diff options
Diffstat (limited to 'arch/powerpc')
57 files changed, 924 insertions, 347 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 1f48bbfb3ce9..65bed1fdeaad 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -860,6 +860,18 @@ config PPC_SUBPAGE_PROT If unsure, say N here. +config PPC_PROT_SAO_LPAR + bool "Support PROT_SAO mappings in LPARs" + depends on PPC_BOOK3S_64 + help + This option adds support for PROT_SAO mappings from userspace + inside LPARs on supported CPUs. + + This may cause issues when performing guest migration from + a CPU that supports SAO to one that does not. + + If unsure, say N here. + config PPC_COPRO_BASE bool diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 6de56c3b33c4..495fc0ccb453 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -20,13 +20,9 @@ #define _PAGE_RW (_PAGE_READ | _PAGE_WRITE) #define _PAGE_RWX (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC) #define _PAGE_PRIVILEGED 0x00008 /* kernel access only */ - -#define _PAGE_CACHE_CTL 0x00030 /* Bits for the folowing cache modes */ - /* No bits set is normal cacheable memory */ - /* 0x00010 unused, is SAO bit on radix POWER9 */ +#define _PAGE_SAO 0x00010 /* Strong access order */ #define _PAGE_NON_IDEMPOTENT 0x00020 /* non idempotent memory */ #define _PAGE_TOLERANT 0x00030 /* tolerant memory, cache inhibited */ - #define _PAGE_DIRTY 0x00080 /* C: page changed */ #define _PAGE_ACCESSED 0x00100 /* R: page referenced */ /* @@ -828,6 +824,8 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, return hash__set_pte_at(mm, addr, ptep, pte, percpu); } +#define _PAGE_CACHE_CTL (_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT) + #define pgprot_noncached pgprot_noncached static inline pgprot_t pgprot_noncached(pgprot_t prot) { diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index fdddb822d564..32a15dc49e8c 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -9,6 +9,11 @@ #ifndef __ASSEMBLY__ +/* + * Added to include __machine_check_early_realmode_* functions + */ +#include <asm/mce.h> + /* This structure can grow, it's real size is used by head.S code * via the mkdefs mechanism. */ @@ -191,7 +196,7 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_SPURR LONG_ASM_CONST(0x0000000001000000) #define CPU_FTR_DSCR LONG_ASM_CONST(0x0000000002000000) #define CPU_FTR_VSX LONG_ASM_CONST(0x0000000004000000) -// Free LONG_ASM_CONST(0x0000000008000000) +#define CPU_FTR_SAO LONG_ASM_CONST(0x0000000008000000) #define CPU_FTR_CP_USE_DCBTZ LONG_ASM_CONST(0x0000000010000000) #define CPU_FTR_UNALIGNED_LD_STD LONG_ASM_CONST(0x0000000020000000) #define CPU_FTR_ASYM_SMT LONG_ASM_CONST(0x0000000040000000) @@ -436,7 +441,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | CPU_FTR_ASYM_SMT | \ + CPU_FTR_DSCR | CPU_FTR_SAO | CPU_FTR_ASYM_SMT | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | \ CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX ) @@ -445,7 +450,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | \ + CPU_FTR_DSCR | CPU_FTR_SAO | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ @@ -456,7 +461,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | \ + CPU_FTR_DSCR | CPU_FTR_SAO | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \ @@ -474,7 +479,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | \ + CPU_FTR_DSCR | CPU_FTR_SAO | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \ diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h index d8a0729cf754..219559d65864 100644 --- a/arch/powerpc/include/asm/device.h +++ b/arch/powerpc/include/asm/device.h @@ -29,9 +29,6 @@ struct dev_archdata { struct iommu_table *iommu_table_base; #endif -#ifdef CONFIG_IOMMU_API - void *iommu_domain; -#endif #ifdef CONFIG_PPC64 struct pci_dn *pci_data; #endif diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 925cf89cbf4b..6bfc87915d5d 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -52,7 +52,7 @@ enum fixed_addresses { FIX_HOLE, /* reserve the top 128K for early debugging purposes */ FIX_EARLY_DEBUG_TOP = FIX_HOLE, - FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128, PAGE_SIZE)/PAGE_SIZE)-1, + FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128K, PAGE_SIZE)/PAGE_SIZE)-1, #ifdef CONFIG_HIGHMEM FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 3a0db7b0b46e..35060be09073 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -200,17 +200,14 @@ static inline bool arch_irqs_disabled(void) #define powerpc_local_irq_pmu_save(flags) \ do { \ raw_local_irq_pmu_save(flags); \ - trace_hardirqs_off(); \ + if (!raw_irqs_disabled_flags(flags)) \ + trace_hardirqs_off(); \ } while(0) #define powerpc_local_irq_pmu_restore(flags) \ do { \ - if (raw_irqs_disabled_flags(flags)) { \ - raw_local_irq_pmu_restore(flags); \ - trace_hardirqs_off(); \ - } else { \ + if (!raw_irqs_disabled_flags(flags)) \ trace_hardirqs_on(); \ - raw_local_irq_pmu_restore(flags); \ - } \ + raw_local_irq_pmu_restore(flags); \ } while(0) #else #define powerpc_local_irq_pmu_save(flags) \ diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h index d635b96c7ea6..7355ed05e65e 100644 --- a/arch/powerpc/include/asm/kasan.h +++ b/arch/powerpc/include/asm/kasan.h @@ -15,11 +15,18 @@ #ifndef __ASSEMBLY__ #include <asm/page.h> +#include <linux/sizes.h> #define KASAN_SHADOW_SCALE_SHIFT 3 +#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_MODULES) && defined(CONFIG_STRICT_KERNEL_RWX) +#define KASAN_KERN_START ALIGN_DOWN(PAGE_OFFSET - SZ_256M, SZ_256M) +#else +#define KASAN_KERN_START PAGE_OFFSET +#endif + #define KASAN_SHADOW_START (KASAN_SHADOW_OFFSET + \ - (PAGE_OFFSET >> KASAN_SHADOW_SCALE_SHIFT)) + (KASAN_KERN_START >> KASAN_SHADOW_SCALE_SHIFT)) #define KASAN_SHADOW_OFFSET ASM_CONST(CONFIG_KASAN_SHADOW_OFFSET) diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h index 9cb7d8be2366..0a6319448cb6 100644 --- a/arch/powerpc/include/asm/kvm_book3s_uvmem.h +++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h @@ -23,6 +23,10 @@ int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn); unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm); void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, struct kvm *kvm, bool skip_page_out); +int kvmppc_uvmem_memslot_create(struct kvm *kvm, + const struct kvm_memory_slot *new); +void kvmppc_uvmem_memslot_delete(struct kvm *kvm, + const struct kvm_memory_slot *old); #else static inline int kvmppc_uvmem_init(void) { @@ -82,5 +86,15 @@ static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn) static inline void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, struct kvm *kvm, bool skip_page_out) { } + +static inline int kvmppc_uvmem_memslot_create(struct kvm *kvm, + const struct kvm_memory_slot *new) +{ + return H_UNSUPPORTED; +} + +static inline void kvmppc_uvmem_memslot_delete(struct kvm *kvm, + const struct kvm_memory_slot *old) { } + #endif /* CONFIG_PPC_UV */ #endif /* __ASM_KVM_BOOK3S_UVMEM_H__ */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index e020d269416d..10ded83414de 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -58,7 +58,8 @@ #define KVM_ARCH_WANT_MMU_NOTIFIER extern int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, + unsigned flags); extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); extern int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index ccf66b3a4c1d..0a056c64c317 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -59,7 +59,7 @@ enum xlate_readwrite { }; extern int kvmppc_vcpu_run(struct kvm_vcpu *vcpu); -extern int __kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu); +extern int __kvmppc_vcpu_run(struct kvm_vcpu *vcpu); extern void kvmppc_handler_highmem(void); extern void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu); diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index adf2cda67f9a..89aa8248a57d 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -210,6 +210,9 @@ struct mce_error_info { #define MCE_EVENT_RELEASE true #define MCE_EVENT_DONTRELEASE false +struct pt_regs; +struct notifier_block; + extern void save_mce_event(struct pt_regs *regs, long handled, struct mce_error_info *mce_err, uint64_t nip, uint64_t addr, uint64_t phys_addr); @@ -225,5 +228,9 @@ int mce_register_notifier(struct notifier_block *nb); int mce_unregister_notifier(struct notifier_block *nb); #ifdef CONFIG_PPC_BOOK3S_64 void flush_and_reload_slb(void); +long __machine_check_early_realmode_p7(struct pt_regs *regs); +long __machine_check_early_realmode_p8(struct pt_regs *regs); +long __machine_check_early_realmode_p9(struct pt_regs *regs); +long __machine_check_early_realmode_p10(struct pt_regs *regs); #endif /* CONFIG_PPC_BOOK3S_64 */ #endif /* __ASM_PPC64_MCE_H__ */ diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h index 7c07728af300..7cb6d18f5cd6 100644 --- a/arch/powerpc/include/asm/mman.h +++ b/arch/powerpc/include/asm/mman.h @@ -13,20 +13,43 @@ #include <linux/pkeys.h> #include <asm/cpu_has_feature.h> -#ifdef CONFIG_PPC_MEM_KEYS static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { - return pkey_to_vmflag_bits(pkey); +#ifdef CONFIG_PPC_MEM_KEYS + return (((prot & PROT_SAO) ? VM_SAO : 0) | pkey_to_vmflag_bits(pkey)); +#else + return ((prot & PROT_SAO) ? VM_SAO : 0); +#endif } #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags) { - return __pgprot(vmflag_to_pte_pkey_bits(vm_flags)); +#ifdef CONFIG_PPC_MEM_KEYS + return (vm_flags & VM_SAO) ? + __pgprot(_PAGE_SAO | vmflag_to_pte_pkey_bits(vm_flags)) : + __pgprot(0 | vmflag_to_pte_pkey_bits(vm_flags)); +#else + return (vm_flags & VM_SAO) ? __pgprot(_PAGE_SAO) : __pgprot(0); +#endif } #define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags) -#endif + +static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) +{ + if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_SAO)) + return false; + if (prot & PROT_SAO) { + if (!cpu_has_feature(CPU_FTR_SAO)) + return false; + if (firmware_has_feature(FW_FEATURE_LPAR) && + !IS_ENABLED(CONFIG_PPC_PROT_SAO_LPAR)) + return false; + } + return true; +} +#define arch_validate_prot arch_validate_prot #endif /* CONFIG_PPC64 */ #endif /* _ASM_POWERPC_MMAN_H */ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 59ee9fa4ae09..6cb8aa357191 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -82,6 +82,8 @@ */ #include <asm/nohash/pte-book3e.h> +#define _PAGE_SAO 0 + #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) /* diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index 1e8b2e1ec1db..daec64d41b44 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -40,4 +40,7 @@ static inline bool is_sier_available(void) { return false; } /* To support perf_regs sier update */ extern bool is_sier_available(void); +/* To define perf extended regs mask value */ +extern u64 PERF_REG_EXTENDED_MASK; +#define PERF_REG_EXTENDED_MASK PERF_REG_EXTENDED_MASK #endif diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h index 86c9eb064b22..f6acabb6c9be 100644 --- a/arch/powerpc/include/asm/perf_event_server.h +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -62,6 +62,11 @@ struct power_pmu { int *blacklist_ev; /* BHRB entries in the PMU */ int bhrb_nr; + /* + * set this flag with `PERF_PMU_CAP_EXTENDED_REGS` if + * the pmu supports extended perf regs capability + */ + int capabilities; }; /* diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 41419f1fc00f..88fb88491fe9 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -474,7 +474,8 @@ #ifndef SPRN_LPID #define SPRN_LPID 0x13F /* Logical Partition Identifier */ #endif -#define LPID_RSVD 0x3ff /* Reserved LPID for partn switching */ +#define LPID_RSVD_POWER7 0x3ff /* Reserved LPID for partn switching */ +#define LPID_RSVD 0xfff /* Reserved LPID for partn switching */ #define SPRN_HMER 0x150 /* Hypervisor maintenance exception reg */ #define HMER_DEBUG_TRIG (1ul << (63 - 17)) /* Debug trigger */ #define SPRN_HMEER 0x151 /* Hyp maintenance exception enable reg */ @@ -1362,6 +1363,7 @@ #define PVR_ARCH_206p 0x0f100003 #define PVR_ARCH_207 0x0f000004 #define PVR_ARCH_300 0x0f000005 +#define PVR_ARCH_31 0x0f000006 /* Macros for setting and retrieving special purpose registers */ #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 64c04ab09112..00699903f1ef 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -38,8 +38,7 @@ static inline void set_fs(mm_segment_t fs) set_thread_flag(TIF_FSCHECK); } -#define segment_eq(a, b) ((a).seg == (b).seg) - +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) #define user_addr_max() (get_fs().seg) #ifdef __powerpc64__ diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h index 3a700351feca..c0c737215b00 100644 --- a/arch/powerpc/include/uapi/asm/mman.h +++ b/arch/powerpc/include/uapi/asm/mman.h @@ -11,7 +11,7 @@ #include <asm-generic/mman-common.h> -#define PROT_SAO 0x10 /* Unsupported since v5.9 */ +#define PROT_SAO 0x10 /* Strong Access Ordering */ #define MAP_RENAME MAP_ANONYMOUS /* In SunOS terminology */ #define MAP_NORESERVE 0x40 /* don't reserve swap pages */ diff --git a/arch/powerpc/include/uapi/asm/perf_regs.h b/arch/powerpc/include/uapi/asm/perf_regs.h index f599064dd8dc..bdf5f10f8b9f 100644 --- a/arch/powerpc/include/uapi/asm/perf_regs.h +++ b/arch/powerpc/include/uapi/asm/perf_regs.h @@ -48,6 +48,24 @@ enum perf_event_powerpc_regs { PERF_REG_POWERPC_DSISR, PERF_REG_POWERPC_SIER, PERF_REG_POWERPC_MMCRA, - PERF_REG_POWERPC_MAX, + /* Extended registers */ + PERF_REG_POWERPC_MMCR0, + PERF_REG_POWERPC_MMCR1, + PERF_REG_POWERPC_MMCR2, + PERF_REG_POWERPC_MMCR3, + PERF_REG_POWERPC_SIER2, + PERF_REG_POWERPC_SIER3, + /* Max regs without the extended regs */ + PERF_REG_POWERPC_MAX = PERF_REG_POWERPC_MMCRA + 1, }; + +#define PERF_REG_PMU_MASK ((1ULL << PERF_REG_POWERPC_MAX) - 1) + +/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_300 */ +#define PERF_REG_PMU_MASK_300 (((1ULL << (PERF_REG_POWERPC_MMCR2 + 1)) - 1) - PERF_REG_PMU_MASK) +/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_31 */ +#define PERF_REG_PMU_MASK_31 (((1ULL << (PERF_REG_POWERPC_SIER3 + 1)) - 1) - PERF_REG_PMU_MASK) + +#define PERF_REG_MAX_ISA_300 (PERF_REG_POWERPC_MMCR2 + 1) +#define PERF_REG_MAX_ISA_31 (PERF_REG_POWERPC_SIER3 + 1) #endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */ diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 3d406a9626e8..2aa89c6b2896 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -72,9 +72,6 @@ extern void __setup_cpu_power9(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power9(void); extern void __setup_cpu_power10(unsigned long offset, struct cpu_spec* spec); extern void __restore_cpu_power10(void); -extern long __machine_check_early_realmode_p7(struct pt_regs *regs); -extern long __machine_check_early_realmode_p8(struct pt_regs *regs); -extern long __machine_check_early_realmode_p9(struct pt_regs *regs); #endif /* CONFIG_PPC64 */ #if defined(CONFIG_E500) extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec); @@ -542,6 +539,25 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check_early = __machine_check_early_realmode_p9, .platform = "power9", }, + { /* Power10 */ + .pvr_mask = 0xffff0000, + .pvr_value = 0x00800000, + .cpu_name = "POWER10 (raw)", + .cpu_features = CPU_FTRS_POWER10, + .cpu_user_features = COMMON_USER_POWER10, + .cpu_user_features2 = COMMON_USER2_POWER10, + .mmu_features = MMU_FTRS_POWER10, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 6, + .pmc_type = PPC_PMC_IBM, + .oprofile_cpu_type = "ppc64/power10", + .oprofile_type = PPC_OPROFILE_INVALID, + .cpu_setup = __setup_cpu_power10, + .cpu_restore = __restore_cpu_power10, + .machine_check_early = __machine_check_early_realmode_p10, + .platform = "power10", + }, { /* Cell Broadband Engine */ .pvr_mask = 0xffff0000, .pvr_value = 0x00700000, diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 6f8c0c6b937a..f204ad79b6b5 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -64,10 +64,6 @@ struct dt_cpu_feature { * Set up the base CPU */ -extern long __machine_check_early_realmode_p8(struct pt_regs *regs); -extern long __machine_check_early_realmode_p9(struct pt_regs *regs); -extern long __machine_check_early_realmode_p10(struct pt_regs *regs); - static int hv_mode; static struct { @@ -657,7 +653,7 @@ static struct dt_cpu_feature_match __initdata {"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL}, {"processor-utilization-of-resources-register", feat_enable_purr, 0}, {"no-execute", feat_enable, 0}, - /* strong-access-ordering is unused */ + {"strong-access-ordering", feat_enable, CPU_FTR_SAO}, {"cache-inhibited-large-page", feat_enable_large_ci, 0}, {"coprocessor-icswx", feat_enable, 0}, {"hypervisor-virtualization-interrupt", feat_enable_hvi, 0}, diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 33a42e42c56f..733e40eba4eb 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -113,6 +113,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) ld r11,exception_marker@toc(r2) std r11,-16(r10) /* "regshere" marker */ +BEGIN_FTR_SECTION + HMT_MEDIUM +END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + /* * RECONCILE_IRQ_STATE without calling trace_hardirqs_off(), which * would clobber syscall parameters. Also we always enter with IRQs diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c index 5ac84efc6ede..9fe4fb3b08aa 100644 --- a/arch/powerpc/kernel/iomap.c +++ b/arch/powerpc/kernel/iomap.c @@ -15,23 +15,23 @@ * Here comes the ppc64 implementation of the IOMAP * interfaces. */ -unsigned int ioread8(void __iomem *addr) +unsigned int ioread8(const void __iomem *addr) { return readb(addr); } -unsigned int ioread16(void __iomem *addr) +unsigned int ioread16(const void __iomem *addr) { return readw(addr); } -unsigned int ioread16be(void __iomem *addr) +unsigned int ioread16be(const void __iomem *addr) { return readw_be(addr); } -unsigned int ioread32(void __iomem *addr) +unsigned int ioread32(const void __iomem *addr) { return readl(addr); } -unsigned int ioread32be(void __iomem *addr) +unsigned int ioread32be(const void __iomem *addr) { return readl_be(addr); } @@ -41,27 +41,27 @@ EXPORT_SYMBOL(ioread16be); EXPORT_SYMBOL(ioread32); EXPORT_SYMBOL(ioread32be); #ifdef __powerpc64__ -u64 ioread64(void __iomem *addr) +u64 ioread64(const void __iomem *addr) { return readq(addr); } -u64 ioread64_lo_hi(void __iomem *addr) +u64 ioread64_lo_hi(const void __iomem *addr) { return readq(addr); } -u64 ioread64_hi_lo(void __iomem *addr) +u64 ioread64_hi_lo(const void __iomem *addr) { return readq(addr); } -u64 ioread64be(void __iomem *addr) +u64 ioread64be(const void __iomem *addr) { return readq_be(addr); } -u64 ioread64be_lo_hi(void __iomem *addr) +u64 ioread64be_lo_hi(const void __iomem *addr) { return readq_be(addr); } -u64 ioread64be_hi_lo(void __iomem *addr) +u64 ioread64be_hi_lo(const void __iomem *addr) { return readq_be(addr); } @@ -139,15 +139,15 @@ EXPORT_SYMBOL(iowrite64be_hi_lo); * FIXME! We could make these do EEH handling if we really * wanted. Not clear if we do. */ -void ioread8_rep(void __iomem *addr, void *dst, unsigned long count) +void ioread8_rep(const void __iomem *addr, void *dst, unsigned long count) { readsb(addr, dst, count); } -void ioread16_rep(void __iomem *addr, void *dst, unsigned long count) +void ioread16_rep(const void __iomem *addr, void *dst, unsigned long count) { readsw(addr, dst, count); } -void ioread32_rep(void __iomem *addr, void *dst, unsigned long count) +void ioread32_rep(const void __iomem *addr, void *dst, unsigned long count) { readsl(addr, dst, count); } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 016bd831908e..73a57043ee66 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -548,7 +548,7 @@ void notrace restore_math(struct pt_regs *regs) * are live for the user thread). */ if ((!