Merge tag 'pull-loongarch-20240523' of https://gitlab.com/gaosong/qemu into staging

pull-loongarch-20240523

# -----BEGIN PGP SIGNATURE-----
#
# iLMEAAEKAB0WIQS4/x2g0v3LLaCcbCxAov/yOSY+3wUCZk6fPgAKCRBAov/yOSY+
# 35rwA/98G/tODhR2PAl7qZr6+6z8vazkiT4iNNHgxnw/T2TKsh2YONe+2gtKhTa1
# HKYANMykWTxOtBZeCYY9Z5QNj8DuC3xKc1zY1pC1AwRcflsMlGz0WoAC78Gbl9TC
# PBCwyu01hsFoYpIstH/dOGbNsR2OFRLnnGUVFUKtPuS3O+59hg==
# =OzUv
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 22 May 2024 06:43:26 PM PDT
# gpg:                using RSA key B8FF1DA0D2FDCB2DA09C6C2C40A2FFF239263EDF
# gpg: Good signature from "Song Gao <m17746591750@163.com>" [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: B8FF 1DA0 D2FD CB2D A09C  6C2C 40A2 FFF2 3926 3EDF

* tag 'pull-loongarch-20240523' of https://gitlab.com/gaosong/qemu:
  hw/loongarch/virt: Fix FDT memory node address width
  target/loongarch: Add loongarch vector property unconditionally
  hw/loongarch: Remove minimum and default memory size
  hw/loongarch: Refine system dram memory region
  hw/loongarch: Refine fwcfg memory map
  hw/loongarch: Refine fadt memory table for numa memory
  hw/loongarch: Refine acpi srat table for numa memory
  hw/loongarch: Add VM mode in IOCSR feature register in kvm mode
  target/loongarch/kvm: fpu save the vreg registers high 192bit
  target/loongarch/kvm: Fix VM recovery from disk failures

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

5 files changed, 176 insertions, 87 deletions

diff --git a/hw/loongarch/acpi-build.c b/hw/loongarch/acpi-build.c
index 5ef010d4da..af45ce526d 100644
--- a/hw/loongarch/acpi-build.c
+++ b/hw/loongarch/acpi-build.c
@@ -166,8 +166,9 @@ static void
 build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
 {
     int i, arch_id, node_id;
-    uint64_t mem_len, mem_base;
-    int nb_numa_nodes = machine->numa_state->num_nodes;
+    hwaddr len, base, gap;
+    NodeInfo *numa_info;
+    int nodes, nb_numa_nodes = machine->numa_state->num_nodes;
     LoongArchVirtMachineState *lvms = LOONGARCH_VIRT_MACHINE(machine);
     MachineClass *mc = MACHINE_GET_CLASS(lvms);
     const CPUArchIdList *arch_ids = mc->possible_cpu_arch_ids(machine);
@@ -196,35 +197,44 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
         build_append_int_noprefix(table_data, 0, 4); /* Reserved */
     }
 
-    /* Node0 */
-    build_srat_memory(table_data, VIRT_LOWMEM_BASE, VIRT_LOWMEM_SIZE,
-                      0, MEM_AFFINITY_ENABLED);
-    mem_base = VIRT_HIGHMEM_BASE;
-    if (!nb_numa_nodes) {
-        mem_len = machine->ram_size - VIRT_LOWMEM_SIZE;
-    } else {
-        mem_len = machine->numa_state->nodes[0].node_mem - VIRT_LOWMEM_SIZE;
+    base = VIRT_LOWMEM_BASE;
+    gap = VIRT_LOWMEM_SIZE;
+    numa_info = machine->numa_state->nodes;
+    nodes = nb_numa_nodes;
+    if (!nodes) {
+        nodes = 1;
     }
-    if (mem_len)
-        build_srat_memory(table_data, mem_base, mem_len, 0, MEM_AFFINITY_ENABLED);
-
-    /* Node1 - Nodemax */
-    if (nb_numa_nodes) {
-        mem_base += mem_len;
-        for (i = 1; i < nb_numa_nodes; ++i) {
-            if (machine->numa_state->nodes[i].node_mem > 0) {
-                build_srat_memory(table_data, mem_base,
-                                  machine->numa_state->nodes[i].node_mem, i,
-                                  MEM_AFFINITY_ENABLED);
-                mem_base += machine->numa_state->nodes[i].node_mem;
-            }
+
+    for (i = 0; i < nodes; i++) {
+        if (nb_numa_nodes) {
+            len = numa_info[i].node_mem;
+        } else {
+            len = machine->ram_size;
+        }
+
+        /*
+         * memory for the node splited into two part
+         *   lowram:  [base, +gap)
+         *   highram: [VIRT_HIGHMEM_BASE, +(len - gap))
+         */
+        if (len >= gap) {
+            build_srat_memory(table_data, base, len, i, MEM_AFFINITY_ENABLED);
+            len -= gap;
+            base = VIRT_HIGHMEM_BASE;
+            gap = machine->ram_size - VIRT_LOWMEM_SIZE;
+        }
+
+        if (len) {
+            build_srat_memory(table_data, base, len, i, MEM_AFFINITY_ENABLED);
+            base += len;
+            gap  -= len;
         }
     }
 
