[PATCH 00/13] KVM: PPC: Book3S: C-ify the P9 entry/exit code

[PATCH 00/13] KVM: PPC: Book3S: C-ify the P9 entry/exit code

[Nicholas Piggin]

This has a lot more implemented, things tidied up, and more things split
out. It's also implemented on top of powerpc next and kvm next which
have a few prerequisite patches (mainly removing EXSLB).

I've got a bunch more things after this including implementing HPT
guests with radix host in the "new" path -- whether we ever actually
want to do that, or port the legacy path up to C, or just leave it to
maintenance mode, I was just testing the waters there and making sure I
wasn't doing something fundamentally incompatible with hash.

I won't post anything further than this for now because I think it's a
good start and gets the total asm code for KVM entry and exit down to
about 160 lines plus the shim for the legacy paths. So would like to
concentrate on getting this in before juggling things around too much
or adding new things.

Thanks,
Nick

Nicholas Piggin (13):
  powerpc/64s: Remove KVM handler support from CBE_RAS interrupts
  powerpc/64s: remove KVM SKIP test from instruction breakpoint handler
  KVM: PPC: Book3S HV: Ensure MSR[ME] is always set in guest MSR
  KVM: PPC: Book3S 64: remove unused kvmppc_h_protect argument
  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 HV: Move hcall early register setup to KVM
  KVM: PPC: Book3S HV: Move interrupt early register setup to KVM
  KVM: PPC: Book3S HV: move bad_host_intr check to HV handler
  KVM: PPC: Book3S HV: Minimise hcall handler calling convention
    differences
  KVM: PPC: Book3S HV: Move radix MMU switching together in the P9 path
  KVM: PPC: Book3S HV: Implement the rest of the P9 entry/exit handling
    in C

 arch/powerpc/include/asm/asm-prototypes.h |   3 +-
 arch/powerpc/include/asm/exception-64s.h  |  13 +
 arch/powerpc/include/asm/kvm_asm.h        |   3 +-
 arch/powerpc/include/asm/kvm_book3s_64.h  |   2 +
 arch/powerpc/include/asm/kvm_ppc.h        |   5 +-
 arch/powerpc/kernel/exceptions-64s.S      | 257 +++----------------
 arch/powerpc/kernel/security.c            |   5 +-
 arch/powerpc/kvm/Makefile                 |   6 +
 arch/powerpc/kvm/book3s_64_entry.S        | 295 ++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv.c              |  69 +++--
 arch/powerpc/kvm/book3s_hv_builtin.c      |   7 +
 arch/powerpc/kvm/book3s_hv_interrupt.c    | 208 +++++++++++++++
 arch/powerpc/kvm/book3s_hv_rm_mmu.c       |   3 +-
 arch/powerpc/kvm/book3s_hv_rmhandlers.S   | 125 +--------
 arch/powerpc/kvm/book3s_segment.S         |   7 +
 arch/powerpc/kvm/book3s_xive.c            |  32 +++
 16 files changed, 670 insertions(+), 370 deletions(-)
 create mode 100644 arch/powerpc/kvm/book3s_64_entry.S
 create mode 100644 arch/powerpc/kvm/book3s_hv_interrupt.c

-- 
2.23.0

[PATCH 01/13] powerpc/64s: Remove KVM handler support from CBE_RAS interrupts

[Nicholas Piggin]

Cell does not support KVM.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/exceptions-64s.S | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 39cbea495154..5d0ad3b38e90 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -2574,8 +2574,6 @@ EXC_VIRT_NONE(0x5100, 0x100)
 INT_DEFINE_BEGIN(cbe_system_error)
 	IVEC=0x1200
 	IHSRR=1
-	IKVM_SKIP=1
-	IKVM_REAL=1
 INT_DEFINE_END(cbe_system_error)
 
 EXC_REAL_BEGIN(cbe_system_error, 0x1200, 0x100)
@@ -2745,8 +2743,6 @@ EXC_COMMON_BEGIN(denorm_exception_common)
 INT_DEFINE_BEGIN(cbe_maintenance)
 	IVEC=0x1600
 	IHSRR=1
-	IKVM_SKIP=1
-	IKVM_REAL=1
 INT_DEFINE_END(cbe_maintenance)
 
 EXC_REAL_BEGIN(cbe_maintenance, 0x1600, 0x100)
@@ -2798,8 +2794,6 @@ EXC_COMMON_BEGIN(altivec_assist_common)
 INT_DEFINE_BEGIN(cbe_thermal)
 	IVEC=0x1800
 	IHSRR=1
-	IKVM_SKIP=1
-	IKVM_REAL=1
 INT_DEFINE_END(cbe_thermal)
 
 EXC_REAL_BEGIN(cbe_thermal, 0x1800, 0x100)
-- 
2.23.0

Re: [PATCH 01/13] powerpc/64s: Remove KVM handler support from CBE_RAS interrupts

[Fabiano Rosas]

Nicholas Piggin <npiggin@gmail.com> writes:

> Cell does not support KVM.
>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>

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

> ---
>  arch/powerpc/kernel/exceptions-64s.S | 6 ------
>  1 file changed, 6 deletions(-)
>
> diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
> index 39cbea495154..5d0ad3b38e90 100644
> --- a/arch/powerpc/kernel/exceptions-64s.S
> +++ b/arch/powerpc/kernel/exceptions-64s.S
> @@ -2574,8 +2574,6 @@ EXC_VIRT_NONE(0x5100, 0x100)
>  INT_DEFINE_BEGIN(cbe_system_error)
>  	IVEC=0x1200
>  	IHSRR=1
> -	IKVM_SKIP=1
> -	IKVM_REAL=1
>  INT_DEFINE_END(cbe_system_error)
>
>  EXC_REAL_BEGIN(cbe_system_error, 0x1200, 0x100)
> @@ -2745,8 +2743,6 @@ EXC_COMMON_BEGIN(denorm_exception_common)
>  INT_DEFINE_BEGIN(cbe_maintenance)
>  	IVEC=0x1600
>  	IHSRR=1
> -	IKVM_SKIP=1
> -	IKVM_REAL=1
>  INT_DEFINE_END(cbe_maintenance)
>
>  EXC_REAL_BEGIN(cbe_maintenance, 0x1600, 0x100)
> @@ -2798,8 +2794,6 @@ EXC_COMMON_BEGIN(altivec_assist_common)
>  INT_DEFINE_BEGIN(cbe_thermal)
>  	IVEC=0x1800
>  	IHSRR=1
> -	IKVM_SKIP=1
> -	IKVM_REAL=1
>  INT_DEFINE_END(cbe_thermal)
>
>  EXC_REAL_BEGIN(cbe_thermal, 0x1800, 0x100)

[PATCH 02/13] powerpc/64s: remove KVM SKIP test from instruction breakpoint handler

[Nicholas Piggin]

The code being executed in KVM_GUEST_MODE_SKIP is hypervisor code with
MSR[IR]=0, so the faults of concern are the d-side ones caused by access
to guest context by the hypervisor.

Instruction breakpoint interrupts are not a concern here. It's unlikely
any good would come of causing breaks in this code, but skipping the
instruction that caused it won't help matters (e.g., skip the mtmsr that
sets MSR[DR]=0 or clears KVM_GUEST_MODE_SKIP).

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/exceptions-64s.S | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 5d0ad3b38e90..5bc689a546ae 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -2597,7 +2597,6 @@ EXC_VIRT_NONE(0x5200, 0x100)
 INT_DEFINE_BEGIN(instruction_breakpoint)
 	IVEC=0x1300
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
-	IKVM_SKIP=1
 	IKVM_REAL=1
 #endif
 INT_DEFINE_END(instruction_breakpoint)
-- 
2.23.0

Re: [PATCH 02/13] powerpc/64s: remove KVM SKIP test from instruction breakpoint handler

[Fabiano Rosas]

Nicholas Piggin <npiggin@gmail.com> writes:

> The code being executed in KVM_GUEST_MODE_SKIP is hypervisor code with
> MSR[IR]=0, so the faults of concern are the d-side ones caused by access
> to guest context by the hypervisor.
>
> Instruction breakpoint interrupts are not a concern here. It's unlikely
> any good would come of causing breaks in this code, but skipping the
> instruction that caused it won't help matters (e.g., skip the mtmsr that
> sets MSR[DR]=0 or clears KVM_GUEST_MODE_SKIP).
>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>

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

> ---
>  arch/powerpc/kernel/exceptions-64s.S | 1 -
>  1 file changed, 1 deletion(-)
>
> diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
> index 5d0ad3b38e90..5bc689a546ae 100644
> --- a/arch/powerpc/kernel/exceptions-64s.S
> +++ b/arch/powerpc/kernel/exceptions-64s.S
> @@ -2597,7 +2597,6 @@ EXC_VIRT_NONE(0x5200, 0x100)
>  INT_DEFINE_BEGIN(instruction_breakpoint)
>  	IVEC=0x1300
>  #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
> -	IKVM_SKIP=1
>  	IKVM_REAL=1
>  #endif
>  INT_DEFINE_END(instruction_breakpoint)

[PATCH 03/13] KVM: PPC: Book3S HV: Ensure MSR[ME] is always set in guest MSR

[Nicholas Piggin]

Rather than add the ME bit to the MSR when the guest is entered, make
it clear that the hypervisor does not allow the guest to clear the bit.

