21 hotfixes, 8 of which are cc:stable. 11 are for MM, the remainder are

for other subsystems.
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZB48xAAKCRDdBJ7gKXxA
 js2rAP4zvcMn90vBJhWNElsA7pBgDYD66QCK6JBDHGe3J1qdeQEA8D606pjMBWkL
 ly7NifwCjOtFhfDRgEHOXu8g8g1k1QM=
 =Cswg
 -----END PGP SIGNATURE-----

Merge tag 'mm-hotfixes-stable-2023-03-24-17-09' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "21 hotfixes, 8 of which are cc:stable. 11 are for MM, the remainder
  are for other subsystems"

* tag 'mm-hotfixes-stable-2023-03-24-17-09' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (21 commits)
  mm: mmap: remove newline at the end of the trace
  mailmap: add entries for Richard Leitner
  kcsan: avoid passing -g for test
  kfence: avoid passing -g for test
  mm: kfence: fix using kfence_metadata without initialization in show_object()
  lib: dhry: fix unstable smp_processor_id(_) usage
  mailmap: add entry for Enric Balletbo i Serra
  mailmap: map Sai Prakash Ranjan's old address to his current one
  mailmap: map Rajendra Nayak's old address to his current one
  Revert "kasan: drop skip_kasan_poison variable in free_pages_prepare"
  mailmap: add entry for Tobias Klauser
  kasan, powerpc: don't rename memintrinsics if compiler adds prefixes
  mm/ksm: fix race with VMA iteration and mm_struct teardown
  kselftest: vm: fix unused variable warning
  mm: fix error handling for map_deny_write_exec
  mm: deduplicate error handling for map_deny_write_exec
  checksyscalls: ignore fstat to silence build warning on LoongArch
  nilfs2: fix kernel-infoleak in nilfs_ioctl_wrap_copy()
  test_maple_tree: add more testing for mas_empty_area()
  maple_tree: fix mas_skip_node() end slot detection
  ...

.mailmap

@@ -133,6 +133,8 @@ Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com>
 Domen Puncer <domen@coderock.org>
 Douglas Gilbert <dougg@torque.net>
 Ed L. Cashin <ecashin@coraid.com>
+Enric Balletbo i Serra <eballetbo@kernel.org> <enric.balletbo@collabora.com>
+Enric Balletbo i Serra <eballetbo@kernel.org> <eballetbo@iseebcn.com>
 Erik Kaneda <erik.kaneda@intel.com> <erik.schmauss@intel.com>
 Eugen Hristev <eugen.hristev@collabora.com> <eugen.hristev@microchip.com>
 Evgeniy Polyakov <johnpol@2ka.mipt.ru>
@@ -379,6 +381,7 @@ Quentin Monnet <quentin@isovalent.com> <quentin.monnet@netronome.com>
 Quentin Perret <qperret@qperret.net> <quentin.perret@arm.com>
 Rafael J. Wysocki <rjw@rjwysocki.net> <rjw@sisk.pl>
 Rajeev Nandan <quic_rajeevny@quicinc.com> <rajeevny@codeaurora.org>
+Rajendra Nayak <quic_rjendra@quicinc.com> <rnayak@codeaurora.org>
 Rajesh Shah <rajesh.shah@intel.com>
 Ralf Baechle <ralf@linux-mips.org>
 Ralf Wildenhues <Ralf.Wildenhues@gmx.de>
@@ -387,6 +390,9 @@ Rémi Denis-Courmont <rdenis@simphalempin.com>
 Ricardo Ribalda <ribalda@kernel.org> <ricardo@ribalda.com>
 Ricardo Ribalda <ribalda@kernel.org> Ricardo Ribalda Delgado <ribalda@kernel.org>
 Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com>
+Richard Leitner <richard.leitner@linux.dev> <dev@g0hl1n.net>
+Richard Leitner <richard.leitner@linux.dev> <me@g0hl1n.net>
+Richard Leitner <richard.leitner@linux.dev> <richard.leitner@skidata.com>
 Robert Foss <rfoss@kernel.org> <robert.foss@linaro.org>
 Roman Gushchin <roman.gushchin@linux.dev> <guro@fb.com>
 Roman Gushchin <roman.gushchin@linux.dev> <guroan@gmail.com>
@@ -397,6 +403,7 @@ Ross Zwisler <zwisler@kernel.org> <ross.zwisler@linux.intel.com>
 Rudolf Marek <R.Marek@sh.cvut.cz>
 Rui Saraiva <rmps@joel.ist.utl.pt>
 Sachin P Sant <ssant@in.ibm.com>
+Sai Prakash Ranjan <quic_saipraka@quicinc.com> <saiprakash.ranjan@codeaurora.org>
 Sakari Ailus <sakari.ailus@linux.intel.com> <sakari.ailus@iki.fi>
 Sam Ravnborg <sam@mars.ravnborg.org>
 Sankeerth Billakanti <quic_sbillaka@quicinc.com> <sbillaka@codeaurora.org>
@@ -437,6 +444,10 @@ Thomas Graf <tgraf@suug.ch>
 Thomas Körper <socketcan@esd.eu> <thomas.koerper@esd.eu>
 Thomas Pedersen <twp@codeaurora.org>
 Tiezhu Yang <yangtiezhu@loongson.cn> <kernelpatch@126.com>
+Tobias Klauser <tklauser@distanz.ch> <tobias.klauser@gmail.com>
+Tobias Klauser <tklauser@distanz.ch> <klto@zhaw.ch>
+Tobias Klauser <tklauser@distanz.ch> <tklauser@nuerscht.ch>
+Tobias Klauser <tklauser@distanz.ch> <tklauser@xenon.tklauser.home>
 Todor Tomov <todor.too@gmail.com> <todor.tomov@linaro.org>
 Tony Luck <tony.luck@intel.com>
 TripleX Chung <xxx.phy@gmail.com> <triplex@zh-kernel.org>

arch/powerpc/include/asm/kasan.h

@@ -2,7 +2,7 @@
 #ifndef __ASM_KASAN_H
 #define __ASM_KASAN_H
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN) && !defined(CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX)
 #define _GLOBAL_KASAN(fn)	_GLOBAL(__##fn)
 #define _GLOBAL_TOC_KASAN(fn)	_GLOBAL_TOC(__##fn)
 #define EXPORT_SYMBOL_KASAN(fn)	EXPORT_SYMBOL(__##fn)

arch/powerpc/include/asm/string.h

@@ -30,11 +30,17 @@ extern int memcmp(const void *,const void *,__kernel_size_t);
 extern void * memchr(const void *,int,__kernel_size_t);
 void memcpy_flushcache(void *dest, const void *src, size_t size);
 
+#ifdef CONFIG_KASAN
+/* __mem variants are used by KASAN to implement instrumented meminstrinsics. */
+#ifdef CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX
+#define __memset memset
+#define __memcpy memcpy
+#define __memmove memmove
+#else /* CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX */
 void *__memset(void *s, int c, __kernel_size_t count);
 void *__memcpy(void *to, const void *from, __kernel_size_t n);
 void *__memmove(void *to, const void *from, __kernel_size_t n);
-
-#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
+#ifndef __SANITIZE_ADDRESS__
 /*
  * For files that are not instrumented (e.g. mm/slub.c) we
  * should use not instrumented version of mem* functions.
@@ -46,8 +52,9 @@ void *__memmove(void *to, const void *from, __kernel_size_t n);
 #ifndef __NO_FORTIFY
 #define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */
 #endif
-
-#endif
+#endif /* !__SANITIZE_ADDRESS__ */
+#endif /* CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX */
+#endif /* CONFIG_KASAN */
 
 #ifdef CONFIG_PPC64
 #ifndef CONFIG_KASAN

arch/powerpc/kernel/prom_init_check.sh

@@ -13,8 +13,13 @@
 # If you really need to reference something from prom_init.o add
 # it to the list below:
 
-grep "^CONFIG_KASAN=y$" ${KCONFIG_CONFIG} >/dev/null
-if [ $? -eq 0 ]
+has_renamed_memintrinsics()
+{
+	grep -q "^CONFIG_KASAN=y$" ${KCONFIG_CONFIG} && \
+		! grep -q "^CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX=y" ${KCONFIG_CONFIG}
+}
+
+if has_renamed_memintrinsics
 then
 	MEM_FUNCS="__memcpy __memset"
 else

fs/nilfs2/ioctl.c

@@ -71,7 +71,7 @@ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs,
 	if (argv->v_index > ~(__u64)0 - argv->v_nmembs)
 		return -EINVAL;
 
-	buf = (void *)__get_free_pages(GFP_NOFS, 0);
+	buf = (void *)get_zeroed_page(GFP_NOFS);
 	if (unlikely(!buf))
 		return -ENOMEM;
 	maxmembs = PAGE_SIZE / argv->v_size;

include/trace/events/mmap.h

@@ -35,7 +35,7 @@ TRACE_EVENT(vm_unmapped_area,
 		__entry->align_offset = info->align_offset;
 	),
 
