Adding upstream version 6.10.3.upstream/6.10.3

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

56 files changed, 2230 insertions, 812 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index c98e11c733..b0a76dff5c 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -622,7 +622,7 @@ config SIGNATURE
 	  Implementation is done using GnuPG MPI library
 
 config DIMLIB
-	bool
+	tristate
 	help
 	  Dynamic Interrupt Moderation library.
 	  Implements an algorithm for dynamically changing CQ moderation values
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 291185f54e..59b6765d86 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -969,6 +969,37 @@ config DEBUG_STACKOVERFLOW
 
 	  If in doubt, say "N".
 
+config CODE_TAGGING
+	bool
+	select KALLSYMS
+
+config MEM_ALLOC_PROFILING
+	bool "Enable memory allocation profiling"
+	default n
+	depends on PROC_FS
+	depends on !DEBUG_FORCE_WEAK_PER_CPU
+	select CODE_TAGGING
+	select PAGE_EXTENSION
+	select SLAB_OBJ_EXT
+	help
+	  Track allocation source code and record total allocation size
+	  initiated at that code location. The mechanism can be used to track
+	  memory leaks with a low performance and memory impact.
+
+config MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT
+	bool "Enable memory allocation profiling by default"
+	default y
+	depends on MEM_ALLOC_PROFILING
+
+config MEM_ALLOC_PROFILING_DEBUG
+	bool "Memory allocation profiler debugging"
+	default n
+	depends on MEM_ALLOC_PROFILING
+	select MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT
+	help
+	  Adds warnings with helpful error messages for memory allocation
+	  profiling.
+
 source "lib/Kconfig.kasan"
 source "lib/Kconfig.kfence"
 source "lib/Kconfig.kmsan"
@@ -1030,6 +1061,20 @@ config SOFTLOCKUP_DETECTOR
 	  chance to run.  The current stack trace is displayed upon
 	  detection and the system will stay locked up.
 
+config SOFTLOCKUP_DETECTOR_INTR_STORM
+	bool "Detect Interrupt Storm in Soft Lockups"
+	depends on SOFTLOCKUP_DETECTOR && IRQ_TIME_ACCOUNTING
+	select GENERIC_IRQ_STAT_SNAPSHOT
+	default y if NR_CPUS <= 128
+	help
+	  Say Y here to enable the kernel to detect interrupt storm
+	  during "soft lockups".
+
+	  "soft lockups" can be caused by a variety of reasons. If one is
+	  caused by an interrupt storm, then the storming interrupts will not
+	  be on the callstack. To detect this case, it is necessary to report
+	  the CPU stats and the interrupt counts during the "soft lockups".
+
 config BOOTPARAM_SOFTLOCKUP_PANIC
 	bool "Panic (Reboot) On Soft Lockups"
 	depends on SOFTLOCKUP_DETECTOR
@@ -1251,7 +1296,7 @@ config SCHED_INFO
 
 config SCHEDSTATS
 	bool "Collect scheduler statistics"
-	depends on DEBUG_KERNEL && PROC_FS
+	depends on PROC_FS
 	select SCHED_INFO
 	help
 	  If you say Y here, additional code will be inserted into the
@@ -2437,7 +2482,6 @@ config TEST_LKM
 
 config TEST_BITOPS
 	tristate "Test module for compilation of bitops operations"
-	depends on m
 	help
 	  This builds the "test_bitops" module that is much like the
 	  TEST_LKM module except that it does a basic exercise of the
@@ -2759,16 +2803,6 @@ config HW_BREAKPOINT_KUNIT_TEST
 
 	  If unsure, say N.
 
-config STRCAT_KUNIT_TEST
-	tristate "Test strcat() family of functions at runtime" if !KUNIT_ALL_TESTS
-	depends on KUNIT
-	default KUNIT_ALL_TESTS
-
-config STRSCPY_KUNIT_TEST
-	tristate "Test strscpy*() family of functions at runtime" if !KUNIT_ALL_TESTS
-	depends on KUNIT
-	default KUNIT_ALL_TESTS
-
 config SIPHASH_KUNIT_TEST
 	tristate "Perform selftest on siphash functions" if !KUNIT_ALL_TESTS
 	depends on KUNIT
@@ -2891,7 +2925,7 @@ config TEST_FREE_PAGES
 
 config TEST_FPU
 	tristate "Test floating point operations in kernel space"
-	depends on X86 && !KCOV_INSTRUMENT_ALL
+	depends on ARCH_HAS_KERNEL_FPU_SUPPORT && !KCOV_INSTRUMENT_ALL
 	help
 	  Enable this option to add /sys/kernel/debug/selftest_helpers/test_fpu
 	  which will trigger a sequence of floating point operations. This is used
diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb
index b5c0e65767..537e1b3f57 100644
--- a/lib/Kconfig.kgdb
+++ b/lib/Kconfig.kgdb
@@ -122,6 +122,7 @@ config KDB_DEFAULT_ENABLE
 config KDB_KEYBOARD
 	bool "KGDB_KDB: keyboard as input device"
 	depends on VT && KGDB_KDB && !PARISC
+	depends on HAS_IOPORT
 	default n
 	help
 	  KDB can use a PS/2 type keyboard for an input device
diff --git a/lib/Makefile b/lib/Makefile
index ffc6b2341b..30337431d1 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -110,30 +110,10 @@ CFLAGS_test_fprobe.o += $(CC_FLAGS_FTRACE)
 obj-$(CONFIG_FPROBE_SANITY_TEST) += test_fprobe.o
 obj-$(CONFIG_TEST_OBJPOOL) += test_objpool.o
 
-#
-# CFLAGS for compiling floating point code inside the kernel. x86/Makefile turns
-# off the generation of FPU/SSE* instructions for kernel proper but FPU_FLAGS
-# get appended last to CFLAGS and thus override those previous compiler options.
-#
-FPU_CFLAGS := -msse -msse2
-ifdef CONFIG_CC_IS_GCC
-# Stack alignment mismatch, proceed with caution.
-# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
-# (8B stack alignment).
-# See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383
-#
-# The "-msse" in the first argument is there so that the
-# -mpreferred-stack-boundary=3 build error:
-#
-#  -mpreferred-stack-boundary=3 is not between 4 and 12
-#
-# can be triggered. Otherwise gcc doesn't complain.
-FPU_CFLAGS += -mhard-float
-FPU_CFLAGS += $(call cc-option,-msse -mpreferred-stack-boundary=3,-mpreferred-stack-boundary=4)
-endif
-
 obj-$(CONFIG_TEST_FPU) += test_fpu.o
-CFLAGS_test_fpu.o += $(FPU_CFLAGS)
+test_fpu-y := test_fpu_glue.o test_fpu_impl.o
+CFLAGS_test_fpu_impl.o += $(CC_FLAGS_FPU)
+CFLAGS_REMOVE_test_fpu_impl.o += $(CC_FLAGS_NO_FPU)
 
 # Some KUnit files (hooks.o) need to be built-in even when KUnit is a module,
 # so we can't just use obj-$(CONFIG_KUNIT).
@@ -233,9 +213,13 @@ obj-$(CONFIG_OF_RECONFIG_NOTIFIER_ERROR_INJECT) += \
 	of-reconfig-notifier-error-inject.o
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 
+obj-$(CONFIG_CODE_TAGGING) += codetag.o
+obj-$(CONFIG_MEM_ALLOC_PROFILING) += alloc_tag.o
+
 lib-$(CONFIG_GENERIC_BUG) += bug.o
 
 obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
+obj-$(CONFIG_ARCH_NEED_CMPXCHG_1_EMU) += cmpxchg-emu.o
 
 obj-$(CONFIG_DYNAMIC_DEBUG_CORE) += dynamic_debug.o
 #ensure exported functions have prototypes
@@ -352,7 +336,7 @@ $(obj)/oid_registry_data.c: $(srctree)/include/linux/oid_registry.h \
 	$(call cmd,build_OID_registry)
 
 quiet_cmd_build_OID_registry = GEN     $@
-      cmd_build_OID_registry = perl $(srctree)/$(src)/build_OID_registry $< $@
+      cmd_build_OID_registry = perl $(src)/build_OID_registry $< $@
 
 clean-files	+= oid_registry_data.c
 
@@ -403,8 +387,6 @@ CFLAGS_fortify_kunit.o += $(call cc-disable-warning, stringop-overread)
 CFLAGS_fortify_kunit.o += $(call cc-disable-warning, stringop-truncation)
 CFLAGS_fortify_kunit.o += $(DISABLE_STRUCTLEAK_PLUGIN)
 obj-$(CONFIG_FORTIFY_KUNIT_TEST) += fortify_kunit.o
-obj-$(CONFIG_STRCAT_KUNIT_TEST) += strcat_kunit.o
-obj-$(CONFIG_STRSCPY_KUNIT_TEST) += strscpy_kunit.o
 obj-$(CONFIG_SIPHASH_KUNIT_TEST) += siphash_kunit.o
 
 obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o
@@ -412,8 +394,8 @@ obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o
 obj-$(CONFIG_FIRMWARE_TABLE) += fw_table.o
 
 # FORTIFY_SOURCE compile-time behavior tests
-TEST_FORTIFY_SRCS = $(wildcard $(srctree)/$(src)/test_fortify/*-*.c)
-TEST_FORTIFY_LOGS = $(patsubst $(srctree)/$(src)/%.c, %.log, $(TEST_FORTIFY_SRCS))
+TEST_FORTIFY_SRCS = $(wildcard $(src)/test_fortify/*-*.c)
+TEST_FORTIFY_LOGS = $(patsubst $(src)/%.c, %.log, $(TEST_FORTIFY_SRCS))
 TEST_FORTIFY_LOG = test_fortify.log
 
 quiet_cmd_test_fortify = TEST    $@
@@ -444,3 +426,7 @@ $(obj)/$(TEST_FORTIFY_LOG): $(addprefix $(obj)/, $(TEST_FORTIFY_LOGS)) FORCE
 ifeq ($(CONFIG_FORTIFY_SOURCE),y)
 $(obj)/string.o: $(obj)/$(TEST_FORTIFY_LOG)
 endif
+
+# Some architectures define __NO_FORTIFY if __SANITIZE_ADDRESS__ is undefined.
+# Pass CFLAGS_KASAN to avoid warnings.
+$(foreach x, $(patsubst %.log,%.o,$(TEST_FORTIFY_LOGS)), $(eval KASAN_SANITIZE_$(x) := y))
diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c
new file mode 100644
index 0000000000..c347b8b72d
--- /dev/null
+++ b/lib/alloc_tag.c
@@ -0,0 +1,273 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/alloc_tag.h>
+#include <linux/fs.h>
+#include <linux/gfp.h>
+#include <linux/module.h>
+#include <linux/page_ext.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_buf.h>
+#include <linux/seq_file.h>
+
+static struct codetag_type *alloc_tag_cttype;
+
+DEFINE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag);
+EXPORT_SYMBOL(_shared_alloc_tag);
+
+DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT,
+			mem_alloc_profiling_key);
+
+struct allocinfo_private {
+	struct codetag_iterator iter;
+	bool print_header;
+};
+
+static void *allocinfo_start(struct seq_file *m, loff_t *pos)
+{
+	struct allocinfo_private *priv;
+	struct codetag *ct;
+	loff_t node = *pos;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	m->private = priv;
+	if (!priv)
+		return NULL;
+
+	priv->print_header = (node == 0);
+	codetag_lock_module_list(alloc_tag_cttype, true);
+	priv->iter = codetag_get_ct_iter(alloc_tag_cttype);
+	while ((ct = codetag_next_ct(&priv->iter)) != NULL && node)
+		node--;
+
+	return ct ? priv : NULL;
+}
+
+static void *allocinfo_next(struct seq_file *m, void *arg, loff_t *pos)
+{
+	struct allocinfo_private *priv = (struct allocinfo_private *)arg;
+	struct codetag *ct = codetag_next_ct(&priv->iter);
+
+	(*pos)++;
+	if (!ct)
+		return NULL;
+
+	return priv;
+}
+
+static void allocinfo_stop(struct seq_file *m, void *arg)
+{
+	struct allocinfo_private *priv = (struct allocinfo_private *)m->private;
+
+	if (priv) {
+		codetag_lock_module_list(alloc_tag_cttype, false);
+		kfree(priv);
+	}
+}
+
+static void print_allocinfo_header(struct seq_buf *buf)
+{
+	/* Output format version, so we can change it. */
+	seq_buf_printf(buf, "allocinfo - version: 1.0\n");
+	seq_buf_printf(buf, "#     <size>  <calls> <tag info>\n");
+}
+
+static void alloc_tag_to_text(struct seq_buf *out, struct codetag *ct)
+{
+	struct alloc_tag *tag = ct_to_alloc_tag(ct);
+	struct alloc_tag_counters counter = alloc_tag_read(tag);
+	s64 bytes = counter.bytes;
+
+	seq_buf_printf(out, "%12lli %8llu ", bytes, counter.calls);
+	codetag_to_text(out, ct);
+	seq_buf_putc(out, ' ');
+	seq_buf_putc(out, '\n');
+}
+
+static int allocinfo_show(struct seq_file *m, void *arg)
+{
+	struct allocinfo_private *priv = (struct allocinfo_private *)arg;
+	char *bufp;
+	size_t n = seq_get_buf(m, &bufp);
+	struct seq_buf buf;
+
+	seq_buf_init(&buf, bufp, n);
+	if (priv->print_header) {
+		print_allocinfo_header(&buf);
+		priv->print_header = false;
+	}
+	alloc_tag_to_text(&buf, priv->iter.ct);
+	seq_commit(m, seq_buf_used(&buf));
+	return 0;
+}
+
+static const struct seq_operations allocinfo_seq_op = {
+	.start	= allocinfo_start,
+	.next	= allocinfo_next,
+	.stop	= allocinfo_stop,
+	.show	= allocinfo_show,
+};
+
+size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sleep)
+{
+	struct codetag_iterator iter;
+	struct codetag *ct;
+	struct codetag_bytes n;
+	unsigned int i, nr = 0;
+
+	if (can_sleep)
+		codetag_lock_module_list(alloc_tag_cttype, true);
+	else if (!codetag_trylock_module_list(alloc_tag_cttype))
+		return 0;
+
+	iter = codetag_get_ct_iter(alloc_tag_cttype);
+	while ((ct = codetag_next_ct(&iter))) {
+		struct alloc_tag_counters counter = alloc_tag_read(ct_to_alloc_tag(ct));
+
+		n.ct	= ct;
+		n.bytes = counter.bytes;
+
+		for (i = 0; i < nr; i++)
+			if (n.bytes > tags[i].bytes)
+				break;
+
+		if (i < count) {
+			nr -= nr == count;
+			memmove(&tags[i + 1],
+				&tags[i],
+				sizeof(tags[0]) * (nr - i));
+			nr++;
+			tags[i] = n;
+		}
+	}
+
+	codetag_lock_module_list(alloc_tag_cttype, false);
+
+	return nr;
+}
+
+static void __init procfs_init(void)
+{
+	proc_create_seq("allocinfo", 0400, NULL, &allocinfo_seq_op);
+}
+
+static bool alloc_tag_module_unload(struct codetag_type *cttype,
+				    struct codetag_module *cmod)
+{
+	struct codetag_iterator iter = codetag_get_ct_iter(cttype);
+	struct alloc_tag_counters counter;
+	bool module_unused = true;
+	struct alloc_tag *tag;
+	struct codetag *ct;
+
+	for (ct = codetag_next_ct(&iter); ct; ct = codetag_next_ct(&iter)) {
+		if (iter.cmod != cmod)
+			continue;
+
+		tag = ct_to_alloc_tag(ct);
+		counter = alloc_tag_read(tag);
+
+		if (WARN(counter.bytes,
+			 "%s:%u module %s func:%s has %llu allocated at module unload",
+			 ct->filename, ct->lineno, ct->modname, ct->function, counter.bytes))
+			module_unused = false;
+	}
+
+	return module_unused;
+}
+
+#ifdef CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT
+static bool mem_profiling_support __meminitdata = true;
+#else
+static bool mem_profiling_support __meminitdata;
+#endif
+
+static int __init setup_early_mem_profiling(char *str)
+{
+	bool enable;
+
+	if (!str || !str[0])
+		return -EINVAL;
+
+	if (!strncmp(str, "never", 5)) {
+		enable = false;
+		mem_profiling_support = false;
+	} else {
+		int res;
+
+		res = kstrtobool(str, &enable);
+		if (res)
+			return res;
+
+		mem_profiling_support = true;
+	}
+
+	if (enable != static_key_enabled(&mem_alloc_profiling_key)) {
+		if (enable)
+			static_branch_enable(&mem_alloc_profiling_key);
+		else
+			static_branch_disable(&mem_alloc_profiling_key);
+	}
+
+	return 0;
+}
+early_param("sysctl.vm.mem_profiling", setup_early_mem_profiling);
+
+static __init bool need_page_alloc_tagging(void)
+{
+	return mem_profiling_support;
+}
+
+static __init void init_page_alloc_tagging(void)
+{
+}
+
+struct page_ext_operations page_alloc_tagging_ops = {
+	.size = sizeof(union codetag_ref),
+	.need = need_page_alloc_tagging,
+	.init = init_page_alloc_tagging,
+};
+EXPORT_SYMBOL(page_alloc_tagging_ops);
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table memory_allocation_profiling_sysctls[] = {
+	{
+		.procname	= "mem_profiling",
+		.data		= &mem_alloc_profiling_key,
+#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG
+		.mode		= 0444,
+#else
+		.mode		= 0644,
+#endif
+		.proc_handler	= proc_do_static_key,
+	},
+	{ }
+};
+
+static void __init sysctl_init(void)
+{
+	if (!mem_profiling_support)
+		memory_allocation_profiling_sysctls[0].mode = 0444;
+
+	register_sysctl_init("vm", memory_allocation_profiling_sysctls);
+}
+#else /* CONFIG_SYSCTL */
+static inline void sysctl_init(void) {}
+#endif /* CONFIG_SYSCTL */
+
+static int __init alloc_tag_init(void)
+{
+	const struct codetag_type_desc desc = {
+		.section	= "alloc_tags",
+		.tag_size	= sizeof(struct alloc_tag),
+		.module_unload	= alloc_tag_module_unload,
+	};
+
+	alloc_tag_cttype = codetag_register_type(&desc);
+	if (IS_ERR(alloc_tag_cttype))
+		return PTR_ERR(alloc_tag_cttype);
+
+	sysctl_init();
+	procfs_init();
+
+	return 0;
+}
+module_init(alloc_tag_init);
diff --git a/lib/build_OID_registry b/lib/build_OID_registry
index d7fc32ea8a..8267e8d713 100755
--- a/lib/build_OID_registry
+++ b/lib/build_OID_registry
@@ -8,6 +8,7 @@
 #
 
 use strict;
+use Cwd qw(abs_path);
 
 my @names = ();
 my @oids = ();
@@ -17,6 +18,8 @@ if ($#ARGV != 1) {
     exit(2);
 }
 
+my $abs_srctree = abs_path($ENV{'srctree'});
+
 #
 # Open the file to read from
 #
@@ -35,7 +38,9 @@ close IN_FILE || die;
 #
 open C_FILE, ">$ARGV[1]" or die;
 print C_FILE "/*\n";
-print C_FILE " * Automatically generated by ", $0, ".  Do not edit\n";
+my $scriptname = $0;
+$scriptname =~ s#^\Q$abs_srctree/\E##;
+print C_FILE " * Automatically generated by ", $scriptname, ".  Do not edit\n";
 print C_FILE " */\n";
 
 #
diff --git a/lib/buildid.c b/lib/buildid.c
index 898301b49e..7954dd92e3 100644
--- a/lib/buildid.c
+++ b/lib/buildid.c
@@ -182,8 +182,8 @@ unsigned char vmlinux_build_id[BUILD_ID_SIZE_MAX] __ro_after_init;
  */
 void __init init_vmlinux_build_id(void)
 {
-	extern const void __start_notes __weak;
-	extern const void __stop_notes __weak;
+	extern const void __start_notes;
+	extern const void __stop_notes;
 	unsigned int size = &__stop_notes - &__start_notes;
 
 	build_id_parse_buf(&__start_notes, vmlinux_build_id, size);
diff --git a/lib/closure.c b/lib/closure.c
index 99380d9b4a..116afae2ee 100644
--- a/lib/closure.c
+++ b/lib/closure.c
@@ -13,7 +13,7 @@
 #include <linux/seq_file.h>
 #include <linux/sched/debug.h>
 
-static inline void closure_put_after_sub(struct closure *cl, int flags)
+static inline void closure_put_after_sub_checks(int flags)
 {
 	int r = flags & CLOSURE_REMAINING_MASK;
 
@@ -22,12 +22,17 @@ static inline void closure_put_after_sub(struct closure *cl, int flags)
 		 flags & CLOSURE_GUARD_MASK, (unsigned) __fls(r)))
 		r &= ~CLOSURE_GUARD_MASK;
 
-	if (!r) {
-		smp_acquire__after_ctrl_dep();
+	WARN(!r && (flags & ~CLOSURE_DESTRUCTOR),
+	     "closure ref hit 0 with incorrect flags set: %x (%u)",
+	     flags & ~CLOSURE_DESTRUCTOR, (unsigned) __fls(flags));
+}
+
+static inline void closure_put_after_sub(struct closure *cl, int flags)
+{
+	closure_put_after_sub_checks(flags);
 
-		WARN(flags & ~CLOSURE_DESTRUCTOR,
-		     "closure ref hit 0 with incorrect flags set: %x (%u)",
-		     flags & ~CLOSURE_DESTRUCTOR, (unsigned) __fls(flags));
+	if (!(flags & CLOSURE_REMAINING_MASK)) {
+		smp_acquire__after_ctrl_dep();
 
 		cl->closure_get_happened = false;
 
@@ -145,6 +150,78 @@ void __sched __closure_sync(struct closure *cl)
 }
 EXPORT_SYMBOL(__closure_sync);
 
