Hi Andrew,
Thanks for the bug report. I need to send a patch to update the maintainers
file...
Haven't had a chance to look into this yet. Will get back to you.
Thanks,
-Jason
On 03/11/2013 10:28 PM, Andrew Cooks wrote:
> On Tue, Mar 12, 2013 at 9:14 AM, Andrew Cooks wrote:
>> Hi Jason
>>
>
On Wed, Sep 12, 2012 at 06:13:30PM -0700, Joe Perches wrote:
> On Thu, 2012-09-06 at 13:53 -0400, Jason Baron wrote:
> > On Thu, Sep 06, 2012 at 09:13:59AM -0700, Greg Kroah-Hartman wrote:
> > > Jason, any ACK on these, or any of the other random dynamic debug
> > > pat
On Sat, Feb 09, 2008 at 11:21:58PM +0100, Jan Engelhardt wrote:
> >>
> >> What's wrong with klogd -c 8 or equivalent?
> >
> >Setting the loglevel higher, will not make pr_debug() calls visible. The only
> >way to make them visible right now, is by re-compiling the kernel.
>
> pr_debug() was IMHO
On Tue, Sep 18, 2012 at 05:36:44PM -0600, Jim Cromie wrote:
> Tell user how big the attempted write was, in case its not obvious.
> This helped identify a missing flush in my stress-test script.
>
> Signed-off-by: Jim Cromie
> ---
> lib/dynamic_debug.c | 3 ++-
> 1 file changed, 2 insertions(+),
On Tue, Sep 18, 2012 at 07:56:42PM -0700, Joe Perches wrote:
> On Tue, 2012-09-18 at 17:36 -0600, Jim Cromie wrote:
> > dynamic_emit_prefix() currently separates modname, funcname, lineno
> > with ':'. This is confounds use of cut -d: , since the field
> > positions can change per callsite with dy
On 08/27/2013 12:20 PM, Joe Perches wrote:
> On Tue, 2013-08-27 at 17:47 +0300, Dmitry Kasatkin wrote:
>> When DEBUG is defined, dev_dbg_ratelimited uses dynamic debug data
>> structures even when CONFIG_DYNAMIC_DEBUG is not defined.
>> It leads to build break.
>> For example, when I try to use dev
; expected.
>>
>> Signed-off-by: Jason Baron
>> ---
>> lib/dynamic_debug.c | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
> How far back should this patch go for older kernels? Is this a bug that
> people are hitting today and causing problems, or is i
fe.
This patch in combination with the patch "epoll: Do not take global 'epmutex'
for simple topologies", shows a dramatic performance improvement in
scalability for SPECjbb.
Tested-by: Nathan Zimmer
Signed-off-by: Jason Baron
---
fs/eventpoll.c | 65 +++
er 40 sockets.
...
Currently the benchmark stops scaling at around 40-44 sockets but it seems like
I found a second unrelated bottleneck.
"
Tested-by: Nathan Zimmer
Signed-off-by: Jason Baron
---
fs/eventpoll.c | 94 ++
1 file chan
I found a second unrelated bottleneck.
"
Thanks,
-Jason
Changes in v2:
-use a union for rcu callback and drop patch #3
v1:
http://marc.info/?l=linux-kernel&m=138057995316598&w=2
Jason Baron (2):
epoll: optimize EPOLL_CTL_DEL using rcu
epoll: Do
On 10/03/2013 05:50 PM, Andrew Morton wrote:
> On Tue, 1 Oct 2013 17:08:14 + (GMT) Jason Baron
> wrote:
>
>> When calling EPOLL_CTL_ADD for an epoll file descriptor that is attached
>> directly to a wakeup source, we do not need to take the global 'epmutex&
On 07/10/2013 04:25 PM, Jiri Kosina wrote:
> Hi,
>
> this is a resurrection of a few years old idea to have jump labels use
> synchronization based on int3 breakpoint rather than relying on
> stop_machine() with all the consequences.
