[Qemu-devel] [PATCH 00/18] [uq/master] Rebased patch queue, part I

[Qemu-devel] [PATCH 00/18] [uq/master] Rebased patch queue, part I

[Jan Kiszka]

In order to make progress with flushing my kvm-upstream queue without
overloading the channels (38 further patches are pending), here comes
part I against updated uq/master.

Changes in this part compared to last postings:

 - Dropped "kvm: Drop return value of kvm_cpu_exec", we will actually
   need it later on.

 - Additional patch to swallow KVM_EXIT_SET_TPR (required now that we
   watch out for unknown exits).

 - Postponed MCE bits, they will follow later as part of a complete
   rework.

CC: Glauber Costa <glommer@redhat.com>

Jan Kiszka (18):
  kvm: x86: Swallow KVM_EXIT_SET_TPR
  kvm: Stop on all fatal exit reasons
  kvm: Improve reporting of fatal errors
  x86: Optionally dump code bytes on cpu_dump_state
  kvm: x86: Align kvm_arch_put_registers code with comment
  kvm: x86: Prepare kvm_get_mp_state for in-kernel irqchip
  kvm: x86: Remove redundant mp_state initialization
  kvm: x86: Fix xcr0 reset mismerge
  kvm: x86: Refactor msr_star/hsave_pa setup and checks
  kvm: x86: Reset paravirtual MSRs
  kvm: x86: Fix !CONFIG_KVM_PARA build
  kvm: Drop smp_cpus argument from init functions
  kvm: Consolidate must-have capability checks
  kvm: x86: Rework identity map and TSS setup for larger BIOS sizes
  kvm: Flush coalesced mmio buffer on IO window exits
  kvm: Do not use qemu_fair_mutex
  kvm: x86: Implicitly clear nmi_injected/pending on reset
  kvm: x86: Only read/write MSR_KVM_ASYNC_PF_EN if supported

 configure            |   39 ++++++---
 cpu-all.h            |    2 +
 cpus.c               |    2 -
 kvm-all.c            |  108 +++++++++++-------------
 kvm-stub.c           |    2 +-
 kvm.h                |   14 +++-
 target-i386/cpu.h    |    8 ++-
 target-i386/cpuid.c  |    5 +-
 target-i386/helper.c |   21 +++++
 target-i386/kvm.c    |  227 +++++++++++++++++++++++++++-----------------------
 target-ppc/kvm.c     |   10 ++-
 target-s390x/kvm.c   |    6 +-
 vl.c                 |    2 +-
 13 files changed, 256 insertions(+), 190 deletions(-)

[Qemu-devel] [PATCH 01/18] kvm: x86: Swallow KVM_EXIT_SET_TPR

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

This exit only triggers activity in the common exit path, but we should
accept it in order to be able to detect unknown exit types.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 target-i386/kvm.c |    3 +++
 1 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index fda07d2..0aeb079 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -1534,6 +1534,9 @@ int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run)
         DPRINTF("handle_hlt\n");
         ret = kvm_handle_halt(env);
         break;
+    case KVM_EXIT_SET_TPR:
+        ret = 1;
+        break;
     }
 
     return ret;
-- 
1.7.1

[Qemu-devel] [PATCH 02/18] kvm: Stop on all fatal exit reasons

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

Ensure that we stop the guest whenever we face a fatal or unknown exit
reason. If we stop, we also have to enforce a cpu loop exit.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 kvm-all.c         |   15 +++++++++++----
 target-i386/kvm.c |    4 ++++
 target-ppc/kvm.c  |    4 ++++
 3 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/kvm-all.c b/kvm-all.c
index 86ddbd6..eaf9272 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -815,7 +815,7 @@ static int kvm_handle_io(uint16_t port, void *data, int direction, int size,
 }
 
 #ifdef KVM_CAP_INTERNAL_ERROR_DATA
-static void kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
+static int kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
 {
 
     if (kvm_check_extension(kvm_state, KVM_CAP_INTERNAL_ERROR_DATA)) {
@@ -833,13 +833,13 @@ static void kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
     if (run->internal.suberror == KVM_INTERNAL_ERROR_EMULATION) {
         fprintf(stderr, "emulation failure\n");
         if (!kvm_arch_stop_on_emulation_error(env)) {
-            return;
+            return 0;
         }
     }
     /* FIXME: Should trigger a qmp message to let management know
      * something went wrong.
      */
-    vm_stop(0);
+    return -1;
 }
 #endif
 
@@ -967,16 +967,19 @@ int kvm_cpu_exec(CPUState *env)
             break;
         case KVM_EXIT_UNKNOWN:
             DPRINTF("kvm_exit_unknown\n");
+            ret = -1;
             break;
         case KVM_EXIT_FAIL_ENTRY:
             DPRINTF("kvm_exit_fail_entry\n");
+            ret = -1;
             break;
         case KVM_EXIT_EXCEPTION:
             DPRINTF("kvm_exit_exception\n");
+            ret = -1;
             break;
 #ifdef KVM_CAP_INTERNAL_ERROR_DATA
         case KVM_EXIT_INTERNAL_ERROR:
-            kvm_handle_internal_error(env, run);
+            ret = kvm_handle_internal_error(env, run);
             break;
 #endif
         case KVM_EXIT_DEBUG:
@@ -997,6 +1000,10 @@ int kvm_cpu_exec(CPUState *env)
         }
     } while (ret > 0);
 
+    if (ret < 0) {
+        vm_stop(0);
+        env->exit_request = 1;
+    }
     if (env->exit_request) {
         env->exit_request = 0;
         env->exception_index = EXCP_INTERRUPT;
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 0aeb079..6b4abaa 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -1537,6 +1537,10 @@ int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run)
     case KVM_EXIT_SET_TPR:
         ret = 1;
         break;
+    default:
+        fprintf(stderr, "KVM: unknown exit reason %d\n", run->exit_reason);
+        ret = -1;
+        break;
     }
 
     return ret;
diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
index 5caa07c..849b404 100644
--- a/target-ppc/kvm.c
+++ b/target-ppc/kvm.c
@@ -307,6 +307,10 @@ int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run)
         dprintf("handle halt\n");
         ret = kvmppc_handle_halt(env);
         break;
+    default:
+        fprintf(stderr, "KVM: unknown exit reason %d\n", run->exit_reason);
+        ret = -1;
+        break;
     }
 
     return ret;
-- 
1.7.1

[Qemu-devel] [PATCH 03/18] kvm: Improve reporting of fatal errors

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

Report KVM_EXIT_UNKNOWN, KVM_EXIT_FAIL_ENTRY, and KVM_EXIT_EXCEPTION
with more details to stderr. The latter two are so far x86-only, so move
them into the arch-specific handler. Integrate the Intel real mode
warning on KVM_EXIT_FAIL_ENTRY that qemu-kvm carries, but actually
restrict it to Intel CPUs. Moreover, always dump the CPU state in case
we fail.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 kvm-all.c           |   22 ++++++++--------------
 target-i386/cpu.h   |    2 ++
 target-i386/cpuid.c |    5 ++---
 target-i386/kvm.c   |   33 +++++++++++++++++++++++++++++++++
 4 files changed, 45 insertions(+), 17 deletions(-)

diff --git a/kvm-all.c b/kvm-all.c
index eaf9272..10e1194 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -817,22 +817,22 @@ static int kvm_handle_io(uint16_t port, void *data, int direction, int size,
 #ifdef KVM_CAP_INTERNAL_ERROR_DATA
 static int kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
 {
-
+    fprintf(stderr, "KVM internal error.");
     if (kvm_check_extension(kvm_state, KVM_CAP_INTERNAL_ERROR_DATA)) {
         int i;
 
