diff options
Diffstat (limited to 'arch/powerpc/include/asm')
75 files changed, 1373 insertions, 606 deletions
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 2542ea15d338..3196d227e351 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -1,4 +1,3 @@ -generic-y += clkdev.h generic-y += div64.h generic-y += export.h generic-y += irq_regs.h diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 016579ef16d3..c615abdce119 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -16,6 +16,7 @@ #define PGD_INDEX_SIZE (32 - PGDIR_SHIFT) #define PMD_CACHE_INDEX PMD_INDEX_SIZE +#define PUD_CACHE_INDEX PUD_INDEX_SIZE #ifndef __ASSEMBLY__ #define PTE_TABLE_SIZE (sizeof(pte_t) << PTE_INDEX_SIZE) @@ -311,6 +312,29 @@ static inline int pte_present(pte_t pte) return pte_val(pte) & _PAGE_PRESENT; } +/* + * We only find page table entry in the last level + * Hence no need for other accessors + */ +#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 ((pteval & need_pte_bits) != need_pte_bits) + return false; + + return true; +} + /* Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. * diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 197ced1eaaa0..67c5475311ee 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -17,6 +17,12 @@ #define H_PUD_TABLE_SIZE (sizeof(pud_t) << H_PUD_INDEX_SIZE) #define H_PGD_TABLE_SIZE (sizeof(pgd_t) << H_PGD_INDEX_SIZE) +#define H_PAGE_F_GIX_SHIFT 53 +#define H_PAGE_F_SECOND _RPAGE_RPN44 /* HPTE is in 2ndary HPTEG */ +#define H_PAGE_F_GIX (_RPAGE_RPN43 | _RPAGE_RPN42 | _RPAGE_RPN41) +#define H_PAGE_BUSY _RPAGE_RSV1 /* software: PTE & hash are busy */ +#define H_PAGE_HASHPTE _RPAGE_RSV2 /* software: PTE & hash are busy */ + /* PTE flags to conserve for HPTE identification */ #define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | \ H_PAGE_F_SECOND | H_PAGE_F_GIX) @@ -49,6 +55,21 @@ static inline int hash__hugepd_ok(hugepd_t hpd) } #endif +/* + * 4K PTE format is different from 64K PTE format. Saving the hash_slot is just + * a matter of returning the PTE bits that need to be modified. On 64K PTE, + * things are a little more involved and hence needs many more parameters to + * accomplish the same. However we want to abstract this out from the caller by + * keeping the prototype consistent across the two formats. + */ +static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte, + unsigned int subpg_index, unsigned long hidx, + int offset) +{ + return (hidx << H_PAGE_F_GIX_SHIFT) & + (H_PAGE_F_SECOND | H_PAGE_F_GIX); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline char *get_hpte_slot_array(pmd_t *pmdp) @@ -101,8 +122,6 @@ extern pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma, extern void hash__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable); extern pgtable_t hash__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); -extern void hash__pmdp_huge_split_prepare(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp); extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); extern int hash__has_transparent_hugepage(void); diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index 8d40cf03cb67..3bcf269f8f55 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -13,21 +13,17 @@ */ #define H_PAGE_COMBO _RPAGE_RPN0 /* this is a combo 4k page */ #define H_PAGE_4K_PFN _RPAGE_RPN1 /* PFN is for a single 4k page */ +#define H_PAGE_BUSY _RPAGE_RPN44 /* software: PTE & hash are busy */ +#define H_PAGE_HASHPTE _RPAGE_RPN43 /* PTE has associated HPTE */ + /* * We need to differentiate between explicit huge page and THP huge * page, since THP huge page also need to track real subpage details */ #define H_PAGE_THP_HUGE H_PAGE_4K_PFN -/* - * Used to track subpage group valid if H_PAGE_COMBO is set - * This overloads H_PAGE_F_GIX and H_PAGE_F_SECOND - */ -#define H_PAGE_COMBO_VALID (H_PAGE_F_GIX | H_PAGE_F_SECOND) - /* PTE flags to conserve for HPTE identification */ -#define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_F_SECOND | \ - H_PAGE_F_GIX | H_PAGE_HASHPTE | H_PAGE_COMBO) +#define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | H_PAGE_COMBO) /* * we support 16 fragments per PTE page of 64K size. */ @@ -49,30 +45,64 @@ * generic accessors and iterators here */ #define __real_pte __real_pte -static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) +static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset) { real_pte_t rpte; unsigned long *hidxp; rpte.pte = pte; - rpte.hidx = 0; - if (pte_val(pte) & H_PAGE_COMBO) { - /* - * Make sure we order the hidx load against the H_PAGE_COMBO - * check. The store side ordering is done in __hash_page_4K - */ - smp_rmb(); - hidxp = (unsigned long *)(ptep + PTRS_PER_PTE); - rpte.hidx = *hidxp; - } + + /* + * Ensure that we do not read the hidx before we read the PTE. Because + * the writer side is expected to finish writing the hidx first followed + * by the PTE, by using smp_wmb(). pte_set_hash_slot() ensures that. + */ + smp_rmb(); + + hidxp = (unsigned long *)(ptep + offset); + rpte.hidx = *hidxp; return rpte; } +/* + * shift the hidx representation by one-modulo-0xf; i.e hidx 0 is respresented + * as 1, 1 as 2,... , and 0xf as 0. This convention lets us represent a + * invalid hidx 0xf with a 0x0 bit value. PTEs are anyway zero'd when + * allocated. We dont have to zero them gain; thus save on the initialization. + */ +#define HIDX_UNSHIFT_BY_ONE(x) ((x + 0xfUL) & 0xfUL) /* shift backward by one */ +#define HIDX_SHIFT_BY_ONE(x) ((x + 0x1UL) & 0xfUL) /* shift forward by one */ +#define HIDX_BITS(x, index) (x << (index << 2)) +#define BITS_TO_HIDX(x, index) ((x >> (index << 2)) & 0xfUL) +#define INVALID_RPTE_HIDX 0x0UL + static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index) { - if ((pte_val(rpte.pte) & H_PAGE_COMBO)) - return (rpte.hidx >> (index<<2)) & 0xf; - return (pte_val(rpte.pte) >> H_PAGE_F_GIX_SHIFT) & 0xf; + return HIDX_UNSHIFT_BY_ONE(BITS_TO_HIDX(rpte.hidx, index)); +} + +/* + * Commit the hidx and return PTE bits that needs to be modified. The caller is + * expected to modify the PTE bits accordingly and commit the PTE to memory. + */ +static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte, + unsigned int subpg_index, + unsigned long hidx, int offset) +{ + unsigned long *hidxp = (unsigned long *)(ptep + offset); + + rpte.hidx &= ~HIDX_BITS(0xfUL, subpg_index); + *hidxp = rpte.hidx | HIDX_BITS(HIDX_SHIFT_BY_ONE(hidx), subpg_index); + + /* + * Anyone reading PTE must ensure hidx bits are read after reading the + * PTE by using the read-side barrier smp_rmb(). __real_pte() can be + * used for that. + */ + smp_wmb(); + + /* No PTE bits to be modified, return 0x0UL */ + return 0x0UL; } #define __rpte_to_pte(r) ((r).pte) @@ -111,13 +141,18 @@ static inline int hash__remap_4k_pfn(struct vm_area_struct *vma, unsigned long a } #define H_PTE_TABLE_SIZE PTE_FRAG_SIZE -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined (CONFIG_HUGETLB_PAGE) #define H_PMD_TABLE_SIZE ((sizeof(pmd_t) << PMD_INDEX_SIZE) + \ (sizeof(unsigned long) << PMD_INDEX_SIZE)) #else #define H_PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE) #endif +#ifdef CONFIG_HUGETLB_PAGE +#define H_PUD_TABLE_SIZE ((sizeof(pud_t) << PUD_INDEX_SIZE) + \ + (sizeof(unsigned long) << PUD_INDEX_SIZE)) +#else #define H_PUD_TABLE_SIZE (sizeof(pud_t) << PUD_INDEX_SIZE) +#endif #define H_PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE) #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -203,8 +238,6 @@ extern pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma, extern void hash__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable); extern pgtable_t hash__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); -extern void hash__pmdp_huge_split_prepare(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp); extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); extern int hash__has_transparent_hugepage(void); diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index ecb1239d74f4..935adcd92a81 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -9,11 +9,6 @@ * */ #define H_PTE_NONE_MASK _PAGE_HPTEFLAGS -#define H_PAGE_F_GIX_SHIFT 56 -#define H_PAGE_BUSY _RPAGE_RSV1 /* software: PTE & hash are busy */ -#define H_PAGE_F_SECOND _RPAGE_RSV2 /* HPTE is in 2ndary HPTEG */ -#define H_PAGE_F_GIX (_RPAGE_RSV3 | _RPAGE_RSV4 | _RPAGE_RPN44) -#define H_PAGE_HASHPTE _RPAGE_RPN43 /* PTE has associated HPTE */ #ifdef CONFIG_PPC_64K_PAGES #include <asm/book3s/64/hash-64k.h> @@ -28,7 +23,8 @@ H_PUD_INDEX_SIZE + H_PGD_INDEX_SIZE + PAGE_SHIFT) #define H_PGTABLE_RANGE (ASM_CONST(1) << H_PGTABLE_EADDR_SIZE) -#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_PPC_64K_PAGES) +#if (defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)) && \ + defined(CONFIG_PPC_64K_PAGES) /* * only with hash 64k we need to use the second half of pmd page table * to store pointer to deposited pgtable_t @@ -38,6 +34,16 @@ #define H_PMD_CACHE_INDEX H_PMD_INDEX_SIZE #endif /* + * We store the slot details in the second half of page table. + * Increase the pud level table so that hugetlb ptes can be stored + * at pud level. + */ +#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_PPC_64K_PAGES) +#define H_PUD_CACHE_INDEX (H_PUD_INDEX_SIZE + 1) +#else +#define H_PUD_CACHE_INDEX (H_PUD_INDEX_SIZE) +#endif +/* * Define the address range of the kernel non-linear virtual area */ #define H_KERN_VIRT_START ASM_CONST(0xD000000000000000) @@ -167,6 +173,9 @@ static inline int hash__pte_none(pte_t pte) return (pte_val(pte) & ~H_PTE_NONE_MASK) == 0; } +unsigned long pte_get_hash_gslot(unsigned long vpn, unsigned long shift, + int ssize, real_pte_t rpte, unsigned int subpg_index); + /* This low level function performs the actual PTE insertion * Setting the PTE depends on the MMU type and other factors. It's * an horrible mess that I'm not going to try to clean up now but diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index e91e115a816f..50ed64fba4ae 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -90,6 +90,8 @@ #define HPTE_R_PP0 ASM_CONST(0x8000000000000000) #define HPTE_R_TS ASM_CONST(0x4000000000000000) #define HPTE_R_KEY_HI ASM_CONST(0x3000000000000000) +#define HPTE_R_KEY_BIT0 ASM_CONST(0x2000000000000000) +#define HPTE_R_KEY_BIT1 ASM_CONST(0x1000000000000000) #define HPTE_R_RPN_SHIFT 12 #define HPTE_R_RPN ASM_CONST(0x0ffffffffffff000) #define HPTE_R_RPN_3_0 ASM_CONST(0x01fffffffffff000) @@ -104,6 +106,9 @@ #define HPTE_R_C ASM_CONST(0x0000000000000080) #define HPTE_R_R ASM_CONST(0x0000000000000100) #define HPTE_R_KEY_LO ASM_CONST(0x0000000000000e00) +#define HPTE_R_KEY_BIT2 ASM_CONST(0x0000000000000800) +#define HPTE_R_KEY_BIT3 ASM_CONST(0x0000000000000400) +#define HPTE_R_KEY_BIT4 ASM_CONST(0x0000000000000200) #define HPTE_R_KEY (HPTE_R_KEY_LO | HPTE_R_KEY_HI) #define HPTE_V_1TB_SEG ASM_CONST(0x4000000000000000) diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index c9448e19847a..0abeb0e2d616 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -108,6 +108,16 @@ typedef struct { #ifdef CONFIG_SPAPR_TCE_IOMMU struct list_head iommu_group_mem_list; #endif + +#ifdef CONFIG_PPC_MEM_KEYS + /* + * Each bit represents one protection key. + * bit set -> key allocated + * bit unset -> key available for allocation + */ + u32 pkey_allocation_map; + s16 execute_only_pkey; /* key holding execute-only protection */ +#endif } mm_context_t; /* diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 1fcfa425cefa..4746bc68d446 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -73,10 +73,16 @@ static inline void radix__pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pgd_t *pgd_alloc(struct mm_struct *mm) { + pgd_t *pgd; + if (radix_enabled()) return radix__pgd_alloc(mm); - return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), - pgtable_gfp_flags(mm, GFP_KERNEL)); + + pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), + pgtable_gfp_flags(mm, GFP_KERNEL)); + memset(pgd, 0, PGD_TABLE_SIZE); + + return pgd; } static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) @@ -93,13 +99,13 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), + return kmem_cache_alloc(PGT_CACHE(PUD_CACHE_INDEX), pgtable_gfp_flags(mm, GFP_KERNEL)); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) { - kmem_cache_free(PGT_CACHE(PUD_INDEX_SIZE), pud); + kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud); } static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) @@ -115,7 +121,7 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, * ahead and flush the page walk cache */ flush_tlb_pgtable(tlb, address); - pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE); + pgtable_free_tlb(tlb, pud, PUD_CACHE_INDEX); } static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 44697817ccc6..a6b9f1d74600 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -14,8 +14,9 @@ */ #define _PAGE_BIT_SWAP_TYPE 0 +#define _PAGE_NA 0 #define _PAGE_RO 0 -#define _PAGE_SHARED 0 +#define _PAGE_USER 0 #define _PAGE_EXEC 0x00001 /* execute permission */ #define _PAGE_WRITE 0x00002 /* write access allowed */ @@ -39,6 +40,7 @@ #define _RPAGE_RSV2 0x0800000000000000UL #define _RPAGE_RSV3 0x0400000000000000UL #define _RPAGE_RSV4 0x0200000000000000UL +#define _RPAGE_RSV5 0x00040UL #define _PAGE_PTE 0x4000000000000000UL /* distinguishes PTEs from pointers */ #define _PAGE_PRESENT 0x8000000000000000UL /* pte contains a translation */ @@ -58,6 +60,25 @@ /* Max physical address bit as per radix table */ #define _RPAGE_PA_MAX 57 +#ifdef CONFIG_PPC_MEM_KEYS +#ifdef CONFIG_PPC_64K_PAGES +#define H_PTE_PKEY_BIT0 _RPAGE_RSV1 +#define H_PTE_PKEY_BIT1 _RPAGE_RSV2 +#else /* CONFIG_PPC_64K_PAGES */ +#define H_PTE_PKEY_BIT0 0 /* _RPAGE_RSV1 is not available */ +#define H_PTE_PKEY_BIT1 0 /* _RPAGE_RSV2 is not available */ +#endif /* CONFIG_PPC_64K_PAGES */ +#define H_PTE_PKEY_BIT2 _RPAGE_RSV3 +#define H_PTE_PKEY_BIT3 _RPAGE_RSV4 +#define H_PTE_PKEY_BIT4 _RPAGE_RSV5 +#else /* CONFIG_PPC_MEM_KEYS */ +#define H_PTE_PKEY_BIT0 0 +#define H_PTE_PKEY_BIT1 0 +#define H_PTE_PKEY_BIT2 0 +#define H_PTE_PKEY_BIT3 0 +#define H_PTE_PKEY_BIT4 0 +#endif /* CONFIG_PPC_MEM_KEYS */ + /* * Max physical address bit we will use for now. * @@ -121,13 +142,16 @@ #define _PAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \ _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE | \ _PAGE_SOFT_DIRTY) + +#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) + _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 @@ -208,11 +232,13 @@ extern unsigned long __pmd_index_size; extern unsigned long __pud_index_size; extern unsigned long __pgd_index_size; extern unsigned long __pmd_cache_index; +extern unsigned long __pud_cache_index; #define PTE_INDEX_SIZE __pte_index_size #define PMD_INDEX_SIZE __pmd_index_size #define PUD_INDEX_SIZE __pud_index_size #define PGD_INDEX_SIZE __pgd_index_size #define PMD_CACHE_INDEX __pmd_cache_index +#define PUD_CACHE_INDEX __pud_cache_index /* * Because of use of pte fragments and THP, size of page table * are not always derived out of index size above. @@ -324,7 +350,7 @@ extern unsigned long pci_io_base; */ #ifndef __real_pte -#define __real_pte(e,p) ((real_pte_t){(e)}) +#define __real_pte(e, p, o) ((real_pte_t){(e)}) #define __rpte_to_pte(r) ((r).pte) #define __rpte_to_hidx(r,index) (pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT) @@ -546,6 +572,40 @@ static inline int pte_present(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 +static inline bool arch_pte_access_permitted(u64 pte, bool write, bool execute) +{ + return true; +} +#endif /* CONFIG_PPC_MEM_KEYS */ + +#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) + return false; + + if ((pteval & clear_pte_bits) == clear_pte_bits) + return false; + + return arch_pte_access_permitted(pte_val(pte), write, 0); +} + /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. @@ -850,6 +910,11 @@ static inline int pud_bad(pud_t pud) return hash__pud_bad(pud); } +#define pud_access_permitted pud_access_permitted +static inline bool pud_access_permitted(pud_t pud, bool write) +{ + return pte_access_permitted(pud_pte(pud), write); +} #define pgd_write(pgd) pte_write(pgd_pte(pgd)) static inline void pgd_set(pgd_t *pgdp, unsigned long val) @@ -889,6 +954,12 @@ static inline int pgd_bad(pgd_t pgd) return hash__pgd_bad(pgd); } +#define pgd_access_permitted pgd_access_permitted +static inline bool pgd_access_permitted(pgd_t pgd, bool write) +{ + return pte_access_permitted(pgd_pte(pgd), write); +} + extern struct page *pgd_page(pgd_t pgd); /* Pointers in the page table tree are physical addresses */ @@ -1009,6 +1080,12 @@ static inline int pmd_protnone(pmd_t pmd) #define __pmd_write(pmd) __pte_write(pmd_pte(pmd)) #define pmd_savedwrite(pmd) pte_savedwrite(pmd_pte(pmd)) +#define pmd_access_permitted pmd_access_permitted +static inline bool pmd_access_permitted(pmd_t pmd, bool write) +{ + return pte_access_permitted(pmd_pte(pmd), write); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot); extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot); @@ -1137,17 +1214,8 @@ static inline pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, } #define __HAVE_ARCH_PMDP_INVALIDATE -extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmdp); - -#define __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE -static inline void pmdp_huge_split_prepare(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp) -{ - if (radix_enabled()) - return radix__pmdp_huge_split_prepare(vma, address, pmdp); - return hash__pmdp_huge_split_prepare(vma, address, pmdp); -} +extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp); #define pmd_move_must_withdraw pmd_move_must_withdraw struct spinlock; diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 19c44e1495ae..365010f66570 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -269,12 +269,6 @@ static inline pmd_t radix__pmd_mkhuge(pmd_t pmd) return __pmd(pmd_val(pmd) | _PAGE_PTE | R_PAGE_LARGE); return __pmd(pmd_val(pmd) | _PAGE_PTE); } -static inline void radix__pmdp_huge_split_prepare(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp) -{ - /* Nothing to do for radix. */ - return; -} extern unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, unsigned long clr, diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h index 849ecaae9e79..64d02a704bcb 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h @@ -51,6 +51,7 @@ static inline void arch_leave_lazy_mmu_mode(void) #define arch_flush_lazy_mmu_mode() do {} while (0) +extern void hash__tlbiel_all(unsigned int action); extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize, unsigned long flags); diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index 6a9e68003387..8eea90f80e45 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -11,6 +11,12 @@ static inline int mmu_get_ap(int psize) return mmu_psize_defs[psize].ap; } +#ifdef CONFIG_PPC_RADIX_MMU +extern void radix__tlbiel_all(unsigned int action); +#else +static inline void radix__tlbiel_all(unsigned int action) { WARN_ON(1); }; +#endif + extern void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start, @@ -47,4 +53,5 @@ extern void radix__flush_tlb_lpid(unsigned long lpid); extern void radix__flush_tlb_all(void); extern void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm, unsigned long address); + #endif diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index 58b576f654b3..0cac17253513 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -8,6 +8,44 @@ #include <asm/book3s/64/tlbflush-hash.h> #include <asm/book3s/64/tlbflush-radix.h> +/* TLB flush actions. Used as argument to tlbiel_all() */ +enum { + TLB_INVAL_SCOPE_GLOBAL = 0, /* invalidate all TLBs */ + TLB_INVAL_SCOPE_LPID = 1, /* invalidate TLBs for current LPID */ +}; + +#ifdef CONFIG_PPC_NATIVE +static inline void tlbiel_all(void) +{ + /* + * This is used for host machine check and bootup. + * + * This uses early_radix_enabled and implementations use + * early_cpu_has_feature etc because that works early in boot + * and this is the machine check path which is not performance + * critical. + */ + if (early_radix_enabled()) + radix__tlbiel_all(TLB_INVAL_SCOPE_GLOBAL); + else + hash__tlbiel_all(TLB_INVAL_SCOPE_GLOBAL); +} +#else +static inline void tlbiel_all(void) { BUG(); }; +#endif + +static inline void tlbiel_all_lpid(bool radix) +{ + /* + * This is used for guest machine check. + */ + if (radix) + radix__tlbiel_all(TLB_INVAL_SCOPE_LPID); + else + hash__tlbiel_all(TLB_INVAL_SCOPE_LPID); +} + + #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE static inline void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index 3c04249bcf39..fd06dbe7d7d3 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -133,9 +133,11 @@ struct pt_regs; extern int do_page_fault(struct pt_regs *, unsigned long, unsigned long); extern void bad_page_fault(struct pt_regs *, unsigned long, int); extern void _exception(int, struct pt_regs *, int, unsigned long); +extern void _exception_pkey(int, struct pt_regs *, int, unsigned long, int); extern void die(const char *, struct pt_regs *, long); extern bool die_will_crash(void); - +extern void panic_flush_kmsg_start(void); +extern void panic_flush_kmsg_end(void); #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index abef812de7f8..812535f40124 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -31,8 +31,10 @@ unsigned int create_cond_branch(const unsigned int *addr, unsigned long target, int flags); int patch_branch(unsigned int *addr, unsigned long target, int flags); int patch_instruction(unsigned int *addr, unsigned int instr); +int raw_patch_instruction(unsigned int *addr, unsigned int instr); int instr_is_relative_branch(unsigned int instr); +int instr_is_relative_link_branch(unsigned int instr); int instr_is_branch_to_addr(const unsigned int *instr, unsigned long addr); unsigned long branch_target(const unsigned int *instr); unsigned int translate_branch(const unsigned int *dest, diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 8a2aecfe9b02..62168e1158f1 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -119,71 +119,6 @@ typedef u32 compat_old_sigset_t; typedef u32 compat_sigset_word; -typedef union compat_sigval { - compat_int_t sival_int; - compat_uptr_t sival_ptr; -} compat_sigval_t; - -#define SI_PAD_SIZE32 (128/sizeof(int) - 3) - -typedef struct compat_siginfo { - int si_signo; - int si_errno; - int si_code; - - union { - int _pad[SI_PAD_SIZE32]; - - /* kill() */ - struct { - compat_pid_t _pid; /* sender's pid */ - __compat_uid_t _uid; /* sender's uid */ - } _kill; - - /* POSIX.1b timers */ - struct { - compat_timer_t _tid; /* timer id */ - int _overrun; /* overrun count */ - compat_sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ - } _timer; - - /* POSIX.1b signals */ - struct { - compat_pid_t _pid; /* sender's pid */ - __compat_uid_t _uid; /* sender's uid */ - compat_sigval_t _sigval; - } _rt; - - /* SIGCHLD */ - struct { - compat_pid_t _pid; /* which child */ - __compat_uid_t _uid; /* sender's uid */ - int _status; /* exit code */ - compat_clock_t _utime; - compat_clock_t _stime; - } _sigchld; - - /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGEMT */ - struct { - unsigned int _addr; /* faulting insn/memory ref. */ - } _sigfault; - - /* SIGPOLL */ - struct { - int _band; /* POLL_IN, POLL_OUT, POLL_MSG */ - int _fd; - } _sigpoll; - - /* SIGSYS */ - struct { - unsigned int _call_addr; /* calling insn */ - int _syscall; /* triggering system call number */ - unsigned int _arch; /* AUDIT_ARCH_* of syscall */ - } _sigsys; - } _sifields; -} compat_siginfo_t; - #define COMPAT_OFF_T_MAX 0x7fffffff /* diff --git a/arch/powerpc/include/asm/cpm.h b/arch/powerpc/include/asm/cpm.h index b925df1b87d0..4c24ea8209bb 100644 --- a/arch/powerpc/include/asm/cpm.h +++ b/arch/powerpc/include/asm/cpm.h @@ -166,6 +166,6 @@ static inline int cpm_command(u32 command, u8 opcode) } #endif /* CONFIG_CPM */ -int cpm2_gpiochip_add32(struct device_node *np); +int cpm2_gpiochip_add32(struct device *dev); #endif diff --git a/arch/powerpc/include/asm/cpm1.h b/arch/powerpc/include/asm/cpm1.h index 3db821876d48..a116fe931789 100644 --- a/arch/powerpc/include/asm/cpm1.h +++ b/arch/powerpc/include/asm/cpm1.h @@ -605,5 +605,7 @@ enum cpm_clk { }; int cpm1_clk_setup(enum cpm_clk_target target, int clock, int mode); +int cpm1_gpiochip_add16(struct device *dev); +int cpm1_gpiochip_add32(struct device *dev); #endif /* __CPM1__ */ diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 0546663a98db..a2c5c95882cf 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -107,12 +107,6 @@ struct cpu_spec { * called in real mode to handle SLB and TLB errors. */ long (*machine_check_early)(struct pt_regs *regs); - - /* - * Processor specific routine to flush tlbs. - */ - void (*flush_tlb)(unsigned int action); - }; extern struct cpu_spec *cur_cpu_spec; @@ -133,12 +127,6 @@ extern void cpu_feature_keys_init(void); static inline void cpu_feature_keys_init(void) { } #endif -/* TLB flush actions. Used as argument to cpu_spec.flush_tlb() hook */ -enum { - TLB_INVAL_SCOPE_GLOBAL = 0, /* invalidate all TLBs */ - TLB_INVAL_SCOPE_LPID = 1, /* invalidate TLBs for current LPID */ -}; - #endif /* __ASSEMBLY__ */ /* CPU kernel features */ @@ -207,7 +195,7 @@ enum { #define CPU_FTR_STCX_CHECKS_ADDRESS LONG_ASM_CONST(0x0004000000000000) #define CPU_FTR_POPCNTB LONG_ASM_CONST(0x0008000000000000) #define CPU_FTR_POPCNTD LONG_ASM_CONST(0x0010000000000000) -/* Free LONG_ASM_CONST(0x0020000000000000) */ +#define CPU_FTR_PKEY LONG_ASM_CONST(0x0020000000000000) #define CPU_FTR_VMX_COPY LONG_ASM_CONST(0x0040000000000000) #define CPU_FTR_TM LONG_ASM_CONST(0x0080000000000000) #define CPU_FTR_CFAR LONG_ASM_CONST(0x0100000000000000) @@ -454,7 +442,7 @@ enum { CPU_FTR_DSCR | CPU_FTR_SAO | CPU_FTR_ASYM_SMT | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | \ - CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX) + CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX | CPU_FTR_PKEY) #define CPU_FTRS_POWER8 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\ CPU_FTR_MMCRA | CPU_FTR_SMT | \ @@ -464,7 +452,7 @@ enum { CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ - CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP) + CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_PKEY) #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG) #define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL) #define CPU_FTRS_POWER9 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ @@ -476,7 +464,8 @@ enum { CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ - CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300) + CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | \ + CPU_FTR_PKEY) #define CPU_FTRS_POWER9_DD1 ((CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) & \ (~CPU_FTR_SAO)) #define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9 diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h index 14e71ff6579e..fc97404de0a3 100644 --- a/arch/powerpc/include/asm/debug.h +++ b/arch/powerpc/include/asm/debug.h @@ -49,7 +49,7 @@ void set_breakpoint(struct arch_hw_breakpoint *brk); void __set_breakpoint(struct arch_hw_breakpoint *brk); #ifdef CONFIG_PPC_ADV_DEBUG_REGS extern void do_send_trap(struct pt_regs *regs, unsigned long address, - unsigned long error_code, int signal_code, int brkpt); + unsigned long error_code, int brkpt); #else extern void do_break(struct pt_regs *regs, unsigned long address, diff --git a/arch/powerpc/include/asm/dma-direct.h b/arch/powerpc/include/asm/dma-direct.h new file mode 100644 index 000000000000..a5b59c765426 --- /dev/null +++ b/arch/powerpc/include/asm/dma-direct.