在 2016年04月06日 18:53, Borislav Petkov 写道:
On Wed, Apr 06, 2016 at 11:37:37AM +0100, One Thousand Gnomes wrote:
Even that would still be wrong for the smaller parity values. The CPU
supports 8bit parity directly going back to the 8086 so the
implementation for 8bit and I think 16bit is still
在 2016年04月07日 03:45, Andi Kleen 写道:
zengzhao...@163.com writes:
From: Zhaoxiu Zeng
Use alternatives, lifted from arch_hweight
Is there actually anything performance critical in the kernel that uses
parity?
FWIW the arch hweight custom calling convention is a problem
在 2016年04月06日 18:53, Borislav Petkov 写道:
On Wed, Apr 06, 2016 at 11:37:37AM +0100, One Thousand Gnomes wrote:
Even that would still be wrong for the smaller parity values. The CPU
supports 8bit parity directly going back to the 8086 so the
implementation for 8bit and I think 16bit is still
在 2016年04月07日 03:45, Andi Kleen 写道:
zengzhao...@163.com writes:
From: Zhaoxiu Zeng
Use alternatives, lifted from arch_hweight
Is there actually anything performance critical in the kernel that uses
parity?
FWIW the arch hweight custom calling convention is a problem for LTO
because it
在 2016年04月07日 02:44, Sam Ravnborg 写道:
Hi Zeng.
Use runtime patching for sparc64, lifted from hweight
No errors found in patch - but a few comments.
In general patch looks good.
Thanks. Sparc, powerpc, and x86 are all new to me.
+++ b/arch/sparc/include/asm/bitops_64.h
@@ -47,6 +47,24 @@
在 2016年04月06日 21:27, Chris Metcalf 写道:
On 4/6/2016 5:08 AM, zengzhao...@163.com wrote:
From: Zhaoxiu Zeng
Signed-off-by: Zhaoxiu Zeng
---
arch/tile/include/asm/bitops.h | 26 ++
1 file changed, 26 insertions(+)
Since
在 2016年04月07日 02:44, Sam Ravnborg 写道:
Hi Zeng.
Use runtime patching for sparc64, lifted from hweight
No errors found in patch - but a few comments.
In general patch looks good.
Thanks. Sparc, powerpc, and x86 are all new to me.
+++ b/arch/sparc/include/asm/bitops_64.h
@@ -47,6 +47,24 @@
在 2016年04月06日 21:27, Chris Metcalf 写道:
On 4/6/2016 5:08 AM, zengzhao...@163.com wrote:
From: Zhaoxiu Zeng
Signed-off-by: Zhaoxiu Zeng
---
arch/tile/include/asm/bitops.h | 26 ++
1 file changed, 26 insertions(+)
Since all the code you are adding here is
在 2016年04月06日 18:13, Borislav Petkov 写道:
On Wed, Apr 06, 2016 at 05:14:45PM +0800, zengzhao...@163.com wrote:
From: Zhaoxiu Zeng
Use alternatives, lifted from arch_hweight
Signed-off-by: Zhaoxiu Zeng
---
arch/x86/include/asm/arch_hweight.h |
在 2016年04月06日 18:13, Borislav Petkov 写道:
On Wed, Apr 06, 2016 at 05:14:45PM +0800, zengzhao...@163.com wrote:
From: Zhaoxiu Zeng
Use alternatives, lifted from arch_hweight
Signed-off-by: Zhaoxiu Zeng
---
arch/x86/include/asm/arch_hweight.h | 5 ++
arch/x86/include/asm/arch_parity.h |
The mm-of-the-moment snapshot 2016-04-06-20-40 has been uploaded to
http://www.ozlabs.org/~akpm/mmotm/
mmotm-readme.txt says
README for mm-of-the-moment:
http://www.ozlabs.org/~akpm/mmotm/
This is a snapshot of my -mm patch queue. Uploaded at random hopefully
more than once a week.
You
The mm-of-the-moment snapshot 2016-04-06-20-40 has been uploaded to
http://www.ozlabs.org/~akpm/mmotm/
mmotm-readme.txt says
README for mm-of-the-moment:
http://www.ozlabs.org/~akpm/mmotm/
This is a snapshot of my -mm patch queue. Uploaded at random hopefully
more than once a week.
