X-Git-Url: https://repo.jachan.dev/qemu.git/blobdiff_plain/76fe21dedafb0319306bc993f23e7646b139cfe4..9397a7c8318d727cea2ac62dbb14493a0e3e5f4b:/kvm-all.c

diff --git a/kvm-all.c b/kvm-all.c
index 7630a7d6e3..4e19eff0ef 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -27,14 +27,18 @@
 #include "sysemu/sysemu.h"
 #include "hw/hw.h"
 #include "hw/pci/msi.h"
+#include "hw/s390x/adapter.h"
 #include "exec/gdbstub.h"
 #include "sysemu/kvm.h"
 #include "qemu/bswap.h"
 #include "exec/memory.h"
+#include "exec/ram_addr.h"
 #include "exec/address-spaces.h"
 #include "qemu/event_notifier.h"
 #include "trace.h"
 
+#include "hw/boards.h"
+
 /* This check must be after config-host.h is included */
 #ifdef CONFIG_EVENTFD
 #include <sys/eventfd.h>
@@ -72,7 +76,8 @@ typedef struct kvm_dirty_log KVMDirtyLog;
 
 struct KVMState
 {
-    KVMSlot slots[32];
+    KVMSlot *slots;
+    int nr_slots;
     int fd;
     int vmfd;
     int coalesced_mmio;
@@ -125,7 +130,7 @@ static KVMSlot *kvm_alloc_slot(KVMState *s)
 {
     int i;
 
-    for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
+    for (i = 0; i < s->nr_slots; i++) {
         if (s->slots[i].memory_size == 0) {
             return &s->slots[i];
         }
@@ -141,7 +146,7 @@ static KVMSlot *kvm_lookup_matching_slot(KVMState *s,
 {
     int i;
 
-    for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
+    for (i = 0; i < s->nr_slots; i++) {
         KVMSlot *mem = &s->slots[i];
 
         if (start_addr == mem->start_addr &&
@@ -163,7 +168,7 @@ static KVMSlot *kvm_lookup_overlapping_slot(KVMState *s,
     KVMSlot *found = NULL;
     int i;
 
-    for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
+    for (i = 0; i < s->nr_slots; i++) {
         KVMSlot *mem = &s->slots[i];
 
         if (mem->memory_size == 0 ||
@@ -185,7 +190,7 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram,
 {
     int i;
 
-    for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
+    for (i = 0; i < s->nr_slots; i++) {
         KVMSlot *mem = &s->slots[i];
 
         if (ram >= mem->ram && ram < mem->ram + mem->memory_size) {
@@ -219,13 +224,6 @@ static int kvm_set_user_memory_region(KVMState *s, KVMSlot *slot)
     return kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
 }
 
-static void kvm_reset_vcpu(void *opaque)
-{
-    CPUState *cpu = opaque;
-
-    kvm_arch_reset_vcpu(cpu);
-}
-
 int kvm_init_vcpu(CPUState *cpu)
 {
     KVMState *s = kvm_state;
@@ -265,10 +263,6 @@ int kvm_init_vcpu(CPUState *cpu)
     }
 
     ret = kvm_arch_init_vcpu(cpu);
-    if (ret == 0) {
-        qemu_register_reset(kvm_reset_vcpu, cpu);
-        kvm_arch_reset_vcpu(cpu);
-    }
 err:
     return ret;
 }
@@ -357,7 +351,7 @@ static int kvm_set_migration_log(int enable)
 
     s->migration_log = enable;
 
-    for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
+    for (i = 0; i < s->nr_slots; i++) {
         mem = &s->slots[i];
 
         if (!mem->memory_size) {
@@ -378,31 +372,10 @@ static int kvm_set_migration_log(int enable)
 static int kvm_get_dirty_pages_log_range(MemoryRegionSection *section,
                                          unsigned long *bitmap)
 {
-    unsigned int i, j;
-    unsigned long page_number, c;
-    hwaddr addr, addr1;
-    unsigned int pages = int128_get64(section->size) / getpagesize();
-    unsigned int len = (pages + HOST_LONG_BITS - 1) / HOST_LONG_BITS;
-    unsigned long hpratio = getpagesize() / TARGET_PAGE_SIZE;
+    ram_addr_t start = section->offset_within_region + section->mr->ram_addr;
+    ram_addr_t pages = int128_get64(section->size) / getpagesize();
 