-        fprintf(stderr, "KVM internal error. Suberror: %d\n",
-                run->internal.suberror);
-
+        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");
     }
-    cpu_dump_state(env, stderr, fprintf, 0);
     if (run->internal.suberror == KVM_INTERNAL_ERROR_EMULATION) {
         fprintf(stderr, "emulation failure\n");
         if (!kvm_arch_stop_on_emulation_error(env)) {
+            cpu_dump_state(env, stderr, fprintf, 0);
             return 0;
         }
     }
@@ -966,15 +966,8 @@ int kvm_cpu_exec(CPUState *env)
             ret = 1;
             break;
         case KVM_EXIT_UNKNOWN:
-            DPRINTF("kvm_exit_unknown\n");
-            ret = -1;
-            break;
-        case KVM_EXIT_FAIL_ENTRY:
-            DPRINTF("kvm_exit_fail_entry\n");
-            ret = -1;
-            break;
-        case KVM_EXIT_EXCEPTION:
-            DPRINTF("kvm_exit_exception\n");
+            fprintf(stderr, "KVM: unknown exit, hardware reason %" PRIx64 "\n",
+                    (uint64_t)run->hw.hardware_exit_reason);
             ret = -1;
             break;
 #ifdef KVM_CAP_INTERNAL_ERROR_DATA
@@ -1001,6 +994,7 @@ int kvm_cpu_exec(CPUState *env)
     } while (ret > 0);
 
     if (ret < 0) {
+        cpu_dump_state(env, stderr, fprintf, 0);
         vm_stop(0);
         env->exit_request = 1;
     }
diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index dddcd74..a457423 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -874,6 +874,8 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
                    uint32_t *ecx, uint32_t *edx);
 int cpu_x86_register (CPUX86State *env, const char *cpu_model);
 void cpu_clear_apic_feature(CPUX86State *env);
+void host_cpuid(uint32_t function, uint32_t count,
+                uint32_t *eax, uint32_t *ebx, uint32_t *ecx, uint32_t *edx);
 
 /* helper.c */
 int cpu_x86_handle_mmu_fault(CPUX86State *env, target_ulong addr,
diff --git a/target-i386/cpuid.c b/target-i386/cpuid.c
index 165045e..5382a28 100644
--- a/target-i386/cpuid.c
+++ b/target-i386/cpuid.c
@@ -103,9 +103,8 @@ typedef struct model_features_t {
 int check_cpuid = 0;
 int enforce_cpuid = 0;
 
-static void host_cpuid(uint32_t function, uint32_t count,
-                       uint32_t *eax, uint32_t *ebx,
-                       uint32_t *ecx, uint32_t *edx)
+void host_cpuid(uint32_t function, uint32_t count,
+                uint32_t *eax, uint32_t *ebx, uint32_t *ecx, uint32_t *edx)
 {
 #if defined(CONFIG_KVM)
     uint32_t vec[4];
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 6b4abaa..0ba13fc 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -1525,8 +1525,19 @@ static int kvm_handle_halt(CPUState *env)
     return 1;
 }
 
+static bool host_supports_vmx(void)
+{
+    uint32_t ecx, unused;
+
+    host_cpuid(1, 0, &unused, &unused, &ecx, &unused);
+    return ecx & CPUID_EXT_VMX;
+}
+
+#define VMX_INVALID_GUEST_STATE 0x80000021
+
 int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run)
 {
+    uint64_t code;
     int ret = 0;
 
     switch (run->exit_reason) {
@@ -1537,6 +1548,28 @@ int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run)
     case KVM_EXIT_SET_TPR:
         ret = 1;
         break;
+    case KVM_EXIT_FAIL_ENTRY:
+        code = run->fail_entry.hardware_entry_failure_reason;
+        fprintf(stderr, "KVM: entry failed, hardware error 0x%" PRIx64 "\n",
+                code);
+        if (host_supports_vmx() && code == VMX_INVALID_GUEST_STATE) {
+            fprintf(stderr,
+                    "\nIf you're runnning a guest on an Intel machine without "
+                        "unrestricted mode\n"
+                    "support, the failure can be most likely due to the guest "
+                        "entering an invalid\n"
+                    "state for Intel VT. For example, the guest maybe running "
+                        "in big real mode\n"
+                    "which is not supported on less recent Intel processors."
+                        "\n\n");
+        }
+        ret = -1;
+        break;
+    case KVM_EXIT_EXCEPTION:
+        fprintf(stderr, "KVM: exception %d exit (error code 0x%x)\n",
+                run->ex.exception, run->ex.error_code);
+        ret = -1;
+        break;
     default:
         fprintf(stderr, "KVM: unknown exit reason %d\n", run->exit_reason);
         ret = -1;
-- 
1.7.1

[Qemu-devel] [PATCH 04/18] x86: Optionally dump code bytes on cpu_dump_state

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

Introduce the cpu_dump_state flag CPU_DUMP_CODE and implement it for
x86. This writes out the code bytes around the current instruction
pointer. Make use of this feature in KVM to help debugging fatal vm
exits.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 cpu-all.h            |    2 ++
 kvm-all.c            |    4 ++--
 target-i386/helper.c |   21 +++++++++++++++++++++
 3 files changed, 25 insertions(+), 2 deletions(-)

diff --git a/cpu-all.h b/cpu-all.h
index 4ce4e83..ffbd6a4 100644
--- a/cpu-all.h
+++ b/cpu-all.h
@@ -765,6 +765,8 @@ int page_check_range(target_ulong start, target_ulong len, int flags);
 CPUState *cpu_copy(CPUState *env);
 CPUState *qemu_get_cpu(int cpu);
 
+#define CPU_DUMP_CODE 0x00010000
+
 void cpu_dump_state(CPUState *env, FILE *f, fprintf_function cpu_fprintf,
                     int flags);
 void cpu_dump_statistics(CPUState *env, FILE *f, fprintf_function cpu_fprintf,
diff --git a/kvm-all.c b/kvm-all.c
index 10e1194..41decde 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -832,7 +832,7 @@ static int kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
     if (run->internal.suberror == KVM_INTERNAL_ERROR_EMULATION) {
         fprintf(stderr, "emulation failure\n");
         if (!kvm_arch_stop_on_emulation_error(env)) {
-            cpu_dump_state(env, stderr, fprintf, 0);
+            cpu_dump_state(env, stderr, fprintf, CPU_DUMP_CODE);
             return 0;
         }
     }
@@ -994,7 +994,7 @@ int kvm_cpu_exec(CPUState *env)
     } while (ret > 0);
 
     if (ret < 0) {
-        cpu_dump_state(env, stderr, fprintf, 0);
+        cpu_dump_state(env, stderr, fprintf, CPU_DUMP_CODE);
         vm_stop(0);
         env->exit_request = 1;
     }
diff --git a/target-i386/helper.c b/target-i386/helper.c
index 6dfa27d..1217452 100644
--- a/target-i386/helper.c
+++ b/target-i386/helper.c
@@ -249,6 +249,9 @@ done:
     cpu_fprintf(f, "\n");
 }
 
