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, 88 insertions, 0 deletions

diff --git a/arch/powerpc/lib/pmem.c b/arch/powerpc/lib/pmem.c
new file mode 100644
index 000000000..0f0f2d851
--- /dev/null
+++ b/arch/powerpc/lib/pmem.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright(c) 2017 IBM Corporation. All rights reserved.
+ */
+
+#include <linux/string.h>
+#include <linux/export.h>
+#include <linux/uaccess.h>
+#include <linux/libnvdimm.h>
+
+#include <asm/cacheflush.h>
+
+static inline void __clean_pmem_range(unsigned long start, unsigned long stop)
+{
+	unsigned long shift = l1_dcache_shift();
+	unsigned long bytes = l1_dcache_bytes();
+	void *addr = (void *)(start & ~(bytes - 1));
+	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
+	unsigned long i;
+
+	for (i = 0; i < size >> shift; i++, addr += bytes)
+		asm volatile(PPC_DCBSTPS(%0, %1): :"i"(0), "r"(addr): "memory");
+}
+
+static inline void __flush_pmem_range(unsigned long start, unsigned long stop)
+{
+	unsigned long shift = l1_dcache_shift();
+	unsigned long bytes = l1_dcache_bytes();
+	void *addr = (void *)(start & ~(bytes - 1));
+	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
+	unsigned long i;
+
+	for (i = 0; i < size >> shift; i++, addr += bytes)
+		asm volatile(PPC_DCBFPS(%0, %1): :"i"(0), "r"(addr): "memory");
+}
+
+static inline void clean_pmem_range(unsigned long start, unsigned long stop)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		return __clean_pmem_range(start, stop);
+}
+
+static inline void flush_pmem_range(unsigned long start, unsigned long stop)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		return __flush_pmem_range(start, stop);
+}
+
+/*
+ * CONFIG_ARCH_HAS_PMEM_API symbols
+ */
+void arch_wb_cache_pmem(void *addr, size_t size)
+{
+	unsigned long start = (unsigned long) addr;
+	clean_pmem_range(start, start + size);
+}
+EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
+
+void arch_invalidate_pmem(void *addr, size_t size)
+{
+	unsigned long start = (unsigned long) addr;
+	flush_pmem_range(start, start + size);
+}
+EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
+
+/*
+ * CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE symbols
+ */
+size_t copy_from_user_flushcache(void *dest, const void __user *src,
+				 size_t size)
+{
+	unsigned long not_copied, start = (unsigned long) dest;
+
+	src = mask_user_address(src);
+	not_copied = __copy_from_user(dest, src, size);
+	clean_pmem_range(start, start + size);
+
+	return not_copied;
+}
+
+void memcpy_flushcache(void *dest, const void *src, size_t size)
+{
+	unsigned long start = (unsigned long) dest;
+
+	memcpy(dest, src, size);
+	clean_pmem_range(start, start + size);
+}
+EXPORT_SYMBOL(memcpy_flushcache);