diff options
Diffstat (limited to 'arch/powerpc/include')
67 files changed, 1301 insertions, 505 deletions
diff --git a/arch/powerpc/include/asm/accounting.h b/arch/powerpc/include/asm/accounting.h index 3abcf98ed2e0..c607c5d835cc 100644 --- a/arch/powerpc/include/asm/accounting.h +++ b/arch/powerpc/include/asm/accounting.h @@ -15,8 +15,10 @@ struct cpu_accounting_data { /* Accumulated cputime values to flush on ticks*/ unsigned long utime; unsigned long stime; +#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME unsigned long utime_scaled; unsigned long stime_scaled; +#endif unsigned long gtime; unsigned long hardirq_time; unsigned long softirq_time; @@ -25,8 +27,10 @@ struct cpu_accounting_data { /* Internal counters */ unsigned long starttime; /* TB value snapshot */ unsigned long starttime_user; /* TB value on exit to usermode */ +#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME unsigned long startspurr; /* SPURR value snapshot */ unsigned long utime_sspurr; /* ->user_time when ->startspurr set */ +#endif }; #endif diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 1f4691ce4126..ec691d489656 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -63,7 +63,6 @@ void program_check_exception(struct pt_regs *regs); void alignment_exception(struct pt_regs *regs); void slb_miss_bad_addr(struct pt_regs *regs); void StackOverflow(struct pt_regs *regs); -void nonrecoverable_exception(struct pt_regs *regs); void kernel_fp_unavailable_exception(struct pt_regs *regs); void altivec_unavailable_exception(struct pt_regs *regs); void vsx_unavailable_exception(struct pt_regs *regs); @@ -78,6 +77,8 @@ void kernel_bad_stack(struct pt_regs *regs); void system_reset_exception(struct pt_regs *regs); void machine_check_exception(struct pt_regs *regs); void emulation_assist_interrupt(struct pt_regs *regs); +long do_slb_fault(struct pt_regs *regs, unsigned long ea); +void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err); /* signals, syscalls and interrupts */ long sys_swapcontext(struct ucontext __user *old_ctx, @@ -150,4 +151,25 @@ extern s32 patch__memset_nocache, patch__memcpy_nocache; extern long flush_count_cache; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +void kvmppc_save_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv); +void kvmppc_restore_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv); +#else +static inline void kvmppc_save_tm_hv(struct kvm_vcpu *vcpu, u64 msr, + bool preserve_nv) { } +static inline void kvmppc_restore_tm_hv(struct kvm_vcpu *vcpu, u64 msr, + bool preserve_nv) { } +#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ + +void kvmhv_save_host_pmu(void); +void kvmhv_load_host_pmu(void); +void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use); +void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu); + +int __kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu); + +long kvmppc_h_set_dabr(struct kvm_vcpu *vcpu, unsigned long dabr); +long kvmppc_h_set_xdabr(struct kvm_vcpu *vcpu, unsigned long dabr, + unsigned long dabrx); + #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */ diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 751cf931bb3f..e61dd3ae5bc0 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -8,7 +8,97 @@ #include <asm/book3s/32/hash.h> /* And here we include common definitions */ -#include <asm/pte-common.h> + +#define _PAGE_KERNEL_RO 0 +#define _PAGE_KERNEL_ROX 0 +#define _PAGE_KERNEL_RW (_PAGE_DIRTY | _PAGE_RW) +#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW) + +#define _PAGE_HPTEFLAGS _PAGE_HASHPTE + +#ifndef __ASSEMBLY__ + +static inline bool pte_user(pte_t pte) +{ + return pte_val(pte) & _PAGE_USER; +} +#endif /* __ASSEMBLY__ */ + +/* + * Location of the PFN in the PTE. Most 32-bit platforms use the same + * as _PAGE_SHIFT here (ie, naturally aligned). + * Platform who don't just pre-define the value so we don't override it here. + */ +#define PTE_RPN_SHIFT (PAGE_SHIFT) + +/* + * The mask covered by the RPN must be a ULL on 32-bit platforms with + * 64-bit PTEs. + */ +#ifdef CONFIG_PTE_64BIT +#define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1)) +#else +#define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) +#endif + +/* + * _PAGE_CHG_MASK masks of bits that are to be preserved across + * pgprot changes. + */ +#define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HASHPTE | _PAGE_DIRTY | \ + _PAGE_ACCESSED | _PAGE_SPECIAL) + +/* + * We define 2 sets of base prot bits, one for basic pages (ie, + * cacheable kernel and user pages) and one for non cacheable + * pages. We always set _PAGE_COHERENT when SMP is enabled or + * the processor might need it for DMA coherency. + */ +#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) +#define _PAGE_BASE (_PAGE_BASE_NC | _PAGE_COHERENT) + +/* + * Permission masks used to generate the __P and __S table. + * + * Note:__pgprot is defined in arch/powerpc/include/asm/page.h + * + * Write permissions imply read permissions for now. + */ +#define PAGE_NONE __pgprot(_PAGE_BASE) +#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) +#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) +#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) +#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER) +#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) +#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER) + +/* Permission masks used for kernel mappings */ +#define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) +#define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NO_CACHE) +#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ + _PAGE_NO_CACHE | _PAGE_GUARDED) +#define PAGE_KERNEL_X __pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX) +#define PAGE_KERNEL_RO __pgprot(_PAGE_BASE | _PAGE_KERNEL_RO) +#define PAGE_KERNEL_ROX __pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX) + +/* + * Protection used for kernel text. We want the debuggers to be able to + * set breakpoints anywhere, so don't write protect the kernel text + * on platforms where such control is possible. + */ +#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\ + defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE) +#define PAGE_KERNEL_TEXT PAGE_KERNEL_X +#else +#define PAGE_KERNEL_TEXT PAGE_KERNEL_ROX +#endif + +/* Make modules code happy. We don't set RO yet */ +#define PAGE_KERNEL_EXEC PAGE_KERNEL_X + +/* Advertise special mapping type for AGP */ +#define PAGE_AGP (PAGE_KERNEL_NC) +#define HAVE_PAGE_AGP #define PTE_INDEX_SIZE PTE_SHIFT #define PMD_INDEX_SIZE 0 @@ -219,7 +309,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - pte_update(ptep, (_PAGE_RW | _PAGE_HWWRITE), _PAGE_RO); + pte_update(ptep, _PAGE_RW, 0); } static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) @@ -234,10 +324,9 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, int psize) { unsigned long set = pte_val(entry) & - (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); - unsigned long clr = ~pte_val(entry) & _PAGE_RO; + (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW); - pte_update(ptep, clr, set); + pte_update(ptep, 0, set); flush_tlb_page(vma, address); } @@ -292,7 +381,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) >> 3 }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val << 3 }) -int map_kernel_page(unsigned long va, phys_addr_t pa, int flags); +int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); /* Generic accessors to PTE bits */ static inline int pte_write(pte_t pte) { return !!(pte_val(pte) & _PAGE_RW);} @@ -301,13 +390,28 @@ static inline int pte_dirty(pte_t pte) { return !!(pte_val(pte) & _PAGE_DIRTY); static inline int pte_young(pte_t pte) { return !!(pte_val(pte) & _PAGE_ACCESSED); } static inline int pte_special(pte_t pte) { return !!(pte_val(pte) & _PAGE_SPECIAL); } static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; } -static inline pgprot_t pte_pgprot(pte_t pte) { return __pgprot(pte_val(pte) & PAGE_PROT_BITS); } +static inline bool pte_exec(pte_t pte) { return true; } static inline int pte_present(pte_t pte) { return pte_val(pte) & _PAGE_PRESENT; } +static inline bool pte_hw_valid(pte_t pte) +{ + return pte_val(pte) & _PAGE_PRESENT; +} + +static inline bool pte_hashpte(pte_t pte) +{ + return !!(pte_val(pte) & _PAGE_HASHPTE); +} + +static inline bool pte_ci(pte_t pte) +{ + return !!(pte_val(pte) & _PAGE_NO_CACHE); +} + /* * We only find page table entry in the last level * Hence no need for other accessors @@ -315,17 +419,14 @@ static inline int pte_present(pte_t pte) #define pte_access_permitted pte_access_permitted static inline bool pte_access_permitted(pte_t pte, bool write) { - unsigned long pteval = pte_val(pte); /* * A read-only access is controlled by _PAGE_USER bit. * We have _PAGE_READ set for WRITE and EXECUTE */ - unsigned long need_pte_bits = _PAGE_PRESENT | _PAGE_USER; - - if (write) - need_pte_bits |= _PAGE_WRITE; + if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte)) + return false; - if ((pteval & need_pte_bits) != need_pte_bits) + if (write && !pte_write(pte)) return false; return true; @@ -354,6 +455,11 @@ static inline pte_t pte_wrprotect(pte_t pte) return __pte(pte_val(pte) & ~_PAGE_RW); } +static inline pte_t pte_exprotect(pte_t pte) +{ + return pte; +} + static inline pte_t pte_mkclean(pte_t pte) { return __pte(pte_val(pte) & ~_PAGE_DIRTY); @@ -364,6 +470,16 @@ static inline pte_t pte_mkold(pte_t pte) return __pte(pte_val(pte) & ~_PAGE_ACCESSED); } +static inline pte_t pte_mkexec(pte_t pte) +{ + return pte; +} + +static inline pte_t pte_mkpte(pte_t pte) +{ + return pte; +} + static inline pte_t pte_mkwrite(pte_t pte) { return __pte(pte_val(pte) | _PAGE_RW); @@ -389,6 +505,16 @@ static inline pte_t pte_mkhuge(pte_t pte) return pte; } +static inline pte_t pte_mkprivileged(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_USER); +} + +static inline pte_t pte_mkuser(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_USER); +} + static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 9a3798660cef..15bc16b1dc9c 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -66,7 +66,7 @@ static inline int hash__hugepd_ok(hugepd_t hpd) * if it is not a pte and have hugepd shift mask * set, then it is a hugepd directory pointer */ - if (!(hpdval & _PAGE_PTE) && + if (!(hpdval & _PAGE_PTE) && (hpdval & _PAGE_PRESENT) && ((hpdval & HUGEPD_SHIFT_MASK) != 0)) return true; return false; diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index d52a51b2ce7b..247aff9cc6ba 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -18,6 +18,11 @@ #include <asm/book3s/64/hash-4k.h> #endif +/* Bits to set in a PMD/PUD/PGD entry valid bit*/ +#define HASH_PMD_VAL_BITS (0x8000000000000000UL) +#define HASH_PUD_VAL_BITS (0x8000000000000000UL) +#define HASH_PGD_VAL_BITS (0x8000000000000000UL) + /* * Size of EA range mapped by our pagetables. */ @@ -196,8 +201,7 @@ static inline void hpte_do_hugepage_flush(struct mm_struct *mm, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -extern int hash__map_kernel_page(unsigned long ea, unsigned long pa, - unsigned long flags); +int hash__map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot); extern int __meminit hash__vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys); diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h index 50888388a359..5b0177733994 100644 --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h @@ -39,4 +39,7 @@ static inline bool gigantic_page_supported(void) } #endif +/* hugepd entry valid bit */ +#define HUGEPD_VAL_BITS (0x8000000000000000UL) + #endif diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index b3520b549cba..12e522807f9f 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -30,7 +30,7 @@ * SLB */ -#define SLB_NUM_BOLTED 3 +#define SLB_NUM_BOLTED 2 #define SLB_CACHE_ENTRIES 8 #define SLB_MIN_SIZE 32 @@ -203,6 +203,18 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize) BUG(); } +static inline unsigned int ap_to_shift(unsigned long ap) +{ + int psize; + + for (psize = 0; psize < MMU_PAGE_COUNT; psize++) { + if (mmu_psize_defs[psize].ap == ap) + return mmu_psize_defs[psize].shift; + } + + return -1; +} + static inline unsigned long get_sllp_encoding(int psize) { unsigned long sllp; @@ -487,6 +499,8 @@ int htab_remove_mapping(unsigned long vstart, unsigned long vend, extern void pseries_add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages); extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr); +extern void hash__setup_new_exec(void); + #ifdef CONFIG_PPC_PSERIES void hpte_init_pseries(void); #else @@ -495,11 +509,18 @@ static inline void hpte_init_pseries(void) { } extern void hpte_init_native(void); +struct slb_entry { + u64 esid; + u64 vsid; +}; + extern void slb_initialize(void); -extern void slb_flush_and_rebolt(void); +void slb_flush_and_restore_bolted(void); void slb_flush_all_realmode(void); void __slb_restore_bolted_realmode(void); void slb_restore_bolted_realmode(void); +void slb_save_contents(struct slb_entry *slb_ptr); +void slb_dump_contents(struct slb_entry *slb_ptr); extern void slb_vmalloc_update(void); extern void slb_set_size(u16 size); @@ -512,13 +533,9 @@ extern void slb_set_size(u16 size); * from mmu context id and effective segment id of the address. * * For user processes max context id is limited to MAX_USER_CONTEXT. - - * For kernel space, we use context ids 1-4 to map addresses as below: - * NOTE: each context only support 64TB now. - * 0x00001 - [ 0xc000000000000000 - 0xc0003fffffffffff ] - * 0x00002 - [ 0xd000000000000000 - 0xd0003fffffffffff ] - * 0x00003 - [ 0xe000000000000000 - 0xe0003fffffffffff ] - * 0x00004 - [ 0xf000000000000000 - 0xf0003fffffffffff ] + * more details in get_user_context + * + * For kernel space get_kernel_context * * The proto-VSIDs are then scrambled into real VSIDs with the * multiplicative hash: @@ -559,6 +576,21 @@ extern void slb_set_size(u16 size); #define ESID_BITS_1T_MASK ((1 << ESID_BITS_1T) - 1) /* + * Now certain config support MAX_PHYSMEM more than 512TB. Hence we will need + * to use more than one context for linear mapping the kernel. + * For