X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=kvm-all.c;h=3a316023593a4c3d46fc4806dec6ecc6d44b8c8d;hb=2b720018060179b394f8ce736983373ab80dd37c;hp=792cdf1d6602ec459718f4c0906d447ed684910d;hpb=20d695a9254c1b086a456d3b79a3c311236643ba;p=qemu.git

diff --git a/kvm-all.c b/kvm-all.c
index 792cdf1d6..3a3160235 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -21,18 +21,19 @@
 #include <linux/kvm.h>
 
 #include "qemu-common.h"
-#include "qemu-barrier.h"
-#include "qemu-option.h"
-#include "qemu-config.h"
-#include "sysemu.h"
+#include "qemu/atomic.h"
+#include "qemu/option.h"
+#include "qemu/config-file.h"
+#include "sysemu/sysemu.h"
 #include "hw/hw.h"
-#include "hw/msi.h"
-#include "gdbstub.h"
-#include "kvm.h"
-#include "bswap.h"
-#include "memory.h"
-#include "exec-memory.h"
-#include "event_notifier.h"
+#include "hw/pci/msi.h"
+#include "exec/gdbstub.h"
+#include "sysemu/kvm.h"
+#include "qemu/bswap.h"
+#include "exec/memory.h"
+#include "exec/address-spaces.h"
+#include "qemu/event_notifier.h"
+#include "trace.h"
 
 /* This check must be after config-host.h is included */
 #ifdef CONFIG_EVENTFD
@@ -109,6 +110,7 @@ bool kvm_async_interrupts_allowed;
 bool kvm_irqfds_allowed;
 bool kvm_msi_via_irqfd_allowed;
 bool kvm_gsi_routing_allowed;
+bool kvm_allowed;
 
 static const KVMCapabilityInfo kvm_required_capabilites[] = {
     KVM_CAP_INFO(USER_MEMORY),
@@ -214,23 +216,22 @@ static void kvm_reset_vcpu(void *opaque)
     kvm_arch_reset_vcpu(cpu);
 }
 
-int kvm_init_vcpu(CPUArchState *env)
+int kvm_init_vcpu(CPUState *cpu)
 {
-    CPUState *cpu = ENV_GET_CPU(env);
     KVMState *s = kvm_state;
     long mmap_size;
     int ret;
 
     DPRINTF("kvm_init_vcpu\n");
 
-    ret = kvm_vm_ioctl(s, KVM_CREATE_VCPU, env->cpu_index);
+    ret = kvm_vm_ioctl(s, KVM_CREATE_VCPU, (void *)kvm_arch_vcpu_id(cpu));
     if (ret < 0) {
         DPRINTF("kvm_create_vcpu failed\n");
         goto err;
     }
 
     cpu->kvm_fd = ret;
-    env->kvm_state = s;
+    cpu->kvm_state = s;
     cpu->kvm_vcpu_dirty = true;
 
     mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0);
@@ -240,9 +241,9 @@ int kvm_init_vcpu(CPUArchState *env)
         goto err;
     }
 
-    env->kvm_run = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+    cpu->kvm_run = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED,
                         cpu->kvm_fd, 0);
-    if (env->kvm_run == MAP_FAILED) {
+    if (cpu->kvm_run == MAP_FAILED) {
         ret = -errno;
         DPRINTF("mmap'ing vcpu state failed\n");
         goto err;
@@ -250,7 +251,7 @@ int kvm_init_vcpu(CPUArchState *env)
 
     if (s->coalesced_mmio && !s->coalesced_mmio_ring) {
         s->coalesced_mmio_ring =
-            (void *)env->kvm_run + s->coalesced_mmio * PAGE_SIZE;
+            (void *)cpu->kvm_run + s->coalesced_mmio * PAGE_SIZE;
     }
 