     if (machine->device_memory) {
         build_srat_memory(table_data, machine->device_memory->base,
                           memory_region_size(&machine->device_memory->mr),
-                          nb_numa_nodes - 1,
+                          nodes - 1,
                           MEM_AFFINITY_HOTPLUGGABLE | MEM_AFFINITY_ENABLED);
     }
 
diff --git a/hw/loongarch/virt.c b/hw/loongarch/virt.c
index f0640d2d80..3e6e93edf3 100644
--- a/hw/loongarch/virt.c
+++ b/hw/loongarch/virt.c
@@ -10,6 +10,7 @@
 #include "qapi/error.h"
 #include "hw/boards.h"
 #include "hw/char/serial.h"
+#include "sysemu/kvm.h"
 #include "sysemu/sysemu.h"
 #include "sysemu/qtest.h"
 #include "sysemu/runstate.h"
@@ -463,7 +464,8 @@ static void fdt_add_memory_node(MachineState *ms,
     char *nodename = g_strdup_printf("/memory@%" PRIx64, base);
 
     qemu_fdt_add_subnode(ms->fdt, nodename);
-    qemu_fdt_setprop_cells(ms->fdt, nodename, "reg", 0, base, 0, size);
+    qemu_fdt_setprop_cells(ms->fdt, nodename, "reg", base >> 32, base,
+                           size >> 32, size);
     qemu_fdt_setprop_string(ms->fdt, nodename, "device_type", "memory");
 
     if (ms->numa_state && ms->numa_state->num_nodes) {
@@ -473,6 +475,48 @@ static void fdt_add_memory_node(MachineState *ms,
     g_free(nodename);
 }
 
+static void fdt_add_memory_nodes(MachineState *ms)
+{
+    hwaddr base, size, ram_size, gap;
+    int i, nb_numa_nodes, nodes;
+    NodeInfo *numa_info;
+
+    ram_size = ms->ram_size;
+    base = VIRT_LOWMEM_BASE;
+    gap = VIRT_LOWMEM_SIZE;
+    nodes = nb_numa_nodes = ms->numa_state->num_nodes;
+    numa_info = ms->numa_state->nodes;
+    if (!nodes) {
+        nodes = 1;
+    }
+
+    for (i = 0; i < nodes; i++) {
+        if (nb_numa_nodes) {
+            size = numa_info[i].node_mem;
+        } else {
+            size = ram_size;
+        }
+
+        /*
+         * memory for the node splited into two part
+         *   lowram:  [base, +gap)
+         *   highram: [VIRT_HIGHMEM_BASE, +(len - gap))
+         */
+        if (size >= gap) {
+            fdt_add_memory_node(ms, base, gap, i);
+            size -= gap;
+            base = VIRT_HIGHMEM_BASE;
+            gap = ram_size - VIRT_LOWMEM_SIZE;
+        }
+
+        if (size) {
+            fdt_add_memory_node(ms, base, size, i);
+            base += size;
+            gap -= size;
+        }
+    }
+}
+
 static void virt_build_smbios(LoongArchVirtMachineState *lvms)
 {
     MachineState *ms = MACHINE(lvms);
@@ -840,18 +884,23 @@ static void virt_iocsr_misc_write(void *opaque, hwaddr addr,
 
