Merge branch 'master' into for-next

13 files changed, 590 insertions, 84 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9ff85bb8dd69..6dea040cc3a1 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -641,6 +641,20 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 
 	/* Are we prepared to handle this kernel fault? */
 	if (fixup_exception(regs)) {
+		/*
+		 * Any interrupt that takes a fault gets the fixup. This makes
+		 * the below recursive fault logic only apply to a faults from
+		 * task context.
+		 */
+		if (in_interrupt())
+			return;
+
+		/*
+		 * Per the above we're !in_interrupt(), aka. task context.
+		 *
+		 * In this case we need to make sure we're not recursively
+		 * faulting through the emulate_vsyscall() logic.
+		 */
 		if (current_thread_info()->sig_on_uaccess_error && signal) {
 			tsk->thread.trap_nr = X86_TRAP_PF;
 			tsk->thread.error_code = error_code | PF_USER;
@@ -649,6 +663,10 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 			/* XXX: hwpoison faults will set the wrong code. */
 			force_sig_info_fault(signal, si_code, address, tsk, 0);
 		}
+
+		/*
+		 * Barring that, we can do the fixup and be happy.
+		 */
 		return;
 	}
 
@@ -983,6 +1001,12 @@ static int fault_in_kernel_space(unsigned long address)
 
 static inline bool smap_violation(int error_code, struct pt_regs *regs)
 {
+	if (!IS_ENABLED(CONFIG_X86_SMAP))
+		return false;
+
+	if (!static_cpu_has(X86_FEATURE_SMAP))
+		return false;
+
 	if (error_code & PF_USER)
 		return false;
 
@@ -1069,11 +1093,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	if (unlikely(error_code & PF_RSVD))
 		pgtable_bad(regs, error_code, address);
 
-	if (static_cpu_has(X86_FEATURE_SMAP)) {
-		if (unlikely(smap_violation(error_code, regs))) {
-			bad_area_nosemaphore(regs, error_code, address);
-			return;
-		}
+	if (unlikely(smap_violation(error_code, regs))) {
+		bad_area_nosemaphore(regs, error_code, address);
+		return;
 	}
 
 	/*
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index dd74e46828c0..207d9aef662d 100644
--- a/arch/x86/mm/gup.c
+++ b/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;
@@ -102,8 +108,8 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 
 static inline void get_head_page_multiple(struct page *page, int nr)
 {
-	VM_BUG_ON(page != compound_head(page));
-	VM_BUG_ON(page_count(page) == 0);
+	VM_BUG_ON_PAGE(page != compound_head(page), page);
+	VM_BUG_ON_PAGE(page_count(page) == 0, page);
 	atomic_add(nr, &page->_count);
 	SetPageReferenced(page);
 }
@@ -129,7 +135,7 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
 	head = pte_page(pte);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
 	do {
-		VM_BUG_ON(compound_head(page) != head);
+		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
 		if (PageTail(page))
 			get_huge_page_tail(page);
@@ -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 {
@@ -199,7 +212,7 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr,
 	head = pte_page(pte);
 	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
 	do {
-		VM_BUG_ON(compound_head(page) != head);
+		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
 		if (PageTail(page))
 			get_huge_page_tail(page);
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 9d980d88b747..8c9f647ff9e1 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -87,9 +87,7 @@ int pmd_huge_support(void)
 }
 #endif
 
-/* x86_64 also uses this file */
-
-#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#ifdef CONFIG_HUGETLB_PAGE
 static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 		unsigned long addr, unsigned long len,
 		unsigned long pgoff, unsigned long flags)
@@ -99,7 +97,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 
 	info.flags = 0;
 	info.length = len;
-	info.low_limit = TASK_UNMAPPED_BASE;
+	info.low_limit = current->mm->mmap_legacy_base;
 	info.high_limit = TASK_SIZE;
 	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
 	info.align_offset = 0;
@@ -172,8 +170,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		return hugetlb_get_unmapped_area_topdown(file, addr, len,
 				pgoff, flags);
 }
-
-#endif /*HAVE_ARCH_HUGETLB_UNMAPPED_AREA*/
+#endif /* CONFIG_HUGETLB_PAGE */
 
