diff options
Diffstat (limited to 'arch/powerpc/mm/hugetlbpage.c')
-rw-r--r-- | arch/powerpc/mm/hugetlbpage.c | 588 |
1 files changed, 63 insertions, 525 deletions
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 73d4873fc7f8..d3c1b749dcfc 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -19,18 +19,17 @@ #include <linux/swap.h> #include <linux/swapops.h> #include <linux/kmemleak.h> -#include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #include <asm/setup.h> #include <asm/hugetlb.h> #include <asm/pte-walk.h> +#include <asm/firmware.h> bool hugetlb_disabled = false; -#define hugepd_none(hpd) (hpd_val(hpd) == 0) - -#define PTE_T_ORDER (__builtin_ffs(sizeof(pte_t)) - __builtin_ffs(sizeof(void *))) +#define PTE_T_ORDER (__builtin_ffs(sizeof(pte_basic_t)) - \ + __builtin_ffs(sizeof(void *))) pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { @@ -41,153 +40,43 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long s return __find_linux_pte(mm->pgd, addr, NULL, NULL); } -static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, - unsigned long address, unsigned int pdshift, - unsigned int pshift, spinlock_t *ptl) +pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, unsigned long sz) { - struct kmem_cache *cachep; - pte_t *new; - int i; - int num_hugepd; - - if (pshift >= pdshift) { - cachep = PGT_CACHE(PTE_T_ORDER); - num_hugepd = 1 << (pshift - pdshift); - } else if (IS_ENABLED(CONFIG_PPC_8xx)) { - cachep = PGT_CACHE(PTE_INDEX_SIZE); - num_hugepd = 1; - } else { - cachep = PGT_CACHE(pdshift - pshift); - num_hugepd = 1; - } - - if (!cachep) { - WARN_ONCE(1, "No page table cache created for hugetlb tables"); - return -ENOMEM; - } - - new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); - - BUG_ON(pshift > HUGEPD_SHIFT_MASK); - BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; - if (!new) - return -ENOMEM; + addr &= ~(sz - 1); - /* - * Make sure other cpus find the hugepd set only after a - * properly initialized page table is visible to them. - * For more details look for comment in __pte_alloc(). - */ - smp_wmb(); + p4d = p4d_offset(pgd_offset(mm, addr), addr); + if (!mm_pud_folded(mm) && sz >= P4D_SIZE) + return (pte_t *)p4d; - spin_lock(ptl); - /* - * We have multiple higher-level entries that point to the same - * actual pte location. Fill in each as we go and backtrack on error. - * We need all of these so the DTLB pgtable walk code can find the - * right higher-level entry without knowing if it's a hugepage or not. - */ - for (i = 0; i < num_hugepd; i++, hpdp++) { - if (unlikely(!hugepd_none(*hpdp))) - break; - hugepd_populate(hpdp, new, pshift); - } - /* If we bailed from the for loop early, an error occurred, clean up */ - if (i < num_hugepd) { - for (i = i - 1 ; i >= 0; i--, hpdp--) - *hpdp = __hugepd(0); - kmem_cache_free(cachep, new); - } else { - kmemleak_ignore(new); - } - spin_unlock(ptl); - return 0; -} + pud = pud_alloc(mm, p4d, addr); + if (!pud) + return NULL; + if (!mm_pmd_folded(mm) && sz >= PUD_SIZE) + return (pte_t *)pud; -/* - * At this point we do the placement change only for BOOK3S 64. This would - * possibly work on other subarchs. - */ -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) -{ - pgd_t *pg; - pud_t *pu; - pmd_t *pm; - hugepd_t *hpdp = NULL; - unsigned pshift = __ffs(sz); - unsigned pdshift = PGDIR_SHIFT; - spinlock_t *ptl; + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return NULL; - addr &= ~(sz-1); - pg = pgd_offset(mm, addr); + if (sz >= PMD_SIZE) { + /* On 8xx, all hugepages