* [PATCH V2 net-next 02/15] smc: establish new socket family
From: Ursula Braun @ 2016-09-27 16:41 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-s390, schwidefsky, heiko.carstens, utz.bacher,
ubraun
In-Reply-To: <20160927164156.26184-1-ubraun@linux.vnet.ibm.com>
* enable smc module loading and unloading
* register new socket family
* basic smc socket creation and deletion
* use backing TCP socket to run CLC (Connection Layer Control)
handshake of SMC protocol
* Setup for infiniband traffic is implemented in follow-on patches.
For now fallback to TCP socket is always used.
Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Reviewed-by: Utz Bacher <utz.bacher@de.ibm.com>
---
MAINTAINERS | 7 +
include/linux/socket.h | 7 +-
net/Kconfig | 1 +
net/Makefile | 1 +
net/core/sock.c | 6 +-
net/smc/Kconfig | 11 +
net/smc/Makefile | 2 +
net/smc/af_smc.c | 623 +++++++++++++++++++++++++++++++++++++++++++++++++
net/smc/smc.h | 36 +++
9 files changed, 690 insertions(+), 4 deletions(-)
create mode 100644 net/smc/Kconfig
create mode 100644 net/smc/Makefile
create mode 100644 net/smc/af_smc.c
create mode 100644 net/smc/smc.h
diff --git a/MAINTAINERS b/MAINTAINERS
index efd69c76..fdf5cc6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10331,6 +10331,13 @@ S: Maintained
F: Documentation/devicetree/bindings/serial/
F: drivers/tty/serial/
+SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS
+M: Ursula Braun <ursula.braun@linux.vnet.ibm.com>
+L: linux-s390@vger.kernel.org
+W: http://www.ibm.com/developerworks/linux/linux390/
+S: Supported
+F: net/smc/
+
SYNOPSYS DESIGNWARE DMAC DRIVER
M: Viresh Kumar <vireshk@kernel.org>
M: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
diff --git a/include/linux/socket.h b/include/linux/socket.h
index b5cc5a6..a4a1cc7 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -202,8 +202,12 @@ struct ucred {
#define AF_VSOCK 40 /* vSockets */
#define AF_KCM 41 /* Kernel Connection Multiplexor*/
#define AF_QIPCRTR 42 /* Qualcomm IPC Router */
+#define AF_SMC 43 /* smc sockets: reserve number for
+ * PF_SMC protocol family that
+ * reuses AF_INET address family
+ */
-#define AF_MAX 43 /* For now.. */
+#define AF_MAX 44 /* For now.. */
/* Protocol families, same as address families. */
#define PF_UNSPEC AF_UNSPEC
@@ -251,6 +255,7 @@ struct ucred {
#define PF_VSOCK AF_VSOCK
#define PF_KCM AF_KCM
#define PF_QIPCRTR AF_QIPCRTR
+#define PF_SMC AF_SMC
#define PF_MAX AF_MAX
/* Maximum queue length specifiable by listen. */
diff --git a/net/Kconfig b/net/Kconfig
index 7b6cd34..c6f611e 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -57,6 +57,7 @@ source "net/packet/Kconfig"
source "net/unix/Kconfig"
source "net/xfrm/Kconfig"
source "net/iucv/Kconfig"
+source "net/smc/Kconfig"
config INET
bool "TCP/IP networking"
diff --git a/net/Makefile b/net/Makefile
index 4cafaa2..5d6e0e5f 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -51,6 +51,7 @@ obj-$(CONFIG_MAC80211) += mac80211/
obj-$(CONFIG_TIPC) += tipc/
obj-$(CONFIG_NETLABEL) += netlabel/
obj-$(CONFIG_IUCV) += iucv/
+obj-$(CONFIG_SMC) += smc/
obj-$(CONFIG_RFKILL) += rfkill/
obj-$(CONFIG_NET_9P) += 9p/
obj-$(CONFIG_CAIF) += caif/
diff --git a/net/core/sock.c b/net/core/sock.c
index ce31244..d275d04 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -222,7 +222,7 @@ static const char *const af_family_key_strings[AF_MAX+1] = {
"sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" ,
"sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" ,
"sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_KCM" ,
- "sk_lock-AF_MAX"
+ "sk_lock-AF_SMC" , "sk_lock-AF_MAX"
};
static const char *const af_family_slock_key_strings[AF_MAX+1] = {
"slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" ,
@@ -239,7 +239,7 @@ static const char *const af_family_slock_key_strings[AF_MAX+1] = {
"slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" ,
"slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" ,
"slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_KCM" ,
- "slock-AF_MAX"
+ "slock-AF_SMC" , "slock-AF_MAX"
};
static const char *const af_family_clock_key_strings[AF_MAX+1] = {
"clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" ,
@@ -256,7 +256,7 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = {
"clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" ,
"clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" ,
"clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_KCM" ,
- "clock-AF_MAX"
+ "closck-AF_smc" , "clock-AF_MAX"
};
/*
diff --git a/net/smc/Kconfig b/net/smc/Kconfig
new file mode 100644
index 0000000..bc02980
--- /dev/null
+++ b/net/smc/Kconfig
@@ -0,0 +1,11 @@
+config SMC
+ tristate "SMC socket protocol family"
+ depends on INET && INFINIBAND
+ ---help---
+ SMC-R provides a "sockets over RDMA" solution making use of
+ RDMA over Converged Ethernet (RoCE) technology to upgrade
+ AF_INET TCP connections transparently.
+ The Linux implementation of the SMC-R solution is designed as
+ a separate socket family SMC.
+
+ Select this option if you want to run SMC socket applications
diff --git a/net/smc/Makefile b/net/smc/Makefile
new file mode 100644
index 0000000..c285c86
--- /dev/null
+++ b/net/smc/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_SMC) += smc.o
+smc-y := af_smc.o
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
new file mode 100644
index 0000000..ae3332c
--- /dev/null
+++ b/net/smc/af_smc.c
@@ -0,0 +1,623 @@
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * AF_SMC protocol family socket handler keeping the AF_INET sock address type
+ * applies to SOCK_STREAM sockets only
+ * offers an alternative communication option for TCP-protocol sockets
+ * applicable with RoCE-cards only
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com>
+ * based on prototype from Frank Blaschka
+ */
+
+#define KMSG_COMPONENT "smc"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/module.h>
+#include <linux/socket.h>
+#include <net/sock.h>
+
+#include "smc.h"
+
+static void smc_set_keepalive(struct sock *sk, int val)
+{
+ struct smc_sock *smc = smc_sk(sk);
+
+ smc->clcsock->sk->sk_prot->keepalive(smc->clcsock->sk, val);
+}
+
+static struct proto smc_proto = {
+ .name = "SMC",
+ .owner = THIS_MODULE,
+ .keepalive = smc_set_keepalive,
+ .obj_size = sizeof(struct smc_sock),
+ .slab_flags = SLAB_DESTROY_BY_RCU,
+};
+
+static int smc_release(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+ struct smc_sock *smc;
+
+ if (!sk)
+ goto out;
+
+ smc = smc_sk(sk);
+ lock_sock(sk);
+
+ sk->sk_state = SMC_CLOSED;
+ if (smc->clcsock) {
+ sock_release(smc->clcsock);
+ smc->clcsock = NULL;
+ }
+
+ /* detach socket */
+ sock_set_flag(sk, SOCK_ZAPPED);
+ sock_orphan(sk);
+ sock->sk = NULL;
+ release_sock(sk);
+
+ sock_put(sk);
+out:
+ return 0;
+}
+
+static void smc_destruct(struct sock *sk)
+{
+ if (sk->sk_state != SMC_CLOSED)
+ return;
+ if (!sock_flag(sk, SOCK_DEAD))
+ return;
+
+ sk_refcnt_debug_dec(sk);
+}
+
+static struct sock *smc_sock_alloc(struct net *net, struct socket *sock)
+{
+ struct smc_sock *smc;
+ struct sock *sk;
+
+ sk = sk_alloc(net, PF_SMC, GFP_KERNEL, &smc_proto, 0);
+ if (!sk)
+ return NULL;
+
+ sock_init_data(sock, sk); /* sets sk_refcnt to 1 */
+ sk->sk_state = SMC_INIT;
+ sk->sk_destruct = smc_destruct;
+ sk->sk_protocol = SMCPROTO_SMC;
+ sk_refcnt_debug_inc(sk);
+
+ smc = smc_sk(sk);
+ smc->clcsock = NULL;
+ smc->use_fallback = 0;
+
+ return sk;
+}
+
+static int smc_bind(struct socket *sock, struct sockaddr *uaddr,
+ int addr_len)
+{
+ struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
+ struct sock *sk = sock->sk;
+ struct smc_sock *smc;
+ int rc;
+
+ smc = smc_sk(sk);
+
+ /* replicate tests from inet_bind(), to be safe wrt. future changes */
+ rc = -EINVAL;
+ if (addr_len < sizeof(struct sockaddr_in))
+ goto out;
+
+ rc = -EAFNOSUPPORT;
+ /* accept AF_UNSPEC (mapped to AF_INET) only if s_addr is INADDR_ANY */
+ if ((addr->sin_family != AF_INET) &&
+ ((addr->sin_family != AF_UNSPEC) ||
+ (addr->sin_addr.s_addr != htonl(INADDR_ANY))))
+ goto out;
+
+ lock_sock(sk);
+
+ /* Check if socket is already active */
+ rc = -EINVAL;
+ if (sk->sk_state != SMC_INIT)
+ goto out_rel;
+
+ smc->clcsock->sk->sk_reuse = sk->sk_reuse;
+ rc = kernel_bind(smc->clcsock, uaddr, addr_len);
+
+out_rel:
+ release_sock(sk);
+out:
+ return rc;
+}
+
+static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk,
+ unsigned long mask)
+{
+ /* options we don't get control via setsockopt for */
+ nsk->sk_type = osk->sk_type;
+ nsk->sk_sndbuf = osk->sk_sndbuf;
+ nsk->sk_rcvbuf = osk->sk_rcvbuf;
+ nsk->sk_sndtimeo = osk->sk_sndtimeo;
+ nsk->sk_rcvtimeo = osk->sk_rcvtimeo;
+ nsk->sk_mark = osk->sk_mark;
+ nsk->sk_priority = osk->sk_priority;
+ nsk->sk_rcvlowat = osk->sk_rcvlowat;
+ nsk->sk_bound_dev_if = osk->sk_bound_dev_if;
+ nsk->sk_err = osk->sk_err;
+
+ nsk->sk_flags &= ~mask;
+ nsk->sk_flags |= osk->sk_flags & mask;
+}
+
+#define SK_FLAGS_SMC_TO_CLC ((1UL << SOCK_URGINLINE) | \
+ (1UL << SOCK_KEEPOPEN) | \
+ (1UL << SOCK_LINGER) | \
+ (1UL << SOCK_BROADCAST) | \
+ (1UL << SOCK_TIMESTAMP) | \
+ (1UL << SOCK_DBG) | \
+ (1UL << SOCK_RCVTSTAMP) | \
+ (1UL << SOCK_RCVTSTAMPNS) | \
+ (1UL << SOCK_LOCALROUTE) | \
+ (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \
+ (1UL << SOCK_RXQ_OVFL) | \
+ (1UL << SOCK_WIFI_STATUS) | \
+ (1UL << SOCK_NOFCS) | \
+ (1UL << SOCK_FILTER_LOCKED))
+/* copy only relevant settings and flags of SOL_SOCKET level from smc to
+ * clc socket (since smc is not called for these options from net/core)
+ */
+static void smc_copy_sock_settings_to_clc(struct smc_sock *smc)
+{
+ smc_copy_sock_settings(smc->clcsock->sk, &smc->sk, SK_FLAGS_SMC_TO_CLC);
+}
+
+#define SK_FLAGS_CLC_TO_SMC ((1UL << SOCK_URGINLINE) | \
+ (1UL << SOCK_KEEPOPEN) | \
+ (1UL << SOCK_LINGER) | \
+ (1UL << SOCK_DBG))
+/* copy only settings and flags relevant for smc from clc to smc socket */
+static void smc_copy_sock_settings_to_smc(struct smc_sock *smc)
+{
+ smc_copy_sock_settings(&smc->sk, smc->clcsock->sk, SK_FLAGS_CLC_TO_SMC);
+}
+
+static int smc_connect(struct socket *sock, struct sockaddr *addr,
+ int alen, int flags)
+{
+ struct sock *sk = sock->sk;
+ struct smc_sock *smc;
+ int rc = -EINVAL;
+
+ smc = smc_sk(sk);
+
+ /* separate smc parameter checking to be safe */
+ if (alen < sizeof(addr->sa_family))
+ goto out_err;
+ if (addr->sa_family != AF_INET)
+ goto out_err;
+
+ lock_sock(sk);
+ switch (sk->sk_state) {
+ default:
+ goto out;
+ case SMC_ACTIVE:
+ rc = -EISCONN;
+ goto out;
+ case SMC_INIT:
+ rc = 0;
+ break;
+ }
+
+ smc_copy_sock_settings_to_clc(smc);
+ rc = kernel_connect(smc->clcsock, addr, alen, flags);
+ if (rc)
+ goto out;
+
+ sk->sk_state = SMC_ACTIVE;
+
+ /* always use TCP fallback as transport mechanism for now;
+ * This will change once RDMA transport is implemented
+ */
+ smc->use_fallback = 1;
+
+out:
+ release_sock(sk);
+out_err:
+ return rc;
+}
+
+static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc)
+{
+ struct sock *sk = &lsmc->sk;
+ struct socket *new_clcsock;
+ struct sock *new_sk;
+ int rc;
+
+ new_sk = smc_sock_alloc(sock_net(sk), NULL);
+ if (!new_sk) {
+ rc = -ENOMEM;
+ lsmc->sk.sk_err = ENOMEM;
+ *new_smc = NULL;
+ goto out;
+ }
+ *new_smc = smc_sk(new_sk);
+
+ rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0);
+ if (rc) {
+ sock_put(new_sk);
+ *new_smc = NULL;
+ goto out;
+ }
+
+ (*new_smc)->clcsock = new_clcsock;
+out:
+ return rc;
+}
+
+static int smc_listen(struct socket *sock, int backlog)
+{
+ struct sock *sk = sock->sk;
+ struct smc_sock *smc;
+ int rc;
+
+ smc = smc_sk(sk);
+ lock_sock(sk);
+
+ rc = -EINVAL;
+ if ((sk->sk_state != SMC_INIT) && (sk->sk_state != SMC_LISTEN))
+ goto out;
+
+ rc = 0;
+ if (sk->sk_state == SMC_LISTEN) {
+ sk->sk_max_ack_backlog = backlog;
+ goto out;
+ }
+ /* some socket options are handled in core, so we could not apply
+ * them to the clc socket -- copy smc socket options to clc socket
+ */
+ smc_copy_sock_settings_to_clc(smc);
+
+ rc = kernel_listen(smc->clcsock, backlog);
+ if (rc)
+ goto out;
+ sk->sk_max_ack_backlog = backlog;
+ sk->sk_ack_backlog = 0;
+ sk->sk_state = SMC_LISTEN;
+
+out:
+ release_sock(sk);
+ return rc;
+}
+
+static int smc_accept(struct socket *sock, struct socket *new_sock,
+ int flags)
+{
+ struct smc_sock *new_smc;
+ struct sock *sk = sock->sk;
+ struct smc_sock *lsmc;
+ int rc;
+
+ lsmc = smc_sk(sk);
+ lock_sock(sk);
+
+ if (lsmc->sk.sk_state != SMC_LISTEN) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ rc = smc_clcsock_accept(lsmc, &new_smc);
+ if (rc)
+ goto out;
+ sock_graft(&new_smc->sk, new_sock);
+ new_smc->sk.sk_state = SMC_ACTIVE;
+
+ smc_copy_sock_settings_to_smc(new_smc);
+
+ /* always use TCP fallback as transport mechanism for now;
+ * This will change once RDMA transport is implemented
+ */
+ new_smc->use_fallback = 1;
