openkylin
/
linux
mirror of https://gitee.com/openkylin/linux.git
9
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'topic/ppc-kvm' into next 

Merge some powerpc KVM patches from our topic branch.

In particular this brings in Nick's big series rewriting parts of the
guest entry/exit path in C.

Conflicts:
	arch/powerpc/kernel/security.c
	arch/powerpc/kvm/book3s_hv_rmhandlers.S
This commit is contained in:
Michael Ellerman 2021-06-17 16:51:38 +10:00
parent 07d8ad6fd8 fae5c9f366
commit 3c53642324
31 changed files with 1594 additions and 1525 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
arch/powerpc/include/asm/asm-prototypes.h
View File

@ -120,6 +120,7 @@ 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;
@ -140,7 +141,7 @@ 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,

13
arch/powerpc/include/asm/exception-64s.h
View File

@ -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
*/

1
arch/powerpc/include/asm/kvm_asm.h
View File

@ -147,6 +147,7 @@
#define KVM_GUEST_MODE_SKIP 2
#define KVM_GUEST_MODE_GUEST_HV 3
#define KVM_GUEST_MODE_HOST_HV 4
#define KVM_GUEST_MODE_HV_P9 5 /* ISA >= v3.0 path */
#define KVM_INST_FETCH_FAILED -1

8
arch/powerpc/include/asm/kvm_book3s_64.h
View File

@ -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, u64 time_limit, unsigned long lpcr);
#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

8
arch/powerpc/include/asm/kvm_host.h
View File

@ -297,7 +297,6 @@ struct kvm_arch {
u8 fwnmi_enabled;
u8 secure_guest;
u8 svm_enabled;
bool threads_indep;
bool nested_enable;
bool dawr1_enabled;
pgd_t *pgtable;
@ -683,7 +682,12 @@ 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

18
arch/powerpc/include/asm/kvm_ppc.h
View File

@ -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);
@ -606,6 +607,7 @@ 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,
@ -638,6 +640,8 @@ 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
@ -655,8 +659,6 @@ extern int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server,
u32 *priority);
extern int kvmppc_xive_int_on(struct kvm *kvm, u32 irq);
extern int kvmppc_xive_int_off(struct kvm *kvm, u32 irq);
extern void kvmppc_xive_init_module(void);
extern void kvmppc_xive_exit_module(void);
extern int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
struct kvm_vcpu *vcpu, u32 cpu);
@ -671,6 +673,8 @@ 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);
extern void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu);
static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
{
@ -680,8 +684,6 @@ static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
extern int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
struct kvm_vcpu *vcpu, u32 cpu);
extern void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu);
extern void kvmppc_xive_native_init_module(void);
extern void kvmppc_xive_native_exit_module(void);
extern int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu,
union kvmppc_one_reg *val);
extern int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu,
@ -695,8 +697,6 @@ static inline int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server,
u32 *priority) { return -1; }
static inline int kvmppc_xive_int_on(struct kvm *kvm, u32 irq) { return -1; }
static inline int kvmppc_xive_int_off(struct kvm *kvm, u32 irq) { return -1; }
static inline void kvmppc_xive_init_module(void) { }
static inline void kvmppc_xive_exit_module(void) { }
static inline int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; }
@ -711,14 +711,14 @@ 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 void kvmppc_xive_rearm_escalation(struct kvm_vcpu *vcpu) { }
static inline int kvmppc_xive_enabled(struct kvm_vcpu *vcpu)
{ return 0; }
static inline int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; }
static inline void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu) { }
static inline void kvmppc_xive_native_init_module(void) { }
static inline void kvmppc_xive_native_exit_module(void) { }
static inline int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu,
union kvmppc_one_reg *val)
{ return 0; }
@ -754,7 +754,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
unsigned long tce_value, unsigned long npages);
long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target,
unsigned int yield_count);
long kvmppc_h_random(struct kvm_vcpu *vcpu);
long kvmppc_rm_h_random(struct kvm_vcpu *vcpu);
void kvmhv_commence_exit(int trap);
void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu);
void kvmppc_subcore_enter_guest(void);

6
arch/powerpc/include/asm/mmu_context.h
View File

@ -121,12 +121,6 @@ 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);

12
arch/powerpc/include/asm/time.h
View File

@ -97,6 +97,18 @@ extern void div128_by_32(u64 dividend_high, u64 dividend_low,
extern void secondary_cpu_time_init(void);
extern void __init time_init(void);
#ifdef CONFIG_PPC64
static inline unsigned long test_irq_work_pending(void)
{
unsigned long x;
asm volatile("lbz %0,%1(13)"
: "=r" (x)
: "i" (offsetof(struct paca_struct, irq_work_pending)));
return x;
}
#endif
DECLARE_PER_CPU(u64, decrementers_next_tb);
/* Convert timebase ticks to nanoseconds */

1
arch/powerpc/kernel/asm-offsets.c
View File

@ -473,7 +473,6 @@ 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);

