Merge commit '8700c95adb03' into timers/nohz

The full dynticks tree needs the latest RCU and sched
upstream updates in order to fix some dependencies.

Merge a common upstream merge point that has these
updates.

Conflicts:
	include/linux/perf_event.h
	kernel/rcutree.h
	kernel/rcutree_plugin.h

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>

11 files changed, 70 insertions, 79 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index fa8c02de0d25..022a9a0a3c63 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -378,10 +378,12 @@ static noinline __kprobes int vmalloc_fault(unsigned long address)
 	if (pgd_none(*pgd_ref))
 		return -1;
 
-	if (pgd_none(*pgd))
+	if (pgd_none(*pgd)) {
 		set_pgd(pgd, *pgd_ref);
-	else
+		arch_flush_lazy_mmu_mode();
+	} else {
 		BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+	}
 
 	/*
 	 * Below here mismatches are bugs because these lower tables
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 6f31ee56c008..252b8f5489ba 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -137,5 +137,4 @@ void __init set_highmem_pages_init(void)
 		add_highpages_with_active_regions(nid, zone_start_pfn,
 				 zone_end_pfn);
 	}
-	totalram_pages += totalhigh_pages;
 }
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 4903a03ae876..fdc5dca14fb3 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -410,9 +410,8 @@ void __init init_mem_mapping(void)
 	/* the ISA range is always mapped regardless of memory holes */
 	init_memory_mapping(0, ISA_END_ADDRESS);
 
-	/* xen has big range in reserved near end of ram, skip it at first */
-	addr = memblock_find_in_range(ISA_END_ADDRESS, end, PMD_SIZE,
-			 PAGE_SIZE);
+	/* xen has big range in reserved near end of ram, skip it at first.*/
+	addr = memblock_find_in_range(ISA_END_ADDRESS, end, PMD_SIZE, PMD_SIZE);
 	real_end = addr + PMD_SIZE;
 
 	/* step_size need to be small so pgt_buf from BRK could cover it */
@@ -516,11 +515,8 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
 
 	for (; addr < end; addr += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(addr));
-		init_page_count(virt_to_page(addr));
 		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
-		free_page(addr);
-		totalram_pages++;
+		free_reserved_page(virt_to_page(addr));
 	}
 #endif
 }
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 2d19001151d5..3ac7e319918d 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -427,14 +427,6 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base)
 	pkmap_page_table = pte;
 }
 
-static void __init add_one_highpage_init(struct page *page)
-{
-	ClearPageReserved(page);
-	init_page_count(page);
-	__free_page(page);
-	totalhigh_pages++;
-}
-
 void __init add_highpages_with_active_regions(int nid,
 			 unsigned long start_pfn, unsigned long end_pfn)
 {
@@ -448,7 +440,7 @@ void __init add_highpages_with_active_regions(int nid,
 					      start_pfn, end_pfn);
 		for ( ; pfn < e_pfn; pfn++)
 			if (pfn_valid(pfn))
-				add_one_highpage_init(pfn_to_page(pfn));
+				free_highmem_page(pfn_to_page(pfn));
 	}
 }
 #else
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 474e28f10815..71ff55a1b287 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1011,11 +1011,8 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct)
 	flush_tlb_all();
 }
 
-void __ref vmemmap_free(struct page *memmap, unsigned long nr_pages)
+void __ref vmemmap_free(unsigned long start, unsigned long end)
 {
-	unsigned long start = (unsigned long)memmap;
-	unsigned long end = (unsigned long)(memmap + nr_pages);
-
 	remove_pagetable(start, end, false);
 }
 
@@ -1067,10 +1064,9 @@ void __init mem_init(void)
 
 	/* clear_bss() already clear the empty_zero_page */
 
-	reservedpages = 0;
-
-	/* this will put all low memory onto the freelists */
 	register_page_bootmem_info();
+
+	/* this will put all memory onto the freelists */
 	totalram_pages = free_all_bootmem();
 
 	absent_pages = absent_pages_in_range(0, max_pfn);
@@ -1285,18 +1281,17 @@ static long __meminitdata addr_start, addr_end;
 static void __meminitdata *p_start, *p_end;
 static int __meminitdata node_start;
 
