Merge branch 'for-5.14/amd-sfh' into for-linus

- support for Renoir and Cezanne SoCs
- support for Ambient Light Sensor
- support for Human Presence Detection sensor

all from Basavaraj Natikar

22 files changed, 255 insertions, 269 deletions

diff --git a/lib/.gitignore b/lib/.gitignore
index 327cb2c7f2c9..5e7fa54c4536 100644
--- a/lib/.gitignore
+++ b/lib/.gitignore
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
-gen_crc32table
-gen_crc64table
-crc32table.h
-crc64table.h
-oid_registry_data.c
+/crc32table.h
+/crc64table.h
+/gen_crc32table
+/gen_crc64table
+/oid_registry_data.c
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index b38bbb5bb00e..678c13967580 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2573,11 +2573,18 @@ config TEST_FPU
 
 endif # RUNTIME_TESTING_MENU
 
+config ARCH_USE_MEMTEST
+	bool
+	help
+	  An architecture should select this when it uses early_memtest()
+	  during boot process.
+
 config MEMTEST
 	bool "Memtest"
+	depends on ARCH_USE_MEMTEST
 	help
 	  This option adds a kernel parameter 'memtest', which allows memtest
-	  to be set.
+	  to be set and executed.
 	        memtest=0, mean disabled; -- default
 	        memtest=1, mean do 1 test pattern;
 	        ...
diff --git a/lib/Kconfig.kfence b/lib/Kconfig.kfence
index 78f50ccb3b45..e641add33947 100644
--- a/lib/Kconfig.kfence
+++ b/lib/Kconfig.kfence
@@ -7,6 +7,7 @@ menuconfig KFENCE
 	bool "KFENCE: low-overhead sampling-based memory safety error detector"
 	depends on HAVE_ARCH_KFENCE && (SLAB || SLUB)
 	select STACKTRACE
+	select IRQ_WORK
 	help
 	  KFENCE is a low-overhead sampling-based detector of heap out-of-bounds
 	  access, use-after-free, and invalid-free errors. KFENCE is designed
diff --git a/lib/Makefile b/lib/Makefile
index e11cfc18b6c0..2cc359ec1fdd 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -348,6 +348,7 @@ obj-$(CONFIG_OBJAGG) += objagg.o
 obj-$(CONFIG_PLDMFW) += pldmfw/
 
 # KUnit tests
+CFLAGS_bitfield_kunit.o := $(call cc-option,-Wframe-larger-than=10240)
 obj-$(CONFIG_BITFIELD_KUNIT) += bitfield_kunit.o
 obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o
 obj-$(CONFIG_LINEAR_RANGES_TEST) += test_linear_ranges.o
diff --git a/lib/bch.c b/lib/bch.c
index 7c031ee8b93b..c8095f30f254 100644
--- a/lib/bch.c
+++ b/lib/bch.c
@@ -584,7 +584,7 @@ static int find_affine4_roots(struct bch_control *bch, unsigned int a,
 	k = a_log(bch, a);
 	rows[0] = c;
 
-	/* buid linear system to solve X^4+aX^2+bX+c = 0 */
+	/* build linear system to solve X^4+aX^2+bX+c = 0 */
 	for (i = 0; i < m; i++) {
 		rows[i+1] = bch->a_pow_tab[4*i]^
 			(a ? bch->a_pow_tab[mod_s(bch, k)] : 0)^
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 9f4626a4c95f..74ceb02f45e3 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -3,17 +3,19 @@
  * lib/bitmap.c
  * Helper functions for bitmap.h.
  */
-#include <linux/export.h>
-#include <linux/thread_info.h>
-#include <linux/ctype.h>
-#include <linux/errno.h>
+
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
 #include <linux/bug.h>
+#include <linux/ctype.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/thread_info.h>
 #include <linux/uaccess.h>
 
 #include <asm/page.h>
@@ -1271,6 +1273,38 @@ void bitmap_free(const unsigned long *bitmap)
 }
 EXPORT_SYMBOL(bitmap_free);
 
+static void devm_bitmap_free(void *data)
+{
+	unsigned long *bitmap = data;
+
+	bitmap_free(bitmap);
+}
+
+unsigned long *devm_bitmap_alloc(struct device *dev,
+				 unsigned int nbits, gfp_t flags)
+{
+	unsigned long *bitmap;
+	int ret;
+
+	bitmap = bitmap_alloc(nbits, flags);
+	if (!bitmap)
+		return NULL;
+
+	ret = devm_add_action_or_reset(dev, devm_bitmap_free, bitmap);
+	if (ret)
+		return NULL;
+
+	return bitmap;
+}
+EXPORT_SYMBOL_GPL(devm_bitmap_alloc);
+
+unsigned long *devm_bitmap_zalloc(struct device *dev,
+				  unsigned int nbits, gfp_t flags)
+{
+	return devm_bitmap_alloc(dev, nbits, flags | __GFP_ZERO);
+}
+EXPORT_SYMBOL_GPL(devm_bitmap_zalloc);
+
 #if BITS_PER_LONG == 64
 /**
  * bitmap_from_arr32 - copy the contents of u32 array of bits to bitmap
diff --git a/lib/bug.c b/lib/bug.c
index 8f9d537bfb2a..45a0584f6541 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -127,6 +127,22 @@ static inline struct bug_entry *module_find_bug(unsigned long bugaddr)
 }
 #endif
 