250
arch/powerpc/kernel/exceptions-64s.S
View File

@ -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.
*
@ -133,7 +117,6 @@ name:
#define IBRANCH_TO_COMMON .L_IBRANCH_TO_COMMON_\name\() /* ENTRY branch to common */
#define IREALMODE_COMMON .L_IREALMODE_COMMON_\name\() /* Common runs in realmode */
#define IMASK .L_IMASK_\name\() /* IRQ soft-mask bit */
#define IKVM_SKIP .L_IKVM_SKIP_\name\() /* Generate KVM skip handler */
#define IKVM_REAL .L_IKVM_REAL_\name\() /* Real entry tests KVM */
#define __IKVM_REAL(name) .L_IKVM_REAL_ ## name
#define IKVM_VIRT .L_IKVM_VIRT_\name\() /* Virt entry tests KVM */
@ -190,9 +173,6 @@ do_define_int n
.ifndef IMASK
IMASK=0
.endif
.ifndef IKVM_SKIP
IKVM_SKIP=0
.endif
.ifndef IKVM_REAL
IKVM_REAL=0
.endif
@ -207,8 +187,6 @@ do_define_int n
.endif
.endm
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
/*
* All interrupts which set HSRR registers, as well as SRESET and MCE and
* syscall when invoked with "sc 1" switch to MSR[HV]=1 (HVMODE) to be taken,
@ -238,88 +216,28 @@ do_define_int n
/*
* If an interrupt is taken while a guest is running, it is immediately routed
* to KVM to handle. If both HV and PR KVM arepossible, KVM interrupts go first
* to kvmppc_interrupt_hv, which handles the PR guest case.
* to KVM to handle.
*/
#define kvmppc_interrupt kvmppc_interrupt_hv
#else
#define kvmppc_interrupt kvmppc_interrupt_pr
#endif
.macro KVMTEST name
.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:
.if IKVM_SKIP
cmpwi r10,KVM_GUEST_MODE_SKIP
beq 89f
.else
BEGIN_FTR_SECTION
ld r10,IAREA+EX_CFAR(r13)
std r10,HSTATE_CFAR(r13)
END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
.endif
ld r10,IAREA+EX_CTR(r13)
mtctr r10
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
.if IKVM_SKIP
89: mtocrf 0x80,r9
ld r10,IAREA+EX_CTR(r13)
mtctr r10
ld r9,IAREA+EX_R9(r13)
ld r10,IAREA+EX_R10(r13)
ld r11,IAREA+EX_R11(r13)
ld r12,IAREA+EX_R12(r13)
.if IHSRR_IF_HVMODE
BEGIN_FTR_SECTION
b kvmppc_skip_Hinterrupt
FTR_SECTION_ELSE
b kvmppc_skip_interrupt
ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
.elseif IHSRR
b kvmppc_skip_Hinterrupt
.else
b kvmppc_skip_interrupt
.endif
.endif
.endm
#else
.macro KVMTEST name
.endm
.macro GEN_KVM name
.endm
bne \handler
#endif
.endm
/*
* This is the BOOK3S interrupt entry code macro.
@ -461,7 +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 */
@ -484,7 +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 */
@ -498,7 +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
@ -1000,8 +918,6 @@ EXC_COMMON_BEGIN(system_reset_common)
EXCEPTION_RESTORE_REGS
RFI_TO_USER_OR_KERNEL
GEN_KVM system_reset
/**
* Interrupt 0x200 - Machine Check Interrupt (MCE).
@ -1070,7 +986,6 @@ INT_DEFINE_BEGIN(machine_check)
ISET_RI=0
IDAR=1
IDSISR=1
IKVM_SKIP=1
IKVM_REAL=1
INT_DEFINE_END(machine_check)
@ -1166,7 +1081,7 @@ 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)
@ -1236,8 +1151,6 @@ EXC_COMMON_BEGIN(machine_check_common)
bl machine_check_exception
b interrupt_return
GEN_KVM machine_check
#ifdef CONFIG_PPC_P7_NAP
/*
@ -1342,7 +1255,6 @@ INT_DEFINE_BEGIN(data_access)
IVEC=0x300
IDAR=1
IDSISR=1
IKVM_SKIP=1
IKVM_REAL=1
INT_DEFINE_END(data_access)
@ -1373,8 +1285,6 @@ 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).
@ -1396,7 +1306,6 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
INT_DEFINE_BEGIN(data_access_slb)
IVEC=0x380
IDAR=1
IKVM_SKIP=1
IKVM_REAL=1
INT_DEFINE_END(data_access_slb)
@ -1425,8 +1334,6 @@ 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).
@ -1463,8 +1370,6 @@ 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).
@ -1509,8 +1414,6 @@ 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.
@ -1555,8 +1458,6 @@ EXC_COMMON_BEGIN(hardware_interrupt_common)
bl do_IRQ
b interrupt_return
GEN_KVM hardware_interrupt
/**
* Interrupt 0x600 - Alignment Interrupt
@ -1584,8 +1485,6 @@ 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).
@ -1693,8 +1592,6 @@ 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.
@ -1744,8 +1641,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
b interrupt_return
#endif
GEN_KVM fp_unavailable
/**
* Interrupt 0x900 - Decrementer Interrupt.
@ -1784,8 +1679,6 @@ EXC_COMMON_BEGIN(decrementer_common)
bl timer_interrupt
b interrupt_return
GEN_KVM decrementer
/**
* Interrupt 0x980 - Hypervisor Decrementer Interrupt.
@ -1831,8 +1724,6 @@ EXC_COMMON_BEGIN(hdecrementer_common)
ld r13,PACA_EXGEN+EX_R13(r13)
HRFI_TO_KERNEL
GEN_KVM hdecrementer
/**
* Interrupt 0xa00 - Directed Privileged Doorbell Interrupt.
@ -1872,8 +1763,6 @@ EXC_COMMON_BEGIN(doorbell_super_common)
