24 files changed, 172 insertions, 93 deletions
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 9541995e4b21..c742944d3805 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -764,7 +764,7 @@ static void atombios_crtc_set_dcpll(struct drm_crtc *crtc,
 }
 static void atombios_crtc_program_pll(struct drm_crtc *crtc,
-                                      int crtc_id,
+                                      u32 crtc_id,
                                      int pll_id,
                                      u32 encoder_mode,
                                      u32 encoder_id,
@@ -851,8 +851,7 @@ static void atombios_crtc_program_pll(struct drm_crtc *crtc,
                        args.v5.ucPpll = pll_id;
                        break;
                case 6:
-                        args.v6.ulCrtcPclkFreq.ucCRTC = crtc_id;
+                        args.v6.ulDispEngClkFreq = cpu_to_le32(crtc_id << 24 | clock / 10);
-                        args.v6.ulCrtcPclkFreq.ulPixelClock = cpu_to_le32(clock / 10);
                        args.v6.ucRefDiv = ref_div;
                        args.v6.usFbDiv = cpu_to_le16(fb_div);
                        args.v6.ulFbDivDecFrac = cpu_to_le32(frac_fb_div * 100000);
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 8c0f9e36ff8e..645b84b3d203 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -627,6 +627,7 @@ struct radeon_dp_link_train_info {
        u8 train_set[4];
        u8 link_status[DP_LINK_STATUS_SIZE];
        u8 tries;
+        bool use_dpencoder;
 };
 static void radeon_dp_update_vs_emph(struct radeon_dp_link_train_info *dp_info)
@@ -646,7 +647,7 @@ static void radeon_dp_set_tp(struct radeon_dp_link_train_info *dp_info, int tp)
        int rtp = 0;
        /* set training pattern on the source */
-        if (ASIC_IS_DCE4(dp_info->rdev)) {
+        if (ASIC_IS_DCE4(dp_info->rdev) || !dp_info->use_dpencoder) {
                switch (tp) {
                case DP_TRAINING_PATTERN_1:
                        rtp = ATOM_ENCODER_CMD_DP_LINK_TRAINING_PATTERN1;
@@ -706,7 +707,7 @@ static int radeon_dp_link_train_init(struct radeon_dp_link_train_info *dp_info)
        radeon_write_dpcd_reg(dp_info->radeon_connector, DP_LINK_BW_SET, tmp);
        /* start training on the source */
-        if (ASIC_IS_DCE4(dp_info->rdev))
+        if (ASIC_IS_DCE4(dp_info->rdev) || !dp_info->use_dpencoder)
                atombios_dig_encoder_setup(dp_info->encoder,
                                           ATOM_ENCODER_CMD_DP_LINK_TRAINING_START, 0);
        else
@@ -731,7 +732,7 @@ static int radeon_dp_link_train_finish(struct radeon_dp_link_train_info *dp_info
                              DP_TRAINING_PATTERN_DISABLE);
        /* disable the training pattern on the source */
-        if (ASIC_IS_DCE4(dp_info->rdev))
+        if (ASIC_IS_DCE4(dp_info->rdev) || !dp_info->use_dpencoder)
                atombios_dig_encoder_setup(dp_info->encoder,
                                           ATOM_ENCODER_CMD_DP_LINK_TRAINING_COMPLETE, 0);
        else
@@ -869,7 +870,8 @@ void radeon_dp_link_train(struct drm_encoder *encoder,
        struct radeon_connector *radeon_connector;
        struct radeon_connector_atom_dig *dig_connector;
        struct radeon_dp_link_train_info dp_info;
-        u8 tmp;
+        int index;
+        u8 tmp, frev, crev;
        if (!radeon_encoder->enc_priv)
                return;
@@ -884,6 +886,18 @@ void radeon_dp_link_train(struct drm_encoder *encoder,
            (dig_connector->dp_sink_type != CONNECTOR_OBJECT_ID_eDP))
                return;
+        /* DPEncoderService newer than 1.1 can't program properly the
+         * training pattern. When facing such version use the
+         * DIGXEncoderControl (X== 1 | 2)
+         */
+        dp_info.use_dpencoder = true;
+        index = GetIndexIntoMasterTable(COMMAND, DPEncoderService);
+        if (atom_parse_cmd_header(rdev->mode_info.atom_context, index, &frev, &crev)) {
+                if (crev > 1) {
+                        dp_info.use_dpencoder = false;
+                }
+        }
        dp_info.enc_id = 0;
        if (dig->dig_encoder)
                dp_info.enc_id |= ATOM_DP_CONFIG_DIG2_ENCODER;
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 15bd0477a3e8..14dce9f22172 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1382,9 +1382,6 @@ int evergreen_cp_resume(struct radeon_device *rdev)
        /* set the wb address wether it's enabled or not */
        WREG32(CP_RB_RPTR_ADDR,
-#ifdef __BIG_ENDIAN
-               RB_RPTR_SWAP(2) |
-#endif
               ((rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC));
