PPC | KVM_REG_PPC_LPCR | 64
PPC | KVM_REG_PPC_PPR | 64
PPC | KVM_REG_PPC_ARCH_COMPAT 32
+ PPC | KVM_REG_PPC_DABRX | 32
PPC | KVM_REG_PPC_TM_GPR0 | 64
...
PPC | KVM_REG_PPC_TM_GPR31 | 64
Allows setting an eventfd to directly trigger a guest interrupt.
kvm_irqfd.fd specifies the file descriptor to use as the eventfd and
kvm_irqfd.gsi specifies the irqchip pin toggled by this event. When
-an event is tiggered on the eventfd, an interrupt is injected into
+an event is triggered on the eventfd, an interrupt is injected into
the guest using the specified gsi pin. The irqfd is removed using
the KVM_IRQFD_FLAG_DEASSIGN flag, specifying both kvm_irqfd.fd
and kvm_irqfd.gsi.
additional eventfd in the kvm_irqfd.resamplefd field. When operating
in resample mode, posting of an interrupt through kvm_irq.fd asserts
the specified gsi in the irqchip. When the irqchip is resampled, such
-as from an EOI, the gsi is de-asserted and the user is notifed via
+as from an EOI, the gsi is de-asserted and the user is notified via
kvm_irqfd.resamplefd. It is the user's responsibility to re-queue
the interrupt if the device making use of it still requires service.
Note that closing the resamplefd is not sufficient to disable the
Capability: basic
Architectures: arm, arm64
Type: vcpu ioctl
-Parameters: struct struct kvm_vcpu_init (in)
+Parameters: struct kvm_vcpu_init (in)
Returns: 0 on success; -1 on error
Errors:
EINVAL: the target is unknown, or the combination of features is invalid.
This ioctl returns the guest registers that are supported for the
KVM_GET_ONE_REG/KVM_SET_ONE_REG calls.
-4.85 KVM_ARM_SET_DEVICE_ADDR
+
+4.85 KVM_ARM_SET_DEVICE_ADDR (deprecated)
Capability: KVM_CAP_ARM_SET_DEVICE_ADDR
Architectures: arm, arm64
KVM_RUN on any of the VCPUs. Calling this ioctl twice for any of the
base addresses will return -EEXIST.
+Note, this IOCTL is deprecated and the more flexible SET/GET_DEVICE_ATTR API
+should be used instead.
+
+
4.86 KVM_PPC_RTAS_DEFINE_TOKEN
Capability: KVM_CAP_PPC_RTAS
config PPC
bool
default y
+ select ARCH_MIGHT_HAVE_PC_PARPORT
select BINFMT_ELF
select OF
select OF_EARLY_FLATTREE
bool
default y
+config PANIC_TIMEOUT
+ int
+ default 180
+
config COMPAT
bool
default y if PPC64
bool "Transactional Memory support for POWERPC"
depends on PPC_BOOK3S_64
depends on SMP
+ select ALTIVEC
+ select VSX
default n
---help---
Support user-mode Transactional Memory on POWERPC.
extern void kvmppc_entry_trampoline(void);
extern void kvmppc_hv_entry_trampoline(void);
- extern void kvmppc_load_up_fpu(void);
- extern void kvmppc_load_up_altivec(void);
- extern void kvmppc_load_up_vsx(void);
extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst);
extern ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst);
extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd);
+extern void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu,
+ struct kvm_vcpu *vcpu);
+extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
+ struct kvmppc_book3s_shadow_vcpu *svcpu);
static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
{
return vcpu->arch.pc;
}
- static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
+ static inline bool kvmppc_need_byteswap(struct kvm_vcpu *vcpu)
{
- ulong pc = kvmppc_get_pc(vcpu);
+ return (vcpu->arch.shared->msr & MSR_LE) != (MSR_KERNEL & MSR_LE);
+ }
+ static inline u32 kvmppc_get_last_inst_internal(struct kvm_vcpu *vcpu, ulong pc)
+ {
/* Load the instruction manually if it failed to do so in the
* exit path */
if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED)
kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false);
- return vcpu->arch.last_inst;
+ return kvmppc_need_byteswap(vcpu) ? swab32(vcpu->arch.last_inst) :
+ vcpu->arch.last_inst;
+ }
+
+ static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
+ {
+ return kvmppc_get_last_inst_internal(vcpu, kvmppc_get_pc(vcpu));
}
/*
*/
static inline u32 kvmppc_get_last_sc(struct kvm_vcpu *vcpu)
{
- ulong pc = kvmppc_get_pc(vcpu) - 4;
-
- /* Load the instruction manually if it failed to do so in the
- * exit path */
- if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED)
- kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false);
-
- return vcpu->arch.last_inst;
+ return kvmppc_get_last_inst_internal(vcpu, kvmppc_get_pc(vcpu) - 4);
}
static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
ulong vmhandler;
ulong scratch0;
ulong scratch1;
+ ulong scratch2;
u8 in_guest;
u8 restore_hid5;
u8 napping;
u8 hwthread_req;
u8 hwthread_state;
u8 host_ipi;
+ u8 ptid;
struct kvm_vcpu *kvm_vcpu;
struct kvmppc_vcore *kvm_vcore;
unsigned long xics_phys;
};
struct kvmppc_book3s_shadow_vcpu {
+ bool in_use;
ulong gpr[14];
u32 cr;
u32 xer;
#define CTRL_TE 0x00c00000 /* thread enable */
#define CTRL_RUNLATCH 0x1
#define SPRN_DAWR 0xB4
+ #define SPRN_CIABR 0xBB
+ #define CIABR_PRIV 0x3
+ #define CIABR_PRIV_USER 1
+ #define CIABR_PRIV_SUPER 2
+ #define CIABR_PRIV_HYPER 3
#define SPRN_DAWRX 0xBC
- #define DAWRX_USER (1UL << 0)
- #define DAWRX_KERNEL (1UL << 1)
- #define DAWRX_HYP (1UL << 2)
+ #define DAWRX_USER __MASK(0)
+ #define DAWRX_KERNEL __MASK(1)
+ #define DAWRX_HYP __MASK(2)
+ #define DAWRX_WTI __MASK(3)
+ #define DAWRX_WT __MASK(4)
+ #define DAWRX_DR __MASK(5)
+ #define DAWRX_DW __MASK(6)
#define SPRN_DABR 0x3F5 /* Data Address Breakpoint Register */
#define SPRN_DABR2 0x13D /* e300 */
#define SPRN_DABRX 0x3F7 /* Data Address Breakpoint Register Extension */
- #define DABRX_USER (1UL << 0)
- #define DABRX_KERNEL (1UL << 1)
- #define DABRX_HYP (1UL << 2)
- #define DABRX_BTI (1UL << 3)
+ #define DABRX_USER __MASK(0)
+ #define DABRX_KERNEL __MASK(1)
+ #define DABRX_HYP __MASK(2)
+ #define DABRX_BTI __MASK(3)
#define DABRX_ALL (DABRX_BTI | DABRX_HYP | DABRX_KERNEL | DABRX_USER)
#define SPRN_DAR 0x013 /* Data Address Register */
#define SPRN_DBCR 0x136 /* e300 Data Breakpoint Control Reg */
#define SPRN_HRMOR 0x139 /* Real mode offset register */
#define SPRN_HSRR0 0x13A /* Hypervisor Save/Restore 0 */
#define SPRN_HSRR1 0x13B /* Hypervisor Save/Restore 1 */
+ #define SPRN_IC 0x350 /* Virtual Instruction Count */
+ #define SPRN_VTB 0x351 /* Virtual Time Base */
/* HFSCR and FSCR bit numbers are the same */
#define FSCR_TAR_LG 8 /* Enable Target Address Register */
#define FSCR_EBB_LG 7 /* Enable Event Based Branching */
#define LPCR_RMLS 0x1C000000 /* impl dependent rmo limit sel */
#define LPCR_RMLS_SH (63-37)
#define LPCR_ILE 0x02000000 /* !HV irqs set MSR:LE */
+ #define LPCR_AIL 0x01800000 /* Alternate interrupt location */
#define LPCR_AIL_0 0x00000000 /* MMU off exception offset 0x0 */
#define LPCR_AIL_3 0x01800000 /* MMU on exception offset 0xc00...4xxx */
- #define LPCR_PECE 0x00007000 /* powersave exit cause enable */
+ #define LPCR_ONL 0x00040000 /* online - PURR/SPURR count */
+ #define LPCR_PECE 0x0001f000 /* powersave exit cause enable */
+ #define LPCR_PECEDP 0x00010000 /* directed priv dbells cause exit */
+ #define LPCR_PECEDH 0x00008000 /* directed hyp dbells cause exit */
#define LPCR_PECE0 0x00004000 /* ext. exceptions can cause exit */
#define LPCR_PECE1 0x00002000 /* decrementer can cause exit */
#define LPCR_PECE2 0x00001000 /* machine check etc can cause exit */
#define SPRN_PCR 0x152 /* Processor compatibility register */
#define PCR_VEC_DIS (1ul << (63-0)) /* Vec. disable (bit NA since POWER8) */
#define PCR_VSX_DIS (1ul << (63-1)) /* VSX disable (bit NA since POWER8) */
+ #define PCR_TM_DIS (1ul << (63-2)) /* Trans. memory disable (POWER8) */
+ #define PCR_ARCH_206 0x4 /* Architecture 2.06 */
#define PCR_ARCH_205 0x2 /* Architecture 2.05 */
#define SPRN_HEIR 0x153 /* Hypervisor Emulated Instruction Register */
#define SPRN_TLBINDEXR 0x154 /* P7 TLB control register */
#define DER_EBRKE 0x00000002 /* External Breakpoint Interrupt */
#define DER_DPIE 0x00000001 /* Dev. Port Nonmaskable Request */
#define SPRN_DMISS 0x3D0 /* Data TLB Miss Register */
+ #define SPRN_DHDES 0x0B1 /* Directed Hyp. Doorbell Exc. State */
+ #define SPRN_DPDES 0x0B0 /* Directed Priv. Doorbell Exc. State */
#define SPRN_EAR 0x11A /* External Address Register */
#define SPRN_HASH1 0x3D2 /* Primary Hash Address Register */
#define SPRN_HASH2 0x3D3 /* Secondary Hash Address Resgister */
#define SPRN_IABR 0x3F2 /* Instruction Address Breakpoint Register */
#define SPRN_IABR2 0x3FA /* 83xx */
#define SPRN_IBCR 0x135 /* 83xx Insn Breakpoint Control Reg */
+ #define SPRN_IAMR 0x03D /* Instr. Authority Mask Reg */
#define SPRN_HID4 0x3F4 /* 970 HID4 */
#define HID4_LPES0 (1ul << (63-0)) /* LPAR env. sel. bit 0 */
#define HID4_RMLS2_SH (63 - 2) /* Real mode limit bottom 2 bits */
#define SPRN_PIR 0x3FF /* Processor Identification Register */
#endif
#define SPRN_TIR 0x1BE /* Thread Identification Register */
+ #define SPRN_PSPB 0x09F /* Problem State Priority Boost reg */
#define SPRN_PTEHI 0x3D5 /* 981 7450 PTE HI word (S/W TLB load) */
#define SPRN_PTELO 0x3D6 /* 982 7450 PTE LO word (S/W TLB load) */
#define SPRN_PURR 0x135 /* Processor Utilization of Resources Reg */
#define SPRN_EBBHR 804 /* Event based branch handler register */
#define SPRN_EBBRR 805 /* Event based branch return register */
#define SPRN_BESCR 806 /* Branch event status and control register */
+ #define SPRN_WORT 895 /* Workload optimization register - thread */
#define SPRN_PMC1 787
#define SPRN_PMC2 788
#define SIER_SIHV 0x1000000 /* Sampled MSR_HV */
#define SIER_SIAR_VALID 0x0400000 /* SIAR contents valid */
#define SIER_SDAR_VALID 0x0200000 /* SDAR contents valid */
+ #define SPRN_TACR 888
+ #define SPRN_TCSCR 889
+ #define SPRN_CSIGR 890
+ #define SPRN_SPMC1 892
+ #define SPRN_SPMC2 893
/* When EBB is enabled, some of MMCR0/MMCR2/SIER are user accessible */
#define MMCR0_USER_MASK (MMCR0_FC | MMCR0_PMXE | MMCR0_PMAO)
#else /* __powerpc64__ */
+#if defined(CONFIG_8xx)
+#define mftbl() ({unsigned long rval; \
+ asm volatile("mftbl %0" : "=r" (rval)); rval;})
+#define mftbu() ({unsigned long rval; \
+ asm volatile("mftbu %0" : "=r" (rval)); rval;})
+#else
#define mftbl() ({unsigned long rval; \
asm volatile("mfspr %0, %1" : "=r" (rval) : \
"i" (SPRN_TBRL)); rval;})
#define mftbu() ({unsigned long rval; \
asm volatile("mfspr %0, %1" : "=r" (rval) : \
"i" (SPRN_TBRU)); rval;})
+#endif
#endif /* !__powerpc64__ */
#define mttbl(v) asm volatile("mttbl %0":: "r"(v))
static inline void save_tar(struct thread_struct *prev) {}
#endif
- extern void load_up_fpu(void);
extern void enable_kernel_fp(void);
extern void enable_kernel_altivec(void);
- extern void load_up_altivec(struct task_struct *);
extern int emulate_altivec(struct pt_regs *);
extern void __giveup_vsx(struct task_struct *);
extern void giveup_vsx(struct task_struct *);
extern void enable_kernel_spe(void);
extern void giveup_spe(struct task_struct *);
extern void load_up_spe(struct task_struct *);
-extern void switch_booke_debug_regs(struct thread_struct *new_thread);
+extern void switch_booke_debug_regs(struct debug_reg *new_debug);
#ifndef CONFIG_SMP
extern void discard_lazy_cpu_state(void);
DEFINE(VCPU_GUEST_PID, offsetof(struct kvm_vcpu, arch.pid));
DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
DEFINE(VCPU_VRSAVE, offsetof(struct kvm_vcpu, arch.vrsave));
- DEFINE(VCPU_FPRS, offsetof(struct kvm_vcpu, arch.fpr));
- DEFINE(VCPU_FPSCR, offsetof(struct kvm_vcpu, arch.fpscr));
+ DEFINE(VCPU_FPRS, offsetof(struct kvm_vcpu, arch.fp.fpr));
#ifdef CONFIG_ALTIVEC
- DEFINE(VCPU_VRS, offsetof(struct kvm_vcpu, arch.vr));
- DEFINE(VCPU_VSCR, offsetof(struct kvm_vcpu, arch.vscr));
- #endif
- #ifdef CONFIG_VSX
