All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Michel Dänzer" <michel@daenzer.net>
To: dri-devel@lists.freedesktop.org, mesa-dev@lists.freedesktop.org
Subject: [PATCH 2/5] drm/radeon: Pass GART page flags to radeon_gart_set_page() explicitly
Date: Thu, 17 Jul 2014 19:01:07 +0900	[thread overview]
Message-ID: <1405591275-14461-3-git-send-email-michel@daenzer.net> (raw)
In-Reply-To: <1405591275-14461-1-git-send-email-michel@daenzer.net>

From: Michel Dänzer <michel.daenzer@amd.com>

Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
---
 drivers/gpu/drm/radeon/r100.c        |  2 +-
 drivers/gpu/drm/radeon/r300.c        | 12 +++++++++---
 drivers/gpu/drm/radeon/radeon.h      | 12 +++++++++---
 drivers/gpu/drm/radeon/radeon_asic.h |  8 ++++----
 drivers/gpu/drm/radeon/radeon_gart.c |  9 ++++++---
 drivers/gpu/drm/radeon/radeon_ttm.c  |  8 ++++++--
 drivers/gpu/drm/radeon/rs400.c       | 13 ++++++++++---
 drivers/gpu/drm/radeon/rs600.c       | 16 +++++++++++-----
 include/uapi/drm/radeon_drm.h        |  4 +++-
 9 files changed, 59 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index ed1c53e..9241b89 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -682,7 +682,7 @@ void r100_pci_gart_disable(struct radeon_device *rdev)
 }
 
 void r100_pci_gart_set_page(struct radeon_device *rdev, unsigned i,
-			    uint64_t addr)
+			    uint64_t addr, uint32_t flags)
 {
 	u32 *gtt = rdev->gart.ptr;
 	gtt[i] = cpu_to_le32(lower_32_bits(addr));
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 8d14e66..75b3033 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -69,17 +69,23 @@ void rv370_pcie_gart_tlb_flush(struct radeon_device *rdev)
 	mb();
 }
 
+#define R300_PTE_UNSNOOPED (1 << 0)
 #define R300_PTE_WRITEABLE (1 << 2)
 #define R300_PTE_READABLE  (1 << 3)
 
 void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
-			      uint64_t addr)
+			      uint64_t addr, uint32_t flags)
 {
 	void __iomem *ptr = rdev->gart.ptr;
 
 	addr = (lower_32_bits(addr) >> 8) |
-	       ((upper_32_bits(addr) & 0xff) << 24) |
-	       R300_PTE_WRITEABLE | R300_PTE_READABLE;
+		((upper_32_bits(addr) & 0xff) << 24);
+	if (flags & RADEON_GART_PAGE_READ)
+		addr |= R300_PTE_READABLE;
+	if (flags & RADEON_GART_PAGE_WRITE)
+		addr |= R300_PTE_WRITEABLE;
+	if (!(flags & RADEON_GART_PAGE_SNOOP))
+		addr |= R300_PTE_UNSNOOPED;
 	/* on x86 we want this to be CPU endian, on powerpc
 	 * on powerpc without HW swappers, it'll get swapped on way
 	 * into VRAM - so no need for cpu_to_le32 on VRAM tables */
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index f4869b4..4dd092e 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -589,6 +589,12 @@ struct radeon_mc;
 #define RADEON_GPU_PAGE_SHIFT 12
 #define RADEON_GPU_PAGE_ALIGN(a) (((a) + RADEON_GPU_PAGE_MASK) & ~RADEON_GPU_PAGE_MASK)
 
+#define RADEON_GART_PAGE_DUMMY  0
+#define RADEON_GART_PAGE_VALID	(1 << 0)
+#define RADEON_GART_PAGE_READ	(1 << 1)
+#define RADEON_GART_PAGE_WRITE	(1 << 2)
+#define RADEON_GART_PAGE_SNOOP	(1 << 3)
+
 struct radeon_gart {
 	dma_addr_t			table_addr;
 	struct radeon_bo		*robj;
@@ -613,7 +619,7 @@ void radeon_gart_unbind(struct radeon_device *rdev, unsigned offset,
 			int pages);
 int radeon_gart_bind(struct radeon_device *rdev, unsigned offset,
 		     int pages, struct page **pagelist,
-		     dma_addr_t *dma_addr);
+		     dma_addr_t *dma_addr, uint32_t flags);
 