 #ifdef CONFIG_X86_64
 static __init int setup_hugepagesz(char *opt)
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 4287f1ffba7e..e39504878aec 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -665,7 +665,7 @@ void __init initmem_init(void)
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
 #endif
 
-	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
+	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
 	sparse_memory_present_with_active_regions(0);
 
 #ifdef CONFIG_FLATMEM
@@ -806,6 +806,9 @@ void __init mem_init(void)
 	BUILD_BUG_ON(VMALLOC_START			>= VMALLOC_END);
 #undef high_memory
 #undef __FIXADDR_TOP
+#ifdef CONFIG_RANDOMIZE_BASE
+	BUILD_BUG_ON(CONFIG_RANDOMIZE_BASE_MAX_OFFSET > KERNEL_IMAGE_SIZE);
+#endif
 
 #ifdef CONFIG_HIGHMEM
 	BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 104d56a9245f..f35c66c5959a 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -643,7 +643,7 @@ kernel_physical_mapping_init(unsigned long start,
 #ifndef CONFIG_NUMA
 void __init initmem_init(void)
 {
-	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
+	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
 }
 #endif
 
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index e5d5e2ce9f77..637ab34ed632 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -11,7 +11,6 @@
 #include <linux/rculist.h>
 #include <linux/spinlock.h>
 #include <linux/hash.h>
-#include <linux/init.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/uaccess.h>
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 8dabbed409ee..1e9da795767a 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -74,7 +74,7 @@ static void __init do_one_pass(u64 pattern, u64 start, u64 end)
 	u64 i;
 	phys_addr_t this_start, this_end;
 
-	for_each_free_mem_range(i, MAX_NUMNODES, &this_start, &this_end, NULL) {
+	for_each_free_mem_range(i, NUMA_NO_NODE, &this_start, &this_end, NULL) {
 		this_start = clamp_t(phys_addr_t, this_start, start, end);
 		this_end = clamp_t(phys_addr_t, this_end, start, end);
 		if (this_start < this_end) {
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 24aec58d6afd..27aa0455fab3 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -211,9 +211,13 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 	 */
 	nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
 	if (!nd_pa) {
-		pr_err("Cannot find %zu bytes in node %d\n",
-		       nd_size, nid);
-		return;
+		nd_pa = __memblock_alloc_base(nd_size, SMP_CACHE_BYTES,
+					      MEMBLOCK_ALLOC_ACCESSIBLE);
+		if (!nd_pa) {
+			pr_err("Cannot find %zu bytes in node %d\n",
+			       nd_size, nid);
+			return;
+		}
 	}
 	nd = __va(nd_pa);
 
@@ -487,7 +491,8 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 
 	for (i = 0; i < mi->nr_blks; i++) {
 		struct numa_memblk *mb = &mi->blk[i];
-		memblock_set_node(mb->start, mb->end - mb->start, mb->nid);
+		memblock_set_node(mb->start, mb->end - mb->start,
+				  &memblock.memory, mb->nid);
 	}
 
