[PATCH v1 0/7] KVM / 64s interrupt handling changes

[PATCH v1 0/7] KVM / 64s interrupt handling changes

[Nicholas Piggin]

This is the second batch of patches split from the big KVM in C
series.

This implements all the changes to exception-64s.S required for the
subsequent C conversion. I think they stand on their own as good
patches.

The main things done here are to make the code more amenable to
adding different KVM interrupt handlers (rather than just PR and
HV), and moving a lot of KVM specific code out of exceptions-64s.S
and moving it to arch/powerpc/kvm/book3s_64_entry.S. Calling
convention between those files is changed to mostly match the
exception-64s.S "GEN_INT_ENTRY" convention, so that's a change but
now you only have to remember that one for both cases (either
branching to KVM handler or continuing to GEN_COMMON handler).

This is tested with HV KVM, nested HV under radix L0+L1, and nested
PR KVM under HPT guest. All seems to be working okay.

Thanks,
Nick

Nicholas Piggin (7):
  KVM: PPC: Book3S 64: move KVM interrupt entry to a common entry point
  KVM: PPC: Book3S 64: Move GUEST_MODE_SKIP test into KVM
  KVM: PPC: Book3S 64: add hcall interrupt handler
  KVM: PPC: Book3S 64: Move hcall early register setup to KVM
  KVM: PPC: Book3S 64: Move interrupt early register setup to KVM
  KVM: PPC: Book3S 64: move bad_host_intr check to HV handler
  KVM: PPC: Book3S 64: Minimise hcall handler calling convention
    differences

 arch/powerpc/include/asm/exception-64s.h |  13 ++
 arch/powerpc/kernel/exceptions-64s.S     | 250 ++++-------------------
 arch/powerpc/kvm/Makefile                |   3 +
 arch/powerpc/kvm/book3s_64_entry.S       | 158 ++++++++++++++
 arch/powerpc/kvm/book3s_hv_rmhandlers.S  |  13 +-
 arch/powerpc/kvm/book3s_segment.S        |   3 +
 6 files changed, 220 insertions(+), 220 deletions(-)
 create mode 100644 arch/powerpc/kvm/book3s_64_entry.S

-- 
2.23.0

[PATCH v1 1/7] KVM: PPC: Book3S 64: move KVM interrupt entry to a common entry point

[Nicholas Piggin]

Rather than bifurcate the call depending on whether or not HV is
possible, and have the HV entry test for PR, just make a single
common point which does the demultiplexing. This makes it simpler
to add another type of exit handler.

Acked-by: Paul Mackerras <paulus@ozlabs.org>
Reviewed-by: Daniel Axtens <dja@axtens.net>
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/exceptions-64s.S    |  8 +-----
 arch/powerpc/kvm/Makefile               |  3 +++
 arch/powerpc/kvm/book3s_64_entry.S      | 36 +++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 11 ++------
 4 files changed, 42 insertions(+), 16 deletions(-)
 create mode 100644 arch/powerpc/kvm/book3s_64_entry.S

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 358cd4b0c08e..bdec40bd92a8 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -208,7 +208,6 @@ do_define_int n
 .endm
 
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 /*
  * All interrupts which set HSRR registers, as well as SRESET and MCE and
  * syscall when invoked with "sc 1" switch to MSR[HV]=1 (HVMODE) to be taken,
@@ -238,13 +237,8 @@ do_define_int n
 
 /*
  * If an interrupt is taken while a guest is running, it is immediately routed
- * to KVM to handle. If both HV and PR KVM arepossible, KVM interrupts go first
- * to kvmppc_interrupt_hv, which handles the PR guest case.
+ * to KVM to handle.
  */
-#define kvmppc_interrupt kvmppc_interrupt_hv
-#else
-#define kvmppc_interrupt kvmppc_interrupt_pr
-#endif
 
 .macro KVMTEST name
 	lbz	r10,HSTATE_IN_GUEST(r13)
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 2bfeaa13befb..cdd119028f64 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -59,6 +59,9 @@ kvm-pr-y := \
 kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
 	tm.o
 
+kvm-book3s_64-builtin-objs-y += \
+	book3s_64_entry.o
+
 ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
 	book3s_rmhandlers.o
diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
new file mode 100644
index 000000000000..7a039ea78f15
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#include <asm/asm-offsets.h>
+#include <asm/cache.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_book3s_asm.h>
+#include <asm/ppc_asm.h>
+#include <asm/reg.h>
+
+/*
+ * This is branched to from interrupt handlers in exception-64s.S which set
+ * IKVM_REAL or IKVM_VIRT, if HSTATE_IN_GUEST was found to be non-zero.
+ */
+.global	kvmppc_interrupt
+.balign IFETCH_ALIGN_BYTES
+kvmppc_interrupt:
+	/*
+	 * Register contents:
+	 * R12		= (guest CR << 32) | interrupt vector
+	 * R13		= PACA
+	 * 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_HOST_HV
+	beq	kvmppc_bad_host_intr
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	cmpwi	r9,KVM_GUEST_MODE_GUEST
+	ld	r9,HSTATE_SCRATCH2(r13)
+	beq	kvmppc_interrupt_pr
+#endif
+	b	kvmppc_interrupt_hv
+#else
+	b	kvmppc_interrupt_pr
+#endif
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 5e634db4809b..f976efb7e4a9 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1269,16 +1269,8 @@ kvmppc_interrupt_hv:
 	 * R13		= PACA
 	 * guest R12 saved in shadow VCPU SCRATCH0
 	 * guest R13 saved in SPRN_SCRATCH0
+	 * guest R9 saved in HSTATE_SCRATCH2
 	 */
-	std	r9, HSTATE_SCRATCH2(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)
-	beq	kvmppc_interrupt_pr
-#endif
 	/* We're now back in the host but in guest MMU context */
 	li	r9, KVM_GUEST_MODE_HOST_HV
 	stb	r9, HSTATE_IN_GUEST(r13)
@@ -3280,6 +3272,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_P9_TM_HV_ASSIST)
  * cfar is saved in HSTATE_CFAR(r13)
  * ppr is saved in HSTATE_PPR(r13)
  */
+.global kvmppc_bad_host_intr
 kvmppc_bad_host_intr:
 	/*
 	 * Switch to the emergency stack, but start half-way down in
-- 
2.23.0

[PATCH v1 2/7] KVM: PPC: Book3S 64: Move GUEST_MODE_SKIP test into KVM

[Nicholas Piggin]

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.

Reviewed-by: Daniel Axtens <dja@axtens.net>
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/exceptions-64s.S | 60 ----------------------------
 arch/powerpc/kvm/book3s_64_entry.S   | 59 ++++++++++++++++++++++++++-
 2 files changed, 58 insertions(+), 61 deletions(-)

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index bdec40bd92a8..5842cc3ebbbb 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/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
@@ -1083,7 +1053,6 @@ INT_DEFINE_BEGIN(machine_check)
 	ISET_RI=0
 	IDAR=1
 	IDSISR=1
-	IKVM_SKIP=1
 	IKVM_REAL=1
 INT_DEFINE_END(machine_check)
 
@@ -1356,7 +1325,6 @@ INT_DEFINE_BEGIN(data_access)
 	IVEC=0x300
 	IDAR=1
 	IDSISR=1
-	IKVM_SKIP=1
 	IKVM_REAL=1
 INT_DEFINE_END(data_access)
 
@@ -1410,7 +1378,6 @@ 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)
 
@@ -2080,7 +2047,6 @@ 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)
@@ -3030,32 +2996,6 @@ 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
diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
index 7a039ea78f15..bf927e7a06af 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -1,6 +1,7 @@
 /* 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
-- 
2.23.0

[PATCH v1 3/7] KVM: PPC: Book3S 64: add hcall interrupt handler

[Nicholas Piggin]

Add a separate hcall entry point. This can be used to deal with the
different calling convention.

