Merge tag 'pull-riscv-to-apply-20230911' of https://github.com/alistair23/qemu into staging

First RISC-V PR for 8.2

 * Remove 'host' CPU from TCG
 * riscv_htif Fixup printing on big endian hosts
 * Add zmmul isa string
 * Add smepmp isa string
 * Fix page_check_range use in fault-only-first
 * Use existing lookup tables for MixColumns
 * Add RISC-V vector cryptographic instruction set support
 * Implement WARL behaviour for mcountinhibit/mcounteren
 * Add Zihintntl extension ISA string to DTS
 * Fix zfa fleq.d and fltq.d
 * Fix upper/lower mtime write calculation
 * Make rtc variable names consistent
 * Use abi type for linux-user target_ucontext
 * Add RISC-V KVM AIA Support
 * Fix riscv,pmu DT node path in the virt machine
 * Update CSR bits name for svadu extension
 * Mark zicond non-experimental
 * Fix satp_mode_finalize() when satp_mode.supported = 0
 * Fix non-KVM --enable-debug build
 * Add new extensions to hwprobe
 * Use accelerated helper for AES64KS1I
 * Allocate itrigger timers only once
 * Respect mseccfg.RLB for pmpaddrX changes
 * Align the AIA model to v1.0 ratified spec
 * Don't read the CSR in riscv_csrrw_do64

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEaukCtqfKh31tZZKWr3yVEwxTgBMFAmT+ttMACgkQr3yVEwxT
# gBN/rg/+KhOvL9xWSNb8pzlIsMQHLvndno0Sq5b9Rb/o5z1ekyYfyg6712N3JJpA
# TIfZzOIW7oYZV8gHyaBtOt8kIbrjwzGB2rpCh4blhm+yNZv7Ym9Ko6AVVzoUDo7k
# 2dWkLnC+52/l3SXGeyYMJOlgUUsQMwjD6ykDEr42P6DfVord34fpTH7ftwSasO9K
# 35qJQqhUCgB3fMzjKTYICN6Rm1UluijTjRNXUZXC0XZlr+UKw2jT/UsybbWVXyNs
# SmkRtF1MEVGvw+b8XOgA/nG1qVCWglTMcPvKjWMY+cY9WLM6/R9nXAV8OL/JPead
# v1LvROJNukfjNtDW6AOl5/svOJTRLbIrV5EO7Hlm1E4kftGmE5C+AKZZ/VT4ucUK
# XgqaHoXh26tFEymVjzbtyFnUHNv0zLuGelTnmc5Ps1byLSe4lT0dBaJy6Zizg0LE
# DpTR7s3LpyV3qB96Xf9bOMaTPsekUjD3dQI/3X634r36+YovRXapJDEDacN9whbU
# BSZc20NoM5UxVXFTbELQXolue/X2BRLxpzB+BDG8/cpu/MPgcCNiOZaVrr/pOo33
# 6rwwrBhLSCfYAXnJ52qTUEBz0Z/FnRPza8AU/uuRYRFk6JhUXIonmO6xkzsoNKuN
# QNnih/v1J+1XqUyyT2InOoAiTotzHiWgKZKaMfAhomt2j/slz+A=
# =aqcx
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 11 Sep 2023 02:42:27 EDT
# gpg:                using RSA key 6AE902B6A7CA877D6D659296AF7C95130C538013
# gpg: Good signature from "Alistair Francis <alistair@alistair23.me>" [unknown]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 6AE9 02B6 A7CA 877D 6D65  9296 AF7C 9513 0C53 8013

* tag 'pull-riscv-to-apply-20230911' of https://github.com/alistair23/qemu: (45 commits)
  target/riscv: don't read CSR in riscv_csrrw_do64
  target/riscv: Align the AIA model to v1.0 ratified spec
  target/riscv/pmp.c: respect mseccfg.RLB for pmpaddrX changes
  target/riscv: Allocate itrigger timers only once
  target/riscv: Use accelerated helper for AES64KS1I
  linux-user/riscv: Add new extensions to hwprobe
  hw/intc/riscv_aplic.c fix non-KVM --enable-debug build
  hw/riscv/virt.c: fix non-KVM --enable-debug build
  riscv: zicond: make non-experimental
  target/riscv: fix satp_mode_finalize() when satp_mode.supported = 0
  target/riscv: Update CSR bits name for svadu extension
  hw/riscv: virt: Fix riscv,pmu DT node path
  target/riscv: select KVM AIA in riscv virt machine
  target/riscv: update APLIC and IMSIC to support KVM AIA
  target/riscv: Create an KVM AIA irqchip
  target/riscv: check the in-kernel irqchip support
  target/riscv: support the AIA device emulation with KVM enabled
  linux-user/riscv: Use abi type for target_ucontext
  hw/intc: Make rtc variable names consistent
  hw/intc: Fix upper/lower mtime write calculation
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

5 files changed, 265 insertions, 209 deletions

diff --git a/hw/char/riscv_htif.c b/hw/char/riscv_htif.c
index 37d3ccc..40de6b8 100644
--- a/hw/char/riscv_htif.c
+++ b/hw/char/riscv_htif.c
@@ -30,6 +30,7 @@
 #include "qemu/timer.h"
 #include "qemu/error-report.h"
 #include "exec/address-spaces.h"
+#include "exec/tswap.h"
 #include "sysemu/dma.h"
 
