[<prev] [next>] [day] [month] [year] [list]
Message-Id: <200701112007.33854.hnguyen@linux.vnet.ibm.com>
Date: Thu, 11 Jan 2007 20:07:33 +0100
From: Hoang-Nam Nguyen <hnguyen@...ux.vnet.ibm.com>
To: Roland Dreier <rdreier@...co.com>, hch@...radead.org,
linux-kernel@...r.kernel.org, linuxppc-dev@...abs.org,
openfabrics-ewg@...nib.org, openib-general@...nib.org
Cc: raisch@...ibm.com
Subject: [PATCH/RFC 2.6.21 0/5] ehca: remove use of do_mmap() from kernel space
Hello Roland and Christoph H.!
Here is a set of patches for ehca, whose main purpose is to remove unproper use of
do_mmap() in ehca kernel space as suggested by Christoph H. Other "small" changes
are:
* Remove "dead" prototype declarations (those without code implementation)
Now detail on mmap() rework:
- For eHCA hardware register block we use remap_pfn_range() as previously.
- For queue pages we call pattern vm_insert_page() to register each allocated
kernel page.
- For each mmap-ed resource (hardware register block, send/recv and completion
queue) we introduce a use counter that is incremented and decremented by
the call-backs open()/close(). Destroying a completion queue or queue pair
will succeed only if all associated counters are zero. That means those resources
must be mmap-ed and munmap-ed properly in user space.
The actual calls of mmap64() and munmap() are done then in ehca user space lib,
ie. libehca, for which I will send a separate patch for another review (by ofed
group).
Thanks
Nam
ehca_classes.h | 29 +-----
ehca_cq.c | 65 +++-----------
ehca_iverbs.h | 10 --
ehca_main.c | 6 -
ehca_qp.c | 78 +++--------------
ehca_uverbs.c | 253 ++++++++++++++++++---------------------------------------
6 files changed, 121 insertions(+), 320 deletions(-)
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists