diff options
Diffstat (limited to 'arch/x86/mm/init_64.c')
-rw-r--r-- | arch/x86/mm/init_64.c | 413 |
1 files changed, 208 insertions, 205 deletions
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a7308b2cd058..9b61c75a2355 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -43,12 +43,10 @@ #include <asm/proto.h> #include <asm/smp.h> #include <asm/sections.h> +#include <asm/kdebug.h> +#include <asm/numa.h> -#ifndef Dprintk -#define Dprintk(x...) -#endif - -const struct dma_mapping_ops* dma_ops; +const struct dma_mapping_ops *dma_ops; EXPORT_SYMBOL(dma_ops); static unsigned long dma_reserve __initdata; @@ -65,22 +63,26 @@ void show_mem(void) { long i, total = 0, reserved = 0; long shared = 0, cached = 0; - pg_data_t *pgdat; struct page *page; + pg_data_t *pgdat; printk(KERN_INFO "Mem-info:\n"); show_free_areas(); - printk(KERN_INFO "Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); + printk(KERN_INFO "Free swap: %6ldkB\n", + nr_swap_pages << (PAGE_SHIFT-10)); for_each_online_pgdat(pgdat) { - for (i = 0; i < pgdat->node_spanned_pages; ++i) { - /* this loop can take a while with 256 GB and 4k pages - so update the NMI watchdog */ - if (unlikely(i % MAX_ORDER_NR_PAGES == 0)) { + for (i = 0; i < pgdat->node_spanned_pages; ++i) { + /* + * This loop can take a while with 256 GB and + * 4k pages so defer the NMI watchdog: + */ + if (unlikely(i % MAX_ORDER_NR_PAGES == 0)) touch_nmi_watchdog(); - } + if (!pfn_valid(pgdat->node_start_pfn + i)) continue; + page = pfn_to_page(pgdat->node_start_pfn + i); total++; if (PageReserved(page)) @@ -89,51 +91,58 @@ void show_mem(void) cached++; else if (page_count(page)) shared += page_count(page) - 1; - } + } } - printk(KERN_INFO "%lu pages of RAM\n", total); - printk(KERN_INFO "%lu reserved pages\n",reserved); - printk(KERN_INFO "%lu pages shared\n",shared); - printk(KERN_INFO "%lu pages swap cached\n",cached); + printk(KERN_INFO "%lu pages of RAM\n", total); + printk(KERN_INFO "%lu reserved pages\n", reserved); + printk(KERN_INFO "%lu pages shared\n", shared); + printk(KERN_INFO "%lu pages swap cached\n", cached); } int after_bootmem; static __init void *spp_getpage(void) -{ +{ void *ptr; + if (after_bootmem) - ptr = (void *) get_zeroed_page(GFP_ATOMIC); + ptr = (void *) get_zeroed_page(GFP_ATOMIC); else ptr = alloc_bootmem_pages(PAGE_SIZE); - if (!ptr || ((unsigned long)ptr & ~PAGE_MASK)) - panic("set_pte_phys: cannot allocate page data %s\n", after_bootmem?"after bootmem":""); - Dprintk("spp_getpage %p\n", ptr); + if (!ptr || ((unsigned long)ptr & ~PAGE_MASK)) { + panic("set_pte_phys: cannot allocate page data %s\n", + after_bootmem ? "after bootmem" : ""); + } + + pr_debug("spp_getpage %p\n", ptr); + return ptr; -} +} -static __init void set_pte_phys(unsigned long vaddr, - unsigned long phys, pgprot_t prot) +static __init void +set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte, new_pte; - Dprintk("set_pte_phys %lx to %lx\n", vaddr, phys); + pr_debug("set_pte_phys %lx to %lx\n", vaddr, phys); pgd = pgd_offset_k(vaddr); if (pgd_none(*pgd)) { - printk("PGD FIXMAP MISSING, it should be setup in head.S!\n"); + printk(KERN_ERR + "PGD FIXMAP MISSING, it should be setup in head.S!\n"); return; } pud = pud_offset(pgd, vaddr); if (pud_none(*pud)) { - pmd = (pmd_t *) spp_getpage(); + pmd = (pmd_t *) spp_getpage(); set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | _PAGE_USER)); if (pmd != pmd_offset(pud, 0)) { - printk("PAGETABLE BUG #01! %p <-> %p\n", pmd, pmd_offset(pud,0)); + printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n", + pmd, pmd_offset(pud, 0)); return; } } @@ -142,7 +151,7 @@ static __init void set_pte_phys(unsigned long vaddr, pte = (pte_t *) spp_getpage(); set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE | _PAGE_USER)); if (pte != pte_offset_kernel(pmd, 0)) { - printk("PAGETABLE BUG #02!