You
On Wed, 2016-04-06 at 20:00 -0400, Tejun Heo wrote:
> Hello, Mike.
>
> On Sun, Mar 13, 2016 at 06:40:35PM +0100, Mike Galbraith wrote:
> > On Sun, 2016-03-13 at 11:00 -0400, Tejun Heo wrote:
> > > Let's say there is an application which wants to manage resource
> > > distributions across its
On Wed, 2016-04-06 at 20:00 -0400, Tejun Heo wrote:
> Hello, Mike.
>
> On Sun, Mar 13, 2016 at 06:40:35PM +0100, Mike Galbraith wrote:
> > On Sun, 2016-03-13 at 11:00 -0400, Tejun Heo wrote:
> > > Let's say there is an application which wants to manage resource
> > > distributions across its
Fixes CHECK: Alignment should match open parenthesis
Signed-off-by: Manav Batra
---
drivers/staging/rts5208/ms.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/staging/rts5208/ms.c b/drivers/staging/rts5208/ms.c
index 3e75db7..0f0cd4a 100644
Fixes CHECK: Alignment should match open parenthesis
Signed-off-by: Manav Batra
---
drivers/staging/rts5208/ms.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/staging/rts5208/ms.c b/drivers/staging/rts5208/ms.c
index 3e75db7..0f0cd4a 100644
---
On 7 April 2016 at 09:40, Jaehoon Chung wrote:
> On 04/06/2016 08:57 PM, Jisheng Zhang wrote:
>>
>>
>> On Wed, 6 Apr 2016 19:38:30 +0800 Baolin Wang wrote:
>>
>>> This patch removes some redundant debug prints, since we have added some
>>> tracepoints to help with
On 7 April 2016 at 09:40, Jaehoon Chung wrote:
> On 04/06/2016 08:57 PM, Jisheng Zhang wrote:
>>
>>
>> On Wed, 6 Apr 2016 19:38:30 +0800 Baolin Wang wrote:
>>
>>> This patch removes some redundant debug prints, since we have added some
>>> tracepoints to help with performance analysis of MMC
On 6 April 2016 at 19:57, Jisheng Zhang wrote:
>
>
> On Wed, 6 Apr 2016 19:38:30 +0800 Baolin Wang wrote:
>
>> This patch removes some redundant debug prints, since we have added some
>> tracepoints to help with performance analysis of MMC subsystem.
>
> I think the debug
On 6 April 2016 at 19:57, Jisheng Zhang wrote:
>
>
> On Wed, 6 Apr 2016 19:38:30 +0800 Baolin Wang wrote:
>
>> This patch removes some redundant debug prints, since we have added some
>> tracepoints to help with performance analysis of MMC subsystem.
>
> I think the debug prints you removed are
On Wed, Apr 06, 2016 at 04:58:03PM +0300, Felipe Balbi wrote:
>
> Hi,
>
> Jun Li writes:
> >> >> >> > Since we already have get_charger_type callback at usb_charger
> >> >> >> > structure, why we still need this API at usb_gadget_ops?
> >> >> >>
> >> >> >> In case some users
On Wed, Apr 06, 2016 at 04:58:03PM +0300, Felipe Balbi wrote:
>
> Hi,
>
> Jun Li writes:
> >> >> >> > Since we already have get_charger_type callback at usb_charger
> >> >> >> > structure, why we still need this API at usb_gadget_ops?
> >> >> >>
> >> >> >> In case some users want to get charger
On Sun, Mar 27, 2016 at 05:10:56PM -0400, Paul Gortmaker wrote:
> The Kconfig currently controlling compilation of this code is:
>
> drivers/bus/Kconfig:config IMX_WEIM
> drivers/bus/Kconfig:bool "Freescale EIM DRIVER
>
> ...meaning that it currently is not being built as a module by anyone.