Reviewed-by: Daniel Axtens <dja@axtens.net>
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/exceptions-64s.S | 6 +++---
 arch/powerpc/kvm/book3s_64_entry.S   | 6 +++++-
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 5842cc3ebbbb..9467fd1038f9 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1989,16 +1989,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	ori	r12,r12,0xc00
 #ifdef CONFIG_RELOCATABLE
 	/*
-	 * Requires __LOAD_FAR_HANDLER beause kvmppc_interrupt lives
+	 * Requires __LOAD_FAR_HANDLER beause kvmppc_hcall lives
 	 * outside the head section.
 	 */
-	__LOAD_FAR_HANDLER(r10, kvmppc_interrupt)
+	__LOAD_FAR_HANDLER(r10, kvmppc_hcall)
 	mtctr   r10
 	ld	r10,PACA_EXGEN+EX_R10(r13)
 	bctr
 #else
 	ld	r10,PACA_EXGEN+EX_R10(r13)
-	b       kvmppc_interrupt
+	b       kvmppc_hcall
 #endif
 #endif
 
diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
index bf927e7a06af..c21fa64059ef 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -8,9 +8,13 @@
 #include <asm/reg.h>
 
 /*
- * This is branched to from interrupt handlers in exception-64s.S which set
+ * These are branched to from interrupt handlers in exception-64s.S which set
  * IKVM_REAL or IKVM_VIRT, if HSTATE_IN_GUEST was found to be non-zero.
  */
+.global	kvmppc_hcall
+.balign IFETCH_ALIGN_BYTES
+kvmppc_hcall:
+
 .global	kvmppc_interrupt
 .balign IFETCH_ALIGN_BYTES
 kvmppc_interrupt:
-- 
2.23.0

[PATCH v1 4/7] KVM: PPC: Book3S 64: Move hcall early register setup to KVM

[Nicholas Piggin]

System calls / hcalls have a different calling convention than
other interrupts, so there is code in the KVMTEST to massage these
into the same form as other interrupt handlers.

Move this work into the KVM hcall handler. This means teaching KVM
a little more about the low level interrupt handler setup, PACA save
areas, etc., although that's not obviously worse than the current
approach of coming up with an entirely different interrupt register
/ save convention.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/exception-64s.h | 13 ++++++++
 arch/powerpc/kernel/exceptions-64s.S     | 42 +-----------------------
 arch/powerpc/kvm/book3s_64_entry.S       | 30 +++++++++++++++++
 3 files changed, 44 insertions(+), 41 deletions(-)

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index c1a8aac01cf9..bb6f78fcf981 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -35,6 +35,19 @@
 /* PACA save area size in u64 units (exgen, exmc, etc) */
 #define EX_SIZE		10
 
+/* PACA save area offsets */
+#define EX_R9		0
+#define EX_R10		8
+#define EX_R11		16
+#define EX_R12		24
+#define EX_R13		32
+#define EX_DAR		40
+#define EX_DSISR	48
+#define EX_CCR		52
+#define EX_CFAR		56
+#define EX_PPR		64
+#define EX_CTR		72
+
 /*
  * maximum recursive depth of MCE exceptions
  */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 9467fd1038f9..1bfd0d7af09e 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -21,22 +21,6 @@
 #include <asm/feature-fixups.h>
 #include <asm/kup.h>
 
-/* PACA save area offsets (exgen, exmc, etc) */
-#define EX_R9		0
-#define EX_R10		8
-#define EX_R11		16
-#define EX_R12		24
-#define EX_R13		32
-#define EX_DAR		40
-#define EX_DSISR	48
-#define EX_CCR		52
-#define EX_CFAR		56
-#define EX_PPR		64
-#define EX_CTR		72
-.if EX_SIZE != 10
-	.error "EX_SIZE is wrong"
-.endif
-
 /*
  * Following are fixed section helper macros.
  *
@@ -1964,29 +1948,8 @@ EXC_VIRT_END(system_call, 0x4c00, 0x100)
 
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 TRAMP_REAL_BEGIN(system_call_kvm)
-	/*
-	 * This is a hcall, so register convention is as above, with these
-	 * differences:
-	 * r13 = PACA
-	 * ctr = orig r13
-	 * orig r10 saved in PACA
-	 */
-	 /*
-	  * Save the PPR (on systems that support it) before changing to
-	  * HMT_MEDIUM. That allows the KVM code to save that value into the
-	  * guest state (it is the guest's PPR value).
-	  */
-BEGIN_FTR_SECTION
-	mfspr	r10,SPRN_PPR
-	std	r10,HSTATE_PPR(r13)
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
-	HMT_MEDIUM
 	mfctr	r10
-	SET_SCRATCH0(r10)
-	mfcr	r10
-	std	r12,HSTATE_SCRATCH0(r13)
-	sldi	r12,r10,32
-	ori	r12,r12,0xc00
+	SET_SCRATCH0(r10) /* Save r13 in SCRATCH0 */
 #ifdef CONFIG_RELOCATABLE
 	/*
 	 * Requires __LOAD_FAR_HANDLER beause kvmppc_hcall lives
@@ -1994,15 +1957,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	 */
 	__LOAD_FAR_HANDLER(r10, kvmppc_hcall)
 	mtctr   r10
-	ld	r10,PACA_EXGEN+EX_R10(r13)
 	bctr
 #else
-	ld	r10,PACA_EXGEN+EX_R10(r13)
 	b       kvmppc_hcall
 #endif
 #endif
 
-
 /**
  * Interrupt 0xd00 - Trace Interrupt.
  * This is a synchronous interrupt in response to instruction step or
diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
index c21fa64059ef..f527e16707db 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -14,6 +14,36 @@
 .global	kvmppc_hcall
 .balign IFETCH_ALIGN_BYTES
 kvmppc_hcall:
+	/*
+	 * This is a hcall, so register convention is as
+	 * Documentation/powerpc/papr_hcalls.rst, with these additions:
+	 * R13		= PACA
+	 * guest R13 saved in SPRN_SCRATCH0
+	 * R10		= free
+	 * guest r10 saved in PACA_EXGEN
+	 *
+	 * This may also be a syscall from PR-KVM userspace that is to be
+	 * reflected to the PR guest kernel, so registers may be set up for
+	 * a system call rather than hcall. We don't currently clobber
+	 * anything here, but the 0xc00 handler has already clobbered CTR
+	 * and CR0, so PR-KVM can not support a guest kernel that preserves
+	 * those registers across its system calls.
+	 */
+	 /*
+	  * Save the PPR (on systems that support it) before changing to
+	  * HMT_MEDIUM. That allows the KVM code to save that value into the
+	  * guest state (it is the guest's PPR value).
+	  */
+BEGIN_FTR_SECTION
+	mfspr	r10,SPRN_PPR
+	std	r10,HSTATE_PPR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+	HMT_MEDIUM
+	mfcr	r10
+	std	r12,HSTATE_SCRATCH0(r13)
+	sldi	r12,r10,32
+	ori	r12,r12,0xc00
+	ld	r10,PACA_EXGEN+EX_R10(r13)
 
 .global	kvmppc_interrupt
 .balign IFETCH_ALIGN_BYTES
-- 
2.23.0

[PATCH v1 5/7] KVM: PPC: Book3S 64: Move interrupt early register setup to KVM

[Nicholas Piggin]

Like the earlier patch for hcalls, KVM interrupt entry requires a
different calling convention than the Linux interrupt handlers
set up. Move the code that converts from one to the other into KVM.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/exceptions-64s.S | 131 +++++----------------------
 arch/powerpc/kvm/book3s_64_entry.S   |  50 +++++++++-
 2 files changed, 71 insertions(+), 110 deletions(-)

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 1bfd0d7af09e..cd1731642b12 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -187,7 +187,6 @@ do_define_int n
 	.endif
 .endm
 
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 /*
  * All interrupts which set HSRR registers, as well as SRESET and MCE and
  * syscall when invoked with "sc 1" switch to MSR[HV]=1 (HVMODE) to be taken,
@@ -220,54 +219,25 @@ do_define_int n
  * to KVM to handle.
  */
 
-.macro KVMTEST name
+.macro KVMTEST name handler
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 	lbz	r10,HSTATE_IN_GUEST(r13)
 	cmpwi	r10,0
-	bne	\name\()_kvm
-.endm
-
-.macro GEN_KVM name
-	.balign IFETCH_ALIGN_BYTES
-\name\()_kvm:
-
-BEGIN_FTR_SECTION
-	ld	r10,IAREA+EX_CFAR(r13)
-	std	r10,HSTATE_CFAR(r13)
-END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
-
-	ld	r10,IAREA+EX_CTR(r13)
-	mtctr	r10
-BEGIN_FTR_SECTION
-	ld	r10,IAREA+EX_PPR(r13)
-	std	r10,HSTATE_PPR(r13)
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
-	ld	r11,IAREA+EX_R11(r13)
-	ld	r12,IAREA+EX_R12(r13)
-	std	r12,HSTATE_SCRATCH0(r13)
-	sldi	r12,r9,32
-	ld	r9,IAREA+EX_R9(r13)
-	ld	r10,IAREA+EX_R10(r13)
 	/* HSRR variants have the 0x2 bit added to their trap number */
 	.if IHSRR_IF_HVMODE
 	BEGIN_FTR_SECTION
-	ori	r12,r12,(IVEC + 0x2)
+	li	r10,(IVEC + 0x2)
 	FTR_SECTION_ELSE
-	ori	r12,r12,(IVEC)
+	li	r10,(IVEC)
 	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
 	.elseif IHSRR
-	ori	r12,r12,(IVEC+ 0x2)
+	li	r10,(IVEC + 0x2)
 	.else
-	ori	r12,r12,(IVEC)
+	li	r10,(IVEC)
 	.endif
-	b	kvmppc_interrupt
-.endm
-
-#else
-.macro KVMTEST name
-.endm
-.macro GEN_KVM name
-.endm
+	bne	\handler
 #endif
+.endm
 