 #define RISCV_DEBUG_HTIF 0
@@ -209,11 +210,11 @@ static void htif_handle_tohost_write(HTIFState *s, uint64_t val_written)
             } else {
                 uint64_t syscall[8];
                 cpu_physical_memory_read(payload, syscall, sizeof(syscall));
-                if (syscall[0] == PK_SYS_WRITE &&
-                    syscall[1] == HTIF_DEV_CONSOLE &&
-                    syscall[3] == HTIF_CONSOLE_CMD_PUTC) {
+                if (tswap64(syscall[0]) == PK_SYS_WRITE &&
+                    tswap64(syscall[1]) == HTIF_DEV_CONSOLE &&
+                    tswap64(syscall[3]) == HTIF_CONSOLE_CMD_PUTC) {
                     uint8_t ch;
-                    cpu_physical_memory_read(syscall[2], &ch, 1);
+                    cpu_physical_memory_read(tswap64(syscall[2]), &ch, 1);
                     qemu_chr_fe_write(&s->chr, &ch, 1);
                     resp = 0x100 | (uint8_t)payload;
                 } else {
@@ -232,7 +233,8 @@ static void htif_handle_tohost_write(HTIFState *s, uint64_t val_written)
             s->tohost = 0; /* clear to indicate we read */
             return;
         } else if (cmd == HTIF_CONSOLE_CMD_PUTC) {
-            qemu_chr_fe_write(&s->chr, (uint8_t *)&payload, 1);
+            uint8_t ch = (uint8_t)payload;
+            qemu_chr_fe_write(&s->chr, &ch, 1);
             resp = 0x100 | (uint8_t)payload;
         } else {
             qemu_log("HTIF device %d: unknown command\n", device);
diff --git a/hw/intc/riscv_aclint.c b/hw/intc/riscv_aclint.c
index b466a6a..25cf7a5 100644
--- a/hw/intc/riscv_aclint.c
+++ b/hw/intc/riscv_aclint.c
@@ -64,13 +64,13 @@ static void riscv_aclint_mtimer_write_timecmp(RISCVAclintMTimerState *mtimer,
     uint64_t next;
     uint64_t diff;
 
-    uint64_t rtc_r = cpu_riscv_read_rtc(mtimer);
+    uint64_t rtc = cpu_riscv_read_rtc(mtimer);
 
     /* Compute the relative hartid w.r.t the socket */
     hartid = hartid - mtimer->hartid_base;
 
     mtimer->timecmp[hartid] = value;
-    if (mtimer->timecmp[hartid] <= rtc_r) {
+    if (mtimer->timecmp[hartid] <= rtc) {
         /*
          * If we're setting an MTIMECMP value in the "past",
          * immediately raise the timer interrupt
@@ -81,7 +81,7 @@ static void riscv_aclint_mtimer_write_timecmp(RISCVAclintMTimerState *mtimer,
 
     /* otherwise, set up the future timer interrupt */
     qemu_irq_lower(mtimer->timer_irqs[hartid]);
-    diff = mtimer->timecmp[hartid] - rtc_r;
+    diff = mtimer->timecmp[hartid] - rtc;
     /* back to ns (note args switched in muldiv64) */
     uint64_t ns_diff = muldiv64(diff, NANOSECONDS_PER_SECOND, timebase_freq);
 
@@ -208,11 +208,12 @@ static void riscv_aclint_mtimer_write(void *opaque, hwaddr addr,
         return;
     } else if (addr == mtimer->time_base || addr == mtimer->time_base + 4) {
         uint64_t rtc_r = cpu_riscv_read_rtc_raw(mtimer->timebase_freq);
+        uint64_t rtc = cpu_riscv_read_rtc(mtimer);
 
         if (addr == mtimer->time_base) {
             if (size == 4) {
                 /* time_lo for RV32/RV64 */
-                mtimer->time_delta = ((rtc_r & ~0xFFFFFFFFULL) | value) - rtc_r;
+                mtimer->time_delta = ((rtc & ~0xFFFFFFFFULL) | value) - rtc_r;
             } else {
                 /* time for RV64 */
                 mtimer->time_delta = value - rtc_r;
@@ -220,7 +221,7 @@ static void riscv_aclint_mtimer_write(void *opaque, hwaddr addr,
         } else {
             if (size == 4) {
                 /* time_hi for RV32/RV64 */
-                mtimer->time_delta = (value << 32 | (rtc_r & 0xFFFFFFFF)) - rtc_r;
+                mtimer->time_delta = (value << 32 | (rtc & 0xFFFFFFFF)) - rtc_r;
             } else {
                 qemu_log_mask(LOG_GUEST_ERROR,
                               "aclint-mtimer: invalid time_hi write: %08x",
diff --git a/hw/intc/riscv_aplic.c b/hw/intc/riscv_aplic.c
index 4bdc6a5..99aae8c 100644
--- a/hw/intc/riscv_aplic.c
+++ b/hw/intc/riscv_aplic.c
@@ -31,6 +31,8 @@
 #include "hw/irq.h"
 #include "target/riscv/cpu.h"
 #include "sysemu/sysemu.h"
+#include "sysemu/kvm.h"
+#include "kvm_riscv.h"
 #include "migration/vmstate.h"
 
 #define APLIC_MAX_IDC                  (1UL << 14)
@@ -148,6 +150,15 @@
 
 #define APLIC_IDC_CLAIMI               0x1c
 
+/*
+ * KVM AIA only supports APLIC MSI, fallback to QEMU emulation if we want to use
+ * APLIC Wired.
+ */
+static bool is_kvm_aia(bool msimode)
+{
+    return kvm_irqchip_in_kernel() && msimode;
+}
+
 static uint32_t riscv_aplic_read_input_word(RISCVAPLICState *aplic,
                                             uint32_t word)
 {
@@ -801,29 +812,35 @@ static void riscv_aplic_realize(DeviceState *dev, Error **errp)
     uint32_t i;
     RISCVAPLICState *aplic = RISCV_APLIC(dev);
 