The ME addition is kept in the code for now, but a future patch will
warn if it's not present.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kvm/book3s_hv_builtin.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index dad118760a4e..ae8f291c5c48 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -661,6 +661,13 @@ static void kvmppc_end_cede(struct kvm_vcpu *vcpu)
 
 void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
 {
+	/*
+	 * Guest must always run with machine check interrupt
+	 * enabled.
+	 */
+	if (!(msr & MSR_ME))
+		msr |= MSR_ME;
+
 	/*
 	 * Check for illegal transactional state bit combination
 	 * and if we find it, force the TS field to a safe state.
-- 
2.23.0

Re: [PATCH 03/13] KVM: PPC: Book3S HV: Ensure MSR[ME] is always set in guest MSR

[Fabiano Rosas]

Nicholas Piggin <npiggin@gmail.com> writes:

> Rather than add the ME bit to the MSR when the guest is entered, make
> it clear that the hypervisor does not allow the guest to clear the bit.
>
> The ME addition is kept in the code for now, but a future patch will
> warn if it's not present.
>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>

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

> ---
>  arch/powerpc/kvm/book3s_hv_builtin.c | 7 +++++++
>  1 file changed, 7 insertions(+)
>
> diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
> index dad118760a4e..ae8f291c5c48 100644
> --- a/arch/powerpc/kvm/book3s_hv_builtin.c
> +++ b/arch/powerpc/kvm/book3s_hv_builtin.c
> @@ -661,6 +661,13 @@ static void kvmppc_end_cede(struct kvm_vcpu *vcpu)
>
>  void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
>  {
> +	/*
> +	 * Guest must always run with machine check interrupt
> +	 * enabled.
> +	 */
> +	if (!(msr & MSR_ME))
> +		msr |= MSR_ME;
> +
>  	/*
>  	 * Check for illegal transactional state bit combination
>  	 * and if we find it, force the TS field to a safe state.

[PATCH 04/13] KVM: PPC: Book3S 64: remove unused kvmppc_h_protect argument

[Nicholas Piggin]

The va argument is not used in the function or set by its asm caller,
so remove it to be safe.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/kvm_ppc.h  | 3 +--
 arch/powerpc/kvm/book3s_hv_rm_mmu.c | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 0a056c64c317..45b7610773b1 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -765,8 +765,7 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
                      unsigned long pte_index, unsigned long avpn);
 long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu);
 long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
-                      unsigned long pte_index, unsigned long avpn,
-                      unsigned long va);
+                      unsigned long pte_index, unsigned long avpn);
 long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
                    unsigned long pte_index);
 long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags,
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index f87237927096..956522b6ea15 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -667,8 +667,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 }
 
 long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
-		      unsigned long pte_index, unsigned long avpn,
-		      unsigned long va)
+		      unsigned long pte_index, unsigned long avpn)
 {
 	struct kvm *kvm = vcpu->kvm;
 	__be64 *hpte;
-- 
2.23.0

[PATCH 05/13] 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.

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      | 35 +++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 11 ++------
 4 files changed, 41 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 5bc689a546ae..a1640d6ea65d 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -212,7 +212,6 @@ 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,
@@ -242,13 +241,8 @@ 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..147ebf1c3c1f
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -0,0 +1,35 @@
+#include <asm/cache.h>
+#include <asm/ppc_asm.h>
+#include <asm/kvm_asm.h>
+#include <asm/reg.h>
+#include <asm/asm-offsets.h>
+#include <asm/kvm_book3s_asm.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 3988873b044c..bbf786a0c0d6 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1255,16 +1255,8 @@ 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)
@@ -3262,6 +3254,7 @@ 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 06/13] 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.

Also add a comment explaining why this this thing exists.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/exceptions-64s.S | 60 --------------------------
 arch/powerpc/kvm/book3s_64_entry.S   | 64 ++++++++++++++++++++++++----
 2 files changed, 56 insertions(+), 68 deletions(-)

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index a1640d6ea65d..96f22c582213 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 */
@@ -191,9 +190,6 @@ do_define_int n
 	.ifndef IMASK
 		IMASK=0
 	.endif
-	.ifndef IKVM_SKIP
-		IKVM_SKIP=0
-	.endif
 	.ifndef IKVM_REAL
 		IKVM_REAL=0
 	.endif
@@ -254,15 +250,10 @@ 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
@@ -289,27 +280,6 @@ 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
@@ -1128,7 +1098,6 @@ INT_DEFINE_BEGIN(machine_check)
 	ISET_RI=0
 	IDAR=1
 	IDSISR=1
-	IKVM_SKIP=1
 	IKVM_REAL=1
 INT_DEFINE_END(machine_check)
 
@@ -1419,7 +1388,6 @@ INT_DEFINE_BEGIN(data_access)
 	IVEC=0x300
 	IDAR=1
 	IDSISR=1
-	IKVM_SKIP=1
 	IKVM_REAL=1
 INT_DEFINE_END(data_access)
 
@@ -1465,7 +1433,6 @@ INT_DEFINE_BEGIN(data_access_slb)
 	IVEC=0x380
 	IRECONCILE=0
 	IDAR=1
-	IKVM_SKIP=1
 	IKVM_REAL=1
 INT_DEFINE_END(data_access_slb)
 
@@ -2111,7 +2078,6 @@ 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)
@@ -3088,32 +3054,6 @@ 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 147ebf1c3c1f..820d103e5f50 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -1,9 +1,10 @@
+#include <asm/asm-offsets.h>
 #include <asm/cache.h>
-#include <asm/ppc_asm.h>
+#include <asm/exception-64s.h>
 #include <asm/kvm_asm.h>
-#include <asm/reg.h>
-#include <asm/asm-offsets.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
@@ -19,17 +20,64 @@ kvmppc_interrupt:
 	 * guest R12 saved in shadow VCPU SCRATCH0
 	 * guest R13 saved in SPRN_SCRATCH0
 	 */
+	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
-	std	r9, HSTATE_SCRATCH2(r13)
-	lbz	r9, HSTATE_IN_GUEST(r13)
-	cmpwi	r9, KVM_GUEST_MODE_HOST_HV
+	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)
+	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
+
+/*
+ * KVM uses a trick where it is running in MSR[HV]=1 mode in real-mode with the
+ * guest MMU context loaded, and it sets KVM_GUEST_MODE_SKIP and enables
+ * 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 without walking page tables.
+ *
+ * However the guest context may not be able to translate, or it may cause a
+ * machine check or other issue, which will result in a fault in the host
+ * (even with KVM-HV).
+ *
+ * These faults are caught here and if the fault was (or was likely) due to
+ * that load, then we just return with the PC advanced +4 and skip the load,
+ * which then goes via the slow path.
+ */
+.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
+	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

Re: [PATCH 06/13] KVM: PPC: Book3S 64: Move GUEST_MODE_SKIP test into KVM

[Fabiano Rosas]

Nicholas Piggin <npiggin@gmail.com> writes:

> 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.
>
> Also add a comment explaining why this this thing exists.

