Merge drm-upstream/drm-next into drm-intel-next-queued

Need MST sideband message transaction to power up/down nodes.

Signed-off-by: Jani Nikula <jani.nikula@intel.com>

54 files changed, 14674 insertions, 165 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 6762529ad9e4..b1445b22a6de 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -192,6 +192,9 @@ config CRC8
 	  when they need to do cyclic redundancy check according CRC8
 	  algorithm. Module will be called crc8.
 
+config XXHASH
+	tristate
+
 config AUDIT_GENERIC
 	bool
 	depends on AUDIT && !AUDIT_ARCH
@@ -246,6 +249,14 @@ config LZ4HC_COMPRESS
 config LZ4_DECOMPRESS
 	tristate
 
+config ZSTD_COMPRESS
+	select XXHASH
+	tristate
+
+config ZSTD_DECOMPRESS
+	select XXHASH
+	tristate
+
 source "lib/xz/Kconfig"
 
 #
@@ -559,9 +570,6 @@ config ARCH_HAS_PMEM_API
 config ARCH_HAS_UACCESS_FLUSHCACHE
 	bool
 
-config ARCH_HAS_MMIO_FLUSH
-	bool
-
 config STACKDEPOT
 	bool
 	select STACKTRACE
@@ -575,4 +583,7 @@ config PARMAN
 config PRIME_NUMBERS
 	tristate
 
+config STRING_SELFTEST
+	bool "Test string functions"
+
 endmenu
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 98fe715522e8..2689b7c50c52 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -219,7 +219,8 @@ config FRAME_WARN
 	range 0 8192
 	default 0 if KASAN
 	default 2048 if GCC_PLUGIN_LATENT_ENTROPY
-	default 1024 if !64BIT
+	default 1280 if (!64BIT && PARISC)
+	default 1024 if (!64BIT && !PARISC)
 	default 2048 if 64BIT
 	help
 	  Tell gcc to warn at build time for stack frames larger than this.
@@ -374,6 +375,9 @@ config STACK_VALIDATION
 	  pointers (if CONFIG_FRAME_POINTER is enabled).  This helps ensure
 	  that runtime stack traces are more reliable.
 
+	  This is also a prerequisite for generation of ORC unwind data, which
+	  is needed for CONFIG_ORC_UNWINDER.
+
 	  For more information, see
 	  tools/objtool/Documentation/stack-validation.txt.
 
@@ -798,6 +802,13 @@ config HARDLOCKUP_DETECTOR_PERF
 	select SOFTLOCKUP_DETECTOR
 
 #
+# Enables a timestamp based low pass filter to compensate for perf based
+# hard lockup detection which runs too fast due to turbo modes.
+#
+config HARDLOCKUP_CHECK_TIMESTAMP
+	bool
+
+#
 # arch/ can define HAVE_HARDLOCKUP_DETECTOR_ARCH to provide their own hard
 # lockup detector rather than the perf based detector.
 #
@@ -1081,6 +1092,8 @@ config PROVE_LOCKING
 	select DEBUG_MUTEXES
 	select DEBUG_RT_MUTEXES if RT_MUTEXES
 	select DEBUG_LOCK_ALLOC
+	select LOCKDEP_CROSSRELEASE
+	select LOCKDEP_COMPLETIONS
 	select TRACE_IRQFLAGS
 	default n
 	help
@@ -1121,7 +1134,7 @@ config LOCKDEP
 	bool
 	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
 	select STACKTRACE
-	select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE && !ARC && !SCORE
+	select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE && !ARC && !SCORE && !X86
 	select KALLSYMS
 	select KALLSYMS_ALL
 
@@ -1150,6 +1163,22 @@ config LOCK_STAT
 	 CONFIG_LOCK_STAT defines "contended" and "acquired" lock events.
 	 (CONFIG_LOCKDEP defines "acquire" and "release" events.)
 
