perf header: Validate bitmap size before allocating in do_read_bitmap()

do_read_bitmap() reads a u64 bit count from the file and passes it
to bitmap_zalloc() without checking it against the remaining section
size. A crafted perf.data could trigger a large allocation that would
only fail later when the per-element reads exceed section bounds.

Additionally, bitmap_zalloc() takes an int parameter, so a crafted
size with bits set above bit 31 (e.g. 0x100000040) would pass the
section bounds check but truncate when passed to bitmap_zalloc(),
allocating a much smaller buffer than the subsequent read loop
expects.

Reject size values that exceed INT_MAX, and check that the data
needed (BITS_TO_U64(size) u64 values) fits in the remaining section
before allocating.  Switch from bitmap_zalloc() to calloc() of u64
units so the allocation size matches the u64 read/write granularity
and avoids unsigned long vs u64 mismatch on 32-bit architectures.

Fix do_write_bitmap() to use memcpy to read u64-sized chunks from
the unsigned long bitmap, preventing out-of-bounds reads on 32-bit
systems where sizeof(unsigned long) is 4 but the bitmap is stored
in u64 units.

Fix process_mem_topology() minimum section size: the check used
nr * 2 * sizeof(u64) per node, but do_read_bitmap() reads an
additional u64 for the bitmap size, so the minimum is 3 * sizeof(u64).

Fix memory leak in process_mem_topology() error paths: replace
free(nodes) with memory_node__delete_nodes() to free per-node
bitmaps allocated by do_read_bitmap().

Currently used by process_mem_topology() for HEADER_MEM_TOPOLOGY.

Fixes: a881fc5603 ("perf header: Sanity check HEADER_MEM_TOPOLOGY")
Closes: https://lore.kernel.org/linux-perf-users/20260414224622.2AE69C19425@smtp.kernel.org/
Closes: https://lore.kernel.org/linux-perf-users/20260410223242.DD76FC19421@smtp.kernel.org/
Reported-by: sashiko-bot@kernel.org # Running on a local machine
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Assisted-by: Claude:claude-opus-4.6-1m
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/header.c

@@ -178,15 +178,25 @@ int do_write(struct feat_fd *ff, const void *buf, size_t size)
 /* Return: 0 if succeeded, -ERR if failed. */
 static int do_write_bitmap(struct feat_fd *ff, unsigned long *set, u64 size)
 {
-	u64 *p = (u64 *) set;
+	size_t byte_size = BITS_TO_LONGS(size) * sizeof(unsigned long);
 	int i, ret;
 
 	ret = do_write(ff, &size, sizeof(size));
 	if (ret < 0)
 		return ret;
 
+	/*
+	 * The on-disk format uses u64 elements, but the in-memory bitmap
+	 * uses unsigned long, which is only 4 bytes on 32-bit architectures.
+	 * Copy with bounded size so the last element doesn't read past the
+	 * bitmap allocation when BITS_TO_LONGS(size) is odd.
+	 */
 	for (i = 0; (u64) i < BITS_TO_U64(size); i++) {
-		ret = do_write(ff, p + i, sizeof(*p));
+		u64 val = 0;
+		size_t off = i * sizeof(val);
+
+		memcpy(&val, (char *)set + off, min(sizeof(val), byte_size - off));
+		ret = do_write(ff, &val, sizeof(val));
 		if (ret < 0)
 			return ret;
 	}
@@ -335,7 +345,20 @@ static int do_read_bitmap(struct feat_fd *ff, unsigned long **pset, u64 *psize)
 	if (ret)
 		return ret;
 
-	set = bitmap_zalloc(size);
+	/* Bitmap APIs use int for nbits; reject u64 values that truncate. */
+	if (size > INT_MAX ||
+	    BITS_TO_U64(size) > (ff->size - ff->offset) / sizeof(u64)) {
+		pr_debug("do_read_bitmap: size %" PRIu64 " exceeds section bounds\n", size);
+		return -1;
+	}
+
+	/*
+	 * bitmap_zalloc() allocates in unsigned long units, which are only
+	 * 4 bytes on 32-bit architectures. The read loop below casts the
+	 * buffer to u64 * and writes 8-byte elements, so allocate in u64
+	 * units to ensure the buffer is large enough.
+	 */
+	set = calloc(BITS_TO_U64(size), sizeof(u64));
 	if (!set)
 		return -ENOMEM;
 
@@ -3497,7 +3520,8 @@ static int process_mem_topology(struct feat_fd *ff,
 		return -1;
 	}
 
-	if (ff->size < 3 * sizeof(u64) + nr * 2 * sizeof(u64)) {
+	/* Per node: node_id(u64) + mem_size(u64) + bitmap_nr_bits(u64) */
+	if (ff->size < 3 * sizeof(u64) + nr * 3 * sizeof(u64)) {
 		pr_err("Invalid HEADER_MEM_TOPOLOGY: section too small (%zu) for %llu nodes\n",
 		       ff->size, (unsigned long long)nr);
 		return -1;
@@ -3532,7 +3556,7 @@ static int process_mem_topology(struct feat_fd *ff,
 
 out:
 	if (ret)
-		free(nodes);
+		memory_node__delete_nodes(nodes, nr);
 	return ret;
 }