@@ -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>
@@ -895,21 +896,10 @@ 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_attrs(gmu->dev, bo->size, bo->virt, bo->iova, bo->attrs);
kfree(bo);
}
@@ -917,94 +907,23 @@ 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)
return ERR_PTR(-ENOMEM);
bo->size = PAGE_ALIGN(size);
+ bo->attrs = DMA_ATTR_WRITE_COMBINE;
- count = bo->size >> PAGE_SHIFT;
+ bo->virt = dma_alloc_attrs(gmu->dev, bo->size, &bo->iova, GFP_KERNEL,
+ bo->attrs);
- 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 */
@@ -1264,10 +1183,6 @@ 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);
@@ -1300,11 +1215,6 @@ 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))
@@ -1350,11 +1260,6 @@ 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:
@@ -13,7 +13,7 @@ struct a6xx_gmu_bo {
void *virt;
size_t size;
u64 iova;
- struct page **pages;
+ unsigned long attrs;
};
/*
@@ -49,9 +49,6 @@ struct a6xx_gmu {
int hfi_irq;
int gmu_irq;
- struct iommu_domain *domain;
- u64 uncached_iova_base;
-
struct device *gxpd;
int idle_level;
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 secnario. Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org> --- drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 107 ++-------------------------------- drivers/gpu/drm/msm/adreno/a6xx_gmu.h | 5 +- 2 files changed, 7 insertions(+), 105 deletions(-)