 /*
  * This is the BOOK3S interrupt entry code macro.
@@ -409,7 +379,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 DEFINE_FIXED_SYMBOL(\name\()_common_real)
 \name\()_common_real:
 	.if IKVM_REAL
-		KVMTEST \name
+		KVMTEST \name kvm_interrupt
 	.endif
 
 	ld	r10,PACAKMSR(r13)	/* get MSR value for kernel */
@@ -432,7 +402,7 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real)
 DEFINE_FIXED_SYMBOL(\name\()_common_virt)
 \name\()_common_virt:
 	.if IKVM_VIRT
-		KVMTEST \name
+		KVMTEST \name kvm_interrupt
 1:
 	.endif
 	.endif /* IVIRT */
@@ -446,7 +416,7 @@ DEFINE_FIXED_SYMBOL(\name\()_common_virt)
 DEFINE_FIXED_SYMBOL(\name\()_common_real)
 \name\()_common_real:
 	.if IKVM_REAL
-		KVMTEST \name
+		KVMTEST \name kvm_interrupt
 	.endif
 .endm
 
@@ -967,8 +937,6 @@ EXC_COMMON_BEGIN(system_reset_common)
 	EXCEPTION_RESTORE_REGS
 	RFI_TO_USER_OR_KERNEL
 
-	GEN_KVM system_reset
-
 
 /**
  * Interrupt 0x200 - Machine Check Interrupt (MCE).
@@ -1132,7 +1100,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
 	/*
 	 * Check if we are coming from guest. If yes, then run the normal
 	 * exception handler which will take the
-	 * machine_check_kvm->kvmppc_interrupt branch to deliver the MC event
+	 * machine_check_kvm->kvm_interrupt branch to deliver the MC event
 	 * to guest.
 	 */
 	lbz	r11,HSTATE_IN_GUEST(r13)
@@ -1203,8 +1171,6 @@ EXC_COMMON_BEGIN(machine_check_common)
 	bl	machine_check_exception
 	b	interrupt_return
 
-	GEN_KVM machine_check
-
 
 #ifdef CONFIG_PPC_P7_NAP
 /*
@@ -1339,8 +1305,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 	REST_NVGPRS(r1)
 	b	interrupt_return
 
-	GEN_KVM data_access
-
 
 /**
  * Interrupt 0x380 - Data Segment Interrupt (DSLB).
@@ -1390,8 +1354,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 	bl	do_bad_slb_fault
 	b	interrupt_return
 
-	GEN_KVM data_access_slb
-
 
 /**
  * Interrupt 0x400 - Instruction Storage Interrupt (ISI).
@@ -1428,8 +1390,6 @@ MMU_FTR_SECTION_ELSE
 ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 	b	interrupt_return
 
-	GEN_KVM instruction_access
-
 
 /**
  * Interrupt 0x480 - Instruction Segment Interrupt (ISLB).
@@ -1474,8 +1434,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 	bl	do_bad_slb_fault
 	b	interrupt_return
 
-	GEN_KVM instruction_access_slb
-
 
 /**
  * Interrupt 0x500 - External Interrupt.
@@ -1521,8 +1479,6 @@ EXC_COMMON_BEGIN(hardware_interrupt_common)
 	bl	do_IRQ
 	b	interrupt_return
 
-	GEN_KVM hardware_interrupt
-
 
 /**
  * Interrupt 0x600 - Alignment Interrupt
@@ -1550,8 +1506,6 @@ EXC_COMMON_BEGIN(alignment_common)
 	REST_NVGPRS(r1) /* instruction emulation may change GPRs */
 	b	interrupt_return
 
-	GEN_KVM alignment
-
 
 /**
  * Interrupt 0x700 - Program Interrupt (program check).
@@ -1659,8 +1613,6 @@ EXC_COMMON_BEGIN(program_check_common)
 	REST_NVGPRS(r1) /* instruction emulation may change GPRs */
 	b	interrupt_return
 
-	GEN_KVM program_check
-
 
 /*
  * Interrupt 0x800 - Floating-Point Unavailable Interrupt.
@@ -1710,8 +1662,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 	b	interrupt_return
 #endif
 
-	GEN_KVM fp_unavailable
-
 
 /**
  * Interrupt 0x900 - Decrementer Interrupt.
@@ -1751,8 +1701,6 @@ EXC_COMMON_BEGIN(decrementer_common)
 	bl	timer_interrupt
 	b	interrupt_return
 
-	GEN_KVM decrementer
-
 
 /**
  * Interrupt 0x980 - Hypervisor Decrementer Interrupt.
@@ -1798,8 +1746,6 @@ EXC_COMMON_BEGIN(hdecrementer_common)
 	ld	r13,PACA_EXGEN+EX_R13(r13)
 	HRFI_TO_KERNEL
 
-	GEN_KVM hdecrementer
-
 
 /**
  * Interrupt 0xa00 - Directed Privileged Doorbell Interrupt.
@@ -1840,8 +1786,6 @@ EXC_COMMON_BEGIN(doorbell_super_common)
 #endif
 	b	interrupt_return
 
-	GEN_KVM doorbell_super
-
 
 EXC_REAL_NONE(0xb00, 0x100)
 EXC_VIRT_NONE(0x4b00, 0x100)
@@ -1891,7 +1835,7 @@ INT_DEFINE_END(system_call)
 	GET_PACA(r13)
 	std	r10,PACA_EXGEN+EX_R10(r13)
 	INTERRUPT_TO_KERNEL
-	KVMTEST system_call /* uses r10, branch to system_call_kvm */
+	KVMTEST system_call kvm_hcall /* uses r10, branch to kvm_hcall */
 	mfctr	r9
 #else
 	mr	r9,r13
@@ -1947,7 +1891,7 @@ EXC_VIRT_BEGIN(system_call, 0x4c00, 0x100)
 EXC_VIRT_END(system_call, 0x4c00, 0x100)
 
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-TRAMP_REAL_BEGIN(system_call_kvm)
+TRAMP_REAL_BEGIN(kvm_hcall)
 	mfctr	r10
 	SET_SCRATCH0(r10) /* Save r13 in SCRATCH0 */
 #ifdef CONFIG_RELOCATABLE
@@ -1987,8 +1931,6 @@ EXC_COMMON_BEGIN(single_step_common)
 	bl	single_step_exception
 	b	interrupt_return
 
-	GEN_KVM single_step
-
 
 /**
  * Interrupt 0xe00 - Hypervisor Data Storage Interrupt (HDSI).
@@ -2027,8 +1969,6 @@ MMU_FTR_SECTION_ELSE
 ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX)
 	b       interrupt_return
 
-	GEN_KVM h_data_storage
-
 
 /**
  * Interrupt 0xe20 - Hypervisor Instruction Storage Interrupt (HISI).
@@ -2054,8 +1994,6 @@ EXC_COMMON_BEGIN(h_instr_storage_common)
 	bl	unknown_exception
 	b	interrupt_return
 
-	GEN_KVM h_instr_storage
-
 
 /**
  * Interrupt 0xe40 - Hypervisor Emulation Assistance Interrupt.
@@ -2080,8 +2018,6 @@ EXC_COMMON_BEGIN(emulation_assist_common)
 	REST_NVGPRS(r1) /* instruction emulation may change GPRs */
 	b	interrupt_return
 
-	GEN_KVM emulation_assist
-
 
 /**
  * Interrupt 0xe60 - Hypervisor Maintenance Interrupt (HMI).
@@ -2153,8 +2089,6 @@ EXC_COMMON_BEGIN(hmi_exception_early_common)
 	EXCEPTION_RESTORE_REGS hsrr=1
 	GEN_INT_ENTRY hmi_exception, virt=0
 