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ASM_POWERPC_DMA_DIRECT_H +#define ASM_POWERPC_DMA_DIRECT_H 1 + +static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) +{ +#ifdef CONFIG_SWIOTLB + struct dev_archdata *sd = &dev->archdata; + + if (sd->max_direct_dma_addr && addr + size > sd->max_direct_dma_addr) + return false; +#endif + + if (!dev->dma_mask) + return false; + + return addr + size - 1 <= *dev->dma_mask; +} + +static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) +{ + return paddr + get_dma_offset(dev); +} + +static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr) +{ + return daddr - get_dma_offset(dev); +} +#endif /* ASM_POWERPC_DMA_DIRECT_H */ diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index 5a6cbe11db6f..8fa394520af6 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -19,13 +19,13 @@ #include <asm/swiotlb.h> /* Some dma direct funcs must be visible for use in other dma_ops */ -extern void *__dma_direct_alloc_coherent(struct device *dev, size_t size, +extern void *__dma_nommu_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs); -extern void __dma_direct_free_coherent(struct device *dev, size_t size, +extern void __dma_nommu_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, unsigned long attrs); -extern int dma_direct_mmap_coherent(struct device *dev, +extern int dma_nommu_mmap_coherent(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t handle, size_t size, unsigned long attrs); @@ -73,7 +73,7 @@ static inline unsigned long device_to_mask(struct device *dev) #ifdef CONFIG_PPC64 extern struct dma_map_ops dma_iommu_ops; #endif -extern const struct dma_map_ops dma_direct_ops; +extern const struct dma_map_ops dma_nommu_ops; static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { @@ -107,39 +107,11 @@ static inline void set_dma_offset(struct device *dev, dma_addr_t off) dev->archdata.dma_offset = off; } -/* this will be removed soon */ -#define flush_write_buffers() - #define HAVE_ARCH_DMA_SET_MASK 1 extern int dma_set_mask(struct device *dev, u64 dma_mask); extern u64 __dma_get_required_mask(struct device *dev); -static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) -{ -#ifdef CONFIG_SWIOTLB - struct dev_archdata *sd = &dev->archdata; - - if (sd->max_direct_dma_addr && addr + size > sd->max_direct_dma_addr) - return false; -#endif - - if (!dev->dma_mask) - return false; - - return addr + size - 1 <= *dev->dma_mask; -} - -static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) -{ - return paddr + get_dma_offset(dev); -} - -static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr) -{ - return daddr - get_dma_offset(dev); -} - #define ARCH_HAS_DMA_MMAP_COHERENT #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h new file mode 100644 index 000000000000..ce242b9ea8c6 --- /dev/null +++ b/arch/powerpc/include/asm/drmem.h @@ -0,0 +1,102 @@ +/* + * drmem.h: Power specific logical memory block representation + * + * Copyright 2017 IBM Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _ASM_POWERPC_LMB_H +#define _ASM_POWERPC_LMB_H + +struct drmem_lmb { + u64 base_addr; + u32 drc_index; + u32 aa_index; + u32 flags; +}; + +struct drmem_lmb_info { + struct drmem_lmb *lmbs; + int n_lmbs; + u32 lmb_size; +}; + +extern struct drmem_lmb_info *drmem_info; + +#define for_each_drmem_lmb_in_range(lmb, start, end) \ + for ((lmb) = (start); (lmb) <= (end); (lmb)++) + +#define for_each_drmem_lmb(lmb) \ + for_each_drmem_lmb_in_range((lmb), \ + &drmem_info->lmbs[0], \ + &drmem_info->lmbs[drmem_info->n_lmbs - 1]) + +/* + * The of_drconf_cell_v1 struct defines the layout of the LMB data + * specified in the ibm,dynamic-memory device tree property. + * The property itself is a 32-bit value specifying the number of + * LMBs followed by an array of of_drconf_cell_v1 entries, one + * per LMB. + */ +struct of_drconf_cell_v1 { + __be64 base_addr; + __be32 drc_index; + __be32 reserved; + __be32 aa_index; + __be32 flags; +}; + +/* + * Version 2 of the ibm,dynamic-memory property is defined as a + * 32-bit value specifying the number of LMB sets followed by an + * array of of_drconf_cell_v2 entries, one per LMB set. + */ +struct of_drconf_cell_v2 { + u32 seq_lmbs; + u64 base_addr; + u32 drc_index; + u32 aa_index; + u32 flags; +} __packed; + +#define DRCONF_MEM_ASSIGNED 0x00000008 +#define DRCONF_MEM_AI_INVALID 0x00000040 +#define DRCONF_MEM_RESERVED 0x00000080 + +static inline u32 drmem_lmb_size(void) +{ + return drmem_info->lmb_size; +} + +#define DRMEM_LMB_RESERVED 0x80000000 + +static inline void drmem_mark_lmb_reserved(struct drmem_lmb *lmb) +{ + lmb->flags |= DRMEM_LMB_RESERVED; +} + +static inline void drmem_remove_lmb_reservation(struct drmem_lmb *lmb) +{ + lmb->flags &= ~DRMEM_LMB_RESERVED; +} + +static inline bool drmem_lmb_reserved(struct drmem_lmb *lmb) +{ + return lmb->flags & DRMEM_LMB_RESERVED; +} + +u64 drmem_lmb_memory_max(void); +void __init walk_drmem_lmbs(struct device_node *dn, + void (*func)(struct drmem_lmb *, const __be32 **)); +int drmem_update_dt(void); + +#ifdef CONFIG_PPC_PSERIES +void __init walk_drmem_lmbs_early(unsigned long node, + void (*func)(struct drmem_lmb *, const __be32 **)); +#endif + +#endif /* _ASM_POWERPC_LMB_H */ diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 5161c37dd039..fd37cc101f4f 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -214,6 +214,7 @@ struct eeh_ops { int (*write_config)(struct pci_dn *pdn, int where, int size, u32 val); int (*next_error)(struct eeh_pe **pe); int (*restore_config)(struct pci_dn *pdn); + int (*notify_resume)(struct pci_dn *pdn); }; extern int eeh_subsystem_flags; @@ -297,6 +298,7 @@ int eeh_pe_reset(struct eeh_pe *pe, int option); int eeh_pe_configure(struct eeh_pe *pe); int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func, unsigned long addr, unsigned long mask); +int eeh_restore_vf_config(struct pci_dn *pdn); /** * EEH_POSSIBLE_ERROR() -- test for possible MMIO failure. diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 7197b179c1b1..471b2274fbeb 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -251,18 +251,40 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) std r10,area+EX_R10(r13); /* save r10 - r12 */ \ OPT_GET_SPR(r10, SPRN_CFAR, CPU_FTR_CFAR) -#define __EXCEPTION_PROLOG_1(area, extra, vec) \ +#define __EXCEPTION_PROLOG_1_PRE(area) \ OPT_SAVE_REG_TO_PACA(area+EX_PPR, r9, CPU_FTR_HAS_PPR); \ OPT_SAVE_REG_TO_PACA(area+EX_CFAR, r10, CPU_FTR_CFAR); \ SAVE_CTR(r10, area); \ - mfcr r9; \ - extra(vec); \ + mfcr r9; + +#define __EXCEPTION_PROLOG_1_POST(area) \ std r11,area+EX_R11(r13); \ std r12,area+EX_R12(r13); \ GET_SCRATCH0(r10); \ std r10,area+EX_R13(r13) + +/* + * This version of the EXCEPTION_PROLOG_1 will carry + * addition parameter called "bitmask" to support + * checking of the interrupt maskable level in the SOFTEN_TEST. + * Intended to be used in MASKABLE_EXCPETION_* macros. + */ +#define MASKABLE_EXCEPTION_PROLOG_1(area, extra, vec, bitmask) \ + __EXCEPTION_PROLOG_1_PRE(area); \ + extra(vec, bitmask); \ + __EXCEPTION_PROLOG_1_POST(area); + +/* + * This version of the EXCEPTION_PROLOG_1 is intended + * to be used in STD_EXCEPTION* macros + */ +#define _EXCEPTION_PROLOG_1(area, extra, vec) \ + __EXCEPTION_PROLOG_1_PRE(area); \ + extra(vec); \ + __EXCEPTION_PROLOG_1_POST(area); + #define EXCEPTION_PROLOG_1(area, extra, vec) \ - __EXCEPTION_PROLOG_1(area, extra, vec) + _EXCEPTION_PROLOG_1(area, extra, vec) #define __EXCEPTION_PROLOG_PSERIES_1(label, h) \ ld r10,PACAKMSR(r13); /* get MSR value for kernel */ \ @@ -485,7 +507,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) mflr r9; /* Get LR, later save to stack */ \ ld r2,PACATOC(r13); /* get kernel TOC into r2 */ \ std r9,_LINK(r1); \ - lbz r10,PACASOFTIRQEN(r13); \ + lbz r10,PACAIRQSOFTMASK(r13); \ mfspr r11,SPRN_XER; /* save XER in stackframe */ \ std r10,SOFTE(r1); \ std r11,_XER(r1); \ @@ -549,22 +571,23 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #define SOFTEN_VALUE_0xe80 PACA_IRQ_DBELL #define SOFTEN_VALUE_0xe60 PACA_IRQ_HMI #define SOFTEN_VALUE_0xea0 PACA_IRQ_EE +#define SOFTEN_VALUE_0xf00 PACA_IRQ_PMI -#define __SOFTEN_TEST(h, vec) \ - lbz r10,PACASOFTIRQEN(r13); \ - cmpwi r10,0; \ +#define __SOFTEN_TEST(h, vec, bitmask) \ + lbz r10,PACAIRQSOFTMASK(r13); \ + andi. r10,r10,bitmask; \ li r10,SOFTEN_VALUE_##vec; \ - beq masked_##h##interrupt + bne masked_##h##interrupt -#define _SOFTEN_TEST(h, vec) __SOFTEN_TEST(h, vec) +#define _SOFTEN_TEST(h, vec, bitmask) __SOFTEN_TEST(h, vec, bitmask) -#define SOFTEN_TEST_PR(vec) \ +#define SOFTEN_TEST_PR(vec, bitmask) \ KVMTEST(EXC_STD, vec); \ - _SOFTEN_TEST(EXC_STD, vec) + _SOFTEN_TEST(EXC_STD, vec, bitmask) -#define SOFTEN_TEST_HV(vec) \ +#define SOFTEN_TEST_HV(vec, bitmask) \ KVMTEST(EXC_HV, vec); \ - _SOFTEN_TEST(EXC_HV, vec) + _SOFTEN_TEST(EXC_HV, vec, bitmask) #define KVMTEST_PR(vec) \ KVMTEST(EXC_STD, vec) @@ -572,53 +595,57 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) #define KVMTEST_HV(vec) \ KVMTEST(EXC_HV, vec) -#define SOFTEN_NOTEST_PR(vec) _SOFTEN_TEST(EXC_STD, vec) -#define SOFTEN_NOTEST_HV(vec) _SOFTEN_TEST(EXC_HV, vec) +#define SOFTEN_NOTEST_PR(vec, bitmask) _SOFTEN_TEST(EXC_STD, vec, bitmask) +#define SOFTEN_NOTEST_HV(vec, bitmask) _SOFTEN_TEST(EXC_HV, vec, bitmask) -#define __MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra) \ +#define __MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra, bitmask) \ SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_PROLOG_0(PACA_EXGEN); \ - __EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec); \ + MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec, bitmask); \ EXCEPTION_PROLOG_PSERIES_1(label, h); -#define _MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra) \ - __MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra) +#define _MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra, bitmask) \ + __MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra, bitmask) -#define MASKABLE_EXCEPTION_PSERIES(loc, vec, label) \ +#define MASKABLE_EXCEPTION_PSERIES(loc, vec, label, bitmask) \ _MASKABLE_EXCEPTION_PSERIES(vec, label, \ - EXC_STD, SOFTEN_TEST_PR) + EXC_STD, SOFTEN_TEST_PR, bitmask) -#define MASKABLE_EXCEPTION_PSERIES_OOL(vec, label) \ - EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_PR, vec); \ +#define MASKABLE_EXCEPTION_PSERIES_OOL(vec, label, bitmask) \ + MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_PR, vec, bitmask);\ EXCEPTION_PROLOG_PSERIES_1(label, EXC_STD) -#define MASKABLE_EXCEPTION_HV(loc, vec, label) \ +#define MASKABLE_EXCEPTION_HV(loc, vec, label, bitmask) \ _MASKABLE_EXCEPTION_PSERIES(vec, label, \ - EXC_HV, SOFTEN_TEST_HV) + EXC_HV, SOFTEN_TEST_HV, bitmask) -#define MASKABLE_EXCEPTION_HV_OOL(vec, label) \ - EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec); \ +#define MASKABLE_EXCEPTION_HV_OOL(vec, label, bitmask) \ + MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec, bitmask);\ EXCEPTION_PROLOG_PSERIES_1(label, EXC_HV) -#define __MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra) \ +#define __MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra, bitmask) \ SET_SCRATCH0(r13); /* save r13 */ \ EXCEPTION_PROLOG_0(PACA_EXGEN); \ - __EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec); \ + MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec, bitmask); \ EXCEPTION_RELON_PROLOG_PSERIES_1(label, h) -#define _MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra) \ - __MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra) +#define _MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra, bitmask)\ + __MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, h, extra, bitmask) -#define MASKABLE_RELON_EXCEPTION_PSERIES(loc, vec, label) \ +#define MASKABLE_RELON_EXCEPTION_PSERIES(loc, vec, label, bitmask) \ _MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, \ - EXC_STD, SOFTEN_NOTEST_PR) + EXC_STD, SOFTEN_NOTEST_PR, bitmask) + +#define MASKABLE_RELON_EXCEPTION_PSERIES_OOL(vec, label, bitmask) \ + MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_PR, vec, bitmask);\ + EXCEPTION_PROLOG_PSERIES_1(label, EXC_STD); -#define MASKABLE_RELON_EXCEPTION_HV(loc, vec, label) \ +#define MASKABLE_RELON_EXCEPTION_HV(loc, vec, label, bitmask) \ _MASKABLE_RELON_EXCEPTION_PSERIES(vec, label, \ - EXC_HV, SOFTEN_TEST_HV) + EXC_HV, SOFTEN_TEST_HV, bitmask) -#define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label) \ - EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec); \ +#define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label, bitmask) \ + MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec, bitmask);\ EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_HV) /* diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 8645897472b1..535add3f7791 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -51,6 +51,8 @@ #define FW_FEATURE_BEST_ENERGY ASM_CONST(0x0000000080000000) #define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000) #define FW_FEATURE_PRRN ASM_CONST(0x0000000200000000) +#define FW_FEATURE_DRMEM_V2 ASM_CONST(0x0000000400000000) +#define FW_FEATURE_DRC_INFO ASM_CONST(0x0000000800000000) #ifndef __ASSEMBLY__ @@ -67,7 +69,8 @@ enum { FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO | FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY | FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN | - FW_FEATURE_HPT_RESIZE, + FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 | + FW_FEATURE_DRC_INFO, FW_FEATURE_PSERIES_ALWAYS = 0, FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL, FW_FEATURE_POWERNV_ALWAYS = 0, diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h index 456f9e7b8d83..5986d473722b 100644 --- a/arch/powerpc/include/asm/hardirq.h +++ b/arch/powerpc/include/asm/hardirq.h @@ -29,6 +29,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); #define local_softirq_pending() __this_cpu_read(irq_stat.__softirq_pending) #define __ARCH_SET_SOFTIRQ_PENDING +#define __ARCH_IRQ_EXIT_IRQS_DISABLED #define set_softirq_pending(x) __this_cpu_write(irq_stat.__softirq_pending, (x)) #define or_softirq_pending(x) __this_cpu_or(irq_stat.