Support POWER8 in HV KVM
Subsystems (3)
cover Support POWER8 in HV KVM
This series adds support for the POWER8 CPU in HV KVM. POWER8 adds several new guest-accessible instructions, special-purpose registers, and other features such as doorbell interrupts and hardware transactional memory. It also adds new hypervisor-controlled features such as relocation-on interrupts, and replaces the DABR/DABRX registers with the new DAWR/DAWRX registers with expanded capabilities. The POWER8 CPU has compatibility modes for architecture 2.06 (POWER7/POWER7+) and 2.05 (POWER6).
This series does not yet handle the checkpointed register state of the guest.
arch/powerpc/include/asm/kvm_asm.h | 2 + arch/powerpc/include/asm/kvm_book3s_asm.h | 1 + arch/powerpc/include/asm/kvm_host.h | 29 +- arch/powerpc/include/asm/reg.h | 25 +- arch/powerpc/include/uapi/asm/kvm.h | 1 + arch/powerpc/kernel/asm-offsets.c | 28 +- arch/powerpc/kvm/book3s_hv.c | 234 +++++++++++-- arch/powerpc/kvm/book3s_hv_interrupts.S | 8 +- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 538 ++++++++++++++++++++++-------- 9 files changed, 694 insertions(+), 172 deletions(-)
Paul.
RFC PATCH 1/10 KVM: PPC: Book3S HV: Align physical CPU thread numbers with virtual
On a threaded processor such as POWER7, we group VCPUs into virtual cores and arrange that the VCPUs in a virtual core run on the same physical core. Currently we don't enforce any correspondence between virtual thread numbers within a virtual core and physical thread numbers. Physical threads are allocated starting at 0 on a first-come first-served basis to runnable virtual threads (VCPUs).
POWER8 implements a new "msgsndp" instruction which guest kernels can use to interrupt other threads in the same core or sub-core. Since the instruction takes the destination physical thread ID as a parameter, it becomes necessary to align the physical thread IDs with the virtual thread IDs, that is, to make sure virtual thread N within a virtual core always runs on physical thread N.
This means that it's possible that thread 0, which is where we call __kvmppc_vcore_entry, may end up running some other vcpu than the one whose task called kvmppc_run_core(), or it may end up running no vcpu at all, if for example thread 0 of the virtual core is currently executing in userspace. Thus we can't rely on thread 0 to be the master responsible for switching the MMU. Instead we now have an explicit 'is_master' flag which is set for the vcpu whose task called kvmppc_run_core(). The master then has to wait for thread 0 to enter real mode before switching the MMU. Also, we no longer pass the vcpu pointer to __kvmppc_vcore_entry, but instead let the assembly code load it from the PACA.
Since the assembly code will need to know the kvm pointer and the thread ID for threads which don't have a vcpu, we move the thread ID into the PACA and we add a kvm pointer to the virtual core structure.
In the case where thread 0 has no vcpu to run, we arrange for it to go to nap mode, using a new flag value in the PACA 'napping' field so we can differentiate it when it wakes from the other nap cases. We set the bit for the thread in the vcore 'napping_threads' field so that when other threads come out of the guest they will send an IPI to thread 0 to wake it up. When it does wake up, we clear that bit, see what caused the wakeup, and either exit back to the kernel, or start running virtual thread 0 in the case where it now wants to enter the guest and the other threads are still in the guest.
