[Qemu-devel] [PATCH STABLE 0/7]

[Qemu-devel] [PATCH STABLE 0/7]

[Glauber Costa]

Here it goes again, a series with all the patches needed (and two fixes sent afterwards)
for cpuid trimming in kvm. They are backported to the stable branch.

[Qemu-devel] [PATCH STABLE 1/7] Introduce kvm_check_extension to check if KVM extensions are supported

[Glauber Costa]

From: Anthony Liguori <aliguori@us.ibm.com>

Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Glauber Costa <glommer@redhat.com>
---
 kvm-all.c |   39 ++++++++++++++++++++++-----------------
 kvm.h     |    2 ++
 2 files changed, 24 insertions(+), 17 deletions(-)

diff --git a/kvm-all.c b/kvm-all.c
index 2b7d535..8c1afb0 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -280,6 +280,18 @@ int kvm_uncoalesce_mmio_region(target_phys_addr_t start, ram_addr_t size)
     return ret;
 }
 
+int kvm_check_extension(KVMState *s, unsigned int extension)
+{
+    int ret;
+
+    ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, extension);
+    if (ret < 0) {
+        ret = 0;
+    }
+
+    return ret;
+}
+
 int kvm_init(int smp_cpus)
 {
     KVMState *s;
@@ -325,10 +337,8 @@ int kvm_init(int smp_cpus)
      * just use a user allocated buffer so we can use phys_ram_base
      * unmodified.  Make sure we have a sufficiently modern version of KVM.
      */
-    ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_USER_MEMORY);
-    if (ret <= 0) {
-        if (ret == 0)
-            ret = -EINVAL;
+    if (!kvm_check_extension(s, KVM_CAP_USER_MEMORY)) {
+        ret = -EINVAL;
         fprintf(stderr, "kvm does not support KVM_CAP_USER_MEMORY\n");
         goto err;
     }
@@ -336,11 +346,8 @@ int kvm_init(int smp_cpus)
     /* 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. */
-    ret = kvm_ioctl(s, KVM_CHECK_EXTENSION,
-                    KVM_CAP_DESTROY_MEMORY_REGION_WORKS);
-    if (ret <= 0) {
-        if (ret == 0)
-            ret = -EINVAL;
+    if (!kvm_check_extension(s, KVM_CAP_DESTROY_MEMORY_REGION_WORKS)) {
+        ret = -EINVAL;
 
         fprintf(stderr,
                 "KVM kernel module broken (DESTROY_MEMORY_REGION)\n"
@@ -348,11 +355,10 @@ int kvm_init(int smp_cpus)
         goto err;
     }
 
-    s->coalesced_mmio = 0;
 #ifdef KVM_CAP_COALESCED_MMIO
-    ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_COALESCED_MMIO);
-    if (ret > 0)
-        s->coalesced_mmio = ret;
+    s->coalesced_mmio = kvm_check_extension(s, KVM_CAP_COALESCED_MMIO);
+#else
+    s->coalesced_mmio = 0;
 #endif
 
     ret = kvm_arch_init(s, smp_cpus);
@@ -650,11 +656,10 @@ int kvm_has_sync_mmu(void)
 #ifdef KVM_CAP_SYNC_MMU
     KVMState *s = kvm_state;
 
-    if (kvm_ioctl(s, KVM_CHECK_EXTENSION, KVM_CAP_SYNC_MMU) > 0)
-        return 1;
-#endif
-
+    return kvm_check_extension(s, KVM_CAP_SYNC_MMU);
+#else
     return 0;
+#endif
 }
 
 void kvm_setup_guest_memory(void *start, size_t size)
diff --git a/kvm.h b/kvm.h
index 5a52f51..cf6c799 100644
--- a/kvm.h
+++ b/kvm.h
@@ -78,4 +78,6 @@ int kvm_arch_init(KVMState *s, int smp_cpus);
 
 int kvm_arch_init_vcpu(CPUState *env);
 
+int kvm_check_extension(KVMState *s, unsigned int extension);
+
 #endif
-- 
1.6.2.2

[Qemu-devel] [PATCH STABLE 2/7] kvm: Add support for querying supported cpu features

[Glauber Costa]

From: Avi Kivity <avi@redhat.com>

kvm does not support all cpu features; add support for dunamically querying
the supported feature set.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Glauber Costa <glommer@redhat.com>
---
 kvm.h             |    2 +
 target-i386/kvm.c |   80 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 82 insertions(+), 0 deletions(-)

diff --git a/kvm.h b/kvm.h
index cf6c799..27465a9 100644
--- a/kvm.h
+++ b/kvm.h
@@ -80,4 +80,6 @@ int kvm_arch_init_vcpu(CPUState *env);
 
 int kvm_check_extension(KVMState *s, unsigned int extension);
 
