[ofa-general] Re: [PATCH 1/1] IB/iSER: Add missing counter incrementation in iser_data_buf_aligned_len

[Roland Dreier]

thanks, applied.

 > The following patch fixes a bug in iSER. Without it, iSER will have poor
 > performance. Can you push it upstream for 2.6.24?

Please put commentary like this (that should not go into the kernel
changelog) after the '---' line in your email, so that it is
automatically dropped when I import the patch into git.

 > diff --git a/drivers/infiniband/ulp/iser/iser_memory.c
 > b/drivers/infiniband/ulp/iser/iser_memory.c
 > index d687980..a28f552 100644
 > --- a/drivers/infiniband/ulp/iser/iser_memory.c

Something line-wrapped your email too...

 > +			if (end_addr == next_addr) {
 > +				cnt++;
 >  				continue;
 > +			}
 >  			else if (!IS_4K_ALIGNED(end_addr)) {

For this type of change, please put the '}' on the same line as the
'else' (I fixed it by hand).

Also, I never noticed this before, but the use of IS_4K_ALIGNED()
seems pretty suspicious here.  Why are you hard-coding 4K?  What would
be the correct thing on a system with 64K pages and an HCA that can
handle 512-byte aligned memory regions?

 - R.