1 files changed, 242 insertions, 19 deletions

diff --git a/mm/ksm.c b/mm/ksm.c
index 2b8d30068cbb..0156bded3a66 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -45,6 +45,9 @@
 #include "internal.h"
 #include "mm_slot.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/ksm.h>
+
 #ifdef CONFIG_NUMA
 #define NUMA(x)		(x)
 #define DO_NUMA(x)	do { (x); } while (0)
@@ -512,6 +515,28 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 	return (ret & VM_FAULT_OOM) ? -ENOMEM : 0;
 }
 
+static bool vma_ksm_compatible(struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & (VM_SHARED  | VM_MAYSHARE   | VM_PFNMAP  |
+			     VM_IO      | VM_DONTEXPAND | VM_HUGETLB |
+			     VM_MIXEDMAP))
+		return false;		/* just ignore the advice */
+
+	if (vma_is_dax(vma))
+		return false;
+
+#ifdef VM_SAO
+	if (vma->vm_flags & VM_SAO)
+		return false;
+#endif
+#ifdef VM_SPARC_ADI
+	if (vma->vm_flags & VM_SPARC_ADI)
+		return false;
+#endif
+
+	return true;
+}
+
 static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm,
 		unsigned long addr)
 {
@@ -633,10 +658,12 @@ static void remove_node_from_stable_tree(struct ksm_stable_node *stable_node)
 	BUG_ON(stable_node->rmap_hlist_len < 0);
 
 	hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
-		if (rmap_item->hlist.next)
+		if (rmap_item->hlist.next) {
 			ksm_pages_sharing--;
-		else
+			trace_ksm_remove_rmap_item(stable_node->kpfn, rmap_item, rmap_item->mm);
+		} else {
 			ksm_pages_shared--;
+		}
 
 		rmap_item->mm->ksm_merging_pages--;
 
@@ -657,6 +684,7 @@ static void remove_node_from_stable_tree(struct ksm_stable_node *stable_node)
 	BUILD_BUG_ON(STABLE_NODE_DUP_HEAD <= &migrate_nodes);
 	BUILD_BUG_ON(STABLE_NODE_DUP_HEAD >= &migrate_nodes + 1);
 
+	trace_ksm_remove_ksm_page(stable_node->kpfn);
 	if (stable_node->head == &migrate_nodes)
 		list_del(&stable_node->list);
 	else
@@ -1020,6 +1048,7 @@ mm_exiting:
 
 			mm_slot_free(mm_slot_cache, mm_slot);
 			clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+			clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
 			mmdrop(mm);
 		} else
 			spin_unlock(&ksm_mmlist_lock);
@@ -1324,6 +1353,8 @@ static int try_to_merge_with_ksm_page(struct ksm_rmap_item *rmap_item,
 	get_anon_vma(vma->anon_vma);
 out:
 	mmap_read_unlock(mm);
+	trace_ksm_merge_with_ksm_page(kpage, page_to_pfn(kpage ? kpage : page),
+				rmap_item, mm, err);
 	return err;
 }
 
@@ -2142,6 +2173,9 @@ static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_ite
 		if (vma) {
 			err = try_to_merge_one_page(vma, page,
 					ZERO_PAGE(rmap_item->address));
+			trace_ksm_merge_one_page(
+				page_to_pfn(ZERO_PAGE(rmap_item->address)),
+				rmap_item, mm, err);
 		} else {
 			/*
 			 * If the vma is out of date, we do not need to
@@ -2264,6 +2298,8 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
 
 	mm_slot = ksm_scan.mm_slot;
 	if (mm_slot == &ksm_mm_head) {
+		trace_ksm_start_scan(ksm_scan.seqnr, ksm_rmap_items);
+
 		/*
 		 * A number of pages can hang around indefinitely on per-cpu
 		 * pagevecs, raised page count preventing write_protect_page
@@ -2395,6 +2431,7 @@ no_vmas:
 
 		mm_slot_free(mm_slot_cache, mm_slot);
 		clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+		clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
 		mmap_read_unlock(mm);
 		mmdrop(mm);
 	} else {
@@ -2414,6 +2451,7 @@ no_vmas:
 	if (mm_slot != &ksm_mm_head)
 		goto next_mm;
 
