15 files changed, 114 insertions, 105 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 41b95d82a185..18af2bcefe6a 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -652,18 +652,9 @@ static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
 }
 #endif
 
-#ifndef pmd_move_must_withdraw
-static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl,
-					 spinlock_t *old_pmd_ptl)
-{
-	/*
-	 * With split pmd lock we also need to move preallocated
-	 * PTE page table if new_pmd is on different PMD page table.
-	 */
-	return new_pmd_ptl != old_pmd_ptl;
-}
+#ifndef arch_needs_pgtable_deposit
+#define arch_needs_pgtable_deposit() (false)
 #endif
-
 /*
  * This function is meant to be used by sites walking pagetables with
  * the mmap_sem hold in read mode to protect against MADV_DONTNEED and
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index c6d667187608..7eed8cf3130a 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -107,11 +107,6 @@ struct mmu_gather {
 	struct mmu_gather_batch	local;
 	struct page		*__pages[MMU_GATHER_BUNDLE];
 	unsigned int		batch_count;
-	/*
-	 * __tlb_adjust_range  will track the new addr here,
-	 * that that we can adjust the range after the flush
-	 */
-	unsigned long addr;
 	int page_size;
 };
 
@@ -125,16 +120,11 @@ extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
 				   int page_size);
 
 static inline void __tlb_adjust_range(struct mmu_gather *tlb,
-				      unsigned long address)
+				      unsigned long address,
+				      unsigned int range_size)
 {
 	tlb->start = min(tlb->start, address);
-	tlb->end = max(tlb->end, address + PAGE_SIZE);
-	/*
-	 * Track the last address with which we adjusted the range. This
-	 * will be used later to adjust again after a mmu_flush due to
-	 * failed __tlb_remove_page
-	 */
-	tlb->addr = address;
+	tlb->end = max(tlb->end, address + range_size);
 }
 
 static inline void __tlb_reset_range(struct mmu_gather *tlb)
@@ -150,15 +140,11 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 static inline void tlb_remove_page_size(struct mmu_gather *tlb,
 					struct page *page, int page_size)
 {
-	if (__tlb_remove_page_size(tlb, page, page_size)) {
+	if (__tlb_remove_page_size(tlb, page, page_size))
 		tlb_flush_mmu(tlb);
-		tlb->page_size = page_size;
-		__tlb_adjust_range(tlb, tlb->addr);
-		__tlb_remove_page_size(tlb, page, page_size);
-	}
 }
 
-static bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
 	return __tlb_remove_page_size(tlb, page, PAGE_SIZE);
 }
@@ -172,14 +158,21 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	return tlb_remove_page_size(tlb, page, PAGE_SIZE);
 }
 
-static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *page)
+#ifndef tlb_remove_check_page_size_change
+#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
+static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
+						     unsigned int page_size)
 {
-	/* active->nr should be zero when we call this */
-	VM_BUG_ON_PAGE(tlb->active->nr, page);
-	tlb->page_size = PAGE_SIZE;
-	__tlb_adjust_range(tlb, tlb->addr);
-	return __tlb_remove_page(tlb, page);
+	/*
+	 * We don't care about page size change, just update
+	 * mmu_gather page size here so that debug checks
+	 * doesn't throw false warning.
+	 */
+#ifdef CONFIG_DEBUG_VM
+	tlb->page_size = page_size;
+#endif
 }
+#endif
 
 /*
  * In the case of tlb vma handling, we can optimise these away in the
@@ -215,10 +208,16 @@ static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *pa
  */
 #define tlb_remove_tlb_entry(tlb, ptep, address)		\
 	do {							\
-		__tlb_adjust_range(tlb, address);		\
+		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
+#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	     \
+	do {							     \
+		__tlb_adjust_range(tlb, address, huge_page_size(h)); \
+		__tlb_remove_tlb_entry(tlb, ptep, address);	     \
+	} while (0)
+
 /**
  * tlb_remove_pmd_tlb_entry - remember a pmd mapping for later tlb invalidation
  * This is a nop so far, because only x86 needs it.
@@ -227,29 +226,47 @@ static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *pa
 #define __tlb_remove_pmd_tlb_entry(tlb, pmdp, address) do {} while (0)
 #endif
 
-#define tlb_remove_pmd_tlb_entry(tlb, pmdp, address)		\
-	do {							\
-		__tlb_adjust_range(tlb, address);		\
-		__tlb_remove_pmd_tlb_entry(tlb, pmdp, address);	\
+#define tlb_remove_pmd_tlb_entry(tlb, pmdp, address)			\
+	do {								\
+		__tlb_adjust_range(tlb, address, HPAGE_PMD_SIZE);	\
+		__tlb_remove_pmd_tlb_entry(tlb, pmdp, address);		\
 	} while (0)
 