this this

>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>

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

> ---
>  arch/powerpc/kernel/exceptions-64s.S | 60 --------------------------
>  arch/powerpc/kvm/book3s_64_entry.S   | 64 ++++++++++++++++++++++++----
>  2 files changed, 56 insertions(+), 68 deletions(-)
>
> diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
> index a1640d6ea65d..96f22c582213 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 */
> @@ -191,9 +190,6 @@ do_define_int n
>  	.ifndef IMASK
>  		IMASK=0
>  	.endif
> -	.ifndef IKVM_SKIP
> -		IKVM_SKIP=0
> -	.endif
>  	.ifndef IKVM_REAL
>  		IKVM_REAL=0
>  	.endif
> @@ -254,15 +250,10 @@ 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
> @@ -289,27 +280,6 @@ 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
> @@ -1128,7 +1098,6 @@ INT_DEFINE_BEGIN(machine_check)
>  	ISET_RI=0
>  	IDAR=1
>  	IDSISR=1
> -	IKVM_SKIP=1
>  	IKVM_REAL=1
>  INT_DEFINE_END(machine_check)
>
> @@ -1419,7 +1388,6 @@ INT_DEFINE_BEGIN(data_access)
>  	IVEC=0x300
>  	IDAR=1
>  	IDSISR=1
> -	IKVM_SKIP=1
>  	IKVM_REAL=1
>  INT_DEFINE_END(data_access)
>
> @@ -1465,7 +1433,6 @@ INT_DEFINE_BEGIN(data_access_slb)
>  	IVEC=0x380
>  	IRECONCILE=0
>  	IDAR=1
> -	IKVM_SKIP=1
>  	IKVM_REAL=1
>  INT_DEFINE_END(data_access_slb)
>
> @@ -2111,7 +2078,6 @@ 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)
> @@ -3088,32 +3054,6 @@ 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 147ebf1c3c1f..820d103e5f50 100644
> --- a/arch/powerpc/kvm/book3s_64_entry.S
> +++ b/arch/powerpc/kvm/book3s_64_entry.S
> @@ -1,9 +1,10 @@
> +#include <asm/asm-offsets.h>
>  #include <asm/cache.h>
> -#include <asm/ppc_asm.h>
> +#include <asm/exception-64s.h>
>  #include <asm/kvm_asm.h>
> -#include <asm/reg.h>
> -#include <asm/asm-offsets.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
> @@ -19,17 +20,64 @@ kvmppc_interrupt:
>  	 * guest R12 saved in shadow VCPU SCRATCH0
>  	 * guest R13 saved in SPRN_SCRATCH0
>  	 */
> +	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
> -	std	r9, HSTATE_SCRATCH2(r13)
> -	lbz	r9, HSTATE_IN_GUEST(r13)
> -	cmpwi	r9, KVM_GUEST_MODE_HOST_HV
> +	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)
> +	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
> +
> +/*
> + * KVM uses a trick where it is running in MSR[HV]=1 mode in real-mode with the
> + * guest MMU context loaded, and it sets KVM_GUEST_MODE_SKIP and enables
> + * 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 without walking page tables.
> + *
> + * However the guest context may not be able to translate, or it may cause a
> + * machine check or other issue, which will result in a fault in the host
> + * (even with KVM-HV).
> + *
> + * These faults are caught here and if the fault was (or was likely) due to
> + * that load, then we just return with the PC advanced +4 and skip the load,
> + * which then goes via the slow path.
> + */
> +.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
> +	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

[PATCH 07/13] 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: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/exceptions-64s.S | 4 ++--
 arch/powerpc/kvm/book3s_64_entry.S   | 6 +++++-
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 96f22c582213..a61a45704925 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -2023,13 +2023,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	 * Requires __LOAD_FAR_HANDLER beause kvmppc_interrupt 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 820d103e5f50..53addbbe7b1a 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -7,9 +7,13 @@
 #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 08/13] KVM: PPC: Book3S HV: 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     | 44 ++----------------------
 arch/powerpc/kvm/book3s_64_entry.S       | 17 +++++++++
 3 files changed, 32 insertions(+), 42 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 a61a45704925..6872f0376003 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.
  *
@@ -1995,45 +1979,21 @@ 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_interrupt lives
+	 * Requires __LOAD_FAR_HANDLER beause kvmppc_hcall lives
 	 * outside the head section.
 	 */
 	__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 53addbbe7b1a..7050197cd359 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -13,6 +13,23 @@
 .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
+	 */
+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 09/13] KVM: PPC: Book3S HV: 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 | 126 ++++-----------------------
 arch/powerpc/kvm/book3s_64_entry.S   |  34 +++++++-
 2 files changed, 50 insertions(+), 110 deletions(-)

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 6872f0376003..4878f05b5325 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -191,7 +191,6 @@ 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,
@@ -224,54 +223,25 @@ 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.
@@ -413,7 +383,7 @@ 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 */
@@ -436,7 +406,7 @@ 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 */
@@ -450,7 +420,7 @@ 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
 
@@ -1011,8 +981,6 @@ EXC_COMMON_BEGIN(system_reset_common)
 	EXCEPTION_RESTORE_REGS
 	RFI_TO_USER_OR_KERNEL
 
-	GEN_KVM system_reset
-
 
 /**
  * Interrupt 0x200 - Machine Check Interrupt (MCE).
@@ -1196,7 +1164,7 @@ 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)
@@ -1267,8 +1235,6 @@ EXC_COMMON_BEGIN(machine_check_common)
 	bl	machine_check_exception
 	b	interrupt_return
 
-	GEN_KVM machine_check
-
 
 #ifdef CONFIG_PPC_P7_NAP
 /*
@@ -1393,8 +1359,6 @@ MMU_FTR_SECTION_ELSE
 	b	handle_page_fault
 ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 
-	GEN_KVM data_access
-
 
 /**
  * Interrupt 0x380 - Data Segment Interrupt (DSLB).
@@ -1449,8 +1413,6 @@ 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).
@@ -1489,8 +1451,6 @@ MMU_FTR_SECTION_ELSE
 	b	handle_page_fault
 ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 
-	GEN_KVM instruction_access
-
 
 /**
  * Interrupt 0x480 - Instruction Segment Interrupt (ISLB).
@@ -1540,8 +1500,6 @@ 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.
@@ -1588,8 +1546,6 @@ EXC_COMMON_BEGIN(hardware_interrupt_common)
 	bl	do_IRQ
 	b	interrupt_return
 
-	GEN_KVM hardware_interrupt
-
 
 /**
  * Interrupt 0x600 - Alignment Interrupt
@@ -1617,8 +1573,6 @@ 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).
@@ -1681,8 +1635,6 @@ 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.
@@ -1735,8 +1687,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 	b	interrupt_return
 #endif
 
-	GEN_KVM fp_unavailable
-
 
 /**
  * Interrupt 0x900 - Decrementer Interrupt.
@@ -1777,8 +1727,6 @@ EXC_COMMON_BEGIN(decrementer_common)
 	bl	timer_interrupt
 	b	interrupt_return
 
-	GEN_KVM decrementer
-
 
 /**
  * Interrupt 0x980 - Hypervisor Decrementer Interrupt.
@@ -1825,8 +1773,6 @@ EXC_COMMON_BEGIN(hdecrementer_common)
 	ld	r13,PACA_EXGEN+EX_R13(r13)
 	HRFI_TO_KERNEL
 
-	GEN_KVM hdecrementer
-
 
 /**
  * Interrupt 0xa00 - Directed Privileged Doorbell Interrupt.
@@ -1868,8 +1814,6 @@ EXC_COMMON_BEGIN(doorbell_super_common)
 #endif
 	b	interrupt_return
 
-	GEN_KVM doorbell_super
-
 
 EXC_REAL_NONE(0xb00, 0x100)
 EXC_VIRT_NONE(0x4b00, 0x100)
@@ -1919,7 +1863,7 @@ 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
@@ -1978,7 +1922,7 @@ 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
@@ -2018,8 +1962,6 @@ EXC_COMMON_BEGIN(single_step_common)
 	bl	single_step_exception
 	b	interrupt_return
 
-	GEN_KVM single_step
-
 
 /**
  * Interrupt 0xe00 - Hypervisor Data Storage Interrupt (HDSI).
@@ -2060,8 +2002,6 @@ 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).
@@ -2087,8 +2027,6 @@ EXC_COMMON_BEGIN(h_instr_storage_common)
 	bl	unknown_exception
 	b	interrupt_return
 
-	GEN_KVM h_instr_storage
-
 
 /**
  * Interrupt 0xe40 - Hypervisor Emulation Assistance Interrupt.
@@ -2113,8 +2051,6 @@ 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).
@@ -2187,8 +2123,6 @@ 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
@@ -2197,8 +2131,6 @@ EXC_COMMON_BEGIN(hmi_exception_common)
 	bl	handle_hmi_exception
 	b	interrupt_return
 
-	GEN_KVM hmi_exception
-
 
 /**
  * Interrupt 0xe80 - Directed Hypervisor Doorbell Interrupt.
@@ -2231,8 +2163,6 @@ EXC_COMMON_BEGIN(h_doorbell_common)
 #endif
 	b	interrupt_return
 
-	GEN_KVM h_doorbell
-
 
 /**
  * Interrupt 0xea0 - Hypervisor Virtualization Interrupt.
@@ -2261,8 +2191,6 @@ 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)
@@ -2308,8 +2236,6 @@ EXC_COMMON_BEGIN(performance_monitor_common)
 	bl	performance_monitor_exception
 	b	interrupt_return
 
-	GEN_KVM performance_monitor
-
 
 /**
  * Interrupt 0xf20 - Vector Unavailable Interrupt.
@@ -2362,8 +2288,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	bl	altivec_unavailable_exception
 	b	interrupt_return
 
-	GEN_KVM altivec_unavailable
-
 
 /**
  * Interrupt 0xf40 - VSX Unavailable Interrupt.
@@ -2415,8 +2339,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	bl	vsx_unavailable_exception
 	b	interrupt_return
 
