diff options
Diffstat (limited to 'arch/powerpc')
51 files changed, 1651 insertions, 1175 deletions
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index 2e637c881d2b..879de5efb073 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -36,7 +36,7 @@ CONFIG_KEXEC=y CONFIG_SCHED_SMT=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="" -CONFIG_PM_RUNTIME=y +CONFIG_PM=y CONFIG_PM_DEBUG=y # CONFIG_SECCOMP is not set # CONFIG_PCI is not set diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h new file mode 100644 index 000000000000..d2f99ca1e3a6 --- /dev/null +++ b/arch/powerpc/include/asm/cpuidle.h @@ -0,0 +1,20 @@ +#ifndef _ASM_POWERPC_CPUIDLE_H +#define _ASM_POWERPC_CPUIDLE_H + +#ifdef CONFIG_PPC_POWERNV +/* Used in powernv idle state management */ +#define PNV_THREAD_RUNNING 0 +#define PNV_THREAD_NAP 1 +#define PNV_THREAD_SLEEP 2 +#define PNV_THREAD_WINKLE 3 +#define PNV_CORE_IDLE_LOCK_BIT 0x100 +#define PNV_CORE_IDLE_THREAD_BITS 0x0FF + +#ifndef __ASSEMBLY__ +extern u32 pnv_fastsleep_workaround_at_entry[]; +extern u32 pnv_fastsleep_workaround_at_exit[]; +#endif + +#endif + +#endif diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index 19c36cba37c4..a46f5f45570c 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -86,6 +86,11 @@ extern int overlaps_crashkernel(unsigned long start, unsigned long size); extern void reserve_crashkernel(void); extern void machine_kexec_mask_interrupts(void); +static inline bool kdump_in_progress(void) +{ + return crashing_cpu >= 0; +} + #else /* !CONFIG_KEXEC */ static inline void crash_kexec_secondary(struct pt_regs *regs) { } @@ -106,6 +111,11 @@ static inline int crash_shutdown_unregister(crash_shutdown_t handler) return 0; } +static inline bool kdump_in_progress(void) +{ + return false; +} + #endif /* CONFIG_KEXEC */ #endif /* ! __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 6acf0c2a0f99..942c7b1678e3 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -170,8 +170,6 @@ extern void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long addr, unsigned long *nb_ret); extern void kvmppc_unpin_guest_page(struct kvm *kvm, void *addr, unsigned long gpa, bool dirty); -extern long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags, - long pte_index, unsigned long pteh, unsigned long ptel); extern long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, long pte_index, unsigned long pteh, unsigned long ptel, pgd_t *pgdir, bool realmode, unsigned long *idx_ret); diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 0aa817933e6a..2d81e202bdcc 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -37,7 +37,6 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu) #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE #define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */ -extern unsigned long kvm_rma_pages; #endif #define VRMA_VSID 0x1ffffffUL /* 1TB VSID reserved for VRMA */ @@ -148,7 +147,7 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, /* This covers 14..54 bits of va*/ rb = (v & ~0x7fUL) << 16; /* AVA field */ - rb |= v >> (62 - 8); /* B field */ + rb |= (v >> HPTE_V_SSIZE_SHIFT) << 8; /* B field */ /* * AVA in v had cleared lower 23 bits. We need to derive * that from pteg index diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 047855619cc4..7efd666a3fa7 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -180,11 +180,6 @@ struct kvmppc_spapr_tce_table { struct page *pages[0]; }; -struct kvm_rma_info { - atomic_t use_count; - unsigned long base_pfn; -}; - /* XICS components, defined in book3s_xics.c */ struct kvmppc_xics; struct kvmppc_icp; @@ -214,16 +209,9 @@ struct revmap_entry { #define KVMPPC_RMAP_PRESENT 0x100000000ul #define KVMPPC_RMAP_INDEX 0xfffffffful -/* Low-order bits in memslot->arch.slot_phys[] */ -#define KVMPPC_PAGE_ORDER_MASK 0x1f -#define KVMPPC_PAGE_NO_CACHE HPTE_R_I /* 0x20 */ -#define KVMPPC_PAGE_WRITETHRU HPTE_R_W /* 0x40 */ -#define KVMPPC_GOT_PAGE 0x80 - struct kvm_arch_memory_slot { #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE unsigned long *rmap; - unsigned long *slot_phys; #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ }; @@ -242,14 +230,12 @@ struct kvm_arch { struct kvm_rma_info *rma; unsigned long vrma_slb_v; int rma_setup_done; - int using_mmu_notifiers; u32 hpt_order; atomic_t vcpus_running; u32 online_vcores; unsigned long hpt_npte; unsigned long hpt_mask; atomic_t hpte_mod_interest; - spinlock_t slot_phys_lock; cpumask_t need_tlb_flush; int hpt_cma_alloc; #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ @@ -297,6 +283,7 @@ struct kvmppc_vcore { struct list_head runnable_threads; spinlock_t lock; wait_queue_head_t wq; + spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */ u64 stolen_tb; u64 preempt_tb; struct kvm_vcpu *runner; @@ -308,6 +295,7 @@ struct kvmppc_vcore { ulong dpdes; /* doorbell state (POWER8) */ void *mpp_buffer; /* Micro Partition Prefetch buffer */ bool mpp_buffer_is_valid; + ulong conferring_threads; }; #define VCORE_ENTRY_COUNT(vc) ((vc)->entry_exit_count & 0xff) @@ -664,6 +652,8 @@ struct kvm_vcpu_arch { spinlock_t tbacct_lock; u64 busy_stolen; u64 busy_preempt; + + u32 emul_inst; #endif }; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index a6dcdb6d13c1..46bf652c9169 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -170,8 +170,6 @@ extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, unsigned long ioba, unsigned long tce); extern long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn, unsigned long ioba); -extern struct kvm_rma_info *kvm_alloc_rma(void); -extern void kvm_release_rma(struct kvm_rma_info *ri); extern struct page *kvm_alloc_hpt(unsigned long nr_pages); extern void kvm_release_hpt(struct page *page, unsigned long nr_pages); extern int kvmppc_core_init_vm(struct kvm *kvm); diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 5cd8d2fddba9..eb95b675109b 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -56,6 +56,14 @@ struct opal_sg_list { #define OPAL_HARDWARE_FROZEN -13 #define OPAL_WRONG_STATE -14 #define OPAL_ASYNC_COMPLETION -15 +#define OPAL_I2C_TIMEOUT -17 +#define OPAL_I2C_INVALID_CMD -18 +#define OPAL_I2C_LBUS_PARITY -19 +#define OPAL_I2C_BKEND_OVERRUN -20 +#define OPAL_I2C_BKEND_ACCESS -21 +#define OPAL_I2C_ARBT_LOST -22 +#define OPAL_I2C_NACK_RCVD -23 +#define OPAL_I2C_STOP_ERR -24 /* API Tokens (in r0) */ #define OPAL_INVALID_CALL -1 @@ -152,12 +160,25 @@ struct opal_sg_list { #define OPAL_PCI_ERR_INJECT 96 #define OPAL_PCI_EEH_FREEZE_SET 97 #define OPAL_HANDLE_HMI 98 +#define OPAL_CONFIG_CPU_IDLE_STATE 99 +#define OPAL_SLW_SET_REG 100 #define OPAL_REGISTER_DUMP_REGION 101 #define OPAL_UNREGISTER_DUMP_REGION 102 #define OPAL_WRITE_TPO 103 #define OPAL_READ_TPO 104 #define OPAL_IPMI_SEND 107 #define OPAL_IPMI_RECV 108 +#define OPAL_I2C_REQUEST 109 + +/* Device tree flags */ + +/* Flags set in power-mgmt nodes in device tree if + * respective idle states are supported in the platform. + */ +#define OPAL_PM_NAP_ENABLED 0x00010000 +#define OPAL_PM_SLEEP_ENABLED 0x00020000 +#define OPAL_PM_WINKLE_ENABLED 0x00040000 +#define OPAL_PM_SLEEP_ENABLED_ER1 0x00080000 #ifndef __ASSEMBLY__ @@ -712,6 +733,24 @@ typedef struct oppanel_line { uint64_t line_len; } oppanel_line_t; +/* OPAL I2C request */ +struct opal_i2c_request { + uint8_t type; +#define OPAL_I2C_RAW_READ 0 +#define OPAL_I2C_RAW_WRITE 1 +#define OPAL_I2C_SM_READ 2 +#define OPAL_I2C_SM_WRITE 3 + uint8_t flags; +#define OPAL_I2C_ADDR_10 0x01 /* Not supported yet */ + uint8_t subaddr_sz; /* Max 4 */ + uint8_t reserved; + __be16 addr; /* 7 or 10 bit address */ + __be16 reserved2; + __be32 subaddr; /* Sub-address if any */ + __be32 size; /* Data size */ + __be64 buffer_ra; /* Buffer real address */ +}; + /* /sys/firmware/opal */ extern struct kobject *opal_kobj; @@ -876,11 +915,14 @@ int64_t opal_sensor_read(uint32_t sensor_hndl, int token, __be32 *sensor_data); int64_t opal_handle_hmi(void); int64_t opal_register_dump_region(uint32_t id, uint64_t start, uint64_t end); int64_t opal_unregister_dump_region(uint32_t id); +int64_t opal_slw_set_reg(uint64_t cpu_pir, uint64_t sprn, uint64_t val); int64_t opal_pci_set_phb_cxl_mode(uint64_t phb_id, uint64_t mode, uint64_t pe_number); int64_t opal_ipmi_send(uint64_t interface, struct opal_ipmi_msg *msg, uint64_t msg_len); int64_t opal_ipmi_recv(uint64_t interface, struct opal_ipmi_msg *msg, uint64_t *msg_len); +int64_t opal_i2c_request(uint64_t async_token, uint32_t bus_id, + struct opal_i2c_request *oreq); /* Internal functions */ extern int early_init_dt_scan_opal(unsigned long node, const char *uname, diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 24a386cbb928..e5f22c6c4bf9 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -152,6 +152,16 @@ struct paca_struct { u64 tm_scratch; /* TM scratch area for reclaim */ #endif +#ifdef CONFIG_PPC_POWERNV + /* Per-core mask tracking idle threads and a lock bit-[L][TTTTTTTT] */ + u32 *core_idle_state_ptr; + u8 thread_idle_state; /* PNV_THREAD_RUNNING/NAP/SLEEP */ + /* Mask to indicate thread id in core */ + u8 thread_mask; + /* Mask to denote subcore sibling threads */ + u8 subcore_sibling_mask; +#endif + #ifdef CONFIG_PPC_BOOK3S_64 /* Exclusive emergency stack pointer for machine check exception. */ void *mc_emergency_sp; diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 1a5287759fc8..03cd858a401c 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -194,6 +194,7 @@ #define PPC_INST_NAP 0x4c000364 #define PPC_INST_SLEEP 0x4c0003a4 +#define PPC_INST_WINKLE 0x4c0003e4 /* A2 specific instructions */ #define PPC_INST_ERATWE 0x7c0001a6 @@ -375,6 +376,7 @@ #define PPC_NAP stringify_in_c(.long PPC_INST_NAP) #define PPC_SLEEP stringify_in_c(.long PPC_INST_SLEEP) +#define PPC_WINKLE stringify_in_c(.long PPC_INST_WINKLE) /* BHRB instructions */ #define PPC_CLRBHRB stringify_in_c(.long PPC_INST_CLRBHRB) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 29c3798cf800..bf117d8fb45f 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -452,7 +452,8 @@ enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF}; extern int powersave_nap; /* set if nap mode can be used in idle loop */ extern unsigned long power7_nap(int check_irq); -extern void power7_sleep(void); +extern unsigned long power7_sleep(void); +extern unsigned long power7_winkle(void); extern void flush_instruction_cache(void); extern void hard_reset_now(void); extern void poweroff_now(void); diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index c998279bd85b..1c874fb533bb 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -118,8 +118,10 @@ #define __MSR (MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV) #ifdef __BIG_ENDIAN__ #define MSR_ __MSR +#define MSR_IDLE (MSR_ME | MSR_SF | MSR_HV) #else #define MSR_ (__MSR | MSR_LE) +#define MSR_IDLE (MSR_ME | MSR_SF | MSR_HV | MSR_LE) #endif #define MSR_KERNEL (MSR_ | MSR_64BIT) #define MSR_USER32 (MSR_ | MSR_PR | MSR_EE) @@ -371,6 +373,7 @@ #define SPRN_DBAT7L 0x23F /* Data BAT 7 Lower Register */ #define SPRN_DBAT7U 0x23E /* Data BAT 7 Upper Register */ #define SPRN_PPR 0x380 /* SMT Thread status Register */ +#define SPRN_TSCR 0x399 /* Thread Switch Control Register */ #define SPRN_DEC 0x016 /* Decrement Register */ #define SPRN_DER 0x095 /* Debug Enable Regsiter */ @@ -728,6 +731,7 @@ #define SPRN_BESCR 806 /* Branch event status and control register */ #define BESCR_GE 0x8000000000000000ULL /* Global Enable */ #define SPRN_WORT 895 /* Workload optimization register - thread */ +#define SPRN_WORC 863 /* Workload optimization register - core */ #define SPRN_PMC1 787 #define SPRN_PMC2 788 diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h index 6240698fee9a..ff21b7a2f0cc 100644 --- a/arch/powerpc/include/asm/syscall.h +++ b/arch/powerpc/include/asm/syscall.h @@ -90,6 +90,10 @@ static inline void syscall_set_arguments(struct task_struct *task, static inline int syscall_get_arch(void) { - return is_32bit_task() ? AUDIT_ARCH_PPC : AUDIT_ARCH_PPC64; + int arch = is_32bit_task() ? AUDIT_ARCH_PPC : AUDIT_ARCH_PPC64; +#ifdef __LITTLE_ENDIAN__ + arch |= __AUDIT_ARCH_LE; +#endif + return arch; } #endif /* _ASM_SYSCALL_H */ diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index ce9577d693be..91062eef582f 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -366,3 +366,4 @@ SYSCALL_SPU(seccomp) SYSCALL_SPU(getrandom) SYSCALL_SPU(memfd_create) SYSCALL_SPU(bpf) +COMPAT_SYS(execveat) diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 9485b43a7c00..a0c071d24e0e 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -284,7 +284,7 @@ do { \ if (!is_kernel_addr((unsigned long)__gu_addr)) \ might_fault(); \ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ - (x) = (__typeof__(*(ptr)))__gu_val; \ + (x) = (__force __typeof__(*(ptr)))__gu_val; \ __gu_err; \ }) #endif /* __powerpc64__ */ @@ -297,7 +297,7 @@ do { \ might_fault(); \ if (access_ok(VERIFY_READ, __gu_addr, (size))) \ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ - (x) = (__typeof__(*(ptr)))__gu_val; \ + (x) = (__force __typeof__(*(ptr)))__gu_val; \ __gu_err; \ }) @@ -308,7 +308,7 @@ do { \ const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ __chk_user_ptr(ptr); \ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ - (x) = (__typeof__(*(ptr)))__gu_val; \ + (x) = (__force __typeof__(*(ptr)))__gu_val; \ __gu_err; \ }) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index e0da021caa00..36b79c31eedd 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -12,7 +12,7 @@ #include <uapi/asm/unistd.h> -#define __NR_syscalls 362 +#define __NR_syscalls 363 #define __NR__exit __NR_exit #define NR_syscalls __NR_syscalls diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h index f55351f2e66e..ef5b5b1f3123 100644 --- a/arch/powerpc/include/uapi/asm/unistd.h +++ b/arch/powerpc/include/uapi/asm/unistd.h @@ -384,5 +384,6 @@ #define __NR_getrandom 359 #define __NR_memfd_create 360 #define __NR_bpf 361 +#define __NR_execveat 362 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index c161ef3f28a1..e624f9646350 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -489,7 +489,6 @@ int main(void) DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid)); DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr)); DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1)); - DEFINE(KVM_TLBIE_LOCK, offsetof(struct kvm, arch.tlbie_lock)); DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits)); DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls)); DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr)); @@ -499,6 +498,7 @@ int main(void) 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_HEIR, offsetof(struct kvm_vcpu, arch.emul_inst)); #endif #ifdef CONFIG_PPC_BOOK3S DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id)); @@ -726,5 +726,16 @@ int main(void) arch.timing_last_enter.tv32.tbl)); #endif +#ifdef CONFIG_PPC_POWERNV + DEFINE(PACA_CORE_IDLE_STATE_PTR, + offsetof(struct paca_struct, core_idle_state_ptr)); + DEFINE(PACA_THREAD_IDLE_STATE, + offsetof(struct paca_struct, thread_idle_state)); + DEFINE(PACA_THREAD_MASK, + offsetof(struct paca_struct, thread_mask)); + DEFINE(PACA_SUBCORE_SIBLING_MASK, + offsetof(struct paca_struct, subcore_sibling_mask)); +#endif + return 0; } diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index db08382e19f1..c2df8150bd7a 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -15,6 +15,7 @@ #include <asm/hw_irq.h> #include <asm/exception-64s.h> #include <asm/ptrace.h> +#include <asm/cpuidle.h> /* * We layout physical memory as follows: @@ -101,23 +102,34 @@ system_reset_pSeries: #ifdef CONFIG_PPC_P7_NAP BEGIN_FTR_SECTION /* Running native on arch 2.06 or later, check if we are - * waking up from nap. We only handle no state loss and - * supervisor state loss. We do -not- handle hypervisor - * state loss at this time. + * waking up from nap/sleep/winkle. */ mfspr