29 files changed, 278 insertions, 79 deletions

diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 41c69469ce20..971d796e071d 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -26,6 +26,7 @@ config DW_APB_TIMER_OF
 
 config ARMADA_370_XP_TIMER
         bool
+        select CLKSRC_OF
 
 config ORION_TIMER
         select CLKSRC_OF
diff --git a/drivers/clocksource/clksrc-of.c b/drivers/clocksource/clksrc-of.c
index 37f5325bec95..b9ddd9e3a2f5 100644
--- a/drivers/clocksource/clksrc-of.c
+++ b/drivers/clocksource/clksrc-of.c
@@ -30,6 +30,9 @@ void __init clocksource_of_init(void)
         clocksource_of_init_fn init_func;
 
         for_each_matching_node_and_match(np, __clksrc_of_table, &match) {
+                if (!of_device_is_available(np))
+                        continue;
+
                 init_func = match->data;
                 init_func(np);
         }
diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c
index b9c81b7c3a3b..3a5909c12d42 100644
--- a/drivers/clocksource/em_sti.c
+++ b/drivers/clocksource/em_sti.c
@@ -301,7 +301,7 @@ static void em_sti_register_clockevent(struct em_sti_priv *p)
         ced->name = dev_name(&p->pdev->dev);
         ced->features = CLOCK_EVT_FEAT_ONESHOT;
         ced->rating = 200;
-        ced->cpumask = cpumask_of(0);
+        ced->cpumask = cpu_possible_mask;
         ced->set_next_event = em_sti_clock_event_next;
         ced->set_mode = em_sti_clock_event_mode;
 
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 5b34768f4d7c..62b0de6a1837 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -428,7 +428,6 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt)
                                 evt->irq);
                         return -EIO;
                 }
-                irq_set_affinity(evt->irq, cpumask_of(cpu));
         } else {
                 enable_percpu_irq(mct_irqs[MCT_L0_IRQ], 0);
         }
@@ -449,6 +448,7 @@ static int exynos4_mct_cpu_notify(struct notifier_block *self,
                                            unsigned long action, void *hcpu)
 {
         struct mct_clock_event_device *mevt;
+        unsigned int cpu;
 
         /*
          * Grab cpu pointer in each case to avoid spurious
@@ -459,6 +459,12 @@ static int exynos4_mct_cpu_notify(struct notifier_block *self,
                 mevt = this_cpu_ptr(&percpu_mct_tick);
                 exynos4_local_timer_setup(&mevt->evt);
                 break;
+        case CPU_ONLINE:
+                cpu = (unsigned long)hcpu;
+                if (mct_int_type == MCT_INT_SPI)
+                        irq_set_affinity(mct_irqs[MCT_L0_IRQ + cpu],
+                                                cpumask_of(cpu));
+                break;
         case CPU_DYING:
                 mevt = this_cpu_ptr(&percpu_mct_tick);
                 exynos4_local_timer_stop(&mevt->evt);
@@ -500,6 +506,8 @@ static void __init exynos4_timer_resources(struct device_node *np, void __iomem
                                          &percpu_mct_tick);
                 WARN(err, "MCT: can't request IRQ %d (%d)\n",
                      mct_irqs[MCT_L0_IRQ], err);
+        } else {
+                irq_set_affinity(mct_irqs[MCT_L0_IRQ], cpumask_of(0));
         }
 
         err = register_cpu_notifier(&exynos4_mct_cpu_nb);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index df9253d890ee..cdfb9da0e4ce 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4800,10 +4800,10 @@ i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc)
 
         if (!mutex_trylock(&dev->struct_mutex)) {
                 if (!mutex_is_locked_by(&dev->struct_mutex, current))
-                        return SHRINK_STOP;
+                        return 0;
 
                 if (dev_priv->mm.shrinker_no_lock_stealing)
-                        return SHRINK_STOP;
+                        return 0;
 
                 unlock = false;
         }
@@ -4901,10 +4901,10 @@ i915_gem_inactive_scan(struct shrinker *shrinker, struct shrink_control *sc)
 
         if (!mutex_trylock(&dev->struct_mutex)) {
                 if (!mutex_is_locked_by(&dev->struct_mutex, current))
-                        return 0;
+                        return SHRINK_STOP;
 
                 if (dev_priv->mm.shrinker_no_lock_stealing)
-                        return 0;
+                        return SHRINK_STOP;
 
                 unlock = false;
         }
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index aba9d7498996..dae364f0028c 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -143,8 +143,10 @@ static void i915_error_vprintf(struct drm_i915_error_state_buf *e,
 
