#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/mmu_notifier.h>
+#include <linux/swap.h>
#include <linux/ksm.h>
#include <asm/tlbflush.h>
static unsigned long ksm_max_kernel_pages;
/* Number of pages ksmd should scan in one batch */
-static unsigned int ksm_thread_pages_to_scan;
+static unsigned int ksm_thread_pages_to_scan = 100;
/* Milliseconds ksmd should sleep between batches */
-static unsigned int ksm_thread_sleep_millisecs;
+static unsigned int ksm_thread_sleep_millisecs = 20;
#define KSM_RUN_STOP 0
#define KSM_RUN_MERGE 1
#define KSM_RUN_UNMERGE 2
-static unsigned int ksm_run;
+static unsigned int ksm_run = KSM_RUN_STOP;
static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait);
static DEFINE_MUTEX(ksm_thread_mutex);
sizeof(struct __struct), __alignof__(struct __struct),\
(__flags), NULL)
+static void __init ksm_init_max_kernel_pages(void)
+{
+ ksm_max_kernel_pages = nr_free_buffer_pages() / 4;
+}
+
static int __init ksm_slab_init(void)
{
rmap_item_cache = KSM_KMEM_CACHE(rmap_item, 0);
return rmap_item->address & STABLE_FLAG;
}
+/*
+ * ksmd, and unmerge_and_remove_all_rmap_items(), must not touch an mm's
+ * page tables after it has passed through ksm_exit() - which, if necessary,
+ * takes mmap_sem briefly to serialize against them. ksm_exit() does not set
+ * a special flag: they can just back out as soon as mm_users goes to zero.
+ * ksm_test_exit() is used throughout to make this test for exit: in some
+ * places for correctness, in some places just to avoid unnecessary work.
+ */
+static inline bool ksm_test_exit(struct mm_struct *mm)
+{
+ return atomic_read(&mm->mm_users) == 0;
+}
+
/*
* We use break_ksm to break COW on a ksm page: it's a stripped down
*
* Could a ksm page appear anywhere else? Actually yes, in a VM_PFNMAP
* mmap of /dev/mem or /dev/kmem, where we would not want to touch it.
*/
-static void break_ksm(struct vm_area_struct *vma, unsigned long addr)
+static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
{
struct page *page;
- int ret;
+ int ret = 0;
do {
cond_resched();
else
ret = VM_FAULT_WRITE;
put_page(page);
- } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS)));
-
- /* Which leaves us looping there if VM_FAULT_OOM: hmmm... */
+ } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_OOM)));
+ /*
+ * We must loop because handle_mm_fault() may back out if there's
+ * any difficulty e.g. if pte accessed bit gets updated concurrently.
+ *
+ * VM_FAULT_WRITE is what we have been hoping for: it indicates that
+ * COW has been broken, even if the vma does not permit VM_WRITE;
+ * but note that a concurrent fault might break PageKsm for us.
+ *
+ * VM_FAULT_SIGBUS could occur if we race with truncation of the
+ * backing file, which also invalidates anonymous pages: that's
+ * okay, that truncation will have unmapped the PageKsm for us.
+ *
+ * VM_FAULT_OOM: at the time of writing (late July 2009), setting
+ * aside mem_cgroup limits, VM_FAULT_OOM would only be set if the
+ * current task has TIF_MEMDIE set, and will be OOM killed on return
+ * to user; and ksmd, having no mm, would never be chosen for that.
+ *
+ * But if the mm is in a limited mem_cgroup, then the fault may fail
+ * with VM_FAULT_OOM even if the current task is not TIF_MEMDIE; and
+ * even ksmd can fail in this way - though it's usually breaking ksm
+ * just to undo a merge it made a moment before, so unlikely to oom.
+ *
+ * That's a pity: we might therefore have more kernel pages allocated
+ * than we're counting as nodes in the stable tree; but ksm_do_scan
+ * will retry to break_cow on each pass, so should recover the page
+ * in due course. The important thing is to not let VM_MERGEABLE
+ * be cleared while any such pages might remain in the area.
+ */
+ return (ret & VM_FAULT_OOM) ? -ENOMEM : 0;
}
static void break_cow(struct mm_struct *mm, unsigned long addr)
struct vm_area_struct *vma;
down_read(&mm->mmap_sem);
+ if (ksm_test_exit(mm))
+ goto out;
vma = find_vma(mm, addr);
if (!vma || vma->vm_start > addr)
goto out;
struct page *page;
down_read(&mm->mmap_sem);
+ if (ksm_test_exit(mm))
+ goto out;
vma = find_vma(mm, addr);
if (!vma || vma->vm_start > addr)
goto out;
} else if (rmap_item->address & NODE_FLAG) {
unsigned char age;
/*
- * ksm_thread can and must skip the rb_erase, because
+ * Usually ksmd can and must skip the rb_erase, because
* root_unstable_tree was already reset to RB_ROOT.
