Merge branch 'akpm' (incoming from Andrew)

Merge patches from Andrew Morton:
 "23 fixes and a MAINTAINERS update"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (24 commits)
  mm/hugetlb: check for pte NULL pointer in __page_check_address()
  fix build with make 3.80
  mm/mempolicy: fix !vma in new_vma_page()
  MAINTAINERS: add Davidlohr as GPT maintainer
  mm/memory-failure.c: recheck PageHuge() after hugetlb page migrate successfully
  mm/compaction: respect ignore_skip_hint in update_pageblock_skip
  mm/mempolicy: correct putback method for isolate pages if failed
  mm: add missing dependency in Kconfig
  sh: always link in helper functions extracted from libgcc
  mm: page_alloc: exclude unreclaimable allocations from zone fairness policy
  mm: numa: defer TLB flush for THP migration as long as possible
  mm: numa: guarantee that tlb_flush_pending updates are visible before page table updates
  mm: fix TLB flush race between migration, and change_protection_range
  mm: numa: avoid unnecessary disruption of NUMA hinting during migration
  mm: numa: clear numa hinting information on mprotect
  sched: numa: skip inaccessible VMAs
  mm: numa: avoid unnecessary work on the failure path
  mm: numa: ensure anon_vma is locked to prevent parallel THP splits
  mm: numa: do not clear PTE for pte_numa update
  mm: numa: do not clear PMD during PTE update scan
  ...

MAINTAINERS

@@ -3833,6 +3833,12 @@ T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/usb/gspca/
 
+GUID PARTITION TABLE (GPT)
+M:	Davidlohr Bueso <davidlohr@hp.com>
+L:	linux-efi@vger.kernel.org
+S:	Maintained
+F:	block/partitions/efi.*
+
 STK1160 USB VIDEO CAPTURE DRIVER
 M:	Ezequiel Garcia <elezegarcia@gmail.com>
 L:	linux-media@vger.kernel.org

Makefile

@@ -732,19 +732,13 @@ export mod_strip_cmd
 # Select initial ramdisk compression format, default is gzip(1).
 # This shall be used by the dracut(8) tool while creating an initramfs image.
 #
-INITRD_COMPRESS=gzip
-ifeq ($(CONFIG_RD_BZIP2), y)
-        INITRD_COMPRESS=bzip2
-else ifeq ($(CONFIG_RD_LZMA), y)
-        INITRD_COMPRESS=lzma
-else ifeq ($(CONFIG_RD_XZ), y)
-        INITRD_COMPRESS=xz
-else ifeq ($(CONFIG_RD_LZO), y)
-        INITRD_COMPRESS=lzo
-else ifeq ($(CONFIG_RD_LZ4), y)
-        INITRD_COMPRESS=lz4
-endif
-export INITRD_COMPRESS
+INITRD_COMPRESS-y                  := gzip
+INITRD_COMPRESS-$(CONFIG_RD_BZIP2) := bzip2
+INITRD_COMPRESS-$(CONFIG_RD_LZMA)  := lzma
+INITRD_COMPRESS-$(CONFIG_RD_XZ)    := xz
+INITRD_COMPRESS-$(CONFIG_RD_LZO)   := lzo
+INITRD_COMPRESS-$(CONFIG_RD_LZ4)   := lz4
+export INITRD_COMPRESS := $(INITRD_COMPRESS-y)
 
 ifdef CONFIG_MODULE_SIG_ALL
 MODSECKEY = ./signing_key.priv

arch/sh/lib/Makefile

@@ -6,7 +6,7 @@ lib-y  = delay.o memmove.o memchr.o \
 	 checksum.o strlen.o div64.o div64-generic.o
 
 # Extracted from libgcc
-lib-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
+obj-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
 	 ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o \
 	 udiv_qrnnd.o
 

arch/sparc/include/asm/pgtable_64.h

@@ -619,7 +619,7 @@ static inline unsigned long pte_present(pte_t pte)
 }
 
 #define pte_accessible pte_accessible
-static inline unsigned long pte_accessible(pte_t a)
+static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a)
 {
 	return pte_val(a) & _PAGE_VALID;
 }
@@ -847,7 +847,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
 	 *             and SUN4V pte layout, so this inline test is fine.
 	 */
-	if (likely(mm != &init_mm) && pte_accessible(orig))
+	if (likely(mm != &init_mm) && pte_accessible(mm, orig))
 		tlb_batch_add(mm, addr, ptep, orig, fullmm);
 }
 

arch/x86/include/asm/pgtable.h

@@ -452,9 +452,16 @@ static inline int pte_present(pte_t a)
 }
 
 #define pte_accessible pte_accessible
-static inline int pte_accessible(pte_t a)
+static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
 {
-	return pte_flags(a) & _PAGE_PRESENT;
+	if (pte_flags(a) & _PAGE_PRESENT)
+		return true;
+
+	if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) &&
+			mm_tlb_flush_pending(mm))
+		return true;
+
+	return false;
 }
 
 static inline int pte_hidden(pte_t pte)

arch/x86/mm/gup.c

@@ -83,6 +83,12 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		pte_t pte = gup_get_pte(ptep);
 		struct page *page;
 
