[Freedreno] [PATCH 16/19] drm/msm/a6xx: Add support for per-instance pagetables

[Jordan Crouse]

On Mon, Aug 17, 2020 at 09:10:46PM +0530, Akhil P Oommen wrote:
> On 8/14/2020 8:11 AM, Rob Clark wrote:
> >From: Jordan Crouse <jcrouse at codeaurora.org>
> >
> >Add support for using per-instance pagetables if all the dependencies are
> >available.
> >
> >Signed-off-by: Jordan Crouse <jcrouse at codeaurora.org>
> >Signed-off-by: Rob Clark <robdclark at chromium.org>
> >---
> >  drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 70 +++++++++++++++++++++++++++
> >  drivers/gpu/drm/msm/adreno/a6xx_gpu.h |  1 +
> >  drivers/gpu/drm/msm/msm_ringbuffer.h  |  1 +
> >  3 files changed, 72 insertions(+)
> >
> >diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> >index 5eabb0109577..9653ac9b3cb8 100644
> >--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> >+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> >@@ -81,6 +81,56 @@ static void get_stats_counter(struct msm_ringbuffer *ring, u32 counter,
> >  	OUT_RING(ring, upper_32_bits(iova));
> >  }
> >+static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
> >+		struct msm_ringbuffer *ring, struct msm_file_private *ctx)
> >+{
> >+	phys_addr_t ttbr;
> >+	u32 asid;
> >+	u64 memptr = rbmemptr(ring, ttbr0);
> >+
> >+	if (ctx == a6xx_gpu->cur_ctx)
> >+		return;
> >+
> >+	if (msm_iommu_pagetable_params(ctx->aspace->mmu, &ttbr, &asid))
> >+		return;
> >+
> >+	/* Execute the table update */
> >+	OUT_PKT7(ring, CP_SMMU_TABLE_UPDATE, 4);
> >+	OUT_RING(ring, CP_SMMU_TABLE_UPDATE_0_TTBR0_LO(lower_32_bits(ttbr)));
> >+
> >+	/*
> >+	 * For now ignore the asid since the smmu driver uses a TLBIASID to
> >+	 * flush the TLB when we use iommu_flush_tlb_all() and the smmu driver
> >+	 * isn't aware that the asid changed.  Instead, keep the default asid
> >+	 * (0, same as the context bank) to make sure the TLB is properly
> >+	 * flushed.
> >+	 */
> >+	OUT_RING(ring,
> >+		CP_SMMU_TABLE_UPDATE_1_TTBR0_HI(upper_32_bits(ttbr)) |
> >+		CP_SMMU_TABLE_UPDATE_1_ASID(0));
> >+	OUT_RING(ring, CP_SMMU_TABLE_UPDATE_2_CONTEXTIDR(0));
> >+	OUT_RING(ring, CP_SMMU_TABLE_UPDATE_3_CONTEXTBANK(0));
> >+
> >+	/*
> >+	 * Write the new TTBR0 to the memstore. This is good for debugging.
> >+	 */
> >+	OUT_PKT7(ring, CP_MEM_WRITE, 4);
> >+	OUT_RING(ring, CP_MEM_WRITE_0_ADDR_LO(lower_32_bits(memptr)));
> >+	OUT_RING(ring, CP_MEM_WRITE_1_ADDR_HI(upper_32_bits(memptr)));
> >+	OUT_RING(ring, lower_32_bits(ttbr));
> >+	OUT_RING(ring, (0 << 16) | upper_32_bits(ttbr));
> why (0 << 16) is required here?

Because that is the ASID we are using and we would want the debug TTBR0 to match
the hardware as closely as possible.

> >+
> >+	/*
> >+	 * And finally, trigger a uche flush to be sure there isn't anything
> >+	 * lingering in that part of the GPU
> >+	 */
> >+
> >+	OUT_PKT7(ring, CP_EVENT_WRITE, 1);
> >+	OUT_RING(ring, 0x31);
> This may be unnecessary, but no harm in keeping it. SMMU_TABLE_UPDATE is
> supposed to do a UCHE flush.

Correct but I think it is wise to try to match the downstream sequence as much
as possible.

Jordan

> -Akhil
> >+
> >+	a6xx_gpu->cur_ctx = ctx;
> >+}
> >+
> >  static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
> >  {
> >  	unsigned int index = submit->seqno % MSM_GPU_SUBMIT_STATS_COUNT;
> >@@ -90,6 +140,8 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
> >  	struct msm_ringbuffer *ring = submit->ring;
> >  	unsigned int i;
> >+	a6xx_set_pagetable(a6xx_gpu, ring, submit->queue->ctx);
> >+
> >  	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP_0_LO,
> >  		rbmemptr_stats(ring, index, cpcycles_start));
> >@@ -696,6 +748,8 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
> >  	/* Always come up on rb 0 */
> >  	a6xx_gpu->cur_ring = gpu->rb[0];
> >+	a6xx_gpu->cur_ctx = NULL;
> >+
> >  	/* Enable the SQE_to start the CP engine */
> >  	gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 1);
> >@@ -1008,6 +1062,21 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu)
> >  	return (unsigned long)busy_time;
> >  }
> >+static struct msm_gem_address_space *
> >+a6xx_create_private_address_space(struct msm_gpu *gpu)
> >+{
> >+	struct msm_gem_address_space *aspace = NULL;
> >+	struct msm_mmu *mmu;
> >+
> >+	mmu = msm_iommu_pagetable_create(gpu->aspace->mmu);
> >+
> >+	if (!IS_ERR(mmu))
> >+		aspace = msm_gem_address_space_create(mmu,
> >+			"gpu", 0x100000000ULL, 0x1ffffffffULL);
> >+
> >+	return aspace;
> >+}
> >+
> >  static const struct adreno_gpu_funcs funcs = {
> >  	.base = {
> >  		.get_param = adreno_get_param,
> >@@ -1031,6 +1100,7 @@ static const struct adreno_gpu_funcs funcs = {
> >  		.gpu_state_put = a6xx_gpu_state_put,
> >  #endif
> >  		.create_address_space = adreno_iommu_create_address_space,
> >+		.create_private_address_space = a6xx_create_private_address_space,
> >  	},
> >  	.get_timestamp = a6xx_get_timestamp,
> >  };
> >diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> >index 03ba60d5b07f..da22d7549d9b 100644
> >--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> >+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> >@@ -19,6 +19,7 @@ struct a6xx_gpu {
> >  	uint64_t sqe_iova;
> >  	struct msm_ringbuffer *cur_ring;
> >+	struct msm_file_private *cur_ctx;
> >  	struct a6xx_gmu gmu;
> >  };
> >diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.h b/drivers/gpu/drm/msm/msm_ringbuffer.h
> >index 7764373d0ed2..0987d6bf848c 100644
> >--- a/drivers/gpu/drm/msm/msm_ringbuffer.h
> >+++ b/drivers/gpu/drm/msm/msm_ringbuffer.h
> >@@ -31,6 +31,7 @@ struct msm_rbmemptrs {
> >  	volatile uint32_t fence;
> >  	volatile struct msm_gpu_submit_stats stats[MSM_GPU_SUBMIT_STATS_COUNT];
> >+	volatile u64 ttbr0;
> >  };
> >  struct msm_ringbuffer {
> >
> 

-- 
The Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum,
a Linux Foundation Collaborative Project