#endif
b interrupt_return
GEN_KVM doorbell_super
EXC_REAL_NONE(0xb00, 0x100)
EXC_VIRT_NONE(0x4b00, 0x100)
@ -1923,7 +1812,7 @@ 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
@ -1979,14 +1868,16 @@ 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)
/*
* This is a hcall, so register convention is as above, with these
* differences:
* r13 = PACA
* ctr = orig r13
* orig r10 saved in PACA
*/
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
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
@ -1994,31 +1885,24 @@ TRAMP_REAL_BEGIN(system_call_kvm)
*/
BEGIN_FTR_SECTION
mfspr r10,SPRN_PPR
std r10,HSTATE_PPR(r13)
std r10,PACA_EXGEN+EX_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
#ifdef CONFIG_RELOCATABLE
/*
* Requires __LOAD_FAR_HANDLER beause kvmppc_interrupt lives
* Requires __LOAD_FAR_HANDLER beause kvmppc_hcall lives
* outside the head section.
*/
__LOAD_FAR_HANDLER(r10, kvmppc_interrupt)
__LOAD_FAR_HANDLER(r10, kvmppc_hcall)
mtctr r10
ld r10,PACA_EXGEN+EX_R10(r13)
bctr
#else
ld r10,PACA_EXGEN+EX_R10(r13)
b kvmppc_interrupt
b kvmppc_hcall
#endif
#endif
/**
* Interrupt 0xd00 - Trace Interrupt.
* This is a synchronous interrupt in response to instruction step or
@ -2043,8 +1927,6 @@ EXC_COMMON_BEGIN(single_step_common)
bl single_step_exception
b interrupt_return
GEN_KVM single_step
/**
* Interrupt 0xe00 - Hypervisor Data Storage Interrupt (HDSI).
@ -2063,7 +1945,6 @@ INT_DEFINE_BEGIN(h_data_storage)
IHSRR=1
IDAR=1
IDSISR=1
IKVM_SKIP=1
IKVM_REAL=1
IKVM_VIRT=1
INT_DEFINE_END(h_data_storage)
@ -2084,8 +1965,6 @@ 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).
@ -2111,8 +1990,6 @@ EXC_COMMON_BEGIN(h_instr_storage_common)
bl unknown_exception
b interrupt_return
GEN_KVM h_instr_storage
/**
* Interrupt 0xe40 - Hypervisor Emulation Assistance Interrupt.
@ -2137,8 +2014,6 @@ 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).
@ -2210,16 +2085,12 @@ 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
addi r3,r1,STACK_FRAME_OVERHEAD
bl handle_hmi_exception
b interrupt_return
GEN_KVM hmi_exception
/**
* Interrupt 0xe80 - Directed Hypervisor Doorbell Interrupt.
@ -2250,8 +2121,6 @@ EXC_COMMON_BEGIN(h_doorbell_common)
#endif
b interrupt_return
GEN_KVM h_doorbell
/**
* Interrupt 0xea0 - Hypervisor Virtualization Interrupt.
@ -2278,8 +2147,6 @@ 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)
@ -2323,8 +2190,6 @@ EXC_COMMON_BEGIN(performance_monitor_common)
bl performance_monitor_exception
b interrupt_return
GEN_KVM performance_monitor
/**
* Interrupt 0xf20 - Vector Unavailable Interrupt.
@ -2374,8 +2239,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
bl altivec_unavailable_exception
b interrupt_return
GEN_KVM altivec_unavailable
/**
* Interrupt 0xf40 - VSX Unavailable Interrupt.
@ -2424,8 +2287,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
bl vsx_unavailable_exception
b interrupt_return
GEN_KVM vsx_unavailable
/**
* Interrupt 0xf60 - Facility Unavailable Interrupt.
@ -2454,8 +2315,6 @@ 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.
@ -2484,8 +2343,6 @@ 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)
@ -2515,8 +2372,6 @@ 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)
@ -2548,8 +2403,6 @@ 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)
@ -2670,8 +2523,6 @@ 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)
@ -2689,8 +2540,6 @@ 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)
@ -2721,8 +2570,6 @@ EXC_COMMON_BEGIN(altivec_assist_common)
#endif
b interrupt_return
GEN_KVM altivec_assist
#ifdef CONFIG_CBE_RAS
INT_DEFINE_BEGIN(cbe_thermal)
@ -2740,8 +2587,6 @@ 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)
@ -2994,6 +2839,15 @@ 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
@ -3009,32 +2863,6 @@ EXPORT_SYMBOL(do_uaccess_flush)
MASKED_INTERRUPT
MASKED_INTERRUPT hsrr=1
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
kvmppc_skip_interrupt:
/*
* Here all GPRs are unchanged from when the interrupt happened
* except for r13, which is saved in SPRG_SCRATCH0.
*/
mfspr r13, SPRN_SRR0
addi r13, r13, 4
mtspr SPRN_SRR0, r13
GET_SCRATCH0(r13)
RFI_TO_KERNEL
b .
kvmppc_skip_Hinterrupt:
/*
* Here all GPRs are unchanged from when the interrupt happened
* except for r13, which is saved in SPRG_SCRATCH0.
*/
mfspr r13, SPRN_HSRR0
addi r13, r13, 4
mtspr SPRN_HSRR0, r13
GET_SCRATCH0(r13)
HRFI_TO_KERNEL
b .
#endif
/*
* Relocation-on interrupts: A subset of the interrupts can be delivered
* with IR=1/DR=1, if AIL==2 and MSR.HV won't be changed by delivering

