Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few misc things

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (132 commits)
  hugetlbfs: dirty pages as they are added to pagecache
  mm: export add_swap_extent()
  mm: split SWP_FILE into SWP_ACTIVATED and SWP_FS
  tools/testing/selftests/vm/map_fixed_noreplace.c: add test for MAP_FIXED_NOREPLACE
  mm: thp: relocate flush_cache_range() in migrate_misplaced_transhuge_page()
  mm: thp: fix mmu_notifier in migrate_misplaced_transhuge_page()
  mm: thp: fix MADV_DONTNEED vs migrate_misplaced_transhuge_page race condition
  mm/kasan/quarantine.c: make quarantine_lock a raw_spinlock_t
  mm/gup: cache dev_pagemap while pinning pages
  Revert "x86/e820: put !E820_TYPE_RAM regions into memblock.reserved"
  mm: return zero_resv_unavail optimization
  mm: zero remaining unavailable struct pages
  tools/testing/selftests/vm/gup_benchmark.c: add MAP_HUGETLB option
  tools/testing/selftests/vm/gup_benchmark.c: add MAP_SHARED option
  tools/testing/selftests/vm/gup_benchmark.c: allow user specified file
  tools/testing/selftests/vm/gup_benchmark.c: fix 'write' flag usage
  mm/gup_benchmark.c: add additional pinning methods
  mm/gup_benchmark.c: time put_page()
  mm: don't raise MEMCG_OOM event due to failed high-order allocation
  mm/page-writeback.c: fix range_cyclic writeback vs writepages deadlock
  ...

6 files changed, 327 insertions, 65 deletions

diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c
index 9f420d98b5fb..8cb504d30384 100644
--- a/tools/accounting/getdelays.c
+++ b/tools/accounting/getdelays.c
@@ -203,6 +203,8 @@ static void print_delayacct(struct taskstats *t)
 	       "SWAP  %15s%15s%15s\n"
 	       "      %15llu%15llu%15llums\n"
 	       "RECLAIM  %12s%15s%15s\n"
+	       "      %15llu%15llu%15llums\n"
+	       "THRASHING%12s%15s%15s\n"
 	       "      %15llu%15llu%15llums\n",
 	       "count", "real total", "virtual total",
 	       "delay total", "delay average",
@@ -222,7 +224,11 @@ static void print_delayacct(struct taskstats *t)
 	       "count", "delay total", "delay average",
 	       (unsigned long long)t->freepages_count,
 	       (unsigned long long)t->freepages_delay_total,
-	       average_ms(t->freepages_delay_total, t->freepages_count));
+	       average_ms(t->freepages_delay_total, t->freepages_count),
+	       "count", "delay total", "delay average",
+	       (unsigned long long)t->thrashing_count,
+	       (unsigned long long)t->thrashing_delay_total,
+	       average_ms(t->thrashing_delay_total, t->thrashing_count));
 }
 
 static void task_context_switch_counts(struct taskstats *t)
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index af5ff83f6d7f..31b3c98b6d34 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -13,3 +13,4 @@ mlock-random-test
 virtual_address_range
 gup_benchmark
 va_128TBswitch
+map_fixed_noreplace
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index e94b7b14bcb2..6e67e726e5a5 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -12,6 +12,7 @@ TEST_GEN_FILES += gup_benchmark
 TEST_GEN_FILES += hugepage-mmap
 TEST_GEN_FILES += hugepage-shm
 TEST_GEN_FILES += map_hugetlb
+TEST_GEN_FILES += map_fixed_noreplace
 TEST_GEN_FILES += map_populate
 TEST_GEN_FILES += mlock-random-test
 TEST_GEN_FILES += mlock2-tests
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index 36df55132036..880b96fc80d4 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -15,9 +15,12 @@
 #define PAGE_SIZE sysconf(_SC_PAGESIZE)
 