 
 /*
@@ -1775,7 +1781,7 @@ struct radeon_asic {
 	struct {
 		void (*tlb_flush)(struct radeon_device *rdev);
 		void (*set_page)(struct radeon_device *rdev, unsigned i,
-				 uint64_t addr);
+				 uint64_t addr, uint32_t flags);
 	} gart;
 	struct {
 		int (*init)(struct radeon_device *rdev);
@@ -2702,7 +2708,7 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
 #define radeon_vga_set_state(rdev, state) (rdev)->asic->vga_set_state((rdev), (state))
 #define radeon_asic_reset(rdev) (rdev)->asic->asic_reset((rdev))
 #define radeon_gart_tlb_flush(rdev) (rdev)->asic->gart.tlb_flush((rdev))
-#define radeon_gart_set_page(rdev, i, p) (rdev)->asic->gart.set_page((rdev), (i), (p))
+#define radeon_gart_set_page(rdev, i, p, f) (rdev)->asic->gart.set_page((rdev), (i), (p), (f))
 #define radeon_asic_vm_init(rdev) (rdev)->asic->vm.init((rdev))
 #define radeon_asic_vm_fini(rdev) (rdev)->asic->vm.fini((rdev))
 #define radeon_asic_vm_set_page(rdev, ib, pe, addr, count, incr, flags) ((rdev)->asic->vm.set_page((rdev), (ib), (pe), (addr), (count), (incr), (flags)))
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 01e7c0a..f632e31 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -68,7 +68,7 @@ int r100_asic_reset(struct radeon_device *rdev);
 u32 r100_get_vblank_counter(struct radeon_device *rdev, int crtc);
 void r100_pci_gart_tlb_flush(struct radeon_device *rdev);
 void r100_pci_gart_set_page(struct radeon_device *rdev, unsigned i,
-			    uint64_t addr);
+			    uint64_t addr, uint32_t flags);
 void r100_ring_start(struct radeon_device *rdev, struct radeon_ring *ring);
 int r100_irq_set(struct radeon_device *rdev);
 int r100_irq_process(struct radeon_device *rdev);
@@ -173,7 +173,7 @@ extern void r300_fence_ring_emit(struct radeon_device *rdev,
 extern int r300_cs_parse(struct radeon_cs_parser *p);
 extern void rv370_pcie_gart_tlb_flush(struct radeon_device *rdev);
 extern void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
-				     uint64_t addr);
+				     uint64_t addr, uint32_t flags);
 extern void rv370_set_pcie_lanes(struct radeon_device *rdev, int lanes);
 extern int rv370_get_pcie_lanes(struct radeon_device *rdev);
 extern void r300_set_reg_safe(struct radeon_device *rdev);
@@ -209,7 +209,7 @@ extern int rs400_suspend(struct radeon_device *rdev);
 extern int rs400_resume(struct radeon_device *rdev);
 void rs400_gart_tlb_flush(struct radeon_device *rdev);
 void rs400_gart_set_page(struct radeon_device *rdev, unsigned i,
-			 uint64_t addr);
+			 uint64_t addr, uint32_t flags);
 uint32_t rs400_mc_rreg(struct radeon_device *rdev, uint32_t reg);
 void rs400_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 int rs400_gart_init(struct radeon_device *rdev);
@@ -233,7 +233,7 @@ void rs600_irq_disable(struct radeon_device *rdev);
 u32 rs600_get_vblank_counter(struct radeon_device *rdev, int crtc);
 void rs600_gart_tlb_flush(struct radeon_device *rdev);
 void rs600_gart_set_page(struct radeon_device *rdev, unsigned i,
-			 uint64_t addr);
+			 uint64_t addr, uint32_t flags);
 uint32_t rs600_mc_rreg(struct radeon_device *rdev, uint32_t reg);
 void rs600_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 void rs600_bandwidth_update(struct radeon_device *rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index b7d3e84..d684642 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -243,7 +243,8 @@ void radeon_gart_unbind(struct radeon_device *rdev, unsigned offset,
 			page_base = rdev->gart.pages_addr[p];
 			for (j = 0; j < (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); j++, t++) {
 				if (rdev->gart.ptr) {
-					radeon_gart_set_page(rdev, t, page_base);
+					radeon_gart_set_page(rdev, t, page_base,
+							     RADEON_GART_PAGE_DUMMY);
 				}
 				page_base += RADEON_GPU_PAGE_SIZE;
 			}
@@ -261,13 +262,15 @@ void radeon_gart_unbind(struct radeon_device *rdev, unsigned offset,
  * @pages: number of pages to bind
  * @pagelist: pages to bind
  * @dma_addr: DMA addresses of pages
+ * @flags: RADEON_GART_PAGE_* flags
  *
  * Binds the requested pages to the gart page table
  * (all asics).
  * Returns 0 for success, -EINVAL for failure.
  */
 int radeon_gart_bind(struct radeon_device *rdev, unsigned offset,
-		     int pages, struct page **pagelist, dma_addr_t *dma_addr)
+		     int pages, struct page **pagelist, dma_addr_t *dma_addr,
+		     uint32_t flags)
 {
 	unsigned t;
 	unsigned p;
@@ -287,7 +290,7 @@ int radeon_gart_bind(struct radeon_device *rdev, unsigned offset,
 		if (rdev->gart.ptr) {
 			page_base = rdev->gart.pages_addr[p];
 			for (j = 0; j < (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); j++, t++) {
-				radeon_gart_set_page(rdev, t, page_base);
+				radeon_gart_set_page(rdev, t, page_base, flags);
 				page_base += RADEON_GPU_PAGE_SIZE;
 			}
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index c8a8a51..7fb7c1c 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -521,6 +521,8 @@ static int radeon_ttm_backend_bind(struct ttm_tt *ttm,
 				   struct ttm_mem_reg *bo_mem)
 {
 	struct radeon_ttm_tt *gtt = (void*)ttm;
+	uint32_t flags = RADEON_GART_PAGE_VALID | RADEON_GART_PAGE_READ |
+		RADEON_GART_PAGE_WRITE;
 	int r;
 
