--- zzzz-none-000/linux-3.10.107/arch/powerpc/include/asm/pgtable-ppc64.h 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/powerpc/include/asm/pgtable-ppc64.h 2021-02-04 17:41:59.000000000 +0000 @@ -10,8 +10,9 @@ #else #include #endif +#include -#define FIRST_USER_ADDRESS 0 +#define FIRST_USER_ADDRESS 0UL /* * Size of EA range mapped by our pagetables. @@ -20,7 +21,11 @@ PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT) #define PGTABLE_RANGE (ASM_CONST(1) << PGTABLE_EADDR_SIZE) - +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define PMD_CACHE_INDEX (PMD_INDEX_SIZE + 1) +#else +#define PMD_CACHE_INDEX PMD_INDEX_SIZE +#endif /* * Define the address range of the kernel non-linear virtual area */ @@ -113,7 +118,7 @@ */ #ifndef __real_pte -#ifdef STRICT_MM_TYPECHECKS +#ifdef CONFIG_STRICT_MM_TYPECHECKS #define __real_pte(e,p) ((real_pte_t){(e)}) #define __rpte_to_pte(r) ((r).pte) #else @@ -129,23 +134,11 @@ #define pte_iterate_hashed_end() } while(0) -#ifdef CONFIG_PPC_HAS_HASH_64K /* * We expect this to be called only for user addresses or kernel virtual * addresses other than the linear mapping. */ -#define pte_pagesize_index(mm, addr, pte) \ - ({ \ - unsigned int psize; \ - if (is_kernel_addr(addr)) \ - psize = MMU_PAGE_4K; \ - else \ - psize = get_slice_psize(mm, addr); \ - psize; \ - }) -#else #define pte_pagesize_index(mm, addr, pte) MMU_PAGE_4K -#endif #endif /* __real_pte */ @@ -159,10 +152,10 @@ #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_bad(pmd) (!is_kernel_addr(pmd_val(pmd)) \ || (pmd_val(pmd) & PMD_BAD_BITS)) -#define pmd_present(pmd) (pmd_val(pmd) != 0) +#define pmd_present(pmd) (!pmd_none(pmd)) #define pmd_clear(pmdp) (pmd_val(*(pmdp)) = 0) #define pmd_page_vaddr(pmd) (pmd_val(pmd) & ~PMD_MASKED_BITS) -#define pmd_page(pmd) virt_to_page(pmd_page_vaddr(pmd)) +extern struct page *pmd_page(pmd_t pmd); #define pud_set(pudp, pudval) (pud_val(*(pudp)) = (pudval)) #define pud_none(pud) (!pud_val(pud)) @@ -171,9 +164,21 @@ #define pud_present(pud) (pud_val(pud) != 0) #define pud_clear(pudp) (pud_val(*(pudp)) = 0) #define pud_page_vaddr(pud) (pud_val(pud) & ~PUD_MASKED_BITS) -#define pud_page(pud) virt_to_page(pud_page_vaddr(pud)) +extern struct page *pud_page(pud_t pud); + +static inline pte_t pud_pte(pud_t pud) +{ + return __pte(pud_val(pud)); +} + +static inline pud_t pte_pud(pte_t pte) +{ + return __pud(pte_val(pte)); +} +#define pud_write(pud) pte_write(pud_pte(pud)) #define pgd_set(pgdp, pudp) ({pgd_val(*(pgdp)) = (unsigned long)(pudp);}) +#define pgd_write(pgd) pte_write(pgd_pte(pgd)) /* * Find an entry in a page-table-directory. We combine the address region @@ -202,6 +207,7 @@ static inline unsigned long pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long clr, + unsigned long set, int huge) { #ifdef PTE_ATOMIC_UPDATES @@ -212,14 +218,15 @@ andi. %1,%0,%6\n\ bne- 1b \n\ andc %1,%0,%4 \n\ + or %1,%1,%7\n\ stdcx. %1,0,%3 \n\ bne- 1b" : "=&r" (old), "=&r" (tmp), "=m" (*ptep) - : "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY) + : "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY), "r" (set) : "cc" ); #else unsigned long old = pte_val(*ptep); - *ptep = __pte(old & ~clr); + *ptep = __pte((old & ~clr) | set); #endif /* huge pages use the old page table lock */ if (!huge) @@ -238,9 +245,9 @@ { unsigned long old; - if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) + if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) return 0; - old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0); + old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); return (old & _PAGE_ACCESSED) != 0; } #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG @@ -259,7 +266,7 @@ if ((pte_val(*ptep) & _PAGE_RW) == 0) return; - pte_update(mm, addr, ptep, _PAGE_RW, 0); + pte_update(mm, addr, ptep, _PAGE_RW, 0, 0); } static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, @@ -268,7 +275,7 @@ if ((pte_val(*ptep) & _PAGE_RW) == 0) return; - pte_update(mm, addr, ptep, _PAGE_RW, 1); + pte_update(mm, addr, ptep, _PAGE_RW, 0, 1); } /* @@ -291,14 +298,14 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0); + unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0); return __pte(old); } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t * ptep) { - pte_update(mm, addr, ptep, ~0UL, 0); + pte_update(mm, addr, ptep, ~0UL, 0, 0); } @@ -333,61 +340,287 @@ #define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0) #define pte_ERROR(e) \ - printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e)) + pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e)) #define pmd_ERROR(e) \ - printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e)) + pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e)) #define