+#define DUMP_CODE_BYTES_TOTAL    50
+#define DUMP_CODE_BYTES_BACKWARD 20
+
 void cpu_dump_state(CPUState *env, FILE *f, fprintf_function cpu_fprintf,
                     int flags)
 {
@@ -434,6 +437,24 @@ void cpu_dump_state(CPUState *env, FILE *f, fprintf_function cpu_fprintf,
                 cpu_fprintf(f, " ");
         }
     }
+    if (flags & CPU_DUMP_CODE) {
+        target_ulong base = env->segs[R_CS].base + env->eip;
+        target_ulong offs = MIN(env->eip, DUMP_CODE_BYTES_BACKWARD);
+        uint8_t code;
+        char codestr[3];
+
+        cpu_fprintf(f, "Code=");
+        for (i = 0; i < DUMP_CODE_BYTES_TOTAL; i++) {
+            if (cpu_memory_rw_debug(env, base - offs + i, &code, 1, 0) == 0) {
+                snprintf(codestr, sizeof(codestr), "%02x", code);
+            } else {
+                snprintf(codestr, sizeof(codestr), "??");
+            }
+            cpu_fprintf(f, "%s%s%s%s", i > 0 ? " " : "",
+                        i == offs ? "<" : "", codestr, i == offs ? ">" : "");
+        }
+        cpu_fprintf(f, "\n");
+    }
 }
 
 /***********************************************************/
-- 
1.7.1

[Qemu-devel] [PATCH 05/18] kvm: x86: Align kvm_arch_put_registers code with comment

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

The ordering doesn't matter in this case, but better keep it consistent.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 target-i386/kvm.c |    6 +++---
 1 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 0ba13fc..9bb34ab 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -1388,12 +1388,12 @@ int kvm_arch_put_registers(CPUState *env, int level)
     if (ret < 0) {
         return ret;
     }
-    /* must be last */
-    ret = kvm_guest_debug_workarounds(env);
+    ret = kvm_put_debugregs(env);
     if (ret < 0) {
         return ret;
     }
-    ret = kvm_put_debugregs(env);
+    /* must be last */
+    ret = kvm_guest_debug_workarounds(env);
     if (ret < 0) {
         return ret;
     }
-- 
1.7.1

[Qemu-devel] [PATCH 06/18] kvm: x86: Prepare kvm_get_mp_state for in-kernel irqchip

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

This code path will not yet be taken as we still lack in-kernel irqchip
support. But qemu-kvm can already make use of it and drop its own
mp_state access services.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 target-i386/kvm.c |    3 +++
 1 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 9bb34ab..531b69e 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -1198,6 +1198,9 @@ static int kvm_get_mp_state(CPUState *env)
         return ret;
     }
     env->mp_state = mp_state.mp_state;
+    if (kvm_irqchip_in_kernel()) {
+        env->halted = (mp_state.mp_state == KVM_MP_STATE_HALTED);
+    }
     return 0;
 }
 
-- 
1.7.1

[Qemu-devel] [PATCH 07/18] kvm: x86: Remove redundant mp_state initialization

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

kvm_arch_reset_vcpu initializes mp_state, and that function is invoked
right after kvm_arch_init_vcpu.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 target-i386/kvm.c |    2 --
 1 files changed, 0 insertions(+), 2 deletions(-)

diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 531b69e..07c75c0 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -321,8 +321,6 @@ int kvm_arch_init_vcpu(CPUState *env)
     uint32_t signature[3];
 #endif
 
-    env->mp_state = KVM_MP_STATE_RUNNABLE;
-
     env->cpuid_features &= kvm_arch_get_supported_cpuid(env, 1, 0, R_EDX);
 
     i = env->cpuid_ext_features & CPUID_EXT_HYPERVISOR;
-- 
1.7.1

[Qemu-devel] [PATCH 08/18] kvm: x86: Fix xcr0 reset mismerge

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

For unknown reasons, xcr0 reset ended up in kvm_arch_update_guest_debug
on upstream merge. Fix this and also remove the misleading comment (1 is
THE reset value).

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 target-i386/kvm.c |    3 +--
 1 files changed, 1 insertions(+), 2 deletions(-)

diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 07c75c0..c4a22dd 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -450,6 +450,7 @@ void kvm_arch_reset_vcpu(CPUState *env)
     env->interrupt_injected = -1;
     env->nmi_injected = 0;
     env->nmi_pending = 0;
+    env->xcr0 = 1;
     if (kvm_irqchip_in_kernel()) {
         env->mp_state = cpu_is_bsp(env) ? KVM_MP_STATE_RUNNABLE :
                                           KVM_MP_STATE_UNINITIALIZED;
@@ -1759,8 +1760,6 @@ void kvm_arch_update_guest_debug(CPUState *env, struct kvm_guest_debug *dbg)
                 ((uint32_t)len_code[hw_breakpoint[n].len] << (18 + n*4));
         }
     }
-    /* Legal xcr0 for loading */
-    env->xcr0 = 1;
 }
 #endif /* KVM_CAP_SET_GUEST_DEBUG */
 
-- 
1.7.1

[Qemu-devel] [PATCH 09/18] kvm: x86: Refactor msr_star/hsave_pa setup and checks

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

Simplify kvm_has_msr_star/hsave_pa to booleans and push their one-time
initialization into kvm_arch_init. Also handle potential errors of that
setup procedure.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 target-i386/kvm.c |   47 +++++++++++++++++++----------------------------
 1 files changed, 19 insertions(+), 28 deletions(-)

diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index c4a22dd..454ddb1 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -54,6 +54,8 @@
 #define BUS_MCEERR_AO 5
 #endif
 
+static bool has_msr_star;
+static bool has_msr_hsave_pa;
 static int lm_capable_kernel;
 
 #ifdef KVM_CAP_EXT_CPUID
@@ -459,13 +461,10 @@ void kvm_arch_reset_vcpu(CPUState *env)
     }
 }
 
-int has_msr_star;
-int has_msr_hsave_pa;
-
-static void kvm_supported_msrs(CPUState *env)
+static int kvm_get_supported_msrs(KVMState *s)
 {
     static int kvm_supported_msrs;
-    int ret;
+    int ret = 0;
 
     /* first time */
     if (kvm_supported_msrs == 0) {
@@ -476,9 +475,9 @@ static void kvm_supported_msrs(CPUState *env)
         /* Obtain MSR list from KVM.  These are the MSRs that we must
          * save/restore */
         msr_list.nmsrs = 0;
-        ret = kvm_ioctl(env->kvm_state, KVM_GET_MSR_INDEX_LIST, &msr_list);
+        ret = kvm_ioctl(s, KVM_GET_MSR_INDEX_LIST, &msr_list);
         if (ret < 0 && ret != -E2BIG) {
-            return;
+            return ret;
         }
         /* Old kernel modules had a bug and could write beyond the provided
            memory. Allocate at least a safe amount of 1K. */
@@ -487,17 +486,17 @@ static void kvm_supported_msrs(CPUState *env)
                                               sizeof(msr_list.indices[0])));
 
         kvm_msr_list->nmsrs = msr_list.nmsrs;
-        ret = kvm_ioctl(env->kvm_state, KVM_GET_MSR_INDEX_LIST, kvm_msr_list);
+        ret = kvm_ioctl(s, KVM_GET_MSR_INDEX_LIST, kvm_msr_list);
         if (ret >= 0) {
             int i;
 
             for (i = 0; i < kvm_msr_list->nmsrs; i++) {
                 if (kvm_msr_list->indices[i] == MSR_STAR) {
-                    has_msr_star = 1;
+                    has_msr_star = true;
                     continue;
                 }
                 if (kvm_msr_list->indices[i] == MSR_VM_HSAVE_PA) {
-                    has_msr_hsave_pa = 1;
+                    has_msr_hsave_pa = true;
                     continue;
                 }
             }
@@ -506,19 +505,7 @@ static void kvm_supported_msrs(CPUState *env)
         free(kvm_msr_list);
     }
 