>
> ftrace has been doing exactly this kind of patching for yea
On 07/11/2013 10:35 AM, Steven Rostedt wrote:
> On Wed, 2013-07-10 at 14:36 -0700, H. Peter Anvin wrote:
>> On 07/10/2013 02:31 PM, Jiri Kosina wrote:
>>> If any CPU instruction execution would collide with the patching,
>>> it'd be trapped by the int3 breakpoint and redirected to the provided
>>>
Thanks Joe - feel free to add:
Acked-by: Jason Baron
On 07/10/2013 06:36 PM, Joe Perches wrote:
> He must be too, umm, busy to update his own bouncing
> email address too.
>
> Signed-off-by: Joe Perches
> ---
>
> poke - prod...
>
> MAINTAINERS | 2 +-
> 1 f
I don't know of many tests. I did find the
> one posted by Jason Baron at https://lkml.org/lkml/2011/2/25/297.
>
> Any thoughts?
>
Hi,
Intersting - I think its also possible to completely drop taking the
'epmutex' for EPOLL_CTL_DEL by using rcu, and restricting it on
hen under the full load of the benchmark.
...
Currently the benchmark stops scaling at around 40-44 sockets but it seems like
I found a second unrelated bottleneck.
"
Jason Baron (3):
epoll: optimize EPOLL_CTL_DEL using rcu
epoll: Do not take global 'epmutex' for si
o not take global 'epmutex'
for simple topologies", shows a dramatic performance improvement in
scalability for SPECjbb.
Tested-by: Nathan Zimmer
Signed-off-by: Jason Baron
---
fs/eventpoll.c | 58 --
1 file changed, 32 insertions(
'struct
rcu_head'.
Note, I've kept this separate from 'epoll: optimize EPOLL_CTL_DEL using rcu'
in order to make clear the hack-ish nature of this thing.
Tested-by: Nathan Zimmer
Signed-off-by: Jason Baron
---
fs/eventpoll.c | 32 ++--
1 file
well
on just over 40 sockets.
...
Currently the benchmark stops scaling at around 40-44 sockets but it seems like
I found a second unrelated bottleneck.
"
Tested-by: Nathan Zimmer
Signed-off-by: Jason Baron
---
fs/eventpoll.c | 94 ++
1 file
On 09/19/2013 12:37 PM, Nathan Zimmer wrote:
> On 09/18/2013 02:09 PM, Jason Baron wrote:
>> On 09/13/2013 11:54 AM, Nathan Zimmer wrote:
>>> We noticed some scaling issue in the SPECjbb benchmark. Running perf
>>> we found that the it was spending lots of time in SYS_e
On 09/22/2013 04:41 PM, Eric Wong wrote:
> Jason Baron wrote:
>> epoll: reduce usage of global 'epmutex' lock
>>
>> Epoll file descriptors that are 1 link from a wakeup source and
>> are not nested within other epoll descriptors, or pointing to
On Sun, Aug 26, 2012 at 04:25:25AM -0700, Joe Perches wrote:
> The recent commit to fix dynamic_debug was a bit unclean.
> Neaten the style for dynamic_debug.
> Reduce the stack use of message logging that uses netdev_printk
> Add utility functions dev_printk_emit and dev_vprintk_emit for /dev/kmsg
On Thu, Sep 06, 2012 at 09:13:59AM -0700, Greg Kroah-Hartman wrote:
> On Thu, Aug 30, 2012 at 09:48:12PM -0600, Jim Cromie wrote:
> > On Thu, Aug 30, 2012 at 11:43 AM, Jim Cromie wrote:
> > > On Sun, Aug 26, 2012 at 5:25 AM, Joe Perches wrote:
> > >> The recent commit to fix dynamic_debug was a b
On Thu, Sep 06, 2012 at 11:43:46AM -0700, Joe Perches wrote:
> On Thu, 2012-09-06 at 13:51 -0400, Jason Baron wrote:
> > On Sun, Aug 26, 2012 at 04:25:25AM -0700, Joe Perches wrote:
> > > The recent commit to fix dynamic_debug was a bit unclean.