-    aplic->bitfield_words = (aplic->num_irqs + 31) >> 5;
-    aplic->sourcecfg = g_new0(uint32_t, aplic->num_irqs);
-    aplic->state = g_new0(uint32_t, aplic->num_irqs);
-    aplic->target = g_new0(uint32_t, aplic->num_irqs);
-    if (!aplic->msimode) {
-        for (i = 0; i < aplic->num_irqs; i++) {
-            aplic->target[i] = 1;
+    if (!is_kvm_aia(aplic->msimode)) {
+        aplic->bitfield_words = (aplic->num_irqs + 31) >> 5;
+        aplic->sourcecfg = g_new0(uint32_t, aplic->num_irqs);
+        aplic->state = g_new0(uint32_t, aplic->num_irqs);
+        aplic->target = g_new0(uint32_t, aplic->num_irqs);
+        if (!aplic->msimode) {
+            for (i = 0; i < aplic->num_irqs; i++) {
+                aplic->target[i] = 1;
+            }
         }
-    }
-    aplic->idelivery = g_new0(uint32_t, aplic->num_harts);
-    aplic->iforce = g_new0(uint32_t, aplic->num_harts);
-    aplic->ithreshold = g_new0(uint32_t, aplic->num_harts);
+        aplic->idelivery = g_new0(uint32_t, aplic->num_harts);
+        aplic->iforce = g_new0(uint32_t, aplic->num_harts);
+        aplic->ithreshold = g_new0(uint32_t, aplic->num_harts);
 
-    memory_region_init_io(&aplic->mmio, OBJECT(dev), &riscv_aplic_ops, aplic,
-                          TYPE_RISCV_APLIC, aplic->aperture_size);
-    sysbus_init_mmio(SYS_BUS_DEVICE(dev), &aplic->mmio);
+        memory_region_init_io(&aplic->mmio, OBJECT(dev), &riscv_aplic_ops,
+                              aplic, TYPE_RISCV_APLIC, aplic->aperture_size);
+        sysbus_init_mmio(SYS_BUS_DEVICE(dev), &aplic->mmio);
+    }
 
     /*
      * Only root APLICs have hardware IRQ lines. All non-root APLICs
      * have IRQ lines delegated by their parent APLIC.
      */
     if (!aplic->parent) {
-        qdev_init_gpio_in(dev, riscv_aplic_request, aplic->num_irqs);
+        if (kvm_enabled() && is_kvm_aia(aplic->msimode)) {
+            qdev_init_gpio_in(dev, riscv_kvm_aplic_request, aplic->num_irqs);
+        } else {
+            qdev_init_gpio_in(dev, riscv_aplic_request, aplic->num_irqs);
+        }
     }
 
     /* Create output IRQ lines for non-MSI mode */
@@ -958,7 +975,10 @@ DeviceState *riscv_aplic_create(hwaddr addr, hwaddr size,
     qdev_prop_set_bit(dev, "mmode", mmode);
 
     sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal);
-    sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, addr);
+
+    if (!is_kvm_aia(msimode)) {
+        sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, addr);
+    }
 
     if (parent) {
         riscv_aplic_add_child(parent, dev);
diff --git a/hw/intc/riscv_imsic.c b/hw/intc/riscv_imsic.c
index fea3385..760dbdd 100644
--- a/hw/intc/riscv_imsic.c
+++ b/hw/intc/riscv_imsic.c
@@ -32,6 +32,7 @@
 #include "target/riscv/cpu.h"
 #include "target/riscv/cpu_bits.h"
 #include "sysemu/sysemu.h"
+#include "sysemu/kvm.h"
 #include "migration/vmstate.h"
 
 #define IMSIC_MMIO_PAGE_LE             0x00
@@ -283,6 +284,20 @@ static void riscv_imsic_write(void *opaque, hwaddr addr, uint64_t value,
         goto err;
     }
 
+#if defined(CONFIG_KVM)
+    if (kvm_irqchip_in_kernel()) {
+        struct kvm_msi msi;
+
+        msi.address_lo = extract64(imsic->mmio.addr + addr, 0, 32);
+        msi.address_hi = extract64(imsic->mmio.addr + addr, 32, 32);
+        msi.data = le32_to_cpu(value);
+
+        kvm_vm_ioctl(kvm_state, KVM_SIGNAL_MSI, &msi);
+
+        return;
+    }
+#endif
+
     /* Writes only supported for MSI little-endian registers */
     page = addr >> IMSIC_MMIO_PAGE_SHIFT;
     if ((addr & (IMSIC_MMIO_PAGE_SZ - 1)) == IMSIC_MMIO_PAGE_LE) {
@@ -320,10 +335,12 @@ static void riscv_imsic_realize(DeviceState *dev, Error **errp)
     CPUState *cpu = cpu_by_arch_id(imsic->hartid);
     CPURISCVState *env = cpu ? cpu->env_ptr : NULL;
 
