diff options
Diffstat (limited to 'arch/powerpc/mm/pgtable-radix.c')
| -rw-r--r-- | arch/powerpc/mm/pgtable-radix.c | 218 |
1 files changed, 144 insertions, 74 deletions
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 2e10a964e290..f1891e215e39 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -48,20 +48,88 @@ static int native_register_process_table(unsigned long base, unsigned long pg_sz return 0; } -static __ref void *early_alloc_pgtable(unsigned long size) +static __ref void *early_alloc_pgtable(unsigned long size, int nid, + unsigned long region_start, unsigned long region_end) { + unsigned long pa = 0; void *pt; - pt = __va(memblock_alloc_base(size, size, MEMBLOCK_ALLOC_ANYWHERE)); + if (region_start || region_end) /* has region hint */ + pa = memblock_alloc_range(size, size, region_start, region_end, + MEMBLOCK_NONE); + else if (nid != -1) /* has node hint */ + pa = memblock_alloc_base_nid(size, size, + MEMBLOCK_ALLOC_ANYWHERE, + nid, MEMBLOCK_NONE); + + if (!pa) + pa = memblock_alloc_base(size, size, MEMBLOCK_ALLOC_ANYWHERE); + + BUG_ON(!pa); + + pt = __va(pa); memset(pt, 0, size); return pt; } -int radix__map_kernel_page(unsigned long ea, unsigned long pa, +static int early_map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t flags, - unsigned int map_page_size) + unsigned int map_page_size, + int nid, + unsigned long region_start, unsigned long region_end) { + unsigned long pfn = pa >> PAGE_SHIFT; + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep; + + pgdp = pgd_offset_k(ea); + if (pgd_none(*pgdp)) { + pudp = early_alloc_pgtable(PUD_TABLE_SIZE, nid, + region_start, region_end); + pgd_populate(&init_mm, pgdp, pudp); + } + pudp = pud_offset(pgdp, ea); + if (map_page_size == PUD_SIZE) { + ptep = (pte_t *)pudp; + goto set_the_pte; + } + if (pud_none(*pudp)) { + pmdp = early_alloc_pgtable(PMD_TABLE_SIZE, nid, + region_start, region_end); + pud_populate(&init_mm, pudp, pmdp); + } + pmdp = pmd_offset(pudp, ea); + if (map_page_size == PMD_SIZE) { + ptep = pmdp_ptep(pmdp); + goto set_the_pte; + } + if (!pmd_present(*pmdp)) { + ptep = early_alloc_pgtable(PAGE_SIZE, nid, + region_start, region_end); + pmd_populate_kernel(&init_mm, pmdp, ptep); + } + ptep = pte_offset_kernel(pmdp, ea); + +set_the_pte: + set_pte_at(&init_mm, ea, ptep, pfn_pte(pfn, flags)); + smp_wmb(); + return 0; +} + +/* + * nid, region_start, and region_end are hints to try to place the page + * table memory in the same node or region. + */ +static int __map_kernel_page(unsigned long ea, unsigned long pa, + pgprot_t flags, + unsigned int map_page_size, + int nid, + unsigned long region_start, unsigned long region_end) +{ + unsigned long pfn = pa >> PAGE_SHIFT; pgd_t *pgdp; pud_t *pudp; pmd_t *pmdp; @@ -70,61 +138,48 @@ int radix__map_kernel_page(unsigned long ea, unsigned long pa, * Make sure task size is correct as per the max adddr */ BUILD_BUG_ON(TASK_SIZE_USER64 > RADIX_PGTABLE_RANGE); - if (slab_is_available()) { - pgdp = pgd_offset_k(ea); - pudp = pud_alloc(&init_mm, pgdp, ea); - if (!pudp) - return -ENOMEM; - if (map_page_size == PUD_SIZE) { - ptep = (pte_t *)pudp; - goto set_the_pte; - } - pmdp = pmd_alloc(&init_mm, pudp, ea); - if (!pmdp) - return -ENOMEM; - if (map_page_size == PMD_SIZE) { - ptep = pmdp_ptep(pmdp); - goto set_the_pte; - } - ptep = pte_alloc_kernel(pmdp, ea); - if (!ptep) - return -ENOMEM; - } else { - pgdp = pgd_offset_k(ea); - if (pgd_none(*pgdp)) { - pudp = early_alloc_pgtable(PUD_TABLE_SIZE); - BUG_ON(pudp == NULL); - pgd_populate(&init_mm, pgdp, pudp); - } - pudp = pud_offset(pgdp, ea); - if (map_page_size == PUD_SIZE) { - ptep = (pte_t *)pudp; - goto set_the_pte; - } - if (pud_none(*pudp)) { - pmdp = early_alloc_pgtable(PMD_TABLE_SIZE); - BUG_ON(pmdp == NULL); - pud_populate(&init_mm, pudp, pmdp); - } - pmdp = pmd_offset(pudp, ea); - if (map_page_size == PMD_SIZE) { - ptep = pmdp_ptep(pmdp); - goto set_the_pte; - } - if (!pmd_present(*pmdp)) { - ptep = early_alloc_pgtable(PAGE_SIZE); - BUG_ON(ptep == NULL); - pmd_populate_kernel(&init_mm, pmdp, ptep); - } - ptep = pte_offset_kernel(pmdp, ea); + + if (unlikely(!slab_is_available())) + return early_map_kernel_page(ea, pa, flags, map_page_size, + nid, region_start, region_end); + + /* + * Should make page table allocation functions be able to take a + * node, so we can place kernel page tables on the right nodes after + * boot. + */ + pgdp = pgd_offset_k(ea); + pudp = pud_alloc(&init_mm, pgdp, ea); + if (!pudp) + return -ENOMEM; + if (map_page_size == PUD_SIZE) { + ptep = (pte_t *)pudp; + goto set_the_pte; + } + pmdp = pmd_alloc(&init_mm, pudp, ea); + if (!pmdp) + return -ENOMEM; + if (map_page_size == PMD_SIZE) { + ptep = pmdp_ptep(pmdp); + goto set_the_pte; } + ptep = pte_alloc_kernel(pmdp, ea); + if (!ptep) + return -ENOMEM; set_the_pte: - set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, flags)); + set_pte_at(&init_mm, ea, ptep, pfn_pte(pfn, flags)); smp_wmb(); return 0; } +int radix__map_kernel_page(unsigned long ea, unsigned long pa, + pgprot_t flags, + unsigned int map_page_size) +{ + return __map_kernel_page(ea, pa, flags, map_page_size, -1, 0, 0); +} + #ifdef CONFIG_STRICT_KERNEL_RWX void radix__change_memory_range(unsigned long start, unsigned long end, unsigned long clear) @@ -211,7 +266,8 @@ static inline void __meminit print_mapping(unsigned long start, } static int __meminit create_physical_mapping(unsigned long start, - unsigned long end) + unsigned long end, + int nid) { unsigned long vaddr, addr, mapping_size = 0; pgprot_t prot; @@ -267,7 +323,7 @@ retry: else prot = PAGE_KERNEL; - rc = radix__map_kernel_page(vaddr, addr, prot, mapping_size); + rc = __map_kernel_page(vaddr, addr, prot, mapping_size, nid, start, end); if (rc) return rc; } @@ -276,7 +332,7 @@ retry: return 0; } -static void __init radix_init_pgtable(void) +void __init radix_init_pgtable(void) { unsigned long rts_field; struct memblock_region *reg; @@ -286,9 +342,16 @@ static void __init radix_init_pgtable(void) /* * Create the linear mapping, using standard page size for now */ - for_each_memblock(memory, reg) + for_each_memblock(memory, reg) { + /* + * The memblock allocator is up at this point, so the + * page tables will be allocated within the range. No + * need or a node (which we don't have yet). + */ WARN_ON(create_physical_mapping(reg->base, - reg->base + reg->size)); + reg->base + reg->size, + -1)); + } /* Find out how many PID bits are supported */ if (cpu_has_feature(CPU_FTR_HVMODE)) { @@ -317,7 +380,7 @@ static void __init radix_init_pgtable(void) * host. */ BUG_ON(PRTB_SIZE_SHIFT > 36); - process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT); + process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT, -1, 0, 0); /* * Fill in the process table. */ @@ -575,12 +638,8 @@ void __init