+config LOCKDEP_CROSSRELEASE
+	bool
+	help
+	 This makes lockdep work for crosslock which is a lock allowed to
+	 be released in a different context from the acquisition context.
+	 Normally a lock must be released in the context acquiring the lock.
+	 However, relexing this constraint helps synchronization primitives
+	 such as page locks or completions can use the lock correctness
+	 detector, lockdep.
+
+config LOCKDEP_COMPLETIONS
+	bool
+	help
+	 A deadlock caused by wait_for_completion() and complete() can be
+	 detected by lockdep using crossrelease feature.
+
 config DEBUG_LOCKDEP
 	bool "Lock dependency engine debugging"
 	depends on DEBUG_KERNEL && LOCKDEP
@@ -1540,7 +1569,7 @@ config FAULT_INJECTION_STACKTRACE_FILTER
 	depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
 	depends on !X86_64
 	select STACKTRACE
-	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC && !SCORE
+	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC && !SCORE && !X86
 	help
 	  Provide stacktrace filter for fault-injection capabilities
 
@@ -1549,7 +1578,7 @@ config LATENCYTOP
 	depends on DEBUG_KERNEL
 	depends on STACKTRACE_SUPPORT
 	depends on PROC_FS
-	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC
+	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC && !X86
 	select KALLSYMS
 	select KALLSYMS_ALL
 	select STACKTRACE
@@ -1902,6 +1931,17 @@ config TEST_KMOD
 
 	  If unsure, say N.
 
+config TEST_DEBUG_VIRTUAL
+	tristate "Test CONFIG_DEBUG_VIRTUAL feature"
+	depends on DEBUG_VIRTUAL
+	help
+	  Test the kernel's ability to detect incorrect calls to
+	  virt_to_phys() done against the non-linear part of the
+	  kernel's virtual address map.
+
+	  If unsure, say N.
+
+
 source "samples/Kconfig"
 
 source "lib/Kconfig.kgdb"
diff --git a/lib/Makefile b/lib/Makefile
index 40c18372b301..dafa79613fb4 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -62,6 +62,7 @@ obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o
 obj-$(CONFIG_TEST_UUID) += test_uuid.o
 obj-$(CONFIG_TEST_PARMAN) += test_parman.o
 obj-$(CONFIG_TEST_KMOD) += test_kmod.o
+obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += test_debug_virtual.o
 
 ifeq ($(CONFIG_DEBUG_KOBJECT),y)
 CFLAGS_kobject.o += -DDEBUG
@@ -102,6 +103,7 @@ obj-$(CONFIG_CRC4)	+= crc4.o
 obj-$(CONFIG_CRC7)	+= crc7.o
 obj-$(CONFIG_LIBCRC32C)	+= libcrc32c.o
 obj-$(CONFIG_CRC8)	+= crc8.o
+obj-$(CONFIG_XXHASH)	+= xxhash.o
 obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
 
 obj-$(CONFIG_842_COMPRESS) += 842/
@@ -115,6 +117,8 @@ obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
 obj-$(CONFIG_LZ4_COMPRESS) += lz4/
 obj-$(CONFIG_LZ4HC_COMPRESS) += lz4/
 obj-$(CONFIG_LZ4_DECOMPRESS) += lz4/
+obj-$(CONFIG_ZSTD_COMPRESS) += zstd/
+obj-$(CONFIG_ZSTD_DECOMPRESS) += zstd/
 obj-$(CONFIG_XZ_DEC) += xz/
 obj-$(CONFIG_RAID6_PQ) += raid6/
 
diff --git a/lib/assoc_array.c b/lib/assoc_array.c
index 59fd7c0b119c..155c55d8db5f 100644
--- a/lib/assoc_array.c
+++ b/lib/assoc_array.c
@@ -1,6 +1,6 @@
 /* Generic associative array implementation.
  *
- * See Documentation/assoc_array.txt for information.
+ * See Documentation/core-api/assoc_array.rst for information.
  *
  * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 9a532805364b..c82c61b66e16 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -513,7 +513,7 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
 		int nmaskbits)
 {
 	unsigned int a, b, old_a, old_b;
-	unsigned int group_size, used_size;
+	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;
@@ -599,6 +599,8 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
 			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)
@@ -608,17 +610,9 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
 		if (b >= nmaskbits)
 			return -ERANGE;
 		while (a <= b) {
-			if (in_partial_range) {
-				static int pos_in_group = 1;
-
-				if (pos_in_group <= used_size)
-					set_bit(a, maskp);
-
-				if (a == b || ++pos_in_group > group_size)
-					pos_in_group = 1;
-			} else
-				set_bit(a, maskp);
-			a++;
+			off = min(b - a + 1, used_size);
+			bitmap_set(maskp, a, off);
+			a += group_size;
 		}
 	} while (buflen && c == ',');
 	return 0;
diff --git a/lib/cmdline.c b/lib/cmdline.c
index 4c0888c4a68d..171c19b6888e 100644
--- a/lib/cmdline.c
+++ b/lib/cmdline.c
@@ -244,5 +244,4 @@ char *next_arg(char *args, char **param, char **val)
 
