Merge branch 'linus' into x86/urgent, to pick up dependent changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

45 files changed, 1793 insertions, 746 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index e86975bfca6a..3577609b61be 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -18,6 +18,23 @@ config RAID6_PQ_BENCHMARK
 	  Benchmark all available RAID6 PQ functions on init and choose the
 	  fastest one.
 
+config PACKING
+	bool "Generic bitfield packing and unpacking"
+	default n
+	help
+	  This option provides the packing() helper function, which permits
+	  converting bitfields between a CPU-usable representation and a
+	  memory representation that can have any combination of these quirks:
+	    - Is little endian (bytes are reversed within a 32-bit group)
+	    - The least-significant 32-bit word comes first (within a 64-bit
+	      group)
+	    - The most significant bit of a byte is at its right (bit 0 of a
+	      register description is numerically 2^7).
+	  Drivers may use these helpers to match the bit indices as described
+	  in the data sheets of the peripherals they are in control of.
+
+	  When in doubt, say N.
+
 config BITREVERSE
 	tristate
 
@@ -29,9 +46,6 @@ config HAVE_ARCH_BITREVERSE
 	  This option enables the use of hardware bit-reversal instructions on
 	  architectures which support such operations.
 
-config RATIONAL
-	bool
-
 config GENERIC_STRNCPY_FROM_USER
 	bool
 
@@ -44,6 +58,8 @@ config GENERIC_NET_UTILS
 config GENERIC_FIND_FIRST_BIT
 	bool
 
+source "lib/math/Kconfig"
+
 config NO_GENERIC_PCI_IOPORT_MAP
 	bool
 
@@ -514,12 +530,6 @@ config LRU_CACHE
 config CLZ_TAB
 	bool
 
-config CORDIC
-	tristate "CORDIC algorithm"
-	help
-	  This option provides an implementation of the CORDIC algorithm;
-	  calculations are in fixed point. Module will be called cordic.
-
 config DDR
 	bool "JEDEC DDR data"
 	help
@@ -611,9 +621,6 @@ config SBITMAP
 config PARMAN
 	tristate "parman" if COMPILE_TEST
 
-config PRIME_NUMBERS
-	tristate
-
 config STRING_SELFTEST
 	tristate "Test string functions"
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index d5a4a4036d2f..fdfa173651eb 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -219,6 +219,14 @@ config DEBUG_INFO_DWARF4
 	  But it significantly improves the success of resolving
 	  variables in gdb on optimized code.
 
+config DEBUG_INFO_BTF
+	bool "Generate BTF typeinfo"
+	depends on DEBUG_INFO
+	help
+	  Generate deduplicated BTF type information from DWARF debug info.
+	  Turning this on expects presence of pahole tool, which will convert
+	  DWARF type info into equivalent deduplicated BTF type info.
+
 config GDB_SCRIPTS
 	bool "Provide GDB scripts for kernel debugging"
 	depends on DEBUG_INFO
@@ -310,6 +318,20 @@ config HEADERS_CHECK
 	  exported to $(INSTALL_HDR_PATH) (usually 'usr/include' in
 	  your build tree), to make sure they're suitable.
 
+config OPTIMIZE_INLINING
+	bool "Allow compiler to uninline functions marked 'inline'"
+	help
+	  This option determines if the kernel forces gcc to inline the functions
+	  developers have marked 'inline'. Doing so takes away freedom from gcc to
+	  do what it thinks is best, which is desirable for the gcc 3.x series of
+	  compilers. The gcc 4.x series have a rewritten inlining algorithm and
+	  enabling this option will generate a smaller kernel there. Hopefully
+	  this algorithm is so good that allowing gcc 4.x and above to make the
+	  decision will become the default in the future. Until then this option
+	  is there to test gcc for this.
+
+	  If unsure, say N.
+
 config DEBUG_SECTION_MISMATCH
 	bool "Enable full Section mismatch analysis"
 	help
@@ -438,6 +460,15 @@ config DEBUG_KERNEL
 	  Say Y here if you are developing drivers or trying to debug and
 	  identify kernel problems.
 
+config DEBUG_MISC
+	bool "Miscellaneous debug code"
+	default DEBUG_KERNEL
+	depends on DEBUG_KERNEL
+	help
+	  Say Y here if you need to enable miscellaneous debug code that should
+	  be under a more specific debug option but isn't.
+
+
 menu "Memory Debugging"
 
 source "mm/Kconfig.debug"
@@ -1350,7 +1381,7 @@ config DEBUG_LIST
 
 	  If unsure, say N.
 
-config DEBUG_PI_LIST
+config DEBUG_PLIST
 	bool "Debug priority linked list manipulation"
 	depends on DEBUG_KERNEL
 	help
@@ -1769,6 +1800,9 @@ config TEST_HEXDUMP
 config TEST_STRING_HELPERS
 	tristate "Test functions located in the string_helpers module at runtime"
 
+config TEST_STRSCPY
+	tristate "Test strscpy*() family of functions at runtime"
+
 config TEST_KSTRTOX
 	tristate "Test kstrto*() family of functions at runtime"
 
@@ -1927,7 +1961,6 @@ config TEST_STATIC_KEYS
 config TEST_KMOD
 	tristate "kmod stress tester"
 	depends on m
-	depends on BLOCK && (64BIT || LBDAF)	  # for XFS, BTRFS
 	depends on NETDEVICES && NET_CORE && INET # for TUN
 	depends on BLOCK
 	select TEST_LKM
diff --git a/lib/Makefile b/lib/Makefile
index e16e7aadc41a..fb7697031a79 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -30,7 +30,7 @@ endif
 
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o timerqueue.o xarray.o \
-	 idr.o int_sqrt.o extable.o \
+	 idr.o extable.o \
 	 sha1.o chacha.o irq_regs.o argv_split.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
@@ -44,11 +44,11 @@ lib-$(CONFIG_SMP) += cpumask.o
 lib-y	+= kobject.o klist.o
 obj-y	+= lockref.o
 
-obj-y += bcd.o div64.o sort.o parser.o debug_locks.o random32.o \
+obj-y += bcd.o sort.o parser.o debug_locks.o random32.o \
 	 bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \
-	 gcd.o lcm.o list_sort.o uuid.o iov_iter.o clz_ctz.o \
+	 list_sort.o uuid.o iov_iter.o clz_ctz.o \
 	 bsearch.o find_bit.o llist.o memweight.o kfifo.o \
-	 percpu-refcount.o rhashtable.o reciprocal_div.o \
+	 percpu-refcount.o rhashtable.o \
 	 once.o refcount.o usercopy.o errseq.o bucket_locks.o \
 	 generic-radix-tree.o
 obj-$(CONFIG_STRING_SELFTEST) += test_string.o
@@ -81,6 +81,7 @@ obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_keys.o
 obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_key_base.o
 obj-$(CONFIG_TEST_PRINTF) += test_printf.o
 obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o
+obj-$(CONFIG_TEST_STRSCPY) += test_strscpy.o
 obj-$(CONFIG_TEST_BITFIELD) += test_bitfield.o
 obj-$(CONFIG_TEST_UUID) += test_uuid.o
 obj-$(CONFIG_TEST_XARRAY) += test_xarray.o
@@ -101,6 +102,8 @@ endif
 obj-$(CONFIG_DEBUG_INFO_REDUCED) += debug_info.o
 CFLAGS_debug_info.o += $(call cc-option, -femit-struct-debug-detailed=any)
 
+obj-y += math/
+
 obj-$(CONFIG_GENERIC_IOMAP) += iomap.o
 obj-$(CONFIG_GENERIC_PCI_IOMAP) += pci_iomap.o
 obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o
@@ -119,7 +122,7 @@ obj-$(CONFIG_DEBUG_LIST) += list_debug.o
 obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
 
 obj-$(CONFIG_BITREVERSE) += bitrev.o
-obj-$(CONFIG_RATIONAL)	+= rational.o
+obj-$(CONFIG_PACKING)	+= packing.o
 obj-$(CONFIG_CRC_CCITT)	+= crc-ccitt.o
 obj-$(CONFIG_CRC16)	+= crc16.o
 obj-$(CONFIG_CRC_T10DIF)+= crc-t10dif.o
@@ -193,8 +196,6 @@ obj-$(CONFIG_ATOMIC64_SELFTEST) += atomic64_test.o
 
 obj-$(CONFIG_CPU_RMAP) += cpu_rmap.o
 
-obj-$(CONFIG_CORDIC) += cordic.o
-
 obj-$(CONFIG_DQL) += dynamic_queue_limits.o
 
 obj-$(CONFIG_GLOB) += glob.o
@@ -236,8 +237,6 @@ obj-$(CONFIG_ASN1) += asn1_decoder.o
 
 obj-$(CONFIG_FONT_SUPPORT) += fonts/
 
-obj-$(CONFIG_PRIME_NUMBERS) += prime_numbers.o
-
 hostprogs-y	:= gen_crc32table
 hostprogs-y	+= gen_crc64table
 clean-files	:= crc32table.h
diff --git a/lib/asn1_decoder.c b/lib/asn1_decoder.c
index dc14beae2c9a..8f3d207d2b00 100644
--- a/lib/asn1_decoder.c
+++ b/lib/asn1_decoder.c
@@ -385,6 +385,8 @@ next_op:
 	case ASN1_OP_END_SET_ACT:
 		if (unlikely(!(flags & FLAG_MATCHED)))
 			goto tag_mismatch;
+		/* fall through */
+
 	case ASN1_OP_END_SEQ:
 	case ASN1_OP_END_SET_OF:
 	case ASN1_OP_END_SEQ_OF:
@@ -450,6 +452,8 @@ next_op:
 			pc += asn1_op_lengths[op];
 			goto next_op;
 		}
+		/* fall through */
+
 	case ASN1_OP_ACT:
 		ret = actions[machine[pc + 1]](context, hdr, tag, data + tdp, len);
 		if (ret < 0)
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 98872e9025da..f235434df87b 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -20,6 +20,8 @@
 
 #include <asm/page.h>
 
+#include "kstrtox.h"
+
 /**
  * DOC: bitmap introduction
  *
@@ -477,12 +479,128 @@ int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp,
 }
 EXPORT_SYMBOL(bitmap_print_to_pagebuf);
 
+/*
+ * Region 9-38:4/10 describes the following bitmap structure:
+ * 0	   9  12    18			38
+ * .........****......****......****......
+ *	    ^  ^     ^			 ^
+ *      start  off   group_len	       end
+ */
+struct region {
+	unsigned int start;
+	unsigned int off;
+	unsigned int group_len;
+	unsigned int end;
+};
+
+static int bitmap_set_region(const struct region *r,
+				unsigned long *bitmap, int nbits)
+{
+	unsigned int start;
+
+	if (r->end >= nbits)
+		return -ERANGE;
+
+	for (start = r->start; start <= r->end; start += r->group_len)
+		bitmap_set(bitmap, start, min(r->end - start + 1, r->off));
+
+	return 0;
+}
+
+static int bitmap_check_region(const struct region *r)
+{
+	if (r->start > r->end || r->group_len == 0 || r->off > r->group_len)
+		return -EINVAL;
+
+	return 0;
+}
+
+static const char *bitmap_getnum(const char *str, unsigned int *num)
+{
+	unsigned long long n;
+	unsigned int len;
+
+	len = _parse_integer(str, 10, &n);
+	if (!len)
+		return ERR_PTR(-EINVAL);
+	if (len & KSTRTOX_OVERFLOW || n != (unsigned int)n)
+		return ERR_PTR(-EOVERFLOW);
+
+	*num = n;
+	return str + len;
+}
+
+static inline bool end_of_str(char c)
+{
+	return c == '\0' || c == '\n';
+}
+
+static inline bool __end_of_region(char c)
+{
+	return isspace(c) || c == ',';
+}
+
+static inline bool end_of_region(char c)
+{
+	return __end_of_region(c) || end_of_str(c);
+}
+
+/*
+ * The format allows commas and whitespases at the beginning
+ * of the region.
+ */
+static const char *bitmap_find_region(const char *str)
+{
+	while (__end_of_region(*str))
+		str++;
+
+	return end_of_str(*str) ? NULL : str;
+}
+
+static const char *bitmap_parse_region(const char *str, struct region *r)
+{
+	str = bitmap_getnum(str, &r->start);
+	if (IS_ERR(str))
+		return str;
+
+	if (end_of_region(*str))
+		goto no_end;
+
+	if (*str != '-')
+		return ERR_PTR(-EINVAL);
+
+	str = bitmap_getnum(str + 1, &r->end);
+	if (IS_ERR(str))
+		return str;
+
+	if (end_of_region(*str))
+		goto no_pattern;
+
+	if (*str != ':')
+		return ERR_PTR(-EINVAL);
+
+	str = bitmap_getnum(str + 1, &r->off);
+	if (IS_ERR(str))
+		return str;
+
+	if (*str != '/')
+		return ERR_PTR(-EINVAL);
+
+	return bitmap_getnum(str + 1, &r->group_len);
+
+no_end:
+	r->end = r->start;
+no_pattern:
+	r->off = r->end + 1;
+	r->group_len = r->end + 1;
+
+	return end_of_str(*str) ? NULL : str;
+}
+
 /**
- * __bitmap_parselist - convert list format ASCII string to bitmap
- * @buf: read nul-terminated user string from this buffer
- * @buflen: buffer size in bytes.  If string is smaller than this
- *    then it must be terminated with a \0.
- * @is_user: location of buffer, 0 indicates kernel space
+ * bitmap_parselist - convert list format ASCII string to bitmap
+ * @buf: read user string from this buffer; must be terminated
+ *    with a \0 or \n.
  * @maskp: write resulting mask here
  * @nmaskbits: number of bits in mask to be written
  *
@@ -498,127 +616,38 @@ EXPORT_SYMBOL(bitmap_print_to_pagebuf);
  *
  * Returns: 0 on success, -errno on invalid input strings. Error values:
  *
- *   - ``-EINVAL``: second number in range smaller than first
+ *   - ``-EINVAL``: wrong region format
  *   - ``-EINVAL``: invalid character in string
  *   - ``-ERANGE``: bit number specified too large for mask
+ *   - ``-EOVERFLOW``: integer overflow in the input parameters
  */
-static int __bitmap_parselist(const char *buf, unsigned int buflen,
-		int is_user, unsigned long *maskp,
-		int nmaskbits)
+int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits)
 {
-	unsigned int a, b, old_a, old_b;
-	unsigned int group_size, used_size, off;
-	int c, old_c, totaldigits, ndigits;
-	const char __user __force *ubuf = (const char __user __force *)buf;
-	int at_start, in_range, in_partial_range;
+	struct region r;
+	long ret;
 
-	totaldigits = c = 0;
-	old_a = old_b = 0;
-	group_size = used_size = 0;
 	bitmap_zero(maskp, nmaskbits);
-	do {
-		at_start = 1;
-		in_range = 0;
-		in_partial_range = 0;
-		a = b = 0;
-		ndigits = totaldigits;
-
-		/* Get the next cpu# or a range of cpu#'s */
-		while (buflen) {
-			old_c = c;
-			if (is_user) {
-				if (__get_user(c, ubuf++))
-					return -EFAULT;
-			} else
-				c = *buf++;
-			buflen--;
-			if (isspace(c))
-				continue;
-
-			/* A '\0' or a ',' signal the end of a cpu# or range */
-			if (c == '\0' || c == ',')
-				break;
-			/*
-			* whitespaces between digits are not allowed,
-			* but it's ok if whitespaces are on head or tail.
-			* when old_c is whilespace,
-			* if totaldigits == ndigits, whitespace is on head.
-			* if whitespace is on tail, it should not run here.
-			* as c was ',' or '\0',
-			* the last code line has broken the current loop.
-			*/
-			if ((totaldigits != ndigits) && isspace(old_c))
-				return -EINVAL;
 
-			if (c == '/') {
-				used_size = a;
-				at_start = 1;
-				in_range = 0;
-				a = b = 0;
-				continue;
-			}
+	while (buf) {
+		buf = bitmap_find_region(buf);
+		if (buf == NULL)
+			return 0;
 
-			if (c == ':') {
-				old_a = a;
-				old_b = b;
-				at_start = 1;
-				in_range = 0;
-				in_partial_range = 1;
-				a = b = 0;
-				continue;
-			}
+		buf = bitmap_parse_region(buf, &r);
+		if (IS_ERR(buf))
+			return PTR_ERR(buf);
 
-			if (c == '-') {
-				if (at_start || in_range)
-					return -EINVAL;
-				b = 0;
-				in_range = 1;
-				at_start = 1;
-				continue;
-			}
+		ret = bitmap_check_region(&r);
+		if (ret)
+			return ret;
 
-			if (!isdigit(c))
-				return -EINVAL;
+		ret = bitmap_set_region(&r, maskp, nmaskbits);
+		if (ret)
+			return ret;
+	}
 
-			b = b * 10 + (c - '0');
-			if (!in_range)
-				a = b;
-			at_start = 0;
-			totaldigits++;
-		}
-		if (ndigits == totaldigits)
-			continue;
-		if (in_partial_range) {
-			group_size = a;
-			a = old_a;
-			b = old_b;
-			old_a = old_b = 0;
-		} else {
-			used_size = group_size = b - a + 1;
-		}
-		/* if no digit is after '-', it's wrong*/
-		if (at_start && in_range)
-			return -EINVAL;
-		if (!(a <= b) || group_size == 0 || !(used_size <= group_size))
-			return -EINVAL;
-		if (b >= nmaskbits)
-			return -ERANGE;
-		while (a <= b) {
-			off = min(b - a + 1, used_size);
-			bitmap_set(maskp, a, off);
-			a += group_size;
-		}
-	} while (buflen && c == ',');
 	return 0;
 }
-
-int bitmap_parselist(const char *bp, unsigned long *maskp, int nmaskbits)
-{
-	char *nl  = strchrnul(bp, '\n');
-	int len = nl - bp;
-
-	return __bitmap_parselist(bp, len, 0, maskp, nmaskbits);
-}
 EXPORT_SYMBOL(bitmap_parselist);
 
 
@@ -632,23 +661,27 @@ EXPORT_SYMBOL(bitmap_parselist);
  * @nmaskbits: size of bitmap, in bits.
  *
  * Wrapper for bitmap_parselist(), providing it with user buffer.
- *
- * We cannot have this as an inline function in bitmap.h because it needs
- * linux/uaccess.h to get the access_ok() declaration and this causes
- * cyclic dependencies.
  */
 int bitmap_parselist_user(const char __user *ubuf,
 			unsigned int ulen, unsigned long *maskp,
 			int nmaskbits)
 {
-	if (!access_ok(ubuf, ulen))
-		return -EFAULT;
-	return __bitmap_parselist((const char __force *)ubuf,
-					ulen, 1, maskp, nmaskbits);
+	char *buf;
+	int ret;
+
+	buf = memdup_user_nul(ubuf, ulen);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
+	ret = bitmap_parselist(buf, maskp, nmaskbits);
+
+	kfree(buf);
+	return ret;
 }
 EXPORT_SYMBOL(bitmap_parselist_user);
 
 
+#ifdef CONFIG_NUMA
 /**
  * bitmap_pos_to_ord - find ordinal of set bit at given position in bitmap
  *	@buf: pointer to a bitmap
@@ -757,7 +790,6 @@ void bitmap_remap(unsigned long *dst, const unsigned long *src,
 			set_bit(bitmap_ord_to_pos(new, n % w, nbits), dst);
 	}
 }
-EXPORT_SYMBOL(bitmap_remap);
 
