* [PATCH -next 20/22] net: socket: add __compat_sys_getsockopt() helper; remove in-kernel call to compat syscall
From: Dominik Brodowski @ 2018-03-16 17:06 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __compat_sys_getsockopt() allows us to avoid
the internal calls to the compat_sys_getsockopt() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
net/compat.c | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)
diff --git a/net/compat.c b/net/compat.c
index 75bfcbbb2e3e..cdf5b0c1b962 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -509,8 +509,9 @@ int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *usersta
}
EXPORT_SYMBOL(compat_sock_get_timestampns);
-COMPAT_SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
- char __user *, optval, int __user *, optlen)
+static int __compat_sys_getsockopt(int fd, int level, int optname,
+ char __user *optval,
+ int __user *optlen)
{
int err;
struct socket *sock = sockfd_lookup(fd, &err);
@@ -536,6 +537,12 @@ COMPAT_SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
return err;
}
+COMPAT_SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
+ char __user *, optval, int __user *, optlen)
+{
+ return __compat_sys_getsockopt(fd, level, optname, optval, optlen);
+}
+
struct compat_group_req {
__u32 gr_interface;
struct __kernel_sockaddr_storage gr_group
@@ -874,8 +881,9 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
compat_ptr(a[3]), a[4]);
break;
case SYS_GETSOCKOPT:
- ret = compat_sys_getsockopt(a0, a1, a[2],
- compat_ptr(a[3]), compat_ptr(a[4]));
+ ret = __compat_sys_getsockopt(a0, a1, a[2],
+ compat_ptr(a[3]),
+ compat_ptr(a[4]));
break;
case SYS_SENDMSG:
ret = compat_sys_sendmsg(a0, compat_ptr(a1), a[2]);
--
2.16.2
^ permalink raw reply related
* [PATCH -next 19/22] net: socket: add __compat_sys_setsockopt() helper; remove in-kernel call to compat syscall
From: Dominik Brodowski @ 2018-03-16 17:06 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __compat_sys_setsockopt() allows us to avoid
the internal calls to the compat_sys_setsockopt() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
net/compat.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/net/compat.c b/net/compat.c
index 513adc8d0e0f..75bfcbbb2e3e 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -383,8 +383,8 @@ static int compat_sock_setsockopt(struct socket *sock, int level, int optname,
return sock_setsockopt(sock, level, optname, optval, optlen);
}
-COMPAT_SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
- char __user *, optval, unsigned int, optlen)
+static int __compat_sys_setsockopt(int fd, int level, int optname,
+ char __user *optval, unsigned int optlen)
{
int err;
struct socket *sock = sockfd_lookup(fd, &err);
@@ -410,6 +410,12 @@ COMPAT_SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
return err;
}
+COMPAT_SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
+ char __user *, optval, unsigned int, optlen)
+{
+ return __compat_sys_setsockopt(fd, level, optname, optval, optlen);
+}
+
static int do_get_sock_timeout(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen)
{
@@ -864,8 +870,8 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = __sys_shutdown(a0, a1);
break;
case SYS_SETSOCKOPT:
- ret = compat_sys_setsockopt(a0, a1, a[2],
- compat_ptr(a[3]), a[4]);
+ ret = __compat_sys_setsockopt(a0, a1, a[2],
+ compat_ptr(a[3]), a[4]);
break;
case SYS_GETSOCKOPT:
ret = compat_sys_getsockopt(a0, a1, a[2],
--
2.16.2
^ permalink raw reply related
* [PATCH -next 18/22] net: socket: add __compat_sys_recvfrom() helper; remove in-kernel call to compat syscall
From: Dominik Brodowski @ 2018-03-16 17:06 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __compat_sys_recvfrom() allows us to avoid
the internal calls to the compat_sys_recvfrom() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
net/compat.c | 23 ++++++++++++++++-------
1 file changed, 16 insertions(+), 7 deletions(-)
diff --git a/net/compat.c b/net/compat.c
index 9e0d030063ad..513adc8d0e0f 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -753,18 +753,25 @@ COMPAT_SYSCALL_DEFINE3(recvmsg, int, fd, struct compat_msghdr __user *, msg, uns
flags | MSG_CMSG_COMPAT, false);
}
+static inline long __compat_sys_recvfrom(int fd, void __user *buf,
+ compat_size_t len, unsigned int flags,
+ struct sockaddr __user *addr,
+ int __user *addrlen)
+{
+ return __sys_recvfrom(fd, buf, len, flags | MSG_CMSG_COMPAT, addr,
+ addrlen);
+}
+
COMPAT_SYSCALL_DEFINE4(recv, int, fd, void __user *, buf, compat_size_t, len, unsigned int, flags)
{
- return __sys_recvfrom(fd, buf, len, flags | MSG_CMSG_COMPAT, NULL,
- NULL);
+ return __compat_sys_recvfrom(fd, buf, len, flags, NULL, NULL);
}
COMPAT_SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, buf, compat_size_t, len,
unsigned int, flags, struct sockaddr __user *, addr,
int __user *, addrlen)
{
- return __sys_recvfrom(fd, buf, len, flags | MSG_CMSG_COMPAT, addr,
- addrlen);
+ return __compat_sys_recvfrom(fd, buf, len, flags, addr, addrlen);
}
COMPAT_SYSCALL_DEFINE5(recvmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
@@ -845,11 +852,13 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
compat_ptr(a[4]), a[5]);
break;
case SYS_RECV:
- ret = compat_sys_recv(a0, compat_ptr(a1), a[2], a[3]);
+ ret = __compat_sys_recvfrom(a0, compat_ptr(a1), a[2], a[3],
+ NULL, NULL);
break;
case SYS_RECVFROM:
- ret = compat_sys_recvfrom(a0, compat_ptr(a1), a[2], a[3],
- compat_ptr(a[4]), compat_ptr(a[5]));
+ ret = __compat_sys_recvfrom(a0, compat_ptr(a1), a[2], a[3],
+ compat_ptr(a[4]),
+ compat_ptr(a[5]));
break;
case SYS_SHUTDOWN:
ret = __sys_shutdown(a0, a1);
--
2.16.2
^ permalink raw reply related
* [PATCH -next 17/22] net: socket: replace call to sys_recv() with __sys_recvfrom()
From: Dominik Brodowski @ 2018-03-16 17:06 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
sys_recv() merely expands the parameters to __sys_recvfrom() by NULL and
NULL. Open-code this in the two places which used sys_recv() as a wrapper
to __sys_recvfrom().
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
net/compat.c | 3 ++-
net/socket.c | 3 ++-
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/compat.c b/net/compat.c
index d55982ff5c59..9e0d030063ad 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -755,7 +755,8 @@ COMPAT_SYSCALL_DEFINE3(recvmsg, int, fd, struct compat_msghdr __user *, msg, uns
COMPAT_SYSCALL_DEFINE4(recv, int, fd, void __user *, buf, compat_size_t, len, unsigned int, flags)
{
- return sys_recv(fd, buf, len, flags | MSG_CMSG_COMPAT);
+ return __sys_recvfrom(fd, buf, len, flags | MSG_CMSG_COMPAT, NULL,
+ NULL);
}
COMPAT_SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, buf, compat_size_t, len,
diff --git a/net/socket.c b/net/socket.c
index c4fb60be194b..34cf4b163f8f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2566,7 +2566,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
(struct sockaddr __user *)a[4], a[5]);
break;
case SYS_RECV:
- err = sys_recv(a0, (void __user *)a1, a[2], a[3]);
+ err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3],
+ NULL, NULL);
break;
case SYS_RECVFROM:
err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3],
--
2.16.2
^ permalink raw reply related
* [PATCH -next 16/22] net: socket: replace calls to sys_send() with __sys_sendto()
From: Dominik Brodowski @ 2018-03-16 17:06 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
sys_send() merely expands the parameters to __sys_sendto() by NULL and 0.
