powerpc/xive: guest exploitation of the XIVE interrupt controller

This is the framework for using XIVE in a PowerVM guest. The support
is very similar to the native one in a much simpler form.

Each source is associated with an Event State Buffer (ESB). This is a
two bit state machine which is used to trigger events. The bits are
named "P" (pending) and "Q" (queued) and can be controlled by MMIO.
The Guest OS registers event (or notifications) queues on which the HW
will post event data for a target to notify.

Instead of OPAL calls, a set of Hypervisors call are used to configure
the interrupt sources and the event/notification queues of the guest:

 - H_INT_GET_SOURCE_INFO

   used to obtain the address of the MMIO page of the Event State
   Buffer (PQ bits) entry associated with the source.

 - H_INT_SET_SOURCE_CONFIG

   assigns a source to a "target".

 - H_INT_GET_SOURCE_CONFIG

   determines to which "target" and "priority" is assigned to a source

 - H_INT_GET_QUEUE_INFO

   returns the address of the notification management page associated
   with the specified "target" and "priority".

 - H_INT_SET_QUEUE_CONFIG

   sets or resets the event queue for a given "target" and "priority".
   It is also used to set the notification config associated with the
   queue, only unconditional notification for the moment.  Reset is
   performed with a queue size of 0 and queueing is disabled in that
   case.

 - H_INT_GET_QUEUE_CONFIG

   returns the queue settings for a given "target" and "priority".

 - H_INT_RESET

   resets all of the partition's interrupt exploitation structures to
   their initial state, losing all configuration set via the hcalls
   H_INT_SET_SOURCE_CONFIG and H_INT_SET_QUEUE_CONFIG.

 - H_INT_SYNC

   issue a synchronisation on a source to make sure sure all
   notifications have reached their queue.

As for XICS, the XIVE interface for the guest is described in the
device tree under the "interrupt-controller" node. A couple of new
properties are specific to XIVE :

 - "reg"

   contains the base address and size of the thread interrupt
   managnement areas (TIMA), also called rings, for the User level and
   for the Guest OS level. Only the Guest OS level is taken into
   account today.

 - "ibm,xive-eq-sizes"

   the size of the event queues. One cell per size supported, contains
   log2 of size, in ascending order.

 - "ibm,xive-lisn-ranges"

   the interrupt numbers ranges assigned to the guest. These are
   allocated using a simple bitmap.

and also :

 - "/ibm,plat-res-int-priorities"

   contains a list of priorities that the hypervisor has reserved for
   its own use.

Tested with a QEMU XIVE model for pseries and with the Power hypervisor.

Signed-off-by: Cédric Le Goater <clg@kaod.org>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

5 files changed, 46 insertions, 7 deletions

diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 3a6dfd14f64b..71dd69d9ec64 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -7,6 +7,7 @@ config PPC_PSERIES
 	select PCI
 	select PCI_MSI
 	select PPC_XICS
+	select PPC_XIVE_SPAPR
 	select PPC_ICP_NATIVE
 	select PPC_ICP_HV
 	select PPC_ICS_RTAS
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index b357f1ae0b0a..fc0d8f97c03a 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -34,6 +34,7 @@
 #include <asm/machdep.h>
 #include <asm/vdso_datapage.h>
 #include <asm/xics.h>
+#include <asm/xive.h>
 #include <asm/plpar_wrappers.h>
 
 #include "pseries.h"
@@ -109,7 +110,10 @@ static void pseries_mach_cpu_die(void)
 
 	local_irq_disable();
 	idle_task_exit();
-	xics_teardown_cpu();
+	if (xive_enabled())
+		xive_teardown_cpu();
+	else
+		xics_teardown_cpu();
 
 	if (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) {
 		set_cpu_current_state(cpu, CPU_STATE_INACTIVE);
@@ -174,7 +178,10 @@ static int pseries_cpu_disable(void)
 		boot_cpuid = cpumask_any(cpu_online_mask);
 
