diff options
Diffstat (limited to 'mm')
49 files changed, 1158 insertions, 813 deletions
diff --git a/mm/Makefile b/mm/Makefile index 7a68d2ab5560..6c2a73a54a43 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -33,7 +33,11 @@ obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o -obj-$(CONFIG_SMP) += percpu.o +ifdef CONFIG_SMP +obj-y += percpu.o +else +obj-y += percpu_up.o +endif obj-$(CONFIG_QUICKLIST) += quicklist.o obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 0e8ca0347707..660a87a22511 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -11,6 +11,8 @@ #include <linux/writeback.h> #include <linux/device.h> +static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); + void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page) { } @@ -25,6 +27,11 @@ struct backing_dev_info default_backing_dev_info = { }; EXPORT_SYMBOL_GPL(default_backing_dev_info); +struct backing_dev_info noop_backing_dev_info = { + .name = "noop", +}; +EXPORT_SYMBOL_GPL(noop_backing_dev_info); + static struct class *bdi_class; /* @@ -41,7 +48,6 @@ static struct timer_list sync_supers_timer; static int bdi_sync_supers(void *); static void sync_supers_timer_fn(unsigned long); -static void arm_supers_timer(void); static void bdi_add_default_flusher_task(struct backing_dev_info *bdi); @@ -227,6 +233,9 @@ static struct device_attribute bdi_dev_attrs[] = { static __init int bdi_class_init(void) { bdi_class = class_create(THIS_MODULE, "bdi"); + if (IS_ERR(bdi_class)) + return PTR_ERR(bdi_class); + bdi_class->dev_attrs = bdi_dev_attrs; bdi_debug_init(); return 0; @@ -242,7 +251,7 @@ static int __init default_bdi_init(void) init_timer(&sync_supers_timer); setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0); - arm_supers_timer(); + bdi_arm_supers_timer(); err = bdi_init(&default_backing_dev_info); if (!err) @@ -364,10 +373,13 @@ static int bdi_sync_supers(void *unused) return 0; } -static void arm_supers_timer(void) +void bdi_arm_supers_timer(void) { unsigned long next; + if (!dirty_writeback_interval) + return; + next = msecs_to_jiffies(dirty_writeback_interval * 10) + jiffies; mod_timer(&sync_supers_timer, round_jiffies_up(next)); } @@ -375,7 +387,7 @@ static void arm_supers_timer(void) static void sync_supers_timer_fn(unsigned long unused) { wake_up_process(sync_supers_tsk); - arm_supers_timer(); + bdi_arm_supers_timer(); } static int bdi_forker_task(void *ptr) @@ -418,7 +430,10 @@ static int bdi_forker_task(void *ptr) spin_unlock_bh(&bdi_lock); wait = msecs_to_jiffies(dirty_writeback_interval * 10); - schedule_timeout(wait); + if (wait) + schedule_timeout(wait); + else + schedule(); try_to_freeze(); continue; } @@ -712,6 +727,33 @@ void bdi_destroy(struct backing_dev_info *bdi) } EXPORT_SYMBOL(bdi_destroy); +/* + * For use from filesystems to quickly init and register a bdi associated + * with dirty writeback + */ +int bdi_setup_and_register(struct backing_dev_info *bdi, char *name, + unsigned int cap) +{ + char tmp[32]; + int err; + + bdi->name = name; + bdi->capabilities = cap; + err = bdi_init(bdi); + if (err) + return err; + + sprintf(tmp, "%.28s%s", name, "-%d"); + err = bdi_register(bdi, NULL, tmp, atomic_long_inc_return(&bdi_seq)); + if (err) { + bdi_destroy(bdi); + return err; + } + + return 0; +} +EXPORT_SYMBOL(bdi_setup_and_register); + static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) diff --git a/mm/bootmem.c b/mm/bootmem.c index d7c791ef0036..58c66cc5056a 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -10,6 +10,7 @@ */ #include <linux/init.h> #include <linux/pfn.h> +#include <linux/slab.h> #include <linux/bootmem.h> #include <linux/module.h> #include <linux/kmemleak.h> @@ -180,19 +181,12 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end) end_aligned = end & ~(BITS_PER_LONG - 1); if (end_aligned <= start_aligned) { -#if 1 - printk(KERN_DEBUG " %lx - %lx\n", start, end); -#endif for (i = start; i < end; i++) __free_pages_bootmem(pfn_to_page(i), 0); return; } -#if 1 - printk(KERN_DEBUG " %lx %lx - %lx %lx\n", - start, start_aligned, end_aligned, end); -#endif for (i = start; i < start_aligned; i++) __free_pages_bootmem(pfn_to_page(i), 0); @@ -310,9 +304,22 @@ unsigned long __init free_all_bootmem_node(pg_data_t *pgdat) unsigned long __init free_all_bootmem(void) { #ifdef CONFIG_NO_BOOTMEM - return free_all_memory_core_early(NODE_DATA(0)->node_id); + /* + * 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 - return free_all_bootmem_core(NODE_DATA(0)->bdata); + unsigned long total_pages = 0; + bootmem_data_t *bdata; + + list_for_each_entry(bdata, &bdata_list, list) + total_pages += free_all_bootmem_core(bdata); + + return total_pages; #endif } @@ -428,9 +435,6 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, { #ifdef CONFIG_NO_BOOTMEM free_early(physaddr, physaddr + size); -#if 0 - printk(KERN_DEBUG "free %lx %lx\n", physaddr, size); -#endif #else unsigned long start, end; @@ -456,9 +460,6 @@ void __init free_bootmem(unsigned long addr, unsigned long size) { #ifdef CONFIG_NO_BOOTMEM free_early(addr, addr + size); -#if 0 - printk(KERN_DEBUG "free %lx %lx\n", addr, size); -#endif #else unsigned long start, end; diff --git a/mm/bounce.c b/mm/bounce.c index a2b76a588e34..13b6dad1eed2 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -6,6 +6,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/swap.h> +#include <linux/gfp.h> #include <linux/bio.h> #include <linux/pagemap.h> #include <linux/mempool.h> diff --git a/mm/failslab.c b/mm/failslab.c index bb41f98dd8b7..c5f88f240ddc 100644 --- a/mm/failslab.c +++ b/mm/failslab.c @@ -1,5 +1,4 @@ #include <linux/fault-inject.h> -#include <linux/gfp.h> #include <linux/slab.h> static struct { diff --git a/mm/filemap.c b/mm/filemap.c index 045b31c37653..140ebda9640f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -10,13 +10,13 @@ * the NFS filesystem used to do this differently, for example) */ #include <linux/module.h> -#include <linux/slab.h> #include <linux/compiler.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <linux/aio.h> #include <linux/capability.h> #include <linux/kernel_stat.h> +#include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/mman.h> diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 78b94f0b6d5d..83364df74a33 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -17,6 +17,7 @@ #include <linux/sched.h> #include <linux/seqlock.h> #include <linux/mutex.h> +#include <linux/gfp.h> #include <asm/tlbflush.h> #include <asm/io.h> diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3a5aeb37c110..4c9e6bbf3772 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2,7 +2,6 @@ * Generic hugetlb support. * (C) William Irwin, April 2004 */ -#include <linux/gfp.h> #include <linux/list.h> #include <linux/init.h> #include <linux/module.h> @@ -18,6 +17,7 @@ #include <linux/mutex.h> #include <linux/bootmem.h> #include <linux/sysfs.h> +#include <linux/slab.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -546,6 +546,7 @@ static void free_huge_page(struct page *page) mapping = (struct address_space *) page_private(page); set_page_private(page, 0); + page->mapping = NULL; BUG_ON(page_count(page)); INIT_LIST_HEAD(&page->lru); @@ -1038,7 +1039,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, page = alloc_buddy_huge_page(h, vma, addr); if (!page) { hugetlb_put_quota(inode->i_mapping, chg); - return ERR_PTR(-VM_FAULT_OOM); + return ERR_PTR(-VM_FAULT_SIGBUS); } } @@ -2447,8 +2448,10 @@ retry: spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); - } else + } else { lock_page(page); + page->mapping = HUGETLB_POISON; + } } /* diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 5b069e4f5e48..2c0d032ac898 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -72,7 +72,6 @@ #include <linux/module.h> #include <linux/kthread.h> #include <linux/prio_tree.h> -#include <linux/gfp.h> #include <linux/fs.h> #include <linux/debugfs.h> #include <linux/seq_file.h> @@ -365,7 +365,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) do { cond_resched(); page = follow_page(vma, addr, FOLL_GET); - if (!page) + if (IS_ERR_OR_NULL(page)) break; if (PageKsm(page)) ret = handle_mm_fault(vma->vm_mm, vma, addr, @@ -447,7 +447,7 @@ static struct page *get_mergeable_page(struct rmap_item *rmap_item) goto out; page = follow_page(vma, addr, FOLL_GET); - if (!page) + if (IS_ERR_OR_NULL(page)) goto out; if (PageAnon(page)) { flush_anon_page(vma, page, addr); @@ -751,7 +751,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, * page */ if (page_mapcount(page) + 1 + swapped != page_count(page)) { - set_pte_at_notify(mm, addr, ptep, entry); + set_pte_at(mm, addr, ptep, entry); goto out_unlock; } entry = pte_wrprotect(entry); @@ -1086,7 +1086,7 @@ struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item, cond_resched(); tree_rmap_item = rb_entry(*new, struct rmap_item, node); tree_page = get_mergeable_page(tree_rmap_item); - if (!tree_page) + if (IS_ERR_OR_NULL(tree_page)) return NULL; /* @@ -1294,7 +1294,7 @@ next_mm: if (ksm_test_exit(mm)) break; *page = follow_page(vma, ksm_scan.address, FOLL_GET); - if (*page && PageAnon(*page)) { + if (!IS_ERR_OR_NULL(*page) && PageAnon(*page)) { flush_anon_page(vma, *page, ksm_scan.address); flush_dcache_page(*page); rmap_item = get_next_rmap_item(slot, @@ -1308,7 +1308,7 @@ next_mm: up_read(&mm->mmap_sem); return rmap_item; } - if (*page) + if (!IS_ERR_OR_NULL(*page)) put_page(*page); ksm_scan.address += PAGE_SIZE; cond_resched(); @@ -1367,7 +1367,7 @@ next_mm: static void ksm_do_scan(unsigned int scan_npages) { struct rmap_item *rmap_item; - struct page *page; + struct page *uninitialized_var(page); while (scan_npages--) { cond_resched(); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7973b5221fb8..c8569bc298ff 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1359,16 +1359,19 @@ void mem_cgroup_update_file_mapped(struct page *page, int val) lock_page_cgroup(pc); mem = pc->mem_cgroup; - if (!mem) - goto done; - - if (!PageCgroupUsed(pc)) + if (!mem || !PageCgroupUsed(pc)) goto done; /* * Preemption is already disabled. We can use __this_cpu_xxx */ - __this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_FILE_MAPPED], val); + if (val > 0) { + __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); + SetPageCgroupFileMapped(pc); + } else { + __this_cpu_dec(mem->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); + ClearPageCgroupFileMapped(pc); + } done: unlock_page_cgroup(pc); @@ -1435,7 +1438,7 @@ static void drain_local_stock(struct work_struct *dummy) /* * Cache charges(val) which is from res_counter, to local per_cpu area. - * This will be consumed by consumt_stock() function, later. + * This will be consumed by consume_stock() function, later. */ static void refill_stock(struct mem_cgroup *mem, int val) { @@ -1598,7 +1601,6 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, * There is a small race that "from" or "to" can be * freed by rmdir, so we use css_tryget(). */ - rcu_read_lock(); from = mc.from; to = mc.to; if (from && css_tryget(&from->css)) { @@ -1619,7 +1621,6 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, do_continue = (to == mem_over_limit); css_put(&to->css); } - rcu_read_unlock(); if (do_continue) { DEFINE_WAIT(wait); prepare_to_wait(&mc.waitq, &wait, @@ -1801,16 +1802,13 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, static void __mem_cgroup_move_account(struct page_cgroup *pc, struct mem_cgroup *from, struct mem_cgroup *to, bool uncharge) { - struct page *page; - VM_BUG_ON(from == to); VM_BUG_ON(PageLRU(pc->page)); VM_BUG_ON(!PageCgroupLocked(pc)); VM_BUG_ON(!PageCgroupUsed(pc)); VM_BUG_ON(pc->mem_cgroup != from); - page = pc->page; - if (page_mapped(page) && !PageAnon(page)) { + if (PageCgroupFileMapped(pc)) { /* Update mapped_file data for mem_cgroup */ preempt_disable(); __this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); @@ -2429,11 +2427,11 @@ int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr) } unlock_page_cgroup(pc); + *ptr = mem; if (mem) { - ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false); + ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, ptr, false); css_put(&mem->css); } - *ptr = mem; return ret; } @@ -3691,8 +3689,10 @@ static struct mem_cgroup *mem_cgroup_alloc(void) else mem = vmalloc(size); - if (mem) - memset(mem, 0, size); + if (!mem) + return NULL; + + memset(mem, 0, size); mem->stat = alloc_percpu(struct mem_cgroup_stat_cpu); if (!mem->stat) { if (size < PAGE_SIZE) @@ -3946,28 +3946,6 @@ one_by_one: } return ret; } -#else /* !CONFIG_MMU */ -static int mem_cgroup_can_attach(struct cgroup_subsys *ss, - struct cgroup *cgroup, - struct task_struct *p, - bool threadgroup) -{ - return 0; -} -static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss, - struct cgroup *cgroup, - struct task_struct *p, - bool threadgroup) -{ -} -static void mem_cgroup_move_task(struct cgroup_subsys *ss, - struct cgroup *cont, - struct cgroup *old_cont, - struct task_struct *p, - bool threadgroup) -{ -} -#endif /** * is_target_pte_for_mc - check a pte whether it is valid for move charge @@ -4330,6 +4308,28 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss, } mem_cgroup_clear_mc(); } +#else /* !CONFIG_MMU */ +static int mem_cgroup_can_attach(struct cgroup_subsys *ss, + struct cgroup *cgroup, + struct task_struct *p, + bool threadgroup) +{ + return 0; +} +static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss, + struct cgroup *cgroup, + struct task_struct *p, + bool threadgroup) +{ +} +static void mem_cgroup_move_task(struct cgroup_subsys *ss, + struct cgroup *cont, + struct cgroup *old_cont, + struct task_struct *p, + bool threadgroup) +{ +} +#endif struct cgroup_subsys mem_cgroup_subsys = { .name = "memory", diff --git a/mm/memory-failure.c b/mm/memory-failure.c index d1f335162976..620b0b461593 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -44,6 +44,7 @@ #include <linux/migrate.h> #include <linux/page-isolation.h> #include <linux/suspend.h> +#include <linux/slab.h> #include "internal.h" int sysctl_memory_failure_early_kill __read_mostly = 0; diff --git a/mm/memory.c b/mm/memory.c index 5b7f2002e54b..833952d8b74d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -56,6 +56,7 @@ #include <linux/kallsyms.h> #include <linux/swapops.h> #include <linux/elf.h> +#include <linux/gfp.h> #include <asm/io.h> #include <asm/pgalloc.h> @@ -124,7 +125,7 @@ core_initcall(init_zero_pfn); #if defined(SPLIT_RSS_COUNTING) -void __sync_task_rss_stat(struct task_struct *task, struct mm_struct *mm) +static void __sync_task_rss_stat(struct task_struct *task, struct mm_struct *mm) { int i; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 643f66e10187..08f40a2f3fe0 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -73,7 +73,6 @@ #include <linux/sched.h> #include <linux/nodemask.h> #include <linux/cpuset.h> -#include <linux/gfp.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/module.h> @@ -806,9 +805,13 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, err = 0; if (nmask) { - task_lock(current); - get_policy_nodemask(pol, nmask); - task_unlock(current); + if (mpol_store_user_nodemask(pol)) { + *nmask = pol->w.user_nodemask; + } else { + task_lock(current); + get_policy_nodemask(pol, nmask); + task_unlock(current); + } } out: @@ -2195,8 +2198,8 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context) char *rest = nodelist; while (isdigit(*rest)) rest++; - if (!*rest) - err = 0; + if (*rest) + goto out; } break; case MPOL_INTERLEAVE: @@ -2205,7 +2208,6 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context) */ if (!nodelist) nodes = node_states[N_HIGH_MEMORY]; - err = 0; break; case MPOL_LOCAL: /* @@ -2215,11 +2217,19 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context) goto out; mode = MPOL_PREFERRED; break; - - /* - * case MPOL_BIND: mpol_new() enforces non-empty nodemask. - * case MPOL_DEFAULT: mpol_new() enforces empty nodemask, ignores flags. - */ + case MPOL_DEFAULT: + /* + * Insist on a empty nodelist + */ + if (!nodelist) + err = 0; + goto out; + case MPOL_BIND: + /* + * Insist on a nodelist + */ + if (!nodelist) + goto out; } mode_flags = 0; @@ -2233,13 +2243,14 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context) else if (!strcmp(flags, "relative")) mode_flags |= MPOL_F_RELATIVE_NODES; else - err = 1; + goto out; } new = mpol_new(mode, mode_flags, &nodes); if (IS_ERR(new)) - err = 1; - else { + goto out; + + { int ret; NODEMASK_SCRATCH(scratch); if (scratch) { @@ -2250,13 +2261,15 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context) ret = -ENOMEM; NODEMASK_SCRATCH_FREE(scratch); if (ret) { - err = 1; mpol_put(new); - } else if (no_context) { - /* save for contextualization */ - new->w.user_nodemask = nodes; + goto out; } } + err = 0; + if (no_context) { + /* save for contextualization */ + new->w.user_nodemask = nodes; + } out: /* Restore string for error message */ diff --git a/mm/migrate.c b/mm/migrate.c index 88000b89fc9a..d3f3f7f81075 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -32,6 +32,7 @@ #include <linux/security.h> #include <linux/memcontrol.h> #include <linux/syscalls.h> +#include <linux/gfp.h> #include "internal.h" diff --git a/mm/mincore.c b/mm/mincore.c index 7a3436ef39eb..f77433c20279 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -7,8 +7,8 @@ /* * The mincore() system call. */ -#include <linux/slab.h> #include <linux/pagemap.h> +#include <linux/gfp.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/syscalls.h> diff --git a/mm/mlock.c b/mm/mlock.c index 8f4e2dfceec1..3f82720e0515 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -607,44 +607,3 @@ void user_shm_unlock(size_t size, struct user_struct *user) spin_unlock(&shmlock_user_lock); free_uid(user); } - -int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim, - size_t size) -{ - unsigned long lim, vm, pgsz; - int error = -ENOMEM; - - pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT; - - down_write(&mm->mmap_sem); - - lim = ACCESS_ONCE(rlim[RLIMIT_AS].rlim_cur) >> PAGE_SHIFT; - vm = mm->total_vm + pgsz; - if (lim < vm) - goto out; - - lim = ACCESS_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur) >> PAGE_SHIFT; - vm = mm->locked_vm + pgsz; - if (lim < vm) - goto out; - - mm->total_vm += pgsz; - mm->locked_vm += pgsz; - - error = 0; - out: - up_write(&mm->mmap_sem); - return error; -} - -void refund_locked_memory(struct mm_struct *mm, size_t size) -{ - unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT; - - down_write(&mm->mmap_sem); - - mm->total_vm -= pgsz; - mm->locked_vm -= pgsz; - - up_write(&mm->mmap_sem); -} diff --git a/mm/mmap.c b/mm/mmap.c index 75557c639ad4..456ec6f27889 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -507,11 +507,12 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start, struct address_space *mapping = NULL; struct prio_tree_root *root = NULL; struct file *file = vma->vm_file; - struct anon_vma *anon_vma = NULL; long adjust_next = 0; int remove_next = 0; if (next && !insert) { + struct vm_area_struct *exporter = NULL; + if (end >= next->vm_end) { /* * vma expands, overlapping all the next, and @@ -519,7 +520,7 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start, */ again: remove_next = 1 + (end > next->vm_end); end = next->vm_end; - anon_vma = next->anon_vma; + exporter = next; importer = vma; } else if (end > next->vm_start) { /* @@ -527,7 +528,7 @@ again: remove_next = 1 + (end > next->vm_end); * mprotect case 5 shifting the boundary up. */ adjust_next = (end - next->vm_start) >> PAGE_SHIFT; - anon_vma = next->anon_vma; + exporter = next; importer = vma; } else if (end < vma->vm_end) { /* @@ -536,28 +537,19 @@ again: remove_next = 1 + (end > next->vm_end); * mprotect case 4 shifting the boundary down. */ adjust_next = - ((vma->vm_end - end) >> PAGE_SHIFT); - anon_vma = next->anon_vma; + exporter = vma; importer = next; } - } - /* - * When changing only vma->vm_end, we don't really need anon_vma lock. - */ - if (vma->anon_vma && (insert || importer || start != vma->vm_start)) - anon_vma = vma->anon_vma; - if (anon_vma) { /* * Easily overlooked: when mprotect shifts the boundary, * make sure the expanding vma has anon_vma set if the * shrinking vma had, to cover any anon pages imported. */ - if (importer && !importer->anon_vma) { - /* Block reverse map lookups until things are set up. */ - if (anon_vma_clone(importer, vma)) { + if (exporter && exporter->anon_vma && !importer->anon_vma) { + if (anon_vma_clone(importer, exporter)) return -ENOMEM; - } - importer->anon_vma = anon_vma; + importer->anon_vma = exporter->anon_vma; } } @@ -825,6 +817,61 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, } /* + * Rough compatbility check to quickly see if it's even worth looking + * at sharing an anon_vma. + * + * They need to have the same vm_file, and the flags can only differ + * in things that mprotect may change. + * + * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that + * we can merge the two vma's. For example, we refuse to merge a vma if + * there is a vm_ops->close() function, because that indicates that the + * driver is doing some kind of reference counting. But that doesn't + * really matter for the anon_vma sharing case. + */ +static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b) +{ + return a->vm_end == b->vm_start && + mpol_equal(vma_policy(a), vma_policy(b)) && + a->vm_file == b->vm_file && + !((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC)) && + b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); +} + +/* + * Do some basic sanity checking to see if we can re-use the anon_vma + * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be + * the same as 'old', the other will be the new one that is trying + * to share the anon_vma. + * + * NOTE! This runs with mm_sem held for reading, so it is possible that + * the anon_vma of 'old' is concurrently in the process of being set up + * by another page fault trying to merge _that_. But that's ok: if it + * is being set up, that automatically means that it will be a singleton + * acceptable for merging, so we can do all of this optimistically. But + * we do that ACCESS_ONCE() to make sure that we never re-load the pointer. + * + * IOW: that the "list_is_singular()" test on the anon_vma_chain only + * matters for the 'stable anon_vma' case (ie the thing we want to avoid + * is to return an anon_vma that is "complex" due to having gone through + * a fork). + * + * We also make sure that the two vma's are compatible (adjacent, + * and with the same memory policies). That's all stable, even with just + * a read lock on the mm_sem. + */ +static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) +{ + if (anon_vma_compatible(a, b)) { + struct anon_vma *anon_vma = ACCESS_ONCE(old->anon_vma); + + if (anon_vma && list_is_singular(&old->anon_vma_chain)) + return anon_vma; + } + return NULL; +} + +/* * find_mergeable_anon_vma is used by anon_vma_prepare, to check * neighbouring vmas for a suitable anon_vma, before it goes off * to allocate a new anon_vma. It checks because a repetitive @@ -834,28 +881,16 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, */ struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) { + struct anon_vma *anon_vma; struct vm_area_struct *near; - unsigned long vm_flags; near = vma->vm_next; if (!near) goto try_prev; - /* - * Since only mprotect tries to remerge vmas, match flags - * which might be mprotected into each other later on. - * Neither mlock nor madvise tries to remerge at present, - * so leave their flags as obstructing a merge. - */ - vm_flags = vma->vm_flags & ~(VM_READ|VM_WRITE|VM_EXEC); - vm_flags |= near->vm_flags & (VM_READ|VM_WRITE|VM_EXEC); - - if (near->anon_vma && vma->vm_end == near->vm_start && - mpol_equal(vma_policy(vma), vma_policy(near)) && - can_vma_merge_before(near, vm_flags, - NULL, vma->vm_file, vma->vm_pgoff + - ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT))) - return near->anon_vma; + anon_vma = reusable_anon_vma(near, vma, near); + if (anon_vma) + return anon_vma; try_prev: /* * It is potentially slow to have to call find_vma_prev here. @@ -868,14 +903,9 @@ try_prev: if (!near) goto none; - vm_flags = vma->vm_flags & ~(VM_READ|VM_WRITE|VM_EXEC); - vm_flags |= near->vm_flags & (VM_READ|VM_WRITE|VM_EXEC); - - if (near->anon_vma && near->vm_end == vma->vm_start && - mpol_equal(vma_policy(near), vma_policy(vma)) && - can_vma_merge_after(near, vm_flags, - NULL, vma->vm_file, vma->vm_pgoff)) - return near->anon_vma; + anon_vma = reusable_anon_vma(near, near, vma); + if (anon_vma) + return anon_vma; none: /* * There's no absolute need to look only at touching neighbours: @@ -1947,7 +1977,8 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, return 0; /* Clean everything up if vma_adjust failed. */ - new->vm_ops->close(new); + if (new->vm_ops && new->vm_ops->close) + new->vm_ops->close(new); if (new->vm_file) { if (vma->vm_flags & VM_EXECUTABLE) removed_exe_file_vma(mm); diff --git a/mm/mmu_context.c b/mm/mmu_context.c index 0777654147c9..9e82e937000e 100644 --- a/mm/mmu_context.c +++ b/mm/mmu_context.c @@ -53,6 +53,7 @@ void unuse_mm(struct mm_struct *mm) struct task_struct *tsk = current; task_lock(tsk); + sync_mm_rss(tsk, mm); tsk->mm = NULL; /* active_mm is still 'mm' */ enter_lazy_tlb(mm, tsk); diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 7e33f2cb3c77..438951d366f2 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -16,6 +16,7 @@ #include <linux/err.h> #include <linux/rcupdate.h> #include <linux/sched.h> +#include <linux/slab.h> /* * This function can't run concurrently against mmu_notifier_register diff --git a/mm/mprotect.c b/mm/mprotect.c index 8bc969d8112d..2d1bf7cf8851 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -10,7 +10,6 @@ #include <linux/mm.h> #include <linux/hugetlb.h> -#include <linux/slab.h> #include <linux/shm.h> #include <linux/mman.h> #include <linux/fs.h> diff --git a/mm/mremap.c b/mm/mremap.c index e9c75efce609..cde56ee51ef7 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -9,7 +9,6 @@ #include <linux/mm.h> #include <linux/hugetlb.h> -#include <linux/slab.h> #include <linux/shm.h> #include <linux/ksm.h> #include <linux/mman.h> diff --git a/mm/msync.c b/mm/msync.c index 4083209b7f02..632df4527c01 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -82,7 +82,7 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) (vma->vm_flags & VM_SHARED)) { get_file(file); up_read(&mm->mmap_sem); - error = vfs_fsync(file, file->f_path.dentry, 0); + error = vfs_fsync(file, 0); fput(file); if (error || start >= end) goto out; diff --git a/mm/nommu.c b/mm/nommu.c index 605ace8982a8..63fa17d121f0 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -146,7 +146,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); for (i = 0; i < nr_pages; i++) { - vma = find_extend_vma(mm, start); + vma = find_vma(mm, start); if (!vma) goto finish_or_fault; @@ -162,7 +162,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, } if (vmas) vmas[i] = vma; - start += PAGE_SIZE; + start = (start + PAGE_SIZE) & PAGE_MASK; } return i; @@ -764,7 +764,7 @@ EXPORT_SYMBOL(find_vma); */ struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr) { - return find_vma(mm, addr & PAGE_MASK); + return find_vma(mm, addr); } /* @@ -1040,10 +1040,9 @@ static int do_mmap_shared_file(struct vm_area_struct *vma) if (ret != -ENOSYS) return ret; - /* getting an ENOSYS error indicates that direct mmap isn't - * possible (as opposed to tried but failed) so we'll fall - * through to making a private copy of the data and mapping - * that if we can */ + /* getting -ENOSYS indicates that direct mmap isn't possible (as + * opposed to tried but failed) so we can only give a suitable error as + * it's not possible to make a private copy if MAP_SHARED was given */ return -ENODEV; } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 9b223af6a147..b68e802a7a7d 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -18,6 +18,7 @@ #include <linux/oom.h> #include <linux/mm.h> #include <linux/err.h> +#include <linux/gfp.h> #include <linux/sched.h> #include <linux/swap.h> #include <linux/timex.h> diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0b19943ecf8b..b289310e2c89 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -597,7 +597,7 @@ static void balance_dirty_pages(struct address_space *mapping, (!laptop_mode && ((global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS)) > background_thresh))) - bdi_start_writeback(bdi, NULL, 0); + bdi_start_writeback(bdi, NULL, 0, 0); } void set_page_dirty_balance(struct page *page, int page_mkwrite) @@ -683,10 +683,6 @@ void throttle_vm_writeout(gfp_t gfp_mask) } } -static void laptop_timer_fn(unsigned long unused); - -static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0); - /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ @@ -694,24 +690,24 @@ int dirty_writeback_centisecs_handler(ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec(table, write, buffer, length, ppos); + bdi_arm_supers_timer(); return 0; } -static void do_laptop_sync(struct work_struct *work) +#ifdef CONFIG_BLOCK +void laptop_mode_timer_fn(unsigned long data) { - wakeup_flusher_threads(0); - kfree(work); -} + struct request_queue *q = (struct request_queue *)data; + int nr_pages = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS); -static void laptop_timer_fn(unsigned long unused) -{ - struct work_struct *work; + /* + * We want to write everything out, not just down to the dirty + * threshold + */ - work = kmalloc(sizeof(*work), GFP_ATOMIC); - if (work) { - INIT_WORK(work, do_laptop_sync); - schedule_work(work); - } + if (bdi_has_dirty_io(&q->backing_dev_info)) + bdi_start_writeback(&q->backing_dev_info, NULL, nr_pages, 0); } /* @@ -719,9 +715,9 @@ static void laptop_timer_fn(unsigned long unused) * of all dirty data a few seconds from now. If the flush is already scheduled * then push it back - the user is still using the disk. */ -void laptop_io_completion(void) +void laptop_io_completion(struct backing_dev_info *info) { - mod_timer(&laptop_mode_wb_timer, jiffies + laptop_mode); + mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode); } /* @@ -731,8 +727,16 @@ void laptop_io_completion(void) */ void laptop_sync_completion(void) { - del_timer(&laptop_mode_wb_timer); + struct backing_dev_info *bdi; + + rcu_read_lock(); + + list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) + del_timer(&bdi->laptop_mode_wb_timer); + + rcu_read_unlock(); } +#endif /* * If ratelimit_pages is too high then we can get into dirty-data overload diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d03c946d5566..a6326c71b663 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2579,7 +2579,7 @@ static int default_zonelist_order(void) struct zone *z; int average_size; /* - * ZONE_DMA and ZONE_DMA32 can be very small area in the sytem. + * ZONE_DMA and ZONE_DMA32 can be very small area in the system. * If they are really small and used heavily, the system can fall * into OOM very easily. * This function detect ZONE_DMA/DMA32 size and confgigures zone order. diff --git a/mm/page_io.c b/mm/page_io.c index a19af956ee1b..31a3b962230a 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -12,6 +12,7 @@ #include <linux/mm.h> #include <linux/kernel_stat.h> +#include <linux/gfp.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/bio.h> diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 7b47a57b6646..8b1a2ce21ee5 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -80,6 +80,37 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, return err; } +#ifdef CONFIG_HUGETLB_PAGE +static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr, + unsigned long end) +{ + unsigned long boundary = (addr & huge_page_mask(h)) + huge_page_size(h); + return boundary < end ? boundary : end; +} + +static int walk_hugetlb_range(struct vm_area_struct *vma, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct hstate *h = hstate_vma(vma); + unsigned long next; + unsigned long hmask = huge_page_mask(h); + pte_t *pte; + int err = 0; + + do { + next = hugetlb_entry_end(h, addr, end); + pte = huge_pte_offset(walk->mm, addr & hmask); + if (pte && walk->hugetlb_entry) + err = walk->hugetlb_entry(pte, hmask, addr, next, walk); + if (err) + return err; + } while (addr = next, addr != end); + + return 0; +} +#endif + /** * walk_page_range - walk a memory map's page tables with a callback * @mm: memory map to walk @@ -128,20 +159,16 @@ int walk_page_range(unsigned long addr, unsigned long end, vma = find_vma(walk->mm, addr); #ifdef CONFIG_HUGETLB_PAGE if (vma && is_vm_hugetlb_page(vma)) { - pte_t *pte; - struct hstate *hs; - if (vma->vm_end < next) next = vma->vm_end; - hs = hstate_vma(vma); - pte = huge_pte_offset(walk->mm, - addr & huge_page_mask(hs)); - if (pte && !huge_pte_none(huge_ptep_get(pte)) - && walk->hugetlb_entry) - err = walk->hugetlb_entry(pte, addr, - next, walk); + /* + * Hugepage is very tightly coupled with vma, so + * walk through hugetlb entries within a given vma. + */ + err = walk_hugetlb_range(vma, addr, next, walk); if (err) break; + pgd = pgd_offset(walk->mm, next); continue; } #endif diff --git a/mm/percpu-km.c b/mm/percpu-km.c new file mode 100644 index 000000000000..df680855540a --- /dev/null +++ b/mm/percpu-km.c @@ -0,0 +1,104 @@ +/* + * mm/percpu-km.c - kernel memory based chunk allocation + * + * Copyright (C) 2010 SUSE Linux Products GmbH + * Copyright (C) 2010 Tejun Heo <tj@kernel.org> + * + * This file is released under the GPLv2. + * + * Chunks are allocated as a contiguous kernel memory using gfp + * allocation. This is to be used on nommu architectures. + * + * To use percpu-km, + * + * - define CONFIG_NEED_PER_CPU_KM from the arch Kconfig. + * + * - CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK must not be defined. It's + * not compatible with PER_CPU_KM. EMBED_FIRST_CHUNK should work + * fine. + * + * - NUMA is not supported. When setting up the first chunk, + * @cpu_distance_fn should be NULL or report all CPUs to be nearer + * than or at LOCAL_DISTANCE. + * + * - It's best if the chunk size is power of two multiple of + * PAGE_SIZE. Because each chunk is allocated as a contiguous + * kernel memory block using alloc_pages(), memory will be wasted if + * chunk size is not aligned. percpu-km code will whine about it. + */ + +#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK +#error "contiguous percpu allocation is incompatible with paged first chunk" +#endif + +#include <linux/log2.h> + +static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size) +{ + /* noop */ + return 0; +} + +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size) +{ + /* nada */ +} + +static struct pcpu_chunk *pcpu_create_chunk(void) +{ + const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT; + struct pcpu_chunk *chunk; + struct page *pages; + int i; + + chunk = pcpu_alloc_chunk(); + if (!chunk) + return NULL; + + pages = alloc_pages(GFP_KERNEL, order_base_2(nr_pages)); + if (!pages) { + pcpu_free_chunk(chunk); + return NULL; + } + + for (i = 0; i < nr_pages; i++) + pcpu_set_page_chunk(nth_page(pages, i), chunk); + + chunk->data = pages; + chunk->base_addr = page_address(pages) - pcpu_group_offsets[0]; + return chunk; +} + +static void pcpu_destroy_chunk(struct pcpu_chunk *chunk) +{ + const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT; + + if (chunk && chunk->data) + __free_pages(chunk->data, order_base_2(nr_pages)); + pcpu_free_chunk(chunk); +} + +static struct page *pcpu_addr_to_page(void *addr) +{ + return virt_to_page(addr); +} + +static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai) +{ + size_t nr_pages, alloc_pages; + + /* all units must be in a single group */ + if (ai->nr_groups != 1) { + printk(KERN_CRIT "percpu: can't handle