-int __meminit
-vmemmap_populate(struct page *start_page, unsigned long size, int node)
+static int __meminit vmemmap_populate_hugepages(unsigned long start,
+						unsigned long end, int node)
 {
-	unsigned long addr = (unsigned long)start_page;
-	unsigned long end = (unsigned long)(start_page + size);
+	unsigned long addr;
 	unsigned long next;
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
 
-	for (; addr < end; addr = next) {
-		void *p = NULL;
+	for (addr = start; addr < end; addr = next) {
+		next = pmd_addr_end(addr, end);
 
 		pgd = vmemmap_pgd_populate(addr, node);
 		if (!pgd)
@@ -1306,31 +1301,14 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 		if (!pud)
 			return -ENOMEM;
 
-		if (!cpu_has_pse) {
-			next = (addr + PAGE_SIZE) & PAGE_MASK;
-			pmd = vmemmap_pmd_populate(pud, addr, node);
-
-			if (!pmd)
-				return -ENOMEM;
-
-			p = vmemmap_pte_populate(pmd, addr, node);
+		pmd = pmd_offset(pud, addr);
+		if (pmd_none(*pmd)) {
+			void *p;
 
-			if (!p)
-				return -ENOMEM;
-
-			addr_end = addr + PAGE_SIZE;
-			p_end = p + PAGE_SIZE;
-		} else {
-			next = pmd_addr_end(addr, end);
-
-			pmd = pmd_offset(pud, addr);
-			if (pmd_none(*pmd)) {
+			p = vmemmap_alloc_block_buf(PMD_SIZE, node);
+			if (p) {
 				pte_t entry;
 
-				p = vmemmap_alloc_block_buf(PMD_SIZE, node);
-				if (!p)
-					return -ENOMEM;
-
 				entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
 						PAGE_KERNEL_LARGE);
 				set_pmd(pmd, __pmd(pte_val(entry)));
@@ -1347,15 +1325,32 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 
 				addr_end = addr + PMD_SIZE;
 				p_end = p + PMD_SIZE;
-			} else
-				vmemmap_verify((pte_t *)pmd, node, addr, next);
+				continue;
+			}
+		} else if (pmd_large(*pmd)) {
+			vmemmap_verify((pte_t *)pmd, node, addr, next);
+			continue;
 		}
-
+		pr_warn_once("vmemmap: falling back to regular page backing\n");
+		if (vmemmap_populate_basepages(addr, next, node))
+			return -ENOMEM;
 	}
-	sync_global_pgds((unsigned long)start_page, end - 1);
 	return 0;
 }
 
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
+{
+	int err;
+
+	if (cpu_has_pse)
+		err = vmemmap_populate_hugepages(start, end, node);
+	else
+		err = vmemmap_populate_basepages(start, end, node);
+	if (!err)
+		sync_global_pgds(start, end - 1);
+	return err;
+}
+
 #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE)
 void register_page_bootmem_memmap(unsigned long section_nr,
 				  struct page *start_page, unsigned long size)
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 78fe3f1ac49f..9a1e6583910c 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -282,12 +282,7 @@ void iounmap(volatile void __iomem *addr)
 	   in parallel. Reuse of the virtual address is prevented by
 	   leaving it in the global lists until we're done with it.
 	   cpa takes care of the direct mappings. */
-	read_lock(&vmlist_lock);
-	for (p = vmlist; p; p = p->next) {
-		if (p->addr == (void __force *)addr)
-			break;
-	}
-	read_unlock(&vmlist_lock);
+	p = find_vm_area((void __force *)addr);
 
 	if (!p) {
 		printk(KERN_ERR "iounmap: bad address %p\n", addr);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 72fe01e9e414..a71c4e207679 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -114,14 +114,11 @@ void numa_clear_node(int cpu)
  */
 void __init setup_node_to_cpumask_map(void)
 {
-	unsigned int node, num = 0;
+	unsigned int node;
 