-	GEN_KVM vsx_unavailable
-
 
 /**
  * Interrupt 0xf60 - Facility Unavailable Interrupt.
@@ -2445,8 +2367,6 @@ 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.
@@ -2475,8 +2395,6 @@ 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)
@@ -2506,8 +2424,6 @@ 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)
@@ -2533,8 +2449,6 @@ 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)
@@ -2655,8 +2569,6 @@ 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)
@@ -2674,8 +2586,6 @@ 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)
@@ -2706,8 +2616,6 @@ EXC_COMMON_BEGIN(altivec_assist_common)
 #endif
 	b	interrupt_return
 
-	GEN_KVM altivec_assist
-
 
 #ifdef CONFIG_CBE_RAS
 INT_DEFINE_BEGIN(cbe_thermal)
@@ -2725,8 +2633,6 @@ 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)
@@ -2999,6 +2905,10 @@ TRAMP_REAL_BEGIN(rfscv_flush_fallback)
 
 USE_TEXT_SECTION()
 
+	/* conditional branch in KVMTEST can't reach all the way, make a stub */
+kvm_interrupt:
+	b	kvmppc_interrupt
+
 _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 7050197cd359..ef946e202773 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -30,15 +30,45 @@ 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
 
 .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 10/13] KVM: PPC: Book3S HV: move bad_host_intr check to HV handler

[Nicholas Piggin]

This is not used by PR KVM.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kvm/book3s_64_entry.S      | 3 ---
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 4 +++-
 arch/powerpc/kvm/book3s_segment.S       | 7 +++++++
 3 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
index ef946e202773..6b2fda5dee38 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -77,11 +77,8 @@ 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
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bbf786a0c0d6..eff4437e381c 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1251,6 +1251,7 @@ 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
@@ -1258,6 +1259,8 @@ 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)
 
@@ -3254,7 +3257,6 @@ 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..ef1d88b869bf 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -167,8 +167,15 @@ kvmppc_interrupt_pr:
 	 * R12             = (guest CR << 32) | exit handler id
 	 * R13             = PACA
 	 * HSTATE.SCRATCH0 = guest R12
+	 *
+	 * If HV is possible, additionally:
+	 * R9              = HSTATE_IN_GUEST
+	 * HSTATE.SCRATCH2 = guest R9
 	 */
 #ifdef CONFIG_PPC64
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	ld	r9,HSTATE_SCRATCH2(r13)
+#endif
 	/* 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 */
-- 
2.23.0

[PATCH 11/13] KVM: PPC: Book3S HV: 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.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/exceptions-64s.S | 16 +++++++++++++++-
 arch/powerpc/kvm/book3s_64_entry.S   | 22 +++-------------------
 2 files changed, 18 insertions(+), 20 deletions(-)

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 4878f05b5325..6f086ee922e0 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1923,8 +1923,22 @@ 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)
+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 6b2fda5dee38..6f06b58b1bdd 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -13,24 +13,9 @@
 .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
-	 */
-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
 
 .global	kvmppc_interrupt
 .balign IFETCH_ALIGN_BYTES
@@ -61,7 +46,6 @@ 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

[PATCH 12/13] KVM: PPC: Book3S HV: Move radix MMU switching together in the P9 path

[Nicholas Piggin]

Switching the MMU from radix<->radix mode is tricky particularly as the
MMU can remain enabled and requires a certain sequence of SPR updates.
Move these together into their own functions.

This also includes the radix TLB check / flush because it's tied in to
MMU switching due to tlbiel getting LPID from LPIDR.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kvm/book3s_hv.c | 50 +++++++++++++++++++++++-------------
 1 file changed, 32 insertions(+), 18 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 53d0cbfe5933..6bf7f5ce4865 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3446,12 +3446,38 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	trace_kvmppc_run_core(vc, 1);
 }
 
+static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpcr)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	struct kvm_nested_guest *nested = vcpu->arch.nested;
+	u32 lpid;
+
+	lpid = nested ? nested->shadow_lpid : kvm->arch.lpid;
+
+	mtspr(SPRN_LPID, lpid);
+	mtspr(SPRN_LPCR, lpcr);
+	mtspr(SPRN_PID, vcpu->arch.pid);
+	isync();
+
+	/* TLBIEL must have LPIDR set, so set guest LPID before flushing. */
+	kvmppc_check_need_tlb_flush(kvm, vc->pcpu, nested);
+}
+
+static void switch_mmu_to_host_radix(struct kvm *kvm, u32 pid)
+{
+	mtspr(SPRN_PID, pid);
+	mtspr(SPRN_LPID, kvm->arch.host_lpid);
+	mtspr(SPRN_LPCR, kvm->arch.host_lpcr);
+	isync();
+}
+
 /*
  * Load up hypervisor-mode registers on P9.
  */
 static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 				     unsigned long lpcr)
 {
+	struct kvm *kvm = vcpu->kvm;
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 	s64 hdec;
 	u64 tb, purr, spurr;
@@ -3467,12 +3493,12 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	 * P8 and P9 suppress the HDEC exception when LPCR[HDICE] = 0,
 	 * so set HDICE before writing HDEC.
 	 */
-	mtspr(SPRN_LPCR, vcpu->kvm->arch.host_lpcr | LPCR_HDICE);
+	mtspr(SPRN_LPCR, kvm->arch.host_lpcr | LPCR_HDICE);
 	isync();
 
 	hdec = time_limit - mftb();
 	if (hdec < 0) {
-		mtspr(SPRN_LPCR, vcpu->kvm->arch.host_lpcr);
+		mtspr(SPRN_LPCR, kvm->arch.host_lpcr);
 		isync();
 		return BOOK3S_INTERRUPT_HV_DECREMENTER;
 	}
@@ -3503,7 +3529,6 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	}
 	mtspr(SPRN_CIABR, vcpu->arch.ciabr);
 	mtspr(SPRN_IC, vcpu->arch.ic);
-	mtspr(SPRN_PID, vcpu->arch.pid);
 
 	mtspr(SPRN_PSSCR, vcpu->arch.psscr | PSSCR_EC |
 	      (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
@@ -3517,8 +3542,7 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	mtspr(SPRN_AMOR, ~0UL);
 
-	mtspr(SPRN_LPCR, lpcr);
-	isync();
+	switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
 
 	kvmppc_xive_push_vcpu(vcpu);
 
@@ -3553,7 +3577,6 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	mtspr(SPRN_CIABR, host_ciabr);
 	mtspr(SPRN_DAWR0, host_dawr);
 	mtspr(SPRN_DAWRX0, host_dawrx);
-	mtspr(SPRN_PID, host_pidr);
 
 	/*
 	 * Since this is radix, do a eieio; tlbsync; ptesync sequence in
@@ -3568,9 +3591,6 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	if (cpu_has_feature(CPU_FTR_ARCH_31))
 		asm volatile(PPC_CP_ABORT);
 
-	mtspr(SPRN_LPID, vcpu->kvm->arch.host_lpid);	/* restore host LPID */
-	isync();
-
 	vc->dpdes = mfspr(SPRN_DPDES);
 	vc->vtb = mfspr(SPRN_VTB);
 	mtspr(SPRN_DPDES, 0);
@@ -3587,7 +3607,8 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	}
 
 	mtspr(SPRN_HDEC, 0x7fffffff);
-	mtspr(SPRN_LPCR, vcpu->kvm->arch.host_lpcr);
+
+	switch_mmu_to_host_radix(kvm, host_pidr);
 
 	return trap;
 }
@@ -4117,7 +4138,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 {
 	struct kvm_run *run = vcpu->run;
 	int trap, r, pcpu;
-	int srcu_idx, lpid;
+	int srcu_idx;
 	struct kvmppc_vcore *vc;
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_nested_guest *nested = vcpu->arch.nested;
@@ -4191,13 +4212,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 	vc->vcore_state = VCORE_RUNNING;
 	trace_kvmppc_run_core(vc, 0);
 
-	if (cpu_has_feature(CPU_FTR_HVMODE)) {
-		lpid = nested ? nested->shadow_lpid : kvm->arch.lpid;
-		mtspr(SPRN_LPID, lpid);
-		isync();
-		kvmppc_check_need_tlb_flush(kvm, pcpu, nested);
-	}
-
 	guest_enter_irqoff();
 
 	srcu_idx = srcu_read_lock(&kvm->srcu);
-- 
2.23.0

Re: [PATCH 12/13] KVM: PPC: Book3S HV: Move radix MMU switching together in the P9 path

[Fabiano Rosas]

Nicholas Piggin <npiggin@gmail.com> writes:

> Switching the MMU from radix<->radix mode is tricky particularly as the
> MMU can remain enabled and requires a certain sequence of SPR updates.
> Move these together into their own functions.
>
> This also includes the radix TLB check / flush because it's tied in to
> MMU switching due to tlbiel getting LPID from LPIDR.
>
> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
> ---