 	/*
@@ -549,6 +554,41 @@ static void __init numa_init_array(void)
 	}
 }
 
+static void __init numa_clear_kernel_node_hotplug(void)
+{
+	int i, nid;
+	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
+	unsigned long start, end;
+	struct memblock_type *type = &memblock.reserved;
+
+	/*
+	 * At this time, all memory regions reserved by memblock are
+	 * used by the kernel. Set the nid in memblock.reserved will
+	 * mark out all the nodes the kernel resides in.
+	 */
+	for (i = 0; i < numa_meminfo.nr_blks; i++) {
+		struct numa_memblk *mb = &numa_meminfo.blk[i];
+		memblock_set_node(mb->start, mb->end - mb->start,
+				  &memblock.reserved, mb->nid);
+	}
+
+	/* Mark all kernel nodes. */
+	for (i = 0; i < type->cnt; i++)
+		node_set(type->regions[i].nid, numa_kernel_nodes);
+
+	/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
+	for (i = 0; i < numa_meminfo.nr_blks; i++) {
+		nid = numa_meminfo.blk[i].nid;
+		if (!node_isset(nid, numa_kernel_nodes))
+			continue;
+
+		start = numa_meminfo.blk[i].start;
+		end = numa_meminfo.blk[i].end;
+
+		memblock_clear_hotplug(start, end - start);
+	}
+}
+
 static int __init numa_init(int (*init_func)(void))
 {
 	int i;
@@ -561,7 +601,12 @@ static int __init numa_init(int (*init_func)(void))
 	nodes_clear(node_possible_map);
 	nodes_clear(node_online_map);
 	memset(&numa_meminfo, 0, sizeof(numa_meminfo));
-	WARN_ON(memblock_set_node(0, ULLONG_MAX, MAX_NUMNODES));
+	WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory,
+				  MAX_NUMNODES));
+	WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved,
+				  MAX_NUMNODES));
+	/* In case that parsing SRAT failed. */
+	WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX));
 	numa_reset_distance();
 
 	ret = init_func();
@@ -597,6 +642,16 @@ static int __init numa_init(int (*init_func)(void))
 			numa_clear_node(i);
 	}
 	numa_init_array();
+
+	/*
+	 * At very early time, the kernel have to use some memory such as
+	 * loading the kernel image. We cannot prevent this anyway. So any
+	 * node the kernel resides in should be un-hotpluggable.
+	 *
+	 * And when we come here, numa_init() won't fail.
+	 */
+	numa_clear_kernel_node_hotplug();
+
 	return 0;
 }
 
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 0342d27ca798..47b6436e41c2 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -52,6 +52,8 @@ void memory_present(int nid, unsigned long start, unsigned long end)
 			nid, start, end);
 	printk(KERN_DEBUG "  Setting physnode_map array to node %d for pfns:\n", nid);
 	printk(KERN_DEBUG "  ");
+	start = round_down(start, PAGES_PER_SECTION);
+	end = round_up(end, PAGES_PER_SECTION);
 	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
 		physnode_map[pfn / PAGES_PER_SECTION] = nid;
 		printk(KERN_CONT "%lx ", pfn);
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index d0b1773d9d2e..461bc8289024 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -8,7 +8,6 @@
 #include <linux/kthread.h>
 #include <linux/random.h>
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <linux/mm.h>
 
 #include <asm/cacheflush.h>
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index bb32480c2d71..b3b19f46c016 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -30,6 +30,7 @@
  */
 struct cpa_data {
 	unsigned long	*vaddr;
+	pgd_t		*pgd;
 	pgprot_t	mask_set;
 	pgprot_t	mask_clr;
 	int		numpages;
@@ -322,17 +323,9 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 	return prot;
 }
 
-/*
- * Lookup the page table entry for a virtual address. Return a pointer
- * to the entry and the level of the mapping.
- *
- * Note: We return pud and pmd either when the entry is marked large
- * or when the present bit is not set. Otherwise we would return a
- * pointer to a nonexisting mapping.
- */
-pte_t *lookup_address(unsigned long address, unsigned int *level)
+static pte_t *__lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
+				      unsigned int *level)
 {
-	pgd_t *pgd = pgd_offset_k(address);
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -361,8 +354,31 @@ pte_t *lookup_address(unsigned long address, unsigned int *level)
 
 	return pte_offset_kernel(pmd, address);
 }
+
+/*
+ * Lookup the page table entry for a virtual address. Return a pointer
+ * to the entry and the level of the mapping.
+ *
+ * Note: We return pud and pmd either when the entry is marked large
+ * or when the present bit is not set. Otherwise we would return a
+ * pointer to a nonexisting mapping.
+ */
+pte_t *lookup_address(unsigned long address, unsigned int *level)
+{
+        return __lookup_address_in_pgd(pgd_offset_k(address), address, level);
+}
 EXPORT_SYMBOL_GPL(lookup_address);
 
