Re: [PATCH v2 24/24] drm/i915/bdw: Dynamic page table allocations in lrc mode

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Tue, Dec 23, 2014 at 05:16:27PM +0000, Michel Thierry wrote:
> Logic ring contexts need to know the PDPs when they are populated. With
> dynamic page table allocations, these PDPs may not exist yet.
> 
> Check if PDPs have been allocated and use the scratch page if they do
> not exist yet.
> 
> Before submission, update the PDPs in the logic ring context as PDPs
> have been allocated.
> 
> Signed-off-by: Michel Thierry <michel.thierry@xxxxxxxxx>

Patch subject is imo a bit misleading. What about "support dynamic pdp
updates in lrc mode"?
-Daniel

> ---
>  drivers/gpu/drm/i915/intel_lrc.c | 80 +++++++++++++++++++++++++++++++++++-----
>  1 file changed, 70 insertions(+), 10 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index 546884b..6abe4bc 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -358,6 +358,7 @@ static void execlists_elsp_write(struct intel_engine_cs *ring,
>  
>  static int execlists_update_context(struct drm_i915_gem_object *ctx_obj,
>  				    struct drm_i915_gem_object *ring_obj,
> +				    struct i915_hw_ppgtt *ppgtt,
>  				    u32 tail)
>  {
>  	struct page *page;
> @@ -369,6 +370,40 @@ static int execlists_update_context(struct drm_i915_gem_object *ctx_obj,
>  	reg_state[CTX_RING_TAIL+1] = tail;
>  	reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(ring_obj);
>  
> +	/* True PPGTT with dynamic page allocation: update PDP registers and
> +	 * point the unallocated PDPs to the scratch page
> +	 */
> +	if (ppgtt) {
> +		if (test_bit(3, ppgtt->pdp.used_pdpes)) {
> +			reg_state[CTX_PDP3_UDW+1] = upper_32_bits(ppgtt->pdp.pagedir[3]->daddr);
> +			reg_state[CTX_PDP3_LDW+1] = lower_32_bits(ppgtt->pdp.pagedir[3]->daddr);
> +		} else {
> +			reg_state[CTX_PDP3_UDW+1] = upper_32_bits(ppgtt->scratch_pd->daddr);
> +			reg_state[CTX_PDP3_LDW+1] = lower_32_bits(ppgtt->scratch_pd->daddr);
> +		}
> +		if (test_bit(2, ppgtt->pdp.used_pdpes)) {
> +			reg_state[CTX_PDP2_UDW+1] = upper_32_bits(ppgtt->pdp.pagedir[2]->daddr);
> +			reg_state[CTX_PDP2_LDW+1] = lower_32_bits(ppgtt->pdp.pagedir[2]->daddr);
> +		} else {
> +			reg_state[CTX_PDP2_UDW+1] = upper_32_bits(ppgtt->scratch_pd->daddr);
> +			reg_state[CTX_PDP2_LDW+1] = lower_32_bits(ppgtt->scratch_pd->daddr);
> +		}
> +		if (test_bit(1, ppgtt->pdp.used_pdpes)) {
> +			reg_state[CTX_PDP1_UDW+1] = upper_32_bits(ppgtt->pdp.pagedir[1]->daddr);
> +			reg_state[CTX_PDP1_LDW+1] = lower_32_bits(ppgtt->pdp.pagedir[1]->daddr);
> +		} else {
> +			reg_state[CTX_PDP1_UDW+1] = upper_32_bits(ppgtt->scratch_pd->daddr);
> +			reg_state[CTX_PDP1_LDW+1] = lower_32_bits(ppgtt->scratch_pd->daddr);
> +		}
> +		if (test_bit(0, ppgtt->pdp.used_pdpes)) {
> +			reg_state[CTX_PDP0_UDW+1] = upper_32_bits(ppgtt->pdp.pagedir[0]->daddr);
> +			reg_state[CTX_PDP0_LDW+1] = lower_32_bits(ppgtt->pdp.pagedir[0]->daddr);
> +		} else {
> +			reg_state[CTX_PDP0_UDW+1] = upper_32_bits(ppgtt->scratch_pd->daddr);
> +			reg_state[CTX_PDP0_LDW+1] = lower_32_bits(ppgtt->scratch_pd->daddr);
> +		}
> +	}
> +
>  	kunmap_atomic(reg_state);
>  
>  	return 0;
> @@ -387,7 +422,7 @@ static void execlists_submit_contexts(struct intel_engine_cs *ring,
>  	WARN_ON(!i915_gem_obj_is_pinned(ctx_obj0));
>  	WARN_ON(!i915_gem_obj_is_pinned(ringbuf0->obj));
>  
> -	execlists_update_context(ctx_obj0, ringbuf0->obj, tail0);
