linux-nfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@infradead.org>
To: Leon Romanovsky <leon@kernel.org>
Cc: Chuck Lever <chuck.lever@oracle.com>,
	Sagi Grimberg <sagi@grimberg.me>,
	linux-rdma@vger.kernel.org, linux-nfs@vger.kernel.org
Subject: Re: [PATCH v3 25/25] IB/mlx4: Workaround for mlx4_alloc_priv_pages() array allocator
Date: Wed, 22 Jun 2016 09:20:51 -0700	[thread overview]
Message-ID: <20160622162051.GA23929@infradead.org> (raw)
In-Reply-To: <20160622155003.GI9762@leon.nu>


On Wed, Jun 22, 2016 at 06:50:03PM +0300, Leon Romanovsky wrote:
> According to [1] dma_alloc_coherent doesn't allocate from pool, but
> calls to the __get_free_page().

Use the source luke!  dma_alloc_coherent implementations vary widely.
While some indeed use alloc_pages there are various complications,
especially on non-x86 architectures, or if the dma mask is not the full
64 bits allowed.

> "A DMA pool is an allocation mechanism for small, coherent DMA mappings.
> Mappings obtained from dma_alloc_coherent may have a minimum size of one
> page."

Just because it's not using the dma_pool_* API it could allocate from
various resource constrained pools.  A trivial example for that is
the swiotlb used for address limited devices if no hardware IOMMU
is available, but other architectures have even more complicated
implementations by default.  Take a look at
arch/arm/mm/dma-mapping.c:__dma_alloc() for fun.

  reply	other threads:[~2016-06-22 16:21 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-20 16:08 [PATCH v3 00/25] NFS/RDMA client patches proposed for v4.8 Chuck Lever
2016-06-20 16:08 ` [PATCH v3 01/25] xprtrdma: Remove FMRs from the unmap list after unmapping Chuck Lever
2016-06-27 17:47   ` Anna Schumaker
2016-06-28 20:53     ` Chuck Lever
2016-06-20 16:08 ` [PATCH v3 02/25] xprtrdma: Create common scatterlist fields in rpcrdma_mw Chuck Lever
2016-06-20 16:08 ` [PATCH v3 03/25] xprtrdma: Move init and release helpers Chuck Lever
2016-06-20 16:09 ` [PATCH v3 04/25] xprtrdma: Rename fields in rpcrdma_fmr Chuck Lever
2016-06-20 16:09 ` [PATCH v3 05/25] xprtrdma: Use scatterlist for DMA mapping and unmapping under FMR Chuck Lever
2016-06-20 16:09 ` [PATCH v3 06/25] xprtrdma: Refactor MR recovery work queues Chuck Lever
2016-06-20 16:09 ` [PATCH v3 07/25] xprtrdma: Do not leak an MW during a DMA map failure Chuck Lever
2016-06-20 16:09 ` [PATCH v3 08/25] xprtrdma: Remove ALLPHYSICAL memory registration mode Chuck Lever
2016-06-20 16:09 ` [PATCH v3 09/25] xprtrdma: Remove rpcrdma_map_one() and friends Chuck Lever
2016-06-20 16:09 ` [PATCH v3 10/25] xprtrdma: Clean up device capability detection Chuck Lever
2016-06-20 16:10 ` [PATCH v3 11/25] xprtrdma: Reply buffer exhaustion can be catastrophic Chuck Lever
2016-06-20 16:10 ` [PATCH v3 12/25] xprtrdma: Honor ->send_request API contract Chuck Lever
2016-06-20 16:10 ` [PATCH v3 13/25] xprtrdma: Chunk list encoders must not return zero Chuck Lever
2016-06-20 16:10 ` [PATCH v3 14/25] xprtrdma: Allocate MRs on demand Chuck Lever
2016-06-20 16:10 ` [PATCH v3 15/25] xprtrdma: Release orphaned MRs immediately Chuck Lever
2016-06-20 16:10 ` [PATCH v3 16/25] xprtrdma: Place registered MWs on a per-req list Chuck Lever
2016-06-20 16:10 ` [PATCH v3 17/25] xprtrdma: Chunk list encoders no longer share one rl_segments array Chuck Lever
2016-06-20 16:11 ` [PATCH v3 18/25] xprtrdma: rpcrdma_inline_fixup() overruns the receive page list Chuck Lever
2016-06-20 16:11 ` [PATCH v3 19/25] xprtrdma: Do not update {head, tail}.iov_len in rpcrdma_inline_fixup() Chuck Lever
2016-06-20 16:11 ` [PATCH v3 20/25] xprtrdma: Update only specific fields in private receive buffer Chuck Lever
2016-06-20 16:11 ` [PATCH v3 21/25] xprtrdma: Clean up fixup_copy_count accounting Chuck Lever
2016-06-20 16:11 ` [PATCH v3 22/25] xprtrdma: No direct data placement with krb5i and krb5p Chuck Lever
2016-06-20 16:11 ` [PATCH v3 23/25] svc: Avoid garbage replies when pc_func() returns rpc_drop_reply Chuck Lever
2016-06-20 16:11 ` [PATCH v3 24/25] NFS: Don't drop CB requests with invalid principals Chuck Lever
2016-06-20 16:12 ` [PATCH v3 25/25] IB/mlx4: Workaround for mlx4_alloc_priv_pages() array allocator Chuck Lever
2016-06-21  5:52   ` Or Gerlitz
2016-06-22 13:29     ` Sagi Grimberg
2016-06-22 13:47       ` Or Gerlitz
2016-06-22 14:02         ` Sagi Grimberg
2016-06-22 11:56   ` Sagi Grimberg
2016-06-22 14:04   ` Sagi Grimberg
2016-06-22 14:09     ` Leon Romanovsky
2016-06-22 14:47     ` Chuck Lever
2016-06-22 15:50       ` Leon Romanovsky
2016-06-22 16:20         ` Christoph Hellwig [this message]
2016-06-20 18:53 ` [PATCH v3 00/25] NFS/RDMA client patches proposed for v4.8 Steve Wise
2016-06-20 19:07   ` Chuck Lever

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=20160622162051.GA23929@infradead.org \
    --to=hch@infradead.org \
    --cc=chuck.lever@oracle.com \
    --cc=leon@kernel.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=sagi@grimberg.me \
    /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).