* [PATCH 018/109] net: socket: add __sys_shutdown() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_shutdown() allows us to avoid the
internal calls to the sys_shutdown() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
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]);
--
2.16.3
^ permalink raw reply related
* [PATCH 019/109] net: socket: add __sys_setsockopt() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_setsockopt() allows us to avoid the
internal calls to the sys_setsockopt() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
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 =
--
2.16.3
^ permalink raw reply related
* [PATCH 020/109] net: socket: add __sys_getsockopt() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_getsockopt() allows us to avoid the
internal calls to the sys_getsockopt() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
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]);
--
2.16.3
^ permalink raw reply related
* [PATCH 021/109] net: socket: add do_sys_recvmmsg() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper do_sys_recvmmsg() allows us to avoid the
internal calls to the sys_getsockopt() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
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..54d19b0edab1 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 int 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,
--
2.16.3
^ permalink raw reply related
* [PATCH 022/109] net: socket: move check for forbid_cmsg_compat to __sys_...msg()
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-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.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
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 54d19b0edab1..a70793a7ce78 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],
--
2.16.3
^ permalink raw reply related
* [PATCH 023/109] net: socket: replace calls to sys_send() with __sys_sendto()
From: Dominik Brodowski @ 2018-03-29 11:23 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-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().
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
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 a70793a7ce78..92de21bb1a2e 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],
--
2.16.3
^ permalink raw reply related
* [PATCH 024/109] net: socket: replace call to sys_recv() with __sys_recvfrom()
From: Dominik Brodowski @ 2018-03-29 11:23 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-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().
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
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 92de21bb1a2e..03702f08aa62 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],
--
2.16.3
^ permalink raw reply related
* [PATCH 025/109] net: socket: add __compat_sys_recvfrom() helper; remove in-kernel call to compat syscall
From: Dominik Brodowski @ 2018-03-29 11:23 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __compat_sys_recvfrom() allows us to avoid
the internal calls to the compat_sys_recvfrom() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
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);
--
2.16.3
^ permalink raw reply related
* [PATCH 026/109] net: socket: add __compat_sys_setsockopt() helper; remove in-kernel call to compat syscall
From: Dominik Brodowski @ 2018-03-29 11:23 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __compat_sys_setsockopt() allows us to avoid
the internal calls to the compat_sys_setsockopt() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
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],
--
2.16.3
^ permalink raw reply related
* [PATCH 027/109] net: socket: add __compat_sys_getsockopt() helper; remove in-kernel call to compat syscall
From: Dominik Brodowski @ 2018-03-29 11:23 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __compat_sys_getsockopt() allows us to avoid
the internal calls to the compat_sys_getsockopt() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
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]);
--
2.16.3
^ permalink raw reply related
* [PATCH 028/109] net: socket: add __compat_sys_recvmmsg() helper; remove in-kernel call to compat syscall
From: Dominik Brodowski @ 2018-03-29 11:23 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __compat_sys_recvmmsg() allows us to avoid
the internal calls to the compat_sys_recvmmsg() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
net/compat.c | 17 ++++++++++++-----
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/net/compat.c b/net/compat.c
index cdf5b0c1b962..7b2ae42a1598 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -787,9 +787,9 @@ COMPAT_SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, buf, compat_size_t, len
return __compat_sys_recvfrom(fd, buf, len, flags, addr, addrlen);
}
-COMPAT_SYSCALL_DEFINE5(recvmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
- unsigned int, vlen, unsigned int, flags,
- struct compat_timespec __user *, timeout)
+static int __compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg,
+ unsigned int vlen, unsigned int flags,
+ struct compat_timespec __user *timeout)
{
int datagrams;
struct timespec ktspec;
@@ -809,6 +809,13 @@ COMPAT_SYSCALL_DEFINE5(recvmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
return datagrams;
}
+COMPAT_SYSCALL_DEFINE5(recvmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
+ unsigned int, vlen, unsigned int, flags,
+ struct compat_timespec __user *, timeout)
+{
+ return __compat_sys_recvmmsg(fd, mmsg, vlen, flags, timeout);
+}
+
COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
{
u32 a[AUDITSC_ARGS];
@@ -895,8 +902,8 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
ret = compat_sys_recvmsg(a0, compat_ptr(a1), a[2]);
break;
case SYS_RECVMMSG:
- ret = compat_sys_recvmmsg(a0, compat_ptr(a1), a[2], a[3],
- compat_ptr(a[4]));
+ ret = __compat_sys_recvmmsg(a0, compat_ptr(a1), a[2], a[3],
+ compat_ptr(a[4]));
break;
case SYS_ACCEPT4:
ret = __sys_accept4(a0, compat_ptr(a1), compat_ptr(a[2]), a[3]);
--
2.16.3
^ permalink raw reply related
* [PATCH 029/109] net: socket: add __compat_sys_...msg() helpers; remove in-kernel calls to compat syscalls
From: Dominik Brodowski @ 2018-03-29 11:23 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helpers __compat_sys_...msg() allows us to avoid
the internal calls to the compat_sys_...msg() syscalls.
