Merge drm/drm-next into drm-misc-next

We haven't done any backmerge for a while due to the merge window, and it
starts to become an issue for komeda. Let's bring 5.4-rc1 in.

Signed-off-by: Maxime Ripard <mripard@kernel.org>

1 files changed, 214 insertions, 40 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 1675d5837c3c..638c821611ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -20,8 +20,12 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  */
+
+#include <linux/delay.h>
+#include <linux/kernel.h>
 #include <linux/firmware.h>
-#include <drm/drmP.h>
+#include <linux/module.h>
+#include <linux/pci.h>
 #include "amdgpu.h"
 #include "amdgpu_gfx.h"
 #include "amdgpu_psp.h"
@@ -56,6 +60,9 @@
 #define F32_CE_PROGRAM_RAM_SIZE		65536
 #define RLCG_UCODE_LOADING_START_ADDRESS	0x00002000L
 
+#define mmCGTT_GS_NGG_CLK_CTRL	0x5087
+#define mmCGTT_GS_NGG_CLK_CTRL_BASE_IDX	1
+
 MODULE_FIRMWARE("amdgpu/navi10_ce.bin");
 MODULE_FIRMWARE("amdgpu/navi10_pfp.bin");
 MODULE_FIRMWARE("amdgpu/navi10_me.bin");
@@ -63,6 +70,25 @@ MODULE_FIRMWARE("amdgpu/navi10_mec.bin");
 MODULE_FIRMWARE("amdgpu/navi10_mec2.bin");
 MODULE_FIRMWARE("amdgpu/navi10_rlc.bin");
 
+MODULE_FIRMWARE("amdgpu/navi14_ce_wks.bin");
+MODULE_FIRMWARE("amdgpu/navi14_pfp_wks.bin");
+MODULE_FIRMWARE("amdgpu/navi14_me_wks.bin");
+MODULE_FIRMWARE("amdgpu/navi14_mec_wks.bin");
+MODULE_FIRMWARE("amdgpu/navi14_mec2_wks.bin");
+MODULE_FIRMWARE("amdgpu/navi14_ce.bin");
+MODULE_FIRMWARE("amdgpu/navi14_pfp.bin");
+MODULE_FIRMWARE("amdgpu/navi14_me.bin");
+MODULE_FIRMWARE("amdgpu/navi14_mec.bin");
+MODULE_FIRMWARE("amdgpu/navi14_mec2.bin");
+MODULE_FIRMWARE("amdgpu/navi14_rlc.bin");
+
+MODULE_FIRMWARE("amdgpu/navi12_ce.bin");
+MODULE_FIRMWARE("amdgpu/navi12_pfp.bin");
+MODULE_FIRMWARE("amdgpu/navi12_me.bin");
+MODULE_FIRMWARE("amdgpu/navi12_mec.bin");
+MODULE_FIRMWARE("amdgpu/navi12_mec2.bin");
+MODULE_FIRMWARE("amdgpu/navi12_rlc.bin");
+
 static const struct soc15_reg_golden golden_settings_gc_10_1[] =
 {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x00400014),
@@ -109,6 +135,99 @@ static const struct soc15_reg_golden golden_settings_gc_10_0_nv10[] =
 	/* Pending on emulation bring up */
 };
 
