[PATCH v3 5/8] drm/i915/gtt: allow overriding the pt alignment

[Matthew Auld <matthew.auld@xxxxxxxxx>]

On some platforms we have alignment restrictions when accessing LMEM
from the GTT. In the next patch few patches we need to be able to modify
the page-tables directly via the GTT itself.

Suggested-by: Ramalingam C <ramalingam.c@xxxxxxxxx>
Signed-off-by: Matthew Auld <matthew.auld@xxxxxxxxx>
Cc: Thomas Hellström <thomas.hellstrom@xxxxxxxxxxxxxxx>
Cc: Ramalingam C <ramalingam.c@xxxxxxxxx>
---
 drivers/gpu/drm/i915/gt/intel_gtt.h   | 10 +++++++++-
 drivers/gpu/drm/i915/gt/intel_ppgtt.c | 16 ++++++++++++----
 2 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index cbc0b5266cb4..a00d278d8175 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -196,6 +196,14 @@ void *__px_vaddr(struct drm_i915_gem_object *p);
 struct i915_vm_pt_stash {
 	/* preallocated chains of page tables/directories */
 	struct i915_page_table *pt[2];
+	/*
+	 * Optionally override the alignment/size of the physical page that
+	 * contains each PT. If not set defaults back to the usual
+	 * I915_GTT_PAGE_SIZE_4K. This does not influence the other paging
+	 * structures. MUST be a power-of-two. ONLY applicable on discrete
+	 * platforms.
+	 */
+	int pt_sz;
 };
 
 struct i915_vma_ops {
@@ -583,7 +591,7 @@ void free_scratch(struct i915_address_space *vm);
 
 struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz);
 struct drm_i915_gem_object *alloc_pt_lmem(struct i915_address_space *vm, int sz);
-struct i915_page_table *alloc_pt(struct i915_address_space *vm);
+struct i915_page_table *alloc_pt(struct i915_address_space *vm, int sz);
 struct i915_page_directory *alloc_pd(struct i915_address_space *vm);
 struct i915_page_directory *__alloc_pd(int npde);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
index b8238f5bc8b1..3c90aea25072 100644
--- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
@@ -12,7 +12,7 @@
 #include "gen6_ppgtt.h"
 #include "gen8_ppgtt.h"
 
-struct i915_page_table *alloc_pt(struct i915_address_space *vm)
+struct i915_page_table *alloc_pt(struct i915_address_space *vm, int sz)
 {
 	struct i915_page_table *pt;
 
@@ -20,7 +20,7 @@ struct i915_page_table *alloc_pt(struct i915_address_space *vm)
 	if (unlikely(!pt))
 		return ERR_PTR(-ENOMEM);
 
-	pt->base = vm->alloc_pt_dma(vm, I915_GTT_PAGE_SIZE_4K);
+	pt->base = vm->alloc_pt_dma(vm, sz);
 	if (IS_ERR(pt->base)) {
 		kfree(pt);
 		return ERR_PTR(-ENOMEM);
@@ -219,17 +219,25 @@ int i915_vm_alloc_pt_stash(struct i915_address_space *vm,
 			   u64 size)
 {
 	unsigned long count;
-	int shift, n;
+	int shift, n, pt_sz;
 
 	shift = vm->pd_shift;
 	if (!shift)
 		return 0;
 
+	pt_sz = stash->pt_sz;
+	if (!pt_sz)
+		pt_sz = I915_GTT_PAGE_SIZE_4K;
+	else
+		GEM_BUG_ON(!IS_DGFX(vm->i915));
+
+	GEM_BUG_ON(!is_power_of_2(pt_sz));
+
 	count = pd_count(size, shift);
 	while (count--) {
 		struct i915_page_table *pt;
 
-		pt = alloc_pt(vm);
+		pt = alloc_pt(vm, pt_sz);
 		if (IS_ERR(pt)) {
 			i915_vm_free_pt_stash(vm, stash);
 			return PTR_ERR(pt);
-- 
2.31.1