[PATCH v4 0/9] target/i386: Misc cleanup on KVM PV defs, outdated comments and error handling

[PATCH v4 0/9] target/i386: Misc cleanup on KVM PV defs, outdated comments and error handling

[Zhao Liu]

Hi,

This is my v4 cleanup series. Compared with v3 [1],
 * Returned kvm_vm_ioctl() directly in kvm_install_msr_filters().
 * Added a patch (patch 9) to clean up ARRAY_SIZE(msr_handlers).


Background and Introduction
===========================

This series picks cleanup from my previous kvmclock [2] (as other
renaming attempts were temporarily put on hold).

In addition, this series also include the cleanup on a historically
workaround, recent comment of coco interface [3] and error handling
corner cases in kvm_arch_init().

Avoiding the fragmentation of these misc cleanups, I consolidated them
all in one series and was able to tackle them in one go!

[1]: https://lore.kernel.org/qemu-devel/20240715044955.3954304-1-zhao1.liu@intel.com/T/
[2]: https://lore.kernel.org/qemu-devel/20240329101954.3954987-1-zhao1.liu@linux.intel.com/
[3]: https://lore.kernel.org/qemu-devel/2815f0f1-9e20-4985-849c-d74c6cdc94ae@intel.com/

Thanks and Best Regards,
Zhao
---
Zhao Liu (9):
  target/i386/kvm: Add feature bit definitions for KVM CPUID
  target/i386/kvm: Remove local MSR_KVM_WALL_CLOCK and
    MSR_KVM_SYSTEM_TIME definitions
  target/i386/kvm: Only save/load kvmclock MSRs when kvmclock enabled
  target/i386/kvm: Save/load MSRs of kvmclock2
    (KVM_FEATURE_CLOCKSOURCE2)
  target/i386/kvm: Drop workaround for KVM_X86_DISABLE_EXITS_HTL typo
  target/i386/confidential-guest: Fix comment of
    x86_confidential_guest_kvm_type()
  target/i386/kvm: Clean up return values of MSR filter related
    functions
  target/i386/kvm: Clean up error handling in kvm_arch_init()
  target/i386/kvm: Replace ARRAY_SIZE(msr_handlers) with
    KVM_MSR_FILTER_MAX_RANGES

 hw/i386/kvm/clock.c              |   5 +-
 target/i386/confidential-guest.h |   2 +-
 target/i386/cpu.h                |  25 +++++++
 target/i386/kvm/kvm.c            | 113 +++++++++++++++++--------------
 target/i386/kvm/kvm_i386.h       |   4 +-
 5 files changed, 92 insertions(+), 57 deletions(-)

-- 
2.34.1

[PATCH v4 1/9] target/i386/kvm: Add feature bit definitions for KVM CPUID

[Zhao Liu]

Add feature definitions for KVM_CPUID_FEATURES in CPUID (
CPUID[4000_0001].EAX and CPUID[4000_0001].EDX), to get rid of lots of
offset calculations.

Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
---
v3: Resolved a rebasing conflict.
v2: Changed the prefix from CPUID_FEAT_KVM_* to CPUID_KVM_*. (Xiaoyao)
---
 hw/i386/kvm/clock.c   |  5 ++---
 target/i386/cpu.h     | 23 +++++++++++++++++++++++
 target/i386/kvm/kvm.c | 28 ++++++++++++++--------------
 3 files changed, 39 insertions(+), 17 deletions(-)

diff --git a/hw/i386/kvm/clock.c b/hw/i386/kvm/clock.c
index 40aa9a32c32c..ce416c05a3d0 100644
--- a/hw/i386/kvm/clock.c
+++ b/hw/i386/kvm/clock.c
@@ -27,7 +27,6 @@
 #include "qapi/error.h"
 
 #include <linux/kvm.h>
-#include "standard-headers/asm-x86/kvm_para.h"
 #include "qom/object.h"
 
 #define TYPE_KVM_CLOCK "kvmclock"
@@ -334,8 +333,8 @@ void kvmclock_create(bool create_always)
 
     assert(kvm_enabled());
     if (create_always ||
-        cpu->env.features[FEAT_KVM] & ((1ULL << KVM_FEATURE_CLOCKSOURCE) |
-                                       (1ULL << KVM_FEATURE_CLOCKSOURCE2))) {
+        cpu->env.features[FEAT_KVM] & (CPUID_KVM_CLOCK |
+                                       CPUID_KVM_CLOCK2)) {
         sysbus_create_simple(TYPE_KVM_CLOCK, -1, NULL);
     }
 }
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index c43ac01c794a..b59bdc1c9d9d 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -28,6 +28,7 @@
 #include "qapi/qapi-types-common.h"
 #include "qemu/cpu-float.h"
 #include "qemu/timer.h"
+#include "standard-headers/asm-x86/kvm_para.h"
 
 #define XEN_NR_VIRQS 24
 
@@ -988,6 +989,28 @@ uint64_t x86_cpu_get_supported_feature_word(X86CPU *cpu, FeatureWord w);
 #define CPUID_8000_0007_EBX_OVERFLOW_RECOV    (1U << 0)
 #define CPUID_8000_0007_EBX_SUCCOR      (1U << 1)
 
+/* (Old) KVM paravirtualized clocksource */
+#define CPUID_KVM_CLOCK            (1U << KVM_FEATURE_CLOCKSOURCE)
+/* (New) KVM specific paravirtualized clocksource */
+#define CPUID_KVM_CLOCK2           (1U << KVM_FEATURE_CLOCKSOURCE2)
+/* KVM asynchronous page fault */
+#define CPUID_KVM_ASYNCPF          (1U << KVM_FEATURE_ASYNC_PF)
+/* KVM stolen (when guest vCPU is not running) time accounting */
+#define CPUID_KVM_STEAL_TIME       (1U << KVM_FEATURE_STEAL_TIME)
+/* KVM paravirtualized end-of-interrupt signaling */
+#define CPUID_KVM_PV_EOI           (1U << KVM_FEATURE_PV_EOI)
+/* KVM paravirtualized spinlocks support */
+#define CPUID_KVM_PV_UNHALT        (1U << KVM_FEATURE_PV_UNHALT)
+/* KVM host-side polling on HLT control from the guest */
+#define CPUID_KVM_POLL_CONTROL     (1U << KVM_FEATURE_POLL_CONTROL)
+/* KVM interrupt based asynchronous page fault*/
+#define CPUID_KVM_ASYNCPF_INT      (1U << KVM_FEATURE_ASYNC_PF_INT)
+/* KVM 'Extended Destination ID' support for external interrupts */
+#define CPUID_KVM_MSI_EXT_DEST_ID  (1U << KVM_FEATURE_MSI_EXT_DEST_ID)
+
+/* Hint to KVM that vCPUs expect never preempted for an unlimited time */
+#define CPUID_KVM_HINTS_REALTIME    (1U << KVM_HINTS_REALTIME)
+
 /* CLZERO instruction */
 #define CPUID_8000_0008_EBX_CLZERO      (1U << 0)
 /* Always save/restore FP error pointers */
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index becca2efa5b4..86e42beb78bf 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -539,13 +539,13 @@ uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function,
          * be enabled without the in-kernel irqchip
          */
         if (!kvm_irqchip_in_kernel()) {
-            ret &= ~(1U << KVM_FEATURE_PV_UNHALT);
+            ret &= ~CPUID_KVM_PV_UNHALT;
         }
         if (kvm_irqchip_is_split()) {
-            ret |= 1U << KVM_FEATURE_MSI_EXT_DEST_ID;
+            ret |= CPUID_KVM_MSI_EXT_DEST_ID;
         }
     } else if (function == KVM_CPUID_FEATURES && reg == R_EDX) {
-        ret |= 1U << KVM_HINTS_REALTIME;
+        ret |= CPUID_KVM_HINTS_REALTIME;
     }
 