On Sun, Mar 27, 2016 at 05:10:56PM -0400, Paul Gortmaker wrote:
> The Kconfig currently controlling compilation of this code is:
>
> drivers/bus/Kconfig:config IMX_WEIM
> drivers/bus/Kconfig:bool "Freescale EIM DRIVER
>
> ...meaning that it currently is not being built as a module by anyone.
On Wed, 6 Apr 2016, Ingo Molnar wrote:
> * Hugh Dickins wrote:
>
> > ---
> > Cc'ed to arch maintainers as an FYI: this patch is not expected to
> > go into the tree in the next few weeks, and depends upon a PageTeam
> > definition not yet available outside this huge tmpfs
On Wed, 6 Apr 2016, Ingo Molnar wrote:
> * Hugh Dickins wrote:
>
> > ---
> > Cc'ed to arch maintainers as an FYI: this patch is not expected to
> > go into the tree in the next few weeks, and depends upon a PageTeam
> > definition not yet available outside this huge tmpfs patchset.
> > Please
From: Mathieu Poirier
The System Trace Macrocell (STM) is an IP block falling under the
CoreSight umbrella. It's main purpose it so expose stimulus channels
to any system component for the purpose of information logging.
Bindings for this IP block adds a couple of
From: Pratik Patel
This driver adds support for the STM CoreSight IP block, allowing any
system compoment (HW or SW) to log and aggregate messages via a
single entity.
The CoreSight STM exposes an application defined number of channels
called stimulus port.
From: Mathieu Poirier
The System Trace Macrocell (STM) is an IP block falling under the
CoreSight umbrella. It's main purpose it so expose stimulus channels
to any system component for the purpose of information logging.
Bindings for this IP block adds a couple of items to the current
From: Pratik Patel
This driver adds support for the STM CoreSight IP block, allowing any
system compoment (HW or SW) to log and aggregate messages via a
single entity.
The CoreSight STM exposes an application defined number of channels
called stimulus port. Configuration is done using entries
From: Mathieu Poirier
>From a core framework point of view an STM device is a source that is
treated the same way as any other tracers. Unlike tracers though STM
devices are not associated with a CPU. As such it doesn't make sense
to associate the path from an STM
From: Alexander Shishkin
Some STM devices adjust software assigned master numbers depending on
the trace source and its runtime state and whatnot. This patch adds
a sysfs attribute to inform the trace-side software that master numbers
assigned to software
From: Mathieu Poirier
>From a core framework point of view an STM device is a source that is
treated the same way as any other tracers. Unlike tracers though STM
devices are not associated with a CPU. As such it doesn't make sense
to associate the path from an STM device to its sink with a
From: Alexander Shishkin
Some STM devices adjust software assigned master numbers depending on
the trace source and its runtime state and whatnot. This patch adds
a sysfs attribute to inform the trace-side software that master numbers
assigned to software sources will not match those in the STP
This patchset adds support for the CoreSight STM IP block.
Changes from V4:
- Rebased the whole patch set onto [4] (v4.6-rc1).
- Made a few minor modifications according to the code changes since v4.5.
- Replaced the original 1/4 with a new patch the Alex provided.
- Another new patch 2/4 in
This patchset adds support for the CoreSight STM IP block.
Changes from V4:
- Rebased the whole patch set onto [4] (v4.6-rc1).
- Made a few minor modifications according to the code changes since v4.5.
- Replaced the original 1/4 with a new patch the Alex provided.
- Another new patch 2/4 in
Commit 'b09d6d991' removes include/linux/clk-private.h and
re-arranges the clock related structures contained in it in
different files. The documentation has not been updated
accordingly, thus it wasn't anymore consistent.
Place the structures referenced by Documentation/clk.txt in the
correct
Commit 'b09d6d991' removes include/linux/clk-private.h and
re-arranges the clock related structures contained in it in
different files. The documentation has not been updated
accordingly, thus it wasn't anymore consistent.
