On 2019-04-12 15:50:56 [+0200], To Guenter Roeck wrote:
> So I have this, let me try to dig further.
I'm such a moron. Patch is coming soon…
> > Guenter
>
Sebastian
On 2019-04-12 06:43:31 [-0700], Guenter Roeck wrote:
> On 4/12/19 1:42 AM, Sebastian Andrzej Siewior wrote:
> > On 2019-04-10 21:07:35 [-0700], Guenter Roeck wrote:
> > > Hi Sebastian,
> > Hi Guenter,
> >
> > > Unfortunately, this patch causes random crashes.
> > …
> > > This is seen with an arm64
On 4/12/19 1:54 AM, Sebastian Andrzej Siewior wrote:
On 2019-04-10 21:39:34 [-0700], Eric Biggers wrote:
Well, from a quick read of the patch, it's probably because it uses
raw_cpu_ptr() instead of per_cpu_ptr() when allocating/freeing the buffers, so
they are unlikely to actually be allocated f
On 4/12/19 1:42 AM, Sebastian Andrzej Siewior wrote:
On 2019-04-10 21:07:35 [-0700], Guenter Roeck wrote:
Hi Sebastian,
Hi Guenter,
Unfortunately, this patch causes random crashes.
…
This is seen with an arm64 image running on qemu with machine xlnx-zcu102
and two CPUs, and crypto test opti
On 2019-04-10 21:39:34 [-0700], Eric Biggers wrote:
> Well, from a quick read of the patch, it's probably because it uses
> raw_cpu_ptr() instead of per_cpu_ptr() when allocating/freeing the buffers, so
> they are unlikely to actually be allocated for all CPUs.
memory is allocated in crypto_scomp_
On 2019-04-10 21:07:35 [-0700], Guenter Roeck wrote:
> Hi Sebastian,
Hi Guenter,
> Unfortunately, this patch causes random crashes.
…
> This is seen with an arm64 image running on qemu with machine xlnx-zcu102
> and two CPUs, and crypto test options enabled. It happens roughly every
> other boot.
On Wed, Apr 10, 2019 at 09:07:35PM -0700, Guenter Roeck wrote:
> Hi Sebastian,
>
> On Fri, Mar 29, 2019 at 02:09:56PM +0100, Sebastian Andrzej Siewior wrote:
> > Two per-CPU variables are allocated as pointer to per-CPU memory which
> > then are used as scratch buffers.
> > We could be smart about
Hi Sebastian,
On Fri, Mar 29, 2019 at 02:09:56PM +0100, Sebastian Andrzej Siewior wrote:
> Two per-CPU variables are allocated as pointer to per-CPU memory which
> then are used as scratch buffers.
> We could be smart about this and use instead a per-CPU struct which
> contains the pointers alread
Two per-CPU variables are allocated as pointer to per-CPU memory which
then are used as scratch buffers.
We could be smart about this and use instead a per-CPU struct which
contains the pointers already and then we need to allocate just the
scratch buffers.
Add a lock to the struct. By doing so we