     if (current_machine->cgs) {
@@ -3424,20 +3424,20 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
         kvm_msr_entry_add(cpu, MSR_IA32_TSC, env->tsc);
         kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, env->system_time_msr);
         kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, env->wall_clock_msr);
-        if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_ASYNC_PF_INT)) {
+        if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF_INT) {
             kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_INT, env->async_pf_int_msr);
         }
-        if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_ASYNC_PF)) {
+        if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF) {
             kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_EN, env->async_pf_en_msr);
         }
-        if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_PV_EOI)) {
+        if (env->features[FEAT_KVM] & CPUID_KVM_PV_EOI) {
             kvm_msr_entry_add(cpu, MSR_KVM_PV_EOI_EN, env->pv_eoi_en_msr);
         }
-        if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_STEAL_TIME)) {
+        if (env->features[FEAT_KVM] & CPUID_KVM_STEAL_TIME) {
             kvm_msr_entry_add(cpu, MSR_KVM_STEAL_TIME, env->steal_time_msr);
         }
 
-        if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_POLL_CONTROL)) {
+        if (env->features[FEAT_KVM] & CPUID_KVM_POLL_CONTROL) {
             kvm_msr_entry_add(cpu, MSR_KVM_POLL_CONTROL, env->poll_control_msr);
         }
 
@@ -3900,19 +3900,19 @@ static int kvm_get_msrs(X86CPU *cpu)
 #endif
     kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, 0);
     kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, 0);
-    if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_ASYNC_PF_INT)) {
+    if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF_INT) {
         kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_INT, 0);
     }
-    if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_ASYNC_PF)) {
+    if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF) {
         kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_EN, 0);
     }
-    if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_PV_EOI)) {
+    if (env->features[FEAT_KVM] & CPUID_KVM_PV_EOI) {
         kvm_msr_entry_add(cpu, MSR_KVM_PV_EOI_EN, 0);
     }
-    if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_STEAL_TIME)) {
+    if (env->features[FEAT_KVM] & CPUID_KVM_STEAL_TIME) {
         kvm_msr_entry_add(cpu, MSR_KVM_STEAL_TIME, 0);
     }
-    if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_POLL_CONTROL)) {
+    if (env->features[FEAT_KVM] & CPUID_KVM_POLL_CONTROL) {
         kvm_msr_entry_add(cpu, MSR_KVM_POLL_CONTROL, 1);
     }
     if (has_architectural_pmu_version > 0) {
@@ -5613,7 +5613,7 @@ uint64_t kvm_swizzle_msi_ext_dest_id(uint64_t address)
         return address;
     }
     env = &X86_CPU(first_cpu)->env;
-    if (!(env->features[FEAT_KVM] & (1 << KVM_FEATURE_MSI_EXT_DEST_ID))) {
+    if (!(env->features[FEAT_KVM] & CPUID_KVM_MSI_EXT_DEST_ID)) {
         return address;
     }
 
-- 
2.34.1

[PATCH v4 2/9] target/i386/kvm: Remove local MSR_KVM_WALL_CLOCK and MSR_KVM_SYSTEM_TIME definitions

[Zhao Liu]

These 2 MSRs have been already defined in kvm_para.h (standard-headers/
asm-x86/kvm_para.h).

Remove QEMU local definitions to avoid duplication.

Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
---
 target/i386/kvm/kvm.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 86e42beb78bf..6ad5a7dbf1fd 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -81,9 +81,6 @@
 #define KVM_APIC_BUS_CYCLE_NS       1
 #define KVM_APIC_BUS_FREQUENCY      (1000000000ULL / KVM_APIC_BUS_CYCLE_NS)
 
-#define MSR_KVM_WALL_CLOCK  0x11
-#define MSR_KVM_SYSTEM_TIME 0x12
-
 /* A 4096-byte buffer can hold the 8-byte kvm_msrs header, plus
  * 255 kvm_msr_entry structs */
 #define MSR_BUF_SIZE 4096
-- 
2.34.1

[PATCH v4 3/9] target/i386/kvm: Only save/load kvmclock MSRs when kvmclock enabled

[Zhao Liu]

MSR_KVM_SYSTEM_TIME and MSR_KVM_WALL_CLOCK are attached with the (old)
kvmclock feature (KVM_FEATURE_CLOCKSOURCE).

So, just save/load them only when kvmclock (KVM_FEATURE_CLOCKSOURCE) is
enabled.

Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
---
 target/i386/kvm/kvm.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 6ad5a7dbf1fd..ac434e83b64c 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -3419,8 +3419,10 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
      */
     if (level >= KVM_PUT_RESET_STATE) {
         kvm_msr_entry_add(cpu, MSR_IA32_TSC, env->tsc);
-        kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, env->system_time_msr);
-        kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, env->wall_clock_msr);
+        if (env->features[FEAT_KVM] & CPUID_KVM_CLOCK) {
+            kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, env->system_time_msr);
+            kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, env->wall_clock_msr);
+        }
         if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF_INT) {
             kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_INT, env->async_pf_int_msr);
         }
@@ -3895,8 +3897,10 @@ static int kvm_get_msrs(X86CPU *cpu)
         }
     }
 #endif
-    kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, 0);
-    kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, 0);
+    if (env->features[FEAT_KVM] & CPUID_KVM_CLOCK) {
+        kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, 0);
+        kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, 0);
+    }
     if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF_INT) {
         kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_INT, 0);
     }
-- 
2.34.1

[PATCH v4 4/9] target/i386/kvm: Save/load MSRs of kvmclock2 (KVM_FEATURE_CLOCKSOURCE2)

[Zhao Liu]

MSR_KVM_SYSTEM_TIME_NEW and MSR_KVM_WALL_CLOCK_NEW are bound to
kvmclock2 (KVM_FEATURE_CLOCKSOURCE2).

Add the save/load support for these 2 MSRs just like kvmclock MSRs.

Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
---
 target/i386/cpu.h     |  2 ++
 target/i386/kvm/kvm.c | 16 ++++++++++++++++
 2 files changed, 18 insertions(+)

diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index b59bdc1c9d9d..35dc68631989 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -1826,6 +1826,8 @@ typedef struct CPUArchState {
 
     uint64_t system_time_msr;
     uint64_t wall_clock_msr;
+    uint64_t system_time_new_msr;
+    uint64_t wall_clock_new_msr;
     uint64_t steal_time_msr;
     uint64_t async_pf_en_msr;
     uint64_t async_pf_int_msr;
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index ac434e83b64c..64e54beac7b3 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -3423,6 +3423,12 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
             kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, env->system_time_msr);
             kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, env->wall_clock_msr);
         }
+        if (env->features[FEAT_KVM] & CPUID_KVM_CLOCK2) {
+            kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME_NEW,
+                              env->system_time_new_msr);
+            kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK_NEW,
+                              env->wall_clock_new_msr);
+        }
         if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF_INT) {
             kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_INT, env->async_pf_int_msr);
         }
@@ -3901,6 +3907,10 @@ static int kvm_get_msrs(X86CPU *cpu)
         kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, 0);
         kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, 0);
     }
+    if (env->features[FEAT_KVM] & CPUID_KVM_CLOCK2) {
+        kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME_NEW, 0);
+        kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK_NEW, 0);
+    }
     if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF_INT) {
         kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_INT, 0);
     }
@@ -4167,6 +4177,12 @@ static int kvm_get_msrs(X86CPU *cpu)
         case MSR_KVM_WALL_CLOCK:
             env->wall_clock_msr = msrs[i].data;
             break;
+        case MSR_KVM_SYSTEM_TIME_NEW:
+            env->system_time_new_msr = msrs[i].data;
+            break;
+        case MSR_KVM_WALL_CLOCK_NEW:
+            env->wall_clock_new_msr = msrs[i].data;
+            break;
         case MSR_MCG_STATUS:
             env->mcg_status = msrs[i].data;
             break;
-- 
2.34.1

[PATCH v4 5/9] target/i386/kvm: Drop workaround for KVM_X86_DISABLE_EXITS_HTL typo

[Zhao Liu]

The KVM_X86_DISABLE_EXITS_HTL typo has been fixed in commit
77d361b13c19 ("linux-headers: Update to kernel mainline commit
b357bf602").