Open-code this in the two places which used sys_send() as a wrapper to
__sys_sendto().
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
net/compat.c | 2 +-
net/socket.c | 3 ++-
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/net/compat.c b/net/compat.c
index 5caa48987bb2..d55982ff5c59 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -837,7 +837,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = __sys_socketpair(a0, a1, a[2], compat_ptr(a[3]));
break;
case SYS_SEND:
- ret = sys_send(a0, compat_ptr(a1), a[2], a[3]);
+ ret = __sys_sendto(a0, compat_ptr(a1), a[2], a[3], NULL, 0);
break;
case SYS_SENDTO:
ret = __sys_sendto(a0, compat_ptr(a1), a[2], a[3],
diff --git a/net/socket.c b/net/socket.c
index 3dcace0ca3d9..c4fb60be194b 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2558,7 +2558,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
err = __sys_socketpair(a0, a1, a[2], (int __user *)a[3]);
break;
case SYS_SEND:
- err = sys_send(a0, (void __user *)a1, a[2], a[3]);
+ err = __sys_sendto(a0, (void __user *)a1, a[2], a[3],
+ NULL, 0);
break;
case SYS_SENDTO:
err = __sys_sendto(a0, (void __user *)a1, a[2], a[3],
--
2.16.2
^ permalink raw reply related
* [PATCH -next 15/22] net: socket: move check for forbid_cmsg_compat to __sys_...msg()
From: Dominik Brodowski @ 2018-03-16 17:06 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
The non-compat codepaths for sys_...msg() verify that MSG_CMSG_COMPAT
is not set. By moving this check to the __sys_...msg() functions
(and making it dependent on a static flag passed to this function), we
can call the __sys...msg() functions instead of the syscall functions
in all cases. __sys_recvmmsg() does not need this trickery, as the
check is handled within the do_sys_recvmmsg() function internal to
net/socket.c.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 13 +++++++++----
net/compat.c | 8 +++++---
net/socket.c | 38 +++++++++++++++++++++++---------------
3 files changed, 37 insertions(+), 22 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index cad120e4ed4b..e2b6bd4fe977 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -346,13 +346,18 @@ extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data);
struct timespec;
-/* The __sys_...msg variants allow MSG_CMSG_COMPAT */
-extern long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned flags);
-extern long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags);
+/* The __sys_...msg variants allow MSG_CMSG_COMPAT iff
+ * forbid_cmsg_compat==false
+ */
+extern long __sys_recvmsg(int fd, struct user_msghdr __user *msg,
+ unsigned int flags, bool forbid_cmsg_compat);
+extern long __sys_sendmsg(int fd, struct user_msghdr __user *msg,
+ unsigned int flags, bool forbid_cmsg_compat);
extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
unsigned int flags, struct timespec *timeout);
extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg,
- unsigned int vlen, unsigned int flags);
+ unsigned int vlen, unsigned int flags,
+ bool forbid_cmsg_compat);
/* helpers which do the actual work for syscalls */
extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
diff --git a/net/compat.c b/net/compat.c
index f1ec23e9dfce..5caa48987bb2 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -736,19 +736,21 @@ static unsigned char nas[21] = {
COMPAT_SYSCALL_DEFINE3(sendmsg, int, fd, struct compat_msghdr __user *, msg, unsigned int, flags)
{
- return __sys_sendmsg(fd, (struct user_msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
+ return __sys_sendmsg(fd, (struct user_msghdr __user *)msg,
+ flags | MSG_CMSG_COMPAT, false);
}
COMPAT_SYSCALL_DEFINE4(sendmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
unsigned int, vlen, unsigned int, flags)
{
return __sys_sendmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
- flags | MSG_CMSG_COMPAT);
+ flags | MSG_CMSG_COMPAT, false);
}
COMPAT_SYSCALL_DEFINE3(recvmsg, int, fd, struct compat_msghdr __user *, msg, unsigned int, flags)
{
- return __sys_recvmsg(fd, (struct user_msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
+ return __sys_recvmsg(fd, (struct user_msghdr __user *)msg,
+ flags | MSG_CMSG_COMPAT, false);
}
COMPAT_SYSCALL_DEFINE4(recv, int, fd, void __user *, buf, compat_size_t, len, unsigned int, flags)
diff --git a/net/socket.c b/net/socket.c
index 72cdaaeccb85..3dcace0ca3d9 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2137,12 +2137,16 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
* BSD sendmsg interface
*/
-long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags)
+long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,
+ bool forbid_cmsg_compat)
{
int fput_needed, err;
struct msghdr msg_sys;
struct socket *sock;
+ if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT))
+ return -EINVAL;
+
sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (!sock)
goto out;
@@ -2156,9 +2160,7 @@ long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags)
SYSCALL_DEFINE3(sendmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags)
{
- if (flags & MSG_CMSG_COMPAT)
- return -EINVAL;
- return __sys_sendmsg(fd, msg, flags);
+ return __sys_sendmsg(fd, msg, flags, true);
}
/*
@@ -2166,7 +2168,7 @@ SYSCALL_DEFINE3(sendmsg, int, fd, struct user_msghdr __user *, msg, unsigned int
*/
int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
- unsigned int flags)
+ unsigned int flags, bool forbid_cmsg_compat)
{
int fput_needed, err, datagrams;
struct socket *sock;
@@ -2176,6 +2178,9 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
struct used_address used_address;
unsigned int oflags = flags;
+ if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT))
+ return -EINVAL;
+
if (vlen > UIO_MAXIOV)
vlen = UIO_MAXIOV;
@@ -2232,9 +2237,7 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg,
unsigned int, vlen, unsigned int, flags)
{
- if (flags & MSG_CMSG_COMPAT)
- return -EINVAL;
- return __sys_sendmmsg(fd, mmsg, vlen, flags);
+ return __sys_sendmmsg(fd, mmsg, vlen, flags, true);
}
static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg,
@@ -2307,12 +2310,16 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg,
* BSD recvmsg interface
*/
-long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned flags)
+long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags,
+ bool forbid_cmsg_compat)
{
int fput_needed, err;
struct msghdr msg_sys;
struct socket *sock;
+ if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT))
+ return -EINVAL;
+
sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (!sock)
goto out;
@@ -2327,9 +2334,7 @@ long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned flags)
SYSCALL_DEFINE3(recvmsg, int, fd, struct user_msghdr __user *, msg,
unsigned int, flags)
{
- if (flags & MSG_CMSG_COMPAT)
- return -EINVAL;
- return __sys_recvmsg(fd, msg, flags);
+ return __sys_recvmsg(fd, msg, flags, true);
}
/*
@@ -2580,13 +2585,16 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
(int __user *)a[4]);
break;
case SYS_SENDMSG:
- err = sys_sendmsg(a0, (struct user_msghdr __user *)a1, a[2]);
+ err = __sys_sendmsg(a0, (struct user_msghdr __user *)a1,
+ a[2], true);
break;
case SYS_SENDMMSG:
- err = sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3]);
+ err = __sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2],
+ a[3], true);
break;
case SYS_RECVMSG:
- err = sys_recvmsg(a0, (struct user_msghdr __user *)a1, a[2]);
+ err = __sys_recvmsg(a0, (struct user_msghdr __user *)a1,
+ a[2], true);
break;
case SYS_RECVMMSG:
err = do_sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2],
--
2.16.2
^ permalink raw reply related
* [PATCH -next 14/22] net: socket: add do_sys_recvmmsg() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-16 17:06 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper do_sys_recvmmsg() allows us to avoid the
internal calls to the sys_getsockopt() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
net/socket.c | 17 ++++++++++++-----
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/net/socket.c b/net/socket.c
index a05289b1f863..72cdaaeccb85 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2445,9 +2445,9 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
return datagrams;
}
-SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg,
- unsigned int, vlen, unsigned int, flags,
- struct timespec __user *, timeout)
+static long do_sys_recvmmsg(int fd, struct mmsghdr __user *mmsg,
+ unsigned int vlen, unsigned int flags,
+ struct timespec __user *timeout)
{
int datagrams;
struct timespec timeout_sys;
@@ -2470,6 +2470,13 @@ SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg,
return datagrams;
}
+SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg,
+ unsigned int, vlen, unsigned int, flags,
+ struct timespec __user *, timeout)
+{
+ return do_sys_recvmmsg(fd, mmsg, vlen, flags, timeout);
+}
+
#ifdef __ARCH_WANT_SYS_SOCKETCALL
/* Argument list sizes for sys_socketcall */
#define AL(x) ((x) * sizeof(unsigned long))
@@ -2582,8 +2589,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
err = sys_recvmsg(a0, (struct user_msghdr __user *)a1, a[2]);
break;
case SYS_RECVMMSG:
- err = sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3],
- (struct timespec __user *)a[4]);
+ err = do_sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2],
+ a[3], (struct timespec __user *)a[4]);
break;
case SYS_ACCEPT4:
err = __sys_accept4(a0, (struct sockaddr __user *)a1,
--
2.16.2
^ permalink raw reply related
* [PATCH -next 13/22] net: socket: add __sys_getsockopt() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-16 17:06 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_getsockopt() allows us to avoid the
internal calls to the sys_getsockopt() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
net/socket.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/net/socket.c b/net/socket.c
index 5dd2e39a6cd4..a05289b1f863 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1918,8 +1918,8 @@ SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
* to pass a user mode parameter for the protocols to sort out.
