/* * Copyright (C) 2016 Red Hat, Inc. * Author: Michael S. Tsirkin * This work is licensed under the terms of the GNU GPL, version 2. * * Common macros and functions for ring benchmarking. */ #ifndef MAIN_H #define MAIN_H #include extern bool do_exit; #if defined(__x86_64__) || defined(__i386__) #include "x86intrin.h" static inline void wait_cycles(unsigned long long cycles) { unsigned long long t; t = __rdtsc(); while (__rdtsc() - t < cycles) {} } #define VMEXIT_CYCLES 500 #define VMENTRY_CYCLES 500 #else static inline void wait_cycles(unsigned long long cycles) { _Exit(5); } #define VMEXIT_CYCLES 0 #define VMENTRY_CYCLES 0 #endif static inline void vmexit(void) { if (!do_exit) return; wait_cycles(VMEXIT_CYCLES); } static inline void vmentry(void) { if (!do_exit) return; wait_cycles(VMENTRY_CYCLES); } /* implemented by ring */ void alloc_ring(void); /* guest side */ int add_inbuf(unsigned, void *, void *); void *get_buf(unsigned *, void **); void disable_call(); bool used_empty(); bool enable_call(); void kick_available(); /* host side */ void disable_kick(); bool avail_empty(); bool enable_kick(); bool use_buf(unsigned *, void **); void call_used(); /* implemented by main */ extern bool do_sleep; void kick(void); void wait_for_kick(void); void call(void); void wait_for_call(void); extern unsigned ring_size; /* Compiler barrier - similar to what Linux uses */ #define barrier() asm volatile("" ::: "memory") /* Is there a portable way to do this? */ #if defined(__x86_64__) || defined(__i386__) #define cpu_relax() asm ("rep; nop" ::: "memory") #else #define cpu_relax() assert(0) #endif extern bool do_relax; static inline void busy_wait(void) { if (do_relax) cpu_relax(); else /* prevent compiler from removing busy loops */ barrier(); } /* * Not using __ATOMIC_SEQ_CST since gcc docs say they are only synchronized * with other __ATOMIC_SEQ_CST calls. */ #define smp_mb() __sync_synchronize() /* * This abuses the atomic builtins for thread fences, and * adds a compiler barrier. */ #define smp_release() do { \ barrier(); \ __atomic_thread_fence(__ATOMIC_RELEASE); \ } while (0) #define smp_acquire() do { \ __atomic_thread_fence(__ATOMIC_ACQUIRE); \ barrier(); \ } while (0) #endif msg
path: root/include/rdma
diff options
context:
space:
mode:
authorDavid Ahern <dsa@cumulusnetworks.com>2016-12-29 15:29:03 -0800
committerDavid S. Miller <davem@davemloft.net>2016-12-29 22:27:23 -0500
commitf5a0aab84b74de68523599817569c057c7ac1622 (patch)
tree321a7119a443d99853b4d3e747db583ad3a39912 /include/rdma
parent2344ef3c86a7fe41f97bf66c7936001b6132860b (diff)
net: ipv4: dst for local input routes should use l3mdev if relevant
IPv4 output routes already use l3mdev device instead of loopback for dst's if it is applicable. Change local input routes to do the same. This fixes icmp responses for unreachable UDP ports which are directed to the wrong table after commit 9d1a6c4ea43e4 because local_input routes use the loopback device. Moving from ingress device to loopback loses the L3 domain causing responses based on the dst to get to lost. Fixes: 9d1a6c4ea43e4 ("net: icmp_route_lookup should use rt dev to determine L3 domain") Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/rdma')