+uint32_t kvm_arch_get_supported_cpuid(CPUState *env, uint32_t function,
+                                      int reg);
 #endif
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index c46900e..5b52de3 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -33,6 +33,86 @@
     do { } while (0)
 #endif
 
+#ifdef KVM_CAP_EXT_CPUID
+
+static struct kvm_cpuid2 *try_get_cpuid(KVMState *s, int max)
+{
+    struct kvm_cpuid2 *cpuid;
+    int r, size;
+
+    size = sizeof(*cpuid) + max * sizeof(*cpuid->entries);
+    cpuid = (struct kvm_cpuid2 *)qemu_mallocz(size);
+    cpuid->nent = max;
+    r = kvm_ioctl(s, KVM_GET_SUPPORTED_CPUID, cpuid);
+    if (r < 0) {
+        if (r == -E2BIG) {
+            qemu_free(cpuid);
+            return NULL;
+        } else {
+            fprintf(stderr, "KVM_GET_SUPPORTED_CPUID failed: %s\n",
+                    strerror(-r));
+            exit(1);
+        }
+    }
+    return cpuid;
+}
+
+uint32_t kvm_arch_get_supported_cpuid(CPUState *env, uint32_t function, int reg)
+{
+    struct kvm_cpuid2 *cpuid;
+    int i, max;
+    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;
+    }
+
+    for (i = 0; i < cpuid->nent; ++i) {
+        if (cpuid->entries[i].function == function) {
+            switch (reg) {
+            case R_EAX:
+                ret = cpuid->entries[i].eax;
+                break;
+            case R_EBX:
+                ret = cpuid->entries[i].ebx;
+                break;
+            case R_ECX:
+                ret = cpuid->entries[i].ecx;
+                break;
+            case R_EDX:
+                ret = cpuid->entries[i].edx;
+                if (function == 0x80000001) {
+                    /* On Intel, kvm returns cpuid according to the Intel spec,
+                     * so add missing bits according to the AMD spec:
+                     */
+                    cpuid_1_edx = kvm_arch_get_supported_cpuid(env, 1, R_EDX);
+                    ret |= cpuid_1_edx & 0xdfeff7ff;
+                }
+                break;
+            }
+        }
+    }
+
+    qemu_free(cpuid);
+
+    return ret;
+}
+
+#else
+
+uint32_t kvm_arch_get_supported_cpuid(CPUState *env, uint32_t function, int reg)
+{
+    return -1U;
+}
+
+#endif
+
 int kvm_arch_init_vcpu(CPUState *env)
 {
     struct {
-- 
1.6.2.2

[Qemu-devel] [PATCH STABLE 3/7] Make x86 cpuid feature names available in file scope

[Glauber Costa]

From: Avi Kivity <avi@redhat.com>

To be used later.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Glauber Costa <glommer@redhat.com>
---
 target-i386/helper.c |   55 +++++++++++++++++++++++++------------------------
 1 files changed, 28 insertions(+), 27 deletions(-)

diff --git a/target-i386/helper.c b/target-i386/helper.c
index 8213703..3eb9697 100644
--- a/target-i386/helper.c
+++ b/target-i386/helper.c
@@ -32,39 +32,40 @@
 
