netdev = rcu_dereference(ndc->vf_netdev);
+ if (vf_netdev) {
+ txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0;
+ qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping;
+ } else {
+ txq = netvsc_pick_tx(ndev, skb);
+ }
+ rcu_read_unlock();
+
+ while (unlikely(txq >= ndev->real_num_tx_queues))
+ txq -= ndev->real_num_tx_queues;
+
+ return txq;
+}
+
static u32 fill_pg_buf(struct page *page, u32 offset, u32 len,
struct hv_page_buffer *pb)
{
@@ -367,6 +405,33 @@ static u32 net_checksum_info(struct sk_buff *skb)
return TRANSPORT_INFO_NOT_IP;
}
+/* Send skb on the slave VF device. */
+static int netvsc_vf_xmit(struct net_device *net, struct net_device *vf_netdev,
+ struct sk_buff *skb)
+{
+ struct net_device_context *ndev_ctx = netdev_priv(net);
+ unsigned int len = skb->len;
+ int rc;
+
+ skb->dev = vf_netdev;
+ skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping;
+
+ rc = dev_queue_xmit(skb);
+ if (likely(rc == NET_XMIT_SUCCESS || rc == NET_XMIT_CN)) {
+ struct netvsc_vf_pcpu_stats *pcpu_stats
+ = this_cpu_ptr(ndev_ctx->vf_stats);
+
+ u64_stats_update_begin(&pcpu_stats->syncp);
+ pcpu_stats->tx_packets++;
+ pcpu_stats->tx_bytes += len;
+ u64_stats_update_end(&pcpu_stats->syncp);
+ } else {
+ this_cpu_inc(ndev_ctx->vf_stats->tx_dropped);
+ }
+
+ return rc;
+}
+
static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
{
struct net_device_context *net_device_ctx = netdev_priv(net);
@@ -375,11 +440,20 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
unsigned int num_data_pgs;
struct rndis_message *rndis_msg;
struct rndis_packet *rndis_pkt;
+ struct net_device *vf_netdev;
u32 rndis_msg_size;
struct rndis_per_packet_info *ppi;
u32 hash;
struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT];
+ /* if VF is present and up then redirect packets
+ * already called with rcu_read_lock_bh
+ */
+ vf_netdev = rcu_dereference_bh(net_device_ctx->vf_netdev);
+ if (vf_netdev && netif_running(vf_netdev) &&
+ !netpoll_tx_running(net))
+ return netvsc_vf_xmit(net, vf_netdev, skb);
+
/* We will atmost need two pages to describe the rndis
* header. We can only transmit MAX_PAGE_BUFFER_COUNT number
* of pages in a single packet. If skb is scattered around
@@ -658,29 +732,18 @@ int netvsc_recv_callback(struct net_device *net,
struct netvsc_device *net_device;
u16 q_idx = channel->offermsg.offer.sub_channel_index;
struct netvsc_channel *nvchan;
- struct net_device *vf_netdev;
struct sk_buff *skb;
struct netvsc_stats *rx_stats;
if (net->reg_state != NETREG_REGISTERED)
return NVSP_STAT_FAIL;
- /*
- * If necessary, inject this packet into the VF interface.
- * On Hyper-V, multicast and brodcast packets are only delivered
- * to the synthetic interface (after subjecting these to
- * policy filters on the host). Deliver these via the VF
- * interface in the guest.
- */
rcu_read_lock();
net_device = rcu_dereference(net_device_ctx->nvdev);
if (unlikely(!net_device))
goto drop;
nvchan = &net_device->chan_table[q_idx];
- vf_netdev = rcu_dereference(net_device_ctx->vf_netdev);
- if (vf_netdev && (vf_netdev->flags & IFF_UP))
- net = vf_netdev;
/* Allocate a skb - TODO direct I/O to pages? */
skb = netvsc_alloc_recv_skb(net, &nvchan->napi,
@@ -692,8 +755,7 @@ int netvsc_recv_callback(struct net_device *net,
return NVSP_STAT_FAIL;
}
- if (net != vf_netdev)
- skb_record_rx_queue(skb, q_idx);
+ skb_record_rx_queue(skb, q_idx);
/*
* Even if injecting the packet, record the statistics
@@ -853,6 +915,7 @@ static int netvsc_set_link_ksettings(struct net_device *dev,
static int netvsc_change_mtu(struct net_device *ndev, int mtu)
{
struct net_device_context *ndevctx = netdev_priv(ndev);
+ struct net_device *vf_netdev = rtnl_dereference(ndevctx->vf_netdev);
struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev);
struct hv_device *hdev = ndevctx->device_ctx;
int orig_mtu = ndev->mtu;
@@ -863,6 +926,13 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
if (!nvdev || nvdev->destroy)
return -ENODEV;
+ /* Change MTU of underlying VF netdev first. */
+ if (vf_netdev) {
+ ret = dev_set_mtu(vf_netdev, mtu);
+ if (ret)
+ return ret;
+ }
+
netif_device_detach(ndev);
was_opened = rndis_filter_opened(nvdev);
if (was_opened)
@@ -883,6 +953,9 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
/* Attempt rollback to original MTU */
ndev->mtu = orig_mtu;
rndis_filter_device_add(hdev, &device_info);
+
+ if (vf_netdev)
+ dev_set_mtu(vf_netdev, orig_mtu);
}
if (was_opened)
@@ -896,16 +969,56 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
return ret;
}
+static void netvsc_get_vf_stats(struct net_device *net,
+ struct netvsc_vf_pcpu_stats *tot)
+{
+ struct net_device_context *ndev_ctx = netdev_priv(net);
+ int i;
+
+ memset(tot, 0, sizeof(*tot));
+
+ for_each_possible_cpu(i) {
+ const struct netvsc_vf_pcpu_stats *stats
+ = per_cpu_ptr(ndev_ctx->vf_stats, i);
+ u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
+ unsigned int start;
+
+ do {
+ start = u64_stats_fetch_begin_irq(&stats->syncp);
+ rx_packets = stats->rx_packets;
+ tx_packets = stats->tx_packets;
+ rx_bytes = stats->rx_bytes;
+ tx_bytes = stats->tx_bytes;
+ } while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+ tot->rx_packets += rx_packets;
+ tot->tx_packets += tx_packets;
+ tot->rx_bytes += rx_bytes;
+ tot->tx_bytes += tx_bytes;
+ tot->tx_dropped += stats->tx_dropped;
+ }
+}
+
static void netvsc_get_stats64(struct net_device *net,
struct rtnl_link_stats64 *t)
{
struct net_device_context *ndev_ctx = netdev_priv(net);
struct netvsc_device *nvdev = rcu_dereference_rtnl(ndev_ctx->nvdev);
- int i;
+ struct netvsc_vf_pcpu_stats vf_tot;
+ int i;
if (!nvdev)
return;
+ netdev_stats_to_stats64(t, &net->stats);
+
+ netvsc_get_vf_stats(net, &vf_tot);
+ t->rx_packets += vf_tot.rx_packets;
+ t->tx_packets += vf_tot.tx_packets;
+ t->rx_bytes += vf_tot.rx_bytes;
+ t->tx_bytes += vf_tot.tx_bytes;
+ t->tx_dropped += vf_tot.tx_dropped;
+
for (i = 0; i < nvdev->num_chn; i++) {
const struct netvsc_channel *nvchan = &nvdev->chan_table[i];
const struct netvsc_stats *stats;
@@ -934,12 +1047,6 @@ static void netvsc_get_stats64(struct net_device *net,
t->rx_packets += packets;
t->multicast += multicast;
}
-
- t->tx_dropped = net->stats.tx_dropped;
- t->tx_errors = net->stats.tx_errors;
-
- t->rx_dropped = net->stats.rx_dropped;
- t->rx_errors = net->stats.rx_errors;
}
static int netvsc_set_mac_addr(struct net_device *ndev, void *p)
@@ -980,9 +1087,16 @@ static const struct {
{ "tx_no_space", offsetof(struct netvsc_ethtool_stats, tx_no_space) },
{ "tx_too_big", offsetof(struct netvsc_ethtool_stats, tx_too_big) },
{ "tx_busy", offsetof(struct netvsc_ethtool_stats, tx_busy) },
+}, vf_stats[] = {
+ { "vf_rx_packets", offsetof(struct netvsc_vf_pcpu_stats, rx_packets) },
+ { "vf_rx_bytes", offsetof(struct netvsc_vf_pcpu_stats, rx_bytes) },
+ { "vf_tx_packets", offsetof(struct netvsc_vf_pcpu_stats, tx_packets) },
+ { "vf_tx_bytes", offsetof(struct netvsc_vf_pcpu_stats, tx_bytes) },
+ { "vf_tx_dropped", offsetof(struct netvsc_vf_pcpu_stats, tx_dropped) },
};
#define NETVSC_GLOBAL_STATS_LEN ARRAY_SIZE(netvsc_stats)
+#define NETVSC_VF_STATS_LEN ARRAY_SIZE(vf_stats)
/* 4 statistics per queue (rx/tx packets/bytes) */
#define NETVSC_QUEUE_STATS_LEN(dev) ((dev)->num_chn * 4)
@@ -997,7 +1111,9 @@ static int netvsc_get_sset_count(struct net_device *dev, int string_set)
switch (string_set) {
case ETH_SS_STATS:
- return NETVSC_GLOBAL_STATS_LEN + NETVSC_QUEUE_STATS_LEN(nvdev);
+ return NETVSC_GLOBAL_STATS_LEN
+ + NETVSC_VF_STATS_LEN
+ + NETVSC_QUEUE_STATS_LEN(nvdev);
default:
return -EINVAL;
}
@@ -1010,6 +1126,7 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
const void *nds = &ndc->eth_stats;
const struct netvsc_stats *qstats;
+ struct netvsc_vf_pcpu_stats sum;
unsigned int start;
u64 packets, bytes;
int i, j;
@@ -1020,6 +1137,10 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
for (i = 0; i < NETVSC_GLOBAL_STATS_LEN; i++)
data[i] = *(unsigned long *)(nds + netvsc_stats[i].offset);
+ netvsc_get_vf_stats(dev, &sum);
+ for (j = 0; j < NETVSC_VF_STATS_LEN; j++)
+ data[i++] = *(u64 *)((void *)&sum + vf_stats[j].offset);
+
for (j = 0; j < nvdev->num_chn; j++) {
qstats = &nvdev->chan_table[j].tx_stats;
@@ -1054,11 +1175,16 @@ static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
switch (stringset) {
case ETH_SS_STATS:
- for (i = 0; i < ARRAY_SIZE(netvsc_stats); i++)
- memcpy(p + i * ETH_GSTRING_LEN,
- netvsc_stats[i].name, ETH_GSTRING_LEN);
+ for (i = 0; i < ARRAY_SIZE(netvsc_stats); i++) {
+ memcpy(p, netvsc_stats[i].name, ETH_GSTRING_LEN);
+ p += ETH_GSTRING_LEN;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(vf_stats); i++) {
+ memcpy(p, vf_stats[i].name, ETH_GSTRING_LEN);
+ p += ETH_GSTRING_LEN;
+ }
- p += i * ETH_GSTRING_LEN;
for (i = 0; i < nvdev->num_chn; i++) {
sprintf(p, "tx_queue_%u_packets", i);
p += ETH_GSTRING_LEN;
@@ -1298,8 +1424,7 @@ static void netvsc_link_change(struct work_struct *w)
case RNDIS_STATUS_MEDIA_CONNECT:
if (rdev->link_state) {
rdev->link_state = false;
- if (!ndev_ctx->datapath)
- netif_carrier_on(net);
+ netif_carrier_on(net);
netif_tx_wake_all_queues(net);
} else {
notify = true;
@@ -1386,6 +1511,104 @@ static struct net_device *get_netvsc_byref(struct net_device *vf_netdev)
return NULL;
}
+/* Called when VF is injecting data into network stack.
+ * Change the associated network device from VF to netvsc.
+ * note: already called with rcu_read_lock
+ */
+static rx_handler_result_t netvsc_vf_handle_frame(struct sk_buff **pskb)
+{
+ struct sk_buff *skb = *pskb;
+ struct net_device *ndev = rcu_dereference(skb->dev->rx_handler_data);
+ struct net_device_context *ndev_ctx = netdev_priv(ndev);
+ struct netvsc_vf_pcpu_stats *pcpu_stats
+ = this_cpu_ptr(ndev_ctx->vf_stats);
+
+ skb->dev = ndev;
+
+ u64_stats_update_begin(&pcpu_stats->syncp);
+ pcpu_stats->rx_packets++;
+ pcpu_stats->rx_bytes += skb->len;
+ u64_stats_update_end(&pcpu_stats->syncp);
+
+ return RX_HANDLER_ANOTHER;
+}
+
+static int netvsc_vf_join(struct net_device *vf_netdev,
+ struct net_device *ndev)
+{
+ struct net_device_context *ndev_ctx = netdev_priv(ndev);
+ int ret;
+
+ ret = netdev_rx_handler_register(vf_netdev,
+ netvsc_vf_handle_frame, ndev);
+ if (ret != 0) {
+ netdev_err(vf_netdev,
+ "can not register netvsc VF receive handler (err = %d)\n",
+ ret);
+ goto rx_handler_failed;
+ }
+
+ ret = netdev_upper_dev_link(vf_netdev, ndev);
+ if (ret != 0) {
+ netdev_err(vf_netdev,
+ "can not set master device %s (err = %d)\n",
+ ndev->name, ret);
+ goto upper_link_failed;
+ }
+
+ /* set slave flag before open to prevent IPv6 addrconf */
+ vf_netdev->flags |= IFF_SLAVE;
+
+ schedule_work(&ndev_ctx->vf_takeover);
+
+ netdev_info(vf_netdev, "joined to %s\n", ndev->name);
+ return 0;
+
+upper_link_failed:
+ netdev_rx_handler_unregister(vf_netdev);
+rx_handler_failed:
+ return ret;
+}
+
+static void __netvsc_vf_setup(struct net_device *ndev,
+ struct net_device *vf_netdev)
+{
+ int ret;
+
+ call_netdevice_notifiers(NETDEV_JOIN, vf_netdev);
+
+ /* Align MTU of VF with master */
+ ret = dev_set_mtu(vf_netdev, ndev->mtu);
+ if (ret)
+ netdev_warn(vf_netdev,
+ "unable to change mtu to %u\n", ndev->mtu);
+
+ if (netif_running(ndev)) {
+ ret = dev_open(vf_netdev);
+ if (ret)
+ netdev_warn(vf_netdev,
+ "unable to open: %d\n", ret);
+ }
+}
+
+/* Setup VF as slave of the synthetic device.
