All of lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Auld <matthew.auld@intel.com>
To: intel-gfx@lists.freedesktop.org
Subject: [PATCH 10/17] drm/i915: support inserting 64K pages into the 48b PPGTT
Date: Tue, 16 May 2017 09:29:41 +0100	[thread overview]
Message-ID: <20170516082948.28090-11-matthew.auld@intel.com> (raw)
In-Reply-To: <20170516082948.28090-1-matthew.auld@intel.com>

If we set the IPS bit, aka PDE[11] then every 16th entry should be used
to index, the HW makes no assumptions for any other PTEs.

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 74 +++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_gem_gtt.h |  2 +
 2 files changed, 76 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 3be3cbfb6d28..874854e77247 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -854,6 +854,77 @@ static __always_inline struct gen8_insert_pte gen8_insert_pte(u64 start)
 }
 
 static __always_inline bool
+gen8_ppgtt_insert_64K_pte_entries(struct i915_hw_ppgtt *ppgtt,
+				  struct i915_page_directory_pointer *pdp,
+				  struct sgt_dma *iter,
+				  struct gen8_insert_pte *idx,
+				  enum i915_cache_level cache_level)
+{
+	struct i915_page_directory *pd;
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level);
+	gen8_pte_t *vaddr;
+	bool ret;
+
+	/* Currently 64K objects should be aligned to 2M to prevent mixing 4K
+	 * and 64K pte's in the same page-table.
+	 */
+	GEM_BUG_ON(idx->pte);
+	GEM_BUG_ON(idx->pdpe >= i915_pdpes_per_pdp(&ppgtt->base));
+	pd = pdp->page_directory[idx->pdpe];
+
+	vaddr = kmap_atomic_px(pd);
+	vaddr[idx->pde] |= GEN8_PDE_IPS_64K;
+	kunmap_atomic(vaddr);
+
+	vaddr = kmap_atomic_px(pd->page_table[idx->pde]);
+	do {
+		vaddr[idx->pte] = pte_encode | iter->dma;
+		iter->dma += I915_GTT_PAGE_SIZE_64K;
+		if (iter->dma >= iter->max) {
+			iter->sg = __sg_next(iter->sg);
+			if (!iter->sg) {
+				ret = false;
+				break;
+			}
+
+			iter->dma = sg_dma_address(iter->sg);
+			iter->max = iter->dma + iter->sg->length;
+		}
+
+		idx->pte += 16;
+
+		if (idx->pte == GEN8_PTES) {
+			idx->pte = 0;
+
+			if (++idx->pde == I915_PDES) {
+				idx->pde = 0;
+
+				if (++idx->pdpe == GEN8_PML4ES_PER_PML4) {
+					idx->pdpe = 0;
+					ret = true;
+					break;
+				}
+
+				GEM_BUG_ON(idx->pdpe >= i915_pdpes_per_pdp(&ppgtt->base));
+				pd = pdp->page_directory[idx->pdpe];
+			}
+
+			kunmap_atomic(vaddr);
+			vaddr = kmap_atomic_px(pd);
+			vaddr[idx->pde] |= GEN8_PDE_IPS_64K;
+			kunmap_atomic(vaddr);
+
+			vaddr = kmap_atomic_px(pd->page_table[idx->pde]);
+		}
+	} while (1);
+	kunmap_atomic(vaddr);
+
+	mark_tlbs_dirty(ppgtt);
+
+	return ret;
+}
+
+static __always_inline bool
 gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt,
 			      struct i915_page_directory_pointer *pdp,
 			      struct sgt_dma *iter,
@@ -954,6 +1025,9 @@ static void gen8_ppgtt_insert_4lvl(struct i915_address_space *vm,
 	case I915_GTT_PAGE_SIZE_4K:
 		insert_entries = gen8_ppgtt_insert_pte_entries;
 		break;
+	case I915_GTT_PAGE_SIZE_64K:
+		insert_entries = gen8_ppgtt_insert_64K_pte_entries;
+		break;
 	default:
 		MISSING_CASE(page_size);
 		return;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 5a2a3907d266..04d37c62c3ef 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -149,6 +149,8 @@ typedef u64 gen8_ppgtt_pml4e_t;
 #define GEN8_PPAT_ELLC_OVERRIDE		(0<<2)
 #define GEN8_PPAT(i, x)			((u64)(x) << ((i) * 8))
 
+#define GEN8_PDE_IPS_64K BIT(11)
+
 struct sg_table;
 
 struct intel_rotation_info {
-- 
2.9.4

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2017-05-16  8:30 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-05-16  8:29 [PATCH 00/17] add support for huge-gtt-pages Matthew Auld
2017-05-16  8:29 ` [PATCH 01/17] drm/i915: introduce page_size_mask to dev_info Matthew Auld
2017-05-16  8:29 ` [PATCH 02/17] drm/i915: introduce gtt page size Matthew Auld
2017-05-16  8:41   ` Chris Wilson
2017-05-16  9:59   ` Chris Wilson
2017-05-23 12:42     ` Matthew Auld
2017-05-23 12:54       ` Chris Wilson
2017-05-23 13:57         ` Matthew Auld
2017-05-23 14:30           ` Chris Wilson
2017-05-16  8:29 ` [PATCH 03/17] drm/i915: align the vma start to the " Matthew Auld
2017-05-16  8:40   ` Chris Wilson
2017-05-16  8:29 ` [PATCH 04/17] drm/i915: align 64K objects to 2M Matthew Auld
2017-05-16  8:29 ` [PATCH 05/17] drm/i915: fallback to normal pages on vma insert failure Matthew Auld
2017-05-16  8:39   ` Chris Wilson
2017-05-16  8:29 ` [PATCH 06/17] mm/shmem: expose driver overridable huge option Matthew Auld
2017-05-16 10:02   ` Kirill A. Shutemov
2017-05-16  8:29 ` [PATCH 07/17] drm/i915: request THP for shmem backed objects Matthew Auld
2017-05-16  8:29   ` Matthew Auld
2017-05-16  8:29 ` [PATCH 08/17] drm/i915: pass gtt page size to insert_entries Matthew Auld
2017-05-16  8:29 ` [PATCH 09/17] drm/i915: enable IPS bit for 64K pages Matthew Auld
2017-05-16  8:29 ` Matthew Auld [this message]
2017-05-16  8:29 ` [PATCH 11/17] drm/i915: disable GTT cache for 2M/1G pages Matthew Auld
2017-05-16 10:04   ` Ville Syrjälä
2017-05-16 10:11     ` Chris Wilson
2017-05-16  8:29 ` [PATCH 12/17] drm/i915: support inserting 2M pages into the 48b PPGTT Matthew Auld
2017-05-16  8:29 ` [PATCH 13/17] drm/i915: support inserting 1G " Matthew Auld
2017-05-16  8:29 ` [PATCH 14/17] drm/i915/debugfs: include some gtt_page_size metrics Matthew Auld
2017-05-19 10:48   ` Chris Wilson
2017-05-19 10:51   ` Chris Wilson
2017-05-16  8:29 ` [PATCH 15/17] drm/i915: enable platform support for 64K pages Matthew Auld
2017-05-16  8:29 ` [PATCH 16/17] drm/i915: enable platform support for 2M pages Matthew Auld
2017-05-16  8:29 ` [PATCH 17/17] drm/i915: enable platform support for 1G pages Matthew Auld
2017-05-16  8:49 ` ✓ Fi.CI.BAT: success for add support for huge-gtt-pages Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170516082948.28090-11-matthew.auld@intel.com \
    --to=matthew.auld@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.