r13,SPRN_SRR1 rlwinm. r13,r13,47-31,30,31 beq 9f - /* waking up from powersave (nap) state */ - cmpwi cr1,r13,2 - /* Total loss of HV state is fatal, we could try to use the - * PIR to locate a PACA, then use an emergency stack etc... - * OPAL v3 based powernv platforms have new idle states - * which fall in this catagory. + cmpwi cr3,r13,2 + + /* + * Check if last bit of HSPGR0 is set. This indicates whether we are + * waking up from winkle. */ - bgt cr1,8f GET_PACA(r13) + clrldi r5,r13,63 + clrrdi r13,r13,1 + cmpwi cr4,r5,1 + mtspr SPRN_HSPRG0,r13 + + lbz r0,PACA_THREAD_IDLE_STATE(r13) + cmpwi cr2,r0,PNV_THREAD_NAP + bgt cr2,8f /* Either sleep or Winkle */ + + /* Waking up from nap should not cause hypervisor state loss */ + bgt cr3,. + + /* Waking up from nap */ + li r0,PNV_THREAD_RUNNING + stb r0,PACA_THREAD_IDLE_STATE(r13) /* Clear thread state */ #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE li r0,KVM_HWTHREAD_IN_KERNEL @@ -133,7 +145,7 @@ BEGIN_FTR_SECTION /* Return SRR1 from power7_nap() */ mfspr r3,SPRN_SRR1 - beq cr1,2f + beq cr3,2f b power7_wakeup_noloss 2: b power7_wakeup_loss @@ -1382,6 +1394,7 @@ machine_check_handle_early: MACHINE_CHECK_HANDLER_WINDUP GET_PACA(r13) ld r1,PACAR1(r13) + li r3,PNV_THREAD_NAP b power7_enter_nap_mode 4: #endif diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index 18c0687e5ab3..05adc8bbdef8 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -18,9 +18,25 @@ #include <asm/hw_irq.h> #include <asm/kvm_book3s_asm.h> #include <asm/opal.h> +#include <asm/cpuidle.h> +#include <asm/mmu-hash64.h> #undef DEBUG +/* + * Use unused space in the interrupt stack to save and restore + * registers for winkle support. + */ +#define _SDR1 GPR3 +#define _RPR GPR4 +#define _SPURR GPR5 +#define _PURR GPR6 +#define _TSCR GPR7 +#define _DSCR GPR8 +#define _AMOR GPR9 +#define _WORT GPR10 +#define _WORC GPR11 + /* Idle state entry routines */ #define IDLE_STATE_ENTER_SEQ(IDLE_INST) \ @@ -37,8 +53,7 @@ /* * Pass requested state in r3: - * 0 - nap - * 1 - sleep + * r3 - PNV_THREAD_NAP/SLEEP/WINKLE * * To check IRQ_HAPPENED in r4 * 0 - don't check @@ -101,18 +116,105 @@ _GLOBAL(power7_powersave_common) std r9,_MSR(r1) std r1,PACAR1(r13) -_GLOBAL(power7_enter_nap_mode) + /* + * Go to real mode to do the nap, as required by the architecture. + * Also, we need to be in real mode before setting hwthread_state, + * because as soon as we do that, another thread can switch + * the MMU context to the guest. + */ + LOAD_REG_IMMEDIATE(r5, MSR_IDLE) + li r6, MSR_RI + andc r6, r9, r6 + LOAD_REG_ADDR(r7, power7_enter_nap_mode) + mtmsrd r6, 1 /* clear RI before setting SRR0/1 */ + mtspr SPRN_SRR0, r7 + mtspr SPRN_SRR1, r5 + rfid + + .globl power7_enter_nap_mode +power7_enter_nap_mode: #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE /* Tell KVM we're napping */ li r4,KVM_HWTHREAD_IN_NAP stb r4,HSTATE_HWTHREAD_STATE(r13) #endif - cmpwi cr0,r3,1 - beq 2f + stb r3,PACA_THREAD_IDLE_STATE(r13) + cmpwi cr3,r3,PNV_THREAD_SLEEP + bge cr3,2f IDLE_STATE_ENTER_SEQ(PPC_NAP) /* No return */ -2: IDLE_STATE_ENTER_SEQ(PPC_SLEEP) - /* No return */ +2: + /* Sleep or winkle */ + lbz r7,PACA_THREAD_MASK(r13) + ld r14,PACA_CORE_IDLE_STATE_PTR(r13) +lwarx_loop1: + lwarx r15,0,r14 + andc r15,r15,r7 /* Clear thread bit */ + + andi. r15,r15,PNV_CORE_IDLE_THREAD_BITS + +/* + * If cr0 = 0, then current thread is the last thread of the core entering + * sleep. Last thread needs to execute the hardware bug workaround code if + * required by the platform. + * Make the workaround call unconditionally here. The below branch call is + * patched out when the idle states are discovered if the platform does not + * require it. + */ +.global pnv_fastsleep_workaround_at_entry +pnv_fastsleep_workaround_at_entry: + beq fastsleep_workaround_at_entry + + stwcx. r15,0,r14 + bne- lwarx_loop1 + isync + +common_enter: /* common code for all the threads entering sleep or winkle */ + bgt cr3,enter_winkle + IDLE_STATE_ENTER_SEQ(PPC_SLEEP) + +fastsleep_workaround_at_entry: + ori r15,r15,PNV_CORE_IDLE_LOCK_BIT + stwcx. r15,0,r14 + bne- lwarx_loop1 + isync + + /* Fast sleep workaround */ + li r3,1 + li r4,1 + li r0,OPAL_CONFIG_CPU_IDLE_STATE + bl opal_call_realmode + + /* Clear Lock bit */ + li r0,0 + lwsync + stw r0,0(r14) + b common_enter + +enter_winkle: + /* + * Note all register i.e per-core, per-subcore or per-thread is saved + * here since any thread in the core might wake up first + */ + mfspr r3,SPRN_SDR1 + std r3,_SDR1(r1) + mfspr r3,SPRN_RPR + std r3,_RPR(r1) + mfspr r3,SPRN_SPURR + std r3,_SPURR(r1) + mfspr r3,SPRN_PURR + std r3,_PURR(r1) + mfspr r3,SPRN_TSCR + std r3,_TSCR(r1) + mfspr r3,SPRN_DSCR + std r3,_DSCR(r1) + mfspr r3,SPRN_AMOR + std r3,_AMOR(r1) + mfspr r3,SPRN_WORT + std r3,_WORT(r1) + mfspr r3,SPRN_WORC + std r3,_WORC(r1) + IDLE_STATE_ENTER_SEQ(PPC_WINKLE) _GLOBAL(power7_idle) /* Now check if user or arch enabled NAP mode */ @@ -125,48 +227,21 @@ _GLOBAL(power7_idle) _GLOBAL(power7_nap) mr r4,r3 - li r3,0 + li r3,PNV_THREAD_NAP b power7_powersave_common /* No return */ _GLOBAL(power7_sleep) - li r3,1 + li r3,PNV_THREAD_SLEEP li r4,1 b power7_powersave_common /* No return */ -/* - * Make opal call in realmode. This is a generic function to be called - * from realmode from reset vector. It handles endianess. - * - * r13 - paca pointer - * r1 - stack pointer - * r3 - opal token - */ -opal_call_realmode: - mflr r12 - std r12,_LINK(r1) - ld r2,PACATOC(r13) - /* Set opal return address */ - LOAD_REG_ADDR(r0,return_from_opal_call) - mtlr r0 - /* Handle endian-ness */ - li r0,MSR_LE - mfmsr r12 - andc r12,r12,r0 - mtspr SPRN_HSRR1,r12 - mr r0,r3 /* Move opal token to r0 */ - LOAD_REG_ADDR(r11,opal) - ld r12,8(r11) - ld r2,0(r11) - mtspr SPRN_HSRR0,r12 - hrfid - -return_from_opal_call: - FIXUP_ENDIAN - ld r0,_LINK(r1) - mtlr r0 - blr +_GLOBAL(power7_winkle) + li r3,3 + li r4,1 + b power7_powersave_common + /* No return */ #define CHECK_HMI_INTERRUPT \ mfspr r0,SPRN_SRR1; \ @@ -181,7 +256,7 @@ ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66); \ ld r2,PACATOC(r13); \ ld r1,PACAR1(r13); \ std r3,ORIG_GPR3(r1); /* Save original r3 */ \ - li r3,OPAL_HANDLE_HMI; /* Pass opal token argument*/ \ + li r0,OPAL_HANDLE_HMI; /* Pass opal token argument*/ \ bl opal_call_realmode; \ ld r3,ORIG_GPR3(r1); /* Restore original r3 */ \ 20: nop; @@ -190,16 +265,190 @@ ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66); \ _GLOBAL(power7_wakeup_tb_loss) ld r2,PACATOC(r13); ld r1,PACAR1(r13) + /* + * Before entering any idle state, the NVGPRs are saved in the stack + * and they are restored before switching to the process context. Hence + * until they are restored, they are free to be used. + * + * Save SRR1 in a NVGPR as it might be clobbered in opal_call_realmode + * (called in CHECK_HMI_INTERRUPT). SRR1 is required to determine the + * wakeup reason if we branch to kvm_start_guest. + */ + mfspr r16,SPRN_SRR1 BEGIN_FTR_SECTION CHECK_HMI_INTERRUPT END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) + + lbz r7,PACA_THREAD_MASK(r13) + ld r14,PACA_CORE_IDLE_STATE_PTR(r13) +lwarx_loop2: + lwarx r15,0,r14 + andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT + /* + * Lock bit is set in one of the 2 cases- + * a. In the sleep/winkle enter path, the last thread is executing + * fastsleep workaround code. + * b. In the wake up path, another thread is executing fastsleep + * workaround undo code or resyncing timebase or restoring context + * In either case loop until the lock bit is cleared. + */ + bne core_idle_lock_held + + cmpwi cr2,r15,0 + lbz r4,PACA_SUBCORE_SIBLING_MASK(r13) + and r4,r4,r15 + cmpwi cr1,r4,0 /* Check if first in subcore */ + + /* + * At this stage + * cr1 - 0b0100 if first thread to wakeup in subcore + * cr2 - 0b0100 if first thread to wakeup in core + * cr3- 0b0010 if waking up from sleep or winkle + * cr4 - 0b0100 if waking up from winkle + */ + + or r15,r15,r7 /* Set thread bit */ + + beq cr1,first_thread_in_subcore + + /* Not first thread in subcore to wake up */ + stwcx. r15,0,r14 + bne- lwarx_loop2 + isync + b common_exit + +core_idle_lock_held: + HMT_LOW +core_idle_lock_loop: + lwz r15,0(14) + andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT + bne core_idle_lock_loop + HMT_MEDIUM + b lwarx_loop2 + +first_thread_in_subcore: + /* First thread in subcore to wakeup */ + ori r15,r15,PNV_CORE_IDLE_LOCK_BIT + stwcx. r15,0,r14 + bne- lwarx_loop2 + isync + + /* + * If waking up from sleep, subcore state is not lost. Hence + * skip subcore state restore + */ + bne cr4,subcore_state_restored + + /* Restore per-subcore state */ + ld r4,_SDR1(r1) + mtspr SPRN_SDR1,r4 + ld r4,_RPR(r1) + mtspr SPRN_RPR,r4 + ld r4,_AMOR(r1) + mtspr SPRN_AMOR,r4 + +subcore_state_restored: + /* + * Check if the thread is also the first thread in the core. If not, + * skip to clear_lock. + */ + bne cr2,clear_lock + +first_thread_in_core: + + /* + * First thread in the core waking up from fastsleep. It needs to + * call the fastsleep workaround code if the platform requires it. + * Call it unconditionally here. The below branch instruction will + * be patched out when the idle states are discovered if platform + * does not require workaround. + */ +.global pnv_fastsleep_workaround_at_exit +pnv_fastsleep_workaround_at_exit: + b fastsleep_workaround_at_exit + +timebase_resync: + /* Do timebase resync if we are waking up from sleep. Use cr3 value + * set in exceptions-64s.S */ + ble cr3,clear_lock /* Time base re-sync */ - li r3,OPAL_RESYNC_TIMEBASE + li r0,OPAL_RESYNC_TIMEBASE bl opal_call_realmode; - /* TODO: Check r3 for failure */ + /* + * If waking up from sleep, per core state is not lost, skip to + * clear_lock. + */ + bne cr4,clear_lock + + /* Restore per core state */ + ld r4,_TSCR(r1) + mtspr SPRN_TSCR,r4 + ld r4,_WORC(r1) + mtspr SPRN_WORC,r4 + +clear_lock: + andi. r15,r15,PNV_CORE_IDLE_THREAD_BITS + lwsync + stw r15,0(r14) + +common_exit: + /* + * Common to all threads. + * + * If waking up from sleep, hypervisor state is not lost. Hence + * skip hypervisor state restore. + */ + bne cr4,hypervisor_state_restored + + /* Waking up from winkle */ + + /* Restore per thread state */ + bl __restore_cpu_power8 + + /* Restore SLB from PACA */ + ld r8,PACA_SLBSHADOWPTR(r13) + + .rept SLB_NUM_BOLTED + li r3, SLBSHADOW_SAVEAREA + LDX_BE r5, r8, r3 + addi r3, r3, 8 + LDX_BE r6, r8, r3 + andis. r7,r5,SLB_ESID_V@h + beq 1f + slbmte r6,r5 +1: addi r8,r8,16 + .endr + + ld r4,_SPURR(r1) + mtspr SPRN_SPURR,r4 + ld r4,_PURR(r1) + mtspr SPRN_PURR,r4 + ld r4,_DSCR(r1) + mtspr SPRN_DSCR,r4 + ld r4,_WORT(r1) + mtspr SPRN_WORT,r4 + +hypervisor_state_restored: + + li r5,PNV_THREAD_RUNNING + stb r5,PACA_THREAD_IDLE_STATE(r13) + + mtspr SPRN_SRR1,r16 +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + li r0,KVM_HWTHREAD_IN_KERNEL + stb r0,HSTATE_HWTHREAD_STATE(r13) + /* Order setting hwthread_state vs. testing hwthread_req */ + sync + lbz r0,HSTATE_HWTHREAD_REQ(r13) + cmpwi r0,0 + beq 6f + b kvm_start_guest +6: +#endif + REST_NVGPRS(r1) REST_GPR(2, r1) ld r3,_CCR(r1) @@ -212,6 +461,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) mtspr SPRN_SRR0,r5 rfid +fastsleep_workaround_at_exit: + li r3,1 + li r4,0 + li r0,OPAL_CONFIG_CPU_IDLE_STATE + bl opal_call_realmode + b timebase_resync + /* * R3 here contains the value that will be returned to the caller * of power7_nap. diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index 879b3aacac32..f96d1ec24189 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -330,7 +330,7 @@ void default_machine_kexec(struct kimage *image) * using debugger IPI. */ - if (crashing_cpu == -1) + if (!kdump_in_progress()) kexec_prepare_cpus(); pr_debug("kexec: Starting switchover sequence.\n"); diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 602eb51d20bc..f5769f19ae25 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -172,6 +172,7 @@ config KVM_XICS depends on KVM_BOOK3S_64 && !KVM_MPIC select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQFD + default y ---help--- Include support for the XICS (eXternal Interrupt Controller Specification) interrupt controller architecture used on diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index b32db4b95361..888bf466d8c6 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -64,14 +64,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; -void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu) -{ -} - -void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu) -{ -} - void kvmppc_unfixup_split_real(struct kvm_vcpu *vcpu) { if (vcpu->arch.hflags & BOOK3S_HFLAG_SPLIT_HACK) { diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index cd0b0730e29e..a2eb6d354a57 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -78,11 +78,6 @@ static inline bool sr_kp(u32 sr_raw) return (sr_raw & 0x20000000) ? true: false; } -static inline bool sr_nx(u32 sr_raw) -{ - return (sr_raw & 0x10000000) ? true: false; -} - static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *pte, bool data, bool iswrite); diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index d40770248b6a..534acb3c6c3d 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -37,8 +37,7 @@ #include <asm/ppc-opcode.h> #include <asm/cputable.h> -/* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */ -#define MAX_LPID_970 63 +#include "trace_hv.h" /* Power architecture requires HPT is at least 256kB */ #define PPC_MIN_HPT_ORDER 18 @@ -229,14 +228,9 @@ int kvmppc_mmu_hv_init(void) if (!cpu_has_feature(CPU_FTR_HVMODE)) return -EINVAL; - /* POWER7 has 10-bit LPIDs, PPC970 and e500mc have 6-bit LPIDs */ - if (cpu_has_feature(CPU_FTR_ARCH_206)) { - host_lpid = mfspr(SPRN_LPID); /* POWER7 */ - rsvd_lpid = LPID_RSVD; - } else { - host_lpid = 0; /* PPC970 */ - rsvd_lpid = MAX_LPID_970; - } + /* POWER7 has 10-bit LPIDs (12-bit in POWER8) */ + host_lpid = mfspr(SPRN_LPID); + rsvd_lpid = LPID_RSVD; kvmppc_init_lpid(rsvd_lpid + 1); @@ -259,130 +253,12 @@ static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu) kvmppc_set_msr(vcpu, msr); } -/* - * This is called to get a reference to a guest page if there isn't - * one already in the memslot->arch.slot_phys[] array. - */ -static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn, - struct kvm_memory_slot *memslot, - unsigned long psize) -{ - unsigned long start; - long np, err; - struct page *page, *hpage, *pages[1]; - unsigned long s, pgsize; - unsigned long *physp; - unsigned int is_io, got, pgorder; - struct vm_area_struct *vma; - unsigned long pfn, i, npages; - - physp = memslot->arch.slot_phys; - if (!physp) - return -EINVAL; - if (physp[gfn - memslot->base_gfn]) - return 0; - - is_io = 0; - got = 0; - page = NULL; - pgsize = psize; - err = -EINVAL; - start = gfn_to_hva_memslot(memslot, gfn); - - /* Instantiate and get the page we want access to */ - np = get_user_pages_fast(start, 1, 1, pages); - if (np != 1) { - /* Look up the vma for the page */ - down_read(¤t->mm->mmap_sem); - vma = find_vma(current->mm, start); - if (!vma || vma->vm_start > start || - start + psize > vma->vm_end || - !(vma->vm_flags & VM_PFNMAP)) - goto up_err; - is_io = hpte_cache_bits(pgprot_val(vma->vm_page_prot)); - pfn = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); - /* check alignment of pfn vs. requested page size */ - if (psize > PAGE_SIZE && (pfn & ((psize >> PAGE_SHIFT) - 1))) - goto up_err; - up_read(¤t->mm->mmap_sem); - - } else { - page = pages[0]; - got = KVMPPC_GOT_PAGE; - - /* See if this is a large page */ - s = PAGE_SIZE; - if (PageHuge(page)) { - hpage = compound_head(page); - s <<= compound_order(hpage); - /* Get the whole large page if slot alignment is ok */ - if (s > psize && slot_is_aligned(memslot, s) && - !