-    return;
-}
-
-static int kvm_has_msr_hsave_pa(CPUState *env)
-{
-    kvm_supported_msrs(env);
-    return has_msr_hsave_pa;
-}
-
-static int kvm_has_msr_star(CPUState *env)
-{
-    kvm_supported_msrs(env);
-    return has_msr_star;
+    return ret;
 }
 
 static int kvm_init_identity_map_page(KVMState *s)
@@ -543,9 +530,13 @@ static int kvm_init_identity_map_page(KVMState *s)
 int kvm_arch_init(KVMState *s, int smp_cpus)
 {
     int ret;
-
     struct utsname utsname;
 
+    ret = kvm_get_supported_msrs(s);
+    if (ret < 0) {
+        return ret;
+    }
+
     uname(&utsname);
     lm_capable_kernel = strcmp(utsname.machine, "x86_64") == 0;
 
@@ -830,10 +821,10 @@ static int kvm_put_msrs(CPUState *env, int level)
     kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_CS, env->sysenter_cs);
     kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_ESP, env->sysenter_esp);
     kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_EIP, env->sysenter_eip);
-    if (kvm_has_msr_star(env)) {
+    if (has_msr_star) {
         kvm_msr_entry_set(&msrs[n++], MSR_STAR, env->star);
     }
-    if (kvm_has_msr_hsave_pa(env)) {
+    if (has_msr_hsave_pa) {
         kvm_msr_entry_set(&msrs[n++], MSR_VM_HSAVE_PA, env->vm_hsave);
     }
 #ifdef TARGET_X86_64
@@ -1076,10 +1067,10 @@ static int kvm_get_msrs(CPUState *env)
     msrs[n++].index = MSR_IA32_SYSENTER_CS;
     msrs[n++].index = MSR_IA32_SYSENTER_ESP;
     msrs[n++].index = MSR_IA32_SYSENTER_EIP;
-    if (kvm_has_msr_star(env)) {
+    if (has_msr_star) {
         msrs[n++].index = MSR_STAR;
     }
-    if (kvm_has_msr_hsave_pa(env)) {
+    if (has_msr_hsave_pa) {
         msrs[n++].index = MSR_VM_HSAVE_PA;
     }
     msrs[n++].index = MSR_IA32_TSC;
-- 
1.7.1

[Qemu-devel] [PATCH 10/18] kvm: x86: Reset paravirtual MSRs

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

Make sure to write the cleared MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
and MSR_KVM_ASYNC_PF_EN to the kernel state so that a freshly booted
guest cannot be disturbed by old values.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
CC: Glauber Costa <glommer@redhat.com>
---
 target-i386/kvm.c |    7 +++++++
 1 files changed, 7 insertions(+), 0 deletions(-)

diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 454ddb1..825af42 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -845,6 +845,13 @@ static int kvm_put_msrs(CPUState *env, int level)
         if (smp_cpus == 1 || env->tsc != 0) {
             kvm_msr_entry_set(&msrs[n++], MSR_IA32_TSC, env->tsc);
         }
+    }
+    /*
+     * The following paravirtual MSRs have side effects on the guest or are
+     * too heavy for normal writeback. Limit them to reset or full state
+     * updates.
+     */
+    if (level >= KVM_PUT_RESET_STATE) {
         kvm_msr_entry_set(&msrs[n++], MSR_KVM_SYSTEM_TIME,
                           env->system_time_msr);
         kvm_msr_entry_set(&msrs[n++], MSR_KVM_WALL_CLOCK, env->wall_clock_msr);
-- 
1.7.1

[Qemu-devel] [PATCH 11/18] kvm: x86: Fix !CONFIG_KVM_PARA build

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

If we lack kvm_para.h, MSR_KVM_ASYNC_PF_EN is not defined. The change in
kvm_arch_init_vcpu is just for consistency reasons.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 target-i386/kvm.c |    8 ++++----
 1 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 825af42..feaf33d 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -319,7 +319,7 @@ int kvm_arch_init_vcpu(CPUState *env)
     uint32_t limit, i, j, cpuid_i;
     uint32_t unused;
     struct kvm_cpuid_entry2 *c;
-#ifdef KVM_CPUID_SIGNATURE
+#ifdef CONFIG_KVM_PARA
     uint32_t signature[3];
 #endif
 
@@ -855,7 +855,7 @@ static int kvm_put_msrs(CPUState *env, int level)
         kvm_msr_entry_set(&msrs[n++], MSR_KVM_SYSTEM_TIME,
                           env->system_time_msr);
         kvm_msr_entry_set(&msrs[n++], MSR_KVM_WALL_CLOCK, env->wall_clock_msr);
-#ifdef KVM_CAP_ASYNC_PF
+#if defined(CONFIG_KVM_PARA) && defined(KVM_CAP_ASYNC_PF)
         kvm_msr_entry_set(&msrs[n++], MSR_KVM_ASYNC_PF_EN, env->async_pf_en_msr);
 #endif
     }
@@ -1091,7 +1091,7 @@ static int kvm_get_msrs(CPUState *env)
 #endif
     msrs[n++].index = MSR_KVM_SYSTEM_TIME;
     msrs[n++].index = MSR_KVM_WALL_CLOCK;
-#ifdef KVM_CAP_ASYNC_PF
+#if defined(CONFIG_KVM_PARA) && defined(KVM_CAP_ASYNC_PF)
     msrs[n++].index = MSR_KVM_ASYNC_PF_EN;
 #endif
 
@@ -1167,7 +1167,7 @@ static int kvm_get_msrs(CPUState *env)
             }
 #endif
             break;
-#ifdef KVM_CAP_ASYNC_PF
+#if defined(CONFIG_KVM_PARA) && defined(KVM_CAP_ASYNC_PF)
         case MSR_KVM_ASYNC_PF_EN:
             env->async_pf_en_msr = msrs[i].data;
             break;
-- 
1.7.1

[Qemu-devel] [PATCH 12/18] kvm: Drop smp_cpus argument from init functions

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

No longer used.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 kvm-all.c          |    4 ++--
 kvm-stub.c         |    2 +-
 kvm.h              |    4 ++--
 target-i386/kvm.c  |    2 +-
 target-ppc/kvm.c   |    2 +-
 target-s390x/kvm.c |    2 +-
 vl.c               |    2 +-
 7 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/kvm-all.c b/kvm-all.c
index 41decde..8053f92 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -636,7 +636,7 @@ static CPUPhysMemoryClient kvm_cpu_phys_memory_client = {
     .migration_log = kvm_client_migration_log,
 };
 
