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 11/20] drm/i915: support 1G pages for the 48b PPGTT
Date: Tue, 27 Jun 2017 15:54:35 +0100	[thread overview]
Message-ID: <20170627145444.20491-12-matthew.auld@intel.com> (raw)
In-Reply-To: <20170627145444.20491-1-matthew.auld@intel.com>

Support inserting 1G gtt pages into the 48b PPGTT.

v2: sanity check sg->length against page_size

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 73 +++++++++++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/i915_gem_gtt.h |  2 +
 2 files changed, 71 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index ae362abd4729..861b1442b6c4 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -945,6 +945,66 @@ static void gen8_ppgtt_insert_3lvl(struct i915_address_space *vm,
 				      cache_level);
 }
 
+static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma,
+					   struct i915_page_directory_pointer **pdps,
+					   struct sgt_dma *iter,
+					   enum i915_cache_level cache_level)
+{
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level);
+	u64 start = vma->node.start;
+
+	do {
+		struct gen8_insert_pte idx = gen8_insert_pte(start);
+		struct i915_page_directory_pointer *pdp = pdps[idx.pml4e];
+		struct i915_page_directory *pd = pdp->page_directory[idx.pdpe];
+		struct i915_page_table *pt = pd->page_table[idx.pde];
+		dma_addr_t rem = iter->max - iter->dma;
+		unsigned int page_size;
+		gen8_pte_t encode = pte_encode;
+		gen8_pte_t *vaddr;
+		u16 index, max;
+
+		if (unlikely(vma->page_sizes.sg & I915_GTT_PAGE_SIZE_1G) &&
+		    IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_1G) &&
+		    rem >= I915_GTT_PAGE_SIZE_1G && !(idx.pte | idx.pde)) {
+			vaddr = kmap_atomic_px(pdp);
+			index = idx.pdpe;
+			max = GEN8_PML4ES_PER_PML4;
+			page_size = I915_GTT_PAGE_SIZE_1G;
+			encode |= GEN8_PDPE_PS_1G;
+		} else {
+			vaddr = kmap_atomic_px(pt);
+			index = idx.pte;
+			max = GEN8_PTES;
+			page_size = I915_GTT_PAGE_SIZE;
+		}
+
+		do {
+			GEM_BUG_ON(iter->sg->length < page_size);
+			vaddr[index++] = encode | iter->dma;
+
+			start += page_size;
+			iter->dma += page_size;
+			if (iter->dma >= iter->max) {
+				iter->sg = __sg_next(iter->sg);
+				if (!iter->sg)
+					break;
+
+				iter->dma = sg_dma_address(iter->sg);
+				iter->max = iter->dma + iter->sg->length;
+
+				if (unlikely(!IS_ALIGNED(iter->dma, page_size)))
+					break;
+			}
+			rem = iter->max - iter->dma;
+
+		} while (rem >= page_size && index < max);
+
+		kunmap_atomic(vaddr);
+
+	} while (iter->sg);
+}
+
 static void gen8_ppgtt_insert_4lvl(struct i915_address_space *vm,
 				   struct i915_vma *vma,
 				   enum i915_cache_level cache_level,
@@ -957,11 +1017,16 @@ static void gen8_ppgtt_insert_4lvl(struct i915_address_space *vm,
 		.max = iter.dma + iter.sg->length,
 	};
 	struct i915_page_directory_pointer **pdps = ppgtt->pml4.pdps;
-	struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start);
 
-	while (gen8_ppgtt_insert_pte_entries(ppgtt, pdps[idx.pml4e++], &iter,
-					     &idx, cache_level))
-		GEM_BUG_ON(idx.pml4e >= GEN8_PML4ES_PER_PML4);
+	if (vma->page_sizes.sg > I915_GTT_PAGE_SIZE) {
+		gen8_ppgtt_insert_huge_entries(vma, pdps, &iter, cache_level);
+	} else {
+		struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start);
+
+		while (gen8_ppgtt_insert_pte_entries(ppgtt, pdps[idx.pml4e++],
+						     &iter, &idx, cache_level))
+			GEM_BUG_ON(idx.pml4e >= GEN8_PML4ES_PER_PML4);
+	}
 }
 
 static void gen8_free_page_tables(struct i915_address_space *vm,
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 57738a61ea6e..e46f05f0cfd9 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_PDPE_PS_1G  BIT(7)
+
 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:[~2017-06-27 14:55 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-06-27 14:54 [PATCH 00/20] huge gtt pages Matthew Auld
2017-06-27 14:54 ` [PATCH 01/20] mm/shmem: introduce shmem_file_setup_with_mnt Matthew Auld
2017-06-27 14:54   ` Matthew Auld
2017-06-27 14:54 ` [PATCH 02/20] drm/i915: introduce simple gemfs Matthew Auld
2017-06-27 14:54   ` Matthew Auld
2017-06-27 14:54 ` [PATCH 03/20] drm/i915/gemfs: enable THP Matthew Auld
2017-06-27 14:54 ` [PATCH 04/20] drm/i915: introduce page_size_mask to dev_info Matthew Auld
2017-06-27 14:54 ` [PATCH 05/20] drm/i915: introduce page_size members Matthew Auld
2017-06-29  6:36   ` Zhenyu Wang
2017-06-29 11:54     ` Matthew Auld
2017-06-29 11:59       ` Chris Wilson
2017-06-29 15:33         ` Zhenyu Wang
2017-06-27 14:54 ` [PATCH 06/20] drm/i915: introduce vm set_pages/clear_pages Matthew Auld
2017-06-27 14:54 ` [PATCH 07/20] drm/i915: align the vma start to the largest gtt page size Matthew Auld
2017-06-27 14:54 ` [PATCH 08/20] drm/i915: align 64K objects to 2M Matthew Auld
2017-06-27 14:54 ` [PATCH 09/20] drm/i915: enable IPS bit for 64K pages Matthew Auld
2017-06-27 14:54 ` [PATCH 10/20] drm/i915: disable GTT cache for 2M/1G pages Matthew Auld
2017-06-27 14:54 ` Matthew Auld [this message]
2017-06-27 14:54 ` [PATCH 12/20] drm/i915: support 2M pages for the 48b PPGTT Matthew Auld
2017-06-27 14:54 ` [PATCH 13/20] drm/i915: support 64K " Matthew Auld
2017-06-27 14:54 ` [PATCH 14/20] drm/i915: accurate page size tracking for the ppgtt Matthew Auld
2017-06-27 14:54 ` [PATCH 15/20] drm/i915/debugfs: include some gtt page size metrics Matthew Auld
2017-06-27 14:54 ` [PATCH 16/20] drm/i915/selftests: huge page tests Matthew Auld
2017-06-27 14:54 ` [PATCH 17/20] drm/i915/selftests: mix huge pages Matthew Auld
2017-06-27 14:54 ` [PATCH 18/20] drm/i915: enable platform support for 64K pages Matthew Auld
2017-06-27 14:54 ` [PATCH 19/20] drm/i915: enable platform support for 2M pages Matthew Auld
2017-06-27 14:54 ` [PATCH 20/20] drm/i915: enable platform support for 1G pages Matthew Auld
2017-06-27 15:14 ` ✓ Fi.CI.BAT: success for huge gtt pages (rev3) Patchwork
2017-06-27 17:19 ` [PATCH 00/20] huge gtt pages Chris Wilson

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=20170627145444.20491-12-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.