(memslot->userspace_addr & (s - 1))) { - start &= ~(s - 1); - pgsize = s; - get_page(hpage); - put_page(page); - page = hpage; - } - } - if (s < psize) - goto out; - pfn = page_to_pfn(page); - } - - npages = pgsize >> PAGE_SHIFT; - pgorder = __ilog2(npages); - physp += (gfn - memslot->base_gfn) & ~(npages - 1); - spin_lock(&kvm->arch.slot_phys_lock); - for (i = 0; i < npages; ++i) { - if (!physp[i]) { - physp[i] = ((pfn + i) << PAGE_SHIFT) + - got + is_io + pgorder; - got = 0; - } - } - spin_unlock(&kvm->arch.slot_phys_lock); - err = 0; - - out: - if (got) - put_page(page); - return err; - - up_err: - up_read(¤t->mm->mmap_sem); - return err; -} - long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags, long pte_index, unsigned long pteh, unsigned long ptel, unsigned long *pte_idx_ret) { - unsigned long psize, gpa, gfn; - struct kvm_memory_slot *memslot; long ret; - if (kvm->arch.using_mmu_notifiers) - goto do_insert; - - psize = hpte_page_size(pteh, ptel); - if (!psize) - return H_PARAMETER; - - pteh &= ~(HPTE_V_HVLOCK | HPTE_V_ABSENT | HPTE_V_VALID); - - /* Find the memslot (if any) for this address */ - gpa = (ptel & HPTE_R_RPN) & ~(psize - 1); - gfn = gpa >> PAGE_SHIFT; - memslot = gfn_to_memslot(kvm, gfn); - if (memslot && !(memslot->flags & KVM_MEMSLOT_INVALID)) { - if (!slot_is_aligned(memslot, psize)) - return H_PARAMETER; - if (kvmppc_get_guest_page(kvm, gfn, memslot, psize) < 0) - return H_PARAMETER; - } - - do_insert: /* Protect linux PTE lookup from page table destruction */ rcu_read_lock_sched(); /* this disables preemption too */ ret = kvmppc_do_h_enter(kvm, flags, pte_index, pteh, ptel, @@ -397,19 +273,6 @@ long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags, } -/* - * We come here on a H_ENTER call from the guest when we are not - * using mmu notifiers and we don't have the requested page pinned - * already. - */ -long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags, - long pte_index, unsigned long pteh, - unsigned long ptel) -{ - return kvmppc_virtmode_do_h_enter(vcpu->kvm, flags, pte_index, - pteh, ptel, &vcpu->arch.gpr[4]); -} - static struct kvmppc_slb *kvmppc_mmu_book3s_hv_find_slbe(struct kvm_vcpu *vcpu, gva_t eaddr) { @@ -494,7 +357,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, gpte->may_execute = gpte->may_read && !(gr & (HPTE_R_N | HPTE_R_G)); /* Storage key permission check for POWER7 */ - if (data && virtmode && cpu_has_feature(CPU_FTR_ARCH_206)) { + if (data && virtmode) { int amrfield = hpte_get_skey_perm(gr, vcpu->arch.amr); if (amrfield & 1) gpte->may_read = 0; @@ -622,14 +485,13 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, gfn = gpa >> PAGE_SHIFT; memslot = gfn_to_memslot(kvm, gfn); + trace_kvm_page_fault_enter(vcpu, hpte, memslot, ea, dsisr); + /* No memslot means it's an emulated MMIO region */ if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea, dsisr & DSISR_ISSTORE); - if (!kvm->arch.using_mmu_notifiers) - return -EFAULT; /* should never get here */ - /* * This should never happen, because of the slot_is_aligned() * check in kvmppc_do_h_enter(). @@ -641,6 +503,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, mmu_seq = kvm->mmu_notifier_seq; smp_rmb(); + ret = -EFAULT; is_io = 0; pfn = 0; page = NULL; @@ -664,7 +527,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } up_read(¤t->mm->mmap_sem); if (!pfn) - return -EFAULT; + goto out_put; } else { page = pages[0]; pfn = page_to_pfn(page); @@ -694,14 +557,14 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } } - ret = -EFAULT; if (psize > pte_size) goto out_put; /* Check WIMG vs. the actual page we're accessing */ if (!hpte_cache_flags_ok(r, is_io)) { if (is_io) - return -EFAULT; + goto out_put; + /* * Allow guest to map emulated device memory as * uncacheable, but actually make it cacheable. @@ -765,6 +628,8 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, SetPageDirty(page); out_put: + trace_kvm_page_fault_exit(vcpu, hpte, ret); + if (page) { /* * We drop pages[0] here, not page because page might @@ -895,8 +760,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, psize = hpte_page_size(be64_to_cpu(hptep[0]), ptel); if ((be64_to_cpu(hptep[0]) & HPTE_V_VALID) && hpte_rpn(ptel, psize) == gfn) { - if (kvm->arch.using_mmu_notifiers) - hptep[0] |= cpu_to_be64(HPTE_V_ABSENT); + hptep[0] |= cpu_to_be64(HPTE_V_ABSENT); kvmppc_invalidate_hpte(kvm, hptep, i); /* Harvest R and C */ rcbits = be64_to_cpu(hptep[1]) & (HPTE_R_R | HPTE_R_C); @@ -914,15 +778,13 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, int kvm_unmap_hva_hv(struct kvm *kvm, unsigned long hva) { - if (kvm->arch.using_mmu_notifiers) - kvm_handle_hva(kvm, hva, kvm_unmap_rmapp); + kvm_handle_hva(kvm, hva, kvm_unmap_rmapp); return 0; } int kvm_unmap_hva_range_hv(struct kvm *kvm, unsigned long start, unsigned long end) { - if (kvm->arch.using_mmu_notifiers) - kvm_handle_hva_range(kvm, start, end, kvm_unmap_rmapp); + kvm_handle_hva_range(kvm, start, end, kvm_unmap_rmapp); return 0; } @@ -1004,8 +866,6 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, int kvm_age_hva_hv(struct kvm *kvm, unsigned long start, unsigned long end) { - if (!kvm->arch.using_mmu_notifiers) - return 0; return kvm_handle_hva_range(kvm, start, end, kvm_age_rmapp); } @@ -1042,15 +902,11 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, int kvm_test_age_hva_hv(struct kvm *kvm, unsigned long hva) { - if (!kvm->arch.using_mmu_notifiers) - return 0; return kvm_handle_hva(kvm, hva, kvm_test_age_rmapp); } void kvm_set_spte_hva_hv(struct kvm *kvm, unsigned long hva, pte_t pte) { - if (!kvm->arch.using_mmu_notifiers) - return; kvm_handle_hva(kvm, hva, kvm_unmap_rmapp); } @@ -1117,8 +973,11 @@ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp) } /* Now check and modify the HPTE */ - if (!(hptep[0] & cpu_to_be64(HPTE_V_VALID))) + if (!(hptep[0] & cpu_to_be64(HPTE_V_VALID))) { + /* unlock and continue */ + hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK); continue; + } /* need to make it temporarily absent so C is stable */ hptep[0] |= cpu_to_be64(HPTE_V_ABSENT); @@ -1206,35 +1065,17 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa, struct page *page, *pages[1]; int npages; unsigned long hva, offset; - unsigned long pa; - unsigned long *physp; int srcu_idx; srcu_idx = srcu_read_lock(&kvm->srcu); memslot = gfn_to_memslot(kvm, gfn); if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) goto err; - if (!kvm->arch.using_mmu_notifiers) { - physp = memslot->arch.slot_phys; - if (!physp) - goto err; - physp += gfn - memslot->base_gfn; - pa = *physp; - if (!pa) { - if (kvmppc_get_guest_page(kvm, gfn, memslot, - PAGE_SIZE) < 0) - goto err; - pa = *physp; - } - page = pfn_to_page(pa >> PAGE_SHIFT); - get_page(page); - } else { - hva = gfn_to_hva_memslot(memslot, gfn); - npages = get_user_pages_fast(hva, 1, 1, pages); - if (npages < 1) - goto err; - page = pages[0]; - } + hva = gfn_to_hva_memslot(memslot, gfn); + npages = get_user_pages_fast(hva, 1, 1, pages); + if (npages < 1) + goto err; + page = pages[0]; srcu_read_unlock(&kvm->srcu, srcu_idx); offset = gpa & (PAGE_SIZE - 1); @@ -1258,7 +1099,7 @@ void kvmppc_unpin_guest_page(struct kvm *kvm, void *va, unsigned long gpa, put_page(page); - if (!dirty || !kvm->arch.using_mmu_notifiers) + if (!dirty) return; /* We need to mark this page dirty in the rmap chain */ @@ -1539,9 +1380,15 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE)); lbuf = (unsigned long __user *)buf; for (j = 0; j < hdr.n_valid; ++j) { + __be64 hpte_v; + __be64 hpte_r; + err = -EFAULT; - if (__get_user(v, lbuf) || __get_user(r, lbuf + 1)) + if (__get_user(hpte_v, lbuf) || + __get_user(hpte_r, lbuf + 1)) goto out; + v = be64_to_cpu(hpte_v); + r = be64_to_cpu(hpte_r); err = -EINVAL; if (!(v & HPTE_V_VALID)) goto out; @@ -1652,10 +1499,7 @@ void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu) { struct kvmppc_mmu *mmu = &vcpu->arch.mmu; - if (cpu_has_feature(CPU_FTR_ARCH_206)) - vcpu->arch.slb_nr = 32; /* POWER7 */ - else - vcpu->arch.slb_nr = 64; + vcpu->arch.slb_nr = 32; /* POWER7/POWER8 */ mmu->xlate = kvmppc_mmu_book3s_64_hv_xlate; mmu->reset_msr = kvmppc_mmu_book3s_64_hv_reset_msr; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index e63587d30b70..de4018a1bc4b 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -58,6 +58,9 @@ #include "book3s.h" +#define CREATE_TRACE_POINTS +#include "trace_hv.h" + /* #define EXIT_DEBUG */ /* #define EXIT_DEBUG_SIMPLE */ /* #define EXIT_DEBUG_INT */ @@ -135,11 +138,10 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) * stolen. * * Updates to busy_stolen are protected by arch.tbacct_lock; - * updates to vc->stolen_tb are protected by the arch.tbacct_lock - * of the vcpu that has taken responsibility for running the vcore - * (i.e. vc->runner). The stolen times are measured in units of - * timebase ticks. (Note that the != TB_NIL checks below are - * purely defensive; they should never fail.) + * updates to vc->stolen_tb are protected by the vcore->stoltb_lock + * lock. The stolen times are measured in units of timebase ticks. + * (Note that the != TB_NIL checks below are purely defensive; + * they should never fail.) */ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu) @@ -147,12 +149,21 @@ 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_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; - vc->preempt_tb = TB_NIL; + /* + * We can test vc->runner without taking the vcore lock, + * because only this task ever sets vc->runner to this + * vcpu, and once it is set to this vcpu, only this task + * ever sets it to NULL. + */ + if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE) { + spin_lock_irqsave(&vc->stoltb_lock, flags); + if (vc->preempt_tb != TB_NIL) { + vc->stolen_tb += mftb() - vc->preempt_tb; + vc->preempt_tb = TB_NIL; + } + spin_unlock_irqrestore(&vc->stoltb_lock, flags); } + spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST && vcpu->arch.busy_preempt != TB_NIL) { vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt; @@ -166,9 +177,12 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) struct kvmppc_vcore *vc = vcpu->arch.vcore; unsigned long flags; - spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); - if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE) + if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE) { + spin_lock_irqsave(&vc->stoltb_lock, flags); vc->preempt_tb = mftb(); + spin_unlock_irqrestore(&vc->stoltb_lock, flags); + } + spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST) vcpu->arch.busy_preempt = mftb(); spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags); @@ -191,9 +205,6 @@ int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) struct kvmppc_vcore *vc = vcpu->arch.vcore; if (arch_compat) { - if (!cpu_has_feature(CPU_FTR_ARCH_206)) - return -EINVAL; /* 970 has no compat mode support */ - switch (arch_compat) { case PVR_ARCH_205: /* @@ -505,25 +516,14 @@ static void kvmppc_update_vpas(struct kvm_vcpu *vcpu) static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now) { u64 p; + unsigned long flags; - /* - * If we are the task running the vcore, then since we hold - * the vcore lock, we can't be preempted, so stolen_tb/preempt_tb - * can't be updated, so we don't need the tbacct_lock. - * If the vcore is inactive, it can't become active (since we - * hold the vcore lock), so the vcpu load/put functions won't - * update stolen_tb/preempt_tb, and we don't need tbacct_lock. - */ + spin_lock_irqsave(&vc->stoltb_lock, flags); + p = vc->stolen_tb; if (vc->vcore_state != VCORE_INACTIVE && - vc->runner->arch.run_task != current) { - 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_irq(&vc->runner->arch.tbacct_lock); - } else { - p = vc->stolen_tb; - } + vc->preempt_tb != TB_NIL) + p += now - vc->preempt_tb; + spin_unlock_irqrestore(&vc->stoltb_lock, flags); return p; } @@ -607,10 +607,45 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags, } } +static int kvm_arch_vcpu_yield_to(struct kvm_vcpu *target) +{ + struct kvmppc_vcore *vcore = target->arch.vcore; + + /* + * We expect to have been called by the real mode handler + * (kvmppc_rm_h_confer()) which would have directly returned + * H_SUCCESS if the source vcore wasn't idle (e.g. if it may + * have useful work to do and should not confer) so we don't + * recheck that here. + */ + + spin_lock(&vcore->lock); + if (target->arch.state == KVMPPC_VCPU_RUNNABLE && + vcore->vcore_state != VCORE_INACTIVE) + target = vcore->runner; + spin_unlock(&vcore->lock); + + return kvm_vcpu_yield_to(target); +} + +static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu) +{ + int yield_count = 0; + struct lppaca *lppaca; + + spin_lock(&vcpu->arch.vpa_update_lock); + lppaca = (struct lppaca *)vcpu->arch.vpa.pinned_addr; + if (lppaca) + yield_count = lppaca->yield_count; + spin_unlock(&vcpu->arch.vpa_update_lock); + return yield_count; +} + int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) { unsigned long req = kvmppc_get_gpr(vcpu, 3); unsigned long target, ret = H_SUCCESS; + int yield_count; struct kvm_vcpu *tvcpu; int idx, rc; @@ -619,14 +654,6 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) return RESUME_HOST; switch (req) { - case H_ENTER: - idx = srcu_read_lock(&vcpu->kvm->srcu); - ret = kvmppc_virtmode_h_enter(vcpu, kvmppc_get_gpr(vcpu, 4), - kvmppc_get_gpr(vcpu, 5), - kvmppc_get_gpr(vcpu, 6), - kvmppc_get_gpr(vcpu, 7)); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - break; case H_CEDE: break; case H_PROD: @@ -654,7 +681,10 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) ret = H_PARAMETER; break; } - kvm_vcpu_yield_to(tvcpu); + yield_count = kvmppc_get_gpr(vcpu, 5); + if (kvmppc_get_yield_count(tvcpu) != yield_count) + break; + kvm_arch_vcpu_yield_to(tvcpu); break; case H_REGISTER_VPA: ret = do_h_register_vpa(vcpu, kvmppc_get_gpr(vcpu, 4), @@ -769,6 +799,8 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, vcpu->stat.ext_intr_exits++; r = RESUME_GUEST; break; + /* HMI is hypervisor interrupt and host has handled it. Resume guest.