+
+out:
+ release_sock(sk);
+ return rc;
+}
+
+static int smc_getname(struct socket *sock, struct sockaddr *addr,
+ int *len, int peer)
+{
+ struct smc_sock *smc;
+
+ if (peer && (sock->sk->sk_state != SMC_ACTIVE))
+ return -ENOTCONN;
+
+ smc = smc_sk(sock->sk);
+
+ return smc->clcsock->ops->getname(smc->clcsock, addr, len, peer);
+}
+
+static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
+{
+ struct sock *sk = sock->sk;
+ struct smc_sock *smc;
+ int rc = -EPIPE;
+
+ smc = smc_sk(sk);
+ lock_sock(sk);
+ if (sk->sk_state != SMC_ACTIVE)
+ goto out;
+ if (smc->use_fallback)
+ rc = smc->clcsock->ops->sendmsg(smc->clcsock, msg, len);
+ else
+ rc = sock_no_sendmsg(sock, msg, len);
+out:
+ release_sock(sk);
+ return rc;
+}
+
+static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+ int flags)
+{
+ struct sock *sk = sock->sk;
+ struct smc_sock *smc;
+ int rc = -ENOTCONN;
+
+ smc = smc_sk(sk);
+ lock_sock(sk);
+ if ((sk->sk_state != SMC_ACTIVE) && (sk->sk_state != SMC_CLOSED))
+ goto out;
+
+ if (smc->use_fallback)
+ rc = smc->clcsock->ops->recvmsg(smc->clcsock, msg, len, flags);
+ else
+ rc = sock_no_recvmsg(sock, msg, len, flags);
+out:
+ release_sock(sk);
+ return rc;
+}
+
+static unsigned int smc_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
+{
+ struct sock *sk = sock->sk;
+ unsigned int mask = 0;
+ struct smc_sock *smc;
+
+ smc = smc_sk(sock->sk);
+ if ((sk->sk_state == SMC_INIT) || (sk->sk_state == SMC_LISTEN) ||
+ smc->use_fallback) {
+ mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
+ /* if non-blocking connect finished ... */
+ lock_sock(sk);
+ if ((sk->sk_state == SMC_INIT) && (mask & POLLOUT)) {
+ sk->sk_state = SMC_ACTIVE;
+ /* always use TCP fallback as transport mechanism;
+ * This will change once RDMA transport is implemented
+ */
+ smc->use_fallback = 1;
+ }
+ release_sock(sk);
+ } else {
+ mask = sock_no_poll(file, sock, wait);
+ }
+
+ return mask;
+}
+
+static int smc_shutdown(struct socket *sock, int how)
+{
+ struct sock *sk = sock->sk;
+ struct smc_sock *smc;
+ int rc = -EINVAL;
+
+ smc = smc_sk(sk);
+
+ if ((how < SHUT_RD) || (how > SHUT_RDWR))
+ goto out_err;
+
+ lock_sock(sk);
+
+ rc = -ENOTCONN;
+ if (sk->sk_state == SMC_CLOSED)
+ goto out;
+ if (smc->use_fallback) {
+ rc = kernel_sock_shutdown(smc->clcsock, how);
+ sk->sk_shutdown = smc->clcsock->sk->sk_shutdown;
+ if (sk->sk_shutdown == SHUTDOWN_MASK)
+ sk->sk_state = SMC_CLOSED;
+ } else {
+ rc = sock_no_shutdown(sock, how);
+ }
+
+out:
+ release_sock(sk);
+
+out_err:
+ return rc;
+}
+
+static int smc_setsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, unsigned int optlen)
+{
+ struct sock *sk = sock->sk;
+ struct smc_sock *smc;
+
+ smc = smc_sk(sk);
+
+ /* generic setsockopts reaching us here always apply to the
+ * CLC socket
+ */
+ return smc->clcsock->ops->setsockopt(smc->clcsock, level, optname,
+ optval, optlen);
+}
+
+static int smc_getsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, int __user *optlen)
+{
+ struct smc_sock *smc;
+
+ smc = smc_sk(sock->sk);
+ /* socket options apply to the CLC socket */
+ return smc->clcsock->ops->getsockopt(smc->clcsock, level, optname,
+ optval, optlen);
+}
+
+static int smc_ioctl(struct socket *sock, unsigned int cmd,
+ unsigned long arg)
+{
+ struct smc_sock *smc;
+
+ smc = smc_sk(sock->sk);
+ if (smc->use_fallback)
+ return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
+ else
+ return sock_no_ioctl(sock, cmd, arg);
+}
+
+static ssize_t smc_sendpage(struct socket *sock, struct page *page,
+ int offset, size_t size, int flags)
+{
+ struct sock *sk = sock->sk;
+ struct smc_sock *smc;
+ int rc = -EPIPE;
+
+ smc = smc_sk(sk);
+ lock_sock(sk);
+ if (sk->sk_state != SMC_ACTIVE)
+ goto out;
+ if (smc->use_fallback)
+ rc = kernel_sendpage(smc->clcsock, page, offset,
+ size, flags);
+ else
+ rc = sock_no_sendpage(sock, page, offset, size, flags);
+
+out:
+ release_sock(sk);
+ return rc;
+}
+
+static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags)
+{
+ struct sock *sk = sock->sk;
+ struct smc_sock *smc;
+ int rc = -ENOTCONN;
+
+ smc = smc_sk(sk);
+ lock_sock(sk);
+ if ((sk->sk_state != SMC_ACTIVE) && (sk->sk_state != SMC_CLOSED))
+ goto out;
+ if (smc->use_fallback) {
+ rc = smc->clcsock->ops->splice_read(smc->clcsock, ppos,
+ pipe, len, flags);
+ } else {
+ rc = -EOPNOTSUPP;
+ }
+out:
+ release_sock(sk);
+ return rc;
+}
+
+/* must look like tcp */
+static const struct proto_ops smc_sock_ops = {
+ .family = PF_SMC,
+ .owner = THIS_MODULE,
+ .release = smc_release,
+ .bind = smc_bind,
+ .connect = smc_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = smc_accept,
+ .getname = smc_getname,
+ .poll = smc_poll,
+ .ioctl = smc_ioctl,
+ .listen = smc_listen,
+ .shutdown = smc_shutdown,
+ .setsockopt = smc_setsockopt,
+ .getsockopt = smc_getsockopt,
+ .sendmsg = smc_sendmsg,
+ .recvmsg = smc_recvmsg,
+ .mmap = sock_no_mmap,
+ .sendpage = smc_sendpage,
+ .splice_read = smc_splice_read,
+};
+
+static int smc_create(struct net *net, struct socket *sock, int protocol,
+ int kern)
+{
+ struct smc_sock *smc;
+ struct sock *sk;
+ int rc;
+
+ rc = -ESOCKTNOSUPPORT;
+ if (sock->type != SOCK_STREAM)
+ goto out;
+
+ rc = -EPROTONOSUPPORT;
+ if ((protocol != IPPROTO_IP) && (protocol != IPPROTO_TCP))
+ goto out;
+
+ rc = -ENOBUFS;
+ sock->ops = &smc_sock_ops;
+ sk = smc_sock_alloc(net, sock);
+ if (!sk)
+ goto out;
+
+ /* create internal TCP socket for CLC handshake and fallback */
+ smc = smc_sk(sk);
+ rc = sock_create_kern(net, PF_INET, SOCK_STREAM,
+ IPPROTO_TCP, &smc->clcsock);
+ if (rc)
+ sk_common_release(sk);
+
+out:
+ return rc;
+}
+
+static const struct net_proto_family smc_sock_family_ops = {
+ .family = PF_SMC,
+ .owner = THIS_MODULE,
+ .create = smc_create,
+};
+
+static int __init smc_init(void)
+{
+ int rc;
+
+ rc = proto_register(&smc_proto, 1);
+ if (rc) {
+ pr_err("%s: proto_register fails with %d\n", __func__, rc);
+ goto out;
+ }
+
+ rc = sock_register(&smc_sock_family_ops);
+ if (rc) {
+ pr_err("%s: sock_register fails with %d\n", __func__, rc);
+ goto out_proto;
+ }
+
+ return 0;
+
+out_proto:
+ proto_unregister(&smc_proto);
+out:
+ return rc;
+}
+
+static void __exit smc_exit(void)
+{
+ sock_unregister(PF_SMC);
+ proto_unregister(&smc_proto);
+}
+
+module_init(smc_init);
+module_exit(smc_exit);
+
+MODULE_AUTHOR("Ursula Braun <ubraun@linux.vnet.ibm.com>");
+MODULE_DESCRIPTION("smc socket address family");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NETPROTO(PF_SMC);
diff --git a/net/smc/smc.h b/net/smc/smc.h
new file mode 100644
index 0000000..46f562d
--- /dev/null
+++ b/net/smc/smc.h
@@ -0,0 +1,36 @@
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Definitions for the SMC module (socket related)
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+#ifndef _SMC_H
+#define _SMC_H
+
+#include <linux/socket.h>
+#include <linux/types.h>
+#include <net/sock.h>
+
+#define SMCPROTO_SMC 0 /* SMC protocol */
+
+enum smc_state { /* possible states of an SMC socket */
+ SMC_ACTIVE = 1,
+ SMC_INIT = 2,
+ SMC_CLOSED = 7,
+ SMC_LISTEN = 10,
+};
+
+struct smc_sock { /* smc sock container */
+ struct sock sk;
+ struct socket *clcsock; /* internal tcp socket */
+ u8 use_fallback : 1; /* fallback to tcp */
+};
+
+static inline struct smc_sock *smc_sk(const struct sock *sk)
+{
+ return (struct smc_sock *)sk;
+}
+#endif /* _SMC_H */
--
2.8.4
^ permalink raw reply related
* [PATCH V2 net-next 00/15] net/smc: Shared Memory Communications - RDMA
From: Ursula Braun @ 2016-09-27 16:41 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-s390, schwidefsky, heiko.carstens, utz.bacher,
ubraun
Dave,
here is now V2 of the SMC-R patches having processed your August feedback
plus reported coccinelle findings. The most important change is the removal
of xchg() calls, I had wrongly used for atomic updates of 64-bit values.
I still see a need for atomic reads and updates of 64-bit SMC-cursors.
If type atomic64_t is not supported, I use plain u64 for SMC-cursors and
add locking when reading or writing the cursors.
V2 changes:
Patch 0002: Add SMC versions for family key strings in net/core/sock.c.
Patch 0006: initialize rb_tree.
Patch 0007: Get rid of unneeded use of xchg() in smc_sndbuf_unuse() and
smc_rmb_unuse().
Patch 0008: Correct error checking logic for ib_function calls.
Define struct smc_link field wr_tx_id as atomic_long_t.
Use "do_div" instead of "%" to be architecture-independent.
Patch 0009: Correct error checking logic for ib_function calls.
Patch 0011: Remove xchg() calls in cursor handling. Use atomic64_t for cursor
overlays on 64-bit architectures. If not available, use plain u64
and add locking for cursor reading and writing.
Implement smc_curs_add() without modulo operator "%".
Patch 0012: Remove xchg() calls in cursor handling.
Implement smc_tx_rdma_writes() without module operator "%".
Patch 0013: Remove xchg() calls in cursor handling.
Patch 0014: Return type bool in smc_wr_tx_has_pending().
Remove unneeded semicolon in smc_close_shutdown_write().
Call smc_close_active() in non-fallback case only.
Get rid of duplicate schedule of sock_put_work().
Take nested sock_lock in smc_listen_work().
Start close stream_wait in case of prepared sends only.
Patch 0015: Remove unneeded socket ref_count in smc_proc_seq_show().
Take lock before list_empty check in smc_proc_sock_list_del().
These patches are the initial part of the implementation of the
"Shared Memory Communications-RDMA" (SMC-R) protocol as defined in
RFC7609 [1]. While SMC-R does not aim to replace TCP,
it taps a wealth of existing data center TCP socket applications
to become more efficient without the need for rewriting them.
SMC-R uses RDMA over Converged Ethernet (RoCE) to save CPU consumption.
For instance, when running 10 parallel connections with uperf, we measured
a decrease of 60% in CPU consumption with SMC-R compared to TCP/IP
(with throughput and latency comparable;
measured on x86_64 with the same RoCE card and port).
SMC-R does not require an RDMA communication manager (RDMA CM).
SMC-R inherits TCP qualities such as reliable connections, host-based
firewall packet filtering (on connection establishment) and unmodified
application of communication encryption such as TLS (transport layer
security) or SSL (secure sockets layer). Since original TCP is used to
establish SMC-R connections, load balancers and packet inspection based
on TCP/IP connection establishment continue to work for SMC-R.
On the other hand, using SMC-R implies:
- either involving a preload library when invoking the unchanged TCP-application
or slightly modifying the source by simply changing the socket family in
the socket() call
- accepting extra overhead and latency in connection establishment due to
SMC Connection Layer Control (CLC) handshake
- explicit coupling of RoCE ports with Ethernet ports
- not routable as currently built on RoCE V1
- bypassing of packet-based networking features
- filtering (netfilter)
- sniffing (libpcap, packet sockets, (E)BPF)
- traffic control (scheduling, shaping)
- bypassing of IP-header based socket options
- bypassing of memory buffer (pressure) management
- unusable together with IPsec
Overview of the SMC-R Protocol described in informational RFC 7609
SMC-R is an open protocol that provides RDMA capabilities over RoCE
transparently for applications exploiting TCP sockets.
A new socket protocol family PF_SMC is introduced.
There are no changes required to applications using the sockets API for TCP
stream sockets other than the specification of the new socket family AF_SMC.
Unmodified applications can be used by means of a dynamic preload shared
library which rewrites the socket API call
socket(AF_INET, SOCK_STREAM, IPPROTO_TCP) into
socket(AF_SMC, SOCK_STREAM, IPPROTO_TCP).
SMC-R re-uses the address family AF_INET for all addressing purposes around
struct sockaddr.
SMC-R system architecture layers:
+=============================================================================+
| | unmodified TCP application |
| native SMC application +--------------------------------------+
| | dynamic preload shared library |
+=============================================================================+
| SMC socket |
+-----------------------------------------------------------------------------+
| | TCP socket (for connection establishment and fallback) |
| IB verbs +--------------------------------------------------------+
| | IP |
+--------------------+--------------------------------------------------------+
| RoCE device driver | some network device driver |
+=============================================================================+
Terms:
A link group is determined by an ordered peer pair of TCP client and TCP server
(IP addresses and subnet). Reversed client server roles cause an own link group.