Place the structures referenced by Documentation/clk.txt in the
correct
FYI, we noticed below warning "BUG: sleeping function called from invalid
context at kernel/locking/mutex.c:97" showed on
https://github.com/0day-ci/linux
Bastien-Philbert/ipv6-icmp-Add-protection-from-concurrent-users-in-the-function-icmpv6_echo_reply/20160406-053
FYI, we noticed below warning "BUG: sleeping function called from invalid
context at kernel/locking/mutex.c:97" showed on
https://github.com/0day-ci/linux
Bastien-Philbert/ipv6-icmp-Add-protection-from-concurrent-users-in-the-function-icmpv6_echo_reply/20160406-053
On Wed, Apr 06, 2016 at 01:25:06PM +0300, Felipe Balbi wrote:
>
> Hi,
>
> Peter Chen writes:
> > On Wed, Apr 06, 2016 at 11:05:26AM +0300, Felipe Balbi wrote:
> >> Peter Chen writes:
> >> > On Wed, Apr 06, 2016 at 10:38:23AM +0300, Felipe Balbi
On Wed, Apr 06, 2016 at 01:25:06PM +0300, Felipe Balbi wrote:
>
> Hi,
>
> Peter Chen writes:
> > On Wed, Apr 06, 2016 at 11:05:26AM +0300, Felipe Balbi wrote:
> >> Peter Chen writes:
> >> > On Wed, Apr 06, 2016 at 10:38:23AM +0300, Felipe Balbi wrote:
> >> >> Peter Chen writes:
> >> >> > On
Hi,
> From: linux-acpi-ow...@vger.kernel.org [mailto:linux-acpi-
> ow...@vger.kernel.org] On Behalf Of Octavian Purdila
> Subject: Re: [RFC PATCH 10/10] acpi: add support for loading SSDTs via
> configfs
>
> On Wed, Apr 6, 2016 at 9:05 AM, Zheng, Lv wrote:
>
> >> It is
Hi,
> From: linux-acpi-ow...@vger.kernel.org [mailto:linux-acpi-
> ow...@vger.kernel.org] On Behalf Of Octavian Purdila
> Subject: Re: [RFC PATCH 10/10] acpi: add support for loading SSDTs via
> configfs
>
> On Wed, Apr 6, 2016 at 9:05 AM, Zheng, Lv wrote:
>
> >> It is hard to create new
Hi Gabriele,
On Wed, 6 Apr 2016 14:50:29 + Gabriele Paoloni wrote:
> Hi, sorry to be late on this
>
> > -Original Message-
> > From: linux-kernel-ow...@vger.kernel.org [mailto:linux-kernel-
> > ow...@vger.kernel.org] On Behalf Of Jisheng Zhang
> > Sent: 16 March 2016 11:41
> > To:
Hi Gabriele,
On Wed, 6 Apr 2016 14:50:29 + Gabriele Paoloni wrote:
> Hi, sorry to be late on this
>
> > -Original Message-
> > From: linux-kernel-ow...@vger.kernel.org [mailto:linux-kernel-
> > ow...@vger.kernel.org] On Behalf Of Jisheng Zhang
> > Sent: 16 March 2016 11:41
> > To:
On 2016/4/7 9:06, kernel test robot wrote:
> FYI, we noticed that will-it-scale.scalability -4.0% regression on
>
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
> commit 6f25a14a7053b69917e2ebea0d31dd444cd31fd5 ("mm: fix invalid node in
> alloc_migrate_target()")
>
On 2016/4/7 9:06, kernel test robot wrote:
> FYI, we noticed that will-it-scale.scalability -4.0% regression on
>
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
> commit 6f25a14a7053b69917e2ebea0d31dd444cd31fd5 ("mm: fix invalid node in
> alloc_migrate_target()")
>
On Mon, Apr 04, 2016 at 03:24:34PM +0200, Vlastimil Babka wrote:
> On 04/04/2016 07:12 AM, Minchan Kim wrote:
> >On Fri, Apr 01, 2016 at 11:29:14PM +0200, Vlastimil Babka wrote:
> >>Might have been better as a separate migration patch and then a
> >>compaction patch. It's prefixed mm/compaction,
On Mon, Apr 04, 2016 at 03:24:34PM +0200, Vlastimil Babka wrote:
> On 04/04/2016 07:12 AM, Minchan Kim wrote:
> >On Fri, Apr 01, 2016 at 11:29:14PM +0200, Vlastimil Babka wrote:
> >>Might have been better as a separate migration patch and then a
> >>compaction patch. It's prefixed mm/compaction,
On 04/07/2016 04:10 AM, Jiancheng Xue wrote:
> Hi Brian,
>Thank you very much for your comments. I'll fix these issues in next
> version.