+void bug_get_file_line(struct bug_entry *bug, const char **file,
+		       unsigned int *line)
+{
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
+	*file = bug->file;
+#else
+	*file = (const char *)bug + bug->file_disp;
+#endif
+	*line = bug->line;
+#else
+	*file = NULL;
+	*line = 0;
+#endif
+}
+
 struct bug_entry *find_bug(unsigned long bugaddr)
 {
 	struct bug_entry *bug;
@@ -153,32 +169,20 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
 
 	disable_trace_on_warning();
 
-	file = NULL;
-	line = 0;
-	warning = 0;
+	bug_get_file_line(bug, &file, &line);
 
-	if (bug) {
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
-		file = bug->file;
-#else
-		file = (const char *)bug + bug->file_disp;
-#endif
-		line = bug->line;
-#endif
-		warning = (bug->flags & BUGFLAG_WARNING) != 0;
-		once = (bug->flags & BUGFLAG_ONCE) != 0;
-		done = (bug->flags & BUGFLAG_DONE) != 0;
-
-		if (warning && once) {
-			if (done)
-				return BUG_TRAP_TYPE_WARN;
-
-			/*
-			 * Since this is the only store, concurrency is not an issue.
-			 */
-			bug->flags |= BUGFLAG_DONE;
-		}
+	warning = (bug->flags & BUGFLAG_WARNING) != 0;
+	once = (bug->flags & BUGFLAG_ONCE) != 0;
+	done = (bug->flags & BUGFLAG_DONE) != 0;
+
+	if (warning && once) {
+		if (done)
+			return BUG_TRAP_TYPE_WARN;
+
+		/*
+		 * Since this is the only store, concurrency is not an issue.
+		 */
+		bug->flags |= BUGFLAG_DONE;
 	}
 
 	/*
diff --git a/lib/cmdline.c b/lib/cmdline.c
index 5d474c626e24..5546bf588780 100644
--- a/lib/cmdline.c
+++ b/lib/cmdline.c
@@ -272,3 +272,4 @@ char *next_arg(char *args, char **param, char **val)
 	/* Chew up trailing spaces. */
 	return skip_spaces(args);
 }
+EXPORT_SYMBOL(next_arg);
diff --git a/lib/crc8.c b/lib/crc8.c
index 595a5a75e3cd..1ad8e501d9b6 100644
--- a/lib/crc8.c
+++ b/lib/crc8.c
@@ -71,7 +71,7 @@ EXPORT_SYMBOL(crc8_populate_lsb);
  * @nbytes: number of bytes in data buffer.
  * @crc: previous returned crc8 value.
  */
-u8 crc8(const u8 table[CRC8_TABLE_SIZE], u8 *pdata, size_t nbytes, u8 crc)
+u8 crc8(const u8 table[CRC8_TABLE_SIZE], const u8 *pdata, size_t nbytes, u8 crc)
 {
 	/* loop over the buffer data */
 	while (nbytes-- > 0)
diff --git a/lib/decompress_unlzma.c b/lib/decompress_unlzma.c
index 1cf409ef8d04..20a858031f12 100644
--- a/lib/decompress_unlzma.c
+++ b/lib/decompress_unlzma.c
@@ -391,7 +391,7 @@ static inline int INIT process_bit0(struct writer *wr, struct rc *rc,
 static inline int INIT process_bit1(struct writer *wr, struct rc *rc,
 					    struct cstate *cst, uint16_t *p,
 					    int pos_state, uint16_t *prob) {
-  int offset;
+	int offset;
 	uint16_t *prob_len;
 	int num_bits;
 	int len;
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index c70d6347afa2..641767b0dce2 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -396,7 +396,7 @@ static int ddebug_parse_query(char *words[], int nwords,
 			/* tail :$info is function or line-range */
 			fline = strchr(query->filename, ':');
 			if (!fline)
-				break;
+				continue;
 			*fline++ = '\0';
 			if (isalpha(*fline) || *fline == '*' || *fline == '?') {
 				/* take as function name */
@@ -586,13 +586,11 @@ static int remaining(int wrote)
 	return 0;
 }
 
-static char *dynamic_emit_prefix(const struct _ddebug *desc, char *buf)
+static char *__dynamic_emit_prefix(const struct _ddebug *desc, char *buf)
 {
 	int pos_after_tid;
 	int pos = 0;
 
-	*buf = '\0';
-
 	if (desc->flags & _DPRINTK_FLAGS_INCL_TID) {
 		if (in_interrupt())
 			pos += snprintf(buf + pos, remaining(pos), "<intr> ");
@@ -618,11 +616,18 @@ static char *dynamic_emit_prefix(const struct _ddebug *desc, char *buf)
 	return buf;
 }
 
+static inline char *dynamic_emit_prefix(struct _ddebug *desc, char *buf)
+{
+	if (unlikely(desc->flags & _DPRINTK_FLAGS_INCL_ANY))
+		return __dynamic_emit_prefix(desc, buf);
+	return buf;
+}
+
 void __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...)
 {
 	va_list args;
 	struct va_format vaf;
-	char buf[PREFIX_SIZE];
+	char buf[PREFIX_SIZE] = "";
 