-    imsic->num_eistate = imsic->num_pages * imsic->num_irqs;
-    imsic->eidelivery = g_new0(uint32_t, imsic->num_pages);
-    imsic->eithreshold = g_new0(uint32_t, imsic->num_pages);
-    imsic->eistate = g_new0(uint32_t, imsic->num_eistate);
+    if (!kvm_irqchip_in_kernel()) {
+        imsic->num_eistate = imsic->num_pages * imsic->num_irqs;
+        imsic->eidelivery = g_new0(uint32_t, imsic->num_pages);
+        imsic->eithreshold = g_new0(uint32_t, imsic->num_pages);
+        imsic->eistate = g_new0(uint32_t, imsic->num_eistate);
+    }
 
     memory_region_init_io(&imsic->mmio, OBJECT(dev), &riscv_imsic_ops,
                           imsic, TYPE_RISCV_IMSIC,
diff --git a/hw/riscv/virt.c b/hw/riscv/virt.c
index a5ac3ab..5edc1d9 100644
--- a/hw/riscv/virt.c
+++ b/hw/riscv/virt.c
@@ -35,6 +35,7 @@
 #include "hw/riscv/virt.h"
 #include "hw/riscv/boot.h"
 #include "hw/riscv/numa.h"
+#include "kvm_riscv.h"
 #include "hw/intc/riscv_aclint.h"
 #include "hw/intc/riscv_aplic.h"
 #include "hw/intc/riscv_imsic.h"
@@ -75,6 +76,12 @@
 #error "Can't accommodate all IMSIC groups in address space"
 #endif
 
+/* KVM AIA only supports APLIC MSI. APLIC Wired is always emulated by QEMU. */
+static bool virt_use_kvm_aia(RISCVVirtState *s)
+{
+    return kvm_irqchip_in_kernel() && s->aia_type == VIRT_AIA_TYPE_APLIC_IMSIC;
+}
+
 static const MemMapEntry virt_memmap[] = {
     [VIRT_DEBUG] =        {        0x0,         0x100 },
     [VIRT_MROM] =         {     0x1000,        0xf000 },
@@ -516,79 +523,28 @@ static uint32_t imsic_num_bits(uint32_t count)
     return ret;
 }
 
-static void create_fdt_imsic(RISCVVirtState *s, const MemMapEntry *memmap,
-                             uint32_t *phandle, uint32_t *intc_phandles,
-                             uint32_t *msi_m_phandle, uint32_t *msi_s_phandle)
+static void create_fdt_one_imsic(RISCVVirtState *s, hwaddr base_addr,
+                                 uint32_t *intc_phandles, uint32_t msi_phandle,
+                                 bool m_mode, uint32_t imsic_guest_bits)
 {
     int cpu, socket;
     char *imsic_name;
     MachineState *ms = MACHINE(s);
     int socket_count = riscv_socket_count(ms);
-    uint32_t imsic_max_hart_per_socket, imsic_guest_bits;
+    uint32_t imsic_max_hart_per_socket;
     uint32_t *imsic_cells, *imsic_regs, imsic_addr, imsic_size;
 
-    *msi_m_phandle = (*phandle)++;
-    *msi_s_phandle = (*phandle)++;
     imsic_cells = g_new0(uint32_t, ms->smp.cpus * 2);
     imsic_regs = g_new0(uint32_t, socket_count * 4);
 
-    /* M-level IMSIC node */
     for (cpu = 0; cpu < ms->smp.cpus; cpu++) {
         imsic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]);
-        imsic_cells[cpu * 2 + 1] = cpu_to_be32(IRQ_M_EXT);
-    }
-    imsic_max_hart_per_socket = 0;
-    for (socket = 0; socket < socket_count; socket++) {
-        imsic_addr = memmap[VIRT_IMSIC_M].base +
-                     socket * VIRT_IMSIC_GROUP_MAX_SIZE;
-        imsic_size = IMSIC_HART_SIZE(0) * s->soc[socket].num_harts;
-        imsic_regs[socket * 4 + 0] = 0;
-        imsic_regs[socket * 4 + 1] = cpu_to_be32(imsic_addr);
-        imsic_regs[socket * 4 + 2] = 0;
-        imsic_regs[socket * 4 + 3] = cpu_to_be32(imsic_size);
-        if (imsic_max_hart_per_socket < s->soc[socket].num_harts) {
-            imsic_max_hart_per_socket = s->soc[socket].num_harts;
-        }
-    }
-    imsic_name = g_strdup_printf("/soc/imsics@%lx",
-        (unsigned long)memmap[VIRT_IMSIC_M].base);
-    qemu_fdt_add_subnode(ms->fdt, imsic_name);
-    qemu_fdt_setprop_string(ms->fdt, imsic_name, "compatible",
-        "riscv,imsics");
-    qemu_fdt_setprop_cell(ms->fdt, imsic_name, "#interrupt-cells",
-        FDT_IMSIC_INT_CELLS);
-    qemu_fdt_setprop(ms->fdt, imsic_name, "interrupt-controller",
-        NULL, 0);
-    qemu_fdt_setprop(ms->fdt, imsic_name, "msi-controller",
-        NULL, 0);
-    qemu_fdt_setprop(ms->fdt, imsic_name, "interrupts-extended",
-        imsic_cells, ms->smp.cpus * sizeof(uint32_t) * 2);
-    qemu_fdt_setprop(ms->fdt, imsic_name, "reg", imsic_regs,
-        socket_count * sizeof(uint32_t) * 4);
-    qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,num-ids",
-        VIRT_IRQCHIP_NUM_MSIS);
-    if (socket_count > 1) {
-        qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,hart-index-bits",
-            imsic_num_bits(imsic_max_hart_per_socket));
-        qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,group-index-bits",
-            imsic_num_bits(socket_count));
-        qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,group-index-shift",
-            IMSIC_MMIO_GROUP_MIN_SHIFT);
+        imsic_cells[cpu * 2 + 1] = cpu_to_be32(m_mode ? IRQ_M_EXT : IRQ_S_EXT);
     }
-    qemu_fdt_setprop_cell(ms->fdt, imsic_name, "phandle", *msi_m_phandle);
 