5
arch/powerpc/kernel/security.c
View File

@ -432,16 +432,19 @@ 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_RAW_NOP()));
patch_instruction_site(site2, ppc_inst(PPC_RAW_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

10
arch/powerpc/kernel/time.c
View File

@ -508,16 +508,6 @@ EXPORT_SYMBOL(profile_pc);
* 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable...
*/
#ifdef CONFIG_PPC64
static inline unsigned long test_irq_work_pending(void)
{
unsigned long x;
asm volatile("lbz %0,%1(13)"
: "=r" (x)
: "i" (offsetof(struct paca_struct, irq_work_pending)));
return x;
}
static inline void set_irq_work_pending_flag(void)
{
asm volatile("stb %0,%1(13)" : :

2
arch/powerpc/kvm/Makefile
View File

@ -57,6 +57,7 @@ kvm-pr-y := \
book3s_32_mmu.o
kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
book3s_64_entry.o \
tm.o
ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
@ -86,6 +87,7 @@ kvm-book3s_64-builtin-tm-objs-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \
ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
book3s_hv_hmi.o \
book3s_hv_p9_entry.o \
book3s_hv_rmhandlers.o \
book3s_hv_rm_mmu.o \
book3s_hv_ras.o \

17
arch/powerpc/kvm/book3s.c
View File

@ -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 */
@ -1044,13 +1050,10 @@ static int kvmppc_book3s_init(void)
#ifdef CONFIG_KVM_XICS
#ifdef CONFIG_KVM_XIVE
if (xics_on_xive()) {
kvmppc_xive_init_module();
kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS);
if (kvmppc_xive_native_supported()) {
kvmppc_xive_native_init_module();
if (kvmppc_xive_native_supported())
kvm_register_device_ops(&kvm_xive_native_ops,
KVM_DEV_TYPE_XIVE);
}
} else
#endif
kvm_register_device_ops(&kvm_xics_ops, KVM_DEV_TYPE_XICS);
@ -1060,12 +1063,6 @@ static int kvmppc_book3s_init(void)
static void kvmppc_book3s_exit(void)
{
#ifdef CONFIG_KVM_XICS
if (xics_on_xive()) {
kvmppc_xive_exit_module();
kvmppc_xive_native_exit_module();
}
#endif
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
kvmppc_book3s_exit_pr();
#endif

416
arch/powerpc/kvm/book3s_64_entry.S Normal file
View File

@ -0,0 +1,416 @@
/* 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
* 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:
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
lbz r10,HSTATE_IN_GUEST(r13)
cmpwi r10,KVM_GUEST_MODE_HV_P9
beq kvmppc_p9_exit_hcall
#endif
ld r10,PACA_EXGEN+EX_R13(r13)
SET_SCRATCH0(r10)
li r10,0xc00
/* Now we look like kvmppc_interrupt */
li r11,PACA_EXGEN
b .Lgot_save_area
/*
* KVM interrupt entry occurs after GEN_INT_ENTRY runs, and follows that
* 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:
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
std r10,HSTATE_SCRATCH0(r13)
lbz r10,HSTATE_IN_GUEST(r13)
cmpwi r10,KVM_GUEST_MODE_HV_P9
beq kvmppc_p9_exit_interrupt
ld r10,HSTATE_SCRATCH0(r13)
#endif
li r11,PACA_EXGEN
cmpdi r10,0x200
bgt+ .Lgot_save_area
li r11,PACA_EXMC
beq .Lgot_save_area
li r11,PACA_EXNMI
.Lgot_save_area:
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)
/*
* 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 HSTATE_SCRATCH0
* guest R13 saved in SPRN_SCRATCH0
*/
std r9,HSTATE_SCRATCH2(r13)
lbz r9,HSTATE_IN_GUEST(r13)
cmpwi r9,KVM_GUEST_MODE_SKIP
beq- .Lmaybe_skip
.Lno_skip:
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
cmpwi r9,KVM_GUEST_MODE_GUEST
beq kvmppc_interrupt_pr
#endif
b kvmppc_interrupt_hv
#else
b kvmppc_interrupt_pr
#endif
/*
* "Skip" interrupts are part of a trick KVM uses a with hash guests to load
* the faulting instruction in guest memory from the the hypervisor without
* walking page tables.
*
* When the guest takes a fault that requires the hypervisor to load the
* instruction (e.g., MMIO emulation), KVM is running in real-mode with HV=1
* and the guest MMU context loaded. It sets KVM_GUEST_MODE_SKIP, and sets
* MSR[DR]=1 while leaving MSR[IR]=0, so it continues to fetch HV instructions
* but loads and stores will access the guest context. This is used to load
* the faulting instruction using the faulting guest effective address.
*
* However the guest context may not be able to translate, or it may cause a
* machine check or other issue, which results in a fault in the host
* (even with KVM-HV).
*
* These faults come here because KVM_GUEST_MODE_SKIP was set, so if they
* are (or are likely) caused by that load, the instruction is skipped by
* just returning with the PC advanced +4, where it is noticed the load did
* not execute and it goes to the slow path which walks the page tables to
* read guest memory.
*/
.Lmaybe_skip:
cmpwi r12,BOOK3S_INTERRUPT_MACHINE_CHECK
beq 1f
cmpwi r12,BOOK3S_INTERRUPT_DATA_STORAGE
beq 1f
cmpwi r12,BOOK3S_INTERRUPT_DATA_SEGMENT
beq 1f
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
/* HSRR interrupts get 2 added to interrupt number */
cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE | 0x2
beq 2f
#endif
b .Lno_skip
1: mfspr r9,SPRN_SRR0
addi r9,r9,4
mtspr SPRN_SRR0,r9
ld r12,HSTATE_SCRATCH0(r13)
ld r9,HSTATE_SCRATCH2(r13)
GET_SCRATCH0(r13)
RFI_TO_KERNEL
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
2: mfspr r9,SPRN_HSRR0
addi r9,r9,4
mtspr SPRN_HSRR0,r9
ld r12,HSTATE_SCRATCH0(r13)
ld r9,HSTATE_SCRATCH2(r13)
GET_SCRATCH0(r13)
HRFI_TO_KERNEL
#endif
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
/* Stack frame offsets for kvmppc_p9_enter_guest */
#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.
*/
.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_HV_P9 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:
BEGIN_MMU_FTR_SECTION
/*
* Hash host doesn't try to recover MMU (requires host SLB reload)
*/
b .
END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
/*
* 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
/*
* 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
/*
* Go back to interrupt handler. MCE and SRESET have their specific
* PACA save area so they should be used directly. They set up their
* own stack. The other handlers all use EXGEN. They will use the
* guest r1 if it looks like a kernel stack, so just load the
* emergency stack and go to program check for all other interrupts.
*/
ld r10,HSTATE_SCRATCH0(r13)
cmpwi r10,BOOK3S_INTERRUPT_MACHINE_CHECK
beq machine_check_common
cmpwi r10,BOOK3S_INTERRUPT_SYSTEM_RESET
beq system_reset_common
b .
#endif