*/
-SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
- char __user *, optval, int __user *, optlen)
+static int __sys_getsockopt(int fd, int level, int optname,
+ char __user *optval, int __user *optlen)
{
int err, fput_needed;
struct socket *sock;
@@ -1944,6 +1944,12 @@ SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
return err;
}
+SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
+ char __user *, optval, int __user *, optlen)
+{
+ return __sys_getsockopt(fd, level, optname, optval, optlen);
+}
+
/*
* Shutdown a socket.
*/
@@ -2563,8 +2569,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
break;
case SYS_GETSOCKOPT:
err =
- sys_getsockopt(a0, a1, a[2], (char __user *)a[3],
- (int __user *)a[4]);
+ __sys_getsockopt(a0, a1, a[2], (char __user *)a[3],
+ (int __user *)a[4]);
break;
case SYS_SENDMSG:
err = sys_sendmsg(a0, (struct user_msghdr __user *)a1, a[2]);
--
2.16.2
^ permalink raw reply related
* [PATCH -next 12/22] net: socket: add __sys_setsockopt() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-16 17:06 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_setsockopt() allows us to avoid the
internal calls to the sys_setsockopt() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 1 +
net/socket.c | 13 ++++++++++---
2 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index b205138b69f1..cad120e4ed4b 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -376,4 +376,5 @@ extern int __sys_socketpair(int family, int type, int protocol,
int __user *usockvec);
extern int __sys_shutdown(int fd, int how);
+
#endif /* _LINUX_SOCKET_H */
diff --git a/net/socket.c b/net/socket.c
index ad5dfd6a1d59..5dd2e39a6cd4 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1878,8 +1878,8 @@ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size,
* to pass the user mode parameter for the protocols to sort out.
*/
-SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
- char __user *, optval, int, optlen)
+static int __sys_setsockopt(int fd, int level, int optname,
+ char __user *optval, int optlen)
{
int err, fput_needed;
struct socket *sock;
@@ -1907,6 +1907,12 @@ SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
return err;
}
+SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
+ char __user *, optval, int, optlen)
+{
+ return __sys_setsockopt(fd, level, optname, optval, optlen);
+}
+
/*
* Get a socket option. Because we don't know the option lengths we have
* to pass a user mode parameter for the protocols to sort out.
@@ -2552,7 +2558,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
err = __sys_shutdown(a0, a1);
break;
case SYS_SETSOCKOPT:
- err = sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]);
+ err = __sys_setsockopt(a0, a1, a[2], (char __user *)a[3],
+ a[4]);
break;
case SYS_GETSOCKOPT:
err =
--
2.16.2
^ permalink raw reply related
* [PATCH -next 11/22] net: socket: add __sys_shutdown() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-16 17:06 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_shutdown() allows us to avoid the
internal calls to the sys_shutdown() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 1 +
net/compat.c | 2 +-
net/socket.c | 9 +++++++--
3 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index dbdddf0d079e..b205138b69f1 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -374,5 +374,6 @@ extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
int __user *usockaddr_len);
extern int __sys_socketpair(int family, int type, int protocol,
int __user *usockvec);
+extern int __sys_shutdown(int fd, int how);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index 04db26316438..f1ec23e9dfce 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -849,7 +849,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
compat_ptr(a[4]), compat_ptr(a[5]));
break;
case SYS_SHUTDOWN:
- ret = sys_shutdown(a0, a1);
+ ret = __sys_shutdown(a0, a1);
break;
case SYS_SETSOCKOPT:
ret = compat_sys_setsockopt(a0, a1, a[2],
diff --git a/net/socket.c b/net/socket.c
index 5861821f46f5..ad5dfd6a1d59 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1942,7 +1942,7 @@ SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
* Shutdown a socket.
*/
-SYSCALL_DEFINE2(shutdown, int, fd, int, how)
+int __sys_shutdown(int fd, int how)
{
int err, fput_needed;
struct socket *sock;
@@ -1957,6 +1957,11 @@ SYSCALL_DEFINE2(shutdown, int, fd, int, how)
return err;
}
+SYSCALL_DEFINE2(shutdown, int, fd, int, how)
+{
+ return __sys_shutdown(fd, how);
+}
+
/* A couple of helpful macros for getting the address of the 32/64 bit
* fields which are the same type (int / unsigned) on our platforms.
*/
@@ -2544,7 +2549,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
(int __user *)a[5]);
break;
case SYS_SHUTDOWN:
- err = sys_shutdown(a0, a1);
+ err = __sys_shutdown(a0, a1);
break;
case SYS_SETSOCKOPT:
err = sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]);
--
2.16.2
^ permalink raw reply related
* [PATCH -next 10/22] net: socket: add __sys_socketpair() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-16 17:06 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_socketpair() allows us to avoid the
internal calls to the sys_socketpair() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 2 ++
net/compat.c | 2 +-
net/socket.c | 11 ++++++++---
3 files changed, 11 insertions(+), 4 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 9ba003e92fea..dbdddf0d079e 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -372,5 +372,7 @@ extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
int __user *usockaddr_len);
extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
int __user *usockaddr_len);
+extern int __sys_socketpair(int family, int type, int protocol,
+ int __user *usockvec);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index 74017f618eb1..04db26316438 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -832,7 +832,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = __sys_getpeername(a0, compat_ptr(a1), compat_ptr(a[2]));
break;
case SYS_SOCKETPAIR:
- ret = sys_socketpair(a0, a1, a[2], compat_ptr(a[3]));
+ ret = __sys_socketpair(a0, a1, a[2], compat_ptr(a[3]));
break;
case SYS_SEND:
ret = sys_send(a0, compat_ptr(a1), a[2], a[3]);
diff --git a/net/socket.c b/net/socket.c
index 007fb9483279..5861821f46f5 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1368,8 +1368,7 @@ SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
* Create a pair of connected sockets.
*/
-SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
- int __user *, usockvec)
+int __sys_socketpair(int family, int type, int protocol, int __user *usockvec)
{
struct socket *sock1, *sock2;
int fd1, fd2, err;
@@ -1454,6 +1453,12 @@ SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
return err;
}
+SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
+ int __user *, usockvec)
+{
+ return __sys_socketpair(family, type, protocol, usockvec);
+}
+
/*
* Bind a name to a socket. Nothing much to do here since it's
* the protocol's responsibility to handle the local address.
