[Devel] [PATCH RHEL COMMIT] ms/sock: allow reading and changing sk_userlocks with setsockopt

Konstantin Khorenko khorenko at virtuozzo.com
Tue Oct 12 16:18:24 MSK 2021


The commit is pushed to "branch-rh9-5.14.vz9.1.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after ark-5.14
------>
commit a9640b425220cc22a25ea88e5c16e26f53894f89
Author: Pavel Tikhomirov <ptikhomirov at virtuozzo.com>
Date:   Tue Oct 12 16:18:23 2021 +0300

    ms/sock: allow reading and changing sk_userlocks with setsockopt
    
    SOCK_SNDBUF_LOCK and SOCK_RCVBUF_LOCK flags disable automatic socket
    buffers adjustment done by kernel (see tcp_fixup_rcvbuf() and
    tcp_sndbuf_expand()). If we've just created a new socket this adjustment
    is enabled on it, but if one changes the socket buffer size by
    setsockopt(SO_{SND,RCV}BUF*) it becomes disabled.
    
    CRIU needs to call setsockopt(SO_{SND,RCV}BUF*) on each socket on
    restore as it first needs to increase buffer sizes for packet queues
    restore and second it needs to restore back original buffer sizes. So
    after CRIU restore all sockets become non-auto-adjustable, which can
    decrease network performance of restored applications significantly.
    
    CRIU need to be able to restore sockets with enabled/disabled adjustment
    to the same state it was before dump, so let's add special setsockopt
    for it.
    
    Let's also export SOCK_SNDBUF_LOCK and SOCK_RCVBUF_LOCK flags to uAPI so
    that using these interface one can reenable automatic socket buffer
    adjustment on their sockets.
    
    Signed-off-by: Pavel Tikhomirov <ptikhomirov at virtuozzo.com>
    
    Reviewed-by: Eric Dumazet <edumazet at google.com>
    Signed-off-by: David S. Miller <davem at davemloft.net>
    
    https://jira.sw.ru/browse/PSBM-131580
    
    (cherry-picked from net-next commit 04190bf8944d ("sock: allow reading
    and changing sk_userlocks with setsockopt")
    Reviewed-by: Alexander Mikhalitsyn <alexander.mikhalitsyn at virtuozzo.com>
    Signed-off-by: Pavel Tikhomirov <ptikhomirov at virtuozzo.com>
    
    Signed-off-by: Cyrill Gorcunov <gorcunov at virtuozzo.com>
---
 arch/alpha/include/uapi/asm/socket.h  |  2 ++
 arch/mips/include/uapi/asm/socket.h   |  2 ++
 arch/parisc/include/uapi/asm/socket.h |  2 ++
 arch/sparc/include/uapi/asm/socket.h  |  2 ++
 include/net/sock.h                    |  3 +--
 include/uapi/asm-generic/socket.h     |  2 ++
 include/uapi/linux/socket.h           |  5 +++++
 net/core/sock.c                       | 13 +++++++++++++
 8 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 6b3daba60987..1dd9baf4a6c2 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -129,6 +129,8 @@
 
 #define SO_NETNS_COOKIE		71
 
+#define SO_BUF_LOCK		72
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index cdf404a831b2..1eaf6a1ca561 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -140,6 +140,8 @@
 
 #define SO_NETNS_COOKIE		71
 
+#define SO_BUF_LOCK		72
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 5b5351cdcb33..8baaad52d799 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -121,6 +121,8 @@
 
 #define SO_NETNS_COOKIE		0x4045
 
+#define SO_BUF_LOCK		0x4046
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 92675dc380fa..e80ee8641ac3 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -122,6 +122,8 @@
 
 #define SO_NETNS_COOKIE          0x0050
 
+#define SO_BUF_LOCK              0x0051
+
 #if !defined(__KERNEL__)
 
 
diff --git a/include/net/sock.h b/include/net/sock.h
index eebc2a671f62..814e7d768712 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -68,6 +68,7 @@
 #include <net/tcp_states.h>
 #include <linux/net_tstamp.h>
 #include <net/l3mdev.h>
+#include <uapi/linux/socket.h>
 
 /*
  * This structure really needs to be cleaned up.
@@ -1438,8 +1439,6 @@ static inline int __sk_prot_rehash(struct sock *sk)
 #define RCV_SHUTDOWN	1
 #define SEND_SHUTDOWN	2
 
-#define SOCK_SNDBUF_LOCK	1
-#define SOCK_RCVBUF_LOCK	2
 #define SOCK_BINDADDR_LOCK	4
 #define SOCK_BINDPORT_LOCK	8
 
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index d588c244ec2f..1f0a2b4864e4 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -124,6 +124,8 @@
 
 #define SO_NETNS_COOKIE		71
 
+#define SO_BUF_LOCK		72
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h
index c3409c8ec0dd..eb0a9a5b6e71 100644
--- a/include/uapi/linux/socket.h
+++ b/include/uapi/linux/socket.h
@@ -26,4 +26,9 @@ struct __kernel_sockaddr_storage {
 	};
 };
 
+#define SOCK_SNDBUF_LOCK	1
+#define SOCK_RCVBUF_LOCK	2
+
+#define SOCK_BUF_LOCK_MASK (SOCK_SNDBUF_LOCK | SOCK_RCVBUF_LOCK)
+
 #endif /* _UAPI_LINUX_SOCKET_H */
diff --git a/net/core/sock.c b/net/core/sock.c
index ae93a46b2772..ff81b59dcb47 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1367,6 +1367,15 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 		ret = sock_bindtoindex_locked(sk, val);
 		break;
 
+	case SO_BUF_LOCK:
+		if (val & ~SOCK_BUF_LOCK_MASK) {
+			ret = -EINVAL;
+			break;
+		}
+		sk->sk_userlocks = val | (sk->sk_userlocks &
+					  ~SOCK_BUF_LOCK_MASK);
+		break;
+
 	default:
 		ret = -ENOPROTOOPT;
 		break;
@@ -1729,6 +1738,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val64 = sock_net(sk)->net_cookie;
 		break;
 
+	case SO_BUF_LOCK:
+		v.val = sk->sk_userlocks & SOCK_BUF_LOCK_MASK;
+		break;
+
 	default:
 		/* We implement the SO_SNDLOWAT etc to not be settable
 		 * (1003.1g 7).


More information about the Devel mailing list