Merge tag 'mm-nonmm-stable-2026-08-22-16-57' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull non-MM updates from Andrew Morton:

 - "ocfs2/dlm: bound peer-controlled lengths in the o2dlm" (Bryam
   Vargas)

   Validate and bound all input lengths and count fields in the o2dlm
   migration and recovery receive handlers to prevent memory corruption
   and kernel panics from malformed cluster messages

 - "ocfs2: validate xattr entry bounds" (Cen Zhang)

   Validate OCFS2 extended attribute entry name and value bounds during
   metadata reads to prevent out-of-range memory accesses during
   retrieval or listing operations.

 - "taskstats: fix cgroupstats invalid fd handling and add selftests"
   (Yiyang Chen)

   Return -EBADF when cgroupstats receives an invalid file descriptor to
   prevent caller hangs and misleading success ACKs. Add a kselftest to
   validate valid cgroup v1 queries and verify proper error handling
   across different Netlink flag combinations.

 - "misc lib/raid/ improvements v2" (Christoph Hellwig)

   Improve benchmark-based algorithm selection for the XOR and RAID6
   libraries, add KUnit benchmark tests, and cleanup minor
   implementation details.

 - "ocfs2: cluster: o2hb_region_pin() fixes" (Joseph Qi)

   Fix sleeping-in-atomic, lock order inversion and error-path cleanup
   bugs in o2hb_region_pin() by releasing o2hb_live_lock across sleeping
   configfs_depend_item() calls and using unlocked variants from
   callback context. Ensure failed pin attempts properly decrement user
   counts and unpin partially initialized heartbeat regions to prevent
   memory leaks and unprotected states.

 - "lib/ucs2_string.c: fix out-of-bounds read in ucs2_strnlen()"
   (Vincent Mailhol)

   Fix an off-by-one which could cause an out-of-bounds read.

 - "ocfs2: harden heartbeat teardown races" (Cen Zhang)

   Fix two OCFS2 heartbeat/o2net teardown races found by KASAN.

 - "taskstats: tidy up the cpumask command path" *Bradley Morgan)

   make two small cleanups in kernel/taskstats.c.

 - "ocfs2: validate active orphan slots during inode read" (ZhengYuan
   Huang)

   Validate active ordinary and append-DIO orphan slots read from OCFS2
   dinodes at the metadata boundary to prevent corrupted slot indices
   from causing out-of-bounds array accesses.

 - "ocfs2: bound-check both readdir re-validation scans" (Zhan Xusheng)

   Enforce strict boundary checks on directory entry record lengths and
   offset calculations during OCFS2 directory re-scans to prevent
   out-of-bounds memory reads and directory position corruption.

* tag 'mm-nonmm-stable-2026-08-22-16-57' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (95 commits)
  mailmap: fix bouncing address for Taniya Das
  ocfs2: bound-check dir entries in the inline-data re-validation scan
  ocfs2: bound-check dir entries in the readdir re-validation scan
  squashfs: avoid thundering-herd cache wakeups
  prctl: fix PR_SET_MM_AUXV losing the forced AT_NULL terminator
  mailmap: update email address for Linfeng Sun
  lib/interval_tree: fix allocation warning messages
  checkpatch: add NOKPROBE_SYMBOL to the whitelist of lines that can occur immediately after functions
  Squashfs: check block offset is not negative
  signal: factor out the kernel reserved si_code check
  ocfs2: fix readdir position truncation on 32-bit kernels
  ocfs2: fix cached cluster count after suballocator reclaim
  ocfs2: fix circular locking dependency in ocfs2_init_acl()
  ocfs2: validate DIO orphan slot during inode read
  ocfs2: validate orphan slot during inode read
  selftests/prctl: fix non-anonymous VMA mapping in set-anon-vma-name test
  MAINTAINERS: add IRC and patchwork for LTP
  include/linux/list.h: mark list_add and __list_add as __always_inline
  tools/mm: prevent page_owner_sort from truncating input
  hung_task: update DETECT_HUNG_TASK_BLOCKER Kconfig help
  ...

23 files changed, 783 insertions, 329 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 55748b68714e..4e6b34c3346d 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -159,12 +159,6 @@ config AUDIT_COMPAT_GENERIC
 	depends on AUDIT_GENERIC && AUDIT_ARCH_COMPAT_GENERIC && COMPAT
 	default y
 
-config RANDOM32_SELFTEST
-	bool "PRNG perform self test on init"
-	help
-	  This option enables the 32 bit PRNG library functions to perform a
-	  self test on initialization.
-
 #
 # compression support is select'ed if needed
 #
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index e97bdf3a42a8..a2f0d3e97889 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1292,10 +1292,10 @@ config DETECT_HUNG_TASK_BLOCKER
 	depends on !PREEMPT_RT
 	default y
 	help
-	  Say Y here to show the blocker task's stacktrace who acquires
-	  the mutex lock which "hung tasks" are waiting.
-	  This will add overhead a bit but shows suspicious tasks and
-	  call trace if it comes from waiting a mutex.
+	  Say Y here to show a possible blocker task's stacktrace when
+	  a hung task is waiting on a mutex, semaphore, or rwsem.
+	  This will add a bit of overhead but shows suspicious tasks and
+	  call traces for waits on one of these locks.
 
 config WQ_WATCHDOG
 	bool "Detect Workqueue Stalls"
@@ -2219,10 +2219,11 @@ config KCOV_INSTRUMENT_ALL
 config KCOV_IRQ_AREA_SIZE
 	hex "Size of interrupt coverage collection area in words"
 	depends on KCOV
+	range 0x80 0x1000000
 	default 0x40000
 	help
-	  KCOV uses preallocated per-cpu areas to collect coverage from
-	  soft interrupts. This specifies the size of those areas in the
+	  KCOV uses preallocated areas to collect coverage from soft
+	  interrupts. This specifies the size of those areas in the
 	  number of unsigned long words.
 
 config KCOV_SELFTEST
@@ -3489,6 +3490,23 @@ config GCD_KUNIT_TEST
 
 	  If unsure, say N
 
+config POLYNOMIAL_KUNIT_TEST
+	tristate "Polynomial calculation (polynomial_calc) test" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	select POLYNOMIAL
+	default KUNIT_ALL_TESTS
+	help
+	  This option enables the KUnit test suite for the polynomial_calc()
+	  function, which evaluates integer polynomials using factor
+	  redistribution to avoid overflow.
+
+	  The test suite verifies correctness for constant, linear, and
+	  quadratic polynomials, negative coefficients, per-step dividers,
+	  divider_leftover, total_divider scaling, and a real sensor
+	  N-to-temperature conversion polynomial.
+
+	  If unsure, say N
+
 config PRIME_NUMBERS_KUNIT_TEST
 	tristate "Prime number generator test" if !KUNIT_ALL_TESTS
 	depends on KUNIT
@@ -3516,6 +3534,15 @@ config GLOB_KUNIT_TEST
 
 	  If unsure, say N
 
+config PRANDOM_KUNIT_TEST
+	tristate "KUnit test for prandom" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	default KUNIT_ALL_TESTS
+	help
+	  Enable this option to test the prandom functions at runtime.
+
+	  If unsure, say N
+
 endif # RUNTIME_TESTING_MENU
 
 config ARCH_USE_MEMTEST
diff --git a/lib/interval_tree_test.c b/lib/interval_tree_test.c
index eba2d3e28980..b0b07270ce7c 100644
--- a/lib/interval_tree_test.c
+++ b/lib/interval_tree_test.c
@@ -140,13 +140,13 @@ static int intersection_range_check(void)
 
 	intxn1 = bitmap_alloc(nnodes, GFP_KERNEL);
 	if (!intxn1) {
-		WARN_ON_ONCE("Failed to allocate intxn1\n");
+		WARN_ONCE(1, "Failed to allocate intxn1\n");
 		return -ENOMEM;
 	}
 
