aboutsummaryrefslogtreecommitdiff
path: root/sys/sys/sockbuf.h
diff options
context:
space:
mode:
authorGleb Smirnoff <glebius@FreeBSD.org>2017-06-08 21:30:34 +0000
committerGleb Smirnoff <glebius@FreeBSD.org>2017-06-08 21:30:34 +0000
commit779f106aa169256b7010a1d8f963ff656b881e92 (patch)
tree01f96ac5827e2a95a385258086155b37b80ec6b9 /sys/sys/sockbuf.h
parent4623e047a7c87148916e11e6c7b80409f6e45519 (diff)
downloadsrc-779f106aa169256b7010a1d8f963ff656b881e92.tar.gz
src-779f106aa169256b7010a1d8f963ff656b881e92.zip
Listening sockets improvements.
o Separate fields of struct socket that belong to listening from fields that belong to normal dataflow, and unionize them. This shrinks the structure a bit. - Take out selinfo's from the socket buffers into the socket. The first reason is to support braindamaged scenario when a socket is added to kevent(2) and then listen(2) is cast on it. The second reason is that there is future plan to make socket buffers pluggable, so that for a dataflow socket a socket buffer can be changed, and in this case we also want to keep same selinfos through the lifetime of a socket. - Remove struct struct so_accf. Since now listening stuff no longer affects struct socket size, just move its fields into listening part of the union. - Provide sol_upcall field and enforce that so_upcall_set() may be called only on a dataflow socket, which has buffers, and for listening sockets provide solisten_upcall_set(). o Remove ACCEPT_LOCK() global. - Add a mutex to socket, to be used instead of socket buffer lock to lock fields of struct socket that don't belong to a socket buffer. - Allow to acquire two socket locks, but the first one must belong to a listening socket. - Make soref()/sorele() to use atomic(9). This allows in some situations to do soref() without owning socket lock. There is place for improvement here, it is possible to make sorele() also to lock optionally. - Most protocols aren't touched by this change, except UNIX local sockets. See below for more information. o Reduce copy-and-paste in kernel modules that accept connections from listening sockets: provide function solisten_dequeue(), and use it in the following modules: ctl(4), iscsi(4), ng_btsocket(4), ng_ksocket(4), infiniband, rpc. o UNIX local sockets. - Removal of ACCEPT_LOCK() global uncovered several races in the UNIX local sockets. Most races exist around spawning a new socket, when we are connecting to a local listening socket. To cover them, we need to hold locks on both PCBs when spawning a third one. This means holding them across sonewconn(). This creates a LOR between pcb locks and unp_list_lock. - To fix the new LOR, abandon the global unp_list_lock in favor of global unp_link_lock. Indeed, separating these two locks didn't provide us any extra parralelism in the UNIX sockets. - Now call into uipc_attach() may happen with unp_link_lock hold if, we are accepting, or without unp_link_lock in case if we are just creating a socket. - Another problem in UNIX sockets is that uipc_close() basicly did nothing for a listening socket. The vnode remained opened for connections. This is fixed by removing vnode in uipc_close(). Maybe the right way would be to do it for all sockets (not only listening), simply move the vnode teardown from uipc_detach() to uipc_close()? Sponsored by: Netflix Differential Revision: https://reviews.freebsd.org/D9770
Notes
Notes: svn path=/head/; revision=319722
Diffstat (limited to 'sys/sys/sockbuf.h')
-rw-r--r--sys/sys/sockbuf.h8
1 files changed, 4 insertions, 4 deletions
diff --git a/sys/sys/sockbuf.h b/sys/sys/sockbuf.h
index b94d4d14c88a..d22e3bce1645 100644
--- a/sys/sys/sockbuf.h
+++ b/sys/sys/sockbuf.h
@@ -32,7 +32,6 @@
*/
#ifndef _SYS_SOCKBUF_H_
#define _SYS_SOCKBUF_H_
-#include <sys/selinfo.h> /* for struct selinfo */
#include <sys/_lock.h>
#include <sys/_mutex.h>
#include <sys/_sx.h>
@@ -64,6 +63,7 @@ struct mbuf;
struct sockaddr;
struct socket;
struct thread;
+struct selinfo;
struct xsockbuf {
u_int sb_cc;
@@ -84,9 +84,9 @@ struct xsockbuf {
* (a) locked by SOCKBUF_LOCK().
*/
struct sockbuf {
- struct selinfo sb_sel; /* process selecting read/write */
- struct mtx sb_mtx; /* sockbuf lock */
- struct sx sb_sx; /* prevent I/O interlacing */
+ struct mtx sb_mtx; /* sockbuf lock */
+ struct sx sb_sx; /* prevent I/O interlacing */
+ struct selinfo *sb_sel; /* process selecting read/write */
short sb_state; /* (a) socket state on sockbuf */
#define sb_startzero sb_mb
struct mbuf *sb_mb; /* (a) the mbuf chain */