+static const struct soc15_reg_golden golden_settings_gc_10_1_1[] =
+{
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x003c0014),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_GS_NGG_CLK_CTRL, 0xffff8fff, 0xffff8100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_IA_CLK_CTRL, 0xffff0fff, 0xffff0100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xc0000000, 0xc0000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0xf8ff0fff, 0x60000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0x40000ff0, 0x40000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_WD_CLK_CTRL, 0xffff8fff, 0xffff8100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCH_PIPE_STEER, 0xffffffff, 0xe4e4e4e4),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCH_VC5_ENABLE, 0x00000002, 0x00000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_SD_CNTL, 0x800007ff, 0x000005ff),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG, 0xffffffff, 0x20000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG2, 0xffffffff, 0x00000420),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0x00000200, 0x00000200),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x04900000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DFSM_TILES_IN_FLIGHT, 0x0000ffff, 0x0000003f),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_LAST_OF_BURST_CONFIG, 0xffffffff, 0x03860204),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff0ffff, 0x00000500),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGE_PRIV_CONTROL, 0x000007ff, 0x000001fe),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0xffffffff, 0xe4e4e4e4),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2A_ADDR_MATCH_MASK, 0xffffffff, 0xffffffe7),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xffffffe7),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CGTT_SCLK_CTRL, 0xffff0fff, 0x10000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CTRL2, 0xffffffff, 0x1402002f),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CTRL3, 0xffffbfff, 0x00000188),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE, 0x3fffffff, 0x08000009),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_1, 0x00400000, 0x04440000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_SPARE, 0xffffffff, 0xffff3101),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ALU_CLK_CTRL, 0xffffffff, 0xffffffff),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ARB_CONFIG, 0x00000133, 0x00000130),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_LDS_CLK_CTRL, 0xffffffff, 0xffffffff),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CNTL, 0x60000010, 0x479c0010),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0x00800000, 0x00800000),
+};
+
+static const struct soc15_reg_golden golden_settings_gc_10_1_2[] =
+{
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0x003e001f, 0x003c0014),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_GS_NGG_CLK_CTRL, 0xffff8fff, 0xffff8100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_IA_CLK_CTRL, 0xffff0fff, 0xffff0100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xff7f0fff, 0xc0000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0xffffcfff, 0x60000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0xffff0fff, 0x40000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_WD_CLK_CTRL, 0xffff8fff, 0xffff8100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCH_PIPE_STEER, 0xffffffff, 0xe4e4e4e4),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCH_VC5_ENABLE, 0x00000003, 0x00000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_SD_CNTL, 0x800007ff, 0x000005ff),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG, 0xffffffff, 0x20000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG2, 0xffffffff, 0x00000420),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000200),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x04800000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DFSM_TILES_IN_FLIGHT, 0x0000ffff, 0x0000003f),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_LAST_OF_BURST_CONFIG, 0xffffffff, 0x03860204),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff0ffff, 0x00000500),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGE_PRIV_CONTROL, 0x00007fff, 0x000001fe),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0xffffffff, 0xe4e4e4e4),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x10321032),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x02310231),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2A_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CGTT_SCLK_CTRL, 0xffff0fff, 0x10000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CTRL2, 0xffffffff, 0x1402002f),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CTRL3, 0xffffbfff, 0x00000188),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_BINNER_EVENT_CNTL_0, 0xffffffff, 0x842a4c02),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_BINNER_TIMEOUT_COUNTER, 0xffffffff, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE, 0x3fffffff, 0x08000009),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_1, 0xffffffff, 0x04440000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0x00000820, 0x00000820),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_SPARE, 0xffffffff, 0xffff3101),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ALU_CLK_CTRL, 0xffffffff, 0xffffffff),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ARB_CONFIG, 0x00000133, 0x00000130),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_LDS_CLK_CTRL, 0xffffffff, 0xffffffff),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CNTL, 0xffdf80ff, 0x479c0010),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffffffff, 0x00800000)
+};
+
+static const struct soc15_reg_golden golden_settings_gc_10_1_nv14[] =
+{
+	/* Pending on emulation bring up */
+};
+
+static const struct soc15_reg_golden golden_settings_gc_10_1_2_nv12[] =
+{
+	/* Pending on emulation bring up */
+};
+
 #define DEFAULT_SH_MEM_CONFIG \
 	((SH_MEM_ADDRESS_MODE_64 << SH_MEM_CONFIG__ADDRESS_MODE__SHIFT) | \
 	 (SH_MEM_ALIGNMENT_MODE_UNALIGNED << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \
@@ -250,6 +369,22 @@ static void gfx_v10_0_init_golden_registers(struct amdgpu_device *adev)
 						golden_settings_gc_10_0_nv10,
 						(const u32)ARRAY_SIZE(golden_settings_gc_10_0_nv10));
 		break;
+	case CHIP_NAVI14:
+		soc15_program_register_sequence(adev,
+						golden_settings_gc_10_1_1,
+						(const u32)ARRAY_SIZE(golden_settings_gc_10_1_1));
+		soc15_program_register_sequence(adev,
+						golden_settings_gc_10_1_nv14,
+						(const u32)ARRAY_SIZE(golden_settings_gc_10_1_nv14));
+		break;
+	case CHIP_NAVI12:
+		soc15_program_register_sequence(adev,
+						golden_settings_gc_10_1_2,
+						(const u32)ARRAY_SIZE(golden_settings_gc_10_1_2));
+		soc15_program_register_sequence(adev,
+						golden_settings_gc_10_1_2_nv12,
+						(const u32)ARRAY_SIZE(golden_settings_gc_10_1_2_nv12));
+		break;
 	default:
 		break;
 	}
@@ -331,7 +466,7 @@ static int gfx_v10_0_ring_test_ring(struct amdgpu_ring *ring)
 		if (amdgpu_emu_mode == 1)
 			msleep(1);
 		else
-			DRM_UDELAY(1);
+			udelay(1);
 	}
 	if (i < adev->usec_timeout) {
 		if (amdgpu_emu_mode == 1)
@@ -464,7 +599,8 @@ static void gfx_v10_0_check_gfxoff_flag(struct amdgpu_device *adev)
 static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 {
 	const char *chip_name;
-	char fw_name[30];
+	char fw_name[40];
+	char wks[10];
 	int err;
 	struct amdgpu_firmware_info *info = NULL;
 	const struct common_firmware_header *header = NULL;
@@ -477,15 +613,25 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 
 	DRM_DEBUG("\n");
 