@@ -2521,7 +2526,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
(int __user *)a[2]);
break;
case SYS_SOCKETPAIR:
- err = sys_socketpair(a0, a1, a[2], (int __user *)a[3]);
+ err = __sys_socketpair(a0, a1, a[2], (int __user *)a[3]);
break;
case SYS_SEND:
err = sys_send(a0, (void __user *)a1, a[2], a[3]);
--
2.16.2
^ permalink raw reply related
* [PATCH -next 09/22] net: socket: add __sys_getpeername() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-16 17:06 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_getpeername() allows us to avoid the
internal calls to the sys_getpeername() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 2 ++
net/compat.c | 2 +-
net/socket.c | 14 ++++++++++----
3 files changed, 13 insertions(+), 5 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index ef0226a61b03..9ba003e92fea 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -370,5 +370,7 @@ extern int __sys_connect(int fd, struct sockaddr __user *uservaddr,
extern int __sys_listen(int fd, int backlog);
extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
int __user *usockaddr_len);
+extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
+ int __user *usockaddr_len);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index efd28d02608c..74017f618eb1 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -829,7 +829,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = __sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2]));
break;
case SYS_GETPEERNAME:
- ret = sys_getpeername(a0, compat_ptr(a1), compat_ptr(a[2]));
+ ret = __sys_getpeername(a0, compat_ptr(a1), compat_ptr(a[2]));
break;
case SYS_SOCKETPAIR:
ret = sys_socketpair(a0, a1, a[2], compat_ptr(a[3]));
diff --git a/net/socket.c b/net/socket.c
index b61e0d20f37b..007fb9483279 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1712,8 +1712,8 @@ SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
* name to user space.
*/
-SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
- int __user *, usockaddr_len)
+int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
+ int __user *usockaddr_len)
{
struct socket *sock;
struct sockaddr_storage address;
@@ -1738,6 +1738,12 @@ SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
return err;
}
+SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
+ int __user *, usockaddr_len)
+{
+ return __sys_getpeername(fd, usockaddr, usockaddr_len);
+}
+
/*
* Send a datagram to a given address. We move the address into kernel
* space and check the user space data area is readable before invoking
@@ -2511,8 +2517,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
break;
case SYS_GETPEERNAME:
err =
- sys_getpeername(a0, (struct sockaddr __user *)a1,
- (int __user *)a[2]);
+ __sys_getpeername(a0, (struct sockaddr __user *)a1,
+ (int __user *)a[2]);
break;
case SYS_SOCKETPAIR:
err = sys_socketpair(a0, a1, a[2], (int __user *)a[3]);
--
2.16.2
^ permalink raw reply related
* [PATCH -next 08/22] net: socket: add __sys_getsockname() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-16 17:06 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_getsockname() allows us to avoid the
internal calls to the sys_getsockname() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 2 ++
net/compat.c | 2 +-
net/socket.c | 14 ++++++++++----
3 files changed, 13 insertions(+), 5 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 7e37af25509d..ef0226a61b03 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -368,5 +368,7 @@ extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
extern int __sys_connect(int fd, struct sockaddr __user *uservaddr,
int addrlen);
extern int __sys_listen(int fd, int backlog);
+extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
+ int __user *usockaddr_len);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index c80cb973f383..efd28d02608c 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -826,7 +826,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = __sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), 0);
break;
case SYS_GETSOCKNAME:
- ret = sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2]));
+ ret = __sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2]));
break;
case SYS_GETPEERNAME:
ret = sys_getpeername(a0, compat_ptr(a1), compat_ptr(a[2]));
diff --git a/net/socket.c b/net/socket.c
index 67d9d70a4734..b61e0d20f37b 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1675,8 +1675,8 @@ SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
* name to user space.
*/
-SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
- int __user *, usockaddr_len)
+int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
+ int __user *usockaddr_len)
{
struct socket *sock;
struct sockaddr_storage address;
@@ -1701,6 +1701,12 @@ SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
return err;
}
+SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
+ int __user *, usockaddr_len)
+{
+ return __sys_getsockname(fd, usockaddr, usockaddr_len);
+}
+
/*
* Get the remote address ('name') of a socket object. Move the obtained
* name to user space.
@@ -2500,8 +2506,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
break;
case SYS_GETSOCKNAME:
err =
- sys_getsockname(a0, (struct sockaddr __user *)a1,
- (int __user *)a[2]);
+ __sys_getsockname(a0, (struct sockaddr __user *)a1,
+ (int __user *)a[2]);
break;
case SYS_GETPEERNAME:
err =
--
2.16.2
^ permalink raw reply related
* [PATCH -next 07/22] net: socket: add __sys_listen() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-16 17:05 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_listen() allows us to avoid the
internal calls to the sys_listen() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 1 +
net/compat.c | 2 +-
net/socket.c | 9 +++++++--
3 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 7daa344d7320..7e37af25509d 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -367,5 +367,6 @@ extern int __sys_socket(int family, int type, int protocol);
extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
extern int __sys_connect(int fd, struct sockaddr __user *uservaddr,
int addrlen);
+extern int __sys_listen(int fd, int backlog);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index 7ab6352268f3..c80cb973f383 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -820,7 +820,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = __sys_connect(a0, compat_ptr(a1), a[2]);
break;
case SYS_LISTEN:
- ret = sys_listen(a0, a1);
+ ret = __sys_listen(a0, a1);
break;
case SYS_ACCEPT:
ret = __sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), 0);
diff --git a/net/socket.c b/net/socket.c
index 64bdfdf6c6e7..67d9d70a4734 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1496,7 +1496,7 @@ SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
* ready for listening.
*/
-SYSCALL_DEFINE2(listen, int, fd, int, backlog)
+int __sys_listen(int fd, int backlog)
{
struct socket *sock;
int err, fput_needed;
@@ -1517,6 +1517,11 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog)
return err;
}
+SYSCALL_DEFINE2(listen, int, fd, int, backlog)
+{
+ return __sys_listen(fd, backlog);
+}
+
/*
* For accept, we attempt to create a new socket, set up the link
* with the client, wake up the client, then return the new
@@ -2487,7 +2492,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
err = __sys_connect(a0, (struct sockaddr __user *)a1, a[2]);
break;
case SYS_LISTEN:
- err = sys_listen(a0, a1);
+ err = __sys_listen(a0, a1);
break;
case SYS_ACCEPT:
err = __sys_accept4(a0, (struct sockaddr __user *)a1,
--
2.16.2
^ permalink raw reply related
* [PATCH -next 06/22] net: socket: add __sys_connect() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-16 17:05 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_connect() allows us to avoid the
internal calls to the sys_connect() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 2 ++
net/compat.c | 2 +-
net/socket.c | 11 ++++++++---
3 files changed, 11 insertions(+), 4 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index e9cee272da13..7daa344d7320 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -365,5 +365,7 @@ extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
int __user *upeer_addrlen, int flags);
extern int __sys_socket(int family, int type, int protocol);
extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
+extern int __sys_connect(int fd, struct sockaddr __user *uservaddr,
+ int addrlen);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index bba555b1d863..7ab6352268f3 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -817,7 +817,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = __sys_bind(a0, compat_ptr(a1), a[2]);
break;
case SYS_CONNECT:
- ret = sys_connect(a0, compat_ptr(a1), a[2]);
+ ret = __sys_connect(a0, compat_ptr(a1), a[2]);
break;
case SYS_LISTEN:
ret = sys_listen(a0, a1);
diff --git a/net/socket.c b/net/socket.c
index 291cdae97341..64bdfdf6c6e7 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1633,8 +1633,7 @@ SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr,
* include the -EINPROGRESS status for such sockets.
*/
-SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
- int, addrlen)
+int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen)
{
struct socket *sock;
struct sockaddr_storage address;
@@ -1660,6 +1659,12 @@ SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
return err;
}
+SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
+ int, addrlen)
+{
+ return __sys_connect(fd, uservaddr, addrlen);
+}
+
/*
* Get the local address ('name') of a socket object. Move the obtained
* name to user space.