> > > Neaten
On Fri, Sep 07, 2012 at 08:12:01AM -0700, Joe Perches wrote:
> On Fri, 2012-09-07 at 10:52 -0400, Jason Baron wrote:
> > On Thu, Sep 06, 2012 at 11:43:46AM -0700, Joe Perches wrote:
> > > On Thu, 2012-09-06 at 13:51 -0400, Jason Baron wrote:
> > > > On Sun, Aug 26,
On Fri, Sep 07, 2012 at 06:55:50PM -0700, Joe Perches wrote:
> On Fri, 2012-09-07 at 11:35 -0400, Jason Baron wrote:
> > If nobody else thinks this patch is better, let's at least add a comment in
> > __dev_printk() and __netdev_printk() to fix dynamic debug, if these are
From: Joe Perches
vpr_info_dq should be a function and vpr_info should have
a do {} while (0)
Add missing newlines to pr_s.
Miscellaneous neatening too.
braces, coalescing formats, alignments, etc...
Signed-off-by: Joe Perches
Signed-off-by: Jason Baron
---
lib/dynamic_debug.c | 118
-off-by: Jason Baron
---
lib/dynamic_debug.c | 47 +++
1 files changed, 35 insertions(+), 12 deletions(-)
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index c0869f1..da820f2 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
ong prefix would impact readability.
To provide line/file etc. information, use pr_debug or similar
before/after print_hex_dump_debug()
Signed-off-by: Vladimir Kondratiev
Signed-off-by: Jason Baron
---
Documentation/dynamic-debug-howto.txt | 15 +--
include/linux/dynamic_debug.h
Hi Greg,
Here's a collection of the latest dyanmic debug patches that I have
pending.
Thanks,
-Jason
Jim Cromie (1):
dynamic_debug: add pr_errs before -EINVALs
Joe Perches (1):
dynamic_debug: Fix vpr_ logging styles
Vladimir Kondratiev (1):
dynamic_debug: dynamic hex dump
Documentati
On Wed, Dec 05, 2012 at 02:05:06PM -0800, Joe Perches wrote:
> On Wed, 2012-12-05 at 16:48 -0500, Jason Baron wrote:
> > Here's a collection of the latest dynamic debug patches that I have
> > pending.
>
> Any update on the jump table support?
>
I have patch
debug __aligned(8) \
> __attribute__((section("__verbose"))) name = { \
> .modname = KBUILD_MODNAME, \
> .function = __func__, \
>
>
Greg, Pls pull this.
Acked-by: Ja
On Thu, Dec 06, 2012 at 03:20:37PM -0700, Alex Williamson wrote:
> The API documents that only flags and guest physical memory space can
> be modified on an existing slot, but we don't enforce that the
> userspace address cannot be modified. Instead we just ignore it.
> This means that a user may
On Fri, Dec 07, 2012 at 11:32:08AM -0700, Alex Williamson wrote:
> On Fri, 2012-12-07 at 13:17 -0500, Jason Baron wrote:
> > On Thu, Dec 06, 2012 at 03:20:37PM -0700, Alex Williamson wrote:
> > > The API documents that only flags and guest physical memory space can
> > >
On Tue, Dec 11, 2012 at 11:36:46AM -0800, Luis R. Rodriguez wrote:
> On Tue, Dec 04, 2012 at 11:28:26AM +0200, Vladimir Kondratiev wrote:
> > Hi Jason,
> >
> > Do you have any update on the status for patches below?
> > Where is it now? When do you expect it to merge? 3.8?
> > I am waiting for thi
On Sun, Nov 18, 2012 at 10:35:40AM -0800, Joe Perches wrote:
> On Sun, 2012-11-18 at 19:01 +0200, Vladimir Kondratiev wrote:
> > In case this option wins, patch follows. There is no need for
> > 2-nd one to fix existing drivers.
>
> Thanks Vladimir.
>
>
Yes, thanks. I've pulled in this patch, a
Hi Andi,
Agreed. However, other users of 'static_key_enabled()', provide their own
locking. For example, in kernel/tracepoint.c, 'static_key_enabled()',
relies on
the tracepoints_mutex. Were there any other users that are problematic?
I agree a 'setstate' would be nice. Maybe something like:
sta
On 06/25/2013 01:29 PM, Joe Perches wrote:
> On Tue, 2013-06-25 at 10:02 -0700, Greg KH wrote:
>> On Tue, Jun 25, 2013 at 05:30:02PM +0100, Rupesh Gujare wrote:
>>> convert all debug messages from printk to dev_dbg() & add kernel config to
>>> enable/disable these messages during compilation.
