pseries: Use Book3S-HV TCE acceleration capabilities
The pseries machine of qemu implements the TCE mechanism used as a
virtual IOMMU for the PAPR defined virtual IO devices. Because the
PAPR spec only defines a small DMA address space, the guest VIO
drivers need to update TCE mappings very frequently - the virtual
network device is particularly bad. This means many slow exits to
qemu to emulate the H_PUT_TCE hypercall.
Sufficiently recent kernels allow this to be mitigated by implementing
H_PUT_TCE in the host kernel. To make use of this, however, qemu
needs to initialize the necessary TCE tables, and map them into itself
so that the VIO device implementations can retrieve the mappings when
they access guest memory (which is treated as a virtual DMA
operation).
This patch adds the necessary calls to use the KVM TCE acceleration.
If the kernel does not support acceleration, or there is some other
error creating the accelerated TCE table, then it will still fall back
to full userspace TCE implementation.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Alexander Graf <agraf@suse.de>
diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
index fd17d23..06cad41 100644
--- a/target-ppc/kvm.c
+++ b/target-ppc/kvm.c
@@ -28,6 +28,7 @@
#include "kvm_ppc.h"
#include "cpu.h"
#include "device_tree.h"
+#include "hw/sysbus.h"
#include "hw/spapr.h"
#include "hw/sysbus.h"
@@ -56,6 +57,7 @@
static int cap_booke_sregs;
static int cap_ppc_smt;
static int cap_ppc_rma;
+static int cap_spapr_tce;
/* XXX We have a race condition where we actually have a level triggered
* interrupt, but the infrastructure can't expose that yet, so the guest
@@ -81,6 +83,7 @@
cap_booke_sregs = kvm_check_extension(s, KVM_CAP_PPC_BOOKE_SREGS);
cap_ppc_smt = kvm_check_extension(s, KVM_CAP_PPC_SMT);
cap_ppc_rma = kvm_check_extension(s, KVM_CAP_PPC_RMA);
+ cap_spapr_tce = kvm_check_extension(s, KVM_CAP_SPAPR_TCE);
if (!cap_interrupt_level) {
fprintf(stderr, "KVM: Couldn't find level irq capability. Expect the "
@@ -802,6 +805,57 @@
return size;
}
+void *kvmppc_create_spapr_tce(uint32_t liobn, uint32_t window_size, int *pfd)
+{
+ struct kvm_create_spapr_tce args = {
+ .liobn = liobn,
+ .window_size = window_size,
+ };
+ long len;
+ int fd;
+ void *table;
+
+ if (!cap_spapr_tce) {
+ return NULL;
+ }
+
+ fd = kvm_vm_ioctl(kvm_state, KVM_CREATE_SPAPR_TCE, &args);
+ if (fd < 0) {
+ return NULL;
+ }
+
+ len = (window_size / SPAPR_VIO_TCE_PAGE_SIZE) * sizeof(VIOsPAPR_RTCE);
+ /* FIXME: round this up to page size */
+
+ table = mmap(NULL, len, PROT_READ, MAP_SHARED, fd, 0);
+ if (table == MAP_FAILED) {
+ close(fd);
+ return NULL;
+ }
+
+ *pfd = fd;
+ return table;
+}
+
+int kvmppc_remove_spapr_tce(void *table, int fd, uint32_t window_size)
+{
+ long len;
+
+ if (fd < 0) {
+ return -1;
+ }
+
+ len = (window_size / SPAPR_VIO_TCE_PAGE_SIZE)*sizeof(VIOsPAPR_RTCE);
+ if ((munmap(table, len) < 0) ||
+ (close(fd) < 0)) {
+ fprintf(stderr, "KVM: Unexpected error removing KVM SPAPR TCE "
+ "table: %s", strerror(errno));
+ /* Leak the table */
+ }
+
+ return 0;
+}
+
bool kvm_arch_stop_on_emulation_error(CPUState *env)
{
return true;
