32 files changed, 913 insertions, 108 deletions
diff --git a/lib/Kconfig b/lib/Kconfig
index df3f3da95990..a5d6f23c4cab 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -342,6 +342,10 @@ config DECOMPRESS_LZ4
 	select LZ4_DECOMPRESS
 	tristate
 
+config DECOMPRESS_ZSTD
+	select ZSTD_DECOMPRESS
+	tristate
+
 #
 # Generic allocator support is selected if needed
 #
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 9ad9210d70a1..3e64a8a809f9 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1117,6 +1117,7 @@ config PROVE_LOCKING
 	select DEBUG_RWSEMS
 	select DEBUG_WW_MUTEX_SLOWPATH
 	select DEBUG_LOCK_ALLOC
+	select PREEMPT_COUNT if !ARCH_NO_PREEMPT
 	select TRACE_IRQFLAGS
 	default n
 	help
@@ -1325,11 +1326,17 @@ config WW_MUTEX_SELFTEST
 endmenu # lock debugging
 
 config TRACE_IRQFLAGS
+	depends on TRACE_IRQFLAGS_SUPPORT
 	bool
 	help
 	  Enables hooks to interrupt enabling and disabling for
 	  either tracing or lock debugging.
 
+config TRACE_IRQFLAGS_NMI
+	def_bool y
+	depends on TRACE_IRQFLAGS
+	depends on TRACE_IRQFLAGS_NMI_SUPPORT
+
 config STACKTRACE
 	bool "Stack backtrace support"
 	depends on STACKTRACE_SUPPORT
@@ -2307,6 +2314,17 @@ config TEST_HMM
 
 	  If unsure, say N.
 
+config TEST_FPU
+	tristate "Test floating point operations in kernel space"
+	depends on X86 && !KCOV_INSTRUMENT_ALL
+	help
+	  Enable this option to add /sys/kernel/debug/selftest_helpers/test_fpu
+	  which will trigger a sequence of floating point operations. This is used
+	  for self-testing floating point control register setting in
+	  kernel_fpu_begin().
+
+	  If unsure, say N.
+
 endif # RUNTIME_TESTING_MENU
 
 config MEMTEST
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index 81f5464ea9e1..34b84bcbd3d9 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -15,11 +15,15 @@ config CC_HAS_KASAN_GENERIC
 config CC_HAS_KASAN_SW_TAGS
 	def_bool $(cc-option, -fsanitize=kernel-hwaddress)
 
+config CC_HAS_WORKING_NOSANITIZE_ADDRESS
+	def_bool !CC_IS_GCC || GCC_VERSION >= 80300
+
 config KASAN
 	bool "KASAN: runtime memory debugger"
 	depends on (HAVE_ARCH_KASAN && CC_HAS_KASAN_GENERIC) || \
 		   (HAVE_ARCH_KASAN_SW_TAGS && CC_HAS_KASAN_SW_TAGS)
 	depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB)
+	depends on CC_HAS_WORKING_NOSANITIZE_ADDRESS
 	help
 	  Enables KASAN (KernelAddressSANitizer) - runtime memory debugger,
 	  designed to find out-of-bounds accesses and use-after-free bugs.
diff --git a/lib/Kconfig.kcsan b/lib/Kconfig.kcsan
index 5ee88e5119c2..3d282d51849b 100644
--- a/lib/Kconfig.kcsan
+++ b/lib/Kconfig.kcsan
@@ -4,7 +4,8 @@ config HAVE_ARCH_KCSAN
 	bool
 
 config HAVE_KCSAN_COMPILER
-	def_bool CC_IS_CLANG && $(cc-option,-fsanitize=thread -mllvm -tsan-distinguish-volatile=1)
+	def_bool (CC_IS_CLANG && $(cc-option,-fsanitize=thread -mllvm -tsan-distinguish-volatile=1)) || \
+		 (CC_IS_GCC && $(cc-option,-fsanitize=thread --param tsan-distinguish-volatile=1))
 	help
 	  For the list of compilers that support KCSAN, please see
 	  <file:Documentation/dev-tools/kcsan.rst>.
@@ -59,7 +60,28 @@ config KCSAN_SELFTEST
 	bool "Perform short selftests on boot"
 	default y
 	help
-	  Run KCSAN selftests on boot. On test failure, causes the kernel to panic.
+	  Run KCSAN selftests on boot. On test failure, causes the kernel to
+	  panic. Recommended to be enabled, ensuring critical functionality
+	  works as intended.
+
+config KCSAN_TEST
+	tristate "KCSAN test for integrated runtime behaviour"
+	depends on TRACEPOINTS && KUNIT
+	select TORTURE_TEST
+	help
+	  KCSAN test focusing on behaviour of the integrated runtime. Tests
+	  various race scenarios, and verifies the reports generated to
+	  console. Makes use of KUnit for test organization, and the Torture
+	  framework for test thread control.
+
+	  Each test case may run at least up to KCSAN_REPORT_ONCE_IN_MS
+	  milliseconds. Test run duration may be optimized by building the
+	  kernel and KCSAN test with KCSAN_REPORT_ONCE_IN_MS set to a lower
+	  than default value.
+
+	  Say Y here if you want the test to be built into the kernel and run
+	  during boot; say M if you want the test to build as a module; say N
+	  if you are unsure.
 
 config KCSAN_EARLY_ENABLE
 	bool "Early enable during boot"
diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb
index ffa7a76de086..256f2486f9bd 100644
--- a/lib/Kconfig.kgdb
+++ b/lib/Kconfig.kgdb
@@ -3,6 +3,11 @@
 config HAVE_ARCH_KGDB
 	bool
 
+# set if architecture has the its kgdb_arch_handle_qxfer_pkt
+# function to enable gdb stub to address XML packet sent from GDB.
+config HAVE_ARCH_KGDB_QXFER_PKT
+	bool
+
 menuconfig KGDB
 	bool "KGDB: kernel debugger"
 	depends on HAVE_ARCH_KGDB
diff --git a/lib/Makefile b/lib/Makefile
index b1c42c10073b..7d24dd73e34c 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -99,6 +99,30 @@ obj-$(CONFIG_TEST_MEMINIT) += test_meminit.o
 obj-$(CONFIG_TEST_LOCKUP) += test_lockup.o
 obj-$(CONFIG_TEST_HMM) += test_hmm.o
 
+#
+# CFLAGS for compiling floating point code inside the kernel. x86/Makefile turns
+# off the generation of FPU/SSE* instructions for kernel proper but FPU_FLAGS
+# get appended last to CFLAGS and thus override those previous compiler options.
+#
+FPU_CFLAGS := -mhard-float -msse -msse2
+ifdef CONFIG_CC_IS_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+# See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383
+#
+# The "-msse" in the first argument is there so that the
+# -mpreferred-stack-boundary=3 build error:
+#
+#  -mpreferred-stack-boundary=3 is not between 4 and 12
+#
+# can be triggered. Otherwise gcc doesn't complain.
+FPU_CFLAGS += $(call cc-option,-msse -mpreferred-stack-boundary=3,-mpreferred-stack-boundary=4)
+endif
+
+obj-$(CONFIG_TEST_FPU) += test_fpu.o
+CFLAGS_test_fpu.o += $(FPU_CFLAGS)
+
 obj-$(CONFIG_TEST_LIVEPATCH) += livepatch/
 
 obj-$(CONFIG_KUNIT) += kunit/
@@ -170,6 +194,7 @@ lib-$(CONFIG_DECOMPRESS_LZMA) += decompress_unlzma.o
 lib-$(CONFIG_DECOMPRESS_XZ) += decompress_unxz.o
 lib-$(CONFIG_DECOMPRESS_LZO) += decompress_unlzo.o
 lib-$(CONFIG_DECOMPRESS_LZ4) += decompress_unlz4.o
+lib-$(CONFIG_DECOMPRESS_ZSTD) += decompress_unzstd.o
 
 obj-$(CONFIG_TEXTSEARCH) += textsearch.o
 obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o
diff --git a/lib/cpumask.c b/lib/cpumask.c
index fb22fb266f93..85da6ab4fbb5 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -6,6 +6,7 @@
 #include <linux/export.h>
 #include <linux/memblock.h>
 #include <linux/numa.h>
+#include <linux/sched/isolation.h>
 