- DEFINE(VCPU_VSRS, offsetof(struct kvm_vcpu, arch.vsr));
+ DEFINE(VCPU_VRS, offsetof(struct kvm_vcpu, arch.vr.vr));
#endif
DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
+ DEFINE(VCPU_TAR, offsetof(struct kvm_vcpu, arch.tar));
DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa.pinned_addr));
DEFINE(VCPU_VPA_DIRTY, offsetof(struct kvm_vcpu, arch.vpa.dirty));
+ DEFINE(VCPU_INTR_MSR, offsetof(struct kvm_vcpu, arch.intr_msr));
#endif
#ifdef CONFIG_PPC_BOOK3S
DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id));
DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr));
DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr));
+ DEFINE(VCPU_IC, offsetof(struct kvm_vcpu, arch.ic));
+ DEFINE(VCPU_VTB, offsetof(struct kvm_vcpu, arch.vtb));
DEFINE(VCPU_DSCR, offsetof(struct kvm_vcpu, arch.dscr));
DEFINE(VCPU_AMR, offsetof(struct kvm_vcpu, arch.amr));
DEFINE(VCPU_UAMOR, offsetof(struct kvm_vcpu, arch.uamor));
+ DEFINE(VCPU_IAMR, offsetof(struct kvm_vcpu, arch.iamr));
DEFINE(VCPU_CTRL, offsetof(struct kvm_vcpu, arch.ctrl));
DEFINE(VCPU_DABR, offsetof(struct kvm_vcpu, arch.dabr));
+ DEFINE(VCPU_DABRX, offsetof(struct kvm_vcpu, arch.dabrx));
+ DEFINE(VCPU_DAWR, offsetof(struct kvm_vcpu, arch.dawr));
+ DEFINE(VCPU_DAWRX, offsetof(struct kvm_vcpu, arch.dawrx));
+ DEFINE(VCPU_CIABR, offsetof(struct kvm_vcpu, arch.ciabr));
DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec));
DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires));
DEFINE(VCPU_PRODDED, offsetof(struct kvm_vcpu, arch.prodded));
DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr));
DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc));
+ DEFINE(VCPU_SPMC, offsetof(struct kvm_vcpu, arch.spmc));
DEFINE(VCPU_SIAR, offsetof(struct kvm_vcpu, arch.siar));
DEFINE(VCPU_SDAR, offsetof(struct kvm_vcpu, arch.sdar));
+ DEFINE(VCPU_SIER, offsetof(struct kvm_vcpu, arch.sier));
DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb));
DEFINE(VCPU_SLB_MAX, offsetof(struct kvm_vcpu, arch.slb_max));
DEFINE(VCPU_SLB_NR, offsetof(struct kvm_vcpu, arch.slb_nr));
DEFINE(VCPU_FAULT_DAR, offsetof(struct kvm_vcpu, arch.fault_dar));
DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap));
- DEFINE(VCPU_PTID, offsetof(struct kvm_vcpu, arch.ptid));
DEFINE(VCPU_CFAR, offsetof(struct kvm_vcpu, arch.cfar));
DEFINE(VCPU_PPR, offsetof(struct kvm_vcpu, arch.ppr));
+ DEFINE(VCPU_FSCR, offsetof(struct kvm_vcpu, arch.fscr));
+ DEFINE(VCPU_PSPB, offsetof(struct kvm_vcpu, arch.pspb));
+ DEFINE(VCPU_EBBHR, offsetof(struct kvm_vcpu, arch.ebbhr));
+ DEFINE(VCPU_EBBRR, offsetof(struct kvm_vcpu, arch.ebbrr));
+ DEFINE(VCPU_BESCR, offsetof(struct kvm_vcpu, arch.bescr));
+ DEFINE(VCPU_CSIGR, offsetof(struct kvm_vcpu, arch.csigr));
+ DEFINE(VCPU_TACR, offsetof(struct kvm_vcpu, arch.tacr));
+ DEFINE(VCPU_TCSCR, offsetof(struct kvm_vcpu, arch.tcscr));
+ DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop));
+ DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
+ DEFINE(VCORE_KVM, offsetof(struct kvmppc_vcore, kvm));
DEFINE(VCORE_TB_OFFSET, offsetof(struct kvmppc_vcore, tb_offset));
DEFINE(VCORE_LPCR, offsetof(struct kvmppc_vcore, lpcr));
DEFINE(VCORE_PCR, offsetof(struct kvmppc_vcore, pcr));
+ DEFINE(VCORE_DPDES, offsetof(struct kvmppc_vcore, dpdes));
DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
DEFINE(VCPU_SLB_V, offsetof(struct kvmppc_slb, origv));
DEFINE(VCPU_SLB_SIZE, sizeof(struct kvmppc_slb));
+ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ DEFINE(VCPU_TFHAR, offsetof(struct kvm_vcpu, arch.tfhar));
+ DEFINE(VCPU_TFIAR, offsetof(struct kvm_vcpu, arch.tfiar));
+ DEFINE(VCPU_TEXASR, offsetof(struct kvm_vcpu, arch.texasr));
+ DEFINE(VCPU_GPR_TM, offsetof(struct kvm_vcpu, arch.gpr_tm));
+ DEFINE(VCPU_FPRS_TM, offsetof(struct kvm_vcpu, arch.fp_tm.fpr));
+ DEFINE(VCPU_VRS_TM, offsetof(struct kvm_vcpu, arch.vr_tm.vr));
+ DEFINE(VCPU_VRSAVE_TM, offsetof(struct kvm_vcpu, arch.vrsave_tm));
+ DEFINE(VCPU_CR_TM, offsetof(struct kvm_vcpu, arch.cr_tm));
+ DEFINE(VCPU_LR_TM, offsetof(struct kvm_vcpu, arch.lr_tm));
+ DEFINE(VCPU_CTR_TM, offsetof(struct kvm_vcpu, arch.ctr_tm));
+ DEFINE(VCPU_AMR_TM, offsetof(struct kvm_vcpu, arch.amr_tm));
+ DEFINE(VCPU_PPR_TM, offsetof(struct kvm_vcpu, arch.ppr_tm));
+ DEFINE(VCPU_DSCR_TM, offsetof(struct kvm_vcpu, arch.dscr_tm));
+ DEFINE(VCPU_TAR_TM, offsetof(struct kvm_vcpu, arch.tar_tm));
+ #endif
#ifdef CONFIG_PPC_BOOK3S_64
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler);
HSTATE_FIELD(HSTATE_SCRATCH0, scratch0);
HSTATE_FIELD(HSTATE_SCRATCH1, scratch1);
+ HSTATE_FIELD(HSTATE_SCRATCH2, scratch2);
HSTATE_FIELD(HSTATE_IN_GUEST, in_guest);
HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5);
HSTATE_FIELD(HSTATE_NAPPING, napping);
HSTATE_FIELD(HSTATE_XICS_PHYS, xics_phys);
HSTATE_FIELD(HSTATE_SAVED_XIRR, saved_xirr);
HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi);
+ HSTATE_FIELD(HSTATE_PTID, ptid);
HSTATE_FIELD(HSTATE_MMCR, host_mmcr);
HSTATE_FIELD(HSTATE_PMC, host_pmc);
HSTATE_FIELD(HSTATE_PURR, host_purr);
static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
{
- kvmppc_set_msr(vcpu, MSR_SF | MSR_ME);
+ kvmppc_set_msr(vcpu, vcpu->arch.intr_msr);
}
/*
slb_v = vcpu->kvm->arch.vrma_slb_v;
}
+ preempt_disable();
/* Find the HPTE in the hash table */
index = kvmppc_hv_find_lock_hpte(kvm, eaddr, slb_v,
HPTE_V_VALID | HPTE_V_ABSENT);
- if (index < 0)
+ if (index < 0) {
+ preempt_enable();
return -ENOENT;
+ }
hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
v = hptep[0] & ~HPTE_V_HVLOCK;
gr = kvm->arch.revmap[index].guest_rpte;
/* Unlock the HPTE */
asm volatile("lwsync" : : : "memory");
hptep[0] = v;
+ preempt_enable();
gpte->eaddr = eaddr;
gpte->vpage = ((v & HPTE_V_AVPN) << 4) | ((eaddr >> 12) & 0xfff);
* we just return and retry the instruction.
*/
- if (instruction_is_store(vcpu->arch.last_inst) != !!is_store)
+ if (instruction_is_store(kvmppc_get_last_inst(vcpu)) != !!is_store)
return RESUME_GUEST;
/*
return -EFAULT;
} else {
page = pages[0];
+ pfn = page_to_pfn(page);
if (PageHuge(page)) {
page = compound_head(page);
pte_size <<= compound_order(page);
}
rcu_read_unlock_sched();
}
- pfn = page_to_pfn(page);
}
ret = -EFAULT;
r = (r & ~(HPTE_R_W|HPTE_R_I|HPTE_R_G)) | HPTE_R_M;
}
- /* Set the HPTE to point to pfn */
- r = (r & ~(HPTE_R_PP0 - pte_size)) | (pfn << PAGE_SHIFT);
+ /*
+ * Set the HPTE to point to pfn.
+ * Since the pfn is at PAGE_SIZE granularity, make sure we
+ * don't mask out lower-order bits if psize < PAGE_SIZE.
+ */
+ if (psize < PAGE_SIZE)
+ psize = PAGE_SIZE;
+ r = (r & ~(HPTE_R_PP0 - psize)) | ((pfn << PAGE_SHIFT) & ~(psize - 1));
if (hpte_is_writable(r) && !write_ok)
r = hpte_make_readonly(r);
ret = RESUME_GUEST;
#include <linux/spinlock.h>
#include <linux/page-flags.h>
#include <linux/srcu.h>
+ #include <linux/miscdevice.h>
#include <asm/reg.h>
#include <asm/cputable.h>
/* CPU points to the first thread of the core */
if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) {
+ #ifdef CONFIG_KVM_XICS
int real_cpu = cpu + vcpu->arch.ptid;
if (paca[real_cpu].kvm_hstate.xics_phys)
xics_wake_cpu(real_cpu);
- else if (cpu_online(cpu))
+ else
+ #endif
+ if (cpu_online(cpu))
smp_send_reschedule(cpu);
}
put_cpu();
static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
+ unsigned long flags;
- spin_lock(&vcpu->arch.tbacct_lock);
+ spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE &&
vc->preempt_tb != TB_NIL) {
vc->stolen_tb += mftb() - vc->preempt_tb;
vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt;
vcpu->arch.busy_preempt = TB_NIL;
}
- spin_unlock(&vcpu->arch.tbacct_lock);
+ spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
}
static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
+ unsigned long flags;
- spin_lock(&vcpu->arch.tbacct_lock);
+ spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE)
vc->preempt_tb = mftb();
if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST)
vcpu->arch.busy_preempt = mftb();
- spin_unlock(&vcpu->arch.tbacct_lock);
+ spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
}
static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
switch (arch_compat) {
case PVR_ARCH_205:
- pcr = PCR_ARCH_205;
+ /*
+ * If an arch bit is set in PCR, all the defined
+ * higher-order arch bits also have to be set.
+ */
+ pcr = PCR_ARCH_206 | PCR_ARCH_205;
break;
case PVR_ARCH_206:
case PVR_ARCH_206p:
+ pcr = PCR_ARCH_206;
+ break;
+ case PVR_ARCH_207:
break;
default:
return -EINVAL;
}
+
+ if (!cpu_has_feature(CPU_FTR_ARCH_207S)) {
+ /* POWER7 can't emulate POWER8 */
+ if (!(pcr & PCR_ARCH_206))
+ return -EINVAL;
+ pcr &= ~PCR_ARCH_206;
+ }
}
spin_lock(&vc->lock);
*/
if (vc->vcore_state != VCORE_INACTIVE &&
vc->runner->arch.run_task != current) {
- spin_lock(&vc->runner->arch.tbacct_lock);
+ spin_lock_irq(&vc->runner->arch.tbacct_lock);
p = vc->stolen_tb;
if (vc->preempt_tb != TB_NIL)
p += now - vc->preempt_tb;
- spin_unlock(&vc->runner->arch.tbacct_lock);
+ spin_unlock_irq(&vc->runner->arch.tbacct_lock);
} else {
p = vc->stolen_tb;
}
core_stolen = vcore_stolen_time(vc, now);
stolen = core_stolen - vcpu->arch.stolen_logged;
vcpu->arch.stolen_logged = core_stolen;
- spin_lock(&vcpu->arch.tbacct_lock);
+ spin_lock_irq(&vcpu->arch.tbacct_lock);
stolen += vcpu->arch.busy_stolen;
vcpu->arch.busy_stolen = 0;
- spin_unlock(&vcpu->arch.tbacct_lock);
+ spin_unlock_irq(&vcpu->arch.tbacct_lock);
if (!dt || !vpa)
return;
memset(dt, 0, sizeof(struct dtl_entry));
if (list_empty(&vcpu->kvm->arch.rtas_tokens))
return RESUME_HOST;
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
rc = kvmppc_rtas_hcall(vcpu);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
if (rc == -ENOENT)
return RESUME_HOST;
r = RESUME_GUEST;
break;
case BOOK3S_INTERRUPT_EXTERNAL:
+ case BOOK3S_INTERRUPT_H_DOORBELL:
vcpu->stat.ext_intr_exits++;
r = RESUME_GUEST;
break;
/* hcall - punt to userspace */
int i;
- if (vcpu->arch.shregs.msr & MSR_PR) {
- /* sc 1 from userspace - reflect to guest syscall */
- kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_SYSCALL);
- r = RESUME_GUEST;
- break;
- }
+ /* hypercall with MSR_PR has already been handled in rmode,
+ * and never reaches here.
+ */
+
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);
* we don't emulate any guest instructions at this stage.
*/
case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
- kvmppc_core_queue_program(vcpu, 0x80000);
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+ r = RESUME_GUEST;
+ break;
+ /*
+ * This occurs if the guest (kernel or userspace), does something that
+ * is prohibited by HFSCR. We just generate a program interrupt to
+ * the guest.
+ */
+ case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+ kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
r = RESUME_GUEST;
break;
default:
u64 mask;
spin_lock(&vc->lock);
+ /*
+ * If ILE (interrupt little-endian) has changed, update the
+ * MSR_LE bit in the intr_msr for each vcpu in this vcore.
+ */
+ if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) {
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_vcpu *vcpu;
+ int i;
+
+ mutex_lock(&kvm->lock);
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (vcpu->arch.vcore != vc)
+ continue;
+ if (new_lpcr & LPCR_ILE)
+ vcpu->arch.intr_msr |= MSR_LE;
+ else
+ vcpu->arch.intr_msr &= ~MSR_LE;
+ }
+ mutex_unlock(&kvm->lock);
+ }
+
/*
* Userspace can only modify DPFD (default prefetch depth),
* ILE (interrupt little-endian) and TC (translation control).
+ * On POWER8 userspace can also modify AIL (alt. interrupt loc.)
