KVM: Don't pre-reserve xarray entries when storing empty/NULL attributesgrafted

Skip the xarray reservation loop when clearing all memory attributes, as
storing NULL only erases the entry and never needs to allocate, so no
reservation (and no cleanup of a failed one) is required in that case.

Suggested-by: Sean Christopherson <seanjc@google.com>
Cc: David Ballesteros <davimaba.v@proton.me>
Signed-off-by: Zeng Chi <zengchi@kylinos.cn>
Link: https://patch.msgid.link/20260921102442.1232375-1-zeng_chi911@163.com
[sean: split to separate patch]
Signed-off-by: Sean Christopherson <seanjc@google.com>

1 files changed, 59 insertions, 0 deletions

diff --git a/drivers/md/dm-vdo/cpu.h b/drivers/md/dm-vdo/cpu.h
new file mode 100644
index 000000000..d6a2615ba
--- /dev/null
+++ b/drivers/md/dm-vdo/cpu.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2023 Red Hat
+ */
+
+#ifndef UDS_CPU_H
+#define UDS_CPU_H
+
+#include <linux/cache.h>
+
+/**
+ * uds_prefetch_address() - Minimize cache-miss latency by attempting to move data into a CPU cache
+ *                          before it is accessed.
+ *
+ * @address: the address to fetch (may be invalid)
+ * @for_write: must be constant at compile time--false if for reading, true if for writing
+ */
+static inline void uds_prefetch_address(const void *address, bool for_write)
+{
+	/*
+	 * for_write won't be a constant if we are compiled with optimization turned off, in which
+	 * case prefetching really doesn't matter. clang can't figure out that if for_write is a
+	 * constant, it can be passed as the second, mandatorily constant argument to prefetch(),
+	 * at least currently on llvm 12.
+	 */
+	if (__builtin_constant_p(for_write)) {
+		if (for_write)
+			__builtin_prefetch(address, true);
+		else
+			__builtin_prefetch(address, false);
+	}
+}
+
+/**
+ * uds_prefetch_range() - Minimize cache-miss latency by attempting to move a range of addresses
+ *                        into a CPU cache before they are accessed.
+ *
+ * @start: the starting address to fetch (may be invalid)
+ * @size: the number of bytes in the address range
+ * @for_write: must be constant at compile time--false if for reading, true if for writing
+ */
+static inline void uds_prefetch_range(const void *start, unsigned int size,
+				      bool for_write)
+{
+	/*
+	 * Count the number of cache lines to fetch, allowing for the address range to span an
+	 * extra cache line boundary due to address alignment.
+	 */
+	const char *address = (const char *) start;
+	unsigned int offset = ((uintptr_t) address % L1_CACHE_BYTES);
+	unsigned int cache_lines = (1 + ((size + offset) / L1_CACHE_BYTES));
+
+	while (cache_lines-- > 0) {
+		uds_prefetch_address(address, for_write);
+		address += L1_CACHE_BYTES;
+	}
+}
+
+#endif /* UDS_CPU_H */