\n"); + printk(KERN_ERR "PAGETABLE BUG #02!\n"); return; } } @@ -162,33 +171,35 @@ static __init void set_pte_phys(unsigned long vaddr, } /* NOTE: this is meant to be run only at boot */ -void __init -__set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t prot) +void __init +__set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot) { unsigned long address = __fix_to_virt(idx); if (idx >= __end_of_fixed_addresses) { - printk("Invalid __set_fixmap\n"); + printk(KERN_ERR "Invalid __set_fixmap\n"); return; } set_pte_phys(address, phys, prot); } -unsigned long __meminitdata table_start, table_end; +static unsigned long __initdata table_start; +static unsigned long __meminitdata table_end; static __meminit void *alloc_low_page(unsigned long *phys) -{ +{ unsigned long pfn = table_end++; void *adr; if (after_bootmem) { adr = (void *)get_zeroed_page(GFP_ATOMIC); *phys = __pa(adr); + return adr; } - if (pfn >= end_pfn) - panic("alloc_low_page: ran out of memory"); + if (pfn >= end_pfn) + panic("alloc_low_page: ran out of memory"); adr = early_ioremap(pfn * PAGE_SIZE, PAGE_SIZE); memset(adr, 0, PAGE_SIZE); @@ -197,44 +208,49 @@ static __meminit void *alloc_low_page(unsigned long *phys) } static __meminit void unmap_low_page(void *adr) -{ - +{ if (after_bootmem) return; early_iounmap(adr, PAGE_SIZE); -} +} /* Must run before zap_low_mappings */ __meminit void *early_ioremap(unsigned long addr, unsigned long size) { - unsigned long vaddr; pmd_t *pmd, *last_pmd; + unsigned long vaddr; int i, pmds; pmds = ((addr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE; vaddr = __START_KERNEL_map; pmd = level2_kernel_pgt; last_pmd = level2_kernel_pgt + PTRS_PER_PMD - 1; + for (; pmd <= last_pmd; pmd++, vaddr += PMD_SIZE) { for (i = 0; i < pmds; i++) { if (pmd_present(pmd[i])) - goto next; + goto continue_outer_loop; } vaddr += addr & ~PMD_MASK; addr &= PMD_MASK; + for (i = 0; i < pmds; i++, addr += PMD_SIZE) - set_pmd(pmd + i,__pmd(addr | _KERNPG_TABLE | _PAGE_PSE)); - __flush_tlb(); + set_pmd(pmd+i, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC)); + __flush_tlb_all(); + return (void *)vaddr; - next: +continue_outer_loop: ; } - printk("early_ioremap(0x%lx, %lu) failed\n", addr, size); + printk(KERN_ERR "early_ioremap(0x%lx, %lu) failed\n", addr, size); + return NULL; } -/* To avoid virtual aliases later */ +/* + * To avoid virtual aliases later: + */ __meminit void early_iounmap(void *addr, unsigned long size) { unsigned long vaddr; @@ -244,9 +260,11 @@ __meminit void early_iounmap(void *addr, unsigned long size) vaddr = (unsigned long)addr; pmds = ((vaddr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE; pmd = level2_kernel_pgt + pmd_index(vaddr); + for (i = 0; i < pmds; i++) pmd_clear(pmd + i); - __flush_tlb(); + + __flush_tlb_all(); } static void __meminit @@ -255,41 +273,40 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end) int i = pmd_index(address); for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) { - unsigned long entry; pmd_t *pmd = pmd_page + pmd_index(address); if (address >= end) { - if (!after_bootmem) + if (!after_bootmem) { for (; i < PTRS_PER_PMD; i++, pmd++) set_pmd(pmd, __pmd(0)); + } break; } if (pmd_val(*pmd)) continue; - entry = _PAGE_NX|_PAGE_PSE|_KERNPG_TABLE|_PAGE_GLOBAL|address; - entry &= __supported_pte_mask; - set_pmd(pmd, __pmd(entry)); + set_pte((pte_t *)pmd, + pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE)); } } static void __meminit phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end) { - pmd_t *pmd = pmd_offset(pud,0); + pmd_t *pmd = pmd_offset(pud, 0); spin_lock(&init_mm.page_table_lock); phys_pmd_init(pmd, address, end); spin_unlock(&init_mm.page_table_lock); __flush_tlb_all(); } -static