+ * Runs in workqueue to avoid recursion in netlink callbacks.
+ */
+static void netvsc_vf_setup(struct work_struct *w)
+{
+ struct net_device_context *ndev_ctx
+ = container_of(w, struct net_device_context, vf_takeover);
+ struct net_device *ndev = hv_get_drvdata(ndev_ctx->device_ctx);
+ struct net_device *vf_netdev;
+
+ rtnl_lock();
+ vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
+ if (vf_netdev)
+ __netvsc_vf_setup(ndev, vf_netdev);
+
+ rtnl_unlock();
+}
+
static int netvsc_register_vf(struct net_device *vf_netdev)
{
struct net_device *ndev;
@@ -1409,10 +1632,12 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
if (!netvsc_dev || rtnl_dereference(net_device_ctx->vf_netdev))
return NOTIFY_DONE;
+ if (netvsc_vf_join(vf_netdev, ndev) != 0)
+ return NOTIFY_DONE;
+
netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
- /*
- * Take a reference on the module.
- */
+
+ /* Prevent this module from being unloaded while VF is registered */
try_module_get(THIS_MODULE);
dev_hold(vf_netdev);
@@ -1420,61 +1645,59 @@ static int netvsc_register_vf(struct net_device *vf_netdev)
return NOTIFY_OK;
}
-static int netvsc_vf_up(struct net_device *vf_netdev)
+/* Change datapath */
+static void netvsc_vf_update(struct work_struct *w)
{
- struct net_device *ndev;
+ struct net_device_context *ndev_ctx
+ = container_of(w, struct net_device_context, vf_notify);
+ struct net_device *ndev = hv_get_drvdata(ndev_ctx->device_ctx);
struct netvsc_device *netvsc_dev;
- struct net_device_context *net_device_ctx;
-
- ndev = get_netvsc_byref(vf_netdev);
- if (!ndev)
- return NOTIFY_DONE;
-
- net_device_ctx = netdev_priv(ndev);
- netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
-
- netdev_info(ndev, "VF up: %s\n", vf_netdev->name);
-
- /*
- * Open the device before switching data path.
- */
- rndis_filter_open(netvsc_dev);
-
- /*
- * notify the host to switch the data path.
- */
- netvsc_switch_datapath(ndev, true);
- netdev_info(ndev, "Data path switched to VF: %s\n", vf_netdev->name);
-
- netif_carrier_off(ndev);
+ struct net_device *vf_netdev;
+ bool vf_is_up;
- /* Now notify peers through VF device. */
- call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, vf_netdev);
+ rtnl_lock();
+ vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev);
+ if (!vf_netdev)
+ goto unlock;
+
+ netvsc_dev = rtnl_dereference(ndev_ctx->nvdev);
+ if (!netvsc_dev)
+ goto unlock;
+
+ vf_is_up = netif_running(vf_netdev);
+ if (vf_is_up != ndev_ctx->datapath) {
+ if (vf_is_up) {
+ netdev_info(ndev, "VF up: %s\n", vf_netdev->name);
+ rndis_filter_open(netvsc_dev);
+ netvsc_switch_datapath(ndev, true);
+ netdev_info(ndev, "Data path switched to VF: %s\n",
+ vf_netdev->name);
+ } else {
+ netdev_info(ndev, "VF down: %s\n", vf_netdev->name);
+ netvsc_switch_datapath(ndev, false);
+ rndis_filter_close(netvsc_dev);
+ netdev_info(ndev, "Data path switched from VF: %s\n",
+ vf_netdev->name);
+ }
- return NOTIFY_OK;
+ /* Now notify peers through VF device. */
+ call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, ndev);
+ }
+unlock:
+ rtnl_unlock();
}
-static int netvsc_vf_down(struct net_device *vf_netdev)
+static int netvsc_vf_notify(struct net_device *vf_netdev)
{
- struct net_device *ndev;
- struct netvsc_device *netvsc_dev;
struct net_device_context *net_device_ctx;
+ struct net_device *ndev;
ndev = get_netvsc_byref(vf_netdev);
if (!ndev)
return NOTIFY_DONE;
net_device_ctx = netdev_priv(ndev);
- netvsc_dev = rtnl_dereference(net_device_ctx->nvdev);
-
- netdev_info(ndev, "VF down: %s\n", vf_netdev->name);
- netvsc_switch_datapath(ndev, false);
- netdev_info(ndev, "Data path switched from VF: %s\n", vf_netdev->name);
- rndis_filter_close(netvsc_dev);
- netif_carrier_on(ndev);
-
- /* Now notify peers through netvsc device. */
- call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, ndev);
+ schedule_work(&net_device_ctx->vf_notify);
return NOTIFY_OK;
}
@@ -1489,9 +1712,12 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev)
return NOTIFY_DONE;
net_device_ctx = netdev_priv(ndev);
+ cancel_work_sync(&net_device_ctx->vf_takeover);
+ cancel_work_sync(&net_device_ctx->vf_notify);
netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name);
+ netdev_upper_dev_unlink(vf_netdev, ndev);
RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL);
dev_put(vf_netdev);
module_put(THIS_MODULE);
@@ -1505,12 +1731,12 @@ static int netvsc_probe(struct hv_device *dev,
struct net_device_context *net_device_ctx;
struct netvsc_device_info device_info;
struct netvsc_device *nvdev;
- int ret;
+ int ret = -ENOMEM;
net = alloc_etherdev_mq(sizeof(struct net_device_context),
VRSS_CHANNEL_MAX);
if (!net)
- return -ENOMEM;
+ goto no_net;
netif_carrier_off(net);
@@ -1529,6 +1755,13 @@ static int netvsc_probe(struct hv_device *dev,
spin_lock_init(&net_device_ctx->lock);
INIT_LIST_HEAD(&net_device_ctx->reconfig_events);
+ INIT_WORK(&net_device_ctx->vf_takeover, netvsc_vf_setup);
+ INIT_WORK(&net_device_ctx->vf_notify, netvsc_vf_update);
+
+ net_device_ctx->vf_stats
+ = netdev_alloc_pcpu_stats(struct netvsc_vf_pcpu_stats);
+ if (!net_device_ctx->vf_stats)
+ goto no_stats;
net->netdev_ops = &device_ops;
net->ethtool_ops = ðtool_ops;
@@ -1546,10 +1779,9 @@ static int netvsc_probe(struct hv_device *dev,
if (IS_ERR(nvdev)) {
ret = PTR_ERR(nvdev);
netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
- free_netdev(net);
- hv_set_drvdata(dev, NULL);
- return ret;
+ goto rndis_failed;
}
+
memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
/* hw_features computed in rndis_filter_device_add */
@@ -1573,11 +1805,20 @@ static int netvsc_probe(struct hv_device *dev,
ret = register_netdev(net);
if (ret != 0) {
pr_err("Unable to register netdev.\n");
- rndis_filter_device_remove(dev, nvdev);
- free_netdev(net);
+ goto register_failed;
}
return ret;
+
+register_failed:
+ rndis_filter_device_remove(dev, nvdev);
+rndis_failed:
+ free_percpu(net_device_ctx->vf_stats);
+no_stats:
+ hv_set_drvdata(dev, NULL);
+ free_netdev(net);
+no_net:
+ return ret;
}
static int netvsc_remove(struct hv_device *dev)
@@ -1611,6 +1852,7 @@ static int netvsc_remove(struct hv_device *dev)
hv_set_drvdata(dev, NULL);
+ free_percpu(ndev_ctx->vf_stats);
free_netdev(net);
return 0;
}
@@ -1665,9 +1907,8 @@ static int netvsc_netdev_event(struct notifier_block *this,
case NETDEV_UNREGISTER:
return netvsc_unregister_vf(event_dev);
case NETDEV_UP:
- return netvsc_vf_up(event_dev);
case NETDEV_DOWN:
- return netvsc_vf_down(event_dev);
+ return netvsc_vf_notify(event_dev);
default:
return NOTIFY_DONE;
}
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v3 2/3] netvsc: add documentation
From: Stephen Hemminger @ 2017-08-02 2:58 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, corbet; +Cc: devel, netdev, linux-doc
In-Reply-To: <20170802025855.11521-1-sthemmin@microsoft.com>
Add some background documentation on netvsc device options
and limitations.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
---
Documentation/networking/netvsc.txt | 63 +++++++++++++++++++++++++++++++++++++
MAINTAINERS | 1 +
2 files changed, 64 insertions(+)
create mode 100644 Documentation/networking/netvsc.txt
diff --git a/Documentation/networking/netvsc.txt b/Documentation/networking/netvsc.txt
new file mode 100644
index 000000000000..4ddb4e4b0426
--- /dev/null
+++ b/Documentation/networking/netvsc.txt
@@ -0,0 +1,63 @@
+Hyper-V network driver
+======================
+
+Compatibility
+=============
+
+This driver is compatible with Windows Server 2012 R2, 2016 and
+Windows 10.
+
+Features
+========
+
+ Checksum offload
+ ----------------
+ The netvsc driver supports checksum offload as long as the
+ Hyper-V host version does. Windows Server 2016 and Azure
+ support checksum offload for TCP and UDP for both IPv4 and
+ IPv6. Windows Server 2012 only supports checksum offload for TCP.
+
+ Receive Side Scaling
+ --------------------
+ Hyper-V supports receive side scaling. For TCP, packets are
+ distributed among available queues based on IP address and port
+ number. Current versions of Hyper-V host, only distribute UDP
+ packets based on the IP source and destination address.
+ The port number is not used as part of the hash value for UDP.
+ Fragmented IP packets are not distributed between queues;
+ all fragmented packets arrive on the first channel.
+
+ Generic Receive Offload, aka GRO
+ --------------------------------
+ The driver supports GRO and it is enabled by default. GRO coalesces
+ like packets and significantly reduces CPU usage under heavy Rx
+ load.
+
+ SR-IOV support
+ --------------
+ Hyper-V supports SR-IOV as a hardware acceleration option. If SR-IOV
+ is enabled in both the vSwitch and the guest configuration, then the
+ Virtual Function (VF) device is passed to the guest as a PCI
+ device. In this case, both a synthetic (netvsc) and VF device are
+ visible in the guest OS and both NIC's have the same MAC address.
+
+ The VF is enslaved by netvsc device. The netvsc driver will transparently
+ switch the data path to the VF when it is available and up.
+ Network state (addresses, firewall, etc) should be applied only to the
+ netvsc device; the slave device should not be accessed directly in
+ most cases. The exceptions are if some special queue discipline or
+ flow direction is desired, these should be applied directly to the
+ VF slave device.
+
+ Receive Buffer
+ --------------
+ Packets are received into a receive area which is created when device
+ is probed. The receive area is broken into MTU sized chunks and each may
+ contain one or more packets. The number of receive sections may be changed
+ via ethtool Rx ring parameters.
+
+ There is a similar send buffer which is used to aggregate packets for sending.
+ The send area is broken into chunks of 6144 bytes, each of section may
+ contain one or more packets. The send buffer is an optimization, the driver
+ will use slower method to handle very large packets or if the send buffer
+ area is exhausted.
diff --git a/MAINTAINERS b/MAINTAINERS
index 207e45310620..448f2f67802f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6258,6 +6258,7 @@ M: Haiyang Zhang <haiyangz@microsoft.com>
M: Stephen Hemminger <sthemmin@microsoft.com>
L: devel@linuxdriverproject.org
S: Maintained
+F: Documentation/networking/netvsc.txt
F: arch/x86/include/asm/mshyperv.h
F: arch/x86/include/uapi/asm/hyperv.h
F: arch/x86/kernel/cpu/mshyperv.c
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v3 3/3] netvsc: remove bonding setup script
From: Stephen Hemminger @ 2017-08-02 2:58 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, corbet; +Cc: devel, netdev, linux-doc
In-Reply-To: <20170802025855.11521-1-sthemmin@microsoft.com>
No longer needed, now all managed by transparent VF logic.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
---
tools/hv/bondvf.sh | 255 -----------------------------------------------------
1 file changed, 255 deletions(-)
delete mode 100755 tools/hv/bondvf.sh
diff --git a/tools/hv/bondvf.sh b/tools/hv/bondvf.sh
deleted file mode 100755
index 80f102860cf8..000000000000
--- a/tools/hv/bondvf.sh
+++ /dev/null
@@ -1,255 +0,0 @@
-#!/bin/bash
-
-# This example script creates bonding network devices based on synthetic NIC
-# (the virtual network adapter usually provided by Hyper-V) and the matching
-# VF NIC (SRIOV virtual function). So the synthetic NIC and VF NIC can
-# function as one network device, and fail over to the synthetic NIC if VF is
-# down.
-#
-# Usage:
-# - After configured vSwitch and vNIC with SRIOV, start Linux virtual
-# machine (VM)
-# - Run this scripts on the VM. It will create configuration files in
-# distro specific directory.
-# - Reboot the VM, so that the bonding config are enabled.
-#
-# The config files are DHCP by default. You may edit them if you need to change
-# to Static IP or change other settings.
