diff options
Diffstat (limited to 'arch/x86/mm')
| -rw-r--r-- | arch/x86/mm/Makefile | 2 | ||||
| -rw-r--r-- | arch/x86/mm/discontig_32.c | 3 | ||||
| -rw-r--r-- | arch/x86/mm/dump_pagetables.c | 10 | ||||
| -rw-r--r-- | arch/x86/mm/gup.c | 295 | ||||
| -rw-r--r-- | arch/x86/mm/hugetlbpage.c | 78 | ||||
| -rw-r--r-- | arch/x86/mm/init_32.c | 5 | ||||
| -rw-r--r-- | arch/x86/mm/init_64.c | 149 | ||||
| -rw-r--r-- | arch/x86/mm/ioremap.c | 8 | ||||
| -rw-r--r-- | arch/x86/mm/memtest.c | 123 | ||||
| -rw-r--r-- | arch/x86/mm/numa_64.c | 8 | ||||
| -rw-r--r-- | arch/x86/mm/pat.c | 94 | ||||
| -rw-r--r-- | arch/x86/mm/pgtable_32.c | 47 |
12 files changed, 594 insertions, 228 deletions
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 9873716e9f7..2977ea37791 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,6 +1,7 @@ obj-y := init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ pat.o pgtable.o +obj-$(CONFIG_HAVE_GET_USER_PAGES_FAST) += gup.o obj-$(CONFIG_X86_32) += pgtable_32.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o @@ -21,3 +22,4 @@ obj-$(CONFIG_K8_NUMA) += k8topology_64.o endif obj-$(CONFIG_ACPI_NUMA) += srat_$(BITS).o +obj-$(CONFIG_MEMTEST) += memtest.o diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c index 5dfef9fa061..62fa440678d 100644 --- a/arch/x86/mm/discontig_32.c +++ b/arch/x86/mm/discontig_32.c @@ -42,7 +42,6 @@ struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); -static bootmem_data_t node0_bdata; /* * numa interface - we expect the numa architecture specific code to have @@ -385,7 +384,7 @@ void __init initmem_init(unsigned long start_pfn, for_each_online_node(nid) memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); - NODE_DATA(0)->bdata = &node0_bdata; + NODE_DATA(0)->bdata = &bootmem_node_data[0]; setup_bootmem_allocator(); } diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 0bb0caed897..a20d1fa64b4 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -148,8 +148,8 @@ static void note_page(struct seq_file *m, struct pg_state *st, * we have now. "break" is either changing perms, levels or * address space marker. */ - prot = pgprot_val(new_prot) & ~(PTE_MASK); - cur = pgprot_val(st->current_prot) & ~(PTE_MASK); + prot = pgprot_val(new_prot) & ~(PTE_PFN_MASK); + cur = pgprot_val(st->current_prot) & ~(PTE_PFN_MASK); if (!st->level) { /* First entry */ @@ -221,7 +221,7 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, for (i = 0; i < PTRS_PER_PMD; i++) { st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT); if (!pmd_none(*start)) { - pgprotval_t prot = pmd_val(*start) & ~PTE_MASK; + pgprotval_t prot = pmd_val(*start) & PTE_FLAGS_MASK; if (pmd_large(*start) || !pmd_present(*start)) note_page(m, st, __pgprot(prot), 3); @@ -253,7 +253,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, for (i = 0; i < PTRS_PER_PUD; i++) { st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT); if (!pud_none(*start)) { - pgprotval_t prot = pud_val(*start) & ~PTE_MASK; + pgprotval_t prot = pud_val(*start) & PTE_FLAGS_MASK; if (pud_large(*start) || !pud_present(*start)) note_page(m, st, __pgprot(prot), 2); @@ -288,7 +288,7 @@ static void walk_pgd_level(struct seq_file *m) for (i = 0; i < PTRS_PER_PGD; i++) { st.current_address = normalize_addr(i * PGD_LEVEL_MULT); if (!pgd_none(*start)) { - pgprotval_t prot = pgd_val(*start) & ~PTE_MASK; + pgprotval_t prot = pgd_val(*start) & PTE_FLAGS_MASK; if (pgd_large(*start) || !pgd_present(*start)) note_page(m, &st, __pgprot(prot), 1); diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c new file mode 100644 index 00000000000..3085f25b435 --- /dev/null +++ b/arch/x86/mm/gup.c @@ -0,0 +1,295 @@ +/* + * Lockless get_user_pages_fast for x86 + * + * Copyright (C) 2008 Nick Piggin + * Copyright (C) 2008 Novell Inc. + */ +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmstat.h> +#include <linux/highmem.h> + +#include <asm/pgtable.h> + +static inline pte_t gup_get_pte(pte_t *ptep) +{ +#ifndef CONFIG_X86_PAE + return *ptep; +#else + /* + * With