void __meminit phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end) -{ +static void __meminit +phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end) +{ int i = pud_index(addr); - - for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE ) { + for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE) { unsigned long pmd_phys; pud_t *pud = pud_page + pud_index(addr); pmd_t *pmd; @@ -297,10 +314,11 @@ static void __meminit phys_pud_init(pud_t *pud_page, unsigned long addr, unsigne if (addr >= end) break; - if (!after_bootmem && !e820_any_mapped(addr,addr+PUD_SIZE,0)) { - set_pud(pud, __pud(0)); + if (!after_bootmem && + !e820_any_mapped(addr, addr+PUD_SIZE, 0)) { + set_pud(pud, __pud(0)); continue; - } + } if (pud_val(*pud)) { phys_pmd_update(pud, addr, end); @@ -308,14 +326,16 @@ static void __meminit phys_pud_init(pud_t *pud_page, unsigned long addr, unsigne } pmd = alloc_low_page(&pmd_phys); + spin_lock(&init_mm.page_table_lock); set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE)); phys_pmd_init(pmd, addr, end); spin_unlock(&init_mm.page_table_lock); + unmap_low_page(pmd); } - __flush_tlb(); -} + __flush_tlb_all(); +} static void __init find_early_table_space(unsigned long end) { @@ -326,11 +346,13 @@ static void __init find_early_table_space(unsigned long end) tables = round_up(puds * sizeof(pud_t), PAGE_SIZE) + round_up(pmds * sizeof(pmd_t), PAGE_SIZE); - /* RED-PEN putting page tables only on node 0 could - cause a hotspot and fill up ZONE_DMA. The page tables - need roughly 0.5KB per GB. */ - start = 0x8000; - table_start = find_e820_area(start, end, tables); + /* + * RED-PEN putting page tables only on node 0 could + * cause a hotspot and fill up ZONE_DMA. The page tables + * need roughly 0.5KB per GB. + */ + start = 0x8000; + table_start = find_e820_area(start, end, tables, PAGE_SIZE); if (table_start == -1UL) panic("Cannot find space for the kernel page tables"); @@ -342,20 +364,23 @@ static void __init find_early_table_space(unsigned long end) (table_start << PAGE_SHIFT) + tables); } -/* Setup the direct mapping of the physical memory at PAGE_OFFSET. - This runs before bootmem is initialized and gets pages directly from the - physical memory. To access them they are temporarily mapped. */ -void __meminit init_memory_mapping(unsigned long start, unsigned long end) -{ - unsigned long next; +/* + * Setup the direct mapping of the physical memory at PAGE_OFFSET. + * This runs before bootmem is initialized and gets pages directly from + * the physical memory. To access them they are temporarily mapped. + */ +void __init_refok init_memory_mapping(unsigned long start, unsigned long end) +{ + unsigned long next; - Dprintk("init_memory_mapping\n"); + pr_debug("init_memory_mapping\n"); - /* + /* * Find space for the kernel direct mapping tables. - * Later we should allocate these tables in the local node of the memory - * mapped. Unfortunately this is done currently before the nodes are - * discovered. + * + * Later we should allocate these tables in the local node of the + * memory mapped. Unfortunately this is done currently before the + * nodes are discovered. */ if (!after_bootmem) find_early_table_space(end); @@ -364,8 +389,8 @@ void __meminit init_memory_mapping(unsigned long start, unsigned long end) end = (unsigned long)__va(end); for (; start < end; start = next) { - unsigned long pud_phys; pgd_t *pgd = pgd_offset_k(start); + unsigned long pud_phys; pud_t *pud; if (after_bootmem) @@ -374,23 +399,28 @@ void __meminit init_memory_mapping(unsigned long start, unsigned long end) pud = alloc_low_page(&pud_phys); next = start + PGDIR_SIZE; - if (next > end) - next = end; + if (next > end) + next = end; phys_pud_init(pud, __pa(start), __pa(next)); if (!after_bootmem) set_pgd(pgd_offset_k(start), mk_kernel_pgd(pud_phys)); unmap_low_page(pud); - } + } if (!after_bootmem) mmu_cr4_features = read_cr4(); __flush_tlb_all(); + + if (!after_bootmem) + reserve_early(table_start << PAGE_SHIFT, + table_end << PAGE_SHIFT, "PGTABLE"); } #ifndef CONFIG_NUMA void __init paging_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN; max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN; @@ -402,40 +432,6 @@ void __init paging_init(void) } #endif -/* Unmap a kernel mapping if it exists. This is useful to avoid prefetches - from the CPU leading to inconsistent cache lines. address and size - must be aligned to 2MB boundaries. - Does nothing when the mapping doesn't exist. */ -void __init clear_kernel_mapping(unsigned long address, unsigned long size) -{ - unsigned long end = address + size; - - BUG_ON(address & ~LARGE_PAGE_MASK); - BUG_ON(size & ~LARGE_PAGE_MASK); - - for (; address < end; address += LARGE_PAGE_SIZE) { - pgd_t *pgd = pgd_offset_k(address); - pud_t *pud; - pmd_t *pmd; - if (pgd_none(*pgd)) - continue; - pud = pud_offset(pgd, address); - if (pud_none(*pud)) - continue; - pmd = pmd_offset(pud, address); - if (!pmd || pmd_none(*pmd)) - continue; - if (0 == (pmd_val(*pmd) & _PAGE_PSE)) { - /* Could handle this, but it should not happen currently. */ - printk(KERN_ERR - "clear_kernel_mapping: mapping has been split. will leak memory\n"); - pmd_ERROR(*pmd); - } - set_pmd(pmd, __pmd(0)); - } - __flush_tlb_all(); -} - /* * Memory hotplug specific functions */ @@ -461,16 +457,12 @@ int arch_add_memory(int nid, u64 start, u64 size) unsigned long nr_pages = size >> PAGE_SHIFT; int ret; - init_memory_mapping(start, (start + size -1)); + init_memory_mapping(start, start + size-1); ret = __add_pages(zone, start_pfn, nr_pages); - if (ret) - goto error; + WARN_ON(1); return ret; -error: - printk("%s: Problem encountered in __add_pages!\n", __func__); - return ret; } EXPORT_SYMBOL_GPL(arch_add_memory); @@ -484,36 +476,8 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif /* CONFIG_MEMORY_HOTPLUG */ -#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE -/* - * Memory Hotadd without sparsemem. The mem_maps have been allocated in advance, - * just online the pages. - */ -int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages) -{ - int err = -EIO; - unsigned long pfn; - unsigned long total = 0, mem = 0; - for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) { - if (pfn_valid(pfn)) { - online_page(pfn_to_page(pfn)); - err = 0; - mem++; - } - total++; - } - if (!err) { - z->spanned_pages += total; - z->present_pages += mem; - z->zone_pgdat->node_spanned_pages += total; - z->zone_pgdat->node_present_pages += mem; - } - return err; -} -#endif - -static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules, - kcore_vsyscall; +static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, + kcore_modules, kcore_vsyscall; void __init mem_init(void) { @@ -521,8 +485,15 @@ void __init mem_init(void) pci_iommu_alloc(); - /* clear the zero-page */ - memset(empty_zero_page, 0, PAGE_SIZE); + /* clear_bss() already clear the empty_zero_page */ + + /* temporary debugging - double check it's true: */ + { + int i; + + for (i = 0; i < 1024; i++) + WARN_ON_ONCE(empty_zero_page[i]); + } reservedpages = 0; @@ -534,7 +505,6 @@ void __init mem_init(void) #endif reservedpages = end_pfn - totalram_pages - absent_pages_in_range(0, end_pfn); - after_bootmem = 1; codesize = (unsigned long) &_etext - (unsigned long) &_text; @@ -542,15 +512,16 @@ void __init