[PATCH] KVM: x86: Use MMCONFIG for all PCI config space accesses

[Julia Suvorova]

Using MMCONFIG instead of I/O ports cuts the number of config space
accesses in half, which is faster on KVM and opens the door for
additional optimizations such as Vitaly's "[PATCH 0/3] KVM: x86: KVM
MEM_PCI_HOLE memory":
https://lore.kernel.org/kvm/20200728143741.2718593-1-vkuznets@xxxxxxxxxx

However, this change will not bring significant performance improvement
unless it is running on x86 within a hypervisor. Moreover, allowing
MMCONFIG access for addresses < 256 can be dangerous for some devices:
see commit a0ca99096094 ("PCI x86: always use conf1 to access config
space below 256 bytes"). That is why a special feature flag is needed.

Introduce KVM_FEATURE_PCI_GO_MMCONFIG, which can be enabled when the
configuration is known to be safe (e.g. in QEMU).

Signed-off-by: Julia Suvorova <jusual@xxxxxxxxxx>
---
 Documentation/virt/kvm/cpuid.rst     |  4 ++++
 arch/x86/include/uapi/asm/kvm_para.h |  1 +
 arch/x86/kernel/kvm.c                | 14 ++++++++++++++
 3 files changed, 19 insertions(+)

diff --git a/Documentation/virt/kvm/cpuid.rst b/Documentation/virt/kvm/cpuid.rst
index a7dff9186bed..711f2074877b 100644
--- a/Documentation/virt/kvm/cpuid.rst
+++ b/Documentation/virt/kvm/cpuid.rst
@@ -92,6 +92,10 @@ KVM_FEATURE_ASYNC_PF_INT          14          guest checks this feature bit
                                               async pf acknowledgment msr
                                               0x4b564d07.
 
+KVM_FEATURE_PCI_GO_MMCONFIG       15          guest checks this feature bit
+                                              before using MMCONFIG for all
+                                              PCI config accesses
+
 KVM_FEATURE_CLOCSOURCE_STABLE_BIT 24          host will warn if no guest-side
                                               per-cpu warps are expeced in
                                               kvmclock
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 812e9b4c1114..5793f372cae0 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -32,6 +32,7 @@
 #define KVM_FEATURE_POLL_CONTROL	12
 #define KVM_FEATURE_PV_SCHED_YIELD	13
 #define KVM_FEATURE_ASYNC_PF_INT	14
+#define KVM_FEATURE_PCI_GO_MMCONFIG	15
 
 #define KVM_HINTS_REALTIME      0
 
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index df63786e7bfa..1ec73e6f25ce 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -33,6 +33,7 @@
 #include <asm/hypervisor.h>
 #include <asm/tlb.h>
 #include <asm/cpuidle_haltpoll.h>
+#include <asm/pci_x86.h>
 
 DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled);
 
@@ -715,6 +716,18 @@ static uint32_t __init kvm_detect(void)
 	return kvm_cpuid_base();
 }
 
+static int __init kvm_pci_arch_init(void)
+{
+	if (raw_pci_ext_ops &&
+	    kvm_para_has_feature(KVM_FEATURE_PCI_GO_MMCONFIG)) {
+		pr_info("PCI: Using MMCONFIG for base access\n");
+		raw_pci_ops = raw_pci_ext_ops;
+		return 0;
+	}
+
+	return 1;
+}
+
 static void __init kvm_apic_init(void)
 {
 #if defined(CONFIG_SMP)
@@ -726,6 +739,7 @@ static void __init kvm_apic_init(void)
 static void __init kvm_init_platform(void)
 {
 	kvmclock_init();
+	x86_init.pci.arch_init = kvm_pci_arch_init;
 	x86_platform.apic_post_init = kvm_apic_init;
 }
 
-- 
2.25.4