add uksm 0.1.2.3 for v3.10 .ge.46.patch

Conflicts:
	fs/exec.c

Signed-off-by: Stefan Guendhoer <stefan@guendhoer.com>

6 files changed, 274 insertions, 18 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index dd6d9b89d..22490a43f 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -453,12 +453,25 @@ extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 			unsigned long size);
 #endif
 
+#ifdef CONFIG_UKSM
+static inline int is_uksm_zero_pfn(unsigned long pfn)
+{
+	extern unsigned long uksm_zero_pfn;
+        return pfn == uksm_zero_pfn;
+}
+#else
+static inline int is_uksm_zero_pfn(unsigned long pfn)
+{
+        return 0;
+}
+#endif
+
 #ifdef __HAVE_COLOR_ZERO_PAGE
 static inline int is_zero_pfn(unsigned long pfn)
 {
 	extern unsigned long zero_pfn;
 	unsigned long offset_from_zero_pfn = pfn - zero_pfn;
-	return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
+	return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT) || is_uksm_zero_pfn(pfn);
 }
 
 #define my_zero_pfn(addr)	page_to_pfn(ZERO_PAGE(addr))
@@ -467,7 +480,7 @@ static inline int is_zero_pfn(unsigned long pfn)
 static inline int is_zero_pfn(unsigned long pfn)
 {
 	extern unsigned long zero_pfn;
-	return pfn == zero_pfn;
+	return (pfn == zero_pfn) || (is_uksm_zero_pfn(pfn));
 }
 
 static inline unsigned long my_zero_pfn(unsigned long addr)
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 45c9b6a17..c7de7a78e 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -19,21 +19,6 @@ struct mem_cgroup;
 #ifdef CONFIG_KSM
 int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 		unsigned long end, int advice, unsigned long *vm_flags);
-int __ksm_enter(struct mm_struct *mm);
-void __ksm_exit(struct mm_struct *mm);
-
-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
-{
-	if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
-		return __ksm_enter(mm);
-	return 0;
-}
-
-static inline void ksm_exit(struct mm_struct *mm)
-{
-	if (test_bit(MMF_VM_MERGEABLE, &mm->flags))
-		__ksm_exit(mm);
-}
 
 /*
  * A KSM page is one of those write-protected "shared pages" or "merged pages"
@@ -80,6 +65,33 @@ int rmap_walk_ksm(struct page *page, int (*rmap_one)(struct page *,
 		  struct vm_area_struct *, unsigned long, void *), void *arg);
 void ksm_migrate_page(struct page *newpage, struct page *oldpage);
 
+#ifdef CONFIG_KSM_LEGACY
+int __ksm_enter(struct mm_struct *mm);
+void __ksm_exit(struct mm_struct *mm);
+static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+	if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
+		return __ksm_enter(mm);
+	return 0;
+}
+
+static inline void ksm_exit(struct mm_struct *mm)
+{
+	if (test_bit(MMF_VM_MERGEABLE, &mm->flags))
+		__ksm_exit(mm);
+}
+
+#elif defined(CONFIG_UKSM)
+static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+	return 0;
+}
+
+static inline void ksm_exit(struct mm_struct *mm)
+{
+}
+#endif /* !CONFIG_UKSM */
+
 #else  /* !CONFIG_KSM */
 
 static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
@@ -132,4 +144,6 @@ static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage)
 #endif /* CONFIG_MMU */
 #endif /* !CONFIG_KSM */
 
+#include <linux/uksm.h>
+
 #endif /* __LINUX_KSM_H */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index e4aaca1c3..d36db9f20 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -294,6 +294,9 @@ struct vm_area_struct {
 #ifdef CONFIG_NUMA
 	struct mempolicy *vm_policy;	/* NUMA policy for the VMA */
 #endif
+#ifdef CONFIG_UKSM
+	struct vma_slot *uksm_vma_slot;
+#endif
 };
 
 struct core_thread {
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index eca4a072a..14bef14cf 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -164,6 +164,9 @@ enum zone_stat_item {
 #if !defined(CONFIG_CMA) || !defined(CONFIG_MTK_SVP) // SVP 16
 	NR_FREE_CMA_PAGES,
 #endif
+#ifdef CONFIG_UKSM
+	NR_UKSM_ZERO_PAGES,
+#endif
 	NR_VM_ZONE_STAT_ITEMS };
 