 	/* Chew up trailing spaces. */
 	return skip_spaces(next);
-	//return next;
 }
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 4731a0895760..8b1a1bd77539 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -6,6 +6,22 @@
 #include <linux/bootmem.h>
 
 /**
+ * cpumask_next - get the next cpu in a cpumask
+ * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @srcp: the cpumask pointer
+ *
+ * Returns >= nr_cpu_ids if no further cpus set.
+ */
+unsigned int cpumask_next(int n, const struct cpumask *srcp)
+{
+	/* -1 is a legal arg here. */
+	if (n != -1)
+		cpumask_check(n);
+	return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1);
+}
+EXPORT_SYMBOL(cpumask_next);
+
+/**
  * cpumask_next_and - get the next cpu in *src1p & *src2p
  * @n: the cpu prior to the place to search (ie. return will be > @n)
  * @src1p: the first cpumask pointer
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 17afb0430161..2f5349c6e81a 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -18,6 +18,7 @@
 #include <linux/debugfs.h>
 #include <linux/slab.h>
 #include <linux/hash.h>
+#include <linux/kmemleak.h>
 
 #define ODEBUG_HASH_BITS	14
 #define ODEBUG_HASH_SIZE	(1 << ODEBUG_HASH_BITS)
@@ -110,6 +111,7 @@ static void fill_pool(void)
 		if (!new)
 			return;
 
+		kmemleak_ignore(new);
 		raw_spin_lock_irqsave(&pool_lock, flags);
 		hlist_add_head(&new->node, &obj_pool);
 		debug_objects_allocated++;
@@ -1080,6 +1082,7 @@ static int __init debug_objects_replace_static_objects(void)
 		obj = kmem_cache_zalloc(obj_cache, GFP_KERNEL);
 		if (!obj)
 			goto free;
+		kmemleak_ignore(obj);
 		hlist_add_head(&obj->node, &objects);
 	}
 
diff --git a/lib/errseq.c b/lib/errseq.c
index 841fa24e6e00..7b900c2a277a 100644
--- a/lib/errseq.c
+++ b/lib/errseq.c
@@ -41,23 +41,20 @@
 #define ERRSEQ_CTR_INC		(1 << (ERRSEQ_SHIFT + 1))
 
 /**
- * __errseq_set - set a errseq_t for later reporting
+ * errseq_set - set a errseq_t for later reporting
  * @eseq: errseq_t field that should be set
- * @err: error to set
+ * @err: error to set (must be between -1 and -MAX_ERRNO)
  *
  * This function sets the error in *eseq, and increments the sequence counter
  * if the last sequence was sampled at some point in the past.
  *
  * Any error set will always overwrite an existing error.
  *
- * Most callers will want to use the errseq_set inline wrapper to efficiently
- * handle the common case where err is 0.
- *
- * We do return an errseq_t here, primarily for debugging purposes. The return
- * value should not be used as a previously sampled value in later calls as it
- * will not have the SEEN flag set.
+ * We do return the latest value here, primarily for debugging purposes. The
+ * return value should not be used as a previously sampled value in later calls
+ * as it will not have the SEEN flag set.
  */
-errseq_t __errseq_set(errseq_t *eseq, int err)
+errseq_t errseq_set(errseq_t *eseq, int err)
 {
 	errseq_t cur, old;
 
