* [PATCH v6 15/48] KVM: PPC: Book3S 64: Move hcall early register setup to KVM
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
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 98bf73df0f57..a23feaa445b5 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
^ permalink raw reply related
* [PATCH v6 16/48] KVM: PPC: Book3S 64: Move interrupt early register setup to KVM
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
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 a23feaa445b5..115cf79f3e82 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)
@@ -2489,8 +2405,6 @@ 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)
@@ -2611,8 +2525,6 @@ 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)
@@ -2630,8 +2542,6 @@ 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)
@@ -2662,8 +2572,6 @@ EXC_COMMON_BEGIN(altivec_assist_common)
#endif
b interrupt_return
- GEN_KVM altivec_assist
-
#ifdef CONFIG_CBE_RAS
INT_DEFINE_BEGIN(cbe_thermal)
@@ -2681,8 +2589,6 @@ 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)
@@ -2935,6 +2841,15 @@ 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
^ permalink raw reply related
* [PATCH v6 17/48] KVM: PPC: Book3S 64: move bad_host_intr check to HV handler
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: Alexey Kardashevskiy, linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
This is not used by PR KVM.
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
^ permalink raw reply related
* [PATCH v6 18/48] KVM: PPC: Book3S 64: Minimise hcall handler calling convention differences
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: Alexey Kardashevskiy, linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
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 | 51 +++++++++++-----------------
2 files changed, 39 insertions(+), 33 deletions(-)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 115cf79f3e82..4615057681c3 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..0c79c89c6a4b 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -11,40 +11,28 @@
* 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 */
/*
* KVM interrupt entry occurs after GEN_INT_ENTRY runs, and follows that
@@ -91,7 +79,6 @@ 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
^ permalink raw reply related
* [PATCH v6 19/48] KVM: PPC: Book3S HV P9: Move radix MMU switching instructions together
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: Alexey Kardashevskiy, linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
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.
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 66 +++++++++++++++++++++++-------------
1 file changed, 43 insertions(+), 23 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index ed77aff9cdb6..3424b1bfa98e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3478,12 +3478,49 @@ 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;
+
+ /*
+ * All the isync()s are overkill but trivially follow the ISA
+ * requirements. Some can likely be replaced with justification
+ * comment for why they are not needed.
+ */
+ isync();
+ mtspr(SPRN_LPID, lpid);
+ isync();
+ mtspr(SPRN_LPCR, lpcr);
+ isync();
+ 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)
+{
+ isync();
+ mtspr(SPRN_PID, pid);
+ isync();
+ mtspr(SPRN_LPID, kvm->arch.host_lpid);
+ isync();
+ 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;
@@ -3506,12 +3543,12 @@ 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;
}
@@ -3546,7 +3583,6 @@ 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));
@@ -3560,8 +3596,7 @@ 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);
@@ -3600,7 +3635,6 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
mtspr(SPRN_DAWR1, host_dawr1);
mtspr(SPRN_DAWRX1, host_dawrx1);
}
- mtspr(SPRN_PID, host_pidr);
/*
* Since this is radix, do a eieio; tlbsync; ptesync sequence in
@@ -3615,9 +3649,6 @@ 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);
@@ -3634,7 +3665,8 @@ 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;
}
@@ -4167,7 +4199,7 @@ 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;
@@ -4241,13 +4273,6 @@ 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);
@@ -4266,11 +4291,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
srcu_read_unlock(&kvm->srcu, srcu_idx);
- if (cpu_has_feature(CPU_FTR_HVMODE)) {
- mtspr(SPRN_LPID, kvm->arch.host_lpid);
- isync();
- }
-
set_irq_happened(trap);
kvmppc_set_host_core(pcpu);
--
2.23.0
^ permalink raw reply related
* [PATCH v6 20/48] KVM: PPC: Book3S HV P9: implement kvmppc_xive_pull_vcpu in C
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc
Cc: Alexey Kardashevskiy, linuxppc-dev, Cédric Le Goater,
Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
This is more symmetric with kvmppc_xive_push_vcpu. The extra test in
the asm will go away in a later change.
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/kvm_ppc.h | 2 ++
arch/powerpc/kvm/book3s_hv.c | 2 ++
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 5 ++++
arch/powerpc/kvm/book3s_xive.c | 31 +++++++++++++++++++++++++
4 files changed, 40 insertions(+)
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 9531b1c1b190..73b1ca5a6471 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -672,6 +672,7 @@ 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)
{
@@ -712,6 +713,7 @@ 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/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3424b1bfa98e..6ca47f26a397 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3605,6 +3605,8 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
trap = __kvmhv_vcpu_entry_p9(vcpu);
+ kvmppc_xive_pull_vcpu(vcpu);
+
/* Advance host PURR/SPURR by the amount used by guest */
purr = mfspr(SPRN_PURR);
spurr = mfspr(SPRN_SPURR);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 75405ef53238..c11597f815e4 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1442,6 +1442,11 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
bl kvmhv_accumulate_time
#endif
#ifdef CONFIG_KVM_XICS
+ /* If we came in through the P9 short path, xive pull is done in C */
+ lwz r0, STACK_SLOT_SHORT_PATH(r1)
+ cmpwi r0, 0
+ bne 1f
+
/* We are exiting, pull the VP from the XIVE */
lbz r0, VCPU_XIVE_PUSHED(r9)
cmpwi cr0, r0, 0
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index e7219b6f5f9a..741bf1f4387a 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -127,6 +127,37 @@ 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;
+
+ /*
+ * Should 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_readl(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_saved_state.lsmfb = 0;
+ vcpu->arch.xive_saved_state.ack = 0xff;
+ vcpu->arch.xive_pushed = 0;
+ 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
^ permalink raw reply related
* [PATCH v6 21/48] KVM: PPC: Book3S HV P9: Move xive vcpu context management into kvmhv_p9_guest_entry
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: Alexey Kardashevskiy, linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
Move the xive management up so the low level register switching can be
pushed further down in a later patch. XIVE MMIO CI operations can run in
higher level code with machine checks, tracing, etc., available.
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6ca47f26a397..2dc65d752f80 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3598,15 +3598,11 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
- kvmppc_xive_push_vcpu(vcpu);
-
mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0);
mtspr(SPRN_SRR1, vcpu->arch.shregs.srr1);
trap = __kvmhv_vcpu_entry_p9(vcpu);
- kvmppc_xive_pull_vcpu(vcpu);
-
/* Advance host PURR/SPURR by the amount used by guest */
purr = mfspr(SPRN_PURR);
spurr = mfspr(SPRN_SPURR);
@@ -3789,7 +3785,10 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
trap = 0;
}
} else {
+ kvmppc_xive_push_vcpu(vcpu);
trap = kvmhv_load_hv_regs_and_go(vcpu, time_limit, lpcr);
+ kvmppc_xive_pull_vcpu(vcpu);
+
}
vcpu->arch.slb_max = 0;
--
2.23.0
^ permalink raw reply related
* [PATCH v6 22/48] KVM: PPC: Book3S HV P9: Stop handling hcalls in real-mode in the P9 path
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc
Cc: Alexey Kardashevskiy, linuxppc-dev, Cédric Le Goater,
Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
In the interest of minimising the amount of code that is run in
"real-mode", don't handle hcalls in real mode in the P9 path. This
requires some new handlers for H_CEDE and xics-on-xive to be added
before xive is pulled or cede logic is checked.
This introduces a change in radix guest behaviour where radix guests
that execute 'sc 1' in userspace now get a privilege fault whereas
previously the 'sc 1' would be reflected as a syscall interrupt to the
guest kernel. That reflection is only required for hash guests that run
PR KVM.
Background:
In POWER8 and earlier processors, it is very expensive to exit from the
HV real mode context of a guest hypervisor interrupt, and switch to host
virtual mode. On those processors, guest->HV interrupts reach the
hypervisor with the MMU off because the MMU is loaded with guest context
(LPCR, SDR1, SLB), and the other threads in the sub-core need to be
pulled out of the guest too. Then the primary must save off guest state,
invalidate SLB and ERAT, and load up host state before the MMU can be
enabled to run in host virtual mode (~= regular Linux mode).
Hash guests also require a lot of hcalls to run due to the nature of the
MMU architecture and paravirtualisation design. The XICS interrupt
controller requires hcalls to run.
So KVM traditionally tries hard to avoid the full exit, by handling
hcalls and other interrupts in real mode as much as possible.
By contrast, POWER9 has independent MMU context per-thread, and in radix
mode the hypervisor is in host virtual memory mode when the HV interrupt
is taken. Radix guests do not require significant hcalls to manage their
translations, and xive guests don't need hcalls to handle interrupts.
So it's much less important from a performance standpoint to handle
hcalls in real mode in P9.
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/kvm_ppc.h | 6 ++
arch/powerpc/kvm/book3s.c | 6 ++
arch/powerpc/kvm/book3s_hv.c | 76 +++++++++++++++++++++----
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 5 ++
arch/powerpc/kvm/book3s_xive.c | 64 +++++++++++++++++++++
5 files changed, 146 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 73b1ca5a6471..cbd8deba2e8a 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -129,6 +129,7 @@ extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu);
extern int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu);
extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu);
extern void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, ulong flags);
+extern void kvmppc_core_queue_syscall(struct kvm_vcpu *vcpu);
extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags);
extern void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu);
extern void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu);
@@ -607,6 +608,7 @@ extern void kvmppc_free_pimap(struct kvm *kvm);
extern int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall);
extern void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu);
extern int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd);
+extern int kvmppc_xive_xics_hcall(struct kvm_vcpu *vcpu, u32 req);
extern u64 kvmppc_xics_get_icp(struct kvm_vcpu *vcpu);
extern int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval);
extern int kvmppc_xics_connect_vcpu(struct kvm_device *dev,
@@ -639,6 +641,8 @@ static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu)
static inline void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu) { }
static inline int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd)
{ return 0; }
+static inline int kvmppc_xive_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
+ { return 0; }
#endif
#ifdef CONFIG_KVM_XIVE
@@ -673,6 +677,7 @@ 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);
+extern void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu);
static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
{
@@ -714,6 +719,7 @@ static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 ir
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 void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu) { }
static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
{ return 0; }
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 44bf567b6589..1658f899e289 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -171,6 +171,12 @@ void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, ulong flags)
}
EXPORT_SYMBOL_GPL(kvmppc_core_queue_machine_check);
+void kvmppc_core_queue_syscall(struct kvm_vcpu *vcpu)
+{
+ kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_SYSCALL, 0);
+}
+EXPORT_SYMBOL(kvmppc_core_queue_syscall);
+
void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags)
{
/* might as well deliver this straight away */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2dc65d752f80..782c02520741 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1142,12 +1142,13 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
}
/*
- * Handle H_CEDE in the nested virtualization case where we haven't
- * called the real-mode hcall handlers in book3s_hv_rmhandlers.S.
+ * Handle H_CEDE in the P9 path where we don't call the real-mode hcall
+ * handlers in book3s_hv_rmhandlers.S.
+ *
* 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;
@@ -1400,17 +1401,34 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
}
case BOOK3S_INTERRUPT_SYSCALL:
{
- /* hcall - punt to userspace */
int i;
- /* hypercall with MSR_PR has already been handled in rmode,
- * and never reaches here.
- */
+ if (unlikely(vcpu->arch.shregs.msr & MSR_PR)) {
+ /*
+ * Guest userspace executed sc 1. This can only be
+ * reached by the P9 path because the old path
+ * handles this case in realmode hcall handlers.
+ *
+ * Radix guests can not run PR KVM or nested HV hash
+ * guests which might run PR KVM, so this is always
+ * a privilege fault. Send a program check to guest
+ * kernel.
+ */
+ kvmppc_core_queue_program(vcpu, SRR1_PROGPRIV);
+ r = RESUME_GUEST;
+ break;
+ }
+ /*
+ * hcall - gather args and set exit_reason. This will next be
+ * handled by kvmppc_pseries_do_hcall which may be able to deal
+ * with it and resume guest, or may punt to userspace.
+ */
run->papr_hcall.nr = kvmppc_get_gpr(vcpu, 3);
for (i = 0; i < 9; ++i)
run->papr_hcall.args[i] = kvmppc_get_gpr(vcpu, 4 + i);
run->exit_reason = KVM_EXIT_PAPR_HCALL;
+ /* Should this only be set if pseries_do_hcall fails? */
vcpu->arch.hcall_needed = 1;
r = RESUME_HOST;
break;
@@ -3669,6 +3687,12 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
return trap;
}
+static inline bool hcall_is_xics(unsigned long req)
+{
+ return req == H_EOI || req == H_CPPR || req == H_IPI ||
+ req == H_IPOLL || req == H_XIRR || req == H_XIRR_X;
+}
+
/*
* Virtual-mode guest entry for POWER9 and later when the host and
* guest are both using the radix MMU. The LPIDR has already been set.