@@ -2479,7 +2484,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
err = __sys_bind(a0, (struct sockaddr __user *)a1, a[2]);
break;
case SYS_CONNECT:
- err = sys_connect(a0, (struct sockaddr __user *)a1, a[2]);
+ err = __sys_connect(a0, (struct sockaddr __user *)a1, a[2]);
break;
case SYS_LISTEN:
err = sys_listen(a0, a1);
--
2.16.2
^ permalink raw reply related
* [PATCH -next 05/22] net: socket: add __sys_bind() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-16 17:05 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_bind() allows us to avoid the
internal calls to the sys_bind() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 1 +
net/compat.c | 2 +-
net/socket.c | 9 +++++++--
3 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index f8d040434a13..e9cee272da13 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -364,5 +364,6 @@ extern int __sys_sendto(int fd, void __user *buff, size_t len,
extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
int __user *upeer_addrlen, int flags);
extern int __sys_socket(int family, int type, int protocol);
+extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index 5b3b74c5812e..bba555b1d863 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -814,7 +814,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = __sys_socket(a0, a1, a[2]);
break;
case SYS_BIND:
- ret = sys_bind(a0, compat_ptr(a1), a[2]);
+ ret = __sys_bind(a0, compat_ptr(a1), a[2]);
break;
case SYS_CONNECT:
ret = sys_connect(a0, compat_ptr(a1), a[2]);
diff --git a/net/socket.c b/net/socket.c
index 07f379e50def..291cdae97341 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1462,7 +1462,7 @@ SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
* the protocol layer (having also checked the address is ok).
*/
-SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
+int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen)
{
struct socket *sock;
struct sockaddr_storage address;
@@ -1485,6 +1485,11 @@ SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
return err;
}
+SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
+{
+ return __sys_bind(fd, umyaddr, addrlen);
+}
+
/*
* Perform a listen. Basically, we allow the protocol to do anything
* necessary for a listen, and if that works, we mark the socket as
@@ -2471,7 +2476,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
err = __sys_socket(a0, a1, a[2]);
break;
case SYS_BIND:
- err = sys_bind(a0, (struct sockaddr __user *)a1, a[2]);
+ err = __sys_bind(a0, (struct sockaddr __user *)a1, a[2]);
break;
case SYS_CONNECT:
err = sys_connect(a0, (struct sockaddr __user *)a1, a[2]);
--
2.16.2
^ permalink raw reply related
* [PATCH -next 04/22] net: socket: add __sys_socket() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-16 17:05 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_socket() allows us to avoid the
internal calls to the sys_socket() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 1 +
net/compat.c | 2 +-
net/socket.c | 9 +++++++--
3 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 6a9840271676..f8d040434a13 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -363,5 +363,6 @@ extern int __sys_sendto(int fd, void __user *buff, size_t len,
int addr_len);
extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
int __user *upeer_addrlen, int flags);
+extern int __sys_socket(int family, int type, int protocol);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index 0ff9f7451b6f..5b3b74c5812e 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -811,7 +811,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
switch (call) {
case SYS_SOCKET:
- ret = sys_socket(a0, a1, a[2]);
+ ret = __sys_socket(a0, a1, a[2]);
break;
case SYS_BIND:
ret = sys_bind(a0, compat_ptr(a1), a[2]);
diff --git a/net/socket.c b/net/socket.c
index 45f6ea0d57a5..07f379e50def 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1332,7 +1332,7 @@ int sock_create_kern(struct net *net, int family, int type, int protocol, struct
}
EXPORT_SYMBOL(sock_create_kern);
-SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
+int __sys_socket(int family, int type, int protocol)
{
int retval;
struct socket *sock;
@@ -1359,6 +1359,11 @@ SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
}
+SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
+{
+ return __sys_socket(family, type, protocol);
+}
+
/*
* Create a pair of connected sockets.
*/
@@ -2463,7 +2468,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
switch (call) {
case SYS_SOCKET:
- err = sys_socket(a0, a1, a[2]);
+ err = __sys_socket(a0, a1, a[2]);
break;
case SYS_BIND:
err = sys_bind(a0, (struct sockaddr __user *)a1, a[2]);
--
2.16.2
^ permalink raw reply related
* [PATCH -next 03/22] net: socket: add __sys_accept4() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-16 17:05 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_accept4() allows us to avoid the
internal calls to the sys_accept4() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 2 ++
net/compat.c | 4 ++--
net/socket.c | 20 +++++++++++++-------
3 files changed, 17 insertions(+), 9 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 54b85abc7265..6a9840271676 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -361,5 +361,7 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
extern int __sys_sendto(int fd, void __user *buff, size_t len,
unsigned int flags, struct sockaddr __user *addr,
int addr_len);
+extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
+ int __user *upeer_addrlen, int flags);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index fc82982d9b84..0ff9f7451b6f 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -823,7 +823,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = sys_listen(a0, a1);
break;
case SYS_ACCEPT:
- ret = sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), 0);
+ ret = __sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), 0);
break;
case SYS_GETSOCKNAME:
ret = sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2]));
@@ -873,7 +873,7 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
compat_ptr(a[4]));
break;
case SYS_ACCEPT4:
- ret = sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), a[3]);
+ ret = __sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), a[3]);
break;
default:
ret = -EINVAL;
diff --git a/net/socket.c b/net/socket.c
index 3f037a21ba5e..45f6ea0d57a5 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1519,8 +1519,8 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog)
* clean when we restucture accept also.
*/
-SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
- int __user *, upeer_addrlen, int, flags)
+int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
+ int __user *upeer_addrlen, int flags)
{
struct socket *sock, *newsock;
struct file *newfile;
@@ -1599,10 +1599,16 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
goto out_put;
}
+SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
+ int __user *, upeer_addrlen, int, flags)
+{
+ return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, flags);
+}
+
SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr,
int __user *, upeer_addrlen)
{
- return sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0);
+ return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0);
}
/*
@@ -2469,8 +2475,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
err = sys_listen(a0, a1);
break;
case SYS_ACCEPT:
- err = sys_accept4(a0, (struct sockaddr __user *)a1,
- (int __user *)a[2], 0);
+ err = __sys_accept4(a0, (struct sockaddr __user *)a1,
+ (int __user *)a[2], 0);
break;
case SYS_GETSOCKNAME:
err =
@@ -2525,8 +2531,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
(struct timespec __user *)a[4]);
break;
case SYS_ACCEPT4:
- err = sys_accept4(a0, (struct sockaddr __user *)a1,
- (int __user *)a[2], a[3]);
+ err = __sys_accept4(a0, (struct sockaddr __user *)a1,
+ (int __user *)a[2], a[3]);
break;
default:
err = -EINVAL;
--
2.16.2
^ permalink raw reply related
* [PATCH -next 02/22] net: socket: add __sys_sendto() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-16 17:05 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_sendto() allows us to avoid the
internal calls to the sys_sendto() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 3 +++
net/compat.c | 3 ++-
net/socket.c | 19 ++++++++++++-------
3 files changed, 17 insertions(+), 8 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 40cc93b91628..54b85abc7265 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -358,5 +358,8 @@ extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg,
extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
unsigned int flags, struct sockaddr __user *addr,
int __user *addr_len);
+extern int __sys_sendto(int fd, void __user *buff, size_t len,
+ unsigned int flags, struct sockaddr __user *addr,
+ int addr_len);
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index 2d8186c277b2..fc82982d9b84 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -838,7 +838,8 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = sys_send(a0, compat_ptr(a1), a[2], a[3]);
break;
case SYS_SENDTO:
- ret = sys_sendto(a0, compat_ptr(a1), a[2], a[3], compat_ptr(a[4]), a[5]);
+ ret = __sys_sendto(a0, compat_ptr(a1), a[2], a[3],
+ compat_ptr(a[4]), a[5]);
break;
case SYS_RECV:
ret = compat_sys_recv(a0, compat_ptr(a1), a[2], a[3]);
diff --git a/net/socket.c b/net/socket.c
index 712d99d8680f..3f037a21ba5e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1711,10 +1711,8 @@ SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr,
* space and check the user space data area is readable before invoking
* the protocol.
