mm, sparsemem: break out of loops early

There are a number of times that we loop over NR_MEM_SECTIONS, looking
for section_present() on each section.  But, when we have very large
physical address spaces (large MAX_PHYSMEM_BITS), NR_MEM_SECTIONS
becomes very large, making the loops quite long.

With MAX_PHYSMEM_BITS=46 and a section size of 128MB, the current loops
are 512k iterations, which we barely notice on modern hardware.  But,
raising MAX_PHYSMEM_BITS higher (like we will see on systems that
support 5-level paging) makes this 64x longer and we start to notice,
especially on slower systems like simulators.  A 10-second delay for
512k iterations is annoying.  But, a 640- second delay is crippling.

This does not help if we have extremely sparse physical address spaces,
but those are quite rare.  We expect that most of the "slow" systems
where this matters will also be quite small and non-sparse.

To fix this, we track the highest section we've ever encountered.  This
lets us know when we will *never* see another section_present(), and
lets us break out of the loops earlier.

Doing the whole for_each_present_section_nr() macro is probably
overkill, but it will ensure that any future loop iterations that we
grow are more likely to be correct.

Kirrill said "It shaved almost 40 seconds from boot time in qemu with
5-level paging enabled for me".

Link: http://lkml.kernel.org/r/20170504174434.C45A4735@viggo.jf.intel.comSigned-off-by: NDave Hansen <dave.hansen@linux.intel.com>
Tested-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

drivers/base/memory.c

@@ -820,6 +820,10 @@ int __init memory_dev_init(void)
 	 */
 	mutex_lock(&mem_sysfs_mutex);
 	for (i = 0; i < NR_MEM_SECTIONS; i += sections_per_block) {
+		/* Don't iterate over sections we know are !present: */
+		if (i > __highest_present_section_nr)
+			break;
+
 		err = add_memory_block(i);
 		if (!ret)
 			ret = err;

include/linux/mmzone.h

@@ -1180,6 +1180,8 @@ static inline struct mem_section *__pfn_to_section(unsigned long pfn)
 	return __nr_to_section(pfn_to_section_nr(pfn));
 }
 
+extern int __highest_present_section_nr;
+
 #ifndef CONFIG_HAVE_ARCH_PFN_VALID
 static inline int pfn_valid(unsigned long pfn)
 {

mm/sparse.c

@@ -168,6 +168,44 @@ void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
 	}
 }
 
+/*
+ * There are a number of times that we loop over NR_MEM_SECTIONS,
+ * looking for section_present() on each.  But, when we have very
+ * large physical address spaces, NR_MEM_SECTIONS can also be
+ * very large which makes the loops quite long.
+ *
+ * Keeping track of this gives us an easy way to break out of
+ * those loops early.
+ */
+int __highest_present_section_nr;
+static void section_mark_present(struct mem_section *ms)
+{
+	int section_nr = __section_nr(ms);
+
+	if (section_nr > __highest_present_section_nr)
+		__highest_present_section_nr = section_nr;
+
+	ms->section_mem_map |= SECTION_MARKED_PRESENT;
+}
+
+static inline int next_present_section_nr(int section_nr)
+{
+	do {
+		section_nr++;
+		if (present_section_nr(section_nr))
+			return section_nr;
+	} while ((section_nr < NR_MEM_SECTIONS) &&
+		 (section_nr <= __highest_present_section_nr));
+
+	return -1;
+}
+#define for_each_present_section_nr(start, section_nr)		\
+	for (section_nr = next_present_section_nr(start-1);	\
+	     ((section_nr >= 0) &&				\
+	      (section_nr < NR_MEM_SECTIONS) &&			\
+	      (section_nr <= __highest_present_section_nr));	\
+	     section_nr = next_present_section_nr(section_nr))
+
 /* Record a memory area against a node. */
 void __init memory_present(int nid, unsigned long start, unsigned long end)
 {
@@ -183,9 +221,10 @@ void __init memory_present(int nid, unsigned long start, unsigned long end)
 		set_section_nid(section, nid);
 
 		ms = __nr_to_section(section);
-		if (!ms->section_mem_map)
-			ms->section_mem_map = sparse_encode_early_nid(nid) |
-							SECTION_MARKED_PRESENT;
+		if (!ms->section_mem_map) {
+			ms->section_mem_map = sparse_encode_early_nid(nid);
+			section_mark_present(ms);
+		}
 	}
 }
 
@@ -476,23 +515,19 @@ static void __init alloc_usemap_and_memmap(void (*alloc_func)
 	int nodeid_begin = 0;
 	unsigned long pnum_begin = 0;
 
-	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
+	for_each_present_section_nr(0, pnum) {
 		struct mem_section *ms;
 
-		if (!present_section_nr(pnum))
-			continue;
 		ms = __nr_to_section(pnum);
 		nodeid_begin = sparse_early_nid(ms);
 		pnum_begin = pnum;
 		break;
 	}
 	map_count = 1;
-	for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) {
+	for_each_present_section_nr(pnum_begin + 1, pnum) {
 		struct mem_section *ms;
 		int nodeid;
 
-		if (!present_section_nr(pnum))
-			continue;
 		ms = __nr_to_section(pnum);
 		nodeid = sparse_early_nid(ms);
 		if (nodeid == nodeid_begin) {
@@ -561,10 +596,7 @@ void __init sparse_init(void)
 							(void *)map_map);
 #endif
 
-	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
-		if (!present_section_nr(pnum))
-			continue;
-
+	for_each_present_section_nr(0, pnum) {
 		usemap = usemap_map[pnum];
 		if (!usemap)
 			continue;
@@ -722,7 +754,7 @@ int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn)
 
 	memset(memmap, 0, sizeof(struct page) * PAGES_PER_SECTION);
 
-	ms->section_mem_map |= SECTION_MARKED_PRESENT;
+	section_mark_present(ms);
 
 	ret = sparse_init_one_section(ms, section_nr, memmap, usemap);