All of lore.kernel.org
 help / color / mirror / Atom feed
From: James Bottomley <James.Bottomley@SteelEye.com>
To: Andrew Morton <akpm@osdl.org>, Linus Torvalds <torvalds@osdl.org>
Cc: Linux Kernel <linux-kernel@vger.kernel.org>
Subject: [BK PATCH] on-chip coherent memory API for DMA
Date: 06 Jul 2004 18:14:35 -0500	[thread overview]
Message-ID: <1089155678.2854.796.camel@mulgrave> (raw)

This is a rollup of the previous patch I sent to the list for the
on-chip API.  It's available at

bk://linux-voyager.bkbits.net/dma-declare-coherent-memory-2.6

I split the patches I sent up into the five separate areas that they
affect:

ChangeSet@1.1783, 2004-06-30 21:44:24-05:00, jejb@mulgrave.(none)
  Convert NCR_Q720 to use dma_declare_coherent_memory
  
  This board makes an ideal example for using the API
  since it consists of 4 SCSI I/O processors and a 
  0.5-2MB block of memory on a single MCA card.
  
  Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>

ChangeSet@1.1782, 2004-06-30 21:38:34-05:00, jejb@mulgrave.(none)
  Add x86 implementation of dma_declare_coherent_memory
  
  This actually implements the API (all except for
  DMA_MEMORY_INCLUDES_CHILDREN).
  
  Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>

ChangeSet@1.1781, 2004-06-30 21:11:14-05:00, jejb@mulgrave.(none)
  Add vmalloc alignment constraints
  
  vmalloc is used by ioremap() to get regions for
  remapping I/O space.  To feed these regions back
  into a __get_free_pages() type memory allocator,
  they are expected to have more alignment than 
  get_vm_area() proves.  So add additional alignment
  constraints for VM_IOREMAP.
  
  Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>

ChangeSet@1.1780, 2004-06-30 21:08:15-05:00, jejb@mulgrave.(none)
  Add memory region bitmap implementations
  
  These APIs deal with bitmaps representing contiguous
  memory regions.  The idea is to set, free and find
  a contiguous area.
  
  For ease of implementation (as well as to conform
  to the standard requirements), the bitmaps always
  return n aligned n length regions.  The implementation
  is also limited to BITS_PER_LONG contiguous regions.
  
  Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>

ChangeSet@1.1779, 2004-06-30 21:02:11-05:00, jejb@mulgrave.(none)
  Add dma_declare_coherent_memory() API
  
  This adds the description and a null prototype.
  
  Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>

And the diffstat is:

 Documentation/DMA-API.txt      |   79 +++++++++++++++++++++++++++++
 arch/i386/kernel/pci-dma.c     |  111 ++++++++++++++++++++++++++++++++++++++++-
 drivers/scsi/NCR_Q720.c        |   21 ++++++-
 include/asm-i386/dma-mapping.h |   12 ++++
 include/linux/bitmap.h         |    3 +
 include/linux/device.h         |    3 +
 include/linux/dma-mapping.h    |   26 +++++++++
 lib/bitmap.c                   |   76 ++++++++++++++++++++++++++++
 mm/vmalloc.c                   |   20 ++++++-
 9 files changed, 344 insertions(+), 7 deletions(-)

James



                 reply	other threads:[~2004-07-06 23:15 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=1089155678.2854.796.camel@mulgrave \
    --to=james.bottomley@steeleye.com \
    --cc=akpm@osdl.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=torvalds@osdl.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.