1 files changed, 130 insertions, 78 deletions

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 55247451ba85..e527d829e1ed 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -826,6 +826,106 @@ void __init paging_init(void)
 	zone_sizes_init();
 }
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+#define PAGE_UNUSED 0xFD
+
+/*
+ * The unused vmemmap range, which was not yet memset(PAGE_UNUSED), ranges
+ * from unused_pmd_start to next PMD_SIZE boundary.
+ */
+static unsigned long unused_pmd_start __meminitdata;
+
+static void __meminit vmemmap_flush_unused_pmd(void)
+{
+	if (!unused_pmd_start)
+		return;
+	/*
+	 * Clears (unused_pmd_start, PMD_END]
+	 */
+	memset((void *)unused_pmd_start, PAGE_UNUSED,
+	       ALIGN(unused_pmd_start, PMD_SIZE) - unused_pmd_start);
+	unused_pmd_start = 0;
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+/* Returns true if the PMD is completely unused and thus it can be freed */
+static bool __meminit vmemmap_pmd_is_unused(unsigned long addr, unsigned long end)
+{
+	unsigned long start = ALIGN_DOWN(addr, PMD_SIZE);
+
+	/*
+	 * Flush the unused range cache to ensure that memchr_inv() will work
+	 * for the whole range.
+	 */
+	vmemmap_flush_unused_pmd();
+	memset((void *)addr, PAGE_UNUSED, end - addr);
+
+	return !memchr_inv((void *)start, PAGE_UNUSED, PMD_SIZE);
+}
+#endif
+
+static void __meminit __vmemmap_use_sub_pmd(unsigned long start)
+{
+	/*
+	 * As we expect to add in the same granularity as we remove, it's
+	 * sufficient to mark only some piece used to block the memmap page from
+	 * getting removed when removing some other adjacent memmap (just in
+	 * case the first memmap never gets initialized e.g., because the memory
+	 * block never gets onlined).
+	 */
+	memset((void *)start, 0, sizeof(struct page));
+}
+
+static void __meminit vmemmap_use_sub_pmd(unsigned long start, unsigned long end)
+{
+	/*
+	 * We only optimize if the new used range directly follows the
+	 * previously unused range (esp., when populating consecutive sections).
+	 */
+	if (unused_pmd_start == start) {
+		if (likely(IS_ALIGNED(end, PMD_SIZE)))
+			unused_pmd_start = 0;
+		else
+			unused_pmd_start = end;
+		return;
+	}
+
+	/*
+	 * If the range does not contiguously follows previous one, make sure
+	 * to mark the unused range of the previous one so it can be removed.
+	 */
+	vmemmap_flush_unused_pmd();
+	__vmemmap_use_sub_pmd(start);
+}
+
+
+static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end)
+{
+	vmemmap_flush_unused_pmd();
+
+	/*
+	 * Could be our memmap page is filled with PAGE_UNUSED already from a
+	 * previous remove. Make sure to reset it.
+	 */
+	__vmemmap_use_sub_pmd(start);
+
+	/*
+	 * Mark with PAGE_UNUSED the unused parts of the new memmap range
+	 */
+	if (!IS_ALIGNED(start, PMD_SIZE))
+		memset((void *)start, PAGE_UNUSED,
+			start - ALIGN_DOWN(start, PMD_SIZE));
+
+	/*
+	 * We want to avoid memset(PAGE_UNUSED) when populating the vmemmap of
+	 * consecutive sections. Remember for the last added PMD where the
+	 * unused range begins.
+	 */
+	if (!IS_ALIGNED(end, PMD_SIZE))
+		unused_pmd_start = end;
+}
+#endif
+
 /*
  * Memory hotplug specific functions
  */
@@ -871,8 +971,6 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	return add_pages(nid, start_pfn, nr_pages, params);
 }
 
-#define PAGE_INUSE 0xFD
-
 static void __meminit free_pagetable(struct page *page, int order)
 {
 	unsigned long magic;
@@ -962,7 +1060,6 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
 {
 	unsigned long next, pages = 0;
 	pte_t *pte;
-	void *page_addr;
 	phys_addr_t phys_addr;
 
 	pte = pte_start + pte_index(addr);
@@ -983,42 +1080,15 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
 		if (phys_addr < (phys_addr_t)0x40000000)
 			return;
 
-		if (PAGE_ALIGNED(addr) && PAGE_ALIGNED(next)) {
-			/*
-			 * Do not free direct mapping pages since they were
-			 * freed when offlining, or simply not in use.
-			 */
-			if (!direct)
-				free_pagetable(pte_page(*pte), 0);
-
-			spin_lock(&init_mm.page_table_lock);
-			pte_clear(&init_mm, addr, pte);
-			spin_unlock(&init_mm.page_table_lock);
-
-			/* For non-direct mapping, pages means nothing. */
-			pages++;
-		} else {
-			/*
-			 * If we are here, we are freeing vmemmap pages since
-			 * direct mapped memory ranges to be freed are aligned.
-			 *
-			 * If we are not removing the whole page, it means
-			 * other page structs in this page are being used and
-			 * we cannot remove them. So fill the unused page_structs
-			 * with 0xFD, and remove the page when it is wholly
-			 * filled with 0xFD.
-			 */
-			memset((void *)addr, PAGE_INUSE, next - addr);
+		if (!direct)
+			free_pagetable(pte_page(*pte), 0);
 