mem_init(void) initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); - kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, + kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); + kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, VMALLOC_END-VMALLOC_START); kclist_add(&kcore_kernel, &_stext, _end - _stext); kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN); - kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START, + kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START, VSYSCALL_END - VSYSCALL_START); - printk("Memory: %luk/%luk available (%ldk kernel code, %ldk reserved, %ldk data, %ldk init)\n", + printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, " + "%ldk reserved, %ldk data, %ldk init)\n", (unsigned long) nr_free_pages() << (PAGE_SHIFT-10), end_pfn << (PAGE_SHIFT-10), codesize >> 10, @@ -566,19 +537,27 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end) if (begin >= end) return; + /* + * If debugging page accesses then do not free this memory but + * mark them not present - any buggy init-section access will + * create a kernel page fault: + */ +#ifdef CONFIG_DEBUG_PAGEALLOC + printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n", + begin, PAGE_ALIGN(end)); + set_memory_np(begin, (end - begin) >> PAGE_SHIFT); +#else printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10); + for (addr = begin; addr < end; addr += PAGE_SIZE) { ClearPageReserved(virt_to_page(addr)); init_page_count(virt_to_page(addr)); memset((void *)(addr & ~(PAGE_SIZE-1)), POISON_FREE_INITMEM, PAGE_SIZE); - if (addr >= __START_KERNEL_map) - change_page_attr_addr(addr, 1, __pgprot(0)); free_page(addr); totalram_pages++; } - if (addr > __START_KERNEL_map) - global_flush_tlb(); +#endif } void free_initmem(void) @@ -589,6 +568,8 @@ void free_initmem(void) } #ifdef CONFIG_DEBUG_RODATA +const int rodata_test_data = 0xC3; +EXPORT_SYMBOL_GPL(rodata_test_data); void mark_rodata_ro(void) { @@ -603,25 +584,34 @@ void mark_rodata_ro(void) #ifdef CONFIG_KPROBES start = (unsigned long)__start_rodata; #endif - + end = (unsigned long)__end_rodata; start = (start + PAGE_SIZE - 1) & PAGE_MASK; end &= PAGE_MASK; if (end <= start) return; - change_page_attr_addr(start, (end - start) >> PAGE_SHIFT, PAGE_KERNEL_RO); printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); + set_memory_ro(start, (end - start) >> PAGE_SHIFT); /* - * change_page_attr_addr() requires a global_flush_tlb() call after it. - * We do this after the printk so that if something went wrong in the - * change, the printk gets out at least to give a better debug hint - * of who is the culprit. + * The rodata section (but not the kernel text!) should also be + * not-executable. */ - global_flush_tlb(); + start = ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK; + set_memory_nx(start, (end - start) >> PAGE_SHIFT); + + rodata_test(); + +#ifdef CONFIG_CPA_DEBUG + printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, end); + set_memory_rw(start, (end-start) >> PAGE_SHIFT); + + printk(KERN_INFO "Testing CPA: again\n"); + set_memory_ro(start, (end-start) >> PAGE_SHIFT); +#endif } #endif @@ -632,17 +622,21 @@ void free_initrd_mem(unsigned long start, unsigned long end) } #endif -void __init reserve_bootmem_generic(unsigned long phys, unsigned len) -{ +void __init reserve_bootmem_generic(unsigned long phys, unsigned len) +{ #ifdef CONFIG_NUMA int nid = phys_to_nid(phys); #endif unsigned long pfn = phys >> PAGE_SHIFT; + if (pfn >= end_pfn) { - /* This can happen with kdump kernels when accessing firmware - tables. */ + /* + * This can happen with kdump kernels when accessing + * firmware tables: + */ if (pfn < end_pfn_map) return; + printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %u\n", phys, len); return; @@ -650,9 +644,9 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len) /* Should check here against the e820 