+/*
+ * For things like page tables caches (ie caching addresses "inside" the
+ * page tables, like x86 does), for legacy reasons, flushing an
+ * individual page had better flush the page table caches behind it. This
+ * is definitely how x86 works, for example. And if you have an
+ * architected non-legacy page table cache (which I'm not aware of
+ * anybody actually doing), you're going to have some architecturally
+ * explicit flushing for that, likely *separate* from a regular TLB entry
+ * flush, and thus you'd need more than just some range expansion..
+ *
+ * So if we ever find an architecture
+ * that would want something that odd, I think it is up to that
+ * architecture to do its own odd thing, not cause pain for others
+ * http://lkml.kernel.org/r/CA+55aFzBggoXtNXQeng5d_mRoDnaMBE5Y+URs+PHR67nUpMtaw@mail.gmail.com
+ *
+ * For now w.r.t page table cache, mark the range_size as PAGE_SIZE
+ */
+
 #define pte_free_tlb(tlb, ptep, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address);		\
+		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
 		__pte_free_tlb(tlb, ptep, address);		\
 	} while (0)
 
 #ifndef __ARCH_HAS_4LEVEL_HACK
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address);		\
+		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
 		__pud_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
 
 #define pmd_free_tlb(tlb, pmdp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address);		\
+		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
 		__pmd_free_tlb(tlb, pmdp, address);		\
 	} while (0)
 
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index c357f27d5483..0b5b1af35e5e 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -136,12 +136,13 @@ struct bdi_writeback {
 struct backing_dev_info {
 	struct list_head bdi_list;
 	unsigned long ra_pages;	/* max readahead in PAGE_SIZE units */
-	unsigned int capabilities; /* Device capabilities */
+	unsigned long io_pages;	/* max allowed IO size */
 	congested_fn *congested_fn; /* Function pointer if device is md/dm */
 	void *congested_data;	/* Pointer to aux data for congested func */
 
 	char *name;
 
+	unsigned int capabilities; /* Device capabilities */
 	unsigned int min_ratio;
 	unsigned int max_ratio, max_prop_frac;
 
diff --git a/include/linux/cma.h b/include/linux/cma.h
index 29f9e774ab76..6f0a91b37f68 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -1,6 +1,9 @@
 #ifndef __CMA_H__
 #define __CMA_H__
 
+#include <linux/init.h>
+#include <linux/types.h>
+
 /*
  * There is always at least global CMA area and a few optional
  * areas configured in kernel .config.
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 928e5ca0caee..0444b1336268 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -21,7 +21,7 @@
  * clobbered. The issue is as follows: while the inline asm might
  * access any memory it wants, the compiler could have fit all of
  * @ptr into memory registers instead, and since @ptr never escaped
- * from that, it proofed that the inline asm wasn't touching any of
+ * from that, it proved that the inline asm wasn't touching any of
  * it. This version works well with both compilers, i.e. we're telling
  * the compiler that the inline asm absolutely may see the contents
  * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index e35e6de633b9..1f782aa1d8e6 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -189,6 +189,8 @@ static inline void deferred_split_huge_page(struct page *page) {}
 #define split_huge_pmd(__vma, __pmd, __address)	\
 	do { } while (0)
 
+static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+		unsigned long address, bool freeze, struct page *page) {}
 static inline void split_huge_pmd_address(struct vm_area_struct *vma,
 		unsigned long address, bool freeze, struct page *page) {}
 
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index c1c3e63d52c1..4fec8b775895 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -175,7 +175,7 @@ __printf(2, 3)
 struct kthread_worker *
 kthread_create_worker(unsigned int flags, const char namefmt[], ...);
 
-struct kthread_worker *
+__printf(3, 4) struct kthread_worker *
 kthread_create_worker_on_cpu(int cpu, unsigned int flags,
 			     const char namefmt[], ...);
 
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 5e5b2969d931..5f4d8281832b 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -7,6 +7,7 @@
 
 
 #include <linux/mmzone.h>
+#include <linux/dax.h>
 #include <linux/slab.h>
 #include <linux/rbtree.h>
 #include <linux/spinlock.h>
@@ -177,6 +178,13 @@ static inline bool vma_migratable(struct vm_area_struct *vma)
 	if (vma->vm_flags & (VM_IO | VM_PFNMAP))
 		return false;
 
