| Message ID | 20170606071708.28229-1-dev@lynxeye.de (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Tue, Jun 06, 2017 at 09:17:06AM +0200, Lucas Stach wrote: > GPU buffers can be quite large, so userspace is expected to deal with > allocation failure. Don't trigger the OOM killer when page allocation for > the GEM objects fails, as this opens an easy possiblity for unprivileged > applications to DOS the system,a s the shmem pages are not fully accounted > to the allocating process. > > Signed-off-by: Lucas Stach <dev@lynxeye.de> > --- > drivers/gpu/drm/etnaviv/etnaviv_gem.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c > index f0efc5d..4c53508 100644 > --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c > +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c > @@ -662,7 +662,8 @@ static struct drm_gem_object *__etnaviv_gem_new(struct drm_device *dev, > * going to pin these pages. > */ > mapping = obj->filp->f_mapping; > - mapping_set_gfp_mask(mapping, GFP_HIGHUSER); > + mapping_set_gfp_mask(mapping, GFP_HIGHUSER | > + __GFP_NORETRY | __GFP_NOWARN); _NORETRY means the mm does try hard at all to free memory. We've just done this patch in 4.12 and totally regret it, because now gpu tasks run out of memory with plenty of (gpu) memory available that could be reaped. There's some discussions going on with Michal Hocko and Chris Wilson about possible solutions for this without so much hacks. -Daniel
Am Dienstag, den 20.06.2017, 11:06 +0200 schrieb Daniel Vetter: > On Tue, Jun 06, 2017 at 09:17:06AM +0200, Lucas Stach wrote: > > GPU buffers can be quite large, so userspace is expected to deal with > > allocation failure. Don't trigger the OOM killer when page allocation for > > the GEM objects fails, as this opens an easy possiblity for unprivileged > > applications to DOS the system,a s the shmem pages are not fully accounted > > to the allocating process. > > > > Signed-off-by: Lucas Stach <dev@lynxeye.de> > > --- > > drivers/gpu/drm/etnaviv/etnaviv_gem.c | 3 ++- > > 1 file changed, 2 insertions(+), 1 deletion(-) > > > > diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c > > index f0efc5d..4c53508 100644 > > --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c > > +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c > > @@ -662,7 +662,8 @@ static struct drm_gem_object *__etnaviv_gem_new(struct drm_device *dev, > > * going to pin these pages. > > */ > > mapping = obj->filp->f_mapping; > > - mapping_set_gfp_mask(mapping, GFP_HIGHUSER); > > + mapping_set_gfp_mask(mapping, GFP_HIGHUSER | > > + __GFP_NORETRY | __GFP_NOWARN); > > _NORETRY means the mm does try hard at all to free memory. We've just done > this patch in 4.12 and totally regret it, because now gpu tasks run out of > memory with plenty of (gpu) memory available that could be reaped. > > There's some discussions going on with Michal Hocko and Chris Wilson > about possible solutions for this without so much hacks. Thanks for the heads up. In contrast to some of the other drivers Etnaviv hasn't grown a proper shrinker yet, so I still think this patch is a step in the right direction for the time being. Currently with Etnaviv sitting on lots of GPU memory and the MM trying hard to free more memory for GPU usage a simple piglit run might pressure the OOM killer hard enough to bring the system down by killing PID 1. Regards, Lucas