+	trace_ksm_stop_scan(ksm_scan.seqnr, ksm_rmap_items);
 	ksm_scan.seqnr++;
 	return NULL;
 }
@@ -2471,6 +2509,136 @@ static int ksm_scan_thread(void *nothing)
 	return 0;
 }
 
+static void __ksm_add_vma(struct vm_area_struct *vma)
+{
+	unsigned long vm_flags = vma->vm_flags;
+
+	if (vm_flags & VM_MERGEABLE)
+		return;
+
+	if (vma_ksm_compatible(vma))
+		vm_flags_set(vma, VM_MERGEABLE);
+}
+
+static int __ksm_del_vma(struct vm_area_struct *vma)
+{
+	int err;
+
+	if (!(vma->vm_flags & VM_MERGEABLE))
+		return 0;
+
+	if (vma->anon_vma) {
+		err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end);
+		if (err)
+			return err;
+	}
+
+	vm_flags_clear(vma, VM_MERGEABLE);
+	return 0;
+}
+/**
+ * ksm_add_vma - Mark vma as mergeable if compatible
+ *
+ * @vma:  Pointer to vma
+ */
+void ksm_add_vma(struct vm_area_struct *vma)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
+		__ksm_add_vma(vma);
+}
+
+static void ksm_add_vmas(struct mm_struct *mm)
+{
+	struct vm_area_struct *vma;
+
+	VMA_ITERATOR(vmi, mm, 0);
+	for_each_vma(vmi, vma)
+		__ksm_add_vma(vma);
+}
+
+static int ksm_del_vmas(struct mm_struct *mm)
+{
+	struct vm_area_struct *vma;
+	int err;
+
+	VMA_ITERATOR(vmi, mm, 0);
+	for_each_vma(vmi, vma) {
+		err = __ksm_del_vma(vma);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+/**
+ * ksm_enable_merge_any - Add mm to mm ksm list and enable merging on all
+ *                        compatible VMA's
+ *
+ * @mm:  Pointer to mm
+ *
+ * Returns 0 on success, otherwise error code
+ */
+int ksm_enable_merge_any(struct mm_struct *mm)
+{
+	int err;
+
+	if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
+		return 0;
+
+	if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
+		err = __ksm_enter(mm);
+		if (err)
+			return err;
+	}
+
+	set_bit(MMF_VM_MERGE_ANY, &mm->flags);
+	ksm_add_vmas(mm);
+
+	return 0;
+}
+
+/**
+ * ksm_disable_merge_any - Disable merging on all compatible VMA's of the mm,
+ *			   previously enabled via ksm_enable_merge_any().
+ *
+ * Disabling merging implies unmerging any merged pages, like setting
+ * MADV_UNMERGEABLE would. If unmerging fails, the whole operation fails and
+ * merging on all compatible VMA's remains enabled.
+ *
+ * @mm: Pointer to mm
+ *
+ * Returns 0 on success, otherwise error code
+ */
+int ksm_disable_merge_any(struct mm_struct *mm)
+{
+	int err;
+
+	if (!test_bit(MMF_VM_MERGE_ANY, &mm->flags))
+		return 0;
+
+	err = ksm_del_vmas(mm);
+	if (err) {
+		ksm_add_vmas(mm);
+		return err;
+	}
+
+	clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
+	return 0;
+}
+
+int ksm_disable(struct mm_struct *mm)
+{
+	mmap_assert_write_locked(mm);
+
+	if (!test_bit(MMF_VM_MERGEABLE, &mm->flags))
+		return 0;
+	if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
+		return ksm_disable_merge_any(mm);
+	return ksm_del_vmas(mm);
+}
+
 int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 		unsigned long end, int advice, unsigned long *vm_flags)
 {
@@ -2479,25 +2647,10 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 
 	switch (advice) {
 	case MADV_MERGEABLE:
-		/*
-		 * Be somewhat over-protective for now!
-		 */
-		if (*vm_flags & (VM_MERGEABLE | VM_SHARED  | VM_MAYSHARE   |
-				 VM_PFNMAP    | VM_IO      | VM_DONTEXPAND |
-				 VM_HUGETLB | VM_MIXEDMAP))
-			return 0;		/* just ignore the advice */
-
-		if (vma_is_dax(vma))
-			return 0;
-
-#ifdef VM_SAO
-		if (*vm_flags & VM_SAO)
+		if (vma->vm_flags & VM_MERGEABLE)
 			return 0;
-#endif
-#ifdef VM_SPARC_ADI
-		if (*vm_flags & VM_SPARC_ADI)
+		if (!vma_ksm_compatible(vma))
 			return 0;
-#endif
 
 		if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
 			err = __ksm_enter(mm);
@@ -2565,6 +2718,7 @@ int __ksm_enter(struct mm_struct *mm)
 	if (needs_wakeup)
 		wake_up_interruptible(&ksm_thread_wait);
 
