[PATCH 23/28] perf tools: Harden compressed event processing

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>

Add several hardening checks to the compressed event decompression
pipeline:

1. Guard against decomp_last_rem underflow: check that
   decomp_last->head does not exceed decomp_last->size before
   subtracting.  A u64 underflow here would produce a huge
   decomp_len, causing an oversized mmap allocation.

2. Validate comp_mmap_len from the HEADER_COMPRESSED feature
   section: reject values that are not 4K-aligned, smaller than
   4096, or larger than ~2 GB (prevents size_t overflow when
   adding decomp_last_rem on 32-bit, while allowing legitimate
   large mmap buffers from perf record -m).

3. Validate COMPRESSED event header size: reject events where
   header.size is too small to contain the fixed struct fields,
   preventing underflow in the payload size calculation.

4. Validate COMPRESSED2 event data_size: check that data_size
   does not exceed the available payload (header.size minus the
   fixed struct fields) for the newer compressed format.

5. Reject compressed events when the HEADER_COMPRESSED feature
   is missing from the file header, which means no decompression
   context was initialized.

Reported-by: sashiko-bot@xxxxxxxxxx # Running on a local machine
Assisted-by: Claude Opus 4.6 (1M context) <noreply@xxxxxxxxxxxxx>
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
 tools/perf/util/header.c | 17 +++++++++++++++++
 tools/perf/util/tool.c   | 38 +++++++++++++++++++++++++++++++++++++-
 2 files changed, 54 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index bda8705e87648800..994e54167ea3196b 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3849,6 +3849,23 @@ static int process_compressed(struct feat_fd *ff,
 	if (do_read_u32(ff, &(env->comp_mmap_len)))
 		return -1;
 
+	/*
+	 * FIXME: perf.data should record the recording system's page
+	 * size — it affects mmap buffer alignment, sample addresses,
+	 * and data_page_size/code_page_size interpretation.  Without
+	 * it we assume 4K (the smallest Linux page size) as a safe
+	 * minimum alignment for comp_mmap_len validation.
+	 *
+	 * Cap at 2 GB to keep decomp_len + decomp_last_rem +
+	 * sizeof(struct decomp) within size_t range on 32-bit.
+	 */
+	if (env->comp_mmap_len < 4096 || env->comp_mmap_len % 4096 ||
+	    env->comp_mmap_len > (2U * 1024 * 1024 * 1024 - 4096)) {
+		pr_err("Invalid HEADER_COMPRESSED: comp_mmap_len (%u) must be a 4K-aligned value in [4096, %u]\n",
+		       env->comp_mmap_len, 2U * 1024 * 1024 * 1024 - 4096);
+		return -1;
+	}
+
 	return 0;
 }
 
diff --git a/tools/perf/util/tool.c b/tools/perf/util/tool.c
index ff2150517b75587a..96fa6d6c55cdca1e 100644
--- a/tools/perf/util/tool.c
+++ b/tools/perf/util/tool.c
@@ -24,7 +24,15 @@ static int perf_session__process_compressed_event(const struct perf_tool *tool _
 	size_t mmap_len, decomp_len = perf_session__env(session)->comp_mmap_len;
 	struct decomp *decomp, *decomp_last = session->active_decomp->decomp_last;
 
+	if (!decomp_len) {
+		pr_err("Compressed events found but HEADER_COMPRESSED not set\n");
+		return -1;
+	}
+
 	if (decomp_last) {
+		/* Prevent u64 underflow in decomp_last_rem */
+		if (decomp_last->head > decomp_last->size)
+			return -1;
 		decomp_last_rem = decomp_last->size - decomp_last->head;
 		decomp_len += decomp_last_rem;
 	}
@@ -47,14 +55,37 @@ static int perf_session__process_compressed_event(const struct perf_tool *tool _
 		decomp->size = decomp_last_rem;
 	}
 
+	/*
+	 * Events are read directly from the mmap'd file; fields could
+	 * theoretically change via a FUSE-backed file, but that applies
+	 * to the entire event processing pipeline, not just here.
+	 */
 	if (event->header.type == PERF_RECORD_COMPRESSED) {
+		if (event->header.size < sizeof(struct perf_record_compressed))
+			goto err_decomp;
 		src = (void *)event + sizeof(struct perf_record_compressed);
 		src_size = event->pack.header.size - sizeof(struct perf_record_compressed);
 	} else if (event->header.type == PERF_RECORD_COMPRESSED2) {
+		/*
+		 * prefetch_event() only guarantees that the 8-byte
+		 * event header fits; validate that header.size covers
+		 * the data_size field before accessing it, otherwise a
+		 * crafted event reads data_size from adjacent memory.
+		 */
+		if (event->header.size < sizeof(struct perf_record_compressed2))
+			goto err_decomp;
 		src = (void *)event + sizeof(struct perf_record_compressed2);
 		src_size = event->pack2.data_size;
+		/*
+		 * data_size is independent of header.size (which
+		 * includes padding); verify it doesn't exceed the
+		 * actual payload to prevent out-of-bounds reads in
+		 * zstd_decompress_stream().
+		 */
+		if (src_size > event->header.size - sizeof(struct perf_record_compressed2))
+			goto err_decomp;
 	} else {
-		return -1;
+		goto err_decomp;
 	}
 
 	decomp_size = zstd_decompress_stream(session->active_decomp->zstd_decomp, src, src_size,
@@ -77,6 +108,11 @@ static int perf_session__process_compressed_event(const struct perf_tool *tool _
 	pr_debug("decomp (B): %zd to %zd\n", src_size, decomp_size);
 
 	return 0;
+
+err_decomp:
+	munmap(decomp, mmap_len);
+	pr_err("Couldn't decompress data\n");
+	return -1;
 }
 #endif
 
-- 
2.54.0