 static uint64_t virt_iocsr_misc_read(void *opaque, hwaddr addr, unsigned size)
 {
+    uint64_t ret;
+
     switch (addr) {
     case VERSION_REG:
         return 0x11ULL;
     case FEATURE_REG:
-        return 1ULL << IOCSRF_MSI | 1ULL << IOCSRF_EXTIOI |
-               1ULL << IOCSRF_CSRIPI;
+        ret = BIT(IOCSRF_MSI) | BIT(IOCSRF_EXTIOI) | BIT(IOCSRF_CSRIPI);
+        if (kvm_enabled()) {
+            ret |= BIT(IOCSRF_VM);
+        }
+        return ret;
     case VENDOR_REG:
         return 0x6e6f73676e6f6f4cULL; /* "Loongson" */
     case CPUNAME_REG:
         return 0x303030354133ULL;     /* "3A5000" */
     case MISC_FUNC_REG:
-        return 1ULL << IOCSRM_EXTIOI_EN;
+        return BIT_ULL(IOCSRM_EXTIOI_EN);
     }
     return 0ULL;
 }
@@ -870,18 +919,70 @@ static const MemoryRegionOps virt_iocsr_misc_ops = {
     },
 };
 
+static void fw_cfg_add_memory(MachineState *ms)
+{
+    hwaddr base, size, ram_size, gap;
+    int nb_numa_nodes, nodes;
+    NodeInfo *numa_info;
+
+    ram_size = ms->ram_size;
+    base = VIRT_LOWMEM_BASE;
+    gap = VIRT_LOWMEM_SIZE;
+    nodes = nb_numa_nodes = ms->numa_state->num_nodes;
+    numa_info = ms->numa_state->nodes;
+    if (!nodes) {
+        nodes = 1;
+    }
+
+    /* add fw_cfg memory map of node0 */
+    if (nb_numa_nodes) {
+        size = numa_info[0].node_mem;
+    } else {
+        size = ram_size;
+    }
+
+    if (size >= gap) {
+        memmap_add_entry(base, gap, 1);
+        size -= gap;
+        base = VIRT_HIGHMEM_BASE;
+        gap = ram_size - VIRT_LOWMEM_SIZE;
+    }
+
+    if (size) {
+        memmap_add_entry(base, size, 1);
+        base += size;
+    }
+
+    if (nodes < 2) {
+        return;
+    }
+
+    /* add fw_cfg memory map of other nodes */
+    size = ram_size - numa_info[0].node_mem;
+    gap  = VIRT_LOWMEM_BASE + VIRT_LOWMEM_SIZE;
+    if (base < gap && (base + size) > gap) {
+        /*
+         * memory map for the maining nodes splited into two part
+         *   lowram:  [base, +(gap - base))
+         *   highram: [VIRT_HIGHMEM_BASE, +(size - (gap - base)))
+         */
+        memmap_add_entry(base, gap - base, 1);
+        size -= gap - base;
+        base = VIRT_HIGHMEM_BASE;
+    }
+
+   if (size)
+        memmap_add_entry(base, size, 1);
+}
+
 static void virt_init(MachineState *machine)
 {
     LoongArchCPU *lacpu;
     const char *cpu_model = machine->cpu_type;
-    ram_addr_t offset = 0;
-    ram_addr_t ram_size = machine->ram_size;
-    uint64_t highram_size = 0, phyAddr = 0;
     MemoryRegion *address_space_mem = get_system_memory();
     LoongArchVirtMachineState *lvms = LOONGARCH_VIRT_MACHINE(machine);
-    int nb_numa_nodes = machine->numa_state->num_nodes;
-    NodeInfo *numa_info = machine->numa_state->nodes;
     int i;
+    hwaddr base, size, ram_size = machine->ram_size;
     const CPUArchIdList *possible_cpus;
     MachineClass *mc = MACHINE_GET_CLASS(machine);
     CPUState *cpu;
@@ -890,10 +991,6 @@ static void virt_init(MachineState *machine)
         cpu_model = LOONGARCH_CPU_TYPE_NAME("la464");
     }
 
-    if (ram_size < 1 * GiB) {
-        error_report("ram_size must be greater than 1G.");
-        exit(1);
-    }
     create_fdt(lvms);
 
     /* Create IOCSR space */
@@ -915,48 +1012,31 @@ static void virt_init(MachineState *machine)
         lacpu->phy_id = machine->possible_cpus->cpus[i].arch_id;
     }
     fdt_add_cpu_nodes(lvms);
+    fdt_add_memory_nodes(machine);
+    fw_cfg_add_memory(machine);
 