+static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
+				  unsigned int *level)
+{
+        if (cpa->pgd)
+		return __lookup_address_in_pgd(cpa->pgd + pgd_index(address),
+					       address, level);
+
+        return lookup_address(address, level);
+}
+
 /*
  * This is necessary because __pa() does not work on some
  * kinds of memory, like vmalloc() or the alloc_remap()
@@ -437,7 +453,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	 * Check for races, another CPU might have split this page
 	 * up already:
 	 */
-	tmp = lookup_address(address, &level);
+	tmp = _lookup_address_cpa(cpa, address, &level);
 	if (tmp != kpte)
 		goto out_unlock;
 
@@ -543,7 +559,8 @@ out_unlock:
 }
 
 static int
-__split_large_page(pte_t *kpte, unsigned long address, struct page *base)
+__split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
+		   struct page *base)
 {
 	pte_t *pbase = (pte_t *)page_address(base);
 	unsigned long pfn, pfninc = 1;
@@ -556,7 +573,7 @@ __split_large_page(pte_t *kpte, unsigned long address, struct page *base)
 	 * Check for races, another CPU might have split this page
 	 * up for us already:
 	 */
-	tmp = lookup_address(address, &level);
+	tmp = _lookup_address_cpa(cpa, address, &level);
 	if (tmp != kpte) {
 		spin_unlock(&pgd_lock);
 		return 1;
@@ -632,7 +649,8 @@ __split_large_page(pte_t *kpte, unsigned long address, struct page *base)
 	return 0;
 }
 
-static int split_large_page(pte_t *kpte, unsigned long address)
+static int split_large_page(struct cpa_data *cpa, pte_t *kpte,
+			    unsigned long address)
 {
 	struct page *base;
 
@@ -644,15 +662,390 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	if (!base)
 		return -ENOMEM;
 
-	if (__split_large_page(kpte, address, base))
+	if (__split_large_page(cpa, kpte, address, base))
 		__free_page(base);
 
