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, 77 insertions, 18 deletions

diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
index 0941aa16157e..22b31ebb3513 100644
--- a/tools/testing/selftests/cgroup/test_kmem.c
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -19,12 +19,12 @@
 
 
 /*
- * Memory cgroup charging and vmstat data aggregation is performed using
- * percpu batches 32 pages big (look at MEMCG_CHARGE_BATCH). So the maximum
- * discrepancy between charge and vmstat entries is number of cpus multiplied
- * by 32 pages multiplied by 2.
+ * Memory cgroup charging is performed using percpu batches 32 pages
+ * big (look at MEMCG_CHARGE_BATCH), whereas memory.stat is exact. So
+ * the maximum discrepancy between charge and vmstat entries is number
+ * of cpus multiplied by 32 pages.
  */
-#define MAX_VMSTAT_ERROR (4096 * 32 * 2 * get_nprocs())
+#define MAX_VMSTAT_ERROR (4096 * 32 * get_nprocs())
 
 
 static int alloc_dcache(const char *cgroup, void *arg)
@@ -162,7 +162,7 @@ static int cg_run_in_subcgroups(const char *parent,
  */
 static int test_kmem_memcg_deletion(const char *root)
 {
-	long current, slab, anon, file, kernel_stack, sum;
+	long current, slab, anon, file, kernel_stack, pagetables, percpu, sock, sum;
 	int ret = KSFT_FAIL;
 	char *parent;
 
@@ -184,11 +184,14 @@ static int test_kmem_memcg_deletion(const char *root)
 	anon = cg_read_key_long(parent, "memory.stat", "anon ");
 	file = cg_read_key_long(parent, "memory.stat", "file ");
 	kernel_stack = cg_read_key_long(parent, "memory.stat", "kernel_stack ");
+	pagetables = cg_read_key_long(parent, "memory.stat", "pagetables ");
+	percpu = cg_read_key_long(parent, "memory.stat", "percpu ");
+	sock = cg_read_key_long(parent, "memory.stat", "sock ");
 	if (current < 0 || slab < 0 || anon < 0 || file < 0 ||
-	    kernel_stack < 0)
+	    kernel_stack < 0 || pagetables < 0 || percpu < 0 || sock < 0)
 		goto cleanup;
 
-	sum = slab + anon + file + kernel_stack;
+	sum = slab + anon + file + kernel_stack + pagetables + percpu + sock;
 	if (abs(sum - current) < MAX_VMSTAT_ERROR) {
 		ret = KSFT_PASS;
 	} else {
@@ -198,6 +201,9 @@ static int test_kmem_memcg_deletion(const char *root)
 		printf("anon = %ld\n", anon);
 		printf("file = %ld\n", file);
 		printf("kernel_stack = %ld\n", kernel_stack);
+		printf("pagetables = %ld\n", pagetables);
+		printf("percpu = %ld\n", percpu);
+		printf("sock = %ld\n", sock);
 	}
 
 cleanup:
diff --git a/tools/testing/selftests/vm/mremap_dontunmap.c b/tools/testing/selftests/vm/mremap_dontunmap.c
index 3a7b5ef0b0c6..f01dc4a85b0b 100644
--- a/tools/testing/selftests/vm/mremap_dontunmap.c
+++ b/tools/testing/selftests/vm/mremap_dontunmap.c
@@ -127,6 +127,57 @@ static void mremap_dontunmap_simple()
 	       "unable to unmap source mapping");
 }
 
+// This test validates that MREMAP_DONTUNMAP on a shared mapping works as expected.
+static void mremap_dontunmap_simple_shmem()
+{
+	unsigned long num_pages = 5;
+
+	int mem_fd = memfd_create("memfd", MFD_CLOEXEC);
+	BUG_ON(mem_fd < 0, "memfd_create");
+
+	BUG_ON(ftruncate(mem_fd, num_pages * page_size) < 0,
+			"ftruncate");
+
+	void *source_mapping =
+	    mmap(NULL, num_pages * page_size, PROT_READ | PROT_WRITE,
+		 MAP_FILE | MAP_SHARED, mem_fd, 0);
+	BUG_ON(source_mapping == MAP_FAILED, "mmap");
+
+	BUG_ON(close(mem_fd) < 0, "close");
+
+	memset(source_mapping, 'a', num_pages * page_size);
+
+	// Try to just move the whole mapping anywhere (not fixed).
+	void *dest_mapping =
+	    mremap(source_mapping, num_pages * page_size, num_pages * page_size,
+		   MREMAP_DONTUNMAP | MREMAP_MAYMOVE, NULL);
+	if (dest_mapping == MAP_FAILED && errno == EINVAL) {
+		// Old kernel which doesn't support MREMAP_DONTUNMAP on shmem.
+		BUG_ON(munmap(source_mapping, num_pages * page_size) == -1,
+			"unable to unmap source mapping");
+		return;
+	}
+
+	BUG_ON(dest_mapping == MAP_FAILED, "mremap");
+
+	// Validate that the pages have been moved, we know they were moved if
+	// the dest_mapping contains a's.
+	BUG_ON(check_region_contains_byte
+	       (dest_mapping, num_pages * page_size, 'a') != 0,
+	       "pages did not migrate");
+
+	// Because the region is backed by shmem, we will actually see the same
+	// memory at the source location still.
+	BUG_ON(check_region_contains_byte
+	       (source_mapping, num_pages * page_size, 'a') != 0,
+	       "source should have no ptes");
+
+	BUG_ON(munmap(dest_mapping, num_pages * page_size) == -1,
+	       "unable to unmap destination mapping");
+	BUG_ON(munmap(source_mapping, num_pages * page_size) == -1,
+	       "unable to unmap source mapping");
+}
+
 // This test validates MREMAP_DONTUNMAP will move page tables to a specific
 // destination using MREMAP_FIXED, also while validating that the source
 // remains intact.
@@ -300,6 +351,7 @@ int main(void)
 	BUG_ON(page_buffer == MAP_FAILED, "unable to mmap a page.");
 