         /* Seek the first printf which is hits start position */
         if (e->pos < e->start) {
-                len = vsnprintf(NULL, 0, f, args);
-                if (!__i915_error_seek(e, len))
+                va_list tmp;
+
+                va_copy(tmp, args);
+                if (!__i915_error_seek(e, vsnprintf(NULL, 0, f, tmp)))
                         return;
         }
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index d8a1d98693e7..e5822e79f912 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -4775,6 +4775,10 @@ static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc)
 
         pipeconf = 0;
 
+        if (dev_priv->quirks & QUIRK_PIPEA_FORCE &&
+            I915_READ(PIPECONF(intel_crtc->pipe)) & PIPECONF_ENABLE)
+                pipeconf |= PIPECONF_ENABLE;
+
         if (intel_crtc->pipe == 0 && INTEL_INFO(dev)->gen < 4) {
                 /* Enable pixel doubling when the dot clock is > 90% of the (display)
                  * core speed.
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 2151d13772b8..79c14e298ba6 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -588,7 +588,18 @@ intel_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode,
                         DRM_DEBUG_KMS("aux_ch native nack\n");
                         return -EREMOTEIO;
                 case AUX_NATIVE_REPLY_DEFER:
-                        udelay(100);
+                        /*
+                         * For now, just give more slack to branch devices. We
+                         * could check the DPCD for I2C bit rate capabilities,
+                         * and if available, adjust the interval. We could also
+                         * be more careful with DP-to-Legacy adapters where a
+                         * long legacy cable may force very low I2C bit rates.
+                         */
+                        if (intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] &
+                            DP_DWN_STRM_PORT_PRESENT)
+                                usleep_range(500, 600);
+                        else
+                                usleep_range(300, 400);
                         continue;
                 default:
                         DRM_ERROR("aux_ch invalid native reply 0x%02x\n",
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index f2c6d7909ae2..dd6f84bf6c22 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -916,6 +916,14 @@ intel_tv_compute_config(struct intel_encoder *encoder,
         DRM_DEBUG_KMS("forcing bpc to 8 for TV\n");
         pipe_config->pipe_bpp = 8*3;
 
+        /* TV has it's own notion of sync and other mode flags, so clear them. */
+        pipe_config->adjusted_mode.flags = 0;
+
+        /*
+         * FIXME: We don't check whether the input mode is actually what we want
+         * or whether userspace is doing something stupid.
+         */
+
         return true;
 }
 
diff --git a/drivers/gpu/drm/msm/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/mdp4/mdp4_kms.c
index 5db5bbaedae2..bc7fd11ad8be 100644
--- a/drivers/gpu/drm/msm/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/mdp4/mdp4_kms.c
@@ -19,8 +19,6 @@
 #include "msm_drv.h"
 #include "mdp4_kms.h"
 
-#include <mach/iommu.h>
-
 static struct mdp4_platform_config *mdp4_get_config(struct platform_device *dev);
 
 static int mdp4_hw_init(struct msm_kms *kms)
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 008d772384c7..b3a2f1629041 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -18,8 +18,6 @@
 #include "msm_drv.h"
 #include "msm_gpu.h"
 
-#include <mach/iommu.h>
-
 static void msm_fb_output_poll_changed(struct drm_device *dev)
 {
         struct msm_drm_private *priv = dev->dev_private;
@@ -62,6 +60,8 @@ int msm_iommu_attach(struct drm_device *dev, struct iommu_domain *iommu,
         int i, ret;
 
         for (i = 0; i < cnt; i++) {
+                /* TODO maybe some day msm iommu won't require this hack: */
+                struct device *msm_iommu_get_ctx(const char *ctx_name);
                 struct device *ctx = msm_iommu_get_ctx(names[i]);
                 if (!ctx)
                         continue;
@@ -199,7 +199,7 @@ static int msm_load(struct drm_device *dev, unsigned long flags)
                  * imx drm driver on iMX5
                  */
                 dev_err(dev->dev, "failed to load kms\n");
-                ret = PTR_ERR(priv->kms);
+                ret = PTR_ERR(kms);
                 goto fail;
         }
 