@@ -107,7 +104,7 @@ errseq_t __errseq_set(errseq_t *eseq, int err)
 	}
 	return cur;
 }
-EXPORT_SYMBOL(__errseq_set);
+EXPORT_SYMBOL(errseq_set);
 
 /**
  * errseq_sample - grab current errseq_t value
diff --git a/lib/hexdump.c b/lib/hexdump.c
index 992457b1284c..81b70ed37209 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -9,6 +9,7 @@
 
 #include <linux/types.h>
 #include <linux/ctype.h>
+#include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <asm/unaligned.h>
@@ -42,7 +43,7 @@ EXPORT_SYMBOL(hex_to_bin);
  * @src: ascii hexadecimal string
  * @count: result length
  *
- * Return 0 on success, -1 in case of bad input.
+ * Return 0 on success, -EINVAL in case of bad input.
  */
 int hex2bin(u8 *dst, const char *src, size_t count)
 {
@@ -51,7 +52,7 @@ int hex2bin(u8 *dst, const char *src, size_t count)
 		int lo = hex_to_bin(*src++);
 
 		if ((hi < 0) || (lo < 0))
-			return -1;
+			return -EINVAL;
 
 		*dst++ = (hi << 4) | lo;
 	}
diff --git a/lib/idr.c b/lib/idr.c
index b13682bb0a1c..f9adf4805fd7 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -7,45 +7,32 @@
 DEFINE_PER_CPU(struct ida_bitmap *, ida_bitmap);
 static DEFINE_SPINLOCK(simple_ida_lock);
 
-/**
- * idr_alloc - allocate an id
- * @idr: idr handle
- * @ptr: pointer to be associated with the new id
- * @start: the minimum id (inclusive)
- * @end: the maximum id (exclusive)
- * @gfp: memory allocation flags
- *
- * Allocates an unused ID in the range [start, end).  Returns -ENOSPC
- * if there are no unused IDs in that range.
- *
- * Note that @end is treated as max when <= 0.  This is to always allow
- * using @start + N as @end as long as N is inside integer range.
- *
- * Simultaneous modifications to the @idr are not allowed and should be
- * prevented by the user, usually with a lock.  idr_alloc() may be called
- * concurrently with read-only accesses to the @idr, such as idr_find() and
- * idr_for_each_entry().
- */
-int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp)
+int idr_alloc_cmn(struct idr *idr, void *ptr, unsigned long *index,
+		  unsigned long start, unsigned long end, gfp_t gfp,
+		  bool ext)
 {
-	void __rcu **slot;
 	struct radix_tree_iter iter;
+	void __rcu **slot;
 
-	if (WARN_ON_ONCE(start < 0))
-		return -EINVAL;
 	if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
 		return -EINVAL;
 
 	radix_tree_iter_init(&iter, start);
-	slot = idr_get_free(&idr->idr_rt, &iter, gfp, end);
+	if (ext)
+		slot = idr_get_free_ext(&idr->idr_rt, &iter, gfp, end);
+	else
+		slot = idr_get_free(&idr->idr_rt, &iter, gfp, end);
 	if (IS_ERR(slot))
 		return PTR_ERR(slot);
 
 	radix_tree_iter_replace(&idr->idr_rt, &iter, slot, ptr);
 	radix_tree_iter_tag_clear(&idr->idr_rt, &iter, IDR_FREE);
-	return iter.index;
+
+	if (index)
+		*index = iter.index;
+	return 0;
 }
-EXPORT_SYMBOL_GPL(idr_alloc);
+EXPORT_SYMBOL_GPL(idr_alloc_cmn);
 
 /**
  * idr_alloc_cyclic - allocate new idr entry in a cyclical fashion
@@ -134,6 +121,20 @@ void *idr_get_next(struct idr *idr, int *nextid)
 }
 EXPORT_SYMBOL(idr_get_next);
 