 /**
  * cpumask_next - get the next cpu in a cpumask
@@ -205,22 +206,27 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
  */
 unsigned int cpumask_local_spread(unsigned int i, int node)
 {
-	int cpu;
+	int cpu, hk_flags;
+	const struct cpumask *mask;
 
+	hk_flags = HK_FLAG_DOMAIN | HK_FLAG_MANAGED_IRQ;
+	mask = housekeeping_cpumask(hk_flags);
 	/* Wrap: we always want a cpu. */
-	i %= num_online_cpus();
+	i %= cpumask_weight(mask);
 
 	if (node == NUMA_NO_NODE) {
-		for_each_cpu(cpu, cpu_online_mask)
+		for_each_cpu(cpu, mask) {
 			if (i-- == 0)
 				return cpu;
+		}
 	} else {
 		/* NUMA first. */
-		for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask)
+		for_each_cpu_and(cpu, cpumask_of_node(node), mask) {
 			if (i-- == 0)
 				return cpu;
+		}
 
-		for_each_cpu(cpu, cpu_online_mask) {
+		for_each_cpu(cpu, mask) {
 			/* Skip NUMA nodes, done above. */
 			if (cpumask_test_cpu(cpu, cpumask_of_node(node)))
 				continue;
diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c
index 8cc01a603416..1ed2ed487097 100644
--- a/lib/crc-t10dif.c
+++ b/lib/crc-t10dif.c
@@ -17,64 +17,69 @@
 #include <linux/notifier.h>
 
 static struct crypto_shash __rcu *crct10dif_tfm;
-static struct static_key crct10dif_fallback __read_mostly;
+static DEFINE_STATIC_KEY_TRUE(crct10dif_fallback);
 static DEFINE_MUTEX(crc_t10dif_mutex);
+static struct work_struct crct10dif_rehash_work;
 
-static int crc_t10dif_rehash(struct notifier_block *self, unsigned long val, void *data)
+static int crc_t10dif_notify(struct notifier_block *self, unsigned long val, void *data)
 {
 	struct crypto_alg *alg = data;
-	struct crypto_shash *new, *old;
 
 	if (val != CRYPTO_MSG_ALG_LOADED ||
-	    static_key_false(&crct10dif_fallback) ||
-	    strncmp(alg->cra_name, CRC_T10DIF_STRING, strlen(CRC_T10DIF_STRING)))
-		return 0;
+	    strcmp(alg->cra_name, CRC_T10DIF_STRING))
+		return NOTIFY_DONE;
+
+	schedule_work(&crct10dif_rehash_work);
+	return NOTIFY_OK;
+}
+
+static void crc_t10dif_rehash(struct work_struct *work)
+{
+	struct crypto_shash *new, *old;
 
 	mutex_lock(&crc_t10dif_mutex);
 	old = rcu_dereference_protected(crct10dif_tfm,
 					lockdep_is_held(&crc_t10dif_mutex));
-	if (!old) {
-		mutex_unlock(&crc_t10dif_mutex);
-		return 0;
-	}
-	new = crypto_alloc_shash("crct10dif", 0, 0);
+	new = crypto_alloc_shash(CRC_T10DIF_STRING, 0, 0);
 	if (IS_ERR(new)) {
 		mutex_unlock(&crc_t10dif_mutex);
-		return 0;
+		return;
 	}
 	rcu_assign_pointer(crct10dif_tfm, new);
 	mutex_unlock(&crc_t10dif_mutex);
 
-	synchronize_rcu();
-	crypto_free_shash(old);
-	return 0;
+	if (old) {
+		synchronize_rcu();
+		crypto_free_shash(old);
+	} else {
+		static_branch_disable(&crct10dif_fallback);
+	}
 }
 
 static struct notifier_block crc_t10dif_nb = {
-	.notifier_call = crc_t10dif_rehash,
+	.notifier_call = crc_t10dif_notify,
 };
 
 __u16 crc_t10dif_update(__u16 crc, const unsigned char *buffer, size_t len)
 {
 	struct {
 		struct shash_desc shash;
-		char ctx[2];
+		__u16 crc;
 	} desc;
 	int err;
 
-	if (static_key_false(&crct10dif_fallback))
+	if (static_branch_unlikely(&crct10dif_fallback))
 		return crc_t10dif_generic(crc, buffer, len);
 
 	rcu_read_lock();
 	desc.shash.tfm = rcu_dereference(crct10dif_tfm);
-	*(__u16 *)desc.ctx = crc;
-
+	desc.crc = crc;
 	err = crypto_shash_update(&desc.shash, buffer, len);
 	rcu_read_unlock();
 
 	BUG_ON(err);
 
-	return *(__u16 *)desc.ctx;
+	return desc.crc;
 }
 EXPORT_SYMBOL(crc_t10dif_update);
 
@@ -86,19 +91,17 @@ EXPORT_SYMBOL(crc_t10dif);
 
 static int __init crc_t10dif_mod_init(void)
 {
+	INIT_WORK(&crct10dif_rehash_work, crc_t10dif_rehash);
 	crypto_register_notifier(&crc_t10dif_nb);
-	crct10dif_tfm = crypto_alloc_shash("crct10dif", 0, 0);
-	if (IS_ERR(crct10dif_tfm)) {
-		static_key_slow_inc(&crct10dif_fallback);
-		crct10dif_tfm = NULL;
-	}
+	crc_t10dif_rehash(&crct10dif_rehash_work);
 	return 0;
 }
 
 static void __exit crc_t10dif_mod_fini(void)
 {
 	crypto_unregister_notifier(&crc_t10dif_nb);
-	crypto_free_shash(crct10dif_tfm);
+	cancel_work_sync(&crct10dif_rehash_work);
+	crypto_free_shash(rcu_dereference_protected(crct10dif_tfm, 1));
 }
 
 module_init(crc_t10dif_mod_init);
@@ -106,15 +109,23 @@ module_exit(crc_t10dif_mod_fini);
 
 static int crc_t10dif_transform_show(char *buffer, const struct kernel_param *kp)
 {
-	if (static_key_false(&crct10dif_fallback))
+	struct crypto_shash *tfm;
+	int len;
+
+	if (static_branch_unlikely(&crct10dif_fallback))
 		return sprintf(buffer, "fallback\n");
 
-	return sprintf(buffer, "%s\n",
-		crypto_tfm_alg_driver_name(crypto_shash_tfm(crct10dif_tfm)));
+	rcu_read_lock();
+	tfm = rcu_dereference(crct10dif_tfm);
+	len = snprintf(buffer, PAGE_SIZE, "%s\n",
+		       crypto_shash_driver_name(tfm));
+	rcu_read_unlock();
+
+	return len;
 }
 