vmalloc and memmap, we use just one context with 512TB. With 64 byte + * struct page size, we need ony 32 TB in memmap for 2PB (51 bits (MAX_PHYSMEM_BITS)). + */ +#if (MAX_PHYSMEM_BITS > MAX_EA_BITS_PER_CONTEXT) +#define MAX_KERNEL_CTX_CNT (1UL << (MAX_PHYSMEM_BITS - MAX_EA_BITS_PER_CONTEXT)) +#else +#define MAX_KERNEL_CTX_CNT 1 +#endif + +#define MAX_VMALLOC_CTX_CNT 1 +#define MAX_MEMMAP_CTX_CNT 1 + +/* * 256MB segment * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments * available for user + kernel mapping. VSID 0 is reserved as invalid, contexts @@ -568,12 +600,13 @@ extern void slb_set_size(u16 size); * We also need to avoid the last segment of the last context, because that * would give a protovsid of 0x1fffffffff. That will result in a VSID 0 * because of the modulo operation in vsid scramble. + * + * We add one extra context to MIN_USER_CONTEXT so that we can map kernel + * context easily. The +1 is to map the unused 0xe region mapping. */ #define MAX_USER_CONTEXT ((ASM_CONST(1) << CONTEXT_BITS) - 2) -#define MIN_USER_CONTEXT (5) - -/* Would be nice to use KERNEL_REGION_ID here */ -#define KERNEL_REGION_CONTEXT_OFFSET (0xc - 1) +#define MIN_USER_CONTEXT (MAX_KERNEL_CTX_CNT + MAX_VMALLOC_CTX_CNT + \ + MAX_MEMMAP_CTX_CNT + 2) /* * For platforms that support on 65bit VA we limit the context bits @@ -734,6 +767,39 @@ static inline unsigned long get_vsid(unsigned long context, unsigned long ea, } /* + * For kernel space, we use context ids as below + * below. Range is 512TB per context. + * + * 0x00001 - [ 0xc000000000000000 - 0xc001ffffffffffff] + * 0x00002 - [ 0xc002000000000000 - 0xc003ffffffffffff] + * 0x00003 - [ 0xc004000000000000 - 0xc005ffffffffffff] + * 0x00004 - [ 0xc006000000000000 - 0xc007ffffffffffff] + + * 0x00005 - [ 0xd000000000000000 - 0xd001ffffffffffff ] + * 0x00006 - Not used - Can map 0xe000000000000000 range. + * 0x00007 - [ 0xf000000000000000 - 0xf001ffffffffffff ] + * + * So we can compute the context from the region (top nibble) by + * subtracting 11, or 0xc - 1. + */ +static inline unsigned long get_kernel_context(unsigned long ea) +{ + unsigned long region_id = REGION_ID(ea); + unsigned long ctx; + /* + * For linear mapping we do support multiple context + */ + if (region_id == KERNEL_REGION_ID) { + /* + * We already verified ea to be not beyond the addr limit. + */ + ctx = 1 + ((ea & ~REGION_MASK) >> MAX_EA_BITS_PER_CONTEXT); + } else + ctx = (region_id - 0xc) + MAX_KERNEL_CTX_CNT; + return ctx; +} + +/* * This is only valid for addresses >= PAGE_OFFSET */ static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) @@ -743,20 +809,7 @@ static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) if (!is_kernel_addr(ea)) return 0; - /* - * For kernel space, we use context ids 1-4 to map the address space as - * below: - * - * 0x00001 - [ 0xc000000000000000 - 0xc0003fffffffffff ] - * 0x00002 - [ 0xd000000000000000 - 0xd0003fffffffffff ] - * 0x00003 - [ 0xe000000000000000 - 0xe0003fffffffffff ] - * 0x00004 - [ 0xf000000000000000 - 0xf0003fffffffffff ] - * - * So we can compute the context from the region (top nibble) by - * subtracting 11, or 0xc - 1. - */ - context = (ea >> 60) - KERNEL_REGION_CONTEXT_OFFSET; - + context = get_kernel_context(ea); return get_vsid(context, ea, ssize); } diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index 9c8c669a6b6a..6328857f259f 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -208,7 +208,7 @@ extern void radix_init_pseries(void); static inline void radix_init_pseries(void) { }; #endif -static inline int get_ea_context(mm_context_t *ctx, unsigned long ea) +static inline int get_user_context(mm_context_t *ctx, unsigned long ea) { int index = ea >> MAX_EA_BITS_PER_CONTEXT; @@ -223,7 +223,7 @@ static inline int get_ea_context(mm_context_t *ctx, unsigned long ea) static inline unsigned long get_user_vsid(mm_context_t *ctx, unsigned long ea, int ssize) { - unsigned long context = get_ea_context(ctx, ea); + unsigned long context = get_user_context(ctx, ea); return get_vsid(context, ea, ssize); } diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h index d7ee249d6890..e3d4dd4ae2fa 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h @@ -10,6 +10,9 @@ * * Defined in such a way that we can optimize away code block at build time * if CONFIG_HUGETLB_PAGE=n. + * + * returns true for pmd migration entries, THP, devmap, hugetlb + * But compile time dependent on CONFIG_HUGETLB_PAGE */ static inline int pmd_huge(pmd_t pmd) { diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 2a2486526d1f..cb5dd4078d42 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -14,10 +14,6 @@ */ #define _PAGE_BIT_SWAP_TYPE 0 -#define _PAGE_NA 0 -#define _PAGE_RO 0 -#define _PAGE_USER 0 - #define _PAGE_EXEC 0x00001 /* execute permission */ #define _PAGE_WRITE 0x00002 /* write access allowed */ #define _PAGE_READ 0x00004 /* read access allowed */ @@ -123,10 +119,6 @@ #define _PAGE_KERNEL_RWX (_PAGE_PRIVILEGED | _PAGE_DIRTY | \ _PAGE_RW | _PAGE_EXEC) /* - * No page size encoding in the linux PTE - */ -#define _PAGE_PSIZE 0 -/* * _PAGE_CHG_MASK masks of bits that are to be preserved across * pgprot changes */ @@ -137,19 +129,12 @@ #define H_PTE_PKEY (H_PTE_PKEY_BIT0 | H_PTE_PKEY_BIT1 | H_PTE_PKEY_BIT2 | \ H_PTE_PKEY_BIT3 | H_PTE_PKEY_BIT4) /* - * Mask of bits returned by pte_pgprot() - */ -#define PAGE_PROT_BITS (_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT | \ - H_PAGE_4K_PFN | _PAGE_PRIVILEGED | _PAGE_ACCESSED | \ - _PAGE_READ | _PAGE_WRITE | _PAGE_DIRTY | _PAGE_EXEC | \ - _PAGE_SOFT_DIRTY | H_PTE_PKEY) -/* * We define 2 sets of base prot bits, one for basic pages (ie, * cacheable kernel and user pages) and one for non cacheable * pages. We always set _PAGE_COHERENT when SMP is enabled or * the processor might need it for DMA coherency. */ -#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE) +#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) #define _PAGE_BASE (_PAGE_BASE_NC) /* Permission masks used to generate the __P and __S table, @@ -159,8 +144,6 @@ * Write permissions imply read permissions for now (we could make write-only * pages on BookE but we don't bother for now). Execute permission control is * possible on platforms that define _PAGE_EXEC - * - * Note due to the way vm flags are laid out, the bits are XWR */ #define PAGE_NONE __pgprot(_PAGE_BASE | _PAGE_PRIVILEGED) #define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_RW) @@ -170,24 +153,6 @@ #define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_READ) #define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC) -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY -#define __P100 PAGE_READONLY_X -#define __P101 PAGE_READONLY_X -#define __P110 PAGE_COPY_X -#define __P111 PAGE_COPY_X - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_READONLY_X -#define __S101 PAGE_READONLY_X -#define __S110 PAGE_SHARED_X -#define __S111 PAGE_SHARED_X - /* Permission masks used for kernel mappings */ #define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) #define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ @@ -519,7 +484,11 @@ static inline int pte_special(pte_t pte) return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SPECIAL)); } -static inline pgprot_t pte_pgprot(pte_t pte) { return __pgprot(pte_val(pte) & PAGE_PROT_BITS); } +static inline bool pte_exec(pte_t pte) +{ + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_EXEC)); +} + #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline bool pte_soft_dirty(pte_t pte) @@ -529,12 +498,12 @@ static inline bool pte_soft_dirty(pte_t pte) static inline pte_t pte_mksoft_dirty(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_SOFT_DIRTY); + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SOFT_DIRTY)); } static inline pte_t pte_clear_soft_dirty(pte_t pte) { - return __pte(pte_val(pte) & ~_PAGE_SOFT_DIRTY); + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_SOFT_DIRTY)); } #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ @@ -555,7 +524,7 @@ static inline pte_t pte_mk_savedwrite(pte_t pte) */ VM_BUG_ON((pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_RWX | _PAGE_PRIVILEGED)) != cpu_to_be64(_PAGE_PRESENT | _PAGE_PRIVILEGED)); - return __pte(pte_val(pte) & ~_PAGE_PRIVILEGED); + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_PRIVILEGED)); } #define pte_clear_savedwrite pte_clear_savedwrite @@ -565,14 +534,14 @@ static inline pte_t pte_clear_savedwrite(pte_t pte) * Used by KSM subsystem to make a protnone pte readonly. */ VM_BUG_ON(!pte_protnone(pte)); - return __pte(pte_val(pte) | _PAGE_PRIVILEGED); + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PRIVILEGED)); } #else #define pte_clear_savedwrite pte_clear_savedwrite static inline pte_t pte_clear_savedwrite(pte_t pte) { VM_WARN_ON(1); - return __pte(pte_val(pte) & ~_PAGE_WRITE); + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_WRITE)); } #endif /* CONFIG_NUMA_BALANCING */ @@ -587,6 +556,11 @@ static inline int pte_present(pte_t pte) return !!(pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_INVALID)); } +static inline bool pte_hw_valid(pte_t pte) +{ + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT)); +} + #ifdef CONFIG_PPC_MEM_KEYS extern bool arch_pte_access_permitted(u64 pte, bool write, bool execute); #else @@ -596,25 +570,22 @@ static inline bool arch_pte_access_permitted(u64 pte, bool write, bool execute) } #endif /* CONFIG_PPC_MEM_KEYS */ +static inline bool pte_user(pte_t pte) +{ + return !(pte_raw(pte) & cpu_to_be64(_PAGE_PRIVILEGED)); +} + #define pte_access_permitted pte_access_permitted static inline bool pte_access_permitted(pte_t pte, bool write) { - unsigned long pteval = pte_val(pte); - /* Also check for pte_user */ - unsigned long clear_pte_bits = _PAGE_PRIVILEGED; /* * _PAGE_READ is needed for any access and will be * cleared for PROT_NONE */ - unsigned long need_pte_bits = _PAGE_PRESENT | _PAGE_READ; - - if (write) - need_pte_bits |= _PAGE_WRITE; - - if ((pteval & need_pte_bits) != need_pte_bits) + if (!pte_present(pte) || !pte_user(pte) || !pte_read(pte)) return false; - if ((pteval & clear_pte_bits) == clear_pte_bits) + if (write && !pte_write(pte)) return false; return arch_pte_access_permitted(pte_val(pte), write, 0); @@ -643,17 +614,32 @@ static inline pte_t pte_wrprotect(pte_t pte) { if (unlikely(pte_savedwrite(pte))) return pte_clear_savedwrite(pte); - return __pte(pte_val(pte) & ~_PAGE_WRITE); + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_WRITE)); +} + +static inline pte_t pte_exprotect(pte_t pte) +{ + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_EXEC)); } static inline pte_t pte_mkclean(pte_t pte) { - return __pte(pte_val(pte) & ~_PAGE_DIRTY); + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_DIRTY)); } static inline pte_t pte_mkold(pte_t pte) { - return __pte(pte_val(pte) & ~_PAGE_ACCESSED); + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_ACCESSED)); +} + +static inline pte_t pte_mkexec(pte_t pte) +{ + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_EXEC)); +} + +static inline pte_t pte_mkpte(pte_t pte) +{ + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PTE)); } static inline pte_t pte_mkwrite(pte_t pte) @@ -661,22 +647,22 @@ static inline pte_t pte_mkwrite(pte_t pte) /* * write implies read, hence set both */ - return __pte(pte_val(pte) | _PAGE_RW); + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_RW)); } static inline pte_t pte_mkdirty(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_DIRTY | _PAGE_SOFT_DIRTY); + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_DIRTY | _PAGE_SOFT_DIRTY)); } static inline pte_t pte_mkyoung(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_ACCESSED); + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_ACCESSED)); } static inline pte_t pte_mkspecial(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_SPECIAL); + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SPECIAL)); } static inline pte_t pte_mkhuge(pte_t pte) @@ -686,7 +672,17 @@ static inline pte_t pte_mkhuge(pte_t pte) static inline pte_t pte_mkdevmap(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_SPECIAL|_PAGE_DEVMAP); + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SPECIAL | _PAGE_DEVMAP)); +} + +static inline pte_t pte_mkprivileged(pte_t pte) +{ + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_PRIVILEGED)); +} + +static inline pte_t pte_mkuser(pte_t pte) +{ + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_PRIVILEGED)); } /* @@ -705,12 +701,8 @@ static inline int pte_devmap(pte_t pte) static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { /* FIXME!! check whether this need to be a conditional */ - return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); -} - -static inline bool pte_user(pte_t pte) -{ - return !