@@ -697,7 +697,7 @@ static struct drm_driver msm_driver = {
         .gem_vm_ops         = &vm_ops,
         .dumb_create        = msm_gem_dumb_create,
         .dumb_map_offset    = msm_gem_dumb_map_offset,
-        .dumb_destroy       = msm_gem_dumb_destroy,
+        .dumb_destroy       = drm_gem_dumb_destroy,
 #ifdef CONFIG_DEBUG_FS
         .debugfs_init       = msm_debugfs_init,
         .debugfs_cleanup    = msm_debugfs_cleanup,
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 29eacfa29cfb..2bae46c66a30 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -319,13 +319,6 @@ int msm_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
                         MSM_BO_SCANOUT | MSM_BO_WC, &args->handle);
 }
 
-int msm_gem_dumb_destroy(struct drm_file *file, struct drm_device *dev,
-                uint32_t handle)
-{
-        /* No special work needed, drop the reference and see what falls out */
-        return drm_gem_handle_delete(file, handle);
-}
-
 int msm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev,
                 uint32_t handle, uint64_t *offset)
 {
diff --git a/drivers/gpu/drm/radeon/btc_dpm.c b/drivers/gpu/drm/radeon/btc_dpm.c
index 05ff315e8e9e..b162e98a2953 100644
--- a/drivers/gpu/drm/radeon/btc_dpm.c
+++ b/drivers/gpu/drm/radeon/btc_dpm.c
@@ -1168,6 +1168,23 @@ 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)
 {
@@ -2080,6 +2097,7 @@ static void btc_apply_state_adjust_rules(struct radeon_device *rdev,
         bool disable_mclk_switching;
         u32 mclk, sclk;
         u16 vddc, vddci;
+        u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
 
         if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
             btc_dpm_vblank_too_short(rdev))
@@ -2121,6 +2139,39 @@ static void btc_apply_state_adjust_rules(struct radeon_device *rdev,
                         ps->low.vddci = max_limits->vddci;
         }
 
+        /* 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);
+
+        if (max_sclk_vddc) {
+                if (ps->low.sclk > max_sclk_vddc)
+                        ps->low.sclk = max_sclk_vddc;
+                if (ps->medium.sclk > max_sclk_vddc)
+                        ps->medium.sclk = max_sclk_vddc;
+                if (ps->high.sclk > max_sclk_vddc)
+                        ps->high.sclk = max_sclk_vddc;
+        }
+        if (max_mclk_vddci) {
+                if (ps->low.mclk > max_mclk_vddci)
+                        ps->low.mclk = max_mclk_vddci;
+                if (ps->medium.mclk > max_mclk_vddci)
+                        ps->medium.mclk = max_mclk_vddci;
+                if (ps->high.mclk > max_mclk_vddci)
+                        ps->high.mclk = max_mclk_vddci;
+        }
+        if (max_mclk_vddc) {
+                if (ps->low.mclk > max_mclk_vddc)
+                        ps->low.mclk = max_mclk_vddc;
+                if (ps->medium.mclk > max_mclk_vddc)
+                        ps->medium.mclk = max_mclk_vddc;
+                if (ps->high.mclk > max_mclk_vddc)
+                        ps->high.mclk = max_mclk_vddc;
+        }
+
         /* XXX validate the min clocks required for display */
 
         if (disable_mclk_switching) {
diff --git a/drivers/gpu/drm/radeon/btc_dpm.h b/drivers/gpu/drm/radeon/btc_dpm.h
index 1a15e0e41950..3b6f12b7760b 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 899627443030..51e947a97edf 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -146,6 +146,8 @@ static const struct ci_pt_config_reg didt_config_ci[] =
 };
 
 extern u8 rv770_get_memory_module_index(struct radeon_device *rdev);
+extern void btc_get_max_clock_from_voltage_dependency_table(struct radeon_clock_voltage_dependency_table *table,
+                                                            u32 *max_clock);
 extern int ni_copy_and_switch_arb_sets(struct radeon_device *rdev,
                                        u32 arb_freq_src, u32 arb_freq_dest);
 extern u8 si_get_ddr3_mclk_frequency_ratio(u32 memory_clock);
@@ -712,6 +714,7 @@ static void ci_apply_state_adjust_rules(struct radeon_device *rdev,
         struct radeon_clock_and_voltage_limits *max_limits;
         bool disable_mclk_switching;
         u32 sclk, mclk;
+        u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
         int i;
 