        WREG32(CP_RB_RPTR_ADDR_HI, upper_32_bits(rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFF);
        WREG32(SCRATCH_ADDR, ((rdev->wb.gpu_addr + RADEON_WB_SCRATCH_OFFSET) >> 8) & 0xFFFFFFFF);
@@ -2047,6 +2044,7 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
        rdev->config.evergreen.tile_config |=
                ((gb_addr_config & 0x30000000) >> 28) << 12;
+        rdev->config.evergreen.backend_map = gb_backend_map;
        WREG32(GB_BACKEND_MAP, gb_backend_map);
        WREG32(GB_ADDR_CONFIG, gb_addr_config);
        WREG32(DMIF_ADDR_CONFIG, gb_addr_config);
@@ -2761,6 +2759,9 @@ int evergreen_irq_process(struct radeon_device *rdev)
                return IRQ_NONE;
        }
 restart_ih:
+        /* Order reading of wptr vs. reading of IH ring data */
+        rmb();
        /* display interrupts */
        evergreen_irq_ack(rdev);
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 23d36417158d..189e86522b5b 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -856,7 +856,6 @@ static inline int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u3
        case SQ_PGM_START_PS:
        case SQ_PGM_START_HS:
        case SQ_PGM_START_LS:
-        case GDS_ADDR_BASE:
        case SQ_CONST_MEM_BASE:
        case SQ_ALU_CONST_CACHE_GS_0:
        case SQ_ALU_CONST_CACHE_GS_1:
@@ -946,6 +945,34 @@ static inline int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u3
                }
                ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
                break;
+        case SX_MEMORY_EXPORT_BASE:
+                if (p->rdev->family >= CHIP_CAYMAN) {
+                        dev_warn(p->dev, "bad SET_CONFIG_REG "
+                                 "0x%04X\n", reg);
+                        return -EINVAL;
+                }
+                r = evergreen_cs_packet_next_reloc(p, &reloc);
+                if (r) {
+                        dev_warn(p->dev, "bad SET_CONFIG_REG "
+                                        "0x%04X\n", reg);
+                        return -EINVAL;
+                }
+                ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+                break;
+        case CAYMAN_SX_SCATTER_EXPORT_BASE:
+                if (p->rdev->family < CHIP_CAYMAN) {
+                        dev_warn(p->dev, "bad SET_CONTEXT_REG "
+                                 "0x%04X\n", reg);
+                        return -EINVAL;
+                }
+                r = evergreen_cs_packet_next_reloc(p, &reloc);
+                if (r) {
+                        dev_warn(p->dev, "bad SET_CONTEXT_REG "
+                                        "0x%04X\n", reg);
+                        return -EINVAL;
+                }
+                ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+                break;
        default:
                dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
                return -EINVAL;
@@ -1153,6 +1180,34 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
                        return r;
                }
                break;
+        case PACKET3_DISPATCH_DIRECT:
+                if (pkt->count != 3) {
+                        DRM_ERROR("bad DISPATCH_DIRECT\n");
+                        return -EINVAL;
+                }
+                r = evergreen_cs_track_check(p);
+                if (r) {
+                        dev_warn(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx);
+                        return r;
+                }
+                break;
+        case PACKET3_DISPATCH_INDIRECT:
+                if (pkt->count != 1) {
+                        DRM_ERROR("bad DISPATCH_INDIRECT\n");
+                        return -EINVAL;
+                }
+                r = evergreen_cs_packet_next_reloc(p, &reloc);
+                if (r) {
+                        DRM_ERROR("bad DISPATCH_INDIRECT\n");
+                        return -EINVAL;
+                }
+                ib[idx+0] = idx_value + (u32)(reloc->lobj.gpu_offset & 0xffffffff);
+                r = evergreen_cs_track_check(p);
+                if (r) {
+                        dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
+                        return r;
+                }
+                break;
        case PACKET3_WAIT_REG_MEM:
                if (pkt->count != 5) {
                        DRM_ERROR("bad WAIT_REG_MEM\n");
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index b7b2714f0b32..7363d9dec909 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -351,6 +351,7 @@