*/
mask = LPCR_DPFD | LPCR_ILE | LPCR_TC;
+ if (cpu_has_feature(CPU_FTR_ARCH_207S))
+ mask |= LPCR_AIL;
vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
spin_unlock(&vc->lock);
}
case KVM_REG_PPC_DABR:
*val = get_reg_val(id, vcpu->arch.dabr);
break;
+ case KVM_REG_PPC_DABRX:
+ *val = get_reg_val(id, vcpu->arch.dabrx);
+ break;
case KVM_REG_PPC_DSCR:
*val = get_reg_val(id, vcpu->arch.dscr);
break;
case KVM_REG_PPC_UAMOR:
*val = get_reg_val(id, vcpu->arch.uamor);
break;
- case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRA:
+ case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
i = id - KVM_REG_PPC_MMCR0;
*val = get_reg_val(id, vcpu->arch.mmcr[i]);
break;
i = id - KVM_REG_PPC_PMC1;
*val = get_reg_val(id, vcpu->arch.pmc[i]);
break;
+ case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
+ i = id - KVM_REG_PPC_SPMC1;
+ *val = get_reg_val(id, vcpu->arch.spmc[i]);
+ break;
case KVM_REG_PPC_SIAR:
*val = get_reg_val(id, vcpu->arch.siar);
break;
case KVM_REG_PPC_SDAR:
*val = get_reg_val(id, vcpu->arch.sdar);
break;
- #ifdef CONFIG_VSX
- case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
- if (cpu_has_feature(CPU_FTR_VSX)) {
- /* VSX => FP reg i is stored in arch.vsr[2*i] */
- long int i = id - KVM_REG_PPC_FPR0;
- *val = get_reg_val(id, vcpu->arch.vsr[2 * i]);
- } else {
- /* let generic code handle it */
- r = -EINVAL;
- }
+ case KVM_REG_PPC_SIER:
+ *val = get_reg_val(id, vcpu->arch.sier);
break;
- case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
- if (cpu_has_feature(CPU_FTR_VSX)) {
- long int i = id - KVM_REG_PPC_VSR0;
- val->vsxval[0] = vcpu->arch.vsr[2 * i];
- val->vsxval[1] = vcpu->arch.vsr[2 * i + 1];
- } else {
- r = -ENXIO;
- }
+ case KVM_REG_PPC_IAMR:
+ *val = get_reg_val(id, vcpu->arch.iamr);
+ break;
+ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ case KVM_REG_PPC_TFHAR:
+ *val = get_reg_val(id, vcpu->arch.tfhar);
+ break;
+ case KVM_REG_PPC_TFIAR:
+ *val = get_reg_val(id, vcpu->arch.tfiar);
+ break;
+ case KVM_REG_PPC_TEXASR:
+ *val = get_reg_val(id, vcpu->arch.texasr);
+ break;
+ #endif
+ case KVM_REG_PPC_FSCR:
+ *val = get_reg_val(id, vcpu->arch.fscr);
+ break;
+ case KVM_REG_PPC_PSPB:
+ *val = get_reg_val(id, vcpu->arch.pspb);
+ break;
+ case KVM_REG_PPC_EBBHR:
+ *val = get_reg_val(id, vcpu->arch.ebbhr);
+ break;
+ case KVM_REG_PPC_EBBRR:
+ *val = get_reg_val(id, vcpu->arch.ebbrr);
+ break;
+ case KVM_REG_PPC_BESCR:
+ *val = get_reg_val(id, vcpu->arch.bescr);
+ break;
+ case KVM_REG_PPC_TAR:
+ *val = get_reg_val(id, vcpu->arch.tar);
+ break;
+ case KVM_REG_PPC_DPDES:
+ *val = get_reg_val(id, vcpu->arch.vcore->dpdes);
+ break;
+ case KVM_REG_PPC_DAWR:
+ *val = get_reg_val(id, vcpu->arch.dawr);
+ break;
+ case KVM_REG_PPC_DAWRX:
+ *val = get_reg_val(id, vcpu->arch.dawrx);
+ break;
+ case KVM_REG_PPC_CIABR:
+ *val = get_reg_val(id, vcpu->arch.ciabr);
+ break;
+ case KVM_REG_PPC_IC:
+ *val = get_reg_val(id, vcpu->arch.ic);
+ break;
+ case KVM_REG_PPC_VTB:
+ *val = get_reg_val(id, vcpu->arch.vtb);
+ break;
+ case KVM_REG_PPC_CSIGR:
+ *val = get_reg_val(id, vcpu->arch.csigr);
+ break;
+ case KVM_REG_PPC_TACR:
+ *val = get_reg_val(id, vcpu->arch.tacr);
+ break;
+ case KVM_REG_PPC_TCSCR:
+ *val = get_reg_val(id, vcpu->arch.tcscr);
+ break;
+ case KVM_REG_PPC_PID:
+ *val = get_reg_val(id, vcpu->arch.pid);
+ break;
+ case KVM_REG_PPC_ACOP:
+ *val = get_reg_val(id, vcpu->arch.acop);
+ break;
+ case KVM_REG_PPC_WORT:
+ *val = get_reg_val(id, vcpu->arch.wort);
break;
- #endif /* CONFIG_VSX */
case KVM_REG_PPC_VPA_ADDR:
spin_lock(&vcpu->arch.vpa_update_lock);
*val = get_reg_val(id, vcpu->arch.vpa.next_gpa);
case KVM_REG_PPC_DABR:
vcpu->arch.dabr = set_reg_val(id, *val);
break;
+ case KVM_REG_PPC_DABRX:
+ vcpu->arch.dabrx = set_reg_val(id, *val) & ~DABRX_HYP;
+ break;
case KVM_REG_PPC_DSCR:
vcpu->arch.dscr = set_reg_val(id, *val);
break;
case KVM_REG_PPC_UAMOR:
vcpu->arch.uamor = set_reg_val(id, *val);
break;
- case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRA:
+ case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
i = id - KVM_REG_PPC_MMCR0;
vcpu->arch.mmcr[i] = set_reg_val(id, *val);
break;
i = id - KVM_REG_PPC_PMC1;
vcpu->arch.pmc[i] = set_reg_val(id, *val);
break;
+ case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
+ i = id - KVM_REG_PPC_SPMC1;
+ vcpu->arch.spmc[i] = set_reg_val(id, *val);
+ break;
case KVM_REG_PPC_SIAR:
vcpu->arch.siar = set_reg_val(id, *val);
break;
case KVM_REG_PPC_SDAR:
vcpu->arch.sdar = set_reg_val(id, *val);
break;
- #ifdef CONFIG_VSX
- case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
- if (cpu_has_feature(CPU_FTR_VSX)) {
- /* VSX => FP reg i is stored in arch.vsr[2*i] */
- long int i = id - KVM_REG_PPC_FPR0;
- vcpu->arch.vsr[2 * i] = set_reg_val(id, *val);
- } else {
- /* let generic code handle it */
- r = -EINVAL;
- }
+ case KVM_REG_PPC_SIER:
+ vcpu->arch.sier = set_reg_val(id, *val);
break;
- case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
- if (cpu_has_feature(CPU_FTR_VSX)) {
- long int i = id - KVM_REG_PPC_VSR0;
- vcpu->arch.vsr[2 * i] = val->vsxval[0];
- vcpu->arch.vsr[2 * i + 1] = val->vsxval[1];
- } else {
- r = -ENXIO;
- }
+ case KVM_REG_PPC_IAMR:
+ vcpu->arch.iamr = set_reg_val(id, *val);
+ break;
+ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ case KVM_REG_PPC_TFHAR:
+ vcpu->arch.tfhar = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TFIAR:
+ vcpu->arch.tfiar = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TEXASR:
+ vcpu->arch.texasr = set_reg_val(id, *val);
+ break;
+ #endif
+ case KVM_REG_PPC_FSCR:
+ vcpu->arch.fscr = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_PSPB:
+ vcpu->arch.pspb = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_EBBHR:
+ vcpu->arch.ebbhr = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_EBBRR:
+ vcpu->arch.ebbrr = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_BESCR:
+ vcpu->arch.bescr = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TAR:
+ vcpu->arch.tar = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_DPDES:
+ vcpu->arch.vcore->dpdes = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_DAWR:
+ vcpu->arch.dawr = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_DAWRX:
+ vcpu->arch.dawrx = set_reg_val(id, *val) & ~DAWRX_HYP;
+ break;
+ case KVM_REG_PPC_CIABR:
+ vcpu->arch.ciabr = set_reg_val(id, *val);
+ /* Don't allow setting breakpoints in hypervisor code */
+ if ((vcpu->arch.ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
+ vcpu->arch.ciabr &= ~CIABR_PRIV; /* disable */
+ break;
+ case KVM_REG_PPC_IC:
+ vcpu->arch.ic = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_VTB:
+ vcpu->arch.vtb = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_CSIGR:
+ vcpu->arch.csigr = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TACR:
+ vcpu->arch.tacr = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_TCSCR:
+ vcpu->arch.tcscr = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_PID:
+ vcpu->arch.pid = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_ACOP:
+ vcpu->arch.acop = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_WORT:
+ vcpu->arch.wort = set_reg_val(id, *val);
break;
- #endif /* CONFIG_VSX */
case KVM_REG_PPC_VPA_ADDR:
addr = set_reg_val(id, *val);
r = -EINVAL;
spin_lock_init(&vcpu->arch.vpa_update_lock);
spin_lock_init(&vcpu->arch.tbacct_lock);
vcpu->arch.busy_preempt = TB_NIL;
+ vcpu->arch.intr_msr = MSR_SF | MSR_ME;
kvmppc_mmu_book3s_hv_init(vcpu);
init_waitqueue_head(&vcore->wq);
vcore->preempt_tb = TB_NIL;
vcore->lpcr = kvm->arch.lpcr;
+ vcore->first_vcpuid = core * threads_per_core;
+ vcore->kvm = kvm;
}
kvm->arch.vcores[core] = vcore;
kvm->arch.online_vcores++;
++vcore->num_threads;
spin_unlock(&vcore->lock);
vcpu->arch.vcore = vcore;
+ vcpu->arch.ptid = vcpu->vcpu_id - vcore->first_vcpuid;
vcpu->arch.cpu_type = KVM_CPU_3S_64;
kvmppc_sanity_check(vcpu);
}
}
- extern int __kvmppc_vcore_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
+ extern void __kvmppc_vcore_entry(void);
static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
struct kvm_vcpu *vcpu)
if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
return;
- spin_lock(&vcpu->arch.tbacct_lock);
+ spin_lock_irq(&vcpu->arch.tbacct_lock);
now = mftb();
vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) -
vcpu->arch.stolen_logged;
vcpu->arch.busy_preempt = now;
vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
- spin_unlock(&vcpu->arch.tbacct_lock);
+ spin_unlock_irq(&vcpu->arch.tbacct_lock);
--vc->n_runnable;
list_del(&vcpu->arch.run_list);
}
tpaca = &paca[cpu];
tpaca->kvm_hstate.kvm_vcpu = vcpu;
tpaca->kvm_hstate.kvm_vcore = vc;
- tpaca->kvm_hstate.napping = 0;
+ tpaca->kvm_hstate.ptid = vcpu->arch.ptid;
vcpu->cpu = vc->pcpu;
smp_wmb();
#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
- if (vcpu->arch.ptid) {
+ if (cpu != smp_processor_id()) {
+ #ifdef CONFIG_KVM_XICS
xics_wake_cpu(cpu);
- ++vc->n_woken;
+ #endif
+ if (vcpu->arch.ptid)
+ ++vc->n_woken;
}
#endif
}
*/
static void kvmppc_run_core(struct kvmppc_vcore *vc)
{
- struct kvm_vcpu *vcpu, *vcpu0, *vnext;
+ struct kvm_vcpu *vcpu, *vnext;
long ret;
u64 now;
- int ptid, i, need_vpa_update;
+ int i, need_vpa_update;
int srcu_idx;
struct kvm_vcpu *vcpus_to_update[threads_per_core];
spin_lock(&vc->lock);
}
- /*
- * Assign physical thread IDs, first to non-ceded vcpus
- * and then to ceded ones.
- */
- ptid = 0;
- vcpu0 = NULL;
- list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
- if (!vcpu->arch.ceded) {
- if (!ptid)
- vcpu0 = vcpu;
- vcpu->arch.ptid = ptid++;
- }
- }
- if (!vcpu0)
- goto out; /* nothing to run; should never happen */
- list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
- if (vcpu->arch.ceded)
- vcpu->arch.ptid = ptid++;
-
/*
* Make sure we are running on thread 0, and that
* secondary threads are offline.
kvmppc_create_dtl_entry(vcpu, vc);
}
+ /* Set this explicitly in case thread 0 doesn't have a vcpu */
+ get_paca()->kvm_hstate.kvm_vcore = vc;
+ get_paca()->kvm_hstate.ptid = 0;
+
vc->vcore_state = VCORE_RUNNING;
preempt_disable();
spin_unlock(&vc->lock);
kvm_guest_enter();
- srcu_idx = srcu_read_lock(&vcpu0->kvm->srcu);
+ srcu_idx = srcu_read_lock(&vc->kvm->srcu);
- __kvmppc_vcore_entry(NULL, vcpu0);
+ __kvmppc_vcore_entry();
spin_lock(&vc->lock);
/* disable sending of IPIs on virtual external irqs */
vc->vcore_state = VCORE_EXITING;
spin_unlock(&vc->lock);
- srcu_read_unlock(&vcpu0->kvm->srcu, srcu_idx);
+ srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
/* make sure updates to secondary vcpu structs are visible now */
smp_mb();
kvm_guest_exit();
preempt_enable();
- kvm_resched(vcpu);
+ cond_resched();
spin_lock(&vc->lock);
now = get_tb();
if (!signal_pending(current)) {
if (vc->vcore_state == VCORE_RUNNING &&
VCORE_EXIT_COUNT(vc) == 0) {
- vcpu->arch.ptid = vc->n_runnable - 1;
kvmppc_create_dtl_entry(vcpu, vc);
kvmppc_start_thread(vcpu);
} else if (vc->vcore_state == VCORE_SLEEPING) {
LPCR_VPM0 | LPCR_VPM1;
kvm->arch.vrma_slb_v = SLB_VSID_B_1T |
(VRMA_VSID << SLB_VSID_SHIFT_1T);
+ /* On POWER8 turn on online bit to enable PURR/SPURR */
+ if (cpu_has_feature(CPU_FTR_ARCH_207S))
+ lpcr |= LPCR_ONL;
}
kvm->arch.lpcr = lpcr;
module_init(kvmppc_book3s_init_hv);
module_exit(kvmppc_book3s_exit_hv);
MODULE_LICENSE("GPL");
+ MODULE_ALIAS_MISCDEV(KVM_MINOR);
+ MODULE_ALIAS("devname:kvm");
unlock_rmap(rmap);
}
- static pte_t lookup_linux_pte(pgd_t *pgdir, unsigned long hva,
+ static pte_t lookup_linux_pte_and_update(pgd_t *pgdir, unsigned long hva,
int writing, unsigned long *pte_sizep)
{
pte_t *ptep;
is_io = pa & (HPTE_R_I | HPTE_R_W);
pte_size = PAGE_SIZE << (pa & KVMPPC_PAGE_ORDER_MASK);
pa &= PAGE_MASK;
+ pa |= gpa & ~PAGE_MASK;
} else {
/* Translate to host virtual address */
hva = __gfn_to_hva_memslot(memslot, gfn);
/* Look up the Linux PTE for the backing page */
pte_size = psize;
- pte = lookup_linux_pte(pgdir, hva, writing, &pte_size);
+ pte = lookup_linux_pte_and_update(pgdir, hva, writing,
+ &pte_size);
if (pte_present(pte)) {
if (writing && !pte_write(pte))
/* make the actual HPTE be read-only */
ptel = hpte_make_readonly(ptel);
is_io = hpte_cache_bits(pte_val(pte));
pa = pte_pfn(pte) << PAGE_SHIFT;
+ pa |= hva & (pte_size - 1);
+ pa |= gpa & ~PAGE_MASK;
}
}
if (pte_size < psize)
return H_PARAMETER;
- if (pa && pte_size > psize)
- pa |= gpa & (pte_size - 1);
ptel &= ~(HPTE_R_PP0 - psize);
ptel |= pa;
memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
if (memslot) {
hva = __gfn_to_hva_memslot(memslot, gfn);
- pte = lookup_linux_pte(pgdir, hva, 1, &psize);
+ pte = lookup_linux_pte_and_update(pgdir, hva,
+ 1, &psize);
if (pte_present(pte) && !pte_write(pte))
r = hpte_make_readonly(r);
}
20, /* 1M, unsupported */
};
+/* When called from virtmode, this func should be protected by
+ * preempt_disable(), otherwise, the holding of HPTE_V_HVLOCK
+ * can trigger deadlock issue.
+ */
long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
unsigned long valid)
{
#error Need to fix lppaca and SLB shadow accesses in little endian mode
#endif
+ /* Values in HSTATE_NAPPING(r13) */
+ #define NAPPING_CEDE 1
+ #define NAPPING_NOVCPU 2
+
/*
* Call kvmppc_hv_entry in real mode.
* Must be called with interrupts hard-disabled.
RFI
kvmppc_call_hv_entry:
+ ld r4, HSTATE_KVM_VCPU(r13)
bl kvmppc_hv_entry
/* Back from guest - restore host state and return to caller */
+ BEGIN_FTR_SECTION
/* Restore host DABR and DABRX */
ld r5,HSTATE_DABR(r13)
li r6,7
mtspr SPRN_DABR,r5
mtspr SPRN_DABRX,r6
+ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
/* Restore SPRG3 */
ld r3,PACA_SPRG3(r13)
mtspr SPRN_SPRG3,r3
- /*
- * Reload DEC. HDEC interrupts were disabled when
- * we reloaded the host's LPCR value.
- */
- ld r3, HSTATE_DECEXP(r13)
- mftb r4
- subf r4, r4, r3
- mtspr SPRN_DEC, r4
-
/* Reload the host's PMU registers */
ld r3, PACALPPACAPTR(r13) /* is the host using the PMU? */
lbz r4, LPPACA_PMCINUSE(r3)
isync
23:
+ /*
+ * Reload DEC. HDEC interrupts were disabled when
+ * we reloaded the host's LPCR value.
+ */
+ ld r3, HSTATE_DECEXP(r13)
+ mftb r4
+ subf r4, r4, r3
+ mtspr SPRN_DEC, r4
+
/*
* For external and machine check interrupts, we need
* to call the Linux handler to process the interrupt.
13: b machine_check_fwnmi
-
+ kvmppc_primary_no_guest:
+ /* We handle this much like a ceded vcpu */
+ /* set our bit in napping_threads */
+ ld r5, HSTATE_KVM_VCORE(r13)
+ lbz r7, HSTATE_PTID(r13)
+ li r0, 1
+ sld r0, r0, r7
+ addi r6, r5, VCORE_NAPPING_THREADS
+ 1: lwarx r3, 0, r6
+ or r3, r3, r0
+ stwcx. r3, 0, r6
+ bne 1b
+ /* order napping_threads update vs testing entry_exit_count */
+ isync
+ li r12, 0
+ lwz r7, VCORE_ENTRY_EXIT(r5)
+ cmpwi r7, 0x100
+ bge kvm_novcpu_exit /* another thread already exiting */
+ li r3, NAPPING_NOVCPU
+ stb r3, HSTATE_NAPPING(r13)
+ li r3, 1
+ stb r3, HSTATE_HWTHREAD_REQ(r13)
+
+ b kvm_do_nap
+
+ kvm_novcpu_wakeup:
+ ld r1, HSTATE_HOST_R1(r13)
+ ld r5, HSTATE_KVM_VCORE(r13)
+ li r0, 0
+ stb r0, HSTATE_NAPPING(r13)
+ stb r0, HSTATE_HWTHREAD_REQ(r13)
+
+ /* check the wake reason */
+ bl kvmppc_check_wake_reason
+
+ /* see if any other thread is already exiting */
+ lwz r0, VCORE_ENTRY_EXIT(r5)
+ cmpwi r0, 0x100
+ bge kvm_novcpu_exit
+
+ /* clear our bit in napping_threads */
+ lbz r7, HSTATE_PTID(r13)
+ li r0, 1
+ sld r0, r0, r7
+ addi r6, r5, VCORE_NAPPING_THREADS
+ 4: lwarx r7, 0, r6
+ andc r7, r7, r0
+ stwcx. r7, 0, r6
+ bne 4b
+
+ /* See if the wake reason means we need to exit */
+ cmpdi r3, 0
+ bge kvm_novcpu_exit
+
+ /* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */
+ ld r4, HSTATE_KVM_VCPU(r13)
+ cmpdi r4, 0
+ bne kvmppc_got_guest
+
+ kvm_novcpu_exit:
+ b hdec_soon
+
/*
- * We come in here when wakened from nap mode on a secondary hw thread.
+ * We come in here when wakened from nap mode.
* Relocation is off and most register values are lost.
* r13 points to the PACA.
*/
.globl kvm_start_guest
kvm_start_guest:
- ld r1,PACAEMERGSP(r13)
- subi r1,r1,STACK_FRAME_OVERHEAD
ld r2,PACATOC(r13)
li r0,KVM_HWTHREAD_IN_KVM
/* were we napping due to cede? */
lbz r0,HSTATE_NAPPING(r13)
- cmpwi r0,0
- bne kvm_end_cede
+ cmpwi r0,NAPPING_CEDE
+ beq kvm_end_cede
+ cmpwi r0,NAPPING_NOVCPU
+ beq kvm_novcpu_wakeup
+
+ ld r1,PACAEMERGSP(r13)
+ subi r1,r1,STACK_FRAME_OVERHEAD
/*
* We weren't napping due to cede, so this must be a secondary
*/
/* Check the wake reason in SRR1 to see why we got here */
- mfspr r3,SPRN_SRR1
- rlwinm r3,r3,44-31,0x7 /* extract wake reason field */
- cmpwi r3,4 /* was it an external interrupt? */
- bne 27f /* if not */
- ld r5,HSTATE_XICS_PHYS(r13)
- li r7,XICS_XIRR /* if it was an external interrupt, */
- lwzcix r8,r5,r7 /* get and ack the interrupt */
- sync
- clrldi. r9,r8,40 /* get interrupt source ID. */
- beq 28f /* none there? */
- cmpwi r9,XICS_IPI /* was it an IPI? */
- bne 29f
- li r0,0xff
- li r6,XICS_MFRR
- stbcix r0,r5,r6 /* clear IPI */
- stwcix r8,r5,r7 /* EOI the interrupt */
- sync /* order loading of vcpu after that */
+ bl kvmppc_check_wake_reason
+ cmpdi r3, 0
+ bge kvm_no_guest
/* get vcpu pointer, NULL if we have no vcpu to run */
ld r4,HSTATE_KVM_VCPU(r13)
cmpdi r4,0
/* if we have no vcpu to run, go back to sleep */
beq kvm_no_guest
- b 30f
- 27: /* XXX should handle hypervisor maintenance interrupts etc. here */
- b kvm_no_guest
- 28: /* SRR1 said external but ICP said nope?? */
- b kvm_no_guest
- 29: /* External non-IPI interrupt to offline secondary thread? help?? */
- stw r8,HSTATE_SAVED_XIRR(r13)
- b kvm_no_guest
+ /* Set HSTATE_DSCR(r13) to something sensible */
+ LOAD_REG_ADDR(r6, dscr_default)
+ ld r6, 0(r6)
+ std r6, HSTATE_DSCR(r13)
- 30: bl kvmppc_hv_entry
+ bl kvmppc_hv_entry
/* Back from the guest, go back to nap */
/* Clear our vcpu pointer so we don't come back in early */
li r0, 0
std r0, HSTATE_KVM_VCPU(r13)
+ /*
+ * Make sure we clear HSTATE_KVM_VCPU(r13) before incrementing
+ * the nap_count, because once the increment to nap_count is
+ * visible we could be given another vcpu.
+ */
lwsync
- /* Clear any pending IPI - we're an offline thread */
- ld r5, HSTATE_XICS_PHYS(r13)
- li r7, XICS_XIRR
- lwzcix r3, r5, r7 /* ack any pending interrupt */
- rlwinm. r0, r3, 0, 0xffffff /* any pending? */
- beq 37f
- sync
- li r0, 0xff
- li r6, XICS_MFRR
- stbcix r0, r5, r6 /* clear the IPI */
- stwcix r3, r5, r7 /* EOI it */
- 37: sync
/* increment the nap count and then go to nap mode */
ld r4, HSTATE_KVM_VCORE(r13)
addi r4, r4, VCORE_NAP_COUNT
- lwsync /* make previous updates visible */
51: lwarx r3, 0, r4
addi r3, r3, 1
stwcx. r3, 0, r4
kvm_no_guest:
li r0, KVM_HWTHREAD_IN_NAP
stb r0, HSTATE_HWTHREAD_STATE(r13)
+ kvm_do_nap:
li r3, LPCR_PECE0
mfspr r4, SPRN_LPCR
rlwimi r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
/* Required state:
*
- * R4 = vcpu pointer
+ * R4 = vcpu pointer (or NULL)
* MSR = ~IR|DR
* R13 = PACA
* R1 = host R1
std r0, PPC_LR_STKOFF(r1)
stdu r1, -112(r1)
- /* Set partition DABR */
- /* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
- li r5,3
- ld r6,VCPU_DABR(r4)
- mtspr SPRN_DABRX,r5
- mtspr SPRN_DABR,r6
- BEGIN_FTR_SECTION
- isync
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
- /* Load guest PMU registers */
- /* R4 is live here (vcpu pointer) */
- li r3, 1
- sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */
- mtspr SPRN_MMCR0, r3 /* freeze all counters, disable ints */
- isync
- lwz r3, VCPU_PMC(r4) /* always load up guest PMU registers */
- lwz r5, VCPU_PMC + 4(r4) /* to prevent information leak */
- lwz r6, VCPU_PMC + 8(r4)
- lwz r7, VCPU_PMC + 12(r4)
- lwz r8, VCPU_PMC + 16(r4)
- lwz r9, VCPU_PMC + 20(r4)
- BEGIN_FTR_SECTION
- lwz r10, VCPU_PMC + 24(r4)
- lwz r11, VCPU_PMC + 28(r4)
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
- mtspr SPRN_PMC1, r3
- mtspr SPRN_PMC2, r5
- mtspr SPRN_PMC3, r6
- mtspr SPRN_PMC4, r7
- mtspr SPRN_PMC5, r8
- mtspr SPRN_PMC6, r9
- BEGIN_FTR_SECTION
- mtspr SPRN_PMC7, r10
- mtspr SPRN_PMC8, r11
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
- ld r3, VCPU_MMCR(r4)
- ld r5, VCPU_MMCR + 8(r4)
- ld r6, VCPU_MMCR + 16(r4)
- ld r7, VCPU_SIAR(r4)
- ld r8, VCPU_SDAR(r4)
- mtspr SPRN_MMCR1, r5
- mtspr SPRN_MMCRA, r6
- mtspr SPRN_SIAR, r7
- mtspr SPRN_SDAR, r8
- mtspr SPRN_MMCR0, r3
- isync
-
- /* Load up FP, VMX and VSX registers */
- bl kvmppc_load_fp
-
- ld r14, VCPU_GPR(R14)(r4)
- ld r15, VCPU_GPR(R15)(r4)
- ld r16, VCPU_GPR(R16)(r4)
- ld r17, VCPU_GPR(R17)(r4)
- ld r18, VCPU_GPR(R18)(r4)
- ld r19, VCPU_GPR(R19)(r4)
- ld r20, VCPU_GPR(R20)(r4)
- ld r21, VCPU_GPR(R21)(r4)
- ld r22, VCPU_GPR(R22)(r4)
- ld r23, VCPU_GPR(R23)(r4)
- ld r24, VCPU_GPR(R24)(r4)
- ld r25, VCPU_GPR(R25)(r4)
- ld r26, VCPU_GPR(R26)(r4)
- ld r27, VCPU_GPR(R27)(r4)
- ld r28, VCPU_GPR(R28)(r4)
- ld r29, VCPU_GPR(R29)(r4)
- ld r30, VCPU_GPR(R30)(r4)
- ld r31, VCPU_GPR(R31)(r4)
-
- BEGIN_FTR_SECTION
- /* Switch DSCR to guest value */
- ld r5, VCPU_DSCR(r4)
- mtspr SPRN_DSCR, r5
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
- /*
- * Set the decrementer to the guest decrementer.
- */
- ld r8,VCPU_DEC_EXPIRES(r4)
- mftb r7
- subf r3,r7,r8
- mtspr SPRN_DEC,r3
- stw r3,VCPU_DEC(r4)
-
- ld r5, VCPU_SPRG0(r4)
- ld r6, VCPU_SPRG1(r4)
- ld r7, VCPU_SPRG2(r4)
- ld r8, VCPU_SPRG3(r4)
- mtspr SPRN_SPRG0, r5
- mtspr SPRN_SPRG1, r6
- mtspr SPRN_SPRG2, r7
- mtspr SPRN_SPRG3, r8
-
/* Save R1 in the PACA */
std r1, HSTATE_HOST_R1(r13)
- /* Load up DAR and DSISR */
- ld r5, VCPU_DAR(r4)
- lwz r6, VCPU_DSISR(r4)
- mtspr SPRN_DAR, r5
- mtspr SPRN_DSISR, r6
-
li r6, KVM_GUEST_MODE_HOST_HV
stb r6, HSTATE_IN_GUEST(r13)
- BEGIN_FTR_SECTION
- /* Restore AMR and UAMOR, set AMOR to all 1s */
- ld r5,VCPU_AMR(r4)
- ld r6,VCPU_UAMOR(r4)
- li r7,-1
- mtspr SPRN_AMR,r5
- mtspr SPRN_UAMOR,r6
- mtspr SPRN_AMOR,r7
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
/* Clear out SLB */
li r6,0
slbmte r6,r6
bne 21b
/* Primary thread switches to guest partition. */
- ld r9,VCPU_KVM(r4) /* pointer to struct kvm */
- lwz r6,VCPU_PTID(r4)
+ ld r9,VCORE_KVM(r5) /* pointer to struct kvm */
+ lbz r6,HSTATE_PTID(r13)
cmpwi r6,0
bne 20f
ld r6,KVM_SDR1(r9)
andc r7,r7,r0
stdcx. r7,0,r6
bne 23b
- li r6,128 /* and flush the TLB */
+ /* Flush the TLB of any entries for this LPID */
+ /* use arch 2.07S as a proxy for POWER8 */
+ BEGIN_FTR_SECTION
+ li r6,512 /* POWER8 has 512 sets */
+ FTR_SECTION_ELSE
+ li r6,128 /* POWER7 has 128 sets */
+ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_207S)
mtctr r6
li r7,0x800 /* IS field = 0b10 */
ptesync
beq 38f
mtspr SPRN_PCR, r7
38:
+
+ BEGIN_FTR_SECTION
+ /* DPDES is shared between threads */
+ ld r8, VCORE_DPDES(r5)
+ mtspr SPRN_DPDES, r8
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
li r0,1
stb r0,VCORE_IN_GUEST(r5) /* signal secondaries to continue */
b 10f
mtspr SPRN_RMOR,r8
isync
- /* Increment yield count if they have a VPA */
- ld r3, VCPU_VPA(r4)
- cmpdi r3, 0
- beq 25f
- lwz r5, LPPACA_YIELDCOUNT(r3)
- addi r5, r5, 1
- stw r5, LPPACA_YIELDCOUNT(r3)
- li r6, 1
- stb r6, VCPU_VPA_DIRTY(r4)
- 25:
/* Check if HDEC expires soon */
mfspr r3,SPRN_HDEC
- cmpwi r3,10
+ cmpwi r3,512 /* 1 microsecond */
li r12,BOOK3S_INTERRUPT_HV_DECREMENTER
- mr r9,r4
blt hdec_soon
-
- /* Save purr/spurr */
- mfspr r5,SPRN_PURR
- mfspr r6,SPRN_SPURR
- std r5,HSTATE_PURR(r13)
- std r6,HSTATE_SPURR(r13)
- ld r7,VCPU_PURR(r4)
- ld r8,VCPU_SPURR(r4)
- mtspr SPRN_PURR,r7
- mtspr SPRN_SPURR,r8
b 31f
/*
* We also have to invalidate the TLB since its
* entries aren't tagged with the LPID.