         if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
@@ -739,6 +742,29 @@ static void ci_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/cik.c b/drivers/gpu/drm/radeon/cik.c
index adbdb6503b05..d02fd1c045d5 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -2845,10 +2845,8 @@ static void cik_gpu_init(struct radeon_device *rdev)
                 rdev->config.cik.tile_config |= (3 << 0);
                 break;
         }
-        if ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT)
-                rdev->config.cik.tile_config |= 1 << 4;
-        else
-                rdev->config.cik.tile_config |= 0 << 4;
+        rdev->config.cik.tile_config |=
+                ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) << 4;
         rdev->config.cik.tile_config |=
                 ((gb_addr_config & PIPE_INTERLEAVE_SIZE_MASK) >> PIPE_INTERLEAVE_SIZE_SHIFT) << 8;
         rdev->config.cik.tile_config |=
@@ -4456,8 +4454,8 @@ static int cik_mc_init(struct radeon_device *rdev)
         rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0);
         rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0);
         /* size in MB on si */
-        rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024;
-        rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024;
+        rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
+        rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
         rdev->mc.visible_vram_size = rdev->mc.aper_size;
         si_vram_gtt_location(rdev, &rdev->mc);
         radeon_update_bandwidth_info(rdev);
@@ -4735,12 +4733,13 @@ static void cik_vm_decode_fault(struct radeon_device *rdev,
         u32 mc_id = (status & MEMORY_CLIENT_ID_MASK) >> MEMORY_CLIENT_ID_SHIFT;
         u32 vmid = (status & FAULT_VMID_MASK) >> FAULT_VMID_SHIFT;
         u32 protections = (status & PROTECTIONS_MASK) >> PROTECTIONS_SHIFT;
-        char *block = (char *)&mc_client;
+        char block[5] = { mc_client >> 24, (mc_client >> 16) & 0xff,
+                (mc_client >> 8) & 0xff, mc_client & 0xff, 0 };
 
