On 7/31/2015 5:42 PM, Michel Thierry wrote:
Introduces the Page Map Level 4 (PML4), ie. the new top level structure
of the page tables.
To facilitate testing, 48b mode will be available on Broadwell and
GEN9+, when i915.enable_ppgtt = 3.
v2: Remove unnecessary CONFIG_X86_64 checks, ppgtt code is already
32/64-bit safe (Chris).
v3: Add goto free_scratch in temp 48-bit mode init code (Akash).
v4: kfree the pdp until the 4lvl alloc/free patch (Akash).
v5: Postpone 48-bit code in sanitize_enable_ppgtt (Akash).
Cc: Akash Goel
Signed-off-by: Michel Thierry
---
drivers/gpu/drm/i915/i915_drv.h | 3 ++-
drivers/gpu/drm/i915/i915_gem_gtt.c | 30 +-
drivers/gpu/drm/i915/i915_gem_gtt.h | 26 +-
3 files changed, 40 insertions(+), 19 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 04aa34a..4729eaf 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2498,7 +2498,8 @@ struct drm_i915_cmd_table {
#define HAS_HW_CONTEXTS(dev) (INTEL_INFO(dev)->gen >= 6)
#define HAS_LOGICAL_RING_CONTEXTS(dev)(INTEL_INFO(dev)->gen >= 8)
#define USES_PPGTT(dev) (i915.enable_ppgtt)
-#define USES_FULL_PPGTT(dev) (i915.enable_ppgtt == 2)
+#define USES_FULL_PPGTT(dev) (i915.enable_ppgtt >= 2)
+#define USES_FULL_48BIT_PPGTT(dev) (i915.enable_ppgtt == 3)
#define HAS_OVERLAY(dev) (INTEL_INFO(dev)->has_overlay)
#define OVERLAY_NEEDS_PHYSICAL(dev)
(INTEL_INFO(dev)->overlay_needs_physical)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c
b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 7f71746..ba99b67 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -689,9 +689,6 @@ gen8_ppgtt_insert_pte_entries(struct i915_address_space *vm,
pt_vaddr = NULL;
for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
- if (WARN_ON(pdpe >= GEN8_LEGACY_PDPES))
- break;
-
Apologize for this eleventh hour comment.
Would this change be better off in the later patch "Add 4 level support
in insert_entries and clear_range".
Best regards
Akash
if (pt_vaddr == NULL) {
struct i915_page_directory *pd =
pdp->page_directory[pdpe];
struct i915_page_table *pt = pd->page_table[pde];
@@ -1105,14 +1102,6 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
return ret;
ppgtt->base.start = 0;
- ppgtt->base.total = 1ULL << 32;
- if (IS_ENABLED(CONFIG_X86_32))
- /* While we have a proliferation of size_t variables
-* we cannot represent the full ppgtt size on 32bit,
-* so limit it to the same size as the GGTT (currently
-* 2GiB).
-*/
- ppgtt->base.total = to_i915(ppgtt->base.dev)->gtt.base.total;
ppgtt->base.cleanup = gen8_ppgtt_cleanup;
ppgtt->base.allocate_va_range = gen8_alloc_va_range;
ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
@@ -1122,10 +,25 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
ppgtt->switch_mm = gen8_mm_switch;
- ret = __pdp_init(false, &ppgtt->pdp);
+ if (!USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) {
+ ret = __pdp_init(false, &ppgtt->pdp);
- if (ret)
+ if (ret)
+ goto free_scratch;
+
+ ppgtt->base.total = 1ULL << 32;
+ if (IS_ENABLED(CONFIG_X86_32))
+ /* While we have a proliferation of size_t variables
+* we cannot represent the full ppgtt size on 32bit,
+* so limit it to the same size as the GGTT (currently
+* 2GiB).
+*/
+ ppgtt->base.total =
to_i915(ppgtt->base.dev)->gtt.base.total;
+ } else {
+ ppgtt->base.total = 1ULL << 48;
+ ret = -EPERM; /* Not yet implemented */
goto free_scratch;
+ }
return 0;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h
b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 87e389c..04bc66f 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -88,9 +88,17 @@ typedef uint64_t gen8_pde_t;
* PDPE | PDE | PTE | offset
* The difference as compared to normal x86 3 level page table is the PDPEs
are
* programmed via register.
+ *
+ * GEN8 48b legacy style address is defined as a 4 level page table:
+ * 47:39 | 38:30 | 29:21 | 20:12 | 11:0
+ * PML4E | PDPE | PDE | PTE | offset
*/
+#define GEN8_PML4ES_PER_PML4 512
+#define GEN8_PML4E_SHIFT 39
#define GEN8_PDPE_SHIFT 30
-#define GEN8_PDPE_MASK 0x3
+/* NB: GEN8_PDPE_MASK is untrue for 32b platforms, but it has no impact on 32