     /* Node0 memory */
-    memmap_add_entry(VIRT_LOWMEM_BASE, VIRT_LOWMEM_SIZE, 1);
-    fdt_add_memory_node(machine, VIRT_LOWMEM_BASE, VIRT_LOWMEM_SIZE, 0);
-    memory_region_init_alias(&lvms->lowmem, NULL, "loongarch.node0.lowram",
-                             machine->ram, offset, VIRT_LOWMEM_SIZE);
-    memory_region_add_subregion(address_space_mem, phyAddr, &lvms->lowmem);
-
-    offset += VIRT_LOWMEM_SIZE;
-    if (nb_numa_nodes > 0) {
-        assert(numa_info[0].node_mem > VIRT_LOWMEM_SIZE);
-        highram_size = numa_info[0].node_mem - VIRT_LOWMEM_SIZE;
-    } else {
-        highram_size = ram_size - VIRT_LOWMEM_SIZE;
+    size = ram_size;
+    base = VIRT_LOWMEM_BASE;
+    if (size > VIRT_LOWMEM_SIZE) {
+        size = VIRT_LOWMEM_SIZE;
     }
-    phyAddr = VIRT_HIGHMEM_BASE;
-    memmap_add_entry(phyAddr, highram_size, 1);
-    fdt_add_memory_node(machine, phyAddr, highram_size, 0);
-    memory_region_init_alias(&lvms->highmem, NULL, "loongarch.node0.highram",
-                              machine->ram, offset, highram_size);
-    memory_region_add_subregion(address_space_mem, phyAddr, &lvms->highmem);
-
-    /* Node1 - Nodemax memory */
-    offset += highram_size;
-    phyAddr += highram_size;
-
-    for (i = 1; i < nb_numa_nodes; i++) {
-        MemoryRegion *nodemem = g_new(MemoryRegion, 1);
-        g_autofree char *ramName = g_strdup_printf("loongarch.node%d.ram", i);
-        memory_region_init_alias(nodemem, NULL, ramName, machine->ram,
-                                 offset,  numa_info[i].node_mem);
-        memory_region_add_subregion(address_space_mem, phyAddr, nodemem);
-        memmap_add_entry(phyAddr, numa_info[i].node_mem, 1);
-        fdt_add_memory_node(machine, phyAddr, numa_info[i].node_mem, i);
-        offset += numa_info[i].node_mem;
-        phyAddr += numa_info[i].node_mem;
+
+    memory_region_init_alias(&lvms->lowmem, NULL, "loongarch.lowram",
+                              machine->ram, base, size);
+    memory_region_add_subregion(address_space_mem, base, &lvms->lowmem);
+    base += size;
+    if (ram_size - size) {
+        base = VIRT_HIGHMEM_BASE;
+        memory_region_init_alias(&lvms->highmem, NULL, "loongarch.highram",
+                machine->ram, VIRT_LOWMEM_BASE + size, ram_size - size);
+        memory_region_add_subregion(address_space_mem, base, &lvms->highmem);
+        base += ram_size - size;
     }
 
     /* initialize device memory address space */
     if (machine->ram_size < machine->maxram_size) {
         ram_addr_t device_mem_size = machine->maxram_size - machine->ram_size;
-        hwaddr device_mem_base;
 
         if (machine->ram_slots > ACPI_MAX_RAM_SLOTS) {
             error_report("unsupported amount of memory slots: %"PRIu64,
@@ -970,9 +1050,7 @@ static void virt_init(MachineState *machine)
                          "%d bytes", TARGET_PAGE_SIZE);
             exit(EXIT_FAILURE);
         }
-        /* device memory base is the top of high memory address. */
-        device_mem_base = ROUND_UP(VIRT_HIGHMEM_BASE + highram_size, 1 * GiB);
-        machine_memory_devices_init(machine, device_mem_base, device_mem_size);
+        machine_memory_devices_init(machine, base, device_mem_size);
     }
 
