#include "i915_trace.h"
#include "intel_drv.h"
-typedef uint32_t gen6_gtt_pte_t;
+#define GEN6_PPGTT_PD_ENTRIES 512
+#define I915_PPGTT_PT_ENTRIES (PAGE_SIZE / sizeof(gen6_gtt_pte_t))
/* PPGTT stuff */
#define GEN6_GTT_ADDR_ENCODE(addr) ((addr) | (((addr) >> 28) & 0xff0))
#define GEN6_PTE_CACHE_LLC_MLC (3 << 1)
#define GEN6_PTE_ADDR_ENCODE(addr) GEN6_GTT_ADDR_ENCODE(addr)
-static inline gen6_gtt_pte_t gen6_pte_encode(struct drm_device *dev,
- dma_addr_t addr,
- enum i915_cache_level level)
+static gen6_gtt_pte_t gen6_pte_encode(struct drm_device *dev,
+ dma_addr_t addr,
+ enum i915_cache_level level)
{
gen6_gtt_pte_t pte = GEN6_PTE_VALID;
pte |= GEN6_PTE_ADDR_ENCODE(addr);
switch (level) {
case I915_CACHE_LLC_MLC:
- /* Haswell doesn't set L3 this way */
- if (IS_HASWELL(dev))
- pte |= GEN6_PTE_CACHE_LLC;
- else
- pte |= GEN6_PTE_CACHE_LLC_MLC;
+ pte |= GEN6_PTE_CACHE_LLC_MLC;
break;
case I915_CACHE_LLC:
pte |= GEN6_PTE_CACHE_LLC;
break;
case I915_CACHE_NONE:
- if (IS_HASWELL(dev))
- pte |= HSW_PTE_UNCACHED;
- else
- pte |= GEN6_PTE_UNCACHED;
+ pte |= GEN6_PTE_UNCACHED;
break;
default:
BUG();
return pte;
}
-static int gen6_ppgtt_enable(struct drm_device *dev)
+#define BYT_PTE_WRITEABLE (1 << 1)
+#define BYT_PTE_SNOOPED_BY_CPU_CACHES (1 << 2)
+
+static gen6_gtt_pte_t byt_pte_encode(struct drm_device *dev,
+ dma_addr_t addr,
+ enum i915_cache_level level)
{
- drm_i915_private_t *dev_priv = dev->dev_private;
- uint32_t pd_offset;
- struct intel_ring_buffer *ring;
- struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
+ gen6_gtt_pte_t pte = GEN6_PTE_VALID;
+ pte |= GEN6_PTE_ADDR_ENCODE(addr);
+
+ /* Mark the page as writeable. Other platforms don't have a
+ * setting for read-only/writable, so this matches that behavior.
+ */
+ pte |= BYT_PTE_WRITEABLE;
+
+ if (level != I915_CACHE_NONE)
+ pte |= BYT_PTE_SNOOPED_BY_CPU_CACHES;
+
+ return pte;
+}
+
+static gen6_gtt_pte_t hsw_pte_encode(struct drm_device *dev,
+ dma_addr_t addr,
+ enum i915_cache_level level)
+{
+ gen6_gtt_pte_t pte = GEN6_PTE_VALID;
+ pte |= GEN6_PTE_ADDR_ENCODE(addr);
+
+ if (level != I915_CACHE_NONE)
+ pte |= GEN6_PTE_CACHE_LLC;
+
+ return pte;
+}
+
+static void gen6_write_pdes(struct i915_hw_ppgtt *ppgtt)
+{
+ struct drm_i915_private *dev_priv = ppgtt->dev->dev_private;
gen6_gtt_pte_t __iomem *pd_addr;
uint32_t pd_entry;
int i;
+ WARN_ON(ppgtt->pd_offset & 0x3f);
pd_addr = (gen6_gtt_pte_t __iomem*)dev_priv->gtt.gsm +
ppgtt->pd_offset / sizeof(gen6_gtt_pte_t);
for (i = 0; i < ppgtt->num_pd_entries; i++) {
writel(pd_entry, pd_addr + i);
}
readl(pd_addr);
+}
+
+static int gen6_ppgtt_enable(struct drm_device *dev)
+{
+ drm_i915_private_t *dev_priv = dev->dev_private;
+ uint32_t pd_offset;
+ struct intel_ring_buffer *ring;
+ struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
+ int i;
+
+ BUG_ON(ppgtt->pd_offset & 0x3f);
+
+ gen6_write_pdes(ppgtt);
pd_offset = ppgtt->pd_offset;
pd_offset /= 64; /* in cachelines, */
unsigned first_entry,
unsigned num_entries)
{
+ struct drm_i915_private *dev_priv = ppgtt->dev->dev_private;
gen6_gtt_pte_t *pt_vaddr, scratch_pte;
unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
unsigned last_pte, i;
- scratch_pte = gen6_pte_encode(ppgtt->dev,
- ppgtt->scratch_page_dma_addr,
- I915_CACHE_LLC);
+ scratch_pte = ppgtt->pte_encode(ppgtt->dev,
+ dev_priv->gtt.scratch.addr,
+ I915_CACHE_LLC);
while (num_entries) {
last_pte = first_pte + num_entries;
dma_addr_t page_addr;
page_addr = sg_page_iter_dma_address(&sg_iter);
- pt_vaddr[act_pte] = gen6_pte_encode(ppgtt->dev, page_addr,
- cache_level);
+ pt_vaddr[act_pte] = ppgtt->pte_encode(ppgtt->dev, page_addr,
+ cache_level);
if (++act_pte == I915_PPGTT_PT_ENTRIES) {
kunmap_atomic(pt_vaddr);
act_pt++;
/* ppgtt PDEs reside in the global gtt pagetable, which has 512*1024
* entries. For aliasing ppgtt support we just steal them at the end for
* now. */
- first_pd_entry_in_global_pt = gtt_total_entries(dev_priv->gtt);