*/
- 30: ld r9,VCPU_KVM(r4) /* pointer to struct kvm */
+ 30: ld r5,HSTATE_KVM_VCORE(r13)
+ ld r9,VCORE_KVM(r5) /* pointer to struct kvm */
/* first take native_tlbie_lock */
.section ".toc","aw"
mfspr r3,SPRN_HDEC
cmpwi r3,10
li r12,BOOK3S_INTERRUPT_HV_DECREMENTER
- mr r9,r4
blt hdec_soon
/* Enable HDEC interrupts */
mfspr r0,SPRN_HID0
mfspr r0,SPRN_HID0
mfspr r0,SPRN_HID0
+ 31:
+ /* Do we have a guest vcpu to run? */
+ cmpdi r4, 0
+ beq kvmppc_primary_no_guest
+ kvmppc_got_guest:
/* Load up guest SLB entries */
- 31: lwz r5,VCPU_SLB_MAX(r4)
+ lwz r5,VCPU_SLB_MAX(r4)
cmpwi r5,0
beq 9f
mtctr r5
addi r6,r6,VCPU_SLB_SIZE
bdnz 1b
9:
+ /* Increment yield count if they have a VPA */
+ ld r3, VCPU_VPA(r4)
+ cmpdi r3, 0
+ beq 25f
+ lwz r5, LPPACA_YIELDCOUNT(r3)
+ addi r5, r5, 1
+ stw r5, LPPACA_YIELDCOUNT(r3)
+ li r6, 1
+ stb r6, VCPU_VPA_DIRTY(r4)
+ 25:
+
+ BEGIN_FTR_SECTION
+ /* Save purr/spurr */
+ mfspr r5,SPRN_PURR
+ mfspr r6,SPRN_SPURR
+ std r5,HSTATE_PURR(r13)
+ std r6,HSTATE_SPURR(r13)
+ ld r7,VCPU_PURR(r4)
+ ld r8,VCPU_SPURR(r4)
+ mtspr SPRN_PURR,r7
+ mtspr SPRN_SPURR,r8
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+ BEGIN_FTR_SECTION
+ /* Set partition DABR */
+ /* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
+ lwz r5,VCPU_DABRX(r4)
+ ld r6,VCPU_DABR(r4)
+ mtspr SPRN_DABRX,r5
+ mtspr SPRN_DABR,r6
+ BEGIN_FTR_SECTION_NESTED(89)
+ isync
+ END_FTR_SECTION_NESTED(CPU_FTR_ARCH_206, CPU_FTR_ARCH_206, 89)
+ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
+
+ /* Load guest PMU registers */
+ /* R4 is live here (vcpu pointer) */
+ li r3, 1
+ sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */
+ mtspr SPRN_MMCR0, r3 /* freeze all counters, disable ints */
+ isync
+ lwz r3, VCPU_PMC(r4) /* always load up guest PMU registers */
+ lwz r5, VCPU_PMC + 4(r4) /* to prevent information leak */
+ lwz r6, VCPU_PMC + 8(r4)
+ lwz r7, VCPU_PMC + 12(r4)
+ lwz r8, VCPU_PMC + 16(r4)
+ lwz r9, VCPU_PMC + 20(r4)
+ BEGIN_FTR_SECTION
+ lwz r10, VCPU_PMC + 24(r4)
+ lwz r11, VCPU_PMC + 28(r4)
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+ mtspr SPRN_PMC1, r3
+ mtspr SPRN_PMC2, r5
+ mtspr SPRN_PMC3, r6
+ mtspr SPRN_PMC4, r7
+ mtspr SPRN_PMC5, r8
+ mtspr SPRN_PMC6, r9
+ BEGIN_FTR_SECTION
+ mtspr SPRN_PMC7, r10
+ mtspr SPRN_PMC8, r11
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+ ld r3, VCPU_MMCR(r4)
+ ld r5, VCPU_MMCR + 8(r4)
+ ld r6, VCPU_MMCR + 16(r4)
+ ld r7, VCPU_SIAR(r4)
+ ld r8, VCPU_SDAR(r4)
+ mtspr SPRN_MMCR1, r5
+ mtspr SPRN_MMCRA, r6
+ mtspr SPRN_SIAR, r7
+ mtspr SPRN_SDAR, r8
+ BEGIN_FTR_SECTION
+ ld r5, VCPU_MMCR + 24(r4)
+ ld r6, VCPU_SIER(r4)
+ lwz r7, VCPU_PMC + 24(r4)
+ lwz r8, VCPU_PMC + 28(r4)
+ ld r9, VCPU_MMCR + 32(r4)
+ mtspr SPRN_MMCR2, r5
+ mtspr SPRN_SIER, r6
+ mtspr SPRN_SPMC1, r7
+ mtspr SPRN_SPMC2, r8
+ mtspr SPRN_MMCRS, r9
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+ mtspr SPRN_MMCR0, r3
+ isync
+
+ /* Load up FP, VMX and VSX registers */
+ bl kvmppc_load_fp
+
+ ld r14, VCPU_GPR(R14)(r4)
+ ld r15, VCPU_GPR(R15)(r4)
+ ld r16, VCPU_GPR(R16)(r4)
+ ld r17, VCPU_GPR(R17)(r4)
+ ld r18, VCPU_GPR(R18)(r4)
+ ld r19, VCPU_GPR(R19)(r4)
+ ld r20, VCPU_GPR(R20)(r4)
+ ld r21, VCPU_GPR(R21)(r4)
+ ld r22, VCPU_GPR(R22)(r4)
+ ld r23, VCPU_GPR(R23)(r4)
+ ld r24, VCPU_GPR(R24)(r4)
+ ld r25, VCPU_GPR(R25)(r4)
+ ld r26, VCPU_GPR(R26)(r4)
+ ld r27, VCPU_GPR(R27)(r4)
+ ld r28, VCPU_GPR(R28)(r4)
+ ld r29, VCPU_GPR(R29)(r4)
+ ld r30, VCPU_GPR(R30)(r4)
+ ld r31, VCPU_GPR(R31)(r4)
+
+ BEGIN_FTR_SECTION
+ /* Switch DSCR to guest value */
+ ld r5, VCPU_DSCR(r4)
+ mtspr SPRN_DSCR, r5
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+ BEGIN_FTR_SECTION
+ /* Skip next section on POWER7 or PPC970 */
+ b 8f
+ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
+ /* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
+ mfmsr r8
+ li r0, 1
+ rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+ mtmsrd r8
+
+ /* Load up POWER8-specific registers */
+ ld r5, VCPU_IAMR(r4)
+ lwz r6, VCPU_PSPB(r4)
+ ld r7, VCPU_FSCR(r4)
+ mtspr SPRN_IAMR, r5
+ mtspr SPRN_PSPB, r6
+ mtspr SPRN_FSCR, r7
+ ld r5, VCPU_DAWR(r4)
+ ld r6, VCPU_DAWRX(r4)
+ ld r7, VCPU_CIABR(r4)
+ ld r8, VCPU_TAR(r4)
+ mtspr SPRN_DAWR, r5
+ mtspr SPRN_DAWRX, r6
+ mtspr SPRN_CIABR, r7
+ mtspr SPRN_TAR, r8
+ ld r5, VCPU_IC(r4)
+ ld r6, VCPU_VTB(r4)
+ mtspr SPRN_IC, r5
+ mtspr SPRN_VTB, r6
+ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ ld r5, VCPU_TFHAR(r4)
+ ld r6, VCPU_TFIAR(r4)
+ ld r7, VCPU_TEXASR(r4)
+ mtspr SPRN_TFHAR, r5
+ mtspr SPRN_TFIAR, r6
+ mtspr SPRN_TEXASR, r7
+ #endif
+ ld r8, VCPU_EBBHR(r4)
+ mtspr SPRN_EBBHR, r8
+ ld r5, VCPU_EBBRR(r4)
+ ld r6, VCPU_BESCR(r4)
+ ld r7, VCPU_CSIGR(r4)
+ ld r8, VCPU_TACR(r4)
+ mtspr SPRN_EBBRR, r5
+ mtspr SPRN_BESCR, r6
+ mtspr SPRN_CSIGR, r7
+ mtspr SPRN_TACR, r8
+ ld r5, VCPU_TCSCR(r4)
+ ld r6, VCPU_ACOP(r4)
+ lwz r7, VCPU_GUEST_PID(r4)
+ ld r8, VCPU_WORT(r4)
+ mtspr SPRN_TCSCR, r5
+ mtspr SPRN_ACOP, r6
+ mtspr SPRN_PID, r7
+ mtspr SPRN_WORT, r8
+ 8:
+
+ /*
+ * Set the decrementer to the guest decrementer.
+ */
+ ld r8,VCPU_DEC_EXPIRES(r4)
+ mftb r7
+ subf r3,r7,r8
+ mtspr SPRN_DEC,r3
+ stw r3,VCPU_DEC(r4)
+
+ ld r5, VCPU_SPRG0(r4)
+ ld r6, VCPU_SPRG1(r4)
+ ld r7, VCPU_SPRG2(r4)
+ ld r8, VCPU_SPRG3(r4)
+ mtspr SPRN_SPRG0, r5
+ mtspr SPRN_SPRG1, r6
+ mtspr SPRN_SPRG2, r7
+ mtspr SPRN_SPRG3, r8
+
+ /* Load up DAR and DSISR */
+ ld r5, VCPU_DAR(r4)
+ lwz r6, VCPU_DSISR(r4)
+ mtspr SPRN_DAR, r5
+ mtspr SPRN_DSISR, r6
+
+ BEGIN_FTR_SECTION
+ /* Restore AMR and UAMOR, set AMOR to all 1s */
+ ld r5,VCPU_AMR(r4)
+ ld r6,VCPU_UAMOR(r4)
+ li r7,-1
+ mtspr SPRN_AMR,r5
+ mtspr SPRN_UAMOR,r6
+ mtspr SPRN_AMOR,r7
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
/* Restore state of CTRL run bit; assume 1 on entry */
lwz r5,VCPU_CTRL(r4)
mtctr r6
mtxer r7
+ kvmppc_cede_reentry: /* r4 = vcpu, r13 = paca */
ld r10, VCPU_PC(r4)
ld r11, VCPU_MSR(r4)
- kvmppc_cede_reentry: /* r4 = vcpu, r13 = paca */
ld r6, VCPU_SRR0(r4)
ld r7, VCPU_SRR1(r4)
+ mtspr SPRN_SRR0, r6
+ mtspr SPRN_SRR1, r7
+ deliver_guest_interrupt:
/* r11 = vcpu->arch.msr & ~MSR_HV */
rldicl r11, r11, 63 - MSR_HV_LG, 1
rotldi r11, r11, 1 + MSR_HV_LG
ori r11, r11, MSR_ME
/* Check if we can deliver an external or decrementer interrupt now */
- ld r0,VCPU_PENDING_EXC(r4)
- lis r8,(1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h
- and r0,r0,r8
- cmpdi cr1,r0,0
- andi. r0,r11,MSR_EE
- beq cr1,11f
+ ld r0, VCPU_PENDING_EXC(r4)
+ rldicl r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL_LEVEL, 63
+ cmpdi cr1, r0, 0
+ andi. r8, r11, MSR_EE
BEGIN_FTR_SECTION
- mfspr r8,SPRN_LPCR
- ori r8,r8,LPCR_MER
- mtspr SPRN_LPCR,r8
+ mfspr r8, SPRN_LPCR
+ /* Insert EXTERNAL_LEVEL bit into LPCR at the MER bit position */
+ rldimi r8, r0, LPCR_MER_SH, 63 - LPCR_MER_SH
+ mtspr SPRN_LPCR, r8
isync
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
beq 5f
- li r0,BOOK3S_INTERRUPT_EXTERNAL
- 12: mr r6,r10
- mr r10,r0
- mr r7,r11
- li r11,(MSR_ME << 1) | 1 /* synthesize MSR_SF | MSR_ME */
- rotldi r11,r11,63
- b 5f
- 11: beq 5f
- mfspr r0,SPRN_DEC
- cmpwi r0,0
- li r0,BOOK3S_INTERRUPT_DECREMENTER
- blt 12b
+ li r0, BOOK3S_INTERRUPT_EXTERNAL
+ bne cr1, 12f
+ mfspr r0, SPRN_DEC
+ cmpwi r0, 0
+ li r0, BOOK3S_INTERRUPT_DECREMENTER
+ bge 5f
- /* Move SRR0 and SRR1 into the respective regs */
- 5: mtspr SPRN_SRR0, r6
- mtspr SPRN_SRR1, r7
+ 12: mtspr SPRN_SRR0, r10
+ mr r10,r0
+ mtspr SPRN_SRR1, r11
+ ld r11, VCPU_INTR_MSR(r4)
+ 5:
+ /*
+ * Required state:
+ * R4 = vcpu
+ * R10: value for HSRR0
+ * R11: value for HSRR1
+ * R13 = PACA
+ */
fast_guest_return:
li r0,0
stb r0,VCPU_CEDED(r4) /* cancel cede */
* guest CR, R12 saved in shadow VCPU SCRATCH1/0
* guest R13 saved in SPRN_SCRATCH0
*/
- /* abuse host_r2 as third scratch area; we get r2 from PACATOC(r13) */
- std r9, HSTATE_HOST_R2(r13)
+ std r9, HSTATE_SCRATCH2(r13)
lbz r9, HSTATE_IN_GUEST(r13)
cmpwi r9, KVM_GUEST_MODE_HOST_HV
beq kvmppc_bad_host_intr
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
cmpwi r9, KVM_GUEST_MODE_GUEST
- ld r9, HSTATE_HOST_R2(r13)
+ ld r9, HSTATE_SCRATCH2(r13)
beq kvmppc_interrupt_pr
#endif
/* We're now back in the host but in guest MMU context */
std r6, VCPU_GPR(R6)(r9)
std r7, VCPU_GPR(R7)(r9)
std r8, VCPU_GPR(R8)(r9)
- ld r0, HSTATE_HOST_R2(r13)
+ ld r0, HSTATE_SCRATCH2(r13)
std r0, VCPU_GPR(R9)(r9)
std r10, VCPU_GPR(R10)(r9)
std r11, VCPU_GPR(R11)(r9)
/* External interrupt, first check for host_ipi. If this is
* set, we know the host wants us out so let's do it now
*/
- do_ext_interrupt:
bl kvmppc_read_intr
cmpdi r3, 0
bgt ext_interrupt_to_host
- /* Allright, looks like an IPI for the guest, we need to set MER */
/* Check if any CPU is heading out to the host, if so head out too */
ld r5, HSTATE_KVM_VCORE(r13)
lwz r0, VCORE_ENTRY_EXIT(r5)
cmpwi r0, 0x100
bge ext_interrupt_to_host
- /* See if there is a pending interrupt for the guest */
- mfspr r8, SPRN_LPCR
- ld r0, VCPU_PENDING_EXC(r9)
- /* Insert EXTERNAL_LEVEL bit into LPCR at the MER bit position */
- rldicl. r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL_LEVEL, 63
- rldimi r8, r0, LPCR_MER_SH, 63 - LPCR_MER_SH
- beq 2f
-
- /* And if the guest EE is set, we can deliver immediately, else
- * we return to the guest with MER set
- */
- andi. r0, r11, MSR_EE
- beq 2f
- mtspr SPRN_SRR0, r10
- mtspr SPRN_SRR1, r11
- li r10, BOOK3S_INTERRUPT_EXTERNAL
- li r11, (MSR_ME << 1) | 1 /* synthesize MSR_SF | MSR_ME */
- rotldi r11, r11, 63
- 2: mr r4, r9
- mtspr SPRN_LPCR, r8
- b fast_guest_return
+ /* Return to guest after delivering any pending interrupt */
+ mr r4, r9
+ b deliver_guest_interrupt
ext_interrupt_to_host:
subf r5,r7,r5
subf r6,r8,r6
- /*
- * Restore host PURR/SPURR and add guest times
- * so that the time in the guest gets accounted.
- */
- ld r3,HSTATE_PURR(r13)
- ld r4,HSTATE_SPURR(r13)
- add r3,r3,r5
- add r4,r4,r6
- mtspr SPRN_PURR,r3
- mtspr SPRN_SPURR,r4
- END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_201)
+ /*
+ * Restore host PURR/SPURR and add guest times
+ * so that the time in the guest gets accounted.