@@ -3780,15 +3804,36 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
/* 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_cede(vcpu);
kvmppc_set_gpr(vcpu, 3, 0);
trap = 0;
}
} else {
kvmppc_xive_push_vcpu(vcpu);
trap = kvmhv_load_hv_regs_and_go(vcpu, time_limit, lpcr);
+ if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested &&
+ !(vcpu->arch.shregs.msr & MSR_PR)) {
+ unsigned long req = kvmppc_get_gpr(vcpu, 3);
+
+ /* H_CEDE has to be handled now, not later */
+ if (req == H_CEDE) {
+ kvmppc_cede(vcpu);
+ kvmppc_xive_rearm_escalation(vcpu); /* may un-cede */
+ kvmppc_set_gpr(vcpu, 3, 0);
+ trap = 0;
+
+ /* XICS hcalls must be handled before xive is pulled */
+ } else if (hcall_is_xics(req)) {
+ int ret;
+
+ ret = kvmppc_xive_xics_hcall(vcpu, req);
+ if (ret != H_TOO_HARD) {
+ kvmppc_set_gpr(vcpu, 3, ret);
+ trap = 0;
+ }
+ }
+ }
kvmppc_xive_pull_vcpu(vcpu);
-
}
vcpu->arch.slb_max = 0;
@@ -4448,8 +4493,17 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
else
r = kvmppc_run_vcpu(vcpu);
- if (run->exit_reason == KVM_EXIT_PAPR_HCALL &&
- !(vcpu->arch.shregs.msr & MSR_PR)) {
+ if (run->exit_reason == KVM_EXIT_PAPR_HCALL) {
+ if (WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_PR)) {
+ /*
+ * These should have been caught reflected
+ * into the guest by now. Final sanity check:
+ * don't allow userspace to execute hcalls in
+ * the hypervisor.
+ */
+ r = RESUME_GUEST;
+ continue;
+ }
trace_kvm_hcall_enter(vcpu);
r = kvmppc_pseries_do_hcall(vcpu);
trace_kvm_hcall_exit(vcpu, r);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index c11597f815e4..2d0d14ed1d92 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1397,9 +1397,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
mr r4,r9
bge fast_guest_return
2:
+ /* If we came in through the P9 short path, no real mode hcalls */
+ lwz r0, STACK_SLOT_SHORT_PATH(r1)
+ cmpwi r0, 0
+ bne no_try_real
/* See if this is an hcall we can handle in real mode */
cmpwi r12,BOOK3S_INTERRUPT_SYSCALL
beq hcall_try_real_mode
+no_try_real:
/* Hypervisor doorbell - exit only if host IPI flag set */
cmpwi r12, BOOK3S_INTERRUPT_H_DOORBELL
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 741bf1f4387a..24c07094651a 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -158,6 +158,40 @@ void kvmppc_xive_pull_vcpu(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvmppc_xive_pull_vcpu);
+void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu)
+{
+ void __iomem *esc_vaddr = (void __iomem *)vcpu->arch.xive_esc_vaddr;
+
+ if (!esc_vaddr)
+ return;
+
+ /* we are using XIVE with single escalation */
+
+ if (vcpu->arch.xive_esc_on) {
+ /*
+ * If we still have a pending escalation, abort the cede,
+ * and we must set PQ to 10 rather than 00 so that we don't
+ * potentially end up with two entries for the escalation
+ * interrupt in the XIVE interrupt queue. In that case
+ * we also don't want to set xive_esc_on to 1 here in
+ * case we race with xive_esc_irq().
+ */
+ vcpu->arch.ceded = 0;
+ /*
+ * The escalation interrupts are special as we don't EOI them.
+ * There is no need to use the load-after-store ordering offset
+ * to set PQ to 10 as we won't use StoreEOI.
+ */
+ __raw_readq(esc_vaddr + XIVE_ESB_SET_PQ_10);
+ } else {
+ vcpu->arch.xive_esc_on = true;
+ mb();
+ __raw_readq(esc_vaddr + XIVE_ESB_SET_PQ_00);
+ }
+ mb();
+}
+EXPORT_SYMBOL_GPL(kvmppc_xive_rearm_escalation);
+
/*
* This is a simple trigger for a generic XIVE IRQ. This must
* only be called for interrupts that support a trigger page
@@ -2106,6 +2140,36 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
return 0;
}
+int kvmppc_xive_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
+{
+ struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+ /* The VM should have configured XICS mode before doing XICS hcalls. */
+ if (!kvmppc_xics_enabled(vcpu))
+ return H_TOO_HARD;
+
+ switch (req) {
+ case H_XIRR:
+ return xive_vm_h_xirr(vcpu);
+ case H_CPPR:
+ return xive_vm_h_cppr(vcpu, kvmppc_get_gpr(vcpu, 4));
+ case H_EOI:
+ return xive_vm_h_eoi(vcpu, kvmppc_get_gpr(vcpu, 4));
+ case H_IPI:
+ return xive_vm_h_ipi(vcpu, kvmppc_get_gpr(vcpu, 4),
+ kvmppc_get_gpr(vcpu, 5));
+ case H_IPOLL:
+ return xive_vm_h_ipoll(vcpu, kvmppc_get_gpr(vcpu, 4));
+ case H_XIRR_X:
+ xive_vm_h_xirr(vcpu);
+ kvmppc_set_gpr(vcpu, 5, get_tb() + vc->tb_offset);
+ return H_SUCCESS;
+ }
+
+ return H_UNSUPPORTED;
+}
+EXPORT_SYMBOL_GPL(kvmppc_xive_xics_hcall);
+
int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu)
{
struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
--
2.23.0
^ permalink raw reply related
* [PATCH v6 23/48] KVM: PPC: Book3S HV P9: Move setting HDEC after switching to guest LPCR
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: Alexey Kardashevskiy, linuxppc-dev, Nicholas Piggin,
Fabiano Rosas
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
LPCR[HDICE]=0 suppresses hypervisor decrementer exceptions on some
processors, so it must be enabled before HDEC is set.
Rather than set it in the host LPCR then setting HDEC, move the HDEC
update to after the guest MMU context (including LPCR) is loaded.
There shouldn't be much concern with delaying HDEC by some 10s or 100s
of nanoseconds by setting it a bit later.
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 19 +++++++------------
1 file changed, 7 insertions(+), 12 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 782c02520741..f2aefd478d8c 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3557,20 +3557,9 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
host_dawrx1 = mfspr(SPRN_DAWRX1);
}
- /*
- * P8 and P9 suppress the HDEC exception when LPCR[HDICE] = 0,
- * so set HDICE before writing HDEC.
- */
- mtspr(SPRN_LPCR, kvm->arch.host_lpcr | LPCR_HDICE);
- isync();
-
hdec = time_limit - mftb();
- if (hdec < 0) {
- mtspr(SPRN_LPCR, kvm->arch.host_lpcr);
- isync();
+ if (hdec < 0)
return BOOK3S_INTERRUPT_HV_DECREMENTER;
- }
- mtspr(SPRN_HDEC, hdec);
if (vc->tb_offset) {
u64 new_tb = mftb() + vc->tb_offset;
@@ -3616,6 +3605,12 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
+ /*
+ * P9 suppresses the HDEC exception when LPCR[HDICE] = 0,
+ * so set guest LPCR (with HDICE) before writing HDEC.
+ */
+ mtspr(SPRN_HDEC, hdec);
+
mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0);
mtspr(SPRN_SRR1, vcpu->arch.shregs.srr1);
--
2.23.0
^ permalink raw reply related
* [PATCH v6 24/48] KVM: PPC: Book3S HV P9: Use large decrementer for HDEC
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: Alexey Kardashevskiy, linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
On processors that don't suppress the HDEC exceptions when LPCR[HDICE]=0,
this could help reduce needless guest exits due to leftover exceptions on
entering the guest.
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/time.h | 2 ++
arch/powerpc/kernel/time.c | 1 +
arch/powerpc/kvm/book3s_hv.c | 3 ++-
3 files changed, 5 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 8dd3cdb25338..68d94711811e 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -18,6 +18,8 @@
#include <asm/vdso/timebase.h>
/* time.c */
+extern u64 decrementer_max;
+
extern unsigned long tb_ticks_per_jiffy;
extern unsigned long tb_ticks_per_usec;
extern unsigned long tb_ticks_per_sec;
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index b67d93a609a2..fc42594c8223 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -89,6 +89,7 @@ static struct clocksource clocksource_timebase = {
#define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF
u64 decrementer_max = DECREMENTER_DEFAULT_MAX;
+EXPORT_SYMBOL_GPL(decrementer_max); /* for KVM HDEC */
static int decrementer_set_next_event(unsigned long evt,
struct clock_event_device *dev);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index f2aefd478d8c..3029ffb4b792 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3675,7 +3675,8 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
vc->tb_offset_applied = 0;
}
- mtspr(SPRN_HDEC, 0x7fffffff);
+ /* HDEC must be at least as large as DEC, so decrementer_max fits */
+ mtspr(SPRN_HDEC, decrementer_max);
switch_mmu_to_host_radix(kvm, host_pidr);
--
2.23.0
^ permalink raw reply related
* [PATCH v6 25/48] KVM: PPC: Book3S HV P9: Use host timer accounting to avoid decrementer read
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
There is no need to save away the host DEC value, as it is derived
from the host timer subsystem, which maintains the next timer time.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/time.h | 5 +++++
arch/powerpc/kernel/time.c | 1 +
arch/powerpc/kvm/book3s_hv.c | 14 +++++++-------
3 files changed, 13 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 68d94711811e..0128cd9769bc 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -101,6 +101,11 @@ extern void __init time_init(void);
DECLARE_PER_CPU(u64, decrementers_next_tb);
+static inline u64 timer_get_next_tb(void)
+{
+ return __this_cpu_read(decrementers_next_tb);
+}
+
/* Convert timebase ticks to nanoseconds */
unsigned long long tb_to_ns(unsigned long long tb_ticks);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index fc42594c8223..8b9b38a8ce57 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -109,6 +109,7 @@ struct clock_event_device decrementer_clockevent = {
EXPORT_SYMBOL(decrementer_clockevent);
DEFINE_PER_CPU(u64, decrementers_next_tb);
+EXPORT_SYMBOL_GPL(decrementers_next_tb);
static DEFINE_PER_CPU(struct clock_event_device, decrementers);
#define XSEC_PER_SEC (1024*1024)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3029ffb4b792..5c4ccebce682 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3703,16 +3703,15 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
unsigned long host_amr = mfspr(SPRN_AMR);
unsigned long host_fscr = mfspr(SPRN_FSCR);
s64 dec;
- u64 tb;
+ u64 tb, next_timer;
int trap, save_pmu;
- dec = mfspr(SPRN_DEC);
tb = mftb();
- if (dec < 0)
+ next_timer = timer_get_next_tb();
+ if (tb >= next_timer)
return BOOK3S_INTERRUPT_HV_DECREMENTER;
- local_paca->kvm_hstate.dec_expires = dec + tb;
- if (local_paca->kvm_hstate.dec_expires < time_limit)
- time_limit = local_paca->kvm_hstate.dec_expires;
+ if (next_timer < time_limit)
+ time_limit = next_timer;
vcpu->arch.ceded = 0;
@@ -3895,7 +3894,8 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
vc->entry_exit_map = 0x101;
vc->in_guest = 0;
- mtspr(SPRN_DEC, local_paca->kvm_hstate.dec_expires - mftb());
+ next_timer = timer_get_next_tb();
+ mtspr(SPRN_DEC, next_timer - mftb());
mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso);
kvmhv_load_host_pmu();
--
2.23.0
^ permalink raw reply related
* [PATCH v6 26/48] KVM: PPC: Book3S HV P9: Reduce mftb per guest entry/exit
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin, Fabiano Rosas
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
mftb is serialising (dispatch next-to-complete) so it is heavy weight
for a mfspr. Avoid reading it multiple times in the entry or exit paths.
A small number of cycles delay to timers is tolerable.
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 5c4ccebce682..f4e5a64457e6 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3557,12 +3557,13 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
host_dawrx1 = mfspr(SPRN_DAWRX1);
}
- hdec = time_limit - mftb();
+ tb = mftb();
+ hdec = time_limit - tb;
if (hdec < 0)
return BOOK3S_INTERRUPT_HV_DECREMENTER;
if (vc->tb_offset) {
- u64 new_tb = mftb() + vc->tb_offset;
+ u64 new_tb = tb + vc->tb_offset;
mtspr(SPRN_TBU40, new_tb);
tb = mftb();
if ((tb & 0xffffff) < (new_tb & 0xffffff))
@@ -3760,7 +3761,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
if (!(vcpu->arch.ctrl & 1))
mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1);
- mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb());
+ mtspr(SPRN_DEC, vcpu->arch.dec_expires - tb);
if (kvmhv_on_pseries()) {
/*
@@ -3895,7 +3896,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
vc->in_guest = 0;
next_timer = timer_get_next_tb();
- mtspr(SPRN_DEC, next_timer - mftb());
+ mtspr(SPRN_DEC, next_timer - tb);
mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso);
kvmhv_load_host_pmu();
--
2.23.0
^ permalink raw reply related
* [PATCH v6 27/48] KVM: PPC: Book3S HV P9: Reduce irq_work vs guest decrementer races
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
irq_work's use of the DEC SPR is racy with guest<->host switch and guest
entry which flips the DEC interrupt to guest, which could lose a host
work interrupt.
