1 files changed, 27 insertions, 14 deletions

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index df1a9927ad29..4cb8763868fc 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -151,7 +151,7 @@ early_param("gbpages", parse_direct_gbpages_on);
  * around without checking the pgd every time.
  */
 
-pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
+pteval_t __supported_pte_mask __read_mostly = ~0;
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
 int force_personality32;
@@ -178,7 +178,7 @@ __setup("noexec32=", nonx32_setup);
  * When memory was added/removed make sure all the processes MM have
  * suitable PGD entries in the local PGD level page.
  */
-void sync_global_pgds(unsigned long start, unsigned long end)
+void sync_global_pgds(unsigned long start, unsigned long end, int removed)
 {
 	unsigned long address;
 
@@ -186,7 +186,12 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 		const pgd_t *pgd_ref = pgd_offset_k(address);
 		struct page *page;
 
-		if (pgd_none(*pgd_ref))
+		/*
+		 * When it is called after memory hot remove, pgd_none()
+		 * returns true. In this case (removed == 1), we must clear
+		 * the PGD entries in the local PGD level page.
+		 */
+		if (pgd_none(*pgd_ref) && !removed)
 			continue;
 
 		spin_lock(&pgd_lock);
@@ -199,12 +204,18 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
 			spin_lock(pgt_lock);
 
-			if (pgd_none(*pgd))
-				set_pgd(pgd, *pgd_ref);
-			else
+			if (!pgd_none(*pgd_ref) && !pgd_none(*pgd))
 				BUG_ON(pgd_page_vaddr(*pgd)
 				       != pgd_page_vaddr(*pgd_ref));
 
+			if (removed) {
+				if (pgd_none(*pgd_ref) && !pgd_none(*pgd))
+					pgd_clear(pgd);
+			} else {
+				if (pgd_none(*pgd))
+					set_pgd(pgd, *pgd_ref);
+			}
+
 			spin_unlock(pgt_lock);
 		}
 		spin_unlock(&pgd_lock);
@@ -633,7 +644,7 @@ kernel_physical_mapping_init(unsigned long start,
 	}
 
 	if (pgd_changed)
-		sync_global_pgds(addr, end - 1);
+		sync_global_pgds(addr, end - 1, 0);
 
 	__flush_tlb_all();
 
@@ -691,7 +702,8 @@ static void  update_end_of_memory_vars(u64 start, u64 size)
 int arch_add_memory(int nid, u64 start, u64 size)
 {
 	struct pglist_data *pgdat = NODE_DATA(nid);
-	struct zone *zone = pgdat->node_zones + ZONE_NORMAL;
+	struct zone *zone = pgdat->node_zones +
+		zone_for_memory(nid, start, size, ZONE_NORMAL);
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
@@ -975,25 +987,26 @@ static void __meminit
 remove_pagetable(unsigned long start, unsigned long end, bool direct)
 {
 	unsigned long next;
+	unsigned long addr;
 	pgd_t *pgd;
 	pud_t *pud;
 	bool pgd_changed = false;
 
-	for (; start < end; start = next) {
-		next = pgd_addr_end(start, end);
+	for (addr = start; addr < end; addr = next) {
+		next = pgd_addr_end(addr, end);
 
-		pgd = pgd_offset_k(start);
+		pgd = pgd_offset_k(addr);
 		if (!pgd_present(*pgd))
 			continue;
 
 		pud = (pud_t *)pgd_page_vaddr(*pgd);
-		remove_pud_table(pud, start, next, direct);
+		remove_pud_table(pud, addr, next, direct);
 		if (free_pud_table(pud, pgd))
 			pgd_changed = true;
 	}
 
 	if (pgd_changed)
-		sync_global_pgds(start, end - 1);
+		sync_global_pgds(start, end - 1, 1);
 
 	flush_tlb_all();
 }
@@ -1340,7 +1353,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 	else
 		err = vmemmap_populate_basepages(start, end, node);
 	if (!err)
-		sync_global_pgds(start, end - 1);
+		sync_global_pgds(start, end - 1, 0);
 	return err;
 }