diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 4 | ||||
| -rw-r--r-- | mm/allocpercpu.c | 2 | ||||
| -rw-r--r-- | mm/bootmem.c | 6 | ||||
| -rw-r--r-- | mm/memory.c | 83 | ||||
| -rw-r--r-- | mm/mempolicy.c | 6 | ||||
| -rw-r--r-- | mm/migrate.c | 12 | ||||
| -rw-r--r-- | mm/mprotect.c | 10 | ||||
| -rw-r--r-- | mm/page-writeback.c | 10 | ||||
| -rw-r--r-- | mm/page_alloc.c | 95 | ||||
| -rw-r--r-- | mm/slab.c | 5 | ||||
| -rw-r--r-- | mm/slub.c | 23 | ||||
| -rw-r--r-- | mm/sparse-vmemmap.c | 2 |
12 files changed, 205 insertions, 53 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 3aa819d628c..c4de85285bb 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -129,7 +129,7 @@ config MEMORY_HOTPLUG bool "Allow for memory hot-add" depends on SPARSEMEM || X86_64_ACPI_NUMA depends on HOTPLUG && !HIBERNATION && ARCH_ENABLE_MEMORY_HOTPLUG - depends on (IA64 || X86 || PPC64 || SUPERH) + depends on (IA64 || X86 || PPC64 || SUPERH || S390) comment "Memory hotplug is currently incompatible with Software Suspend" depends on SPARSEMEM && HOTPLUG && HIBERNATION @@ -199,7 +199,7 @@ config BOUNCE config NR_QUICK int depends on QUICKLIST - default "2" if SUPERH + default "2" if SUPERH || AVR32 default "1" config VIRT_TO_BUS diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c index f4026bae6ee..05f2b4009cc 100644 --- a/mm/allocpercpu.c +++ b/mm/allocpercpu.c @@ -1,7 +1,7 @@ /* * linux/mm/allocpercpu.c * - * Separated from slab.c August 11, 2006 Christoph Lameter <clameter@sgi.com> + * Separated from slab.c August 11, 2006 Christoph Lameter */ #include <linux/mm.h> #include <linux/module.h> diff --git a/mm/bootmem.c b/mm/bootmem.c index e8fb927392b..8d9f60e06f6 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -442,15 +442,17 @@ unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn, return init_bootmem_core(pgdat, freepfn, startpfn, endpfn); } -void __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, +int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, unsigned long size, int flags) { int ret; ret = can_reserve_bootmem_core(pgdat->bdata, physaddr, size, flags); if (ret < 0) - return; + return -ENOMEM; reserve_bootmem_core(pgdat->bdata, physaddr, size, flags); + + return 0; } void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, diff --git a/mm/memory.c b/mm/memory.c index 19e0ae9beec..2302d228fe0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -999,17 +999,15 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, goto no_page_table; ptep = pte_offset_map_lock(mm, pmd, address, &ptl); - if (!ptep) - goto out; pte = *ptep; if (!pte_present(pte)) - goto unlock; + goto no_page; if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; page = vm_normal_page(vma, address, pte); if (unlikely(!page)) - goto unlock; + goto bad_page; if (flags & FOLL_GET) get_page(page); @@ -1024,6 +1022,15 @@ unlock: out: return page; +bad_page: + pte_unmap_unlock(ptep, ptl); + return ERR_PTR(-EFAULT); + +no_page: + pte_unmap_unlock(ptep, ptl); + if (!pte_none(pte)) + return page; + /* Fall through to ZERO_PAGE handling */ no_page_table: /* * When core dumping an enormous anonymous area that nobody @@ -1038,6 +1045,26 @@ no_page_table: return page; } +/* Can we do the FOLL_ANON optimization? */ +static inline int use_zero_page(struct vm_area_struct *vma) +{ + /* + * We don't want to optimize FOLL_ANON for make_pages_present() + * when it tries to page in a VM_LOCKED region. As to VM_SHARED, + * we want to get the page from the page tables to make sure + * that we serialize and update with any other user of that + * mapping. + */ + if (vma->vm_flags & (VM_LOCKED | VM_SHARED)) + return 0; + /* + * And if we have a fault or a nopfn routine, it's not an + * anonymous region. + */ + return !vma->vm_ops || + (!vma->vm_ops->fault && !vma->vm_ops->nopfn); +} + int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int len, int write, int force, struct page **pages, struct vm_area_struct **vmas) @@ -1112,8 +1139,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, foll_flags = FOLL_TOUCH; if (pages) foll_flags |= FOLL_GET; - if (!write && !