 	/* FIXME: abstract this to not be platform specific later on */
-	xics_migrate_irqs_away();
+	if (xive_enabled())
+		xive_smp_disable_cpu();
+	else
+		xics_migrate_irqs_away();
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c
index 6681ac97fb18..eeb13429d685 100644
--- a/arch/powerpc/platforms/pseries/kexec.c
+++ b/arch/powerpc/platforms/pseries/kexec.c
@@ -15,6 +15,7 @@
 #include <asm/firmware.h>
 #include <asm/kexec.h>
 #include <asm/xics.h>
+#include <asm/xive.h>
 #include <asm/smp.h>
 #include <asm/plpar_wrappers.h>
 
@@ -51,5 +52,8 @@ void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
 		}
 	}
 
-	xics_kexec_teardown_cpu(secondary);
+	if (xive_enabled())
+		xive_kexec_teardown_cpu(secondary);
+	else
+		xics_kexec_teardown_cpu(secondary);
 }
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index b5b650910cf5..5f1beb8367ac 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -57,6 +57,7 @@
 #include <asm/nvram.h>
 #include <asm/pmc.h>
 #include <asm/xics.h>
+#include <asm/xive.h>
 #include <asm/ppc-pci.h>
 #include <asm/i8259.h>
 #include <asm/udbg.h>
@@ -176,8 +177,11 @@ static void __init pseries_setup_i8259_cascade(void)
 
 static void __init pseries_init_irq(void)
 {
-	xics_init();
-	pseries_setup_i8259_cascade();
+	/* Try using a XIVE if available, otherwise use a XICS */
+	if (!xive_spapr_init()) {
+		xics_init();
+		pseries_setup_i8259_cascade();
+	}
 }
 
 static void pseries_lpar_enable_pmcs(void)
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 24785f63fb40..2e184829e5d4 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -41,6 +41,7 @@
 #include <asm/vdso_datapage.h>
 #include <asm/cputhreads.h>
 #include <asm/xics.h>
+#include <asm/xive.h>
 #include <asm/dbell.h>
 #include <asm/plpar_wrappers.h>
 #include <asm/code-patching.h>
@@ -136,7 +137,9 @@ out:
 
 static void smp_setup_cpu(int cpu)
 {
-	if (cpu != boot_cpuid)
+	if (xive_enabled())
+		xive_smp_setup_cpu();
+	else if (cpu != boot_cpuid)
 		xics_setup_cpu();
 
 	if (firmware_has_feature(FW_FEATURE_SPLPAR))
@@ -181,6 +184,13 @@ static int smp_pSeries_kick_cpu(int nr)
 	return 0;
 }
 
+static int pseries_smp_prepare_cpu(int cpu)
+{
+	if (xive_enabled())
+		return xive_smp_prepare_cpu(cpu);
+	return 0;
+}
+
 static void smp_pseries_cause_ipi(int cpu)
 {
 	/* POWER9 should not use this handler */
@@ -211,7 +221,7 @@ static int pseries_cause_nmi_ipi(int cpu)
 	return 0;
 }
 
-static __init void pSeries_smp_probe(void)
+static __init void pSeries_smp_probe_xics(void)
 {
 	xics_smp_probe();
 
@@ -221,11 +231,24 @@ static __init void pSeries_smp_probe(void)
 		smp_ops->cause_ipi = icp_ops->cause_ipi;
 }
 
+static __init void pSeries_smp_probe(void)
+{
+	if (xive_enabled())
+		/*
+		 * Don't use P9 doorbells when XIVE is enabled. IPIs
+		 * using MMIOs should be faster
+		 */
+		xive_smp_probe();
+	else
+		pSeries_smp_probe_xics();
+}
+
 static struct smp_ops_t pseries_smp_ops = {
 	.message_pass	= NULL,	/* Use smp_muxed_ipi_message_pass */
 	.cause_ipi	= NULL,	/* Filled at runtime by pSeries_smp_probe() */
 	.cause_nmi_ipi	= pseries_cause_nmi_ipi,
 	.probe		= pSeries_smp_probe,
+	.prepare_cpu	= pseries_smp_prepare_cpu,
 	.kick_cpu	= smp_pSeries_kick_cpu,
 	.setup_cpu	= smp_setup_cpu,
 	.cpu_bootable	= smp_generic_cpu_bootable,