x86/amd_node: Fix PCI device reference counting in amd_smn_init()grafted

The local "root" pointer is a temporary variable used during the device
search. Therefore, refcount related to the search iterators should be cleaned
up after the search is complete.

Use the __free() cleanup macro to ensure the refcount is decremented when the
temporary pointer goes out of scope.

Additionally, increment the refcount when caching a root pointer. This ensures
the in-use refcount is separate from the temporary search refcounting.

Finally, drop the redundant "root = NULL" before the second search loop. The
pci_get_class() iterator always decrements the refcount of its "from"
argument, so the first loop can only fall through with "root" already NULL.

Fixes: 0a4b61d9c2e4 ("x86/amd_node: Fix AMD root device caching")
Closes: https://sashiko.dev/#/patchset/20260806160159.230453-1-jason.andryuk%40amd.com
Reported-by: Sashiko <sashiko-bot@kernel.org>
Assisted-by: LLM
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Cc: <stable@kernel.org>
Link: https://patch.msgid.link/20260903154325.74343-1-yazen.ghannam@amd.com

1 files changed, 179 insertions, 0 deletions

diff --git a/arch/microblaze/lib/memcpy.c b/arch/microblaze/lib/memcpy.c
new file mode 100644
index 000000000..9966dce55
--- /dev/null
+++ b/arch/microblaze/lib/memcpy.c
@@ -0,0 +1,179 @@
+/*
+ * Copyright (C) 2008-2009 Michal Simek <monstr@monstr.eu>
+ * Copyright (C) 2008-2009 PetaLogix
+ * Copyright (C) 2007 John Williams
+ *
+ * Reasonably optimised generic C-code for memcpy on Microblaze
+ * This is generic C code to do efficient, alignment-aware memcpy.
+ *
+ * It is based on demo code originally Copyright 2001 by Intel Corp, taken from
+ * http://www.embedded.com/showArticle.jhtml?articleID=19205567
+ *
+ * Attempts were made, unsuccessfully, to contact the original
+ * author of this code (Michael Morrow, Intel).  Below is the original
+ * copyright notice.
+ *
+ * This software has been developed by Intel Corporation.
+ * Intel specifically disclaims all warranties, express or
+ * implied, and all liability, including consequential and
+ * other indirect damages, for the use of this program, including
+ * liability for infringement of any proprietary rights,
+ * and including the warranties of merchantability and fitness
+ * for a particular purpose. Intel does not assume any
+ * responsibility for and errors which may appear in this program
+ * not any responsibility to update it.
+ */
+
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/compiler.h>
+
+#include <linux/string.h>
+
+#ifdef CONFIG_OPT_LIB_FUNCTION
+void *memcpy(void *v_dst, const void *v_src, __kernel_size_t c)
+{
+	const char *src = v_src;
+	char *dst = v_dst;
+
+	/* The following code tries to optimize the copy by using unsigned
+	 * alignment. This will work fine if both source and destination are
+	 * aligned on the same boundary. However, if they are aligned on
+	 * different boundaries shifts will be necessary. This might result in
+	 * bad performance on MicroBlaze systems without a barrel shifter.
+	 */
+	const uint32_t *i_src;
+	uint32_t *i_dst;
+
+	if (likely(c >= 4)) {
+		unsigned  value, buf_hold;
+
+		/* Align the destination to a word boundary. */
+		/* This is done in an endian independent manner. */
+		switch ((unsigned long)dst & 3) {
+		case 1:
+			*dst++ = *src++;
+			--c;
+			fallthrough;
+		case 2:
+			*dst++ = *src++;
+			--c;
+			fallthrough;
+		case 3:
+			*dst++ = *src++;
+			--c;
+		}
+
+		i_dst = (void *)dst;
+
+		/* Choose a copy scheme based on the source */
+		/* alignment relative to destination. */
+		switch ((unsigned long)src & 3) {
+		case 0x0:	/* Both byte offsets are aligned */
+			i_src  = (const void *)src;
+
+			for (; c >= 4; c -= 4)
+				*i_dst++ = *i_src++;
+
+			src  = (const void *)i_src;
+			break;
+		case 0x1:	/* Unaligned - Off by 1 */
+			/* Word align the source */
+			i_src = (const void *) ((unsigned)src & ~3);
+#ifndef __MICROBLAZEEL__
+			/* Load the holding buffer */
+			buf_hold = *i_src++ << 8;
+
+			for (; c >= 4; c -= 4) {
+				value = *i_src++;
+				*i_dst++ = buf_hold | value >> 24;
+				buf_hold = value << 8;
+			}
+#else
+			/* Load the holding buffer */
+			buf_hold = (*i_src++ & 0xFFFFFF00) >> 8;
+
+			for (; c >= 4; c -= 4) {
+				value = *i_src++;
+				*i_dst++ = buf_hold | ((value & 0xFF) << 24);
+				buf_hold = (value & 0xFFFFFF00) >> 8;
+			}
+#endif
+			/* Realign the source */
+			src = (const void *)i_src;
+			src -= 3;
+			break;
+		case 0x2:	/* Unaligned - Off by 2 */
+			/* Word align the source */
+			i_src = (const void *) ((unsigned)src & ~3);
+#ifndef __MICROBLAZEEL__
+			/* Load the holding buffer */
+			buf_hold = *i_src++ << 16;
+
+			for (; c >= 4; c -= 4) {
+				value = *i_src++;
+				*i_dst++ = buf_hold | value >> 16;
+				buf_hold = value << 16;
+			}
+#else
+			/* Load the holding buffer */
+			buf_hold = (*i_src++ & 0xFFFF0000) >> 16;
+
+			for (; c >= 4; c -= 4) {
+				value = *i_src++;
+				*i_dst++ = buf_hold | ((value & 0xFFFF) << 16);
+				buf_hold = (value & 0xFFFF0000) >> 16;
+			}
+#endif
+			/* Realign the source */
+			src = (const void *)i_src;
+			src -= 2;
+			break;
+		case 0x3:	/* Unaligned - Off by 3 */
+			/* Word align the source */
+			i_src = (const void *) ((unsigned)src & ~3);
+#ifndef __MICROBLAZEEL__
+			/* Load the holding buffer */
+			buf_hold = *i_src++ << 24;
+
+			for (; c >= 4; c -= 4) {
+				value = *i_src++;
+				*i_dst++ = buf_hold | value >> 8;
+				buf_hold = value << 24;
+			}
+#else
+			/* Load the holding buffer */
+			buf_hold = (*i_src++ & 0xFF000000) >> 24;
+
+			for (; c >= 4; c -= 4) {
+				value = *i_src++;
+				*i_dst++ = buf_hold | ((value & 0xFFFFFF) << 8);
+				buf_hold = (value & 0xFF000000) >> 24;
+			}
+#endif
+			/* Realign the source */
+			src = (const void *)i_src;
+			src -= 1;
+			break;
+		}
+		dst = (void *)i_dst;
+	}
+
+	/* Finish off any remaining bytes */
+	/* simple fast copy, ... unless a cache boundary is crossed */
+	switch (c) {
+	case 3:
+		*dst++ = *src++;
+		fallthrough;
+	case 2:
+		*dst++ = *src++;
+		fallthrough;
+	case 1:
+		*dst++ = *src++;
+	}
+
+	return v_dst;
+}
+EXPORT_SYMBOL(memcpy);
+#endif /* CONFIG_OPT_LIB_FUNCTION */