Merge tag 'mm-nonmm-stable-2024-09-21-07-52' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull non-MM updates from Andrew Morton:
 "Many singleton patches - please see the various changelogs for
  details.

  Quite a lot of nilfs2 work this time around.

  Notable patch series in this pull request are:

   - "mul_u64_u64_div_u64: new implementation" by Nicolas Pitre, with
     assistance from Uwe Kleine-König. Reimplement mul_u64_u64_div_u64()
     to provide (much) more accurate results. The current implementation
     was causing Uwe some issues in the PWM drivers.

   - "xz: Updates to license, filters, and compression options" from
     Lasse Collin. Miscellaneous maintenance and kinor feature work to
     the xz decompressor.

   - "Fix some GDB command error and add some GDB commands" from
     Kuan-Ying Lee. Fixes and enhancements to the gdb scripts.

   - "treewide: add missing MODULE_DESCRIPTION() macros" from Jeff
     Johnson. Adds lots of MODULE_DESCRIPTIONs, thus fixing lots of
     warnings about this.

   - "nilfs2: add support for some common ioctls" from Ryusuke Konishi.
     Adds various commonly-available ioctls to nilfs2.

   - "This series fixes a number of formatting issues in kernel doc
     comments" from Ryusuke Konishi does that.

   - "nilfs2: prevent unexpected ENOENT propagation" from Ryusuke
     Konishi. Fix issues where -ENOENT was being unintentionally and
     inappropriately returned to userspace.

   - "nilfs2: assorted cleanups" from Huang Xiaojia.

   - "nilfs2: fix potential issues with empty b-tree nodes" from Ryusuke
     Konishi fixes some issues which can occur on corrupted nilfs2
     filesystems.

   - "scripts/decode_stacktrace.sh: improve error reporting and
     usability" from Luca Ceresoli does those things"

* tag 'mm-nonmm-stable-2024-09-21-07-52' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (103 commits)
  list: test: increase coverage of list_test_list_replace*()
  list: test: fix tests for list_cut_position()
  proc: use __auto_type more
  treewide: correct the typo 'retun'
  ocfs2: cleanup return value and mlog in ocfs2_global_read_info()
  nilfs2: remove duplicate 'unlikely()' usage
  nilfs2: fix potential oob read in nilfs_btree_check_delete()
  nilfs2: determine empty node blocks as corrupted
  nilfs2: fix potential null-ptr-deref in nilfs_btree_insert()
  user_namespace: use kmemdup_array() instead of kmemdup() for multiple allocation
  tools/mm: rm thp_swap_allocator_test when make clean
  squashfs: fix percpu address space issues in decompressor_multi_percpu.c
  lib: glob.c: added null check for character class
  nilfs2: refactor nilfs_segctor_thread()
  nilfs2: use kthread_create and kthread_stop for the log writer thread
  nilfs2: remove sc_timer_task
  nilfs2: do not repair reserved inode bitmap in nilfs_new_inode()
  nilfs2: eliminate the shared counter and spinlock for i_generation
  nilfs2: separate inode type information from i_state field
  nilfs2: use the BITS_PER_LONG macro
  ...

29 files changed, 477 insertions, 163 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 3b8a915558ef..62fce4ce0b16 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1515,7 +1515,7 @@ config LOCKDEP_BITS
 config LOCKDEP_CHAINS_BITS
 	int "Bitsize for MAX_LOCKDEP_CHAINS"
 	depends on LOCKDEP && !LOCKDEP_SMALL
-	range 10 30
+	range 10 21
 	default 16
 	help
 	  Try increasing this value if you hit "BUG: MAX_LOCKDEP_CHAINS too low!" message.
@@ -2289,6 +2289,16 @@ config TEST_DIV64
 
 	  If unsure, say N.
 