(msr & MSR_FP)) && should_restore_fp()) - new_msr |= MSR_FP | current->thread.fpexc_mode; + new_msr |= MSR_FP; if ((!(msr & MSR_VEC)) && should_restore_altivec()) new_msr |= MSR_VEC; @@ -559,11 +559,17 @@ void notrace restore_math(struct pt_regs *regs) } if (new_msr) { + unsigned long fpexc_mode = 0; + msr_check_and_set(new_msr); - if (new_msr & MSR_FP) + if (new_msr & MSR_FP) { do_restore_fp(); + // This also covers VSX, because VSX implies FP + fpexc_mode = current->thread.fpexc_mode; + } + if (new_msr & MSR_VEC) do_restore_altivec(); @@ -572,7 +578,7 @@ void notrace restore_math(struct pt_regs *regs) msr_check_and_clear(new_msr); - regs->msr |= new_msr; + regs->msr |= new_msr | fpexc_mode; } } #endif diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index b198b0ff25bc..808ec9fab605 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -311,6 +311,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) min = pvr & 0xFF; break; case 0x004e: /* POWER9 bits 12-15 give chip type */ + case 0x0080: /* POWER10 bit 12 gives SMT8/4 */ maj = (pvr >> 8) & 0x0F; min = pvr & 0xFF; break; diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index be9f74546068..c2d737ff2e7b 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -197,7 +197,7 @@ 146 common writev sys_writev compat_sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync -149 nospu _sysctl sys_sysctl compat_sys_sysctl +149 nospu _sysctl sys_ni_syscall 150 common mlock sys_mlock 151 common munlock sys_munlock 152 common mlockall sys_mlockall diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 41fedec69ac3..49db50d1db04 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -834,7 +834,8 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm, kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new, change); } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end); } diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 7c5a1812a1c3..38ea396a23d6 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -260,11 +260,15 @@ int kvmppc_mmu_hv_init(void) if (!mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE)) return -EINVAL; - /* POWER7 has 10-bit LPIDs (12-bit in POWER8) */ host_lpid = 0; if (cpu_has_feature(CPU_FTR_HVMODE)) host_lpid = mfspr(SPRN_LPID); - rsvd_lpid = LPID_RSVD; + + /* POWER8 and above have 12-bit LPIDs (10-bit in POWER7) */ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + rsvd_lpid = LPID_RSVD; + else + rsvd_lpid = LPID_RSVD_POWER7; kvmppc_init_lpid(rsvd_lpid + 1); diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 777aa5625d5f..22a677b18695 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -161,7 +161,9 @@ int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr, return -EINVAL; /* Read the entry from guest memory */ addr = base + (index * sizeof(rpte)); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); ret = kvm_read_guest(kvm, addr, &rpte, sizeof(rpte)); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); if (ret) { if (pte_ret_p) *pte_ret_p = addr; @@ -237,7 +239,9 @@ int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr, /* Read the table to find the root of the radix tree */ ptbl = (table & PRTB_MASK) + (table_index * sizeof(entry)); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); ret = kvm_read_guest(kvm, ptbl, &entry, sizeof(entry)); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); if (ret) return ret; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 0f83f39a2bd2..4ba06a2a306c 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -343,13 +343,18 @@ static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr) vcpu->arch.pvr = pvr; } +/* Dummy value used in computing PCR value below */ +#define PCR_ARCH_31 (PCR_ARCH_300 << 1) + static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) { unsigned long host_pcr_bit = 0, guest_pcr_bit = 0; struct kvmppc_vcore *vc = vcpu->arch.vcore; /* We can (emulate) our own architecture version and anything older */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) + if (cpu_has_feature(CPU_FTR_ARCH_31)) + host_pcr_bit = PCR_ARCH_31; + else if (cpu_has_feature(CPU_FTR_ARCH_300)) host_pcr_bit = PCR_ARCH_300; else if (cpu_has_feature(CPU_FTR_ARCH_207S)) host_pcr_bit = PCR_ARCH_207; @@ -375,6 +380,9 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) case PVR_ARCH_300: guest_pcr_bit = PCR_ARCH_300; break; + case PVR_ARCH_31: + guest_pcr_bit = PCR_ARCH_31; + break; default: return -EINVAL; } @@ -2355,7 +2363,7 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) * to trap and then we emulate them. */ vcpu->arch.hfscr = HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB | - HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP; + HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP | HFSCR_PREFIX; if (cpu_has_feature(CPU_FTR_HVMODE)) { vcpu->arch.hfscr &= mfspr(SPRN_HFSCR); if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) @@ -4552,16 +4560,14 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, switch (change) { case KVM_MR_CREATE: - if (kvmppc_uvmem_slot_init(kvm, new)) - return; - uv_register_mem_slot(kvm->arch.lpid, - new->base_gfn << PAGE_SHIFT, - new->npages * PAGE_SIZE, - 0, new->id); + /* + * @TODO kvmppc_uvmem_memslot_create() can fail and + * return error. Fix this. + */ + kvmppc_uvmem_memslot_create(kvm, new); break; case KVM_MR_DELETE: - uv_unregister_mem_slot(kvm->arch.lpid, old->id); - kvmppc_uvmem_slot_free(kvm, old); + kvmppc_uvmem_memslot_delete(kvm, old); break; default: /* TODO: Handle KVM_MR_MOVE */ diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 2c849a65db77..6822d23a2da4 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -233,20 +233,21 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) /* copy parameters in */ hv_ptr = kvmppc_get_gpr(vcpu, 4); + regs_ptr = kvmppc_get_gpr(vcpu, 5); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); err = kvm_vcpu_read_guest(vcpu, hv_ptr, &l2_hv, - sizeof(struct hv_guest_state)); + sizeof(struct hv_guest_state)) || + kvm_vcpu_read_guest(vcpu, regs_ptr, &l2_regs, + sizeof(struct pt_regs)); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (err) return H_PARAMETER; + if (kvmppc_need_byteswap(vcpu)) byteswap_hv_regs(&l2_hv); if (l2_hv.version != HV_GUEST_STATE_VERSION) return H_P2; - regs_ptr = kvmppc_get_gpr(vcpu, 5); - err = kvm_vcpu_read_guest(vcpu, regs_ptr, &l2_regs, - sizeof(struct pt_regs)); - if (err) - return H_PARAMETER; if (kvmppc_need_byteswap(vcpu)) byteswap_pt_regs(&l2_regs); if (l2_hv.vcpu_token >= NR_CPUS) @@ -323,12 +324,12 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) byteswap_hv_regs(&l2_hv); byteswap_pt_regs(&l2_regs); } + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); err = kvm_vcpu_write_guest(vcpu, hv_ptr, &l2_hv, - sizeof(struct hv_guest_state)); - if (err) - return H_AUTHORITY; - err = kvm_vcpu_write_guest(vcpu, regs_ptr, &l2_regs, + sizeof(struct hv_guest_state)) || + kvm_vcpu_write_guest(vcpu, regs_ptr, &l2_regs, sizeof(struct pt_regs)); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (err) return H_AUTHORITY; @@ -508,12 +509,16 @@ long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu) goto not_found; /* Write what was loaded into our buffer back to the L1 guest */ + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); rc = kvm_vcpu_write_guest(vcpu, gp_to, buf, n); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (rc) goto not_found; } else { /* Load the data to be stored from the L1 guest into our buf */ + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); rc = kvm_vcpu_read_guest(vcpu, gp_from, buf, n); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (rc) goto not_found; @@ -548,9 +553,12 @@ static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp) ret = -EFAULT; ptbl_addr = (kvm->arch.l1_ptcr & PRTB_MASK) + (gp->l1_lpid << 4); - if (gp->l1_lpid < (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 8))) + if (gp->l1_lpid < (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 8))) { + int srcu_idx = srcu_read_lock(&kvm->srcu); ret = kvm_read_guest(kvm, ptbl_addr, &ptbl_entry, sizeof(ptbl_entry)); + srcu_read_unlock(&kvm->srcu, srcu_idx); + } if (ret) { gp->l1_gr_to_hr = 0; gp->process_table = 0; diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 6850bd04bcb9..7705d5557239 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -93,12 +93,133 @@ #include <asm/ultravisor.h> #include <asm/mman.h> #include <asm/kvm_ppc.h> +#include <asm/kvm_book3s_uvmem.h> static struct dev_pagemap kvmppc_uvmem_pgmap; static unsigned long *kvmppc_uvmem_bitmap; static DEFINE_SPINLOCK(kvmppc_uvmem_bitmap_lock); -#define KVMPPC_UVMEM_PFN (1UL << 63) +/* + * States of a GFN + * --------------- + * The GFN can be in one of the following states. + * + * (a) Secure - The GFN is secure. The GFN is associated with + * a Secure VM, the contents of the GFN is not accessible + * to the