A link is a logical point-to-point connection based on an
infiniband reliable connected queue pair (RC-QP) between two RoCE ports
(MACs and GIDs) of a peer pair.
A link group can have 1..8 links for failover and load balancing.
This initial Linux implementation always has 1 link per link group.
Each link group on a peer can have 1..255 remote memory buffers (RMBs).
If more RMBs are needed, a peer can open another link group
(this initial Linux implementation) or fall back to TCP.
Each RMB has its own particular size and its own (R)DMA mapping and credentials
(rtoken consisting of rkey and RDMA "virtual address").
This initial Linux implementation uses physically contiguous memory for RMBs
but we are working towards scattered memory because of memory fragmentation.
Each RMB has 1..255 RMB elements (RMBEs) of equal size
to provide multiplexing of connections within an RMB.
An RMBE is the RDMA Write destination organized as wrapping ring buffer
for data transmit of a particular connection in one direction
(duplex by means of mirror symmetry as with TCP).
This initial Linux implementation always has 1 RMBE per RMB
and thus an individual RMB for each connection.
SMC-R connection establishment with subsequent data transfer:
CLIENT SERVER
TCP three-way handshake:
regular TCP SYN
-------------------------------------------------------->
regular TCP SYN ACK
<--------------------------------------------------------
regular TCP ACK
-------------------------------------------------------->
SMC Connection Layer Control (CLC) handshake
exchanges RDMA credentials between peers:
via above TCP connection: SMC CLC Proposal
-------------------------------------------------------->
via above TCP connection: SMC CLC Accept
<--------------------------------------------------------
via above TCP connection: SMC CLC Confirm
-------------------------------------------------------->
SMC Link Layer Control (LLC) (only once per link, i.e. 1st conn. of link group):
RoCE RC-QP: SMC LLC Confirm Link
<========================================================
RoCE RC-QP: SMC LLC Confirm Link response
========================================================>
SMC data transmission (incl. SMC Connection Data Control (CDC) message):
RoCE RC-QP: RDMA Write
========================================================>
RoCE RC-QP: SMC CDC message (flow control)
========================================================>
...
RoCE RC-QP: RDMA Write
<========================================================
RoCE RC-QP: SMC CDC message (flow control)
<========================================================
...
Data flow within an established connection:
+----------------------------------------------------------------------------
| SENDER
| sendmsg()
| |
| | produces into sndbuf [sender's process context]
| v
| +--------+
| | sndbuf | [ring buffer]
| +--------+
| |
| | consumes from sndbuf and produces into receiver's RMBE [any context]
| | by sending RDMA Write followed by SMC CDC message over RoCE RC-QP
| |
+----|-----------------------------------------------------------------------
|
+----|-----------------------------------------------------------------------
| v RECEIVER
| +------+
| | RMBE | [ring buffer, can have size different from sender's sndbuf]
| | | [RMBE represents rcvbuf, no further de-coupling as on sender side]
| +------+
| |
| | consumes from RMBE [receiver's process context]
| v
| recvmsg()
+----------------------------------------------------------------------------
Flow control ("cursor" updates) by means of SMC CDC messages:
SENDER RECEIVER
sends updates via CDC-------------+ sends updates via CDC
on consuming from sndbuf | on consuming from RMBE
and producing into RMBE | by means of recvmsg()
| |
| |
+-----------------------------------|------------+
| |
+--v-------------------------+ +--v-----------------------+
| receiver's consumer cursor | | sender's producer cursor----+
+----------------|-----------+ +--------------------------+ |
| |
| receiver's RMBE |
| +--------------------------+ |
| | | |
+--------------------------------+ | |
| | | |
| v | |
| +------------| |
|-------------+////////////| |
|//RDMA data written by////| |
|////sender that is////////| |
|/available to be consumed/| |
|///////// +---------------| |
|----------+^ | |
| | | |
| +-----------------+
| |
+--------------------------+
Sending updates of the producer cursor is immediate for low latency;
something like Nagle's algorithm (absence of TCP_NODELAY) is optional and
currently not part of this initial Linux implementation.
Sending updates of the consumer cursor is conditional to avoid the
silly window syndrome.
Normal connection termination:
Normal connection termination starts transitioning from socket state
ACTIVE via either "Active Close" or "Passive Close".
shutdown rdwr +-----------------+
or close, +-------------->| INIT / CLOSED |<-------------+
send PeerCon|nClosed +-----------------+ | PeerConnClosed
| | | received
| connection | established |
| V |
+----------------+ +-----------------+ +----------------+
|AppFinCloseWait | | ACTIVE | |PeerFinCloseWait|
+----------------+ +-----------------+ +----------------+
| | | |
| Active Close: | |Passive Close: |
| close or | |PeerConnClosed or |
| shutdown wr or| |PeerDoneWriting |
| shutdown rdwr | |received |
| V V |
PeerConnClo|sed +--------------+ +-------------+ | close or
received +--<----|PeerCloseWait1| |AppCloseWait1|--->----+ shutdown rdwr,
| +--------------+ +-------------+ | send
| PeerDoneWri|ting | shutdown wr, | PeerConnClosed
| received | send Pee|rDoneWriting |
| V V |
| +--------------+ +-------------+ |
+--<----|PeerCloseWait2| |AppCloseWait2|--->----+
+--------------+ +-------------+
In state CLOSED, the socket can be destructed only, once the application has
issued a close().
Abnormal connection termination:
+-----------------+
+-------------->| INIT / CLOSED |<-------------+
| +-----------------+ |
| |
| +-----------------------+ |
| | Any state | |
PeerConnAbo|rt | (before setting | | send
received | | PeerConnClosed | | PeerConnAbort
| | indicator in | |
| | peer's RMBE) | |
| +-----------------------+ |
| | | |
| Active Abort: | | Passive Abort: |
| problem, | | PeerConnAbort |
| send | | received, |
| PeerConnAbort,| | ECONNRESET |
| ECONNABORTED | | |
| V V |
| +--------------+ +--------------+ |
+-------|PeerAbortWait | | ProcessAbort |------+
+--------------+ +--------------+
Implementation notes beyond RFC 7609:
A PNET table in sysfs provides the mapping between network device names and
RoCE Infiniband device names for the transparent switch of data communication.
A PNET table can contain an arbitrary number of PNETIDs.
Each PNETID contains exactly one (Ethernet) network device name
and one or more RoCE Infiniband device names.
Each device name can only exist in at most one PNETID (no overlapping).
This initial Linux implementation allows at most one RoCE Infiniband device
name per PNETID.
After a new TCP connection is established, the network device name
used for egress traffic with the TCP connection's local source IP address
is used as key to lookup the unique PNETID, and the RoCE Infiniband device
of this PNETID is used to switch data communication from TCP to RDMA
during SMC CLC handshake.
Problem determination:
A protocol dissector is available with upstream wireshark for formatting
SMC-R related RoCE LAN traffic.
[https://code.wireshark.org/review/gitweb?p=wireshark.git;a=blob;f=epan/dissectors/packet-smcr.c]
We are working on enhancing the Linux implementation to cover:
- Improve default socket closing asynchronicity
- Address corner cases with many parallel connections
- Tracing
- Integrated load balancing and fail-over within a link group
- Splice and sendpage support
- IPv6 addressing support
- Keepalive, Cork
- Namespaces support
- Urgent data
- More socket options
- Diagnostics
- Statistics support
- SNMP support
References:
[1] SMC-R Informational RFC: http://www.rfc-editor.org/info/rfc7609
Thomas Richter (1):
smc: establish pnet table management
Ursula Braun (14):
net: introduce keepalive function in struct proto
smc: establish new socket family
smc: introduce SMC as an IB-client
smc: CLC handshake (incl. preparation steps)
smc: connection and link group creation
smc: remote memory buffers (RMBs)
smc: work request (WR) base for use by LLC and CDC
smc: initialize IB transport incl. PD, MR, QP, CQ, event, WR
smc: link layer control (LLC)
smc: connection data control (CDC)
smc: send data (through RDMA)
smc: receive data from RMBE
smc: socket closing and linkgroup cleanup
smc: proc-fs interface for smc connections
MAINTAINERS | 7 +
include/linux/socket.h | 7 +-
include/net/sock.h | 1 +
net/Kconfig | 1 +
net/Makefile | 1 +
net/core/sock.c | 13 +-
net/ipv4/tcp_ipv4.c | 1 +
net/ipv4/tcp_timer.c | 1 +
net/ipv6/tcp_ipv6.c | 1 +
net/smc/Kconfig | 11 +
net/smc/Makefile | 3 +
net/smc/af_smc.c | 1380 ++++++++++++++++++++++++++++++++++++++++++++++++
net/smc/smc.h | 269 ++++++++++
net/smc/smc_cdc.c | 302 +++++++++++
net/smc/smc_cdc.h | 217 ++++++++
net/smc/smc_clc.c | 276 ++++++++++
net/smc/smc_clc.h | 113 ++++
net/smc/smc_close.c | 435 +++++++++++++++
net/smc/smc_close.h | 27 +
net/smc/smc_core.c | 704 ++++++++++++++++++++++++
net/smc/smc_core.h | 178 +++++++
net/smc/smc_ib.c | 485 +++++++++++++++++
net/smc/smc_ib.h | 67 +++
net/smc/smc_llc.c | 158 ++++++
net/smc/smc_llc.h | 63 +++
net/smc/smc_pnet.c | 611 +++++++++++++++++++++
net/smc/smc_pnet.h | 26 +
net/smc/smc_proc.c | 247 +++++++++
net/smc/smc_proc.h | 19 +
net/smc/smc_rx.c | 216 ++++++++
net/smc/smc_rx.h | 22 +
net/smc/smc_tx.c | 482 +++++++++++++++++
net/smc/smc_tx.h | 35 ++
net/smc/smc_wr.c | 612 +++++++++++++++++++++
net/smc/smc_wr.h | 103 ++++
35 files changed, 7085 insertions(+), 9 deletions(-)
create mode 100644 net/smc/Kconfig
create mode 100644 net/smc/Makefile
create mode 100644 net/smc/af_smc.c
create mode 100644 net/smc/smc.h
create mode 100644 net/smc/smc_cdc.c
create mode 100644 net/smc/smc_cdc.h
create mode 100644 net/smc/smc_clc.c
create mode 100644 net/smc/smc_clc.h
create mode 100644 net/smc/smc_close.c
create mode 100644 net/smc/smc_close.h
create mode 100644 net/smc/smc_core.c
create mode 100644 net/smc/smc_core.h
create mode 100644 net/smc/smc_ib.c
create mode 100644 net/smc/smc_ib.h
create mode 100644 net/smc/smc_llc.c
create mode 100644 net/smc/smc_llc.h
create mode 100644 net/smc/smc_pnet.c
create mode 100644 net/smc/smc_pnet.h
create mode 100644 net/smc/smc_proc.c
create mode 100644 net/smc/smc_proc.h
create mode 100644 net/smc/smc_rx.c
create mode 100644 net/smc/smc_rx.h
create mode 100644 net/smc/smc_tx.c
create mode 100644 net/smc/smc_tx.h
create mode 100644 net/smc/smc_wr.c
create mode 100644 net/smc/smc_wr.h
--
2.8.4
^ permalink raw reply
* [PATCH V2 net-next 01/15] net: introduce keepalive function in struct proto
From: Ursula Braun @ 2016-09-27 16:41 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-s390, schwidefsky, heiko.carstens, utz.bacher,
ubraun
In-Reply-To: <20160927164156.26184-1-ubraun@linux.vnet.ibm.com>
Direct call of tcp_set_keepalive() function from protocol-agnostic
sock_setsockopt() function in net/core/sock.c violates network
layering. And newly introduced protocol (SMC-R) will need its own
keepalive function. Therefore, add "keepalive" function pointer
to "struct proto", and call it from sock_setsockopt() via this pointer.
Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Reviewed-by: Utz Bacher <utz.bacher@de.ibm.com>
---
include/net/sock.h | 1 +
net/core/sock.c | 7 ++-----
net/ipv4/tcp_ipv4.c | 1 +
net/ipv4/tcp_timer.c | 1 +
net/ipv6/tcp_ipv6.c | 1 +
5 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index ebf75db..474e89f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -988,6 +988,7 @@ struct proto {
int (*getsockopt)(struct sock *sk, int level,
int optname, char __user *optval,
int __user *option);
+ void (*keepalive)(struct sock *sk, int valbool);
#ifdef CONFIG_COMPAT
int (*compat_setsockopt)(struct sock *sk,
int level,
diff --git a/net/core/sock.c b/net/core/sock.c
index 038e660..ce31244 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -761,11 +761,8 @@ set_rcvbuf:
goto set_rcvbuf;
case SO_KEEPALIVE:
-#ifdef CONFIG_INET
- if (sk->sk_protocol == IPPROTO_TCP &&
- sk->sk_type == SOCK_STREAM)
- tcp_set_keepalive(sk, valbool);
-#endif
+ if (sk->sk_prot->keepalive)
+ sk->sk_prot->keepalive(sk, valbool);
sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
break;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7ac37c3..a7ddb16 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2361,6 +2361,7 @@ struct proto tcp_prot = {
.shutdown = tcp_shutdown,
.setsockopt = tcp_setsockopt,
.getsockopt = tcp_getsockopt,
+ .keepalive = tcp_set_keepalive,
.recvmsg = tcp_recvmsg,
.sendmsg = tcp_sendmsg,
.sendpage = tcp_sendpage,
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index f712b41..abb1ea1 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -613,6 +613,7 @@ void tcp_set_keepalive(struct sock *sk, int val)
else if (!val)
inet_csk_delete_keepalive_timer(sk);
}
+EXPORT_SYMBOL(tcp_set_keepalive);
static void tcp_keepalive_timer (unsigned long data)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 54cf719..a4ea411 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1876,6 +1876,7 @@ struct proto tcpv6_prot = {
.shutdown = tcp_shutdown,
.setsockopt = tcp_setsockopt,
.getsockopt = tcp_getsockopt,
+ .keepalive = tcp_set_keepalive,
.recvmsg = tcp_recvmsg,
.sendmsg = tcp_sendmsg,
.sendpage = tcp_sendpage,
--
2.8.4
^ permalink raw reply related
* Re: [PATCH net-next 2/3] net: mpls: Fixups for GSO
From: David Ahern @ 2016-09-27 16:38 UTC (permalink / raw)
To: Jiri Benc
Cc: pravin shelar, Simon Horman, Pravin B Shelar,
Linux Kernel Network Developers, David S. Miller, buytenh,
Eric W. Biederman, rshearma, tom, Thomas Graf, olivier.dugeon,
Alexander Duyck, roopa
In-Reply-To: <20160927094536.392c5045@griffin>
On 9/27/16 1:45 AM, Jiri Benc wrote:
> On Mon, 26 Sep 2016 20:04:06 -0600, David Ahern wrote:
>> you know this code better than me, but key_extract pulls the eth
>> header and then sets network header. If MPLS labels are present then
>> it is the labels that the network_header now points to. How did come
>> to the conclusion it is after the labels?
>
> Look ~100 lines below that, to "if (eth_p_mpls(key->eth.type))".
