From: Rob Clark <[email protected]>
In theory a context can be destroyed and a new one allocated at the same
address, making the pointer comparision to detect when we don't need to
update the current pagetables invalid. Instead assign a sequence number
to each context on creation, and use this for the check.
Fixes: 84c31ee16f90 ("drm/msm/a6xx: Add support for per-instance pagetables")
Signed-off-by: Rob Clark <[email protected]>
---
drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 6 +++---
drivers/gpu/drm/msm/adreno/a6xx_gpu.h | 11 ++++++++++-
drivers/gpu/drm/msm/msm_drv.c | 3 +++
drivers/gpu/drm/msm/msm_drv.h | 1 +
4 files changed, 17 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 5e1ae3df42ba..e0a8b2fd1ff0 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -106,7 +106,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
u32 asid;
u64 memptr = rbmemptr(ring, ttbr0);
- if (ctx == a6xx_gpu->cur_ctx)
+ if (ctx->seqno == a6xx_gpu->cur_ctx_seqno)
return;
if (msm_iommu_pagetable_params(ctx->aspace->mmu, &ttbr, &asid))
@@ -139,7 +139,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
OUT_PKT7(ring, CP_EVENT_WRITE, 1);
OUT_RING(ring, 0x31);
- a6xx_gpu->cur_ctx = ctx;
+ a6xx_gpu->cur_ctx_seqno = ctx->seqno;
}
static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
@@ -1081,7 +1081,7 @@ static int hw_init(struct msm_gpu *gpu)
/* Always come up on rb 0 */
a6xx_gpu->cur_ring = gpu->rb[0];
- a6xx_gpu->cur_ctx = NULL;
+ a6xx_gpu->cur_ctx_seqno = 0;
/* Enable the SQE_to start the CP engine */
gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 1);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
index 0bc2d062f54a..8e5527c881b1 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
@@ -19,7 +19,16 @@ struct a6xx_gpu {
uint64_t sqe_iova;
struct msm_ringbuffer *cur_ring;
- struct msm_file_private *cur_ctx;
+
+ /**
+ * cur_ctx_seqno:
+ *
+ * The ctx->seqno value of the context with current pgtables
+ * installed. Tracked by seqno rather than pointer value to
+ * avoid dangling pointers, and cases where a ctx can be freed
+ * and a new one created with the same address.
+ */
+ int cur_ctx_seqno;
struct a6xx_gmu gmu;
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 624078b3adf2..30c1efc3d8a0 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -711,6 +711,7 @@ static void load_gpu(struct drm_device *dev)
static int context_init(struct drm_device *dev, struct drm_file *file)
{
+ static atomic_t ident = ATOMIC_INIT(0);
struct msm_drm_private *priv = dev->dev_private;
struct msm_file_private *ctx;
@@ -727,6 +728,8 @@ static int context_init(struct drm_device *dev, struct drm_file *file)
ctx->aspace = msm_gpu_create_private_address_space(priv->gpu, current);
file->driver_priv = ctx;
+ ctx->seqno = atomic_inc_return(&ident);
+
return 0;
}
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index de062450add4..8633d0059a3e 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -59,6 +59,7 @@ struct msm_file_private {
int queueid;
struct msm_gem_address_space *aspace;
struct kref ref;
+ int seqno;
};
enum msm_mdp_plane_property {
--
2.31.1
On Thu, Sep 30, 2021 at 8:20 PM Rob Clark <[email protected]> wrote:
>
> From: Rob Clark <[email protected]>
>
> In theory a context can be destroyed and a new one allocated at the same
> address, making the pointer comparision to detect when we don't need to
> update the current pagetables invalid. Instead assign a sequence number
> to each context on creation, and use this for the check.
>
> Fixes: 84c31ee16f90 ("drm/msm/a6xx: Add support for per-instance pagetables")
> Signed-off-by: Rob Clark <[email protected]>
Usually the weak reference pattern is to wrap a spinlock or something
around it and clear it out on destruction. Or hold a full reference
(e.g. on intel hw the hw goes unhappy if there's no context/pagetables
at all, so we always need some). But I guess this works too.