Hypervisor. This GFN can be backed by a secure-PFN, + * or can be backed by a normal-PFN with contents encrypted. + * The former is true when the GFN is paged-in into the + * ultravisor. The latter is true when the GFN is paged-out + * of the ultravisor. + * + * (b) Shared - The GFN is shared. The GFN is associated with a + * a secure VM. The contents of the GFN is accessible to + * Hypervisor. This GFN is backed by a normal-PFN and its + * content is un-encrypted. + * + * (c) Normal - The GFN is a normal. The GFN is associated with + * a normal VM. The contents of the GFN is accesible to + * the Hypervisor. Its content is never encrypted. + * + * States of a VM. + * --------------- + * + * Normal VM: A VM whose contents are always accessible to + * the hypervisor. All its GFNs are normal-GFNs. + * + * Secure VM: A VM whose contents are not accessible to the + * hypervisor without the VM's consent. Its GFNs are + * either Shared-GFN or Secure-GFNs. + * + * Transient VM: A Normal VM that is transitioning to secure VM. + * The transition starts on successful return of + * H_SVM_INIT_START, and ends on successful return + * of H_SVM_INIT_DONE. This transient VM, can have GFNs + * in any of the three states; i.e Secure-GFN, Shared-GFN, + * and Normal-GFN. The VM never executes in this state + * in supervisor-mode. + * + * Memory slot State. + * ----------------------------- + * The state of a memory slot mirrors the state of the + * VM the memory slot is associated with. + * + * VM State transition. + * -------------------- + * + * A VM always starts in Normal Mode. + * + * H_SVM_INIT_START moves the VM into transient state. During this + * time the Ultravisor may request some of its GFNs to be shared or + * secured. So its GFNs can be in one of the three GFN states. + * + * H_SVM_INIT_DONE moves the VM entirely from transient state to + * secure-state. At this point any left-over normal-GFNs are + * transitioned to Secure-GFN. + * + * H_SVM_INIT_ABORT moves the transient VM back to normal VM. + * All its GFNs are moved to Normal-GFNs. + * + * UV_TERMINATE transitions the secure-VM back to normal-VM. All + * the secure-GFN and shared-GFNs are tranistioned to normal-GFN + * Note: The contents of the normal-GFN is undefined at this point. + * + * GFN state implementation: + * ------------------------- + * + * Secure GFN is associated with a secure-PFN; also called uvmem_pfn, + * when the GFN is paged-in. Its pfn[] has KVMPPC_GFN_UVMEM_PFN flag + * set, and contains the value of the secure-PFN. + * It is associated with a normal-PFN; also called mem_pfn, when + * the GFN is pagedout. Its pfn[] has KVMPPC_GFN_MEM_PFN flag set. + * The value of the normal-PFN is not tracked. + * + * Shared GFN is associated with a normal-PFN. Its pfn[] has + * KVMPPC_UVMEM_SHARED_PFN flag set. The value of the normal-PFN + * is not tracked. + * + * Normal GFN is associated with normal-PFN. Its pfn[] has + * no flag set. The value of the normal-PFN is not tracked. + * + * Life cycle of a GFN + * -------------------- + * + * -------------------------------------------------------------- + * | | Share | Unshare | SVM |H_SVM_INIT_DONE| + * | |operation |operation | abort/ | | + * | | | | terminate | | + * ------------------------------------------------------------- + * | | | | | | + * | Secure | Shared | Secure |Normal |Secure | + * | | | | | | + * | Shared | Shared | Secure |Normal |Shared | + * | | | | | | + * | Normal | Shared | Secure |Normal |Secure | + * -------------------------------------------------------------- + * + * Life cycle of a VM + * -------------------- + * + * -------------------------------------------------------------------- + * | | start | H_SVM_ |H_SVM_ |H_SVM_ |UV_SVM_ | + * | | VM |INIT_START|INIT_DONE|INIT_ABORT |TERMINATE | + * | | | | | | | + * --------- ---------------------------------------------------------- + * | | | | | | | + * | Normal | Normal | Transient|Error |Error |Normal | + * | | | | | | | + * | Secure | Error | Error |Error |Error |Normal | + * | | | | | | | + * |Transient| N/A | Error |Secure |Normal |Normal | + * -------------------------------------------------------------------- + */ + +#define KVMPPC_GFN_UVMEM_PFN (1UL << 63) +#define KVMPPC_GFN_MEM_PFN (1UL << 62) +#define KVMPPC_GFN_SHARED (1UL << 61) +#define KVMPPC_GFN_SECURE (KVMPPC_GFN_UVMEM_PFN | KVMPPC_GFN_MEM_PFN) +#define KVMPPC_GFN_FLAG_MASK (KVMPPC_GFN_SECURE | KVMPPC_GFN_SHARED) +#define KVMPPC_GFN_PFN_MASK (~KVMPPC_GFN_FLAG_MASK) struct kvmppc_uvmem_slot { struct list_head list; @@ -106,11 +227,11 @@ struct kvmppc_uvmem_slot { unsigned long base_pfn; unsigned long *pfns; }; - struct kvmppc_uvmem_page_pvt { struct kvm *kvm; unsigned long gpa; bool skip_page_out; + bool remove_gfn; }; bool kvmppc_uvmem_available(void) @@ -163,8 +284,8 @@ void kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot) mutex_unlock(&kvm->arch.uvmem_lock); } -static void kvmppc_uvmem_pfn_insert(unsigned long gfn, unsigned long uvmem_pfn, - struct kvm *kvm) +static void kvmppc_mark_gfn(unsigned long gfn, struct kvm *kvm, + unsigned long flag, unsigned long uvmem_pfn) { struct kvmppc_uvmem_slot *p; @@ -172,24 +293,41 @@ static void kvmppc_uvmem_pfn_insert(unsigned long gfn, unsigned long uvmem_pfn, if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) { unsigned long index = gfn - p->base_pfn; - p->pfns[index] = uvmem_pfn | KVMPPC_UVMEM_PFN; + if (flag == KVMPPC_GFN_UVMEM_PFN) + p->pfns[index] = uvmem_pfn | flag; + else + p->pfns[index] = flag; return; } } } -static void kvmppc_uvmem_pfn_remove(unsigned long gfn, struct kvm *kvm) +/* mark the GFN as secure-GFN associated with @uvmem pfn device-PFN. */ +static void kvmppc_gfn_secure_uvmem_pfn(unsigned long gfn, + unsigned long uvmem_pfn, struct kvm *kvm) { - struct kvmppc_uvmem_slot *p; + kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_UVMEM_PFN, uvmem_pfn); +} - list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) { - if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) { - p->pfns[gfn - p->base_pfn] = 0; - return; - } - } +/* mark the GFN as secure-GFN associated with a memory-PFN. */ +static void kvmppc_gfn_secure_mem_pfn(unsigned long gfn, struct kvm *kvm) +{ + kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_MEM_PFN, 0); +} + +/* mark the GFN as a shared GFN. */ +static void kvmppc_gfn_shared(unsigned long gfn, struct kvm *kvm) +{ + kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_SHARED, 0); +} + +/* mark the GFN as a non-existent GFN. */ +static void kvmppc_gfn_remove(unsigned long gfn, struct kvm *kvm) +{ + kvmppc_mark_gfn(gfn, kvm, 0, 0); } +/* return true, if the GFN is a secure-GFN backed by a secure-PFN */ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm, unsigned long *uvmem_pfn) { @@ -199,10 +337,10 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm, if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) { unsigned long index = gfn - p->base_pfn; - if (p->pfns[index] & KVMPPC_UVMEM_PFN) { + if (p->pfns[index] & KVMPPC_GFN_UVMEM_PFN) { if (uvmem_pfn) *uvmem_pfn = p->pfns[index] & - ~KVMPPC_UVMEM_PFN; + KVMPPC_GFN_PFN_MASK; return true; } else return false; @@ -211,10 +349,114 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm, return false; } +/* + * starting from *gfn search for the next available GFN that is not yet + * transitioned to a secure GFN. return the value of that GFN in *gfn. If a + * GFN is found, return true, else return false + * + * Must be called with kvm->arch.uvmem_lock held. + */ +static bool kvmppc_next_nontransitioned_gfn(const struct kvm_memory_slot *memslot, + struct kvm *kvm, unsigned long *gfn) +{ + struct kvmppc_uvmem_slot *p; + bool ret = false; + unsigned long i; + + list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) + if (*gfn >= p->base_pfn && *gfn < p->base_pfn + p->nr_pfns) + break; + if (!p) + return ret; + /* + * The code below assumes, one to one correspondence between + * kvmppc_uvmem_slot and memslot. + */ + for (i = *gfn; i < p->base_pfn + p->nr_pfns; i++) { + unsigned long index = i - p->base_pfn; + + if (!