 /*
@@ -930,7 +933,7 @@ static inline int is_normal_idx(enum zone_type idx)
 }
 
 /**
- * is_highmem - helper function to quickly check if a struct zone is a 
+ * is_highmem - helper function to quickly check if a struct zone is a
  *              highmem zone or not.  This is an attempt to keep references
  *              to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum.
  * @zone - pointer to struct zone variable
diff --git a/include/linux/sradix-tree.h b/include/linux/sradix-tree.h
new file mode 100644
index 000000000..6780fdb0a
--- /dev/null
+++ b/include/linux/sradix-tree.h
@@ -0,0 +1,77 @@
+#ifndef _LINUX_SRADIX_TREE_H
+#define _LINUX_SRADIX_TREE_H
+
+
+#define INIT_SRADIX_TREE(root, mask)					\
+do {									\
+	(root)->height = 0;						\
+	(root)->gfp_mask = (mask);					\
+	(root)->rnode = NULL;						\
+} while (0)
+
+#define ULONG_BITS	(sizeof(unsigned long) * 8)
+#define SRADIX_TREE_INDEX_BITS  (8 /* CHAR_BIT */ * sizeof(unsigned long))
+//#define SRADIX_TREE_MAP_SHIFT	6
+//#define SRADIX_TREE_MAP_SIZE	(1UL << SRADIX_TREE_MAP_SHIFT)
+//#define SRADIX_TREE_MAP_MASK	(SRADIX_TREE_MAP_SIZE-1)
+
+struct sradix_tree_node {
+	unsigned int	height;		/* Height from the bottom */
+	unsigned int	count;		
+	unsigned int	fulls;		/* Number of full sublevel trees */ 
+	struct sradix_tree_node *parent;
+	void *stores[0];
+};
+
+/* A simple radix tree implementation */
+struct sradix_tree_root {
+        unsigned int            height;
+        struct sradix_tree_node *rnode;
+
+	/* Where found to have available empty stores in its sublevels */
+        struct sradix_tree_node *enter_node;
+	unsigned int shift;
+	unsigned int stores_size;
+	unsigned int mask;
+	unsigned long min;	/* The first hole index */
+	unsigned long num;
+	//unsigned long *height_to_maxindex;
+
+	/* How the node is allocated and freed. */
+	struct sradix_tree_node *(*alloc)(void); 
+	void (*free)(struct sradix_tree_node *node);
+
+	/* When a new node is added and removed */
+	void (*extend)(struct sradix_tree_node *parent, struct sradix_tree_node *child);
+	void (*assign)(struct sradix_tree_node *node, unsigned index, void *item);
+	void (*rm)(struct sradix_tree_node *node, unsigned offset);
+};
+
+struct sradix_tree_path {
+	struct sradix_tree_node *node;
+	int offset;
+};
+
+static inline 
+void init_sradix_tree_root(struct sradix_tree_root *root, unsigned long shift)
+{
+	root->height = 0;
+	root->rnode = NULL;
+	root->shift = shift;
+	root->stores_size = 1UL << shift;
+	root->mask = root->stores_size - 1;
+}
+
+
+extern void *sradix_tree_next(struct sradix_tree_root *root,
+		       struct sradix_tree_node *node, unsigned long index,
+		       int (*iter)(void *, unsigned long));
+
+extern int sradix_tree_enter(struct sradix_tree_root *root, void **item, int num);
+
+extern void sradix_tree_delete_from_leaf(struct sradix_tree_root *root, 
+			struct sradix_tree_node *node, unsigned long index);
+
+extern void *sradix_tree_lookup(struct sradix_tree_root *root, unsigned long index);
+
+#endif /* _LINUX_SRADIX_TREE_H */
diff --git a/include/linux/uksm.h b/include/linux/uksm.h
new file mode 100644
index 000000000..a644bcae0
--- /dev/null
+++ b/include/linux/uksm.h
@@ -0,0 +1,146 @@
+#ifndef __LINUX_UKSM_H
+#define __LINUX_UKSM_H
+/*
+ * Memory merging support.
+ *
+ * This code enables dynamic sharing of identical pages found in different
+ * memory areas, even if they are not shared by fork().
+ */
+
+/* if !CONFIG_UKSM this file should not be compiled at all. */
