Merge branch 'next' into for-linus

Prepare input updates for 6.1 merge window.

46 files changed, 1541 insertions, 1180 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index eaaad4d85bf2..dc1ab2ed1dc6 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -118,6 +118,13 @@ config INDIRECT_IOMEM_FALLBACK
 	  mmio accesses when the IO memory address is not a registered
 	  emulated region.
 
+config TRACE_MMIO_ACCESS
+	bool "Register read/write tracing"
+	depends on TRACING && ARCH_HAVE_TRACE_MMIO_ACCESS
+	help
+	  Create tracepoints for MMIO read/write operations. These trace events
+	  can be used for logging all MMIO read/write operations.
+
 source "lib/crypto/Kconfig"
 
 config LIB_MEMNEQ
@@ -685,15 +692,6 @@ config STACKDEPOT_ALWAYS_INIT
 	bool
 	select STACKDEPOT
 
-config STACK_HASH_ORDER
-	int "stack depot hash size (12 => 4KB, 20 => 1024KB)"
-	range 12 20
-	default 20
-	depends on STACKDEPOT
-	help
-	 Select the hash size as a power of 2 for the stackdepot hash table.
-	 Choose a lower value to reduce the memory impact.
-
 config REF_TRACKER
 	bool
 	depends on STACKTRACE_SUPPORT
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 2e24db4bff19..072e4b289c13 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -498,7 +498,7 @@ config STACK_VALIDATION
 	  runtime stack traces are more reliable.
 
 	  For more information, see
-	  tools/objtool/Documentation/stack-validation.txt.
+	  tools/objtool/Documentation/objtool.txt.
 
 config NOINSTR_VALIDATION
 	bool
@@ -699,6 +699,14 @@ config DEBUG_OBJECTS_ENABLE_DEFAULT
 	help
 	  Debug objects boot parameter default value
 
+config SHRINKER_DEBUG
+	bool "Enable shrinker debugging support"
+	depends on DEBUG_FS
+	help
+	  Say Y to enable the shrinker debugfs interface which provides
+	  visibility into the kernel memory shrinkers subsystem.
+	  Disable it to avoid an extra memory footprint.
+
 config HAVE_DEBUG_KMEMLEAK
 	bool
 
@@ -1560,7 +1568,7 @@ config DEBUG_KOBJECT_RELEASE
 	help
 	  kobjects are reference counted objects.  This means that their
 	  last reference count put is not predictable, and the kobject can
-	  live on past the point at which a driver decides to drop it's
+	  live on past the point at which a driver decides to drop its
 	  initial reference to the kobject gained on allocation.  An
 	  example of this would be a struct device which has just been
 	  unregistered.
@@ -2021,6 +2029,15 @@ config LKDTM
 	Documentation on how to use the module can be found in
 	Documentation/fault-injection/provoke-crashes.rst
 
+config TEST_CPUMASK
+	tristate "cpumask tests" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	default KUNIT_ALL_TESTS
+	help
+	  Enable to turn on cpumask tests, running at boot or module load time.
+
+	  If unsure, say N.
+
 config TEST_LIST_SORT
 	tristate "Linked list sorting test" if !KUNIT_ALL_TESTS
 	depends on KUNIT
diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan
index a9f7eb047768..fd15230a703b 100644
--- a/lib/Kconfig.ubsan
+++ b/lib/Kconfig.ubsan
@@ -84,6 +84,9 @@ config UBSAN_SHIFT
 config UBSAN_DIV_ZERO
 	bool "Perform checking for integer divide-by-zero"
 	depends on $(cc-option,-fsanitize=integer-divide-by-zero)
+	# https://github.com/ClangBuiltLinux/linux/issues/1657
+	# https://github.com/llvm/llvm-project/issues/56289
+	depends on !CC_IS_CLANG
 	help
 	  This option enables -fsanitize=integer-divide-by-zero which checks
 	  for integer division by zero. This is effectively redundant with the
diff --git a/lib/Makefile b/lib/Makefile
index f99bf61f8bbc..c95212141928 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -29,15 +29,14 @@ endif
 