-    g_free(imsic_name);
-
-    /* S-level IMSIC node */
-    for (cpu = 0; cpu < ms->smp.cpus; cpu++) {
-        imsic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]);
-        imsic_cells[cpu * 2 + 1] = cpu_to_be32(IRQ_S_EXT);
-    }
-    imsic_guest_bits = imsic_num_bits(s->aia_guests + 1);
     imsic_max_hart_per_socket = 0;
     for (socket = 0; socket < socket_count; socket++) {
-        imsic_addr = memmap[VIRT_IMSIC_S].base +
-                     socket * VIRT_IMSIC_GROUP_MAX_SIZE;
+        imsic_addr = base_addr + socket * VIRT_IMSIC_GROUP_MAX_SIZE;
         imsic_size = IMSIC_HART_SIZE(imsic_guest_bits) *
                      s->soc[socket].num_harts;
         imsic_regs[socket * 4 + 0] = 0;
@@ -599,119 +555,151 @@ static void create_fdt_imsic(RISCVVirtState *s, const MemMapEntry *memmap,
             imsic_max_hart_per_socket = s->soc[socket].num_harts;
         }
     }
-    imsic_name = g_strdup_printf("/soc/imsics@%lx",
-        (unsigned long)memmap[VIRT_IMSIC_S].base);
+
+    imsic_name = g_strdup_printf("/soc/imsics@%lx", (unsigned long)base_addr);
     qemu_fdt_add_subnode(ms->fdt, imsic_name);
-    qemu_fdt_setprop_string(ms->fdt, imsic_name, "compatible",
-        "riscv,imsics");
+    qemu_fdt_setprop_string(ms->fdt, imsic_name, "compatible", "riscv,imsics");
     qemu_fdt_setprop_cell(ms->fdt, imsic_name, "#interrupt-cells",
-        FDT_IMSIC_INT_CELLS);
-    qemu_fdt_setprop(ms->fdt, imsic_name, "interrupt-controller",
-        NULL, 0);
-    qemu_fdt_setprop(ms->fdt, imsic_name, "msi-controller",
-        NULL, 0);
+                          FDT_IMSIC_INT_CELLS);
+    qemu_fdt_setprop(ms->fdt, imsic_name, "interrupt-controller", NULL, 0);
+    qemu_fdt_setprop(ms->fdt, imsic_name, "msi-controller", NULL, 0);
     qemu_fdt_setprop(ms->fdt, imsic_name, "interrupts-extended",
-        imsic_cells, ms->smp.cpus * sizeof(uint32_t) * 2);
+                     imsic_cells, ms->smp.cpus * sizeof(uint32_t) * 2);
     qemu_fdt_setprop(ms->fdt, imsic_name, "reg", imsic_regs,
-        socket_count * sizeof(uint32_t) * 4);
+                     socket_count * sizeof(uint32_t) * 4);
     qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,num-ids",
-        VIRT_IRQCHIP_NUM_MSIS);
+                     VIRT_IRQCHIP_NUM_MSIS);
+
     if (imsic_guest_bits) {
         qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,guest-index-bits",
-            imsic_guest_bits);
+                              imsic_guest_bits);
     }
+
     if (socket_count > 1) {
         qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,hart-index-bits",
-            imsic_num_bits(imsic_max_hart_per_socket));
+                              imsic_num_bits(imsic_max_hart_per_socket));
         qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,group-index-bits",
-            imsic_num_bits(socket_count));
+                              imsic_num_bits(socket_count));
         qemu_fdt_setprop_cell(ms->fdt, imsic_name, "riscv,group-index-shift",
-            IMSIC_MMIO_GROUP_MIN_SHIFT);
+                              IMSIC_MMIO_GROUP_MIN_SHIFT);
     }
-    qemu_fdt_setprop_cell(ms->fdt, imsic_name, "phandle", *msi_s_phandle);
-    g_free(imsic_name);
+    qemu_fdt_setprop_cell(ms->fdt, imsic_name, "phandle", msi_phandle);
 
+    g_free(imsic_name);
     g_free(imsic_regs);
     g_free(imsic_cells);
 }
 
-static void create_fdt_socket_aplic(RISCVVirtState *s,
-                                    const MemMapEntry *memmap, int socket,
-                                    uint32_t msi_m_phandle,
-                                    uint32_t msi_s_phandle,
-                                    uint32_t *phandle,
-                                    uint32_t *intc_phandles,
-                                    uint32_t *aplic_phandles)
+static void create_fdt_imsic(RISCVVirtState *s, const MemMapEntry *memmap,
+                             uint32_t *phandle, uint32_t *intc_phandles,
+                             uint32_t *msi_m_phandle, uint32_t *msi_s_phandle)
+{
+    *msi_m_phandle = (*phandle)++;
+    *msi_s_phandle = (*phandle)++;
+
+    if (!kvm_enabled()) {
+        /* M-level IMSIC node */
+        create_fdt_one_imsic(s, memmap[VIRT_IMSIC_M].base, intc_phandles,
+                             *msi_m_phandle, true, 0);
+    }
+
+    /* S-level IMSIC node */
+    create_fdt_one_imsic(s, memmap[VIRT_IMSIC_S].base, intc_phandles,
+                         *msi_s_phandle, false,
+                         imsic_num_bits(s->aia_guests + 1));
+
+}
+
+static void create_fdt_one_aplic(RISCVVirtState *s, int socket,
+                                 unsigned long aplic_addr, uint32_t aplic_size,
+                                 uint32_t msi_phandle,
+                                 uint32_t *intc_phandles,
+                                 uint32_t aplic_phandle,
+                                 uint32_t aplic_child_phandle,
+                                 bool m_mode, int num_harts)
 {
     int cpu;
     char *aplic_name;
     uint32_t *aplic_cells;
-    unsigned long aplic_addr;
     MachineState *ms = MACHINE(s);
-    uint32_t aplic_m_phandle, aplic_s_phandle;
 
