Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "One of the largest releases for KVM...  Hardly any generic
  changes, but lots of architecture-specific updates.

  ARM:
   - VHE support so that we can run the kernel at EL2 on ARMv8.1 systems
   - PMU support for guests
   - 32bit world switch rewritten in C
   - various optimizations to the vgic save/restore code.

  PPC:
   - enabled KVM-VFIO integration ("VFIO device")
   - optimizations to speed up IPIs between vcpus
   - in-kernel handling of IOMMU hypercalls
   - support for dynamic DMA windows (DDW).

  s390:
   - provide the floating point registers via sync regs;
   - separated instruction vs.  data accesses
   - dirty log improvements for huge guests
   - bugfixes and documentation improvements.

  x86:
   - Hyper-V VMBus hypercall userspace exit
   - alternative implementation of lowest-priority interrupts using
     vector hashing (for better VT-d posted interrupt support)
   - fixed guest debugging with nested virtualizations
   - improved interrupt tracking in the in-kernel IOAPIC
   - generic infrastructure for tracking writes to guest
     memory - currently its only use is to speedup the legacy shadow
     paging (pre-EPT) case, but in the future it will be used for
     virtual GPUs as well
   - much cleanup (LAPIC, kvmclock, MMU, PIT), including ubsan fixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (217 commits)
  KVM: x86: remove eager_fpu field of struct kvm_vcpu_arch
  KVM: x86: disable MPX if host did not enable MPX XSAVE features
  arm64: KVM: vgic-v3: Only wipe LRs on vcpu exit
  arm64: KVM: vgic-v3: Reset LRs at boot time
  arm64: KVM: vgic-v3: Do not save an LR known to be empty
  arm64: KVM: vgic-v3: Save maintenance interrupt state only if required
  arm64: KVM: vgic-v3: Avoid accessing ICH registers
  KVM: arm/arm64: vgic-v2: Make GICD_SGIR quicker to hit
  KVM: arm/arm64: vgic-v2: Only wipe LRs on vcpu exit
  KVM: arm/arm64: vgic-v2: Reset LRs at boot time
  KVM: arm/arm64: vgic-v2: Do not save an LR known to be empty
  KVM: arm/arm64: vgic-v2: Move GICH_ELRSR saving to its own function
  KVM: arm/arm64: vgic-v2: Save maintenance interrupt state only if required
  KVM: arm/arm64: vgic-v2: Avoid accessing GICH registers
  KVM: s390: allocate only one DMA page per VM
  KVM: s390: enable STFLE interpretation only if enabled for the guest
  KVM: s390: wake up when the VCPU cpu timer expires
  KVM: s390: step the VCPU timer while in enabled wait
  KVM: s390: protect VCPU cpu timer with a seqcount
  KVM: s390: step VCPU cpu timer during kvm_run ioctl
  ...

4 files changed, 43 insertions, 5 deletions

diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index fffa4ac6c25a..b0ab4e93db0d 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -110,9 +110,6 @@ int main(void)
   DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_regs, regs));
   DEFINE(CPU_FP_REGS,		offsetof(struct kvm_regs, fp_regs));
   DEFINE(VCPU_FPEXC32_EL2,	offsetof(struct kvm_vcpu, arch.ctxt.sys_regs[FPEXC32_EL2]));
-  DEFINE(VCPU_ESR_EL2,		offsetof(struct kvm_vcpu, arch.fault.esr_el2));
-  DEFINE(VCPU_FAR_EL2,		offsetof(struct kvm_vcpu, arch.fault.far_el2));
-  DEFINE(VCPU_HPFAR_EL2,	offsetof(struct kvm_vcpu, arch.fault.hpfar_el2));
   DEFINE(VCPU_HOST_CONTEXT,	offsetof(struct kvm_vcpu, arch.host_cpu_context));
 #endif
 #ifdef CONFIG_CPU_PM
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 5c90aa490a2b..ba745199297e 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -26,6 +26,7 @@
 #include <asm/cpu_ops.h>
 #include <asm/processor.h>
 #include <asm/sysreg.h>
+#include <asm/virt.h>
 
 unsigned long elf_hwcap __read_mostly;
 EXPORT_SYMBOL_GPL(elf_hwcap);
@@ -621,6 +622,11 @@ static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry)
 	return has_sre;
 }
 
+static bool runs_at_el2(const struct arm64_cpu_capabilities *entry)
+{
+	return is_kernel_in_hyp_mode();
+}
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
@@ -651,6 +657,11 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.min_field_value = 2,
 	},
 #endif /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */
+	{
+		.desc = "Virtualization Host Extensions",
+		.capability = ARM64_HAS_VIRT_HOST_EXTN,
+		.matches = runs_at_el2,
+	},
 	{},
 };
 
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 917d98108b3f..6f2f37743d3b 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -30,6 +30,7 @@
 #include <asm/cache.h>
 #include <asm/cputype.h>
 #include <asm/kernel-pgtable.h>
+#include <asm/kvm_arm.h>
 #include <asm/memory.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
@@ -464,9 +465,27 @@ CPU_LE(	bic	x0, x0, #(3 << 24)	)	// Clear the EE and E0E bits for EL1
 	isb
 	ret
 
+2:
+#ifdef CONFIG_ARM64_VHE
+	/*
+	 * Check for VHE being present. For the rest of the EL2 setup,
+	 * x2 being non-zero indicates that we do have VHE, and that the
+	 * kernel is intended to run at EL2.
+	 */
+	mrs	x2, id_aa64mmfr1_el1
+	ubfx	x2, x2, #8, #4
+#else
+	mov	x2, xzr
+#endif
+
 	/* Hyp configuration. */
-2:	mov	x0, #(1 << 31)			// 64-bit EL1
+	mov	x0, #HCR_RW			// 64-bit EL1
+	cbz	x2, set_hcr
+	orr	x0, x0, #HCR_TGE		// Enable Host Extensions
+	orr	x0, x0, #HCR_E2H
+set_hcr:
 	msr	hcr_el2, x0
+	isb
 
 	/* Generic timers. */
 	mrs	x0, cnthctl_el2
@@ -526,6 +545,13 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 	/* Stage-2 translation */
 	msr	vttbr_el2, xzr
 
+	cbz	x2, install_el2_stub
+
+	mov	w20, #BOOT_CPU_MODE_EL2		// This CPU booted in EL2
+	isb
+	ret
+
+install_el2_stub:
 	/* Hypervisor stub */
 	adrp	x0, __hyp_stub_vectors
 	add	x0, x0, #:lo12:__hyp_stub_vectors
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index f7ab14c4d5df..1b52269ffa87 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -20,6 +20,7 @@
  */
 
 #include <asm/irq_regs.h>
+#include <asm/virt.h>
 
 #include <linux/of.h>
 #include <linux/perf/arm_pmu.h>
@@ -691,9 +692,12 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 
 	if (attr->exclude_idle)
 		return -EPERM;
+	if (is_kernel_in_hyp_mode() &&
+	    attr->exclude_kernel != attr->exclude_hv)
+		return -EINVAL;
 	if (attr->exclude_user)
 		config_base |= ARMV8_EXCLUDE_EL0;
-	if (attr->exclude_kernel)
+	if (!is_kernel_in_hyp_mode() && attr->exclude_kernel)
 		config_base |= ARMV8_EXCLUDE_EL1;
 	if (!attr->exclude_hv)
 		config_base |= ARMV8_INCLUDE_EL2;