ib_flush_fmr_pool() is called,
and other FMR users are not affected. Simply move used entries
from the clean list onto the dirty list before letting the
cleanup thread do its job.
Signed-off-by: Pete Wyckoff <[EMAIL PROTECTED]>
---
drivers/infiniband/core/fmr_pool.c | 17 ++
used FMR
entries also to be purged. During that process, another thread
can see that there are no free FMRs and fail, even though
there should always have been enough available.
Signed-off-by: Pete Wyckoff <[EMAIL PROTECTED]>
---
drivers/infiniband/core/fmr_pool.c | 21 ++
[EMAIL PROTECTED] wrote on Mon, 25 Feb 2008 15:02 -0800:
> Ugh.
[pw wrote:]
> > Looking at the FMR dirty list unmapping code in
> > ib_fmr_batch_release(), there is a section that pulls all the dirty
> > entries onto a list that it will later unmap and put back on the
> > free list.
>
> > But
[EMAIL PROTECTED] wrote on Tue, 12 Feb 2008 20:09 -0800:
> One other area that has not been brought up yet (I think) is the
> applicability of notifiers in letting users know when pinned memory
> is reclaimed by the kernel. This is useful when a lower-level
> library employs lazy deregistration st
[EMAIL PROTECTED] wrote on Wed, 30 Jan 2008 10:34 -0600:
> On Wed, 2008-01-30 at 09:38 +0100, Bart Van Assche wrote:
> > On Jan 30, 2008 12:32 AM, FUJITA Tomonori <[EMAIL PROTECTED]> wrote:
> > >
> > > iSER has parameters to limit the maximum size of RDMA (it needs to
> > > repeat RDMA with a poor
[EMAIL PROTECTED] wrote on Wed, 16 Jan 2008 16:31 +0100:
>
> * Pete Wyckoff <[EMAIL PROTECTED]> wrote:
>
> > > pretty sure this is the culprit is that num_possible_cpus() > 1,
> > > which would mean cpu_possible_map contains the second cpu... but i'm
&
>From 0cdcd494bc0e27f49438bc2fc72fd3823629802b Mon Sep 17 00:00:00 2001
From: Pete Wyckoff <[EMAIL PROTECTED]>
Date: Tue, 15 Jan 2008 17:42:28 -0500
Subject: [PATCH] use tsc on 1 cpu smp
Use num_online_cpus() instead of num_present_cpus() as the
parameter to check when deciding if TSC is g
[EMAIL PROTECTED] wrote on Fri, 11 Jan 2008 19:16 -0500:
> James Bottomley wrote:
>> On Thu, 2008-01-10 at 16:46 -0500, Pete Wyckoff wrote:
>>> [EMAIL PROTECTED] wrote on Thu, 10 Jan 2008 14:55 -0600:
>>>> On Thu, 2008-01-10 at 15:43 -0500, Pete Wyckoff wrote:
>&g
[EMAIL PROTECTED] wrote on Thu, 10 Jan 2008 14:55 -0600:
> On Thu, 2008-01-10 at 15:43 -0500, Pete Wyckoff wrote:
> > [EMAIL PROTECTED] wrote on Wed, 09 Jan 2008 09:11 +0900:
> > > On Tue, 8 Jan 2008 17:09:18 -0500
> > > Pete Wyckoff <[EMAIL PROTECTED]> wrote:
&
[EMAIL PROTECTED] wrote on Wed, 09 Jan 2008 09:11 +0900:
> On Tue, 8 Jan 2008 17:09:18 -0500
> Pete Wyckoff <[EMAIL PROTECTED]> wrote:
> > I took another look at the compat approach, to see if it is feasible
> > to keep the compat handling somewhere else, w
[EMAIL PROTECTED] wrote on Sat, 05 Jan 2008 14:01 +0900:
> From: Deepak Colluru <[EMAIL PROTECTED]>
> Subject: [PATCH] bsg : Add support for io vectors in bsg
> Date: Fri, 4 Jan 2008 21:47:34 +0530 (IST)
>
> > From: Deepak Colluru <[EMAIL PROTECTED]>
> >
> > Add support for io vectors in bsg.
> >
[EMAIL PROTECTED] wrote on Fri, 21 Dec 2007 17:18 -0500:
> On Fri, 2007-12-21 at 16:52 -0500, David Dillow wrote:
> > I'm getting the following oops when doing the following commands:
> >
> > modprobe ib_srp
> >
> > rmmod ib_srp
> > modprobe ib_srp
> >
> >
> > I'm going to try and track down ho
[EMAIL PROTECTED] said:
> I'd like to monitor CPU, memory, and I/O utilization in a
> long-running multithreaded daemon under kernels 2.2, 2.4,
> and possibly also Solaris (#ifdefs are ok).