+		/* Similar to the PMD case, NUMA hinting must take slow path */
+		if (pte_numa(pte)) {
+			pte_unmap(ptep);
+			return 0;
+		}
+
 		if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
 			pte_unmap(ptep);
 			return 0;
@@ -167,6 +173,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
 		if (unlikely(pmd_large(pmd))) {
+			/*
+			 * NUMA hinting faults need to be handled in the GUP
+			 * slowpath for accounting purposes and so that they
+			 * can be serialised against THP migration.
+			 */
+			if (pmd_numa(pmd))
+				return 0;
 			if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))
 				return 0;
 		} else {

include/asm-generic/pgtable.h

@@ -217,7 +217,7 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 #endif
 
 #ifndef pte_accessible
-# define pte_accessible(pte)		((void)(pte),1)
+# define pte_accessible(mm, pte)	((void)(pte), 1)
 #endif
 
 #ifndef flush_tlb_fix_spurious_fault

include/linux/migrate.h

@@ -90,10 +90,19 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 #endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_NUMA_BALANCING
+extern bool pmd_trans_migrating(pmd_t pmd);
+extern void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd);
 extern int migrate_misplaced_page(struct page *page,
 				  struct vm_area_struct *vma, int node);
 extern bool migrate_ratelimited(int node);
 #else
+static inline bool pmd_trans_migrating(pmd_t pmd)
+{
+	return false;
+}
+static inline void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
+{
+}
 static inline int migrate_misplaced_page(struct page *page,
 					 struct vm_area_struct *vma, int node)
 {

include/linux/mm_types.h

@@ -442,6 +442,14 @@ struct mm_struct {
 
 	/* numa_scan_seq prevents two threads setting pte_numa */
 	int numa_scan_seq;
+#endif
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+	/*
+	 * An operation with batched TLB flushing is going on. Anything that
+	 * can move process memory needs to flush the TLB when moving a
+	 * PROT_NONE or PROT_NUMA mapped page.
+	 */
+	bool tlb_flush_pending;
 #endif
 	struct uprobes_state uprobes_state;
 };
@@ -459,4 +467,45 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
 	return mm->cpu_vm_mask_var;
 }
 
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+/*
+ * Memory barriers to keep this state in sync are graciously provided by
+ * the page table locks, outside of which no page table modifications happen.
+ * The barriers below prevent the compiler from re-ordering the instructions
+ * around the memory barriers that are already present in the code.
+ */
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+	barrier();
+	return mm->tlb_flush_pending;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+	mm->tlb_flush_pending = true;
+
+	/*
+	 * Guarantee that the tlb_flush_pending store does not leak into the
+	 * critical section updating the page tables
+	 */
+	smp_mb__before_spinlock();
+}
+/* Clearing is done after a TLB flush, which also provides a barrier. */
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+	barrier();
+	mm->tlb_flush_pending = false;
+}
+#else
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+	return false;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+#endif
+
 #endif /* _LINUX_MM_TYPES_H */

include/linux/reboot.h

@@ -43,6 +43,7 @@ extern int unregister_reboot_notifier(struct notifier_block *);
  * Architecture-specific implementations of sys_reboot commands.
  */
 
+extern void migrate_to_reboot_cpu(void);
 extern void machine_restart(char *cmd);
 extern void machine_halt(void);
 extern void machine_power_off(void);

kernel/fork.c

@@ -537,6 +537,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	spin_lock_init(&mm->page_table_lock);
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
+	clear_tlb_flush_pending(mm);
 
 	if (likely(!mm_alloc_pgd(mm))) {
 		mm->def_flags = 0;

kernel/kexec.c

@@ -1680,6 +1680,7 @@ int kernel_kexec(void)
 	{
 		kexec_in_progress = true;
 		kernel_restart_prepare(NULL);
+		migrate_to_reboot_cpu();
 		printk(KERN_EMERG "Starting new kernel\n");
 		machine_shutdown();
 	}

kernel/reboot.c

@@ -104,7 +104,7 @@ int unregister_reboot_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_reboot_notifier);
 
-static void migrate_to_reboot_cpu(void)
+void migrate_to_reboot_cpu(void)
 {
 	/* The boot cpu is always logical cpu 0 */
 	int cpu = reboot_cpu;

kernel/sched/fair.c

@@ -1738,6 +1738,13 @@ void task_numa_work(struct callback_head *work)
 		    (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ)))
 			continue;
 