 #define         COLOR_BUFFER_SIZE(x)                            ((x) << 0)
 #define         POSITION_BUFFER_SIZE(x)                         ((x) << 8)
 #define         SMX_BUFFER_SIZE(x)                              ((x) << 16)
+#define SX_MEMORY_EXPORT_BASE                           0x9010
 #define SX_MISC                                         0x28350
 #define CB_PERF_CTR0_SEL_0                              0x9A20
@@ -1122,6 +1123,7 @@
 #define CAYMAN_PA_SC_AA_CONFIG                          0x28BE0
 #define         CAYMAN_MSAA_NUM_SAMPLES_SHIFT           0
 #define         CAYMAN_MSAA_NUM_SAMPLES_MASK            0x7
+#define CAYMAN_SX_SCATTER_EXPORT_BASE                   0x28358
 /* cayman packet3 addition */
 #define CAYMAN_PACKET3_DEALLOC_STATE                    0x14
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 559dbd412906..44c4750f4518 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -833,6 +833,7 @@ static void cayman_gpu_init(struct radeon_device *rdev)
        rdev->config.cayman.tile_config |=
                ((gb_addr_config & ROW_SIZE_MASK) >> ROW_SIZE_SHIFT) << 12;
+        rdev->config.cayman.backend_map = gb_backend_map;
        WREG32(GB_BACKEND_MAP, gb_backend_map);
        WREG32(GB_ADDR_CONFIG, gb_addr_config);
        WREG32(DMIF_ADDR_CONFIG, gb_addr_config);
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index bc54b26cb32f..aa5571b73aa0 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1662,6 +1662,7 @@ void r600_gpu_init(struct radeon_device *rdev)
                                                                               R6XX_MAX_BACKENDS_MASK) >> 16)),
                                                        (cc_rb_backend_disable >> 16));
        rdev->config.r600.tile_config = tiling_config;
+        rdev->config.r600.backend_map = backend_map;
        tiling_config |= BACKEND_MAP(backend_map);
        WREG32(GB_TILING_CONFIG, tiling_config);
        WREG32(DCP_TILING_CONFIG, tiling_config & 0xffff);
@@ -2212,9 +2213,6 @@ int r600_cp_resume(struct radeon_device *rdev)
        /* set the wb address whether it's enabled or not */
        WREG32(CP_RB_RPTR_ADDR,
-#ifdef __BIG_ENDIAN
-               RB_RPTR_SWAP(2) |
-#endif
               ((rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC));
        WREG32(CP_RB_RPTR_ADDR_HI, upper_32_bits(rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFF);
        WREG32(SCRATCH_ADDR, ((rdev->wb.gpu_addr + RADEON_WB_SCRATCH_OFFSET) >> 8) & 0xFFFFFFFF);
@@ -2994,10 +2992,6 @@ int r600_irq_init(struct radeon_device *rdev)
        /* RPTR_REARM only works if msi's are enabled */
        if (rdev->msi_enabled)
                ih_cntl |= RPTR_REARM;
-#ifdef __BIG_ENDIAN
-        ih_cntl |= IH_MC_SWAP(IH_MC_SWAP_32BIT);
-#endif
        WREG32(IH_CNTL, ih_cntl);
        /* force the active interrupt state to all disabled */
@@ -3308,6 +3302,10 @@ int r600_irq_process(struct radeon_device *rdev)
        if (!rdev->ih.enabled || rdev->shutdown)
                return IRQ_NONE;
+        /* No MSIs, need a dummy read to flush PCI DMAs */
+        if (!rdev->msi_enabled)
+                RREG32(IH_RB_WPTR);
        wptr = r600_get_ih_wptr(rdev);
        rptr = rdev->ih.rptr;
        DRM_DEBUG("r600_irq_process start: rptr %d, wptr %d\n", rptr, wptr);
@@ -3320,6 +3318,9 @@ int r600_irq_process(struct radeon_device *rdev)
        }
 restart_ih:
+        /* Order reading of wptr vs. reading of IH ring data */
+        rmb();
        /* display interrupts */
        r600_irq_ack(rdev);
diff --git a/drivers/gpu/drm/radeon/r600_cp.c b/drivers/gpu/drm/radeon/r600_cp.c
index c3ab959bdc7c..45fd592f9606 100644
--- a/drivers/gpu/drm/radeon/r600_cp.c
+++ b/drivers/gpu/drm/radeon/r600_cp.c
@@ -1802,8 +1802,8 @@ static void r600_cp_init_ring_buffer(struct drm_device *dev,
        /* Set ring buffer size */
 #ifdef __BIG_ENDIAN
        RADEON_WRITE(R600_CP_RB_CNTL,
-                     RADEON_BUF_SWAP_32BIT |
+                     R600_BUF_SWAP_32BIT |
-                     RADEON_RB_NO_UPDATE |
+                     R600_RB_NO_UPDATE |
                     (dev_priv->ring.rptr_update_l2qw << 8) |
                     dev_priv->ring.size_l2qw);
 #else
@@ -1820,15 +1820,15 @@ static void r600_cp_init_ring_buffer(struct drm_device *dev,
 #ifdef __BIG_ENDIAN
        RADEON_WRITE(R600_CP_RB_CNTL,
-                     RADEON_BUF_SWAP_32BIT |
+                     R600_BUF_SWAP_32BIT |
-                     RADEON_RB_NO_UPDATE |
+                     R600_RB_NO_UPDATE |
-                     RADEON_RB_RPTR_WR_ENA |
+                     R600_RB_RPTR_WR_ENA |