 	mremap_dontunmap_simple();
+	mremap_dontunmap_simple_shmem();
 	mremap_dontunmap_simple_fixed();
 	mremap_dontunmap_partial_mapping();
 	mremap_dontunmap_partial_mapping_overwrite();
diff --git a/tools/testing/selftests/vm/test_vmalloc.sh b/tools/testing/selftests/vm/test_vmalloc.sh
index 06d2bb109f06..d73b846736f1 100755
--- a/tools/testing/selftests/vm/test_vmalloc.sh
+++ b/tools/testing/selftests/vm/test_vmalloc.sh
@@ -11,6 +11,7 @@
 
 TEST_NAME="vmalloc"
 DRIVER="test_${TEST_NAME}"
+NUM_CPUS=`grep -c ^processor /proc/cpuinfo`
 
 # 1 if fails
 exitcode=1
@@ -22,9 +23,9 @@ ksft_skip=4
 # Static templates for performance, stressing and smoke tests.
 # Also it is possible to pass any supported parameters manualy.
 #
-PERF_PARAM="single_cpu_test=1 sequential_test_order=1 test_repeat_count=3"
-SMOKE_PARAM="single_cpu_test=1 test_loop_count=10000 test_repeat_count=10"
-STRESS_PARAM="test_repeat_count=20"
+PERF_PARAM="sequential_test_order=1 test_repeat_count=3"
+SMOKE_PARAM="test_loop_count=10000 test_repeat_count=10"
+STRESS_PARAM="nr_threads=$NUM_CPUS test_repeat_count=20"
 
 check_test_requirements()
 {
@@ -58,8 +59,8 @@ run_perfformance_check()
 
 run_stability_check()
 {
-	echo "Run stability tests. In order to stress vmalloc subsystem we run"
-	echo "all available test cases on all available CPUs simultaneously."
+	echo "Run stability tests. In order to stress vmalloc subsystem all"
+	echo "available test cases are run by NUM_CPUS workers simultaneously."
 	echo "It will take time, so be patient."
 
 	modprobe $DRIVER $STRESS_PARAM > /dev/null 2>&1
@@ -92,17 +93,17 @@ usage()
 	echo "# Shows help message"
 	echo "./${DRIVER}.sh"
 	echo
-	echo "# Runs 1 test(id_1), repeats it 5 times on all online CPUs"
-	echo "./${DRIVER}.sh run_test_mask=1 test_repeat_count=5"
+	echo "# Runs 1 test(id_1), repeats it 5 times by NUM_CPUS workers"
+	echo "./${DRIVER}.sh nr_threads=$NUM_CPUS run_test_mask=1 test_repeat_count=5"
 	echo
 	echo -n "# Runs 4 tests(id_1|id_2|id_4|id_16) on one CPU with "
 	echo "sequential order"
-	echo -n "./${DRIVER}.sh single_cpu_test=1 sequential_test_order=1 "
+	echo -n "./${DRIVER}.sh sequential_test_order=1 "
 	echo "run_test_mask=23"
 	echo
-	echo -n "# Runs all tests on all online CPUs, shuffled order, repeats "
+	echo -n "# Runs all tests by NUM_CPUS workers, shuffled order, repeats "
 	echo "20 times"
-	echo "./${DRIVER}.sh test_repeat_count=20"
+	echo "./${DRIVER}.sh nr_threads=$NUM_CPUS test_repeat_count=20"
 	echo
 	echo "# Performance analysis"
 	echo "./${DRIVER}.sh performance"