12
arch/powerpc/kvm/book3s_64_vio_hv.c
View File

@ -391,10 +391,6 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
/* liobn, ioba, tce); */
/* For radix, we might be in virtual mode, so punt */
if (kvm_is_radix(vcpu->kvm))
return H_TOO_HARD;
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
@ -489,10 +485,6 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
bool prereg = false;
struct kvmppc_spapr_tce_iommu_table *stit;
/* For radix, we might be in virtual mode, so punt */
if (kvm_is_radix(vcpu->kvm))
return H_TOO_HARD;
/*
* used to check for invalidations in progress
*/
@ -602,10 +594,6 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
long i, ret;
struct kvmppc_spapr_tce_iommu_table *stit;
/* For radix, we might be in virtual mode, so punt */
if (kvm_is_radix(vcpu->kvm))
return H_TOO_HARD;
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;

712
arch/powerpc/kvm/book3s_hv.c
View File

File diff suppressed because it is too large Load Diff

135
arch/powerpc/kvm/book3s_hv_builtin.c
View File

@ -34,21 +34,6 @@
#include "book3s_xics.h"
#include "book3s_xive.h"
/*
* The XIVE module will populate these when it loads
*/
unsigned long (*__xive_vm_h_xirr)(struct kvm_vcpu *vcpu);
unsigned long (*__xive_vm_h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server);
int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
unsigned long mfrr);
int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr);
int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
EXPORT_SYMBOL_GPL(__xive_vm_h_xirr);
EXPORT_SYMBOL_GPL(__xive_vm_h_ipoll);
EXPORT_SYMBOL_GPL(__xive_vm_h_ipi);
EXPORT_SYMBOL_GPL(__xive_vm_h_cppr);
EXPORT_SYMBOL_GPL(__xive_vm_h_eoi);
/*
* Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
* should be power of 2.
@ -196,16 +181,9 @@ int kvmppc_hwrng_present(void)
}
EXPORT_SYMBOL_GPL(kvmppc_hwrng_present);
long kvmppc_h_random(struct kvm_vcpu *vcpu)
long kvmppc_rm_h_random(struct kvm_vcpu *vcpu)
{
int r;
/* Only need to do the expensive mfmsr() on radix */
if (kvm_is_radix(vcpu->kvm) && (mfmsr() & MSR_IR))
r = powernv_get_random_long(&vcpu->arch.regs.gpr[4]);
else
r = powernv_get_random_real_mode(&vcpu->arch.regs.gpr[4]);
if (r)
if (powernv_get_random_real_mode(&vcpu->arch.regs.gpr[4]))
return H_SUCCESS;
return H_HARDWARE;
@ -221,15 +199,6 @@ void kvmhv_rm_send_ipi(int cpu)
void __iomem *xics_phys;
unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
/* For a nested hypervisor, use the XICS via hcall */
if (kvmhv_on_pseries()) {
unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
plpar_hcall_raw(H_IPI, retbuf, get_hard_smp_processor_id(cpu),
IPI_PRIORITY);
return;
}
/* On POWER9 we can use msgsnd for any destination cpu. */
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
msg |= get_hard_smp_processor_id(cpu);
@ -442,19 +411,12 @@ static long kvmppc_read_one_intr(bool *again)
return 1;
/* Now read the interrupt from the ICP */
if (kvmhv_on_pseries()) {
unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
rc = plpar_hcall_raw(H_XIRR, retbuf, 0xFF);
xirr = cpu_to_be32(retbuf[0]);
} else {
xics_phys = local_paca->kvm_hstate.xics_phys;
rc = 0;
if (!xics_phys)
rc = opal_int_get_xirr(&xirr, false);
else
xirr = __raw_rm_readl(xics_phys + XICS_XIRR);
}
xics_phys = local_paca->kvm_hstate.xics_phys;
rc = 0;
if (!xics_phys)
rc = opal_int_get_xirr(&xirr, false);
else
xirr = __raw_rm_readl(xics_phys + XICS_XIRR);
if (rc < 0)
return 1;
@ -483,13 +445,7 @@ static long kvmppc_read_one_intr(bool *again)
*/
if (xisr == XICS_IPI) {
rc = 0;
if (kvmhv_on_pseries()) {
unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
plpar_hcall_raw(H_IPI, retbuf,
hard_smp_processor_id(), 0xff);
plpar_hcall_raw(H_EOI, retbuf, h_xirr);
} else if (xics_phys) {
if (xics_phys) {
__raw_rm_writeb(0xff, xics_phys + XICS_MFRR);
__raw_rm_writel(xirr, xics_phys + XICS_XIRR);
} else {
@ -515,13 +471,7 @@ static long kvmppc_read_one_intr(bool *again)
/* We raced with the host,
* we need to resend that IPI, bummer
*/
if (kvmhv_on_pseries()) {
unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
plpar_hcall_raw(H_IPI, retbuf,
hard_smp_processor_id(),
IPI_PRIORITY);
} else if (xics_phys)
if (xics_phys)
__raw_rm_writeb(IPI_PRIORITY,
xics_phys + XICS_MFRR);
else
@ -541,22 +491,13 @@ static long kvmppc_read_one_intr(bool *again)
}
#ifdef CONFIG_KVM_XICS
static inline bool is_rm(void)
{
return !(mfmsr() & MSR_DR);
}
unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu)
{
if (!kvmppc_xics_enabled(vcpu))
return H_TOO_HARD;
if (xics_on_xive()) {
if (is_rm())
return xive_rm_h_xirr(vcpu);
if (unlikely(!__xive_vm_h_xirr))
return H_NOT_AVAILABLE;
return __xive_vm_h_xirr(vcpu);
} else
if (xics_on_xive())
return xive_rm_h_xirr(vcpu);
else
return xics_rm_h_xirr(vcpu);
}
@ -565,13 +506,9 @@ unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu)
if (!kvmppc_xics_enabled(vcpu))
return H_TOO_HARD;
vcpu->arch.regs.gpr[5] = get_tb();
if (xics_on_xive()) {
if (is_rm())
return xive_rm_h_xirr(vcpu);
if (unlikely(!__xive_vm_h_xirr))
return H_NOT_AVAILABLE;
return __xive_vm_h_xirr(vcpu);
} else
if (xics_on_xive())
return xive_rm_h_xirr(vcpu);
else
return xics_rm_h_xirr(vcpu);
}
@ -579,13 +516,9 @@ unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server)
{
if (!kvmppc_xics_enabled(vcpu))
return H_TOO_HARD;
if (xics_on_xive()) {
if (is_rm())
return xive_rm_h_ipoll(vcpu, server);
if (unlikely(!__xive_vm_h_ipoll))
return H_NOT_AVAILABLE;
return __xive_vm_h_ipoll(vcpu, server);
} else
if (xics_on_xive())
return xive_rm_h_ipoll(vcpu, server);
else
return H_TOO_HARD;
}
@ -594,13 +527,9 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
{
if (!kvmppc_xics_enabled(vcpu))
return H_TOO_HARD;
if (xics_on_xive()) {
if (is_rm())
return xive_rm_h_ipi(vcpu, server, mfrr);
if (unlikely(!__xive_vm_h_ipi))
return H_NOT_AVAILABLE;
return __xive_vm_h_ipi(vcpu, server, mfrr);
} else
if (xics_on_xive())
return xive_rm_h_ipi(vcpu, server, mfrr);
else
return xics_rm_h_ipi(vcpu, server, mfrr);
}
@ -608,13 +537,9 @@ int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
{
if (!kvmppc_xics_enabled(vcpu))
return H_TOO_HARD;
if (xics_on_xive()) {
if (is_rm())
return xive_rm_h_cppr(vcpu, cppr);
if (unlikely(!__xive_vm_h_cppr))
return H_NOT_AVAILABLE;
return __xive_vm_h_cppr(vcpu, cppr);
} else
if (xics_on_xive())
return xive_rm_h_cppr(vcpu, cppr);
else
return xics_rm_h_cppr(vcpu, cppr);
}
@ -622,13 +547,9 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
{
if (!kvmppc_xics_enabled(vcpu))
return H_TOO_HARD;
if (xics_on_xive()) {
if (is_rm())
return xive_rm_h_eoi(vcpu, xirr);
if (unlikely(!__xive_vm_h_eoi))
return H_NOT_AVAILABLE;
return __xive_vm_h_eoi(vcpu, xirr);
} else
if (xics_on_xive())
return xive_rm_h_eoi(vcpu, xirr);
else
return xics_rm_h_eoi(vcpu, xirr);
}
#endif /* CONFIG_KVM_XICS */