     /* load the BIOS image. */
@@ -1198,7 +1276,6 @@ static void virt_class_init(ObjectClass *oc, void *data)
     HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc);
 
     mc->init = virt_init;
-    mc->default_ram_size = 1 * GiB;
     mc->default_cpu_type = LOONGARCH_CPU_TYPE_NAME("la464");
     mc->default_ram_id = "loongarch.ram";
     mc->max_cpus = LOONGARCH_MAX_CPUS;
diff --git a/target/loongarch/cpu.c b/target/loongarch/cpu.c
index a0cad53676..b5c1ec94af 100644
--- a/target/loongarch/cpu.c
+++ b/target/loongarch/cpu.c
@@ -645,16 +645,10 @@ static void loongarch_set_lasx(Object *obj, bool value, Error **errp)
 
 void loongarch_cpu_post_init(Object *obj)
 {
-    LoongArchCPU *cpu = LOONGARCH_CPU(obj);
-
-    if (FIELD_EX32(cpu->env.cpucfg[2], CPUCFG2, LSX)) {
-        object_property_add_bool(obj, "lsx", loongarch_get_lsx,
-                                 loongarch_set_lsx);
-    }
-    if (FIELD_EX32(cpu->env.cpucfg[2], CPUCFG2, LASX)) {
-        object_property_add_bool(obj, "lasx", loongarch_get_lasx,
-                                 loongarch_set_lasx);
-    }
+    object_property_add_bool(obj, "lsx", loongarch_get_lsx,
+                             loongarch_set_lsx);
+    object_property_add_bool(obj, "lasx", loongarch_get_lasx,
+                             loongarch_set_lasx);
 }
 
 static void loongarch_cpu_init(Object *obj)
diff --git a/target/loongarch/kvm/kvm.c b/target/loongarch/kvm/kvm.c
index bc75552d0f..8e6e27c8bf 100644
--- a/target/loongarch/kvm/kvm.c
+++ b/target/loongarch/kvm/kvm.c
@@ -436,6 +436,9 @@ static int kvm_loongarch_get_regs_fp(CPUState *cs)
     env->fcsr0 = fpu.fcsr;
     for (i = 0; i < 32; i++) {
         env->fpr[i].vreg.UD[0] = fpu.fpr[i].val64[0];
+        env->fpr[i].vreg.UD[1] = fpu.fpr[i].val64[1];
+        env->fpr[i].vreg.UD[2] = fpu.fpr[i].val64[2];
+        env->fpr[i].vreg.UD[3] = fpu.fpr[i].val64[3];
     }
     for (i = 0; i < 8; i++) {
         env->cf[i] = fpu.fcc & 0xFF;
@@ -455,6 +458,9 @@ static int kvm_loongarch_put_regs_fp(CPUState *cs)
     fpu.fcc = 0;
     for (i = 0; i < 32; i++) {
         fpu.fpr[i].val64[0] = env->fpr[i].vreg.UD[0];
+        fpu.fpr[i].val64[1] = env->fpr[i].vreg.UD[1];
+        fpu.fpr[i].val64[2] = env->fpr[i].vreg.UD[2];
+        fpu.fpr[i].val64[3] = env->fpr[i].vreg.UD[3];
     }
 
     for (i = 0; i < 8; i++) {
diff --git a/target/loongarch/machine.c b/target/loongarch/machine.c
index 9cd9e848d6..08a7fa5370 100644
--- a/target/loongarch/machine.c
+++ b/target/loongarch/machine.c
@@ -145,8 +145,8 @@ static const VMStateDescription vmstate_tlb = {
 /* LoongArch CPU state */
 const VMStateDescription vmstate_loongarch_cpu = {
     .name = "cpu",
-    .version_id = 1,
-    .minimum_version_id = 1,
+    .version_id = 2,
+    .minimum_version_id = 2,
     .fields = (const VMStateField[]) {
         VMSTATE_UINTTL_ARRAY(env.gpr, LoongArchCPU, 32),
         VMSTATE_UINTTL(env.pc, LoongArchCPU),
@@ -208,6 +208,8 @@ const VMStateDescription vmstate_loongarch_cpu = {
         VMSTATE_UINT64(env.CSR_DERA, LoongArchCPU),
         VMSTATE_UINT64(env.CSR_DSAVE, LoongArchCPU),
 
+        VMSTATE_UINT64(kvm_state_counter, LoongArchCPU),
+
         VMSTATE_END_OF_LIST()
     },
     .subsections = (const VMStateDescription * const []) {