get_user_pages_fast, we walk down the pagetables without taking + * any locks. For this we would like to load the pointers atoimcally, + * but that is not possible (without expensive cmpxchg8b) on PAE. What + * we do have is the guarantee that a pte will only either go from not + * present to present, or present to not present or both -- it will not + * switch to a completely different present page without a TLB flush in + * between; something that we are blocking by holding interrupts off. + * + * Setting ptes from not present to present goes: + * ptep->pte_high = h; + * smp_wmb(); + * ptep->pte_low = l; + * + * And present to not present goes: + * ptep->pte_low = 0; + * smp_wmb(); + * ptep->pte_high = 0; + * + * We must ensure here that the load of pte_low sees l iff pte_high + * sees h. We load pte_high *after* loading pte_low, which ensures we + * don't see an older value of pte_high. *Then* we recheck pte_low, + * which ensures that we haven't picked up a changed pte high. We might + * have got rubbish values from pte_low and pte_high, but we are + * guaranteed that pte_low will not have the present bit set *unless* + * it is 'l'. And get_user_pages_fast only operates on present ptes, so + * we're safe. + * + * gup_get_pte should not be used or copied outside gup.c without being + * very careful -- it does not atomically load the pte or anything that + * is likely to be useful for you. + */ + pte_t pte; + +retry: + pte.pte_low = ptep->pte_low; + smp_rmb(); + pte.pte_high = ptep->pte_high; + smp_rmb(); + if (unlikely(pte.pte_low != ptep->pte_low)) + goto retry; + + return pte; +#endif +} + +/* + * The performance critical leaf functions are made noinline otherwise gcc + * inlines everything into a single function which results in too much + * register pressure. + */ +static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + unsigned long mask; + pte_t *ptep; + + mask = _PAGE_PRESENT|_PAGE_USER; + if (write) + mask |= _PAGE_RW; + + ptep = pte_offset_map(&pmd, addr); + do { + pte_t pte = gup_get_pte(ptep); + struct page *page; + + if ((pte_val(pte) & (mask | _PAGE_SPECIAL)) != mask) { + pte_unmap(ptep); + return 0; + } + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + page = pte_page(pte); + get_page(page); + pages[*nr] = page; + (*nr)++; + + } while (ptep++, addr += PAGE_SIZE, addr != end); + pte_unmap(ptep - 1); + + return 1; +} + +static inline void get_head_page_multiple(struct page *page, int nr) +{ + VM_BUG_ON(page != compound_head(page)); + VM_BUG_ON(page_count(page) == 0); + atomic_add(nr, &page->_count); +} + +static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + unsigned long mask; + pte_t pte = *(pte_t *)&pmd; + struct page *head, *page; + int refs; + + mask = _PAGE_PRESENT|_PAGE_USER; + if (write) + mask |= _PAGE_RW; + if ((pte_val(pte) & mask) != mask) + return 0; + /* hugepages are never "special" */ + VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL); + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + + refs = 0; + head = pte_page(pte); + page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + do { + VM_BUG_ON(compound_head(page) != head); + pages[*nr] = page; + (*nr)++; + page++; + refs++; + } while (addr += PAGE_SIZE, addr != end); + get_head_page_multiple(head, refs); + + return 1; +} + +static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + pmd_t *pmdp; + + pmdp = pmd_offset(&pud, addr); + do { + pmd_t pmd = *pmdp; + + next = pmd_addr_end(addr, end); + if (pmd_none(pmd)) + return 0; + if (unlikely(pmd_large(pmd))) { + if (!gup_huge_pmd(pmd, addr, next, write, pages, nr)) + return 0; + } else { + if (!gup_pte_range(pmd, addr, next, write, pages, nr)) + return 0; + } + } while (pmdp++, addr = next, addr != end); + + return 1; +} + +static noinline int gup_huge_pud(pud_t pud, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + unsigned long mask; + pte_t pte = *(pte_t *)&pud; + struct page *head, *page; + int refs; + + mask = _PAGE_PRESENT|_PAGE_USER; + if (write) + mask |= _PAGE_RW; + if ((pte_val(pte) & mask) != mask) + return 0; + /* hugepages are never "special" */ + VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL); + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + + refs = 0; + head = pte_page(pte); + page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + do { + VM_BUG_ON(compound_head(page) != head); + pages[*nr] = page; + (*nr)++; + page++; + refs++; + } while (addr += PAGE_SIZE, addr != end); + get_head_page_multiple(head, refs); + + return 1; +} + +static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + pud_t *pudp; + + pudp = pud_offset(&pgd, addr); + do { + pud_t pud = *pudp; + + next = pud_addr_end(addr, end); + if (pud_none(pud)) + return 0; + if (unlikely(pud_large(pud))) { + if (!gup_huge_pud(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); + + return 1; +} + +int get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages) +{ + struct mm_struct *mm = current->mm; + unsigned long end = start + (nr_pages << PAGE_SHIFT); + unsigned long addr = start; + unsigned long next; + pgd_t *pgdp; + int nr = 0; + + if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ, + start, nr_pages*PAGE_SIZE))) + goto slow_irqon; + + /* + * XXX: batch / limit 'nr', to avoid large irq off latency + * needs some instrumenting to determine the common sizes used by + * important workloads (eg. DB2), and whether limiting the batch size + * will decrease performance. + * + * It seems like we're in the clear for the moment. Direct-IO is + * the main guy that batches up lots of get_user_pages, and even + * they are limited to 64-at-a-time which is not so many. + */ + /* + * This doesn't prevent pagetable teardown, but does prevent + * the pagetables and pages from being freed on x86. + * + * So long as we atomically load page table pointers versus teardown + * (which we do on x86, with the above PAE exception), we can follow the + * address down to the the page and take a ref on it. + */ + local_irq_disable(); + pgdp = pgd_offset(mm, addr); + do { + pgd_t pgd = *pgdp; + + next = pgd_addr_end(addr, end); + if (pgd_none(pgd)) + goto slow; + if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + goto slow; + } while (pgdp++, addr = next, addr != end); + local_irq_enable(); + + VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); + return nr; + + { + int ret; + +slow: + local_irq_enable(); +slow_irqon: + /* Try to get the remaining pages with get_user_pages */ + start += nr << PAGE_SHIFT; + pages += nr; + + down_read(&mm->mmap_sem); + ret = get_user_pages(current, mm, start, + (end - start) >> PAGE_SHIFT, write, 0, pages, NULL); + up_read(&mm->mmap_sem); + + /* Have to be a bit careful with return values */ + if (nr > 0) { + if (ret < 0) + ret = nr; + else + ret += nr; + } + + return ret; + } +} diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 0b3d567e686..8f307d914c2 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -124,7 +124,8 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) return 1; } -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) { pgd_t *pgd; pud_t *pud; @@ -133,9 +134,14 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) pgd = pgd_offset(mm, addr); pud = pud_alloc(mm, pgd, addr); if (pud) { - if (pud_none(*pud)) - huge_pmd_share(mm, addr, pud); - pte = (pte_t *) pmd_alloc(mm, pud, addr); + if (sz == PUD_SIZE) { + pte = (pte_t *)pud; + } else { + BUG_ON(sz != PMD_SIZE); + if (pud_none(*pud)) + huge_pmd_share(mm, addr, pud); + pte = (pte_t *) pmd_alloc(mm, pud, addr); + } } BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte)); @@ -151,8 +157,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) pgd = pgd_offset(mm, addr); if (pgd_present(*pgd)) { pud = pud_offset(pgd, addr); - if (pud_present(*pud)) + if (pud_present(*pud)) { + if (pud_large(*pud)) + return (pte_t *)pud; pmd = pmd_offset(pud, addr); + } } return (pte_t *) pmd; } @@ -188,6 +197,11 @@ int pmd_huge(pmd_t pmd) return 0; } +int pud_huge(pud_t pud) +{ + return 0; +} + struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) @@ -208,6 +222,11 @@ int pmd_huge(pmd_t pmd) return !!