This handler is in charge of stabilizing the flow of event notifications in the XIVE controller before migrating a guest. This is a requirement before transferring the guest EQ pages to a destination.
When the VM is stopped, the handler masks the sources (PQ=01) to stop the flow of events and saves their previous state. The XIVE controller is then synced through KVM to flush any in-flight event notification and to stabilize the EQs. At this stage, the EQ pages are marked dirty to make sure the EQ pages are transferred if a migration sequence is in progress. The previous configuration of the sources is restored when the VM resumes, after a migration or a stop. Signed-off-by: Cédric Le Goater <c...@kaod.org> --- include/hw/ppc/spapr_xive.h | 1 + hw/intc/spapr_xive_kvm.c | 77 ++++++++++++++++++++++++++++++++++++- 2 files changed, 77 insertions(+), 1 deletion(-) diff --git a/include/hw/ppc/spapr_xive.h b/include/hw/ppc/spapr_xive.h index ebd65e7fe36b..298d204d54ef 100644 --- a/include/hw/ppc/spapr_xive.h +++ b/include/hw/ppc/spapr_xive.h @@ -42,6 +42,7 @@ typedef struct sPAPRXive { /* KVM support */ int fd; void *tm_mmap; + VMChangeStateEntry *change; } sPAPRXive; /* diff --git a/hw/intc/spapr_xive_kvm.c b/hw/intc/spapr_xive_kvm.c index 4b1ffb9835f9..44d80175b1b5 100644 --- a/hw/intc/spapr_xive_kvm.c +++ b/hw/intc/spapr_xive_kvm.c @@ -419,9 +419,81 @@ static void kvmppc_xive_get_queues(sPAPRXive *xive, Error **errp) } } +/* + * The primary goal of the XIVE VM change handler is to mark the EQ + * pages dirty when all XIVE event notifications have stopped. + * + * Whenever the VM is stopped, the VM change handler masks the sources + * (PQ=01) to stop the flow of events and saves the previous state in + * anticipation of a migration. The XIVE controller is then synced + * through KVM to flush any in-flight event notification and stabilize + * the EQs. + * + * At this stage, we can mark the EQ page dirty and let a migration + * sequence transfer the EQ pages to the destination, which is done + * just after the stop state. + * + * The previous configuration of the sources is restored when the VM + * runs again. + */ +static void kvmppc_xive_change_state_handler(void *opaque, int running, + RunState state) +{ + sPAPRXive *xive = opaque; + XiveSource *xsrc = &xive->source; + Error *local_err = NULL; + int i; + + /* + * Restore the sources to their initial state. This is called when + * the VM resumes after a stop or a migration. + */ + if (running) { + for (i = 0; i < xsrc->nr_irqs; i++) { + uint8_t pq = xive_source_esb_get(xsrc, i); + if (xive_esb_read(xsrc, i, XIVE_ESB_SET_PQ_00 + (pq << 8)) != 0x1) { + error_report("XIVE: IRQ %d has an invalid state", i); + } + } + + return; + } + + /* + * Mask the sources, to stop the flow of event notifications, and + * save the PQs locally in the XiveSource object. The XiveSource + * state will be collected later on by its vmstate handler if a + * migration is in progress. + */ + for (i = 0; i < xsrc->nr_irqs; i++) { + uint8_t pq = xive_esb_read(xsrc, i, XIVE_ESB_SET_PQ_01); + xive_source_esb_set(xsrc, i, pq); + } + + /* + * Sync the XIVE controller in KVM, to flush in-flight event + * notification that should be enqueued in the EQs and mark the + * XIVE EQ pages dirty to collect all updates. + */ + kvm_device_access(xive->fd, KVM_DEV_XIVE_GRP_CTRL, + KVM_DEV_XIVE_EQ_SYNC, NULL, true, &local_err); + if (local_err) { + error_report_err(local_err); + return; + } +} + void kvmppc_xive_synchronize_state(sPAPRXive *xive, Error **errp) { - kvmppc_xive_source_get_state(&xive->source); + /* + * When the VM is stopped, the sources are masked and the previous + * state is saved in anticipation of a migration. We should not + * synchronize the source state in that case else we will override + * the saved state. + */ + if (runstate_is_running()) { + kvmppc_xive_source_get_state(&xive->source); + } /* EAT: there is no extra state to query from KVM */ @@ -501,6 +573,9 @@ void kvmppc_xive_connect(sPAPRXive *xive, Error **errp) "xive.tima", tima_len, xive->tm_mmap); sysbus_init_mmio(SYS_BUS_DEVICE(xive), &xive->tm_mmio); + xive->change = qemu_add_vm_change_state_handler( + kvmppc_xive_change_state_handler, xive); + kvm_kernel_irqchip = true; kvm_msi_via_irqfd_allowed = true; kvm_gsi_direct_mapping = true; -- 2.20.1