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o timerqueue.o xarray.o \
-	 idr.o extable.o sha1.o irq_regs.o argv_split.o \
+	 idr.o extable.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 \
 	 earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
-	 nmi_backtrace.o nodemask.o win_minmax.o memcat_p.o \
-	 buildid.o
+	 nmi_backtrace.o win_minmax.o memcat_p.o \
+	 buildid.o cpumask.o
 
 lib-$(CONFIG_PRINTK) += dump_stack.o
-lib-$(CONFIG_SMP) += cpumask.o
 
 lib-y	+= kobject.o klist.o
 obj-y	+= lockref.o
@@ -46,7 +45,7 @@ obj-y += bcd.o sort.o parser.o debug_locks.o random32.o \
 	 bust_spinlocks.o kasprintf.o bitmap.o scatterlist.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 \
+	 percpu-refcount.o rhashtable.o base64.o \
 	 once.o refcount.o usercopy.o errseq.o bucket_locks.o \
 	 generic-radix-tree.o
 obj-$(CONFIG_STRING_SELFTEST) += test_string.o
@@ -100,6 +99,7 @@ obj-$(CONFIG_TEST_HMM) += test_hmm.o
 obj-$(CONFIG_TEST_FREE_PAGES) += test_free_pages.o
 obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
 obj-$(CONFIG_TEST_REF_TRACKER) += test_ref_tracker.o
+obj-$(CONFIG_TEST_CPUMASK) += test_cpumask.o
 CFLAGS_test_fprobe.o += $(CC_FLAGS_FTRACE)
 obj-$(CONFIG_FPROBE_SANITY_TEST) += test_fprobe.o
 #
@@ -151,6 +151,8 @@ lib-y += logic_pio.o
 
 lib-$(CONFIG_INDIRECT_IOMEM) += logic_iomem.o
 
+obj-$(CONFIG_TRACE_MMIO_ACCESS) += trace_readwrite.o
+
 obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
 
 obj-$(CONFIG_BTREE) += btree.o
diff --git a/lib/base64.c b/lib/base64.c
new file mode 100644
index 000000000000..b736a7a431c5
--- /dev/null
+++ b/lib/base64.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * base64.c - RFC4648-compliant base64 encoding
+ *
+ * Copyright (c) 2020 Hannes Reinecke, SUSE
+ *
+ * Based on the base64url routines from fs/crypto/fname.c
+ * (which are using the URL-safe base64 encoding),
+ * modified to use the standard coding table from RFC4648 section 4.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/export.h>
+#include <linux/string.h>
+#include <linux/base64.h>
+
+static const char base64_table[65] =
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
+
+/**
+ * base64_encode() - base64-encode some binary data
+ * @src: the binary data to encode
+ * @srclen: the length of @src in bytes
+ * @dst: (output) the base64-encoded string.  Not NUL-terminated.
+ *
+ * Encodes data using base64 encoding, i.e. the "Base 64 Encoding" specified
+ * by RFC 4648, including the  '='-padding.
+ *
+ * Return: the length of the resulting base64-encoded string in bytes.
+ */
+int base64_encode(const u8 *src, int srclen, char *dst)
+{
+	u32 ac = 0;
+	int bits = 0;
+	int i;
+	char *cp = dst;
+
+	for (i = 0; i < srclen; i++) {
+		ac = (ac << 8) | src[i];
+		bits += 8;
+		do {
+			bits -= 6;
+			*cp++ = base64_table[(ac >> bits) & 0x3f];
+		} while (bits >= 6);
+	}
+	if (bits) {
+		*cp++ = base64_table[(ac << (6 - bits)) & 0x3f];
+		bits -= 6;
+	}
+	while (bits < 0) {
+		*cp++ = '=';
+		bits += 2;
+	}
+	return cp - dst;
+}
+EXPORT_SYMBOL_GPL(base64_encode);
+
+/**
+ * base64_decode() - base64-decode a string
+ * @src: the string to decode.  Doesn't need to be NUL-terminated.
+ * @srclen: the length of @src in bytes
+ * @dst: (output) the decoded binary data
+ *
+ * Decodes a string using base64 encoding, i.e. the "Base 64 Encoding"
+ * specified by RFC 4648, including the  '='-padding.
+ *
+ * This implementation hasn't been optimized for performance.
+ *
+ * Return: the length of the resulting decoded binary data in bytes,
+ *	   or -1 if the string isn't a valid base64 string.
+ */
+int base64_decode(const char *src, int srclen, u8 *dst)
+{
+	u32 ac = 0;
+	int bits = 0;
+	int i;
+	u8 *bp = dst;
+
+	for (i = 0; i < srclen; i++) {
+		const char *p = strchr(base64_table, src[i]);
+
+		if (src[i] == '=') {
+			ac = (ac << 6);
+			bits += 6;
+			if (bits >= 8)
+				bits -= 8;
+			continue;
+		}
+		if (p == NULL || src[i] == 0)
+			return -1;
+		ac = (ac << 6) | (p - base64_table);
+		bits += 6;
+		if (bits >= 8) {
+			bits -= 8;
+			*bp++ = (u8)(ac >> bits);
+		}
+	}
+	if (ac & ((1 << bits) - 1))
+		return -1;
+	return bp - dst;
+}
+EXPORT_SYMBOL_GPL(base64_decode);
diff --git a/lib/bitmap.c b/lib/bitmap.c
index b18e31ea6e66..488e6c3e5acc 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -237,7 +237,7 @@ void bitmap_cut(unsigned long *dst, const unsigned long *src,
 }
 EXPORT_SYMBOL(bitmap_cut);
 
-int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
 				const unsigned long *bitmap2, unsigned int bits)
 {
 	unsigned int k;
@@ -275,7 +275,7 @@ void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
 }
 EXPORT_SYMBOL(__bitmap_xor);
 
-int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
+bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
 				const unsigned long *bitmap2, unsigned int bits)
 {
 	unsigned int k;
@@ -333,10 +333,9 @@ bool __bitmap_subset(const unsigned long *bitmap1,
 }
 EXPORT_SYMBOL(__bitmap_subset);
 
-int __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
+unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
 {
-	unsigned int k, lim = bits/BITS_PER_LONG;
-	int w = 0;
+	unsigned int k, lim = bits/BITS_PER_LONG, w = 0;
 
 	for (k = 0; k < lim; k++)
 		w += hweight_long(bitmap[k]);
@@ -1564,7 +1563,7 @@ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits)
 
 	/* Clear tail bits in the last element of array beyond nbits. */
 	if (nbits % 64)
-		buf[-1] &= GENMASK_ULL(nbits % 64, 0);
+		buf[-1] &= GENMASK_ULL((nbits - 1) % 64, 0);
 }
 EXPORT_SYMBOL(bitmap_to_arr64);
 #endif
diff --git a/lib/btree.c b/lib/btree.c
index b4cf08a5c267..a82100c73b55 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -238,7 +238,7 @@ static int keyzero(struct btree_geo *geo, unsigned long *key)
 	return 1;
 }
 
-void *btree_lookup(struct btree_head *head, struct btree_geo *geo,
+static void *btree_lookup_node(struct btree_head *head, struct btree_geo *geo,
 		unsigned long *key)
 {
 	int i, height = head->height;
@@ -257,7 +257,16 @@ void *btree_lookup(struct btree_head *head, struct btree_geo *geo,
 		if (!node)
 			return NULL;
 	}
+	return node;
+}
 
+void *btree_lookup(struct btree_head *head, struct btree_geo *geo,
+		unsigned long *key)
+{
+	int i;
+	unsigned long *node;
+
+	node = btree_lookup_node(head, geo, key);
 	if (!node)
 		return NULL;
 
@@ -271,23 +280,10 @@ EXPORT_SYMBOL_GPL(btree_lookup);
 int btree_update(struct btree_head *head, struct btree_geo *geo,
 		 unsigned long *key, void *val)
 {
-	int i, height = head->height;
-	unsigned long *node = head->node;
-
-	if (height == 0)
-		return -ENOENT;
-
-	for ( ; height > 1; height--) {
-		for (i = 0; i < geo->no_pairs; i++)
-			if (keycmp(geo, node, i, key) <= 0)
-				break;
-		if (i == geo->no_pairs)
-			return -ENOENT;
-		node = bval(geo, node, i);
-		if (!node)
-			return -ENOENT;
-	}
+	int i;
+	unsigned long *node;
 
+	node = btree_lookup_node(head, geo, key);
 	if (!node)
 		return -ENOENT;
 
diff --git a/lib/cpumask.c b/lib/cpumask.c
index a971a82d2f43..8baeb37e23d3 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -8,61 +8,6 @@
 #include <linux/numa.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
- * @src2p: the second cpumask pointer
- *
- * Returns >= nr_cpu_ids if no further cpus set in both.
- */
-int cpumask_next_and(int n, const struct cpumask *src1p,
-		     const struct cpumask *src2p)
-{
-	/* -1 is a legal arg here. */
-	if (n != -1)
-		cpumask_check(n);
-	return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p),
-		nr_cpumask_bits, n + 1);
-}
-EXPORT_SYMBOL(cpumask_next_and);
-
-/**
- * cpumask_any_but - return a "random" in a cpumask, but not this one.
- * @mask: the cpumask to search
- * @cpu: the cpu to ignore.
- *
- * Often used to find any cpu but smp_processor_id() in a mask.
- * Returns >= nr_cpu_ids if no cpus set.
- */
-int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
-{
-	unsigned int i;
-
-	cpumask_check(cpu);
-	for_each_cpu(i, mask)
-		if (i != cpu)
-			break;
-	return i;
-}
-EXPORT_SYMBOL(cpumask_any_but);
-
-/**
  * cpumask_next_wrap - helper to implement for_each_cpu_wrap
  * @n: the cpu prior to the place to search
  * @mask: the cpumask pointer
@@ -74,9 +19,9 @@ EXPORT_SYMBOL(cpumask_any_but);
  * Note: the @wrap argument is required for the start condition when
  * we cannot assume @start is set in @mask.
  */
-int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
+unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
 {
-	int next;
+	unsigned int next;
 
 again:
 	next = cpumask_next(n, mask);
@@ -125,34 +70,6 @@ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
 }
 EXPORT_SYMBOL(alloc_cpumask_var_node);
 
-bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
-{
-	return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node);
-}
-EXPORT_SYMBOL(zalloc_cpumask_var_node);
-
-/**
- * alloc_cpumask_var - allocate a struct cpumask
- * @mask: pointer to cpumask_var_t where the cpumask is returned
- * @flags: GFP_ flags
- *
- * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
- * a nop returning a constant 1 (in <linux/cpumask.h>).
- *
- * See alloc_cpumask_var_node.
- */
-bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
-{
-	return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE);
-}
-EXPORT_SYMBOL(alloc_cpumask_var);
-
-bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
-{
-	return alloc_cpumask_var(mask, flags | __GFP_ZERO);
-}
-EXPORT_SYMBOL(zalloc_cpumask_var);
-
 /**
  * alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena.
  * @mask: pointer to cpumask_var_t where the cpumask is returned
@@ -192,6 +109,7 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
 }
 #endif
 
+#if NR_CPUS > 1
 /**
  * cpumask_local_spread - select the i'th cpu with local numa cpu's first
  * @i: index number
@@ -205,7 +123,7 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
  */
 unsigned int cpumask_local_spread(unsigned int i, int node)
 {
-	int cpu;
+	unsigned int cpu;
 
 	/* Wrap: we always want a cpu. */
 	i %= num_online_cpus();
@@ -243,10 +161,10 @@ static DEFINE_PER_CPU(int, distribute_cpu_mask_prev);
  *
  * Returns >= nr_cpu_ids if the intersection is empty.
  */
-int cpumask_any_and_distribute(const struct cpumask *src1p,
+unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
 			       const struct cpumask *src2p)
 {
-	int next, prev;
+	unsigned int next, prev;
 
 	/* NOTE: our first selection will skip 0. */
 	prev = __this_cpu_read(distribute_cpu_mask_prev);
@@ -262,9 +180,9 @@ int cpumask_any_and_distribute(const struct cpumask *src1p,
 }
 EXPORT_SYMBOL(cpumask_any_and_distribute);
 
-int cpumask_any_distribute(const struct cpumask *srcp)
+unsigned int cpumask_any_distribute(const struct cpumask *srcp)
 {
-	int next, prev;
+	unsigned int next, prev;
 
 	/* NOTE: our first selection will skip 0. */
 	prev = __this_cpu_read(distribute_cpu_mask_prev);
@@ -279,3 +197,4 @@ int cpumask_any_distribute(const struct cpumask *srcp)
 	return next;
 }
 EXPORT_SYMBOL(cpumask_any_distribute);
+#endif /* NR_CPUS */
diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig
index 2082af43d51f..9ff549f63540 100644
--- a/lib/crypto/Kconfig
+++ b/lib/crypto/Kconfig
@@ -121,6 +121,9 @@ config CRYPTO_LIB_CHACHA20POLY1305
 	select CRYPTO_LIB_POLY1305
 	select CRYPTO_ALGAPI
 
+config CRYPTO_LIB_SHA1
+	tristate
+
 config CRYPTO_LIB_SHA256
 	tristate
 
diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index 26be2bbe09c5..919cbb2c220d 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -34,6 +34,9 @@ libpoly1305-y					:= poly1305-donna32.o
 libpoly1305-$(CONFIG_ARCH_SUPPORTS_INT128)	:= poly1305-donna64.o
 libpoly1305-y					+= poly1305.o
 
+obj-$(CONFIG_CRYPTO_LIB_SHA1)			+= libsha1.o
+libsha1-y					:= sha1.o
+
 obj-$(CONFIG_CRYPTO_LIB_SHA256)			+= libsha256.o
 libsha256-y					:= sha256.o
 
diff --git a/lib/crypto/blake2s-selftest.c b/lib/crypto/blake2s-selftest.c
index 409e4b728770..7d77dea15587 100644
--- a/lib/crypto/blake2s-selftest.c
+++ b/lib/crypto/blake2s-selftest.c
@@ -4,6 +4,8 @@
  */
 
 #include <crypto/internal/blake2s.h>
+#include <linux/kernel.h>
+#include <linux/random.h>
 #include <linux/string.h>
 
 /*
@@ -587,5 +589,44 @@ bool __init blake2s_selftest(void)
 		}
 	}
 
+	for (i = 0; i < 32; ++i) {
+		enum { TEST_ALIGNMENT = 16 };
+		u8 unaligned_block[BLAKE2S_BLOCK_SIZE + TEST_ALIGNMENT - 1]
+					__aligned(TEST_ALIGNMENT);
+		u8 blocks[BLAKE2S_BLOCK_SIZE * 2];
+		struct blake2s_state state1, state2;
+
+		get_random_bytes(blocks, sizeof(blocks));
+		get_random_bytes(&state, sizeof(state));
+
+#if defined(CONFIG_CRYPTO_LIB_BLAKE2S_GENERIC) && \
+    defined(CONFIG_CRYPTO_ARCH_HAVE_LIB_BLAKE2S)
+		memcpy(&state1, &state, sizeof(state1));
+		memcpy(&state2, &state, sizeof(state2));
+		blake2s_compress(&state1, blocks, 2, BLAKE2S_BLOCK_SIZE);
+		blake2s_compress_generic(&state2, blocks, 2, BLAKE2S_BLOCK_SIZE);
+		if (memcmp(&state1, &state2, sizeof(state1))) {
+			pr_err("blake2s random compress self-test %d: FAIL\n",
+			       i + 1);
+			success = false;
+		}
+#endif
+
+		memcpy(&state1, &state, sizeof(state1));
+		blake2s_compress(&state1, blocks, 1, BLAKE2S_BLOCK_SIZE);
+		for (l = 1; l < TEST_ALIGNMENT; ++l) {
+			memcpy(unaligned_block + l, blocks,
+			       BLAKE2S_BLOCK_SIZE);
+			memcpy(&state2, &state, sizeof(state2));
+			blake2s_compress(&state2, unaligned_block + l, 1,
+					 BLAKE2S_BLOCK_SIZE);
+			if (memcmp(&state1, &state2, sizeof(state1))) {
+				pr_err("blake2s random compress align %d self-test %d: FAIL\n",
+				       l, i + 1);
+				success = false;
+			}
+		}
+	}
+
 	return success;
 }
diff --git a/lib/crypto/blake2s.c b/lib/crypto/blake2s.c
index c71c09621c09..98e688c6d891 100644
--- a/lib/crypto/blake2s.c
+++ b/lib/crypto/blake2s.c
@@ -16,16 +16,44 @@
 #include <linux/init.h>
 #include <linux/bug.h>
 
+static inline void blake2s_set_lastblock(struct blake2s_state *state)
+{
+	state->f[0] = -1;
+}
+
 void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen)
 {
-	__blake2s_update(state, in, inlen, false);
+	const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen;
+
+	if (unlikely(!inlen))
+		return;
+	if (inlen > fill) {
+		memcpy(state->buf + state->buflen, in, fill);
+		blake2s_compress(state, state->buf, 1, BLAKE2S_BLOCK_SIZE);
+		state->buflen = 0;
+		in += fill;
+		inlen -= fill;
+	}
+	if (inlen > BLAKE2S_BLOCK_SIZE) {
+		const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE);
+		blake2s_compress(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE);
+		in += BLAKE2S_BLOCK_SIZE * (nblocks - 1);
+		inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1);
+	}
+	memcpy(state->buf + state->buflen, in, inlen);
+	state->buflen += inlen;
 }
 EXPORT_SYMBOL(blake2s_update);
 
 void blake2s_final(struct blake2s_state *state, u8 *out)
 {
 	WARN_ON(IS_ENABLED(DEBUG) && !out);
-	__blake2s_final(state, out, false);
+	blake2s_set_lastblock(state);
+	memset(state->buf + state->buflen, 0,
+	       BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */
+	blake2s_compress(state, state->buf, 1, state->buflen);
+	cpu_to_le32_array(state->h, ARRAY_SIZE(state->h));
+	memcpy(out, state->h, state->outlen);
 	memzero_explicit(state, sizeof(*state));
 }
 EXPORT_SYMBOL(blake2s_final);
@@ -38,12 +66,7 @@ static int __init blake2s_mod_init(void)
 	return 0;
 }
 
-static void __exit blake2s_mod_exit(void)
-{
-}
-
 module_init(blake2s_mod_init);
-module_exit(blake2s_mod_exit);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("BLAKE2s hash function");
 MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
diff --git a/lib/sha1.c b/lib/crypto/sha1.c
index 0494766fc574..1aebe7be9401 100644
--- a/lib/sha1.c
+++ b/lib/crypto/sha1.c
@@ -8,6 +8,7 @@
 
 #include <linux/kernel.h>
 #include <linux/export.h>
+#include <linux/module.h>
 #include <linux/bitops.h>
 #include <linux/string.h>
 #include <crypto/sha1.h>
@@ -135,3 +136,5 @@ void sha1_init(__u32 *buf)
 	buf[4] = 0xc3d2e1f0;
 }
 EXPORT_SYMBOL(sha1_init);
+
+MODULE_LICENSE("GPL");
diff --git a/lib/devres.c b/lib/devres.c
index 14664bbb4875..55eb07e80cbb 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -29,7 +29,8 @@ static void __iomem *__devm_ioremap(struct device *dev, resource_size_t offset,
 {
 	void __iomem **ptr, *addr = NULL;
 
-	ptr = devres_alloc(devm_ioremap_release, sizeof(*ptr), GFP_KERNEL);
+	ptr = devres_alloc_node(devm_ioremap_release, sizeof(*ptr), GFP_KERNEL,
+				dev_to_node(dev));
 	if (!ptr)
 		return NULL;
 
@@ -292,7 +293,8 @@ void __iomem *devm_ioport_map(struct device *dev, unsigned long port,
 {
 	void __iomem **ptr, *addr;
 
-	ptr = devres_alloc(devm_ioport_map_release, sizeof(*ptr), GFP_KERNEL);
+	ptr = devres_alloc_node(devm_ioport_map_release, sizeof(*ptr), GFP_KERNEL,
+				dev_to_node(dev));
 	if (!ptr)
 		return NULL;
 
@@ -366,7 +368,8 @@ void __iomem * const *pcim_iomap_table(struct pci_dev *pdev)
 	if (dr)
 		return dr->table;
 
-	new_dr = devres_alloc(pcim_iomap_release, sizeof(*new_dr), GFP_KERNEL);
+	new_dr = devres_alloc_node(pcim_iomap_release, sizeof(*new_dr), GFP_KERNEL,
+				   dev_to_node(&pdev->dev));
 	if (!new_dr)
 		return NULL;
 	dr = devres_get(&pdev->dev, new_dr, NULL, NULL);
@@ -548,7 +551,8 @@ int devm_arch_phys_wc_add(struct device *dev, unsigned long base, unsigned long
 	int *mtrr;
 	int ret;