This patch closes one race, and attempts to comment another class of
races.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index f4e5a64457e6..dae59f05ef50 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3761,6 +3761,18 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
if (!(vcpu->arch.ctrl & 1))
mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1);
+ /*
+ * When setting DEC, we must always deal with irq_work_raise via NMI vs
+ * setting DEC. The problem occurs right as we switch into guest mode
+ * if a NMI hits and sets pending work and sets DEC, then that will
+ * apply to the guest and not bring us back to the host.
+ *
+ * irq_work_raise could check a flag (or possibly LPCR[HDICE] for
+ * example) and set HDEC to 1? That wouldn't solve the nested hv
+ * case which needs to abort the hcall or zero the time limit.
+ *
+ * XXX: Another day's problem.
+ */
mtspr(SPRN_DEC, vcpu->arch.dec_expires - tb);
if (kvmhv_on_pseries()) {
@@ -3897,6 +3909,9 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
next_timer = timer_get_next_tb();
mtspr(SPRN_DEC, next_timer - tb);
+ /* We may have raced with new irq work */
+ if (test_irq_work_pending())
+ set_dec(1);
mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso);
kvmhv_load_host_pmu();
--
2.23.0
^ permalink raw reply related
* [PATCH v6 28/48] KMV: PPC: Book3S HV: Use set_dec to set decrementer to host
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: Alexey Kardashevskiy, linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
The host Linux timer code arms the decrementer with the value
'decrementers_next_tb - current_tb' using set_dec(), which stores
val - 1 on Book3S-64, which is not quite the same as what KVM does
to re-arm the host decrementer when exiting the guest.
This shouldn't be a significant change, but it makes the logic match
and avoids this small extra change being brought into the next patch.
Suggested-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index dae59f05ef50..65ddae3958ab 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3908,7 +3908,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
vc->in_guest = 0;
next_timer = timer_get_next_tb();
- mtspr(SPRN_DEC, next_timer - tb);
+ set_dec(next_timer - tb);
/* We may have raced with new irq work */
if (test_irq_work_pending())
set_dec(1);
--
2.23.0
^ permalink raw reply related
* [PATCH v6 29/48] powerpc/time: add API for KVM to re-arm the host timer/decrementer
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
Rather than have KVM look up the host timer and fiddle with the
irq-work internal details, have the powerpc/time.c code provide a
function for KVM to re-arm the Linux timer code when exiting a
guest.
This is implementation has an improvement over existing code of
marking a decrementer interrupt as soft-pending if a timer has
expired, rather than setting DEC to a -ve value, which tended to
cause host timers to take two interrupts (first hdec to exit the
guest, then the immediate dec).
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/time.h | 4 ++++
arch/powerpc/kernel/time.c | 41 +++++++++++++++++++++++++--------
arch/powerpc/kvm/book3s_hv.c | 6 +----
3 files changed, 37 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 0128cd9769bc..924b2157882f 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -106,6 +106,10 @@ static inline u64 timer_get_next_tb(void)
return __this_cpu_read(decrementers_next_tb);
}
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+void timer_rearm_host_dec(u64 now);
+#endif
+
/* Convert timebase ticks to nanoseconds */
unsigned long long tb_to_ns(unsigned long long tb_ticks);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 8b9b38a8ce57..8bbcc6be40c0 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -563,13 +563,43 @@ void arch_irq_work_raise(void)
preempt_enable();
}
+static void set_dec_or_work(u64 val)
+{
+ set_dec(val);
+ /* We may have raced with new irq work */
+ if (unlikely(test_irq_work_pending()))
+ set_dec(1);
+}
+
#else /* CONFIG_IRQ_WORK */
#define test_irq_work_pending() 0
#define clear_irq_work_pending()
+static void set_dec_or_work(u64 val)
+{
+ set_dec(val);
+}
#endif /* CONFIG_IRQ_WORK */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+void timer_rearm_host_dec(u64 now)
+{
+ u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
+
+ WARN_ON_ONCE(!arch_irqs_disabled());
+ WARN_ON_ONCE(mfmsr() & MSR_EE);
+
+ if (now >= *next_tb) {
+ now = *next_tb - now;
+ set_dec_or_work(now);
+ } else {
+ local_paca->irq_happened |= PACA_IRQ_DEC;
+ }
+}
+EXPORT_SYMBOL_GPL(timer_rearm_host_dec);
+#endif
+
/*
* timer_interrupt - gets called when the decrementer overflows,
* with interrupts disabled.
@@ -630,10 +660,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
} else {
now = *next_tb - now;
if (now <= decrementer_max)
- set_dec(now);
- /* We may have raced with new irq work */
- if (test_irq_work_pending())
- set_dec(1);
+ set_dec_or_work(now);
__this_cpu_inc(irq_stat.timer_irqs_others);
}
@@ -875,11 +902,7 @@ static int decrementer_set_next_event(unsigned long evt,
struct clock_event_device *dev)
{
__this_cpu_write(decrementers_next_tb, get_tb() + evt);
- set_dec(evt);
-
- /* We may have raced with new irq work */
- if (test_irq_work_pending())
- set_dec(1);
+ set_dec_or_work(evt);
return 0;
}
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 65ddae3958ab..353a0c8b79fa 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3907,11 +3907,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
vc->entry_exit_map = 0x101;
vc->in_guest = 0;
- next_timer = timer_get_next_tb();
- set_dec(next_timer - tb);
- /* We may have raced with new irq work */
- if (test_irq_work_pending())
- set_dec(1);
+ timer_rearm_host_dec(tb);
mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso);
kvmhv_load_host_pmu();
--
2.23.0
^ permalink raw reply related
* [PATCH v6 30/48] KVM: PPC: Book3S HV P9: Implement the rest of the P9 path in C
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
Almost all logic is moved to C, by introducing a new in_guest mode for
the P9 path that branches very early in the KVM interrupt handler to
P9 exit code.
The main P9 entry and exit assembly is now only about 160 lines of low
level stack setup and register save/restore, plus a bad-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". 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,
but it does lack any loop to return quickly back into the guest without
switching out of realmode in the case of unimportant or easily handled
interrupts. As explained in previous changes, handling HV interrupts
in real mode is not so important for P9.
Use of Linux 64s interrupt entry code register conventions including
paca EX_ save areas are brought into the KVM code. There is no point
shuffling things into different paca save areas and making up a
different calling convention for KVM.
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 | 8 +
arch/powerpc/include/asm/kvm_host.h | 7 +-
arch/powerpc/kernel/security.c | 5 +-
arch/powerpc/kvm/Makefile | 1 +
arch/powerpc/kvm/book3s_64_entry.S | 247 ++++++++++++++++++++++
arch/powerpc/kvm/book3s_hv.c | 9 +-
arch/powerpc/kvm/book3s_hv_interrupt.c | 218 +++++++++++++++++++
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 125 +----------
10 files changed, 501 insertions(+), 125 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 939f3c94c8f3..7c74c80ed994 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -122,6 +122,7 @@ 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_p9;
extern s32 patch__memset_nocache, patch__memcpy_nocache;
extern long flush_branch_caches;
@@ -142,7 +143,7 @@ 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..c214bcffb441 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -153,9 +153,17 @@ 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
+/*
+ * Invalid HDSISR value which is used to indicate when HW has not set the reg.
+ * Used to work around an errata.
+ */
+#define HDSISR_CANARY 0x7fff
+
/*
* We use a lock bit in HPTE dword 0 to synchronize updates and
* accesses to each HPTE, and another bit to indicate non-present
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 05fb00d37609..fa0083345b11 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -690,7 +690,12 @@ struct kvm_vcpu_arch {
ulong fault_dar;
u32 fault_dsisr;
unsigned long intr_msr;
- ulong fault_gpa; /* guest real address of page fault (POWER9) */
+ /*
+ * POWER9 and later, fault_gpa contains the guest real address of page
+ * fault for a radix guest, or segment descriptor (equivalent to result
+ * from slbmfev of SLB entry that translated the EA) for hash guests.
+ */
+ ulong fault_gpa;
#endif
#ifdef CONFIG_BOOKE
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index e4e1a94ccf6a..3a607c11f20f 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_p9;
// 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..ca7c86aa9360 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -88,6 +88,7 @@ kvm-book3s_64-builtin-tm-objs-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \
ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
+ book3s_hv_interrupt.o \
book3s_hv_hmi.o \
book3s_hv_rmhandlers.o \
book3s_hv_rm_mmu.o \
diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S
index 0c79c89c6a4b..d98ad580fd98 100644
--- a/arch/powerpc/kvm/book3s_64_entry.S
+++ b/arch/powerpc/kvm/book3s_64_entry.S
@@ -1,11 +1,16 @@
/* SPDX-License-Identifier: GPL-2.0-only */
#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/mmu.h>
#include <asm/ppc_asm.h>
+#include <asm/ptrace.h>
#include <asm/reg.h>
+#include <asm/ultravisor-api.h>
/*
* These are branched to from interrupt handlers in exception-64s.S which set
@@ -29,10 +34,15 @@
.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
/* Now we look like kvmppc_interrupt */
+ li r11,PACA_EXGEN
+ b 1f
/*
* KVM interrupt entry occurs after GEN_INT_ENTRY runs, and follows that
@@ -53,6 +63,12 @@ kvmppc_hcall:
.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
@@ -154,3 +170,234 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
GET_SCRATCH0(r13)
HRFI_TO_KERNEL
#endif
+
+/* Stack frame offsets for kvmppc_hv_entry */
+#define SFS (144 + STACK_FRAME_MIN_SIZE)
+#define STACK_SLOT_NVGPRS (SFS - 144) /* 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)
+
+ 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().
+ *
+ * The exit code recovers the host stack and vcpu pointer, saves all guest GPRs
+ * and CR, LR, 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, which saves CTR and other guest registers
+ * (SPRs and FP, VEC, etc).
+ */
+.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:
+ /*
+ * If set to KVM_GUEST_MODE_GUEST_HV_FAST but we're still in the
+ * hypervisor, that means we can't return from the entry stack.
+ */
+ rldicl. r10,r12,64-MSR_HV_LG,63
+ bne- kvmppc_p9_bad_interrupt
+
+ std r1,HSTATE_SCRATCH1(r13)
+ std r3,HSTATE_SCRATCH2(r13)
+ ld r1,HSTATE_HOST_R1(r13)
+ ld r3,HSTATE_KVM_VCPU(r13)
+
+ 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_p9
+
+ addi r1,r1,SFS
+ ld r0,PPC_LR_STKOFF(r1)
+ mtlr r0
+ blr
+
+/*
+ * Took an interrupt somewhere right before HRFID to guest, so registers are
+ * in a bad way. Return things hopefully enough to run host virtual code and
+ * run the Linux interrupt handler (SRESET or MCE) to print something useful.
+ *
+ * We could be really clever and save all host registers in known locations
+ * before setting HSTATE_IN_GUEST, then restoring them all here, and setting
+ * return address to a fixup that sets them up again. But that's a lot of
+ * effort for a small bit of code. Lots of other things to do first.
+ */
+kvmppc_p9_bad_interrupt:
+ /*
+ * Set GUEST_MODE_NONE so the handler won't branch to KVM, and clear
+ * MSR_RI in r12 ([H]SRR1) so the handler won't try to return.
+ */
+ li r10,KVM_GUEST_MODE_NONE
+ stb r10,HSTATE_IN_GUEST(r13)
+ li r10,MSR_RI
+ andc r12,r12,r10
+
+ /*
+ * Clean up guest registers to give host a chance to run.
+ */
+ li r10,0
+ mtspr SPRN_AMR,r10
+ mtspr SPRN_IAMR,r10
+ mtspr SPRN_CIABR,r10
+ mtspr SPRN_DAWRX0,r10
+BEGIN_FTR_SECTION
+ mtspr SPRN_DAWRX1,r10
+END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
+ mtspr SPRN_PID,r10
+
+ /*
+ * Switch to host MMU mode
+ */
+ ld r10, HSTATE_KVM_VCPU(r13)
+ ld r10, VCPU_KVM(r10)
+ lwz r10, KVM_HOST_LPID(r10)
+ mtspr SPRN_LPID,r10
+
+ ld r10, HSTATE_KVM_VCPU(r13)
+ ld r10, VCPU_KVM(r10)
+ ld r10, KVM_HOST_LPCR(r10)
+ mtspr SPRN_LPCR,r10
+
+ /*
+ * Go back to interrupt handler
+ */
+ ld r10,HSTATE_SCRATCH0(r13)
+ cmpwi r10,BOOK3S_INTERRUPT_MACHINE_CHECK
+ beq machine_check_common
+
+ ld r10,HSTATE_SCRATCH0(r13)
+ cmpwi r10,BOOK3S_INTERRUPT_SYSTEM_RESET
+ beq system_reset_common
+
+ b .
