diff options
Diffstat (limited to 'arch/sparc/mm/init_64.c')
-rw-r--r-- | arch/sparc/mm/init_64.c | 256 |
1 files changed, 146 insertions, 110 deletions
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index e6d91819da92..1ca9054d9b97 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -27,11 +27,11 @@ #include <linux/percpu.h> #include <linux/mmzone.h> #include <linux/gfp.h> +#include <linux/bootmem_info.h> #include <asm/head.h> #include <asm/page.h> #include <asm/pgalloc.h> -#include <asm/pgtable.h> #include <asm/oplib.h> #include <asm/iommu.h> #include <asm/io.h> @@ -195,21 +195,26 @@ atomic_t dcpage_flushes_xcall = ATOMIC_INIT(0); #endif #endif -inline void flush_dcache_page_impl(struct page *page) +inline void flush_dcache_folio_impl(struct folio *folio) { + unsigned int i, nr = folio_nr_pages(folio); + BUG_ON(tlb_type == hypervisor); #ifdef CONFIG_DEBUG_DCFLUSH atomic_inc(&dcpage_flushes); #endif #ifdef DCACHE_ALIASING_POSSIBLE - __flush_dcache_page(page_address(page), - ((tlb_type == spitfire) && - page_mapping_file(page) != NULL)); + for (i = 0; i < nr; i++) + __flush_dcache_page(folio_address(folio) + i * PAGE_SIZE, + ((tlb_type == spitfire) && + folio_flush_mapping(folio) != NULL)); #else - if (page_mapping_file(page) != NULL && - tlb_type == spitfire) - __flush_icache_page(__pa(page_address(page))); + if (folio_flush_mapping(folio) != NULL && + tlb_type == spitfire) { + for (i = 0; i < nr; i++) + __flush_icache_page((pfn + i) * PAGE_SIZE); + } #endif } @@ -218,10 +223,10 @@ inline void flush_dcache_page_impl(struct page *page) #define PG_dcache_cpu_mask \ ((1UL<<ilog2(roundup_pow_of_two(NR_CPUS)))-1UL) -#define dcache_dirty_cpu(page) \ - (((page)->flags >> PG_dcache_cpu_shift) & PG_dcache_cpu_mask) +#define dcache_dirty_cpu(folio) \ + (((folio)->flags >> PG_dcache_cpu_shift) & PG_dcache_cpu_mask) -static inline void set_dcache_dirty(struct page *page, int this_cpu) +static inline void set_dcache_dirty(struct folio *folio, int this_cpu) { unsigned long mask = this_cpu; unsigned long non_cpu_bits; @@ -238,11 +243,11 @@ static inline void set_dcache_dirty(struct page *page, int this_cpu) "bne,pn %%xcc, 1b\n\t" " nop" : /* no outputs */ - : "r" (mask), "r" (non_cpu_bits), "r" (&page->flags) + : "r" (mask), "r" (non_cpu_bits), "r" (&folio->flags) : "g1", "g7"); } -static inline void clear_dcache_dirty_cpu(struct page *page, unsigned long cpu) +static inline void clear_dcache_dirty_cpu(struct folio *folio, unsigned long cpu) { unsigned long mask = (1UL << PG_dcache_dirty); @@ -260,7 +265,7 @@ static inline void clear_dcache_dirty_cpu(struct page *page, unsigned long cpu) " nop\n" "2:" : /* no outputs */ - : "r" (cpu), "r" (mask), "r" (&page->flags), + : "r" (cpu), "r" (mask), "r" (&folio->flags), "i" (PG_dcache_cpu_mask), "i" (PG_dcache_cpu_shift) : "g1", "g7"); @@ -284,9 +289,10 @@ static void flush_dcache(unsigned long pfn) page = pfn_to_page(pfn); if (page) { + struct folio *folio = page_folio(page); unsigned long pg_flags; - pg_flags = page->flags; + pg_flags = folio->flags; if (pg_flags & (1UL << PG_dcache_dirty)) { int cpu = ((pg_flags >> PG_dcache_cpu_shift) & PG_dcache_cpu_mask); @@ -296,11 +302,11 @@ static void flush_dcache(unsigned long pfn) * in the SMP case. */ if (cpu == this_cpu) - flush_dcache_page_impl(page); + flush_dcache_folio_impl(folio); else - smp_flush_dcache_page_impl(page, cpu); + smp_flush_dcache_folio_impl(folio, cpu); - clear_dcache_dirty_cpu(page, cpu); + clear_dcache_dirty_cpu(folio, cpu); put_cpu(); } @@ -325,23 +331,12 @@ static void __update_mmu_tsb_insert(struct mm_struct *mm, unsigned long tsb_inde } #ifdef CONFIG_HUGETLB_PAGE -static void __init add_huge_page_size(unsigned long size) -{ - unsigned int order; - - if (size_to_hstate(size)) - return; - - order = ilog2(size) - PAGE_SHIFT; - hugetlb_add_hstate(order); -} - static int __init hugetlbpage_init(void) { - add_huge_page_size(1UL << HPAGE_64K_SHIFT); - add_huge_page_size(1UL << HPAGE_SHIFT); - add_huge_page_size(1UL << HPAGE_256MB_SHIFT); - add_huge_page_size(1UL << HPAGE_2GB_SHIFT); + hugetlb_add_hstate(HPAGE_64K_SHIFT - PAGE_SHIFT); + hugetlb_add_hstate(HPAGE_SHIFT - PAGE_SHIFT); + hugetlb_add_hstate(HPAGE_256MB_SHIFT - PAGE_SHIFT); + hugetlb_add_hstate(HPAGE_2GB_SHIFT - PAGE_SHIFT); return 0; } @@ -360,16 +355,11 @@ static void __init pud_huge_patch(void) __asm__ __volatile__("flush %0" : : "r" (addr)); } -static int __init setup_hugepagesz(char *string) +bool __init arch_hugetlb_valid_size(unsigned long size) { - unsigned long long hugepage_size; - unsigned int hugepage_shift; + unsigned int hugepage_shift = ilog2(size); unsigned short hv_pgsz_idx; unsigned int hv_pgsz_mask; - int rc = 0; - - hugepage_size = memparse(string, &string); - hugepage_shift = ilog2(hugepage_size); switch (hugepage_shift) { case HPAGE_16GB_SHIFT: @@ -397,28 +387,21 @@ static int __init setup_hugepagesz(char *string) hv_pgsz_mask = 0; } - if ((hv_pgsz_mask & cpu_pgsz_mask) == 0U) { - hugetlb_bad_size(); - pr_err("hugepagesz=%llu not supported by MMU.\n", - hugepage_size); - goto out; - } + if ((hv_pgsz_mask & cpu_pgsz_mask) == 0U) + return false; - add_huge_page_size(hugepage_size); - rc = 1; - -out: - return rc; + return true; } -__setup("hugepagesz=", setup_hugepagesz); #endif /* CONFIG_HUGETLB_PAGE */ -void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) +void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, unsigned int nr) { struct mm_struct *mm; unsigned long flags; bool is_huge_tsb; pte_t pte = *ptep; + unsigned int i; if (tlb_type != hypervisor) { unsigned long pfn = pte_pfn(pte); @@ -465,15 +448,21 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t * } } #endif - if (!is_huge_tsb) - __update_mmu_tsb_insert(mm, MM_TSB_BASE, PAGE_SHIFT, - address, pte_val(pte)); + if (!is_huge_tsb) { + for (i = 0; i < nr; i++) { + __update_mmu_tsb_insert(mm, MM_TSB_BASE, PAGE_SHIFT, + address, pte_val(pte)); + address += PAGE_SIZE; + pte_val(pte) += PAGE_SIZE; + } + } spin_unlock_irqrestore(&mm->context.lock, flags); } -void flush_dcache_page(struct page *page) +void flush_dcache_folio(struct folio *folio) { + unsigned long pfn = folio_pfn(folio); struct address_space *mapping; int this_cpu; @@ -484,35 +473,35 @@ void flush_dcache_page(struct page *page) * is merely the zero page. The 'bigcore' testcase in GDB * causes this case to run millions of times. */ - if (page == ZERO_PAGE(0)) + if (is_zero_pfn(pfn)) return; this_cpu = get_cpu(); - mapping = page_mapping_file(page); + mapping = folio_flush_mapping(folio); if (mapping && !mapping_mapped(mapping)) { - int dirty = test_bit(PG_dcache_dirty, &page->flags); + bool dirty = test_bit(PG_dcache_dirty, &folio->flags); if (dirty) { - int dirty_cpu = dcache_dirty_cpu(page); + int dirty_cpu = dcache_dirty_cpu(folio); if (dirty_cpu == this_cpu) goto out; - smp_flush_dcache_page_impl(page, dirty_cpu); + smp_flush_dcache_folio_impl(folio, dirty_cpu); } - set_dcache_dirty(page, this_cpu); + set_dcache_dirty(folio, this_cpu); } else { /* We could delay the flush for the !page_mapping * case too. But that case is for exec env/arg * pages and those are %99 certainly going to get * faulted into the tlb (and thus flushed) anyways. */ - flush_dcache_page_impl(page); + flush_dcache_folio_impl(folio); } out: put_cpu(); } -EXPORT_SYMBOL(flush_dcache_page); +EXPORT_SYMBOL(flush_dcache_folio); void __kprobes flush_icache_range(unsigned long start, unsigned long end) { @@ -529,10 +518,7 @@ void __kprobes flush_icache_range(unsigned long start, unsigned long end) if (kaddr >= PAGE_OFFSET) paddr = kaddr & mask; else { - pgd_t *pgdp = pgd_offset_k(kaddr); - pud_t *pudp = pud_offset(pgdp, kaddr); - pmd_t *pmdp = pmd_offset(pudp, kaddr); - pte_t *ptep = pte_offset_kernel(pmdp, kaddr); + pte_t *ptep = virt_to_kpte(kaddr); paddr = pte_val(*ptep) & mask; } @@ -737,9 +723,10 @@ static void __init inherit_prom_mappings(void) void prom_world(int