(p->pfns[index] & KVMPPC_GFN_FLAG_MASK)) { + *gfn = i; + ret = true; + break; + } + } + return ret; +} + +static int kvmppc_memslot_page_merge(struct kvm *kvm, + const struct kvm_memory_slot *memslot, bool merge) +{ + unsigned long gfn = memslot->base_gfn; + unsigned long end, start = gfn_to_hva(kvm, gfn); + int ret = 0; + struct vm_area_struct *vma; + int merge_flag = (merge) ? MADV_MERGEABLE : MADV_UNMERGEABLE; + + if (kvm_is_error_hva(start)) + return H_STATE; + + end = start + (memslot->npages << PAGE_SHIFT); + + mmap_write_lock(kvm->mm); + do { + vma = find_vma_intersection(kvm->mm, start, end); + if (!vma) { + ret = H_STATE; + break; + } + ret = ksm_madvise(vma, vma->vm_start, vma->vm_end, + merge_flag, &vma->vm_flags); + if (ret) { + ret = H_STATE; + break; + } + start = vma->vm_end; + } while (end > vma->vm_end); + + mmap_write_unlock(kvm->mm); + return ret; +} + +static void __kvmppc_uvmem_memslot_delete(struct kvm *kvm, + const struct kvm_memory_slot *memslot) +{ + uv_unregister_mem_slot(kvm->arch.lpid, memslot->id); + kvmppc_uvmem_slot_free(kvm, memslot); + kvmppc_memslot_page_merge(kvm, memslot, true); +} + +static int __kvmppc_uvmem_memslot_create(struct kvm *kvm, + const struct kvm_memory_slot *memslot) +{ + int ret = H_PARAMETER; + + if (kvmppc_memslot_page_merge(kvm, memslot, false)) + return ret; + + if (kvmppc_uvmem_slot_init(kvm, memslot)) + goto out1; + + ret = uv_register_mem_slot(kvm->arch.lpid, + memslot->base_gfn << PAGE_SHIFT, + memslot->npages * PAGE_SIZE, + 0, memslot->id); + if (ret < 0) { + ret = H_PARAMETER; + goto out; + } + return 0; +out: + kvmppc_uvmem_slot_free(kvm, memslot); +out1: + kvmppc_memslot_page_merge(kvm, memslot, true); + return ret; +} + unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) { struct kvm_memslots *slots; - struct kvm_memory_slot *memslot; + struct kvm_memory_slot *memslot, *m; int ret = H_SUCCESS; int srcu_idx; @@ -232,35 +474,117 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) return H_AUTHORITY; srcu_idx = srcu_read_lock(&kvm->srcu); + + /* register the memslot */ slots = kvm_memslots(kvm); kvm_for_each_memslot(memslot, slots) { - if (kvmppc_uvmem_slot_init(kvm, memslot)) { - ret = H_PARAMETER; - goto out; - } - ret = uv_register_mem_slot(kvm->arch.lpid, - memslot->base_gfn << PAGE_SHIFT, - memslot->npages * PAGE_SIZE, - 0, memslot->id); - if (ret < 0) { - kvmppc_uvmem_slot_free(kvm, memslot); - ret = H_PARAMETER; - goto out; + ret = __kvmppc_uvmem_memslot_create(kvm, memslot); + if (ret) + break; + } + + if (ret) { + slots = kvm_memslots(kvm); + kvm_for_each_memslot(m, slots) { + if (m == memslot) + break; + __kvmppc_uvmem_memslot_delete(kvm, memslot); } } -out: + srcu_read_unlock(&kvm->srcu, srcu_idx); return ret; } -unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) +/* + * Provision a new page on HV side and copy over the contents + * from secure memory using UV_PAGE_OUT uvcall. + * Caller must held kvm->arch.uvmem_lock. + */ +static int __kvmppc_svm_page_out(struct vm_area_struct *vma, + unsigned long start, + unsigned long end, unsigned long page_shift, + struct kvm *kvm, unsigned long gpa) { - if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) - return H_UNSUPPORTED; + unsigned long src_pfn, dst_pfn = 0; + struct migrate_vma mig; + struct page *dpage, *spage; + struct kvmppc_uvmem_page_pvt *pvt; + unsigned long pfn; + int ret = U_SUCCESS; - kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE; - pr_info("LPID %d went secure\n", kvm->arch.lpid); - return H_SUCCESS; + memset(&mig, 0, sizeof(mig)); + mig.vma = vma; + mig.start = start; + mig.end = end; + mig.src = &src_pfn; + mig.dst = &dst_pfn; + mig.pgmap_owner = &kvmppc_uvmem_pgmap; + mig.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; + + /* The requested page is already paged-out, nothing to do */ + if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL)) + return ret; + + ret = migrate_vma_setup(&mig); + if (ret) + return -1; + + spage = migrate_pfn_to_page(*mig.src); + if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE)) + goto out_finalize; + + if (!is_zone_device_page(spage)) + goto out_finalize; + + dpage = alloc_page_vma(GFP_HIGHUSER, vma, start); + if (!dpage) { + ret = -1; + goto out_finalize; + } + + lock_page(dpage); + pvt = spage->zone_device_data; + pfn = page_to_pfn(dpage); + + /* + * This function is used in two cases: + * - When HV touches a secure page, for which we do UV_PAGE_OUT + * - When a secure page is converted to shared page, we *get* + * the page to essentially unmap the device page. In this + * case we skip page-out. + */ + if (!pvt->skip_page_out) + ret = uv_page_out(kvm->arch.lpid, pfn << page_shift, + gpa, 0, page_shift); + + if (ret == U_SUCCESS) + *mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED; + else { + unlock_page(dpage); + __free_page(dpage); + goto out_finalize; + } + + migrate_vma_pages(&mig); + +out_finalize: + migrate_vma_finalize(&mig); + return ret; +} + +static inline int kvmppc_svm_page_out(struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long page_shift, + struct kvm *kvm, unsigned long gpa) +{ + int ret; + + mutex_lock(&kvm->arch.uvmem_lock); + ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa); + mutex_unlock(&kvm->arch.uvmem_lock); + + return ret; } /* @@ -271,33 +595,53 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) * fault on them, do fault time migration to replace the device PTEs in * QEMU page table with normal PTEs from newly allocated pages. */ -void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, +void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot, struct kvm *kvm, bool skip_page_out) { int i; struct kvmppc_uvmem_page_pvt *pvt; - unsigned long pfn, uvmem_pfn; - unsigned long gfn = free->base_gfn; + struct page *uvmem_page; + struct vm_area_struct *vma = NULL; + unsigned long uvmem_pfn, gfn; + unsigned long addr; - for (i = free->npages; i; --i, ++gfn) { - struct page *uvmem_page; + mmap_read_lock(kvm->mm); + + addr = slot->userspace_addr; + + gfn = slot->base_gfn; + for (i = slot->npages; i; --i, ++gfn, addr += PAGE_SIZE) { + + /* Fetch the VMA if addr is not in the latest fetched one */ + if (!vma || addr >= vma->vm_end) { + vma = find_vma_intersection(kvm->mm, addr, addr+1); + if (!vma) { + pr_err("Can't find VMA for gfn:0x%lx\n", gfn); + break; + } + } mutex_lock(&kvm->arch.uvmem_lock); - if (!kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) { - mutex_unlock(&kvm->arch.uvmem_lock); - continue; + + if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) { + uvmem_page = pfn_to_page(uvmem_pfn); + pvt = uvmem_page->zone_device_data; + pvt->skip_page_out = skip_page_out; + pvt->remove_gfn = true; + + if (__kvmppc_svm_page_out(vma, addr, addr + PAGE_SIZE, + PAGE_SHIFT, kvm, pvt->gpa)) + pr_err("Can't page out gpa:0x%lx addr:0x%lx\n", + pvt->gpa, addr); + } else { + /* Remove the shared flag if any */ + kvmppc_gfn_remove(gfn, kvm); } - uvmem_page = pfn_to_page(uvmem_pfn); - pvt = uvmem_page->zone_device_data; - pvt->skip_page_out = skip_page_out; mutex_unlock(&kvm->arch.uvmem_lock); - - pfn = gfn_to_pfn(kvm, gfn); - if (is_error_noslot_pfn(pfn)) - continue; - kvm_release_pfn_clean(pfn); } + + mmap_read_unlock(kvm->mm); } unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm) @@ -360,7 +704,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) goto out_clear; uvmem_pfn = bit + pfn_first; - kvmppc_uvmem_pfn_insert(gpa >> PAGE_SHIFT, uvmem_pfn, kvm); + kvmppc_gfn_secure_uvmem_pfn(gpa >> PAGE_SHIFT, uvmem_pfn, kvm); pvt->gpa = gpa; pvt->kvm = kvm; @@ -379,13 +723,14 @@ out: } /* - * Alloc a PFN from private device memory pool and copy page from normal - * memory to secure memory using UV_PAGE_IN uvcall. + * Alloc a PFN from private device memory pool. If @pagein is true, + * copy page from normal memory to secure memory using UV_PAGE_IN uvcall. */ -static int -kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start, - unsigned long end, unsigned long gpa, struct kvm *kvm, - unsigned long page_shift, bool *downgrade) +static int kvmppc_svm_page_in(struct vm_area_struct *vma, + unsigned long start, + unsigned long end, unsigned long gpa, struct kvm *kvm, + unsigned long page_shift, + bool pagein) { unsigned long src_pfn, dst_pfn = 0; struct migrate_vma mig; @@ -402,18 +747,6 @@ kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start, mig.dst = &dst_pfn; mig.flags = MIGRATE_VMA_SELECT_SYSTEM; - /* - * We come here with mmap_lock write lock held just for - * ksm_madvise(), otherwise we only need read mmap_lock. - * Hence downgrade to read lock once ksm_madvise() is done. - */ - ret = ksm_madvise(vma, vma->vm_start, vma->vm_end, - MADV_UNMERGEABLE, &vma->vm_flags); - mmap_write_downgrade(kvm->mm); - *downgrade = true; - if (ret) - return ret; - ret = migrate_vma_setup(&mig); if (ret) return ret; @@ -429,11 +762,16 @@ kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start, goto out_finalize; } - pfn = *mig.src >> MIGRATE_PFN_SHIFT; - spage = migrate_pfn_to_page(*mig.src); - if (spage) - uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0, - page_shift); + if (pagein) { + pfn = *mig.src >> MIGRATE_PFN_SHIFT; + spage = migrate_pfn_to_page(*mig.src); + if (spage) { + ret = uv_page_in(kvm->arch.lpid, pfn << page_shift, + gpa, 0, page_shift); + if (ret) + goto out_finalize; + } + } *mig.dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; migrate_vma_pages(&mig); @@ -442,6 +780,80 @@ out_finalize: return ret; } +static int kvmppc_uv_migrate_mem_slot(struct kvm *kvm, + const struct kvm_memory_slot *memslot) +{ + unsigned long gfn = memslot->base_gfn; + struct vm_area_struct *vma; + unsigned long start, end; + int ret = 0; + + mmap_read_lock(kvm->mm); + mutex_lock(&kvm->arch.uvmem_lock); + while (kvmppc_next_nontransitioned_gfn(memslot, kvm, &gfn)) { + ret = H_STATE; + start = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(start)) + break; + + end = start + (1UL << PAGE_SHIFT); + vma = find_vma_intersection(kvm->mm, start, end); + if (!vma || vma->vm_start > start || vma->vm_end < end) + break; + + ret = kvmppc_svm_page_in(vma, start, end, + (gfn << PAGE_SHIFT), kvm, PAGE_SHIFT, false); + if (ret) { + ret = H_STATE; + break; + } + + /* relinquish the cpu if needed */ + cond_resched(); + } + mutex_unlock(&kvm->arch.uvmem_lock); + mmap_read_unlock(kvm->mm); + return ret; +} + +unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int srcu_idx; + long ret = H_SUCCESS; + + if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) + return H_UNSUPPORTED; + + /* migrate any unmoved normal pfn to device pfns*/ + srcu_idx = srcu_read_lock(&kvm->srcu); + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) { + ret = kvmppc_uv_migrate_mem_slot(kvm, memslot); + if (ret) { + /* + * The pages will remain transitioned. + * Its the callers responsibility to + * terminate the VM, which will undo + * all state of the VM. Till then + * this VM is in a