Implement the PAPR (pSeries) virtualized interrupt controller (xics)

PAPR defines an interrupt control architecture which is logically divided
into ICS (Interrupt Control Presentation, each unit is responsible for
presenting interrupts to a particular "interrupt server", i.e. CPU) and
ICS (Interrupt Control Source, each unit responsible for one or more
hardware interrupts as numbered globally across the system).  All PAPR
virtual IO devices expect to deliver interrupts via this mechanism.  In
Linux, this interrupt controller system is handled by the "xics" driver.

On pSeries systems, access to the interrupt controller is virtualized via
hypercalls and RTAS methods.  However, the virtualized interface is very
similar to the underlying interrupt controller hardware, and similar PICs
exist un-virtualized in some other systems.

This patch implements both the ICP and ICS sides of the PAPR interrupt
controller.  For now, only the hypercall virtualized interface is provided,
however it would be relatively straightforward to graft an emulated
register interface onto the underlying interrupt logic if we want to add
a machine with a hardware ICS/ICP system in the future.

There are some limitations in this implementation: it is assumed for now
that only one instance of the ICS exists, although a full xics system can
have several, each responsible for a different group of hardware irqs.
ICP/ICS can handle both level-sensitve (LSI) and message signalled (MSI)
interrupt inputs.  For now, this implementation supports only MSI
interrupts, since that is used by PAPR virtual IO devices.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>

4 files changed, 554 insertions, 0 deletions

diff --git a/hw/spapr.c b/hw/spapr.c
index 6c64de82de..b5aefd72c3 100644
--- a/hw/spapr.c
+++ b/hw/spapr.c
@@ -34,6 +34,7 @@
 
 #include "hw/spapr.h"
 #include "hw/spapr_vio.h"
+#include "hw/xics.h"
 
 #include <libfdt.h>
 
@@ -45,6 +46,7 @@
 #define TIMEBASE_FREQ           512000000ULL
 
 #define MAX_CPUS                32
+#define XICS_IRQS		1024
 
 sPAPREnvironment *spapr;
 
@@ -64,6 +66,7 @@ static void *spapr_create_fdt(int *fdt_size, ram_addr_t ramsize,
     uint32_t end_prop = cpu_to_be32(initrd_base + initrd_size);
     uint32_t pft_size_prop[] = {0, cpu_to_be32(hash_shift)};
     char hypertas_prop[] = "hcall-pft\0hcall-term\0hcall-dabr";
+    uint32_t interrupt_server_ranges_prop[] = {0, cpu_to_be32(smp_cpus)};
     int i;
     char *modelname;
     int ret;
@@ -125,6 +128,7 @@ static void *spapr_create_fdt(int *fdt_size, ram_addr_t ramsize,
 
     for (i = 0; i < smp_cpus; i++) {
         CPUState *env = envs[i];
+        uint32_t gserver_prop[] = {cpu_to_be32(i), 0}; /* HACK! */
         char *nodename;
         uint32_t segs[] = {cpu_to_be32(28), cpu_to_be32(40),
                            0xffffffff, 0xffffffff};
@@ -155,6 +159,9 @@ static void *spapr_create_fdt(int *fdt_size, ram_addr_t ramsize,
                            pft_size_prop, sizeof(pft_size_prop))));
         _FDT((fdt_property_string(fdt, "status", "okay")));
         _FDT((fdt_property(fdt, "64-bit", NULL, 0)));
+        _FDT((fdt_property_cell(fdt, "ibm,ppc-interrupt-server#s", i)));
+        _FDT((fdt_property(fdt, "ibm,ppc-interrupt-gserver#s",
+                           gserver_prop, sizeof(gserver_prop))));
 
         if (envs[i]->mmu_model & POWERPC_MMU_1TSEG) {
             _FDT((fdt_property(fdt, "ibm,processor-segment-sizes",
@@ -176,6 +183,20 @@ static void *spapr_create_fdt(int *fdt_size, ram_addr_t ramsize,
 
     _FDT((fdt_end_node(fdt)));
 
+    /* interrupt controller */
+    _FDT((fdt_begin_node(fdt, "interrupt-controller@0")));
+
+    _FDT((fdt_property_string(fdt, "device_type",
+                              "PowerPC-External-Interrupt-Presentation")));
+    _FDT((fdt_property_string(fdt, "compatible", "IBM,ppc-xicp")));
+    _FDT((fdt_property_cell(fdt, "reg", 0)));
+    _FDT((fdt_property(fdt, "interrupt-controller", NULL, 0)));
+    _FDT((fdt_property(fdt, "ibm,interrupt-server-ranges",
+                       interrupt_server_ranges_prop,
+                       sizeof(interrupt_server_ranges_prop))));
+
+    _FDT((fdt_end_node(fdt)));
+
     /* vdevice */
     _FDT((fdt_begin_node(fdt, "vdevice")));
 
