[Qemu-devel] [PATCH v3 06/35] spapr/xive: introduce a XIVE interrupt presenter model

["Cédric Le Goater" <clg@kaod.org>]

The XIVE presenter engine uses a set of registers to handle priority
management and interrupt acknowledgment among other things. The most
important ones being :

  - Interrupt Priority Register (PIPR)
  - Interrupt Pending Buffer (IPB)
  - Current Processor Priority (CPPR)
  - Notification Source Register (NSR)

There is one set of registers per level of privilege, four in all :
HW, HV pool, OS and User. These are called rings. All registers are
accessible through a specific MMIO region called the Thread Interrupt
Management Areas (TIMA) but, depending on the privilege level of the
CPU, the view of the TIMA is filtered. The sPAPR machine runs at the
OS privilege and therefore can only accesses the OS and the User
rings. The others are for hypervisor levels.

The CPU interrupt state is modeled with a XiveNVT object which stores
the values of the different registers. The different TIMA views are
mapped at the same address for each CPU and 'current_cpu' is used to
retrieve the XiveNVT holding the ring registers.

Signed-off-by: Cédric Le Goater <clg@kaod.org>
---

 Changes since v2 :

 - introduced the XiveFabric interface

 hw/intc/spapr_xive.c        |  25 ++++
 hw/intc/xive.c              | 279 ++++++++++++++++++++++++++++++++++++++++++++
 include/hw/ppc/spapr_xive.h |   5 +
 include/hw/ppc/xive.h       |  31 +++++
 include/hw/ppc/xive_regs.h  |  84 +++++++++++++
 5 files changed, 424 insertions(+)

diff --git a/hw/intc/spapr_xive.c b/hw/intc/spapr_xive.c
index 90cde8a4082d..f07832bf0a00 100644
--- a/hw/intc/spapr_xive.c
+++ b/hw/intc/spapr_xive.c
@@ -13,6 +13,7 @@
 #include "target/ppc/cpu.h"
 #include "sysemu/cpus.h"
 #include "monitor/monitor.h"
+#include "hw/ppc/spapr.h"
 #include "hw/ppc/spapr_xive.h"
 #include "hw/ppc/xive.h"
 #include "hw/ppc/xive_regs.h"
@@ -95,6 +96,22 @@ static void spapr_xive_realize(DeviceState *dev, Error **errp)
 
     /* Allocate the Interrupt Virtualization Table */
     xive->ivt = g_new0(XiveIVE, xive->nr_irqs);
+
+    /* The Thread Interrupt Management Area has the same address for
+     * each chip. On sPAPR, we only need to expose the User and OS
+     * level views of the TIMA.
+     */
+    xive->tm_base = XIVE_TM_BASE;
+
+    memory_region_init_io(&xive->tm_mmio_user, OBJECT(xive),
+                          &xive_tm_user_ops, xive, "xive.tima.user",
+                          1ull << TM_SHIFT);
+    sysbus_init_mmio(SYS_BUS_DEVICE(dev), &xive->tm_mmio_user);
+
+    memory_region_init_io(&xive->tm_mmio_os, OBJECT(xive),
+                          &xive_tm_os_ops, xive, "xive.tima.os",
+                          1ull << TM_SHIFT);
+    sysbus_init_mmio(SYS_BUS_DEVICE(dev), &xive->tm_mmio_os);
 }
 
 static XiveIVE *spapr_xive_get_ive(XiveFabric *xf, uint32_t lisn)
@@ -104,6 +121,13 @@ static XiveIVE *spapr_xive_get_ive(XiveFabric *xf, uint32_t lisn)
     return lisn < xive->nr_irqs ? &xive->ivt[lisn] : NULL;
 }
 