-	TP_printk("addr=0x%lx err=%ld total_vm=0x%lx flags=0x%lx len=0x%lx lo=0x%lx hi=0x%lx mask=0x%lx ofs=0x%lx\n",
+	TP_printk("addr=0x%lx err=%ld total_vm=0x%lx flags=0x%lx len=0x%lx lo=0x%lx hi=0x%lx mask=0x%lx ofs=0x%lx",
 		IS_ERR_VALUE(__entry->addr) ? 0 : __entry->addr,
 		IS_ERR_VALUE(__entry->addr) ? __entry->addr : 0,
 		__entry->total_vm, __entry->flags, __entry->length,
@@ -110,7 +110,7 @@ TRACE_EVENT(exit_mmap,
 		       __entry->mt		= &mm->mm_mt;
 	),
 
-	TP_printk("mt_mod %p, DESTROY\n",
+	TP_printk("mt_mod %p, DESTROY",
 		  __entry->mt
 	)
 );

kernel/kcsan/Makefile

@@ -16,6 +16,6 @@ obj-y := core.o debugfs.o report.o
 KCSAN_INSTRUMENT_BARRIERS_selftest.o := y
 obj-$(CONFIG_KCSAN_SELFTEST) += selftest.o
 
-CFLAGS_kcsan_test.o := $(CFLAGS_KCSAN) -g -fno-omit-frame-pointer
+CFLAGS_kcsan_test.o := $(CFLAGS_KCSAN) -fno-omit-frame-pointer
 CFLAGS_kcsan_test.o += $(DISABLE_STRUCTLEAK_PLUGIN)
 obj-$(CONFIG_KCSAN_KUNIT_TEST) += kcsan_test.o

lib/dhry_run.c

@@ -31,6 +31,7 @@ MODULE_PARM_DESC(iterations,
 
 static void dhry_benchmark(void)
 {
+	unsigned int cpu = get_cpu();
 	int i, n;
 
 	if (iterations > 0) {
@@ -45,9 +46,10 @@ static void dhry_benchmark(void)
 	}
 
 report:
+	put_cpu();
 	if (n >= 0)
-		pr_info("CPU%u: Dhrystones per Second: %d (%d DMIPS)\n",
-			smp_processor_id(), n, n / DHRY_VAX);
+		pr_info("CPU%u: Dhrystones per Second: %d (%d DMIPS)\n", cpu,
+			n, n / DHRY_VAX);
 	else if (n == -EAGAIN)
 		pr_err("Please increase the number of iterations\n");
 	else

lib/maple_tree.c

@@ -5099,35 +5099,21 @@ static inline bool mas_rewind_node(struct ma_state *mas)
  */
 static inline bool mas_skip_node(struct ma_state *mas)
 {
-	unsigned char slot, slot_count;
-	unsigned long *pivots;
-	enum maple_type mt;
+	if (mas_is_err(mas))
+		return false;
 
-	mt = mte_node_type(mas->node);
-	slot_count = mt_slots[mt] - 1;
 	do {
 		if (mte_is_root(mas->node)) {
-			slot = mas->offset;
-			if (slot > slot_count) {
+			if (mas->offset >= mas_data_end(mas)) {
 				mas_set_err(mas, -EBUSY);
 				return false;
 			}
 		} else {
 			mas_ascend(mas);
-			slot = mas->offset;
-			mt = mte_node_type(mas->node);
-			slot_count = mt_slots[mt] - 1;
 		}
-	} while (slot > slot_count);
-
-	mas->offset = ++slot;
-	pivots = ma_pivots(mas_mn(mas), mt);
-	if (slot > 0)
-		mas->min = pivots[slot - 1] + 1;
-
-	if (slot <= slot_count)
-		mas->max = pivots[slot];
+	} while (mas->offset >= mas_data_end(mas));
 
+	mas->offset++;
 	return true;
 }
 

lib/test_maple_tree.c

@@ -2670,6 +2670,49 @@ static noinline void check_empty_area_window(struct maple_tree *mt)
 	rcu_read_unlock();
 }
 
+static noinline void check_empty_area_fill(struct maple_tree *mt)
+{
+	const unsigned long max = 0x25D78000;
+	unsigned long size;
+	int loop, shift;
+	MA_STATE(mas, mt, 0, 0);
+
+	mt_set_non_kernel(99999);
+	for (shift = 12; shift <= 16; shift++) {
+		loop = 5000;
+		size = 1 << shift;
+		while (loop--) {
+			mas_set(&mas, 0);
+			mas_lock(&mas);
+			MT_BUG_ON(mt, mas_empty_area(&mas, 0, max, size) != 0);
+			MT_BUG_ON(mt, mas.last != mas.index + size - 1);
+			mas_store_gfp(&mas, (void *)size, GFP_KERNEL);
+			mas_unlock(&mas);
+			mas_reset(&mas);
+		}
+	}
+
+	/* No space left. */
+	size = 0x1000;
+	rcu_read_lock();
+	MT_BUG_ON(mt, mas_empty_area(&mas, 0, max, size) != -EBUSY);
+	rcu_read_unlock();
+
+	/* Fill a depth 3 node to the maximum */
+	for (unsigned long i = 629440511; i <= 629440800; i += 6)
+		mtree_store_range(mt, i, i + 5, (void *)i, GFP_KERNEL);
+	/* Make space in the second-last depth 4 node */
+	mtree_erase(mt, 631668735);
+	/* Make space in the last depth 4 node */
+	mtree_erase(mt, 629506047);
+	mas_reset(&mas);
+	/* Search from just after the gap in the second-last depth 4 */
+	rcu_read_lock();
+	MT_BUG_ON(mt, mas_empty_area(&mas, 629506048, 690000000, 0x5000) != 0);
+	rcu_read_unlock();
+	mt_set_non_kernel(0);
+}
+
 static DEFINE_MTREE(tree);
 static int maple_tree_seed(void)
 {
@@ -2926,6 +2969,11 @@ static int maple_tree_seed(void)
 	check_empty_area_window(&tree);
 	mtree_destroy(&tree);
 
+	mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
+	check_empty_area_fill(&tree);
+	mtree_destroy(&tree);
+
+
 #if defined(BENCH)
 skip:
 #endif

mm/kfence/Makefile

@@ -2,5 +2,5 @@
 
 obj-y := core.o report.o
 
-CFLAGS_kfence_test.o := -g -fno-omit-frame-pointer -fno-optimize-sibling-calls
+CFLAGS_kfence_test.o := -fno-omit-frame-pointer -fno-optimize-sibling-calls
 obj-$(CONFIG_KFENCE_KUNIT_TEST) += kfence_test.o

mm/kfence/core.c

@@ -726,10 +726,14 @@ static const struct seq_operations objects_sops = {
 };
 DEFINE_SEQ_ATTRIBUTE(objects);
 
-static int __init kfence_debugfs_init(void)
+static int kfence_debugfs_init(void)
 {
-	struct dentry *kfence_dir = debugfs_create_dir("kfence", NULL);
+	struct dentry *kfence_dir;
 
+	if (!READ_ONCE(kfence_enabled))
+		return 0;
+
+	kfence_dir = debugfs_create_dir("kfence", NULL);
 	debugfs_create_file("stats", 0444, kfence_dir, NULL, &stats_fops);
 	debugfs_create_file("objects", 0400, kfence_dir, NULL, &objects_fops);
 	return 0;
@@ -883,6 +887,8 @@ static int kfence_init_late(void)
 	}
 
 	kfence_init_enable();
+	kfence_debugfs_init();
+
 	return 0;
 }
 

mm/ksm.c

@@ -988,9 +988,15 @@ static int unmerge_and_remove_all_rmap_items(void)
 
 		mm = mm_slot->slot.mm;
 		mmap_read_lock(mm);
+
+		/*
+		 * Exit right away if mm is exiting to avoid lockdep issue in
+		 * the maple tree
+		 */
+		if (ksm_test_exit(mm))
+			goto mm_exiting;
+
 		for_each_vma(vmi, vma) {
-			if (ksm_test_exit(mm))
-				break;
 			if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma)
 				continue;
 			err = unmerge_ksm_pages(vma,
@@ -999,6 +1005,7 @@ static int unmerge_and_remove_all_rmap_items(void)
 				goto error;
 		}
 
+mm_exiting:
 		remove_trailing_rmap_items(&mm_slot->rmap_list);
 		mmap_read_unlock(mm);
 

mm/mmap.c

@@ -2621,12 +2621,7 @@ cannot_expand:
 
 	if (map_deny_write_exec(vma, vma->vm_flags)) {
 		error = -EACCES;
-		if (file)
-			goto close_and_free_vma;
-		else if (vma->vm_file)
-			goto unmap_and_free_vma;
-		else
-			goto free_vma;
+		goto close_and_free_vma;
 	}
 