-	GEN_KVM hmi_exception_early
-
 EXC_COMMON_BEGIN(hmi_exception_common)
 	GEN_COMMON hmi_exception
 	FINISH_NAP
@@ -2162,8 +2096,6 @@ EXC_COMMON_BEGIN(hmi_exception_common)
 	bl	handle_hmi_exception
 	b	interrupt_return
 
-	GEN_KVM hmi_exception
-
 
 /**
  * Interrupt 0xe80 - Directed Hypervisor Doorbell Interrupt.
@@ -2195,8 +2127,6 @@ EXC_COMMON_BEGIN(h_doorbell_common)
 #endif
 	b	interrupt_return
 
-	GEN_KVM h_doorbell
-
 
 /**
  * Interrupt 0xea0 - Hypervisor Virtualization Interrupt.
@@ -2224,8 +2154,6 @@ EXC_COMMON_BEGIN(h_virt_irq_common)
 	bl	do_IRQ
 	b	interrupt_return
 
-	GEN_KVM h_virt_irq
-
 
 EXC_REAL_NONE(0xec0, 0x20)
 EXC_VIRT_NONE(0x4ec0, 0x20)
@@ -2270,8 +2198,6 @@ EXC_COMMON_BEGIN(performance_monitor_common)
 	bl	performance_monitor_exception
 	b	interrupt_return
 
-	GEN_KVM performance_monitor
-
 
 /**
  * Interrupt 0xf20 - Vector Unavailable Interrupt.
@@ -2321,8 +2247,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	bl	altivec_unavailable_exception
 	b	interrupt_return
 
-	GEN_KVM altivec_unavailable
-
 
 /**
  * Interrupt 0xf40 - VSX Unavailable Interrupt.
@@ -2371,8 +2295,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	bl	vsx_unavailable_exception
 	b	interrupt_return
 
-	GEN_KVM vsx_unavailable
-
 
 /**
  * Interrupt 0xf60 - Facility Unavailable Interrupt.
@@ -2401,8 +2323,6 @@ EXC_COMMON_BEGIN(facility_unavailable_common)
 	REST_NVGPRS(r1) /* instruction emulation may change GPRs */
 	b	interrupt_return
 
-	GEN_KVM facility_unavailable
-
 
 /**
  * Interrupt 0xf60 - Hypervisor Facility Unavailable Interrupt.
@@ -2431,8 +2351,6 @@ EXC_COMMON_BEGIN(h_facility_unavailable_common)
 	REST_NVGPRS(r1) /* XXX Shouldn't be necessary in practice */
 	b	interrupt_return
 
-	GEN_KVM h_facility_unavailable
-
 
 EXC_REAL_NONE(0xfa0, 0x20)
 EXC_VIRT_NONE(0x4fa0, 0x20)
@@ -2462,8 +2380,6 @@ EXC_COMMON_BEGIN(cbe_system_error_common)
 	bl	cbe_system_error_exception
 	b	interrupt_return
 
-	GEN_KVM cbe_system_error
-
 #else /* CONFIG_CBE_RAS */
 EXC_REAL_NONE(0x1200, 0x100)
 EXC_VIRT_NONE(0x5200, 0x100)
@@ -2495,8 +2411,6 @@ EXC_COMMON_BEGIN(instruction_breakpoint_common)
 	bl	instruction_breakpoint_exception
 	b	interrupt_return
 
-	GEN_KVM instruction_breakpoint
-
 
 EXC_REAL_NONE(0x1400, 0x100)
 EXC_VIRT_NONE(0x5400, 0x100)
@@ -2617,8 +2531,6 @@ EXC_COMMON_BEGIN(denorm_exception_common)
 	bl	unknown_exception
 	b	interrupt_return
 
-	GEN_KVM denorm_exception
-
 
 #ifdef CONFIG_CBE_RAS
 INT_DEFINE_BEGIN(cbe_maintenance)
@@ -2636,8 +2548,6 @@ EXC_COMMON_BEGIN(cbe_maintenance_common)
 	bl	cbe_maintenance_exception
 	b	interrupt_return
 
-	GEN_KVM cbe_maintenance
-
 #else /* CONFIG_CBE_RAS */
 EXC_REAL_NONE(0x1600, 0x100)
 EXC_VIRT_NONE(0x5600, 0x100)
@@ -2668,8 +2578,6 @@ EXC_COMMON_BEGIN(altivec_assist_common)
 #endif
 	b	interrupt_return
 
-	GEN_KVM altivec_assist
-
 
 #ifdef CONFIG_CBE_RAS
 INT_DEFINE_BEGIN(cbe_thermal)
@@ -2687,8 +2595,6 @@ EXC_COMMON_BEGIN(cbe_thermal_common)
 	bl	cbe_thermal_exception
 	b	interrupt_return
 
-	GEN_KVM cbe_thermal
-
 #else /* CONFIG_CBE_RAS */
 EXC_REAL_NONE(0x1800, 0x100)
 EXC_VIRT_NONE(0x5800, 0x100)
@@ -2941,6 +2847,15 @@ TRAMP_REAL_BEGIN(rfscv_flush_fallback)
 
 USE_TEXT_SECTION()
 
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+kvm_interrupt:
+	/*
+	 * The conditional branch in KVMTEST can't reach all the way,
+	 * make a stub.
+	 */
+	b	kvmppc_interrupt
+#endif
+
 _GLOBAL(do_uaccess_flush)
 	UACCESS_FLUSH_FIXUP_SECTION
 	nop
diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
index f527e16707db..2c9d106145e8 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -44,15 +44,61 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	sldi	r12,r10,32
 	ori	r12,r12,0xc00
 	ld	r10,PACA_EXGEN+EX_R10(r13)
+	b	do_kvm_interrupt
 
+/*
+ * KVM interrupt entry occurs after GEN_INT_ENTRY runs, and follows that
+ * call convention:
+ *
+ * guest R9-R13, CTR, CFAR, PPR saved in PACA EX_xxx save area
+ * guest (H)DAR, (H)DSISR are also in the save area for relevant interrupts
+ * guest R13 also saved in SCRATCH0
+ * R13		= PACA
+ * R11		= (H)SRR0
+ * R12		= (H)SRR1
+ * R9		= guest CR
+ * PPR is set to medium
+ *
+ * With the addition for KVM:
+ * R10		= trap vector
+ */
 .global	kvmppc_interrupt
 .balign IFETCH_ALIGN_BYTES
 kvmppc_interrupt:
+	li	r11,PACA_EXGEN
+	cmpdi	r10,0x200
+	bgt+	1f
+	li	r11,PACA_EXMC
+	beq	1f
+	li	r11,PACA_EXNMI
+1:	add	r11,r11,r13
+
+BEGIN_FTR_SECTION
+	ld	r12,EX_CFAR(r11)
+	std	r12,HSTATE_CFAR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+	ld	r12,EX_CTR(r11)
+	mtctr	r12
+BEGIN_FTR_SECTION
+	ld	r12,EX_PPR(r11)
+	std	r12,HSTATE_PPR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+	ld	r12,EX_R12(r11)
+	std	r12,HSTATE_SCRATCH0(r13)
+	sldi	r12,r9,32
+	or	r12,r12,r10
+	ld	r9,EX_R9(r11)
+	ld	r10,EX_R10(r11)
+	ld	r11,EX_R11(r11)
+
+do_kvm_interrupt:
 	/*
-	 * Register contents:
+	 * Hcalls and other interrupts come here after normalising register
+	 * contents and save locations:
+	 *
 	 * R12		= (guest CR << 32) | interrupt vector
 	 * R13		= PACA
-	 * guest R12 saved in shadow VCPU SCRATCH0
+	 * guest R12 saved in shadow HSTATE_SCRATCH0
 	 * guest R13 saved in SPRN_SCRATCH0
 	 */
 	std	r9,HSTATE_SCRATCH2(r13)
-- 
2.23.0

[PATCH v1 6/7] KVM: PPC: Book3S 64: move bad_host_intr check to HV handler

[Nicholas Piggin]

The bad_host_intr check will never be true with PR KVM, move
it to HV code.

Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kvm/book3s_64_entry.S      | 4 ----
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 4 +++-
 arch/powerpc/kvm/book3s_segment.S       | 3 +++
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
index 2c9d106145e8..66170ea85bc2 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -107,16 +107,12 @@ do_kvm_interrupt:
 	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
 	cmpwi	r9,KVM_GUEST_MODE_GUEST
-	ld	r9,HSTATE_SCRATCH2(r13)
 	beq	kvmppc_interrupt_pr
 #endif
 	b	kvmppc_interrupt_hv
 #else
-	ld	r9,HSTATE_SCRATCH2(r13)
 	b	kvmppc_interrupt_pr
 #endif
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index f976efb7e4a9..75405ef53238 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1265,6 +1265,7 @@ hdec_soon:
 kvmppc_interrupt_hv:
 	/*
 	 * Register contents:
+	 * R9		= HSTATE_IN_GUEST
 	 * R12		= (guest CR << 32) | interrupt vector
 	 * R13		= PACA
 	 * guest R12 saved in shadow VCPU SCRATCH0
@@ -1272,6 +1273,8 @@ kvmppc_interrupt_hv:
 	 * guest R9 saved in HSTATE_SCRATCH2
 	 */
 	/* We're now back in the host but in guest MMU context */
+	cmpwi	r9,KVM_GUEST_MODE_HOST_HV
+	beq	kvmppc_bad_host_intr
 	li	r9, KVM_GUEST_MODE_HOST_HV
 	stb	r9, HSTATE_IN_GUEST(r13)
 
@@ -3272,7 +3275,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_P9_TM_HV_ASSIST)
  * cfar is saved in HSTATE_CFAR(r13)
  * ppr is saved in HSTATE_PPR(r13)
  */
-.global kvmppc_bad_host_intr
 kvmppc_bad_host_intr:
 	/*
 	 * Switch to the emergency stack, but start half-way down in
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 1f492aa4c8d6..202046a83fc1 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -164,12 +164,15 @@ kvmppc_interrupt_pr:
 	/* 64-bit entry. Register usage at this point:
 	 *
 	 * SPRG_SCRATCH0   = guest R13
+	 * R9              = HSTATE_IN_GUEST
 	 * R12             = (guest CR << 32) | exit handler id
 	 * R13             = PACA
 	 * HSTATE.SCRATCH0 = guest R12
+	 * HSTATE.SCRATCH2 = guest R9
 	 */
 #ifdef CONFIG_PPC64
 	/* Match 32-bit entry */
+	ld	r9,HSTATE_SCRATCH2(r13)
 	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 */
-- 
2.23.0

[PATCH v1 7/7] KVM: PPC: Book3S 64: Minimise hcall handler calling convention differences

[Nicholas Piggin]

This sets up the same calling convention from interrupt entry to
KVM interrupt handler for system calls as exists for other interrupt
types.

This is a better API, it uses a save area rather than SPR, and it has
more registers free to use. Using a single common API helps maintain
it, and it becomes easier to use in C in a later patch.

Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/exceptions-64s.S | 21 +++++++++-
 arch/powerpc/kvm/book3s_64_entry.S   | 61 ++++++++++++----------------
 2 files changed, 45 insertions(+), 37 deletions(-)

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index cd1731642b12..24c54b6fb3d7 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1892,8 +1892,27 @@ EXC_VIRT_END(system_call, 0x4c00, 0x100)
 
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 TRAMP_REAL_BEGIN(kvm_hcall)
+	std	r9,PACA_EXGEN+EX_R9(r13)
+	std	r11,PACA_EXGEN+EX_R11(r13)
+	std	r12,PACA_EXGEN+EX_R12(r13)
+	mfcr	r9
 	mfctr	r10
-	SET_SCRATCH0(r10) /* Save r13 in SCRATCH0 */
+	std	r10,PACA_EXGEN+EX_R13(r13)
+	li	r10,0
+	std	r10,PACA_EXGEN+EX_CFAR(r13)
+	std	r10,PACA_EXGEN+EX_CTR(r13)
+	 /*
+	  * Save the PPR (on systems that support it) before changing to
+	  * HMT_MEDIUM. That allows the KVM code to save that value into the
+	  * guest state (it is the guest's PPR value).
+	  */
+BEGIN_FTR_SECTION
+	mfspr	r10,SPRN_PPR
+	std	r10,PACA_EXGEN+EX_PPR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
+	HMT_MEDIUM
+
 #ifdef CONFIG_RELOCATABLE
 	/*
 	 * Requires __LOAD_FAR_HANDLER beause kvmppc_hcall lives
diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
index 66170ea85bc2..a01046202eef 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -11,40 +11,30 @@
  * These are branched to from interrupt handlers in exception-64s.S which set
  * IKVM_REAL or IKVM_VIRT, if HSTATE_IN_GUEST was found to be non-zero.
  */
+
+/*
+ * This is a hcall, so register convention is as
+ * Documentation/powerpc/papr_hcalls.rst.
+ *
+ * This may also be a syscall from PR-KVM userspace that is to be
+ * reflected to the PR guest kernel, so registers may be set up for
+ * a system call rather than hcall. We don't currently clobber
+ * anything here, but the 0xc00 handler has already clobbered CTR
+ * and CR0, so PR-KVM can not support a guest kernel that preserves
+ * those registers across its system calls.
+ *
+ * The state of registers is as kvmppc_interrupt, except CFAR is not
+ * saved, R13 is not in SCRATCH0, and R10 does not contain the trap.
+ */
 .global	kvmppc_hcall
 .balign IFETCH_ALIGN_BYTES
 kvmppc_hcall:
-	/*
-	 * This is a hcall, so register convention is as
-	 * Documentation/powerpc/papr_hcalls.rst, with these additions:
-	 * R13		= PACA
-	 * guest R13 saved in SPRN_SCRATCH0
-	 * R10		= free
-	 * guest r10 saved in PACA_EXGEN
-	 *
-	 * This may also be a syscall from PR-KVM userspace that is to be
-	 * reflected to the PR guest kernel, so registers may be set up for
-	 * a system call rather than hcall. We don't currently clobber
-	 * anything here, but the 0xc00 handler has already clobbered CTR
-	 * and CR0, so PR-KVM can not support a guest kernel that preserves
-	 * those registers across its system calls.
-	 */
-	 /*
-	  * Save the PPR (on systems that support it) before changing to
-	  * HMT_MEDIUM. That allows the KVM code to save that value into the
-	  * guest state (it is the guest's PPR value).
-	  */
-BEGIN_FTR_SECTION
-	mfspr	r10,SPRN_PPR
-	std	r10,HSTATE_PPR(r13)
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
-	HMT_MEDIUM
-	mfcr	r10
-	std	r12,HSTATE_SCRATCH0(r13)
-	sldi	r12,r10,32
-	ori	r12,r12,0xc00
-	ld	r10,PACA_EXGEN+EX_R10(r13)
-	b	do_kvm_interrupt
+	ld	r10,PACA_EXGEN+EX_R13(r13)
+	SET_SCRATCH0(r10)
+	li	r10,0xc00
+	/* Now we look like kvmppc_interrupt */
+	li	r11,PACA_EXGEN
+	b	.Lgot_save_area
 
 /*
  * KVM interrupt entry occurs after GEN_INT_ENTRY runs, and follows that
@@ -67,12 +57,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 kvmppc_interrupt:
 	li	r11,PACA_EXGEN
 	cmpdi	r10,0x200
-	bgt+	1f
+	bgt+	.Lgot_save_area
 	li	r11,PACA_EXMC
-	beq	1f
+	beq	.Lgot_save_area
 	li	r11,PACA_EXNMI
-1:	add	r11,r11,r13
-
+.Lgot_save_area:
+	add	r11,r11,r13
 BEGIN_FTR_SECTION
 	ld	r12,EX_CFAR(r11)
 	std	r12,HSTATE_CFAR(r13)
@@ -91,7 +81,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	ld	r10,EX_R10(r11)
 	ld	r11,EX_R11(r11)
 
-do_kvm_interrupt:
 	/*
 	 * Hcalls and other interrupts come here after normalising register
 	 * contents and save locations:
-- 
2.23.0

Re: [PATCH v1 5/7] KVM: PPC: Book3S 64: Move interrupt early register setup to KVM

[Fabiano Rosas]

Nicholas Piggin <npiggin@gmail.com> writes:

> Like the earlier patch for hcalls, KVM interrupt entry requires a
> different calling convention than the Linux interrupt handlers
> set up. Move the code that converts from one to the other into KVM.
>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>

Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>

> ---
>  arch/powerpc/kernel/exceptions-64s.S | 131 +++++----------------------
>  arch/powerpc/kvm/book3s_64_entry.S   |  50 +++++++++-
>  2 files changed, 71 insertions(+), 110 deletions(-)
>
> diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
> index 1bfd0d7af09e..cd1731642b12 100644
> --- a/arch/powerpc/kernel/exceptions-64s.S
> +++ b/arch/powerpc/kernel/exceptions-64s.S
> @@ -187,7 +187,6 @@ do_define_int n
>  	.endif
>  .endm
>
> -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
>  /*
>   * All interrupts which set HSRR registers, as well as SRESET and MCE and
>   * syscall when invoked with "sc 1" switch to MSR[HV]=1 (HVMODE) to be taken,
> @@ -220,54 +219,25 @@ do_define_int n
>   * to KVM to handle.
>   */
>
> -.macro KVMTEST name
> +.macro KVMTEST name handler
> +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
>  	lbz	r10,HSTATE_IN_GUEST(r13)
>  	cmpwi	r10,0
> -	bne	\name\()_kvm
> -.endm
> -
> -.macro GEN_KVM name
> -	.balign IFETCH_ALIGN_BYTES
> -\name\()_kvm:
> -
> -BEGIN_FTR_SECTION
> -	ld	r10,IAREA+EX_CFAR(r13)
> -	std	r10,HSTATE_CFAR(r13)
> -END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
> -
> -	ld	r10,IAREA+EX_CTR(r13)
> -	mtctr	r10
> -BEGIN_FTR_SECTION
> -	ld	r10,IAREA+EX_PPR(r13)
> -	std	r10,HSTATE_PPR(r13)
> -END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
> -	ld	r11,IAREA+EX_R11(r13)
> -	ld	r12,IAREA+EX_R12(r13)
> -	std	r12,HSTATE_SCRATCH0(r13)
> -	sldi	r12,r9,32
> -	ld	r9,IAREA+EX_R9(r13)
> -	ld	r10,IAREA+EX_R10(r13)
>  	/* HSRR variants have the 0x2 bit added to their trap number */
>  	.if IHSRR_IF_HVMODE
>  	BEGIN_FTR_SECTION
> -	ori	r12,r12,(IVEC + 0x2)
> +	li	r10,(IVEC + 0x2)
>  	FTR_SECTION_ELSE
> -	ori	r12,r12,(IVEC)
> +	li	r10,(IVEC)
>  	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
>  	.elseif IHSRR
> -	ori	r12,r12,(IVEC+ 0x2)
> +	li	r10,(IVEC + 0x2)
>  	.else
> -	ori	r12,r12,(IVEC)
> +	li	r10,(IVEC)
>  	.endif
> -	b	kvmppc_interrupt
> -.endm
> -
> -#else
> -.macro KVMTEST name
> -.endm
> -.macro GEN_KVM name
> -.endm
> +	bne	\handler
>  #endif
> +.endm
>
>  /*
>   * This is the BOOK3S interrupt entry code macro.
> @@ -409,7 +379,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
>  DEFINE_FIXED_SYMBOL(\name\()_common_real)
>  \name\()_common_real:
>  	.if IKVM_REAL
> -		KVMTEST \name
> +		KVMTEST \name kvm_interrupt
>  	.endif
>
>  	ld	r10,PACAKMSR(r13)	/* get MSR value for kernel */
> @@ -432,7 +402,7 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real)
>  DEFINE_FIXED_SYMBOL(\name\()_common_virt)
>  \name\()_common_virt:
>  	.if IKVM_VIRT
> -		KVMTEST \name
> +		KVMTEST \name kvm_interrupt
>  1:
>  	.endif
>  	.endif /* IVIRT */
> @@ -446,7 +416,7 @@ DEFINE_FIXED_SYMBOL(\name\()_common_virt)
>  DEFINE_FIXED_SYMBOL(\name\()_common_real)
>  \name\()_common_real:
>  	.if IKVM_REAL
> -		KVMTEST \name
> +		KVMTEST \name kvm_interrupt
>  	.endif
>  .endm
>
> @@ -967,8 +937,6 @@ EXC_COMMON_BEGIN(system_reset_common)
>  	EXCEPTION_RESTORE_REGS
>  	RFI_TO_USER_OR_KERNEL
>
> -	GEN_KVM system_reset
> -
>
>  /**
>   * Interrupt 0x200 - Machine Check Interrupt (MCE).
> @@ -1132,7 +1100,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
>  	/*
>  	 * Check if we are coming from guest. If yes, then run the normal
>  	 * exception handler which will take the
> -	 * machine_check_kvm->kvmppc_interrupt branch to deliver the MC event
> +	 * machine_check_kvm->kvm_interrupt branch to deliver the MC event
>  	 * to guest.
>  	 */
>  	lbz	r11,HSTATE_IN_GUEST(r13)
> @@ -1203,8 +1171,6 @@ EXC_COMMON_BEGIN(machine_check_common)
>  	bl	machine_check_exception
>  	b	interrupt_return
>
> -	GEN_KVM machine_check
> -
>
>  #ifdef CONFIG_PPC_P7_NAP
>  /*
> @@ -1339,8 +1305,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
>  	REST_NVGPRS(r1)
>  	b	interrupt_return
>
> -	GEN_KVM data_access
> -
>
>  /**
>   * Interrupt 0x380 - Data Segment Interrupt (DSLB).
> @@ -1390,8 +1354,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
>  	bl	do_bad_slb_fault
>  	b	interrupt_return
>
> -	GEN_KVM data_access_slb
> -
>
>  /**
>   * Interrupt 0x400 - Instruction Storage Interrupt (ISI).
> @@ -1428,8 +1390,6 @@ MMU_FTR_SECTION_ELSE
>  ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
>  	b	interrupt_return
>
> -	GEN_KVM instruction_access
> -
>
>  /**
>   * Interrupt 0x480 - Instruction Segment Interrupt (ISLB).
> @@ -1474,8 +1434,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
>  	bl	do_bad_slb_fault
>  	b	interrupt_return
>
> -	GEN_KVM instruction_access_slb
> -
>
>  /**
>   * Interrupt 0x500 - External Interrupt.
> @@ -1521,8 +1479,6 @@ EXC_COMMON_BEGIN(hardware_interrupt_common)
>  	bl	do_IRQ
>  	b	interrupt_return
>
> -	GEN_KVM hardware_interrupt
> -
>
>  /**
>   * Interrupt 0x600 - Alignment Interrupt
> @@ -1550,8 +1506,6 @@ EXC_COMMON_BEGIN(alignment_common)
>  	REST_NVGPRS(r1) /* instruction emulation may change GPRs */
>  	b	interrupt_return
>
> -	GEN_KVM alignment
> -
>
>  /**
>   * Interrupt 0x700 - Program Interrupt (program check).
> @@ -1659,8 +1613,6 @@ EXC_COMMON_BEGIN(program_check_common)
>  	REST_NVGPRS(r1) /* instruction emulation may change GPRs */
>  	b	interrupt_return
>
> -	GEN_KVM program_check
> -
>
>  /*
>   * Interrupt 0x800 - Floating-Point Unavailable Interrupt.
> @@ -1710,8 +1662,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
>  	b	interrupt_return
>  #endif
>
> -	GEN_KVM fp_unavailable
> -
>
>  /**
>   * Interrupt 0x900 - Decrementer Interrupt.
> @@ -1751,8 +1701,6 @@ EXC_COMMON_BEGIN(decrementer_common)
>  	bl	timer_interrupt
>  	b	interrupt_return
>
> -	GEN_KVM decrementer
> -
>
>  /**
>   * Interrupt 0x980 - Hypervisor Decrementer Interrupt.
> @@ -1798,8 +1746,6 @@ EXC_COMMON_BEGIN(hdecrementer_common)
>  	ld	r13,PACA_EXGEN+EX_R13(r13)
>  	HRFI_TO_KERNEL
>
> -	GEN_KVM hdecrementer
> -
>
>  /**
>   * Interrupt 0xa00 - Directed Privileged Doorbell Interrupt.
> @@ -1840,8 +1786,6 @@ EXC_COMMON_BEGIN(doorbell_super_common)
>  #endif
>  	b	interrupt_return
>
> -	GEN_KVM doorbell_super
> -
>
>  EXC_REAL_NONE(0xb00, 0x100)
>  EXC_VIRT_NONE(0x4b00, 0x100)
> @@ -1891,7 +1835,7 @@ INT_DEFINE_END(system_call)
>  	GET_PACA(r13)
>  	std	r10,PACA_EXGEN+EX_R10(r13)
>  	INTERRUPT_TO_KERNEL
> -	KVMTEST system_call /* uses r10, branch to system_call_kvm */
> +	KVMTEST system_call kvm_hcall /* uses r10, branch to kvm_hcall */
>  	mfctr	r9
>  #else
>  	mr	r9,r13
> @@ -1947,7 +1891,7 @@ EXC_VIRT_BEGIN(system_call, 0x4c00, 0x100)
>  EXC_VIRT_END(system_call, 0x4c00, 0x100)
>
>  #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
> -TRAMP_REAL_BEGIN(system_call_kvm)
> +TRAMP_REAL_BEGIN(kvm_hcall)
>  	mfctr	r10
>  	SET_SCRATCH0(r10) /* Save r13 in SCRATCH0 */
>  #ifdef CONFIG_RELOCATABLE
> @@ -1987,8 +1931,6 @@ EXC_COMMON_BEGIN(single_step_common)
>  	bl	single_step_exception
>  	b	interrupt_return
>
> -	GEN_KVM single_step
> -
>
>  /**
>   * Interrupt 0xe00 - Hypervisor Data Storage Interrupt (HDSI).
> @@ -2027,8 +1969,6 @@ MMU_FTR_SECTION_ELSE
>  ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX)
>  	b       interrupt_return
>
> -	GEN_KVM h_data_storage
> -
>
>  /**
>   * Interrupt 0xe20 - Hypervisor Instruction Storage Interrupt (HISI).
> @@ -2054,8 +1994,6 @@ EXC_COMMON_BEGIN(h_instr_storage_common)
>  	bl	unknown_exception
>  	b	interrupt_return
>
> -	GEN_KVM h_instr_storage
> -
>
>  /**
>   * Interrupt 0xe40 - Hypervisor Emulation Assistance Interrupt.
> @@ -2080,8 +2018,6 @@ EXC_COMMON_BEGIN(emulation_assist_common)
>  	REST_NVGPRS(r1) /* instruction emulation may change GPRs */
>  	b	interrupt_return
>
> -	GEN_KVM emulation_assist
> -
>
>  /**
>   * Interrupt 0xe60 - Hypervisor Maintenance Interrupt (HMI).
> @@ -2153,8 +2089,6 @@ EXC_COMMON_BEGIN(hmi_exception_early_common)
>  	EXCEPTION_RESTORE_REGS hsrr=1
>  	GEN_INT_ENTRY hmi_exception, virt=0
>
> -	GEN_KVM hmi_exception_early
> -
>  EXC_COMMON_BEGIN(hmi_exception_common)
>  	GEN_COMMON hmi_exception
>  	FINISH_NAP
> @@ -2162,8 +2096,6 @@ EXC_COMMON_BEGIN(hmi_exception_common)
>  	bl	handle_hmi_exception
>  	b	interrupt_return
>
> -	GEN_KVM hmi_exception
> -
>
>  /**
>   * Interrupt 0xe80 - Directed Hypervisor Doorbell Interrupt.
> @@ -2195,8 +2127,6 @@ EXC_COMMON_BEGIN(h_doorbell_common)
>  #endif
>  	b	interrupt_return
>
> -	GEN_KVM h_doorbell
> -
>
>  /**
>   * Interrupt 0xea0 - Hypervisor Virtualization Interrupt.
> @@ -2224,8 +2154,6 @@ EXC_COMMON_BEGIN(h_virt_irq_common)
>  	bl	do_IRQ
>  	b	interrupt_return
>
> -	GEN_KVM h_virt_irq
> -
>
>  EXC_REAL_NONE(0xec0, 0x20)
>  EXC_VIRT_NONE(0x4ec0, 0x20)
> @@ -2270,8 +2198,6 @@ EXC_COMMON_BEGIN(performance_monitor_common)
>  	bl	performance_monitor_exception
>  	b	interrupt_return
>
> -	GEN_KVM performance_monitor
> -
>
>  /**
>   * Interrupt 0xf20 - Vector Unavailable Interrupt.
> @@ -2321,8 +2247,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
>  	bl	altivec_unavailable_exception
>  	b	interrupt_return
>
> -	GEN_KVM altivec_unavailable
> -
>
>  /**
>   * Interrupt 0xf40 - VSX Unavailable Interrupt.
> @@ -2371,8 +2295,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
>  	bl	vsx_unavailable_exception
>  	b	interrupt_return
>
> -	GEN_KVM vsx_unavailable
> -
>
>  /**
>   * Interrupt 0xf60 - Facility Unavailable Interrupt.
> @@ -2401,8 +2323,6 @@ EXC_COMMON_BEGIN(facility_unavailable_common)
>  	REST_NVGPRS(r1) /* instruction emulation may change GPRs */
>  	b	interrupt_return
>
> -	GEN_KVM facility_unavailable
> -
>
>  /**
>   * Interrupt 0xf60 - Hypervisor Facility Unavailable Interrupt.
> @@ -2431,8 +2351,6 @@ EXC_COMMON_BEGIN(h_facility_unavailable_common)
>  	REST_NVGPRS(r1) /* XXX Shouldn't be necessary in practice */
>  	b	interrupt_return
>
> -	GEN_KVM h_facility_unavailable
> -
>
>  EXC_REAL_NONE(0xfa0, 0x20)
>  EXC_VIRT_NONE(0x4fa0, 0x20)
> @@ -2462,8 +2380,6 @@ EXC_COMMON_BEGIN(cbe_system_error_common)
>  	bl	cbe_system_error_exception
>  	b	interrupt_return
>
> -	GEN_KVM cbe_system_error
> -
>  #else /* CONFIG_CBE_RAS */
>  EXC_REAL_NONE(0x1200, 0x100)
>  EXC_VIRT_NONE(0x5200, 0x100)
> @@ -2495,8 +2411,6 @@ EXC_COMMON_BEGIN(instruction_breakpoint_common)
>  	bl	instruction_breakpoint_exception
>  	b	interrupt_return
>
> -	GEN_KVM instruction_breakpoint
> -
>
>  EXC_REAL_NONE(0x1400, 0x100)
>  EXC_VIRT_NONE(0x5400, 0x100)
> @@ -2617,8 +2531,6 @@ EXC_COMMON_BEGIN(denorm_exception_common)
>  	bl	unknown_exception
>  	b	interrupt_return
>
> -	GEN_KVM denorm_exception
> -
>
>  #ifdef CONFIG_CBE_RAS
>  INT_DEFINE_BEGIN(cbe_maintenance)
> @@ -2636,8 +2548,6 @@ EXC_COMMON_BEGIN(cbe_maintenance_common)
>  	bl	cbe_maintenance_exception
>  	b	interrupt_return
>
> -	GEN_KVM cbe_maintenance
> -
>  #else /* CONFIG_CBE_RAS */
>  EXC_REAL_NONE(0x1600, 0x100)
>  EXC_VIRT_NONE(0x5600, 0x100)
> @@ -2668,8 +2578,6 @@ EXC_COMMON_BEGIN(altivec_assist_common)
>  #endif
>  	b	interrupt_return
>
> -	GEN_KVM altivec_assist
> -
>
>  #ifdef CONFIG_CBE_RAS
>  INT_DEFINE_BEGIN(cbe_thermal)
> @@ -2687,8 +2595,6 @@ EXC_COMMON_BEGIN(cbe_thermal_common)
>  	bl	cbe_thermal_exception
>  	b	interrupt_return
>
> -	GEN_KVM cbe_thermal
> -
>  #else /* CONFIG_CBE_RAS */
>  EXC_REAL_NONE(0x1800, 0x100)
>  EXC_VIRT_NONE(0x5800, 0x100)
> @@ -2941,6 +2847,15 @@ TRAMP_REAL_BEGIN(rfscv_flush_fallback)
>
>  USE_TEXT_SECTION()
>
> +#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
> +kvm_interrupt:
> +	/*
> +	 * The conditional branch in KVMTEST can't reach all the way,
> +	 * make a stub.
> +	 */
> +	b	kvmppc_interrupt
> +#endif
> +
>  _GLOBAL(do_uaccess_flush)
>  	UACCESS_FLUSH_FIXUP_SECTION
>  	nop
> diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
> index f527e16707db..2c9d106145e8 100644
> --- a/arch/powerpc/kvm/book3s_64_entry.S
> +++ b/arch/powerpc/kvm/book3s_64_entry.S
> @@ -44,15 +44,61 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
>  	sldi	r12,r10,32
>  	ori	r12,r12,0xc00
>  	ld	r10,PACA_EXGEN+EX_R10(r13)
> +	b	do_kvm_interrupt
>
> +/*
> + * KVM interrupt entry occurs after GEN_INT_ENTRY runs, and follows that
> + * call convention:
> + *
> + * guest R9-R13, CTR, CFAR, PPR saved in PACA EX_xxx save area
> + * guest (H)DAR, (H)DSISR are also in the save area for relevant interrupts
> + * guest R13 also saved in SCRATCH0
> + * R13		= PACA
> + * R11		= (H)SRR0
> + * R12		= (H)SRR1
> + * R9		= guest CR
> + * PPR is set to medium
> + *
> + * With the addition for KVM:
> + * R10		= trap vector
> + */
>  .global	kvmppc_interrupt
>  .balign IFETCH_ALIGN_BYTES
>  kvmppc_interrupt:
> +	li	r11,PACA_EXGEN
> +	cmpdi	r10,0x200
> +	bgt+	1f
> +	li	r11,PACA_EXMC
> +	beq	1f
> +	li	r11,PACA_EXNMI
> +1:	add	r11,r11,r13
> +
> +BEGIN_FTR_SECTION
> +	ld	r12,EX_CFAR(r11)
> +	std	r12,HSTATE_CFAR(r13)
> +END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
> +	ld	r12,EX_CTR(r11)
> +	mtctr	r12
> +BEGIN_FTR_SECTION
> +	ld	r12,EX_PPR(r11)
> +	std	r12,HSTATE_PPR(r13)
> +END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
> +	ld	r12,EX_R12(r11)
> +	std	r12,HSTATE_SCRATCH0(r13)
> +	sldi	r12,r9,32
> +	or	r12,r12,r10
> +	ld	r9,EX_R9(r11)
> +	ld	r10,EX_R10(r11)
> +	ld	r11,EX_R11(r11)
> +
> +do_kvm_interrupt:
>  	/*
> -	 * Register contents:
> +	 * Hcalls and other interrupts come here after normalising register
> +	 * contents and save locations:
> +	 *
>  	 * R12		= (guest CR << 32) | interrupt vector
>  	 * R13		= PACA
> -	 * guest R12 saved in shadow VCPU SCRATCH0
> +	 * guest R12 saved in shadow HSTATE_SCRATCH0
>  	 * guest R13 saved in SPRN_SCRATCH0
>  	 */
>  	std	r9,HSTATE_SCRATCH2(r13)