+ */
+ ld r3,HSTATE_PURR(r13)
+ ld r4,HSTATE_SPURR(r13)
+ add r3,r3,r5
+ add r4,r4,r6
+ mtspr SPRN_PURR,r3
+ mtspr SPRN_SPURR,r4
+ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_201)
+
+ /* Save DEC */
+ mfspr r5,SPRN_DEC
+ mftb r6
+ extsw r5,r5
+ add r5,r5,r6
+ std r5,VCPU_DEC_EXPIRES(r9)
+
+ BEGIN_FTR_SECTION
+ b 8f
+ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
+ /* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
+ mfmsr r8
+ li r0, 1
+ rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+ mtmsrd r8
+
+ /* Save POWER8-specific registers */
+ mfspr r5, SPRN_IAMR
+ mfspr r6, SPRN_PSPB
+ mfspr r7, SPRN_FSCR
+ std r5, VCPU_IAMR(r9)
+ stw r6, VCPU_PSPB(r9)
+ std r7, VCPU_FSCR(r9)
+ mfspr r5, SPRN_IC
+ mfspr r6, SPRN_VTB
+ mfspr r7, SPRN_TAR
+ std r5, VCPU_IC(r9)
+ std r6, VCPU_VTB(r9)
+ std r7, VCPU_TAR(r9)
+ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ mfspr r5, SPRN_TFHAR
+ mfspr r6, SPRN_TFIAR
+ mfspr r7, SPRN_TEXASR
+ std r5, VCPU_TFHAR(r9)
+ std r6, VCPU_TFIAR(r9)
+ std r7, VCPU_TEXASR(r9)
+ #endif
+ mfspr r8, SPRN_EBBHR
+ std r8, VCPU_EBBHR(r9)
+ mfspr r5, SPRN_EBBRR
+ mfspr r6, SPRN_BESCR
+ mfspr r7, SPRN_CSIGR
+ mfspr r8, SPRN_TACR
+ std r5, VCPU_EBBRR(r9)
+ std r6, VCPU_BESCR(r9)
+ std r7, VCPU_CSIGR(r9)
+ std r8, VCPU_TACR(r9)
+ mfspr r5, SPRN_TCSCR
+ mfspr r6, SPRN_ACOP
+ mfspr r7, SPRN_PID
+ mfspr r8, SPRN_WORT
+ std r5, VCPU_TCSCR(r9)
+ std r6, VCPU_ACOP(r9)
+ stw r7, VCPU_GUEST_PID(r9)
+ std r8, VCPU_WORT(r9)
+ 8:
+
+ /* Save and reset AMR and UAMOR before turning on the MMU */
+ BEGIN_FTR_SECTION
+ mfspr r5,SPRN_AMR
+ mfspr r6,SPRN_UAMOR
+ std r5,VCPU_AMR(r9)
+ std r6,VCPU_UAMOR(r9)
+ li r6,0
+ mtspr SPRN_AMR,r6
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+ /* Switch DSCR back to host value */
+ BEGIN_FTR_SECTION
+ mfspr r8, SPRN_DSCR
+ ld r7, HSTATE_DSCR(r13)
+ std r8, VCPU_DSCR(r9)
+ mtspr SPRN_DSCR, r7
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
+ /* Save non-volatile GPRs */
+ std r14, VCPU_GPR(R14)(r9)
+ std r15, VCPU_GPR(R15)(r9)
+ std r16, VCPU_GPR(R16)(r9)
+ std r17, VCPU_GPR(R17)(r9)
+ std r18, VCPU_GPR(R18)(r9)
+ std r19, VCPU_GPR(R19)(r9)
+ std r20, VCPU_GPR(R20)(r9)
+ std r21, VCPU_GPR(R21)(r9)
+ std r22, VCPU_GPR(R22)(r9)
+ std r23, VCPU_GPR(R23)(r9)
+ std r24, VCPU_GPR(R24)(r9)
+ std r25, VCPU_GPR(R25)(r9)
+ std r26, VCPU_GPR(R26)(r9)
+ std r27, VCPU_GPR(R27)(r9)
+ std r28, VCPU_GPR(R28)(r9)
+ std r29, VCPU_GPR(R29)(r9)
+ std r30, VCPU_GPR(R30)(r9)
+ std r31, VCPU_GPR(R31)(r9)
+
+ /* Save SPRGs */
+ mfspr r3, SPRN_SPRG0
+ mfspr r4, SPRN_SPRG1
+ mfspr r5, SPRN_SPRG2
+ mfspr r6, SPRN_SPRG3
+ std r3, VCPU_SPRG0(r9)
+ std r4, VCPU_SPRG1(r9)
+ std r5, VCPU_SPRG2(r9)
+ std r6, VCPU_SPRG3(r9)
+
+ /* save FP state */
+ mr r3, r9
+ bl kvmppc_save_fp
+ /* Increment yield count if they have a VPA */
+ ld r8, VCPU_VPA(r9) /* do they have a VPA? */
+ cmpdi r8, 0
+ beq 25f
+ lwz r3, LPPACA_YIELDCOUNT(r8)
+ addi r3, r3, 1
+ stw r3, LPPACA_YIELDCOUNT(r8)
+ li r3, 1
+ stb r3, VCPU_VPA_DIRTY(r9)
+ 25:
+ /* Save PMU registers if requested */
+ /* r8 and cr0.eq are live here */
+ li r3, 1
+ sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */
+ mfspr r4, SPRN_MMCR0 /* save MMCR0 */
+ mtspr SPRN_MMCR0, r3 /* freeze all counters, disable ints */
+ mfspr r6, SPRN_MMCRA
+ BEGIN_FTR_SECTION
+ /* On P7, clear MMCRA in order to disable SDAR updates */
+ li r7, 0
+ mtspr SPRN_MMCRA, r7
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+ isync
+ beq 21f /* if no VPA, save PMU stuff anyway */
+ lbz r7, LPPACA_PMCINUSE(r8)
+ cmpwi r7, 0 /* did they ask for PMU stuff to be saved? */
+ bne 21f
+ std r3, VCPU_MMCR(r9) /* if not, set saved MMCR0 to FC */
+ b 22f
+ 21: mfspr r5, SPRN_MMCR1
+ mfspr r7, SPRN_SIAR
+ mfspr r8, SPRN_SDAR
+ std r4, VCPU_MMCR(r9)
+ std r5, VCPU_MMCR + 8(r9)
+ std r6, VCPU_MMCR + 16(r9)
+ std r7, VCPU_SIAR(r9)
+ std r8, VCPU_SDAR(r9)
+ mfspr r3, SPRN_PMC1
+ mfspr r4, SPRN_PMC2
+ mfspr r5, SPRN_PMC3
+ mfspr r6, SPRN_PMC4
+ mfspr r7, SPRN_PMC5
+ mfspr r8, SPRN_PMC6
+ BEGIN_FTR_SECTION
+ mfspr r10, SPRN_PMC7
+ mfspr r11, SPRN_PMC8
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+ stw r3, VCPU_PMC(r9)
+ stw r4, VCPU_PMC + 4(r9)
+ stw r5, VCPU_PMC + 8(r9)
+ stw r6, VCPU_PMC + 12(r9)
+ stw r7, VCPU_PMC + 16(r9)
+ stw r8, VCPU_PMC + 20(r9)
+ BEGIN_FTR_SECTION
+ stw r10, VCPU_PMC + 24(r9)
+ stw r11, VCPU_PMC + 28(r9)
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
+ BEGIN_FTR_SECTION
+ mfspr r4, SPRN_MMCR2
+ mfspr r5, SPRN_SIER
+ mfspr r6, SPRN_SPMC1
+ mfspr r7, SPRN_SPMC2
+ mfspr r8, SPRN_MMCRS
+ std r4, VCPU_MMCR + 24(r9)
+ std r5, VCPU_SIER(r9)
+ stw r6, VCPU_PMC + 24(r9)
+ stw r7, VCPU_PMC + 28(r9)
+ std r8, VCPU_MMCR + 32(r9)
+ lis r4, 0x8000
+ mtspr SPRN_MMCRS, r4
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+ 22:
/* Clear out SLB */
li r5,0
slbmte r5,r5
slbia
ptesync
- hdec_soon: /* r9 = vcpu, r12 = trap, r13 = paca */
+ hdec_soon: /* r12 = trap, r13 = paca */
BEGIN_FTR_SECTION
b 32f
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
*/
/* Increment the threads-exiting-guest count in the 0xff00
bits of vcore->entry_exit_count */
- lwsync
ld r5,HSTATE_KVM_VCORE(r13)
addi r6,r5,VCORE_ENTRY_EXIT
41: lwarx r3,0,r6
addi r0,r3,0x100
stwcx. r0,0,r6
bne 41b
- lwsync
+ isync /* order stwcx. vs. reading napping_threads */
/*
* At this point we have an interrupt that we have to pass
*/
cmpwi r3,0x100 /* Are we the first here? */
bge 43f
- cmpwi r3,1 /* Are any other threads in the guest? */
- ble 43f
cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
beq 40f
li r0,0
* doesn't wake CPUs up from nap.
*/
lwz r3,VCORE_NAPPING_THREADS(r5)
- lwz r4,VCPU_PTID(r9)
+ lbz r4,HSTATE_PTID(r13)
li r0,1
sld r0,r0,r4
andc. r3,r3,r0 /* no sense IPI'ing ourselves */
beq 43f
+ /* Order entry/exit update vs. IPIs */
+ sync
mulli r4,r4,PACA_SIZE /* get paca for thread 0 */
subf r6,r4,r13
42: andi. r0,r3,1
addi r6,r6,PACA_SIZE
bne 42b
+ secondary_too_late:
/* Secondary threads wait for primary to do partition switch */
- 43: ld r4,VCPU_KVM(r9) /* pointer to struct kvm */
- ld r5,HSTATE_KVM_VCORE(r13)
- lwz r3,VCPU_PTID(r9)
+ 43: ld r5,HSTATE_KVM_VCORE(r13)
+ ld r4,VCORE_KVM(r5) /* pointer to struct kvm */
+ lbz r3,HSTATE_PTID(r13)
cmpwi r3,0
beq 15f
HMT_LOW
mtspr SPRN_LPID,r7
isync
+ BEGIN_FTR_SECTION
+ /* DPDES is shared between threads */
+ mfspr r7, SPRN_DPDES
+ std r7, VCORE_DPDES(r5)
+ /* clear DPDES so we don't get guest doorbells in the host */
+ li r8, 0
+ mtspr SPRN_DPDES, r8
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
/* Subtract timebase offset from timebase */
ld r8,VCORE_TB_OFFSET(r5)
cmpdi r8,0
* We have to lock against concurrent tlbies, and
* we have to flush the whole TLB.
*/
- 32: ld r4,VCPU_KVM(r9) /* pointer to struct kvm */
+ 32: ld r5,HSTATE_KVM_VCORE(r13)
+ ld r4,VCORE_KVM(r5) /* pointer to struct kvm */
/* Take the guest's tlbie_lock */
#ifdef __BIG_ENDIAN__
add r5,r5,r6
std r5,VCPU_DEC_EXPIRES(r9)
+ BEGIN_FTR_SECTION
+ b 8f
+ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
+ /* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
+ mfmsr r8
+ li r0, 1
+ rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+ mtmsrd r8
+
+ /* Save POWER8-specific registers */
+ mfspr r5, SPRN_IAMR
+ mfspr r6, SPRN_PSPB
+ mfspr r7, SPRN_FSCR
+ std r5, VCPU_IAMR(r9)
+ stw r6, VCPU_PSPB(r9)
+ std r7, VCPU_FSCR(r9)
+ mfspr r5, SPRN_IC
+ mfspr r6, SPRN_VTB
+ mfspr r7, SPRN_TAR
+ std r5, VCPU_IC(r9)
+ std r6, VCPU_VTB(r9)
+ std r7, VCPU_TAR(r9)
+ #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ mfspr r5, SPRN_TFHAR
+ mfspr r6, SPRN_TFIAR
+ mfspr r7, SPRN_TEXASR
+ std r5, VCPU_TFHAR(r9)
+ std r6, VCPU_TFIAR(r9)
+ std r7, VCPU_TEXASR(r9)
+ #endif
+ mfspr r8, SPRN_EBBHR
+ std r8, VCPU_EBBHR(r9)
+ mfspr r5, SPRN_EBBRR
+ mfspr r6, SPRN_BESCR
+ mfspr r7, SPRN_CSIGR
+ mfspr r8, SPRN_TACR
+ std r5, VCPU_EBBRR(r9)
+ std r6, VCPU_BESCR(r9)
+ std r7, VCPU_CSIGR(r9)
+ std r8, VCPU_TACR(r9)
+ mfspr r5, SPRN_TCSCR
+ mfspr r6, SPRN_ACOP
+ mfspr r7, SPRN_PID
+ mfspr r8, SPRN_WORT
+ std r5, VCPU_TCSCR(r9)
+ std r6, VCPU_ACOP(r9)
+ stw r7, VCPU_GUEST_PID(r9)
+ std r8, VCPU_WORT(r9)
+ 8:
+
/* Save and reset AMR and UAMOR before turning on the MMU */
BEGIN_FTR_SECTION
mfspr r5,SPRN_AMR
li r0, KVM_GUEST_MODE_NONE
stb r0, HSTATE_IN_GUEST(r13)
- /* Switch DSCR back to host value */
- BEGIN_FTR_SECTION
- mfspr r8, SPRN_DSCR
- ld r7, HSTATE_DSCR(r13)
- std r8, VCPU_DSCR(r9)
- mtspr SPRN_DSCR, r7
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
- /* Save non-volatile GPRs */
- std r14, VCPU_GPR(R14)(r9)
- std r15, VCPU_GPR(R15)(r9)
- std r16, VCPU_GPR(R16)(r9)
- std r17, VCPU_GPR(R17)(r9)
- std r18, VCPU_GPR(R18)(r9)
- std r19, VCPU_GPR(R19)(r9)
- std r20, VCPU_GPR(R20)(r9)
- std r21, VCPU_GPR(R21)(r9)
- std r22, VCPU_GPR(R22)(r9)
- std r23, VCPU_GPR(R23)(r9)
- std r24, VCPU_GPR(R24)(r9)
- std r25, VCPU_GPR(R25)(r9)
- std r26, VCPU_GPR(R26)(r9)
- std r27, VCPU_GPR(R27)(r9)
- std r28, VCPU_GPR(R28)(r9)
- std r29, VCPU_GPR(R29)(r9)
- std r30, VCPU_GPR(R30)(r9)
- std r31, VCPU_GPR(R31)(r9)
-
- /* Save SPRGs */
- mfspr r3, SPRN_SPRG0
- mfspr r4, SPRN_SPRG1
- mfspr r5, SPRN_SPRG2
- mfspr r6, SPRN_SPRG3
- std r3, VCPU_SPRG0(r9)
- std r4, VCPU_SPRG1(r9)
- std r5, VCPU_SPRG2(r9)
- std r6, VCPU_SPRG3(r9)
-
- /* save FP state */
- mr r3, r9
- bl .kvmppc_save_fp
-
- /* Increment yield count if they have a VPA */
- ld r8, VCPU_VPA(r9) /* do they have a VPA? */
- cmpdi r8, 0
- beq 25f
- lwz r3, LPPACA_YIELDCOUNT(r8)
- addi r3, r3, 1
- stw r3, LPPACA_YIELDCOUNT(r8)
- li r3, 1
- stb r3, VCPU_VPA_DIRTY(r9)
- 25:
- /* Save PMU registers if requested */
- /* r8 and cr0.eq are live here */
- li r3, 1
- sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */
- mfspr r4, SPRN_MMCR0 /* save MMCR0 */
- mtspr SPRN_MMCR0, r3 /* freeze all counters, disable ints */
- mfspr r6, SPRN_MMCRA
- BEGIN_FTR_SECTION
- /* On P7, clear MMCRA in order to disable SDAR updates */
- li r7, 0
- mtspr SPRN_MMCRA, r7
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
- isync
- beq 21f /* if no VPA, save PMU stuff anyway */
- lbz r7, LPPACA_PMCINUSE(r8)
- cmpwi r7, 0 /* did they ask for PMU stuff to be saved? */
- bne 21f
- std r3, VCPU_MMCR(r9) /* if not, set saved MMCR0 to FC */
- b 22f
- 21: mfspr r5, SPRN_MMCR1
- mfspr r7, SPRN_SIAR
- mfspr r8, SPRN_SDAR
- std r4, VCPU_MMCR(r9)
- std r5, VCPU_MMCR + 8(r9)
- std r6, VCPU_MMCR + 16(r9)
- std r7, VCPU_SIAR(r9)
- std r8, VCPU_SDAR(r9)
- mfspr r3, SPRN_PMC1
- mfspr r4, SPRN_PMC2
- mfspr r5, SPRN_PMC3
- mfspr r6, SPRN_PMC4
- mfspr r7, SPRN_PMC5
- mfspr r8, SPRN_PMC6
- BEGIN_FTR_SECTION
- mfspr r10, SPRN_PMC7
- mfspr r11, SPRN_PMC8
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
- stw r3, VCPU_PMC(r9)
- stw r4, VCPU_PMC + 4(r9)
- stw r5, VCPU_PMC + 8(r9)
- stw r6, VCPU_PMC + 12(r9)
- stw r7, VCPU_PMC + 16(r9)
- stw r8, VCPU_PMC + 20(r9)
- BEGIN_FTR_SECTION
- stw r10, VCPU_PMC + 24(r9)
- stw r11, VCPU_PMC + 28(r9)
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
- 22:
ld r0, 112+PPC_LR_STKOFF(r1)
addi r1, r1, 112
mtlr r0
blr
- secondary_too_late:
- ld r5,HSTATE_KVM_VCORE(r13)
- HMT_LOW
- 13: lbz r3,VCORE_IN_GUEST(r5)
- cmpwi r3,0
- bne 13b
- HMT_MEDIUM
- li r0, KVM_GUEST_MODE_NONE
- stb r0, HSTATE_IN_GUEST(r13)
- ld r11,PACA_SLBSHADOWPTR(r13)
-
- .rept SLB_NUM_BOLTED
- ld r5,SLBSHADOW_SAVEAREA(r11)
- ld r6,SLBSHADOW_SAVEAREA+8(r11)
- andis. r7,r5,SLB_ESID_V@h
- beq 1f
- slbmte r6,r5
- 1: addi r11,r11,16
- .endr
- b 22b
/*
* Check whether an HDSI is an HPTE not found fault or something else.
mtspr SPRN_SRR0, r10
mtspr SPRN_SRR1, r11
li r10, BOOK3S_INTERRUPT_DATA_STORAGE
- li r11, (MSR_ME << 1) | 1 /* synthesize MSR_SF | MSR_ME */
- rotldi r11, r11, 63
+ ld r11, VCPU_INTR_MSR(r9)
fast_interrupt_c_return:
6: ld r7, VCPU_CTR(r9)
lwz r8, VCPU_XER(r9)
1: mtspr SPRN_SRR0, r10
mtspr SPRN_SRR1, r11
li r10, BOOK3S_INTERRUPT_INST_STORAGE
- li r11, (MSR_ME << 1) | 1 /* synthesize MSR_SF | MSR_ME */
- rotldi r11, r11, 63
+ ld r11, VCPU_INTR_MSR(r9)
b fast_interrupt_c_return
3: ld r6, VCPU_KVM(r9) /* not relocated, use VRMA */
hcall_try_real_mode:
ld r3,VCPU_GPR(R3)(r9)
andi. r0,r11,MSR_PR
- bne guest_exit_cont
+ /* sc 1 from userspace - reflect to guest syscall */
+ bne sc_1_fast_return
clrrdi r3,r3,2
cmpldi r3,hcall_real_table_end - hcall_real_table
bge guest_exit_cont
ld r11,VCPU_MSR(r4)
b fast_guest_return
+ sc_1_fast_return:
+ mtspr SPRN_SRR0,r10
+ mtspr SPRN_SRR1,r11
+ li r10, BOOK3S_INTERRUPT_SYSCALL
+ ld r11, VCPU_INTR_MSR(r9)
+ mr r4,r9
+ b fast_guest_return
+
/* We've attempted a real mode hcall, but it's punted it back
* to userspace. We need to restore some clobbered volatiles
* before resuming the pass-it-to-qemu path */
.long 0 /* 0x11c */
.long 0 /* 0x120 */
.long .kvmppc_h_bulk_remove - hcall_real_table
+ .long 0 /* 0x128 */
+ .long 0 /* 0x12c */
+ .long 0 /* 0x130 */
+ .long .kvmppc_h_set_xdabr - hcall_real_table
hcall_real_table_end:
ignore_hdec:
mr r4,r9
b fast_guest_return
+ _GLOBAL(kvmppc_h_set_xdabr)
+ andi. r0, r5, DABRX_USER | DABRX_KERNEL
+ beq 6f
+ li r0, DABRX_USER | DABRX_KERNEL | DABRX_BTI
+ andc. r0, r5, r0
+ beq 3f
+ 6: li r3, H_PARAMETER
+ blr
+
_GLOBAL(kvmppc_h_set_dabr)
+ li r5, DABRX_USER | DABRX_KERNEL
+ 3:
+ BEGIN_FTR_SECTION
+ b 2f
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
std r4,VCPU_DABR(r3)
+ stw r5, VCPU_DABRX(r3)
+ mtspr SPRN_DABRX, r5
/* Work around P7 bug where DABR can get corrupted on mtspr */
1: mtspr SPRN_DABR,r4
mfspr r5, SPRN_DABR
li r3,0
blr
+ /* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */
+ 2: rlwimi r5, r4, 5, DAWRX_DR | DAWRX_DW
+ rlwimi r5, r4, 1, DAWRX_WT
+ clrrdi r4, r4, 3
+ std r4, VCPU_DAWR(r3)
+ std r5, VCPU_DAWRX(r3)
+ mtspr SPRN_DAWR, r4
+ mtspr SPRN_DAWRX, r5
+ li r3, 0
+ blr
+
_GLOBAL(kvmppc_h_cede)
ori r11,r11,MSR_EE
std r11,VCPU_MSR(r3)
* up to the host.
*/
ld r5,HSTATE_KVM_VCORE(r13)
- lwz r6,VCPU_PTID(r3)
+ lbz r6,HSTATE_PTID(r13)
lwz r8,VCORE_ENTRY_EXIT(r5)
clrldi r8,r8,56
li r0,1
bge kvm_cede_exit
stwcx. r4,0,r6
bne 31b
- li r0,1
+ /* order napping_threads update vs testing entry_exit_count */
+ isync
+ li r0,NAPPING_CEDE
stb r0,HSTATE_NAPPING(r13)
- mr r4,r3
- /* order napping_threads update vs testing entry_exit_count */
- lwsync
lwz r7,VCORE_ENTRY_EXIT(r5)
cmpwi r7,0x100
bge 33f /* another thread already exiting */
std r31, VCPU_GPR(R31)(r3)
/* save FP state */
- bl .kvmppc_save_fp
+ bl kvmppc_save_fp
/*
- * Take a nap until a decrementer or external interrupt occurs,
- * with PECE1 (wake on decr) and PECE0 (wake on external) set in LPCR
+ * Take a nap until a decrementer or external or doobell interrupt
+ * occurs, with PECE1, PECE0 and PECEDP set in LPCR
*/
li r0,1
stb r0,HSTATE_HWTHREAD_REQ(r13)
mfspr r5,SPRN_LPCR
ori r5,r5,LPCR_PECE0 | LPCR_PECE1
+ BEGIN_FTR_SECTION
+ oris r5,r5,LPCR_PECEDP@h
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mtspr SPRN_LPCR,r5
isync
li r0, 0
nap
b .
+ 33: mr r4, r3
+ li r3, 0
+ li r12, 0
+ b 34f
+
kvm_end_cede:
/* get vcpu pointer */
ld r4, HSTATE_KVM_VCPU(r13)
ld r29, VCPU_GPR(R29)(r4)
ld r30, VCPU_GPR(R30)(r4)
ld r31, VCPU_GPR(R31)(r4)
+
+ /* Check the wake reason in SRR1 to see why we got here */
+ bl kvmppc_check_wake_reason
/* clear our bit in vcore->napping_threads */
- 33: ld r5,HSTATE_KVM_VCORE(r13)
- lwz r3,VCPU_PTID(r4)
+ 34: ld r5,HSTATE_KVM_VCORE(r13)
+ lbz r7,HSTATE_PTID(r13)
li r0,1
- sld r0,r0,r3
+ sld r0,r0,r7
addi r6,r5,VCORE_NAPPING_THREADS
32: lwarx r7,0,r6
andc r7,r7,r0
li r0,0
stb r0,HSTATE_NAPPING(r13)
- /* Check the wake reason in SRR1 to see why we got here */
- mfspr r3, SPRN_SRR1
- rlwinm r3, r3, 44-31, 0x7 /* extract wake reason field */
- cmpwi r3, 4 /* was it an external interrupt? */
- li r12, BOOK3S_INTERRUPT_EXTERNAL
+ /* See if the wake reason means we need to exit */
+ stw r12, VCPU_TRAP(r4)
mr r9, r4
- ld r10, VCPU_PC(r9)
- ld r11, VCPU_MSR(r9)
- beq do_ext_interrupt /* if so */
+ cmpdi r3, 0
+ bgt guest_exit_cont
/* see if any other thread is already exiting */
lwz r0,VCORE_ENTRY_EXIT(r5)
cmpwi r0,0x100
- blt kvmppc_cede_reentry /* if not go back to guest */
+ bge guest_exit_cont
- /* some threads are exiting, so go to the guest exit path */
- b hcall_real_fallback
+ b kvmppc_cede_reentry /* if not go back to guest */
/* cede when already previously prodded case */
kvm_cede_prodded:
beq mc_cont
/* If not, deliver a machine check. SRR0/1 are already set */
li r10, BOOK3S_INTERRUPT_MACHINE_CHECK
- li r11, (MSR_ME << 1) | 1 /* synthesize MSR_SF | MSR_ME */
- rotldi r11, r11, 63
+ ld r11, VCPU_INTR_MSR(r9)
b fast_interrupt_c_return
+ /*
+ * Check the reason we woke from nap, and take appropriate action.
+ * Returns:
+ * 0 if nothing needs to be done
+ * 1 if something happened that needs to be handled by the host
+ * -1 if there was a guest wakeup (IPI)
+ *
+ * Also sets r12 to the interrupt vector for any interrupt that needs
+ * to be handled now by the host (0x500 for external interrupt), or zero.
+ */
+ kvmppc_check_wake_reason:
+ mfspr r6, SPRN_SRR1
+ BEGIN_FTR_SECTION
+ rlwinm r6, r6, 45-31, 0xf /* extract wake reason field (P8) */
+ FTR_SECTION_ELSE
+ rlwinm r6, r6, 45-31, 0xe /* P7 wake reason field is 3 bits */
+ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_207S)
+ cmpwi r6, 8 /* was it an external interrupt? */
+ li r12, BOOK3S_INTERRUPT_EXTERNAL
+ beq kvmppc_read_intr /* if so, see what it was */
+ li r3, 0
+ li r12, 0
+ cmpwi r6, 6 /* was it the decrementer? */
+ beq 0f
+ BEGIN_FTR_SECTION
+ cmpwi r6, 5 /* privileged doorbell? */
+ beq 0f
+ cmpwi r6, 3 /* hypervisor doorbell? */
+ beq 3f
+ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+ li r3, 1 /* anything else, return 1 */
+ 0: blr
+
+ /* hypervisor doorbell */
+ 3: li r12, BOOK3S_INTERRUPT_H_DOORBELL
+ li r3, 1
+ blr
+
/*
* Determine what sort of external interrupt is pending (if any).
* Returns:
* interrupts directly to the guest
*/
cmpwi r3, XICS_IPI /* if there is, is it an IPI? */
- li r3, 1
bne 42f
/* It's an IPI, clear the MFRR and EOI it */
* before exit, it will be picked up by the host ICP driver
*/
stw r0, HSTATE_SAVED_XIRR(r13)
+ li r3, 1
b 1b
43: /* We raced with the host, we need to resend that IPI, bummer */
li r0, IPI_PRIORITY
stbcix r0, r6, r8 /* set the IPI */
sync
+ li r3, 1
b 1b
/*
* Save away FP, VMX and VSX registers.
* r3 = vcpu pointer
+ * N.B. r30 and r31 are volatile across this function,
+ * thus it is not callable from C.
*/
- _GLOBAL(kvmppc_save_fp)
+ kvmppc_save_fp:
+ mflr r30
+ mr r31,r3
mfmsr r5
ori r8,r5,MSR_FP
#ifdef CONFIG_ALTIVEC
#endif
mtmsrd r8
isync
- #ifdef CONFIG_VSX
- BEGIN_FTR_SECTION
- reg = 0
- .rept 32
- li r6,reg*16+VCPU_VSRS
- STXVD2X(reg,R6,R3)
- reg = reg + 1
- .endr
- FTR_SECTION_ELSE
- #endif
- reg = 0
- .rept 32
- stfd reg,reg*8+VCPU_FPRS(r3)
- reg = reg + 1
- .endr
- #ifdef CONFIG_VSX
- ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX)
- #endif
- mffs fr0
- stfd fr0,VCPU_FPSCR(r3)
-
+ addi r3,r3,VCPU_FPRS
+ bl .store_fp_state
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
- reg = 0
- .rept 32
- li r6,reg*16+VCPU_VRS
- stvx reg,r6,r3
- reg = reg + 1
- .endr
- mfvscr vr0
- li r6,VCPU_VSCR
- stvx vr0,r6,r3
+ addi r3,r31,VCPU_VRS
+ bl .store_vr_state
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
mfspr r6,SPRN_VRSAVE
stw r6,VCPU_VRSAVE(r3)
+ mtlr r30
mtmsrd r5
isync
blr
/*
* Load up FP, VMX and VSX registers
* r4 = vcpu pointer
+ * N.B. r30 and r31 are volatile across this function,
+ * thus it is not callable from C.
*/
- .globl kvmppc_load_fp
kvmppc_load_fp:
+ mflr r30
+ mr r31,r4
mfmsr r9
ori r8,r9,MSR_FP
#ifdef CONFIG_ALTIVEC
#endif
mtmsrd r8
isync
- lfd fr0,VCPU_FPSCR(r4)
- MTFSF_L(fr0)
- #ifdef CONFIG_VSX
- BEGIN_FTR_SECTION
- reg = 0
- .rept 32
- li r7,reg*16+VCPU_VSRS
- LXVD2X(reg,R7,R4)
- reg = reg + 1
- .endr
- FTR_SECTION_ELSE
- #endif
- reg = 0
- .rept 32
- lfd reg,reg*8+VCPU_FPRS(r4)
- reg = reg + 1
- .endr
- #ifdef CONFIG_VSX
- ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX)
- #endif
-
+ addi r3,r4,VCPU_FPRS
+ bl .load_fp_state
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
- li r7,VCPU_VSCR
- lvx vr0,r7,r4
- mtvscr vr0
- reg = 0
- .rept 32
- li r7,reg*16+VCPU_VRS
- lvx reg,r7,r4
- reg = reg + 1
- .endr
+ addi r3,r31,VCPU_VRS
+ bl .load_vr_state
END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
#endif
lwz r7,VCPU_VRSAVE(r4)
mtspr SPRN_VRSAVE,r7
+ mtlr r30
+ mr r4,r31
blr
/*
#include <linux/vmalloc.h>
#include <linux/highmem.h>
#include <linux/module.h>
+ #include <linux/miscdevice.h>
#include "book3s.h"
struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
memcpy(svcpu->slb, to_book3s(vcpu)->slb_shadow, sizeof(svcpu->slb));
svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max;
+ svcpu->in_use = 0;
svcpu_put(svcpu);
#endif
vcpu->cpu = smp_processor_id();
{
#ifdef CONFIG_PPC_BOOK3S_64
struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+ if (svcpu->in_use) {
+ kvmppc_copy_from_svcpu(vcpu, svcpu);
+ }
memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb));
to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max;
svcpu_put(svcpu);
svcpu->ctr = vcpu->arch.ctr;
svcpu->lr = vcpu->arch.lr;
svcpu->pc = vcpu->arch.pc;
+ svcpu->in_use = true;
}
/* Copy data touched by real-mode code from shadow vcpu back to vcpu */
void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
struct kvmppc_book3s_shadow_vcpu *svcpu)
{
+ /*
+ * vcpu_put would just call us again because in_use hasn't
+ * been updated yet.