     ret = kvm_arch_init_vcpu(cpu);
@@ -501,6 +502,66 @@ 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,
+                                  bool assign, uint32_t size, bool datamatch)
+{
+    int ret;
+    struct kvm_ioeventfd iofd;
+
+    iofd.datamatch = datamatch ? val : 0;
+    iofd.addr = addr;
+    iofd.len = size;
+    iofd.flags = 0;
+    iofd.fd = fd;
+
+    if (!kvm_enabled()) {
+        return -ENOSYS;
+    }
+
+    if (datamatch) {
+        iofd.flags |= KVM_IOEVENTFD_FLAG_DATAMATCH;
+    }
+    if (!assign) {
+        iofd.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
+    }
+
+    ret = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &iofd);
+
+    if (ret < 0) {
+        return -errno;
+    }
+
+    return 0;
+}
+
+static int kvm_set_ioeventfd_pio(int fd, uint16_t addr, uint16_t val,
+                                 bool assign, uint32_t size, bool datamatch)
+{
+    struct kvm_ioeventfd kick = {
+        .datamatch = datamatch ? val : 0,
+        .addr = addr,
+        .flags = KVM_IOEVENTFD_FLAG_PIO,
+        .len = size,
+        .fd = fd,
+    };
+    int r;
+    if (!kvm_enabled()) {
+        return -ENOSYS;
+    }
+    if (datamatch) {
+        kick.flags |= KVM_IOEVENTFD_FLAG_DATAMATCH;
+    }
+    if (!assign) {
+        kick.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
+    }
+    r = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &kick);
+    if (r < 0) {
+        return r;
+    }
+    return 0;
+}
+
+
 static int kvm_check_many_ioeventfds(void)
 {
     /* Userspace can use ioeventfd for io notification.  This requires a host
@@ -518,7 +579,7 @@ static int kvm_check_many_ioeventfds(void)
         if (ioeventfds[i] < 0) {
             break;
         }
-        ret = kvm_set_ioeventfd_pio_word(ioeventfds[i], 0, i, true);
+        ret = kvm_set_ioeventfd_pio(ioeventfds[i], 0, i, true, 2, true);
         if (ret < 0) {
             close(ioeventfds[i]);
             break;
@@ -529,7 +590,7 @@ static int kvm_check_many_ioeventfds(void)
     ret = i == ARRAY_SIZE(ioeventfds);
 
     while (i-- > 0) {
-        kvm_set_ioeventfd_pio_word(ioeventfds[i], 0, i, false);
+        kvm_set_ioeventfd_pio(ioeventfds[i], 0, i, false, 2, true);
         close(ioeventfds[i]);
     }
     return ret;
@@ -749,10 +810,8 @@ static void kvm_mem_ioeventfd_add(MemoryListener *listener,
     int fd = event_notifier_get_fd(e);
     int r;
 
-    assert(match_data && section->size <= 8);
-
     r = kvm_set_ioeventfd_mmio(fd, section->offset_within_address_space,
-                               data, true, section->size);
+                               data, true, section->size, match_data);
     if (r < 0) {
         abort();
     }
@@ -767,7 +826,7 @@ static void kvm_mem_ioeventfd_del(MemoryListener *listener,
     int r;
 
     r = kvm_set_ioeventfd_mmio(fd, section->offset_within_address_space,
-                               data, false, section->size);
+                               data, false, section->size, match_data);
     if (r < 0) {
         abort();
     }
@@ -781,10 +840,8 @@ static void kvm_io_ioeventfd_add(MemoryListener *listener,
     int fd = event_notifier_get_fd(e);
     int r;
 
-    assert(match_data && section->size == 2);
-
-    r = kvm_set_ioeventfd_pio_word(fd, section->offset_within_address_space,
-                                   data, true);
+    r = kvm_set_ioeventfd_pio(fd, section->offset_within_address_space,
+                              data, true, section->size, match_data);
     if (r < 0) {
         abort();
     }
@@ -799,8 +856,8 @@ static void kvm_io_ioeventfd_del(MemoryListener *listener,
     int fd = event_notifier_get_fd(e);
     int r;
 
-    r = kvm_set_ioeventfd_pio_word(fd, section->offset_within_address_space,
-                                   data, false);
+    r = kvm_set_ioeventfd_pio(fd, section->offset_within_address_space,
+                              data, false, section->size, match_data);
     if (r < 0) {
         abort();
     }
@@ -827,11 +884,9 @@ static MemoryListener kvm_io_listener = {
     .priority = 10,
 };
 