> There's a while loop advancing network header.
got it, thanks. so that block can drop the while loop and just set mpls.top_lse
^ permalink raw reply
* [RFC PATCH net-next 2/2] sfc: report 4-tuple UDP hashing to ethtool, if it's enabled
From: Edward Cree @ 2016-09-27 16:35 UTC (permalink / raw)
To: linux-net-drivers, netdev, davem; +Cc: bkenward
In-Reply-To: <cc07d60a-189c-8475-ecb3-b612ff13bd5a@solarflare.com>
Signed-off-by: Edward Cree <ecree@solarflare.com>
---
drivers/net/ethernet/sfc/ef10.c | 6 ++++--
drivers/net/ethernet/sfc/ethtool.c | 14 ++++++++++----
drivers/net/ethernet/sfc/net_driver.h | 2 ++
3 files changed, 16 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 9f6d769..e61807e 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -2319,8 +2319,10 @@ static void efx_ef10_set_rss_flags(struct efx_nic *efx, u32 context)
flags |= RSS_MODE_HASH_PORTS << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_UDP_IPV4_RSS_MODE_LBN;
flags |= RSS_MODE_HASH_PORTS << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_UDP_IPV6_RSS_MODE_LBN;
MCDI_SET_DWORD(inbuf, RSS_CONTEXT_SET_FLAGS_IN_FLAGS, flags);
- efx_mcdi_rpc(efx, MC_CMD_RSS_CONTEXT_SET_FLAGS, inbuf, sizeof(inbuf),
- NULL, 0, NULL);
+ if (!efx_mcdi_rpc(efx, MC_CMD_RSS_CONTEXT_SET_FLAGS, inbuf, sizeof(inbuf),
+ NULL, 0, NULL))
+ /* Succeeded, so UDP 4-tuple is now enabled */
+ efx->rx_hash_udp_4tuple = true;
}
static int efx_ef10_alloc_rss_context(struct efx_nic *efx, u32 *context,
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 445ccdb..4a58899 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -968,20 +968,26 @@ efx_ethtool_get_rxnfc(struct net_device *net_dev,
info->data = 0;
switch (info->flow_type) {
+ case UDP_V4_FLOW:
+ if (efx->rx_hash_udp_4tuple)
+ /* fall through */
+ /* else fall further! */
case TCP_V4_FLOW:
- info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
/* fall through */
- case UDP_V4_FLOW:
case SCTP_V4_FLOW:
case AH_ESP_V4_FLOW:
case IPV4_FLOW:
info->data |= RXH_IP_SRC | RXH_IP_DST;
min_revision = EFX_REV_FALCON_B0;
break;
+ case UDP_V6_FLOW:
+ if (efx->rx_hash_udp_4tuple)
+ /* fall through */
+ /* else fall further! */
case TCP_V6_FLOW:
- info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
/* fall through */
- case UDP_V6_FLOW:
case SCTP_V6_FLOW:
case AH_ESP_V6_FLOW:
case IPV6_FLOW:
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 99d8c82..fec51c4 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -853,6 +853,7 @@ struct vfdi_status;
* @rx_hash_key: Toeplitz hash key for RSS
* @rx_indir_table: Indirection table for RSS
* @rx_scatter: Scatter mode enabled for receives
+ * @rx_hash_udp_4tuple: UDP 4-tuple hashing enabled
* @int_error_count: Number of internal errors seen recently
* @int_error_expire: Time at which error count will be expired
* @irq_soft_enabled: Are IRQs soft-enabled? If not, IRQ handler will
@@ -990,6 +991,7 @@ struct efx_nic {
u8 rx_hash_key[40];
u32 rx_indir_table[128];
bool rx_scatter;
+ bool rx_hash_udp_4tuple;
unsigned int_error_count;
unsigned long int_error_expire;
^ permalink raw reply related
* [RFC PATCH net-next 1/2] sfc: enable 4-tuple RSS hashing for UDP
From: Edward Cree @ 2016-09-27 16:35 UTC (permalink / raw)
To: linux-net-drivers, netdev, davem; +Cc: bkenward
In-Reply-To: <cc07d60a-189c-8475-ecb3-b612ff13bd5a@solarflare.com>
This improves UDP spreading, and also slightly improves GRO performance
of encapsulated TCP on 7000 series NICs.
Signed-off-by: Edward Cree <ecree@solarflare.com>
---
drivers/net/ethernet/sfc/ef10.c | 82 +++++++++++++++++++++++++++++++++++++++++
1 file changed, 82 insertions(+)
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 00279da..9f6d769 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -2245,6 +2245,84 @@ static void efx_ef10_tx_write(struct efx_tx_queue *tx_queue)
}
}
+#define RSS_MODE_HASH_ADDRS (1 << RSS_MODE_HASH_SRC_ADDR_LBN |\
+ 1 << RSS_MODE_HASH_DST_ADDR_LBN)
+#define RSS_MODE_HASH_PORTS (1 << RSS_MODE_HASH_SRC_PORT_LBN |\
+ 1 << RSS_MODE_HASH_DST_PORT_LBN)
+#define RSS_CONTEXT_FLAGS_DEFAULT (1 << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_IPV4_EN_LBN |\
+ 1 << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_TCPV4_EN_LBN |\
+ 1 << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_IPV6_EN_LBN |\
+ 1 << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_TCPV6_EN_LBN |\
+ (RSS_MODE_HASH_ADDRS | RSS_MODE_HASH_PORTS) << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TCP_IPV4_RSS_MODE_LBN |\
+ RSS_MODE_HASH_ADDRS << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_UDP_IPV4_RSS_MODE_LBN |\
+ RSS_MODE_HASH_ADDRS << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_OTHER_IPV4_RSS_MODE_LBN |\
+ (RSS_MODE_HASH_ADDRS | RSS_MODE_HASH_PORTS) << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TCP_IPV6_RSS_MODE_LBN |\
+ RSS_MODE_HASH_ADDRS << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_UDP_IPV6_RSS_MODE_LBN |\
+ RSS_MODE_HASH_ADDRS << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_OTHER_IPV6_RSS_MODE_LBN)
+
+static int efx_ef10_get_rss_flags(struct efx_nic *efx, u32 context, u32 *flags)
+{
+ /* Firmware had a bug (sfc bug 61952) where it would not actually
+ * fill in the flags field in the response to MC_CMD_RSS_CONTEXT_GET_FLAGS.
+ * This meant that it would always contain whatever was previously
+ * in the MCDI buffer. Fortunately, all firmware versions with
+ * this bug have the same default flags value for a newly-allocated
+ * RSS context, and the only time we want to get the flags is just
+ * after allocating. Moreover, the response has a 32-bit hole
+ * where the context ID would be in the request, so we can use an
+ * overlength buffer in the request and pre-fill the flags field
+ * with what we believe the default to be. Thus if the firmware
+ * has the bug, it will leave our pre-filled value in the flags
+ * field of the response, and we will get the right answer.
+ *
+ * However, this does mean that this function should NOT be used if
+ * the RSS context flags might not be their defaults - it is ONLY
+ * reliably correct for a newly-allocated RSS context.
+ */
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_LEN);
+ size_t outlen;
+ int rc;
+
+ /* Check we have a hole for the context ID */
+ BUILD_BUG_ON(MC_CMD_RSS_CONTEXT_GET_FLAGS_IN_LEN != MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_FLAGS_OFST);
+ MCDI_SET_DWORD(inbuf, RSS_CONTEXT_GET_FLAGS_IN_RSS_CONTEXT_ID, context);
+ MCDI_SET_DWORD(inbuf, RSS_CONTEXT_GET_FLAGS_OUT_FLAGS,
+ RSS_CONTEXT_FLAGS_DEFAULT);
+ rc = efx_mcdi_rpc(efx, MC_CMD_RSS_CONTEXT_GET_FLAGS, inbuf,
+ sizeof(inbuf), outbuf, sizeof(outbuf), &outlen);
+ if (rc == 0) {
+ if (outlen < MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_LEN)
+ rc = -EIO;
+ else
+ *flags = MCDI_DWORD(outbuf, RSS_CONTEXT_GET_FLAGS_OUT_FLAGS);
+ }
+ return rc;
+}
+
+/* Attempt to enable 4-tuple UDP hashing on the specified RSS context.
+ * If we fail, we just leave the RSS context at its default hash settings,
+ * which is safe but may slightly reduce performance.
+ * Defaults are 4-tuple for TCP and 2-tuple for UDP and other-IP, so we
+ * just need to set the UDP ports flags (for both IP versions).
+ */
+static void efx_ef10_set_rss_flags(struct efx_nic *efx, u32 context)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_LEN);
+ u32 flags;
+
+ BUILD_BUG_ON(MC_CMD_RSS_CONTEXT_SET_FLAGS_OUT_LEN != 0);
+
+ if (efx_ef10_get_rss_flags(efx, context, &flags) != 0)
+ return;
+ MCDI_SET_DWORD(inbuf, RSS_CONTEXT_SET_FLAGS_IN_RSS_CONTEXT_ID, context);
+ flags |= RSS_MODE_HASH_PORTS << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_UDP_IPV4_RSS_MODE_LBN;
+ flags |= RSS_MODE_HASH_PORTS << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_UDP_IPV6_RSS_MODE_LBN;
+ MCDI_SET_DWORD(inbuf, RSS_CONTEXT_SET_FLAGS_IN_FLAGS, flags);
+ efx_mcdi_rpc(efx, MC_CMD_RSS_CONTEXT_SET_FLAGS, inbuf, sizeof(inbuf),
+ NULL, 0, NULL);
+}
+
static int efx_ef10_alloc_rss_context(struct efx_nic *efx, u32 *context,
bool exclusive, unsigned *context_size)
{
@@ -2290,6 +2368,10 @@ static int efx_ef10_alloc_rss_context(struct efx_nic *efx, u32 *context,
if (context_size)
*context_size = rss_spread;
+ if (nic_data->datapath_caps &
+ 1 << MC_CMD_GET_CAPABILITIES_OUT_ADDITIONAL_RSS_MODES_LBN)
+ efx_ef10_set_rss_flags(efx, *context);
+
return 0;
}
^ permalink raw reply related
* [RFC PATCH net-next 0/2] sfc: enable 4-tuple UDP RSS hashing
From: Edward Cree @ 2016-09-27 16:32 UTC (permalink / raw)
To: linux-net-drivers, netdev; +Cc: davem, bkenward
EF10 based NICs have configurable RSS hash fields, and can be made to take the
ports into the hash on UDP (they already do so for TCP). This patch series
enables this, in order to improve spreading of UDP traffic.
Patch 2/2, which updates the ETHTOOL_GRXFH handling to report the new RSS hash
settings, uses a somewhat unorthodox construct to control fall-through flow in
a switch statement - is this acceptable style?
Edward Cree (2):
sfc: enable 4-tuple RSS hashing for UDP
sfc: report 4-tuple UDP hashing to ethtool, if it's enabled
drivers/net/ethernet/sfc/ef10.c | 84 +++++++++++++++++++++++++++++++++++
drivers/net/ethernet/sfc/ethtool.c | 14 ++++--
drivers/net/ethernet/sfc/net_driver.h | 2 +
3 files changed, 96 insertions(+), 4 deletions(-)
^ permalink raw reply
* Re: [PATCH net-next] tcp: Change txhash on every SYN and RTO retransmit
From: Eric Dumazet @ 2016-09-27 16:29 UTC (permalink / raw)
To: Lawrence Brakmo; +Cc: netdev, Kernel Team
In-Reply-To: <20160927160629.1174360-1-brakmo@fb.com>
On Tue, 2016-09-27 at 09:06 -0700, Lawrence Brakmo wrote:
> The current code changes txhash (flowlables) on every retransmitted
> SYN/ACK, but only after the 2nd retransmitted SYN and only after
> tcp_retries1 RTO retransmits.
>
> With this patch:
> 1) txhash is changed with every SYN retransmist
> 2) adds the option for the txhash to be changed before tcp_retries1
> RTO retransmits. A new sysctl tcp_rto_txhash_prob represents the
> probability that txhash will be changed. The default value is 0
> which maintains previous behavior and a value of 100 will always
> change it.
...
> @@ -213,6 +215,11 @@ static int tcp_write_timeout(struct sock *sk)
> tcp_mtu_probing(icsk, sk);
>
> dst_negative_advice(sk);
> + } else if (sk->sk_txhash && sysctl_tcp_rto_txhash_prob > 0) {
> + u32 v = prandom_u32() % 100;
> +
> + if (v < sysctl_tcp_rto_txhash_prob)
> + sk_set_txhash(sk);
>
Write timeouts are rare events and sk_txhash should already be set.
Also prandom_u32_max() is a bit faster (no divide, and even no multiply
for 100 which is 5*5*4, compiler can emit 2 lea instructions )
I would suggest not using all these tests and instead be very simple :
} else if (prandom_u32_max(100) < sysctl_tcp_rto_txhash_prob) {
sk_set_txhash(sk);
}
Finally, adding a new sysctl requires a Documentation update
( Documentation/networking/ip-sysctl.txt )
Thanks.
^ permalink raw reply
* Re: [PATCH net-next V2] net/sched: pkt_cls: change tc actions order to be as the user sets
From: Cong Wang @ 2016-09-27 16:29 UTC (permalink / raw)
To: Hadar Hen Zion
Cc: David S. Miller, Linux Kernel Network Developers,
Jamal Hadi Salim, Or Gerlitz
In-Reply-To: <1474963791-3717-1-git-send-email-hadarh@mellanox.com>
On Tue, Sep 27, 2016 at 1:09 AM, Hadar Hen Zion <hadarh@mellanox.com> wrote:
> Currently the created tc actions list is reversed against the order
> set by the user.
> Change the actions list order to be the same as was set by the user.
>
> This patch doesn't affect dump actions behavior.
> For dumping, action->order parameter is used so the list order doesn't
> matter.
>
> Signed-off-by: Hadar Hen Zion <hadarh@mellanox.com>
> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Thanks for updating changelog!
^ permalink raw reply
* [ANNOUNCE] Netdev 1.2 updates (27th September, 2016)
From: Hajime Tazaki @ 2016-09-27 16:18 UTC (permalink / raw)
To: netdev, netfilter-devel, linux-wireless, netdev-conference, lwn
Hello folks,
The Linux netdev 1.2 conference will start on next week and
I hope everyone is ready to join us.
== program ==
The full list of accepted sessions (keynotes, workshops,
talks, bofs) are available at the following page.
http://netdevconf.org/1.2/accepted-sessions.html
We will have a great series of the talks; thank you for
your contributions for the great conference.
We're heavily working on finalizing the program; we will
announce it very soon on the web page. Stay tuned.
== travel information ==
You might be the first time to visit Tokyo/Japan (or even
Asian countries). Several trip tips (transportation, venue
access, etc) are listed in our web page; please check it
out before your trip.
http://netdevconf.org/1.2/travel.html
== mailing list ==
We have received a couple of requests to prepare one-time
mailing list only for the netdev 1.2 attendees. We will
prepare the list asap; please freely use the list to
chat/discuss/communicate among the conference attendees.
