From 9cc63f8bcd560c760d0b12e15bba8f81c86237cf Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Fri, 14 Aug 2026 15:43:51 -0700
Subject: Merge branches 'expcb.2026.07.24a', 'misc.2026.07.30a',
 'rcu-tasks.2026.07.30a', 'srcu.2026.08.11a' and 'torture.2026.08.14a' into
 HEAD

Changes:

Make expedited grace periods expedite normal RCU callbacks

Miscellaneous fixes:
 * Improve diagnostic output with character task states.
 * Mark accesses to inform KCSAN of concurrency design.
 * Move from kmalloc() to kmalloc_obj().
 * Documentation updates.
 * Improve handling of RCU deferred quiescent states.
 * Clean up unused function arguments and structure fields.
 * Reduce show_rcu_gp_kthreads() stack space.

Tasks RCU updates:
 * Clean up after SRCU re-implementation of Tasks Trace RCU.
 * Mark accesses to inform KCSAN of concurrency design.
 * Add ->lazy_timer status to diagnostic output.
 * Remove an unnecessary memory barrier.
 * Fix a data race, courtesy of KCSAN.
 * Documentation updates.
 * Convert cond_resched_tasks_rcu_qs() from macro to static inline
   function.

SRCU updates:
 * Add Rust helpers for SRCU.
 * Avoid losing queued work at cleanup_srcu_struct() time.

Torture-test updates:
 * Preparation work for immediate RCU priority deboosting.
 * Test RCU readers from real interrupt handlers (as opposed to softirq).
 * Simplify code through use of cpumask_next_wrap().
 * Improve diagnostic output with character task states.
 * Add rcutorture.nwriters parameter to allow lightweight stall testing,
   and rcutorture.stall_only to make doing so easier.
 * Test an RCU Tasks Trace grace period implying an RCU grace period.
 * Make RCU Tasks Trace torturing track reader batches.
 * Fix a data race, courtesy of KCSAN.
 * Plug a shuffle_tmp_mask memory leak on kthread spawn failure.
---
 lib/crypto/utils.c | 90 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 90 insertions(+)
 create mode 100644 lib/crypto/utils.c

(limited to 'lib/crypto/utils.c')

diff --git a/lib/crypto/utils.c b/lib/crypto/utils.c
new file mode 100644
index 000000000..dec381d5e
--- /dev/null
+++ b/lib/crypto/utils.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Crypto library utility functions
+ *
+ * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+
+#include <crypto/utils.h>
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/unaligned.h>
+
+/*
+ * XOR @len bytes from @src1 and @src2 together, writing the result to @dst
+ * (which may alias one of the sources).  Don't call this directly; call
+ * crypto_xor() or crypto_xor_cpy() instead.
+ */
+void __crypto_xor(u8 *dst, const u8 *src1, const u8 *src2, unsigned int len)
+{
+	int relalign = 0;
+
+	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+		int size = sizeof(unsigned long);
+		int d = (((unsigned long)dst ^ (unsigned long)src1) |
+			 ((unsigned long)dst ^ (unsigned long)src2)) &
+			(size - 1);
+
+		relalign = d ? 1 << __ffs(d) : size;
+
+		/*
+		 * If we care about alignment, process as many bytes as
+		 * needed to advance dst and src to values whose alignments
+		 * equal their relative alignment. This will allow us to
+		 * process the remainder of the input using optimal strides.
+		 */
+		while (((unsigned long)dst & (relalign - 1)) && len > 0) {
+			*dst++ = *src1++ ^ *src2++;
+			len--;
+		}
+	}
+
+	while (IS_ENABLED(CONFIG_64BIT) && len >= 8 && !(relalign & 7)) {
+		if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+			u64 l = get_unaligned((u64 *)src1) ^
+				get_unaligned((u64 *)src2);
+			put_unaligned(l, (u64 *)dst);
+		} else {
+			*(u64 *)dst = *(u64 *)src1 ^ *(u64 *)src2;
+		}
+		dst += 8;
+		src1 += 8;
+		src2 += 8;
+		len -= 8;
+	}
+
+	while (len >= 4 && !(relalign & 3)) {
+		if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+			u32 l = get_unaligned((u32 *)src1) ^
+				get_unaligned((u32 *)src2);
+			put_unaligned(l, (u32 *)dst);
+		} else {
+			*(u32 *)dst = *(u32 *)src1 ^ *(u32 *)src2;
+		}
+		dst += 4;
+		src1 += 4;
+		src2 += 4;
+		len -= 4;
+	}
+
+	while (len >= 2 && !(relalign & 1)) {
+		if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+			u16 l = get_unaligned((u16 *)src1) ^
+				get_unaligned((u16 *)src2);
+			put_unaligned(l, (u16 *)dst);
+		} else {
+			*(u16 *)dst = *(u16 *)src1 ^ *(u16 *)src2;
+		}
+		dst += 2;
+		src1 += 2;
+		src2 += 2;
+		len -= 2;
+	}
+
+	while (len--)
+		*dst++ = *src1++ ^ *src2++;
+}
+EXPORT_SYMBOL_GPL(__crypto_xor);
+
+MODULE_DESCRIPTION("Crypto library utility functions");
+MODULE_LICENSE("GPL");
-- 
cgit v1.3.1