-static void kvm_handle_interrupt(CPUArchState *env, int mask)
+static void kvm_handle_interrupt(CPUState *cpu, int mask)
 {
-    CPUState *cpu = ENV_GET_CPU(env);
-
-    env->interrupt_request |= mask;
+    cpu->interrupt_request |= mask;
 
     if (!qemu_cpu_is_self(cpu)) {
         qemu_cpu_kick(cpu);
@@ -992,8 +1047,6 @@ void kvm_irqchip_release_virq(KVMState *s, int virq)
         }
     }
     clear_gsi(s, virq);
-
-    kvm_irqchip_commit_routes(s);
 }
 
 static unsigned int kvm_hash_msi(uint32_t data)
@@ -1184,6 +1237,11 @@ static int kvm_irqchip_assign_irqfd(KVMState *s, int fd, int virq, bool assign)
 {
     abort();
 }
+
+int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg)
+{
+    return -ENOSYS;
+}
 #endif /* !KVM_CAP_IRQ_ROUTING */
 
 int kvm_irqchip_add_irqfd_notifier(KVMState *s, EventNotifier *n, int virq)
@@ -1510,18 +1568,14 @@ void kvm_cpu_synchronize_state(CPUArchState *env)
     }
 }
 
-void kvm_cpu_synchronize_post_reset(CPUArchState *env)
+void kvm_cpu_synchronize_post_reset(CPUState *cpu)
 {
-    CPUState *cpu = ENV_GET_CPU(env);
-
     kvm_arch_put_registers(cpu, KVM_PUT_RESET_STATE);
     cpu->kvm_vcpu_dirty = false;
 }
 
-void kvm_cpu_synchronize_post_init(CPUArchState *env)
+void kvm_cpu_synchronize_post_init(CPUState *cpu)
 {
-    CPUState *cpu = ENV_GET_CPU(env);
-
     kvm_arch_put_registers(cpu, KVM_PUT_FULL_STATE);
     cpu->kvm_vcpu_dirty = false;
 }
@@ -1529,13 +1583,13 @@ void kvm_cpu_synchronize_post_init(CPUArchState *env)
 int kvm_cpu_exec(CPUArchState *env)
 {
     CPUState *cpu = ENV_GET_CPU(env);
-    struct kvm_run *run = env->kvm_run;
+    struct kvm_run *run = cpu->kvm_run;
     int ret, run_ret;
 
     DPRINTF("kvm_cpu_exec()\n");
 
     if (kvm_arch_process_async_events(cpu)) {
-        env->exit_request = 0;
+        cpu->exit_request = 0;
         return EXCP_HLT;
     }
 
@@ -1546,7 +1600,7 @@ int kvm_cpu_exec(CPUArchState *env)
         }
 
         kvm_arch_pre_run(cpu, run);
-        if (env->exit_request) {
+        if (cpu->exit_request) {
             DPRINTF("interrupt exit requested\n");
             /*
              * KVM requires us to reenter the kernel after IO exits to complete
@@ -1557,7 +1611,7 @@ int kvm_cpu_exec(CPUArchState *env)
         }
         qemu_mutex_unlock_iothread();
 
-        run_ret = kvm_vcpu_ioctl(env, KVM_RUN, 0);
+        run_ret = kvm_vcpu_ioctl(cpu, KVM_RUN, 0);
 
         qemu_mutex_lock_iothread();
         kvm_arch_post_run(cpu, run);
@@ -1573,6 +1627,7 @@ int kvm_cpu_exec(CPUArchState *env)
             abort();
         }
 
+        trace_kvm_run_exit(cpu->cpu_index, run->exit_reason);
         switch (run->exit_reason) {
         case KVM_EXIT_IO:
             DPRINTF("handle_io\n");
@@ -1620,7 +1675,7 @@ int kvm_cpu_exec(CPUArchState *env)
         vm_stop(RUN_STATE_INTERNAL_ERROR);
     }
 
-    env->exit_request = 0;
+    cpu->exit_request = 0;
     return ret;
 }
 
@@ -1634,6 +1689,7 @@ int kvm_ioctl(KVMState *s, int type, ...)
     arg = va_arg(ap, void *);
     va_end(ap);
 
+    trace_kvm_ioctl(type, arg);
     ret = ioctl(s->fd, type, arg);
     if (ret == -1) {
         ret = -errno;
@@ -1651,6 +1707,7 @@ int kvm_vm_ioctl(KVMState *s, int type, ...)
     arg = va_arg(ap, void *);
     va_end(ap);
 