*/
-
-SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
- unsigned int, flags, struct sockaddr __user *, addr,
- int, addr_len)
+int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags,
+ struct sockaddr __user *addr, int addr_len)
{
struct socket *sock;
struct sockaddr_storage address;
@@ -1752,6 +1750,13 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
return err;
}
+SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
+ unsigned int, flags, struct sockaddr __user *, addr,
+ int, addr_len)
+{
+ return __sys_sendto(fd, buff, len, flags, addr, addr_len);
+}
+
/*
* Send a datagram down a socket.
*/
@@ -1759,7 +1764,7 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len,
unsigned int, flags)
{
- return sys_sendto(fd, buff, len, flags, NULL, 0);
+ return __sys_sendto(fd, buff, len, flags, NULL, 0);
}
/*
@@ -2484,8 +2489,8 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
err = sys_send(a0, (void __user *)a1, a[2], a[3]);
break;
case SYS_SENDTO:
- err = sys_sendto(a0, (void __user *)a1, a[2], a[3],
- (struct sockaddr __user *)a[4], a[5]);
+ err = __sys_sendto(a0, (void __user *)a1, a[2], a[3],
+ (struct sockaddr __user *)a[4], a[5]);
break;
case SYS_RECV:
err = sys_recv(a0, (void __user *)a1, a[2], a[3]);
--
2.16.2
^ permalink raw reply related
* [PATCH -next 01/22] net: socket: add __sys_recvfrom() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-16 17:05 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
In-Reply-To: <20180316170614.5392-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_recvfrom() allows us to avoid the
internal calls to the sys_recvfrom() syscall.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/linux/socket.h | 6 ++++++
net/compat.c | 3 ++-
net/socket.c | 21 +++++++++++++--------
3 files changed, 21 insertions(+), 9 deletions(-)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 9286a5a8c60c..40cc93b91628 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -353,4 +353,10 @@ extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen
unsigned int flags, struct timespec *timeout);
extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg,
unsigned int vlen, unsigned int flags);
+
+/* helpers which do the actual work for syscalls */
+extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
+ unsigned int flags, struct sockaddr __user *addr,
+ int __user *addr_len);
+
#endif /* _LINUX_SOCKET_H */
diff --git a/net/compat.c b/net/compat.c
index 22381719718c..2d8186c277b2 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -760,7 +760,8 @@ COMPAT_SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, buf, compat_size_t, len
unsigned int, flags, struct sockaddr __user *, addr,
int __user *, addrlen)
{
- return sys_recvfrom(fd, buf, len, flags | MSG_CMSG_COMPAT, addr, addrlen);
+ return __sys_recvfrom(fd, buf, len, flags | MSG_CMSG_COMPAT, addr,
+ addrlen);
}
COMPAT_SYSCALL_DEFINE5(recvmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
diff --git a/net/socket.c b/net/socket.c
index a93c99b518ca..712d99d8680f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1767,10 +1767,8 @@ SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len,
* sender. We verify the buffers are writable and if needed move the
* sender address from kernel to user space.
*/
-
-SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
- unsigned int, flags, struct sockaddr __user *, addr,
- int __user *, addr_len)
+int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags,
+ struct sockaddr __user *addr, int __user *addr_len)
{
struct socket *sock;
struct iovec iov;
@@ -1810,6 +1808,13 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
return err;
}
+SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
+ unsigned int, flags, struct sockaddr __user *, addr,
+ int __user *, addr_len)
+{
+ return __sys_recvfrom(fd, ubuf, size, flags, addr, addr_len);
+}
+
/*
* Receive a datagram from a socket.
*/
@@ -1817,7 +1822,7 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size,
unsigned int, flags)
{
- return sys_recvfrom(fd, ubuf, size, flags, NULL, NULL);
+ return __sys_recvfrom(fd, ubuf, size, flags, NULL, NULL);
}
/*
@@ -2486,9 +2491,9 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args)
err = sys_recv(a0, (void __user *)a1, a[2], a[3]);
break;
case SYS_RECVFROM:
- err = sys_recvfrom(a0, (void __user *)a1, a[2], a[3],
- (struct sockaddr __user *)a[4],
- (int __user *)a[5]);
+ err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3],
+ (struct sockaddr __user *)a[4],
+ (int __user *)a[5]);
break;
case SYS_SHUTDOWN:
err = sys_shutdown(a0, a1);
--
2.16.2
^ permalink raw reply related
* [PATCH -next 00/22] remove in-kernel syscall invocations (part 2 == netdev)
From: Dominik Brodowski @ 2018-03-16 17:05 UTC (permalink / raw)
To: linux-kernel, torvalds, davem; +Cc: netdev
Here is another series of patches which reduce the number of syscall
invocations from within the kernel. This series is focused solely on
the net/ part of the kernel and get rids of syscall and compat_syscall
invocations from within the kernel completely. It is also available at
https://git.kernel.org/pub/scm/linux/kernel/git/brodo/linux.git syscalls-net-next
The rationale of this change is described in patch 1 of part 1[*] as follows:
The syscall entry points to the kernel defined by SYSCALL_DEFINEx()
and COMPAT_SYSCALL_DEFINEx() should only be called from userspace
through kernel entry points, but not from the kernel itself. This
will allow cleanups and optimizations to the entry paths *and* to
the parts of the kernel code which currently need to pretend to be
userspace in order to make use of syscalls.
At present, these patches are based on v4.16-rc5; there is one trivial
conflict against net-next. Dave, I presume that you prefer to take them
through net-next? If you want to, I can re-base them against net-next.
If you prefer otherwise, though, I can route them as part of my whole
syscall series.
Thanks,
Dominik
[*] The cover letter for v2 is available at
http://lkml.kernel.org/r/20180315190529.20943-1-linux@dominikbrodowski.net ;
the whole patchset -- in its current, slightly modified form -- is available at
at https://git.kernel.org/pub/scm/linux/kernel/git/brodo/linux.git syscalls-next
Dominik Brodowski (22):
net: socket: add __sys_recvfrom() helper; remove in-kernel call to
syscall
net: socket: add __sys_sendto() helper; remove in-kernel call to
syscall
net: socket: add __sys_accept4() helper; remove in-kernel call to
syscall
net: socket: add __sys_socket() helper; remove in-kernel call to
syscall
net: socket: add __sys_bind() helper; remove in-kernel call to syscall
net: socket: add __sys_connect() helper; remove in-kernel call to
syscall
net: socket: add __sys_listen() helper; remove in-kernel call to
syscall
net: socket: add __sys_getsockname() helper; remove in-kernel call to
syscall
net: socket: add __sys_getpeername() helper; remove in-kernel call to
syscall
net: socket: add __sys_socketpair() helper; remove in-kernel call to
syscall
net: socket: add __sys_shutdown() helper; remove in-kernel call to
syscall
net: socket: add __sys_setsockopt() helper; remove in-kernel call to
syscall
net: socket: add __sys_getsockopt() helper; remove in-kernel call to
syscall
net: socket: add do_sys_recvmmsg() helper; remove in-kernel call to
syscall
net: socket: move check for forbid_cmsg_compat to __sys_...msg()
net: socket: replace calls to sys_send() with __sys_sendto()
net: socket: replace call to sys_recv() with __sys_recvfrom()
net: socket: add __compat_sys_recvfrom() helper; remove in-kernel call
to compat syscall
net: socket: add __compat_sys_setsockopt() helper; remove in-kernel
call to compat syscall
net: socket: add __compat_sys_getsockopt() helper; remove in-kernel
call to compat syscall
net: socket: add __compat_sys_recvmmsg() helper; remove in-kernel call
to compat syscall
net: socket: add __compat_sys_...msg() helpers; remove in-kernel calls
to compat syscalls
include/linux/socket.h | 37 +++++++-
net/compat.c | 136 +++++++++++++++++++---------
net/socket.c | 234 ++++++++++++++++++++++++++++++++++---------------
3 files changed, 291 insertions(+), 116 deletions(-)
--
2.16.2
^ permalink raw reply
* [PATCH net] net: dsa: mv88e6xxx: Fix binding documentation for MDIO busses
From: Andrew Lunn @ 2018-03-16 17:03 UTC (permalink / raw)
To: David Miller; +Cc: netdev, yxj790222, Andrew Lunn
The MDIO busses are switch proprieties and so should be inside the
switch node. Fix the examples in the binding document.