 /**
  * bitmap_bitremap - Apply map defined by a pair of bitmaps to a single bit
@@ -795,7 +827,6 @@ int bitmap_bitremap(int oldbit, const unsigned long *old,
 	else
 		return bitmap_ord_to_pos(new, n % w, bits);
 }
-EXPORT_SYMBOL(bitmap_bitremap);
 
 /**
  * bitmap_onto - translate one bitmap relative to another
@@ -930,7 +961,6 @@ void bitmap_onto(unsigned long *dst, const unsigned long *orig,
 		m++;
 	}
 }
-EXPORT_SYMBOL(bitmap_onto);
 
 /**
  * bitmap_fold - fold larger bitmap into smaller, modulo specified size
@@ -955,7 +985,7 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig,
 	for_each_set_bit(oldbit, orig, nbits)
 		set_bit(oldbit % sz, dst);
 }
-EXPORT_SYMBOL(bitmap_fold);
+#endif /* CONFIG_NUMA */
 
 /*
  * Common code for bitmap_*_region() routines.
diff --git a/lib/cmdline.c b/lib/cmdline.c
index 171c19b6888e..dc59d6216318 100644
--- a/lib/cmdline.c
+++ b/lib/cmdline.c
@@ -135,18 +135,23 @@ unsigned long long memparse(const char *ptr, char **retptr)
 	case 'E':
 	case 'e':
 		ret <<= 10;
+		/* fall through */
 	case 'P':
 	case 'p':
 		ret <<= 10;
+		/* fall through */
 	case 'T':
 	case 't':
 		ret <<= 10;
+		/* fall through */
 	case 'G':
 	case 'g':
 		ret <<= 10;
+		/* fall through */
 	case 'M':
 	case 'm':
 		ret <<= 10;
+		/* fall through */
 	case 'K':
 	case 'k':
 		ret <<= 10;
diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c
index 4d0d47c1ffbd..e89ebfdbb0fc 100644
--- a/lib/crc-t10dif.c
+++ b/lib/crc-t10dif.c
@@ -69,7 +69,6 @@ __u16 crc_t10dif_update(__u16 crc, const unsigned char *buffer, size_t len)
 
 	rcu_read_lock();
 	desc.shash.tfm = rcu_dereference(crct10dif_tfm);
-	desc.shash.flags = 0;
 	*(__u16 *)desc.ctx = crc;
 
 	err = crypto_shash_update(&desc.shash, buffer, len);
diff --git a/lib/digsig.c b/lib/digsig.c
index 6ba6fcd92dd1..3b0a579bdcdf 100644
--- a/lib/digsig.c
+++ b/lib/digsig.c
@@ -240,7 +240,6 @@ int digsig_verify(struct key *keyring, const char *sig, int siglen,
 		goto err;
 
 	desc->tfm = shash;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	crypto_shash_init(desc);
 	crypto_shash_update(desc, data, datalen);
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index 7bdf98c37e91..8a16c2d498e9 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -37,6 +37,8 @@
 #include <linux/device.h>
 #include <linux/netdevice.h>
 
+#include <rdma/ib_verbs.h>
+
 extern struct _ddebug __start___verbose[];
 extern struct _ddebug __stop___verbose[];
 
@@ -636,6 +638,41 @@ EXPORT_SYMBOL(__dynamic_netdev_dbg);
 
 #endif
 
+#if IS_ENABLED(CONFIG_INFINIBAND)
+
+void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
+			 const struct ib_device *ibdev, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	if (ibdev && ibdev->dev.parent) {
+		char buf[PREFIX_SIZE];
+
+		dev_printk_emit(LOGLEVEL_DEBUG, ibdev->dev.parent,
+				"%s%s %s %s: %pV",
+				dynamic_emit_prefix(descriptor, buf),
+				dev_driver_string(ibdev->dev.parent),
+				dev_name(ibdev->dev.parent),
+				dev_name(&ibdev->dev),
+				&vaf);
+	} else if (ibdev) {
+		printk(KERN_DEBUG "%s: %pV", dev_name(&ibdev->dev), &vaf);
+	} else {
+		printk(KERN_DEBUG "(NULL ib_device): %pV", &vaf);
+	}
+
+	va_end(args);
+}
+EXPORT_SYMBOL(__dynamic_ibdev_dbg);
+
+#endif
+
 #define DDEBUG_STRING_SIZE 1024
 static __initdata char ddebug_setup_string[DDEBUG_STRING_SIZE];
 
diff --git a/lib/error-inject.c b/lib/error-inject.c
index c0d4600f4896..aa63751c916f 100644
--- a/lib/error-inject.c
+++ b/lib/error-inject.c
@@ -189,7 +189,7 @@ static int ei_seq_show(struct seq_file *m, void *v)
 {
 	struct ei_entry *ent = list_entry(v, struct ei_entry, list);
 
-	seq_printf(m, "%pf\t%s\n", (void *)ent->start_addr,
+	seq_printf(m, "%ps\t%s\n", (void *)ent->start_addr,
 		   error_type_string(ent->etype));
 	return 0;
 }
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index b396d328a764..f74fa832f3aa 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1293,7 +1293,9 @@ ssize_t iov_iter_get_pages(struct iov_iter *i,
 			len = maxpages * PAGE_SIZE;
 		addr &= ~(PAGE_SIZE - 1);
 		n = DIV_ROUND_UP(len, PAGE_SIZE);
-		res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE, pages);
+		res = get_user_pages_fast(addr, n,
+				iov_iter_rw(i) != WRITE ?  FOLL_WRITE : 0,
+				pages);
 		if (unlikely(res < 0))
 			return res;
 		return (res == n ? len : res * PAGE_SIZE) - *start;
@@ -1374,7 +1376,8 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
 		p = get_pages_array(n);
 		if (!p)
 			return -ENOMEM;
-		res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE, p);
+		res = get_user_pages_fast(addr, n,
+				iov_iter_rw(i) != WRITE ?  FOLL_WRITE : 0, p);
 		if (unlikely(res < 0)) {
 			kvfree(p);
 			return res;
diff --git a/lib/kobject.c b/lib/kobject.c
index aa89edcd2b63..f2ccdbac8ed9 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -18,7 +18,7 @@
 #include <linux/random.h>
 
 /**
- * kobject_namespace - return @kobj's namespace tag
+ * kobject_namespace() - Return @kobj's namespace tag.
  * @kobj: kobject in question
  *
  * Returns namespace tag of @kobj if its parent has namespace ops enabled
@@ -36,7 +36,7 @@ const void *kobject_namespace(struct kobject *kobj)
 }
 
 /**
- * kobject_get_ownership - get sysfs ownership data for @kobj
+ * kobject_get_ownership() - Get sysfs ownership data for @kobj.
  * @kobj: kobject in question
  * @uid: kernel user ID for sysfs objects
  * @gid: kernel group ID for sysfs objects
@@ -82,6 +82,7 @@ static int populate_dir(struct kobject *kobj)
 
 static int create_dir(struct kobject *kobj)
 {
+	const struct kobj_type *ktype = get_ktype(kobj);
 	const struct kobj_ns_type_operations *ops;
 	int error;
 
@@ -95,6 +96,14 @@ static int create_dir(struct kobject *kobj)
 		return error;
 	}
 
+	if (ktype) {
+		error = sysfs_create_groups(kobj, ktype->default_groups);
+		if (error) {
+			sysfs_remove_dir(kobj);
+			return error;
+		}
+	}
+
 	/*
 	 * @kobj->sd may be deleted by an ancestor going away.  Hold an
 	 * extra reference so that it stays until @kobj is gone.
@@ -153,12 +162,11 @@ static void fill_kobj_path(struct kobject *kobj, char *path, int length)
 }
 
 /**
- * kobject_get_path - generate and return the path associated with a given kobj and kset pair.
- *
+ * kobject_get_path() - Allocate memory and fill in the path for @kobj.
  * @kobj:	kobject in question, with which to build the path
  * @gfp_mask:	the allocation type used to allocate the path
  *
- * The result must be freed by the caller with kfree().
+ * Return: The newly allocated memory, caller must free with kfree().
  */
 char *kobject_get_path(struct kobject *kobj, gfp_t gfp_mask)
 {
@@ -265,7 +273,7 @@ static int kobject_add_internal(struct kobject *kobj)
 }
 
 /**
- * kobject_set_name_vargs - Set the name of an kobject
+ * kobject_set_name_vargs() - Set the name of a kobject.
  * @kobj: struct kobject to set the name of
  * @fmt: format string used to build the name
  * @vargs: vargs to format the string.
@@ -305,7 +313,7 @@ int kobject_set_name_vargs(struct kobject *kobj, const char *fmt,
 }
 
 /**
- * kobject_set_name - Set the name of a kobject
+ * kobject_set_name() - Set the name of a kobject.
  * @kobj: struct kobject to set the name of
  * @fmt: format string used to build the name
  *
@@ -327,7 +335,7 @@ int kobject_set_name(struct kobject *kobj, const char *fmt, ...)
 EXPORT_SYMBOL(kobject_set_name);
 
 /**
- * kobject_init - initialize a kobject structure
+ * kobject_init() - Initialize a kobject structure.
  * @kobj: pointer to the kobject to initialize
  * @ktype: pointer to the ktype for this kobject.
  *
@@ -383,7 +391,7 @@ static __printf(3, 0) int kobject_add_varg(struct kobject *kobj,
 }
 
 /**
- * kobject_add - the main kobject add function
+ * kobject_add() - The main kobject add function.
  * @kobj: the kobject to add
  * @parent: pointer to the parent of the kobject.
  * @fmt: format to name the kobject with.
@@ -397,15 +405,23 @@ static __printf(3, 0) int kobject_add_varg(struct kobject *kobj,
  * is assigned to the kobject, then the kobject will be located in the
  * root of the sysfs tree.
  *
- * If this function returns an error, kobject_put() must be called to
- * properly clean up the memory associated with the object.
- * Under no instance should the kobject that is passed to this function
- * be directly freed with a call to kfree(), that can leak memory.
- *
  * Note, no "add" uevent will be created with this call, the caller should set
  * up all of the necessary sysfs files for the object and then call
  * kobject_uevent() with the UEVENT_ADD parameter to ensure that
  * userspace is properly notified of this kobject's creation.
+ *
+ * Return: If this function returns an error, kobject_put() must be
+ *         called to properly clean up the memory associated with the
+ *         object.  Under no instance should the kobject that is passed
+ *         to this function be directly freed with a call to kfree(),
+ *         that can leak memory.
+ *
+ *         If this function returns success, kobject_put() must also be called
+ *         in order to properly clean up the memory associated with the object.
+ *
+ *         In short, once this function is called, kobject_put() MUST be called
+ *         when the use of the object is finished in order to properly free
+ *         everything.
  */
 int kobject_add(struct kobject *kobj, struct kobject *parent,
 		const char *fmt, ...)
@@ -431,15 +447,19 @@ int kobject_add(struct kobject *kobj, struct kobject *parent,
 EXPORT_SYMBOL(kobject_add);
 
 /**
- * kobject_init_and_add - initialize a kobject structure and add it to the kobject hierarchy
+ * kobject_init_and_add() - Initialize a kobject structure and add it to
+ *                          the kobject hierarchy.
  * @kobj: pointer to the kobject to initialize
  * @ktype: pointer to the ktype for this kobject.
  * @parent: pointer to the parent of this kobject.
  * @fmt: the name of the kobject.
  *
- * This function combines the call to kobject_init() and
- * kobject_add().  The same type of error handling after a call to
- * kobject_add() and kobject lifetime rules are the same here.
+ * This function combines the call to kobject_init() and kobject_add().
+ *
+ * If this function returns an error, kobject_put() must be called to
+ * properly clean up the memory associated with the object.  This is the
+ * same type of error handling after a call to kobject_add() and kobject
+ * lifetime rules are the same here.
  */
 int kobject_init_and_add(struct kobject *kobj, struct kobj_type *ktype,
 			 struct kobject *parent, const char *fmt, ...)
@@ -458,7 +478,7 @@ int kobject_init_and_add(struct kobject *kobj, struct kobj_type *ktype,
 EXPORT_SYMBOL_GPL(kobject_init_and_add);
 
 /**
- * kobject_rename - change the name of an object
+ * kobject_rename() - Change the name of an object.
  * @kobj: object in question.
  * @new_name: object's new name
  *
@@ -525,7 +545,7 @@ out:
 EXPORT_SYMBOL_GPL(kobject_rename);
 
 /**
- * kobject_move - move object to another parent
+ * kobject_move() - Move object to another parent.
  * @kobj: object in question.
  * @new_parent: object's new parent (can be NULL)
  */
@@ -578,17 +598,26 @@ out:
 EXPORT_SYMBOL_GPL(kobject_move);
 
 /**
- * kobject_del - unlink kobject from hierarchy.
+ * kobject_del() - Unlink kobject from hierarchy.
  * @kobj: object.
+ *
+ * This is the function that should be called to delete an object
+ * successfully added via kobject_add().
  */
 void kobject_del(struct kobject *kobj)
 {
 	struct kernfs_node *sd;
+	const struct kobj_type *ktype;
 
 	if (!kobj)
 		return;
 
 	sd = kobj->sd;
+	ktype = get_ktype(kobj);
+
+	if (ktype)
+		sysfs_remove_groups(kobj, ktype->default_groups);
+
 	sysfs_remove_dir(kobj);
 	sysfs_put(sd);
 
@@ -600,7 +629,7 @@ void kobject_del(struct kobject *kobj)
 EXPORT_SYMBOL(kobject_del);
 
 /**
- * kobject_get - increment refcount for object.
+ * kobject_get() - Increment refcount for object.
  * @kobj: object.
  */
 struct kobject *kobject_get(struct kobject *kobj)
@@ -693,7 +722,7 @@ static void kobject_release(struct kref *kref)
 }
 
 /**
- * kobject_put - decrement refcount for object.
+ * kobject_put() - Decrement refcount for object.
  * @kobj: object.
  *
  * Decrement the refcount, and if 0, call kobject_cleanup().
@@ -722,7 +751,7 @@ static struct kobj_type dynamic_kobj_ktype = {
 };
 
 /**
- * kobject_create - create a struct kobject dynamically
+ * kobject_create() - Create a struct kobject dynamically.
  *
  * This function creates a kobject structure dynamically and sets it up
  * to be a "dynamic" kobject with a default release function set up.
@@ -745,8 +774,8 @@ struct kobject *kobject_create(void)
 }
 
 /**
- * kobject_create_and_add - create a struct kobject dynamically and register it with sysfs
- *
+ * kobject_create_and_add() - Create a struct kobject dynamically and
+ *                            register it with sysfs.
  * @name: the name for the kobject
  * @parent: the parent kobject of this kobject, if any.
  *
@@ -777,7 +806,7 @@ struct kobject *kobject_create_and_add(const char *name, struct kobject *parent)
 EXPORT_SYMBOL_GPL(kobject_create_and_add);
 
 /**
- * kset_init - initialize a kset for use
+ * kset_init() - Initialize a kset for use.
  * @k: kset
  */
 void kset_init(struct kset *k)
@@ -819,7 +848,7 @@ const struct sysfs_ops kobj_sysfs_ops = {
 EXPORT_SYMBOL_GPL(kobj_sysfs_ops);
 
 /**
- * kset_register - initialize and add a kset.
+ * kset_register() - Initialize and add a kset.
  * @k: kset.
  */
 int kset_register(struct kset *k)
@@ -839,7 +868,7 @@ int kset_register(struct kset *k)
 EXPORT_SYMBOL(kset_register);
 
 /**
- * kset_unregister - remove a kset.
+ * kset_unregister() - Remove a kset.
  * @k: kset.
  */
 void kset_unregister(struct kset *k)
@@ -852,7 +881,7 @@ void kset_unregister(struct kset *k)
 EXPORT_SYMBOL(kset_unregister);
 
 /**
- * kset_find_obj - search for object in kset.
+ * kset_find_obj() - Search for object in kset.
  * @kset: kset we're looking in.
  * @name: object's name.
  *
@@ -900,7 +929,7 @@ static struct kobj_type kset_ktype = {
 };
 
 /**
- * kset_create - create a struct kset dynamically
+ * kset_create() - Create a struct kset dynamically.
  *
  * @name: the name for the kset
  * @uevent_ops: a struct kset_uevent_ops for the kset
@@ -944,7 +973,7 @@ static struct kset *kset_create(const char *name,
 }
 
 /**
- * kset_create_and_add - create a struct kset dynamically and add it to sysfs
+ * kset_create_and_add() - Create a struct kset dynamically and add it to sysfs.
  *
  * @name: the name for the kset
  * @uevent_ops: a struct kset_uevent_ops for the kset
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index f05802687ba4..7998affa45d4 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -466,6 +466,13 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 	int i = 0;
 	int retval = 0;
 
+	/*
+	 * Mark "remove" event done regardless of result, for some subsystems
+	 * do not want to re-trigger "remove" event via automatic cleanup.
+	 */
+	if (action == KOBJ_REMOVE)
+		kobj->state_remove_uevent_sent = 1;
+
 	pr_debug("kobject: '%s' (%p): %s\n",
 		 kobject_name(kobj), kobj, __func__);
 
@@ -567,10 +574,6 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 		kobj->state_add_uevent_sent = 1;
 		break;
 
-	case KOBJ_REMOVE:
-		kobj->state_remove_uevent_sent = 1;
-		break;
-
 	case KOBJ_UNBIND:
 		zap_modalias_env(env);
 		break;
diff --git a/lib/libcrc32c.c b/lib/libcrc32c.c
index f0a2934605bf..4e9829c4d64c 100644
--- a/lib/libcrc32c.c
+++ b/lib/libcrc32c.c
@@ -47,7 +47,6 @@ u32 crc32c(u32 crc, const void *address, unsigned int length)
 	int err;
 
 	shash->tfm = tfm;
-	shash->flags = 0;
 	*ctx = crc;
 
 	err = crypto_shash_update(shash, address, length);
diff --git a/lib/list_sort.c b/lib/list_sort.c
index 85759928215b..06e900c5587b 100644
--- a/lib/list_sort.c
+++ b/lib/list_sort.c
@@ -7,33 +7,41 @@
 #include <linux/list_sort.h>
 #include <linux/list.h>
 
-#define MAX_LIST_LENGTH_BITS 20
+typedef int __attribute__((nonnull(2,3))) (*cmp_func)(void *,
+		struct list_head const *, struct list_head const *);
 
 /*
  * Returns a list organized in an intermediate format suited
  * to chaining of merge() calls: null-terminated, no reserved or
  * sentinel head node, "prev" links not maintained.
  */
-static struct list_head *merge(void *priv,
-				int (*cmp)(void *priv, struct list_head *a,
-					struct list_head *b),
+__attribute__((nonnull(2,3,4)))
+static struct list_head *merge(void *priv, cmp_func cmp,
 				struct list_head *a, struct list_head *b)
 {
-	struct list_head head, *tail = &head;
+	struct list_head *head, **tail = &head;
 
-	while (a && b) {
+	for (;;) {
 		/* if equal, take 'a' -- important for sort stability */
-		if ((*cmp)(priv, a, b) <= 0) {
-			tail->next = a;
+		if (cmp(priv, a, b) <= 0) {
+			*tail = a;
+			tail = &a->next;
 			a = a->next;
+			if (!a) {
+				*tail = b;
+				break;
+			}
 		} else {
-			tail->next = b;
+			*tail = b;
+			tail = &b->next;
 			b = b->next;
+			if (!b) {
+				*tail = a;
+				break;
+			}
 		}
-		tail = tail->next;
 	}
-	tail->next = a?:b;
-	return head.next;
+	return head;
 }
 