more than one groups\n"); + return -EINVAL; + } + + nr_pages = (ai->groups[0].nr_units * ai->unit_size) >> PAGE_SHIFT; + alloc_pages = roundup_pow_of_two(nr_pages); + + if (alloc_pages > nr_pages) + printk(KERN_WARNING "percpu: wasting %zu pages per chunk\n", + alloc_pages - nr_pages); + + return 0; +} diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c new file mode 100644 index 000000000000..7d9c1d0ebd3f --- /dev/null +++ b/mm/percpu-vm.c @@ -0,0 +1,451 @@ +/* + * mm/percpu-vm.c - vmalloc area based chunk allocation + * + * Copyright (C) 2010 SUSE Linux Products GmbH + * Copyright (C) 2010 Tejun Heo <tj@kernel.org> + * + * This file is released under the GPLv2. + * + * Chunks are mapped into vmalloc areas and populated page by page. + * This is the default chunk allocator. + */ + +static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) +{ + /* must not be used on pre-mapped chunk */ + WARN_ON(chunk->immutable); + + return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx)); +} + +/** + * pcpu_get_pages_and_bitmap - get temp pages array and bitmap + * @chunk: chunk of interest + * @bitmapp: output parameter for bitmap + * @may_alloc: may allocate the array + * + * Returns pointer to array of pointers to struct page and bitmap, + * both of which can be indexed with pcpu_page_idx(). The returned + * array is cleared to zero and *@bitmapp is copied from + * @chunk->populated. Note that there is only one array and bitmap + * and access exclusion is the caller's responsibility. + * + * CONTEXT: + * pcpu_alloc_mutex and does GFP_KERNEL allocation if @may_alloc. + * Otherwise, don't care. + * + * RETURNS: + * Pointer to temp pages array on success, NULL on failure. + */ +static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk, + unsigned long **bitmapp, + bool may_alloc) +{ + static struct page **pages; + static unsigned long *bitmap; + size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]); + size_t bitmap_size = BITS_TO_LONGS(pcpu_unit_pages) * + sizeof(unsigned long); + + if (!pages || !bitmap) { + if (may_alloc && !pages) + pages = pcpu_mem_alloc(pages_size); + if (may_alloc && !bitmap) + bitmap = pcpu_mem_alloc(bitmap_size); + if (!pages || !bitmap) + return NULL; + } + + memset(pages, 0, pages_size); + bitmap_copy(bitmap, chunk->populated, pcpu_unit_pages); + + *bitmapp = bitmap; + return pages; +} + +/** + * pcpu_free_pages - free pages which were allocated for @chunk + * @chunk: chunk pages were allocated for + * @pages: array of pages to be freed, indexed by pcpu_page_idx() + * @populated: populated bitmap + * @page_start: page index of the first page to be freed + * @page_end: page index of the last page to be freed + 1 + * + * Free pages [@page_start and @page_end) in @pages for all units. + * The pages were allocated for @chunk. + */ +static void pcpu_free_pages(struct pcpu_chunk *chunk, + struct page **pages, unsigned long *populated, + int page_start, int page_end) +{ + unsigned int cpu; + int i; + + for_each_possible_cpu(cpu) { + for (i = page_start; i < page_end; i++) { + struct page *page = pages[pcpu_page_idx(cpu, i)]; + + if (page) + __free_page(page); + } + } +} + +/** + * pcpu_alloc_pages - allocates pages for @chunk + * @chunk: target chunk + * @pages: array to put the allocated pages into, indexed by pcpu_page_idx() + * @populated: populated bitmap + * @page_start: page index of the first page to be allocated + * @page_end: page index of the last page to be allocated + 1 + * + * Allocate pages [@page_start,@page_end) into @pages for all units. + * The allocation is for @chunk. Percpu core doesn't care about the + * content of @pages and will pass it verbatim to pcpu_map_pages(). + */ +static int pcpu_alloc_pages(struct pcpu_chunk *chunk, + struct page **pages, unsigned long *populated, + int page_start, int page_end) +{ + const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD; + unsigned int cpu; + int i; + + for_each_possible_cpu(cpu) { + for (i = page_start; i < page_end; i++) { + struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; + + *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); + if (!*pagep) { + pcpu_free_pages(chunk, pages, populated, + page_start, page_end); + return -ENOMEM; + } + } + } + return 0; +} + +/** + * pcpu_pre_unmap_flush - flush cache prior to unmapping + * @chunk: chunk the regions to be flushed belongs to + * @page_start: page index of the first page to be flushed + * @page_end: page index of the last page to be flushed + 1 + * + * Pages in [@page_start,@page_end) of @chunk are about to be + * unmapped. Flush cache. As each flushing trial can be very + * expensive, issue flush on the whole region at once rather than + * doing it for each cpu. This could be an overkill but is more + * scalable. + */ +static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk, + int page_start, int page_end) +{ + flush_cache_vunmap( + pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start), + pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end)); +} + +static void __pcpu_unmap_pages(unsigned long addr, int nr_pages) +{ + unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT); +} + +/** + * pcpu_unmap_pages - unmap pages out of a pcpu_chunk + * @chunk: chunk of interest + * @pages: pages array which can be used to pass information to free + * @populated: populated bitmap + * @page_start: page index of the first page to unmap + * @page_end: page index of the last page to unmap + 1 + * + * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. + * Corresponding elements in @pages were cleared by the caller and can + * be used to carry information to pcpu_free_pages() which will be + * called after all unmaps are finished. The caller should call + * proper pre/post flush functions. + */ +static void pcpu_unmap_pages(struct pcpu_chunk *chunk, + struct page **pages, unsigned long *populated, + int page_start, int page_end) +{ + unsigned int cpu; + int i; + + for_each_possible_cpu(cpu) { + for (i = page_start; i < page_end; i++) { + struct page *page; + + page = pcpu_chunk_page(chunk, cpu, i); + WARN_ON(!page); + pages[pcpu_page_idx(cpu, i)] = page; + } + __pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start), + page_end - page_start); + } + + for (i = page_start; i < page_end; i++) + __clear_bit(i, populated); +} + +/** + * pcpu_post_unmap_tlb_flush - flush TLB after unmapping + * @chunk: pcpu_chunk the regions to be flushed belong to + * @page_start: page index of the first page to be flushed + * @page_end: page index of the last page to be flushed + 1 + * + * Pages [@page_start,@page_end) of @chunk have been unmapped. Flush + * TLB for the regions. This can be skipped if the area is to be + * returned to vmalloc as vmalloc will handle TLB flushing lazily. + * + * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once + * for the whole region. + */ +static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, + int page_start, int page_end) +{ + flush_tlb_kernel_range( + pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start), + pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end)); +} + +static int __pcpu_map_pages(unsigned long addr, struct page **pages, + int nr_pages) +{ + return map_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT, + PAGE_KERNEL, pages); +} + +/** + * pcpu_map_pages - map pages into a pcpu_chunk + * @chunk: chunk of interest + * @pages: pages array containing pages to be mapped + * @populated: populated bitmap + * @page_start: page index of the first page to map + * @page_end: page index of the last page to map + 1 + * + * For each cpu, map pages [@page_start,@page_end) into @chunk. The + * caller is responsible for calling pcpu_post_map_flush() after all + * mappings are complete. + * + * This function is responsible for setting corresponding bits in + * @chunk->populated bitmap and whatever is necessary for reverse + * lookup (addr -> chunk). + */ +static int pcpu_map_pages(struct pcpu_chunk *chunk, + struct page **pages, unsigned long *populated, + int page_start, int page_end) +{ + unsigned int cpu, tcpu; + int i, err; + + for_each_possible_cpu(cpu) { + err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start), + &pages[pcpu_page_idx(cpu, page_start)], + page_end - page_start); + if (err < 0) + goto err; + } + + /* mapping successful, link chunk and mark populated */ + for (i = page_start; i < page_end; i++) { + for_each_possible_cpu(cpu) + pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)], + chunk); + __set_bit(i, populated); + } + + return 0; + +err: + for_each_possible_cpu(tcpu) { + if (tcpu == cpu) + break; + __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), + page_end - page_start); + } + return err; +} + +/** + * pcpu_post_map_flush - flush cache after mapping + * @chunk: pcpu_chunk the regions to be flushed belong to + * @page_start: page index of the first page to be flushed + * @page_end: page index of the last page to be flushed + 1 + * + * Pages [@page_start,@page_end) of @chunk have been mapped. Flush + * cache. + * + * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once + * for the whole region. + */ +static void pcpu_post_map_flush(struct pcpu_chunk *chunk, + int page_start, int page_end) +{ + flush_cache_vmap( + pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start), + pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end)); +} + +/** + * pcpu_populate_chunk - populate and map an area of a pcpu_chunk + * @chunk: chunk of interest + * @off: offset to the area to populate + * @size: size of the area to populate in bytes + * + * For each cpu, populate and map pages [@page_start,@page_end) into + * @chunk. The area is cleared on return. + * + * CONTEXT: + * pcpu_alloc_mutex, does GFP_KERNEL allocation. + */ +static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size) +{ + int page_start = PFN_DOWN(off); + int page_end = PFN_UP(off + size); + int free_end = page_start, unmap_end = page_start; + struct page **pages; + unsigned long *populated; + unsigned int cpu; + int rs, re, rc; + + /* quick path, check whether all pages are already there */ + rs = page_start; + pcpu_next_pop(chunk, &rs, &re, page_end); + if (rs == page_start && re == page_end) + goto clear; + + /* need to allocate and map pages, this chunk can't be immutable */ + WARN_ON(chunk->immutable); + + pages = pcpu_get_pages_and_bitmap(chunk, &populated, true); + if (!pages) + return -ENOMEM; + + /* alloc and map */ + pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) { + rc = pcpu_alloc_pages(chunk, pages, populated, rs, re); + if (rc) + goto err_free; + free_end = re; + } + + pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) { + rc = pcpu_map_pages(chunk, pages, populated, rs, re); + if (rc) + goto err_unmap; + unmap_end = re; + } + pcpu_post_map_flush(chunk, page_start, page_end); + + /* commit new bitmap */ + bitmap_copy(chunk->populated, populated, pcpu_unit_pages); +clear: + for_each_possible_cpu(cpu) + memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size); + return 0; + +err_unmap: + pcpu_pre_unmap_flush(chunk, page_start, unmap_end); + pcpu_for_each_unpop_region(chunk, rs, re, page_start, unmap_end) + pcpu_unmap_pages(chunk, pages, populated, rs, re); + pcpu_post_unmap_tlb_flush(chunk, page_start, unmap_end); +err_free: + pcpu_for_each_unpop_region(chunk, rs, re, page_start, free_end) + pcpu_free_pages(chunk, pages, populated, rs, re); + return rc; +} + +/** + * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk + * @chunk: chunk to depopulate + * @off: offset to the area to depopulate + * @size: size of the area to depopulate in bytes + * @flush: whether to flush cache and tlb or not + * + * For each cpu, depopulate and unmap pages [@page_start,@page_end) + * from @chunk. If @flush is true, vcache is flushed before unmapping + * and tlb after. + * + * CONTEXT: + * pcpu_alloc_mutex. + */ +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size) +{ + int page_start = PFN_DOWN(off); + int page_end = PFN_UP(off + size); + struct page **pages; + unsigned long *populated; + int rs, re; + + /* quick path, check whether it's empty already */ + rs = page_start; + pcpu_next_unpop(chunk, &rs, &re, page_end); + if (rs == page_start && re == page_end) + return; + + /* immutable chunks can't be depopulated */ + WARN_ON(chunk->immutable); + + /* + * If control reaches here, there must have been at least one + * successful population attempt so the temp pages array must + * be available now. + */ + pages = pcpu_get_pages_and_bitmap(chunk, &populated, false); + BUG_ON(!pages); + + /* unmap and free */ + pcpu_pre_unmap_flush(chunk, page_start, page_end); + + pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end) + pcpu_unmap_pages(chunk, pages, populated, rs, re); + + /* no need to flush tlb, vmalloc will handle it lazily */ + + pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end) + pcpu_free_pages(chunk, pages, populated, rs, re); + + /* commit new bitmap */ + bitmap_copy(chunk->populated, populated, pcpu_unit_pages); +} + +static struct pcpu_chunk *pcpu_create_chunk(void) +{ + struct pcpu_chunk *chunk; + struct vm_struct **vms; + + chunk = pcpu_alloc_chunk(); + if (!chunk) + return NULL; + + vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, + pcpu_nr_groups, pcpu_atom_size, GFP_KERNEL); + if (!vms) { + pcpu_free_chunk(chunk); + return NULL; + } + + chunk->data = vms; + chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0]; + return chunk; +} + +static void pcpu_destroy_chunk(struct pcpu_chunk *chunk) +{ + if (chunk && chunk->data) + pcpu_free_vm_areas(chunk->data, pcpu_nr_groups); + pcpu_free_chunk(chunk); +} + +static struct page *pcpu_addr_to_page(void *addr) +{ + return vmalloc_to_page(addr); +} + +static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai) +{ + /* no extra restriction */ + return 0; +} diff --git a/mm/percpu.c b/mm/percpu.c index 768419d44ad7..39f7dfd59585 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1,5 +1,5 @@ /* - * linux/mm/percpu.c - percpu memory allocator + * mm/percpu.c - percpu memory allocator * * Copyright (C) 2009 SUSE Linux Products GmbH * Copyright (C) 2009 Tejun Heo <tj@kernel.org> @@ -7,14 +7,13 @@ * This file is released under the GPLv2. * * This is percpu allocator which can handle both static and dynamic - * areas. Percpu areas are allocated in chunks in vmalloc area. Each - * chunk is consisted of boot-time determined number of units and the - * first chunk is used for static percpu variables in the kernel image + * areas. Percpu areas are allocated in chunks. Each chunk is + * consisted of boot-time determined number of units and the first + * chunk is used for static percpu variables in the kernel image * (special boot time alloc/init handling necessary as these areas * need to be brought up before allocation services are running). * Unit grows as necessary and all units grow or shrink in unison. - * When a chunk is filled up, another chunk is allocated. ie. in - * vmalloc area + * When a chunk is filled up, another chunk is allocated. * * c0 c1 c2 * ------------------- ------------------- ------------ @@ -99,7 +98,7 @@ struct pcpu_chunk { int map_used; /* # of map entries used */ int map_alloc; /* # of map entries allocated */ int *map; /* allocation map */ - struct vm_struct **vms; /* mapped vmalloc regions */ + void *data; /* chunk data */ bool immutable; /* no [de]population allowed */ unsigned long populated[]; /* populated bitmap */ }; @@ -177,6 +176,21 @@ static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */ static void pcpu_reclaim(struct work_struct *work); static DECLARE_WORK(pcpu_reclaim_work, pcpu_reclaim); +static bool pcpu_addr_in_first_chunk(void *addr) +{ + void *first_start = pcpu_first_chunk->base_addr; + + return addr >= first_start && addr < first_start + pcpu_unit_size; +} + +static bool pcpu_addr_in_reserved_chunk(void *addr) +{ + void *first_start = pcpu_first_chunk->base_addr; + + return addr >= first_start && + addr < first_start + pcpu_reserved_chunk_limit; +} + static int __pcpu_size_to_slot(int size) { int highbit = fls(size); /* size is in bytes */ @@ -198,27 +212,6 @@ static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) return pcpu_size_to_slot(chunk->free_size); } -static int pcpu_page_idx(unsigned int cpu, int page_idx) -{ - return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx; -} - -static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, - unsigned int cpu, int page_idx) -{ - return (unsigned long)chunk->base_addr + pcpu_unit_offsets[cpu] + - (page_idx << PAGE_SHIFT); -} - -static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, - unsigned int cpu, int page_idx) -{ - /* must not be used on pre-mapped chunk */ - WARN_ON(chunk->immutable); - - return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx)); -} - /* set the pointer to a chunk in a page struct */ static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) { @@ -231,13 +224,27 @@ static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) return (struct pcpu_chunk *)page->index; } -static void pcpu_next_unpop(struct pcpu_chunk *chunk, int *rs, int *re, int end) +static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx) +{ + return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx; +} + +static unsigned long __maybe_unused pcpu_chunk_addr(struct pcpu_chunk *chunk, + unsigned int cpu, int page_idx) +{ + return (unsigned long)chunk->base_addr + pcpu_unit_offsets[cpu] + + (page_idx << PAGE_SHIFT); +} + +static void __maybe_unused pcpu_next_unpop(struct pcpu_chunk *chunk, + int *rs, int *re, int end) { *rs = find_next_zero_bit(chunk->populated, end, *rs); *re = find_next_bit(chunk->populated, end, *rs + 1); } -static void pcpu_next_pop(struct pcpu_chunk *chunk, int *rs, int *re, int end) +static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk, + int *rs, int *re, int end) { *rs = find_next_bit(chunk->populated, end, *rs); *re = find_next_zero_bit(chunk->populated, end, *rs + 1); @@ -326,36 +333,6 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) } /** - * pcpu_chunk_addr_search - determine chunk containing specified address - * @addr: address for which the chunk needs to be determined. - * - * RETURNS: - * The address of the found chunk. - */ -static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) -{ - void *first_start = pcpu_first_chunk->base_addr; - - /* is it in the first chunk? */ - if (addr >= first_start && addr < first_start + pcpu_unit_size) { - /* is it in the reserved area? */ - if (addr < first_start + pcpu_reserved_chunk_limit) - return pcpu_reserved_chunk; - return pcpu_first_chunk; - } - - /* - * The address is relative to unit0 which might be unused and - * thus unmapped. Offset the address to the unit space of the - * current processor before looking it up in the vmalloc - * space. Note that any possible cpu id can be used here, so - * there's no need to worry about preemption or cpu hotplug. - */ - addr += pcpu_unit_offsets[raw_smp_processor_id()]; - return pcpu_get_page_chunk(vmalloc_to_page(addr)); -} - -/** * pcpu_need_to_extend - determine whether chunk area map needs to be extended * @chunk: chunk of interest * @@ -623,434 +600,92 @@ static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme) pcpu_chunk_relocate(chunk, oslot); } -/** - * pcpu_get_pages_and_bitmap - get temp pages array and bitmap - * @chunk: chunk of interest - * @bitmapp: output parameter for bitmap - * @may_alloc: may allocate the array - * - * Returns pointer to array of pointers to struct page and bitmap, - * both of which can be indexed with pcpu_page_idx(). The returned - * array is cleared to zero and *@bitmapp is copied from - * @chunk->populated. Note that there is only one array and bitmap - * and access exclusion is the caller's responsibility. - * - * CONTEXT: - * pcpu_alloc_mutex and does GFP_KERNEL allocation if @may_alloc. - * Otherwise, don't care. - * - * RETURNS: - * Pointer to temp pages array on success, NULL on failure. - */ -static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk, - unsigned long **bitmapp, - bool may_alloc) -{ - static struct page **pages; - static unsigned long *bitmap; - size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]); - size_t bitmap_size = BITS_TO_LONGS(pcpu_unit_pages) * - sizeof(unsigned long); - - if (!pages || !bitmap) { - if (may_alloc && !pages) - pages = pcpu_mem_alloc(pages_size); - if (may_alloc && !bitmap) - bitmap = pcpu_mem_alloc(bitmap_size); - if (!pages || !bitmap) - return NULL; - } - - memset(pages, 0, pages_size); - bitmap_copy(bitmap, chunk->populated, pcpu_unit_pages); - - *bitmapp = bitmap; - return pages; -} - -/** - * pcpu_free_pages - free pages which were allocated for @chunk - * @chunk: chunk pages were allocated for - * @pages: array of pages to be freed, indexed by pcpu_page_idx() - * @populated: populated bitmap - * @page_start: page index of the first page to be freed - * @page_end: page index of the last page to be freed + 1 - * - * Free pages [@page_start and @page_end) in @pages for all units. - * The pages were allocated for @chunk. - */ -static void pcpu_free_pages(struct pcpu_chunk *chunk, - struct page **pages, unsigned long *populated, - int page_start, int page_end) +static struct pcpu_chunk *pcpu_alloc_chunk(void) { - unsigned int cpu; - int i; + struct pcpu_chunk *chunk; - for_each_possible_cpu(cpu) { - for (i = page_start; i < page_end; i++) { - struct page *page = pages[pcpu_page_idx(cpu, i)]; + chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL); + if (!chunk) + return NULL; - if (page) - __free_page(page); - } + chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); + if (!chunk->map) { + kfree(chunk); + return NULL; } -} -/** - * pcpu_alloc_pages - allocates pages for @chunk - * @chunk: target chunk - * @pages: array to put the allocated pages into, indexed by pcpu_page_idx() - * @populated: populated bitmap - * @page_start: page index of the first page to be allocated - * @page_end: page index of the last page to be allocated + 1 - * - * Allocate pages [@page_start,@page_end) into @pages for all units. - * The allocation is for @chunk. Percpu core doesn't care about the - * content of @pages and will pass it verbatim to pcpu_map_pages(). - */ -static int pcpu_alloc_pages(struct pcpu_chunk *chunk, - struct page **pages, unsigned long *populated, - int page_start, int page_end) -{ - const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD; - unsigned int cpu; - int i; + chunk->map_alloc = PCPU_DFL_MAP_ALLOC; + chunk->map[chunk->map_used++] = pcpu_unit_size; - for_each_possible_cpu(cpu) { - for (i = page_start; i < page_end; i++) { - struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; - - *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); - if (!