Merge branch 'perf/core' into perf/uprobes

Merge in latest upstream (and the latest perf development tree),
to prepare for tooling changes, and also to pick up v3.4 MM
changes that the uprobes code needs to take care of.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 79 insertions, 30 deletions

diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 333cde9d4e7..81801c176aa 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -65,6 +65,40 @@ MODULE_FIRMWARE(FIRMWARE_R520);
 
 #include "r100_track.h"
 
+void r100_wait_for_vblank(struct radeon_device *rdev, int crtc)
+{
+	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc];
+	int i;
+
+	if (radeon_crtc->crtc_id == 0) {
+		if (RREG32(RADEON_CRTC_GEN_CNTL) & RADEON_CRTC_EN) {
+			for (i = 0; i < rdev->usec_timeout; i++) {
+				if (!(RREG32(RADEON_CRTC_STATUS) & RADEON_CRTC_VBLANK_CUR))
+					break;
+				udelay(1);
+			}
+			for (i = 0; i < rdev->usec_timeout; i++) {
+				if (RREG32(RADEON_CRTC_STATUS) & RADEON_CRTC_VBLANK_CUR)
+					break;
+				udelay(1);
+			}
+		}
+	} else {
+		if (RREG32(RADEON_CRTC2_GEN_CNTL) & RADEON_CRTC2_EN) {
+			for (i = 0; i < rdev->usec_timeout; i++) {
+				if (!(RREG32(RADEON_CRTC2_STATUS) & RADEON_CRTC2_VBLANK_CUR))
+					break;
+				udelay(1);
+			}
+			for (i = 0; i < rdev->usec_timeout; i++) {
+				if (RREG32(RADEON_CRTC2_STATUS) & RADEON_CRTC2_VBLANK_CUR)
+					break;
+				udelay(1);
+			}
+		}
+	}
+}
+
 /* This files gather functions specifics to:
  * r100,rv100,rs100,rv200,rs200,r200,rv250,rs300,rv280
  */
@@ -87,23 +121,27 @@ int r100_reloc_pitch_offset(struct radeon_cs_parser *p,
 		r100_cs_dump_packet(p, pkt);
 		return r;
 	}
+
 	value = radeon_get_ib_value(p, idx);
 	tmp = value & 0x003fffff;
 	tmp += (((u32)reloc->lobj.gpu_offset) >> 10);
 
-	if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
-		tile_flags |= RADEON_DST_TILE_MACRO;
-	if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
-		if (reg == RADEON_SRC_PITCH_OFFSET) {
-			DRM_ERROR("Cannot src blit from microtiled surface\n");
-			r100_cs_dump_packet(p, pkt);
-			return -EINVAL;
+	if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
+		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+			tile_flags |= RADEON_DST_TILE_MACRO;
+		if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
+			if (reg == RADEON_SRC_PITCH_OFFSET) {
+				DRM_ERROR("Cannot src blit from microtiled surface\n");
+				r100_cs_dump_packet(p, pkt);
+				return -EINVAL;
+			}
+			tile_flags |= RADEON_DST_TILE_MICRO;
 		}
-		tile_flags |= RADEON_DST_TILE_MICRO;
-	}
 
-	tmp |= tile_flags;
-	p->ib->ptr[idx] = (value & 0x3fc00000) | tmp;
+		tmp |= tile_flags;
+		p->ib->ptr[idx] = (value & 0x3fc00000) | tmp;
+	} else
+		p->ib->ptr[idx] = (value & 0xffc00000) | tmp;
 	return 0;
 }
 
