RE: [PATCH v7 0/4] arch: Add lightweight memory barriers for coherent memory access

[Skidmore, Donald C]

> -----Original Message-----
> From: Alexander Duyck [mailto:alexander.duyck@xxxxxxxxx]
> Sent: Wednesday, December 10, 2014 9:29 PM
> To: Alexander Duyck; linux-arch@xxxxxxxxxxxxxxx; netdev@xxxxxxxxxxxxxxx;
> linux-kernel@xxxxxxxxxxxxxxx; arnd@xxxxxxxx; davem@xxxxxxxxxxxxx
> Cc: mathieu.desnoyers@xxxxxxxxxx; peterz@xxxxxxxxxxxxx;
> benh@xxxxxxxxxxxxxxxxxxx; heiko.carstens@xxxxxxxxxx; mingo@xxxxxxxxxx;
> mikey@xxxxxxxxxxx; linux@xxxxxxxxxxxxxxxx; Skidmore, Donald C; Vick,
> Matthew; geert@xxxxxxxxxxxxxx; Kirsher, Jeffrey T; romieu@xxxxxxxxxxxxx;
> paulmck@xxxxxxxxxxxxxxxxxx; nic_swsd@xxxxxxxxxxx;
> will.deacon@xxxxxxx; michael@xxxxxxxxxxxxxx; Luck, Tony; torvalds@linux-
> foundation.org; oleg@xxxxxxxxxx; schwidefsky@xxxxxxxxxx;
> fweisbec@xxxxxxxxx
> Subject: Re: [PATCH v7 0/4] arch: Add lightweight memory barriers for
> coherent memory access
> 
> On 11/25/2014 12:35 PM, Alexander Duyck wrote:
> > These patches introduce two new primitives for synchronizing cache
> > coherent memory writes and reads.  These two new primitives are:
> >
> > 	dma_rmb()
> > 	dma_wmb()
> >
> > The first patch cleans up some unnecessary overhead related to the
> > definition of read_barrier_depends, smp_read_barrier_depends, and
> > comments related to the barrier.
> >
> > The second patch adds the primitives for the applicable architectures
> > and asm-generic.
> >
> > The third patch adds the barriers to r8169 which turns out to be a
> > good example of where the new barriers might be useful as they have
> > full
> > rmb()/wmb() barriers ordering accesses to the descriptors and the
> > DescOwn bit.
> >
> > The fourth patch adds support for coherent_rmb() to the Intel fm10k,
> > igb, and ixgbe drivers.  Testing with the ixgbe driver has shown a
> > processing time reduction of at least 7ns per 64B frame on a Core i7-4930K.
> >
> > This patch series is essentially the v7 for:
> > v4-6:	Add lightweight memory barriers for coherent memory access
> > v3:	Add lightweight memory barriers fast_rmb() and fast_wmb()
> > v2:	Introduce load_acquire() and store_release()
> > v1:	Introduce read_acquire()
> >
> > The key changes in this patch series versus the earlier patches are:
> > v7:
> > 	- Dropped test/debug patch that was accidentally slipped in
> > v6:
> > 	- Replaced "memory based device I/O" with "consistent memory" in
> > 	  docs
> > 	- Added reference to DMA-API.txt to explain consistent memory
> > v5:
> > 	- Renamed barriers dma_rmb and dma_wmb
> > 	- Undid smp_wmb changes in x86 and PowerPC
> > 	- Defined smp_rmb as __lwsync for SMP case on PowerPC
> > v4:
> > 	- Renamed barriers coherent_rmb and coherent_wmb
> > 	- Added smp_lwsync for use in
> smp_load_acquire/smp_store_release
> > v3:
> > 	- Moved away from acquire()/store() and instead focused on barriers
> > 	- Added cleanup of read_barrier_depends
> > 	- Added change in r8169 to fix cur_tx/DescOwn ordering
> > 	- Simplified changes to just replacing/moving barriers in r8169
> > 	- Added update to documentation with code example
> > v2:
> > 	- Renamed read_acquire() to be consistent with smp_load_acquire()
> > 	- Changed barrier used to be consistent with smp_load_acquire()
> > 	- Updated PowerPC code to use __lwsync based on IBM article
> > 	- Added store_release() as this is a viable use case for drivers
> > 	- Added r8169 patch which is able to fully use primitives
> > 	- Added fm10k/igb/ixgbe patch which is able to test performance
> >
> > ---
> >
> > Alexander Duyck (4):
> >       arch: Cleanup read_barrier_depends() and comments
> >       arch: Add lightweight memory barriers dma_rmb() and dma_wmb()
> >       r8169: Use dma_rmb() and dma_wmb() for DescOwn checks
> >       fm10k/igb/ixgbe: Use dma_rmb on Rx descriptor reads
> >
> >
> >  Documentation/memory-barriers.txt             |   42 +++++++++++++++
> >  arch/alpha/include/asm/barrier.h              |   51 ++++++++++++++++++
> >  arch/arm/include/asm/barrier.h                |    4 +
> >  arch/arm64/include/asm/barrier.h              |    3 +
> >  arch/blackfin/include/asm/barrier.h           |   51 ++++++++++++++++++
> >  arch/ia64/include/asm/barrier.h               |   25 ++++-----
> >  arch/metag/include/asm/barrier.h              |   19 ++++---
> >  arch/mips/include/asm/barrier.h               |   61 ++--------------------
> >  arch/powerpc/include/asm/barrier.h            |   19 ++++---
> >  arch/s390/include/asm/barrier.h               |    7 ++-
> >  arch/sparc/include/asm/barrier_64.h           |    7 ++-
> >  arch/x86/include/asm/barrier.h                |   70 ++++---------------------
> >  arch/x86/um/asm/barrier.h                     |   20 ++++---
> >  drivers/net/ethernet/intel/fm10k/fm10k_main.c |    6 +-
> >  drivers/net/ethernet/intel/igb/igb_main.c     |    6 +-
> >  drivers/net/ethernet/intel/ixgbe/ixgbe_main.c |    9 +--
> >  drivers/net/ethernet/realtek/r8169.c          |   29 ++++++++--
> >  include/asm-generic/barrier.h                 |    8 +++
> >  18 files changed, 258 insertions(+), 179 deletions(-)
> >
> > --
> 
> It occurs to me that I never got a sign off from any of the maintainers on
> getting this pulled in.
> 
> Since the merge window is open I was wondering which tree I should make
> sure these patches apply to and who will be the one to pull them in?
> Since I was modifying network drivers should I resubmit them for netdev, or
> should I submit them for asm-generic or some other tree?
> 
> - Alex

For at least ixgbe, it looks good to me.

Acked-by: Don Skidmore <donald.c.skidmore@xxxxxxxxx>