+static XiveNVT *spapr_xive_get_nvt(XiveFabric *xf, uint32_t server)
+{
+    PowerPCCPU *cpu = spapr_find_cpu(server);
+
+    return cpu ? XIVE_NVT(cpu->intc) : NULL;
+}
+
 static const VMStateDescription vmstate_spapr_xive_ive = {
     .name = TYPE_SPAPR_XIVE "/ive",
     .version_id = 1,
@@ -143,6 +167,7 @@ static void spapr_xive_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_spapr_xive;
 
     xfc->get_ive = spapr_xive_get_ive;
+    xfc->get_nvt = spapr_xive_get_nvt;
 }
 
 static const TypeInfo spapr_xive_info = {
diff --git a/hw/intc/xive.c b/hw/intc/xive.c
index dccad0318834..5691bb9474e4 100644
--- a/hw/intc/xive.c
+++ b/hw/intc/xive.c
@@ -14,7 +14,278 @@
 #include "sysemu/cpus.h"
 #include "sysemu/dma.h"
 #include "monitor/monitor.h"
+#include "hw/ppc/xics.h" /* for ICP_PROP_CPU */
 #include "hw/ppc/xive.h"
+#include "hw/ppc/xive_regs.h"
+
+/*
+ * XIVE Interrupt Presenter
+ */
+
+static uint64_t xive_nvt_accept(XiveNVT *nvt)
+{
+    return 0;
+}
+
+static void xive_nvt_set_cppr(XiveNVT *nvt, uint8_t cppr)
+{
+    if (cppr > XIVE_PRIORITY_MAX) {
+        cppr = 0xff;
+    }
+
+    nvt->ring_os[TM_CPPR] = cppr;
+}
+
+/*
+ * OS Thread Interrupt Management Area MMIO
+ */
+static uint64_t xive_tm_read_special(XiveNVT *nvt, hwaddr offset,
+                                           unsigned size)
+{
+    uint64_t ret = -1;
+
+    if (offset == TM_SPC_ACK_OS_REG && size == 2) {
+        ret = xive_nvt_accept(nvt);
+    } else {
+        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid TIMA read @%"
+                      HWADDR_PRIx" size %d\n", offset, size);
+    }
+
+    return ret;
+}
+
+#define TM_RING(offset) ((offset) & 0xf0)
+
+static uint64_t xive_tm_os_read(void *opaque, hwaddr offset,
+                                      unsigned size)
+{
+    PowerPCCPU *cpu = POWERPC_CPU(current_cpu);
+    XiveNVT *nvt = XIVE_NVT(cpu->intc);
+    uint64_t ret = -1;
+    int i;
+
+    if (offset >= TM_SPC_ACK_EBB) {
+        return xive_tm_read_special(nvt, offset, size);
+    }
+
+    if (TM_RING(offset) != TM_QW1_OS) {
+        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid access to non-OS ring @%"
+                      HWADDR_PRIx"\n", offset);
+        return ret;
+    }
+
+    ret = 0;
+    for (i = 0; i < size; i++) {
+        ret |= (uint64_t) nvt->regs[offset + i] << (8 * (size - i - 1));
+    }
+
+    return ret;
+}
+
+static bool xive_tm_is_readonly(uint8_t offset)
+{
+    return offset != TM_QW1_OS + TM_CPPR;
+}
+
+static void xive_tm_write_special(XiveNVT *nvt, hwaddr offset,
+                                        uint64_t value, unsigned size)
+{
+    /* TODO: support TM_SPC_SET_OS_PENDING */
+
+    /* TODO: support TM_SPC_ACK_OS_EL */
+}
+
+static void xive_tm_os_write(void *opaque, hwaddr offset,
+                                   uint64_t value, unsigned size)
+{
+    PowerPCCPU *cpu = POWERPC_CPU(current_cpu);
+    XiveNVT *nvt = XIVE_NVT(cpu->intc);
+    int i;
+
+    if (offset >= TM_SPC_ACK_EBB) {
+        xive_tm_write_special(nvt, offset, value, size);
+        return;
+    }
+
+    if (TM_RING(offset) != TM_QW1_OS) {
+        qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid access to non-OS ring @%"
+                      HWADDR_PRIx"\n", offset);
+        return;
+    }
+
+    switch (size) {
+    case 1:
+        if (offset == TM_QW1_OS + TM_CPPR) {
+            xive_nvt_set_cppr(nvt, value & 0xff);
+        }
+        break;
+    case 4:
+    case 8:
+        for (i = 0; i < size; i++) {
+            if (!xive_tm_is_readonly(offset + i)) {
+                nvt->regs[offset + i] = (value >> (8 * (size - i - 1))) & 0xff;
+            }
+        }
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
+const MemoryRegionOps xive_tm_os_ops = {
+    .read = xive_tm_os_read,
+    .write = xive_tm_os_write,
+    .endianness = DEVICE_BIG_ENDIAN,
+    .valid = {
+        .min_access_size = 1,
