From: Nitin Gupta Date: Fri, 5 May 2017 01:28:46 +0000 (-0700) Subject: sparc64: Add 16GB hugepage support X-Git-Tag: v4.1.12-104.0.20170618_1145~22 X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=ab1b2a71c145d1b63ff1f2cca59f6f5b674f1d46;p=users%2Fjedix%2Flinux-maple.git sparc64: Add 16GB hugepage support Adds support for 16GB hugepage size. To use this page size use kernel parameters as: default_hugepagesz=16G hugepagesz=16G hugepages=10 Testing: Tested with the stream benchmark which allocates 48G of arrays backed by 16G hugepages and does RW operation on them in parallel. Orabug: 25858371 Signed-off-by: Nitin Gupta Signed-off-by: Allen Pais --- diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h index e04f805f208c9..e45aba4254f04 100644 --- a/arch/sparc/include/asm/page_64.h +++ b/arch/sparc/include/asm/page_64.h @@ -17,6 +17,7 @@ #define HPAGE_SHIFT 23 #define REAL_HPAGE_SHIFT 22 +#define HPAGE_16GB_SHIFT 34 #define HPAGE_2GB_SHIFT 31 #define HPAGE_256MB_SHIFT 28 #define HPAGE_64K_SHIFT 16 @@ -28,7 +29,7 @@ #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA #define REAL_HPAGE_PER_HPAGE (_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT)) -#define HUGE_MAX_HSTATE 4 +#define HUGE_MAX_HSTATE 5 #endif #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 0377f573df696..2adb60264bce8 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -431,6 +431,11 @@ static inline bool is_hugetlb_pmd(pmd_t pmd) return !!(pmd_val(pmd) & _PAGE_PMD_HUGE); } +static inline bool is_hugetlb_pud(pud_t pud) +{ + return !!(pud_val(pud) & _PAGE_PUD_HUGE); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline pmd_t pmd_mkhuge(pmd_t pmd) { @@ -716,6 +721,8 @@ static inline unsigned long pmd_write(pmd_t pmd) return pte_write(pte); } +#define pud_write(pud) pte_write(__pte(pud_val(pud))) + #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline unsigned long pmd_dirty(pmd_t pmd) { @@ -866,10 +873,19 @@ static inline unsigned long __pmd_page(pmd_t pmd) return ((unsigned long) __va(pfn << PAGE_SHIFT)); } +static inline unsigned long pud_page_vaddr(pud_t pud) +{ + pte_t pte = __pte(pud_val(pud)); + unsigned long pfn; + + pfn = pte_pfn(pte); + + return ((unsigned long) __va(pfn << PAGE_SHIFT)); +} + #define pmd_page(pmd) virt_to_page((void *)__pmd_page(pmd)) #define pmd_clear(pmdp) (pmd_val(*(pmdp)) = 0UL) -#define pud_page_vaddr(pud) \ - ((unsigned long) __va(pud_val(pud))) + #define pud_page(pud) virt_to_page((void *)pud_page_vaddr(pud)) #define pud_present(pud) (pud_val(pud) != 0U) #define pud_clear(pudp) (pud_val(*(pudp)) = 0UL) diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h index d2e79744d9018..cc79862cacf90 100644 --- a/arch/sparc/include/asm/tsb.h +++ b/arch/sparc/include/asm/tsb.h @@ -200,6 +200,35 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; nop; \ 699: + /* PUD has been loaded into REG1, interpret the value, seeing + * if it is a HUGE PUD or a normal one. If it is not valid + * then jump to FAIL_LABEL. If it is a HUGE PUD, and it + * translates to a valid PTE, branch to PTE_LABEL. + * + * We have to propagate bits [32:22] from the virtual address + * to resolve at 4M granularity. + */ +#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) +#define USER_PGTABLE_CHECK_PUD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, PTE_LABEL) \ + brz,pn REG1, FAIL_LABEL; \ + sethi %uhi(_PAGE_PUD_HUGE), REG2; \ + sllx REG2, 32, REG2; \ + andcc REG1, REG2, %g0; \ + be,pt %xcc, 700f; \ + sethi %hi(0x1ffc0000), REG2; \ + sllx REG2, 1, REG2; \ + brgez,pn REG1, FAIL_LABEL; \ + andn REG1, REG2, REG1; \ + and VADDR, REG2, REG2; \ + brlz,pt REG1, PTE_LABEL; \ + or REG1, REG2, REG1; \ +700: +#else +#define USER_PGTABLE_CHECK_PUD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, PTE_LABEL) \ + brz,pn REG1, FAIL_LABEL; \ + nop; +#endif + /* PMD has been loaded into REG1, interpret the value, seeing * if it is a HUGE PMD or a normal one. If it is not valid * then jump to FAIL_LABEL. If it is a HUGE PMD, and it @@ -252,6 +281,7 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; srlx REG2, 64 - PAGE_SHIFT, REG2; \ andn REG2, 0x7, REG2; \ ldxa [REG1 + REG2] ASI_PHYS_USE_EC, REG1; \ + USER_PGTABLE_CHECK_PUD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, 800f) \ brz,pn REG1, FAIL_LABEL; \ sllx VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \ srlx REG2, 64 - PAGE_SHIFT, REG2; \ diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S index 07c0df9249603..5f42ac099fcb7 100644 --- a/arch/sparc/kernel/tsb.S +++ b/arch/sparc/kernel/tsb.S @@ -117,7 +117,7 @@ tsb_miss_page_table_walk_sun4v_fastpath: /* Valid PTE is now in %g5. */ #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) - sethi %uhi(_PAGE_PMD_HUGE), %g7 + sethi %uhi(_PAGE_PMD_HUGE | _PAGE_PUD_HUGE), %g7 sllx %g7, 32, %g7 andcc %g5, %g7, %g0 diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c index 9c962f905a9ed..408fcbbe7fec1 100644 --- a/arch/sparc/mm/gup.c +++ b/arch/sparc/mm/gup.c @@ -83,6 +83,8 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, refs = 0; head = pmd_page(pmd); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + if (PageTail(head)) + head = compound_head(head); tail = page; do { VM_BUG_ON(compound_head(page) != head); @@ -116,6 +118,57 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, return 1; } +static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr, + unsigned long end, int write, struct page **pages, + int *nr) +{ + struct page *head, *page, *tail; + int refs; + + if (!(pud_val(pud) & _PAGE_VALID)) + return 0; + + if (write && !pud_write(pud)) + return 0; + + refs = 0; + head = pud_page(pud); + page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + if (PageTail(head)) + head = compound_head(head); + tail = page; + do { + VM_BUG_ON(compound_head(page) != head); + pages[*nr] = page; + (*nr)++; + page++; + refs++; + } while (addr += PAGE_SIZE, addr != end); + + if (!page_cache_add_speculative(head, refs)) { + *nr -= refs; + return 0; + } + + if (unlikely(pud_val(pud) != pud_val(*pudp))) { + *nr -= refs; + while (refs--) + put_page(head); + return 0; + } + + /* Any tail page need their mapcount reference taken before we + * return. + */ + while (refs--) { + if (PageTail(tail)) + get_huge_page_tail(tail); + tail++; + } + + return 1; +} + static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { @@ -154,7 +207,11 @@ static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, next = pud_addr_end(addr, end); if (pud_none(pud)) return 0; - if (!gup_pmd_range(pud, addr, next, write, pages, nr)) + if (unlikely(pud_large(pud))) { + if (!gup_huge_pud(pudp, pud, addr, next, + write, pages, nr)) + return 0; + } else if (!gup_pmd_range(pud, addr, next, write, pages, nr)) return 