+ first_pd_entry_in_global_pt = gtt_total_entries(dev_priv->gtt);
- ppgtt->num_pd_entries = I915_PPGTT_PD_ENTRIES;
+ if (IS_HASWELL(dev)) {
+ ppgtt->pte_encode = hsw_pte_encode;
+ } else if (IS_VALLEYVIEW(dev)) {
+ ppgtt->pte_encode = byt_pte_encode;
+ } else {
+ ppgtt->pte_encode = gen6_pte_encode;
+ }
+ ppgtt->num_pd_entries = GEN6_PPGTT_PD_ENTRIES;
ppgtt->enable = gen6_ppgtt_enable;
ppgtt->clear_range = gen6_ppgtt_clear_range;
ppgtt->insert_entries = gen6_ppgtt_insert_entries;
return -ENOMEM;
ppgtt->dev = dev;
- ppgtt->scratch_page_dma_addr = dev_priv->gtt.scratch_page_dma;
if (INTEL_INFO(dev)->gen < 8)
ret = gen6_ppgtt_init(ppgtt);
dev_priv->gtt.gtt_clear_range(dev, dev_priv->gtt.start / PAGE_SIZE,
dev_priv->gtt.total / PAGE_SIZE);
- list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list) {
+ list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
i915_gem_clflush_object(obj);
i915_gem_gtt_bind_object(obj, obj->cache_level);
}
for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) {
addr = sg_page_iter_dma_address(&sg_iter);
- iowrite32(gen6_pte_encode(dev, addr, level), >t_entries[i]);
+ iowrite32(dev_priv->gtt.pte_encode(dev, addr, level),
+ >t_entries[i]);
i++;
}
*/
if (i != 0)
WARN_ON(readl(>t_entries[i-1])
- != gen6_pte_encode(dev, addr, level));
+ != dev_priv->gtt.pte_encode(dev, addr, level));
/* This next bit makes the above posting read even more important. We
* want to flush the TLBs only after we're certain all the PTE updates
first_entry, num_entries, max_entries))
num_entries = max_entries;
- scratch_pte = gen6_pte_encode(dev, dev_priv->gtt.scratch_page_dma,
- I915_CACHE_LLC);
+ scratch_pte = dev_priv->gtt.pte_encode(dev, dev_priv->gtt.scratch.addr,
+ I915_CACHE_LLC);
for (i = 0; i < num_entries; i++)
iowrite32(scratch_pte, >t_base[i]);
readl(gtt_base);
dev_priv->mm.gtt_space.color_adjust = i915_gtt_color_adjust;
/* Mark any preallocated objects as occupied */
- list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list) {
+ list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
DRM_DEBUG_KMS("reserving preallocated space: %x + %zx\n",
obj->gtt_offset, obj->base.size);
if (INTEL_INFO(dev)->gen <= 7) {
/* PPGTT pdes are stolen from global gtt ptes, so shrink the
* aperture accordingly when using aliasing ppgtt. */
- gtt_size -= I915_PPGTT_PD_ENTRIES*PAGE_SIZE;
+ gtt_size -= GEN6_PPGTT_PD_ENTRIES * PAGE_SIZE;
}
i915_gem_setup_global_gtt(dev, 0, mappable_size, gtt_size);
DRM_ERROR("Aliased PPGTT setup failed %d\n", ret);
drm_mm_takedown(&dev_priv->mm.gtt_space);
- gtt_size += I915_PPGTT_PD_ENTRIES*PAGE_SIZE;
+ gtt_size += GEN6_PPGTT_PD_ENTRIES * PAGE_SIZE;
}
i915_gem_setup_global_gtt(dev, 0, mappable_size, gtt_size);
}
#else
dma_addr = page_to_phys(page);
#endif
- dev_priv->gtt.scratch_page = page;
- dev_priv->gtt.scratch_page_dma = dma_addr;
+ dev_priv->gtt.scratch.page = page;
+ dev_priv->gtt.scratch.addr = dma_addr;
return 0;
}
static void teardown_scratch_page(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- set_pages_wb(dev_priv->gtt.scratch_page, 1);
- pci_unmap_page(dev->pdev, dev_priv->gtt.scratch_page_dma,
+ set_pages_wb(dev_priv->gtt.scratch.page, 1);
+ pci_unmap_page(dev->pdev, dev_priv->gtt.scratch.addr,
PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
- put_page(dev_priv->gtt.scratch_page);
- __free_page(dev_priv->gtt.scratch_page);
+ put_page(dev_priv->gtt.scratch.page);
+ __free_page(dev_priv->gtt.scratch.page);
}
static inline unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
} else {
dev_priv->gtt.gtt_probe = gen6_gmch_probe;
dev_priv->gtt.gtt_remove = gen6_gmch_remove;
+ if (IS_HASWELL(dev)) {
+ dev_priv->gtt.pte_encode = hsw_pte_encode;
+ } else if (IS_VALLEYVIEW(dev)) {
+ dev_priv->gtt.pte_encode = byt_pte_encode;
+ } else {
+ dev_priv->gtt.pte_encode = gen6_pte_encode;
+ }
}
ret = dev_priv->gtt.gtt_probe(dev, &dev_priv->gtt.total,