                     (dev_priv->ring.rptr_update_l2qw << 8) |
                     dev_priv->ring.size_l2qw);
 #else
        RADEON_WRITE(R600_CP_RB_CNTL,
-                     RADEON_RB_NO_UPDATE |
+                     R600_RB_NO_UPDATE |
-                     RADEON_RB_RPTR_WR_ENA |
+                     R600_RB_RPTR_WR_ENA |
                     (dev_priv->ring.rptr_update_l2qw << 8) |
                     dev_priv->ring.size_l2qw);
 #endif
@@ -1851,13 +1851,8 @@ static void r600_cp_init_ring_buffer(struct drm_device *dev,
                        - ((unsigned long) dev->sg->virtual)
                        + dev_priv->gart_vm_start;
        }
-        RADEON_WRITE(R600_CP_RB_RPTR_ADDR,
+        RADEON_WRITE(R600_CP_RB_RPTR_ADDR, (rptr_addr & 0xfffffffc));
-#ifdef __BIG_ENDIAN
+        RADEON_WRITE(R600_CP_RB_RPTR_ADDR_HI, upper_32_bits(rptr_addr));
-                     (2 << 0) |
-#endif
-                     (rptr_addr & 0xfffffffc));
-        RADEON_WRITE(R600_CP_RB_RPTR_ADDR_HI,
-                     upper_32_bits(rptr_addr));
 #ifdef __BIG_ENDIAN
        RADEON_WRITE(R600_CP_RB_CNTL,
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 909bda8dd550..db8ef1905d5f 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -1200,6 +1200,15 @@ static inline int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx
                }
                ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
                break;
+        case SX_MEMORY_EXPORT_BASE:
+                r = r600_cs_packet_next_reloc(p, &reloc);
+                if (r) {
+                        dev_warn(p->dev, "bad SET_CONFIG_REG "
+                                        "0x%04X\n", reg);
+                        return -EINVAL;
+                }
+                ib[idx] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
+                break;
        default:
                dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
                return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index ef0e0e016914..ef37a9b5a3cc 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1003,6 +1003,7 @@ struct r600_asic {
        unsigned                tiling_npipes;
        unsigned                tiling_group_size;
        unsigned                tile_config;
+        unsigned                backend_map;
        struct r100_gpu_lockup  lockup;
 };
@@ -1028,6 +1029,7 @@ struct rv770_asic {
        unsigned                tiling_npipes;
        unsigned                tiling_group_size;
        unsigned                tile_config;
+        unsigned                backend_map;
        struct r100_gpu_lockup  lockup;
 };
@@ -1054,6 +1056,7 @@ struct evergreen_asic {
        unsigned tiling_npipes;
        unsigned tiling_group_size;
        unsigned tile_config;
+        unsigned backend_map;
        struct r100_gpu_lockup  lockup;
 };
@@ -1174,7 +1177,7 @@ struct radeon_device {
        /* Register mmio */
        resource_size_t                 rmmio_base;
        resource_size_t                 rmmio_size;
-        void                            *rmmio;
+        void __iomem                    *rmmio;
        radeon_rreg_t                   mc_rreg;
        radeon_wreg_t                   mc_wreg;
        radeon_rreg_t                   pll_rreg;
@@ -1251,20 +1254,20 @@ int radeon_gpu_wait_for_idle(struct radeon_device *rdev);
 static inline uint32_t r100_mm_rreg(struct radeon_device *rdev, uint32_t reg)
 {
        if (reg < rdev->rmmio_size)
-                return readl(((void __iomem *)rdev->rmmio) + reg);
+                return readl((rdev->rmmio) + reg);
        else {
-                writel(reg, ((void __iomem *)rdev->rmmio) + RADEON_MM_INDEX);
+                writel(reg, (rdev->rmmio) + RADEON_MM_INDEX);
-                return readl(((void __iomem *)rdev->rmmio) + RADEON_MM_DATA);
+                return readl((rdev->rmmio) + RADEON_MM_DATA);
        }
 }
 static inline void r100_mm_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v)
 {
        if (reg < rdev->rmmio_size)
-                writel(v, ((void __iomem *)rdev->rmmio) + reg);
+                writel(v, (rdev->rmmio) + reg);
        else {
-                writel(reg, ((void __iomem *)rdev->rmmio) + RADEON_MM_INDEX);
+                writel(reg, (rdev->rmmio) + RADEON_MM_INDEX);
-                writel(v, ((void __iomem *)rdev->rmmio) + RADEON_MM_DATA);
+                writel(v, (rdev->rmmio) + RADEON_MM_DATA);
        }
 }
@@ -1296,10 +1299,10 @@ static inline void r100_io_wreg(struct radeon_device *rdev, u32 reg, u32 v)
 /*
 * Registers read & write functions.