+    trace_kvm_vm_ioctl(type, arg);
     ret = ioctl(s->vmfd, type, arg);
     if (ret == -1) {
         ret = -errno;
@@ -1658,9 +1715,8 @@ int kvm_vm_ioctl(KVMState *s, int type, ...)
     return ret;
 }
 
-int kvm_vcpu_ioctl(CPUArchState *env, int type, ...)
+int kvm_vcpu_ioctl(CPUState *cpu, int type, ...)
 {
-    CPUState *cpu = ENV_GET_CPU(env);
     int ret;
     void *arg;
     va_list ap;
@@ -1669,6 +1725,7 @@ int kvm_vcpu_ioctl(CPUArchState *env, int type, ...)
     arg = va_arg(ap, void *);
     va_end(ap);
 
+    trace_kvm_vcpu_ioctl(cpu->cpu_index, type, arg);
     ret = ioctl(cpu->kvm_fd, type, arg);
     if (ret == -1) {
         ret = -errno;
@@ -1764,12 +1821,12 @@ void kvm_setup_guest_memory(void *start, size_t size)
 }
 
 #ifdef KVM_CAP_SET_GUEST_DEBUG
-struct kvm_sw_breakpoint *kvm_find_sw_breakpoint(CPUArchState *env,
+struct kvm_sw_breakpoint *kvm_find_sw_breakpoint(CPUState *cpu,
                                                  target_ulong pc)
 {
     struct kvm_sw_breakpoint *bp;
 
-    QTAILQ_FOREACH(bp, &env->kvm_state->kvm_sw_breakpoints, entry) {
+    QTAILQ_FOREACH(bp, &cpu->kvm_state->kvm_sw_breakpoints, entry) {
         if (bp->pc == pc) {
             return bp;
         }
@@ -1777,23 +1834,23 @@ struct kvm_sw_breakpoint *kvm_find_sw_breakpoint(CPUArchState *env,
     return NULL;
 }
 
-int kvm_sw_breakpoints_active(CPUArchState *env)
+int kvm_sw_breakpoints_active(CPUState *cpu)
 {
-    return !QTAILQ_EMPTY(&env->kvm_state->kvm_sw_breakpoints);
+    return !QTAILQ_EMPTY(&cpu->kvm_state->kvm_sw_breakpoints);
 }
 
 struct kvm_set_guest_debug_data {
     struct kvm_guest_debug dbg;
-    CPUArchState *env;
+    CPUState *cpu;
     int err;
 };
 
 static void kvm_invoke_set_guest_debug(void *data)
 {
     struct kvm_set_guest_debug_data *dbg_data = data;
-    CPUArchState *env = dbg_data->env;
 
-    dbg_data->err = kvm_vcpu_ioctl(env, KVM_SET_GUEST_DEBUG, &dbg_data->dbg);
+    dbg_data->err = kvm_vcpu_ioctl(dbg_data->cpu, KVM_SET_GUEST_DEBUG,
+                                   &dbg_data->dbg);
 }
 
 int kvm_update_guest_debug(CPUArchState *env, unsigned long reinject_trap)
@@ -1807,7 +1864,7 @@ int kvm_update_guest_debug(CPUArchState *env, unsigned long reinject_trap)
         data.dbg.control |= KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP;
     }
     kvm_arch_update_guest_debug(cpu, &data.dbg);
-    data.env = env;
+    data.cpu = cpu;
 
     run_on_cpu(cpu, kvm_invoke_set_guest_debug, &data);
     return data.err;
@@ -1822,7 +1879,7 @@ int kvm_insert_breakpoint(CPUArchState *current_env, target_ulong addr,
     int err;
 
     if (type == GDB_BREAKPOINT_SW) {
-        bp = kvm_find_sw_breakpoint(current_env, addr);
+        bp = kvm_find_sw_breakpoint(current_cpu, addr);
         if (bp) {
             bp->use_count++;
             return 0;
@@ -1841,7 +1898,7 @@ int kvm_insert_breakpoint(CPUArchState *current_env, target_ulong addr,
             return err;
         }
 