compat_sys_recvmmsg() is handled in a different patch.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
net/compat.c | 37 ++++++++++++++++++++++++++++++-------
1 file changed, 30 insertions(+), 7 deletions(-)
diff --git a/net/compat.c b/net/compat.c
index 7b2ae42a1598..5ae7437d3853 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -747,25 +747,48 @@ static unsigned char nas[21] = {
};
#undef AL
-COMPAT_SYSCALL_DEFINE3(sendmsg, int, fd, struct compat_msghdr __user *, msg, unsigned int, flags)
+static inline long __compat_sys_sendmsg(int fd,
+ struct compat_msghdr __user *msg,
+ unsigned int flags)
{
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)
+COMPAT_SYSCALL_DEFINE3(sendmsg, int, fd, struct compat_msghdr __user *, msg,
+ unsigned int, flags)
+{
+ return __compat_sys_sendmsg(fd, msg, flags);
+}
+
+static inline long __compat_sys_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, false);
}
-COMPAT_SYSCALL_DEFINE3(recvmsg, int, fd, struct compat_msghdr __user *, msg, unsigned int, flags)
+COMPAT_SYSCALL_DEFINE4(sendmmsg, int, fd, struct compat_mmsghdr __user *, mmsg,
+ unsigned int, vlen, unsigned int, flags)
+{
+ return __compat_sys_sendmmsg(fd, mmsg, vlen, flags);
+}
+
+static inline long __compat_sys_recvmsg(int fd,
+ struct compat_msghdr __user *msg,
+ unsigned int flags)
{
return __sys_recvmsg(fd, (struct user_msghdr __user *)msg,
flags | MSG_CMSG_COMPAT, false);
}
+COMPAT_SYSCALL_DEFINE3(recvmsg, int, fd, struct compat_msghdr __user *, msg,
+ unsigned int, flags)
+{
+ return __compat_sys_recvmsg(fd, msg, flags);
+}
+
static inline long __compat_sys_recvfrom(int fd, void __user *buf,
compat_size_t len, unsigned int flags,
struct sockaddr __user *addr,
@@ -893,13 +916,13 @@ COMPAT_SYSCALL_DEFINE2(socketcall, int, call, u32 __user *, args)
compat_ptr(a[4]));
break;
case SYS_SENDMSG:
- ret = compat_sys_sendmsg(a0, compat_ptr(a1), a[2]);
+ ret = __compat_sys_sendmsg(a0, compat_ptr(a1), a[2]);
break;
case SYS_SENDMMSG:
- ret = compat_sys_sendmmsg(a0, compat_ptr(a1), a[2], a[3]);
+ ret = __compat_sys_sendmmsg(a0, compat_ptr(a1), a[2], a[3]);
break;
case SYS_RECVMSG:
- ret = compat_sys_recvmsg(a0, compat_ptr(a1), a[2]);
+ ret = __compat_sys_recvmsg(a0, compat_ptr(a1), a[2]);
break;
case SYS_RECVMMSG:
ret = __compat_sys_recvmmsg(a0, compat_ptr(a1), a[2], a[3],
--
2.16.3
^ permalink raw reply related
* [PATCH 104/109] net: remove compat_sys_*() prototypes from net/compat.h
From: Dominik Brodowski @ 2018-03-29 11:24 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
As the syscall functions should only be called from the system call table
but not from elsewhere in the kernel, it is sufficient that they are
defined in linux/compat.h.
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
include/net/compat.h | 11 -----------
1 file changed, 11 deletions(-)
diff --git a/include/net/compat.h b/include/net/compat.h
index a91bea80b9fc..4c6d75612b6c 100644
--- a/include/net/compat.h
+++ b/include/net/compat.h
@@ -44,17 +44,6 @@ int compat_sock_get_timestampns(struct sock *, struct timespec __user *);
int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *,
struct sockaddr __user **, struct iovec **);
struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval);
-asmlinkage long compat_sys_sendmsg(int, struct compat_msghdr __user *,
- unsigned int);
-asmlinkage long compat_sys_sendmmsg(int, struct compat_mmsghdr __user *,
- unsigned int, unsigned int);
-asmlinkage long compat_sys_recvmsg(int, struct compat_msghdr __user *,
- unsigned int);
-asmlinkage long compat_sys_recvmmsg(int, struct compat_mmsghdr __user *,
- unsigned int, unsigned int,
- struct compat_timespec __user *);
-asmlinkage long compat_sys_getsockopt(int, int, int, char __user *,
- int __user *);
int put_cmsg_compat(struct msghdr*, int, int, int, void *);
int cmsghdr_from_user_compat_to_kern(struct msghdr *, struct sock *,
--
2.16.3
^ permalink raw reply related
* [PATCH 106/109] syscalls/x86: auto-create compat_sys_*() prototypes
From: Dominik Brodowski @ 2018-03-29 11:24 UTC (permalink / raw)
To: linux-kernel
Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev,
Thomas Gleixner, Andi Kleen, Ingo Molnar, Andrew Morton, Al Viro,
x86
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
compat_sys_*() functions are no longer called from within the kernel on
x86 except from the system call table. Linking the system call does not
require compat_sys_*() function prototypes at least on x86. Therefore,
generate compat_sys_*() prototypes on-the-fly within the
COMPAT_SYSCALL_DEFINEx() macro, and remove x86-specific prototypes from
various header files.