 */
-#define RREG8(reg) readb(((void __iomem *)rdev->rmmio) + (reg))
+#define RREG8(reg) readb((rdev->rmmio) + (reg))
-#define WREG8(reg, v) writeb(v, ((void __iomem *)rdev->rmmio) + (reg))
+#define WREG8(reg, v) writeb(v, (rdev->rmmio) + (reg))
-#define RREG16(reg) readw(((void __iomem *)rdev->rmmio) + (reg))
+#define RREG16(reg) readw((rdev->rmmio) + (reg))
-#define WREG16(reg, v) writew(v, ((void __iomem *)rdev->rmmio) + (reg))
+#define WREG16(reg, v) writew(v, (rdev->rmmio) + (reg))
 #define RREG32(reg) r100_mm_rreg(rdev, (reg))
 #define DREG32(reg) printk(KERN_INFO "REGISTER: " #reg " : 0x%08X\n", r100_mm_rreg(rdev, (reg)))
 #define WREG32(reg, v) r100_mm_wreg(rdev, (reg), (v))
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index b2449629537d..df8218bb83a6 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -625,7 +625,7 @@ static struct radeon_asic r600_asic = {
        .fence_ring_emit = &r600_fence_ring_emit,
        .cs_parse = &r600_cs_parse,
        .copy_blit = &r600_copy_blit,
-        .copy_dma = &r600_copy_blit,
+        .copy_dma = NULL,
        .copy = &r600_copy_blit,
        .get_engine_clock = &radeon_atom_get_engine_clock,
        .set_engine_clock = &radeon_atom_set_engine_clock,
@@ -672,7 +672,7 @@ static struct radeon_asic rs780_asic = {
        .fence_ring_emit = &r600_fence_ring_emit,
        .cs_parse = &r600_cs_parse,
        .copy_blit = &r600_copy_blit,
-        .copy_dma = &r600_copy_blit,
+        .copy_dma = NULL,
        .copy = &r600_copy_blit,
        .get_engine_clock = &radeon_atom_get_engine_clock,
        .set_engine_clock = &radeon_atom_set_engine_clock,
@@ -719,7 +719,7 @@ static struct radeon_asic rv770_asic = {
        .fence_ring_emit = &r600_fence_ring_emit,
        .cs_parse = &r600_cs_parse,
        .copy_blit = &r600_copy_blit,
-        .copy_dma = &r600_copy_blit,
+        .copy_dma = NULL,
        .copy = &r600_copy_blit,
        .get_engine_clock = &radeon_atom_get_engine_clock,
        .set_engine_clock = &radeon_atom_set_engine_clock,
@@ -766,7 +766,7 @@ static struct radeon_asic evergreen_asic = {
        .fence_ring_emit = &r600_fence_ring_emit,
        .cs_parse = &evergreen_cs_parse,
        .copy_blit = &evergreen_copy_blit,
-        .copy_dma = &evergreen_copy_blit,
+        .copy_dma = NULL,
        .copy = &evergreen_copy_blit,
        .get_engine_clock = &radeon_atom_get_engine_clock,
        .set_engine_clock = &radeon_atom_set_engine_clock,
@@ -813,7 +813,7 @@ static struct radeon_asic sumo_asic = {
        .fence_ring_emit = &r600_fence_ring_emit,
        .cs_parse = &evergreen_cs_parse,
        .copy_blit = &evergreen_copy_blit,
-        .copy_dma = &evergreen_copy_blit,
+        .copy_dma = NULL,
        .copy = &evergreen_copy_blit,
        .get_engine_clock = &radeon_atom_get_engine_clock,
        .set_engine_clock = &radeon_atom_set_engine_clock,
@@ -860,7 +860,7 @@ static struct radeon_asic btc_asic = {
        .fence_ring_emit = &r600_fence_ring_emit,
        .cs_parse = &evergreen_cs_parse,
        .copy_blit = &evergreen_copy_blit,
-        .copy_dma = &evergreen_copy_blit,
+        .copy_dma = NULL,
        .copy = &evergreen_copy_blit,
        .get_engine_clock = &radeon_atom_get_engine_clock,
        .set_engine_clock = &radeon_atom_set_engine_clock,
@@ -907,7 +907,7 @@ static struct radeon_asic cayman_asic = {
        .fence_ring_emit = &r600_fence_ring_emit,
        .cs_parse = &evergreen_cs_parse,
        .copy_blit = &evergreen_copy_blit,
-        .copy_dma = &evergreen_copy_blit,
+        .copy_dma = NULL,
        .copy = &evergreen_copy_blit,
        .get_engine_clock = &radeon_atom_get_engine_clock,
        .set_engine_clock = &radeon_atom_set_engine_clock,
diff --git a/drivers/gpu/drm/radeon/radeon_clocks.c b/drivers/gpu/drm/radeon/radeon_clocks.c
index 2d48e7a1474b..dcd0863e31ae 100644
--- a/drivers/gpu/drm/radeon/radeon_clocks.c
+++ b/drivers/gpu/drm/radeon/radeon_clocks.c
@@ -96,7 +96,7 @@ uint32_t radeon_legacy_get_memory_clock(struct radeon_device *rdev)
 * Read XTAL (ref clock), SCLK and MCLK from Open Firmware device
 * tree. Hopefully, ATI OF driver is kind enough to fill these