9
arch/powerpc/kvm/book3s_hv_interrupts.S
View File

@ -58,7 +58,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
/*
* Put whatever is in the decrementer into the
* hypervisor decrementer.
* Because of a hardware deviation in P8 and P9,
* Because of a hardware deviation in P8,
* we need to set LPCR[HDICE] before writing HDEC.
*/
ld r5, HSTATE_KVM_VCORE(r13)
@ -67,15 +67,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
ori r8, r9, LPCR_HDICE
mtspr SPRN_LPCR, r8
isync
andis. r0, r9, LPCR_LD@h
mfspr r8,SPRN_DEC
mftb r7
BEGIN_FTR_SECTION
/* On POWER9, don't sign-extend if host LPCR[LD] bit is set */
bne 32f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
extsw r8,r8
32: mtspr SPRN_HDEC,r8
mtspr SPRN_HDEC,r8
add r8,r8,r7
std r8,HSTATE_DECEXP(r13)

508
arch/powerpc/kvm/book3s_hv_p9_entry.c Normal file
View File

@ -0,0 +1,508 @@
// 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>
#include <asm/ppc-opcode.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(u64 slbee, u64 slbev)
{
asm volatile("slbmte %0,%1" :: "r" (slbev), "r" (slbee));
}
static inline void clear_slb_entry(unsigned int idx)
{
mtslb(idx, 0);
}
static inline void slb_clear_invalidate_partition(void)
{
clear_slb_entry(0);
asm volatile(PPC_SLBIA(6));
}
/*
* 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)
{
int i;
for (i = 0; i < 4; i++)
clear_slb_entry(i);
}
static void switch_mmu_to_guest_radix(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpcr)
{
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();
}
static void switch_mmu_to_guest_hpt(struct kvm *kvm, struct kvm_vcpu *vcpu, u64 lpcr)
{
u32 lpid;
int i;
lpid = kvm->arch.lpid;
mtspr(SPRN_LPID, lpid);
mtspr(SPRN_LPCR, lpcr);
mtspr(SPRN_PID, vcpu->arch.pid);
for (i = 0; i < vcpu->arch.slb_max; i++)
mtslb(vcpu->arch.slb[i].orige, vcpu->arch.slb[i].origv);
isync();
}
static void switch_mmu_to_host(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();
if (!radix_enabled())
slb_restore_bolted_realmode();
}
static void save_clear_host_mmu(struct kvm *kvm)
{
if (!radix_enabled()) {
/*
* Hash host could save and restore host SLB entries to
* reduce SLB fault overheads of VM exits, but for now the
* existing code clears all entries and restores just the
* bolted ones when switching back to host.
*/
slb_clear_invalidate_partition();
}
}
static void save_clear_guest_mmu(struct kvm *kvm, struct kvm_vcpu *vcpu)
{
if (kvm_is_radix(kvm)) {
radix_clear_slb();
} else {
int i;
int nr = 0;
/*
* This must run before switching to host (radix host can't
* access all SLBs).
*/
for (i = 0; i < vcpu->arch.slb_nr; i++) {
u64 slbee, slbev;
mfslb(i, &slbee, &slbev);
if (slbee & SLB_ESID_V) {
vcpu->arch.slb[nr].orige = slbee | i;
vcpu->arch.slb[nr].origv = slbev;
nr++;
}
}
vcpu->arch.slb_max = nr;
slb_clear_invalidate_partition();
}
}
int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr)
{
struct kvm *kvm = vcpu->kvm;
struct kvm_nested_guest *nested = vcpu->arch.nested;
struct kvmppc_vcore *vc = vcpu->arch.vcore;
s64 hdec;
u64 tb, purr, spurr;
u64 *exsave;
bool ri_set;
int trap;
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;
hdec = time_limit - mftb();
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 = mftb() + 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;
}
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);
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_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);
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);
local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_HV_P9;
/*
* Hash host, hash guest, or radix guest with prefetch bug, all have
* to disable the MMU before switching to guest MMU state.
*/
if (!radix_enabled() || !kvm_is_radix(kvm) ||
cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
__mtmsrd(msr & ~(MSR_IR|MSR_DR|MSR_RI), 0);
save_clear_host_mmu(kvm);
if (kvm_is_radix(kvm)) {
switch_mmu_to_guest_radix(kvm, vcpu, lpcr);
if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
__mtmsrd(0, 1); /* clear RI */
} else {
switch_mmu_to_guest_hpt(kvm, vcpu, lpcr);
