Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "A few misc subsystems and some of MM.

  175 patches.

  Subsystems affected by this patch series: ia64, kbuild, scripts, sh,
  ocfs2, kfifo, vfs, kernel/watchdog, and mm (slab-generic, slub,
  kmemleak, debug, pagecache, msync, gup, memremap, memcg, pagemap,
  mremap, dma, sparsemem, vmalloc, documentation, kasan, initialization,
  pagealloc, and memory-failure)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (175 commits)
  mm/memory-failure: unnecessary amount of unmapping
  mm/mmzone.h: fix existing kernel-doc comments and link them to core-api
  mm: page_alloc: ignore init_on_free=1 for debug_pagealloc=1
  net: page_pool: use alloc_pages_bulk in refill code path
  net: page_pool: refactor dma_map into own function page_pool_dma_map
  SUNRPC: refresh rq_pages using a bulk page allocator
  SUNRPC: set rq_page_end differently
  mm/page_alloc: inline __rmqueue_pcplist
  mm/page_alloc: optimize code layout for __alloc_pages_bulk
  mm/page_alloc: add an array-based interface to the bulk page allocator
  mm/page_alloc: add a bulk page allocator
  mm/page_alloc: rename alloced to allocated
  mm/page_alloc: duplicate include linux/vmalloc.h
  mm, page_alloc: avoid page_to_pfn() in move_freepages()
  mm/Kconfig: remove default DISCONTIGMEM_MANUAL
  mm: page_alloc: dump migrate-failed pages
  mm/mempolicy: fix mpol_misplaced kernel-doc
  mm/mempolicy: rewrite alloc_pages_vma documentation
  mm/mempolicy: rewrite alloc_pages documentation
  mm/mempolicy: rename alloc_pages_current to alloc_pages
  ...

3 files changed, 79 insertions, 117 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index b38bbb5bb00e..678c13967580 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2573,11 +2573,18 @@ config TEST_FPU
 
 endif # RUNTIME_TESTING_MENU
 
+config ARCH_USE_MEMTEST
+	bool
+	help
+	  An architecture should select this when it uses early_memtest()
+	  during boot process.
+
 config MEMTEST
 	bool "Memtest"
+	depends on ARCH_USE_MEMTEST
 	help
 	  This option adds a kernel parameter 'memtest', which allows memtest
-	  to be set.
+	  to be set and executed.
 	        memtest=0, mean disabled; -- default
 	        memtest=1, mean do 1 test pattern;
 	        ...
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 785e724ce0d8..dc05cfc2d12f 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -54,6 +54,10 @@ static int kasan_test_init(struct kunit *test)
 
 	multishot = kasan_save_enable_multi_shot();
 	kasan_set_tagging_report_once(false);
+	fail_data.report_found = false;
+	fail_data.report_expected = false;
+	kunit_add_named_resource(test, NULL, NULL, &resource,
+					"kasan_data", &fail_data);
 	return 0;
 }
 
@@ -61,6 +65,7 @@ static void kasan_test_exit(struct kunit *test)
 {
 	kasan_set_tagging_report_once(true);
 	kasan_restore_multi_shot(multishot);
+	KUNIT_EXPECT_FALSE(test, fail_data.report_found);
 }
 
