merge mm-hotfixes-stable into mm-stable to pick up depended-upon changes

lib/maple_tree.c

@@ -4107,6 +4107,10 @@ static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas)
  * mas_wr_append: Attempt to append
  * @wr_mas: the maple write state
  *
+ * This is currently unsafe in rcu mode since the end of the node may be cached
+ * by readers while the node contents may be updated which could result in
+ * inaccurate information.
+ *
  * Return: True if appended, false otherwise
  */
 static inline bool mas_wr_append(struct ma_wr_state *wr_mas,
@@ -4116,6 +4120,9 @@ static inline bool mas_wr_append(struct ma_wr_state *wr_mas,
 	struct ma_state *mas = wr_mas->mas;
 	unsigned char node_pivots = mt_pivots[wr_mas->type];
 
+	if (mt_in_rcu(mas->tree))
+		return false;
+
 	if (mas->offset != wr_mas->node_end)
 		return false;
 

mm/huge_memory.c

@@ -1607,7 +1607,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	 * If other processes are mapping this folio, we couldn't discard
 	 * the folio unless they all do MADV_FREE so let's skip the folio.
 	 */
-	if (folio_mapcount(folio) != 1)
+	if (folio_estimated_sharers(folio) != 1)
 		goto out;
 
 	if (!folio_trylock(folio))

mm/madvise.c

@@ -383,7 +383,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
 		folio = pfn_folio(pmd_pfn(orig_pmd));
 
 		/* Do not interfere with other mappings of this folio */
-		if (folio_mapcount(folio) != 1)
+		if (folio_estimated_sharers(folio) != 1)
 			goto huge_unlock;
 
 		if (pageout_anon_only_filter && !folio_test_anon(folio))
@@ -459,7 +459,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
 		if (folio_test_large(folio)) {
 			int err;
 
-			if (folio_mapcount(folio) != 1)
+			if (folio_estimated_sharers(folio) != 1)
 				break;
 			if (pageout_anon_only_filter && !folio_test_anon(folio))
 				break;
@@ -683,7 +683,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 		if (folio_test_large(folio)) {
 			int err;
 
-			if (folio_mapcount(folio) != 1)
+			if (folio_estimated_sharers(folio) != 1)
 				break;
 			if (!folio_trylock(folio))
 				break;

mm/shmem.c

@@ -806,14 +806,16 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping,
 	XA_STATE(xas, &mapping->i_pages, start);
 	struct page *page;
 	unsigned long swapped = 0;
+	unsigned long max = end - 1;
 
 	rcu_read_lock();
-	xas_for_each(&xas, page, end - 1) {
+	xas_for_each(&xas, page, max) {
 		if (xas_retry(&xas, page))
 			continue;
 		if (xa_is_value(page))
 			swapped++;
-
+		if (xas.xa_index == max)
+			break;
 		if (need_resched()) {
 			xas_pause(&xas);
 			cond_resched_rcu();

tools/testing/selftests/cachestat/test_cachestat.c

@@ -4,10 +4,12 @@
 #include <stdio.h>
 #include <stdbool.h>
 #include <linux/kernel.h>
+#include <linux/magic.h>
 #include <linux/mman.h>
 #include <sys/mman.h>
 #include <sys/shm.h>
 #include <sys/syscall.h>
+#include <sys/vfs.h>
 #include <unistd.h>
 #include <string.h>
 #include <fcntl.h>
@@ -15,6 +17,8 @@
 
 #include "../kselftest.h"
 
+#define NR_TESTS	9
+
 static const char * const dev_files[] = {
 	"/dev/zero", "/dev/null", "/dev/urandom",
 	"/proc/version", "/proc"
@@ -90,6 +94,20 @@ bool write_exactly(int fd, size_t filesize)
 	return ret;
 }
 
+/*
+ * fsync() is implemented via noop_fsync() on tmpfs. This makes the fsync()
+ * test fail below, so we need to check for test file living on a tmpfs.
+ */
+static bool is_on_tmpfs(int fd)
+{
+	struct statfs statfs_buf;
+
+	if (fstatfs(fd, &statfs_buf))
+		return false;
+
+	return statfs_buf.f_type == TMPFS_MAGIC;
+}
+
 /*
  * Open/create the file at filename, (optionally) write random data to it
  * (exactly num_pages), then test the cachestat syscall on this file.
@@ -97,13 +115,13 @@ bool write_exactly(int fd, size_t filesize)
  * If test_fsync == true, fsync the file, then check the number of dirty
  * pages.
  */
-bool test_cachestat(const char *filename, bool write_random, bool create,
-		bool test_fsync, unsigned long num_pages, int open_flags,
-		mode_t open_mode)
+static int test_cachestat(const char *filename, bool write_random, bool create,
+			  bool test_fsync, unsigned long num_pages,
+			  int open_flags, mode_t open_mode)
 {
 	size_t PS = sysconf(_SC_PAGESIZE);
 	int filesize = num_pages * PS;
-	bool ret = true;
+	int ret = KSFT_PASS;
 	long syscall_ret;
 	struct cachestat cs;
 	struct cachestat_range cs_range = { 0, filesize };
@@ -112,7 +130,7 @@ bool test_cachestat(const char *filename, bool write_random, bool create,
 