-#
-
-sysdir=/sys/class/net
-netvsc_cls={f8615163-df3e-46c5-913f-f2d2f965ed0e}
-bondcnt=0
-
-# Detect Distro
-if [ -f /etc/redhat-release ];
-then
- cfgdir=/etc/sysconfig/network-scripts
- distro=redhat
-elif grep -q 'Ubuntu' /etc/issue
-then
- cfgdir=/etc/network
- distro=ubuntu
-elif grep -q 'SUSE' /etc/issue
-then
- cfgdir=/etc/sysconfig/network
- distro=suse
-else
- echo "Unsupported Distro"
- exit 1
-fi
-
-echo Detected Distro: $distro, or compatible
-
-# Get a list of ethernet names
-list_eth=(`cd $sysdir && ls -d */ | cut -d/ -f1 | grep -v bond`)
-eth_cnt=${#list_eth[@]}
-
-echo List of net devices:
-
-# Get the MAC addresses
-for (( i=0; i < $eth_cnt; i++ ))
-do
- list_mac[$i]=`cat $sysdir/${list_eth[$i]}/address`
- echo ${list_eth[$i]}, ${list_mac[$i]}
-done
-
-# Find NIC with matching MAC
-for (( i=0; i < $eth_cnt-1; i++ ))
-do
- for (( j=i+1; j < $eth_cnt; j++ ))
- do
- if [ "${list_mac[$i]}" = "${list_mac[$j]}" ]
- then
- list_match[$i]=${list_eth[$j]}
- break
- fi
- done
-done
-
-function create_eth_cfg_redhat {
- local fn=$cfgdir/ifcfg-$1
-
- rm -f $fn
- echo DEVICE=$1 >>$fn
- echo TYPE=Ethernet >>$fn
- echo BOOTPROTO=none >>$fn
- echo UUID=`uuidgen` >>$fn
- echo ONBOOT=yes >>$fn
- echo PEERDNS=yes >>$fn
- echo IPV6INIT=yes >>$fn
- echo MASTER=$2 >>$fn
- echo SLAVE=yes >>$fn
-}
-
-function create_eth_cfg_pri_redhat {
- create_eth_cfg_redhat $1 $2
-}
-
-function create_bond_cfg_redhat {
- local fn=$cfgdir/ifcfg-$1
-
- rm -f $fn
- echo DEVICE=$1 >>$fn
- echo TYPE=Bond >>$fn
- echo BOOTPROTO=dhcp >>$fn
- echo UUID=`uuidgen` >>$fn
- echo ONBOOT=yes >>$fn
- echo PEERDNS=yes >>$fn
- echo IPV6INIT=yes >>$fn
- echo BONDING_MASTER=yes >>$fn
- echo BONDING_OPTS=\"mode=active-backup miimon=100 primary=$2\" >>$fn
-}
-
-function del_eth_cfg_ubuntu {
- local mainfn=$cfgdir/interfaces
- local fnlist=( $mainfn )
-
- local dirlist=(`awk '/^[ \t]*source/{print $2}' $mainfn`)
-
- local i
- for i in "${dirlist[@]}"
- do
- fnlist+=(`ls $i 2>/dev/null`)
- done
-
- local tmpfl=$(mktemp)
-
- local nic_start='^[ \t]*(auto|iface|mapping|allow-.*)[ \t]+'$1
- local nic_end='^[ \t]*(auto|iface|mapping|allow-.*|source)'
-
- local fn
- for fn in "${fnlist[@]}"
- do
- awk "/$nic_end/{x=0} x{next} /$nic_start/{x=1;next} 1" \
- $fn >$tmpfl
-
- cp $tmpfl $fn
- done
-
- rm $tmpfl
-}
-
-function create_eth_cfg_ubuntu {
- local fn=$cfgdir/interfaces
-
- del_eth_cfg_ubuntu $1
- echo $'\n'auto $1 >>$fn
- echo iface $1 inet manual >>$fn
- echo bond-master $2 >>$fn
-}
-
-function create_eth_cfg_pri_ubuntu {
- local fn=$cfgdir/interfaces
-
- del_eth_cfg_ubuntu $1
- echo $'\n'allow-hotplug $1 >>$fn
- echo iface $1 inet manual >>$fn
- echo bond-master $2 >>$fn
- echo bond-primary $1 >>$fn
-}
-
-function create_bond_cfg_ubuntu {
- local fn=$cfgdir/interfaces
-
- del_eth_cfg_ubuntu $1
-
- echo $'\n'auto $1 >>$fn
- echo iface $1 inet dhcp >>$fn
- echo bond-mode active-backup >>$fn
- echo bond-miimon 100 >>$fn
- echo bond-slaves none >>$fn
-}
-
-function create_eth_cfg_suse {
- local fn=$cfgdir/ifcfg-$1
-
- rm -f $fn
- echo BOOTPROTO=none >>$fn
- echo STARTMODE=auto >>$fn
-}
-
-function create_eth_cfg_pri_suse {
- local fn=$cfgdir/ifcfg-$1
-
- rm -f $fn
- echo BOOTPROTO=none >>$fn
- echo STARTMODE=hotplug >>$fn
-}
-
-function create_bond_cfg_suse {
- local fn=$cfgdir/ifcfg-$1
-
- rm -f $fn
- echo BOOTPROTO=dhcp >>$fn
- echo STARTMODE=auto >>$fn
- echo BONDING_MASTER=yes >>$fn
- echo BONDING_SLAVE_0=$2 >>$fn
- echo BONDING_SLAVE_1=$3 >>$fn
- echo BONDING_MODULE_OPTS=\'mode=active-backup miimon=100 primary=$2\' >>$fn
-}
-
-function create_bond {
- local bondname=bond$bondcnt
- local primary
- local secondary
-
- local class_id1=`cat $sysdir/$1/device/class_id 2>/dev/null`
- local class_id2=`cat $sysdir/$2/device/class_id 2>/dev/null`
-
- if [ "$class_id1" = "$netvsc_cls" ]
- then
- primary=$2
- secondary=$1
- elif [ "$class_id2" = "$netvsc_cls" ]
- then
- primary=$1
- secondary=$2
- else
- return 0
- fi
-
- echo $'\nBond name:' $bondname
-
- if [ $distro == ubuntu ]
- then
- local mainfn=$cfgdir/interfaces
- local s="^[ \t]*(auto|iface|mapping|allow-.*)[ \t]+${bondname}"
-
- grep -E "$s" $mainfn
- if [ $? -eq 0 ]
- then
- echo "WARNING: ${bondname} has been configured already"
- return
- fi
- elif [ $distro == redhat ] || [ $distro == suse ]
- then
- local fn=$cfgdir/ifcfg-$bondname
- if [ -f $fn ]
- then
- echo "WARNING: ${bondname} has been configured already"
- return
- fi
- else
- echo "Unsupported Distro: ${distro}"
- return
- fi
-
- echo configuring $primary
- create_eth_cfg_pri_$distro $primary $bondname
-
- echo configuring $secondary
- create_eth_cfg_$distro $secondary $bondname
-
- echo creating: $bondname with primary slave: $primary
- create_bond_cfg_$distro $bondname $primary $secondary
-}
-
-for (( i=0; i < $eth_cnt-1; i++ ))
-do
- if [ -n "${list_match[$i]}" ]
- then
- create_bond ${list_eth[$i]} ${list_match[$i]}
- let bondcnt=bondcnt+1
- fi
-done
--
2.11.0
^ permalink raw reply related
* Re: [PATCH net 0/7] drivers: net: Fix 64-bit statistics seqcount init
From: David Miller @ 2017-08-02 3:06 UTC (permalink / raw)
To: f.fainelli; +Cc: netdev, edumazet
In-Reply-To: <20170801191113.8754-1-f.fainelli@gmail.com>
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 1 Aug 2017 12:11:05 -0700
> This patch series fixes a bunch of drivers to have their 64-bit statistics
> seqcount cookie be initialized correctly. Most of these drivers (except b44,
> gtp) are probably used on 64-bit only hosts and so the lockdep splat might have
> never been seen.
Series applied, thanks.
^ permalink raw reply
* Re: [PATCH net-next v2 00/11] net: dsa: rework EEE support
From: David Miller @ 2017-08-02 3:09 UTC (permalink / raw)
To: vivien.didelot; +Cc: netdev, linux-kernel, kernel, f.fainelli, andrew, john
In-Reply-To: <20170801203241.22294-1-vivien.didelot@savoirfairelinux.com>
From: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Date: Tue, 1 Aug 2017 16:32:30 -0400
> EEE implies configuring the port's PHY and MAC of both ends of the wire.
>
> The current EEE support in DSA mixes PHY and MAC configuration, which is
> bad because PHYs must be configured through a proper PHY driver. The DSA
> switch operations for EEE are only meant for configuring the port's MAC,
> which are integrated in the Ethernet switch device.
>
> This patchset fixes the EEE support in qca8k driver, makes the DSA layer
> call phy_init_eee for all drivers, and remove the EEE support from the
> mv88e6xxx driver since the Marvell PHY driver should be enough for it.
>
> Changes in v2:
> - make PHY device and DSA EEE ops mandatory for slave EEE operations.
> - simply return 0 in drivers which don't need to do anything to
> configure the port' MAC. Subsequent PHY calls will be enough.
Series applied, thanks Vivien.
^ permalink raw reply
* [PATCH v2 net-next 0/4] ulp: Generalize ULP infrastructure
From: Tom Herbert @ 2017-08-02 3:18 UTC (permalink / raw)
To: netdev; +Cc: rohit, davejwatson, Tom Herbert
Generalize the ULP infrastructure that was recently introduced to
support kTLS. This adds a SO_ULP socket option and creates new fields in
sock structure for ULP ops and ULP data. Also, the interface allows
additional per ULP parameters to be set so that a ULP can be pushed
and operations started in one shot.
This patch sets:
- Minor dependency fix in inet_common.h
- Implement ULP infrastructure as a socket mechanism
- Fixes TCP and TLS to use the new method (maintaining backwards
API compatibility)
- Adds a ulp.txt document
Tested: Ran simple ULP.
- v2: Fix compliation errors when CONFIG_ULP_SOCK not set.
Tom Herbert (4):
inet: include net/sock.h in inet_common.h
sock: ULP infrastructure
tcp: Adjust TCP ULP to defer to sockets ULP
ulp: Documention for ULP infrastructure
Documentation/networking/tls.txt | 6 +-
Documentation/networking/ulp.txt | 82 ++++++++++++++
arch/alpha/include/uapi/asm/socket.h | 2 +
arch/frv/include/uapi/asm/socket.h | 2 +
arch/ia64/include/uapi/asm/socket.h | 2 +
arch/m32r/include/uapi/asm/socket.h | 2 +
arch/mips/include/uapi/asm/socket.h | 2 +
arch/mn10300/include/uapi/asm/socket.h | 2 +
arch/parisc/include/uapi/asm/socket.h | 2 +
arch/s390/include/uapi/asm/socket.h | 2 +
arch/sparc/include/uapi/asm/socket.h | 2 +
arch/xtensa/include/uapi/asm/socket.h | 2 +
include/linux/socket.h | 9 ++
include/net/inet_common.h | 2 +
include/net/inet_connection_sock.h | 4 -
include/net/sock.h | 5 +
include/net/tcp.h | 25 -----
include/net/tls.h | 4 +-
include/net/ulp_sock.h | 75 +++++++++++++
include/uapi/asm-generic/socket.h | 2 +
net/Kconfig | 4 +
net/core/Makefile | 1 +
net/core/sock.c | 14 +++
net/core/sysctl_net_core.c | 25 +++++
net/core/ulp_sock.c | 194 +++++++++++++++++++++++++++++++++
net/ipv4/sysctl_net_ipv4.c | 9 +-
net/ipv4/tcp.c | 40 ++++---
net/ipv4/tcp_ipv4.c | 2 -
net/ipv4/tcp_ulp.c | 135 -----------------------
net/tls/Kconfig | 1 +
net/tls/tls_main.c | 21 ++--
31 files changed, 480 insertions(+), 200 deletions(-)
create mode 100644 Documentation/networking/ulp.txt
create mode 100644 include/net/ulp_sock.h
create mode 100644 net/core/ulp_sock.c
delete mode 100644 net/ipv4/tcp_ulp.c
--
2.11.0
^ permalink raw reply
* [PATCH v2 net-next 1/4] inet: include net/sock.h in inet_common.h
From: Tom Herbert @ 2017-08-02 3:18 UTC (permalink / raw)
To: netdev; +Cc: rohit, davejwatson, Tom Herbert
In-Reply-To: <20170802031846.21993-1-tom@quantonium.net>
inet_common.h has a dependency on sock.h so it should include that.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
include/net/inet_common.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index f39ae697347f..df0119a317aa 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -1,6 +1,8 @@
#ifndef _INET_COMMON_H
#define _INET_COMMON_H
+#include <net/sock.h>
+
extern const struct proto_ops inet_stream_ops;
extern const struct proto_ops inet_dgram_ops;
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 2/4] sock: ULP infrastructure
From: Tom Herbert @ 2017-08-02 3:18 UTC (permalink / raw)
To: netdev; +Cc: rohit, davejwatson, Tom Herbert
In-Reply-To: <20170802031846.21993-1-tom@quantonium.net>
Generalize the TCP ULP infrastructure recently introduced to support
kTLS. This adds a SO_ULP socket option and creates new fields in
sock structure for ULP ops and ULP data. Also, the interface allows
additional per ULP parameters to be set so that a ULP can be pushed
and operations started in one shot.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
arch/alpha/include/uapi/asm/socket.h | 2 +
arch/frv/include/uapi/asm/socket.h | 2 +
arch/ia64/include/uapi/asm/socket.h | 2 +
arch/m32r/include/uapi/asm/socket.h | 2 +
arch/mips/include/uapi/asm/socket.h | 2 +
arch/mn10300/include/uapi/asm/socket.h | 2 +
arch/parisc/include/uapi/asm/socket.h | 2 +
arch/s390/include/uapi/asm/socket.h | 2 +
arch/sparc/include/uapi/asm/socket.h | 2 +
arch/xtensa/include/uapi/asm/socket.h | 2 +
include/linux/socket.h | 9 ++
include/net/sock.h | 5 +
include/net/ulp_sock.h | 75 +++++++++++++
include/uapi/asm-generic/socket.h | 2 +
net/Kconfig | 4 +
net/core/Makefile | 1 +
net/core/sock.c | 14 +++
net/core/sysctl_net_core.c | 25 +++++
net/core/ulp_sock.c | 194 +++++++++++++++++++++++++++++++++
19 files changed, 349 insertions(+)
create mode 100644 include/net/ulp_sock.h
create mode 100644 net/core/ulp_sock.c
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 7b285dd4fe05..885e8fca79b0 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -109,4 +109,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
index f1e3b20dce9f..8ba71f2a3bf3 100644
--- a/arch/frv/include/uapi/asm/socket.h
+++ b/arch/frv/include/uapi/asm/socket.h
@@ -102,5 +102,7 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index 5dd5c5d0d642..2de1c53f88b5 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -111,4 +111,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h
index f8f7b47e247f..b2d394381787 100644
--- a/arch/m32r/include/uapi/asm/socket.h
+++ b/arch/m32r/include/uapi/asm/socket.h
@@ -102,4 +102,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 882823bec153..d0bdf8c78220 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -120,4 +120,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
index c710db354ff2..686fbf497a13 100644
--- a/arch/mn10300/include/uapi/asm/socket.h
+++ b/arch/mn10300/include/uapi/asm/socket.h
@@ -102,4 +102,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index a0d4dc9f4eb2..d6e99deca976 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -101,4 +101,6 @@
#define SO_PEERGROUPS 0x4034
+#define SO_ULP 0x4035
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index 52a63f4175cb..6b52f162369a 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -108,4 +108,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 186fd8199f54..e765bf781107 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -98,6 +98,8 @@
#define SO_PEERGROUPS 0x003d
+#define SO_ULP 0x003e
+
/* Security levels - as per NRL IPv6 - don't actually do anything */
#define SO_SECURITY_AUTHENTICATION 0x5001
#define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index 3eed2761c149..8eaa2e9e27b6 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -113,4 +113,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* _XTENSA_SOCKET_H */
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 8b13db5163cc..8f6e8c46a91e 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -156,6 +156,15 @@ struct ucred {
__u32 gid;
};
+/* ULP configuration for socket */
+
+#define ULP_NAME_MAX 16
+
+struct ulp_config {
+ char ulp_name[ULP_NAME_MAX];
+ __u8 ulp_params[0];
+};
+
/* Supported address families. */
#define AF_UNSPEC 0
#define AF_UNIX 1 /* Unix domain sockets */
diff --git a/include/net/sock.h b/include/net/sock.h
index 393c38e9f6aa..a1e5586aa767 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -72,6 +72,7 @@
#include <net/tcp_states.h>
#include <linux/net_tstamp.h>
#include <net/smc.h>
+#include <net/ulp_sock.h>
/*
* This structure really needs to be cleaned up.