+	/*
+	 * DAX device mappings require predictable access latency, so avoid
+	 * incurring periodic faults.
+	 */
+	if (vma_is_dax(vma))
+		return false;
+
 #ifndef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
 	if (vma->vm_flags & VM_HUGETLB)
 		return false;
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index 4341f32516d8..271b3fdf0070 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -71,6 +71,7 @@ extern int early_init_dt_scan_chosen_stdout(void);
 extern void early_init_fdt_scan_reserved_mem(void);
 extern void early_init_fdt_reserve_self(void);
 extern void early_init_dt_add_memory_arch(u64 base, u64 size);
+extern int early_init_dt_mark_hotplug_memory_arch(u64 base, u64 size);
 extern int early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size,
 					     bool no_map);
 extern void * early_init_dt_alloc_memory_arch(u64 size, u64 align);
diff --git a/include/linux/printk.h b/include/linux/printk.h
index eac1af8502bb..3472cc6b7a60 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -10,6 +10,8 @@
 extern const char linux_banner[];
 extern const char linux_proc_banner[];
 
+#define PRINTK_MAX_SINGLE_HEADER_LEN 2
+
 static inline int printk_get_level(const char *buffer)
 {
 	if (buffer[0] == KERN_SOH_ASCII && buffer[1]) {
@@ -31,6 +33,14 @@ static inline const char *printk_skip_level(const char *buffer)
 	return buffer;
 }
 
+static inline const char *printk_skip_headers(const char *buffer)
+{
+	while (printk_get_level(buffer))
+		buffer = printk_skip_level(buffer);
+
+	return buffer;
+}
+
 #define CONSOLE_EXT_LOG_MAX	8192
 
 /* printk's without a loglevel use this.. */
@@ -40,10 +50,15 @@ static inline const char *printk_skip_level(const char *buffer)
 #define CONSOLE_LOGLEVEL_SILENT  0 /* Mum's the word */
 #define CONSOLE_LOGLEVEL_MIN	 1 /* Minimum loglevel we let people use */
 #define CONSOLE_LOGLEVEL_QUIET	 4 /* Shhh ..., when booted with "quiet" */
-#define CONSOLE_LOGLEVEL_DEFAULT 7 /* anything MORE serious than KERN_DEBUG */
 #define CONSOLE_LOGLEVEL_DEBUG	10 /* issue debug messages */
 #define CONSOLE_LOGLEVEL_MOTORMOUTH 15	/* You can't shut this one up */
 
+/*
+ * Default used to be hard-coded at 7, we're now allowing it to be set from
+ * kernel config.
+ */
+#define CONSOLE_LOGLEVEL_DEFAULT CONFIG_CONSOLE_LOGLEVEL_DEFAULT
+
 extern int console_printk[];
 
 #define console_loglevel (console_printk[0])
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index af3581b8a451..744486057e9e 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -80,14 +80,11 @@ static inline bool radix_tree_is_internal_node(void *ptr)
 #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \
 					  RADIX_TREE_MAP_SHIFT))
 
-/* Internally used bits of node->count */
-#define RADIX_TREE_COUNT_SHIFT	(RADIX_TREE_MAP_SHIFT + 1)
-#define RADIX_TREE_COUNT_MASK	((1UL << RADIX_TREE_COUNT_SHIFT) - 1)
-
 struct radix_tree_node {
-	unsigned char	shift;	/* Bits remaining in each slot */
-	unsigned char	offset;	/* Slot offset in parent */
-	unsigned int	count;
+	unsigned char	shift;		/* Bits remaining in each slot */
+	unsigned char	offset;		/* Slot offset in parent */
+	unsigned char	count;		/* Total entry count */
+	unsigned char	exceptional;	/* Exceptional entry count */
 	union {
 		struct {
 			/* Used when ascending tree */
@@ -248,20 +245,6 @@ static inline int radix_tree_exception(void *arg)
 	return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK);
 }
 