 	return 0;
 }
 
+static bool try_to_free_pte_page(pte_t *pte)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		if (!pte_none(pte[i]))
+			return false;
+
+	free_page((unsigned long)pte);
+	return true;
+}
+
+static bool try_to_free_pmd_page(pmd_t *pmd)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PMD; i++)
+		if (!pmd_none(pmd[i]))
+			return false;
+
+	free_page((unsigned long)pmd);
+	return true;
+}
+
+static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
+{
+	pte_t *pte = pte_offset_kernel(pmd, start);
+
+	while (start < end) {
+		set_pte(pte, __pte(0));
+
+		start += PAGE_SIZE;
+		pte++;
+	}
+
+	if (try_to_free_pte_page((pte_t *)pmd_page_vaddr(*pmd))) {
+		pmd_clear(pmd);
+		return true;
+	}
+	return false;
+}
+
+static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd,
+			      unsigned long start, unsigned long end)
+{
+	if (unmap_pte_range(pmd, start, end))
+		if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
+			pud_clear(pud);
+}
+
+static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end)
+{
+	pmd_t *pmd = pmd_offset(pud, start);
+
+	/*
+	 * Not on a 2MB page boundary?
+	 */
+	if (start & (PMD_SIZE - 1)) {
+		unsigned long next_page = (start + PMD_SIZE) & PMD_MASK;
+		unsigned long pre_end = min_t(unsigned long, end, next_page);
+
+		__unmap_pmd_range(pud, pmd, start, pre_end);
+
+		start = pre_end;
+		pmd++;
+	}
+
+	/*
+	 * Try to unmap in 2M chunks.
+	 */
+	while (end - start >= PMD_SIZE) {
+		if (pmd_large(*pmd))
+			pmd_clear(pmd);
+		else
+			__unmap_pmd_range(pud, pmd, start, start + PMD_SIZE);
+
+		start += PMD_SIZE;
+		pmd++;
+	}
+
+	/*
+	 * 4K leftovers?
+	 */
+	if (start < end)
+		return __unmap_pmd_range(pud, pmd, start, end);
+
+	/*
+	 * Try again to free the PMD page if haven't succeeded above.
+	 */
+	if (!pud_none(*pud))
+		if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
+			pud_clear(pud);
+}
+
+static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
+{
+	pud_t *pud = pud_offset(pgd, start);
+
+	/*
+	 * Not on a GB page boundary?
+	 */
+	if (start & (PUD_SIZE - 1)) {
+		unsigned long next_page = (start + PUD_SIZE) & PUD_MASK;
+		unsigned long pre_end	= min_t(unsigned long, end, next_page);
+
+		unmap_pmd_range(pud, start, pre_end);
+
+		start = pre_end;
+		pud++;
+	}
+
+	/*
+	 * Try to unmap in 1G chunks?
+	 */
+	while (end - start >= PUD_SIZE) {
+
+		if (pud_large(*pud))
+			pud_clear(pud);
+		else
+			unmap_pmd_range(pud, start, start + PUD_SIZE);
+
+		start += PUD_SIZE;
+		pud++;
+	}
+
+	/*
+	 * 2M leftovers?
+	 */
+	if (start < end)
+		unmap_pmd_range(pud, start, end);
+
+	/*
+	 * No need to try to free the PUD page because we'll free it in
+	 * populate_pgd's error path
+	 */
+}
+
+static int alloc_pte_page(pmd_t *pmd)
+{
+	pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
+	if (!pte)
+		return -1;
+
+	set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
+	return 0;
+}
+
+static int alloc_pmd_page(pud_t *pud)
+{
+	pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
+	if (!pmd)
+		return -1;
+
+	set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+	return 0;
+}
+
+static void populate_pte(struct cpa_data *cpa,
+			 unsigned long start, unsigned long end,
+			 unsigned num_pages, pmd_t *pmd, pgprot_t pgprot)
+{
+	pte_t *pte;
+
+	pte = pte_offset_kernel(pmd, start);
+
+	while (num_pages-- && start < end) {
+
+		/* deal with the NX bit */
+		if (!(pgprot_val(pgprot) & _PAGE_NX))
+			cpa->pfn &= ~_PAGE_NX;
+
+		set_pte(pte, pfn_pte(cpa->pfn >> PAGE_SHIFT, pgprot));
+
+		start	 += PAGE_SIZE;
+		cpa->pfn += PAGE_SIZE;
+		pte++;
+	}
+}
+
+static int populate_pmd(struct cpa_data *cpa,
+			unsigned long start, unsigned long end,
+			unsigned num_pages, pud_t *pud, pgprot_t pgprot)
+{
+	unsigned int cur_pages = 0;
+	pmd_t *pmd;
+
+	/*
+	 * Not on a 2M boundary?
+	 */
+	if (start & (PMD_SIZE - 1)) {
+		unsigned long pre_end = start + (num_pages << PAGE_SHIFT);
+		unsigned long next_page = (start + PMD_SIZE) & PMD_MASK;
+
+		pre_end   = min_t(unsigned long, pre_end, next_page);
+		cur_pages = (pre_end - start) >> PAGE_SHIFT;
+		cur_pages = min_t(unsigned int, num_pages, cur_pages);
+
+		/*
+		 * Need a PTE page?
+		 */
+		pmd = pmd_offset(pud, start);
