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, 47 insertions, 0 deletions

diff --git a/lib/crc/crc64-neon.c b/lib/crc/crc64-neon.c
new file mode 100644
index 000000000..4753fb94a
--- /dev/null
+++ b/lib/crc/crc64-neon.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Accelerated CRC64 (NVMe) using ARM NEON C intrinsics
+ */
+
+#include <linux/types.h>
+#include <asm/neon-intrinsics.h>
+
+#include "crc64-neon.h"
+
+u64 crc64_nvme_neon(u64 crc, const u8 *p, size_t len);
+
+/* x^191 mod G, x^127 mod G */
+static const u64 fold_consts_val[2] = { 0xeadc41fd2ba3d420ULL,
+					0x21e9761e252621acULL };
+/* floor(x^127 / G), (G - x^64) / x */
+static const u64 bconsts_val[2] = { 0x27ecfa329aef9f77ULL,
+				    0x34d926535897936aULL };
+
+u64 crc64_nvme_neon(u64 crc, const u8 *p, size_t len)
+{
+	uint64x2_t fold_consts = vld1q_u64(fold_consts_val);
+	uint64x2_t v0 = { crc, 0 };
+	uint64x2_t zero = { };
+
+	for (;;) {
+		v0 ^= vreinterpretq_u64_u8(vld1q_u8(p));
+
+		p += 16;
+		len -= 16;
+		if (len < 16)
+			break;
+
+		v0 = pmull64(fold_consts, v0) ^ pmull64_high(fold_consts, v0);
+	}
+
+	/* Multiply the 128-bit value by x^64 and reduce it back to 128 bits. */
+	v0 = vextq_u64(v0, zero, 1) ^ pmull64_hi_lo(fold_consts, v0);
+
+	/* Final Barrett reduction */
+	uint64x2_t bconsts = vld1q_u64(bconsts_val);
+	uint64x2_t final = pmull64(bconsts, v0);
+
+	v0 ^= vextq_u64(zero, final, 1) ^ pmull64_hi_lo(bconsts, final);
+
+	return vgetq_lane_u64(v0, 1);
+}