@@ -183,6 +204,8 @@ static void *spapr_create_fdt(int *fdt_size, ram_addr_t ramsize,
     _FDT((fdt_property_string(fdt, "compatible", "IBM,vdevice")));
     _FDT((fdt_property_cell(fdt, "#address-cells", 0x1)));
     _FDT((fdt_property_cell(fdt, "#size-cells", 0x0)));
+    _FDT((fdt_property_cell(fdt, "#interrupt-cells", 0x2)));
+    _FDT((fdt_property(fdt, "interrupt-controller", NULL, 0)));
 
     _FDT((fdt_end_node(fdt)));
 
@@ -296,6 +319,10 @@ static void ppc_spapr_init(ram_addr_t ram_size,
     }
     qemu_free(filename);
 
+    /* Set up Interrupt Controller */
+    spapr->icp = xics_system_init(smp_cpus, envs, XICS_IRQS);
+
+    /* Set up VIO bus */
     spapr->vio_bus = spapr_vio_bus_init();
 
     for (i = 0; i < MAX_SERIAL_PORTS; i++) {
diff --git a/hw/spapr.h b/hw/spapr.h
index 0dcb83a5ae..fae8e1351c 100644
--- a/hw/spapr.h
+++ b/hw/spapr.h
@@ -2,9 +2,11 @@
 #define __HW_SPAPR_H__
 
 struct VIOsPAPRBus;
+struct icp_state;
 
 typedef struct sPAPREnvironment {
     struct VIOsPAPRBus *vio_bus;
+    struct icp_state *icp;
 } sPAPREnvironment;
 
