BIOS changes for configuring irq0->inti2 override

index 8684987..ddfa828 100755
@@ -445,6 +445,9 @@ uint32_t cpuid_ext_features;
 unsigned long ram_size;
 uint64_t ram_end;
 uint8_t bios_uuid[16];
+#ifdef BX_QEMU
+uint8_t irq0_override;
+#endif
 #ifdef BX_USE_EBDA_TABLES
 unsigned long ebda_cur_addr;
 #endif

@@ -477,6 +480,7 @@ void wrmsr_smp(uint32_t index, uint64_t val)
 #define QEMU_CFG_SIGNATURE  0x00
 #define QEMU_CFG_ID         0x01
 #define QEMU_CFG_UUID       0x02
+#define QEMU_CFG_IRQ0_OVERRIDE 0x0e
 
 int qemu_cfg_port;
 

@@ -518,6 +522,18 @@ void uuid_probe(void)
     memset(bios_uuid, 0, 16);
 }
 
+#ifdef BX_QEMU
+void irq0_override_probe(void)
+{
+    if(qemu_cfg_port) {
+        qemu_cfg_select(QEMU_CFG_IRQ0_OVERRIDE);
+        qemu_cfg_read(&irq0_override, 1);
+        return;
+    }
+    memset(&irq0_override, 0, 1);
+}
+#endif
+
 void cpu_probe(void)
 {
     uint32_t eax, ebx, ecx, edx;

@@ -1160,6 +1176,13 @@ static void mptable_init(void)
 
     /* irqs */
     for(i = 0; i < 16; i++) {
+#ifdef BX_QEMU
+        /* One entry per ioapic interrupt destination. Destination 2 is covered
+         * by irq0->inti2 override (i == 0). Source IRQ 2 is unused 
+         */
+        if (irq0_override && i == 2)
+            continue;
+#endif
         putb(&q, 3); /* entry type = I/O interrupt */
         putb(&q, 0); /* interrupt type = vectored interrupt */
         putb(&q, 0); /* flags: po=0, el=0 */

@@ -1167,7 +1190,12 @@ static void mptable_init(void)
         putb(&q, 0); /* source bus ID = ISA */
         putb(&q, i); /* source bus IRQ */
         putb(&q, ioapic_id); /* dest I/O APIC ID */
-        putb(&q, i); /* dest I/O APIC interrupt in */
+#ifdef BX_QEMU
+        if (irq0_override && i == 0)
+            putb(&q, 2); /* dest I/O APIC interrupt in */
+        else
+#endif
+            putb(&q, i); /* dest I/O APIC interrupt in */
     }
     /* patch length */
     len = q - mp_config_table;

@@ -1550,16 +1578,18 @@ void acpi_bios_init(void)
 
     addr = (addr + 7) & ~7;
     madt_addr = addr;
+    madt = (void *)(addr);
     madt_size = sizeof(*madt) +
         sizeof(struct madt_processor_apic) * MAX_CPUS +
-#ifdef BX_QEMU
-        sizeof(struct madt_io_apic) /* + sizeof(struct madt_int_override) */;
-#else
         sizeof(struct madt_io_apic);
+#ifdef BX_QEMU
+    for (i = 0; i < 16; i++)
+        if (PCI_ISA_IRQ_MASK & (1U << i))
+            madt_size += sizeof(struct madt_int_override);
+    if (irq0_override)
+        madt_size += sizeof(struct madt_int_override);
 #endif
-    madt = (void *)(addr);
     addr += madt_size;
-
 #ifdef BX_QEMU
 #ifdef HPET_WORKS_IN_KVM
     addr = (addr + 7) & ~7;