 /*
@@ -43,44 +51,52 @@ static struct list_head *merge(void *priv,
  * prev-link restoration pass, or maintaining the prev links
  * throughout.
  */
-static void merge_and_restore_back_links(void *priv,
-				int (*cmp)(void *priv, struct list_head *a,
-					struct list_head *b),
-				struct list_head *head,
-				struct list_head *a, struct list_head *b)
+__attribute__((nonnull(2,3,4,5)))
+static void merge_final(void *priv, cmp_func cmp, struct list_head *head,
+			struct list_head *a, struct list_head *b)
 {
 	struct list_head *tail = head;
 	u8 count = 0;
 
-	while (a && b) {
+	for (;;) {
 		/* if equal, take 'a' -- important for sort stability */
-		if ((*cmp)(priv, a, b) <= 0) {
+		if (cmp(priv, a, b) <= 0) {
 			tail->next = a;
 			a->prev = tail;
+			tail = a;
 			a = a->next;
+			if (!a)
+				break;
 		} else {
 			tail->next = b;
 			b->prev = tail;
+			tail = b;
 			b = b->next;
+			if (!b) {
+				b = a;
+				break;
+			}
 		}
-		tail = tail->next;
 	}
-	tail->next = a ? : b;
 
+	/* Finish linking remainder of list b on to tail */
+	tail->next = b;
 	do {
 		/*
-		 * In worst cases this loop may run many iterations.
+		 * If the merge is highly unbalanced (e.g. the input is
+		 * already sorted), this loop may run many iterations.
 		 * Continue callbacks to the client even though no
 		 * element comparison is needed, so the client's cmp()
 		 * routine can invoke cond_resched() periodically.
 		 */
-		if (unlikely(!(++count)))
-			(*cmp)(priv, tail->next, tail->next);
-
-		tail->next->prev = tail;
-		tail = tail->next;
-	} while (tail->next);
-
+		if (unlikely(!++count))
+			cmp(priv, b, b);
+		b->prev = tail;
+		tail = b;
+		b = b->next;
+	} while (b);
+
+	/* And the final links to make a circular doubly-linked list */
 	tail->next = head;
 	head->prev = tail;
 }
@@ -91,55 +107,149 @@ static void merge_and_restore_back_links(void *priv,
  * @head: the list to sort
  * @cmp: the elements comparison function
  *
- * This function implements "merge sort", which has O(nlog(n))
- * complexity.
+ * The comparison funtion @cmp must return > 0 if @a should sort after
+ * @b ("@a > @b" if you want an ascending sort), and <= 0 if @a should
+ * sort before @b *or* their original order should be preserved.  It is
+ * always called with the element that came first in the input in @a,
+ * and list_sort is a stable sort, so it is not necessary to distinguish
+ * the @a < @b and @a == @b cases.
+ *
+ * This is compatible with two styles of @cmp function:
+ * - The traditional style which returns <0 / =0 / >0, or
+ * - Returning a boolean 0/1.
+ * The latter offers a chance to save a few cycles in the comparison
+ * (which is used by e.g. plug_ctx_cmp() in block/blk-mq.c).
+ *
+ * A good way to write a multi-word comparison is
+ *	if (a->high != b->high)
+ *		return a->high > b->high;
+ *	if (a->middle != b->middle)
+ *		return a->middle > b->middle;
+ *	return a->low > b->low;
+ *
+ *
+ * This mergesort is as eager as possible while always performing at least
+ * 2:1 balanced merges.  Given two pending sublists of size 2^k, they are
+ * merged to a size-2^(k+1) list as soon as we have 2^k following elements.
+ *
+ * Thus, it will avoid cache thrashing as long as 3*2^k elements can
+ * fit into the cache.  Not quite as good as a fully-eager bottom-up
+ * mergesort, but it does use 0.2*n fewer comparisons, so is faster in
+ * the common case that everything fits into L1.
+ *
+ *
+ * The merging is controlled by "count", the number of elements in the
+ * pending lists.  This is beautiully simple code, but rather subtle.
  *
- * The comparison function @cmp must return a negative value if @a
- * should sort before @b, and a positive value if @a should sort after
- * @b. If @a and @b are equivalent, and their original relative
- * ordering is to be preserved, @cmp must return 0.
+ * 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
+ * for each bit, when count increments to 2^k), we merge two lists of
+ * size 2^k into one list of size 2^(k+1).
+ *
+ * This merge happens exactly when the count reaches an odd multiple of
+ * 2^k, which is when we have 2^k elements pending in smaller lists,
+ * so it's safe to merge away two lists of size 2^k.
+ *
+ * After this happens twice, we have created two lists of size 2^(k+1),
+ * which will be merged into a list of size 2^(k+2) before we create
+ * a third list of size 2^(k+1), so there are never more than two pending.
+ *
+ * The number of pending lists of size 2^k is determined by the
+ * state of bit k of "count" plus two extra pieces of information:
+ * - The state of bit k-1 (when k == 0, consider bit -1 always set), and
+ * - Whether the higher-order bits are zero or non-zero (i.e.
+ *   is count >= 2^(k+1)).
+ * There are six states we distinguish.  "x" represents some arbitrary
+ * bits, and "y" represents some arbitrary non-zero bits:
+ * 0:  00x: 0 pending of size 2^k;           x pending of sizes < 2^k
+ * 1:  01x: 0 pending of size 2^k; 2^(k-1) + x pending of sizes < 2^k
+ * 2: x10x: 0 pending of size 2^k; 2^k     + x pending of sizes < 2^k
+ * 3: x11x: 1 pending of size 2^k; 2^(k-1) + x pending of sizes < 2^k
+ * 4: y00x: 1 pending of size 2^k; 2^k     + x pending of sizes < 2^k
+ * 5: y01x: 2 pending of size 2^k; 2^(k-1) + x pending of sizes < 2^k
+ * (merge and loop back to state 2)
+ *
+ * We gain lists of size 2^k in the 2->3 and 4->5 transitions (because
+ * bit k-1 is set while the more significant bits are non-zero) and
+ * merge them away in the 5->2 transition.  Note in particular that just
+ * before the 5->2 transition, all lower-order bits are 11 (state 3),
+ * so there is one list of each smaller size.
+ *
+ * When we reach the end of the input, we merge all the pending
+ * lists, from smallest to largest.  If you work through cases 2 to
+ * 5 above, you can see that the number of elements we merge with a list
+ * of size 2^k varies from 2^(k-1) (cases 3 and 5 when x == 0) to
+ * 2^(k+1) - 1 (second merge of case 5 when x == 2^(k-1) - 1).
  */
+__attribute__((nonnull(2,3)))
 void list_sort(void *priv, struct list_head *head,
 		int (*cmp)(void *priv, struct list_head *a,
 			struct list_head *b))
 {
-	struct list_head *part[MAX_LIST_LENGTH_BITS+1]; /* sorted partial lists
-						-- last slot is a sentinel */
-	int lev;  /* index into part[] */
-	int max_lev = 0;
-	struct list_head *list;
+	struct list_head *list = head->next, *pending = NULL;
+	size_t count = 0;	/* Count of pending */
 
-	if (list_empty(head))
+	if (list == head->prev)	/* Zero or one elements */
 		return;
 
-	memset(part, 0, sizeof(part));
-
+	/* Convert to a null-terminated singly-linked list. */
 	head->prev->next = NULL;
-	list = head->next;
-
-	while (list) {
-		struct list_head *cur = list;
-		list = list->next;
-		cur->next = NULL;
 
-		for (lev = 0; part[lev]; lev++) {
-			cur = merge(priv, cmp, part[lev], cur);
-			part[lev] = NULL;
-		}
-		if (lev > max_lev) {
-			if (unlikely(lev >= ARRAY_SIZE(part)-1)) {
-				printk_once(KERN_DEBUG "list too long for efficiency\n");
-				lev--;
-			}
-			max_lev = lev;
+	/*
+	 * Data structure invariants:
+	 * - All lists are singly linked and null-terminated; prev
+	 *   pointers are not maintained.
+	 * - pending is a prev-linked "list of lists" of sorted
+	 *   sublists awaiting further merging.
+	 * - Each of the sorted sublists is power-of-two in size.
+	 * - Sublists are sorted by size and age, smallest & newest at front.
+	 * - There are zero to two sublists of each size.
+	 * - A pair of pending sublists are merged as soon as the number
+	 *   of following pending elements equals their size (i.e.
+	 *   each time count reaches an odd multiple of that size).
+	 *   That ensures each later final merge will be at worst 2:1.
+	 * - Each round consists of:
+	 *   - Merging the two sublists selected by the highest bit
+	 *     which flips when count is incremented, and
+	 *   - Adding an element from the input as a size-1 sublist.
+	 */
+	do {
+		size_t bits;
+		struct list_head **tail = &pending;
+
+		/* Find the least-significant clear bit in count */
+		for (bits = count; bits & 1; bits >>= 1)
+			tail = &(*tail)->prev;
+		/* Do the indicated merge */
+		if (likely(bits)) {
+			struct list_head *a = *tail, *b = a->prev;
+
+			a = merge(priv, (cmp_func)cmp, b, a);
+			/* Install the merged result in place of the inputs */
+			a->prev = b->prev;
+			*tail = a;
 		}
-		part[lev] = cur;
-	}
 
-	for (lev = 0; lev < max_lev; lev++)
-		if (part[lev])
-			list = merge(priv, cmp, part[lev], list);
-
-	merge_and_restore_back_links(priv, cmp, head, part[max_lev], list);
+		/* Move one element from input list to pending */
+		list->prev = pending;
+		pending = list;
+		list = list->next;
+		pending->next = NULL;
+		count++;
+	} while (list);
+
+	/* End of input; merge together all the pending lists. */
+	list = pending;
+	pending = pending->prev;
+	for (;;) {
+		struct list_head *next = pending->prev;
+
+		if (!next)
+			break;
+		list = merge(priv, (cmp_func)cmp, pending, list);
+		pending = next;
+	}
+	/* The final merge, rebuilding prev links */
+	merge_final(priv, (cmp_func)cmp, head, pending, list);
 }
 EXPORT_SYMBOL(list_sort);
diff --git a/lib/math/Kconfig b/lib/math/Kconfig
new file mode 100644
index 000000000000..73bdf37178d1
--- /dev/null
+++ b/lib/math/Kconfig
@@ -0,0 +1,11 @@
+config CORDIC
+	tristate "CORDIC algorithm"
+	help
+	  This option provides an implementation of the CORDIC algorithm;
+	  calculations are in fixed point. Module will be called cordic.
+
+config PRIME_NUMBERS
+	tristate
+
+config RATIONAL
+	bool
diff --git a/lib/math/Makefile b/lib/math/Makefile
new file mode 100644
index 000000000000..583bbfebfc09
--- /dev/null
+++ b/lib/math/Makefile
@@ -0,0 +1,5 @@
+obj-y += div64.o gcd.o lcm.o int_pow.o int_sqrt.o reciprocal_div.o
+
+obj-$(CONFIG_CORDIC)		+= cordic.o
+obj-$(CONFIG_PRIME_NUMBERS)	+= prime_numbers.o
+obj-$(CONFIG_RATIONAL)		+= rational.o
diff --git a/lib/cordic.c b/lib/math/cordic.c
index 8ef27c12956f..8ef27c12956f 100644
--- a/lib/cordic.c
+++ b/lib/math/cordic.c
diff --git a/lib/div64.c b/lib/math/div64.c
index ee146bb4c558..368ca7fd0d82 100644
--- a/lib/div64.c
+++ b/lib/math/div64.c
@@ -10,7 +10,7 @@
  * Generic C version of 64bit/32bit division and modulo, with
  * 64bit result and 32bit remainder.
  *
- * The fast case for (n>>32 == 0) is handled inline by do_div(). 
+ * The fast case for (n>>32 == 0) is handled inline by do_div().
  *
  * Code generated for this function might be very inefficient
  * for some CPUs. __div64_32() can be overridden by linking arch-specific
diff --git a/lib/gcd.c b/lib/math/gcd.c
index 7948ab27f0a4..7948ab27f0a4 100644
--- a/lib/gcd.c
+++ b/lib/math/gcd.c
diff --git a/lib/math/int_pow.c b/lib/math/int_pow.c
new file mode 100644
index 000000000000..622fc1ab3c74
--- /dev/null
+++ b/lib/math/int_pow.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * An integer based power function
+ *
+ * Derived from drivers/video/backlight/pwm_bl.c
+ */
+
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+/**
+ * int_pow - computes the exponentiation of the given base and exponent
+ * @base: base which will be raised to the given power
+ * @exp: power to be raised to
+ *
+ * Computes: pow(base, exp), i.e. @base raised to the @exp power
+ */
+u64 int_pow(u64 base, unsigned int exp)
+{
+	u64 result = 1;
+
+	while (exp) {
+		if (exp & 1)
+			result *= base;
+		exp >>= 1;
+		base *= base;
+	}
+
+	return result;
+}
+EXPORT_SYMBOL_GPL(int_pow);
diff --git a/lib/int_sqrt.c b/lib/math/int_sqrt.c
index 30e0f9770f88..30e0f9770f88 100644
--- a/lib/int_sqrt.c
+++ b/lib/math/int_sqrt.c
diff --git a/lib/lcm.c b/lib/math/lcm.c
index 03d7fcb420b5..03d7fcb420b5 100644
--- a/lib/lcm.c
+++ b/lib/math/lcm.c
diff --git a/lib/prime_numbers.c b/lib/math/prime_numbers.c
index 550eec457c2e..550eec457c2e 100644
--- a/lib/prime_numbers.c
+++ b/lib/math/prime_numbers.c
diff --git a/lib/rational.c b/lib/math/rational.c
index ba7443677c90..ba7443677c90 100644
--- a/lib/rational.c
+++ b/lib/math/rational.c
diff --git a/lib/reciprocal_div.c b/lib/math/reciprocal_div.c
index bf043258fa00..bf043258fa00 100644
--- a/lib/reciprocal_div.c
+++ b/lib/math/reciprocal_div.c
diff --git a/lib/nlattr.c b/lib/nlattr.c
index d26de6156b97..cace9b307781 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -69,7 +69,8 @@ static int validate_nla_bitfield32(const struct nlattr *nla,
 
 static int nla_validate_array(const struct nlattr *head, int len, int maxtype,
 			      const struct nla_policy *policy,
-			      struct netlink_ext_ack *extack)
+			      struct netlink_ext_ack *extack,
+			      unsigned int validate)
 {
 	const struct nlattr *entry;
 	int rem;
@@ -86,8 +87,8 @@ static int nla_validate_array(const struct nlattr *head, int len, int maxtype,
 			return -ERANGE;
 		}
 
-		ret = nla_validate(nla_data(entry), nla_len(entry),
-				   maxtype, policy, extack);
+		ret = __nla_validate(nla_data(entry), nla_len(entry),
+				     maxtype, policy, validate, extack);
 		if (ret < 0)
 			return ret;
 	}
@@ -154,13 +155,17 @@ static int nla_validate_int_range(const struct nla_policy *pt,
 }
 
 static int validate_nla(const struct nlattr *nla, int maxtype,
-			const struct nla_policy *policy,
+			const struct nla_policy *policy, unsigned int validate,
 			struct netlink_ext_ack *extack)
 {
+	u16 strict_start_type = policy[0].strict_start_type;
 	const struct nla_policy *pt;
 	int minlen = 0, attrlen = nla_len(nla), type = nla_type(nla);
 	int err = -ERANGE;
 
+	if (strict_start_type && type >= strict_start_type)
+		validate |= NL_VALIDATE_STRICT;
+
 	if (type <= 0 || type > maxtype)
 		return 0;
 
@@ -172,6 +177,26 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 	    (pt->type == NLA_EXACT_LEN_WARN && attrlen != pt->len)) {
 		pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n",
 				    current->comm, type);
+		if (validate & NL_VALIDATE_STRICT_ATTRS) {
+			NL_SET_ERR_MSG_ATTR(extack, nla,
+					    "invalid attribute length");
+			return -EINVAL;
+		}
+	}
+
+	if (validate & NL_VALIDATE_NESTED) {
+		if ((pt->type == NLA_NESTED || pt->type == NLA_NESTED_ARRAY) &&
+		    !(nla->nla_type & NLA_F_NESTED)) {
+			NL_SET_ERR_MSG_ATTR(extack, nla,
+					    "NLA_F_NESTED is missing");
+			return -EINVAL;
+		}
+		if (pt->type != NLA_NESTED && pt->type != NLA_NESTED_ARRAY &&
+		    pt->type != NLA_UNSPEC && (nla->nla_type & NLA_F_NESTED)) {
+			NL_SET_ERR_MSG_ATTR(extack, nla,
+					    "NLA_F_NESTED not expected");
+			return -EINVAL;
+		}
 	}
 
 	switch (pt->type) {
@@ -244,8 +269,9 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 		if (attrlen < NLA_HDRLEN)
 			goto out_err;
 		if (pt->validation_data) {
-			err = nla_validate(nla_data(nla), nla_len(nla), pt->len,
-					   pt->validation_data, extack);
+			err = __nla_validate(nla_data(nla), nla_len(nla), pt->len,
+					     pt->validation_data, validate,
+					     extack);
 			if (err < 0) {
 				/*
 				 * return directly to preserve the inner
@@ -268,7 +294,7 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 
 			err = nla_validate_array(nla_data(nla), nla_len(nla),
 						 pt->len, pt->validation_data,
-						 extack);
+						 extack, validate);
 			if (err < 0) {
 				/*
 				 * return directly to preserve the inner
@@ -278,10 +304,23 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 			}
 		}
 		break;
+
+	case NLA_UNSPEC:
+		if (validate & NL_VALIDATE_UNSPEC) {
+			NL_SET_ERR_MSG_ATTR(extack, nla,
+					    "Unsupported attribute");
+			return -EINVAL;
+		}
+		/* fall through */
+	case NLA_MIN_LEN:
+		if (attrlen < pt->len)
+			goto out_err;
+		break;
+
 	default:
 		if (pt->len)
 			minlen = pt->len;
-		else if (pt->type != NLA_UNSPEC)
+		else
 			minlen = nla_attr_minlen[pt->type];
 
 		if (attrlen < minlen)
@@ -315,37 +354,76 @@ out_err:
 	return err;
 }
 
+static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype,
+				const struct nla_policy *policy,
+				unsigned int validate,
+				struct netlink_ext_ack *extack,
+				struct nlattr **tb)
+{
+	const struct nlattr *nla;
+	int rem;
+
+	if (tb)
+		memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
+
+	nla_for_each_attr(nla, head, len, rem) {
+		u16 type = nla_type(nla);
+
+		if (type == 0 || type > maxtype) {
+			if (validate & NL_VALIDATE_MAXTYPE) {
+				NL_SET_ERR_MSG_ATTR(extack, nla,
+						    "Unknown attribute type");
+				return -EINVAL;
+			}
+			continue;
+		}
+		if (policy) {
+			int err = validate_nla(nla, maxtype, policy,
+					       validate, extack);
+
+			if (err < 0)
+				return err;
+		}
+
+		if (tb)
+			tb[type] = (struct nlattr *)nla;
+	}
+
+	if (unlikely(rem > 0)) {
+		pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n",
+				    rem, current->comm);
+		NL_SET_ERR_MSG(extack, "bytes leftover after parsing attributes");
+		if (validate & NL_VALIDATE_TRAILING)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 /**
- * nla_validate - Validate a stream of attributes
+ * __nla_validate - Validate a stream of attributes
  * @head: head of attribute stream
  * @len: length of attribute stream
  * @maxtype: maximum attribute type to be expected
  * @policy: validation policy
+ * @validate: validation strictness
  * @extack: extended ACK report struct
  *
  * Validates all attributes in the specified attribute stream against the
- * specified policy. Attributes with a type exceeding maxtype will be
- * ignored. See documenation of struct nla_policy for more details.
+ * specified policy. Validation depends on the validate flags passed, see
+ * &enum netlink_validation for more details on that.
+ * See documenation of struct nla_policy for more details.
  *
  * Returns 0 on success or a negative error code.
  */
-int nla_validate(const struct nlattr *head, int len, int maxtype,
-		 const struct nla_policy *policy,
-		 struct netlink_ext_ack *extack)
+int __nla_validate(const struct nlattr *head, int len, int maxtype,
+		   const struct nla_policy *policy, unsigned int validate,
+		   struct netlink_ext_ack *extack)
 {
-	const struct nlattr *nla;
-	int rem;
-
-	nla_for_each_attr(nla, head, len, rem) {
-		int err = validate_nla(nla, maxtype, policy, extack);
-
-		if (err < 0)
-			return err;
-	}
-
-	return 0;
+	return __nla_validate_parse(head, len, maxtype, policy, validate,
+				    extack, NULL);
 }
-EXPORT_SYMBOL(nla_validate);
+EXPORT_SYMBOL(__nla_validate);
 
