KVM: PPC: Book3S: Change interrupt call to reduce scratch space use on HV

Change the calling convention to put the trap number together with
CR in two halves of r12, which frees up HSTATE_SCRATCH2 in the HV
handler.

The 64-bit PR handler entry translates the calling convention back
to match the previous call convention (i.e., shared with 32-bit), for
simplicity.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/exception-64s.h

@@ -233,7 +233,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 
 #endif
 
-#define __KVM_HANDLER_PROLOG(area, n)					\
+#define __KVM_HANDLER(area, h, n)					\
 	BEGIN_FTR_SECTION_NESTED(947)					\
 	ld	r10,area+EX_CFAR(r13);					\
 	std	r10,HSTATE_CFAR(r13);					\
@@ -243,30 +243,28 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	std	r10,HSTATE_PPR(r13);					\
 	END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948);	\
 	ld	r10,area+EX_R10(r13);					\
-	stw	r9,HSTATE_SCRATCH1(r13);				\
-	ld	r9,area+EX_R9(r13);					\
 	std	r12,HSTATE_SCRATCH0(r13);				\
-
-#define __KVM_HANDLER(area, h, n)					\
-	__KVM_HANDLER_PROLOG(area, n)					\
-	li	r12,n;							\
+	sldi	r12,r9,32;						\
+	ori	r12,r12,(n);						\
+	ld	r9,area+EX_R9(r13);					\
 	b	kvmppc_interrupt
 
 #define __KVM_HANDLER_SKIP(area, h, n)					\
 	cmpwi	r10,KVM_GUEST_MODE_SKIP;				\
-	ld	r10,area+EX_R10(r13);					\
 	beq	89f;							\
-	stw	r9,HSTATE_SCRATCH1(r13);				\
 	BEGIN_FTR_SECTION_NESTED(948)					\
-	ld	r9,area+EX_PPR(r13);					\
-	std	r9,HSTATE_PPR(r13);					\
+	ld	r10,area+EX_PPR(r13);					\
+	std	r10,HSTATE_PPR(r13);					\
 	END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948);	\
-	ld	r9,area+EX_R9(r13);					\
+	ld	r10,area+EX_R10(r13);					\
 	std	r12,HSTATE_SCRATCH0(r13);				\
-	li	r12,n;							\
+	sldi	r12,r9,32;						\
+	ori	r12,r12,(n);						\
+	ld	r9,area+EX_R9(r13);					\
 	b	kvmppc_interrupt;					\
 89:	mtocrf	0x80,r9;						\
 	ld	r9,area+EX_R9(r13);					\
+	ld	r10,area+EX_R10(r13);					\
 	b	kvmppc_skip_##h##interrupt
 
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1057,19 +1057,18 @@ hdec_soon:
 kvmppc_interrupt_hv:
 	/*
 	 * Register contents:
-	 * R12		= interrupt vector
+	 * R12		= (guest CR << 32) | interrupt vector
 	 * R13		= PACA
-	 * guest CR, R12 saved in shadow VCPU SCRATCH1/0
+	 * guest R12 saved in shadow VCPU SCRATCH0
 	 * guest R13 saved in SPRN_SCRATCH0
 	 */
-	std	r9, HSTATE_SCRATCH2(r13)
-
+	std	r9, HSTATE_SCRATCH1(r13)
 	lbz	r9, HSTATE_IN_GUEST(r13)
 	cmpwi	r9, KVM_GUEST_MODE_HOST_HV
 	beq	kvmppc_bad_host_intr
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 	cmpwi	r9, KVM_GUEST_MODE_GUEST
-	ld	r9, HSTATE_SCRATCH2(r13)
+	ld	r9, HSTATE_SCRATCH1(r13)
 	beq	kvmppc_interrupt_pr
 #endif
 	/* We're now back in the host but in guest MMU context */
@@ -1089,13 +1088,14 @@ kvmppc_interrupt_hv:
 	std	r6, VCPU_GPR(R6)(r9)
 	std	r7, VCPU_GPR(R7)(r9)
 	std	r8, VCPU_GPR(R8)(r9)
-	ld	r0, HSTATE_SCRATCH2(r13)
+	ld	r0, HSTATE_SCRATCH1(r13)
 	std	r0, VCPU_GPR(R9)(r9)
 	std	r10, VCPU_GPR(R10)(r9)
 	std	r11, VCPU_GPR(R11)(r9)
 	ld	r3, HSTATE_SCRATCH0(r13)
-	lwz	r4, HSTATE_SCRATCH1(r13)
 	std	r3, VCPU_GPR(R12)(r9)
+	/* CR is in the high half of r12 */
+	srdi	r4, r12, 32
 	stw	r4, VCPU_CR(r9)
 BEGIN_FTR_SECTION
 	ld	r3, HSTATE_CFAR(r13)
@@ -1114,6 +1114,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	mfspr	r11, SPRN_SRR1
 	std	r10, VCPU_SRR0(r9)
 	std	r11, VCPU_SRR1(r9)
+	/* trap is in the low half of r12, clear CR from the high half */
+	clrldi	r12, r12, 32
 	andi.	r0, r12, 2		/* need to read HSRR0/1? */
 	beq	1f
 	mfspr	r10, SPRN_HSRR0

arch/powerpc/kvm/book3s_segment.S

@@ -167,20 +167,31 @@ kvmppc_handler_trampoline_enter_end:
  *                                                                            *
  *****************************************************************************/
 
-.global kvmppc_handler_trampoline_exit
-kvmppc_handler_trampoline_exit:
-
 .global kvmppc_interrupt_pr
 kvmppc_interrupt_pr:
+	/* 64-bit entry. Register usage at this point:
+	 *
+	 * SPRG_SCRATCH0   = guest R13
+	 * R12             = (guest CR << 32) | exit handler id
+	 * R13             = PACA
+	 * HSTATE.SCRATCH0 = guest R12
+	 */
+#ifdef CONFIG_PPC64
+	/* Match 32-bit entry */
+	rotldi	r12, r12, 32		  /* Flip R12 halves for stw */
+	stw	r12, HSTATE_SCRATCH1(r13) /* CR is now in the low half */
+	srdi	r12, r12, 32		  /* shift trap into low half */
+#endif
 
+.global kvmppc_handler_trampoline_exit
+kvmppc_handler_trampoline_exit:
 	/* Register usage at this point:
 	 *
-	 * SPRG_SCRATCH0  = guest R13
-	 * R12            = exit handler id
-	 * R13            = shadow vcpu (32-bit) or PACA (64-bit)
+	 * SPRG_SCRATCH0   = guest R13
+	 * R12             = exit handler id
+	 * R13             = shadow vcpu (32-bit) or PACA (64-bit)
 	 * HSTATE.SCRATCH0 = guest R12
 	 * HSTATE.SCRATCH1 = guest CR
-	 *
 	 */
 
 	/* Save registers */