(vma->vm_flags & VM_LOCKED) && - (!vma->vm_ops || !vma->vm_ops->fault)) + if (!write && use_zero_page(vma)) foll_flags |= FOLL_ANON; do { @@ -1125,7 +1151,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, * be processed until returning to user space. */ if (unlikely(test_tsk_thread_flag(tsk, TIF_MEMDIE))) - return -ENOMEM; + return i ? i : -ENOMEM; if (write) foll_flags |= FOLL_WRITE; @@ -1159,6 +1185,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, cond_resched(); } + if (IS_ERR(page)) + return i ? i : PTR_ERR(page); if (pages) { pages[i] = page; @@ -1669,8 +1697,19 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page *dirty_page = NULL; old_page = vm_normal_page(vma, address, orig_pte); - if (!old_page) + if (!old_page) { + /* + * VM_MIXEDMAP !pfn_valid() case + * + * We should not cow pages in a shared writeable mapping. + * Just mark the pages writable as we can't do any dirty + * accounting on raw pfn maps. + */ + if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == + (VM_WRITE|VM_SHARED)) + goto reuse; goto gotten; + } /* * Take out anonymous pages first, anonymous shared vmas are @@ -1723,6 +1762,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, } if (reuse) { +reuse: flush_cache_page(vma, address, pte_pfn(orig_pte)); entry = pte_mkyoung(orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); @@ -1757,7 +1797,6 @@ gotten: page_table = pte_offset_map_lock(mm, pmd, address, &ptl); if (likely(pte_same(*page_table, orig_pte))) { if (old_page) { - page_remove_rmap(old_page, vma); if (!PageAnon(old_page)) { dec_mm_counter(mm, file_rss); inc_mm_counter(mm, anon_rss); @@ -1779,6 +1818,32 @@ gotten: lru_cache_add_active(new_page); page_add_new_anon_rmap(new_page, vma, address); + if (old_page) { + /* + * Only after switching the pte to the new page may + * we remove the mapcount here. Otherwise another + * process may come and find the rmap count decremented + * before the pte is switched to the new page, and + * "reuse" the old page writing into it while our pte + * here still points into it and can be read by other + * threads. + * + * The critical issue is to order this + * page_remove_rmap with the ptp_clear_flush above. + * Those stores are ordered by (if nothing else,) + * the barrier present in the atomic_add_negative + * in page_remove_rmap. + * + * Then the TLB flush in ptep_clear_flush ensures that + * no process can access the old page before the + * decremented mapcount is visible. And the old page + * cannot be reused until after the decremented + * mapcount is visible. So transitively, TLBs to + * old page will be flushed before it can be reused. + */ + page_remove_rmap(old_page, vma); + } + /* Free the old page.. */ new_page = old_page; ret |= VM_FAULT_WRITE; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index a37a5034f63..c94e58b192c 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -729,7 +729,11 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, } else { *policy = pol == &default_policy ? MPOL_DEFAULT : pol->mode; - *policy |= pol->flags; + /* + * Internal mempolicy flags must be masked off before exposing + * the policy to userspace. + */ + *policy |= (pol->flags & MPOL_MODE_FLAGS); } if (vma) { diff --git a/mm/migrate.c b/mm/migrate.c index 449d77d409f..55bd355d170 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -9,7 +9,7 @@ * IWAMOTO Toshihiro <iwamoto@valinux.co.jp> * Hirokazu Takahashi <taka@valinux.co.jp> * Dave Hansen <haveblue@us.ibm.com> - * Christoph Lameter <clameter@sgi.com> + * Christoph Lameter */ #include <linux/migrate.h> @@ -865,6 +865,11 @@ static int do_move_pages(struct mm_struct *mm, struct page_to_node *pm, goto set_status; page = follow_page(vma, pp->addr, FOLL_GET); + + err = PTR_ERR(page); + if (IS_ERR(page)) + goto set_status; + err = -ENOENT; if (!page) goto set_status; @@ -928,6 +933,11 @@ static int do_pages_stat(struct mm_struct *mm, struct page_to_node *pm) goto set_status; page = follow_page(vma, pm->addr, 0); + + err = PTR_ERR(page); + if (IS_ERR(page)) + goto set_status; + err = -ENOENT; /* Use PageReserved to check for zero page */ if (!page || PageReserved(page)) diff --git a/mm/mprotect.c b/mm/mprotect.c index a5bf31c2737..acfe7c8d72f 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -47,19 +47,17 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd, if (pte_present(oldpte)) { pte_t ptent; - /* Avoid an SMP race with hardware updated dirty/clean - * bits by wiping the pte and then setting the new pte - * into place. - */ - ptent = ptep_get_and_clear(mm, addr, pte); + ptent = ptep_modify_prot_start(mm, addr, pte); ptent = pte_modify(ptent, newprot); + /* * Avoid taking write faults for pages we know to be * dirty. */ if (dirty_accountable && pte_dirty(ptent)) ptent = pte_mkwrite(ptent); - set_pte_at(mm, addr, pte, ptent); + + ptep_modify_prot_commit(mm, addr, pte, ptent); #ifdef CONFIG_MIGRATION } else if (!pte_file(oldpte)) { swp_entry_t entry = pte_to_swp_entry(oldpte); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 789b6adbef3..b38f700825f 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -126,8 +126,6 @@ static void background_writeout(unsigned long _min_pages); static struct prop_descriptor vm_completions; static struct prop_descriptor vm_dirties; -static unsigned long determine_dirtyable_memory(void); - /* * couple the period to the dirty_ratio: * @@ -347,7 +345,13 @@ static unsigned long highmem_dirtyable_memory(unsigned long total) #endif } -static unsigned long determine_dirtyable_memory(void) +/** + * determine_dirtyable_memory - amount of memory that may be used + * + * Returns the numebr of pages that can currently be freed and used + * by the kernel for direct mappings. + */ +unsigned long determine_dirtyable_memory(void) { unsigned long x; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2f552955a02..f024b9b3a2a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2328,7 +2328,6 @@ static void build_zonelists(pg_data_t *pgdat) static void build_zonelist_cache(pg_data_t *pgdat) { pgdat->node_zonelists[0].zlcache_ptr = NULL; - pgdat->node_zonelists[1].zlcache_ptr = NULL; } #endif /* CONFIG_NUMA */ @@ -2930,6 +2929,18 @@ void __init free_bootmem_with_active_regions(int nid, } } +void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data) +{ + int i; + int ret; + + for_each_active_range_index_in_nid(i, nid) { + ret = work_fn(early_node_map[i].start_pfn, + early_node_map[i].end_pfn, data); + if (ret) + break; + } +} /** * sparse_memory_present_with_active_regions - Call memory_present for each active range * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used. @@ -3462,6 +3473,11 @@ void __paginginit free_area_init_node(int nid, struct pglist_data *pgdat, calculate_node_totalpages(pgdat, zones_size, zholes_size); alloc_node_mem_map(pgdat); +#ifdef CONFIG_FLAT_NODE_MEM_MAP + printk(KERN_DEBUG "free_area_init_node: node %d, pgdat %08lx, node_mem_map %08lx\n", + nid, (unsigned long)pgdat, + (unsigned long)pgdat->node_mem_map); +#endif free_area_init_core(pgdat, zones_size, zholes_size); } @@ -3504,7 +3520,7 @@ void __init add_active_range(unsigned int nid, unsigned long start_pfn, { int i; - printk(KERN_DEBUG "Entering add_active_range(%d, %lu, %lu) " + printk(KERN_DEBUG "Entering add_active_range(%d, %#lx, %#lx) " "%d entries of %d used\n", nid, start_pfn, end_pfn, nr_nodemap_entries, MAX_ACTIVE_REGIONS); @@ -3548,27 +3564,68 @@ void __init add_active_range(unsigned int nid, unsigned long start_pfn, } /** - * shrink_active_range - Shrink an existing registered range of PFNs + * remove_active_range - Shrink an existing registered range of PFNs * @nid: The node id the range is on that should be shrunk - * @old_end_pfn: The old end PFN of the range - * @new_end_pfn: The new PFN of the range + * @start_pfn: The new PFN of the range + * @end_pfn: The new PFN of the range * * i386 with NUMA use alloc_remap() to store a node_mem_map on a local node. - * The map is kept at the end physical page range that has already been - * registered with add_active_range(). This function allows an arch to shrink - * an existing registered range. + * The map is kept near the end physical page range that has already been + * registered. This function allows an arch to shrink an existing registered + * range. */ -void __init shrink_active_range(unsigned int nid, unsigned long old_end_pfn, - unsigned long new_end_pfn) +void __init remove_active_range(unsigned int nid, unsigned long start_pfn, + unsigned long end_pfn) { - int i; + int i, j; + int removed = 0; + + printk(KERN_DEBUG "remove_active_range (%d, %lu, %lu)\n", + nid, start_pfn, end_pfn); /* Find the old active region end and shrink */ - for_each_active_range_index_in_nid(i, nid) - if (early_node_map[i].end_pfn == old_end_pfn) { - early_node_map[i].end_pfn = new_end_pfn; - break; + for_each_active_range_index_in_nid(i, nid) { + if (early_node_map[i].start_pfn >= start_pfn && + early_node_map[i].end_pfn <= end_pfn) { + /* clear it */ + early_node_map[i].start_pfn = 0; + early_node_map[i].end_pfn = 0; + removed = 1; + continue; + } + if (early_node_map[i].start_pfn < start_pfn && + early_node_map[i].end_pfn > start_pfn) { + unsigned long temp_end_pfn = early_node_map[i].end_pfn; + early_node_map[i].end_pfn = start_pfn; + if (temp_end_pfn > end_pfn) + add_active_range(nid, end_pfn, temp_end_pfn); + continue; } + if (early_node_map[i].start_pfn >= start_pfn && + early_node_map[i].end_pfn > end_pfn && + early_node_map[i].start_pfn < end_pfn) { + early_node_map[i].start_pfn = end_pfn; + continue; + } + } + + if (!removed) + return; + + /* remove the blank ones */ + for (i = nr_nodemap_entries - 1; i > 0; i--) { + if (early_node_map[i].nid != nid) + continue; + if (early_node_map[i].end_pfn) + continue; + /* we found it, get rid of it */ + for (j = i; j < nr_nodemap_entries - 1; j++) + memcpy(&early_node_map[j], &early_node_map[j+1], + sizeof(early_node_map[j])); + j = nr_nodemap_entries - 1; + memset(&early_node_map[j], 0, sizeof(early_node_map[j])); + nr_nodemap_entries--; + } } /** @@ -3612,7 +3669,7 @@ static void __init sort_node_map(void) } /* Find the lowest pfn for a node */ -unsigned long __init find_min_pfn_for_node(unsigned long nid) +unsigned long __init find_min_pfn_for_node(int nid) { int i; unsigned long min_pfn = ULONG_MAX; @@ -3623,7 +3680,7 @@ unsigned long __init find_min_pfn_for_node(unsigned long nid) if (min_pfn == ULONG_MAX) { printk(KERN_WARNING - "Could not find start_pfn for node %lu\n", nid); + "Could not find start_pfn for node %d\n", nid); return 