diff options
Diffstat (limited to 'arch/powerpc/mm/hugetlbpage.c')
| -rw-r--r-- | arch/powerpc/mm/hugetlbpage.c | 219 |
1 files changed, 38 insertions, 181 deletions
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index e1bf5ca397fe..1571a498a33f 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -24,6 +24,8 @@ #include <asm/tlb.h> #include <asm/setup.h> #include <asm/hugetlb.h> +#include <asm/pte-walk.h> + #ifdef CONFIG_HUGETLB_PAGE @@ -36,32 +38,15 @@ unsigned int HPAGE_SHIFT; EXPORT_SYMBOL(HPAGE_SHIFT); -/* - * Tracks gpages after the device tree is scanned and before the - * huge_boot_pages list is ready. On non-Freescale implementations, this is - * just used to track 16G pages and so is a single array. FSL-based - * implementations may have more than one gpage size, so we need multiple - * arrays - */ -#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx) -#define MAX_NUMBER_GPAGES 128 -struct psize_gpages { - u64 gpage_list[MAX_NUMBER_GPAGES]; - unsigned int nr_gpages; -}; -static struct psize_gpages gpage_freearray[MMU_PAGE_COUNT]; -#else -#define MAX_NUMBER_GPAGES 1024 -static u64 gpage_freearray[MAX_NUMBER_GPAGES]; -static unsigned nr_gpages; -#endif - #define hugepd_none(hpd) (hpd_val(hpd) == 0) pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { - /* Only called for hugetlbfs pages, hence can ignore THP */ - return __find_linux_pte_or_hugepte(mm->pgd, addr, NULL, NULL); + /* + * Only called for hugetlbfs pages, hence can ignore THP and the + * irq disabled walk. + */ + return __find_linux_pte(mm->pgd, addr, NULL, NULL); } static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, @@ -210,145 +195,20 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz return hugepte_offset(*hpdp, addr, pdshift); } -#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx) -/* Build list of addresses of gigantic pages. This function is used in early - * boot before the buddy allocator is setup. - */ -void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages) -{ - unsigned int idx = shift_to_mmu_psize(__ffs(page_size)); - int i; - - if (addr == 0) - return; - - gpage_freearray[idx].nr_gpages = number_of_pages; - - for (i = 0; i < number_of_pages; i++) { - gpage_freearray[idx].gpage_list[i] = addr; - addr += page_size; - } -} - -/* - * Moves the gigantic page addresses from the temporary list to the - * huge_boot_pages list. - */ -int alloc_bootmem_huge_page(struct hstate *hstate) -{ - struct huge_bootmem_page *m; - int idx = shift_to_mmu_psize(huge_page_shift(hstate)); - int nr_gpages = gpage_freearray[idx].nr_gpages; - - if (nr_gpages == 0) - return 0; - -#ifdef CONFIG_HIGHMEM - /* - * If gpages can be in highmem we can't use the trick of storing the - * data structure in the page; allocate space for this - */ - m = memblock_virt_alloc(sizeof(struct huge_bootmem_page), 0); - m->phys = gpage_freearray[idx].gpage_list[--nr_gpages]; -#else - m = phys_to_virt(gpage_freearray[idx].gpage_list[--nr_gpages]); -#endif - - list_add(&m->list, &huge_boot_pages); - gpage_freearray[idx].nr_gpages = nr_gpages; - gpage_freearray[idx].gpage_list[nr_gpages] = 0; - m->hstate = hstate; - - return 1; -} +#ifdef CONFIG_PPC_BOOK3S_64 /* - * Scan the command line hugepagesz= options for gigantic pages; store those in - * a list that we use to allocate the memory once all options are parsed. + * Tracks gpages after the device tree is scanned and before the + * huge_boot_pages list is ready on pseries. */ - -unsigned long gpage_npages[MMU_PAGE_COUNT]; - -static int __init do_gpage_early_setup(char *param, char *val, - const char *unused, void *arg) -{ - static phys_addr_t size; - unsigned long npages; - - /* - * The hugepagesz and hugepages cmdline options are interleaved. We - * use the size variable to keep track of whether or not this was done - * properly and skip over instances where it is incorrect. Other - * command-line parsing code will issue warnings, so we don't need to. - * - */ - if ((strcmp(param, "default_hugepagesz") == 0) || - (strcmp(param, "hugepagesz") == 0)) { - size = memparse(val, NULL); - } else if (strcmp(param, "hugepages") == 0) { - if (size != 0) { - if (sscanf(val, "%lu", &npages) <= 0) - npages = 0; - if (npages > MAX_NUMBER_GPAGES) { - pr_warn("MMU: %lu pages requested for page " -#ifdef CONFIG_PHYS_ADDR_T_64BIT - "size %llu KB, limiting to " -#else - "size %u KB, limiting to " -#endif - __stringify(MAX_NUMBER_GPAGES) "\n", - npages, size / 1024); - npages = MAX_NUMBER_GPAGES; - } - gpage_npages[shift_to_mmu_psize(__ffs(size))] = npages; - size = 