summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/gt/intel_ggtt.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/i915/gt/intel_ggtt.c')
-rw-r--r--drivers/gpu/drm/i915/gt/intel_ggtt.c102
1 files changed, 80 insertions, 22 deletions
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index 700588bc9d57..670c1271e7d5 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -10,6 +10,8 @@
#include <drm/i915_drm.h>
+#include "gem/i915_gem_lmem.h"
+
#include "intel_gt.h"
#include "i915_drv.h"
#include "i915_scatterlist.h"
@@ -92,7 +94,7 @@ int i915_ggtt_init_hw(struct drm_i915_private *i915)
}
/*
- * Certain Gen5 chipsets require require idling the GPU before
+ * Certain Gen5 chipsets require idling the GPU before
* unmapping anything from the GTT when VT-d is enabled.
*/
static bool needs_idle_maps(struct drm_i915_private *i915)
@@ -189,7 +191,12 @@ static u64 gen8_ggtt_pte_encode(dma_addr_t addr,
enum i915_cache_level level,
u32 flags)
{
- return addr | _PAGE_PRESENT;
+ gen8_pte_t pte = addr | _PAGE_PRESENT;
+
+ if (flags & PTE_LM)
+ pte |= GEN12_GGTT_PTE_LM;
+
+ return pte;
}
static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
@@ -201,13 +208,13 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm,
dma_addr_t addr,
u64 offset,
enum i915_cache_level level,
- u32 unused)
+ u32 flags)
{
struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
gen8_pte_t __iomem *pte =
(gen8_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
- gen8_set_pte(pte, gen8_ggtt_pte_encode(addr, level, 0));
+ gen8_set_pte(pte, gen8_ggtt_pte_encode(addr, level, flags));
ggtt->invalidate(ggtt);
}
@@ -217,7 +224,7 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
enum i915_cache_level level,
u32 flags)
{
- const gen8_pte_t pte_encode = gen8_ggtt_pte_encode(0, level, 0);
+ const gen8_pte_t pte_encode = gen8_ggtt_pte_encode(0, level, flags);
struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
gen8_pte_t __iomem *gte;
gen8_pte_t __iomem *end;
@@ -459,6 +466,8 @@ static void ggtt_bind_vma(struct i915_address_space *vm,
pte_flags = 0;
if (i915_gem_object_is_readonly(obj))
pte_flags |= PTE_READ_ONLY;
+ if (i915_gem_object_is_lmem(obj))
+ pte_flags |= PTE_LM;
vm->insert_entries(vm, vma, cache_level, pte_flags);
vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
@@ -647,7 +656,9 @@ static int init_aliasing_ppgtt(struct i915_ggtt *ggtt)
if (err)
goto err_ppgtt;
+ i915_gem_object_lock(ppgtt->vm.scratch[0], NULL);
err = i915_vm_pin_pt_stash(&ppgtt->vm, &stash);
+ i915_gem_object_unlock(ppgtt->vm.scratch[0]);
if (err)
goto err_stash;
@@ -734,6 +745,7 @@ static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)
mutex_unlock(&ggtt->vm.mutex);
i915_address_space_fini(&ggtt->vm);
+ dma_resv_fini(&ggtt->vm.resv);
arch_phys_wc_del(ggtt->mtrr);
@@ -792,8 +804,9 @@ static unsigned int chv_get_total_gtt_size(u16 gmch_ctrl)
static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
{
struct drm_i915_private *i915 = ggtt->vm.i915;
- struct pci_dev *pdev = i915->drm.pdev;
+ struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
phys_addr_t phys_addr;
+ u32 pte_flags;
int ret;
/* For Modern GENs the PTEs and register space are split in the BAR */
@@ -823,9 +836,13 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
return ret;
}
+ pte_flags = 0;
+ if (i915_gem_object_is_lmem(ggtt->vm.scratch[0]))
+ pte_flags |= PTE_LM;
+
ggtt->vm.scratch[0]->encode =
ggtt->vm.pte_encode(px_dma(ggtt->vm.scratch[0]),
- I915_CACHE_NONE, 0);
+ I915_CACHE_NONE, pte_flags);
return 0;
}
@@ -862,7 +879,7 @@ static struct resource pci_resource(struct pci_dev *pdev, int bar)
static int gen8_gmch_probe(struct i915_ggtt *ggtt)
{
struct drm_i915_private *i915 = ggtt->vm.i915;
- struct pci_dev *pdev = i915->drm.pdev;
+ struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
unsigned int size;
u16 snb_gmch_ctl;
@@ -1006,7 +1023,7 @@ static u64 iris_pte_encode(dma_addr_t addr,
static int gen6_gmch_probe(struct i915_ggtt *ggtt)
{
struct drm_i915_private *i915 = ggtt->vm.i915;
- struct pci_dev *pdev = i915->drm.pdev;
+ struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
unsigned int size;
u16 snb_gmch_ctl;