== sponsors ==
We have finally a great list of our sponsors. Without such
a huge support, the conference never makes it happen. Many
many thanks !
- Platinum
Verizon, Facebook, Cumulus Networks
- Gold
Mojatatu Networks, VMWare, Google, NTT, LinkedIn, Cisco
- Silver
NetApp, IIJ, Netronome, SolarFlare, Mellanox, Sophos,
RedHat, Intel (new)
- Bronze
Zen Load Balancer
- Media sponsor
LWN.net
We're really looking forward to seeing you in Tokyo. We
hope you will have a safe and great trip.
-- Hajime
^ permalink raw reply
* [PATCH net-next] tcp: Change txhash on every SYN and RTO retransmit
From: Lawrence Brakmo @ 2016-09-27 16:06 UTC (permalink / raw)
To: netdev; +Cc: Kernel Team, Eric Dumazet
The current code changes txhash (flowlables) on every retransmitted
SYN/ACK, but only after the 2nd retransmitted SYN and only after
tcp_retries1 RTO retransmits.
With this patch:
1) txhash is changed with every SYN retransmist
2) adds the option for the txhash to be changed before tcp_retries1
RTO retransmits. A new sysctl tcp_rto_txhash_prob represents the
probability that txhash will be changed. The default value is 0
which maintains previous behavior and a value of 100 will always
change it.
Tested with packetdrill tests
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
---
include/net/tcp.h | 1 +
net/ipv4/sysctl_net_ipv4.c | 10 ++++++++++
net/ipv4/tcp_input.c | 2 ++
net/ipv4/tcp_timer.c | 7 +++++++
4 files changed, 20 insertions(+)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f83b7f2..406d474 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -271,6 +271,7 @@ extern int sysctl_tcp_autocorking;
extern int sysctl_tcp_invalid_ratelimit;
extern int sysctl_tcp_pacing_ss_ratio;
extern int sysctl_tcp_pacing_ca_ratio;
+extern int sysctl_tcp_rto_txhash_prob;
extern atomic_long_t tcp_memory_allocated;
extern struct percpu_counter tcp_sockets_allocated;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 1cb67de..0b185a1 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -28,6 +28,7 @@
static int zero;
static int one = 1;
static int four = 4;
+static int hundred = 100;
static int thousand = 1000;
static int gso_max_segs = GSO_MAX_SEGS;
static int tcp_retr1_max = 255;
@@ -624,6 +625,15 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec_ms_jiffies,
},
{
+ .procname = "tcp_rto_txhash_prob",
+ .data = &sysctl_tcp_rto_txhash_prob,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &hundred,
+ },
+ {
.procname = "icmp_msgs_per_sec",
.data = &sysctl_icmp_msgs_per_sec,
.maxlen = sizeof(int),
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8c6ad2d..2fea29d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -101,6 +101,8 @@ int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
int sysctl_tcp_early_retrans __read_mostly = 3;
int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
+int sysctl_tcp_rto_txhash_prob __read_mostly = 100;
+
#define FLAG_DATA 0x01 /* Incoming frame contained data. */
#define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */
#define FLAG_DATA_ACKED 0x04 /* This ACK acknowledged new data. */
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index f712b41..0df8c5f 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -192,6 +192,8 @@ static int tcp_write_timeout(struct sock *sk)
if (tp->syn_data && icsk->icsk_retransmits == 1)
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPFASTOPENACTIVEFAIL);
+ } else if (!tp->syn_data && !tp->syn_fastopen) {
+ sk_rethink_txhash(sk);
}
retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
syn_set = true;
@@ -213,6 +215,11 @@ static int tcp_write_timeout(struct sock *sk)
tcp_mtu_probing(icsk, sk);
dst_negative_advice(sk);
+ } else if (sk->sk_txhash && sysctl_tcp_rto_txhash_prob > 0) {
+ u32 v = prandom_u32() % 100;
+
+ if (v < sysctl_tcp_rto_txhash_prob)
+ sk_set_txhash(sk);
}
retry_until = net->ipv4.sysctl_tcp_retries2;
--
2.9.3
^ permalink raw reply related
* [RFC 3/3] xfrm: remove flow cache
From: Florian Westphal @ 2016-09-27 16:05 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
In-Reply-To: <1474992323-11327-1-git-send-email-fw@strlen.de>
has similar problems as the ipv4 route cache had.
After rcu conversions scalability issues in forward tests
have been resolved.
Performance degradation is currently between 30% (small 64byte packets)
and 10% (1400 byte packets, udp forwarding), mostly due to extra dst
alloc/free overhead.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
include/net/flow.h | 52 -----
include/net/netns/xfrm.h | 10 -
include/net/xfrm.h | 3 -
net/core/Makefile | 1 -
net/core/flow.c | 523 -----------------------------------------------
net/ipv4/xfrm4_policy.c | 9 -
net/ipv6/xfrm6_policy.c | 9 -
net/xfrm/xfrm_policy.c | 294 ++++----------------------
net/xfrm/xfrm_user.c | 2 -
9 files changed, 36 insertions(+), 867 deletions(-)
delete mode 100644 net/core/flow.c
diff --git a/include/net/flow.h b/include/net/flow.h
index 035aa7716967..ccea17714f6b 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -193,57 +193,6 @@ static inline struct flowi *flowidn_to_flowi(struct flowidn *fldn)
return container_of(fldn, struct flowi, u.dn);
}
-typedef unsigned long flow_compare_t;
-
-static inline size_t flow_key_size(u16 family)
-{
- switch (family) {
- case AF_INET:
- BUILD_BUG_ON(sizeof(struct flowi4) % sizeof(flow_compare_t));
- return sizeof(struct flowi4) / sizeof(flow_compare_t);
- case AF_INET6:
- BUILD_BUG_ON(sizeof(struct flowi6) % sizeof(flow_compare_t));
- return sizeof(struct flowi6) / sizeof(flow_compare_t);
- case AF_DECnet:
- BUILD_BUG_ON(sizeof(struct flowidn) % sizeof(flow_compare_t));
- return sizeof(struct flowidn) / sizeof(flow_compare_t);
- }
- return 0;
-}
-
-#define FLOW_DIR_IN 0
-#define FLOW_DIR_OUT 1
-#define FLOW_DIR_FWD 2
-
-struct net;
-struct sock;
-struct flow_cache_ops;
-
-struct flow_cache_object {
- const struct flow_cache_ops *ops;
-};
-
-struct flow_cache_ops {
- struct flow_cache_object *(*get)(struct flow_cache_object *);
- int (*check)(struct flow_cache_object *);
- void (*delete)(struct flow_cache_object *);
-};
-
-typedef struct flow_cache_object *(*flow_resolve_t)(
- struct net *net, const struct flowi *key, u16 family,
- u8 dir, struct flow_cache_object *oldobj, void *ctx);
-
-struct flow_cache_object *flow_cache_lookup(struct net *net,
- const struct flowi *key, u16 family,
- u8 dir, flow_resolve_t resolver,
- void *ctx);
-int flow_cache_init(struct net *net);
-void flow_cache_fini(struct net *net);
-
-void flow_cache_flush(struct net *net);
-void flow_cache_flush_deferred(struct net *net);
-extern atomic_t flow_cache_genid;
-
__u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys);
static inline __u32 get_hash_from_flowi6(const struct flowi6 *fl6)
@@ -261,5 +210,4 @@ static inline __u32 get_hash_from_flowi4(const struct flowi4 *fl4)
return __get_hash_from_flowi4(fl4, &keys);
}
-
#endif
diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 27bb9633c69d..9dc622ab2328 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -73,16 +73,6 @@ struct netns_xfrm {
spinlock_t xfrm_state_lock;
spinlock_t xfrm_policy_lock;
struct mutex xfrm_cfg_mutex;
-
- /* flow cache part */
- struct flow_cache flow_cache_global;
- atomic_t flow_cache_genid;
- struct list_head flow_cache_gc_list;
- atomic_t flow_cache_gc_count;
- spinlock_t flow_cache_gc_lock;
- struct work_struct flow_cache_gc_work;
- struct work_struct flow_cache_flush_work;
- struct mutex flow_flush_sem;
};
#endif
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 31947b9c21d6..01721c18587c 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -280,7 +280,6 @@ struct xfrm_dst;
struct xfrm_policy_afinfo {
unsigned short family;
struct dst_ops *dst_ops;
- void (*garbage_collect)(struct net *net);
struct dst_entry *(*dst_lookup)(struct net *net,
int tos, int oif,
const xfrm_address_t *saddr,
@@ -527,7 +526,6 @@ struct xfrm_policy {
atomic_t refcnt;
struct timer_list timer;
- struct flow_cache_object flo;
atomic_t genid;
u32 priority;
u32 index;
@@ -941,7 +939,6 @@ struct xfrm_dst {
struct rt6_info rt6;
} u;
struct dst_entry *route;
- struct flow_cache_object flo;
struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
int num_pols, num_xfrms;
#ifdef CONFIG_XFRM_SUB_POLICY
diff --git a/net/core/Makefile b/net/core/Makefile
index d6508c2ddca5..1239317a5b0c 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -11,7 +11,6 @@ obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \
neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
sock_diag.o dev_ioctl.o tso.o sock_reuseport.o
-obj-$(CONFIG_XFRM) += flow.o
obj-y += net-sysfs.o
obj-$(CONFIG_PROC_FS) += net-procfs.o
obj-$(CONFIG_NET_PKTGEN) += pktgen.o
diff --git a/net/core/flow.c b/net/core/flow.c
deleted file mode 100644
index 3937b1b68d5b..000000000000
--- a/net/core/flow.c
+++ /dev/null
@@ -1,523 +0,0 @@
-/* flow.c: Generic flow cache.
- *
- * Copyright (C) 2003 Alexey N. Kuznetsov (kuznet@ms2.inr.ac.ru)
- * Copyright (C) 2003 David S. Miller (davem@redhat.com)
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/list.h>
-#include <linux/jhash.h>
-#include <linux/interrupt.h>
-#include <linux/mm.h>
-#include <linux/random.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/smp.h>
-#include <linux/completion.h>
-#include <linux/percpu.h>
-#include <linux/bitops.h>
-#include <linux/notifier.h>
-#include <linux/cpu.h>
-#include <linux/cpumask.h>
-#include <linux/mutex.h>
-#include <net/flow.h>
-#include <linux/atomic.h>
-#include <linux/security.h>
-#include <net/net_namespace.h>
-
-struct flow_cache_entry {
- union {
- struct hlist_node hlist;
- struct list_head gc_list;
- } u;
- struct net *net;
- u16 family;
- u8 dir;
- u32 genid;
- struct flowi key;
- struct flow_cache_object *object;
-};
-
-struct flow_flush_info {
- struct flow_cache *cache;
- atomic_t cpuleft;
- struct completion completion;
-};
-
-static struct kmem_cache *flow_cachep __read_mostly;
-
-#define flow_cache_hash_size(cache) (1 << (cache)->hash_shift)
-#define FLOW_HASH_RND_PERIOD (10 * 60 * HZ)
-
-static void flow_cache_new_hashrnd(unsigned long arg)
-{
- struct flow_cache *fc = (void *) arg;
- int i;
-
- for_each_possible_cpu(i)
- per_cpu_ptr(fc->percpu, i)->hash_rnd_recalc = 1;
-
- fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD;
- add_timer(&fc->rnd_timer);
-}
-
-static int flow_entry_valid(struct flow_cache_entry *fle,
- struct netns_xfrm *xfrm)
-{
- if (atomic_read(&xfrm->flow_cache_genid) != fle->genid)
- return 0;
- if (fle->object && !fle->object->ops->check(fle->object))
- return 0;
- return 1;
-}
-
-static void flow_entry_kill(struct flow_cache_entry *fle,
- struct netns_xfrm *xfrm)
-{
- if (fle->object)
- fle->object->ops->delete(fle->object);
- kmem_cache_free(flow_cachep, fle);
-}
-
-static void flow_cache_gc_task(struct work_struct *work)
-{
- struct list_head gc_list;
- struct flow_cache_entry *fce, *n;
- struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
- flow_cache_gc_work);
-
- INIT_LIST_HEAD(&gc_list);
- spin_lock_bh(&xfrm->flow_cache_gc_lock);
- list_splice_tail_init(&xfrm->flow_cache_gc_list, &gc_list);
- spin_unlock_bh(&xfrm->flow_cache_gc_lock);
-
- list_for_each_entry_safe(fce, n, &gc_list, u.gc_list) {
- flow_entry_kill(fce, xfrm);
- atomic_dec(&xfrm->flow_cache_gc_count);
- WARN_ON(atomic_read(&xfrm->flow_cache_gc_count) < 0);
- }
-}
-
-static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
- int deleted, struct list_head *gc_list,
- struct netns_xfrm *xfrm)
-{
- if (deleted) {
- atomic_add(deleted, &xfrm->flow_cache_gc_count);
- fcp->hash_count -= deleted;
- spin_lock_bh(&xfrm->flow_cache_gc_lock);
- list_splice_tail(gc_list, &xfrm->flow_cache_gc_list);
- spin_unlock_bh(&xfrm->flow_cache_gc_lock);
- schedule_work(&xfrm->flow_cache_gc_work);
- }
-}
-
-static void __flow_cache_shrink(struct flow_cache *fc,
- struct flow_cache_percpu *fcp,
- int shrink_to)
-{
- struct flow_cache_entry *fle;
- struct hlist_node *tmp;
- LIST_HEAD(gc_list);
- int i, deleted = 0;
- struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
- flow_cache_global);
-
- for (i = 0; i < flow_cache_hash_size(fc); i++) {
- int saved = 0;
-
- hlist_for_each_entry_safe(fle, tmp,
- &fcp->hash_table[i], u.hlist) {
- if (saved < shrink_to &&
- flow_entry_valid(fle, xfrm)) {
- saved++;
- } else {
- deleted++;
- hlist_del(&fle->u.hlist);
- list_add_tail(&fle->u.gc_list, &gc_list);
- }
- }
- }
-
- flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);
-}
-
-static void flow_cache_shrink(struct flow_cache *fc,
- struct flow_cache_percpu *fcp)
-{
- int shrink_to = fc->low_watermark / flow_cache_hash_size(fc);
-
- __flow_cache_shrink(fc, fcp, shrink_to);
-}
-
-static void flow_new_hash_rnd(struct flow_cache *fc,
- struct flow_cache_percpu *fcp)
-{
- get_random_bytes(&fcp->hash_rnd, sizeof(u32));
- fcp->hash_rnd_recalc = 0;
- __flow_cache_shrink(fc, fcp, 0);
-}
-
-static u32 flow_hash_code(struct flow_cache *fc,
- struct flow_cache_percpu *fcp,
- const struct flowi *key,
- size_t keysize)
-{
- const u32 *k = (const u32 *) key;
- const u32 length = keysize * sizeof(flow_compare_t) / sizeof(u32);
-
- return jhash2(k, length, fcp->hash_rnd)
- & (flow_cache_hash_size(fc) - 1);
-}
-
-/* I hear what you're saying, use memcmp. But memcmp cannot make
- * important assumptions that we can here, such as alignment.
- */
-static int flow_key_compare(const struct flowi *key1, const struct flowi *key2,
- size_t keysize)
-{
- const flow_compare_t *k1, *k1_lim, *k2;
-
- k1 = (const flow_compare_t *) key1;
- k1_lim = k1 + keysize;
-
- k2 = (const flow_compare_t *) key2;
-
- do {
- if (*k1++ != *k2++)
- return 1;
- } while (k1 < k1_lim);
-
- return 0;
-}
-
-struct flow_cache_object *
-flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
- flow_resolve_t resolver, void *ctx)
-{
- struct flow_cache *fc = &net->xfrm.flow_cache_global;
- struct flow_cache_percpu *fcp;
- struct flow_cache_entry *fle, *tfle;
- struct flow_cache_object *flo;
- size_t keysize;
- unsigned int hash;
-
- local_bh_disable();
- fcp = this_cpu_ptr(fc->percpu);
-
- fle = NULL;
- flo = NULL;
-
- keysize = flow_key_size(family);
- if (!keysize)
- goto nocache;
-
- /* Packet really early in init? Making flow_cache_init a
- * pre-smp initcall would solve this. --RR */
- if (!fcp->hash_table)
- goto nocache;
-
- if (fcp->hash_rnd_recalc)
- flow_new_hash_rnd(fc, fcp);
-
- hash = flow_hash_code(fc, fcp, key, keysize);
- hlist_for_each_entry(tfle, &fcp->hash_table[hash], u.hlist) {
- if (tfle->net == net &&
- tfle->family == family &&
- tfle->dir == dir &&
- flow_key_compare(key, &tfle->key, keysize) == 0) {
- fle = tfle;
- break;
- }
- }
-
- if (unlikely(!fle)) {
- if (fcp->hash_count > fc->high_watermark)
- flow_cache_shrink(fc, fcp);
-
- if (fcp->hash_count > 2 * fc->high_watermark ||
- atomic_read(&net->xfrm.flow_cache_gc_count) > fc->high_watermark) {
- atomic_inc(&net->xfrm.flow_cache_genid);
- flo = ERR_PTR(-ENOBUFS);
- goto ret_object;
- }
-
- fle = kmem_cache_alloc(flow_cachep, GFP_ATOMIC);
- if (fle) {
- fle->net = net;
- fle->family = family;
- fle->dir = dir;
- memcpy(&fle->key, key, keysize * sizeof(flow_compare_t));
- fle->object = NULL;
- hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]);
- fcp->hash_count++;
- }
- } else if (likely(fle->genid == atomic_read(&net->xfrm.flow_cache_genid))) {
- flo = fle->object;
- if (!flo)
- goto ret_object;
- flo = flo->ops->get(flo);
- if (flo)
- goto ret_object;
- } else if (fle->object) {
- flo = fle->object;
- flo->ops->delete(flo);
- fle->object = NULL;
- }
-
-nocache:
- flo = NULL;
- if (fle) {
- flo = fle->object;
- fle->object = NULL;
- }
- flo = resolver(net, key, family, dir, flo, ctx);
- if (fle) {
- fle->genid = atomic_read(&net->xfrm.flow_cache_genid);
- if (!IS_ERR(flo))
- fle->object = flo;
- else
- fle->genid--;
- } else {
- if (!IS_ERR_OR_NULL(flo))
- flo->ops->delete(flo);
- }
-ret_object:
- local_bh_enable();
- return flo;
-}
-EXPORT_SYMBOL(flow_cache_lookup);
-
-static void flow_cache_flush_tasklet(unsigned long data)
-{
- struct flow_flush_info *info = (void *)data;
- struct flow_cache *fc = info->cache;
- struct flow_cache_percpu *fcp;
- struct flow_cache_entry *fle;
- struct hlist_node *tmp;
- LIST_HEAD(gc_list);
- int i, deleted = 0;
- struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
- flow_cache_global);
-
- fcp = this_cpu_ptr(fc->percpu);
- for (i = 0; i < flow_cache_hash_size(fc); i++) {
- hlist_for_each_entry_safe(fle, tmp,
- &fcp->hash_table[i], u.hlist) {
- if (flow_entry_valid(fle, xfrm))
- continue;
-
- deleted++;
- hlist_del(&fle->u.hlist);
- list_add_tail(&fle->u.gc_list, &gc_list);
- }
- }
-
- flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);
-
- if (atomic_dec_and_test(&info->cpuleft))
- complete(&info->completion);
-}
-
-/*
- * Return whether a cpu needs flushing. Conservatively, we assume
- * the presence of any entries means the core may require flushing,
- * since the flow_cache_ops.check() function may assume it's running
- * on the same core as the per-cpu cache component.
- */
-static int flow_cache_percpu_empty(struct flow_cache *fc, int cpu)
-{
- struct flow_cache_percpu *fcp;
- int i;
-
- fcp = per_cpu_ptr(fc->percpu, cpu);
- for (i = 0; i < flow_cache_hash_size(fc); i++)
- if (!hlist_empty(&fcp->hash_table[i]))
- return 0;
- return 1;
-}
-
-static void flow_cache_flush_per_cpu(void *data)
-{
- struct flow_flush_info *info = data;
- struct tasklet_struct *tasklet;
-
- tasklet = &this_cpu_ptr(info->cache->percpu)->flush_tasklet;
- tasklet->data = (unsigned long)info;
- tasklet_schedule(tasklet);
-}
-
-void flow_cache_flush(struct net *net)
-{
- struct flow_flush_info info;
- cpumask_var_t mask;
- int i, self;
-
- /* Track which cpus need flushing to avoid disturbing all cores. */
- if (!alloc_cpumask_var(&mask, GFP_KERNEL))
- return;
- cpumask_clear(mask);
-
- /* Don't want cpus going down or up during this. */
- get_online_cpus();
- mutex_lock(&net->xfrm.flow_flush_sem);
- info.cache = &net->xfrm.flow_cache_global;
- for_each_online_cpu(i)
- if (!flow_cache_percpu_empty(info.cache, i))
- cpumask_set_cpu(i, mask);
- atomic_set(&info.cpuleft, cpumask_weight(mask));
- if (atomic_read(&info.cpuleft) == 0)
- goto done;
-
- init_completion(&info.completion);
-
- local_bh_disable();
- self = cpumask_test_and_clear_cpu(smp_processor_id(), mask);
- on_each_cpu_mask(mask, flow_cache_flush_per_cpu, &info, 0);
- if (self)
- flow_cache_flush_tasklet((unsigned long)&info);
- local_bh_enable();
-
- wait_for_completion(&info.completion);
-
-done:
- mutex_unlock(&net->xfrm.flow_flush_sem);
- put_online_cpus();
- free_cpumask_var(mask);
-}
-
-static void flow_cache_flush_task(struct work_struct *work)
-{
- struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
- flow_cache_flush_work);
- struct net *net = container_of(xfrm, struct net, xfrm);
-
- flow_cache_flush(net);
-}
-
-void flow_cache_flush_deferred(struct net *net)
-{
- schedule_work(&net->xfrm.flow_cache_flush_work);
-}
-
-static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
-{
- struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
- size_t sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc);
-
- if (!fcp->hash_table) {
- fcp->hash_table = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
- if (!fcp->hash_table) {
- pr_err("NET: failed to allocate flow cache sz %zu\n", sz);
- return -ENOMEM;
- }
- fcp->hash_rnd_recalc = 1;
- fcp->hash_count = 0;
- tasklet_init(&fcp->flush_tasklet, flow_cache_flush_tasklet, 0);
- }
- return 0;
-}
-
-static int flow_cache_cpu(struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
-{
- struct flow_cache *fc = container_of(nfb, struct flow_cache,
- hotcpu_notifier);
- int res, cpu = (unsigned long) hcpu;
- struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
-
- switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- res = flow_cache_cpu_prepare(fc, cpu);
- if (res)
- return notifier_from_errno(res);
- break;
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- __flow_cache_shrink(fc, fcp, 0);
- break;
- }
- return NOTIFY_OK;
-}
-
-int flow_cache_init(struct net *net)
-{
- int i;
- struct flow_cache *fc = &net->xfrm.flow_cache_global;
-
- if (!flow_cachep)
- flow_cachep = kmem_cache_create("flow_cache",
- sizeof(struct flow_cache_entry),
- 0, SLAB_PANIC, NULL);
- spin_lock_init(&net->xfrm.flow_cache_gc_lock);
- INIT_LIST_HEAD(&net->xfrm.flow_cache_gc_list);
- INIT_WORK(&net->xfrm.flow_cache_gc_work, flow_cache_gc_task);
- INIT_WORK(&net->xfrm.flow_cache_flush_work, flow_cache_flush_task);
- mutex_init(&net->xfrm.flow_flush_sem);
- atomic_set(&net->xfrm.flow_cache_gc_count, 0);
-
- fc->hash_shift = 10;
- fc->low_watermark = 2 * flow_cache_hash_size(fc);
- fc->high_watermark = 4 * flow_cache_hash_size(fc);
-
- fc->percpu = alloc_percpu(struct flow_cache_percpu);
- if (!fc->percpu)
- return -ENOMEM;
-
- cpu_notifier_register_begin();
-
- for_each_online_cpu(i) {
- if (flow_cache_cpu_prepare(fc, i))
- goto err;
- }
- fc->hotcpu_notifier = (struct notifier_block){
- .notifier_call = flow_cache_cpu,
- };
- __register_hotcpu_notifier(&fc->hotcpu_notifier);
-
- cpu_notifier_register_done();
-
- setup_timer(&fc->rnd_timer, flow_cache_new_hashrnd,
- (unsigned long) fc);
- fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD;
- add_timer(&fc->rnd_timer);
-
- return 0;
-
-err:
- for_each_possible_cpu(i) {
- struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i);
- kfree(fcp->hash_table);
- fcp->hash_table = NULL;
- }
-
- cpu_notifier_register_done();
-
- free_percpu(fc->percpu);
- fc->percpu = NULL;
-
- return -ENOMEM;
-}
-EXPORT_SYMBOL(flow_cache_init);
-
-void flow_cache_fini(struct net *net)
-{
- int i;
- struct flow_cache *fc = &net->xfrm.flow_cache_global;
-
- del_timer_sync(&fc->rnd_timer);
- unregister_hotcpu_notifier(&fc->hotcpu_notifier);
-
- for_each_possible_cpu(i) {
- struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i);
- kfree(fcp->hash_table);
- fcp->hash_table = NULL;
- }
-
- free_percpu(fc->percpu);
- fc->percpu = NULL;
-}
-EXPORT_SYMBOL(flow_cache_fini);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 6a7ff6957535..592ccf5a738a 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -215,14 +215,6 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
fl4->flowi4_tos = iph->tos;
}
-static inline int xfrm4_garbage_collect(struct dst_ops *ops)
-{
- struct net *net = container_of(ops, struct net, xfrm.xfrm4_dst_ops);
-
- xfrm4_policy_afinfo.garbage_collect(net);
- return (dst_entries_get_slow(ops) > ops->gc_thresh * 2);
-}
-
static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
{
@@ -261,7 +253,6 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
static struct dst_ops xfrm4_dst_ops_template = {
.family = AF_INET,
- .gc = xfrm4_garbage_collect,
.update_pmtu = xfrm4_update_pmtu,
.redirect = xfrm4_redirect,
.cow_metrics = dst_cow_metrics_generic,
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index e0f71c01d728..5f9494338d00 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -216,14 +216,6 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
}
}
-static inline int xfrm6_garbage_collect(struct dst_ops *ops)
-{
- struct net *net = container_of(ops, struct net, xfrm.xfrm6_dst_ops);
-
- xfrm6_policy_afinfo.garbage_collect(net);
- return dst_entries_get_fast(ops) > ops->gc_thresh * 2;
-}
-
static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
{
@@ -281,7 +273,6 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
static struct dst_ops xfrm6_dst_ops_template = {
.family = AF_INET6,
- .gc = xfrm6_garbage_collect,
.update_pmtu = xfrm6_update_pmtu,
.redirect = xfrm6_redirect,
.cow_metrics = dst_cow_metrics_generic,
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index fd6986634e6f..b8981ef67b55 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -251,36 +251,6 @@ expired:
xfrm_pol_put(xp);
}
-static struct flow_cache_object *xfrm_policy_flo_get(struct flow_cache_object *flo)
-{
- struct xfrm_policy *pol = container_of(flo, struct xfrm_policy, flo);
-
- if (unlikely(pol->walk.dead))
- flo = NULL;
- else
- xfrm_pol_hold(pol);
-
- return flo;
-}
-
-static int xfrm_policy_flo_check(struct flow_cache_object *flo)
-{
- struct xfrm_policy *pol = container_of(flo, struct xfrm_policy, flo);
-
- return !pol->walk.dead;
-}
-
-static void xfrm_policy_flo_delete(struct flow_cache_object *flo)
-{
- xfrm_pol_put(container_of(flo, struct xfrm_policy, flo));
-}
-
-static const struct flow_cache_ops xfrm_policy_fc_ops = {
- .get = xfrm_policy_flo_get,
- .check = xfrm_policy_flo_check,
- .delete = xfrm_policy_flo_delete,
-};
-
/* Allocate xfrm_policy. Not used here, it is supposed to be used by pfkeyv2
* SPD calls.
*/
@@ -303,7 +273,6 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp)
(unsigned long)policy);
setup_timer(&policy->polq.hold_timer, xfrm_policy_queue_process,
(unsigned long)policy);
- policy->flo.ops = &xfrm_policy_fc_ops;
}
return policy;
}
@@ -803,7 +772,6 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
else
hlist_add_head(&policy->bydst, chain);
__xfrm_policy_link(policy, dir);
- atomic_inc(&net->xfrm.flow_cache_genid);
/* After previous checking, family can either be AF_INET or AF_INET6 */
if (policy->family == AF_INET)
@@ -1192,59 +1160,11 @@ __xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir
return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir);
}
-static int flow_to_policy_dir(int dir)
-{
- if (XFRM_POLICY_IN == FLOW_DIR_IN &&
- XFRM_POLICY_OUT == FLOW_DIR_OUT &&
- XFRM_POLICY_FWD == FLOW_DIR_FWD)
- return dir;
-
- switch (dir) {
- default:
- case FLOW_DIR_IN:
- return XFRM_POLICY_IN;
- case FLOW_DIR_OUT:
- return XFRM_POLICY_OUT;
- case FLOW_DIR_FWD:
- return XFRM_POLICY_FWD;
- }
-}
-
-static struct flow_cache_object *
+static struct xfrm_policy *
xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family,
- u8 dir, struct flow_cache_object *old_obj, void *ctx)
+ u8 dir, void *ctx)
{
- struct xfrm_policy *pol;
-
- if (old_obj)
- xfrm_pol_put(container_of(old_obj, struct xfrm_policy, flo));
-
- pol = __xfrm_policy_lookup(net, fl, family, flow_to_policy_dir(dir));
- if (IS_ERR_OR_NULL(pol))
- return ERR_CAST(pol);
-
- /* Resolver returns two references:
- * one for cache and one for caller of flow_cache_lookup() */
- xfrm_pol_hold(pol);
-
- return &pol->flo;
-}
-
-static inline int policy_to_flow_dir(int dir)
-{
- if (XFRM_POLICY_IN == FLOW_DIR_IN &&
- XFRM_POLICY_OUT == FLOW_DIR_OUT &&
- XFRM_POLICY_FWD == FLOW_DIR_FWD)
- return dir;
- switch (dir) {
- default:
- case XFRM_POLICY_IN:
- return FLOW_DIR_IN;
- case XFRM_POLICY_OUT:
- return FLOW_DIR_OUT;
- case XFRM_POLICY_FWD:
- return FLOW_DIR_FWD;
- }
+ return __xfrm_policy_lookup(net, fl, family, dir);
}
static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
@@ -1267,7 +1187,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
}
err = security_xfrm_policy_lookup(pol->security,
fl->flowi_secid,
- policy_to_flow_dir(dir));
+ dir);
if (!err && !xfrm_pol_hold_rcu(pol))
goto again;
else if (err == -ESRCH)
@@ -1555,56 +1475,6 @@ static inline int xfrm_get_tos(const struct flowi *fl, int family)
return tos;
}
-static struct flow_cache_object *xfrm_bundle_flo_get(struct flow_cache_object *flo)
-{
- struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo);
- struct dst_entry *dst = &xdst->u.dst;
-
- if (xdst->route == NULL) {
- /* Dummy bundle - if it has xfrms we were not
- * able to build bundle as template resolution failed.