 	BUG_ON(!descriptor);
 	BUG_ON(!fmt);
@@ -655,7 +660,7 @@ void __dynamic_dev_dbg(struct _ddebug *descriptor,
 	if (!dev) {
 		printk(KERN_DEBUG "(NULL device *): %pV", &vaf);
 	} else {
-		char buf[PREFIX_SIZE];
+		char buf[PREFIX_SIZE] = "";
 
 		dev_printk_emit(LOGLEVEL_DEBUG, dev, "%s%s %s: %pV",
 				dynamic_emit_prefix(descriptor, buf),
@@ -684,7 +689,7 @@ void __dynamic_netdev_dbg(struct _ddebug *descriptor,
 	vaf.va = &args;
 
 	if (dev && dev->dev.parent) {
-		char buf[PREFIX_SIZE];
+		char buf[PREFIX_SIZE] = "";
 
 		dev_printk_emit(LOGLEVEL_DEBUG, dev->dev.parent,
 				"%s%s %s %s%s: %pV",
@@ -720,7 +725,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
 	vaf.va = &args;
 
 	if (ibdev && ibdev->dev.parent) {
-		char buf[PREFIX_SIZE];
+		char buf[PREFIX_SIZE] = "";
 
 		dev_printk_emit(LOGLEVEL_DEBUG, ibdev->dev.parent,
 				"%s%s %s %s: %pV",
@@ -915,7 +920,6 @@ static const struct seq_operations ddebug_proc_seqops = {
 
 static int ddebug_proc_open(struct inode *inode, struct file *file)
 {
-	vpr_info("called\n");
 	return seq_open_private(file, &ddebug_proc_seqops,
 				sizeof(struct ddebug_iter));
 }
diff --git a/lib/find_bit.c b/lib/find_bit.c
index f67f86fd2f62..0f8e2e369b1d 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -29,7 +29,7 @@
  *    searching it for one bits.
  *  - The optional "addr2", which is anded with "addr1" if present.
  */
-static unsigned long _find_next_bit(const unsigned long *addr1,
+unsigned long _find_next_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long nbits,
 		unsigned long start, unsigned long invert, unsigned long le)
 {
@@ -68,44 +68,14 @@ static unsigned long _find_next_bit(const unsigned long *addr1,
 
 	return min(start + __ffs(tmp), nbits);
 }
-#endif
-
-#ifndef find_next_bit
-/*
- * Find the next set bit in a memory region.
- */
-unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
-			    unsigned long offset)
-{
-	return _find_next_bit(addr, NULL, size, offset, 0UL, 0);
-}
-EXPORT_SYMBOL(find_next_bit);
-#endif
-
-#ifndef find_next_zero_bit
-unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
-				 unsigned long offset)
-{
-	return _find_next_bit(addr, NULL, size, offset, ~0UL, 0);
-}
-EXPORT_SYMBOL(find_next_zero_bit);
-#endif
-
-#if !defined(find_next_and_bit)
-unsigned long find_next_and_bit(const unsigned long *addr1,
-		const unsigned long *addr2, unsigned long size,
-		unsigned long offset)
-{
-	return _find_next_bit(addr1, addr2, size, offset, 0UL, 0);
-}
-EXPORT_SYMBOL(find_next_and_bit);
+EXPORT_SYMBOL(_find_next_bit);
 #endif
 
 #ifndef find_first_bit
 /*
  * Find the first set bit in a memory region.
  */
-unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
+unsigned long _find_first_bit(const unsigned long *addr, unsigned long size)
 {
 	unsigned long idx;
 
@@ -116,14 +86,14 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
 
 	return size;
 }
-EXPORT_SYMBOL(find_first_bit);
+EXPORT_SYMBOL(_find_first_bit);
 #endif
 
 #ifndef find_first_zero_bit
 /*
  * Find the first cleared bit in a memory region.
  */
-unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
+unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size)
 {
 	unsigned long idx;
 
@@ -134,11 +104,11 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
 
 	return size;
 }
-EXPORT_SYMBOL(find_first_zero_bit);
+EXPORT_SYMBOL(_find_first_zero_bit);
 #endif
 
 #ifndef find_last_bit
-unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
+unsigned long _find_last_bit(const unsigned long *addr, unsigned long size)
 {
 	if (size) {
 		unsigned long val = BITMAP_LAST_WORD_MASK(size);
@@ -154,31 +124,9 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
 	}
 	return size;
 }
-EXPORT_SYMBOL(find_last_bit);
-#endif
-
-#ifdef __BIG_ENDIAN
-
-#ifndef find_next_zero_bit_le
-unsigned long find_next_zero_bit_le(const void *addr, unsigned
-		long size, unsigned long offset)
-{
-	return _find_next_bit(addr, NULL, size, offset, ~0UL, 1);
-}
-EXPORT_SYMBOL(find_next_zero_bit_le);
-#endif
-
-#ifndef find_next_bit_le
-unsigned long find_next_bit_le(const void *addr, unsigned
-		long size, unsigned long offset)
-{
-	return _find_next_bit(addr, NULL, size, offset, 0UL, 1);
-}
-EXPORT_SYMBOL(find_next_bit_le);
+EXPORT_SYMBOL(_find_last_bit);
 #endif
 