 	/* setup nr_node_ids if not done yet */
-	if (nr_node_ids == MAX_NUMNODES) {
-		for_each_node_mask(node, node_possible_map)
-			num = node;
-		nr_node_ids = num + 1;
-	}
+	if (nr_node_ids == MAX_NUMNODES)
+		setup_nr_node_ids();
 
 	/* allocate the map */
 	for (node = 0; node < nr_node_ids; node++)
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index b0086567271c..d0b1773d9d2e 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -68,7 +68,7 @@ static int print_split(struct split_state *s)
 			s->gpg++;
 			i += GPS/PAGE_SIZE;
 		} else if (level == PG_LEVEL_2M) {
-			if (!(pte_val(*pte) & _PAGE_PSE)) {
+			if ((pte_val(*pte) & _PAGE_PRESENT) && !(pte_val(*pte) & _PAGE_PSE)) {
 				printk(KERN_ERR
 					"%lx level %d but not PSE %Lx\n",
 					addr, level, (u64)pte_val(*pte));
@@ -130,13 +130,12 @@ static int pageattr_test(void)
 	}
 
 	failed += print_split(&sa);
-	srandom32(100);
 
 	for (i = 0; i < NTEST; i++) {
-		unsigned long pfn = random32() % max_pfn_mapped;
+		unsigned long pfn = prandom_u32() % max_pfn_mapped;
 
 		addr[i] = (unsigned long)__va(pfn << PAGE_SHIFT);
-		len[i] = random32() % 100;
+		len[i] = prandom_u32() % 100;
 		len[i] = min_t(unsigned long, len[i], max_pfn_mapped - pfn - 1);
 
 		if (len[i] == 0)
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 091934e1d0d9..fb4e73ec24d8 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -467,7 +467,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	 * We are safe now. Check whether the new pgprot is the same:
 	 */
 	old_pte = *kpte;
-	old_prot = new_prot = req_prot = pte_pgprot(old_pte);
+	old_prot = req_prot = pte_pgprot(old_pte);
 
 	pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr);
 	pgprot_val(req_prot) |= pgprot_val(cpa->mask_set);
@@ -478,12 +478,12 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	 * a non present pmd. The canon_pgprot will clear _PAGE_GLOBAL
 	 * for the ancient hardware that doesn't support it.
 	 */
-	if (pgprot_val(new_prot) & _PAGE_PRESENT)
-		pgprot_val(new_prot) |= _PAGE_PSE | _PAGE_GLOBAL;
+	if (pgprot_val(req_prot) & _PAGE_PRESENT)
+		pgprot_val(req_prot) |= _PAGE_PSE | _PAGE_GLOBAL;
 	else
-		pgprot_val(new_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL);
+		pgprot_val(req_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL);
 
-	new_prot = canon_pgprot(new_prot);
+	req_prot = canon_pgprot(req_prot);
 
 	/*
 	 * old_pte points to the large page base address. So we need
@@ -1413,6 +1413,8 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
 	 * but that can deadlock->flush only current cpu:
 	 */
 	__flush_tlb_all();
+
+	arch_flush_lazy_mmu_mode();
 }
 
 #ifdef CONFIG_HIBERNATION
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 2610bd93c896..657438858e83 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -563,6 +563,13 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
 	if (base > __pa(high_memory-1))
 		return 0;
 
+	/*
+	 * some areas in the middle of the kernel identity range
+	 * are not mapped, like the PCI space.
+	 */
+	if (!page_is_ram(base >> PAGE_SHIFT))
+		return 0;
+
 	id_sz = (__pa(high_memory-1) <= base + size) ?
 				__pa(high_memory) - base :
 				size;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 193350b51f90..17fda6a8b3c2 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -58,6 +58,13 @@ void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 {
 	paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT);
+	/*
+	 * NOTE! For PAE, any changes to the top page-directory-pointer-table
+	 * entries need a full cr3 reload to flush.
+	 */
+#ifdef CONFIG_X86_PAE
+	tlb->need_flush_all = 1;
+#endif
 	tlb_remove_page(tlb, virt_to_page(pmd));
 }