 	intxn2 = bitmap_alloc(nnodes, GFP_KERNEL);
 	if (!intxn2) {
-		WARN_ON_ONCE("Failed to allocate intxn2\n");
+		WARN_ONCE(1, "Failed to allocate intxn2\n");
 		bitmap_free(intxn1);
 		return -ENOMEM;
 	}
diff --git a/lib/math/tests/Makefile b/lib/math/tests/Makefile
index 13dc96e48408..85e1ad59f29d 100644
--- a/lib/math/tests/Makefile
+++ b/lib/math/tests/Makefile
@@ -4,5 +4,6 @@ obj-$(CONFIG_GCD_KUNIT_TEST)		+= gcd_kunit.o
 obj-$(CONFIG_INT_LOG_KUNIT_TEST)	+= int_log_kunit.o
 obj-$(CONFIG_INT_POW_KUNIT_TEST)	+= int_pow_kunit.o
 obj-$(CONFIG_INT_SQRT_KUNIT_TEST)	+= int_sqrt_kunit.o
+obj-$(CONFIG_POLYNOMIAL_KUNIT_TEST)	+= polynomial_kunit.o
 obj-$(CONFIG_PRIME_NUMBERS_KUNIT_TEST)	+= prime_numbers_kunit.o
 obj-$(CONFIG_RATIONAL_KUNIT_TEST)	+= rational_kunit.o
diff --git a/lib/math/tests/polynomial_kunit.c b/lib/math/tests/polynomial_kunit.c
new file mode 100644
index 000000000000..ef443b57fc12
--- /dev/null
+++ b/lib/math/tests/polynomial_kunit.c
@@ -0,0 +1,270 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <kunit/test.h>
+#include <linux/polynomial.h>
+
+struct polynomial_test_param {
+	const struct polynomial *poly;
+	long data;
+	long expected;
+	const char *name;
+};
+
+/* f(x) = 5 */
+static const struct polynomial poly_constant = {
+	.total_divider = 1,
+	.terms = {
+		{0, 5, 1, 1},
+	}
+};
+
+/* f(x) = 2x^2 + 3x + 5 */
+static const struct polynomial poly_simple = {
+	.total_divider = 1,
+	.terms = {
+		{2, 2, 1, 1},
+		{1, 3, 1, 1},
+		{0, 5, 1, 1},
+	}
+};
+
+/* f(x) = -5x + 100 */
+static const struct polynomial poly_negative_coef = {
+	.total_divider = 1,
+	.terms = {
+		{1, -5, 1, 1},
+		{0, 100, 1, 1},
+	}
+};
+
+/* f(x) = (150x + 50) / 10 */
+static const struct polynomial poly_total_divider = {
+	.total_divider = 10,
+	.terms = {
+		{1, 150, 1, 1},
+		{0,  50, 1, 1},
+	}
+};
+
+/*
+ * f(x) = x / 2
+ * divider=2 applied once per multiply: mult_frac(coef, data, 2) = coef*data/2
+ */
+static const struct polynomial poly_step_divider = {
+	.total_divider = 1,
+	.terms = {
+		{1, 1, 2, 1},
+		{0, 0, 1, 1},
+	}
+};
+
+/*
+ * f(x) = (100/500) * x^2 = 0.2 * x^2
+ * Encoded as coef=100, divider=10, divider_leftover=5:
+ *   denom = 10^2 * 5 = 500
+ */
+static const struct polynomial poly_leftover = {
+	.total_divider = 1,
+	.terms = {
+		{2, 100, 10, 5},
+		{0,   0,  1, 1},
+	}
+};
+
+/*
+ * f(x) = 2x^3  (single high-degree term, no constant)
+ * Used to exercise the power loop alone.
+ */
+static const struct polynomial poly_cubic = {
+	.total_divider = 1,
+	.terms = {
+		{3, 2, 1, 1},
+		{0, 0, 1, 1},
+	}
+};
+
+/*
+ * f(x) = 4x + 1  with a zero-coefficient quadratic term.
+ * The deg-2 term contributes nothing regardless of input.
+ */
+static const struct polynomial poly_zero_coef = {
+	.total_divider = 1,
+	.terms = {
+		{2, 0, 1, 1},
+		{1, 4, 1, 1},
+		{0, 1, 1, 1},
+	}
+};
+
+/*
+ * f(x) = 9  with total_divider = 0.
+ * The implementation treats 0 as 1 via `total_divider ?: 1`, so the
+ * result must equal the constant term unchanged.
+ */
+static const struct polynomial poly_zero_total_divider = {
+	.total_divider = 0,
+	.terms = {
+		{0, 9, 1, 1},
+	}
+};
+
+
+static const struct polynomial_test_param test_params[] = {
+	{
+		.poly     = &poly_constant,
+		.data     = 0,
+		.expected = 5,
+		.name     = "Constant polynomial at x=0",
+	},
+	{
+		.poly     = &poly_constant,
+		.data     = 42,
+		.expected = 5,
+		.name     = "Constant polynomial is independent of input",
+	},
+	{
+		.poly     = &poly_simple,
+		.data     = 0,
+		.expected = 5,	/* zero input collapses all power terms */
+		.name     = "Zero input yields constant term only",
+	},
+	{
+		.poly     = &poly_simple,
+		.data     = 10,
+		.expected = 235,	/* 2*100 + 3*10 + 5 */
+		.name     = "Simple quadratic at x=10",
+	},
+	{
+		.poly     = &poly_negative_coef,
+		.data     = 10,
+		.expected = 50,		/* -5*10 + 100 */
+		.name     = "Negative coefficient at x=10",
+	},
+	{
+		.poly     = &poly_negative_coef,
+		.data     = 20,
+		.expected = 0,		/* -5*20 + 100 = 0 */
+		.name     = "Negative coefficient result is zero",
+	},
+	{
+		.poly     = &poly_total_divider,
+		.data     = 3,
+		.expected = 50,		/* (150*3 + 50) / 10 = 500/10 */
+		.name     = "total_divider scales the final sum",
+	},
+	{
+		.poly     = &poly_step_divider,
+		.data     = 100,
+		.expected = 50,		/* 1*100/2 */
+		.name     = "Per-step divider halves input",
+	},
+	{
+		.poly     = &poly_leftover,
+		.data     = 30,
+		.expected = 180,	/* 100*30^2 / (10^2 * 5) = 90000/500 */
+		.name     = "divider_leftover with quadratic term",
+	},
+	/* Boundary: unit and negative-unit input */
+	{
+		/*
+		 * data=1: each mult_frac(tmp, 1, divider) strips one factor of
+		 * divider from coef per degree, so coef is left-shifted right
+		 * until intermediate precision is exhausted.
+		 * 2*1 + 3*1 + 5 = 10
+		 */
+		.poly     = &poly_simple,
+		.data     = 1,
+		.expected = 10,
+		.name     = "Boundary: data=1 (unit input)",
+	},
+	{
+		/*
+		 * data=-1: even degrees produce positive contributions,
+		 * odd degrees produce negative ones.
+		 * 2*(-1)^2 + 3*(-1) + 5 = 2 - 3 + 5 = 4
+		 */
+		.poly     = &poly_simple,
+		.data     = -1,
+		.expected = 4,
+		.name     = "Boundary: data=-1 (negative unit input)",
+	},
+
+	/* Boundary: negative non-trivial input */
+	{
+		/*
+		 * 2*(-3)^2 + 3*(-3) + 5 = 18 - 9 + 5 = 14
+		 * Verifies sign handling for negative data across all degrees.
+		 */
+		.poly     = &poly_simple,
+		.data     = -3,
+		.expected = 14,
+		.name     = "Boundary: negative data with quadratic",
+	},
+
+	/* Boundary: total_divider = 0 is treated as 1 */
+	{
+		.poly     = &poly_zero_total_divider,
+		.data     = 42,
+		.expected = 9,
+		.name     = "Boundary: total_divider=0 defaults to 1",
+	},
+
+	/* Boundary: zero-coefficient high-degree term */
+	{
+		/*
+		 * The deg-2 term has coef=0, so it contributes 0 regardless
+		 * of data. Result: 0 + 4*10 + 1 = 41
+		 */
+		.poly     = &poly_zero_coef,
+		.data     = 10,
+		.expected = 41,
+		.name     = "Boundary: zero-coefficient term is inert",
+	},
+
+	/* Boundary: single high-degree term, no constant */
+	{
+		/* 2 * 5^3 = 250; also verifies the loop terminates on deg-0 */
+		.poly     = &poly_cubic,
+		.data     = 5,
+		.expected = 250,
+		.name     = "Boundary: single cubic term",
+	},
+	{
+		/* 2 * (-2)^3 = -16; odd power preserves sign of negative data */
+		.poly     = &poly_cubic,
+		.data     = -2,
+		.expected = -16,
+		.name     = "Boundary: single cubic term, negative data",
+	},
+
+};
+
+static void get_desc(const struct polynomial_test_param *param, char *desc)
+{
+	strscpy(desc, param->name, KUNIT_PARAM_DESC_SIZE);
+}
+
+KUNIT_ARRAY_PARAM(polynomial, test_params, get_desc);
+
+static void polynomial_calc_test(struct kunit *test)
+{
+	const struct polynomial_test_param *param = test->param_value;
+
+	KUNIT_EXPECT_EQ(test, polynomial_calc(param->poly, param->data),
+			param->expected);
+}
+
+static struct kunit_case polynomial_test_cases[] = {
+	KUNIT_CASE_PARAM(polynomial_calc_test, polynomial_gen_params),
+	{}
+};
+
+static struct kunit_suite polynomial_test_suite = {
+	.name = "math-polynomial",
+	.test_cases = polynomial_test_cases,
+};
+
+kunit_test_suites(&polynomial_test_suite);
+
+MODULE_DESCRIPTION("math.polynomial_calc KUnit test suite");
+MODULE_LICENSE("GPL");
diff --git a/lib/raid/Kconfig b/lib/raid/Kconfig
index 978cd6ba08ac..01f007b2522c 100644
--- a/lib/raid/Kconfig
+++ b/lib/raid/Kconfig
@@ -29,6 +29,12 @@ config XOR_KUNIT_TEST
 	  This is intended to help people writing architecture-specific
 	  optimized versions.  If unsure, say N.
 
+config XOR_BENCHMARK
+	bool "Benchmark for xor_gen"
+	depends on XOR_KUNIT_TEST
+	help
+	  Include benchmarks in the KUnit test suite for xor_gen.
+
 config RAID6_PQ
 	tristate
 
@@ -54,6 +60,12 @@ config RAID6_PQ_KUNIT_TEST
 	  This is intended to help people writing architecture-specific
 	  optimized versions.  If unsure, say N.
 