}
/* TLBIEL uses LPID=LPIDR, so run this after setting guest LPID */
kvmppc_check_need_tlb_flush(kvm, vc->pcpu, nested);
/*
* P9 suppresses the HDEC exception when LPCR[HDICE] = 0,
* so set guest LPCR (with HDICE) before writing HDEC.
*/
mtspr(SPRN_HDEC, hdec);
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);
kvmppc_p9_enter_guest(vcpu);
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;
/* 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;
} 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;
/*
* 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)];
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
}
accumulate_time(vcpu, &vcpu->arch.rm_exit);
/* 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);
}
if (kvm_is_radix(kvm)) {
/*
* 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;
}
mtspr(SPRN_HDEC, 0x7fffffff);
save_clear_guest_mmu(kvm, vcpu);
switch_mmu_to_host(kvm, host_pidr);
local_paca->kvm_hstate.in_guest = KVM_GUEST_MODE_NONE;
/*
* 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);
end_timing(vcpu);
return trap;
}
EXPORT_SYMBOL_GPL(kvmhv_vcpu_entry_p9);

12
arch/powerpc/kvm/book3s_hv_rm_mmu.c
View File

@ -46,6 +46,10 @@ static int global_invalidates(struct kvm *kvm)
else
global = 1;
/* LPID has been switched to host if in virt mode so can't do local */
if (!global && (mfmsr() & (MSR_IR|MSR_DR)))
global = 1;
if (!global) {
/* any other core might now have stale TLB entries... */
smp_wmb();
@ -398,6 +402,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
vcpu->arch.pgdir, true,
&vcpu->arch.regs.gpr[4]);
}
EXPORT_SYMBOL_GPL(kvmppc_h_enter);
#ifdef __BIG_ENDIAN__
#define LOCK_TOKEN (*(u32 *)(&get_paca()->lock_token))
@ -542,6 +547,7 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
return kvmppc_do_h_remove(vcpu->kvm, flags, pte_index, avpn,
&vcpu->arch.regs.gpr[4]);
}
EXPORT_SYMBOL_GPL(kvmppc_h_remove);
long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
{
@ -660,6 +666,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
return ret;
}
EXPORT_SYMBOL_GPL(kvmppc_h_bulk_remove);
long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
unsigned long pte_index, unsigned long avpn)
@ -730,6 +737,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
return H_SUCCESS;
}
EXPORT_SYMBOL_GPL(kvmppc_h_protect);
long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
unsigned long pte_index)
@ -770,6 +778,7 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
}
return H_SUCCESS;
}
EXPORT_SYMBOL_GPL(kvmppc_h_read);
long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags,
unsigned long pte_index)
@ -818,6 +827,7 @@ long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags,
unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
return ret;
}
EXPORT_SYMBOL_GPL(kvmppc_h_clear_ref);
long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
unsigned long pte_index)
@ -865,6 +875,7 @@ long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
return ret;
}
EXPORT_SYMBOL_GPL(kvmppc_h_clear_mod);
static int kvmppc_get_hpa(struct kvm_vcpu *vcpu, unsigned long mmu_seq,
unsigned long gpa, int writing, unsigned long *hpa,
@ -1283,3 +1294,4 @@ long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
return -1; /* send fault up to host kernel mode */
}
EXPORT_SYMBOL_GPL(kvmppc_hpte_hv_fault);

15
arch/powerpc/kvm/book3s_hv_rm_xics.c
View File

@ -141,13 +141,6 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
return;
}
if (xive_enabled() && kvmhv_on_pseries()) {
/* No XICS access or hypercalls available, too hard */
this_icp->rm_action |= XICS_RM_KICK_VCPU;
this_icp->rm_kick_target = vcpu;
return;
}
/*
* Check if the core is loaded,
* if not, find an available host core to post to wake the VCPU,
@ -771,14 +764,6 @@ static void icp_eoi(struct irq_chip *c, u32 hwirq, __be32 xirr, bool *again)
void __iomem *xics_phys;
int64_t rc;
if (kvmhv_on_pseries()) {
unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
iosync();
plpar_hcall_raw(H_EOI, retbuf, hwirq);
return;
}
rc = pnv_opal_pci_msi_eoi(c, hwirq);
if (rc)