+/*
+ * closure_return_sync - finish running a closure, synchronously (i.e. waiting
+ * for outstanding get()s to finish) and returning once closure refcount is 0.
+ *
+ * Unlike closure_sync() this doesn't reinit the ref to 1; subsequent
+ * closure_get_not_zero() calls waill fail.
+ */
+void __sched closure_return_sync(struct closure *cl)
+{
+	struct closure_syncer s = { .task = current };
+
+	cl->s = &s;
+	set_closure_fn(cl, closure_sync_fn, NULL);
+
+	unsigned flags = atomic_sub_return_release(1 + CLOSURE_RUNNING - CLOSURE_DESTRUCTOR,
+						   &cl->remaining);
+
+	closure_put_after_sub_checks(flags);
+
+	if (unlikely(flags & CLOSURE_REMAINING_MASK)) {
+		while (1) {
+			set_current_state(TASK_UNINTERRUPTIBLE);
+			if (s.done)
+				break;
+			schedule();
+		}
+
+		__set_current_state(TASK_RUNNING);
+	}
+
+	if (cl->parent)
+		closure_put(cl->parent);
+}
+EXPORT_SYMBOL(closure_return_sync);
+
+int __sched __closure_sync_timeout(struct closure *cl, unsigned long timeout)
+{
+	struct closure_syncer s = { .task = current };
+	int ret = 0;
+
+	cl->s = &s;
+	continue_at(cl, closure_sync_fn, NULL);
+
+	while (1) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (s.done)
+			break;
+		if (!timeout) {
+			/*
+			 * Carefully undo the continue_at() - but only if it
+			 * hasn't completed, i.e. the final closure_put() hasn't
+			 * happened yet:
+			 */
+			unsigned old, new, v = atomic_read(&cl->remaining);
+			do {
+				old = v;
+				if (!old || (old & CLOSURE_RUNNING))
+					goto success;
+
+				new = old + CLOSURE_REMAINING_INITIALIZER;
+			} while ((v = atomic_cmpxchg(&cl->remaining, old, new)) != old);
+			ret = -ETIME;
+		}
+
+		timeout = schedule_timeout(timeout);
+	}
+success:
+	__set_current_state(TASK_RUNNING);
+	return ret;
+}
+EXPORT_SYMBOL(__closure_sync_timeout);
+
 #ifdef CONFIG_DEBUG_CLOSURES
 
 static LIST_HEAD(closure_list);
@@ -167,6 +244,9 @@ void closure_debug_destroy(struct closure *cl)
 {
 	unsigned long flags;
 
+	if (cl->magic == CLOSURE_MAGIC_STACK)
+		return;
+
 	BUG_ON(cl->magic != CLOSURE_MAGIC_ALIVE);
 	cl->magic = CLOSURE_MAGIC_DEAD;
 
diff --git a/lib/cmpxchg-emu.c b/lib/cmpxchg-emu.c
new file mode 100644
index 0000000000..27f6f97cb6
--- /dev/null
+++ b/lib/cmpxchg-emu.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Emulated 1-byte cmpxchg operation for architectures lacking direct
+ * support for this size.  This is implemented in terms of 4-byte cmpxchg
+ * operations.
+ *
+ * Copyright (C) 2024 Paul E. McKenney.
+ */
+
+#include <linux/types.h>
+#include <linux/export.h>
+#include <linux/instrumented.h>
+#include <linux/atomic.h>
+#include <linux/panic.h>
+#include <linux/bug.h>
+#include <asm-generic/rwonce.h>
+#include <linux/cmpxchg-emu.h>
+
+union u8_32 {
+	u8 b[4];
+	u32 w;
+};
+
+/* Emulate one-byte cmpxchg() in terms of 4-byte cmpxchg. */
+uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new)
+{
+	u32 *p32 = (u32 *)(((uintptr_t)p) & ~0x3);
+	int i = ((uintptr_t)p) & 0x3;
+	union u8_32 old32;
+	union u8_32 new32;
+	u32 ret;
+
+	ret = READ_ONCE(*p32);
+	do {
+		old32.w = ret;
+		if (old32.b[i] != old)
+			return old32.b[i];
+		new32.w = old32.w;
+		new32.b[i] = new;
+		instrument_atomic_read_write(p, 1);
+		ret = data_race(cmpxchg(p32, old32.w, new32.w)); // Overridden above.
+	} while (ret != old32.w);
+	return old;
+}
+EXPORT_SYMBOL_GPL(cmpxchg_emu_u8);
diff --git a/lib/codetag.c b/lib/codetag.c
new file mode 100644
index 0000000000..5ace625f23
--- /dev/null
+++ b/lib/codetag.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/codetag.h>
+#include <linux/idr.h>
+#include <linux/kallsyms.h>
+#include <linux/module.h>
+#include <linux/seq_buf.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+struct codetag_type {
+	struct list_head link;
+	unsigned int count;
+	struct idr mod_idr;
+	struct rw_semaphore mod_lock; /* protects mod_idr */
+	struct codetag_type_desc desc;
+};
+
+struct codetag_range {
+	struct codetag *start;
+	struct codetag *stop;
+};
+
+struct codetag_module {
+	struct module *mod;
+	struct codetag_range range;
+};
+
+static DEFINE_MUTEX(codetag_lock);
+static LIST_HEAD(codetag_types);
+
+void codetag_lock_module_list(struct codetag_type *cttype, bool lock)
+{
+	if (lock)
+		down_read(&cttype->mod_lock);
+	else
+		up_read(&cttype->mod_lock);
+}
+
+bool codetag_trylock_module_list(struct codetag_type *cttype)
+{
+	return down_read_trylock(&cttype->mod_lock) != 0;
+}
+
+struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype)
+{
+	struct codetag_iterator iter = {
+		.cttype = cttype,
+		.cmod = NULL,
+		.mod_id = 0,
+		.ct = NULL,
+	};
+
+	return iter;
+}
+
+static inline struct codetag *get_first_module_ct(struct codetag_module *cmod)
+{
+	return cmod->range.start < cmod->range.stop ? cmod->range.start : NULL;
+}
+
+static inline
+struct codetag *get_next_module_ct(struct codetag_iterator *iter)
+{
+	struct codetag *res = (struct codetag *)
+			((char *)iter->ct + iter->cttype->desc.tag_size);
+
+	return res < iter->cmod->range.stop ? res : NULL;
+}
+
+struct codetag *codetag_next_ct(struct codetag_iterator *iter)
+{
+	struct codetag_type *cttype = iter->cttype;
+	struct codetag_module *cmod;
+	struct codetag *ct;
+
+	lockdep_assert_held(&cttype->mod_lock);
+
+	if (unlikely(idr_is_empty(&cttype->mod_idr)))
+		return NULL;
+
+	ct = NULL;
+	while (true) {
+		cmod = idr_find(&cttype->mod_idr, iter->mod_id);
+
+		/* If module was removed move to the next one */
+		if (!cmod)
+			cmod = idr_get_next_ul(&cttype->mod_idr,
+					       &iter->mod_id);
+
+		/* Exit if no more modules */
+		if (!cmod)
+			break;
+
+		if (cmod != iter->cmod) {
+			iter->cmod = cmod;
+			ct = get_first_module_ct(cmod);
+		} else
+			ct = get_next_module_ct(iter);
+
+		if (ct)
+			break;
+
+		iter->mod_id++;
+	}
+
+	iter->ct = ct;
+	return ct;
+}
+
+void codetag_to_text(struct seq_buf *out, struct codetag *ct)
+{
+	if (ct->modname)
+		seq_buf_printf(out, "%s:%u [%s] func:%s",
+			       ct->filename, ct->lineno,
+			       ct->modname, ct->function);
+	else
+		seq_buf_printf(out, "%s:%u func:%s",
+			       ct->filename, ct->lineno, ct->function);
+}
+
+static inline size_t range_size(const struct codetag_type *cttype,
+				const struct codetag_range *range)
+{
+	return ((char *)range->stop - (char *)range->start) /
+			cttype->desc.tag_size;
+}
+
+#ifdef CONFIG_MODULES
+static void *get_symbol(struct module *mod, const char *prefix, const char *name)
+{
+	DECLARE_SEQ_BUF(sb, KSYM_NAME_LEN);
+	const char *buf;
+	void *ret;
+
+	seq_buf_printf(&sb, "%s%s", prefix, name);
+	if (seq_buf_has_overflowed(&sb))
+		return NULL;
+
+	buf = seq_buf_str(&sb);
+	preempt_disable();
+	ret = mod ?
+		(void *)find_kallsyms_symbol_value(mod, buf) :
+		(void *)kallsyms_lookup_name(buf);
+	preempt_enable();
+
+	return ret;
+}
+
+static struct codetag_range get_section_range(struct module *mod,
+					      const char *section)
+{
+	return (struct codetag_range) {
+		get_symbol(mod, "__start_", section),
+		get_symbol(mod, "__stop_", section),
+	};
+}
+
+static int codetag_module_init(struct codetag_type *cttype, struct module *mod)
+{
+	struct codetag_range range;
+	struct codetag_module *cmod;
+	int err;
+
+	range = get_section_range(mod, cttype->desc.section);
+	if (!range.start || !range.stop) {
+		pr_warn("Failed to load code tags of type %s from the module %s\n",
+			cttype->desc.section,
+			mod ? mod->name : "(built-in)");
+		return -EINVAL;
+	}
+
+	/* Ignore empty ranges */
+	if (range.start == range.stop)
+		return 0;
+
+	BUG_ON(range.start > range.stop);
+
+	cmod = kmalloc(sizeof(*cmod), GFP_KERNEL);
+	if (unlikely(!cmod))
+		return -ENOMEM;
+
+	cmod->mod = mod;
+	cmod->range = range;
+
+	down_write(&cttype->mod_lock);
+	err = idr_alloc(&cttype->mod_idr, cmod, 0, 0, GFP_KERNEL);
+	if (err >= 0) {
+		cttype->count += range_size(cttype, &range);
+		if (cttype->desc.module_load)
+			cttype->desc.module_load(cttype, cmod);
+	}
+	up_write(&cttype->mod_lock);
+
+	if (err < 0) {
+		kfree(cmod);
+		return err;
+	}
+
+	return 0;
+}
+
+void codetag_load_module(struct module *mod)
+{
+	struct codetag_type *cttype;
+
+	if (!mod)
+		return;
+
+	mutex_lock(&codetag_lock);
+	list_for_each_entry(cttype, &codetag_types, link)
+		codetag_module_init(cttype, mod);
+	mutex_unlock(&codetag_lock);
+}
+
+bool codetag_unload_module(struct module *mod)
+{
+	struct codetag_type *cttype;
+	bool unload_ok = true;
+
+	if (!mod)
+		return true;
+
+	mutex_lock(&codetag_lock);
+	list_for_each_entry(cttype, &codetag_types, link) {
+		struct codetag_module *found = NULL;
+		struct codetag_module *cmod;
+		unsigned long mod_id, tmp;
+
+		down_write(&cttype->mod_lock);
+		idr_for_each_entry_ul(&cttype->mod_idr, cmod, tmp, mod_id) {
+			if (cmod->mod && cmod->mod == mod) {
+				found = cmod;
+				break;
+			}
+		}
+		if (found) {
+			if (cttype->desc.module_unload)
+				if (!cttype->desc.module_unload(cttype, cmod))
+					unload_ok = false;
+
+			cttype->count -= range_size(cttype, &cmod->range);
+			idr_remove(&cttype->mod_idr, mod_id);
+			kfree(cmod);
+		}
+		up_write(&cttype->mod_lock);
+	}
+	mutex_unlock(&codetag_lock);
+
+	return unload_ok;
+}
+
+#else /* CONFIG_MODULES */
+static int codetag_module_init(struct codetag_type *cttype, struct module *mod) { return 0; }
+#endif /* CONFIG_MODULES */
+
+struct codetag_type *
+codetag_register_type(const struct codetag_type_desc *desc)
+{
+	struct codetag_type *cttype;
+	int err;
+
+	BUG_ON(desc->tag_size <= 0);
+
+	cttype = kzalloc(sizeof(*cttype), GFP_KERNEL);
+	if (unlikely(!cttype))
+		return ERR_PTR(-ENOMEM);
+
+	cttype->desc = *desc;
+	idr_init(&cttype->mod_idr);
+	init_rwsem(&cttype->mod_lock);
+
+	err = codetag_module_init(cttype, NULL);
+	if (unlikely(err)) {
+		kfree(cttype);
+		return ERR_PTR(err);
+	}
+
+	mutex_lock(&codetag_lock);
+	list_add_tail(&cttype->link, &codetag_types);
+	mutex_unlock(&codetag_lock);
+
+	return cttype;
+}
diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig
index 45436bfc6d..b01253cac7 100644
--- a/lib/crypto/Kconfig
+++ b/lib/crypto/Kconfig
@@ -8,6 +8,11 @@ config CRYPTO_LIB_UTILS
 config CRYPTO_LIB_AES
 	tristate
 
+config CRYPTO_LIB_AESCFB
+	tristate
+	select CRYPTO_LIB_AES
+	select CRYPTO_LIB_UTILS
+
 config CRYPTO_LIB_AESGCM
 	tristate
 	select CRYPTO_LIB_AES
diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index 8d1446c2be..969baab8c8 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -10,6 +10,9 @@ obj-$(CONFIG_CRYPTO_LIB_CHACHA_GENERIC)		+= libchacha.o
 obj-$(CONFIG_CRYPTO_LIB_AES)			+= libaes.o
 libaes-y					:= aes.o
 
+obj-$(CONFIG_CRYPTO_LIB_AESCFB)			+= libaescfb.o
+libaescfb-y					:= aescfb.o
+
 obj-$(CONFIG_CRYPTO_LIB_AESGCM)			+= libaesgcm.o
 libaesgcm-y					:= aesgcm.o
 
diff --git a/lib/crypto/aescfb.c b/lib/crypto/aescfb.c
new file mode 100644
index 0000000000..749dc1258a
--- /dev/null
+++ b/lib/crypto/aescfb.c
@@ -0,0 +1,257 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Minimal library implementation of AES in CFB mode
+ *
+ * Copyright 2023 Google LLC
+ */
+
+#include <linux/module.h>
+
+#include <crypto/algapi.h>
+#include <crypto/aes.h>
+
+#include <asm/irqflags.h>
+
+static void aescfb_encrypt_block(const struct crypto_aes_ctx *ctx, void *dst,
+				 const void *src)
+{
+	unsigned long flags;
+
+	/*
+	 * In AES-CFB, the AES encryption operates on known 'plaintext' (the IV
+	 * and ciphertext), making it susceptible to timing attacks on the
+	 * encryption key. The AES library already mitigates this risk to some
+	 * extent by pulling the entire S-box into the caches before doing any
+	 * substitutions, but this strategy is more effective when running with
+	 * interrupts disabled.
+	 */
+	local_irq_save(flags);
+	aes_encrypt(ctx, dst, src);
+	local_irq_restore(flags);
+}
+
+/**
+ * aescfb_encrypt - Perform AES-CFB encryption on a block of data
+ *
+ * @ctx:	The AES-CFB key schedule
+ * @dst:	Pointer to the ciphertext output buffer
+ * @src:	Pointer the plaintext (may equal @dst for encryption in place)
+ * @len:	The size in bytes of the plaintext and ciphertext.
+ * @iv:		The initialization vector (IV) to use for this block of data
+ */
+void aescfb_encrypt(const struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src,
+		    int len, const u8 iv[AES_BLOCK_SIZE])
+{
+	u8 ks[AES_BLOCK_SIZE];
+	const u8 *v = iv;
+
+	while (len > 0) {
+		aescfb_encrypt_block(ctx, ks, v);
+		crypto_xor_cpy(dst, src, ks, min(len, AES_BLOCK_SIZE));
+		v = dst;
+
+		dst += AES_BLOCK_SIZE;
+		src += AES_BLOCK_SIZE;
+		len -= AES_BLOCK_SIZE;
+	}
+
+	memzero_explicit(ks, sizeof(ks));
+}
+EXPORT_SYMBOL(aescfb_encrypt);
+
+/**
+ * aescfb_decrypt - Perform AES-CFB decryption on a block of data
+ *
+ * @ctx:	The AES-CFB key schedule
+ * @dst:	Pointer to the plaintext output buffer
+ * @src:	Pointer the ciphertext (may equal @dst for decryption in place)
+ * @len:	The size in bytes of the plaintext and ciphertext.
+ * @iv:		The initialization vector (IV) to use for this block of data
+ */
+void aescfb_decrypt(const struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src,
+		    int len, const u8 iv[AES_BLOCK_SIZE])
+{
+	u8 ks[2][AES_BLOCK_SIZE];
+
+	aescfb_encrypt_block(ctx, ks[0], iv);
+
+	for (int i = 0; len > 0; i ^= 1) {
+		if (len > AES_BLOCK_SIZE)
+			/*
+			 * Generate the keystream for the next block before
+			 * performing the XOR, as that may update in place and
+			 * overwrite the ciphertext.
+			 */
+			aescfb_encrypt_block(ctx, ks[!i], src);
+
+		crypto_xor_cpy(dst, src, ks[i], min(len, AES_BLOCK_SIZE));
+
+		dst += AES_BLOCK_SIZE;
+		src += AES_BLOCK_SIZE;
+		len -= AES_BLOCK_SIZE;
+	}
+
+	memzero_explicit(ks, sizeof(ks));
+}
+EXPORT_SYMBOL(aescfb_decrypt);
+
+MODULE_DESCRIPTION("Generic AES-CFB library");
+MODULE_AUTHOR("Ard Biesheuvel <ardb@kernel.org>");
+MODULE_LICENSE("GPL");
+
+#ifndef CONFIG_CRYPTO_MANAGER_DISABLE_TESTS
+
+/*
+ * Test code below. Vectors taken from crypto/testmgr.h
+ */
+
+static struct {
+	u8	ptext[64];
+	u8	ctext[64];
+
+	u8	key[AES_MAX_KEY_SIZE];
+	u8	iv[AES_BLOCK_SIZE];
+
+	int	klen;
+	int	len;
+} const aescfb_tv[] __initconst = {
+	{ /* From NIST SP800-38A */
+		.key    = "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
+			  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
+		.klen	= 16,
+		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
+			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
+			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
+			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
+			  "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11"
+			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
+			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
+			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
+		.ctext	= "\x3b\x3f\xd9\x2e\xb7\x2d\xad\x20"
+			  "\x33\x34\x49\xf8\xe8\x3c\xfb\x4a"
+			  "\xc8\xa6\x45\x37\xa0\xb3\xa9\x3f"
+			  "\xcd\xe3\xcd\xad\x9f\x1c\xe5\x8b"
+			  "\x26\x75\x1f\x67\xa3\xcb\xb1\x40"
+			  "\xb1\x80\x8c\xf1\x87\xa4\xf4\xdf"
+			  "\xc0\x4b\x05\x35\x7c\x5d\x1c\x0e"
+			  "\xea\xc4\xc6\x6f\x9f\xf7\xf2\xe6",
+		.len	= 64,
+	}, {
+		.key	= "\x8e\x73\xb0\xf7\xda\x0e\x64\x52"
+			  "\xc8\x10\xf3\x2b\x80\x90\x79\xe5"
+			  "\x62\xf8\xea\xd2\x52\x2c\x6b\x7b",
+		.klen	= 24,
+		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
+			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
+			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
+			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
+			  "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11"
+			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
+			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
+			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
+		.ctext	= "\xcd\xc8\x0d\x6f\xdd\xf1\x8c\xab"
+			  "\x34\xc2\x59\x09\xc9\x9a\x41\x74"
+			  "\x67\xce\x7f\x7f\x81\x17\x36\x21"
+			  "\x96\x1a\x2b\x70\x17\x1d\x3d\x7a"
+			  "\x2e\x1e\x8a\x1d\xd5\x9b\x88\xb1"
+			  "\xc8\xe6\x0f\xed\x1e\xfa\xc4\xc9"
+			  "\xc0\x5f\x9f\x9c\xa9\x83\x4f\xa0"
+			  "\x42\xae\x8f\xba\x58\x4b\x09\xff",
+		.len	= 64,
+	}, {
+		.key	= "\x60\x3d\xeb\x10\x15\xca\x71\xbe"
+			  "\x2b\x73\xae\xf0\x85\x7d\x77\x81"
+			  "\x1f\x35\x2c\x07\x3b\x61\x08\xd7"
+			  "\x2d\x98\x10\xa3\x09\x14\xdf\xf4",
+		.klen	= 32,
+		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
+			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
+			  "\xae\x2d\x8a\x57\x1e\x03\xac\x9c"
+			  "\x9e\xb7\x6f\xac\x45\xaf\x8e\x51"
+			  "\x30\xc8\x1c\x46\xa3\x5c\xe4\x11"
+			  "\xe5\xfb\xc1\x19\x1a\x0a\x52\xef"
+			  "\xf6\x9f\x24\x45\xdf\x4f\x9b\x17"
+			  "\xad\x2b\x41\x7b\xe6\x6c\x37\x10",
+		.ctext	= "\xdc\x7e\x84\xbf\xda\x79\x16\x4b"
+			  "\x7e\xcd\x84\x86\x98\x5d\x38\x60"
+			  "\x39\xff\xed\x14\x3b\x28\xb1\xc8"
+			  "\x32\x11\x3c\x63\x31\xe5\x40\x7b"
+			  "\xdf\x10\x13\x24\x15\xe5\x4b\x92"
+			  "\xa1\x3e\xd0\xa8\x26\x7a\xe2\xf9"
+			  "\x75\xa3\x85\x74\x1a\xb9\xce\xf8"
+			  "\x20\x31\x62\x3d\x55\xb1\xe4\x71",
+		.len	= 64,
+	}, { /* > 16 bytes, not a multiple of 16 bytes */
+		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
+			  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
+		.klen	= 16,
+		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f\x96"
+			  "\xe9\x3d\x7e\x11\x73\x93\x17\x2a"
+			  "\xae",
+		.ctext	= "\x3b\x3f\xd9\x2e\xb7\x2d\xad\x20"
+			  "\x33\x34\x49\xf8\xe8\x3c\xfb\x4a"
+			  "\xc8",
+		.len	= 17,
+	}, { /* < 16 bytes */
+		.key	= "\x2b\x7e\x15\x16\x28\xae\xd2\xa6"
+			  "\xab\xf7\x15\x88\x09\xcf\x4f\x3c",
+		.klen	= 16,
+		.iv	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.ptext	= "\x6b\xc1\xbe\xe2\x2e\x40\x9f",
+		.ctext	= "\x3b\x3f\xd9\x2e\xb7\x2d\xad",
+		.len	= 7,
+	},
+};
+
+static int __init libaescfb_init(void)
+{
+	for (int i = 0; i < ARRAY_SIZE(aescfb_tv); i++) {
+		struct crypto_aes_ctx ctx;
+		u8 buf[64];
+
+		if (aes_expandkey(&ctx, aescfb_tv[i].key, aescfb_tv[i].klen)) {
+			pr_err("aes_expandkey() failed on vector %d\n", i);
+			return -ENODEV;
+		}
+
+		aescfb_encrypt(&ctx, buf, aescfb_tv[i].ptext, aescfb_tv[i].len,
+			       aescfb_tv[i].iv);
+		if (memcmp(buf, aescfb_tv[i].ctext, aescfb_tv[i].len)) {
+			pr_err("aescfb_encrypt() #1 failed on vector %d\n", i);
+			return -ENODEV;
+		}
+
+		/* decrypt in place */
+		aescfb_decrypt(&ctx, buf, buf, aescfb_tv[i].len, aescfb_tv[i].iv);
+		if (memcmp(buf, aescfb_tv[i].ptext, aescfb_tv[i].len)) {
+			pr_err("aescfb_decrypt() failed on vector %d\n", i);
+			return -ENODEV;
+		}
+
+		/* encrypt in place */
+		aescfb_encrypt(&ctx, buf, buf, aescfb_tv[i].len, aescfb_tv[i].iv);
+		if (memcmp(buf, aescfb_tv[i].ctext, aescfb_tv[i].len)) {
+			pr_err("aescfb_encrypt() #2 failed on vector %d\n", i);
+
+			return -ENODEV;
+		}
+
+	}
+	return 0;
+}
+module_init(libaescfb_init);
+
+static void __exit libaescfb_exit(void)
+{
+}
+module_exit(libaescfb_exit);
+#endif
diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
index 3518e7394e..ca736166f1 100644
--- a/lib/decompress_bunzip2.c
+++ b/lib/decompress_bunzip2.c
@@ -232,7 +232,8 @@ static int INIT get_next_block(struct bunzip_data *bd)
 	   RUNB) */
 	symCount = symTotal+2;
 	for (j = 0; j < groupCount; j++) {
-		unsigned char length[MAX_SYMBOLS], temp[MAX_HUFCODE_BITS+1];
+		unsigned char length[MAX_SYMBOLS];
+		unsigned short temp[MAX_HUFCODE_BITS+1];
 		int	minLen,	maxLen, pp;
 		/* Read Huffman code lengths for each symbol.  They're
 		   stored in a way similar to mtf; record a starting
diff --git a/lib/devres.c b/lib/devres.c
index fe0c63caeb..4fc152de6d 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -1,10 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/bug.h>
 #include <linux/device.h>
-#include <linux/err.h>
-#include <linux/io.h>
-#include <linux/gfp.h>
+#include <linux/errno.h>
 #include <linux/export.h>
+#include <linux/gfp_types.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
 #include <linux/of_address.h>
+#include <linux/types.h>
 
 enum devm_ioremap_type {
 	DEVM_IOREMAP = 0,
@@ -125,12 +128,13 @@ __devm_ioremap_resource(struct device *dev, const struct resource *res,
 	resource_size_t size;
 	void __iomem *dest_ptr;
 	char *pretty_name;
+	int ret;
 