 //#define DEBUG_MMU
 
+/* feature flags taken from "Intel Processor Identification and the CPUID
+ * Instruction" and AMD's "CPUID Specification". In cases of disagreement
+ * about feature names, the Linux name is used. */
+static const char *feature_name[] = {
+    "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce",
+    "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov",
+    "pat", "pse36", "pn" /* Intel psn */, "clflush" /* Intel clfsh */, NULL, "ds" /* Intel dts */, "acpi", "mmx",
+    "fxsr", "sse", "sse2", "ss", "ht" /* Intel htt */, "tm", "ia64", "pbe",
+};
+static const char *ext_feature_name[] = {
+    "pni" /* Intel,AMD sse3 */, NULL, NULL, "monitor", "ds_cpl", "vmx", NULL /* Linux smx */, "est",
+    "tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL,
+    NULL, NULL, "dca", NULL, NULL, NULL, NULL, "popcnt",
+       NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+};
+static const char *ext2_feature_name[] = {
+    "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce",
+    "cx8" /* AMD CMPXCHG8B */, "apic", NULL, "syscall", "mtrr", "pge", "mca", "cmov",
+    "pat", "pse36", NULL, NULL /* Linux mp */, "nx" /* Intel xd */, NULL, "mmxext", "mmx",
+    "fxsr", "fxsr_opt" /* AMD ffxsr */, "pdpe1gb" /* AMD Page1GB */, "rdtscp", NULL, "lm" /* Intel 64 */, "3dnowext", "3dnow",
+};
+static const char *ext3_feature_name[] = {
+    "lahf_lm" /* AMD LahfSahf */, "cmp_legacy", "svm", "extapic" /* AMD ExtApicSpace */, "cr8legacy" /* AMD AltMovCr8 */, "abm", "sse4a", "misalignsse",
+    "3dnowprefetch", "osvw", NULL /* Linux ibs */, NULL, "skinit", "wdt", NULL, NULL,
+    NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+    NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+};
+
 static void add_flagname_to_bitmaps(char *flagname, uint32_t *features, 
                                     uint32_t *ext_features, 
                                     uint32_t *ext2_features, 
                                     uint32_t *ext3_features)
 {
     int i;
-    /* feature flags taken from "Intel Processor Identification and the CPUID
-     * Instruction" and AMD's "CPUID Specification". In cases of disagreement 
-     * about feature names, the Linux name is used. */
-    static const char *feature_name[] = {
-        "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce",
-        "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov",
-        "pat", "pse36", "pn" /* Intel psn */, "clflush" /* Intel clfsh */, NULL, "ds" /* Intel dts */, "acpi", "mmx",
-        "fxsr", "sse", "sse2", "ss", "ht" /* Intel htt */, "tm", "ia64", "pbe",
-    };
-    static const char *ext_feature_name[] = {
-       "pni" /* Intel,AMD sse3 */, NULL, NULL, "monitor", "ds_cpl", "vmx", NULL /* Linux smx */, "est",
-       "tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL,
-       NULL, NULL, "dca", NULL, NULL, NULL, NULL, "popcnt",
-       NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-    };
-    static const char *ext2_feature_name[] = {
-       "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce",
-       "cx8" /* AMD CMPXCHG8B */, "apic", NULL, "syscall", "mtrr", "pge", "mca", "cmov",
-       "pat", "pse36", NULL, NULL /* Linux mp */, "nx" /* Intel xd */, NULL, "mmxext", "mmx",
-       "fxsr", "fxsr_opt" /* AMD ffxsr */, "pdpe1gb" /* AMD Page1GB */, "rdtscp", NULL, "lm" /* Intel 64 */, "3dnowext", "3dnow",
-    };
-    static const char *ext3_feature_name[] = {
-       "lahf_lm" /* AMD LahfSahf */, "cmp_legacy", "svm", "extapic" /* AMD ExtApicSpace */, "cr8legacy" /* AMD AltMovCr8 */, "abm", "sse4a", "misalignsse",
-       "3dnowprefetch", "osvw", NULL /* Linux ibs */, NULL, "skinit", "wdt", NULL, NULL,
-       NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-       NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
-    };
 
     for ( i = 0 ; i < 32 ; i++ ) 
         if (feature_name[i] && !strcmp (flagname, feature_name[i])) {
-- 
1.6.2.2

[Qemu-devel] [PATCH STABLE 4/7] Fix x86 feature modifications for features that set multiple bits

[Glauber Costa]

From: Avi Kivity <avi@redhat.com>

QEMU allows adding or removing cpu features by using the syntax '-cpu +feature'
or '-cpu -feature'.  Some cpuid features cause more than one bit to be set or
cleared; but QEMU stops after just one bit has been modified, causing the
feature bits to be inconsistent.

Fix by allowing all feature bits corresponding to a given name to be set.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Glauber Costa <glommer@redhat.com>
---
 target-i386/helper.c |   13 ++++++++-----
 1 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/target-i386/helper.c b/target-i386/helper.c
index 3eb9697..1433857 100644
--- a/target-i386/helper.c
+++ b/target-i386/helper.c
@@ -66,28 +66,31 @@ static void add_flagname_to_bitmaps(char *flagname, uint32_t *features,
                                     uint32_t *ext3_features)
 {
     int i;
+    int found = 0;
 
     for ( i = 0 ; i < 32 ; i++ ) 
         if (feature_name[i] && !strcmp (flagname, feature_name[i])) {
             *features |= 1 << i;
-            return;
+            found = 1;
         }
     for ( i = 0 ; i < 32 ; i++ ) 
         if (ext_feature_name[i] && !strcmp (flagname, ext_feature_name[i])) {
             *ext_features |= 1 << i;
-            return;
+            found = 1;
         }
     for ( i = 0 ; i < 32 ; i++ ) 
         if (ext2_feature_name[i] && !strcmp (flagname, ext2_feature_name[i])) {
             *ext2_features |= 1 << i;
-            return;
+            found = 1;
         }
     for ( i = 0 ; i < 32 ; i++ ) 
         if (ext3_feature_name[i] && !strcmp (flagname, ext3_feature_name[i])) {
             *ext3_features |= 1 << i;
-            return;
+            found = 1;
         }
-    fprintf(stderr, "CPU feature %s not found\n", flagname);
+    if (!found) {
+        fprintf(stderr, "CPU feature %s not found\n", flagname);
+    }
 }
 
 typedef struct x86_def_t {
-- 
1.6.2.2

[Qemu-devel] [PATCH STABLE 5/7] kvm: Trim cpu features not supported by kvm

[Glauber Costa]