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 353a0c8b79fa..9a1476daca8c 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1442,6 +1442,8 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu,
*/
case BOOK3S_INTERRUPT_H_DATA_STORAGE:
r = RESUME_PAGE_FAULT;
+ if (vcpu->arch.fault_dsisr == HDSISR_CANARY)
+ r = RESUME_GUEST; /* Just retry if it's the canary */
break;
case BOOK3S_INTERRUPT_H_INST_STORAGE:
vcpu->arch.fault_dar = kvmppc_get_pc(vcpu);
@@ -3707,6 +3709,8 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
u64 tb, next_timer;
int trap, save_pmu;
+ WARN_ON_ONCE(vcpu->arch.ceded);
+
tb = mftb();
next_timer = timer_get_next_tb();
if (tb >= next_timer)
@@ -3714,8 +3718,6 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
if (next_timer < time_limit)
time_limit = next_timer;
- vcpu->arch.ceded = 0;
-
kvmhv_save_host_pmu(); /* saves it to PACA kvm_hstate */
kvmppc_subcore_enter_guest();
@@ -3842,9 +3844,10 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
}
}
kvmppc_xive_pull_vcpu(vcpu);
+
+ vcpu->arch.slb_max = 0;
}
- vcpu->arch.slb_max = 0;
dec = mfspr(SPRN_DEC);
if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */
dec = (s32) dec;
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
new file mode 100644
index 000000000000..3c507daed064
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#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));
+}
+
+/*
+ * 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);
+
+ /*
+ * On POWER9 DD2.1 and below, sometimes on a Hypervisor Data Storage
+ * Interrupt (HDSI) the HDSISR is not be updated at all.
+ *
+ * To work around this we put a canary value into the HDSISR before
+ * returning to a guest and then check for this canary when we take a
+ * HDSI. If we find the canary on a HDSI, we know the hardware didn't
+ * update the HDSISR. In this case we return to the guest to retake the
+ * HDSI which should correctly update the HDSISR the second time HDSI
+ * entry.
+ *
+ * Just do this on all p9 processors for now.
+ */
+ mtspr(SPRN_HDSISR, HDSISR_CANARY);
+
+ 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);
+
+ /* XXX: Could get these from r11/12 and paca exsave instead */
+ 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);
+
+ /* 0x2 bit for HSRR is only used by PR and P7/8 HV paths, clear it */
+ 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_early(vcpu)) {
+ /* Prevent it being handled again. */
+ trap = 0;
+ }
+ }
+#endif
+ }
+
+ radix_clear_slb();
+
+ __mtmsrd(msr, 0);
+ mtspr(SPRN_CTRLT, 1);
+
+ accumulate_time(vcpu, &vcpu->arch.rm_exit);
+
+ end_timing(vcpu);
+
+ return trap;
+}
+EXPORT_SYMBOL_GPL(__kvmhv_vcpu_entry_p9);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 2d0d14ed1d92..85c2595ead8d 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -44,9 +44,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
#define NAPPING_UNSPLIT 3
/* Stack frame offsets for kvmppc_hv_entry */
-#define SFS 208
+#define SFS 160
#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)
@@ -59,8 +58,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
#define STACK_SLOT_UAMOR (SFS-88)
#define STACK_SLOT_DAWR1 (SFS-96)
#define STACK_SLOT_DAWRX1 (SFS-104)
-/* the following is used by the P9 short path */
-#define STACK_SLOT_NVGPRS (SFS-152) /* 18 gprs */
/*
* Call kvmppc_hv_entry in real mode.
@@ -1008,9 +1005,6 @@ 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)
@@ -1030,7 +1024,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
mtspr SPRN_SRR0, r6
mtspr SPRN_SRR1, r7
-fast_guest_entry_c:
ld r10, VCPU_PC(r4)
ld r11, VCPU_MSR(r4)
/* r11 = vcpu->arch.msr & ~MSR_HV */
@@ -1135,97 +1128,6 @@ 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)
@@ -1397,14 +1299,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
mr r4,r9
bge fast_guest_return
2:
- /* If we came in through the P9 short path, no real mode hcalls */
- lwz r0, STACK_SLOT_SHORT_PATH(r1)
- cmpwi r0, 0
- bne no_try_real
/* See if this is an hcall we can handle in real mode */
cmpwi r12,BOOK3S_INTERRUPT_SYSCALL
beq hcall_try_real_mode
-no_try_real:
/* Hypervisor doorbell - exit only if host IPI flag set */
cmpwi r12, BOOK3S_INTERRUPT_H_DOORBELL
@@ -1447,11 +1344,6 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
bl kvmhv_accumulate_time
#endif
#ifdef CONFIG_KVM_XICS
- /* If we came in through the P9 short path, xive pull is done in C */
- lwz r0, STACK_SLOT_SHORT_PATH(r1)
- cmpwi r0, 0
- bne 1f
-
/* We are exiting, pull the VP from the XIVE */
lbz r0, VCPU_XIVE_PUSHED(r9)
cmpwi cr0, r0, 0
@@ -1491,16 +1383,11 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
/*
* Possibly flush the link stack here, before we do a blr in
- * guest_exit_short_path.
+ * kvmhv_switch_to_host.
*/
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)
@@ -1548,8 +1435,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
b guest_bypass
0: /*
- * Sanitise radix guest SLB, see guest_exit_short_path comment.
- * We clear vcpu->arch.slb_max to match earlier behaviour.
+ * 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
stw r0,VCPU_SLB_MAX(r9)
@@ -3362,7 +3251,7 @@ BEGIN_FTR_SECTION
mtspr SPRN_DAWRX1, r0
END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
- /* Clear hash and radix guest SLB, see guest_exit_short_path comment. */
+ /* Clear hash and radix guest SLB. */
slbmte r0, r0
PPC_SLBIA(6)
--
2.23.0
^ permalink raw reply related
* [PATCH v6 31/48] KVM: PPC: Book3S HV P9: inline kvmhv_load_hv_regs_and_go into __kvmhv_vcpu_entry_p9
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin, Fabiano Rosas
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
Now the initial C implementation is done, inline more HV code to make
rearranging things easier.
And rename __kvmhv_vcpu_entry_p9 to drop the leading underscores as it's
now C, and is now a more complete vcpu entry.
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/kvm_book3s_64.h | 2 +-
arch/powerpc/kvm/book3s_hv.c | 192 +----------------------
arch/powerpc/kvm/book3s_hv_interrupt.c | 179 ++++++++++++++++++++-
3 files changed, 180 insertions(+), 193 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index c214bcffb441..eaf3a562bf1e 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -153,7 +153,7 @@ static inline bool kvmhv_vcpu_is_radix(struct kvm_vcpu *vcpu)
return radix;
}
-int __kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu);
+int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr);
#define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */
#endif
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 9a1476daca8c..d6eecedaa5a5 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3498,194 +3498,6 @@ 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;
-
- /*
- * All the isync()s are overkill but trivially follow the ISA
- * requirements. Some can likely be replaced with justification
- * comment for why they are not needed.
- */
- isync();
- mtspr(SPRN_LPID, lpid);
- isync();
- mtspr(SPRN_LPCR, lpcr);
- isync();
- 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)
-{
- isync();
- mtspr(SPRN_PID, pid);
- isync();
- mtspr(SPRN_LPID, kvm->arch.host_lpid);
- isync();
- 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;
- int trap;
- unsigned long host_hfscr = mfspr(SPRN_HFSCR);
- unsigned long host_ciabr = mfspr(SPRN_CIABR);
- unsigned long host_dawr0 = mfspr(SPRN_DAWR0);
- unsigned long host_dawrx0 = mfspr(SPRN_DAWRX0);
- unsigned long host_psscr = mfspr(SPRN_PSSCR);
- unsigned long host_pidr = mfspr(SPRN_PID);
- unsigned long host_dawr1 = 0;
- unsigned long host_dawrx1 = 0;
-
- if (cpu_has_feature(CPU_FTR_DAWR1)) {
- host_dawr1 = mfspr(SPRN_DAWR1);
- host_dawrx1 = mfspr(SPRN_DAWRX1);
- }
-
- tb = mftb();
- hdec = time_limit - tb;
- if (hdec < 0)
- return BOOK3S_INTERRUPT_HV_DECREMENTER;
-
- if (vc->tb_offset) {
- u64 new_tb = tb + vc->tb_offset;
- mtspr(SPRN_TBU40, new_tb);
- tb = mftb();
- if ((tb & 0xffffff) < (new_tb & 0xffffff))
- mtspr(SPRN_TBU40, new_tb + 0x1000000);
- vc->tb_offset_applied = vc->tb_offset;
- }
-
- if (vc->pcr)
- mtspr(SPRN_PCR, vc->pcr | PCR_MASK);
- mtspr(SPRN_DPDES, vc->dpdes);
- mtspr(SPRN_VTB, vc->vtb);
-
- local_paca->kvm_hstate.host_purr = mfspr(SPRN_PURR);
- local_paca->kvm_hstate.host_spurr = mfspr(SPRN_SPURR);
- mtspr(SPRN_PURR, vcpu->arch.purr);
- mtspr(SPRN_SPURR, vcpu->arch.spurr);
-
- if (dawr_enabled()) {
- mtspr(SPRN_DAWR0, vcpu->arch.dawr0);
- mtspr(SPRN_DAWRX0, vcpu->arch.dawrx0);
- if (cpu_has_feature(CPU_FTR_DAWR1)) {
- mtspr(SPRN_DAWR1, vcpu->arch.dawr1);
- mtspr(SPRN_DAWRX1, vcpu->arch.dawrx1);
- }
- }
- mtspr(SPRN_CIABR, vcpu->arch.ciabr);
- mtspr(SPRN_IC, vcpu->arch.ic);
-
- mtspr(SPRN_PSSCR, vcpu->arch.psscr | PSSCR_EC |
- (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
-
- mtspr(SPRN_HFSCR, vcpu->arch.hfscr);
-
- mtspr(SPRN_SPRG0, vcpu->arch.shregs.sprg0);
- mtspr(SPRN_SPRG1, vcpu->arch.shregs.sprg1);
- mtspr(SPRN_SPRG2, vcpu->arch.shregs.sprg2);
- mtspr(SPRN_SPRG3, vcpu->arch.shregs.sprg3);
-
- mtspr(SPRN_AMOR, ~0UL);
-
- switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
-
- /*
- * P9 suppresses the HDEC exception when LPCR[HDICE] = 0,
- * so set guest LPCR (with HDICE) before writing HDEC.
- */
- mtspr(SPRN_HDEC, hdec);
-
- mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0);
- mtspr(SPRN_SRR1, vcpu->arch.shregs.srr1);
-
- trap = __kvmhv_vcpu_entry_p9(vcpu);
-
- /* Advance host PURR/SPURR by the amount used by guest */
- purr = mfspr(SPRN_PURR);
- spurr = mfspr(SPRN_SPURR);
- mtspr(SPRN_PURR, local_paca->kvm_hstate.host_purr +
- purr - vcpu->arch.purr);
- mtspr(SPRN_SPURR, local_paca->kvm_hstate.host_spurr +
- spurr - vcpu->arch.spurr);
- vcpu->arch.purr = purr;
- vcpu->arch.spurr = spurr;
-
- vcpu->arch.ic = mfspr(SPRN_IC);
- vcpu->arch.pid = mfspr(SPRN_PID);
- vcpu->arch.psscr = mfspr(SPRN_PSSCR) & PSSCR_GUEST_VIS;
-
- vcpu->arch.shregs.sprg0 = mfspr(SPRN_SPRG0);
- vcpu->arch.shregs.sprg1 = mfspr(SPRN_SPRG1);
- vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2);
- vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3);
-
- /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */
- mtspr(SPRN_PSSCR, host_psscr |
- (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
- mtspr(SPRN_HFSCR, host_hfscr);
- mtspr(SPRN_CIABR, host_ciabr);
- mtspr(SPRN_DAWR0, host_dawr0);
- mtspr(SPRN_DAWRX0, host_dawrx0);
- if (cpu_has_feature(CPU_FTR_DAWR1)) {
- mtspr(SPRN_DAWR1, host_dawr1);
- mtspr(SPRN_DAWRX1, host_dawrx1);
- }
-
- /*
- * Since this is radix, do a eieio; tlbsync; ptesync sequence in
- * case we interrupted the guest between a tlbie and a ptesync.
