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, 76 insertions, 0 deletions

diff --git a/lib/crypto/powerpc/chacha.h b/lib/crypto/powerpc/chacha.h
new file mode 100644
index 000000000..1df6e1ce3
--- /dev/null
+++ b/lib/crypto/powerpc/chacha.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * ChaCha stream cipher (P10 accelerated)
+ *
+ * Copyright 2023- IBM Corp. All rights reserved.
+ */
+
+#include <crypto/internal/simd.h>
+#include <linux/kernel.h>
+#include <linux/cpufeature.h>
+#include <linux/sizes.h>
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+
+asmlinkage void chacha_p10le_8x(const struct chacha_state *state, u8 *dst,
+				const u8 *src, unsigned int len, int nrounds);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_p10);
+
+static void vsx_begin(void)
+{
+	preempt_disable();
+	enable_kernel_vsx();
+}
+
+static void vsx_end(void)
+{
+	disable_kernel_vsx();
+	preempt_enable();
+}
+
+static void chacha_p10_do_8x(struct chacha_state *state, u8 *dst, const u8 *src,
+			     unsigned int bytes, int nrounds)
+{
+	unsigned int l = bytes & ~0x0FF;
+
+	if (l > 0) {
+		chacha_p10le_8x(state, dst, src, l, nrounds);
+		bytes -= l;
+		src += l;
+		dst += l;
+		state->x[12] += l / CHACHA_BLOCK_SIZE;
+	}
+
+	if (bytes > 0)
+		chacha_crypt_generic(state, dst, src, bytes, nrounds);
+}
+
+#define hchacha_block_arch hchacha_block_generic /* not implemented yet */
+
+static void chacha_crypt_arch(struct chacha_state *state, u8 *dst,
+			      const u8 *src, unsigned int bytes, int nrounds)
+{
+	if (!static_branch_likely(&have_p10) || bytes <= CHACHA_BLOCK_SIZE ||
+	    !crypto_simd_usable())
+		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+
+	do {
+		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+		vsx_begin();
+		chacha_p10_do_8x(state, dst, src, todo, nrounds);
+		vsx_end();
+
+		bytes -= todo;
+		src += todo;
+		dst += todo;
+	} while (bytes);
+}
+
+#define chacha_mod_init_arch chacha_mod_init_arch
+static void chacha_mod_init_arch(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_31))
+		static_branch_enable(&have_p10);
+}