+		/*
+		 * Skip inaccessible VMAs to avoid any confusion between
+		 * PROT_NONE and NUMA hinting ptes
+		 */
+		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
+			continue;
+
 		do {
 			start = max(start, vma->vm_start);
 			end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);

mm/Kconfig

@@ -543,7 +543,7 @@ config ZSWAP
 
 config MEM_SOFT_DIRTY
 	bool "Track memory changes"
-	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY
+	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
 	select PROC_PAGE_MONITOR
 	help
 	  This option enables memory changes tracking by introducing a

mm/compaction.c

@@ -134,6 +134,10 @@ static void update_pageblock_skip(struct compact_control *cc,
 			bool migrate_scanner)
 {
 	struct zone *zone = cc->zone;
+
+	if (cc->ignore_skip_hint)
+		return;
+
 	if (!page)
 		return;
 

mm/huge_memory.c

@@ -882,6 +882,10 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		ret = 0;
 		goto out_unlock;
 	}
+
+	/* mmap_sem prevents this happening but warn if that changes */
+	WARN_ON(pmd_trans_migrating(pmd));
+
 	if (unlikely(pmd_trans_splitting(pmd))) {
 		/* split huge page running from under us */
 		spin_unlock(src_ptl);
@@ -1243,6 +1247,10 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))
 		return ERR_PTR(-EFAULT);
 
+	/* Full NUMA hinting faults to serialise migration in fault paths */
+	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+		goto out;
+
 	page = pmd_page(*pmd);
 	VM_BUG_ON(!PageHead(page));
 	if (flags & FOLL_TOUCH) {
@@ -1295,6 +1303,17 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(!pmd_same(pmd, *pmdp)))
 		goto out_unlock;
 
+	/*
+	 * If there are potential migrations, wait for completion and retry
+	 * without disrupting NUMA hinting information. Do not relock and
+	 * check_same as the page may no longer be mapped.
+	 */
+	if (unlikely(pmd_trans_migrating(*pmdp))) {
+		spin_unlock(ptl);
+		wait_migrate_huge_page(vma->anon_vma, pmdp);
+		goto out;
+	}
+
 	page = pmd_page(pmd);
 	BUG_ON(is_huge_zero_page(page));
 	page_nid = page_to_nid(page);
@@ -1323,23 +1342,22 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		/* If the page was locked, there are no parallel migrations */
 		if (page_locked)
 			goto clear_pmdnuma;
+	}
 
-		/*
-		 * Otherwise wait for potential migrations and retry. We do
-		 * relock and check_same as the page may no longer be mapped.
-		 * As the fault is being retried, do not account for it.
-		 */
+	/* Migration could have started since the pmd_trans_migrating check */
+	if (!page_locked) {
 		spin_unlock(ptl);
 		wait_on_page_locked(page);
 		page_nid = -1;
 		goto out;
 	}
 
-	/* Page is misplaced, serialise migrations and parallel THP splits */
+	/*
+	 * Page is misplaced. Page lock serialises migrations. Acquire anon_vma
+	 * to serialises splits
+	 */
 	get_page(page);
 	spin_unlock(ptl);
-	if (!page_locked)
-		lock_page(page);
 	anon_vma = page_lock_anon_vma_read(page);
 
 	/* Confirm the PMD did not change while page_table_lock was released */
@@ -1351,6 +1369,13 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_unlock;
 	}
 
+	/* Bail if we fail to protect against THP splits for any reason */
+	if (unlikely(!anon_vma)) {
+		put_page(page);
+		page_nid = -1;
+		goto clear_pmdnuma;
+	}
+
 	/*
 	 * Migrate the THP to the requested node, returns with page unlocked
 	 * and pmd_numa cleared.
@@ -1517,6 +1542,8 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		ret = 1;
 		if (!prot_numa) {
 			entry = pmdp_get_and_clear(mm, addr, pmd);
+			if (pmd_numa(entry))
+				entry = pmd_mknonnuma(entry);
 			entry = pmd_modify(entry, newprot);
 			ret = HPAGE_PMD_NR;
 			BUG_ON(pmd_write(entry));
@@ -1531,7 +1558,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			 */
 			if (!is_huge_zero_page(page) &&
 			    !pmd_numa(*pmd)) {
-				entry = pmdp_get_and_clear(mm, addr, pmd);
+				entry = *pmd;
 				entry = pmd_mknuma(entry);
 				ret = HPAGE_PMD_NR;
 			}

mm/memory-failure.c

@@ -1505,10 +1505,16 @@ static int soft_offline_huge_page(struct page *page, int flags)
 		if (ret > 0)
 			ret = -EIO;
 	} else {
-		set_page_hwpoison_huge_page(hpage);
-		dequeue_hwpoisoned_huge_page(hpage);
-		atomic_long_add(1 << compound_order(hpage),
-				&num_poisoned_pages);
+		/* overcommit hugetlb page will be freed to buddy */
+		if (PageHuge(page)) {
+			set_page_hwpoison_huge_page(hpage);
+			dequeue_hwpoisoned_huge_page(hpage);
+			atomic_long_add(1 << compound_order(hpage),
+					&num_poisoned_pages);
+		} else {
+			SetPageHWPoison(page);
+			atomic_long_inc(&num_poisoned_pages);
+		}
 	}
 	return ret;
 }