--- arch/powerpc/include/asm/kvm_book3s_asm.h | 1 + arch/powerpc/include/asm/kvm_host.h | 4 + arch/powerpc/kernel/asm-offsets.c | 5 +- arch/powerpc/kvm/book3s_hv.c | 49 ++++---- arch/powerpc/kvm/book3s_hv_interrupts.S | 6 +- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 188 +++++++++++++++++++++++++----- 6 files changed, 192 insertions(+), 61 deletions(-)
arch/powerpc/include/asm/kvm_book3s_asm.h +1 -0
@@ -87,6 +87,7 @@ struct kvmppc_host_state {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;
arch/powerpc/include/asm/kvm_host.h +4 -0
@@ -284,6 +284,8 @@ struct kvmppc_vcore {int n_woken;int nap_count;int napping_threads; +int real_mode_threads; +int first_vcpuid;u16 pcpu;u16 last_cpu;u8 vcore_state;
@@ -294,6 +296,7 @@ struct kvmppc_vcore {u64 stolen_tb;u64 preempt_tb;struct kvm_vcpu *runner; +struct kvm *kvm;u64 tb_offset;/* guest timebase - host timebase */ u32 arch_compat;ulong pcr;
@@ -575,6 +578,7 @@ struct kvm_vcpu_arch {int state;int ptid;bool timer_running; +u8 is_master;wait_queue_head_t cpu_run;struct kvm_vcpu_arch_shared *shared;
arch/powerpc/kernel/asm-offsets.c +4 -1
@@ -514,13 +514,15 @@ int main(void) 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_IS_MASTER, offsetof(struct kvm_vcpu, arch.is_master)); DEFINE(VCPU_CFAR, offsetof(struct kvm_vcpu, arch.cfar)); DEFINE(VCPU_PPR, offsetof(struct kvm_vcpu, arch.ppr));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_RM_THREADS , offsetof(struct kvmppc_vcore , real_mode_threads)); +DEFINE (VCORE_KVM , offsetof(struct kvmppc_vcore , kvm));DEFINE (VCORE_TB_OFFSET , offsetof(struct kvmppc_vcore , tb_offset));DEFINE (VCORE_PCR , offsetof(struct kvmppc_vcore , pcr)); DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
@@ -590,6 +592,7 @@ int main(void)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);
arch/powerpc/kvm/book3s_hv.c +20 -29
134 lines not on this page · raw message
arch/powerpc/kvm/book3s_hv_interrupts.S +2 -4
@@ -35,7 +35,7 @@ ****************************************************************************/ /* Registers: - * r4: vcpu pointer + * none */ _GLOBAL(__kvmppc_vcore_entry)
@@ -69,7 +69,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) mtmsrd r10,1 /* Save host PMU registers */ - /* R4 is live here (vcpu pointer) but not r3 or r5 */ li r3, 1 sldi r3, r3, 31 /* MMCR0_FC (freeze counters) bit */ mfspr r7, SPRN_MMCR0 /* save MMCR0 */
@@ -134,16 +133,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) * enters the guest with interrupts enabled. */ BEGIN_FTR_SECTION + ld r4, HSTATE_KVM_VCPU(r13) ld r0, VCPU_PENDING_EXC(r4) li r7, (1 << BOOK3S_IRQPRIO_EXTERNAL) oris r7, r7, (1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h and. r0, r0, r7 beq 32f - mr r31, r4 lhz r3, PACAPACAINDEX(r13) bl smp_send_reschedule nop - mr r4, r31 32: END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) #endif /* CONFIG_SMP */
arch/powerpc/kvm/book3s_hv_rmhandlers.S +161 -27
294 lines not on this page · raw message
Signature · 1 line
1.8.4.rc3
RFC PATCH 2/10 KVM: PPC: Book3S HV: Don't set DABR on POWER8
In reply to Paul MackerrasFrom: Michael Neuling <[email protected]>
POWER8 doesn't have the DABR and DABRX registers; instead it has new DAWR/DAWRX registers, which will be handled in a later patch.
--- arch/powerpc/kvm/book3s_hv_interrupts.S | 2 ++ arch/powerpc/kvm/book3s_hv_rmhandlers.S | 13 ++++++++++--- 2 files changed, 12 insertions(+), 3 deletions(-)
arch/powerpc/kvm/book3s_hv_interrupts.S +2 -0
@@ -57,9 +57,11 @@ BEGIN_FTR_SECTION std r3, HSTATE_DSCR(r13) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) +BEGIN_FTR_SECTION /* Save host DABR */ mfspr r3, SPRN_DABR std r3, HSTATE_DABR(r13) +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) /* Hard-disable interrupts */ mfmsr r10
arch/powerpc/kvm/book3s_hv_rmhandlers.S +10 -3
@@ -95,11 +95,13 @@ kvmppc_got_guest: /* 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)
@@ -423,15 +425,17 @@ kvmppc_hv_entry: std r0, PPC_LR_STKOFF(r1) stdu r1, -112(r1) +BEGIN_FTR_SECTION /* 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 + BEGIN_FTR_SECTION_NESTED(89) isync -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + 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) */
@@ -1716,6 +1720,9 @@ ignore_hdec: b fast_guest_return _GLOBAL(kvmppc_h_set_dabr) +BEGIN_FTR_SECTION + b 2f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) std r4,VCPU_DABR(r3) /* Work around P7 bug where DABR can get corrupted on mtspr */ 1: mtspr SPRN_DABR,r4
@@ -1723,7 +1730,7 @@ _GLOBAL(kvmppc_h_set_dabr) cmpd r4, r5 bne 1b isync - li r3,0 +2: li r3,0 blr _GLOBAL(kvmppc_h_cede)
Signature · 1 line
1.8.4.rc3
RFC PATCH 3/10 KVM: PPC: Book3S HV: Context-switch new POWER8 SPRs
In reply to Paul MackerrasFrom: Michael Neuling <[email protected]>
This adds fields to the struct kvm_vcpu_arch to store the new guest-accessible SPRs on POWER8, adds code to the get/set_one_reg functions to allow userspace to access this state, and adds code to the guest entry and exit to context-switch these SPRs between host and guest.