Drop the related workaround.

Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
---
 target/i386/kvm/kvm.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 64e54beac7b3..4aae4ffc9ccd 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -2728,10 +2728,6 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
 
     if (enable_cpu_pm) {
         int disable_exits = kvm_check_extension(s, KVM_CAP_X86_DISABLE_EXITS);
-/* Work around for kernel header with a typo. TODO: fix header and drop. */
-#if defined(KVM_X86_DISABLE_EXITS_HTL) && !defined(KVM_X86_DISABLE_EXITS_HLT)
-#define KVM_X86_DISABLE_EXITS_HLT KVM_X86_DISABLE_EXITS_HTL
-#endif
         if (disable_exits) {
             disable_exits &= (KVM_X86_DISABLE_EXITS_MWAIT |
                               KVM_X86_DISABLE_EXITS_HLT |
-- 
2.34.1

[PATCH v4 6/9] target/i386/confidential-guest: Fix comment of x86_confidential_guest_kvm_type()

[Zhao Liu]

Update the comment to match the X86ConfidentialGuestClass
implementation.

Reported-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>
---
 target/i386/confidential-guest.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/target/i386/confidential-guest.h b/target/i386/confidential-guest.h
index 7342d2843aa5..c90a59bac41a 100644
--- a/target/i386/confidential-guest.h
+++ b/target/i386/confidential-guest.h
@@ -46,7 +46,7 @@ struct X86ConfidentialGuestClass {
 /**
  * x86_confidential_guest_kvm_type:
  *
- * Calls #X86ConfidentialGuestClass.unplug callback of @plug_handler.
+ * Calls #X86ConfidentialGuestClass.kvm_type() callback.
  */
 static inline int x86_confidential_guest_kvm_type(X86ConfidentialGuest *cg)
 {
-- 
2.34.1

[PATCH v4 7/9] target/i386/kvm: Clean up return values of MSR filter related functions

[Zhao Liu]

At present, the error code of MSR filter enablement attempts to print in
error_report().

Unfortunately, this behavior doesn't work because the MSR filter-related
functions return the boolean and current error_report() use the wrong
return value.

So fix this by making MSR filter related functions return int type and
printing such returned value in error_report().

Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
---
v4: Returned kvm_vm_ioctl() directly. (Zide)
v3: new commit.
---
 target/i386/kvm/kvm.c      | 34 ++++++++++++++--------------------
 target/i386/kvm/kvm_i386.h |  4 ++--
 2 files changed, 16 insertions(+), 22 deletions(-)

diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 4aae4ffc9ccd..f68be68eb411 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -2780,8 +2780,6 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
             }
     }
     if (kvm_vm_check_extension(s, KVM_CAP_X86_USER_SPACE_MSR)) {
-        bool r;
-
         ret = kvm_vm_enable_cap(s, KVM_CAP_X86_USER_SPACE_MSR, 0,
                                 KVM_MSR_EXIT_REASON_FILTER);
         if (ret) {
@@ -2790,9 +2788,9 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
             exit(1);
         }
 
-        r = kvm_filter_msr(s, MSR_CORE_THREAD_COUNT,
-                           kvm_rdmsr_core_thread_count, NULL);
-        if (!r) {
+        ret = kvm_filter_msr(s, MSR_CORE_THREAD_COUNT,
+                             kvm_rdmsr_core_thread_count, NULL);
+        if (ret) {
             error_report("Could not install MSR_CORE_THREAD_COUNT handler: %s",
                          strerror(-ret));
             exit(1);
@@ -5274,13 +5272,13 @@ void kvm_arch_update_guest_debug(CPUState *cpu, struct kvm_guest_debug *dbg)
     }
 }
 
-static bool kvm_install_msr_filters(KVMState *s)
+static int kvm_install_msr_filters(KVMState *s)
 {
     uint64_t zero = 0;
     struct kvm_msr_filter filter = {
         .flags = KVM_MSR_FILTER_DEFAULT_ALLOW,
     };
-    int r, i, j = 0;
+    int i, j = 0;
 
     for (i = 0; i < KVM_MSR_FILTER_MAX_RANGES; i++) {
         KVMMSRHandlers *handler = &msr_handlers[i];
@@ -5304,18 +5302,13 @@ static bool kvm_install_msr_filters(KVMState *s)
         }
     }
 
-    r = kvm_vm_ioctl(s, KVM_X86_SET_MSR_FILTER, &filter);
-    if (r) {
-        return false;
-    }
-
-    return true;
+    return kvm_vm_ioctl(s, KVM_X86_SET_MSR_FILTER, &filter);
 }
 
-bool kvm_filter_msr(KVMState *s, uint32_t msr, QEMURDMSRHandler *rdmsr,
-                    QEMUWRMSRHandler *wrmsr)
+int kvm_filter_msr(KVMState *s, uint32_t msr, QEMURDMSRHandler *rdmsr,
+                   QEMUWRMSRHandler *wrmsr)
 {
-    int i;
+    int i, ret;
 
     for (i = 0; i < ARRAY_SIZE(msr_handlers); i++) {
         if (!msr_handlers[i].msr) {
@@ -5325,16 +5318,17 @@ bool kvm_filter_msr(KVMState *s, uint32_t msr, QEMURDMSRHandler *rdmsr,
                 .wrmsr = wrmsr,
             };
 
-            if (!kvm_install_msr_filters(s)) {
+            ret = kvm_install_msr_filters(s);
+            if (ret) {
                 msr_handlers[i] = (KVMMSRHandlers) { };
-                return false;
+                return ret;
             }
 
-            return true;
+            return 0;
         }
     }
 
-    return false;
+    return 0;
 }
 
 static int kvm_handle_rdmsr(X86CPU *cpu, struct kvm_run *run)
diff --git a/target/i386/kvm/kvm_i386.h b/target/i386/kvm/kvm_i386.h
index 34fc60774b86..91c2d6e69163 100644
--- a/target/i386/kvm/kvm_i386.h
+++ b/target/i386/kvm/kvm_i386.h
@@ -74,8 +74,8 @@ typedef struct kvm_msr_handlers {
     QEMUWRMSRHandler *wrmsr;
 } KVMMSRHandlers;
 
-bool kvm_filter_msr(KVMState *s, uint32_t msr, QEMURDMSRHandler *rdmsr,
-                    QEMUWRMSRHandler *wrmsr);
+int kvm_filter_msr(KVMState *s, uint32_t msr, QEMURDMSRHandler *rdmsr,
+                   QEMUWRMSRHandler *wrmsr);
 
 #endif /* CONFIG_KVM */
 
-- 
2.34.1

[PATCH v4 8/9] target/i386/kvm: Clean up error handling in kvm_arch_init()

[Zhao Liu]

Currently, there're following incorrect error handling cases in
kvm_arch_init():
* Missed to handle failure of kvm_get_supported_feature_msrs().
* Missed to return when KVM_CAP_X86_DISABLE_EXITS enabling fails.
* MSR filter related cases called exit() directly instead of returning
  to kvm_init().