+void *idr_get_next_ext(struct idr *idr, unsigned long *nextid)
+{
+	struct radix_tree_iter iter;
+	void __rcu **slot;
+
+	slot = radix_tree_iter_find(&idr->idr_rt, &iter, *nextid);
+	if (!slot)
+		return NULL;
+
+	*nextid = iter.index;
+	return rcu_dereference_raw(*slot);
+}
+EXPORT_SYMBOL(idr_get_next_ext);
+
 /**
  * idr_replace - replace pointer for given id
  * @idr: idr handle
@@ -150,12 +151,19 @@ EXPORT_SYMBOL(idr_get_next);
  */
 void *idr_replace(struct idr *idr, void *ptr, int id)
 {
+	if (id < 0)
+		return ERR_PTR(-EINVAL);
+
+	return idr_replace_ext(idr, ptr, id);
+}
+EXPORT_SYMBOL(idr_replace);
+
+void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id)
+{
 	struct radix_tree_node *node;
 	void __rcu **slot = NULL;
 	void *entry;
 
-	if (WARN_ON_ONCE(id < 0))
-		return ERR_PTR(-EINVAL);
 	if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
 		return ERR_PTR(-EINVAL);
 
@@ -167,7 +175,7 @@ void *idr_replace(struct idr *idr, void *ptr, int id)
 
 	return entry;
 }
-EXPORT_SYMBOL(idr_replace);
+EXPORT_SYMBOL(idr_replace_ext);
 
 /**
  * DOC: IDA description
diff --git a/lib/interval_tree_test.c b/lib/interval_tree_test.c
index df495fe81421..0e343fd29570 100644
--- a/lib/interval_tree_test.c
+++ b/lib/interval_tree_test.c
@@ -19,14 +19,14 @@ __param(bool, search_all, false, "Searches will iterate all nodes in the tree");
 
 __param(uint, max_endpoint, ~0, "Largest value for the interval's endpoint");
 
-static struct rb_root root = RB_ROOT;
+static struct rb_root_cached root = RB_ROOT_CACHED;
 static struct interval_tree_node *nodes = NULL;
 static u32 *queries = NULL;
 
 static struct rnd_state rnd;
 
 static inline unsigned long
-search(struct rb_root *root, unsigned long start, unsigned long last)
+search(struct rb_root_cached *root, unsigned long start, unsigned long last)
 {
 	struct interval_tree_node *node;
 	unsigned long results = 0;
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 52c8dd6d8e82..1c1c06ddc20a 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -687,8 +687,10 @@ EXPORT_SYMBOL(_copy_from_iter_full_nocache);
 
 static inline bool page_copy_sane(struct page *page, size_t offset, size_t n)
 {
-	size_t v = n + offset;
-	if (likely(n <= v && v <= (PAGE_SIZE << compound_order(page))))
+	struct page *head = compound_head(page);
+	size_t v = n + offset + page_address(page) - page_address(head);
+
+	if (likely(n <= v && v <= (PAGE_SIZE << compound_order(head))))
 		return true;
 	WARN_ON(1);
 	return false;
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 719c155fce20..e590523ea476 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -52,6 +52,8 @@ static const char *kobject_actions[] = {
 	[KOBJ_MOVE] =		"move",
 	[KOBJ_ONLINE] =		"online",
 	[KOBJ_OFFLINE] =	"offline",
+	[KOBJ_BIND] =		"bind",
+	[KOBJ_UNBIND] =		"unbind",
 };
 
 static int kobject_action_type(const char *buf, size_t count,
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index 6f2b135dc5e8..cd0b5c964bd0 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -363,6 +363,103 @@ static void rsem_AA3(void)
 }
 