(pte_raw(pte) & cpu_to_be64(_PAGE_PRIVILEGED)); + return __pte_raw((pte_raw(pte) & cpu_to_be64(_PAGE_CHG_MASK)) | + cpu_to_be64(pgprot_val(newprot))); } /* Encode and de-code a swap entry */ @@ -741,6 +733,8 @@ static inline bool pte_user(pte_t pte) */ #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) & ~_PAGE_PTE }) #define __swp_entry_to_pte(x) __pte((x).val | _PAGE_PTE) +#define __pmd_to_swp_entry(pmd) (__pte_to_swp_entry(pmd_pte(pmd))) +#define __swp_entry_to_pmd(x) (pte_pmd(__swp_entry_to_pte(x))) #ifdef CONFIG_MEM_SOFT_DIRTY #define _PAGE_SWP_SOFT_DIRTY (1UL << (SWP_TYPE_BITS + _PAGE_BIT_SWAP_TYPE)) @@ -751,7 +745,7 @@ static inline bool pte_user(pte_t pte) #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_SWP_SOFT_DIRTY); + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SWP_SOFT_DIRTY)); } static inline bool pte_swp_soft_dirty(pte_t pte) @@ -761,7 +755,7 @@ static inline bool pte_swp_soft_dirty(pte_t pte) static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { - return __pte(pte_val(pte) & ~_PAGE_SWP_SOFT_DIRTY); + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_SWP_SOFT_DIRTY)); } #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ @@ -850,10 +844,10 @@ static inline pgprot_t pgprot_writecombine(pgprot_t prot) */ static inline bool pte_ci(pte_t pte) { - unsigned long pte_v = pte_val(pte); + __be64 pte_v = pte_raw(pte); - if (((pte_v & _PAGE_CACHE_CTL) == _PAGE_TOLERANT) || - ((pte_v & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT)) + if (((pte_v & cpu_to_be64(_PAGE_CACHE_CTL)) == cpu_to_be64(_PAGE_TOLERANT)) || + ((pte_v & cpu_to_be64(_PAGE_CACHE_CTL)) == cpu_to_be64(_PAGE_NON_IDEMPOTENT))) return true; return false; } @@ -875,8 +869,16 @@ static inline int pmd_none(pmd_t pmd) static inline int pmd_present(pmd_t pmd) { + /* + * A pmd is considerent present if _PAGE_PRESENT is set. + * We also need to consider the pmd present which is marked + * invalid during a split. Hence we look for _PAGE_INVALID + * if we find _PAGE_PRESENT cleared. + */ + if (pmd_raw(pmd) & cpu_to_be64(_PAGE_PRESENT | _PAGE_INVALID)) + return true; - return !pmd_none(pmd); + return false; } static inline int pmd_bad(pmd_t pmd) @@ -903,7 +905,7 @@ static inline int pud_none(pud_t pud) static inline int pud_present(pud_t pud) { - return !pud_none(pud); + return (pud_raw(pud) & cpu_to_be64(_PAGE_PRESENT)); } extern struct page *pud_page(pud_t pud); @@ -950,7 +952,7 @@ static inline int pgd_none(pgd_t pgd) static inline int pgd_present(pgd_t pgd) { - return !pgd_none(pgd); + return (pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT)); } static inline pte_t pgd_pte(pgd_t pgd) @@ -1020,17 +1022,16 @@ extern struct page *pgd_page(pgd_t pgd); #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) -static inline int map_kernel_page(unsigned long ea, unsigned long pa, - unsigned long flags) +static inline int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot) { if (radix_enabled()) { #if defined(CONFIG_PPC_RADIX_MMU) && defined(DEBUG_VM) unsigned long page_size = 1 << mmu_psize_defs[mmu_io_psize].shift; WARN((page_size != PAGE_SIZE), "I/O page size != PAGE_SIZE"); #endif - return radix__map_kernel_page(ea, pa, __pgprot(flags), PAGE_SIZE); + return radix__map_kernel_page(ea, pa, prot, PAGE_SIZE); } - return hash__map_kernel_page(ea, pa, flags); + return hash__map_kernel_page(ea, pa, prot); } static inline int __meminit vmemmap_create_mapping(unsigned long start, @@ -1082,6 +1083,12 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd) #define pmd_soft_dirty(pmd) pte_soft_dirty(pmd_pte(pmd)) #define pmd_mksoft_dirty(pmd) pte_pmd(pte_mksoft_dirty(pmd_pte(pmd))) #define pmd_clear_soft_dirty(pmd) pte_pmd(pte_clear_soft_dirty(pmd_pte(pmd))) + +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION +#define pmd_swp_mksoft_dirty(pmd) pte_pmd(pte_swp_mksoft_dirty(pmd_pte(pmd))) +#define pmd_swp_soft_dirty(pmd) pte_swp_soft_dirty(pmd_pte(pmd)) +#define pmd_swp_clear_soft_dirty(pmd) pte_pmd(pte_swp_clear_soft_dirty(pmd_pte(pmd))) +#endif #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ #ifdef CONFIG_NUMA_BALANCING @@ -1127,6 +1134,10 @@ pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, return hash__pmd_hugepage_update(mm, addr, pmdp, clr, set); } +/* + * returns true for pmd migration entries, THP, devmap, hugetlb + * But compile time dependent on THP config + */ static inline int pmd_large(pmd_t pmd) { return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); @@ -1161,8 +1172,22 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_hugepage_update(mm, addr, pmdp, 0, _PAGE_PRIVILEGED); } +/* + * Only returns true for a THP. False for pmd migration entry. + * We also need to return true when we come across a pte that + * in between a thp split. While splitting THP, we mark the pmd + * invalid (pmdp_invalidate()) before we set it with pte page + * address. A pmd_trans_huge() check against a pmd entry during that time + * should return true. + * We should not call this on a hugetlb entry. We should check for HugeTLB + * entry using vma->vm_flags + * The page table walk rule is explained in Documentation/vm/transhuge.rst + */ static inline int pmd_trans_huge(pmd_t pmd) { + if (!pmd_present(pmd)) + return false; + if (radix_enabled()) return radix__pmd_trans_huge(pmd); return hash__pmd_trans_huge(pmd); diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index 1154a6dc6d26..671316f9e95d 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -53,6 +53,7 @@ extern void radix__flush_tlb_lpid_page(unsigned int lpid, unsigned long addr, unsigned long page_size); extern void radix__flush_pwc_lpid(unsigned int lpid); +extern void radix__flush_tlb_lpid(unsigned int lpid); extern void radix__local_flush_tlb_lpid(unsigned int lpid); extern void radix__local_flush_tlb_lpid_guest(unsigned int lpid); diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 85c8af2bb272..74d0db511099 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -8,6 +8,8 @@ #include <linux/types.h> #include <linux/sched.h> +#include <asm-generic/compat.h> + #define COMPAT_USER_HZ 100 #ifdef __BIG_ENDIAN__ #define COMPAT_UTS_MACHINE "ppc\0\0" @@ -15,34 +17,18 @@ #define COMPAT_UTS_MACHINE "ppcle\0\0" #endif -typedef u32 compat_size_t; -typedef s32 compat_ssize_t; -typedef s32 compat_clock_t; -typedef s32 compat_pid_t; typedef u32 __compat_uid_t; typedef u32 __compat_gid_t; typedef u32 __compat_uid32_t; typedef u32 __compat_gid32_t; typedef u32 compat_mode_t; -typedef u32 compat_ino_t; typedef u32 compat_dev_t; -typedef s32 compat_off_t; -typedef s64 compat_loff_t; typedef s16 compat_nlink_t; typedef u16 compat_ipc_pid_t; -typedef s32 compat_daddr_t; typedef u32 compat_caddr_t; typedef __kernel_fsid_t compat_fsid_t; -typedef s32 compat_key_t; -typedef s32 compat_timer_t; - -typedef s32 compat_int_t; -typedef s32 compat_long_t; typedef s64 compat_s64; -typedef u32 compat_uint_t; -typedef u32 compat_ulong_t; typedef u64 compat_u64; -typedef u32 compat_uptr_t; struct compat_stat { compat_dev_t st_dev; @@ -55,11 +41,11 @@ struct compat_stat { compat_off_t st_size; compat_off_t st_blksize; compat_off_t st_blocks; - compat_time_t st_atime; + old_time32_t st_atime; u32 st_atime_nsec; - compat_time_t st_mtime; + old_time32_t st_mtime; u32 st_mtime_nsec; - compat_time_t st_ctime; + old_time32_t st_ctime; u32 st_ctime_nsec; u32 __unused4[2]; }; diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h index d71a90924f3b..deb99fd6e060 100644 --- a/arch/powerpc/include/asm/cputhreads.h +++ b/arch/powerpc/include/asm/cputhreads.h @@ -23,11 +23,13 @@ extern int threads_per_core; extern int threads_per_subcore; extern int threads_shift; +extern bool has_big_cores; extern cpumask_t threads_core_mask; #else #define threads_per_core 1 #define threads_per_subcore 1 #define threads_shift 0 +#define has_big_cores 0 #define threads_core_mask (*get_cpu_mask(0)) #endif diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index 133672744b2e..ae73dc8da2d4 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -61,7 +61,6 @@ static inline void arch_vtime_task_switch(struct task_struct *prev) struct cpu_accounting_data *acct0 = get_accounting(prev); acct->starttime = acct0->starttime; - acct->startspurr = acct0->startspurr; } #endif diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h index ce242b9ea8c6..7c1d8e74b25d 100644 --- a/arch/powerpc/include/asm/drmem.h +++ b/arch/powerpc/include/asm/drmem.h @@ -99,4 +99,9 @@ void __init walk_drmem_lmbs_early(unsigned long node, void (*func)(struct drmem_lmb *, const __be32 **)); #endif +static inline void invalidate_lmb_associativity_index(struct drmem_lmb *lmb) +{ + lmb->aa_index = 0xffffffff; +} + #endif /* _ASM_POWERPC_LMB_H */ diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 219637ea69a1..8b596d096ebe 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -43,7 +43,6 @@ struct pci_dn; #define EEH_VALID_PE_ZERO 0x10 /* PE#0 is valid */ #define EEH_ENABLE_IO_FOR_LOG 0x20 /* Enable IO for log */ #define EEH_EARLY_DUMP_LOG 0x40 /* Dump log immediately */ -#define EEH_POSTPONED_PROBE 0x80 /* Powernv may postpone device probe */ /* * Delay for PE reset, all in ms @@ -99,13 +98,13 @@ struct eeh_pe { atomic_t pass_dev_cnt; /* Count of passed through devs */ struct eeh_pe *parent; /* Parent PE */ void *data; /* PE auxillary data */ - struct list_head child_list; /* Link PE to the child list */ - struct list_head edevs; /* Link list of EEH devices */ - struct list_head child; /* Child PEs */ + struct list_head child_list; /* List of PEs below this PE */ + struct list_head child; /* Memb. child_list/eeh_phb_pe */ + struct list_head edevs; /* List of eeh_dev in this PE */ }; #define eeh_pe_for_each_dev(pe, edev, tmp) \ - list_for_each_entry_safe(edev, tmp, &pe->edevs, list) + list_for_each_entry_safe(edev, tmp, &pe->edevs, entry) #define eeh_for_each_pe(root, pe) \ for (pe = root; pe; pe = eeh_pe_next(pe, root)) @@ -142,13 +141,12 @@ struct eeh_dev { int aer_cap; /* Saved AER capability */ int af_cap; /* Saved AF capability */ struct eeh_pe *pe; /* Associated PE */ - struct list_head list; /* Form link list in the PE */ - struct list_head rmv_list; /* Record the removed edevs */ + struct list_head entry; /* Membership in eeh_pe.edevs */ + struct list_head rmv_entry; /* Membership in rmv_list */ struct pci_dn *pdn; /* Associated PCI device node */ struct pci_dev *pdev; /* Associated PCI device */ bool in_error; /* Error flag for edev */ struct pci_dev *physfn; /* Associated SRIOV PF */ - struct pci_bus *bus; /* PCI bus for partial hotplug */ }; static inline struct pci_dn *eeh_dev_to_pdn(struct eeh_dev *edev) @@ -207,9 +205,8 @@ struct eeh_ops { void* (*probe)(struct pci_dn *pdn, void *data); int (*set_option)(struct eeh_pe *pe, int option); int (*get_pe_addr)(struct eeh_pe *pe); - int (*get_state)(struct eeh_pe *pe, int *state); + int (*get_state)(struct eeh_pe *pe, int *delay); int (*reset)(struct eeh_pe *pe, int option); - int (*wait_state)(struct eeh_pe *pe, int max_wait); int (*get_log)(struct eeh_pe *pe, int severity, char *drv_log, unsigned long len); int (*configure_bridge)(struct eeh_pe *pe); int (*err_inject)(struct eeh_pe *pe, int type, int func, @@ -243,11 +240,7 @@ static inline bool eeh_has_flag(int flag) static inline bool eeh_enabled(void) { - if (eeh_has_flag(EEH_FORCE_DISABLED) || - !eeh_has_flag(EEH_ENABLED)) - return false; - - return true; + return eeh_has_flag(EEH_ENABLED) && !eeh_has_flag(EEH_FORCE_DISABLED); } static inline void eeh_serialize_lock(unsigned long *flags) @@ -270,6 +263,7 @@ typedef void *(*eeh_edev_traverse_func)(struct eeh_dev *edev, void *flag); typedef void *(*eeh_pe_traverse_func)(struct eeh_pe *pe, void *flag); void eeh_set_pe_aux_size(int size); int eeh_phb_pe_create(struct pci_controller *phb); +int eeh_wait_state(struct eeh_pe *pe, int max_wait); struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb); struct eeh_pe *eeh_pe_next(struct eeh_pe *pe, struct eeh_pe *root); struct eeh_pe *eeh_pe_get(struct pci_controller *phb, diff --git a/arch/powerpc/include/asm/error-injection.h b/arch/powerpc/include/asm/error-injection.h new file mode 100644 index 000000000000..62fd24739852 --- /dev/null +++ b/arch/powerpc/include/asm/error-injection.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _ASM_ERROR_INJECTION_H +#define _ASM_ERROR_INJECTION_H + +#include <linux/compiler.h> +#include <linux/linkage.h> +#include <asm/ptrace.h> +#include <asm-generic/error-injection.h> + +void override_function_with_return(struct pt_regs *regs); + +#endif /* _ASM_ERROR_INJECTION_H */ diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index a86feddddad0..3b4767ed3ec5 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -61,14 +61,6 @@ #define MAX_MCE_DEPTH 4 /* - * EX_LR is only used in EXSLB and where it does not overlap with EX_DAR - * EX_CCR similarly with DSISR, but being 4 byte registers there is a hole - * in the save area so it's not necessary to overlap them. Could be used - * for future savings though if another 4 byte register was to be saved. - */ -#define EX_LR EX_DAR - -/* * EX_R3 is only used by the bad_stack handler. bad_stack reloads and * saves DAR from SPRN_DAR, and EX_DAR is not used. So EX_R3 can overlap * with EX_DAR. @@ -236,11 +228,10 @@ * PPR save/restore macros used in exceptions_64s.S * Used for P7 or later processors */ -#define SAVE_PPR(area, ra, rb) \ +#define SAVE_PPR(area, ra) \ BEGIN_FTR_SECTION_NESTED(940) \ - ld ra,PACACURRENT(r13); \ - ld rb,area+EX_PPR(r13); /* Read PPR from paca */ \ - std rb,TASKTHREADPPR(ra); \ + ld ra,area+EX_PPR(r13); /* Read PPR from paca */ \ + std ra,_PPR(r1); \ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,940) #define RESTORE_PPR_PACA(area, ra) \ @@ -508,7 +499,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) 3: EXCEPTION_PROLOG_COMMON_1(); \ beq 4f; /* if from kernel mode */ \ ACCOUNT_CPU_USER_ENTRY(r13, r9, r10); \ - SAVE_PPR(area, r9, r10); \ + SAVE_PPR(area, r9); \ 4: EXCEPTION_PROLOG_COMMON_2(area) \ EXCEPTION_PROLOG_COMMON_3(n) \ ACCOUNT_STOLEN_TIME diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 7a051bd21f87..00bc42d95679 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -52,6 +52,8 @@ #define FW_FEATURE_PRRN ASM_CONST(0x0000000200000000) #define FW_FEATURE_DRMEM_V2 ASM_CONST(0x0000000400000000) #define FW_FEATURE_DRC_INFO ASM_CONST(0x0000000800000000) +#define FW_FEATURE_BLOCK_REMOVE ASM_CONST(0x0000001000000000) +#define FW_FEATURE_PAPR_SCM ASM_CONST(0x0000002000000000) #ifndef __ASSEMBLY__ @@ -69,7 +71,8 @@ enum { FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY | FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN | FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 | - FW_FEATURE_DRC_INFO, + FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE | + FW_FEATURE_PAPR_SCM, FW_FEATURE_PSERIES_ALWAYS = 0, FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL, FW_FEATURE_POWERNV_ALWAYS = 0, diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 41cc15c14eee..b9fbed84ddca 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -72,7 +72,7 @@ enum fixed_addresses { static inline void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { - map_kernel_page(fix_to_virt(idx), phys, pgprot_val(flags)); + map_kernel_page(fix_to_virt(idx), phys, flags); } #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index a0b17f9f1ea4..33a4fc891947 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -278,6 +278,7 @@ #define H_COP 0x304 #define H_GET_MPP_X 0x314 #define H_SET_MODE 0x31C +#define H_BLOCK_REMOVE 0x328 #define H_CLEAR_HPT 0x358 #define H_REQUEST_VMC 0x360 #define H_RESIZE_HPT_PREPARE 0x36C @@ -295,7 +296,15 @@ #define H_INT_ESB 0x3C8 #define H_INT_SYNC 0x3CC #define H_INT_RESET 0x3D0 -#define MAX_HCALL_OPCODE H_INT_RESET +#define H_SCM_READ_METADATA 0x3E4 +#define H_SCM_WRITE_METADATA 0x3E8 +#define H_SCM_BIND_MEM 0x3EC +#define H_SCM_UNBIND_MEM 0x3F0 +#define H_SCM_QUERY_BLOCK_MEM_BINDING 0x3F4 +#define H_SCM_QUERY_LOGICAL_MEM_BINDING 0x3F8 +#define H_SCM_MEM_QUERY 0x3FC +#define H_SCM_BLOCK_CLEAR 0x400 +#define MAX_HCALL_OPCODE H_SCM_BLOCK_CLEAR /* H_VIOCTL functions */ #define H_GET_VIOA_DUMP_SIZE 0x01 @@ -322,6 +331,11 @@ #define H_GET_24X7_DATA 0xF07C #define H_GET_PERF_COUNTER_INFO 0xF080 +/* Platform-specific hcalls used for nested HV KVM */ +#define H_SET_PARTITION_TABLE 0xF800 +#define H_ENTER_NESTED 0xF804 +#define H_TLB_INVALIDATE 0xF808 + /* Values for 2nd argument to H_SET_MODE */ #define H_SET_MODE_RESOURCE_SET_CIABR 1 #define H_SET_MODE_RESOURCE_SET_DAWR 2 @@ -461,6 +475,42 @@ struct h_cpu_char_result { u64 behaviour; }; +/* Register state for entering a nested guest with H_ENTER_NESTED */ +struct hv_guest_state { + u64 version; /* version of this structure layout */ + u32 lpid; + u32 vcpu_token; + /* These registers are hypervisor privileged (at least for writing) */ + u64 lpcr; + u64 pcr; + u64 amor; + u64 dpdes; + u64 hfscr; + s64 tb_offset; + u64 dawr0; + u64 dawrx0; + u64 ciabr; + u64 hdec_expiry; + u64 purr; + u64 spurr; + u64 ic; + u64 vtb; + u64 hdar; + u64 hdsisr; + u64 heir; + u64 asdr; + /* These are OS privileged but need to be set late in guest entry */ + u64 srr0; + u64 srr1; + u64 sprg[4]; + u64 pidr; + u64 cfar; + u64 ppr; +}; + +/* Latest version of hv_guest_state structure */ +#define HV_GUEST_STATE_VERSION 1 + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_HVCALL_H */ diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index e0331e754568..3ef40b703c4a 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -3,6 +3,9 @@ #ifdef __KERNEL__ #define ARCH_HAS_IOREMAP_WC +#ifdef CONFIG_PPC32 +#define ARCH_HAS_IOREMAP_WT +#endif /* * This program is free software; you can redistribute it and/or @@ -108,25 +111,6 @@ extern bool isa_io_special; #define IO_SET_SYNC_FLAG() #endif -/* gcc 4.0 and older doesn't have 'Z' constraint */ -#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ == 0) -#define DEF_MMIO_IN_X(name, size, insn) \ -static inline u##size name(const volatile u##size __iomem *addr) \ -{ \ - u##size ret; \ - __asm__ __volatile__("sync;"#insn" %0,0,%1;twi 0,%0,0;isync" \ - : "=r" (ret) : "r" (addr), "m" (*addr) : "memory"); \ - return ret; \ -} - -#define DEF_MMIO_OUT_X(name, size, insn) \ -static inline void name(volatile u##size __iomem *addr, u##size val) \ -{ \ - __asm__ __volatile__("sync;"#insn" %1,0,%2" \ - : "=m" (*addr) : "r" (val), "r" (addr) : "memory"); \ - IO_SET_SYNC_FLAG(); \ -} -#else /* newer gcc */ #define DEF_MMIO_IN_X(name, size, insn) \ static inline u##size name(const volatile u##size __iomem *addr) \ { \ @@ -143,7 +127,6 @@ static inline void name(volatile u##size __iomem *addr, u##size val) \ : "=Z" (*addr) : "r" (val) : "memory"); \ IO_SET_SYNC_FLAG(); \ } -#endif #define DEF_MMIO_IN_D(name, size, insn) \ static inline u##size name(const volatile u##size __iomem *addr) \ @@ -746,6 +729,10 @@ static inline void iosync(void) * * * ioremap_wc enables write combining * + * * ioremap_wt enables write through + * + * * ioremap_coherent maps coherent cached memory + * * * iounmap undoes such a mapping and can be hooked * * * __ioremap_at (and the pending __iounmap_at) are low level functions to @@ -767,6 +754,8 @@ extern void __iomem *ioremap(phys_addr_t address, unsigned long size); extern void __iomem *ioremap_prot(phys_addr_t address, unsigned long size, unsigned long flags); extern void __iomem *ioremap_wc(phys_addr_t address, unsigned long size); +void __iomem *ioremap_wt(phys_addr_t address, unsigned long size); +void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size); #define ioremap_nocache(addr, size) ioremap((addr), (size)) #define ioremap_uc(addr, size) ioremap((addr), (size)) #define ioremap_cache(addr, size) \ @@ -777,12 +766,12 @@ extern void iounmap(volatile void __iomem *addr); extern void __iomem *__ioremap(phys_addr_t, unsigned long size, unsigned long flags); extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size, - unsigned long flags, void *caller); + pgprot_t prot, void *caller); extern void __iounmap(volatile void __iomem *addr); extern void __iomem * __ioremap_at(phys_addr_t pa, void *ea, - unsigned long size, unsigned long flags); + unsigned long size, pgprot_t prot); extern void __iounmap_at(void *ea, unsigned long size); /* diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 3d4b88cb8599..35db0cbc9222 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -126,7 +126,7 @@ struct iommu_table { int it_nid; }; -#define IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry) \ +#define IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry) \ ((tbl)->it_ops->useraddrptr((tbl), (entry), false)) #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \ ((tbl)->it_ops->useraddrptr((tbl), (entry), true)) diff --git a/arch/powerpc/include/asm/kgdb.h b/arch/powerpc/include/asm/kgdb.h index 9db24e77b9f4..a9e098a3b881 100644 --- a/arch/powerpc/include/asm/kgdb.h +++ b/arch/powerpc/include/asm/kgdb.h @@ -26,9 +26,12 @@ #define BREAK_INSTR_SIZE 4 #define BUFMAX ((NUMREGBYTES * 2) + 512) #define OUTBUFMAX ((NUMREGBYTES * 2) + 512) + +#define BREAK_INSTR 0x7d821008 /* twge r2, r2 */ + static inline void arch_kgdb_breakpoint(void) { - asm(".long 0x7d821008"); /* twge r2, r2 */ + asm(stringify_in_c(.long BREAK_INSTR)); } #define CACHE_FLUSH_IS_SAFE 1 #define DBG_MAX_REG_NUM 70 diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index a790d5cf6ea3..1f321914676d 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -84,7 +84,6 @@ #define BOOK3S_INTERRUPT_INST_STORAGE 0x400 #define BOOK3S_INTERRUPT_INST_SEGMENT 0x480 #define BOOK3S_INTERRUPT_EXTERNAL 0x500 -#define BOOK3S_INTERRUPT_EXTERNAL_LEVEL 0x501 #define BOOK3S_INTERRUPT_EXTERNAL_HV 0x502 #define BOOK3S_INTERRUPT_ALIGNMENT 0x600 #define BOOK3S_INTERRUPT_PROGRAM 0x700 @@ -134,8 +133,7 @@ #define BOOK3S_IRQPRIO_EXTERNAL 14 #define BOOK3S_IRQPRIO_DECREMENTER 15 #define BOOK3S_IRQPRIO_PERFORMANCE_MONITOR 16 -#define BOOK3S_IRQPRIO_EXTERNAL_LEVEL 17 -#define BOOK3S_IRQPRIO_MAX 18 +#define BOOK3S_IRQPRIO_MAX 17 #define BOOK3S_HFLAG_DCBZ32 0x1 #define BOOK3S_HFLAG_SLB 0x2 diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 83a9aa3cf689..09f8e9ba69bc 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -188,14 +188,37 @@ extern int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hc); extern int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned long ea, unsigned long dsisr); +extern int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr, + struct kvmppc_pte *gpte, u64 root, + u64 *pte_ret_p); +extern int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr, + struct kvmppc_pte *gpte, u64 table, + int table_index, u64 *pte_ret_p); extern int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *gpte, bool data, bool iswrite); +extern void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa, + unsigned int shift, struct kvm_memory_slot *memslot, + unsigned int lpid); +extern bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable, + bool writing, unsigned long gpa, + unsigned int lpid); +extern int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu, + unsigned long gpa, + struct kvm_memory_slot *memslot, + bool writing, bool kvm_ro, + pte_t *inserted_pte, unsigned int *levelp); extern int kvmppc_init_vm_radix(struct kvm *kvm); extern void kvmppc_free_radix(struct kvm *kvm); +extern void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd, + unsigned int lpid); extern int kvmppc_radix_init(void); extern void kvmppc_radix_exit(void); extern int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn); +extern void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, + unsigned long gpa, unsigned int shift, + struct kvm_memory_slot *memslot, + unsigned int lpid); extern int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long gfn); extern int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, @@ -271,6 +294,21 @@ static inline void kvmppc_save_tm_sprs(struct kvm_vcpu *vcpu) {} static inline void kvmppc_restore_tm_sprs(struct kvm_vcpu *vcpu) {} #endif +long kvmhv_nested_init(void); +void kvmhv_nested_exit(void); +void kvmhv_vm_nested_init(struct kvm *kvm); +long kvmhv_set_partition_table(struct kvm_vcpu *vcpu); +void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1); +void kvmhv_release_all_nested(struct kvm *kvm); +long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu); +long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu); +int kvmhv_run_single_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu, + u64 time_limit, unsigned long lpcr); +void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr); +void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu, + struct hv_guest_state *hr); +long int kvmhv_nested_page_fault(struct kvm_vcpu *vcpu); + void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac); extern int kvm_irq_bypass; @@ -301,12 +339,12 @@ static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) { - vcpu->arch.cr = val; + vcpu->arch.regs.ccr = val; } static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) { - return vcpu->arch.cr; + return vcpu->arch.regs.ccr; } static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, ulong val) @@ -384,9 +422,6 @@ extern int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu); /* TO = 31 for unconditional trap */ #define INS_TW 0x7fe00008 -/* LPIDs we support with this build -- runtime limit may be lower */ -#define KVMPPC_NR_LPIDS (LPID_RSVD + 1) - #define SPLIT_HACK_MASK 0xff000000 #define SPLIT_HACK_OFFS 0xfb000000 diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index dc435a5af7d6..6d298145d564 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -23,6 +23,108 @@ #include <linux/string.h> #include <asm/bitops.h> #include <asm/book3s/64/mmu-hash.h> +#include <asm/cpu_has_feature.h> +#include <asm/ppc-opcode.h> + +#ifdef CONFIG_PPC_PSERIES +static inline bool kvmhv_on_pseries(void) +{ + return !cpu_has_feature(CPU_FTR_HVMODE); +} +#else +static inline bool kvmhv_on_pseries(void) +{ + return false; +} +#endif + +/* + * Structure for a nested guest, that is, for a guest that is managed by + * one of our guests. + */ +struct kvm_nested_guest { + struct kvm *l1_host; /* L1 VM that owns this nested guest */ + int l1_lpid; /* lpid L1 guest thinks this guest is */ + int shadow_lpid; /* real lpid of this nested guest */ + pgd_t *shadow_pgtable; /* our page table for this guest */ + u64 l1_gr_to_hr; /* L1's addr of part'n-scoped table */ + u64 process_table; /* process table entry for this guest */ + long refcnt; /* number of pointers to this struct */ + struct mutex tlb_lock; /* serialize page faults and tlbies */ + struct kvm_nested_guest *next; + cpumask_t need_tlb_flush; + cpumask_t cpu_in_guest; + short prev_cpu[NR_CPUS]; +}; + +/* + * We define a nested rmap entry as a single 64-bit quantity + * 0xFFF0000000000000 12-bit lpid field + * 0x000FFFFFFFFFF000 40-bit guest 4k page frame number + * 0x0000000000000001 1-bit single entry flag + */ +#define RMAP_NESTED_LPID_MASK 0xFFF0000000000000UL +#define RMAP_NESTED_LPID_SHIFT (52) +#define RMAP_NESTED_GPA_MASK 0x000FFFFFFFFFF000UL +#define RMAP_NESTED_IS_SINGLE_ENTRY 0x0000000000000001UL + +/* Structure for a nested guest rmap entry */ +struct rmap_nested { + struct llist_node list; + u64 rmap; +}; + +/* + * for_each_nest_rmap_safe - iterate over the list of nested rmap entries + * safe against removal of the list entry or NULL list + * @pos: a (struct rmap_nested *) to use as a loop cursor + * @node: pointer to the first entry + * NOTE: this can be NULL + * @rmapp: an (unsigned long *) in which to return the rmap entries on each + * iteration + * NOTE: this must point to already allocated memory + * + * The nested_rmap is a llist of (struct rmap_nested) entries pointed to by the + * rmap entry in the memslot. The list is always terminated by a "single entry" + * stored in the list element of the final entry of the llist. If there is ONLY + * a single entry then this is itself in the rmap entry of the memslot, not a + * llist head pointer. + * + * Note that the iterator below assumes that a nested rmap entry is always + * non-zero. This is true for our usage because the LPID field is always + * non-zero (zero is reserved for the host). + * + * This should be used to iterate over the list of rmap_nested entries with + * processing done on the u64 rmap value given by each iteration. This is safe + * against removal of list entries and it is always safe to call free on (pos). + * + * e.g. + * struct rmap_nested *cursor; + * struct llist_node *first; + * unsigned long rmap; + * for_each_nest_rmap_safe(cursor, first, &rmap) { + * do_something(rmap); + * free(cursor); + * } + */ +#define for_each_nest_rmap_safe(pos, node, rmapp) \ + for ((pos) = llist_entry((node), typeof(*(pos)), list); \ + (node) && \ + (*(rmapp) = ((RMAP_NESTED_IS_SINGLE_ENTRY & ((u64) (node))) ? \ + ((u64) (node)) : ((pos)->rmap))) && \ + (((node) = ((RMAP_NESTED_IS_SINGLE_ENTRY & ((u64) (node))) ? \ + ((struct llist_node *) ((pos) = NULL)) : \ + (pos)->list.next)), true); \ + (pos) = llist_entry((node), typeof(*(pos)), list)) + +struct kvm_nested_guest *kvmhv_get_nested(struct kvm *kvm, int l1_lpid, + bool create); +void kvmhv_put_nested(struct kvm_nested_guest *gp); +int kvmhv_nested_next_lpid(struct kvm *kvm, int lpid); + +/* Encoding of first parameter for H_TLB_INVALIDATE */ +#define H_TLBIE_P1_ENC(ric, prs, r) (___PPC_RIC(ric) | ___PPC_PRS(prs) | \ + ___PPC_R(r)) /* Power architecture requires HPT is at least 256kiB, at most 64TiB */ #define