 #define H_SUCCESS         0
diff --git a/hw/xics.c b/hw/xics.c
new file mode 100644
index 0000000000..66047a6c57
--- /dev/null
+++ b/hw/xics.c
@@ -0,0 +1,486 @@
+/*
+ * QEMU PowerPC pSeries Logical Partition (aka sPAPR) hardware System Emulator
+ *
+ * PAPR Virtualized Interrupt System, aka ICS/ICP aka xics
+ *
+ * Copyright (c) 2010,2011 David Gibson, IBM Corporation.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ *
+ */
+
+#include "hw.h"
+#include "hw/spapr.h"
+#include "hw/xics.h"
+
+#include <pthread.h>
+
+/*
+ * ICP: Presentation layer
+ */
+
+struct icp_server_state {
+    uint32_t xirr;
+    uint8_t pending_priority;
+    uint8_t mfrr;
+    qemu_irq output;
+};
+
+#define XISR_MASK  0x00ffffff
+#define CPPR_MASK  0xff000000
+
+#define XISR(ss)   (((ss)->xirr) & XISR_MASK)
+#define CPPR(ss)   (((ss)->xirr) >> 24)
+
+struct ics_state;
+
+struct icp_state {
+    long nr_servers;
+    struct icp_server_state *ss;
+    struct ics_state *ics;
+};
+
+static void ics_reject(struct ics_state *ics, int nr);
+static void ics_resend(struct ics_state *ics);
+static void ics_eoi(struct ics_state *ics, int nr);
+
+static void icp_check_ipi(struct icp_state *icp, int server)
+{
+    struct icp_server_state *ss = icp->ss + server;
+
+    if (XISR(ss) && (ss->pending_priority <= ss->mfrr)) {
+        return;
+    }
+
+    if (XISR(ss)) {
+        ics_reject(icp->ics, XISR(ss));
+    }
+
+    ss->xirr = (ss->xirr & ~XISR_MASK) | XICS_IPI;
+    ss->pending_priority = ss->mfrr;
+    qemu_irq_raise(ss->output);
+}
+
+static void icp_resend(struct icp_state *icp, int server)
+{
+    struct icp_server_state *ss = icp->ss + server;
+
+    if (ss->mfrr < CPPR(ss)) {
+        icp_check_ipi(icp, server);
+    }
+    ics_resend(icp->ics);
+}
+
+static void icp_set_cppr(struct icp_state *icp, int server, uint8_t cppr)
+{
+    struct icp_server_state *ss = icp->ss + server;
+    uint8_t old_cppr;
+    uint32_t old_xisr;
+
+    old_cppr = CPPR(ss);
+    ss->xirr = (ss->xirr & ~CPPR_MASK) | (cppr << 24);
+
+    if (cppr < old_cppr) {
+        if (XISR(ss) && (cppr <= ss->pending_priority)) {
+            old_xisr = XISR(ss);
+            ss->xirr &= ~XISR_MASK; /* Clear XISR */
+            qemu_irq_lower(ss->output);
+            ics_reject(icp->ics, old_xisr);
+        }
+    } else {
+        if (!XISR(ss)) {
+            icp_resend(icp, server);
+        }
+    }
+}
+
+static void icp_set_mfrr(struct icp_state *icp, int nr, uint8_t mfrr)
+{
+    struct icp_server_state *ss = icp->ss + nr;
+
+    ss->mfrr = mfrr;
+    if (mfrr < CPPR(ss)) {
+        icp_check_ipi(icp, nr);
+    }
+}
+
+static uint32_t icp_accept(struct icp_server_state *ss)
+{
+    uint32_t xirr;
+
+    qemu_irq_lower(ss->output);
+    xirr = ss->xirr;
+    ss->xirr = ss->pending_priority << 24;
+    return xirr;
+}
+
+static void icp_eoi(struct icp_state *icp, int server, uint32_t xirr)
+{
+    struct icp_server_state *ss = icp->ss + server;
+
+    ics_eoi(icp->ics, xirr & XISR_MASK);
+    /* Send EOI -> ICS */
+    ss->xirr = (ss->xirr & ~CPPR_MASK) | (xirr & CPPR_MASK);
+    if (!XISR(ss)) {
+        icp_resend(icp, server);
+    }
+}
+
+static void icp_irq(struct icp_state *icp, int server, int nr, uint8_t priority)
+{
+    struct icp_server_state *ss = icp->ss + server;
+
+    if ((priority >= CPPR(ss))
+        || (XISR(ss) && (ss->pending_priority <= priority))) {
+        ics_reject(icp->ics, nr);
+    } else {
+        if (XISR(ss)) {
+            ics_reject(icp->ics, XISR(ss));
+        }
+        ss->xirr = (ss->xirr & ~XISR_MASK) | (nr & XISR_MASK);
+        ss->pending_priority = priority;
+        qemu_irq_raise(ss->output);
+    }
+}
+
+/*
+ * ICS: Source layer
+ */
+
+struct ics_irq_state {
+    int server;
+    uint8_t priority;
+    uint8_t saved_priority;
+    /* int pending:1; */
+    /* int presented:1; */
+    int rejected:1;
+    int masked_pending:1;
+};
+
+struct ics_state {
+    int nr_irqs;
+    int offset;
+    qemu_irq *qirqs;
+    struct ics_irq_state *irqs;
+    struct icp_state *icp;
+};
+
+static int ics_valid_irq(struct ics_state *ics, uint32_t nr)
+{
+    return (nr >= ics->offset)
+        && (nr < (ics->offset + ics->nr_irqs));
+}
+
+static void ics_set_irq_msi(void *opaque, int nr, int val)
+{