<snip>

> @@ -4117,7 +4138,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
>  {
>  	struct kvm_run *run = vcpu->run;
>  	int trap, r, pcpu;
> -	int srcu_idx, lpid;
> +	int srcu_idx;
>  	struct kvmppc_vcore *vc;
>  	struct kvm *kvm = vcpu->kvm;
>  	struct kvm_nested_guest *nested = vcpu->arch.nested;
> @@ -4191,13 +4212,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
>  	vc->vcore_state = VCORE_RUNNING;
>  	trace_kvmppc_run_core(vc, 0);
>
> -	if (cpu_has_feature(CPU_FTR_HVMODE)) {
> -		lpid = nested ? nested->shadow_lpid : kvm->arch.lpid;
> -		mtspr(SPRN_LPID, lpid);
> -		isync();
> -		kvmppc_check_need_tlb_flush(kvm, pcpu, nested);
> -	}
> -

What about the counterpart to this^ down below?

	if (cpu_has_feature(CPU_FTR_HVMODE)) {
		mtspr(SPRN_LPID, kvm->arch.host_lpid);
		isync();
	}
        
>  	guest_enter_irqoff();
>
>  	srcu_idx = srcu_read_lock(&kvm->srcu);

Re: [PATCH 12/13] KVM: PPC: Book3S HV: Move radix MMU switching together in the P9 path

[Nicholas Piggin]

Excerpts from Fabiano Rosas's message of February 25, 2021 6:36 am:
> Nicholas Piggin <npiggin@gmail.com> writes:
> 
>> Switching the MMU from radix<->radix mode is tricky particularly as the
>> MMU can remain enabled and requires a certain sequence of SPR updates.
>> Move these together into their own functions.
>>
>> This also includes the radix TLB check / flush because it's tied in to
>> MMU switching due to tlbiel getting LPID from LPIDR.
>>
>> Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
>> ---
> 
> <snip>
> 
>> @@ -4117,7 +4138,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
>>  {
>>  	struct kvm_run *run = vcpu->run;
>>  	int trap, r, pcpu;
>> -	int srcu_idx, lpid;
>> +	int srcu_idx;
>>  	struct kvmppc_vcore *vc;
>>  	struct kvm *kvm = vcpu->kvm;
>>  	struct kvm_nested_guest *nested = vcpu->arch.nested;
>> @@ -4191,13 +4212,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
>>  	vc->vcore_state = VCORE_RUNNING;
>>  	trace_kvmppc_run_core(vc, 0);
>>
>> -	if (cpu_has_feature(CPU_FTR_HVMODE)) {
>> -		lpid = nested ? nested->shadow_lpid : kvm->arch.lpid;
>> -		mtspr(SPRN_LPID, lpid);
>> -		isync();
>> -		kvmppc_check_need_tlb_flush(kvm, pcpu, nested);
>> -	}
>> -
> 
> What about the counterpart to this^ down below?
> 
> 	if (cpu_has_feature(CPU_FTR_HVMODE)) {
> 		mtspr(SPRN_LPID, kvm->arch.host_lpid);
> 		isync();
> 	}

Good catch, you're right that can be removed too.

Thanks,
Nick

[PATCH 13/13] KVM: PPC: Book3S HV: Implement the rest of the P9 entry/exit handling in C

[Nicholas Piggin]

Almost all logic is moved to C, by introducing a new in_guest mode that
selects and branches very early in the interrupt handler to the P9 exit
code.

The remaining assembly is only about 160 lines of low level stack setup,
with VCPU vs host register save and restore, plus a small shim to the
legacy paths in the interrupt handler.

There are two motivations for this, the first is just make the code more
maintainable being in C. The second is to reduce the amount of code
running in a special KVM mode, "realmode". I put that in quotes because
with radix it is no longer necessarily real-mode in the MMU, but it
still has to be treated specially because it may be in real-mode, and
has various important registers like PID, DEC, TB, etc set to guest.
This is hostile to the rest of Linux and can't use arbitrary kernel
functionality or be instrumented well.

This initial patch is a reasonably faithful conversion of the asm code,
one notable difference being no real-mode hcall handler which necessitates
a small change to the H_CEDE call (although that makes it nicely common
with the nested HV case).

This also lacks any loop to return quickly back into the guest without
switching out of realmode in the case of unimportant or easily handled
interrupts.

The point was to reduce complexity and improve the ability to instrument
things, and it actually remains to be seen whether these short cuts are
required for modern processors. Radix, independent threads, XIVE, large
decrementer etc should all combine to vastly reduce guest exit frequency
compared with a POWER8. And radix mode additionally makes such exits
less costly by avoiding the need to flush and reload the SLB, flush
ERATs, etc.

Some of these things may be re-added if performance requires, or if more
of the other paths begin to be converted into C as well.

not-yet-Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/include/asm/asm-prototypes.h |   3 +-
 arch/powerpc/include/asm/kvm_asm.h        |   3 +-
 arch/powerpc/include/asm/kvm_book3s_64.h  |   2 +
 arch/powerpc/include/asm/kvm_ppc.h        |   2 +
 arch/powerpc/kernel/security.c            |   5 +-
 arch/powerpc/kvm/Makefile                 |   3 +
 arch/powerpc/kvm/book3s_64_entry.S        | 180 +++++++++++++++++++
 arch/powerpc/kvm/book3s_hv.c              |  19 +-
 arch/powerpc/kvm/book3s_hv_interrupt.c    | 208 ++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv_rmhandlers.S   | 112 +-----------
 arch/powerpc/kvm/book3s_xive.c            |  32 ++++
 11 files changed, 453 insertions(+), 116 deletions(-)
 create mode 100644 arch/powerpc/kvm/book3s_hv_interrupt.c

diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index d0b832cbbec8..00eb5224019c 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -151,6 +151,7 @@ extern s32 patch__call_flush_branch_caches3;
 extern s32 patch__flush_count_cache_return;
 extern s32 patch__flush_link_stack_return;
 extern s32 patch__call_kvm_flush_link_stack;
+extern s32 patch__call_kvm_flush_link_stack_2;
 extern s32 patch__memset_nocache, patch__memcpy_nocache;
 
 extern long flush_branch_caches;
@@ -171,7 +172,7 @@ void kvmhv_load_host_pmu(void);
 void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use);
 void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu);
 
-int __kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu);
+void kvmppc_p9_enter_guest(struct kvm_vcpu *vcpu);
 
 long kvmppc_h_set_dabr(struct kvm_vcpu *vcpu, unsigned long dabr);
 long kvmppc_h_set_xdabr(struct kvm_vcpu *vcpu, unsigned long dabr,
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index a3633560493b..b4f9996bd331 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -146,7 +146,8 @@
 #define KVM_GUEST_MODE_GUEST	1
 #define KVM_GUEST_MODE_SKIP	2
 #define KVM_GUEST_MODE_GUEST_HV	3
-#define KVM_GUEST_MODE_HOST_HV	4
+#define KVM_GUEST_MODE_GUEST_HV_FAST	4 /* ISA v3.0 with host radix mode */
+#define KVM_GUEST_MODE_HOST_HV	5
 
 #define KVM_INST_FETCH_FAILED	-1
 
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 9bb9bb370b53..7f08f6ed73df 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -153,6 +153,8 @@ static inline bool kvmhv_vcpu_is_radix(struct kvm_vcpu *vcpu)
 	return radix;
 }
 
+int __kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu);
+
 #define KVM_DEFAULT_HPT_ORDER	24	/* 16MB HPT by default */
 #endif
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 45b7610773b1..013e9d8b0754 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -670,6 +670,7 @@ extern int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval);
 extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
 			       int level, bool line_status);
 extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu);
+extern void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu);
 
 static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
 {
@@ -710,6 +711,7 @@ static inline int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval) { retur
 static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
 				      int level, bool line_status) { return -ENODEV; }
 static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { }
+static inline void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu) { }
 
 static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
 	{ return 0; }
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index e4e1a94ccf6a..6c37aeed0650 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -430,16 +430,19 @@ device_initcall(stf_barrier_debugfs_init);
 
 static void update_branch_cache_flush(void)
 {
-	u32 *site;
+	u32 *site, __maybe_unused *site2;
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	site = &patch__call_kvm_flush_link_stack;
+	site2 = &patch__call_kvm_flush_link_stack_2;
 	// This controls the branch from guest_exit_cont to kvm_flush_link_stack
 	if (link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) {
 		patch_instruction_site(site, ppc_inst(PPC_INST_NOP));
+		patch_instruction_site(site2, ppc_inst(PPC_INST_NOP));
 	} else {
 		// Could use HW flush, but that could also flush count cache
 		patch_branch_site(site, (u64)&kvm_flush_link_stack, BRANCH_SET_LINK);
+		patch_branch_site(site2, (u64)&kvm_flush_link_stack, BRANCH_SET_LINK);
 	}
 #endif
 