+		if (pmd_none(*pmd))
+			if (alloc_pte_page(pmd))
+				return -1;
+
+		populate_pte(cpa, start, pre_end, cur_pages, pmd, pgprot);
+
+		start = pre_end;
+	}
+
+	/*
+	 * We mapped them all?
+	 */
+	if (num_pages == cur_pages)
+		return cur_pages;
+
+	while (end - start >= PMD_SIZE) {
+
+		/*
+		 * We cannot use a 1G page so allocate a PMD page if needed.
+		 */
+		if (pud_none(*pud))
+			if (alloc_pmd_page(pud))
+				return -1;
+
+		pmd = pmd_offset(pud, start);
+
+		set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot)));
+
+		start	  += PMD_SIZE;
+		cpa->pfn  += PMD_SIZE;
+		cur_pages += PMD_SIZE >> PAGE_SHIFT;
+	}
+
+	/*
+	 * Map trailing 4K pages.
+	 */
+	if (start < end) {
+		pmd = pmd_offset(pud, start);
+		if (pmd_none(*pmd))
+			if (alloc_pte_page(pmd))
+				return -1;
+
+		populate_pte(cpa, start, end, num_pages - cur_pages,
+			     pmd, pgprot);
+	}
+	return num_pages;
+}
+
+static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
+			pgprot_t pgprot)
+{
+	pud_t *pud;
+	unsigned long end;
+	int cur_pages = 0;
+
+	end = start + (cpa->numpages << PAGE_SHIFT);
+
+	/*
+	 * Not on a Gb page boundary? => map everything up to it with
+	 * smaller pages.
+	 */
+	if (start & (PUD_SIZE - 1)) {
+		unsigned long pre_end;
+		unsigned long next_page = (start + PUD_SIZE) & PUD_MASK;
+
+		pre_end   = min_t(unsigned long, end, next_page);
+		cur_pages = (pre_end - start) >> PAGE_SHIFT;
+		cur_pages = min_t(int, (int)cpa->numpages, cur_pages);
+
+		pud = pud_offset(pgd, start);
+
+		/*
+		 * Need a PMD page?
+		 */
+		if (pud_none(*pud))
+			if (alloc_pmd_page(pud))
+				return -1;
+
+		cur_pages = populate_pmd(cpa, start, pre_end, cur_pages,
+					 pud, pgprot);
+		if (cur_pages < 0)
+			return cur_pages;
+
+		start = pre_end;
+	}
+
+	/* We mapped them all? */
+	if (cpa->numpages == cur_pages)
+		return cur_pages;
+
+	pud = pud_offset(pgd, start);
+
+	/*
+	 * Map everything starting from the Gb boundary, possibly with 1G pages
+	 */
+	while (end - start >= PUD_SIZE) {
+		set_pud(pud, __pud(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot)));
+
+		start	  += PUD_SIZE;
+		cpa->pfn  += PUD_SIZE;
+		cur_pages += PUD_SIZE >> PAGE_SHIFT;
+		pud++;
+	}
+
+	/* Map trailing leftover */
+	if (start < end) {
+		int tmp;
+
+		pud = pud_offset(pgd, start);
+		if (pud_none(*pud))
+			if (alloc_pmd_page(pud))
+				return -1;
+
+		tmp = populate_pmd(cpa, start, end, cpa->numpages - cur_pages,
+				   pud, pgprot);
+		if (tmp < 0)
+			return cur_pages;
+
+		cur_pages += tmp;
+	}
+	return cur_pages;
+}
+
+/*
+ * Restrictions for kernel page table do not necessarily apply when mapping in
+ * an alternate PGD.
+ */
+static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
+{
+	pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
+	bool allocd_pgd = false;
+	pgd_t *pgd_entry;
+	pud_t *pud = NULL;	/* shut up gcc */
+	int ret;
+
+	pgd_entry = cpa->pgd + pgd_index(addr);
+
+	/*
+	 * Allocate a PUD page and hand it down for mapping.
+	 */
+	if (pgd_none(*pgd_entry)) {
+		pud = (pud_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
+		if (!pud)
+			return -1;
+
+		set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE));
+		allocd_pgd = true;
+	}
+
+	pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr);
+	pgprot_val(pgprot) |=  pgprot_val(cpa->mask_set);
+
+	ret = populate_pud(cpa, addr, pgd_entry, pgprot);
+	if (ret < 0) {
+		unmap_pud_range(pgd_entry, addr,
+				addr + (cpa->numpages << PAGE_SHIFT));
+
+		if (allocd_pgd) {
+			/*
+			 * If I allocated this PUD page, I can just as well
+			 * free it in this error path.
+			 */
+			pgd_clear(pgd_entry);
+			free_page((unsigned long)pud);
+		}
+		return ret;
+	}
+	cpa->numpages = ret;
+	return 0;
+}
+
 static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr,
 			       int primary)
 {
+	if (cpa->pgd)
+		return populate_pgd(cpa, vaddr);
+
 	/*
 	 * Ignore all non primary paths.
 	 */
@@ -697,7 +1090,7 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
 	else
 		address = *cpa->vaddr;
 repeat:
-	kpte = lookup_address(address, &level);
+	kpte = _lookup_address_cpa(cpa, address, &level);
 	if (!kpte)
 		return __cpa_process_fault(cpa, address, primary);
 