+#ifdef CONFIG_UKSM
+
+#include <linux/bitops.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/rmap.h>
+#include <linux/sched.h>
+
+extern unsigned long zero_pfn __read_mostly;
+extern unsigned long uksm_zero_pfn __read_mostly;
+extern struct page *empty_uksm_zero_page;
+
+/* must be done before linked to mm */
+extern void uksm_vma_add_new(struct vm_area_struct *vma);
+extern void uksm_remove_vma(struct vm_area_struct *vma);
+
+#define UKSM_SLOT_NEED_SORT	(1 << 0)
+#define UKSM_SLOT_NEED_RERAND 	(1 << 1)
+#define UKSM_SLOT_SCANNED     	(1 << 2) /* It's scanned in this round */
+#define UKSM_SLOT_FUL_SCANNED 	(1 << 3)
+#define UKSM_SLOT_IN_UKSM 	(1 << 4)
+
+struct vma_slot {
+	struct sradix_tree_node *snode;
+	unsigned long sindex;
+
+	struct list_head slot_list;
+	unsigned long fully_scanned_round;
+	unsigned long dedup_num;
+	unsigned long pages_scanned;
+	unsigned long last_scanned;
+	unsigned long pages_to_scan;
+	struct scan_rung *rung;
+	struct page **rmap_list_pool;
+	unsigned int *pool_counts;
+	unsigned long pool_size;
+	struct vm_area_struct *vma;
+	struct mm_struct *mm;
+	unsigned long ctime_j;
+	unsigned long pages;
+	unsigned long flags;
+	unsigned long pages_cowed; /* pages cowed this round */
+	unsigned long pages_merged; /* pages merged this round */
+	unsigned long pages_bemerged;
+
+	/* when it has page merged in this eval round */
+	struct list_head dedup_list;
+};
+
+static inline void uksm_unmap_zero_page(pte_t pte)
+{
+	if (pte_pfn(pte) == uksm_zero_pfn)
+		__dec_zone_page_state(empty_uksm_zero_page, NR_UKSM_ZERO_PAGES);
+}
+
+static inline void uksm_map_zero_page(pte_t pte)
+{
+	if (pte_pfn(pte) == uksm_zero_pfn)
+		__inc_zone_page_state(empty_uksm_zero_page, NR_UKSM_ZERO_PAGES);
+}
+
+static inline void uksm_cow_page(struct vm_area_struct *vma, struct page *page)
+{
+	if (vma->uksm_vma_slot && PageKsm(page))
+		vma->uksm_vma_slot->pages_cowed++;
+}
+
+static inline void uksm_cow_pte(struct vm_area_struct *vma, pte_t pte)
+{
+	if (vma->uksm_vma_slot && pte_pfn(pte) == uksm_zero_pfn)
+		vma->uksm_vma_slot->pages_cowed++;
+}
+
+static inline int uksm_flags_can_scan(unsigned long vm_flags)
+{
+#ifndef VM_SAO
+#define VM_SAO 0
+#endif
+	return !(vm_flags & (VM_PFNMAP | VM_IO  | VM_DONTEXPAND |
+			     VM_HUGETLB | VM_NONLINEAR | VM_MIXEDMAP |
+			     VM_SHARED  | VM_MAYSHARE | VM_GROWSUP | VM_GROWSDOWN | VM_SAO));
+}
+
+static inline void uksm_vm_flags_mod(unsigned long *vm_flags_p)
+{
+	if (uksm_flags_can_scan(*vm_flags_p))
+		*vm_flags_p |= VM_MERGEABLE;
+}
+
+/*
+ * Just a wrapper for BUG_ON for where ksm_zeropage must not be. TODO: it will
+ * be removed when uksm zero page patch is stable enough.
+ */
+static inline void uksm_bugon_zeropage(pte_t pte)
+{
+	BUG_ON(pte_pfn(pte) == uksm_zero_pfn);
+}
+#else
+static inline void uksm_vma_add_new(struct vm_area_struct *vma)
+{
+}
+
+static inline void uksm_remove_vma(struct vm_area_struct *vma)
+{
+}
+
+static inline void uksm_unmap_zero_page(pte_t pte)
+{
+}
+
+static inline void uksm_map_zero_page(pte_t pte)
+{
+}
+
+static inline void uksm_cow_page(struct vm_area_struct *vma, struct page *page)
+{
+}
+
+static inline void uksm_cow_pte(struct vm_area_struct *vma, pte_t pte)
+{
+}
+
+static inline int uksm_flags_can_scan(unsigned long vm_flags)
+{
+	return 0;
+}
+
+static inline void uksm_vm_flags_mod(unsigned long *vm_flags_p)
+{
+}
+
+static inline void uksm_bugon_zeropage(pte_t pte)
+{
+}
+#endif /* !CONFIG_UKSM */
+#endif /* __LINUX_UKSM_H */