@@ -312,6 +313,8 @@ struct sock_common {
* @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
* @sk_reuseport_cb: reuseport group container
* @sk_rcu: used during RCU grace period
+ * @sk_ulp_ops: pluggable ULP control hook
+ * @sk_ulp_data: ULP private data
*/
struct sock {
/*
@@ -415,6 +418,8 @@ struct sock {
unsigned int sk_gso_max_size;
gfp_t sk_allocation;
__u32 sk_txhash;
+ const struct ulp_ops *sk_ulp_ops;
+ void *sk_ulp_data;
/*
* Because of non atomicity rules, all
diff --git a/include/net/ulp_sock.h b/include/net/ulp_sock.h
new file mode 100644
index 000000000000..37bf4d2e16b9
--- /dev/null
+++ b/include/net/ulp_sock.h
@@ -0,0 +1,75 @@
+/*
+ * Pluggable upper layer protocol support in sockets.
+ *
+ * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved.
+ * Copyright (c) 2017, Tom Herbert <tom@quantonium.net>. All rights reserved.
+ *
+ */
+
+#ifndef __NET_ULP_SOCK_H
+#define __NET_ULP_SOCK_H
+
+#include <linux/socket.h>
+
+#define ULP_MAX 128
+#define ULP_BUF_MAX (ULP_NAME_MAX * ULP_MAX)
+
+struct ulp_ops {
+ struct list_head list;
+
+ /* initialize ulp */
+ int (*init)(struct sock *sk, char __user *optval, int len);
+
+ /* cleanup ulp */
+ void (*release)(struct sock *sk);
+
+ /* Get ULP specific parameters in getsockopt */
+ int (*get_params)(struct sock *sk, char __user *optval, int *optlen);
+
+ char name[ULP_NAME_MAX];
+ struct module *owner;
+};
+
+#ifdef CONFIG_ULP_SOCK
+
+int ulp_register(struct ulp_ops *type);
+void ulp_unregister(struct ulp_ops *type);
+int ulp_set(struct sock *sk, char __user *optval, int len);
+int ulp_get_config(struct sock *sk, char __user *optval, int *optlen);
+void ulp_get_available(char *buf, size_t len);
+void ulp_cleanup(struct sock *sk);
+
+#else
+
+static inline int ulp_register(struct ulp_ops *type)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void ulp_unregister(struct ulp_ops *type)
+{
+}
+
+static inline int ulp_set(struct sock *sk, char __user *optval, int len)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int ulp_get_config(struct sock *sk, char __user *optval,
+ int *optlen)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void ulp_get_available(char *buf, size_t len)
+{
+}
+
+static inline void ulp_cleanup(struct sock *sk)
+{
+}
+
+#endif
+
+#endif /* __NET_ULP_SOCK_H */
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 9861be8da65e..bf15ae98f3b2 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -104,4 +104,6 @@
#define SO_PEERGROUPS 59
+#define SO_ULP 60
+
#endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/net/Kconfig b/net/Kconfig
index 7d57ef34b79c..2b8d2d88bc2b 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -419,6 +419,10 @@ config GRO_CELLS
bool
default n
+config ULP_SOCK
+ bool
+ default n
+
config NET_DEVLINK
tristate "Network physical/parent device Netlink interface"
help
diff --git a/net/core/Makefile b/net/core/Makefile
index d501c4278015..fcfd29ef9926 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -28,3 +28,4 @@ obj-$(CONFIG_DST_CACHE) += dst_cache.o
obj-$(CONFIG_HWBM) += hwbm.o
obj-$(CONFIG_NET_DEVLINK) += devlink.o
obj-$(CONFIG_GRO_CELLS) += gro_cells.o
+obj-$(CONFIG_ULP_SOCK) += ulp_sock.o
diff --git a/net/core/sock.c b/net/core/sock.c
index 742f68c9c84a..cb03af11b536 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1055,6 +1055,11 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
if (val == 1)
dst_negative_advice(sk);
break;
+
+ case SO_ULP:
+ ret = ulp_set(sk, optval, optlen);
+ break;
+
default:
ret = -ENOPROTOOPT;
break;
@@ -1383,6 +1388,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val64 = sock_gen_cookie(sk);
break;
+ case SO_ULP:
+ return ulp_get_config(sk, optval, optlen);
+
default:
/* We implement the SO_SNDLOWAT etc to not be settable
* (1003.1g 7).
@@ -2943,6 +2951,12 @@ EXPORT_SYMBOL(compat_sock_common_setsockopt);
void sk_common_release(struct sock *sk)
{
+ /* Clean up ULP before destroying protocol socket since ULP might
+ * be dependent on transport (and not the other way around).
+ */
+
+ ulp_cleanup(sk);
+
if (sk->sk_prot->destroy)
sk->sk_prot->destroy(sk);
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index b7cd9aafe99e..9e14f91b57eb 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -21,6 +21,7 @@
#include <net/net_ratelimit.h>
#include <net/busy_poll.h>
#include <net/pkt_sched.h>
+#include <net/ulp_sock.h>
static int zero = 0;
static int one = 1;
@@ -249,6 +250,24 @@ static int proc_do_rss_key(struct ctl_table *table, int write,
return proc_dostring(&fake_table, write, buffer, lenp, ppos);
}
+static int proc_ulp_available(struct ctl_table *ctl,
+ int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ struct ctl_table tbl = { .maxlen = ULP_BUF_MAX, };
+ int ret;
+
+ tbl.data = kmalloc(tbl.maxlen, GFP_USER);
+ if (!tbl.data)
+ return -ENOMEM;
+ ulp_get_available(tbl.data, ULP_BUF_MAX);
+ ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+ kfree(tbl.data);
+
+ return ret;
+}
+
static struct ctl_table net_core_table[] = {
#ifdef CONFIG_NET
{
@@ -460,6 +479,12 @@ static struct ctl_table net_core_table[] = {
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
},
+ {
+ .procname = "ulp_available",
+ .maxlen = ULP_BUF_MAX,
+ .mode = 0444,
+ .proc_handler = proc_ulp_available,
+ },
{ }
};
diff --git a/net/core/ulp_sock.c b/net/core/ulp_sock.c
new file mode 100644
index 000000000000..0f49489b7eb6
--- /dev/null
+++ b/net/core/ulp_sock.c
@@ -0,0 +1,194 @@
+/*
+ * Pluggable upper layer protocol support in sockets.
+ *
+ * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved.
+ * Copyright (c) 2017, Tom Herbert <tom@quantonium.net>. All rights reserved.
+ *
+ */
+
+#include <linux/gfp.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <net/sock.h>
+#include <net/ulp_sock.h>
+
+static DEFINE_SPINLOCK(ulp_list_lock);
+static LIST_HEAD(ulp_list);
+
+/* Simple linear search, don't expect many entries! */
+static struct ulp_ops *ulp_find(const char *name)
+{
+ struct ulp_ops *e;
+
+ list_for_each_entry_rcu(e, &ulp_list, list) {
+ if (strcmp(e->name, name) == 0)
+ return e;
+ }
+
+ return NULL;
+}
+
+static const struct ulp_ops *__ulp_find_autoload(const char *name)
+{
+ const struct ulp_ops *ulp = NULL;
+
+ rcu_read_lock();
+ ulp = ulp_find(name);
+
+#ifdef CONFIG_MODULES
+ if (!ulp && capable(CAP_NET_ADMIN)) {
+ rcu_read_unlock();
+ request_module("%s", name);
+ rcu_read_lock();
+ ulp = ulp_find(name);
+ }
+#endif
+ if (!ulp || !try_module_get(ulp->owner))
+ ulp = NULL;
+
+ rcu_read_unlock();
+ return ulp;
+}
+
+/* Attach new upper layer protocol to the list
+ * of available protocols.
+ */
+int ulp_register(struct ulp_ops *ulp)
+{
+ int ret = 0;
+
+ spin_lock(&ulp_list_lock);
+ if (ulp_find(ulp->name)) {
+ pr_notice("%s already registered or non-unique name\n",
+ ulp->name);
+ ret = -EEXIST;
+ } else {
+ list_add_tail_rcu(&ulp->list, &ulp_list);
+ }
+ spin_unlock(&ulp_list_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ulp_register);
+
+void ulp_unregister(struct ulp_ops *ulp)
+{
+ spin_lock(&ulp_list_lock);
+ list_del_rcu(&ulp->list);
+ spin_unlock(&ulp_list_lock);
+
+ synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(ulp_unregister);
+
+/* Build string with list of available upper layer protocl values */
+void ulp_get_available(char *buf, size_t maxlen)
+{
+ struct ulp_ops *ulp_ops;
+ size_t offs = 0;
+
+ *buf = '\0';
+ rcu_read_lock();
+ list_for_each_entry_rcu(ulp_ops, &ulp_list, list) {
+ offs += snprintf(buf + offs, maxlen - offs,
+ "%s%s",
+ offs == 0 ? "" : " ", ulp_ops->name);
+ }
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(ulp_get_available);
+
+void ulp_cleanup(struct sock *sk)
+{
+ if (!sk->sk_ulp_ops)
+ return;
+
+ if (sk->sk_ulp_ops->release)
+ sk->sk_ulp_ops->release(sk);
+
+ module_put(sk->sk_ulp_ops->owner);
+}
+EXPORT_SYMBOL_GPL(ulp_cleanup);
+
+/* Change upper layer protocol for socket, Called from setsockopt. */
+int ulp_set(struct sock *sk, char __user *optval, int len)
+{
+ const struct ulp_ops *ulp_ops;
+ struct ulp_config ulpc;
+ int err = 0;
+
+ if (len < sizeof(ulpc))
+ return -EINVAL;
+
+ if (copy_from_user(&ulpc, optval, sizeof(ulpc)))
+ return -EFAULT;
+
+ if (sk->sk_ulp_ops)
+ return -EEXIST;
+
+ ulp_ops = __ulp_find_autoload(ulpc.ulp_name);
+ if (!ulp_ops)
+ return -ENOENT;
+
+ optval += sizeof(ulpc);
+ len -= sizeof(ulpc);
+
+ err = ulp_ops->init(sk, optval, len);
+ if (err)
+ return err;
+
+ sk->sk_ulp_ops = ulp_ops;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ulp_set);
+
+/* Get upper layer protocol for socket. Called from getsockopt. */
+int ulp_get_config(struct sock *sk, char __user *optval, int *optlen)
+{
+ struct ulp_config ulpc;
+ int len = *optlen;
+ int used_len;
+ int ret;
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+
+ if (len < sizeof(ulpc))
+ return -EINVAL;
+
+ if (!sk->sk_ulp_ops) {
+ if (put_user(0, optlen))
+ return -EFAULT;
+ return 0;
+ }
+
+ memcpy(ulpc.ulp_name, sk->sk_ulp_ops->name,
+ sizeof(ulpc.ulp_name));
+
+ if (copy_to_user(optval, &ulpc, sizeof(ulpc)))
+ return -EFAULT;
+
+ used_len = sizeof(ulpc);
+
+ if (sk->sk_ulp_ops->get_params) {
+ len -= sizeof(ulpc);
+ optval += sizeof(ulpc);
+
+ ret = sk->sk_ulp_ops->get_params(sk, optval, &len);
+ if (ret)
+ return ret;
+
+ used_len += len;
+ }
+
+ if (put_user(used_len, optlen))
+ return -EFAULT;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ulp_get_config);
+
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 3/4] tcp: Adjust TCP ULP to defer to sockets ULP
From: Tom Herbert @ 2017-08-02 3:18 UTC (permalink / raw)
To: netdev; +Cc: rohit, davejwatson, Tom Herbert
In-Reply-To: <20170802031846.21993-1-tom@quantonium.net>
Fix TCP and TLS to use the newer ULP infrastructure in sockets.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
Documentation/networking/tls.txt | 6 +-
include/net/inet_connection_sock.h | 4 --
include/net/tcp.h | 25 -------
include/net/tls.h | 4 +-
net/ipv4/sysctl_net_ipv4.c | 9 ++-
net/ipv4/tcp.c | 40 ++++++-----
net/ipv4/tcp_ipv4.c | 2 -
net/ipv4/tcp_ulp.c | 135 -------------------------------------
net/tls/Kconfig | 1 +
net/tls/tls_main.c | 21 +++---
10 files changed, 47 insertions(+), 200 deletions(-)
delete mode 100644 net/ipv4/tcp_ulp.c
diff --git a/Documentation/networking/tls.txt b/Documentation/networking/tls.txt
index 77ed00631c12..b70309df4709 100644
--- a/Documentation/networking/tls.txt
+++ b/Documentation/networking/tls.txt
@@ -12,8 +12,12 @@ Creating a TLS connection
First create a new TCP socket and set the TLS ULP.
