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, 79 insertions, 0 deletions

diff --git a/crypto/aegis.h b/crypto/aegis.h
new file mode 100644
index 000000000..ffcf8e85e
--- /dev/null
+++ b/crypto/aegis.h
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * AEGIS common definitions
+ *
+ * Copyright (c) 2018 Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (c) 2018 Red Hat, Inc. All rights reserved.
+ */
+
+#ifndef _CRYPTO_AEGIS_H
+#define _CRYPTO_AEGIS_H
+
+#include <crypto/aes.h>
+#include <linux/bitops.h>
+#include <linux/types.h>
+
+#define AEGIS_BLOCK_SIZE 16
+
+union aegis_block {
+	__le64 words64[AEGIS_BLOCK_SIZE / sizeof(__le64)];
+	__le32 words32[AEGIS_BLOCK_SIZE / sizeof(__le32)];
+	u8 bytes[AEGIS_BLOCK_SIZE];
+};
+
+struct aegis_state;
+
+extern int aegis128_have_aes_insn;
+
+#define AEGIS_BLOCK_ALIGN (__alignof__(union aegis_block))
+#define AEGIS_ALIGNED(p) IS_ALIGNED((uintptr_t)p, AEGIS_BLOCK_ALIGN)
+
+bool crypto_aegis128_have_simd(void);
+void crypto_aegis128_update_simd(struct aegis_state *state, const void *msg);
+void crypto_aegis128_init_simd(struct aegis_state *state,
+			       const union aegis_block *key,
+			       const u8 *iv);
+void crypto_aegis128_encrypt_chunk_simd(struct aegis_state *state, u8 *dst,
+					const u8 *src, unsigned int size);
+void crypto_aegis128_decrypt_chunk_simd(struct aegis_state *state, u8 *dst,
+					const u8 *src, unsigned int size);
+int crypto_aegis128_final_simd(struct aegis_state *state,
+			       union aegis_block *tag_xor,
+			       unsigned int assoclen,
+			       unsigned int cryptlen,
+			       unsigned int authsize);
+
+static __always_inline void crypto_aegis_block_xor(union aegis_block *dst,
+						   const union aegis_block *src)
+{
+	dst->words64[0] ^= src->words64[0];
+	dst->words64[1] ^= src->words64[1];
+}
+
+static __always_inline void crypto_aegis_block_and(union aegis_block *dst,
+						   const union aegis_block *src)
+{
+	dst->words64[0] &= src->words64[0];
+	dst->words64[1] &= src->words64[1];
+}
+
+static __always_inline void crypto_aegis_aesenc(union aegis_block *dst,
+						const union aegis_block *src,
+						const union aegis_block *key)
+{
+	const u8  *s  = src->bytes;
+	const u32 *t = aes_enc_tab;
+	u32 d0, d1, d2, d3;
+
+	d0 = t[s[ 0]] ^ rol32(t[s[ 5]], 8) ^ rol32(t[s[10]], 16) ^ rol32(t[s[15]], 24);
+	d1 = t[s[ 4]] ^ rol32(t[s[ 9]], 8) ^ rol32(t[s[14]], 16) ^ rol32(t[s[ 3]], 24);
+	d2 = t[s[ 8]] ^ rol32(t[s[13]], 8) ^ rol32(t[s[ 2]], 16) ^ rol32(t[s[ 7]], 24);
+	d3 = t[s[12]] ^ rol32(t[s[ 1]], 8) ^ rol32(t[s[ 6]], 16) ^ rol32(t[s[11]], 24);
+
+	dst->words32[0] = cpu_to_le32(d0) ^ key->words32[0];
+	dst->words32[1] = cpu_to_le32(d1) ^ key->words32[1];
+	dst->words32[2] = cpu_to_le32(d2) ^ key->words32[2];
+	dst->words32[3] = cpu_to_le32(d3) ^ key->words32[3];
+}
+
+#endif /* _CRYPTO_AEGIS_H */