-#endif /* __BIG_ENDIAN */
-
 unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr,
 			       unsigned long size, unsigned long offset)
 {
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 5dcf9cdcbc46..9a57257988c7 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -642,6 +642,7 @@ EXPORT_SYMBOL(gen_pool_set_algo);
  * @nr: The number of zeroed bits we're looking for
  * @data: additional data - unused
  * @pool: pool to find the fit region memory from
+ * @start_addr: not used in this function
  */
 unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data,
@@ -660,6 +661,7 @@ EXPORT_SYMBOL(gen_pool_first_fit);
  * @nr: The number of zeroed bits we're looking for
  * @data: data for alignment
  * @pool: pool to get order from
+ * @start_addr: start addr of alloction chunk
  */
 unsigned long gen_pool_first_fit_align(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data,
@@ -687,6 +689,7 @@ EXPORT_SYMBOL(gen_pool_first_fit_align);
  * @nr: The number of zeroed bits we're looking for
  * @data: data for alignment
  * @pool: pool to get order from
+ * @start_addr: not used in this function
  */
 unsigned long gen_pool_fixed_alloc(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data,
@@ -721,6 +724,7 @@ EXPORT_SYMBOL(gen_pool_fixed_alloc);
  * @nr: The number of zeroed bits we're looking for
  * @data: additional data - unused
  * @pool: pool to find the fit region memory from
+ * @start_addr: not used in this function
  */
 unsigned long gen_pool_first_fit_order_align(unsigned long *map,
 		unsigned long size, unsigned long start,
@@ -735,13 +739,14 @@ EXPORT_SYMBOL(gen_pool_first_fit_order_align);
 
 /**
  * gen_pool_best_fit - find the best fitting region of memory
- * macthing the size requirement (no alignment constraint)
+ * matching the size requirement (no alignment constraint)
  * @map: The address to base the search on
  * @size: The bitmap size in bits
  * @start: The bitnumber to start searching at
  * @nr: The number of zeroed bits we're looking for
  * @data: additional data - unused
  * @pool: pool to find the fit region memory from
+ * @start_addr: not used in this function
  *
  * Iterate over the bitmap to find the smallest free region
  * which we can allocate the memory.
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 61228a6c69f8..c701b7a187f2 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -5,6 +5,7 @@
 #include <linux/fault-inject-usercopy.h>
 #include <linux/uio.h>
 #include <linux/pagemap.h>
+#include <linux/highmem.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/splice.h>
@@ -507,13 +508,6 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction,
 }
 EXPORT_SYMBOL(iov_iter_init);
 
-static void memzero_page(struct page *page, size_t offset, size_t len)
-{
-	char *addr = kmap_atomic(page);
-	memset(addr + offset, 0, len);
-	kunmap_atomic(addr);
-}
-
 static inline bool allocated(struct pipe_buffer *buf)
 {
 	return buf->ops == &default_pipe_buf_ops;
diff --git a/lib/list_sort.c b/lib/list_sort.c
index a926d96ffd44..1e1e37762799 100644
--- a/lib/list_sort.c
+++ b/lib/list_sort.c
@@ -137,7 +137,7 @@ static void merge_final(void *priv, list_cmp_func_t cmp, struct list_head *head,
  *
  *
  * The merging is controlled by "count", the number of elements in the
- * pending lists.  This is beautiully simple code, but rather subtle.
+ * pending lists.  This is beautifully simple code, but rather subtle.
  *
  * Each time we increment "count", we set one bit (bit k) and clear
  * bits k-1 .. 0.  Each time this happens (except the very first time
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 5b6116e81f9f..1d051ef66afe 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -828,7 +828,7 @@ int nla_strcmp(const struct nlattr *nla, const char *str)
 	int attrlen = nla_len(nla);
 	int d;
 
-	if (attrlen > 0 && buf[attrlen - 1] == '\0')
+	while (attrlen > 0 && buf[attrlen - 1] == '\0')
 		attrlen--;
 
 	d = attrlen - len;
diff --git a/lib/parser.c b/lib/parser.c
index 7a5769db389f..f1a6d90b8c34 100644
--- a/lib/parser.c
+++ b/lib/parser.c
@@ -98,7 +98,7 @@ static int match_one(char *s, const char *p, substring_t args[])
  * locations.
  *
  * Description: Detects which if any of a set of token strings has been passed
- * to it. Tokens can include up to MAX_OPT_ARGS instances of basic c-style
+ * to it. Tokens can include up to %MAX_OPT_ARGS instances of basic c-style
  * format identifiers which will be taken into account when matching the
  * tokens, and whose locations will be returned in the @args array.
  */
@@ -120,8 +120,10 @@ EXPORT_SYMBOL(match_token);
  * @base: base to use when converting string
  *
  * Description: Given a &substring_t and a base, attempts to parse the substring
- * as a number in that base. On success, sets @result to the integer represented
- * by the string and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
+ * as a number in that base.
+ *
+ * Return: On success, sets @result to the integer represented by the
+ * string and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
  */
 static int match_number(substring_t *s, int *result, int base)
 {
@@ -153,8 +155,10 @@ static int match_number(substring_t *s, int *result, int base)
  * @base: base to use when converting string
  *
  * Description: Given a &substring_t and a base, attempts to parse the substring
- * as a number in that base. On success, sets @result to the integer represented
- * by the string and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
+ * as a number in that base.
+ *
+ * Return: On success, sets @result to the integer represented by the
+ * string and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
  */
 static int match_u64int(substring_t *s, u64 *result, int base)
 {
@@ -178,9 +182,10 @@ static int match_u64int(substring_t *s, u64 *result, int base)
  * @s: substring_t to be scanned
  * @result: resulting integer on success
  *
- * Description: Attempts to parse the &substring_t @s as a decimal integer. On
- * success, sets @result to the integer represented by the string and returns 0.
- * Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
+ * Description: Attempts to parse the &substring_t @s as a decimal integer.
+ *
+ * Return: On success, sets @result to the integer represented by the string
+ * and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
  */
 int match_int(substring_t *s, int *result)
 {
@@ -188,14 +193,15 @@ int match_int(substring_t *s, int *result)
 }
 EXPORT_SYMBOL(match_int);
 
-/*
+/**
  * match_uint - scan a decimal representation of an integer from a substring_t
  * @s: substring_t to be scanned
  * @result: resulting integer on success
  *
- * Description: Attempts to parse the &substring_t @s as a decimal integer. On
- * success, sets @result to the integer represented by the string and returns 0.
- * Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
+ * Description: Attempts to parse the &substring_t @s as a decimal integer.
+ *
+ * Return: On success, sets @result to the integer represented by the string
+ * and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
  */
 int match_uint(substring_t *s, unsigned int *result)
 {
@@ -217,9 +223,10 @@ EXPORT_SYMBOL(match_uint);
  * @result: resulting unsigned long long on success
  *
  * Description: Attempts to parse the &substring_t @s as a long decimal
- * integer. On success, sets @result to the integer represented by the
- * string and returns 0.
- * Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
+ * integer.
+ *
+ * Return: On success, sets @result to the integer represented by the string
+ * and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
  */
 int match_u64(substring_t *s, u64 *result)
 {
@@ -232,9 +239,10 @@ EXPORT_SYMBOL(match_u64);
  * @s: substring_t to be scanned
  * @result: resulting integer on success
  *
- * Description: Attempts to parse the &substring_t @s as an octal integer. On
- * success, sets @result to the integer represented by the string and returns
- * 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
+ * Description: Attempts to parse the &substring_t @s as an octal integer.
+ *
+ * Return: On success, sets @result to the integer represented by the string
+ * and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
  */
 int match_octal(substring_t *s, int *result)
 {
@@ -248,8 +256,9 @@ EXPORT_SYMBOL(match_octal);
  * @result: resulting integer on success
  *
  * Description: Attempts to parse the &substring_t @s as a hexadecimal integer.
- * On success, sets @result to the integer represented by the string and
- * returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
+ *
+ * Return: On success, sets @result to the integer represented by the string
+ * and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
  */
 int match_hex(substring_t *s, int *result)
 {
@@ -263,10 +272,11 @@ EXPORT_SYMBOL(match_hex);
  * @str: the string to be parsed
  *
  * Description: Parse the string @str to check if matches wildcard
- * pattern @pattern. The pattern may contain two type wildcardes:
+ * pattern @pattern. The pattern may contain two types of wildcards:
  *   '*' - matches zero or more characters
  *   '?' - matches one character
- * If it's matched, return true, else return false.
+ *
+ * Return: If the @str matches the @pattern, return true, else return false.
  */
 bool match_wildcard(const char *pattern, const char *str)
 {
@@ -316,7 +326,9 @@ EXPORT_SYMBOL(match_wildcard);
  *
  * Description: Copy the characters in &substring_t @src to the
  * c-style string @dest.  Copy no more than @size - 1 characters, plus
- * the terminating NUL.  Return length of @src.
+ * the terminating NUL.
+ *
+ * Return: length of @src.
  */
 size_t match_strlcpy(char *dest, const substring_t *src, size_t size)
 {
@@ -338,6 +350,9 @@ EXPORT_SYMBOL(match_strlcpy);
  * Description: Allocates and returns a string filled with the contents of
  * the &substring_t @s. The caller is responsible for freeing the returned
  * string with kfree().
+ *
+ * Return: the address of the newly allocated NUL-terminated string or
+ * %NULL on error.
  */
 char *match_strdup(const substring_t *s)
 {
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index a1071cdefb5a..af9302141bcf 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -275,7 +275,7 @@ static void __percpu_ref_switch_mode(struct percpu_ref *ref,
 	wait_event_lock_irq(percpu_ref_switch_waitq, !data->confirm_switch,
 			    percpu_ref_switch_lock);
 
-	if (data->force_atomic || (ref->percpu_count_ptr & __PERCPU_REF_DEAD))
+	if (data->force_atomic || percpu_ref_is_dying(ref))
 		__percpu_ref_switch_to_atomic(ref, confirm_switch);
 	else
 		__percpu_ref_switch_to_percpu(ref);
@@ -385,7 +385,7 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 
 	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
 
-	WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_DEAD,
+	WARN_ONCE(percpu_ref_is_dying(ref),
 		  "%s called more than once on %ps!", __func__,
 		  ref->data->release);
 
@@ -465,7 +465,7 @@ void percpu_ref_resurrect(struct percpu_ref *ref)
 
 	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
 
-	WARN_ON_ONCE(!(ref->percpu_count_ptr & __PERCPU_REF_DEAD));
+	WARN_ON_ONCE(!percpu_ref_is_dying(ref));
 	WARN_ON_ONCE(__ref_is_percpu(ref, &percpu_count));
 
 	ref->percpu_count_ptr &= ~__PERCPU_REF_DEAD;
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 00f666d94486..ed610b75dc32 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -72,7 +72,7 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
 }
 EXPORT_SYMBOL(percpu_counter_set);
 
-/**
+/*
  * This function is both preempt and irq safe. The former is due to explicit
  * preemption disable. The latter is guaranteed by the fact that the slow path
  * is explicitly protected by an irq-safe spinlock whereas the fast patch uses
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 49f67a0c6e5d..df9179f4f441 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -71,7 +71,7 @@ static void *stack_slabs[STACK_ALLOC_MAX_SLABS];
 static int depot_index;
 static int next_slab_inited;
 static size_t depot_offset;
-static DEFINE_SPINLOCK(depot_lock);
+static DEFINE_RAW_SPINLOCK(depot_lock);
 
 static bool init_stack_slab(void **prealloc)
 {
@@ -305,7 +305,7 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries,
 			prealloc = page_address(page);
 	}
 