+ struct ulp_config ulpc = {
+ .ulp_name = "tls",
+ };
+
sock = socket(AF_INET, SOCK_STREAM, 0);
- setsockopt(sock, SOL_TCP, TCP_ULP, "tls", sizeof("tls"));
+ setsockopt(sock, SOL_SOCKET, SO_ULP, &ulpc, sizeof(ulpc))
Setting the TLS ULP allows us to set/get TLS socket options. Currently
only the symmetric encryption is handled in the kernel. After the TLS
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 13e4c89a8231..c7a577976bec 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -75,8 +75,6 @@ struct inet_connection_sock_af_ops {
* @icsk_pmtu_cookie Last pmtu seen by socket
* @icsk_ca_ops Pluggable congestion control hook
* @icsk_af_ops Operations which are AF_INET{4,6} specific
- * @icsk_ulp_ops Pluggable ULP control hook
- * @icsk_ulp_data ULP private data
* @icsk_ca_state: Congestion control state
* @icsk_retransmits: Number of unrecovered [RTO] timeouts
* @icsk_pending: Scheduled timer event
@@ -99,8 +97,6 @@ struct inet_connection_sock {
__u32 icsk_pmtu_cookie;
const struct tcp_congestion_ops *icsk_ca_ops;
const struct inet_connection_sock_af_ops *icsk_af_ops;
- const struct tcp_ulp_ops *icsk_ulp_ops;
- void *icsk_ulp_data;
unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
__u8 icsk_ca_state:6,
icsk_ca_setsockopt:1,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index bb1881b4ce48..65c462da3740 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1968,31 +1968,6 @@ static inline void tcp_listendrop(const struct sock *sk)
enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer);
-/*
- * Interface for adding Upper Level Protocols over TCP
- */
-
-#define TCP_ULP_NAME_MAX 16
-#define TCP_ULP_MAX 128
-#define TCP_ULP_BUF_MAX (TCP_ULP_NAME_MAX*TCP_ULP_MAX)
-
-struct tcp_ulp_ops {
- struct list_head list;
-
- /* initialize ulp */
- int (*init)(struct sock *sk);
- /* cleanup ulp */
- void (*release)(struct sock *sk);
-
- char name[TCP_ULP_NAME_MAX];
- struct module *owner;
-};
-int tcp_register_ulp(struct tcp_ulp_ops *type);
-void tcp_unregister_ulp(struct tcp_ulp_ops *type);
-int tcp_set_ulp(struct sock *sk, const char *name);
-void tcp_get_available_ulp(char *buf, size_t len);
-void tcp_cleanup_ulp(struct sock *sk);
-
/* Call BPF_SOCK_OPS program that returns an int. If the return value
* is < 0, then the BPF op failed (for example if the loaded BPF
* program does not support the chosen operation or there is no BPF
diff --git a/include/net/tls.h b/include/net/tls.h
index b89d397dd62f..7d88a6e2f5a7 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -214,9 +214,7 @@ static inline void tls_fill_prepend(struct tls_context *ctx,
static inline struct tls_context *tls_get_ctx(const struct sock *sk)
{
- struct inet_connection_sock *icsk = inet_csk(sk);
-
- return icsk->icsk_ulp_data;
+ return sk->sk_ulp_data;
}
static inline struct tls_sw_context *tls_sw_ctx(
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 0d3c038d7b04..9ab0c278b7ba 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -21,6 +21,7 @@
#include <net/route.h>
#include <net/tcp.h>
#include <net/udp.h>
+#include <net/ulp_sock.h>
#include <net/cipso_ipv4.h>
#include <net/inet_frag.h>
#include <net/ping.h>
@@ -372,13 +373,15 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- struct ctl_table tbl = { .maxlen = TCP_ULP_BUF_MAX, };
+ struct ctl_table tbl = { .maxlen = ULP_BUF_MAX, };
int ret;
tbl.data = kmalloc(tbl.maxlen, GFP_USER);
if (!tbl.data)
return -ENOMEM;
- tcp_get_available_ulp(tbl.data, TCP_ULP_BUF_MAX);
+
+ /* Just return all ULPs for compatibility */
+ ulp_get_available(tbl.data, ULP_BUF_MAX);
ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
kfree(tbl.data);
@@ -709,7 +712,7 @@ static struct ctl_table ipv4_table[] = {
},
{
.procname = "tcp_available_ulp",
- .maxlen = TCP_ULP_BUF_MAX,
+ .maxlen = ULP_BUF_MAX,
.mode = 0444,
.proc_handler = proc_tcp_available_ulp,
},
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9dd6f4dba9b1..26f0d9821e6d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2404,24 +2404,24 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
release_sock(sk);
return err;
}
+
case TCP_ULP: {
- char name[TCP_ULP_NAME_MAX];
+ struct ulp_config ulpc;
if (optlen < 1)
return -EINVAL;
- val = strncpy_from_user(name, optval,
- min_t(long, TCP_ULP_NAME_MAX - 1,
+ val = strncpy_from_user(ulpc.ulp_name, optval,
+ min_t(long, ULP_NAME_MAX - 1,
optlen));
if (val < 0)
return -EFAULT;
- name[val] = 0;
+ ulpc.ulp_name[val] = 0;
- lock_sock(sk);
- err = tcp_set_ulp(sk, name);
- release_sock(sk);
- return err;
+ return kernel_setsockopt(sk->sk_socket, SOL_SOCKET, SO_ULP,
+ (char *)&ulpc, sizeof(ulpc));
}
+
default:
/* fallthru */
break;
@@ -2993,20 +2993,28 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
return -EFAULT;
return 0;
- case TCP_ULP:
+ case TCP_ULP: {
+ struct ulp_config ulpc;
+ int ulen, ret;
+
if (get_user(len, optlen))
return -EFAULT;
- len = min_t(unsigned int, len, TCP_ULP_NAME_MAX);
- if (!icsk->icsk_ulp_ops) {
- if (put_user(0, optlen))
- return -EFAULT;
- return 0;
- }
+ len = min_t(unsigned int, len, ULP_NAME_MAX);
+
+ ulen = sizeof(ulpc);
+
+ /* Backwards compatbility */
+ ret = kernel_getsockopt(sk->sk_socket, SOL_SOCKET, SO_ULP,
+ (char *)&ulpc, &ulen);
+ if (ret)
+ return ret;
+
if (put_user(len, optlen))
return -EFAULT;
- if (copy_to_user(optval, icsk->icsk_ulp_ops->name, len))
+ if (copy_to_user(optval, ulpc.ulp_name, len))
return -EFAULT;
return 0;
+ }
case TCP_THIN_LINEAR_TIMEOUTS:
val = tp->thin_lto;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 9b51663cd5a4..89fafd2c5d36 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1858,8 +1858,6 @@ void tcp_v4_destroy_sock(struct sock *sk)
tcp_cleanup_congestion_control(sk);
- tcp_cleanup_ulp(sk);
-
/* Cleanup up the write buffer. */
tcp_write_queue_purge(sk);
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
deleted file mode 100644
index 2417f55374c5..000000000000
--- a/net/ipv4/tcp_ulp.c
+++ /dev/null
@@ -1,135 +0,0 @@
-/*
- * Pluggable TCP upper layer protocol support.
- *
- * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved.
- *
- */
-
-#include<linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/gfp.h>
-#include <net/tcp.h>
-
-static DEFINE_SPINLOCK(tcp_ulp_list_lock);
-static LIST_HEAD(tcp_ulp_list);
-
-/* Simple linear search, don't expect many entries! */
-static struct tcp_ulp_ops *tcp_ulp_find(const char *name)
-{
- struct tcp_ulp_ops *e;
-
- list_for_each_entry_rcu(e, &tcp_ulp_list, list) {
- if (strcmp(e->name, name) == 0)
- return e;
- }
-
- return NULL;
-}
-
-static const struct tcp_ulp_ops *__tcp_ulp_find_autoload(const char *name)
-{
- const struct tcp_ulp_ops *ulp = NULL;
-
- rcu_read_lock();
- ulp = tcp_ulp_find(name);
-
-#ifdef CONFIG_MODULES
- if (!ulp && capable(CAP_NET_ADMIN)) {
- rcu_read_unlock();
- request_module("%s", name);
- rcu_read_lock();
- ulp = tcp_ulp_find(name);
- }
-#endif
- if (!ulp || !try_module_get(ulp->owner))
- ulp = NULL;
-
- rcu_read_unlock();
- return ulp;
-}
-
-/* Attach new upper layer protocol to the list
- * of available protocols.
- */
-int tcp_register_ulp(struct tcp_ulp_ops *ulp)
-{
- int ret = 0;
-
- spin_lock(&tcp_ulp_list_lock);
- if (tcp_ulp_find(ulp->name)) {
- pr_notice("%s already registered or non-unique name\n",
- ulp->name);
- ret = -EEXIST;
- } else {
- list_add_tail_rcu(&ulp->list, &tcp_ulp_list);
- }
- spin_unlock(&tcp_ulp_list_lock);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(tcp_register_ulp);
-
-void tcp_unregister_ulp(struct tcp_ulp_ops *ulp)
-{
- spin_lock(&tcp_ulp_list_lock);
- list_del_rcu(&ulp->list);
- spin_unlock(&tcp_ulp_list_lock);
-
- synchronize_rcu();
-}
-EXPORT_SYMBOL_GPL(tcp_unregister_ulp);
-
-/* Build string with list of available upper layer protocl values */
-void tcp_get_available_ulp(char *buf, size_t maxlen)
-{
- struct tcp_ulp_ops *ulp_ops;
- size_t offs = 0;
-
- *buf = '\0';
- rcu_read_lock();
- list_for_each_entry_rcu(ulp_ops, &tcp_ulp_list, list) {
- offs += snprintf(buf + offs, maxlen - offs,
- "%s%s",
- offs == 0 ? "" : " ", ulp_ops->name);
- }
- rcu_read_unlock();
-}
-
-void tcp_cleanup_ulp(struct sock *sk)
-{
- struct inet_connection_sock *icsk = inet_csk(sk);
-
- if (!icsk->icsk_ulp_ops)
- return;
-
- if (icsk->icsk_ulp_ops->release)
- icsk->icsk_ulp_ops->release(sk);
- module_put(icsk->icsk_ulp_ops->owner);
-}
-
-/* Change upper layer protocol for socket */
-int tcp_set_ulp(struct sock *sk, const char *name)
-{
- struct inet_connection_sock *icsk = inet_csk(sk);
- const struct tcp_ulp_ops *ulp_ops;
- int err = 0;
-
- if (icsk->icsk_ulp_ops)
- return -EEXIST;
-
- ulp_ops = __tcp_ulp_find_autoload(name);
- if (!ulp_ops)
- err = -ENOENT;
- else
- err = ulp_ops->init(sk);
-
- if (err)
- goto out;
-
- icsk->icsk_ulp_ops = ulp_ops;
- out:
- return err;
-}
diff --git a/net/tls/Kconfig b/net/tls/Kconfig
index eb583038c67e..60ae4e9b257e 100644
--- a/net/tls/Kconfig
+++ b/net/tls/Kconfig
@@ -7,6 +7,7 @@ config TLS
select CRYPTO
select CRYPTO_AES
select CRYPTO_GCM
+ select ULP_SOCK
default n
---help---
Enable kernel support for TLS protocol. This allows symmetric
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 60aff60e30ad..00ccbec96820 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -31,15 +31,15 @@
* SOFTWARE.
*/
-#include <linux/module.h>
-
-#include <net/tcp.h>
-#include <net/inet_common.h>
#include <linux/highmem.h>
+#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/sched/signal.h>
-
+#include <net/inet_common.h>
+#include <net/sock.h>
+#include <net/tcp.h>
#include <net/tls.h>
+#include <net/ulp_sock.h>
MODULE_AUTHOR("Mellanox Technologies");
MODULE_DESCRIPTION("Transport Layer Security Support");
@@ -438,9 +438,8 @@ static int tls_setsockopt(struct sock *sk, int level, int optname,
return do_tls_setsockopt(sk, optname, optval, optlen);
}
-static int tls_init(struct sock *sk)
+static int tls_init(struct sock *sk, char __user *optval, int len)
{
- struct inet_connection_sock *icsk = inet_csk(sk);
struct tls_context *ctx;
int rc = 0;
@@ -450,7 +449,7 @@ static int tls_init(struct sock *sk)
rc = -ENOMEM;
goto out;
}
- icsk->icsk_ulp_data = ctx;
+ sk->sk_ulp_data = ctx;
ctx->setsockopt = sk->sk_prot->setsockopt;
ctx->getsockopt = sk->sk_prot->getsockopt;
sk->sk_prot = &tls_base_prot;
@@ -458,7 +457,7 @@ static int tls_init(struct sock *sk)
return rc;
}
-static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = {
+static struct ulp_ops ulp_tls_ops __read_mostly = {
.name = "tls",
.owner = THIS_MODULE,
.init = tls_init,
@@ -475,14 +474,14 @@ static int __init tls_register(void)
tls_sw_prot.sendpage = tls_sw_sendpage;
tls_sw_prot.close = tls_sk_proto_close;
- tcp_register_ulp(&tcp_tls_ulp_ops);
+ ulp_register(&ulp_tls_ops);
return 0;
}
static void __exit tls_unregister(void)
{
- tcp_unregister_ulp(&tcp_tls_ulp_ops);
+ ulp_unregister(&ulp_tls_ops);
}
module_init(tls_register);
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 4/4] ulp: Documention for ULP infrastructure
From: Tom Herbert @ 2017-08-02 3:18 UTC (permalink / raw)
To: netdev; +Cc: rohit, davejwatson, Tom Herbert
In-Reply-To: <20170802031846.21993-1-tom@quantonium.net>
Add a doc in Documentation/networking
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
Documentation/networking/ulp.txt | 82 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 82 insertions(+)
create mode 100644 Documentation/networking/ulp.txt
diff --git a/Documentation/networking/ulp.txt b/Documentation/networking/ulp.txt
new file mode 100644
index 000000000000..4d830314b0ff
--- /dev/null
+++ b/Documentation/networking/ulp.txt
@@ -0,0 +1,82 @@
+Upper Layer Protocol (ULP) Infrastructure
+=========================================
+
+The ULP kernel infrastructure provides a means to hook upper layer
+protocol support on a socket. A module may register a ULP hook
+in the kernel. ULP processing is enabled by a setsockopt on a socket
+that specifies the name of the registered ULP to invoked. An
+initialization function is defined for each ULP that can change the
+function entry points of the socket (sendmsg, rcvmsg, etc.) or change
+the socket in other fundamental ways.
+
+Note, no synchronization is enforced between the setsockopt to enable
+a ULP and ongoing asynchronous operations on the socket (such as a
+blocked read). If synchronization is required this must be handled by
+the ULP and caller.
+
+User interface
+==============
+
+The structure for the socket SOL_ULP options is defined in socket.h.
+
+Example to enable "my_ulp" ULP on a socket:
+
+struct ulp_config ulpc = {
+ .ulp_name = "my_ulp",
+};
+
+setsockopt(sock, SOL_SOCKET, SO_ULP, &ulpc, sizeof(ulpc))
+
+The ulp_config includes a "__u8 ulp_params[0]" filled that may be used
+to refer ULP specific parameters being set.
+
+Kernel interface
+================
+
+The interface for ULP infrastructure is defined in net/ulp_sock.h.
+
+ULP registration functions
+--------------------------
+
+int ulp_register(struct ulp_ops *type)
+
+ Called to register a ULP. The ulp_ops structure is described below.
+
+void ulp_unregister(struct ulp_ops *type);
+
+ Called to unregister a ULP.