+	trace_ksm_enter(mm);
 	return 0;
 }
 
@@ -2600,12 +2754,15 @@ void __ksm_exit(struct mm_struct *mm)
 
 	if (easy_to_free) {
 		mm_slot_free(mm_slot_cache, mm_slot);
+		clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
 		clear_bit(MMF_VM_MERGEABLE, &mm->flags);
 		mmdrop(mm);
 	} else if (mm_slot) {
 		mmap_write_lock(mm);
 		mmap_write_unlock(mm);
 	}
+
+	trace_ksm_exit(mm);
 }
 
 struct page *ksm_might_need_to_copy(struct page *page,
@@ -2721,6 +2878,51 @@ again:
 		goto again;
 }
 
+#ifdef CONFIG_MEMORY_FAILURE
+/*
+ * Collect processes when the error hit an ksm page.
+ */
+void collect_procs_ksm(struct page *page, struct list_head *to_kill,
+		       int force_early)
+{
+	struct ksm_stable_node *stable_node;
+	struct ksm_rmap_item *rmap_item;
+	struct folio *folio = page_folio(page);
+	struct vm_area_struct *vma;
+	struct task_struct *tsk;
+
+	stable_node = folio_stable_node(folio);
+	if (!stable_node)
+		return;
+	hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
+		struct anon_vma *av = rmap_item->anon_vma;
+
+		anon_vma_lock_read(av);
+		read_lock(&tasklist_lock);
+		for_each_process(tsk) {
+			struct anon_vma_chain *vmac;
+			unsigned long addr;
+			struct task_struct *t =
+				task_early_kill(tsk, force_early);
+			if (!t)
+				continue;
+			anon_vma_interval_tree_foreach(vmac, &av->rb_root, 0,
+						       ULONG_MAX)
+			{
+				vma = vmac->vma;
+				if (vma->vm_mm == t->mm) {
+					addr = rmap_item->address & PAGE_MASK;
+					add_to_kill_ksm(t, page, vma, to_kill,
+							addr);
+				}
+			}
+		}
+		read_unlock(&tasklist_lock);
+		anon_vma_unlock_read(av);
+	}
+}
+#endif
+
 #ifdef CONFIG_MIGRATION
 void folio_migrate_ksm(struct folio *newfolio, struct folio *folio)
 {
@@ -2875,6 +3077,14 @@ static void wait_while_offlining(void)
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
+#ifdef CONFIG_PROC_FS
+long ksm_process_profit(struct mm_struct *mm)
+{
+	return mm->ksm_merging_pages * PAGE_SIZE -
+		mm->ksm_rmap_items * sizeof(struct ksm_rmap_item);
+}
+#endif /* CONFIG_PROC_FS */
+
 #ifdef CONFIG_SYSFS
 /*
  * This all compiles without CONFIG_SYSFS, but is a waste of space.
@@ -3139,6 +3349,18 @@ static ssize_t pages_volatile_show(struct kobject *kobj,
 }
 KSM_ATTR_RO(pages_volatile);
 
+static ssize_t general_profit_show(struct kobject *kobj,
+				   struct kobj_attribute *attr, char *buf)
+{
+	long general_profit;
+
+	general_profit = ksm_pages_sharing * PAGE_SIZE -
+				ksm_rmap_items * sizeof(struct ksm_rmap_item);
+
+	return sysfs_emit(buf, "%ld\n", general_profit);
+}
+KSM_ATTR_RO(general_profit);
+
 static ssize_t stable_node_dups_show(struct kobject *kobj,
 				     struct kobj_attribute *attr, char *buf)
 {
@@ -3203,6 +3425,7 @@ static struct attribute *ksm_attrs[] = {
 	&stable_node_dups_attr.attr,
 	&stable_node_chains_prune_millisecs_attr.attr,
 	&use_zero_pages_attr.attr,
+	&general_profit_attr.attr,
 	NULL,
 };