Note that DPDES (Directed Privileged Doorbell Exception State) is shared between threads on a core; hence we store it in struct kvmppc_vcore and have the master thread save and restore it.
--- arch/powerpc/include/asm/kvm_host.h | 25 +++++- arch/powerpc/include/asm/reg.h | 17 ++++ arch/powerpc/include/uapi/asm/kvm.h | 1 + arch/powerpc/kernel/asm-offsets.c | 23 +++++ arch/powerpc/kvm/book3s_hv.c | 153 +++++++++++++++++++++++++++++++- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 144 ++++++++++++++++++++++++++++++ 6 files changed, 360 insertions(+), 3 deletions(-)
arch/powerpc/include/asm/kvm_host.h +24 -1
@@ -300,6 +300,7 @@ struct kvmppc_vcore {u64 tb_offset;/* guest timebase - host timebase */ u32 arch_compat;ulong pcr; +ulong dpdes;/* doorbell state (POWER8) */ };#define VCORE_ENTRY_COUNT (vc) ((vc)->entry_exit_count & 0xff)
@@ -454,6 +455,7 @@ struct kvm_vcpu_arch {ulong pc;ulong ctr;ulong lr; +ulong tar;ulong xer;u32 cr;
@@ -463,13 +465,32 @@ struct kvm_vcpu_arch {ulong guest_owned_ext;ulong purr;ulong spurr; +ulong ic; +ulong vtb;ulong dscr;ulong amr;ulong uamor; +ulong iamr;u32 ctrl;ulong dabr; +ulong dawr; +ulong dawrx; +ulong ciabr;ulong cfar;ulong ppr; +ulong pspb; +ulong fscr; +ulong tfhar; +ulong tfiar; +ulong texasr; +ulong ebbhr; +ulong ebbrr; +ulong bescr; +ulong csigr; +ulong tacr; +ulong tcscr; +ulong acop; +ulong wort;#endif u32 vrsave;/* also USPRG0 */ u32 mmucr;
@@ -503,10 +524,12 @@ struct kvm_vcpu_arch {u32 ccr1;u32 dbsr; -u64 mmcr[3 ]; +u64 mmcr[5 ];u32 pmc[8 ]; +u32 spmc[2 ];u64 siar;u64 sdar; +u64 sier;#ifdef CONFIG_KVM_EXIT_TIMING struct mutex exit_timing_lock;
arch/powerpc/include/asm/reg.h +17 -0
@@ -218,6 +218,11 @@#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)
@@ -255,6 +260,8 @@#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 */ #define SPRN_FSCR 0x099/* Facility Status & Control Register */ #define FSCR_TAR (1 << (63-55))/* Enable Target Address Register */ #define FSCR_EBB (1 << (63-56))/* Enable Event Based Branching */
@@ -354,6 +361,8 @@#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 */
@@ -413,6 +422,7 @@#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 */
@@ -526,6 +536,7 @@#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 */
@@ -667,6 +678,7 @@#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
@@ -683,6 +695,11 @@#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)
arch/powerpc/include/uapi/asm/kvm.h +1 -0
@@ -531,6 +531,7 @@ struct kvm_get_htab_header {#define KVM_REG_PPC_TCSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb1)#define KVM_REG_PPC_PID (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb2)#define KVM_REG_PPC_ACOP (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb3) +#define KVM_REG_PPC_WORT (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb4)#define KVM_REG_PPC_VRSAVE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4)#define KVM_REG_PPC_LPCR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5)
arch/powerpc/kernel/asm-offsets.c +23 -0
@@ -440,6 +440,7 @@ int main(void) 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_64_HV