-    /*
-     * bitmap-traveling is faster than memory-traveling (for addr...)
-     * especially when most of the memory is not dirty.
-     */
-    for (i = 0; i < len; i++) {
-        if (bitmap[i] != 0) {
-            c = leul_to_cpu(bitmap[i]);
-            do {
-                j = ffsl(c) - 1;
-                c &= ~(1ul << j);
-                page_number = (i * HOST_LONG_BITS + j) * hpratio;
-                addr1 = page_number * TARGET_PAGE_SIZE;
-                addr = section->offset_within_region + addr1;
-                memory_region_set_dirty(section->mr, addr,
-                                        TARGET_PAGE_SIZE * hpratio);
-            } while (c != 0);
-        }
-    }
+    cpu_physical_memory_set_dirty_lebitmap(bitmap, start, pages);
     return 0;
 }
 
@@ -518,7 +491,7 @@ int kvm_check_extension(KVMState *s, unsigned int extension)
     return ret;
 }
 
-static int kvm_set_ioeventfd_mmio(int fd, uint32_t addr, uint32_t val,
+static int kvm_set_ioeventfd_mmio(int fd, hwaddr addr, uint32_t val,
                                   bool assign, uint32_t size, bool datamatch)
 {
     int ret;
@@ -1264,6 +1237,35 @@ static int kvm_irqchip_assign_irqfd(KVMState *s, int fd, int rfd, int virq,
     return kvm_vm_ioctl(s, KVM_IRQFD, &irqfd);
 }
 
+int kvm_irqchip_add_adapter_route(KVMState *s, AdapterInfo *adapter)
+{
+    struct kvm_irq_routing_entry kroute;
+    int virq;
+
+    if (!kvm_gsi_routing_enabled()) {
+        return -ENOSYS;
+    }
+
+    virq = kvm_irqchip_get_virq(s);
+    if (virq < 0) {
+        return virq;
+    }
+
+    kroute.gsi = virq;
+    kroute.type = KVM_IRQ_ROUTING_S390_ADAPTER;
+    kroute.flags = 0;
+    kroute.u.adapter.summary_addr = adapter->summary_addr;
+    kroute.u.adapter.ind_addr = adapter->ind_addr;
+    kroute.u.adapter.summary_offset = adapter->summary_offset;
+    kroute.u.adapter.ind_offset = adapter->ind_offset;
+    kroute.u.adapter.adapter_id = adapter->adapter_id;
+
+    kvm_add_routing_entry(s, &kroute);
+    kvm_irqchip_commit_routes(s);
+
+    return virq;
+}
+
 #else /* !KVM_CAP_IRQ_ROUTING */
 
 void kvm_init_irq_routing(KVMState *s)
@@ -1284,6 +1286,11 @@ int kvm_irqchip_add_msi_route(KVMState *s, MSIMessage msg)
     return -ENOSYS;
 }
 
+int kvm_irqchip_add_adapter_route(KVMState *s, AdapterInfo *adapter)
+{
+    return -ENOSYS;
+}
+
 static int kvm_irqchip_assign_irqfd(KVMState *s, int fd, int virq, bool assign)
 {
     abort();
@@ -1313,14 +1320,22 @@ static int kvm_irqchip_create(KVMState *s)
     int ret;
 
     if (!qemu_opt_get_bool(qemu_get_machine_opts(), "kernel_irqchip", true) ||
-        !kvm_check_extension(s, KVM_CAP_IRQCHIP)) {
+        (!kvm_check_extension(s, KVM_CAP_IRQCHIP) &&
+         (kvm_vm_enable_cap(s, KVM_CAP_S390_IRQCHIP, 0) < 0))) {
         return 0;
     }
 
-    ret = kvm_vm_ioctl(s, KVM_CREATE_IRQCHIP);
+    /* First probe and see if there's a arch-specific hook to create the
+     * in-kernel irqchip for us */
+    ret = kvm_arch_irqchip_create(s);
     if (ret < 0) {
-        fprintf(stderr, "Create kernel irqchip failed\n");
         return ret;
+    } else if (ret == 0) {
+        ret = kvm_vm_ioctl(s, KVM_CREATE_IRQCHIP);
+        if (ret < 0) {
+            fprintf(stderr, "Create kernel irqchip failed\n");
+            return ret;
+        }
     }
 
     kvm_kernel_irqchip = true;
@@ -1351,7 +1366,7 @@ static int kvm_max_vcpus(KVMState *s)
     return (ret) ? ret : kvm_recommended_vcpus(s);
 }
 