-int kvm_init(int smp_cpus)
+int kvm_init(void)
 {
     static const char upgrade_note[] =
         "Please upgrade to at least kernel 2.6.29 or recent kvm-kmod\n"
@@ -749,7 +749,7 @@ int kvm_init(int smp_cpus)
     s->xcrs = kvm_check_extension(s, KVM_CAP_XCRS);
 #endif
 
-    ret = kvm_arch_init(s, smp_cpus);
+    ret = kvm_arch_init(s);
     if (ret < 0) {
         goto err;
     }
diff --git a/kvm-stub.c b/kvm-stub.c
index 33d4476..88682f2 100644
--- a/kvm-stub.c
+++ b/kvm-stub.c
@@ -58,7 +58,7 @@ int kvm_check_extension(KVMState *s, unsigned int extension)
     return 0;
 }
 
-int kvm_init(int smp_cpus)
+int kvm_init(void)
 {
     return -ENOSYS;
 }
diff --git a/kvm.h b/kvm.h
index ce08d42..a971752 100644
--- a/kvm.h
+++ b/kvm.h
@@ -34,7 +34,7 @@ struct kvm_run;
 
 /* external API */
 
-int kvm_init(int smp_cpus);
+int kvm_init(void);
 
 int kvm_has_sync_mmu(void);
 int kvm_has_vcpu_events(void);
@@ -105,7 +105,7 @@ int kvm_arch_get_registers(CPUState *env);
 
 int kvm_arch_put_registers(CPUState *env, int level);
 
-int kvm_arch_init(KVMState *s, int smp_cpus);
+int kvm_arch_init(KVMState *s);
 
 int kvm_arch_init_vcpu(CPUState *env);
 
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index feaf33d..016b67d 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -527,7 +527,7 @@ static int kvm_init_identity_map_page(KVMState *s)
     return 0;
 }
 
-int kvm_arch_init(KVMState *s, int smp_cpus)
+int kvm_arch_init(KVMState *s)
 {
     int ret;
     struct utsname utsname;
diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
index 849b404..3c05630 100644
--- a/target-ppc/kvm.c
+++ b/target-ppc/kvm.c
@@ -56,7 +56,7 @@ static void kvm_kick_env(void *env)
     qemu_cpu_kick(env);
 }
 
-int kvm_arch_init(KVMState *s, int smp_cpus)
+int kvm_arch_init(KVMState *s)
 {
 #ifdef KVM_CAP_PPC_UNSET_IRQ
     cap_interrupt_unset = kvm_check_extension(s, KVM_CAP_PPC_UNSET_IRQ);
diff --git a/target-s390x/kvm.c b/target-s390x/kvm.c
index adf4a9e..b177e10 100644
--- a/target-s390x/kvm.c
+++ b/target-s390x/kvm.c
@@ -70,7 +70,7 @@
 #define SCLP_CMDW_READ_SCP_INFO         0x00020001
 #define SCLP_CMDW_READ_SCP_INFO_FORCED  0x00120001
 
-int kvm_arch_init(KVMState *s, int smp_cpus)
+int kvm_arch_init(KVMState *s)
 {
     return 0;
 }
diff --git a/vl.c b/vl.c
index 0292184..33f844f 100644
--- a/vl.c
+++ b/vl.c
@@ -2836,7 +2836,7 @@ int main(int argc, char **argv, char **envp)
     }
 
     if (kvm_allowed) {
-        int ret = kvm_init(smp_cpus);
+        int ret = kvm_init();
         if (ret < 0) {
             if (!kvm_available()) {
                 printf("KVM not supported for this target\n");
-- 
1.7.1

[Qemu-devel] [PATCH 13/18] kvm: Consolidate must-have capability checks

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

Instead of splattering the code with #ifdefs and runtime checks for
capabilities we cannot work without anyway, provide central test
infrastructure for verifying their availability both at build and
runtime.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 configure          |   39 ++++++++++++++++++++----------
 kvm-all.c          |   67 +++++++++++++++++++++-------------------------------
 kvm.h              |   10 +++++++
 target-i386/kvm.c  |   39 ++++++------------------------
 target-ppc/kvm.c   |    4 +++
 target-s390x/kvm.c |    4 +++
 6 files changed, 79 insertions(+), 84 deletions(-)

diff --git a/configure b/configure
index 9a02d1f..4673bf0 100755
--- a/configure
+++ b/configure
@@ -1662,18 +1662,31 @@ if test "$kvm" != "no" ; then
 #if !defined(KVM_API_VERSION) || KVM_API_VERSION < 12 || KVM_API_VERSION > 12
 #error Invalid KVM version
 #endif
-#if !defined(KVM_CAP_USER_MEMORY)
-#error Missing KVM capability KVM_CAP_USER_MEMORY
-#endif
-#if !defined(KVM_CAP_SET_TSS_ADDR)
-#error Missing KVM capability KVM_CAP_SET_TSS_ADDR
-#endif
-#if !defined(KVM_CAP_DESTROY_MEMORY_REGION_WORKS)
-#error Missing KVM capability KVM_CAP_DESTROY_MEMORY_REGION_WORKS
-#endif
-#if !defined(KVM_CAP_USER_NMI)
-#error Missing KVM capability KVM_CAP_USER_NMI
+EOF
+    must_have_caps="KVM_CAP_USER_MEMORY \
+                    KVM_CAP_DESTROY_MEMORY_REGION_WORKS \
+                    KVM_CAP_COALESCED_MMIO \
+                    KVM_CAP_SYNC_MMU \
+                   "
+    if test \( "$cpu" = "i386" -o "$cpu" = "x86_64" \) ; then
+      must_have_caps="$caps \
+                      KVM_CAP_SET_TSS_ADDR \
+                      KVM_CAP_EXT_CPUID \
+                      KVM_CAP_CLOCKSOURCE \
+                      KVM_CAP_NOP_IO_DELAY \
+                      KVM_CAP_PV_MMU \
+                      KVM_CAP_MP_STATE \
+                      KVM_CAP_USER_NMI \
+                     "
+    fi
+    for c in $must_have_caps ; do
+      cat >> $TMPC <<EOF
+#if !defined($c)
+#error Missing KVM capability $c
 #endif
+EOF
+    done
+    cat >> $TMPC <<EOF
 int main(void) { return 0; }
 EOF
   if test "$kerneldir" != "" ; then
@@ -1708,8 +1721,8 @@ EOF
 	| awk -F "error: " '{if (NR>1) printf(", "); printf("%s",$2);}'`
         if test "$kvmerr" != "" ; then
           echo -e "${kvmerr}\n\
-      NOTE: To enable KVM support, update your kernel to 2.6.29+ or install \
-  recent kvm-kmod from http://sourceforge.net/projects/kvm."
+NOTE: To enable KVM support, update your kernel to 2.6.29+ or install \
+recent kvm-kmod from http://sourceforge.net/projects/kvm."
         fi
       fi
       feature_not_found "kvm"
diff --git a/kvm-all.c b/kvm-all.c
index 8053f92..3a1f63b 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -63,9 +63,7 @@ struct KVMState
     int fd;
     int vmfd;
     int coalesced_mmio;
-#ifdef KVM_CAP_COALESCED_MMIO
     struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
-#endif
     int broken_set_mem_region;
     int migration_log;
     int vcpu_events;
@@ -82,6 +80,12 @@ struct KVMState
 
 static KVMState *kvm_state;
 