- */
- asm volatile("eieio; tlbsync; ptesync");
-
- /*
- * cp_abort is required if the processor supports local copy-paste
- * to clear the copy buffer that was under control of the guest.
- */
- if (cpu_has_feature(CPU_FTR_ARCH_31))
- asm volatile(PPC_CP_ABORT);
-
- vc->dpdes = mfspr(SPRN_DPDES);
- vc->vtb = mfspr(SPRN_VTB);
- mtspr(SPRN_DPDES, 0);
- if (vc->pcr)
- mtspr(SPRN_PCR, PCR_MASK);
-
- if (vc->tb_offset_applied) {
- u64 new_tb = mftb() - vc->tb_offset_applied;
- mtspr(SPRN_TBU40, new_tb);
- tb = mftb();
- if ((tb & 0xffffff) < (new_tb & 0xffffff))
- mtspr(SPRN_TBU40, new_tb + 0x1000000);
- vc->tb_offset_applied = 0;
- }
-
- /* HDEC must be at least as large as DEC, so decrementer_max fits */
- mtspr(SPRN_HDEC, decrementer_max);
-
- switch_mmu_to_host_radix(kvm, host_pidr);
-
- return trap;
-}
-
static inline bool hcall_is_xics(unsigned long req)
{
return req == H_EOI || req == H_CPPR || req == H_IPI ||
@@ -3782,7 +3594,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
* We need to save and restore the guest visible part of the
* psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor
* doesn't do this for us. Note only required if pseries since
- * this is done in kvmhv_load_hv_regs_and_go() below otherwise.
+ * this is done in kvmhv_vcpu_entry_p9() below otherwise.
*/
unsigned long host_psscr;
/* call our hypervisor to load up HV regs and go */
@@ -3820,7 +3632,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
}
} else {
kvmppc_xive_push_vcpu(vcpu);
- trap = kvmhv_load_hv_regs_and_go(vcpu, time_limit, lpcr);
+ trap = kvmhv_vcpu_entry_p9(vcpu, time_limit, lpcr);
if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested &&
!(vcpu->arch.shregs.msr & MSR_PR)) {
unsigned long req = kvmppc_get_gpr(vcpu, 3);
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
index 3c507daed064..6fdd93936e16 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupt.c
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -55,6 +55,42 @@ static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator
#define accumulate_time(vcpu, next) do {} while (0)
#endif
+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;
+
+ /*
+ * All the isync()s are overkill but trivially follow the ISA
+ * requirements. Some can likely be replaced with justification
+ * comment for why they are not needed.
+ */
+ isync();
+ mtspr(SPRN_LPID, lpid);
+ isync();
+ mtspr(SPRN_LPCR, lpcr);
+ isync();
+ 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)
+{
+ isync();
+ mtspr(SPRN_PID, pid);
+ isync();
+ mtspr(SPRN_LPID, kvm->arch.host_lpid);
+ isync();
+ mtspr(SPRN_LPCR, kvm->arch.host_lpcr);
+ isync();
+}
+
static inline void mfslb(unsigned int idx, u64 *slbee, u64 *slbev)
{
asm volatile("slbmfev %0,%1" : "=r" (*slbev) : "r" (idx));
@@ -89,11 +125,86 @@ static void radix_clear_slb(void)
}
}
-int __kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu)
+int kvmhv_vcpu_entry_p9(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;
u64 *exsave;
unsigned long msr = mfmsr();
int trap;
+ unsigned long host_hfscr = mfspr(SPRN_HFSCR);
+ unsigned long host_ciabr = mfspr(SPRN_CIABR);
+ unsigned long host_dawr0 = mfspr(SPRN_DAWR0);
+ unsigned long host_dawrx0 = mfspr(SPRN_DAWRX0);
+ unsigned long host_psscr = mfspr(SPRN_PSSCR);
+ unsigned long host_pidr = mfspr(SPRN_PID);
+ unsigned long host_dawr1 = 0;
+ unsigned long host_dawrx1 = 0;
+
+ if (cpu_has_feature(CPU_FTR_DAWR1)) {
+ host_dawr1 = mfspr(SPRN_DAWR1);
+ host_dawrx1 = mfspr(SPRN_DAWRX1);
+ }
+
+ tb = mftb();
+ hdec = time_limit - tb;
+ if (hdec < 0)
+ return BOOK3S_INTERRUPT_HV_DECREMENTER;
+
+ if (vc->tb_offset) {
+ u64 new_tb = tb + vc->tb_offset;
+ mtspr(SPRN_TBU40, new_tb);
+ tb = mftb();
+ if ((tb & 0xffffff) < (new_tb & 0xffffff))
+ mtspr(SPRN_TBU40, new_tb + 0x1000000);
+ vc->tb_offset_applied = vc->tb_offset;
+ }
+
+ if (vc->pcr)
+ mtspr(SPRN_PCR, vc->pcr | PCR_MASK);
+ mtspr(SPRN_DPDES, vc->dpdes);
+ mtspr(SPRN_VTB, vc->vtb);
+
+ local_paca->kvm_hstate.host_purr = mfspr(SPRN_PURR);
+ local_paca->kvm_hstate.host_spurr = mfspr(SPRN_SPURR);
+ mtspr(SPRN_PURR, vcpu->arch.purr);
+ mtspr(SPRN_SPURR, vcpu->arch.spurr);
+
+ if (dawr_enabled()) {
+ mtspr(SPRN_DAWR0, vcpu->arch.dawr0);
+ mtspr(SPRN_DAWRX0, vcpu->arch.dawrx0);
+ if (cpu_has_feature(CPU_FTR_DAWR1)) {
+ mtspr(SPRN_DAWR1, vcpu->arch.dawr1);
+ mtspr(SPRN_DAWRX1, vcpu->arch.dawrx1);
+ }
+ }
+ mtspr(SPRN_CIABR, vcpu->arch.ciabr);
+ mtspr(SPRN_IC, vcpu->arch.ic);
+
+ mtspr(SPRN_PSSCR, vcpu->arch.psscr | PSSCR_EC |
+ (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
+
+ mtspr(SPRN_HFSCR, vcpu->arch.hfscr);
+
+ mtspr(SPRN_SPRG0, vcpu->arch.shregs.sprg0);
+ mtspr(SPRN_SPRG1, vcpu->arch.shregs.sprg1);
+ mtspr(SPRN_SPRG2, vcpu->arch.shregs.sprg2);
+ mtspr(SPRN_SPRG3, vcpu->arch.shregs.sprg3);
+
+ mtspr(SPRN_AMOR, ~0UL);
+
+ switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
+
+ /*
+ * P9 suppresses the HDEC exception when LPCR[HDICE] = 0,
+ * so set guest LPCR (with HDICE) before writing HDEC.
+ */
+ mtspr(SPRN_HDEC, hdec);
+
+ mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0);
+ mtspr(SPRN_SRR1, vcpu->arch.shregs.srr1);
start_timing(vcpu, &vcpu->arch.rm_entry);
@@ -213,6 +324,70 @@ int __kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu)
end_timing(vcpu);
+ /* Advance host PURR/SPURR by the amount used by guest */
+ purr = mfspr(SPRN_PURR);
+ spurr = mfspr(SPRN_SPURR);
+ mtspr(SPRN_PURR, local_paca->kvm_hstate.host_purr +
+ purr - vcpu->arch.purr);
+ mtspr(SPRN_SPURR, local_paca->kvm_hstate.host_spurr +
+ spurr - vcpu->arch.spurr);
+ vcpu->arch.purr = purr;
+ vcpu->arch.spurr = spurr;
+
+ vcpu->arch.ic = mfspr(SPRN_IC);
+ vcpu->arch.pid = mfspr(SPRN_PID);
+ vcpu->arch.psscr = mfspr(SPRN_PSSCR) & PSSCR_GUEST_VIS;
+
+ vcpu->arch.shregs.sprg0 = mfspr(SPRN_SPRG0);
+ vcpu->arch.shregs.sprg1 = mfspr(SPRN_SPRG1);
+ vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2);
+ vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3);
+
+ /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */
+ mtspr(SPRN_PSSCR, host_psscr |
+ (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
+ mtspr(SPRN_HFSCR, host_hfscr);
+ mtspr(SPRN_CIABR, host_ciabr);
+ mtspr(SPRN_DAWR0, host_dawr0);
+ mtspr(SPRN_DAWRX0, host_dawrx0);
+ if (cpu_has_feature(CPU_FTR_DAWR1)) {
+ mtspr(SPRN_DAWR1, host_dawr1);
+ mtspr(SPRN_DAWRX1, host_dawrx1);
+ }
+
+ /*
+ * Since this is radix, do a eieio; tlbsync; ptesync sequence in
+ * case we interrupted the guest between a tlbie and a ptesync.
+ */
+ asm volatile("eieio; tlbsync; ptesync");
+
+ /*
+ * cp_abort is required if the processor supports local copy-paste
+ * to clear the copy buffer that was under control of the guest.
+ */
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ asm volatile(PPC_CP_ABORT);
+
+ vc->dpdes = mfspr(SPRN_DPDES);
+ vc->vtb = mfspr(SPRN_VTB);
+ mtspr(SPRN_DPDES, 0);
+ if (vc->pcr)
+ mtspr(SPRN_PCR, PCR_MASK);
+
+ if (vc->tb_offset_applied) {
+ u64 new_tb = mftb() - vc->tb_offset_applied;
+ mtspr(SPRN_TBU40, new_tb);
+ tb = mftb();
+ if ((tb & 0xffffff) < (new_tb & 0xffffff))
+ mtspr(SPRN_TBU40, new_tb + 0x1000000);
+ vc->tb_offset_applied = 0;
+ }
+
+ /* HDEC must be at least as large as DEC, so decrementer_max fits */
+ mtspr(SPRN_HDEC, decrementer_max);
+
+ switch_mmu_to_host_radix(kvm, host_pidr);
+
return trap;
}
-EXPORT_SYMBOL_GPL(__kvmhv_vcpu_entry_p9);
+EXPORT_SYMBOL_GPL(kvmhv_vcpu_entry_p9);
--
2.23.0
^ permalink raw reply related
* [PATCH v6 32/48] KVM: PPC: Book3S HV P9: Read machine check registers while MSR[RI] is 0
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
SRR0/1, DAR, DSISR must all be protected from machine check which can
clobber them. Ensure MSR[RI] is clear while they are live.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 11 +++++++--
arch/powerpc/kvm/book3s_hv_interrupt.c | 33 +++++++++++++++++++++++---
arch/powerpc/kvm/book3s_hv_ras.c | 2 ++
3 files changed, 41 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index d6eecedaa5a5..5f0ac6567a06 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3567,11 +3567,16 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
mtspr(SPRN_BESCR, vcpu->arch.bescr);
mtspr(SPRN_WORT, vcpu->arch.wort);
mtspr(SPRN_TIDR, vcpu->arch.tid);
- mtspr(SPRN_DAR, vcpu->arch.shregs.dar);
- mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr);
mtspr(SPRN_AMR, vcpu->arch.amr);
mtspr(SPRN_UAMOR, vcpu->arch.uamor);
+ /*
+ * DAR, DSISR, and for nested HV, SPRGs must be set with MSR[RI]
+ * clear (or hstate set appropriately to catch those registers
+ * being clobbered if we take a MCE or SRESET), so those are done
+ * later.