PPC_MIN_HPT_ORDER 18 @@ -435,6 +537,7 @@ static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm) } extern void kvmppc_mmu_debugfs_init(struct kvm *kvm); +extern void kvmhv_radix_debugfs_init(struct kvm *kvm); extern void kvmhv_rm_send_ipi(int cpu); @@ -482,7 +585,7 @@ static inline u64 sanitize_msr(u64 msr) #ifdef CONFIG_PPC_TRANSACTIONAL_MEM static inline void copy_from_checkpoint(struct kvm_vcpu *vcpu) { - vcpu->arch.cr = vcpu->arch.cr_tm; + vcpu->arch.regs.ccr = vcpu->arch.cr_tm; vcpu->arch.regs.xer = vcpu->arch.xer_tm; vcpu->arch.regs.link = vcpu->arch.lr_tm; vcpu->arch.regs.ctr = vcpu->arch.ctr_tm; @@ -499,7 +602,7 @@ static inline void copy_from_checkpoint(struct kvm_vcpu *vcpu) static inline void copy_to_checkpoint(struct kvm_vcpu *vcpu) { - vcpu->arch.cr_tm = vcpu->arch.cr; + vcpu->arch.cr_tm = vcpu->arch.regs.ccr; vcpu->arch.xer_tm = vcpu->arch.regs.xer; vcpu->arch.lr_tm = vcpu->arch.regs.link; vcpu->arch.ctr_tm = vcpu->arch.regs.ctr; @@ -515,6 +618,17 @@ static inline void copy_to_checkpoint(struct kvm_vcpu *vcpu) } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ +extern int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte, + unsigned long gpa, unsigned int level, + unsigned long mmu_seq, unsigned int lpid, + unsigned long *rmapp, struct rmap_nested **n_rmap); +extern void kvmhv_insert_nest_rmap(struct kvm *kvm, unsigned long *rmapp, + struct rmap_nested **n_rmap); +extern void kvmhv_remove_nest_rmap_range(struct kvm *kvm, + struct kvm_memory_slot *memslot, + unsigned long gpa, unsigned long hpa, + unsigned long nbytes); + #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #endif /* __ASM_KVM_BOOK3S_64_H__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index d978fdf698af..eb3ba6390108 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -25,6 +25,9 @@ #define XICS_MFRR 0xc #define XICS_IPI 2 /* interrupt source # for IPIs */ +/* LPIDs we support with this build -- runtime limit may be lower */ +#define KVMPPC_NR_LPIDS (LPID_RSVD + 1) + /* Maximum number of threads per physical core */ #define MAX_SMT_THREADS 8 diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h index d513e3ed1c65..f0cef625f17c 100644 --- a/arch/powerpc/include/asm/kvm_booke.h +++ b/arch/powerpc/include/asm/kvm_booke.h @@ -46,12 +46,12 @@ static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num) static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val) { - vcpu->arch.cr = val; + vcpu->arch.regs.ccr = val; } static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu) { - return vcpu->arch.cr; + return vcpu->arch.regs.ccr; } static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, ulong val) diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 906bcbdfd2a1..fac6f631ed29 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -46,6 +46,7 @@ #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE #include <asm/kvm_book3s_asm.h> /* for MAX_SMT_THREADS */ #define KVM_MAX_VCPU_ID (MAX_SMT_THREADS * KVM_MAX_VCORES) +#define KVM_MAX_NESTED_GUESTS KVMPPC_NR_LPIDS #else #define KVM_MAX_VCPU_ID KVM_MAX_VCPUS @@ -94,6 +95,7 @@ struct dtl_entry; struct kvmppc_vcpu_book3s; struct kvmppc_book3s_shadow_vcpu; +struct kvm_nested_guest; struct kvm_vm_stat { ulong remote_tlb_flush; @@ -287,10 +289,12 @@ struct kvm_arch { u8 radix; u8 fwnmi_enabled; bool threads_indep; + bool nested_enable; pgd_t *pgtable; u64 process_table; struct dentry *debugfs_dir; struct dentry *htab_dentry; + struct dentry *radix_dentry; struct kvm_resize_hpt *resize_hpt; /* protected by kvm->lock */ #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE @@ -311,6 +315,9 @@ struct kvm_arch { #endif struct kvmppc_ops *kvm_ops; #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + u64 l1_ptcr; + int max_nested_lpid; + struct kvm_nested_guest *nested_guests[KVM_MAX_NESTED_GUESTS]; /* This array can grow quite large, keep it at the end */ struct kvmppc_vcore *vcores[KVM_MAX_VCORES]; #endif @@ -360,7 +367,9 @@ struct kvmppc_pte { bool may_write : 1; bool may_execute : 1; unsigned long wimg; + unsigned long rc; u8 page_size; /* MMU_PAGE_xxx */ + u8 page_shift; }; struct kvmppc_mmu { @@ -537,8 +546,6 @@ struct kvm_vcpu_arch { ulong tar; #endif - u32 cr; - #ifdef CONFIG_PPC_BOOK3S ulong hflags; ulong guest_owned_ext; @@ -707,6 +714,7 @@ struct kvm_vcpu_arch { u8 hcall_needed; u8 epr_flags; /* KVMPPC_EPR_xxx */ u8 epr_needed; + u8 external_oneshot; /* clear external irq after delivery */ u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */ @@ -781,6 +789,10 @@ struct kvm_vcpu_arch { u32 emul_inst; u32 online; + + /* For support of nested guests */ + struct kvm_nested_guest *nested; + u32 nested_vcpu_id; #endif #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index e991821dd7fa..9b89b1918dfc 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -194,9 +194,7 @@ extern struct kvmppc_spapr_tce_table *kvmppc_find_table( (iommu_tce_check_ioba((stt)->page_shift, (stt)->offset, \ (stt)->size, (ioba), (npages)) ? \ H_PARAMETER : H_SUCCESS) -extern long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *tt, - unsigned long tce); -extern long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa, +extern long kvmppc_tce_to_ua(struct kvm *kvm, unsigned long tce, unsigned long *ua, unsigned long **prmap); extern void kvmppc_tce_put(struct kvmppc_spapr_tce_table *tt, unsigned long idx, unsigned long tce); @@ -327,6 +325,7 @@ struct kvmppc_ops { int (*set_smt_mode)(struct kvm *kvm, unsigned long mode, unsigned long flags); void (*giveup_ext)(struct kvm_vcpu *vcpu, ulong msr); + int (*enable_nested)(struct kvm *kvm); }; extern struct kvmppc_ops *kvmppc_hv_ops; @@ -585,6 +584,7 @@ extern int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval); extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status); +extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu); #else static inline int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server, u32 priority) { return -1; } @@ -607,6 +607,7 @@ static inline int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval) { retur static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status) { return -ENODEV; } +static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { } #endif /* CONFIG_KVM_XIVE */ /* @@ -652,6 +653,7 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server, unsigned long mfrr); int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr); int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr); +void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu); /* * Host-side operations we want to set up while running in real diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index a47de82fb8e2..8311869005fa 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -35,7 +35,7 @@ struct machdep_calls { char *name; #ifdef CONFIG_PPC64 void __iomem * (*ioremap)(phys_addr_t addr, unsigned long size, - unsigned long flags, void *caller); + pgprot_t prot, void *caller); void (*iounmap)(volatile void __iomem *token); #ifdef CONFIG_PM @@ -108,6 +108,7 @@ struct machdep_calls { /* Early exception handlers called in realmode */ int (*hmi_exception_early)(struct pt_regs *regs); + long (*machine_check_early)(struct pt_regs *regs); /* Called during machine check exception to retrive fixup address. */ bool (*mce_check_early_recovery)(struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index 3a1226e9b465..a8b8903e1844 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -210,4 +210,7 @@ extern void release_mce_event(void); extern void machine_check_queue_event(void); extern void machine_check_print_event_info(struct machine_check_event *evt, bool user_mode); +#ifdef CONFIG_PPC_BOOK3S_64 +void flush_and_reload_slb(void); +#endif /* CONFIG_PPC_BOOK3S_64 */ #endif /* __ASM_PPC64_MCE_H__ */ diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 13ea441ac531..eb20eb3b8fb0 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -309,6 +309,21 @@ static inline u16 get_mm_addr_key(struct mm_struct *mm, unsigned long address) */ #define MMU_PAGE_COUNT 16 +/* + * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS + * if we increase SECTIONS_WIDTH we will not store node details in page->flags and + * page_to_nid does a page->section->node lookup + * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce + * memory requirements with large number of sections. + * 51 bits is the max physical real address on POWER9 + */ +#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) && \ + defined (CONFIG_PPC_64K_PAGES) +#define MAX_PHYSMEM_BITS 51 +#else +#define MAX_PHYSMEM_BITS 46 +#endif + #ifdef CONFIG_PPC_BOOK3S_64 #include <asm/book3s/64/mmu.h> #else /* CONFIG_PPC_BOOK3S_64 */ diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index b694d6af1150..0381394a425b 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -82,7 +82,7 @@ static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea) { int context_id; - context_id = get_ea_context(&mm->context, ea); + context_id = get_user_context(&mm->context, ea); if (!context_id) return true; return false; diff --git a/arch/powerpc/include/asm/mpic.h b/arch/powerpc/include/asm/mpic.h index fad8ddd697ac..0abf2e7fd222 100644 --- a/arch/powerpc/include/asm/mpic.h +++ b/arch/powerpc/include/asm/mpic.h @@ -393,7 +393,14 @@ extern struct bus_type mpic_subsys; #define MPIC_REGSET_TSI108 MPIC_REGSET(1) /* Tsi108/109 PIC */ /* Get the version of primary MPIC */ +#ifdef CONFIG_MPIC extern u32 fsl_mpic_primary_get_version(void); +#else +static inline u32 fsl_mpic_primary_get_version(void) +{ + return 0; +} +#endif /* Allocate the controller structure and setup the linux irq descs * for the range if interrupts passed in. No HW initialization is diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index a507a65b0866..f7b129a83054 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -128,14 +128,65 @@ extern int icache_44x_need_flush; #include <asm/nohash/32/pte-8xx.h> #endif -/* And here we include common definitions */ -#include <asm/pte-common.h> +/* + * Location of the PFN in the PTE. Most 32-bit platforms use the same + * as _PAGE_SHIFT here (ie, naturally aligned). + * Platform who don't just pre-define the value so we don't override it here. + */ +#ifndef PTE_RPN_SHIFT +#define PTE_RPN_SHIFT (PAGE_SHIFT) +#endif + +/* + * The mask covered by the RPN must be a ULL on 32-bit platforms with + * 64-bit PTEs. + */ +#if defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) +#define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1)) +#else +#define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) +#endif + +/* + * _PAGE_CHG_MASK masks of bits that are to be preserved across + * pgprot changes. + */ +#define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPECIAL) #ifndef __ASSEMBLY__ #define pte_clear(mm, addr, ptep) \ do { pte_update(ptep, ~0, 0); } while (0) +#ifndef pte_mkwrite +static inline pte_t pte_mkwrite(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_RW); +} +#endif + +static inline pte_t pte_mkdirty(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_DIRTY); +} + +static inline pte_t pte_mkyoung(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_ACCESSED); +} + +#ifndef pte_wrprotect +static inline pte_t pte_wrprotect(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_RW); +} +#endif + +static inline pte_t pte_mkexec(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_EXEC); +} + #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_bad(pmd) (pmd_val(pmd) & _PMD_BAD) #define pmd_present(pmd) (pmd_val(pmd) & _PMD_PRESENT_MASK) @@ -244,7 +295,10 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - pte_update(ptep, (_PAGE_RW | _PAGE_HWWRITE), _PAGE_RO); + unsigned long clr = ~pte_val(pte_wrprotect(__pte(~0))); + unsigned long set = pte_val(pte_wrprotect(__pte(0))); + + pte_update(ptep, clr, set); } static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) @@ -258,9 +312,10 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, int psize) { - unsigned long set = pte_val(entry) & - (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); - unsigned long clr = ~pte_val(entry) & (_PAGE_RO | _PAGE_NA); + pte_t pte_set = pte_mkyoung(pte_mkdirty(pte_mkwrite(pte_mkexec(__pte(0))))); + pte_t pte_clr = pte_mkyoung(pte_mkdirty(pte_mkwrite(pte_mkexec(__pte(~0))))); + unsigned long set = pte_val(entry) & pte_val(pte_set); + unsigned long clr = ~pte_val(entry) & ~pte_val(pte_clr); pte_update(ptep, clr, set); @@ -323,7 +378,7 @@ static inline int pte_young(pte_t pte) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) >> 3 }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val << 3 }) -int map_kernel_page(unsigned long va, phys_addr_t pa, int flags); +int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-40x.h b/arch/powerpc/include/asm/nohash/32/pte-40x.h index bb4b3a4b92a0..661f4599f2fc 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-40x.h +++ b/arch/powerpc/include/asm/nohash/32/pte-40x.h @@ -50,13 +50,56 @@ #define _PAGE_EXEC 0x200 /* hardware: EX permission */ #define _PAGE_ACCESSED 0x400 /* software: R: page referenced */ +/* No page size encoding in the linux PTE */ +#define _PAGE_PSIZE 0 + +/* cache related flags non existing on 40x */ +#define _PAGE_COHERENT 0 + +#define _PAGE_KERNEL_RO 0 +#define _PAGE_KERNEL_ROX _PAGE_EXEC +#define _PAGE_KERNEL_RW (_PAGE_DIRTY | _PAGE_RW | _PAGE_HWWRITE) +#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW | _PAGE_HWWRITE | _PAGE_EXEC) + #define _PMD_PRESENT 0x400 /* PMD points to page of PTEs */ +#define _PMD_PRESENT_MASK _PMD_PRESENT #define _PMD_BAD 0x802 #define _PMD_SIZE_4M 0x0c0 #define _PMD_SIZE_16M 0x0e0 +#define _PMD_USER 0 + +#define _PTE_NONE_MASK 0 /* Until my rework is finished, 40x still needs atomic PTE updates */ #define PTE_ATOMIC_UPDATES 1 +#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) +#define _PAGE_BASE (_PAGE_BASE_NC) + +/* Permission masks used to generate the __P and __S table */ +#define PAGE_NONE __pgprot(_PAGE_BASE) +#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) +#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) +#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) +#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) +#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) + +#ifndef __ASSEMBLY__ +static inline pte_t pte_wrprotect(pte_t pte) +{ + return __pte(pte_val(pte) & ~(_PAGE_RW | _PAGE_HWWRITE)); +} + +#define pte_wrprotect pte_wrprotect + +static inline pte_t pte_mkclean(pte_t pte) +{ + return __pte(pte_val(pte) & ~(_PAGE_DIRTY | _PAGE_HWWRITE)); +} + +#define pte_mkclean pte_mkclean +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_NOHASH_32_PTE_40x_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-44x.h b/arch/powerpc/include/asm/nohash/32/pte-44x.h index f812c0272364..78bc304f750e 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-44x.h +++ b/arch/powerpc/include/asm/nohash/32/pte-44x.h @@ -85,14 +85,44 @@ #define _PAGE_NO_CACHE 0x00000400 /* H: I bit */ #define _PAGE_WRITETHRU 0x00000800 /* H: W bit */ +/* No page size encoding in the linux PTE */ +#define _PAGE_PSIZE 0 + +#define _PAGE_KERNEL_RO 0 +#define _PAGE_KERNEL_ROX _PAGE_EXEC +#define _PAGE_KERNEL_RW (_PAGE_DIRTY | _PAGE_RW) +#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC) + /* TODO: Add large page lowmem mapping support */ #define _PMD_PRESENT 0 #define _PMD_PRESENT_MASK (PAGE_MASK) #define _PMD_BAD (~PAGE_MASK) +#define _PMD_USER 0 /* ERPN in a PTE never gets cleared, ignore it */ #define _PTE_NONE_MASK 0xffffffff00000000ULL +/* + * We define 2 sets of base prot bits, one for basic pages (ie, + * cacheable kernel and user pages) and one for non cacheable + * pages. We always set _PAGE_COHERENT when SMP is enabled or + * the processor might need it for DMA coherency. + */ +#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) +#if defined(CONFIG_SMP) +#define _PAGE_BASE (_PAGE_BASE_NC | _PAGE_COHERENT) +#else +#define _PAGE_BASE (_PAGE_BASE_NC) +#endif + +/* Permission masks used to generate the __P and __S table */ +#define PAGE_NONE __pgprot(_PAGE_BASE) +#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) +#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) +#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) +#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) +#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_NOHASH_32_PTE_44x_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h index f04cb46ae8a1..6bfe041ef59d 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h @@ -29,10 +29,10 @@ */ /* Definitions for 8xx embedded chips. */ -#define _PAGE_PRESENT 0x0001 /* Page is valid */ -#define _PAGE_NO_CACHE 0x0002 /* I: cache inhibit */ -#define _PAGE_PRIVILEGED 0x0004 /* No ASID (context) compare */ -#define _PAGE_HUGE 0x0008 /* SPS: Small Page Size (1 if 16k, 512k or 8M)*/ +#define _PAGE_PRESENT 0x0001 /* V: Page is valid */ +#define _PAGE_NO_CACHE 0x0002 /* CI: cache inhibit */ +#define _PAGE_SH 0x0004 /* SH: No ASID (context) compare */ +#define _PAGE_SPS 0x0008 /* SPS: Small Page Size (1 if 16k, 512k or 8M)*/ #define _PAGE_DIRTY 0x0100 /* C: page changed */ /* These 4 software bits must be masked out when the L2 entry is loaded @@ -46,18 +46,95 @@ #define _PAGE_NA 0x0200 /* Supervisor NA, User no access */ #define _PAGE_RO 0x0600 /* Supervisor RO, User no access */ +/* cache related flags non existing on 8xx */ +#define _PAGE_COHERENT 0 +#define _PAGE_WRITETHRU 0 + +#define _PAGE_KERNEL_RO (_PAGE_SH | _PAGE_RO) +#define _PAGE_KERNEL_ROX (_PAGE_SH | _PAGE_RO | _PAGE_EXEC) +#define _PAGE_KERNEL_RW (_PAGE_SH | _PAGE_DIRTY) +#define _PAGE_KERNEL_RWX (_PAGE_SH | _PAGE_DIRTY | _PAGE_EXEC) + #define _PMD_PRESENT 0x0001 +#define _PMD_PRESENT_MASK _PMD_PRESENT #define _PMD_BAD 0x0fd0 #define _PMD_PAGE_MASK 0x000c #define _PMD_PAGE_8M 0x000c #define _PMD_PAGE_512K 0x0004 #define _PMD_USER 0x0020 /* APG 1 */ +#define _PTE_NONE_MASK 0 + /* Until my rework is finished, 8xx still needs atomic PTE updates */ #define PTE_ATOMIC_UPDATES 1 #ifdef CONFIG_PPC_16K_PAGES -#define _PAGE_PSIZE _PAGE_HUGE +#define _PAGE_PSIZE _PAGE_SPS +#else +#define _PAGE_PSIZE 0 +#endif + +#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE) +#define _PAGE_BASE (_PAGE_BASE_NC) + +/* Permission masks used to generate the __P and __S table */ +#define PAGE_NONE __pgprot(_PAGE_BASE | _PAGE_NA) +#define PAGE_SHARED __pgprot(_PAGE_BASE) +#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_EXEC) +#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_RO) +#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_RO | _PAGE_EXEC) +#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_RO) +#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_RO | _PAGE_EXEC) + +#ifndef __ASSEMBLY__ +static inline pte_t pte_wrprotect(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_RO); +} + +#define pte_wrprotect pte_wrprotect + +static inline int pte_write(pte_t pte) +{ + return !(pte_val(pte) & _PAGE_RO); +} + +#define pte_write pte_write + +static inline pte_t pte_mkwrite(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_RO); +} + +#define pte_mkwrite pte_mkwrite + +static inline bool pte_user(pte_t pte) +{ + return !(pte_val(pte) & _PAGE_SH); +} + +#define pte_user pte_user + +static inline pte_t pte_mkprivileged(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SH); +} + +#define pte_mkprivileged pte_mkprivileged + +static inline pte_t pte_mkuser(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_SH); +} + +#define pte_mkuser pte_mkuser + +static inline pte_t pte_mkhuge(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SPS); +} + +#define pte_mkhuge pte_mkhuge #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h b/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h index d1ee24e9e137..0fc1bd42bb3e 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h +++ b/arch/powerpc/include/asm/nohash/32/pte-fsl-booke.h @@ -31,11 +31,44 @@ #define _PAGE_WRITETHRU 0x00400 /* H: W bit */ #define _PAGE_SPECIAL 0x00800 /* S: Special page */ +#define _PAGE_KERNEL_RO 0 +#define _PAGE_KERNEL_ROX _PAGE_EXEC +#define _PAGE_KERNEL_RW (_PAGE_DIRTY | _PAGE_RW) +#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW | _PAGE_EXEC) + +/* No page size encoding in the linux PTE */ +#define _PAGE_PSIZE 0 + #define _PMD_PRESENT 0 #define _PMD_PRESENT_MASK (PAGE_MASK) #define _PMD_BAD (~PAGE_MASK) +#define _PMD_USER 0 + +#define _PTE_NONE_MASK 0 #define PTE_WIMGE_SHIFT (6) +/* + * We define 2 sets of base prot bits, one for basic pages (ie, + * cacheable kernel and user pages) and one for non cacheable + * pages. We always set _PAGE_COHERENT when SMP is enabled or + * the processor might need it for DMA coherency. + */ +#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED) +#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC) +#define _PAGE_BASE (_PAGE_BASE_NC | _PAGE_COHERENT) +#else +#define _PAGE_BASE (_PAGE_BASE_NC) +#endif + +/* Permission masks used to generate the __P and __S table */ +#define PAGE_NONE __pgprot(_PAGE_BASE) +#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) +#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) +#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) +#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) +#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_NOHASH_32_PTE_FSL_BOOKE_H */ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 7cd6809f4d33..dc6bb9da3f23 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -89,11 +89,47 @@ * Include the PTE bits definitions */ #include <asm/nohash/pte-book3e.h> -#include <asm/pte-common.h> + +#define _PAGE_SAO 0 + +#define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) + +/* + * _PAGE_CHG_MASK masks of bits that are to be preserved across + * pgprot changes. + */ +#define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPECIAL) + +#define H_PAGE_4K_PFN 0 #ifndef __ASSEMBLY__ /* pte_clear moved to later in this file */ +static inline pte_t pte_mkwrite(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_RW); +} + +static inline pte_t pte_mkdirty(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_DIRTY); +} + +static inline pte_t pte_mkyoung(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_ACCESSED); +} + +static inline pte_t pte_wrprotect(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_RW); +} + +static inline pte_t pte_mkexec(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_EXEC); +} + #define PMD_BAD_BITS (PTE_TABLE_SIZE-1) #define PUD_BAD_BITS (PMD_TABLE_SIZE-1) @@ -327,8 +363,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) #define __swp_entry_to_pte(x) __pte((x).val) -extern int map_kernel_page(unsigned long ea, unsigned long pa, - unsigned long flags); +int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot); extern int __meminit vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys); diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index b321c82b3624..70ff23974b59 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -8,18 +8,50 @@ #include <asm/nohash/32/pgtable.h> #endif +/* Permission masks used for kernel mappings */ +#define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) +#define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NO_CACHE) +#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ + _PAGE_NO_CACHE | _PAGE_GUARDED) +#define PAGE_KERNEL_X __pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX) +#define PAGE_KERNEL_RO __pgprot(_PAGE_BASE | _PAGE_KERNEL_RO) +#define PAGE_KERNEL_ROX __pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX) + +/* + * Protection used for kernel text. We want the debuggers to be able to + * set breakpoints anywhere, so don't write protect the kernel text + * on platforms where such control is possible. + */ +#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\ + defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE) +#define PAGE_KERNEL_TEXT PAGE_KERNEL_X +#else +#define PAGE_KERNEL_TEXT PAGE_KERNEL_ROX +#endif + +/* Make modules code happy. We don't set RO yet */ +#define PAGE_KERNEL_EXEC PAGE_KERNEL_X + +/* Advertise special mapping type for AGP */ +#define PAGE_AGP (PAGE_KERNEL_NC) +#define HAVE_PAGE_AGP + #ifndef __ASSEMBLY__ /* Generic accessors to PTE bits */ +#ifndef pte_write static inline int pte_write(pte_t pte) { - return (pte_val(pte) & (_PAGE_RW | _PAGE_RO)) != _PAGE_RO; + return pte_val(pte) & _PAGE_RW; } +#endif static inline int pte_read(pte_t pte) { return 1; } static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; } static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; } -static inline pgprot_t pte_pgprot(pte_t pte) { return __pgprot(pte_val(pte) & PAGE_PROT_BITS); } +static inline bool pte_hashpte(pte_t pte) { return false; } +static inline bool pte_ci(pte_t pte) { return pte_val(pte) & _PAGE_NO_CACHE; } +static inline bool pte_exec(pte_t pte) { return pte_val(pte) & _PAGE_EXEC; } #ifdef CONFIG_NUMA_BALANCING /* @@ -29,8 +61,7 @@ static inline pgprot_t pte_pgprot(pte_t pte) { return __pgprot(pte_val(pte) & PA */ static inline int pte_protnone(pte_t pte) { - return (pte_val(pte) & - (_PAGE_PRESENT | _PAGE_USER)) == _PAGE_PRESENT; + return pte_present(pte) && !pte_user(pte); } static inline int pmd_protnone(pmd_t pmd) @@ -44,6 +75,23 @@ static inline int pte_present(pte_t pte) return pte_val(pte) & _PAGE_PRESENT; } +static inline bool pte_hw_valid(pte_t pte) +{ + return pte_val(pte) & _PAGE_PRESENT; +} + +/* + * Don't just check for any non zero bits in __PAGE_USER, since for book3e + * and PTE_64BIT, PAGE_KERNEL_X contains _PAGE_BAP_SR which is also in + * _PAGE_USER. Need to explicitly match _PAGE_BAP_UR bit in that case too. + */ +#ifndef pte_user +static inline bool pte_user(pte_t pte) +{ + return (pte_val(pte) & _PAGE_USER) == _PAGE_USER; +} +#endif + /* * We only find page table entry in the last level * Hence no need for other accessors @@ -77,53 +125,53 @@ static inline unsigned long pte_pfn(pte_t pte) { return pte_val(pte) >> PTE_RPN_SHIFT; } /* Generic modifiers for PTE bits */ -static inline pte_t pte_wrprotect(pte_t pte) +static inline pte_t pte_exprotect(pte_t pte) { - pte_basic_t ptev; - - ptev = pte_val(pte) & ~(_PAGE_RW | _PAGE_HWWRITE); - ptev |= _PAGE_RO; - return __pte(ptev); + return __pte(pte_val(pte) & ~_PAGE_EXEC); } +#ifndef pte_mkclean static inline pte_t pte_mkclean(pte_t pte) { - return __pte(pte_val(pte) & ~(_PAGE_DIRTY | _PAGE_HWWRITE)); + return __pte(pte_val(pte) & ~_PAGE_DIRTY); } +#endif static inline pte_t pte_mkold(pte_t pte) { return __pte(pte_val(pte) & ~_PAGE_ACCESSED); } -static inline pte_t pte_mkwrite(pte_t pte) +static inline pte_t pte_mkpte(pte_t pte) { - pte_basic_t ptev; - - ptev = pte_val(pte) & ~_PAGE_RO; - ptev |= _PAGE_RW; - return __pte(ptev); + return pte; } -static inline pte_t pte_mkdirty(pte_t pte) +static inline pte_t pte_mkspecial(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_DIRTY); + return __pte(pte_val(pte) | _PAGE_SPECIAL); } -static inline pte_t pte_mkyoung(pte_t pte) +#ifndef pte_mkhuge +static inline pte_t pte_mkhuge(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_ACCESSED); + return __pte(pte_val(pte)); } +#endif -static inline pte_t pte_mkspecial(pte_t pte) +#ifndef pte_mkprivileged +static inline pte_t pte_mkprivileged(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_SPECIAL); + return __pte(pte_val(pte) & ~_PAGE_USER); } +#endif -static inline pte_t pte_mkhuge(pte_t pte) +#ifndef pte_mkuser +static inline pte_t pte_mkuser(pte_t pte) { - return __pte(pte_val(pte) | _PAGE_HUGE); + return __pte(pte_val(pte) | _PAGE_USER); } +#endif static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { @@ -197,6 +245,8 @@ extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addre #if _PAGE_WRITETHRU != 0 #define pgprot_cached_wthru(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ _PAGE_COHERENT | _PAGE_WRITETHRU)) +#else +#define pgprot_cached_wthru(prot) pgprot_noncached(prot) #endif #define pgprot_cached_noncoherent(prot) \ diff --git a/arch/powerpc/include/asm/nohash/pte-book3e.h b/arch/powerpc/include/asm/nohash/pte-book3e.h index 12730b81cd98..dd40d200f274 100644 --- a/arch/powerpc/include/asm/nohash/pte-book3e.h +++ b/arch/powerpc/include/asm/nohash/pte-book3e.h @@ -77,7 +77,48 @@ #define _PMD_PRESENT 0 #define _PMD_PRESENT_MASK (PAGE_MASK) #define _PMD_BAD (~PAGE_MASK) +#define _PMD_USER 0 +#else +#define _PTE_NONE_MASK 0 +#endif + +/* + * We define 2 sets of base prot bits, one for basic pages (ie, + * cacheable kernel and user pages) and one for non cacheable + * pages. We always set _PAGE_COHERENT when SMP is enabled or + * the processor might need it for DMA coherency. + */ +#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE) +#if defined(CONFIG_SMP) +#define _PAGE_BASE (_PAGE_BASE_NC | _PAGE_COHERENT) +#else +#define _PAGE_BASE (_PAGE_BASE_NC) #endif +/* Permission masks used to generate the __P and __S table */ +#define PAGE_NONE __pgprot(_PAGE_BASE) +#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) +#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | _PAGE_EXEC) +#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER) +#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) +#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER) +#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_EXEC) + +#ifndef __ASSEMBLY__ +static inline pte_t pte_mkprivileged(pte_t pte) +{ + return __pte((pte_val(pte) & ~_PAGE_USER) | _PAGE_PRIVILEGED); +} + +#define pte_mkprivileged pte_mkprivileged + +static inline pte_t pte_mkuser(pte_t pte) +{ + return __pte((pte_val(pte) & ~_PAGE_PRIVILEGED) | _PAGE_USER); +} + +#define pte_mkuser pte_mkuser +#endif /* __ASSEMBLY__ */ + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_NOHASH_PTE_BOOK3E_H */ diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index 8365353330b4..870fb7b239ea 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -1050,6 +1050,7 @@ enum OpalSysCooling { enum { OPAL_REBOOT_NORMAL = 0, OPAL_REBOOT_PLATFORM_ERROR = 1, + OPAL_REBOOT_FULL_IPL = 2, }; /* Argument to OPAL_PCI_TCE_KILL */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index ad4f16164619..e843bc5d1a0f 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -113,7 +113,13 @@ struct paca_struct { * on the linear mapping */ /* SLB related definitions */ u16 vmalloc_sllp; - u16 slb_cache_ptr; + u8 slb_cache_ptr; + u8 stab_rr; /* stab/slb round-robin counter */ +#ifdef CONFIG_DEBUG_VM + u8 in_kernel_slb_handler; +#endif + u32 slb_used_bitmap; /* Bitmaps for first 32 SLB entries. */ + u32 slb_kern_bitmap; u32 slb_cache[SLB_CACHE_ENTRIES]; #endif /* CONFIG_PPC_BOOK3S_64 */ @@ -160,7 +166,6 @@ struct paca_struct { */ struct task_struct *__current; /* Pointer to current */ u64 kstack; /* Saved Kernel stack addr */ - u64 stab_rr; /* stab/slb round-robin counter */ u64 saved_r1; /* r1 save for RTAS calls or PM or EE=0 */ u64 saved_msr; /* MSR saved here by enter_rtas */ u16 trap_save; /* Used when bad stack is encountered */ @@ -250,6 +255,15 @@ struct paca_struct { #ifdef CONFIG_PPC_PSERIES u8 *mce_data_buf; /* buffer to hold per cpu rtas errlog */ #endif /* CONFIG_PPC_PSERIES */ + +#ifdef CONFIG_PPC_BOOK3S_64 + /* Capture SLB related old contents in MCE handler. */ + struct slb_entry *mce_faulty_slbs; + u16 slb_save_cache_ptr; +#endif /* CONFIG_PPC_BOOK3S_64 */ +#ifdef CONFIG_STACKPROTECTOR + unsigned long canary; +#endif } ____cacheline_aligned; extern void copy_mm_to_paca(struct mm_struct *mm); diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 14c79a7dc855..9679b7519a35 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -20,6 +20,25 @@ struct mm_struct; #include <asm/nohash/pgtable.h> #endif /* !CONFIG_PPC_BOOK3S */ +/* Note due to the way vm flags are laid out, the bits are XWR */ +#define __P000 PAGE_NONE +#define __P001 PAGE_READONLY +#define __P010 PAGE_COPY +#define __P011 PAGE_COPY +#define __P100 PAGE_READONLY_X +#define __P101 PAGE_READONLY_X +#define __P110 PAGE_COPY_X +#define __P111 PAGE_COPY_X + +#define __S000 PAGE_NONE +#define __S001 PAGE_READONLY +#define __S010 PAGE_SHARED +#define __S011 PAGE_SHARED +#define __S100 PAGE_READONLY_X +#define __S101 PAGE_READONLY_X +#define __S110 PAGE_SHARED_X +#define __S111 PAGE_SHARED_X + #ifndef __ASSEMBLY__ #include <asm/tlbflush.h> @@ -27,6 +46,16 @@ struct mm_struct; /* Keep these as a macros to avoid include dependency mess */ #define pte_page(x) pfn_to_page(pte_pfn(x)) #define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) +/* + * Select all bits except the pfn + */ +static inline pgprot_t pte_pgprot(pte_t pte) +{ + unsigned long pte_flags; + + pte_flags = pte_val(pte) & ~PTE_RPN_MASK; + return __pgprot(pte_flags); +} /* * ZERO_PAGE is a global shared page that is always zero: used diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h index 7f627e3f4da4..630eb8b1b7ed 100644 --- a/arch/powerpc/include/asm/pnv-pci.h +++ b/arch/powerpc/include/asm/pnv-pci.h @@ -54,7 +54,6 @@ void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs, struct pnv_php_slot { struct hotplug_slot slot; - struct hotplug_slot_info slot_info; uint64_t id; char *name; int slot_no; @@ -72,6 +71,7 @@ struct pnv_php_slot { struct pci_dev *pdev; struct pci_bus *bus; bool power_state_check; + u8 attention_state; void *fdt; void *dt; struct of_changeset ocs; diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 665af14850e4..6093bc8f74e5 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -104,6 +104,7 @@ #define OP_31_XOP_LHZUX 311 #define OP_31_XOP_MSGSNDP 142 #define OP_31_XOP_MSGCLRP 174 +#define OP_31_XOP_TLBIE 306 #define OP_31_XOP_MFSPR 339 #define OP_31_XOP_LWAX 341 #define OP_31_XOP_LHAX 343 diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index 726288048652..f67da277d652 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -58,6 +58,7 @@ void eeh_save_bars(struct eeh_dev *edev); int rtas_write_config(struct pci_dn *, int where, int size, u32 val); int rtas_read_config(struct pci_dn *, int where, int size, u32 *val); void eeh_pe_state_mark(struct eeh_pe *pe, int state); +void eeh_pe_mark_isolated(struct eeh_pe *pe); void eeh_pe_state_clear(struct eeh_pe *pe, int state); void eeh_pe_state_mark_with_cfg(struct eeh_pe *pe, int state); void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode); diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 52fadded5c1e..7d04d60a39c9 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -32,9 +32,9 @@ /* Default SMT priority is set to 3. Use 11- 13bits to save priority. */ #define PPR_PRIORITY 3 #ifdef __ASSEMBLY__ -#define INIT_PPR (PPR_PRIORITY << 50) +#define DEFAULT_PPR (PPR_PRIORITY << 50) #else -#define INIT_PPR ((u64)PPR_PRIORITY << 50) +#define DEFAULT_PPR ((u64)PPR_PRIORITY << 50) #endif /* __ASSEMBLY__ */ #endif /* CONFIG_PPC64 */ @@ -273,6 +273,7 @@ struct thread_struct { #endif /* CONFIG_HAVE_HW_BREAKPOINT */ struct arch_hw_breakpoint hw_brk; /* info on the hardware breakpoint */ unsigned long trap_nr; /* last trap # on this thread */ + u8 load_slb; /* Ages out SLB preload cache entries */ u8 load_fp; #ifdef CONFIG_ALTIVEC u8 load_vec; @@ -341,7 +342,6 @@ struct thread_struct { * onwards. */ int dscr_inherit; - unsigned long ppr; /* used to save/restore SMT priority */ unsigned long tidr; #endif #ifdef CONFIG_PPC_BOOK3S_64 @@ -389,7 +389,6 @@ struct thread_struct { .regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \ .addr_limit = KERNEL_DS, \ .fpexc_mode = 0, \ - .ppr = INIT_PPR, \ .fscr = FSCR_TAR | FSCR_EBB \ } #endif diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h deleted file mode 100644 index bef56141a549..000000000000 --- a/arch/powerpc/include/asm/pte-common.h +++ /dev/null @@ -1,219 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Included from asm/pgtable-*.h only ! */ - -/* - * Some bits are only used on some cpu families... Make sure that all - * the undefined gets a sensible default - */ -#ifndef _PAGE_HASHPTE -#define _PAGE_HASHPTE 0 -#endif -#ifndef _PAGE_HWWRITE -#define _PAGE_HWWRITE 0 -#endif -#ifndef _PAGE_EXEC -#define _PAGE_EXEC 0 -#endif -#ifndef _PAGE_ENDIAN -#define _PAGE_ENDIAN 0 -#endif -#ifndef _PAGE_COHERENT -#define _PAGE_COHERENT 0 -#endif -#ifndef _PAGE_WRITETHRU -#define _PAGE_WRITETHRU 0 -#endif -#ifndef _PAGE_4K_PFN -#define _PAGE_4K_PFN 0 -#endif -#ifndef _PAGE_SAO -#define _PAGE_SAO 0 -#endif -#ifndef _PAGE_PSIZE -#define _PAGE_PSIZE 0 -#endif -/* _PAGE_RO and _PAGE_RW shall not be defined at the same time */ -#ifndef _PAGE_RO -#define _PAGE_RO 0 -#else -#define _PAGE_RW 0 -#endif - -#ifndef _PAGE_PTE -#define _PAGE_PTE 0 -#endif -/* At least one of _PAGE_PRIVILEGED or _PAGE_USER must be defined */ -#ifndef _PAGE_PRIVILEGED -#define _PAGE_PRIVILEGED 0 -#else -#ifndef _PAGE_USER -#define _PAGE_USER 0 -#endif -#endif -#ifndef _PAGE_NA -#define _PAGE_NA 0 -#endif -#ifndef _PAGE_HUGE -#define _PAGE_HUGE 0 -#endif - -#ifndef _PMD_PRESENT_MASK -#define _PMD_PRESENT_MASK _PMD_PRESENT -#endif -#ifndef _PMD_USER -#define _PMD_USER 0 -#endif -#ifndef _PAGE_KERNEL_RO -#define _PAGE_KERNEL_RO (_PAGE_PRIVILEGED | _PAGE_RO) -#endif -#ifndef _PAGE_KERNEL_ROX -#define _PAGE_KERNEL_ROX (_PAGE_PRIVILEGED | _PAGE_RO | _PAGE_EXEC) -#endif -#ifndef _PAGE_KERNEL_RW -#define _PAGE_KERNEL_RW (_PAGE_PRIVILEGED | _PAGE_DIRTY | _PAGE_RW | \ - _PAGE_HWWRITE) -#endif -#ifndef _PAGE_KERNEL_RWX -#define _PAGE_KERNEL_RWX (_PAGE_PRIVILEGED | _PAGE_DIRTY | _PAGE_RW | \ - _PAGE_HWWRITE | _PAGE_EXEC) -#endif -#ifndef _PAGE_HPTEFLAGS -#define _PAGE_HPTEFLAGS _PAGE_HASHPTE -#endif -#ifndef _PTE_NONE_MASK -#define _PTE_NONE_MASK _PAGE_HPTEFLAGS -#endif - -#ifndef __ASSEMBLY__ - -/* - * Don't just check for any non zero bits in __PAGE_USER, since for book3e - * and PTE_64BIT, PAGE_KERNEL_X contains _PAGE_BAP_SR which is also in - * _PAGE_USER. Need to explicitly match _PAGE_BAP_UR bit in that case too. - */ -static inline bool pte_user(pte_t pte) -{ - return (pte_val(pte) & (_PAGE_USER | _PAGE_PRIVILEGED)) == _PAGE_USER; -} -#endif /* __ASSEMBLY__ */ - -/* Location of the PFN in the PTE. Most 32-bit platforms use the same - * as _PAGE_SHIFT here (ie, naturally aligned). - * Platform who don't just pre-define the value so we don't override it here - */ -#ifndef PTE_RPN_SHIFT -#define PTE_RPN_SHIFT (PAGE_SHIFT) -#endif - -/* The mask covered by the RPN must be a ULL on 32-bit platforms with - * 64-bit PTEs - */ -#if defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) -#define PTE_RPN_MASK (~((1ULL<<PTE_RPN_SHIFT)-1)) -#else -#define PTE_RPN_MASK (~((1UL<<PTE_RPN_SHIFT)-1)) -#endif - -/* _PAGE_CHG_MASK masks of bits that are to be preserved across - * pgprot changes - */ -#define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \ - _PAGE_ACCESSED | _PAGE_SPECIAL) - -/* Mask of bits returned by pte_pgprot() */ -#define PAGE_PROT_BITS (_PAGE_GUARDED | _PAGE_COHERENT | _PAGE_NO_CACHE | \ - _PAGE_WRITETHRU | _PAGE_ENDIAN | _PAGE_4K_PFN | \ - _PAGE_USER | _PAGE_ACCESSED | _PAGE_RO | _PAGE_NA | \ - _PAGE_PRIVILEGED | \ - _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | _PAGE_EXEC) - -/* - * We define 2 sets of base prot bits, one for basic pages (ie, - * cacheable kernel and user pages) and one for non cacheable - * pages. We always set _PAGE_COHERENT when SMP is enabled or - * the processor might need it for DMA coherency. - */ -#define _PAGE_BASE_NC (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_PSIZE) -#if defined(CONFIG_SMP) || defined(CONFIG_PPC_STD_MMU) || \ - defined(CONFIG_PPC_E500MC) -#define _PAGE_BASE (_PAGE_BASE_NC | _PAGE_COHERENT) -#else -#define _PAGE_BASE (_PAGE_BASE_NC) -#endif - -/* Permission masks used to generate the __P and __S table, - * - * Note:__pgprot is defined in arch/powerpc/include/asm/page.h - * - * Write permissions imply read permissions for now (we could make write-only - * pages on BookE but we don't bother for now). Execute permission control is - * possible on platforms that define _PAGE_EXEC - * - * Note due to the way vm flags are laid out, the bits are XWR - */ -#define PAGE_NONE __pgprot(_PAGE_BASE | _PAGE_NA) -#define PAGE_SHARED __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW) -#define PAGE_SHARED_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RW | \ - _PAGE_EXEC) -#define PAGE_COPY __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RO) -#define PAGE_COPY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RO | \ - _PAGE_EXEC) -#define PAGE_READONLY __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RO) -#define PAGE_READONLY_X __pgprot(_PAGE_BASE | _PAGE_USER | _PAGE_RO | \ - _PAGE_EXEC) - -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY -#define __P100 PAGE_READONLY_X -#define __P101 PAGE_READONLY_X -#define __P110 PAGE_COPY_X -#define __P111 PAGE_COPY_X - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_READONLY_X -#define __S101 PAGE_READONLY_X -#define __S110 PAGE_SHARED_X -#define __S111 PAGE_SHARED_X - -/* Permission masks used for kernel mappings */ -#define PAGE_KERNEL __pgprot(_PAGE_BASE | _PAGE_KERNEL_RW) -#define PAGE_KERNEL_NC __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ - _PAGE_NO_CACHE) -#define PAGE_KERNEL_NCG __pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | \ - _PAGE_NO_CACHE | _PAGE_GUARDED) -#define PAGE_KERNEL_X __pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX) -#define PAGE_KERNEL_RO __pgprot(_PAGE_BASE | _PAGE_KERNEL_RO) -#define PAGE_KERNEL_ROX __pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX) - -/* Protection used for kernel text. We want the debuggers to be able to - * set breakpoints anywhere, so don't write protect the kernel text - * on platforms where such control is possible. - */ -#if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\ - defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE) -#define PAGE_KERNEL_TEXT PAGE_KERNEL_X -#else -#define PAGE_KERNEL_TEXT PAGE_KERNEL_ROX -#endif - -/* Make modules code happy. We don't set RO yet */ -#define PAGE_KERNEL_EXEC PAGE_KERNEL_X - -/* Advertise special mapping type for AGP */ -#define PAGE_AGP (PAGE_KERNEL_NC) -#define HAVE_PAGE_AGP - -#ifndef _PAGE_READ -/* if not defined, we should not find _PAGE_WRITE too */ -#define _PAGE_READ 0 -#define _PAGE_WRITE _PAGE_RW -#endif - -#ifndef H_PAGE_4K_PFN -#define H_PAGE_4K_PFN 0 -#endif diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 5b480e1d5909..f73886a1a7f5 