Suggested-by: Andy Lutomirski <luto@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David S. Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: x86@kernel.org
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
arch/x86/ia32/ia32_signal.c | 1 -
arch/x86/ia32/sys_ia32.c | 2 +-
arch/x86/include/asm/sys_ia32.h | 64 -----------------------------------------
include/linux/compat.h | 17 ++---------
4 files changed, 4 insertions(+), 80 deletions(-)
delete mode 100644 arch/x86/include/asm/sys_ia32.h
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 41c671854642..86b1341cba9a 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -33,7 +33,6 @@
#include <asm/vdso.h>
#include <asm/sigframe.h>
#include <asm/sighandling.h>
-#include <asm/sys_ia32.h>
#include <asm/smap.h>
/*
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index bd8a7020b9a7..11ef7b7c9cc8 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -47,7 +47,7 @@
#include <linux/uaccess.h>
#include <linux/atomic.h>
#include <asm/vgtod.h>
-#include <asm/sys_ia32.h>
+#include <asm/ia32.h>
#define AA(__x) ((unsigned long)(__x))
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
deleted file mode 100644
index 2ee6e3b96656..000000000000
--- a/arch/x86/include/asm/sys_ia32.h
+++ /dev/null
@@ -1,64 +0,0 @@
-/*
- * sys_ia32.h - Linux ia32 syscall interfaces
- *
- * Copyright (c) 2008 Jaswinder Singh Rajput
- *
- * This file is released under the GPLv2.
- * See the file COPYING for more details.
- */
-
-#ifndef _ASM_X86_SYS_IA32_H
-#define _ASM_X86_SYS_IA32_H
-
-#ifdef CONFIG_COMPAT
-
-#include <linux/compiler.h>
-#include <linux/linkage.h>
-#include <linux/types.h>
-#include <linux/signal.h>
-#include <asm/compat.h>
-#include <asm/ia32.h>
-
-/* ia32/sys_ia32.c */
-asmlinkage long compat_sys_x86_truncate64(const char __user *, unsigned long,
- unsigned long);
-asmlinkage long compat_sys_x86_ftruncate64(unsigned int, unsigned long,
- unsigned long);
-
-asmlinkage long compat_sys_x86_stat64(const char __user *,
- struct stat64 __user *);
-asmlinkage long compat_sys_x86_lstat64(const char __user *,
- struct stat64 __user *);
-asmlinkage long compat_sys_x86_fstat64(unsigned int, struct stat64 __user *);
-asmlinkage long compat_sys_x86_fstatat(unsigned int, const char __user *,
- struct stat64 __user *, int);
-struct mmap_arg_struct32;
-asmlinkage long compat_sys_x86_mmap(struct mmap_arg_struct32 __user *);
-
-asmlinkage long compat_sys_x86_pread(unsigned int, char __user *, u32, u32,
- u32);
-asmlinkage long compat_sys_x86_pwrite(unsigned int, const char __user *, u32,
- u32, u32);
-
-asmlinkage long compat_sys_x86_fadvise64_64(int, __u32, __u32, __u32, __u32,
- int);
-
-asmlinkage ssize_t compat_sys_x86_readahead(int, unsigned int, unsigned int,
- size_t);
-asmlinkage long compat_sys_x86_sync_file_range(int, unsigned int, unsigned int,
- unsigned int, unsigned int,
- int);
-asmlinkage long compat_sys_x86_fadvise64(int, unsigned int, unsigned int,
- size_t, int);
-asmlinkage long compat_sys_x86_fallocate(int, int, unsigned int, unsigned int,
- unsigned int, unsigned int);
-asmlinkage long compat_sys_x86_clone(unsigned long, unsigned long, int __user *,
- unsigned long, int __user *);
-
-/* ia32/ia32_signal.c */
-asmlinkage long sys32_sigreturn(void);
-asmlinkage long sys32_rt_sigreturn(void);
-
-#endif /* CONFIG_COMPAT */
-
-#endif /* _ASM_X86_SYS_IA32_H */
diff --git a/include/linux/compat.h b/include/linux/compat.h
index f881cce627f6..8cb8710db0ab 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -49,6 +49,7 @@
COMPAT_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__)
#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \
+ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))\
__attribute__((alias(__stringify(compat_SyS##name)))); \
static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
@@ -507,8 +508,8 @@ int __compat_save_altstack(compat_stack_t __user *, unsigned long);
/*
* These syscall function prototypes are kept in the same order as
- * include/uapi/asm-generic/unistd.h. Architecture specific entries go below,
- * followed by deprecated or obsolete system calls.