>> No
On 06/25/2013 02:03 PM, Joe Perches wrote:
> (Using Jason Baron's most current email address)
>
> On Tue, 2013-06-25 at 10:56 -0700, Joe Perches wrote:
>> On Tue, 2013-06-25 at 10:38 -0700, Greg KH wrote:
>>> On Tue, Jun 25, 2013 at 10:29:50AM -0700, Joe Perches wrote:
a long needed extension
On 06/29/2013 03:20 AM, Ingo Molnar wrote:
* jba...@akamai.com wrote:
Hi,
As pointed out by Andi Kleen, some static key users can be racy because they
check the value of the key->enabled, and then subsequently update the branch
direction. A number of call sites have 'higher' level locking tha
led to this. Each change log should be sufficient to stand
on its own.
Explain why this patch is needed. And it's not about the use of a
simpler API.
It actually fixes a real bug.
Signed-off-by: Jason Baron
---
net/ipv4/udp.c |9 -
net/ipv6/udp.c |9 -
2 files ch
On 08/14/2013 12:51 PM, Joe Perches wrote:
> On Wed, 2013-08-14 at 09:40 -0700, Sarah Sharp wrote:
>> Hi Xenia,
>>
>> I'm a bit confused. I thought that debugging messages would be turned
>> off by default for a module if CONFIG_DYNAMIC_DEBUG was turned on. When
>> I tested your patch to remove t
On 07/25/2013 12:47 PM, Joe Perches wrote:
On Thu, 2013-07-25 at 21:02 +0800, Du, Changbin wrote:
From: "Du, Changbin"
This patch add wildcard '*'(matches zero or more characters) and '?'
(matches one character) support when qurying debug flags.
Seems very useful. Caveat below.
diff --git
On 08/05/2013 03:40 PM, Marek Polacek wrote:
On Mon, Aug 05, 2013 at 11:34:55AM -0700, Linus Torvalds wrote:
On Mon, Aug 5, 2013 at 11:24 AM, Linus Torvalds
wrote:
Ugh. I can see the attraction of your section thing for that case, I
just get the feeling that we should be able to do better some
On 08/05/2013 02:39 PM, Steven Rostedt wrote:
On Mon, 2013-08-05 at 11:20 -0700, Linus Torvalds wrote:
Of course, it would be good to optimize static_key_false() itself -
right now those static key jumps are always five bytes, and while they
get nopped out, it would still be nice if there was s
On 08/05/2013 04:35 PM, Richard Henderson wrote:
On 08/05/2013 09:57 AM, Jason Baron wrote:
On 08/05/2013 03:40 PM, Marek Polacek wrote:
On Mon, Aug 05, 2013 at 11:34:55AM -0700, Linus Torvalds wrote:
On Mon, Aug 5, 2013 at 11:24 AM, Linus Torvalds
wrote:
Ugh. I can see the attraction of
On 08/07/2013 03:22 PM, Linus Torvalds wrote:
> On Wed, Aug 7, 2013 at 10:54 AM, Steven Rostedt wrote:
>> On another box, using a distro config, I had even better results:
>>
>> [2.352448] short jumps: 193
>> [2.355407] long jumps: 219
> .. well, another way of looking at this is to say t
On 08/07/2013 04:47 PM, Linus Torvalds wrote:
> On Wed, Aug 7, 2013 at 1:19 PM, Jason Baron wrote:
>> The whole point of the thread started with wanting to move the default
>> 'disabled' branch further out-of-line.
> Yeah, but I always disagreed with that.
>
> Pu
-add documentation about pr_debug kernel-parameters.txt
Signed-off-by: Jason Baron <[EMAIL PROTECTED]>
---
Documentation/kernel-parameters.txt |5 +
1 files changed, 5 insertions(+), 0 deletions(-)
diff --git a/Documentation/kernel-parameters.txt
b/Documentation/
-add /proc/sys/debug/pr_debug, to toggle pr_debug() on/off
Signed-off-by: Jason Baron <[EMAIL PROTECTED]>
---
kernel/sysctl.c | 41 +
1 files changed, 41 insertions(+), 0 deletions(-)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 7
hi,
make the pr_debug() function dependent upon the new immediate infrastruture.
