Merge tag 'kvm-arm64/for-3.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into kvm-next

A handful of fixes for KVM/arm64:

- A couple a basic fixes for running BE guests on a LE host
- A performance improvement for overcommitted VMs (same as the equivalent
  patch for ARM)

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Conflicts:
	arch/arm/include/asm/kvm_emulate.h
	arch/arm64/include/asm/kvm_emulate.h

7 files changed, 201 insertions, 18 deletions

diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 708e4d8a647f..0fa90c962ac8 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -162,4 +162,50 @@ static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu)
         return vcpu->arch.cp15[c0_MPIDR];
 }
 
+static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
+{
+        *vcpu_cpsr(vcpu) |= PSR_E_BIT;
+}
+
+static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu)
+{
+        return !!(*vcpu_cpsr(vcpu) & PSR_E_BIT);
+}
+
+static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,
+                                                    unsigned long data,
+                                                    unsigned int len)
+{
+        if (kvm_vcpu_is_be(vcpu)) {
+                switch (len) {
+                case 1:
+                        return data & 0xff;
+                case 2:
+                        return be16_to_cpu(data & 0xffff);
+                default:
+                        return be32_to_cpu(data);
+                }
+        }
+
+        return data;            /* Leave LE untouched */
+}
+
+static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
+                                                    unsigned long data,
+                                                    unsigned int len)
+{
+        if (kvm_vcpu_is_be(vcpu)) {
+                switch (len) {
+                case 1:
+                        return data & 0xff;
+                case 2:
+                        return cpu_to_be16(data & 0xffff);
+                default:
+                        return cpu_to_be32(data);
+                }
+        }
+
+        return data;            /* Leave LE untouched */
+}
+
 #endif /* __ARM_KVM_EMULATE_H__ */
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index 0c25d9487d53..4cb5a93182e9 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -23,6 +23,68 @@
 
 #include "trace.h"
 
+static void mmio_write_buf(char *buf, unsigned int len, unsigned long data)
+{
+        void *datap = NULL;
+        union {
+                u8      byte;
+                u16     hword;
+                u32     word;
+                u64     dword;
+        } tmp;
+
+        switch (len) {
+        case 1:
+                tmp.byte        = data;
+                datap           = &tmp.byte;
+                break;
+        case 2:
+                tmp.hword       = data;
+                datap           = &tmp.hword;
+                break;
+        case 4:
+                tmp.word        = data;
+                datap           = &tmp.word;
+                break;
+        case 8:
+                tmp.dword       = data;
+                datap           = &tmp.dword;
+                break;
+        }
+
+        memcpy(buf, datap, len);
+}
+
+static unsigned long mmio_read_buf(char *buf, unsigned int len)
+{
+        unsigned long data = 0;
+        union {
+                u16     hword;
+                u32     word;
+                u64     dword;
+        } tmp;
+
+        switch (len) {
+        case 1:
+                data = buf[0];
+                break;
+        case 2:
+                memcpy(&tmp.hword, buf, len);
+                data = tmp.hword;
+                break;
+        case 4:
+                memcpy(&tmp.word, buf, len);
+                data = tmp.word;
+                break;
+        case 8:
+                memcpy(&tmp.dword, buf, len);
+                data = tmp.dword;
+                break;
+        }
+
+        return data;
+}
+
 /**
  * kvm_handle_mmio_return -- Handle MMIO loads after user space emulation
  * @vcpu: The VCPU pointer
@@ -33,28 +95,27 @@
  */
 int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-        unsigned long *dest;
+        unsigned long data;
         unsigned int len;
         int mask;
 
         if (!run->mmio.is_write) {
-                dest = vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt);
-                *dest = 0;
-
                 len = run->mmio.len;
                 if (len > sizeof(unsigned long))
                         return -EINVAL;
 
-                memcpy(dest, run->mmio.data, len);
-
-                trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
-                                *((u64 *)run->mmio.data));
+                data = mmio_read_buf(run->mmio.data, len);
 
                 if (vcpu->arch.mmio_decode.sign_extend &&
                     len < sizeof(unsigned long)) {
                         mask = 1U << ((len * 8) - 1);
-                        *dest = (*dest ^ mask) - mask;
+                        data = (data ^ mask) - mask;
                 }
+
+                trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
+                               data);
+                data = vcpu_data_host_to_guest(vcpu, data, len);
+                *vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt) = data;
         }
 
         return 0;
@@ -105,6 +166,7 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
                  phys_addr_t fault_ipa)
 {
         struct kvm_exit_mmio mmio;
+        unsigned long data;
         unsigned long rt;
         int ret;
 
@@ -125,13 +187,15 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
         }
 
         rt = vcpu->arch.mmio_decode.rt;
+        data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), mmio.len);
+
         trace_kvm_mmio((mmio.is_write) ? KVM_TRACE_MMIO_WRITE :
                                          KVM_TRACE_MMIO_READ_UNSATISFIED,
                         mmio.len, fault_ipa,
-                        (mmio.is_write) ? *vcpu_reg(vcpu, rt) : 0);
+                        (mmio.is_write) ? data : 0);
 
         if (mmio.is_write)
-                memcpy(mmio.data, vcpu_reg(vcpu, rt), mmio.len);
+                mmio_write_buf(mmio.data, mmio.len, data);
 
         if (vgic_handle_mmio(vcpu, run, &mmio))
                 return 1;
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 311263124acf..0881bf169fbc 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -71,6 +71,10 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
                 vcpu_set_thumb(vcpu);
         }
 