-int kvm_init(void)
+int kvm_init(MachineClass *mc)
 {
     static const char upgrade_note[] =
         "Please upgrade to at least kernel 2.6.29 or recent kvm-kmod\n"
@@ -1368,7 +1383,8 @@ int kvm_init(void)
     KVMState *s;
     const KVMCapabilityInfo *missing_cap;
     int ret;
-    int i;
+    int i, type = 0;
+    const char *kvm_type;
 
     s = g_malloc0(sizeof(KVMState));
 
@@ -1379,13 +1395,11 @@ int kvm_init(void)
      * page size for the system though.
      */
     assert(TARGET_PAGE_SIZE <= getpagesize());
+    page_size_init();
 
 #ifdef KVM_CAP_SET_GUEST_DEBUG
     QTAILQ_INIT(&s->kvm_sw_breakpoints);
 #endif
-    for (i = 0; i < ARRAY_SIZE(s->slots); i++) {
-        s->slots[i].slot = i;
-    }
     s->vmfd = -1;
     s->fd = qemu_open("/dev/kvm", O_RDWR);
     if (s->fd == -1) {
@@ -1396,7 +1410,7 @@ int kvm_init(void)
 
     ret = kvm_ioctl(s, KVM_GET_API_VERSION, 0);
     if (ret < KVM_API_VERSION) {
-        if (ret > 0) {
+        if (ret >= 0) {
             ret = -EINVAL;
         }
         fprintf(stderr, "kvm version too old\n");
@@ -1409,6 +1423,19 @@ int kvm_init(void)
         goto err;
     }
 
+    s->nr_slots = kvm_check_extension(s, KVM_CAP_NR_MEMSLOTS);
+
+    /* If unspecified, use the default value */
+    if (!s->nr_slots) {
+        s->nr_slots = 32;
+    }
+
+    s->slots = g_malloc0(s->nr_slots * sizeof(KVMSlot));
+
+    for (i = 0; i < s->nr_slots; i++) {
+        s->slots[i].slot = i;
+    }
+
     /* check the vcpu limits */
     soft_vcpus_limit = kvm_recommended_vcpus(s);
     hard_vcpus_limit = kvm_max_vcpus(s);
@@ -1421,26 +1448,40 @@ int kvm_init(void)
                     nc->name, nc->num, soft_vcpus_limit);
 
             if (nc->num > hard_vcpus_limit) {
-                ret = -EINVAL;
                 fprintf(stderr, "Number of %s cpus requested (%d) exceeds "
                         "the maximum cpus supported by KVM (%d)\n",
                         nc->name, nc->num, hard_vcpus_limit);
-                goto err;
+                exit(1);
             }
         }
         nc++;
     }
 
-    s->vmfd = kvm_ioctl(s, KVM_CREATE_VM, 0);
-    if (s->vmfd < 0) {
+    kvm_type = qemu_opt_get(qemu_get_machine_opts(), "kvm-type");
+    if (mc->kvm_type) {
+        type = mc->kvm_type(kvm_type);
+    } else if (kvm_type) {
+        ret = -EINVAL;
+        fprintf(stderr, "Invalid argument kvm-type=%s\n", kvm_type);
+        goto err;
+    }
+
+    do {
+        ret = kvm_ioctl(s, KVM_CREATE_VM, type);
+    } while (ret == -EINTR);
+
+    if (ret < 0) {
+        fprintf(stderr, "ioctl(KVM_CREATE_VM) failed: %d %s\n", -ret,
+                strerror(-ret));
+
 #ifdef TARGET_S390X
         fprintf(stderr, "Please add the 'switch_amode' kernel parameter to "
                         "your host kernel command line\n");
 #endif
-        ret = s->vmfd;
         goto err;
     }
 