0; } @@ -3879,7 +3936,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) for (i = 0; i < MAX_NR_ZONES; i++) { if (i == ZONE_MOVABLE) continue; - printk(" %-8s %8lu -> %8lu\n", + printk(" %-8s %0#10lx -> %0#10lx\n", zone_names[i], arch_zone_lowest_possible_pfn[i], arch_zone_highest_possible_pfn[i]); @@ -3895,7 +3952,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) /* Print out the early_node_map[] */ printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries); for (i = 0; i < nr_nodemap_entries; i++) - printk(" %3d: %8lu -> %8lu\n", early_node_map[i].nid, + printk(" %3d: %0#10lx -> %0#10lx\n", early_node_map[i].nid, early_node_map[i].start_pfn, early_node_map[i].end_pfn); diff --git a/mm/slab.c b/mm/slab.c index 06236e4ddc1..046607f05f3 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3263,9 +3263,12 @@ retry: if (cpuset_zone_allowed_hardwall(zone, flags) && cache->nodelists[nid] && - cache->nodelists[nid]->free_objects) + cache->nodelists[nid]->free_objects) { obj = ____cache_alloc_node(cache, flags | GFP_THISNODE, nid); + if (obj) + break; + } } if (!obj) { diff --git a/mm/slub.c b/mm/slub.c index 0987d1cd943..5f6e2c4a2ba 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5,7 +5,7 @@ * The allocator synchronizes using per slab locks and only * uses a centralized lock to manage a pool of partial slabs. * - * (C) 2007 SGI, Christoph Lameter <clameter@sgi.com> + * (C) 2007 SGI, Christoph Lameter */ #include <linux/mm.h> @@ -431,9 +431,8 @@ static void print_track(const char *s, struct track *t) if (!t->addr) return; - printk(KERN_ERR "INFO: %s in ", s); - __print_symbol("%s", (unsigned long)t->addr); - printk(" age=%lu cpu=%u pid=%d\n", jiffies - t->when, t->cpu, t->pid); + printk(KERN_ERR "INFO: %s in %pS age=%lu cpu=%u pid=%d\n", + s, t->addr, jiffies - t->when, t->cpu, t->pid); } static void print_tracking(struct kmem_cache *s, void *object) @@ -1628,9 +1627,11 @@ static __always_inline void *slab_alloc(struct kmem_cache *s, void **object; struct kmem_cache_cpu *c; unsigned long flags; + unsigned int objsize; local_irq_save(flags); c = get_cpu_slab(s, smp_processor_id()); + objsize = c->objsize; if (unlikely(!c->freelist || !node_match(c, node))) object = __slab_alloc(s, gfpflags, node, addr, c); @@ -1643,7 +1644,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s, local_irq_restore(flags); if (unlikely((gfpflags & __GFP_ZERO) && object)) - memset(object, 0, c->objsize); + memset(object, 0, objsize); return object; } @@ -2995,8 +2996,6 @@ void __init kmem_cache_init(void) create_kmalloc_cache(&kmalloc_caches[1], "kmalloc-96", 96, GFP_KERNEL); caches++; - } - if (KMALLOC_MIN_SIZE <= 128) { create_kmalloc_cache(&kmalloc_caches[2], "kmalloc-192", 192, GFP_KERNEL); caches++; @@ -3026,6 +3025,16 @@ void __init kmem_cache_init(void) for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) size_index[(i - 1) / 8] = KMALLOC_SHIFT_LOW; + if (KMALLOC_MIN_SIZE == 128) { + /* + * The 192 byte sized cache is not used if the alignment + * is 128 byte. Redirect kmalloc to use the 256 byte cache + * instead. + */ + for (i = 128 + 8; i <= 192; i += 8) + size_index[(i - 1) / 8] = 8; + } + slab_state = UP; /* Provide the correct kmalloc names now that the caches are up */ diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 99c4f36eb8a..a91b5f8fcaf 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -1,7 +1,7 @@ /* * Virtual Memory Map support * - * (C) 2007 sgi. Christoph Lameter <clameter@sgi.com>. + * (C) 2007 sgi. Christoph Lameter. * * Virtual memory maps allow VM primitives pfn_to_page, page_to_pfn, * virt_to_page, page_address() to be implemented as a base offset |