Merge branch 'drm-fixes-3.18' of git://people.freedesktop.org/~agd5f/linux into drm-fixes

First round of fixes for 3.18.
- Use gart for DMA ring tests to avoid caching issues with HDP
- SI dpm stability fixes
- Performance stabilization fixes
- misc other things

* 'drm-fixes-3.18' of git://people.freedesktop.org/~agd5f/linux:
  drm/radeon: reduce sparse false positive warnings
  drm/radeon: fix vm page table block size calculation
  drm/ttm: Don't evict BOs outside of the requested placement range
  drm/ttm: Don't skip fpfn check if lpfn is 0 in ttm_bo_mem_compat
  drm/radeon: use gart memory for DMA ring tests
  drm/radeon: fix speaker allocation setup
  drm/radeon: initialize sadb to NULL in the audio code
  Revert "drm/radeon/dpm: drop clk/voltage dependency filters for SI"
  Revert "drm/radeon: drop btc_get_max_clock_from_voltage_dependency_table"

20 files changed, 113 insertions, 37 deletions

diff --git a/drivers/gpu/drm/radeon/btc_dpm.c b/drivers/gpu/drm/radeon/btc_dpm.c
index 300d971187c..0b2929de9f4 100644
--- a/drivers/gpu/drm/radeon/btc_dpm.c
+++ b/drivers/gpu/drm/radeon/btc_dpm.c
@@ -24,6 +24,7 @@
 
 #include "drmP.h"
 #include "radeon.h"
+#include "radeon_asic.h"
 #include "btcd.h"
 #include "r600_dpm.h"
 #include "cypress_dpm.h"
@@ -1170,6 +1171,23 @@ static const struct radeon_blacklist_clocks btc_blacklist_clocks[] =
         { 25000, 30000, RADEON_SCLK_UP }
 };
 
+void btc_get_max_clock_from_voltage_dependency_table(struct radeon_clock_voltage_dependency_table *table,
+						     u32 *max_clock)
+{
+	u32 i, clock = 0;
+
+	if ((table == NULL) || (table->count == 0)) {
+		*max_clock = clock;
+		return;
+	}
+
+	for (i = 0; i < table->count; i++) {
+		if (clock < table->entries[i].clk)
+			clock = table->entries[i].clk;
+	}
+	*max_clock = clock;
+}
+
 void btc_apply_voltage_dependency_rules(struct radeon_clock_voltage_dependency_table *table,
 					u32 clock, u16 max_voltage, u16 *voltage)
 {
diff --git a/drivers/gpu/drm/radeon/btc_dpm.h b/drivers/gpu/drm/radeon/btc_dpm.h
index 1a15e0e4195..3b6f12b7760 100644
--- a/drivers/gpu/drm/radeon/btc_dpm.h
+++ b/drivers/gpu/drm/radeon/btc_dpm.h
@@ -46,6 +46,8 @@ void btc_adjust_clock_combinations(struct radeon_device *rdev,
 				   struct rv7xx_pl *pl);
 void btc_apply_voltage_dependency_rules(struct radeon_clock_voltage_dependency_table *table,
 					u32 clock, u16 max_voltage, u16 *voltage);
+void btc_get_max_clock_from_voltage_dependency_table(struct radeon_clock_voltage_dependency_table *table,
+						     u32 *max_clock);
 void btc_apply_voltage_delta_rules(struct radeon_device *rdev,
 				   u16 max_vddc, u16 max_vddci,
 				   u16 *vddc, u16 *vddci);
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index f5c8c0445a9..11a55e9dad7 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -24,6 +24,7 @@
 #include <linux/firmware.h>
 #include "drmP.h"
 #include "radeon.h"
+#include "radeon_asic.h"
 #include "radeon_ucode.h"
 #include "cikd.h"
 #include "r600_dpm.h"
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index c77dad1a457..4e8432d07f1 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -611,16 +611,19 @@ int cik_sdma_ring_test(struct radeon_device *rdev,
 {
 	unsigned i;
 	int r;
-	void __iomem *ptr = (void *)rdev->vram_scratch.ptr;
+	unsigned index;
 	u32 tmp;
+	u64 gpu_addr;
 