@@ -1660,23 +1690,21 @@ void acpi_bios_init(void)
         io_apic->io_apic_id = smp_cpus;
         io_apic->address = cpu_to_le32(0xfec00000);
         io_apic->interrupt = cpu_to_le32(0);
+        int_override = (struct madt_int_override*)(io_apic + 1);
 #ifdef BX_QEMU
-#ifdef HPET_WORKS_IN_KVM
-        io_apic++;
-
-        int_override = (void *)io_apic;
-        int_override->type = APIC_XRUPT_OVERRIDE;
-        int_override->length = sizeof(*int_override);
-        int_override->bus = cpu_to_le32(0);
-        int_override->source = cpu_to_le32(0);
-        int_override->gsi = cpu_to_le32(2);
-        int_override->flags = cpu_to_le32(0);
-#endif
+        if (irq0_override) {
+            int_override = (void *)io_apic;
+            int_override->type = APIC_XRUPT_OVERRIDE;
+            int_override->length = sizeof(*int_override);
+            int_override->bus = cpu_to_le32(0);
+            int_override->source = cpu_to_le32(0);
+            int_override->gsi = cpu_to_le32(2);
+            int_override->flags = cpu_to_le32(0); /* conforms to bus specifications */
+            int_override++;
+        }
 #endif
-
-        int_override = (struct madt_int_override*)(io_apic + 1);
         for ( i = 0; i < 16; i++ ) {
-            if ( PCI_ISA_IRQ_MASK & (1U << i) ) {
+            if (PCI_ISA_IRQ_MASK & (1U << i)) {
                 memset(int_override, 0, sizeof(*int_override));
                 int_override->type   = APIC_XRUPT_OVERRIDE;
                 int_override->length = sizeof(*int_override);

@@ -1688,7 +1716,6 @@ void acpi_bios_init(void)
                 continue;
             }
             int_override++;
-            madt_size += sizeof(struct madt_int_override);
         }
         acpi_build_table_header((struct acpi_table_header *)madt,
                                 "APIC", madt_size, 1);

index e1b19d7..bb74f38 100644
@@ -279,6 +279,7 @@ void *fw_cfg_init(uint32_t ctl_port, uint32_t data_port,
     fw_cfg_add_bytes(s, FW_CFG_UUID, qemu_uuid, 16);
     fw_cfg_add_i16(s, FW_CFG_NOGRAPHIC, (uint16_t)nographic);
     fw_cfg_add_i16(s, FW_CFG_NB_CPUS, (uint16_t)smp_cpus);
+    fw_cfg_add_i16(s, FW_CFG_IRQ0_OVERRIDE, (uint16_t)irq0override);
 
     register_savevm("fw_cfg", -1, 1, fw_cfg_save, fw_cfg_load, s);
     qemu_register_reset(fw_cfg_reset, s);

index f616ed2..498c1e3 100644
@@ -15,6 +15,7 @@
 #define FW_CFG_INITRD_SIZE      0x0b
 #define FW_CFG_BOOT_DEVICE      0x0c
 #define FW_CFG_NUMA             0x0d
+#define FW_CFG_IRQ0_OVERRIDE    0x0e
 #define FW_CFG_MAX_ENTRY        0x10
 
 #define FW_CFG_WRITE_CHANNEL    0x4000

index 0b70cf6..2d77a2c 100644
@@ -23,6 +23,7 @@
 
 #include "hw.h"
 #include "pc.h"
+#include "sysemu.h"
 #include "qemu-timer.h"
 #include "host-utils.h"
 

@@ -95,14 +96,13 @@ void ioapic_set_irq(void *opaque, int vector, int level)
 {
     IOAPICState *s = opaque;
 
-#if 0
     /* ISA IRQs map to GSI 1-1 except for IRQ0 which maps
      * to GSI 2.  GSI maps to ioapic 1-1.  This is not
      * the cleanest way of doing it but it should work. */
 
-    if (vector == 0)
+    if (vector == 0 && irq0override) {
         vector = 2;
-#endif
+    }
 
     if (vector >= 0 && vector < IOAPIC_NUM_PINS) {
         uint32_t mask = 1 << vector;

index 68a9218..5b27179 100644
@@ -814,9 +814,14 @@ int kvm_qemu_create_context(void)
                 return r;
         }
         for (i = 0; i < 24; ++i) {
-            r = kvm_add_irq_route(kvm_context, i, KVM_IRQCHIP_IOAPIC, i);
-            if (r < 0)
+            if (i == 0) {
+                r = kvm_add_irq_route(kvm_context, i, KVM_IRQCHIP_IOAPIC, 2);
+            } else if (i != 2) {
+                r = kvm_add_irq_route(kvm_context, i, KVM_IRQCHIP_IOAPIC, i);
+            }
+            if (r < 0) {
                 return r;
+            }
         }
         kvm_commit_irq_routes(kvm_context);
     }