+
+ulp_ops structure
+-----------------
+
+int (*init)(struct sock *sk, char __user *optval, int len)
+
+ Initialization function for the ULP. This is called from setsockopt
+ when the ULP name in the ulp_config argument matches the registered
+ ULP. optval is a userspace pointer to the ULP specific parameters.
+ len is the length of the ULP specific parameters.
+
+void (*release)(struct sock *sk)
+
+ Called when socket is being destroyed. The ULP implementation
+ should cancel any asynchronous operations (such as timers) and
+ release any acquired resources.
+
+int (*get_params)(struct sock *sk, char __user *optval, int *optlen)
+
+ Get the ULP specific parameters previous set in the init function
+ for the ULP. Note that optlen is a pointer to kernel memory.
+
+char name[ULP_NAME_MAX]
+
+ Name of the ULP. Must be NULL terminated.
+
+struct module *owner
+
+ Corresponding owner for ref count.
+
+Author
+======
+
+Tom Herbert (tom@quantonium.net)
+
--
2.11.0
^ permalink raw reply related
* Re: [PATCH 1/2] [for 4.13] net: qcom/emac: disable flow control autonegotiation by default
From: Timur Tabi @ 2017-08-02 3:22 UTC (permalink / raw)
To: Andrew Lunn; +Cc: David S. Miller, netdev
In-Reply-To: <20170802025847.GB8415@lunn.ch>
On 8/1/17 9:58 PM, Andrew Lunn wrote:
> The PHY does not participate directly in flow control/pause frames except by
> making sure that the SUPPORTED_Pause and SUPPORTED_AsymPause bits are set in
> MII_ADVERTISE to indicate towards the link partner that the Ethernet MAC
> controller supports such a thing. Since flow control/pause frames generation
> involves the Ethernet MAC driver, it is recommended that this driver takes care
> of properly indicating advertisement and support for such features by setting
> the SUPPORTED_Pause and SUPPORTED_AsymPause bits accordingly. This can be done
> either before or after phy_connect() and/or as a result of implementing the
> ethtool::set_pauseparam feature.
>
> So just check if the MAC driver is setting SUPPORTED_Pause and
> SUPPORTED_AsymPause.
I think this was covered in this thread:
http://www.spinics.net/lists/netdev/msg408978.html
--
Sent by an employee of the Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of the
Code Aurora Forum, hosted by The Linux Foundation.
^ permalink raw reply
* (unknown),
From: helga.brickl @ 2017-08-02 3:45 UTC (permalink / raw)
To: netdev
[-- Attachment #1: EMAIL_2820973694253_netdev.zip --]
[-- Type: application/zip, Size: 2772 bytes --]
^ permalink raw reply
* Re: Extremely important and Urgent
From: Singer Valve @ 2017-08-02 3:46 UTC (permalink / raw)
To: Recipients
I am getting in touch with you regarding an extremely important and urgent matter.
If you would oblige me the opportunity, I shall provide you with details upon your response.
Faithfully,
Ms. Singer Valve
^ permalink raw reply
* Re: [PATCH v2 05/11] net: stmmac: dwmac-rk: Add internal phy support
From: Chen-Yu Tsai @ 2017-08-02 3:46 UTC (permalink / raw)
To: David.Wu
Cc: Florian Fainelli, Andrew Lunn, Mark Rutland, Tao Huang,
hwg-TNX95d0MmH7DzftRWevZcw, Heiko Stübner, Arnd Bergmann,
devicetree, Catalin Marinas, Will Deacon, Russell King,
linux-kernel, open list:ARM/Rockchip SoC..., Rob Herring, netdev,
Olof Johansson, Giuseppe Cavallaro, David Miller,
linux-arm-kernel
In-Reply-To: <69ad9443-ff65-8e49-df68-7e5e6c812d45-TNX95d0MmH7DzftRWevZcw@public.gmane.org>
Hi David, Florian, Andrew
(resent in plain text)
On Fri, Jul 28, 2017 at 2:56 PM, David.Wu <david.wu-TNX95d0MmH7DzftRWevZcw@public.gmane.org> wrote:
>
> Hi Florian,
>
> 在 2017/7/28 0:54, Florian Fainelli 写道:
>>
>> - if you need knowledge about this PHY connection type prior to binding
>> the PHY device and its driver (that is, before of_phy_connect()) we
>> could add a boolean property e.g: "phy-is-internal" that allows us to
>> know that, or we can have a new phy-mode value, e.g: "internal-rmii"
>> which describes that, either way would probably be fine, but the former
>> scales better
>>
>
> Using "phy-is-internal" is very helpful, but it is easy to confuse with
> the real internal PHY, may we use the other words like phy is inlined.
If "internal" is confusing, would "phy-is-integrated" in the MAC node work?
Either way we would like to have a definitive solution to this. Our
dwmac-sun8i driver is already in v4.13-rc1, with a somewhat flaky
method of knowing whether the internal PHY is used (phy-mode = "mii").
We really want a fix for this release, otherwise we would be force
to revert either the internal PHY part or the whole driver.
ChenYu
>
>> Then again, using phy-mode = "internal" even though this is Reduced MII
>> is not big of a deal IMHO as long as there is no loss of information and
>> that internal de-facto means internal reduced MII for instance.
>> --
>
>
>
> _______________________________________________
> linux-arm-kernel mailing list
> linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org
> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
--
To unsubscribe from this list: send the line "unsubscribe devicetree" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: repost: af_packet vs virtio (was packed ring layout proposal v2)
From: Steven Luong @ 2017-08-02 3:54 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: john.fastabend, alexei.starovoitov, netdev, virtio-dev,
virtualization, kvm
In-Reply-To: <20170414054318-mutt-send-email-mst@kernel.org>
[-- Attachment #1: Type: text/plain, Size: 8689 bytes --]
Michael,
I have a question on s/g
On Thu, Apr 13, 2017 at 7:50 PM, Michael S. Tsirkin <mst@redhat.com> wrote:
> On Fri, Apr 14, 2017 at 05:42:58AM +0300, Michael S. Tsirkin wrote:
> > Hi all, I wanted to raise the question of similarities between virtio
> > and new zero copy af_packet interfaces.
> >
> > First I would like to mention that virtio device development isn't spec
> > limited - spec is there to help interoperability and add peace of mind
> > for people worried about IPR.
> >
> > So I tend to accept patches without requiring people write it up in the
> > spec as work on spec proceeds at its own pace - all I ask is that the
> > virtio mailing list is copied, this requires contributor to subscribe
> > and in the process contributor promises that it's ok for us to add this
> > to spec in the future.
> >
> > There shouldn't thus be a fundamental problem preventing use of virtio
> > format or reusing some of the code for af_packet, but it still might or
> > might not make sense - it was designed for CPU to CPU communication so
> > it seems to make sense though. So I would like that discussion to
> > happen even if we decide against.
> >
> > And even if people decide against, the problem space is very similar.
> You
> > can look up packed ring layout proposal v2 - should I repost here? Our
> > prototyping shows significant performance improvements from using it as
> > compared to head/tail layout.
> >
> > To start this discission I'm going to reply to this email reposting a
> > copy of the simplified virtio layout that might be appropriate for
> > af_packet as well.
>
> Here's the repost (slightly cut down) sorry about the duplicates.
>
> The idea is to have a r/w descriptor in a ring structure,
> replacing the used and available ring, index and descriptor
> buffer.
>
> * Descriptor ring:
>
> Guest adds descriptors with unique index values and DESC_HW set in flags.
> Host overwrites used descriptors with correct len, index, and DESC_HW
> clear. Flags are always set/cleared last.
>
> #define DESC_HW 0x0080
>
> struct desc {
> __le64 addr;
> __le32 len;
> __le16 index;
> __le16 flags;
> };
>
> When DESC_HW is set, descriptor belongs to device. When it is clear,
> it belongs to the driver.
>
> We can use 1 bit to set direction
> /* This marks a buffer as write-only (otherwise read-only). */
> #define VRING_DESC_F_WRITE 2
>
> * Scatter/gather support
>
> We can use 1 bit to chain s/g entries in a request, same as virtio 1.0:
>
> /* This marks a buffer as continuing via the next field. */
>
This comment here is confusing to me. In 1.0, virtq_desc has the next
field. When the flag VRING_DESC_F_NEXT is set, the next entry to continue
is specified in the next field.
Here in 1.1, struct desc does not have the next field, only addr, len,
index, and flags. So when VRING_DESC_F_NEXT is set in struct desc's flags
field, where is the next entry to continue the current descriptor, the
entry immediately following the current entry? ie, if the current entry is
at index 10 in the descriptor table and its flags is set for
VRING_DESC_F_NEXT, is the entry continuing the current entry in index 11?
Steven
> #define VRING_DESC_F_NEXT 1
>
> Unlike virtio 1.0, all descriptors must have distinct ID values.
>
> Also unlike virtio 1.0, use of this flag will be an optional feature
> (e.g. VIRTIO_F_DESC_NEXT) so both devices and drivers can opt out of it.
>
> * Indirect buffers
>
> Can be marked like in virtio 1.0:
>
> /* This means the buffer contains a table of buffer descriptors. */
> #define VRING_DESC_F_INDIRECT 4
>
> Unlike virtio 1.0, this is a table, not a list:
> struct indirect_descriptor_table {
> /* The actual descriptors (16 bytes each) */
> struct virtq_desc desc[len / 16];
> };
>
> The first descriptor is located at start of the indirect descriptor
> table, additional indirect descriptors come immediately afterwards.
> DESC_F_WRITE is the only valid flag for descriptors in the indirect
> table. Others should be set to 0 and are ignored. id is also set to 0
> and should be ignored.
>
> virtio 1.0 seems to allow a s/g entry followed by
> an indirect descriptor. This does not seem useful,
> so we do not allow that anymore.
>
> This support would be an optional feature, same as in virtio 1.0
>
> * Batching descriptors:
>
> virtio 1.0 allows passing a batch of descriptors in both directions, by
> incrementing the used/avail index by values > 1. We can support this by
> chaining a list of descriptors through a bit the flags field.
> To allow use together with s/g, a different bit will be used.
>
> #define VRING_DESC_F_BATCH_NEXT 0x0010
>
> Batching works for both driver and device descriptors.
>
>
>
> * Processing descriptors in and out of order
>
> Device processing all descriptors in order can simply flip
> the DESC_HW bit as it is done with descriptors.
>
> Device can write descriptors out in order as they are used, overwriting
> descriptors that are there.
>
> Device must not use a descriptor until DESC_HW is set.
> It is only required to look at the first descriptor
> submitted.
>
> Driver must not overwrite a descriptor until DESC_HW is clear.
> It is only required to look at the first descriptor
> submitted.
>
> * Device specific descriptor flags
> We have a lot of unused space in the descriptor. This can be put to
> good use by reserving some flag bits for device use.
> For example, network device can set a bit to request
> that header in the descriptor is suppressed
> (in case it's all 0s anyway). This reduces cache utilization.
>
> Note: this feature can be supported in virtio 1.0 as well,
> as we have unused bits in both descriptor and used ring there.
>
> * Descriptor length in device descriptors
>
> virtio 1.0 places strict requirements on descriptor length. For example
> it must be 0 in used ring of TX VQ of a network device since nothing is
> written. In practice guests do not seem to use this, so we can simplify
> devices a bit by removing this requirement - if length is unused it
> should be ignored by driver.
>
> Some devices use identically-sized buffers in all descriptors.
> Ignoring length for driver descriptors there could be an option too.
>
> * Writing at an offset
>
> Some devices might want to write into some descriptors
> at an offset, the offset would be in config space,
> and a descriptor flag could indicate this:
>
> #define VRING_DESC_F_OFFSET 0x0020
>
> How exactly to use the offset would be device specific,
> for example it can be used to align beginning of packet
> in the 1st buffer for mergeable buffers to cache line boundary
> while also aligning rest of buffers.
>
> * Non power-of-2 ring sizes
>
> As the ring simply wraps around, there's no reason to
> require ring size to be power of two.
> It can be made a separate feature though.
>
>
> * Interrupt/event suppression
>
> virtio 1.0 has two mechanisms for suppression but only
> one can be used at a time. we pack them together
> in a structure - one for interrupts, one for notifications:
>
> struct event {
> __le16 idx;
> __le16 flags;
> }
>
> Both fields would be optional, with a feature bit:
> VIRTIO_F_EVENT_IDX
> VIRTIO_F_EVENT_FLAGS
>
> * Flags can be used like in virtio 1.0, by storing a special
> value there:
>
> #define VRING_F_EVENT_ENABLE 0x0
>
> #define VRING_F_EVENT_DISABLE 0x1
>
> * Event index would be in the range 0 to 2 * Queue Size
> (to detect wrap arounds) and wrap to 0 after that.
>
> The assumption is that each side maintains an internal
> descriptor counter 0 to 2 * Queue Size that wraps to 0.
> In that case, interrupt triggers when counter reaches
> the given value.
>
> * If both features are negotiated, a special flags value
> can be used to switch to event idx:
>
> #define VRING_F_EVENT_IDX 0x2
>
>
> * Prototype
>
> A partial prototype can be found under
> tools/virtio/ringtest/ring.c
>
> Test run:
> [mst@tuck ringtest]$ time ./ring
> real 0m0.399s
> user 0m0.791s
> sys 0m0.000s
> [mst@tuck ringtest]$ time ./virtio_ring_0_9
> real 0m0.503s
> user 0m0.999s
> sys 0m0.000s
>
> This seems to match the theoretical analysis showing marking
> descriptors themselves as invalid works better than a head/tail design.
> Future changes and enhancements can be tested against this prototype.
>
> A dpdk based implementation can be found here:
>
> git://dpdk.org/next/dpdk-next-virtio for-testing
>
>
>
> --
> MST
>
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: virtio-dev-unsubscribe@lists.oasis-open.org
> For additional commands, e-mail: virtio-dev-help@lists.oasis-open.org
>
>
[-- Attachment #2: Type: text/html, Size: 10435 bytes --]
^ permalink raw reply
* (unknown),
From: системы администратор @ 2017-08-02 3:47 UTC (permalink / raw)
внимания;
Ваши сообщения превысил лимит памяти, который составляет 5 Гб, определенных администратором, который в настоящее время работает на 10.9GB, Вы не сможете отправить или получить новую почту, пока вы повторно не проверить ваш почтовый ящик почты. Чтобы восстановить работоспособность Вашего почтового ящика, отправьте следующую информацию ниже:
имя:
Имя пользователя:
пароль:
Подтверждение пароля:
Адрес электронной почты:
телефон:
Если вы не в состоянии перепроверить сообщения, ваш почтовый ящик будет отключен!