 /**
@@ -78,33 +83,31 @@ static void kasan_test_exit(struct kunit *test)
  * fields, it can reorder or optimize away the accesses to those fields.
  * Use READ/WRITE_ONCE() for the accesses and compiler barriers around the
  * expression to prevent that.
+ *
+ * In between KUNIT_EXPECT_KASAN_FAIL checks, fail_data.report_found is kept as
+ * false. This allows detecting KASAN reports that happen outside of the checks
+ * by asserting !fail_data.report_found at the start of KUNIT_EXPECT_KASAN_FAIL
+ * and in kasan_test_exit.
  */
-#define KUNIT_EXPECT_KASAN_FAIL(test, expression) do {		\
-	if (IS_ENABLED(CONFIG_KASAN_HW_TAGS) &&			\
-	    !kasan_async_mode_enabled())			\
-		migrate_disable();				\
-	WRITE_ONCE(fail_data.report_expected, true);		\
-	WRITE_ONCE(fail_data.report_found, false);		\
-	kunit_add_named_resource(test,				\
-				NULL,				\
-				NULL,				\
-				&resource,			\
-				"kasan_data", &fail_data);	\
-	barrier();						\
-	expression;						\
-	barrier();						\
-	if (kasan_async_mode_enabled())				\
-		kasan_force_async_fault();			\
-	barrier();						\
-	KUNIT_EXPECT_EQ(test,					\
-			READ_ONCE(fail_data.report_expected),	\
-			READ_ONCE(fail_data.report_found));	\
-	if (IS_ENABLED(CONFIG_KASAN_HW_TAGS) &&			\
-	    !kasan_async_mode_enabled()) {			\
-		if (READ_ONCE(fail_data.report_found))		\
-			kasan_enable_tagging_sync();		\
-		migrate_enable();				\
-	}							\
+#define KUNIT_EXPECT_KASAN_FAIL(test, expression) do {			\
+	if (IS_ENABLED(CONFIG_KASAN_HW_TAGS) &&				\
+	    !kasan_async_mode_enabled())				\
+		migrate_disable();					\
+	KUNIT_EXPECT_FALSE(test, READ_ONCE(fail_data.report_found));	\
+	WRITE_ONCE(fail_data.report_expected, true);			\
+	barrier();							\
+	expression;							\
+	barrier();							\
+	KUNIT_EXPECT_EQ(test,						\
+			READ_ONCE(fail_data.report_expected),		\
+			READ_ONCE(fail_data.report_found));		\
+	if (IS_ENABLED(CONFIG_KASAN_HW_TAGS)) {				\
+		if (READ_ONCE(fail_data.report_found))			\
+			kasan_enable_tagging_sync();			\
+		migrate_enable();					\
+	}								\
+	WRITE_ONCE(fail_data.report_found, false);			\
+	WRITE_ONCE(fail_data.report_expected, false);			\
 } while (0)
 
 #define KASAN_TEST_NEEDS_CONFIG_ON(test, config) do {			\
@@ -1049,14 +1052,14 @@ static void match_all_mem_tag(struct kunit *test)
 			continue;
 
 		/* Mark the first memory granule with the chosen memory tag. */
-		kasan_poison(ptr, KASAN_GRANULE_SIZE, (u8)tag);
+		kasan_poison(ptr, KASAN_GRANULE_SIZE, (u8)tag, false);
 
 		/* This access must cause a KASAN report. */
 		KUNIT_EXPECT_KASAN_FAIL(test, *ptr = 0);
 	}
 
 	/* Recover the memory tag and free. */
-	kasan_poison(ptr, KASAN_GRANULE_SIZE, get_tag(ptr));
+	kasan_poison(ptr, KASAN_GRANULE_SIZE, get_tag(ptr), false);
 	kfree(ptr);
 }
 
diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c
index 5cf2fe9aab9e..01e9543de566 100644
--- a/lib/test_vmalloc.c
+++ b/lib/test_vmalloc.c
@@ -23,8 +23,8 @@
 	module_param(name, type, 0444);			\
 	MODULE_PARM_DESC(name, msg)				\
 
-__param(bool, single_cpu_test, false,
-	"Use single first online CPU to run tests");
+__param(int, nr_threads, 0,
+	"Number of workers to perform tests(min: 1 max: USHRT_MAX)");
 
 __param(bool, sequential_test_order, false,
 	"Use sequential stress tests order");
@@ -47,19 +47,10 @@ __param(int, run_test_mask, INT_MAX,
 		"\t\tid: 128,  name: pcpu_alloc_test\n"
 		"\t\tid: 256,  name: kvfree_rcu_1_arg_vmalloc_test\n"
 		"\t\tid: 512,  name: kvfree_rcu_2_arg_vmalloc_test\n"
-		"\t\tid: 1024, name: kvfree_rcu_1_arg_slab_test\n"
-		"\t\tid: 2048, name: kvfree_rcu_2_arg_slab_test\n"
 		/* Add a new test case description here. */
 );
 