(pmd_val(pmd) & _PAGE_PSE); } +int pud_huge(pud_t pud) +{ + return !!(pud_val(pud) & _PAGE_PSE); +} + struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) @@ -216,9 +235,22 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, page = pte_page(*(pte_t *)pmd); if (page) - page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT); + page += ((address & ~PMD_MASK) >> PAGE_SHIFT); + return page; +} + +struct page * +follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int write) +{ + struct page *page; + + page = pte_page(*(pte_t *)pud); + if (page) + page += ((address & ~PUD_MASK) >> PAGE_SHIFT); return page; } + #endif /* x86_64 also uses this file */ @@ -228,6 +260,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { + struct hstate *h = hstate_file(file); struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long start_addr; @@ -240,7 +273,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, } full_search: - addr = ALIGN(start_addr, HPAGE_SIZE); + addr = ALIGN(start_addr, huge_page_size(h)); for (vma = find_vma(mm, addr); ; vma = vma->vm_next) { /* At this point: (!vma || addr < vma->vm_end). */ @@ -262,7 +295,7 @@ full_search: } if (addr + mm->cached_hole_size < vma->vm_start) mm->cached_hole_size = vma->vm_start - addr; - addr = ALIGN(vma->vm_end, HPAGE_SIZE); + addr = ALIGN(vma->vm_end, huge_page_size(h)); } } @@ -270,6 +303,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr0, unsigned long len, unsigned long pgoff, unsigned long flags) { + struct hstate *h = hstate_file(file); struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev_vma; unsigned long base = mm->mmap_base, addr = addr0; @@ -290,7 +324,7 @@ try_again: goto fail; /* either no address requested or cant fit in requested address hole */ - addr = (mm->free_area_cache - len) & HPAGE_MASK; + addr = (mm->free_area_cache - len) & huge_page_mask(h); do { /* * Lookup failure means no vma is above this address, @@ -321,7 +355,7 @@ try_again: largest_hole = vma->vm_start - addr; /* try just below the current vma->vm_start */ - addr = (vma->vm_start - len) & HPAGE_MASK; + addr = (vma->vm_start - len) & huge_page_mask(h); } while (len <= vma->vm_start); fail: @@ -359,22 +393,23 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { + struct hstate *h = hstate_file(file); struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - if (len & ~HPAGE_MASK) + if (len & ~huge_page_mask(h)) return -EINVAL; if (len > TASK_SIZE) return -ENOMEM; if (flags & MAP_FIXED) { - if (prepare_hugepage_range(addr, len)) + if (prepare_hugepage_range(file, addr, len)) return -EINVAL; return addr; } if (addr) { - addr = ALIGN(addr, HPAGE_SIZE); + addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && (!vma || addr + len <= vma->vm_start)) @@ -390,3 +425,20 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, #endif /*HAVE_ARCH_HUGETLB_UNMAPPED_AREA*/ +#ifdef CONFIG_X86_64 +static __init int setup_hugepagesz(char *opt) +{ + unsigned long ps = memparse(opt, &opt); + if (ps == PMD_SIZE) { + hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); + } else if (ps == PUD_SIZE && cpu_has_gbpages) { + hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); + } else { + printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n", + ps >> 20); + return 0; + } + return 1; +} +__setup("hugepagesz=", setup_hugepagesz); +#endif diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 9689a5138e6..d37f29376b0 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -844,6 +844,9 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, reserve_early(table_start << PAGE_SHIFT, table_end << PAGE_SHIFT, "PGTABLE"); + if (!after_init_bootmem) + early_memtest(start, end); + return end >> PAGE_SHIFT; } @@ -868,8 +871,6 @@ void __init paging_init(void) */ sparse_init(); zone_sizes_init(); - - paravirt_post_allocator_init(); } /* diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 306049edd55..129618ca0ea 