+config TEST_MULDIV64
+	tristate "mul_u64_u64_div_u64() test"
+	depends on DEBUG_KERNEL || m
+	help
+	  Enable this to turn on 'mul_u64_u64_div_u64()' function test.
+	  This test is executed only once during system boot (so affects
+	  only boot time), or at module load time.
+
+	  If unsure, say N.
+
 config TEST_IOV_ITER
 	tristate "Test iov_iter operation" if !KUNIT_ALL_TESTS
 	depends on KUNIT
diff --git a/lib/Makefile b/lib/Makefile
index 2f1c5a9277af..773adf88af41 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -14,6 +14,7 @@ KCOV_INSTRUMENT_list_debug.o := n
 KCOV_INSTRUMENT_debugobjects.o := n
 KCOV_INSTRUMENT_dynamic_debug.o := n
 KCOV_INSTRUMENT_fault-inject.o := n
+KCOV_INSTRUMENT_find_bit.o := n
 
 # string.o implements standard library functions like memset/memcpy etc.
 # Use -ffreestanding to ensure that the compiler does not try to "optimize"
diff --git a/lib/bcd.c b/lib/bcd.c
index 7e4750b6e801..c5e79ba9cd7b 100644
--- a/lib/bcd.c
+++ b/lib/bcd.c
@@ -10,6 +10,8 @@ EXPORT_SYMBOL(_bcd2bin);
 
 unsigned char _bin2bcd(unsigned val)
 {
-	return ((val / 10) << 4) + val % 10;
+	const unsigned int t = (val * 103) >> 10;
+
+	return (t << 4) | (val - t * 10);
 }
 EXPORT_SYMBOL(_bin2bcd);
diff --git a/lib/checksum_kunit.c b/lib/checksum_kunit.c
index 4e4d081a1d3b..be04aa42125c 100644
--- a/lib/checksum_kunit.c
+++ b/lib/checksum_kunit.c
@@ -468,12 +468,9 @@ static __wsum to_wsum(u32 x)
 
 static void assert_setup_correct(struct kunit *test)
 {
-	CHECK_EQ(sizeof(random_buf) / sizeof(random_buf[0]), MAX_LEN);
-	CHECK_EQ(sizeof(expected_results) / sizeof(expected_results[0]),
-		 MAX_LEN);
-	CHECK_EQ(sizeof(init_sums_no_overflow) /
-			 sizeof(init_sums_no_overflow[0]),
-		 MAX_LEN);
+	CHECK_EQ(ARRAY_SIZE(random_buf), MAX_LEN);
+	CHECK_EQ(ARRAY_SIZE(expected_results), MAX_LEN);
+	CHECK_EQ(ARRAY_SIZE(init_sums_no_overflow), MAX_LEN);
 }
 
 /*
diff --git a/lib/closure.c b/lib/closure.c
index 116afae2eed9..2bfe7d2a0048 100644
--- a/lib/closure.c
+++ b/lib/closure.c
@@ -278,7 +278,7 @@ static int debug_show(struct seq_file *f, void *data)
 			seq_printf(f, " W %pS\n",
 				   (void *) cl->waiting_on);
 
-		seq_puts(f, "\n");
+		seq_putc(f, '\n');
 	}
 
 	spin_unlock_irq(&closure_list_lock);
diff --git a/lib/decompress_unxz.c b/lib/decompress_unxz.c
index 842894158944..32138bb8ef77 100644
--- a/lib/decompress_unxz.c
+++ b/lib/decompress_unxz.c
@@ -1,10 +1,9 @@
+// SPDX-License-Identifier: 0BSD
+
 /*
  * Wrapper for decompressing XZ-compressed kernel, initramfs, and initrd
  *
  * Author: Lasse Collin <lasse.collin@tukaani.org>
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
  */
 
 /*
@@ -103,12 +102,11 @@
 #ifdef STATIC
 #	define XZ_PREBOOT
 #else
-#include <linux/decompress/unxz.h>
+#	include <linux/decompress/unxz.h>
 #endif
 #ifdef __KERNEL__
 #	include <linux/decompress/mm.h>
 #endif
-#define XZ_EXTERN STATIC
 
 #ifndef XZ_PREBOOT
 #	include <linux/slab.h>
@@ -127,11 +125,21 @@
 #ifdef CONFIG_X86
 #	define XZ_DEC_X86
 #endif
-#ifdef CONFIG_PPC
+#if defined(CONFIG_PPC) && defined(CONFIG_CPU_BIG_ENDIAN)
 #	define XZ_DEC_POWERPC
 #endif
 #ifdef CONFIG_ARM
-#	define XZ_DEC_ARM
+#	ifdef CONFIG_THUMB2_KERNEL
+#		define XZ_DEC_ARMTHUMB
+#	else
+#		define XZ_DEC_ARM
+#	endif
+#endif
+#ifdef CONFIG_ARM64
+#	define XZ_DEC_ARM64
+#endif
+#ifdef CONFIG_RISCV
+#	define XZ_DEC_RISCV
 #endif
 #ifdef CONFIG_SPARC
 #	define XZ_DEC_SPARC
@@ -220,7 +228,7 @@ void *memmove(void *dest, const void *src, size_t size)
 #endif
 
 /*
- * Since we need memmove anyway, would use it as memcpy too.
+ * Since we need memmove anyway, we could use it as memcpy too.
  * Commented out for now to avoid breaking things.
  */
 /*
@@ -390,17 +398,17 @@ error_alloc_state:
 }
 
 /*
- * This macro is used by architecture-specific files to decompress
+ * This function is used by architecture-specific files to decompress
  * the kernel image.
  */
 #ifdef XZ_PREBOOT
-STATIC int INIT __decompress(unsigned char *buf, long len,
-			   long (*fill)(void*, unsigned long),
-			   long (*flush)(void*, unsigned long),
-			   unsigned char *out_buf, long olen,
-			   long *pos,
-			   void (*error)(char *x))
+STATIC int INIT __decompress(unsigned char *in, long in_size,
+			     long (*fill)(void *dest, unsigned long size),
+			     long (*flush)(void *src, unsigned long size),
+			     unsigned char *out, long out_size,
+			     long *in_used,
+			     void (*error)(char *x))
 {
-	return unxz(buf, len, fill, flush, out_buf, pos, error);
+	return unxz(in, in_size, fill, flush, out, in_used, error);
 }
 #endif
diff --git a/lib/dim/Makefile b/lib/dim/Makefile
index c4cc4026c451..5b9bfaac7ac1 100644
--- a/lib/dim/Makefile
+++ b/lib/dim/Makefile
@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_DIMLIB) += dimlib.o
 
-dimlib-objs := dim.o net_dim.o rdma_dim.o
+dimlib-y := dim.o net_dim.o rdma_dim.o
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index f2c5e7910bb1..5a007952f7f2 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -1147,7 +1147,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
 		   iter->table->mod_name, dp->function,
 		   ddebug_describe_flags(dp->flags, &flags));
 	seq_escape_str(m, dp->format, ESCAPE_SPACE, "\t\r\n\"");
-	seq_puts(m, "\"");
+	seq_putc(m, '"');
 
 	if (dp->class_id != _DPRINTK_CLASS_DFLT) {
 		class = ddebug_class_name(iter, dp);
@@ -1156,7 +1156,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
 		else
 			seq_printf(m, " class unknown, _id:%d", dp->class_id);
 	}
-	seq_puts(m, "\n");
+	seq_putc(m, '\n');
 
 	return 0;
 }
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index d608f9b48c10..52eb6ba29698 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -2,6 +2,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/random.h>
+#include <linux/debugfs.h>
 #include <linux/sched.h>
 #include <linux/stat.h>
 #include <linux/types.h>
diff --git a/lib/glob.c b/lib/glob.c
index 15b73f490720..aa57900d2062 100644
--- a/lib/glob.c
+++ b/lib/glob.c
@@ -68,6 +68,8 @@ bool __pure glob_match(char const *pat, char const *str)
 			back_str = --str;	/* Allow zero-length match */
 			break;
 		case '[': {	/* Character class */
+			if (c == '\0')	/* No possible match */
+				return false;
 			bool match = false, inverted = (*pat == '!');
 			char const *class = pat + inverted;
 			unsigned char a = *class++;
diff --git a/lib/list-test.c b/lib/list-test.c
index 37cbc33e9fdb..4f3dc75baec1 100644
--- a/lib/list-test.c
+++ b/lib/list-test.c
@@ -102,6 +102,8 @@ static void list_test_list_replace(struct kunit *test)
 	/* now: [list] -> a_new -> b */
 	KUNIT_EXPECT_PTR_EQ(test, list.next, &a_new);
 	KUNIT_EXPECT_PTR_EQ(test, b.prev, &a_new);
+	KUNIT_EXPECT_PTR_EQ(test, a_new.next, &b);
+	KUNIT_EXPECT_PTR_EQ(test, a_new.prev, &list);
 }
 
 static void list_test_list_replace_init(struct kunit *test)
@@ -118,6 +120,8 @@ static void list_test_list_replace_init(struct kunit *test)
 	/* now: [list] -> a_new -> b */
 	KUNIT_EXPECT_PTR_EQ(test, list.next, &a_new);
 	KUNIT_EXPECT_PTR_EQ(test, b.prev, &a_new);
+	KUNIT_EXPECT_PTR_EQ(test, a_new.next, &b);
+	KUNIT_EXPECT_PTR_EQ(test, a_new.prev, &list);
 
 	/* check a_old is empty (initialized) */
 	KUNIT_EXPECT_TRUE(test, list_empty_careful(&a_old));
@@ -404,10 +408,13 @@ static void list_test_list_cut_position(struct kunit *test)
 
 	KUNIT_EXPECT_EQ(test, i, 2);
 
+	i = 0;
 	list_for_each(cur, &list1) {
 		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
 		i++;
 	}
+
+	KUNIT_EXPECT_EQ(test, i, 1);
 }
 
 static void list_test_list_cut_before(struct kunit *test)
@@ -432,10 +439,13 @@ static void list_test_list_cut_before(struct kunit *test)
 
 	KUNIT_EXPECT_EQ(test, i, 1);
 
+	i = 0;
 	list_for_each(cur, &list1) {
 		KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]);
 		i++;
 	}
+
+	KUNIT_EXPECT_EQ(test, i, 2);
 }
 
 static void list_test_list_splice(struct kunit *test)
diff --git a/lib/lru_cache.c b/lib/lru_cache.c
index b3d9187611de..9e0d469c7658 100644
--- a/lib/lru_cache.c
+++ b/lib/lru_cache.c
@@ -243,7 +243,7 @@ static struct lc_element *__lc_find(struct lru_cache *lc, unsigned int enr,
 
 	BUG_ON(!lc);
 	BUG_ON(!lc->nr_elements);
-	hlist_for_each_entry(e, lc_hash_slot(lc, enr), colision) {
+	hlist_for_each_entry(e, lc_hash_slot(lc, enr), collision) {
 		/* "about to be changed" elements, pending transaction commit,
 		 * are hashed by their "new number". "Normal" elements have
 		 * lc_number == lc_new_number. */
@@ -303,7 +303,7 @@ void lc_del(struct lru_cache *lc, struct lc_element *e)
 	BUG_ON(e->refcnt);
 
 	e->lc_number = e->lc_new_number = LC_FREE;
-	hlist_del_init(&e->colision);
+	hlist_del_init(&e->collision);
 	list_move(&e->list, &lc->free);
 	RETURN();
 }
@@ -324,9 +324,9 @@ static struct lc_element *lc_prepare_for_change(struct lru_cache *lc, unsigned n
 	PARANOIA_LC_ELEMENT(lc, e);
 
 	e->lc_new_number = new_number;
-	if (!hlist_unhashed(&e->colision))
-		__hlist_del(&e->colision);
-	hlist_add_head(&e->colision, lc_hash_slot(lc, new_number));
+	if (!hlist_unhashed(&e->collision))
+		__hlist_del(&e->collision);
+	hlist_add_head(&e->collision, lc_hash_slot(lc, new_number));
 	list_move(&e->list, &lc->to_be_changed);
 
 	return e;
diff --git a/lib/math/Makefile b/lib/math/Makefile
index 3c1f92a7459d..3ef11305f8d2 100644
--- a/lib/math/Makefile
+++ b/lib/math/Makefile
@@ -7,4 +7,5 @@ obj-$(CONFIG_RATIONAL)		+= rational.o
 
 obj-$(CONFIG_INT_POW_TEST)  += tests/int_pow_kunit.o
 obj-$(CONFIG_TEST_DIV64)	+= test_div64.o
+obj-$(CONFIG_TEST_MULDIV64)	+= test_mul_u64_u64_div_u64.o
 obj-$(CONFIG_RATIONAL_KUNIT_TEST) += rational-test.o
diff --git a/lib/math/div64.c b/lib/math/div64.c
index 191761b1b623..5faa29208bdb 100644
--- a/lib/math/div64.c
+++ b/lib/math/div64.c
@@ -186,55 +186,84 @@ 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;
+	if (ilog2(a) + ilog2(b) <= 62)
+		return div64_u64(a * b, c);
 
-	/* can a * b overflow ? */
-	if (ilog2(a) + ilog2(b) > 62) {
-		/*
-		 * Note that the algorithm after the if block below might lose
-		 * some precision and the result is more exact for b > a. So
-		 * exchange a and b if a is bigger than b.
-		 *
-		 * For example with a = 43980465100800, b = 100000000, c = 1000000000
-		 * the below calculation doesn't modify b at all because div == 0
-		 * and then shift becomes 45 + 26 - 62 = 9 and so the result
-		 * becomes 4398035251080. However with a and b swapped the exact
-		 * result is calculated (i.e. 4398046510080).
-		 */
-		if (a > b)
-			swap(a, b);
+#if defined(__SIZEOF_INT128__)
+
+	/* native 64x64=128 bits multiplication */
+	u128 prod = (u128)a * b;
+	u64 n_lo = prod, n_hi = prod >> 64;
+
+#else
+
+	/* perform a 64x64=128 bits multiplication manually */
+	u32 a_lo = a, a_hi = a >> 32, b_lo = b, b_hi = b >> 32;
+	u64 x, y, z;
+
+	x = (u64)a_lo * b_lo;
+	y = (u64)a_lo * b_hi + (u32)(x >> 32);
+	z = (u64)a_hi * b_hi + (u32)(y >> 32);
+	y = (u64)a_hi * b_lo + (u32)y;
+	z += (u32)(y >> 32);
+	x = (y << 32) + (u32)x;
+
+	u64 n_lo = x, n_hi = z;
+
+#endif
+
+	/* make sure c is not zero, trigger exception otherwise */
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wdiv-by-zero"
+	if (unlikely(c == 0))
+		return 1/0;
+#pragma GCC diagnostic pop
+
+	int shift = __builtin_ctzll(c);
 
+	/* try reducing the fraction in case the dividend becomes <= 64 bits */
+	if ((n_hi >> shift) == 0) {
+		u64 n = shift ? (n_lo >> shift) | (n_hi << (64 - shift)) : n_lo;
+
+		return div64_u64(n, c >> shift);
 		/*
-		 * (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;
+		 * The remainder value if needed would be:
+		 *   res = div64_u64_rem(n, c >> shift, &rem);
+		 *   rem = (rem << shift) + (n_lo - (n << shift));
 		 */
-		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);
+	if (n_hi >= c) {
+		/* overflow: result is unrepresentable in a u64 */
+		return -1;
+	}
+
+	/* Do the full 128 by 64 bits division */
+
+	shift = __builtin_clzll(c);
+	c <<= shift;
+
+	int p = 64 + shift;
+	u64 res = 0;
+	bool carry;
+
+	do {
+		carry = n_hi >> 63;
+		shift = carry ? 1 : __builtin_clzll(n_hi);
+		if (p < shift)
+			break;
+		p -= shift;
+		n_hi <<= shift;
+		n_hi |= n_lo >> (64 - shift);
+		n_lo <<= shift;
+		if (carry || (n_hi >= c)) {
+			n_hi -= c;
+			res |= 1ULL << p;
+		}
+	} while (n_hi);
+	/* The remainder value if needed would be n_hi << p */
+
+	return res;
 }
 EXPORT_SYMBOL(mul_u64_u64_div_u64);
 #endif
diff --git a/lib/math/test_mul_u64_u64_div_u64.c b/lib/math/test_mul_u64_u64_div_u64.c
new file mode 100644
index 000000000000..58d058de4e73
--- /dev/null
+++ b/lib/math/test_mul_u64_u64_div_u64.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 BayLibre SAS
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/math64.h>
+
+typedef struct { u64 a; u64 b; u64 c; u64 result; } test_params;
+
+static test_params test_values[] = {
+/* this contains many edge values followed by a couple random values */
+{                0xb,                0x7,                0x3,               0x19 },
+{         0xffff0000,         0xffff0000,                0xf, 0x1110eeef00000000 },
+{         0xffffffff,         0xffffffff,                0x1, 0xfffffffe00000001 },
+{         0xffffffff,         0xffffffff,                0x2, 0x7fffffff00000000 },
+{        0x1ffffffff,         0xffffffff,                0x2, 0xfffffffe80000000 },
+{        0x1ffffffff,         0xffffffff,                0x3, 0xaaaaaaa9aaaaaaab },
+{        0x1ffffffff,        0x1ffffffff,                0x4, 0xffffffff00000000 },
+{ 0xffff000000000000, 0xffff000000000000, 0xffff000000000001, 0xfffeffffffffffff },
+{ 0x3333333333333333, 0x3333333333333333, 0x5555555555555555, 0x1eb851eb851eb851 },
+{ 0x7fffffffffffffff,                0x2,                0x3, 0x5555555555555554 },
+{ 0xffffffffffffffff,                0x2, 0x8000000000000000,                0x3 },
+{ 0xffffffffffffffff,                0x2, 0xc000000000000000,                0x2 },
+{ 0xffffffffffffffff, 0x4000000000000004, 0x8000000000000000, 0x8000000000000007 },
+{ 0xffffffffffffffff, 0x4000000000000001, 0x8000000000000000, 0x8000000000000001 },
+{ 0xffffffffffffffff, 0x8000000000000001, 0xffffffffffffffff, 0x8000000000000001 },
+{ 0xfffffffffffffffe, 0x8000000000000001, 0xffffffffffffffff, 0x8000000000000000 },
+{ 0xffffffffffffffff, 0x8000000000000001, 0xfffffffffffffffe, 0x8000000000000001 },
+{ 0xffffffffffffffff, 0x8000000000000001, 0xfffffffffffffffd, 0x8000000000000002 },
+{ 0x7fffffffffffffff, 0xffffffffffffffff, 0xc000000000000000, 0xaaaaaaaaaaaaaaa8 },
+{ 0xffffffffffffffff, 0x7fffffffffffffff, 0xa000000000000000, 0xccccccccccccccca },
+{ 0xffffffffffffffff, 0x7fffffffffffffff, 0x9000000000000000, 0xe38e38e38e38e38b },
+{ 0x7fffffffffffffff, 0x7fffffffffffffff, 0x5000000000000000, 0xccccccccccccccc9 },
+{ 0xffffffffffffffff, 0xfffffffffffffffe, 0xffffffffffffffff, 0xfffffffffffffffe },
+{ 0xe6102d256d7ea3ae, 0x70a77d0be4c31201, 0xd63ec35ab3220357, 0x78f8bf8cc86c6e18 },
+{ 0xf53bae05cb86c6e1, 0x3847b32d2f8d32e0, 0xcfd4f55a647f403c, 0x42687f79d8998d35 },
+{ 0x9951c5498f941092, 0x1f8c8bfdf287a251, 0xa3c8dc5f81ea3fe2, 0x1d887cb25900091f },
+{ 0x374fee9daa1bb2bb, 0x0d0bfbff7b8ae3ef, 0xc169337bd42d5179, 0x03bb2dbaffcbb961 },
+{ 0xeac0d03ac10eeaf0, 0x89be05dfa162ed9b, 0x92bb1679a41f0e4b, 0xdc5f5cc9e270d216 },
+};
+
+/*
+ * The above table can be verified with the following shell script:
+ *
+ * #!/bin/sh
+ * sed -ne 's/^{ \+\(.*\), \+\(.*\), \+\(.*\), \+\(.*\) },$/\1 \2 \3 \4/p' \
+ *     lib/math/test_mul_u64_u64_div_u64.c |
+ * while read a b c r; do
+ *   expected=$( printf "obase=16; ibase=16; %X * %X / %X\n" $a $b $c | bc )
+ *   given=$( printf "%X\n" $r )
+ *   if [ "$expected" = "$given" ]; then
+ *     echo "$a * $b / $c = $r OK"
+ *   else
+ *     echo "$a * $b / $c = $r is wrong" >&2
+ *     echo "should be equivalent to 0x$expected" >&2
+ *     exit 1
+ *   fi
+ * done
+ */
+
+static int __init test_init(void)
+{
+	int i;
+
+	pr_info("Starting mul_u64_u64_div_u64() test\n");
+
+	for (i = 0; i < ARRAY_SIZE(test_values); i++) {
+		u64 a = test_values[i].a;
+		u64 b = test_values[i].b;
+		u64 c = test_values[i].c;
+		u64 expected_result = test_values[i].result;
+		u64 result = mul_u64_u64_div_u64(a, b, c);
+
+		if (result != expected_result) {
+			pr_err("ERROR: 0x%016llx * 0x%016llx / 0x%016llx\n", a, b, c);
+			pr_err("ERROR: expected result: %016llx\n", expected_result);
+			pr_err("ERROR: obtained result: %016llx\n", result);
+		}
+	}
+
+	pr_info("Completed mul_u64_u64_div_u64() test\n");
+	return 0;
+}
+
+static void __exit test_exit(void)
+{
+}
+
+module_init(test_init);
+module_exit(test_exit);
+
+MODULE_AUTHOR("Nicolas Pitre");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("mul_u64_u64_div_u64() test module");
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 51bc5246986d..2891f94a11c6 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -209,7 +209,7 @@ int __percpu_counter_init_many(struct percpu_counter *fbc, s64 amount,
 		INIT_LIST_HEAD(&fbc[i].list);
 #endif
 		fbc[i].count = amount;
-		fbc[i].counters = (void *)counters + (i * counter_size);
+		fbc[i].counters = (void __percpu *)counters + i * counter_size;
 
 		debug_percpu_counter_activate(&fbc[i]);
 	}
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index dbbed19f8fff..6c902639728b 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -189,7 +189,7 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
 
 	size = nbuckets;
 
-	if (tbl == NULL && (gfp & ~__GFP_NOFAIL) != GFP_KERNEL) {
+	if (tbl == NULL && !gfpflags_allow_blocking(gfp)) {
 		tbl = nested_bucket_table_alloc(ht, nbuckets, gfp);
 		nbuckets = 0;
 	}
diff --git a/lib/test_fpu_glue.c b/lib/test_fpu_glue.c
index 074f30301f29..c0596426370a 100644
--- a/lib/test_fpu_glue.c
+++ b/lib/test_fpu_glue.c
@@ -42,7 +42,7 @@ static int __init test_fpu_init(void)
 		return -EINVAL;
 
 	selftest_dir = debugfs_create_dir("selftest_helpers", NULL);
-	if (!selftest_dir)
+	if (IS_ERR(selftest_dir))
 		return -ENOMEM;
 
 	debugfs_create_file_unsafe("test_fpu", 0444, selftest_dir, NULL,
diff --git a/lib/test_objpool.c b/lib/test_objpool.c
index bfdb81599832..5a3f6961a70f 100644
--- a/lib/test_objpool.c
+++ b/lib/test_objpool.c
@@ -687,4 +687,5 @@ static void __exit ot_mod_exit(void)
 module_init(ot_mod_init);
 module_exit(ot_mod_exit);
 
-MODULE_LICENSE("GPL");
\ No newline at end of file
+MODULE_DESCRIPTION("Test module for lockless object pool");
+MODULE_LICENSE("GPL");
diff --git a/lib/xz/Kconfig b/lib/xz/Kconfig
index aef086a6bf2f..20aa459bfb3e 100644
--- a/lib/xz/Kconfig
+++ b/lib/xz/Kconfig
@@ -5,7 +5,8 @@ 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/staging/xz.rst for more information.
+	  CRC32 is supported. See Documentation/staging/xz.rst for more
+	  information.
 
 if XZ_DEC
 
@@ -29,11 +30,21 @@ config XZ_DEC_ARMTHUMB
 	default y
 	select XZ_DEC_BCJ
 
+config XZ_DEC_ARM64
+	bool "ARM64 BCJ filter decoder" if EXPERT
+	default y
+	select XZ_DEC_BCJ
+
 config XZ_DEC_SPARC
 	bool "SPARC BCJ filter decoder" if EXPERT
 	default y
 	select XZ_DEC_BCJ
 
+config XZ_DEC_RISCV
+	bool "RISC-V BCJ filter decoder" if EXPERT
+	default y
+	select XZ_DEC_BCJ
+
 config XZ_DEC_MICROLZMA
 	bool "MicroLZMA decoder"
 	default n
diff --git a/lib/xz/xz_crc32.c b/lib/xz/xz_crc32.c
index 88a2c35e1b59..6a7906a328ba 100644
--- a/lib/xz/xz_crc32.c
+++ b/lib/xz/xz_crc32.c
@@ -1,11 +1,10 @@
+// SPDX-License-Identifier: 0BSD
+
 /*
  * CRC32 using the polynomial from IEEE-802.3
  *
  * Authors: Lasse Collin <lasse.collin@tukaani.org>
  *          Igor Pavlov <https://7-zip.org/>
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
  */
 
 /*
@@ -27,9 +26,9 @@
 
 STATIC_RW_DATA uint32_t xz_crc32_table[256];
 
-XZ_EXTERN void xz_crc32_init(void)
+void xz_crc32_init(void)
 {
-	const uint32_t poly = CRC32_POLY_LE;
+	const uint32_t poly = 0xEDB88320;
 
 	uint32_t i;
 	uint32_t j;
@@ -46,7 +45,7 @@ XZ_EXTERN void xz_crc32_init(void)
 	return;
 }
 
-XZ_EXTERN uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc)
+uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc)
 {
 	crc = ~crc;
 
diff --git a/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c
index ef449e97d1a1..8237db17eee3 100644
--- a/lib/xz/xz_dec_bcj.c
+++ b/lib/xz/xz_dec_bcj.c
@@ -1,11 +1,10 @@
+// SPDX-License-Identifier: 0BSD
+
 /*
  * Branch/Call/Jump (BCJ) filter decoders
  *
  * Authors: Lasse Collin <lasse.collin@tukaani.org>
  *          Igor Pavlov <https://7-zip.org/>
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
  */
 
 #include "xz_private.h"
@@ -24,7 +23,9 @@ struct xz_dec_bcj {
 		BCJ_IA64 = 6,       /* Big or little endian */
 		BCJ_ARM = 7,        /* Little endian only */
 		BCJ_ARMTHUMB = 8,   /* Little endian only */
-		BCJ_SPARC = 9       /* Big or little endian */
+		BCJ_SPARC = 9,      /* Big or little endian */
+		BCJ_ARM64 = 10,     /* AArch64 */
+		BCJ_RISCV = 11      /* RV32GQC_Zfh, RV64GQC_Zfh */
 	} type;
 
 	/*
@@ -162,7 +163,9 @@ static size_t bcj_powerpc(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
 	size_t i;
 	uint32_t instr;
 
-	for (i = 0; i + 4 <= size; i += 4) {
+	size &= ~(size_t)3;
+
+	for (i = 0; i < size; i += 4) {
 		instr = get_unaligned_be32(buf + i);
 		if ((instr & 0xFC000003) == 0x48000001) {
 			instr &= 0x03FFFFFC;
@@ -219,7 +222,9 @@ static size_t bcj_ia64(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
 	/* Instruction normalized with bit_res for easier manipulation */
 	uint64_t norm;
 
-	for (i = 0; i + 16 <= size; i += 16) {
+	size &= ~(size_t)15;
+
+	for (i = 0; i < size; i += 16) {
 		mask = branch_table[buf[i] & 0x1F];
 		for (slot = 0, bit_pos = 5; slot < 3; ++slot, bit_pos += 41) {
 			if (((mask >> slot) & 1) == 0)
@@ -267,7 +272,9 @@ static size_t bcj_arm(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
 	size_t i;
 	uint32_t addr;
 
-	for (i = 0; i + 4 <= size; i += 4) {
+	size &= ~(size_t)3;
+
+