KVM: PPC: Book3S 64: Move GUEST_MODE_SKIP test into KVM

Move the GUEST_MODE_SKIP logic into KVM code. This is quite a KVM
internal detail that has no real need to be in common handlers.

Add a comment explaining the what and why of KVM "skip" interrupts.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Daniel Axtens <dja@axtens.net>
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210528090752.3542186-3-npiggin@gmail.com

arch/powerpc/kernel/exceptions-64s.S

@@ -133,7 +133,6 @@ name:
 #define IBRANCH_TO_COMMON	.L_IBRANCH_TO_COMMON_\name\() /* ENTRY branch to common */
 #define IREALMODE_COMMON	.L_IREALMODE_COMMON_\name\() /* Common runs in realmode */
 #define IMASK		.L_IMASK_\name\()	/* IRQ soft-mask bit */
-#define IKVM_SKIP	.L_IKVM_SKIP_\name\()	/* Generate KVM skip handler */
 #define IKVM_REAL	.L_IKVM_REAL_\name\()	/* Real entry tests KVM */
 #define __IKVM_REAL(name)	.L_IKVM_REAL_ ## name
 #define IKVM_VIRT	.L_IKVM_VIRT_\name\()	/* Virt entry tests KVM */
@@ -190,9 +189,6 @@ do_define_int n
 	.ifndef IMASK
 		IMASK=0
 	.endif
-	.ifndef IKVM_SKIP
-		IKVM_SKIP=0
-	.endif
 	.ifndef IKVM_REAL
 		IKVM_REAL=0
 	.endif
@@ -250,15 +246,10 @@ do_define_int n
 	.balign IFETCH_ALIGN_BYTES
 \name\()_kvm:
 
-	.if IKVM_SKIP
-	cmpwi	r10,KVM_GUEST_MODE_SKIP
-	beq	89f
-	.else
 BEGIN_FTR_SECTION
 	ld	r10,IAREA+EX_CFAR(r13)
 	std	r10,HSTATE_CFAR(r13)
 END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
-	.endif
 
 	ld	r10,IAREA+EX_CTR(r13)
 	mtctr	r10
@@ -285,27 +276,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	ori	r12,r12,(IVEC)
 	.endif
 	b	kvmppc_interrupt
-
-	.if IKVM_SKIP
-89:	mtocrf	0x80,r9
-	ld	r10,IAREA+EX_CTR(r13)
-	mtctr	r10
-	ld	r9,IAREA+EX_R9(r13)
-	ld	r10,IAREA+EX_R10(r13)
-	ld	r11,IAREA+EX_R11(r13)
-	ld	r12,IAREA+EX_R12(r13)
-	.if IHSRR_IF_HVMODE
-	BEGIN_FTR_SECTION
-	b	kvmppc_skip_Hinterrupt
-	FTR_SECTION_ELSE
-	b	kvmppc_skip_interrupt
-	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-	.elseif IHSRR
-	b	kvmppc_skip_Hinterrupt
-	.else
-	b	kvmppc_skip_interrupt
-	.endif
-	.endif
 .endm
 
 #else
@@ -1064,7 +1034,6 @@ INT_DEFINE_BEGIN(machine_check)
 	ISET_RI=0
 	IDAR=1
 	IDSISR=1
-	IKVM_SKIP=1
 	IKVM_REAL=1
 INT_DEFINE_END(machine_check)
 
@@ -1336,7 +1305,6 @@ INT_DEFINE_BEGIN(data_access)
 	IVEC=0x300
 	IDAR=1
 	IDSISR=1
-	IKVM_SKIP=1
 	IKVM_REAL=1
 INT_DEFINE_END(data_access)
 
@@ -1390,7 +1358,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 INT_DEFINE_BEGIN(data_access_slb)
 	IVEC=0x380
 	IDAR=1
-	IKVM_SKIP=1
 	IKVM_REAL=1
 INT_DEFINE_END(data_access_slb)
 
@@ -2057,7 +2024,6 @@ INT_DEFINE_BEGIN(h_data_storage)
 	IHSRR=1
 	IDAR=1
 	IDSISR=1
-	IKVM_SKIP=1
 	IKVM_REAL=1
 	IKVM_VIRT=1
 INT_DEFINE_END(h_data_storage)
@@ -3003,32 +2969,6 @@ EXPORT_SYMBOL(do_uaccess_flush)
 MASKED_INTERRUPT
 MASKED_INTERRUPT hsrr=1
 