+        .max_access_size = 8,
+    },
+    .impl = {
+        .min_access_size = 1,
+        .max_access_size = 8,
+    },
+};
+
+/*
+ * User Thread Interrupt Management Area MMIO
+ */
+
+static uint64_t xive_tm_user_read(void *opaque, hwaddr offset,
+                                        unsigned size)
+{
+    qemu_log_mask(LOG_UNIMP, "XIVE: invalid access to User TIMA @%"
+                  HWADDR_PRIx"\n", offset);
+    return -1;
+}
+
+static void xive_tm_user_write(void *opaque, hwaddr offset,
+                                     uint64_t value, unsigned size)
+{
+    qemu_log_mask(LOG_UNIMP, "XIVE: invalid access to User TIMA @%"
+                  HWADDR_PRIx"\n", offset);
+}
+
+
+const MemoryRegionOps xive_tm_user_ops = {
+    .read = xive_tm_user_read,
+    .write = xive_tm_user_write,
+    .endianness = DEVICE_BIG_ENDIAN,
+    .valid = {
+        .min_access_size = 1,
+        .max_access_size = 8,
+    },
+    .impl = {
+        .min_access_size = 1,
+        .max_access_size = 8,
+    },
+};
+
+static char *xive_nvt_ring_print(uint8_t *ring)
+{
+    uint32_t w2 = be32_to_cpu(*((uint32_t *) &ring[TM_WORD2]));
+
+    return g_strdup_printf("%02x  %02x   %02x  %02x    %02x   "
+                   "%02x  %02x  %02x   %08x",
+                   ring[TM_NSR], ring[TM_CPPR], ring[TM_IPB], ring[TM_LSMFB],
+                   ring[TM_ACK_CNT], ring[TM_INC], ring[TM_AGE], ring[TM_PIPR],
+                   w2);
+}
+
+void xive_nvt_pic_print_info(XiveNVT *nvt, Monitor *mon)
+{
+    int cpu_index = nvt->cs ? nvt->cs->cpu_index : -1;
+    char *s;
+
+    monitor_printf(mon, "CPU[%04x]: QW    NSR CPPR IPB LSMFB ACK# INC AGE PIPR"
+                   " W2\n", cpu_index);
+
+    s = xive_nvt_ring_print(&nvt->regs[TM_QW1_OS]);
+    monitor_printf(mon, "CPU[%04x]: OS    %s\n", cpu_index, s);
+    g_free(s);
+    s = xive_nvt_ring_print(&nvt->regs[TM_QW0_USER]);
+    monitor_printf(mon, "CPU[%04x]: USER  %s\n", cpu_index, s);
+    g_free(s);
+}
+
+static void xive_nvt_reset(void *dev)
+{
+    XiveNVT *nvt = XIVE_NVT(dev);
+
+    memset(nvt->regs, 0, sizeof(nvt->regs));
+}
+
+static void xive_nvt_realize(DeviceState *dev, Error **errp)
+{
+    XiveNVT *nvt = XIVE_NVT(dev);
+    PowerPCCPU *cpu;
+    CPUPPCState *env;
+    Object *obj;
+    Error *err = NULL;
+
+    obj = object_property_get_link(OBJECT(dev), ICP_PROP_CPU, &err);
+    if (!obj) {
+        error_propagate(errp, err);
+        error_prepend(errp, "required link '" ICP_PROP_CPU "' not found: ");
+        return;
+    }
+
+    cpu = POWERPC_CPU(obj);
+    nvt->cs = CPU(obj);
+
+    env = &cpu->env;
+    switch (PPC_INPUT(env)) {
+    case PPC_FLAGS_INPUT_POWER7:
+        nvt->output = env->irq_inputs[POWER7_INPUT_INT];
+        break;
+
+    default:
+        error_setg(errp, "XIVE interrupt controller does not support "
+                   "this CPU bus model");
+        return;
+    }
+
+    qemu_register_reset(xive_nvt_reset, dev);
+}
+
+static void xive_nvt_unrealize(DeviceState *dev, Error **errp)
+{
+    qemu_unregister_reset(xive_nvt_reset, dev);
+}
+
+static void xive_nvt_init(Object *obj)
+{
+    XiveNVT *nvt = XIVE_NVT(obj);
+
+    nvt->ring_os = &nvt->regs[TM_QW1_OS];
+}
+
+static const VMStateDescription vmstate_xive_nvt = {
+    .name = TYPE_XIVE_NVT,
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_BUFFER(regs, XiveNVT),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
+static void xive_nvt_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+
+    dc->realize = xive_nvt_realize;
+    dc->unrealize = xive_nvt_unrealize;
+    dc->desc = "XIVE Interrupt Presenter";
+    dc->vmsd = &vmstate_xive_nvt;
+}
+
+static const TypeInfo xive_nvt_info = {
+    .name          = TYPE_XIVE_NVT,
+    .parent        = TYPE_DEVICE,
+    .instance_size = sizeof(XiveNVT),
+    .instance_init = xive_nvt_init,
+    .class_init    = xive_nvt_class_init,
+};
 
 /*
  * XIVE Fabric
@@ -27,6 +298,13 @@ XiveIVE *xive_fabric_get_ive(XiveFabric *xf, uint32_t lisn)
     return xfc->get_ive(xf, lisn);
 }
 
+XiveNVT *xive_fabric_get_nvt(XiveFabric *xf, uint32_t server)
+{
+    XiveFabricClass *xfc = XIVE_FABRIC_GET_CLASS(xf);
+
+    return xfc->get_nvt(xf, server);
+}
+
 static void xive_fabric_route(XiveFabric *xf, int lisn)
 {
 
@@ -418,6 +696,7 @@ static void xive_register_types(void)
 {
     type_register_static(&xive_source_info);
     type_register_static(&xive_fabric_info);
+    type_register_static(&xive_nvt_info);
 }
 
 type_init(xive_register_types)
diff --git a/include/hw/ppc/spapr_xive.h b/include/hw/ppc/spapr_xive.h
index 4538c622b60a..25d78eec884d 100644
--- a/include/hw/ppc/spapr_xive.h
+++ b/include/hw/ppc/spapr_xive.h
@@ -25,6 +25,11 @@ typedef struct sPAPRXive {
     /* Routing table */
     XiveIVE      *ivt;
     uint32_t     nr_irqs;
+
+    /* TIMA memory regions */
+    hwaddr       tm_base;
+    MemoryRegion tm_mmio_user;
+    MemoryRegion tm_mmio_os;
 } sPAPRXive;
 
 bool spapr_xive_irq_enable(sPAPRXive *xive, uint32_t lisn, bool lsi);
diff --git a/include/hw/ppc/xive.h b/include/hw/ppc/xive.h
index 57295715a4a5..1a2da610d91c 100644
--- a/include/hw/ppc/xive.h
+++ b/include/hw/ppc/xive.h
@@ -20,6 +20,7 @@ typedef struct XiveFabric XiveFabric;
  */
 