Thus, b/c of the low runtime impact, we can dynamically enable/disable
pr_debug withoug recompiling. Patch allows 'pr_debug=0/1' on the command
line or via /proc/sys/debug/pr_debug.
thanks,
-Jason
--
To unsubscrib
-make pr_debug() dynamic so it can be switched on/off. The off state
is implemented on top of the immediate infrastructure, so as to promote
more dynamic printing and debugging. depends on CONFIG_HAVE_IMMEDIATE
and CONFIG_PRINTK
Signed-off-by: Jason Baron <[EMAIL PROTECTED]>
---
i
-make pptp_msg_name dependent on CONFIG_PR_DEBUG_DYNAMIC
Signed-off-by: Jason Baron <[EMAIL PROTECTED]>
---
net/netfilter/nf_conntrack_pptp.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/net/netfilter/nf_conntrack_pptp.c
b/net/netfilter/nf_conntrack_pptp.c
On Thu, Feb 07, 2008 at 02:42:14PM -0800, Joe Perches wrote:
> On Thu, 2008-02-07 at 16:03 -0500, Jason Baron wrote:
> > make the pr_debug() function dependent upon the new immediate infrastruture.
>
> What's wrong with klogd -c 8 or equivalent?
>
>
Setting the logl
On Thu, Feb 07, 2008 at 01:26:04PM -0800, Randy Dunlap wrote:
> > --- a/Documentation/kernel-parameters.txt
> > +++ b/Documentation/kernel-parameters.txt
> > @@ -1494,6 +1494,11 @@ and is between 256 and 4096 characters. It is
> > defined in the file
> > autoconfiguration.
> >
On Thu, Feb 07, 2008 at 04:10:52PM -0800, Stephen Hemminger wrote:
> Jason Baron <[EMAIL PROTECTED]> wrote:
>
> >
> > -add /proc/sys/debug/pr_debug, to toggle pr_debug() on/off
> >
> > Signed-off-by: Jason Baron <[EMAIL PROTECTED]>
On Thu, Jul 19, 2012 at 01:46:19PM -0600, Jim Cromie wrote:
> 3 patches here, 1st is bugfix, others are trivial.
>
> 1- fix __dev_printk, which broke dev_dbg() prefix under CONFIG_DYNAMIC_DEBUG.
>
Patch looks good, and would be really nice to get into 3.5. Kay, are you
ok with this patch?
> 2-
dds "[tid] module:func:line:" to the string,
> those additions all got lost.
>
> Signed-off-by: Jim Cromie
> ---
> drivers/base/core.c |9 +++++++--
> 1 file changed, 7 insertions(+), 2 deletions(-)
>
Acked-by: Jason Baron
> diff --git a/drivers/base/core.c b/d
On Fri, Aug 17, 2012 at 10:39:39AM -0400, Steven Rostedt wrote:
> On Fri, 2012-08-17 at 11:04 -0300, Ezequiel Garcia wrote:
> > On Fri, Aug 17, 2012 at 10:55 AM, Steven Rostedt
> > wrote:
> > > On Fri, 2012-08-17 at 08:01 -0300, Ezequiel Garcia wrote:
> > >
> > >> Regarding the 'complete solution
On Mon, Jan 07, 2013 at 08:58:09AM -0500, Sasha Levin wrote:
> jump_label_text_reserved() doesn't modify the memory it works on, it just
> checks whether there are any jump labels there.
>
> Constify the parameters of it to prevent warnings when working with it.
>
I don't see any 'const' data pa
On Sun, 27 Feb 2005, Linus Torvalds wrote:
>
>
> On Sun, 27 Feb 2005, Marcelo Tosatti wrote:
> >
> > Alan, Linus, what correction to the which the above thread discusses has
> > been deployed?
>
> This is the hacky "hide the problem" patch that is in my current tree (and
> was discussed in
hi,
This is a re-posting of a fix for a race condition between changing the
line discipline on a pty and and a poll on the 'other' side. The reference
is: http://marc.theaimsgroup.com/?l=linux-kernel&m=111342171410005&w=2.
