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, 85 insertions, 0 deletions

diff --git a/lib/crc/arm64/crc32.h b/lib/crc/arm64/crc32.h
new file mode 100644
index 000000000..1939a5dee
--- /dev/null
+++ b/lib/crc/arm64/crc32.h
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
+#include <asm/simd.h>
+
+// The minimum input length to consider the 4-way interleaved code path
+static const size_t min_len = 1024;
+
+asmlinkage u32 crc32_le_arm64(u32 crc, unsigned char const *p, size_t len);
+asmlinkage u32 crc32c_le_arm64(u32 crc, unsigned char const *p, size_t len);
+asmlinkage u32 crc32_be_arm64(u32 crc, unsigned char const *p, size_t len);
+
+asmlinkage u32 crc32_le_arm64_4way(u32 crc, unsigned char const *p, size_t len);
+asmlinkage u32 crc32c_le_arm64_4way(u32 crc, unsigned char const *p, size_t len);
+asmlinkage u32 crc32_be_arm64_4way(u32 crc, unsigned char const *p, size_t len);
+
+static inline u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
+{
+	if (!alternative_has_cap_likely(ARM64_HAS_CRC32))
+		return crc32_le_base(crc, p, len);
+
+	if (len >= min_len && cpu_have_named_feature(PMULL) &&
+	    likely(may_use_simd())) {
+		scoped_ksimd()
+			crc = crc32_le_arm64_4way(crc, p, len);
+
+		p += round_down(len, 64);
+		len %= 64;
+
+		if (!len)
+			return crc;
+	}
+
+	return crc32_le_arm64(crc, p, len);
+}
+
+static inline u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
+{
+	if (!alternative_has_cap_likely(ARM64_HAS_CRC32))
+		return crc32c_base(crc, p, len);
+
+	if (len >= min_len && cpu_have_named_feature(PMULL) &&
+	    likely(may_use_simd())) {
+		scoped_ksimd()
+			crc = crc32c_le_arm64_4way(crc, p, len);
+
+		p += round_down(len, 64);
+		len %= 64;
+
+		if (!len)
+			return crc;
+	}
+
+	return crc32c_le_arm64(crc, p, len);
+}
+
+static inline u32 crc32_be_arch(u32 crc, const u8 *p, size_t len)
+{
+	if (!alternative_has_cap_likely(ARM64_HAS_CRC32))
+		return crc32_be_base(crc, p, len);
+
+	if (len >= min_len && cpu_have_named_feature(PMULL) &&
+	    likely(may_use_simd())) {
+		scoped_ksimd()
+			crc = crc32_be_arm64_4way(crc, p, len);
+
+		p += round_down(len, 64);
+		len %= 64;
+
+		if (!len)
+			return crc;
+	}
+
+	return crc32_be_arm64(crc, p, len);
+}
+
+static inline u32 crc32_optimizations_arch(void)
+{
+	if (alternative_has_cap_likely(ARM64_HAS_CRC32))
+		return CRC32_LE_OPTIMIZATION |
+		       CRC32_BE_OPTIMIZATION |
+		       CRC32C_OPTIMIZATION;
+	return 0;
+}