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index cdd119028f64..b94be8c9bad1 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -43,6 +43,9 @@ kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs)
 kvm-book3s_64-builtin-objs-$(CONFIG_SPAPR_TCE_IOMMU) := \
 	book3s_64_vio_hv.o
 
+kvm-book3s_64-objs-y += \
+	book3s_hv_interrupt.o
+
 kvm-pr-y := \
 	fpu.o \
 	emulate.o \
diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
index 6f06b58b1bdd..5fb605dc457c 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -1,10 +1,13 @@
 #include <asm/asm-offsets.h>
 #include <asm/cache.h>
+#include <asm/code-patching-asm.h>
 #include <asm/exception-64s.h>
+#include <asm/export.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_book3s_asm.h>
 #include <asm/ppc_asm.h>
 #include <asm/reg.h>
+#include <asm/ultravisor-api.h>
 
 /*
  * These are branched to from interrupt handlers in exception-64s.S which set
@@ -13,13 +16,24 @@
 .global	kvmppc_hcall
 .balign IFETCH_ALIGN_BYTES
 kvmppc_hcall:
+	lbz	r10,HSTATE_IN_GUEST(r13)
+	cmpwi	r10,KVM_GUEST_MODE_GUEST_HV_FAST
+	beq	kvmppc_p9_exit_hcall
 	ld	r10,PACA_EXGEN+EX_R13(r13)
 	SET_SCRATCH0(r10)
 	li	r10,0xc00
+	li	r11,PACA_EXGEN
+	b	1f
 
 .global	kvmppc_interrupt
 .balign IFETCH_ALIGN_BYTES
 kvmppc_interrupt:
+	std	r10,HSTATE_SCRATCH0(r13)
+	lbz	r10,HSTATE_IN_GUEST(r13)
+	cmpwi	r10,KVM_GUEST_MODE_GUEST_HV_FAST
+	beq	kvmppc_p9_exit_interrupt
+	ld	r10,HSTATE_SCRATCH0(r13)
+	lbz	r11,HSTATE_IN_GUEST(r13)
 	li	r11,PACA_EXGEN
 	cmpdi	r10,0x200
 	bgt+	1f
@@ -113,3 +127,169 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	GET_SCRATCH0(r13)
 	HRFI_TO_KERNEL
 #endif
+
+/* Stack frame offsets for kvmppc_hv_entry */
+#define SFS			208
+#define STACK_SLOT_VCPU		(SFS-8)
+#define STACK_SLOT_NVGPRS	(SFS-152)	/* 18 gprs */
+
+/*
+ * void kvmppc_p9_enter_guest(struct vcpu *vcpu);
+ *
+ * Enter the guest on a ISAv3.0 or later system where we have exactly
+ * one vcpu per vcore, and both the host and guest are radix, and threads
+ * are set to "indepdent mode".
+ */
+.balign	IFETCH_ALIGN_BYTES
+_GLOBAL(kvmppc_p9_enter_guest)
+EXPORT_SYMBOL_GPL(kvmppc_p9_enter_guest)
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+	stdu	r1, -SFS(r1)
+
+	std	r1, HSTATE_HOST_R1(r13)
+	std	r3, STACK_SLOT_VCPU(r1)
+
+	mfcr	r4
+	stw	r4, SFS+8(r1)
+
+	reg = 14
+	.rept	18
+	std	reg, STACK_SLOT_NVGPRS + ((reg - 14) * 8)(r1)
+	reg = reg + 1
+	.endr
+
+	ld	r4,VCPU_LR(r3)
+	mtlr	r4
+	ld	r4,VCPU_CTR(r3)
+	mtctr	r4
+	ld	r4,VCPU_XER(r3)
+	mtspr	SPRN_XER,r4
+
+	ld	r1,VCPU_CR(r3)
+
+BEGIN_FTR_SECTION
+	ld	r4,VCPU_CFAR(r3)
+	mtspr	SPRN_CFAR,r4
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+BEGIN_FTR_SECTION
+	ld	r4,VCPU_PPR(r3)
+	mtspr	SPRN_PPR,r4
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
+	reg = 4
+	.rept	28
+	ld	reg, __VCPU_GPR(reg)(r3)
+	reg = reg + 1
+	.endr
+
+	ld	r4,VCPU_KVM(r3)
+	lbz	r4,KVM_SECURE_GUEST(r4)
+	cmpdi	r4,0
+	ld	r4,VCPU_GPR(R4)(r3)
+	bne	.Lret_to_ultra
+
+	mtcr	r1
+
+	ld	r0,VCPU_GPR(R0)(r3)
+	ld	r1,VCPU_GPR(R1)(r3)
+	ld	r2,VCPU_GPR(R2)(r3)
+	ld	r3,VCPU_GPR(R3)(r3)
+
+	HRFI_TO_GUEST
+	b	.
+
+	/*
+	 * Use UV_RETURN ultracall to return control back to the Ultravisor
+	 * after processing an hypercall or interrupt that was forwarded
+	 * (a.k.a. reflected) to the Hypervisor.
+	 *
+	 * All registers have already been reloaded except the ucall requires:
+	 *   R0 = hcall result
+	 *   R2 = SRR1, so UV can detect a synthesized interrupt (if any)
+	 *   R3 = UV_RETURN
+	 */
+.Lret_to_ultra:
+	mtcr	r1
+	ld	r1,VCPU_GPR(R1)(r3)
+
+	ld	r0,VCPU_GPR(R3)(r3)
+	mfspr	r2,SPRN_SRR1
+	LOAD_REG_IMMEDIATE(r3, UV_RETURN)
+	sc	2
+
+/*
+ * kvmppc_p9_exit_hcall and kvmppc_p9_exit_interrupt are branched to from
+ * above if the interrupt was taken for a guest that was entered via
+ * kvmppc_p9_enter_guest().
+ *
+ * This code recovers the host stack and vcpu pointer, saves all GPRs and
+ * CR, LR, CTR, XER as well as guest MSR and NIA into the VCPU, then re-
+ * establishes the host stack and registers to return from  the
+ * kvmppc_p9_enter_guest() function.
+ */
+.balign	IFETCH_ALIGN_BYTES
+kvmppc_p9_exit_hcall:
+	mfspr	r11,SPRN_SRR0
+	mfspr	r12,SPRN_SRR1
+	li	r10,0xc00
+	std	r10,HSTATE_SCRATCH0(r13)
+
+.balign	IFETCH_ALIGN_BYTES
+kvmppc_p9_exit_interrupt:
+	std     r1,HSTATE_SCRATCH1(r13)
+	std     r3,HSTATE_SCRATCH2(r13)
+	ld	r1,HSTATE_HOST_R1(r13)
+	ld	r3, STACK_SLOT_VCPU(r1)
+
+	std	r9,VCPU_CR(r3)
+
+1:
+	std	r11,VCPU_PC(r3)
+	std	r12,VCPU_MSR(r3)
+
+	reg = 14
+	.rept	18
+	std	reg,__VCPU_GPR(reg)(r3)
+	reg = reg + 1
+	.endr
+
+	/* r1, r3, r9-r13 are saved to vcpu by C code */
+	std	r0,VCPU_GPR(R0)(r3)
+	std	r2,VCPU_GPR(R2)(r3)
+	reg = 4
+	.rept	5
+	std	reg,__VCPU_GPR(reg)(r3)
+	reg = reg + 1
+	.endr
+
+	ld	r2,PACATOC(r13)
+
+	mflr	r4
+	std	r4,VCPU_LR(r3)
+	mfspr	r4,SPRN_XER
+	std	r4,VCPU_XER(r3)
+
+	reg = 14
+	.rept	18
+	ld	reg, STACK_SLOT_NVGPRS + ((reg - 14) * 8)(r1)
+	reg = reg + 1
+	.endr
+
+	lwz	r4, SFS+8(r1)
+	mtcr	r4
+
+	/*
+	 * Flush the link stack here, before executing the first blr on the
+	 * way out of the guest.
+	 *
+	 * The link stack won't match coming out of the guest anyway so the
+	 * only cost is the flush itself. The call clobbers r0.
+	 */
+1:	nop
+	patch_site 1b patch__call_kvm_flush_link_stack_2
+
+	addi	r1, r1, SFS
+	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
+	blr
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6bf7f5ce4865..a2eafc207407 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1127,7 +1127,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
  * This has to be done early, not in kvmppc_pseries_do_hcall(), so
  * that the cede logic in kvmppc_run_single_vcpu() works properly.
  */
-static void kvmppc_nested_cede(struct kvm_vcpu *vcpu)
+static void kvmppc_cede(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.shregs.msr |= MSR_EE;
 	vcpu->arch.ceded = 1;
@@ -3719,18 +3719,18 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 		vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR);
 		vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR);
 		mtspr(SPRN_PSSCR_PR, host_psscr);
-
-		/* H_CEDE has to be handled now, not later */
-		if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested &&
-		    kvmppc_get_gpr(vcpu, 3) == H_CEDE) {
-			kvmppc_nested_cede(vcpu);
-			kvmppc_set_gpr(vcpu, 3, 0);
-			trap = 0;
-		}
 	} else {
 		trap = kvmhv_load_hv_regs_and_go(vcpu, time_limit, lpcr);
 	}
 