*pagep) { - pcpu_free_pages(chunk, pages, populated, - page_start, page_end); - return -ENOMEM; - } - } - } - return 0; -} + INIT_LIST_HEAD(&chunk->list); + chunk->free_size = pcpu_unit_size; + chunk->contig_hint = pcpu_unit_size; -/** - * pcpu_pre_unmap_flush - flush cache prior to unmapping - * @chunk: chunk the regions to be flushed belongs to - * @page_start: page index of the first page to be flushed - * @page_end: page index of the last page to be flushed + 1 - * - * Pages in [@page_start,@page_end) of @chunk are about to be - * unmapped. Flush cache. As each flushing trial can be very - * expensive, issue flush on the whole region at once rather than - * doing it for each cpu. This could be an overkill but is more - * scalable. - */ -static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk, - int page_start, int page_end) -{ - flush_cache_vunmap( - pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start), - pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end)); + return chunk; } -static void __pcpu_unmap_pages(unsigned long addr, int nr_pages) +static void pcpu_free_chunk(struct pcpu_chunk *chunk) { - unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT); + if (!chunk) + return; + pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0])); + kfree(chunk); } -/** - * pcpu_unmap_pages - unmap pages out of a pcpu_chunk - * @chunk: chunk of interest - * @pages: pages array which can be used to pass information to free - * @populated: populated bitmap - * @page_start: page index of the first page to unmap - * @page_end: page index of the last page to unmap + 1 - * - * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. - * Corresponding elements in @pages were cleared by the caller and can - * be used to carry information to pcpu_free_pages() which will be - * called after all unmaps are finished. The caller should call - * proper pre/post flush functions. +/* + * Chunk management implementation. + * + * To allow different implementations, chunk alloc/free and + * [de]population are implemented in a separate file which is pulled + * into this file and compiled together. The following functions + * should be implemented. + * + * pcpu_populate_chunk - populate the specified range of a chunk + * pcpu_depopulate_chunk - depopulate the specified range of a chunk + * pcpu_create_chunk - create a new chunk + * pcpu_destroy_chunk - destroy a chunk, always preceded by full depop + * pcpu_addr_to_page - translate address to physical address + * pcpu_verify_alloc_info - check alloc_info is acceptable during init */ -static void pcpu_unmap_pages(struct pcpu_chunk *chunk, - struct page **pages, unsigned long *populated, - int page_start, int page_end) -{ - unsigned int cpu; - int i; - - for_each_possible_cpu(cpu) { - for (i = page_start; i < page_end; i++) { - struct page *page; - - page = pcpu_chunk_page(chunk, cpu, i); - WARN_ON(!page); - pages[pcpu_page_idx(cpu, i)] = page; - } - __pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start), - page_end - page_start); - } - - for (i = page_start; i < page_end; i++) - __clear_bit(i, populated); -} +static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size); +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size); +static struct pcpu_chunk *pcpu_create_chunk(void); +static void pcpu_destroy_chunk(struct pcpu_chunk *chunk); +static struct page *pcpu_addr_to_page(void *addr); +static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai); + +#ifdef CONFIG_NEED_PER_CPU_KM +#include "percpu-km.c" +#else +#include "percpu-vm.c" +#endif /** - * pcpu_post_unmap_tlb_flush - flush TLB after unmapping - * @chunk: pcpu_chunk the regions to be flushed belong to - * @page_start: page index of the first page to be flushed - * @page_end: page index of the last page to be flushed + 1 - * - * Pages [@page_start,@page_end) of @chunk have been unmapped. Flush - * TLB for the regions. This can be skipped if the area is to be - * returned to vmalloc as vmalloc will handle TLB flushing lazily. + * pcpu_chunk_addr_search - determine chunk containing specified address + * @addr: address for which the chunk needs to be determined. * - * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once - * for the whole region. - */ -static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, - int page_start, int page_end) -{ - flush_tlb_kernel_range( - pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start), - pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end)); -} - -static int __pcpu_map_pages(unsigned long addr, struct page **pages, - int nr_pages) -{ - return map_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT, - PAGE_KERNEL, pages); -} - -/** - * pcpu_map_pages - map pages into a pcpu_chunk - * @chunk: chunk of interest - * @pages: pages array containing pages to be mapped - * @populated: populated bitmap - * @page_start: page index of the first page to map - * @page_end: page index of the last page to map + 1 - * - * For each cpu, map pages [@page_start,@page_end) into @chunk. The - * caller is responsible for calling pcpu_post_map_flush() after all - * mappings are complete. - * - * This function is responsible for setting corresponding bits in - * @chunk->populated bitmap and whatever is necessary for reverse - * lookup (addr -> chunk). + * RETURNS: + * The address of the found chunk. */ -static int pcpu_map_pages(struct pcpu_chunk *chunk, - struct page **pages, unsigned long *populated, - int page_start, int page_end) +static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) { - unsigned int cpu, tcpu; - int i, err; - - for_each_possible_cpu(cpu) { - err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start), - &pages[pcpu_page_idx(cpu, page_start)], - page_end - page_start); - if (err < 0) - goto err; - } - - /* mapping successful, link chunk and mark populated */ - for (i = page_start; i < page_end; i++) { - for_each_possible_cpu(cpu) - pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)], - chunk); - __set_bit(i, populated); - } - - return 0; - -err: - for_each_possible_cpu(tcpu) { - if (tcpu == cpu) - break; - __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), - page_end - page_start); + /* is it in the first chunk? */ + if (pcpu_addr_in_first_chunk(addr)) { + /* is it in the reserved area? */ + if (pcpu_addr_in_reserved_chunk(addr)) + return pcpu_reserved_chunk; + return pcpu_first_chunk; } - return err; -} - -/** - * pcpu_post_map_flush - flush cache after mapping - * @chunk: pcpu_chunk the regions to be flushed belong to - * @page_start: page index of the first page to be flushed - * @page_end: page index of the last page to be flushed + 1 - * - * Pages [@page_start,@page_end) of @chunk have been mapped. Flush - * cache. - * - * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once - * for the whole region. - */ -static void pcpu_post_map_flush(struct pcpu_chunk *chunk, - int page_start, int page_end) -{ - flush_cache_vmap( - pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start), - pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end)); -} - -/** - * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk - * @chunk: chunk to depopulate - * @off: offset to the area to depopulate - * @size: size of the area to depopulate in bytes - * @flush: whether to flush cache and tlb or not - * - * For each cpu, depopulate and unmap pages [@page_start,@page_end) - * from @chunk. If @flush is true, vcache is flushed before unmapping - * and tlb after. - * - * CONTEXT: - * pcpu_alloc_mutex. - */ -static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size) -{ - int page_start = PFN_DOWN(off); - int page_end = PFN_UP(off + size); - struct page **pages; - unsigned long *populated; - int rs, re; - - /* quick path, check whether it's empty already */ - rs = page_start; - pcpu_next_unpop(chunk, &rs, &re, page_end); - if (rs == page_start && re == page_end) - return; - - /* immutable chunks can't be depopulated */ - WARN_ON(chunk->immutable); /* - * If control reaches here, there must have been at least one - * successful population attempt so the temp pages array must - * be available now. + * The address is relative to unit0 which might be unused and + * thus unmapped. Offset the address to the unit space of the + * current processor before looking it up in the vmalloc + * space. Note that any possible cpu id can be used here, so + * there's no need to worry about preemption or cpu hotplug. */ - pages = pcpu_get_pages_and_bitmap(chunk, &populated, false); - BUG_ON(!pages); - - /* unmap and free */ - pcpu_pre_unmap_flush(chunk, page_start, page_end); - - pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end) - pcpu_unmap_pages(chunk, pages, populated, rs, re); - - /* no need to flush tlb, vmalloc will handle it lazily */ - - pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end) - pcpu_free_pages(chunk, pages, populated, rs, re); - - /* commit new bitmap */ - bitmap_copy(chunk->populated, populated, pcpu_unit_pages); -} - -/** - * pcpu_populate_chunk - populate and map an area of a pcpu_chunk - * @chunk: chunk of interest - * @off: offset to the area to populate - * @size: size of the area to populate in bytes - * - * For each cpu, populate and map pages [@page_start,@page_end) into - * @chunk. The area is cleared on return. - * - * CONTEXT: - * pcpu_alloc_mutex, does GFP_KERNEL allocation. - */ -static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size) -{ - int page_start = PFN_DOWN(off); - int page_end = PFN_UP(off + size); - int free_end = page_start, unmap_end = page_start; - struct page **pages; - unsigned long *populated; - unsigned int cpu; - int rs, re, rc; - - /* quick path, check whether all pages are already there */ - rs = page_start; - pcpu_next_pop(chunk, &rs, &re, page_end); - if (rs == page_start && re == page_end) - goto clear; - - /* need to allocate and map pages, this chunk can't be immutable */ - WARN_ON(chunk->immutable); - - pages = pcpu_get_pages_and_bitmap(chunk, &populated, true); - if (!pages) - return -ENOMEM; - - /* alloc and map */ - pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) { - rc = pcpu_alloc_pages(chunk, pages, populated, rs, re); - if (rc) - goto err_free; - free_end = re; - } - - pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) { - rc = pcpu_map_pages(chunk, pages, populated, rs, re); - if (rc) - goto err_unmap; - unmap_end = re; - } - pcpu_post_map_flush(chunk, page_start, page_end); - - /* commit new bitmap */ - bitmap_copy(chunk->populated, populated, pcpu_unit_pages); -clear: - for_each_possible_cpu(cpu) - memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size); - return 0; - -err_unmap: - pcpu_pre_unmap_flush(chunk, page_start, unmap_end); - pcpu_for_each_unpop_region(chunk, rs, re, page_start, unmap_end) - pcpu_unmap_pages(chunk, pages, populated, rs, re); - pcpu_post_unmap_tlb_flush(chunk, page_start, unmap_end); -err_free: - pcpu_for_each_unpop_region(chunk, rs, re, page_start, free_end) - pcpu_free_pages(chunk, pages, populated, rs, re); - return rc; -} - -static void free_pcpu_chunk(struct pcpu_chunk *chunk) -{ - if (!chunk) - return; - if (chunk->vms) - pcpu_free_vm_areas(chunk->vms, pcpu_nr_groups); - pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0])); - kfree(chunk); -} - -static struct pcpu_chunk *alloc_pcpu_chunk(void) -{ - struct pcpu_chunk *chunk; - - chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL); - if (!chunk) - return NULL; - - chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); - chunk->map_alloc = PCPU_DFL_MAP_ALLOC; - chunk->map[chunk->map_used++] = pcpu_unit_size; - - chunk->vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, - pcpu_nr_groups, pcpu_atom_size, - GFP_KERNEL); - if (!chunk->vms) { - free_pcpu_chunk(chunk); - return NULL; - } - - INIT_LIST_HEAD(&chunk->list); - chunk->free_size = pcpu_unit_size; - chunk->contig_hint = pcpu_unit_size; - chunk->base_addr = chunk->vms[0]->addr - pcpu_group_offsets[0]; - - return chunk; + addr += pcpu_unit_offsets[raw_smp_processor_id()]; + return pcpu_get_page_chunk(pcpu_addr_to_page(addr)); } /** @@ -1142,7 +777,7 @@ restart: /* hmmm... no space left, create a new chunk */ spin_unlock_irqrestore(&pcpu_lock, flags); - chunk = alloc_pcpu_chunk(); + chunk = pcpu_create_chunk(); if (!chunk) { err = "failed to allocate new chunk"; goto fail_unlock_mutex; @@ -1254,7 +889,7 @@ static void pcpu_reclaim(struct work_struct *work) list_for_each_entry_safe(chunk, next, &todo, list) { pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size); - free_pcpu_chunk(chunk); + pcpu_destroy_chunk(chunk); } mutex_unlock(&pcpu_alloc_mutex); @@ -1304,6 +939,32 @@ void free_percpu(void __percpu *ptr) EXPORT_SYMBOL_GPL(free_percpu); /** + * is_kernel_percpu_address - test whether address is from static percpu area + * @addr: address to test + * + * Test whether @addr belongs to in-kernel static percpu area. Module + * static percpu areas are not