are handled as contiguous PTEs */ + if (IS_ENABLED(CONFIG_PPC_8xx)) { + int i; -#ifdef CONFIG_PPC_BOOK3S_64 - if (pshift == PGDIR_SHIFT) - /* 16GB huge page */ - return (pte_t *) pg; - else if (pshift > PUD_SHIFT) { - /* - * We need to use hugepd table - */ - ptl = &mm->page_table_lock; - hpdp = (hugepd_t *)pg; - } else { - pdshift = PUD_SHIFT; - pu = pud_alloc(mm, pg, addr); - if (!pu) - return NULL; - if (pshift == PUD_SHIFT) - return (pte_t *)pu; - else if (pshift > PMD_SHIFT) { - ptl = pud_lockptr(mm, pu); - hpdp = (hugepd_t *)pu; - } else { - pdshift = PMD_SHIFT; - pm = pmd_alloc(mm, pu, addr); - if (!pm) - return NULL; - if (pshift == PMD_SHIFT) - /* 16MB hugepage */ - return (pte_t *)pm; - else { - ptl = pmd_lockptr(mm, pm); - hpdp = (hugepd_t *)pm; + for (i = 0; i < sz / PMD_SIZE; i++) { + if (!pte_alloc_huge(mm, pmd + i, addr)) + return NULL; } } + return (pte_t *)pmd; } -#else - if (pshift >= PGDIR_SHIFT) { - ptl = &mm->page_table_lock; - hpdp = (hugepd_t *)pg; - } else { - pdshift = PUD_SHIFT; - pu = pud_alloc(mm, pg, addr); - if (!pu) - return NULL; - if (pshift >= PUD_SHIFT) { - ptl = pud_lockptr(mm, pu); - hpdp = (hugepd_t *)pu; - } else { - pdshift = PMD_SHIFT; - pm = pmd_alloc(mm, pu, addr); - if (!pm) - return NULL; - ptl = pmd_lockptr(mm, pm); - hpdp = (hugepd_t *)pm; - } - } -#endif - if (!hpdp) - return NULL; - BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp)); - - if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, - pdshift, pshift, ptl)) - return NULL; - - return hugepte_offset(*hpdp, addr, pdshift); + return pte_alloc_huge(mm, pmd, addr); } #ifdef CONFIG_PPC_BOOK3S_64 @@ -215,344 +104,37 @@ void __init pseries_add_gpage(u64 addr, u64 page_size, unsigned long number_of_p } } -int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate) +static int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate) { struct huge_bootmem_page *m; if (nr_gpages == 0) return 0; m = phys_to_virt(gpage_freearray[--nr_gpages]); gpage_freearray[nr_gpages] = 0; - list_add(&m->list, &huge_boot_pages); + list_add(&m->list, &huge_boot_pages[0]); m->hstate = hstate; + m->flags = 0; return 1; } -#endif - -int __init alloc_bootmem_huge_page(struct hstate *h) +bool __init hugetlb_node_alloc_supported(void) { - -#ifdef CONFIG_PPC_BOOK3S_64 - if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled()) - return pseries_alloc_bootmem_huge_page(h); -#endif - return __alloc_bootmem_huge_page(h); -} - -#ifndef CONFIG_PPC_BOOK3S_64 -#define HUGEPD_FREELIST_SIZE \ - ((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t)) - -struct hugepd_freelist { - struct rcu_head rcu; - unsigned int index; - void *ptes[0]; -}; - -static DEFINE_PER_CPU(struct hugepd_freelist *, hugepd_freelist_cur); - -static void hugepd_free_rcu_callback(struct rcu_head *head) -{ - struct hugepd_freelist *batch = - container_of(head, struct hugepd_freelist, rcu); - unsigned int i; - - for (i = 0; i < batch->index; i++) - kmem_cache_free(PGT_CACHE(PTE_T_ORDER), batch->ptes[i]); - - free_page((unsigned long)batch); -} - -static void hugepd_free(struct mmu_gather *tlb, void *hugepte) -{ - struct hugepd_freelist **batchp; - - batchp = &get_cpu_var(hugepd_freelist_cur); - - if (atomic_read(&tlb->mm->mm_users) < 2 || - mm_is_thread_local(tlb->mm)) { - kmem_cache_free(PGT_CACHE(PTE_T_ORDER), hugepte); - put_cpu_var(hugepd_freelist_cur); - return; - } - - if (*batchp == NULL) { - *batchp = (struct hugepd_freelist *)__get_free_page(GFP_ATOMIC); - (*batchp)->index = 