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