+ * include/uapi/asm-generic/unistd.h. Deprecated or obsolete system calls
+ * go below.
*
* Please note that these prototypes here are only provided for information
* purposes, for static analysis, and for linking from the syscall table.
@@ -882,18 +883,6 @@ asmlinkage long compat_sys_pwritev64v2(unsigned long fd,
#endif
-/*
- * Architecture-specific system calls
- */
-
-/* fs/quota/compat.c -- x86 only */
-asmlinkage long compat_sys_quotactl32(unsigned int cmd,
- const char __user *special, qid_t id, void __user *addr);
-
-/* arch_prctl -- x86 */
-asmlinkage long compat_sys_arch_prctl(int option, unsigned long arg2);
-
-
/*
* Deprecated system calls which are still defined in
* include/uapi/asm-generic/unistd.h and wanted by >= 1 arch
--
2.16.3
^ permalink raw reply related
* [PATCH 008/109] net: socket: add __sys_recvfrom() helper; remove in-kernel call to syscall
From: Dominik Brodowski @ 2018-03-29 11:22 UTC (permalink / raw)
To: linux-kernel; +Cc: viro, torvalds, arnd, linux-arch, David S . Miller, netdev
In-Reply-To: <20180329112426.23043-1-linux@dominikbrodowski.net>
Using the net-internal helper __sys_recvfrom() allows us to avoid the
internal calls to the sys_recvfrom() syscall.
This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net
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);
--
2.16.3
^ permalink raw reply related
* [PATCH net-next] net: tcp: update mib LISTENOVERFLOWS if syn flood
From: yuan linyu @ 2018-03-29 11:20 UTC (permalink / raw)
To: netdev; +Cc: David S . Miller, yuan linyu
From: yuan linyu <Linyu.Yuan@alcatel-sbell.com.cn>
it's better to update mib LISTENOVERFLOWS even if packet is flood
Signed-off-by: yuan linyu <Linyu.Yuan@alcatel-sbell.com.cn>
---
net/ipv4/tcp_input.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 451ef3012636..581f5b03ae54 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6220,6 +6220,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
struct sock *fastopen_sk = NULL;
struct request_sock *req;
bool want_cookie = false;
+ bool want_drop = false;
struct dst_entry *dst;
struct flowi fl;
@@ -6231,14 +6232,17 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
inet_csk_reqsk_queue_is_full(sk)) && !isn) {
want_cookie = tcp_syn_flood_action(sk, skb, rsk_ops->slab_name);
if (!want_cookie)
- goto drop;
+ want_drop = true;
}
if (sk_acceptq_is_full(sk)) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
- goto drop;
+ want_drop = true;
}
+ if (want_drop)
+ goto drop;
+
req = inet_reqsk_alloc(rsk_ops, sk, !want_cookie);
if (!req)
goto drop;
--
2.14.1
^ permalink raw reply related
* Re: [PATCH 1/2] net: mvneta: split rxq/txq init into SW and HW parts
From: Thomas Petazzoni @ 2018-03-29 11:42 UTC (permalink / raw)
To: Jisheng Zhang; +Cc: David Miller, netdev, linux-arm-kernel, linux-kernel
In-Reply-To: <20180329181356.6489ee2e@xhacker.debian>
Hello,
On Thu, 29 Mar 2018 18:13:56 +0800, Jisheng Zhang wrote:
> This is to prepare the suspend/resume improvement in next patch. The
> SW parts can be optimized out during resume.
>
> Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Thanks, I have two very minor nits below, but otherwise:
Acked-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
> +/* Create a specified RX queue */
> +static int mvneta_rxq_init(struct mvneta_port *pp,
> + struct mvneta_rx_queue *rxq)
> +
> +{
> + int ret;
> +
> + ret = mvneta_rxq_sw_init(pp, rxq);
> + if (ret)
Here you're testing if (ret), while in mvneta_txq_init(), in the same
situation, you're doing if (ret < 0). I don't have a preference for one
or the other, but having them consistent between the two lpaces would
be nice.
