[PATCH v6 2/2] drm/msm/a6xx: Use the DMA API for GMU memory objects

From: Jordan Crouse
Date: Thu Mar 19 2020 - 23:36:46 EST


The GMU has very few memory allocations and uses a flat memory space so
there is no good reason to go out of our way to bypass the DMA APIs which
were basically designed for this exact scenario.

v7: Check return value of dma_set_mask_and_coherent
v4: Use dma_alloc_wc()
v3: Set the dma mask correctly and use dma_addr_t for the iova type
v2: Pass force_dma false to of_dma_configure to require that the DMA
region be set up and return error from of_dma_configure to fail probe.

Reviewed-by: Michael J. Ruhl <michael.j.ruhl@xxxxxxxxx>
Signed-off-by: Jordan Crouse <jcrouse@xxxxxxxxxxxxxx>
---

drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 115 +++-----------------------
drivers/gpu/drm/msm/adreno/a6xx_gmu.h | 6 +-
2 files changed, 14 insertions(+), 107 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 748cd379065f..c4e71abbdd53 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -2,6 +2,7 @@
/* Copyright (c) 2017-2019 The Linux Foundation. All rights reserved. */

#include <linux/clk.h>
+#include <linux/dma-mapping.h>
#include <linux/interconnect.h>
#include <linux/pm_domain.h>
#include <linux/pm_opp.h>
@@ -920,21 +921,10 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)

static void a6xx_gmu_memory_free(struct a6xx_gmu *gmu, struct a6xx_gmu_bo *bo)
{
- int count, i;
- u64 iova;
-
if (IS_ERR_OR_NULL(bo))
return;

- count = bo->size >> PAGE_SHIFT;
- iova = bo->iova;
-
- for (i = 0; i < count; i++, iova += PAGE_SIZE) {
- iommu_unmap(gmu->domain, iova, PAGE_SIZE);
- __free_pages(bo->pages[i], 0);
- }
-
- kfree(bo->pages);
+ dma_free_wc(gmu->dev, bo->size, bo->virt, bo->iova);
kfree(bo);
}

@@ -942,7 +932,6 @@ static struct a6xx_gmu_bo *a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu,
size_t size)
{
struct a6xx_gmu_bo *bo;
- int ret, count, i;

bo = kzalloc(sizeof(*bo), GFP_KERNEL);
if (!bo)
@@ -950,86 +939,14 @@ static struct a6xx_gmu_bo *a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu,

bo->size = PAGE_ALIGN(size);

- count = bo->size >> PAGE_SHIFT;
+ bo->virt = dma_alloc_wc(gmu->dev, bo->size, &bo->iova, GFP_KERNEL);

- bo->pages = kcalloc(count, sizeof(struct page *), GFP_KERNEL);
- if (!bo->pages) {
+ if (!bo->virt) {
kfree(bo);
return ERR_PTR(-ENOMEM);
}

- for (i = 0; i < count; i++) {
- bo->pages[i] = alloc_page(GFP_KERNEL);
- if (!bo->pages[i])
- goto err;
- }
-
- bo->iova = gmu->uncached_iova_base;
-
- for (i = 0; i < count; i++) {
- ret = iommu_map(gmu->domain,
- bo->iova + (PAGE_SIZE * i),
- page_to_phys(bo->pages[i]), PAGE_SIZE,
- IOMMU_READ | IOMMU_WRITE);
-
- if (ret) {
- DRM_DEV_ERROR(gmu->dev, "Unable to map GMU buffer object\n");
-
- for (i = i - 1 ; i >= 0; i--)
- iommu_unmap(gmu->domain,
- bo->iova + (PAGE_SIZE * i),
- PAGE_SIZE);
-
- goto err;
- }
- }
-
- bo->virt = vmap(bo->pages, count, VM_IOREMAP,
- pgprot_writecombine(PAGE_KERNEL));
- if (!bo->virt)
- goto err;
-
- /* Align future IOVA addresses on 1MB boundaries */
- gmu->uncached_iova_base += ALIGN(size, SZ_1M);
-
return bo;
-
-err:
- for (i = 0; i < count; i++) {
- if (bo->pages[i])
- __free_pages(bo->pages[i], 0);
- }
-
- kfree(bo->pages);
- kfree(bo);
-
- return ERR_PTR(-ENOMEM);
-}
-
-static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu)
-{
- int ret;
-
- /*
- * The GMU address space is hardcoded to treat the range
- * 0x60000000 - 0x80000000 as un-cached memory. All buffers shared
- * between the GMU and the CPU will live in this space
- */
- gmu->uncached_iova_base = 0x60000000;
-
-
- gmu->domain = iommu_domain_alloc(&platform_bus_type);
- if (!gmu->domain)
- return -ENODEV;
-
- ret = iommu_attach_device(gmu->domain, gmu->dev);
-
- if (ret) {
- iommu_domain_free(gmu->domain);
- gmu->domain = NULL;
- }
-
- return ret;
}

/* Return the 'arc-level' for the given frequency */
@@ -1289,10 +1206,6 @@ void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu)

a6xx_gmu_memory_free(gmu, gmu->hfi);

- iommu_detach_device(gmu->domain, gmu->dev);
-
- iommu_domain_free(gmu->domain);
-
free_irq(gmu->gmu_irq, gmu);
free_irq(gmu->hfi_irq, gmu);

@@ -1313,7 +1226,15 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)

gmu->dev = &pdev->dev;

- of_dma_configure(gmu->dev, node, true);
+ /* Pass force_dma false to require the DT to set the dma region */
+ ret = of_dma_configure(gmu->dev, node, false);
+ if (ret)
+ return ret;
+
+ /* Set the mask after the of_dma_configure() */
+ ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(31));
+ if (ret)
+ return ret;

/* Fow now, don't do anything fancy until we get our feet under us */
gmu->idle_level = GMU_IDLE_STATE_ACTIVE;
@@ -1325,11 +1246,6 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
if (ret)
goto err_put_device;

- /* Set up the IOMMU context bank */
- ret = a6xx_gmu_memory_probe(gmu);
- if (ret)
- goto err_put_device;
-
/* Allocate memory for for the HFI queues */
gmu->hfi = a6xx_gmu_memory_alloc(gmu, SZ_16K);
if (IS_ERR(gmu->hfi))
@@ -1375,11 +1291,6 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
err_memory:
a6xx_gmu_memory_free(gmu, gmu->hfi);

- if (gmu->domain) {
- iommu_detach_device(gmu->domain, gmu->dev);
-
- iommu_domain_free(gmu->domain);
- }
ret = -ENODEV;

err_put_device:
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
index 2af91ed7ed0c..4af65a36d5ca 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
@@ -12,8 +12,7 @@
struct a6xx_gmu_bo {
void *virt;
size_t size;
- u64 iova;
- struct page **pages;
+ dma_addr_t iova;
};

/*
@@ -49,9 +48,6 @@ struct a6xx_gmu {
int hfi_irq;
int gmu_irq;

- struct iommu_domain *domain;
- u64 uncached_iova_base;
-
struct device *gxpd;

int idle_level;
--
2.17.1