 /**
  * nla_policy_len - Determin the max. length of a policy
@@ -377,76 +455,30 @@ nla_policy_len(const struct nla_policy *p, int n)
 EXPORT_SYMBOL(nla_policy_len);
 
 /**
- * nla_parse - Parse a stream of attributes into a tb buffer
+ * __nla_parse - Parse a stream of attributes into a tb buffer
  * @tb: destination array with maxtype+1 elements
  * @maxtype: maximum attribute type to be expected
  * @head: head of attribute stream
  * @len: length of attribute stream
  * @policy: validation policy
+ * @validate: validation strictness
+ * @extack: extended ACK pointer
  *
  * Parses a stream of attributes and stores a pointer to each attribute in
- * the tb array accessible via the attribute type. Attributes with a type
- * exceeding maxtype will be silently ignored for backwards compatibility
- * reasons. policy may be set to NULL if no validation is required.
+ * the tb array accessible via the attribute type.
+ * Validation is controlled by the @validate parameter.
  *
  * Returns 0 on success or a negative error code.
  */
-static int __nla_parse(struct nlattr **tb, int maxtype,
-		       const struct nlattr *head, int len,
-		       bool strict, const struct nla_policy *policy,
-		       struct netlink_ext_ack *extack)
-{
-	const struct nlattr *nla;
-	int rem;
-
-	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
-
-	nla_for_each_attr(nla, head, len, rem) {
-		u16 type = nla_type(nla);
-
-		if (type == 0 || type > maxtype) {
-			if (strict) {
-				NL_SET_ERR_MSG(extack, "Unknown attribute type");
-				return -EINVAL;
-			}
-			continue;
-		}
-		if (policy) {
-			int err = validate_nla(nla, maxtype, policy, extack);
-
-			if (err < 0)
-				return err;
-		}
-
-		tb[type] = (struct nlattr *)nla;
-	}
-
-	if (unlikely(rem > 0)) {
-		pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n",
-				    rem, current->comm);
-		NL_SET_ERR_MSG(extack, "bytes leftover after parsing attributes");
-		if (strict)
-			return -EINVAL;
-	}
-
-	return 0;
-}
-
-int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
-	      int len, const struct nla_policy *policy,
-	      struct netlink_ext_ack *extack)
-{
-	return __nla_parse(tb, maxtype, head, len, false, policy, extack);
-}
-EXPORT_SYMBOL(nla_parse);
-
-int nla_parse_strict(struct nlattr **tb, int maxtype, const struct nlattr *head,
-		     int len, const struct nla_policy *policy,
-		     struct netlink_ext_ack *extack)
+int __nla_parse(struct nlattr **tb, int maxtype,
+		const struct nlattr *head, int len,
+		const struct nla_policy *policy, unsigned int validate,
+		struct netlink_ext_ack *extack)
 {
-	return __nla_parse(tb, maxtype, head, len, true, policy, extack);
+	return __nla_validate_parse(head, len, maxtype, policy, validate,
+				    extack, tb);
 }
-EXPORT_SYMBOL(nla_parse_strict);
+EXPORT_SYMBOL(__nla_parse);
 
 /**
  * nla_find - Find a specific attribute in a stream of attributes
diff --git a/lib/packing.c b/lib/packing.c
new file mode 100644
index 000000000000..50d1e9f2f5a7
--- /dev/null
+++ b/lib/packing.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018, NXP Semiconductors
+ * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+#include <linux/packing.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+
+static int get_le_offset(int offset)
+{
+	int closest_multiple_of_4;
+
+	closest_multiple_of_4 = (offset / 4) * 4;
+	offset -= closest_multiple_of_4;
+	return closest_multiple_of_4 + (3 - offset);
+}
+
+static int get_reverse_lsw32_offset(int offset, size_t len)
+{
+	int closest_multiple_of_4;
+	int word_index;
+
+	word_index = offset / 4;
+	closest_multiple_of_4 = word_index * 4;
+	offset -= closest_multiple_of_4;
+	word_index = (len / 4) - word_index - 1;
+	return word_index * 4 + offset;
+}
+
+static u64 bit_reverse(u64 val, unsigned int width)
+{
+	u64 new_val = 0;
+	unsigned int bit;
+	unsigned int i;
+
+	for (i = 0; i < width; i++) {
+		bit = (val & (1 << i)) != 0;
+		new_val |= (bit << (width - i - 1));
+	}
+	return new_val;
+}
+
+static void adjust_for_msb_right_quirk(u64 *to_write, int *box_start_bit,
+				       int *box_end_bit, u8 *box_mask)
+{
+	int box_bit_width = *box_start_bit - *box_end_bit + 1;
+	int new_box_start_bit, new_box_end_bit;
+
+	*to_write >>= *box_end_bit;
+	*to_write = bit_reverse(*to_write, box_bit_width);
+	*to_write <<= *box_end_bit;
+
+	new_box_end_bit   = box_bit_width - *box_start_bit - 1;
+	new_box_start_bit = box_bit_width - *box_end_bit - 1;
+	*box_mask = GENMASK_ULL(new_box_start_bit, new_box_end_bit);
+	*box_start_bit = new_box_start_bit;
+	*box_end_bit   = new_box_end_bit;
+}
+
+/**
+ * packing - Convert numbers (currently u64) between a packed and an unpacked
+ *	     format. Unpacked means laid out in memory in the CPU's native
+ *	     understanding of integers, while packed means anything else that
+ *	     requires translation.
+ *
+ * @pbuf: Pointer to a buffer holding the packed value.
+ * @uval: Pointer to an u64 holding the unpacked value.
+ * @startbit: The index (in logical notation, compensated for quirks) where
+ *	      the packed value starts within pbuf. Must be larger than, or
+ *	      equal to, endbit.
+ * @endbit: The index (in logical notation, compensated for quirks) where
+ *	    the packed value ends within pbuf. Must be smaller than, or equal
+ *	    to, startbit.
+ * @op: If PACK, then uval will be treated as const pointer and copied (packed)
+ *	into pbuf, between startbit and endbit.
+ *	If UNPACK, then pbuf will be treated as const pointer and the logical
+ *	value between startbit and endbit will be copied (unpacked) to uval.
+ * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and
+ *	    QUIRK_MSB_ON_THE_RIGHT.
+ *
+ * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming
+ *	   correct usage, return code may be discarded.
+ *	   If op is PACK, pbuf is modified.
+ *	   If op is UNPACK, uval is modified.
+ */
+int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen,
+	    enum packing_op op, u8 quirks)
+{
+	/* Number of bits for storing "uval"
+	 * also width of the field to access in the pbuf
+	 */
+	u64 value_width;
+	/* Logical byte indices corresponding to the
+	 * start and end of the field.
+	 */
+	int plogical_first_u8, plogical_last_u8, box;
+
+	/* startbit is expected to be larger than endbit */
+	if (startbit < endbit)
+		/* Invalid function call */
+		return -EINVAL;
+
+	value_width = startbit - endbit + 1;
+	if (value_width > 64)
+		return -ERANGE;
+
+	/* Check if "uval" fits in "value_width" bits.
+	 * If value_width is 64, the check will fail, but any
+	 * 64-bit uval will surely fit.
+	 */
+	if (op == PACK && value_width < 64 && (*uval >= (1ull << value_width)))
+		/* Cannot store "uval" inside "value_width" bits.
+		 * Truncating "uval" is most certainly not desirable,
+		 * so simply erroring out is appropriate.
+		 */
+		return -ERANGE;
+
+	/* Initialize parameter */
+	if (op == UNPACK)
+		*uval = 0;
+
+	/* Iterate through an idealistic view of the pbuf as an u64 with
+	 * no quirks, u8 by u8 (aligned at u8 boundaries), from high to low
+	 * logical bit significance. "box" denotes the current logical u8.
+	 */
+	plogical_first_u8 = startbit / 8;
+	plogical_last_u8  = endbit / 8;
+
+	for (box = plogical_first_u8; box >= plogical_last_u8; box--) {
+		/* Bit indices into the currently accessed 8-bit box */
+		int box_start_bit, box_end_bit, box_addr;
+		u8  box_mask;
+		/* Corresponding bits from the unpacked u64 parameter */
+		int proj_start_bit, proj_end_bit;
+		u64 proj_mask;
+
+		/* This u8 may need to be accessed in its entirety
+		 * (from bit 7 to bit 0), or not, depending on the
+		 * input arguments startbit and endbit.
+		 */
+		if (box == plogical_first_u8)
+			box_start_bit = startbit % 8;
+		else
+			box_start_bit = 7;
+		if (box == plogical_last_u8)
+			box_end_bit = endbit % 8;
+		else
+			box_end_bit = 0;
+
+		/* We have determined the box bit start and end.
+		 * Now we calculate where this (masked) u8 box would fit
+		 * in the unpacked (CPU-readable) u64 - the u8 box's
+		 * projection onto the unpacked u64. Though the
+		 * box is u8, the projection is u64 because it may fall
+		 * anywhere within the unpacked u64.
+		 */
+		proj_start_bit = ((box * 8) + box_start_bit) - endbit;
+		proj_end_bit   = ((box * 8) + box_end_bit) - endbit;
+		proj_mask = GENMASK_ULL(proj_start_bit, proj_end_bit);
+		box_mask  = GENMASK_ULL(box_start_bit, box_end_bit);
+
+		/* Determine the offset of the u8 box inside the pbuf,
+		 * adjusted for quirks. The adjusted box_addr will be used for
+		 * effective addressing inside the pbuf (so it's not
+		 * logical any longer).
+		 */
+		box_addr = pbuflen - box - 1;
+		if (quirks & QUIRK_LITTLE_ENDIAN)
+			box_addr = get_le_offset(box_addr);
+		if (quirks & QUIRK_LSW32_IS_FIRST)
+			box_addr = get_reverse_lsw32_offset(box_addr,
+							    pbuflen);
+
+		if (op == UNPACK) {
+			u64 pval;
+
+			/* Read from pbuf, write to uval */
+			pval = ((u8 *)pbuf)[box_addr] & box_mask;
+			if (quirks & QUIRK_MSB_ON_THE_RIGHT)
+				adjust_for_msb_right_quirk(&pval,
+							   &box_start_bit,
+							   &box_end_bit,
+							   &box_mask);
+
+			pval >>= box_end_bit;
+			pval <<= proj_end_bit;
+			*uval &= ~proj_mask;
+			*uval |= pval;
+		} else {
+			u64 pval;
+
+			/* Write to pbuf, read from uval */
+			pval = (*uval) & proj_mask;
+			pval >>= proj_end_bit;
+			if (quirks & QUIRK_MSB_ON_THE_RIGHT)
+				adjust_for_msb_right_quirk(&pval,
+							   &box_start_bit,
+							   &box_end_bit,
+							   &box_mask);
+
+			pval <<= box_end_bit;
+			((u8 *)pbuf)[box_addr] &= ~box_mask;
+			((u8 *)pbuf)[box_addr] |= pval;
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL(packing);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Generic bitfield packing and unpacking");
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 9877682e49c7..da54318d3b55 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -151,7 +151,7 @@ static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu)
 	atomic_long_add((long)count - PERCPU_COUNT_BIAS, &ref->count);
 
 	WARN_ONCE(atomic_long_read(&ref->count) <= 0,
-		  "percpu ref (%pf) <= 0 (%ld) after switching to atomic",
+		  "percpu ref (%ps) <= 0 (%ld) after switching to atomic",
 		  ref->release, atomic_long_read(&ref->count));
 
 	/* @ref is viewed as dead on all CPUs, send out switch confirmation */
@@ -333,7 +333,7 @@ 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,
-		  "%s called more than once on %pf!", __func__, ref->release);
+		  "%s called more than once on %ps!", __func__, ref->release);
 
 	ref->percpu_count_ptr |= __PERCPU_REF_DEAD;
 	__percpu_ref_switch_mode(ref, confirm_kill);
diff --git a/lib/plist.c b/lib/plist.c
index 199408f91057..d3bd8827186f 100644
--- a/lib/plist.c
+++ b/lib/plist.c
@@ -26,7 +26,7 @@
 #include <linux/bug.h>
 #include <linux/plist.h>
 
-#ifdef CONFIG_DEBUG_PI_LIST
+#ifdef CONFIG_DEBUG_PLIST
 
 static struct plist_head test_head;
 
@@ -173,7 +173,7 @@ void plist_requeue(struct plist_node *node, struct plist_head *head)
 	plist_check_head(head);
 }
 
-#ifdef CONFIG_DEBUG_PI_LIST
+#ifdef CONFIG_DEBUG_PLIST
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 #include <linux/module.h>
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 97f59abc3e92..6529fe1b45c1 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -31,11 +31,10 @@
 
 #define HASH_DEFAULT_SIZE	64UL
 #define HASH_MIN_SIZE		4U
-#define BUCKET_LOCKS_PER_CPU	32UL
 
 union nested_table {
 	union nested_table __rcu *table;
-	struct rhash_head __rcu *bucket;
+	struct rhash_lock_head __rcu *bucket;
 };
 
 static u32 head_hashfn(struct rhashtable *ht,
@@ -56,9 +55,11 @@ EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held);
 
 int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash)
 {
-	spinlock_t *lock = rht_bucket_lock(tbl, hash);
-
-	return (debug_locks) ? lockdep_is_held(lock) : 1;
+	if (!debug_locks)
+		return 1;
+	if (unlikely(tbl->nest))
+		return 1;
+	return bit_spin_is_locked(0, (unsigned long *)&tbl->buckets[hash]);
 }
 EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held);
 #else
@@ -104,7 +105,6 @@ static void bucket_table_free(const struct bucket_table *tbl)
 	if (tbl->nest)
 		nested_bucket_table_free(tbl);
 
-	free_bucket_spinlocks(tbl->locks);
 	kvfree(tbl);
 }
 
@@ -131,9 +131,11 @@ static union nested_table *nested_table_alloc(struct rhashtable *ht,
 			INIT_RHT_NULLS_HEAD(ntbl[i].bucket);
 	}
 
-	rcu_assign_pointer(*prev, ntbl);
-
-	return ntbl;
+	if (cmpxchg(prev, NULL, ntbl) == NULL)
+		return ntbl;
+	/* Raced with another thread. */
+	kfree(ntbl);
+	return rcu_dereference(*prev);
 }
 
 static struct bucket_table *nested_bucket_table_alloc(struct rhashtable *ht,
@@ -169,11 +171,11 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
 					       gfp_t gfp)
 {
 	struct bucket_table *tbl = NULL;
-	size_t size, max_locks;
+	size_t size;
 	int i;
+	static struct lock_class_key __key;
 
-	size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]);
-	tbl = kvzalloc(size, gfp);
+	tbl = kvzalloc(struct_size(tbl, buckets, nbuckets), gfp);
 
 	size = nbuckets;
 
@@ -185,18 +187,11 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
 	if (tbl == NULL)
 		return NULL;
 
-	tbl->size = size;
-
-	max_locks = size >> 1;
-	if (tbl->nest)
-		max_locks = min_t(size_t, max_locks, 1U << tbl->nest);
+	lockdep_init_map(&tbl->dep_map, "rhashtable_bucket", &__key, 0);
 
-	if (alloc_bucket_spinlocks(&tbl->locks, &tbl->locks_mask, max_locks,
-				   ht->p.locks_mul, gfp) < 0) {
-		bucket_table_free(tbl);
-		return NULL;
-	}
+	tbl->size = size;
 
+	rcu_head_init(&tbl->rcu);
 	INIT_LIST_HEAD(&tbl->walkers);
 
 	tbl->hash_rnd = get_random_u32();
@@ -220,14 +215,15 @@ static struct bucket_table *rhashtable_last_table(struct rhashtable *ht,
 	return new_tbl;
 }
 
-static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
+static int rhashtable_rehash_one(struct rhashtable *ht,
+				 struct rhash_lock_head __rcu **bkt,
+				 unsigned int old_hash)
 {
 	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
 	struct bucket_table *new_tbl = rhashtable_last_table(ht, old_tbl);
-	struct rhash_head __rcu **pprev = rht_bucket_var(old_tbl, old_hash);
 	int err = -EAGAIN;
 	struct rhash_head *head, *next, *entry;
-	spinlock_t *new_bucket_lock;
+	struct rhash_head __rcu **pprev = NULL;
 	unsigned int new_hash;
 
 	if (new_tbl->nest)
@@ -235,7 +231,8 @@ static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
 
 	err = -ENOENT;
 
-	rht_for_each(entry, old_tbl, old_hash) {
+	rht_for_each_from(entry, rht_ptr(bkt, old_tbl, old_hash),
+			  old_tbl, old_hash) {
 		err = 0;
 		next = rht_dereference_bucket(entry->next, old_tbl, old_hash);
 
@@ -250,18 +247,19 @@ static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
 
 	new_hash = head_hashfn(ht, new_tbl, entry);
 
-	new_bucket_lock = rht_bucket_lock(new_tbl, new_hash);
+	rht_lock_nested(new_tbl, &new_tbl->buckets[new_hash], SINGLE_DEPTH_NESTING);
 
-	spin_lock_nested(new_bucket_lock, SINGLE_DEPTH_NESTING);
-	head = rht_dereference_bucket(new_tbl->buckets[new_hash],
-				      new_tbl, new_hash);
+	head = rht_ptr(new_tbl->buckets + new_hash, new_tbl, new_hash);
 
 	RCU_INIT_POINTER(entry->next, head);
 
-	rcu_assign_pointer(new_tbl->buckets[new_hash], entry);
-	spin_unlock(new_bucket_lock);
+	rht_assign_unlock(new_tbl, &new_tbl->buckets[new_hash], entry);
 
-	rcu_assign_pointer(*pprev, next);
+	if (pprev)
+		rcu_assign_pointer(*pprev, next);
+	else
+		/* Need to preserved the bit lock. */
+		rht_assign_locked(bkt, next);
 
 out:
 	return err;
@@ -271,20 +269,19 @@ static int rhashtable_rehash_chain(struct rhashtable *ht,
 				    unsigned int old_hash)
 {
 	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
-	spinlock_t *old_bucket_lock;
+	struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash);
 	int err;
 