index ca59af8..a836579 100644
@@ -166,6 +166,7 @@ void qemu_kvm_cpu_stop(CPUState *env);
 #define kvm_enabled() (kvm_allowed)
 #define qemu_kvm_irqchip_in_kernel() kvm_irqchip_in_kernel(kvm_context)
 #define qemu_kvm_pit_in_kernel() kvm_pit_in_kernel(kvm_context)
+#define qemu_kvm_has_gsi_routing() kvm_has_gsi_routing(kvm_context)
 #define kvm_has_sync_mmu() qemu_kvm_has_sync_mmu()
 void kvm_init_vcpu(CPUState *env);
 void kvm_load_tsc(CPUState *env);

index e8dd381..a5f96f9 100644
@@ -96,6 +96,7 @@ extern int graphic_width;
 extern int graphic_height;
 extern int graphic_depth;
 extern int nographic;
+extern int irq0override;
 extern const char *keyboard_layout;
 extern int win2k_install_hack;
 extern int rtc_td_hack;

index 9ff4a5a..ee7f29a 100644
@@ -207,6 +207,7 @@ static int vga_ram_size;
 enum vga_retrace_method vga_retrace_method = VGA_RETRACE_DUMB;
 static DisplayState *display_state;
 int nographic;
+int irq0override;
 static int curses;
 static int sdl;
 const char* keyboard_layout = NULL;

@@ -4599,6 +4600,7 @@ int main(int argc, char **argv, char **envp)
     vga_ram_size = VGA_RAM_SIZE;
     snapshot = 0;
     nographic = 0;
+    irq0override = 1;
     curses = 0;
     kernel_filename = NULL;
     kernel_cmdline = "";

@@ -5682,8 +5684,14 @@ int main(int argc, char **argv, char **envp)
         }
     }
 
-    if (kvm_enabled())
-	kvm_init_ap();
+    if (kvm_enabled()) {
+       kvm_init_ap();
+#ifdef USE_KVM
+        if (kvm_irqchip && !qemu_kvm_has_gsi_routing()) {
+           irq0override = 0;
+        }
+#endif
+    }
 
     machine->init(ram_size, vga_ram_size, boot_devices,
                   kernel_filename, kernel_cmdline, initrd_filename, cpu_model);

index ddfa828..7441cd7 100755
@@ -1293,7 +1293,7 @@ struct rsdt_descriptor_rev1
 {
 	ACPI_TABLE_HEADER_DEF                           /* ACPI common table header */
 #ifdef BX_QEMU
-	uint32_t                             table_offset_entry [2]; /* Array of pointers to other */
+	uint32_t                             table_offset_entry [3]; /* Array of pointers to other */
 //	uint32_t                             table_offset_entry [4]; /* Array of pointers to other */
 #else
 	uint32_t                             table_offset_entry [3]; /* Array of pointers to other */

@@ -1450,8 +1450,8 @@ struct acpi_20_generic_address {
 } __attribute__((__packed__));
 
 /*
- *  * HPET Description Table
- *   */
+ *  HPET Description Table
+ */
 struct acpi_20_hpet {
     ACPI_TABLE_HEADER_DEF                           /* ACPI common table header */
     uint32_t           timer_block_id;

@@ -1591,13 +1591,11 @@ void acpi_bios_init(void)
 #endif
     addr += madt_size;
 #ifdef BX_QEMU
-#ifdef HPET_WORKS_IN_KVM
     addr = (addr + 7) & ~7;
     hpet_addr = addr;
     hpet = (void *)(addr);
     addr += sizeof(*hpet);
 #endif
-#endif
 
     acpi_tables_size = addr - base_addr;
 

