diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Makefile | 8 | ||||
| -rw-r--r-- | mm/bootmem.c | 180 | ||||
| -rw-r--r-- | mm/huge_memory.c | 34 | ||||
| -rw-r--r-- | mm/memory.c | 2 | ||||
| -rw-r--r-- | mm/mempolicy.c | 16 | ||||
| -rw-r--r-- | mm/migrate.c | 6 | ||||
| -rw-r--r-- | mm/mremap.c | 4 | ||||
| -rw-r--r-- | mm/nobootmem.c | 435 | ||||
| -rw-r--r-- | mm/page_alloc.c | 76 | ||||
| -rw-r--r-- | mm/rmap.c | 54 | ||||
| -rw-r--r-- | mm/shmem.c | 13 | ||||
| -rw-r--r-- | mm/swapfile.c | 2 | ||||
| -rw-r--r-- | mm/truncate.c | 2 | ||||
| -rw-r--r-- | mm/vmscan.c | 32 |
14 files changed, 593 insertions, 271 deletions
diff --git a/mm/Makefile b/mm/Makefile index 2b1b575ae712..42a8326c3e3d 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -7,7 +7,7 @@ mmu-$(CONFIG_MMU) := fremap.o highmem.o madvise.o memory.o mincore.o \ mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \ vmalloc.o pagewalk.o pgtable-generic.o -obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \ +obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page_alloc.o page-writeback.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ @@ -15,6 +15,12 @@ obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \ $(mmu-y) obj-y += init-mm.o +ifdef CONFIG_NO_BOOTMEM + obj-y += nobootmem.o +else + obj-y += bootmem.o +endif + obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o obj-$(CONFIG_BOUNCE) += bounce.o diff --git a/mm/bootmem.c b/mm/bootmem.c index 13b0caa9793c..07aeb89e396e 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -23,6 +23,13 @@ #include "internal.h" +#ifndef CONFIG_NEED_MULTIPLE_NODES +struct pglist_data __refdata contig_page_data = { + .bdata = &bootmem_node_data[0] +}; +EXPORT_SYMBOL(contig_page_data); +#endif + unsigned long max_low_pfn; unsigned long min_low_pfn; unsigned long max_pfn; @@ -35,7 +42,6 @@ unsigned long max_pfn; unsigned long saved_max_pfn; #endif -#ifndef CONFIG_NO_BOOTMEM bootmem_data_t bootmem_node_data[MAX_NUMNODES] __initdata; static struct list_head bdata_list __initdata = LIST_HEAD_INIT(bdata_list); @@ -146,7 +152,7 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages) min_low_pfn = start; return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages); } -#endif + /* * free_bootmem_late - free bootmem pages directly to page allocator * @addr: starting address of the range @@ -171,53 +177,6 @@ void __init free_bootmem_late(unsigned long addr, unsigned long size) } } -#ifdef CONFIG_NO_BOOTMEM -static void __init __free_pages_memory(unsigned long start, unsigned long end) -{ - int i; - unsigned long start_aligned, end_aligned; - int order = ilog2(BITS_PER_LONG); - - start_aligned = (start + (BITS_PER_LONG - 1)) & ~(BITS_PER_LONG - 1); - end_aligned = end & ~(BITS_PER_LONG - 1); - - if (end_aligned <= start_aligned) { - for (i = start; i < end; i++) - __free_pages_bootmem(pfn_to_page(i), 0); - - return; - } - - for (i = start; i < start_aligned; i++) - __free_pages_bootmem(pfn_to_page(i), 0); - - for (i = start_aligned; i < end_aligned; i += BITS_PER_LONG) - __free_pages_bootmem(pfn_to_page(i), order); - - for (i = end_aligned; i < end; i++) - __free_pages_bootmem(pfn_to_page(i), 0); -} - -unsigned long __init free_all_memory_core_early(int nodeid) -{ - int i; - u64 start, end; - unsigned long count = 0; - struct range *range = NULL; - int nr_range; - - nr_range = get_free_all_memory_range(&range, nodeid); - - for (i = 0; i < nr_range; i++) { - start = range[i].start; - end = range[i].end; - count += end - start; - __free_pages_memory(start, end); - } - - return count; -} -#else static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) { int aligned; @@ -278,7 +237,6 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) return count; } -#endif /** * free_all_bootmem_node - release a node's free pages to the buddy allocator @@ -289,12 +247,7 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) unsigned long __init free_all_bootmem_node(pg_data_t *pgdat) { register_page_bootmem_info_node(pgdat); -#ifdef CONFIG_NO_BOOTMEM - /* free_all_memory_core_early(MAX_NUMNODES) will be called later */ - return 0; -#else return free_all_bootmem_core(pgdat->bdata); -#endif } /** @@ -304,16 +257,6 @@ unsigned long __init free_all_bootmem_node(pg_data_t *pgdat) */ unsigned long __init free_all_bootmem(void) { -#ifdef CONFIG_NO_BOOTMEM - /* - * We need to use MAX_NUMNODES instead of NODE_DATA(0)->node_id - * because in some case like Node0 doesnt have RAM installed - * low ram will be on Node1 - * Use MAX_NUMNODES will make sure all ranges in early_node_map[] - * will be used instead of only Node0 related - */ - return free_all_memory_core_early(MAX_NUMNODES); -#else unsigned long total_pages = 0; bootmem_data_t *bdata; @@ -321,10 +264,8 @@ unsigned long __init free_all_bootmem(void) total_pages += free_all_bootmem_core(bdata); return