-        printk("VM fault (0x%02x, vmid %d) at page %u, %s from %s (%d)\n",
+        printk("VM fault (0x%02x, vmid %d) at page %u, %s from '%s' (0x%08x) (%d)\n",
                protections, vmid, addr,
                (status & MEMORY_CLIENT_RW_MASK) ? "write" : "read",
-               block, mc_id);
+               block, mc_client, mc_id);
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index 6c398a456d78..f26339028154 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -787,6 +787,7 @@ static void ni_apply_state_adjust_rules(struct radeon_device *rdev,
         bool disable_mclk_switching;
         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) ||
@@ -813,6 +814,29 @@ static void ni_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/r100.c b/drivers/gpu/drm/radeon/r100.c
index 24175717307b..d71333033b2b 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -2933,9 +2933,11 @@ static int r100_debugfs_cp_ring_info(struct seq_file *m, void *data)
         seq_printf(m, "CP_RB_RPTR 0x%08x\n", rdp);
         seq_printf(m, "%u free dwords in ring\n", ring->ring_free_dw);
         seq_printf(m, "%u dwords in ring\n", count);
-        for (j = 0; j <= count; j++) {
-                i = (rdp + j) & ring->ptr_mask;
-                seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
+        if (ring->ready) {
+                for (j = 0; j <= count; j++) {
+                        i = (rdp + j) & ring->ptr_mask;
+                        seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
+                }
         }
         return 0;
 }
diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c
index e65f211a7be0..5513d8f06252 100644
--- a/drivers/gpu/drm/radeon/r600_dpm.c
+++ b/drivers/gpu/drm/radeon/r600_dpm.c
@@ -1084,7 +1084,7 @@ int r600_parse_extended_power_table(struct radeon_device *rdev)
                                 rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries[i].dclk =
                                         le16_to_cpu(uvd_clk->usDClkLow) | (uvd_clk->ucDClkHigh << 16);
                                 rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries[i].v =
-                                        le16_to_cpu(limits->entries[i].usVoltage);
+                                        le16_to_cpu(entry->usVoltage);
                                 entry = (ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record *)
                                         ((u8 *)entry + sizeof(ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record));
                         }
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index f443010ce90b..b0fa6002af3e 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -257,10 +257,7 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
          * number (coefficient of two integer numbers.  DCCG_AUDIO_DTOx_PHASE
          * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator
          */
-        if (ASIC_IS_DCE3(rdev)) {
-                /* according to the reg specs, this should DCE3.2 only, but in
-                 * practice it seems to cover DCE3.0 as well.
-                 */
+        if (ASIC_IS_DCE32(rdev)) {
                 if (dig->dig_encoder == 0) {
                         dto_cntl = RREG32(DCCG_AUDIO_DTO0_CNTL) & ~DCCG_AUDIO_DTO_WALLCLOCK_RATIO_MASK;
                         dto_cntl |= DCCG_AUDIO_DTO_WALLCLOCK_RATIO(wallclock_ratio);
@@ -276,8 +273,21 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
                         WREG32(DCCG_AUDIO_DTO1_MODULE, dto_modulo);
                         WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */
                 }
+        } else if (ASIC_IS_DCE3(rdev)) {
+                /* according to the reg specs, this should DCE3.2 only, but in
+                 * practice it seems to cover DCE3.0/3.1 as well.
+                 */
+                if (dig->dig_encoder == 0) {
