ftrace: Synchronize the initialization of ftrace_opsgrafted

There's some internal state that ftrace_ops needs to have set, but since
it can be declared outside of the ftrace.c code, it calls
ftrace_ops_init() on the ops in every global function. The issue is that
if two tasks call it on the same ops at the same time it is possible to
have the initialization of one corrupt the initialization of the other
call.

Create a ops_mutex to use to synchronize every initialization of the
ftrace_ops. The mutex is taken within checking the ftrace_ops flag that
states it was initializied but the flag is checked again after the mutex
has been taken. Checking first outside the mutex allows it to shortcut
having to take the mutex. But then the check needs to be done again after
the mute is taken in case of races.

Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260902095501.6b59af20@gandalf.local.home
Fixes: f04f24fb7e48d ("ftrace, kprobes: Fix a deadlock on ftrace_regex_lock")
Reported-by: sashiko-bot@kernel.org
Close: https://lore.kernel.org/all/20260829025528.49A831F000E9@smtp.kernel.org/
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

1 files changed, 62 insertions, 0 deletions

diff --git a/lib/crypto/x86/blake2s.h b/lib/crypto/x86/blake2s.h
new file mode 100644
index 000000000..f8eed6cb0
--- /dev/null
+++ b/lib/crypto/x86/blake2s.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <asm/cpufeature.h>
+#include <asm/fpu/api.h>
+#include <asm/processor.h>
+#include <asm/simd.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/sizes.h>
+
+asmlinkage void blake2s_compress_ssse3(struct blake2s_ctx *ctx,
+				       const u8 *data, size_t nblocks, u32 inc);
+asmlinkage void blake2s_compress_avx512(struct blake2s_ctx *ctx,
+					const u8 *data, size_t nblocks, u32 inc);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_ssse3);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_avx512);
+
+static void blake2s_compress(struct blake2s_ctx *ctx,
+			     const u8 *data, size_t nblocks, u32 inc)
+{
+	/* SIMD disables preemption, so relax after processing each page. */
+	BUILD_BUG_ON(SZ_4K / BLAKE2S_BLOCK_SIZE < 8);
+
+	if (!static_branch_likely(&blake2s_use_ssse3) || !may_use_simd()) {
+		blake2s_compress_generic(ctx, data, nblocks, inc);
+		return;
+	}
+
+	do {
+		const size_t blocks = min_t(size_t, nblocks,
+					    SZ_4K / BLAKE2S_BLOCK_SIZE);
+
+		kernel_fpu_begin();
+		if (static_branch_likely(&blake2s_use_avx512))
+			blake2s_compress_avx512(ctx, data, blocks, inc);
+		else
+			blake2s_compress_ssse3(ctx, data, blocks, inc);
+		kernel_fpu_end();
+
+		data += blocks * BLAKE2S_BLOCK_SIZE;
+		nblocks -= blocks;
+	} while (nblocks);
+}
+
+#define blake2s_mod_init_arch blake2s_mod_init_arch
+static void blake2s_mod_init_arch(void)
+{
+	if (boot_cpu_has(X86_FEATURE_SSSE3))
+		static_branch_enable(&blake2s_use_ssse3);
+
+	if (boot_cpu_has(X86_FEATURE_AVX) &&
+	    boot_cpu_has(X86_FEATURE_AVX2) &&
+	    boot_cpu_has(X86_FEATURE_AVX512F) &&
+	    boot_cpu_has(X86_FEATURE_AVX512VL) &&
+	    cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM |
+			      XFEATURE_MASK_AVX512, NULL))
+		static_branch_enable(&blake2s_use_avx512);
+}