-	if (!ptr) {
-		DRM_ERROR("invalid vram scratch pointer\n");
-		return -EINVAL;
-	}
+	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+		index = R600_WB_DMA_RING_TEST_OFFSET;
+	else
+		index = CAYMAN_WB_DMA1_RING_TEST_OFFSET;
+
+	gpu_addr = rdev->wb.gpu_addr + index;
 
 	tmp = 0xCAFEDEAD;
-	writel(tmp, ptr);
+	rdev->wb.wb[index/4] = cpu_to_le32(tmp);
 
 	r = radeon_ring_lock(rdev, ring, 5);
 	if (r) {
@@ -628,14 +631,14 @@ int cik_sdma_ring_test(struct radeon_device *rdev,
 		return r;
 	}
 	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0));
-	radeon_ring_write(ring, rdev->vram_scratch.gpu_addr & 0xfffffffc);
-	radeon_ring_write(ring, upper_32_bits(rdev->vram_scratch.gpu_addr));
+	radeon_ring_write(ring, lower_32_bits(gpu_addr));
+	radeon_ring_write(ring, upper_32_bits(gpu_addr));
 	radeon_ring_write(ring, 1); /* number of DWs to follow */
 	radeon_ring_write(ring, 0xDEADBEEF);
 	radeon_ring_unlock_commit(rdev, ring, false);
 
 	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = readl(ptr);
+		tmp = le32_to_cpu(rdev->wb.wb[index/4]);
 		if (tmp == 0xDEADBEEF)
 			break;
 		DRM_UDELAY(1);
diff --git a/drivers/gpu/drm/radeon/cypress_dpm.c b/drivers/gpu/drm/radeon/cypress_dpm.c
index 47d31e91575..9aad0327e4d 100644
--- a/drivers/gpu/drm/radeon/cypress_dpm.c
+++ b/drivers/gpu/drm/radeon/cypress_dpm.c
@@ -24,6 +24,7 @@
 
 #include "drmP.h"
 #include "radeon.h"
+#include "radeon_asic.h"
 #include "evergreend.h"
 #include "r600_dpm.h"
 #include "cypress_dpm.h"
diff --git a/drivers/gpu/drm/radeon/dce3_1_afmt.c b/drivers/gpu/drm/radeon/dce3_1_afmt.c
index 950af153f30..2fe8cfc966d 100644
--- a/drivers/gpu/drm/radeon/dce3_1_afmt.c
+++ b/drivers/gpu/drm/radeon/dce3_1_afmt.c
@@ -32,7 +32,7 @@ static void dce3_2_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 	struct drm_connector *connector;
 	struct radeon_connector *radeon_connector = NULL;
 	u32 tmp;
-	u8 *sadb;
+	u8 *sadb = NULL;
 	int sad_count;
 
 	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
@@ -49,8 +49,8 @@ static void dce3_2_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 
 	sad_count = drm_edid_to_speaker_allocation(radeon_connector->edid, &sadb);
 	if (sad_count < 0) {
-		DRM_ERROR("Couldn't read Speaker Allocation Data Block: %d\n", sad_count);
-		return;
+		DRM_DEBUG("Couldn't read Speaker Allocation Data Block: %d\n", sad_count);
+		sad_count = 0;
 	}
 
 	/* program the speaker allocation */
diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c
index c0bbf68dbc2..f312edf4d50 100644
--- a/drivers/gpu/drm/radeon/dce6_afmt.c
+++ b/drivers/gpu/drm/radeon/dce6_afmt.c
@@ -155,7 +155,7 @@ void dce6_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 	struct drm_connector *connector;
 	struct radeon_connector *radeon_connector = NULL;
 	u32 offset, tmp;
-	u8 *sadb;
+	u8 *sadb = NULL;
 	int sad_count;
 
 	if (!dig || !dig->afmt || !dig->afmt->pin)
@@ -176,9 +176,9 @@ void dce6_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 	}
 
 	sad_count = drm_edid_to_speaker_allocation(radeon_connector_edid(connector), &sadb);
-	if (sad_count <= 0) {
-		DRM_ERROR("Couldn't read Speaker Allocation Data Block: %d\n", sad_count);
-		return;
+	if (sad_count < 0) {
+		DRM_DEBUG("Couldn't read Speaker Allocation Data Block: %d\n", sad_count);
+		sad_count = 0;
 	}
 