__softirq_pending, (x)) diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h index fdcff76e9a25..7e0e93f24cb7 100644 --- a/arch/powerpc/include/asm/head-64.h +++ b/arch/powerpc/include/asm/head-64.h @@ -178,7 +178,7 @@ name: * TRAMP_REAL_* - real, unrelocated helpers (virt can call these) * TRAMP_VIRT_* - virt, unreloc helpers (in practice, real can use) * TRAMP_KVM - KVM handlers that get put into real, unrelocated - * EXC_COMMON_* - virt, relocated common handlers + * EXC_COMMON - virt, relocated common handlers * * The EXC handlers are given a name, and branch to name_common, or the * appropriate KVM or masking function. Vector handler verieties are as @@ -211,7 +211,6 @@ name: * EXC_COMMON_BEGIN/END - used to open-code the handler * EXC_COMMON * EXC_COMMON_ASYNC - * EXC_COMMON_HV * * TRAMP_REAL and TRAMP_VIRT can be used with BEGIN/END. KVM * and OOL handlers are implemented as types of TRAMP and TRAMP_VIRT handlers. @@ -269,14 +268,14 @@ name: STD_RELON_EXCEPTION_PSERIES(start, realvec, name##_common); \ EXC_VIRT_END(name, start, size); -#define EXC_REAL_MASKABLE(name, start, size) \ +#define EXC_REAL_MASKABLE(name, start, size, bitmask) \ EXC_REAL_BEGIN(name, start, size); \ - MASKABLE_EXCEPTION_PSERIES(start, start, name##_common); \ + MASKABLE_EXCEPTION_PSERIES(start, start, name##_common, bitmask);\ EXC_REAL_END(name, start, size); -#define EXC_VIRT_MASKABLE(name, start, size, realvec) \ +#define EXC_VIRT_MASKABLE(name, start, size, realvec, bitmask) \ EXC_VIRT_BEGIN(name, start, size); \ - MASKABLE_RELON_EXCEPTION_PSERIES(start, realvec, name##_common); \ + MASKABLE_RELON_EXCEPTION_PSERIES(start, realvec, name##_common, bitmask);\ EXC_VIRT_END(name, start, size); #define EXC_REAL_HV(name, start, size) \ @@ -305,13 +304,13 @@ name: #define __EXC_REAL_OOL_MASKABLE(name, start, size) \ __EXC_REAL_OOL(name, start, size); -#define __TRAMP_REAL_OOL_MASKABLE(name, vec) \ +#define __TRAMP_REAL_OOL_MASKABLE(name, vec, bitmask) \ TRAMP_REAL_BEGIN(tramp_real_##name); \ - MASKABLE_EXCEPTION_PSERIES_OOL(vec, name##_common); \ + MASKABLE_EXCEPTION_PSERIES_OOL(vec, name##_common, bitmask); \ -#define EXC_REAL_OOL_MASKABLE(name, start, size) \ +#define EXC_REAL_OOL_MASKABLE(name, start, size, bitmask) \ __EXC_REAL_OOL_MASKABLE(name, start, size); \ - __TRAMP_REAL_OOL_MASKABLE(name, start); + __TRAMP_REAL_OOL_MASKABLE(name, start, bitmask); #define __EXC_REAL_OOL_HV_DIRECT(name, start, size, handler) \ EXC_REAL_BEGIN(name, start, size); \ @@ -332,13 +331,13 @@ name: #define __EXC_REAL_OOL_MASKABLE_HV(name, start, size) \ __EXC_REAL_OOL(name, start, size); -#define __TRAMP_REAL_OOL_MASKABLE_HV(name, vec) \ +#define __TRAMP_REAL_OOL_MASKABLE_HV(name, vec, bitmask) \ TRAMP_REAL_BEGIN(tramp_real_##name); \ - MASKABLE_EXCEPTION_HV_OOL(vec, name##_common); \ + MASKABLE_EXCEPTION_HV_OOL(vec, name##_common, bitmask); \ -#define EXC_REAL_OOL_MASKABLE_HV(name, start, size) \ +#define EXC_REAL_OOL_MASKABLE_HV(name, start, size, bitmask) \ __EXC_REAL_OOL_MASKABLE_HV(name, start, size); \ - __TRAMP_REAL_OOL_MASKABLE_HV(name, start); + __TRAMP_REAL_OOL_MASKABLE_HV(name, start, bitmask); #define __EXC_VIRT_OOL(name, start, size) \ EXC_VIRT_BEGIN(name, start, size); \ @@ -356,13 +355,13 @@ name: #define __EXC_VIRT_OOL_MASKABLE(name, start, size) \ __EXC_VIRT_OOL(name, start, size); -#define __TRAMP_VIRT_OOL_MASKABLE(name, realvec) \ +#define __TRAMP_VIRT_OOL_MASKABLE(name, realvec, bitmask) \ TRAMP_VIRT_BEGIN(tramp_virt_##name); \ - MASKABLE_RELON_EXCEPTION_PSERIES_OOL(realvec, name##_common); \ + MASKABLE_RELON_EXCEPTION_PSERIES_OOL(realvec, name##_common, bitmask);\ -#define EXC_VIRT_OOL_MASKABLE(name, start, size, realvec) \ +#define EXC_VIRT_OOL_MASKABLE(name, start, size, realvec, bitmask) \ __EXC_VIRT_OOL_MASKABLE(name, start, size); \ - __TRAMP_VIRT_OOL_MASKABLE(name, realvec); + __TRAMP_VIRT_OOL_MASKABLE(name, realvec, bitmask); #define __EXC_VIRT_OOL_HV(name, start, size) \ __EXC_VIRT_OOL(name, start, size); @@ -378,13 +377,13 @@ name: #define __EXC_VIRT_OOL_MASKABLE_HV(name, start, size) \ __EXC_VIRT_OOL(name, start, size); -#define __TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec) \ +#define __TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec, bitmask) \ TRAMP_VIRT_BEGIN(tramp_virt_##name); \ - MASKABLE_RELON_EXCEPTION_HV_OOL(realvec, name##_common); \ + MASKABLE_RELON_EXCEPTION_HV_OOL(realvec, name##_common, bitmask);\ -#define EXC_VIRT_OOL_MASKABLE_HV(name, start, size, realvec) \ +#define EXC_VIRT_OOL_MASKABLE_HV(name, start, size, realvec, bitmask) \ __EXC_VIRT_OOL_MASKABLE_HV(name, start, size); \ - __TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec); + __TRAMP_VIRT_OOL_MASKABLE_HV(name, realvec, bitmask); #define TRAMP_KVM(area, n) \ TRAMP_KVM_BEGIN(do_kvm_##n); \ @@ -413,10 +412,6 @@ name: EXC_COMMON_BEGIN(name); \ STD_EXCEPTION_COMMON_ASYNC(realvec, name, hdlr); \ -#define EXC_COMMON_HV(name, realvec, hdlr) \ - EXC_COMMON_BEGIN(name); \ - STD_EXCEPTION_COMMON(realvec + 0x2, name, hdlr); \ - #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_HEAD_64_H */ diff --git a/arch/powerpc/include/asm/hmi.h b/arch/powerpc/include/asm/hmi.h index 85b7a1a21e22..9c14f7b5c46c 100644 --- a/arch/powerpc/include/asm/hmi.h +++ b/arch/powerpc/include/asm/hmi.h @@ -42,4 +42,8 @@ extern void wait_for_tb_resync(void); static inline void wait_for_subcore_guest_exit(void) { } static inline void wait_for_tb_resync(void) { } #endif + +struct pt_regs; +extern long hmi_handle_debugtrig(struct pt_regs *regs); + #endif /* __ASM_PPC64_HMI_H__ */ diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 14c9d44f355b..1a4847f67ea8 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -47,8 +47,7 @@ static inline pte_t *hugepd_page(hugepd_t hpd) { BUG_ON(!hugepd_ok(hpd)); #ifdef CONFIG_PPC_8xx - return (pte_t *)__va(hpd_val(hpd) & - ~(_PMD_PAGE_MASK | _PMD_PRESENT_MASK)); + return (pte_t *)__va(hpd_val(hpd) & ~HUGEPD_SHIFT_MASK); #else return (pte_t *)((hpd_val(hpd) & ~HUGEPD_SHIFT_MASK) | PD_HUGE); diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 3818fa0164f0..855e17d158b1 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -27,6 +27,25 @@ #define PACA_IRQ_DEC 0x08 /* Or FIT */ #define PACA_IRQ_EE_EDGE 0x10 /* BookE only */ #define PACA_IRQ_HMI 0x20 +#define PACA_IRQ_PMI 0x40 + +/* + * Some soft-masked interrupts must be hard masked until they are replayed + * (e.g., because the soft-masked handler does not clear the exception). + */ +#ifdef CONFIG_PPC_BOOK3S +#define PACA_IRQ_MUST_HARD_MASK (PACA_IRQ_EE|PACA_IRQ_PMI) +#else +#define PACA_IRQ_MUST_HARD_MASK (PACA_IRQ_EE) +#endif + +/* + * flags for paca->irq_soft_mask + */ +#define IRQS_ENABLED 0 +#define IRQS_DISABLED 1 /* local_irq_disable() interrupts */ +#define IRQS_PMI_DISABLED 2 +#define IRQS_ALL_DISABLED (IRQS_DISABLED | IRQS_PMI_DISABLED) #endif /* CONFIG_PPC64 */ @@ -43,46 +62,112 @@ extern void unknown_exception(struct pt_regs *regs); #ifdef CONFIG_PPC64 #include <asm/paca.h> -static inline unsigned long arch_local_save_flags(void) +static inline notrace unsigned long irq_soft_mask_return(void) { unsigned long flags; asm volatile( "lbz %0,%1(13)" : "=r" (flags) - : "i" (offsetof(struct paca_struct, soft_enabled))); + : "i" (offsetof(struct paca_struct, irq_soft_mask))); return flags; } -static inline unsigned long arch_local_irq_disable(void) +/* + * The "memory" clobber acts as both a compiler barrier + * for the critical section and as a clobber because + * we changed paca->irq_soft_mask + */ +static inline notrace void irq_soft_mask_set(unsigned long mask) +{ +#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG + /* + * The irq mask must always include the STD bit if any are set. + * + * and interrupts don't get replayed until the standard + * interrupt (local_irq_disable()) is unmasked. + * + * Other masks must only provide additional masking beyond + * the standard, and they are also not replayed until the + * standard interrupt becomes unmasked. + * + * This could be changed, but it will require partial + * unmasks to be replayed, among other things. For now, take + * the simple approach. + */ + WARN_ON(mask && !(mask & IRQS_DISABLED)); +#endif + + asm volatile( + "stb %0,%1(13)" + : + : "r" (mask), + "i" (offsetof(struct paca_struct, irq_soft_mask)) + : "memory"); +} + +static inline notrace unsigned long irq_soft_mask_set_return(unsigned long mask) { - unsigned long flags, zero; + unsigned long flags; + +#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG + WARN_ON(mask && !(mask & IRQS_DISABLED)); +#endif asm volatile( - "li %1,0; lbz %0,%2(13); stb %1,%2(13)" - : "=r" (flags), "=&r" (zero) - : "i" (offsetof(struct paca_struct, soft_enabled)) + "lbz %0,%1(13); stb %2,%1(13)" + : "=&r" (flags) + : "i" (offsetof(struct paca_struct, irq_soft_mask)), + "r" (mask) : "memory"); return flags; } +static inline notrace unsigned long irq_soft_mask_or_return(unsigned long mask) +{ + unsigned long flags, tmp; + + asm volatile( + "lbz %0,%2(13); or %1,%0,%3; stb %1,%2(13)" + : "=&r" (flags), "=r" (tmp) + : "i" (offsetof(struct paca_struct, irq_soft_mask)), + "r" (mask) + : "memory"); + +#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG + WARN_ON((mask | flags) && !((mask | flags) & IRQS_DISABLED)); +#endif + + return flags; +} + +static inline unsigned long arch_local_save_flags(void) +{ + return irq_soft_mask_return(); +} + +static inline void arch_local_irq_disable(void) +{ + irq_soft_mask_set(IRQS_DISABLED); +} + extern void arch_local_irq_restore(unsigned long); static inline void arch_local_irq_enable(void) { - arch_local_irq_restore(1); + arch_local_irq_restore(IRQS_ENABLED); } static inline unsigned long arch_local_irq_save(void) { - return arch_local_irq_disable(); + return irq_soft_mask_set_return(IRQS_DISABLED); } static inline bool arch_irqs_disabled_flags(unsigned long flags) { - return flags == 0; + return flags & IRQS_DISABLED; } static inline bool arch_irqs_disabled(void) @@ -90,6 +175,55 @@ static inline bool arch_irqs_disabled(void) return arch_irqs_disabled_flags(arch_local_save_flags()); } +#ifdef CONFIG_PPC_BOOK3S +/* + * To support disabling and enabling of irq with PMI, set of + * new powerpc_local_irq_pmu_save() and powerpc_local_irq_restore() + * functions are added. These macros are implemented using generic + * linux local_irq_* code from include/linux/irqflags.h. + */ +#define raw_local_irq_pmu_save(flags) \ + do { \ + typecheck(unsigned long, flags); \ + flags = irq_soft_mask_or_return(IRQS_DISABLED | \ + IRQS_PMI_DISABLED); \ + } while(0) + +#define raw_local_irq_pmu_restore(flags) \ + do { \ + typecheck(unsigned long, flags); \ + arch_local_irq_restore(flags); \ + } while(0) + +#ifdef CONFIG_TRACE_IRQFLAGS +#define powerpc_local_irq_pmu_save(flags) \ + do { \ + raw_local_irq_pmu_save(flags); \ + trace_hardirqs_off(); \ + } while(0) +#define powerpc_local_irq_pmu_restore(flags) \ + do { \ + if (raw_irqs_disabled_flags(flags)) { \ + raw_local_irq_pmu_restore(flags); \ + trace_hardirqs_off(); \ + } else { \ + trace_hardirqs_on(); \ + raw_local_irq_pmu_restore(flags); \ + } \ + } while(0) +#else +#define powerpc_local_irq_pmu_save(flags) \ + do { \ + raw_local_irq_pmu_save(flags); \ + } while(0) +#define powerpc_local_irq_pmu_restore(flags) \ + do { \ + raw_local_irq_pmu_restore(flags); \ + } while (0) +#endif /* CONFIG_TRACE_IRQFLAGS */ + +#endif /* CONFIG_PPC_BOOK3S */ + #ifdef CONFIG_PPC_BOOK3E #define __hard_irq_enable() asm volatile("wrteei 1" : : : "memory") #define __hard_irq_disable() asm volatile("wrteei 0" : : : "memory") @@ -98,14 +232,13 @@ static inline bool arch_irqs_disabled(void) #define __hard_irq_disable() __mtmsrd(local_paca->kernel_msr, 1) #endif -#define hard_irq_disable() do { \ - u8 _was_enabled; \ - __hard_irq_disable(); \ - _was_enabled = local_paca->soft_enabled; \ - local_paca->soft_enabled = 0; \ - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; \ - if (_was_enabled) \ - trace_hardirqs_off(); \ +#define hard_irq_disable() do { \ + unsigned long flags; \ + __hard_irq_disable(); \ + flags = irq_soft_mask_set_return(IRQS_ALL_DISABLED); \ + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; \ + if (!arch_irqs_disabled_flags(flags)) \ + trace_hardirqs_off(); \ } while(0) static inline bool lazy_irq_pending(void) @@ -121,13 +254,13 @@ static inline bool lazy_irq_pending(void) static inline void may_hard_irq_enable(void) { get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS; - if (!(get_paca()->irq_happened & PACA_IRQ_EE)) + if (!(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK)) __hard_irq_enable(); } static inline bool arch_irq_disabled_regs(struct pt_regs *regs) { - return !regs->softe; + return (regs->softe & IRQS_DISABLED); } extern bool prep_irq_for_idle(void); diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h index fad0e6ff460f..d76cb11be3e3 100644 --- a/arch/powerpc/include/asm/imc-pmu.h +++ b/arch/powerpc/include/asm/imc-pmu.h @@ -35,6 +35,13 @@ #define THREAD_IMC_ENABLE 0x8000000000000000ULL /* + * For debugfs interface for imc-mode and imc-command + */ +#define IMC_CNTL_BLK_OFFSET 0x3FC00 +#define IMC_CNTL_BLK_CMD_OFFSET 8 +#define IMC_CNTL_BLK_MODE_OFFSET 32 + +/* * Structure to hold memory address information for imc units. */ struct imc_mem_info { @@ -71,7 +78,7 @@ struct imc_events { struct imc_pmu { struct pmu pmu; struct imc_mem_info *mem_info; - struct imc_events **events; + struct imc_events *events; /* * Attribute groups for the PMU. Slot 0 used for * format attribute, slot 1 used for cpusmask attribute, diff --git a/arch/powerpc/include/asm/irqflags.h b/arch/powerpc/include/asm/irqflags.h index 1aeb5f13b8c4..1a6c1ce17735 100644 --- a/arch/powerpc/include/asm/irqflags.h +++ b/arch/powerpc/include/asm/irqflags.h @@ -47,14 +47,14 @@ * be clobbered. */ #define RECONCILE_IRQ_STATE(__rA, __rB) \ - lbz __rA,PACASOFTIRQEN(r13); \ + lbz __rA,PACAIRQSOFTMASK(r13); \ lbz __rB,PACAIRQHAPPENED(r13); \ - cmpwi cr0,__rA,0; \ - li __rA,0; \ + andi. __rA,__rA,IRQS_DISABLED; \ + li __rA,IRQS_DISABLED; \ ori __rB,__rB,PACA_IRQ_HARD_DIS; \ stb __rB,PACAIRQHAPPENED(r13); \ - beq 44f; \ - stb __rA,PACASOFTIRQEN(r13); \ + bne 44f; \ + stb __rA,PACAIRQSOFTMASK(r13); \ TRACE_DISABLE_INTS; \ 44: @@ -64,9 +64,9 @@ #define RECONCILE_IRQ_STATE(__rA, __rB) \ lbz __rA,PACAIRQHAPPENED(r13); \ - li __rB,0; \ + li __rB,IRQS_DISABLED; \ ori __rA,__rA,PACA_IRQ_HARD_DIS; \ - stb __rB,PACASOFTIRQEN(r13); \ + stb __rB,PACAIRQSOFTMASK(r13); \ stb __rA,PACAIRQHAPPENED(r13) #endif #endif diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index 4419d435639a..d8b1e8e7e035 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -73,6 +73,8 @@ extern void kexec_smp_wait(void); /* get and clear naca physid, wait for master to copy new code to 0 */ extern int crashing_cpu; extern void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)); +extern void crash_ipi_callback(struct pt_regs *); +extern int crash_wake_offline; struct kimage; struct pt_regs; @@ -138,6 +140,12 @@ static inline bool kdump_in_progress(void) return false; } +static inline void crash_ipi_callback(struct pt_regs *regs) { } + +static inline void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) +{ +} + #endif /* CONFIG_KEXEC_CORE */ #endif /* ! __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 9a667007bff8..376ae803b69c 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -249,10 +249,8 @@ extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd); extern void kvmppc_pr_init_default_hcalls(struct kvm *kvm); extern int kvmppc_hcall_impl_pr(unsigned long cmd); extern int kvmppc_hcall_impl_hv_realmode(unsigned long cmd); -extern void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu, - struct kvm_vcpu *vcpu); -extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu, - struct kvmppc_book3s_shadow_vcpu *svcpu); +extern void kvmppc_copy_to_svcpu(struct kvm_vcpu *vcpu); +extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu); extern int kvm_irq_bypass; static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu) diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 735cfa35298a..998f7b7aaa9e 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -122,13 +122,13 @@ static inline int kvmppc_hpte_page_shifts(unsigned long h, unsigned long l) lphi = (l >> 16) & 0xf; switch ((l >> 12) & 0xf) { case 0: - return !lphi ? 