 	/* Allow architectures to sanity-check the vm_flags */

mm/mprotect.c

@@ -805,7 +805,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 
 		if (map_deny_write_exec(vma, newflags)) {
 			error = -EACCES;
-			goto out;
+			break;
 		}
 
 		/* Allow architectures to sanity-check the new flags */

mm/page_alloc.c

@@ -1398,6 +1398,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
 			unsigned int order, bool check_free, fpi_t fpi_flags)
 {
 	int bad = 0;
+	bool skip_kasan_poison = should_skip_kasan_poison(page, fpi_flags);
 	bool init = want_init_on_free();
 
 	VM_BUG_ON_PAGE(PageTail(page), page);
@@ -1470,7 +1471,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	 * With hardware tag-based KASAN, memory tags must be set before the
 	 * page becomes unavailable via debug_pagealloc or arch_free_page.
 	 */
-	if (!should_skip_kasan_poison(page, fpi_flags)) {
+	if (!skip_kasan_poison) {
 		kasan_poison_pages(page, order, init);
 
 		/* Memory is already initialized if KASAN did it internally. */

mm/vmalloc.c

@@ -2883,6 +2883,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 		unsigned int order, unsigned int nr_pages, struct page **pages)
 {
 	unsigned int nr_allocated = 0;
+	gfp_t alloc_gfp = gfp;
+	bool nofail = false;
 	struct page *page;
 	int i;
 
@@ -2893,6 +2895,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 	 * more permissive.
 	 */
 	if (!order) {
+		/* bulk allocator doesn't support nofail req. officially */
 		gfp_t bulk_gfp = gfp & ~__GFP_NOFAIL;
 
 		while (nr_allocated < nr_pages) {
@@ -2931,20 +2934,35 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			if (nr != nr_pages_request)
 				break;
 		}
+	} else if (gfp & __GFP_NOFAIL) {
+		/*
+		 * Higher order nofail allocations are really expensive and
+		 * potentially dangerous (pre-mature OOM, disruptive reclaim
+		 * and compaction etc.
+		 */
+		alloc_gfp &= ~__GFP_NOFAIL;
+		nofail = true;
 	}
 
 	/* High-order pages or fallback path if "bulk" fails. */
-
 	while (nr_allocated < nr_pages) {
 		if (fatal_signal_pending(current))
 			break;
 
 		if (nid == NUMA_NO_NODE)
-			page = alloc_pages(gfp, order);
+			page = alloc_pages(alloc_gfp, order);
 		else
-			page = alloc_pages_node(nid, gfp, order);
-		if (unlikely(!page))
-			break;
+			page = alloc_pages_node(nid, alloc_gfp, order);
+		if (unlikely(!page)) {
+			if (!nofail)
+				break;
+
+			/* fall back to the zero order allocations */
+			alloc_gfp |= __GFP_NOFAIL;
+			order = 0;
+			continue;
+		}
+
 		/*
 		 * Higher order allocations must be able to be treated as
 		 * indepdenent small pages by callers (as they can with

scripts/checksyscalls.sh

@@ -114,7 +114,6 @@ cat << EOF
 #define __IGNORE_truncate
 #define __IGNORE_stat
 #define __IGNORE_lstat
-#define __IGNORE_fstat
 #define __IGNORE_fcntl
 #define __IGNORE_fadvise64
 #define __IGNORE_newfstatat
@@ -255,6 +254,9 @@ cat << EOF
 /* 64-bit ports never needed these, and new 32-bit ports can use statx */
 #define __IGNORE_fstat64
 #define __IGNORE_fstatat64
+
+/* Newer ports are not required to provide fstat in favor of statx */
+#define __IGNORE_fstat
 EOF
 }
 

tools/testing/selftests/mm/mdwe_test.c

@@ -163,9 +163,8 @@ TEST_F(mdwe, mprotect_WRITE_EXEC)
 
 TEST_F(mdwe, mmap_FIXED)
 {
-	void *p, *p2;
+	void *p;
 
-	p2 = mmap(NULL, self->size, PROT_READ | PROT_EXEC, self->flags, 0, 0);
 	self->p = mmap(NULL, self->size, PROT_READ, self->flags, 0, 0);
 	ASSERT_NE(self->p, MAP_FAILED);