Reported-by: 尤晓杰 <yxj790222@163.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Fixes: a3c53be55c95 ("net: dsa: mv88e6xxx: Support multiple MDIO busses")
---
.../devicetree/bindings/net/dsa/marvell.txt | 48 +++++++++++-----------
1 file changed, 25 insertions(+), 23 deletions(-)
diff --git a/Documentation/devicetree/bindings/net/dsa/marvell.txt b/Documentation/devicetree/bindings/net/dsa/marvell.txt
index 1d4d0f49c9d0..8c033d48e2ba 100644
--- a/Documentation/devicetree/bindings/net/dsa/marvell.txt
+++ b/Documentation/devicetree/bindings/net/dsa/marvell.txt
@@ -50,14 +50,15 @@ Example:
compatible = "marvell,mv88e6085";
reg = <0>;
reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>;
- };
- mdio {
- #address-cells = <1>;
- #size-cells = <0>;
- switch1phy0: switch1phy0@0 {
- reg = <0>;
- interrupt-parent = <&switch0>;
- interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+
+ mdio {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ switch1phy0: switch1phy0@0 {
+ reg = <0>;
+ interrupt-parent = <&switch0>;
+ interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+ };
};
};
};
@@ -74,23 +75,24 @@ Example:
compatible = "marvell,mv88e6390";
reg = <0>;
reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>;
- };
- mdio {
- #address-cells = <1>;
- #size-cells = <0>;
- switch1phy0: switch1phy0@0 {
- reg = <0>;
- interrupt-parent = <&switch0>;
- interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+
+ mdio {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ switch1phy0: switch1phy0@0 {
+ reg = <0>;
+ interrupt-parent = <&switch0>;
+ interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+ };
};
- };
- mdio1 {
- compatible = "marvell,mv88e6xxx-mdio-external";
- #address-cells = <1>;
- #size-cells = <0>;
- switch1phy9: switch1phy0@9 {
- reg = <9>;
+ mdio1 {
+ compatible = "marvell,mv88e6xxx-mdio-external";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ switch1phy9: switch1phy0@9 {
+ reg = <9>;
+ };
};
};
};
--
2.16.2
^ permalink raw reply related
* HW question: i210 vs. BCM5461S over SGMII: no response from PHY to MDIO requests?
From: Frantisek Rysanek @ 2018-03-16 16:48 UTC (permalink / raw)
To: netdev
Dear polite inhabitants of the "netdev" mailing list,
this is for a skunkworks project at the fringe of my job...
More of a DIY hobby thing :-) I'm tinkering and having fun.
The wizards from linux-ptp have taught me how to use the i210 for
precise timestamping, which works fine at all copper speeds
and likely also for gigabit fiber (SERDES) which the i210 natively
supports (and which links fine).
The catch is: I'm trying to get this to work on 100Base-FX :-)
which is not a native interface for the i210.
It can do SERDES only at 1Gb. But, it can do SGMII.
I've managed to find an i210-based NIC from DeLock with an SFP slot
and I've managed to find two models of 100Base-FX SGMII SFP's.
My assumption is that the SFP's have SGMII instead of SERDES
and MDIO instead of SPD I2C - and the manufacturers of the board
and of the SFP's don't dispute that. Yet they have both vaguely
warned me in advance that it would not work work :-)
Well I've given it a try anyway, and I'm stuck at the MDIO level.
With one of the SFP's, I know for a fact that it's based on the
BCM5461S. The actual marking on the chip goes BCM5461SA... etc.
I've managed to modify the EEPROM of the NIC with EEUPDATE.
The Device ID wouldn't change, but the "flash config words" that I
needed were all willing to accept the change. So I can switch the
chip to SGMII with external MDIO, and I can even see the chip
generate an MDIO read transaction right after power-up.
http://support.fccps.cz/download/adv/frr/ptp/MDIO_oscillograms.zip
And this is where I'm stuck:
the BCM chip does not respond to the i210 MDIO requests.
I've hacked the igb driver a little, adding printks where I needed
them, to see what's going on... I believe I've also
spotted a minor bug where some PHY detection routine
tries to read the status register before the phy.addr is even
initialized...
This is what the Intel chip does on power up:
"read PHY reg. 0 from PHY addr <whatever I specify in the flash> ".
(= read PHY_CONTROL)
The igb driver does:
1) ret_val = hw->phy.ops.write_reg(hw, 0x1B, 0x8084);
...which succeeds, as apparently there's no "ACK bit" in the write
sequence. The MDIO master never gets to know if the slave PHY is
alive or not :-)
2) read "PHY control" == read PHY register 0
... this fails. The PHY just doesn't do its part, and the MDIO
controller HW in the MAC doesn't raise the status flag saying
"transaction completed".
The PHY just doesn't take over. It seems as if the i210 does not even
continue sending CLK pulses - as if waiting for an active 0 (ACK?)
from the PHY, and the ACK never comes.
I have modified the igb driver to just go ahead and try the next
step:
3) read PHY device ID == read PHY_ID1 == PHY register 0x02.
...which fails.
I did not bother to try other registers.
The one thing I'm not certain about is the required PHY addr.
Not sure if this is hardwired in the PHY chip, or set by pin straps,
or set by soft straps in the SFP's EEPROM or something.
(Not that I've seen an EEPROM inside the SFP.)
I've noticed some earlier suggested patches by Jonathan Toppins and
Alan Liebthal of Cumulus Networks (from mid 2015) who seem to have
gotten the "server ATOM's" MAC to work with a BCM5461S.
Their code mentioned phy_addr = 5, which was possibly board-specific
in their hardware.
I've actually tried wrapping the steps 1) 2) 3) above in a FOR loop,
iterating over phy_addr from 1 to 31.
I can see on an oscilloscope that the i210's MDIO controller keeps
trying different PHY addresses in the respective 5 bits of phy_addr,
but the SFP just doesn't respond to any read transaction.
The MDC (clock) from the i210 is a nice 50:50 rectangle at 2 MHz.
I have reasons to believe that the SFP is powered. There's a P-FET in
3.3Vcc driven by SDP3, which opens when SDP3 goes log.0.
Which does happen - the required state of SDP3 is encoded
in the flash and the driver also writes the CTRL_EXT at runtime
just in case.
Also, it works in SERDES mode, where the NIC links just fine.
And, I believe I can see some erratic responses from the SFP if I
turn off external MDIO = when the i210 SGMII tries to run with i2c
for management access to the PHY. In i2c mode, the controller runs
the clock line at 100 kHz (and obviously the framing/protocol is
different) - seems to me on the scope that the PHY starts babbling
something on the data line. The read transactions in i2c mode even
seem to succeed, but they read garbage. Interestingly regular,
garbage. Mii-diag says:
Basic registers of MII PHY #1:
7fff ff80 8000 007f 7fff ff80 8000 00ff.
And that pattern repeats always the same.
The SPF vendor has already replied that, as per spec, the BCM PHY
should support up to 2.5 MHz MDC. And, they provided a framing
diagram which looks like a perfect IEEE clause 22.