+    s->vmfd = ret;
     missing_cap = kvm_check_extension_list(s, kvm_required_capabilites);
     if (!missing_cap) {
         missing_cap =
@@ -1521,12 +1562,14 @@ int kvm_init(void)
     return 0;
 
 err:
+    assert(ret < 0);
     if (s->vmfd >= 0) {
         close(s->vmfd);
     }
     if (s->fd != -1) {
         close(s->fd);
     }
+    g_free(s->slots);
     g_free(s);
 
     return ret;
@@ -1547,17 +1590,16 @@ static void kvm_handle_io(uint16_t port, void *data, int direction, int size,
 
 static int kvm_handle_internal_error(CPUState *cpu, struct kvm_run *run)
 {
-    fprintf(stderr, "KVM internal error.");
+    fprintf(stderr, "KVM internal error. Suberror: %d\n",
+            run->internal.suberror);
+
     if (kvm_check_extension(kvm_state, KVM_CAP_INTERNAL_ERROR_DATA)) {
         int i;
 
-        fprintf(stderr, " Suberror: %d\n", run->internal.suberror);
         for (i = 0; i < run->internal.ndata; ++i) {
             fprintf(stderr, "extra data[%d]: %"PRIx64"\n",
                     i, (uint64_t)run->internal.data[i]);
         }
-    } else {
-        fprintf(stderr, "\n");
     }
     if (run->internal.suberror == KVM_INTERNAL_ERROR_EMULATION) {
         fprintf(stderr, "emulation failure\n");
@@ -1779,6 +1821,24 @@ int kvm_vcpu_ioctl(CPUState *cpu, int type, ...)
     return ret;
 }
 
+int kvm_device_ioctl(int fd, int type, ...)
+{
+    int ret;
+    void *arg;
+    va_list ap;
+
+    va_start(ap, type);
+    arg = va_arg(ap, void *);
+    va_end(ap);
+
+    trace_kvm_device_ioctl(fd, type, arg);
+    ret = ioctl(fd, type, arg);
+    if (ret == -1) {
+        ret = -errno;
+    }
+    return ret;
+}
+
 int kvm_has_sync_mmu(void)
 {
     return kvm_check_extension(kvm_state, KVM_CAP_SYNC_MMU);
@@ -1836,19 +1896,6 @@ int kvm_has_intx_set_mask(void)
     return kvm_state->intx_set_mask;
 }
 
-void *kvm_ram_alloc(ram_addr_t size)
-{
-#ifdef TARGET_S390X
-    void *mem;
-
-    mem = kvm_arch_ram_alloc(size);
-    if (mem) {
-        return mem;
-    }
-#endif
-    return qemu_anon_ram_alloc(size);
-}
-
 void kvm_setup_guest_memory(void *start, size_t size)
 {
 #ifdef CONFIG_VALGRIND_H
@@ -2073,3 +2120,52 @@ int kvm_on_sigbus(int code, void *addr)
 {
     return kvm_arch_on_sigbus(code, addr);
 }
+
+int kvm_create_device(KVMState *s, uint64_t type, bool test)
+{
+    int ret;
+    struct kvm_create_device create_dev;
+
+    create_dev.type = type;
+    create_dev.fd = -1;
+    create_dev.flags = test ? KVM_CREATE_DEVICE_TEST : 0;
+
+    if (!kvm_check_extension(s, KVM_CAP_DEVICE_CTRL)) {
+        return -ENOTSUP;
+    }
+
+    ret = kvm_vm_ioctl(s, KVM_CREATE_DEVICE, &create_dev);
+    if (ret) {
+        return ret;
+    }
+
+    return test ? 0 : create_dev.fd;
+}
+
+int kvm_set_one_reg(CPUState *cs, uint64_t id, void *source)
+{
+    struct kvm_one_reg reg;
+    int r;
+
+    reg.id = id;
+    reg.addr = (uintptr_t) source;
+    r = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
+    if (r) {
+        trace_kvm_failed_reg_set(id, strerror(r));
+    }
+    return r;
+}
+
+int kvm_get_one_reg(CPUState *cs, uint64_t id, void *target)
+{
+    struct kvm_one_reg reg;
+    int r;
+
+    reg.id = id;
+    reg.addr = (uintptr_t) target;
+    r = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
+    if (r) {
+        trace_kvm_failed_reg_get(id, strerror(r));
+    }
+    return r;
+}