*/ + case BOOK3S_INTERRUPT_HMI: case BOOK3S_INTERRUPT_PERFMON: r = RESUME_GUEST; break; @@ -837,6 +869,10 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, * Accordingly return to Guest or Host. */ case BOOK3S_INTERRUPT_H_EMUL_ASSIST: + if (vcpu->arch.emul_inst != KVM_INST_FETCH_FAILED) + vcpu->arch.last_inst = kvmppc_need_byteswap(vcpu) ? + swab32(vcpu->arch.emul_inst) : + vcpu->arch.emul_inst; if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) { r = kvmppc_emulate_debug_inst(run, vcpu); } else { @@ -1357,6 +1393,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core) INIT_LIST_HEAD(&vcore->runnable_threads); spin_lock_init(&vcore->lock); + spin_lock_init(&vcore->stoltb_lock); init_waitqueue_head(&vcore->wq); vcore->preempt_tb = TB_NIL; vcore->lpcr = kvm->arch.lpcr; @@ -1694,9 +1731,11 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc) vc->n_woken = 0; vc->nap_count = 0; vc->entry_exit_count = 0; + vc->preempt_tb = TB_NIL; vc->vcore_state = VCORE_STARTING; vc->in_guest = 0; vc->napping_threads = 0; + vc->conferring_threads = 0; /* * Updating any of the vpas requires calling kvmppc_pin_guest_page, @@ -1726,6 +1765,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc) list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) { kvmppc_start_thread(vcpu); kvmppc_create_dtl_entry(vcpu, vc); + trace_kvm_guest_enter(vcpu); } /* Set this explicitly in case thread 0 doesn't have a vcpu */ @@ -1734,6 +1774,9 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc) vc->vcore_state = VCORE_RUNNING; preempt_disable(); + + trace_kvmppc_run_core(vc, 0); + spin_unlock(&vc->lock); kvm_guest_enter(); @@ -1779,6 +1822,8 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc) kvmppc_core_pending_dec(vcpu)) kvmppc_core_dequeue_dec(vcpu); + trace_kvm_guest_exit(vcpu); + ret = RESUME_GUEST; if (vcpu->arch.trap) ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu, @@ -1804,6 +1849,8 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc) wake_up(&vcpu->arch.cpu_run); } } + + trace_kvmppc_run_core(vc, 1); } /* @@ -1826,15 +1873,37 @@ static void kvmppc_wait_for_exec(struct kvm_vcpu *vcpu, int wait_state) */ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) { + struct kvm_vcpu *vcpu; + int do_sleep = 1; + DEFINE_WAIT(wait); prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE); + + /* + * Check one last time for pending exceptions and ceded state after + * we put ourselves on the wait queue + */ + list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) { + if (vcpu->arch.pending_exceptions || !vcpu->arch.ceded) { + do_sleep = 0; + break; + } + } + + if (!do_sleep) { + finish_wait(&vc->wq, &wait); + return; + } + vc->vcore_state = VCORE_SLEEPING; + trace_kvmppc_vcore_blocked(vc, 0); spin_unlock(&vc->lock); schedule(); finish_wait(&vc->wq, &wait); spin_lock(&vc->lock); vc->vcore_state = VCORE_INACTIVE; + trace_kvmppc_vcore_blocked(vc, 1); } static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) @@ -1843,6 +1912,8 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) struct kvmppc_vcore *vc; struct kvm_vcpu *v, *vn; + trace_kvmppc_run_vcpu_enter(vcpu); + kvm_run->exit_reason = 0; vcpu->arch.ret = RESUME_GUEST; vcpu->arch.trap = 0; @@ -1872,6 +1943,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) VCORE_EXIT_COUNT(vc) == 0) { kvmppc_create_dtl_entry(vcpu, vc); kvmppc_start_thread(vcpu); + trace_kvm_guest_enter(vcpu); } else if (vc->vcore_state == VCORE_SLEEPING) { wake_up(&vc->wq); } @@ -1936,6 +2008,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) wake_up(&v->arch.cpu_run); } + trace_kvmppc_run_vcpu_exit(vcpu, kvm_run); spin_unlock(&vc->lock); return vcpu->arch.ret; } @@ -1962,7 +2035,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) /* Order vcpus_running vs. rma_setup_done, see kvmppc_alloc_reset_hpt */ smp_mb(); - /* On the first time here, set up HTAB and VRMA or RMA */ + /* On the first time here, set up HTAB and VRMA */ if (!vcpu->kvm->arch.rma_setup_done) { r = kvmppc_hv_setup_htab_rma(vcpu); if (r) @@ -1981,7 +2054,9 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) if (run->exit_reason == KVM_EXIT_PAPR_HCALL && !(vcpu->arch.shregs.msr & MSR_PR)) { + trace_kvm_hcall_enter(vcpu); r = kvmppc_pseries_do_hcall(vcpu); + trace_kvm_hcall_exit(vcpu, r); kvmppc_core_prepare_to_enter(vcpu); } else if (r == RESUME_PAGE_FAULT) { srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); @@ -1997,98 +2072,6 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) return r; } - -/* Work out RMLS (real mode limit selector) field value for a given RMA size. - Assumes POWER7 or PPC970. */ -static inline int lpcr_rmls(unsigned long rma_size) -{ - switch (rma_size) { - case 32ul << 20: /* 32 MB */ - if (cpu_has_feature(CPU_FTR_ARCH_206)) - return 8; /* only supported on POWER7 */ - return -1; - case 64ul << 20: /* 64 MB */ - return 3; - case 128ul << 20: /* 128 MB */ - return 7; - case 256ul << 20: /* 256 MB */ - return 4; - case 1ul << 30: /* 1 GB */ - return 2; - case 16ul << 30: /* 16 GB */ - return 1; - case 256ul << 30: /* 256 GB */ - return 0; - default: - return -1; - } -} - -static int kvm_rma_fault(struct vm_area_struct *vma, struct vm_fault *vmf) -{ - struct page *page; - struct kvm_rma_info *ri = vma->vm_file->private_data; - - if (vmf->pgoff >= kvm_rma_pages) - return VM_FAULT_SIGBUS; - - page = pfn_to_page(ri->base_pfn + vmf->pgoff); - get_page(page); - vmf->page = page; - return 0; -} - -static const struct vm_operations_struct kvm_rma_vm_ops = { - .fault = kvm_rma_fault, -}; - -static int kvm_rma_mmap(struct file *file, struct vm_area_struct *vma) -{ - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; - vma->vm_ops = &kvm_rma_vm_ops; - return 0; -} - -static int kvm_rma_release(struct inode *inode, struct file *filp) -{ - struct kvm_rma_info *ri = filp->private_data; - - kvm_release_rma(ri); - return 0; -} - -static const struct file_operations kvm_rma_fops = { - .mmap = kvm_rma_mmap, - .release = kvm_rma_release, -}; - -static long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, - struct kvm_allocate_rma *ret) -{ - long fd; - struct kvm_rma_info *ri; - /* - * Only do this on PPC970 in HV mode - */ - if (!cpu_has_feature(CPU_FTR_HVMODE) || - !cpu_has_feature(CPU_FTR_ARCH_201)) - return -EINVAL; - - if (!kvm_rma_pages) - return -EINVAL; - - ri = kvm_alloc_rma(); - if (!ri) - return -ENOMEM; - - fd = anon_inode_getfd("kvm-rma", &kvm_rma_fops, ri, O_RDWR | O_CLOEXEC); - if (fd < 0) - kvm_release_rma(ri); - - ret->rma_size = kvm_rma_pages << PAGE_SHIFT; - return fd; -} - static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps, int linux_psize) { @@ -2167,26 +2150,6 @@ out: return r; } -static void unpin_slot(struct kvm_memory_slot *memslot) -{ - unsigned long *physp; - unsigned long j, npages, pfn; - struct page *page; - - physp = memslot->arch.slot_phys; - npages = memslot->npages; - if (!physp) - return; - for (j = 0; j < npages; j++) { - if (!(physp[j] & KVMPPC_GOT_PAGE)) - continue; - pfn = physp[j] >> PAGE_SHIFT; - page = pfn_to_page(pfn); - SetPageDirty(page); - put_page(page); - } -} - static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { @@ -2194,11 +2157,6 @@ static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free, vfree(free->arch.rmap); free->arch.rmap = NULL; } - if (!dont || free->arch.slot_phys != dont->arch.slot_phys) { - unpin_slot(free); - vfree(free->arch.slot_phys); - free->arch.slot_phys = NULL; - } } static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot, @@ -2207,7 +2165,6 @@ static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot, slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap)); if (!slot->arch.rmap) return -ENOMEM; - slot->arch.slot_phys = NULL; return 0; } @@ -2216,17 +2173,6 @@ static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem) { - unsigned long *phys; - - /* Allocate a slot_phys array if needed */ - phys = memslot->arch.slot_phys; - if (!kvm->arch.using_mmu_notifiers && !phys && memslot->npages) { - phys = vzalloc(memslot->npages * sizeof(unsigned long)); - if (!phys) - return -ENOMEM; - memslot->arch.slot_phys = phys; - } - return 0; } @@ -2284,17 +2230,11 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) { int err = 0; struct kvm *kvm = vcpu->kvm; - struct kvm_rma_info *ri = NULL; unsigned long hva; struct kvm_memory_slot *memslot; struct vm_area_struct *vma; unsigned long lpcr = 0, senc; - unsigned long lpcr_mask = 0; unsigned long psize, porder; - unsigned long rma_size; - unsigned long rmls; - unsigned long *physp; - unsigned long i, npages; int srcu_idx; mutex_lock(&kvm->lock); @@ -2329,88 +2269,25 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) psize = vma_kernel_pagesize(vma); porder = __ilog2(psize); - /* Is this one of our preallocated RMAs? */ - if (vma->vm_file && vma->vm_file->f_op == &kvm_rma_fops && - hva == vma->vm_start) - ri = vma->vm_file->private_data; - up_read(¤t->mm->mmap_sem); - if (!ri) { - /* On POWER7, use VRMA; on PPC970, give up */ - err = -EPERM; - if (cpu_has_feature(CPU_FTR_ARCH_201)) { - pr_err("KVM: CPU requires an RMO\n"); - goto out_srcu; - } + /* We can handle 4k, 64k or 16M pages in the VRMA */ + err = -EINVAL; + if (!(psize == 0x1000 || psize == 0x10000 || + psize == 0x1000000)) + goto out_srcu; - /* We can handle 4k, 64k or 16M pages in the VRMA */ - err = -EINVAL; - if (!(psize == 0x1000 || psize == 0x10000 || - psize == 0x1000000)) - goto out_srcu; + /* Update VRMASD field in the LPCR */ + senc = slb_pgsize_encoding(psize); + kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T | + (VRMA_VSID << SLB_VSID_SHIFT_1T); + /* the -4 is to account for senc values starting at 0x10 */ + lpcr = senc << (LPCR_VRMASD_SH - 4); - /* Update VRMASD field in the LPCR */ - senc = slb_pgsize_encoding(psize); - kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T | - (VRMA_VSID << SLB_VSID_SHIFT_1T); - lpcr_mask = LPCR_VRMASD; - /* the -4 is to account for senc values starting at 0x10 */ - lpcr = senc << (LPCR_VRMASD_SH - 4); + /* Create HPTEs in the hash page table for the VRMA */ + kvmppc_map_vrma(vcpu, memslot, porder); - /* Create HPTEs in the hash page table for the VRMA */ - kvmppc_map_vrma(vcpu, memslot, porder); - - } else { - /* Set up to use an RMO region */ - rma_size = kvm_rma_pages; - if (rma_size > memslot->npages) - rma_size = memslot->npages; - rma_size <<= PAGE_SHIFT; - rmls = lpcr_rmls(rma_size); - err = -EINVAL; - if ((long)rmls < 0) { - pr_err("KVM: Can't use RMA of 0x%lx bytes\n", rma_size); - goto out_srcu; - } - atomic_inc(&ri->use_count); - kvm->arch.rma = ri; - - /* Update LPCR and RMOR */ - if (cpu_has_feature(CPU_FTR_ARCH_201)) { - /* PPC970; insert RMLS value (split field) in HID4 */ - lpcr_mask = (1ul << HID4_RMLS0_SH) | - (3ul << HID4_RMLS2_SH) | HID4_RMOR; - lpcr = ((rmls >> 2) << HID4_RMLS0_SH) | - ((rmls & 3) << HID4_RMLS2_SH); - /* RMOR is also in HID4 */ - lpcr |= ((ri->base_pfn >> (26 - PAGE_SHIFT)) & 0xffff) - << HID4_RMOR_SH; - } else { - /* POWER7 */ - lpcr_mask = LPCR_VPM0 | LPCR_VRMA_L | LPCR_RMLS; - lpcr = rmls << LPCR_RMLS_SH; - kvm->arch.rmor = ri->base_pfn << PAGE_SHIFT; - } - pr_info("KVM: Using RMO at %lx size %lx (LPCR = %lx)\n", - ri->base_pfn << PAGE_SHIFT, rma_size, lpcr); - - /* Initialize phys addrs of pages in RMO */ - npages = kvm_rma_pages; - porder = __ilog2(npages); - physp = memslot->arch.slot_phys; - if (physp) { - if (npages > memslot->npages) - npages = memslot->npages; - spin_lock(&kvm->arch.slot_phys_lock); - for (i = 0; i < npages; ++i) - physp[i] = ((ri->base_pfn + i) << PAGE_SHIFT) + - porder; - spin_unlock(&kvm->arch.slot_phys_lock); - } - } - - kvmppc_update_lpcr(kvm, lpcr, lpcr_mask); + kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD); /* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */ smp_wmb(); @@ -2449,35 +2326,21 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) memcpy(kvm->arch.enabled_hcalls, default_enabled_hcalls, sizeof(kvm->arch.enabled_hcalls)); - kvm->arch.rma = NULL; - kvm->arch.host_sdr1 = mfspr(SPRN_SDR1); - if (cpu_has_feature(CPU_FTR_ARCH_201)) { - /* PPC970; HID4 is effectively the LPCR */ - kvm->arch.host_lpid = 0; - kvm->arch.host_lpcr = lpcr = mfspr(SPRN_HID4); - lpcr &= ~((3 << HID4_LPID1_SH) | (0xful << HID4_LPID5_SH)); - lpcr |= ((lpid >> 4) << HID4_LPID1_SH) | - ((lpid & 0xf) << HID4_LPID5_SH); - } else { - /* POWER7; init LPCR for virtual RMA mode */ - kvm->arch.host_lpid = mfspr(SPRN_LPID); - kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR); - lpcr &= LPCR_PECE | LPCR_LPES; - lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE | - 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; - } + /* Init LPCR for virtual RMA mode */ + kvm->arch.host_lpid = mfspr(SPRN_LPID); + kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR); + lpcr &= LPCR_PECE | LPCR_LPES; + lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE | + 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; - kvm->arch.using_mmu_notifiers = !!cpu_has_feature(CPU_FTR_ARCH_206); - spin_lock_init(&kvm->arch.slot_phys_lock); - /* * Track that we now have a HV mode VM active. This blocks secondary * CPU threads from coming online. @@ -2507,10 +2370,6 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) kvm_hv_vm_deactivated(); kvmppc_free_vcores(kvm); - if (kvm->arch.rma) { - kvm_release_rma(kvm->arch.rma); - kvm->arch.rma = NULL; - } kvmppc_free_hpt(kvm); } @@ -2536,7 +2395,8 @@ static int kvmppc_core_emulate_mfspr_hv(struct kvm_vcpu *vcpu, int sprn, static int kvmppc_core_check_processor_compat_hv(void) { - if (!cpu_has_feature(CPU_FTR_HVMODE)) + if (!cpu_has_feature(CPU_FTR_HVMODE) || + !cpu_has_feature(CPU_FTR_ARCH_206)) return -EIO; return 0; } @@ -2550,16 +2410,6 @@ static long kvm_arch_vm_ioctl_hv(struct file *filp, switch (ioctl) { - case KVM_ALLOCATE_RMA: { - struct kvm_allocate_rma rma; - struct kvm *kvm = filp->private_data; - - r = kvm_vm_ioctl_allocate_rma(kvm, &rma); - if (r >= 0 && copy_to_user(argp, &rma, sizeof(rma))) - r = -EFAULT; - break; - } - case KVM_PPC_ALLOCATE_HTAB: { u32 htab_order; diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 3f1bb5a36c27..1f083ff8a61a 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -16,6 +16,7 @@ #include <linux/memblock.h> #include <linux/sizes.h> #include <linux/cma.h> +#include <linux/bitops.h> #include <asm/cputable.h> #include <asm/kvm_ppc.h> @@ -32,95 +33,9 @@ * By default we reserve 5% of memory for hash pagetable allocation. */ static unsigned long kvm_cma_resv_ratio = 5; -/* - * We allocate RMAs (real mode areas) for KVM guests from the KVM CMA area. - * Each RMA has to be physically contiguous and of a size that the - * hardware supports. PPC970 and POWER7 support 64MB, 128MB and 256MB, - * and other larger sizes. Since we are unlikely to be allocate that - * much physically contiguous memory after the system is up and running, - * we preallocate a set of RMAs in early boot using CMA. - * should be power of 2. - */ -unsigned long kvm_rma_pages = (1 << 27) >> PAGE_SHIFT; /* 128MB */ -EXPORT_SYMBOL_GPL(kvm_rma_pages); static struct cma *kvm_cma; -/* Work out RMLS (real mode limit selector) field value for a given RMA size. - Assumes POWER7 or PPC970. */ -static inline int lpcr_rmls(unsigned long rma_size) -{ - switch (rma_size) { - case 32ul << 20: /* 32 MB */ - if (cpu_has_feature(CPU_FTR_ARCH_206)) - return 8; /* only supported on POWER7 */ - return -1; - case 64ul << 20: /* 64 MB */ - return 3; - case 128ul << 20: /* 128 MB */ - return 7; - case 256ul << 20: /* 256 MB */ - return 4; - case 1ul << 30: /* 1 GB */ - return 2; - case 16ul << 30: /* 16 GB */ - return 1; - case 256ul << 30: /* 256 GB */ - return 0; - default: - return -1; - } -} - -static int __init early_parse_rma_size(char *p) -{ - unsigned long kvm_rma_size; - - pr_debug("%s(%s)\n", __func__, p); - if (!p) - return -EINVAL; - kvm_rma_size = memparse(p, &p); - /* - * Check that the requested size is one supported in hardware - */ - if (lpcr_rmls(kvm_rma_size) < 0) { - pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size); - return -EINVAL; - } - kvm_rma_pages = kvm_rma_size >> PAGE_SHIFT; - return 0; -} -early_param("kvm_rma_size", early_parse_rma_size); - -struct kvm_rma_info *kvm_alloc_rma() -{ - struct page *page; - struct kvm_rma_info *ri; - - ri = kmalloc(sizeof(struct kvm_rma_info), GFP_KERNEL); - if (!ri) - return NULL; - page = cma_alloc(kvm_cma, kvm_rma_pages, order_base_2(kvm_rma_pages)); - if (!page) - goto err_out; - atomic_set(&ri->use_count, 1); - ri->base_pfn = page_to_pfn(page); - return ri; -err_out: - kfree(ri); - return NULL; -} -EXPORT_SYMBOL_GPL(kvm_alloc_rma); - -void kvm_release_rma(struct kvm_rma_info *ri) -{ - if (atomic_dec_and_test(&ri->use_count)) { - cma_release(kvm_cma, pfn_to_page(ri->base_pfn), kvm_rma_pages); - kfree(ri); - } -} -EXPORT_SYMBOL_GPL(kvm_release_rma); - static int __init early_parse_kvm_cma_resv(char *p) { pr_debug("%s(%s)\n", __func__, p); @@ -132,14 +47,9 @@ early_param("kvm_cma_resv_ratio", early_parse_kvm_cma_resv); struct page *kvm_alloc_hpt(unsigned long nr_pages) { - unsigned long align_pages = HPT_ALIGN_PAGES; - VM_BUG_ON(order_base_2(nr_pages) < KVM_CMA_CHUNK_ORDER - PAGE_SHIFT); - /* Old CPUs require HPT aligned on a multiple of its size */ - if (!cpu_has_feature(CPU_FTR_ARCH_206)) - align_pages = nr_pages; - return cma_alloc(kvm_cma, nr_pages, order_base_2(align_pages)); + return cma_alloc(kvm_cma, nr_pages, order_base_2(HPT_ALIGN_PAGES)); } EXPORT_SYMBOL_GPL(kvm_alloc_hpt); @@ -180,22 +90,44 @@ void __init kvm_cma_reserve(void) if (selected_size) { pr_debug("%s: reserving %ld MiB for global area\n", __func__, (unsigned long)selected_size / SZ_1M); - /* - * Old CPUs require HPT aligned on a multiple of its size. So for them - * make the alignment as max size we could request. - */ - if (!cpu_has_feature(CPU_FTR_ARCH_206)) - align_size = __rounddown_pow_of_two(selected_size); - else - align_size = HPT_ALIGN_PAGES << PAGE_SHIFT; - - align_size = max(kvm_rma_pages << PAGE_SHIFT, align_size); + align_size = HPT_ALIGN_PAGES << PAGE_SHIFT; cma_declare_contiguous(0, selected_size, 0, align_size, KVM_CMA_CHUNK_ORDER - PAGE_SHIFT, false, &kvm_cma); } } /* + * Real-mode H_CONFER implementation. + * We check if we are the only vcpu out of this virtual core + * still running in the guest and not ceded. If so, we pop up + * to the virtual-mode implementation; if not, just return to + * the guest. + */ +long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target, + unsigned int yield_count) +{ + struct kvmppc_vcore *vc = vcpu->arch.vcore; + int threads_running; + int threads_ceded; + int threads_conferring; + u64 stop = get_tb() + 10 * tb_ticks_per_usec; + int rv = H_SUCCESS; /* => don't yield */ + + set_bit(vcpu->arch.ptid, &vc->conferring_threads); + while ((get_tb() < stop) && (VCORE_EXIT_COUNT(vc) == 0)) { + threads_running = VCORE_ENTRY_COUNT(vc); + threads_ceded = hweight32(vc->napping_threads); + threads_conferring = hweight32(vc->conferring_threads); + if (threads_ceded + threads_conferring >= threads_running) { + rv = H_TOO_HARD; /* => do yield */ + break; + } + } + clear_bit(vcpu->arch.ptid, &vc->conferring_threads); + return rv; +} + +/* * When running HV mode KVM we need to block certain operations while KVM VMs * exist in the system. We use a counter of VMs to track this. * diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S index 731be7478b27..36540a99d178 100644 --- a/arch/powerpc/kvm/book3s_hv_interrupts.S +++ b/arch/powerpc/kvm/book3s_hv_interrupts.S @@ -52,10 +52,8 @@ _GLOBAL(__kvmppc_vcore_entry) std r3, _CCR(r1) /* Save host DSCR */ -BEGIN_FTR_SECTION mfspr r3, SPRN_DSCR std r3, HSTATE_DSCR(r13) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) BEGIN_FTR_SECTION /* Save host DABR */ @@ -84,11 +82,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) mfspr r7, SPRN_MMCR0 /* save MMCR0 */ mtspr SPRN_MMCR0, r3 /* freeze all counters, disable interrupts */ mfspr r6, SPRN_MMCRA -BEGIN_FTR_SECTION - /* On P7, clear MMCRA in order to disable SDAR updates */ + /* Clear MMCRA in order to disable SDAR updates */ li r5, 0 mtspr SPRN_MMCRA, r5 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) isync ld r3, PACALPPACAPTR(r13) /* is the host using the PMU? */ lbz r5, LPPACA_PMCINUSE(r3) @@ -113,20 +109,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) mfspr r7, SPRN_PMC4 mfspr r8, SPRN_PMC5 mfspr r9, SPRN_PMC6 -BEGIN_FTR_SECTION - mfspr r10, SPRN_PMC7 - mfspr r11, SPRN_PMC8 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) stw r3, HSTATE_PMC(r13) stw r5, HSTATE_PMC + 4(r13) stw r6, HSTATE_PMC + 8(r13) stw r7, HSTATE_PMC + 12(r13) stw r8, HSTATE_PMC + 16(r13) stw r9, HSTATE_PMC + 20(r13) -BEGIN_FTR_SECTION - stw r10, HSTATE_PMC + 24(r13) - stw r11, HSTATE_PMC + 28(r13) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) 31: /* @@ -140,31 +128,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) add r8,r8,r7 std r8,HSTATE_DECEXP(r13) -#ifdef CONFIG_SMP - /* - * On PPC970, if the guest vcpu has an external interrupt pending, - * send ourselves an IPI so as to interrupt the guest once it - * enables interrupts. (It must have interrupts disabled, - * otherwise we would already have delivered the interrupt.) - * - * XXX If this is a UP build, smp_send_reschedule is not available, - * so the interrupt will be delayed until the next time the vcpu - * 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 - lhz r3, PACAPACAINDEX(r13) - bl smp_send_reschedule - nop -32: -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) -#endif /* CONFIG_SMP */ - /* Jump to partition switch code */ bl kvmppc_hv_entry_trampoline nop diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c index d562c8e2bc30..60081bd75847 100644 --- a/arch/powerpc/kvm/book3s_hv_ras.c +++ b/arch/powerpc/kvm/book3s_hv_ras.c @@ -138,8 +138,5 @@ out: long kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu) { - if (cpu_has_feature(CPU_FTR_ARCH_206)) - return kvmppc_realmode_mc_power7(vcpu); - - return 0; + return kvmppc_realmode_mc_power7(vcpu); } diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 084ad54c73cd..510bdfbc4073 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -45,16 +45,12 @@ static int global_invalidates(struct kvm *kvm, unsigned long flags) * as indicated by local_paca->kvm_hstate.kvm_vcpu being set, * we can use tlbiel as long as we mark all other physical * cores as potentially having stale TLB entries for this lpid. - * If we're not using MMU notifiers, we never take pages away - * from the guest, so we can use tlbiel if requested. * Otherwise, don't use tlbiel. */ if (kvm->arch.online_vcores == 1 && local_paca->kvm_hstate.kvm_vcpu) global = 0; - else if (kvm->arch.using_mmu_notifiers) - global = 1; else - global = !(flags & H_LOCAL); + global = 1; if (!global) { /* any other core might now have stale TLB entries... */ @@ -170,7 +166,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, struct revmap_entry *rev; unsigned long g_ptel; struct kvm_memory_slot *memslot; - unsigned long *physp, pte_size; + unsigned long pte_size; unsigned long is_io; unsigned long *rmap; pte_t pte; @@ -198,9 +194,6 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, is_io = ~0ul; rmap = NULL; if (!(memslot && !(memslot->flags & KVM_MEMSLOT_INVALID))) { - /* PPC970 can't do emulated MMIO */ - if (!cpu_has_feature(CPU_FTR_ARCH_206)) - return H_PARAMETER; /* Emulated MMIO - mark this with key=31 */ pteh |= HPTE_V_ABSENT; ptel |= HPTE_R_KEY_HI | HPTE_R_KEY_LO; @@ -213,37 +206,20 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, slot_fn = gfn - memslot->base_gfn; rmap = &memslot->arch.rmap[slot_fn]; - if (!kvm->arch.using_mmu_notifiers) { - physp = memslot->arch.slot_phys; - if (!physp) - return H_PARAMETER; - physp += slot_fn; - if (realmode) - physp = real_vmalloc_addr(physp); - pa = *physp; - if (!pa) - return H_TOO_HARD; - is_io = pa & (HPTE_R_I | HPTE_R_W); - pte_size = PAGE_SIZE << (pa & KVMPPC_PAGE_ORDER_MASK); - pa &= PAGE_MASK; + /* 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_and_update(pgdir, hva, writing, &pte_size); + if (pte_present(pte) && !pte_numa(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; - } 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_and_update(pgdir, hva, writing, - &pte_size); - if (pte_present(pte) && !pte_numa(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) @@ -337,8 +313,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, rmap = real_vmalloc_addr(rmap); lock_rmap(rmap); /* Check for pending invalidations under the rmap chain lock */ - if (kvm->arch.using_mmu_notifiers && - mmu_notifier_retry(kvm, mmu_seq)) { + if (mmu_notifier_retry(kvm, mmu_seq)) { /* inval in progress, write a non-present HPTE */ pteh |= HPTE_V_ABSENT; pteh &= ~HPTE_V_VALID; @@ -395,61 +370,11 @@ static inline int try_lock_tlbie(unsigned int *lock) return old == 0; } -/* - * tlbie/tlbiel is a bit different on the PPC970 compared to later - * processors such as POWER7; the large page bit is in the instruction - * not RB, and the top 16 bits and the bottom 12 bits of the VA - * in RB must be 0. - */ -static void do_tlbies_970(struct kvm *kvm, unsigned long *rbvalues, - long npages, int global, bool need_sync) -{ - long i; - - if (global) { - while (!try_lock_tlbie(&kvm->arch.tlbie_lock)) - cpu_relax(); - if (need_sync) - asm volatile("ptesync" : : : "memory"); - for (i = 0; i < npages; ++i) { - unsigned long rb = rbvalues[i]; - - if (rb & 1) /* large page */ - asm volatile("tlbie %0,1" : : - "r" (rb & 0x0000fffffffff000ul)); - else - asm volatile("tlbie %0,0" : : - "r" (rb & 0x0000fffffffff000ul)); - } - asm volatile("eieio; tlbsync; ptesync" : : : "memory"); - kvm->arch.tlbie_lock = 0; - } else { - if (need_sync) - asm volatile("ptesync" : : : "memory"); - for (i = 0; i < npages; ++i) { - unsigned long rb = rbvalues[i]; - - if (rb & 1) /* large page */ - asm volatile("tlbiel %0,1" : : - "r" (rb & 0x0000fffffffff000ul)); - else - asm volatile("tlbiel %0,0" : : - "r" (rb & 0x0000fffffffff000ul)); - } - asm volatile("ptesync" : : : "memory"); - } -} - static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues, long npages, int global, bool need_sync) { long i; - if (cpu_has_feature(CPU_FTR_ARCH_201)) { - /* PPC970 tlbie instruction is a bit different */ - do_tlbies_970(kvm, rbvalues, npages, global, need_sync); - return; - } if (global) { while (!try_lock_tlbie(&kvm->arch.tlbie_lock)) cpu_relax(); @@ -667,40 +592,29 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, rev->guest_rpte = r; note_hpte_modification(kvm, rev); } - r = (be64_to_cpu(hpte[1]) & ~mask) | bits; /* Update HPTE */ if (v & HPTE_V_VALID) { - rb = compute_tlbie_rb(v, r, pte_index); - hpte[0] = cpu_to_be64(v & ~HPTE_V_VALID); - do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true); /* - * If the host has this page as readonly but the guest - * wants to make it read/write, reduce the permissions. - * Checking the host permissions involves finding the - * memslot and then the Linux PTE for the page. + * If the page is valid, don't let it transition from + * readonly to writable. If it should be writable, we'll + * take a trap and let the page fault code sort it out. */ - if (hpte_is_writable(r) && kvm->arch.using_mmu_notifiers) { - unsigned long psize, gfn, hva; - struct kvm_memory_slot *memslot; - pgd_t *pgdir = vcpu->arch.pgdir; - pte_t pte; - - psize = hpte_page_size(v, r); - gfn = ((r & HPTE_R_RPN) & ~(psize - 1)) >> PAGE_SHIFT; - memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn); - if (memslot) { - hva = __gfn_to_hva_memslot(memslot, gfn); - pte = lookup_linux_pte_and_update(pgdir, hva, - 1, &psize); - if (pte_present(pte) && !pte_write(pte)) - r = hpte_make_readonly(r); - } + pte = be64_to_cpu(hpte[1]); + r = (pte & ~mask) | bits; + if (hpte_is_writable(r) && !hpte_is_writable(pte)) + r = hpte_make_readonly(r); + /* If the PTE is changing, invalidate it first */ + if (r != pte) { + rb = compute_tlbie_rb(v, r, pte_index); + hpte[0] = cpu_to_be64((v & ~HPTE_V_VALID) | + HPTE_V_ABSENT); + do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), + true); + hpte[1] = cpu_to_be64(r); } } - hpte[1] = cpu_to_be64(r); - eieio(); - hpte[0] = cpu_to_be64(v & ~HPTE_V_HVLOCK); + unlock_hpte(hpte, v & ~HPTE_V_HVLOCK); asm volatile("ptesync" : : : "memory"); return H_SUCCESS; } diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c index 3ee38e6e884f..7b066f6b02ad 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_xics.c +++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -183,8 +183,10 @@ static void icp_rm_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp, * state update in HW (ie bus transactions) so we can handle them * separately here as well. */ - if (resend) + if (resend) { icp->rm_action |= XICS_RM_CHECK_RESEND; + icp->rm_resend_icp = icp; + } } @@ -254,10 +256,25 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, * nothing needs to be done as there can be no XISR to * reject. * + * ICP state: Check_IPI + * * If the CPPR is less favored, then we might be replacing - * an interrupt, and thus need to possibly reject it as in + * an interrupt, and thus need to possibly reject it. * - * ICP state: Check_IPI + * ICP State: IPI + * + * Besides rejecting any pending interrupts, we also + * update XISR and pending_pri to mark IPI as pending. + * + * PAPR does not describe this state, but if the MFRR is being + * made less favored than its earlier value, there might be + * a previously-rejected interrupt needing to be resent. + * Ideally, we would want to resend only if + * prio(pending_interrupt) < mfrr && + * prio(pending_interrupt) < cppr + * where pending interrupt is the one that was rejected. But + * we don't have that state, so we simply trigger a resend + * whenever the MFRR is made less favored. */ do { old_state = new_state = ACCESS_ONCE(icp->state); @@ -270,13 +287,14 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, resend = false; if (mfrr < new_state.cppr) { /* Reject a pending interrupt if not an IPI */ - if (mfrr <= new_state.pending_pri) + if (mfrr <= new_state.pending_pri) { reject = new_state.xisr; - new_state.pending_pri = mfrr; - new_state.xisr = XICS_IPI; + new_state.pending_pri = mfrr; + new_state.xisr = XICS_IPI; + } } - if (mfrr > old_state.mfrr && mfrr > new_state.cppr) { + if (mfrr > old_state.mfrr) { resend = new_state.need_resend; new_state.need_resend = 0; } @@ -289,8 +307,10 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, } /* Pass resends to virtual mode */ - if (resend) + if (resend) { this_icp->rm_action |= XICS_RM_CHECK_RESEND; + this_icp->rm_resend_icp = icp; + } return check_too_hard(xics, this_icp); } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 65c105b17a25..10554df13852 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -94,20 +94,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG) lwz r6, HSTATE_PMC + 12(r13) lwz r8, HSTATE_PMC + 16(r13) lwz r9, HSTATE_PMC + 20(r13) -BEGIN_FTR_SECTION - lwz r10, HSTATE_PMC + 24(r13) - lwz r11, HSTATE_PMC + 28(r13) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) mtspr SPRN_PMC1, r3 mtspr SPRN_PMC2, r4 mtspr SPRN_PMC3, r5 mtspr SPRN_PMC4, r6 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, HSTATE_MMCR(r13) ld r4, HSTATE_MMCR + 8(r13) ld r5, HSTATE_MMCR + 16(r13) @@ -153,11 +145,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) cmpwi cr1, r12, BOOK3S_INTERRUPT_MACHINE_CHECK cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL -BEGIN_FTR_SECTION beq 11f cmpwi cr2, r12, BOOK3S_INTERRUPT_HMI beq cr2, 14f /* HMI check */ -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) /* RFI into the highmem handler, or branch to interrupt handler */ mfmsr r6 @@ -166,7 +156,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) mtmsrd r6, 1 /* Clear RI in MSR */ mtsrr0 r8 mtsrr1 r7 - beqa 0x500 /* external interrupt (PPC970) */ beq cr1, 13f /* machine check */ RFI @@ -393,11 +382,8 @@ kvmppc_hv_entry: slbia ptesync -BEGIN_FTR_SECTION - b 30f -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) /* - * POWER7 host -> guest partition switch code. + * POWER7/POWER8 host -> guest partition switch code. * We don't have to lock against concurrent tlbies, * but we do have to coordinate across hardware threads. */ @@ -505,97 +491,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) cmpwi r3,512 /* 1 microsecond */ li r12,BOOK3S_INTERRUPT_HV_DECREMENTER blt hdec_soon - b 31f - - /* - * PPC970 host -> guest partition switch code. - * We have to lock against concurrent tlbies, - * using native_tlbie_lock to lock against host tlbies - * and kvm->arch.tlbie_lock to lock against guest tlbies. - * We also have to invalidate the TLB since its - * entries aren't tagged with the LPID. - */ -30: ld r5,HSTATE_KVM_VCORE(r13) - ld r9,VCORE_KVM(r5) /* pointer to struct kvm */ - - /* first take native_tlbie_lock */ - .section ".toc","aw" -toc_tlbie_lock: - .tc native_tlbie_lock[TC],native_tlbie_lock - .previous - ld r3,toc_tlbie_lock@toc(r2) -#ifdef __BIG_ENDIAN__ - lwz r8,PACA_LOCK_TOKEN(r13) -#else - lwz r8,PACAPACAINDEX(r13) -#endif -24: lwarx r0,0,r3 - cmpwi r0,0 - bne 24b - stwcx. r8,0,r3 - bne 24b - isync - - ld r5,HSTATE_KVM_VCORE(r13) - ld r7,VCORE_LPCR(r5) /* use vcore->lpcr to store HID4 */ - li r0,0x18f - rotldi r0,r0,HID4_LPID5_SH /* all lpid bits in HID4 = 1 */ - or r0,r7,r0 - ptesync - sync - mtspr SPRN_HID4,r0 /* switch to reserved LPID */ - isync - li r0,0 - stw r0,0(r3) /* drop native_tlbie_lock */ - - /* invalidate the whole TLB */ - li r0,256 - mtctr r0 - li r6,0 -25: tlbiel r6 - addi r6,r6,0x1000 - bdnz 25b - ptesync - /* Take the guest's tlbie_lock */ - addi r3,r9,KVM_TLBIE_LOCK -24: lwarx r0,0,r3 - cmpwi r0,0 - bne 24b - stwcx. r8,0,r3 - bne 24b - isync - ld r6,KVM_SDR1(r9) - mtspr SPRN_SDR1,r6 /* switch to partition page table */ - - /* Set up HID4 with the guest's LPID etc. */ - sync - mtspr SPRN_HID4,r7 - isync - - /* drop the guest's tlbie_lock */ - li r0,0 - stw r0,0(r3) - - /* Check if HDEC expires soon */ - mfspr r3,SPRN_HDEC - cmpwi r3,10 - li r12,BOOK3S_INTERRUPT_HV_DECREMENTER - blt hdec_soon - - /* Enable HDEC interrupts */ - mfspr r0,SPRN_HID0 - li r3,1 - rldimi r0,r3, HID0_HDICE_SH, 64-HID0_HDICE_SH-1 - sync - mtspr SPRN_HID0,r0 - mfspr r0,SPRN_HID0 - mfspr r0,SPRN_HID0 - mfspr r0,SPRN_HID0 - 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 @@ -625,7 +521,6 @@ kvmppc_got_guest: stb r6, VCPU_VPA_DIRTY(r4) 25: -BEGIN_FTR_SECTION /* Save purr/spurr */ mfspr r5,SPRN_PURR mfspr r6,SPRN_SPURR @@ -635,7 +530,6 @@ BEGIN_FTR_SECTION 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 */ @@ -644,9 +538,7 @@ BEGIN_FTR_SECTION 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) #ifdef CONFIG_PPC_TRANSACTIONAL_MEM @@ -777,20 +669,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG) 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) @@ -837,14 +721,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) 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 */ + /* Skip next section on POWER7 */ b 8f END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) /* Turn on TM so we can access TFHAR/TFIAR/TEXASR */ @@ -920,7 +802,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) 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) @@ -928,7 +809,6 @@ BEGIN_FTR_SECTION 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) @@ -963,13 +843,11 @@ deliver_guest_interrupt: 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 /* 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 bne cr1, 12f @@ -1124,15 +1002,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) stw r12,VCPU_TRAP(r9) - /* Save HEIR (HV emulation assist reg) in last_inst + /* Save HEIR (HV emulation assist reg) in emul_inst if this is an HEI (HV emulation interrupt, e40) */ li r3,KVM_INST_FETCH_FAILED -BEGIN_FTR_SECTION cmpwi r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST bne 11f mfspr r3,SPRN_HEIR -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) -11: stw r3,VCPU_LAST_INST(r9) +11: stw r3,VCPU_HEIR(r9) /* these are volatile across C function calls */ mfctr r3 @@ -1140,13 +1016,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) std r3, VCPU_CTR(r9) stw r4, VCPU_XER(r9) -BEGIN_FTR_SECTION /* If this is a page table miss then see if it's theirs or ours */ cmpwi r12, BOOK3S_INTERRUPT_H_DATA_STORAGE beq kvmppc_hdsi cmpwi r12, BOOK3S_INTERRUPT_H_INST_STORAGE beq kvmppc_hisi -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) /* See if this is a leftover HDEC interrupt */ cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER @@ -1159,11 +1033,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) cmpwi r12,BOOK3S_INTERRUPT_SYSCALL beq hcall_try_real_mode - /* Only handle external interrupts here on arch 206 and later */ -BEGIN_FTR_SECTION - b ext_interrupt_to_host -END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) - /* External interrupt ? */ cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL bne+ ext_interrupt_to_host @@ -1193,11 +1062,9 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ mfdsisr r7 std r6, VCPU_DAR(r9) stw r7, VCPU_DSISR(r9) -BEGIN_FTR_SECTION /* don't overwrite fault_dar/fault_dsisr if HDSI */ cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE beq 6f -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) std r6, VCPU_FAULT_DAR(r9) stw r7, VCPU_FAULT_DSISR(r9) @@ -1236,7 +1103,6 @@ mc_cont: /* * Save the guest PURR/SPURR */ -BEGIN_FTR_SECTION mfspr r5,SPRN_PURR mfspr r6,SPRN_SPURR ld r7,VCPU_PURR(r9) @@ -1256,7 +1122,6 @@ BEGIN_FTR_SECTION 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 @@ -1306,22 +1171,18 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) 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) @@ -1503,11 +1364,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) 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 */ + /* 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) @@ -1532,10 +1391,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) 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) @@ -1543,10 +1398,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) 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 r5, SPRN_SIER mfspr r6, SPRN_SPMC1 mfspr r7, SPRN_SPMC2 @@ -1566,11 +1417,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) ptesync hdec_soon: /* r12 = trap, r13 = paca */ -BEGIN_FTR_SECTION - b 32f -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) /* - * POWER7 guest -> host partition switch code. + * POWER7/POWER8 guest -> host partition switch code. * We don't have to lock against tlbies but we do * have to coordinate the hardware threads. */ @@ -1698,87 +1546,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) 16: ld r8,KVM_HOST_LPCR(r4) mtspr SPRN_LPCR,r8 isync - b 33f - - /* - * PPC970 guest -> host partition switch code. - * We have to lock against concurrent tlbies, and - * we have to flush the whole TLB. - */ -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__ - lwz r8,PACA_LOCK_TOKEN(r13) -#else - lwz r8,PACAPACAINDEX(r13) -#endif - addi r3,r4,KVM_TLBIE_LOCK -24: lwarx r0,0,r3 - cmpwi r0,0 - bne 24b - stwcx. r8,0,r3 - bne 24b - isync - - ld r7,KVM_HOST_LPCR(r4) /* use kvm->arch.host_lpcr for HID4 */ - li r0,0x18f - rotldi r0,r0,HID4_LPID5_SH /* all lpid bits in HID4 = 1 */ - or r0,r7,r0 - ptesync - sync - mtspr SPRN_HID4,r0 /* switch to reserved LPID */ - isync - li r0,0 - stw r0,0(r3) /* drop guest tlbie_lock */ - - /* invalidate the whole TLB */ - li r0,256 - mtctr r0 - li r6,0 -25: tlbiel r6 - addi r6,r6,0x1000 - bdnz 25b - ptesync - - /* take native_tlbie_lock */ - ld r3,toc_tlbie_lock@toc(2) -24: lwarx r0,0,r3 - cmpwi r0,0 - bne 24b - stwcx. r8,0,r3 - bne 24b - isync - - ld r6,KVM_HOST_SDR1(r4) - mtspr SPRN_SDR1,r6 /* switch to host page table */ - - /* Set up host HID4 value */ - sync - mtspr SPRN_HID4,r7 - isync - li r0,0 - stw r0,0(r3) /* drop native_tlbie_lock */ - - lis r8,0x7fff /* MAX_INT@h */ - mtspr SPRN_HDEC,r8 - - /* Disable HDEC interrupts */ - mfspr r0,SPRN_HID0 - li r3,0 - rldimi r0,r3, HID0_HDICE_SH, 64-HID0_HDICE_SH-1 - sync - mtspr SPRN_HID0,r0 - mfspr r0,SPRN_HID0 - mfspr r0,SPRN_HID0 - mfspr r0,SPRN_HID0 - mfspr r0,SPRN_HID0 - mfspr r0,SPRN_HID0 - mfspr r0,SPRN_HID0 /* load host SLB entries */ -33: ld r8,PACA_SLBSHADOWPTR(r13) + ld r8,PACA_SLBSHADOWPTR(r13) .rept SLB_NUM_BOLTED li r3, SLBSHADOW_SAVEAREA @@ -2047,7 +1817,7 @@ hcall_real_table: .long 0 /* 0xd8 */ .long 0 /* 0xdc */ .long DOTSYM(kvmppc_h_cede) - hcall_real_table - .long 0 /* 0xe4 */ + .long DOTSYM(kvmppc_rm_h_confer) - hcall_real_table .long 0 /* 0xe8 */ .long 0 /* 0xec */ .long 0 /* 0xf0 */ @@ -2126,9 +1896,6 @@ _GLOBAL(kvmppc_h_cede) stw r0,VCPU_TRAP(r3) li r0,H_SUCCESS std r0,VCPU_GPR(R3)(r3) -BEGIN_FTR_SECTION - b kvm_cede_exit /* just send it up to host on 970 */ -END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) /* * Set our bit in the bitmask of napping threads unless all the @@ -2455,7 +2222,6 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_VSX) #endif mtmsrd r8 - isync addi r3,r3,VCPU_FPRS bl store_fp_state #ifdef CONFIG_ALTIVEC @@ -2491,7 +2257,6 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_VSX) #endif mtmsrd r8 - isync addi r3,r4,VCPU_FPRS bl load_fp_state #ifdef CONFIG_ALTIVEC diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c index bfb8035314e3..bd6ab1672ae6 100644 --- a/arch/powerpc/kvm/book3s_paired_singles.c +++ b/arch/powerpc/kvm/book3s_paired_singles.c @@ -352,14 +352,6 @@ static inline u32 inst_get_field(u32 inst, int msb, int lsb) return kvmppc_get_field(inst, msb + 32, lsb + 32); } -/* - * Replaces inst bits with ordering according to spec. - */ -static inline u32 inst_set_field(u32 inst, int msb, int lsb, int value) -{ - return kvmppc_set_field(inst, msb + 32, lsb + 32, value); -} - bool kvmppc_inst_is_paired_single(struct kvm_vcpu *vcpu, u32 inst) { if (!(vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)) diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index cf2eb16846d1..f57383941d03 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -644,11 +644,6 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, return r; } -static inline int get_fpr_index(int i) -{ - return i * TS_FPRWIDTH; -} - /* Give up external provider (FPU, Altivec, VSX) */ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr) { diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index eaeb78047fb8..807351f76f84 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -613,10 +613,25 @@ static noinline int kvmppc_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, * there might be a previously-rejected interrupt needing * to be resent. * + * ICP state: Check_IPI + * * If the CPPR is less favored, then we might be replacing - * an interrupt, and thus need to possibly reject it as in + * an interrupt, and thus need to possibly reject it. * - * ICP state: Check_IPI + * ICP State: IPI + * + * Besides rejecting any pending interrupts, we also + * update XISR and pending_pri to mark IPI as pending. + * + * PAPR does not describe this state, but if the MFRR is being + * made less favored than its earlier value, there might be + * a previously-rejected interrupt needing to be resent. + * Ideally, we would want to resend only if + * prio(pending_interrupt) < mfrr && + * prio(pending_interrupt) < cppr + * where pending interrupt is the one that was rejected. But + * we don't have that state, so we simply trigger a resend + * whenever the MFRR is made less favored. */ do { old_state = new_state = ACCESS_ONCE(icp->state); @@ -629,13 +644,14 @@ static noinline int kvmppc_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, resend = false; if (mfrr < new_state.cppr) { /* Reject a pending interrupt if not an IPI */ - if (mfrr <= new_state.pending_pri) + if (mfrr <= new_state.pending_pri) { reject = new_state.xisr; - new_state.pending_pri = mfrr; - new_state.xisr = XICS_IPI; + new_state.pending_pri = mfrr; + new_state.xisr = XICS_IPI; + } } - if (mfrr > old_state.mfrr && mfrr > new_state.cppr) { + if (mfrr > old_state.mfrr) { resend = new_state.need_resend; new_state.need_resend = 0; } @@ -789,7 +805,7 @@ static noinline int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall) if (icp->rm_action & XICS_RM_KICK_VCPU) kvmppc_fast_vcpu_kick(icp->rm_kick_target); if (icp->rm_action & XICS_RM_CHECK_RESEND) - icp_check_resend(xics, icp); + icp_check_resend(xics, icp->rm_resend_icp); if (icp->rm_action & XICS_RM_REJECT) icp_deliver_irq(xics, icp, icp->rm_reject); if (icp->rm_action & XICS_RM_NOTIFY_EOI) diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h index e8aaa7a3f209..73f0f2723c07 100644 --- a/arch/powerpc/kvm/book3s_xics.h +++ b/arch/powerpc/kvm/book3s_xics.h @@ -74,6 +74,7 @@ struct kvmppc_icp { #define XICS_RM_NOTIFY_EOI 0x8 u32 rm_action; struct kvm_vcpu *rm_kick_target; + struct kvmppc_icp *rm_resend_icp; u32 rm_reject; u32 rm_eoied_irq; diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index 16095841afe1..b29ce752c7d6 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -78,7 +78,7 @@ static inline int local_sid_setup_one(struct id *entry) sid = __this_cpu_inc_return(pcpu_last_used_sid); if (sid < NUM_TIDS) { - __this_cpu_write(pcpu_sids)entry[sid], entry); + __this_cpu_write(pcpu_sids.entry[sid], entry); entry->val = sid; entry->pentry = this_cpu_ptr(&pcpu_sids.entry[sid]); ret = sid; @@ -299,14 +299,6 @@ void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr) kvmppc_e500_recalc_shadow_pid(to_e500(vcpu)); } -void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu) -{ -} - -void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu) -{ -} - static void kvmppc_core_vcpu_load_e500(struct kvm_vcpu *vcpu, int cpu) { kvmppc_booke_vcpu_load(vcpu, cpu); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index c1f8f53cd312..c45eaab752b0 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -527,18 +527,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 0; break; case KVM_CAP_PPC_RMA: - r = hv_enabled; - /* PPC970 requires an RMA */ - if (r && cpu_has_feature(CPU_FTR_ARCH_201)) - r = 2; + r = 0; break; #endif case KVM_CAP_SYNC_MMU: #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE - if (hv_enabled) - r = cpu_has_feature(CPU_FTR_ARCH_206) ? 1 : 0; - else - r = 0; + r = hv_enabled; #elif defined(KVM_ARCH_WANT_MMU_NOTIFIER) r = 1; #else diff --git a/arch/powerpc/kvm/trace_book3s.h b/arch/powerpc/kvm/trace_book3s.h new file mode 100644 index 000000000000..f647ce0f428b --- /dev/null +++ b/arch/powerpc/kvm/trace_book3s.h @@ -0,0 +1,32 @@ +#if !defined(_TRACE_KVM_BOOK3S_H) +#define _TRACE_KVM_BOOK3S_H + +/* + * Common defines used by the trace macros in trace_pr.h and trace_hv.h + */ + +#define kvm_trace_symbol_exit \ + {0x100, "SYSTEM_RESET"}, \ + {0x200, "MACHINE_CHECK"}, \ + {0x300, "DATA_STORAGE"}, \ + {0x380, "DATA_SEGMENT"}, \ + {0x400, "INST_STORAGE"}, \ + {0x480, "INST_SEGMENT"}, \ + {0x500, "EXTERNAL"}, \ + {0x501, "EXTERNAL_LEVEL"}, \ + {0x502, "EXTERNAL_HV"}, \ + {0x600, "ALIGNMENT"}, \ + {0x700, "PROGRAM"}, \ + {0x800, "FP_UNAVAIL"}, \ + {0x900, "DECREMENTER"}, \ + {0x980, "HV_DECREMENTER"}, \ + {0xc00, "SYSCALL"}, \ + {0xd00, "TRACE"}, \ + {0xe00, "H_DATA_STORAGE"}, \ + {0xe20, "H_INST_STORAGE"}, \ + {0xe40, "H_EMUL_ASSIST"}, \ + {0xf00, "PERFMON"}, \ + {0xf20, "ALTIVEC"}, \ + {0xf40, "VSX"} + +#endif diff --git a/arch/powerpc/kvm/trace_booke.h b/arch/powerpc/kvm/trace_booke.h index f7537cf26ce7..7ec534d1db9f 100644 --- a/arch/powerpc/kvm/trace_booke.h +++ b/arch/powerpc/kvm/trace_booke.h @@ -151,6 +151,47 @@ TRACE_EVENT(kvm_booke206_ref_release, __entry->pfn, __entry->flags) ); +#ifdef CONFIG_SPE_POSSIBLE +#define kvm_trace_symbol_irqprio_spe \ + {BOOKE_IRQPRIO_SPE_UNAVAIL, "SPE_UNAVAIL"}, \ + {BOOKE_IRQPRIO_SPE_FP_DATA, "SPE_FP_DATA"}, \ + {BOOKE_IRQPRIO_SPE_FP_ROUND, "SPE_FP_ROUND"}, +#else +#define kvm_trace_symbol_irqprio_spe +#endif + +#ifdef CONFIG_PPC_E500MC +#define kvm_trace_symbol_irqprio_e500mc \ + {BOOKE_IRQPRIO_ALTIVEC_UNAVAIL, "ALTIVEC_UNAVAIL"}, \ + {BOOKE_IRQPRIO_ALTIVEC_ASSIST, "ALTIVEC_ASSIST"}, +#else +#define kvm_trace_symbol_irqprio_e500mc +#endif + +#define kvm_trace_symbol_irqprio \ + kvm_trace_symbol_irqprio_spe \ + kvm_trace_symbol_irqprio_e500mc \ + {BOOKE_IRQPRIO_DATA_STORAGE, "DATA_STORAGE"}, \ + {BOOKE_IRQPRIO_INST_STORAGE, "INST_STORAGE"}, \ + {BOOKE_IRQPRIO_ALIGNMENT, "ALIGNMENT"}, \ + {BOOKE_IRQPRIO_PROGRAM, "PROGRAM"}, \ + {BOOKE_IRQPRIO_FP_UNAVAIL, "FP_UNAVAIL"}, \ + {BOOKE_IRQPRIO_SYSCALL, "SYSCALL"}, \ + {BOOKE_IRQPRIO_AP_UNAVAIL, "AP_UNAVAIL"}, \ + {BOOKE_IRQPRIO_DTLB_MISS, "DTLB_MISS"}, \ + {BOOKE_IRQPRIO_ITLB_MISS, "ITLB_MISS"}, \ + {BOOKE_IRQPRIO_MACHINE_CHECK, "MACHINE_CHECK"}, \ + {BOOKE_IRQPRIO_DEBUG, "DEBUG"}, \ + {BOOKE_IRQPRIO_CRITICAL, "CRITICAL"}, \ + {BOOKE_IRQPRIO_WATCHDOG, "WATCHDOG"}, \ + {BOOKE_IRQPRIO_EXTERNAL, "EXTERNAL"}, \ + {BOOKE_IRQPRIO_FIT, "FIT"}, \ + {BOOKE_IRQPRIO_DECREMENTER, "DECREMENTER"}, \ + {BOOKE_IRQPRIO_PERFORMANCE_MONITOR, "PERFORMANCE_MONITOR"}, \ + {BOOKE_IRQPRIO_EXTERNAL_LEVEL, "EXTERNAL_LEVEL"}, \ + {BOOKE_IRQPRIO_DBELL, "DBELL"}, \ + {BOOKE_IRQPRIO_DBELL_CRIT, "DBELL_CRIT"} \ + TRACE_EVENT(kvm_booke_queue_irqprio, TP_PROTO(struct kvm_vcpu *vcpu, unsigned int priority), TP_ARGS(vcpu, priority), @@ -167,8 +208,10 @@ TRACE_EVENT(kvm_booke_queue_irqprio, __entry->pending = vcpu->arch.pending_exceptions; ), - TP_printk("vcpu=%x prio=%x pending=%lx", - __entry->cpu_nr, __entry->priority, __entry->pending) + TP_printk("vcpu=%x prio=%s pending=%lx", + __entry->cpu_nr, + __print_symbolic(__entry->priority, kvm_trace_symbol_irqprio), + __entry->pending) ); #endif diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h new file mode 100644 index 000000000000..33d9daff5783 --- /dev/null +++ b/arch/powerpc/kvm/trace_hv.h @@ -0,0 +1,477 @@ +#if !defined(_TRACE_KVM_HV_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_KVM_HV_H + +#include <linux/tracepoint.h> +#include "trace_book3s.h" +#include <asm/hvcall.h> +#include <asm/kvm_asm.