 	gtt->offset = (unsigned long)(bo_mem->start << PAGE_SHIFT);
@@ -528,8 +530,10 @@ static int radeon_ttm_backend_bind(struct ttm_tt *ttm,
 		WARN(1, "nothing to bind %lu pages for mreg %p back %p!\n",
 		     ttm->num_pages, bo_mem, ttm);
 	}
-	r = radeon_gart_bind(gtt->rdev, gtt->offset,
-			     ttm->num_pages, ttm->pages, gtt->ttm.dma_address);
+	if (ttm->caching_state == tt_cached)
+		flags |= RADEON_GART_PAGE_SNOOP;
+	r = radeon_gart_bind(gtt->rdev, gtt->offset, ttm->num_pages,
+			     ttm->pages, gtt->ttm.dma_address, flags);
 	if (r) {
 		DRM_ERROR("failed to bind %lu pages at 0x%08X\n",
 			  ttm->num_pages, (unsigned)gtt->offset);
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index 4519f9c..6c1fc33 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -208,17 +208,24 @@ void rs400_gart_fini(struct radeon_device *rdev)
 	radeon_gart_table_ram_free(rdev);
 }
 
+#define RS400_PTE_UNSNOOPED (1 << 0)
 #define RS400_PTE_WRITEABLE (1 << 2)
 #define RS400_PTE_READABLE  (1 << 3)
 
-void rs400_gart_set_page(struct radeon_device *rdev, unsigned i, uint64_t addr)
+void rs400_gart_set_page(struct radeon_device *rdev, unsigned i,
+			 uint64_t addr, uint32_t flags)
 {
 	uint32_t entry;
 	u32 *gtt = rdev->gart.ptr;
 
 	entry = (lower_32_bits(addr) & PAGE_MASK) |
-		((upper_32_bits(addr) & 0xff) << 4) |
-		RS400_PTE_WRITEABLE | RS400_PTE_READABLE;
+		((upper_32_bits(addr) & 0xff) << 4);
+	if (flags & RADEON_GART_PAGE_READ)
+		addr |= RS400_PTE_READABLE;
+	if (flags & RADEON_GART_PAGE_WRITE)
+		addr |= RS400_PTE_WRITEABLE;
+	if (!(flags & RADEON_GART_PAGE_SNOOP))
+		entry |= RS400_PTE_UNSNOOPED;
 	entry = cpu_to_le32(entry);
 	gtt[i] = entry;
 }
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 27a56ad..5f6db46 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -625,15 +625,21 @@ static void rs600_gart_fini(struct radeon_device *rdev)
 	radeon_gart_table_vram_free(rdev);
 }
 