Fix the above cases.

Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
---
v3: new commit.
---
 target/i386/kvm/kvm.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index f68be68eb411..d47476e96813 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -2682,7 +2682,10 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
         return ret;
     }
 
-    kvm_get_supported_feature_msrs(s);
+    ret = kvm_get_supported_feature_msrs(s);
+    if (ret < 0) {
+        return ret;
+    }
 
     uname(&utsname);
     lm_capable_kernel = strcmp(utsname.machine, "x86_64") == 0;
@@ -2740,6 +2743,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
         if (ret < 0) {
             error_report("kvm: guest stopping CPU not supported: %s",
                          strerror(-ret));
+            return ret;
         }
     }
 
@@ -2785,7 +2789,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
         if (ret) {
             error_report("Could not enable user space MSRs: %s",
                          strerror(-ret));
-            exit(1);
+            return ret;
         }
 
         ret = kvm_filter_msr(s, MSR_CORE_THREAD_COUNT,
@@ -2793,7 +2797,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
         if (ret) {
             error_report("Could not install MSR_CORE_THREAD_COUNT handler: %s",
                          strerror(-ret));
-            exit(1);
+            return ret;
         }
     }
 
-- 
2.34.1

[PATCH v4 9/9] target/i386/kvm: Replace ARRAY_SIZE(msr_handlers) with KVM_MSR_FILTER_MAX_RANGES

[Zhao Liu]

kvm_install_msr_filters() uses KVM_MSR_FILTER_MAX_RANGES as the bound
when traversing msr_handlers[], while other places still compute the
size by ARRAY_SIZE(msr_handlers).

In fact, msr_handlers[] is an array with the fixed size
KVM_MSR_FILTER_MAX_RANGES, so there is no difference between the two
ways.

For the code consistency and to avoid additional computational overhead,
use KVM_MSR_FILTER_MAX_RANGES instead of ARRAY_SIZE(msr_handlers).

Suggested-by: Zide Chen <zide.chen@intel.com>
Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
---
v4: new commit.
---
 target/i386/kvm/kvm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index d47476e96813..43b2ea63d584 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -5314,7 +5314,7 @@ int kvm_filter_msr(KVMState *s, uint32_t msr, QEMURDMSRHandler *rdmsr,
 {
     int i, ret;
 
-    for (i = 0; i < ARRAY_SIZE(msr_handlers); i++) {
+    for (i = 0; i < KVM_MSR_FILTER_MAX_RANGES; i++) {
         if (!msr_handlers[i].msr) {
             msr_handlers[i] = (KVMMSRHandlers) {
                 .msr = msr,
@@ -5340,7 +5340,7 @@ static int kvm_handle_rdmsr(X86CPU *cpu, struct kvm_run *run)
     int i;
     bool r;
 
-    for (i = 0; i < ARRAY_SIZE(msr_handlers); i++) {
+    for (i = 0; i < KVM_MSR_FILTER_MAX_RANGES; i++) {
         KVMMSRHandlers *handler = &msr_handlers[i];
         if (run->msr.index == handler->msr) {
             if (handler->rdmsr) {
@@ -5360,7 +5360,7 @@ static int kvm_handle_wrmsr(X86CPU *cpu, struct kvm_run *run)
     int i;
     bool r;
 
-    for (i = 0; i < ARRAY_SIZE(msr_handlers); i++) {
+    for (i = 0; i < KVM_MSR_FILTER_MAX_RANGES; i++) {
         KVMMSRHandlers *handler = &msr_handlers[i];
         if (run->msr.index == handler->msr) {
             if (handler->wrmsr) {
-- 
2.34.1

Re: [PATCH v4 1/9] target/i386/kvm: Add feature bit definitions for KVM CPUID

[Chen, Zide]

On 7/16/2024 9:10 AM, Zhao Liu wrote:
> Add feature definitions for KVM_CPUID_FEATURES in CPUID (
> CPUID[4000_0001].EAX and CPUID[4000_0001].EDX), to get rid of lots of
> offset calculations.
> 
> Signed-off-by: Zhao Liu <zhao1.liu@intel.com>