erroneous state. + * Its KVMPPC_SECURE_INIT_DONE will + * remain unset. + */ + ret = H_STATE; + goto out; + } + } + + kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE; + pr_info("LPID %d went secure\n", kvm->arch.lpid); + +out: + srcu_read_unlock(&kvm->srcu, srcu_idx); + return ret; +} + /* * Shares the page with HV, thus making it a normal page. * @@ -451,8 +863,8 @@ out_finalize: * In the former case, uses dev_pagemap_ops.migrate_to_ram handler * to unmap the device page from QEMU's page tables. */ -static unsigned long -kvmppc_share_page(struct kvm *kvm, unsigned long gpa, unsigned long page_shift) +static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa, + unsigned long page_shift) { int ret = H_PARAMETER; @@ -469,6 +881,11 @@ kvmppc_share_page(struct kvm *kvm, unsigned long gpa, unsigned long page_shift) uvmem_page = pfn_to_page(uvmem_pfn); pvt = uvmem_page->zone_device_data; pvt->skip_page_out = true; + /* + * do not drop the GFN. It is a valid GFN + * that is transitioned to a shared GFN. + */ + pvt->remove_gfn = false; } retry: @@ -482,12 +899,16 @@ retry: uvmem_page = pfn_to_page(uvmem_pfn); pvt = uvmem_page->zone_device_data; pvt->skip_page_out = true; + pvt->remove_gfn = false; /* it continues to be a valid GFN */ kvm_release_pfn_clean(pfn); goto retry; } - if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0, page_shift)) + if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0, + page_shift)) { + kvmppc_gfn_shared(gfn, kvm); ret = H_SUCCESS; + } kvm_release_pfn_clean(pfn); mutex_unlock(&kvm->arch.uvmem_lock); out: @@ -501,11 +922,10 @@ out: * H_PAGE_IN_SHARED flag makes the page shared which means that the same * memory in is visible from both UV and HV. */ -unsigned long -kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa, - unsigned long flags, unsigned long page_shift) +unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa, + unsigned long flags, + unsigned long page_shift) { - bool downgrade = false; unsigned long start, end; struct vm_area_struct *vma; int srcu_idx; @@ -526,7 +946,7 @@ kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa, ret = H_PARAMETER; srcu_idx = srcu_read_lock(&kvm->srcu); - mmap_write_lock(kvm->mm); + mmap_read_lock(kvm->mm); start = gfn_to_hva(kvm, gfn); if (kvm_is_error_hva(start)) @@ -542,97 +962,20 @@ kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa, if (!vma || vma->vm_start > start || vma->vm_end < end) goto out_unlock; - if (!kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift, - &downgrade)) - ret = H_SUCCESS; + if (kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift, + true)) + goto out_unlock; + + ret = H_SUCCESS; + out_unlock: mutex_unlock(&kvm->arch.uvmem_lock); out: - if (downgrade) - mmap_read_unlock(kvm->mm); - else - mmap_write_unlock(kvm->mm); + mmap_read_unlock(kvm->mm); srcu_read_unlock(&kvm->srcu, srcu_idx); return ret; } -/* - * Provision a new page on HV side and copy over the contents - * from secure memory using UV_PAGE_OUT uvcall. - */ -static int -kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start, - unsigned long end, unsigned long page_shift, - struct kvm *kvm, unsigned long gpa) -{ - unsigned long src_pfn, dst_pfn = 0; - struct migrate_vma mig; - struct page *dpage, *spage; - struct kvmppc_uvmem_page_pvt *pvt; - unsigned long pfn; - int ret = U_SUCCESS; - - memset(&mig, 0, sizeof(mig)); - mig.vma = vma; - mig.start = start; - mig.end = end; - mig.src = &src_pfn; - mig.dst = &dst_pfn; - mig.pgmap_owner = &kvmppc_uvmem_pgmap; - mig.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; - - mutex_lock(&kvm->arch.uvmem_lock); - /* The requested page is already paged-out, nothing to do */ - if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL)) - goto out; - - ret = migrate_vma_setup(&mig); - if (ret) - goto out; - - spage = migrate_pfn_to_page(*mig.src); - if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE)) - goto out_finalize; - - if (!is_zone_device_page(spage)) - goto out_finalize; - - dpage = alloc_page_vma(GFP_HIGHUSER, vma, start); - if (!dpage) { - ret = -1; - goto out_finalize; - } - - lock_page(dpage); - pvt = spage->zone_device_data; - pfn = page_to_pfn(dpage); - - /* - * This function is used in two cases: - * - When HV touches a secure page, for which we do UV_PAGE_OUT - * - When a secure page is converted to shared page, we *get* - * the page to essentially unmap the device page. In this - * case we skip page-out. - */ - if (!pvt->skip_page_out) - ret = uv_page_out(kvm->arch.lpid, pfn << page_shift, - gpa, 0, page_shift); - - if (ret == U_SUCCESS) - *mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED; - else { - unlock_page(dpage); - __free_page(dpage); - goto out_finalize; - } - - migrate_vma_pages(&mig); -out_finalize: - migrate_vma_finalize(&mig); -out: - mutex_unlock(&kvm->arch.uvmem_lock); - return ret; -} /* * Fault handler callback that gets called when HV touches any page that @@ -657,7 +1000,8 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf) /* * Release the device PFN back to the pool * - * Gets called when secure page becomes a normal page during H_SVM_PAGE_OUT. + * Gets called when secure GFN tranistions from a secure-PFN + * to a normal PFN during H_SVM_PAGE_OUT. * Gets called with kvm->arch.uvmem_lock held. */ static void kvmppc_uvmem_page_free(struct page *page) @@ -672,7 +1016,10 @@ static void kvmppc_uvmem_page_free(struct page *page) pvt = page->zone_device_data; page->zone_device_data = NULL; - kvmppc_uvmem_pfn_remove(pvt->gpa >> PAGE_SHIFT, pvt->kvm); + if (pvt->remove_gfn) + kvmppc_gfn_remove(pvt->gpa >> PAGE_SHIFT, pvt->kvm); + else + kvmppc_gfn_secure_mem_pfn(pvt->gpa >> PAGE_SHIFT, pvt->kvm); kfree(pvt); } @@ -744,6 +1091,21 @@ out: return (ret == U_SUCCESS) ? RESUME_GUEST : -EFAULT; } +int kvmppc_uvmem_memslot_create(struct kvm *kvm, const struct kvm_memory_slot *new) +{ + int ret = __kvmppc_uvmem_memslot_create(kvm, new); + + if (!ret) + ret = kvmppc_uv_migrate_mem_slot(kvm, new); + + return ret; +} + +void kvmppc_uvmem_memslot_delete(struct kvm *kvm, const struct kvm_memory_slot *old) +{ + __kvmppc_uvmem_memslot_delete(kvm, old); +} + static u64 kvmppc_get_secmem_size(void) { struct device_node *np; diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S index 607a9b99c334..25a3679fb590 100644 --- a/arch/powerpc/kvm/book3s_interrupts.S +++ b/arch/powerpc/kvm/book3s_interrupts.S @@ -55,8 +55,7 @@ ****************************************************************************/ /* Registers: - * r3: kvm_run pointer - * r4: vcpu pointer + * r3: vcpu pointer */ _GLOBAL(__kvmppc_vcpu_run) @@ -68,8 +67,8 @@ kvm_start_entry: /* Save host state to the stack */ PPC_STLU r1, -SWITCH_FRAME_SIZE(r1) - /* Save r3 (kvm_run) and r4 (vcpu) */ - SAVE_2GPRS(3, r1) + /* Save r3 (vcpu) */ + SAVE_GPR(3, r1) /* Save non-volatile registers (r14 - r31) */ SAVE_NVGPRS(r1) @@ -82,47 +81,46 @@ kvm_start_entry: PPC_STL r0, _LINK(r1) /* Load non-volatile guest state from the vcpu */ - VCPU_LOAD_NVGPRS(r4) + VCPU_LOAD_NVGPRS(r3) kvm_start_lightweight: /* Copy registers into shadow vcpu so we can access them in real mode */ - mr r3, r4 bl FUNC(kvmppc_copy_to_svcpu) nop - REST_GPR(4, r1) + REST_GPR(3, r1) #ifdef CONFIG_PPC_BOOK3S_64 /* Get the dcbz32 flag */ - PPC_LL r3, VCPU_HFLAGS(r4) - rldicl r3, r3, 0, 63 /* r3 &= 1 */ - stb r3, HSTATE_RESTORE_HID5(r13) + PPC_LL r0, VCPU_HFLAGS(r3) + rldicl r0, r0, 0, 63 /* r3 &= 1 */ + stb r0, HSTATE_RESTORE_HID5(r13) /* Load up guest SPRG3 value, since it's user readable */ - lwz r3, VCPU_SHAREDBE(r4) - cmpwi r3, 0 - ld r5, VCPU_SHARED(r4) + lbz r4, VCPU_SHAREDBE(r3) + cmpwi r4, 0 + ld r5, VCPU_SHARED(r3) beq sprg3_little_endian sprg3_big_endian: #ifdef __BIG_ENDIAN__ - ld r3, VCPU_SHARED_SPRG3(r5) + ld r4, VCPU_SHARED_SPRG3(r5) #else addi r5, r5, VCPU_SHARED_SPRG3 - ldbrx r3, 0, r5 + ldbrx r4, 0, r5 #endif b after_sprg3_load sprg3_little_endian: #ifdef __LITTLE_ENDIAN__ - ld r3, VCPU_SHARED_SPRG3(r5) + ld r4, VCPU_SHARED_SPRG3(r5) #else addi r5, r5, VCPU_SHARED_SPRG3 - ldbrx r3, 0, r5 + ldbrx r4, 0, r5 #endif after_sprg3_load: - mtspr SPRN_SPRG3, r3 + mtspr SPRN_SPRG3, r4 #endif /* CONFIG_PPC_BOOK3S_64 */ - PPC_LL r4, VCPU_SHADOW_MSR(r4) /* get shadow_msr */ + PPC_LL r4, VCPU_SHADOW_MSR(r3) /* get shadow_msr */ /* Jump to segment patching handler and into our guest */ bl FUNC(kvmppc_entry_trampoline) @@ -146,7 +144,7 @@ after_sprg3_load: * */ - PPC_LL r3, GPR4(r1) /* vcpu pointer */ + PPC_LL r3, GPR3(r1) /* vcpu pointer */ /* * kvmppc_copy_from_svcpu can clobber volatile registers, save @@ -169,7 +167,7 @@ after_sprg3_load: #endif /* CONFIG_PPC_BOOK3S_64 */ /* R7 = vcpu */ - PPC_LL r7, GPR4(r1) + PPC_LL r7, GPR3(r1) PPC_STL r14, VCPU_GPR(R14)(r7) PPC_STL r15, VCPU_GPR(R15)(r7) @@ -190,11 +188,11 @@ after_sprg3_load: PPC_STL r30, VCPU_GPR(R30)(r7) PPC_STL r31, VCPU_GPR(R31)(r7) - /* Pass the exit number as 3rd argument to kvmppc_handle_exit */ - lwz r5, VCPU_TRAP(r7) + /* Pass the exit number as 2nd argument to kvmppc_handle_exit */ + lwz r4, VCPU_TRAP(r7) - /* Restore r3 (kvm_run) and r4 (vcpu) */ - REST_2GPRS(3, r1) + /* Restore r3 (vcpu) */ + REST_GPR(3, r1) bl FUNC(kvmppc_handle_exit_pr) /* If RESUME_GUEST, get back in the loop */ @@ -223,11 +221,11 @@ kvm_loop_heavyweight: PPC_LL r4, _LINK(r1) PPC_STL r4, (PPC_LR_STKOFF + SWITCH_FRAME_SIZE)(r1) - /* Load vcpu and cpu_run */ - REST_2GPRS(3, r1) + /* Load vcpu */ + REST_GPR(3, r1) /* Load non-volatile guest state from the vcpu */ - VCPU_LOAD_NVGPRS(r4) + VCPU_LOAD_NVGPRS(r3) /* Jump