-	old_bucket_lock = rht_bucket_lock(old_tbl, old_hash);
+	if (!bkt)
+		return 0;
+	rht_lock(old_tbl, bkt);
 
-	spin_lock_bh(old_bucket_lock);
-	while (!(err = rhashtable_rehash_one(ht, old_hash)))
+	while (!(err = rhashtable_rehash_one(ht, bkt, old_hash)))
 		;
 
-	if (err == -ENOENT) {
-		old_tbl->rehash++;
+	if (err == -ENOENT)
 		err = 0;
-	}
-	spin_unlock_bh(old_bucket_lock);
+	rht_unlock(old_tbl, bkt);
 
 	return err;
 }
@@ -330,13 +327,16 @@ static int rhashtable_rehash_table(struct rhashtable *ht)
 	spin_lock(&ht->lock);
 	list_for_each_entry(walker, &old_tbl->walkers, list)
 		walker->tbl = NULL;
-	spin_unlock(&ht->lock);
 
 	/* Wait for readers. All new readers will see the new
 	 * table, and thus no references to the old table will
 	 * remain.
+	 * We do this inside the locked region so that
+	 * rhashtable_walk_stop() can use rcu_head_after_call_rcu()
+	 * to check if it should not re-link the table.
 	 */
 	call_rcu(&old_tbl->rcu, bucket_table_free_rcu);
+	spin_unlock(&ht->lock);
 
 	return rht_dereference(new_tbl->future_tbl, ht) ? -EAGAIN : 0;
 }
@@ -478,6 +478,7 @@ fail:
 }
 
 static void *rhashtable_lookup_one(struct rhashtable *ht,
+				   struct rhash_lock_head __rcu **bkt,
 				   struct bucket_table *tbl, unsigned int hash,
 				   const void *key, struct rhash_head *obj)
 {
@@ -485,13 +486,12 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 		.ht = ht,
 		.key = key,
 	};
-	struct rhash_head __rcu **pprev;
+	struct rhash_head __rcu **pprev = NULL;
 	struct rhash_head *head;
 	int elasticity;
 
 	elasticity = RHT_ELASTICITY;
-	pprev = rht_bucket_var(tbl, hash);
-	rht_for_each_continue(head, *pprev, tbl, hash) {
+	rht_for_each_from(head, rht_ptr(bkt, tbl, hash), tbl, hash) {
 		struct rhlist_head *list;
 		struct rhlist_head *plist;
 
@@ -513,7 +513,11 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 		RCU_INIT_POINTER(list->next, plist);
 		head = rht_dereference_bucket(head->next, tbl, hash);
 		RCU_INIT_POINTER(list->rhead.next, head);
-		rcu_assign_pointer(*pprev, obj);
+		if (pprev)
+			rcu_assign_pointer(*pprev, obj);
+		else
+			/* Need to preserve the bit lock */
+			rht_assign_locked(bkt, obj);
 
 		return NULL;
 	}
@@ -525,12 +529,12 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 }
 
 static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
+						  struct rhash_lock_head __rcu **bkt,
 						  struct bucket_table *tbl,
 						  unsigned int hash,
 						  struct rhash_head *obj,
 						  void *data)
 {
-	struct rhash_head __rcu **pprev;
 	struct bucket_table *new_tbl;
 	struct rhash_head *head;
 
@@ -553,11 +557,7 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
 	if (unlikely(rht_grow_above_100(ht, tbl)))
 		return ERR_PTR(-EAGAIN);
 
-	pprev = rht_bucket_insert(ht, tbl, hash);
-	if (!pprev)
-		return ERR_PTR(-ENOMEM);
-
-	head = rht_dereference_bucket(*pprev, tbl, hash);
+	head = rht_ptr(bkt, tbl, hash);
 
 	RCU_INIT_POINTER(obj->next, head);
 	if (ht->rhlist) {
@@ -567,7 +567,10 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
 		RCU_INIT_POINTER(list->next, NULL);
 	}
 
-	rcu_assign_pointer(*pprev, obj);
+	/* bkt is always the head of the list, so it holds
+	 * the lock, which we need to preserve
+	 */
+	rht_assign_locked(bkt, obj);
 
 	atomic_inc(&ht->nelems);
 	if (rht_grow_above_75(ht, tbl))
@@ -581,47 +584,35 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
 {
 	struct bucket_table *new_tbl;
 	struct bucket_table *tbl;
+	struct rhash_lock_head __rcu **bkt;
 	unsigned int hash;
-	spinlock_t *lock;
 	void *data;
 
-	tbl = rcu_dereference(ht->tbl);
-
-	/* All insertions must grab the oldest table containing
-	 * the hashed bucket that is yet to be rehashed.
-	 */
-	for (;;) {
-		hash = rht_head_hashfn(ht, tbl, obj, ht->p);
-		lock = rht_bucket_lock(tbl, hash);
-		spin_lock_bh(lock);
-
-		if (tbl->rehash <= hash)
-			break;
-
-		spin_unlock_bh(lock);
-		tbl = rht_dereference_rcu(tbl->future_tbl, ht);
-	}
-
-	data = rhashtable_lookup_one(ht, tbl, hash, key, obj);
-	new_tbl = rhashtable_insert_one(ht, tbl, hash, obj, data);
-	if (PTR_ERR(new_tbl) != -EEXIST)
-		data = ERR_CAST(new_tbl);
+	new_tbl = rcu_dereference(ht->tbl);
 
-	while (!IS_ERR_OR_NULL(new_tbl)) {
+	do {
 		tbl = new_tbl;
 		hash = rht_head_hashfn(ht, tbl, obj, ht->p);
-		spin_lock_nested(rht_bucket_lock(tbl, hash),
-				 SINGLE_DEPTH_NESTING);
-
-		data = rhashtable_lookup_one(ht, tbl, hash, key, obj);
-		new_tbl = rhashtable_insert_one(ht, tbl, hash, obj, data);
-		if (PTR_ERR(new_tbl) != -EEXIST)
-			data = ERR_CAST(new_tbl);
-
-		spin_unlock(rht_bucket_lock(tbl, hash));
-	}
-
-	spin_unlock_bh(lock);
+		if (rcu_access_pointer(tbl->future_tbl))
+			/* Failure is OK */
+			bkt = rht_bucket_var(tbl, hash);
+		else
+			bkt = rht_bucket_insert(ht, tbl, hash);
+		if (bkt == NULL) {
+			new_tbl = rht_dereference_rcu(tbl->future_tbl, ht);
+			data = ERR_PTR(-EAGAIN);
+		} else {
+			rht_lock(tbl, bkt);
+			data = rhashtable_lookup_one(ht, bkt, tbl,
+						     hash, key, obj);
+			new_tbl = rhashtable_insert_one(ht, bkt, tbl,
+							hash, obj, data);
+			if (PTR_ERR(new_tbl) != -EEXIST)
+				data = ERR_CAST(new_tbl);
+
+			rht_unlock(tbl, bkt);
+		}
+	} while (!IS_ERR_OR_NULL(new_tbl));
 
 	if (PTR_ERR(data) == -EAGAIN)
 		data = ERR_PTR(rhashtable_insert_rehash(ht, tbl) ?:
@@ -943,10 +934,11 @@ void rhashtable_walk_stop(struct rhashtable_iter *iter)
 	ht = iter->ht;
 
 	spin_lock(&ht->lock);
-	if (tbl->rehash < tbl->size)
-		list_add(&iter->walker.list, &tbl->walkers);
-	else
+	if (rcu_head_after_call_rcu(&tbl->rcu, bucket_table_free_rcu))
+		/* This bucket table is being freed, don't re-link it. */
 		iter->walker.tbl = NULL;
+	else
+		list_add(&iter->walker.list, &tbl->walkers);
 	spin_unlock(&ht->lock);
 
 out:
@@ -1046,11 +1038,6 @@ int rhashtable_init(struct rhashtable *ht,
 
 	size = rounded_hashtable_size(&ht->p);
 
-	if (params->locks_mul)
-		ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);
-	else
-		ht->p.locks_mul = BUCKET_LOCKS_PER_CPU;
-
 	ht->key_len = ht->p.key_len;
 	if (!params->hashfn) {
 		ht->p.hashfn = jhash;
@@ -1152,7 +1139,7 @@ restart:
 			struct rhash_head *pos, *next;
 
 			cond_resched();
-			for (pos = rht_dereference(*rht_bucket(tbl, i), ht),
+			for (pos = rht_ptr_exclusive(rht_bucket(tbl, i)),
 			     next = !rht_is_a_nulls(pos) ?
 					rht_dereference(pos->next, ht) : NULL;
 			     !rht_is_a_nulls(pos);
@@ -1179,11 +1166,10 @@ void rhashtable_destroy(struct rhashtable *ht)
 }
 EXPORT_SYMBOL_GPL(rhashtable_destroy);
 
-struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
-					    unsigned int hash)
+struct rhash_lock_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl,
+						   unsigned int hash)
 {
 	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
-	static struct rhash_head __rcu *rhnull;
 	unsigned int index = hash & ((1 << tbl->nest) - 1);
 	unsigned int size = tbl->size >> tbl->nest;
 	unsigned int subhash = hash;
@@ -1201,20 +1187,28 @@ struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
 		subhash >>= shift;
 	}
 
-	if (!ntbl) {
-		if (!rhnull)
-			INIT_RHT_NULLS_HEAD(rhnull);
-		return &rhnull;
-	}
+	if (!ntbl)
+		return NULL;
 
 	return &ntbl[subhash].bucket;
 
 }
+EXPORT_SYMBOL_GPL(__rht_bucket_nested);
+
+struct rhash_lock_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
+						 unsigned int hash)
+{
+	static struct rhash_lock_head __rcu *rhnull;
+
+	if (!rhnull)
+		INIT_RHT_NULLS_HEAD(rhnull);
+	return __rht_bucket_nested(tbl, hash) ?: &rhnull;
+}
 EXPORT_SYMBOL_GPL(rht_bucket_nested);
 
-struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
-						   struct bucket_table *tbl,
-						   unsigned int hash)
+struct rhash_lock_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
+							struct bucket_table *tbl,
+							unsigned int hash)
 {
 	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
 	unsigned int index = hash & ((1 << tbl->nest) - 1);
diff --git a/lib/siphash.c b/lib/siphash.c
index 3ae58b4edad6..c47bb6ff2149 100644
--- a/lib/siphash.c
+++ b/lib/siphash.c
@@ -68,11 +68,11 @@ u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key)
 						  bytemask_from_count(left)));
 #else
 	switch (left) {
-	case 7: b |= ((u64)end[6]) << 48;
-	case 6: b |= ((u64)end[5]) << 40;
-	case 5: b |= ((u64)end[4]) << 32;
+	case 7: b |= ((u64)end[6]) << 48; /* fall through */
+	case 6: b |= ((u64)end[5]) << 40; /* fall through */
+	case 5: b |= ((u64)end[4]) << 32; /* fall through */
 	case 4: b |= le32_to_cpup(data); break;
-	case 3: b |= ((u64)end[2]) << 16;
+	case 3: b |= ((u64)end[2]) << 16; /* fall through */
 	case 2: b |= le16_to_cpup(data); break;
 	case 1: b |= end[0];
 	}
@@ -101,11 +101,11 @@ u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key)
 						  bytemask_from_count(left)));
 #else
 	switch (left) {
-	case 7: b |= ((u64)end[6]) << 48;
-	case 6: b |= ((u64)end[5]) << 40;
-	case 5: b |= ((u64)end[4]) << 32;
+	case 7: b |= ((u64)end[6]) << 48; /* fall through */
+	case 6: b |= ((u64)end[5]) << 40; /* fall through */
+	case 5: b |= ((u64)end[4]) << 32; /* fall through */
 	case 4: b |= get_unaligned_le32(end); break;
-	case 3: b |= ((u64)end[2]) << 16;
+	case 3: b |= ((u64)end[2]) << 16; /* fall through */
 	case 2: b |= get_unaligned_le16(end); break;
 	case 1: b |= end[0];
 	}
@@ -268,11 +268,11 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
 						  bytemask_from_count(left)));
 #else
 	switch (left) {
-	case 7: b |= ((u64)end[6]) << 48;
-	case 6: b |= ((u64)end[5]) << 40;
-	case 5: b |= ((u64)end[4]) << 32;
+	case 7: b |= ((u64)end[6]) << 48; /* fall through */
+	case 6: b |= ((u64)end[5]) << 40; /* fall through */
+	case 5: b |= ((u64)end[4]) << 32; /* fall through */
 	case 4: b |= le32_to_cpup(data); break;
-	case 3: b |= ((u64)end[2]) << 16;
+	case 3: b |= ((u64)end[2]) << 16; /* fall through */
 	case 2: b |= le16_to_cpup(data); break;
 	case 1: b |= end[0];
 	}
@@ -301,11 +301,11 @@ u32 __hsiphash_unaligned(const void *data, size_t len,
 						  bytemask_from_count(left)));
 #else
 	switch (left) {
-	case 7: b |= ((u64)end[6]) << 48;
-	case 6: b |= ((u64)end[5]) << 40;
-	case 5: b |= ((u64)end[4]) << 32;
+	case 7: b |= ((u64)end[6]) << 48; /* fall through */
+	case 6: b |= ((u64)end[5]) << 40; /* fall through */
+	case 5: b |= ((u64)end[4]) << 32; /* fall through */
 	case 4: b |= get_unaligned_le32(end); break;
-	case 3: b |= ((u64)end[2]) << 16;
+	case 3: b |= ((u64)end[2]) << 16; /* fall through */
 	case 2: b |= get_unaligned_le16(end); break;
 	case 1: b |= end[0];
 	}
@@ -431,7 +431,7 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
 		v0 ^= m;
 	}
 	switch (left) {
-	case 3: b |= ((u32)end[2]) << 16;
+	case 3: b |= ((u32)end[2]) << 16; /* fall through */
 	case 2: b |= le16_to_cpup(data); break;
 	case 1: b |= end[0];
 	}
@@ -454,7 +454,7 @@ u32 __hsiphash_unaligned(const void *data, size_t len,
 		v0 ^= m;
 	}
 	switch (left) {
-	case 3: b |= ((u32)end[2]) << 16;
+	case 3: b |= ((u32)end[2]) << 16; /* fall through */
 	case 2: b |= get_unaligned_le16(end); break;
 	case 1: b |= end[0];
 	}
diff --git a/lib/sort.c b/lib/sort.c
index d6b7a202b0b6..50855ea8c262 100644
--- a/lib/sort.c
+++ b/lib/sort.c
@@ -1,8 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * A fast, small, non-recursive O(nlog n) sort for the Linux kernel
+ * A fast, small, non-recursive O(n log n) sort for the Linux kernel
  *
- * Jan 23 2005  Matt Mackall <mpm@selenic.com>
+ * This performs n*log2(n) + 0.37*n + o(n) comparisons on average,
+ * and 1.5*n*log2(n) + O(n) in the (very contrived) worst case.
+ *
+ * Glibc qsort() manages n*log2(n) - 1.26*n for random inputs (1.63*n
+ * better) at the expense of stack usage and much larger code to avoid
+ * quicksort's O(n^2) worst case.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -11,35 +16,155 @@
 #include <linux/export.h>
 #include <linux/sort.h>
 
-static int alignment_ok(const void *base, int align)
+/**
+ * is_aligned - is this pointer & size okay for word-wide copying?
+ * @base: pointer to data
+ * @size: size of each element
+ * @align: required alignment (typically 4 or 8)
+ *
+ * Returns true if elements can be copied using word loads and stores.
+ * The size must be a multiple of the alignment, and the base address must
+ * be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS.
+ *
+ * For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)"
+ * to "if ((a | b) & mask)", so we do that by hand.
+ */
+__attribute_const__ __always_inline
+static bool is_aligned(const void *base, size_t size, unsigned char align)
 {
-	return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
-		((unsigned long)base & (align - 1)) == 0;
+	unsigned char lsbits = (unsigned char)size;
+
+	(void)base;
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	lsbits |= (unsigned char)(uintptr_t)base;
+#endif
+	return (lsbits & (align - 1)) == 0;
 }
 
-static void u32_swap(void *a, void *b, int size)
+/**
+ * swap_words_32 - swap two elements in 32-bit chunks
+ * @a, @b: pointers to the elements
+ * @size: element size (must be a multiple of 4)
+ *
+ * Exchange the two objects in memory.  This exploits base+index addressing,
+ * which basically all CPUs have, to minimize loop overhead computations.
+ *
+ * For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the
+ * bottom of the loop, even though the zero flag is stil valid from the
+ * subtract (since the intervening mov instructions don't alter the flags).
+ * Gcc 8.1.0 doesn't have that problem.
+ */
+static void swap_words_32(void *a, void *b, size_t n)
 {
-	u32 t = *(u32 *)a;
-	*(u32 *)a = *(u32 *)b;
-	*(u32 *)b = t;
+	do {
+		u32 t = *(u32 *)(a + (n -= 4));
+		*(u32 *)(a + n) = *(u32 *)(b + n);
+		*(u32 *)(b + n) = t;
+	} while (n);
 }
 
-static void u64_swap(void *a, void *b, int size)
+/**
+ * swap_words_64 - swap two elements in 64-bit chunks
+ * @a, @b: pointers to the elements
+ * @size: element size (must be a multiple of 8)
+ *
+ * Exchange the two objects in memory.  This exploits base+index
+ * addressing, which basically all CPUs have, to minimize loop overhead
+ * computations.
+ *
+ * We'd like to use 64-bit loads if possible.  If they're not, emulating
+ * one requires base+index+4 addressing which x86 has but most other
+ * processors do not.  If CONFIG_64BIT, we definitely have 64-bit loads,
+ * but it's possible to have 64-bit loads without 64-bit pointers (e.g.
+ * x32 ABI).  Are there any cases the kernel needs to worry about?
+ */
+static void swap_words_64(void *a, void *b, size_t n)
 {
-	u64 t = *(u64 *)a;
-	*(u64 *)a = *(u64 *)b;
-	*(u64 *)b = t;
+	do {
+#ifdef CONFIG_64BIT
+		u64 t = *(u64 *)(a + (n -= 8));
+		*(u64 *)(a + n) = *(u64 *)(b + n);
+		*(u64 *)(b + n) = t;
+#else
+		/* Use two 32-bit transfers to avoid base+index+4 addressing */
+		u32 t = *(u32 *)(a + (n -= 4));
+		*(u32 *)(a + n) = *(u32 *)(b + n);
+		*(u32 *)(b + n) = t;
+
+		t = *(u32 *)(a + (n -= 4));
+		*(u32 *)(a + n) = *(u32 *)(b + n);
+		*(u32 *)(b + n) = t;
+#endif
+	} while (n);
 }
 