total_pages; -#endif } -#ifndef CONFIG_NO_BOOTMEM static void __init __free(bootmem_data_t *bdata, unsigned long sidx, unsigned long eidx) { @@ -419,7 +360,6 @@ static int __init mark_bootmem(unsigned long start, unsigned long end, } BUG(); } -#endif /** * free_bootmem_node - mark a page range as usable @@ -434,10 +374,6 @@ static int __init mark_bootmem(unsigned long start, unsigned long end, void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, unsigned long size) { -#ifdef CONFIG_NO_BOOTMEM - kmemleak_free_part(__va(physaddr), size); - memblock_x86_free_range(physaddr, physaddr + size); -#else unsigned long start, end; kmemleak_free_part(__va(physaddr), size); @@ -446,7 +382,6 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, end = PFN_DOWN(physaddr + size); mark_bootmem_node(pgdat->bdata, start, end, 0, 0); -#endif } /** @@ -460,10 +395,6 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, */ void __init free_bootmem(unsigned long addr, unsigned long size) { -#ifdef CONFIG_NO_BOOTMEM - kmemleak_free_part(__va(addr), size); - memblock_x86_free_range(addr, addr + size); -#else unsigned long start, end; kmemleak_free_part(__va(addr), size); @@ -472,7 +403,6 @@ void __init free_bootmem(unsigned long addr, unsigned long size) end = PFN_DOWN(addr + size); mark_bootmem(start, end, 0, 0); -#endif } /** @@ -489,17 +419,12 @@ void __init free_bootmem(unsigned long addr, unsigned long size) int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, unsigned long size, int flags) { -#ifdef CONFIG_NO_BOOTMEM - panic("no bootmem"); - return 0; -#else unsigned long start, end; start = PFN_DOWN(physaddr); end = PFN_UP(physaddr + size); return mark_bootmem_node(pgdat->bdata, start, end, 1, flags); -#endif } /** @@ -515,20 +440,14 @@ int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, int __init reserve_bootmem(unsigned long addr, unsigned long size, int flags) { -#ifdef CONFIG_NO_BOOTMEM - panic("no bootmem"); - return 0; -#else unsigned long start, end; start = PFN_DOWN(addr); end = PFN_UP(addr + size); return mark_bootmem(start, end, 1, flags); -#endif } -#ifndef CONFIG_NO_BOOTMEM int __weak __init reserve_bootmem_generic(unsigned long phys, unsigned long len, int flags) { @@ -685,33 +604,12 @@ static void * __init alloc_arch_preferred_bootmem(bootmem_data_t *bdata, #endif return NULL; } -#endif static void * __init ___alloc_bootmem_nopanic(unsigned long size, unsigned long align, unsigned long goal, unsigned long limit) { -#ifdef CONFIG_NO_BOOTMEM - void *ptr; - - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc(size, GFP_NOWAIT); - -restart: - - ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, goal, limit); - - if (ptr) - return ptr; - - if (goal != 0) { - goal = 0; - goto restart; - } - - return NULL; -#else bootmem_data_t *bdata; void *region; @@ -737,7 +635,6 @@ restart: } return NULL; -#endif } /** @@ -758,10 +655,6 @@ void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align, { unsigned long limit = 0; -#ifdef CONFIG_NO_BOOTMEM - limit = -1UL; -#endif - return ___alloc_bootmem_nopanic(size, align, goal, limit); } @@ -798,14 +691,9 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align, { unsigned long limit = 0; -#ifdef CONFIG_NO_BOOTMEM - limit = -1UL; -#endif - return ___alloc_bootmem(size, align, goal, limit); } -#ifndef CONFIG_NO_BOOTMEM static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata, unsigned long size, unsigned long align, unsigned long goal, unsigned long limit) @@ -822,7 +710,6 @@ static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata, return ___alloc_bootmem(size, align, goal, limit); } -#endif /** * __alloc_bootmem_node - allocate boot memory from a specific node @@ -842,24 +729,10 @@ static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata, void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal) { - void *ptr; - if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); -#ifdef CONFIG_NO_BOOTMEM - ptr = __alloc_memory_core_early(pgdat->node_id, size, align, - goal, -1ULL); - if (ptr) - return ptr; - - ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, - goal, -1ULL); -#else - ptr = ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0); -#endif - - return ptr; + return ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0); } void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, @@ -880,13 +753,8 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, unsigned long new_goal; new_goal = MAX_DMA32_PFN << PAGE_SHIFT; -#ifdef CONFIG_NO_BOOTMEM - ptr = __alloc_memory_core_early(pgdat->node_id, size, align, - new_goal, -1ULL); -#else ptr = alloc_bootmem_core(pgdat->bdata, size, align, new_goal, 0); -#endif if (ptr) return ptr; } @@ -907,16 +775,6 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, void * __init alloc_bootmem_section(unsigned long