24 : -1; /* 16MB */ + return !lphi ? 24 : 0; /* 16MB */ break; case 1: return 16; /* 64kB */ break; case 3: - return !lphi ? 34 : -1; /* 16GB */ + return !lphi ? 34 : 0; /* 16GB */ break; case 7: return (16 << 8) + 12; /* 64kB in 4kB */ @@ -140,7 +140,7 @@ static inline int kvmppc_hpte_page_shifts(unsigned long h, unsigned long l) return (24 << 8) + 12; /* 16MB in 4kB */ break; } - return -1; + return 0; } static inline int kvmppc_hpte_base_page_shift(unsigned long h, unsigned long l) @@ -159,7 +159,11 @@ static inline int kvmppc_hpte_actual_page_shift(unsigned long h, unsigned long l static inline unsigned long kvmppc_actual_pgsz(unsigned long v, unsigned long r) { - return 1ul << kvmppc_hpte_actual_page_shift(v, r); + int shift = kvmppc_hpte_actual_page_shift(v, r); + + if (shift) + return 1ul << shift; + return 0; } static inline int kvmppc_pgsize_lp_encoding(int base_shift, int actual_shift) @@ -232,7 +236,7 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, va_low ^= v >> (SID_SHIFT_1T - 16); va_low &= 0x7ff; - if (b_pgshift == 12) { + if (b_pgshift <= 12) { if (a_pgshift > 12) { sllp = (a_pgshift == 16) ? 5 : 4; rb |= sllp << 5; /* AP field */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 3aa5b577cd60..1f53b562726f 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -690,6 +690,7 @@ struct kvm_vcpu_arch { u8 mmio_vsx_offset; u8 mmio_vsx_copy_type; u8 mmio_vsx_tx_sx_enabled; + u8 mmio_vmx_copy_nums; u8 osi_needed; u8 osi_enabled; u8 papr_enabled; @@ -709,6 +710,7 @@ struct kvm_vcpu_arch { u8 ceded; u8 prodded; u8 doorbell_request; + u8 irq_pending; /* Used by XIVE to signal pending guest irqs */ u32 last_inst; struct swait_queue_head *wqp; @@ -738,8 +740,11 @@ struct kvm_vcpu_arch { struct kvmppc_icp *icp; /* XICS presentation controller */ struct kvmppc_xive_vcpu *xive_vcpu; /* XIVE virtual CPU data */ __be32 xive_cam_word; /* Cooked W2 in proper endian with valid bit */ - u32 xive_pushed; /* Is the VP pushed on the physical CPU ? */ + u8 xive_pushed; /* Is the VP pushed on the physical CPU ? */ + u8 xive_esc_on; /* Is the escalation irq enabled ? */ union xive_tma_w01 xive_saved_state; /* W0..1 of XIVE thread state */ + u64 xive_esc_raddr; /* Escalation interrupt ESB real addr */ + u64 xive_esc_vaddr; /* Escalation interrupt ESB virt addr */ #endif #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE @@ -800,6 +805,7 @@ struct kvm_vcpu_arch { #define KVM_MMIO_REG_QPR 0x0040 #define KVM_MMIO_REG_FQPR 0x0060 #define KVM_MMIO_REG_VSX 0x0080 +#define KVM_MMIO_REG_VMX 0x00c0 #define __KVM_HAVE_ARCH_WQP #define __KVM_HAVE_CREATE_DEVICE diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 941c2a3f231b..7765a800ddae 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -81,6 +81,10 @@ extern int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu, extern int kvmppc_handle_vsx_load(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int rt, unsigned int bytes, int is_default_endian, int mmio_sign_extend); +extern int kvmppc_handle_load128_by2x64(struct kvm_run *run, + struct kvm_vcpu *vcpu, unsigned int rt, int is_default_endian); +extern int kvmppc_handle_store128_by2x64(struct kvm_run *run, + struct kvm_vcpu *vcpu, unsigned int rs, int is_default_endian); extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, u64 val, unsigned int bytes, int is_default_endian); @@ -873,7 +877,7 @@ static inline void kvmppc_fix_ee_before_entry(void) /* Only need to enable IRQs by hard enabling them after this */ local_paca->irq_happened = 0; - local_paca->soft_enabled = 1; + irq_soft_mask_set(IRQS_ENABLED); #endif } diff --git a/arch/powerpc/include/asm/local.h b/arch/powerpc/include/asm/local.h index 600a68bd77f5..fdd00939270b 100644 --- a/arch/powerpc/include/asm/local.h +++ b/arch/powerpc/include/asm/local.h @@ -2,76 +2,64 @@ #ifndef _ARCH_POWERPC_LOCAL_H #define _ARCH_POWERPC_LOCAL_H +#ifdef CONFIG_PPC_BOOK3S_64 + #include <linux/percpu.h> #include <linux/atomic.h> +#include <linux/irqflags.h> + +#include <asm/hw_irq.h> typedef struct { - atomic_long_t a; + long v; } local_t; -#define LOCAL_INIT(i) { ATOMIC_LONG_INIT(i) } - -#define local_read(l) atomic_long_read(&(l)->a) -#define local_set(l,i) atomic_long_set(&(l)->a, (i)) +#define LOCAL_INIT(i) { (i) } -#define local_add(i,l) atomic_long_add((i),(&(l)->a)) -#define local_sub(i,l) atomic_long_sub((i),(&(l)->a)) -#define local_inc(l) atomic_long_inc(&(l)->a) -#define local_dec(l) atomic_long_dec(&(l)->a) - -static __inline__ long local_add_return(long a, local_t *l) +static __inline__ long local_read(local_t *l) { - long t; - - __asm__ __volatile__( -"1:" PPC_LLARX(%0,0,%2,0) " # local_add_return\n\ - add %0,%1,%0\n" - PPC405_ERR77(0,%2) - PPC_STLCX "%0,0,%2 \n\ - bne- 1b" - : "=&r" (t) - : "r" (a), "r" (&(l->a.counter)) - : "cc", "memory"); - - return t; + return READ_ONCE(l->v); } -#define local_add_negative(a, l) (local_add_return((a), (l)) < 0) - -static __inline__ long local_sub_return(long a, local_t *l) +static __inline__ void local_set(local_t *l, long i) { - long t; + WRITE_ONCE(l->v, i); +} - __asm__ __volatile__( -"1:" PPC_LLARX(%0,0,%2,0) " # local_sub_return\n\ - subf %0,%1,%0\n" - PPC405_ERR77(0,%2) - PPC_STLCX "%0,0,%2 \n\ - bne- 1b" - : "=&r" (t) - : "r" (a), "r" (&(l->a.counter)) - : "cc", "memory"); +#define LOCAL_OP(op, c_op) \ +static __inline__ void local_##op(long i, local_t *l) \ +{ \ + unsigned long flags; \ + \ + powerpc_local_irq_pmu_save(flags); \ + l->v c_op i; \ + powerpc_local_irq_pmu_restore(flags); \ +} - return t; +#define LOCAL_OP_RETURN(op, c_op) \ +static __inline__ long local_##op##_return(long a, local_t *l) \ +{ \ + long t; \ + unsigned long flags; \ + \ + powerpc_local_irq_pmu_save(flags); \ + t = (l->v c_op a); \ + powerpc_local_irq_pmu_restore(flags); \ + \ + return t; \ } -static __inline__ long local_inc_return(local_t *l) -{ - long t; +#define LOCAL_OPS(op, c_op) \ + LOCAL_OP(op, c_op) \ + LOCAL_OP_RETURN(op, c_op) - __asm__ __volatile__( -"1:" PPC_LLARX(%0,0,%1,0) " # local_inc_return\n\ - addic %0,%0,1\n" - PPC405_ERR77(0,%1) - PPC_STLCX "%0,0,%1 \n\ - bne- 1b" - : "=&r" (t) - : "r" (&(l->a.counter)) - : "cc", "xer", "memory"); +LOCAL_OPS(add, +=) +LOCAL_OPS(sub, -=) - return t; -} +#define local_add_negative(a, l) (local_add_return((a), (l)) < 0) +#define local_inc_return(l) local_add_return(1LL, l) +#define local_inc(l) local_inc_return(l) /* * local_inc_and_test - increment and test @@ -81,28 +69,39 @@ static __inline__ long local_inc_return(local_t *l) * and returns true if the result is zero, or false for all * other cases. */ -#define local_inc_and_test(l) (local_inc_return(l) == 0) +#define local_inc_and_test(l) (local_inc_return(l) == 0) -static __inline__ long local_dec_return(local_t *l) +#define local_dec_return(l) local_sub_return(1LL, l) +#define local_dec(l) local_dec_return(l) +#define local_sub_and_test(a, l) (local_sub_return((a), (l)) == 0) +#define local_dec_and_test(l) (local_dec_return((l)) == 0) + +static __inline__ long local_cmpxchg(local_t *l, long o, long n) { long t; + unsigned long flags; - __asm__ __volatile__( -"1:" PPC_LLARX(%0,0,%1,0) " # local_dec_return\n\ - addic %0,%0,-1\n" - PPC405_ERR77(0,%1) - PPC_STLCX "%0,0,%1\n\ - bne- 1b" - : "=&r" (t) - : "r" (&(l->a.counter)) - : "cc", "xer", "memory"); + powerpc_local_irq_pmu_save(flags); + t = l->v; + if (t == o) + l->v = n; + powerpc_local_irq_pmu_restore(flags); return t; } -#define local_cmpxchg(l, o, n) \ - (cmpxchg_local(&((l)->a.counter), (o), (n))) -#define local_xchg(l, n) (xchg_local(&((l)->a.counter), (n))) +static __inline__ long local_xchg(local_t *l, long n) +{ + long t; + unsigned long flags; + + powerpc_local_irq_pmu_save(flags); + t = l->v; + l->v = n; + powerpc_local_irq_pmu_restore(flags); + + return t; +} /** * local_add_unless - add unless the number is a given value @@ -115,62 +114,35 @@ static __inline__ long local_dec_return(local_t *l) */ static __inline__ int local_add_unless(local_t *l, long a, long u) { - long t; - - __asm__ __volatile__ ( -"1:" PPC_LLARX(%0,0,%1,0) " # local_add_unless\n\ - cmpw 0,%0,%3 \n\ - beq- 2f \n\ - add %0,%2,%0 \n" - PPC405_ERR77(0,%2) - PPC_STLCX "%0,0,%1 \n\ - bne- 1b \n" -" subf %0,%2,%0 \n\ -2:" - : "=&r" (t) - : "r" (&(l->a.counter)), "r" (a), "r" (u) - : "cc", "memory"); - - return t != u; -} - -#define local_inc_not_zero(l) local_add_unless((l), 1, 0) - -#define local_sub_and_test(a, l) (local_sub_return((a), (l)) == 0) -#define local_dec_and_test(l) (local_dec_return((l)) == 0) - -/* - * Atomically test *l and decrement if it is greater than 0. - * The function returns the old value of *l minus 1. - */ -static __inline__ long local_dec_if_positive(local_t *l) -{ - long t; + unsigned long flags; + int ret = 0; - __asm__ __volatile__( -"1:" PPC_LLARX(%0,0,%1,0) " # local_dec_if_positive\n\ - cmpwi %0,1\n\ - addi %0,%0,-1\n\ - blt- 2f\n" - PPC405_ERR77(0,%1) - PPC_STLCX "%0,0,%1\n\ - bne- 1b" - "\n\ -2:" : "=&b" (t) - : "r" (&(l->a.counter)) - : "cc", "memory"); + powerpc_local_irq_pmu_save(flags); + if (l->v != u) { + l->v += a; + ret = 1; + } + powerpc_local_irq_pmu_restore(flags); - return t; + return ret; } +#define local_inc_not_zero(l) local_add_unless((l), 1, 0) + /* Use these for per-cpu local_t variables: on some archs they are * much more efficient than these naive implementations. Note they take * a variable, not an address. */ -#define __local_inc(l) ((l)->a.counter++) -#define __local_dec(l) ((l)->a.counter++) -#define __local_add(i,l) ((l)->a.counter+=(i)) -#define __local_sub(i,l) ((l)->a.counter-=(i)) +#define __local_inc(l) ((l)->v++) +#define __local_dec(l) ((l)->v++) +#define __local_add(i,l) ((l)->v+=(i)) +#define __local_sub(i,l) ((l)->v-=(i)) + +#else /* CONFIG_PPC64 */ + +#include <asm-generic/local.h> + +#endif /* CONFIG_PPC64 */ #endif /* _ARCH_POWERPC_LOCAL_H */ diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index cd2fc1cc1cc7..ffe7c71e1132 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -173,11 +173,19 @@ struct machdep_calls { /* Called after scan and before resource survey */ void (*pcibios_fixup_phb)(struct pci_controller *hose); + /* + * Called after device has been added to bus and + * before sysfs has been created. + */ + void (*pcibios_bus_add_device)(struct pci_dev *pdev); + resource_size_t (*pcibios_default_alignment)(void); #ifdef CONFIG_PCI_IOV void (*pcibios_fixup_sriov)(struct pci_dev *pdev); resource_size_t (*pcibios_iov_resource_alignment)(struct pci_dev *, int resno); + int (*pcibios_sriov_enable)(struct pci_dev *pdev, u16 num_vfs); + int (*pcibios_sriov_disable)(struct pci_dev *pdev); #endif /* CONFIG_PCI_IOV */ /* Called to shutdown machine specific hardware not already controlled diff --git a/arch/powerpc/include/asm/membarrier.h b/arch/powerpc/include/asm/membarrier.h new file mode 100644 index 000000000000..6e20bb5c74ea --- /dev/null +++ b/arch/powerpc/include/asm/membarrier.h @@ -0,0 +1,27 @@ +#ifndef _ASM_POWERPC_MEMBARRIER_H +#define _ASM_POWERPC_MEMBARRIER_H + +static inline void membarrier_arch_switch_mm(struct mm_struct *prev, + struct mm_struct *next, + struct task_struct *tsk) +{ + /* + * Only need the full barrier when switching between processes. + * Barrier when switching from kernel to userspace is not + * required here, given that it is implied by mmdrop(). Barrier + * when switching from userspace to kernel is not needed after + * store to rq->curr. + */ + if (likely(!