-static void generic_swap(void *a, void *b, int size)
+/**
+ * swap_bytes - swap two elements a byte at a time
+ * @a, @b: pointers to the elements
+ * @size: element size
+ *
+ * This is the fallback if alignment doesn't allow using larger chunks.
+ */
+static void swap_bytes(void *a, void *b, size_t n)
 {
-	char t;
-
 	do {
-		t = *(char *)a;
-		*(char *)a++ = *(char *)b;
-		*(char *)b++ = t;
-	} while (--size > 0);
+		char t = ((char *)a)[--n];
+		((char *)a)[n] = ((char *)b)[n];
+		((char *)b)[n] = t;
+	} while (n);
+}
+
+typedef void (*swap_func_t)(void *a, void *b, int size);
+
+/*
+ * The values are arbitrary as long as they can't be confused with
+ * a pointer, but small integers make for the smallest compare
+ * instructions.
+ */
+#define SWAP_WORDS_64 (swap_func_t)0
+#define SWAP_WORDS_32 (swap_func_t)1
+#define SWAP_BYTES    (swap_func_t)2
+
+/*
+ * The function pointer is last to make tail calls most efficient if the
+ * compiler decides not to inline this function.
+ */
+static void do_swap(void *a, void *b, size_t size, swap_func_t swap_func)
+{
+	if (swap_func == SWAP_WORDS_64)
+		swap_words_64(a, b, size);
+	else if (swap_func == SWAP_WORDS_32)
+		swap_words_32(a, b, size);
+	else if (swap_func == SWAP_BYTES)
+		swap_bytes(a, b, size);
+	else
+		swap_func(a, b, (int)size);
+}
+
+/**
+ * parent - given the offset of the child, find the offset of the parent.
+ * @i: the offset of the heap element whose parent is sought.  Non-zero.
+ * @lsbit: a precomputed 1-bit mask, equal to "size & -size"
+ * @size: size of each element
+ *
+ * In terms of array indexes, the parent of element j = @i/@size is simply
+ * (j-1)/2.  But when working in byte offsets, we can't use implicit
+ * truncation of integer divides.
+ *
+ * Fortunately, we only need one bit of the quotient, not the full divide.
+ * @size has a least significant bit.  That bit will be clear if @i is
+ * an even multiple of @size, and set if it's an odd multiple.
+ *
+ * Logically, we're doing "if (i & lsbit) i -= size;", but since the
+ * branch is unpredictable, it's done with a bit of clever branch-free
+ * code instead.
+ */
+__attribute_const__ __always_inline
+static size_t parent(size_t i, unsigned int lsbit, size_t size)
+{
+	i -= size;
+	i -= size & -(i & lsbit);
+	return i / 2;
 }
 
 /**
@@ -50,57 +175,78 @@ static void generic_swap(void *a, void *b, int size)
  * @cmp_func: pointer to comparison function
  * @swap_func: pointer to swap function or NULL
  *
- * This function does a heapsort on the given array. You may provide a
- * swap_func function optimized to your element type.
+ * This function does a heapsort on the given array.  You may provide
+ * a swap_func function if you need to do something more than a memory
+ * copy (e.g. fix up pointers or auxiliary data), but the built-in swap
+ * avoids a slow retpoline and so is significantly faster.
  *
  * Sorting time is O(n log n) both on average and worst-case. While
- * qsort is about 20% faster on average, it suffers from exploitable
+ * quicksort is slightly faster on average, it suffers from exploitable
  * O(n*n) worst-case behavior and extra memory requirements that make
  * it less suitable for kernel use.
  */
-
 void sort(void *base, size_t num, size_t size,
 	  int (*cmp_func)(const void *, const void *),
 	  void (*swap_func)(void *, void *, int size))
 {
 	/* pre-scale counters for performance */
-	int i = (num/2 - 1) * size, n = num * size, c, r;
+	size_t n = num * size, a = (num/2) * size;
+	const unsigned int lsbit = size & -size;  /* Used to find parent */
+
+	if (!a)		/* num < 2 || size == 0 */
+		return;
 
 	if (!swap_func) {
-		if (size == 4 && alignment_ok(base, 4))
-			swap_func = u32_swap;
-		else if (size == 8 && alignment_ok(base, 8))
-			swap_func = u64_swap;
+		if (is_aligned(base, size, 8))
+			swap_func = SWAP_WORDS_64;
+		else if (is_aligned(base, size, 4))
+			swap_func = SWAP_WORDS_32;
 		else
-			swap_func = generic_swap;
+			swap_func = SWAP_BYTES;
 	}
 
-	/* heapify */
-	for ( ; i >= 0; i -= size) {
-		for (r = i; r * 2 + size < n; r  = c) {
-			c = r * 2 + size;
-			if (c < n - size &&
-					cmp_func(base + c, base + c + size) < 0)
-				c += size;
-			if (cmp_func(base + r, base + c) >= 0)
-				break;
-			swap_func(base + r, base + c, size);
-		}
-	}
+	/*
+	 * Loop invariants:
+	 * 1. elements [a,n) satisfy the heap property (compare greater than
+	 *    all of their children),
+	 * 2. elements [n,num*size) are sorted, and
+	 * 3. a <= b <= c <= d <= n (whenever they are valid).
+	 */
+	for (;;) {
+		size_t b, c, d;
+
+		if (a)			/* Building heap: sift down --a */
+			a -= size;
+		else if (n -= size)	/* Sorting: Extract root to --n */
+			do_swap(base, base + n, size, swap_func);
+		else			/* Sort complete */
+			break;
 
-	/* sort */
-	for (i = n - size; i > 0; i -= size) {
-		swap_func(base, base + i, size);
-		for (r = 0; r * 2 + size < i; r = c) {
-			c = r * 2 + size;
-			if (c < i - size &&
-					cmp_func(base + c, base + c + size) < 0)
-				c += size;
-			if (cmp_func(base + r, base + c) >= 0)
-				break;
-			swap_func(base + r, base + c, size);
+		/*
+		 * Sift element at "a" down into heap.  This is the
+		 * "bottom-up" variant, which significantly reduces
+		 * calls to cmp_func(): we find the sift-down path all
+		 * the way to the leaves (one compare per level), then
+		 * backtrack to find where to insert the target element.
+		 *
+		 * Because elements tend to sift down close to the leaves,
+		 * this uses fewer compares than doing two per level
+		 * on the way down.  (A bit more than half as many on
+		 * average, 3/4 worst-case.)
+		 */
+		for (b = a; c = 2*b + size, (d = c + size) < n;)
+			b = cmp_func(base + c, base + d) >= 0 ? c : d;
+		if (d == n)	/* Special case last leaf with no sibling */
+			b = c;
+
+		/* Now backtrack from "b" to the correct location for "a" */
+		while (b != a && cmp_func(base + a, base + b) >= 0)
+			b = parent(b, lsbit, size);
+		c = b;			/* Where "a" belongs */
+		while (b != a) {	/* Shift it into place */
+			b = parent(b, lsbit, size);
+			do_swap(base + b, base + c, size, swap_func);
 		}
 	}
 }
-
 EXPORT_SYMBOL(sort);
diff --git a/lib/string.c b/lib/string.c
index 3ab861c1a857..6016eb3ac73d 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -159,11 +159,9 @@ EXPORT_SYMBOL(strlcpy);
  * @src: Where to copy the string from
  * @count: Size of destination buffer
  *
- * Copy the string, or as much of it as fits, into the dest buffer.
- * The routine returns the number of characters copied (not including
- * the trailing NUL) or -E2BIG if the destination buffer wasn't big enough.
- * The behavior is undefined if the string buffers overlap.
- * The destination buffer is always NUL terminated, unless it's zero-sized.
+ * Copy the string, or as much of it as fits, into the dest buffer.  The
+ * behavior is undefined if the string buffers overlap.  The destination
+ * buffer is always NUL terminated, unless it's zero-sized.
  *
  * Preferred to strlcpy() since the API doesn't require reading memory
  * from the src string beyond the specified "count" bytes, and since
@@ -173,8 +171,10 @@ EXPORT_SYMBOL(strlcpy);
  *
  * Preferred to strncpy() since it always returns a valid string, and
  * doesn't unnecessarily force the tail of the destination buffer to be
- * zeroed.  If the zeroing is desired, it's likely cleaner to use strscpy()
- * with an overflow test, then just memset() the tail of the dest buffer.
+ * zeroed.  If zeroing is desired please use strscpy_pad().
+ *
+ * Return: The number of characters copied (not including the trailing
+ *         %NUL) or -E2BIG if the destination buffer wasn't big enough.
  */
 ssize_t strscpy(char *dest, const char *src, size_t count)
 {
@@ -237,6 +237,39 @@ ssize_t strscpy(char *dest, const char *src, size_t count)
 EXPORT_SYMBOL(strscpy);
 #endif
 
+/**
+ * strscpy_pad() - Copy a C-string into a sized buffer
+ * @dest: Where to copy the string to
+ * @src: Where to copy the string from
+ * @count: Size of destination buffer
+ *
+ * Copy the string, or as much of it as fits, into the dest buffer.  The
+ * behavior is undefined if the string buffers overlap.  The destination
+ * buffer is always %NUL terminated, unless it's zero-sized.
+ *
+ * If the source string is shorter than the destination buffer, zeros
+ * the tail of the destination buffer.
+ *
+ * For full explanation of why you may want to consider using the
+ * 'strscpy' functions please see the function docstring for strscpy().
+ *
+ * Return: The number of characters copied (not including the trailing
+ *         %NUL) or -E2BIG if the destination buffer wasn't big enough.
+ */
+ssize_t strscpy_pad(char *dest, const char *src, size_t count)
+{
+	ssize_t written;
+
+	written = strscpy(dest, src, count);
+	if (written < 0 || written == count - 1)
+		return written;
+
+	memset(dest + written + 1, 0, count - written - 1);
+
+	return written;
+}
+EXPORT_SYMBOL(strscpy_pad);
+
 #ifndef __HAVE_ARCH_STRCAT
 /**
  * strcat - Append one %NUL-terminated string to another
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index 6cd7d0740005..d3a501f2a81a 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -11,6 +11,9 @@
 #include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/uaccess.h>
+
+#include "../tools/testing/selftests/kselftest_module.h"
 
 static unsigned total_tests __initdata;
 static unsigned failed_tests __initdata;
@@ -224,7 +227,8 @@ static const unsigned long exp[] __initconst = {
 	BITMAP_FROM_U64(0xffffffff),
 	BITMAP_FROM_U64(0xfffffffe),
 	BITMAP_FROM_U64(0x3333333311111111ULL),
-	BITMAP_FROM_U64(0xffffffff77777777ULL)
+	BITMAP_FROM_U64(0xffffffff77777777ULL),
+	BITMAP_FROM_U64(0),
 };
 
 static const unsigned long exp2[] __initconst = {
@@ -247,55 +251,93 @@ static const struct test_bitmap_parselist parselist_tests[] __initconst = {
 	{0, "1-31:4/4",			&exp[9 * step], 32, 0},
 	{0, "0-31:1/4,32-63:2/4",	&exp[10 * step], 64, 0},
 	{0, "0-31:3/4,32-63:4/4",	&exp[11 * step], 64, 0},
+	{0, "  ,,  0-31:3/4  ,, 32-63:4/4  ,,  ",	&exp[11 * step], 64, 0},
 
 	{0, "0-31:1/4,32-63:2/4,64-95:3/4,96-127:4/4",	exp2, 128, 0},
 
 	{0, "0-2047:128/256", NULL, 2048, PARSE_TIME},
 
+	{0, "",				&exp[12 * step], 8, 0},
+	{0, "\n",			&exp[12 * step], 8, 0},
+	{0, ",,  ,,  , ,  ,",		&exp[12 * step], 8, 0},
+	{0, " ,  ,,  , ,   ",		&exp[12 * step], 8, 0},
+	{0, " ,  ,,  , ,   \n",		&exp[12 * step], 8, 0},
+
 	{-EINVAL, "-1",	NULL, 8, 0},
 	{-EINVAL, "-0",	NULL, 8, 0},
 	{-EINVAL, "10-1", NULL, 8, 0},
 	{-EINVAL, "0-31:", NULL, 8, 0},
 	{-EINVAL, "0-31:0", NULL, 8, 0},
+	{-EINVAL, "0-31:0/", NULL, 8, 0},
 	{-EINVAL, "0-31:0/0", NULL, 8, 0},
 	{-EINVAL, "0-31:1/0", NULL, 8, 0},
 	{-EINVAL, "0-31:10/1", NULL, 8, 0},
+	{-EOVERFLOW, "0-98765432123456789:10/1", NULL, 8, 0},
+
+	{-EINVAL, "a-31", NULL, 8, 0},
+	{-EINVAL, "0-a1", NULL, 8, 0},
+	{-EINVAL, "a-31:10/1", NULL, 8, 0},
+	{-EINVAL, "0-31:a/1", NULL, 8, 0},
+	{-EINVAL, "0-\n", NULL, 8, 0},
 };
 
-static void __init test_bitmap_parselist(void)
+static void __init __test_bitmap_parselist(int is_user)
 {
 	int i;
 	int err;
-	cycles_t cycles;
+	ktime_t time;
 	DECLARE_BITMAP(bmap, 2048);
+	char *mode = is_user ? "_user"  : "";
 
 	for (i = 0; i < ARRAY_SIZE(parselist_tests); i++) {
 #define ptest parselist_tests[i]
 
-		cycles = get_cycles();
-		err = bitmap_parselist(ptest.in, bmap, ptest.nbits);
-		cycles = get_cycles() - cycles;
+		if (is_user) {
+			mm_segment_t orig_fs = get_fs();
+			size_t len = strlen(ptest.in);
+
+			set_fs(KERNEL_DS);
+			time = ktime_get();
+			err = bitmap_parselist_user(ptest.in, len,
+						    bmap, ptest.nbits);
+			time = ktime_get() - time;
+			set_fs(orig_fs);
+		} else {
+			time = ktime_get();
+			err = bitmap_parselist(ptest.in, bmap, ptest.nbits);
+			time = ktime_get() - time;
+		}
 
 		if (err != ptest.errno) {
-			pr_err("test %d: input is %s, errno is %d, expected %d\n",
-					i, ptest.in, err, ptest.errno);
+			pr_err("parselist%s: %d: input is %s, errno is %d, expected %d\n",
+					mode, i, ptest.in, err, ptest.errno);
 			continue;
 		}
 
 		if (!err && ptest.expected
 			 && !__bitmap_equal(bmap, ptest.expected, ptest.nbits)) {
-			pr_err("test %d: input is %s, result is 0x%lx, expected 0x%lx\n",
-					i, ptest.in, bmap[0], *ptest.expected);
+			pr_err("parselist%s: %d: input is %s, result is 0x%lx, expected 0x%lx\n",
+					mode, i, ptest.in, bmap[0],
+					*ptest.expected);
 			continue;
 		}
 
 		if (ptest.flags & PARSE_TIME)
-			pr_err("test %d: input is '%s' OK, Time: %llu\n",
-					i, ptest.in,
-					(unsigned long long)cycles);
+			pr_err("parselist%s: %d: input is '%s' OK, Time: %llu\n",
+					mode, i, ptest.in, time);
 	}
 }
 
+static void __init test_bitmap_parselist(void)
+{
+	__test_bitmap_parselist(0);
+}
+
+static void __init test_bitmap_parselist_user(void)
+{
+	__test_bitmap_parselist(1);
+}
+
 #define EXP_BYTES	(sizeof(exp) * 8)
 
 static void __init test_bitmap_arr32(void)
@@ -361,30 +403,17 @@ static void noinline __init test_mem_optimisations(void)
 	}
 }
 
-static int __init test_bitmap_init(void)
+static void __init selftest(void)
 {
 	test_zero_clear();
 	test_fill_set();
 	test_copy();
 	test_bitmap_arr32();
 	test_bitmap_parselist();
+	test_bitmap_parselist_user();
 	test_mem_optimisations();
-
-	if (failed_tests == 0)
-		pr_info("all %u tests passed\n", total_tests);
-	else
-		pr_warn("failed %u out of %u tests\n",
-			failed_tests, total_tests);
-
-	return failed_tests ? -EINVAL : 0;
 }
 
-static void __exit test_bitmap_cleanup(void)
-{
-}
-
-module_init(test_bitmap_init);
-module_exit(test_bitmap_cleanup);
-
+KSTM_MODULE_LOADERS(test_bitmap);
 MODULE_AUTHOR("david decotigny <david.decotigny@googlers.com>");
 MODULE_LICENSE("GPL");
diff --git a/lib/test_printf.c b/lib/test_printf.c
index 659b6cc0d483..93da0a5000ec 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -21,6 +21,8 @@
 #include <linux/gfp.h>
 #include <linux/mm.h>
 
+#include "../tools/testing/selftests/kselftest_module.h"
+
 #define BUF_SIZE 256
 #define PAD_SIZE 16
 #define FILL_CHAR '$'
@@ -239,6 +241,7 @@ plain_format(void)
 #define PTR ((void *)0x456789ab)
 #define PTR_STR "456789ab"
 #define PTR_VAL_NO_CRNG "(ptrval)"
+#define ZEROS ""
 
 static int __init
 plain_format(void)
@@ -268,7 +271,6 @@ plain_hash_to_buffer(const void *p, char *buf, size_t len)
 	return 0;
 }
 
-
 static int __init
 plain_hash(void)
 {
@@ -326,6 +328,24 @@ test_hashed(const char *fmt, const void *p)
 }
 
 static void __init
+null_pointer(void)
+{
+	test_hashed("%p", NULL);
+	test(ZEROS "00000000", "%px", NULL);
+	test("(null)", "%pE", NULL);
+}
+
+#define PTR_INVALID ((void *)0x000000ab)
+
+static void __init
+invalid_pointer(void)
+{
+	test_hashed("%p", PTR_INVALID);
+	test(ZEROS "000000ab", "%px", PTR_INVALID);
+	test("(efault)", "%pE", PTR_INVALID);
+}
+
+static void __init
 symbol_ptr(void)
 {
 }
@@ -462,8 +482,7 @@ struct_rtc_time(void)
 		.tm_year = 118,
 	};
 
-	test_hashed("%pt", &tm);
-
+	test("(%ptR?)", "%pt", &tm);
 	test("2018-11-26T05:35:43", "%ptR", &tm);
 	test("0118-10-26T05:35:43", "%ptRr", &tm);
 	test("05:35:43|2018-11-26", "%ptRt|%ptRd", &tm, &tm);
@@ -481,14 +500,14 @@ static void __init
 large_bitmap(void)
 {
 	const int nbits = 1 << 16;
-	unsigned long *bits = kcalloc(BITS_TO_LONGS(nbits), sizeof(long), GFP_KERNEL);
+	unsigned long *bits = bitmap_zalloc(nbits, GFP_KERNEL);
 	if (!bits)
 		return;
 
 	bitmap_set(bits, 1, 20);
 	bitmap_set(bits, 60000, 15);
 	test("1-20,60000-60014", "%*pbl", nbits, bits);
-	kfree(bits);
+	bitmap_free(bits);
 }
 
 static void __init
@@ -572,6 +591,8 @@ static void __init
 test_pointer(void)
 {
 	plain();
+	null_pointer();
+	invalid_pointer();
 	symbol_ptr();
 	kernel_ptr();
 	struct_resource();
@@ -590,12 +611,11 @@ test_pointer(void)
 	flags();
 }
 
-static int __init
-test_printf_init(void)
+static void __init selftest(void)
 {
 	alloced_buffer = kmalloc(BUF_SIZE + 2*PAD_SIZE, GFP_KERNEL);
 	if (!alloced_buffer)
-		return -ENOMEM;
+		return;
 	test_buffer = alloced_buffer + PAD_SIZE;
 
 	test_basic();
@@ -604,16 +624,8 @@ test_printf_init(void)
 	test_pointer();
 
 	kfree(alloced_buffer);
-
-	if (failed_tests == 0)
-		pr_info("all %u tests passed\n", total_tests);
-	else
-		pr_warn("failed %u out of %u tests\n", failed_tests, total_tests);
-
-	return failed_tests ? -EINVAL : 0;
 }
 
