Re: [PATCH] tcp_vu: Fix off-by one in header count array adjustment

[Stefano Brivio <sbrivio@redhat.com>]

On Wed, 12 Feb 2025 11:57:10 +1100
David Gibson <david@gibson.dropbear.id.au> wrote:

> On Tue, Feb 11, 2025 at 08:51:33PM +0100, Stefano Brivio wrote:
> > From: Laurent Vivier <lvivier@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@gibson.dropbear.id.au>
> > [sbrivio: commit message, albeit not really descriptive]
> > Signed-off-by: Stefano Brivio <sbrivio@redhat.com>  
> 
> I think I've understood the surrounding code enough to say,
> 
> Reviewed-by: David Gibson <david@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.
> 
> ###

Ah, great, that starts making sense. Applied with this commit message.

-- 
Stefano