-        QTAILQ_INSERT_HEAD(&current_env->kvm_state->kvm_sw_breakpoints,
+        QTAILQ_INSERT_HEAD(&current_cpu->kvm_state->kvm_sw_breakpoints,
                           bp, entry);
     } else {
         err = kvm_arch_insert_hw_breakpoint(addr, len, type);
@@ -1868,7 +1925,7 @@ int kvm_remove_breakpoint(CPUArchState *current_env, target_ulong addr,
     int err;
 
     if (type == GDB_BREAKPOINT_SW) {
-        bp = kvm_find_sw_breakpoint(current_env, addr);
+        bp = kvm_find_sw_breakpoint(current_cpu, addr);
         if (!bp) {
             return -ENOENT;
         }
@@ -1883,7 +1940,7 @@ int kvm_remove_breakpoint(CPUArchState *current_env, target_ulong addr,
             return err;
         }
 
-        QTAILQ_REMOVE(&current_env->kvm_state->kvm_sw_breakpoints, bp, entry);
+        QTAILQ_REMOVE(&current_cpu->kvm_state->kvm_sw_breakpoints, bp, entry);
         g_free(bp);
     } else {
         err = kvm_arch_remove_hw_breakpoint(addr, len, type);
@@ -1905,7 +1962,7 @@ void kvm_remove_all_breakpoints(CPUArchState *current_env)
 {
     CPUState *current_cpu = ENV_GET_CPU(current_env);
     struct kvm_sw_breakpoint *bp, *next;
-    KVMState *s = current_env->kvm_state;
+    KVMState *s = current_cpu->kvm_state;
     CPUArchState *env;
     CPUState *cpu;
 
@@ -1955,78 +2012,25 @@ void kvm_remove_all_breakpoints(CPUArchState *current_env)
 
 int kvm_set_signal_mask(CPUArchState *env, const sigset_t *sigset)
 {
+    CPUState *cpu = ENV_GET_CPU(env);
     struct kvm_signal_mask *sigmask;
     int r;
 
     if (!sigset) {
-        return kvm_vcpu_ioctl(env, KVM_SET_SIGNAL_MASK, NULL);
+        return kvm_vcpu_ioctl(cpu, KVM_SET_SIGNAL_MASK, NULL);
     }
 
     sigmask = g_malloc(sizeof(*sigmask) + sizeof(*sigset));
 
     sigmask->len = 8;
     memcpy(sigmask->sigset, sigset, sizeof(*sigset));
-    r = kvm_vcpu_ioctl(env, KVM_SET_SIGNAL_MASK, sigmask);
+    r = kvm_vcpu_ioctl(cpu, KVM_SET_SIGNAL_MASK, sigmask);
     g_free(sigmask);
 
     return r;
 }
-
-int kvm_set_ioeventfd_mmio(int fd, uint32_t addr, uint32_t val, bool assign,
-                           uint32_t size)
-{
-    int ret;
-    struct kvm_ioeventfd iofd;
-
-    iofd.datamatch = val;
-    iofd.addr = addr;
-    iofd.len = size;
-    iofd.flags = KVM_IOEVENTFD_FLAG_DATAMATCH;
-    iofd.fd = fd;
-
-    if (!kvm_enabled()) {
-        return -ENOSYS;
-    }
-
-    if (!assign) {
-        iofd.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
-    }
-
-    ret = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &iofd);
-
-    if (ret < 0) {
-        return -errno;
-    }
-
-    return 0;
-}
-
-int kvm_set_ioeventfd_pio_word(int fd, uint16_t addr, uint16_t val, bool assign)
-{
-    struct kvm_ioeventfd kick = {
-        .datamatch = val,
-        .addr = addr,
-        .len = 2,
-        .flags = KVM_IOEVENTFD_FLAG_DATAMATCH | KVM_IOEVENTFD_FLAG_PIO,
-        .fd = fd,
-    };
-    int r;
-    if (!kvm_enabled()) {
-        return -ENOSYS;
-    }
-    if (!assign) {
-        kick.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
-    }
-    r = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &kick);
-    if (r < 0) {
-        return r;
-    }
-    return 0;
-}
-
-int kvm_on_sigbus_vcpu(CPUArchState *env, int code, void *addr)
+int kvm_on_sigbus_vcpu(CPUState *cpu, int code, void *addr)
 {
-    CPUState *cpu = ENV_GET_CPU(env);
     return kvm_arch_on_sigbus_vcpu(cpu, code, addr);
 }