map to avoid double free */ #ifdef CONFIG_NUMA - reserve_bootmem_node(NODE_DATA(nid), phys, len); -#else - reserve_bootmem(phys, len); + reserve_bootmem_node(NODE_DATA(nid), phys, len); +#else + reserve_bootmem(phys, len); #endif if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) { dma_reserve += len / PAGE_SIZE; @@ -660,46 +654,49 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len) } } -int kern_addr_valid(unsigned long addr) -{ +int kern_addr_valid(unsigned long addr) +{ unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; if (above != 0 && above != -1UL) - return 0; - + return 0; + pgd = pgd_offset_k(addr); if (pgd_none(*pgd)) return 0; pud = pud_offset(pgd, addr); if (pud_none(*pud)) - return 0; + return 0; pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) return 0; + if (pmd_large(*pmd)) return pfn_valid(pmd_pfn(*pmd)); pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) return 0; + return pfn_valid(pte_pfn(*pte)); } -/* A pseudo VMA to allow ptrace access for the vsyscall page. This only - covers the 64bit vsyscall page now. 32bit has a real VMA now and does - not need special handling anymore. */ - +/* + * A pseudo VMA to allow ptrace access for the vsyscall page. This only + * covers the 64bit vsyscall page now. 32bit has a real VMA now and does + * not need special handling anymore: + */ static struct vm_area_struct gate_vma = { - .vm_start = VSYSCALL_START, - .vm_end = VSYSCALL_START + (VSYSCALL_MAPPED_PAGES << PAGE_SHIFT), - .vm_page_prot = PAGE_READONLY_EXEC, - .vm_flags = VM_READ | VM_EXEC + .vm_start = VSYSCALL_START, + .vm_end = VSYSCALL_START + (VSYSCALL_MAPPED_PAGES * PAGE_SIZE), + .vm_page_prot = PAGE_READONLY_EXEC, + .vm_flags = VM_READ | VM_EXEC }; struct vm_area_struct *get_gate_vma(struct task_struct *tsk) @@ -714,14 +711,17 @@ struct vm_area_struct *get_gate_vma(struct task_struct *tsk) int in_gate_area(struct task_struct *task, unsigned long addr) { struct vm_area_struct *vma = get_gate_vma(task); + if (!vma) return 0; + return (addr >= vma->vm_start) && (addr < vma->vm_end); } -/* Use this when you have no reliable task/vma, typically from interrupt - * context. It is less reliable than using the task's vma and may give - * false positives. +/* + * Use this when you have no reliable task/vma, typically from interrupt + * context. It is less reliable than using the task's vma and may give + * false positives: */ int in_gate_area_no_task(unsigned long addr) { @@ -741,8 +741,8 @@ const char *arch_vma_name(struct vm_area_struct *vma) /* * Initialise the sparsemem vmemmap using huge-pages at the PMD level. */ -int __meminit vmemmap_populate(struct page *start_page, - unsigned long size, int node) +int __meminit +vmemmap_populate(struct page *start_page, unsigned long size, int node) { unsigned long addr = (unsigned long)start_page; unsigned long end = (unsigned long)(start_page + size); @@ -757,6 +757,7 @@ int __meminit vmemmap_populate(struct page *start_page, pgd = vmemmap_pgd_populate(addr, node); if (!pgd) return -ENOMEM; + pud = vmemmap_pud_populate(pgd, addr, node); if (!pud) return -ENOMEM; @@ -764,20 +765,22 @@ int __meminit vmemmap_populate(struct page *start_page, pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) { pte_t entry; - void *p = vmemmap_alloc_block(PMD_SIZE, node); + void *p; + + p = vmemmap_alloc_block(PMD_SIZE, node); if (!p) return -ENOMEM; - entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL); - mk_pte_huge(entry); + entry = pfn_pte(__pa(p) >> PAGE_SHIFT, + PAGE_KERNEL_LARGE); set_pmd(pmd, __pmd(pte_val(entry))); printk(KERN_DEBUG " [%lx-%lx] PMD ->%p on node %d\n", addr, addr + PMD_SIZE - 1, p, node); - } else + } else { vmemmap_verify((pte_t *)pmd, node, addr, next); + } } - return 0; } #endif |