pgd_ERROR(e) \ - printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) + pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) /* Encode and de-code a swap entry */ -#define __swp_type(entry) (((entry).val >> 1) & 0x3f) -#define __swp_offset(entry) ((entry).val >> 8) -#define __swp_entry(type, offset) ((swp_entry_t){((type)<< 1)|((offset)<<8)}) -#define __pte_to_swp_entry(pte) ((swp_entry_t){pte_val(pte) >> PTE_RPN_SHIFT}) -#define __swp_entry_to_pte(x) ((pte_t) { (x).val << PTE_RPN_SHIFT }) -#define pte_to_pgoff(pte) (pte_val(pte) >> PTE_RPN_SHIFT) -#define pgoff_to_pte(off) ((pte_t) {((off) << PTE_RPN_SHIFT)|_PAGE_FILE}) -#define PTE_FILE_MAX_BITS (BITS_PER_LONG - PTE_RPN_SHIFT) +#define MAX_SWAPFILES_CHECK() do { \ + BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \ + /* \ + * Don't have overlapping bits with _PAGE_HPTEFLAGS \ + * We filter HPTEFLAGS on set_pte. \ + */ \ + BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \ + } while (0) +/* + * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT; + */ +#define SWP_TYPE_BITS 5 +#define __swp_type(x) (((x).val >> _PAGE_BIT_SWAP_TYPE) \ + & ((1UL << SWP_TYPE_BITS) - 1)) +#define __swp_offset(x) ((x).val >> PTE_RPN_SHIFT) +#define __swp_entry(type, offset) ((swp_entry_t) { \ + ((type) << _PAGE_BIT_SWAP_TYPE) \ + | ((offset) << PTE_RPN_SHIFT) }) + +#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) +#define __swp_entry_to_pte(x) __pte((x).val) void pgtable_cache_add(unsigned shift, void (*ctor)(void *)); void pgtable_cache_init(void); +#endif /* __ASSEMBLY__ */ + +/* + * THP pages can't be special. So use the _PAGE_SPECIAL + */ +#define _PAGE_SPLITTING _PAGE_SPECIAL + +/* + * We need to differentiate between explicit huge page and THP huge + * page, since THP huge page also need to track real subpage details + */ +#define _PAGE_THP_HUGE _PAGE_4K_PFN + +/* + * set of bits not changed in pmd_modify. + */ +#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | \ + _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPLITTING | \ + _PAGE_THP_HUGE) +#ifndef __ASSEMBLY__ /* - * find_linux_pte returns the address of a linux pte for a given - * effective address and directory. If not found, it returns zero. + * The linux hugepage PMD now include the pmd entries followed by the address + * to the stashed pgtable_t. The stashed pgtable_t contains the hpte bits. + * [ 1 bit secondary | 3 bit hidx | 1 bit valid | 000]. We use one byte per + * each HPTE entry. With 16MB hugepage and 64K HPTE we need 256 entries and + * with 4K HPTE we need 4096 entries. Both will fit in a 4K pgtable_t. + * + * The last three bits are intentionally left to zero. This memory location + * are also used as normal page PTE pointers. So if we have any pointers + * left around while we collapse a hugepage, we need to make sure + * _PAGE_PRESENT bit of that is zero when we look at them */ -static inline pte_t *find_linux_pte(pgd_t *pgdir, unsigned long ea) +static inline unsigned int hpte_valid(unsigned char *hpte_slot_array, int index) { - pgd_t *pg; - pud_t *pu; - pmd_t *pm; - pte_t *pt = NULL; - - pg = pgdir + pgd_index(ea); - if (!pgd_none(*pg)) { - pu = pud_offset(pg, ea); - if (!pud_none(*pu)) { - pm = pmd_offset(pu, ea); - if (pmd_present(*pm)) - pt = pte_offset_kernel(pm, ea); - } - } - return pt; -} - -#ifdef CONFIG_HUGETLB_PAGE -pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, - unsigned *shift); + return (hpte_slot_array[index] >> 3) & 0x1; +} + +static inline unsigned int hpte_hash_index(unsigned char *hpte_slot_array, + int index) +{ + return hpte_slot_array[index] >> 4; +} + +static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array, + unsigned int index, unsigned int hidx) +{ + hpte_slot_array[index] = hidx << 4 | 0x1 << 3; +} + +struct page *realmode_pfn_to_page(unsigned long pfn); + +static inline char *get_hpte_slot_array(pmd_t *pmdp) +{ + /* + * The hpte hindex is stored in the pgtable whose address is in the + * second half of the PMD + * + * Order this load with the test for pmd_trans_huge in the caller + */ + smp_rmb(); + return *(char **)(pmdp + PTRS_PER_PMD); + + +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, unsigned long old_pmd); +extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot); +extern pmd_t mk_pmd(struct page *page, pgprot_t pgprot); +extern pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot); +extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd); +extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd); +/* + * + * For core kernel code by design pmd_trans_huge is never run on any hugetlbfs + * page. The hugetlbfs page table walking and mangling paths are totally + * separated form the core VM paths