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, 96 insertions, 0 deletions

diff --git a/lib/crc/arm/crc32.h b/lib/crc/arm/crc32.h
new file mode 100644
index 000000000..f33de6b22
--- /dev/null
+++ b/lib/crc/arm/crc32.h
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Accelerated CRC32(C) using ARM CRC, NEON and Crypto Extensions instructions
+ *
+ * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/cpufeature.h>
+
+#include <asm/hwcap.h>
+#include <asm/simd.h>
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_crc32);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_pmull);
+
+#define PMULL_MIN_LEN	64	/* min size of buffer for pmull functions */
+
+asmlinkage u32 crc32_pmull_le(const u8 buf[], u32 len, u32 init_crc);
+asmlinkage u32 crc32_armv8_le(u32 init_crc, const u8 buf[], u32 len);
+
+asmlinkage u32 crc32c_pmull_le(const u8 buf[], u32 len, u32 init_crc);
+asmlinkage u32 crc32c_armv8_le(u32 init_crc, const u8 buf[], u32 len);
+
+static inline u32 crc32_le_scalar(u32 crc, const u8 *p, size_t len)
+{
+	if (static_branch_likely(&have_crc32))
+		return crc32_armv8_le(crc, p, len);
+	return crc32_le_base(crc, p, len);
+}
+
+static inline u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
+{
+	if (len >= PMULL_MIN_LEN + 15 &&
+	    static_branch_likely(&have_pmull) && likely(may_use_simd())) {
+		size_t n = -(uintptr_t)p & 15;
+
+		/* align p to 16-byte boundary */
+		if (n) {
+			crc = crc32_le_scalar(crc, p, n);
+			p += n;
+			len -= n;
+		}
+		n = round_down(len, 16);
+		scoped_ksimd()
+			crc = crc32_pmull_le(p, n, crc);
+		p += n;
+		len -= n;
+	}
+	return crc32_le_scalar(crc, p, len);
+}
+
+static inline u32 crc32c_scalar(u32 crc, const u8 *p, size_t len)
+{
+	if (static_branch_likely(&have_crc32))
+		return crc32c_armv8_le(crc, p, len);
+	return crc32c_base(crc, p, len);
+}
+
+static inline u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
+{
+	if (len >= PMULL_MIN_LEN + 15 &&
+	    static_branch_likely(&have_pmull) && likely(may_use_simd())) {
+		size_t n = -(uintptr_t)p & 15;
+
+		/* align p to 16-byte boundary */
+		if (n) {
+			crc = crc32c_scalar(crc, p, n);
+			p += n;
+			len -= n;
+		}
+		n = round_down(len, 16);
+		scoped_ksimd()
+			crc = crc32c_pmull_le(p, n, crc);
+		p += n;
+		len -= n;
+	}
+	return crc32c_scalar(crc, p, len);
+}
+
+#define crc32_be_arch crc32_be_base /* not implemented on this arch */
+
+#define crc32_mod_init_arch crc32_mod_init_arch
+static void crc32_mod_init_arch(void)
+{
+	if (elf_hwcap2 & HWCAP2_CRC32)
+		static_branch_enable(&have_crc32);
+	if (elf_hwcap2 & HWCAP2_PMULL)
+		static_branch_enable(&have_pmull);
+}
+
+static inline u32 crc32_optimizations_arch(void)
+{
+	if (elf_hwcap2 & (HWCAP2_CRC32 | HWCAP2_PMULL))
+		return CRC32_LE_OPTIMIZATION | CRC32C_OPTIMIZATION;
+	return 0;
+}