+	memset(wks, 0, sizeof(wks));
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
 		chip_name = "navi10";
 		break;
+	case CHIP_NAVI14:
+		chip_name = "navi14";
+		if (!(adev->pdev->device == 0x7340 &&
+		      adev->pdev->revision != 0x00))
+			snprintf(wks, sizeof(wks), "_wks");
+		break;
+	case CHIP_NAVI12:
+		chip_name = "navi12";
+		break;
 	default:
 		BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -496,7 +642,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.pfp_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -507,7 +653,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.me_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.me_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -572,7 +718,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 	if (adev->gfx.rlc.is_rlc_v2_1)
 		gfx_v10_0_init_rlc_ext_microcode(adev);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -583,7 +729,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.mec_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.mec_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev);
 	if (!err) {
 		err = amdgpu_ucode_validate(adev->gfx.mec2_fw);
@@ -1026,6 +1172,8 @@ static void gfx_v10_0_gpu_early_init(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
+	case CHIP_NAVI14:
+	case CHIP_NAVI12:
 		adev->gfx.config.max_hw_contexts = 8;
 		adev->gfx.config.sc_prim_fifo_size_frontend = 0x20;
 		adev->gfx.config.sc_prim_fifo_size_backend = 0x100;
@@ -1133,6 +1281,8 @@ static int gfx_v10_0_sw_init(void *handle)
 
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
+	case CHIP_NAVI14:
+	case CHIP_NAVI12:
 		adev->gfx.me.num_me = 1;
 		adev->gfx.me.num_pipe_per_me = 2;
 		adev->gfx.me.num_queue_per_pipe = 1;
@@ -1441,8 +1591,36 @@ static void gfx_v10_0_init_compute_vmid(struct amdgpu_device *adev)
 	}
 	nv_grbm_select(adev, 0, 0, 0, 0);
 	mutex_unlock(&adev->srbm_mutex);
+
+	/* Initialize all compute VMIDs to have no GDS, GWS, or OA
+	   acccess. These should be enabled by FW for target VMIDs. */
+	for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_BASE, 2 * i, 0);
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_SIZE, 2 * i, 0);
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_GWS_VMID0, i, 0);
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_OA_VMID0, i, 0);
+	}
 }
 
+static void gfx_v10_0_init_gds_vmid(struct amdgpu_device *adev)
+{
+	int vmid;
+
+	/*
+	 * Initialize all compute and user-gfx VMIDs to have no GDS, GWS, or OA
+	 * access. Compute VMIDs should be enabled by FW for target VMIDs,
+	 * the driver can enable them for graphics. VMID0 should maintain
+	 * access so that HWS firmware can save/restore entries.
+	 */
+	for (vmid = 1; vmid < 16; vmid++) {
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_BASE, 2 * vmid, 0);
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_SIZE, 2 * vmid, 0);
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_GWS_VMID0, vmid, 0);
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_OA_VMID0, vmid, 0);
+	}
+}
+
+
 static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev)
 {
 	int i, j, k;
@@ -1452,7 +1630,8 @@ static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev)
 	u32 utcl_invreq_disable = 0;
 	/*
 	 * GCRD_TARGETS_DISABLE field contains
-	 * for Navi10: GL1C=[18:15], SQC=[14:10], TCP=[9:0]
+	 * for Navi10/Navi12: GL1C=[18:15], SQC=[14:10], TCP=[9:0]
+	 * for Navi14: GL1C=[21:18], SQC=[17:12], TCP=[11:0]
 	 */
 	u32 gcrd_targets_disable_mask = amdgpu_gfx_create_bitmask(
 		2 * max_wgp_per_sh + /* TCP */
@@ -1460,7 +1639,8 @@ static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev)
 		4); /* GL1C */
 	/*
 	 * UTCL1_UTCL0_INVREQ_DISABLE field contains
-	 * for Navi10: SQG=[24], RMI=[23:20], SQC=[19:10], TCP=[9:0]
+	 * for Navi10Navi12: SQG=[24], RMI=[23:20], SQC=[19:10], TCP=[9:0]
+	 * for Navi14: SQG=[28], RMI=[27:24], SQC=[23:12], TCP=[11:0]
 	 */
 	u32 utcl_invreq_disable_mask = amdgpu_gfx_create_bitmask(
 		2 * max_wgp_per_sh + /* TCP */
@@ -1468,7 +1648,9 @@ static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev)
 		4 + /* RMI */
 		1); /* SQG */
 