-module_init(test_printf_init);
-
+KSTM_MODULE_LOADERS(test_printf);
 MODULE_AUTHOR("Rasmus Villemoes <linux@rasmusvillemoes.dk>");
 MODULE_LICENSE("GPL");
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index 3bd2e91bfc29..084fe5a6ac57 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -500,7 +500,7 @@ static unsigned int __init print_ht(struct rhltable *rhlt)
 		struct rhash_head *pos, *next;
 		struct test_obj_rhl *p;
 
-		pos = rht_dereference(tbl->buckets[i], ht);
+		pos = rht_ptr_exclusive(tbl->buckets + i);
 		next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL;
 
 		if (!rht_is_a_nulls(pos)) {
diff --git a/lib/test_strscpy.c b/lib/test_strscpy.c
new file mode 100644
index 000000000000..a827f94601f5
--- /dev/null
+++ b/lib/test_strscpy.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/string.h>
+
+#include "../tools/testing/selftests/kselftest_module.h"
+
+/*
+ * Kernel module for testing 'strscpy' family of functions.
+ */
+
+KSTM_MODULE_GLOBALS();
+
+/*
+ * tc() - Run a specific test case.
+ * @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()
+ * @terminator: 1 if there should be a terminating null byte 0 otherwise.
+ * @chars: Number of characters from the src string expected to be
+ *         written to the dst buffer.
+ * @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 int __init tc(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';
+
+	total_tests++;
+
+	if (!src) {
+		pr_err("null source string not supported\n");
+		return -1;
+	}
+
+	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 */
+	if (count > max_count) {
+		pr_err("count (%d) is too big (%d) ... aborting", count, max_count);
+		return -1;
+	}
+	if (expected > max_expected) {
+		pr_warn("expected (%d) is bigger than can possibly be returned (%d)",
+			expected, max_expected);
+	}
+
+	written = strscpy_pad(buf, src, count);
+	if ((written) != (expected)) {
+		pr_err("%d != %d (written, expected)\n", written, expected);
+		goto fail;
+	}
+
+	if (count && written == -E2BIG) {
+		if (strncmp(buf, src, count - 1) != 0) {
+			pr_err("buffer state invalid for -E2BIG\n");
+			goto fail;
+		}
+		if (buf[count - 1] != '\0') {
+			pr_err("too big string is not null terminated correctly\n");
+			goto fail;
+		}
+	}
+
+	for (i = 0; i < chars; i++) {
+		if (buf[i] != src[i]) {
+			pr_err("buf[i]==%c != src[i]==%c\n", buf[i], src[i]);
+			goto fail;
+		}
+	}
+
+	if (terminator) {
+		if (buf[count - 1] != '\0') {
+			pr_err("string is not null terminated correctly\n");
+			goto fail;
+		}
+	}
+
+	for (i = 0; i < pad; i++) {
+		index = chars + terminator + i;
+		if (buf[index] != '\0') {
+			pr_err("padding missing at index: %d\n", i);
+			goto fail;
+		}
+	}
+
+	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 */
+		if (buf[index] != POISON) {
+			pr_err("poison value missing at index: %d\n", i);
+			goto fail;
+		}
+	}
+
+	return 0;
+fail:
+	failed_tests++;
+	return -1;
+}
+
+static void __init selftest(void)
+{
+	/*
+	 * tc() 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().
+	 */
+
+	/* tc(src, count, expected, chars, terminator, pad) */
+	KSTM_CHECK_ZERO(tc("a", 0, -E2BIG, 0, 0, 0));
+	KSTM_CHECK_ZERO(tc("", 0, -E2BIG, 0, 0, 0));
+
+	KSTM_CHECK_ZERO(tc("a", 1, -E2BIG, 0, 1, 0));
+	KSTM_CHECK_ZERO(tc("", 1, 0, 0, 1, 0));
+
+	KSTM_CHECK_ZERO(tc("ab", 2, -E2BIG, 1, 1, 0));
+	KSTM_CHECK_ZERO(tc("a", 2, 1, 1, 1, 0));
+	KSTM_CHECK_ZERO(tc("", 2, 0, 0, 1, 1));
+
+	KSTM_CHECK_ZERO(tc("abc", 3, -E2BIG, 2, 1, 0));
+	KSTM_CHECK_ZERO(tc("ab", 3, 2, 2, 1, 0));
+	KSTM_CHECK_ZERO(tc("a", 3, 1, 1, 1, 1));
+	KSTM_CHECK_ZERO(tc("", 3, 0, 0, 1, 2));
+
+	KSTM_CHECK_ZERO(tc("abcd", 4, -E2BIG, 3, 1, 0));
+	KSTM_CHECK_ZERO(tc("abc", 4, 3, 3, 1, 0));
+	KSTM_CHECK_ZERO(tc("ab", 4, 2, 2, 1, 1));
+	KSTM_CHECK_ZERO(tc("a", 4, 1, 1, 1, 2));
+	KSTM_CHECK_ZERO(tc("", 4, 0, 0, 1, 3));
+}
+
+KSTM_MODULE_LOADERS(test_strscpy);
+MODULE_AUTHOR("Tobin C. Harding <tobin@kernel.org>");
+MODULE_LICENSE("GPL");
diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c
index 3dd801c1c85b..566dad3f4196 100644
--- a/lib/test_sysctl.c
+++ b/lib/test_sysctl.c
@@ -47,6 +47,9 @@ struct test_sysctl_data {
 	unsigned int uint_0001;
 
 	char string_0001[65];
+
+#define SYSCTL_TEST_BITMAP_SIZE	65536
+	unsigned long *bitmap_0001;
 };
 
 static struct test_sysctl_data test_data = {
@@ -102,6 +105,13 @@ static struct ctl_table test_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dostring,
 	},
+	{
+		.procname	= "bitmap_0001",
+		.data		= &test_data.bitmap_0001,
+		.maxlen		= SYSCTL_TEST_BITMAP_SIZE,
+		.mode		= 0644,
+		.proc_handler	= proc_do_large_bitmap,
+	},
 	{ }
 };
 
@@ -129,15 +139,21 @@ static struct ctl_table_header *test_sysctl_header;
 
 static int __init test_sysctl_init(void)
 {
+	test_data.bitmap_0001 = kzalloc(SYSCTL_TEST_BITMAP_SIZE/8, GFP_KERNEL);
+	if (!test_data.bitmap_0001)
+		return -ENOMEM;
 	test_sysctl_header = register_sysctl_table(test_sysctl_root_table);
-	if (!test_sysctl_header)
+	if (!test_sysctl_header) {
+		kfree(test_data.bitmap_0001);
 		return -ENOMEM;
+	}
 	return 0;
 }
 late_initcall(test_sysctl_init);
 
 static void __exit test_sysctl_exit(void)
 {
+	kfree(test_data.bitmap_0001);
 	if (test_sysctl_header)
 		unregister_sysctl_table(test_sysctl_header);
 }
diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c
index f832b095afba..8bbefcaddfe8 100644
--- a/lib/test_vmalloc.c
+++ b/lib/test_vmalloc.c
@@ -384,12 +384,11 @@ static int test_func(void *private)
 {
 	struct test_driver *t = private;
 	int random_array[ARRAY_SIZE(test_case_array)];
-	int index, i, j, ret;
+	int index, i, j;
 	ktime_t kt;
 	u64 delta;
 
-	ret = set_cpus_allowed_ptr(current, cpumask_of(t->cpu));
-	if (ret < 0)
+	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++)
@@ -415,8 +414,7 @@ static int test_func(void *private)
 
 		kt = ktime_get();
 		for (j = 0; j < test_repeat_count; j++) {
-			ret = test_case_array[index].test_func();
-			if (!ret)
+			if (!test_case_array[index].test_func())
 				per_cpu_test_data[t->cpu][index].test_passed++;
 			else
 				per_cpu_test_data[t->cpu][index].test_failed++;
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 791b6fa36905..2f003cfe340e 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -593,15 +593,13 @@ char *widen_string(char *buf, int n, char *end, struct printf_spec spec)
 	return buf;
 }
 
-static noinline_for_stack
-char *string(char *buf, char *end, const char *s, struct printf_spec spec)
+/* Handle string from a well known address. */
+static char *string_nocheck(char *buf, char *end, const char *s,
+			    struct printf_spec spec)
 {
 	int len = 0;
 	size_t lim = spec.precision;
 
-	if ((unsigned long)s < PAGE_SIZE)
-		s = "(null)";
-
 	while (lim--) {
 		char c = *s++;
 		if (!c)
@@ -614,9 +612,64 @@ char *string(char *buf, char *end, const char *s, struct printf_spec spec)
 	return widen_string(buf, len, end, spec);
 }
 
+/* Be careful: error messages must fit into the given buffer. */
+static char *error_string(char *buf, char *end, const char *s,
+			  struct printf_spec spec)
+{
+	/*
+	 * Hard limit to avoid a completely insane messages. It actually
+	 * works pretty well because most error messages are in
+	 * the many pointer format modifiers.
+	 */
+	if (spec.precision == -1)
+		spec.precision = 2 * sizeof(void *);
+
+	return string_nocheck(buf, end, s, spec);
+}
+
+/*
+ * Do not call any complex external code here. Nested printk()/vsprintf()
+ * might cause infinite loops. Failures might break printk() and would
+ * be hard to debug.
+ */
+static const char *check_pointer_msg(const void *ptr)
+{
+	if (!ptr)
+		return "(null)";
+
+	if ((unsigned long)ptr < PAGE_SIZE || IS_ERR_VALUE(ptr))
+		return "(efault)";
+
+	return NULL;
+}
+
+static int check_pointer(char **buf, char *end, const void *ptr,
+			 struct printf_spec spec)
+{
+	const char *err_msg;
+
+	err_msg = check_pointer_msg(ptr);
+	if (err_msg) {
+		*buf = error_string(*buf, end, err_msg, spec);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
 static noinline_for_stack
-char *pointer_string(char *buf, char *end, const void *ptr,
-		     struct printf_spec spec)
+char *string(char *buf, char *end, const char *s,
+	     struct printf_spec spec)
+{
+	if (check_pointer(&buf, end, s, spec))
+		return buf;
+
+	return string_nocheck(buf, end, s, spec);
+}
+
+static char *pointer_string(char *buf, char *end,
+			    const void *ptr,
+			    struct printf_spec spec)
 {
 	spec.base = 16;
 	spec.flags |= SMALL;
@@ -701,7 +754,7 @@ static char *ptr_to_id(char *buf, char *end, const void *ptr,
 	if (static_branch_unlikely(&not_filled_random_ptr_key)) {
 		spec.field_width = 2 * sizeof(ptr);
 		/* string length must be less than default_width */
-		return string(buf, end, str, spec);
+		return error_string(buf, end, str, spec);
 	}
 
 #ifdef CONFIG_64BIT
@@ -717,6 +770,55 @@ static char *ptr_to_id(char *buf, char *end, const void *ptr,
 	return pointer_string(buf, end, (const void *)hashval, spec);
 }
 
+int kptr_restrict __read_mostly;
+
+static noinline_for_stack
+char *restricted_pointer(char *buf, char *end, const void *ptr,
+			 struct printf_spec spec)
+{
+	switch (kptr_restrict) {
+	case 0:
+		/* Handle as %p, hash and do _not_ leak addresses. */
+		return ptr_to_id(buf, end, ptr, spec);
+	case 1: {
+		const struct cred *cred;
+
+		/*
+		 * kptr_restrict==1 cannot be used in IRQ context
+		 * because its test for CAP_SYSLOG would be meaningless.
+		 */
+		if (in_irq() || in_serving_softirq() || in_nmi()) {
+			if (spec.field_width == -1)
+				spec.field_width = 2 * sizeof(ptr);
+			return error_string(buf, end, "pK-error", spec);
+		}
+
+		/*
+		 * Only print the real pointer value if the current
+		 * process has CAP_SYSLOG and is running with the
+		 * same credentials it started with. This is because
+		 * access to files is checked at open() time, but %pK
+		 * checks permission at read() time. We don't want to
+		 * leak pointer values if a binary opens a file using
+		 * %pK and then elevates privileges before reading it.
+		 */
+		cred = current_cred();
+		if (!has_capability_noaudit(current, CAP_SYSLOG) ||
+		    !uid_eq(cred->euid, cred->uid) ||
+		    !gid_eq(cred->egid, cred->gid))
+			ptr = NULL;
+		break;
+	}
+	case 2:
+	default:
+		/* Always print 0's for %pK */
+		ptr = NULL;
+		break;
+	}
+
+	return pointer_string(buf, end, ptr, spec);
+}
+
 static noinline_for_stack
 char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_spec spec,
 		  const char *fmt)
@@ -736,6 +838,11 @@ char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_sp
 
 	rcu_read_lock();
 	for (i = 0; i < depth; i++, d = p) {
+		if (check_pointer(&buf, end, d, spec)) {
+			rcu_read_unlock();
+			return buf;
+		}
+
 		p = READ_ONCE(d->d_parent);
 		array[i] = READ_ONCE(d->d_name.name);
 		if (p == d) {
@@ -766,8 +873,12 @@ static noinline_for_stack
 char *bdev_name(char *buf, char *end, struct block_device *bdev,
 		struct printf_spec spec, const char *fmt)
 {
-	struct gendisk *hd = bdev->bd_disk;
-	
+	struct gendisk *hd;
+
+	if (check_pointer(&buf, end, bdev, spec))
+		return buf;
+
+	hd = bdev->bd_disk;
 	buf = string(buf, end, hd->disk_name, spec);
 	if (bdev->bd_part->partno) {
 		if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) {
@@ -802,7 +913,7 @@ char *symbol_string(char *buf, char *end, void *ptr,
 	else
 		sprint_symbol_no_offset(sym, value);
 
-	return string(buf, end, sym, spec);
+	return string_nocheck(buf, end, sym, spec);
 #else
 	return special_hex_number(buf, end, value, sizeof(void *));
 #endif
@@ -886,29 +997,32 @@ char *resource_string(char *buf, char *end, struct resource *res,
 	int decode = (fmt[0] == 'R') ? 1 : 0;
 	const struct printf_spec *specp;
 
+	if (check_pointer(&buf, end, res, spec))
+		return buf;
+
 	*p++ = '[';
 	if (res->flags & IORESOURCE_IO) {
-		p = string(p, pend, "io  ", str_spec);
+		p = string_nocheck(p, pend, "io  ", str_spec);
 		specp = &io_spec;
 	} else if (res->flags & IORESOURCE_MEM) {
-		p = string(p, pend, "mem ", str_spec);
+		p = string_nocheck(p, pend, "mem ", str_spec);
 		specp = &mem_spec;
 	} else if (res->flags & IORESOURCE_IRQ) {
-		p = string(p, pend, "irq ", str_spec);
+		p = string_nocheck(p, pend, "irq ", str_spec);
 		specp = &default_dec_spec;
 	} else if (res->flags & IORESOURCE_DMA) {
-		p = string(p, pend, "dma ", str_spec);
+		p = string_nocheck(p, pend, "dma ", str_spec);
 		specp = &default_dec_spec;
 	} else if (res->flags & IORESOURCE_BUS) {
-		p = string(p, pend, "bus ", str_spec);
+		p = string_nocheck(p, pend, "bus ", str_spec);
 		specp = &bus_spec;
 	} else {
-		p = string(p, pend, "??? ", str_spec);
+		p = string_nocheck(p, pend, "??? ", str_spec);
 		specp = &mem_spec;
 		decode = 0;
 	}
 	if (decode && res->flags & IORESOURCE_UNSET) {
-		p = string(p, pend, "size ", str_spec);
+		p = string_nocheck(p, pend, "size ", str_spec);
 		p = number(p, pend, resource_size(res), *specp);
 	} else {
 		p = number(p, pend, res->start, *specp);
@@ -919,21 +1033,21 @@ char *resource_string(char *buf, char *end, struct resource *res,
 	}
 	if (decode) {
 		if (res->flags & IORESOURCE_MEM_64)
-			p = string(p, pend, " 64bit", str_spec);
+			p = string_nocheck(p, pend, " 64bit", str_spec);
 		if (res->flags & IORESOURCE_PREFETCH)
-			p = string(p, pend, " pref", str_spec);
+			p = string_nocheck(p, pend, " pref", str_spec);
 		if (res->flags & IORESOURCE_WINDOW)
-			p = string(p, pend, " window", str_spec);
+			p = string_nocheck(p, pend, " window", str_spec);
 		if (res->flags & IORESOURCE_DISABLED)
-			p = string(p, pend, " disabled", str_spec);
+			p = string_nocheck(p, pend, " disabled", str_spec);
 	} else {
-		p = string(p, pend, " flags ", str_spec);
+		p = string_nocheck(p, pend, " flags ", str_spec);
 		p = number(p, pend, res->flags, default_flag_spec);
 	}
 	*p++ = ']';
 	*p = '\0';
 
-	return string(buf, end, sym, spec);
+	return string_nocheck(buf, end, sym, spec);
 }
 
 static noinline_for_stack
@@ -948,9 +1062,8 @@ char *hex_string(char *buf, char *end, u8 *addr, struct printf_spec spec,
 		/* nothing to print */
 		return buf;
 
-	if (ZERO_OR_NULL_PTR(addr))
-		/* NULL pointer */
-		return string(buf, end, NULL, spec);
+	if (check_pointer(&buf, end, addr, spec))
+		return buf;
 
 	switch (fmt[1]) {
 	case 'C':
@@ -997,6 +1110,9 @@ char *bitmap_string(char *buf, char *end, unsigned long *bitmap,
 	int i, chunksz;
 	bool first = true;
 
+	if (check_pointer(&buf, end, bitmap, spec))
+		return buf;
+
 	/* reused to print numbers */
 	spec = (struct printf_spec){ .flags = SMALL | ZEROPAD, .base = 16 };
 
@@ -1038,6 +1154,9 @@ char *bitmap_list_string(char *buf, char *end, unsigned long *bitmap,
 	int cur, rbot, rtop;
 	bool first = true;
 
+	if (check_pointer(&buf, end, bitmap, spec))
+		return buf;
+
 	rbot = cur = find_first_bit(bitmap, nr_bits);
 	while (cur < nr_bits) {
 		rtop = cur;
@@ -1076,6 +1195,9 @@ char *mac_address_string(char *buf, char *end, u8 *addr,
 	char separator;
 	bool reversed = false;
 
+	if (check_pointer(&buf, end, addr, spec))
+		return buf;
+
 	switch (fmt[1]) {
 	case 'F':
 		separator = '-';
@@ -1101,7 +1223,7 @@ char *mac_address_string(char *buf, char *end, u8 *addr,
 	}
 	*p = '\0';
 
-	return string(buf, end, mac_addr, spec);
+	return string_nocheck(buf, end, mac_addr, spec);
 }
 
 static noinline_for_stack
@@ -1264,7 +1386,7 @@ char *ip6_addr_string(char *buf, char *end, const u8 *addr,
 	else
 		ip6_string(ip6_addr, addr, fmt);
 
-	return string(buf, end, ip6_addr, spec);
+	return string_nocheck(buf, end, ip6_addr, spec);
 }
 
 static noinline_for_stack
@@ -1275,7 +1397,7 @@ char *ip4_addr_string(char *buf, char *end, const u8 *addr,
 
 	ip4_string(ip4_addr, addr, fmt);
 