 #define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
+#define GUP_LONGTERM_BENCHMARK	_IOWR('g', 2, struct gup_benchmark)
+#define GUP_BENCHMARK		_IOWR('g', 3, struct gup_benchmark)
 
 struct gup_benchmark {
-	__u64 delta_usec;
+	__u64 get_delta_usec;
+	__u64 put_delta_usec;
 	__u64 addr;
 	__u64 size;
 	__u32 nr_pages_per_call;
@@ -28,10 +31,12 @@ int main(int argc, char **argv)
 {
 	struct gup_benchmark gup;
 	unsigned long size = 128 * MB;
-	int i, fd, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
+	int i, fd, filed, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
+	int cmd = GUP_FAST_BENCHMARK, flags = MAP_PRIVATE;
+	char *file = "/dev/zero";
 	char *p;
 
-	while ((opt = getopt(argc, argv, "m:r:n:tT")) != -1) {
+	while ((opt = getopt(argc, argv, "m:r:n:f:tTLUSH")) != -1) {
 		switch (opt) {
 		case 'm':
 			size = atoi(optarg) * MB;
@@ -48,13 +53,36 @@ int main(int argc, char **argv)
 		case 'T':
 			thp = 0;
 			break;
+		case 'L':
+			cmd = GUP_LONGTERM_BENCHMARK;
+			break;
+		case 'U':
+			cmd = GUP_BENCHMARK;
+			break;
 		case 'w':
 			write = 1;
+			break;
+		case 'f':
+			file = optarg;
+			break;
+		case 'S':
+			flags &= ~MAP_PRIVATE;
+			flags |= MAP_SHARED;
+			break;
+		case 'H':
+			flags |= MAP_HUGETLB;
+			break;
 		default:
 			return -1;
 		}
 	}
 
+	filed = open(file, O_RDWR|O_CREAT);
+	if (filed < 0) {
+		perror("open");
+		exit(filed);
+	}
+
 	gup.nr_pages_per_call = nr_pages;
 	gup.flags = write;
 
@@ -62,8 +90,7 @@ int main(int argc, char **argv)
 	if (fd == -1)
 		perror("open"), exit(1);
 
-	p = mmap(NULL, size, PROT_READ | PROT_WRITE,
-			MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	p = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, filed, 0);
 	if (p == MAP_FAILED)
 		perror("mmap"), exit(1);
 	gup.addr = (unsigned long)p;
@@ -78,10 +105,11 @@ int main(int argc, char **argv)
 
 	for (i = 0; i < repeats; i++) {
 		gup.size = size;
-		if (ioctl(fd, GUP_FAST_BENCHMARK, &gup))
+		if (ioctl(fd, cmd, &gup))
 			perror("ioctl"), exit(1);
 