+    struct ics_state *ics = (struct ics_state *)opaque;
+    struct ics_irq_state *irq = ics->irqs + nr;
+
+    if (val) {
+        if (irq->priority == 0xff) {
+            irq->masked_pending = 1;
+            /* masked pending */ ;
+        } else  {
+            icp_irq(ics->icp, irq->server, nr + ics->offset, irq->priority);
+        }
+    }
+}
+
+static void ics_reject_msi(struct ics_state *ics, int nr)
+{
+    struct ics_irq_state *irq = ics->irqs + nr - ics->offset;
+
+    irq->rejected = 1;
+}
+
+static void ics_resend_msi(struct ics_state *ics)
+{
+    int i;
+
+    for (i = 0; i < ics->nr_irqs; i++) {
+        struct ics_irq_state *irq = ics->irqs + i;
+
+        /* FIXME: filter by server#? */
+        if (irq->rejected) {
+            irq->rejected = 0;
+            if (irq->priority != 0xff) {
+                icp_irq(ics->icp, irq->server, i + ics->offset, irq->priority);
+            }
+        }
+    }
+}
+
+static void ics_write_xive_msi(struct ics_state *ics, int nr, int server,
+                               uint8_t priority)
+{
+    struct ics_irq_state *irq = ics->irqs + nr;
+
+    irq->server = server;
+    irq->priority = priority;
+
+    if (!irq->masked_pending || (priority == 0xff)) {
+        return;
+    }
+
+    irq->masked_pending = 0;
+    icp_irq(ics->icp, server, nr + ics->offset, priority);
+}
+
+static void ics_reject(struct ics_state *ics, int nr)
+{
+    ics_reject_msi(ics, nr);
+}
+
+static void ics_resend(struct ics_state *ics)
+{
+    ics_resend_msi(ics);
+}
+
+static void ics_eoi(struct ics_state *ics, int nr)
+{
+}
+
+/*
+ * Exported functions
+ */
+
+qemu_irq xics_find_qirq(struct icp_state *icp, int irq)
+{
+    if ((irq < icp->ics->offset)
+        || (irq >= (icp->ics->offset + icp->ics->nr_irqs))) {
+        return NULL;
+    }
+
+    return icp->ics->qirqs[irq - icp->ics->offset];
+}
+
+static target_ulong h_cppr(CPUState *env, sPAPREnvironment *spapr,
+                           target_ulong opcode, target_ulong *args)
+{
+    target_ulong cppr = args[0];
+
+    icp_set_cppr(spapr->icp, env->cpu_index, cppr);
+    return H_SUCCESS;
+}
+
+static target_ulong h_ipi(CPUState *env, sPAPREnvironment *spapr,
+                          target_ulong opcode, target_ulong *args)
+{
+    target_ulong server = args[0];
+    target_ulong mfrr = args[1];
+
+    if (server >= spapr->icp->nr_servers) {
+        return H_PARAMETER;
+    }
+
+    icp_set_mfrr(spapr->icp, server, mfrr);
+    return H_SUCCESS;
+
+}
+
+static target_ulong h_xirr(CPUState *env, sPAPREnvironment *spapr,
+                           target_ulong opcode, target_ulong *args)
+{
+    uint32_t xirr = icp_accept(spapr->icp->ss + env->cpu_index);
+
+    args[0] = xirr;
+    return H_SUCCESS;
+}
+
+static target_ulong h_eoi(CPUState *env, sPAPREnvironment *spapr,
+                          target_ulong opcode, target_ulong *args)
+{
+    target_ulong xirr = args[0];
+
+    icp_eoi(spapr->icp, env->cpu_index, xirr);
+    return H_SUCCESS;
+}
+
+static void rtas_set_xive(sPAPREnvironment *spapr, uint32_t token,
+                          uint32_t nargs, target_ulong args,
+                          uint32_t nret, target_ulong rets)
+{
+    struct ics_state *ics = spapr->icp->ics;
+    uint32_t nr, server, priority;
+
+    if ((nargs != 3) || (nret != 1)) {
+        rtas_st(rets, 0, -3);
+        return;
+    }
+
+    nr = rtas_ld(args, 0);
+    server = rtas_ld(args, 1);
+    priority = rtas_ld(args, 2);
+
+    if (!ics_valid_irq(ics, nr) || (server >= ics->icp->nr_servers)
+        || (priority > 0xff)) {
+        rtas_st(rets, 0, -3);
+        return;
+    }
+
+    ics_write_xive_msi(ics, nr - ics->offset, server, priority);
+
+    rtas_st(rets, 0, 0); /* Success */
+}
+
+static void rtas_get_xive(sPAPREnvironment *spapr, uint32_t token,
+                          uint32_t nargs, target_ulong args,
+                          uint32_t nret, target_ulong rets)
+{
+    struct ics_state *ics = spapr->icp->ics;
+    uint32_t nr;
+
+    if ((nargs != 1) || (nret != 3)) {
+        rtas_st(rets, 0, -3);
+        return;
+    }
+
+    nr = rtas_ld(args, 0);
+
+    if (!ics_valid_irq(ics, nr)) {
+        rtas_st(rets, 0, -3);
+        return;
+    }
+
+    rtas_st(rets, 0, 0); /* Success */
