instmem for GK20A is allocated using dma_alloc_coherent(), which
provides us with a coherent CPU mapping that we never use because
instmem objects are accessed through PRAMIN. Switch to
dma_alloc_attrs() which gives us the option to dismiss that CPU mapping
and free up some CPU virtual space.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
#include <core/mm.h>
#include <core/device.h>
#include <core/mm.h>
#include <core/device.h>
+#ifdef __KERNEL__
+#include <linux/dma-attrs.h>
+#endif
+
#include "priv.h"
struct gk20a_instobj_priv {
#include "priv.h"
struct gk20a_instobj_priv {
struct nvkm_instmem base;
spinlock_t lock;
u64 addr;
struct nvkm_instmem base;
spinlock_t lock;
u64 addr;
+ struct dma_attrs attrs;
if (unlikely(!node->handle))
return;
if (unlikely(!node->handle))
return;
- dma_free_coherent(dev, node->mem->size << PAGE_SHIFT, node->cpuaddr,
- node->handle);
+ dma_free_attrs(dev, node->mem->size << PAGE_SHIFT, node->cpuaddr,
+ node->handle, &priv->attrs);
nvkm_instobj_destroy(&node->base);
}
nvkm_instobj_destroy(&node->base);
}
- node->cpuaddr = dma_alloc_coherent(dev, npages << PAGE_SHIFT,
- &node->handle, GFP_KERNEL);
+ node->cpuaddr = dma_alloc_attrs(dev, npages << PAGE_SHIFT,
+ &node->handle, GFP_KERNEL,
+ &priv->attrs);
if (!node->cpuaddr) {
nv_error(priv, "cannot allocate DMA memory\n");
return -ENOMEM;
if (!node->cpuaddr) {
nv_error(priv, "cannot allocate DMA memory\n");
return -ENOMEM;
spin_lock_init(&priv->lock);
spin_lock_init(&priv->lock);
+ init_dma_attrs(&priv->attrs);
+ /*
+ * We will access instmem through PRAMIN and thus do not need a
+ * consistent CPU pointer or kernel mapping
+ */
+ dma_set_attr(DMA_ATTR_NON_CONSISTENT, &priv->attrs);
+ dma_set_attr(DMA_ATTR_WEAK_ORDERING, &priv->attrs);
+ dma_set_attr(DMA_ATTR_WRITE_COMBINE, &priv->attrs);
+ dma_set_attr(DMA_ATTR_NO_KERNEL_MAPPING, &priv->attrs);
+