0; } while (pudp++, addr = next, addr != end); diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index 3eab5ac44b2fa..a8e04c70c07d9 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -147,6 +147,10 @@ static pte_t sun4v_hugepage_shift_to_tte(pte_t entry, unsigned int shift) pte_val(entry) = pte_val(entry) & ~_PAGE_SZALL_4V; switch (shift) { + case HPAGE_16GB_SHIFT: + hugepage_size = _PAGE_SZ16GB_4V; + pte_val(entry) |= _PAGE_PUD_HUGE; + break; case HPAGE_2GB_SHIFT: hugepage_size = _PAGE_SZ2GB_4V; pte_val(entry) |= _PAGE_PMD_HUGE; @@ -199,6 +203,9 @@ static unsigned int sun4v_huge_tte_to_shift(pte_t entry) unsigned int shift; switch (tte_szbits) { + case _PAGE_SZ16GB_4V: + shift = HPAGE_16GB_SHIFT; + break; case _PAGE_SZ2GB_4V: shift = HPAGE_2GB_SHIFT; break; @@ -272,25 +279,22 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, p4d_t *p4d; pud_t *pud; pmd_t *pmd; - pte_t *pte = NULL; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); - if (p4d) { - pud = pud_alloc(mm, p4d, addr); - if (pud) { - pmd = pmd_alloc(mm, pud, addr); - if (!pmd) - return NULL; - - if (sz >= PMD_SIZE) - pte = (pte_t *)pmd; - else - pte = pte_alloc_map(mm, NULL, pmd, addr); - } - } - - return pte; + if (!p4d) + return NULL; + pud = pud_alloc(mm, p4d, addr); + if (!pud) + return NULL; + if (sz >= PUD_SIZE) + return (pte_t *)pud; + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return NULL; + if (sz >= PMD_SIZE) + return (pte_t *)pmd; + return pte_alloc_map(mm, NULL, pmd, addr); } pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) @@ -299,37 +303,43 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) p4d_t *p4d; pud_t *pud; pmd_t *pmd; - pte_t *pte = NULL; pgd = pgd_offset(mm, addr); - if (!pgd_none(*pgd)) { - p4d = p4d_offset(pgd, addr); - if (!p4d_none(*p4d)) { - pud = pud_offset(p4d, addr); - if (!pud_none(*pud)) { - pmd = pmd_offset(pud, addr); - if (!pmd_none(*pmd)) { - if (is_hugetlb_pmd(*pmd)) - pte = (pte_t *)pmd; - else - pte = pte_offset_map(pmd, addr); - } - } - } - } - - return pte; + if (pgd_none(*pgd)) + return NULL; + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) + return NULL; + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) + return NULL; + if (is_hugetlb_pud(*pud)) + return (pte_t *)pud; + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return NULL; + if (is_hugetlb_pmd(*pmd)) + return (pte_t *)pmd; + return pte_offset_map(pmd, addr); } void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t entry) { - unsigned int i, nptes, orig_shift, shift; - unsigned long size; + unsigned int nptes, orig_shift, shift; + unsigned long i, size; pte_t orig; size = huge_tte_to_size(entry); - shift = size >= HPAGE_SIZE ? PMD_SHIFT : PAGE_SHIFT; + + shift = PAGE_SHIFT; + if (size >= PUD_SIZE) + shift = PUD_SHIFT; + else if (size >= PMD_SIZE) + shift = PMD_SHIFT; + else + shift = PAGE_SHIFT; + nptes = size >> shift; if (!pte_present(*ptep) && pte_present(entry)) @@ -352,19 +362,23 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - unsigned int i, nptes, hugepage_shift; + unsigned int i, nptes, orig_shift, shift; unsigned long size; pte_t entry; entry = *ptep; size = huge_tte_to_size(entry); - if (size >= HPAGE_SIZE) - nptes = size >> PMD_SHIFT; + + shift = PAGE_SHIFT; + if (size >= PUD_SIZE) + shift = PUD_SHIFT; + else if (size >= PMD_SIZE) + shift = PMD_SHIFT; else - nptes = size >> PAGE_SHIFT; + shift = PAGE_SHIFT; - hugepage_shift = pte_none(entry) ? PAGE_SHIFT : - huge_tte_to_shift(entry); + nptes = size >> shift; + orig_shift = pte_none(entry) ? PAGE_SHIFT : huge_tte_to_shift(entry); if (pte_present(entry)) mm->context.hugetlb_pte_count -= nptes; @@ -373,11 +387,11 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, for (i = 0; i < nptes; i++) ptep[i] = __pte(0UL); - maybe_tlb_batch_add(mm, addr, ptep, entry, 0, hugepage_shift); + maybe_tlb_batch_add(mm, addr, ptep, entry, 0, orig_shift); /* An HPAGE_SIZE'ed page is composed of two REAL_HPAGE_SIZE'ed pages */ if (size == HPAGE_SIZE) maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, entry, 0, - hugepage_shift); + orig_shift); return entry; } @@ -390,7 +404,8 @@ int pmd_huge(pmd_t pmd) int pud_huge(pud_t pud) { - return 0; + return !pud_none(pud) && + (pud_val(pud) & (_PAGE_VALID|_PAGE_PUD_HUGE)) != _PAGE_VALID; } static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, @@ -454,8 +469,11 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; - hugetlb_free_pmd_range(tlb, pud, addr, next, floor, - ceiling); + if (is_hugetlb_pud(*pud)) + pud_clear(pud); + else + hugetlb_free_pmd_range(tlb, pud, addr, next, floor, + ceiling); } while (pud++, addr = next, addr != end); start &= P4D_MASK; diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index e3447a02c49aa..1509da6d3ff36 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -453,6 +453,10 @@ static int __init setup_hugepagesz(char *string) hugepage_shift = ilog2(hugepage_size); switch (hugepage_shift) { + case HPAGE_16GB_SHIFT: + hv_pgsz_mask = HV_PGSZ_MASK_16GB; + hv_pgsz_idx = HV_PGSZ_IDX_16GB; + break; case HPAGE_2GB_SHIFT: hv_pgsz_mask = HV_PGSZ_MASK_2GB; hv_pgsz_idx = HV_PGSZ_IDX_2GB; @@ -492,6 +496,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t * { struct mm_struct *mm; unsigned long flags; + bool is_huge_tsb; pte_t pte = *ptep; if (tlb_type != hypervisor) { @@ -509,15 +514,37 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t * spin_lock_irqsave(&mm->context.lock, flags); + is_huge_tsb = false; #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) - if ((mm->context.hugetlb_pte_count || mm->context.thp_pte_count) && - is_hugetlb_pmd(__pmd(pte_val(pte)))) { - /* We are fabricating 8MB pages using 4MB real hw pages. */ - pte_val(pte) |= (address & (1UL << REAL_HPAGE_SHIFT)); - __update_mmu_tsb_insert(mm, MM_TSB_HUGE, REAL_HPAGE_SHIFT, - address, pte_val(pte)); - } else + if (mm->context.hugetlb_pte_count || mm->context.thp_pte_count) { + unsigned long hugepage_size = PAGE_SIZE; + + if (is_vm_hugetlb_page(vma)) + hugepage_size = huge_page_size(hstate_vma(vma)); + + if (hugepage_size >= PUD_SIZE) { + unsigned long mask = 0x1ffc00000UL; + + /* Transfer bits [32:22] from address to resolve + * at 4M granularity. + */ + pte_val(pte) &= ~mask; + pte_val(pte) |= (address & mask); + } else if (hugepage_size >= PMD_SIZE) { + /* We are fabricating 8MB pages using 4MB + * real hw pages. + */ + pte_val(pte) |= (address & (1UL << REAL_HPAGE_SHIFT)); + } + + if (hugepage_size >= PMD_SIZE) { + __update_mmu_tsb_insert(mm, MM_TSB_HUGE, + REAL_HPAGE_SHIFT, address, pte_val(pte)); + is_huge_tsb = true; + } + } #endif + if (!is_huge_tsb) __update_mmu_tsb_insert(mm, MM_TSB_BASE, PAGE_SHIFT, address, pte_val(pte));