From: Avi Kivity <avi@redhat.com>

Remove cpu features that are not supported by kvm from the cpuid features
reported to the guest.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Glauber Costa <glommer@redhat.com>
---
 target-i386/helper.c |   30 ++++++++++++++++++++++++++++++
 1 files changed, 30 insertions(+), 0 deletions(-)

diff --git a/target-i386/helper.c b/target-i386/helper.c
index 1433857..c98cdcc 100644
--- a/target-i386/helper.c
+++ b/target-i386/helper.c
@@ -93,6 +93,21 @@ static void add_flagname_to_bitmaps(char *flagname, uint32_t *features,
     }
 }
 
+static void kvm_trim_features(uint32_t *features, uint32_t supported,
+                              const char *names[])
+{
+    int i;
+    uint32_t mask;
+
+    for (i = 0; i < 32; ++i) {
+        mask = 1U << i;
+        if ((*features & mask) && !(supported & mask)) {
+            printf("Processor feature %s not supported by kvm\n", names[i]);
+            *features &= ~mask;
+        }
+    }
+}
+
 typedef struct x86_def_t {
     const char *name;
     uint32_t level;
@@ -1674,5 +1689,20 @@ CPUX86State *cpu_x86_init(const char *cpu_model)
 #endif
     if (kvm_enabled())
         kvm_init_vcpu(env);
+    if (kvm_enabled()) {
+        kvm_trim_features(&env->cpuid_features,
+                          kvm_arch_get_supported_cpuid(env, 1, R_EDX),
+                          feature_name);
+        kvm_trim_features(&env->cpuid_ext_features,
+                          kvm_arch_get_supported_cpuid(env, 1, R_ECX),
+                          ext_feature_name);
+        kvm_trim_features(&env->cpuid_ext2_features,
+                          kvm_arch_get_supported_cpuid(env, 0x80000001, R_EDX),
+                          ext2_feature_name);
+        kvm_trim_features(&env->cpuid_ext3_features,
+                          kvm_arch_get_supported_cpuid(env, 0x80000001, R_ECX),
+                          ext3_feature_name);
+    }
+
     return env;
 }
-- 
1.6.2.2

[Qemu-devel] [PATCH STABLE 6/7] Remove noisy printf when KVM masks CPU features

[Glauber Costa]

From: Anthony Liguori <aliguori@us.ibm.com>

Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Glauber Costa <glommer@redhat.com>
---
 target-i386/helper.c |    1 -
 1 files changed, 0 insertions(+), 1 deletions(-)

diff --git a/target-i386/helper.c b/target-i386/helper.c
index c98cdcc..e714994 100644
--- a/target-i386/helper.c
+++ b/target-i386/helper.c
@@ -102,7 +102,6 @@ static void kvm_trim_features(uint32_t *features, uint32_t supported,
     for (i = 0; i < 32; ++i) {
         mask = 1U << i;
         if ((*features & mask) && !(supported & mask)) {
-            printf("Processor feature %s not supported by kvm\n", names[i]);
             *features &= ~mask;
         }
     }
-- 
1.6.2.2

[Qemu-devel] [PATCH STABLE 7/7] kvm: work around supported cpuid ioctl() brokenness

[Glauber Costa]

From: Mark McLoughlin <markmc@redhat.com>

KVM_GET_SUPPORTED_CPUID has been known to fail to return -E2BIG
when it runs out of entries. Detect this by always trying again
with a bigger table if the ioctl() fills the table.

Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: Glauber Costa <glommer@redhat.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 5b52de3..eb61598 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -44,6 +44,9 @@ static struct kvm_cpuid2 *try_get_cpuid(KVMState *s, int max)
     cpuid = (struct kvm_cpuid2 *)qemu_mallocz(size);
     cpuid->nent = max;
     r = kvm_ioctl(s, KVM_GET_SUPPORTED_CPUID, cpuid);
+    if (r == 0 && cpuid->nent >= max) {
+        r = -E2BIG;
+    }
     if (r < 0) {
         if (r == -E2BIG) {
             qemu_free(cpuid);
-- 
1.6.2.2