radix__early_init_mmu(void) #ifdef CONFIG_PCI pci_io_base = ISA_IO_BASE; #endif - - /* - * For now radix also use the same frag size - */ - __pte_frag_nr = H_PTE_FRAG_NR; - __pte_frag_size_shift = H_PTE_FRAG_SIZE_SHIFT; + __pte_frag_nr = RADIX_PTE_FRAG_NR; + __pte_frag_size_shift = RADIX_PTE_FRAG_SIZE_SHIFT; if (!firmware_has_feature(FW_FEATURE_LPAR)) { radix_init_native(); @@ -695,7 +754,7 @@ struct change_mapping_params { unsigned long aligned_end; }; -static int stop_machine_change_mapping(void *data) +static int __meminit stop_machine_change_mapping(void *data) { struct change_mapping_params *params = (struct change_mapping_params *)data; @@ -705,8 +764,8 @@ static int stop_machine_change_mapping(void *data) spin_unlock(&init_mm.page_table_lock); pte_clear(&init_mm, params->aligned_start, params->pte); - create_physical_mapping(params->aligned_start, params->start); - create_physical_mapping(params->end, params->aligned_end); + create_physical_mapping(params->aligned_start, params->start, -1); + create_physical_mapping(params->end, params->aligned_end, -1); spin_lock(&init_mm.page_table_lock); return 0; } @@ -742,7 +801,7 @@ static void remove_pte_table(pte_t *pte_start, unsigned long addr, /* * clear the pte and potentially split the mapping helper */ -static void split_kernel_mapping(unsigned long addr, unsigned long end, +static void __meminit split_kernel_mapping(unsigned long addr, unsigned long end, unsigned long size, pte_t *pte) { unsigned long mask = ~(size - 1); @@ -835,7 +894,7 @@ static void remove_pud_table(pud_t *pud_start, unsigned long addr, } } -static void remove_pagetable(unsigned long start, unsigned long end) +static void __meminit remove_pagetable(unsigned long start, unsigned long end) { unsigned long addr, next; pud_t *pud_base; @@ -863,12 +922,12 @@ static void remove_pagetable(unsigned long start, unsigned long end) radix__flush_tlb_kernel_range(start, end); } -int __ref radix__create_section_mapping(unsigned long start, unsigned long end) +int __meminit radix__create_section_mapping(unsigned long start, unsigned long end, int nid) { - return create_physical_mapping(start, end); + return create_physical_mapping(start, end, nid); } -int radix__remove_section_mapping(unsigned long start, unsigned long end) +int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end) { remove_pagetable(start, end); return 0; @@ -876,19 +935,30 @@ int radix__remove_section_mapping(unsigned long start, unsigned long end) #endif /* CONFIG_MEMORY_HOTPLUG */ #ifdef CONFIG_SPARSEMEM_VMEMMAP +static int __map_kernel_page_nid(unsigned long ea, unsigned long pa, + pgprot_t flags, unsigned int map_page_size, + int nid) +{ + return __map_kernel_page(ea, pa, flags, map_page_size, nid, 0, 0); +} + int __meminit radix__vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys) { /* Create a PTE encoding */ unsigned long flags = _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_KERNEL_RW; + int nid = early_pfn_to_nid(phys >> PAGE_SHIFT); + int ret; + + ret = __map_kernel_page_nid(start, phys, __pgprot(flags), page_size, nid); + BUG_ON(ret); - BUG_ON(radix__map_kernel_page(start, phys, __pgprot(flags), page_size)); return 0; } #ifdef CONFIG_MEMORY_HOTPLUG -void radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size) +void __meminit radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size) { remove_pagetable(start, start + page_size); } |