considered. For those, use + * is_module_percpu_address(). + * + * RETURNS: + * %true if @addr is from in-kernel static percpu area, %false otherwise. + */ +bool is_kernel_percpu_address(unsigned long addr) +{ + const size_t static_size = __per_cpu_end - __per_cpu_start; + void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); + unsigned int cpu; + + for_each_possible_cpu(cpu) { + void *start = per_cpu_ptr(base, cpu); + + if ((void *)addr >= start && (void *)addr < start + static_size) + return true; + } + return false; +} + +/** * per_cpu_ptr_to_phys - convert translated percpu address to physical address * @addr: the address to be converted to physical address * @@ -1317,11 +978,14 @@ EXPORT_SYMBOL_GPL(free_percpu); */ phys_addr_t per_cpu_ptr_to_phys(void *addr) { - if ((unsigned long)addr < VMALLOC_START || - (unsigned long)addr >= VMALLOC_END) - return __pa(addr); - else - return page_to_phys(vmalloc_to_page(addr)); + if (pcpu_addr_in_first_chunk(addr)) { + if ((unsigned long)addr < VMALLOC_START || + (unsigned long)addr >= VMALLOC_END) + return __pa(addr); + else + return page_to_phys(vmalloc_to_page(addr)); + } else + return page_to_phys(pcpu_addr_to_page(addr)); } static inline size_t pcpu_calc_fc_sizes(size_t static_size, @@ -1693,6 +1357,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, PCPU_SETUP_BUG_ON(ai->unit_size < size_sum); PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK); PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE); + PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[0])); diff --git a/mm/percpu_up.c b/mm/percpu_up.c new file mode 100644 index 000000000000..c4351c7f57d2 --- /dev/null +++ b/mm/percpu_up.c @@ -0,0 +1,30 @@ +/* + * mm/percpu_up.c - dummy percpu memory allocator implementation for UP + */ + +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/slab.h> + +void __percpu *__alloc_percpu(size_t size, size_t align) +{ + /* + * Can't easily make larger alignment work with kmalloc. WARN + * on it. Larger alignment should only be used for module + * percpu sections on SMP for which this path isn't used. + */ + WARN_ON_ONCE(align > SMP_CACHE_BYTES); + return kzalloc(size, GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(__alloc_percpu); + +void free_percpu(void __percpu *p) +{ + kfree(p); +} +EXPORT_SYMBOL_GPL(free_percpu); + +phys_addr_t per_cpu_ptr_to_phys(void *addr) +{ + return __pa(addr); +} diff --git a/mm/quicklist.c b/mm/quicklist.c index 6633965bb27b..2876349339a7 100644 --- a/mm/quicklist.c +++ b/mm/quicklist.c @@ -14,6 +14,7 @@ */ #include <linux/kernel.h> +#include <linux/gfp.h> #include <linux/mm.h> #include <linux/mmzone.h> #include <linux/module.h> diff --git a/mm/readahead.c b/mm/readahead.c index 337b20e946f6..dfa9a1a03a11 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/fs.h> +#include <linux/gfp.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/blkdev.h> @@ -502,7 +503,7 @@ void page_cache_sync_readahead(struct address_space *mapping, return; /* be dumb */ - if (filp->f_mode & FMODE_RANDOM) { + if (filp && (filp->f_mode & FMODE_RANDOM)) { force_page_cache_readahead(mapping, filp, offset, req_size); return; } diff --git a/mm/rmap.c b/mm/rmap.c index fcd593c9c997..0feeef860a8f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -133,8 +133,8 @@ int anon_vma_prepare(struct vm_area_struct *vma) goto out_enomem_free_avc; allocated = anon_vma; } - spin_lock(&anon_vma->lock); + spin_lock(&anon_vma->lock); /* page_table_lock to protect against threads */ spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { @@ -144,14 +144,15 @@ int anon_vma_prepare(struct vm_area_struct *vma) list_add(&avc->same_vma, &vma->anon_vma_chain); list_add(&avc->same_anon_vma, &anon_vma->head); allocated = NULL; + avc = NULL; } spin_unlock(&mm->page_table_lock); - spin_unlock(&anon_vma->lock); - if (unlikely(allocated)) { + + if (unlikely(allocated)) anon_vma_free(allocated); + if (unlikely(avc)) anon_vma_chain_free(avc); - } } return 0; @@ -182,7 +183,7 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { struct anon_vma_chain *avc, *pavc; - list_for_each_entry(pavc, &src->anon_vma_chain, same_vma) { + list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) { avc = anon_vma_chain_alloc(); if (!avc) goto enomem_failure; @@ -232,6 +233,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) out_error_free_anon_vma: anon_vma_free(anon_vma); out_error: + unlink_anon_vmas(vma); return -ENOMEM; } @@ -334,14 +336,13 @@ vma_address(struct page *page, struct vm_area_struct *vma) /* * At what user virtual address is page expected in vma? - * checking that the page matches the vma. + * Caller should check the page is actually part of the vma. */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { - if (PageAnon(page)) { - if (vma->anon_vma != page_anon_vma(page)) - return -EFAULT; - } else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) { + if (PageAnon(page)) + ; + else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) { if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping) return -EFAULT; @@ -729,13 +730,29 @@ void page_move_anon_rmap(struct page *page, * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped + * @exclusive: the page is exclusively owned by the current process */ static void __page_set_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address) + struct vm_area_struct *vma, unsigned long address, int exclusive) { struct anon_vma *anon_vma = vma->anon_vma; BUG_ON(!anon_vma); + + /* + * If the page isn't exclusively mapped into this vma, + * we must use the _oldest_ possible anon_vma for the + * page mapping! + * + * So take the last AVC chain entry in the vma, which is + * the deepest ancestor, and use the anon_vma from that. + */ + if (!exclusive) { + struct anon_vma_chain *avc; + avc = list_entry(vma->anon_vma_chain.prev, struct anon_vma_chain, same_vma); + anon_vma = avc->anon_vma; + } + anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; page->mapping = (struct address_space *) anon_vma; page->index = linear_page_index(vma, address); @@ -790,7 +807,7 @@ void page_add_anon_rmap(struct page *page, VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end); if (first) - __page_set_anon_rmap(page, vma, address); + __page_set_anon_rmap(page, vma, address, 0); else __page_check_anon_rmap(page, vma, address); } @@ -812,7 +829,7 @@ void page_add_new_anon_rmap(struct page *page, SetPageSwapBacked(page); atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */ __inc_zone_page_state(page, NR_ANON_PAGES); - __page_set_anon_rmap(page, vma, address); + __page_set_anon_rmap(page, vma, address, 1); if (page_evictable(page, vma)) lru_cache_add_lru(page, LRU_ACTIVE_ANON); else diff --git a/mm/shmem.c b/mm/shmem.c index eef4ebea5158..0cd7f66f1c66 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1545,8 +1545,8 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) return 0; } -static struct inode *shmem_get_inode(struct super_block *sb, int mode, - dev_t dev, unsigned long flags) +static struct inode *shmem_get_inode(struct super_block *sb, const struct inode *dir, + int mode, dev_t dev, unsigned long flags) { struct inode *inode; struct shmem_inode_info *info; @@ -1557,9 +1557,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, int mode, inode = new_inode(sb); if (inode) { - inode->i_mode = mode; - inode->i_uid = current_fsuid(); - inode->i_gid = current_fsgid(); + inode_init_owner(inode, dir, mode); inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &shmem_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; @@ -1814,7 +1812,7 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) struct inode *inode; int error = -ENOSPC; - inode = shmem_get_inode(dir->i_sb, mode, dev, VM_NORESERVE); + inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE); if (inode) { error = security_inode_init_security(inode, dir, NULL, NULL, NULL); @@ -1833,11 +1831,6 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) #else error = 0; #endif - if (dir->i_mode & S_ISGID) { - inode->i_gid = dir->i_gid; - if (S_ISDIR(mode)) - inode->i_mode |= S_ISGID; - } dir->i_size += BOGO_DIRENT_SIZE; dir->i_ctime = dir->i_mtime = CURRENT_TIME; d_instantiate(dentry, inode); @@ -1957,7 +1950,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s if (len > PAGE_CACHE_SIZE) return -ENAMETOOLONG; - inode = shmem_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0, VM_NORESERVE); + inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0, VM_NORESERVE); if (!inode) return -ENOSPC; @@ -1992,8 +1985,6 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s unlock_page(page); page_cache_release(page); } - if (dir->i_mode & S_ISGID) - inode->i_gid = dir->i_gid; dir->i_size += BOGO_DIRENT_SIZE; dir->i_ctime = dir->i_mtime = CURRENT_TIME; d_instantiate(dentry, inode); @@ -2071,14 +2062,14 @@ static int shmem_xattr_security_set(struct dentry *dentry, const char *name, size, flags); } -static struct xattr_handler shmem_xattr_security_handler = { +static const struct xattr_handler shmem_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .list = shmem_xattr_security_list, .get = shmem_xattr_security_get, .set = shmem_xattr_security_set, }; -static struct xattr_handler *shmem_xattr_handlers[] = { +static const struct xattr_handler *shmem_xattr_handlers[] = { &generic_acl_access_handler, &generic_acl_default_handler, &shmem_xattr_security_handler, @@ -2366,7 +2357,7 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags |= MS_POSIXACL; #endif - inode = shmem_get_inode(sb, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE); + inode = shmem_get_inode(sb, NULL, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE); if (!inode) goto failed; inode->i_uid = sbinfo->uid; @@ -2611,7 +2602,7 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) #define shmem_vm_ops generic_file_vm_ops #define shmem_file_operations ramfs_file_operations -#define shmem_get_inode(sb, mode, dev, flags) ramfs_get_inode(sb, mode, dev) +#define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev) #define shmem_acct_size(flags, size) 0 #define shmem_unacct_size(flags, size) do {} while (0) #define SHMEM_MAX_BYTES MAX_LFS_FILESIZE @@ -2655,7 +2646,7 @@ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags path.mnt = mntget(shm_mnt); error = -ENOSPC; - inode = shmem_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0, flags); + inode = shmem_get_inode(root->d_sb, NULL, S_IFREG | S_IRWXUGO, 0, flags); if (!inode) goto put_dentry; diff --git a/mm/slab.c b/mm/slab.c index 3230cd2c6b3b..50a73fca19c4 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -145,30 +145,6 @@ #define BYTES_PER_WORD sizeof(void *) #define REDZONE_ALIGN max(BYTES_PER_WORD, __alignof__(unsigned long long)) -#ifndef ARCH_KMALLOC_MINALIGN -/* - * Enforce a minimum alignment for the kmalloc caches. - * Usually, the kmalloc caches are cache_line_size() aligned, except when - * DEBUG and FORCED_DEBUG are enabled, then they are BYTES_PER_WORD aligned. - * Some archs want to perform DMA into kmalloc caches and need a guaranteed - * alignment larger than the alignment of a 64-bit integer. - * ARCH_KMALLOC_MINALIGN allows that. - * Note that increasing this value may disable some debug features. - */ -#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) -#endif - -#ifndef ARCH_SLAB_MINALIGN -/* - * Enforce a minimum alignment for all caches. - * Intended for archs that get misalignment faults even for BYTES_PER_WORD - * aligned buffers. Includes ARCH_KMALLOC_MINALIGN. - * If possible: Do not enable this flag for CONFIG_DEBUG_SLAB, it disables - * some debug features. - */ -#define ARCH_SLAB_MINALIGN 0 -#endif - #ifndef ARCH_KMALLOC_FLAGS #define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN #endif @@ -2313,8 +2289,8 @@ kmem_cache_create (const char *name, size_t size, size_t align, if (ralign < align) { ralign = align; } - /* disable debug if necessary */ - if (ralign > __alignof__(unsigned