 	if (fd == -1) {
 		ksft_print_msg("Unable to create/open file.\n");
-		ret = false;
+		ret = KSFT_FAIL;
 		goto out;
 	} else {
 		ksft_print_msg("Create/open %s\n", filename);
@@ -121,7 +139,7 @@ bool test_cachestat(const char *filename, bool write_random, bool create,
 	if (write_random) {
 		if (!write_exactly(fd, filesize)) {
 			ksft_print_msg("Unable to access urandom.\n");
-			ret = false;
+			ret = KSFT_FAIL;
 			goto out1;
 		}
 	}
@@ -132,7 +150,7 @@ bool test_cachestat(const char *filename, bool write_random, bool create,
 
 	if (syscall_ret) {
 		ksft_print_msg("Cachestat returned non-zero.\n");
-		ret = false;
+		ret = KSFT_FAIL;
 		goto out1;
 
 	} else {
@@ -142,15 +160,17 @@ bool test_cachestat(const char *filename, bool write_random, bool create,
 			if (cs.nr_cache + cs.nr_evicted != num_pages) {
 				ksft_print_msg(
 					"Total number of cached and evicted pages is off.\n");
-				ret = false;
+				ret = KSFT_FAIL;
 			}
 		}
 	}
 
 	if (test_fsync) {
-		if (fsync(fd)) {
+		if (is_on_tmpfs(fd)) {
+			ret = KSFT_SKIP;
+		} else if (fsync(fd)) {
 			ksft_print_msg("fsync fails.\n");
-			ret = false;
+			ret = KSFT_FAIL;
 		} else {
 			syscall_ret = syscall(cachestat_nr, fd, &cs_range, &cs, 0);
 
@@ -161,13 +181,13 @@ bool test_cachestat(const char *filename, bool write_random, bool create,
 				print_cachestat(&cs);
 
 				if (cs.nr_dirty) {
-					ret = false;
+					ret = KSFT_FAIL;
 					ksft_print_msg(
 						"Number of dirty should be zero after fsync.\n");
 				}
 			} else {
 				ksft_print_msg("Cachestat (after fsync) returned non-zero.\n");
-				ret = false;
+				ret = KSFT_FAIL;
 				goto out1;
 			}
 		}
@@ -236,13 +256,29 @@ bool test_cachestat_shmem(void)
 
 int main(void)
 {
-	int ret = 0;
+	int ret;
+
+	ksft_print_header();
+
+	ret = syscall(__NR_cachestat, -1, NULL, NULL, 0);
+	if (ret == -1 && errno == ENOSYS)
+		ksft_exit_skip("cachestat syscall not available\n");
+
+	ksft_set_plan(NR_TESTS);
+
+	if (ret == -1 && errno == EBADF) {
+		ksft_test_result_pass("bad file descriptor recognized\n");
+		ret = 0;
+	} else {
+		ksft_test_result_fail("bad file descriptor ignored\n");
+		ret = 1;
+	}
 
 	for (int i = 0; i < 5; i++) {
 		const char *dev_filename = dev_files[i];
 
 		if (test_cachestat(dev_filename, false, false, false,
-			4, O_RDONLY, 0400))
+			4, O_RDONLY, 0400) == KSFT_PASS)
 			ksft_test_result_pass("cachestat works with %s\n", dev_filename);
 		else {
 			ksft_test_result_fail("cachestat fails with %s\n", dev_filename);
@@ -251,13 +287,27 @@ int main(void)
 	}
 
 	if (test_cachestat("tmpfilecachestat", true, true,
-		true, 4, O_CREAT | O_RDWR, 0400 | 0600))
+		false, 4, O_CREAT | O_RDWR, 0600) == KSFT_PASS)
 		ksft_test_result_pass("cachestat works with a normal file\n");
 	else {
 		ksft_test_result_fail("cachestat fails with normal file\n");
 		ret = 1;
 	}
 
+	switch (test_cachestat("tmpfilecachestat", true, true,
+		true, 4, O_CREAT | O_RDWR, 0600)) {
+	case KSFT_FAIL:
+		ksft_test_result_fail("cachestat fsync fails with normal file\n");
+		ret = KSFT_FAIL;
+		break;
+	case KSFT_PASS:
+		ksft_test_result_pass("cachestat fsync works with a normal file\n");
+		break;
+	case KSFT_SKIP:
+		ksft_test_result_skip("tmpfilecachestat is on tmpfs\n");
+		break;
+	}
+
 	if (test_cachestat_shmem())
 		ksft_test_result_pass("cachestat works with a shmem file\n");
 	else {