[PATCH v4 03/14] ARM: KVM: handle 64bit values passed to mrcc or from mcrr instructions in BE case

[Victor Kamensky]

In some cases the mcrr and mrrc instructions in combination with the ldrd
and strd instructions need to deal with 64bit value in memory. The ldrd
and strd instructions already handle endianness within word (register)
boundaries but to get effect of the whole 64bit value represented correctly,
rr_lo_hi macro is introduced and is used to swap registers positions when
the mcrr and mrrc instructions are used. That has the effect of swapping
two words.

Signed-off-by: Victor Kamensky <victor.kamensky at linaro.org>
Reviewed-by: Christoffer Dall <christoffer.dall at linaro.org>
Acked-by: Marc Zyngier <marc.zyngier at arm.com>
---
 arch/arm/include/asm/kvm_asm.h | 18 ++++++++++++++++++
 arch/arm/kvm/init.S            |  4 ++--
 arch/arm/kvm/interrupts.S      |  4 ++--
 arch/arm/kvm/interrupts_head.S |  6 +++---
 4 files changed, 25 insertions(+), 7 deletions(-)

diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 53b3c4a..3a67bec 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -61,6 +61,24 @@
 #define ARM_EXCEPTION_FIQ	  6
 #define ARM_EXCEPTION_HVC	  7
 
+/*
+ * The rr_lo_hi macro swaps a pair of registers depending on
+ * current endianness. It is used in conjunction with ldrd and strd
+ * instructions that load/store a 64-bit value from/to memory to/from
+ * a pair of registers which are used with the mrrc and mcrr instructions.
+ * If used with the ldrd/strd instructions, the a1 parameter is the first
+ * source/destination register and the a2 parameter is the second
+ * source/destination register. Note that the ldrd/strd instructions
+ * already swap the bytes within the words correctly according to the
+ * endianness setting, but the order of the registers need to be effectively
+ * swapped when used with the mrrc/mcrr instructions.
+ */
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define rr_lo_hi(a1, a2) a2, a1
+#else
+#define rr_lo_hi(a1, a2) a1, a2
+#endif
+
 #ifndef __ASSEMBLY__
 struct kvm;
 struct kvm_vcpu;
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index 74f0718..2d10b2d 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -74,7 +74,7 @@ __do_hyp_init:
 ARM_BE8(setend	be) @ Switch to Big Endian mode if needed
 
 	@ Set the HTTBR to point to the hypervisor PGD pointer passed
-	mcrr	p15, 4, r2, r3, c2
+	mcrr	p15, 4, rr_lo_hi(r2, r3), c2
 
 	@ Set the HTCR and VTCR to the same shareability and cacheability
 	@ settings as the non-secure TTBCR and with T0SZ == 0.
@@ -140,7 +140,7 @@ phase2:
 	mov	pc, r0
 
 target:	@ We're now in the trampoline code, switch page tables
-	mcrr	p15, 4, r2, r3, c2
+	mcrr	p15, 4, rr_lo_hi(r2, r3), c2
 	isb
 
 	@ Invalidate the old TLBs
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index 0d68d40..24d4e65 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -52,7 +52,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 	dsb	ishst
 	add	r0, r0, #KVM_VTTBR
 	ldrd	r2, r3, [r0]
-	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
+	mcrr	p15, 6, rr_lo_hi(r2, r3), c2	@ Write VTTBR
 	isb
 	mcr     p15, 0, r0, c8, c3, 0	@ TLBIALLIS (rt ignored)
 	dsb	ish
@@ -135,7 +135,7 @@ ENTRY(__kvm_vcpu_run)
 	ldr	r1, [vcpu, #VCPU_KVM]
 	add	r1, r1, #KVM_VTTBR
 	ldrd	r2, r3, [r1]
-	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
+	mcrr	p15, 6, rr_lo_hi(r2, r3), c2	@ Write VTTBR
 
 	@ We're all done, just restore the GPRs and go to the guest
 	restore_guest_regs
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index e627858..104977f 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -520,7 +520,7 @@ ARM_BE8(rev	r6, r6  )
 	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
 	isb
 
-	mrrc	p15, 3, r2, r3, c14	@ CNTV_CVAL
+	mrrc	p15, 3, rr_lo_hi(r2, r3), c14	@ CNTV_CVAL
 	ldr	r4, =VCPU_TIMER_CNTV_CVAL
 	add	r5, vcpu, r4
 	strd	r2, r3, [r5]
@@ -560,12 +560,12 @@ ARM_BE8(rev	r6, r6  )
 
 	ldr	r2, [r4, #KVM_TIMER_CNTVOFF]
 	ldr	r3, [r4, #(KVM_TIMER_CNTVOFF + 4)]
-	mcrr	p15, 4, r2, r3, c14	@ CNTVOFF
+	mcrr	p15, 4, rr_lo_hi(r2, r3), c14	@ CNTVOFF
 
 	ldr	r4, =VCPU_TIMER_CNTV_CVAL
 	add	r5, vcpu, r4
 	ldrd	r2, r3, [r5]
-	mcrr	p15, 3, r2, r3, c14	@ CNTV_CVAL
+	mcrr	p15, 3, rr_lo_hi(r2, r3), c14	@ CNTV_CVAL
 	isb
 
 	ldr	r2, [vcpu, #VCPU_TIMER_CNTV_CTL]
-- 
1.8.1.4