size, unsigned long section_nr) { -#ifdef CONFIG_NO_BOOTMEM - unsigned long pfn, goal, limit; - - pfn = section_nr_to_pfn(section_nr); - goal = pfn << PAGE_SHIFT; - limit = section_nr_to_pfn(section_nr + 1) << PAGE_SHIFT; - - return __alloc_memory_core_early(early_pfn_to_nid(pfn), size, - SMP_CACHE_BYTES, goal, limit); -#else bootmem_data_t *bdata; unsigned long pfn, goal, limit; @@ -926,7 +784,6 @@ void * __init alloc_bootmem_section(unsigned long size, bdata = &bootmem_node_data[early_pfn_to_nid(pfn)]; return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, limit); -#endif } #endif @@ -938,16 +795,11 @@ void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); -#ifdef CONFIG_NO_BOOTMEM - ptr = __alloc_memory_core_early(pgdat->node_id, size, align, - goal, -1ULL); -#else ptr = alloc_arch_preferred_bootmem(pgdat->bdata, size, align, goal, 0); if (ptr) return ptr; ptr = alloc_bootmem_core(pgdat->bdata, size, align, goal, 0); -#endif if (ptr) return ptr; @@ -995,21 +847,9 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal) { - void *ptr; - if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); -#ifdef CONFIG_NO_BOOTMEM - ptr = __alloc_memory_core_early(pgdat->node_id, size, align, + return ___alloc_bootmem_node(pgdat->bdata, size, align, goal, ARCH_LOW_ADDRESS_LIMIT); - if (ptr) - return ptr; - ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, - goal, ARCH_LOW_ADDRESS_LIMIT); -#else - ptr = ___alloc_bootmem_node(pgdat->bdata, size, align, - goal, ARCH_LOW_ADDRESS_LIMIT); -#endif - return ptr; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 3e29781ee762..113e35c47502 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -650,10 +650,10 @@ static inline gfp_t alloc_hugepage_gfpmask(int defrag) static inline struct page *alloc_hugepage_vma(int defrag, struct vm_area_struct *vma, - unsigned long haddr) + unsigned long haddr, int nd) { return alloc_pages_vma(alloc_hugepage_gfpmask(defrag), - HPAGE_PMD_ORDER, vma, haddr); + HPAGE_PMD_ORDER, vma, haddr, nd); } #ifndef CONFIG_NUMA @@ -678,7 +678,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(khugepaged_enter(vma))) return VM_FAULT_OOM; page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr); + vma, haddr, numa_node_id()); if (unlikely(!page)) goto out; if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) { @@ -799,8 +799,8 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, } for (i = 0; i < HPAGE_PMD_NR; i++) { - pages[i] = alloc_page_vma(GFP_HIGHUSER_MOVABLE, - vma, address); + pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE, + vma, address, page_to_nid(page)); if (unlikely(!pages[i] || mem_cgroup_newpage_charge(pages[i], mm, GFP_KERNEL))) { @@ -902,7 +902,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, if (transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr); + vma, haddr, numa_node_id()); else new_page = NULL; @@ -1745,7 +1745,8 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, static void collapse_huge_page(struct mm_struct *mm, unsigned long address, struct page **hpage, - struct vm_area_struct *vma) + struct vm_area_struct *vma, + int node) { pgd_t *pgd; pud_t *pud; @@ -1761,6 +1762,10 @@ static void collapse_huge_page(struct mm_struct *mm, #ifndef CONFIG_NUMA VM_BUG_ON(!*hpage); new_page = *hpage; + if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { + up_read(&mm->mmap_sem); + return; + } #else VM_BUG_ON(*hpage); /* @@ -1773,18 +1778,19 @@ static void collapse_huge_page(struct mm_struct *mm, * mmap_sem in read mode is good idea also to allow greater * scalability. */ - new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address); + new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address, + node); if (unlikely(!new_page)) { up_read(&mm->mmap_sem); *hpage = ERR_PTR(-ENOMEM); return; } -#endif if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { up_read(&mm->mmap_sem); put_page(new_page); return; } +#endif /* after allocating the hugepage upgrade to mmap_sem write mode */ up_read(&mm->mmap_sem); @@ -1919,6 +1925,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, struct page *page; unsigned long _address; spinlock_t *ptl; + int node = -1; VM_BUG_ON(address & ~HPAGE_PMD_MASK); @@ -1949,6 +1956,13 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, page = vm_normal_page(vma, _address, pteval); if (unlikely(!page)) goto out_unmap; + /* + * Chose the node of the first page. This could + * be more sophisticated and look at more pages, + * but isn't for now. + */ + if (node == -1) + node = page_to_nid(page); VM_BUG_ON(PageCompound(page)); if (!PageLRU(page) || PageLocked(page) || !PageAnon(page)) goto out_unmap; @@ -1965,7 +1979,7 @@ out_unmap: pte_unmap_unlock(pte, ptl); if (ret) /* collapse_huge_page will return with the mmap_sem released */ - collapse_huge_page(mm, address, hpage, vma); + collapse_huge_page(mm, address, hpage, vma, node); out: return ret; } diff --git a/mm/memory.c b/mm/memory.c index 8e8c18324863..5823698c2b71 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2648,6 +2648,7 @@ void unmap_mapping_range(struct address_space *mapping, details.last_index = ULONG_MAX; details.i_mmap_lock = &mapping->i_mmap_lock; + mutex_lock(&mapping->unmap_mutex); spin_lock(&mapping->i_mmap_lock); /* Protect against endless unmapping loops */ @@ -2664,6 +2665,7 @@ void unmap_mapping_range(struct address_space *mapping, if (unlikely(!list_empty(&mapping->i_mmap_nonlinear))) unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details); spin_unlock(&mapping->i_mmap_lock); + mutex_unlock(&mapping->unmap_mutex); } EXPORT_SYMBOL(unmap_mapping_range); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 368fc9d23610..b53ec99f1428 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1524,10 +1524,9 @@ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) } /* Return a zonelist indicated by gfp for node representing a mempolicy */ -static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy) +static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy, + int nd) { - int nd = numa_node_id(); - switch (policy->mode) { case MPOL_PREFERRED: if (!(policy->flags & MPOL_F_LOCAL)) @@ -1679,7 +1678,7 @@ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, zl = node_zonelist(interleave_nid(*mpol, vma, addr, huge_page_shift(hstate_vma(vma))), gfp_flags); } else { - zl = policy_zonelist(gfp_flags, *mpol); + zl = policy_zonelist(gfp_flags, *mpol, numa_node_id()); if ((*mpol)->mode == MPOL_BIND) *nodemask = &(*mpol)->v.nodes; } @@ -1820,7 +1819,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr) + unsigned long addr, int node) { struct mempolicy *pol = get_vma_policy(current, vma, addr); struct zonelist *zl; @@ -1830,13 +1829,13 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, if (unlikely(pol->mode == MPOL_INTERLEAVE)) { unsigned nid; - nid = interleave_nid(pol, vma, addr, PAGE_SHIFT); + nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); page = alloc_page_interleave(gfp, order, nid); put_mems_allowed(); return page; } - zl = policy_zonelist(gfp, pol); + zl = policy_zonelist(gfp, pol, node); if (unlikely(mpol_needs_cond_ref(pol))) { /* * slow path: ref counted shared policy @@ -1892,7 +1891,8 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order) page = alloc_page_interleave(gfp, order, interleave_nodes(pol)); else page = __alloc_pages_nodemask(gfp, order, - policy_zonelist(gfp, pol), policy_nodemask(gfp, pol)); + policy_zonelist(gfp, pol, numa_node_id()), + policy_nodemask(gfp, pol)); put_mems_allowed(); return page; } diff --git a/mm/migrate.c b/mm/migrate.c index 766115253807..352de555626c 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1287,14 +1287,14 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, return -EPERM; /* Find the mm_struct */ - read_lock(&tasklist_lock); + rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { - read_unlock(&tasklist_lock); + rcu_read_unlock(); return -ESRCH; } mm = get_task_mm(task); - read_unlock(&tasklist_lock); + rcu_read_unlock(); if (!mm) return -EINVAL; diff --git a/mm/mremap.c b/mm/mremap.c index 9925b6391b80..1de98d492ddc 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -94,9 +94,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, */ mapping = vma->vm_file->f_mapping; spin_lock(&mapping->i_mmap_lock); - if (new_vma->vm_truncate_count && - new_vma->vm_truncate_count != vma->vm_truncate_count) - new_vma->vm_truncate_count = 0; + new_vma->vm_truncate_count = 0; } /* diff --git a/mm/nobootmem.c b/mm/nobootmem.c new file mode 100644 index 000000000000..e2bdb07079ce --- /dev/null +++ b/mm/nobootmem.c @@ -0,0 +1,435 @@ +/* + * bootmem - A boot-time physical memory allocator and configurator + * + * Copyright (C) 1999 Ingo Molnar + * 1999 Kanoj Sarcar, SGI + * 2008 Johannes Weiner + * + * Access to this subsystem has to be serialized externally (which is true + * for the boot process anyway). + */ +#include <linux/init.h> +#include <linux/pfn.h> +#include <linux/slab.h> +#include <linux/bootmem.h> +#include <linux/module.h> +#include <linux/kmemleak.h> +#include <linux/range.h> +#include <linux/memblock.h> + +#include <asm/bug.h> +#include <asm/io.h> +#include <asm/processor.h> + +#include "internal.h" + +#ifndef CONFIG_NEED_MULTIPLE_NODES +struct pglist_data __refdata contig_page_data; +EXPORT_SYMBOL(contig_page_data); +#endif + +unsigned long max_low_pfn; +unsigned long min_low_pfn; +unsigned long max_pfn; + +#ifdef CONFIG_CRASH_DUMP +/* + * If we have booted due to a crash, max_pfn will be a very low value. We need + * to know the amount of memory that the previous kernel used. + */ +unsigned long saved_max_pfn; +#endif + +static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, + u64 goal, u64 