-	spin_lock_irqsave(&depot_lock, flags);
+	raw_spin_lock_irqsave(&depot_lock, flags);
 
 	found = find_stack(*bucket, entries, nr_entries, hash);
 	if (!found) {
@@ -329,7 +329,7 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries,
 		WARN_ON(!init_stack_slab(&prealloc));
 	}
 
-	spin_unlock_irqrestore(&depot_lock, flags);
+	raw_spin_unlock_irqrestore(&depot_lock, flags);
 exit:
 	if (prealloc) {
 		/* Nobody used this memory, ok to free it. */
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 785e724ce0d8..cacbbbdef768 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -54,6 +54,10 @@ static int kasan_test_init(struct kunit *test)
 
 	multishot = kasan_save_enable_multi_shot();
 	kasan_set_tagging_report_once(false);
+	fail_data.report_found = false;
+	fail_data.report_expected = false;
+	kunit_add_named_resource(test, NULL, NULL, &resource,
+					"kasan_data", &fail_data);
 	return 0;
 }
 
@@ -61,6 +65,7 @@ static void kasan_test_exit(struct kunit *test)
 {
 	kasan_set_tagging_report_once(true);
 	kasan_restore_multi_shot(multishot);
+	KUNIT_EXPECT_FALSE(test, fail_data.report_found);
 }
 
 /**
@@ -78,33 +83,31 @@ static void kasan_test_exit(struct kunit *test)
  * fields, it can reorder or optimize away the accesses to those fields.
  * Use READ/WRITE_ONCE() for the accesses and compiler barriers around the
  * expression to prevent that.
+ *
+ * In between KUNIT_EXPECT_KASAN_FAIL checks, fail_data.report_found is kept as
+ * false. This allows detecting KASAN reports that happen outside of the checks
+ * by asserting !fail_data.report_found at the start of KUNIT_EXPECT_KASAN_FAIL
+ * and in kasan_test_exit.
  */
-#define KUNIT_EXPECT_KASAN_FAIL(test, expression) do {		\
-	if (IS_ENABLED(CONFIG_KASAN_HW_TAGS) &&			\
-	    !kasan_async_mode_enabled())			\
-		migrate_disable();				\
-	WRITE_ONCE(fail_data.report_expected, true);		\
-	WRITE_ONCE(fail_data.report_found, false);		\
-	kunit_add_named_resource(test,				\
-				NULL,				\
-				NULL,				\
-				&resource,			\
-				"kasan_data", &fail_data);	\
-	barrier();						\
-	expression;						\
-	barrier();						\
-	if (kasan_async_mode_enabled())				\
-		kasan_force_async_fault();			\
-	barrier();						\
-	KUNIT_EXPECT_EQ(test,					\
-			READ_ONCE(fail_data.report_expected),	\
-			READ_ONCE(fail_data.report_found));	\
-	if (IS_ENABLED(CONFIG_KASAN_HW_TAGS) &&			\
-	    !kasan_async_mode_enabled()) {			\
-		if (READ_ONCE(fail_data.report_found))		\
-			kasan_enable_tagging_sync();		\
-		migrate_enable();				\
-	}							\
+#define KUNIT_EXPECT_KASAN_FAIL(test, expression) do {			\
+	if (IS_ENABLED(CONFIG_KASAN_HW_TAGS) &&				\
+	    !kasan_async_mode_enabled())				\
+		migrate_disable();					\
+	KUNIT_EXPECT_FALSE(test, READ_ONCE(fail_data.report_found));	\
+	WRITE_ONCE(fail_data.report_expected, true);			\
+	barrier();							\
+	expression;							\
+	barrier();							\
+	KUNIT_EXPECT_EQ(test,						\
+			READ_ONCE(fail_data.report_expected),		\
+			READ_ONCE(fail_data.report_found));		\
+	if (IS_ENABLED(CONFIG_KASAN_HW_TAGS)) {				\
+		if (READ_ONCE(fail_data.report_found))			\
+			kasan_enable_tagging_sync();			\
+		migrate_enable();					\
+	}								\
+	WRITE_ONCE(fail_data.report_found, false);			\
+	WRITE_ONCE(fail_data.report_expected, false);			\
 } while (0)
 
 #define KASAN_TEST_NEEDS_CONFIG_ON(test, config) do {			\
@@ -651,8 +654,20 @@ static char global_array[10];
 
 static void kasan_global_oob(struct kunit *test)
 {
-	volatile int i = 3;
-	char *p = &global_array[ARRAY_SIZE(global_array) + i];
+	/*
+	 * Deliberate out-of-bounds access. To prevent CONFIG_UBSAN_LOCAL_BOUNDS
+	 * from failing here and panicing the kernel, access the array via a
+	 * volatile pointer, which will prevent the compiler from being able to
+	 * determine the array bounds.
+	 *
+	 * This access uses a volatile pointer to char (char *volatile) rather
+	 * than the more conventional pointer to volatile char (volatile char *)
+	 * because we want to prevent the compiler from making inferences about
+	 * the pointer itself (i.e. its array bounds), not the data that it
+	 * refers to.
+	 */
+	char *volatile array = global_array;
+	char *p = &array[ARRAY_SIZE(global_array) + 3];
 
 	/* Only generic mode instruments globals. */
 	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC);
@@ -700,8 +715,9 @@ static void ksize_uaf(struct kunit *test)
 static void kasan_stack_oob(struct kunit *test)
 {
 	char stack_array[10];
-	volatile int i = OOB_TAG_OFF;
-	char *p = &stack_array[ARRAY_SIZE(stack_array) + i];
+	/* See comment in kasan_global_oob. */
+	char *volatile array = stack_array;
+	char *p = &array[ARRAY_SIZE(stack_array) + OOB_TAG_OFF];
 