 #define XIVE_VC_BASE   0x0006010000000000ull
+#define XIVE_TM_BASE   0x0006030203180000ull
 
 /*
  * XIVE Interrupt Source
@@ -155,6 +156,34 @@ static inline void xive_source_irq_set(XiveSource *xsrc, uint32_t srcno,
 }
 
 /*
+ * XIVE Interrupt Presenter
+ */
+
+#define TYPE_XIVE_NVT "xive-nvt"
+#define XIVE_NVT(obj) OBJECT_CHECK(XiveNVT, (obj), TYPE_XIVE_NVT)
+
+#define TM_RING_COUNT           4
+#define TM_RING_SIZE            0x10
+
+typedef struct XiveNVT {
+    DeviceState parent_obj;
+
+    CPUState  *cs;
+    qemu_irq  output;
+
+    /* Thread interrupt Management (TM) registers */
+    uint8_t   regs[TM_RING_COUNT * TM_RING_SIZE];
+
+    /* Shortcuts to rings */
+    uint8_t   *ring_os;
+} XiveNVT;
+
+extern const MemoryRegionOps xive_tm_user_ops;
+extern const MemoryRegionOps xive_tm_os_ops;
+
+void xive_nvt_pic_print_info(XiveNVT *nvt, Monitor *mon);
+
+/*
  * XIVE Fabric
  */
 
@@ -175,8 +204,10 @@ typedef struct XiveFabricClass {
     void (*notify)(XiveFabric *xf, uint32_t lisn);
 
     XiveIVE *(*get_ive)(XiveFabric *xf, uint32_t lisn);
+    XiveNVT *(*get_nvt)(XiveFabric *xf, uint32_t server);
 } XiveFabricClass;
 
 XiveIVE *xive_fabric_get_ive(XiveFabric *xf, uint32_t lisn);
+XiveNVT *xive_fabric_get_nvt(XiveFabric *xf, uint32_t server);
 
 #endif /* PPC_XIVE_H */
diff --git a/include/hw/ppc/xive_regs.h b/include/hw/ppc/xive_regs.h
index 5903f29eb789..f2e2a1ac8f6e 100644
--- a/include/hw/ppc/xive_regs.h
+++ b/include/hw/ppc/xive_regs.h
@@ -10,6 +10,88 @@
 #ifndef _PPC_XIVE_REGS_H
 #define _PPC_XIVE_REGS_H
 