- * But __ksm_exit has to be careful: do the rb_erase
- * if it's interrupting a scan, and this rmap_item was
- * inserted by this scan rather than left from before.
- *
- * Because of the case in which remove_mm_from_lists
- * increments seqnr before removing rmaps, unstable_nr
- * may even be 2 behind seqnr, but should never be
- * further behind. Yes, I did have trouble with this!
+ * But be careful when an mm is exiting: do the rb_erase
+ * if this rmap_item was inserted by this scan, rather
+ * than left over from before.
*/
age = (unsigned char)(ksm_scan.seqnr - rmap_item->address);
- BUG_ON(age > 2);
+ BUG_ON(age > 1);
if (!age)
rb_erase(&rmap_item->node, &root_unstable_tree);
ksm_pages_unshared--;
* to the next pass of ksmd - consider, for example, how ksmd might be
* in cmp_and_merge_page on one of the rmap_items we would be removing.
*/
-static void unmerge_ksm_pages(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
+static int unmerge_ksm_pages(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
{
unsigned long addr;
+ int err = 0;
- for (addr = start; addr < end; addr += PAGE_SIZE)
- break_ksm(vma, addr);
+ for (addr = start; addr < end && !err; addr += PAGE_SIZE) {
+ if (ksm_test_exit(vma->vm_mm))
+ break;
+ if (signal_pending(current))
+ err = -ERESTARTSYS;
+ else
+ err = break_ksm(vma, addr);
+ }
+ return err;
}
-static void unmerge_and_remove_all_rmap_items(void)
+#ifdef CONFIG_SYSFS
+/*
+ * Only called through the sysfs control interface:
+ */
+static int unmerge_and_remove_all_rmap_items(void)
{
struct mm_slot *mm_slot;
struct mm_struct *mm;
struct vm_area_struct *vma;
+ int err = 0;
- list_for_each_entry(mm_slot, &ksm_mm_head.mm_list, mm_list) {
+ spin_lock(&ksm_mmlist_lock);
+ ksm_scan.mm_slot = list_entry(ksm_mm_head.mm_list.next,
+ struct mm_slot, mm_list);
+ spin_unlock(&ksm_mmlist_lock);
+
+ for (mm_slot = ksm_scan.mm_slot;
+ mm_slot != &ksm_mm_head; mm_slot = ksm_scan.mm_slot) {
mm = mm_slot->mm;
down_read(&mm->mmap_sem);
for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (ksm_test_exit(mm))
+ break;
if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
continue;
- unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end);
+ err = unmerge_ksm_pages(vma,
+ vma->vm_start, vma->vm_end);
+ if (err)
+ goto error;
}
+
remove_trailing_rmap_items(mm_slot, mm_slot->rmap_list.next);
- up_read(&mm->mmap_sem);
- }
- spin_lock(&ksm_mmlist_lock);
- if (ksm_scan.mm_slot != &ksm_mm_head) {
- ksm_scan.mm_slot = &ksm_mm_head;
- ksm_scan.seqnr++;
+ spin_lock(&ksm_mmlist_lock);
+ ksm_scan.mm_slot = list_entry(mm_slot->mm_list.next,
+ struct mm_slot, mm_list);
+ if (ksm_test_exit(mm)) {
+ hlist_del(&mm_slot->link);
+ list_del(&mm_slot->mm_list);
+ spin_unlock(&ksm_mmlist_lock);
+
+ free_mm_slot(mm_slot);
+ clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+ up_read(&mm->mmap_sem);
+ mmdrop(mm);
+ } else {
+ spin_unlock(&ksm_mmlist_lock);
+ up_read(&mm->mmap_sem);
+ }
}
- spin_unlock(&ksm_mmlist_lock);
-}
-static void remove_mm_from_lists(struct mm_struct *mm)
-{
- struct mm_slot *mm_slot;
+ ksm_scan.seqnr = 0;
+ return 0;
+error:
+ up_read(&mm->mmap_sem);
spin_lock(&ksm_mmlist_lock);
- mm_slot = get_mm_slot(mm);
-
- /*
- * This mm_slot is always at the scanning cursor when we're
- * called from scan_get_next_rmap_item; but it's a special
- * case when we're called from __ksm_exit.
