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, 126 insertions, 0 deletions

diff --git a/arch/hexagon/mm/cache.c b/arch/hexagon/mm/cache.c
new file mode 100644
index 000000000..7e46f40c8
--- /dev/null
+++ b/arch/hexagon/mm/cache.c
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Cache management functions for Hexagon
+ *
+ * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/mm.h>
+#include <asm/cacheflush.h>
+#include <asm/hexagon_vm.h>
+
+#define spanlines(start, end) \
+	(((end - (start & ~(LINESIZE - 1))) >> LINEBITS) + 1)
+
+void flush_dcache_range(unsigned long start, unsigned long end)
+{
+	unsigned long lines = spanlines(start, end-1);
+	unsigned long i, flags;
+
+	start &= ~(LINESIZE - 1);
+
+	local_irq_save(flags);
+
+	for (i = 0; i < lines; i++) {
+		__asm__ __volatile__ (
+		"	dccleaninva(%0);	"
+		:
+		: "r" (start)
+		);
+		start += LINESIZE;
+	}
+	local_irq_restore(flags);
+}
+
+void flush_icache_range(unsigned long start, unsigned long end)
+{
+	unsigned long lines = spanlines(start, end-1);
+	unsigned long i, flags;
+
+	start &= ~(LINESIZE - 1);
+
+	local_irq_save(flags);
+
+	for (i = 0; i < lines; i++) {
+		__asm__ __volatile__ (
+			"	dccleana(%0); "
+			"	icinva(%0);	"
+			:
+			: "r" (start)
+		);
+		start += LINESIZE;
+	}
+	__asm__ __volatile__ (
+		"isync"
+	);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(flush_icache_range);
+
+void hexagon_clean_dcache_range(unsigned long start, unsigned long end)
+{
+	unsigned long lines = spanlines(start, end-1);
+	unsigned long i, flags;
+
+	start &= ~(LINESIZE - 1);
+
+	local_irq_save(flags);
+
+	for (i = 0; i < lines; i++) {
+		__asm__ __volatile__ (
+		"	dccleana(%0);	"
+		:
+		: "r" (start)
+		);
+		start += LINESIZE;
+	}
+	local_irq_restore(flags);
+}
+
+void hexagon_inv_dcache_range(unsigned long start, unsigned long end)
+{
+	unsigned long lines = spanlines(start, end-1);
+	unsigned long i, flags;
+
+	start &= ~(LINESIZE - 1);
+
+	local_irq_save(flags);
+
+	for (i = 0; i < lines; i++) {
+		__asm__ __volatile__ (
+		"	dcinva(%0);	"
+		:
+		: "r" (start)
+		);
+		start += LINESIZE;
+	}
+	local_irq_restore(flags);
+}
+
+
+
+
+/*
+ * This is just really brutal and shouldn't be used anyways,
+ * especially on V2.  Left here just in case.
+ */
+void flush_cache_all_hexagon(void)
+{
+	unsigned long flags;
+	local_irq_save(flags);
+	__vmcache_ickill();
+	__vmcache_dckill();
+	__vmcache_l2kill();
+	local_irq_restore(flags);
+	mb();
+}
+
+void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
+		       unsigned long vaddr, void *dst, void *src, int len)
+{
+	memcpy(dst, src, len);
+	if (vma->vm_flags & VM_EXEC) {
+		flush_icache_range((unsigned long) dst,
+		(unsigned long) dst + len);
+	}
+}