@@ -492,11 +493,17 @@ int main(void)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_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));
@@ -505,8 +512,10 @@ int main(void) 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));
@@ -517,6 +526,19 @@ int main(void) DEFINE(VCPU_IS_MASTER, offsetof(struct kvm_vcpu, arch.is_master)); 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_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_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 (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));
@@ -525,6 +547,7 @@ int main(void)DEFINE (VCORE_KVM , offsetof(struct kvmppc_vcore , kvm));DEFINE (VCORE_TB_OFFSET , offsetof(struct kvmppc_vcore , tb_offset));DEFINE (VCORE_PCR , offsetof(struct kvmppc_vcore , pcr)); +DEFINE (VCORE_DPDES , offsetof(struct kvmppc_vcore , dpdes));DEFINE (VCPU_SVCPU , offsetof(struct kvmppc_vcpu_book3s , shadow_vcpu) - offsetof(struct kvmppc_vcpu_book3s , vcpu));DEFINE (VCPU_SLB_E , offsetof(struct kvmppc_slb , orige));
arch/powerpc/kvm/book3s_hv.c +151 -2
189 lines not on this page · raw message
arch/powerpc/kvm/book3s_hv_rmhandlers.S +144 -0
180 lines not on this page · raw message
Signature · 1 line
1.8.4.rc3
RFC PATCH 4/10 KVM: PPC: Book3S HV: Flush the correct number of TLB sets on POWER8
In reply to Paul MackerrasPOWER8 has 512 sets in the TLB, compared to 128 for POWER7, so we need to do more tlbiel instructions when flushing the TLB on POWER8.
--- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
arch/powerpc/kvm/book3s_hv_rmhandlers.S +7 -1
@@ -667,7 +667,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) 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
Signature · 1 line
1.8.4.rc3
RFC PATCH 5/10 KVM: PPC: Book3S HV: Add handler for HV facility unavailable
In reply to Paul MackerrasFrom: Michael Ellerman <[email protected]>
At present this should never happen, since the host kernel sets HFSCR to allow access to all facilities. It's better to be prepared to handle it cleanly if it does ever happen, though.
--- arch/powerpc/include/asm/kvm_asm.h | 1 + arch/powerpc/kvm/book3s_hv.c | 9 +++++++++ 2 files changed, 10 insertions(+)
arch/powerpc/include/asm/kvm_asm.h +1 -0
@@ -99,6 +99,7 @@#define BOOK3S_INTERRUPT_PERFMON 0xf00#define BOOK3S_INTERRUPT_ALTIVEC 0xf20#define BOOK3S_INTERRUPT_VSX 0xf40 +#define BOOK3S_INTERRUPT_H_FAC_UNAVAIL 0xf80#define BOOK3S_IRQPRIO_SYSTEM_RESET 0#define BOOK3S_IRQPRIO_DATA_SEGMENT 1
arch/powerpc/kvm/book3s_hv.c +9 -0
@@ -704,6 +704,15 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,kvmppc_core_queue_program (vcpu,0x80000 ); 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,0x80000 ); + r =RESUME_GUEST ; +break ;default :kvmppc_dump_regs (vcpu); printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
Signature · 1 line
1.8.4.rc3
Re: [RFC PATCH 05/10] KVM: PPC: Book3S HV: Add handler for HV facility unavailable
Quoted 30 lines · Paul Mackerras
From: Michael Ellerman <[email protected]>
At present this should never happen, since the host kernel sets HFSCR to allow access to all facilities. It's better to be prepared to handle it cleanly if it does ever happen, though.