>
> getrusage() looked promising, and might even work for CPU utilization.
> Dunno if it returns info for
[EMAIL PROTECTED] said:
> typedef struct page {
[..]
> + unsigned long index;/* Our offset within mapping. */
[..]
> + * A page may belong to an inode's memory mapping. In this case,
> + * page->mapping is the pointer to the inode, and page->offset is the
> + * file offset of the
[EMAIL PROTECTED] said:
> [EMAIL PROTECTED] writes:
> > So are there any intresting changes one can make to the acenic?
>
> Like I said, there is an entire firmware developer kit, so the only
> limit is your imagination and coding skills :-)
I wrote a new firmware from scratch to offload most o
[EMAIL PROTECTED] said:
> My driver uses a variable-size DMA buffer that it shares with user-space; I
> provide an ioctl() to choose the buffer size and allocate the buffer. Say
> the user program chooses a large buffer size, and mmap()s the entire buffer.
> Later, the program calls the ioctl() ag
[EMAIL PROTECTED] said:
> I am writing a device driver that, like many others, exposes a shared memory
> region to user-space via mmap(). The region is allocated with vmalloc(), the
> pages are marked reserved, and the user-space mapping is implemented with
> remap_page_range().
>
> In my driver,
[EMAIL PROTECTED] said:
> The following patch generates saner Ctags and will build cscope
> output. It's against 2.4.5
>
> --- Makefile.old Mon May 28 22:44:01 2001
> +++ Makefile Wed May 30 17:50:01 2001
> @@ -334,11 +334,32 @@
>
> # Exuberant ctags works better with -I
> tags: dummy
[EMAIL PROTECTED] said:
> On Wed, 30 May 2001 [EMAIL PROTECTED] wrote:
> > I use the 'pgt_offset', 'pmd_offset', 'pte_offset' and 'pte_page'
> > inside a module to get the physical address of a user space virtual
> > address. The physical address returned by 'pte_page' is not page
> > aligned wher
Rather than print proc twice, you probably intend to show the prog.
(At least, I had wanted to see the prog in the debugging output. :) )
-- Pete
diff -X dontdiff -ruN linux-2.4.5-kdb/fs/lockd/mon.c linux-2.4.5/fs/lockd/mon.c
--- linux-2.4.5-kdb/fs/lockd/mon.c Mon Oct 16 15:
[EMAIL PROTECTED] said:
> Anyone have any good tips on getting tags to generate nicely?
>
> I'm having some problems with some tags for macros and such being
> declared in several places since ctags doesn't honour any CPP #if'ing.
> I've currently got my Makefile doing this, which seems to give m
[EMAIL PROTECTED] said:
> # cd /usr/src/linux
> # find -name '*.[ch]' | ctags -L- &
>
> On 15 May 2001, Xavier Bestel wrote:
> > # cd /usr/src/linux
> > # make tags
>
> No, I never use that one because it skips very useful entries like the
> ones from EXPORT_SYMBOL etc. Also, it only shows the cu
[EMAIL PROTECTED] said:
> > But in the case of an application which fits in main memory, and
> > has been running for a while (so all pages are present and
> > dirty), all you'd really have to do is verify the page tables are
> > in the proper state and skip the TLB flush,
[EMAIL PROTECTED] said:
> > A couple of concerns I have:
> > * How to pin or pagelock the application buffer without
> > making a kernel transition.
>
> You need to pin them in advance. And pinning pages is _expensive_ so you dont
> want to keep pinning/unpinning pages
I can't convince myself w
[EMAIL PROTECTED] said:
> I am trying to mmap() into user space a kernel buffer and am having
> problems.
> I have a simple test example, can someone please tell me what I have got
> wrong ?
>
> In a driver I do:
> uint*kva;
>
> kva = (uint*)kmalloc(4096, GFP_KERNEL);
> *kva = 0
The hardware also must support jumbo MTUs. Hamachi limit is 1518 or
1522 (vlan) bytes, and the driver can't fix that.
-- Pete
[EMAIL PROTECTED] said:
> I'm trying to get some Gigabit ethernet cards that use the Packet
> Engines Hamachi GNIC-II chip to use a large mtu to attempt
My joystick stopped working at 2.4.0-test10 due to a patch to
drivers/char/joystick/ns558.c that moves pci probing ahead of
isa probing.
The problem is that pci_module_init can return -ENODEV into i,
which is then used to index the ISA portlist. ISA probing assumes
that i is initialized to zero.
27 matches
Mail list logo