0; - } - - (*batchp)->ptes[(*batchp)->index++] = hugepte; - if ((*batchp)->index == HUGEPD_FREELIST_SIZE) { - call_rcu(&(*batchp)->rcu, hugepd_free_rcu_callback); - *batchp = NULL; - } - put_cpu_var(hugepd_freelist_cur); + return false; } -#else -static inline void hugepd_free(struct mmu_gather *tlb, void *hugepte) {} #endif -static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshift, - unsigned long start, unsigned long end, - unsigned long floor, unsigned long ceiling) -{ - pte_t *hugepte = hugepd_page(*hpdp); - int i; - - unsigned long pdmask = ~((1UL << pdshift) - 1); - unsigned int num_hugepd = 1; - unsigned int shift = hugepd_shift(*hpdp); - - /* Note: On fsl the hpdp may be the first of several */ - if (shift > pdshift) - num_hugepd = 1 << (shift - pdshift); - - start &= pdmask; - if (start < floor) - return; - if (ceiling) { - ceiling &= pdmask; - if (! ceiling) - return; - } - if (end - 1 > ceiling - 1) - return; - - for (i = 0; i < num_hugepd; i++, hpdp++) - *hpdp = __hugepd(0); - - if (shift >= pdshift) - hugepd_free(tlb, hugepte); - else if (IS_ENABLED(CONFIG_PPC_8xx)) - pgtable_free_tlb(tlb, hugepte, - get_hugepd_cache_index(PTE_INDEX_SIZE)); - else - pgtable_free_tlb(tlb, hugepte, - get_hugepd_cache_index(pdshift - shift)); -} - -static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud, - unsigned long addr, unsigned long end, - unsigned long floor, unsigned long ceiling) -{ - pmd_t *pmd; - unsigned long next; - unsigned long start; - - start = addr; - do { - unsigned long more; - - pmd = pmd_offset(pud, addr); - next = pmd_addr_end(addr, end); - if (!is_hugepd(__hugepd(pmd_val(*pmd)))) { - /* - * if it is not hugepd pointer, we should already find - * it cleared. - */ - WARN_ON(!pmd_none_or_clear_bad(pmd)); - continue; - } - /* - * Increment next by the size of the huge mapping since - * there may be more than one entry at this level for a - * single hugepage, but all of them point to - * the same kmem cache that holds the hugepte. - */ - more = addr + (1 << hugepd_shift(*(hugepd_t *)pmd)); - if (more > next) - next = more; - - free_hugepd_range(tlb, (hugepd_t *)pmd, PMD_SHIFT, - addr, next, floor, ceiling); - } while (addr = next, addr != end); - - start &= PUD_MASK; - if (start < floor) - return; - if (ceiling) { - ceiling &= PUD_MASK; - if (!ceiling) - return; - } - if (end - 1 > ceiling - 1) - return; - - pmd = pmd_offset(pud, start); - pud_clear(pud); - pmd_free_tlb(tlb, pmd, start); - mm_dec_nr_pmds(tlb->mm); -} -static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, - unsigned long addr, unsigned long end, - unsigned long floor, unsigned long ceiling) -{ - pud_t *pud; - unsigned long next; - unsigned long start; - - start = addr; - do { - pud = pud_offset(pgd, addr); - next = pud_addr_end(addr, end); - if (!is_hugepd(__hugepd(pud_val(*pud)))) { - if (pud_none_or_clear_bad(pud)) - continue; - hugetlb_free_pmd_range(tlb, pud, addr, next, floor, - ceiling); - } else { - unsigned long more; - /* - * Increment next by the size of the huge mapping since - * there may be more than one entry at this level for a - * single hugepage, but all of them point to - * the same kmem cache that holds the hugepte. - */ - more = addr + (1 << hugepd_shift(*(hugepd_t *)pud)); - if (more > next) - next = more; - - free_hugepd_range(tlb, (hugepd_t *)pud, PUD_SHIFT, - addr, next, floor, ceiling); - } - } while (addr = next, addr != end); - - start &= PGDIR_MASK; - if (start < floor) - return; - if (ceiling) { - ceiling &= PGDIR_MASK; - if (!ceiling) - return; - } - if (end - 1 > ceiling - 1) - return; - - pud = pud_offset(pgd, start); - pgd_clear(pgd); - pud_free_tlb(tlb, pud, start); - mm_dec_nr_puds(tlb->mm); -} - -/* - * This function frees user-level page tables of a process. - */ -void hugetlb_free_pgd_range(struct mmu_gather *tlb, - unsigned long addr, unsigned long end, - unsigned long floor, unsigned long ceiling) +int __init alloc_bootmem_huge_page(struct hstate *h, int nid) { - pgd_t *pgd; - unsigned long next; - /* - * Because there are a number of different possible pagetable - * layouts for hugepage ranges, we limit knowledge of how - * things should be laid out to the allocation path - * (huge_pte_alloc(), above). Everything else works out the - * structure as it goes from information in the hugepd - * pointers. That means that we can't here use the - * optimization used in the normal page free_pgd_range(), of - * checking whether we're actually covering a large enough - * range to have to do anything at the top level of the walk - * instead of at the bottom. - * - * To make sense of this, you should probably go read the big - * block comment at the top of the normal free_pgd_range(), - * too. - */ - - do { - next = pgd_addr_end(addr, end); - pgd = pgd_offset(tlb->mm, addr); - if (!is_hugepd(__hugepd(pgd_val(*pgd)))) { - if (pgd_none_or_clear_bad(pgd)) - continue; - hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling); - } else { - unsigned long more; - /* - * Increment next by the size of the huge mapping since - * there may be more than one entry at the pgd level - * for a single hugepage, but all of them point to the - * same kmem cache that holds the hugepte. - */ - more = addr + (1 << hugepd_shift(*(hugepd_t *)pgd)); - if (more > next) - next = more; - - free_hugepd_range(tlb, (hugepd_t *)pgd, PGDIR_SHIFT, - addr, next, floor, ceiling); - } - } while (addr = next, addr != end); -} - -struct page *follow_huge_pd(struct vm_area_struct *vma, - unsigned long address, hugepd_t hpd, - int flags, int pdshift) -{ - pte_t *ptep; - spinlock_t *ptl; - struct page *page = NULL; - unsigned long mask; - int shift = hugepd_shift(hpd); - struct mm_struct *mm = vma->vm_mm; - -retry: - /* - * hugepage directory entries are protected by mm->page_table_lock - * Use this instead of huge_pte_lockptr - */ - ptl = &mm->page_table_lock; - spin_lock(ptl); - - ptep = hugepte_offset(hpd, address, pdshift); - if (pte_present(*ptep)) { - mask = (1UL << shift) - 1; - page = pte_page(*ptep); - page += ((address & mask) >> PAGE_SHIFT); - if (flags & FOLL_GET) - get_page(page); - } else { - if (is_hugetlb_entry_migration(*ptep)) { - spin_unlock(ptl); - __migration_entry_wait(mm, ptep, ptl); - goto retry; - } - } - spin_unlock(ptl); - return page; -} - -#ifdef CONFIG_PPC_MM_SLICES -unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags) -{ - struct hstate *hstate = hstate_file(file); - int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate)); - -#ifdef CONFIG_PPC_RADIX_MMU - if (radix_enabled()) - return radix__hugetlb_get_unmapped_area(file, addr, len, - pgoff, flags); -#endif - return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1); -} +#ifdef CONFIG_PPC_BOOK3S_64 + if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled()) + return pseries_alloc_bootmem_huge_page(h); #endif - -unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) -{ - /* With radix we don't use slice, so derive it from vma*/ - if (IS_ENABLED(CONFIG_PPC_MM_SLICES) && !radix_enabled()) { - unsigned int psize = get_slice_psize(vma->vm_mm, vma->vm_start); - - return 