-		printf("Time: %lld us", gup.delta_usec);
+		printf("Time: get:%lld put:%lld us", gup.get_delta_usec,
+			gup.put_delta_usec);
 		if (gup.size != size)
 			printf(", truncated (size: %lld)", gup.size);
 		printf("\n");
diff --git a/tools/testing/selftests/vm/map_fixed_noreplace.c b/tools/testing/selftests/vm/map_fixed_noreplace.c
new file mode 100644
index 000000000000..d91bde511268
--- /dev/null
+++ b/tools/testing/selftests/vm/map_fixed_noreplace.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Test that MAP_FIXED_NOREPLACE works.
+ *
+ * Copyright 2018, Jann Horn <jannh@google.com>
+ * Copyright 2018, Michael Ellerman, IBM Corporation.
+ */
+
+#include <sys/mman.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#ifndef MAP_FIXED_NOREPLACE
+#define MAP_FIXED_NOREPLACE 0x100000
+#endif
+
+#define BASE_ADDRESS	(256ul * 1024 * 1024)
+
+
+static void dump_maps(void)
+{
+	char cmd[32];
+
+	snprintf(cmd, sizeof(cmd), "cat /proc/%d/maps", getpid());
+	system(cmd);
+}
+
+int main(void)
+{
+	unsigned long flags, addr, size, page_size;
+	char *p;
+
+	page_size = sysconf(_SC_PAGE_SIZE);
+
+	flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED_NOREPLACE;
+
+	// Check we can map all the areas we need below
+	errno = 0;
+	addr = BASE_ADDRESS;
+	size = 5 * page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p == MAP_FAILED) {
+		dump_maps();
+		printf("Error: couldn't map the space we need for the test\n");
+		return 1;
+	}
+
+	errno = 0;
+	if (munmap((void *)addr, 5 * page_size) != 0) {
+		dump_maps();
+		printf("Error: munmap failed!?\n");
+		return 1;
+	}
+	printf("unmap() successful\n");
+
+	errno = 0;
+	addr = BASE_ADDRESS + page_size;
+	size = 3 * page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p == MAP_FAILED) {
+		dump_maps();
+		printf("Error: first mmap() failed unexpectedly\n");
+		return 1;
+	}
+
+	/*
+	 * Exact same mapping again:
+	 *   base |  free  | new
+	 *     +1 | mapped | new
+	 *     +2 | mapped | new
+	 *     +3 | mapped | new
+	 *     +4 |  free  | new
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS;
+	size = 5 * page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p != MAP_FAILED) {
+		dump_maps();
+		printf("Error:1: mmap() succeeded when it shouldn't have\n");
+		return 1;
+	}
+
+	/*
+	 * Second mapping contained within first:
+	 *
+	 *   base |  free  |
+	 *     +1 | mapped |
+	 *     +2 | mapped | new
+	 *     +3 | mapped |
+	 *     +4 |  free  |
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS + (2 * page_size);
+	size = page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p != MAP_FAILED) {
+		dump_maps();
+		printf("Error:2: mmap() succeeded when it shouldn't have\n");
+		return 1;
+	}
+
+	/*
+	 * Overlap end of existing mapping:
+	 *   base |  free  |
+	 *     +1 | mapped |
+	 *     +2 | mapped |
+	 *     +3 | mapped | new
+	 *     +4 |  free  | new
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS + (3 * page_size);
+	size = 2 * page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p != MAP_FAILED) {
+		dump_maps();
+		printf("Error:3: mmap() succeeded when it shouldn't have\n");
+		return 1;
+	}
+
+	/*
+	 * Overlap start of existing mapping:
+	 *   base |  free  | new
+	 *     +1 | mapped | new
+	 *     +2 | mapped |
+	 *     +3 | mapped |
+	 *     +4 |  free  |
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS;
+	size = 2 * page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p != MAP_FAILED) {
+		dump_maps();
+		printf("Error:4: mmap() succeeded when it shouldn't have\n");
+		return 1;
+	}
+
+	/*
+	 * Adjacent to start of existing mapping:
+	 *   base |  free  | new
+	 *     +1 | mapped |
+	 *     +2 | mapped |
+	 *     +3 | mapped |
+	 *     +4 |  free  |
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS;
+	size = page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p == MAP_FAILED) {
+		dump_maps();
+		printf("Error:5: mmap() failed when it shouldn't have\n");
+		return 1;
+	}
+
+	/*
+	 * Adjacent to end of existing mapping:
+	 *   base |  free  |
+	 *     +1 | mapped |
+	 *     +2 | mapped |
+	 *     +3 | mapped |
+	 *     +4 |  free  |  new
+	 */
+	errno = 0;
+	addr = BASE_ADDRESS + (4 * page_size);
+	size = page_size;
+	p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
+	printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
+
+	if (p == MAP_FAILED) {
+		dump_maps();
+		printf("Error:6: mmap() failed when it shouldn't have\n");
+		return 1;
+	}
+
+	addr = BASE_ADDRESS;
+	size = 5 * page_size;
+	if (munmap((void *)addr, size) != 0) {
+		dump_maps();
+		printf("Error: munmap failed!?\n");
+		return 1;
+	}
+	printf("unmap() successful\n");
+
+	printf("OK\n");
+	return 0;
+}
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 7b8171e3128a..5d1db824f73a 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -34,18 +34,6 @@
  * per-CPU threads 1 by triggering userfaults inside
  * pthread_mutex_lock will also verify the atomicity of the memory
  * transfer (UFFDIO_COPY).
- *
- * The program takes two parameters: the amounts of physical memory in
- * megabytes (MiB) of the area and the number of bounces to execute.
- *
- * # 100MiB 99999 bounces
- * ./userfaultfd 100 99999
- *
- * # 1GiB 99 bounces
- * ./userfaultfd 1000 99
- *
- * # 10MiB-~6GiB 999 bounces, continue forever unless an error triggers
- * while ./userfaultfd $[RANDOM % 6000 + 10] 999; do true; done
  */
 
 #define _GNU_SOURCE
@@ -115,6 +103,30 @@ pthread_attr_t attr;
 				 ~(unsigned long)(sizeof(unsigned long long) \
 						  -  1)))
 
+const char *examples =
+    "# Run anonymous memory test on 100MiB region with 99999 bounces:\n"
+    "./userfaultfd anon 100 99999\n\n"
+    "# Run share memory test on 1GiB region with 99 bounces:\n"
+    "./userfaultfd shmem 1000 99\n\n"
+    "# Run hugetlb memory test on 256MiB region with 50 bounces (using /dev/hugepages/hugefile):\n"
+    "./userfaultfd hugetlb 256 50 /dev/hugepages/hugefile\n\n"
+    "# Run the same hugetlb test but using shmem:\n"
+    "./userfaultfd hugetlb_shared 256 50 /dev/hugepages/hugefile\n\n"
+    "# 10MiB-~6GiB 999 bounces anonymous test, "
+    "continue forever unless an error triggers\n"
+    "while ./userfaultfd anon $[RANDOM % 6000 + 10] 999; do true; done\n\n";
+
+static void usage(void)
+{
+	fprintf(stderr, "\nUsage: ./userfaultfd <test type> <MiB> <bounces> "
+		"[hugetlbfs_file]\n\n");
+	fprintf(stderr, "Supported <test type>: anon, hugetlb, "
+		"hugetlb_shared, shmem\n\n");
+	fprintf(stderr, "Examples:\n\n");
+	fprintf(stderr, examples);
+	exit(1);
+}
+
 static int anon_release_pages(char *rel_area)
 {
 	int ret = 0;
@@ -439,6 +451,43 @@ static int copy_page(int ufd, unsigned long offset)
 	return __copy_page(ufd, offset, false);
 }
 
+static int uffd_read_msg(int ufd, struct uffd_msg *msg)
+{
+	int ret = read(uffd, msg, sizeof(*msg));
+
+	if (ret != sizeof(*msg)) {
+		if (ret < 0) {
+			if (errno == EAGAIN)
+				return 1;
+			else
+				perror("blocking read error"), exit(1);
+		} else {
+			fprintf(stderr, "short read\n"), exit(1);
+		}
+	}
+
+	return 0;
+}
+
+/* Return 1 if page fault handled by us; otherwise 0 */
+static int uffd_handle_page_fault(struct uffd_msg *msg)
+{
+	unsigned long offset;
+
+	if (msg->event != UFFD_EVENT_PAGEFAULT)
+		fprintf(stderr, "unexpected msg event %u\n",
+			msg->event), exit(1);
+
+	if (bounces & BOUNCE_VERIFY &&
+	    msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
+		fprintf(stderr, "unexpected write fault\n"), exit(1);
+
+	offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst;
+	offset &= ~(page_size-1);
+
+	return copy_page(uffd, offset);
+}
+
 static void *uffd_poll_thread(void *arg)
 {
 	unsigned long cpu = (unsigned long) arg;
@@ -446,7 +495,6 @@ static void *uffd_poll_thread(void *arg)
 	struct uffd_msg msg;
 	struct uffdio_register uffd_reg;
 	int ret;
-	unsigned long offset;
 	char tmp_chr;
 	unsigned long userfaults = 0;
 
@@ -470,25 +518,15 @@ static void *uffd_poll_thread(void *arg)
 		if (!(pollfd[0].revents & POLLIN))
 			fprintf(stderr, "pollfd[0].revents %d\n",
 				pollfd[0].revents), exit(1);
-		ret = read(uffd, &msg, sizeof(msg));
-		if (ret < 0) {
-			if (errno == EAGAIN)
-				continue;
-			perror("nonblocking read error"), exit(1);
-		}
+		if (uffd_read_msg(uffd, &msg))
+			continue;
 		switch (msg.event) {
 		default:
 			fprintf(stderr, "unexpected msg event %u\n",
 				msg.event), exit(1);
 			break;
 		case UFFD_EVENT_PAGEFAULT:
-			if (msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
-				fprintf(stderr, "unexpected write fault\n"), exit(1);
-			offset = (char *)(unsigned long)msg.arg.pagefault.address -
-				area_dst;
-			offset &= ~(page_size-1);
-			if (copy_page(uffd, offset))
-				userfaults++;
+			userfaults += uffd_handle_page_fault(&msg);
 			break;
 		case UFFD_EVENT_FORK:
 			close(uffd);
@@ -516,8 +554,6 @@ static void *uffd_read_thread(void *arg)
 {
 	unsigned long *this_cpu_userfaults;
 	struct uffd_msg msg;
-	unsigned long offset;
-	int ret;
 
 	this_cpu_userfaults = (unsigned long *) arg;
 	*this_cpu_userfaults = 0;
@@ -526,24 +562,9 @@ static void *uffd_read_thread(void *arg)
 	/* from here cancellation is ok */
 
 	for (;;) {
-		ret = read(uffd, &msg, sizeof(msg));
-		if (ret != sizeof(msg)) {
-			if (ret < 0)
-				perror("blocking read error"), exit(1);
-			else
-				fprintf(stderr, "short read\n"), exit(1);
-		}
-		if (msg.event != UFFD_EVENT_PAGEFAULT)
-			fprintf(stderr, "unexpected msg event %u\n",
-				msg.event), exit(1);
-		if (bounces & BOUNCE_VERIFY &&
-		    msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE)
-			fprintf(stderr, "unexpected write fault\n"), exit(1);
-		offset = (char *)(unsigned long)msg.arg.pagefault.address -
-			 area_dst;
-		offset &= ~(page_size-1);
-		if (copy_page(uffd, offset))
-			(*this_cpu_userfaults)++;
+		if (uffd_read_msg(uffd, &msg))
+			continue;
+		(*this_cpu_userfaults) += uffd_handle_page_fault(&msg);
 	}
 	return (void *)NULL;
 }
@@ -605,6 +626,12 @@ static int stress(unsigned long *userfaults)
 	if (uffd_test_ops->release_pages(area_src))
 		return 1;
 
+
+	finished = 1;
+	for (cpu = 0; cpu < nr_cpus; cpu++)
+		if (pthread_join(locking_threads[cpu], NULL))
+			return 1;
+
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		char c;
 		if (bounces & BOUNCE_POLL) {
@@ -622,11 +649,6 @@ static int stress(unsigned long *userfaults)
 		}
 	}
 
-	finished = 1;
-	for (cpu = 0; cpu < nr_cpus; cpu++)
-		if (pthread_join(locking_threads[cpu], NULL))
-			return 1;
-
 	return 0;
 }
 
@@ -1272,8 +1294,7 @@ static void sigalrm(int sig)
 int main(int argc, char **argv)
 {
 	if (argc < 4)
-		fprintf(stderr, "Usage: <test type> <MiB> <bounces> [hugetlbfs_file]\n"),
-				exit(1);
+		usage();
 
 	if (signal(SIGALRM, sigalrm) == SIG_ERR)
 		fprintf(stderr, "failed to arm SIGALRM"), exit(1);
@@ -1286,20 +1307,19 @@ int main(int argc, char **argv)
 		nr_cpus;
 	if (!nr_pages_per_cpu) {
 		fprintf(stderr, "invalid MiB\n");
-		fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
+		usage();
 	}
 
 	bounces = atoi(argv[3]);
 	if (bounces <= 0) {
 		fprintf(stderr, "invalid bounces\n");
-		fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
+		usage();
 	}
 	nr_pages = nr_pages_per_cpu * nr_cpus;
 
 	if (test_type == TEST_HUGETLB) {
 		if (argc < 5)
-			fprintf(stderr, "Usage: hugetlb <MiB> <bounces> <hugetlbfs_file>\n"),
-				exit(1);
+			usage();
 		huge_fd = open(argv[4], O_CREAT | O_RDWR, 0755);
 		if (huge_fd < 0) {
 			fprintf(stderr, "Open of %s failed", argv[3]);