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -86,43 +86,6 @@ early_param("gbpages", parse_direct_gbpages_on); * around without checking the pgd every time. */ -void show_mem(void) -{ - long i, total = 0, reserved = 0; - long shared = 0, cached = 0; - struct page *page; - pg_data_t *pgdat; - - printk(KERN_INFO "Mem-info:\n"); - show_free_areas(); - 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 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)) - reserved++; - else if (PageSwapCache(page)) - 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); -} - int after_bootmem; static __init void *spp_getpage(void) @@ -517,118 +480,6 @@ static void __init init_gbpages(void) direct_gbpages = 0; } -#ifdef CONFIG_MEMTEST - -static void __init memtest(unsigned long start_phys, unsigned long size, - unsigned pattern) -{ - unsigned long i; - unsigned long *start; - unsigned long start_bad; - unsigned long last_bad; - unsigned long val; - unsigned long start_phys_aligned; - unsigned long count; - unsigned long incr; - - switch (pattern) { - case 0: - val = 0UL; - break; - case 1: - val = -1UL; - break; - case 2: - val = 0x5555555555555555UL; - break; - case 3: - val = 0xaaaaaaaaaaaaaaaaUL; - break; - default: - return; - } - - incr = sizeof(unsigned long); - start_phys_aligned = ALIGN(start_phys, incr); - count = (size - (start_phys_aligned - start_phys))/incr; - start = __va(start_phys_aligned); - start_bad = 0; - last_bad = 0; - - for (i = 0; i < count; i++) - start[i] = val; - for (i = 0; i < count; i++, start++, start_phys_aligned += incr) { - if (*start != val) { - if (start_phys_aligned == last_bad + incr) { - last_bad += incr; - } else { - if (start_bad) { - printk(KERN_CONT "\n %016lx bad mem addr %016lx - %016lx reserved", - val, start_bad, last_bad + incr); - reserve_early(start_bad, last_bad - start_bad, "BAD RAM"); - } - start_bad = last_bad = start_phys_aligned; - } - } - } - if (start_bad) { - printk(KERN_CONT "\n %016lx bad mem addr %016lx - %016lx reserved", - val, start_bad, last_bad + incr); - reserve_early(start_bad, last_bad - start_bad, "BAD RAM"); - } - -} - -/* default is disabled */ -static int memtest_pattern __initdata; - -static int __init parse_memtest(char *arg) -{ - if (arg) - memtest_pattern = simple_strtoul(arg, NULL, 0); - return 0; -} - -early_param("memtest", parse_memtest); - -static void __init early_memtest(unsigned long start, unsigned long end) -{ - u64 t_start, t_size; - unsigned pattern; - - if (!memtest_pattern) - return; - - printk(KERN_INFO "early_memtest: pattern num %d", memtest_pattern); - for (pattern = 0; pattern < memtest_pattern; pattern++) { - t_start = start; - t_size = 0; - while (t_start < end) { - t_start = find_e820_area_size(t_start, &t_size, 1); - - /* done ? */ - if (t_start >= end) - break; - if (t_start + t_size > end) - t_size = end - t_start; - - printk(KERN_CONT "\n %016llx - %016llx pattern %d", - (unsigned long long)t_start, - (unsigned long long)t_start + t_size, pattern); - - memtest(t_start, t_size, pattern); - - t_start += t_size; - } - } - printk(KERN_CONT "\n"); -} -#else -static void __init early_memtest(unsigned long start, unsigned long end) -{ -} -#endif - static unsigned long __init kernel_physical_mapping_init(unsigned long start, unsigned long end, unsigned long page_size_mask) diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 24c1d3c3018..016f335bbee 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -330,6 +330,14 @@ static void __iomem *ioremap_default(resource_size_t phys_addr, return (void __iomem *)ret; } +void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size, + unsigned long prot_val) +{ + return __ioremap_caller(phys_addr, size, (prot_val & _PAGE_CACHE_MASK), + __builtin_return_address(0)); +} +EXPORT_SYMBOL(ioremap_prot); + /** * iounmap - Free a IO remapping * @addr: virtual address from ioremap_* diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c new file mode 100644 index 00000000000..672e17f8262 --- /dev/null +++ b/arch/x86/mm/memtest.c @@ -0,0 +1,123 @@ +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/init.h> +#include <linux/pfn.h> + +#include <asm/e820.h> + +static void __init memtest(unsigned long start_phys, unsigned long size, + unsigned pattern) +{ + unsigned long i; + unsigned long *start; + unsigned long start_bad; + unsigned long last_bad; + unsigned long val; + unsigned long start_phys_aligned; + unsigned long count; + unsigned long incr; + + switch (pattern) { + case 0: + val = 0UL; + break; + case 1: + val = -1UL; + break; + case 2: +#ifdef CONFIG_X86_64 + val = 0x5555555555555555UL; +#else + val = 0x55555555UL; +#endif + break; + case 3: +#ifdef CONFIG_X86_64 + val = 0xaaaaaaaaaaaaaaaaUL; +#else + val = 0xaaaaaaaaUL; +#endif + break; + default: + return; + } + + incr = sizeof(unsigned long); + start_phys_aligned = ALIGN(start_phys, incr); + count = (size - (start_phys_aligned - start_phys))/incr; + start = __va(start_phys_aligned); + start_bad = 0; + last_bad = 0; + + for (i = 0; i < count; i++) + start[i] = val; + for (i = 0; i < count; i++, start++, start_phys_aligned += incr) { + if (*start != val) { + if (start_phys_aligned == last_bad + incr) { + last_bad += incr; + } else { + if (start_bad) { + printk(KERN_CONT "\n %010lx bad mem addr %010lx - %010lx reserved", + val, start_bad, last_bad + incr); + reserve_early(start_bad, last_bad - start_bad, "BAD RAM"); + } + start_bad = last_bad = start_phys_aligned; + } + } + } + if (start_bad) { + printk(KERN_CONT "\n %016lx bad mem addr %010lx - %010lx reserved", + val, start_bad, last_bad + incr); + reserve_early(start_bad, last_bad - start_bad, "BAD RAM"); + } + +} + +/* default is disabled */ +static int memtest_pattern __initdata; + +static int __init parse_memtest(char *arg) +{ + if (arg) + memtest_pattern = simple_strtoul(arg, NULL, 0); + return 0; +} + +early_param("memtest", parse_memtest); + +void __init early_memtest(unsigned long start, unsigned long end) +{ + u64 t_start, t_size; + unsigned pattern; + + if (!memtest_pattern) + return; + + printk(KERN_INFO "early_memtest: pattern num %d", memtest_pattern); + for (pattern = 0; pattern < memtest_pattern; pattern++) { + t_start = start; + t_size = 0; + while (t_start < end) { + t_start = find_e820_area_size(t_start, &t_size, 1); + + /* done ? */ + if (t_start >= end) + break; + if (t_start + t_size > end) + t_size = end - t_start; + + printk(KERN_CONT "\n %010llx - %010llx pattern %d", + (unsigned long long)t_start, + (unsigned long long)t_start + t_size, pattern); + + memtest(t_start, t_size, pattern); + + t_start += t_size; + } + } + printk(KERN_CONT "\n"); +} diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index b432d578177..a4dd793d600 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -20,15 +20,9 @@ #include <asm/acpi.h> #include <asm/k8.h> -#ifndef Dprintk -#define Dprintk(x...) -#endif - struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); -static bootmem_data_t plat_node_bdata[MAX_NUMNODES]; - struct memnode memnode; s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = { @@ -202,7 +196,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, nodedata_phys + pgdat_size - 1); memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t)); - NODE_DATA(nodeid)->bdata = &plat_node_bdata[nodeid]; + NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid]; NODE_DATA(nodeid)->node_start_pfn = start_pfn; NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn; diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index d4585077977..2fe30916d4b 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -12,6 +12,8 @@ #include <linux/gfp.h> #include <linux/fs.h> #include <linux/bootmem.