1UL << mmu_psize_to_shift(psize); - } - return vma_kernel_pagesize(vma); + return __alloc_bootmem_huge_page(h, nid); } -static int __init add_huge_page_size(unsigned long long size) +bool __init arch_hugetlb_valid_size(unsigned long size) { int shift = __ffs(size); int mmu_psize; @@ -560,37 +142,27 @@ static int __init add_huge_page_size(unsigned long long size) /* Check that it is a page size supported by the hardware and * that it fits within pagetable and slice limits. */ if (size <= PAGE_SIZE || !is_power_of_2(size)) - return -EINVAL; + return false; mmu_psize = check_and_get_huge_psize(shift); if (mmu_psize < 0) - return -EINVAL; + return false; BUG_ON(mmu_psize_defs[mmu_psize].shift != shift); - /* Return if huge page size has already been setup */ - if (size_to_hstate(size)) - return 0; - - hugetlb_add_hstate(shift - PAGE_SHIFT); - - return 0; + return true; } -static int __init hugepage_setup_sz(char *str) +static int __init add_huge_page_size(unsigned long long size) { - unsigned long long size; - - size = memparse(str, &str); + int shift = __ffs(size); - if (add_huge_page_size(size) != 0) { - hugetlb_bad_size(); - pr_err("Invalid huge page size specified(%llu)\n", size); - } + if (!arch_hugetlb_valid_size((unsigned long)size)) + return -EINVAL; - return 1; + hugetlb_add_hstate(shift - PAGE_SHIFT); + return 0; } -__setup("hugepagesz=", hugepage_setup_sz); static int __init hugetlbpage_init(void) { @@ -608,51 +180,19 @@ static int __init hugetlbpage_init(void) for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { unsigned shift; - unsigned pdshift; if (!mmu_psize_defs[psize].shift) continue; shift = mmu_psize_to_shift(psize); -#ifdef CONFIG_PPC_BOOK3S_64 - if (shift > PGDIR_SHIFT) - continue; - else if (shift > PUD_SHIFT) - pdshift = PGDIR_SHIFT; - else if (shift > PMD_SHIFT) - pdshift = PUD_SHIFT; - else - pdshift = PMD_SHIFT; -#else - if (shift < PUD_SHIFT) - pdshift = PMD_SHIFT; - else if (shift < PGDIR_SHIFT) - pdshift = PUD_SHIFT; - else - pdshift = PGDIR_SHIFT; -#endif - if (add_huge_page_size(1ULL << shift) < 0) continue; - /* - * if we have pdshift and shift value same, we don't - * use pgt cache for hugepd. - */ - if (pdshift > shift && IS_ENABLED(CONFIG_PPC_8xx)) - pgtable_cache_add(PTE_INDEX_SIZE); - else if (pdshift > shift) - pgtable_cache_add(pdshift - shift); - else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || IS_ENABLED(CONFIG_PPC_8xx)) - pgtable_cache_add(PTE_T_ORDER); configured = true; } - if (configured) { - if (IS_ENABLED(CONFIG_HUGETLB_PAGE_SIZE_VARIABLE)) - hugetlbpage_init_default(); - } else + if (!configured) pr_info("Failed to initialize. Disabling HugeTLB"); return 0; @@ -660,20 +200,18 @@ static int __init hugetlbpage_init(void) arch_initcall(hugetlbpage_init); -void flush_dcache_icache_hugepage(struct page *page) +void __init gigantic_hugetlb_cma_reserve(void) { - int i; - void *start; - - BUG_ON(!PageCompound(page)); - - for (i = 0; i < compound_nr(page); i++) { - if (!PageHighMem(page)) { - __flush_dcache_icache(page_address(page+i)); - } else { - start = kmap_atomic(page+i); - __flush_dcache_icache(start); - kunmap_atomic(start); - } - } + unsigned long order = 0; + + if (radix_enabled()) + order = PUD_SHIFT - PAGE_SHIFT; + else if (!firmware_has_feature(FW_FEATURE_LPAR) && mmu_psize_defs[MMU_PAGE_16G].shift) + /* + * For pseries we do use ibm,expected#pages for reserving 16G pages. + */ + order = mmu_psize_to_shift(MMU_PAGE_16G) - PAGE_SHIFT; + + if (order) + hugetlb_cma_reserve(order); } |