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, 78 insertions, 0 deletions

diff --git a/lib/iomap_copy.c b/lib/iomap_copy.c
new file mode 100644
index 000000000..2fd5712fb
--- /dev/null
+++ b/lib/iomap_copy.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2006 PathScale, Inc.  All Rights Reserved.
+ */
+
+#include <linux/export.h>
+#include <linux/io.h>
+
+/**
+ * __iowrite32_copy - copy data to MMIO space, in 32-bit units
+ * @to: destination, in MMIO space (must be 32-bit aligned)
+ * @from: source (must be 32-bit aligned)
+ * @count: number of 32-bit quantities to copy
+ *
+ * Copy data from kernel space to MMIO space, in units of 32 bits at a
+ * time.  Order of access is not guaranteed, nor is a memory barrier
+ * performed afterwards.
+ */
+#ifndef __iowrite32_copy
+void __iowrite32_copy(void __iomem *to, const void *from, size_t count)
+{
+	u32 __iomem *dst = to;
+	const u32 *src = from;
+	const u32 *end = src + count;
+
+	while (src < end)
+		__raw_writel(*src++, dst++);
+}
+EXPORT_SYMBOL_GPL(__iowrite32_copy);
+#endif
+
+/**
+ * __ioread32_copy - copy data from MMIO space, in 32-bit units
+ * @to: destination (must be 32-bit aligned)
+ * @from: source, in MMIO space (must be 32-bit aligned)
+ * @count: number of 32-bit quantities to copy
+ *
+ * Copy data from MMIO space to kernel space, in units of 32 bits at a
+ * time.  Order of access is not guaranteed, nor is a memory barrier
+ * performed afterwards.
+ */
+void __ioread32_copy(void *to, const void __iomem *from, size_t count)
+{
+	u32 *dst = to;
+	const u32 __iomem *src = from;
+	const u32 __iomem *end = src + count;
+
+	while (src < end)
+		*dst++ = __raw_readl(src++);
+}
+EXPORT_SYMBOL_GPL(__ioread32_copy);
+
+/**
+ * __iowrite64_copy - copy data to MMIO space, in 64-bit or 32-bit units
+ * @to: destination, in MMIO space (must be 64-bit aligned)
+ * @from: source (must be 64-bit aligned)
+ * @count: number of 64-bit quantities to copy
+ *
+ * Copy data from kernel space to MMIO space, in units of 32 or 64 bits at a
+ * time.  Order of access is not guaranteed, nor is a memory barrier
+ * performed afterwards.
+ */
+#ifndef __iowrite64_copy
+void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
+{
+#ifdef CONFIG_64BIT
+	u64 __iomem *dst = to;
+	const u64 *src = from;
+	const u64 *end = src + count;
+
+	while (src < end)
+		__raw_writeq(*src++, dst++);
+#else
+	__iowrite32_copy(to, from, count * 2);
+#endif
+}
+EXPORT_SYMBOL_GPL(__iowrite64_copy);
+#endif