-			page_addr = page_address(pte_page(*pte));
-			if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) {
-				free_pagetable(pte_page(*pte), 0);
+		spin_lock(&init_mm.page_table_lock);
+		pte_clear(&init_mm, addr, pte);
+		spin_unlock(&init_mm.page_table_lock);
 
-				spin_lock(&init_mm.page_table_lock);
-				pte_clear(&init_mm, addr, pte);
-				spin_unlock(&init_mm.page_table_lock);
-			}
-		}
+		/* For non-direct mapping, pages means nothing. */
+		pages++;
 	}
 
 	/* Call free_pte_table() in remove_pmd_table(). */
@@ -1034,7 +1104,6 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
 	unsigned long next, pages = 0;
 	pte_t *pte_base;
 	pmd_t *pmd;
-	void *page_addr;
 
 	pmd = pmd_start + pmd_index(addr);
 	for (; addr < end; addr = next, pmd++) {
@@ -1054,22 +1123,16 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
 				pmd_clear(pmd);
 				spin_unlock(&init_mm.page_table_lock);
 				pages++;
-			} else {
-				/* If here, we are freeing vmemmap pages. */
-				memset((void *)addr, PAGE_INUSE, next - addr);
-
-				page_addr = page_address(pmd_page(*pmd));
-				if (!memchr_inv(page_addr, PAGE_INUSE,
-						PMD_SIZE)) {
+			}
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+			else if (vmemmap_pmd_is_unused(addr, next)) {
 					free_hugepage_table(pmd_page(*pmd),
 							    altmap);
-
 					spin_lock(&init_mm.page_table_lock);
 					pmd_clear(pmd);
 					spin_unlock(&init_mm.page_table_lock);
-				}
 			}
-
+#endif
 			continue;
 		}
 
@@ -1090,7 +1153,6 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
 	unsigned long next, pages = 0;
 	pmd_t *pmd_base;
 	pud_t *pud;
-	void *page_addr;
 
 	pud = pud_start + pud_index(addr);
 	for (; addr < end; addr = next, pud++) {
@@ -1099,33 +1161,13 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
 		if (!pud_present(*pud))
 			continue;
 
-		if (pud_large(*pud)) {
-			if (IS_ALIGNED(addr, PUD_SIZE) &&
-			    IS_ALIGNED(next, PUD_SIZE)) {
-				if (!direct)
-					free_pagetable(pud_page(*pud),
-						       get_order(PUD_SIZE));
-
-				spin_lock(&init_mm.page_table_lock);
-				pud_clear(pud);
-				spin_unlock(&init_mm.page_table_lock);
-				pages++;
-			} else {
-				/* If here, we are freeing vmemmap pages. */
-				memset((void *)addr, PAGE_INUSE, next - addr);
-
-				page_addr = page_address(pud_page(*pud));
-				if (!memchr_inv(page_addr, PAGE_INUSE,
-						PUD_SIZE)) {
-					free_pagetable(pud_page(*pud),
-						       get_order(PUD_SIZE));
-
-					spin_lock(&init_mm.page_table_lock);
-					pud_clear(pud);
-					spin_unlock(&init_mm.page_table_lock);
-				}
-			}
-
+		if (pud_large(*pud) &&
+		    IS_ALIGNED(addr, PUD_SIZE) &&
+		    IS_ALIGNED(next, PUD_SIZE)) {
+			spin_lock(&init_mm.page_table_lock);
+			pud_clear(pud);
+			spin_unlock(&init_mm.page_table_lock);
+			pages++;
 			continue;
 		}
 
@@ -1197,6 +1239,9 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct,
 void __ref vmemmap_free(unsigned long start, unsigned long end,
 		struct vmem_altmap *altmap)
 {
+	VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE));
+	VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE));
+
 	remove_pagetable(start, end, false, altmap);
 }
 
@@ -1306,8 +1351,6 @@ void __init mem_init(void)
 		kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER);
 
 	preallocate_vmalloc_pages();
-
-	mem_init_print_info(NULL);
 }
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
@@ -1538,11 +1581,17 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start,
 
 				addr_end = addr + PMD_SIZE;
 				p_end = p + PMD_SIZE;
+
+				if (!IS_ALIGNED(addr, PMD_SIZE) ||
+				    !IS_ALIGNED(next, PMD_SIZE))
+					vmemmap_use_new_sub_pmd(addr, next);
+
 				continue;
 			} else if (altmap)
 				return -ENOMEM; /* no fallback */
 		} else if (pmd_large(*pmd)) {
 			vmemmap_verify((pte_t *)pmd, node, addr, next);
+			vmemmap_use_sub_pmd(addr, next);
 			continue;
 		}
 		if (vmemmap_populate_basepages(addr, next, node, NULL))
@@ -1556,6 +1605,9 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 {
 	int err;
 
+	VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE));
+	VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE));
+
 	if (end - start < PAGES_PER_SECTION * sizeof(struct page))
 		err = vmemmap_populate_basepages(start, end, node, NULL);
 	else if (boot_cpu_has(X86_FEATURE_PSE))