Reviewed-by: zide.chen@intel.com


> ---
> v3: Resolved a rebasing conflict.
> v2: Changed the prefix from CPUID_FEAT_KVM_* to CPUID_KVM_*. (Xiaoyao)
> ---
>  hw/i386/kvm/clock.c   |  5 ++---
>  target/i386/cpu.h     | 23 +++++++++++++++++++++++
>  target/i386/kvm/kvm.c | 28 ++++++++++++++--------------
>  3 files changed, 39 insertions(+), 17 deletions(-)
> 
> diff --git a/hw/i386/kvm/clock.c b/hw/i386/kvm/clock.c
> index 40aa9a32c32c..ce416c05a3d0 100644
> --- a/hw/i386/kvm/clock.c
> +++ b/hw/i386/kvm/clock.c
> @@ -27,7 +27,6 @@
>  #include "qapi/error.h"
>  
>  #include <linux/kvm.h>
> -#include "standard-headers/asm-x86/kvm_para.h"
>  #include "qom/object.h"
>  
>  #define TYPE_KVM_CLOCK "kvmclock"
> @@ -334,8 +333,8 @@ void kvmclock_create(bool create_always)
>  
>      assert(kvm_enabled());
>      if (create_always ||
> -        cpu->env.features[FEAT_KVM] & ((1ULL << KVM_FEATURE_CLOCKSOURCE) |
> -                                       (1ULL << KVM_FEATURE_CLOCKSOURCE2))) {
> +        cpu->env.features[FEAT_KVM] & (CPUID_KVM_CLOCK |
> +                                       CPUID_KVM_CLOCK2)) {
>          sysbus_create_simple(TYPE_KVM_CLOCK, -1, NULL);
>      }
>  }
> diff --git a/target/i386/cpu.h b/target/i386/cpu.h
> index c43ac01c794a..b59bdc1c9d9d 100644
> --- a/target/i386/cpu.h
> +++ b/target/i386/cpu.h
> @@ -28,6 +28,7 @@
>  #include "qapi/qapi-types-common.h"
>  #include "qemu/cpu-float.h"
>  #include "qemu/timer.h"
> +#include "standard-headers/asm-x86/kvm_para.h"
>  
>  #define XEN_NR_VIRQS 24
>  
> @@ -988,6 +989,28 @@ uint64_t x86_cpu_get_supported_feature_word(X86CPU *cpu, FeatureWord w);
>  #define CPUID_8000_0007_EBX_OVERFLOW_RECOV    (1U << 0)
>  #define CPUID_8000_0007_EBX_SUCCOR      (1U << 1)
>  
> +/* (Old) KVM paravirtualized clocksource */
> +#define CPUID_KVM_CLOCK            (1U << KVM_FEATURE_CLOCKSOURCE)
> +/* (New) KVM specific paravirtualized clocksource */
> +#define CPUID_KVM_CLOCK2           (1U << KVM_FEATURE_CLOCKSOURCE2)
> +/* KVM asynchronous page fault */
> +#define CPUID_KVM_ASYNCPF          (1U << KVM_FEATURE_ASYNC_PF)
> +/* KVM stolen (when guest vCPU is not running) time accounting */
> +#define CPUID_KVM_STEAL_TIME       (1U << KVM_FEATURE_STEAL_TIME)
> +/* KVM paravirtualized end-of-interrupt signaling */
> +#define CPUID_KVM_PV_EOI           (1U << KVM_FEATURE_PV_EOI)
> +/* KVM paravirtualized spinlocks support */
> +#define CPUID_KVM_PV_UNHALT        (1U << KVM_FEATURE_PV_UNHALT)
> +/* KVM host-side polling on HLT control from the guest */
> +#define CPUID_KVM_POLL_CONTROL     (1U << KVM_FEATURE_POLL_CONTROL)
> +/* KVM interrupt based asynchronous page fault*/
> +#define CPUID_KVM_ASYNCPF_INT      (1U << KVM_FEATURE_ASYNC_PF_INT)
> +/* KVM 'Extended Destination ID' support for external interrupts */
> +#define CPUID_KVM_MSI_EXT_DEST_ID  (1U << KVM_FEATURE_MSI_EXT_DEST_ID)
> +
> +/* Hint to KVM that vCPUs expect never preempted for an unlimited time */
> +#define CPUID_KVM_HINTS_REALTIME    (1U << KVM_HINTS_REALTIME)
> +
>  /* CLZERO instruction */
>  #define CPUID_8000_0008_EBX_CLZERO      (1U << 0)
>  /* Always save/restore FP error pointers */
> diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
> index becca2efa5b4..86e42beb78bf 100644
> --- a/target/i386/kvm/kvm.c
> +++ b/target/i386/kvm/kvm.c
> @@ -539,13 +539,13 @@ uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function,
>           * be enabled without the in-kernel irqchip
>           */
>          if (!kvm_irqchip_in_kernel()) {
> -            ret &= ~(1U << KVM_FEATURE_PV_UNHALT);
> +            ret &= ~CPUID_KVM_PV_UNHALT;
>          }
>          if (kvm_irqchip_is_split()) {
> -            ret |= 1U << KVM_FEATURE_MSI_EXT_DEST_ID;
> +            ret |= CPUID_KVM_MSI_EXT_DEST_ID;
>          }
>      } else if (function == KVM_CPUID_FEATURES && reg == R_EDX) {
> -        ret |= 1U << KVM_HINTS_REALTIME;
> +        ret |= CPUID_KVM_HINTS_REALTIME;
>      }
>  
>      if (current_machine->cgs) {
> @@ -3424,20 +3424,20 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
>          kvm_msr_entry_add(cpu, MSR_IA32_TSC, env->tsc);
>          kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, env->system_time_msr);
>          kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, env->wall_clock_msr);
> -        if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_ASYNC_PF_INT)) {
> +        if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF_INT) {
>              kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_INT, env->async_pf_int_msr);
>          }
> -        if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_ASYNC_PF)) {
> +        if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF) {
>              kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_EN, env->async_pf_en_msr);
>          }
> -        if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_PV_EOI)) {
> +        if (env->features[FEAT_KVM] & CPUID_KVM_PV_EOI) {
>              kvm_msr_entry_add(cpu, MSR_KVM_PV_EOI_EN, env->pv_eoi_en_msr);
>          }
> -        if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_STEAL_TIME)) {
> +        if (env->features[FEAT_KVM] & CPUID_KVM_STEAL_TIME) {
>              kvm_msr_entry_add(cpu, MSR_KVM_STEAL_TIME, env->steal_time_msr);
>          }
>  
> -        if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_POLL_CONTROL)) {
> +        if (env->features[FEAT_KVM] & CPUID_KVM_POLL_CONTROL) {
>              kvm_msr_entry_add(cpu, MSR_KVM_POLL_CONTROL, env->poll_control_msr);
>          }
>  
> @@ -3900,19 +3900,19 @@ static int kvm_get_msrs(X86CPU *cpu)
>  #endif
>      kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, 0);
>      kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, 0);
> -    if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_ASYNC_PF_INT)) {
> +    if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF_INT) {
>          kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_INT, 0);
>      }
> -    if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_ASYNC_PF)) {
> +    if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF) {
>          kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_EN, 0);
>      }
> -    if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_PV_EOI)) {
> +    if (env->features[FEAT_KVM] & CPUID_KVM_PV_EOI) {
>          kvm_msr_entry_add(cpu, MSR_KVM_PV_EOI_EN, 0);
>      }
> -    if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_STEAL_TIME)) {
> +    if (env->features[FEAT_KVM] & CPUID_KVM_STEAL_TIME) {
>          kvm_msr_entry_add(cpu, MSR_KVM_STEAL_TIME, 0);
>      }
> -    if (env->features[FEAT_KVM] & (1 << KVM_FEATURE_POLL_CONTROL)) {
> +    if (env->features[FEAT_KVM] & CPUID_KVM_POLL_CONTROL) {
>          kvm_msr_entry_add(cpu, MSR_KVM_POLL_CONTROL, 1);
>      }
>      if (has_architectural_pmu_version > 0) {
> @@ -5613,7 +5613,7 @@ uint64_t kvm_swizzle_msi_ext_dest_id(uint64_t address)
>          return address;
>      }
>      env = &X86_CPU(first_cpu)->env;
> -    if (!(env->features[FEAT_KVM] & (1 << KVM_FEATURE_MSI_EXT_DEST_ID))) {
> +    if (!(env->features[FEAT_KVM] & CPUID_KVM_MSI_EXT_DEST_ID)) {
>          return address;
>      }
>  

Re: [PATCH v4 2/9] target/i386/kvm: Remove local MSR_KVM_WALL_CLOCK and MSR_KVM_SYSTEM_TIME definitions

[Chen, Zide]

On 7/16/2024 9:10 AM, Zhao Liu wrote:
> These 2 MSRs have been already defined in kvm_para.h (standard-headers/
> asm-x86/kvm_para.h).
> 
> Remove QEMU local definitions to avoid duplication.
> 
> Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
> Signed-off-by: Zhao Liu <zhao1.liu@intel.com>


Reviewed-by: zide.chen@intel.com

> ---
>  target/i386/kvm/kvm.c | 3 ---
>  1 file changed, 3 deletions(-)
> 
> diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
> index 86e42beb78bf..6ad5a7dbf1fd 100644
> --- a/target/i386/kvm/kvm.c
> +++ b/target/i386/kvm/kvm.c
> @@ -81,9 +81,6 @@
>  #define KVM_APIC_BUS_CYCLE_NS       1
>  #define KVM_APIC_BUS_FREQUENCY      (1000000000ULL / KVM_APIC_BUS_CYCLE_NS)
>  
> -#define MSR_KVM_WALL_CLOCK  0x11
> -#define MSR_KVM_SYSTEM_TIME 0x12
> -
>  /* A 4096-byte buffer can hold the 8-byte kvm_msrs header, plus
>   * 255 kvm_msr_entry structs */
>  #define MSR_BUF_SIZE 4096

Re: [PATCH v4 3/9] target/i386/kvm: Only save/load kvmclock MSRs when kvmclock enabled

[Chen, Zide]

On 7/16/2024 9:10 AM, Zhao Liu wrote:
> MSR_KVM_SYSTEM_TIME and MSR_KVM_WALL_CLOCK are attached with the (old)
> kvmclock feature (KVM_FEATURE_CLOCKSOURCE).
> 
> So, just save/load them only when kvmclock (KVM_FEATURE_CLOCKSOURCE) is
> enabled.
> 
> Signed-off-by: Zhao Liu <zhao1.liu@intel.com>

