s390x/kvm: make setting of in-kernel irq routes more efficient

qemu with hax to log dma reads & writes jcs.org/2018/11/12/vfio

When we add new adapter routes we call kvm_irqchip_add_route() for every
virtqueue and in the same step also do the KVM_SET_GSI_ROUTING ioctl.

This is unnecessary costly as the interface allows us to set multiple
routes in one go. Let's first add all routes to the table stored in the
global kvm_state and then do the ioctl to commit the routes to the
in-kernel irqchip.

This saves us several ioctls to the kernel where for each call a list
is reallocated and populated.

Signed-off-by: Jens Freimann <jfrei@linux.vnet.ibm.com>
Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>

authored by

Jens Freimann and committed by

Cornelia Huck 10 years ago c0194a00 9f70b85c

+2 -1

2 changed files

expand all

intc

s390_flic_kvm.c

kvm-all.c

hw/intc/s390_flic_kvm.c

··· 228 228 routes->gsi[i] = ret; 229 229 routes->adapter.ind_offset++; 230 230 } 231 + kvm_irqchip_commit_routes(kvm_state); 232 + 231 233 /* Restore passed-in structure to original state. */ 232 234 routes->adapter.ind_offset = ind_offset; 233 235 return 0;

-1

kvm-all.c

··· 1293 1293 kroute.u.adapter.adapter_id = adapter->adapter_id; 1294 1294 1295 1295 kvm_add_routing_entry(s, &kroute); 1296 - kvm_irqchip_commit_routes(s); 1297 1296 1298 1297 return virq; 1299 1298 }