limit) +{ + void *ptr; + u64 addr; + + if (limit > memblock.current_limit) + limit = memblock.current_limit; + + addr = find_memory_core_early(nid, size, align, goal, limit); + + if (addr == MEMBLOCK_ERROR) + return NULL; + + ptr = phys_to_virt(addr); + memset(ptr, 0, size); + memblock_x86_reserve_range(addr, addr + size, "BOOTMEM"); + /* + * The min_count is set to 0 so that bootmem allocated blocks + * are never reported as leaks. + */ + kmemleak_alloc(ptr, size, 0, 0); + return ptr; +} + +/* + * free_bootmem_late - free bootmem pages directly to page allocator + * @addr: starting address of the range + * @size: size of the range in bytes + * + * This is only useful when the bootmem allocator has already been torn + * down, but we are still initializing the system. Pages are given directly + * to the page allocator, no bootmem metadata is updated because it is gone. + */ +void __init free_bootmem_late(unsigned long addr, unsigned long size) +{ + unsigned long cursor, end; + + kmemleak_free_part(__va(addr), size); + + cursor = PFN_UP(addr); + end = PFN_DOWN(addr + size); + + for (; cursor < end; cursor++) { + __free_pages_bootmem(pfn_to_page(cursor), 0); + totalram_pages++; + } +} + +static void __init __free_pages_memory(unsigned long start, unsigned long end) +{ + int i; + unsigned long start_aligned, end_aligned; + int order = ilog2(BITS_PER_LONG); + + start_aligned = (start + (BITS_PER_LONG - 1)) & ~(BITS_PER_LONG - 1); + end_aligned = end & ~(BITS_PER_LONG - 1); + + if (end_aligned <= start_aligned) { + for (i = start; i < end; i++) + __free_pages_bootmem(pfn_to_page(i), 0); + + return; + } + + for (i = start; i < start_aligned; i++) + __free_pages_bootmem(pfn_to_page(i), 0); + + for (i = start_aligned; i < end_aligned; i += BITS_PER_LONG) + __free_pages_bootmem(pfn_to_page(i), order); + + for (i = end_aligned; i < end; i++) + __free_pages_bootmem(pfn_to_page(i), 0); +} + +unsigned long __init free_all_memory_core_early(int nodeid) +{ + int i; + u64 start, end; + unsigned long count = 0; + struct range *range = NULL; + int nr_range; + + nr_range = get_free_all_memory_range(&range, nodeid); + + for (i = 0; i < nr_range; i++) { + start = range[i].start; + end = range[i].end; + count += end - start; + __free_pages_memory(start, end); + } + + return count; +} + +/** + * free_all_bootmem_node - release a node's free pages to the buddy allocator + * @pgdat: node to be released + * + * Returns the number of pages actually released. + */ +unsigned long __init free_all_bootmem_node(pg_data_t *pgdat) +{ + register_page_bootmem_info_node(pgdat); + + /* free_all_memory_core_early(MAX_NUMNODES) will be called later */ + return 0; +} + +/** + * free_all_bootmem - release free pages to the buddy allocator + * + * Returns the number of pages actually released. + */ +unsigned long __init free_all_bootmem(void) +{ + /* + * We need to use MAX_NUMNODES instead of NODE_DATA(0)->node_id + * because in some case like Node0 doesnt have RAM installed + * low ram will be on Node1 + * Use MAX_NUMNODES will make sure all ranges in early_node_map[] + * will be used instead of only Node0 related + */ + return free_all_memory_core_early(MAX_NUMNODES); +} + +/** + * free_bootmem_node - mark a page range as usable + * @pgdat: node the range resides on + * @physaddr: starting address of the range + * @size: size of the range in bytes + * + * Partial pages will be considered reserved and left as they are. + * + * The range must reside completely on the specified node. + */ +void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, + unsigned long size) +{ + kmemleak_free_part(__va(physaddr), size); + memblock_x86_free_range(physaddr, physaddr + size); +} + +/** + * free_bootmem - mark a page range as usable + * @addr: starting address of the range + * @size: size of the range in bytes + * + * Partial pages will be considered reserved and left as they are. + * + * The range must be contiguous but may span node boundaries. + */ +void __init free_bootmem(unsigned long addr, unsigned long size) +{ + kmemleak_free_part(__va(addr), size); + memblock_x86_free_range(addr, addr + size); +} + +static void * __init ___alloc_bootmem_nopanic(unsigned long size, + unsigned long align, + unsigned long goal, + unsigned long limit) +{ + void *ptr; + + if (WARN_ON_ONCE(slab_is_available())) + return kzalloc(size, GFP_NOWAIT); + +restart: + + ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, goal, limit); + + if (ptr) + return ptr; + + if (goal != 0) { + goal = 0; + goto restart; + } + + return NULL; +} + +/** + * __alloc_bootmem_nopanic - allocate boot memory without panicking + * @size: size of the request in bytes + * @align: alignment of the region + * @goal: preferred starting address of the region + * + * The goal is dropped if it can not be satisfied and the allocation will + * fall