Date: Mon, 30 May 2011 09:43:55 +0000 (UTC) From: Robert Watson <rwatson@FreeBSD.org> To: cvs-src-old@freebsd.org Subject: cvs commit: src/sys/contrib/pf/net pf.c src/sys/netinet in_pcb.c in_pcb.h ip_divert.c raw_ip.c siftr.c tcp_input.c tcp_subr.c tcp_syncache.c tcp_timer.c tcp_usrreq.c udp_usrreq.c src/sys/netinet/ipfw ip_fw2.c src/sys/netinet6 in6_pcb.c in6_pcb.h ... Message-ID: <201105300944.p4U9iUgC054716@repoman.freebsd.org>
next in thread | raw e-mail | index | archive | help
rwatson 2011-05-30 09:43:55 UTC
FreeBSD src repository
Modified files:
sys/contrib/pf/net pf.c
sys/netinet in_pcb.c in_pcb.h ip_divert.c raw_ip.c
siftr.c tcp_input.c tcp_subr.c
tcp_syncache.c tcp_timer.c tcp_usrreq.c
udp_usrreq.c
sys/netinet/ipfw ip_fw2.c
sys/netinet6 in6_pcb.c in6_pcb.h in6_src.c
udp6_usrreq.c
Log:
SVN rev 222488 on 2011-05-30 09:43:55Z by rwatson
Decompose the current single inpcbinfo lock into two locks:
- The existing ipi_lock continues to protect the global inpcb list and
inpcb counter. This lock is now relegated to a small number of
allocation and free operations, and occasional operations that walk
all connections (including, awkwardly, certain UDP multicast receive
operations -- something to revisit).
- A new ipi_hash_lock protects the two inpcbinfo hash tables for
looking up connections and bound sockets, manipulated using new
INP_HASH_*() macros. This lock, combined with inpcb locks, protects
the 4-tuple address space.
Unlike the current ipi_lock, ipi_hash_lock follows the individual inpcb
connection locks, so may be acquired while manipulating a connection on
which a lock is already held, avoiding the need to acquire the inpcbinfo
lock preemptively when a binding change might later be required. As a
result, however, lookup operations necessarily go through a reference
acquire while holding the lookup lock, later acquiring an inpcb lock --
if required.
A new function in_pcblookup() looks up connections, and accepts flags
indicating how to return the inpcb. Due to lock order changes, callers
no longer need acquire locks before performing a lookup: the lookup
routine will acquire the ipi_hash_lock as needed. In the future, it will
also be able to use alternative lookup and locking strategies
transparently to callers, such as pcbgroup lookup. New lookup flags are,
supplementing the existing INPLOOKUP_WILDCARD flag:
INPLOOKUP_RLOCKPCB - Acquire a read lock on the returned inpcb
INPLOOKUP_WLOCKPCB - Acquire a write lock on the returned inpcb
Callers must pass exactly one of these flags (for the time being).
Some notes:
- All protocols are updated to work within the new regime; especially,
TCP, UDPv4, and UDPv6. pcbinfo ipi_lock acquisitions are largely
eliminated, and global hash lock hold times are dramatically reduced
compared to previous locking.
- The TCP syncache still relies on the pcbinfo lock, something that we
may want to revisit.
- Support for reverting to the FreeBSD 7.x locking strategy in TCP input
is no longer available -- hash lookup locks are now held only very
briefly during inpcb lookup, rather than for potentially extended
periods. However, the pcbinfo ipi_lock will still be acquired if a
connection state might change such that a connection is added or
removed.
- Raw IP sockets continue to use the pcbinfo ipi_lock for protection,
due to maintaining their own hash tables.
- The interface in6_pcblookup_hash_locked() is maintained, which allows
callers to acquire hash locks and perform one or more lookups atomically
with 4-tuple allocation: this is required only for TCPv6, as there is no
in6_pcbconnect_setup(), which there should be.
- UDPv6 locking remains significantly more conservative than UDPv4
locking, which relates to source address selection. This needs
attention, as it likely significantly reduces parallelism in this code
for multithreaded socket use (such as in BIND).
- In the UDPv4 and UDPv6 multicast cases, we need to revisit locking
somewhat, as they relied on ipi_lock to stablise 4-tuple matches, which
is no longer sufficient. A second check once the inpcb lock is held
should do the trick, keeping the general case from requiring the inpcb
lock for every inpcb visited.
- This work reminds us that we need to revisit locking of the v4/v6 flags,
which may be accessed lock-free both before and after this change.
- Right now, a single lock name is used for the pcbhash lock -- this is
undesirable, and probably another argument is required to take care of
this (or a char array name field in the pcbinfo?).
This is not an MFC candidate for 8.x due to its impact on lookup and
locking semantics. It's possible some of these issues could be worked
around with compatibility wrappers, if necessary.
Reviewed by: bz
Sponsored by: Juniper Networks, Inc.
Revision Changes Path
1.74 +14 -17 src/sys/contrib/pf/net/pf.c
1.278 +90 -19 src/sys/netinet/in_pcb.c
1.149 +38 -12 src/sys/netinet/in_pcb.h
1.169 +3 -3 src/sys/netinet/ip_divert.c
1.54 +31 -19 src/sys/netinet/ipfw/ip_fw2.c
1.236 +10 -19 src/sys/netinet/raw_ip.c
1.15 +8 -14 src/sys/netinet/siftr.c
1.433 +100 -140 src/sys/netinet/tcp_input.c
1.379 +19 -31 src/sys/netinet/tcp_subr.c
1.188 +5 -0 src/sys/netinet/tcp_syncache.c
1.121 +1 -1 src/sys/netinet/tcp_timer.c
1.203 +51 -45 src/sys/netinet/tcp_usrreq.c
1.278 +69 -67 src/sys/netinet/udp_usrreq.c
1.125 +67 -11 src/sys/netinet6/in6_pcb.c
1.26 +7 -3 src/sys/netinet6/in6_pcb.h
1.84 +1 -1 src/sys/netinet6/in6_src.c
1.121 +44 -34 src/sys/netinet6/udp6_usrreq.c
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201105300944.p4U9iUgC054716>