> -/* Create and initialize a tx queue */
> -static int mvneta_txq_init(struct mvneta_port *pp,
> - struct mvneta_tx_queue *txq)
> +static int mvneta_txq_sw_init(struct mvneta_port *pp,
> + struct mvneta_tx_queue *txq)
> {
> int cpu;
>
> @@ -2872,7 +2889,6 @@ static int mvneta_txq_init(struct mvneta_port *pp,
> txq->tx_stop_threshold = txq->size - MVNETA_MAX_SKB_DESCS;
> txq->tx_wake_threshold = txq->tx_stop_threshold / 2;
>
> -
Spurious change.
Thanks!
Thomas Petazzoni
--
Thomas Petazzoni, CTO, Bootlin (formerly Free Electrons)
Embedded Linux and Kernel engineering
https://bootlin.com
^ permalink raw reply
* Re: [PATCH 2/2] net: mvneta: improve suspend/resume
From: Thomas Petazzoni @ 2018-03-29 11:54 UTC (permalink / raw)
To: Jisheng Zhang; +Cc: David Miller, netdev, linux-arm-kernel, linux-kernel
In-Reply-To: <20180329181536.46e065d2@xhacker.debian>
Hello Jisheng,
On Thu, 29 Mar 2018 18:15:36 +0800, Jisheng Zhang wrote:
> Current suspend/resume implementation reuses the mvneta_open() and
> mvneta_close(), but it could be optimized to take only necessary
> actions during suspend/resume.
>
> One obvious problem of current implementation is: after hundreds of
> system suspend/resume cycles, the resume of mvneta could fail due to
> fragmented dma coherent memory. After this patch, the non-necessary
> memory alloc/free is optimized out.
Indeed, this needs to be fixed, you're totally right.
> Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
> ---
> drivers/net/ethernet/marvell/mvneta.c | 76 ++++++++++++++++++++++++++++++-----
> 1 file changed, 66 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
> index 4ec69bbd1eb4..1870f1dd7093 100644
> --- a/drivers/net/ethernet/marvell/mvneta.c
> +++ b/drivers/net/ethernet/marvell/mvneta.c
> @@ -4575,14 +4575,46 @@ static int mvneta_remove(struct platform_device *pdev)
> #ifdef CONFIG_PM_SLEEP
> static int mvneta_suspend(struct device *device)
> {
> + int queue;
> struct net_device *dev = dev_get_drvdata(device);
> struct mvneta_port *pp = netdev_priv(dev);
>
> - rtnl_lock();
> - if (netif_running(dev))
> - mvneta_stop(dev);
> - rtnl_unlock();
> + if (!netif_running(dev))
> + return 0;
This is changing the behavior I believe. The current code is:
rtnl_lock();
if (netif_running(dev))
mvneta_stop(dev);
rtnl_unlock();
netif_device_detach(dev);
clk_disable_unprepare(pp->clk_bus);
clk_disable_unprepare(pp->clk);
return 0;
So, when netif_running(dev) is false, we're indeed not calling
mvneta_stop(), but we're still doing netif_device_detach(), and
disabling the clocks. With your change, we're no longer doing these
steps.
> +
> netif_device_detach(dev);
> +
> + mvneta_stop_dev(pp);
> +
> + if (!pp->neta_armada3700) {
> + spin_lock(&pp->lock);
> + pp->is_stopped = true;
> + spin_unlock(&pp->lock);
Real question: is it OK to set pp->is_stopped *after* calling
mvneta_stop_dev(), while it was set before calling mvneta_stop_dev() in
the current code ?
> +
> + cpuhp_state_remove_instance_nocalls(online_hpstate,
> + &pp->node_online);
> + cpuhp_state_remove_instance_nocalls(CPUHP_NET_MVNETA_DEAD,
> + &pp->node_dead);
Do we need to remove/add those CPU notifiers when suspending/resuming ?
> + }
> +
> + for (queue = 0; queue < rxq_number; queue++) {
> + struct mvneta_rx_queue *rxq = &pp->rxqs[queue];
> +
> + mvneta_rxq_drop_pkts(pp, rxq);
> + }
Wouldn't it make sense to have
mvneta_rxq_sw_deinit/mvneta_rxq_hw_deinit(), like you did for the
initialization ?
> +
> + for (queue = 0; queue < txq_number; queue++) {
> + struct mvneta_tx_queue *txq = &pp->txqs[queue];
> +
> + /* Set minimum bandwidth for disabled TXQs */
> + mvreg_write(pp, MVETH_TXQ_TOKEN_CFG_REG(txq->id), 0);
> + mvreg_write(pp, MVETH_TXQ_TOKEN_COUNT_REG(txq->id), 0);
> +
> + /* Set Tx descriptors queue starting address and size */
> + mvreg_write(pp, MVNETA_TXQ_BASE_ADDR_REG(txq->id), 0);
> + mvreg_write(pp, MVNETA_TXQ_SIZE_REG(txq->id), 0);
> + }
Same comment here: a mvneta_txq_sw_deinit()/mvneta_txq_hw_deinit()
would be good, and would avoid duplicating this logic.