 	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_STACK);
 
@@ -712,7 +728,9 @@ static void kasan_alloca_oob_left(struct kunit *test)
 {
 	volatile int i = 10;
 	char alloca_array[i];
-	char *p = alloca_array - 1;
+	/* See comment in kasan_global_oob. */
+	char *volatile array = alloca_array;
+	char *p = array - 1;
 
 	/* Only generic mode instruments dynamic allocas. */
 	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC);
@@ -725,7 +743,9 @@ static void kasan_alloca_oob_right(struct kunit *test)
 {
 	volatile int i = 10;
 	char alloca_array[i];
-	char *p = alloca_array + i;
+	/* See comment in kasan_global_oob. */
+	char *volatile array = alloca_array;
+	char *p = array + i;
 
 	/* Only generic mode instruments dynamic allocas. */
 	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC);
@@ -1049,14 +1069,14 @@ static void match_all_mem_tag(struct kunit *test)
 			continue;
 
 		/* Mark the first memory granule with the chosen memory tag. */
-		kasan_poison(ptr, KASAN_GRANULE_SIZE, (u8)tag);
+		kasan_poison(ptr, KASAN_GRANULE_SIZE, (u8)tag, false);
 
 		/* This access must cause a KASAN report. */
 		KUNIT_EXPECT_KASAN_FAIL(test, *ptr = 0);
 	}
 
 	/* Recover the memory tag and free. */
-	kasan_poison(ptr, KASAN_GRANULE_SIZE, get_tag(ptr));
+	kasan_poison(ptr, KASAN_GRANULE_SIZE, get_tag(ptr), false);
 	kfree(ptr);
 }
 
diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c
index 5cf2fe9aab9e..01e9543de566 100644
--- a/lib/test_vmalloc.c
+++ b/lib/test_vmalloc.c
@@ -23,8 +23,8 @@
 	module_param(name, type, 0444);			\
 	MODULE_PARM_DESC(name, msg)				\
 
-__param(bool, single_cpu_test, false,
-	"Use single first online CPU to run tests");
+__param(int, nr_threads, 0,
+	"Number of workers to perform tests(min: 1 max: USHRT_MAX)");
 
 __param(bool, sequential_test_order, false,
 	"Use sequential stress tests order");
@@ -47,19 +47,10 @@ __param(int, run_test_mask, INT_MAX,
 		"\t\tid: 128,  name: pcpu_alloc_test\n"
 		"\t\tid: 256,  name: kvfree_rcu_1_arg_vmalloc_test\n"
 		"\t\tid: 512,  name: kvfree_rcu_2_arg_vmalloc_test\n"
-		"\t\tid: 1024, name: kvfree_rcu_1_arg_slab_test\n"
-		"\t\tid: 2048, name: kvfree_rcu_2_arg_slab_test\n"
 		/* Add a new test case description here. */
 );
 
 /*
- * Depends on single_cpu_test parameter. If it is true, then
- * use first online CPU to trigger a test on, otherwise go with
- * all online CPUs.
- */
-static cpumask_t cpus_run_test_mask = CPU_MASK_NONE;
-
-/*
  * Read write semaphore for synchronization of setup
  * phase that is done in main thread and workers.
  */
@@ -363,42 +354,6 @@ kvfree_rcu_2_arg_vmalloc_test(void)
 	return 0;
 }
 
-static int
-kvfree_rcu_1_arg_slab_test(void)
-{
-	struct test_kvfree_rcu *p;
-	int i;
-
-	for (i = 0; i < test_loop_count; i++) {
-		p = kmalloc(sizeof(*p), GFP_KERNEL);
-		if (!p)
-			return -1;
-
-		p->array[0] = 'a';
-		kvfree_rcu(p);
-	}
-
-	return 0;
-}
-
-static int
-kvfree_rcu_2_arg_slab_test(void)
-{
-	struct test_kvfree_rcu *p;
-	int i;
-
-	for (i = 0; i < test_loop_count; i++) {
-		p = kmalloc(sizeof(*p), GFP_KERNEL);
-		if (!p)
-			return -1;
-
-		p->array[0] = 'a';
-		kvfree_rcu(p, rcu);
-	}
-
-	return 0;
-}
-
 struct test_case_desc {
 	const char *test_name;
 	int (*test_func)(void);
@@ -415,8 +370,6 @@ static struct test_case_desc test_case_array[] = {
 	{ "pcpu_alloc_test", pcpu_alloc_test },
 	{ "kvfree_rcu_1_arg_vmalloc_test", kvfree_rcu_1_arg_vmalloc_test },
 	{ "kvfree_rcu_2_arg_vmalloc_test", kvfree_rcu_2_arg_vmalloc_test },
-	{ "kvfree_rcu_1_arg_slab_test", kvfree_rcu_1_arg_slab_test },
-	{ "kvfree_rcu_2_arg_slab_test", kvfree_rcu_2_arg_slab_test },
 	/* Add a new test case here. */
 };
 
@@ -426,16 +379,13 @@ struct test_case_data {
 	u64 time;
 };
 