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kvm_hv +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace_hv + +#define kvm_trace_symbol_hcall \ + {H_REMOVE, "H_REMOVE"}, \ + {H_ENTER, "H_ENTER"}, \ + {H_READ, "H_READ"}, \ + {H_CLEAR_MOD, "H_CLEAR_MOD"}, \ + {H_CLEAR_REF, "H_CLEAR_REF"}, \ + {H_PROTECT, "H_PROTECT"}, \ + {H_GET_TCE, "H_GET_TCE"}, \ + {H_PUT_TCE, "H_PUT_TCE"}, \ + {H_SET_SPRG0, "H_SET_SPRG0"}, \ + {H_SET_DABR, "H_SET_DABR"}, \ + {H_PAGE_INIT, "H_PAGE_INIT"}, \ + {H_SET_ASR, "H_SET_ASR"}, \ + {H_ASR_ON, "H_ASR_ON"}, \ + {H_ASR_OFF, "H_ASR_OFF"}, \ + {H_LOGICAL_CI_LOAD, "H_LOGICAL_CI_LOAD"}, \ + {H_LOGICAL_CI_STORE, "H_LOGICAL_CI_STORE"}, \ + {H_LOGICAL_CACHE_LOAD, "H_LOGICAL_CACHE_LOAD"}, \ + {H_LOGICAL_CACHE_STORE, "H_LOGICAL_CACHE_STORE"}, \ + {H_LOGICAL_ICBI, "H_LOGICAL_ICBI"}, \ + {H_LOGICAL_DCBF, "H_LOGICAL_DCBF"}, \ + {H_GET_TERM_CHAR, "H_GET_TERM_CHAR"}, \ + {H_PUT_TERM_CHAR, "H_PUT_TERM_CHAR"}, \ + {H_REAL_TO_LOGICAL, "H_REAL_TO_LOGICAL"}, \ + {H_HYPERVISOR_DATA, "H_HYPERVISOR_DATA"}, \ + {H_EOI, "H_EOI"}, \ + {H_CPPR, "H_CPPR"}, \ + {H_IPI, "H_IPI"}, \ + {H_IPOLL, "H_IPOLL"}, \ + {H_XIRR, "H_XIRR"}, \ + {H_PERFMON, "H_PERFMON"}, \ + {H_MIGRATE_DMA, "H_MIGRATE_DMA"}, \ + {H_REGISTER_VPA, "H_REGISTER_VPA"}, \ + {H_CEDE, "H_CEDE"}, \ + {H_CONFER, "H_CONFER"}, \ + {H_PROD, "H_PROD"}, \ + {H_GET_PPP, "H_GET_PPP"}, \ + {H_SET_PPP, "H_SET_PPP"}, \ + {H_PURR, "H_PURR"}, \ + {H_PIC, "H_PIC"}, \ + {H_REG_CRQ, "H_REG_CRQ"}, \ + {H_FREE_CRQ, "H_FREE_CRQ"}, \ + {H_VIO_SIGNAL, "H_VIO_SIGNAL"}, \ + {H_SEND_CRQ, "H_SEND_CRQ"}, \ + {H_COPY_RDMA, "H_COPY_RDMA"}, \ + {H_REGISTER_LOGICAL_LAN, "H_REGISTER_LOGICAL_LAN"}, \ + {H_FREE_LOGICAL_LAN, "H_FREE_LOGICAL_LAN"}, \ + {H_ADD_LOGICAL_LAN_BUFFER, "H_ADD_LOGICAL_LAN_BUFFER"}, \ + {H_SEND_LOGICAL_LAN, "H_SEND_LOGICAL_LAN"}, \ + {H_BULK_REMOVE, "H_BULK_REMOVE"}, \ + {H_MULTICAST_CTRL, "H_MULTICAST_CTRL"}, \ + {H_SET_XDABR, "H_SET_XDABR"}, \ + {H_STUFF_TCE, "H_STUFF_TCE"}, \ + {H_PUT_TCE_INDIRECT, "H_PUT_TCE_INDIRECT"}, \ + {H_CHANGE_LOGICAL_LAN_MAC, "H_CHANGE_LOGICAL_LAN_MAC"}, \ + {H_VTERM_PARTNER_INFO, "H_VTERM_PARTNER_INFO"}, \ + {H_REGISTER_VTERM, "H_REGISTER_VTERM"}, \ + {H_FREE_VTERM, "H_FREE_VTERM"}, \ + {H_RESET_EVENTS, "H_RESET_EVENTS"}, \ + {H_ALLOC_RESOURCE, "H_ALLOC_RESOURCE"}, \ + {H_FREE_RESOURCE, "H_FREE_RESOURCE"}, \ + {H_MODIFY_QP, "H_MODIFY_QP"}, \ + {H_QUERY_QP, "H_QUERY_QP"}, \ + {H_REREGISTER_PMR, "H_REREGISTER_PMR"}, \ + {H_REGISTER_SMR, "H_REGISTER_SMR"}, \ + {H_QUERY_MR, "H_QUERY_MR"}, \ + {H_QUERY_MW, "H_QUERY_MW"}, \ + {H_QUERY_HCA, "H_QUERY_HCA"}, \ + {H_QUERY_PORT, "H_QUERY_PORT"}, \ + {H_MODIFY_PORT, "H_MODIFY_PORT"}, \ + {H_DEFINE_AQP1, "H_DEFINE_AQP1"}, \ + {H_GET_TRACE_BUFFER, "H_GET_TRACE_BUFFER"}, \ + {H_DEFINE_AQP0, "H_DEFINE_AQP0"}, \ + {H_RESIZE_MR, "H_RESIZE_MR"}, \ + {H_ATTACH_MCQP, "H_ATTACH_MCQP"}, \ + {H_DETACH_MCQP, "H_DETACH_MCQP"}, \ + {H_CREATE_RPT, "H_CREATE_RPT"}, \ + {H_REMOVE_RPT, "H_REMOVE_RPT"}, \ + {H_REGISTER_RPAGES, "H_REGISTER_RPAGES"}, \ + {H_DISABLE_AND_GETC, "H_DISABLE_AND_GETC"}, \ + {H_ERROR_DATA, "H_ERROR_DATA"}, \ + {H_GET_HCA_INFO, "H_GET_HCA_INFO"}, \ + {H_GET_PERF_COUNT, "H_GET_PERF_COUNT"}, \ + {H_MANAGE_TRACE, "H_MANAGE_TRACE"}, \ + {H_FREE_LOGICAL_LAN_BUFFER, "H_FREE_LOGICAL_LAN_BUFFER"}, \ + {H_QUERY_INT_STATE, "H_QUERY_INT_STATE"}, \ + {H_POLL_PENDING, "H_POLL_PENDING"}, \ + {H_ILLAN_ATTRIBUTES, "H_ILLAN_ATTRIBUTES"}, \ + {H_MODIFY_HEA_QP, "H_MODIFY_HEA_QP"}, \ + {H_QUERY_HEA_QP, "H_QUERY_HEA_QP"}, \ + {H_QUERY_HEA, "H_QUERY_HEA"}, \ + {H_QUERY_HEA_PORT, "H_QUERY_HEA_PORT"}, \ + {H_MODIFY_HEA_PORT, "H_MODIFY_HEA_PORT"}, \ + {H_REG_BCMC, "H_REG_BCMC"}, \ + {H_DEREG_BCMC, "H_DEREG_BCMC"}, \ + {H_REGISTER_HEA_RPAGES, "H_REGISTER_HEA_RPAGES"}, \ + {H_DISABLE_AND_GET_HEA, "H_DISABLE_AND_GET_HEA"}, \ + {H_GET_HEA_INFO, "H_GET_HEA_INFO"}, \ + {H_ALLOC_HEA_RESOURCE, "H_ALLOC_HEA_RESOURCE"}, \ + {H_ADD_CONN, "H_ADD_CONN"}, \ + {H_DEL_CONN, "H_DEL_CONN"}, \ + {H_JOIN, "H_JOIN"}, \ + {H_VASI_STATE, "H_VASI_STATE"}, \ + {H_ENABLE_CRQ, "H_ENABLE_CRQ"}, \ + {H_GET_EM_PARMS, "H_GET_EM_PARMS"}, \ + {H_SET_MPP, "H_SET_MPP"}, \ + {H_GET_MPP, "H_GET_MPP"}, \ + {H_HOME_NODE_ASSOCIATIVITY, "H_HOME_NODE_ASSOCIATIVITY"}, \ + {H_BEST_ENERGY, "H_BEST_ENERGY"}, \ + {H_XIRR_X, "H_XIRR_X"}, \ + {H_RANDOM, "H_RANDOM"}, \ + {H_COP, "H_COP"}, \ + {H_GET_MPP_X, "H_GET_MPP_X"}, \ + {H_SET_MODE, "H_SET_MODE"}, \ + {H_RTAS, "H_RTAS"} + +#define kvm_trace_symbol_kvmret \ + {RESUME_GUEST, "RESUME_GUEST"}, \ + {RESUME_GUEST_NV, "RESUME_GUEST_NV"}, \ + {RESUME_HOST, "RESUME_HOST"}, \ + {RESUME_HOST_NV, "RESUME_HOST_NV"} + +#define kvm_trace_symbol_hcall_rc \ + {H_SUCCESS, "H_SUCCESS"}, \ + {H_BUSY, "H_BUSY"}, \ + {H_CLOSED, "H_CLOSED"}, \ + {H_NOT_AVAILABLE, "H_NOT_AVAILABLE"}, \ + {H_CONSTRAINED, "H_CONSTRAINED"}, \ + {H_PARTIAL, "H_PARTIAL"}, \ + {H_IN_PROGRESS, "H_IN_PROGRESS"}, \ + {H_PAGE_REGISTERED, "H_PAGE_REGISTERED"}, \ + {H_PARTIAL_STORE, "H_PARTIAL_STORE"}, \ + {H_PENDING, "H_PENDING"}, \ + {H_CONTINUE, "H_CONTINUE"}, \ + {H_LONG_BUSY_START_RANGE, "H_LONG_BUSY_START_RANGE"}, \ + {H_LONG_BUSY_ORDER_1_MSEC, "H_LONG_BUSY_ORDER_1_MSEC"}, \ + {H_LONG_BUSY_ORDER_10_MSEC, "H_LONG_BUSY_ORDER_10_MSEC"}, \ + {H_LONG_BUSY_ORDER_100_MSEC, "H_LONG_BUSY_ORDER_100_MSEC"}, \ + {H_LONG_BUSY_ORDER_1_SEC, "H_LONG_BUSY_ORDER_1_SEC"}, \ + {H_LONG_BUSY_ORDER_10_SEC, "H_LONG_BUSY_ORDER_10_SEC"}, \ + {H_LONG_BUSY_ORDER_100_SEC, "H_LONG_BUSY_ORDER_100_SEC"}, \ + {H_LONG_BUSY_END_RANGE, "H_LONG_BUSY_END_RANGE"}, \ + {H_TOO_HARD, "H_TOO_HARD"}, \ + {H_HARDWARE, "H_HARDWARE"}, \ + {H_FUNCTION, "H_FUNCTION"}, \ + {H_PRIVILEGE, "H_PRIVILEGE"}, \ + {H_PARAMETER, "H_PARAMETER"}, \ + {H_BAD_MODE, "H_BAD_MODE"}, \ + {H_PTEG_FULL, "H_PTEG_FULL"}, \ + {H_NOT_FOUND, "H_NOT_FOUND"}, \ + {H_RESERVED_DABR, "H_RESERVED_DABR"}, \ + {H_NO_MEM, "H_NO_MEM"}, \ + {H_AUTHORITY, "H_AUTHORITY"}, \ + {H_PERMISSION, "H_PERMISSION"}, \ + {H_DROPPED, "H_DROPPED"}, \ + {H_SOURCE_PARM, "H_SOURCE_PARM"}, \ + {H_DEST_PARM, "H_DEST_PARM"}, \ + {H_REMOTE_PARM, "H_REMOTE_PARM"}, \ + {H_RESOURCE, "H_RESOURCE"}, \ + {H_ADAPTER_PARM, "H_ADAPTER_PARM"}, \ + {H_RH_PARM, "H_RH_PARM"}, \ + {H_RCQ_PARM, "H_RCQ_PARM"}, \ + {H_SCQ_PARM, "H_SCQ_PARM"}, \ + {H_EQ_PARM, "H_EQ_PARM"}, \ + {H_RT_PARM, "H_RT_PARM"}, \ + {H_ST_PARM, "H_ST_PARM"}, \ + {H_SIGT_PARM, "H_SIGT_PARM"}, \ + {H_TOKEN_PARM, "H_TOKEN_PARM"}, \ + {H_MLENGTH_PARM, "H_MLENGTH_PARM"}, \ + {H_MEM_PARM, "H_MEM_PARM"}, \ + {H_MEM_ACCESS_PARM, "H_MEM_ACCESS_PARM"}, \ + {H_ATTR_PARM, "H_ATTR_PARM"}, \ + {H_PORT_PARM, "H_PORT_PARM"}, \ + {H_MCG_PARM, "H_MCG_PARM"}, \ + {H_VL_PARM, "H_VL_PARM"}, \ + {H_TSIZE_PARM, "H_TSIZE_PARM"}, \ + {H_TRACE_PARM, "H_TRACE_PARM"}, \ + {H_MASK_PARM, "H_MASK_PARM"}, \ + {H_MCG_FULL, "H_MCG_FULL"}, \ + {H_ALIAS_EXIST, "H_ALIAS_EXIST"}, \ + {H_P_COUNTER, "H_P_COUNTER"}, \ + {H_TABLE_FULL, "H_TABLE_FULL"}, \ + {H_ALT_TABLE, "H_ALT_TABLE"}, \ + {H_MR_CONDITION, "H_MR_CONDITION"}, \ + {H_NOT_ENOUGH_RESOURCES, "H_NOT_ENOUGH_RESOURCES"}, \ + {H_R_STATE, "H_R_STATE"}, \ + {H_RESCINDED, "H_RESCINDED"}, \ + {H_P2, "H_P2"}, \ + {H_P3, "H_P3"}, \ + {H_P4, "H_P4"}, \ + {H_P5, "H_P5"}, \ + {H_P6, "H_P6"}, \ + {H_P7, "H_P7"}, \ + {H_P8, "H_P8"}, \ + {H_P9, "H_P9"}, \ + {H_TOO_BIG, "H_TOO_BIG"}, \ + {H_OVERLAP, "H_OVERLAP"}, \ + {H_INTERRUPT, "H_INTERRUPT"}, \ + {H_BAD_DATA, "H_BAD_DATA"}, \ + {H_NOT_ACTIVE, "H_NOT_ACTIVE"}, \ + {H_SG_LIST, "H_SG_LIST"}, \ + {H_OP_MODE, "H_OP_MODE"}, \ + {H_COP_HW, "H_COP_HW"}, \ + {H_UNSUPPORTED_FLAG_START, "H_UNSUPPORTED_FLAG_START"}, \ + {H_UNSUPPORTED_FLAG_END, "H_UNSUPPORTED_FLAG_END"}, \ + {H_MULTI_THREADS_ACTIVE, "H_MULTI_THREADS_ACTIVE"}, \ + {H_OUTSTANDING_COP_OPS, "H_OUTSTANDING_COP_OPS"} + +TRACE_EVENT(kvm_guest_enter, + TP_PROTO(struct kvm_vcpu *vcpu), + TP_ARGS(vcpu), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(unsigned long, pc) + __field(unsigned long, pending_exceptions) + __field(u8, ceded) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + __entry->pc = kvmppc_get_pc(vcpu); + __entry->ceded = vcpu->arch.ceded; + __entry->pending_exceptions = vcpu->arch.pending_exceptions; + ), + + TP_printk("VCPU %d: pc=0x%lx pexcp=0x%lx ceded=%d", + __entry->vcpu_id, + __entry->pc, + __entry->pending_exceptions, __entry->ceded) +); + +TRACE_EVENT(kvm_guest_exit, + TP_PROTO(struct kvm_vcpu *vcpu), + TP_ARGS(vcpu), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, trap) + __field(unsigned long, pc) + __field(unsigned long, msr) + __field(u8, ceded) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + __entry->trap = vcpu->arch.trap; + __entry->ceded = vcpu->arch.ceded; + __entry->pc = kvmppc_get_pc(vcpu); + __entry->msr = vcpu->arch.shregs.msr; + ), + + TP_printk("VCPU %d: trap=%s pc=0x%lx msr=0x%lx, ceded=%d", + __entry->vcpu_id, + __print_symbolic(__entry->trap, kvm_trace_symbol_exit), + __entry->pc, __entry->msr, __entry->ceded + ) +); + +TRACE_EVENT(kvm_page_fault_enter, + TP_PROTO(struct kvm_vcpu *vcpu, unsigned long *hptep, + struct kvm_memory_slot *memslot, unsigned long ea, + unsigned long dsisr), + + TP_ARGS(vcpu, hptep, memslot, ea, dsisr), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(unsigned long, hpte_v) + __field(unsigned long, hpte_r) + __field(unsigned long, gpte_r) + __field(unsigned long, ea) + __field(u64, base_gfn) + __field(u32, slot_flags) + __field(u32, dsisr) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + __entry->hpte_v = hptep[0]; + __entry->hpte_r = hptep[1]; + __entry->gpte_r = hptep[2]; + __entry->ea = ea; + __entry->dsisr = dsisr; + __entry->base_gfn = memslot ? memslot->base_gfn : -1UL; + __entry->slot_flags = memslot ? memslot->flags : 0; + ), + + TP_printk("VCPU %d: hpte=0x%lx:0x%lx guest=0x%lx ea=0x%lx,%x slot=0x%llx,0x%x", + __entry->vcpu_id, + __entry->hpte_v, __entry->hpte_r, __entry->gpte_r, + __entry->ea, __entry->dsisr, + __entry->base_gfn, __entry->slot_flags) +); + +TRACE_EVENT(kvm_page_fault_exit, + TP_PROTO(struct kvm_vcpu *vcpu, unsigned long *hptep, long ret), + + TP_ARGS(vcpu, hptep, ret), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(unsigned long, hpte_v) + __field(unsigned long, hpte_r) + __field(long, ret) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + __entry->hpte_v = hptep[0]; + __entry->hpte_r = hptep[1]; + __entry->ret = ret; + ), + + TP_printk("VCPU %d: hpte=0x%lx:0x%lx ret=0x%lx", + __entry->vcpu_id, + __entry->hpte_v, __entry->hpte_r, __entry->ret) +); + +TRACE_EVENT(kvm_hcall_enter, + TP_PROTO(struct kvm_vcpu *vcpu), + + TP_ARGS(vcpu), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(unsigned long, req) + __field(unsigned long, gpr4) + __field(unsigned long, gpr5) + __field(unsigned long, gpr6) + __field(unsigned long, gpr7) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + __entry->req = kvmppc_get_gpr(vcpu, 3); + __entry->gpr4 = kvmppc_get_gpr(vcpu, 4); + __entry->gpr5 = kvmppc_get_gpr(vcpu, 5); + __entry->gpr6 = kvmppc_get_gpr(vcpu, 6); + __entry->gpr7 = kvmppc_get_gpr(vcpu, 7); + ), + + TP_printk("VCPU %d: hcall=%s GPR4-7=0x%lx,0x%lx,0x%lx,0x%lx", + __entry->vcpu_id, + __print_symbolic(__entry->req, kvm_trace_symbol_hcall), + __entry->gpr4, __entry->gpr5, __entry->gpr6, __entry->gpr7) +); + +TRACE_EVENT(kvm_hcall_exit, + TP_PROTO(struct kvm_vcpu *vcpu, int ret), + + TP_ARGS(vcpu, ret), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(unsigned long, ret) + __field(unsigned long, hcall_rc) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + __entry->ret = ret; + __entry->hcall_rc = kvmppc_get_gpr(vcpu, 3); + ), + + TP_printk("VCPU %d: ret=%s hcall_rc=%s", + __entry->vcpu_id, + __print_symbolic(__entry->ret, kvm_trace_symbol_kvmret), + __print_symbolic(__entry->ret & RESUME_FLAG_HOST ? + H_TOO_HARD : __entry->hcall_rc, + kvm_trace_symbol_hcall_rc)) +); + +TRACE_EVENT(kvmppc_run_core, + TP_PROTO(struct kvmppc_vcore *vc, int where), + + TP_ARGS(vc, where), + + TP_STRUCT__entry( + __field(int, n_runnable) + __field(int, runner_vcpu) + __field(int, where) + __field(pid_t, tgid) + ), + + TP_fast_assign( + __entry->runner_vcpu = vc->runner->vcpu_id; + __entry->n_runnable = vc->n_runnable; + __entry->where = where; + __entry->tgid = current->tgid; + ), + + TP_printk("%s runner_vcpu==%d runnable=%d tgid=%d", + __entry->where ? "Exit" : "Enter", + __entry->runner_vcpu, __entry->n_runnable, __entry->tgid) +); + +TRACE_EVENT(kvmppc_vcore_blocked, + TP_PROTO(struct kvmppc_vcore *vc, int where), + + TP_ARGS(vc, where), + + TP_STRUCT__entry( + __field(int, n_runnable) + __field(int, runner_vcpu) + __field(int, where) + __field(pid_t, tgid) + ), + + TP_fast_assign( + __entry->runner_vcpu = vc->runner->vcpu_id; + __entry->n_runnable = vc->n_runnable; + __entry->where = where; + __entry->tgid = current->tgid; + ), + + TP_printk("%s runner_vcpu=%d runnable=%d tgid=%d", + __entry->where ? "Exit" : "Enter", + __entry->runner_vcpu, __entry->n_runnable, __entry->tgid) +); + +TRACE_EVENT(kvmppc_run_vcpu_enter, + TP_PROTO(struct kvm_vcpu *vcpu), + + TP_ARGS(vcpu), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(pid_t, tgid) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + __entry->tgid = current->tgid; + ), + + TP_printk("VCPU %d: tgid=%d", __entry->vcpu_id, __entry->tgid) +); + +TRACE_EVENT(kvmppc_run_vcpu_exit, + TP_PROTO(struct kvm_vcpu *vcpu, struct kvm_run *run), + + TP_ARGS(vcpu, run), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, exit) + __field(int, ret) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + __entry->exit = run->exit_reason; + __entry->ret = vcpu->arch.ret; + ), + + TP_printk("VCPU %d: exit=%d, ret=%d", + __entry->vcpu_id, __entry->exit, __entry->ret) +); + +#endif /* _TRACE_KVM_HV_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/powerpc/kvm/trace_pr.h b/arch/powerpc/kvm/trace_pr.h index e1357cd8dc1f..810507cb688a 100644 --- a/arch/powerpc/kvm/trace_pr.h +++ b/arch/powerpc/kvm/trace_pr.h @@ -3,36 +3,13 @@ #define _TRACE_KVM_PR_H #include <linux/tracepoint.h> +#include "trace_book3s.h" #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm_pr #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE trace_pr -#define kvm_trace_symbol_exit \ - {0x100, "SYSTEM_RESET"}, \ - {0x200, "MACHINE_CHECK"}, \ - {0x300, "DATA_STORAGE"}, \ - {0x380, "DATA_SEGMENT"}, \ - {0x400, "INST_STORAGE"}, \ - {0x480, "INST_SEGMENT"}, \ - {0x500, "EXTERNAL"}, \ - {0x501, "EXTERNAL_LEVEL"}, \ - {0x502, "EXTERNAL_HV"}, \ - {0x600, "ALIGNMENT"}, \ - {0x700, "PROGRAM"}, \ - {0x800, "FP_UNAVAIL"}, \ - {0x900, "DECREMENTER"}, \ - {0x980, "HV_DECREMENTER"}, \ - {0xc00, "SYSCALL"}, \ - {0xd00, "TRACE"}, \ - {0xe00, "H_DATA_STORAGE"}, \ - {0xe20, "H_INST_STORAGE"}, \ - {0xe40, "H_EMUL_ASSIST"}, \ - {0xf00, "PERFMON"}, \ - {0xf20, "ALTIVEC"}, \ - {0xf40, "VSX"} - TRACE_EVENT(kvm_book3s_reenter, TP_PROTO(int r, struct kvm_vcpu *vcpu), TP_ARGS(r, vcpu), diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index dba34088da28..f162d0b8eea3 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -177,7 +177,7 @@ static ssize_t _name##_show(struct device *dev, \ } \ ret = sprintf(buf, _fmt, _expr); \ e_free: \ - kfree(page); \ + kmem_cache_free(hv_page_cache, page); \ return ret; \ } \ static DEVICE_ATTR_RO(_name) @@ -217,11 +217,14 @@ static bool is_physical_domain(int domain) domain == HV_24X7_PERF_DOMAIN_PHYSICAL_CORE; } +DEFINE_PER_CPU(char, hv_24x7_reqb[4096]) __aligned(4096); +DEFINE_PER_CPU(char, hv_24x7_resb[4096]) __aligned(4096); + static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix, u16 