 */
-static bool __devinit radeon_read_clocks_OF(struct drm_device *dev)
+static bool radeon_read_clocks_OF(struct drm_device *dev)
 {
        struct radeon_device *rdev = dev->dev_private;
        struct device_node *dp = rdev->pdev->dev.of_node;
@@ -166,7 +166,7 @@ static bool __devinit radeon_read_clocks_OF(struct drm_device *dev)
        return true;
 }
 #else
-static bool __devinit radeon_read_clocks_OF(struct drm_device *dev)
+static bool radeon_read_clocks_OF(struct drm_device *dev)
 {
        return false;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index e4594676a07c..a74217cd192f 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -779,7 +779,8 @@ void radeon_combios_i2c_init(struct radeon_device *rdev)
                                }
                        }
                }
-        } else if (rdev->family >= CHIP_R200) {
+        } else if ((rdev->family == CHIP_R200) ||
+                   (rdev->family >= CHIP_R300)) {
                /* 0x68 */
                i2c = combios_setup_i2c_bus(rdev, DDC_MONID, 0, 0);
                rdev->i2c_bus[3] = radeon_i2c_create(dev, &i2c, "MONID");
diff --git a/drivers/gpu/drm/radeon/radeon_cp.c b/drivers/gpu/drm/radeon/radeon_cp.c
index 75867792a4e2..045ec59478f9 100644
--- a/drivers/gpu/drm/radeon/radeon_cp.c
+++ b/drivers/gpu/drm/radeon/radeon_cp.c
@@ -2115,7 +2115,7 @@ int radeon_driver_load(struct drm_device *dev, unsigned long flags)
        if (drm_pci_device_is_agp(dev))
                dev_priv->flags |= RADEON_IS_AGP;
-        else if (drm_pci_device_is_pcie(dev))
+        else if (pci_is_pcie(dev->pdev))
                dev_priv->flags |= RADEON_IS_PCIE;
        else
                dev_priv->flags |= RADEON_IS_PCI;
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 292f73f0ddbd..28f4655905bc 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -282,7 +282,7 @@ void radeon_crtc_handle_flip(struct radeon_device *rdev, int crtc_id)
        spin_lock_irqsave(&rdev->ddev->event_lock, flags);
        work = radeon_crtc->unpin_work;
        if (work == NULL ||
-            !radeon_fence_signaled(work->fence)) {
+            (work->fence && !radeon_fence_signaled(work->fence))) {
                spin_unlock_irqrestore(&rdev->ddev->event_lock, flags);
                return;
        }
@@ -348,7 +348,6 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
        struct radeon_framebuffer *new_radeon_fb;
        struct drm_gem_object *obj;
        struct radeon_bo *rbo;
-        struct radeon_fence *fence;
        struct radeon_unpin_work *work;
        unsigned long flags;
        u32 tiling_flags, pitch_pixels;
@@ -359,16 +358,9 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
        if (work == NULL)
                return -ENOMEM;
-        r = radeon_fence_create(rdev, &fence);
-        if (unlikely(r != 0)) {
-                kfree(work);
-                DRM_ERROR("flip queue: failed to create fence.\n");
-                return -ENOMEM;
-        }
        work->event = event;
        work->rdev = rdev;
        work->crtc_id = radeon_crtc->crtc_id;
-        work->fence = radeon_fence_ref(fence);
        old_radeon_fb = to_radeon_framebuffer(crtc->fb);
        new_radeon_fb = to_radeon_framebuffer(fb);
        /* schedule unpin of the old buffer */
@@ -377,6 +369,10 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
        drm_gem_object_reference(obj);
        rbo = gem_to_radeon_bo(obj);
        work->old_rbo = rbo;
+        obj = new_radeon_fb->obj;
+        rbo = gem_to_radeon_bo(obj);
+        if (rbo->tbo.sync_obj)
+                work->fence = radeon_fence_ref(rbo->tbo.sync_obj);
        INIT_WORK(&work->work, radeon_unpin_work_func);
        /* We borrow the event spin lock for protecting unpin_work */
@@ -391,9 +387,6 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
        spin_unlock_irqrestore(&dev->event_lock, flags);
        /* pin the new buffer */
-        obj = new_radeon_fb->obj;
-        rbo = gem_to_radeon_bo(obj);
        DRM_DEBUG_DRIVER("flip-ioctl() cur_fbo = %p, cur_bbo = %p\n",
                         work->old_rbo, rbo);