+static const KVMCapabilityInfo kvm_required_capabilites[] = {
+    KVM_CAP_INFO(USER_MEMORY),
+    KVM_CAP_INFO(DESTROY_MEMORY_REGION_WORKS),
+    KVM_CAP_LAST_INFO
+};
+
 static KVMSlot *kvm_alloc_slot(KVMState *s)
 {
     int i;
@@ -227,12 +231,10 @@ int kvm_init_vcpu(CPUState *env)
         goto err;
     }
 
-#ifdef KVM_CAP_COALESCED_MMIO
     if (s->coalesced_mmio && !s->coalesced_mmio_ring) {
         s->coalesced_mmio_ring =
             (void *)env->kvm_run + s->coalesced_mmio * PAGE_SIZE;
     }
-#endif
 
     ret = kvm_arch_init_vcpu(env);
     if (ret == 0) {
@@ -401,7 +403,6 @@ static int kvm_physical_sync_dirty_bitmap(target_phys_addr_t start_addr,
 int kvm_coalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
 {
     int ret = -ENOSYS;
-#ifdef KVM_CAP_COALESCED_MMIO
     KVMState *s = kvm_state;
 
     if (s->coalesced_mmio) {
@@ -412,7 +413,6 @@ int kvm_coalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
 
         ret = kvm_vm_ioctl(s, KVM_REGISTER_COALESCED_MMIO, &zone);
     }
-#endif
 
     return ret;
 }
@@ -420,7 +420,6 @@ int kvm_coalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
 int kvm_uncoalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
 {
     int ret = -ENOSYS;
-#ifdef KVM_CAP_COALESCED_MMIO
     KVMState *s = kvm_state;
 
     if (s->coalesced_mmio) {
@@ -431,7 +430,6 @@ int kvm_uncoalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
 
         ret = kvm_vm_ioctl(s, KVM_UNREGISTER_COALESCED_MMIO, &zone);
     }
-#endif
 
     return ret;
 }
@@ -481,6 +479,18 @@ static int kvm_check_many_ioeventfds(void)
 #endif
 }
 
+static const KVMCapabilityInfo *
+kvm_check_extension_list(KVMState *s, const KVMCapabilityInfo *list)
+{
+    while (list->name) {
+        if (!kvm_check_extension(s, list->value)) {
+            return list;
+        }
+        list++;
+    }
+    return NULL;
+}
+
 static void kvm_set_phys_mem(target_phys_addr_t start_addr, ram_addr_t size,
                              ram_addr_t phys_offset)
 {
@@ -642,6 +652,7 @@ int kvm_init(void)
         "Please upgrade to at least kernel 2.6.29 or recent kvm-kmod\n"
         "(see http://sourceforge.net/projects/kvm).\n";
     KVMState *s;
+    const KVMCapabilityInfo *missing_cap;
     int ret;
     int i;
 
@@ -685,35 +696,19 @@ int kvm_init(void)
         goto err;
     }
 
-    /* initially, KVM allocated its own memory and we had to jump through
-     * hooks to make phys_ram_base point to this.  Modern versions of KVM
-     * just use a user allocated buffer so we can use regular pages
-     * unmodified.  Make sure we have a sufficiently modern version of KVM.
-     */
-    if (!kvm_check_extension(s, KVM_CAP_USER_MEMORY)) {
-        ret = -EINVAL;
-        fprintf(stderr, "kvm does not support KVM_CAP_USER_MEMORY\n%s",
-                upgrade_note);
-        goto err;
+    missing_cap = kvm_check_extension_list(s, kvm_required_capabilites);
+    if (!missing_cap) {
+        missing_cap =
+            kvm_check_extension_list(s, kvm_arch_required_capabilities);
     }
-
-    /* There was a nasty bug in < kvm-80 that prevents memory slots from being
-     * destroyed properly.  Since we rely on this capability, refuse to work
-     * with any kernel without this capability. */
-    if (!kvm_check_extension(s, KVM_CAP_DESTROY_MEMORY_REGION_WORKS)) {
+    if (missing_cap) {
         ret = -EINVAL;
-
-        fprintf(stderr,
-                "KVM kernel module broken (DESTROY_MEMORY_REGION).\n%s",
-                upgrade_note);
+        fprintf(stderr, "kvm does not support %s\n%s",
+                missing_cap->name, upgrade_note);
         goto err;
     }
 
-    s->coalesced_mmio = 0;
-#ifdef KVM_CAP_COALESCED_MMIO
     s->coalesced_mmio = kvm_check_extension(s, KVM_CAP_COALESCED_MMIO);
-    s->coalesced_mmio_ring = NULL;
-#endif
 
     s->broken_set_mem_region = 1;
 #ifdef KVM_CAP_JOIN_MEMORY_REGIONS_WORKS
@@ -845,7 +840,6 @@ static int kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
 
 void kvm_flush_coalesced_mmio_buffer(void)
 {
-#ifdef KVM_CAP_COALESCED_MMIO
     KVMState *s = kvm_state;
     if (s->coalesced_mmio_ring) {
         struct kvm_coalesced_mmio_ring *ring = s->coalesced_mmio_ring;
@@ -859,7 +853,6 @@ void kvm_flush_coalesced_mmio_buffer(void)
             ring->first = (ring->first + 1) % KVM_COALESCED_MMIO_MAX;
         }
     }
-#endif
 }
 
 static void do_kvm_cpu_synchronize_state(void *_env)
@@ -1059,13 +1052,7 @@ int kvm_vcpu_ioctl(CPUState *env, int type, ...)
 
 int kvm_has_sync_mmu(void)
 {
-#ifdef KVM_CAP_SYNC_MMU
-    KVMState *s = kvm_state;
-
-    return kvm_check_extension(s, KVM_CAP_SYNC_MMU);
-#else
-    return 0;
-#endif
+    return kvm_check_extension(kvm_state, KVM_CAP_SYNC_MMU);
 }
 
 int kvm_has_vcpu_events(void)
diff --git a/kvm.h b/kvm.h
index a971752..ca57517 100644
--- a/kvm.h
+++ b/kvm.h
@@ -32,6 +32,14 @@ extern int kvm_allowed;
 
 struct kvm_run;
 
+typedef struct KVMCapabilityInfo {
+    const char *name;
+    int value;
+} KVMCapabilityInfo;
+
+#define KVM_CAP_INFO(CAP) { "KVM_CAP_" stringify(CAP), KVM_CAP_##CAP }
+#define KVM_CAP_LAST_INFO { NULL, 0 }
+
 /* external API */
 
 int kvm_init(void);
@@ -86,6 +94,8 @@ int kvm_vcpu_ioctl(CPUState *env, int type, ...);
 
 /* Arch specific hooks */
 
+extern const KVMCapabilityInfo kvm_arch_required_capabilities[];
+
 int kvm_arch_post_run(CPUState *env, struct kvm_run *run);
 
 int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run);
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 016b67d..1db8227 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -54,12 +54,17 @@
 #define BUS_MCEERR_AO 5
 #endif
 