> +
> clk_disable_unprepare(pp->clk_bus);
> clk_disable_unprepare(pp->clk);
> return 0;
> @@ -4593,7 +4625,7 @@ static int mvneta_resume(struct device *device)
> struct platform_device *pdev = to_platform_device(device);
> struct net_device *dev = dev_get_drvdata(device);
> struct mvneta_port *pp = netdev_priv(dev);
> - int err;
> + int err, queue;
>
> clk_prepare_enable(pp->clk);
> if (!IS_ERR(pp->clk_bus))
> @@ -4614,13 +4646,37 @@ static int mvneta_resume(struct device *device)
> return err;
> }
>
> + if (!netif_running(dev))
> + return 0;
> +
> netif_device_attach(dev);
> - rtnl_lock();
> - if (netif_running(dev)) {
> - mvneta_open(dev);
> - mvneta_set_rx_mode(dev);
> +
> + for (queue = 0; queue < rxq_number; queue++) {
> + struct mvneta_rx_queue *rxq = &pp->rxqs[queue];
> +
> + rxq->next_desc_to_proc = 0;
> + mvneta_rxq_hw_init(pp, rxq);
> }
> - rtnl_unlock();
> +
> + for (queue = 0; queue < txq_number; queue++) {
> + struct mvneta_tx_queue *txq = &pp->txqs[queue];
> +
> + txq->next_desc_to_proc = 0;
> + mvneta_txq_hw_init(pp, txq);
> + }
> +
> + if (!pp->neta_armada3700) {
> + spin_lock(&pp->lock);
> + pp->is_stopped = false;
> + spin_unlock(&pp->lock);
> + cpuhp_state_add_instance_nocalls(online_hpstate,
> + &pp->node_online);
> + cpuhp_state_add_instance_nocalls(CPUHP_NET_MVNETA_DEAD,
> + &pp->node_dead);
> + }
> +
> + mvneta_set_rx_mode(dev);
> + mvneta_start_dev(pp);
Thanks!
Thomas
--
Thomas Petazzoni, CTO, Bootlin (formerly Free Electrons)
Embedded Linux and Kernel engineering
https://bootlin.com
^ permalink raw reply
* [PATCH] qed: fix spelling mistake: "checksumed" -> "checksummed"
From: Colin King @ 2018-03-29 11:59 UTC (permalink / raw)
To: Ariel Elior, everest-linux-l2, netdev; +Cc: kernel-janitors, linux-kernel
From: Colin Ian King <colin.king@canonical.com>
Trivial fix to spelling mistake in DP_INFO message text
Signed-off-by: Colin Ian King <colin.king@canonical.com>
---
drivers/net/ethernet/qlogic/qed/qed_ll2.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index c4f14fdc4e77..0c50ed1955c4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -2383,7 +2383,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb)
u8 flags = 0;
if (unlikely(skb->ip_summed != CHECKSUM_NONE)) {
- DP_INFO(cdev, "Cannot transmit a checksumed packet\n");
+ DP_INFO(cdev, "Cannot transmit a checksummed packet\n");
return -EINVAL;
}
--
2.15.1
^ permalink raw reply related
* Re: [PATCH net] net/dim: Fix int overflow
From: Andy Gospodarek @ 2018-03-29 12:01 UTC (permalink / raw)
To: Tal Gilboa
Cc: David S. Miller, netdev, Tariq Toukan, Andy Gospodarek,
Saeed Mahameed
In-Reply-To: <1522320832-18416-1-git-send-email-talgi@mellanox.com>
On Thu, Mar 29, 2018 at 01:53:52PM +0300, Tal Gilboa wrote:
> When calculating difference between samples, the values
> are multiplied by 100. Large values may cause int overflow
> when multiplied (usually on first iteration).
> Fixed by forcing 100 to be of type unsigned long.