- * It means we need to try again resolving. */
- if (xdst->num_xfrms > 0)
- return NULL;
- } else if (dst->flags & DST_XFRM_QUEUE) {
- return NULL;
- } else {
- /* Real bundle */
- if (stale_bundle(dst))
- return NULL;
- }
-
- dst_hold(dst);
- return flo;
-}
-
-static int xfrm_bundle_flo_check(struct flow_cache_object *flo)
-{
- struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo);
- struct dst_entry *dst = &xdst->u.dst;
-
- if (!xdst->route)
- return 0;
- if (stale_bundle(dst))
- return 0;
-
- return 1;
-}
-
-static void xfrm_bundle_flo_delete(struct flow_cache_object *flo)
-{
- struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo);
- struct dst_entry *dst = &xdst->u.dst;
-
- dst_free(dst);
-}
-
-static const struct flow_cache_ops xfrm_bundle_fc_ops = {
- .get = xfrm_bundle_flo_get,
- .check = xfrm_bundle_flo_check,
- .delete = xfrm_bundle_flo_delete,
-};
-
static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
{
struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
@@ -1626,13 +1496,12 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
default:
BUG();
}
- xdst = dst_alloc(dst_ops, NULL, 0, DST_OBSOLETE_NONE, 0);
+ xdst = dst_alloc(dst_ops, NULL, 0, DST_OBSOLETE_NONE, DST_NOCACHE);
if (likely(xdst)) {
struct dst_entry *dst = &xdst->u.dst;
memset(dst + 1, 0, sizeof(*xdst) - sizeof(*dst));
- xdst->flo.ops = &xfrm_bundle_fc_ops;
} else
xdst = ERR_PTR(-ENOBUFS);
@@ -2108,81 +1977,43 @@ free_dst:
goto out;
}
-static struct flow_cache_object *
-xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir,
- struct flow_cache_object *oldflo, void *ctx)
+static struct xfrm_dst *
+xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, struct xfrm_flo *xflo)
{
- struct xfrm_flo *xflo = (struct xfrm_flo *)ctx;
struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
- struct xfrm_dst *xdst, *new_xdst;
- int num_pols = 0, num_xfrms = 0, i, err, pol_dead;
-
- /* Check if the policies from old bundle are usable */
- xdst = NULL;
- if (oldflo) {
- xdst = container_of(oldflo, struct xfrm_dst, flo);
- num_pols = xdst->num_pols;
- num_xfrms = xdst->num_xfrms;
- pol_dead = 0;
- for (i = 0; i < num_pols; i++) {
- pols[i] = xdst->pols[i];
- pol_dead |= pols[i]->walk.dead;
- }
- if (pol_dead) {
- dst_free(&xdst->u.dst);
- xdst = NULL;
- num_pols = 0;
- num_xfrms = 0;
- oldflo = NULL;
- }
- }
+ struct xfrm_dst *xdst;
+ int num_pols = 0, num_xfrms = 0, err;
/* Resolve policies to use if we couldn't get them from
* previous cache entry */
- if (xdst == NULL) {
- num_pols = 1;
- pols[0] = __xfrm_policy_lookup(net, fl, family,
- flow_to_policy_dir(dir));
- err = xfrm_expand_policies(fl, family, pols,
+ num_pols = 1;
+ pols[0] = __xfrm_policy_lookup(net, fl, family, dir);
+ err = xfrm_expand_policies(fl, family, pols,
&num_pols, &num_xfrms);
- if (err < 0)
- goto inc_error;
- if (num_pols == 0)
- return NULL;
- if (num_xfrms <= 0)
- goto make_dummy_bundle;
- }
+ if (err < 0)
+ goto inc_error;
+ if (num_pols == 0)
+ return NULL;
+ if (num_xfrms <= 0)
+ goto make_dummy_bundle;
- new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family,
+ xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family,
xflo->dst_orig);
- if (IS_ERR(new_xdst)) {
- err = PTR_ERR(new_xdst);
+ if (IS_ERR(xdst)) {
+ err = PTR_ERR(xdst);
if (err != -EAGAIN)
goto error;
- if (oldflo == NULL)
- goto make_dummy_bundle;
- dst_hold(&xdst->u.dst);
- return oldflo;
- } else if (new_xdst == NULL) {
+ goto make_dummy_bundle;
+ } else if (xdst == NULL) {
num_xfrms = 0;
- if (oldflo == NULL)
- goto make_dummy_bundle;
- xdst->num_xfrms = 0;
- dst_hold(&xdst->u.dst);
- return oldflo;
- }
-
- /* Kill the previous bundle */
- if (xdst) {
- /* The policies were stolen for newly generated bundle */
- xdst->num_pols = 0;
- dst_free(&xdst->u.dst);
+ goto make_dummy_bundle;
}
/* Flow cache does not have reference, it dst_free()'s,
* but we do need to return one reference for original caller */
- dst_hold(&new_xdst->u.dst);
- return &new_xdst->flo;
+ dst_hold(&xdst->u.dst);
+
+ return xdst;
make_dummy_bundle:
/* We found policies, but there's no bundles to instantiate:
@@ -2198,15 +2029,12 @@ make_dummy_bundle:
memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
dst_hold(&xdst->u.dst);
- return &xdst->flo;
+ return xdst;
inc_error:
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
error:
- if (xdst != NULL)
- dst_free(&xdst->u.dst);
- else
- xfrm_pols_put(pols, num_pols);
+ xfrm_pols_put(pols, num_pols);
return ERR_PTR(err);
}
@@ -2237,11 +2065,10 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
const struct sock *sk, int flags)
{
struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
- struct flow_cache_object *flo;
struct xfrm_dst *xdst;
struct dst_entry *dst, *route;
u16 family = dst_orig->ops->family;
- u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT);
+ u8 dir = XFRM_POLICY_OUT;
int i, err, num_pols, num_xfrms = 0, drop_pols = 0;
dst = NULL;
@@ -2293,15 +2120,13 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
!net->xfrm.policy_count[XFRM_POLICY_OUT])
goto nopol;
- flo = flow_cache_lookup(net, fl, family, dir,
- xfrm_bundle_lookup, &xflo);
- if (flo == NULL)
+ xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo);
+ if (xdst == NULL)
goto nopol;
- if (IS_ERR(flo)) {
- err = PTR_ERR(flo);
+ if (IS_ERR(xdst)) {
+ err = PTR_ERR(xdst);
goto dropdst;
}
- xdst = container_of(flo, struct xfrm_dst, flo);
num_pols = xdst->num_pols;
num_xfrms = xdst->num_xfrms;
@@ -2500,12 +2325,10 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
int pi;
int reverse;
struct flowi fl;
- u8 fl_dir;
int xerr_idx = -1;
reverse = dir & ~XFRM_POLICY_MASK;
dir &= XFRM_POLICY_MASK;
- fl_dir = policy_to_flow_dir(dir);
if (__xfrm_decode_session(skb, &fl, family, reverse) < 0) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
@@ -2537,16 +2360,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
}
}
- if (!pol) {
- struct flow_cache_object *flo;
-
- flo = flow_cache_lookup(net, &fl, family, fl_dir,
- xfrm_policy_lookup, NULL);
- if (IS_ERR_OR_NULL(flo))
- pol = ERR_CAST(flo);
- else
- pol = container_of(flo, struct xfrm_policy, flo);
- }
+ if (!pol)
+ pol = xfrm_policy_lookup(net, &fl, family, dir, NULL);
if (IS_ERR(pol)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
@@ -2734,17 +2549,6 @@ static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst)
return dst;
}
-void xfrm_garbage_collect(struct net *net)
-{
- flow_cache_flush(net);
-}
-EXPORT_SYMBOL(xfrm_garbage_collect);
-
-static void xfrm_garbage_collect_deferred(struct net *net)
-{
- flow_cache_flush_deferred(net);
-}
-
static void xfrm_init_pmtu(struct dst_entry *dst)
{
do {
@@ -2880,8 +2684,6 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
dst_ops->link_failure = xfrm_link_failure;
if (likely(dst_ops->neigh_lookup == NULL))
dst_ops->neigh_lookup = xfrm_neigh_lookup;
- if (likely(afinfo->garbage_collect == NULL))
- afinfo->garbage_collect = xfrm_garbage_collect_deferred;
rcu_assign_pointer(xfrm_policy_afinfo[afinfo->family], afinfo);
}
spin_unlock(&xfrm_policy_afinfo_lock);
@@ -2915,27 +2717,11 @@ int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo)
dst_ops->check = NULL;
dst_ops->negative_advice = NULL;
dst_ops->link_failure = NULL;
- afinfo->garbage_collect = NULL;
}
return err;
}
EXPORT_SYMBOL(xfrm_policy_unregister_afinfo);
-static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr)
-{
- struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-
- switch (event) {
- case NETDEV_DOWN:
- xfrm_garbage_collect(dev_net(dev));
- }
- return NOTIFY_DONE;
-}
-
-static struct notifier_block xfrm_dev_notifier = {
- .notifier_call = xfrm_dev_event,
-};
-
#ifdef CONFIG_XFRM_STATISTICS
static int __net_init xfrm_statistics_init(struct net *net)
{
@@ -3011,8 +2797,6 @@ static int __net_init xfrm_policy_init(struct net *net)
INIT_LIST_HEAD(&net->xfrm.policy_all);
INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize);
INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild);
- if (net_eq(net, &init_net))
- register_netdevice_notifier(&xfrm_dev_notifier);
return 0;
out_bydst:
@@ -3072,9 +2856,6 @@ static int __net_init xfrm_net_init(struct net *net)
rv = xfrm_sysctl_init(net);
if (rv < 0)
goto out_sysctl;
- rv = flow_cache_init(net);
- if (rv < 0)
- goto out;
/* Initialize the per-net locks here */
spin_lock_init(&net->xfrm.xfrm_state_lock);
@@ -3083,8 +2864,6 @@ static int __net_init xfrm_net_init(struct net *net)
return 0;
-out:
- xfrm_sysctl_fini(net);
out_sysctl:
xfrm_policy_fini(net);
out_policy:
@@ -3097,7 +2876,6 @@ out_statistics:
static void __net_exit xfrm_net_exit(struct net *net)
{
- flow_cache_fini(net);
xfrm_sysctl_fini(net);
xfrm_policy_fini(net);
xfrm_state_fini(net);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 08892091cfe3..478545291a91 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1780,8 +1780,6 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
out:
xfrm_pol_put(xp);
- if (delete && err == 0)
- xfrm_garbage_collect(net);
return err;
}
--
2.7.3
^ permalink raw reply related
* [RFC 1/3] xfrm: state: do not acquire lock in get_mtu helpers
From: Florian Westphal @ 2016-09-27 16:05 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
In-Reply-To: <1474992323-11327-1-git-send-email-fw@strlen.de>
Once flow cache is removed the mtu initialisation happens for every skb
that gets an xfrm attached to it.
It is not obvious why this lock is required -- the caller holds
reference on the state struct.
xfrm_init_state already has been called (else private data accessed
by type->get_mtu() would not be set up).
So just remove the lock -- the race on the state (DEAD?) doesn't
matter (could change right after dropping the lock too).
Signed-off-by: Florian Westphal <fw@strlen.de>
---
net/xfrm/xfrm_state.c | 13 +++++--------
1 file changed, 5 insertions(+), 8 deletions(-)
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index f9a255457a1d..bf5969aa7dc2 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2008,16 +2008,13 @@ EXPORT_SYMBOL(xfrm_state_delete_tunnel);
int xfrm_state_mtu(struct xfrm_state *x, int mtu)
{
- int res;
+ const struct xfrm_type *type = READ_ONCE(x->type);
- spin_lock_bh(&x->lock);
if (x->km.state == XFRM_STATE_VALID &&
- x->type && x->type->get_mtu)
- res = x->type->get_mtu(x, mtu);
- else
- res = mtu - x->props.header_len;
- spin_unlock_bh(&x->lock);
- return res;
+ type && type->get_mtu)
+ return type->get_mtu(x, mtu);
+
+ return mtu - x->props.header_len;
}
int __xfrm_init_state(struct xfrm_state *x, bool init_replay)
--
2.7.3
^ permalink raw reply related
* [RFC 2/3] vti: revert flush x-netns xfrm cache when vti interface is removed
From: Florian Westphal @ 2016-09-27 16:05 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
In-Reply-To: <1474992323-11327-1-git-send-email-fw@strlen.de>
flow cache is removed in next patch.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
net/ipv4/ip_vti.c | 31 -------------------------------
1 file changed, 31 deletions(-)
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 5d7944f394d9..c9957edee25e 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -570,33 +570,6 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = {
.get_link_net = ip_tunnel_get_link_net,
};
-static bool is_vti_tunnel(const struct net_device *dev)
-{
- return dev->netdev_ops == &vti_netdev_ops;
-}
-
-static int vti_device_event(struct notifier_block *unused,
- unsigned long event, void *ptr)
-{
- struct net_device *dev = netdev_notifier_info_to_dev(ptr);
- struct ip_tunnel *tunnel = netdev_priv(dev);
-
- if (!is_vti_tunnel(dev))
- return NOTIFY_DONE;
-
- switch (event) {
- case NETDEV_DOWN:
- if (!net_eq(tunnel->net, dev_net(dev)))
- xfrm_garbage_collect(tunnel->net);
- break;
- }
- return NOTIFY_DONE;
-}
-
-static struct notifier_block vti_notifier_block __read_mostly = {
- .notifier_call = vti_device_event,
-};
-
static int __init vti_init(void)
{
const char *msg;
@@ -604,8 +577,6 @@ static int __init vti_init(void)
pr_info("IPv4 over IPsec tunneling driver\n");
- register_netdevice_notifier(&vti_notifier_block);
-
msg = "tunnel device";
err = register_pernet_device(&vti_net_ops);
if (err < 0)
@@ -638,7 +609,6 @@ xfrm_proto_ah_failed:
xfrm_proto_esp_failed:
unregister_pernet_device(&vti_net_ops);
pernet_dev_failed:
- unregister_netdevice_notifier(&vti_notifier_block);
pr_err("vti init: failed to register %s\n", msg);
return err;
}
@@ -650,7 +620,6 @@ static void __exit vti_fini(void)
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
unregister_pernet_device(&vti_net_ops);
- unregister_netdevice_notifier(&vti_notifier_block);
}
module_init(vti_init);
--
2.7.3
^ permalink raw reply related
* [RFC 0/3] ipsec: flow cache removal
From: Florian Westphal @ 2016-09-27 16:05 UTC (permalink / raw)
To: netdev
Please do not apply these patches.