Signed-off-by Michael Ellerman <[email protected]>Signed-off-by Paul Mackerras <[email protected]>---
arch/powerpc/include/asm/kvm_asm.h| 1 +arch/powerpc/kvm/book3s_hv.c| 9 +++++++++2 files changed, 10 insertions(+)arch/powerpc/include/asm/kvm_asm.h +1
-0@@ -99,6 +99,7 @@#define BOOK3S_INTERRUPT_PERFMON 0xf00#define BOOK3S_INTERRUPT_ALTIVEC 0xf20#define BOOK3S_INTERRUPT_VSX 0xf40 +#define BOOK3S_INTERRUPT_H_FAC_UNAVAIL 0xf80#define BOOK3S_IRQPRIO_SYSTEM_RESET 0#define BOOK3S_IRQPRIO_DATA_SEGMENT 1arch/powerpc/kvm/book3s_hv.c +0
-0
arch/powerpc/kvm/book3s_hv.c static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, · line 713
Quoted 10 lines
arch/powerpc/kvm/book3s_hv.c +7
-0@@ -704,6 +704,15 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,kvmppc_core_queue_program (vcpu,0x80000 ); 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,0x80000 );
Would be nice to have a name for that bit.
Alex
Quoted 8 lines
arch/powerpc/kvm/book3s_hv.c +2
-0+ r =RESUME_GUEST ; +break ;default :kvmppc_dump_regs (vcpu); printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",Signature · 1 line
1.8.4.rc3
RFC PATCH 6/10 KVM: PPC: Book3S HV: Implement architecture compatibility modes for POWER8
In reply to Paul MackerrasThis allows us to select architecture 2.05 (POWER6) or 2.06 (POWER7) compatibility modes on a POWER8 processor.
--- arch/powerpc/include/asm/reg.h | 2 ++ arch/powerpc/kvm/book3s_hv.c | 16 +++++++++++++++- 2 files changed, 17 insertions(+), 1 deletion(-)
arch/powerpc/include/asm/reg.h +2 -0
@@ -315,6 +315,8 @@#define SPRN_PCR 0x152/* Processor compatibility register */ #define PCR_VEC_DIS (1ul << (63-0))/* Vec. disable (pre POWER8) */ #define PCR_VSX_DIS (1ul << (63-1))/* VSX disable (pre 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 */
arch/powerpc/kvm/book3s_hv.c +15 -1
@@ -177,14 +177,28 @@ int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)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);
Signature · 1 line
1.8.4.rc3
Re: [RFC PATCH 06/10] KVM: PPC: Book3S HV: Implement architecture compatibility modes for POWER8
Quoted 14 lines · Paul Mackerras
This allows us to select architecture 2.05 (POWER6) or 2.06 (POWER7) compatibility modes on a POWER8 processor.
Signed-off-by Paul Mackerras <[email protected]>---
arch/powerpc/include/asm/reg.h| 2 ++arch/powerpc/kvm/book3s_hv.c| 16 +++++++++++++++-2 files changed, 17 insertions(+), 1 deletion(-)arch/powerpc/include/asm/reg.h +0
-0
arch/powerpc/include/asm/reg.h line 318
Quoted 4 lines
arch/powerpc/include/asm/reg.h +1
-0@@ -315,6 +315,8 @@#define SPRN_PCR 0x152/* Processor compatibility register */ #define PCR_VEC_DIS (1ul << (63-0))/* Vec. disable (pre POWER8) */ #define PCR_VSX_DIS (1ul << (63-1))/* VSX disable (pre POWER8) */ +#define PCR_TM_DIS (1ul << (63-2))/* Trans. memory disable (POWER8) */
Is this going to get used?
Alex
Re: [RFC PATCH 06/10] KVM: PPC: Book3S HV: Implement architecture compatibility modes for POWER8
Quoted 12 lines · Alexander Graf
Quoted 9 lines · Paul Mackerras
This allows us to select architecture 2.05 (POWER6) or 2.06 (POWER7) compatibility modes on a POWER8 processor.
Signed-off-by Paul Mackerras <[email protected]>---
arch/powerpc/include/asm/reg.h| 2 ++arch/powerpc/kvm/book3s_hv.c| 16 +++++++++++++++-2 files changed, 17 insertions(+), 1 deletion(-)
Quoted 11 lines
arch/powerpc/include/asm/reg.h line 318
Quoted 9 lines
arch/powerpc/include/asm/reg.h +1
-0@@ -315,6 +315,8 @@#define SPRN_PCR 0x152/* Processor compatibility register */ #define PCR_VEC_DIS (1ul << (63-0))/* Vec. disable (pre POWER8) */ #define PCR_VSX_DIS (1ul << (63-1))/* VSX disable (pre POWER8) */ +#define PCR_TM_DIS (1ul << (63-2))/* Trans. memory disable (POWER8) */ Is this going to get used?
