mm/debug-pagealloc: make debug-pagealloc boottime configurable

Now, we have prepared to avoid using debug-pagealloc in boottime.  So
introduce new kernel-parameter to disable debug-pagealloc in boottime, and
makes related functions to be disabled in this case.

Only non-intuitive part is change of guard page functions.  Because guard
page is effective only if debug-pagealloc is enabled, turning off
according to debug-pagealloc is reasonable thing to do.

Signed-off-by: Joonsoo Kim <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Michal Nazarewicz <[email protected]>
Cc: Jungsoo Son <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Joonsoo Kim <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Author: JoonsooKim

Documentation/kernel-parameters.txt

@@ -829,6 +829,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			CONFIG_DEBUG_PAGEALLOC, hence this option will not help
 			tracking down these problems.
 
+	debug_pagealloc=
+			[KNL] When CONFIG_DEBUG_PAGEALLOC is set, this
+			parameter enables the feature at boot time. In
+			default, it is disabled. We can avoid allocating huge
+			chunk of memory for debug pagealloc if we don't enable
+			it at boot time and the system will work mostly same
+			with the kernel built without CONFIG_DEBUG_PAGEALLOC.
+			on: enable the feature
+
 	debugpat	[X86] Enable PAT debugging
 
 	decnet.addr=	[HW,NET]

arch/powerpc/mm/hash_utils_64.c

@@ -1514,7 +1514,7 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
 			       mmu_kernel_ssize, 0);
 }
 
-void kernel_map_pages(struct page *page, int numpages, int enable)
+void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	unsigned long flags, vaddr, lmi;
 	int i;

arch/powerpc/mm/pgtable_32.c

@@ -429,7 +429,7 @@ static int change_page_attr(struct page *page, int numpages, pgprot_t prot)
 }
 
 
-void kernel_map_pages(struct page *page, int numpages, int enable)
+void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (PageHighMem(page))
 		return;

arch/s390/mm/pageattr.c

@@ -120,7 +120,7 @@ static void ipte_range(pte_t *pte, unsigned long address, int nr)
 	}
 }
 
-void kernel_map_pages(struct page *page, int numpages, int enable)
+void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	unsigned long address;
 	int nr, i, j;

arch/sparc/mm/init_64.c

@@ -1621,7 +1621,7 @@ static void __init kernel_physical_mapping_init(void)
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
-void kernel_map_pages(struct page *page, int numpages, int enable)
+void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	unsigned long phys_start = page_to_pfn(page) << PAGE_SHIFT;
 	unsigned long phys_end = phys_start + (numpages * PAGE_SIZE);

arch/x86/mm/pageattr.c

@@ -1817,7 +1817,7 @@ static int __set_pages_np(struct page *page, int numpages)
 	return __change_page_attr_set_clr(&cpa, 0);
 }
 
-void kernel_map_pages(struct page *page, int numpages, int enable)
+void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (PageHighMem(page))
 		return;

include/linux/mm.h

@@ -2061,7 +2061,22 @@ static inline void vm_stat_account(struct mm_struct *mm,
 #endif /* CONFIG_PROC_FS */
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
-extern void kernel_map_pages(struct page *page, int numpages, int enable);
+extern bool _debug_pagealloc_enabled;
+extern void __kernel_map_pages(struct page *page, int numpages, int enable);
+
+static inline bool debug_pagealloc_enabled(void)
+{
+	return _debug_pagealloc_enabled;
+}
+
+static inline void
+kernel_map_pages(struct page *page, int numpages, int enable)
+{
+	if (!debug_pagealloc_enabled())
+		return;
+
+	__kernel_map_pages(page, numpages, enable);
+}
 #ifdef CONFIG_HIBERNATION
 extern bool kernel_page_present(struct page *page);
 #endif /* CONFIG_HIBERNATION */

mm/debug-pagealloc.c

@@ -10,11 +10,17 @@ static bool page_poisoning_enabled __read_mostly;
 
 static bool need_page_poisoning(void)
 {
+	if (!debug_pagealloc_enabled())
+		return false;
+
 	return true;
 }
 
 static void init_page_poisoning(void)
 {
+	if (!debug_pagealloc_enabled())
+		return;
+
 	page_poisoning_enabled = true;
 }
 
@@ -119,7 +125,7 @@ static void unpoison_pages(struct page *page, int n)
 		unpoison_page(page + i);
 }
 
-void kernel_map_pages(struct page *page, int numpages, int enable)
+void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (!page_poisoning_enabled)
 		return;

mm/page_alloc.c

@@ -425,15 +425,35 @@ static inline void prep_zero_page(struct page *page, unsigned int order,
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 unsigned int _debug_guardpage_minorder;
+bool _debug_pagealloc_enabled __read_mostly;
 bool _debug_guardpage_enabled __read_mostly;
 
+static int __init early_debug_pagealloc(char *buf)
+{
+	if (!buf)
+		return -EINVAL;
+
+	if (strcmp(buf, "on") == 0)
+		_debug_pagealloc_enabled = true;
+
+	return 0;
+}
+early_param("debug_pagealloc", early_debug_pagealloc);
+
 static bool need_debug_guardpage(void)
 {
+	/* If we don't use debug_pagealloc, we don't need guard page */
+	if (!debug_pagealloc_enabled())
+		return false;
+
 	return true;
 }
 
 static void init_debug_guardpage(void)
 {
+	if (!debug_pagealloc_enabled())
+		return;
+
 	_debug_guardpage_enabled = true;
 }