@@ -412,7 +450,7 @@ void r100_pm_misc(struct radeon_device *rdev)
 	/* set pcie lanes */
 	if ((rdev->flags & RADEON_IS_PCIE) &&
 	    !(rdev->flags & RADEON_IS_IGP) &&
-	    rdev->asic->set_pcie_lanes &&
+	    rdev->asic->pm.set_pcie_lanes &&
 	    (ps->pcie_lanes !=
 	     rdev->pm.power_state[rdev->pm.current_power_state_index].pcie_lanes)) {
 		radeon_set_pcie_lanes(rdev,
@@ -592,8 +630,8 @@ int r100_pci_gart_init(struct radeon_device *rdev)
 	if (r)
 		return r;
 	rdev->gart.table_size = rdev->gart.num_gpu_pages * 4;
-	rdev->asic->gart_tlb_flush = &r100_pci_gart_tlb_flush;
-	rdev->asic->gart_set_page = &r100_pci_gart_set_page;
+	rdev->asic->gart.tlb_flush = &r100_pci_gart_tlb_flush;
+	rdev->asic->gart.set_page = &r100_pci_gart_set_page;
 	return radeon_gart_table_ram_alloc(rdev);
 }
 
@@ -930,9 +968,8 @@ static int r100_cp_wait_for_idle(struct radeon_device *rdev)
 	return -1;
 }
 
-void r100_ring_start(struct radeon_device *rdev)
+void r100_ring_start(struct radeon_device *rdev, struct radeon_ring *ring)
 {
-	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	int r;
 
 	r = radeon_ring_lock(rdev, ring, 2);
@@ -1143,8 +1180,8 @@ int r100_cp_init(struct radeon_device *rdev, unsigned ring_size)
 	WREG32(RADEON_CP_RB_WPTR_DELAY, 0);
 	WREG32(RADEON_CP_CSQ_MODE, 0x00004D4D);
 	WREG32(RADEON_CP_CSQ_CNTL, RADEON_CSQ_PRIBM_INDBM);
-	radeon_ring_start(rdev);
-	r = radeon_ring_test(rdev, ring);
+	radeon_ring_start(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
+	r = radeon_ring_test(rdev, RADEON_RING_TYPE_GFX_INDEX, ring);
 	if (r) {
 		DRM_ERROR("radeon: cp isn't working (%d).\n", r);
 		return r;
@@ -1552,7 +1589,17 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 			r100_cs_dump_packet(p, pkt);
 			return r;
 		}
-		ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
+		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+				tile_flags |= RADEON_TXO_MACRO_TILE;
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+				tile_flags |= RADEON_TXO_MICRO_TILE_X2;
+
+			tmp = idx_value & ~(0x7 << 2);
+			tmp |= tile_flags;
+			ib[idx] = tmp + ((u32)reloc->lobj.gpu_offset);
+		} else
+			ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset);
 		track->textures[i].robj = reloc->robj;
 		track->tex_dirty = true;
 		break;
@@ -1623,15 +1670,17 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 			r100_cs_dump_packet(p, pkt);
 			return r;
 		}
-
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
-			tile_flags |= RADEON_COLOR_TILE_ENABLE;
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
-			tile_flags |= RADEON_COLOR_MICROTILE_ENABLE;
-
-		tmp = idx_value & ~(0x7 << 16);
-		tmp |= tile_flags;
-		ib[idx] = tmp;
+		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+				tile_flags |= RADEON_COLOR_TILE_ENABLE;
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+				tile_flags |= RADEON_COLOR_MICROTILE_ENABLE;
+
+			tmp = idx_value & ~(0x7 << 16);
+			tmp |= tile_flags;
+			ib[idx] = tmp;
+		} else
+			ib[idx] = idx_value;
 
 		track->cb[0].pitch = idx_value & RADEON_COLORPITCH_MASK;
 		track->cb_dirty = true;
@@ -3691,7 +3740,7 @@ void r100_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 	radeon_ring_write(ring, ib->length_dw);
 }
 
-int r100_ib_test(struct radeon_device *rdev)
+int r100_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	struct radeon_ib *ib;
 	uint32_t scratch;
@@ -3916,7 +3965,7 @@ static int r100_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = r100_ib_test(rdev);
+	r = radeon_ib_test(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
 	if (r) {
 		dev_err(rdev->dev, "failed testing IB (%d).\n", r);
 		rdev->accel_working = false;