 	/* program the speaker allocation */
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index 2514d659b1b..53abd9b17a5 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -133,7 +133,7 @@ static void dce4_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 	struct drm_connector *connector;
 	struct radeon_connector *radeon_connector = NULL;
 	u32 tmp;
-	u8 *sadb;
+	u8 *sadb = NULL;
 	int sad_count;
 
 	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
@@ -149,9 +149,9 @@ static void dce4_afmt_write_speaker_allocation(struct drm_encoder *encoder)
 	}
 
 	sad_count = drm_edid_to_speaker_allocation(radeon_connector_edid(connector), &sadb);
-	if (sad_count <= 0) {
-		DRM_ERROR("Couldn't read Speaker Allocation Data Block: %d\n", sad_count);
-		return;
+	if (sad_count < 0) {
+		DRM_DEBUG("Couldn't read Speaker Allocation Data Block: %d\n", sad_count);
+		sad_count = 0;
 	}
 
 	/* program the speaker allocation */
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index 715b181c624..6d2f16cf2c1 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -23,6 +23,7 @@
 
 #include "drmP.h"
 #include "radeon.h"
+#include "radeon_asic.h"
 #include "nid.h"
 #include "r600_dpm.h"
 #include "ni_dpm.h"
diff --git a/drivers/gpu/drm/radeon/r600_dma.c b/drivers/gpu/drm/radeon/r600_dma.c
index 100189ec5fa..aabc343b9a8 100644
--- a/drivers/gpu/drm/radeon/r600_dma.c
+++ b/drivers/gpu/drm/radeon/r600_dma.c
@@ -232,16 +232,19 @@ int r600_dma_ring_test(struct radeon_device *rdev,
 {
 	unsigned i;
 	int r;
-	void __iomem *ptr = (void *)rdev->vram_scratch.ptr;
+	unsigned index;
 	u32 tmp;
+	u64 gpu_addr;
 
-	if (!ptr) {
-		DRM_ERROR("invalid vram scratch pointer\n");
-		return -EINVAL;
-	}
+	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+		index = R600_WB_DMA_RING_TEST_OFFSET;
+	else
+		index = CAYMAN_WB_DMA1_RING_TEST_OFFSET;
+
+	gpu_addr = rdev->wb.gpu_addr + index;
 
 	tmp = 0xCAFEDEAD;
-	writel(tmp, ptr);
+	rdev->wb.wb[index/4] = cpu_to_le32(tmp);
 
 	r = radeon_ring_lock(rdev, ring, 4);
 	if (r) {
@@ -249,13 +252,13 @@ int r600_dma_ring_test(struct radeon_device *rdev,
 		return r;
 	}
 	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 1));
-	radeon_ring_write(ring, rdev->vram_scratch.gpu_addr & 0xfffffffc);
-	radeon_ring_write(ring, upper_32_bits(rdev->vram_scratch.gpu_addr) & 0xff);
+	radeon_ring_write(ring, lower_32_bits(gpu_addr));
+	radeon_ring_write(ring, upper_32_bits(gpu_addr) & 0xff);
 	radeon_ring_write(ring, 0xDEADBEEF);
 	radeon_ring_unlock_commit(rdev, ring, false);
 
 	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = readl(ptr);
+		tmp = le32_to_cpu(rdev->wb.wb[index/4]);
 		if (tmp == 0xDEADBEEF)
 			break;
 		DRM_UDELAY(1);
diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c
index 9c61b74ef44..f6309bd23e0 100644
--- a/drivers/gpu/drm/radeon/r600_dpm.c
+++ b/drivers/gpu/drm/radeon/r600_dpm.c
@@ -24,6 +24,7 @@
 