+config RAID6_PQ_KUNIT_BENCHMARK
+	bool "Benchmark for RAID6 PQ"
+	depends on RAID6_PQ_KUNIT_TEST
+	help
+	  Include benchmarks in the KUnit test suite for raid P/Q generation.
+
 config RAID6_PQ_BENCHMARK
 	bool "Automatically choose fastest RAID6 PQ functions"
 	depends on RAID6_PQ
diff --git a/lib/raid/raid6/Makefile b/lib/raid/raid6/Makefile
index 038d6c74d1ba..5cdb7223de2a 100644
--- a/lib/raid/raid6/Makefile
+++ b/lib/raid/raid6/Makefile
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
+CONTEXT_ANALYSIS := y
+
 ccflags-y			+= -I $(src)
 
 ifeq ($(CONFIG_RAID6_PQ_ARCH),y)
diff --git a/lib/raid/raid6/algos.c b/lib/raid/raid6/algos.c
index 6f5c89ab2b17..011aa9d0eb3c 100644
--- a/lib/raid/raid6/algos.c
+++ b/lib/raid/raid6/algos.c
@@ -152,40 +152,37 @@ void raid6_recov_datap(int disks, size_t bytes, int faila, void **ptrs)
 }
 EXPORT_SYMBOL_GPL(raid6_recov_datap);
 
-#define RAID6_TIME_JIFFIES_LG2	4
-#define RAID6_TEST_DISKS	8
+#define BENCH_SIZE	SZ_4K
+#define NR_SRCS		8
+#define NR_DISKS	(NR_SRCS + 2)
+#define REPS		800U
 
-static int raid6_choose_gen(void *(*const dptrs)[RAID6_TEST_DISKS],
-		const int disks)
+static int raid6_choose_gen(void *dptrs[NR_DISKS], const int disks)
 {
-	/* work on the second half of the disks */
-	int start = (disks >> 1) - 1, stop = disks - 3;
 	const struct raid6_calls *best = NULL;
 	unsigned long bestgenperf = 0;
 	unsigned int i;
 
 	for (i = 0; i < raid6_nr_algos; i++) {
 		const struct raid6_calls *algo = raid6_algos[i];
-		unsigned long perf = 0, j0, j1;
+		unsigned long perf = 0;
+		u64 t;
+		int i;
 
 		preempt_disable();
-		j0 = jiffies;
-		while ((j1 = jiffies) == j0)
-			cpu_relax();
-		while (time_before(jiffies,
-				    j1 + (1<<RAID6_TIME_JIFFIES_LG2))) {
-			algo->gen_syndrome(disks, PAGE_SIZE, *dptrs);
-			perf++;
-		}
+		t = ktime_get_ns();
+		for (i = 0; i < REPS; i++)
+			algo->gen_syndrome(disks, BENCH_SIZE, dptrs);
+		t = max(ktime_get_ns() - t, 1);
 		preempt_enable();
 
+		/* bytes/ns == GB/s, multiply by 1000 to get MB/s [not MiB/s] */
+		perf = div64_u64((u64)BENCH_SIZE * REPS * NR_SRCS * 1000, t);
 		if (perf > bestgenperf) {
 			bestgenperf = perf;
 			best = algo;
 		}
-		pr_info("raid6: %-8s gen() %5ld MB/s\n", algo->name,
-			(perf * HZ * (disks-2)) >>
-			(20 - PAGE_SHIFT + RAID6_TIME_JIFFIES_LG2));
+		pr_info("raid6: %-8s gen() %5lu MB/s\n", algo->name, perf);
 	}
 
 	if (!best) {
@@ -197,28 +194,24 @@ static int raid6_choose_gen(void *(*const dptrs)[RAID6_TEST_DISKS],
 	static_call_update(raid6_xor_syndrome_impl, best->xor_syndrome);
 
 	pr_info("raid6: using algorithm %s gen() %ld MB/s\n",
-		best->name,
-		(bestgenperf * HZ * (disks - 2)) >>
-		(20 - PAGE_SHIFT + RAID6_TIME_JIFFIES_LG2));
+		best->name, bestgenperf);
 
 	if (best->xor_syndrome) {
-		unsigned long perf = 0, j0, j1;
+		/* work on the second half of the disks */
+		int start = (disks / 2) - 1, stop = disks - 3;
+		u64 t;
 
 		preempt_disable();
-		j0 = jiffies;
-		while ((j1 = jiffies) == j0)
-			cpu_relax();
-		while (time_before(jiffies,
-				   j1 + (1 << RAID6_TIME_JIFFIES_LG2))) {
-			best->xor_syndrome(disks, start, stop,
-					   PAGE_SIZE, *dptrs);
-			perf++;
-		}
+		t = ktime_get_ns();
+		for (i = 0; i < REPS; i++)
+			best->xor_syndrome(disks, start, stop, BENCH_SIZE,
+				dptrs);
+		t = max(ktime_get_ns() - t, 1);
 		preempt_enable();
 
-		pr_info("raid6: .... xor() %ld MB/s, rmw enabled\n",
-			(perf * HZ * (disks - 2)) >>
-			(20 - PAGE_SHIFT + RAID6_TIME_JIFFIES_LG2 + 1));
+		pr_info("raid6: .... xor() %llu MB/s, rmw enabled\n",
+			div64_u64((u64)BENCH_SIZE * REPS * NR_SRCS / 2 * 1000,
+				t));
 	}
 
 	return 0;
@@ -230,24 +223,20 @@ static int raid6_choose_gen(void *(*const dptrs)[RAID6_TEST_DISKS],
 
 static int __init raid6_select_algo(void)
 {
-	const int disks = RAID6_TEST_DISKS;
+	const int disks = NR_DISKS;
+	void *dptrs[NR_DISKS];
 	char *disk_ptr, *p;
-	void *dptrs[RAID6_TEST_DISKS];
 	int i, cycle;
 	int error;
 
 	if (!IS_ENABLED(CONFIG_RAID6_PQ_BENCHMARK) || raid6_nr_algos == 1) {
 		pr_info("raid6: skipped pq benchmark and selected %s\n",
 			raid6_algos[raid6_nr_algos - 1]->name);
-		static_call_update(raid6_gen_syndrome_impl,
-				raid6_algos[raid6_nr_algos - 1]->gen_syndrome);
-		static_call_update(raid6_xor_syndrome_impl,
-				raid6_algos[raid6_nr_algos - 1]->xor_syndrome);
 		return 0;
 	}
 
 	/* prepare the buffer and fill it circularly with gfmul table */
-	disk_ptr = kmalloc(PAGE_SIZE * RAID6_TEST_DISKS, GFP_KERNEL);
+	disk_ptr = kmalloc_array(NR_DISKS, BENCH_SIZE, GFP_KERNEL);
 	if (!disk_ptr) {
 		pr_err("raid6: Yikes!  No memory available.\n");
 		return -ENOMEM;
@@ -255,19 +244,19 @@ static int __init raid6_select_algo(void)
 
 	p = disk_ptr;
 	for (i = 0; i < disks; i++)
-		dptrs[i] = p + PAGE_SIZE * i;
+		dptrs[i] = p + BENCH_SIZE * i;
 
-	cycle = ((disks - 2) * PAGE_SIZE) / 65536;
+	cycle = ((disks - 2) * BENCH_SIZE) / 65536;
 	for (i = 0; i < cycle; i++) {
 		memcpy(p, raid6_gfmul, 65536);
 		p += 65536;
 	}
 
-	if ((disks - 2) * PAGE_SIZE % 65536)
-		memcpy(p, raid6_gfmul, (disks - 2) * PAGE_SIZE % 65536);
+	if ((disks - 2) * BENCH_SIZE % 65536)
+		memcpy(p, raid6_gfmul, (disks - 2) * BENCH_SIZE % 65536);
 
 	/* select raid gen_syndrome function */
-	error = raid6_choose_gen(&dptrs, disks);
+	error = raid6_choose_gen(dptrs, disks);
 
 	kfree(disk_ptr);
 
@@ -329,13 +318,34 @@ static int __init raid6_init(void)
 	static_call_update(raid6_recov_datap_impl, raid6_recov_algo->datap);
 	pr_info("raid6: using %s recovery algorithm\n", raid6_recov_algo->name);
 
+	/*
+	 * Pick the last registered implementation as the temporary default until
+	 * calibration happens.
+	 */
+	static_call_update(raid6_gen_syndrome_impl,
+			raid6_algos[raid6_nr_algos - 1]->gen_syndrome);
+	static_call_update(raid6_xor_syndrome_impl,
+			raid6_algos[raid6_nr_algos - 1]->xor_syndrome);
+
+#ifdef MODULE
 	return raid6_select_algo();
+#else
+	return 0;
+#endif
 }
 
 static void __exit raid6_exit(void)
 {
 }
 
+/*
+ * When built-in we must register the default implementation before md
+ * initializes, but we don't want calibration to run that early as that
+ * would delay the boot process.
+ */
+#ifndef MODULE
+device_initcall(raid6_select_algo);
+#endif
 subsys_initcall(raid6_init);
 module_exit(raid6_exit);
 MODULE_LICENSE("GPL");
diff --git a/lib/raid/raid6/tests/raid6_kunit.c b/lib/raid/raid6/tests/raid6_kunit.c
index 9f3e671a1224..7d0a1ec98001 100644
--- a/lib/raid/raid6/tests/raid6_kunit.c
+++ b/lib/raid/raid6/tests/raid6_kunit.c
@@ -18,6 +18,7 @@ MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
 #define RAID6_KUNIT_MAX_BUFFERS		64 /* Including P and Q */
 #define RAID6_KUNIT_MAX_FAILURES	2
 #define RAID6_KUNIT_MAX_BYTES		PAGE_SIZE
+#define RAID6_KUNIT_ALLOC_BYTES		SZ_16K
 
 static struct rnd_state rng;
 static void *test_buffers[RAID6_KUNIT_MAX_BUFFERS];
@@ -229,6 +230,68 @@ static void raid6_test(struct kunit *test)
 		raid6_test_one(test);
 }
 
+static void raid6_benchmark(struct kunit *test)
+{
+	static const unsigned int nr_to_test[] = {
+		4, 5, 6, 7, 8, 10, 12, 15, 16, 32,
+	};
+	static const unsigned int len_to_test[] = {
+		SZ_4K, SZ_16K,
+	};
+	unsigned int i, j, l;
+	u64 t;
+
+	if (!IS_ENABLED(CONFIG_RAID6_PQ_KUNIT_BENCHMARK))
+		kunit_skip(test, "not enabled");
+
+	/* warm-up */
+	for (i = 0; i < ARRAY_SIZE(nr_to_test); i++) {
+		for (j = 0; j < ARRAY_SIZE(len_to_test); j++) {
+			for (l = 0; l < 10; l++) {
+				raid6_gen_syndrome(nr_to_test[i],
+						len_to_test[j], test_buffers);
+			}
+		}
+	}
+
+	/*
+	 * Preferably this would be a loop over len_to_test, but the kunit
+	 * logging always adds a newline to each logged format string.
+	 */
+	static_assert(ARRAY_SIZE(len_to_test) == 2);
+	kunit_info(test, "          \t%5u bytes\t%5u bytes\n",
+			len_to_test[0], len_to_test[1]);
+
+	for (i = 0; i < ARRAY_SIZE(nr_to_test); i++) {
+		unsigned int nr = nr_to_test[i];
+		u64 speed[ARRAY_SIZE(len_to_test)];
+
+		KUNIT_ASSERT_LE(test, nr, RAID6_KUNIT_MAX_BUFFERS);
+
+		for (j = 0; j < ARRAY_SIZE(len_to_test); j++) {
+			unsigned int len = len_to_test[j];
+			const unsigned long num_iters = 1000;
+
+			KUNIT_ASSERT_GT(test, len, 0);
+			KUNIT_ASSERT_LE(test, len, RAID6_KUNIT_ALLOC_BYTES);
+
+			preempt_disable();
+			t = ktime_get_ns();
+			for (l = 0; l < num_iters; l++)
+				raid6_gen_syndrome(nr_to_test[i],
+						len_to_test[j], test_buffers);
+			t = max(ktime_get_ns() - t, 1);
+			preempt_enable();
+
+			speed[j] = div64_u64((u64)len * num_iters * nr, t);
+		}
+
+		static_assert(ARRAY_SIZE(len_to_test) == 2);
+		kunit_info(test, "%3u disks:\t%5llu  GB/s\t%5llu  GB/s\n",
+				nr, speed[0], speed[1]);
+	}
+}
+
 static const void *raid6_gen_params(struct kunit *test, const void *prev,
 		char *desc)
 {
@@ -256,6 +319,7 @@ next_algo:
 
 static struct kunit_case raid6_test_cases[] = {
 	KUNIT_CASE_PARAM(raid6_test, raid6_gen_params),
+	KUNIT_CASE(raid6_benchmark),
 	{},
 };
 
@@ -270,7 +334,7 @@ static int raid6_suite_init(struct kunit_suite *suite)
 	 * so that it is immediately followed by a guard page.  This allows
 	 * buffer overreads to be detected, even in assembly code.
 	 */
-	test_buflen = round_up(RAID6_KUNIT_MAX_BYTES, PAGE_SIZE);
+	test_buflen = round_up(RAID6_KUNIT_ALLOC_BYTES, PAGE_SIZE);
 	for (i = 0; i < RAID6_KUNIT_MAX_FAILURES; i++) {
 		test_recov_buffers[i] = vmalloc(test_buflen);
 		if (!test_recov_buffers[i])
diff --git a/lib/raid/xor/Makefile b/lib/raid/xor/Makefile
index e8ecec3c09f9..9b0fad459cdb 100644
--- a/lib/raid/xor/Makefile
+++ b/lib/raid/xor/Makefile
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
+CONTEXT_ANALYSIS := y
+
 ccflags-y			+= -I $(src)
 
 obj-$(CONFIG_XOR_BLOCKS)	+= xor.o
diff --git a/lib/raid/xor/tests/Makefile b/lib/raid/xor/tests/Makefile
index 661e8f6ffd1f..1cce833cd7fd 100644
--- a/lib/raid/xor/tests/Makefile
+++ b/lib/raid/xor/tests/Makefile
@@ -1,3 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
+CONTEXT_ANALYSIS := y
+
 obj-$(CONFIG_XOR_KUNIT_TEST) += xor_kunit.o
diff --git a/lib/raid/xor/tests/xor_kunit.c b/lib/raid/xor/tests/xor_kunit.c
index 0c2a3a420bf9..1fb30b2c7c47 100644
--- a/lib/raid/xor/tests/xor_kunit.c
+++ b/lib/raid/xor/tests/xor_kunit.c
@@ -85,7 +85,7 @@ static void xor_test(struct kunit *test)
 			xor_generate_random_data();
 
 		/*
-		 * If we're not using the entire buffer size, inject randomize
+		 * If we're not using the entire buffer size, inject randomized
 		 * alignment into the buffer.
 		 */
 		max_alignment = XOR_KUNIT_MAX_BYTES - len;
@@ -125,8 +125,70 @@ static void xor_test(struct kunit *test)
 	}
 }
 
+static void xor_benchmark(struct kunit *test)
+{
+	static const unsigned int nr_to_test[] = {
+		4, 5, 6, 7, 8, 10, 12, 15, 16, 32,
+	};
+	static const unsigned int len_to_test[] = {
+		SZ_4K, SZ_16K,
+	};
+	unsigned int i, j, l;
+	u64 t;
+
+	if (!IS_ENABLED(CONFIG_XOR_BENCHMARK))
+		kunit_skip(test, "not enabled");
+
+	/* warm-up */
+	for (i = 0; i < ARRAY_SIZE(nr_to_test); i++) {
+		for (j = 0; j < ARRAY_SIZE(len_to_test); j++) {
+			for (l = 0; l < 10; l++) {
+				xor_gen(test_dest, test_buffers, nr_to_test[i],
+						len_to_test[j]);
+			}
+		}
+	}
+
+	/*
+	 * Preferably this would be a loop over len_to_test, but the kunit
+	 * logging always adds a newline to each logged format string.
+	 */
+	static_assert(ARRAY_SIZE(len_to_test) == 2);
+	kunit_info(test, "          \t%5u bytes\t%5u bytes\n",
+			len_to_test[0], len_to_test[1]);
+
+	for (i = 0; i < ARRAY_SIZE(nr_to_test); i++) {
+		unsigned int nr = nr_to_test[i];
+		u64 speed[ARRAY_SIZE(len_to_test)];
+
+		KUNIT_ASSERT_LE(test, nr, XOR_KUNIT_MAX_BUFFERS);
+
+		for (j = 0; j < ARRAY_SIZE(len_to_test); j++) {
+			unsigned int len = len_to_test[j];
+			const unsigned long num_iters = 1000;
+
+			KUNIT_ASSERT_GT(test, len, 0);
+			KUNIT_ASSERT_LE(test, len, XOR_KUNIT_MAX_BYTES);
+
+			preempt_disable();
+			t = ktime_get_ns();
+			for (l = 0; l < num_iters; l++)
+				xor_gen(test_dest, test_buffers, nr, len);
+			t = max(ktime_get_ns() - t, 1);
+			preempt_enable();
+
+			speed[j] = div64_u64((u64)len * num_iters * nr, t);
+		}
+
+		static_assert(ARRAY_SIZE(len_to_test) == 2);
+		kunit_info(test, "%3u disks:\t%5llu  GB/s\t%5llu  GB/s\n",
+				nr, speed[0], speed[1]);
+	}
+}
+
 static struct kunit_case xor_test_cases[] = {
 	KUNIT_CASE(xor_test),
+	KUNIT_CASE(xor_benchmark),
 	{},
 };
 
diff --git a/lib/raid/xor/xor-core.c b/lib/raid/xor/xor-core.c
index 50931fbf0324..f9d61b096b11 100644
--- a/lib/raid/xor/xor-core.c
+++ b/lib/raid/xor/xor-core.c
@@ -10,7 +10,6 @@
 #include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/raid/xor.h>
-#include <linux/jiffies.h>
 #include <linux/preempt.h>
 #include <linux/static_call.h>
 #include "xor_impl.h"
@@ -73,59 +72,56 @@ void __init xor_force(struct xor_block_template *tmpl)
 	forced_template = tmpl;
 }
 
-#define BENCH_SIZE	4096
+#define BENCH_SIZE	SZ_4K
+#define NR_SRCS		4
 #define REPS		800U
 
-static void __init
-do_xor_speed(struct xor_block_template *tmpl, void *b1, void *b2)
+static void __init do_xor_speed(struct xor_block_template *tmpl, void *dest,
+		void *srcs[NR_SRCS])
 {
-	int speed;
-	unsigned long reps;
-	ktime_t min, start, t0;
-	void *srcs[1] = { b2 };
+	u64 t;
+	int i;
 
 	preempt_disable();
-
-	reps = 0;
-	t0 = ktime_get();
-	/* delay start until time has advanced */
-	while ((start = ktime_get()) == t0)
-		cpu_relax();
-	do {
+	t = ktime_get_ns();
+	for (i = 0; i < REPS; i++) {
 		mb(); /* prevent loop optimization */
-		tmpl->xor_gen(b1, srcs, 1, BENCH_SIZE);
+		tmpl->xor_gen(dest, srcs, NR_SRCS, BENCH_SIZE);
 		mb();
-	} while (reps++ < REPS || (t0 = ktime_get()) == start);
-	min = ktime_sub(t0, start);
-
+	}
+	t = max(ktime_get_ns() - t, 1);
 	preempt_enable();
 
-	// bytes/ns == GB/s, multiply by 1000 to get MB/s [not MiB/s]
-	speed = (1000 * reps * BENCH_SIZE) / (unsigned int)ktime_to_ns(min);
-	tmpl->speed = speed;
+	/* bytes/ns == GB/s, multiply by 1000 to get MB/s [not MiB/s] */
+	tmpl->speed = div64_u64((u64)BENCH_SIZE * REPS * NR_SRCS * 1000, t);
 
-	pr_info("   %-16s: %5d MB/sec\n", tmpl->name, speed);
+	pr_info("   %-16s: %5d MB/sec\n", tmpl->name, tmpl->speed);
 }
 
 static int __init calibrate_xor_blocks(void)
 {
-	void *b1, *b2;
 	struct xor_block_template *f, *fastest;
+	void *srcs[NR_SRCS];
+	void *buf, *dest;
+	int i;
 
 	if (forced_template)
 		return 0;
 
-	b1 = kmalloc(PAGE_SIZE * 4, GFP_KERNEL);
-	if (!b1) {
+	buf = kmalloc(BENCH_SIZE * (NR_SRCS + 1), GFP_KERNEL);
+	if (!buf) {
 		pr_warn("xor: Yikes!  No memory available.\n");
 		return -ENOMEM;
 	}
-	b2 = b1 + 2*PAGE_SIZE + BENCH_SIZE;
+	get_random_bytes(buf, BENCH_SIZE * (NR_SRCS + 1));
+	dest = buf;
+	for (i = 0; i < NR_SRCS; i++)
+		srcs[i] = buf + (i + 1) * BENCH_SIZE;
 
 	pr_info("xor: measuring software checksum speed\n");
 	fastest = template_list;
 	for (f = template_list; f; f = f->next) {
-		do_xor_speed(f, b1, b2);
+		do_xor_speed(f, dest, srcs);
 		if (f->speed > fastest->speed)
 			fastest = f;
 	}
@@ -133,9 +129,10 @@ static int __init calibrate_xor_blocks(void)
 	pr_info("xor: using function: %s (%d MB/sec)\n",
 	       fastest->name, fastest->speed);
 
-	kfree(b1);
+	kfree(buf);
 	return 0;
 }
+#undef NR_SRCS
 
 #ifdef CONFIG_XOR_BLOCKS_ARCH
 #include "xor_arch.h" /* $SRCARCH/xor_arch.h */
diff --git a/lib/random32.c b/lib/random32.c
index 24e7acd9343f..dad90219c351 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -41,6 +41,7 @@
 #include <linux/bitops.h>
 #include <linux/slab.h>
 #include <linux/unaligned.h>
+#include <kunit/visibility.h>
 
 /**
  *	prandom_u32_state - seeded pseudo-random number generator.
@@ -92,7 +93,14 @@ void prandom_bytes_state(struct rnd_state *state, void *buf, size_t bytes)
 }
 EXPORT_SYMBOL(prandom_bytes_state);
 
-static void prandom_warmup(struct rnd_state *state)
+/*
+ * Only declared here so that it has a prototype when made
+ * non-static for KUnit testing (avoids -Wmissing-prototypes).
+ */
+#if IS_ENABLED(CONFIG_KUNIT)
+void prandom_warmup(struct rnd_state *state);
+#endif
+VISIBLE_IF_KUNIT void prandom_warmup(struct rnd_state *state)
 {
 	/* Calling RNG ten times to satisfy recurrence condition */
 	prandom_u32_state(state);
@@ -106,6 +114,7 @@ static void prandom_warmup(struct rnd_state *state)
 	prandom_u32_state(state);
 	prandom_u32_state(state);
 }
+EXPORT_SYMBOL_IF_KUNIT(prandom_warmup);
 
 void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state)
 {
@@ -125,176 +134,3 @@ void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state)
 	}
 }
 EXPORT_SYMBOL(prandom_seed_full_state);
-
-#ifdef CONFIG_RANDOM32_SELFTEST
-static struct prandom_test1 {
-	u32 seed;
-	u32 result;
-} test1[] = {
-	{ 1U, 3484351685U },
-	{ 2U, 2623130059U },
-	{ 3U, 3125133893U },
-	{ 4U,  984847254U },
-};
-
-static struct prandom_test2 {
-	u32 seed;
-	u32 iteration;
-	u32 result;
-} test2[] = {
-	/* Test cases against taus113 from GSL library. */
-	{  931557656U, 959U, 2975593782U },
-	{ 1339693295U, 876U, 3887776532U },
-	{ 1545556285U, 961U, 1615538833U },
-	{  601730776U, 723U, 1776162651U },
-	{ 1027516047U, 687U,  511983079U },
-	{  416526298U, 700U,  916156552U },
-	{ 1395522032U, 652U, 2222063676U },
-	{  366221443U, 617U, 2992857763U },
-	{ 1539836965U, 714U, 3783265725U },
-	{  556206671U, 994U,  799626459U },
-	{  684907218U, 799U,  367789491U },
-	{ 2121230701U, 931U, 2115467001U },
-	{ 1668516451U, 644U, 3620590685U },
-	{  768046066U, 883U, 2034077390U },
-	{ 1989159136U, 833U, 1195767305U },
-	{  536585145U, 996U, 3577259204U },
-	{ 1008129373U, 642U, 1478080776U },
-	{ 1740775604U, 939U, 1264980372U },
-	{ 1967883163U, 508U,   10734624U },
-	{ 1923019697U, 730U, 3821419629U },
-	{  442079932U, 560U, 3440032343U },
-	{ 1961302714U, 845U,  841962572U },
-	{ 2030205964U, 962U, 1325144227U },
-	{ 1160407529U, 507U,  240940858U },
-	{  635482502U, 779U, 4200489746U },
-	{ 1252788931U, 699U,  867195434U },
-	{ 1961817131U, 719U,  668237657U },
-	{ 1071468216U, 983U,  917876630U },
-	{ 1281848367U, 932U, 1003100039U },
-	{  582537119U, 780U, 1127273778U },
-	{ 1973672777U, 853U, 1071368872U },
-	{ 1896756996U, 762U, 1127851055U },
-	{  847917054U, 500U, 1717499075U },
-	{ 1240520510U, 951U, 2849576657U },
-	{ 1685071682U, 567U, 1961810396U },
-	{ 1516232129U, 557U,    3173877U },
-	{ 1208118903U, 612U, 1613145022U },
-	{ 1817269927U, 693U, 4279122573U },
-	{ 1510091701U, 717U,  638191229U },
-	{  365916850U, 807U,  600424314U },
-	{  399324359U, 702U, 1803598116U },
-	{ 1318480274U, 779U, 2074237022U },
-	{  697758115U, 840U, 1483639402U },
-	{ 1696507773U, 840U,  577415447U },
-	{ 2081979121U, 981U, 3041486449U },
-	{  955646687U, 742U, 3846494357U },
-	{ 1250683506U, 749U,  836419859U },
-	{  595003102U, 534U,  366794109U },
-	{   47485338U, 558U, 3521120834U },
-	{  619433479U, 610U, 3991783875U },
-	{  704096520U, 518U, 4139493852U },
-	{ 1712224984U, 606U, 2393312003U },
-	{ 1318233152U, 922U, 3880361134U },
-	{  855572992U, 761U, 1472974787U },
-	{   64721421U, 703U,  683860550U },
-	{  678931758U, 840U,  380616043U },
-	{  692711973U, 778U, 1382361947U },
-	{  677703619U, 530U, 2826914161U },
-	{   92393223U, 586U, 1522128471U },
-	{ 1222592920U, 743U, 3466726667U },
-	{  358288986U, 695U, 1091956998U },
-	{ 1935056945U, 958U,  514864477U },
-	{  735675993U, 990U, 1294239989U },
-	{ 1560089402U, 897U, 2238551287U },
-	{   70616361U, 829U,   22483098U },
-	{  368234700U, 731U, 2913875084U },
-	{   20221190U, 879U, 1564152970U },
-	{  539444654U, 682U, 1835141259U },
-	{ 1314987297U, 840U, 1801114136U },
-	{ 2019295544U, 645U, 3286438930U },
-	{  469023838U, 716U, 1637918202U },
-	{ 1843754496U, 653U, 2562092152U },
-	{  400672036U, 809U, 4264212785U },
-	{  404722249U, 965U, 2704116999U },
-	{  600702209U, 758U,  584979986U },
-	{  519953954U, 667U, 2574436237U },
-	{ 1658071126U, 694U, 2214569490U },
-	{  420480037U, 749U, 3430010866U },
-	{  690103647U, 969U, 3700758083U },
-	{ 1029424799U, 937U, 3787746841U },
-	{ 2012608669U, 506U, 3362628973U },
-	{ 1535432887U, 998U,   42610943U },
-	{ 1330635533U, 857U, 3040806504U },
-	{ 1223800550U, 539U, 3954229517U },
-	{ 1322411537U, 680U, 3223250324U },
-	{ 1877847898U, 945U, 2915147143U },
-	{ 1646356099U, 874U,  965988280U },
-	{  805687536U, 744U, 4032277920U },
-	{ 1948093210U, 633U, 1346597684U },
-	{  392609744U, 783U, 1636083295U },
-	{  690241304U, 770U, 1201031298U },
-	{ 1360302965U, 696U, 1665394461U },
-	{ 1220090946U, 780U, 1316922812U },
-	{  447092251U, 500U, 3438743375U },
-	{ 1613868791U, 592U,  828546883U },
-	{  523430951U, 548U, 2552392304U },
-	{  726692899U, 810U, 1656872867U },
-	{ 1364340021U, 836U, 3710513486U },
-	{ 1986257729U, 931U,  935013962U },
-	{  407983964U, 921U,  728767059U },
-};
-
-static void prandom_state_selftest_seed(struct rnd_state *state, u32 seed)
-{
-#define LCG(x)	 ((x) * 69069U)	/* super-duper LCG */
-	state->s1 = __seed(LCG(seed),        2U);
-	state->s2 = __seed(LCG(state->s1),   8U);
-	state->s3 = __seed(LCG(state->s2),  16U);
-	state->s4 = __seed(LCG(state->s3), 128U);
-}
-
-static int __init prandom_state_selftest(void)
-{
-	int i, j, errors = 0, runs = 0;
-	bool error = false;
-
-	for (i = 0; i < ARRAY_SIZE(test1); i++) {
-		struct rnd_state state;
-
-		prandom_state_selftest_seed(&state, test1[i].seed);
-		prandom_warmup(&state);
-
-		if (test1[i].result != prandom_u32_state(&state))
-			error = true;
-	}
-
-	if (error)
-		pr_warn("prandom: seed boundary self test failed\n");
-	else
-		pr_info("prandom: seed boundary self test passed\n");
-
-	for (i = 0; i < ARRAY_SIZE(test2); i++) {
-		struct rnd_state state;
-
-		prandom_state_selftest_seed(&state, test2[i].seed);
-		prandom_warmup(&state);
-
-		for (j = 0; j < test2[i].iteration - 1; j++)
-			prandom_u32_state(&state);
-
-		if (test2[i].result != prandom_u32_state(&state))
-			errors++;
-
-		runs++;
-		cond_resched();
-	}
-
-	if (errors)
-		pr_warn("prandom: %d/%d self tests failed\n", errors, runs);
-	else
-		pr_info("prandom: %d self tests passed\n", runs);
-	return 0;
-}
-core_initcall(prandom_state_selftest);
-#endif
diff --git a/lib/string.c b/lib/string.c
index a4e8ad23577d..a3778d5aab4a 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -821,7 +821,8 @@ void *memchr_inv(const void *start, int c, size_t bytes)
 {
 	u8 value = c;
 	u64 value64;
-	unsigned int words, prefix;
+	size_t words;
+	unsigned int prefix;
 
 	if (bytes <= 16)
 		return check_bytes8(start, value, bytes);
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 6205fb313bd0..6e72a0d8a53d 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -1312,16 +1312,10 @@ static int dmirror_migrate_to_device(struct dmirror *dmirror,
 	if (!mmget_not_zero(mm))
 		return -EINVAL;
 
-	ret = -ENOMEM;
 	src_pfns = kvcalloc(PTRS_PER_PTE, sizeof(*src_pfns),
 			  GFP_KERNEL | __GFP_NOFAIL);
-	if (!src_pfns)
-		goto free_mem;
-
 	dst_pfns = kvcalloc(PTRS_PER_PTE, sizeof(*dst_pfns),
 			  GFP_KERNEL | __GFP_NOFAIL);
-	if (!dst_pfns)
-		goto free_mem;
 
 	ret = 0;
 	mmap_read_lock(mm);
diff --git a/lib/tests/Makefile b/lib/tests/Makefile
index 4ead57602eac..3cac3b63a752 100644
--- a/lib/tests/Makefile
+++ b/lib/tests/Makefile
@@ -41,8 +41,7 @@ obj-$(CONFIG_MEMCPY_KUNIT_TEST) += memcpy_kunit.o
 obj-$(CONFIG_MIN_HEAP_KUNIT_TEST) += min_heap_kunit.o
 CFLAGS_overflow_kunit.o = $(call cc-disable-warning, tautological-constant-out-of-range-compare)
 obj-$(CONFIG_OVERFLOW_KUNIT_TEST) += overflow_kunit.o
-# GCC < 12.1 can miscompile errptr() test when branch profiling is enabled.
-CFLAGS_printf_kunit.o += -DDISABLE_BRANCH_PROFILING
+obj-$(CONFIG_PRANDOM_KUNIT_TEST) += random32_kunit.o
 obj-$(CONFIG_PRINTF_KUNIT_TEST) += printf_kunit.o
 obj-$(CONFIG_RANDSTRUCT_KUNIT_TEST) += randstruct_kunit.o
 obj-$(CONFIG_SCANF_KUNIT_TEST) += scanf_kunit.o
diff --git a/lib/tests/random32_kunit.c b/lib/tests/random32_kunit.c
new file mode 100644
index 000000000000..0b4af2b09c01
--- /dev/null
+++ b/lib/tests/random32_kunit.c
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test cases for random32 functions.
+ */
+
+#include <linux/prandom.h>
+#include <kunit/test.h>
+
+/* prandom_warmup() is static in lib/random32.c; exposed for testing only. */
+void prandom_warmup(struct rnd_state *state);
+
+static const struct prandom_test1 {
+	u32 seed;
+	u32 result;
+} test1[] = {
+	{ 1U, 3484351685U },
+	{ 2U, 2623130059U },
+	{ 3U, 3125133893U },
+	{ 4U,  984847254U },
+};
+
+static const struct prandom_test2 {
+	u32 seed;
+	u32 iteration;
+	u32 result;
+} test2[] = {
+	/* Test cases against taus113 from GSL library. */
+	{  931557656U, 959U, 2975593782U },
+	{ 1339693295U, 876U, 3887776532U },
+	{ 1545556285U, 961U, 1615538833U },
+	{  601730776U, 723U, 1776162651U },
+	{ 1027516047U, 687U,  511983079U },
+	{  416526298U, 700U,  916156552U },
+	{ 1395522032U, 652U, 2222063676U },
+	{  366221443U, 617U, 2992857763U },
+	{ 1539836965U, 714U, 3783265725U },
+	{  556206671U, 994U,  799626459U },
+	{  684907218U, 799U,  367789491U },
+	{ 2121230701U, 931U, 2115467001U },
+	{ 1668516451U, 644U, 3620590685U },
+	{  768046066U, 883U, 2034077390U },
+	{ 1989159136U, 833U, 1195767305U },
+	{  536585145U, 996U, 3577259204U },
+	{ 1008129373U, 642U, 1478080776U },
+	{ 1740775604U, 939U, 1264980372U },
+	{ 1967883163U, 508U,   10734624U },
+	{ 1923019697U, 730U, 3821419629U },
+	{  442079932U, 560U, 3440032343U },
+	{ 1961302714U, 845U,  841962572U },
+	{ 2030205964U, 962U, 1325144227U },
+	{ 1160407529U, 507U,  240940858U },
+	{  635482502U, 779U, 4200489746U },
+	{ 1252788931U, 699U,  867195434U },
+	{ 1961817131U, 719U,  668237657U },
+	{ 1071468216U, 983U,  917876630U },
+	{ 1281848367U, 932U, 1003100039U },
+	{  582537119U, 780U, 1127273778U },
+	{ 1973672777U, 853U, 1071368872U },
+	{ 1896756996U, 762U, 1127851055U },
+	{  847917054U, 500U, 1717499075U },
+	{ 1240520510U, 951U, 2849576657U },
+	{ 1685071682U, 567U, 1961810396U },
+	{ 1516232129U, 557U,    3173877U },
+	{ 1208118903U, 612U, 1613145022U },
+	{ 1817269927U, 693U, 4279122573U },
+	{ 1510091701U, 717U,  638191229U },
+	{  365916850U, 807U,  600424314U },
+	{  399324359U, 702U, 1803598116U },
+	{ 1318480274U, 779U, 2074237022U },
+	{  697758115U, 840U, 1483639402U },
+	{ 1696507773U, 840U,  577415447U },
+	{ 2081979121U, 981U, 3041486449U },
+	{  955646687U, 742U, 3846494357U },
+	{ 1250683506U, 749U,  836419859U },
+	{  595003102U, 534U,  366794109U },
+	{   47485338U, 558U, 3521120834U },
+	{  619433479U, 610U, 3991783875U },
+	{  704096520U, 518U, 4139493852U },
+	{ 1712224984U, 606U, 2393312003U },
+	{ 1318233152U, 922U, 3880361134U },
+	{  855572992U, 761U, 1472974787U },
+	{   64721421U, 703U,  683860550U },
+	{  678931758U, 840U,  380616043U },
+	{  692711973U, 778U, 1382361947U },
+	{  677703619U, 530U, 2826914161U },
+	{   92393223U, 586U, 1522128471U },
+	{ 1222592920U, 743U, 3466726667U },
+	{  358288986U, 695U, 1091956998U },
+	{ 1935056945U, 958U,  514864477U },
+	{  735675993U, 990U, 1294239989U },
+	{ 1560089402U, 897U, 2238551287U },
+	{   70616361U, 829U,   22483098U },
+	{  368234700U, 731U, 2913875084U },
+	{   20221190U, 879U, 1564152970U },
+	{  539444654U, 682U, 1835141259U },
+	{ 1314987297U, 840U, 1801114136U },
+	{ 2019295544U, 645U, 3286438930U },
+	{  469023838U, 716U, 1637918202U },
+	{ 1843754496U, 653U, 2562092152U },
+	{  400672036U, 809U, 4264212785U },
+	{  404722249U, 965U, 2704116999U },
+	{  600702209U, 758U,  584979986U },
+	{  519953954U, 667U, 2574436237U },
+	{ 1658071126U, 694U, 2214569490U },
+	{  420480037U, 749U, 3430010866U },
+	{  690103647U, 969U, 3700758083U },
+	{ 1029424799U, 937U, 3787746841U },
+	{ 2012608669U, 506U, 3362628973U },
+	{ 1535432887U, 998U,   42610943U },
+	{ 1330635533U, 857U, 3040806504U },
+	{ 1223800550U, 539U, 3954229517U },
+	{ 1322411537U, 680U, 3223250324U },
+	{ 1877847898U, 945U, 2915147143U },
+	{ 1646356099U, 874U,  965988280U },
+	{  805687536U, 744U, 4032277920U },
+	{ 1948093210U, 633U, 1346597684U },
+	{  392609744U, 783U, 1636083295U },
+	{  690241304U, 770U, 1201031298U },
+	{ 1360302965U, 696U, 1665394461U },
+	{ 1220090946U, 780U, 1316922812U },
+	{  447092251U, 500U, 3438743375U },
+	{ 1613868791U, 592U,  828546883U },
+	{  523430951U, 548U, 2552392304U },
+	{  726692899U, 810U, 1656872867U },
+	{ 1364340021U, 836U, 3710513486U },
+	{ 1986257729U, 931U,  935013962U },
+	{  407983964U, 921U,  728767059U },
+};
+
+static void prandom_state_test_seed(struct rnd_state *state, u32 seed)
+{
+#define LCG(x)	 ((x) * 69069U)	/* super-duper LCG */
+	state->s1 = __seed(LCG(seed),        2U);
+	state->s2 = __seed(LCG(state->s1),   8U);
+	state->s3 = __seed(LCG(state->s2),  16U);
+	state->s4 = __seed(LCG(state->s3), 128U);
+}
+
+static void test_prandom_seed_boundary(struct kunit *test)
+{
+	int i;
+	struct rnd_state state;
+
+	for (i = 0; i < ARRAY_SIZE(test1); i++) {
+		prandom_state_test_seed(&state, test1[i].seed);
+		prandom_warmup(&state);
+		KUNIT_EXPECT_EQ(test, test1[i].result, prandom_u32_state(&state));
+	}
+}
+
+static void test_prandom_taus113(struct kunit *test)
+{
+	int i, j;
+	struct rnd_state state;
+
+	for (i = 0; i < ARRAY_SIZE(test2); i++) {
+		prandom_state_test_seed(&state, test2[i].seed);
+		prandom_warmup(&state);
+
+		for (j = 0; j < test2[i].iteration - 1; j++)
+			prandom_u32_state(&state);
+
+		KUNIT_EXPECT_EQ(test, test2[i].result, prandom_u32_state(&state));
+	}
+}
+
+static struct kunit_case prandom_test_cases[] = {
+	KUNIT_CASE(test_prandom_seed_boundary),
+	KUNIT_CASE(test_prandom_taus113),
+	{}
+};
+
+static struct kunit_suite prandom_test_suite = {
+	.name = "prandom",
+	.test_cases = prandom_test_cases,
+};
+
+kunit_test_suite(prandom_test_suite);
+
+MODULE_DESCRIPTION("KUnit test for prandom");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c
index dfb4f2358cab..1f7dd4eb640a 100644
--- a/lib/ucs2_string.c
+++ b/lib/ucs2_string.c
@@ -6,18 +6,18 @@
 unsigned long
 ucs2_strnlen(const ucs2_char_t *s, size_t maxlength)
 {
-        unsigned long length = 0;
+	unsigned long length = 0;
 
-        while (*s++ != 0 && length < maxlength)
-                length++;
-        return length;
+	while (length < maxlength && *s++ != 0)
+		length++;
+	return length;
 }
 EXPORT_SYMBOL(ucs2_strnlen);
 
 unsigned long
 ucs2_strlen(const ucs2_char_t *s)
 {
-        return ucs2_strnlen(s, ~0UL);
+	return ucs2_strnlen(s, ~0UL);
 }
 EXPORT_SYMBOL(ucs2_strlen);
 
@@ -28,7 +28,7 @@ EXPORT_SYMBOL(ucs2_strlen);
 unsigned long
 ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength)
 {
-        return ucs2_strnlen(data, maxlength/sizeof(ucs2_char_t)) * sizeof(ucs2_char_t);
+	return ucs2_strnlen(data, maxlength/sizeof(ucs2_char_t)) * sizeof(ucs2_char_t);
 }
 EXPORT_SYMBOL(ucs2_strsize);
 
@@ -87,19 +87,19 @@ EXPORT_SYMBOL(ucs2_strscpy);
 int
 ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len)
 {
-        while (1) {
-                if (len == 0)
-                        return 0;
-                if (*a < *b)
-                        return -1;
-                if (*a > *b)
-                        return 1;
-                if (*a == 0) /* implies *b == 0 */
-                        return 0;
-                a++;
-                b++;
-                len--;
-        }
+	while (1) {
+		if (len == 0)
+			return 0;
+		if (*a < *b)
+			return -1;
+		if (*a > *b)
+			return 1;
+		if (*a == 0) /* implies *b == 0 */
+			return 0;
+		a++;
+		b++;
+		len--;
+	}
 }
 EXPORT_SYMBOL(ucs2_strncmp);
 
diff --git a/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c
index cc49a300a5b2..88922323f96e 100644
--- a/lib/xz/xz_dec_bcj.c
+++ b/lib/xz/xz_dec_bcj.c
@@ -466,7 +466,7 @@ static void bcj_flush(struct xz_dec_bcj *s, struct xz_buf *b)
 {
 	size_t copy_size;
 
-	copy_size = min_t(size_t, s->temp.filtered, b->out_size - b->out_pos);
+	copy_size = min(s->temp.filtered, b->out_size - b->out_pos);
 	memcpy(b->out + b->out_pos, s->temp.buf, copy_size);
 	b->out_pos += copy_size;
 
diff --git a/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c
index 4b783ac94e71..46c2df6ad6f5 100644
--- a/lib/xz/xz_dec_lzma2.c
+++ b/lib/xz/xz_dec_lzma2.c
@@ -135,14 +135,16 @@ struct lzma_dec {
 	uint32_t rep2;
 	uint32_t rep3;
 
-	/* Types of the most recently seen LZMA symbols */
-	enum lzma_state state;
-
 	/*
 	 * Length of a match. This is updated so that dict_repeat can
-	 * be called again to finish repeating the whole match.
+	 * be called again to finish repeating the whole match. This is
+	 * size_t because a pointer to this is passed to dict_repeat,
+	 * and there it's nicer to have size_t instead of uint32_t.
 	 */
-	uint32_t len;
+	size_t len;
+
+	/* Types of the most recently seen LZMA symbols */
+	enum lzma_state state;
 
 	/*
 	 * LZMA properties or related bit masks (number of literal
@@ -228,13 +230,13 @@ struct lzma2_dec {
 	enum lzma2_seq next_sequence;
 
 	/* Uncompressed size of LZMA chunk (2 MiB at maximum) */
-	uint32_t uncompressed;
+	size_t uncompressed;
 
 	/*
 	 * Compressed size of LZMA chunk or compressed/uncompressed
 	 * size of uncompressed chunk (64 KiB at maximum)
 	 */
-	uint32_t compressed;
+	size_t compressed;
 
 	/*
 	 * True if dictionary reset is needed. This is false before
@@ -269,11 +271,11 @@ struct xz_dec_lzma2 {
 	struct lzma_dec lzma;
 
 	/*
-	 * Temporary buffer which holds small number of input bytes between
+	 * Temporary buffer which holds a small number of input bytes between
 	 * decoder calls. See lzma2_lzma() for details.
 	 */
 	struct {
-		uint32_t size;
+		size_t size;
 		uint8_t buf[3 * LZMA_IN_REQUIRED];
 	} temp;
 };
@@ -320,7 +322,7 @@ static inline bool dict_has_space(const struct dictionary *dict)
  * still empty. This special case is needed for single-call decoding to
  * avoid writing a '\0' to the end of the destination buffer.
  */
-static inline uint32_t dict_get(const struct dictionary *dict, uint32_t dist)
+static inline uint32_t dict_get(const struct dictionary *dict, size_t dist)
 {
 	size_t offset = dict->pos - dist - 1;
 
@@ -346,15 +348,15 @@ static inline void dict_put(struct dictionary *dict, uint8_t byte)
  * invalid, false is returned. On success, true is returned and *len is
  * updated to indicate how many bytes were left to be repeated.
  */
-static bool dict_repeat(struct dictionary *dict, uint32_t *len, uint32_t dist)
+static bool dict_repeat(struct dictionary *dict, size_t *len, size_t dist)
 {
 	size_t back;
-	uint32_t left;
+	size_t left;
 
 	if (dist >= dict->full || dist >= dict->size)
 		return false;
 
-	left = min_t(size_t, dict->limit - dict->pos, *len);
+	left = min(dict->limit - dict->pos, *len);
 	*len -= left;
 
 	back = dict->pos - dist - 1;
@@ -375,7 +377,7 @@ static bool dict_repeat(struct dictionary *dict, uint32_t *len, uint32_t dist)
 
 /* Copy uncompressed data as is from input to dictionary and output buffers. */
 static void dict_uncompressed(struct dictionary *dict, struct xz_buf *b,
-			      uint32_t *left)
+			      size_t *left)
 {
 	size_t copy_size;
 
@@ -433,7 +435,7 @@ static void dict_uncompressed(struct dictionary *dict, struct xz_buf *b,
  * enough space in b->out. This is guaranteed because caller uses dict_limit()
  * before decoding data into the dictionary.
  */
-static uint32_t dict_flush(struct dictionary *dict, struct xz_buf *b)
+static size_t dict_flush(struct dictionary *dict, struct xz_buf *b)
 {
 	size_t copy_size = dict->pos - dict->start;
 
@@ -755,8 +757,8 @@ static bool lzma_main(struct xz_dec_lzma2 *s)
 	uint32_t pos_state;
 
 	/*
-	 * If the dictionary was reached during the previous call, try to
-	 * finish the possibly pending repeat in the dictionary.
+	 * If the dictionary write limit was reached during the previous call,
+	 * try to finish the possibly pending repeat in the dictionary.
 	 */
 	if (dict_has_space(&s->dict) && s->lzma.len > 0)
 		dict_repeat(&s->dict, &s->lzma.len, s->lzma.rep0);
@@ -878,7 +880,7 @@ static bool lzma_props(struct xz_dec_lzma2 *s, uint8_t props)
 static bool lzma2_lzma(struct xz_dec_lzma2 *s, struct xz_buf *b)
 {
 	size_t in_avail;
-	uint32_t tmp;
+	size_t tmp;
 
 	in_avail = b->in_size - b->in_pos;
 	if (s->temp.size > 0 || s->lzma2.compressed == 0) {
@@ -976,7 +978,7 @@ enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, struct xz_buf *b)
 			 *          an uncompressed chunk
 			 *   0x02   Uncompressed chunk (no dictionary reset)
 			 *
-			 * Highest three bits (s->control & 0xE0):
+			 * Highest three bits (tmp & 0xE0):
 			 *   0xE0   Dictionary reset, new properties and state
 			 *          reset, followed by LZMA compressed chunk
 			 *   0xC0   New properties and state reset, followed
@@ -988,7 +990,7 @@ enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, struct xz_buf *b)
 			 *   0x80   LZMA chunk (no dictionary or state reset)
 			 *
 			 * For LZMA compressed chunks, the lowest five bits
-			 * (s->control & 1F) are the highest bits of the
+			 * (tmp & 1F) are the highest bits of the
 			 * uncompressed size (bits 16-20).
 			 *
 			 * A new LZMA2 stream must begin with a dictionary
@@ -1046,25 +1048,23 @@ enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, struct xz_buf *b)
 
 		case SEQ_UNCOMPRESSED_1:
 			s->lzma2.uncompressed
-					+= (uint32_t)b->in[b->in_pos++] << 8;
+					+= (size_t)b->in[b->in_pos++] << 8;
 			s->lzma2.sequence = SEQ_UNCOMPRESSED_2;
 			break;
 
 		case SEQ_UNCOMPRESSED_2:
 			s->lzma2.uncompressed
-					+= (uint32_t)b->in[b->in_pos++] + 1;
+					+= (size_t)b->in[b->in_pos++] + 1;
 			s->lzma2.sequence = SEQ_COMPRESSED_0;
 			break;
 
 		case SEQ_COMPRESSED_0:
-			s->lzma2.compressed
-					= (uint32_t)b->in[b->in_pos++] << 8;
+			s->lzma2.compressed = (size_t)b->in[b->in_pos++] << 8;
 			s->lzma2.sequence = SEQ_COMPRESSED_1;
 			break;
 
 		case SEQ_COMPRESSED_1:
-			s->lzma2.compressed
-					+= (uint32_t)b->in[b->in_pos++] + 1;
+			s->lzma2.compressed += (size_t)b->in[b->in_pos++] + 1;
 			s->lzma2.sequence = s->lzma2.next_sequence;
 			break;
 
@@ -1091,16 +1091,15 @@ enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, struct xz_buf *b)
 		case SEQ_LZMA_RUN:
 			/*
 			 * Set dictionary limit to indicate how much we want
-			 * to be encoded at maximum. Decode new data into the
+			 * to be decoded at maximum. Decode new data into the
 			 * dictionary. Flush the new data from dictionary to
 			 * b->out. Check if we finished decoding this chunk.
 			 * In case the dictionary got full but we didn't fill
 			 * the output buffer yet, we may run this loop
 			 * multiple times without changing s->lzma2.sequence.
 			 */
-			dict_limit(&s->dict, min_t(size_t,
-					b->out_size - b->out_pos,
-					s->lzma2.uncompressed));
+			dict_limit(&s->dict, min(b->out_size - b->out_pos,
+						 s->lzma2.uncompressed));
 			if (!lzma2_lzma(s, b))
 				return XZ_DATA_ERROR;
 
@@ -1260,8 +1259,8 @@ enum xz_ret xz_dec_microlzma_run(struct xz_dec_microlzma *s_ptr,
 		s->dict.end = b->out_size - b->out_pos;
 
 	while (true) {
-		dict_limit(&s->dict, min_t(size_t, b->out_size - b->out_pos,
-					   s->lzma2.uncompressed));
+		dict_limit(&s->dict, min(b->out_size - b->out_pos,
+					 s->lzma2.uncompressed));
 
 		if (!lzma2_lzma(s, b))
 			return XZ_DATA_ERROR;
diff --git a/lib/xz/xz_dec_stream.c b/lib/xz/xz_dec_stream.c
index 59bfd54ffee7..0bed6daefac2 100644
--- a/lib/xz/xz_dec_stream.c
+++ b/lib/xz/xz_dec_stream.c
@@ -155,8 +155,8 @@ static const uint8_t check_sizes[16] = {
  */
 static bool fill_temp(struct xz_dec *s, struct xz_buf *b)
 {
-	size_t copy_size = min_t(size_t,
-			b->in_size - b->in_pos, s->temp.size - s->temp.pos);
+	size_t copy_size = min(b->in_size - b->in_pos,
+			       s->temp.size - s->temp.pos);
 
 	memcpy(s->temp.buf + s->temp.pos, b->in + b->in_pos, copy_size);
 	b->in_pos += copy_size;
diff --git a/lib/xz/xz_lzma2.h b/lib/xz/xz_lzma2.h
index d2632b7dfb9c..a612ce4fd450 100644
--- a/lib/xz/xz_lzma2.h
+++ b/lib/xz/xz_lzma2.h
@@ -143,7 +143,7 @@ static inline bool lzma_state_is_literal(enum lzma_state state)
  * Get the index of the appropriate probability array for decoding
  * the distance slot.
  */
-static inline uint32_t lzma_get_dist_state(uint32_t len)
+static inline size_t lzma_get_dist_state(size_t len)
 {
 	return len < DIST_STATES + MATCH_LEN_MIN
 			? len - MATCH_LEN_MIN : DIST_STATES - 1;