drm/i915/gen8: begin bitmap tracking

Like with gen6/7, we can enable bitmap tracking with all the
preallocations to make sure things actually don't blow up.

v2: Rebased to match changes from previous patches.
v3: Without teardown logic, rely on used_pdpes and used_pdes when
freeing page tables.
v4: Rebased after s/page_tables/page_table/.
v5: Rebased after page table generalizations.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Michel Thierry <michel.thierry@intel.com> (v2+)
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 1e1b42f8da42be39e32e783df71fba875422465c..1be0a8ee8dd7fa1914504bab9b0bbff1a15e2cae 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -437,6 +437,7 @@ static void unmap_and_free_pd(struct i915_page_directory *pd,
        if (pd->page) {
                i915_dma_unmap_single(pd, dev);
                __free_page(pd->page);
+               kfree(pd->used_pdes);
                kfree(pd);
        }
 }
@@ -444,26 +445,35 @@ static void unmap_and_free_pd(struct i915_page_directory *pd,
 static struct i915_page_directory *alloc_pd_single(struct drm_device *dev)
 {
        struct i915_page_directory *pd;
-       int ret;
+       int ret = -ENOMEM;
 
        pd = kzalloc(sizeof(*pd), GFP_KERNEL);
        if (!pd)
                return ERR_PTR(-ENOMEM);
 
+       pd->used_pdes = kcalloc(BITS_TO_LONGS(I915_PDES),
+                               sizeof(*pd->used_pdes), GFP_KERNEL);
+       if (!pd->used_pdes)
+               goto free_pd;
+
        pd->page = alloc_page(GFP_KERNEL);
-       if (!pd->page) {
-               kfree(pd);
-               return ERR_PTR(-ENOMEM);
-       }
+       if (!pd->page)
+               goto free_bitmap;
 
        ret = i915_dma_map_single(pd, dev);
-       if (ret) {
-               __free_page(pd->page);
-               kfree(pd);
-               return ERR_PTR(ret);
-       }
+       if (ret)
+               goto free_page;
 
        return pd;
+
+free_page:
+       __free_page(pd->page);
+free_bitmap:
+       kfree(pd->used_pdes);
+free_pd:
+       kfree(pd);
+
+       return ERR_PTR(ret);
 }
 
 /* Broadwell Page Directory Pointer Descriptors */
@@ -675,7 +685,7 @@ static void gen8_free_page_tables(struct i915_page_directory *pd, struct drm_dev
        if (!pd->page)
                return;
 
-       for (i = 0; i < I915_PDES; i++) {
+       for_each_set_bit(i, pd->used_pdes, I915_PDES) {
                if (WARN_ON(!pd->page_table[i]))
                        continue;
 
@@ -688,7 +698,7 @@ static void gen8_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
 {
        int i;
 
-       for (i = 0; i < GEN8_LEGACY_PDPES; i++) {
+       for_each_set_bit(i, ppgtt->pdp.used_pdpes, GEN8_LEGACY_PDPES) {
                if (WARN_ON(!ppgtt->pdp.page_directory[i]))
                        continue;
 
@@ -752,6 +762,7 @@ static int gen8_ppgtt_alloc_page_directories(struct i915_hw_ppgtt *ppgtt,
        gen8_for_each_pdpe(unused, pdp, start, length, temp, pdpe) {
                WARN_ON(unused);
                pdp->page_directory[pdpe] = alloc_pd_single(dev);
+
                if (IS_ERR(pdp->page_directory[pdpe]))
                        goto unwind_out;
 
@@ -775,10 +786,13 @@ static int gen8_alloc_va_range(struct i915_address_space *vm,
        struct i915_hw_ppgtt *ppgtt =
                container_of(vm, struct i915_hw_ppgtt, base);
        struct i915_page_directory *pd;
+       const uint64_t orig_start = start;
+       const uint64_t orig_length = length;
        uint64_t temp;
        uint32_t pdpe;
        int ret;
 
+       /* Do the allocations first so we can easily bail out */
        ret = gen8_ppgtt_alloc_page_directories(ppgtt, &ppgtt->pdp, start, length);
        if (ret)
                return ret;
@@ -789,6 +803,27 @@ static int gen8_alloc_va_range(struct i915_address_space *vm,
                        goto err_out;
        }
 
+       /* Now mark everything we've touched as used. This doesn't allow for
+        * robust error checking, but it makes the code a hell of a lot simpler.
+        */
+       start = orig_start;
+       length = orig_length;
+
+       gen8_for_each_pdpe(pd, &ppgtt->pdp, start, length, temp, pdpe) {
+               struct i915_page_table *pt;
+               uint64_t pd_len = gen8_clamp_pd(start, length);
+               uint64_t pd_start = start;
+               uint32_t pde;
+
+               gen8_for_each_pde(pt, &ppgtt->pd, pd_start, pd_len, temp, pde) {
+                       bitmap_set(pd->page_table[pde]->used_ptes,
+                                  gen8_pte_index(start),
+                                  gen8_pte_count(start, length));
+                       set_bit(pde, pd->used_pdes);
+               }
+               set_bit(pdpe, ppgtt->pdp.used_pdpes);
+       }
+
        return 0;
 
 err_out:

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index c3d5d40b78b260fb5392b7f6b9f5b7353afac278..29de64d1164efb12bc9d347d1727c6080671357b 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -220,11 +220,13 @@ struct i915_page_directory {
                dma_addr_t daddr;
        };
 
+       unsigned long *used_pdes;
        struct i915_page_table *page_table[I915_PDES]; /* PDEs */
 };
 
 struct i915_page_directory_pointer {
        /* struct page *page; */
+       DECLARE_BITMAP(used_pdpes, GEN8_LEGACY_PDPES);
        struct i915_page_directory *page_directory[GEN8_LEGACY_PDPES];
 };
 
@@ -453,6 +455,11 @@ static inline uint32_t gen8_pml4e_index(uint64_t address)
        return 0;
 }
 
+static inline size_t gen8_pte_count(uint64_t address, uint64_t length)
+{
+       return i915_pte_count(address, length, GEN8_PDE_SHIFT);
+}
+
 int i915_gem_gtt_init(struct drm_device *dev);
 void i915_gem_init_global_gtt(struct drm_device *dev);
 void i915_global_gtt_cleanup(struct drm_device *dev);