 /*
+ * read_lock(A)
+ * spin_lock(B)
+ *		spin_lock(B)
+ *		write_lock(A)
+ */
+static void rlock_ABBA1(void)
+{
+	RL(X1);
+	L(Y1);
+	U(Y1);
+	RU(X1);
+
+	L(Y1);
+	WL(X1);
+	WU(X1);
+	U(Y1); // should fail
+}
+
+static void rwsem_ABBA1(void)
+{
+	RSL(X1);
+	ML(Y1);
+	MU(Y1);
+	RSU(X1);
+
+	ML(Y1);
+	WSL(X1);
+	WSU(X1);
+	MU(Y1); // should fail
+}
+
+/*
+ * read_lock(A)
+ * spin_lock(B)
+ *		spin_lock(B)
+ *		read_lock(A)
+ */
+static void rlock_ABBA2(void)
+{
+	RL(X1);
+	L(Y1);
+	U(Y1);
+	RU(X1);
+
+	L(Y1);
+	RL(X1);
+	RU(X1);
+	U(Y1); // should NOT fail
+}
+
+static void rwsem_ABBA2(void)
+{
+	RSL(X1);
+	ML(Y1);
+	MU(Y1);
+	RSU(X1);
+
+	ML(Y1);
+	RSL(X1);
+	RSU(X1);
+	MU(Y1); // should fail
+}
+
+
+/*
+ * write_lock(A)
+ * spin_lock(B)
+ *		spin_lock(B)
+ *		write_lock(A)
+ */
+static void rlock_ABBA3(void)
+{
+	WL(X1);
+	L(Y1);
+	U(Y1);
+	WU(X1);
+
+	L(Y1);
+	WL(X1);
+	WU(X1);
+	U(Y1); // should fail
+}
+
+static void rwsem_ABBA3(void)
+{
+	WSL(X1);
+	ML(Y1);
+	MU(Y1);
+	WSU(X1);
+
+	ML(Y1);
+	WSL(X1);
+	WSU(X1);
+	MU(Y1); // should fail
+}
+
+/*
  * ABBA deadlock:
  */
 
@@ -1056,8 +1153,6 @@ static void dotest(void (*testcase_fn)(void), int expected, int lockclass_mask)
 	if (debug_locks != expected) {
 		unexpected_testcase_failures++;
 		pr_cont("FAILED|");
-
-		dump_stack();
 	} else {
 		testcase_successes++;
 		pr_cont("  ok  |");
@@ -1933,6 +2028,30 @@ void locking_selftest(void)
 	dotest(rsem_AA3, FAILURE, LOCKTYPE_RWSEM);
 	pr_cont("\n");
 
+	print_testname("mixed read-lock/lock-write ABBA");
+	pr_cont("             |");
+	dotest(rlock_ABBA1, FAILURE, LOCKTYPE_RWLOCK);
+	/*
+	 * Lockdep does indeed fail here, but there's nothing we can do about
+	 * that now.  Don't kill lockdep for it.
+	 */
+	unexpected_testcase_failures--;
+
+	pr_cont("             |");
+	dotest(rwsem_ABBA1, FAILURE, LOCKTYPE_RWSEM);
+
+	print_testname("mixed read-lock/lock-read ABBA");
+	pr_cont("             |");
+	dotest(rlock_ABBA2, SUCCESS, LOCKTYPE_RWLOCK);
+	pr_cont("             |");
+	dotest(rwsem_ABBA2, FAILURE, LOCKTYPE_RWSEM);
+
+	print_testname("mixed write-lock/lock-write ABBA");
+	pr_cont("             |");
+	dotest(rlock_ABBA3, FAILURE, LOCKTYPE_RWLOCK);
+	pr_cont("             |");
+	dotest(rwsem_ABBA3, FAILURE, LOCKTYPE_RWSEM);
+
 	printk("  --------------------------------------------------------------------------\n");
 
 	/*
diff --git a/lib/mpi/longlong.h b/lib/mpi/longlong.h
index 93336502af08..57fd45ab7af1 100644
--- a/lib/mpi/longlong.h
+++ b/lib/mpi/longlong.h
@@ -176,8 +176,8 @@ extern UDItype __udiv_qrnnd(UDItype *, UDItype, UDItype, UDItype);
 #define add_ssaaaa(sh, sl, ah, al, bh, bl) \
 	__asm__ ("adds %1, %4, %5\n" \
 		"adc  %0, %2, %3" \
-	: "=r" ((USItype)(sh)), \
-		"=&r" ((USItype)(sl)) \
+	: "=r" (sh), \
+		"=&r" (sl) \
 	: "%r" ((USItype)(ah)), \
 		"rI" ((USItype)(bh)), \
 		"%r" ((USItype)(al)), \
@@ -185,15 +185,15 @@ extern UDItype __udiv_qrnnd(UDItype *, UDItype, UDItype,