-/**
- * radix_tree_replace_slot	- replace item in a slot
- * @pslot:	pointer to slot, returned by radix_tree_lookup_slot
- * @item:	new item to store in the slot.
- *
- * For use with radix_tree_lookup_slot().  Caller must hold tree write locked
- * across slot lookup and replacement.
- */
-static inline void radix_tree_replace_slot(void **pslot, void *item)
-{
-	BUG_ON(radix_tree_is_internal_node(item));
-	rcu_assign_pointer(*pslot, item);
-}
-
 int __radix_tree_create(struct radix_tree_root *root, unsigned long index,
 			unsigned order, struct radix_tree_node **nodep,
 			void ***slotp);
@@ -276,7 +259,14 @@ void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index,
 			  struct radix_tree_node **nodep, void ***slotp);
 void *radix_tree_lookup(struct radix_tree_root *, unsigned long);
 void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long);
-bool __radix_tree_delete_node(struct radix_tree_root *root,
+typedef void (*radix_tree_update_node_t)(struct radix_tree_node *, void *);
+void __radix_tree_replace(struct radix_tree_root *root,
+			  struct radix_tree_node *node,
+			  void **slot, void *item,
+			  radix_tree_update_node_t update_node, void *private);
+void radix_tree_replace_slot(struct radix_tree_root *root,
+			     void **slot, void *item);
+void __radix_tree_delete_node(struct radix_tree_root *root,
 			      struct radix_tree_node *node);
 void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
 void *radix_tree_delete(struct radix_tree_root *, unsigned long);
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index b46bb5620a76..15321fb1df6b 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -137,11 +137,19 @@ static inline void anon_vma_unlock_read(struct anon_vma *anon_vma)
  * anon_vma helper functions.
  */
 void anon_vma_init(void);	/* create anon_vma_cachep */
-int  anon_vma_prepare(struct vm_area_struct *);
+int  __anon_vma_prepare(struct vm_area_struct *);
 void unlink_anon_vmas(struct vm_area_struct *);
 int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *);
 int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *);
 
+static inline int anon_vma_prepare(struct vm_area_struct *vma)
+{
+	if (likely(vma->anon_vma))
+		return 0;
+
+	return __anon_vma_prepare(vma);
+}
+
 static inline void anon_vma_merge(struct vm_area_struct *vma,
 				  struct vm_area_struct *next)
 {
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7551d3e2ab70..0e90f2973719 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -540,7 +540,11 @@ static inline int get_dumpable(struct mm_struct *mm)
 					/* leave room for more dump flags */
 #define MMF_VM_MERGEABLE	16	/* KSM may merge identical pages */
 #define MMF_VM_HUGEPAGE		17	/* set when VM_HUGEPAGE is set on vma */
-#define MMF_EXE_FILE_CHANGED	18	/* see prctl_set_mm_exe_file() */
+/*
+ * This one-shot flag is dropped due to necessity of changing exe once again
+ * on NFS restore
+ */
+//#define MMF_EXE_FILE_CHANGED	18	/* see prctl_set_mm_exe_file() */
 
 #define MMF_HAS_UPROBES		19	/* has uprobes */
 #define MMF_RECALC_UPROBES	20	/* MMF_HAS_UPROBES can be wrong */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index a56523cefb9b..09b212d37f1d 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -246,39 +246,7 @@ struct swap_info_struct {
 void *workingset_eviction(struct address_space *mapping, struct page *page);
 bool workingset_refault(void *shadow);
 void workingset_activation(struct page *page);
-extern struct list_lru workingset_shadow_nodes;
-
-static inline unsigned int workingset_node_pages(struct radix_tree_node *node)
-{
-	return node->count & RADIX_TREE_COUNT_MASK;
-}
-
-static inline void workingset_node_pages_inc(struct radix_tree_node *node)
-{
-	node->count++;
-}
-
-static inline void workingset_node_pages_dec(struct radix_tree_node *node)
-{
-	VM_WARN_ON_ONCE(!workingset_node_pages(node));
-	node->count--;
-}
-
-static inline unsigned int workingset_node_shadows(struct radix_tree_node *node)
-{
-	return node->count >> RADIX_TREE_COUNT_SHIFT;
-}
-
-static inline void workingset_node_shadows_inc(struct radix_tree_node *node)
-{
-	node->count += 1U << RADIX_TREE_COUNT_SHIFT;
-}
-
-static inline void workingset_node_shadows_dec(struct radix_tree_node *node)
-{
-	VM_WARN_ON_ONCE(!workingset_node_shadows(node));
-	node->count -= 1U << RADIX_TREE_COUNT_SHIFT;
-}
+void workingset_update_node(struct radix_tree_node *node, void *private);
 
 /* linux/mm/page_alloc.c */
 extern unsigned long totalram_pages;
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 3d9d786a943c..d68edffbf142 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -82,6 +82,7 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align,
 			const void *caller);
 
 extern void vfree(const void *addr);
+extern void vfree_atomic(const void *addr);
 
 extern void *vmap(struct page **pages, unsigned int count,
 			unsigned long flags, pgprot_t prot);