From: Leon Romanovsky <leon@kernel.org>
To: Doug Ledford <dledford@redhat.com>, Jason Gunthorpe <jgg@nvidia.com>
Cc: Leon Romanovsky <leonro@nvidia.com>,
linux-kernel@vger.kernel.org, linux-rdma@vger.kernel.org,
Yishai Hadas <yishaih@nvida.com>,
Yishai Hadas <yishaih@nvidia.com>,
Christoph Hellwig <hch@infradead.org>
Subject: [PATCH rdma-next v1 0/4] Improve ODP by using HMM API
Date: Thu, 17 Sep 2020 14:21:48 +0300 [thread overview]
Message-ID: <20200917112152.1075974-1-leon@kernel.org> (raw)
From: Leon Romanovsky <leonro@nvidia.com>
Changelog:
v1:
* Cleaned code.
* Support a potential valid dma_address of NULL by flags detection,
note was added to clarify things as was asked.
* Fix 80 character lines in few places.
v0: https://lore.kernel.org/lkml/20200914113949.346562-1-leon@kernel.org
Based on:
https://lore.kernel.org/lkml/20200914112653.345244-1-leon@kernel.org/
---------------------------------------------------------------------------------------
From Yishai:
This series improves ODP performance by moving to use the HMM API as of below.
The get_user_pages_remote() functionality was replaced by HMM:
- No need anymore to allocate and free memory to hold its output per call.
- No need anymore to use the put_page() to unpin the pages.
- The logic to detect contiguous pages is done based on the returned order
from HMM, no need to run per page, and evaluate.
Moving to use the HMM enables to reduce page faults in the system by using the
snapshot mode. This mode allows existing pages in the CPU to become presented
to the device without faulting.
This non-faulting mode may be used explicitly by an application with some new
option of advice MR (i.e. PREFETCH_NO_FAULT) and is used upon ODP MR
registration internally as part of initiating the device page table.
To achieve the above, internal changes in the ODP data structures were done
and some flows were cleaned-up/adapted accordingly.
Thanks
Yishai Hadas (4):
IB/core: Improve ODP to use hmm_range_fault()
IB/core: Enable ODP sync without faulting
RDMA/mlx5: Extend advice MR to support non faulting mode
RDMA/mlx5: Sync device with CPU pages upon ODP MR registration
drivers/infiniband/Kconfig | 1 +
drivers/infiniband/core/umem_odp.c | 286 ++++++++++--------------
drivers/infiniband/hw/mlx5/mlx5_ib.h | 6 +
drivers/infiniband/hw/mlx5/mr.c | 14 +-
drivers/infiniband/hw/mlx5/odp.c | 49 ++--
include/rdma/ib_umem_odp.h | 21 +-
include/uapi/rdma/ib_user_ioctl_verbs.h | 1 +
7 files changed, 176 insertions(+), 202 deletions(-)
--
2.26.2
reply other threads:[~2020-09-17 11:22 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200917112152.1075974-1-leon@kernel.org \
--to=leon@kernel.org \
--cc=dledford@redhat.com \
--cc=hch@infradead.org \
--cc=jgg@nvidia.com \
--cc=leonro@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=yishaih@nvida.com \
--cc=yishaih@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).