@@ -761,7 +1154,7 @@ repeat:
 	/*
 	 * We have to split the large page:
 	 */
-	err = split_large_page(kpte, address);
+	err = split_large_page(cpa, kpte, address);
 	if (!err) {
 		/*
 	 	 * Do a global flush tlb after splitting the large page
@@ -910,6 +1303,8 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 	int ret, cache, checkalias;
 	unsigned long baddr = 0;
 
+	memset(&cpa, 0, sizeof(cpa));
+
 	/*
 	 * Check, if we are requested to change a not supported
 	 * feature:
@@ -1356,6 +1751,7 @@ static int __set_pages_p(struct page *page, int numpages)
 {
 	unsigned long tempaddr = (unsigned long) page_address(page);
 	struct cpa_data cpa = { .vaddr = &tempaddr,
+				.pgd = NULL,
 				.numpages = numpages,
 				.mask_set = __pgprot(_PAGE_PRESENT | _PAGE_RW),
 				.mask_clr = __pgprot(0),
@@ -1374,6 +1770,7 @@ static int __set_pages_np(struct page *page, int numpages)
 {
 	unsigned long tempaddr = (unsigned long) page_address(page);
 	struct cpa_data cpa = { .vaddr = &tempaddr,
+				.pgd = NULL,
 				.numpages = numpages,
 				.mask_set = __pgprot(0),
 				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW),
@@ -1434,6 +1831,36 @@ bool kernel_page_present(struct page *page)
 
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
+int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
+			    unsigned numpages, unsigned long page_flags)
+{
+	int retval = -EINVAL;
+
+	struct cpa_data cpa = {
+		.vaddr = &address,
+		.pfn = pfn,
+		.pgd = pgd,
+		.numpages = numpages,
+		.mask_set = __pgprot(0),
+		.mask_clr = __pgprot(0),
+		.flags = 0,
+	};
+
+	if (!(__supported_pte_mask & _PAGE_NX))
+		goto out;
+
+	if (!(page_flags & _PAGE_NX))
+		cpa.mask_clr = __pgprot(_PAGE_NX);
+
+	cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags);
+
+	retval = __change_page_attr_set_clr(&cpa, 0);
+	__flush_tlb_all();
+
+out:
+	return retval;
+}
+
 /*
  * The testcases use internal knowledge of the implementation that shouldn't
  * be exposed to the rest of the kernel. Include these directly here.
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 266ca912f62e..1953e9c9391a 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -42,15 +42,25 @@ static __init inline int srat_disabled(void)
 	return acpi_numa < 0;
 }
 
-/* Callback for SLIT parsing */
+/*
+ * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
+ * I/O localities since SRAT does not list them.  I/O localities are
+ * not supported at this point.
+ */
 void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 {
 	int i, j;
 
-	for (i = 0; i < slit->locality_count; i++)
-		for (j = 0; j < slit->locality_count; j++)
+	for (i = 0; i < slit->locality_count; i++) {
+		if (pxm_to_node(i) == NUMA_NO_NODE)
+			continue;
+		for (j = 0; j < slit->locality_count; j++) {
+			if (pxm_to_node(j) == NUMA_NO_NODE)
+				continue;
 			numa_set_distance(pxm_to_node(i), pxm_to_node(j),
 				slit->entry[slit->locality_count * i + j]);
+		}
+	}
 }
 