@@ -1069,7 +1086,7 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt)
phys_addr_t gmadr_base;
int ret;
- ret = intel_gmch_probe(i915->bridge_dev, i915->drm.pdev, NULL);
+ ret = intel_gmch_probe(i915->bridge_dev, to_pci_dev(i915->drm.dev), NULL);
if (!ret) {
drm_err(&i915->drm, "failed to set up gmch\n");
return -EIO;
@@ -1114,7 +1131,8 @@ static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt)
ggtt->vm.gt = gt;
ggtt->vm.i915 = i915;
- ggtt->vm.dma = &i915->drm.pdev->dev;
+ ggtt->vm.dma = i915->drm.dev;
+ dma_resv_init(&ggtt->vm.resv);
if (INTEL_GEN(i915) <= 5)
ret = i915_gmch_probe(ggtt);
@@ -1122,8 +1140,10 @@ static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt)
ret = gen6_gmch_probe(ggtt);
else
ret = gen8_gmch_probe(ggtt);
- if (ret)
+ if (ret) {
+ dma_resv_fini(&ggtt->vm.resv);
return ret;
+ }
if ((ggtt->vm.total - 1) >> 32) {
drm_err(&i915->drm,
@@ -1247,14 +1267,16 @@ void i915_ggtt_resume(struct i915_ggtt *ggtt)
static struct scatterlist *
rotate_pages(struct drm_i915_gem_object *obj, unsigned int offset,
unsigned int width, unsigned int height,
- unsigned int stride,
+ unsigned int src_stride, unsigned int dst_stride,
struct sg_table *st, struct scatterlist *sg)
{
unsigned int column, row;
unsigned int src_idx;
for (column = 0; column < width; column++) {
- src_idx = stride * (height - 1) + column + offset;
+ unsigned int left;
+
+ src_idx = src_stride * (height - 1) + column + offset;
for (row = 0; row < height; row++) {
st->nents++;
/*
@@ -1267,8 +1289,25 @@ rotate_pages(struct drm_i915_gem_object *obj, unsigned int offset,
i915_gem_object_get_dma_address(obj, src_idx);
sg_dma_len(sg) = I915_GTT_PAGE_SIZE;
sg = sg_next(sg);
- src_idx -= stride;
+ src_idx -= src_stride;
}
+
+ left = (dst_stride - height) * I915_GTT_PAGE_SIZE;
+
+ if (!left)
+ continue;
+
+ st->nents++;
+
+ /*
+ * The DE ignores the PTEs for the padding tiles, the sg entry
+ * here is just a conenience to indicate how many padding PTEs
+ * to insert at this spot.
+ */
+ sg_set_page(sg, NULL, left, 0);
+ sg_dma_address(sg) = 0;
+ sg_dma_len(sg) = left;
+ sg = sg_next(sg);
}
return sg;
@@ -1297,11 +1336,12 @@ intel_rotate_pages(struct intel_rotation_info *rot_info,
st->nents = 0;
sg = st->sgl;
- for (i = 0 ; i < ARRAY_SIZE(rot_info->plane); i++) {
+ for (i = 0 ; i < ARRAY_SIZE(rot_info->plane); i++)
sg = rotate_pages(obj, rot_info->plane[i].offset,
rot_info->plane[i].width, rot_info->plane[i].height,
- rot_info->plane[i].stride, st, sg);
- }
+ rot_info->plane[i].src_stride,
+ rot_info->plane[i].dst_stride,
+ st, sg);
return st;
@@ -1319,7 +1359,7 @@ err_st_alloc:
static struct scatterlist *
remap_pages(struct drm_i915_gem_object *obj, unsigned int offset,
unsigned int width, unsigned int height,
- unsigned int stride,
+ unsigned int src_stride, unsigned int dst_stride,
struct sg_table *st, struct scatterlist *sg)
{
unsigned int row;
@@ -1352,7 +1392,24 @@ remap_pages(struct drm_i915_gem_object *obj, unsigned int offset,
left -= length;
}
- offset += stride - width;
+ offset += src_stride - width;
+
+ left = (dst_stride - width) * I915_GTT_PAGE_SIZE;
+
+ if (!left)
+ continue;
+
+ st->nents++;
+
+ /*
+ * The DE ignores the PTEs for the padding tiles, the sg entry
+ * here is just a conenience to indicate how many padding PTEs
+ * to insert at this spot.
+ */
+ sg_set_page(sg, NULL, left, 0);
+ sg_dma_address(sg) = 0;
+ sg_dma_len(sg) = left;
+ sg = sg_next(sg);
}
return sg;
@@ -1384,7 +1441,8 @@ intel_remap_pages(struct intel_remapped_info *rem_info,
for (i = 0 ; i < ARRAY_SIZE(rem_info->plane); i++) {
sg = remap_pages(obj, rem_info->plane[i].offset,
rem_info->plane[i].width, rem_info->plane[i].height,
- rem_info->plane[i].stride, st, sg);
+ rem_info->plane[i].src_stride, rem_info->plane[i].dst_stride,
+ st, sg);
}
i915_sg_trim(st);
@@ -1420,7 +1478,7 @@ intel_partial_pages(const struct i915_ggtt_view *view,
if (ret)
goto err_sg_alloc;
- iter = i915_gem_object_get_sg_dma(obj, view->partial.offset, &offset);
+ iter = i915_gem_object_get_sg_dma(obj, view->partial.offset, &offset, true);
GEM_BUG_ON(!iter);
sg = st->sgl;
generated by cgit v1.2.3 (git 2.39.0) at 2025-10-31 17:16:59 +0300