Re: [PATCH] `iwlist scan` fails with many networks available

On Tue, 2019-08-13 at 00:43 +0000, James Nylen wrote:

quoted

I suppose we could consider applying a workaround like this if it has a
condition checking that the buffer passed in is the maximum possible
buffer (65535 bytes, due to iw_point::length being u16)

This is what the latest patch does (attached to my email from
yesterday / https://lkml.org/lkml/2019/8/10/452 ).

Hmm, yes, you're right. I evidently missed the comparisons to 0xFFFF
there, sorry about that.

If you'd like to apply it, I'm happy to make any needed revisions.
Otherwise I'm going to have to keep patching my kernels for this
issue, unfortunately I don't have the time to try to get wicd to
migrate to a better solution.

Not sure which would be easier, but ok :-)

Can you please fix the patch to
 1) use /* */ style comments (see
    https://www.kernel.org/doc/html/latest/process/coding-style.html)

 2) remove extra braces (also per coding style)

 3) use U16_MAX instead of 0xFFFF

I'd also consider renaming "maybe_current_ev" to "next_ev" or something
shorter anyway, and would probably argue that rewriting this

+		if (IS_ERR(maybe_current_ev)) {
+			err = PTR_ERR(maybe_current_ev);
+			if (err == -E2BIG) {
+				// Last BSS failed to copy into buffer.  As
+				// above, only report an error if `iwlist` will
+				// retry again with a larger buffer.
+				if (len >= 0xFFFF) {
+					err = 0;
+				}
+			}
 			break;
+		} else {
+			current_ev = maybe_current_ev;
 		}

to something like

	next_ev = ...
	if (IS_ERR(next_ev)) {
		err = PTR_ERR(next_ev);
		/* mask error and truncate in case buffer cannot be
                 * increased
                 */
		if (err == -E2BIG && len < U16_MAX)
			err = 0;
		break;
	}

	current_ev = next_ev;


could be more readable, but that's just editorial really.

Thanks,
johannes