Still I'm wondering if I should try to marry the igb driver with the
"phylib" (which has some specific support for the BCM5461) and
specifically with the bit-banging MDIO driver.
Bit-banging might get me around some protocol incompatibility in MDIO
(Broadcom vs. Intel) but I would face another problem:
the way I understand it, the i210 needs to auto-configure the MAC
block based on data it gets via MDIO autonomously from the PHY. (I
understand that the high-speed SGMII lane for payload cannot
transport PHY management data in-band, is that correct?)
So if I bit-bang the MDIO protocol, and even get to talk to the SFP,
I probably won't be able to configure the MAC accordingly
explicitly...
After a few hours of playing with this, I finally stumbled (a little
too late) across this FAQ entry in an Intel i210/i211 FAQ PDF:
"For external PHY use SerDes SKU and configure to use SGMII with
SGMII capable PHY such as a Marvell 88e1112. Be advised, ND has not
been able to inter-operate with BRCM SGMII PHY so far."
Which does not explain any details. The full PDF is here:
https://www.intel.com/content/dam/www/public/us/en/documents/faqs/ethe
rnet-controller-i210-i211-faq.pdf
Anyway... if you've read this far, thanks for your kind attention
- and, any sort of comments are welcome :-)
Frank Rysanek
^ permalink raw reply
* Re: [PATCH net-next v3 1/7] ibmvnic: Generalize TX pool structure
From: David Miller @ 2018-03-16 16:52 UTC (permalink / raw)
To: tlfalcon; +Cc: netdev, jallen, nfont
In-Reply-To: <1521129763-21030-2-git-send-email-tlfalcon@linux.vnet.ibm.com>
From: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Date: Thu, 15 Mar 2018 11:02:37 -0500
> Remove some unused fields in the structure and include values
> describing the individual buffer size and number of buffers in
> a TX pool. This allows us to use these fields for TX pool buffer
> accounting as opposed to using hard coded values. Finally, split
> TSO buffers out and provide an additional TX pool array for TSO.
>
> Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
...
> diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
> index 099c89d..a2e21b3 100644
> --- a/drivers/net/ethernet/ibm/ibmvnic.h
> +++ b/drivers/net/ethernet/ibm/ibmvnic.h
> @@ -917,11 +917,9 @@ struct ibmvnic_tx_pool {
> int *free_map;
> int consumer_index;
> int producer_index;
> - wait_queue_head_t ibmvnic_tx_comp_q;
> - struct task_struct *work_thread;
> struct ibmvnic_long_term_buff long_term_buff;
> - struct ibmvnic_long_term_buff tso_ltb;
> - int tso_index;
> + int num_buffers;
> + int buf_size;
> };
>
> struct ibmvnic_rx_buff {
Thomas, members like tso_ltb are used in the code at this point.
You can't remove it here like this, because it makes your patch series
non-bisectable. The tree should compile cleanly and work properly at
each stage of your series.
Thank you.
^ permalink raw reply
* Re: [bpf-next PATCH v2 05/18] bpf: create tcp_bpf_ulp allowing BPF to monitor socket TX/RX data
From: John Fastabend @ 2018-03-16 16:47 UTC (permalink / raw)
To: Daniel Borkmann, Alexei Starovoitov; +Cc: davem, ast, davejwatson, netdev
In-Reply-To: <7791bf7d-5ca8-7e28-b740-bd6c40be402c@iogearbox.net>
On 03/15/2018 05:37 PM, Daniel Borkmann wrote:
> On 03/16/2018 12:06 AM, Alexei Starovoitov wrote:
>> On Thu, Mar 15, 2018 at 11:55:39PM +0100, Daniel Borkmann wrote:
>>> On 03/15/2018 11:20 PM, Alexei Starovoitov wrote:
>>>> On Thu, Mar 15, 2018 at 11:17:12PM +0100, Daniel Borkmann wrote:
>>>>> On 03/15/2018 10:59 PM, Alexei Starovoitov wrote:
>>>>>> On Mon, Mar 12, 2018 at 12:23:29PM -0700, John Fastabend wrote:
>>>>>>>
>>>>>>> +/* User return codes for SK_MSG prog type. */
>>>>>>> +enum sk_msg_action {
>>>>>>> + SK_MSG_DROP = 0,
>>>>>>> + SK_MSG_PASS,
>>>>>>> +};
>>>>>>
>>>>>> do we really need new enum here?
>>>>>> It's the same as 'enum sk_action' and SK_DROP == SK_MSG_DROP
>>>>>> and there will be only drop/pass in both enums.
>>>>>> Also I don't see where these two new SK_MSG_* are used...
>>>>>>
>>>>>>> +
>>>>>>> +/* user accessible metadata for SK_MSG packet hook, new fields must
>>>>>>> + * be added to the end of this structure
>>>>>>> + */
>>>>>>> +struct sk_msg_md {
>>>>>>> + __u32 data;
>>>>>>> + __u32 data_end;
>>>>>>> +};
>>>>>>
>>>>>> I think it's time for me to ask for forgiveness :)
>>>>>
>>>>> :-)
>>>>>
>>>>>> I used __u32 for data and data_end only because all other fields
>>>>>> in __sk_buff were __u32 at the time and I couldn't easily figure out
>>>>>> how to teach verifier to recognize 8-byte rewrites.
>>>>>> Unfortunately my mistake stuck and was copied over into xdp.
>>>>>> Since this is new struct let's do it right and add
>>>>>> 'void *data, *data_end' here,
>>>>>> since bpf prog will use them as 'void *' pointers.
>>>>>> There are no compat issues here, since bpf is always 64-bit.
>>>>>
>>>>> But at least offset-wise when you do the ctx rewrite this would then
>>>>> be a bit more tricky when you have 64 bit kernel with 32 bit user
>>>>> space since void * members are in each cases at different offset. So
>>>>> unless I'm missing something, this still should either be __u32 or
>>>>> __u64 instead of void *, no?
>>>>
>>>> there is no 32-bit user space. these structs are seen by bpf progs only
>>>> and bpf is 64-bit only too.
>>>> unless I'm missing your point.
>>>
>>> Ok, so lets say you have 32 bit LLVM binary and compile the prog where
>>> you access md->data_end. Given the void * in the struct will that access
>>> end up being BPF_W at ctx offset 4 or BPF_DW at ctx offset 8 from clang
>>> perspective (iow, is the back end treating this special and always use
>>> fixed BPF_DW in such case)? If not and it would be the first case with
>>> offset 4, then we could have the case that underlying 64 bit kernel is
>>> expecting ctx offset 8 for doing the md ctx conversion.
>>
>> i'm still not quite following.
>> Whether llvm itself is 32-bit binary or it's arm32 or sprac32 binary
>> doesn't matter. It will produce the same 64-bit bpf code.
>> It will see 'void *' deref from this struct and will emit DW.
>> May be confusion is from newly added -mattr=+alu32 flag?
>> That option doesn't change that sizeof(void*)==8.
>> It only allows backend to emit 32-bit alu insns.
>
> Ok, so conclusion we had is that while BPF target is unconditionally 64 bit,
> it depends which clang front end you use for compilation wrt structs. E.g.
> on 32 bit native (e.g. arm) clang front end it would compile the ctx void *
> pointers as 4 byte while using clang -target bpf it would compile it as 8
> byte. The native clang front end is needed in case of tracing when accessing
> pt_regs for walking data structures, but not for networking use case, so
> always using -target bpf there is proper way. Meaning there would be no
> confusion on the void * since size will always be 8 regardless of underlying
> arch being 32 or 64 bit or clang/llvm binary being 32 bit on 64 bit kernel.
> Thus, sticking to void * would be fine, but definitely samples/sockmap/Makefile
> must be fixed as well, such that people don't copy it wrongly.
>
> Cheers,
> Danie
I'll send a fix for sockmap/Makefile then as a separate series. And
go ahead and change this series to use 'void *'.
Thanks for the follow-up on this.
^ 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