-    aplic_m_phandle = (*phandle)++;
-    aplic_s_phandle = (*phandle)++;
-    aplic_cells = g_new0(uint32_t, s->soc[socket].num_harts * 2);
+    aplic_cells = g_new0(uint32_t, num_harts * 2);
 
-    /* M-level APLIC node */
-    for (cpu = 0; cpu < s->soc[socket].num_harts; cpu++) {
+    for (cpu = 0; cpu < num_harts; cpu++) {
         aplic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]);
-        aplic_cells[cpu * 2 + 1] = cpu_to_be32(IRQ_M_EXT);
+        aplic_cells[cpu * 2 + 1] = cpu_to_be32(m_mode ? IRQ_M_EXT : IRQ_S_EXT);
     }
-    aplic_addr = memmap[VIRT_APLIC_M].base +
-                 (memmap[VIRT_APLIC_M].size * socket);
+
     aplic_name = g_strdup_printf("/soc/aplic@%lx", aplic_addr);
     qemu_fdt_add_subnode(ms->fdt, aplic_name);
     qemu_fdt_setprop_string(ms->fdt, aplic_name, "compatible", "riscv,aplic");
     qemu_fdt_setprop_cell(ms->fdt, aplic_name,
-        "#interrupt-cells", FDT_APLIC_INT_CELLS);
+                          "#interrupt-cells", FDT_APLIC_INT_CELLS);
     qemu_fdt_setprop(ms->fdt, aplic_name, "interrupt-controller", NULL, 0);
+
     if (s->aia_type == VIRT_AIA_TYPE_APLIC) {
         qemu_fdt_setprop(ms->fdt, aplic_name, "interrupts-extended",
-            aplic_cells, s->soc[socket].num_harts * sizeof(uint32_t) * 2);
+                         aplic_cells, num_harts * sizeof(uint32_t) * 2);
     } else {
-        qemu_fdt_setprop_cell(ms->fdt, aplic_name, "msi-parent",
-            msi_m_phandle);
+        qemu_fdt_setprop_cell(ms->fdt, aplic_name, "msi-parent", msi_phandle);
     }
+
     qemu_fdt_setprop_cells(ms->fdt, aplic_name, "reg",
-        0x0, aplic_addr, 0x0, memmap[VIRT_APLIC_M].size);
+                           0x0, aplic_addr, 0x0, aplic_size);
     qemu_fdt_setprop_cell(ms->fdt, aplic_name, "riscv,num-sources",
-        VIRT_IRQCHIP_NUM_SOURCES);
-    qemu_fdt_setprop_cell(ms->fdt, aplic_name, "riscv,children",
-        aplic_s_phandle);
-    qemu_fdt_setprop_cells(ms->fdt, aplic_name, "riscv,delegate",
-        aplic_s_phandle, 0x1, VIRT_IRQCHIP_NUM_SOURCES);
+                          VIRT_IRQCHIP_NUM_SOURCES);
+
+    if (aplic_child_phandle) {
+        qemu_fdt_setprop_cell(ms->fdt, aplic_name, "riscv,children",
+                              aplic_child_phandle);
+        qemu_fdt_setprop_cells(ms->fdt, aplic_name, "riscv,delegate",
+                               aplic_child_phandle, 0x1,
+                               VIRT_IRQCHIP_NUM_SOURCES);
+    }
+
     riscv_socket_fdt_write_id(ms, aplic_name, socket);
-    qemu_fdt_setprop_cell(ms->fdt, aplic_name, "phandle", aplic_m_phandle);
+    qemu_fdt_setprop_cell(ms->fdt, aplic_name, "phandle", aplic_phandle);
+
     g_free(aplic_name);
+    g_free(aplic_cells);
+}
 
