Re: [RESEND][PATCH 0/7] Avoid overflow at boundary_size

[Christoph Hellwig <hch@xxxxxx>]

On Tue, Sep 01, 2020 at 12:54:01AM -0700, Nicolin Chen wrote:
> Hi Christoph,
> 
> On Tue, Sep 01, 2020 at 09:36:23AM +0200, Christoph Hellwig wrote:
> > I really don't like all the open coded smarts in the various drivers.
> > What do you think about a helper like the one in the untested patch
> 
> A helper function will be actually better. I was thinking of
> one yet not very sure about the naming and where to put it.
> 
> > below (on top of your series).  Also please include the original
> > segment boundary patch with the next resend so that the series has
> > the full context.
> 
> I will use your change instead and resend with the ULONG_MAX
> change. But in that case, should I make separate changes for
> different files like this series, or just one single change
> like yours?
> 
> Asking this as I was expecting that those changes would get
> applied by different maintainers. But now it feels like you
> will merge it to your tree at once?

I guess one patch is fine.  I can queue it up in the dma-mapping
tree as a prep patch for the default boundary change.