Re: [PATCH v1 4/7] KVM: PPC: Book3S 64: Move hcall early register setup to KVM

[Fabiano Rosas]

Nicholas Piggin <npiggin@gmail.com> writes:

> System calls / hcalls have a different calling convention than
> other interrupts, so there is code in the KVMTEST to massage these
> into the same form as other interrupt handlers.
>
> Move this work into the KVM hcall handler. This means teaching KVM
> a little more about the low level interrupt handler setup, PACA save
> areas, etc., although that's not obviously worse than the current
> approach of coming up with an entirely different interrupt register
> / save convention.
>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>

Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>

> ---
>  arch/powerpc/include/asm/exception-64s.h | 13 ++++++++
>  arch/powerpc/kernel/exceptions-64s.S     | 42 +-----------------------
>  arch/powerpc/kvm/book3s_64_entry.S       | 30 +++++++++++++++++
>  3 files changed, 44 insertions(+), 41 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
> index c1a8aac01cf9..bb6f78fcf981 100644
> --- a/arch/powerpc/include/asm/exception-64s.h
> +++ b/arch/powerpc/include/asm/exception-64s.h
> @@ -35,6 +35,19 @@
>  /* PACA save area size in u64 units (exgen, exmc, etc) */
>  #define EX_SIZE		10
>
> +/* PACA save area offsets */
> +#define EX_R9		0
> +#define EX_R10		8
> +#define EX_R11		16
> +#define EX_R12		24
> +#define EX_R13		32
> +#define EX_DAR		40
> +#define EX_DSISR	48
> +#define EX_CCR		52
> +#define EX_CFAR		56
> +#define EX_PPR		64
> +#define EX_CTR		72
> +
>  /*
>   * maximum recursive depth of MCE exceptions
>   */
> diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
> index 9467fd1038f9..1bfd0d7af09e 100644
> --- a/arch/powerpc/kernel/exceptions-64s.S
> +++ b/arch/powerpc/kernel/exceptions-64s.S
> @@ -21,22 +21,6 @@
>  #include <asm/feature-fixups.h>
>  #include <asm/kup.h>
>
> -/* PACA save area offsets (exgen, exmc, etc) */
> -#define EX_R9		0
> -#define EX_R10		8
> -#define EX_R11		16
> -#define EX_R12		24
> -#define EX_R13		32
> -#define EX_DAR		40
> -#define EX_DSISR	48
> -#define EX_CCR		52
> -#define EX_CFAR		56
> -#define EX_PPR		64
> -#define EX_CTR		72
> -.if EX_SIZE != 10
> -	.error "EX_SIZE is wrong"
> -.endif
> -
>  /*
>   * Following are fixed section helper macros.
>   *
> @@ -1964,29 +1948,8 @@ EXC_VIRT_END(system_call, 0x4c00, 0x100)
>
>  #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
>  TRAMP_REAL_BEGIN(system_call_kvm)
> -	/*
> -	 * This is a hcall, so register convention is as above, with these
> -	 * differences:
> -	 * r13 = PACA
> -	 * ctr = orig r13
> -	 * orig r10 saved in PACA
> -	 */
> -	 /*
> -	  * Save the PPR (on systems that support it) before changing to
> -	  * HMT_MEDIUM. That allows the KVM code to save that value into the
> -	  * guest state (it is the guest's PPR value).
> -	  */
> -BEGIN_FTR_SECTION
> -	mfspr	r10,SPRN_PPR
> -	std	r10,HSTATE_PPR(r13)
> -END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
> -	HMT_MEDIUM
>  	mfctr	r10
> -	SET_SCRATCH0(r10)
> -	mfcr	r10
> -	std	r12,HSTATE_SCRATCH0(r13)
> -	sldi	r12,r10,32
> -	ori	r12,r12,0xc00
> +	SET_SCRATCH0(r10) /* Save r13 in SCRATCH0 */
>  #ifdef CONFIG_RELOCATABLE
>  	/*
>  	 * Requires __LOAD_FAR_HANDLER beause kvmppc_hcall lives
> @@ -1994,15 +1957,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
>  	 */
>  	__LOAD_FAR_HANDLER(r10, kvmppc_hcall)
>  	mtctr   r10
> -	ld	r10,PACA_EXGEN+EX_R10(r13)
>  	bctr
>  #else
> -	ld	r10,PACA_EXGEN+EX_R10(r13)
>  	b       kvmppc_hcall
>  #endif
>  #endif
>
> -
>  /**
>   * Interrupt 0xd00 - Trace Interrupt.
>   * This is a synchronous interrupt in response to instruction step or
> diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
> index c21fa64059ef..f527e16707db 100644
> --- a/arch/powerpc/kvm/book3s_64_entry.S
> +++ b/arch/powerpc/kvm/book3s_64_entry.S
> @@ -14,6 +14,36 @@
>  .global	kvmppc_hcall
>  .balign IFETCH_ALIGN_BYTES
>  kvmppc_hcall:
> +	/*
> +	 * This is a hcall, so register convention is as
> +	 * Documentation/powerpc/papr_hcalls.rst, with these additions:
> +	 * R13		= PACA
> +	 * guest R13 saved in SPRN_SCRATCH0
> +	 * R10		= free
> +	 * guest r10 saved in PACA_EXGEN
> +	 *
> +	 * This may also be a syscall from PR-KVM userspace that is to be
> +	 * reflected to the PR guest kernel, so registers may be set up for
> +	 * a system call rather than hcall. We don't currently clobber
> +	 * anything here, but the 0xc00 handler has already clobbered CTR
> +	 * and CR0, so PR-KVM can not support a guest kernel that preserves
> +	 * those registers across its system calls.
> +	 */
> +	 /*
> +	  * Save the PPR (on systems that support it) before changing to
> +	  * HMT_MEDIUM. That allows the KVM code to save that value into the
> +	  * guest state (it is the guest's PPR value).
> +	  */
> +BEGIN_FTR_SECTION
> +	mfspr	r10,SPRN_PPR
> +	std	r10,HSTATE_PPR(r13)
> +END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
> +	HMT_MEDIUM
> +	mfcr	r10
> +	std	r12,HSTATE_SCRATCH0(r13)
> +	sldi	r12,r10,32
> +	ori	r12,r12,0xc00
> +	ld	r10,PACA_EXGEN+EX_R10(r13)
>
>  .global	kvmppc_interrupt
>  .balign IFETCH_ALIGN_BYTES