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-kvmppc_skip_interrupt:
-	/*
-	 * Here all GPRs are unchanged from when the interrupt happened
-	 * except for r13, which is saved in SPRG_SCRATCH0.
-	 */
-	mfspr	r13, SPRN_SRR0
-	addi	r13, r13, 4
-	mtspr	SPRN_SRR0, r13
-	GET_SCRATCH0(r13)
-	RFI_TO_KERNEL
-	b	.
-
-kvmppc_skip_Hinterrupt:
-	/*
-	 * Here all GPRs are unchanged from when the interrupt happened
-	 * except for r13, which is saved in SPRG_SCRATCH0.
-	 */
-	mfspr	r13, SPRN_HSRR0
-	addi	r13, r13, 4
-	mtspr	SPRN_HSRR0, r13
-	GET_SCRATCH0(r13)
-	HRFI_TO_KERNEL
-	b	.
-#endif
-
 	/*
 	 * Relocation-on interrupts: A subset of the interrupts can be delivered
 	 * with IR=1/DR=1, if AIL==2 and MSR.HV won't be changed by delivering

arch/powerpc/kvm/book3s_64_entry.S

 /* SPDX-License-Identifier: GPL-2.0-only */
 #include <asm/asm-offsets.h>
 #include <asm/cache.h>
+#include <asm/exception-64s.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_book3s_asm.h>
 #include <asm/ppc_asm.h>
@@ -20,9 +21,12 @@ kvmppc_interrupt:
 	 * guest R12 saved in shadow VCPU SCRATCH0
 	 * guest R13 saved in SPRN_SCRATCH0
 	 */
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	std	r9,HSTATE_SCRATCH2(r13)
 	lbz	r9,HSTATE_IN_GUEST(r13)
+	cmpwi	r9,KVM_GUEST_MODE_SKIP
+	beq-	.Lmaybe_skip
+.Lno_skip:
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	cmpwi	r9,KVM_GUEST_MODE_HOST_HV
 	beq	kvmppc_bad_host_intr
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
@@ -32,5 +36,58 @@ kvmppc_interrupt:
 #endif
 	b	kvmppc_interrupt_hv
 #else
+	ld	r9,HSTATE_SCRATCH2(r13)
 	b	kvmppc_interrupt_pr
 #endif
+
+/*
+ * "Skip" interrupts are part of a trick KVM uses a with hash guests to load
+ * the faulting instruction in guest memory from the the hypervisor without
+ * walking page tables.
+ *
+ * When the guest takes a fault that requires the hypervisor to load the
+ * instruction (e.g., MMIO emulation), KVM is running in real-mode with HV=1
+ * and the guest MMU context loaded. It sets KVM_GUEST_MODE_SKIP, and sets
+ * MSR[DR]=1 while leaving MSR[IR]=0, so it continues to fetch HV instructions
+ * but loads and stores will access the guest context. This is used to load
+ * the faulting instruction using the faulting guest effective address.
+ *
+ * However the guest context may not be able to translate, or it may cause a
+ * machine check or other issue, which results in a fault in the host
+ * (even with KVM-HV).
+ *
+ * These faults come here because KVM_GUEST_MODE_SKIP was set, so if they
+ * are (or are likely) caused by that load, the instruction is skipped by
+ * just returning with the PC advanced +4, where it is noticed the load did
+ * not execute and it goes to the slow path which walks the page tables to
+ * read guest memory.
+ */
+.Lmaybe_skip:
+	cmpwi	r12,BOOK3S_INTERRUPT_MACHINE_CHECK
+	beq	1f
+	cmpwi	r12,BOOK3S_INTERRUPT_DATA_STORAGE
+	beq	1f
+	cmpwi	r12,BOOK3S_INTERRUPT_DATA_SEGMENT
+	beq	1f
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/* HSRR interrupts get 2 added to interrupt number */
+	cmpwi	r12,BOOK3S_INTERRUPT_H_DATA_STORAGE | 0x2
+	beq	2f
+#endif
+	b	.Lno_skip
+1:	mfspr	r9,SPRN_SRR0
+	addi	r9,r9,4
+	mtspr	SPRN_SRR0,r9
+	ld	r12,HSTATE_SCRATCH0(r13)
+	ld	r9,HSTATE_SCRATCH2(r13)
+	GET_SCRATCH0(r13)
+	RFI_TO_KERNEL
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+2:	mfspr	r9,SPRN_HSRR0
+	addi	r9,r9,4
+	mtspr	SPRN_HSRR0,r9
+	ld	r12,HSTATE_SCRATCH0(r13)
+	ld	r9,HSTATE_SCRATCH2(r13)
+	GET_SCRATCH0(r13)
+	HRFI_TO_KERNEL
+#endif