-Daniel
> ---
> drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 6 +++---
> drivers/gpu/drm/msm/adreno/a6xx_gpu.h | 11 ++++++++++-
> drivers/gpu/drm/msm/msm_drv.c | 3 +++
> drivers/gpu/drm/msm/msm_drv.h | 1 +
> 4 files changed, 17 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> index 5e1ae3df42ba..e0a8b2fd1ff0 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> @@ -106,7 +106,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
> u32 asid;
> u64 memptr = rbmemptr(ring, ttbr0);
>
> - if (ctx == a6xx_gpu->cur_ctx)
> + if (ctx->seqno == a6xx_gpu->cur_ctx_seqno)
> return;
>
> if (msm_iommu_pagetable_params(ctx->aspace->mmu, &ttbr, &asid))
> @@ -139,7 +139,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
> OUT_PKT7(ring, CP_EVENT_WRITE, 1);
> OUT_RING(ring, 0x31);
>
> - a6xx_gpu->cur_ctx = ctx;
> + a6xx_gpu->cur_ctx_seqno = ctx->seqno;
> }
>
> static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
> @@ -1081,7 +1081,7 @@ static int hw_init(struct msm_gpu *gpu)
> /* Always come up on rb 0 */
> a6xx_gpu->cur_ring = gpu->rb[0];
>
> - a6xx_gpu->cur_ctx = NULL;
> + a6xx_gpu->cur_ctx_seqno = 0;
>
> /* Enable the SQE_to start the CP engine */
> gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 1);
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> index 0bc2d062f54a..8e5527c881b1 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> @@ -19,7 +19,16 @@ struct a6xx_gpu {
> uint64_t sqe_iova;
>
> struct msm_ringbuffer *cur_ring;
> - struct msm_file_private *cur_ctx;
> +
> + /**
> + * cur_ctx_seqno:
> + *
> + * The ctx->seqno value of the context with current pgtables
> + * installed. Tracked by seqno rather than pointer value to
> + * avoid dangling pointers, and cases where a ctx can be freed
> + * and a new one created with the same address.
> + */
> + int cur_ctx_seqno;
>
> struct a6xx_gmu gmu;
>
> diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
> index 624078b3adf2..30c1efc3d8a0 100644
> --- a/drivers/gpu/drm/msm/msm_drv.c
> +++ b/drivers/gpu/drm/msm/msm_drv.c
> @@ -711,6 +711,7 @@ static void load_gpu(struct drm_device *dev)
>
> static int context_init(struct drm_device *dev, struct drm_file *file)
> {
> + static atomic_t ident = ATOMIC_INIT(0);
> struct msm_drm_private *priv = dev->dev_private;
> struct msm_file_private *ctx;
>
> @@ -727,6 +728,8 @@ static int context_init(struct drm_device *dev, struct drm_file *file)
> ctx->aspace = msm_gpu_create_private_address_space(priv->gpu, current);
> file->driver_priv = ctx;
>
> + ctx->seqno = atomic_inc_return(&ident);
> +
> return 0;
> }
>
> diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
> index de062450add4..8633d0059a3e 100644
> --- a/drivers/gpu/drm/msm/msm_drv.h
> +++ b/drivers/gpu/drm/msm/msm_drv.h
> @@ -59,6 +59,7 @@ struct msm_file_private {
> int queueid;
> struct msm_gem_address_space *aspace;
> struct kref ref;
> + int seqno;
> };
>
> enum msm_mdp_plane_property {
> --
> 2.31.1
>
--
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
On Thu, Sep 30, 2021 at 11:34 AM Daniel Vetter <[email protected]> wrote:
>
> On Thu, Sep 30, 2021 at 8:20 PM Rob Clark <[email protected]> wrote:
> >
> > From: Rob Clark <[email protected]>
> >
> > In theory a context can be destroyed and a new one allocated at the same
> > address, making the pointer comparision to detect when we don't need to
> > update the current pagetables invalid. Instead assign a sequence number
> > to each context on creation, and use this for the check.
> >
> > Fixes: 84c31ee16f90 ("drm/msm/a6xx: Add support for per-instance pagetables")
> > Signed-off-by: Rob Clark <[email protected]>
>
> Usually the weak reference pattern is to wrap a spinlock or something
> around it and clear it out on destruction. Or hold a full reference
> (e.g. on intel hw the hw goes unhappy if there's no context/pagetables
> at all, so we always need some). But I guess this works too.
yeah, the seqno approach was so that gen agnostic code didn't have to
go fishing around in a6xx_gpu..
