On Tue, Feb 11, 2025 at 08:51:33PM +0100, Stefano
Brivio wrote:
From: Laurent Vivier <lvivier(a)redhat.com>
Not entirely clear to me why, but Laurent proposed this patch to fix
an issue were we would end up with a zero buf_cnt in
tcp_vu_data_from_sock() and all sorts of weirdnesses.
Reported-by: David Gibson <david(a)gibson.dropbear.id.au>
[sbrivio: commit message, albeit not really descriptive]
Signed-off-by: Stefano Brivio <sbrivio(a)redhat.com>
I think I've understood the surrounding code enough to say,
Reviewed-by: David Gibson <david(a)gibson.dropbear.id.au>
and offer this possible description if we don't hear from Laurent in
time.
###
head_cnt represents the number of frames we're going to forward to the
guest in tcp_vu_sock_recv(), each of which could require multiple
buffers ("elements"). We initialise it with as many frames as we can
find space for in vu buffers, and we then need to adjust it down to
the number of frames we actually (partially) filled.
We adjust it down based on number of individual buffers used by the
data from recvmsg(). At this point 'i' is *one greater than* that
number of buffers, so we need to discard all (unused) frames with a
buffer index >= i, instead of > i.
###