On Tue, Jun 20, 2017 at 11:22:06AM +0200, Lucas Stach wrote: > Am Dienstag, den 20.06.2017, 11:06 +0200 schrieb Daniel Vetter: > > On Tue, Jun 06, 2017 at 09:17:06AM +0200, Lucas Stach wrote: > > > GPU buffers can be quite large, so userspace is expected to deal with > > > allocation failure. Don't trigger the OOM killer when page allocation for > > > the GEM objects fails, as this opens an easy possiblity for unprivileged > > > applications to DOS the system,a s the shmem pages are not fully accounted > > > to the allocating process. > > > > > > Signed-off-by: Lucas Stach <dev@lynxeye.de> > > > --- > > > drivers/gpu/drm/etnaviv/etnaviv_gem.c | 3 ++- > > > 1 file changed, 2 insertions(+), 1 deletion(-) > > > > > > diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c > > > index f0efc5d..4c53508 100644 > > > --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c > > > +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c > > > @@ -662,7 +662,8 @@ static struct drm_gem_object *__etnaviv_gem_new(struct drm_device *dev, > > > * going to pin these pages. > > > */ > > > mapping = obj->filp->f_mapping; > > > - mapping_set_gfp_mask(mapping, GFP_HIGHUSER); > > > + mapping_set_gfp_mask(mapping, GFP_HIGHUSER | > > > + __GFP_NORETRY | __GFP_NOWARN); > > > > _NORETRY means the mm does try hard at all to free memory. We've just done > > this patch in 4.12 and totally regret it, because now gpu tasks run out of > > memory with plenty of (gpu) memory available that could be reaped. > > > > There's some discussions going on with Michal Hocko and Chris Wilson > > about possible solutions for this without so much hacks. > > Thanks for the heads up. In contrast to some of the other drivers > Etnaviv hasn't grown a proper shrinker yet, so I still think this patch > is a step in the right direction for the time being. > Currently with Etnaviv sitting on lots of GPU memory and the MM trying > hard to free more memory for GPU usage a simple piglit run might > pressure the OOM killer hard enough to bring the system down by killing > PID 1. Ah ok, that changes the balance of course. Time to type that shrinker I'd say :-) -Daniel
On Tue 20-06-17 11:25:24, Daniel Vetter wrote: > On Tue, Jun 20, 2017 at 11:22:06AM +0200, Lucas Stach wrote: > > Am Dienstag, den 20.06.2017, 11:06 +0200 schrieb Daniel Vetter: > > > On Tue, Jun 06, 2017 at 09:17:06AM +0200, Lucas Stach wrote: > > > > GPU buffers can be quite large, so userspace is expected to deal with > > > > allocation failure. Don't trigger the OOM killer when page allocation for > > > > the GEM objects fails, as this opens an easy possiblity for unprivileged > > > > applications to DOS the system,a s the shmem pages are not fully accounted > > > > to the allocating process. > > > > > > > > Signed-off-by: Lucas Stach <dev@lynxeye.de> > > > > --- > > > > drivers/gpu/drm/etnaviv/etnaviv_gem.c | 3 ++- > > > > 1 file changed, 2 insertions(+), 1 deletion(-) > > > > > > > > diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c > > > > index f0efc5d..4c53508 100644 > > > > --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c > > > > +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c > > > > @@ -662,7 +662,8 @@ static struct drm_gem_object *__etnaviv_gem_new(struct drm_device *dev, > > > > * going to pin these pages. > > > > */ > > > > mapping = obj->filp->f_mapping; > > > > - mapping_set_gfp_mask(mapping, GFP_HIGHUSER); > > > > + mapping_set_gfp_mask(mapping, GFP_HIGHUSER | > > > > + __GFP_NORETRY | __GFP_NOWARN); > > > > > > _NORETRY means the mm does try hard at all to free memory. We've just done > > > this patch in 4.12 and totally regret it, because now gpu tasks run out of > > > memory with plenty of (gpu) memory available that could be reaped. > > > > > > There's some discussions going on with Michal Hocko and Chris Wilson > > > about possible solutions for this without so much hacks. > > > > Thanks for the heads up. In contrast to some of the other drivers > > Etnaviv hasn't grown a proper shrinker yet, so I still think this patch > > is a step in the right direction for the time being. > > Currently with Etnaviv sitting on lots of GPU memory and the MM trying > > hard to free more memory for GPU usage a simple piglit run might > > pressure the OOM killer hard enough to bring the system down by killing > > PID 1. > > Ah ok, that changes the balance of course. Time to type that shrinker I'd > say :-) Yeah, shrinker sounds like an absolute must. Anyway, I've posted __GFP_RETRY_MAYFAIL patchset [1] so you can use that flag. [1] http://lkml.kernel.org/r/20170623085345.11304-1-mhocko@kernel.org