@@ -461,37 +454,18 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
                goto pflip_cleanup1;
        }
-        /* 32 ought to cover us */
-        r = radeon_ring_lock(rdev, 32);
-        if (r) {
-                DRM_ERROR("failed to lock the ring before flip\n");
-                goto pflip_cleanup2;
-        }
-        /* emit the fence */
-        radeon_fence_emit(rdev, fence);
        /* set the proper interrupt */
        radeon_pre_page_flip(rdev, radeon_crtc->crtc_id);
-        /* fire the ring */
-        radeon_ring_unlock_commit(rdev);
        return 0;
-pflip_cleanup2:
-        drm_vblank_put(dev, radeon_crtc->crtc_id);
 pflip_cleanup1:
-        r = radeon_bo_reserve(rbo, false);
+        if (unlikely(radeon_bo_reserve(rbo, false) != 0)) {
-        if (unlikely(r != 0)) {
                DRM_ERROR("failed to reserve new rbo in error path\n");
                goto pflip_cleanup;
        }
-        r = radeon_bo_unpin(rbo);
+        if (unlikely(radeon_bo_unpin(rbo) != 0)) {
-        if (unlikely(r != 0)) {
-                radeon_bo_unreserve(rbo);
-                r = -EINVAL;
                DRM_ERROR("failed to unpin new rbo in error path\n");
-                goto pflip_cleanup;
        }
        radeon_bo_unreserve(rbo);
@@ -501,7 +475,7 @@ pflip_cleanup:
 unlock_free:
        drm_gem_object_unreference_unlocked(old_radeon_fb->obj);
        spin_unlock_irqrestore(&dev->event_lock, flags);
-        radeon_fence_unref(&fence);
+        radeon_fence_unref(&work->fence);
        kfree(work);
        return r;
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 73dfbe8e5f9e..85f033f19a8a 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -50,10 +50,11 @@
 *   2.7.0 - fixups for r600 2D tiling support. (no external ABI change), add eg dyn gpr regs
 *   2.8.0 - pageflip support, r500 US_FORMAT regs. r500 ARGB2101010 colorbuf, r300->r500 CMASK, clock crystal query
 *   2.9.0 - r600 tiling (s3tc,rgtc) working, SET_PREDICATION packet 3 on r600 + eg, backend query
- *   2.10.0 - fusion 2D tiling
+ *   2.10.0 - fusion 2D tiling, initial compute support for the CS checker
+ *   2.11.0 - backend map
 */
 #define KMS_DRIVER_MAJOR        2
-#define KMS_DRIVER_MINOR        10
+#define KMS_DRIVER_MINOR        11
 #define KMS_DRIVER_PATCHLEVEL   0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index bd58af658581..be2c1224e68a 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -60,7 +60,7 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags)
        /* update BUS flag */
        if (drm_pci_device_is_agp(dev)) {
                flags |= RADEON_IS_AGP;
-        } else if (drm_pci_device_is_pcie(dev)) {
+        } else if (pci_is_pcie(dev->pdev)) {
                flags |= RADEON_IS_PCIE;
        } else {
                flags |= RADEON_IS_PCI;
@@ -237,6 +237,19 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
        case RADEON_INFO_FUSION_GART_WORKING:
                value = 1;
                break;
+        case RADEON_INFO_BACKEND_MAP:
+                if (rdev->family >= CHIP_CAYMAN)
+                        value = rdev->config.cayman.backend_map;
+                else if (rdev->family >= CHIP_CEDAR)
+                        value = rdev->config.evergreen.backend_map;
+                else if (rdev->family >= CHIP_RV770)
+                        value = rdev->config.rv770.backend_map;
+                else if (rdev->family >= CHIP_R600)
+                        value = rdev->config.r600.backend_map;
+                else {
+                        return -EINVAL;
+                }
+                break;
        default:
                DRM_DEBUG_KMS("Invalid request %d\n", info->request);
                return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index aaa19dc418a0..6fabe89fa6a1 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -594,6 +594,9 @@ int radeon_pm_init(struct radeon_device *rdev)
                        if (rdev->pm.default_vddc)
                                radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
                                                        SET_VOLTAGE_TYPE_ASIC_VDDC);