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -26,6 +26,37 @@ #include <uapi/asm/ptrace.h> #include <asm/asm-const.h> +#ifndef __ASSEMBLY__ +struct pt_regs +{ + union { + struct user_pt_regs user_regs; + struct { + unsigned long gpr[32]; + unsigned long nip; + unsigned long msr; + unsigned long orig_gpr3; + unsigned long ctr; + unsigned long link; + unsigned long xer; + unsigned long ccr; +#ifdef CONFIG_PPC64 + unsigned long softe; +#else + unsigned long mq; +#endif + unsigned long trap; + unsigned long dar; + unsigned long dsisr; + unsigned long result; + }; + }; + +#ifdef CONFIG_PPC64 + unsigned long ppr; +#endif +}; +#endif #ifdef __powerpc64__ @@ -102,6 +133,11 @@ static inline long regs_return_value(struct pt_regs *regs) return -regs->gpr[3]; } +static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) +{ + regs->gpr[3] = rc; +} + #ifdef __powerpc64__ #define user_mode(regs) ((((regs)->msr) >> MSR_PR_LG) & 0x1) #else diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index e5b314ed054e..de52c3166ba4 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -118,11 +118,16 @@ #define MSR_TS_S __MASK(MSR_TS_S_LG) /* Transaction Suspended */ #define MSR_TS_T __MASK(MSR_TS_T_LG) /* Transaction Transactional */ #define MSR_TS_MASK (MSR_TS_T | MSR_TS_S) /* Transaction State bits */ -#define MSR_TM_ACTIVE(x) (((x) & MSR_TS_MASK) != 0) /* Transaction active? */ #define MSR_TM_RESV(x) (((x) & MSR_TS_MASK) == MSR_TS_MASK) /* Reserved */ #define MSR_TM_TRANSACTIONAL(x) (((x) & MSR_TS_MASK) == MSR_TS_T) #define MSR_TM_SUSPENDED(x) (((x) & MSR_TS_MASK) == MSR_TS_S) +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +#define MSR_TM_ACTIVE(x) (((x) & MSR_TS_MASK) != 0) /* Transaction active? */ +#else +#define MSR_TM_ACTIVE(x) 0 +#endif + #if defined(CONFIG_PPC_BOOK3S_64) #define MSR_64BIT MSR_SF @@ -415,6 +420,7 @@ #define HFSCR_DSCR __MASK(FSCR_DSCR_LG) #define HFSCR_VECVSX __MASK(FSCR_VECVSX_LG) #define HFSCR_FP __MASK(FSCR_FP_LG) +#define HFSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56) /* interrupt cause */ #define SPRN_TAR 0x32f /* Target Address Register */ #define SPRN_LPCR 0x13E /* LPAR Control Register */ #define LPCR_VPM0 ASM_CONST(0x8000000000000000) @@ -766,6 +772,7 @@ #define SPRN_HSRR0 0x13A /* Save/Restore Register 0 */ #define SPRN_HSRR1 0x13B /* Save/Restore Register 1 */ #define HSRR1_DENORM 0x00100000 /* Denorm exception */ +#define HSRR1_HISI_WRITE 0x00010000 /* HISI bcs couldn't update mem */ #define SPRN_TBCTL 0x35f /* PA6T Timebase control register */ #define TBCTL_FREEZE 0x0000000000000000ull /* Freeze all tbs */ diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 71e393c46a49..bb38dd67d47d 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -125,6 +125,7 @@ struct rtas_suspend_me_data { #define RTAS_TYPE_INFO 0xE2 #define RTAS_TYPE_DEALLOC 0xE3 #define RTAS_TYPE_DUMP 0xE4 +#define RTAS_TYPE_HOTPLUG 0xE5 /* I don't add PowerMGM events right now, this is a different topic */ #define RTAS_TYPE_PMGM_POWER_SW_ON 0x60 #define RTAS_TYPE_PMGM_POWER_SW_OFF 0x61 @@ -185,11 +186,23 @@ static inline uint8_t rtas_error_disposition(const struct rtas_error_log *elog) return (elog->byte1 & 0x18) >> 3; } +static inline +void rtas_set_disposition_recovered(struct rtas_error_log *elog) +{ + elog->byte1 &= ~0x18; + elog->byte1 |= (RTAS_DISP_FULLY_RECOVERED << 3); +} + static inline uint8_t rtas_error_extended(const struct rtas_error_log *elog) { return (elog->byte1 & 0x04) >> 2; } +static inline uint8_t rtas_error_initiator(const struct rtas_error_log *elog) +{ + return (elog->byte2 & 0xf0) >> 4; +} + #define rtas_error_type(x) ((x)->byte3) static inline @@ -275,6 +288,7 @@ inline uint32_t rtas_ext_event_company_id(struct rtas_ext_event_log_v6 *ext_log) #define PSERIES_ELOG_SECT_ID_CALL_HOME (('C' << 8) | 'H') #define PSERIES_ELOG_SECT_ID_USER_DEF (('U' << 8) | 'D') #define PSERIES_ELOG_SECT_ID_HOTPLUG (('H' << 8) | 'P') +#define PSERIES_ELOG_SECT_ID_MCE (('M' << 8) | 'C') /* Vendor specific Platform Event Log Format, Version 6, section header */ struct pseries_errorlog { @@ -316,6 +330,7 @@ struct pseries_hp_errorlog { #define PSERIES_HP_ELOG_RESOURCE_MEM 2 #define PSERIES_HP_ELOG_RESOURCE_SLOT 3 #define PSERIES_HP_ELOG_RESOURCE_PHB 4 +#define PSERIES_HP_ELOG_RESOURCE_PMEM 6 #define PSERIES_HP_ELOG_ACTION_ADD 1 #define PSERIES_HP_ELOG_ACTION_REMOVE 2 diff --git a/arch/powerpc/include/asm/slice.h b/arch/powerpc/include/asm/slice.h index e40406cf5628..a595461c9cb0 100644 --- a/arch/powerpc/include/asm/slice.h +++ b/arch/powerpc/include/asm/slice.h @@ -32,6 +32,7 @@ void slice_set_range_psize(struct mm_struct *mm, unsigned long start, unsigned long len, unsigned int psize); void slice_init_new_context_exec(struct mm_struct *mm); +void slice_setup_new_exec(void); #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 95b66a0c639b..41695745032c 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -100,6 +100,7 @@ static inline void set_hard_smp_processor_id(int cpu, int phys) DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map); DECLARE_PER_CPU(cpumask_var_t, cpu_l2_cache_map); DECLARE_PER_CPU(cpumask_var_t, cpu_core_map); +DECLARE_PER_CPU(cpumask_var_t, cpu_smallcore_map); static inline struct cpumask *cpu_sibling_mask(int cpu) { @@ -116,6 +117,11 @@ static inline struct cpumask *cpu_l2_cache_mask(int cpu) return per_cpu(cpu_l2_cache_map, cpu); } +static inline struct cpumask *cpu_smallcore_mask(int cpu) +{ + return per_cpu(cpu_smallcore_map, cpu); +} + extern int cpu_to_core_id(int cpu); /* Since OpenPIC has only 4 IPIs, we use slightly different message numbers. @@ -166,6 +172,11 @@ static inline const struct cpumask *cpu_sibling_mask(int cpu) return cpumask_of(cpu); } +static inline const struct cpumask *cpu_smallcore_mask(int cpu) +{ + return cpumask_of(cpu); +} + #endif /* CONFIG_SMP */ #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h index 28f5dae25db6..68da49320592 100644 --- a/arch/powerpc/include/asm/sparsemem.h +++ b/arch/powerpc/include/asm/sparsemem.h @@ -9,17 +9,6 @@ * MAX_PHYSMEM_BITS 2^N: how much memory we can have in that space */ #define SECTION_SIZE_BITS 24 -/* - * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS - * if we increase SECTIONS_WIDTH we will not store node details in page->flags and - * page_to_nid does a page->section->node lookup - * Hence only increase for VMEMMAP. - */ -#ifdef CONFIG_SPARSEMEM_VMEMMAP -#define MAX_PHYSMEM_BITS 47 -#else -#define MAX_PHYSMEM_BITS 46 -#endif #endif /* CONFIG_SPARSEMEM */ diff --git a/arch/powerpc/include/asm/stackprotector.h b/arch/powerpc/include/asm/stackprotector.h new file mode 100644 index 000000000000..1c8460e23583 --- /dev/null +++ b/arch/powerpc/include/asm/stackprotector.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * GCC stack protector support. + * + */ + +#ifndef _ASM_STACKPROTECTOR_H +#define _ASM_STACKPROTECTOR_H + +#include <linux/random.h> +#include <linux/version.h> +#include <asm/reg.h> +#include <asm/current.h> +#include <asm/paca.h> + +/* + * Initialize the stackprotector canary value. + * + * NOTE: this must only be called from functions that never return, + * and it must always be inlined. + */ +static __always_inline void boot_init_stack_canary(void) +{ + unsigned long canary; + + /* Try to get a semi random initial value. */ + canary = get_random_canary(); + canary ^= mftb(); + canary ^= LINUX_VERSION_CODE; + canary &= CANARY_MASK; + + current->stack_canary = canary; +#ifdef CONFIG_PPC64 + get_paca()->canary = canary; +#endif +} + +#endif /* _ASM_STACKPROTECTOR_H */ diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 3c0002044bc9..544cac0474cb 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -29,6 +29,7 @@ #include <asm/page.h> #include <asm/accounting.h> +#define SLB_PRELOAD_NR 16U /* * low level task data. */ @@ -44,6 +45,10 @@ struct thread_info { #if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC32) struct cpu_accounting_data accounting; #endif + unsigned char slb_preload_nr; + unsigned char slb_preload_tail; + u32 slb_preload_esid[SLB_PRELOAD_NR]; + /* low level flags - has atomic operations done on it */ unsigned long flags ____cacheline_aligned_in_smp; }; @@ -72,6 +77,12 @@ static inline struct thread_info *current_thread_info(void) } extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); + +#ifdef CONFIG_PPC_BOOK3S_64 +void arch_setup_new_exec(void); +#define arch_setup_new_exec arch_setup_new_exec +#endif + #endif /* __ASSEMBLY__ */ /* @@ -81,7 +92,7 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src #define TIF_SIGPENDING 1 /* signal pending */ #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ #define TIF_FSCHECK 3 /* Check FS is USER_DS on return */ -#define TIF_32BIT 4 /* 32 bit binary */ +#define TIF_SYSCALL_EMU 4 /* syscall emulation active */ #define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */ #define TIF_PATCH_PENDING 6 /* pending live patching update */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ @@ -100,6 +111,7 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src #define TIF_ELF2ABI 18 /* function descriptors must die! */ #endif #define TIF_POLLING_NRFLAG 19 /* true if poll_idle() is polling TIF_NEED_RESCHED */ +#define TIF_32BIT 20 /* 32 bit binary */ /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) @@ -120,9 +132,10 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src #define _TIF_EMULATE_STACK_STORE (1<<TIF_EMULATE_STACK_STORE) #define _TIF_NOHZ (1<<TIF_NOHZ) #define _TIF_FSCHECK (1<<TIF_FSCHECK) +#define _TIF_SYSCALL_EMU (1<<TIF_SYSCALL_EMU) #define _TIF_SYSCALL_DOTRACE (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \ - _TIF_NOHZ) + _TIF_NOHZ | _TIF_SYSCALL_EMU) #define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h index d018e8602694..58ef8c43a89d 100644 --- a/arch/powerpc/include/asm/trace.h +++ b/arch/powerpc/include/asm/trace.h @@ -201,6 +201,21 @@ TRACE_EVENT(tlbie, __entry->r) ); +TRACE_EVENT(tlbia, + + TP_PROTO(unsigned long id), + TP_ARGS(id), + TP_STRUCT__entry( + __field(unsigned long, id) + ), + + TP_fast_assign( + __entry->id = id; + ), + + TP_printk("ctx.id=0x%lx", __entry->id) +); + #endif /* _TRACE_POWERPC_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index bac225bb7f64..15bea9a0f260 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -260,7 +260,7 @@ do { \ ({ \ long __gu_err; \ __long_type(*(ptr)) __gu_val; \ - const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ + __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ __chk_user_ptr(ptr); \ if (!is_kernel_addr((unsigned long)__gu_addr)) \ might_fault(); \ @@ -274,7 +274,7 @@ do { \ ({ \ long __gu_err = -EFAULT; \ __long_type(*(ptr)) __gu_val = 0; \ - const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ + __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ might_fault(); \ if (access_ok(VERIFY_READ, __gu_addr, (size))) { \ barrier_nospec(); \ @@ -288,7 +288,7 @@ do { \ ({ \ long __gu_err; \ __long_type(*(ptr)) __gu_val; \ - const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ + __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ __chk_user_ptr(ptr); \ barrier_nospec(); \ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index c19379f0a32e..b0de85b477e1 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -22,6 +22,7 @@ #include <linux/compiler.h> #include <linux/linkage.h> +#define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_STAT64 #define __ARCH_WANT_SYS_ALARM @@ -35,7 +36,6 @@ #define __ARCH_WANT_SYS_SOCKETCALL #define __ARCH_WANT_SYS_FADVISE64 #define __ARCH_WANT_SYS_GETPGRP -#define __ARCH_WANT_SYS_LLSEEK #define __ARCH_WANT_SYS_NICE #define __ARCH_WANT_SYS_OLD_GETRLIMIT #define __ARCH_WANT_SYS_OLD_UNAME @@ -47,6 +47,7 @@ #endif #ifdef CONFIG_PPC64 #define __ARCH_WANT_COMPAT_SYS_TIME +#define __ARCH_WANT_SYS_UTIME32 #define __ARCH_WANT_SYS_NEWFSTATAT #define __ARCH_WANT_COMPAT_SYS_SENDFILE #endif diff --git a/arch/powerpc/include/asm/user.h b/arch/powerpc/include/asm/user.h index 5c0e082eae7b..99443b8594e7 100644 --- a/arch/powerpc/include/asm/user.h +++ b/arch/powerpc/include/asm/user.h @@ -31,7 +31,7 @@ * to write an integer number of pages. */ struct user { - struct pt_regs regs; /* entire machine state */ + struct user_pt_regs regs; /* entire machine state */ size_t u_tsize; /* text size (pages) */ size_t u_dsize; /* data size (pages) */ size_t u_ssize; /* stack size (pages) */ diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 1b32b56a03d3..8c876c166ef2 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -634,6 +634,7 @@ struct kvm_ppc_cpu_char { #define KVM_REG_PPC_DEC_EXPIRY (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe) #define KVM_REG_PPC_ONLINE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf) +#define KVM_REG_PPC_PTCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc0) /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs diff --git a/arch/powerpc/include/uapi/asm/ptrace.h b/arch/powerpc/include/uapi/asm/ptrace.h index 5e3edc2a7634..f5f1ccc740fc 100644 --- a/arch/powerpc/include/uapi/asm/ptrace.h +++ b/arch/powerpc/include/uapi/asm/ptrace.h @@ -29,7 +29,12 @@ #ifndef __ASSEMBLY__ -struct pt_regs { +#ifdef __KERNEL__ +struct user_pt_regs +#else +struct pt_regs +#endif +{ unsigned long gpr[32]; unsigned long nip; unsigned long msr; @@ -160,6 +165,10 @@ struct pt_regs { #define PTRACE_GETVSRREGS 0x1b #define PTRACE_SETVSRREGS 0x1c +/* Syscall emulation defines */ +#define PTRACE_SYSEMU 0x1d +#define PTRACE_SYSEMU_SINGLESTEP 0x1e + /* * Get or set a debug register. The first 16 are DABR registers and the * second 16 are IABR registers. diff --git a/arch/powerpc/include/uapi/asm/sigcontext.h b/arch/powerpc/include/uapi/asm/sigcontext.h index 2fbe485acdb4..630aeda56d59 100644 --- a/arch/powerpc/include/uapi/asm/sigcontext.h +++ b/arch/powerpc/include/uapi/asm/sigcontext.h @@ -22,7 +22,11 @@ struct sigcontext { #endif unsigned long handler; unsigned long oldmask; - struct pt_regs __user *regs; +#ifdef __KERNEL__ + struct user_pt_regs __user *regs; +#else + struct pt_regs *regs; +#endif #ifdef __powerpc64__ elf_gregset_t gp_regs; elf_fpregset_t fp_regs; |