back into the beginning of this function */ b kvm_start_lightweight @@ -235,7 +233,7 @@ kvm_loop_heavyweight: kvm_loop_lightweight: /* We'll need the vcpu pointer */ - REST_GPR(4, r1) + REST_GPR(3, r1) /* Jump back into the beginning of this function */ b kvm_start_lightweight diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index ed12dfbf9bb5..88fac22fbf09 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1151,9 +1151,9 @@ static int kvmppc_exit_pr_progint(struct kvm_vcpu *vcpu, unsigned int exit_nr) return r; } -int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu, - unsigned int exit_nr) +int kvmppc_handle_exit_pr(struct kvm_vcpu *vcpu, unsigned int exit_nr) { + struct kvm_run *run = vcpu->run; int r = RESUME_HOST; int s; @@ -1826,12 +1826,11 @@ static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu) static int kvmppc_vcpu_run_pr(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu->run; int ret; /* Check if we can run the vcpu at all */ if (!vcpu->arch.sane) { - run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; ret = -EINVAL; goto out; } @@ -1858,7 +1857,7 @@ static int kvmppc_vcpu_run_pr(struct kvm_vcpu *vcpu) kvmppc_fix_ee_before_entry(); - ret = __kvmppc_vcpu_run(run, vcpu); + ret = __kvmppc_vcpu_run(vcpu); kvmppc_clear_debug(vcpu); diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c index 26b25994c969..c5e677508d3b 100644 --- a/arch/powerpc/kvm/book3s_rtas.c +++ b/arch/powerpc/kvm/book3s_rtas.c @@ -229,7 +229,9 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu) */ args_phys = kvmppc_get_gpr(vcpu, 4) & KVM_PAM; + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); rc = kvm_read_guest(vcpu->kvm, args_phys, &args, sizeof(args)); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (rc) goto fail; diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index c0d62a917e20..3e1c9f08e302 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -731,12 +731,11 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu) int kvmppc_vcpu_run(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu->run; int ret, s; struct debug_reg debug; if (!vcpu->arch.sane) { - run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; return -EINVAL; } @@ -778,7 +777,7 @@ int kvmppc_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.pgdir = vcpu->kvm->mm->pgd; kvmppc_fix_ee_before_entry(); - ret = __kvmppc_vcpu_run(run, vcpu); + ret = __kvmppc_vcpu_run(vcpu); /* No need for guest_exit. It's done in handle_exit. We also get here with interrupts enabled. */ @@ -982,9 +981,9 @@ static int kvmppc_resume_inst_load(struct kvm_vcpu *vcpu, * * Return value is in the form (errcode<<2 | RESUME_FLAG_HOST | RESUME_FLAG_NV) */ -int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, - unsigned int exit_nr) +int kvmppc_handle_exit(struct kvm_vcpu *vcpu, unsigned int exit_nr) { + struct kvm_run *run = vcpu->run; int r = RESUME_HOST; int s; int idx; diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S index 2e56ab5a5f55..6fa82efe833b 100644 --- a/arch/powerpc/kvm/booke_interrupts.S +++ b/arch/powerpc/kvm/booke_interrupts.S @@ -237,7 +237,7 @@ _GLOBAL(kvmppc_resume_host) /* Switch to kernel stack and jump to handler. */ LOAD_REG_ADDR(r3, kvmppc_handle_exit) mtctr r3 - lwz r3, HOST_RUN(r1) + mr r3, r4 lwz r2, HOST_R2(r1) mr r14, r4 /* Save vcpu pointer. */ @@ -337,15 +337,14 @@ heavyweight_exit: /* Registers: - * r3: kvm_run pointer - * r4: vcpu pointer + * r3: vcpu pointer */ _GLOBAL(__kvmppc_vcpu_run) stwu r1, -HOST_STACK_SIZE(r1) - stw r1, VCPU_HOST_STACK(r4) /* Save stack pointer to vcpu. */ + stw r1, VCPU_HOST_STACK(r3) /* Save stack pointer to vcpu. */ /* Save host state to stack. */ - stw r3, HOST_RUN(r1) + mr r4, r3 mflr r3 stw r3, HOST_STACK_LR(r1) mfcr r5 diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S index c577ba4b3169..8262c14fc9e6 100644 --- a/arch/powerpc/kvm/bookehv_interrupts.S +++ b/arch/powerpc/kvm/bookehv_interrupts.S @@ -434,9 +434,10 @@ _GLOBAL(kvmppc_resume_host) #endif /* Switch to kernel stack and jump to handler. */ - PPC_LL r3, HOST_RUN(r1) + mr r3, r4 mr r5, r14 /* intno */ mr r14, r4 /* Save vcpu pointer. */ + mr r4, r5 bl kvmppc_handle_exit /* Restore vcpu pointer and the nonvolatiles we used. */ @@ -525,15 +526,14 @@ heavyweight_exit: blr /* Registers: - * r3: kvm_run pointer - * r4: vcpu pointer + * r3: vcpu pointer */ _GLOBAL(__kvmppc_vcpu_run) stwu r1, -HOST_STACK_SIZE(r1) - PPC_STL r1, VCPU_HOST_STACK(r4) /* Save stack pointer to vcpu. */ + PPC_STL r1, VCPU_HOST_STACK(r3) /* Save stack pointer to vcpu. */ /* Save host state to stack. */ - PPC_STL r3, HOST_RUN(r1) + mr r4, r3 mflr r3 mfcr r5 PPC_STL r3, HOST_STACK_LR(r1) diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index d6c1069e9954..ed0c9c43d0cf 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -734,7 +734,8 @@ static int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) return 0; } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { /* kvm_unmap_hva flushes everything anyways */ kvm_unmap_hva(kvm, start); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index aaa7b62f2f82..13999123b735 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -403,7 +403,10 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, return EMULATE_DONE; } - if (kvm_read_guest(vcpu->kvm, pte.raddr, ptr, size)) + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + rc = kvm_read_guest(vcpu->kvm, pte.raddr, ptr, size); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + if (rc) return EMULATE_DO_MMIO; return EMULATE_DONE; diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index c0162911f6cb..d426eaf76bb0 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -191,10 +191,17 @@ static bool is_module_segment(unsigned long addr) { if (!IS_ENABLED(CONFIG_MODULES)) return false; +#ifdef MODULES_VADDR + if (addr < ALIGN_DOWN(MODULES_VADDR, SZ_256M)) + return false; + if (addr > ALIGN(MODULES_END, SZ_256M) - 1) + return false; +#else if (addr < ALIGN_DOWN(VMALLOC_START, SZ_256M)) return false; - if (addr >= ALIGN(VMALLOC_END, SZ_256M)) + if (addr > ALIGN(VMALLOC_END, SZ_256M) - 1) return false; +#endif return true; } diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 1478fceeb683..c663e7ba801f 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -232,6 +232,8 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags) rflags |= HPTE_R_I; else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT) rflags |= (HPTE_R_I | HPTE_R_G); + else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO) + rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M); else /* * Add memory coherence if cache inhibited is not set @@ -1116,7 +1118,8 @@ void hash__early_init_mmu_secondary(void) tlbiel_all(); #ifdef CONFIG_PPC_MEM_KEYS - mtspr(SPRN_UAMOR, default_uamor); + if (mmu_has_feature(MMU_FTR_PKEY)) + mtspr(SPRN_UAMOR, default_uamor); #endif } #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c index 69a6b87f2bb4..b1d091a97611 100644 --- a/arch/powerpc/mm/book3s64/pkeys.c +++ b/arch/powerpc/mm/book3s64/pkeys.c @@ -73,12 +73,6 @@ static int scan_pkey_feature(void) if (early_radix_enabled()) return 0; - /* - * Only P7 and above supports SPRN_AMR update with MSR[PR] = 1 - */ - if (!early_cpu_has_feature(CPU_FTR_ARCH_206)) - return 0; - ret = of_scan_flat_dt(dt_scan_storage_keys, &pkeys_total); if (ret == 0) { /* @@ -124,6 +118,12 @@ void __init pkey_early_init_devtree(void) __builtin_popcountl(ARCH_VM_PKEY_FLAGS >> VM_PKEY_SHIFT) != (sizeof(u64) * BITS_PER_BYTE)); + /* + * Only P7 and above supports SPRN_AMR update with MSR[PR] = 1 + */ + if (!early_cpu_has_feature(CPU_FTR_ARCH_206)) + return; + /* scan the device tree for pkey feature */ pkeys_total = scan_pkey_feature(); if (!pkeys_total) diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index b83abbead4a2..8acd00178956 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -64,7 +64,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, } ret = 0; - *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0); + *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL); if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; @@ -76,11 +76,6 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, BUG(); } - if (*flt & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; - out_unlock: mmap_read_unlock(mm); return ret; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 925a7231abb3..0add963a849b 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -511,7 +511,7 @@ retry: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); major |= fault & VM_FAULT_MAJOR; @@ -537,14 +537,9 @@ retry: /* * Major/minor page fault accounting. */ - if (major) { - current->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); + if (major) cmo_account_page_fault(); - } else { - current->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); - } + return 0; } NOKPROBE_SYMBOL(__do_page_fault); diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 16d09b36fe06..78d61f97371e 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -475,7 +475,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: true_cond = COND_NE; - /* Fall through */ + fallthrough; cond_branch: /* same targets, can avoid doing the test :) */ if (filter[i].jt == filter[i].jf) { diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 78fe34986594..08643cba1494 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1557,9 +1557,16 @@ nocheck: ret = 0; out: if (has_branch_stack(event)) { - power_pmu_bhrb_enable(event); - cpuhw->bhrb_filter = ppmu->bhrb_filter_map( - event->attr.branch_sample_type); + u64 bhrb_filter = -1; + + if (ppmu->bhrb_filter_map) + bhrb_filter = ppmu->bhrb_filter_map( + event->attr.branch_sample_type); + + if (bhrb_filter != -1) { + cpuhw->bhrb_filter = bhrb_filter; + power_pmu_bhrb_enable(event); + } } perf_pmu_enable(event->pmu); @@ -1881,7 +1888,6 @@ static int power_pmu_event_init(struct perf_event *event) int n; int err; struct cpu_hw_events *cpuhw; - u64 bhrb_filter; if (!ppmu) return -ENOENT; @@ -1987,7 +1993,10 @@ static int power_pmu_event_init(struct perf_event *event) err = power_check_constraints(cpuhw, events, cflags, n + 1); if (has_branch_stack(event)) { - bhrb_filter = ppmu->bhrb_filter_map( + u64 bhrb_filter = -1; + + if (ppmu->bhrb_filter_map) + bhrb_filter = ppmu->bhrb_filter_map( event->attr.branch_sample_type); if (bhrb_filter == -1) { @@ -2141,6 +2150,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (perf_event_overflow(event, &data, regs)) power_pmu_stop(event, 0); + } else if (period) { + /* Account for interrupt in case of invalid SIAR */ + if (perf_event_account_interrupt(event)) + power_pmu_stop(event, 0); } } @@ -2323,6 +2336,7 @@ int register_power_pmu(struct power_pmu *pmu) pmu->name); power_pmu.attr_groups = ppmu->attr_groups; + power_pmu.capabilities |= (ppmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS); #ifdef MSR_HV /* diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index cdb7bfbd157e..6e7e820508df 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -1128,6 +1128,15 @@ static struct bin_attribute *if_bin_attrs[] = { NULL, }; +static struct attribute *cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group cpumask_attr_group = { + .attrs = cpumask_attrs, +}; + static struct attribute *if_attrs[] = { &dev_attr_catalog_len.attr, &dev_attr_catalog_version.attr, @@ -1135,7 +1144,6 @@ static struct attribute *if_attrs[] = { &dev_attr_sockets.attr, &dev_attr_chipspersocket.attr, &dev_attr_coresperchip.attr, - &dev_attr_cpumask.attr, NULL, }; @@ -1151,6 +1159,7 @@ static const struct attribute_group *attr_groups[] = { &event_desc_group, &event_long_desc_group, &if_group, + &cpumask_attr_group, NULL, }; diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index a45d694a5d5d..62d0b54086f8 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -1289,7 +1289,7 @@ static int trace_imc_prepare_sample(struct trace_imc_data *mem, header->misc = 0; if (cpu_has_feature(CPU_FTR_ARCH_31)) { - switch (IMC_TRACE_RECORD_VAL_HVPR(mem->val)) { + switch (IMC_TRACE_RECORD_VAL_HVPR(be64_to_cpu(READ_ONCE(mem->val)))) { case 0:/* when MSR HV and PR not set in the trace-record */ header->misc |= PERF_RECORD_MISC_GUEST_KERNEL; break; @@ -1297,7 +1297,7 @@ static int trace_imc_prepare_sample(struct trace_imc_data *mem, header->misc |= PERF_RECORD_MISC_GUEST_USER; break; case 2: /* MSR HV is 1 and PR is 0 */ - header->misc |= PERF_RECORD_MISC_HYPERVISOR; + header->misc |= PERF_RECORD_MISC_KERNEL; break; case 3: /* MSR HV is 1 and PR is 1 */ header->misc |= PERF_RECORD_MISC_USER; diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c index a213a0aa5d25..8e53f2fc3fe0 100644 --- a/arch/powerpc/perf/perf_regs.c +++ b/arch/powerpc/perf/perf_regs.c @@ -13,9 +13,11 @@ #include <asm/ptrace.h> #include <asm/perf_regs.h> +u64 PERF_REG_EXTENDED_MASK; + #define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r) -#define REG_RESERVED (~((1ULL << PERF_REG_POWERPC_MAX) - 1)) +#define REG_RESERVED (~(PERF_REG_EXTENDED_MASK | PERF_REG_PMU_MASK)) static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = { PT_REGS_OFFSET(PERF_REG_POWERPC_R0, gpr[0]), @@ -69,10 +71,36 @@ static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = { PT_REGS_OFFSET(PERF_REG_POWERPC_MMCRA, dsisr), }; +/* Function to return the extended register values */ +static u64 get_ext_regs_value(int idx) +{ + switch (idx) { + case PERF_REG_POWERPC_MMCR0: + return mfspr(SPRN_MMCR0); + case PERF_REG_POWERPC_MMCR1: + return mfspr(SPRN_MMCR1); + case PERF_REG_POWERPC_MMCR2: + return mfspr(SPRN_MMCR2); +#ifdef CONFIG_PPC64 + case PERF_REG_POWERPC_MMCR3: + return mfspr(SPRN_MMCR3); + case PERF_REG_POWERPC_SIER2: + return mfspr(SPRN_SIER2); + case PERF_REG_POWERPC_SIER3: + return mfspr(SPRN_SIER3); +#endif + default: return 0; + } +} + u64 perf_reg_value(struct pt_regs *regs, int idx) { - if (WARN_ON_ONCE(idx >= PERF_REG_POWERPC_MAX)) - return 0; + u64 perf_reg_extended_max = PERF_REG_POWERPC_MAX; + + if (cpu_has_feature(CPU_FTR_ARCH_31)) + perf_reg_extended_max = PERF_REG_MAX_ISA_31; + else if (cpu_has_feature(CPU_FTR_ARCH_300)) + perf_reg_extended_max = PERF_REG_MAX_ISA_300; if (idx == PERF_REG_POWERPC_SIER && (IS_ENABLED(CONFIG_FSL_EMB_PERF_EVENT) || @@ -85,6 +113,16 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) IS_ENABLED(CONFIG_PPC32))) return 0; + if (idx >= PERF_REG_POWERPC_MAX && idx < perf_reg_extended_max) + return get_ext_regs_value(idx); + + /* + * If the idx is referring to value beyond the + * supported registers, return 0 with a warning + */ + if (WARN_ON_ONCE(idx >= perf_reg_extended_max)) + return 0; + return regs_get_register(regs, pt_regs_offset[idx]); } diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c index f7cff7f36a1c..83148656b524 100644 --- a/arch/powerpc/perf/power10-pmu.c +++ b/arch/powerpc/perf/power10-pmu.c @@ -87,6 +87,8 @@ #define POWER10_MMCRA_IFM3 0x00000000C0000000UL #define POWER10_MMCRA_BHRB_MASK 0x00000000C0000000UL +extern u64 PERF_REG_EXTENDED_MASK; + /* Table of alternatives, sorted by column 0 */ static const unsigned int power10_event_alternatives[][MAX_ALT] = { { PM_RUN_CYC_ALT, PM_RUN_CYC }, @@ -397,6 +399,7 @@ static struct power_pmu power10_pmu = { .cache_events = &power10_cache_events, .attr_groups = power10_pmu_attr_groups, .bhrb_nr = 32, + .capabilities = PERF_PMU_CAP_EXTENDED_REGS, }; int init_power10_pmu(void) @@ -408,6 +411,9 @@ int init_power10_pmu(void) strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power10")) return -ENODEV; + /* Set the PERF_REG_EXTENDED_MASK here */ + PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_31; + rc = register_power_pmu(&power10_pmu); if (rc) return rc; diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index 05dae38b969a..2a57e93a79dc 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -90,6 +90,8 @@ enum { #define POWER9_MMCRA_IFM3 0x00000000C0000000UL #define POWER9_MMCRA_BHRB_MASK 0x00000000C0000000UL +extern u64 PERF_REG_EXTENDED_MASK; + /* Nasty Power9 specific hack */ #define PVR_POWER9_CUMULUS 0x00002000 @@ -434,6 +436,7 @@ static struct power_pmu power9_pmu = { .cache_events = &power9_cache_events, .attr_groups = power9_pmu_attr_groups, .bhrb_nr = 32, + .capabilities = PERF_PMU_CAP_EXTENDED_REGS, }; int init_power9_pmu(void) @@ -457,6 +460,9 @@ int init_power9_pmu(void) } } + /* Set the PERF_REG_EXTENDED_MASK here */ + PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_300; + rc = register_power_pmu(&power9_pmu); if (rc) return rc; diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 87737ec86d39..1dc9d3c81872 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -36,7 +36,7 @@ config PPC_BOOK3S_6xx select PPC_HAVE_PMU_SUPPORT select PPC_HAVE_KUEP select PPC_HAVE_KUAP - select HAVE_ARCH_VMAP_STACK + select HAVE_ARCH_VMAP_STACK if !ADB_PMU config PPC_BOOK3S_601 bool "PowerPC 601" diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 77513a80cef9..345ab062b21a 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -1223,7 +1223,7 @@ static void __init pnv_probe_idle_states(void) return; } - if (pvr_version_is(PVR_POWER9)) + if (cpu_has_feature(CPU_FTR_ARCH_300)) pnv_power9_idle_init(); for (i = 0; i < nr_pnv_idle_states; i++) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index c9c25fb0783c..023a4f987bb2 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2705,7 +2705,7 @@ void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe) struct iommu_table *tbl = pe->table_group.tables[0]; int64_t rc; - if (pe->dma_setup_done) + if (!pe->dma_setup_done) return; rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index c6e0d8abf75e..7a974ed6b240 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -107,22 +107,28 @@ static int pseries_cpu_disable(void) */ static void pseries_cpu_die(unsigned int cpu) { - int tries; int cpu_status = 1; unsigned int pcpu = get_hard_smp_processor_id(cpu); + unsigned long timeout = jiffies + msecs_to_jiffies(120000); - for (tries = 0; tries < 25; tries++) { + while (true) { cpu_status = smp_query_cpu_stopped(pcpu); if (cpu_status == QCSS_STOPPED || cpu_status == QCSS_HARDWARE_ERROR) break; - cpu_relax(); + if (time_after(jiffies, timeout)) { + pr_warn("CPU %i (hwid %i) didn't die after 120 seconds\n", + cpu, pcpu); + timeout = jiffies + msecs_to_jiffies(120000); + } + + cond_resched(); } - if (cpu_status != 0) { - printk("Querying DEAD? cpu %i (%i) shows %i\n", - cpu, pcpu, cpu_status); + if (cpu_status == QCSS_HARDWARE_ERROR) { + pr_warn("CPU %i (hwid %i) reported error while dying\n", + cpu, pcpu); } /* Isolation and deallocation are definitely done by diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index f3736fcd98fc..13c86a292c6d 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -184,7 +184,6 @@ static void handle_system_shutdown(char event_modifier) case EPOW_SHUTDOWN_ON_UPS: pr_emerg("Loss of system power detected. System is running on" " UPS/battery. Check RTAS error log for details\n"); - orderly_poweroff(true); break; case EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS: |