-module_param_call(transform, NULL, crc_t10dif_transform_show, NULL, 0644);
+module_param_call(transform, NULL, crc_t10dif_transform_show, NULL, 0444);
 
-MODULE_DESCRIPTION("T10 DIF CRC calculation");
+MODULE_DESCRIPTION("T10 DIF CRC calculation (library API)");
 MODULE_LICENSE("GPL");
 MODULE_SOFTDEP("pre: crct10dif");
diff --git a/lib/crc32.c b/lib/crc32.c
index 4a20455d1f61..35a03d03f973 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -24,7 +24,7 @@
  * Version 2.  See the file COPYING for more details.
  */
 
-/* see: Documentation/crc32.txt for a description of algorithms */
+/* see: Documentation/staging/crc32.rst for a description of algorithms */
 
 #include <linux/crc32.h>
 #include <linux/crc32poly.h>
diff --git a/lib/crypto/chacha20poly1305.c b/lib/crypto/chacha20poly1305.c
index ad0699ce702f..431e04280332 100644
--- a/lib/crypto/chacha20poly1305.c
+++ b/lib/crypto/chacha20poly1305.c
@@ -21,8 +21,6 @@
 
 #define CHACHA_KEY_WORDS	(CHACHA_KEY_SIZE / sizeof(u32))
 
-bool __init chacha20poly1305_selftest(void);
-
 static void chacha_load_key(u32 *k, const u8 *in)
 {
 	k[0] = get_unaligned_le32(in);
diff --git a/lib/crypto/sha256.c b/lib/crypto/sha256.c
index 2e621697c5c3..2321f6cb322f 100644
--- a/lib/crypto/sha256.c
+++ b/lib/crypto/sha256.c
@@ -280,4 +280,14 @@ void sha224_final(struct sha256_state *sctx, u8 *out)
 }
 EXPORT_SYMBOL(sha224_final);
 
+void sha256(const u8 *data, unsigned int len, u8 *out)
+{
+	struct sha256_state sctx;
+
+	sha256_init(&sctx);
+	sha256_update(&sctx, data, len);
+	sha256_final(&sctx, out);
+}
+EXPORT_SYMBOL(sha256);
+
 MODULE_LICENSE("GPL");
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 48054dbf1b51..fe4557955d97 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -1022,18 +1022,7 @@ static int debug_stats_show(struct seq_file *m, void *v)
 	seq_printf(m, "objs_freed    :%d\n", debug_objects_freed);
 	return 0;
 }
-
-static int debug_stats_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, debug_stats_show, NULL);
-}
-
-static const struct file_operations debug_stats_fops = {
-	.open		= debug_stats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(debug_stats);
 
 static int __init debug_objects_init_debugfs(void)
 {
diff --git a/lib/decompress.c b/lib/decompress.c
index 857ab1af1ef3..ab3fc90ffc64 100644
--- a/lib/decompress.c
+++ b/lib/decompress.c
@@ -13,6 +13,7 @@
 #include <linux/decompress/inflate.h>
 #include <linux/decompress/unlzo.h>
 #include <linux/decompress/unlz4.h>
+#include <linux/decompress/unzstd.h>
 
 #include <linux/types.h>
 #include <linux/string.h>
@@ -37,6 +38,9 @@
 #ifndef CONFIG_DECOMPRESS_LZ4
 # define unlz4 NULL
 #endif
+#ifndef CONFIG_DECOMPRESS_ZSTD
+# define unzstd NULL
+#endif
 
 struct compress_format {
 	unsigned char magic[2];
@@ -52,6 +56,7 @@ static const struct compress_format compressed_formats[] __initconst = {
 	{ {0xfd, 0x37}, "xz", unxz },
 	{ {0x89, 0x4c}, "lzo", unlzo },
 	{ {0x02, 0x21}, "lz4", unlz4 },
+	{ {0x28, 0xb5}, "zstd", unzstd },
 	{ {0, 0}, NULL, NULL }
 };
 
diff --git a/lib/decompress_unzstd.c b/lib/decompress_unzstd.c
new file mode 100644
index 000000000000..0ad2c15479ed
--- /dev/null
+++ b/lib/decompress_unzstd.c
@@ -0,0 +1,345 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Important notes about in-place decompression
+ *
+ * At least on x86, the kernel is decompressed in place: the compressed data
+ * is placed to the end of the output buffer, and the decompressor overwrites
+ * most of the compressed data. There must be enough safety margin to
+ * guarantee that the write position is always behind the read position.
+ *
+ * The safety margin for ZSTD with a 128 KB block size is calculated below.
+ * Note that the margin with ZSTD is bigger than with GZIP or XZ!
+ *
+ * The worst case for in-place decompression is that the beginning of
+ * the file is compressed extremely well, and the rest of the file is
+ * uncompressible. Thus, we must look for worst-case expansion when the
+ * compressor is encoding uncompressible data.
+ *
+ * The structure of the .zst file in case of a compresed kernel is as follows.
+ * Maximum sizes (as bytes) of the fields are in parenthesis.
+ *
+ *    Frame Header: (18)
+ *    Blocks: (N)
+ *    Checksum: (4)
+ *
+ * The frame header and checksum overhead is at most 22 bytes.
+ *
+ * ZSTD stores the data in blocks. Each block has a header whose size is
+ * a 3 bytes. After the block header, there is up to 128 KB of payload.
+ * The maximum uncompressed size of the payload is 128 KB. The minimum
+ * uncompressed size of the payload is never less than the payload size
+ * (excluding the block header).
+ *
+ * The assumption, that the uncompressed size of the payload is never
+ * smaller than the payload itself, is valid only when talking about
+ * the payload as a whole. It is possible that the payload has parts where
+ * the decompressor consumes more input than it produces output. Calculating
+ * the worst case for this would be tricky. Instead of trying to do that,
+ * let's simply make sure that the decompressor never overwrites any bytes
+ * of the payload which it is currently reading.
+ *
+ * Now we have enough information to calculate the safety margin. We need
+ *   - 22 bytes for the .zst file format headers;
+ *   - 3 bytes per every 128 KiB of uncompressed size (one block header per
+ *     block); and
+ *   - 128 KiB (biggest possible zstd block size) to make sure that the
+ *     decompressor never overwrites anything from the block it is currently
+ *     reading.
+ *
+ * We get the following formula:
+ *
+ *    safety_margin = 22 + uncompressed_size * 3 / 131072 + 131072
+ *                 <= 22 + (uncompressed_size >> 15) + 131072
+ */
+
+/*
+ * Preboot environments #include "path/to/decompress_unzstd.c".
+ * All of the source files we depend on must be #included.
+ * zstd's only source dependeny is xxhash, which has no source
+ * dependencies.
+ *
+ * When UNZSTD_PREBOOT is defined we declare __decompress(), which is
+ * used for kernel decompression, instead of unzstd().
+ *
+ * Define __DISABLE_EXPORTS in preboot environments to prevent symbols
+ * from xxhash and zstd from being exported by the EXPORT_SYMBOL macro.
+ */
+#ifdef STATIC
+# define UNZSTD_PREBOOT
+# include "xxhash.c"
+# include "zstd/entropy_common.c"
+# include "zstd/fse_decompress.c"
+# include "zstd/huf_decompress.c"
+# include "zstd/zstd_common.c"
+# include "zstd/decompress.c"
+#endif
+
+#include <linux/decompress/mm.h>
+#include <linux/kernel.h>
+#include <linux/zstd.h>
+
+/* 128MB is the maximum window size supported by zstd. */
+#define ZSTD_WINDOWSIZE_MAX	(1 << ZSTD_WINDOWLOG_MAX)
+/*
+ * Size of the input and output buffers in multi-call mode.
+ * Pick a larger size because it isn't used during kernel decompression,
+ * since that is single pass, and we have to allocate a large buffer for
+ * zstd's window anyway. The larger size speeds up initramfs decompression.
+ */
+#define ZSTD_IOBUF_SIZE		(1 << 17)
+
+static int INIT handle_zstd_error(size_t ret, void (*error)(char *x))
+{
+	const int err = ZSTD_getErrorCode(ret);
+
+	if (!ZSTD_isError(ret))
+		return 0;
+
+	switch (err) {
+	case ZSTD_error_memory_allocation:
+		error("ZSTD decompressor ran out of memory");
+		break;
+	case ZSTD_error_prefix_unknown:
+		error("Input is not in the ZSTD format (wrong magic bytes)");
+		break;
+	case ZSTD_error_dstSize_tooSmall:
+	case ZSTD_error_corruption_detected:
+	case ZSTD_error_checksum_wrong:
+		error("ZSTD-compressed data is corrupt");
+		break;
+	default:
+		error("ZSTD-compressed data is probably corrupt");
+		break;
+	}
+	return -1;
+}
+
+/*
+ * Handle the case where we have the entire input and output in one segment.
+ * We can allocate less memory (no circular buffer for the sliding window),
+ * and avoid some memcpy() calls.
+ */
+static int INIT decompress_single(const u8 *in_buf, long in_len, u8 *out_buf,
+				  long out_len, long *in_pos,
+				  void (*error)(char *x))
+{
+	const size_t wksp_size = ZSTD_DCtxWorkspaceBound();
+	void *wksp = large_malloc(wksp_size);
+	ZSTD_DCtx *dctx = ZSTD_initDCtx(wksp, wksp_size);
+	int err;
+	size_t ret;
+
+	if (dctx == NULL) {
+		error("Out of memory while allocating ZSTD_DCtx");
+		err = -1;
+		goto out;
+	}
+	/*
+	 * Find out how large the frame actually is, there may be junk at
+	 * the end of the frame that ZSTD_decompressDCtx() can't handle.
+	 */
+	ret = ZSTD_findFrameCompressedSize(in_buf, in_len);
+	err = handle_zstd_error(ret, error);
+	if (err)
+		goto out;
+	in_len = (long)ret;
+
+	ret = ZSTD_decompressDCtx(dctx, out_buf, out_len, in_buf, in_len);
+	err = handle_zstd_error(ret, error);
+	if (err)
+		goto out;
+
+	if (in_pos != NULL)
+		*in_pos = in_len;
+
+	err = 0;
+out:
+	if (wksp != NULL)
+		large_free(wksp);
+	return err;
+}
+
+static int INIT __unzstd(unsigned char *in_buf, long in_len,
+			 long (*fill)(void*, unsigned long),
+			 long (*flush)(void*, unsigned long),
+			 unsigned char *out_buf, long out_len,
+			 long *in_pos,
+			 void (*error)(char *x))
+{
+	ZSTD_inBuffer in;
+	ZSTD_outBuffer out;
+	ZSTD_frameParams params;
+	void *in_allocated = NULL;
+	void *out_allocated = NULL;
+	void *wksp = NULL;
+	size_t wksp_size;
+	ZSTD_DStream *dstream;
+	int err;
+	size_t ret;
+
+	if (out_len == 0)
+		out_len = LONG_MAX; /* no limit */
+
+	if (fill == NULL && flush == NULL)
+		/*
+		 * We can decompress faster and with less memory when we have a
+		 * single chunk.
+		 */
+		return decompress_single(in_buf, in_len, out_buf, out_len,
+					 in_pos, error);
+
+	/*
+	 * If in_buf is not provided, we must be using fill(), so allocate
+	 * a large enough buffer. If it is provided, it must be at least
+	 * ZSTD_IOBUF_SIZE large.
+	 */
+	if (in_buf == NULL) {
+		in_allocated = large_malloc(ZSTD_IOBUF_SIZE);
+		if (in_allocated == NULL) {
+			error("Out of memory while allocating input buffer");
+			err = -1;
+			goto out;
+		}
+		in_buf = in_allocated;
+		in_len = 0;
+	}
+	/* Read the first chunk, since we need to decode the frame header. */
+	if (fill != NULL)
+		in_len = fill(in_buf, ZSTD_IOBUF_SIZE);
+	if (in_len < 0) {
+		error("ZSTD-compressed data is truncated");
+		err = -1;
+		goto out;
+	}
+	/* Set the first non-empty input buffer. */
+	in.src = in_buf;
+	in.pos = 0;
+	in.size = in_len;
+	/* Allocate the output buffer if we are using flush(). */
+	if (flush != NULL) {
+		out_allocated = large_malloc(ZSTD_IOBUF_SIZE);
+		if (out_allocated == NULL) {
+			error("Out of memory while allocating output buffer");
+			err = -1;
+			goto out;
+		}
+		out_buf = out_allocated;
+		out_len = ZSTD_IOBUF_SIZE;
+	}
+	/* Set the output buffer. */
+	out.dst = out_buf;
+	out.pos = 0;
+	out.size = out_len;
+
+	/*
+	 * We need to know the window size to allocate the ZSTD_DStream.
+	 * Since we are streaming, we need to allocate a buffer for the sliding
+	 * window. The window size varies from 1 KB to ZSTD_WINDOWSIZE_MAX
+	 * (8 MB), so it is important to use the actual value so as not to
+	 * waste memory when it is smaller.
+	 */
+	ret = ZSTD_getFrameParams(&params, in.src, in.size);
+	err = handle_zstd_error(ret, error);
+	if (err)
+		goto out;
+	if (ret != 0) {
+		error("ZSTD-compressed data has an incomplete frame header");
+		err = -1;
+		goto out;
+	}
+	if (params.windowSize > ZSTD_WINDOWSIZE_MAX) {
+		error("ZSTD-compressed data has too large a window size");
+		err = -1;
+		goto out;
+	}
+
+	/*
+	 * Allocate the ZSTD_DStream now that we know how much memory is
+	 * required.
+	 */
+	wksp_size = ZSTD_DStreamWorkspaceBound(params.windowSize);
+	wksp = large_malloc(wksp_size);
+	dstream = ZSTD_initDStream(params.windowSize, wksp, wksp_size);
+	if (dstream == NULL) {
+		error("Out of memory while allocating ZSTD_DStream");
+		err = -1;
+		goto out;
+	}
+
+	/*
+	 * Decompression loop:
+	 * Read more data if necessary (error if no more data can be read).
+	 * Call the decompression function, which returns 0 when finished.
+	 * Flush any data produced if using flush().
+	 */
+	if (in_pos != NULL)
+		*in_pos = 0;
+	do {
+		/*
+		 * If we need to reload data, either we have fill() and can
+		 * try to get more data, or we don't and the input is truncated.
+		 */
+		if (in.pos == in.size) {
+			if (in_pos != NULL)
+				*in_pos += in.pos;
+			in_len = fill ? fill(in_buf, ZSTD_IOBUF_SIZE) : -1;
+			if (in_len < 0) {
+				error("ZSTD-compressed data is truncated");
+				err = -1;
+				goto out;
+			}
+			in.pos = 0;
+			in.size = in_len;
+		}
+		/* Returns zero when the frame is complete. */
+		ret = ZSTD_decompressStream(dstream, &out, &in);
+		err = handle_zstd_error(ret, error);
+		if (err)
+			goto out;
+		/* Flush all of the data produced if using flush(). */
+		if (flush != NULL && out.pos > 0) {
+			if (out.pos != flush(out.dst, out.pos)) {
+				error("Failed to flush()");
+				err = -1;
+				goto out;
+			}
+			out.pos = 0;
+		}
+	} while (ret != 0);
+
+	if (in_pos != NULL)
+		*in_pos += in.pos;
+
+	err = 0;
+out:
+	if (in_allocated != NULL)
+		large_free(in_allocated);
+	if (out_allocated != NULL)
+		large_free(out_allocated);
+	if (wksp != NULL)
+		large_free(wksp);
+	return err;
+}
+
+#ifndef UNZSTD_PREBOOT
+STATIC int INIT unzstd(unsigned char *buf, long len,
+		       long (*fill)(void*, unsigned long),
+		       long (*flush)(void*, unsigned long),
+		       unsigned char *out_buf,
+		       long *pos,
+		       void (*error)(char *x))
+{
+	return __unzstd(buf, len, fill, flush, out_buf, 0, pos, error);
+}
+#else
+STATIC int INIT __decompress(unsigned char *buf, long len,
+			     long (*fill)(void*, unsigned long),
+			     long (*flush)(void*, unsigned long),
+			     unsigned char *out_buf, long out_len,
+			     long *pos,
+			     void (*error)(char *x))
+{
+	return __unzstd(buf, len, fill, flush, out_buf, out_len, pos, error);
+}
+#endif
diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c
index 2717c7963acd..7892a40cf765 100644
--- a/lib/lzo/lzo1x_decompress_safe.c
+++ b/lib/lzo/lzo1x_decompress_safe.c
@@ -32,7 +32,7 @@
  * depending on the base count. Since the base count is taken from a u8
  * and a few bits, it is safe to assume that it will always be lower than
  * or equal to 2*255, thus we can always prevent any overflow by accepting
- * two less 255 steps. See Documentation/lzo.txt for more information.
+ * two less 255 steps. See Documentation/staging/lzo.rst for more information.
  */
 #define MAX_255_COUNT      ((((size_t)~0) / 255) - 2)
 
diff --git a/lib/math/div64.c b/lib/math/div64.c
index 368ca7fd0d82..3952a07130d8 100644
--- a/lib/math/div64.c
+++ b/lib/math/div64.c
@@ -190,3 +190,44 @@ u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder)
 	return __iter_div_u64_rem(dividend, divisor, remainder);
 }
 EXPORT_SYMBOL(iter_div_u64_rem);
+
+#ifndef mul_u64_u64_div_u64
+u64 mul_u64_u64_div_u64(u64 a, u64 b, u64 c)
+{
+	u64 res = 0, div, rem;
+	int shift;
+
+	/* can a * b overflow ? */
+	if (ilog2(a) + ilog2(b) > 62) {
+		/*
+		 * (b * a) / c is equal to
+		 *
+		 *      (b / c) * a +
+		 *      (b % c) * a / c
+		 *
+		 * if nothing overflows. Can the 1st multiplication
+		 * overflow? Yes, but we do not care: this can only
+		 * happen if the end result can't fit in u64 anyway.
+		 *
+		 * So the code below does
+		 *
+		 *      res = (b / c) * a;
+		 *      b = b % c;
+		 */
+		div = div64_u64_rem(b, c, &rem);
+		res = div * a;
+		b = rem;
+
+		shift = ilog2(a) + ilog2(b) - 62;
+		if (shift > 0) {
+			/* drop precision */
+			b >>= shift;
+			c >>= shift;
+			if (!c)
+				return res;
+		}
+	}
+
+	return res + div64_u64(a * b, c);
+}
+#endif
diff --git a/lib/mpi/Makefile b/lib/mpi/Makefile
index d5874a7f5ff9..43b8fce14079 100644
--- a/lib/mpi/Makefile
+++ b/lib/mpi/Makefile
@@ -16,6 +16,7 @@ mpi-y = \
 	mpicoder.o			\
 	mpi-bit.o			\
 	mpi-cmp.o			\
+	mpi-sub-ui.o			\
 	mpih-cmp.o			\
 	mpih-div.o			\
 	mpih-mul.o			\
diff --git a/lib/mpi/mpi-sub-ui.c b/lib/mpi/mpi-sub-ui.c
new file mode 100644
index 000000000000..b41b082b5f3e
--- /dev/null
+++ b/lib/mpi/mpi-sub-ui.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* mpi-sub-ui.c - Subtract an unsigned integer from an MPI.
+ *
+ * Copyright 1991, 1993, 1994, 1996, 1999-2002, 2004, 2012, 2013, 2015
+ * Free Software Foundation, Inc.
+ *
+ * This file was based on the GNU MP Library source file:
+ * https://gmplib.org/repo/gmp-6.2/file/510b83519d1c/mpz/aors_ui.h
+ *
+ * The GNU MP Library is free software; you can redistribute it and/or modify
+ * it under the terms of either:
+ *
+ *   * the GNU Lesser General Public License as published by the Free
+ *     Software Foundation; either version 3 of the License, or (at your
+ *     option) any later version.
+ *
+ * or
+ *
+ *   * the GNU General Public License as published by the Free Software
+ *     Foundation; either version 2 of the License, or (at your option) any
+ *     later version.
+ *
+ * or both in parallel, as here.
+ *
+ * The GNU MP Library is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+ * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * for more details.
+ *
+ * You should have received copies of the GNU General Public License and the
+ * GNU Lesser General Public License along with the GNU MP Library.  If not,
+ * see https://www.gnu.org/licenses/.
+ */
+
+#include "mpi-internal.h"
+
+int mpi_sub_ui(MPI w, MPI u, unsigned long vval)
+{
+	if (u->nlimbs == 0) {
+		if (mpi_resize(w, 1) < 0)
+			return -ENOMEM;
+		w->d[0] = vval;
+		w->nlimbs = (vval != 0);
+		w->sign = (vval != 0);
+		return 0;
+	}
+
+	/* If not space for W (and possible carry), increase space. */
+	if (mpi_resize(w, u->nlimbs + 1))
+		return -ENOMEM;
+
+	if (u->sign) {
+		mpi_limb_t cy;
+
+		cy = mpihelp_add_1(w->d, u->d, u->nlimbs, (mpi_limb_t) vval);
+		w->d[u->nlimbs] = cy;
+		w->nlimbs = u->nlimbs + cy;
+		w->sign = 1;
+	} else {
+		/* The signs are different.  Need exact comparison to determine
+		 * which operand to subtract from which.
+		 */
+		if (u->nlimbs == 1 && u->d[0] < vval) {
+			w->d[0] = vval - u->d[0];
+			w->nlimbs = 1;
+			w->sign = 1;
+		} else {
+			mpihelp_sub_1(w->d, u->d, u->nlimbs, (mpi_limb_t) vval);
+			/* Size can decrease with at most one limb. */
+			w->nlimbs = (u->nlimbs - (w->d[u->nlimbs - 1] == 0));
+			w->sign = 0;
+		}
+	}
+
+	mpi_normalize(w);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mpi_sub_ui);
diff --git a/lib/packing.c b/lib/packing.c
index 50d1e9f2f5a7..6ed72dccfdb5 100644
--- a/lib/packing.c
+++ b/lib/packing.c
@@ -73,6 +73,7 @@ static void adjust_for_msb_right_quirk(u64 *to_write, int *box_start_bit,
  * @endbit: The index (in logical notation, compensated for quirks) where
  *	    the packed value ends within pbuf. Must be smaller than, or equal
  *	    to, startbit.
+ * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf.
  * @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
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 34e406fe561f..8e4a3a4397f2 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1029,7 +1029,7 @@ void *radix_tree_tag_clear(struct radix_tree_root *root,
 {
 	struct radix_tree_node *node, *parent;
 	unsigned long maxindex;
-	int uninitialized_var(offset);
+	int offset;
 
 	radix_tree_load_root(root, &node, &maxindex);
 	if (index > maxindex)
diff --git a/lib/random32.c b/lib/random32.c
index 763b920a6206..3d749abb9e80 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -48,7 +48,7 @@ static inline void prandom_state_selftest(void)
 }
 #endif
 
-static DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy;
+DEFINE_PER_CPU(struct rnd_state, net_rand_state);
 
 /**
  *	prandom_u32_state - seeded pseudo-random number generator.
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 9f6890aedd1a..c949c1e3b87c 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -31,7 +31,7 @@
 
 union nested_table {
 	union nested_table __rcu *table;
-	struct rhash_lock_head *bucket;
+	struct rhash_lock_head __rcu *bucket;
 };
 
 static u32 head_hashfn(struct rhashtable *ht,
@@ -222,7 +222,7 @@ static struct bucket_table *rhashtable_last_table(struct rhashtable *ht,
 }
 
 static int rhashtable_rehash_one(struct rhashtable *ht,
-				 struct rhash_lock_head **bkt,
+				 struct rhash_lock_head __rcu **bkt,
 				 unsigned int old_hash)
 {
 	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
@@ -275,7 +275,7 @@ static int rhashtable_rehash_chain(struct rhashtable *ht,
 				    unsigned int old_hash)
 {
 	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
-	struct rhash_lock_head **bkt = rht_bucket_var(old_tbl, old_hash);
+	struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash);
 	int err;
 
 	if (!bkt)
@@ -485,7 +485,7 @@ fail:
 }
 
 static void *rhashtable_lookup_one(struct rhashtable *ht,
-				   struct rhash_lock_head **bkt,
+				   struct rhash_lock_head __rcu **bkt,
 				   struct bucket_table *tbl, unsigned int hash,
 				   const void *key, struct rhash_head *obj)
 {
@@ -535,12 +535,10 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 	return ERR_PTR(-ENOENT);
 }
 
-static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
-						  struct rhash_lock_head **bkt,
-						  struct bucket_table *tbl,
-						  unsigned int hash,
-						  struct rhash_head *obj,
-						  void *data)
+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 bucket_table *new_tbl;
 	struct rhash_head *head;
@@ -591,7 +589,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
 {
 	struct bucket_table *new_tbl;
 	struct bucket_table *tbl;
-	struct rhash_lock_head **bkt;
+	struct rhash_lock_head __rcu **bkt;
 	unsigned int hash;
 	void *data;
 
@@ -1173,8 +1171,8 @@ void rhashtable_destroy(struct rhashtable *ht)
 }
 EXPORT_SYMBOL_GPL(rhashtable_destroy);
 
-struct rhash_lock_head **__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 *));
 	unsigned int index = hash & ((1 << tbl->nest) - 1);
@@ -1202,10 +1200,10 @@ struct rhash_lock_head **__rht_bucket_nested(const struct bucket_table *tbl,
 }
 EXPORT_SYMBOL_GPL(__rht_bucket_nested);
 
-struct rhash_lock_head **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)
 {
-	static struct rhash_lock_head *rhnull;
+	static struct rhash_lock_head __rcu *rhnull;
 
 	if (!rhnull)
 		INIT_RHT_NULLS_HEAD(rhnull);
@@ -1213,9 +1211,8 @@ struct rhash_lock_head **rht_bucket_nested(const struct bucket_table *tbl,
 }
 EXPORT_SYMBOL_GPL(rht_bucket_nested);
 
-struct rhash_lock_head **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/sbitmap.c b/lib/sbitmap.c
index af88d1346dd7..267aa7709416 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -292,8 +292,11 @@ void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m)
 
 	for (i = 0; i < sb->map_nr; i++) {
 		unsigned long word = READ_ONCE(sb->map[i].word);
+		unsigned long cleared = READ_ONCE(sb->map[i].cleared);
 		unsigned int word_bits = READ_ONCE(sb->map[i].depth);
 
+		word &= ~cleared;
+
 		while (word_bits > 0) {
 			unsigned int bits = min(8 - byte_bits, word_bits);
 
diff --git a/lib/test-string_helpers.c b/lib/test-string_helpers.c
index 25b5cbfb7615..10360d4ea273 100644
--- a/lib/test-string_helpers.c
+++ b/lib/test-string_helpers.c
@@ -238,6 +238,28 @@ static const struct test_string_2 escape1[] __initconst = {{
 	/* terminator */
 }};
 
+static const struct test_string strings_upper[] __initconst = {
+	{
+		.in = "abcdefgh1234567890test",
+		.out = "ABCDEFGH1234567890TEST",
+	},
+	{
+		.in = "abCdeFgH1234567890TesT",
+		.out = "ABCDEFGH1234567890TEST",
+	},
+};
+
+static const struct test_string strings_lower[] __initconst = {
+	{
+		.in = "ABCDEFGH1234567890TEST",
+		.out = "abcdefgh1234567890test",
+	},
+	{
+		.in = "abCdeFgH1234567890TesT",
+		.out = "abcdefgh1234567890test",
+	},
+};
+
 static __init const char *test_string_find_match(const struct test_string_2 *s2,
 						 unsigned int flags)
 {
@@ -390,6 +412,48 @@ static __init void test_string_get_size(void)
 	test_string_get_size_one(4096, U64_MAX, "75.6 ZB", "64.0 ZiB");
 }
 
+static void __init test_string_upper_lower(void)
+{
+	char *dst;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(strings_upper); i++) {
+		const char *s = strings_upper[i].in;
+		int len = strlen(strings_upper[i].in) + 1;
+
+		dst = kmalloc(len, GFP_KERNEL);
+		if (!dst)
+			return;
+
+		string_upper(dst, s);
+		if (memcmp(dst, strings_upper[i].out, len)) {
+			pr_warn("Test 'string_upper' failed : expected %s, got %s!\n",
+				strings_upper[i].out, dst);
+			kfree(dst);
+			return;
+		}
+		kfree(dst);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(strings_lower); i++) {
+		const char *s = strings_lower[i].in;
+		int len = strlen(strings_lower[i].in) + 1;
+
+		dst = kmalloc(len, GFP_KERNEL);
+		if (!dst)
+			return;
+
+		string_lower(dst, s);
+		if (memcmp(dst, strings_lower[i].out, len)) {
+			pr_warn("Test 'string_lower failed : : expected %s, got %s!\n",
+				strings_lower[i].out, dst);
+			kfree(dst);
+			return;
+		}
+		kfree(dst);
+	}
+}
+
 static int __init test_string_helpers_init(void)
 {
 	unsigned int i;
@@ -411,6 +475,9 @@ static int __init test_string_helpers_init(void)
 	/* Test string_get_size() */
 	test_string_get_size();
 
+	/* Test string upper(), string_lower() */
+	test_string_upper_lower();
+
 	return -EINVAL;
 }
 module_init(test_string_helpers_init);
diff --git a/lib/test_fpu.c b/lib/test_fpu.c
new file mode 100644
index 000000000000..c33764aa3eb8
--- /dev/null
+++ b/lib/test_fpu.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Test cases for using floating point operations inside a kernel module.
+ *
+ * This tests kernel_fpu_begin() and kernel_fpu_end() functions, especially
+ * when userland has modified the floating point control registers. The kernel
+ * state might depend on the state set by the userland thread that was active
+ * before a syscall.
+ *
+ * To facilitate the test, this module registers file
+ * /sys/kernel/debug/selftest_helpers/test_fpu, which when read causes a
+ * sequence of floating point operations. If the operations fail, either the
+ * read returns error status or the kernel crashes.
+ * If the operations succeed, the read returns "1\n".
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/debugfs.h>
+#include <asm/fpu/api.h>
+
+static int test_fpu(void)
+{
+	/*
+	 * This sequence of operations tests that rounding mode is
+	 * to nearest and that denormal numbers are supported.
+	 * Volatile variables are used to avoid compiler optimizing
+	 * the calculations away.
+	 */
+	volatile double a, b, c, d, e, f, g;
+
+	a = 4.0;
+	b = 1e-15;
+	c = 1e-310;
+
+	/* Sets precision flag */
+	d = a + b;
+
+	/* Result depends on rounding mode */
+	e = a + b / 2;
+
+	/* Denormal and very large values */
+	f = b / c;
+
+	/* Depends on denormal support */
+	g = a + c * f;
+
+	if (d > a && e > a && g > a)
+		return 0;
+	else
+		return -EINVAL;
+}
+
+static int test_fpu_get(void *data, u64 *val)
+{
+	int status = -EINVAL;
+
+	kernel_fpu_begin();
+	status = test_fpu();
+	kernel_fpu_end();
+
+	*val = 1;
+	return status;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(test_fpu_fops, test_fpu_get, NULL, "%lld\n");
+static struct dentry *selftest_dir;
+
+static int __init test_fpu_init(void)
+{
+	selftest_dir = debugfs_create_dir("selftest_helpers", NULL);
+	if (!selftest_dir)
+		return -ENOMEM;
+
+	debugfs_create_file("test_fpu", 0444, selftest_dir, NULL,
+			    &test_fpu_fops);
+
+	return 0;
+}
+
+static void __exit test_fpu_exit(void)
+{
+	debugfs_remove(selftest_dir);
+}
+
+module_init(test_fpu_init);
+module_exit(test_fpu_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 28528285942c..a2a82262b97b 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -520,8 +520,7 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
 err_free:
 	kfree(devmem);
 err_release:
-	release_mem_region(devmem->pagemap.res.start,
-			   resource_size(&devmem->pagemap.res));
+	release_mem_region(res->start, resource_size(res));
 err:
 	mutex_unlock(&mdevice->devmem_lock);
 	return false;
diff --git a/lib/test_lockup.c b/lib/test_lockup.c
index bd7c7ff39f6b..ff26f36d729f 100644
--- a/lib/test_lockup.c
+++ b/lib/test_lockup.c
@@ -168,7 +168,7 @@ static int master_cpu;
 
 static void test_lock(bool master, bool verbose)
 {
-	u64 uninitialized_var(wait_start);
+	u64 wait_start;
 
 	if (measure_lock_wait)
 		wait_start = local_clock();
diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c
index ddc9685702b1..5cf2fe9aab9e 100644
--- a/lib/test_vmalloc.c
+++ b/lib/test_vmalloc.c
@@ -15,6 +15,8 @@
 #include <linux/delay.h>
 #include <linux/rwsem.h>
 #include <linux/mm.h>
+#include <linux/rcupdate.h>
+#include <linux/slab.h>
 
 #define __param(type, name, init, msg)		\
 	static type name = init;				\
@@ -35,14 +37,18 @@ __param(int, test_loop_count, 1000000,
 
 __param(int, run_test_mask, INT_MAX,
 	"Set tests specified in the mask.\n\n"
-		"\t\tid: 1,   name: fix_size_alloc_test\n"
-		"\t\tid: 2,   name: full_fit_alloc_test\n"
-		"\t\tid: 4,   name: long_busy_list_alloc_test\n"
-		"\t\tid: 8,   name: random_size_alloc_test\n"
-		"\t\tid: 16,  name: fix_align_alloc_test\n"
-		"\t\tid: 32,  name: random_size_align_alloc_test\n"
-		"\t\tid: 64,  name: align_shift_alloc_test\n"
-		"\t\tid: 128, name: pcpu_alloc_test\n"
+		"\t\tid: 1,    name: fix_size_alloc_test\n"
+		"\t\tid: 2,    name: full_fit_alloc_test\n"
+		"\t\tid: 4,    name: long_busy_list_alloc_test\n"
+		"\t\tid: 8,    name: random_size_alloc_test\n"
+		"\t\tid: 16,   name: fix_align_alloc_test\n"
+		"\t\tid: 32,   name: random_size_align_alloc_test\n"
+		"\t\tid: 64,   name: align_shift_alloc_test\n"
+		"\t\tid: 128,  name: pcpu_alloc_test\n"
+		"\t\tid: 256,  name: kvfree_rcu_1_arg_vmalloc_test\n"
+		"\t\tid: 512,  name: kvfree_rcu_2_arg_vmalloc_test\n"
+		"\t\tid: 1024, name: kvfree_rcu_1_arg_slab_test\n"
+		"\t\tid: 2048, name: kvfree_rcu_2_arg_slab_test\n"
 		/* Add a new test case description here. */
 );
 
@@ -316,6 +322,83 @@ pcpu_alloc_test(void)
 	return rv;
 }
 
+struct test_kvfree_rcu {
+	struct rcu_head rcu;
+	unsigned char array[20];
+};
+
+static int
+kvfree_rcu_1_arg_vmalloc_test(void)
+{
+	struct test_kvfree_rcu *p;
+	int i;
+
+	for (i = 0; i < test_loop_count; i++) {
+		p = vmalloc(1 * PAGE_SIZE);
+		if (!p)
+			return -1;
+
+		p->array[0] = 'a';
+		kvfree_rcu(p);
+	}
+
+	return 0;
+}
+
+static int
+kvfree_rcu_2_arg_vmalloc_test(void)
+{
+	struct test_kvfree_rcu *p;
+	int i;
+
+	for (i = 0; i < test_loop_count; i++) {
+		p = vmalloc(1 * PAGE_SIZE);
+		if (!p)
+			return -1;
+
+		p->array[0] = 'a';
+		kvfree_rcu(p, rcu);
+	}
+
+	return 0;
+}
+
+static int
+kvfree_rcu_1_arg_slab_test(void)
+{
+	struct test_kvfree_rcu *p;
+	int i;
+
+	for (i = 0; i < test_loop_count; i++) {
+		p = kmalloc(sizeof(*p), GFP_KERNEL);
+		if (!p)
+			return -1;
+
+		p->array[0] = 'a';
+		kvfree_rcu(p);
+	}
+
+	return 0;
+}
+
+static int
+kvfree_rcu_2_arg_slab_test(void)
+{
+	struct test_kvfree_rcu *p;
+	int i;
+
+	for (i = 0; i < test_loop_count; i++) {
+		p = kmalloc(sizeof(*p), GFP_KERNEL);
+		if (!p)
+			return -1;
+
+		p->array[0] = 'a';
+		kvfree_rcu(p, rcu);
+	}
+
+	return 0;
+}
+
 struct test_case_desc {
 	const char *test_name;
 	int (*test_func)(void);
@@ -330,6 +413,10 @@ static struct test_case_desc test_case_array[] = {
 	{ "random_size_align_alloc_test", random_size_align_alloc_test },
 	{ "align_shift_alloc_test", align_shift_alloc_test },
 	{ "pcpu_alloc_test", pcpu_alloc_test },
+	{ "kvfree_rcu_1_arg_vmalloc_test", kvfree_rcu_1_arg_vmalloc_test },
+	{ "kvfree_rcu_2_arg_vmalloc_test", kvfree_rcu_2_arg_vmalloc_test },
+	{ "kvfree_rcu_1_arg_slab_test", kvfree_rcu_1_arg_slab_test },
+	{ "kvfree_rcu_2_arg_slab_test", kvfree_rcu_2_arg_slab_test },
 	/* Add a new test case here. */
 };
 
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 259e55895933..c155769559ab 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -381,6 +381,9 @@ int num_to_str(char *buf, int size, unsigned long long num, unsigned int width)
 #define SMALL	32		/* use lowercase in hex (must be 32 == 0x20) */
 #define SPECIAL	64		/* prefix hex with "0x", octal with "0" */
 
+static_assert(ZEROPAD == ('0' - ' '));
+static_assert(SMALL == ' ');
+
 enum format_type {
 	FORMAT_TYPE_NONE, /* Just a string part */
 	FORMAT_TYPE_WIDTH,
@@ -507,7 +510,7 @@ char *number(char *buf, char *end, unsigned long long num,
 	/* zero or space padding */
 	if (!(spec.flags & LEFT)) {
 		char c = ' ' + (spec.flags & ZEROPAD);
-		BUILD_BUG_ON(' ' + ZEROPAD != '0');
+
 		while (--field_width >= 0) {
 			if (buf < end)
 				*buf = c;
@@ -1934,7 +1937,7 @@ char *flags_string(char *buf, char *end, void *flags_ptr,
 		names = vmaflag_names;
 		break;
 	case 'g':
-		flags = *(gfp_t *)flags_ptr;
+		flags = (__force unsigned long)(*(gfp_t *)flags_ptr);
 		names = gfpflag_names;
 		break;
 	default:
@@ -1976,12 +1979,6 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
 	char *buf_start = buf;
 	struct property *prop;
 	bool has_mult, pass;
-	static const struct printf_spec num_spec = {
-		.flags = SMALL,
-		.field_width = -1,
-		.precision = -1,
-		.base = 10,
-	};
 
 	struct printf_spec str_spec = spec;
 	str_spec.field_width = -1;
@@ -2021,7 +2018,7 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
 			str_spec.precision = precision;
 			break;
 		case 'p':	/* phandle */
-			buf = number(buf, end, (unsigned int)dn->phandle, num_spec);
+			buf = number(buf, end, (unsigned int)dn->phandle, default_dec_spec);
 			break;
 		case 'P':	/* path-spec */
 			p = fwnode_get_name(of_fwnode_handle(dn));
@@ -2134,7 +2131,7 @@ char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode,
  *       [4] or [6] and is able to print port [p], flowinfo [f], scope [s]
  * - '[Ii][4S][hnbl]' IPv4 addresses in host, network, big or little endian order
  * - 'I[6S]c' for IPv6 addresses printed as specified by
- *       http://tools.ietf.org/html/rfc5952
+ *       https://tools.ietf.org/html/rfc5952
  * - 'E[achnops]' For an escaped buffer, where rules are defined by combination
  *                of the following flags (see string_escape_mem() for the
  *                details):
diff --git a/lib/xz/Kconfig b/lib/xz/Kconfig
index 22528743d4ce..5cb50245a878 100644
--- a/lib/xz/Kconfig
+++ b/lib/xz/Kconfig
@@ -5,7 +5,7 @@ config XZ_DEC
 	help
 	  LZMA2 compression algorithm and BCJ filters are supported using
 	  the .xz file format as the container. For integrity checking,
-	  CRC32 is supported. See Documentation/xz.txt for more information.
+	  CRC32 is supported. See Documentation/staging/xz.rst for more information.
 
 if XZ_DEC
 
diff --git a/lib/zstd/fse_decompress.c b/lib/zstd/fse_decompress.c
index a84300e5a013..0b353530fb3f 100644
--- a/lib/zstd/fse_decompress.c
+++ b/lib/zstd/fse_decompress.c
@@ -47,6 +47,7 @@
 ****************************************************************/
 #include "bitstream.h"
 #include "fse.h"
+#include "zstd_internal.h"
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/string.h> /* memcpy, memset */
@@ -60,14 +61,6 @@
 		enum { FSE_static_assert = 1 / (int)(!!(c)) }; \
 	} /* use only *after* variable declarations */
 
-/* check and forward error code */
-#define CHECK_F(f)                  \
-	{                           \
-		size_t const e = f; \
-		if (FSE_isError(e)) \
-			return e;   \
-	}
-
 /* **************************************************************
 *  Templates
 ****************************************************************/
diff --git a/lib/zstd/zstd_internal.h b/lib/zstd/zstd_internal.h
index 1a79fab9e13a..dac753397f86 100644
--- a/lib/zstd/zstd_internal.h
+++ b/lib/zstd/zstd_internal.h
@@ -127,7 +127,14 @@ static const U32 OF_defaultNormLog = OF_DEFAULTNORMLOG;
 *  Shared functions to include for inlining
 *********************************************/
 ZSTD_STATIC void ZSTD_copy8(void *dst, const void *src) {
-	memcpy(dst, src, 8);
+	/*
+	 * zstd relies heavily on gcc being able to analyze and inline this
+	 * memcpy() call, since it is called in a tight loop. Preboot mode
+	 * is compiled in freestanding mode, which stops gcc from analyzing
+	 * memcpy(). Use __builtin_memcpy() to tell gcc to analyze this as a
+	 * regular memcpy().
+	 */
+	__builtin_memcpy(dst, src, 8);
 }
 /*! ZSTD_wildcopy() :
 *   custom version of memcpy(), can copy up to 7 bytes too many (8 bytes if length==0) */
@@ -137,13 +144,16 @@ ZSTD_STATIC void ZSTD_wildcopy(void *dst, const void *src, ptrdiff_t length)
 	const BYTE* ip = (const BYTE*)src;
 	BYTE* op = (BYTE*)dst;
 	BYTE* const oend = op + length;
-	/* Work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388.
+#if defined(GCC_VERSION) && GCC_VERSION >= 70000 && GCC_VERSION < 70200
+	/*
+	 * Work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388.
 	 * Avoid the bad case where the loop only runs once by handling the
 	 * special case separately. This doesn't trigger the bug because it
 	 * doesn't involve pointer/integer overflow.
 	 */
 	if (length <= 8)
 		return ZSTD_copy8(dst, src);
+#endif
 	do {
 		ZSTD_copy8(op, ip);
 		op += 8;