+const KVMCapabilityInfo kvm_arch_required_capabilities[] = {
+    KVM_CAP_INFO(SET_TSS_ADDR),
+    KVM_CAP_INFO(EXT_CPUID),
+    KVM_CAP_INFO(MP_STATE),
+    KVM_CAP_LAST_INFO
+};
+
 static bool has_msr_star;
 static bool has_msr_hsave_pa;
 static int lm_capable_kernel;
 
-#ifdef KVM_CAP_EXT_CPUID
-
 static struct kvm_cpuid2 *try_get_cpuid(KVMState *s, int max)
 {
     struct kvm_cpuid2 *cpuid;
@@ -93,10 +98,6 @@ uint32_t kvm_arch_get_supported_cpuid(CPUState *env, uint32_t function,
     uint32_t ret = 0;
     uint32_t cpuid_1_edx;
 
-    if (!kvm_check_extension(env->kvm_state, KVM_CAP_EXT_CPUID)) {
-        return -1U;
-    }
-
     max = 1;
     while ((cpuid = try_get_cpuid(env->kvm_state, max)) == NULL) {
         max *= 2;
@@ -140,30 +141,14 @@ uint32_t kvm_arch_get_supported_cpuid(CPUState *env, uint32_t function,
     return ret;
 }
 
-#else
-
-uint32_t kvm_arch_get_supported_cpuid(CPUState *env, uint32_t function,
-                                      uint32_t index, int reg)
-{
-    return -1U;
-}
-
-#endif
-
 #ifdef CONFIG_KVM_PARA
 struct kvm_para_features {
     int cap;
     int feature;
 } para_features[] = {
-#ifdef KVM_CAP_CLOCKSOURCE
     { KVM_CAP_CLOCKSOURCE, KVM_FEATURE_CLOCKSOURCE },
-#endif
-#ifdef KVM_CAP_NOP_IO_DELAY
     { KVM_CAP_NOP_IO_DELAY, KVM_FEATURE_NOP_IO_DELAY },
-#endif
-#ifdef KVM_CAP_PV_MMU
     { KVM_CAP_PV_MMU, KVM_FEATURE_MMU_OP },
-#endif
 #ifdef KVM_CAP_ASYNC_PF
     { KVM_CAP_ASYNC_PF, KVM_FEATURE_ASYNC_PF },
 #endif
@@ -542,15 +527,7 @@ int kvm_arch_init(KVMState *s)
 
     /* create vm86 tss.  KVM uses vm86 mode to emulate 16-bit code
      * directly.  In order to use vm86 mode, a TSS is needed.  Since this
-     * must be part of guest physical memory, we need to allocate it.  Older
-     * versions of KVM just assumed that it would be at the end of physical
-     * memory but that doesn't work with more than 4GB of memory.  We simply
-     * refuse to work with those older versions of KVM. */
-    ret = kvm_check_extension(s, KVM_CAP_SET_TSS_ADDR);
-    if (ret <= 0) {
-        fprintf(stderr, "kvm does not support KVM_CAP_SET_TSS_ADDR\n");
-        return ret;
-    }
+     * must be part of guest physical memory, we need to allocate it. */
 
     /* this address is 3 pages before the bios, and the bios should present
      * as unavaible memory.  FIXME, need to ensure the e820 map deals with
diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
index 3c05630..710eca1 100644
--- a/target-ppc/kvm.c
+++ b/target-ppc/kvm.c
@@ -37,6 +37,10 @@
     do { } while (0)
 #endif
 
+const KVMCapabilityInfo kvm_arch_required_capabilities[] = {
+    KVM_CAP_LAST_INFO
+};
+
 static int cap_interrupt_unset = false;
 static int cap_interrupt_level = false;
 
diff --git a/target-s390x/kvm.c b/target-s390x/kvm.c
index b177e10..38823f5 100644
--- a/target-s390x/kvm.c
+++ b/target-s390x/kvm.c
@@ -70,6 +70,10 @@
 #define SCLP_CMDW_READ_SCP_INFO         0x00020001
 #define SCLP_CMDW_READ_SCP_INFO_FORCED  0x00120001
 
+const KVMCapabilityInfo kvm_arch_required_capabilities[] = {
+    KVM_CAP_LAST_INFO
+};
+
 int kvm_arch_init(KVMState *s)
 {
     return 0;
-- 
1.7.1

[Qemu-devel] [PATCH 14/18] kvm: x86: Rework identity map and TSS setup for larger BIOS sizes

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

In order to support loading BIOSes > 256K, reorder the code, adjusting
the base if the kernel supports moving the identity map.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 target-i386/kvm.c |   63 +++++++++++++++++++++++++---------------------------
 1 files changed, 30 insertions(+), 33 deletions(-)

diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 1db8227..72f9fdf 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -493,27 +493,9 @@ static int kvm_get_supported_msrs(KVMState *s)
     return ret;
 }
 
-static int kvm_init_identity_map_page(KVMState *s)
-{
-#ifdef KVM_CAP_SET_IDENTITY_MAP_ADDR
-    int ret;
-    uint64_t addr = 0xfffbc000;
-
-    if (!kvm_check_extension(s, KVM_CAP_SET_IDENTITY_MAP_ADDR)) {
-        return 0;
-    }
-
-    ret = kvm_vm_ioctl(s, KVM_SET_IDENTITY_MAP_ADDR, &addr);
-    if (ret < 0) {
-        fprintf(stderr, "kvm_set_identity_map_addr: %s\n", strerror(ret));
-        return ret;
-    }
-#endif
-    return 0;
-}
-
 int kvm_arch_init(KVMState *s)
 {
+    uint64_t identity_base = 0xfffbc000;
     int ret;
     struct utsname utsname;
 
@@ -525,27 +507,42 @@ int kvm_arch_init(KVMState *s)
     uname(&utsname);
     lm_capable_kernel = strcmp(utsname.machine, "x86_64") == 0;
 
-    /* create vm86 tss.  KVM uses vm86 mode to emulate 16-bit code
-     * directly.  In order to use vm86 mode, a TSS is needed.  Since this
-     * must be part of guest physical memory, we need to allocate it. */
-
-    /* this address is 3 pages before the bios, and the bios should present
-     * as unavaible memory.  FIXME, need to ensure the e820 map deals with
-     * this?
-     */
     /*
-     * Tell fw_cfg to notify the BIOS to reserve the range.
+     * On older Intel CPUs, KVM uses vm86 mode to emulate 16-bit code directly.
+     * In order to use vm86 mode, an EPT identity map and a TSS  are needed.
+     * Since these must be part of guest physical memory, we need to allocate
+     * them, both by setting their start addresses in the kernel and by
+     * creating a corresponding e820 entry. We need 4 pages before the BIOS.
+     *
+     * Older KVM versions may not support setting the identity map base. In
+     * that case we need to stick with the default, i.e. a 256K maximum BIOS
+     * size.
      */
-    if (e820_add_entry(0xfffbc000, 0x4000, E820_RESERVED) < 0) {
-        perror("e820_add_entry() table is full");
-        exit(1);
+#ifdef KVM_CAP_SET_IDENTITY_MAP_ADDR
+    if (kvm_check_extension(s, KVM_CAP_SET_IDENTITY_MAP_ADDR)) {
+        /* Allows up to 16M BIOSes. */
+        identity_base = 0xfeffc000;
+
+        ret = kvm_vm_ioctl(s, KVM_SET_IDENTITY_MAP_ADDR, &identity_base);
+        if (ret < 0) {
+            return ret;
+        }
     }
-    ret = kvm_vm_ioctl(s, KVM_SET_TSS_ADDR, 0xfffbd000);
+#endif
+    /* Set TSS base one page after EPT identity map. */
+    ret = kvm_vm_ioctl(s, KVM_SET_TSS_ADDR, identity_base + 0x1000);
+    if (ret < 0) {
+        return ret;
+    }
+
+    /* Tell fw_cfg to notify the BIOS to reserve the range. */
+    ret = e820_add_entry(identity_base, 0x4000, E820_RESERVED);
     if (ret < 0) {
+        fprintf(stderr, "e820_add_entry() table is full\n");
         return ret;
     }
 