+                        if (rdev->pm.default_vddci)
+                                radeon_atom_set_voltage(rdev, rdev->pm.default_vddci,
+                                                        SET_VOLTAGE_TYPE_ASIC_VDDCI);
                        if (rdev->pm.default_sclk)
                                radeon_set_engine_clock(rdev, rdev->pm.default_sclk);
                        if (rdev->pm.default_mclk)
diff --git a/drivers/gpu/drm/radeon/radeon_reg.h b/drivers/gpu/drm/radeon/radeon_reg.h
index bc44a3d35ec6..b4ce86455707 100644
--- a/drivers/gpu/drm/radeon/radeon_reg.h
+++ b/drivers/gpu/drm/radeon/radeon_reg.h
@@ -3295,7 +3295,7 @@
 #       define RADEON_RB_BUFSZ_MASK             (0x3f << 0)
 #       define RADEON_RB_BLKSZ_SHIFT            8
 #       define RADEON_RB_BLKSZ_MASK             (0x3f << 8)
-#       define RADEON_BUF_SWAP_32BIT            (1 << 17)
+#       define RADEON_BUF_SWAP_32BIT            (2 << 16)
 #       define RADEON_MAX_FETCH_SHIFT           18
 #       define RADEON_MAX_FETCH_MASK            (0x3 << 18)
 #       define RADEON_RB_NO_UPDATE              (1 << 27)
diff --git a/drivers/gpu/drm/radeon/reg_srcs/cayman b/drivers/gpu/drm/radeon/reg_srcs/cayman
index 0aa8e85a9457..2316977eb924 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/cayman
+++ b/drivers/gpu/drm/radeon/reg_srcs/cayman
@@ -208,6 +208,7 @@ cayman 0x9400
 0x0002834C PA_SC_VPORT_ZMAX_15
 0x00028350 SX_MISC
 0x00028354 SX_SURFACE_SYNC
+0x0002835C SX_SCATTER_EXPORT_SIZE
 0x00028380 SQ_VTX_SEMANTIC_0
 0x00028384 SQ_VTX_SEMANTIC_1
 0x00028388 SQ_VTX_SEMANTIC_2
@@ -432,6 +433,7 @@ cayman 0x9400
 0x00028700 SPI_STACK_MGMT
 0x00028704 SPI_WAVE_MGMT_1
 0x00028708 SPI_WAVE_MGMT_2
+0x00028720 GDS_ADDR_BASE
 0x00028724 GDS_ADDR_SIZE
 0x00028780 CB_BLEND0_CONTROL
 0x00028784 CB_BLEND1_CONTROL
diff --git a/drivers/gpu/drm/radeon/reg_srcs/evergreen b/drivers/gpu/drm/radeon/reg_srcs/evergreen
index 0e28cae7ea43..161737a28c23 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/evergreen
+++ b/drivers/gpu/drm/radeon/reg_srcs/evergreen
@@ -44,6 +44,7 @@ evergreen 0x9400
 0x00008E28 SQ_STATIC_THREAD_MGMT_3
 0x00008E2C SQ_LDS_RESOURCE_MGMT
 0x00008E48 SQ_EX_ALLOC_TABLE_SLOTS
+0x00009014 SX_MEMORY_EXPORT_SIZE
 0x00009100 SPI_CONFIG_CNTL
 0x0000913C SPI_CONFIG_CNTL_1
 0x00009508 TA_CNTL_AUX
@@ -442,7 +443,9 @@ evergreen 0x9400
 0x000286EC SPI_COMPUTE_NUM_THREAD_X
 0x000286F0 SPI_COMPUTE_NUM_THREAD_Y
 0x000286F4 SPI_COMPUTE_NUM_THREAD_Z
+0x00028720 GDS_ADDR_BASE
 0x00028724 GDS_ADDR_SIZE
+0x00028728 GDS_ORDERED_WAVE_PER_SE
 0x00028780 CB_BLEND0_CONTROL
 0x00028784 CB_BLEND1_CONTROL
 0x00028788 CB_BLEND2_CONTROL
diff --git a/drivers/gpu/drm/radeon/reg_srcs/r600 b/drivers/gpu/drm/radeon/reg_srcs/r600
index ea49752ee99c..0380c5c15f80 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/r600
+++ b/drivers/gpu/drm/radeon/reg_srcs/r600
@@ -429,6 +429,7 @@ r600 0x9400
 0x00028438 SX_ALPHA_REF
 0x00028410 SX_ALPHA_TEST_CONTROL
 0x00028350 SX_MISC
+0x00009014 SX_MEMORY_EXPORT_SIZE
 0x00009604 TC_INVALIDATE
 0x00009400 TD_FILTER4
 0x00009404 TD_FILTER4_1
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 1f5850e473cc..4b5d0e6974a8 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -530,7 +530,7 @@ int rs600_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr)
        addr = addr & 0xFFFFFFFFFFFFF000ULL;
        addr |= R600_PTE_VALID | R600_PTE_SYSTEM | R600_PTE_SNOOPED;
        addr |= R600_PTE_READABLE | R600_PTE_WRITEABLE;
-        writeq(addr, ((void __iomem *)ptr) + (i * 8));
+        writeq(addr, ptr + (i * 8));
        return 0;
 }
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 4de51891aa6d..4720d000d440 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -778,6 +778,7 @@ static void rv770_gpu_init(struct radeon_device *rdev)
                                                                (cc_rb_backend_disable >> 16));
        rdev->config.rv770.tile_config = gb_tiling_config;
+        rdev->config.rv770.backend_map = backend_map;
        gb_tiling_config |= BACKEND_MAP(backend_map);
        WREG32(GB_TILING_CONFIG, gb_tiling_config);