+ */
+
if (!(vcpu->arch.ctrl & 1))
mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1);
@@ -3614,6 +3619,8 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
hvregs.vcpu_token = vcpu->vcpu_id;
}
hvregs.hdec_expiry = time_limit;
+ mtspr(SPRN_DAR, vcpu->arch.shregs.dar);
+ mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr);
trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs),
__pa(&vcpu->arch.regs));
kvmhv_restore_hv_return_state(vcpu, &hvregs);
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
index 6fdd93936e16..e93d2a6456ff 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupt.c
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -132,6 +132,7 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
s64 hdec;
u64 tb, purr, spurr;
u64 *exsave;
+ bool ri_set;
unsigned long msr = mfmsr();
int trap;
unsigned long host_hfscr = mfspr(SPRN_HFSCR);
@@ -203,9 +204,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
*/
mtspr(SPRN_HDEC, hdec);
- mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0);
- mtspr(SPRN_SRR1, vcpu->arch.shregs.srr1);
-
start_timing(vcpu, &vcpu->arch.rm_entry);
vcpu->arch.ceded = 0;
@@ -231,6 +229,13 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
*/
mtspr(SPRN_HDSISR, HDSISR_CANARY);
+ __mtmsrd(0, 1); /* clear RI */
+
+ mtspr(SPRN_DAR, vcpu->arch.shregs.dar);
+ mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr);
+ mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0);
+ mtspr(SPRN_SRR1, vcpu->arch.shregs.srr1);
+
accumulate_time(vcpu, &vcpu->arch.guest_time);
local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_GUEST_HV_FAST;
@@ -248,7 +253,13 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
/* 0x2 bit for HSRR is only used by PR and P7/8 HV paths, clear it */
trap = local_paca->kvm_hstate.scratch0 & ~0x2;
+
+ /* HSRR interrupts leave MSR[RI] unchanged, SRR interrupts clear it. */
+ ri_set = false;
if (likely(trap > BOOK3S_INTERRUPT_MACHINE_CHECK)) {
+ if (trap != BOOK3S_INTERRUPT_SYSCALL &&
+ (vcpu->arch.shregs.msr & MSR_RI))
+ ri_set = true;
exsave = local_paca->exgen;
} else if (trap == BOOK3S_INTERRUPT_SYSTEM_RESET) {
exsave = local_paca->exnmi;
@@ -258,6 +269,22 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
vcpu->arch.regs.gpr[1] = local_paca->kvm_hstate.scratch1;
vcpu->arch.regs.gpr[3] = local_paca->kvm_hstate.scratch2;
+
+ /*
+ * Only set RI after reading machine check regs (DAR, DSISR, SRR0/1)
+ * and hstate scratch (which we need to move into exsave to make
+ * re-entrant vs SRESET/MCE)
+ */
+ if (ri_set) {
+ if (unlikely(!(mfmsr() & MSR_RI))) {
+ __mtmsrd(MSR_RI, 1);
+ WARN_ON_ONCE(1);
+ }
+ } else {
+ WARN_ON_ONCE(mfmsr() & MSR_RI);
+ __mtmsrd(MSR_RI, 1);
+ }
+
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)];
diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c
index d4bca93b79f6..8d8a4d5f0b55 100644
--- a/arch/powerpc/kvm/book3s_hv_ras.c
+++ b/arch/powerpc/kvm/book3s_hv_ras.c
@@ -199,6 +199,8 @@ static void kvmppc_tb_resync_done(void)
* know about the exact state of the TB value. Resync TB call will
* restore TB to host timebase.
*
+ * This could use the new OPAL_HANDLE_HMI2 to avoid resyncing TB every time.
+ *
* Things to consider:
* - On TB error, HMI interrupt is reported on all the threads of the core
* that has encountered TB error irrespective of split-core mode.
--
2.23.0
^ permalink raw reply related
* [PATCH v6 33/48] KVM: PPC: Book3S HV P9: Improve exit timing accounting coverage
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
The C conversion caused exit timing to become a bit cramped. Expand it
to cover more of the entry and exit code.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv_interrupt.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
index e93d2a6456ff..44c77f907f91 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupt.c
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -154,6 +154,8 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
if (hdec < 0)
return BOOK3S_INTERRUPT_HV_DECREMENTER;
+ start_timing(vcpu, &vcpu->arch.rm_entry);
+
if (vc->tb_offset) {
u64 new_tb = tb + vc->tb_offset;
mtspr(SPRN_TBU40, new_tb);
@@ -204,8 +206,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
*/
mtspr(SPRN_HDEC, hdec);
- start_timing(vcpu, &vcpu->arch.rm_entry);
-
vcpu->arch.ceded = 0;
WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_HV);
@@ -349,8 +349,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
accumulate_time(vcpu, &vcpu->arch.rm_exit);
- end_timing(vcpu);
-
/* Advance host PURR/SPURR by the amount used by guest */
purr = mfspr(SPRN_PURR);
spurr = mfspr(SPRN_SPURR);
@@ -415,6 +413,8 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
switch_mmu_to_host_radix(kvm, host_pidr);
+ end_timing(vcpu);
+
return trap;
}
EXPORT_SYMBOL_GPL(kvmhv_vcpu_entry_p9);
--
2.23.0
^ permalink raw reply related
* [PATCH v6 34/48] KVM: PPC: Book3S HV P9: Move SPR loading after expiry time check
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
This is wasted work if the time limit is exceeded.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv_interrupt.c | 36 ++++++++++++++++----------
1 file changed, 22 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
index 44c77f907f91..b12bf7c01460 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupt.c
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -133,21 +133,16 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
u64 tb, purr, spurr;
u64 *exsave;
bool ri_set;
- unsigned long msr = mfmsr();
int trap;
- unsigned long host_hfscr = mfspr(SPRN_HFSCR);
- unsigned long host_ciabr = mfspr(SPRN_CIABR);
- unsigned long host_dawr0 = mfspr(SPRN_DAWR0);
- unsigned long host_dawrx0 = mfspr(SPRN_DAWRX0);
- unsigned long host_psscr = mfspr(SPRN_PSSCR);
- unsigned long host_pidr = mfspr(SPRN_PID);
- unsigned long host_dawr1 = 0;
- unsigned long host_dawrx1 = 0;
-
- if (cpu_has_feature(CPU_FTR_DAWR1)) {
- host_dawr1 = mfspr(SPRN_DAWR1);
- host_dawrx1 = mfspr(SPRN_DAWRX1);
- }
+ unsigned long msr;
+ unsigned long host_hfscr;
+ unsigned long host_ciabr;
+ unsigned long host_dawr0;
+ unsigned long host_dawrx0;
+ unsigned long host_psscr;
+ unsigned long host_pidr;
+ unsigned long host_dawr1;
+ unsigned long host_dawrx1;
tb = mftb();
hdec = time_limit - tb;
@@ -165,6 +160,19 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
vc->tb_offset_applied = vc->tb_offset;
}
+ msr = mfmsr();
+
+ host_hfscr = mfspr(SPRN_HFSCR);
+ host_ciabr = mfspr(SPRN_CIABR);
+ host_dawr0 = mfspr(SPRN_DAWR0);
+ host_dawrx0 = mfspr(SPRN_DAWRX0);
+ host_psscr = mfspr(SPRN_PSSCR);
+ host_pidr = mfspr(SPRN_PID);
+ if (cpu_has_feature(CPU_FTR_DAWR1)) {
+ host_dawr1 = mfspr(SPRN_DAWR1);
+ host_dawrx1 = mfspr(SPRN_DAWRX1);
+ }
+
if (vc->pcr)
mtspr(SPRN_PCR, vc->pcr | PCR_MASK);
mtspr(SPRN_DPDES, vc->dpdes);
--
2.23.0
^ permalink raw reply related
* [PATCH v6 35/48] KVM: PPC: Book3S HV P9: Add helpers for OS SPR handling
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
This is a first step to wrapping supervisor and user SPR saving and
loading up into helpers, which will then be called independently in
bare metal and nested HV cases in order to optimise SPR access.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv.c | 141 ++++++++++++++++++++++-------------
1 file changed, 89 insertions(+), 52 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 5f0ac6567a06..c2098464eb5e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3498,6 +3498,89 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
trace_kvmppc_run_core(vc, 1);
}
+static void load_spr_state(struct kvm_vcpu *vcpu)
+{
+ mtspr(SPRN_DSCR, vcpu->arch.dscr);
+ mtspr(SPRN_IAMR, vcpu->arch.iamr);
+ mtspr(SPRN_PSPB, vcpu->arch.pspb);
+ mtspr(SPRN_FSCR, vcpu->arch.fscr);
+ mtspr(SPRN_TAR, vcpu->arch.tar);
+ mtspr(SPRN_EBBHR, vcpu->arch.ebbhr);
+ mtspr(SPRN_EBBRR, vcpu->arch.ebbrr);
+ mtspr(SPRN_BESCR, vcpu->arch.bescr);
+ mtspr(SPRN_WORT, vcpu->arch.wort);
+ mtspr(SPRN_TIDR, vcpu->arch.tid);
+ mtspr(SPRN_AMR, vcpu->arch.amr);
+ mtspr(SPRN_UAMOR, vcpu->arch.uamor);
+
+ /*
+ * DAR, DSISR, and for nested HV, SPRGs must be set with MSR[RI]
+ * clear (or hstate set appropriately to catch those registers
+ * being clobbered if we take a MCE or SRESET), so those are done
+ * later.
+ */
+
+ if (!(vcpu->arch.ctrl & 1))
+ mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1);
+}
+
+static void store_spr_state(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.ctrl = mfspr(SPRN_CTRLF);
+
+ vcpu->arch.iamr = mfspr(SPRN_IAMR);
+ vcpu->arch.pspb = mfspr(SPRN_PSPB);
+ vcpu->arch.fscr = mfspr(SPRN_FSCR);
+ vcpu->arch.tar = mfspr(SPRN_TAR);
+ vcpu->arch.ebbhr = mfspr(SPRN_EBBHR);
+ vcpu->arch.ebbrr = mfspr(SPRN_EBBRR);
+ vcpu->arch.bescr = mfspr(SPRN_BESCR);
+ vcpu->arch.wort = mfspr(SPRN_WORT);
+ vcpu->arch.tid = mfspr(SPRN_TIDR);
+ vcpu->arch.amr = mfspr(SPRN_AMR);
+ vcpu->arch.uamor = mfspr(SPRN_UAMOR);
+ vcpu->arch.dscr = mfspr(SPRN_DSCR);
+}
+
+/*
+ * Privileged (non-hypervisor) host registers to save.
+ */
+struct p9_host_os_sprs {
+ unsigned long dscr;
+ unsigned long tidr;
+ unsigned long iamr;
+ unsigned long amr;
+ unsigned long fscr;
+};
+
+static void save_p9_host_os_sprs(struct p9_host_os_sprs *host_os_sprs)
+{
+ host_os_sprs->dscr = mfspr(SPRN_DSCR);
+ host_os_sprs->tidr = mfspr(SPRN_TIDR);
+ host_os_sprs->iamr = mfspr(SPRN_IAMR);
+ host_os_sprs->amr = mfspr(SPRN_AMR);
+ host_os_sprs->fscr = mfspr(SPRN_FSCR);
+}
+
+/* vcpu guest regs must already be saved */
+static void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu,
+ struct p9_host_os_sprs *host_os_sprs)
+{
+ mtspr(SPRN_PSPB, 0);
+ mtspr(SPRN_WORT, 0);
+ mtspr(SPRN_UAMOR, 0);
+
+ mtspr(SPRN_DSCR, host_os_sprs->dscr);
+ mtspr(SPRN_TIDR, host_os_sprs->tidr);
+ mtspr(SPRN_IAMR, host_os_sprs->iamr);
+
+ if (host_os_sprs->amr != vcpu->arch.amr)
+ mtspr(SPRN_AMR, host_os_sprs->amr);
+
+ if (host_os_sprs->fscr != vcpu->arch.fscr)
+ mtspr(SPRN_FSCR, host_os_sprs->fscr);
+}
+
static inline bool hcall_is_xics(unsigned long req)
{
return req == H_EOI || req == H_CPPR || req == H_IPI ||
@@ -3512,11 +3595,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
unsigned long lpcr)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
- unsigned long host_dscr = mfspr(SPRN_DSCR);
- unsigned long host_tidr = mfspr(SPRN_TIDR);
- unsigned long host_iamr = mfspr(SPRN_IAMR);
- unsigned long host_amr = mfspr(SPRN_AMR);
- unsigned long host_fscr = mfspr(SPRN_FSCR);
+ struct p9_host_os_sprs host_os_sprs;
s64 dec;
u64 tb, next_timer;
int trap, save_pmu;
@@ -3530,6 +3609,8 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
if (next_timer < time_limit)
time_limit = next_timer;
+ save_p9_host_os_sprs(&host_os_sprs);
+
kvmhv_save_host_pmu(); /* saves it to PACA kvm_hstate */
kvmppc_subcore_enter_guest();
@@ -3557,28 +3638,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
#endif
mtspr(SPRN_VRSAVE, vcpu->arch.vrsave);
- mtspr(SPRN_DSCR, vcpu->arch.dscr);
- mtspr(SPRN_IAMR, vcpu->arch.iamr);
- mtspr(SPRN_PSPB, vcpu->arch.pspb);
- mtspr(SPRN_FSCR, vcpu->arch.fscr);
- mtspr(SPRN_TAR, vcpu->arch.tar);
- mtspr(SPRN_EBBHR, vcpu->arch.ebbhr);
- mtspr(SPRN_EBBRR, vcpu->arch.ebbrr);
- mtspr(SPRN_BESCR, vcpu->arch.bescr);
- mtspr(SPRN_WORT, vcpu->arch.wort);
- mtspr(SPRN_TIDR, vcpu->arch.tid);
- mtspr(SPRN_AMR, vcpu->arch.amr);
- mtspr(SPRN_UAMOR, vcpu->arch.uamor);
-
- /*
- * DAR, DSISR, and for nested HV, SPRGs must be set with MSR[RI]
- * clear (or hstate set appropriately to catch those registers
- * being clobbered if we take a MCE or SRESET), so those are done
- * later.
