Chris Wilson <ch...@chris-wilson.co.uk> writes:
> We assume that the CSB is written using the normal ringbuffer
> coherency protocols, as outlined in kernel/events/ring_buffer.c:
>
> * (HW) (DRIVER)
> *
> * if (LOAD ->data_tail) { LOAD ->data_head
> * (A) smp_rmb() (C)
> * STORE $data LOAD $data
> * smp_wmb() (B) smp_mb() (D)
> * STORE ->data_head STORE ->data_tail
> * }
>
> So we assume that the HW fulfils its ordering requirements (B), and so
> we should use a complimentary rmb (C) to ensure that our read of its
> WRITE pointer is completed before we start accessing the data.
>
> The final mb (D) is implied by the uncached mmio we perform to inform
> the HW of our READ pointer.
>
> References: https://bugs.freedesktop.org/show_bug.cgi?id=105064
> References: https://bugs.freedesktop.org/show_bug.cgi?id=105888
> References: https://bugs.freedesktop.org/show_bug.cgi?id=106185
> Fixes: 767a983ab255 ("drm/i915/execlists: Read the context-status HEAD from
> the HWSP")
> References: 61bf9719fa17 ("drm/i915/cnl: Use mmio access to context status
> buffer")
> Suggested-by: Mika Kuoppala <mika.kuopp...@linux.intel.com>
> Signed-off-by: Chris Wilson <ch...@chris-wilson.co.uk>
> Cc: Mika Kuoppala <mika.kuopp...@linux.intel.com>
> Cc: Joonas Lahtinen <joonas.lahti...@linux.intel.com>
> Cc: Tvrtko Ursulin <tvrtko.ursu...@intel.com>
> Cc: Michał Winiarski <michal.winiar...@intel.com>
> Cc: Rafael Antognolli <rafael.antogno...@intel.com>
> Cc: Michel Thierry <michel.thie...@intel.com>
> Cc: Timo Aaltonen <tjaal...@ubuntu.com>
> Tested-by: Timo Aaltonen <tjaal...@ubuntu.com>
Acked-by: Mika Kuoppala <mika.kuopp...@intel.com>
This also makes the hwsp access work fine with iommu on (kbl).
-Mika
> ---
> drivers/gpu/drm/i915/intel_lrc.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c
> b/drivers/gpu/drm/i915/intel_lrc.c
> index 911f288f78aa..8977600f0d81 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -992,6 +992,7 @@ static void execlists_submission_tasklet(unsigned long
> data)
>
> head = execlists->csb_head;
> tail = READ_ONCE(buf[write_idx]);
> + rmb(); /* Hopefully paired with a wmb() in HW */
> }
> GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n",
> engine->name,
> --
> 2.17.0
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