> In addition, for easy understanding I'd like to rewrite hisi_spi_nor_write and
> hisi_spi_nor_read. Your comments on these modifications will be highly
On 04/07/2016 04:10 AM, Jiancheng Xue wrote:
> Hi Brian,
>Thank you very much for your comments. I'll fix these issues in next
> version.
> In addition, for easy understanding I'd like to rewrite hisi_spi_nor_write and
> hisi_spi_nor_read. Your comments on these modifications will be highly
On Mon, Apr 04, 2016 at 03:09:22PM +0200, Vlastimil Babka wrote:
> On 04/04/2016 04:25 AM, Minchan Kim wrote:
> >>
> >>Ah, I see, so it's designed with page lock to handle the concurrent
> >>isolations etc.
> >>
> >>In http://marc.info/?l=linux-mm=143816716511904=2 Mel has warned
> >>about doing
On Mon, Apr 04, 2016 at 03:09:22PM +0200, Vlastimil Babka wrote:
> On 04/04/2016 04:25 AM, Minchan Kim wrote:
> >>
> >>Ah, I see, so it's designed with page lock to handle the concurrent
> >>isolations etc.
> >>
> >>In http://marc.info/?l=linux-mm=143816716511904=2 Mel has warned
> >>about doing
On Wed, Apr 6, 2016 at 7:12 PM, Franklin S Cooper Jr. wrote:
> Hi All,
>
> Currently linux-next is failing to boot via NFS on my AM335x GP evm,
> AM437x GP evm and Beagle X15. I bisected the problem down to the commit
> "udp: remove headers from UDP packets before queueing".
>
> I
On Wed, Apr 6, 2016 at 7:12 PM, Franklin S Cooper Jr. wrote:
> Hi All,
>
> Currently linux-next is failing to boot via NFS on my AM335x GP evm,
> AM437x GP evm and Beagle X15. I bisected the problem down to the commit
> "udp: remove headers from UDP packets before queueing".
>
> I had to revert
Galileo Gen2 board uses the PCAL9535 as the GPIO expansion,
it is different from PCA9535 and includes interrupt mask/status registers,
The current driver does not support the interrupt registers configuration,
it causes some gpio pins cannot trigger interrupt events,
this patch fix this issue. The
Galileo Gen2 board uses the PCAL9535 as the GPIO expansion,
it is different from PCA9535 and includes interrupt mask/status registers,
The current driver does not support the interrupt registers configuration,
it causes some gpio pins cannot trigger interrupt events,
this patch fix this issue. The
On Thu, Apr 7, 2016 at 9:56 AM, Eric Wheeler wrote:
> On Thu, 7 Apr 2016, Ming Lei wrote:
>
>> On Thu, Apr 7, 2016 at 9:36 AM, Eric Wheeler
>> wrote:
>> > On Wed, 6 Apr 2016, Ming Lei wrote:
>> >
>> >> After arbitrary bio size is supported,
On Thu, Apr 7, 2016 at 9:56 AM, Eric Wheeler wrote:
> On Thu, 7 Apr 2016, Ming Lei wrote:
>
>> On Thu, Apr 7, 2016 at 9:36 AM, Eric Wheeler
>> wrote:
>> > On Wed, 6 Apr 2016, Ming Lei wrote:
>> >
>> >> After arbitrary bio size is supported, the incoming bio may
>> >> be very big. We have to
Hi Brian,
Thank you very much for your comments. I'll fix these issues in next version.
In addition, for easy understanding I'd like to rewrite hisi_spi_nor_write and
hisi_spi_nor_read. Your comments on these modifications will be highly
appreciated.
static int hisi_spi_nor_read(struct
Hi Brian,
Thank you very much for your comments. I'll fix these issues in next version.