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> #include <asm/msr.h> #include <asm/tlbflush.h> @@ -373,8 +375,8 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, return vma_prot; } -#ifdef CONFIG_NONPROMISC_DEVMEM -/* This check is done in drivers/char/mem.c in case of NONPROMISC_DEVMEM*/ +#ifdef CONFIG_STRICT_DEVMEM +/* This check is done in drivers/char/mem.c in case of STRICT_DEVMEM*/ static inline int range_is_allowed(unsigned long pfn, unsigned long size) { return 1; @@ -398,7 +400,7 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) } return 1; } -#endif /* CONFIG_NONPROMISC_DEVMEM */ +#endif /* CONFIG_STRICT_DEVMEM */ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot) @@ -489,3 +491,89 @@ void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) free_memtype(addr, addr + size); } + +#if defined(CONFIG_DEBUG_FS) + +/* get Nth element of the linked list */ +static struct memtype *memtype_get_idx(loff_t pos) +{ + struct memtype *list_node, *print_entry; + int i = 1; + + print_entry = kmalloc(sizeof(struct memtype), GFP_KERNEL); + if (!print_entry) + return NULL; + + spin_lock(&memtype_lock); + list_for_each_entry(list_node, &memtype_list, nd) { + if (pos == i) { + *print_entry = *list_node; + spin_unlock(&memtype_lock); + return print_entry; + } + ++i; + } + spin_unlock(&memtype_lock); + kfree(print_entry); + return NULL; +} + +static void *memtype_seq_start(struct seq_file *seq, loff_t *pos) +{ + if (*pos == 0) { + ++*pos; + seq_printf(seq, "PAT memtype list:\n"); + } + + return memtype_get_idx(*pos); +} + +static void *memtype_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + ++*pos; + return memtype_get_idx(*pos); +} + +static void memtype_seq_stop(struct seq_file *seq, void *v) +{ +} + +static int memtype_seq_show(struct seq_file *seq, void *v) +{ + struct memtype *print_entry = (struct memtype *)v; + + seq_printf(seq, "%s @ 0x%Lx-0x%Lx\n", cattr_name(print_entry->type), + print_entry->start, print_entry->end); + kfree(print_entry); + return 0; +} + +static struct seq_operations memtype_seq_ops = { + .start = memtype_seq_start, + .next = memtype_seq_next, + .stop = memtype_seq_stop, + .show = memtype_seq_show, +}; + +static int memtype_seq_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &memtype_seq_ops); +} + +static const struct file_operations memtype_fops = { + .open = memtype_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init pat_memtype_list_init(void) +{ + debugfs_create_file("pat_memtype_list", S_IRUSR, arch_debugfs_dir, + NULL, &memtype_fops); + return 0; +} + +late_initcall(pat_memtype_list_init); + +#endif /* CONFIG_DEBUG_FS */ diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index b4becbf8c57..cab0abbd1eb 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -20,53 +20,6 @@ #include <asm/tlb.h> #include <asm/tlbflush.h> -void show_mem(void) -{ - int total = 0, reserved = 0; - int shared = 0, cached = 0; - int highmem = 0; - struct page *page; - pg_data_t *pgdat; - unsigned long i; - unsigned long flags; - - printk(KERN_INFO "Mem-info:\n"); - show_free_areas(); - for_each_online_pgdat(pgdat) { - pgdat_resize_lock(pgdat, &flags); - for (i = 0; i < pgdat->node_spanned_pages; ++i) { - if (unlikely(i % MAX_ORDER_NR_PAGES == 0)) - touch_nmi_watchdog(); - page = pgdat_page_nr(pgdat, i); - total++; - if (PageHighMem(page)) - highmem++; - if (PageReserved(page)) - reserved++; - else if (PageSwapCache(page)) - cached++; - else if (page_count(page)) - shared += page_count(page) - 1; - } - pgdat_resize_unlock(pgdat, &flags); - } - printk(KERN_INFO "%d pages of RAM\n", total); - printk(KERN_INFO "%d pages of HIGHMEM\n", highmem); - printk(KERN_INFO "%d reserved pages\n", reserved); - printk(KERN_INFO "%d pages shared\n", shared); - printk(KERN_INFO "%d pages swap cached\n", cached); - - printk(KERN_INFO "%lu pages dirty\n", global_page_state(NR_FILE_DIRTY)); - printk(KERN_INFO "%lu pages writeback\n", - global_page_state(NR_WRITEBACK)); - printk(KERN_INFO "%lu pages mapped\n", global_page_state(NR_FILE_MAPPED)); - printk(KERN_INFO "%lu pages slab\n", - global_page_state(NR_SLAB_RECLAIMABLE) + - global_page_state(NR_SLAB_UNRECLAIMABLE)); - printk(KERN_INFO "%lu pages pagetables\n", - global_page_state(NR_PAGETABLE)); -} - /* * Associate a virtual page frame with a given physical page frame * and protection flags for that frame. |