-	if (adev->asic_type == CHIP_NAVI10) {
+	if (adev->asic_type == CHIP_NAVI10 ||
+	    adev->asic_type == CHIP_NAVI14 ||
+	    adev->asic_type == CHIP_NAVI12) {
 		mutex_lock(&adev->grbm_idx_mutex);
 		for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
 			for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
@@ -1526,7 +1708,7 @@ static void gfx_v10_0_constants_init(struct amdgpu_device *adev)
 	/* XXX SH_MEM regs */
 	/* where to put LDS, scratch, GPUVM in FSA64 space */
 	mutex_lock(&adev->srbm_mutex);
-	for (i = 0; i < adev->vm_manager.id_mgr[AMDGPU_GFXHUB].num_ids; i++) {
+	for (i = 0; i < adev->vm_manager.id_mgr[AMDGPU_GFXHUB_0].num_ids; i++) {
 		nv_grbm_select(adev, 0, 0, 0, i);
 		/* CP and shaders */
 		WREG32_SOC15(GC, 0, mmSH_MEM_CONFIG, DEFAULT_SH_MEM_CONFIG);
@@ -1543,6 +1725,7 @@ static void gfx_v10_0_constants_init(struct amdgpu_device *adev)
 	mutex_unlock(&adev->srbm_mutex);
 
 	gfx_v10_0_init_compute_vmid(adev);
+	gfx_v10_0_init_gds_vmid(adev);
 
 }
 
@@ -1575,9 +1758,12 @@ static void gfx_v10_0_init_csb(struct amdgpu_device *adev)
 
 static void gfx_v10_0_init_pg(struct amdgpu_device *adev)
 {
+	int i;
+
 	gfx_v10_0_init_csb(adev);
 
-	amdgpu_gmc_flush_gpu_tlb(adev, 0, 0);
+	for (i = 0; i < adev->num_vmhubs; i++)
+		amdgpu_gmc_flush_gpu_tlb(adev, 0, i, 0);
 
 	/* TODO: init power gating */
 	return;
@@ -1615,9 +1801,9 @@ static void gfx_v10_0_rlc_smu_handshake_cntl(struct amdgpu_device *adev,
 		 * hence no handshake between SMU & RLC
 		 * GFXOFF will be disabled
 		 */
-		rlc_pg_cntl |= 0x80000;
+		rlc_pg_cntl |= 0x800000;
 	} else
-		rlc_pg_cntl &= ~0x80000;
+		rlc_pg_cntl &= ~0x800000;
 	WREG32_SOC15(GC, 0, mmRLC_PG_CNTL, rlc_pg_cntl);
 }
 
@@ -3605,20 +3791,12 @@ static int gfx_v10_0_hw_fini(void *handle)
 
 static int gfx_v10_0_suspend(void *handle)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	adev->in_suspend = true;
-	return gfx_v10_0_hw_fini(adev);
+	return gfx_v10_0_hw_fini(handle);
 }
 
 static int gfx_v10_0_resume(void *handle)
 {
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	int r;
-
-	r = gfx_v10_0_hw_init(adev);
-	adev->in_suspend = false;
-	return r;
+	return gfx_v10_0_hw_init(handle);
 }
 
 static bool gfx_v10_0_is_idle(void *handle)
@@ -4028,6 +4206,7 @@ static int gfx_v10_0_set_powergating_state(void *handle,
 	bool enable = (state == AMD_PG_STATE_GATE) ? true : false;
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
+	case CHIP_NAVI14:
 		if (!enable) {
 			amdgpu_gfx_off_ctrl(adev, false);
 			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
@@ -4047,6 +4226,8 @@ static int gfx_v10_0_set_clockgating_state(void *handle,
 
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
+	case CHIP_NAVI14:
+	case CHIP_NAVI12:
 		gfx_v10_0_update_gfx_clock_gating(adev,
 						 state == AMD_CG_STATE_GATE ? true : false);
 		break;
@@ -4197,15 +4378,6 @@ static void gfx_v10_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 	u32 header, control = 0;
 