684
arch/powerpc/kvm/book3s_hv_rmhandlers.S
View File

File diff suppressed because it is too large Load Diff

3
arch/powerpc/kvm/book3s_segment.S
View File

@ -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 */

113
arch/powerpc/kvm/book3s_xive.c
View File

@ -127,6 +127,71 @@ 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);
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
@ -2075,6 +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;
@ -2257,21 +2352,3 @@ struct kvm_device_ops kvm_xive_ops = {
.get_attr = xive_get_attr,
.has_attr = xive_has_attr,
};
void kvmppc_xive_init_module(void)
{
__xive_vm_h_xirr = xive_vm_h_xirr;
__xive_vm_h_ipoll = xive_vm_h_ipoll;
__xive_vm_h_ipi = xive_vm_h_ipi;
__xive_vm_h_cppr = xive_vm_h_cppr;
__xive_vm_h_eoi = xive_vm_h_eoi;
}
void kvmppc_xive_exit_module(void)
{
__xive_vm_h_xirr = NULL;
__xive_vm_h_ipoll = NULL;
__xive_vm_h_ipi = NULL;
__xive_vm_h_cppr = NULL;
__xive_vm_h_eoi = NULL;
}

7
arch/powerpc/kvm/book3s_xive.h
View File

@ -289,13 +289,6 @@ extern int xive_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
extern int xive_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
extern int xive_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr);
extern unsigned long (*__xive_vm_h_xirr)(struct kvm_vcpu *vcpu);
extern unsigned long (*__xive_vm_h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server);
extern int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
unsigned long mfrr);
extern int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr);
extern int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
/*
* Common Xive routines for XICS-over-XIVE and XIVE native
*/

10
arch/powerpc/kvm/book3s_xive_native.c
View File

@ -1281,13 +1281,3 @@ struct kvm_device_ops kvm_xive_native_ops = {
.has_attr = kvmppc_xive_native_has_attr,
.mmap = kvmppc_xive_native_mmap,
};
void kvmppc_xive_native_init_module(void)
{
;
}
void kvmppc_xive_native_exit_module(void)
{
;
}

27
arch/powerpc/mm/book3s64/radix_pgtable.c
View File

@ -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

46
arch/powerpc/mm/book3s64/radix_tlb.c
View File

@ -1344,49 +1344,3 @@ 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 */

4
arch/powerpc/mm/mmu_context.c
View File

@ -83,9 +83,7 @@ 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);
/*

52
arch/powerpc/platforms/powernv/idle.c
View File

@ -604,7 +604,7 @@ struct p9_sprs {
u64 uamor;
};
static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
static unsigned long power9_idle_stop(unsigned long psscr)
{
int cpu = raw_smp_processor_id();
int first = cpu_first_thread_sibling(cpu);
@ -620,8 +620,6 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
if (!(psscr & (PSSCR_EC|PSSCR_ESL))) {
/* EC=ESL=0 case */
BUG_ON(!mmu_on);
/*
* Wake synchronously. SRESET via xscom may still cause
* a 0x100 powersave wakeup with SRR1 reason!
@ -803,8 +801,7 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
__slb_restore_bolted_realmode();
out:
if (mmu_on)
mtmsr(MSR_KERNEL);
mtmsr(MSR_KERNEL);
return srr1;
}
@ -895,7 +892,7 @@ struct p10_sprs {
*/
};
static unsigned long power10_idle_stop(unsigned long psscr, bool mmu_on)
static unsigned long power10_idle_stop(unsigned long psscr)
{
int cpu = raw_smp_processor_id();
int first = cpu_first_thread_sibling(cpu);
@ -909,8 +906,6 @@ static unsigned long power10_idle_stop(unsigned long psscr, bool mmu_on)
if (!(psscr & (PSSCR_EC|PSSCR_ESL))) {
/* EC=ESL=0 case */
BUG_ON(!mmu_on);
/*
* Wake synchronously. SRESET via xscom may still cause
* a 0x100 powersave wakeup with SRR1 reason!
@ -991,8 +986,7 @@ static unsigned long power10_idle_stop(unsigned long psscr, bool mmu_on)
__slb_restore_bolted_realmode();
out:
if (mmu_on)
mtmsr(MSR_KERNEL);
mtmsr(MSR_KERNEL);
return srr1;
}
@ -1002,40 +996,10 @@ static unsigned long arch300_offline_stop(unsigned long psscr)
{
unsigned long srr1;
#ifndef CONFIG_KVM_BOOK3S_HV_POSSIBLE
__ppc64_runlatch_off();
if (cpu_has_feature(CPU_FTR_ARCH_31))
srr1 = power10_idle_stop(psscr, true);
srr1 = power10_idle_stop(psscr);
else
srr1 = power9_idle_stop(psscr, true);
__ppc64_runlatch_on();
#else
/*
* Tell KVM we're entering idle.
* This does not have to be done in real mode because the P9 MMU
* is independent per-thread. Some steppings share radix/hash mode
* between threads, but in that case KVM has a barrier sync in real
* mode before and after switching between radix and hash.
*
* kvm_start_guest must still be called in real mode though, hence
* the false argument.
*/
local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_IDLE;
__ppc64_runlatch_off();
if (cpu_has_feature(CPU_FTR_ARCH_31))
srr1 = power10_idle_stop(psscr, false);
else
srr1 = power9_idle_stop(psscr, false);
__ppc64_runlatch_on();
local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_KERNEL;
/* Order setting hwthread_state vs. testing hwthread_req */
smp_mb();
if (local_paca->kvm_hstate.hwthread_req)
srr1 = idle_kvm_start_guest(srr1);
mtmsr(MSR_KERNEL);
#endif
srr1 = power9_idle_stop(psscr);
return srr1;
}
@ -1055,9 +1019,9 @@ void arch300_idle_type(unsigned long stop_psscr_val,
__ppc64_runlatch_off();
if (cpu_has_feature(CPU_FTR_ARCH_31))
srr1 = power10_idle_stop(psscr, true);
srr1 = power10_idle_stop(psscr);
else
srr1 = power9_idle_stop(psscr, true);
srr1 = power9_idle_stop(psscr);
__ppc64_runlatch_on();
fini_irq_for_idle_irqsoff();