Perhaps not, but I thought it worthwhile to document that the bit exists.
Paul.
Re: [RFC PATCH 06/10] KVM: PPC: Book3S HV: Implement architecture compatibility modes for POWER8
Am 05.11.2013 um 04:53 schrieb Paul Mackerras <[email protected]>:
Quoted 25 lines · Alexander Graf
Quoted 12 lines · Paul Mackerras
Quoted 10 lines
This allows us to select architecture 2.05 (POWER6) or 2.06 (POWER7) compatibility modes on a POWER8 processor.
Signed-off-by Paul Mackerras <[email protected]>---
arch/powerpc/include/asm/reg.h| 2 ++arch/powerpc/kvm/book3s_hv.c| 16 +++++++++++++++-2 files changed, 17 insertions(+), 1 deletion(-)Quoted 11 lines
arch/powerpc/include/asm/reg.h line 318
Quoted 9 lines
arch/powerpc/include/asm/reg.h +1
-0@@ -315,6 +315,8 @@#define SPRN_PCR 0x152/* Processor compatibility register */ #define PCR_VEC_DIS (1ul << (63-0))/* Vec. disable (pre POWER8) */ #define PCR_VSX_DIS (1ul << (63-1))/* VSX disable (pre POWER8) */ +#define PCR_TM_DIS (1ul << (63-2))/* Trans. memory disable (POWER8) */ Is this going to get used?
Quoted 2 lines
Perhaps not, but I thought it worthwhile to document that the bit exists.
But why not? Does that mean we allow TM to be used in p7 compat mode?
Alex
Quoted 2 lines
Paul.
Re: [RFC PATCH 06/10] KVM: PPC: Book3S HV: Implement architecture compatibility modes for POWER8
Quoted 29 lines · Alexander Graf
Am 05.11.2013 um 04:53 schrieb Paul Mackerras <[email protected]>:
Quoted 25 lines · Alexander Graf
Quoted 23 lines · Paul Mackerras
Quoted 15 lines
This allows us to select architecture 2.05 (POWER6) or 2.06 (POWER7) compatibility modes on a POWER8 processor.
Signed-off-by Paul Mackerras <[email protected]>---
arch/powerpc/include/asm/reg.h| 2 ++arch/powerpc/kvm/book3s_hv.c| 16 +++++++++++++++-2 files changed, 17 insertions(+), 1 deletion(-)arch/powerpc/include/asm/reg.h +0
-0arch/powerpc/include/asm/reg.h line 318
Quoted 4 lines
arch/powerpc/include/asm/reg.h +1
-0@@ -315,6 +315,8 @@#define SPRN_PCR 0x152/* Processor compatibility register */ #define PCR_VEC_DIS (1ul << (63-0))/* Vec. disable (pre POWER8) */ #define PCR_VSX_DIS (1ul << (63-1))/* VSX disable (pre POWER8) */ +#define PCR_TM_DIS (1ul << (63-2))/* Trans. memory disable (POWER8) */ Is this going to get used?
Quoted 4 lines
Quoted 2 lines
Perhaps not, but I thought it worthwhile to document that the bit exists.
But why not? Does that mean we allow TM to be used in p7 compat mode?
No; TM is disabled if either or both of the PCR_TM_DIS and PCR_ARCH_206 bits are set.
Paul.
RFC PATCH 7/10 KVM: PPC: Book3S HV: Consolidate code that checks reason for wake from nap
In reply to Paul MackerrasCurrently in book3s_hv_rmhandlers.S we have three places where we have woken up from nap mode and we check the reason field in SRR1 to see what event woke us up. This consolidates them into a new function, kvmppc_check_wake_reason. It looks at the wake reason field in SRR1, and if it indicates that an external interrupt caused the wakeup, calls kvmppc_read_intr to check what sort of interrupt it was.