 Reviewed-by: Zide Chen <zide.chen@intel.com>


> ---
>  target/i386/kvm/kvm.c | 12 ++++++++----
>  1 file changed, 8 insertions(+), 4 deletions(-)
> 
> diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
> index 6ad5a7dbf1fd..ac434e83b64c 100644
> --- a/target/i386/kvm/kvm.c
> +++ b/target/i386/kvm/kvm.c
> @@ -3419,8 +3419,10 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
>       */
>      if (level >= KVM_PUT_RESET_STATE) {
>          kvm_msr_entry_add(cpu, MSR_IA32_TSC, env->tsc);
> -        kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, env->system_time_msr);
> -        kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, env->wall_clock_msr);
> +        if (env->features[FEAT_KVM] & CPUID_KVM_CLOCK) {
> +            kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, env->system_time_msr);
> +            kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, env->wall_clock_msr);
> +        }
>          if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF_INT) {
>              kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_INT, env->async_pf_int_msr);
>          }
> @@ -3895,8 +3897,10 @@ static int kvm_get_msrs(X86CPU *cpu)
>          }
>      }
>  #endif
> -    kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, 0);
> -    kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, 0);
> +    if (env->features[FEAT_KVM] & CPUID_KVM_CLOCK) {
> +        kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, 0);
> +        kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, 0);
> +    }
>      if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF_INT) {
>          kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_INT, 0);
>      }

Re: [PATCH v4 4/9] target/i386/kvm: Save/load MSRs of kvmclock2 (KVM_FEATURE_CLOCKSOURCE2)

[Chen, Zide]

On 7/16/2024 9:10 AM, Zhao Liu wrote:
> MSR_KVM_SYSTEM_TIME_NEW and MSR_KVM_WALL_CLOCK_NEW are bound to
> kvmclock2 (KVM_FEATURE_CLOCKSOURCE2).
> 
> Add the save/load support for these 2 MSRs just like kvmclock MSRs.
> 
> Signed-off-by: Zhao Liu <zhao1.liu@intel.com>

Reviewed-by: Zide Chen <zide.chen@intel.com>

> ---
>  target/i386/cpu.h     |  2 ++
>  target/i386/kvm/kvm.c | 16 ++++++++++++++++
>  2 files changed, 18 insertions(+)
> 
> diff --git a/target/i386/cpu.h b/target/i386/cpu.h
> index b59bdc1c9d9d..35dc68631989 100644
> --- a/target/i386/cpu.h
> +++ b/target/i386/cpu.h
> @@ -1826,6 +1826,8 @@ typedef struct CPUArchState {
>  
>      uint64_t system_time_msr;
>      uint64_t wall_clock_msr;
> +    uint64_t system_time_new_msr;
> +    uint64_t wall_clock_new_msr;
>      uint64_t steal_time_msr;
>      uint64_t async_pf_en_msr;
>      uint64_t async_pf_int_msr;
> diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
> index ac434e83b64c..64e54beac7b3 100644
> --- a/target/i386/kvm/kvm.c
> +++ b/target/i386/kvm/kvm.c
> @@ -3423,6 +3423,12 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
>              kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, env->system_time_msr);
>              kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, env->wall_clock_msr);
>          }
> +        if (env->features[FEAT_KVM] & CPUID_KVM_CLOCK2) {
> +            kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME_NEW,
> +                              env->system_time_new_msr);
> +            kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK_NEW,
> +                              env->wall_clock_new_msr);
> +        }
>          if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF_INT) {
>              kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_INT, env->async_pf_int_msr);
>          }
> @@ -3901,6 +3907,10 @@ static int kvm_get_msrs(X86CPU *cpu)
>          kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME, 0);
>          kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK, 0);
>      }
> +    if (env->features[FEAT_KVM] & CPUID_KVM_CLOCK2) {
> +        kvm_msr_entry_add(cpu, MSR_KVM_SYSTEM_TIME_NEW, 0);
> +        kvm_msr_entry_add(cpu, MSR_KVM_WALL_CLOCK_NEW, 0);
> +    }
>      if (env->features[FEAT_KVM] & CPUID_KVM_ASYNCPF_INT) {
>          kvm_msr_entry_add(cpu, MSR_KVM_ASYNC_PF_INT, 0);
>      }
> @@ -4167,6 +4177,12 @@ static int kvm_get_msrs(X86CPU *cpu)
>          case MSR_KVM_WALL_CLOCK:
>              env->wall_clock_msr = msrs[i].data;
>              break;
> +        case MSR_KVM_SYSTEM_TIME_NEW:
> +            env->system_time_new_msr = msrs[i].data;
> +            break;
> +        case MSR_KVM_WALL_CLOCK_NEW:
> +            env->wall_clock_new_msr = msrs[i].data;
> +            break;
>          case MSR_MCG_STATUS:
>              env->mcg_status = msrs[i].data;
>              break;

Re: [PATCH v4 5/9] target/i386/kvm: Drop workaround for KVM_X86_DISABLE_EXITS_HTL typo

[Chen, Zide]

On 7/16/2024 9:10 AM, Zhao Liu wrote:
> The KVM_X86_DISABLE_EXITS_HTL typo has been fixed in commit
> 77d361b13c19 ("linux-headers: Update to kernel mainline commit
> b357bf602").
> 
> Drop the related workaround.
> 
> Signed-off-by: Zhao Liu <zhao1.liu@intel.com>

Reviewed-by: Zide Chen <zide.chen@intel.com>

> ---
>  target/i386/kvm/kvm.c | 4 ----
>  1 file changed, 4 deletions(-)
> 
> diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
> index 64e54beac7b3..4aae4ffc9ccd 100644
> --- a/target/i386/kvm/kvm.c
> +++ b/target/i386/kvm/kvm.c
> @@ -2728,10 +2728,6 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
>  
>      if (enable_cpu_pm) {
>          int disable_exits = kvm_check_extension(s, KVM_CAP_X86_DISABLE_EXITS);
> -/* Work around for kernel header with a typo. TODO: fix header and drop. */
> -#if defined(KVM_X86_DISABLE_EXITS_HTL) && !defined(KVM_X86_DISABLE_EXITS_HLT)
> -#define KVM_X86_DISABLE_EXITS_HLT KVM_X86_DISABLE_EXITS_HTL
> -#endif
>          if (disable_exits) {
>              disable_exits &= (KVM_X86_DISABLE_EXITS_MWAIT |
>                                KVM_X86_DISABLE_EXITS_HLT |

Re: [PATCH v4 7/9] target/i386/kvm: Clean up return values of MSR filter related functions

[Chen, Zide]

On 7/16/2024 9:10 AM, Zhao Liu wrote:
> At present, the error code of MSR filter enablement attempts to print in
> error_report().
> 
> Unfortunately, this behavior doesn't work because the MSR filter-related
> functions return the boolean and current error_report() use the wrong
> return value.
> 
> So fix this by making MSR filter related functions return int type and
> printing such returned value in error_report().
> 
> Signed-off-by: Zhao Liu <zhao1.liu@intel.com>