and they're differentiated by + * VM_HUGETLB being set on vm_flags well before any pmd_trans_huge could run. + * + * pmd_trans_huge() is defined as false at build time if + * CONFIG_TRANSPARENT_HUGEPAGE=n to optimize away code blocks at build + * time in such case. + * + * For ppc64 we need to differntiate from explicit hugepages from THP, because + * for THP we also track the subpage details at the pmd level. We don't do + * that for explicit huge pages. + * + */ +static inline int pmd_trans_huge(pmd_t pmd) +{ + /* + * leaf pte for huge page, bottom two bits != 00 + */ + return (pmd_val(pmd) & 0x3) && (pmd_val(pmd) & _PAGE_THP_HUGE); +} + +static inline int pmd_trans_splitting(pmd_t pmd) +{ + if (pmd_trans_huge(pmd)) + return pmd_val(pmd) & _PAGE_SPLITTING; + return 0; +} + +extern int has_transparent_hugepage(void); #else -static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, - unsigned *shift) +static inline void hpte_do_hugepage_flush(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp, + unsigned long old_pmd) { - if (shift) - *shift = 0; - return find_linux_pte(pgdir, ea); + + WARN(1, "%s called with THP disabled\n", __func__); } -#endif /* !CONFIG_HUGETLB_PAGE */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -#endif /* __ASSEMBLY__ */ +static inline int pmd_large(pmd_t pmd) +{ + /* + * leaf pte for huge page, bottom two bits != 00 + */ + return ((pmd_val(pmd) & 0x3) != 0x0); +} + +static inline pte_t pmd_pte(pmd_t pmd) +{ + return __pte(pmd_val(pmd)); +} + +static inline pmd_t pte_pmd(pte_t pte) +{ + return __pmd(pte_val(pte)); +} + +static inline pte_t *pmdp_ptep(pmd_t *pmd) +{ + return (pte_t *)pmd; +} + +#define pmd_pfn(pmd) pte_pfn(pmd_pte(pmd)) +#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) +#define pmd_young(pmd) pte_young(pmd_pte(pmd)) +#define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) +#define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) +#define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) +#define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) +#define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) + +#define __HAVE_ARCH_PMD_WRITE +#define pmd_write(pmd) pte_write(pmd_pte(pmd)) + +static inline pmd_t pmd_mkhuge(pmd_t pmd) +{ + /* Do nothing, mk_pmd() does this part. */ + return pmd; +} + +static inline pmd_t pmd_mknotpresent(pmd_t pmd) +{ + pmd_val(pmd) &= ~_PAGE_PRESENT; + return pmd; +} + +static inline pmd_t pmd_mksplitting(pmd_t pmd) +{ + pmd_val(pmd) |= _PAGE_SPLITTING; + return pmd; +} + +#define __HAVE_ARCH_PMD_SAME +static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) +{ + return (((pmd_val(pmd_a) ^ pmd_val(pmd_b)) & ~_PAGE_HPTEFLAGS) == 0); +} + +#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS +extern int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty); + +extern unsigned long pmd_hugepage_update(struct mm_struct *mm, + unsigned long addr, + pmd_t *pmdp, + unsigned long clr, + unsigned long set); + +static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp) +{ + unsigned long old; + if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) + return 0; + old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0); + return ((old & _PAGE_ACCESSED) != 0); +} + +#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG +extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH +extern int pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); + +#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR +extern pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp); + +#define __HAVE_ARCH_PMDP_SET_WRPROTECT +static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + + if ((pmd_val(*pmdp) & _PAGE_RW) == 0) + return; + + pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW, 0); +} + +#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH +extern void pmdp_splitting_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); + +extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +#define pmdp_collapse_flush pmdp_collapse_flush + +#define __HAVE_ARCH_PGTABLE_DEPOSIT +extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable); +#define __HAVE_ARCH_PGTABLE_WITHDRAW +extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); + +#define __HAVE_ARCH_PMDP_INVALIDATE +extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp); + +#define pmd_move_must_withdraw pmd_move_must_withdraw +struct spinlock; +static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl) +{ + /* + * Archs like ppc64 use pgtable to store per pmd + * specific information. So when we switch the pmd, + * we should also withdraw and deposit the pgtable + */ + return true; +} +#endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_PGTABLE_PPC64_H_ */