> +	execlists_update_context(ctx_obj0, ringbuf0->obj, to0->ppgtt, tail0);
>  
>  	if (to1) {
>  		ringbuf1 = to1->engine[ring->id].ringbuf;
> @@ -396,7 +431,7 @@ static void execlists_submit_contexts(struct intel_engine_cs *ring,
>  		WARN_ON(!i915_gem_obj_is_pinned(ctx_obj1));
>  		WARN_ON(!i915_gem_obj_is_pinned(ringbuf1->obj));
>  
> -		execlists_update_context(ctx_obj1, ringbuf1->obj, tail1);
> +		execlists_update_context(ctx_obj1, ringbuf1->obj, to1->ppgtt, tail1);
>  	}
>  
>  	execlists_elsp_write(ring, ctx_obj0, ctx_obj1);
> @@ -1731,14 +1766,39 @@ populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_o
>  	reg_state[CTX_PDP1_LDW] = GEN8_RING_PDP_LDW(ring, 1);
>  	reg_state[CTX_PDP0_UDW] = GEN8_RING_PDP_UDW(ring, 0);
>  	reg_state[CTX_PDP0_LDW] = GEN8_RING_PDP_LDW(ring, 0);
> -	reg_state[CTX_PDP3_UDW+1] = upper_32_bits(ppgtt->pdp.pagedir[3]->daddr);
> -	reg_state[CTX_PDP3_LDW+1] = lower_32_bits(ppgtt->pdp.pagedir[3]->daddr);
> -	reg_state[CTX_PDP2_UDW+1] = upper_32_bits(ppgtt->pdp.pagedir[2]->daddr);
> -	reg_state[CTX_PDP2_LDW+1] = lower_32_bits(ppgtt->pdp.pagedir[2]->daddr);
> -	reg_state[CTX_PDP1_UDW+1] = upper_32_bits(ppgtt->pdp.pagedir[1]->daddr);
> -	reg_state[CTX_PDP1_LDW+1] = lower_32_bits(ppgtt->pdp.pagedir[1]->daddr);
> -	reg_state[CTX_PDP0_UDW+1] = upper_32_bits(ppgtt->pdp.pagedir[0]->daddr);
> -	reg_state[CTX_PDP0_LDW+1] = lower_32_bits(ppgtt->pdp.pagedir[0]->daddr);
> +
> +	/* With dynamic page allocation, PDPs may not be allocated at this point,
> +	 * Point the unallocated PDPs to the scratch page
> +	 */
> +	if (test_bit(3, ppgtt->pdp.used_pdpes)) {
> +		reg_state[CTX_PDP3_UDW+1] = upper_32_bits(ppgtt->pdp.pagedir[3]->daddr);
> +		reg_state[CTX_PDP3_LDW+1] = lower_32_bits(ppgtt->pdp.pagedir[3]->daddr);
> +	} else {
> +		reg_state[CTX_PDP3_UDW+1] = upper_32_bits(ppgtt->scratch_pd->daddr);
> +		reg_state[CTX_PDP3_LDW+1] = lower_32_bits(ppgtt->scratch_pd->daddr);
> +	}
> +	if (test_bit(2, ppgtt->pdp.used_pdpes)) {
> +		reg_state[CTX_PDP2_UDW+1] = upper_32_bits(ppgtt->pdp.pagedir[2]->daddr);
> +		reg_state[CTX_PDP2_LDW+1] = lower_32_bits(ppgtt->pdp.pagedir[2]->daddr);
> +	} else {
> +		reg_state[CTX_PDP2_UDW+1] = upper_32_bits(ppgtt->scratch_pd->daddr);
> +		reg_state[CTX_PDP2_LDW+1] = lower_32_bits(ppgtt->scratch_pd->daddr);
> +	}
> +	if (test_bit(1, ppgtt->pdp.used_pdpes)) {
> +		reg_state[CTX_PDP1_UDW+1] = upper_32_bits(ppgtt->pdp.pagedir[1]->daddr);
> +		reg_state[CTX_PDP1_LDW+1] = lower_32_bits(ppgtt->pdp.pagedir[1]->daddr);
> +	} else {
> +		reg_state[CTX_PDP1_UDW+1] = upper_32_bits(ppgtt->scratch_pd->daddr);
> +		reg_state[CTX_PDP1_LDW+1] = lower_32_bits(ppgtt->scratch_pd->daddr);
> +	}
> +	if (test_bit(0, ppgtt->pdp.used_pdpes)) {
> +		reg_state[CTX_PDP0_UDW+1] = upper_32_bits(ppgtt->pdp.pagedir[0]->daddr);
> +		reg_state[CTX_PDP0_LDW+1] = lower_32_bits(ppgtt->pdp.pagedir[0]->daddr);
> +	} else {
> +		reg_state[CTX_PDP0_UDW+1] = upper_32_bits(ppgtt->scratch_pd->daddr);
> +		reg_state[CTX_PDP0_LDW+1] = lower_32_bits(ppgtt->scratch_pd->daddr);
> +	}
> +
>  	if (ring->id == RCS) {
>  		reg_state[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
>  		reg_state[CTX_R_PWR_CLK_STATE] = 0x20c8;
> -- 
> 2.1.1
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx

-- 
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
http://lists.freedesktop.org/mailman/listinfo/intel-gfx




[Index of Archives]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]
  Powered by Linux