+#define TM_SHIFT                16
+
+/* TM register offsets */
+#define TM_QW0_USER             0x000 /* All rings */
+#define TM_QW1_OS               0x010 /* Ring 0..2 */
+#define TM_QW2_HV_POOL          0x020 /* Ring 0..1 */
+#define TM_QW3_HV_PHYS          0x030 /* Ring 0..1 */
+
+/* Byte offsets inside a QW             QW0 QW1 QW2 QW3 */
+#define TM_NSR                  0x0  /*  +   +   -   +  */
+#define TM_CPPR                 0x1  /*  -   +   -   +  */
+#define TM_IPB                  0x2  /*  -   +   +   +  */
+#define TM_LSMFB                0x3  /*  -   +   +   +  */
+#define TM_ACK_CNT              0x4  /*  -   +   -   -  */
+#define TM_INC                  0x5  /*  -   +   -   +  */
+#define TM_AGE                  0x6  /*  -   +   -   +  */
+#define TM_PIPR                 0x7  /*  -   +   -   +  */
+
+#define TM_WORD0                0x0
+#define TM_WORD1                0x4
+
+/*
+ * QW word 2 contains the valid bit at the top and other fields
+ * depending on the QW.
+ */
+#define TM_WORD2                0x8
+#define   TM_QW0W2_VU           PPC_BIT32(0)
+#define   TM_QW0W2_LOGIC_SERV   PPC_BITMASK32(1, 31) /* XX 2,31 ? */
+#define   TM_QW1W2_VO           PPC_BIT32(0)
+#define   TM_QW1W2_OS_CAM       PPC_BITMASK32(8, 31)
+#define   TM_QW2W2_VP           PPC_BIT32(0)
+#define   TM_QW2W2_POOL_CAM     PPC_BITMASK32(8, 31)
+#define   TM_QW3W2_VT           PPC_BIT32(0)
+#define   TM_QW3W2_LP           PPC_BIT32(6)
+#define   TM_QW3W2_LE           PPC_BIT32(7)
+#define   TM_QW3W2_T            PPC_BIT32(31)
+
+/*
+ * In addition to normal loads to "peek" and writes (only when invalid)
+ * using 4 and 8 bytes accesses, the above registers support these
+ * "special" byte operations:
+ *
+ *   - Byte load from QW0[NSR] - User level NSR (EBB)
+ *   - Byte store to QW0[NSR] - User level NSR (EBB)
+ *   - Byte load/store to QW1[CPPR] and QW3[CPPR] - CPPR access
+ *   - Byte load from QW3[TM_WORD2] - Read VT||00000||LP||LE on thrd 0
+ *                                    otherwise VT||0000000
+ *   - Byte store to QW3[TM_WORD2] - Set VT bit (and LP/LE if present)
+ *
+ * Then we have all these "special" CI ops at these offset that trigger
+ * all sorts of side effects:
+ */
+#define TM_SPC_ACK_EBB          0x800   /* Load8 ack EBB to reg*/
+#define TM_SPC_ACK_OS_REG       0x810   /* Load16 ack OS irq to reg */
+#define TM_SPC_PUSH_USR_CTX     0x808   /* Store32 Push/Validate user context */
+#define TM_SPC_PULL_USR_CTX     0x808   /* Load32 Pull/Invalidate user
+                                         * context */
+#define TM_SPC_SET_OS_PENDING   0x812   /* Store8 Set OS irq pending bit */
+#define TM_SPC_PULL_OS_CTX      0x818   /* Load32/Load64 Pull/Invalidate OS
+                                         * context to reg */
+#define TM_SPC_PULL_POOL_CTX    0x828   /* Load32/Load64 Pull/Invalidate Pool
+                                         * context to reg*/
+#define TM_SPC_ACK_HV_REG       0x830   /* Load16 ack HV irq to reg */
+#define TM_SPC_PULL_USR_CTX_OL  0xc08   /* Store8 Pull/Inval usr ctx to odd
+                                         * line */
+#define TM_SPC_ACK_OS_EL        0xc10   /* Store8 ack OS irq to even line */
+#define TM_SPC_ACK_HV_POOL_EL   0xc20   /* Store8 ack HV evt pool to even
+                                         * line */
+#define TM_SPC_ACK_HV_EL        0xc30   /* Store8 ack HV irq to even line */
+/* XXX more... */
+
+/* NSR fields for the various QW ack types */
+#define TM_QW0_NSR_EB           PPC_BIT8(0)
+#define TM_QW1_NSR_EO           PPC_BIT8(0)
+#define TM_QW3_NSR_HE           PPC_BITMASK8(0, 1)
+#define  TM_QW3_NSR_HE_NONE     0
+#define  TM_QW3_NSR_HE_POOL     1
+#define  TM_QW3_NSR_HE_PHYS     2
+#define  TM_QW3_NSR_HE_LSI      3
+#define TM_QW3_NSR_I            PPC_BIT8(2)
+#define TM_QW3_NSR_GRP_LVL      PPC_BIT8(3, 7)
+
 /* IVE/EAS
  *
  * One per interrupt source. Targets that interrupt to a given EQ
@@ -30,4 +112,6 @@ typedef struct XiveIVE {
 #define IVE_EQ_DATA     PPC_BITMASK(33, 63)      /* Data written to the EQ */
 } XiveIVE;
 
+#define XIVE_PRIORITY_MAX  7
+
 #endif /* _INTC_XIVE_INTERNAL_H */
-- 
2.13.6