nit: I would expect the version to trail "PATCH" in the subject, like:
[PATCH v2]
On Tue, Jun 26, 2018 at 5:50 AM, Chris von Recklinghausen
wrote:
> Enabling HARDENED_USER_COPY causes measurable regressions in the
> networking performances, up to 8% under UDP flood.
Please include the details on
[hopefully fixed the 'mm' recipient]
On Tue, 2018-06-26 at 09:54 -0700, Kees Cook wrote:
> On Tue, Jun 26, 2018 at 2:48 AM, Paolo Abeni wrote:
> > With CONFIG_HARDENED_USERCOPY=y, perf shows ~6% of CPU time spent
> > cumulatively in __check_object_size (~4%) and __virt_addr_valid (~2%).
>
> Are
On Tue, Jun 26, 2018 at 2:48 AM, Paolo Abeni wrote:
> Hi,
>
> On Mon, 25 Jun 2018 11:21:38 -0700 Kees Cook wrote:
>> On Mon, Jun 25, 2018 at 8:08 AM, Chris von Recklinghausen
>> wrote:
>> > Enabling HARDENED_USER_COPY causes measurable regressions in the
>> > networking performances, up to 8% un
On 06/26/2018 08:50 AM, Chris von Recklinghausen wrote:
> Enabling HARDENED_USER_COPY causes measurable regressions in the
> networking performances, up to 8% under UDP flood.
>
> A generic distro may want to enable HARDENED_USER_COPY in their default
> kernel config, but at the same time, such dis
Enabling HARDENED_USER_COPY causes measurable regressions in the
networking performances, up to 8% under UDP flood.
A generic distro may want to enable HARDENED_USER_COPY in their default
kernel config, but at the same time, such distro may want to be able to
avoid the performance penalties in wit
Hi,
On Mon, 25 Jun 2018 11:21:38 -0700 Kees Cook wrote:
> On Mon, Jun 25, 2018 at 8:08 AM, Chris von Recklinghausen
> wrote:
> > Enabling HARDENED_USER_COPY causes measurable regressions in the
> > networking performances, up to 8% under UDP flood.
>
> Which function is "hot"? i.e. which copy*u
On 06/25/2018 06:35 PM, Kees Cook wrote:
> On Mon, Jun 25, 2018 at 3:29 PM, Christoph von Recklinghausen
> wrote:
>> I have a small set of customers that want CONFIG_HARDENED_USERCOPY
>> enabled, and a large number of customers who would be impacted by its
>> default behavior (before my change).
On Mon, Jun 25, 2018 at 3:29 PM, Christoph von Recklinghausen
wrote:
> I have a small set of customers that want CONFIG_HARDENED_USERCOPY
> enabled, and a large number of customers who would be impacted by its
> default behavior (before my change). The desire was to have the smaller
> number of u
On 06/25/2018 03:44 PM, Laura Abbott wrote:
> On 06/25/2018 08:22 AM, Christoph von Recklinghausen wrote:
>> Add correct address for linux-mm
>>
>> On 06/25/2018 11:08 AM, Chris von Recklinghausen wrote:
>>> Enabling HARDENED_USER_COPY causes measurable regressions in the
>>> networking performance
On 06/25/2018 08:22 AM, Christoph von Recklinghausen wrote:
Add correct address for linux-mm
On 06/25/2018 11:08 AM, Chris von Recklinghausen wrote:
Enabling HARDENED_USER_COPY causes measurable regressions in the
networking performances, up to 8% under UDP flood.
A generic distro may want to
Hi Chris,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on linus/master]
[also build test ERROR on v4.18-rc2 next-20180625]
[if your patch is applied to the wrong git tree, please drop us a note to help
improve the system]
url:
https://github.com/0day-ci/linux/co
On Mon, Jun 25, 2018 at 8:08 AM, Chris von Recklinghausen
wrote:
> Enabling HARDENED_USER_COPY causes measurable regressions in the
> networking performances, up to 8% under UDP flood.
Which function is "hot"? i.e. which copy*user() is taking up the time?
Do you have a workload that at can be use
Hi Chris,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on linus/master]
[also build test ERROR on v4.18-rc2 next-20180625]
[if your patch is applied to the wrong git tree, please drop us a note to help
improve the system]
url:
https://github.com/0day-ci/linux/co
On 06/25/2018 08:08 AM, Chris von Recklinghausen wrote:
> Enabling HARDENED_USER_COPY causes measurable regressions in the
> networking performances, up to 8% under UDP flood.
>
> A generic distro may want to enable HARDENED_USER_COPY in their default
> kernel config, but at the same time, such di
Add correct address for linux-mm
On 06/25/2018 11:08 AM, Chris von Recklinghausen wrote:
> Enabling HARDENED_USER_COPY causes measurable regressions in the
> networking performances, up to 8% under UDP flood.
>
> A generic distro may want to enable HARDENED_USER_COPY in their default
> kernel conf
Enabling HARDENED_USER_COPY causes measurable regressions in the
networking performances, up to 8% under UDP flood.
A generic distro may want to enable HARDENED_USER_COPY in their default
kernel config, but at the same time, such distro may want to be able to
avoid the performance penalties in wit
16 matches
Mail list logo
