Linux Virtualization - Apr 2017 - [PATCH v3 00/11] x86: xen cpuid() cleanup

Reduce special casing of xen_cpuid() by using cpu capabilities instead
of faked cpuid nodes.

This cleanup enables us remove the hypervisor specific set_cpu_features
callback as the same effect can be reached via
setup_[clear|force]_cpu_cap().

Removing the rest faked nodes from xen_cpuid() requires some more work
as the remaining cases (mwait leafs and extended topology info) have
to be handled at the consumer sides of this information.

Changes in V3:
- rewrite patch 9 (xsave) to use xgetbv instruction to test for osxsave
  availability (Andrew Cooper)

Changes in V2:
- added several features to this scheme
- removed hypervisor specific set_cpu_features() callbacks

Cc: Alok Kataria <akataria at vmware.com> 
Cc: Thomas Gleixner <tglx at linutronix.de> 
Cc: Ingo Molnar <mingo at redhat.com> 
Cc: "H. Peter Anvin" <hpa at zytor.com> 
Cc: x86 at kernel.org 
Cc: virtualization at lists.linux-foundation.org

Juergen Gross (11):
  xen: set cpu capabilities from xen_start_kernel()
  x86/xen: don't indicate DCA support in pv domains
  x86/xen: use capabilities instead of fake cpuid values for aperf
  x86/xen: use capabilities instead of fake cpuid values for mtrr
  x86/xen: use capabilities instead of fake cpuid values for acc
  x86/xen: use capabilities instead of fake cpuid values for acpi
  x86/xen: use capabilities instead of fake cpuid values for mwait
  x86/xen: use capabilities instead of fake cpuid values for x2apic
  x86/xen: use capabilities instead of fake cpuid values for xsave
  vmware: set cpu capabilities during platform initialization
  x86/cpu: remove hypervisor specific set_cpu_features

 arch/x86/include/asm/hypervisor.h |  5 ---
 arch/x86/kernel/cpu/common.c      |  1 -
 arch/x86/kernel/cpu/hypervisor.c  |  8 ----
 arch/x86/kernel/cpu/vmware.c      | 39 ++++++++--------
 arch/x86/xen/enlighten_pv.c       | 95 +++++++++++++++++----------------------
 5 files changed, 61 insertions(+), 87 deletions(-)

-- 
2.12.0

There is no need to set the same capabilities for each cpu
individually. This can be done for all cpus in platform initialization.

Cc: Alok Kataria <akataria at vmware.com>
Cc: Thomas Gleixner <tglx at linutronix.de>
Cc: Ingo Molnar <mingo at redhat.com>
Cc: "H. Peter Anvin" <hpa at zytor.com>
Cc: x86 at kernel.org
Cc: virtualization at lists.linux-foundation.org
Signed-off-by: Juergen Gross <jgross at suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky at oracle.com>
Acked-by: Alok Kataria <akataria at vmware.com>
---
 arch/x86/kernel/cpu/vmware.c | 39 ++++++++++++++++++++-------------------
 1 file changed, 20 insertions(+), 19 deletions(-)

diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 22403a28caf5..40ed26852ebd 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -113,6 +113,24 @@ static void __init vmware_paravirt_ops_setup(void)
 #define vmware_paravirt_ops_setup() do {} while (0)
 #endif
 
+/*
+ * VMware hypervisor takes care of exporting a reliable TSC to the guest.
+ * Still, due to timing difference when running on virtual cpus, the TSC can
+ * be marked as unstable in some cases. For example, the TSC sync check at
+ * bootup can fail due to a marginal offset between vcpus' TSCs (though the
+ * TSCs do not drift from each other).  Also, the ACPI PM timer clocksource
+ * is not suitable as a watchdog when running on a hypervisor because the
+ * kernel may miss a wrap of the counter if the vcpu is descheduled for a
+ * long time. To skip these checks at runtime we set these capability bits,
+ * so that the kernel could just trust the hypervisor with providing a
+ * reliable virtual TSC that is suitable for timekeeping.
+ */
+static void __init vmware_set_capabilities(void)
+{
+	setup_force_cpu_cap(X86_FEATURE_CONSTANT_TSC);
+	setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
+}
+
 static void __init vmware_platform_setup(void)
 {
 	uint32_t eax, ebx, ecx, edx;
@@ -152,6 +170,8 @@ static void __init vmware_platform_setup(void)
 #ifdef CONFIG_X86_IO_APIC
 	no_timer_check = 1;
 #endif
+
+	vmware_set_capabilities();
 }
 
 /*
@@ -176,24 +196,6 @@ static uint32_t __init vmware_platform(void)
 	return 0;
 }
 
-/*
- * VMware hypervisor takes care of exporting a reliable TSC to the guest.
- * Still, due to timing difference when running on virtual cpus, the TSC can
- * be marked as unstable in some cases. For example, the TSC sync check at
- * bootup can fail due to a marginal offset between vcpus' TSCs (though the
- * TSCs do not drift from each other).  Also, the ACPI PM timer clocksource
- * is not suitable as a watchdog when running on a hypervisor because the
- * kernel may miss a wrap of the counter if the vcpu is descheduled for a
- * long time. To skip these checks at runtime we set these capability bits,
- * so that the kernel could just trust the hypervisor with providing a
- * reliable virtual TSC that is suitable for timekeeping.
- */
-static void vmware_set_cpu_features(struct cpuinfo_x86 *c)
-{
-	set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-	set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE);
-}
-
 /* Checks if hypervisor supports x2apic without VT-D interrupt remapping. */
 static bool __init vmware_legacy_x2apic_available(void)
 {
@@ -206,7 +208,6 @@ static bool __init vmware_legacy_x2apic_available(void)
 const __refconst struct hypervisor_x86 x86_hyper_vmware = {
 	.name			= "VMware",
 	.detect			= vmware_platform,
-	.set_cpu_features	= vmware_set_cpu_features,
 	.init_platform		= vmware_platform_setup,
 	.x2apic_available	= vmware_legacy_x2apic_available,
 };
-- 
2.12.0