 /*
- * Depends on single_cpu_test parameter. If it is true, then
- * use first online CPU to trigger a test on, otherwise go with
- * all online CPUs.
- */
-static cpumask_t cpus_run_test_mask = CPU_MASK_NONE;
-
-/*
  * Read write semaphore for synchronization of setup
  * phase that is done in main thread and workers.
  */
@@ -363,42 +354,6 @@ kvfree_rcu_2_arg_vmalloc_test(void)
 	return 0;
 }
 
-static int
-kvfree_rcu_1_arg_slab_test(void)
-{
-	struct test_kvfree_rcu *p;
-	int i;
-
-	for (i = 0; i < test_loop_count; i++) {
-		p = kmalloc(sizeof(*p), GFP_KERNEL);
-		if (!p)
-			return -1;
-
-		p->array[0] = 'a';
-		kvfree_rcu(p);
-	}
-
-	return 0;
-}
-
-static int
-kvfree_rcu_2_arg_slab_test(void)
-{
-	struct test_kvfree_rcu *p;
-	int i;
-
-	for (i = 0; i < test_loop_count; i++) {
-		p = kmalloc(sizeof(*p), GFP_KERNEL);
-		if (!p)
-			return -1;
-
-		p->array[0] = 'a';
-		kvfree_rcu(p, rcu);
-	}
-
-	return 0;
-}
-
 struct test_case_desc {
 	const char *test_name;
 	int (*test_func)(void);
@@ -415,8 +370,6 @@ static struct test_case_desc test_case_array[] = {
 	{ "pcpu_alloc_test", pcpu_alloc_test },
 	{ "kvfree_rcu_1_arg_vmalloc_test", kvfree_rcu_1_arg_vmalloc_test },
 	{ "kvfree_rcu_2_arg_vmalloc_test", kvfree_rcu_2_arg_vmalloc_test },
-	{ "kvfree_rcu_1_arg_slab_test", kvfree_rcu_1_arg_slab_test },
-	{ "kvfree_rcu_2_arg_slab_test", kvfree_rcu_2_arg_slab_test },
 	/* Add a new test case here. */
 };
 
@@ -426,16 +379,13 @@ struct test_case_data {
 	u64 time;
 };
 
-/* Split it to get rid of: WARNING: line over 80 characters */
-static struct test_case_data
-	per_cpu_test_data[NR_CPUS][ARRAY_SIZE(test_case_array)];
-
 static struct test_driver {
 	struct task_struct *task;
+	struct test_case_data data[ARRAY_SIZE(test_case_array)];
+
 	unsigned long start;
 	unsigned long stop;
-	int cpu;
-} per_cpu_test_driver[NR_CPUS];
+} *tdriver;
 
 static void shuffle_array(int *arr, int n)
 {
@@ -463,9 +413,6 @@ static int test_func(void *private)
 	ktime_t kt;
 	u64 delta;
 
-	if (set_cpus_allowed_ptr(current, cpumask_of(t->cpu)) < 0)
-		pr_err("Failed to set affinity to %d CPU\n", t->cpu);
-
 	for (i = 0; i < ARRAY_SIZE(test_case_array); i++)
 		random_array[i] = i;
 
@@ -490,9 +437,9 @@ static int test_func(void *private)
 		kt = ktime_get();
 		for (j = 0; j < test_repeat_count; j++) {
 			if (!test_case_array[index].test_func())
-				per_cpu_test_data[t->cpu][index].test_passed++;
+				t->data[index].test_passed++;
 			else
-				per_cpu_test_data[t->cpu][index].test_failed++;
+				t->data[index].test_failed++;
 		}
 
 		/*
@@ -501,7 +448,7 @@ static int test_func(void *private)
 		delta = (u64) ktime_us_delta(ktime_get(), kt);
 		do_div(delta, (u32) test_repeat_count);
 
-		per_cpu_test_data[t->cpu][index].time = delta;
+		t->data[index].time = delta;
 	}
 	t->stop = get_cycles();
 
@@ -517,53 +464,56 @@ static int test_func(void *private)
 	return 0;
 }
 
-static void
+static int
 init_test_configurtion(void)
 {
 	/*
-	 * Reset all data of all CPUs.
+	 * A maximum number of workers is defined as hard-coded
+	 * value and set to USHRT_MAX. We add such gap just in
+	 * case and for potential heavy stressing.
 	 */
-	memset(per_cpu_test_data, 0, sizeof(per_cpu_test_data));
+	nr_threads = clamp(nr_threads, 1, (int) USHRT_MAX);
 
-	if (single_cpu_test)
-		cpumask_set_cpu(cpumask_first(cpu_online_mask),
-			&cpus_run_test_mask);
-	else
-		cpumask_and(&cpus_run_test_mask, cpu_online_mask,
-			cpu_online_mask);
+	/* Allocate the space for test instances. */
+	tdriver = kvcalloc(nr_threads, sizeof(*tdriver), GFP_KERNEL);
+	if (tdriver == NULL)
+		return -1;
 
 	if (test_repeat_count <= 0)
 		test_repeat_count = 1;
 
 	if (test_loop_count <= 0)
 		test_loop_count = 1;
+
+	return 0;
 }
 
 static void do_concurrent_test(void)
 {
-	int cpu, ret;
+	int i, ret;
 
 	/*
 	 * Set some basic configurations plus sanity check.
 	 */
-	init_test_configurtion();
+	ret = init_test_configurtion();
+	if (ret < 0)
+		return;
 
 	/*
 	 * Put on hold all workers.
 	 */
 	down_write(&prepare_for_test_rwsem);
 
-	for_each_cpu(cpu, &cpus_run_test_mask) {
-		struct test_driver *t = &per_cpu_test_driver[cpu];
+	for (i = 0; i < nr_threads; i++) {
+		struct test_driver *t = &tdriver[i];
 
-		t->cpu = cpu;
-		t->task = kthread_run(test_func, t, "vmalloc_test/%d", cpu);
+		t->task = kthread_run(test_func, t, "vmalloc_test/%d", i);
 
 		if (!IS_ERR(t->task))
 			/* Success. */
 			atomic_inc(&test_n_undone);
 		else
-			pr_err("Failed to start kthread for %d CPU\n", cpu);
+			pr_err("Failed to start %d kthread\n", i);
 	}
 
 	/*
@@ -581,29 +531,31 @@ static void do_concurrent_test(void)
 		ret = wait_for_completion_timeout(&test_all_done_comp, HZ);
 	} while (!ret);
 
-	for_each_cpu(cpu, &cpus_run_test_mask) {
-		struct test_driver *t = &per_cpu_test_driver[cpu];
-		int i;
+	for (i = 0; i < nr_threads; i++) {
+		struct test_driver *t = &tdriver[i];
+		int j;
 
 		if (!IS_ERR(t->task))
 			kthread_stop(t->task);
 
-		for (i = 0; i < ARRAY_SIZE(test_case_array); i++) {
-			if (!((run_test_mask & (1 << i)) >> i))
+		for (j = 0; j < ARRAY_SIZE(test_case_array); j++) {
+			if (!((run_test_mask & (1 << j)) >> j))
 				continue;
 
 			pr_info(
 				"Summary: %s passed: %d failed: %d repeat: %d loops: %d avg: %llu usec\n",
-				test_case_array[i].test_name,
-				per_cpu_test_data[cpu][i].test_passed,
-				per_cpu_test_data[cpu][i].test_failed,
+				test_case_array[j].test_name,
+				t->data[j].test_passed,
+				t->data[j].test_failed,
 				test_repeat_count, test_loop_count,
-				per_cpu_test_data[cpu][i].time);
+				t->data[j].time);
 		}
 
-		pr_info("All test took CPU%d=%lu cycles\n",
-			cpu, t->stop - t->start);
+		pr_info("All test took worker%d=%lu cycles\n",
+			i, t->stop - t->start);
 	}
+
+	kvfree(tdriver);
 }
 
 static int vmalloc_test_init(void)