lpar, u64 *res, bool success_expected) { - unsigned long ret = -ENOMEM; + unsigned long ret; /* * request_buffer and result_buffer are not required to be 4k aligned, @@ -243,13 +246,11 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix, BUILD_BUG_ON(sizeof(*request_buffer) > 4096); BUILD_BUG_ON(sizeof(*result_buffer) > 4096); - request_buffer = kmem_cache_zalloc(hv_page_cache, GFP_USER); - if (!request_buffer) - goto out; + request_buffer = (void *)get_cpu_var(hv_24x7_reqb); + result_buffer = (void *)get_cpu_var(hv_24x7_resb); - result_buffer = kmem_cache_zalloc(hv_page_cache, GFP_USER); - if (!result_buffer) - goto out_free_request_buffer; + memset(request_buffer, 0, 4096); + memset(result_buffer, 0, 4096); *request_buffer = (struct reqb) { .buf = { @@ -278,15 +279,11 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix, domain, offset, ix, lpar, ret, ret, result_buffer->buf.detailed_rc, result_buffer->buf.failing_request_ix); - goto out_free_result_buffer; + goto out; } *res = be64_to_cpu(result_buffer->result); -out_free_result_buffer: - kfree(result_buffer); -out_free_request_buffer: - kfree(request_buffer); out: return ret; } diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 0a299be588af..54eca8b3b288 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -158,6 +158,43 @@ opal_tracepoint_return: blr #endif +/* + * Make opal call in realmode. This is a generic function to be called + * from realmode. It handles endianness. + * + * r13 - paca pointer + * r1 - stack pointer + * r0 - opal token + */ +_GLOBAL(opal_call_realmode) + mflr r12 + std r12,PPC_LR_STKOFF(r1) + ld r2,PACATOC(r13) + /* Set opal return address */ + LOAD_REG_ADDR(r12,return_from_opal_call) + mtlr r12 + + mfmsr r12 +#ifdef __LITTLE_ENDIAN__ + /* Handle endian-ness */ + li r11,MSR_LE + andc r12,r12,r11 +#endif + mtspr SPRN_HSRR1,r12 + LOAD_REG_ADDR(r11,opal) + ld r12,8(r11) + ld r2,0(r11) + mtspr SPRN_HSRR0,r12 + hrfid + +return_from_opal_call: +#ifdef __LITTLE_ENDIAN__ + FIXUP_ENDIAN +#endif + ld r12,PPC_LR_STKOFF(r1) + mtlr r12 + blr + OPAL_CALL(opal_invalid_call, OPAL_INVALID_CALL); OPAL_CALL(opal_console_write, OPAL_CONSOLE_WRITE); OPAL_CALL(opal_console_read, OPAL_CONSOLE_READ); @@ -247,6 +284,7 @@ OPAL_CALL(opal_sensor_read, OPAL_SENSOR_READ); OPAL_CALL(opal_get_param, OPAL_GET_PARAM); OPAL_CALL(opal_set_param, OPAL_SET_PARAM); OPAL_CALL(opal_handle_hmi, OPAL_HANDLE_HMI); +OPAL_CALL(opal_slw_set_reg, OPAL_SLW_SET_REG); OPAL_CALL(opal_register_dump_region, OPAL_REGISTER_DUMP_REGION); OPAL_CALL(opal_unregister_dump_region, OPAL_UNREGISTER_DUMP_REGION); OPAL_CALL(opal_pci_set_phb_cxl_mode, OPAL_PCI_SET_PHB_CXL_MODE); @@ -254,3 +292,4 @@ OPAL_CALL(opal_tpo_write, OPAL_WRITE_TPO); OPAL_CALL(opal_tpo_read, OPAL_READ_TPO); OPAL_CALL(opal_ipmi_send, OPAL_IPMI_SEND); OPAL_CALL(opal_ipmi_recv, OPAL_IPMI_RECV); +OPAL_CALL(opal_i2c_request, OPAL_I2C_REQUEST); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index cb0b6de79cd4..f10b9ec8c1f5 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -9,8 +9,9 @@ * 2 of the License, or (at your option) any later version. */ -#undef DEBUG +#define pr_fmt(fmt) "opal: " fmt +#include <linux/printk.h> #include <linux/types.h> #include <linux/of.h> #include <linux/of_fdt.h> @@ -625,6 +626,39 @@ static int opal_sysfs_init(void) return 0; } +static ssize_t symbol_map_read(struct file *fp, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t count) +{ + return memory_read_from_buffer(buf, count, &off, bin_attr->private, + bin_attr->size); +} + +static BIN_ATTR_RO(symbol_map, 0); + +static void opal_export_symmap(void) +{ + const __be64 *syms; + unsigned int size; + struct device_node *fw; + int rc; + + fw = of_find_node_by_path("/ibm,opal/firmware"); + if (!fw) + return; + syms = of_get_property(fw, "symbol-map", &size); + if (!syms || size != 2 * sizeof(__be64)) + return; + + /* Setup attributes */ + bin_attr_symbol_map.private = __va(be64_to_cpu(syms[0])); + bin_attr_symbol_map.size = be64_to_cpu(syms[1]); + + rc = sysfs_create_bin_file(opal_kobj, &bin_attr_symbol_map); + if (rc) + pr_warn("Error %d creating OPAL symbols file\n", rc); +} + static void __init opal_dump_region_init(void) { void *addr; @@ -653,6 +687,14 @@ static void opal_ipmi_init(struct device_node *opal_node) of_platform_device_create(np, NULL, NULL); } +static void opal_i2c_create_devs(void) +{ + struct device_node *np; + + for_each_compatible_node(np, NULL, "ibm,opal-i2c") + of_platform_device_create(np, NULL, NULL); +} + static int __init opal_init(void) { struct device_node *np, *consoles; @@ -679,6 +721,9 @@ static int __init opal_init(void) of_node_put(consoles); } + /* Create i2c platform devices */ + opal_i2c_create_devs(); + /* Find all OPAL interrupts and request them */ irqs = of_get_property(opal_node, "opal-interrupts", &irqlen); pr_debug("opal: Found %d interrupts reserved for OPAL\n", @@ -702,6 +747,8 @@ static int __init opal_init(void) /* Create "opal" kobject under /sys/firmware */ rc = opal_sysfs_init(); if (rc == 0) { + /* Export symbol map to userspace */ + opal_export_symmap(); /* Setup dump region interface */ opal_dump_region_init(); /* Setup error log interface */ @@ -824,3 +871,4 @@ EXPORT_SYMBOL_GPL(opal_rtc_read); EXPORT_SYMBOL_GPL(opal_rtc_write); EXPORT_SYMBOL_GPL(opal_tpo_read); EXPORT_SYMBOL_GPL(opal_tpo_write); +EXPORT_SYMBOL_GPL(opal_i2c_request); diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index 6c8e2d188cd0..604c48e7879a 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -29,6 +29,8 @@ static inline u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev) } #endif +extern u32 pnv_get_supported_cpuidle_states(void); + extern void pnv_lpc_init(void); bool cpu_core_split_required(void); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 30b1c3e298a6..b700a329c31d 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -36,8 +36,12 @@ #include <asm/opal.h> #include <asm/kexec.h> #include <asm/smp.h> +#include <asm/cputhreads.h> +#include <asm/cpuidle.h> +#include <asm/code-patching.h> #include "powernv.h" +#include "subcore.h" static void __init pnv_setup_arch(void) { @@ -288,6 +292,168 @@ static void __init pnv_setup_machdep_rtas(void) } #endif /* CONFIG_PPC_POWERNV_RTAS */ +static u32 supported_cpuidle_states; + +int pnv_save_sprs_for_winkle(void) +{ + int cpu; + int rc; + + /* + * hid0, hid1, hid4, hid5, hmeer and lpcr values are symmetric accross + * all cpus at boot. Get these reg values of current cpu and use the + * same accross all cpus. + */ + uint64_t lpcr_val = mfspr(SPRN_LPCR); + uint64_t hid0_val = mfspr(SPRN_HID0); + uint64_t hid1_val = mfspr(SPRN_HID1); + uint64_t hid4_val = mfspr(SPRN_HID4); + uint64_t hid5_val = mfspr(SPRN_HID5); + uint64_t hmeer_val = mfspr(SPRN_HMEER); + + for_each_possible_cpu(cpu) { + uint64_t pir = get_hard_smp_processor_id(cpu); + uint64_t hsprg0_val = (uint64_t)&paca[cpu]; + + /* + * HSPRG0 is used to store the cpu's pointer to paca. Hence last + * 3 bits are guaranteed to be 0. Program slw to restore HSPRG0 + * with 63rd bit set, so that when a thread wakes up at 0x100 we + * can use this bit to distinguish between fastsleep and + * deep winkle. + */ + hsprg0_val |= 1; + + rc = opal_slw_set_reg(pir, SPRN_HSPRG0, hsprg0_val); + if (rc != 0) + return rc; + + rc = opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val); + if (rc != 0) + return rc; + + /* HIDs are per core registers */ + if (cpu_thread_in_core(cpu) == 0) { + + rc = opal_slw_set_reg(pir, SPRN_HMEER, hmeer_val); + if (rc != 0) + return rc; + + rc = opal_slw_set_reg(pir, SPRN_HID0, hid0_val); + if (rc != 0) + return rc; + + rc = opal_slw_set_reg(pir, SPRN_HID1, hid1_val); + if (rc != 0) + return rc; + + rc = opal_slw_set_reg(pir, SPRN_HID4, hid4_val); + if (rc != 0) + return rc; + + rc = opal_slw_set_reg(pir, SPRN_HID5, hid5_val); + if (rc != 0) + return rc; + } + } + + return 0; +} + +static void pnv_alloc_idle_core_states(void) +{ + int i, j; + int nr_cores = cpu_nr_cores(); + u32 *core_idle_state; + + /* + * core_idle_state - First 8 bits track the idle state of each thread + * of the core. The 8th bit is the lock bit. Initially all thread bits + * are set. They are cleared when the thread enters deep idle state + * like sleep and winkle. Initially the lock bit is cleared. + * The lock bit has 2 purposes + * a. While the first thread is restoring core state, it prevents + * other threads in the core from switching to process context. + * b. While the last thread in the core is saving the core state, it + * prevents a different thread from waking up. + */ + for (i = 0; i < nr_cores; i++) { + int first_cpu = i * threads_per_core; + int node = cpu_to_node(first_cpu); + + core_idle_state = kmalloc_node(sizeof(u32), GFP_KERNEL, node); + *core_idle_state = PNV_CORE_IDLE_THREAD_BITS; + + for (j = 0; j < threads_per_core; j++) { + int cpu = first_cpu + j; + + paca[cpu].core_idle_state_ptr = core_idle_state; + paca[cpu].thread_idle_state = PNV_THREAD_RUNNING; + paca[cpu].thread_mask = 1 << j; + } + } + + update_subcore_sibling_mask(); + + if (supported_cpuidle_states & OPAL_PM_WINKLE_ENABLED) + pnv_save_sprs_for_winkle(); +} + +u32 pnv_get_supported_cpuidle_states(void) +{ + return supported_cpuidle_states; +} +EXPORT_SYMBOL_GPL(pnv_get_supported_cpuidle_states); + +static int __init pnv_init_idle_states(void) +{ + struct device_node *power_mgt; + int dt_idle_states; + const __be32 *idle_state_flags; + u32 len_flags, flags; + int i; + + supported_cpuidle_states = 0; + + if (cpuidle_disable != IDLE_NO_OVERRIDE) + return 0; + + if (!firmware_has_feature(FW_FEATURE_OPALv3)) + return 0; + + power_mgt = of_find_node_by_path("/ibm,opal/power-mgt"); + if (!power_mgt) { + pr_warn("opal: PowerMgmt Node not found\n"); + return 0; + } + + idle_state_flags = of_get_property(power_mgt, + "ibm,cpu-idle-state-flags", &len_flags); + if (!idle_state_flags) { + pr_warn("DT-PowerMgmt: missing ibm,cpu-idle-state-flags\n"); + return 0; + } + + dt_idle_states = len_flags / sizeof(u32); + + for (i = 0; i < dt_idle_states; i++) { + flags = be32_to_cpu(idle_state_flags[i]); + supported_cpuidle_states |= flags; + } + if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) { + patch_instruction( + (unsigned int *)pnv_fastsleep_workaround_at_entry, + PPC_INST_NOP); + patch_instruction( + (unsigned int *)pnv_fastsleep_workaround_at_exit, + PPC_INST_NOP); + } + pnv_alloc_idle_core_states(); + return 0; +} + +subsys_initcall(pnv_init_idle_states); + static int __init pnv_probe(void) { unsigned long root = of_get_flat_dt_root(); diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index b716f666e48a..fc34025ef822 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -150,6 +150,7 @@ static void pnv_smp_cpu_kill_self(void) { unsigned int cpu; unsigned long srr1; + u32 idle_states; /* Standard hot unplug procedure */ local_irq_disable(); @@ -160,13 +161,23 @@ static void pnv_smp_cpu_kill_self(void) generic_set_cpu_dead(cpu); smp_wmb(); + idle_states = pnv_get_supported_cpuidle_states(); /* We don't want to take decrementer interrupts while we are offline, * so clear LPCR:PECE1. We keep PECE2 enabled. */ mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1); while (!generic_check_cpu_restart(cpu)) { + ppc64_runlatch_off(); - srr1 = power7_nap(1); + + if (idle_states & OPAL_PM_WINKLE_ENABLED) + srr1 = power7_winkle(); + else if ((idle_states & OPAL_PM_SLEEP_ENABLED) || + (idle_states & OPAL_PM_SLEEP_ENABLED_ER1)) + srr1 = power7_sleep(); + else + srr1 = power7_nap(1); + ppc64_runlatch_on(); /* @@ -198,13 +209,27 @@ static void pnv_smp_cpu_kill_self(void) #endif /* CONFIG_HOTPLUG_CPU */ +static int pnv_cpu_bootable(unsigned int nr) +{ + /* + * Starting with POWER8, the subcore logic relies on all threads of a + * core being booted so that they can participate in split mode + * switches. So on those machines we ignore the smt_enabled_at_boot + * setting (smt-enabled on the kernel command line). + */ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + return 1; + + return smp_generic_cpu_bootable(nr); +} + static struct smp_ops_t pnv_smp_ops = { .message_pass = smp_muxed_ipi_message_pass, .cause_ipi = NULL, /* Filled at runtime by xics_smp_probe() */ .probe = xics_smp_probe, .kick_cpu = pnv_smp_kick_cpu, .setup_cpu = pnv_smp_setup_cpu, - .cpu_bootable = smp_generic_cpu_bootable, + .cpu_bootable = pnv_cpu_bootable, #ifdef CONFIG_HOTPLUG_CPU .cpu_disable = pnv_smp_cpu_disable, .cpu_die = generic_cpu_die, diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c index c87f96b79d1a..f60f80ada903 100644 --- a/arch/powerpc/platforms/powernv/subcore.c +++ b/arch/powerpc/platforms/powernv/subcore.c @@ -160,6 +160,18 @@ static void wait_for_sync_step(int step) mb(); } +static void update_hid_in_slw(u64 hid0) +{ + u64 idle_states = pnv_get_supported_cpuidle_states(); + + if (idle_states & OPAL_PM_WINKLE_ENABLED) { + /* OPAL call to patch slw with the new HID0 value */ + u64 cpu_pir = hard_smp_processor_id(); + + opal_slw_set_reg(cpu_pir, SPRN_HID0, hid0); + } +} + static void unsplit_core(void) { u64 hid0, mask; @@ -179,6 +191,7 @@ static void unsplit_core(void) hid0 = mfspr(SPRN_HID0); hid0 &= ~HID0_POWER8_DYNLPARDIS; mtspr(SPRN_HID0, hid0); + update_hid_in_slw(hid0); while (mfspr(SPRN_HID0) & mask) cpu_relax(); @@ -215,6 +228,7 @@ static void split_core(int new_mode) hid0 = mfspr(SPRN_HID0); hid0 |= HID0_POWER8_DYNLPARDIS | split_parms[i].value; mtspr(SPRN_HID0, hid0); + update_hid_in_slw(hid0); /* Wait for it to happen */ while (!(mfspr(SPRN_HID0) & split_parms[i].mask)) @@ -251,6 +265,25 @@ bool cpu_core_split_required(void) return true; } +void update_subcore_sibling_mask(void) +{ + int cpu; + /* + * sibling mask for the first cpu. Left shift this by required bits + * to get sibling mask for the rest of the cpus. + */ + int sibling_mask_first_cpu = (1 << threads_per_subcore) - 1; + + for_each_possible_cpu(cpu) { + int tid = cpu_thread_in_core(cpu); + int offset = (tid / threads_per_subcore) * threads_per_subcore; + int mask = sibling_mask_first_cpu << offset; + + paca[cpu].subcore_sibling_mask = mask; + + } +} + static int cpu_update_split_mode(void *data) { int cpu, new_mode = *(int *)data; @@ -284,6 +317,7 @@ static int cpu_update_split_mode(void *data) /* Make the new mode public */ subcores_per_core = new_mode; threads_per_subcore = threads_per_core / subcores_per_core; + update_subcore_sibling_mask(); /* Make sure the new mode is written before we exit */ mb(); diff --git a/arch/powerpc/platforms/powernv/subcore.h b/arch/powerpc/platforms/powernv/subcore.h index 148abc91debf..84e02ae52895 100644 --- a/arch/powerpc/platforms/powernv/subcore.h +++ b/arch/powerpc/platforms/powernv/subcore.h @@ -14,5 +14,12 @@ #define SYNC_STEP_FINISHED 3 /* Set by secondary when split/unsplit is done */ #ifndef __ASSEMBLY__ + +#ifdef CONFIG_SMP void split_core_secondary_loop(u8 *state); -#endif +extern void update_subcore_sibling_mask(void); +#else +static inline void update_subcore_sibling_mask(void) { }; +#endif /* CONFIG_SMP */ + +#endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 469751d92004..b5682fd6c984 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -43,6 +43,7 @@ #include <asm/trace.h> #include <asm/firmware.h> #include <asm/plpar_wrappers.h> +#include <asm/kexec.h> #include <asm/fadump.h> #include "pseries.h" @@ -267,8 +268,13 @@ static void pSeries_lpar_hptab_clear(void) * out to the user, but at least this will stop us from * continuing on further and creating an even more * difficult to debug situation. + * + * There is a known problem when kdump'ing, if cpus are offline + * the above call will fail. Rather than panicking again, keep + * going and hope the kdump kernel is also little endian, which + * it usually is. */ - if (rc) + if (rc && !kdump_in_progress()) panic("Could not enable big endian exceptions"); } #endif |