 #include "drmP.h"
 #include "radeon.h"
+#include "radeon_asic.h"
 #include "r600d.h"
 #include "r600_dpm.h"
 #include "atom.h"
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index f7c4b226a28..a9717b3fbf1 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1133,6 +1133,8 @@ struct radeon_wb {
 #define R600_WB_EVENT_OFFSET     3072
 #define CIK_WB_CP1_WPTR_OFFSET     3328
 #define CIK_WB_CP2_WPTR_OFFSET     3584
+#define R600_WB_DMA_RING_TEST_OFFSET 3588
+#define CAYMAN_WB_DMA1_RING_TEST_OFFSET 3592
 
 /**
  * struct radeon_pm - power management datas
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index f41cc1538e4..ea2676954dd 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1130,7 +1130,7 @@ static void radeon_check_arguments(struct radeon_device *rdev)
 	if (radeon_vm_block_size == -1) {
 
 		/* Total bits covered by PD + PTs */
-		unsigned bits = ilog2(radeon_vm_size) + 17;
+		unsigned bits = ilog2(radeon_vm_size) + 18;
 
 		/* Make sure the PD is 4K in size up to 8GB address space.
 		   Above that split equal between PD and PTs */
diff --git a/drivers/gpu/drm/radeon/rs780_dpm.c b/drivers/gpu/drm/radeon/rs780_dpm.c
index 02f7710de47..9031f4b6982 100644
--- a/drivers/gpu/drm/radeon/rs780_dpm.c
+++ b/drivers/gpu/drm/radeon/rs780_dpm.c
@@ -24,6 +24,7 @@
 
 #include "drmP.h"
 #include "radeon.h"
+#include "radeon_asic.h"
 #include "rs780d.h"
 #include "r600_dpm.h"
 #include "rs780_dpm.h"
diff --git a/drivers/gpu/drm/radeon/rv6xx_dpm.c b/drivers/gpu/drm/radeon/rv6xx_dpm.c
index e7045b08571..6a5c233361e 100644
--- a/drivers/gpu/drm/radeon/rv6xx_dpm.c
+++ b/drivers/gpu/drm/radeon/rv6xx_dpm.c
@@ -24,6 +24,7 @@
 
 #include "drmP.h"
 #include "radeon.h"
+#include "radeon_asic.h"
 #include "rv6xxd.h"
 #include "r600_dpm.h"
 #include "rv6xx_dpm.h"
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c
index 3c76e1dcdf0..755a8f96fe4 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.c
+++ b/drivers/gpu/drm/radeon/rv770_dpm.c
@@ -24,6 +24,7 @@
 
 #include "drmP.h"
 #include "radeon.h"
+#include "radeon_asic.h"
 #include "rv770d.h"
 #include "r600_dpm.h"
 #include "rv770_dpm.h"
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 9e4d5d7d348..a53c2e79d9c 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -23,6 +23,7 @@
 
 #include "drmP.h"
 #include "radeon.h"
+#include "radeon_asic.h"
 #include "sid.h"
 #include "r600_dpm.h"
 #include "si_dpm.h"
@@ -2916,6 +2917,7 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 	bool disable_sclk_switching = false;
 	u32 mclk, sclk;
 	u16 vddc, vddci;
+	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
 	int i;
 
 	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
@@ -2949,6 +2951,29 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 		}
 	}
 
+	/* limit clocks to max supported clocks based on voltage dependency tables */
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk,
+							&max_sclk_vddc);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk,
+							&max_mclk_vddci);
+	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk,
+							&max_mclk_vddc);
+
+	for (i = 0; i < ps->performance_level_count; i++) {
+		if (max_sclk_vddc) {
+			if (ps->performance_levels[i].sclk > max_sclk_vddc)
+				ps->performance_levels[i].sclk = max_sclk_vddc;
+		}
+		if (max_mclk_vddci) {
+			if (ps->performance_levels[i].mclk > max_mclk_vddci)
+				ps->performance_levels[i].mclk = max_mclk_vddci;
+		}
+		if (max_mclk_vddc) {
+			if (ps->performance_levels[i].mclk > max_mclk_vddc)
+				ps->performance_levels[i].mclk = max_mclk_vddc;
+		}
+	}
+
 	/* XXX validate the min clocks required for display */
 
 	if (disable_mclk_switching) {
diff --git a/drivers/gpu/drm/radeon/sumo_dpm.c b/drivers/gpu/drm/radeon/sumo_dpm.c
index 3f0e8d7b8db..1f8a8833e1b 100644
--- a/drivers/gpu/drm/radeon/sumo_dpm.c
+++ b/drivers/gpu/drm/radeon/sumo_dpm.c
@@ -23,6 +23,7 @@
 