Приносим извинения за неудобства.
Проверочный код: EN: Ru...776774990..2017
Почты технической поддержки ©2017
спасибо
системы администратор
^ permalink raw reply
* [PATCH] Adding Agile-SD TCP module and modifying Kconfig and Makefile
From: mohamedalrshah @ 2017-08-02 4:37 UTC (permalink / raw)
To: davem; +Cc: netdev, torvalds, linux-kernel, mohamed.a.alrshah
In-Reply-To: <stephen@networkplumber.org>
Published:
Alrshah, M.A., Othman, M., Ali, B. and Hanapi, Z.M., 2015. Agile-SD: a Linux-based
TCP congestion control algorithm for supporting high-speed and short-distance networks.
Journal of Network and Computer Applications, 55, pp.181-190.
Agile-SD is a new loss-based and RTT-independent TCP congestion
control algorithm designed to support high-speed and Short-Distance (SD)
networks. It mainly contributes the agility factor mechanism, which allows
Agile-SD to deal with small buffer sizes while reducing its sensitivity to
packet loss. Due to the use of this mechanism, Agile-SD improves the
throughput of TCP up to 50% compared to Cubic-TCP and Compound-TCP. Its
performance was evaluated using the well-known NS2 simulator to measure
the average throughput, loss ratio and fairness.
Agile-SD is designed and implemented by Mohamed A. Alrshah et al. (2015) as
a Linux kernel module in the real Linux operating system (openSUSE 42.1 Leap),
which is implemented at the Network, Parallel and Distributed Computing Laboratory,
A2.10, second floor, Block A, Faculty of Computer Science and Information Technology,
Universiti Putra Malaysia, over real PCs connected to the Internet for daily uses and
evaluation purposes.
The main motivation behind Agile-SD is to support the short-distance networks such
as local area networks and data center networks in order to increase the bandwidth
utilization over high-speed networks. Moreover, Agile-SD is introduced in support
of the open source community, where it can be used under the OpenGL agreement.
---
net/ipv4/Kconfig | 15 ++++
net/ipv4/Makefile | 1 +
net/ipv4/tcp_agilesd.c | 221 +++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 237 insertions(+)
create mode 100755 net/ipv4/tcp_agilesd.c
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 91a25579..22d824b1 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -677,6 +677,17 @@ config TCP_CONG_BBR
bufferbloat, policers, or AQM schemes that do not provide a delay
signal. It requires the fq ("Fair Queue") pacing packet scheduler.
+config TCP_CONG_AGILESD
+ tristate "Agile-SD Congestion control"
+ default n
+ ---help---
+
+ This is version 1.0 of Agile-SD TCP. It is a sender-side only.
+ It contributes the Agility Factor (AF) to shorten the epoch time
+ and to make TCP independent from RTT. AF reduces the sensitivity
+ to packet losses, which in turn Agile-SD to achieve better throughput
+ over high-speed networks.
+
choice
prompt "Default TCP congestion control"
default DEFAULT_CUBIC
@@ -713,6 +724,9 @@ choice
config DEFAULT_BBR
bool "BBR" if TCP_CONG_BBR=y
+
+ config DEFAULT_AGILESD
+ bool "AGILESD" if TCP_CONG_AGILESD=y
config DEFAULT_RENO
bool "Reno"
@@ -738,6 +752,7 @@ config DEFAULT_TCP_CONG
default "dctcp" if DEFAULT_DCTCP
default "cdg" if DEFAULT_CDG
default "bbr" if DEFAULT_BBR
+ default "agilesd" if DEFAULT_AGILESD
default "cubic"
config TCP_MD5SIG
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index f83de23a..33d398b5 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -44,6 +44,7 @@ obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o
obj-$(CONFIG_INET_RAW_DIAG) += raw_diag.o
obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o
obj-$(CONFIG_TCP_CONG_BBR) += tcp_bbr.o
+obj-$(CONFIG_TCP_CONG_AGILESD) += tcp_agilesd.o
obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o
obj-$(CONFIG_TCP_CONG_CDG) += tcp_cdg.o
obj-$(CONFIG_TCP_CONG_CUBIC) += tcp_cubic.o
diff --git a/net/ipv4/tcp_agilesd.c b/net/ipv4/tcp_agilesd.c
new file mode 100755
index 00000000..fd040ff2
--- /dev/null
+++ b/net/ipv4/tcp_agilesd.c
@@ -0,0 +1,221 @@
+/* agilesd is a Loss-Based Congestion Control Algorithm for TCP v1.0.
+ * agilesd has been created by Mohamed A. Alrshah,
+ * at Faculty of Computer Science and Information Technology,
+ * Universiti Putra Malaysia.
+ * agilesd is based on the article, which is published in 2015 as below:
+ *
+ * Alrshah, M.A., Othman, M., Ali, B. and Hanapi, Z.M., 2015.
+ * Agile-SD: a Linux-based TCP congestion control algorithm for supporting high-speed and short-distance networks.
+ * Journal of Network and Computer Applications, 55, pp.181-190.
+ */
+
+/* These includes are very important to operate the algorithm under NS2. */
+//#define NS_PROTOCOL "tcp_agilesd.c"
+//#include "../ns-linux-c.h"
+//#include "../ns-linux-util.h"
+//#include <math.h>
+/* These includes are very important to operate the algorithm under NS2. */
+
+/* These includes are very important to operate the algorithm under Linux OS. */
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/math64.h>
+#include <net/tcp.h>
+//#include <linux/skbuff.h> // optional
+//#include <linux/inet_diag.h> // optional
+/* These includes are very important to operate the algorithm under Linux OS. */
+
+#define SCALE 1000 /* Scale factor to avoid fractions */
+#define Double_SCALE 1000000 /* Double_SCALE must be equal to SCALE^2 */
+#define beta 900 /* beta for multiplicative decrease */
+
+static int initial_ssthresh __read_mostly;
+//static int beta __read_mostly = 900; /*the initial value of beta is equal to 90%*/
+
+module_param(initial_ssthresh, int, 0644);
+MODULE_PARM_DESC(initial_ssthresh, "initial value of slow start threshold");
+//module_param(beta, int, 0444);
+//MODULE_PARM_DESC(beta, "beta for multiplicative decrease");
+
+/* agilesd Parameters */
+struct agilesdtcp {
+ u32 loss_cwnd; // congestion window at last loss.
+ u32 frac_tracer; // This is to trace the fractions of the increment.
+ u32 degraded_loss_cwnd; // loss_cwnd after degradation.
+ enum dystate{SS=0, CA=1} agilesd_tcp_status;
+};
+
+static inline void agilesdtcp_reset(struct sock *sk)
+{
+ /*After timeout loss cntRTT and baseRTT must be reset to the initial values as below */
+}
+
+/* This function is called after the first acknowledgment is received and before the congestion
+ * control algorithm will be called for the first time. If the congestion control algorithm has
+ * private data, it should initialize its private date here. */
+static void agilesdtcp_init(struct sock *sk)
+{
+ struct agilesdtcp *ca = inet_csk_ca(sk);
+
+ // If the value of initial_ssthresh is not set, snd_ssthresh will be initialized by a large value.
+ if (initial_ssthresh)
+ tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
+ else
+ tcp_sk(sk)->snd_ssthresh = 0x7fffffff;
+
+ ca->loss_cwnd = 0;
+ ca->frac_tracer = 0;
+ ca->agilesd_tcp_status = SS;
+}
+
+/* This function is called whenever an ack is received and the congestion window can be increased.
+ * This is equivalent to opencwnd in tcp.cc.
+ * ack is the number of bytes that are acknowledged in the latest acknowledgment;
+ * rtt is the the rtt measured by the latest acknowledgment;
+ * in_flight is the packet in flight before the latest acknowledgment;
+ * good_ack is an indicator whether the current situation is normal (no duplicate ack, no loss and no SACK). */
+static void agilesdtcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) //For Linux Kernel Use.
+//static void agilesdtcp_cong_avoid(struct sock *sk, u32 ack, u32 seq_rtt, u32 in_flight, int data_acked) //For NS2 Use.
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct agilesdtcp *ca = inet_csk_ca(sk);
+ u32 inc_factor;
+ u32 ca_inc;
+ u32 current_gap, total_gap;
+ /* The value of inc_factor is limited by lower_fl and upper_fl.
+ * The lower_fl must be always = 1. The greater the upper_fl the higher the aggressiveness.
+ * But, if upper_fl set to 1, agilesd will work exactly as newreno.
+ * We have already designed an equation to calculate the optimum upper_fl based on the given beta.
+ * This equation will be revealed once its article is published*/
+ u32 lower_fl = 1 * SCALE;
+ u32 upper_fl = 3 * SCALE;
+
+ //if (!tcp_is_cwnd_limited(sk, in_flight)) return; //For NS-2 Use, if the in flight packets not >= cwnd do nothing//
+ if (!tcp_is_cwnd_limited(sk)) return; // For Linux Kernel Use.
+
+ if (tp->snd_cwnd < tp->snd_ssthresh){
+ ca->agilesd_tcp_status = SS;
+ //tcp_slow_start(tp); //For NS-2 Use
+ tcp_slow_start(tp, in_flight); // For Linux Kernel Use.
+ }
+ else {
+ ca->agilesd_tcp_status = CA;
+
+ if (ca->loss_cwnd > ca->degraded_loss_cwnd)
+ total_gap = ca->loss_cwnd - ca->degraded_loss_cwnd;
+ else
+ total_gap = 1;
+
+ if (ca->loss_cwnd > tp->snd_cwnd)
+ current_gap = ca->loss_cwnd - tp->snd_cwnd;
+ else
+ current_gap = 0;
+
+ inc_factor = min(max(((upper_fl * current_gap) / total_gap), lower_fl), upper_fl);
+
+ ca_inc = ((inc_factor * SCALE) / tp->snd_cwnd); /* SCALE is used to avoid fractions*/
+
+ ca->frac_tracer += ca_inc; /* This in order to take the fraction increase into account */
+ if (ca->frac_tracer >= Double_SCALE) /* To take factor scale into account */
+ {
+ tp->snd_cwnd += 1;
+ ca->frac_tracer -= Double_SCALE;
+ }
+ }
+}
+
+/* This function is called when the TCP flow detects a loss.
+ * It returns the slow start threshold of a flow, after a packet loss is detected. */
+static u32 agilesdtcp_recalc_ssthresh(struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ struct agilesdtcp *ca = inet_csk_ca(sk);
+
+ ca->loss_cwnd = tp->snd_cwnd;
+
+ if (ca->agilesd_tcp_status == CA)
+ ca->degraded_loss_cwnd = max((tp->snd_cwnd * beta) / SCALE, 2U);
+ else
+ ca->degraded_loss_cwnd = max((tp->snd_cwnd * beta) / SCALE, 2U);
+
+ ca->frac_tracer = 0;
+
+ return ca->degraded_loss_cwnd;
+}
+
+/* This function is called when the TCP flow detects a loss.
+ * It returns the congestion window of a flow, after a packet loss is detected;
+ * (for many algorithms, this will be equal to ssthresh). When a loss is detected,
+ * min_cwnd is called after ssthresh. But some others algorithms might set min_cwnd
+ * to be smaller than ssthresh. If this is the case, there will be a slow start after loss recovery. */
+//static u32 agilesdtcp_min_cwnd(const struct sock *sk)
+//{
+// return tcp_sk(sk)->snd_ssthresh;
+//}
+
+static u32 agilesdtcp_undo_cwnd(struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ const struct agilesdtcp *ca = inet_csk_ca(sk);
+ return max(tp->snd_cwnd, ca->loss_cwnd);
+}
+
+/* This function is called when the congestion state of the TCP is changed.
+ * newstate is the state code for the state that TCP is going to be in.
+ * The possible states are listed below:
+ * The current congestion control state, which can be one of the followings:
+ * TCP_CA_Open: normal state
+ * TCP_CA_Recovery: Loss Recovery after a Fast Transmission
+ * TCP_CA_Loss: Loss Recovery after a Timeout
+ * (The following two states are not effective in TCP-Linux but is effective in Linux)
+ * TCP_CA_Disorder: duplicate packets detected, but haven't reach the threshold. So TCP shall assume that packet reordering is happening.
+ * TCP_CA_CWR: the state that congestion window is decreasing (after local congestion in NIC, or ECN and etc).
+ * It is to notify the congestion control algorithm and is used by some
+ * algorithms which turn off their special control during loss recovery. */
+static void agilesdtcp_state(struct sock *sk, u8 new_state)
+{
+ if (new_state == TCP_CA_Loss)
+ agilesdtcp_reset(inet_csk_ca(sk));
+}
+
+/* This function is called when there is an acknowledgment that acknowledges some new packets.
+ * num_acked is the number of packets that are acknowledged by this acknowledgments. */
+//static void agilesdtcp_acked(struct sock *sk, u32 num_acked, ktime_t rtt_us) //For NS2 Use.
+static void agilesdtcp_acked(struct sock *sk, u32 num_acked, s32 rtt_us) //For Linux Kernel Use.
+{
+
+}
+
+static struct tcp_congestion_ops agilesdtcp __read_mostly = {
+ .init = agilesdtcp_init,
+ .ssthresh = agilesdtcp_recalc_ssthresh, //REQUIRED
+ .cong_avoid = agilesdtcp_cong_avoid, //REQUIRED
+ .set_state = agilesdtcp_state,
+ .undo_cwnd = agilesdtcp_undo_cwnd,
+ .pkts_acked = agilesdtcp_acked,
+ .owner = THIS_MODULE,
+ .name = "agilesd", //REQUIRED
+ //.min_cwnd = agilesdtcp_min_cwnd, //NOT REQUIRED
+};
+
+static int __init agilesdtcp_register(void)
+{
+ BUILD_BUG_ON(sizeof(struct agilesdtcp) > ICSK_CA_PRIV_SIZE);
+ return tcp_register_congestion_control(&agilesdtcp);
+}
+
+static void __exit agilesdtcp_unregister(void)
+{
+ tcp_unregister_congestion_control(&agilesdtcp);
+}
+
+module_init(agilesdtcp_register);
+module_exit(agilesdtcp_unregister);
+
+MODULE_AUTHOR("Mohamed A. Alrshah <mohamed.a.alrshah@ieee.org>");
+MODULE_AUTHOR("Mohamed Othman");
+MODULE_AUTHOR("Borhanuddin Ali");
+MODULE_AUTHOR("Zurina Hanapi");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("agilesd is a Loss-Based Congestion Control Algorithm for TCP v1.0. By Mohamed A. Alrshah");
+MODULE_VERSION("1.0");
--
2.12.3
^ permalink raw reply related
* [PATCH] Adding Agile-SD TCP module and modifying Kconfig and Makefile
From: mohamedalrshah @ 2017-08-02 4:43 UTC (permalink / raw)
To: davem; +Cc: netdev, torvalds, linux-kernel, mohamed.a.alrshah, mohamed.asnd
In-Reply-To: <stephen@networkplumber.org>
Published:
Alrshah, M.A., Othman, M., Ali, B. and Hanapi, Z.M., 2015. Agile-SD: a Linux-based
TCP congestion control algorithm for supporting high-speed and short-distance networks.