back to memory below @goal. + * + * Allocation may happen on any node in the system. + * + * Returns NULL on failure. + */ +void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align, + unsigned long goal) +{ + unsigned long limit = -1UL; + + return ___alloc_bootmem_nopanic(size, align, goal, limit); +} + +static void * __init ___alloc_bootmem(unsigned long size, unsigned long align, + unsigned long goal, unsigned long limit) +{ + void *mem = ___alloc_bootmem_nopanic(size, align, goal, limit); + + if (mem) + return mem; + /* + * Whoops, we cannot satisfy the allocation request. + */ + printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size); + panic("Out of memory"); + return NULL; +} + +/** + * __alloc_bootmem - allocate boot memory + * @size: size of the request in bytes + * @align: alignment of the region + * @goal: preferred starting address of the region + * + * The goal is dropped if it can not be satisfied and the allocation will + * fall back to memory below @goal. + * + * Allocation may happen on any node in the system. + * + * The function panics if the request can not be satisfied. + */ +void * __init __alloc_bootmem(unsigned long size, unsigned long align, + unsigned long goal) +{ + unsigned long limit = -1UL; + + return ___alloc_bootmem(size, align, goal, limit); +} + +/** + * __alloc_bootmem_node - allocate boot memory from a specific node + * @pgdat: node to allocate from + * @size: size of the request in bytes + * @align: alignment of the region + * @goal: preferred starting address of the region + * + * The goal is dropped if it can not be satisfied and the allocation will + * fall back to memory below @goal. + * + * Allocation may fall back to any node in the system if the specified node + * can not hold the requested memory. + * + * The function panics if the request can not be satisfied. + */ +void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, + unsigned long align, unsigned long goal) +{ + void *ptr; + + if (WARN_ON_ONCE(slab_is_available())) + return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); + + ptr = __alloc_memory_core_early(pgdat->node_id, size, align, + goal, -1ULL); + if (ptr) + return ptr; + + return __alloc_memory_core_early(MAX_NUMNODES, size, align, + goal, -1ULL); +} + +void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, + unsigned long align, unsigned long goal) +{ +#ifdef MAX_DMA32_PFN + unsigned long end_pfn; + + if (WARN_ON_ONCE(slab_is_available())) + return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); + + /* update goal according ...MAX_DMA32_PFN */ + end_pfn = pgdat->node_start_pfn + pgdat->node_spanned_pages; + + if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) && + (goal >> PAGE_SHIFT) < MAX_DMA32_PFN) { + void *ptr; + unsigned long new_goal; + + new_goal = MAX_DMA32_PFN << PAGE_SHIFT; + ptr = __alloc_memory_core_early(pgdat->node_id, size, align, + new_goal, -1ULL); + if (ptr) + return ptr; + } +#endif + + return __alloc_bootmem_node(pgdat, size, align, goal); + +} + +#ifdef CONFIG_SPARSEMEM +/** + * alloc_bootmem_section - allocate boot memory from a specific section + * @size: size of the request in bytes + * @section_nr: sparse map section to allocate from + * + * Return NULL on failure. + */ +void * __init alloc_bootmem_section(unsigned long size, + unsigned long section_nr) +{ + unsigned long pfn, goal, limit; + + pfn = section_nr_to_pfn(section_nr); + goal = pfn << PAGE_SHIFT; + limit = section_nr_to_pfn(section_nr + 1) << PAGE_SHIFT; + + return __alloc_memory_core_early(early_pfn_to_nid(pfn), size, + SMP_CACHE_BYTES, goal, limit); +} +#endif + +void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, + unsigned long align, unsigned long goal) +{ + void *ptr; + + if (WARN_ON_ONCE(slab_is_available())) + return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); + + ptr = __alloc_memory_core_early(pgdat->node_id, size, align, + goal, -1ULL); + if (ptr) + return ptr; + + return __alloc_bootmem_nopanic(size, align, goal); +} + +#ifndef ARCH_LOW_ADDRESS_LIMIT +#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL +#endif + +/** + * __alloc_bootmem_low - allocate low boot memory + * @size: size of the request in bytes + * @align: alignment of the region + * @goal: preferred starting address of the region + * + * The goal is dropped if it can not be satisfied and the allocation will + * fall back to memory below @goal. + * + * Allocation may happen on any node in the system. + * + * The function panics if the request can not be satisfied. + */ +void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, + unsigned long goal) +{ + return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT); +} + +/** + * __alloc_bootmem_low_node - allocate low boot memory from a specific node + * @pgdat: node to allocate from + * @size: size of the request in