-/* Split it to get rid of: WARNING: line over 80 characters */
-static struct test_case_data
-	per_cpu_test_data[NR_CPUS][ARRAY_SIZE(test_case_array)];
-
 static struct test_driver {
 	struct task_struct *task;
+	struct test_case_data data[ARRAY_SIZE(test_case_array)];
+
 	unsigned long start;
 	unsigned long stop;
-	int cpu;
-} per_cpu_test_driver[NR_CPUS];
+} *tdriver;
 
 static void shuffle_array(int *arr, int n)
 {
@@ -463,9 +413,6 @@ static int test_func(void *private)
 	ktime_t kt;
 	u64 delta;
 
-	if (set_cpus_allowed_ptr(current, cpumask_of(t->cpu)) < 0)
-		pr_err("Failed to set affinity to %d CPU\n", t->cpu);
-
 	for (i = 0; i < ARRAY_SIZE(test_case_array); i++)
 		random_array[i] = i;
 
@@ -490,9 +437,9 @@ static int test_func(void *private)
 		kt = ktime_get();
 		for (j = 0; j < test_repeat_count; j++) {
 			if (!test_case_array[index].test_func())
-				per_cpu_test_data[t->cpu][index].test_passed++;
+				t->data[index].test_passed++;
 			else
-				per_cpu_test_data[t->cpu][index].test_failed++;
+				t->data[index].test_failed++;
 		}
 
 		/*
@@ -501,7 +448,7 @@ static int test_func(void *private)
 		delta = (u64) ktime_us_delta(ktime_get(), kt);
 		do_div(delta, (u32) test_repeat_count);
 
-		per_cpu_test_data[t->cpu][index].time = delta;
+		t->data[index].time = delta;
 	}
 	t->stop = get_cycles();
 
@@ -517,53 +464,56 @@ static int test_func(void *private)
 	return 0;
 }
 
-static void
+static int
 init_test_configurtion(void)
 {
 	/*
-	 * Reset all data of all CPUs.
+	 * A maximum number of workers is defined as hard-coded
+	 * value and set to USHRT_MAX. We add such gap just in
+	 * case and for potential heavy stressing.
 	 */
-	memset(per_cpu_test_data, 0, sizeof(per_cpu_test_data));
+	nr_threads = clamp(nr_threads, 1, (int) USHRT_MAX);
 
-	if (single_cpu_test)
-		cpumask_set_cpu(cpumask_first(cpu_online_mask),
-			&cpus_run_test_mask);
-	else
-		cpumask_and(&cpus_run_test_mask, cpu_online_mask,
-			cpu_online_mask);
+	/* Allocate the space for test instances. */
+	tdriver = kvcalloc(nr_threads, sizeof(*tdriver), GFP_KERNEL);
+	if (tdriver == NULL)
+		return -1;
 
 	if (test_repeat_count <= 0)
 		test_repeat_count = 1;
 
 	if (test_loop_count <= 0)
 		test_loop_count = 1;
+
+	return 0;
 }
 
 static void do_concurrent_test(void)
 {
-	int cpu, ret;
+	int i, ret;
 
 	/*
 	 * Set some basic configurations plus sanity check.
 	 */
-	init_test_configurtion();
+	ret = init_test_configurtion();
+	if (ret < 0)
+		return;
 
 	/*
 	 * Put on hold all workers.
 	 */
 	down_write(&prepare_for_test_rwsem);
 
-	for_each_cpu(cpu, &cpus_run_test_mask) {
-		struct test_driver *t = &per_cpu_test_driver[cpu];
+	for (i = 0; i < nr_threads; i++) {
+		struct test_driver *t = &tdriver[i];
 
-		t->cpu = cpu;
-		t->task = kthread_run(test_func, t, "vmalloc_test/%d", cpu);
+		t->task = kthread_run(test_func, t, "vmalloc_test/%d", i);
 
 		if (!IS_ERR(t->task))
 			/* Success. */
 			atomic_inc(&test_n_undone);
 		else
-			pr_err("Failed to start kthread for %d CPU\n", cpu);
+			pr_err("Failed to start %d kthread\n", i);
 	}
 
 	/*
@@ -581,29 +531,31 @@ static void do_concurrent_test(void)
 		ret = wait_for_completion_timeout(&test_all_done_comp, HZ);
 	} while (!ret);
 
-	for_each_cpu(cpu, &cpus_run_test_mask) {
-		struct test_driver *t = &per_cpu_test_driver[cpu];
-		int i;
+	for (i = 0; i < nr_threads; i++) {
+		struct test_driver *t = &tdriver[i];
+		int j;
 
 		if (!IS_ERR(t->task))
 			kthread_stop(t->task);
 
-		for (i = 0; i < ARRAY_SIZE(test_case_array); i++) {
-			if (!((run_test_mask & (1 << i)) >> i))
+		for (j = 0; j < ARRAY_SIZE(test_case_array); j++) {
+			if (!((run_test_mask & (1 << j)) >> j))
 				continue;
 
 			pr_info(
 				"Summary: %s passed: %d failed: %d repeat: %d loops: %d avg: %llu usec\n",
-				test_case_array[i].test_name,
-				per_cpu_test_data[cpu][i].test_passed,
-				per_cpu_test_data[cpu][i].test_failed,
+				test_case_array[j].test_name,
+				t->data[j].test_passed,
+				t->data[j].test_failed,
 				test_repeat_count, test_loop_count,
-				per_cpu_test_data[cpu][i].time);
+				t->data[j].time);
 		}
 
-		pr_info("All test took CPU%d=%lu cycles\n",
-			cpu, t->stop - t->start);
+		pr_info("All test took worker%d=%lu cycles\n",
+			i, t->stop - t->start);
 	}
+
+	kvfree(tdriver);
 }
 
 static int vmalloc_test_init(void)