In addition, for easy understanding I'd like to rewrite hisi_spi_nor_write and
hisi_spi_nor_read. Your comments on these modifications will be highly
appreciated.
static int hisi_spi_nor_read(struct
On Wed, Apr 06, 2016 at 04:26:33PM -0700, Kees Cook wrote:
> Hi Greg,
>
> Please pull these lkdtm changes for 4.6-rc3. (BTW, should I send these
> lkdtm pulls to you, or to Linus?)
I can take them, not a problem.
Or you send send me patches if that's easier.
> The following changes since
On Wed, Apr 06, 2016 at 04:26:33PM -0700, Kees Cook wrote:
> Hi Greg,
>
> Please pull these lkdtm changes for 4.6-rc3. (BTW, should I send these
> lkdtm pulls to you, or to Linus?)
I can take them, not a problem.
Or you send send me patches if that's easier.
> The following changes since
On 2016/4/5 23:54, Radim Krčmář wrote:
2016-04-05 14:18+0800, Yang Zhang:
On 2016/4/5 5:00, Rik van Riel wrote:
Given that delivering a timer to a guest seems to
involve trapping from the guest to the host, anyway,
I don't see a downside to your patch.
If that is ever changed (eg. allowing
On 2016/4/5 23:54, Radim Krčmář wrote:
2016-04-05 14:18+0800, Yang Zhang:
On 2016/4/5 5:00, Rik van Riel wrote:
Given that delivering a timer to a guest seems to
involve trapping from the guest to the host, anyway,
I don't see a downside to your patch.
If that is ever changed (eg. allowing
On Wed, 6 Apr 2016, Mika Penttila wrote:
> On 04/06/2016 12:53 AM, Hugh Dickins wrote:
> > +static void shmem_recovery_work(struct work_struct *work)
...
> > +
> > + if (head) {
> > + /* We are resuming work from a previous partial recovery */
> > + if (PageTeam(page))
> > +
On Wed, 6 Apr 2016, Mika Penttila wrote:
> On 04/06/2016 12:53 AM, Hugh Dickins wrote:
> > +static void shmem_recovery_work(struct work_struct *work)
...
> > +
> > + if (head) {
> > + /* We are resuming work from a previous partial recovery */
> > + if (PageTeam(page))
> > +
On Thu, 7 Apr 2016, Ming Lei wrote:
> On Thu, Apr 7, 2016 at 9:36 AM, Eric Wheeler
> wrote:
> > On Wed, 6 Apr 2016, Ming Lei wrote:
> >
> >> After arbitrary bio size is supported, the incoming bio may
> >> be very big. We have to split the bio into small bios so that
On Thu, 7 Apr 2016, Ming Lei wrote:
> On Thu, Apr 7, 2016 at 9:36 AM, Eric Wheeler
> wrote:
> > On Wed, 6 Apr 2016, Ming Lei wrote:
> >
> >> After arbitrary bio size is supported, the incoming bio may
> >> be very big. We have to split the bio into small bios so that
> >> each holds at most
On Thu, Apr 7, 2016 at 9:36 AM, Eric Wheeler wrote:
> On Wed, 6 Apr 2016, Ming Lei wrote:
>
>> After arbitrary bio size is supported, the incoming bio may
>> be very big. We have to split the bio into small bios so that
>> each holds at most BIO_MAX_PAGES bvecs for
On Thu, Apr 7, 2016 at 9:36 AM, Eric Wheeler wrote:
> On Wed, 6 Apr 2016, Ming Lei wrote:
>
>> After arbitrary bio size is supported, the incoming bio may
>> be very big. We have to split the bio into small bios so that
>> each holds at most BIO_MAX_PAGES bvecs for safety reason, such
>> as
On Wed, 6 Apr 2016, Ming Lei wrote:
> On Wed, Apr 6, 2016 at 1:44 AM, Ming Lei wrote:
> > After arbitrary bio size is supported, the incoming bio may
> > be very big. We have to split the bio into small bios so that
> > each holds at most BIO_MAX_PAGES bvecs for safety
On Wed, 6 Apr 2016, Ming Lei wrote:
> On Wed, Apr 6, 2016 at 1:44 AM, Ming Lei wrote:
> > After arbitrary bio size is supported, the incoming bio may
> > be very big. We have to split the bio into small bios so that
> > each holds at most BIO_MAX_PAGES bvecs for safety reason, such
> > as
avoid memset in perf_fetch_caller_regs, since it's the critical path of all
tracepoints.