 	BUG_ON(!dev);
 
 	if (!res || resource_type(res) != IORESOURCE_MEM) {
-		dev_err(dev, "invalid resource %pR\n", res);
-		return IOMEM_ERR_PTR(-EINVAL);
+		ret = dev_err_probe(dev, -EINVAL, "invalid resource %pR\n", res);
+		return IOMEM_ERR_PTR(ret);
 	}
 
 	if (type == DEVM_IOREMAP && res->flags & IORESOURCE_MEM_NONPOSTED)
@@ -144,20 +148,20 @@ __devm_ioremap_resource(struct device *dev, const struct resource *res,
 	else
 		pretty_name = devm_kstrdup(dev, dev_name(dev), GFP_KERNEL);
 	if (!pretty_name) {
-		dev_err(dev, "can't generate pretty name for resource %pR\n", res);
-		return IOMEM_ERR_PTR(-ENOMEM);
+		ret = dev_err_probe(dev, -ENOMEM, "can't generate pretty name for resource %pR\n", res);
+		return IOMEM_ERR_PTR(ret);
 	}
 
 	if (!devm_request_mem_region(dev, res->start, size, pretty_name)) {
-		dev_err(dev, "can't request region for resource %pR\n", res);
-		return IOMEM_ERR_PTR(-EBUSY);
+		ret = dev_err_probe(dev, -EBUSY, "can't request region for resource %pR\n", res);
+		return IOMEM_ERR_PTR(ret);
 	}
 
 	dest_ptr = __devm_ioremap(dev, res->start, size, type);
 	if (!dest_ptr) {
-		dev_err(dev, "ioremap failed for resource %pR\n", res);
 		devm_release_mem_region(dev, res->start, size);
-		dest_ptr = IOMEM_ERR_PTR(-ENOMEM);
+		ret = dev_err_probe(dev, -ENOMEM, "ioremap failed for resource %pR\n", res);
+		return IOMEM_ERR_PTR(ret);
 	}
 
 	return dest_ptr;
diff --git a/lib/dim/Makefile b/lib/dim/Makefile
index 1d6858a108..c4cc4026c4 100644
--- a/lib/dim/Makefile
+++ b/lib/dim/Makefile
@@ -2,6 +2,6 @@
 # DIM Dynamic Interrupt Moderation library
 #
 
-obj-$(CONFIG_DIMLIB) += dim.o
+obj-$(CONFIG_DIMLIB) += dimlib.o
 
-dim-y := dim.o net_dim.o rdma_dim.o
+dimlib-objs := dim.o net_dim.o rdma_dim.o
diff --git a/lib/dim/dim.c b/lib/dim/dim.c
index e89aaf07bd..83b65ac74d 100644
--- a/lib/dim/dim.c
+++ b/lib/dim/dim.c
@@ -82,3 +82,6 @@ bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
 	return true;
 }
 EXPORT_SYMBOL(dim_calc_stats);
+
+MODULE_DESCRIPTION("Dynamic Interrupt Moderation (DIM) library");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c
index a1389db1c3..e49deddd3d 100644
--- a/lib/dynamic_queue_limits.c
+++ b/lib/dynamic_queue_limits.c
@@ -15,12 +15,10 @@
 #define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0)
 #define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0)
 
-static void dql_check_stall(struct dql *dql)
+static void dql_check_stall(struct dql *dql, unsigned short stall_thrs)
 {
-	unsigned short stall_thrs;
 	unsigned long now;
 
-	stall_thrs = READ_ONCE(dql->stall_thrs);
 	if (!stall_thrs)
 		return;
 
@@ -86,9 +84,16 @@ void dql_completed(struct dql *dql, unsigned int count)
 {
 	unsigned int inprogress, prev_inprogress, limit;
 	unsigned int ovlimit, completed, num_queued;
+	unsigned short stall_thrs;
 	bool all_prev_completed;
 
 	num_queued = READ_ONCE(dql->num_queued);
+	/* Read stall_thrs in advance since it belongs to the same (first)
+	 * cache line as ->num_queued. This way, dql_check_stall() does not
+	 * need to touch the first cache line again later, reducing the window
+	 * of possible false sharing.
+	 */
+	stall_thrs = READ_ONCE(dql->stall_thrs);
 
 	/* Can't complete more than what's in queue */
 	BUG_ON(count > num_queued - dql->num_completed);
@@ -178,7 +183,7 @@ void dql_completed(struct dql *dql, unsigned int count)
 	dql->num_completed = completed;
 	dql->prev_num_queued = num_queued;
 
-	dql_check_stall(dql);
+	dql_check_stall(dql, stall_thrs);
 }
 EXPORT_SYMBOL(dql_completed);
 
diff --git a/lib/find_bit.c b/lib/find_bit.c
index 32f99e9a67..0836bb3d76 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -87,7 +87,7 @@ out:										\
 	if (sz % BITS_PER_LONG)							\
 		tmp = (FETCH) & BITMAP_LAST_WORD_MASK(sz);			\
 found:										\
-	sz = min(idx * BITS_PER_LONG + fns(tmp, nr), sz);			\
+	sz = idx * BITS_PER_LONG + fns(tmp, nr);				\
 out:										\
 	sz;									\
 })
@@ -116,6 +116,18 @@ unsigned long _find_first_and_bit(const unsigned long *addr1,
 EXPORT_SYMBOL(_find_first_and_bit);
 #endif
 
+/*
+ * Find the first set bit in three memory regions.
+ */
+unsigned long _find_first_and_and_bit(const unsigned long *addr1,
+				      const unsigned long *addr2,
+				      const unsigned long *addr3,
+				      unsigned long size)
+{
+	return FIND_FIRST_BIT(addr1[idx] & addr2[idx] & addr3[idx], /* nop */, size);
+}
+EXPORT_SYMBOL(_find_first_and_and_bit);
+
 #ifndef find_first_zero_bit
 /*
  * Find the first cleared bit in a memory region.
diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c
index ad29721b95..e17d520f53 100644
--- a/lib/fortify_kunit.c
+++ b/lib/fortify_kunit.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Runtime test cases for CONFIG_FORTIFY_SOURCE. For testing memcpy(),
- * see FORTIFY_MEM_* tests in LKDTM (drivers/misc/lkdtm/fortify.c).
+ * Runtime test cases for CONFIG_FORTIFY_SOURCE. For additional memcpy()
+ * testing see FORTIFY_MEM_* tests in LKDTM (drivers/misc/lkdtm/fortify.c).
  *
  * For corner cases with UBSAN, try testing with:
  *
@@ -18,8 +18,10 @@
 /* We don't need to fill dmesg with the fortify WARNs during testing. */
 #ifdef DEBUG
 # define FORTIFY_REPORT_KUNIT(x...) __fortify_report(x)
+# define FORTIFY_WARN_KUNIT(x...)   WARN_ONCE(x)
 #else
 # define FORTIFY_REPORT_KUNIT(x...) do { } while (0)
+# define FORTIFY_WARN_KUNIT(x...)   do { } while (0)
 #endif
 
 /* Redefine fortify_panic() to track failures. */
@@ -30,6 +32,14 @@ void fortify_add_kunit_error(int write);
 	return (retfail);						\
 } while (0)
 
+/* Redefine fortify_warn_once() to track memcpy() failures. */
+#define fortify_warn_once(chk_func, x...) do {				\
+	bool __result = chk_func;					\
+	FORTIFY_WARN_KUNIT(__result, x);				\
+	if (__result)							\
+		fortify_add_kunit_error(1);				\
+} while (0)
+
 #include <kunit/device.h>
 #include <kunit/test.h>
 #include <kunit/test-bug.h>
@@ -71,7 +81,7 @@ void fortify_add_kunit_error(int write)
 	kunit_put_resource(resource);
 }
 
-static void known_sizes_test(struct kunit *test)
+static void fortify_test_known_sizes(struct kunit *test)
 {
 	KUNIT_EXPECT_EQ(test, __compiletime_strlen("88888888"), 8);
 	KUNIT_EXPECT_EQ(test, __compiletime_strlen(array_of_10), 10);
@@ -104,7 +114,7 @@ static noinline size_t want_minus_one(int pick)
 	return __compiletime_strlen(str);
 }
 
-static void control_flow_split_test(struct kunit *test)
+static void fortify_test_control_flow_split(struct kunit *test)
 {
 	KUNIT_EXPECT_EQ(test, want_minus_one(pick), SIZE_MAX);
 }
@@ -180,11 +190,11 @@ static volatile size_t unknown_size = 50;
 #endif
 
 #define DEFINE_ALLOC_SIZE_TEST_PAIR(allocator)				\
-static void alloc_size_##allocator##_const_test(struct kunit *test)	\
+static void fortify_test_alloc_size_##allocator##_const(struct kunit *test) \
 {									\
 	CONST_TEST_BODY(TEST_##allocator);				\
 }									\
-static void alloc_size_##allocator##_dynamic_test(struct kunit *test)	\
+static void fortify_test_alloc_size_##allocator##_dynamic(struct kunit *test) \
 {									\
 	DYNAMIC_TEST_BODY(TEST_##allocator);				\
 }
@@ -226,9 +236,6 @@ static void alloc_size_##allocator##_dynamic_test(struct kunit *test)	\
 		kfree(p));						\
 	checker(expected_size, __kmalloc(alloc_size, gfp),		\
 		kfree(p));						\
-	checker(expected_size,						\
-		__kmalloc_node(alloc_size, gfp, NUMA_NO_NODE),		\
-		kfree(p));						\
 									\
 	orig = kmalloc(alloc_size, gfp);				\
 	KUNIT_EXPECT_TRUE(test, orig != NULL);				\
@@ -353,6 +360,31 @@ DEFINE_ALLOC_SIZE_TEST_PAIR(kvmalloc)
 } while (0)
 DEFINE_ALLOC_SIZE_TEST_PAIR(devm_kmalloc)
 
+static const char * const test_strs[] = {
+	"",
+	"Hello there",
+	"A longer string, just for variety",
+};
+
+#define TEST_realloc(checker)	do {					\
+	gfp_t gfp = GFP_KERNEL;						\
+	size_t len;							\
+	int i;								\
+									\
+	for (i = 0; i < ARRAY_SIZE(test_strs); i++) {			\
+		len = strlen(test_strs[i]);				\
+		KUNIT_EXPECT_EQ(test, __builtin_constant_p(len), 0);	\
+		checker(len, kmemdup_array(test_strs[i], 1, len, gfp),	\
+			kfree(p));					\
+		checker(len, kmemdup(test_strs[i], len, gfp),		\
+			kfree(p));					\
+	}								\
+} while (0)
+static void fortify_test_realloc_size(struct kunit *test)
+{
+	TEST_realloc(check_dynamic);
+}
+
 /*
  * We can't have an array at the end of a structure or else
  * builds without -fstrict-flex-arrays=3 will report them as
@@ -368,7 +400,7 @@ struct fortify_padding {
 /* Force compiler into not being able to resolve size at compile-time. */
 static volatile int unconst;
 
-static void strlen_test(struct kunit *test)
+static void fortify_test_strlen(struct kunit *test)
 {
 	struct fortify_padding pad = { };
 	int i, end = sizeof(pad.buf) - 1;
@@ -391,7 +423,7 @@ static void strlen_test(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 1);
 }
 
-static void strnlen_test(struct kunit *test)
+static void fortify_test_strnlen(struct kunit *test)
 {
 	struct fortify_padding pad = { };
 	int i, end = sizeof(pad.buf) - 1;
@@ -429,7 +461,7 @@ static void strnlen_test(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 2);
 }
 
-static void strcpy_test(struct kunit *test)
+static void fortify_test_strcpy(struct kunit *test)
 {
 	struct fortify_padding pad = { };
 	char src[sizeof(pad.buf) + 1] = { };
@@ -487,7 +519,7 @@ static void strcpy_test(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, pad.bytes_after, 0);
 }
 
-static void strncpy_test(struct kunit *test)
+static void fortify_test_strncpy(struct kunit *test)
 {
 	struct fortify_padding pad = { };
 	char src[] = "Copy me fully into a small buffer and I will overflow!";
@@ -546,7 +578,7 @@ static void strncpy_test(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, pad.bytes_after, 0);
 }
 
-static void strscpy_test(struct kunit *test)
+static void fortify_test_strscpy(struct kunit *test)
 {
 	struct fortify_padding pad = { };
 	char src[] = "Copy me fully into a small buffer and I will overflow!";
@@ -603,7 +635,7 @@ static void strscpy_test(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, pad.bytes_after, 0);
 }
 
-static void strcat_test(struct kunit *test)
+static void fortify_test_strcat(struct kunit *test)
 {
 	struct fortify_padding pad = { };
 	char src[sizeof(pad.buf) / 2] = { };
@@ -660,7 +692,7 @@ static void strcat_test(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, pad.bytes_after, 0);
 }
 
-static void strncat_test(struct kunit *test)
+static void fortify_test_strncat(struct kunit *test)
 {
 	struct fortify_padding pad = { };
 	char src[sizeof(pad.buf)] = { };
@@ -733,7 +765,7 @@ static void strncat_test(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, pad.bytes_after, 0);
 }
 
-static void strlcat_test(struct kunit *test)
+static void fortify_test_strlcat(struct kunit *test)
 {
 	struct fortify_padding pad = { };
 	char src[sizeof(pad.buf)] = { };
@@ -818,7 +850,75 @@ static void strlcat_test(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, pad.bytes_after, 0);
 }
 
-static void memscan_test(struct kunit *test)
+/* Check for 0-sized arrays... */
+struct fortify_zero_sized {
+	unsigned long bytes_before;
+	char buf[0];
+	unsigned long bytes_after;
+};
+
+#define __fortify_test(memfunc)					\
+static void fortify_test_##memfunc(struct kunit *test)		\
+{								\
+	struct fortify_zero_sized zero = { };			\
+	struct fortify_padding pad = { };			\
+	char srcA[sizeof(pad.buf) + 2];				\
+	char srcB[sizeof(pad.buf) + 2];				\
+	size_t len = sizeof(pad.buf) + unconst;			\
+								\
+	memset(srcA, 'A', sizeof(srcA));			\
+	KUNIT_ASSERT_EQ(test, srcA[0], 'A');			\
+	memset(srcB, 'B', sizeof(srcB));			\
+	KUNIT_ASSERT_EQ(test, srcB[0], 'B');			\
+								\
+	memfunc(pad.buf, srcA, 0 + unconst);			\
+	KUNIT_EXPECT_EQ(test, pad.buf[0], '\0');		\
+	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0);	\
+	KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0);	\
+	memfunc(pad.buf + 1, srcB, 1 + unconst);		\
+	KUNIT_EXPECT_EQ(test, pad.buf[0], '\0');		\
+	KUNIT_EXPECT_EQ(test, pad.buf[1], 'B');			\
+	KUNIT_EXPECT_EQ(test, pad.buf[2], '\0');		\
+	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0);	\
+	KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0);	\
+	memfunc(pad.buf, srcA, 1 + unconst);			\
+	KUNIT_EXPECT_EQ(test, pad.buf[0], 'A');			\
+	KUNIT_EXPECT_EQ(test, pad.buf[1], 'B');			\
+	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0);	\
+	KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0);	\
+	memfunc(pad.buf, srcA, len - 1);			\
+	KUNIT_EXPECT_EQ(test, pad.buf[1], 'A');			\
+	KUNIT_EXPECT_EQ(test, pad.buf[len - 1], '\0');		\
+	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0);	\
+	KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0);	\
+	memfunc(pad.buf, srcA, len);				\
+	KUNIT_EXPECT_EQ(test, pad.buf[1], 'A');			\
+	KUNIT_EXPECT_EQ(test, pad.buf[len - 1], 'A');		\
+	KUNIT_EXPECT_EQ(test, pad.bytes_after, 0);		\
+	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0);	\
+	KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0);	\
+	memfunc(pad.buf, srcA, len + 1);			\
+	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0);	\
+	KUNIT_EXPECT_EQ(test, fortify_write_overflows, 1);	\
+	memfunc(pad.buf + 1, srcB, len);			\
+	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0);	\
+	KUNIT_EXPECT_EQ(test, fortify_write_overflows, 2);	\
+								\
+	/* Reset error counter. */				\
+	fortify_write_overflows = 0;				\
+	/* Copy nothing into nothing: no errors. */		\
+	memfunc(zero.buf, srcB, 0 + unconst);			\
+	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0);	\
+	KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0);	\
+	/* We currently explicitly ignore zero-sized dests. */	\
+	memfunc(zero.buf, srcB, 1 + unconst);			\
+	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0);	\
+	KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0);	\
+}
+__fortify_test(memcpy)
+__fortify_test(memmove)
+
+static void fortify_test_memscan(struct kunit *test)
 {
 	char haystack[] = "Where oh where is my memory range?";
 	char *mem = haystack + strlen("Where oh where is ");
@@ -837,7 +937,7 @@ static void memscan_test(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 2);
 }
 
-static void memchr_test(struct kunit *test)
+static void fortify_test_memchr(struct kunit *test)
 {
 	char haystack[] = "Where oh where is my memory range?";
 	char *mem = haystack + strlen("Where oh where is ");
@@ -856,7 +956,7 @@ static void memchr_test(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 2);
 }
 
-static void memchr_inv_test(struct kunit *test)
+static void fortify_test_memchr_inv(struct kunit *test)
 {
 	char haystack[] = "Where oh where is my memory range?";
 	char *mem = haystack + 1;
@@ -876,7 +976,7 @@ static void memchr_inv_test(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 2);
 }
 
-static void memcmp_test(struct kunit *test)
+static void fortify_test_memcmp(struct kunit *test)
 {
 	char one[] = "My mind is going ...";
 	char two[] = "My mind is going ... I can feel it.";
@@ -887,7 +987,7 @@ static void memcmp_test(struct kunit *test)
 	KUNIT_ASSERT_EQ(test, memcmp(one, two, one_len), 0);
 	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0);
 	/* Still in bounds, but no longer matching. */
-	KUNIT_ASSERT_EQ(test, memcmp(one, two, one_len + 1), -32);
+	KUNIT_ASSERT_LT(test, memcmp(one, two, one_len + 1), 0);
 	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0);
 
 	/* Catch too-large ranges. */
@@ -898,7 +998,7 @@ static void memcmp_test(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, fortify_read_overflows, 2);
 }
 
-static void kmemdup_test(struct kunit *test)
+static void fortify_test_kmemdup(struct kunit *test)
 {
 	char src[] = "I got Doom running on it!";
 	char *copy;
@@ -958,31 +1058,33 @@ static int fortify_test_init(struct kunit *test)
 }
 
 static struct kunit_case fortify_test_cases[] = {
-	KUNIT_CASE(known_sizes_test),
-	KUNIT_CASE(control_flow_split_test),
-	KUNIT_CASE(alloc_size_kmalloc_const_test),
-	KUNIT_CASE(alloc_size_kmalloc_dynamic_test),
-	KUNIT_CASE(alloc_size_vmalloc_const_test),
-	KUNIT_CASE(alloc_size_vmalloc_dynamic_test),
-	KUNIT_CASE(alloc_size_kvmalloc_const_test),
-	KUNIT_CASE(alloc_size_kvmalloc_dynamic_test),
-	KUNIT_CASE(alloc_size_devm_kmalloc_const_test),
-	KUNIT_CASE(alloc_size_devm_kmalloc_dynamic_test),
-	KUNIT_CASE(strlen_test),
-	KUNIT_CASE(strnlen_test),
-	KUNIT_CASE(strcpy_test),
-	KUNIT_CASE(strncpy_test),
-	KUNIT_CASE(strscpy_test),
-	KUNIT_CASE(strcat_test),
-	KUNIT_CASE(strncat_test),
-	KUNIT_CASE(strlcat_test),
+	KUNIT_CASE(fortify_test_known_sizes),
+	KUNIT_CASE(fortify_test_control_flow_split),
+	KUNIT_CASE(fortify_test_alloc_size_kmalloc_const),
+	KUNIT_CASE(fortify_test_alloc_size_kmalloc_dynamic),
+	KUNIT_CASE(fortify_test_alloc_size_vmalloc_const),
+	KUNIT_CASE(fortify_test_alloc_size_vmalloc_dynamic),
+	KUNIT_CASE(fortify_test_alloc_size_kvmalloc_const),
+	KUNIT_CASE(fortify_test_alloc_size_kvmalloc_dynamic),
+	KUNIT_CASE(fortify_test_alloc_size_devm_kmalloc_const),
+	KUNIT_CASE(fortify_test_alloc_size_devm_kmalloc_dynamic),
+	KUNIT_CASE(fortify_test_realloc_size),
+	KUNIT_CASE(fortify_test_strlen),
+	KUNIT_CASE(fortify_test_strnlen),
+	KUNIT_CASE(fortify_test_strcpy),
+	KUNIT_CASE(fortify_test_strncpy),
+	KUNIT_CASE(fortify_test_strscpy),
+	KUNIT_CASE(fortify_test_strcat),
+	KUNIT_CASE(fortify_test_strncat),
+	KUNIT_CASE(fortify_test_strlcat),
 	/* skip memset: performs bounds checking on whole structs */
-	/* skip memcpy: still using warn-and-overwrite instead of hard-fail */
-	KUNIT_CASE(memscan_test),
-	KUNIT_CASE(memchr_test),
-	KUNIT_CASE(memchr_inv_test),
-	KUNIT_CASE(memcmp_test),
-	KUNIT_CASE(kmemdup_test),
+	KUNIT_CASE(fortify_test_memcpy),
+	KUNIT_CASE(fortify_test_memmove),
+	KUNIT_CASE(fortify_test_memscan),
+	KUNIT_CASE(fortify_test_memchr),
+	KUNIT_CASE(fortify_test_memchr_inv),
+	KUNIT_CASE(fortify_test_memcmp),
+	KUNIT_CASE(fortify_test_kmemdup),
 	{}
 };
 
diff --git a/lib/iomap_copy.c b/lib/iomap_copy.c
index 5de7c04e05..2fd5712fb7 100644
--- a/lib/iomap_copy.c
+++ b/lib/iomap_copy.c
@@ -16,9 +16,8 @@
  * time.  Order of access is not guaranteed, nor is a memory barrier
  * performed afterwards.
  */
-void __attribute__((weak)) __iowrite32_copy(void __iomem *to,
-					    const void *from,
-					    size_t count)
+#ifndef __iowrite32_copy
+void __iowrite32_copy(void __iomem *to, const void *from, size_t count)
 {
 	u32 __iomem *dst = to;
 	const u32 *src = from;
@@ -28,6 +27,7 @@ void __attribute__((weak)) __iowrite32_copy(void __iomem *to,
 		__raw_writel(*src++, dst++);
 }
 EXPORT_SYMBOL_GPL(__iowrite32_copy);
+#endif
 
 /**
  * __ioread32_copy - copy data from MMIO space, in 32-bit units
@@ -60,9 +60,8 @@ EXPORT_SYMBOL_GPL(__ioread32_copy);
  * time.  Order of access is not guaranteed, nor is a memory barrier
  * performed afterwards.
  */
-void __attribute__((weak)) __iowrite64_copy(void __iomem *to,
-					    const void *from,
-					    size_t count)
+#ifndef __iowrite64_copy
+void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
 {
 #ifdef CONFIG_64BIT
 	u64 __iomem *dst = to;
@@ -75,5 +74,5 @@ void __attribute__((weak)) __iowrite64_copy(void __iomem *to,
 	__iowrite32_copy(to, from, count * 2);
 #endif
 }
-
 EXPORT_SYMBOL_GPL(__iowrite64_copy);
+#endif
diff --git a/lib/kfifo.c b/lib/kfifo.c
index 12f5a347aa..a8b2eed905 100644
--- a/lib/kfifo.c
+++ b/lib/kfifo.c
@@ -5,13 +5,14 @@
  * Copyright (C) 2009/2010 Stefani Seibold <stefani@seibold.net>
  */
 
-#include <linux/kernel.h>
-#include <linux/export.h>
-#include <linux/slab.h>
+#include <linux/dma-mapping.h>
 #include <linux/err.h>
+#include <linux/export.h>
+#include <linux/kfifo.h>
 #include <linux/log2.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
 #include <linux/uaccess.h>
-#include <linux/kfifo.h>
 
 /*
  * internal helper to calculate the unused elements in a fifo
@@ -163,6 +164,19 @@ unsigned int __kfifo_out_peek(struct __kfifo *fifo,
 }
 EXPORT_SYMBOL(__kfifo_out_peek);
 
+unsigned int __kfifo_out_linear(struct __kfifo *fifo,
+		unsigned int *tail, unsigned int n)
+{
+	unsigned int size = fifo->mask + 1;
+	unsigned int off = fifo->out & fifo->mask;
+
+	if (tail)
+		*tail = off;
+
+	return min3(n, fifo->in - fifo->out, size - off);
+}
+EXPORT_SYMBOL(__kfifo_out_linear);
+
 unsigned int __kfifo_out(struct __kfifo *fifo,
 		void *buf, unsigned int len)
 {
@@ -292,51 +306,31 @@ int __kfifo_to_user(struct __kfifo *fifo, void __user *to,
 }
 EXPORT_SYMBOL(__kfifo_to_user);
 
-static int setup_sgl_buf(struct scatterlist *sgl, void *buf,
-		int nents, unsigned int len)
+static unsigned int setup_sgl_buf(struct __kfifo *fifo, struct scatterlist *sgl,
+				  unsigned int data_offset, int nents,
+				  unsigned int len, dma_addr_t dma)
 {
-	int n;
-	unsigned int l;
-	unsigned int off;
-	struct page *page;
+	const void *buf = fifo->data + data_offset;
 
-	if (!nents)
+	if (!nents || !len)
 		return 0;
 
-	if (!len)
-		return 0;
+	sg_set_buf(sgl, buf, len);
 
-	n = 0;
-	page = virt_to_page(buf);
-	off = offset_in_page(buf);
-	l = 0;
-
-	while (len >= l + PAGE_SIZE - off) {
-		struct page *npage;
-
-		l += PAGE_SIZE;
-		buf += PAGE_SIZE;
-		npage = virt_to_page(buf);
-		if (page_to_phys(page) != page_to_phys(npage) - l) {
-			sg_set_page(sgl, page, l - off, off);
-			sgl = sg_next(sgl);
-			if (++n == nents || sgl == NULL)
-				return n;
-			page = npage;
-			len -= l - off;
-			l = off = 0;
-		}
+	if (dma != DMA_MAPPING_ERROR) {
+		sg_dma_address(sgl) = dma + data_offset;
+		sg_dma_len(sgl) = len;
 	}
-	sg_set_page(sgl, page, len, off);
-	return n + 1;
+
+	return 1;
 }
 
 static unsigned int setup_sgl(struct __kfifo *fifo, struct scatterlist *sgl,
-		int nents, unsigned int len, unsigned int off)
+		int nents, unsigned int len, unsigned int off, dma_addr_t dma)
 {
 	unsigned int size = fifo->mask + 1;
 	unsigned int esize = fifo->esize;
-	unsigned int l;
+	unsigned int len_to_end;
 	unsigned int n;
 
 	off &= fifo->mask;
@@ -345,16 +339,17 @@ static unsigned int setup_sgl(struct __kfifo *fifo, struct scatterlist *sgl,
 		size *= esize;
 		len *= esize;
 	}
-	l = min(len, size - off);
+	len_to_end = min(len, size - off);
 
-	n = setup_sgl_buf(sgl, fifo->data + off, nents, l);
-	n += setup_sgl_buf(sgl + n, fifo->data, nents - n, len - l);
+	n = setup_sgl_buf(fifo, sgl, off, nents, len_to_end, dma);
+	n += setup_sgl_buf(fifo, sgl + n, 0, nents - n, len - len_to_end, dma);
 
 	return n;
 }
 
 unsigned int __kfifo_dma_in_prepare(struct __kfifo *fifo,
-		struct scatterlist *sgl, int nents, unsigned int len)
+		struct scatterlist *sgl, int nents, unsigned int len,
+		dma_addr_t dma)
 {
 	unsigned int l;
 
@@ -362,12 +357,13 @@ unsigned int __kfifo_dma_in_prepare(struct __kfifo *fifo,
 	if (len > l)
 		len = l;
 
-	return setup_sgl(fifo, sgl, nents, len, fifo->in);
+	return setup_sgl(fifo, sgl, nents, len, fifo->in, dma);
 }
 EXPORT_SYMBOL(__kfifo_dma_in_prepare);
 
 unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo,
-		struct scatterlist *sgl, int nents, unsigned int len)
+		struct scatterlist *sgl, int nents, unsigned int len,
+		dma_addr_t dma)
 {
 	unsigned int l;
 
@@ -375,7 +371,7 @@ unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo,
 	if (len > l)
 		len = l;
 
-	return setup_sgl(fifo, sgl, nents, len, fifo->out);
+	return setup_sgl(fifo, sgl, nents, len, fifo->out, dma);
 }
 EXPORT_SYMBOL(__kfifo_dma_out_prepare);
 
@@ -473,6 +469,19 @@ unsigned int __kfifo_out_peek_r(struct __kfifo *fifo, void *buf,
 }
 EXPORT_SYMBOL(__kfifo_out_peek_r);
 
+unsigned int __kfifo_out_linear_r(struct __kfifo *fifo,
+		unsigned int *tail, unsigned int n, size_t recsize)
+{
+	if (fifo->in == fifo->out)
+		return 0;
+
+	if (tail)
+		*tail = fifo->out + recsize;
+
+	return min(n, __kfifo_peek_n(fifo, recsize));
+}
+EXPORT_SYMBOL(__kfifo_out_linear_r);
+
 unsigned int __kfifo_out_r(struct __kfifo *fifo, void *buf,
 		unsigned int len, size_t recsize)
 {
@@ -546,7 +555,8 @@ int __kfifo_to_user_r(struct __kfifo *fifo, void __user *to,
 EXPORT_SYMBOL(__kfifo_to_user_r);
 
 unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo,
-	struct scatterlist *sgl, int nents, unsigned int len, size_t recsize)
+	struct scatterlist *sgl, int nents, unsigned int len, size_t recsize,
+	dma_addr_t dma)
 {
 	BUG_ON(!nents);
 
@@ -555,7 +565,7 @@ unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo,
 	if (len + recsize > kfifo_unused(fifo))
 		return 0;
 
-	return setup_sgl(fifo, sgl, nents, len, fifo->in + recsize);
+	return setup_sgl(fifo, sgl, nents, len, fifo->in + recsize, dma);
 }
 EXPORT_SYMBOL(__kfifo_dma_in_prepare_r);
 
@@ -569,7 +579,8 @@ void __kfifo_dma_in_finish_r(struct __kfifo *fifo,
 EXPORT_SYMBOL(__kfifo_dma_in_finish_r);
 
 unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo,
-	struct scatterlist *sgl, int nents, unsigned int len, size_t recsize)
+	struct scatterlist *sgl, int nents, unsigned int len, size_t recsize,
+	dma_addr_t dma)
 {
 	BUG_ON(!nents);
 
@@ -578,15 +589,7 @@ unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo,
 	if (len + recsize > fifo->in - fifo->out)
 		return 0;
 
-	return setup_sgl(fifo, sgl, nents, len, fifo->out + recsize);
+	return setup_sgl(fifo, sgl, nents, len, fifo->out + recsize, dma);
 }
 EXPORT_SYMBOL(__kfifo_dma_out_prepare_r);
 
-void __kfifo_dma_out_finish_r(struct __kfifo *fifo, size_t recsize)
-{
-	unsigned int len;
-
-	len = __kfifo_peek_n(fifo, recsize);
-	fifo->out += len + recsize;
-}
-EXPORT_SYMBOL(__kfifo_dma_out_finish_r);
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 03b427e270..b7f2fa08d9 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -433,8 +433,23 @@ static void zap_modalias_env(struct kobj_uevent_env *env)
 		len = strlen(env->envp[i]) + 1;
 
 		if (i != env->envp_idx - 1) {
+			/* @env->envp[] contains pointers to @env->buf[]
+			 * with @env->buflen chars, and we are removing
+			 * variable MODALIAS here pointed by @env->envp[i]
+			 * with length @len as shown below:
+			 *
+			 * 0               @env->buf[]      @env->buflen
+			 * ---------------------------------------------
+			 * ^             ^              ^              ^
+			 * |             |->   @len   <-| target block |
+			 * @env->envp[0] @env->envp[i]  @env->envp[i + 1]
+			 *
+			 * so the "target block" indicated above is moved
+			 * backward by @len, and its right size is
+			 * @env->buflen - (@env->envp[i + 1] - @env->envp[0]).
+			 */
 			memmove(env->envp[i], env->envp[i + 1],
-				env->buflen - len);
+				env->buflen - (env->envp[i + 1] - env->envp[0]));
 
 			for (j = i; j < env->envp_idx - 1; j++)
 				env->envp[j] = env->envp[j + 1] - len;
diff --git a/lib/kunit/Kconfig b/lib/kunit/Kconfig
index 68a6daec0a..34d7242d52 100644
--- a/lib/kunit/Kconfig
+++ b/lib/kunit/Kconfig
@@ -24,6 +24,17 @@ config KUNIT_DEBUGFS
 	  test suite, which allow users to see results of the last test suite
 	  run that occurred.
 
+config KUNIT_FAULT_TEST
+	bool "Enable KUnit tests which print BUG stacktraces"
+	depends on KUNIT_TEST
+	depends on !UML
+	default y
+	help
+	  Enables fault handling tests for the KUnit framework. These tests may
+	  trigger a kernel BUG(), and the associated stack trace, even when they
+	  pass. If this conflicts with your test infrastrcture (or is confusing
+	  or annoying), they can be disabled by setting this to N.
+
 config KUNIT_TEST
 	tristate "KUnit test for KUnit" if !KUNIT_ALL_TESTS
 	default KUNIT_ALL_TESTS
diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c
index f7980ef236..e3412e0ca3 100644
--- a/lib/kunit/kunit-test.c
+++ b/lib/kunit/kunit-test.c
@@ -109,6 +109,48 @@ static struct kunit_suite kunit_try_catch_test_suite = {
 	.test_cases = kunit_try_catch_test_cases,
 };
 
+#if IS_ENABLED(CONFIG_KUNIT_FAULT_TEST)
+
+static void kunit_test_null_dereference(void *data)
+{
+	struct kunit *test = data;
+	int *null = NULL;
+
+	*null = 0;
+
+	KUNIT_FAIL(test, "This line should never be reached\n");
+}
+
+static void kunit_test_fault_null_dereference(struct kunit *test)
+{
+	struct kunit_try_catch_test_context *ctx = test->priv;
+	struct kunit_try_catch *try_catch = ctx->try_catch;
+
+	kunit_try_catch_init(try_catch,
+			     test,
+			     kunit_test_null_dereference,
+			     kunit_test_catch);
+	kunit_try_catch_run(try_catch, test);
+
+	KUNIT_EXPECT_EQ(test, try_catch->try_result, -EINTR);
+	KUNIT_EXPECT_TRUE(test, ctx->function_called);
+}
+
+#endif /* CONFIG_KUNIT_FAULT_TEST */
+
+static struct kunit_case kunit_fault_test_cases[] = {
+#if IS_ENABLED(CONFIG_KUNIT_FAULT_TEST)
+	KUNIT_CASE(kunit_test_fault_null_dereference),
+#endif /* CONFIG_KUNIT_FAULT_TEST */
+	{}
+};
+
+static struct kunit_suite kunit_fault_test_suite = {
+	.name = "kunit_fault",
+	.init = kunit_try_catch_test_init,
+	.test_cases = kunit_fault_test_cases,
+};
+
 /*
  * Context for testing test managed resources
  * is_resource_initialized is used to test arbitrary resources
@@ -826,6 +868,7 @@ static struct kunit_suite kunit_current_test_suite = {
 
 kunit_test_suites(&kunit_try_catch_test_suite, &kunit_resource_test_suite,
 		  &kunit_log_test_suite, &kunit_status_test_suite,
-		  &kunit_current_test_suite, &kunit_device_test_suite);
+		  &kunit_current_test_suite, &kunit_device_test_suite,
+		  &kunit_fault_test_suite);
 
 MODULE_LICENSE("GPL v2");
diff --git a/lib/kunit/string-stream-test.c b/lib/kunit/string-stream-test.c
index 03fb511826..7511442ea9 100644
--- a/lib/kunit/string-stream-test.c
+++ b/lib/kunit/string-stream-test.c
@@ -22,18 +22,10 @@ struct string_stream_test_priv {
 };
 
 /* Avoids a cast warning if kfree() is passed direct to kunit_add_action(). */
-static void kfree_wrapper(void *p)
-{
-	kfree(p);
-}
+KUNIT_DEFINE_ACTION_WRAPPER(kfree_wrapper, kfree, const void *);
 
 /* Avoids a cast warning if string_stream_destroy() is passed direct to kunit_add_action(). */
-static void cleanup_raw_stream(void *p)
-{
-	struct string_stream *stream = p;
-
-	string_stream_destroy(stream);
-}
+KUNIT_DEFINE_ACTION_WRAPPER(cleanup_raw_stream, string_stream_destroy, struct string_stream *);
 
 static char *get_concatenated_string(struct kunit *test, struct string_stream *stream)
 {
diff --git a/lib/kunit/try-catch.c b/lib/kunit/try-catch.c
index 9c9e4dcf06..6bbe0025b0 100644
--- a/lib/kunit/try-catch.c
+++ b/lib/kunit/try-catch.c
@@ -18,7 +18,7 @@
 void __noreturn kunit_try_catch_throw(struct kunit_try_catch *try_catch)
 {
 	try_catch->try_result = -EFAULT;
-	kthread_complete_and_exit(try_catch->try_completion, -EFAULT);
+	kthread_exit(0);
 }
 EXPORT_SYMBOL_GPL(kunit_try_catch_throw);
 
@@ -26,9 +26,12 @@ static int kunit_generic_run_threadfn_adapter(void *data)
 {
 	struct kunit_try_catch *try_catch = data;
 
+	try_catch->try_result = -EINTR;
 	try_catch->try(try_catch->context);
+	if (try_catch->try_result == -EINTR)
+		try_catch->try_result = 0;
 
-	kthread_complete_and_exit(try_catch->try_completion, 0);
+	return 0;
 }
 
 static unsigned long kunit_test_timeout(void)
@@ -58,24 +61,31 @@ static unsigned long kunit_test_timeout(void)
 
 void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context)
 {
-	DECLARE_COMPLETION_ONSTACK(try_completion);
 	struct kunit *test = try_catch->test;
 	struct task_struct *task_struct;
+	struct completion *task_done;
 	int exit_code, time_remaining;
 
 	try_catch->context = context;
-	try_catch->try_completion = &try_completion;
 	try_catch->try_result = 0;
 	task_struct = kthread_create(kunit_generic_run_threadfn_adapter,
 				     try_catch, "kunit_try_catch_thread");
 	if (IS_ERR(task_struct)) {
+		try_catch->try_result = PTR_ERR(task_struct);
 		try_catch->catch(try_catch->context);
 		return;
 	}
 	get_task_struct(task_struct);
+	/*
+	 * As for a vfork(2), task_struct->vfork_done (pointing to the
+	 * underlying kthread->exited) can be used to wait for the end of a
+	 * kernel thread. It is set to NULL when the thread exits, so we
+	 * keep a copy here.
+	 */
+	task_done = task_struct->vfork_done;
 	wake_up_process(task_struct);
 
-	time_remaining = wait_for_completion_timeout(&try_completion,
+	time_remaining = wait_for_completion_timeout(task_done,
 						     kunit_test_timeout());
 	if (time_remaining == 0) {
 		try_catch->try_result = -ETIMEDOUT;
@@ -90,9 +100,13 @@ void kunit_try_catch_run(struct kunit_try_catch *try_catch, void *context)
 
 	if (exit_code == -EFAULT)
 		try_catch->try_result = 0;
-	else if (exit_code == -EINTR)
-		kunit_err(test, "wake_up_process() was never called\n");
-	else if (exit_code == -ETIMEDOUT)
+	else if (exit_code == -EINTR) {
+		if (test->last_seen.file)
+			kunit_err(test, "try faulted: last line seen %s:%d\n",
+				  test->last_seen.file, test->last_seen.line);
+		else
+			kunit_err(test, "try faulted\n");
+	} else if (exit_code == -ETIMEDOUT)
 		kunit_err(test, "try timed out\n");
 	else if (exit_code)
 		kunit_err(test, "Unknown error: %d\n", exit_code);
diff --git a/lib/kunit_iov_iter.c b/lib/kunit_iov_iter.c
index 859b67c4d6..27e0c8ee71 100644
--- a/lib/kunit_iov_iter.c
+++ b/lib/kunit_iov_iter.c
@@ -139,7 +139,7 @@ static void __init iov_kunit_copy_to_kvec(struct kunit *test)
 			return;
 	}
 
-	KUNIT_SUCCEED();
+	KUNIT_SUCCEED(test);
 }
 
 /*
@@ -194,7 +194,7 @@ stop:
 			return;
 	}
 
-	KUNIT_SUCCEED();
+	KUNIT_SUCCEED(test);
 }
 
 struct bvec_test_range {
@@ -302,7 +302,7 @@ static void __init iov_kunit_copy_to_bvec(struct kunit *test)
 			return;
 	}
 
-	KUNIT_SUCCEED();
+	KUNIT_SUCCEED(test);
 }
 
 /*
@@ -359,7 +359,7 @@ stop:
 			return;
 	}
 
-	KUNIT_SUCCEED();
+	KUNIT_SUCCEED(test);
 }
 
 static void iov_kunit_destroy_xarray(void *data)
@@ -453,7 +453,7 @@ static void __init iov_kunit_copy_to_xarray(struct kunit *test)
 			return;
 	}
 
-	KUNIT_SUCCEED();
+	KUNIT_SUCCEED(test);
 }
 
 /*
@@ -516,7 +516,7 @@ stop:
 			return;
 	}
 
-	KUNIT_SUCCEED();
+	KUNIT_SUCCEED(test);
 }
 
 /*
@@ -596,7 +596,7 @@ static void __init iov_kunit_extract_pages_kvec(struct kunit *test)
 stop:
 	KUNIT_EXPECT_EQ(test, size, 0);
 	KUNIT_EXPECT_EQ(test, iter.count, 0);
-	KUNIT_SUCCEED();
+	KUNIT_SUCCEED(test);
 }
 
 /*
@@ -674,7 +674,7 @@ static void __init iov_kunit_extract_pages_bvec(struct kunit *test)
 stop:
 	KUNIT_EXPECT_EQ(test, size, 0);
 	KUNIT_EXPECT_EQ(test, iter.count, 0);
-	KUNIT_SUCCEED();
+	KUNIT_SUCCEED(test);
 }
 
 /*
@@ -753,7 +753,7 @@ static void __init iov_kunit_extract_pages_xarray(struct kunit *test)
 	}
 
 stop:
-	KUNIT_SUCCEED();
+	KUNIT_SUCCEED(test);
 }
 
 static struct kunit_case __refdata iov_kunit_cases[] = {
diff --git a/lib/math/prime_numbers.c b/lib/math/prime_numbers.c
index d42cebf740..d3b64b10da 100644
--- a/lib/math/prime_numbers.c
+++ b/lib/math/prime_numbers.c
@@ -6,8 +6,6 @@
 #include <linux/prime_numbers.h>
 #include <linux/slab.h>
 
-#define bitmap_size(nbits) (BITS_TO_LONGS(nbits) * sizeof(unsigned long))
-
 struct primes {
 	struct rcu_head rcu;
 	unsigned long last, sz;
diff --git a/lib/memcpy_kunit.c b/lib/memcpy_kunit.c
index fd16e6ce53..20ea9038c3 100644
--- a/lib/memcpy_kunit.c
+++ b/lib/memcpy_kunit.c
@@ -493,58 +493,6 @@ static void memmove_overlap_test(struct kunit *test)
 	}
 }
 
-static void strtomem_test(struct kunit *test)
-{
-	static const char input[sizeof(unsigned long)] = "hi";
-	static const char truncate[] = "this is too long";
-	struct {
-		unsigned long canary1;
-		unsigned char output[sizeof(unsigned long)] __nonstring;
-		unsigned long canary2;
-	} wrap;
-
-	memset(&wrap, 0xFF, sizeof(wrap));
-	KUNIT_EXPECT_EQ_MSG(test, wrap.canary1, ULONG_MAX,
-			    "bad initial canary value");
-	KUNIT_EXPECT_EQ_MSG(test, wrap.canary2, ULONG_MAX,
-			    "bad initial canary value");
-
-	/* Check unpadded copy leaves surroundings untouched. */
-	strtomem(wrap.output, input);
-	KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX);
-	KUNIT_EXPECT_EQ(test, wrap.output[0], input[0]);
-	KUNIT_EXPECT_EQ(test, wrap.output[1], input[1]);
-	for (size_t i = 2; i < sizeof(wrap.output); i++)
-		KUNIT_EXPECT_EQ(test, wrap.output[i], 0xFF);
-	KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX);
-
-	/* Check truncated copy leaves surroundings untouched. */
-	memset(&wrap, 0xFF, sizeof(wrap));
-	strtomem(wrap.output, truncate);
-	KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX);
-	for (size_t i = 0; i < sizeof(wrap.output); i++)
-		KUNIT_EXPECT_EQ(test, wrap.output[i], truncate[i]);
-	KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX);
-
-	/* Check padded copy leaves only string padded. */
-	memset(&wrap, 0xFF, sizeof(wrap));
-	strtomem_pad(wrap.output, input, 0xAA);
-	KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX);
-	KUNIT_EXPECT_EQ(test, wrap.output[0], input[0]);
-	KUNIT_EXPECT_EQ(test, wrap.output[1], input[1]);
-	for (size_t i = 2; i < sizeof(wrap.output); i++)
-		KUNIT_EXPECT_EQ(test, wrap.output[i], 0xAA);
-	KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX);
-
-	/* Check truncated padded copy has no padding. */
-	memset(&wrap, 0xFF, sizeof(wrap));
-	strtomem(wrap.output, truncate);
-	KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX);
-	for (size_t i = 0; i < sizeof(wrap.output); i++)
-		KUNIT_EXPECT_EQ(test, wrap.output[i], truncate[i]);
-	KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX);
-}
-
 static struct kunit_case memcpy_test_cases[] = {
 	KUNIT_CASE(memset_test),
 	KUNIT_CASE(memcpy_test),
@@ -552,7 +500,6 @@ static struct kunit_case memcpy_test_cases[] = {
 	KUNIT_CASE_SLOW(memmove_test),
 	KUNIT_CASE_SLOW(memmove_large_test),
 	KUNIT_CASE_SLOW(memmove_overlap_test),
-	KUNIT_CASE(strtomem_test),
 	{}
 };
 
diff --git a/lib/objagg.c b/lib/objagg.c
index 1e248629ed..1608895b00 100644
--- a/lib/objagg.c
+++ b/lib/objagg.c
@@ -167,6 +167,9 @@ static int objagg_obj_parent_assign(struct objagg *objagg,
 {
 	void *delta_priv;
 
+	if (WARN_ON(!objagg_obj_is_root(parent)))
+		return -EINVAL;
+
 	delta_priv = objagg->ops->delta_create(objagg->priv, parent->obj,
 					       objagg_obj->obj);
 	if (IS_ERR(delta_priv))
@@ -903,20 +906,6 @@ static const struct objagg_opt_algo *objagg_opt_algos[] = {
 	[OBJAGG_OPT_ALGO_SIMPLE_GREEDY] = &objagg_opt_simple_greedy,
 };
 
-static int objagg_hints_obj_cmp(struct rhashtable_compare_arg *arg,
-				const void *obj)
-{
-	struct rhashtable *ht = arg->ht;
-	struct objagg_hints *objagg_hints =
-			container_of(ht, struct objagg_hints, node_ht);
-	const struct objagg_ops *ops = objagg_hints->ops;
-	const char *ptr = obj;
-
-	ptr += ht->p.key_offset;
-	return ops->hints_obj_cmp ? ops->hints_obj_cmp(ptr, arg->key) :
-				    memcmp(ptr, arg->key, ht->p.key_len);
-}
-
 /**
  * objagg_hints_get - obtains hints instance
  * @objagg:		objagg instance
@@ -955,7 +944,6 @@ struct objagg_hints *objagg_hints_get(struct objagg *objagg,
 				offsetof(struct objagg_hints_node, obj);
 	objagg_hints->ht_params.head_offset =
 				offsetof(struct objagg_hints_node, ht_node);
-	objagg_hints->ht_params.obj_cmpfn = objagg_hints_obj_cmp;
 
 	err = rhashtable_init(&objagg_hints->node_ht, &objagg_hints->ht_params);
 	if (err)
diff --git a/lib/objpool.c b/lib/objpool.c
index cfdc024208..234f9d0bd0 100644
--- a/lib/objpool.c
+++ b/lib/objpool.c
@@ -50,7 +50,7 @@ objpool_init_percpu_slots(struct objpool_head *pool, int nr_objs,
 {
 	int i, cpu_count = 0;
 
-	for (i = 0; i < pool->nr_cpus; i++) {
+	for (i = 0; i < nr_cpu_ids; i++) {
 
 		struct objpool_slot *slot;
 		int nodes, size, rc;
@@ -60,8 +60,8 @@ objpool_init_percpu_slots(struct objpool_head *pool, int nr_objs,
 			continue;
 
 		/* compute how many objects to be allocated with this slot */
-		nodes = nr_objs / num_possible_cpus();
-		if (cpu_count < (nr_objs % num_possible_cpus()))
+		nodes = nr_objs / pool->nr_possible_cpus;
+		if (cpu_count < (nr_objs % pool->nr_possible_cpus))
 			nodes++;
 		cpu_count++;
 
@@ -103,7 +103,7 @@ static void objpool_fini_percpu_slots(struct objpool_head *pool)
 	if (!pool->cpu_slots)
 		return;
 
-	for (i = 0; i < pool->nr_cpus; i++)
+	for (i = 0; i < nr_cpu_ids; i++)
 		kvfree(pool->cpu_slots[i]);
 	kfree(pool->cpu_slots);
 }
@@ -130,13 +130,13 @@ int objpool_init(struct objpool_head *pool, int nr_objs, int object_size,
 
 	/* initialize objpool pool */
 	memset(pool, 0, sizeof(struct objpool_head));
-	pool->nr_cpus = nr_cpu_ids;
+	pool->nr_possible_cpus = num_possible_cpus();
 	pool->obj_size = object_size;
 	pool->capacity = capacity;
 	pool->gfp = gfp & ~__GFP_ZERO;
 	pool->context = context;
 	pool->release = release;
-	slot_size = pool->nr_cpus * sizeof(struct objpool_slot);
+	slot_size = nr_cpu_ids * sizeof(struct objpool_slot);
 	pool->cpu_slots = kzalloc(slot_size, pool->gfp);
 	if (!pool->cpu_slots)
 		return -ENOMEM;
@@ -152,106 +152,6 @@ int objpool_init(struct objpool_head *pool, int nr_objs, int object_size,
 }
 EXPORT_SYMBOL_GPL(objpool_init);
 
-/* adding object to slot, abort if the slot was already full */
-static inline int
-objpool_try_add_slot(void *obj, struct objpool_head *pool, int cpu)
-{
-	struct objpool_slot *slot = pool->cpu_slots[cpu];
-	uint32_t head, tail;
-
-	/* loading tail and head as a local snapshot, tail first */
-	tail = READ_ONCE(slot->tail);
-
-	do {
-		head = READ_ONCE(slot->head);
-		/* fault caught: something must be wrong */
-		WARN_ON_ONCE(tail - head > pool->nr_objs);
-	} while (!try_cmpxchg_acquire(&slot->tail, &tail, tail + 1));
-
-	/* now the tail position is reserved for the given obj */
-	WRITE_ONCE(slot->entries[tail & slot->mask], obj);
-	/* update sequence to make this obj available for pop() */
-	smp_store_release(&slot->last, tail + 1);
-
-	return 0;
-}
-
-/* reclaim an object to object pool */
-int objpool_push(void *obj, struct objpool_head *pool)
-{
-	unsigned long flags;
-	int rc;
-
-	/* disable local irq to avoid preemption & interruption */
-	raw_local_irq_save(flags);
-	rc = objpool_try_add_slot(obj, pool, raw_smp_processor_id());
-	raw_local_irq_restore(flags);
-
-	return rc;
-}
-EXPORT_SYMBOL_GPL(objpool_push);
-
-/* try to retrieve object from slot */
-static inline void *objpool_try_get_slot(struct objpool_head *pool, int cpu)
-{
-	struct objpool_slot *slot = pool->cpu_slots[cpu];
-	/* load head snapshot, other cpus may change it */
-	uint32_t head = smp_load_acquire(&slot->head);
-
-	while (head != READ_ONCE(slot->last)) {
-		void *obj;
-
-		/*
-		 * data visibility of 'last' and 'head' could be out of
-		 * order since memory updating of 'last' and 'head' are
-		 * performed in push() and pop() independently
-		 *
-		 * before any retrieving attempts, pop() must guarantee
-		 * 'last' is behind 'head', that is to say, there must
-		 * be available objects in slot, which could be ensured
-		 * by condition 'last != head && last - head <= nr_objs'
-		 * that is equivalent to 'last - head - 1 < nr_objs' as
-		 * 'last' and 'head' are both unsigned int32
-		 */
-		if (READ_ONCE(slot->last) - head - 1 >= pool->nr_objs) {
-			head = READ_ONCE(slot->head);
-			continue;
-		}
-
-		/* obj must be retrieved before moving forward head */
-		obj = READ_ONCE(slot->entries[head & slot->mask]);
-
-		/* move head forward to mark it's consumption */
-		if (try_cmpxchg_release(&slot->head, &head, head + 1))
-			return obj;
-	}
-
-	return NULL;
-}
-
-/* allocate an object from object pool */
-void *objpool_pop(struct objpool_head *pool)
-{
-	void *obj = NULL;
-	unsigned long flags;
-	int i, cpu;
-
-	/* disable local irq to avoid preemption & interruption */
-	raw_local_irq_save(flags);
-
-	cpu = raw_smp_processor_id();
-	for (i = 0; i < num_possible_cpus(); i++) {
-		obj = objpool_try_get_slot(pool, cpu);
-		if (obj)
-			break;
-		cpu = cpumask_next_wrap(cpu, cpu_possible_mask, -1, 1);
-	}
-	raw_local_irq_restore(flags);
-
-	return obj;
-}
-EXPORT_SYMBOL_GPL(objpool_pop);
-
 /* release whole objpool forcely */
 void objpool_free(struct objpool_head *pool)
 {
diff --git a/lib/overflow_kunit.c b/lib/overflow_kunit.c
index 4ef31b0bb7..d305b0c054 100644
--- a/lib/overflow_kunit.c
+++ b/lib/overflow_kunit.c
@@ -1178,14 +1178,28 @@ struct foo {
 	s16 array[] __counted_by(counter);
 };
 
+struct bar {
+	int a;
+	u32 counter;
+	s16 array[];
+};
+
 static void DEFINE_FLEX_test(struct kunit *test)
 {
-	DEFINE_RAW_FLEX(struct foo, two, array, 2);
+	/* Using _RAW_ on a __counted_by struct will initialize "counter" to zero */
+	DEFINE_RAW_FLEX(struct foo, two_but_zero, array, 2);
+#if __has_attribute(__counted_by__)
+	int expected_raw_size = sizeof(struct foo);
+#else
+	int expected_raw_size = sizeof(struct foo) + 2 * sizeof(s16);
+#endif
+	/* Without annotation, it will always be on-stack size. */
+	DEFINE_RAW_FLEX(struct bar, two, array, 2);
 	DEFINE_FLEX(struct foo, eight, array, counter, 8);
 	DEFINE_FLEX(struct foo, empty, array, counter, 0);
 
-	KUNIT_EXPECT_EQ(test, __struct_size(two),
-			sizeof(struct foo) + sizeof(s16) + sizeof(s16));
+	KUNIT_EXPECT_EQ(test, __struct_size(two_but_zero), expected_raw_size);
+	KUNIT_EXPECT_EQ(test, __struct_size(two), sizeof(struct bar) + 2 * sizeof(s16));
 	KUNIT_EXPECT_EQ(test, __struct_size(eight), 24);
 	KUNIT_EXPECT_EQ(test, __struct_size(empty), sizeof(struct foo));
 }
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 385a94aa0b..29127dd05d 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -33,27 +33,8 @@ CFLAGS_REMOVE_vpermxor8.o += -msoft-float
 endif
 endif
 
-# The GCC option -ffreestanding is required in order to compile code containing
-# ARM/NEON intrinsics in a non C99-compliant environment (such as the kernel)
-ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
-NEON_FLAGS := -ffreestanding
-# Enable <arm_neon.h>
-NEON_FLAGS += -isystem $(shell $(CC) -print-file-name=include)
-ifeq ($(ARCH),arm)
-NEON_FLAGS += -march=armv7-a -mfloat-abi=softfp -mfpu=neon
-endif
-CFLAGS_recov_neon_inner.o += $(NEON_FLAGS)
-ifeq ($(ARCH),arm64)
-CFLAGS_REMOVE_recov_neon_inner.o += -mgeneral-regs-only
-CFLAGS_REMOVE_neon1.o += -mgeneral-regs-only
-CFLAGS_REMOVE_neon2.o += -mgeneral-regs-only
-CFLAGS_REMOVE_neon4.o += -mgeneral-regs-only
-CFLAGS_REMOVE_neon8.o += -mgeneral-regs-only
-endif
-endif
-
 quiet_cmd_unroll = UNROLL  $@
-      cmd_unroll = $(AWK) -v N=$* -f $(srctree)/$(src)/unroll.awk < $< > $@
+      cmd_unroll = $(AWK) -v N=$* -f $(src)/unroll.awk < $< > $@
 
 targets += int1.c int2.c int4.c int8.c
 $(obj)/int%.c: $(src)/int.uc $(src)/unroll.awk FORCE
@@ -75,10 +56,16 @@ targets += vpermxor1.c vpermxor2.c vpermxor4.c vpermxor8.c
 $(obj)/vpermxor%.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE
 	$(call if_changed,unroll)
 
-CFLAGS_neon1.o += $(NEON_FLAGS)
-CFLAGS_neon2.o += $(NEON_FLAGS)
-CFLAGS_neon4.o += $(NEON_FLAGS)
-CFLAGS_neon8.o += $(NEON_FLAGS)
+CFLAGS_neon1.o += $(CC_FLAGS_FPU)
+CFLAGS_neon2.o += $(CC_FLAGS_FPU)
+CFLAGS_neon4.o += $(CC_FLAGS_FPU)
+CFLAGS_neon8.o += $(CC_FLAGS_FPU)
+CFLAGS_recov_neon_inner.o += $(CC_FLAGS_FPU)
+CFLAGS_REMOVE_neon1.o += $(CC_FLAGS_NO_FPU)
+CFLAGS_REMOVE_neon2.o += $(CC_FLAGS_NO_FPU)
+CFLAGS_REMOVE_neon4.o += $(CC_FLAGS_NO_FPU)
+CFLAGS_REMOVE_neon8.o += $(CC_FLAGS_NO_FPU)
+CFLAGS_REMOVE_recov_neon_inner.o += $(CC_FLAGS_NO_FPU)
 targets += neon1.c neon2.c neon4.c neon8.c
 $(obj)/neon%.c: $(src)/neon.uc $(src)/unroll.awk FORCE
 	$(call if_changed,unroll)
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 6ae2ba8e06..dbbed19f8f 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -130,7 +130,8 @@ static union nested_table *nested_table_alloc(struct rhashtable *ht,
 	if (ntbl)
 		return ntbl;
 
-	ntbl = kzalloc(PAGE_SIZE, GFP_ATOMIC);
+	ntbl = alloc_hooks_tag(ht->alloc_tag,
+			kmalloc_noprof(PAGE_SIZE, GFP_ATOMIC|__GFP_ZERO));
 
 	if (ntbl && leaf) {
 		for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0]); i++)
@@ -157,7 +158,8 @@ static struct bucket_table *nested_bucket_table_alloc(struct rhashtable *ht,
 
 	size = sizeof(*tbl) + sizeof(tbl->buckets[0]);
 
-	tbl = kzalloc(size, gfp);
+	tbl = alloc_hooks_tag(ht->alloc_tag,
+			kmalloc_noprof(size, gfp|__GFP_ZERO));
 	if (!tbl)
 		return NULL;
 
@@ -181,7 +183,9 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
 	int i;
 	static struct lock_class_key __key;
 
-	tbl = kvzalloc(struct_size(tbl, buckets, nbuckets), gfp);
+	tbl = alloc_hooks_tag(ht->alloc_tag,
+			kvmalloc_node_noprof(struct_size(tbl, buckets, nbuckets),
+					     gfp|__GFP_ZERO, NUMA_NO_NODE));
 
 	size = nbuckets;
 
@@ -1016,7 +1020,7 @@ static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed)
  *	.obj_hashfn = my_hash_fn,
  * };
  */
-int rhashtable_init(struct rhashtable *ht,
+int rhashtable_init_noprof(struct rhashtable *ht,
 		    const struct rhashtable_params *params)
 {
 	struct bucket_table *tbl;
@@ -1031,6 +1035,8 @@ int rhashtable_init(struct rhashtable *ht,
 	spin_lock_init(&ht->lock);
 	memcpy(&ht->p, params, sizeof(*params));
 
+	alloc_tag_record(ht->alloc_tag);
+
 	if (params->min_size)
 		ht->p.min_size = roundup_pow_of_two(params->min_size);
 
@@ -1076,7 +1082,7 @@ int rhashtable_init(struct rhashtable *ht,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(rhashtable_init);
+EXPORT_SYMBOL_GPL(rhashtable_init_noprof);
 
 /**
  * rhltable_init - initialize a new hash list table
@@ -1087,15 +1093,15 @@ EXPORT_SYMBOL_GPL(rhashtable_init);
  *
  * See documentation for rhashtable_init.
  */
-int rhltable_init(struct rhltable *hlt, const struct rhashtable_params *params)
+int rhltable_init_noprof(struct rhltable *hlt, const struct rhashtable_params *params)
 {
 	int err;
 
-	err = rhashtable_init(&hlt->ht, params);
+	err = rhashtable_init_noprof(&hlt->ht, params);
 	hlt->ht.rhlist = true;
 	return err;
 }
-EXPORT_SYMBOL_GPL(rhltable_init);
+EXPORT_SYMBOL_GPL(rhltable_init_noprof);
 
 static void rhashtable_free_one(struct rhashtable *ht, struct rhash_head *obj,
 				void (*free_fn)(void *ptr, void *arg),
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 92c6b1fd89..5e2e93307f 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -60,12 +60,30 @@ static inline void update_alloc_hint_after_get(struct sbitmap *sb,
 /*
  * See if we have deferred clears that we can batch move
  */
-static inline bool sbitmap_deferred_clear(struct sbitmap_word *map)
+static inline bool sbitmap_deferred_clear(struct sbitmap_word *map,
+		unsigned int depth, unsigned int alloc_hint, bool wrap)
 {
-	unsigned long mask;
+	unsigned long mask, word_mask;
 
-	if (!READ_ONCE(map->cleared))
-		return false;
+	guard(spinlock_irqsave)(&map->swap_lock);
+
+	if (!map->cleared) {
+		if (depth == 0)
+			return false;
+
+		word_mask = (~0UL) >> (BITS_PER_LONG - depth);
+		/*
+		 * The current behavior is to always retry after moving
+		 * ->cleared to word, and we change it to retry in case
+		 * of any free bits. To avoid an infinite loop, we need
+		 * to take wrap & alloc_hint into account, otherwise a
+		 * soft lockup may occur.
+		 */
+		if (!wrap && alloc_hint)
+			word_mask &= ~((1UL << alloc_hint) - 1);
+
+		return (READ_ONCE(map->word) & word_mask) != word_mask;
+	}
 
 	/*
 	 * First get a stable cleared mask, setting the old mask to 0.
@@ -85,6 +103,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
 		      bool alloc_hint)
 {
 	unsigned int bits_per_word;
+	int i;
 
 	if (shift < 0)
 		shift = sbitmap_calculate_shift(depth);
@@ -116,6 +135,9 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
 		return -ENOMEM;
 	}
 
+	for (i = 0; i < sb->map_nr; i++)
+		spin_lock_init(&sb->map[i].swap_lock);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(sbitmap_init_node);
@@ -126,7 +148,7 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth)
 	unsigned int i;
 
 	for (i = 0; i < sb->map_nr; i++)
-		sbitmap_deferred_clear(&sb->map[i]);
+		sbitmap_deferred_clear(&sb->map[i], 0, 0, 0);
 
 	sb->depth = depth;
 	sb->map_nr = DIV_ROUND_UP(sb->depth, bits_per_word);
@@ -179,7 +201,7 @@ static int sbitmap_find_bit_in_word(struct sbitmap_word *map,
 					alloc_hint, wrap);
 		if (nr != -1)
 			break;
-		if (!sbitmap_deferred_clear(map))
+		if (!sbitmap_deferred_clear(map, depth, alloc_hint, wrap))
 			break;
 	} while (1);
 
@@ -494,18 +516,18 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
 		struct sbitmap_word *map = &sb->map[index];
 		unsigned long get_mask;
 		unsigned int map_depth = __map_depth(sb, index);
+		unsigned long val;
 
-		sbitmap_deferred_clear(map);
-		if (map->word == (1UL << (map_depth - 1)) - 1)
+		sbitmap_deferred_clear(map, 0, 0, 0);
+		val = READ_ONCE(map->word);
+		if (val == (1UL << (map_depth - 1)) - 1)
 			goto next;
 
-		nr = find_first_zero_bit(&map->word, map_depth);
+		nr = find_first_zero_bit(&val, map_depth);
 		if (nr + nr_tags <= map_depth) {
 			atomic_long_t *ptr = (atomic_long_t *) &map->word;
-			unsigned long val;
 
 			get_mask = ((1UL << nr_tags) - 1) << nr;
-			val = READ_ONCE(map->word);
 			while (!atomic_long_try_cmpxchg(ptr, &val,
 							  get_mask | val))
 				;
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index cd8f234552..5ed34cc963 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -624,15 +624,8 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 	 * we won't be able to do that under the lock.
 	 */
 	if (unlikely(can_alloc && !READ_ONCE(new_pool))) {
-		/*
-		 * Zero out zone modifiers, as we don't have specific zone
-		 * requirements. Keep the flags related to allocation in atomic
-		 * contexts, I/O, nolockdep.
-		 */
-		alloc_flags &= ~GFP_ZONEMASK;
-		alloc_flags &= (GFP_ATOMIC | GFP_KERNEL | __GFP_NOLOCKDEP);
-		alloc_flags |= __GFP_NOWARN;
-		page = alloc_pages(alloc_flags, DEPOT_POOL_ORDER);
+		page = alloc_pages(gfp_nested_mask(alloc_flags),
+				   DEPOT_POOL_ORDER);
 		if (page)
 			prealloc = page_address(page);
 	}
diff --git a/lib/strcat_kunit.c b/lib/strcat_kunit.c
deleted file mode 100644
index ca09f7f0e6..0000000000
--- a/lib/strcat_kunit.c
+++ /dev/null
@@ -1,104 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Kernel module for testing 'strcat' family of functions.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <kunit/test.h>
-#include <linux/string.h>
-
-static volatile int unconst;
-
-static void test_strcat(struct kunit *test)
-{
-	char dest[8];
-
-	/* Destination is terminated. */
-	memset(dest, 0, sizeof(dest));
-	KUNIT_EXPECT_EQ(test, strlen(dest), 0);
-	/* Empty copy does nothing. */
-	KUNIT_EXPECT_TRUE(test, strcat(dest, "") == dest);
-	KUNIT_EXPECT_STREQ(test, dest, "");
-	/* 4 characters copied in, stops at %NUL. */
-	KUNIT_EXPECT_TRUE(test, strcat(dest, "four\000123") == dest);
-	KUNIT_EXPECT_STREQ(test, dest, "four");
-	KUNIT_EXPECT_EQ(test, dest[5], '\0');
-	/* 2 more characters copied in okay. */
-	KUNIT_EXPECT_TRUE(test, strcat(dest, "AB") == dest);
-	KUNIT_EXPECT_STREQ(test, dest, "fourAB");
-}
-
-static void test_strncat(struct kunit *test)
-{
-	char dest[8];
-
-	/* Destination is terminated. */
-	memset(dest, 0, sizeof(dest));
-	KUNIT_EXPECT_EQ(test, strlen(dest), 0);
-	/* Empty copy of size 0 does nothing. */
-	KUNIT_EXPECT_TRUE(test, strncat(dest, "", 0 + unconst) == dest);
-	KUNIT_EXPECT_STREQ(test, dest, "");
-	/* Empty copy of size 1 does nothing too. */
-	KUNIT_EXPECT_TRUE(test, strncat(dest, "", 1 + unconst) == dest);
-	KUNIT_EXPECT_STREQ(test, dest, "");
-	/* Copy of max 0 characters should do nothing. */
-	KUNIT_EXPECT_TRUE(test, strncat(dest, "asdf", 0 + unconst) == dest);
-	KUNIT_EXPECT_STREQ(test, dest, "");
-
-	/* 4 characters copied in, even if max is 8. */
-	KUNIT_EXPECT_TRUE(test, strncat(dest, "four\000123", 8 + unconst) == dest);
-	KUNIT_EXPECT_STREQ(test, dest, "four");
-	KUNIT_EXPECT_EQ(test, dest[5], '\0');
-	KUNIT_EXPECT_EQ(test, dest[6], '\0');
-	/* 2 characters copied in okay, 2 ignored. */
-	KUNIT_EXPECT_TRUE(test, strncat(dest, "ABCD", 2 + unconst) == dest);
-	KUNIT_EXPECT_STREQ(test, dest, "fourAB");
-}
-
-static void test_strlcat(struct kunit *test)
-{
-	char dest[8] = "";
-	int len = sizeof(dest) + unconst;
-
-	/* Destination is terminated. */
-	KUNIT_EXPECT_EQ(test, strlen(dest), 0);
-	/* Empty copy is size 0. */
-	KUNIT_EXPECT_EQ(test, strlcat(dest, "", len), 0);
-	KUNIT_EXPECT_STREQ(test, dest, "");
-	/* Size 1 should keep buffer terminated, report size of source only. */
-	KUNIT_EXPECT_EQ(test, strlcat(dest, "four", 1 + unconst), 4);
-	KUNIT_EXPECT_STREQ(test, dest, "");
-
-	/* 4 characters copied in. */
-	KUNIT_EXPECT_EQ(test, strlcat(dest, "four", len), 4);
-	KUNIT_EXPECT_STREQ(test, dest, "four");
-	/* 2 characters copied in okay, gets to 6 total. */
-	KUNIT_EXPECT_EQ(test, strlcat(dest, "AB", len), 6);
-	KUNIT_EXPECT_STREQ(test, dest, "fourAB");
-	/* 2 characters ignored if max size (7) reached. */
-	KUNIT_EXPECT_EQ(test, strlcat(dest, "CD", 7 + unconst), 8);
-	KUNIT_EXPECT_STREQ(test, dest, "fourAB");
-	/* 1 of 2 characters skipped, now at true max size. */
-	KUNIT_EXPECT_EQ(test, strlcat(dest, "EFG", len), 9);
-	KUNIT_EXPECT_STREQ(test, dest, "fourABE");
-	/* Everything else ignored, now at full size. */
-	KUNIT_EXPECT_EQ(test, strlcat(dest, "1234", len), 11);
-	KUNIT_EXPECT_STREQ(test, dest, "fourABE");
-}
-
-static struct kunit_case strcat_test_cases[] = {
-	KUNIT_CASE(test_strcat),
-	KUNIT_CASE(test_strncat),
-	KUNIT_CASE(test_strlcat),
-	{}
-};
-
-static struct kunit_suite strcat_test_suite = {
-	.name = "strcat",
-	.test_cases = strcat_test_cases,
-};
-
-kunit_test_suite(strcat_test_suite);
-
-MODULE_LICENSE("GPL");
diff --git a/lib/string_helpers_kunit.c b/lib/string_helpers_kunit.c
index f88e39fd68..c853046183 100644
--- a/lib/string_helpers_kunit.c
+++ b/lib/string_helpers_kunit.c
@@ -625,4 +625,5 @@ static struct kunit_suite string_helpers_test_suite = {
 
 kunit_test_suites(&string_helpers_test_suite);
 
+MODULE_DESCRIPTION("Test cases for string helpers module");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/lib/string_kunit.c b/lib/string_kunit.c
index dd19bd7748..c919e3293d 100644
--- a/lib/string_kunit.c
+++ b/lib/string_kunit.c
@@ -17,7 +17,7 @@
 #define STRCMP_TEST_EXPECT_LOWER(test, fn, ...) KUNIT_EXPECT_LT(test, fn(__VA_ARGS__), 0)
 #define STRCMP_TEST_EXPECT_GREATER(test, fn, ...) KUNIT_EXPECT_GT(test, fn(__VA_ARGS__), 0)
 
-static void test_memset16(struct kunit *test)
+static void string_test_memset16(struct kunit *test)
 {
 	unsigned i, j, k;
 	u16 v, *p;
@@ -46,7 +46,7 @@ static void test_memset16(struct kunit *test)
 	}
 }
 
-static void test_memset32(struct kunit *test)
+static void string_test_memset32(struct kunit *test)
 {
 	unsigned i, j, k;
 	u32 v, *p;
@@ -75,7 +75,7 @@ static void test_memset32(struct kunit *test)
 	}
 }
 
-static void test_memset64(struct kunit *test)
+static void string_test_memset64(struct kunit *test)
 {
 	unsigned i, j, k;
 	u64 v, *p;
@@ -104,7 +104,7 @@ static void test_memset64(struct kunit *test)
 	}
 }
 
-static void test_strchr(struct kunit *test)
+static void string_test_strchr(struct kunit *test)
 {
 	const char *test_string = "abcdefghijkl";
 	const char *empty_string = "";
@@ -127,7 +127,7 @@ static void test_strchr(struct kunit *test)
 	KUNIT_ASSERT_NULL(test, result);
 }
 
-static void test_strnchr(struct kunit *test)
+static void string_test_strnchr(struct kunit *test)
 {
 	const char *test_string = "abcdefghijkl";
 	const char *empty_string = "";
@@ -160,7 +160,7 @@ static void test_strnchr(struct kunit *test)
 	KUNIT_ASSERT_NULL(test, result);
 }
 
-static void test_strspn(struct kunit *test)
+static void string_test_strspn(struct kunit *test)
 {
 	static const struct strspn_test {
 		const char str[16];
@@ -196,7 +196,7 @@ static void strcmp_fill_buffers(char fill1, char fill2)
 	strcmp_buffer2[STRCMP_LARGE_BUF_LEN - 1] = 0;
 }
 
-static void test_strcmp(struct kunit *test)
+static void string_test_strcmp(struct kunit *test)
 {
 	/* Equal strings */
 	STRCMP_TEST_EXPECT_EQUAL(test, strcmp, "Hello, Kernel!", "Hello, Kernel!");
@@ -214,7 +214,7 @@ static void test_strcmp(struct kunit *test)
 	STRCMP_TEST_EXPECT_LOWER(test, strcmp, "Just a string", "Just a string and something else");
 }
 
-static void test_strcmp_long_strings(struct kunit *test)
+static void string_test_strcmp_long_strings(struct kunit *test)
 {
 	strcmp_fill_buffers('B', 'B');
 	STRCMP_TEST_EXPECT_EQUAL(test, strcmp, strcmp_buffer1, strcmp_buffer2);
@@ -226,7 +226,7 @@ static void test_strcmp_long_strings(struct kunit *test)
 	STRCMP_TEST_EXPECT_GREATER(test, strcmp, strcmp_buffer1, strcmp_buffer2);
 }
 
-static void test_strncmp(struct kunit *test)
+static void string_test_strncmp(struct kunit *test)
 {
 	/* Equal strings */
 	STRCMP_TEST_EXPECT_EQUAL(test, strncmp, "Hello, KUnit!", "Hello, KUnit!", 13);
@@ -249,7 +249,7 @@ static void test_strncmp(struct kunit *test)
 				 strlen("Just a string"));
 }
 
-static void test_strncmp_long_strings(struct kunit *test)
+static void string_test_strncmp_long_strings(struct kunit *test)
 {
 	strcmp_fill_buffers('B', 'B');
 	STRCMP_TEST_EXPECT_EQUAL(test, strncmp, strcmp_buffer1,
@@ -269,7 +269,7 @@ static void test_strncmp_long_strings(struct kunit *test)
 				   strcmp_buffer2, STRCMP_CHANGE_POINT + 1);
 }
 
-static void test_strcasecmp(struct kunit *test)
+static void string_test_strcasecmp(struct kunit *test)
 {
 	/* Same strings in different case should be equal */
 	STRCMP_TEST_EXPECT_EQUAL(test, strcasecmp, "Hello, Kernel!", "HeLLO, KErNeL!");
@@ -282,7 +282,7 @@ static void test_strcasecmp(struct kunit *test)
 	STRCMP_TEST_EXPECT_EQUAL(test, strcasecmp, "-+**.1230ghTTT~^", "-+**.1230Ghttt~^");
 }
 
-static void test_strcasecmp_long_strings(struct kunit *test)
+static void string_test_strcasecmp_long_strings(struct kunit *test)
 {
 	strcmp_fill_buffers('b', 'B');
 	STRCMP_TEST_EXPECT_EQUAL(test, strcasecmp, strcmp_buffer1, strcmp_buffer2);
@@ -294,7 +294,7 @@ static void test_strcasecmp_long_strings(struct kunit *test)
 	STRCMP_TEST_EXPECT_GREATER(test, strcasecmp, strcmp_buffer1, strcmp_buffer2);
 }
 
-static void test_strncasecmp(struct kunit *test)
+static void string_test_strncasecmp(struct kunit *test)
 {
 	/* Same strings in different case should be equal */
 	STRCMP_TEST_EXPECT_EQUAL(test, strncasecmp, "AbAcAbA", "Abacaba", strlen("Abacaba"));
@@ -306,7 +306,7 @@ static void test_strncasecmp(struct kunit *test)
 	STRCMP_TEST_EXPECT_EQUAL(test, strncasecmp, "Abacaba", "Not abacaba", 0);
 }
 
-static void test_strncasecmp_long_strings(struct kunit *test)
+static void string_test_strncasecmp_long_strings(struct kunit *test)
 {
 	strcmp_fill_buffers('b', 'B');
 	STRCMP_TEST_EXPECT_EQUAL(test, strncasecmp, strcmp_buffer1,
@@ -326,21 +326,303 @@ static void test_strncasecmp_long_strings(struct kunit *test)
 				   strcmp_buffer2, STRCMP_CHANGE_POINT + 1);
 }
 
+/**
+ * strscpy_check() - Run a specific test case.
+ * @test: KUnit test context pointer
+ * @src: Source string, argument to strscpy_pad()
+ * @count: Size of destination buffer, argument to strscpy_pad()
+ * @expected: Expected return value from call to strscpy_pad()
+ * @chars: Number of characters from the src string expected to be
+ *         written to the dst buffer.
+ * @terminator: 1 if there should be a terminating null byte 0 otherwise.
+ * @pad: Number of pad characters expected (in the tail of dst buffer).
+ *       (@pad does not include the null terminator byte.)
+ *
+ * Calls strscpy_pad() and verifies the return value and state of the
+ * destination buffer after the call returns.
+ */
+static void strscpy_check(struct kunit *test, char *src, int count,
+			  int expected, int chars, int terminator, int pad)
+{
+	int nr_bytes_poison;
+	int max_expected;
+	int max_count;
+	int written;
+	char buf[6];
+	int index, i;
+	const char POISON = 'z';
+
+	KUNIT_ASSERT_TRUE_MSG(test, src != NULL,
+			      "null source string not supported");
+
+	memset(buf, POISON, sizeof(buf));
+	/* Future proofing test suite, validate args */
+	max_count = sizeof(buf) - 2; /* Space for null and to verify overflow */
+	max_expected = count - 1;    /* Space for the null */
+
+	KUNIT_ASSERT_LE_MSG(test, count, max_count,
+		"count (%d) is too big (%d) ... aborting", count, max_count);
+	KUNIT_EXPECT_LE_MSG(test, expected, max_expected,
+		"expected (%d) is bigger than can possibly be returned (%d)",
+		expected, max_expected);
+
+	written = strscpy_pad(buf, src, count);
+	KUNIT_ASSERT_EQ(test, written, expected);
+
+	if (count && written == -E2BIG) {
+		KUNIT_ASSERT_EQ_MSG(test, 0, strncmp(buf, src, count - 1),
+			"buffer state invalid for -E2BIG");
+		KUNIT_ASSERT_EQ_MSG(test, buf[count - 1], '\0',
+			"too big string is not null terminated correctly");
+	}
+
+	for (i = 0; i < chars; i++)
+		KUNIT_ASSERT_EQ_MSG(test, buf[i], src[i],
+			"buf[i]==%c != src[i]==%c", buf[i], src[i]);
+
+	if (terminator)
+		KUNIT_ASSERT_EQ_MSG(test, buf[count - 1], '\0',
+			"string is not null terminated correctly");
+
+	for (i = 0; i < pad; i++) {
+		index = chars + terminator + i;
+		KUNIT_ASSERT_EQ_MSG(test, buf[index], '\0',
+			"padding missing at index: %d", i);
+	}
+
+	nr_bytes_poison = sizeof(buf) - chars - terminator - pad;
+	for (i = 0; i < nr_bytes_poison; i++) {
+		index = sizeof(buf) - 1 - i; /* Check from the end back */
+		KUNIT_ASSERT_EQ_MSG(test, buf[index], POISON,
+			"poison value missing at index: %d", i);
+	}
+}
+
+static void string_test_strscpy(struct kunit *test)
+{
+	char dest[8];
+
+	/*
+	 * strscpy_check() uses a destination buffer of size 6 and needs at
+	 * least 2 characters spare (one for null and one to check for
+	 * overflow).  This means we should only call tc() with
+	 * strings up to a maximum of 4 characters long and 'count'
+	 * should not exceed 4.  To test with longer strings increase
+	 * the buffer size in tc().
+	 */
+
+	/* strscpy_check(test, src, count, expected, chars, terminator, pad) */
+	strscpy_check(test, "a", 0, -E2BIG, 0, 0, 0);
+	strscpy_check(test, "",  0, -E2BIG, 0, 0, 0);
+
+	strscpy_check(test, "a", 1, -E2BIG, 0, 1, 0);
+	strscpy_check(test, "",  1, 0,	 0, 1, 0);
+
+	strscpy_check(test, "ab", 2, -E2BIG, 1, 1, 0);
+	strscpy_check(test, "a",  2, 1,	  1, 1, 0);
+	strscpy_check(test, "",   2, 0,	  0, 1, 1);
+
+	strscpy_check(test, "abc", 3, -E2BIG, 2, 1, 0);
+	strscpy_check(test, "ab",  3, 2,	   2, 1, 0);
+	strscpy_check(test, "a",   3, 1,	   1, 1, 1);
+	strscpy_check(test, "",    3, 0,	   0, 1, 2);
+
+	strscpy_check(test, "abcd", 4, -E2BIG, 3, 1, 0);
+	strscpy_check(test, "abc",  4, 3,	    3, 1, 0);
+	strscpy_check(test, "ab",   4, 2,	    2, 1, 1);
+	strscpy_check(test, "a",    4, 1,	    1, 1, 2);
+	strscpy_check(test, "",     4, 0,	    0, 1, 3);
+
+	/* Compile-time-known source strings. */
+	KUNIT_EXPECT_EQ(test, strscpy(dest, "", ARRAY_SIZE(dest)), 0);
+	KUNIT_EXPECT_EQ(test, strscpy(dest, "", 3), 0);
+	KUNIT_EXPECT_EQ(test, strscpy(dest, "", 1), 0);
+	KUNIT_EXPECT_EQ(test, strscpy(dest, "", 0), -E2BIG);
+	KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", ARRAY_SIZE(dest)), 5);
+	KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", 3), -E2BIG);
+	KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", 1), -E2BIG);
+	KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", 0), -E2BIG);
+	KUNIT_EXPECT_EQ(test, strscpy(dest, "This is too long", ARRAY_SIZE(dest)), -E2BIG);
+}
+
+static volatile int unconst;
+
+static void string_test_strcat(struct kunit *test)
+{
+	char dest[8];
+
+	/* Destination is terminated. */
+	memset(dest, 0, sizeof(dest));
+	KUNIT_EXPECT_EQ(test, strlen(dest), 0);
+	/* Empty copy does nothing. */
+	KUNIT_EXPECT_TRUE(test, strcat(dest, "") == dest);
+	KUNIT_EXPECT_STREQ(test, dest, "");
+	/* 4 characters copied in, stops at %NUL. */
+	KUNIT_EXPECT_TRUE(test, strcat(dest, "four\000123") == dest);
+	KUNIT_EXPECT_STREQ(test, dest, "four");
+	KUNIT_EXPECT_EQ(test, dest[5], '\0');
+	/* 2 more characters copied in okay. */
+	KUNIT_EXPECT_TRUE(test, strcat(dest, "AB") == dest);
+	KUNIT_EXPECT_STREQ(test, dest, "fourAB");
+}
+
+static void string_test_strncat(struct kunit *test)
+{
+	char dest[8];
+
+	/* Destination is terminated. */
+	memset(dest, 0, sizeof(dest));
+	KUNIT_EXPECT_EQ(test, strlen(dest), 0);
+	/* Empty copy of size 0 does nothing. */
+	KUNIT_EXPECT_TRUE(test, strncat(dest, "", 0 + unconst) == dest);
+	KUNIT_EXPECT_STREQ(test, dest, "");
+	/* Empty copy of size 1 does nothing too. */
+	KUNIT_EXPECT_TRUE(test, strncat(dest, "", 1 + unconst) == dest);
+	KUNIT_EXPECT_STREQ(test, dest, "");
+	/* Copy of max 0 characters should do nothing. */
+	KUNIT_EXPECT_TRUE(test, strncat(dest, "asdf", 0 + unconst) == dest);
+	KUNIT_EXPECT_STREQ(test, dest, "");
+
+	/* 4 characters copied in, even if max is 8. */
+	KUNIT_EXPECT_TRUE(test, strncat(dest, "four\000123", 8 + unconst) == dest);
+	KUNIT_EXPECT_STREQ(test, dest, "four");
+	KUNIT_EXPECT_EQ(test, dest[5], '\0');
+	KUNIT_EXPECT_EQ(test, dest[6], '\0');
+	/* 2 characters copied in okay, 2 ignored. */
+	KUNIT_EXPECT_TRUE(test, strncat(dest, "ABCD", 2 + unconst) == dest);
+	KUNIT_EXPECT_STREQ(test, dest, "fourAB");
+}
+
+static void string_test_strlcat(struct kunit *test)
+{
+	char dest[8] = "";
+	int len = sizeof(dest) + unconst;
+
+	/* Destination is terminated. */
+	KUNIT_EXPECT_EQ(test, strlen(dest), 0);
+	/* Empty copy is size 0. */
+	KUNIT_EXPECT_EQ(test, strlcat(dest, "", len), 0);
+	KUNIT_EXPECT_STREQ(test, dest, "");
+	/* Size 1 should keep buffer terminated, report size of source only. */
+	KUNIT_EXPECT_EQ(test, strlcat(dest, "four", 1 + unconst), 4);
+	KUNIT_EXPECT_STREQ(test, dest, "");
+
+	/* 4 characters copied in. */
+	KUNIT_EXPECT_EQ(test, strlcat(dest, "four", len), 4);
+	KUNIT_EXPECT_STREQ(test, dest, "four");
+	/* 2 characters copied in okay, gets to 6 total. */
+	KUNIT_EXPECT_EQ(test, strlcat(dest, "AB", len), 6);
+	KUNIT_EXPECT_STREQ(test, dest, "fourAB");
+	/* 2 characters ignored if max size (7) reached. */
+	KUNIT_EXPECT_EQ(test, strlcat(dest, "CD", 7 + unconst), 8);
+	KUNIT_EXPECT_STREQ(test, dest, "fourAB");
+	/* 1 of 2 characters skipped, now at true max size. */
+	KUNIT_EXPECT_EQ(test, strlcat(dest, "EFG", len), 9);
+	KUNIT_EXPECT_STREQ(test, dest, "fourABE");
+	/* Everything else ignored, now at full size. */
+	KUNIT_EXPECT_EQ(test, strlcat(dest, "1234", len), 11);
+	KUNIT_EXPECT_STREQ(test, dest, "fourABE");
+}
+
+static void string_test_strtomem(struct kunit *test)
+{
+	static const char input[sizeof(unsigned long)] = "hi";
+	static const char truncate[] = "this is too long";
+	struct {
+		unsigned long canary1;
+		unsigned char output[sizeof(unsigned long)] __nonstring;
+		unsigned long canary2;
+	} wrap;
+
+	memset(&wrap, 0xFF, sizeof(wrap));
+	KUNIT_EXPECT_EQ_MSG(test, wrap.canary1, ULONG_MAX,
+			    "bad initial canary value");
+	KUNIT_EXPECT_EQ_MSG(test, wrap.canary2, ULONG_MAX,
+			    "bad initial canary value");
+
+	/* Check unpadded copy leaves surroundings untouched. */
+	strtomem(wrap.output, input);
+	KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX);
+	KUNIT_EXPECT_EQ(test, wrap.output[0], input[0]);
+	KUNIT_EXPECT_EQ(test, wrap.output[1], input[1]);
+	for (size_t i = 2; i < sizeof(wrap.output); i++)
+		KUNIT_EXPECT_EQ(test, wrap.output[i], 0xFF);
+	KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX);
+
+	/* Check truncated copy leaves surroundings untouched. */
+	memset(&wrap, 0xFF, sizeof(wrap));
+	strtomem(wrap.output, truncate);
+	KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX);
+	for (size_t i = 0; i < sizeof(wrap.output); i++)
+		KUNIT_EXPECT_EQ(test, wrap.output[i], truncate[i]);
+	KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX);
+
+	/* Check padded copy leaves only string padded. */
+	memset(&wrap, 0xFF, sizeof(wrap));
+	strtomem_pad(wrap.output, input, 0xAA);
+	KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX);
+	KUNIT_EXPECT_EQ(test, wrap.output[0], input[0]);
+	KUNIT_EXPECT_EQ(test, wrap.output[1], input[1]);
+	for (size_t i = 2; i < sizeof(wrap.output); i++)
+		KUNIT_EXPECT_EQ(test, wrap.output[i], 0xAA);
+	KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX);
+
+	/* Check truncated padded copy has no padding. */
+	memset(&wrap, 0xFF, sizeof(wrap));
+	strtomem(wrap.output, truncate);
+	KUNIT_EXPECT_EQ(test, wrap.canary1, ULONG_MAX);
+	for (size_t i = 0; i < sizeof(wrap.output); i++)
+		KUNIT_EXPECT_EQ(test, wrap.output[i], truncate[i]);
+	KUNIT_EXPECT_EQ(test, wrap.canary2, ULONG_MAX);
+}
+
+
+static void string_test_memtostr(struct kunit *test)
+{
+	char nonstring[7] = { 'a', 'b', 'c', 'd', 'e', 'f', 'g' };
+	char nonstring_small[3] = { 'a', 'b', 'c' };
+	char dest[sizeof(nonstring) + 1];
+
+	/* Copy in a non-NUL-terminated string into exactly right-sized dest. */
+	KUNIT_EXPECT_EQ(test, sizeof(dest), sizeof(nonstring) + 1);
+	memset(dest, 'X', sizeof(dest));
+	memtostr(dest, nonstring);
+	KUNIT_EXPECT_STREQ(test, dest, "abcdefg");
+	memset(dest, 'X', sizeof(dest));
+	memtostr(dest, nonstring_small);
+	KUNIT_EXPECT_STREQ(test, dest, "abc");
+	KUNIT_EXPECT_EQ(test, dest[7], 'X');
+
+	memset(dest, 'X', sizeof(dest));
+	memtostr_pad(dest, nonstring);
+	KUNIT_EXPECT_STREQ(test, dest, "abcdefg");
+	memset(dest, 'X', sizeof(dest));
+	memtostr_pad(dest, nonstring_small);
+	KUNIT_EXPECT_STREQ(test, dest, "abc");
+	KUNIT_EXPECT_EQ(test, dest[7], '\0');
+}
+
 static struct kunit_case string_test_cases[] = {
-	KUNIT_CASE(test_memset16),
-	KUNIT_CASE(test_memset32),
-	KUNIT_CASE(test_memset64),
-	KUNIT_CASE(test_strchr),
-	KUNIT_CASE(test_strnchr),
-	KUNIT_CASE(test_strspn),
-	KUNIT_CASE(test_strcmp),
-	KUNIT_CASE(test_strcmp_long_strings),
-	KUNIT_CASE(test_strncmp),
-	KUNIT_CASE(test_strncmp_long_strings),
-	KUNIT_CASE(test_strcasecmp),
-	KUNIT_CASE(test_strcasecmp_long_strings),
-	KUNIT_CASE(test_strncasecmp),
-	KUNIT_CASE(test_strncasecmp_long_strings),
+	KUNIT_CASE(string_test_memset16),
+	KUNIT_CASE(string_test_memset32),
+	KUNIT_CASE(string_test_memset64),
+	KUNIT_CASE(string_test_strchr),
+	KUNIT_CASE(string_test_strnchr),
+	KUNIT_CASE(string_test_strspn),
+	KUNIT_CASE(string_test_strcmp),
+	KUNIT_CASE(string_test_strcmp_long_strings),
+	KUNIT_CASE(string_test_strncmp),
+	KUNIT_CASE(string_test_strncmp_long_strings),
+	KUNIT_CASE(string_test_strcasecmp),
+	KUNIT_CASE(string_test_strcasecmp_long_strings),
+	KUNIT_CASE(string_test_strncasecmp),
+	KUNIT_CASE(string_test_strncasecmp_long_strings),
+	KUNIT_CASE(string_test_strscpy),
+	KUNIT_CASE(string_test_strcat),
+	KUNIT_CASE(string_test_strncat),
+	KUNIT_CASE(string_test_strlcat),
+	KUNIT_CASE(string_test_strtomem),
+	KUNIT_CASE(string_test_memtostr),
 	{}
 };
 
