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>

arch/powerpc/include/asm/hvcall.h

@@ -280,7 +280,18 @@
 #define H_RESIZE_HPT_COMMIT	0x370
 #define H_REGISTER_PROC_TBL	0x37C
 #define H_SIGNAL_SYS_RESET	0x380
-#define MAX_HCALL_OPCODE	H_SIGNAL_SYS_RESET
+#define H_INT_GET_SOURCE_INFO   0x3A8
+#define H_INT_SET_SOURCE_CONFIG 0x3AC
+#define H_INT_GET_SOURCE_CONFIG 0x3B0
+#define H_INT_GET_QUEUE_INFO    0x3B4
+#define H_INT_SET_QUEUE_CONFIG  0x3B8
+#define H_INT_GET_QUEUE_CONFIG  0x3BC
+#define H_INT_SET_OS_REPORTING_LINE 0x3C0
+#define H_INT_GET_OS_REPORTING_LINE 0x3C4
+#define H_INT_ESB               0x3C8
+#define H_INT_SYNC              0x3CC
+#define H_INT_RESET             0x3D0
+#define MAX_HCALL_OPCODE	H_INT_RESET
 
 /* H_VIOCTL functions */
 #define H_GET_VIOA_DUMP_SIZE	0x01

arch/powerpc/include/asm/xive.h

@@ -110,11 +110,13 @@ extern bool __xive_enabled;
 
 static inline bool xive_enabled(void) { return __xive_enabled; }
 
+extern bool xive_spapr_init(void);
 extern bool xive_native_init(void);
 extern void xive_smp_probe(void);
 extern int  xive_smp_prepare_cpu(unsigned int cpu);
 extern void xive_smp_setup_cpu(void);
 extern void xive_smp_disable_cpu(void);
+extern void xive_teardown_cpu(void);
 extern void xive_kexec_teardown_cpu(int secondary);
 extern void xive_shutdown(void);
 extern void xive_flush_interrupt(void);
@@ -147,6 +149,7 @@ extern int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id)
 
 static inline bool xive_enabled(void) { return false; }
 
+static inline bool xive_spapr_init(void) { return false; }
 static inline bool xive_native_init(void) { return false; }
 static inline void xive_smp_probe(void) { }
 extern inline int  xive_smp_prepare_cpu(unsigned int cpu) { return -EINVAL; }

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

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;
 }
 

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);
 }

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)

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 @@ static inline int smp_startup_cpu(unsigned int lcpu)
 
 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,

arch/powerpc/sysdev/xive/Kconfig

@@ -9,3 +9,8 @@ config PPC_XIVE_NATIVE
 	default n
 	select PPC_XIVE
 	depends on PPC_POWERNV
+
+config PPC_XIVE_SPAPR
+	bool
+	default n
+	select PPC_XIVE

arch/powerpc/sysdev/xive/Makefile

@@ -2,3 +2,4 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 obj-y				+= common.o
 obj-$(CONFIG_PPC_XIVE_NATIVE)	+= native.o
+obj-$(CONFIG_PPC_XIVE_SPAPR)	+= spapr.o

arch/powerpc/sysdev/xive/common.c

@@ -1372,6 +1372,19 @@ void xive_flush_interrupt(void)
 
 #endif /* CONFIG_SMP */
 
+void xive_teardown_cpu(void)
+{
+	struct xive_cpu *xc = __this_cpu_read(xive_cpu);
+	unsigned int cpu = smp_processor_id();
+
+	/* Set CPPR to 0 to disable flow of interrupts */
+	xc->cppr = 0;
+	out_8(xive_tima + xive_tima_offset + TM_CPPR, 0);
+
+	if (xive_ops->teardown_cpu)
+		xive_ops->teardown_cpu(cpu, xc);
+}
+
 void xive_kexec_teardown_cpu(int secondary)
 {
 	struct xive_cpu *xc = __this_cpu_read(xive_cpu);