enter) { - if (!enter) - set_fs(get_fs()); - + /* + * No need to change the address space any more, just flush + * the register windows + */ __asm__ __volatile__("flushw"); } @@ -932,7 +919,7 @@ struct node_mem_mask { static struct node_mem_mask node_masks[MAX_NUMNODES]; static int num_node_masks; -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA struct mdesc_mlgroup { u64 node; @@ -1088,7 +1075,7 @@ static void __init allocate_node_data(int nid) { struct pglist_data *p; unsigned long start_pfn, end_pfn; -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA NODE_DATA(nid) = memblock_alloc_node(sizeof(struct pglist_data), SMP_CACHE_BYTES, nid); @@ -1109,7 +1096,7 @@ static void __init allocate_node_data(int nid) static void init_node_masks_nonnuma(void) { -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA int i; #endif @@ -1119,7 +1106,7 @@ static void init_node_masks_nonnuma(void) node_masks[0].match = 0; num_node_masks = 1; -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA for (i = 0; i < NR_CPUS; i++) numa_cpu_lookup_table[i] = 0; @@ -1127,7 +1114,7 @@ static void init_node_masks_nonnuma(void) #endif } -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA struct pglist_data *node_data[MAX_NUMNODES]; EXPORT_SYMBOL(numa_cpu_lookup_table); @@ -1221,18 +1208,14 @@ int of_node_to_nid(struct device_node *dp) static void __init add_node_ranges(void) { - struct memblock_region *reg; + phys_addr_t start, end; unsigned long prev_max; + u64 i; memblock_resized: prev_max = memblock.memory.max; - for_each_memblock(memory, reg) { - unsigned long size = reg->size; - unsigned long start, end; - - start = reg->base; - end = start + size; + for_each_mem_range(i, &start, &end) { while (start < end) { unsigned long this_end; int nid; @@ -1240,7 +1223,7 @@ memblock_resized: this_end = memblock_nid_range(start, end, &nid); numadbg("Setting memblock NUMA node nid[%d] " - "start[%lx] end[%lx]\n", + "start[%llx] end[%lx]\n", nid, start, this_end); memblock_set_node(start, this_end - start, @@ -1639,7 +1622,6 @@ static unsigned long __init bootmem_init(unsigned long phys_base) /* XXX cpu notifier XXX */ - sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); return end_pfn; @@ -1653,6 +1635,7 @@ static unsigned long max_phys_bits = 40; bool kern_addr_valid(unsigned long addr) { pgd_t *pgd; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -1672,29 +1655,32 @@ bool kern_addr_valid(unsigned long addr) pgd = pgd_offset_k(addr); if (pgd_none(*pgd)) - return 0; + return false; - pud = pud_offset(pgd, addr); + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) + return false; + + pud = pud_offset(p4d, addr); if (pud_none(*pud)) - return 0; + return false; - if (pud_large(*pud)) + if (pud_leaf(*pud)) return pfn_valid(pud_pfn(*pud)); pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) - return 0; + return false; - if (pmd_large(*pmd)) + if (pmd_leaf(*pmd)) return pfn_valid(pmd_pfn(*pmd)); pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) - return 0; + return false; return pfn_valid(pte_pfn(*pte)); } -EXPORT_SYMBOL(kern_addr_valid); static unsigned long __ref kernel_map_hugepud(unsigned long vstart, unsigned long vend, @@ -1800,6 +1786,7 @@ static unsigned long __ref kernel_map_range(unsigned long pstart, while (vstart < vend) { unsigned long this_end, paddr = __pa(vstart); pgd_t *pgd = pgd_offset_k(vstart); + p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; @@ -1814,7 +1801,20 @@ static unsigned long __ref kernel_map_range(unsigned long pstart, alloc_bytes += PAGE_SIZE; pgd_populate(&init_mm, pgd, new); } - pud = pud_offset(pgd, vstart); + + p4d = p4d_offset(pgd, vstart); + if (p4d_none(*p4d)) { + pud_t *new; + + new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, + PAGE_SIZE); + if (!new) + goto err_alloc; + alloc_bytes += PAGE_SIZE; + p4d_populate(&init_mm, p4d, new); + } + + pud = pud_offset(p4d, vstart); if (pud_none(*pud)) { pmd_t *new; @@ -2294,10 +2294,10 @@ void __init paging_init(void) setup_page_offset(); /* These build time checkes make sure that the dcache_dirty_cpu() - * page->flags usage will work. + * folio->flags usage will work. * * When a page gets marked as dcache-dirty, we store the - * cpu number starting at bit 32 in the page->flags. Also, + * cpu number starting at bit 32 in the folio->flags. Also, * functions like clear_dcache_dirty_cpu use the cpu mask * in 13-bit signed-immediate instruction fields. */ @@ -2468,7 +2468,7 @@ void __init paging_init(void) max_zone_pfns[ZONE_NORMAL] = end_pfn; - free_area_init_nodes(max_zone_pfns); + free_area_init(max_zone_pfns); } printk("Booting Linux...\n"); @@ -2502,7 +2502,7 @@ int page_in_phys_avail(unsigned long paddr) static void __init register_page_bootmem_info(void) { -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA int i; for_each_online_node(i) @@ -2535,7 +2535,6 @@ void __init mem_init(void) } mark_page_reserved(mem_map_zero); - mem_init_print_info(NULL); if (tlb_type == cheetah || tlb_type == cheetah_plus) cheetah_ecache_flush_init(); @@ -2612,13 +2611,18 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend, for (; vstart < vend; vstart += PMD_SIZE) { pgd_t *pgd = vmemmap_pgd_populate(vstart, node); unsigned long pte; + p4d_t *p4d; pud_t *pud; pmd_t *pmd; if (!pgd) return -ENOMEM; - pud = vmemmap_pud_populate(pgd, vstart, node); + p4d = vmemmap_p4d_populate(pgd, vstart, node); + if (!p4d) + return -ENOMEM; + + pud = vmemmap_pud_populate(p4d, vstart, node); if (!pud) return -ENOMEM; @@ -2643,6 +2647,9 @@ void vmemmap_free(unsigned long start, unsigned long end, } #endif /* CONFIG_SPARSEMEM_VMEMMAP */ +/* These are actually filled in at boot time by sun4{u,v}_pgprot_init() */ +static pgprot_t protection_map[16] __ro_after_init; + static void prot_init_common(unsigned long page_none, unsigned long page_shared, unsigned long page_copy, @@ -2900,14 +2907,15 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm) pgtable_t pte_alloc_one(struct mm_struct *mm) { - struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL | __GFP_ZERO, 0); + + if (!ptdesc) return NULL; - if (!pgtable_pte_page_ctor(page)) { - free_unref_page(page); + if (!pagetable_pte_ctor(ptdesc)) { + pagetable_free(ptdesc); return NULL; } - return (pte_t *) page_address(page); + return ptdesc_address(ptdesc); } void pte_free_kernel(struct mm_struct *mm, pte_t *pte) @@ -2917,10 +2925,10 @@ void pte_free_kernel(struct mm_struct *mm, pte_t *pte) static void __pte_free(pgtable_t pte) { - struct page *page = virt_to_page(pte); + struct ptdesc *ptdesc = virt_to_ptdesc(pte); - pgtable_pte_page_dtor(page); - __free_page(page); + pagetable_pte_dtor(ptdesc); + pagetable_free(ptdesc); } void pte_free(struct mm_struct *mm, pgtable_t pte) @@ -2937,6 +2945,22 @@ void pgtable_free(void *table, bool is_page) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void pte_free_now(struct rcu_head *head) +{ + struct page *page; + + page = container_of(head, struct page, rcu_head); + __pte_free((pgtable_t)page_address(page)); +} + +void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable) +{ + struct page *page; + + page = virt_to_page(pgtable); + call_rcu(&page->rcu_head, pte_free_now); +} + void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) { @@ -2944,7 +2968,7 @@ void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, struct mm_struct *mm; pmd_t entry = *pmd; - if (!pmd_large(entry) || !pmd_young(entry)) + if (!pmd_leaf(entry) || !pmd_young(entry)) return; pte = pmd_val(entry); @@ -3193,3 +3217,15 @@ void copy_highpage(struct page *to, struct page *from) } } EXPORT_SYMBOL(copy_highpage); + +pgprot_t vm_get_page_prot(unsigned long vm_flags) +{ + unsigned long prot = pgprot_val(protection_map[vm_flags & + (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]); + + if (vm_flags & VM_SPARC_ADI) + prot |= _PAGE_MCD_4V; + + return __pgprot(prot); +} +EXPORT_SYMBOL(vm_get_page_prot); |