(atomic_read(&next->membarrier_state) & + (MEMBARRIER_STATE_PRIVATE_EXPEDITED | + MEMBARRIER_STATE_GLOBAL_EXPEDITED)) || !prev)) + return; + + /* + * The membarrier system call requires a full memory barrier + * after storing to rq->curr, before going back to user-space. + */ + smp_mb(); +} + +#endif /* _ASM_POWERPC_MEMBARRIER_H */ diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h index 30922f699341..07e3f54de9e3 100644 --- a/arch/powerpc/include/asm/mman.h +++ b/arch/powerpc/include/asm/mman.h @@ -13,6 +13,7 @@ #include <asm/cputable.h> #include <linux/mm.h> +#include <linux/pkeys.h> #include <asm/cpu_has_feature.h> /* @@ -22,13 +23,23 @@ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { - return (prot & PROT_SAO) ? VM_SAO : 0; +#ifdef CONFIG_PPC_MEM_KEYS + return (((prot & PROT_SAO) ? VM_SAO : 0) | pkey_to_vmflag_bits(pkey)); +#else + return ((prot & PROT_SAO) ? VM_SAO : 0); +#endif } #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags) { +#ifdef CONFIG_PPC_MEM_KEYS + return (vm_flags & VM_SAO) ? + __pgprot(_PAGE_SAO | vmflag_to_pte_pkey_bits(vm_flags)) : + __pgprot(0 | vmflag_to_pte_pkey_bits(vm_flags)); +#else return (vm_flags & VM_SAO) ? __pgprot(_PAGE_SAO) : __pgprot(0); +#endif } #define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags) diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/mmu-8xx.h index 5bb3dbede41a..2f806e329648 100644 --- a/arch/powerpc/include/asm/mmu-8xx.h +++ b/arch/powerpc/include/asm/mmu-8xx.h @@ -29,17 +29,25 @@ #define MI_Kp 0x40000000 /* Should always be set */ /* - * All pages' PP exec bits are set to 000, which means Execute for Supervisor - * and no Execute for User. - * Then we use the APG to say whether accesses are according to Page rules, - * "all Supervisor" rules (Exec for all) and "all User" rules (Exec for noone) - * Therefore, we define 4 APG groups. msb is _PAGE_EXEC, lsb is _PAGE_USER - * 0 (00) => Not User, no exec => 11 (all accesses performed as user) - * 1 (01) => User but no exec => 11 (all accesses performed as user) - * 2 (10) => Not User, exec => 01 (rights according to page definition) - * 3 (11) => User, exec => 00 (all accesses performed as supervisor) - */ -#define MI_APG_INIT 0xf4ffffff + * All pages' PP data bits are set to either 001 or 011 by copying _PAGE_EXEC + * into bit 21 in the ITLBmiss handler (bit 21 is the middle bit), which means + * respectively NA for All or X for Supervisor and no access for User. + * Then we use the APG to say whether accesses are according to Page rules or + * "all Supervisor" rules (Access to all) + * We also use the 2nd APG bit for _PAGE_ACCESSED when having SWAP: + * When that bit is not set access is done iaw "all user" + * which means no access iaw page rules. + * Therefore, we define 4 APG groups. lsb is _PMD_USER, 2nd is _PAGE_ACCESSED + * 0x => No access => 11 (all accesses performed as user iaw page definition) + * 10 => No user => 01 (all accesses performed according to page definition) + * 11 => User => 00 (all accesses performed as supervisor iaw page definition) + * We define all 16 groups so that all other bits of APG can take any value + */ +#ifdef CONFIG_SWAP +#define MI_APG_INIT 0xf4f4f4f4 +#else +#define MI_APG_INIT 0x44444444 +#endif /* The effective page number register. When read, contains the information * about the last instruction TLB miss. When MI_RPN is written, bits in @@ -102,17 +110,25 @@ #define MD_Kp 0x40000000 /* Should always be set */ /* - * All pages' PP data bits are set to either 000 or 011, which means + * All pages' PP data bits are set to either 000 or 011 or 001, which means * respectively RW for Supervisor and no access for User, or RO for - * Supervisor and no access for user. + * Supervisor and no access for user and NA for ALL. * Then we use the APG to say whether accesses are according to Page rules or * "all Supervisor" rules (Access to all) - * Therefore, we define 2 APG groups. lsb is _PAGE_USER - * 0 => No user => 01 (all accesses performed according to page definition) - * 1 => User => 00 (all accesses performed as supervisor - * according to page definition) - */ -#define MD_APG_INIT 0x4fffffff + * We also use the 2nd APG bit for _PAGE_ACCESSED when having SWAP: + * When that bit is not set access is done iaw "all user" + * which means no access iaw page rules. + * Therefore, we define 4 APG groups. lsb is _PMD_USER, 2nd is _PAGE_ACCESSED + * 0x => No access => 11 (all accesses performed as user iaw page definition) + * 10 => No user => 01 (all accesses performed according to page definition) + * 11 => User => 00 (all accesses performed as supervisor iaw page definition) + * We define all 16 groups so that all other bits of APG can take any value + */ +#ifdef CONFIG_SWAP +#define MD_APG_INIT 0xf4f4f4f4 +#else +#define MD_APG_INIT 0x44444444 +#endif /* The effective page number register. When read, contains the information * about the last instruction TLB miss. When MD_RPN is written, bits in @@ -164,6 +180,12 @@ */ #define SPRN_M_TW 799 +/* APGs */ +#define M_APG0 0x00000000 +#define M_APG1 0x00000020 +#define M_APG2 0x00000040 +#define M_APG3 0x00000060 + #ifndef __ASSEMBLY__ typedef struct { unsigned int id; diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 6364f5c2cc3e..bb38312cff28 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -260,6 +260,15 @@ static inline bool early_radix_enabled(void) } #endif +#ifdef CONFIG_PPC_MEM_KEYS +extern u16 get_mm_addr_key(struct mm_struct *mm, unsigned long address); +#else +static inline u16 get_mm_addr_key(struct mm_struct *mm, unsigned long address) +{ + return 0; +} +#endif /* CONFIG_PPC_MEM_KEYS */ + #endif /* !__ASSEMBLY__ */ /* The kernel use the constants below to index in the page sizes array. diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index e2a2b8400490..051b3d63afe3 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -187,11 +187,33 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm, { } +#ifdef CONFIG_PPC_MEM_KEYS +bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, + bool execute, bool foreign); +#else /* CONFIG_PPC_MEM_KEYS */ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, bool execute, bool foreign) { /* by default, allow everything */ return true; } + +#define pkey_mm_init(mm) +#define thread_pkey_regs_save(thread) +#define thread_pkey_regs_restore(new_thread, old_thread) +#define thread_pkey_regs_init(thread) + +static inline int vma_pkey(struct vm_area_struct *vma) +{ + return 0; +} + +static inline u64 pte_to_hpte_pkey_bits(u64 pteflags) +{ + return 0x0UL; +} + +#endif /* CONFIG_PPC_MEM_KEYS */ + #endif /* __KERNEL__ */ #endif /* __ASM_POWERPC_MMU_CONTEXT_H */ diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index 6c0132c7212f..7e28442827f1 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -45,6 +45,9 @@ struct mod_arch_specific { unsigned long tramp; #endif + /* For module function descriptor dereference */ + unsigned long start_opd; + unsigned long end_opd; #else /* powerpc64 */ /* Indices of PLT sections within module. */ unsigned int core_plt_section; diff --git a/arch/powerpc/include/asm/mpic_timer.h b/arch/powerpc/include/asm/mpic_timer.h index 0e23cd4ac8aa..13e6702ec458 100644 --- a/arch/powerpc/include/asm/mpic_timer.h +++ b/arch/powerpc/include/asm/mpic_timer.h @@ -29,17 +29,17 @@ struct mpic_timer { #ifdef CONFIG_MPIC_TIMER struct mpic_timer *mpic_request_timer(irq_handler_t fn, void *dev, - const struct timeval *time); + time64_t time); void mpic_start_timer(struct mpic_timer *handle); void mpic_stop_timer(struct mpic_timer *handle); -void mpic_get_remain_time(struct mpic_timer *handle, struct timeval *time); +void mpic_get_remain_time(struct mpic_timer *handle, time64_t *time); void mpic_free_timer(struct mpic_timer *handle); #else struct mpic_timer *mpic_request_timer(irq_handler_t fn, void *dev, - const struct timeval *time) { return NULL; } + time64_t time) { return NULL; } void mpic_start_timer(struct mpic_timer *handle) { } void mpic_stop_timer(struct mpic_timer *handle) { } -void mpic_get_remain_time(struct mpic_timer *handle, struct timeval *time) { } +void mpic_get_remain_time(struct mpic_timer *handle, time64_t *time) { } void mpic_free_timer(struct mpic_timer *handle) { } #endif diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h index e97f58689ca7..9c80939b4d14 100644 --- a/arch/powerpc/include/asm/nmi.h +++ b/arch/powerpc/include/asm/nmi.h @@ -4,10 +4,6 @@ #ifdef CONFIG_PPC_WATCHDOG extern void arch_touch_nmi_watchdog(void); -extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, - bool exclude_self); -#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace - #else static inline void arch_touch_nmi_watchdog(void) {} #endif diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h index d072139ff2e5..29d37bd1f3b3 100644 --- a/arch/powerpc/include/asm/nohash/32/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h @@ -61,7 +61,8 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pte_page) { - *pmdp = __pmd((page_to_pfn(pte_page) << PAGE_SHIFT) | _PMD_PRESENT); + *pmdp = __pmd((page_to_pfn(pte_page) << PAGE_SHIFT) | _PMD_USER | + _PMD_PRESENT); } #define pmd_pgtable(pmd) pmd_page(pmd) diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index cc2bfec3aa3b..03bbd1149530 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -24,6 +24,7 @@ extern int icache_44x_need_flush; #define PGD_INDEX_SIZE (32 - PGDIR_SHIFT) #define PMD_CACHE_INDEX PMD_INDEX_SIZE +#define PUD_CACHE_INDEX PUD_INDEX_SIZE #ifndef __ASSEMBLY__ #define PTE_TABLE_SIZE (sizeof(pte_t) << PTE_INDEX_SIZE) @@ -282,7 +283,7 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm, { unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); - unsigned long clr = ~pte_val(entry) & _PAGE_RO; + unsigned long clr = ~pte_val(entry) & (_PAGE_RO | _PAGE_NA); pte_update(ptep, clr, set); } diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h index 6dc0180fd5c7..f04cb46ae8a1 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h @@ -31,37 +31,34 @@ /* Definitions for 8xx embedded chips. */ #define _PAGE_PRESENT 0x0001 /* Page is valid */ #define _PAGE_NO_CACHE 0x0002 /* I: cache inhibit */ -#define _PAGE_SHARED 0x0004 /* No ASID (context) compare */ -#define _PAGE_SPECIAL 0x0008 /* SW entry, forced to 0 by the TLB miss */ +#define _PAGE_PRIVILEGED 0x0004 /* No ASID (context) compare */ +#define _PAGE_HUGE 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 * into the TLB. */ #define _PAGE_GUARDED 0x0010 /* Copied to L1 G entry in DTLB */ -#define _PAGE_USER 0x0020 /* Copied to L1 APG lsb */ -#define _PAGE_EXEC 0x0040 /* Copied to L1 APG */ -#define _PAGE_WRITETHRU 0x0080 /* software: caching is write through */ -#define _PAGE_ACCESSED 0x0800 /* software: page referenced */ +#define _PAGE_SPECIAL 0x0020 /* SW entry */ +#define _PAGE_EXEC 0x0040 /* Copied to PP (bit 21) in ITLB */ +#define _PAGE_ACCESSED 0x0080 /* software: page referenced */ +#define _PAGE_NA 0x0200 /* Supervisor NA, User no access */ #define _PAGE_RO 0x0600 /* Supervisor RO, User no access */ #define _PMD_PRESENT 0x0001 -#define _PMD_BAD 0x0ff0 +#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 */ /* Until my rework is finished, 8xx still needs atomic PTE updates */ #define PTE_ATOMIC_UPDATES 1 -/* We need to add _PAGE_SHARED to kernel pages */ -#define _PAGE_KERNEL_RO (_PAGE_SHARED | _PAGE_RO) -#define _PAGE_KERNEL_ROX (_PAGE_SHARED | _PAGE_RO | _PAGE_EXEC) -#define _PAGE_KERNEL_RW (_PAGE_SHARED | _PAGE_DIRTY | _PAGE_RW | \ - _PAGE_HWWRITE) -#define _PAGE_KERNEL_RWX (_PAGE_SHARED | _PAGE_DIRTY | _PAGE_RW | \ - _PAGE_HWWRITE | _PAGE_EXEC) +#ifdef CONFIG_PPC_16K_PAGES +#define _PAGE_PSIZE _PAGE_HUGE +#endif #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_NOHASH_32_PTE_8xx_H */ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index abddf5830ad5..5c5f75d005ad 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -27,6 +27,7 @@ #else #define PMD_CACHE_INDEX PMD_INDEX_SIZE #endif +#define PUD_CACHE_INDEX PUD_INDEX_SIZE /* * Define the address range of the kernel non-linear virtual area diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index 5c68f4a59f75..c56de1e8026f 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -45,6 +45,29 @@ static inline int pte_present(pte_t pte) return pte_val(pte) & _PAGE_PRESENT; } +/* + * We only find page table entry in the last level + * Hence no need for other accessors + */ +#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 ((pteval & need_pte_bits) != need_pte_bits) + return false; + + return true; +} + /* Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. * @@ -103,7 +126,7 @@ static inline pte_t pte_mkspecial(pte_t pte) static inline pte_t pte_mkhuge(pte_t pte) { - return pte; + return __pte(pte_val(pte) | _PAGE_HUGE); } static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) @@ -212,8 +235,10 @@ extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addre #define pgprot_cached(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ _PAGE_COHERENT)) +#if _PAGE_WRITETHRU != 0 #define pgprot_cached_wthru(prot) (__pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) | \ _PAGE_COHERENT | _PAGE_WRITETHRU)) +#endif #define pgprot_cached_noncoherent(prot) \ (__pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL)) diff --git a/arch/powerpc/include/asm/nohash/pte-book3e.h b/arch/powerpc/include/asm/nohash/pte-book3e.h index 2da4532ca377..ccee8eb509bb 100644 --- a/arch/powerpc/include/asm/nohash/pte-book3e.h +++ b/arch/powerpc/include/asm/nohash/pte-book3e.h @@ -55,6 +55,7 @@ #define _PAGE_KERNEL_RWX (_PAGE_BAP_SW | _PAGE_BAP_SR | _PAGE_DIRTY | _PAGE_BAP_SX) #define _PAGE_KERNEL_ROX (_PAGE_BAP_SR | _PAGE_BAP_SX) #define _PAGE_USER (_PAGE_BAP_UR | _PAGE_BAP_SR) /* Can be read */ +#define _PAGE_PRIVILEGED (_PAGE_BAP_SR) #define _PAGE_HASHPTE 0 #define _PAGE_BUSY 0 diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index 233c7504b1f2..94bd1bf2c873 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -201,7 +201,10 @@ #define OPAL_SET_POWER_SHIFT_RATIO 155 #define OPAL_SENSOR_GROUP_CLEAR 156 #define OPAL_PCI_SET_P2P 157 -#define OPAL_LAST 157 +#define OPAL_NPU_SPA_SETUP 159 +#define OPAL_NPU_SPA_CLEAR_CACHE 160 +#define OPAL_NPU_TL_SET 161 +#define OPAL_LAST 161 /* Device tree flags */ @@ -1073,6 +1076,7 @@ enum { /* Flags for OPAL_XIVE_GET/SET_VP_INFO */ enum { OPAL_XIVE_VP_ENABLED = 0x00000001, + OPAL_XIVE_VP_SINGLE_ESCALATION = 0x00000002, }; /* "Any chip" replacement for chip ID for allocation functions */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 0c545f7fc77b..12e70fb58700 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -34,6 +34,12 @@ int64_t opal_npu_init_context(uint64_t phb_id, int pasid, uint64_t msr, uint64_t bdf); int64_t opal_npu_map_lpar(uint64_t phb_id, uint64_t bdf, uint64_t lparid, uint64_t lpcr); +int64_t opal_npu_spa_setup(uint64_t phb_id, uint32_t bdfn, + uint64_t addr, uint64_t PE_mask); +int64_t opal_npu_spa_clear_cache(uint64_t phb_id, uint32_t bdfn, + uint64_t PE_handle); +int64_t opal_npu_tl_set(uint64_t phb_id, uint32_t bdfn, long cap, + uint64_t rate_phys, uint32_t size); int64_t opal_console_write(int64_t term_number, __be64 *length, const uint8_t *buffer); int64_t opal_console_read(int64_t term_number, __be64 *length, diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 23ac7fc0af23..b62c31037cad 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -159,7 +159,7 @@ struct paca_struct { u64 