+    rtas_st(rets, 1, ics->irqs[nr - ics->offset].server);
+    rtas_st(rets, 2, ics->irqs[nr - ics->offset].priority);
+}
+
+static void rtas_int_off(sPAPREnvironment *spapr, uint32_t token,
+                         uint32_t nargs, target_ulong args,
+                         uint32_t nret, target_ulong rets)
+{
+    struct ics_state *ics = spapr->icp->ics;
+    uint32_t nr;
+
+    if ((nargs != 1) || (nret != 1)) {
+        rtas_st(rets, 0, -3);
+        return;
+    }
+
+    nr = rtas_ld(args, 0);
+
+    if (!ics_valid_irq(ics, nr)) {
+        rtas_st(rets, 0, -3);
+        return;
+    }
+
+    /* This is a NOP for now, since the described PAPR semantics don't
+     * seem to gel with what Linux does */
+#if 0
+    struct ics_irq_state *irq = xics->irqs + (nr - xics->offset);
+
+    irq->saved_priority = irq->priority;
+    ics_write_xive_msi(xics, nr - xics->offset, irq->server, 0xff);
+#endif
+
+    rtas_st(rets, 0, 0); /* Success */
+}
+
+static void rtas_int_on(sPAPREnvironment *spapr, uint32_t token,
+                        uint32_t nargs, target_ulong args,
+                        uint32_t nret, target_ulong rets)
+{
+    struct ics_state *ics = spapr->icp->ics;
+    uint32_t nr;
+
+    if ((nargs != 1) || (nret != 1)) {
+        rtas_st(rets, 0, -3);
+        return;
+    }
+
+    nr = rtas_ld(args, 0);
+
+    if (!ics_valid_irq(ics, nr)) {
+        rtas_st(rets, 0, -3);
+        return;
+    }
+
+    /* This is a NOP for now, since the described PAPR semantics don't
+     * seem to gel with what Linux does */
+#if 0
+    struct ics_irq_state *irq = xics->irqs + (nr - xics->offset);
+
+    ics_write_xive_msi(xics, nr - xics->offset,
+                       irq->server, irq->saved_priority);
+#endif
+
+    rtas_st(rets, 0, 0); /* Success */
+}
+
+struct icp_state *xics_system_init(int nr_servers, CPUState *servers[],
+                                   int nr_irqs)
+{
+    int i;
+    struct icp_state *icp;
+    struct ics_state *ics;
+
+    icp = qemu_mallocz(sizeof(*icp));
+    icp->nr_servers = nr_servers;
+    icp->ss = qemu_mallocz(nr_servers * sizeof(struct icp_server_state));
+
+    for (i = 0; i < nr_servers; i++) {
+        servers[i]->cpu_index = i;
+
+        switch (PPC_INPUT(servers[i])) {
+        case PPC_FLAGS_INPUT_POWER7:
+            icp->ss[i].output = servers[i]->irq_inputs[POWER7_INPUT_INT];
+            break;
+
+        case PPC_FLAGS_INPUT_970:
+            icp->ss[i].output = servers[i]->irq_inputs[PPC970_INPUT_INT];
+            break;
+
+        default:
+            hw_error("XICS interrupt model does not support this CPU bus "
+                     "model\n");
+            exit(1);
+        }
+
+        icp->ss[i].mfrr = 0xff;
+    }
+
+    ics = qemu_mallocz(sizeof(*ics));
+    ics->nr_irqs = nr_irqs;
+    ics->offset = 16;
+    ics->irqs = qemu_mallocz(nr_irqs * sizeof(struct ics_irq_state));
+
+    icp->ics = ics;
+    ics->icp = icp;
+
+    for (i = 0; i < nr_irqs; i++) {
+        ics->irqs[i].priority = 0xff;
+        ics->irqs[i].saved_priority = 0xff;
+    }
+
+    ics->qirqs = qemu_allocate_irqs(ics_set_irq_msi, ics, nr_irqs);
+
+    spapr_register_hypercall(H_CPPR, h_cppr);
+    spapr_register_hypercall(H_IPI, h_ipi);
+    spapr_register_hypercall(H_XIRR, h_xirr);
+    spapr_register_hypercall(H_EOI, h_eoi);
+
+    spapr_rtas_register("ibm,set-xive", rtas_set_xive);
+    spapr_rtas_register("ibm,get-xive", rtas_get_xive);
+    spapr_rtas_register("ibm,int-off", rtas_int_off);
+    spapr_rtas_register("ibm,int-on", rtas_int_on);
+
+    return icp;
+}
diff --git a/hw/xics.h b/hw/xics.h
new file mode 100644
index 0000000000..096eeb346d
--- /dev/null
+++ b/hw/xics.h
@@ -0,0 +1,39 @@
+/*
+ * QEMU PowerPC pSeries Logical Partition (aka sPAPR) hardware System Emulator
+ *
+ * PAPR Virtualized Interrupt System, aka ICS/ICP aka xics
+ *
+ * Copyright (c) 2010,2011 David Gibson, IBM Corporation.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ *
+ */
+#if !defined(__XICS_H__)
+#define __XICS_H__
+
+#define XICS_IPI        0x2
+
+struct icp_state;
+
+qemu_irq xics_find_qirq(struct icp_state *icp, int irq);
+
+struct icp_state *xics_system_init(int nr_servers, CPUState *servers[],
+                                   int nr_irqs);
+
+#endif /* __XICS_H__ */