These are part of tests I made for the ipsec workshop at upcoming
netdev 1.2 and I wanted to post these before the conference.
Short version is that there appear to be no major scalability issues
anymore without flow cache. Performance hit can be up to 30%
in my tests (with 64 byte packets), however without flow cache we
also avoid some undesirable effects when flow cache is constantly
overloaded.
Seems most of the extra cost is mainly because of extra xfrm dst
init/destruction (and not e.g. due to policy lookup).
Lets discuss more at the workshop.
Thanks,
Florian
^ permalink raw reply
* [PATCH v3] Net Driver: Add Cypress GX3 VID=04b4 PID=3610.
From: chris.roth @ 2016-09-27 15:57 UTC (permalink / raw)
To: linux-usb, netdev, linux-kernel; +Cc: Chris Roth, Allan Chou
From: Chris Roth <chris.roth@usask.ca>
>From Allan Chou <allan@asix.com.tw>
From: Chris Roth <chris.roth@usask.ca>
Add support for Cypress GX3 SuperSpeed to Gigabit Ethernet
Bridge Controller (Vendor=04b4 ProdID=3610).
Patch verified on x64 linux kernel 4.7.4 system with the
Kensington SD4600P USB-C Universal Dock with Power, which uses the
Cypress GX3 SuperSpeed to Gigabit Ethernet Bridge Controller.
A similar patch was signed-off and tested-by Allan Chou
<allan@asix.com.tw> on 2015-12-01.
Allan verified his similar patch on x86 Linux kernel 4.1.6 system
with Cypress GX3 SuperSpeed to Gigabit Ethernet Bridge Controller.
Tested-by: Allan Chou <allan@asix.com.tw>
Tested-by: Chris Roth <chris.roth@usask.ca>
Signed-off-by: Allan Chou <allan@asix.com.tw>
Signed-off-by: Chris Roth <chris.roth@usask.ca>
---
drivers/net/usb/ax88179_178a.c | 17 +++++++++++++++++
1 file changed, 17 insertions(+)
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index e6338c1..8a6675d 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1656,6 +1656,19 @@ static const struct driver_info ax88178a_info = {
.tx_fixup = ax88179_tx_fixup,
};
+static const struct driver_info cypress_GX3_info = {
+ .description = "Cypress GX3 SuperSpeed to Gigabit Ethernet Controller",
+ .bind = ax88179_bind,
+ .unbind = ax88179_unbind,
+ .status = ax88179_status,
+ .link_reset = ax88179_link_reset,
+ .reset = ax88179_reset,
+ .stop = ax88179_stop,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
+ .rx_fixup = ax88179_rx_fixup,
+ .tx_fixup = ax88179_tx_fixup,
+};
+
static const struct driver_info dlink_dub1312_info = {
.description = "D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter",
.bind = ax88179_bind,
@@ -1718,6 +1731,10 @@ static const struct usb_device_id products[] = {
USB_DEVICE(0x0b95, 0x178a),
.driver_info = (unsigned long)&ax88178a_info,
}, {
+ /* Cypress GX3 SuperSpeed to Gigabit Ethernet Bridge Controller */
+ USB_DEVICE(0x04b4, 0x3610),
+ .driver_info = (unsigned long)&cypress_GX3_info,
+}, {
/* D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter */
USB_DEVICE(0x2001, 0x4a00),
.driver_info = (unsigned long)&dlink_dub1312_info,
--
2.7.4
^ permalink raw reply related
* [PATCH ipsec-next] xfrm: remove unused helper
From: Florian Westphal @ 2016-09-27 15:53 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
Not used anymore since 2009 (9e0d57fd6dad37,
'xfrm: SAD entries do not expire correctly after suspend-resume').
Signed-off-by: Florian Westphal <fw@strlen.de>
---
net/xfrm/xfrm_state.c | 8 --------
1 file changed, 8 deletions(-)
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index bf5969aa7dc2..9ca9a30c3fcf 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -388,14 +388,6 @@ static void xfrm_state_gc_task(struct work_struct *work)
xfrm_state_gc_destroy(x);
}
-static inline unsigned long make_jiffies(long secs)
-{
- if (secs >= (MAX_SCHEDULE_TIMEOUT-1)/HZ)
- return MAX_SCHEDULE_TIMEOUT-1;
- else
- return secs*HZ;
-}
-
static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
{
struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer);
--
2.7.3
^ permalink raw reply related
* Re: [V2, 4.9] brcmfmac: use correct skb freeing helper when deleting flowring
From: Kalle Valo @ 2016-09-27 15:48 UTC (permalink / raw)
To: Rafał Miłecki
Cc: Arend van Spriel, Franky Lin, Hante Meuleman,
Pieter-Paul Giesberts, Franky Lin, linux-wireless,
brcm80211-dev-list.pdl, netdev, linux-kernel,
Rafał Miłecki
In-Reply-To: <20160927121104.5771-1-zajec5@gmail.com>
Rafał Miłecki wrote:
> From: Rafał Miłecki <rafal@milecki.pl>
>
> Flowrings contain skbs waiting for transmission that were passed to us
> by netif. It means we checked every one of them looking for 802.1x
> Ethernet type. When deleting flowring we have to use freeing function
> that will check for 802.1x type as well.
>
> Freeing skbs without a proper check was leading to counter not being
> properly decreased. This was triggering a WARNING every time
> brcmf_netdev_wait_pend8021x was called.
>
> Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
> Acked-by: Arend van Spriel <arend@broadcom.com>
> Cc: stable@vger.kernel.org # 4.5+
Patch applied to wireless-drivers-next.git, thanks.
7f00ee2bbc63 brcmfmac: use correct skb freeing helper when deleting flowring
--
https://patchwork.kernel.org/patch/9351797/
Documentation about submitting wireless patches and checking status
from patchwork:
https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches
^ permalink raw reply
* Re: brcmfmac: replace WARNING on timeout with a simple error message
From: Kalle Valo @ 2016-09-27 15:47 UTC (permalink / raw)
To: Rafał Miłecki
Cc: Arend van Spriel, Franky Lin, Hante Meuleman,
Pieter-Paul Giesberts, Franky Lin, linux-wireless,
brcm80211-dev-list.pdl, netdev, linux-kernel,
Rafał Miłecki
In-Reply-To: <20160927101224.3534-1-zajec5@gmail.com>
Rafał Miłecki wrote:
> From: Rafał Miłecki <rafal@milecki.pl>
>
> Even with timeout increased to 950 ms we get WARNINGs from time to time.
> It mostly happens on A-MPDU stalls (e.g. when station goes out of
> range). It may take up to 5-10 secods for the firmware to recover and
> for that time it doesn't process packets.
>
> It's still useful to have a message on time out as it may indicate some
> firmware problem and incorrect key update. Raising a WARNING however
> wasn't really that necessary, it doesn't point to any driver bug anymore
> and backtrace wasn't much useful.
>
> Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
> Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Patch applied to wireless-drivers-next.git, thanks.
2f0e56fa37cc brcmfmac: replace WARNING on timeout with a simple error message
--
https://patchwork.kernel.org/patch/9351657/
Documentation about submitting wireless patches and checking status
from patchwork:
https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches
^ permalink raw reply
* Re: [PATCH v4] net: ip, diag -- Add diag interface for raw sockets
From: Cyrill Gorcunov @ 2016-09-27 15:45 UTC (permalink / raw)
To: Eric Dumazet
Cc: David Ahern, netdev, linux-kernel, David Miller, kuznet, jmorris,
yoshfuji, kaber, avagin, stephen
In-Reply-To: <1474990799.28155.54.camel@edumazet-glaptop3.roam.corp.google.com>
On Tue, Sep 27, 2016 at 08:39:59AM -0700, Eric Dumazet wrote:
...
> > + }
> > + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
> > + sk = NULL;
>
> Minor detail, but note that raw sockets do not use rcu (yet)
>
> Since you have read_lock(&hashinfo->lock), no writer can suddenly change
> sk->sk_refcnt to a zero value.
>
> Therefore, a mere "sock_hold(sk)" should be enough to get a reference on
> the socket.
>
> Using atomic_inc_not_zero() also works, but might distract/confuse the
> next guy trying to understand this code ;)
Oh, I see. Thanks Eric! I'll update the patch (hopefully tonight)
and send it out (need to finish urgent task atm).
^ permalink raw reply
* Re: rtlwifi: Add switch variable to 'switch case not processed' messages
From: Kalle Valo @ 2016-09-27 15:45 UTC (permalink / raw)
To: Joe Perches
Cc: Larry Finger, Jean Delvare, Chaoming Li, linux-wireless, netdev,
linux-kernel
In-Reply-To: <d091f73a6adf3bdaa09ab0399c22a9fdfe9b188c.1474654979.git.joe@perches.com>
Joe Perches <joe@perches.com> wrote:
> Help along debugging by showing what switch/case variable is not
> being processed in these messages.
>
> Signed-off-by: Joe Perches <joe@perches.com>
> Acked-by: Larry Finger <Larry.Finger@lwfinger.net>
Patch applied to wireless-drivers-next.git, thanks.
ad5748893b27 rtlwifi: Add switch variable to 'switch case not processed' messages
--
https://patchwork.kernel.org/patch/9348573/
Documentation about submitting wireless patches and checking status
from patchwork:
https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches
^ permalink raw reply
* [PATCH trival -resend 1/2] bpf: clean up put_cpu_var usage
From: Shaohua Li @ 2016-09-27 15:42 UTC (permalink / raw)
To: linux-kernel, netdev
Cc: David S . Miller, akpm, Tejun Heo, Alexei Starovoitov
put_cpu_var takes the percpu data, not the data returned from
get_cpu_var.
This doesn't change the behavior.
Cc: Tejun Heo <tj@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Shaohua Li <shli@fb.com>
---
kernel/bpf/core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 7b7baae..aa6d981 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1031,7 +1031,7 @@ BPF_CALL_0(bpf_user_rnd_u32)
state = &get_cpu_var(bpf_user_rnd_state);
res = prandom_u32_state(state);
- put_cpu_var(state);
+ put_cpu_var(bpf_user_rnd_state);
return res;
}
--
2.9.3
^ permalink raw reply related
* [PATCH trival -resend 2/2] lib: clean up put_cpu_var usage
From: Shaohua Li @ 2016-09-27 15:42 UTC (permalink / raw)
To: linux-kernel, netdev; +Cc: David S . Miller, akpm, Tejun Heo
In-Reply-To: <7ffd1960225e024a738e4c372f091bb49096e294.1474990741.git.shli@fb.com>
put_cpu_var takes the percpu data, not the data returned from
get_cpu_var.
This doesn't change the behavior.
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Shaohua Li <shli@fb.com>
---
lib/random32.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/lib/random32.c b/lib/random32.c
index a309235..fa594b1 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -81,7 +81,7 @@ u32 prandom_u32(void)
u32 res;
res = prandom_u32_state(state);
- put_cpu_var(state);
+ put_cpu_var(net_rand_state);
return res;
}
@@ -128,7 +128,7 @@ void prandom_bytes(void *buf, size_t bytes)
struct rnd_state *state = &get_cpu_var(net_rand_state);
prandom_bytes_state(state, buf, bytes);
- put_cpu_var(state);
+ put_cpu_var(net_rand_state);
}
EXPORT_SYMBOL(prandom_bytes);
--
2.9.3
^ permalink raw reply related
* Re: [PATCH v2] Net Driver: Add Cypress GX3 VID=04b4 PID=3610.
From: Greg KH @ 2016-09-27 15:40 UTC (permalink / raw)
To: Chris Roth; +Cc: linux-usb, netdev, linux-kernel
In-Reply-To: <CAPZMiRa6=So14ic8SMSkbHdrVH8-7vA1+Wg_hWJoAgr8G_mhyw@mail.gmail.com>
On Mon, Sep 26, 2016 at 03:56:59PM -0600, Chris Roth wrote:
> I'm not sure what I'm doing wrong:
>
> I'm trying to get the from statement to read original author (Allan
> Chou) first, and then me (Chris Roth) second. I've used the following
> two commands:
>
> git format-patch -o /tmp/ --subject-prefix="PATCH v2" --from="Allan
> Chou <allan@asix.com.tw>" HEAD^
>
> and
>
> git send-email --to linux-usb@vger.kernel.org --to
> netdev@vger.kernel.org --to linux-kernel@vger.kernel.org --from="Allan
> Chou <allan@asix.com.tw>"
> /tmp/0001-Net-Driver-Add-Cypress-GX3-VID-04b4-PID-3610.patch
>
> I thought that adding the --from portions to the git format-patch and
> git send-email commands would force the addition of Allan to the top
> of the patch, but it hasn't. Can anyone tell me specifically how I
> need to change these commands in order to get the desired result? Then
> I'll submit a PATCH v3.
Take the patch that you have, hand-edit it with your favorite editor to
have the correct headers and signed-off-by and other fields, and then
use git send-email without the --from line, and you should be fine.
thanks,
greg k-h
^ permalink raw reply
* Re: [PATCH v4] net: ip, diag -- Add diag interface for raw sockets
From: Eric Dumazet @ 2016-09-27 15:39 UTC (permalink / raw)
To: Cyrill Gorcunov
Cc: David Ahern, netdev, linux-kernel, David Miller, kuznet, jmorris,
yoshfuji, kaber, avagin, stephen
In-Reply-To: <20160927150831.GN1876@uranus.lan>
On Tue, 2016-09-27 at 18:08 +0300, Cyrill Gorcunov wrote:
> +static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 *r)
> +{
> + struct raw_hashinfo *hashinfo = raw_get_hashinfo(r);
> + struct sock *sk = NULL, *s;
> + int slot;
> +
> + if (IS_ERR(hashinfo))
> + return ERR_CAST(hashinfo);
> +
> + read_lock(&hashinfo->lock);
> + for (slot = 0; slot < RAW_HTABLE_SIZE; slot++) {
> + sk_for_each(s, &hashinfo->ht[slot]) {
> + sk = raw_lookup(net, s, r);
> + if (sk)
> + break;
> + }
> + }
> + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
> + sk = NULL;
Minor detail, but note that raw sockets do not use rcu (yet)
Since you have read_lock(&hashinfo->lock), no writer can suddenly change
sk->sk_refcnt to a zero value.
Therefore, a mere "sock_hold(sk)" should be enough to get a reference on
the socket.
Using atomic_inc_not_zero() also works, but might distract/confuse the
next guy trying to understand this code ;)
> + read_unlock(&hashinfo->lock);
> +
> + return sk ? sk : ERR_PTR(-ENOENT);
> +}
> +
^ permalink raw reply
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