Below is a diff against the current tree.
thanks,
-Jason
--- linux-2
On Mon, 11 Jul 2005, Tom Zanussi wrote:
>
> Hi Andrew, can you please merge relayfs? It provides a low-overhead
> logging and buffering capability, which does not currently exist in
> the kernel.
>
One concern I had regarding relayfs, which was raised previously, was
regarding its use of vma
There are a couple of tty race conditions, which lead to inconsistent tty
reference counting and tty layer oopses.
The first is a tty_open vs. tty_close race in drivers/char/tty.io.c.
Basically, from the time that the tty->count is deemed to be 1 and that we
are going to free it to the time th
The patch simply checks for a NULL tty *after* it has been attached to the
proper session group and clears it as necessary. Alternatively, we could
simply do the tty assignment after the the process is added to the proper
session group.
thanks,
-Jason
Signed-off-by: Jason Baron <[EMAIL
On Tue, 12 Dec 2006, Pete Zaitcev wrote:
> Hi, Roman & All:
>
> In 2.6.19 (and Linus' curent tree), I found the following:
>
> libpath=$$dir/lib; lib=qt; osdir=""; \
> $(HOSTCXX) -print-multi-os-directory > /dev/null 2>&1 && \
> osdir=x$$($(HOSTCXX) -print-multi-
On Sat, 16 Jun 2007, Christoph Hellwig wrote:
> On Fri, Jun 15, 2007 at 11:20:31AM -0400, Jason Baron wrote:
> > hi,
> >
> > i was just looking at the new madvise_need_mmap_write() call...can we
> > avoid an extra case statement and function call as follows?
>
hi,
i was just looking at the new madvise_need_mmap_write() call...can we
avoid an extra case statement and function call as follows?
thanks,
-Jason
Signed-off-by: Jason Baron <[EMAIL PROTECTED]>
diff --git a/mm/madvise.c b/mm/madvise.c
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@
27;ve included one such patch below, which also
introduces a 'event', thiking of things like lock timings that were
mentioned, but this is not necessary.
thanks,
-Jason
Signed-off-by: Jason Baron <[EMAIL PROTECTED]>
--- linux-2.6.22-rc2-lockdep/include/linux/lockdep.
On Wed, 23 May 2007, Peter Zijlstra wrote:
> Count lock contention events per lock class. Additionally track the first four
> callsites that resulted in the contention.
>
I think that we need the total number of locking calls, not just the total
number of *contended* locking calls, in order to
On Wed, 23 May 2007, Peter Zijlstra wrote:
> On Wed, 2007-05-23 at 10:40 -0400, Jason Baron wrote:
> > On Wed, 23 May 2007, Peter Zijlstra wrote:
> >
> > > Count lock contention events per lock class. Additionally track the first
> > > four
> > >
On Wed, 23 May 2007, Peter Zijlstra wrote:
> On Wed, 2007-05-23 at 12:11 -0400, Jason Baron wrote:
> > On Wed, 23 May 2007, Peter Zijlstra wrote:
> >
> > > On Wed, 2007-05-23 at 10:40 -0400, Jason Baron wrote:
> > > > On Wed, 23 May 2007, Peter Zijlstra
Hi,
After looking at this further we found that there is actually
a rate limit on 'rst' packets sent by OSX on a closed socket.
Its set to 250 per second and controlled via:
net.inet.icmp.icmplim. Increasing that limit resolves the
issue, but the default is apparently 250.