+	/* H_CEDE has to be handled now, not later */
+	if (trap == BOOK3S_INTERRUPT_SYSCALL &&
+	    kvmppc_get_gpr(vcpu, 3) == H_CEDE) {
+		kvmppc_cede(vcpu);
+		kvmppc_set_gpr(vcpu, 3, 0);
+		trap = 0;
+	}
+
 	vcpu->arch.slb_max = 0;
 	dec = mfspr(SPRN_DEC);
 	if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */
@@ -4396,6 +4396,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
 			r = kvmppc_pseries_do_hcall(vcpu);
 			trace_kvm_hcall_exit(vcpu, r);
 			kvmppc_core_prepare_to_enter(vcpu);
+			/* XXX: reflect sc 1 from PR=1 as a syscall to guest? */
 		} else if (r == RESUME_PAGE_FAULT) {
 			srcu_idx = srcu_read_lock(&kvm->srcu);
 			r = kvmppc_book3s_hv_page_fault(vcpu,
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
new file mode 100644
index 000000000000..8623fc927ed3
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -0,0 +1,208 @@
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <asm/asm-prototypes.h>
+#include <asm/dbell.h>
+#include <asm/kvm_ppc.h>
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+static void __start_timing(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	u64 tb = mftb() - vc->tb_offset_applied;
+
+	vcpu->arch.cur_activity = next;
+	vcpu->arch.cur_tb_start = tb;
+}
+
+static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	struct kvmhv_tb_accumulator *curr;
+	u64 tb = mftb() - vc->tb_offset_applied;
+	u64 prev_tb;
+	u64 delta;
+	u64 seq;
+
+	curr = vcpu->arch.cur_activity;
+	vcpu->arch.cur_activity = next;
+	prev_tb = vcpu->arch.cur_tb_start;
+	vcpu->arch.cur_tb_start = tb;
+
+	if (!curr)
+		return;
+
+	delta = tb - prev_tb;
+
+	seq = curr->seqcount;
+	curr->seqcount = seq + 1;
+	smp_wmb();
+	curr->tb_total += delta;
+	if (seq == 0 || delta < curr->tb_min)
+		curr->tb_min = delta;
+	if (delta > curr->tb_max)
+		curr->tb_max = delta;
+	smp_wmb();
+	curr->seqcount = seq + 2;
+}
+
+#define start_timing(vcpu, next) __start_timing(vcpu, next)
+#define end_timing(vcpu) __start_timing(vcpu, NULL)
+#define accumulate_time(vcpu, next) __accumulate_time(vcpu, next)
+#else
+#define start_timing(vcpu, next) do {} while (0)
+#define end_timing(vcpu) do {} while (0)
+#define accumulate_time(vcpu, next) do {} while (0)
+#endif
+
+static inline void mfslb(unsigned int idx, u64 *slbee, u64 *slbev)
+{
+	asm volatile("slbmfev  %0,%1" : "=r" (*slbev) : "r" (idx));
+	asm volatile("slbmfee  %0,%1" : "=r" (*slbee) : "r" (idx));
+}
+
+static inline void mtslb(unsigned int idx, u64 slbee, u64 slbev)
+{
+	BUG_ON((slbee & 0xfff) != idx);
+
+	asm volatile("slbmte %0,%1" :: "r" (slbev), "r" (slbee));
+}
+
+static inline void slb_invalidate(unsigned int ih)
+{
+	asm volatile("slbia %0" :: "i"(ih));
+}
+
+/*
+ * Malicious or buggy radix guests may have inserted SLB entries
+ * (only 0..3 because radix always runs with UPRT=1), so these must
+ * be cleared here to avoid side-channels. slbmte is used rather
+ * than slbia, as it won't clear cached translations.
+ */
+static void radix_clear_slb(void)
+{
+	u64 slbee, slbev;
+	int i;
+
+	for (i = 0; i < 4; i++) {
+		mfslb(i, &slbee, &slbev);
+		if (unlikely(slbee || slbev)) {
+			slbee = i;
+			slbev = 0;
+			mtslb(i, slbee, slbev);
+		}
+	}
+}
+
+int __kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu)
+{
+	u64 *exsave;
+	unsigned long msr = mfmsr();
+	int trap;
+
+	start_timing(vcpu, &vcpu->arch.rm_entry);
+
+	vcpu->arch.ceded = 0;
+
+	WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_HV);
+	WARN_ON_ONCE(!(vcpu->arch.shregs.msr & MSR_ME));
+
+	mtspr(SPRN_HSRR0, vcpu->arch.regs.nip);
+	mtspr(SPRN_HSRR1, (vcpu->arch.shregs.msr & ~MSR_HV) | MSR_ME);
+
+	accumulate_time(vcpu, &vcpu->arch.guest_time);
+
+	local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_GUEST_HV_FAST;
+	kvmppc_p9_enter_guest(vcpu);
+	// Radix host and guest means host never runs with guest MMU state
+	local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_NONE;
+
+	accumulate_time(vcpu, &vcpu->arch.rm_intr);
+
+	/* Get these from r11/12 and paca exsave */
+	vcpu->arch.shregs.srr0 = mfspr(SPRN_SRR0);
+	vcpu->arch.shregs.srr1 = mfspr(SPRN_SRR1);
+	vcpu->arch.shregs.dar = mfspr(SPRN_DAR);
+	vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR);
+
+	trap = local_paca->kvm_hstate.scratch0 & ~0x2;
+	if (likely(trap > BOOK3S_INTERRUPT_MACHINE_CHECK)) {
+		exsave = local_paca->exgen;
+	} else if (trap == BOOK3S_INTERRUPT_SYSTEM_RESET) {
+		exsave = local_paca->exnmi;
+	} else { /* trap == 0x200 */
+		exsave = local_paca->exmc;
+	}
+
+	vcpu->arch.regs.gpr[1] = local_paca->kvm_hstate.scratch1;
+	vcpu->arch.regs.gpr[3] = local_paca->kvm_hstate.scratch2;
+	vcpu->arch.regs.gpr[9] = exsave[EX_R9/sizeof(u64)];
+	vcpu->arch.regs.gpr[10] = exsave[EX_R10/sizeof(u64)];
+	vcpu->arch.regs.gpr[11] = exsave[EX_R11/sizeof(u64)];
+	vcpu->arch.regs.gpr[12] = exsave[EX_R12/sizeof(u64)];
+	vcpu->arch.regs.gpr[13] = exsave[EX_R13/sizeof(u64)];
+	vcpu->arch.ppr = exsave[EX_PPR/sizeof(u64)];
+	vcpu->arch.cfar = exsave[EX_CFAR/sizeof(u64)];
+	vcpu->arch.regs.ctr = exsave[EX_CTR/sizeof(u64)];
+
+	vcpu->arch.last_inst = KVM_INST_FETCH_FAILED;
+
+	if (unlikely(trap == BOOK3S_INTERRUPT_MACHINE_CHECK)) {
+		vcpu->arch.fault_dar = exsave[EX_DAR/sizeof(u64)];
+		vcpu->arch.fault_dsisr = exsave[EX_DSISR/sizeof(u64)];
+		kvmppc_realmode_machine_check(vcpu);
+
+	} else if (unlikely(trap == BOOK3S_INTERRUPT_HMI)) {
+		kvmppc_realmode_hmi_handler();
+
+	} else if (trap == BOOK3S_INTERRUPT_H_EMUL_ASSIST) {
+		vcpu->arch.emul_inst = mfspr(SPRN_HEIR);
+
+	} else if (trap == BOOK3S_INTERRUPT_H_DATA_STORAGE) {
+		vcpu->arch.fault_dar = exsave[EX_DAR/sizeof(u64)];
+		vcpu->arch.fault_dsisr = exsave[EX_DSISR/sizeof(u64)];
+		vcpu->arch.fault_gpa = mfspr(SPRN_ASDR);
+
+	} else if (trap == BOOK3S_INTERRUPT_H_INST_STORAGE) {
+		vcpu->arch.fault_gpa = mfspr(SPRN_ASDR);
+
+	} else if (trap == BOOK3S_INTERRUPT_H_FAC_UNAVAIL) {
+		vcpu->arch.hfscr = mfspr(SPRN_HFSCR);
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/*
+	 * Softpatch interrupt for transactional memory emulation cases
+	 * on POWER9 DD2.2.  This is early in the guest exit path - we
+	 * haven't saved registers or done a treclaim yet.
+	 */
+	} else if (trap == BOOK3S_INTERRUPT_HV_SOFTPATCH) {
+		vcpu->arch.emul_inst = mfspr(SPRN_HEIR);
+
+		/*
+		 * The cases we want to handle here are those where the guest
+		 * is in real suspend mode and is trying to transition to
+		 * transactional mode.
+		 */
+		if (local_paca->kvm_hstate.fake_suspend &&
+				(vcpu->arch.shregs.msr & MSR_TS_S)) {
+			if (kvmhv_p9_tm_emulation(vcpu)) {
+				/* Could return to guest quickly if handled */
+				/* XXX: can this all be done by the hv exit
+				 * handler? May need to adjust hv exit handler.
+				 */
+			}
+		}
+#endif
+	}
+
+	radix_clear_slb();
+
+	__mtmsrd(msr, 0);
+
+	accumulate_time(vcpu, &vcpu->arch.rm_exit);
+
+	kvmppc_xive_pull_vcpu(vcpu);
+
+	end_timing(vcpu);
+
+	return trap;
+}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index eff4437e381c..aa8199c148f2 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -46,7 +46,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 /* Stack frame offsets for kvmppc_hv_entry */
 #define SFS			208
 #define STACK_SLOT_TRAP		(SFS-4)
-#define STACK_SLOT_SHORT_PATH	(SFS-8)
 #define STACK_SLOT_TID		(SFS-16)
 #define STACK_SLOT_PSSCR	(SFS-24)
 #define STACK_SLOT_PID		(SFS-32)
@@ -994,9 +993,6 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 no_xive:
 #endif /* CONFIG_KVM_XICS */
 