- */
- if (ksm_scan.mm_slot == mm_slot) {
- ksm_scan.mm_slot = list_entry(
- mm_slot->mm_list.next, struct mm_slot, mm_list);
- ksm_scan.address = 0;
- ksm_scan.rmap_item = list_entry(
- &ksm_scan.mm_slot->rmap_list, struct rmap_item, link);
- if (ksm_scan.mm_slot == &ksm_mm_head)
- ksm_scan.seqnr++;
- }
-
- hlist_del(&mm_slot->link);
- list_del(&mm_slot->mm_list);
+ ksm_scan.mm_slot = &ksm_mm_head;
spin_unlock(&ksm_mmlist_lock);
-
- remove_trailing_rmap_items(mm_slot, mm_slot->rmap_list.next);
- free_mm_slot(mm_slot);
- clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+ return err;
}
+#endif /* CONFIG_SYSFS */
static u32 calc_checksum(struct page *page)
{
int err = -EFAULT;
down_read(&mm1->mmap_sem);
+ if (ksm_test_exit(mm1))
+ goto out;
+
vma = find_vma(mm1, addr1);
if (!vma || vma->vm_start > addr1)
goto out;
return err;
down_read(&mm1->mmap_sem);
+ if (ksm_test_exit(mm1)) {
+ up_read(&mm1->mmap_sem);
+ goto out;
+ }
vma = find_vma(mm1, addr1);
if (!vma || vma->vm_start > addr1) {
up_read(&mm1->mmap_sem);
/*
* A ksm page might have got here by fork, but its other
* references have already been removed from the stable tree.
+ * Or it might be left over from a break_ksm which failed
+ * when the mem_cgroup had reached its limit: try again now.
*/
if (PageKsm(page))
break_cow(rmap_item->mm, rmap_item->address);
mm = slot->mm;
down_read(&mm->mmap_sem);
- for (vma = find_vma(mm, ksm_scan.address); vma; vma = vma->vm_next) {
+ if (ksm_test_exit(mm))
+ vma = NULL;
+ else
+ vma = find_vma(mm, ksm_scan.address);
+
+ for (; vma; vma = vma->vm_next) {
if (!(vma->vm_flags & VM_MERGEABLE))
continue;
if (ksm_scan.address < vma->vm_start)
ksm_scan.address = vma->vm_end;
while (ksm_scan.address < vma->vm_end) {
+ if (ksm_test_exit(mm))
+ break;
*page = follow_page(vma, ksm_scan.address, FOLL_GET);
if (*page && PageAnon(*page)) {
flush_anon_page(vma, *page, ksm_scan.address);
}
}
- if (!ksm_scan.address) {
- /*
- * We've completed a full scan of all vmas, holding mmap_sem
- * throughout, and found no VM_MERGEABLE: so do the same as
- * __ksm_exit does to remove this mm from all our lists now.
- */
- remove_mm_from_lists(mm);
- up_read(&mm->mmap_sem);
- slot = ksm_scan.mm_slot;
- if (slot != &ksm_mm_head)
- goto next_mm;
- return NULL;
+ if (ksm_test_exit(mm)) {
+ ksm_scan.address = 0;
+ ksm_scan.rmap_item = list_entry(&slot->rmap_list,
+ struct rmap_item, link);
}
-
/*
* Nuke all the rmap_items that are above this current rmap:
* because there were no VM_MERGEABLE vmas with such addresses.
*/
remove_trailing_rmap_items(slot, ksm_scan.rmap_item->link.next);
- up_read(&mm->mmap_sem);
spin_lock(&ksm_mmlist_lock);
- slot = list_entry(slot->mm_list.next, struct mm_slot, mm_list);
- ksm_scan.mm_slot = slot;
- spin_unlock(&ksm_mmlist_lock);
+ ksm_scan.mm_slot = list_entry(slot->mm_list.next,
+ struct mm_slot, mm_list);
+ if (ksm_scan.address == 0) {
+ /*
+ * We've completed a full scan of all vmas, holding mmap_sem
+ * throughout, and found no VM_MERGEABLE: so do the same as
+ * __ksm_exit does to remove this mm from all our lists now.
+ * This applies either when cleaning up after __ksm_exit
+ * (but beware: we can reach here even before __ksm_exit),
+ * or when all VM_MERGEABLE areas have been unmapped (and
+ * mmap_sem then protects against race with MADV_MERGEABLE).
+ */
+ hlist_del(&slot->link);
+ list_del(&slot->mm_list);
+ spin_unlock(&ksm_mmlist_lock);
+
+ free_mm_slot(slot);
+ clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+ up_read(&mm->mmap_sem);
+ mmdrop(mm);
+ } else {
+ spin_unlock(&ksm_mmlist_lock);
+ up_read(&mm->mmap_sem);
+ }
/* Repeat until we've completed scanning the whole list */
+ slot = ksm_scan.mm_slot;
if (slot != &ksm_mm_head)
goto next_mm;
- /*
- * Bump seqnr here rather than at top, so that __ksm_exit
- * can skip rb_erase on unstable tree until we run again.