-    return kvm_init_identity_map_page(s);
+    return 0;
 }
 
 static void set_v8086_seg(struct kvm_segment *lhs, const SegmentCache *rhs)
-- 
1.7.1

[Qemu-devel] [PATCH 15/18] kvm: Flush coalesced mmio buffer on IO window exits

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

We must flush pending mmio writes if we leave kvm_cpu_exec for an IO
window. Otherwise we risk to loose those requests when migrating to a
different host during that window.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 kvm-all.c |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/kvm-all.c b/kvm-all.c
index 3a1f63b..9976762 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -918,6 +918,8 @@ int kvm_cpu_exec(CPUState *env)
         cpu_single_env = env;
         kvm_arch_post_run(env, run);
 
+        kvm_flush_coalesced_mmio_buffer();
+
         if (ret == -EINTR || ret == -EAGAIN) {
             cpu_exit(env);
             DPRINTF("io window exit\n");
@@ -930,8 +932,6 @@ int kvm_cpu_exec(CPUState *env)
             abort();
         }
 
-        kvm_flush_coalesced_mmio_buffer();
-
         ret = 0; /* exit loop */
         switch (run->exit_reason) {
         case KVM_EXIT_IO:
-- 
1.7.1

[Qemu-devel] [PATCH 16/18] kvm: Do not use qemu_fair_mutex

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

The imbalance in the hold time of qemu_global_mutex only exists in TCG
mode. In contrast to TCG VCPUs, KVM drops the global lock during guest
execution. We already avoid touching the fairness lock from the
IO-thread in KVM mode, so also stop using it from the VCPU threads.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 cpus.c |    2 --
 1 files changed, 0 insertions(+), 2 deletions(-)

diff --git a/cpus.c b/cpus.c
index 0309189..4c9928e 100644
--- a/cpus.c
+++ b/cpus.c
@@ -735,9 +735,7 @@ static sigset_t block_io_signals(void)
 void qemu_mutex_lock_iothread(void)
 {
     if (kvm_enabled()) {
-        qemu_mutex_lock(&qemu_fair_mutex);
         qemu_mutex_lock(&qemu_global_mutex);
-        qemu_mutex_unlock(&qemu_fair_mutex);
     } else {
         qemu_mutex_lock(&qemu_fair_mutex);
         if (qemu_mutex_trylock(&qemu_global_mutex)) {
-- 
1.7.1

[Qemu-devel] [PATCH 17/18] kvm: x86: Implicitly clear nmi_injected/pending on reset

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

All CPUX86State variables before CPU_COMMON are automatically cleared on
reset. Reorder nmi_injected and nmi_pending to avoid having to touch
them explicitly.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 target-i386/cpu.h |    6 ++++--
 target-i386/kvm.c |    2 --
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index a457423..af701a4 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -699,6 +699,10 @@ typedef struct CPUX86State {
     uint32_t smbase;
     int old_exception;  /* exception in flight */
 
+    /* KVM states, automatically cleared on reset */
+    uint8_t nmi_injected;
+    uint8_t nmi_pending;
+
     CPU_COMMON
 
     /* processor features (e.g. for CPUID insn) */
@@ -726,8 +730,6 @@ typedef struct CPUX86State {
     int32_t exception_injected;
     int32_t interrupt_injected;
     uint8_t soft_interrupt;
-    uint8_t nmi_injected;
-    uint8_t nmi_pending;
     uint8_t has_error_code;
     uint32_t sipi_vector;
     uint32_t cpuid_kvm_features;
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 72f9fdf..b2c5ee0 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -435,8 +435,6 @@ void kvm_arch_reset_vcpu(CPUState *env)
 {
     env->exception_injected = -1;
     env->interrupt_injected = -1;
-    env->nmi_injected = 0;
-    env->nmi_pending = 0;
     env->xcr0 = 1;
     if (kvm_irqchip_in_kernel()) {
         env->mp_state = cpu_is_bsp(env) ? KVM_MP_STATE_RUNNABLE :
-- 
1.7.1

[Qemu-devel] [PATCH 18/18] kvm: x86: Only read/write MSR_KVM_ASYNC_PF_EN if supported

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

If the kernel does not support KVM_CAP_ASYNC_PF, it also does not know
about the related MSR. So skip it during state synchronization in that
case. Fixes annoying kernel warnings.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 target-i386/kvm.c |   13 +++++++++++--
 1 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index b2c5ee0..8e8880a 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -63,6 +63,9 @@ const KVMCapabilityInfo kvm_arch_required_capabilities[] = {
 
 static bool has_msr_star;
 static bool has_msr_hsave_pa;
+#if defined(CONFIG_KVM_PARA) && defined(KVM_CAP_ASYNC_PF)
+static bool has_msr_async_pf_en;
+#endif
 static int lm_capable_kernel;
 
 static struct kvm_cpuid2 *try_get_cpuid(KVMState *s, int max)
@@ -164,6 +167,7 @@ static int get_para_features(CPUState *env)
             features |= (1 << para_features[i].feature);
         }
     }
+    has_msr_async_pf_en = features & (1 << KVM_FEATURE_ASYNC_PF);
     return features;
 }
 #endif
@@ -828,7 +832,10 @@ static int kvm_put_msrs(CPUState *env, int level)
                           env->system_time_msr);
         kvm_msr_entry_set(&msrs[n++], MSR_KVM_WALL_CLOCK, env->wall_clock_msr);
 #if defined(CONFIG_KVM_PARA) && defined(KVM_CAP_ASYNC_PF)
-        kvm_msr_entry_set(&msrs[n++], MSR_KVM_ASYNC_PF_EN, env->async_pf_en_msr);
+        if (has_msr_async_pf_en) {
+            kvm_msr_entry_set(&msrs[n++], MSR_KVM_ASYNC_PF_EN,
+                              env->async_pf_en_msr);
+        }
 #endif
     }
 #ifdef KVM_CAP_MCE
@@ -1064,7 +1071,9 @@ static int kvm_get_msrs(CPUState *env)
     msrs[n++].index = MSR_KVM_SYSTEM_TIME;
     msrs[n++].index = MSR_KVM_WALL_CLOCK;
 #if defined(CONFIG_KVM_PARA) && defined(KVM_CAP_ASYNC_PF)
-    msrs[n++].index = MSR_KVM_ASYNC_PF_EN;
+    if (has_msr_async_pf_en) {
+        msrs[n++].index = MSR_KVM_ASYNC_PF_EN;
+    }
 #endif
 
 #ifdef KVM_CAP_MCE
-- 
1.7.1