-	li	r0, 0
-	stw	r0, STACK_SLOT_SHORT_PATH(r1)
-
 deliver_guest_interrupt:	/* r4 = vcpu, r13 = paca */
 	/* Check if we can deliver an external or decrementer interrupt now */
 	ld	r0, VCPU_PENDING_EXC(r4)
@@ -1121,97 +1117,6 @@ ret_to_ultra:
 	ld	r4, VCPU_GPR(R4)(r4)
 	sc	2
 
-/*
- * Enter the guest on a P9 or later system where we have exactly
- * one vcpu per vcore and we don't need to go to real mode
- * (which implies that host and guest are both using radix MMU mode).
- * r3 = vcpu pointer
- * Most SPRs and all the VSRs have been loaded already.
- */
-_GLOBAL(__kvmhv_vcpu_entry_p9)
-EXPORT_SYMBOL_GPL(__kvmhv_vcpu_entry_p9)
-	mflr	r0
-	std	r0, PPC_LR_STKOFF(r1)
-	stdu	r1, -SFS(r1)
-
-	li	r0, 1
-	stw	r0, STACK_SLOT_SHORT_PATH(r1)
-
-	std	r3, HSTATE_KVM_VCPU(r13)
-	mfcr	r4
-	stw	r4, SFS+8(r1)
-
-	std	r1, HSTATE_HOST_R1(r13)
-
-	reg = 14
-	.rept	18
-	std	reg, STACK_SLOT_NVGPRS + ((reg - 14) * 8)(r1)
-	reg = reg + 1
-	.endr
-
-	reg = 14
-	.rept	18
-	ld	reg, __VCPU_GPR(reg)(r3)
-	reg = reg + 1
-	.endr
-
-	mfmsr	r10
-	std	r10, HSTATE_HOST_MSR(r13)
-
-	mr	r4, r3
-	b	fast_guest_entry_c
-guest_exit_short_path:
-	/*
-	 * Malicious or buggy radix guests may have inserted SLB entries
-	 * (only 0..3 because radix always runs with UPRT=1), so these must
-	 * be cleared here to avoid side-channels. slbmte is used rather
-	 * than slbia, as it won't clear cached translations.
-	 */
-	li	r0,0
-	slbmte	r0,r0
-	li	r4,1
-	slbmte	r0,r4
-	li	r4,2
-	slbmte	r0,r4
-	li	r4,3
-	slbmte	r0,r4
-
-	li	r0, KVM_GUEST_MODE_NONE
-	stb	r0, HSTATE_IN_GUEST(r13)
-
-	reg = 14
-	.rept	18
-	std	reg, __VCPU_GPR(reg)(r9)
-	reg = reg + 1
-	.endr
-
-	reg = 14
-	.rept	18
-	ld	reg, STACK_SLOT_NVGPRS + ((reg - 14) * 8)(r1)
-	reg = reg + 1
-	.endr
-
-	lwz	r4, SFS+8(r1)
-	mtcr	r4
-
-	mr	r3, r12		/* trap number */
-
-	addi	r1, r1, SFS
-	ld	r0, PPC_LR_STKOFF(r1)
-	mtlr	r0
-
-	/* If we are in real mode, do a rfid to get back to the caller */
-	mfmsr	r4
-	andi.	r5, r4, MSR_IR
-	bnelr
-	rldicl	r5, r4, 64 - MSR_TS_S_LG, 62	/* extract TS field */
-	mtspr	SPRN_SRR0, r0
-	ld	r10, HSTATE_HOST_MSR(r13)
-	rldimi	r10, r5, MSR_TS_S_LG, 63 - MSR_TS_T_LG
-	mtspr	SPRN_SRR1, r10
-	RFI_TO_KERNEL
-	b	.
-
 secondary_too_late:
 	li	r12, 0
 	stw	r12, STACK_SLOT_TRAP(r1)
@@ -1466,17 +1371,11 @@ guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 #endif /* CONFIG_KVM_XICS */
 
 	/*
-	 * Possibly flush the link stack here, before we do a blr in
-	 * guest_exit_short_path.
+	 * Possibly flush the link stack here.
 	 */
 1:	nop
 	patch_site 1b patch__call_kvm_flush_link_stack
 
-	/* If we came in through the P9 short path, go back out to C now */
-	lwz	r0, STACK_SLOT_SHORT_PATH(r1)
-	cmpwi	r0, 0
-	bne	guest_exit_short_path
-
 	/* For hash guest, read the guest SLB and save it away */
 	ld	r5, VCPU_KVM(r9)
 	lbz	r0, KVM_RADIX(r5)
@@ -1529,7 +1428,12 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 	 * This is probably harmless but is unexpected.
 	 */
 	stw	r5,VCPU_SLB_MAX(r9)
-	/* Sanitise radix guest SLB, see guest_exit_short_path comment. */
+	/*
+	 * Malicious or buggy radix guests may have inserted SLB entries
+	 * (only 0..3 because radix always runs with UPRT=1), so these must
+	 * be cleared here to avoid side-channels. slbmte is used rather
+	 * than slbia, as it won't clear cached translations.
+	 */
 	li	r0,0
 	slbmte	r0,r0
 	li	r4,1
@@ -3331,7 +3235,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	mtspr	SPRN_CIABR, r0
 	mtspr	SPRN_DAWRX0, r0
 
-	/* Clear hash and radix guest SLB, see guest_exit_short_path comment. */
+	/* Clear hash and radix guest SLB. */
 	slbmte	r0, r0
 	PPC_SLBIA(6)
 
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 30dfeac731c6..22a3be0aafa1 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -127,6 +127,38 @@ void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvmppc_xive_push_vcpu);
 
+/*
+ * Pull a vcpu's context from the XIVE on guest exit.
+ * This assumes we are in virtual mode (MMU on)
+ */
+void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu)
+{
+	void __iomem *tima = local_paca->kvm_hstate.xive_tima_virt;
+
+	if (!vcpu->arch.xive_pushed)
+		return;
+
+	/*
+	 * Sould not have been pushed if there is no tima
+	 */
+	if (WARN_ON(!tima))
+		return
+
+	eieio();
+	/* First load to pull the context, we ignore the value */
+	__raw_readw(tima + TM_SPC_PULL_OS_CTX);
+	/* Second load to recover the context state (Words 0 and 1) */
+	vcpu->arch.xive_saved_state.w01 = __raw_readq(tima + TM_QW1_OS);
+
+	/* Fixup some of the state for the next load */
+	vcpu->arch.xive_pushed = 0;
+	vcpu->arch.xive_saved_state.lsmfb = 0;
+	vcpu->arch.xive_saved_state.ack = 0xff;
+	eieio();
+}
+EXPORT_SYMBOL_GPL(kvmppc_xive_pull_vcpu);
+
+
 /*
  * This is a simple trigger for a generic XIVE IRQ. This must
  * only be called for interrupts that support a trigger page
-- 
2.23.0