- */
-
- if (!(vcpu->arch.ctrl & 1))
- mtspr(SPRN_CTRLT, mfspr(SPRN_CTRLF) & ~1);
+ load_spr_state(vcpu);
/*
* When setting DEC, we must always deal with irq_work_raise via NMI vs
@@ -3674,33 +3734,10 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
vcpu->arch.dec_expires = dec + tb;
vcpu->cpu = -1;
vcpu->arch.thread_cpu = -1;
- vcpu->arch.ctrl = mfspr(SPRN_CTRLF);
-
- vcpu->arch.iamr = mfspr(SPRN_IAMR);
- vcpu->arch.pspb = mfspr(SPRN_PSPB);
- vcpu->arch.fscr = mfspr(SPRN_FSCR);
- vcpu->arch.tar = mfspr(SPRN_TAR);
- vcpu->arch.ebbhr = mfspr(SPRN_EBBHR);
- vcpu->arch.ebbrr = mfspr(SPRN_EBBRR);
- vcpu->arch.bescr = mfspr(SPRN_BESCR);
- vcpu->arch.wort = mfspr(SPRN_WORT);
- vcpu->arch.tid = mfspr(SPRN_TIDR);
- vcpu->arch.amr = mfspr(SPRN_AMR);
- vcpu->arch.uamor = mfspr(SPRN_UAMOR);
- vcpu->arch.dscr = mfspr(SPRN_DSCR);
-
- mtspr(SPRN_PSPB, 0);
- mtspr(SPRN_WORT, 0);
- mtspr(SPRN_UAMOR, 0);
- mtspr(SPRN_DSCR, host_dscr);
- mtspr(SPRN_TIDR, host_tidr);
- mtspr(SPRN_IAMR, host_iamr);
- if (host_amr != vcpu->arch.amr)
- mtspr(SPRN_AMR, host_amr);
+ store_spr_state(vcpu);
- if (host_fscr != vcpu->arch.fscr)
- mtspr(SPRN_FSCR, host_fscr);
+ restore_p9_host_os_sprs(vcpu, &host_os_sprs);
msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
store_fp_state(&vcpu->arch.fp);
--
2.23.0
^ permalink raw reply related
* [PATCH v6 36/48] KVM: PPC: Book3S HV P9: Switch to guest MMU context as late as possible
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
Move MMU context switch as late as reasonably possible to minimise code
running with guest context switched in. This becomes more important when
this code may run in real-mode, with later changes.
Move WARN_ON as early as possible so program check interrupts are less
likely to tangle everything up.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv_interrupt.c | 40 +++++++++++++-------------
1 file changed, 20 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
index b12bf7c01460..a430cefb822a 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupt.c
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -149,8 +149,13 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
if (hdec < 0)
return BOOK3S_INTERRUPT_HV_DECREMENTER;
+ WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_HV);
+ WARN_ON_ONCE(!(vcpu->arch.shregs.msr & MSR_ME));
+
start_timing(vcpu, &vcpu->arch.rm_entry);
+ vcpu->arch.ceded = 0;
+
if (vc->tb_offset) {
u64 new_tb = tb + vc->tb_offset;
mtspr(SPRN_TBU40, new_tb);
@@ -199,26 +204,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
mtspr(SPRN_HFSCR, vcpu->arch.hfscr);
- mtspr(SPRN_SPRG0, vcpu->arch.shregs.sprg0);
- mtspr(SPRN_SPRG1, vcpu->arch.shregs.sprg1);
- mtspr(SPRN_SPRG2, vcpu->arch.shregs.sprg2);
- mtspr(SPRN_SPRG3, vcpu->arch.shregs.sprg3);
-
- mtspr(SPRN_AMOR, ~0UL);
-
- switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
-
- /*
- * P9 suppresses the HDEC exception when LPCR[HDICE] = 0,
- * so set guest LPCR (with HDICE) before writing HDEC.
- */
- mtspr(SPRN_HDEC, hdec);
-
- 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);
@@ -237,6 +222,21 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
*/
mtspr(SPRN_HDSISR, HDSISR_CANARY);
+ mtspr(SPRN_SPRG0, vcpu->arch.shregs.sprg0);
+ mtspr(SPRN_SPRG1, vcpu->arch.shregs.sprg1);
+ mtspr(SPRN_SPRG2, vcpu->arch.shregs.sprg2);
+ mtspr(SPRN_SPRG3, vcpu->arch.shregs.sprg3);
+
+ mtspr(SPRN_AMOR, ~0UL);
+
+ switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
+
+ /*
+ * P9 suppresses the HDEC exception when LPCR[HDICE] = 0,
+ * so set guest LPCR (with HDICE) before writing HDEC.
+ */
+ mtspr(SPRN_HDEC, hdec);
+
__mtmsrd(0, 1); /* clear RI */
mtspr(SPRN_DAR, vcpu->arch.shregs.dar);
--
2.23.0
^ permalink raw reply related
* [PATCH v6 37/48] KVM: PPC: Book3S HV: Implement radix prefetch workaround by disabling MMU
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
Rather than partition the guest PID space + flush a rogue guest PID to
work around this problem, instead fix it by always disabling the MMU when
switching in or out of guest MMU context in HV mode.
This may be a bit less efficient, but it is a lot less complicated and
allows the P9 path to trivally implement the workaround too. Newer CPUs
are not subject to this issue.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/mmu_context.h | 6 ----
arch/powerpc/kvm/book3s_hv.c | 21 +++++++----
arch/powerpc/kvm/book3s_hv_interrupt.c | 16 ++++++---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 34 ------------------
arch/powerpc/mm/book3s64/radix_pgtable.c | 27 +++++---------
arch/powerpc/mm/book3s64/radix_tlb.c | 46 ------------------------
arch/powerpc/mm/mmu_context.c | 4 +--
7 files changed, 36 insertions(+), 118 deletions(-)
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 652ce85f9410..bb5c7e5e142e 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -122,12 +122,6 @@ static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea)
}
#endif
-#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU)
-extern void radix_kvm_prefetch_workaround(struct mm_struct *mm);
-#else
-static inline void radix_kvm_prefetch_workaround(struct mm_struct *mm) { }
-#endif
-
extern void switch_cop(struct mm_struct *next);
extern int use_cop(unsigned long acop, struct mm_struct *mm);
extern void drop_cop(unsigned long acop, struct mm_struct *mm);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index c2098464eb5e..21e13f93235a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -809,6 +809,9 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
*/
if (mflags != 0 && mflags != 3)
return H_UNSUPPORTED_FLAG_START;
+ if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG) &&
+ kvmhv_vcpu_is_radix(vcpu) && mflags == 3)
+ return H_UNSUPPORTED_FLAG_START;
return H_TOO_HARD;
default:
return H_TOO_HARD;
@@ -1674,6 +1677,14 @@ unsigned long kvmppc_filter_lpcr_hv(struct kvm *kvm, unsigned long lpcr)
lpcr &= ~LPCR_AIL;
if ((lpcr & LPCR_AIL) != LPCR_AIL_3)
lpcr &= ~LPCR_AIL; /* LPCR[AIL]=1/2 is disallowed */
+ /*
+ * On some POWER9s we force AIL off for radix guests to prevent
+ * executing in MSR[HV]=1 mode with the MMU enabled and PIDR set to
+ * guest, which can result in Q0 translations with LPID=0 PID=PIDR to
+ * be cached, which the host TLB management does not expect.
+ */
+ if (kvm_is_radix(kvm) && cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
+ lpcr &= ~LPCR_AIL;
/*
* On POWER9, allow userspace to enable large decrementer for the
@@ -4349,12 +4360,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
do {
- /*
- * The TLB prefetch bug fixup is only in the kvmppc_run_vcpu
- * path, which also handles hash and dependent threads mode.
- */
- if (kvm->arch.threads_indep && kvm_is_radix(kvm) &&
- !cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
+ if (kvm->arch.threads_indep && kvm_is_radix(kvm))
r = kvmhv_run_single_vcpu(vcpu, ~(u64)0,
vcpu->arch.vcore->lpcr);
else
@@ -4985,6 +4991,9 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
if (!indep_threads_mode && !cpu_has_feature(CPU_FTR_HVMODE)) {
pr_warn("KVM: Ignoring indep_threads_mode=N in nested hypervisor\n");
kvm->arch.threads_indep = true;
+ } else if (!indep_threads_mode && cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
+ pr_warn("KVM: Ignoring indep_threads_mode=N on pre-DD2.2 POWER9\n");
+ kvm->arch.threads_indep = true;
} else {
kvm->arch.threads_indep = indep_threads_mode;
}
diff --git a/arch/powerpc/kvm/book3s_hv_interrupt.c b/arch/powerpc/kvm/book3s_hv_interrupt.c
index a430cefb822a..f09b11ea2033 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupt.c
+++ b/arch/powerpc/kvm/book3s_hv_interrupt.c
@@ -229,6 +229,9 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
mtspr(SPRN_AMOR, ~0UL);
+ if (cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
+ __mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0);
+
switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
/*
@@ -237,7 +240,8 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
*/
mtspr(SPRN_HDEC, hdec);
- __mtmsrd(0, 1); /* clear RI */
+ if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
+ __mtmsrd(0, 1); /* clear RI */
mtspr(SPRN_DAR, vcpu->arch.shregs.dar);
mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr);
@@ -352,9 +356,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
radix_clear_slb();
- __mtmsrd(msr, 0);
- mtspr(SPRN_CTRLT, 1);
-
accumulate_time(vcpu, &vcpu->arch.rm_exit);
/* Advance host PURR/SPURR by the amount used by guest */
@@ -421,6 +422,13 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
switch_mmu_to_host_radix(kvm, host_pidr);
+ /*
+ * If we are in real mode, only switch MMU on after the MMU is
+ * switched to host, to avoid the P9_RADIX_PREFETCH_BUG.
+ */
+ __mtmsrd(msr, 0);
+ mtspr(SPRN_CTRLT, 1);
+
end_timing(vcpu);
return trap;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 85c2595ead8d..9fd7e9e7fda6 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1710,40 +1710,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
eieio
tlbsync
ptesync
-
-BEGIN_FTR_SECTION
- /* Radix: Handle the case where the guest used an illegal PID */
- LOAD_REG_ADDR(r4, mmu_base_pid)
- lwz r3, VCPU_GUEST_PID(r9)
- lwz r5, 0(r4)
- cmpw cr0,r3,r5
- blt 2f
-
- /*
- * Illegal PID, the HW might have prefetched and cached in the TLB
- * some translations for the LPID 0 / guest PID combination which
- * Linux doesn't know about, so we need to flush that PID out of
- * the TLB. First we need to set LPIDR to 0 so tlbiel applies to
- * the right context.
- */
- li r0,0
- mtspr SPRN_LPID,r0
- isync
-
- /* Then do a congruence class local flush */
- ld r6,VCPU_KVM(r9)
- lwz r0,KVM_TLB_SETS(r6)
- mtctr r0
- li r7,0x400 /* IS field = 0b01 */
- ptesync
- sldi r0,r3,32 /* RS has PID */
-1: PPC_TLBIEL(7,0,2,1,1) /* RIC=2, PRS=1, R=1 */
- addi r7,r7,0x1000
- bdnz 1b
- ptesync
-END_FTR_SECTION_IFSET(CPU_FTR_P9_RADIX_PREFETCH_BUG)
-
-2:
#endif /* CONFIG_PPC_RADIX_MMU */
/*
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 98f0b243c1ab..1ea95891a79e 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -357,30 +357,19 @@ static void __init radix_init_pgtable(void)
}
/* Find out how many PID bits are supported */
- if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
- if (!mmu_pid_bits)
- mmu_pid_bits = 20;
- mmu_base_pid = 1;
- } else if (cpu_has_feature(CPU_FTR_HVMODE)) {
- if (!mmu_pid_bits)
- mmu_pid_bits = 20;
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ if (!cpu_has_feature(CPU_FTR_HVMODE) &&
+ cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
/*
- * When KVM is possible, we only use the top half of the
- * PID space to avoid collisions between host and guest PIDs
- * which can cause problems due to prefetch when exiting the
- * guest with AIL=3
+ * Older versions of KVM on these machines perfer if the
+ * guest only uses the low 19 PID bits.
*/
- mmu_base_pid = 1 << (mmu_pid_bits - 1);
-#else
- mmu_base_pid = 1;
-#endif
- } else {
- /* The guest uses the bottom half of the PID space */
if (!mmu_pid_bits)
mmu_pid_bits = 19;
- mmu_base_pid = 1;
+ } else {
+ if (!mmu_pid_bits)
+ mmu_pid_bits = 20;
}
+ mmu_base_pid = 1;
/*
* Allocate Partition table and process table for the
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index 409e61210789..312236a6b085 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -1336,49 +1336,3 @@ void radix__flush_tlb_all(void)
: : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(0) : "memory");
asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
-
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
-{
- unsigned long pid = mm->context.id;
-
- if (unlikely(pid == MMU_NO_CONTEXT))
- return;
-
- if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
- return;
-
- /*
- * If this context hasn't run on that CPU before and KVM is
- * around, there's a slim chance that the guest on another
- * CPU just brought in obsolete translation into the TLB of
- * this CPU due to a bad prefetch using the guest PID on
- * the way into the hypervisor.