saved_r1; /* r1 save for RTAS calls or PM */ u64 saved_msr; /* MSR saved here by enter_rtas */ u16 trap_save; /* Used when bad stack is encountered */ - u8 soft_enabled; /* irq soft-enable flag */ + u8 irq_soft_mask; /* mask for irq soft masking */ u8 irq_happened; /* irq happened while soft-disabled */ u8 io_sync; /* writel() needs spin_unlock sync */ u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */ @@ -239,8 +239,7 @@ struct paca_struct { */ u64 exrfi[EX_SIZE] __aligned(0x80); void *rfi_flush_fallback_area; - u64 l1d_flush_congruence; - u64 l1d_flush_sets; + u64 l1d_flush_size; #endif }; diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 62ed83db04ae..94d449031b18 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -197,25 +197,22 @@ struct pci_dn { struct iommu_table_group *table_group; /* for phb's or bridges */ int pci_ext_config_space; /* for pci devices */ - - struct pci_dev *pcidev; /* back-pointer to the pci device */ #ifdef CONFIG_EEH struct eeh_dev *edev; /* eeh device */ #endif #define IODA_INVALID_PE 0xFFFFFFFF -#ifdef CONFIG_PPC_POWERNV unsigned int pe_number; - int vf_index; /* VF index in the PF */ #ifdef CONFIG_PCI_IOV + int vf_index; /* VF index in the PF */ u16 vfs_expanded; /* number of VFs IOV BAR expanded */ u16 num_vfs; /* number of VFs enabled*/ unsigned int *pe_num_map; /* PE# for the first VF PE or array */ bool m64_single_mode; /* Use M64 BAR in Single Mode */ #define IODA_INVALID_M64 (-1) - int (*m64_map)[PCI_SRIOV_NUM_BARS]; + int (*m64_map)[PCI_SRIOV_NUM_BARS]; /* Only used on powernv */ + int last_allow_rc; /* Only used on pseries */ #endif /* CONFIG_PCI_IOV */ int mps; /* Maximum Payload Size */ -#endif struct list_head child_list; struct list_head list; struct resource holes[PCI_SRIOV_NUM_BARS]; diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 8dc32eacc97c..d82802ff5088 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -121,6 +121,8 @@ extern int remove_phb_dynamic(struct pci_controller *phb); extern struct pci_dev *of_create_pci_dev(struct device_node *node, struct pci_bus *bus, int devfn); +extern unsigned int pci_parse_of_flags(u32 addr0, int bridge); + extern void of_scan_pci_bridge(struct pci_dev *dev); extern void of_scan_bus(struct device_node *node, struct pci_bus *bus); diff --git a/arch/powerpc/include/asm/pkeys.h b/arch/powerpc/include/asm/pkeys.h new file mode 100644 index 000000000000..0409c80c32c0 --- /dev/null +++ b/arch/powerpc/include/asm/pkeys.h @@ -0,0 +1,218 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * PowerPC Memory Protection Keys management + * + * Copyright 2017, Ram Pai, IBM Corporation. + */ + +#ifndef _ASM_POWERPC_KEYS_H +#define _ASM_POWERPC_KEYS_H + +#include <linux/jump_label.h> +#include <asm/firmware.h> + +DECLARE_STATIC_KEY_TRUE(pkey_disabled); +extern int pkeys_total; /* total pkeys as per device tree */ +extern u32 initial_allocation_mask; /* bits set for reserved keys */ + +/* + * Define these here temporarily so we're not dependent on patching linux/mm.h. + * Once it's updated we can drop these. + */ +#ifndef VM_PKEY_BIT0 +# define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 +# define VM_PKEY_BIT0 VM_HIGH_ARCH_0 +# define VM_PKEY_BIT1 VM_HIGH_ARCH_1 +# define VM_PKEY_BIT2 VM_HIGH_ARCH_2 +# define VM_PKEY_BIT3 VM_HIGH_ARCH_3 +# define VM_PKEY_BIT4 VM_HIGH_ARCH_4 +#endif + +#define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | \ + VM_PKEY_BIT3 | VM_PKEY_BIT4) + +/* Override any generic PKEY permission defines */ +#define PKEY_DISABLE_EXECUTE 0x4 +#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS | \ + PKEY_DISABLE_WRITE | \ + PKEY_DISABLE_EXECUTE) + +static inline u64 pkey_to_vmflag_bits(u16 pkey) +{ + return (((u64)pkey << VM_PKEY_SHIFT) & ARCH_VM_PKEY_FLAGS); +} + +static inline u64 vmflag_to_pte_pkey_bits(u64 vm_flags) +{ + if (static_branch_likely(&pkey_disabled)) + return 0x0UL; + + return (((vm_flags & VM_PKEY_BIT0) ? H_PTE_PKEY_BIT4 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT1) ? H_PTE_PKEY_BIT3 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT2) ? H_PTE_PKEY_BIT2 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT3) ? H_PTE_PKEY_BIT1 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT4) ? H_PTE_PKEY_BIT0 : 0x0UL)); +} + +static inline int vma_pkey(struct vm_area_struct *vma) +{ + if (static_branch_likely(&pkey_disabled)) + return 0; + return (vma->vm_flags & ARCH_VM_PKEY_FLAGS) >> VM_PKEY_SHIFT; +} + +#define arch_max_pkey() pkeys_total + +static inline u64 pte_to_hpte_pkey_bits(u64 pteflags) +{ + return (((pteflags & H_PTE_PKEY_BIT0) ? HPTE_R_KEY_BIT0 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT1) ? HPTE_R_KEY_BIT1 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT2) ? HPTE_R_KEY_BIT2 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT3) ? HPTE_R_KEY_BIT3 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT4) ? HPTE_R_KEY_BIT4 : 0x0UL)); +} + +static inline u16 pte_to_pkey_bits(u64 pteflags) +{ + return (((pteflags & H_PTE_PKEY_BIT0) ? 0x10 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT1) ? 0x8 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT2) ? 0x4 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT3) ? 0x2 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT4) ? 0x1 : 0x0UL)); +} + +#define pkey_alloc_mask(pkey) (0x1 << pkey) + +#define mm_pkey_allocation_map(mm) (mm->context.pkey_allocation_map) + +#define __mm_pkey_allocated(mm, pkey) { \ + mm_pkey_allocation_map(mm) |= pkey_alloc_mask(pkey); \ +} + +#define __mm_pkey_free(mm, pkey) { \ + mm_pkey_allocation_map(mm) &= ~pkey_alloc_mask(pkey); \ +} + +#define __mm_pkey_is_allocated(mm, pkey) \ + (mm_pkey_allocation_map(mm) & pkey_alloc_mask(pkey)) + +#define __mm_pkey_is_reserved(pkey) (initial_allocation_mask & \ + pkey_alloc_mask(pkey)) + +static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) +{ + /* A reserved key is never considered as 'explicitly allocated' */ + return ((pkey < arch_max_pkey()) && + !__mm_pkey_is_reserved(pkey) && + __mm_pkey_is_allocated(mm, pkey)); +} + +extern void __arch_activate_pkey(int pkey); +extern void __arch_deactivate_pkey(int pkey); +/* + * Returns a positive, 5-bit key on success, or -1 on failure. + * Relies on the mmap_sem to protect against concurrency in mm_pkey_alloc() and + * mm_pkey_free(). + */ +static inline int mm_pkey_alloc(struct mm_struct *mm) +{ + /* + * Note: this is the one and only place we make sure that the pkey is + * valid as far as the hardware is concerned. The rest of the kernel + * trusts that only good, valid pkeys come out of here. + */ + u32 all_pkeys_mask = (u32)(~(0x0)); + int ret; + + if (static_branch_likely(&pkey_disabled)) + return -1; + + /* + * Are we out of pkeys? We must handle this specially because ffz() + * behavior is undefined if there are no zeros. + */ + if (mm_pkey_allocation_map(mm) == all_pkeys_mask) + return -1; + + ret = ffz((u32)mm_pkey_allocation_map(mm)); + __mm_pkey_allocated(mm, ret); + + /* + * Enable the key in the hardware + */ + if (ret > 0) + __arch_activate_pkey(ret); + return ret; +} + +static inline int mm_pkey_free(struct mm_struct *mm, int pkey) +{ + if (static_branch_likely(&pkey_disabled)) + return -1; + + if (!mm_pkey_is_allocated(mm, pkey)) + return -EINVAL; + + /* + * Disable the key in the hardware + */ + __arch_deactivate_pkey(pkey); + __mm_pkey_free(mm, pkey); + + return 0; +} + +/* + * Try to dedicate one of the protection keys to be used as an + * execute-only protection key. + */ +extern int __execute_only_pkey(struct mm_struct *mm); +static inline int execute_only_pkey(struct mm_struct *mm) +{ + if (static_branch_likely(&pkey_disabled)) + return -1; + + return __execute_only_pkey(mm); +} + +extern int __arch_override_mprotect_pkey(struct vm_area_struct *vma, + int prot, int pkey); +static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, + int prot, int pkey) +{ + if (static_branch_likely(&pkey_disabled)) + return 0; + + /* + * Is this an mprotect_pkey() call? If so, never override the value that + * came from the user. + */ + if (pkey != -1) + return pkey; + + return __arch_override_mprotect_pkey(vma, prot, pkey); +} + +extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, + unsigned long init_val); +static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, + unsigned long init_val) +{ + if (static_branch_likely(&pkey_disabled)) + return -EINVAL; + return __arch_set_user_pkey_access(tsk, pkey, init_val); +} + +static inline bool arch_pkeys_enabled(void) +{ + return !static_branch_likely(&pkey_disabled); +} + +extern void pkey_mm_init(struct mm_struct *mm); +extern bool arch_supports_pkeys(int cap); +extern unsigned int arch_usable_pkeys(void); +extern void thread_pkey_regs_save(struct thread_struct *thread); +extern void thread_pkey_regs_restore(struct thread_struct *new_thread, + struct thread_struct *old_thread); +extern void thread_pkey_regs_init(struct thread_struct *thread); +#endif /*_ASM_POWERPC_KEYS_H */ diff --git a/arch/powerpc/include/asm/pnv-ocxl.h b/arch/powerpc/include/asm/pnv-ocxl.h new file mode 100644 index 000000000000..f6945d3bc971 --- /dev/null +++ b/arch/powerpc/include/asm/pnv-ocxl.h @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright 2017 IBM Corp. +#ifndef _ASM_PNV_OCXL_H +#define _ASM_PNV_OCXL_H + +#include <linux/pci.h> + +#define PNV_OCXL_TL_MAX_TEMPLATE 63 +#define PNV_OCXL_TL_BITS_PER_RATE 4 +#define PNV_OCXL_TL_RATE_BUF_SIZE ((PNV_OCXL_TL_MAX_TEMPLATE+1) * PNV_OCXL_TL_BITS_PER_RATE / 8) + +extern int pnv_ocxl_get_actag(struct pci_dev *dev, u16 *base, u16 *enabled, + u16 *supported); +extern int pnv_ocxl_get_pasid_count(struct pci_dev *dev, int *count); + +extern int pnv_ocxl_get_tl_cap(struct pci_dev *dev, long *cap, + char *rate_buf, int rate_buf_size); +extern int pnv_ocxl_set_tl_conf(struct pci_dev *dev, long cap, + uint64_t rate_buf_phys, int rate_buf_size); + +extern int pnv_ocxl_get_xsl_irq(struct pci_dev *dev, int *hwirq); +extern void pnv_ocxl_unmap_xsl_regs(void __iomem *dsisr, void __iomem *dar, + void __iomem *tfc, void __iomem *pe_handle); +extern int pnv_ocxl_map_xsl_regs(struct pci_dev *dev, void __iomem **dsisr, + void __iomem **dar, void __iomem **tfc, + void __iomem **pe_handle); + +extern int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask, + void **platform_data); +extern void pnv_ocxl_spa_release(void *platform_data); +extern int pnv_ocxl_spa_remove_pe(void *platform_data, int pe_handle); + +extern int pnv_ocxl_alloc_xive_irq(u32 *irq, u64 *trigger_addr); +extern void pnv_ocxl_free_xive_irq(u32 irq); + +#endif /* _ASM_PNV_OCXL_H */ diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index ce0930d68857..f1083bcf449c 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -156,6 +156,12 @@ #define OP_31_XOP_LFDX 599 #define OP_31_XOP_LFDUX 631 +/* VMX Vector Load Instructions */ +#define OP_31_XOP_LVX 103 + +/* VMX Vector Store Instructions */ +#define OP_31_XOP_STVX 231 + #define OP_LWZ 32 #define OP_STFS 52 #define OP_STFSU 53 @@ -236,6 +242,7 @@ #define PPC_INST_RFCI 0x4c000066 #define PPC_INST_RFDI 0x4c00004e #define PPC_INST_RFMCI 0x4c00004c +#define PPC_INST_MFSPR 0x7c0002a6 #define PPC_INST_MFSPR_DSCR 0x7c1102a6 #define PPC_INST_MFSPR_DSCR_MASK 0xfc1ffffe #define PPC_INST_MTSPR_DSCR 0x7c1103a6 @@ -383,6 +390,7 @@ #define __PPC_ME64(s) __PPC_MB64(s) #define __PPC_BI(s) (((s) & 0x1f) << 16) #define __PPC_CT(t) (((t) & 0x0f) << 21) +#define __PPC_SPR(r) ((((r) & 0x1f) << 16) | ((((r) >> 5) & 0x1f) << 11)) /* * Only use the larx hint bit on 64bit CPUs. e500v1/v2 based CPUs will treat a diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index bdab3b74eb98..01299cdc9806 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -309,6 +309,11 @@ struct thread_struct { struct thread_vr_state ckvr_state; /* Checkpointed VR state */ unsigned long ckvrsave; /* Checkpointed VRSAVE */ #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ +#ifdef CONFIG_PPC_MEM_KEYS + unsigned long amr; + unsigned long iamr; + unsigned long uamor; +#endif #ifdef CONFIG_KVM_BOOK3S_32_HANDLER void* kvm_shadow_vcpu; /* KVM internal data */ #endif /* CONFIG_KVM_BOOK3S_32_HANDLER */ diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index 825bd5998701..b04c5ce8191b 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -80,21 +80,20 @@ extern void of_instantiate_rtc(void); extern int of_get_ibm_chip_id(struct device_node *np); -/* The of_drconf_cell struct defines the layout of the LMB array - * specified in the device tree property - * ibm,dynamic-reconfiguration-memory/ibm,dynamic-memory - */ -struct of_drconf_cell { - u64 base_addr; - u32 drc_index; - u32 reserved; - u32 aa_index; - u32 flags; +struct of_drc_info { + char *drc_type; + char *drc_name_prefix; + u32 drc_index_start; + u32 drc_name_suffix_start; + u32 num_sequential_elems; + u32 sequential_inc; + u32 drc_power_domain; + u32 last_drc_index; }; -#define DRCONF_MEM_ASSIGNED 0x00000008 -#define DRCONF_MEM_AI_INVALID 0x00000040 -#define DRCONF_MEM_RESERVED 0x00000080 +extern int of_read_drc_info_cell(struct property **prop, + const __be32 **curval, struct of_drc_info *data); + /* * There are two methods for telling firmware what our capabilities are. @@ -159,6 +158,7 @@ struct of_drconf_cell { #define OV5_PFO_HW_842 0x1140 /* PFO Compression Accelerator */ #define OV5_PFO_HW_ENCR 0x1120 /* PFO Encryption Accelerator */ #define OV5_SUB_PROCESSORS 0x1501 /* 1,2,or 4 Sub-Processors supported */ +#define OV5_DRMEM_V2 0x1680 /* ibm,dynamic-reconfiguration-v2 */ #define OV5_XIVE_SUPPORT 0x17C0 /* XIVE Exploitation Support Mask */ #define OV5_XIVE_LEGACY 0x1700 /* XIVE legacy mode Only */ #define OV5_XIVE_EXPLOIT 0x1740 /* XIVE exploitation mode Only */ @@ -175,6 +175,7 @@ struct of_drconf_cell { #define OV5_HASH_GTSE 0x1940 /* Guest Translation Shoot Down Avail */ /* Radix Table Extensions */ #define OV5_RADIX_GTSE 0x1A40 /* Guest Translation Shoot Down Avail */ +#define OV5_DRC_INFO 0x1640 /* Redef Prop Structures: drc-info */ /* Option Vector 6: IBM PAPR hints */ #define OV6_LINUX 0x02 /* Linux is our OS */ diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h index ce142ef99ba7..c4a72c7a8c83 100644 --- a/arch/powerpc/include/asm/pte-common.h +++ b/arch/powerpc/include/asm/pte-common.h @@ -8,9 +8,6 @@ #ifndef _PAGE_HASHPTE #define _PAGE_HASHPTE 0 #endif -#ifndef _PAGE_SHARED -#define _PAGE_SHARED 0 -#endif #ifndef _PAGE_HWWRITE #define _PAGE_HWWRITE 0 #endif @@ -45,6 +42,20 @@ #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 @@ -53,17 +64,22 @@ #define _PMD_SIZE 0 #define PMD_PAGE_SIZE(pmd) bad_call_to_PMD_PAGE_SIZE() #endif +#ifndef _PMD_USER +#define _PMD_USER 0 +#endif #ifndef _PAGE_KERNEL_RO -#define _PAGE_KERNEL_RO (_PAGE_RO) +#define _PAGE_KERNEL_RO (_PAGE_PRIVILEGED | _PAGE_RO) #endif #ifndef _PAGE_KERNEL_ROX -#define _PAGE_KERNEL_ROX (_PAGE_EXEC | _PAGE_RO) +#define _PAGE_KERNEL_ROX (_PAGE_PRIVILEGED | _PAGE_RO | _PAGE_EXEC) #endif #ifndef _PAGE_KERNEL_RW -#define _PAGE_KERNEL_RW (_PAGE_DIRTY | _PAGE_RW | _PAGE_HWWRITE) +#define _PAGE_KERNEL_RW (_PAGE_PRIVILEGED | _PAGE_DIRTY | _PAGE_RW | \ + _PAGE_HWWRITE) #endif #ifndef _PAGE_KERNEL_RWX -#define _PAGE_KERNEL_RWX (_PAGE_DIRTY | _PAGE_RW | _PAGE_HWWRITE | _PAGE_EXEC) +#define _PAGE_KERNEL_RWX (_PAGE_PRIVILEGED | _PAGE_DIRTY | _PAGE_RW | \ + _PAGE_HWWRITE | _PAGE_EXEC) #endif #ifndef _PAGE_HPTEFLAGS #define _PAGE_HPTEFLAGS _PAGE_HASHPTE @@ -85,7 +101,7 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void); */ static inline bool pte_user(pte_t pte) { - return (pte_val(pte) & _PAGE_USER) == _PAGE_USER; + return (pte_val(pte) & (_PAGE_USER | _PAGE_PRIVILEGED)) == _PAGE_USER; } #endif /* __ASSEMBLY__ */ @@ -115,7 +131,8 @@ static inline bool pte_user(pte_t pte) /* 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_USER | _PAGE_ACCESSED | _PAGE_RO | _PAGE_NA | \ + _PAGE_PRIVILEGED | \ _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | _PAGE_EXEC) /* @@ -142,7 +159,7 @@ static inline bool pte_user(pte_t pte) * * Note due to the way vm flags are laid out, the bits are XWR */ -#define PAGE_NONE __pgprot(_PAGE_BASE) +#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) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index b779f3ccd412..e6c7eadf6bce 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -312,7 +312,6 @@ DSISR_BAD_EXT_CTRL) #define DSISR_BAD_FAULT_64S (DSISR_BAD_FAULT_32S | \ DSISR_ATTR_CONFLICT | \ - DSISR_KEYFAULT | \ DSISR_UNSUPP_MMU | \ DSISR_PRTABLE_FAULT | \ DSISR_ICSWX_NO_CT | \ @@ -432,8 +431,9 @@ #define SPRN_LPID 0x13F /* Logical Partition Identifier */ #endif #define LPID_RSVD 0x3ff /* Reserved LPID for partn switching */ -#define SPRN_HMER 0x150 /* Hardware m? error recovery */ -#define SPRN_HMEER 0x151 /* Hardware m? enable error recovery */ +#define SPRN_HMER 0x150 /* Hypervisor maintenance exception reg */ +#define HMER_DEBUG_TRIG (1ul << (63 - 17)) /* Debug trigger */ +#define SPRN_HMEER 0x151 /* Hyp maintenance exception enable reg */ #define SPRN_PCR 0x152 /* Processor compatibility register */ #define PCR_VEC_DIS (1ul << (63-0)) /* Vec. disable (bit NA since POWER8) */ #define PCR_VSX_DIS (1ul << (63-1)) /* VSX disable (bit NA since POWER8) */ diff --git a/arch/powerpc/include/asm/reg_8xx.h b/arch/powerpc/include/asm/reg_8xx.h index 53a7e2955d3e..7192eece6c3e 100644 --- a/arch/powerpc/include/asm/reg_8xx.h +++ b/arch/powerpc/include/asm/reg_8xx.h @@ -66,86 +66,4 @@ #define DC_DFWT 0x40000000 /* Data cache is forced write through */ #define DC_LES 0x20000000 /* Caches are little endian mode */ -#ifdef CONFIG_8xx_CPU6 -#define do_mtspr_cpu6(rn, rn_addr, v) \ - do { \ - int _reg_cpu6 = rn_addr, _tmp_cpu6; \ - asm volatile("stw %0, %1;" \ - "lwz %0, %1;" \ - "mtspr " __stringify(rn) ",%2" : \ - : "r" (_reg_cpu6), "m"(_tmp_cpu6), \ - "r" ((unsigned long)(v)) \ - : "memory"); \ - } while (0) - -#define do_mtspr(rn, v) asm volatile("mtspr " __stringify(rn) ",%0" : \ - : "r" ((unsigned long)(v)) \ - : "memory") -#define mtspr(rn, v) \ - do { \ - if (rn == SPRN_IMMR) \ - do_mtspr_cpu6(rn, 0x3d30, v); \ - else if (rn == SPRN_IC_CST) \ - do_mtspr_cpu6(rn, 0x2110, v); \ - else if (rn == SPRN_IC_ADR) \ - do_mtspr_cpu6(rn, 0x2310, v); \ - else if (rn == SPRN_IC_DAT) \ - do_mtspr_cpu6(rn, 0x2510, v); \ - else if (rn == SPRN_DC_CST) \ - do_mtspr_cpu6(rn, 0x3110, v); \ - else if (rn == SPRN_DC_ADR) \ - do_mtspr_cpu6(rn, 0x3310, v); \ - else if (rn == SPRN_DC_DAT) \ - do_mtspr_cpu6(rn, 0x3510, v); \ - else if (rn == SPRN_MI_CTR) \ - do_mtspr_cpu6(rn, 0x2180, v); \ - else if (rn == SPRN_MI_AP) \ - do_mtspr_cpu6(rn, 0x2580, v); \ - else if (rn == SPRN_MI_EPN) \ - do_mtspr_cpu6(rn, 0x2780, v); \ - else if (rn == SPRN_MI_TWC) \ - do_mtspr_cpu6(rn, 0x2b80, v); \ - else if (rn == SPRN_MI_RPN) \ - do_mtspr_cpu6(rn, 0x2d80, v); \ - else if (rn == SPRN_MI_CAM) \ - do_mtspr_cpu6(rn, 0x2190, v); \ - else if (rn == SPRN_MI_RAM0) \ - do_mtspr_cpu6(rn, 0x2390, v); \ - else if (rn == SPRN_MI_RAM1) \ - do_mtspr_cpu6(rn, 0x2590, v); \ - else if (rn == SPRN_MD_CTR) \ - do_mtspr_cpu6(rn, 0x3180, v); \ - else if (rn == SPRN_M_CASID) \ - do_mtspr_cpu6(rn, 0x3380, v); \ - else if (rn == SPRN_MD_AP) \ - do_mtspr_cpu6(rn, 0x3580, v); \ - else if (rn == SPRN_MD_EPN) \ - do_mtspr_cpu6(rn, 0x3780, v); \ - else if (rn == SPRN_M_TWB) \ - do_mtspr_cpu6(rn, 0x3980, v); \ - else if (rn == SPRN_MD_TWC) \ - do_mtspr_cpu6(rn, 0x3b80, v); \ - else if (rn == SPRN_MD_RPN) \ - do_mtspr_cpu6(rn, 0x3d80, v); \ - else if (rn == SPRN_M_TW) \ - do_mtspr_cpu6(rn, 0x3f80, v); \ - else if (rn == SPRN_MD_CAM) \ - do_mtspr_cpu6(rn, 0x3190, v); \ - else if (rn == SPRN_MD_RAM0) \ - do_mtspr_cpu6(rn, 0x3390, v); \ - else if (rn == SPRN_MD_RAM1) \ - do_mtspr_cpu6(rn, 0x3590, v); \ - else if (rn == SPRN_DEC) \ - do_mtspr_cpu6(rn, 0x2c00, v); \ - else if (rn == SPRN_TBWL) \ - do_mtspr_cpu6(rn, 0x3880, v); \ - else if (rn == SPRN_TBWU) \ - do_mtspr_cpu6(rn, 0x3a80, v); \ - else if (rn == SPRN_DPDR) \ - do_mtspr_cpu6(rn, 0x2d30, v); \ - else \ - do_mtspr(rn, v); \ - } while (0) -#endif - #endif /* _ASM_POWERPC_REG_8xx_H */ diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 82bec63bbd4f..e335a8f846af 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -66,6 +66,9 @@ static inline int overlaps_kvm_tmp(unsigned long start, unsigned long end) } #ifdef PPC64_ELF_ABI_v1 + +#define HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR 1 + #undef dereference_function_descriptor static inline void *dereference_function_descriptor(void *ptr) { @@ -76,6 +79,15 @@ static inline void *dereference_function_descriptor(void *ptr) ptr = p; return ptr; } + +#undef dereference_kernel_function_descriptor +static inline void *dereference_kernel_function_descriptor(void *ptr) +{ + if (ptr < (void *)__start_opd || ptr >= (void *)__end_opd) + return ptr; + + return dereference_function_descriptor(ptr); +} #endif /* PPC64_ELF_ABI_v1 */ #endif diff --git a/arch/powerpc/include/asm/swiotlb.h b/arch/powerpc/include/asm/swiotlb.h index 01d45a5fd00b..f65ecf57b66c 100644 --- a/arch/powerpc/include/asm/swiotlb.h +++ b/arch/powerpc/include/asm/swiotlb.h @@ -13,9 +13,7 @@ #include <linux/swiotlb.h> -extern const struct dma_map_ops swiotlb_dma_ops; - -static inline void dma_mark_clean(void *addr, size_t size) {} +extern const struct dma_map_ops powerpc_swiotlb_dma_ops; extern unsigned int ppc_swiotlb_enable; int __init swiotlb_setup_bus_notifier(void); diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 449912f057f6..d61f9c96d916 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -389,3 +389,6 @@ COMPAT_SYS_SPU(preadv2) COMPAT_SYS_SPU(pwritev2) SYSCALL(kexec_file_load) SYSCALL(statx) +SYSCALL(pkey_alloc) +SYSCALL(pkey_free) +SYSCALL(pkey_mprotect) diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index a264c3ad366b..4a12c00f8de3 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -58,9 +58,6 @@ struct thread_info { .flags = 0, \ } -#define init_thread_info (init_thread_union.thread_info) -#define init_stack (init_thread_union.stack) - #define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT) /* how to get the thread information struct from C */ diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 88187c285c70..9f421641a35c 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -44,6 +44,11 @@ extern int sysfs_add_device_to_node(struct device *dev, int nid); extern void sysfs_remove_device_from_node(struct device *dev, int nid); extern int numa_update_cpu_topology(bool cpus_locked); +static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) +{ + numa_cpu_lookup_table[cpu] = node; +} + static inline int early_cpu_to_node(int cpu) { int nid; @@ -76,12 +81,16 @@ static inline int numa_update_cpu_topology(bool cpus_locked) { return 0; } + +static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {} + #endif /* CONFIG_NUMA */ #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) extern int start_topology_update(void); extern int stop_topology_update(void); extern int prrn_is_enabled(void); +extern int find_and_online_cpu_nid(int cpu); #else static inline int start_topology_update(void) { @@ -95,6 +104,10 @@ static inline int prrn_is_enabled(void) { return 0; } +static inline int find_and_online_cpu_nid(int cpu) +{ + return 0; +} #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */ #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_NEED_MULTIPLE_NODES) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 9ba11dbcaca9..daf1ba97a00c 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -12,14 +12,10 @@ #include <uapi/asm/unistd.h> -#define NR_syscalls 384 +#define NR_syscalls 387 #define __NR__exit __NR_exit -#define __IGNORE_pkey_mprotect -#define __IGNORE_pkey_alloc -#define __IGNORE_pkey_free - #ifndef __ASSEMBLY__ #include <linux/types.h> diff --git a/arch/powerpc/include/asm/xive-regs.h b/arch/powerpc/include/asm/xive-regs.h index 1d3f2be5ae39..fa4288822b68 100644 --- a/arch/powerpc/include/asm/xive-regs.h +++ b/arch/powerpc/include/asm/xive-regs.h @@ -10,6 +10,41 @@ #define _ASM_POWERPC_XIVE_REGS_H /* + * "magic" Event State Buffer (ESB) MMIO offsets. + * + * Each interrupt source has a 2-bit state machine called ESB + * which can be controlled by MMIO. It's made of 2 bits, P and + * Q. P indicates that an interrupt is pending (has been sent + * to a queue and is waiting for an EOI). Q indicates that the + * interrupt has been triggered while pending. + * + * This acts as a coalescing mechanism in order to guarantee + * that a given interrupt only occurs at most once in a queue. + * + * When doing an EOI, the Q bit will indicate if the interrupt + * needs to be re-triggered. + * + * The following offsets into the ESB MMIO allow to read or + * manipulate the PQ bits. They must be used with an 8-bytes + * load instruction. They all return the previous state of the + * interrupt (atomically). + * + * Additionally, some ESB pages support doing an EOI via a + * store at 0 and some ESBs support doing a trigger via a + * separate trigger page. + */ +#define XIVE_ESB_STORE_EOI 0x400 /* Store */ +#define XIVE_ESB_LOAD_EOI 0x000 /* Load */ +#define XIVE_ESB_GET 0x800 /* Load */ +#define XIVE_ESB_SET_PQ_00 0xc00 /* Load */ +#define XIVE_ESB_SET_PQ_01 0xd00 /* Load */ +#define XIVE_ESB_SET_PQ_10 0xe00 /* Load */ +#define XIVE_ESB_SET_PQ_11 0xf00 /* Load */ + +#define XIVE_ESB_VAL_P 0x2 +#define XIVE_ESB_VAL_Q 0x1 + +/* * Thread Management (aka "TM") registers */ diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h index 371fbebf1ec9..8d1a2792484f 100644 --- a/arch/powerpc/include/asm/xive.h +++ b/arch/powerpc/include/asm/xive.h @@ -58,6 +58,9 @@ struct xive_irq_data { #define XIVE_IRQ_FLAG_EOI_FW 0x10 #define XIVE_IRQ_FLAG_H_INT_ESB 0x20 +/* Special flag set by KVM for excalation interrupts */ +#define XIVE_IRQ_NO_EOI 0x80 + #define XIVE_INVALID_CHIP_ID -1 /* A queue tracking structure in a CPU */ @@ -72,41 +75,6 @@ struct xive_q { atomic_t pending_count; }; -/* - * "magic" Event State Buffer (ESB) MMIO offsets. - * - * Each interrupt source has a 2-bit state machine called ESB - * which can be controlled by MMIO. It's made of 2 bits, P and - * Q. P indicates that an interrupt is pending (has been sent - * to a queue and is waiting for an EOI). Q indicates that the - * interrupt has been triggered while pending. - * - * This acts as a coalescing mechanism in order to guarantee - * that a given interrupt only occurs at most once in a queue. - * - * When doing an EOI, the Q bit will indicate if the interrupt - * needs to be re-triggered. - * - * The following offsets into the ESB MMIO allow to read or - * manipulate the PQ bits. They must be used with an 8-bytes - * load instruction. They all return the previous state of the - * interrupt (atomically). - * - * Additionally, some ESB pages support doing an EOI via a - * store at 0 and some ESBs support doing a trigger via a - * separate trigger page. - */ -#define XIVE_ESB_STORE_EOI 0x400 /* Store */ -#define XIVE_ESB_LOAD_EOI 0x000 /* Load */ -#define XIVE_ESB_GET 0x800 /* Load */ -#define XIVE_ESB_SET_PQ_00 0xc00 /* Load */ -#define XIVE_ESB_SET_PQ_01 0xd00 /* Load */ -#define XIVE_ESB_SET_PQ_10 0xe00 /* Load */ -#define XIVE_ESB_SET_PQ_11 0xf00 /* Load */ - -#define XIVE_ESB_VAL_P 0x2 -#define XIVE_ESB_VAL_Q 0x1 - /* Global enable flags for the XIVE support */ extern bool __xive_enabled; @@ -143,9 +111,10 @@ extern void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio); extern void xive_native_sync_source(u32 hw_irq); extern bool is_xive_irq(struct irq_chip *chip); -extern int xive_native_enable_vp(u32 vp_id); +extern int xive_native_enable_vp(u32 vp_id, bool single_escalation); extern int xive_native_disable_vp(u32 vp_id); extern int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id); +extern bool xive_native_has_single_escalation(void); #else @@ -154,7 +123,7 @@ static inline bool xive_enabled(void) { return false; } static inline bool xive_spapr_init(void) { return false; } static inline bool xive_native_init(void) { return false; } static inline void xive_smp_probe(void) { } -extern inline int xive_smp_prepare_cpu(unsigned int cpu) { return -EINVAL; } +static inline int xive_smp_prepare_cpu(unsigned int cpu) { return -EINVAL; } static inline void xive_smp_setup_cpu(void) { } static inline void xive_smp_disable_cpu(void) { } static inline void xive_kexec_teardown_cpu(int secondary) { } |