On Fri, Oct 4, 2013 at 7:33 AM, Vasiliy Tolstov v.tols...@selfip.ru wrote:
Hi All.
I'm interesting of mellanox ConnectX-3 cards that support VPI.
As a read from
http://www.openfabrics.org/downloads/OFED/ofed-1.4/OFED-1.4-docs/mlx4_release_notes.txt
VPI provide ability to autodetect link type
On Wed, 2 Oct 2013 12:48:19 +0200
Alexander Gordeev agord...@redhat.com wrote:
Multiple MSIs have never been supported on s390 architecture,
but the platform code fails to report single MSI only.
Signed-off-by: Alexander Gordeev agord...@redhat.com
---
arch/s390/pci/pci.c |2 ++
1
On Wed, 2 Oct 2013 12:48:20 +0200
Alexander Gordeev agord...@redhat.com wrote:
arch_setup_msi_irqs() hook can only be called from the generic
MSI code which ensures correct MSI type parameter.
Signed-off-by: Alexander Gordeev agord...@redhat.com
---
arch/s390/pci/pci.c |2 --
1
On Thu, Oct 03, 2013 at 11:49:45PM +0100, Ben Hutchings wrote:
On Wed, 2013-10-02 at 12:48 +0200, Alexander Gordeev wrote:
This update converts pci_enable_msix() and pci_enable_msi_block()
interfaces to canonical kernel functions and makes them return a
error code in case of failure or 0 in
It seems to me that a more useful interface would take a minimum and
maximum number of vectors from the driver. This wouldn't allow the
driver to specify that it could only accept, say, any even number within
a certain range, but you could still leave the current functions
available for
On Fri, Oct 04, 2013 at 09:31:49AM +0100, David Laight wrote:
Mmmm.. I am not sure I am getting it. Could you please rephrase?
One possibility is for drivers than can use a lot of interrupts to
request a minimum number initially and then request the additional
ones much later on.
That
Signed-off-by: Somnath Kotur somnath.ko...@emulex.com
---
v2: Incorporated Steve's comments and changed sockaddr to sockaddr_storage
krping.c | 51 ---
1 files changed, 36 insertions(+), 15 deletions(-)
diff --git a/krping.c b/krping.c
index
These two patches fix flaws that have been
observed in the with qib.
The issue has also been code inspected by
Jan Kara in his get_user_pages_unlocked()
patch series.
By using get_user_pages_fast() the dependency
on Jan's patch set has been removed. I can't
find any issue with losing the force
From: Jan Kara j...@suse.cz
Function ipath_user_sdma_queue_pkts() gets called with mmap_sem held for
writing. Except for get_user_pages() deep down in
ipath_user_sdma_pin_pages() we don't seem to need mmap_sem at all. Even
more interestingly the function ipath_user_sdma_queue_pkts() (and also
These two patches fix flaws that have been
observed in the wild with qib.
The issue has also been code inspected by
Jan Kara in his get_user_pages_unlocked()
patch series.
By using get_user_pages_fast() the dependency
on Jan's patch set has been removed. I can't
find any issue with losing the
From: Jan Kara j...@suse.cz
Function qib_user_sdma_queue_pkts() gets called with mmap_sem held for
writing. Except for get_user_pages() deep down in
qib_user_sdma_pin_pages() we don't seem to need mmap_sem at all. Even
more interestingly the function qib_user_sdma_queue_pkts() (and also
-Original Message-
From: Jan Kara [mailto:j...@suse.cz]
Sent: Wednesday, October 02, 2013 11:39 AM
To: Marciniszyn, Mike
Cc: Jan Kara; LKML; linux...@kvack.org; infinipath; Roland Dreier; linux-
r...@vger.kernel.org
Subject: Re: [PATCH 23/26] ib: Convert qib_get_user_pages() to
The PSM side of the code is a more traditional use of GUP (like direct I/O),
so
I think it is a different use case than the locking for IB memory regions.
I have resubmitted the two deadlock fixes using get_user_pages_fast() and
marked them stable.
See
Even more interestingly the function ipath_user_sdma_queue_pkts() (and
also
ipath_user_sdma_coalesce() called somewhat later) call copy_from_user()
which can hit a page fault and we deadlock on trying to get mmap_sem
when handling that fault. So just make ipath_user_sdma_pin_pages() use
Inadvertent send!
Mike
-Original Message-
From: Marciniszyn, Mike
Sent: Friday, October 04, 2013 9:39 AM
To: Jan Kara
Cc: LKML; linux...@kvack.org; infinipath; Roland Dreier; linux-
r...@vger.kernel.org
Subject: RE: [PATCH 23/26] ib: Convert qib_get_user_pages() to
Convert qib_get_user_pages() to use get_user_pages_unlocked(). This
shortens the section where we hold mmap_sem for writing and also removes
the knowledge about get_user_pages() locking from ipath driver. We also fix
a bug in testing pinned number of pages when changing the code.
This
On 10/4/2013 6:24 AM, Somnath Kotur wrote:
Signed-off-by: Somnath Kotur somnath.ko...@emulex.com
---
v2: Incorporated Steve's comments and changed sockaddr to sockaddr_storage
Hey Somnath, thanks for providing this. What HW have you tested with?
Steve.
--
To unsubscribe from this list:
On Fri 04-10-13 13:52:49, Marciniszyn, Mike wrote:
Convert qib_get_user_pages() to use get_user_pages_unlocked(). This
shortens the section where we hold mmap_sem for writing and also removes
the knowledge about get_user_pages() locking from ipath driver. We also fix
a bug in testing
On Mon, Sep 30, 2013 at 8:56 AM, Marciniszyn, Mike
mike.marcinis...@intel.com wrote:
Is something like the following what you had in mind? If so, I can
just queue it up. Otherwise, I'll wait for Yijing to post a v2 patch.
IB/qib: Use pcie_set_mps() and pcie_get_mps() to simplify code
[-cc extra folks]
On Tue, Sep 24, 2013 at 2:39 PM, Bjorn Helgaas bhelg...@google.com wrote:
On Mon, Sep 09, 2013 at 09:13:06PM +0800, Yijing Wang wrote:
Refactor qib_tune_pcie_caps() function, use pcie_set_mps()
and pcie_get_mps() to simply code. Because pci core caches
the PCI-E Max Payload
On Fri, 2013-10-04 at 10:29 +0200, Alexander Gordeev wrote:
On Thu, Oct 03, 2013 at 11:49:45PM +0100, Ben Hutchings wrote:
On Wed, 2013-10-02 at 12:48 +0200, Alexander Gordeev wrote:
This update converts pci_enable_msix() and pci_enable_msi_block()
interfaces to canonical kernel functions
Hey Somnath, thanks for providing this. What HW have you tested with?
Steve.
Thank you Steve. Have tested it against the Emulex HW / ocrdma driver
--
To unsubscribe from this list: send the line unsubscribe linux-rdma in
the body of a message to majord...@vger.kernel.org
More majordomo
22 matches
Mail list logo