>
> Fixes: 4c4dbb4a7363 ("net/mlx5e: Move dynamic interrupt coalescing code to include/linux")
> Signed-off-by: Tal Gilboa <talgi@mellanox.com>
Reviewed-by: Andy Gospodarek <gospo@broadcom.com>
> ---
> include/linux/net_dim.h | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h
> index bebeaad..29ed8fd 100644
> --- a/include/linux/net_dim.h
> +++ b/include/linux/net_dim.h
> @@ -231,7 +231,7 @@ static inline void net_dim_exit_parking(struct net_dim *dim)
> }
>
> #define IS_SIGNIFICANT_DIFF(val, ref) \
> - (((100 * abs((val) - (ref))) / (ref)) > 10) /* more than 10% difference */
> + (((100UL * abs((val) - (ref))) / (ref)) > 10) /* more than 10% difference */
>
> static inline int net_dim_stats_compare(struct net_dim_stats *curr,
> struct net_dim_stats *prev)
> --
> 1.8.3.1
>
^ permalink raw reply
* NAK: [PATCH] qed: fix spelling mistake: "checksumed" -> "checksummed"
From: Colin Ian King @ 2018-03-29 12:05 UTC (permalink / raw)
To: Ariel Elior, everest-linux-l2, netdev; +Cc: kernel-janitors, linux-kernel
In-Reply-To: <20180329115947.26920-1-colin.king@canonical.com>
On 29/03/18 12:59, Colin King wrote:
> From: Colin Ian King <colin.king@canonical.com>
>
> Trivial fix to spelling mistake in DP_INFO message text
>
> Signed-off-by: Colin Ian King <colin.king@canonical.com>
> ---
> drivers/net/ethernet/qlogic/qed/qed_ll2.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
> index c4f14fdc4e77..0c50ed1955c4 100644
> --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
> +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
> @@ -2383,7 +2383,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb)
> u8 flags = 0;
>
> if (unlikely(skb->ip_summed != CHECKSUM_NONE)) {
> - DP_INFO(cdev, "Cannot transmit a checksumed packet\n");
> + DP_INFO(cdev, "Cannot transmit a checksummed packet\n");
> return -EINVAL;
> }
>
>
Found some more issues, I'll send an updated fix in a while
^ permalink raw reply
* [PATCH v2 0/2] gfs2: Stop using rhashtable_walk_peek
From: Andreas Gruenbacher @ 2018-03-29 12:06 UTC (permalink / raw)
To: cluster-devel
Cc: netdev, linux-kernel, NeilBrown, Thomas Graf, Herbert Xu,
Tom Herbert, Andreas Gruenbacher
Here's a second version of the patch (now a patch set) to eliminate
rhashtable_walk_peek in gfs2.
The first patch introduces lockref_put_not_zero, the inverse of
lockref_get_not_zero.
The second patch eliminates rhashtable_walk_peek in gfs2. In
gfs2_glock_iter_next, the new lockref function from patch one is used to
drop a lockref count as long as the count doesn't drop to zero. This is
almost always the case; if there is a risk of dropping the last
reference, we must defer that to a work queue because dropping the last
reference may sleep.
Thanks,
Andreas
Andreas Gruenbacher (2):
lockref: Add lockref_put_not_zero
gfs2: Stop using rhashtable_walk_peek
fs/gfs2/glock.c | 47 ++++++++++++++++++++++++++++-------------------
include/linux/lockref.h | 1 +
lib/lockref.c | 28 ++++++++++++++++++++++++++++
3 files changed, 57 insertions(+), 19 deletions(-)
--
2.14.3
^ permalink raw reply
* [PATCH v2 1/2] lockref: Add lockref_put_not_zero
From: Andreas Gruenbacher @ 2018-03-29 12:06 UTC (permalink / raw)
To: cluster-devel
Cc: netdev, linux-kernel, NeilBrown, Thomas Graf, Herbert Xu,
Tom Herbert, Andreas Gruenbacher
In-Reply-To: <20180329120612.6104-1-agruenba@redhat.com>
Put a lockref unless the lockref is dead or its count would become zero.
This is the same as lockref_put_or_lock except that the lock is never
left held.
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
include/linux/lockref.h | 1 +
lib/lockref.c | 28 ++++++++++++++++++++++++++++
2 files changed, 29 insertions(+)
diff --git a/include/linux/lockref.h b/include/linux/lockref.h
index 2eac32095113..99f17cc8e163 100644
--- a/include/linux/lockref.h
+++ b/include/linux/lockref.h
@@ -37,6 +37,7 @@ struct lockref {
extern void lockref_get(struct lockref *);
extern int lockref_put_return(struct lockref *);
extern int lockref_get_not_zero(struct lockref *);
+extern int lockref_put_not_zero(struct lockref *);
extern int lockref_get_or_lock(struct lockref *);
extern int lockref_put_or_lock(struct lockref *);
diff --git a/lib/lockref.c b/lib/lockref.c
index 47169ed7e964..3d468b53d4c9 100644
--- a/lib/lockref.c
+++ b/lib/lockref.c
@@ -80,6 +80,34 @@ int lockref_get_not_zero(struct lockref *lockref)
}
EXPORT_SYMBOL(lockref_get_not_zero);
+/**
+ * lockref_put_not_zero - Decrements count unless count <= 1 before decrement
+ * @lockref: pointer to lockref structure
+ * Return: 1 if count updated successfully or 0 if count would become zero
+ */
+int lockref_put_not_zero(struct lockref *lockref)
+{
+ int retval;
+
+ CMPXCHG_LOOP(
+ new.count--;
+ if (old.count <= 1)
+ return 0;
+ ,
+ return 1;
+ );
+
+ spin_lock(&lockref->lock);
+ retval = 0;
+ if (lockref->count > 1) {
+ lockref->count--;
+ retval = 1;
+ }
+ spin_unlock(&lockref->lock);
+ return retval;
+}
+EXPORT_SYMBOL(lockref_put_not_zero);
+
/**
* lockref_get_or_lock - Increments count unless the count is 0 or dead
* @lockref: pointer to lockref structure
--
2.14.3
^ permalink raw reply related
* [PATCH v2 2/2] gfs2: Stop using rhashtable_walk_peek
From: Andreas Gruenbacher @ 2018-03-29 12:06 UTC (permalink / raw)
To: cluster-devel
Cc: netdev, linux-kernel, NeilBrown, Thomas Graf, Herbert Xu,
Tom Herbert, Andreas Gruenbacher
In-Reply-To: <20180329120612.6104-1-agruenba@redhat.com>
Function rhashtable_walk_peek is problematic because there is no
guarantee that the glock previously returned still exists; when that key
is deleted, rhashtable_walk_peek can end up returning a different key,
which will cause an inconsistent glock dump. Fix this by keeping track
of the current glock in the seq file iterator functions instead.
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
fs/gfs2/glock.c | 47 ++++++++++++++++++++++++++++-------------------
1 file changed, 28 insertions(+), 19 deletions(-)
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 82fb5583445c..097bd3c0f270 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1923,28 +1923,37 @@ void gfs2_glock_exit(void)
static void gfs2_glock_iter_next(struct gfs2_glock_iter *gi, loff_t n)
{
- if (n == 0)
- gi->gl = rhashtable_walk_peek(&gi->hti);
- else {
- gi->gl = rhashtable_walk_next(&gi->hti);
- n--;
+ struct gfs2_glock *gl = gi->gl;
+
+ if (gl) {
+ if (n == 0)
+ return;
+ if (!lockref_put_not_zero(&gl->gl_lockref))
+ gfs2_glock_queue_put(gl);
}
for (;;) {
- if (IS_ERR_OR_NULL(gi->gl)) {
- if (!gi->gl)
- return;
- if (PTR_ERR(gi->gl) != -EAGAIN) {
- gi->gl = NULL;
- return;
+ gl = rhashtable_walk_next(&gi->hti);
+ if (IS_ERR_OR_NULL(gl)) {
+ if (gl == ERR_PTR(-EAGAIN)) {
+ n = 1;
+ continue;
}
- n = 0;
- } else if (gi->sdp == gi->gl->gl_name.ln_sbd &&
- !__lockref_is_dead(&gi->gl->gl_lockref)) {
- if (!n--)
- break;
+ gl = NULL;
+ break;
+ }
+ if (gl->gl_name.ln_sbd != gi->sdp)
+ continue;
+ if (n <= 1) {
+ if (!lockref_get_not_dead(&gl->gl_lockref))
+ continue;
+ break;
+ } else {
+ if (__lockref_is_dead(&gl->gl_lockref))
+ continue;
+ n--;
}
- gi->gl = rhashtable_walk_next(&gi->hti);
}
+ gi->gl = gl;
}
static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos)
@@ -1988,7 +1997,6 @@ static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr)
{
struct gfs2_glock_iter *gi = seq->private;
- gi->gl = NULL;
rhashtable_walk_stop(&gi->hti);
}
@@ -2076,7 +2084,8 @@ static int gfs2_glocks_release(struct inode *inode, struct file *file)
struct seq_file *seq = file->private_data;
struct gfs2_glock_iter *gi = seq->private;
- gi->gl = NULL;
+ if (gi->gl)
+ gfs2_glock_put(gi->gl);
rhashtable_walk_exit(&gi->hti);
return seq_release_private(inode, file);
}
--
2.14.3
^ permalink raw reply related
* Re: [Patch net] llc: properly handle dev_queue_xmit() return value
From: Noam Rathaus @ 2018-03-29 12:11 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Cong Wang
In-Reply-To: <20180327.131302.1341878964762035147.davem@davemloft.net>
Hi,
Will you notify me when its been accepted? if not, how can I do this
checking myself to see if it was accepted?
On Tue, Mar 27, 2018 at 8:13 PM, David Miller <davem@davemloft.net> wrote:
> From: Noam Rathaus <noamr@beyondsecurity.com>
> Date: Tue, 27 Mar 2018 16:27:49 +0000
>
>> Guys please fill me in on the next step?
>>
>> If it’s applied it means it’s part of the official code of the kernel now?
>
> It means it is in my networking GIT tree and will make it's way to Linus
> in the not so distant future.
--
Thanks,
Noam Rathaus
Beyond Security
PGP Key ID: 7EF920D3C045D63F (Exp 2019-03)
^ 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