- *
- * We work around this here. If KVM is possible, we check if
- * any sibling thread is in KVM. If it is, the window may exist
- * and thus we flush that PID from the core.
- *
- * A potential future improvement would be to mark which PIDs
- * have never been used on the system and avoid it if the PID
- * is new and the process has no other cpumask bit set.
- */
- if (cpu_has_feature(CPU_FTR_HVMODE) && radix_enabled()) {
- int cpu = smp_processor_id();
- int sib = cpu_first_thread_sibling(cpu);
- bool flush = false;
-
- for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) {
- if (sib == cpu)
- continue;
- if (!cpu_possible(sib))
- continue;
- if (paca_ptrs[sib]->kvm_hstate.kvm_vcpu)
- flush = true;
- }
- if (flush)
- _tlbiel_pid(pid, RIC_FLUSH_ALL);
- }
-}
-EXPORT_SYMBOL_GPL(radix_kvm_prefetch_workaround);
-#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c
index 18f20da0d348..7479d39976c9 100644
--- a/arch/powerpc/mm/mmu_context.c
+++ b/arch/powerpc/mm/mmu_context.c
@@ -81,9 +81,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
if (cpu_has_feature(CPU_FTR_ALTIVEC))
asm volatile ("dssall");
- if (new_on_cpu)
- radix_kvm_prefetch_workaround(next);
- else
+ if (!new_on_cpu)
membarrier_arch_switch_mm(prev, next, tsk);
/*
--
2.23.0
^ permalink raw reply related
* [PATCH v6 38/48] KVM: PPC: Book3S HV: Remove support for dependent threads mode on P9
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
Radix guest support will be removed from the P7/8 path, so disallow
dependent threads mode on P9.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/kvm_host.h | 1 -
arch/powerpc/kvm/book3s_hv.c | 27 +++++----------------------
2 files changed, 5 insertions(+), 23 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index fa0083345b11..102928811da9 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -304,7 +304,6 @@ struct kvm_arch {
u8 fwnmi_enabled;
u8 secure_guest;
u8 svm_enabled;
- bool threads_indep;
bool nested_enable;
bool dawr1_enabled;
pgd_t *pgtable;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 21e13f93235a..20ced6c5edfd 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -103,13 +103,9 @@ static int target_smt_mode;
module_param(target_smt_mode, int, 0644);
MODULE_PARM_DESC(target_smt_mode, "Target threads per core (0 = max)");
-static bool indep_threads_mode = true;
-module_param(indep_threads_mode, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(indep_threads_mode, "Independent-threads mode (only on POWER9)");
-
static bool one_vm_per_core;
module_param(one_vm_per_core, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(one_vm_per_core, "Only run vCPUs from the same VM on a core (requires indep_threads_mode=N)");
+MODULE_PARM_DESC(one_vm_per_core, "Only run vCPUs from the same VM on a core (requires POWER8 or older)");
#ifdef CONFIG_KVM_XICS
static const struct kernel_param_ops module_param_ops = {
@@ -2264,7 +2260,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
*/
static int threads_per_vcore(struct kvm *kvm)
{
- if (kvm->arch.threads_indep)
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
return 1;
return threads_per_subcore;
}
@@ -4360,7 +4356,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
do {
- if (kvm->arch.threads_indep && kvm_is_radix(kvm))
+ if (kvm_is_radix(kvm))
r = kvmhv_run_single_vcpu(vcpu, ~(u64)0,
vcpu->arch.vcore->lpcr);
else
@@ -4984,21 +4980,8 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
/*
* Track that we now have a HV mode VM active. This blocks secondary
* CPU threads from coming online.
- * On POWER9, we only need to do this if the "indep_threads_mode"
- * module parameter has been set to N.
*/
- if (cpu_has_feature(CPU_FTR_ARCH_300)) {
- if (!indep_threads_mode && !cpu_has_feature(CPU_FTR_HVMODE)) {
- pr_warn("KVM: Ignoring indep_threads_mode=N in nested hypervisor\n");
- kvm->arch.threads_indep = true;
- } else if (!indep_threads_mode && cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
- pr_warn("KVM: Ignoring indep_threads_mode=N on pre-DD2.2 POWER9\n");
- kvm->arch.threads_indep = true;
- } else {
- kvm->arch.threads_indep = indep_threads_mode;
- }
- }
- if (!kvm->arch.threads_indep)
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
kvm_hv_vm_activated();
/*
@@ -5039,7 +5022,7 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
{
debugfs_remove_recursive(kvm->arch.debugfs_dir);
- if (!kvm->arch.threads_indep)
+ if (!cpu_has_feature(CPU_FTR_ARCH_300))
kvm_hv_vm_deactivated();
kvmppc_free_vcores(kvm);
--
2.23.0
^ permalink raw reply related
* [PATCH v6 39/48] KVM: PPC: Book3S HV: Remove radix guest support from P7/8 path
From: Nicholas Piggin @ 2021-04-05 1:19 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, Nicholas Piggin
In-Reply-To: <20210405011948.675354-1-npiggin@gmail.com>
The P9 path now runs all supported radix guest combinations, so
remove radix guest support from the P7/8 path.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kernel/asm-offsets.c | 1 -
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 103 +-----------------------
2 files changed, 3 insertions(+), 101 deletions(-)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index f3a662201a9f..0da926258ab2 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -551,7 +551,6 @@ int main(void)
OFFSET(VCPU_SLB_NR, kvm_vcpu, arch.slb_nr);
OFFSET(VCPU_FAULT_DSISR, kvm_vcpu, arch.fault_dsisr);
OFFSET(VCPU_FAULT_DAR, kvm_vcpu, arch.fault_dar);
- OFFSET(VCPU_FAULT_GPA, kvm_vcpu, arch.fault_gpa);
OFFSET(VCPU_INTR_MSR, kvm_vcpu, arch.intr_msr);
OFFSET(VCPU_LAST_INST, kvm_vcpu, arch.last_inst);
OFFSET(VCPU_TRAP, kvm_vcpu, arch.trap);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 9fd7e9e7fda6..87fa8bda3515 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -133,15 +133,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
/* Return the trap number on this thread as the return value */
mr r3, r12
- /*
- * If we came back from the guest via a relocation-on interrupt,
- * we will be in virtual mode at this point, which makes it a
- * little easier to get back to the caller.
- */
- mfmsr r0
- andi. r0, r0, MSR_IR /* in real mode? */
- bne .Lvirt_return
-
/* RFI into the highmem handler */
mfmsr r6
li r0, MSR_RI
@@ -151,11 +142,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
mtsrr1 r7
RFI_TO_KERNEL
- /* Virtual-mode return */
-.Lvirt_return:
- mtlr r8
- blr
-
kvmppc_primary_no_guest:
/* We handle this much like a ceded vcpu */
/* put the HDEC into the DEC, since HDEC interrupts don't wake us */
@@ -899,11 +885,6 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
cmpdi r3, 512 /* 1 microsecond */
blt hdec_soon
- ld r6, VCPU_KVM(r4)
- lbz r0, KVM_RADIX(r6)
- cmpwi r0, 0
- bne 9f
-
/* For hash guest, clear out and reload the SLB */
BEGIN_MMU_FTR_SECTION
/* Radix host won't have populated the SLB, so no need to clear */
@@ -1091,12 +1072,8 @@ BEGIN_FTR_SECTION
mtspr SPRN_HDSISR, r0
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
- ld r6, VCPU_KVM(r4)
- lbz r7, KVM_SECURE_GUEST(r6)
- cmpdi r7, 0
ld r6, VCPU_GPR(R6)(r4)
ld r7, VCPU_GPR(R7)(r4)
- bne ret_to_ultra
ld r0, VCPU_CR(r4)
mtcr r0
@@ -1107,26 +1084,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
ld r4, VCPU_GPR(R4)(r4)
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 loaded, except:
- * R0 = hcall result
- * R2 = SRR1, so UV can detect a synthesized interrupt (if any)
- * R3 = UV_RETURN
- */
-ret_to_ultra:
- ld r0, VCPU_CR(r4)
- mtcr r0
-
- ld r0, VCPU_GPR(R3)(r4)
- mfspr r2, SPRN_SRR1
- li r3, 0
- ori r3, r3, UV_RETURN
- ld r4, VCPU_GPR(R4)(r4)
- sc 2
secondary_too_late:
li r12, 0
@@ -1389,11 +1346,7 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
patch_site 1b patch__call_kvm_flush_link_stack
/* For hash guest, read the guest SLB and save it away */
- ld r5, VCPU_KVM(r9)
- lbz r0, KVM_RADIX(r5)
li r5, 0
- cmpwi r0, 0
- bne 0f /* for radix, save 0 entries */
lwz r0,VCPU_SLB_NR(r9) /* number of entries in SLB */
mtctr r0
li r6,0
@@ -1432,23 +1385,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
slbmte r6,r5
1: addi r8,r8,16
.endr
- b guest_bypass
-
-0: /*
- * 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
- stw r0,VCPU_SLB_MAX(r9)
- slbmte r0,r0
- li r4,1
- slbmte r0,r4
- li r4,2
- slbmte r0,r4
- li r4,3
- slbmte r0,r4
guest_bypass:
stw r12, STACK_SLOT_TRAP(r1)
@@ -1694,24 +1630,6 @@ BEGIN_FTR_SECTION
mtspr SPRN_PID, r7
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-#ifdef CONFIG_PPC_RADIX_MMU
- /*
- * Are we running hash or radix ?
- */
- ld r5, VCPU_KVM(r9)
- lbz r0, KVM_RADIX(r5)
- cmpwi cr2, r0, 0
- beq cr2, 2f
-
- /*
- * Radix: do eieio; tlbsync; ptesync sequence in case we
- * interrupted the guest between a tlbie and a ptesync.
- */
- eieio
- tlbsync
- ptesync
-#endif /* CONFIG_PPC_RADIX_MMU */
-
/*
* cp_abort is required if the processor supports local copy-paste
* to clear the copy buffer that was under control of the guest.
@@ -1970,8 +1888,6 @@ kvmppc_tm_emul:
* reflect the HDSI to the guest as a DSI.
*/
kvmppc_hdsi:
- ld r3, VCPU_KVM(r9)
- lbz r0, KVM_RADIX(r3)
mfspr r4, SPRN_HDAR
mfspr r6, SPRN_HDSISR
BEGIN_FTR_SECTION
@@ -1979,8 +1895,6 @@ BEGIN_FTR_SECTION
cmpdi r6, 0x7fff
beq 6f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
- cmpwi r0, 0
- bne .Lradix_hdsi /* on radix, just save DAR/DSISR/ASDR */
/* HPTE not found fault or protection fault? */
andis. r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h
beq 1f /* if not, send it to the guest */
@@ -2057,23 +1971,11 @@ fast_interrupt_c_return:
stb r0, HSTATE_IN_GUEST(r13)
b guest_exit_cont
-.Lradix_hdsi:
- std r4, VCPU_FAULT_DAR(r9)
- stw r6, VCPU_FAULT_DSISR(r9)
-.Lradix_hisi:
- mfspr r5, SPRN_ASDR
- std r5, VCPU_FAULT_GPA(r9)
- b guest_exit_cont
-
/*
* Similarly for an HISI, reflect it to the guest as an ISI unless
* it is an HPTE not found fault for a page that we have paged out.
*/
kvmppc_hisi:
- ld r3, VCPU_KVM(r9)
- lbz r0, KVM_RADIX(r3)
- cmpwi r0, 0
- bne .Lradix_hisi /* for radix, just save ASDR */
andis. r0, r11, SRR1_ISI_NOPT@h
beq 1f
andi. r0, r11, MSR_IR /* instruction relocation enabled? */
@@ -3217,15 +3119,16 @@ BEGIN_FTR_SECTION
mtspr SPRN_DAWRX1, r0
END_FTR_SECTION_IFSET(CPU_FTR_DAWR1)
- /* Clear hash and radix guest SLB. */
+ /* Clear guest SLB. */
slbmte r0, r0
PPC_SLBIA(6)
+ ptesync
BEGIN_MMU_FTR_SECTION
b 4f
END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
- ptesync
+ /* load host SLB entries */
ld r8, PACA_SLBSHADOWPTR(r13)
.rept SLB_NUM_BOLTED
li r3, SLBSHADOW_SAVEAREA
--
2.23.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox