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, 52 insertions, 0 deletions

diff --git a/lib/crypto/arm64/sha3.h b/lib/crypto/arm64/sha3.h
new file mode 100644
index 000000000..eaaba3224
--- /dev/null
+++ b/lib/crypto/arm64/sha3.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/simd.h>
+#include <linux/cpufeature.h>
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_sha3);
+
+asmlinkage void sha3_ce_transform(struct sha3_state *state, const u8 *data,
+				  size_t nblocks, size_t block_size);
+
+static void sha3_absorb_blocks(struct sha3_state *state, const u8 *data,
+			       size_t nblocks, size_t block_size)
+{
+	if (static_branch_likely(&have_sha3) && likely(may_use_simd())) {
+		scoped_ksimd()
+			sha3_ce_transform(state, data, nblocks, block_size);
+	} else {
+		sha3_absorb_blocks_generic(state, data, nblocks, block_size);
+	}
+}
+
+static void sha3_keccakf(struct sha3_state *state)
+{
+	if (static_branch_likely(&have_sha3) && likely(may_use_simd())) {
+		/*
+		 * Passing zeroes into sha3_ce_transform() gives the plain
+		 * Keccak-f permutation, which is what we want here.  Any
+		 * supported block size may be used.  Use SHA3_512_BLOCK_SIZE
+		 * since it's the shortest.
+		 */
+		static const u8 zeroes[SHA3_512_BLOCK_SIZE];
+
+		scoped_ksimd()
+			sha3_ce_transform(state, zeroes, 1, sizeof(zeroes));
+	} else {
+		sha3_keccakf_generic(state);
+	}
+}
+
+#define sha3_mod_init_arch sha3_mod_init_arch
+static void sha3_mod_init_arch(void)
+{
+	if (cpu_have_named_feature(SHA3))
+		static_branch_enable(&have_sha3);
+}