On Mon, May 12, 2025 at 11:58 AM Song Liu song@kernel.org wrote:

On Mon, May 12, 2025 at 10:41 AM T.J. Mercier tjmercier@google.com wrote: [...]

...

+static int udmabuf;

static int udmabuf = -1;

...

+static const char udmabuf_test_buffer_name[DMA_BUF_NAME_LEN] = "udmabuf_test_buffer_for_iter"; +static size_t udmabuf_test_buffer_size; +static int sysheap_dmabuf;

static int sysheap_dmabuf = -1;

We don't really need the -1 since the rework in this version initializes them to -1 on failure, but I'll add it anyway.

...

+static const char sysheap_test_buffer_name[DMA_BUF_NAME_LEN] = "sysheap_test_buffer_for_iter"; +static size_t sysheap_test_buffer_size;

+static int create_udmabuf(void) +{

•   struct udmabuf_create create;
  

nit: zero initialize create to be future proof.

Ok, done.

...

•   int dev_udmabuf, memfd, local_udmabuf;
  

•   udmabuf_test_buffer_size = 10 * getpagesize();
  

[...]

...

+static void subtest_dmabuf_iter_check_default_iter(struct dmabuf_iter *skel) +{

•   bool found_test_sysheap_dmabuf = false;
  

•   bool found_test_udmabuf = false;
  

•   struct DmabufInfo bufinfo;
  

•   size_t linesize = 0;
  

•   char *line = NULL;
  

•   FILE *iter_file;
  

•   int iter_fd, f = INODE;
  

•   iter_fd = bpf_iter_create(bpf_link__fd(skel->links.dmabuf_collector));
  

•   ASSERT_OK_FD(iter_fd, "iter_create");
  

Should we check ASSERT_OK_FD() and exit early on failures?

We should fallthrough on error, but let's add the early out.

...

•   iter_file = fdopen(iter_fd, "r");
  

•   ASSERT_OK_PTR(iter_file, "fdopen");
  

Same here. [...]

...

+/*

• • Fields output by this iterator are delimited by newlines. Convert any
• • newlines in user-provided printed strings to spaces.
• */

+static void sanitize_string(char *src, size_t size) +{

•   for (char *c = src; c && (size_t)(c - src) < size; ++c)
  

Should this be:

for (char *c = src; *c && (size_t)(c - src) < size; ++c)

?

Yes! Thanks.

Thanks, Song

[...]