summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorCédric Le Goater2019-09-11 15:39:37 +0200
committerDavid Gibson2019-10-04 02:25:23 +0200
commit4c3539d491026a0cc68e3b886f16cb7f57efd46b (patch)
tree963d79521ceafe914aa8a57d74050359298f1495
parentspapr/irq: Introduce an ics_irq_free() helper (diff)
downloadqemu-4c3539d491026a0cc68e3b886f16cb7f57efd46b.tar.gz
qemu-4c3539d491026a0cc68e3b886f16cb7f57efd46b.tar.xz
qemu-4c3539d491026a0cc68e3b886f16cb7f57efd46b.zip
spapr/irq: Only claim VALID interrupts at the KVM level
A typical pseries VM with 16 vCPUs, one disk, one network adapater uses less than 100 interrupts but the whole IRQ number space of the QEMU machine is allocated at reset time and it is 8K wide. This is wasting a considerable amount of interrupt numbers in the global IRQ space which has 1M interrupts per socket on a POWER9. To optimise the HW resources, only request at the KVM level interrupts which have been claimed by the guest. This will help to increase the maximum number of VMs per system and also help supporting nested guests using the XIVE interrupt mode. Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-Id: <20190911133937.2716-3-clg@kaod.org> Signed-off-by: Greg Kurz <groug@kaod.org> Message-Id: <156942766014.1274533.10792048853177121231.stgit@bahia.lan> [dwg: Folded in fix up from Greg Kurz] Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
-rw-r--r--hw/intc/spapr_xive_kvm.c40
-rw-r--r--hw/intc/xics_kvm.c8
2 files changed, 45 insertions, 3 deletions
diff --git a/hw/intc/spapr_xive_kvm.c b/hw/intc/spapr_xive_kvm.c
index 17af4d19f5..2006f96aec 100644
--- a/hw/intc/spapr_xive_kvm.c
+++ b/hw/intc/spapr_xive_kvm.c
@@ -255,11 +255,16 @@ void kvmppc_xive_source_reset_one(XiveSource *xsrc, int srcno, Error **errp)
static void kvmppc_xive_source_reset(XiveSource *xsrc, Error **errp)
{
+ SpaprXive *xive = SPAPR_XIVE(xsrc->xive);
int i;
for (i = 0; i < xsrc->nr_irqs; i++) {
Error *local_err = NULL;
+ if (!xive_eas_is_valid(&xive->eat[i])) {
+ continue;
+ }
+
kvmppc_xive_source_reset_one(xsrc, i, &local_err);
if (local_err) {
error_propagate(errp, local_err);
@@ -328,11 +333,18 @@ uint64_t kvmppc_xive_esb_rw(XiveSource *xsrc, int srcno, uint32_t offset,
static void kvmppc_xive_source_get_state(XiveSource *xsrc)
{
+ SpaprXive *xive = SPAPR_XIVE(xsrc->xive);
int i;
for (i = 0; i < xsrc->nr_irqs; i++) {
+ uint8_t pq;
+
+ if (!xive_eas_is_valid(&xive->eat[i])) {
+ continue;
+ }
+
/* Perform a load without side effect to retrieve the PQ bits */
- uint8_t pq = xive_esb_read(xsrc, i, XIVE_ESB_GET);
+ pq = xive_esb_read(xsrc, i, XIVE_ESB_GET);
/* and save PQ locally */
xive_source_esb_set(xsrc, i, pq);
@@ -521,9 +533,14 @@ static void kvmppc_xive_change_state_handler(void *opaque, int running,
*/
if (running) {
for (i = 0; i < xsrc->nr_irqs; i++) {
- uint8_t pq = xive_source_esb_get(xsrc, i);
+ uint8_t pq;
uint8_t old_pq;
+ if (!xive_eas_is_valid(&xive->eat[i])) {
+ continue;
+ }
+
+ pq = xive_source_esb_get(xsrc, i);
old_pq = xive_esb_read(xsrc, i, XIVE_ESB_SET_PQ_00 + (pq << 8));
/*
@@ -545,7 +562,13 @@ static void kvmppc_xive_change_state_handler(void *opaque, int running,
* migration is in progress.
*/
for (i = 0; i < xsrc->nr_irqs; i++) {
- uint8_t pq = xive_esb_read(xsrc, i, XIVE_ESB_GET);
+ uint8_t pq;
+
+ if (!xive_eas_is_valid(&xive->eat[i])) {
+ continue;
+ }
+
+ pq = xive_esb_read(xsrc, i, XIVE_ESB_GET);
/*
* PQ is set to PENDING to possibly catch a triggered
@@ -655,6 +678,17 @@ int kvmppc_xive_post_load(SpaprXive *xive, int version_id)
continue;
}
+ /*
+ * We can only restore the source config if the source has been
+ * previously set in KVM. Since we don't do that for all interrupts
+ * at reset time anymore, let's do it now.
+ */
+ kvmppc_xive_source_reset_one(&xive->source, i, &local_err);
+ if (local_err) {
+ error_report_err(local_err);
+ return -1;
+ }
+
kvmppc_xive_set_source_config(xive, i, &xive->eat[i], &local_err);
if (local_err) {
error_report_err(local_err);
diff --git a/hw/intc/xics_kvm.c b/hw/intc/xics_kvm.c
index a4d2e876cc..ba90d6dc96 100644
--- a/hw/intc/xics_kvm.c
+++ b/hw/intc/xics_kvm.c
@@ -190,6 +190,10 @@ void ics_get_kvm_state(ICSState *ics)
for (i = 0; i < ics->nr_irqs; i++) {
ICSIRQState *irq = &ics->irqs[i];
+ if (ics_irq_free(ics, i)) {
+ continue;
+ }
+
kvm_device_access(kernel_xics_fd, KVM_DEV_XICS_GRP_SOURCES,
i + ics->offset, &state, false, &error_fatal);
@@ -301,6 +305,10 @@ int ics_set_kvm_state(ICSState *ics, Error **errp)
Error *local_err = NULL;
int ret;
+ if (ics_irq_free(ics, i)) {
+ continue;
+ }
+
ret = ics_set_kvm_state_one(ics, i, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);