+                        WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
+                        WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100);
+                        WREG32(DCCG_AUDIO_DTO_SELECT, 0); /* select DTO0 */
+                } else {
+                        WREG32(DCCG_AUDIO_DTO1_PHASE, base_rate * 100);
+                        WREG32(DCCG_AUDIO_DTO1_MODULE, clock * 100);
+                        WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */
+                }
         } else {
-                /* according to the reg specs, this should be DCE2.0 and DCE3.0 */
+                /* according to the reg specs, this should be DCE2.0 and DCE3.0/3.1 */
                 WREG32(AUDIO_DTO, AUDIO_DTO_PHASE(base_rate / 10) |
                        AUDIO_DTO_MODULE(clock / 10));
         }
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 5003385a7512..8f7e04538fd6 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1004,6 +1004,8 @@ static struct radeon_asic rv6xx_asic = {
                 .wait_for_vblank = &avivo_wait_for_vblank,
                 .set_backlight_level = &atombios_set_backlight_level,
                 .get_backlight_level = &atombios_get_backlight_level,
+                .hdmi_enable = &r600_hdmi_enable,
+                .hdmi_setmode = &r600_hdmi_setmode,
         },
         .copy = {
                 .blit = &r600_copy_cpdma,
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index 404e25d285ba..f79ee184ffd5 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -1367,6 +1367,7 @@ bool radeon_atombios_get_ppll_ss_info(struct radeon_device *rdev,
         int index = GetIndexIntoMasterTable(DATA, PPLL_SS_Info);
         uint16_t data_offset, size;
         struct _ATOM_SPREAD_SPECTRUM_INFO *ss_info;
+        struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT *ss_assign;
         uint8_t frev, crev;
         int i, num_indices;
 
@@ -1378,18 +1379,21 @@ bool radeon_atombios_get_ppll_ss_info(struct radeon_device *rdev,
 
                 num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
                         sizeof(ATOM_SPREAD_SPECTRUM_ASSIGNMENT);
-
+                ss_assign = (struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT*)
+                        ((u8 *)&ss_info->asSS_Info[0]);
                 for (i = 0; i < num_indices; i++) {
-                        if (ss_info->asSS_Info[i].ucSS_Id == id) {
+                        if (ss_assign->ucSS_Id == id) {
                                 ss->percentage =
-                                        le16_to_cpu(ss_info->asSS_Info[i].usSpreadSpectrumPercentage);
-                                ss->type = ss_info->asSS_Info[i].ucSpreadSpectrumType;
-                                ss->step = ss_info->asSS_Info[i].ucSS_Step;
-                                ss->delay = ss_info->asSS_Info[i].ucSS_Delay;
-                                ss->range = ss_info->asSS_Info[i].ucSS_Range;
-                                ss->refdiv = ss_info->asSS_Info[i].ucRecommendedRef_Div;
+                                        le16_to_cpu(ss_assign->usSpreadSpectrumPercentage);
+                                ss->type = ss_assign->ucSpreadSpectrumType;
+                                ss->step = ss_assign->ucSS_Step;
+                                ss->delay = ss_assign->ucSS_Delay;
+                                ss->range = ss_assign->ucSS_Range;
+                                ss->refdiv = ss_assign->ucRecommendedRef_Div;
                                 return true;
                         }
+                        ss_assign = (struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT*)
+                                ((u8 *)ss_assign + sizeof(struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT));
                 }
         }
         return false;
@@ -1477,6 +1481,12 @@ union asic_ss_info {
         struct _ATOM_ASIC_INTERNAL_SS_INFO_V3 info_3;
 };
 