Am Montag, den 26.06.2017, 07:52 +0200 schrieb Michal Hocko: > On Tue 20-06-17 11:25:24, Daniel Vetter wrote: > > On Tue, Jun 20, 2017 at 11:22:06AM +0200, Lucas Stach wrote: > > > Am Dienstag, den 20.06.2017, 11:06 +0200 schrieb Daniel Vetter: > > > > On Tue, Jun 06, 2017 at 09:17:06AM +0200, Lucas Stach wrote: > > > > > GPU buffers can be quite large, so userspace is expected to > > > > > deal with > > > > > allocation failure. Don't trigger the OOM killer when page > > > > > allocation for > > > > > the GEM objects fails, as this opens an easy possiblity for > > > > > unprivileged > > > > > applications to DOS the system,a s the shmem pages are not > > > > > fully accounted > > > > > to the allocating process. > > > > > > > > > > Signed-off-by: Lucas Stach <dev@lynxeye.de> > > > > > --- > > > > > drivers/gpu/drm/etnaviv/etnaviv_gem.c | 3 ++- > > > > > 1 file changed, 2 insertions(+), 1 deletion(-) > > > > > > > > > > diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c > > > > > b/drivers/gpu/drm/etnaviv/etnaviv_gem.c > > > > > index f0efc5d..4c53508 100644 > > > > > --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c > > > > > +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c > > > > > @@ -662,7 +662,8 @@ static struct drm_gem_object > > > > > *__etnaviv_gem_new(struct drm_device *dev, > > > > > * going to pin these pages. > > > > > */ > > > > > mapping = obj->filp->f_mapping; > > > > > - mapping_set_gfp_mask(mapping, GFP_HIGHUSER); > > > > > + mapping_set_gfp_mask(mapping, GFP_HIGHUSER | > > > > > + __GFP_NORETRY | > > > > > __GFP_NOWARN); > > > > > > > > _NORETRY means the mm does try hard at all to free memory. > > > > We've just done > > > > this patch in 4.12 and totally regret it, because now gpu tasks > > > > run out of > > > > memory with plenty of (gpu) memory available that could be > > > > reaped. > > > > > > > > There's some discussions going on with Michal Hocko and Chris > > > > Wilson > > > > about possible solutions for this without so much hacks. > > > > > > Thanks for the heads up. In contrast to some of the other drivers > > > Etnaviv hasn't grown a proper shrinker yet, so I still think this > > > patch > > > is a step in the right direction for the time being. > > > Currently with Etnaviv sitting on lots of GPU memory and the MM > > > trying > > > hard to free more memory for GPU usage a simple piglit run might > > > pressure the OOM killer hard enough to bring the system down by > > > killing > > > PID 1. > > > > Ah ok, that changes the balance of course. Time to type that > > shrinker I'd > > say :-) > > Yeah, shrinker sounds like an absolute must. Anyway, I've posted > __GFP_RETRY_MAYFAIL patchset [1] so you can use that flag. > > [1] http://lkml.kernel.org/r/20170623085345.11304-1-mhocko@kernel.org Thanks, I'll switch etnaviv over to use this flag when the patchset gets applied. A proper shrinker is on the TODO list, but there are only so much hours in a day... Regards, Lucas
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index f0efc5d..4c53508 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -662,7 +662,8 @@ static struct drm_gem_object *__etnaviv_gem_new(struct drm_device *dev, * going to pin these pages. */ mapping = obj->filp->f_mapping; - mapping_set_gfp_mask(mapping, GFP_HIGHUSER); + mapping_set_gfp_mask(mapping, GFP_HIGHUSER | + __GFP_NORETRY | __GFP_NOWARN); } if (ret)
GPU buffers can be quite large, so userspace is expected to deal with allocation failure. Don't trigger the OOM killer when page allocation for the GEM objects fails, as this opens an easy possiblity for unprivileged applications to DOS the system,a s the shmem pages are not fully accounted to the allocating process. Signed-off-by: Lucas Stach <dev@lynxeye.de> --- drivers/gpu/drm/etnaviv/etnaviv_gem.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)