+        /* Propagate caller endianness */
+        if (kvm_vcpu_is_be(source_vcpu))
+                kvm_vcpu_set_be(vcpu);
+
         *vcpu_pc(vcpu) = target_pc;
         vcpu->arch.pause = false;
         smp_mb();               /* Make sure the above is visible */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index a5f28e2720c7..c98ef4771c73 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -63,6 +63,7 @@
  * TAC:         Trap ACTLR
  * TSC:         Trap SMC
  * TSW:         Trap cache operations by set/way
+ * TWE:         Trap WFE
  * TWI:         Trap WFI
  * TIDCP:       Trap L2CTLR/L2ECTLR
  * BSU_IS:      Upgrade barriers to the inner shareable domain
@@ -72,8 +73,9 @@
  * FMO:         Override CPSR.F and enable signaling with VF
  * SWIO:        Turn set/way invalidates into set/way clean+invalidate
  */
-#define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \
-                         HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \
+#define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
+                         HCR_BSU_IS | HCR_FB | HCR_TAC | \
+                         HCR_AMO | HCR_IMO | HCR_FMO | \
                          HCR_SWIO | HCR_TIDCP | HCR_RW)
 #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
 
@@ -242,4 +244,6 @@
 
 #define ESR_EL2_EC_xABT_xFSR_EXTABT     0x10
 
+#define ESR_EL2_EC_WFI_ISS_WFE  (1 << 0)
+
 #endif /* __ARM64_KVM_ARM_H__ */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 6df93cdc652b..dd8ecfc3f995 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -182,4 +182,60 @@ static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu)
         return vcpu_sys_reg(vcpu, MPIDR_EL1);
 }
 
+static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
+{
+        if (vcpu_mode_is_32bit(vcpu))
+                *vcpu_cpsr(vcpu) |= COMPAT_PSR_E_BIT;
+        else
+                vcpu_sys_reg(vcpu, SCTLR_EL1) |= (1 << 25);
+}
+
+static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu)
+{
+        if (vcpu_mode_is_32bit(vcpu))
+                return !!(*vcpu_cpsr(vcpu) & COMPAT_PSR_E_BIT);
+
+        return !!(vcpu_sys_reg(vcpu, SCTLR_EL1) & (1 << 25));
+}
+
+static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,
+                                                    unsigned long data,
+                                                    unsigned int len)
+{
+        if (kvm_vcpu_is_be(vcpu)) {
+                switch (len) {
+                case 1:
+                        return data & 0xff;
+                case 2:
+                        return be16_to_cpu(data & 0xffff);
+                case 4:
+                        return be32_to_cpu(data & 0xffffffff);
+                default:
+                        return be64_to_cpu(data);
+                }
+        }
+
+        return data;            /* Leave LE untouched */
+}
+
+static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
+                                                    unsigned long data,
+                                                    unsigned int len)
+{
+        if (kvm_vcpu_is_be(vcpu)) {
+                switch (len) {
+                case 1:
+                        return data & 0xff;
+                case 2:
+                        return cpu_to_be16(data & 0xffff);
+                case 4:
+                        return cpu_to_be32(data & 0xffffffff);
+                default:
+                        return cpu_to_be64(data);
+                }
+        }
+
+        return data;            /* Leave LE untouched */
+}
+
 #endif /* __ARM64_KVM_EMULATE_H__ */
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 21e90820bd23..4480ab339a00 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -21,6 +21,7 @@ config KVM
         select MMU_NOTIFIER
         select PREEMPT_NOTIFIERS
         select ANON_INODES
+        select HAVE_KVM_CPU_RELAX_INTERCEPT
         select KVM_MMIO
         select KVM_ARM_HOST
         select KVM_ARM_VGIC
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 9beaca033437..8da56067c304 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -47,21 +47,29 @@ static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 }
 
 /**
- * kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest
+ * kvm_handle_wfx - handle a wait-for-interrupts or wait-for-event
+ *                  instruction executed by a guest
+ *
  * @vcpu:       the vcpu pointer
  *
- * Simply call kvm_vcpu_block(), which will halt execution of
+ * WFE: Yield the CPU and come back to this vcpu when the scheduler
+ * decides to.
+ * WFI: Simply call kvm_vcpu_block(), which will halt execution of
  * world-switches and schedule other host processes until there is an
  * incoming IRQ or FIQ to the VM.
  */
-static int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-        kvm_vcpu_block(vcpu);
+        if (kvm_vcpu_get_hsr(vcpu) & ESR_EL2_EC_WFI_ISS_WFE)
+                kvm_vcpu_on_spin(vcpu);
+        else
+                kvm_vcpu_block(vcpu);
+
         return 1;
 }
 
 static exit_handle_fn arm_exit_handlers[] = {
-        [ESR_EL2_EC_WFI]        = kvm_handle_wfi,
+        [ESR_EL2_EC_WFI]        = kvm_handle_wfx,
         [ESR_EL2_EC_CP15_32]    = kvm_handle_cp15_32,
         [ESR_EL2_EC_CP15_64]    = kvm_handle_cp15_64,
         [ESR_EL2_EC_CP14_MR]    = kvm_handle_cp14_access,