Thanks,
-Jason
On 07
Hi,
On 09/23/2016 03:24 AM, Nicholas Piggin wrote:
On Fri, 23 Sep 2016 14:42:53 +0800
"Hillf Danton" wrote:
The select(2) syscall performs a kmalloc(size, GFP_KERNEL) where size grows
with the number of fds passed. We had a customer report page allocation
failures of order-4 for this allocat
On 09/05/2016 01:25 PM, Catalin Marinas wrote:
This patch adds static keys transparently for all the cpu_hwcaps
features by implementing an array of default-false static keys and
enabling them when detected. The cpus_have_cap() check uses the static
keys if the feature being checked is a constant
On 10/16/2017 10:42 AM, Petr Mladek wrote:
> On Thu 2017-10-12 17:12:28, Jason Baron wrote:
>> In preparation for __klp_enable_patch() to call a number of 'static'
>> functions, in a subsequent patch, move them earlier in core.c. This patch
>> should be a nop from
Hi,
I posted a patch to completely remove the lock here from the
ep_poll_safewake() patch here:
http://lkml.iu.edu/hypermail/linux/kernel/1710.1/05834.html
So these are going to conflict. The reason its safe to remove the lock
is that there are loop and depth checks now that are performed during
Kaby Lake seems to work just like Skylake.
Signed-off-by: Jason Baron
Reported-and-tested-by: Doug Thompson
Cc: Borislav Petkov
Cc: Mauro Carvalho Chehab
Cc: Tony Luck
---
drivers/edac/ie31200_edac.c | 12 +++-
1 file changed, 11 insertions(+), 1 deletion(-)
diff --git a/drivers
On 10/28/2017 10:05 AM, Davidlohr Bueso wrote:
> On Wed, 18 Oct 2017, Jason Baron wrote:
>
>> http://lkml.iu.edu/hypermail//linux/kernel/1501.1/05905.html
>>
>> We can work through these ideas or others...
>
> So, unsurprisingly, I got some _really_ good results o
On 11/01/2017 04:53 PM, Andrew Morton wrote:
> On Tue, 31 Oct 2017 07:58:21 -0700 Davidlohr Bueso wrote:
>
>> On Tue, 31 Oct 2017, Jason Baron wrote:
>>
>>> The use of ep_call_nested() in ep_eventpoll_poll(), which is the .poll
>>> routine for an epoll fd,
Cc: Steven Rostedt
Cc: Ingo Molnar
Signed-off-by: Jason Baron
---
kernel/jump_label.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 0bf2e8f5..7c3774a 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -769,7 +769,7
On 10/17/2017 09:50 AM, Miroslav Benes wrote:
> On Tue, 17 Oct 2017, Miroslav Benes wrote:
>
>> On Tue, 10 Oct 2017, Jason Baron wrote:
>>
>>>
>>>
>>> On 10/06/2017 06:32 PM, Josh Poimboeuf wrote:
>>>> On Wed, Sep 27, 2017 at 11:41:30PM -
On 10/17/2017 10:18 AM, Petr Mladek wrote:
> On Thu 2017-10-12 17:12:29, Jason Baron wrote:
>> Sometimes we would like to revert a particular fix. This is currently
>> This is not easy because we want to keep all other fixes active and we
>> could revert only the last app
On 10/17/2017 11:37 AM, Davidlohr Bueso wrote:
> On Fri, 13 Oct 2017, Jason Baron wrote:
>
>> The ep_poll_safewake() function is used to wakeup potentially nested
>> epoll
>> file descriptors. The function uses ep_call_nested() to prevent entering
>> the same wak
On 10/17/2017 11:53 AM, Davidlohr Bueso wrote:
> On Mon, 16 Oct 2017, Jason Baron wrote:
>
>> Hi,
>>
>> I posted a patch to completely remove the lock here from the
>> ep_poll_safewake() patch here:
>>
>> http://lkml.iu.edu/hypermail/linux/kernel/1710.
On 10/18/2017 07:25 AM, Petr Mladek wrote:
> On Wed 2017-10-18 11:10:09, Miroslav Benes wrote:
>> On Tue, 17 Oct 2017, Jason Baron wrote:
>>> If the atomic replace patch does
>>> not contain any immediates, then we can drop the reference on the
>>> immed
On 10/18/2017 05:10 AM, Miroslav Benes wrote:
> On Tue, 17 Oct 2017, Jason Baron wrote:
>
>>
>>
>> On 10/17/2017 09:50 AM, Miroslav Benes wrote:
>>> On Tue, 17 Oct 2017, Miroslav Benes wrote:
>>>
>>>> On Tue, 10 Oct 2017, Jason Baron wrot
d via ep_scan_ready_list() only continues nesting if there
are events available. Since ep_call_nested() is implemented using a global
lock, applications that make use of nested epoll can see large performance
improvements with this change.