+union asic_ss_assignment {
+        struct _ATOM_ASIC_SS_ASSIGNMENT v1;
+        struct _ATOM_ASIC_SS_ASSIGNMENT_V2 v2;
+        struct _ATOM_ASIC_SS_ASSIGNMENT_V3 v3;
+};
+
 bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev,
                                       struct radeon_atom_ss *ss,
                                       int id, u32 clock)
@@ -1485,6 +1495,7 @@ bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev,
         int index = GetIndexIntoMasterTable(DATA, ASIC_InternalSS_Info);
         uint16_t data_offset, size;
         union asic_ss_info *ss_info;
+        union asic_ss_assignment *ss_assign;
         uint8_t frev, crev;
         int i, num_indices;
 
@@ -1509,45 +1520,52 @@ bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev,
                         num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
                                 sizeof(ATOM_ASIC_SS_ASSIGNMENT);
 
+                        ss_assign = (union asic_ss_assignment *)((u8 *)&ss_info->info.asSpreadSpectrum[0]);
                         for (i = 0; i < num_indices; i++) {
-                                if ((ss_info->info.asSpreadSpectrum[i].ucClockIndication == id) &&
-                                    (clock <= le32_to_cpu(ss_info->info.asSpreadSpectrum[i].ulTargetClockRange))) {
+                                if ((ss_assign->v1.ucClockIndication == id) &&
+                                    (clock <= le32_to_cpu(ss_assign->v1.ulTargetClockRange))) {
                                         ss->percentage =
-                                                le16_to_cpu(ss_info->info.asSpreadSpectrum[i].usSpreadSpectrumPercentage);
-                                        ss->type = ss_info->info.asSpreadSpectrum[i].ucSpreadSpectrumMode;
-                                        ss->rate = le16_to_cpu(ss_info->info.asSpreadSpectrum[i].usSpreadRateInKhz);
+                                                le16_to_cpu(ss_assign->v1.usSpreadSpectrumPercentage);
+                                        ss->type = ss_assign->v1.ucSpreadSpectrumMode;
+                                        ss->rate = le16_to_cpu(ss_assign->v1.usSpreadRateInKhz);
                                         return true;
                                 }
+                                ss_assign = (union asic_ss_assignment *)
+                                        ((u8 *)ss_assign + sizeof(ATOM_ASIC_SS_ASSIGNMENT));
                         }
                         break;
                 case 2:
                         num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
                                 sizeof(ATOM_ASIC_SS_ASSIGNMENT_V2);
+                        ss_assign = (union asic_ss_assignment *)((u8 *)&ss_info->info_2.asSpreadSpectrum[0]);
                         for (i = 0; i < num_indices; i++) {
-                                if ((ss_info->info_2.asSpreadSpectrum[i].ucClockIndication == id) &&
-                                    (clock <= le32_to_cpu(ss_info->info_2.asSpreadSpectrum[i].ulTargetClockRange))) {
+                                if ((ss_assign->v2.ucClockIndication == id) &&
+                                    (clock <= le32_to_cpu(ss_assign->v2.ulTargetClockRange))) {
                                         ss->percentage =
-                                                le16_to_cpu(ss_info->info_2.asSpreadSpectrum[i].usSpreadSpectrumPercentage);
-                                        ss->type = ss_info->info_2.asSpreadSpectrum[i].ucSpreadSpectrumMode;
-                                        ss->rate = le16_to_cpu(ss_info->info_2.asSpreadSpectrum[i].usSpreadRateIn10Hz);
+                                                le16_to_cpu(ss_assign->v2.usSpreadSpectrumPercentage);
+                                        ss->type = ss_assign->v2.ucSpreadSpectrumMode;
+                                        ss->rate = le16_to_cpu(ss_assign->v2.usSpreadRateIn10Hz);
                                         if ((crev == 2) &&
                                             ((id == ASIC_INTERNAL_ENGINE_SS) ||
                                              (id == ASIC_INTERNAL_MEMORY_SS)))
                                                 ss->rate /= 100;
                                         return true;
                                 }
+                                ss_assign = (union asic_ss_assignment *)
+                                        ((u8 *)ss_assign + sizeof(ATOM_ASIC_SS_ASSIGNMENT_V2));
                         }
                         break;
                 case 3:
                         num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) /
                                 sizeof(ATOM_ASIC_SS_ASSIGNMENT_V3);
+                        ss_assign = (union asic_ss_assignment *)((u8 *)&ss_info->info_3.asSpreadSpectrum[0]);
                         for (i = 0; i < num_indices; i++) {
-                                if ((ss_info->info_3.asSpreadSpectrum[i].ucClockIndication == id) &&
-                                    (clock <= le32_to_cpu(ss_info->info_3.asSpreadSpectrum[i].ulTargetClockRange))) {
+                                if ((ss_assign->v3.ucClockIndication == id) &&
+                                    (clock <= le32_to_cpu(ss_assign->v3.ulTargetClockRange))) {
                                         ss->percentage =
-                                                le16_to_cpu(ss_info->info_3.asSpreadSpectrum[i].usSpreadSpectrumPercentage);
-                                        ss->type = ss_info->info_3.asSpreadSpectrum[i].ucSpreadSpectrumMode;
-                                        ss->rate = le16_to_cpu(ss_info->info_3.asSpreadSpectrum[i].usSpreadRateIn10Hz);
+                                                le16_to_cpu(ss_assign->v3.usSpreadSpectrumPercentage);
+                                        ss->type = ss_assign->v3.ucSpreadSpectrumMode;
+                                        ss->rate = le16_to_cpu(ss_assign->v3.usSpreadRateIn10Hz);
                                         if ((id == ASIC_INTERNAL_ENGINE_SS) ||
                                             (id == ASIC_INTERNAL_MEMORY_SS))
                                                 ss->rate /= 100;
@@ -1555,6 +1573,8 @@ bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev,
                                                 radeon_atombios_get_igp_ss_overrides(rdev, ss, id);
                                         return true;
                                 }
+                                ss_assign = (union asic_ss_assignment *)
+                                        ((u8 *)ss_assign + sizeof(ATOM_ASIC_SS_ASSIGNMENT_V3));
                         }
                         break;
                 default:
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index ac6ece61a476..66c222836631 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -85,8 +85,9 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
                    VRAM, also but everything into VRAM on AGP cards to avoid
                    image corruptions */
                 if (p->ring == R600_RING_TYPE_UVD_INDEX &&
-                    (i == 0 || p->rdev->flags & RADEON_IS_AGP)) {
-                        /* TODO: is this still needed for NI+ ? */
+                    p->rdev->family < CHIP_PALM &&
+                    (i == 0 || drm_pci_device_is_agp(p->rdev->ddev))) {
+
                         p->relocs[i].lobj.domain =
                                 RADEON_GEM_DOMAIN_VRAM;
 