long long)) + /* disable debug if not aligning with REDZONE_ALIGN */ + if (ralign & (__alignof__(unsigned long long) - 1)) flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); /* * 4) Store it. @@ -2340,8 +2316,8 @@ kmem_cache_create (const char *name, size_t size, size_t align, */ if (flags & SLAB_RED_ZONE) { /* add space for red zone words */ - cachep->obj_offset += sizeof(unsigned long long); - size += 2 * sizeof(unsigned long long); + cachep->obj_offset += align; + size += align + sizeof(unsigned long long); } if (flags & SLAB_STORE_USER) { /* user store requires one word storage behind the end of @@ -3695,21 +3671,10 @@ EXPORT_SYMBOL(kmem_cache_alloc_notrace); */ int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr) { - unsigned long addr = (unsigned long)ptr; - unsigned long min_addr = PAGE_OFFSET; - unsigned long align_mask = BYTES_PER_WORD - 1; unsigned long size = cachep->buffer_size; struct page *page; - if (unlikely(addr < min_addr)) - goto out; - if (unlikely(addr > (unsigned long)high_memory - size)) - goto out; - if (unlikely(addr & align_mask)) - goto out; - if (unlikely(!kern_addr_valid(addr))) - goto out; - if (unlikely(!kern_addr_valid(addr + size - 1))) + if (unlikely(!kern_ptr_validate(ptr, size))) goto out; page = virt_to_page(ptr); if (unlikely(!PageSlab(page))) @@ -4320,10 +4285,11 @@ static int s_show(struct seq_file *m, void *p) unsigned long node_frees = cachep->node_frees; unsigned long overflows = cachep->node_overflow; - seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu \ - %4lu %4lu %4lu %4lu %4lu", allocs, high, grown, - reaped, errors, max_freeable, node_allocs, - node_frees, overflows); + seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu " + "%4lu %4lu %4lu %4lu %4lu", + allocs, high, grown, + reaped, errors, max_freeable, node_allocs, + node_frees, overflows); } /* cpu stats */ { diff --git a/mm/slob.c b/mm/slob.c index 837ebd64cc34..23631e2bb57a 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -467,14 +467,6 @@ out: * End of slob allocator proper. Begin kmem_cache_alloc and kmalloc frontend. */ -#ifndef ARCH_KMALLOC_MINALIGN -#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long) -#endif - -#ifndef ARCH_SLAB_MINALIGN -#define ARCH_SLAB_MINALIGN __alignof__(unsigned long) -#endif - void *__kmalloc_node(size_t size, gfp_t gfp, int node) { unsigned int *m; diff --git a/mm/slub.c b/mm/slub.c index b364844a1068..e46e3129697d 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -157,14 +157,6 @@ #define SLUB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \ SLAB_CACHE_DMA | SLAB_NOTRACK) -#ifndef ARCH_KMALLOC_MINALIGN -#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) -#endif - -#ifndef ARCH_SLAB_MINALIGN -#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) -#endif - #define OO_SHIFT 16 #define OO_MASK ((1 << OO_SHIFT) - 1) #define MAX_OBJS_PER_PAGE 65535 /* since page.objects is u16 */ @@ -1084,7 +1076,7 @@ static inline struct page *alloc_slab_page(gfp_t flags, int node, if (node == -1) return alloc_pages(flags, order); else - return alloc_pages_node(node, flags, order); + return alloc_pages_exact_node(node, flags, order); } static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) @@ -2153,7 +2145,7 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags) int local_node; if (slab_state >= UP && (s < kmalloc_caches || - s > kmalloc_caches + KMALLOC_CACHES)) + s >= kmalloc_caches + KMALLOC_CACHES)) local_node = page_to_nid(virt_to_page(s)); else local_node = 0; @@ -2386,6 +2378,9 @@ int kmem_ptr_validate(struct kmem_cache *s, const void *object) { struct page *page; + if (!kern_ptr_validate(object, s->size)) + return 0; + page = get_object_page(object); if (!page || s != page->slab) @@ -2426,9 +2421,11 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, #ifdef CONFIG_SLUB_DEBUG void *addr = page_address(page); void *p; - DECLARE_BITMAP(map, page->objects); + long *map = kzalloc(BITS_TO_LONGS(page->objects) * sizeof(long), + GFP_ATOMIC); - bitmap_zero(map, page->objects); + if (!map) + return; slab_err(s, page, "%s", text); slab_lock(page); for_each_free_object(p, s, page->freelist) @@ -2443,6 +2440,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, } } slab_unlock(page); + kfree(map); #endif } @@ -3335,8 +3333,15 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, struct kmem_cache *s; void *ret; - if (unlikely(size > SLUB_MAX_SIZE)) - return kmalloc_large_node(size, gfpflags, node); + if (unlikely(size > SLUB_MAX_SIZE)) { + ret = kmalloc_large_node(size, gfpflags, node); + + trace_kmalloc_node(caller, ret, + size, PAGE_SIZE << get_order(size), + gfpflags, node); + + return ret; + } s = get_slab(size, gfpflags); @@ -3648,10 +3653,10 @@ static int add_location(struct loc_track *t, struct kmem_cache *s, } static void process_slab(struct loc_track *t, struct kmem_cache *s, - struct page *page, enum track_item alloc) + struct page *page, enum track_item alloc, + long *map) { void *addr = page_address(page); - DECLARE_BITMAP(map, page->objects); void *p; bitmap_zero(map, page->objects); @@ -3670,11 +3675,14 @@ static int list_locations(struct kmem_cache *s, char *buf, unsigned long i; struct loc_track t = { 0, 0, NULL }; int node; + unsigned long *map = kmalloc(BITS_TO_LONGS(oo_objects(s->max)) * + sizeof(unsigned long), GFP_KERNEL); - if (!alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location), - GFP_TEMPORARY)) + if (!map || !alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location), + GFP_TEMPORARY)) { + kfree(map); return sprintf(buf, "Out of memory\n"); - + } /* Push back cpu slabs */ flush_all(s); @@ -3688,9 +3696,9 @@ static int list_locations(struct kmem_cache *s, char *buf, spin_lock_irqsave(&n->list_lock, flags); list_for_each_entry(page, &n->partial, lru) - process_slab(&t, s, page, alloc); + process_slab(&t, s, page, alloc, map); list_for_each_entry(page, &n->full, lru) - process_slab(&t, s, page, alloc); + process_slab(&t, s, page, alloc, map); spin_unlock_irqrestore(&n->list_lock, flags); } @@ -3741,6 +3749,7 @@ static int list_locations(struct kmem_cache *s, char *buf, } free_loc_track(&t); + kfree(map); if (!t.count) len += sprintf(buf, "No data\n"); return len; diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 392b9bb5bc01..aa33fd67fa41 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -22,6 +22,7 @@ #include <linux/bootmem.h> #include <linux/highmem.h> #include <linux/module.h> +#include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <linux/sched.h> diff --git a/mm/sparse.c b/mm/sparse.c index 22896d589133..dc0cc4d43ff3 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -2,6 +2,7 @@ * sparse memory mappings. */ #include <linux/mm.h> +#include <linux/slab.h> #include <linux/mmzone.h> #include <linux/bootmem.h> #include <linux/highmem.h> diff --git a/mm/swap.c b/mm/swap.c index 9036b89813ac..7cd60bf0a972 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -30,6 +30,7 @@ #include <linux/notifier.h> #include <linux/backing-dev.h> #include <linux/memcontrol.h> +#include <linux/gfp.h> #include "internal.h" diff --git a/mm/swap_state.c b/mm/swap_state.c index 6d1daeb1cb4a..e10f5833167f 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -8,6 +8,7 @@ */ #include <linux/module.h> #include <linux/mm.h> +#include <linux/gfp.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/swapops.h> diff --git a/mm/swapfile.c b/mm/swapfile.c index 6cd0a8f90dc7..03aa2d55f1a2 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -139,7 +139,8 @@ static int discard_swap(struct swap_info_struct *si) nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL, DISCARD_FL_BARRIER); + nr_blocks, GFP_KERNEL, + BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); if (err) return err; cond_resched(); @@ -150,7 +151,8 @@ static int discard_swap(struct swap_info_struct *si) nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL, DISCARD_FL_BARRIER); + nr_blocks, GFP_KERNEL, + BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); if (err) break; @@ -189,7 +191,8 @@ static void discard_swap_cluster(struct swap_info_struct *si, start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_NOIO, DISCARD_FL_BARRIER)) + nr_blocks, GFP_NOIO, BLKDEV_IFL_WAIT | + BLKDEV_IFL_BARRIER)) break; } @@ -574,6 +577,7 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, /* free if no reference */ if (!usage) { + struct gendisk *disk = p->bdev->bd_disk; if (offset < p->lowest_bit) p->lowest_bit = offset; if (offset > p->highest_bit) @@ -583,6 +587,9 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, swap_list.next = p->type; nr_swap_pages++; p->inuse_pages--; + if ((p->flags & SWP_BLKDEV) && + disk->fops->swap_slot_free_notify) + disk->fops->swap_slot_free_notify(p->bdev, offset); } return usage; @@ -1884,6 +1891,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (error < 0) goto bad_swap; p->bdev = bdev; + p->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { p->bdev = inode->i_sb->s_bdev; mutex_lock(&inode->i_mutex); diff --git a/mm/truncate.c b/mm/truncate.c index e87e37244829..f42675a3615d 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/backing-dev.h> +#include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/module.h> diff --git a/mm/util.c b/mm/util.c index 834db7be240f..f5712e8964be 100644 --- a/mm/util.c +++ b/mm/util.c @@ -186,6 +186,27 @@ void kzfree(const void *p) } EXPORT_SYMBOL(kzfree); +int kern_ptr_validate(const void *ptr, unsigned long size) +{ + unsigned long addr = (unsigned long)ptr; + unsigned long min_addr = PAGE_OFFSET; + unsigned long align_mask = sizeof(void *) - 1; + + if (unlikely(addr < min_addr)) + goto out; + if (unlikely(addr > (unsigned long)high_memory - size)) + goto out; + if (unlikely(addr & align_mask)) + goto out; + if (unlikely(!kern_addr_valid(addr))) + goto out; + if (unlikely(!kern_addr_valid(addr + size - 1))) + goto out; + return 1; +out: + return 0; +} + /* * strndup_user - duplicate an existing string from user space * @s: The string to duplicate diff --git a/mm/vmscan.c b/mm/vmscan.c index 79c809895fba..3ff3311447f5 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -13,7 +13,7 @@ #include <linux/mm.h> #include <linux/module.h> -#include <linux/slab.h> +#include <linux/gfp.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/pagemap.h> @@ -1535,13 +1535,6 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc, unsigned long ap, fp; struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc); - /* If we have no swap space, do not bother scanning anon pages. */ - if (!sc->may_swap || (nr_swap_pages <= 0)) { - percent[0] = 0; - percent[1] = 100; - return; - } - anon = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) + zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON); file = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) + @@ -1639,20 +1632,22 @@ static void shrink_zone(int priority, struct zone *zone, unsigned long nr_reclaimed = sc->nr_reclaimed; unsigned long nr_to_reclaim = sc->nr_to_reclaim; struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc); + int noswap = 0; - get_scan_ratio(zone, sc, percent); + /* If we have no swap space, do not bother scanning anon pages. */ + if (!sc->may_swap || (nr_swap_pages <= 0)) { + noswap = 1; + percent[0] = 0; + percent[1] = 100; + } else + get_scan_ratio(zone, sc, percent); for_each_evictable_lru(l) { int file = is_file_lru(l); unsigned long scan; - if (percent[file] == 0) { - nr[l] = 0; - continue; - } - scan = zone_nr_lru_pages(zone, sc, l); - if (priority) { + if (priority || noswap) { scan >>= priority; scan = (scan * percent[file]) / 100; } diff --git a/mm/vmstat.c b/mm/vmstat.c index 7f760cbc73f3..fa12ea3051fb 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -12,6 +12,7 @@ #include <linux/mm.h> #include <linux/err.h> #include <linux/module.h> +#include <linux/slab.h> #include <linux/cpu.h> #include <linux/vmstat.h> #include <linux/sched.h> |