I guess the downside is userspace could open/close the dev file 2^32
times without submitting any rendering to trigger the same sort of
issue. But there are plenty of easier ways for userspace to trigger
faults if it wanted.
BR,
-R
> -Daniel
>
> > ---
> > drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 6 +++---
> > drivers/gpu/drm/msm/adreno/a6xx_gpu.h | 11 ++++++++++-
> > drivers/gpu/drm/msm/msm_drv.c | 3 +++
> > drivers/gpu/drm/msm/msm_drv.h | 1 +
> > 4 files changed, 17 insertions(+), 4 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> > index 5e1ae3df42ba..e0a8b2fd1ff0 100644
> > --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> > +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> > @@ -106,7 +106,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
> > u32 asid;
> > u64 memptr = rbmemptr(ring, ttbr0);
> >
> > - if (ctx == a6xx_gpu->cur_ctx)
> > + if (ctx->seqno == a6xx_gpu->cur_ctx_seqno)
> > return;
> >
> > if (msm_iommu_pagetable_params(ctx->aspace->mmu, &ttbr, &asid))
> > @@ -139,7 +139,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
> > OUT_PKT7(ring, CP_EVENT_WRITE, 1);
> > OUT_RING(ring, 0x31);
> >
> > - a6xx_gpu->cur_ctx = ctx;
> > + a6xx_gpu->cur_ctx_seqno = ctx->seqno;
> > }
> >
> > static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
> > @@ -1081,7 +1081,7 @@ static int hw_init(struct msm_gpu *gpu)
> > /* Always come up on rb 0 */
> > a6xx_gpu->cur_ring = gpu->rb[0];
> >
> > - a6xx_gpu->cur_ctx = NULL;
> > + a6xx_gpu->cur_ctx_seqno = 0;
> >
> > /* Enable the SQE_to start the CP engine */
> > gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 1);
> > diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> > index 0bc2d062f54a..8e5527c881b1 100644
> > --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> > +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> > @@ -19,7 +19,16 @@ struct a6xx_gpu {
> > uint64_t sqe_iova;
> >
> > struct msm_ringbuffer *cur_ring;
> > - struct msm_file_private *cur_ctx;
> > +
> > + /**
> > + * cur_ctx_seqno:
> > + *
> > + * The ctx->seqno value of the context with current pgtables
> > + * installed. Tracked by seqno rather than pointer value to
> > + * avoid dangling pointers, and cases where a ctx can be freed
> > + * and a new one created with the same address.
> > + */
> > + int cur_ctx_seqno;
> >
> > struct a6xx_gmu gmu;
> >
> > diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
> > index 624078b3adf2..30c1efc3d8a0 100644
> > --- a/drivers/gpu/drm/msm/msm_drv.c
> > +++ b/drivers/gpu/drm/msm/msm_drv.c
> > @@ -711,6 +711,7 @@ static void load_gpu(struct drm_device *dev)
> >
> > static int context_init(struct drm_device *dev, struct drm_file *file)
> > {
> > + static atomic_t ident = ATOMIC_INIT(0);
> > struct msm_drm_private *priv = dev->dev_private;
> > struct msm_file_private *ctx;
> >
> > @@ -727,6 +728,8 @@ static int context_init(struct drm_device *dev, struct drm_file *file)
> > ctx->aspace = msm_gpu_create_private_address_space(priv->gpu, current);
> > file->driver_priv = ctx;
> >
> > + ctx->seqno = atomic_inc_return(&ident);
> > +
> > return 0;
> > }
> >
> > diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
> > index de062450add4..8633d0059a3e 100644
> > --- a/drivers/gpu/drm/msm/msm_drv.h
> > +++ b/drivers/gpu/drm/msm/msm_drv.h
> > @@ -59,6 +59,7 @@ struct msm_file_private {
> > int queueid;
> > struct msm_gem_address_space *aspace;
> > struct kref ref;
> > + int seqno;
> > };
> >
> > enum msm_mdp_plane_property {
> > --
> > 2.31.1
> >
>
>
> --
> Daniel Vetter
> Software Engineer, Intel Corporation
> http://blog.ffwll.ch