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index e29faa73b574..841d0e09be3e 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1320,13 +1320,22 @@ int radeon_device_init(struct radeon_device *rdev,
                         return r;
         }
         if ((radeon_testing & 1)) {
-                radeon_test_moves(rdev);
+                if (rdev->accel_working)
+                        radeon_test_moves(rdev);
+                else
+                        DRM_INFO("radeon: acceleration disabled, skipping move tests\n");
         }
         if ((radeon_testing & 2)) {
-                radeon_test_syncing(rdev);
+                if (rdev->accel_working)
+                        radeon_test_syncing(rdev);
+                else
+                        DRM_INFO("radeon: acceleration disabled, skipping sync tests\n");
         }
         if (radeon_benchmarking) {
-                radeon_benchmark(rdev, radeon_benchmarking);
+                if (rdev->accel_working)
+                        radeon_benchmark(rdev, radeon_benchmarking);
+                else
+                        DRM_INFO("radeon: acceleration disabled, skipping benchmarks\n");
         }
         return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 87e1d69e8fdb..ac07ad1d4f8c 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -1002,7 +1002,7 @@ static void radeon_pm_resume_old(struct radeon_device *rdev)
 {
         /* set up the default clocks if the MC ucode is loaded */
         if ((rdev->family >= CHIP_BARTS) &&
-            (rdev->family <= CHIP_HAINAN) &&
+            (rdev->family <= CHIP_CAYMAN) &&
             rdev->mc_fw) {
                 if (rdev->pm.default_vddc)
                         radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
@@ -1046,7 +1046,7 @@ static void radeon_pm_resume_dpm(struct radeon_device *rdev)
         if (ret) {
                 DRM_ERROR("radeon: dpm resume failed\n");
                 if ((rdev->family >= CHIP_BARTS) &&
-                    (rdev->family <= CHIP_HAINAN) &&
+                    (rdev->family <= CHIP_CAYMAN) &&
                     rdev->mc_fw) {
                         if (rdev->pm.default_vddc)
                                 radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
@@ -1097,7 +1097,7 @@ static int radeon_pm_init_old(struct radeon_device *rdev)
                 radeon_pm_init_profile(rdev);
                 /* set up the default clocks if the MC ucode is loaded */
                 if ((rdev->family >= CHIP_BARTS) &&
-                    (rdev->family <= CHIP_HAINAN) &&
+                    (rdev->family <= CHIP_CAYMAN) &&
                     rdev->mc_fw) {
                         if (rdev->pm.default_vddc)
                                 radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
@@ -1183,7 +1183,7 @@ static int radeon_pm_init_dpm(struct radeon_device *rdev)
         if (ret) {
                 rdev->pm.dpm_enabled = false;
                 if ((rdev->family >= CHIP_BARTS) &&
-                    (rdev->family <= CHIP_HAINAN) &&
+                    (rdev->family <= CHIP_CAYMAN) &&
                     rdev->mc_fw) {
                         if (rdev->pm.default_vddc)
                                 radeon_atom_set_voltage(rdev, rdev->pm.default_vddc,
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 46a25f037b84..18254e1c3e71 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -839,9 +839,11 @@ static int radeon_debugfs_ring_info(struct seq_file *m, void *data)
          * packet that is the root issue
          */
         i = (ring->rptr + ring->ptr_mask + 1 - 32) & ring->ptr_mask;
-        for (j = 0; j <= (count + 32); j++) {
-                seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]);
-                i = (i + 1) & ring->ptr_mask;
+        if (ring->ready) {
+                for (j = 0; j <= (count + 32); j++) {
+                        seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]);
+                        i = (i + 1) & ring->ptr_mask;
+                }
         }
         return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 1a01bbff9bfa..a0f11856ddde 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -476,8 +476,7 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p,
                 return -EINVAL;
         }
 
-        /* TODO: is this still necessary on NI+ ? */
-        if ((cmd == 0 || cmd == 0x3) &&
+        if (p->rdev->family < CHIP_PALM && (cmd == 0 || cmd == 0x3) &&
             (start >> 28) != (p->rdev->uvd.gpu_addr >> 28)) {
                 DRM_ERROR("msg/fb buffer %LX-%LX out of 256MB segment!\n",
                           start, end);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index cfe5d4d28915..9ace28702c76 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2910,6 +2910,7 @@ 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) ||
@@ -2943,6 +2944,29 @@ 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/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c
index 7266805d9786..3100fa9cb52f 100644
--- a/drivers/gpu/drm/radeon/uvd_v1_0.c
+++ b/drivers/gpu/drm/radeon/uvd_v1_0.c
@@ -212,8 +212,8 @@ int uvd_v1_0_start(struct radeon_device *rdev)
         /* enable VCPU clock */
         WREG32(UVD_VCPU_CNTL,  1 << 9);
 
-        /* enable UMC */
-        WREG32_P(UVD_LMI_CTRL2, 0, ~(1 << 8));
+        /* enable UMC and NC0 */
+        WREG32_P(UVD_LMI_CTRL2, 1 << 13, ~((1 << 8) | (1 << 13)));
 
         /* boot up the VCPU */
         WREG32(UVD_SOFT_RESET, 0);