+ */
+ preempt_disable();
+
+ /*
+ * Maybe we were already preempted and synced the svcpu from
+ * our preempt notifiers. Don't bother touching this svcpu then.
+ */
+ if (!svcpu->in_use)
+ goto out;
+
vcpu->arch.gpr[0] = svcpu->gpr[0];
vcpu->arch.gpr[1] = svcpu->gpr[1];
vcpu->arch.gpr[2] = svcpu->gpr[2];
vcpu->arch.fault_dar = svcpu->fault_dar;
vcpu->arch.fault_dsisr = svcpu->fault_dsisr;
vcpu->arch.last_inst = svcpu->last_inst;
+ svcpu->in_use = false;
+
+out:
+ preempt_enable();
}
static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu)
void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
{
struct thread_struct *t = ¤t->thread;
- u64 *vcpu_fpr = vcpu->arch.fpr;
- #ifdef CONFIG_VSX
- u64 *vcpu_vsx = vcpu->arch.vsr;
- #endif
- u64 *thread_fpr = &t->fp_state.fpr[0][0];
- int i;
/*
* VSX instructions can access FP and vector registers, so if
* both the traditional FP registers and the added VSX
* registers into thread.fp_state.fpr[].
*/
- if (current->thread.regs->msr & MSR_FP)
+ if (t->regs->msr & MSR_FP)
giveup_fpu(current);
- for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
- vcpu_fpr[i] = thread_fpr[get_fpr_index(i)];
-
- vcpu->arch.fpscr = t->fp_state.fpscr;
-
- #ifdef CONFIG_VSX
- if (cpu_has_feature(CPU_FTR_VSX))
- for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr) / 2; i++)
- vcpu_vsx[i] = thread_fpr[get_fpr_index(i) + 1];
- #endif
+ t->fp_save_area = NULL;
}
#ifdef CONFIG_ALTIVEC
if (msr & MSR_VEC) {
if (current->thread.regs->msr & MSR_VEC)
giveup_altivec(current);
- memcpy(vcpu->arch.vr, t->vr_state.vr, sizeof(vcpu->arch.vr));
- vcpu->arch.vscr = t->vr_state.vscr;
+ t->vr_save_area = NULL;
}
#endif
ulong msr)
{
struct thread_struct *t = ¤t->thread;
- u64 *vcpu_fpr = vcpu->arch.fpr;
- #ifdef CONFIG_VSX
- u64 *vcpu_vsx = vcpu->arch.vsr;
- #endif
- u64 *thread_fpr = &t->fp_state.fpr[0][0];
- int i;
/* When we have paired singles, we emulate in software */
if (vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)
#endif
if (msr & MSR_FP) {
- for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
- thread_fpr[get_fpr_index(i)] = vcpu_fpr[i];
- #ifdef CONFIG_VSX
- for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr) / 2; i++)
- thread_fpr[get_fpr_index(i) + 1] = vcpu_vsx[i];
- #endif
- t->fp_state.fpscr = vcpu->arch.fpscr;
- t->fpexc_mode = 0;
- kvmppc_load_up_fpu();
+ enable_kernel_fp();
+ load_fp_state(&vcpu->arch.fp);
+ t->fp_save_area = &vcpu->arch.fp;
}
if (msr & MSR_VEC) {
#ifdef CONFIG_ALTIVEC
- memcpy(t->vr_state.vr, vcpu->arch.vr, sizeof(vcpu->arch.vr));
- t->vr_state.vscr = vcpu->arch.vscr;
- t->vrsave = -1;
- kvmppc_load_up_altivec();
+ enable_kernel_altivec();
+ load_vr_state(&vcpu->arch.vr);
+ t->vr_save_area = &vcpu->arch.vr;
#endif
}
- current->thread.regs->msr |= msr;
+ t->regs->msr |= msr;
vcpu->arch.guest_owned_ext |= msr;
kvmppc_recalc_shadow_msr(vcpu);
if (!lost_ext)
return;
- if (lost_ext & MSR_FP)
- kvmppc_load_up_fpu();
+ if (lost_ext & MSR_FP) {
+ enable_kernel_fp();
+ load_fp_state(&vcpu->arch.fp);
+ }
#ifdef CONFIG_ALTIVEC
- if (lost_ext & MSR_VEC)
- kvmppc_load_up_altivec();
+ if (lost_ext & MSR_VEC) {
+ enable_kernel_altivec();
+ load_vr_state(&vcpu->arch.vr);
+ }
#endif
current->thread.regs->msr |= lost_ext;
}
/* We're good on these - the host merely wanted to get our attention */
case BOOK3S_INTERRUPT_DECREMENTER:
case BOOK3S_INTERRUPT_HV_DECREMENTER:
+ case BOOK3S_INTERRUPT_DOORBELL:
vcpu->stat.dec_exits++;
r = RESUME_GUEST;
break;
* and if we really did time things so badly, then we just exit
* again due to a host external interrupt.
*/
- local_irq_disable();
s = kvmppc_prepare_to_enter(vcpu);
- if (s <= 0) {
- local_irq_enable();
+ if (s <= 0)
r = s;
- } else {
+ else {
+ /* interrupts now hard-disabled */
kvmppc_fix_ee_before_entry();
}
+
kvmppc_handle_lost_ext(vcpu);
}
case KVM_REG_PPC_HIOR:
*val = get_reg_val(id, to_book3s(vcpu)->hior);
break;
- #ifdef CONFIG_VSX
- case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: {
- long int i = id - KVM_REG_PPC_VSR0;
-
- if (!cpu_has_feature(CPU_FTR_VSX)) {
- r = -ENXIO;
- break;
- }
- val->vsxval[0] = vcpu->arch.fpr[i];
- val->vsxval[1] = vcpu->arch.vsr[i];
- break;
- }
- #endif /* CONFIG_VSX */
default:
r = -EINVAL;
break;
to_book3s(vcpu)->hior = set_reg_val(id, *val);
to_book3s(vcpu)->hior_explicit = true;
break;
- #ifdef CONFIG_VSX
- case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31: {
- long int i = id - KVM_REG_PPC_VSR0;
-
- if (!cpu_has_feature(CPU_FTR_VSX)) {
- r = -ENXIO;
- break;
- }
- vcpu->arch.fpr[i] = val->vsxval[0];
- vcpu->arch.vsr[i] = val->vsxval[1];
- break;
- }
- #endif /* CONFIG_VSX */
default:
r = -EINVAL;
break;
static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
{
int ret;
- struct thread_fp_state fp;
- int fpexc_mode;
#ifdef CONFIG_ALTIVEC
- struct thread_vr_state vr;
unsigned long uninitialized_var(vrsave);
- int used_vr;
#endif
- #ifdef CONFIG_VSX
- int used_vsr;
- #endif
- ulong ext_msr;
/* Check if we can run the vcpu at all */
if (!vcpu->arch.sane) {
* really did time things so badly, then we just exit again due to
* a host external interrupt.
*/
- local_irq_disable();
ret = kvmppc_prepare_to_enter(vcpu);
- if (ret <= 0) {
- local_irq_enable();
+ if (ret <= 0)
goto out;
- }
+ /* interrupts now hard-disabled */
- /* Save FPU state in stack */
+ /* Save FPU state in thread_struct */
if (current->thread.regs->msr & MSR_FP)
giveup_fpu(current);
- fp = current->thread.fp_state;
- fpexc_mode = current->thread.fpexc_mode;
#ifdef CONFIG_ALTIVEC
- /* Save Altivec state in stack */
- used_vr = current->thread.used_vr;
- if (used_vr) {
- if (current->thread.regs->msr & MSR_VEC)
- giveup_altivec(current);
- vr = current->thread.vr_state;
- vrsave = current->thread.vrsave;
- }
+ /* Save Altivec state in thread_struct */
+ if (current->thread.regs->msr & MSR_VEC)
+ giveup_altivec(current);
#endif
#ifdef CONFIG_VSX
- /* Save VSX state in stack */
- used_vsr = current->thread.used_vsr;
- if (used_vsr && (current->thread.regs->msr & MSR_VSX))
+ /* Save VSX state in thread_struct */
+ if (current->thread.regs->msr & MSR_VSX)
__giveup_vsx(current);
#endif
- /* Remember the MSR with disabled extensions */
- ext_msr = current->thread.regs->msr;
-
/* Preload FPU if it's enabled */
if (vcpu->arch.shared->msr & MSR_FP)
kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
/* Make sure we save the guest FPU/Altivec/VSX state */
kvmppc_giveup_ext(vcpu, MSR_FP | MSR_VEC | MSR_VSX);
- current->thread.regs->msr = ext_msr;
-
- /* Restore FPU/VSX state from stack */
- current->thread.fp_state = fp;
- current->thread.fpexc_mode = fpexc_mode;
-
- #ifdef CONFIG_ALTIVEC
- /* Restore Altivec state from stack */
- if (used_vr && current->thread.used_vr) {
- current->thread.vr_state = vr;
- current->thread.vrsave = vrsave;
- }
- current->thread.used_vr = used_vr;
- #endif
-
- #ifdef CONFIG_VSX
- current->thread.used_vsr = used_vsr;
- #endif
-
out:
vcpu->mode = OUTSIDE_GUEST_MODE;
return ret;
module_exit(kvmppc_book3s_exit_pr);
MODULE_LICENSE("GPL");
+ MODULE_ALIAS_MISCDEV(KVM_MINOR);
+ MODULE_ALIAS("devname:kvm");
#endif
li r6, MSR_IR | MSR_DR
andc r6, r5, r6 /* Clear DR and IR in MSR value */
-#ifdef CONFIG_PPC_BOOK3S_32
/*
* Set EE in HOST_MSR so that it's enabled when we get into our
- * C exit handler function. On 64-bit we delay enabling
- * interrupts until we have finished transferring stuff
- * to or from the PACA.
+ * C exit handler function.
*/
ori r5, r5, MSR_EE
-#endif
mtsrr0 r7
mtsrr1 r6
RFI
- #if defined(CONFIG_PPC_BOOK3S_32)
- #define STACK_LR INT_FRAME_SIZE+4
-
- /* load_up_xxx have to run with MSR_DR=0 on Book3S_32 */
- #define MSR_EXT_START \
- PPC_STL r20, _NIP(r1); \
- mfmsr r20; \
- LOAD_REG_IMMEDIATE(r3, MSR_DR|MSR_EE); \
- andc r3,r20,r3; /* Disable DR,EE */ \
- mtmsr r3; \
- sync
-
- #define MSR_EXT_END \
- mtmsr r20; /* Enable DR,EE */ \
- sync; \
- PPC_LL r20, _NIP(r1)
-
- #elif defined(CONFIG_PPC_BOOK3S_64)
- #define STACK_LR _LINK
- #define MSR_EXT_START
- #define MSR_EXT_END
- #endif
-
- /*
- * Activate current's external feature (FPU/Altivec/VSX)
- */
- #define define_load_up(what) \
- \
- _GLOBAL(kvmppc_load_up_ ## what); \
- PPC_STLU r1, -INT_FRAME_SIZE(r1); \
- mflr r3; \
- PPC_STL r3, STACK_LR(r1); \
- MSR_EXT_START; \
- \
- bl FUNC(load_up_ ## what); \
- \
- MSR_EXT_END; \
- PPC_LL r3, STACK_LR(r1); \
- mtlr r3; \
- addi r1, r1, INT_FRAME_SIZE; \
- blr
-
- define_load_up(fpu)
- #ifdef CONFIG_ALTIVEC
- define_load_up(altivec)
- #endif
-
#include "book3s_segment.S"
local_irq_enable();
kvm_vcpu_block(vcpu);
clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
- local_irq_disable();
+ hard_irq_disable();
kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
r = 1;
int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
{
int ret, s;
- struct thread_struct thread;
+ struct debug_reg debug;
- #ifdef CONFIG_PPC_FPU
- struct thread_fp_state fp;
- int fpexc_mode;
- #endif
if (!vcpu->arch.sane) {
kvm_run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
return -EINVAL;
}
- local_irq_disable();
s = kvmppc_prepare_to_enter(vcpu);
if (s <= 0) {
- local_irq_enable();
ret = s;
goto out;
}
+ /* interrupts now hard-disabled */
#ifdef CONFIG_PPC_FPU
/* Save userspace FPU state in stack */
enable_kernel_fp();
- fp = current->thread.fp_state;
- fpexc_mode = current->thread.fpexc_mode;
-
- /* Restore guest FPU state to thread */
- memcpy(current->thread.fp_state.fpr, vcpu->arch.fpr,
- sizeof(vcpu->arch.fpr));
- current->thread.fp_state.fpscr = vcpu->arch.fpscr;
/*
* Since we can't trap on MSR_FP in GS-mode, we consider the guest
#endif
/* Switch to guest debug context */
- thread.debug = vcpu->arch.shadow_dbg_reg;
- switch_booke_debug_regs(&thread);
- thread.debug = current->thread.debug;
+ debug = vcpu->arch.shadow_dbg_reg;
+ switch_booke_debug_regs(&debug);
+ debug = current->thread.debug;
current->thread.debug = vcpu->arch.shadow_dbg_reg;
+ vcpu->arch.pgdir = current->mm->pgd;
kvmppc_fix_ee_before_entry();
ret = __kvmppc_vcpu_run(kvm_run, vcpu);
We also get here with interrupts enabled. */
/* Switch back to user space debug context */
- switch_booke_debug_regs(&thread);
- current->thread.debug = thread.debug;
+ switch_booke_debug_regs(&debug);
+ current->thread.debug = debug;
#ifdef CONFIG_PPC_FPU
kvmppc_save_guest_fp(vcpu);
vcpu->fpu_active = 0;
-
- /* Save guest FPU state from thread */
- memcpy(vcpu->arch.fpr, current->thread.fp_state.fpr,
- sizeof(vcpu->arch.fpr));
- vcpu->arch.fpscr = current->thread.fp_state.fpscr;
-
- /* Restore userspace FPU state from stack */
- current->thread.fp_state = fp;
- current->thread.fpexc_mode = fpexc_mode;
#endif
out:
int s;
int idx;
- #ifdef CONFIG_PPC64
- WARN_ON(local_paca->irq_happened != 0);
- #endif
-
- /*
- * We enter with interrupts disabled in hardware, but
- * we need to call hard_irq_disable anyway to ensure that
- * the software state is kept in sync.
- */
- hard_irq_disable();
-
/* update before a new last_exit_type is rewritten */
kvmppc_update_timing_stats(vcpu);
* aren't already exiting to userspace for some other reason.
*/
if (!(r & RESUME_HOST)) {
- local_irq_disable();
s = kvmppc_prepare_to_enter(vcpu);
- if (s <= 0) {
- local_irq_enable();
+ if (s <= 0)
r = (s << 2) | RESUME_HOST | (r & RESUME_FLAG_NV);
- } else {
+ else {
+ /* interrupts now hard-disabled */
kvmppc_fix_ee_before_entry();
}
}