@@ -1620,10 +1618,10 @@ void acpi_bios_init(void)
     memset(rsdt, 0, sizeof(*rsdt));
     rsdt->table_offset_entry[0] = cpu_to_le32(fadt_addr);
     rsdt->table_offset_entry[1] = cpu_to_le32(madt_addr);
-    //rsdt->table_offset_entry[2] = cpu_to_le32(ssdt_addr);
 #ifdef BX_QEMU
-    //rsdt->table_offset_entry[3] = cpu_to_le32(hpet_addr);
+    rsdt->table_offset_entry[2] = cpu_to_le32(hpet_addr);
 #endif
+    //rsdt->table_offset_entry[3] = cpu_to_le32(ssdt_addr);
     acpi_build_table_header((struct acpi_table_header *)rsdt,
                             "RSDT", sizeof(*rsdt), 1);
 

@@ -1723,7 +1721,6 @@ void acpi_bios_init(void)
 
 #ifdef BX_QEMU
     /* HPET */
-#ifdef HPET_WORKS_IN_KVM
     memset(hpet, 0, sizeof(*hpet));
     /* Note timer_block_id value must be kept in sync with value advertised by
      * emulated hpet

@@ -1733,7 +1730,6 @@ void acpi_bios_init(void)
     acpi_build_table_header((struct  acpi_table_header *)hpet,
                              "HPET", sizeof(*hpet), 1);
 #endif
-#endif
 
 }
 

index c7945ec..47c9f89 100644
@@ -30,6 +30,7 @@
 #include "console.h"
 #include "qemu-timer.h"
 #include "hpet_emul.h"
+#include "qemu-kvm.h"
 
 //#define HPET_DEBUG
 #ifdef HPET_DEBUG

@@ -48,6 +49,43 @@ uint32_t hpet_in_legacy_mode(void)
         return 0;
 }
 
+static void hpet_kpit_enable(void)
+{
+    struct kvm_pit_state ps;
+    kvm_get_pit(kvm_context, &ps);
+    kvm_set_pit(kvm_context, &ps);
+}
+
+static void hpet_kpit_disable(void)
+{
+    struct kvm_pit_state ps;
+    kvm_get_pit(kvm_context, &ps);
+    ps.channels[0].mode = 0xff;
+    kvm_set_pit(kvm_context, &ps);
+}
+
+static void hpet_legacy_enable(void)
+{
+    if (qemu_kvm_pit_in_kernel()) {
+       hpet_kpit_disable();
+       dprintf("qemu: hpet disabled kernel pit\n");
+    } else {
+       hpet_pit_disable();
+       dprintf("qemu: hpet disabled userspace pit\n");
+    }
+}
+
+static void hpet_legacy_disable(void)
+{
+    if (qemu_kvm_pit_in_kernel()) {
+       hpet_kpit_enable();
+       dprintf("qemu: hpet enabled kernel pit\n");
+    } else {
+       hpet_pit_enable();
+       dprintf("qemu: hpet enabled userspace pit\n");
+    }
+}
+
 static uint32_t timer_int_route(struct HPETTimer *timer)
 {
     uint32_t route;

@@ -475,9 +513,9 @@ static void hpet_ram_writel(void *opaque, target_phys_addr_t addr,
                 }
                 /* i8254 and RTC are disabled when HPET is in legacy mode */
                 if (activating_bit(old_val, new_val, HPET_CFG_LEGACY)) {
-                    hpet_pit_disable();
+                    hpet_legacy_enable();
                 } else if (deactivating_bit(old_val, new_val, HPET_CFG_LEGACY)) {
-                    hpet_pit_enable();
+                    hpet_legacy_disable();
                 }
                 break;
             case HPET_CFG + 4:

@@ -560,7 +598,7 @@ static void hpet_reset(void *opaque) {
          * hpet_reset is called due to system reset. At this point control must
          * be returned to pit until SW reenables hpet.
          */
-        hpet_pit_enable();
+        hpet_legacy_disable();
     count = 1;
 }
 

index 5eacd6a..1334344 100644
@@ -5666,10 +5666,15 @@ int main(int argc, char **argv, char **envp)
     }
 
     if (kvm_enabled()) {
-       kvm_init_ap();
+        kvm_init_ap();
 #ifdef USE_KVM
         if (kvm_irqchip && !qemu_kvm_has_gsi_routing()) {
-           irq0override = 0;
+            irq0override = 0;
+            /* if kernel can't do irq routing, interrupt source
+             * override 0->2 can not be set up as required by hpet,
+             * so disable hpet.
+             */
+            no_hpet=1;
         }
 #endif
     }