-    /* S-level APLIC node */
-    for (cpu = 0; cpu < s->soc[socket].num_harts; cpu++) {
-        aplic_cells[cpu * 2 + 0] = cpu_to_be32(intc_phandles[cpu]);
-        aplic_cells[cpu * 2 + 1] = cpu_to_be32(IRQ_S_EXT);
+static void create_fdt_socket_aplic(RISCVVirtState *s,
+                                    const MemMapEntry *memmap, int socket,
+                                    uint32_t msi_m_phandle,
+                                    uint32_t msi_s_phandle,
+                                    uint32_t *phandle,
+                                    uint32_t *intc_phandles,
+                                    uint32_t *aplic_phandles,
+                                    int num_harts)
+{
+    char *aplic_name;
+    unsigned long aplic_addr;
+    MachineState *ms = MACHINE(s);
+    uint32_t aplic_m_phandle, aplic_s_phandle;
+
+    aplic_m_phandle = (*phandle)++;
+    aplic_s_phandle = (*phandle)++;
+
+    if (!kvm_enabled()) {
+        /* M-level APLIC node */
+        aplic_addr = memmap[VIRT_APLIC_M].base +
+                     (memmap[VIRT_APLIC_M].size * socket);
+        create_fdt_one_aplic(s, socket, aplic_addr, memmap[VIRT_APLIC_M].size,
+                             msi_m_phandle, intc_phandles,
+                             aplic_m_phandle, aplic_s_phandle,
+                             true, num_harts);
     }
+
+    /* S-level APLIC node */
     aplic_addr = memmap[VIRT_APLIC_S].base +
                  (memmap[VIRT_APLIC_S].size * socket);
+    create_fdt_one_aplic(s, socket, aplic_addr, memmap[VIRT_APLIC_S].size,
+                         msi_s_phandle, intc_phandles,
+                         aplic_s_phandle, 0,
+                         false, num_harts);
+
     aplic_name = g_strdup_printf("/soc/aplic@%lx", aplic_addr);
-    qemu_fdt_add_subnode(ms->fdt, aplic_name);
-    qemu_fdt_setprop_string(ms->fdt, aplic_name, "compatible", "riscv,aplic");
-    qemu_fdt_setprop_cell(ms->fdt, aplic_name,
-        "#interrupt-cells", FDT_APLIC_INT_CELLS);
-    qemu_fdt_setprop(ms->fdt, aplic_name, "interrupt-controller", NULL, 0);
-    if (s->aia_type == VIRT_AIA_TYPE_APLIC) {
-        qemu_fdt_setprop(ms->fdt, aplic_name, "interrupts-extended",
-            aplic_cells, s->soc[socket].num_harts * sizeof(uint32_t) * 2);
-    } else {
-        qemu_fdt_setprop_cell(ms->fdt, aplic_name, "msi-parent",
-            msi_s_phandle);
-    }
-    qemu_fdt_setprop_cells(ms->fdt, aplic_name, "reg",
-        0x0, aplic_addr, 0x0, memmap[VIRT_APLIC_S].size);
-    qemu_fdt_setprop_cell(ms->fdt, aplic_name, "riscv,num-sources",
-        VIRT_IRQCHIP_NUM_SOURCES);
-    riscv_socket_fdt_write_id(ms, aplic_name, socket);
-    qemu_fdt_setprop_cell(ms->fdt, aplic_name, "phandle", aplic_s_phandle);
 
     if (!socket) {
         platform_bus_add_all_fdt_nodes(ms->fdt, aplic_name,
@@ -722,7 +710,6 @@ static void create_fdt_socket_aplic(RISCVVirtState *s,
 
     g_free(aplic_name);
 
-    g_free(aplic_cells);
     aplic_phandles[socket] = aplic_s_phandle;
 }
 
@@ -732,7 +719,7 @@ static void create_fdt_pmu(RISCVVirtState *s)
     MachineState *ms = MACHINE(s);
     RISCVCPU hart = s->soc[0].harts[0];
 
-    pmu_name = g_strdup_printf("/soc/pmu");
+    pmu_name = g_strdup_printf("/pmu");
     qemu_fdt_add_subnode(ms->fdt, pmu_name);
     qemu_fdt_setprop_string(ms->fdt, pmu_name, "compatible", "riscv,pmu");
     riscv_pmu_generate_fdt_node(ms->fdt, hart.cfg.pmu_num, pmu_name);
@@ -794,34 +781,51 @@ static void create_fdt_sockets(RISCVVirtState *s, const MemMapEntry *memmap,
         *msi_pcie_phandle = msi_s_phandle;
     }
 
-    phandle_pos = ms->smp.cpus;
-    for (socket = (socket_count - 1); socket >= 0; socket--) {
-        phandle_pos -= s->soc[socket].num_harts;
-
-        if (s->aia_type == VIRT_AIA_TYPE_NONE) {
-            create_fdt_socket_plic(s, memmap, socket, phandle,
-                &intc_phandles[phandle_pos], xplic_phandles);
-        } else {
-            create_fdt_socket_aplic(s, memmap, socket,
-                msi_m_phandle, msi_s_phandle, phandle,
-                &intc_phandles[phandle_pos], xplic_phandles);
+    /* KVM AIA only has one APLIC instance */
+    if (kvm_enabled() && virt_use_kvm_aia(s)) {
+        create_fdt_socket_aplic(s, memmap, 0,
+                                msi_m_phandle, msi_s_phandle, phandle,
+                                &intc_phandles[0], xplic_phandles,
+                                ms->smp.cpus);
+    } else {
+        phandle_pos = ms->smp.cpus;
+        for (socket = (socket_count - 1); socket >= 0; socket--) {
+            phandle_pos -= s->soc[socket].num_harts;
+
+            if (s->aia_type == VIRT_AIA_TYPE_NONE) {
+                create_fdt_socket_plic(s, memmap, socket, phandle,
+                                       &intc_phandles[phandle_pos],
+                                       xplic_phandles);
+            } else {
+                create_fdt_socket_aplic(s, memmap, socket,
+                                        msi_m_phandle, msi_s_phandle, phandle,
+                                        &intc_phandles[phandle_pos],
+                                        xplic_phandles,
+                                        s->soc[socket].num_harts);
+            }
         }
     }
 
     g_free(intc_phandles);
 
-    for (socket = 0; socket < socket_count; socket++) {
-        if (socket == 0) {
-            *irq_mmio_phandle = xplic_phandles[socket];
-            *irq_virtio_phandle = xplic_phandles[socket];
-            *irq_pcie_phandle = xplic_phandles[socket];
-        }
-        if (socket == 1) {
-            *irq_virtio_phandle = xplic_phandles[socket];
-            *irq_pcie_phandle = xplic_phandles[socket];
-        }
-        if (socket == 2) {
-            *irq_pcie_phandle = xplic_phandles[socket];
+    if (kvm_enabled() && virt_use_kvm_aia(s)) {
+        *irq_mmio_phandle = xplic_phandles[0];
+        *irq_virtio_phandle = xplic_phandles[0];
+        *irq_pcie_phandle = xplic_phandles[0];
+    } else {
+        for (socket = 0; socket < socket_count; socket++) {
+            if (socket == 0) {
+                *irq_mmio_phandle = xplic_phandles[socket];
+                *irq_virtio_phandle = xplic_phandles[socket];
+                *irq_pcie_phandle = xplic_phandles[socket];
+            }
+            if (socket == 1) {
+                *irq_virtio_phandle = xplic_phandles[socket];
+                *irq_pcie_phandle = xplic_phandles[socket];
+            }
+            if (socket == 2) {
+                *irq_pcie_phandle = xplic_phandles[socket];
+            }
         }
     }
 