-	/* Prevent a hw deadlock due to a wave ID mismatch between ME and GDS.
-	 * This resets the wave ID counters. (needed by transform feedback)
-	 * TODO: This might only be needed on a VMID switch when we change
-	 *       the GDS OA mapping, not sure.
-	 */
-	amdgpu_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
-	amdgpu_ring_write(ring, mmVGT_GS_MAX_WAVE_ID);
-	amdgpu_ring_write(ring, ring->adev->gds.vgt_gs_max_wave_id);
-
 	if (ib->flags & AMDGPU_IB_FLAG_CE)
 		header = PACKET3(PACKET3_INDIRECT_BUFFER_CNST, 2);
 	else
@@ -4453,7 +4625,7 @@ static int gfx_v10_0_ring_preempt_ib(struct amdgpu_ring *ring)
 		if (ring->trail_seq ==
 		    le32_to_cpu(*(ring->trail_fence_cpu_addr)))
 			break;
-		DRM_UDELAY(1);
+		udelay(1);
 	}
 
 	if (i >= adev->usec_timeout) {
@@ -4611,6 +4783,7 @@ gfx_v10_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev,
 		cp_int_cntl = REG_SET_FIELD(cp_int_cntl, CP_INT_CNTL_RING0,
 					    TIME_STAMP_INT_ENABLE, 0);
 		WREG32(cp_int_cntl_reg, cp_int_cntl);
+		break;
 	case AMDGPU_IRQ_STATE_ENABLE:
 		cp_int_cntl = RREG32(cp_int_cntl_reg);
 		cp_int_cntl = REG_SET_FIELD(cp_int_cntl, CP_INT_CNTL_RING0,
@@ -4926,7 +5099,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = {
 	.align_mask = 0xff,
 	.nop = PACKET3(PACKET3_NOP, 0x3FFF),
 	.support_64bit_ptrs = true,
-	.vmhub = AMDGPU_GFXHUB,
+	.vmhub = AMDGPU_GFXHUB_0,
 	.get_rptr = gfx_v10_0_ring_get_rptr_gfx,
 	.get_wptr = gfx_v10_0_ring_get_wptr_gfx,
 	.set_wptr = gfx_v10_0_ring_set_wptr_gfx,
@@ -4951,7 +5124,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = {
 		5 + /* HDP_INVL */
 		8 + 8 + /* FENCE x2 */
 		2, /* SWITCH_BUFFER */
-	.emit_ib_size =	7, /* gfx_v10_0_ring_emit_ib_gfx */
+	.emit_ib_size =	4, /* gfx_v10_0_ring_emit_ib_gfx */
 	.emit_ib = gfx_v10_0_ring_emit_ib_gfx,
 	.emit_fence = gfx_v10_0_ring_emit_fence,
 	.emit_pipeline_sync = gfx_v10_0_ring_emit_pipeline_sync,
@@ -4977,7 +5150,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = {
 	.align_mask = 0xff,
 	.nop = PACKET3(PACKET3_NOP, 0x3FFF),
 	.support_64bit_ptrs = true,
-	.vmhub = AMDGPU_GFXHUB,
+	.vmhub = AMDGPU_GFXHUB_0,
 	.get_rptr = gfx_v10_0_ring_get_rptr_compute,
 	.get_wptr = gfx_v10_0_ring_get_wptr_compute,
 	.set_wptr = gfx_v10_0_ring_set_wptr_compute,
@@ -5010,7 +5183,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = {
 	.align_mask = 0xff,
 	.nop = PACKET3(PACKET3_NOP, 0x3FFF),
 	.support_64bit_ptrs = true,
-	.vmhub = AMDGPU_GFXHUB,
+	.vmhub = AMDGPU_GFXHUB_0,
 	.get_rptr = gfx_v10_0_ring_get_rptr_compute,
 	.get_wptr = gfx_v10_0_ring_get_wptr_compute,
 	.set_wptr = gfx_v10_0_ring_set_wptr_compute,
@@ -5087,6 +5260,8 @@ static void gfx_v10_0_set_rlc_funcs(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
+	case CHIP_NAVI14:
+	case CHIP_NAVI12:
 		adev->gfx.rlc.funcs = &gfx_v10_0_rlc_funcs;
 		break;
 	default:
@@ -5102,7 +5277,6 @@ static void gfx_v10_0_set_gds_init(struct amdgpu_device *adev)
 	default:
 		adev->gds.gds_size = 0x10000;
 		adev->gds.gds_compute_max_wave_id = 0x4ff;
-		adev->gds.vgt_gs_max_wave_id = 0x3ff;
 		break;
 	}