bytes + * @align: alignment of the region + * @goal: preferred starting address of the region + * + * The goal is dropped if it can not be satisfied and the allocation will + * fall back to memory below @goal. + * + * Allocation may fall back to any node in the system if the specified node + * can not hold the requested memory. + * + * The function panics if the request can not be satisfied. + */ +void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size, + unsigned long align, unsigned long goal) +{ + void *ptr; + + if (WARN_ON_ONCE(slab_is_available())) + return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); + + ptr = __alloc_memory_core_early(pgdat->node_id, size, align, + goal, ARCH_LOW_ADDRESS_LIMIT); + if (ptr) + return ptr; + + return __alloc_memory_core_early(MAX_NUMNODES, size, align, + goal, ARCH_LOW_ADDRESS_LIMIT); +} diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a873e61e312e..bd7625676a64 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3699,13 +3699,45 @@ void __init free_bootmem_with_active_regions(int nid, } #ifdef CONFIG_HAVE_MEMBLOCK +/* + * Basic iterator support. Return the last range of PFNs for a node + * Note: nid == MAX_NUMNODES returns last region regardless of node + */ +static int __meminit last_active_region_index_in_nid(int nid) +{ + int i; + + for (i = nr_nodemap_entries - 1; i >= 0; i--) + if (nid == MAX_NUMNODES || early_node_map[i].nid == nid) + return i; + + return -1; +} + +/* + * Basic iterator support. Return the previous active range of PFNs for a node + * Note: nid == MAX_NUMNODES returns next region regardless of node + */ +static int __meminit previous_active_region_index_in_nid(int index, int nid) +{ + for (index = index - 1; index >= 0; index--) + if (nid == MAX_NUMNODES || early_node_map[index].nid == nid) + return index; + + return -1; +} + +#define for_each_active_range_index_in_nid_reverse(i, nid) \ + for (i = last_active_region_index_in_nid(nid); i != -1; \ + i = previous_active_region_index_in_nid(i, nid)) + u64 __init find_memory_core_early(int nid, u64 size, u64 align, u64 goal, u64 limit) { int i; /* Need to go over early_node_map to find out good range for node */ - for_each_active_range_index_in_nid(i, nid) { + for_each_active_range_index_in_nid_reverse(i, nid) { u64 addr; u64 ei_start, ei_last; u64 final_start, final_end; @@ -3748,34 +3780,6 @@ int __init add_from_early_node_map(struct range *range, int az, return nr_range; } -#ifdef CONFIG_NO_BOOTMEM -void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, - u64 goal, u64 limit) -{ - void *ptr; - u64 addr; - - if (limit > memblock.current_limit) - limit = memblock.current_limit; - - addr = find_memory_core_early(nid, size, align, goal, limit); - - if (addr == MEMBLOCK_ERROR) - return NULL; - - ptr = phys_to_virt(addr); - memset(ptr, 0, size); - memblock_x86_reserve_range(addr, addr + size, "BOOTMEM"); - /* - * The min_count is set to 0 so that bootmem allocated blocks - * are never reported as leaks. - */ - kmemleak_alloc(ptr, size, 0, 0); - return ptr; -} -#endif - - void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data) { int i; @@ -4809,15 +4813,6 @@ void __init set_dma_reserve(unsigned long new_dma_reserve) dma_reserve = new_dma_reserve; } -#ifndef CONFIG_NEED_MULTIPLE_NODES -struct pglist_data __refdata contig_page_data = { -#ifndef CONFIG_NO_BOOTMEM - .bdata = &bootmem_node_data[0] -#endif - }; -EXPORT_SYMBOL(contig_page_data); -#endif - void __init free_area_init(unsigned long *zones_size) { free_area_init_node(0, zones_size, @@ -5376,10 +5371,9 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count) for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) { unsigned long check = pfn + iter; - if (!pfn_valid_within(check)) { - iter++; + if (!pfn_valid_within(check)) continue; - } + page = pfn_to_page(check); if (!page_count(page)) { if (PageBuddy(page)) diff --git a/mm/rmap.c b/mm/rmap.c index f21f4a1d6a1c..941bf82e8961 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -497,41 +497,51 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; int referenced = 0; - /* - * Don't want to elevate referenced for mlocked page that gets this far, - * in order that it progresses to try_to_unmap and is moved to the - * unevictable list. - */ - if (vma->vm_flags & VM_LOCKED) { - *mapcount = 0; /* break early from loop */ - *vm_flags |= VM_LOCKED; - goto out; - } - - /* Pretend the page is referenced if the task has the - swap token and is in the middle of a page fault. */ - if (mm != current->mm && has_swap_token(mm) && - rwsem_is_locked(&mm->mmap_sem)) - referenced++; - if (unlikely(PageTransHuge(page))) { pmd_t *pmd; spin_lock(&mm->page_table_lock); + /* + * rmap might return false positives; we must filter + * these out using page_check_address_pmd(). + */ pmd = page_check_address_pmd(page, mm, address, PAGE_CHECK_ADDRESS_PMD_FLAG); - if (pmd && !pmd_trans_splitting(*pmd) && - pmdp_clear_flush_young_notify(vma, address, pmd)) + if (!pmd) { + spin_unlock(&mm->page_table_lock); + goto out; + } + + if (vma->vm_flags & VM_LOCKED) { + spin_unlock(&mm->page_table_lock); + *mapcount = 0; /* break early from loop */ + *vm_flags |= VM_LOCKED; + goto out; + } + + /* go ahead even if the pmd is pmd_trans_splitting() */ + if (pmdp_clear_flush_young_notify(vma, address, pmd)) referenced++; spin_unlock(&mm->page_table_lock); } else { pte_t *pte; spinlock_t *ptl; + /* + * rmap might return false positives; we must filter + * these out using page_check_address(). + */ pte = page_check_address(page, mm, address, &ptl, 0); if (!pte) goto out; + if (vma->vm_flags & VM_LOCKED) { + pte_unmap_unlock(pte, ptl); + *mapcount = 0; /* break early from loop */ + *vm_flags |= VM_LOCKED; + goto out; + } + if (ptep_clear_flush_young_notify(vma, address, pte)) { /* * Don't treat a reference through a sequentially read @@ -546,6 +556,12 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, pte_unmap_unlock(pte, ptl); } + /* Pretend the page is referenced if the task has the + swap token and is in the middle of a page fault. */ + if (mm != current->mm && has_swap_token(mm) && + rwsem_is_locked(&mm->mmap_sem)) + referenced++; + (*mapcount)--; if (referenced) diff --git a/mm/shmem.c b/mm/shmem.c index 5ee67c990602..41f82bb59eec 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1843,8 +1843,9 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE); if (inode) { - error = security_inode_init_security(inode, dir, NULL, NULL, - NULL); + error = security_inode_init_security(inode, dir, + &dentry->d_name, NULL, + NULL, NULL); if (error) { if (error != -EOPNOTSUPP) { iput(inode); @@ -1983,8 +1984,8 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s if (!inode) return -ENOSPC; - error = security_inode_init_security(inode, dir, NULL, NULL, - NULL); + error = security_inode_init_security(inode, dir, &dentry->d_name, NULL, + NULL, NULL); if (error) { if (error != -EOPNOTSUPP) { iput(inode); @@ -2144,8 +2145,10 @@ static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len, { struct inode *inode = dentry->d_inode; - if (*len < 3) + if (*len < 3) { + *len = 3; return 255; + } if (inode_unhashed(inode)) { /* Unfortunately insert_inode_hash is not idempotent, diff --git a/mm/swapfile.c b/mm/swapfile.c index 07a458d72fa8..0341c5700e34 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1940,7 +1940,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = -EINVAL; if (S_ISBLK(inode->i_mode)) { - bdev = I_BDEV(inode); + bdev = bdgrab(I_BDEV(inode)); error = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, sys_swapon); if (error < 0) { diff --git a/mm/truncate.c b/mm/truncate.c index 49feb46e77b8..d64296be00d3 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -225,6 +225,7 @@ void truncate_inode_pages_range(struct address_space *mapping, next = start; while (next <= end && pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) { + mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; pgoff_t page_index = page->index; @@ -247,6 +248,7 @@ void truncate_inode_pages_range(struct address_space *mapping, unlock_page(page); } pagevec_release(&pvec); + mem_cgroup_uncharge_end(); cond_resched(); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 17497d0cd8b9..6771ea70bfe7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1841,16 +1841,28 @@ static inline bool should_continue_reclaim(struct zone *zone, if (!(sc->reclaim_mode & RECLAIM_MODE_COMPACTION)) return false; - /* - * If we failed to reclaim and have scanned the full list, stop. - * NOTE: Checking just nr_reclaimed would exit reclaim/compaction far - * faster but obviously would be less likely to succeed - * allocation. If this is desirable, use GFP_REPEAT to decide - * if both reclaimed and scanned should be checked or just - * reclaimed - */ - if (!nr_reclaimed && !nr_scanned) - return false; + /* Consider stopping depending on scan and reclaim activity */ + if (sc->gfp_mask & __GFP_REPEAT) { + /* + * For __GFP_REPEAT allocations, stop reclaiming if the + * full LRU list has been scanned and we are still failing + * to reclaim pages. This full LRU scan is potentially + * expensive but a __GFP_REPEAT caller really wants to succeed + */ + if (!nr_reclaimed && !nr_scanned) + return false; + } else { + /* + * For non-__GFP_REPEAT allocations which can presumably + * fail without consequence, stop if we failed to reclaim + * any pages from the last SWAP_CLUSTER_MAX number of + * pages that were scanned. This will return to the + * caller faster at the risk reclaim/compaction and + * the resulting allocation attempt fails + */ + if (!nr_reclaimed) + return false; + } /* * If we have not reclaimed enough pages for compaction and the |