@@ -1163,16 +1167,20 @@ static DeviceState *virt_create_aia(RISCVVirtAIAType aia_type, int aia_guests,
     int i;
     hwaddr addr;
     uint32_t guest_bits;
-    DeviceState *aplic_m;
-    bool msimode = (aia_type == VIRT_AIA_TYPE_APLIC_IMSIC) ? true : false;
+    DeviceState *aplic_s = NULL;
+    DeviceState *aplic_m = NULL;
+    bool msimode = aia_type == VIRT_AIA_TYPE_APLIC_IMSIC;
 
     if (msimode) {
-        /* Per-socket M-level IMSICs */
-        addr = memmap[VIRT_IMSIC_M].base + socket * VIRT_IMSIC_GROUP_MAX_SIZE;
-        for (i = 0; i < hart_count; i++) {
-            riscv_imsic_create(addr + i * IMSIC_HART_SIZE(0),
-                               base_hartid + i, true, 1,
-                               VIRT_IRQCHIP_NUM_MSIS);
+        if (!kvm_enabled()) {
+            /* Per-socket M-level IMSICs */
+            addr = memmap[VIRT_IMSIC_M].base +
+                   socket * VIRT_IMSIC_GROUP_MAX_SIZE;
+            for (i = 0; i < hart_count; i++) {
+                riscv_imsic_create(addr + i * IMSIC_HART_SIZE(0),
+                                   base_hartid + i, true, 1,
+                                   VIRT_IRQCHIP_NUM_MSIS);
+            }
         }
 
         /* Per-socket S-level IMSICs */
@@ -1185,29 +1193,29 @@ static DeviceState *virt_create_aia(RISCVVirtAIAType aia_type, int aia_guests,
         }
     }
 
-    /* Per-socket M-level APLIC */
-    aplic_m = riscv_aplic_create(
-        memmap[VIRT_APLIC_M].base + socket * memmap[VIRT_APLIC_M].size,
-        memmap[VIRT_APLIC_M].size,
-        (msimode) ? 0 : base_hartid,
-        (msimode) ? 0 : hart_count,
-        VIRT_IRQCHIP_NUM_SOURCES,
-        VIRT_IRQCHIP_NUM_PRIO_BITS,
-        msimode, true, NULL);
-
-    if (aplic_m) {
-        /* Per-socket S-level APLIC */
-        riscv_aplic_create(
-            memmap[VIRT_APLIC_S].base + socket * memmap[VIRT_APLIC_S].size,
-            memmap[VIRT_APLIC_S].size,
-            (msimode) ? 0 : base_hartid,
-            (msimode) ? 0 : hart_count,
-            VIRT_IRQCHIP_NUM_SOURCES,
-            VIRT_IRQCHIP_NUM_PRIO_BITS,
-            msimode, false, aplic_m);
+    if (!kvm_enabled()) {
+        /* Per-socket M-level APLIC */
+        aplic_m = riscv_aplic_create(memmap[VIRT_APLIC_M].base +
+                                     socket * memmap[VIRT_APLIC_M].size,
+                                     memmap[VIRT_APLIC_M].size,
+                                     (msimode) ? 0 : base_hartid,
+                                     (msimode) ? 0 : hart_count,
+                                     VIRT_IRQCHIP_NUM_SOURCES,
+                                     VIRT_IRQCHIP_NUM_PRIO_BITS,
+                                     msimode, true, NULL);
     }
 
-    return aplic_m;
+    /* Per-socket S-level APLIC */
+    aplic_s = riscv_aplic_create(memmap[VIRT_APLIC_S].base +
+                                 socket * memmap[VIRT_APLIC_S].size,
+                                 memmap[VIRT_APLIC_S].size,
+                                 (msimode) ? 0 : base_hartid,
+                                 (msimode) ? 0 : hart_count,
+                                 VIRT_IRQCHIP_NUM_SOURCES,
+                                 VIRT_IRQCHIP_NUM_PRIO_BITS,
+                                 msimode, false, aplic_m);
+
+    return kvm_enabled() ? aplic_s : aplic_m;
 }
 
 static void create_platform_bus(RISCVVirtState *s, DeviceState *irqchip)
@@ -1453,6 +1461,14 @@ static void virt_machine_init(MachineState *machine)
         }
     }
 
+    if (kvm_enabled() && virt_use_kvm_aia(s)) {
+        kvm_riscv_aia_create(machine, IMSIC_MMIO_GROUP_MIN_SHIFT,
+                             VIRT_IRQCHIP_NUM_SOURCES, VIRT_IRQCHIP_NUM_MSIS,
+                             memmap[VIRT_APLIC_S].base,
+                             memmap[VIRT_IMSIC_S].base,
+                             s->aia_guests);
+    }
+
     if (riscv_is_32bit(&s->soc[0])) {
 #if HOST_LONG_BITS == 64
         /* limit RAM size in a 32-bit system */