-void rs600_gart_set_page(struct radeon_device *rdev, unsigned i, uint64_t addr)
+void rs600_gart_set_page(struct radeon_device *rdev, unsigned i,
+			 uint64_t addr, uint32_t flags)
 {
 	void __iomem *ptr = (void *)rdev->gart.ptr;
 
 	addr = addr & 0xFFFFFFFFFFFFF000ULL;
-	if (addr == rdev->dummy_page.addr)
-		addr |= R600_PTE_SYSTEM | R600_PTE_SNOOPED;
-	else
-		addr |= R600_PTE_GART;
+	addr |= R600_PTE_SYSTEM;
+	if (flags & RADEON_GART_PAGE_VALID)
+		addr |= R600_PTE_VALID;
+	if (flags & RADEON_GART_PAGE_READ)
+		addr |= R600_PTE_READABLE;
+	if (flags & RADEON_GART_PAGE_WRITE)
+		addr |= R600_PTE_WRITEABLE;
+	if (flags & RADEON_GART_PAGE_SNOOP)
+		addr |= R600_PTE_SNOOPED;
 	writeq(addr, ptr + (i * 8));
 }
 
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 1cc0b61..509b2d7 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -796,7 +796,9 @@ struct drm_radeon_gem_info {
 	uint64_t	vram_visible;
 };
 
-#define RADEON_GEM_NO_BACKING_STORE 1
+#define RADEON_GEM_NO_BACKING_STORE	(1 << 0)
+#define RADEON_GEM_GTT_UC		(1 << 1)
+#define RADEON_GEM_GTT_WC		(1 << 2)
 
 struct drm_radeon_gem_create {
 	uint64_t	size;
-- 
2.0.0

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

  parent reply	other threads:[~2014-07-17 10:01 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-07-17 10:01 [PATCH 0/5] radeon: Write-combined CPU mappings of BOs in GTT Michel Dänzer
2014-07-17 10:01 ` [PATCH 1/5] drm/radeon: Remove radeon_gart_restore() Michel Dänzer
2014-07-17 10:01 ` Michel Dänzer [this message]
2014-07-17 10:01 ` [PATCH 3/5] drm/radeon: Allow write-combined CPU mappings of BOs in GTT Michel Dänzer
2014-07-17 10:01 ` [PATCH 4/5] drm/radeon: Use write-combined CPU mappings of rings and IBs on >= SI Michel Dänzer
2014-07-17 10:01 ` [PATCH 5/5] drm/radeon: Use VRAM for indirect buffers " Michel Dänzer
2014-07-17 10:01 ` [PATCH 1/5] winsys/radeon: Use separate caching buffer managers for VRAM and GTT Michel Dänzer
2014-07-17 10:01 ` [PATCH 2/5] r600g/radeonsi: Use write-combined CPU mappings of some BOs in GTT Michel Dänzer
2014-07-17 10:01 ` [PATCH 3/5] r600g/radeonsi: Prefer VRAM for CPU -> GPU streaming buffers Michel Dänzer
2014-07-17 10:01 ` [PATCH 4/5] r600g, radeonsi: Use write-combined persistent GTT mappings Michel Dänzer
2014-07-17 10:56   ` Grigori Goronzy
2014-07-17 12:00   ` Marek Olšák
2014-07-18  3:19     ` [Mesa-dev] " Michel Dänzer
2014-07-18 11:45       ` Marek Olšák
2014-07-18 19:50         ` [Mesa-dev] " Grigori Goronzy
2014-07-18 20:52           ` Marek Olšák
2014-07-23  6:32         ` Michel Dänzer
2014-07-23 11:52           ` Marek Olšák
2014-07-18 20:55       ` Marek Olšák
2014-07-17 10:01 ` [PATCH 5/5] r600g, radeonsi: Prefer VRAM for persistent mappings Michel Dänzer
2014-07-17 12:17   ` Marek Olšák
2014-07-17 10:09 ` [PATCH 0/5] radeon: Write-combined CPU mappings of BOs in GTT Christian König
2014-07-18  3:07   ` Michel Dänzer
2014-07-18  3:58     ` Dieter Nützel
2014-07-18  9:52       ` Michel Dänzer
2014-07-18 15:47     ` Christian König
2014-07-18 17:47       ` Marek Olšák
2014-07-18 22:03         ` Marek Olšák
2014-07-19  1:15       ` Michel Dänzer
2014-07-21  8:07         ` Christian König
2014-07-23  3:54           ` Michel Dänzer
2014-07-23  6:42             ` Christian König
2014-07-23  7:21               ` Michel Dänzer
2014-07-23  7:32                 ` Christian König
2014-07-23 12:07                 ` Marek Olšák
2014-07-23 13:59             ` Alex Deucher
2014-07-17 12:25 ` Marek Olšák
2014-07-17 13:35 ` Alex Deucher

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=1405591275-14461-3-git-send-email-michel@daenzer.net \
    --to=michel@daenzer.net \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=mesa-dev@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.