 /* Callback for Proximity Domain -> x2APIC mapping */
@@ -181,6 +191,11 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 		(unsigned long long) start, (unsigned long long) end - 1,
 		hotpluggable ? " hotplug" : "");
 
+	/* Mark hotplug range in memblock. */
+	if (hotpluggable && memblock_mark_hotplug(start, ma->length))
+		pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n",
+			(unsigned long long)start, (unsigned long long)end - 1);
+
 	return 0;
 out_err_bad_srat:
 	bad_srat();
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index ae699b3bbac8..dd8dda167a24 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -103,7 +103,7 @@ static void flush_tlb_func(void *info)
 	if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
 		return;
 
-	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
 		if (f->flush_end == TLB_FLUSH_ALL)
 			local_flush_tlb();
@@ -131,7 +131,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 	info.flush_start = start;
 	info.flush_end = end;
 
-	count_vm_event(NR_TLB_REMOTE_FLUSH);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	if (is_uv_system()) {
 		unsigned int cpu;
 
@@ -151,44 +151,19 @@ void flush_tlb_current_task(void)
 
 	preempt_disable();
 
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	local_flush_tlb();
 	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
 		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
 	preempt_enable();
 }
 
-/*
- * It can find out the THP large page, or
- * HUGETLB page in tlb_flush when THP disabled
- */
-static inline unsigned long has_large_page(struct mm_struct *mm,
-				 unsigned long start, unsigned long end)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	unsigned long addr = ALIGN(start, HPAGE_SIZE);
-	for (; addr < end; addr += HPAGE_SIZE) {
-		pgd = pgd_offset(mm, addr);
-		if (likely(!pgd_none(*pgd))) {
-			pud = pud_offset(pgd, addr);
-			if (likely(!pud_none(*pud))) {
-				pmd = pmd_offset(pud, addr);
-				if (likely(!pmd_none(*pmd)))
-					if (pmd_large(*pmd))
-						return addr;
-			}
-		}
-	}
-	return 0;
-}
-
 void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				unsigned long end, unsigned long vmflag)
 {
 	unsigned long addr;
 	unsigned act_entries, tlb_entries = 0;
+	unsigned long nr_base_pages;
 
 	preempt_disable();
 	if (current->active_mm != mm)
@@ -210,21 +185,20 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 		tlb_entries = tlb_lli_4k[ENTRIES];
 	else
 		tlb_entries = tlb_lld_4k[ENTRIES];
+
 	/* Assume all of TLB entries was occupied by this task */
-	act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm;
+	act_entries = tlb_entries >> tlb_flushall_shift;
+	act_entries = mm->total_vm > act_entries ? act_entries : mm->total_vm;
+	nr_base_pages = (end - start) >> PAGE_SHIFT;
 
 	/* tlb_flushall_shift is on balance point, details in commit log */
-	if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) {
-		count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	if (nr_base_pages > act_entries) {
+		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 		local_flush_tlb();
 	} else {
-		if (has_large_page(mm, start, end)) {
-			local_flush_tlb();
-			goto flush_all;
-		}
 		/* flush range by one by one 'invlpg' */
 		for (addr = start; addr < end;	addr += PAGE_SIZE) {
-			count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
+			count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 			__flush_tlb_single(addr);
 		}
 
@@ -262,7 +236,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
 
 static void do_flush_tlb_all(void *info)
 {
-	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	__flush_tlb_all();
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
 		leave_mm(smp_processor_id());
@@ -270,7 +244,7 @@ static void do_flush_tlb_all(void *info)
 
 void flush_tlb_all(void)
 {
-	count_vm_event(NR_TLB_REMOTE_FLUSH);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	on_each_cpu(do_flush_tlb_all, NULL, 1);
 }