@@ -351,4 +633,5 @@ static struct kunit_suite string_test_suite = {
 
 kunit_test_suites(&string_test_suite);
 
+MODULE_DESCRIPTION("Test cases for string functions");
 MODULE_LICENSE("GPL v2");
diff --git a/lib/strscpy_kunit.c b/lib/strscpy_kunit.c
deleted file mode 100644
index b6d1d93a88..0000000000
--- a/lib/strscpy_kunit.c
+++ /dev/null
@@ -1,143 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * Kernel module for testing 'strscpy' family of functions.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <kunit/test.h>
-#include <linux/string.h>
-
-/**
- * strscpy_check() - Run a specific test case.
- * @test: KUnit test context pointer
- * @src: Source string, argument to strscpy_pad()
- * @count: Size of destination buffer, argument to strscpy_pad()
- * @expected: Expected return value from call to strscpy_pad()
- * @chars: Number of characters from the src string expected to be
- *         written to the dst buffer.
- * @terminator: 1 if there should be a terminating null byte 0 otherwise.
- * @pad: Number of pad characters expected (in the tail of dst buffer).
- *       (@pad does not include the null terminator byte.)
- *
- * Calls strscpy_pad() and verifies the return value and state of the
- * destination buffer after the call returns.
- */
-static void strscpy_check(struct kunit *test, char *src, int count,
-			  int expected, int chars, int terminator, int pad)
-{
-	int nr_bytes_poison;
-	int max_expected;
-	int max_count;
-	int written;
-	char buf[6];
-	int index, i;
-	const char POISON = 'z';
-
-	KUNIT_ASSERT_TRUE_MSG(test, src != NULL,
-			      "null source string not supported");
-
-	memset(buf, POISON, sizeof(buf));
-	/* Future proofing test suite, validate args */
-	max_count = sizeof(buf) - 2; /* Space for null and to verify overflow */
-	max_expected = count - 1;    /* Space for the null */
-
-	KUNIT_ASSERT_LE_MSG(test, count, max_count,
-		"count (%d) is too big (%d) ... aborting", count, max_count);
-	KUNIT_EXPECT_LE_MSG(test, expected, max_expected,
-		"expected (%d) is bigger than can possibly be returned (%d)",
-		expected, max_expected);
-
-	written = strscpy_pad(buf, src, count);
-	KUNIT_ASSERT_EQ(test, written, expected);
-
-	if (count && written == -E2BIG) {
-		KUNIT_ASSERT_EQ_MSG(test, 0, strncmp(buf, src, count - 1),
-			"buffer state invalid for -E2BIG");
-		KUNIT_ASSERT_EQ_MSG(test, buf[count - 1], '\0',
-			"too big string is not null terminated correctly");
-	}
-
-	for (i = 0; i < chars; i++)
-		KUNIT_ASSERT_EQ_MSG(test, buf[i], src[i],
-			"buf[i]==%c != src[i]==%c", buf[i], src[i]);
-
-	if (terminator)
-		KUNIT_ASSERT_EQ_MSG(test, buf[count - 1], '\0',
-			"string is not null terminated correctly");
-
-	for (i = 0; i < pad; i++) {
-		index = chars + terminator + i;
-		KUNIT_ASSERT_EQ_MSG(test, buf[index], '\0',
-			"padding missing at index: %d", i);
-	}
-
-	nr_bytes_poison = sizeof(buf) - chars - terminator - pad;
-	for (i = 0; i < nr_bytes_poison; i++) {
-		index = sizeof(buf) - 1 - i; /* Check from the end back */
-		KUNIT_ASSERT_EQ_MSG(test, buf[index], POISON,
-			"poison value missing at index: %d", i);
-	}
-}
-
-static void test_strscpy(struct kunit *test)
-{
-	char dest[8];
-
-	/*
-	 * strscpy_check() uses a destination buffer of size 6 and needs at
-	 * least 2 characters spare (one for null and one to check for
-	 * overflow).  This means we should only call tc() with
-	 * strings up to a maximum of 4 characters long and 'count'
-	 * should not exceed 4.  To test with longer strings increase
-	 * the buffer size in tc().
-	 */
-
-	/* strscpy_check(test, src, count, expected, chars, terminator, pad) */
-	strscpy_check(test, "a", 0, -E2BIG, 0, 0, 0);
-	strscpy_check(test, "",  0, -E2BIG, 0, 0, 0);
-
-	strscpy_check(test, "a", 1, -E2BIG, 0, 1, 0);
-	strscpy_check(test, "",  1, 0,	 0, 1, 0);
-
-	strscpy_check(test, "ab", 2, -E2BIG, 1, 1, 0);
-	strscpy_check(test, "a",  2, 1,	  1, 1, 0);
-	strscpy_check(test, "",   2, 0,	  0, 1, 1);
-
-	strscpy_check(test, "abc", 3, -E2BIG, 2, 1, 0);
-	strscpy_check(test, "ab",  3, 2,	   2, 1, 0);
-	strscpy_check(test, "a",   3, 1,	   1, 1, 1);
-	strscpy_check(test, "",    3, 0,	   0, 1, 2);
-
-	strscpy_check(test, "abcd", 4, -E2BIG, 3, 1, 0);
-	strscpy_check(test, "abc",  4, 3,	    3, 1, 0);
-	strscpy_check(test, "ab",   4, 2,	    2, 1, 1);
-	strscpy_check(test, "a",    4, 1,	    1, 1, 2);
-	strscpy_check(test, "",     4, 0,	    0, 1, 3);
-
-	/* Compile-time-known source strings. */
-	KUNIT_EXPECT_EQ(test, strscpy(dest, "", ARRAY_SIZE(dest)), 0);
-	KUNIT_EXPECT_EQ(test, strscpy(dest, "", 3), 0);
-	KUNIT_EXPECT_EQ(test, strscpy(dest, "", 1), 0);
-	KUNIT_EXPECT_EQ(test, strscpy(dest, "", 0), -E2BIG);
-	KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", ARRAY_SIZE(dest)), 5);
-	KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", 3), -E2BIG);
-	KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", 1), -E2BIG);
-	KUNIT_EXPECT_EQ(test, strscpy(dest, "Fixed", 0), -E2BIG);
-	KUNIT_EXPECT_EQ(test, strscpy(dest, "This is too long", ARRAY_SIZE(dest)), -E2BIG);
-}
-
-static struct kunit_case strscpy_test_cases[] = {
-	KUNIT_CASE(test_strscpy),
-	{}
-};
-
-static struct kunit_suite strscpy_test_suite = {
-	.name = "strscpy",
-	.test_cases = strscpy_test_cases,
-};
-
-kunit_test_suite(strscpy_test_suite);
-
-MODULE_AUTHOR("Tobin C. Harding <tobin@kernel.org>");
-MODULE_LICENSE("GPL");
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index 6b2b33579f..6dfb8d46a4 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -60,18 +60,17 @@ static const unsigned long exp3_1_0[] __initconst = {
 };
 
 static bool __init
-__check_eq_uint(const char *srcfile, unsigned int line,
-		const unsigned int exp_uint, unsigned int x)
+__check_eq_ulong(const char *srcfile, unsigned int line,
+		 const unsigned long exp_ulong, unsigned long x)
 {
-	if (exp_uint != x) {
-		pr_err("[%s:%u] expected %u, got %u\n",
-			srcfile, line, exp_uint, x);
+	if (exp_ulong != x) {
+		pr_err("[%s:%u] expected %lu, got %lu\n",
+			srcfile, line, exp_ulong, x);
 		return false;
 	}
 	return true;
 }
 
-
 static bool __init
 __check_eq_bitmap(const char *srcfile, unsigned int line,
 		  const unsigned long *exp_bmap, const unsigned long *bmap,
@@ -185,7 +184,8 @@ __check_eq_str(const char *srcfile, unsigned int line,
 		result;							\
 	})
 
-#define expect_eq_uint(...)		__expect_eq(uint, ##__VA_ARGS__)
+#define expect_eq_ulong(...)		__expect_eq(ulong, ##__VA_ARGS__)
+#define expect_eq_uint(x, y)		expect_eq_ulong((unsigned int)(x), (unsigned int)(y))
 #define expect_eq_bitmap(...)		__expect_eq(bitmap, ##__VA_ARGS__)
 #define expect_eq_pbl(...)		__expect_eq(pbl, ##__VA_ARGS__)
 #define expect_eq_u32_array(...)	__expect_eq(u32_array, ##__VA_ARGS__)
@@ -244,7 +244,7 @@ static void __init test_find_nth_bit(void)
 	expect_eq_uint(60,  find_nth_bit(bmap, 64 * 3, 5));
 	expect_eq_uint(80,  find_nth_bit(bmap, 64 * 3, 6));
 	expect_eq_uint(123, find_nth_bit(bmap, 64 * 3, 7));
-	expect_eq_uint(64 * 3, find_nth_bit(bmap, 64 * 3, 8));
+	expect_eq_uint(0,   !!(find_nth_bit(bmap, 64 * 3, 8) < 64 * 3));
 
 	expect_eq_uint(10,  find_nth_bit(bmap, 64 * 3 - 1, 0));
 	expect_eq_uint(20,  find_nth_bit(bmap, 64 * 3 - 1, 1));
@@ -254,7 +254,7 @@ static void __init test_find_nth_bit(void)
 	expect_eq_uint(60,  find_nth_bit(bmap, 64 * 3 - 1, 5));
 	expect_eq_uint(80,  find_nth_bit(bmap, 64 * 3 - 1, 6));
 	expect_eq_uint(123, find_nth_bit(bmap, 64 * 3 - 1, 7));
-	expect_eq_uint(64 * 3 - 1, find_nth_bit(bmap, 64 * 3 - 1, 8));
+	expect_eq_uint(0,   !!(find_nth_bit(bmap, 64 * 3 - 1, 8) < 64 * 3 - 1));
 
 	for_each_set_bit(bit, exp1, EXP1_IN_BITS) {
 		b = find_nth_bit(exp1, EXP1_IN_BITS, cnt++);
@@ -548,7 +548,7 @@ static void __init test_bitmap_parselist(void)
 		}
 
 		if (ptest.flags & PARSE_TIME)
-			pr_err("parselist: %d: input is '%s' OK, Time: %llu\n",
+			pr_info("parselist: %d: input is '%s' OK, Time: %llu\n",
 					i, ptest.in, time);
 
 #undef ptest
@@ -587,7 +587,7 @@ static void __init test_bitmap_printlist(void)
 		goto out;
 	}
 
-	pr_err("bitmap_print_to_pagebuf: input is '%s', Time: %llu\n", buf, time);
+	pr_info("bitmap_print_to_pagebuf: input is '%s', Time: %llu\n", buf, time);
 out:
 	kfree(buf);
 	kfree(bmap);
@@ -665,7 +665,7 @@ static void __init test_bitmap_parse(void)
 		}
 
 		if (test.flags & PARSE_TIME)
-			pr_err("parse: %d: input is '%s' OK, Time: %llu\n",
+			pr_info("parse: %d: input is '%s' OK, Time: %llu\n",
 					i, test.in, time);
 	}
 }
@@ -1245,14 +1245,7 @@ static void __init test_bitmap_const_eval(void)
 	 * in runtime.
 	 */
 
-	/*
-	 * Equals to `unsigned long bitmap[1] = { GENMASK(6, 5), }`.
-	 * Clang on s390 optimizes bitops at compile-time as intended, but at
-	 * the same time stops treating @bitmap and @bitopvar as compile-time
-	 * constants after regular test_bit() is executed, thus triggering the
-	 * build bugs below. So, call const_test_bit() there directly until
-	 * the compiler is fixed.
-	 */
+	/* Equals to `unsigned long bitmap[1] = { GENMASK(6, 5), }` */
 	bitmap_clear(bitmap, 0, BITS_PER_LONG);
 	if (!test_bit(7, bitmap))
 		bitmap_set(bitmap, 5, 2);
@@ -1284,8 +1277,179 @@ static void __init test_bitmap_const_eval(void)
 	/* ~BIT(25) */
 	BUILD_BUG_ON(!__builtin_constant_p(~var));
 	BUILD_BUG_ON(~var != ~BIT(25));
+
+	/* ~BIT(25) | BIT(25) == ~0UL */
+	bitmap_complement(&var, &var, BITS_PER_LONG);
+	__assign_bit(25, &var, true);
+
+	/* !(~(~0UL)) == 1 */
+	res = bitmap_full(&var, BITS_PER_LONG);
+	BUILD_BUG_ON(!__builtin_constant_p(res));
+	BUILD_BUG_ON(!res);
+}
+
+/*
+ * Test bitmap should be big enough to include the cases when start is not in
+ * the first word, and start+nbits lands in the following word.
+ */
+#define TEST_BIT_LEN (1000)
+
+/*
+ * Helper function to test bitmap_write() overwriting the chosen byte pattern.
+ */
+static void __init test_bitmap_write_helper(const char *pattern)
+{
+	DECLARE_BITMAP(bitmap, TEST_BIT_LEN);
+	DECLARE_BITMAP(exp_bitmap, TEST_BIT_LEN);
+	DECLARE_BITMAP(pat_bitmap, TEST_BIT_LEN);
+	unsigned long w, r, bit;
+	int i, n, nbits;
+
+	/*
+	 * Only parse the pattern once and store the result in the intermediate
+	 * bitmap.
+	 */
+	bitmap_parselist(pattern, pat_bitmap, TEST_BIT_LEN);
+
+	/*
+	 * Check that writing a single bit does not accidentally touch the
+	 * adjacent bits.
+	 */
+	for (i = 0; i < TEST_BIT_LEN; i++) {
+		bitmap_copy(bitmap, pat_bitmap, TEST_BIT_LEN);
+		bitmap_copy(exp_bitmap, pat_bitmap, TEST_BIT_LEN);
+		for (bit = 0; bit <= 1; bit++) {
+			bitmap_write(bitmap, bit, i, 1);
+			__assign_bit(i, exp_bitmap, bit);
+			expect_eq_bitmap(exp_bitmap, bitmap,
+					 TEST_BIT_LEN);
+		}
+	}
+
+	/* Ensure writing 0 bits does not change anything. */
+	bitmap_copy(bitmap, pat_bitmap, TEST_BIT_LEN);
+	bitmap_copy(exp_bitmap, pat_bitmap, TEST_BIT_LEN);
+	for (i = 0; i < TEST_BIT_LEN; i++) {
+		bitmap_write(bitmap, ~0UL, i, 0);
+		expect_eq_bitmap(exp_bitmap, bitmap, TEST_BIT_LEN);
+	}
+
+	for (nbits = BITS_PER_LONG; nbits >= 1; nbits--) {
+		w = IS_ENABLED(CONFIG_64BIT) ? 0xdeadbeefdeadbeefUL
+					     : 0xdeadbeefUL;
+		w >>= (BITS_PER_LONG - nbits);
+		for (i = 0; i <= TEST_BIT_LEN - nbits; i++) {
+			bitmap_copy(bitmap, pat_bitmap, TEST_BIT_LEN);
+			bitmap_copy(exp_bitmap, pat_bitmap, TEST_BIT_LEN);
+			for (n = 0; n < nbits; n++)
+				__assign_bit(i + n, exp_bitmap, w & BIT(n));
+			bitmap_write(bitmap, w, i, nbits);
+			expect_eq_bitmap(exp_bitmap, bitmap, TEST_BIT_LEN);
+			r = bitmap_read(bitmap, i, nbits);
+			expect_eq_ulong(r, w);
+		}
+	}
+}
+
+static void __init test_bitmap_read_write(void)
+{
+	unsigned char *pattern[3] = {"", "all:1/2", "all"};
+	DECLARE_BITMAP(bitmap, TEST_BIT_LEN);
+	unsigned long zero_bits = 0, bits_per_long = BITS_PER_LONG;
+	unsigned long val;
+	int i, pi;
+
+	/*
+	 * Reading/writing zero bits should not crash the kernel.
+	 * READ_ONCE() prevents constant folding.
+	 */
+	bitmap_write(NULL, 0, 0, READ_ONCE(zero_bits));
+	/* Return value of bitmap_read() is undefined here. */
+	bitmap_read(NULL, 0, READ_ONCE(zero_bits));
+
+	/*
+	 * Reading/writing more than BITS_PER_LONG bits should not crash the
+	 * kernel. READ_ONCE() prevents constant folding.
+	 */
+	bitmap_write(NULL, 0, 0, READ_ONCE(bits_per_long) + 1);
+	/* Return value of bitmap_read() is undefined here. */
+	bitmap_read(NULL, 0, READ_ONCE(bits_per_long) + 1);
+
+	/*
+	 * Ensure that bitmap_read() reads the same value that was previously
+	 * written, and two consequent values are correctly merged.
+	 * The resulting bit pattern is asymmetric to rule out possible issues
+	 * with bit numeration order.
+	 */
+	for (i = 0; i < TEST_BIT_LEN - 7; i++) {
+		bitmap_zero(bitmap, TEST_BIT_LEN);
+
+		bitmap_write(bitmap, 0b10101UL, i, 5);
+		val = bitmap_read(bitmap, i, 5);
+		expect_eq_ulong(0b10101UL, val);
+
+		bitmap_write(bitmap, 0b101UL, i + 5, 3);
+		val = bitmap_read(bitmap, i + 5, 3);
+		expect_eq_ulong(0b101UL, val);
+
+		val = bitmap_read(bitmap, i, 8);
+		expect_eq_ulong(0b10110101UL, val);
+	}
+
+	for (pi = 0; pi < ARRAY_SIZE(pattern); pi++)
+		test_bitmap_write_helper(pattern[pi]);
 }
 
+static void __init test_bitmap_read_perf(void)
+{
+	DECLARE_BITMAP(bitmap, TEST_BIT_LEN);
+	unsigned int cnt, nbits, i;
+	unsigned long val;
+	ktime_t time;
+
+	bitmap_fill(bitmap, TEST_BIT_LEN);
+	time = ktime_get();
+	for (cnt = 0; cnt < 5; cnt++) {
+		for (nbits = 1; nbits <= BITS_PER_LONG; nbits++) {
+			for (i = 0; i < TEST_BIT_LEN; i++) {
+				if (i + nbits > TEST_BIT_LEN)
+					break;
+				/*
+				 * Prevent the compiler from optimizing away the
+				 * bitmap_read() by using its value.
+				 */
+				WRITE_ONCE(val, bitmap_read(bitmap, i, nbits));
+			}
+		}
+	}
+	time = ktime_get() - time;
+	pr_info("Time spent in %s:\t%llu\n", __func__, time);
+}
+
+static void __init test_bitmap_write_perf(void)
+{
+	DECLARE_BITMAP(bitmap, TEST_BIT_LEN);
+	unsigned int cnt, nbits, i;
+	unsigned long val = 0xfeedface;
+	ktime_t time;
+
+	bitmap_zero(bitmap, TEST_BIT_LEN);
+	time = ktime_get();
+	for (cnt = 0; cnt < 5; cnt++) {
+		for (nbits = 1; nbits <= BITS_PER_LONG; nbits++) {
+			for (i = 0; i < TEST_BIT_LEN; i++) {
+				if (i + nbits > TEST_BIT_LEN)
+					break;
+				bitmap_write(bitmap, val, i, nbits);
+			}
+		}
+	}
+	time = ktime_get() - time;
+	pr_info("Time spent in %s:\t%llu\n", __func__, time);
+}
+
+#undef TEST_BIT_LEN
+
 static void __init selftest(void)
 {
 	test_zero_clear();
@@ -1303,6 +1467,9 @@ static void __init selftest(void)
 	test_bitmap_cut();
 	test_bitmap_print_buf();
 	test_bitmap_const_eval();
+	test_bitmap_read_write();
+	test_bitmap_read_perf();
+	test_bitmap_write_perf();
 
 	test_find_nth_bit();
 	test_for_each_set_bit();
diff --git a/lib/test_bitops.c b/lib/test_bitops.c
index 3b7bcbee84..55669624bb 100644
--- a/lib/test_bitops.c
+++ b/lib/test_bitops.c
@@ -5,9 +5,11 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/cleanup.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/printk.h>
+#include <linux/slab.h>
 
 /* a tiny module only meant to test
  *
@@ -50,6 +52,30 @@ static unsigned long order_comb_long[][2] = {
 };
 #endif
 
+static int __init test_fns(void)
+{
+	static volatile __always_used unsigned long tmp __initdata;
+	unsigned long *buf __free(kfree) = NULL;
+	unsigned int i, n;
+	ktime_t time;
+
+	buf = kmalloc_array(10000, sizeof(unsigned long), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	get_random_bytes(buf, 10000 * sizeof(unsigned long));
+	time = ktime_get();
+
+	for (n = 0; n < BITS_PER_LONG; n++)
+		for (i = 0; i < 10000; i++)
+			tmp = fns(buf[i], n);
+
+	time = ktime_get() - time;
+	pr_err("fns:  %18llu ns\n", time);
+
+	return 0;
+}
+
 static int __init test_bitops_startup(void)
 {
 	int i, bit_set;
@@ -94,6 +120,8 @@ static int __init test_bitops_startup(void)
 	if (bit_set != BITOPS_LAST)
 		pr_err("ERROR: FOUND SET BIT %d\n", bit_set);
 
+	test_fns();
+
 	pr_info("Completed bitops test\n");
 
 	return 0;
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 569e6d2dc5..207ff87194 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -13431,7 +13431,7 @@ static struct bpf_test tests[] = {
 		.stack_depth = 8,
 		.nr_testruns = NR_PATTERN_RUNS,
 	},
-	/* 64-bit atomic magnitudes */
+	/* 32-bit atomic magnitudes */
 	{
 		"ATOMIC_W_ADD: all operand magnitudes",
 		{ },
diff --git a/lib/test_fpu.h b/lib/test_fpu.h
new file mode 100644
index 0000000000..4459807084
--- /dev/null
+++ b/lib/test_fpu.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _LIB_TEST_FPU_H
+#define _LIB_TEST_FPU_H
+
+int test_fpu(void);
+
+#endif
diff --git a/lib/test_fpu.c b/lib/test_fpu_glue.c
index e82db19fed..eef282a271 100644
--- a/lib/test_fpu.c
+++ b/lib/test_fpu_glue.c
@@ -17,39 +17,9 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/debugfs.h>
-#include <asm/fpu/api.h>
+#include <linux/fpu.h>
 
-static int test_fpu(void)
-{
-	/*
-	 * This sequence of operations tests that rounding mode is
-	 * to nearest and that denormal numbers are supported.
-	 * Volatile variables are used to avoid compiler optimizing
-	 * the calculations away.
-	 */
-	volatile double a, b, c, d, e, f, g;
-
-	a = 4.0;
-	b = 1e-15;
-	c = 1e-310;
-
-	/* Sets precision flag */
-	d = a + b;
-
-	/* Result depends on rounding mode */
-	e = a + b / 2;
-
-	/* Denormal and very large values */
-	f = b / c;
-
-	/* Depends on denormal support */
-	g = a + c * f;
-
-	if (d > a && e > a && g > a)
-		return 0;
-	else
-		return -EINVAL;
-}
+#include "test_fpu.h"
 
 static int test_fpu_get(void *data, u64 *val)
 {
@@ -68,6 +38,9 @@ static struct dentry *selftest_dir;
 
 static int __init test_fpu_init(void)
 {
+	if (!kernel_fpu_available())
+		return -EINVAL;
+
 	selftest_dir = debugfs_create_dir("selftest_helpers", NULL);
 	if (!selftest_dir)
 		return -ENOMEM;
diff --git a/lib/test_fpu_impl.c b/lib/test_fpu_impl.c
new file mode 100644
index 0000000000..777894dbbe
--- /dev/null
+++ b/lib/test_fpu_impl.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <linux/errno.h>
+
+#include "test_fpu.h"
+
+int test_fpu(void)
+{
+	/*
+	 * This sequence of operations tests that rounding mode is
+	 * to nearest and that denormal numbers are supported.
+	 * Volatile variables are used to avoid compiler optimizing
+	 * the calculations away.
+	 */
+	volatile double a, b, c, d, e, f, g;
+
+	a = 4.0;
+	b = 1e-15;
+	c = 1e-310;
+
+	/* Sets precision flag */
+	d = a + b;
+
+	/* Result depends on rounding mode */
+	e = a + b / 2;
+
+	/* Denormal and very large values */
+	f = b / c;
+
+	/* Depends on denormal support */
+	g = a + c * f;
+
+	if (d > a && e > a && g > a)
+		return 0;
+	else
+		return -EINVAL;
+}
diff --git a/lib/test_hexdump.c b/lib/test_hexdump.c
index b916801f23..fe2682bb21 100644
--- a/lib/test_hexdump.c
+++ b/lib/test_hexdump.c
@@ -113,7 +113,7 @@ static void __init test_hexdump_prepare_test(size_t len, int rowsize,
 			*p++ = ' ';
 		} while (p < test + rs * 2 + rs / gs + 1);
 
-		strncpy(p, data_a, l);
+		memcpy(p, data_a, l);
 		p += l;
 	}
 
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index 42b5852082..c63db03ebb 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -811,4 +811,5 @@ static void __exit test_rht_exit(void)
 module_init(test_rht_init);
 module_exit(test_rht_exit);
 
+MODULE_DESCRIPTION("Resizable, Scalable, Concurrent Hash Table test module");
 MODULE_LICENSE("GPL v2");
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 928fc20337..ab9cc42a0d 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -2001,6 +2001,97 @@ static noinline void check_get_order(struct xarray *xa)
 	}
 }
 
+static noinline void check_xas_get_order(struct xarray *xa)
+{
+	XA_STATE(xas, xa, 0);
+
+	unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1;
+	unsigned int order;
+	unsigned long i, j;
+
+	for (order = 0; order < max_order; order++) {
+		for (i = 0; i < 10; i++) {
+			xas_set_order(&xas, i << order, order);
+			do {
+				xas_lock(&xas);
+				xas_store(&xas, xa_mk_value(i));
+				xas_unlock(&xas);
+			} while (xas_nomem(&xas, GFP_KERNEL));
+
+			for (j = i << order; j < (i + 1) << order; j++) {
+				xas_set_order(&xas, j, 0);
+				rcu_read_lock();
+				xas_load(&xas);
+				XA_BUG_ON(xa, xas_get_order(&xas) != order);
+				rcu_read_unlock();
+			}
+
+			xas_lock(&xas);
+			xas_set_order(&xas, i << order, order);
+			xas_store(&xas, NULL);
+			xas_unlock(&xas);
+		}
+	}
+}
+
+static noinline void check_xas_conflict_get_order(struct xarray *xa)
+{
+	XA_STATE(xas, xa, 0);
+
+	void *entry;
+	int only_once;
+	unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1;
+	unsigned int order;
+	unsigned long i, j, k;
+
+	for (order = 0; order < max_order; order++) {
+		for (i = 0; i < 10; i++) {
+			xas_set_order(&xas, i << order, order);
+			do {
+				xas_lock(&xas);
+				xas_store(&xas, xa_mk_value(i));
+				xas_unlock(&xas);
+			} while (xas_nomem(&xas, GFP_KERNEL));
+
+			/*
+			 * Ensure xas_get_order works with xas_for_each_conflict.
+			 */
+			j = i << order;
+			for (k = 0; k < order; k++) {
+				only_once = 0;
+				xas_set_order(&xas, j + (1 << k), k);
+				xas_lock(&xas);
+				xas_for_each_conflict(&xas, entry) {
+					XA_BUG_ON(xa, entry != xa_mk_value(i));
+					XA_BUG_ON(xa, xas_get_order(&xas) != order);
+					only_once++;
+				}
+				XA_BUG_ON(xa, only_once != 1);
+				xas_unlock(&xas);
+			}
+
+			if (order < max_order - 1) {
+				only_once = 0;
+				xas_set_order(&xas, (i & ~1UL) << order, order + 1);
+				xas_lock(&xas);
+				xas_for_each_conflict(&xas, entry) {
+					XA_BUG_ON(xa, entry != xa_mk_value(i));
+					XA_BUG_ON(xa, xas_get_order(&xas) != order);
+					only_once++;
+				}
+				XA_BUG_ON(xa, only_once != 1);
+				xas_unlock(&xas);
+			}
+
+			xas_set_order(&xas, i << order, order);
+			xas_lock(&xas);
+			xas_store(&xas, NULL);
+			xas_unlock(&xas);
+		}
+	}
+}
+
+
 static noinline void check_destroy(struct xarray *xa)
 {
 	unsigned long index;
@@ -2052,6 +2143,8 @@ static int xarray_checks(void)
 	check_multi_store(&array);
 	check_multi_store_advanced(&array);
 	check_get_order(&array);
+	check_xas_get_order(&array);
+	check_xas_conflict_get_order(&array);
 	check_xa_alloc();
 	check_find(&array);
 	check_find_entry(&array);
diff --git a/lib/ubsan.h b/lib/ubsan.h
index 0982578fbd..07e37d4429 100644
--- a/lib/ubsan.h
+++ b/lib/ubsan.h
@@ -43,7 +43,7 @@ enum {
 struct type_descriptor {
 	u16 type_kind;
 	u16 type_info;
-	char type_name[1];
+	char type_name[];
 };
 
 struct source_location {
diff --git a/lib/usercopy.c b/lib/usercopy.c
index d29fe29c68..499a7a7d54 100644
--- a/lib/usercopy.c
+++ b/lib/usercopy.c
@@ -1,9 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/export.h>
 #include <linux/fault-inject-usercopy.h>
 #include <linux/instrumented.h>
-#include <linux/uaccess.h>
+#include <linux/kernel.h>
 #include <linux/nospec.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/wordpart.h>
 
 /* out-of-line parts */
 
diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig
index d883ac2995..c46c230051 100644
--- a/lib/vdso/Kconfig
+++ b/lib/vdso/Kconfig
@@ -30,4 +30,11 @@ config GENERIC_VDSO_TIME_NS
 	  Selected by architectures which support time namespaces in the
 	  VDSO
 
+config GENERIC_VDSO_OVERFLOW_PROTECT
+	bool
+	help
+	  Select to add multiplication overflow protection to the VDSO
+	  time getter functions for the price of an extra conditional
+	  in the hotpath.
+
 endif
diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index ce2f695520..899850bd6f 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -5,15 +5,23 @@
 #include <vdso/datapage.h>
 #include <vdso/helpers.h>
 
-#ifndef vdso_calc_delta
-/*
- * Default implementation which works for all sane clocksources. That
- * obviously excludes x86/TSC.
- */
-static __always_inline
-u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
+#ifndef vdso_calc_ns
+
+#ifdef VDSO_DELTA_NOMASK
+# define VDSO_DELTA_MASK(vd)	ULLONG_MAX
+#else
+# define VDSO_DELTA_MASK(vd)	(vd->mask)
+#endif
+
+#ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT
+static __always_inline bool vdso_delta_ok(const struct vdso_data *vd, u64 delta)
+{
+	return delta < vd->max_cycles;
+}
+#else
+static __always_inline bool vdso_delta_ok(const struct vdso_data *vd, u64 delta)
 {
-	return ((cycles - last) & mask) * mult;
+	return true;
 }
 #endif
 
@@ -24,6 +32,21 @@ static __always_inline u64 vdso_shift_ns(u64 ns, u32 shift)
 }
 #endif
 
+/*
+ * Default implementation which works for all sane clocksources. That
+ * obviously excludes x86/TSC.
+ */
+static __always_inline u64 vdso_calc_ns(const struct vdso_data *vd, u64 cycles, u64 base)
+{
+	u64 delta = (cycles - vd->cycle_last) & VDSO_DELTA_MASK(vd);
+
+	if (likely(vdso_delta_ok(vd, delta)))
+		return vdso_shift_ns((delta * vd->mult) + base, vd->shift);
+
+	return mul_u64_u32_add_u64_shr(delta, vd->mult, base, vd->shift);
+}
+#endif /* vdso_calc_ns */
+
 #ifndef __arch_vdso_hres_capable
 static inline bool __arch_vdso_hres_capable(void)
 {
@@ -49,10 +72,10 @@ static inline bool vdso_cycles_ok(u64 cycles)
 static __always_inline int do_hres_timens(const struct vdso_data *vdns, clockid_t clk,
 					  struct __kernel_timespec *ts)
 {
-	const struct vdso_data *vd;
 	const struct timens_offset *offs = &vdns->offset[clk];
 	const struct vdso_timestamp *vdso_ts;
-	u64 cycles, last, ns;
+	const struct vdso_data *vd;
+	u64 cycles, ns;
 	u32 seq;
 	s64 sec;
 
@@ -73,10 +96,7 @@ static __always_inline int do_hres_timens(const struct vdso_data *vdns, clockid_
 		cycles = __arch_get_hw_counter(vd->clock_mode, vd);
 		if (unlikely(!vdso_cycles_ok(cycles)))
 			return -1;
-		ns = vdso_ts->nsec;
-		last = vd->cycle_last;
-		ns += vdso_calc_delta(cycles, last, vd->mask, vd->mult);
-		ns = vdso_shift_ns(ns, vd->shift);
+		ns = vdso_calc_ns(vd, cycles, vdso_ts->nsec);
 		sec = vdso_ts->sec;
 	} while (unlikely(vdso_read_retry(vd, seq)));
 
@@ -111,7 +131,7 @@ static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk,
 				   struct __kernel_timespec *ts)
 {
 	const struct vdso_timestamp *vdso_ts = &vd->basetime[clk];
-	u64 cycles, last, sec, ns;
+	u64 cycles, sec, ns;
 	u32 seq;
 
 	/* Allows to compile the high resolution parts out */
@@ -144,10 +164,7 @@ static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk,
 		cycles = __arch_get_hw_counter(vd->clock_mode, vd);
 		if (unlikely(!vdso_cycles_ok(cycles)))
 			return -1;
-		ns = vdso_ts->nsec;
-		last = vd->cycle_last;
-		ns += vdso_calc_delta(cycles, last, vd->mask, vd->mult);
-		ns = vdso_shift_ns(ns, vd->shift);
+		ns = vdso_calc_ns(vd, cycles, vdso_ts->nsec);
 		sec = vdso_ts->sec;
 	} while (unlikely(vdso_read_retry(vd, seq)));
 
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 552738f142..cdd4e2314b 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -966,13 +966,13 @@ char *bdev_name(char *buf, char *end, struct block_device *bdev,
 
 	hd = bdev->bd_disk;
 	buf = string(buf, end, hd->disk_name, spec);
-	if (bdev->bd_partno) {
+	if (bdev_is_partition(bdev)) {
 		if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) {
 			if (buf < end)
 				*buf = 'p';
 			buf++;
 		}
-		buf = number(buf, end, bdev->bd_partno, spec);
+		buf = number(buf, end, bdev_partno(bdev), spec);
 	}
 	return buf;
 }
diff --git a/lib/xarray.c b/lib/xarray.c
index 5e7d6334d7..32d4bac8c9 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -200,7 +200,8 @@ static void *xas_start(struct xa_state *xas)
 	return entry;
 }
 
-static void *xas_descend(struct xa_state *xas, struct xa_node *node)
+static __always_inline void *xas_descend(struct xa_state *xas,
+					struct xa_node *node)
 {
 	unsigned int offset = get_offset(xas->xa_index, node);
 	void *entry = xa_entry(xas->xa, node, offset);
@@ -1765,39 +1766,52 @@ unlock:
 EXPORT_SYMBOL(xa_store_range);
 
 /**
- * xa_get_order() - Get the order of an entry.
- * @xa: XArray.
- * @index: Index of the entry.
+ * xas_get_order() - Get the order of an entry.
+ * @xas: XArray operation state.
+ *
+ * Called after xas_load, the xas should not be in an error state.
  *
  * Return: A number between 0 and 63 indicating the order of the entry.
  */
-int xa_get_order(struct xarray *xa, unsigned long index)
+int xas_get_order(struct xa_state *xas)
 {
-	XA_STATE(xas, xa, index);
-	void *entry;
 	int order = 0;
 
-	rcu_read_lock();
-	entry = xas_load(&xas);
-
-	if (!entry)
-		goto unlock;
-
-	if (!xas.xa_node)
-		goto unlock;
+	if (!xas->xa_node)
+		return 0;
 
 	for (;;) {
-		unsigned int slot = xas.xa_offset + (1 << order);
+		unsigned int slot = xas->xa_offset + (1 << order);
 
 		if (slot >= XA_CHUNK_SIZE)
 			break;
-		if (!xa_is_sibling(xas.xa_node->slots[slot]))
+		if (!xa_is_sibling(xa_entry(xas->xa, xas->xa_node, slot)))
 			break;
 		order++;
 	}
 
-	order += xas.xa_node->shift;
-unlock:
+	order += xas->xa_node->shift;
+	return order;
+}
+EXPORT_SYMBOL_GPL(xas_get_order);
+
+/**
+ * xa_get_order() - Get the order of an entry.
+ * @xa: XArray.
+ * @index: Index of the entry.
+ *
+ * Return: A number between 0 and 63 indicating the order of the entry.
+ */
+int xa_get_order(struct xarray *xa, unsigned long index)
+{
+	XA_STATE(xas, xa, index);
+	int order = 0;
+	void *entry;
+
+	rcu_read_lock();
+	entry = xas_load(&xas);
+	if (entry)
+		order = xas_get_order(&xas);
 	rcu_read_unlock();
 
 	return order;