 #include "drmP.h"
 #include "radeon.h"
+#include "radeon_asic.h"
 #include "sumod.h"
 #include "r600_dpm.h"
 #include "cypress_dpm.h"
diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c
index 57f780053b3..b4ec5c4e796 100644
--- a/drivers/gpu/drm/radeon/trinity_dpm.c
+++ b/drivers/gpu/drm/radeon/trinity_dpm.c
@@ -23,6 +23,7 @@
 
 #include "drmP.h"
 #include "radeon.h"
+#include "radeon_asic.h"
 #include "trinityd.h"
 #include "r600_dpm.h"
 #include "trinity_dpm.h"
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 8f5cec67c47..d395b0bef73 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -709,6 +709,7 @@ out:
 
 static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 				uint32_t mem_type,
+				const struct ttm_place *place,
 				bool interruptible,
 				bool no_wait_gpu)
 {
@@ -720,8 +721,21 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 	spin_lock(&glob->lru_lock);
 	list_for_each_entry(bo, &man->lru, lru) {
 		ret = __ttm_bo_reserve(bo, false, true, false, NULL);
-		if (!ret)
+		if (!ret) {
+			if (place && (place->fpfn || place->lpfn)) {
+				/* Don't evict this BO if it's outside of the
+				 * requested placement range
+				 */
+				if (place->fpfn >= (bo->mem.start + bo->mem.size) ||
+				    (place->lpfn && place->lpfn <= bo->mem.start)) {
+					__ttm_bo_unreserve(bo);
+					ret = -EBUSY;
+					continue;
+				}
+			}
+
 			break;
+		}
 	}
 
 	if (ret) {
@@ -782,7 +796,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 			return ret;
 		if (mem->mm_node)
 			break;
-		ret = ttm_mem_evict_first(bdev, mem_type,
+		ret = ttm_mem_evict_first(bdev, mem_type, place,
 					  interruptible, no_wait_gpu);
 		if (unlikely(ret != 0))
 			return ret;
@@ -994,9 +1008,9 @@ static bool ttm_bo_mem_compat(struct ttm_placement *placement,
 
 	for (i = 0; i < placement->num_placement; i++) {
 		const struct ttm_place *heap = &placement->placement[i];
-		if (mem->mm_node && heap->lpfn != 0 &&
+		if (mem->mm_node &&
 		    (mem->start < heap->fpfn ||
-		     mem->start + mem->num_pages > heap->lpfn))
+		     (heap->lpfn != 0 && (mem->start + mem->num_pages) > heap->lpfn)))
 			continue;
 
 		*new_flags = heap->flags;
@@ -1007,9 +1021,9 @@ static bool ttm_bo_mem_compat(struct ttm_placement *placement,
 
 	for (i = 0; i < placement->num_busy_placement; i++) {
 		const struct ttm_place *heap = &placement->busy_placement[i];
-		if (mem->mm_node && heap->lpfn != 0 &&
+		if (mem->mm_node &&
 		    (mem->start < heap->fpfn ||
-		     mem->start + mem->num_pages > heap->lpfn))
+		     (heap->lpfn != 0 && (mem->start + mem->num_pages) > heap->lpfn)))
 			continue;
 
 		*new_flags = heap->flags;
@@ -1233,7 +1247,7 @@ static int ttm_bo_force_list_clean(struct ttm_bo_device *bdev,
 	spin_lock(&glob->lru_lock);
 	while (!list_empty(&man->lru)) {
 		spin_unlock(&glob->lru_lock);
-		ret = ttm_mem_evict_first(bdev, mem_type, false, false);
+		ret = ttm_mem_evict_first(bdev, mem_type, NULL, false, false);
 		if (ret) {
 			if (allow_errors) {
 				return ret;