Journal of Network and Computer Applications, 55, pp.181-190.
Agile-SD is a new loss-based and RTT-independent TCP congestion
control algorithm designed to support high-speed and Short-Distance (SD)
networks. It mainly contributes the agility factor mechanism, which allows
Agile-SD to deal with small buffer sizes while reducing its sensitivity to
packet loss. Due to the use of this mechanism, Agile-SD improves the
throughput of TCP up to 50% compared to Cubic-TCP and Compound-TCP. Its
performance was evaluated using the well-known NS2 simulator to measure
the average throughput, loss ratio and fairness.
Agile-SD is designed and implemented by Mohamed A. Alrshah et al. (2015) as
a Linux kernel module in the real Linux operating system (openSUSE 42.1 Leap),
which is implemented at the Network, Parallel and Distributed Computing Laboratory,
A2.10, second floor, Block A, Faculty of Computer Science and Information Technology,
Universiti Putra Malaysia, over real PCs connected to the Internet for daily uses and
evaluation purposes.
The main motivation behind Agile-SD is to support the short-distance networks such
as local area networks and data center networks in order to increase the bandwidth
utilization over high-speed networks. Moreover, Agile-SD is introduced in support
of the open source community, where it can be used under the OpenGL agreement.
---
net/ipv4/Kconfig | 15 ++++
net/ipv4/Makefile | 1 +
net/ipv4/tcp_agilesd.c | 221 +++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 237 insertions(+)
create mode 100755 net/ipv4/tcp_agilesd.c
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 91a25579..22d824b1 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -677,6 +677,17 @@ config TCP_CONG_BBR
bufferbloat, policers, or AQM schemes that do not provide a delay
signal. It requires the fq ("Fair Queue") pacing packet scheduler.
+config TCP_CONG_AGILESD
+ tristate "Agile-SD Congestion control"
+ default n
+ ---help---
+
+ This is version 1.0 of Agile-SD TCP. It is a sender-side only.
+ It contributes the Agility Factor (AF) to shorten the epoch time
+ and to make TCP independent from RTT. AF reduces the sensitivity
+ to packet losses, which in turn Agile-SD to achieve better throughput
+ over high-speed networks.
+
choice
prompt "Default TCP congestion control"
default DEFAULT_CUBIC
@@ -713,6 +724,9 @@ choice
config DEFAULT_BBR
bool "BBR" if TCP_CONG_BBR=y
+
+ config DEFAULT_AGILESD
+ bool "AGILESD" if TCP_CONG_AGILESD=y
config DEFAULT_RENO
bool "Reno"
@@ -738,6 +752,7 @@ config DEFAULT_TCP_CONG
default "dctcp" if DEFAULT_DCTCP
default "cdg" if DEFAULT_CDG
default "bbr" if DEFAULT_BBR
+ default "agilesd" if DEFAULT_AGILESD
default "cubic"
config TCP_MD5SIG
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index f83de23a..33d398b5 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -44,6 +44,7 @@ obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o
obj-$(CONFIG_INET_RAW_DIAG) += raw_diag.o
obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o
obj-$(CONFIG_TCP_CONG_BBR) += tcp_bbr.o
+obj-$(CONFIG_TCP_CONG_AGILESD) += tcp_agilesd.o
obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o
obj-$(CONFIG_TCP_CONG_CDG) += tcp_cdg.o
obj-$(CONFIG_TCP_CONG_CUBIC) += tcp_cubic.o
diff --git a/net/ipv4/tcp_agilesd.c b/net/ipv4/tcp_agilesd.c
new file mode 100755
index 00000000..fd040ff2
--- /dev/null
+++ b/net/ipv4/tcp_agilesd.c
@@ -0,0 +1,221 @@
+/* agilesd is a Loss-Based Congestion Control Algorithm for TCP v1.0.
+ * agilesd has been created by Mohamed A. Alrshah,
+ * at Faculty of Computer Science and Information Technology,
+ * Universiti Putra Malaysia.
+ * agilesd is based on the article, which is published in 2015 as below:
+ *
+ * Alrshah, M.A., Othman, M., Ali, B. and Hanapi, Z.M., 2015.
+ * Agile-SD: a Linux-based TCP congestion control algorithm for supporting high-speed and short-distance networks.
+ * Journal of Network and Computer Applications, 55, pp.181-190.
+ */
+
+/* These includes are very important to operate the algorithm under NS2. */
+//#define NS_PROTOCOL "tcp_agilesd.c"
+//#include "../ns-linux-c.h"
+//#include "../ns-linux-util.h"
+//#include <math.h>
+/* These includes are very important to operate the algorithm under NS2. */
+
+/* These includes are very important to operate the algorithm under Linux OS. */
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/math64.h>
+#include <net/tcp.h>
+//#include <linux/skbuff.h> // optional
+//#include <linux/inet_diag.h> // optional
+/* These includes are very important to operate the algorithm under Linux OS. */
+
+#define SCALE 1000 /* Scale factor to avoid fractions */
+#define Double_SCALE 1000000 /* Double_SCALE must be equal to SCALE^2 */
+#define beta 900 /* beta for multiplicative decrease */
+
+static int initial_ssthresh __read_mostly;
+//static int beta __read_mostly = 900; /*the initial value of beta is equal to 90%*/
+
+module_param(initial_ssthresh, int, 0644);
+MODULE_PARM_DESC(initial_ssthresh, "initial value of slow start threshold");
+//module_param(beta, int, 0444);
+//MODULE_PARM_DESC(beta, "beta for multiplicative decrease");
+
+/* agilesd Parameters */
+struct agilesdtcp {
+ u32 loss_cwnd; // congestion window at last loss.
+ u32 frac_tracer; // This is to trace the fractions of the increment.
+ u32 degraded_loss_cwnd; // loss_cwnd after degradation.
+ enum dystate{SS=0, CA=1} agilesd_tcp_status;
+};
+
+static inline void agilesdtcp_reset(struct sock *sk)
+{
+ /*After timeout loss cntRTT and baseRTT must be reset to the initial values as below */
+}
+
+/* This function is called after the first acknowledgment is received and before the congestion
+ * control algorithm will be called for the first time. If the congestion control algorithm has
+ * private data, it should initialize its private date here. */
+static void agilesdtcp_init(struct sock *sk)
+{
+ struct agilesdtcp *ca = inet_csk_ca(sk);
+
+ // If the value of initial_ssthresh is not set, snd_ssthresh will be initialized by a large value.
+ if (initial_ssthresh)
+ tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
+ else
+ tcp_sk(sk)->snd_ssthresh = 0x7fffffff;
+
+ ca->loss_cwnd = 0;
+ ca->frac_tracer = 0;
+ ca->agilesd_tcp_status = SS;
+}
+
+/* This function is called whenever an ack is received and the congestion window can be increased.
+ * This is equivalent to opencwnd in tcp.cc.
+ * ack is the number of bytes that are acknowledged in the latest acknowledgment;
+ * rtt is the the rtt measured by the latest acknowledgment;
+ * in_flight is the packet in flight before the latest acknowledgment;
+ * good_ack is an indicator whether the current situation is normal (no duplicate ack, no loss and no SACK). */
+static void agilesdtcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) //For Linux Kernel Use.
+//static void agilesdtcp_cong_avoid(struct sock *sk, u32 ack, u32 seq_rtt, u32 in_flight, int data_acked) //For NS2 Use.
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct agilesdtcp *ca = inet_csk_ca(sk);
+ u32 inc_factor;
+ u32 ca_inc;
+ u32 current_gap, total_gap;
+ /* The value of inc_factor is limited by lower_fl and upper_fl.
+ * The lower_fl must be always = 1. The greater the upper_fl the higher the aggressiveness.
+ * But, if upper_fl set to 1, agilesd will work exactly as newreno.
+ * We have already designed an equation to calculate the optimum upper_fl based on the given beta.
+ * This equation will be revealed once its article is published*/
+ u32 lower_fl = 1 * SCALE;
+ u32 upper_fl = 3 * SCALE;
+
+ //if (!tcp_is_cwnd_limited(sk, in_flight)) return; //For NS-2 Use, if the in flight packets not >= cwnd do nothing//
+ if (!tcp_is_cwnd_limited(sk)) return; // For Linux Kernel Use.
+
+ if (tp->snd_cwnd < tp->snd_ssthresh){
+ ca->agilesd_tcp_status = SS;
+ //tcp_slow_start(tp); //For NS-2 Use
+ tcp_slow_start(tp, in_flight); // For Linux Kernel Use.
+ }
+ else {
+ ca->agilesd_tcp_status = CA;
+
+ if (ca->loss_cwnd > ca->degraded_loss_cwnd)
+ total_gap = ca->loss_cwnd - ca->degraded_loss_cwnd;
+ else
+ total_gap = 1;
+
+ if (ca->loss_cwnd > tp->snd_cwnd)
+ current_gap = ca->loss_cwnd - tp->snd_cwnd;
+ else
+ current_gap = 0;
+
+ inc_factor = min(max(((upper_fl * current_gap) / total_gap), lower_fl), upper_fl);
+
+ ca_inc = ((inc_factor * SCALE) / tp->snd_cwnd); /* SCALE is used to avoid fractions*/
+
+ ca->frac_tracer += ca_inc; /* This in order to take the fraction increase into account */
+ if (ca->frac_tracer >= Double_SCALE) /* To take factor scale into account */
+ {
+ tp->snd_cwnd += 1;
+ ca->frac_tracer -= Double_SCALE;
+ }
+ }
+}
+
+/* This function is called when the TCP flow detects a loss.
+ * It returns the slow start threshold of a flow, after a packet loss is detected. */
+static u32 agilesdtcp_recalc_ssthresh(struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ struct agilesdtcp *ca = inet_csk_ca(sk);
+
+ ca->loss_cwnd = tp->snd_cwnd;
+
+ if (ca->agilesd_tcp_status == CA)
+ ca->degraded_loss_cwnd = max((tp->snd_cwnd * beta) / SCALE, 2U);
+ else
+ ca->degraded_loss_cwnd = max((tp->snd_cwnd * beta) / SCALE, 2U);
+
+ ca->frac_tracer = 0;
+
+ return ca->degraded_loss_cwnd;
+}
+
+/* This function is called when the TCP flow detects a loss.
+ * It returns the congestion window of a flow, after a packet loss is detected;
+ * (for many algorithms, this will be equal to ssthresh). When a loss is detected,
+ * min_cwnd is called after ssthresh. But some others algorithms might set min_cwnd
+ * to be smaller than ssthresh. If this is the case, there will be a slow start after loss recovery. */
+//static u32 agilesdtcp_min_cwnd(const struct sock *sk)
+//{
+// return tcp_sk(sk)->snd_ssthresh;
+//}
+
+static u32 agilesdtcp_undo_cwnd(struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ const struct agilesdtcp *ca = inet_csk_ca(sk);
+ return max(tp->snd_cwnd, ca->loss_cwnd);
+}
+
+/* This function is called when the congestion state of the TCP is changed.
+ * newstate is the state code for the state that TCP is going to be in.
+ * The possible states are listed below:
+ * The current congestion control state, which can be one of the followings:
+ * TCP_CA_Open: normal state
+ * TCP_CA_Recovery: Loss Recovery after a Fast Transmission
+ * TCP_CA_Loss: Loss Recovery after a Timeout
+ * (The following two states are not effective in TCP-Linux but is effective in Linux)
+ * TCP_CA_Disorder: duplicate packets detected, but haven't reach the threshold. So TCP shall assume that packet reordering is happening.
+ * TCP_CA_CWR: the state that congestion window is decreasing (after local congestion in NIC, or ECN and etc).
+ * It is to notify the congestion control algorithm and is used by some
+ * algorithms which turn off their special control during loss recovery. */
+static void agilesdtcp_state(struct sock *sk, u8 new_state)
+{
+ if (new_state == TCP_CA_Loss)
+ agilesdtcp_reset(inet_csk_ca(sk));
+}
+
+/* This function is called when there is an acknowledgment that acknowledges some new packets.
+ * num_acked is the number of packets that are acknowledged by this acknowledgments. */
+//static void agilesdtcp_acked(struct sock *sk, u32 num_acked, ktime_t rtt_us) //For NS2 Use.
+static void agilesdtcp_acked(struct sock *sk, u32 num_acked, s32 rtt_us) //For Linux Kernel Use.
+{
+
+}
+
+static struct tcp_congestion_ops agilesdtcp __read_mostly = {
+ .init = agilesdtcp_init,
+ .ssthresh = agilesdtcp_recalc_ssthresh, //REQUIRED
+ .cong_avoid = agilesdtcp_cong_avoid, //REQUIRED
+ .set_state = agilesdtcp_state,
+ .undo_cwnd = agilesdtcp_undo_cwnd,
+ .pkts_acked = agilesdtcp_acked,
+ .owner = THIS_MODULE,
+ .name = "agilesd", //REQUIRED
+ //.min_cwnd = agilesdtcp_min_cwnd, //NOT REQUIRED
+};
+
+static int __init agilesdtcp_register(void)
+{
+ BUILD_BUG_ON(sizeof(struct agilesdtcp) > ICSK_CA_PRIV_SIZE);
+ return tcp_register_congestion_control(&agilesdtcp);
+}
+
+static void __exit agilesdtcp_unregister(void)
+{
+ tcp_unregister_congestion_control(&agilesdtcp);
+}
+
+module_init(agilesdtcp_register);
+module_exit(agilesdtcp_unregister);
+
+MODULE_AUTHOR("Mohamed A. Alrshah <mohamed.a.alrshah@ieee.org>");
+MODULE_AUTHOR("Mohamed Othman");
+MODULE_AUTHOR("Borhanuddin Ali");
+MODULE_AUTHOR("Zurina Hanapi");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("agilesd is a Loss-Based Congestion Control Algorithm for TCP v1.0. By Mohamed A. Alrshah");
+MODULE_VERSION("1.0");
--
2.12.3
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox