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, 46 insertions, 0 deletions

diff --git a/lib/crypto/arm/sha256.h b/lib/crypto/arm/sha256.h
new file mode 100644
index 000000000..ae7e52dd6
--- /dev/null
+++ b/lib/crypto/arm/sha256.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * SHA-256 optimized for ARM
+ *
+ * Copyright 2025 Google LLC
+ */
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_ce);
+
+asmlinkage void sha256_block_data_order(struct sha256_block_state *state,
+					const u8 *data, size_t nblocks);
+asmlinkage void sha256_block_data_order_neon(struct sha256_block_state *state,
+					     const u8 *data, size_t nblocks);
+asmlinkage void sha256_ce_transform(struct sha256_block_state *state,
+				    const u8 *data, size_t nblocks);
+
+static void sha256_blocks(struct sha256_block_state *state,
+			  const u8 *data, size_t nblocks)
+{
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+	    static_branch_likely(&have_neon) && likely(may_use_simd())) {
+		scoped_ksimd() {
+			if (static_branch_likely(&have_ce))
+				sha256_ce_transform(state, data, nblocks);
+			else
+				sha256_block_data_order_neon(state, data, nblocks);
+		}
+	} else {
+		sha256_block_data_order(state, data, nblocks);
+	}
+}
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+#define sha256_mod_init_arch sha256_mod_init_arch
+static void sha256_mod_init_arch(void)
+{
+	if (elf_hwcap & HWCAP_NEON) {
+		static_branch_enable(&have_neon);
+		if (elf_hwcap2 & HWCAP2_SHA2)
+			static_branch_enable(&have_ce);
+	}
+}
+#endif /* CONFIG_KERNEL_MODE_NEON */