It's called from perf_sw_event_sched, perf_event_task_sched_in and all of
perf_trace_##call
with this_cpu_ptr(&__perf_regs[..]) which are zero initialized by perpcu init
logic and
subsequent call to
avoid memset in perf_fetch_caller_regs, since it's the critical path of all
tracepoints.
It's called from perf_sw_event_sched, perf_event_task_sched_in and all of
perf_trace_##call
with this_cpu_ptr(&__perf_regs[..]) which are zero initialized by perpcu init
logic and
subsequent call to
introduce BPF_PROG_TYPE_TRACEPOINT program type and allow it to be attached
to the perf tracepoint handler, which will copy the arguments into
the per-cpu buffer and pass it to the bpf program as its first argument.
The layout of the fields can be discovered by doing
'cat
introduce BPF_PROG_TYPE_TRACEPOINT program type and allow it to be attached
to the perf tracepoint handler, which will copy the arguments into
the per-cpu buffer and pass it to the bpf program as its first argument.
The layout of the fields can be discovered by doing
'cat
Hi Steven, Peter,
v1->v2: addressed Peter's comments:
- fixed wording in patch 1, added ack
- refactored 2nd patch into 3:
2/10 remove unused __perf_addr macro which frees up
an argument in perf_trace_buf_submit
3/10 split perf_trace_buf_prepare into alloc and update parts, so that bpf
programs
now all calls to perf_trace_buf_submit() pass 0 as 4th
argument which will be repurposed in the next patch which will
change the meaning of 1st arg of perf_tp_event() to event_type
Signed-off-by: Alexei Starovoitov
---
include/trace/perf.h | 7 ++-
Hi Steven, Peter,
v1->v2: addressed Peter's comments:
- fixed wording in patch 1, added ack
- refactored 2nd patch into 3:
2/10 remove unused __perf_addr macro which frees up
an argument in perf_trace_buf_submit
3/10 split perf_trace_buf_prepare into alloc and update parts, so that bpf
programs
now all calls to perf_trace_buf_submit() pass 0 as 4th
argument which will be repurposed in the next patch which will
change the meaning of 1st arg of perf_tp_event() to event_type
Signed-off-by: Alexei Starovoitov
---
include/trace/perf.h | 7 ++-
include/trace/trace_events.h | 3
split allows to move expensive update of 'struct trace_entry' to later phase.
Repurpose unused 1st argument of perf_tp_event() to indicate event type.
While splitting use temp variable 'rctx' instead of '*rctx' to avoid
unnecessary loads done by the compiler due to -fno-strict-aliasing
Recognize "tracepoint/" section name prefix and attach the program
to that tracepoint.
Signed-off-by: Alexei Starovoitov
---
samples/bpf/bpf_load.c | 26 +-
1 file changed, 21 insertions(+), 5 deletions(-)
diff --git a/samples/bpf/bpf_load.c
the first microbenchmark does
fd=open("/proc/self/comm");
for() {
write(fd, "test");
}
and on 4 cpus in parallel:
writes per sec
base (no tracepoints, no kprobes) 930k
with kprobe at __set_task_comm() 420k
with tracepoint at task:task_rename
needs two wrapper functions to fetch 'struct pt_regs *' to convert
tracepoint bpf context into kprobe bpf context to reuse existing
helper functions
Signed-off-by: Alexei Starovoitov
---
include/linux/bpf.h | 1 +
kernel/bpf/stackmap.c| 2 +-
kernel/trace/bpf_trace.c
split allows to move expensive update of 'struct trace_entry' to later phase.
Repurpose unused 1st argument of perf_tp_event() to indicate event type.