-	return string(buf, end, ip4_addr, spec);
+	return string_nocheck(buf, end, ip4_addr, spec);
 }
 
 static noinline_for_stack
@@ -1337,7 +1459,7 @@ char *ip6_addr_string_sa(char *buf, char *end, const struct sockaddr_in6 *sa,
 	}
 	*p = '\0';
 
-	return string(buf, end, ip6_addr, spec);
+	return string_nocheck(buf, end, ip6_addr, spec);
 }
 
 static noinline_for_stack
@@ -1372,7 +1494,42 @@ char *ip4_addr_string_sa(char *buf, char *end, const struct sockaddr_in *sa,
 	}
 	*p = '\0';
 
-	return string(buf, end, ip4_addr, spec);
+	return string_nocheck(buf, end, ip4_addr, spec);
+}
+
+static noinline_for_stack
+char *ip_addr_string(char *buf, char *end, const void *ptr,
+		     struct printf_spec spec, const char *fmt)
+{
+	char *err_fmt_msg;
+
+	if (check_pointer(&buf, end, ptr, spec))
+		return buf;
+
+	switch (fmt[1]) {
+	case '6':
+		return ip6_addr_string(buf, end, ptr, spec, fmt);
+	case '4':
+		return ip4_addr_string(buf, end, ptr, spec, fmt);
+	case 'S': {
+		const union {
+			struct sockaddr		raw;
+			struct sockaddr_in	v4;
+			struct sockaddr_in6	v6;
+		} *sa = ptr;
+
+		switch (sa->raw.sa_family) {
+		case AF_INET:
+			return ip4_addr_string_sa(buf, end, &sa->v4, spec, fmt);
+		case AF_INET6:
+			return ip6_addr_string_sa(buf, end, &sa->v6, spec, fmt);
+		default:
+			return error_string(buf, end, "(einval)", spec);
+		}}
+	}
+
+	err_fmt_msg = fmt[0] == 'i' ? "(%pi?)" : "(%pI?)";
+	return error_string(buf, end, err_fmt_msg, spec);
 }
 
 static noinline_for_stack
@@ -1387,9 +1544,8 @@ char *escaped_string(char *buf, char *end, u8 *addr, struct printf_spec spec,
 	if (spec.field_width == 0)
 		return buf;				/* nothing to print */
 
-	if (ZERO_OR_NULL_PTR(addr))
-		return string(buf, end, NULL, spec);	/* NULL pointer */
-
+	if (check_pointer(&buf, end, addr, spec))
+		return buf;
 
 	do {
 		switch (fmt[count++]) {
@@ -1435,6 +1591,21 @@ char *escaped_string(char *buf, char *end, u8 *addr, struct printf_spec spec,
 	return buf;
 }
 
+static char *va_format(char *buf, char *end, struct va_format *va_fmt,
+		       struct printf_spec spec, const char *fmt)
+{
+	va_list va;
+
+	if (check_pointer(&buf, end, va_fmt, spec))
+		return buf;
+
+	va_copy(va, *va_fmt->va);
+	buf += vsnprintf(buf, end > buf ? end - buf : 0, va_fmt->fmt, va);
+	va_end(va);
+
+	return buf;
+}
+
 static noinline_for_stack
 char *uuid_string(char *buf, char *end, const u8 *addr,
 		  struct printf_spec spec, const char *fmt)
@@ -1445,6 +1616,9 @@ char *uuid_string(char *buf, char *end, const u8 *addr,
 	const u8 *index = uuid_index;
 	bool uc = false;
 
+	if (check_pointer(&buf, end, addr, spec))
+		return buf;
+
 	switch (*(++fmt)) {
 	case 'L':
 		uc = true;		/* fall-through */
@@ -1473,56 +1647,7 @@ char *uuid_string(char *buf, char *end, const u8 *addr,
 
 	*p = 0;
 
-	return string(buf, end, uuid, spec);
-}
-
-int kptr_restrict __read_mostly;
-
-static noinline_for_stack
-char *restricted_pointer(char *buf, char *end, const void *ptr,
-			 struct printf_spec spec)
-{
-	switch (kptr_restrict) {
-	case 0:
-		/* Always print %pK values */
-		break;
-	case 1: {
-		const struct cred *cred;
-
-		/*
-		 * kptr_restrict==1 cannot be used in IRQ context
-		 * because its test for CAP_SYSLOG would be meaningless.
-		 */
-		if (in_irq() || in_serving_softirq() || in_nmi()) {
-			if (spec.field_width == -1)
-				spec.field_width = 2 * sizeof(ptr);
-			return string(buf, end, "pK-error", spec);
-		}
-
-		/*
-		 * Only print the real pointer value if the current
-		 * process has CAP_SYSLOG and is running with the
-		 * same credentials it started with. This is because
-		 * access to files is checked at open() time, but %pK
-		 * checks permission at read() time. We don't want to
-		 * leak pointer values if a binary opens a file using
-		 * %pK and then elevates privileges before reading it.
-		 */
-		cred = current_cred();
-		if (!has_capability_noaudit(current, CAP_SYSLOG) ||
-		    !uid_eq(cred->euid, cred->uid) ||
-		    !gid_eq(cred->egid, cred->gid))
-			ptr = NULL;
-		break;
-	}
-	case 2:
-	default:
-		/* Always print 0's for %pK */
-		ptr = NULL;
-		break;
-	}
-
-	return pointer_string(buf, end, ptr, spec);
+	return string_nocheck(buf, end, uuid, spec);
 }
 
 static noinline_for_stack
@@ -1532,24 +1657,31 @@ char *netdev_bits(char *buf, char *end, const void *addr,
 	unsigned long long num;
 	int size;
 
+	if (check_pointer(&buf, end, addr, spec))
+		return buf;
+
 	switch (fmt[1]) {
 	case 'F':
 		num = *(const netdev_features_t *)addr;
 		size = sizeof(netdev_features_t);
 		break;
 	default:
-		return ptr_to_id(buf, end, addr, spec);
+		return error_string(buf, end, "(%pN?)", spec);
 	}
 
 	return special_hex_number(buf, end, num, size);
 }
 
 static noinline_for_stack
-char *address_val(char *buf, char *end, const void *addr, const char *fmt)
+char *address_val(char *buf, char *end, const void *addr,
+		  struct printf_spec spec, const char *fmt)
 {
 	unsigned long long num;
 	int size;
 
+	if (check_pointer(&buf, end, addr, spec))
+		return buf;
+
 	switch (fmt[1]) {
 	case 'd':
 		num = *(const dma_addr_t *)addr;
@@ -1601,12 +1733,16 @@ char *time_str(char *buf, char *end, const struct rtc_time *tm, bool r)
 }
 
 static noinline_for_stack
-char *rtc_str(char *buf, char *end, const struct rtc_time *tm, const char *fmt)
+char *rtc_str(char *buf, char *end, const struct rtc_time *tm,
+	      struct printf_spec spec, const char *fmt)
 {
 	bool have_t = true, have_d = true;
 	bool raw = false;
 	int count = 2;
 
+	if (check_pointer(&buf, end, tm, spec))
+		return buf;
+
 	switch (fmt[count]) {
 	case 'd':
 		have_t = false;
@@ -1640,9 +1776,9 @@ char *time_and_date(char *buf, char *end, void *ptr, struct printf_spec spec,
 {
 	switch (fmt[1]) {
 	case 'R':
-		return rtc_str(buf, end, (const struct rtc_time *)ptr, fmt);
+		return rtc_str(buf, end, (const struct rtc_time *)ptr, spec, fmt);
 	default:
-		return ptr_to_id(buf, end, ptr, spec);
+		return error_string(buf, end, "(%ptR?)", spec);
 	}
 }
 
@@ -1650,8 +1786,11 @@ static noinline_for_stack
 char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec,
 	    const char *fmt)
 {
-	if (!IS_ENABLED(CONFIG_HAVE_CLK) || !clk)
-		return string(buf, end, NULL, spec);
+	if (!IS_ENABLED(CONFIG_HAVE_CLK))
+		return error_string(buf, end, "(%pC?)", spec);
+
+	if (check_pointer(&buf, end, clk, spec))
+		return buf;
 
 	switch (fmt[1]) {
 	case 'n':
@@ -1659,7 +1798,7 @@ char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec,
 #ifdef CONFIG_COMMON_CLK
 		return string(buf, end, __clk_get_name(clk), spec);
 #else
-		return ptr_to_id(buf, end, clk, spec);
+		return error_string(buf, end, "(%pC?)", spec);
 #endif
 	}
 }
@@ -1692,11 +1831,15 @@ char *format_flags(char *buf, char *end, unsigned long flags,
 }
 
 static noinline_for_stack
-char *flags_string(char *buf, char *end, void *flags_ptr, const char *fmt)
+char *flags_string(char *buf, char *end, void *flags_ptr,
+		   struct printf_spec spec, const char *fmt)
 {
 	unsigned long flags;
 	const struct trace_print_flags *names;
 
+	if (check_pointer(&buf, end, flags_ptr, spec))
+		return buf;
+
 	switch (fmt[1]) {
 	case 'p':
 		flags = *(unsigned long *)flags_ptr;
@@ -1713,8 +1856,7 @@ char *flags_string(char *buf, char *end, void *flags_ptr, const char *fmt)
 		names = gfpflag_names;
 		break;
 	default:
-		WARN_ONCE(1, "Unsupported flags modifier: %c\n", fmt[1]);
-		return buf;
+		return error_string(buf, end, "(%pG?)", spec);
 	}
 
 	return format_flags(buf, end, flags, names);
@@ -1736,13 +1878,13 @@ char *device_node_gen_full_name(const struct device_node *np, char *buf, char *e
 
 	/* special case for root node */
 	if (!parent)
-		return string(buf, end, "/", default_str_spec);
+		return string_nocheck(buf, end, "/", default_str_spec);
 
 	for (depth = 0; parent->parent; depth++)
 		parent = parent->parent;
 
 	for ( ; depth >= 0; depth--) {
-		buf = string(buf, end, "/", default_str_spec);
+		buf = string_nocheck(buf, end, "/", default_str_spec);
 		buf = string(buf, end, device_node_name_for_depth(np, depth),
 			     default_str_spec);
 	}
@@ -1770,10 +1912,10 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
 	str_spec.field_width = -1;
 
 	if (!IS_ENABLED(CONFIG_OF))
-		return string(buf, end, "(!OF)", spec);
+		return error_string(buf, end, "(%pOF?)", spec);
 
-	if ((unsigned long)dn < PAGE_SIZE)
-		return string(buf, end, "(null)", spec);
+	if (check_pointer(&buf, end, dn, spec))
+		return buf;
 
 	/* simple case without anything any more format specifiers */
 	fmt++;
@@ -1814,7 +1956,7 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
 			tbuf[2] = of_node_check_flag(dn, OF_POPULATED) ? 'P' : '-';
 			tbuf[3] = of_node_check_flag(dn, OF_POPULATED_BUS) ? 'B' : '-';
 			tbuf[4] = 0;
-			buf = string(buf, end, tbuf, str_spec);
+			buf = string_nocheck(buf, end, tbuf, str_spec);
 			break;
 		case 'c':	/* major compatible string */
 			ret = of_property_read_string(dn, "compatible", &p);
@@ -1825,10 +1967,10 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
 			has_mult = false;
 			of_property_for_each_string(dn, "compatible", prop, p) {
 				if (has_mult)
-					buf = string(buf, end, ",", str_spec);
-				buf = string(buf, end, "\"", str_spec);
+					buf = string_nocheck(buf, end, ",", str_spec);
+				buf = string_nocheck(buf, end, "\"", str_spec);
 				buf = string(buf, end, p, str_spec);
-				buf = string(buf, end, "\"", str_spec);
+				buf = string_nocheck(buf, end, "\"", str_spec);
 
 				has_mult = true;
 			}
@@ -1841,6 +1983,17 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
 	return widen_string(buf, buf - buf_start, end, spec);
 }
 
+static char *kobject_string(char *buf, char *end, void *ptr,
+			    struct printf_spec spec, const char *fmt)
+{
+	switch (fmt[1]) {
+	case 'F':
+		return device_node_string(buf, end, ptr, spec, fmt + 1);
+	}
+
+	return error_string(buf, end, "(%pO?)", spec);
+}
+
 /*
  * Show a '%p' thing.  A kernel extension is that the '%p' is followed
  * by an extra set of alphanumeric characters that are extended format
@@ -1957,18 +2110,6 @@ static noinline_for_stack
 char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 	      struct printf_spec spec)
 {
-	const int default_width = 2 * sizeof(void *);
-
-	if (!ptr && *fmt != 'K' && *fmt != 'x') {
-		/*
-		 * Print (null) with the same width as a pointer so it makes
-		 * tabular output look nice.
-		 */
-		if (spec.field_width == -1)
-			spec.field_width = default_width;
-		return string(buf, end, "(null)", spec);
-	}
-
 	switch (*fmt) {
 	case 'F':
 	case 'f':
@@ -2004,50 +2145,19 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 					 * 4:	001.002.003.004
 					 * 6:   000102...0f
 					 */
-		switch (fmt[1]) {
-		case '6':
-			return ip6_addr_string(buf, end, ptr, spec, fmt);
-		case '4':
-			return ip4_addr_string(buf, end, ptr, spec, fmt);
-		case 'S': {
-			const union {
-				struct sockaddr		raw;
-				struct sockaddr_in	v4;
-				struct sockaddr_in6	v6;
-			} *sa = ptr;
-
-			switch (sa->raw.sa_family) {
-			case AF_INET:
-				return ip4_addr_string_sa(buf, end, &sa->v4, spec, fmt);
-			case AF_INET6:
-				return ip6_addr_string_sa(buf, end, &sa->v6, spec, fmt);
-			default:
-				return string(buf, end, "(invalid address)", spec);
-			}}
-		}
-		break;
+		return ip_addr_string(buf, end, ptr, spec, fmt);
 	case 'E':
 		return escaped_string(buf, end, ptr, spec, fmt);
 	case 'U':
 		return uuid_string(buf, end, ptr, spec, fmt);
 	case 'V':
-		{
-			va_list va;
-
-			va_copy(va, *((struct va_format *)ptr)->va);
-			buf += vsnprintf(buf, end > buf ? end - buf : 0,
-					 ((struct va_format *)ptr)->fmt, va);
-			va_end(va);
-			return buf;
-		}
+		return va_format(buf, end, ptr, spec, fmt);
 	case 'K':
-		if (!kptr_restrict)
-			break;
 		return restricted_pointer(buf, end, ptr, spec);
 	case 'N':
 		return netdev_bits(buf, end, ptr, spec, fmt);
 	case 'a':
-		return address_val(buf, end, ptr, fmt);
+		return address_val(buf, end, ptr, spec, fmt);
 	case 'd':
 		return dentry_name(buf, end, ptr, spec, fmt);
 	case 't':
@@ -2064,13 +2174,9 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 #endif
 
 	case 'G':
-		return flags_string(buf, end, ptr, fmt);
+		return flags_string(buf, end, ptr, spec, fmt);
 	case 'O':
-		switch (fmt[1]) {
-		case 'F':
-			return device_node_string(buf, end, ptr, spec, fmt + 1);
-		}
-		break;
+		return kobject_string(buf, end, ptr, spec, fmt);
 	case 'x':
 		return pointer_string(buf, end, ptr, spec);
 	}
@@ -2685,11 +2791,13 @@ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args)
 
 		case FORMAT_TYPE_STR: {
 			const char *save_str = va_arg(args, char *);
+			const char *err_msg;
 			size_t len;
 
-			if ((unsigned long)save_str > (unsigned long)-PAGE_SIZE
-					|| (unsigned long)save_str < PAGE_SIZE)
-				save_str = "(null)";
+			err_msg = check_pointer_msg(save_str);
+			if (err_msg)
+				save_str = err_msg;
+
 			len = strlen(save_str) + 1;
 			if (str + len < end)
 				memcpy(str, save_str, len);
diff --git a/lib/zstd/bitstream.h b/lib/zstd/bitstream.h
index a826b99e1d63..3a49784d5c61 100644
--- a/lib/zstd/bitstream.h
+++ b/lib/zstd/bitstream.h
@@ -259,10 +259,15 @@ ZSTD_STATIC size_t BIT_initDStream(BIT_DStream_t *bitD, const void *srcBuffer, s
 		bitD->bitContainer = *(const BYTE *)(bitD->start);
 		switch (srcSize) {
 		case 7: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[6]) << (sizeof(bitD->bitContainer) * 8 - 16);
+			/* fall through */
 		case 6: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[5]) << (sizeof(bitD->bitContainer) * 8 - 24);
+			/* fall through */
 		case 5: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[4]) << (sizeof(bitD->bitContainer) * 8 - 32);
+			/* fall through */
 		case 4: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[3]) << 24;
+			/* fall through */
 		case 3: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[2]) << 16;
+			/* fall through */
 		case 2: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[1]) << 8;
 		default:;
 		}
diff --git a/lib/zstd/compress.c b/lib/zstd/compress.c
index f9166cf4f7a9..5e0b67003e55 100644
--- a/lib/zstd/compress.c
+++ b/lib/zstd/compress.c
@@ -3182,6 +3182,7 @@ static size_t ZSTD_compressStream_generic(ZSTD_CStream *zcs, void *dst, size_t *
 				zcs->outBuffFlushedSize = 0;
 				zcs->stage = zcss_flush; /* pass-through to flush stage */
 			}
+			/* fall through */
 
 		case zcss_flush: {
 			size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize;
diff --git a/lib/zstd/decompress.c b/lib/zstd/decompress.c
index b17846725ca0..269ee9a796c1 100644
--- a/lib/zstd/decompress.c
+++ b/lib/zstd/decompress.c
@@ -1768,6 +1768,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, c
 			return 0;
 		}
 		dctx->expected = 0; /* not necessary to copy more */
+		/* fall through */
 
 	case ZSTDds_decodeFrameHeader:
 		memcpy(dctx->headerBuffer + ZSTD_frameHeaderSize_prefix, src, dctx->expected);
@@ -2375,7 +2376,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB
 			}
 			zds->stage = zdss_read;
 		}
-		/* pass-through */
+		/* fall through */
 
 		case zdss_read: {
 			size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
@@ -2404,6 +2405,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB
 			zds->stage = zdss_load;
 			/* pass-through */
 		}
+		/* fall through */
 
 		case zdss_load: {
 			size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
@@ -2436,6 +2438,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB
 				/* pass-through */
 			}
 		}
+		/* fall through */
 
 		case zdss_flush: {
 			size_t const toFlushSize = zds->outEnd - zds->outStart;
diff --git a/lib/zstd/huf_compress.c b/lib/zstd/huf_compress.c
index 40055a7016e6..e727812d12aa 100644
--- a/lib/zstd/huf_compress.c
+++ b/lib/zstd/huf_compress.c
@@ -556,7 +556,9 @@ size_t HUF_compress1X_usingCTable(void *dst, size_t dstSize, const void *src, si
 	n = srcSize & ~3; /* join to mod 4 */
 	switch (srcSize & 3) {
 	case 3: HUF_encodeSymbol(&bitC, ip[n + 2], CTable); HUF_FLUSHBITS_2(&bitC);
+		/* fall through */
 	case 2: HUF_encodeSymbol(&bitC, ip[n + 1], CTable); HUF_FLUSHBITS_1(&bitC);
+		/* fall through */
 	case 1: HUF_encodeSymbol(&bitC, ip[n + 0], CTable); HUF_FLUSHBITS(&bitC);
 	case 0:
 	default:;