- */
ksm_scan.seqnr++;
return NULL;
}
unsigned long end, int advice, unsigned long *vm_flags)
{
struct mm_struct *mm = vma->vm_mm;
+ int err;
switch (advice) {
case MADV_MERGEABLE:
VM_MIXEDMAP | VM_SAO))
return 0; /* just ignore the advice */
- if (!test_bit(MMF_VM_MERGEABLE, &mm->flags))
- if (__ksm_enter(mm) < 0)
- return -EAGAIN;
+ if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
+ err = __ksm_enter(mm);
+ if (err)
+ return err;
+ }
*vm_flags |= VM_MERGEABLE;
break;
if (!(*vm_flags & VM_MERGEABLE))
return 0; /* just ignore the advice */
- if (vma->anon_vma)
- unmerge_ksm_pages(vma, start, end);
+ if (vma->anon_vma) {
+ err = unmerge_ksm_pages(vma, start, end);
+ if (err)
+ return err;
+ }
*vm_flags &= ~VM_MERGEABLE;
break;
spin_unlock(&ksm_mmlist_lock);
set_bit(MMF_VM_MERGEABLE, &mm->flags);
+ atomic_inc(&mm->mm_count);
if (needs_wakeup)
wake_up_interruptible(&ksm_thread_wait);
void __ksm_exit(struct mm_struct *mm)
{
+ struct mm_slot *mm_slot;
+ int easy_to_free = 0;
+
/*
- * This process is exiting: doesn't hold and doesn't need mmap_sem;
- * but we do need to exclude ksmd and other exiters while we modify
- * the various lists and trees.
+ * This process is exiting: if it's straightforward (as is the
+ * case when ksmd was never running), free mm_slot immediately.
+ * But if it's at the cursor or has rmap_items linked to it, use
+ * mmap_sem to synchronize with any break_cows before pagetables
+ * are freed, and leave the mm_slot on the list for ksmd to free.
+ * Beware: ksm may already have noticed it exiting and freed the slot.
*/
- mutex_lock(&ksm_thread_mutex);
- remove_mm_from_lists(mm);
- mutex_unlock(&ksm_thread_mutex);
+
+ spin_lock(&ksm_mmlist_lock);
+ mm_slot = get_mm_slot(mm);
+ if (mm_slot && ksm_scan.mm_slot != mm_slot) {
+ if (list_empty(&mm_slot->rmap_list)) {
+ hlist_del(&mm_slot->link);
+ list_del(&mm_slot->mm_list);
+ easy_to_free = 1;
+ } else {
+ list_move(&mm_slot->mm_list,
+ &ksm_scan.mm_slot->mm_list);
+ }
+ }
+ spin_unlock(&ksm_mmlist_lock);
+
+ if (easy_to_free) {
+ free_mm_slot(mm_slot);
+ clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+ mmdrop(mm);
+ } else if (mm_slot) {
+ down_write(&mm->mmap_sem);
+ up_write(&mm->mmap_sem);
+ }
}
+#ifdef CONFIG_SYSFS
+/*
+ * This all compiles without CONFIG_SYSFS, but is a waste of space.
+ */
+
#define KSM_ATTR_RO(_name) \
static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
#define KSM_ATTR(_name) \
mutex_lock(&ksm_thread_mutex);
if (ksm_run != flags) {
ksm_run = flags;
- if (flags & KSM_RUN_UNMERGE)
- unmerge_and_remove_all_rmap_items();
+ if (flags & KSM_RUN_UNMERGE) {
+ current->flags |= PF_OOM_ORIGIN;
+ err = unmerge_and_remove_all_rmap_items();
+ current->flags &= ~PF_OOM_ORIGIN;
+ if (err) {
+ ksm_run = KSM_RUN_STOP;
+ count = err;
+ }
+ }
}
mutex_unlock(&ksm_thread_mutex);
.attrs = ksm_attrs,
.name = "ksm",
};
+#endif /* CONFIG_SYSFS */
static int __init ksm_init(void)
{
struct task_struct *ksm_thread;
int err;
+ ksm_init_max_kernel_pages();
+
err = ksm_slab_init();
if (err)
goto out;
goto out_free2;
}
+#ifdef CONFIG_SYSFS
err = sysfs_create_group(mm_kobj, &ksm_attr_group);
if (err) {
printk(KERN_ERR "ksm: register sysfs failed\n");
- goto out_free3;
+ kthread_stop(ksm_thread);
+ goto out_free2;
}
+#endif /* CONFIG_SYSFS */
return 0;
-out_free3:
- kthread_stop(ksm_thread);
out_free2:
mm_slots_hash_free();
out_free1: