diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4a30688699d5..a33c78f030d9 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -2744,7 +2744,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 			trigger_error(&auxtrace_snapshot_trigger);
 			trigger_error(&switch_output_trigger);
 			err = -1;
-			goto out_child;
+			goto out_child_no_flush;
 		}
 
 		if (auxtrace_record__snapshot_started) {
@@ -2891,6 +2891,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 out_child:
 	record__stop_threads(rec);
 	record__mmap_read_all(rec, true);
+	goto out_free_threads;
+out_child_no_flush:
+	/* mmap read already failed — retrying would just fail again */
+	record__stop_threads(rec);
 out_free_threads:
 	record__free_thread_data(rec);
 	evlist__finalize_ctlfd(rec->evlist);
diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c
index 57027e0ac7b6..ecda9deb53b7 100644
--- a/tools/perf/util/zstd.c
+++ b/tools/perf/util/zstd.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <string.h>
+#include <linux/perf_event.h>
 
 #include "util/compress.h"
 #include "util/debug.h"
@@ -54,7 +55,13 @@ ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_
 
 	while (input.pos < input.size) {
 		record = dst;
+		/* process_header writes the event header into record */
+		if (dst_size < sizeof(struct perf_event_header))
+			goto reset;
 		size = process_header(record, 0);
+		/* Output buffer full — cannot fit even the record header */
+		if (size > dst_size)
+			goto reset;
 		compressed += size;
 		dst += size;
 		dst_size -= size;
@@ -65,10 +72,18 @@ ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_
 		if (ZSTD_isError(ret)) {
 			pr_err("failed to compress %ld bytes: %s\n",
 				(long)src_size, ZSTD_getErrorName(ret));
-			memcpy(dst, src, src_size);
-			return src_size;
+			goto reset;
 		}
 		size = output.pos;
+		/*
+		 * No progress: ZSTD couldn't emit any bytes into the
+		 * remaining output buffer.  Calling process_header
+		 * with size=0 would re-trigger header initialization,
+		 * double-subtracting the header size from dst_size and
+		 * underflowing the unsigned counter.
+		 */
+		if (size == 0)
+			goto reset;
 		size = process_header(record, size);
 		compressed += size;
 		dst += size;
@@ -76,6 +91,14 @@ ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, 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,