Signed-off-by: Jason Baron
Cc: Davidlohr Bueso
Cc: Alexander
On 10/05/2015 03:41 AM, Peter Zijlstra wrote:
> On Fri, Oct 02, 2015 at 08:44:02PM +0000, Jason Baron wrote:
>> diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
>> index f789423..b8ed1bc 100644
>> --- a/net/unix/af_unix.c
>> +++ b/net/unix/af_unix.c
>
>&g
On 10/05/2015 12:31 PM, Rainer Weikusat wrote:
> Jason Baron writes:
>> The unix_dgram_poll() routine calls sock_poll_wait() not only for the wait
>> queue associated with the socket s that we are poll'ing against, but also
>> calls
>> sock_poll_wait() for
Convert gc_flags to flags in perparation for the subsequent patch, which will
make use of a flag bit for a non-gc purpose.
Signed-off-by: Jason Baron
---
include/net/af_unix.h | 2 +-
net/unix/garbage.c| 12 ++--
2 files changed, 7 insertions(+), 7 deletions(-)
diff --git a
comments in 3/3 (Peter Zijlstra)
-clean up unix_dgram_writable() function in 3/3 (Joe Perches)
Jason Baron (3):
net: unix: fix use-after-free in unix_dgram_poll()
net: unix: Convert gc_flags to flags
net: unix: optimize wakeups in unix_dgram_recvmsg()
include/net/af_unix.h | 4 +-
net/unix
epoll().
I've implemented this for sock-type, SOCK_RAW, SOCK_DGRAM, and SOCK_SEQPACKET
but not for SOCK_STREAM, since SOCK_STREAM does not use unix_dgram_poll().
Introduced in commit ec0d215f9420 ("af_unix: fix 'poll for write'/connected
DGRAM sockets").
Tested-by: Mathias Krau
Now that connect() permanently registers a callback routine, we can induce
extra overhead in unix_dgram_recvmsg(), which unconditionally wakes up
its peer_wait queue on every receive. This patch makes the wakeup there
conditional on there being waiters.
Signed-off-by: Jason Baron
---
include
On 10/09/2015 10:38 AM, Hannes Frederic Sowa wrote:
> Hi,
>
> Jason Baron writes:
>
>> The unix_dgram_poll() routine calls sock_poll_wait() not only for the wait
>> queue associated with the socket s that we are poll'ing against, but also
>> calls
>> so
On 10/11/2015 07:55 AM, David Miller wrote:
> From: Jason Baron
> Date: Fri, 9 Oct 2015 00:15:59 -0400
>
>> These patches are against mainline, I can re-base to net-next, please
>> let me know.
>>
>> They have been tested against: https://lkml.org/lkml/2015/
On 10/12/2015 04:41 PM, Rainer Weikusat wrote:
> Jason Baron writes:
>> On 10/05/2015 12:31 PM, Rainer Weikusat wrote:
>
> [...]
>
>>> Here's a more simple idea which _might_ work. The underlying problem
>>> seems to be that the second sock_poll_wait
On 09/07/2015 03:18 PM, Jonathan Corbet wrote:
> 412758cb2670 (jump label, locking/static_keys: Update docs) introduced a
> typo that might as well get fixed.
>
> Signed-off-by: Jonathan Corbet
> ---
> Documentation/static-keys.txt | 2 +-
> include/linux/jump_label.h| 2 +-
> 2 files chan
>
> X-Signed-Off-By: Rainer Weikusat
>
Hi,
So the patches I've posted and yours both use the idea of a relaying
the remote peer wakeup via callbacks that are internal to the net/unix,
such that we avoid exposing the remote peer wakeup to the external
poll()/select()/epoll(). They differ i
On 10/18/2015 04:58 PM, Rainer Weikusat wrote:
[...]
>
> The idea behind 'the wait queue' (insofar I'm aware of it) is that it
> will be used as list of threads who need to be notified when the
> associated event occurs. Since you seem to argue that the run-of-the-mill
> algorithm is too slow fo
1 - 100 of 455 matches
Mail list logo