0; - } - } - return 0; -} - +#define MAX_NUMBER_GPAGES 1024 +__initdata static u64 gpage_freearray[MAX_NUMBER_GPAGES]; +__initdata static unsigned nr_gpages; /* - * This function allocates physical space for pages that are larger than the - * buddy allocator can handle. We want to allocate these in highmem because - * the amount of lowmem is limited. This means that this function MUST be - * called before lowmem_end_addr is set up in MMU_init() in order for the lmb - * allocate to grab highmem. - */ -void __init reserve_hugetlb_gpages(void) -{ - static __initdata char cmdline[COMMAND_LINE_SIZE]; - phys_addr_t size, base; - int i; - - strlcpy(cmdline, boot_command_line, COMMAND_LINE_SIZE); - parse_args("hugetlb gpages", cmdline, NULL, 0, 0, 0, - NULL, &do_gpage_early_setup); - - /* - * Walk gpage list in reverse, allocating larger page sizes first. - * Skip over unsupported sizes, or sizes that have 0 gpages allocated. - * When we reach the point in the list where pages are no longer - * considered gpages, we're done. - */ - for (i = MMU_PAGE_COUNT-1; i >= 0; i--) { - if (mmu_psize_defs[i].shift == 0 || gpage_npages[i] == 0) - continue; - else if (mmu_psize_to_shift(i) < (MAX_ORDER + PAGE_SHIFT)) - break; - - size = (phys_addr_t)(1ULL << mmu_psize_to_shift(i)); - base = memblock_alloc_base(size * gpage_npages[i], size, - MEMBLOCK_ALLOC_ANYWHERE); - add_gpage(base, size, gpage_npages[i]); - } -} - -#else /* !PPC_FSL_BOOK3E */ - -/* Build list of addresses of gigantic pages. This function is used in early + * Build list of addresses of gigantic pages. This function is used in early * boot before the buddy allocator is setup. */ -void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages) +void __init pseries_add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages) { if (!addr) return; @@ -360,10 +220,7 @@ void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages) } } -/* Moves the gigantic page addresses from the temporary list to the - * huge_boot_pages list. - */ -int alloc_bootmem_huge_page(struct hstate *hstate) +int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate) { struct huge_bootmem_page *m; if (nr_gpages == 0) @@ -376,6 +233,17 @@ int alloc_bootmem_huge_page(struct hstate *hstate) } #endif + +int __init alloc_bootmem_huge_page(struct hstate *h) +{ + +#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); +} + #if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx) #define HUGEPD_FREELIST_SIZE \ ((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t)) @@ -407,8 +275,7 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) batchp = &get_cpu_var(hugepd_freelist_cur); if (atomic_read(&tlb->mm->mm_users) < 2 || - cpumask_equal(mm_cpumask(tlb->mm), - cpumask_of(smp_processor_id()))) { + mm_is_thread_local(tlb->mm)) { kmem_cache_free(hugepte_cache, hugepte); put_cpu_var(hugepd_freelist_cur); return; @@ -886,9 +753,8 @@ void flush_dcache_icache_hugepage(struct page *page) * This function need to be called with interrupts disabled. We use this variant * when we have MSR[EE] = 0 but the paca->soft_enabled = 1 */ - -pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, - bool *is_thp, unsigned *shift) +pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea, + bool *is_thp, unsigned *hpage_shift) { pgd_t pgd, *pgdp; pud_t pud, *pudp; @@ -897,8 +763,8 @@ pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, hugepd_t *hpdp = NULL; unsigned pdshift = PGDIR_SHIFT; - if (shift) - *shift = 0; + if (hpage_shift) + *hpage_shift = 0; if (is_thp) *is_thp = false; @@ -968,16 +834,15 @@ pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, ret_pte = hugepte_offset(*hpdp, ea, pdshift); pdshift = hugepd_shift(*hpdp); out: - if (shift) - *shift = pdshift; + if (hpage_shift) + *hpage_shift = pdshift; return ret_pte; } -EXPORT_SYMBOL_GPL(__find_linux_pte_or_hugepte); +EXPORT_SYMBOL_GPL(__find_linux_pte); int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { - unsigned long mask; unsigned long pte_end; struct page *head, *page; pte_t pte; @@ -988,18 +853,10 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, end = pte_end; pte = READ_ONCE(*ptep); - mask = _PAGE_PRESENT | _PAGE_READ; - /* - * On some CPUs like the 8xx, _PAGE_RW hence _PAGE_WRITE is defined - * as 0 and _PAGE_RO has to be set when a page is not writable - */ - if (write) - mask |= _PAGE_WRITE; - else - mask |= _PAGE_RO; - - if ((pte_val(pte) & mask) != mask) + if (!pte_present(pte) || !pte_read(pte)) + return 0; + if (write && !pte_write(pte)) return 0; /* hugepages are never "special" */ |