This also consolidates the two places where we synthesize an external interrupt (0x500 vector) for the guest. Now, if the guest exit code finds that there was an external interrupt which has been handled (i.e. it was an IPI indicating that there is now an interrupt pending for the guest), it jumps to deliver_guest_interrupt, which is in the last part of the guest entry code, where we synthesize guest external and decrementer interrupts. That code has been streamlined a little and now clears LPCR[MER] when appropriate as well as setting it.
The extra clearing of any pending IPI on a secondary, offline CPU thread before going back to nap mode has been removed. It is no longer necessary now that we have code to read and acknowledge IPIs in the guest exit path.
This fixes a minor bug in the H_CEDE real-mode handling - previously, if we found that other threads were already exiting the guest when we were about to go to nap mode, we would branch to the cede wakeup path and end up looking in SRR1 for a wakeup reason. Now we branch to a point after we have checked the wakeup reason.
This also fixes a minor bug in kvmppc_read_intr - previously it could return 0xff rather than 1, in the case where we find that a host IPI is pending after we have cleared the IPI. Now it returns 1.
--- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 193 +++++++++++++------------------- 1 file changed, 78 insertions(+), 115 deletions(-)
arch/powerpc/kvm/book3s_hv_rmhandlers.S +78 -115
@@ -234,8 +234,10 @@ kvm_novcpu_wakeup: 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 */ - li r12, 0 lwz r0, VCORE_ENTRY_EXIT(r5) cmpwi r0, 0x100 bge kvm_novcpu_exit
@@ -245,23 +247,14 @@ kvm_novcpu_wakeup: li r0, 1 sld r0, r0, r7 addi r6, r5, VCORE_NAPPING_THREADS -4: lwarx r3, 0, r6 - andc r3, r3, r0 - stwcx. r3, 0, r6 +4: lwarx r7, 0, r6 + andc r7, r7, r0 + stwcx. r7, 0, r6 bne 4b - /* 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 kvm_novcpu_exit /* if not, exit the guest */ - - /* extern interrupt - read and handle it */ - li r12, BOOK3S_INTERRUPT_EXTERNAL - bl kvmppc_read_intr + /* See if the wake reason means we need to exit */ cmpdi r3, 0 bge kvm_novcpu_exit - li r12, 0 /* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */ ld r4, HSTATE_KVM_VCPU(r13)
@@ -325,58 +318,23 @@ kvm_start_guest: */ /* 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 - -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) 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)
@@ -862,47 +820,46 @@ toc_tlbie_lock: 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 + li r0, BOOK3S_INTERRUPT_EXTERNAL + bne cr1, 12f + mfspr r0, SPRN_DEC + cmpwi r0, 0 + li r0, BOOK3S_INTERRUPT_DECREMENTER + bge 5f + +12: mtspr SPRN_SRR0, r10 mr r10,r0 - mr r7,r11 + mtspr SPRN_SRR1, 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 - - /* Move SRR0 and SRR1 into the respective regs */ -5: mtspr SPRN_SRR0, r6 - mtspr SPRN_SRR1, r7 +5: fast_guest_return: li r0,0
@@ -1075,39 +1032,19 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) /* 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:
@@ -1923,7 +1860,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) stb r0,HSTATE_NAPPING(r13) /* order napping_threads update vs testing entry_exit_count */ lwsync - mr r4,r3 lwz r7,VCORE_ENTRY_EXIT(r5) cmpwi r7,0x100 bge 33f /* another thread already exiting */
@@ -1976,6 +1912,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) 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)
@@ -2005,12 +1946,15 @@ kvm_end_cede: 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) - lbz r3,HSTATE_PTID(r13) +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
@@ -2019,23 +1963,18 @@ kvm_end_cede: 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:
@@ -2066,6 +2005,29 @@ machine_check_realmode: 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 + rlwinm r6, r6, 44-31, 0x7 /* extract wake reason field */ + cmpwi r6, 4 /* 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 + li r3, 1 /* anything else, return 1 */ +0: blr + +/* * Determine what sort of external interrupt is pending (if any). * Returns: * 0 if no interrupt is pending
@@ -2096,7 +2058,6 @@ kvmppc_read_intr: * 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 */
@@ -2122,12 +2083,14 @@ kvmppc_read_intr: * 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 /*
Signature · 1 line
1.8.4.rc3
RFC PATCH 8/10 KVM: PPC: Book3S HV: Handle guest using doorbells for IPIs
In reply to Paul Mackerras* SRR1 wake reason field for system reset interrupt on wakeup from nap is now a 4-bit field on P8, compared to 3 bits on P7.
* Set PECEDP in LPCR when napping because of H_CEDE so guest doorbells will wake us up.
* Waking up from nap because of a guest doorbell interrupt is not a reason to exit the guest.
--- arch/powerpc/include/asm/reg.h | 4 +++- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 19 +++++++++++++++---- 2 files changed, 18 insertions(+), 5 deletions(-)
arch/powerpc/include/asm/reg.h +3 -1
@@ -293,7 +293,9 @@#define LPCR_ILE 0x02000000/* !HV irqs set MSR:LE */ #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_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 */
arch/powerpc/kvm/book3s_hv_rmhandlers.S +15 -4
@@ -1894,13 +1894,16 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) 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
@@ -2016,14 +2019,22 @@ machine_check_realmode: */ kvmppc_check_wake_reason: mfspr r6, SPRN_SRR1 - rlwinm r6, r6, 44-31, 0x7 /* extract wake reason field */ - cmpwi r6, 4 /* was it an external interrupt? */ +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 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) li r3, 1 /* anything else, return 1 */ 0: blr
Signature · 1 line
1.8.4.rc3
RFC PATCH 9/10 KVM: PPC: Book3S HV: Handle new LPCR bits on POWER8
In reply to Paul MackerrasPOWER8 has a bit in the LPCR to enable or disable the PURR and SPURR registers to count when in the guest. Set this bit.
POWER8 has a field in the LPCR called AIL (Alternate Interrupt Location) which is used to enable relocation-on interrupts. Allow userspace to set this field.
--- arch/powerpc/include/asm/reg.h | 2 ++ arch/powerpc/kvm/book3s_hv.c | 6 ++++++ 2 files changed, 8 insertions(+)
arch/powerpc/include/asm/reg.h +2 -0
@@ -291,8 +291,10 @@#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_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 */
arch/powerpc/kvm/book3s_hv.c +6 -0
@@ -783,8 +783,11 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr)/* * 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 ; kvm->arch.lpcr = (kvm->arch.lpcr & ~mask) | (new_lpcr & mask);mutex_unlock (&kvm->lock); }
@@ -2169,6 +2172,9 @@ int kvmppc_core_init_vm(struct kvm *kvm)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;
Signature · 1 line
1.8.4.rc3
RFC PATCH 10/10 KVM: PPC: Book3S HV: Prepare for host using hypervisor doorbells
In reply to Paul MackerrasPOWER8 has support for hypervisor doorbell interrupts. Though the kernel doesn't use them for IPIs on the powernv platform yet, it probably will in future, so this makes KVM cope gracefully if a hypervisor doorbell interrupt arrives while in a guest.
--- arch/powerpc/include/asm/kvm_asm.h | 1 + arch/powerpc/kvm/book3s_hv.c | 1 + arch/powerpc/kvm/book3s_hv_rmhandlers.S | 7 +++++++ 3 files changed, 9 insertions(+)
arch/powerpc/include/asm/kvm_asm.h +1 -0
@@ -96,6 +96,7 @@#define BOOK3S_INTERRUPT_H_DATA_STORAGE 0xe00#define BOOK3S_INTERRUPT_H_INST_STORAGE 0xe20#define BOOK3S_INTERRUPT_H_EMUL_ASSIST 0xe40 +#define BOOK3S_INTERRUPT_H_DOORBELL 0xe80#define BOOK3S_INTERRUPT_PERFMON 0xf00#define BOOK3S_INTERRUPT_ALTIVEC 0xf20#define BOOK3S_INTERRUPT_VSX 0xf40
arch/powerpc/kvm/book3s_hv.c +1 -0
@@ -644,6 +644,7 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, r =RESUME_GUEST ;break ;case BOOK3S_INTERRUPT_EXTERNAL : +case BOOK3S_INTERRUPT_H_DOORBELL : vcpu->stat.ext_intr_exits++; r =RESUME_GUEST ;break ;
arch/powerpc/kvm/book3s_hv_rmhandlers.S +7 -0
@@ -2034,10 +2034,17 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_207S) 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:
Signature · 1 line
1.8.4.rc3