 Reviewed-by: Zide Chen <zide.chen@intel.com>

> ---
> v4: Returned kvm_vm_ioctl() directly. (Zide)
> v3: new commit.
> ---
>  target/i386/kvm/kvm.c      | 34 ++++++++++++++--------------------
>  target/i386/kvm/kvm_i386.h |  4 ++--
>  2 files changed, 16 insertions(+), 22 deletions(-)
> 
> diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
> index 4aae4ffc9ccd..f68be68eb411 100644
> --- a/target/i386/kvm/kvm.c
> +++ b/target/i386/kvm/kvm.c
> @@ -2780,8 +2780,6 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
>              }
>      }
>      if (kvm_vm_check_extension(s, KVM_CAP_X86_USER_SPACE_MSR)) {
> -        bool r;
> -
>          ret = kvm_vm_enable_cap(s, KVM_CAP_X86_USER_SPACE_MSR, 0,
>                                  KVM_MSR_EXIT_REASON_FILTER);
>          if (ret) {
> @@ -2790,9 +2788,9 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
>              exit(1);
>          }
>  
> -        r = kvm_filter_msr(s, MSR_CORE_THREAD_COUNT,
> -                           kvm_rdmsr_core_thread_count, NULL);
> -        if (!r) {
> +        ret = kvm_filter_msr(s, MSR_CORE_THREAD_COUNT,
> +                             kvm_rdmsr_core_thread_count, NULL);
> +        if (ret) {
>              error_report("Could not install MSR_CORE_THREAD_COUNT handler: %s",
>                           strerror(-ret));
>              exit(1);
> @@ -5274,13 +5272,13 @@ void kvm_arch_update_guest_debug(CPUState *cpu, struct kvm_guest_debug *dbg)
>      }
>  }
>  
> -static bool kvm_install_msr_filters(KVMState *s)
> +static int kvm_install_msr_filters(KVMState *s)
>  {
>      uint64_t zero = 0;
>      struct kvm_msr_filter filter = {
>          .flags = KVM_MSR_FILTER_DEFAULT_ALLOW,
>      };
> -    int r, i, j = 0;
> +    int i, j = 0;
>  
>      for (i = 0; i < KVM_MSR_FILTER_MAX_RANGES; i++) {
>          KVMMSRHandlers *handler = &msr_handlers[i];
> @@ -5304,18 +5302,13 @@ static bool kvm_install_msr_filters(KVMState *s)
>          }
>      }
>  
> -    r = kvm_vm_ioctl(s, KVM_X86_SET_MSR_FILTER, &filter);
> -    if (r) {
> -        return false;
> -    }
> -
> -    return true;
> +    return kvm_vm_ioctl(s, KVM_X86_SET_MSR_FILTER, &filter);
>  }
>  
> -bool kvm_filter_msr(KVMState *s, uint32_t msr, QEMURDMSRHandler *rdmsr,
> -                    QEMUWRMSRHandler *wrmsr)
> +int kvm_filter_msr(KVMState *s, uint32_t msr, QEMURDMSRHandler *rdmsr,
> +                   QEMUWRMSRHandler *wrmsr)
>  {
> -    int i;
> +    int i, ret;
>  
>      for (i = 0; i < ARRAY_SIZE(msr_handlers); i++) {
>          if (!msr_handlers[i].msr) {
> @@ -5325,16 +5318,17 @@ bool kvm_filter_msr(KVMState *s, uint32_t msr, QEMURDMSRHandler *rdmsr,
>                  .wrmsr = wrmsr,
>              };
>  
> -            if (!kvm_install_msr_filters(s)) {
> +            ret = kvm_install_msr_filters(s);
> +            if (ret) {
>                  msr_handlers[i] = (KVMMSRHandlers) { };
> -                return false;
> +                return ret;
>              }
>  
> -            return true;
> +            return 0;
>          }
>      }
>  
> -    return false;
> +    return 0;
>  }
>  
>  static int kvm_handle_rdmsr(X86CPU *cpu, struct kvm_run *run)
> diff --git a/target/i386/kvm/kvm_i386.h b/target/i386/kvm/kvm_i386.h
> index 34fc60774b86..91c2d6e69163 100644
> --- a/target/i386/kvm/kvm_i386.h
> +++ b/target/i386/kvm/kvm_i386.h
> @@ -74,8 +74,8 @@ typedef struct kvm_msr_handlers {
>      QEMUWRMSRHandler *wrmsr;
>  } KVMMSRHandlers;
>  
> -bool kvm_filter_msr(KVMState *s, uint32_t msr, QEMURDMSRHandler *rdmsr,
> -                    QEMUWRMSRHandler *wrmsr);
> +int kvm_filter_msr(KVMState *s, uint32_t msr, QEMURDMSRHandler *rdmsr,
> +                   QEMUWRMSRHandler *wrmsr);
>  
>  #endif /* CONFIG_KVM */
>  

Re: [PATCH v4 8/9] target/i386/kvm: Clean up error handling in kvm_arch_init()

[Chen, Zide]

On 7/16/2024 9:10 AM, Zhao Liu wrote:
> Currently, there're following incorrect error handling cases in
> kvm_arch_init():
> * Missed to handle failure of kvm_get_supported_feature_msrs().
> * Missed to return when KVM_CAP_X86_DISABLE_EXITS enabling fails.
> * MSR filter related cases called exit() directly instead of returning
>   to kvm_init().
> 
> Fix the above cases.
> 
> Signed-off-by: Zhao Liu <zhao1.liu@intel.com>

Reviewed-by: Zide Chen <zide.chen@intel.com>


> ---
> v3: new commit.
> ---
>  target/i386/kvm/kvm.c | 10 +++++++---
>  1 file changed, 7 insertions(+), 3 deletions(-)
> 
> diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
> index f68be68eb411..d47476e96813 100644
> --- a/target/i386/kvm/kvm.c
> +++ b/target/i386/kvm/kvm.c
> @@ -2682,7 +2682,10 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
>          return ret;
>      }
>  
> -    kvm_get_supported_feature_msrs(s);
> +    ret = kvm_get_supported_feature_msrs(s);
> +    if (ret < 0) {
> +        return ret;
> +    }
>  
>      uname(&utsname);
>      lm_capable_kernel = strcmp(utsname.machine, "x86_64") == 0;
> @@ -2740,6 +2743,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
>          if (ret < 0) {
>              error_report("kvm: guest stopping CPU not supported: %s",
>                           strerror(-ret));
> +            return ret;
>          }
>      }
>  
> @@ -2785,7 +2789,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
>          if (ret) {
>              error_report("Could not enable user space MSRs: %s",
>                           strerror(-ret));
> -            exit(1);
> +            return ret;
>          }
>  
>          ret = kvm_filter_msr(s, MSR_CORE_THREAD_COUNT,
> @@ -2793,7 +2797,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
>          if (ret) {
>              error_report("Could not install MSR_CORE_THREAD_COUNT handler: %s",
>                           strerror(-ret));
> -            exit(1);
> +            return ret;
>          }
>      }
>  

Re: [PATCH v4 9/9] target/i386/kvm: Replace ARRAY_SIZE(msr_handlers) with KVM_MSR_FILTER_MAX_RANGES

[Chen, Zide]

On 7/16/2024 9:10 AM, Zhao Liu wrote:
> kvm_install_msr_filters() uses KVM_MSR_FILTER_MAX_RANGES as the bound
> when traversing msr_handlers[], while other places still compute the
> size by ARRAY_SIZE(msr_handlers).
> 
> In fact, msr_handlers[] is an array with the fixed size
> KVM_MSR_FILTER_MAX_RANGES, so there is no difference between the two
> ways.
> 
> For the code consistency and to avoid additional computational overhead,
> use KVM_MSR_FILTER_MAX_RANGES instead of ARRAY_SIZE(msr_handlers).
> 
> Suggested-by: Zide Chen <zide.chen@intel.com>
> Signed-off-by: Zhao Liu <zhao1.liu@intel.com>

