diff options
Diffstat (limited to 'mm/ksm.c')
| -rw-r--r-- | mm/ksm.c | 88 |
1 files changed, 81 insertions, 7 deletions
@@ -34,6 +34,7 @@ #include <linux/swap.h> #include <linux/ksm.h> #include <linux/hash.h> +#include <linux/freezer.h> #include <asm/tlbflush.h> #include "internal.h" @@ -411,6 +412,20 @@ out: up_read(&mm->mmap_sem); } +static struct page *page_trans_compound_anon(struct page *page) +{ + if (PageTransCompound(page)) { + struct page *head = compound_trans_head(page); + /* + * head may actually be splitted and freed from under + * us but it's ok here. + */ + if (PageAnon(head)) + return head; + } + return NULL; +} + static struct page *get_mergeable_page(struct rmap_item *rmap_item) { struct mm_struct *mm = rmap_item->mm; @@ -430,7 +445,7 @@ static struct page *get_mergeable_page(struct rmap_item *rmap_item) page = follow_page(vma, addr, FOLL_GET); if (IS_ERR_OR_NULL(page)) goto out; - if (PageAnon(page)) { + if (PageAnon(page) || page_trans_compound_anon(page)) { flush_anon_page(vma, page, addr); flush_dcache_page(page); } else { @@ -708,6 +723,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, if (addr == -EFAULT) goto out; + BUG_ON(PageTransCompound(page)); ptep = page_check_address(page, mm, addr, &ptl, 0); if (!ptep) goto out; @@ -783,6 +799,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, goto out; pmd = pmd_offset(pud, addr); + BUG_ON(pmd_trans_huge(*pmd)); if (!pmd_present(*pmd)) goto out; @@ -800,6 +817,8 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot)); page_remove_rmap(page); + if (!page_mapped(page)) + try_to_free_swap(page); put_page(page); pte_unmap_unlock(ptep, ptl); @@ -808,6 +827,33 @@ out: return err; } +static int page_trans_compound_anon_split(struct page *page) +{ + int ret = 0; + struct page *transhuge_head = page_trans_compound_anon(page); + if (transhuge_head) { + /* Get the reference on the head to split it. */ + if (get_page_unless_zero(transhuge_head)) { + /* + * Recheck we got the reference while the head + * was still anonymous. + */ + if (PageAnon(transhuge_head)) + ret = split_huge_page(transhuge_head); + else + /* + * Retry later if split_huge_page run + * from under us. + */ + ret = 1; + put_page(transhuge_head); + } else + /* Retry later if split_huge_page run from under us. */ + ret = 1; + } + return ret; +} + /* * try_to_merge_one_page - take two pages and merge them into one * @vma: the vma that holds the pte pointing to page @@ -828,6 +874,9 @@ static int try_to_merge_one_page(struct vm_area_struct *vma, if (!(vma->vm_flags & VM_MERGEABLE)) goto out; + if (PageTransCompound(page) && page_trans_compound_anon_split(page)) + goto out; + BUG_ON(PageTransCompound(page)); if (!PageAnon(page)) goto out; @@ -1247,6 +1296,18 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page) slot = ksm_scan.mm_slot; if (slot == &ksm_mm_head) { + /* + * A number of pages can hang around indefinitely on per-cpu + * pagevecs, raised page count preventing write_protect_page + * from merging them. Though it doesn't really matter much, + * it is puzzling to see some stuck in pages_volatile until + * other activity jostles them out, and they also prevented + * LTP's KSM test from succeeding deterministically; so drain + * them here (here rather than on entry to ksm_do_scan(), + * so we don't IPI too often when pages_to_scan is set low). + */ + lru_add_drain_all(); + root_unstable_tree = RB_ROOT; spin_lock(&ksm_mmlist_lock); @@ -1277,7 +1338,13 @@ next_mm: if (ksm_test_exit(mm)) break; *page = follow_page(vma, ksm_scan.address, FOLL_GET); - if (!IS_ERR_OR_NULL(*page) && PageAnon(*page)) { + if (IS_ERR_OR_NULL(*page)) { + ksm_scan.address += PAGE_SIZE; + cond_resched(); + continue; + } + if (PageAnon(*page) || + page_trans_compound_anon(*page)) { flush_anon_page(vma, *page, ksm_scan.address); flush_dcache_page(*page); rmap_item = get_next_rmap_item(slot, @@ -1291,8 +1358,7 @@ next_mm: up_read(&mm->mmap_sem); return rmap_item; } - if (!IS_ERR_OR_NULL(*page)) - put_page(*page); + put_page(*page); ksm_scan.address += PAGE_SIZE; cond_resched(); } @@ -1352,7 +1418,7 @@ static void ksm_do_scan(unsigned int scan_npages) struct rmap_item *rmap_item; struct page *uninitialized_var(page); - while (scan_npages--) { + while (scan_npages-- && likely(!freezing(current))) { cond_resched(); rmap_item = scan_get_next_rmap_item(&page); if (!rmap_item) @@ -1370,6 +1436,7 @@ static int ksmd_should_run(void) static int ksm_scan_thread(void *nothing) { + set_freezable(); set_user_nice(current, 5); while (!kthread_should_stop()) { @@ -1378,11 +1445,13 @@ static int ksm_scan_thread(void *nothing) ksm_do_scan(ksm_thread_pages_to_scan); mutex_unlock(&ksm_thread_mutex); + try_to_freeze(); + if (ksmd_should_run()) { schedule_timeout_interruptible( msecs_to_jiffies(ksm_thread_sleep_millisecs)); } else { - wait_event_interruptible(ksm_thread_wait, + wait_event_freezable(ksm_thread_wait, ksmd_should_run() || kthread_should_stop()); } } @@ -1724,8 +1793,13 @@ static int ksm_memory_callback(struct notifier_block *self, /* * Keep it very simple for now: just lock out ksmd and * MADV_UNMERGEABLE while any memory is going offline. + * mutex_lock_nested() is necessary because lockdep was alarmed + * that here we take ksm_thread_mutex inside notifier chain + * mutex, and later take notifier chain mutex inside + * ksm_thread_mutex to unlock it. But that's safe because both + * are inside mem_hotplug_mutex. */ - mutex_lock(&ksm_thread_mutex); + mutex_lock_nested(&ksm_thread_mutex, SINGLE_DEPTH_NESTING); break; case MEM_OFFLINE: |