While splitting use temp variable 'rctx' instead of '*rctx' to avoid
unnecessary loads done by the compiler due to -fno-strict-aliasing
Recognize "tracepoint/" section name prefix and attach the program
to that tracepoint.
Signed-off-by: Alexei Starovoitov
---
samples/bpf/bpf_load.c | 26 +-
1 file changed, 21 insertions(+), 5 deletions(-)
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
the first microbenchmark does
fd=open("/proc/self/comm");
for() {
write(fd, "test");
}
and on 4 cpus in parallel:
writes per sec
base (no tracepoints, no kprobes) 930k
with kprobe at __set_task_comm() 420k
with tracepoint at task:task_rename
needs two wrapper functions to fetch 'struct pt_regs *' to convert
tracepoint bpf context into kprobe bpf context to reuse existing
helper functions
Signed-off-by: Alexei Starovoitov
---
include/linux/bpf.h | 1 +
kernel/bpf/stackmap.c| 2 +-
kernel/trace/bpf_trace.c | 42
during bpf program loading remember the last byte of ctx access
and at the time of attaching the program to tracepoint check that
the program doesn't access bytes beyond defined in tracepoint fields
This also disallows access to __dynamic_array fields, but can be
relaxed in the future.
during bpf program loading remember the last byte of ctx access
and at the time of attaching the program to tracepoint check that
the program doesn't access bytes beyond defined in tracepoint fields
This also disallows access to __dynamic_array fields, but can be
relaxed in the future.
modify offwaketime to work with sched/sched_switch tracepoint
instead of kprobe into finish_task_switch
Signed-off-by: Alexei Starovoitov
---
samples/bpf/offwaketime_kern.c | 26 ++
1 file changed, 22 insertions(+), 4 deletions(-)
diff --git
modify offwaketime to work with sched/sched_switch tracepoint
instead of kprobe into finish_task_switch
Signed-off-by: Alexei Starovoitov
---
samples/bpf/offwaketime_kern.c | 26 ++
1 file changed, 22 insertions(+), 4 deletions(-)
diff --git
register tracepoint bpf program type and let it call the same set
of helper functions as BPF_PROG_TYPE_KPROBE
Signed-off-by: Alexei Starovoitov
---
kernel/trace/bpf_trace.c | 45 +++--
1 file changed, 43 insertions(+), 2 deletions(-)
register tracepoint bpf program type and let it call the same set
of helper functions as BPF_PROG_TYPE_KPROBE
Signed-off-by: Alexei Starovoitov
---
kernel/trace/bpf_trace.c | 45 +++--
1 file changed, 43 insertions(+), 2 deletions(-)
diff --git
On 04/06/2016 08:57 PM, Jisheng Zhang wrote:
>
>
> On Wed, 6 Apr 2016 19:38:30 +0800 Baolin Wang wrote:
>
>> This patch removes some redundant debug prints, since we have added some
>> tracepoints to help with performance analysis of MMC subsystem.
>
> I think the debug prints you removed are
On 04/06/2016 08:57 PM, Jisheng Zhang wrote:
>
>
> On Wed, 6 Apr 2016 19:38:30 +0800 Baolin Wang wrote:
>
>> This patch removes some redundant debug prints, since we have added some
>> tracepoints to help with performance analysis of MMC subsystem.
>
> I think the debug prints you removed are
Hi Julien,
On 2016/4/6 19:32, Julien Grall wrote:
> Hi Shannon,
>
> On 01/04/2016 16:48, Shannon Zhao wrote:
>> This patch set adds ACPI support for Xen Dom0 on ARM64. The relevant Xen
>> ACPI on ARM64 design document could be found from [1].
>>
>> This patch set adds a new FDT node "uefi" under
Hi Julien,
On 2016/4/6 19:32, Julien Grall wrote:
> Hi Shannon,
>
> On 01/04/2016 16:48, Shannon Zhao wrote:
>> This patch set adds ACPI support for Xen Dom0 on ARM64. The relevant Xen
>> ACPI on ARM64 design document could be found from [1].
>>
>> This patch set adds a new FDT node "uefi" under
101 - 200 of 1854 matches
Mail list logo