Reviewed-by: Zide Chen <zide.chen@intel.com>


> ---
> v4: new commit.
> ---
>  target/i386/kvm/kvm.c | 6 +++---
>  1 file changed, 3 insertions(+), 3 deletions(-)
> 
> diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
> index d47476e96813..43b2ea63d584 100644
> --- a/target/i386/kvm/kvm.c
> +++ b/target/i386/kvm/kvm.c
> @@ -5314,7 +5314,7 @@ int kvm_filter_msr(KVMState *s, uint32_t msr, QEMURDMSRHandler *rdmsr,
>  {
>      int i, ret;
>  
> -    for (i = 0; i < ARRAY_SIZE(msr_handlers); i++) {
> +    for (i = 0; i < KVM_MSR_FILTER_MAX_RANGES; i++) {
>          if (!msr_handlers[i].msr) {
>              msr_handlers[i] = (KVMMSRHandlers) {
>                  .msr = msr,
> @@ -5340,7 +5340,7 @@ static int kvm_handle_rdmsr(X86CPU *cpu, struct kvm_run *run)
>      int i;
>      bool r;
>  
> -    for (i = 0; i < ARRAY_SIZE(msr_handlers); i++) {
> +    for (i = 0; i < KVM_MSR_FILTER_MAX_RANGES; i++) {
>          KVMMSRHandlers *handler = &msr_handlers[i];
>          if (run->msr.index == handler->msr) {
>              if (handler->rdmsr) {
> @@ -5360,7 +5360,7 @@ static int kvm_handle_wrmsr(X86CPU *cpu, struct kvm_run *run)
>      int i;
>      bool r;
>  
> -    for (i = 0; i < ARRAY_SIZE(msr_handlers); i++) {
> +    for (i = 0; i < KVM_MSR_FILTER_MAX_RANGES; i++) {
>          KVMMSRHandlers *handler = &msr_handlers[i];
>          if (run->msr.index == handler->msr) {
>              if (handler->wrmsr) {

Re: [PATCH v4 0/9] target/i386: Misc cleanup on KVM PV defs, outdated comments and error handling

[Zhao Liu]

Hi Paolo,

Just a kindly ping.

Thanks,
Zhao

On Wed, Jul 17, 2024 at 12:10:06AM +0800, Zhao Liu wrote:
> Date: Wed, 17 Jul 2024 00:10:06 +0800
> From: Zhao Liu <zhao1.liu@intel.com>
> Subject: [PATCH v4 0/9] target/i386: Misc cleanup on KVM PV defs, outdated
>  comments and error handling
> X-Mailer: git-send-email 2.34.1
> 
> Hi,
> 
> This is my v4 cleanup series. Compared with v3 [1],
>  * Returned kvm_vm_ioctl() directly in kvm_install_msr_filters().
>  * Added a patch (patch 9) to clean up ARRAY_SIZE(msr_handlers).
> 
> 
> Background and Introduction
> ===========================
> 
> This series picks cleanup from my previous kvmclock [2] (as other
> renaming attempts were temporarily put on hold).
> 
> In addition, this series also include the cleanup on a historically
> workaround, recent comment of coco interface [3] and error handling
> corner cases in kvm_arch_init().
> 
> Avoiding the fragmentation of these misc cleanups, I consolidated them
> all in one series and was able to tackle them in one go!
> 
> [1]: https://lore.kernel.org/qemu-devel/20240715044955.3954304-1-zhao1.liu@intel.com/T/
> [2]: https://lore.kernel.org/qemu-devel/20240329101954.3954987-1-zhao1.liu@linux.intel.com/
> [3]: https://lore.kernel.org/qemu-devel/2815f0f1-9e20-4985-849c-d74c6cdc94ae@intel.com/
> 
> Thanks and Best Regards,
> Zhao
> ---
> Zhao Liu (9):
>   target/i386/kvm: Add feature bit definitions for KVM CPUID
>   target/i386/kvm: Remove local MSR_KVM_WALL_CLOCK and
>     MSR_KVM_SYSTEM_TIME definitions
>   target/i386/kvm: Only save/load kvmclock MSRs when kvmclock enabled
>   target/i386/kvm: Save/load MSRs of kvmclock2
>     (KVM_FEATURE_CLOCKSOURCE2)
>   target/i386/kvm: Drop workaround for KVM_X86_DISABLE_EXITS_HTL typo
>   target/i386/confidential-guest: Fix comment of
>     x86_confidential_guest_kvm_type()
>   target/i386/kvm: Clean up return values of MSR filter related
>     functions
>   target/i386/kvm: Clean up error handling in kvm_arch_init()
>   target/i386/kvm: Replace ARRAY_SIZE(msr_handlers) with
>     KVM_MSR_FILTER_MAX_RANGES
> 
>  hw/i386/kvm/clock.c              |   5 +-
>  target/i386/confidential-guest.h |   2 +-
>  target/i386/cpu.h                |  25 +++++++
>  target/i386/kvm/kvm.c            | 113 +++++++++++++++++--------------
>  target/i386/kvm/kvm_i386.h       |   4 +-
>  5 files changed, 92 insertions(+), 57 deletions(-)
> 
> -- 
> 2.34.1
> 

Re: [PATCH v4 0/9] target/i386: Misc cleanup on KVM PV defs, outdated comments and error handling

[Paolo Bonzini]

On 9/4/24 15:46, Zhao Liu wrote:
> Hi Paolo,
> 
> Just a kindly ping.

It's on my list now that 9.1 has been released.

Paolo

> 
> Thanks,
> Zhao
> 
> On Wed, Jul 17, 2024 at 12:10:06AM +0800, Zhao Liu wrote:
>> Date: Wed, 17 Jul 2024 00:10:06 +0800
>> From: Zhao Liu <zhao1.liu@intel.com>
>> Subject: [PATCH v4 0/9] target/i386: Misc cleanup on KVM PV defs, outdated
>>   comments and error handling
>> X-Mailer: git-send-email 2.34.1
>>
>> Hi,
>>
>> This is my v4 cleanup series. Compared with v3 [1],
>>   * Returned kvm_vm_ioctl() directly in kvm_install_msr_filters().
>>   * Added a patch (patch 9) to clean up ARRAY_SIZE(msr_handlers).
>>
>>
>> Background and Introduction
>> ===========================
>>
>> This series picks cleanup from my previous kvmclock [2] (as other
>> renaming attempts were temporarily put on hold).
>>
>> In addition, this series also include the cleanup on a historically
>> workaround, recent comment of coco interface [3] and error handling
>> corner cases in kvm_arch_init().
>>
>> Avoiding the fragmentation of these misc cleanups, I consolidated them
>> all in one series and was able to tackle them in one go!
>>
>> [1]: https://lore.kernel.org/qemu-devel/20240715044955.3954304-1-zhao1.liu@intel.com/T/
>> [2]: https://lore.kernel.org/qemu-devel/20240329101954.3954987-1-zhao1.liu@linux.intel.com/
>> [3]: https://lore.kernel.org/qemu-devel/2815f0f1-9e20-4985-849c-d74c6cdc94ae@intel.com/
>>
>> Thanks and Best Regards,
>> Zhao
>> ---
>> Zhao Liu (9):
>>    target/i386/kvm: Add feature bit definitions for KVM CPUID
>>    target/i386/kvm: Remove local MSR_KVM_WALL_CLOCK and
>>      MSR_KVM_SYSTEM_TIME definitions
>>    target/i386/kvm: Only save/load kvmclock MSRs when kvmclock enabled
>>    target/i386/kvm: Save/load MSRs of kvmclock2
>>      (KVM_FEATURE_CLOCKSOURCE2)
>>    target/i386/kvm: Drop workaround for KVM_X86_DISABLE_EXITS_HTL typo
>>    target/i386/confidential-guest: Fix comment of
>>      x86_confidential_guest_kvm_type()
>>    target/i386/kvm: Clean up return values of MSR filter related
>>      functions
>>    target/i386/kvm: Clean up error handling in kvm_arch_init()
>>    target/i386/kvm: Replace ARRAY_SIZE(msr_handlers) with
>>      KVM_MSR_FILTER_MAX_RANGES
>>
>>   hw/i386/kvm/clock.c              |   5 +-
>>   target/i386/confidential-guest.h |   2 +-
>>   target/i386/cpu.h                |  25 +++++++
>>   target/i386/kvm/kvm.c            | 113 +++++++++++++++++--------------
>>   target/i386/kvm/kvm_i386.h       |   4 +-
>>   5 files changed, 92 insertions(+), 57 deletions(-)
>>
>> -- 
>> 2.34.1
>>
> 
>