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, 152 insertions, 0 deletions

diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c
new file mode 100644
index 000000000..d98014902
--- /dev/null
+++ b/tools/perf/util/zstd.c
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <string.h>
+#include <linux/perf_event.h>
+
+#include "util/compress.h"
+#include "util/debug.h"
+
+int zstd_init(struct zstd_data *data, int level)
+{
+	data->comp_level = level;
+	data->dstream = NULL;
+	data->cstream = NULL;
+	return 0;
+}
+
+int zstd_fini(struct zstd_data *data)
+{
+	if (data->dstream) {
+		ZSTD_freeDStream(data->dstream);
+		data->dstream = NULL;
+	}
+
+	if (data->cstream) {
+		ZSTD_freeCStream(data->cstream);
+		data->cstream = NULL;
+	}
+
+	return 0;
+}
+
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
+				       void *src, size_t src_size, size_t max_record_size,
+				       ssize_t process_header(void *record, size_t dst_size,
+							      size_t data_size))
+{
+	size_t ret, compressed = 0;
+	ssize_t size;
+	ZSTD_inBuffer input = { src, src_size, 0 };
+	ZSTD_outBuffer output;
+	void *record;
+
+	if (!data->cstream) {
+		data->cstream = ZSTD_createCStream();
+		if (data->cstream == NULL) {
+			pr_err("Couldn't create compression stream.\n");
+			return -1;
+		}
+
+		ret = ZSTD_initCStream(data->cstream, data->comp_level);
+		if (ZSTD_isError(ret)) {
+			pr_err("Failed to initialize compression stream: %s\n",
+				ZSTD_getErrorName(ret));
+			return -1;
+		}
+	}
+
+	while (input.pos < input.size) {
+		record = dst;
+		size = process_header(record, dst_size, 0);
+		/* Output buffer full — cannot fit even the record header */
+		if (size < 0)
+			goto reset;
+		compressed += size;
+		dst += size;
+		dst_size -= size;
+		output = (ZSTD_outBuffer){ dst, (dst_size > max_record_size) ?
+						max_record_size : dst_size, 0 };
+		ret = ZSTD_compressStream(data->cstream, &output, &input);
+		ZSTD_flushStream(data->cstream, &output);
+		if (ZSTD_isError(ret)) {
+			pr_err("failed to compress %ld bytes: %s\n",
+				(long)src_size, ZSTD_getErrorName(ret));
+			goto reset;
+		}
+		compressed += output.pos;
+		dst += output.pos;
+		dst_size -= output.pos;
+		/*
+		 * No progress: ZSTD couldn't emit any bytes into the
+		 * remaining output buffer.  Calling process_header
+		 * with output.pos=0 would re-trigger header initialization,
+		 * double-subtracting the header size from dst_size and
+		 * underflowing the unsigned counter.
+		 */
+		if (output.pos == 0)
+			goto reset;
+		size = process_header(record, dst_size, output.pos);
+		if (size < 0)
+			goto reset;
+		compressed += size;
+		dst += size;
+		dst_size -= size;
+	}
+
+	return compressed;
+
+reset:
+	/* Reset so the context is usable if the caller retries */
+	ret = ZSTD_initCStream(data->cstream, data->comp_level);
+	if (ZSTD_isError(ret))
+		pr_err("failed to reset compression context: %s\n",
+			ZSTD_getErrorName(ret));
+	return -1;
+}
+
+size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size,
+			      void *dst, size_t dst_size)
+{
+	size_t ret;
+	ZSTD_inBuffer input = { src, src_size, 0 };
+	ZSTD_outBuffer output = { dst, dst_size, 0 };
+
+	if (!data->dstream) {
+		data->dstream = ZSTD_createDStream();
+		if (data->dstream == NULL) {
+			pr_err("Couldn't create decompression stream.\n");
+			return 0;
+		}
+
+		ret = ZSTD_initDStream(data->dstream);
+		if (ZSTD_isError(ret)) {
+			pr_err("Failed to initialize decompression stream: %s\n",
+				ZSTD_getErrorName(ret));
+			return 0;
+		}
+	}
+	while (input.pos < input.size) {
+		size_t prev_in = input.pos;
+		size_t prev_out = output.pos;
+
+		ret = ZSTD_decompressStream(data->dstream, &output, &input);
+		if (ZSTD_isError(ret)) {
+			pr_err("failed to decompress (B): %zd -> %zd, dst_size %zd : %s\n",
+			       src_size, output.pos, dst_size, ZSTD_getErrorName(ret));
+			return 0;
+		}
+		/*
+		 * Neither stream advanced — decompression is stuck.
+		 * Return 0 (error) rather than partial output: perf
+		 * uses ZSTD_flushStream (not ZSTD_endStream), so the
+		 * stream is continuous across compressed events.
+		 * Discarding unconsumed input would desynchronize the
+		 * decompressor, causing the next call to produce
+		 * garbage that could be misinterpreted as valid events.
+		 */
+		if (input.pos == prev_in && output.pos == prev_out)
+			return 0;
+	}
+
+	return output.pos;
+}