Merge git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fix from Avi Kivity:
 "A one-liner fix for a buffer overflow"

* git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: Fix buffer overflow in kvm_set_irq()
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index 2e3994b..62bcea7 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -173,7 +173,7 @@
 	unsigned long newsp;
 
 #ifdef __ARCH_SYNC_CORE_DCACHE
-	if (current->rt.nr_cpus_allowed == num_possible_cpus())
+	if (current->nr_cpus_allowed == num_possible_cpus())
 		set_cpus_allowed_ptr(current, cpumask_of(smp_processor_id()));
 #endif
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f56f96d..fd019d7 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -410,15 +410,7 @@
 /* maps the cpu to the sched domain representing multi-core */
 const struct cpumask *cpu_coregroup_mask(int cpu)
 {
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
-	/*
-	 * For perf, we return last level cache shared map.
-	 * And for power savings, we return cpu_core_map
-	 */
-	if (!(cpu_has(c, X86_FEATURE_AMD_DCM)))
-		return cpu_core_mask(cpu);
-	else
-		return cpu_llc_shared_mask(cpu);
+	return cpu_llc_shared_mask(cpu);
 }
 
 static void impress_friends(void)
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 3df4efa..3186522 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -460,15 +460,28 @@
 		rdev->config.cayman.max_pipes_per_simd = 4;
 		rdev->config.cayman.max_tile_pipes = 2;
 		if ((rdev->pdev->device == 0x9900) ||
-		    (rdev->pdev->device == 0x9901)) {
+		    (rdev->pdev->device == 0x9901) ||
+		    (rdev->pdev->device == 0x9905) ||
+		    (rdev->pdev->device == 0x9906) ||
+		    (rdev->pdev->device == 0x9907) ||
+		    (rdev->pdev->device == 0x9908) ||
+		    (rdev->pdev->device == 0x9909) ||
+		    (rdev->pdev->device == 0x9910) ||
+		    (rdev->pdev->device == 0x9917)) {
 			rdev->config.cayman.max_simds_per_se = 6;
 			rdev->config.cayman.max_backends_per_se = 2;
 		} else if ((rdev->pdev->device == 0x9903) ||
-			   (rdev->pdev->device == 0x9904)) {
+			   (rdev->pdev->device == 0x9904) ||
+			   (rdev->pdev->device == 0x990A) ||
+			   (rdev->pdev->device == 0x9913) ||
+			   (rdev->pdev->device == 0x9918)) {
 			rdev->config.cayman.max_simds_per_se = 4;
 			rdev->config.cayman.max_backends_per_se = 2;
-		} else if ((rdev->pdev->device == 0x9990) ||
-			   (rdev->pdev->device == 0x9991)) {
+		} else if ((rdev->pdev->device == 0x9919) ||
+			   (rdev->pdev->device == 0x9990) ||
+			   (rdev->pdev->device == 0x9991) ||
+			   (rdev->pdev->device == 0x9994) ||
+			   (rdev->pdev->device == 0x99A0)) {
 			rdev->config.cayman.max_simds_per_se = 3;
 			rdev->config.cayman.max_backends_per_se = 1;
 		} else {
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 45cfcea..f30dc95 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2426,6 +2426,12 @@
 	if (r)
 		return r;
 
+	r = r600_audio_init(rdev);
+	if (r) {
+		DRM_ERROR("radeon: audio init failed\n");
+		return r;
+	}
+
 	return 0;
 }
 
@@ -2462,12 +2468,6 @@
 		return r;
 	}
 
-	r = r600_audio_init(rdev);
-	if (r) {
-		DRM_ERROR("radeon: audio resume failed\n");
-		return r;
-	}
-
 	return r;
 }
 
@@ -2577,9 +2577,6 @@
 		rdev->accel_working = false;
 	}
 
-	r = r600_audio_init(rdev);
-	if (r)
-		return r; /* TODO error handling */
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/r600_audio.c b/drivers/gpu/drm/radeon/r600_audio.c
index 7c4fa77..7479a5c 100644
--- a/drivers/gpu/drm/radeon/r600_audio.c
+++ b/drivers/gpu/drm/radeon/r600_audio.c
@@ -192,6 +192,7 @@
 	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc);
 	int base_rate = 48000;
 
 	switch (radeon_encoder->encoder_id) {
@@ -217,8 +218,8 @@
 		WREG32(EVERGREEN_AUDIO_PLL1_DIV, clock * 10);
 		WREG32(EVERGREEN_AUDIO_PLL1_UNK, 0x00000071);
 
-		/* Some magic trigger or src sel? */
-		WREG32_P(0x5ac, 0x01, ~0x77);
+		/* Select DTO source */
+		WREG32(0x5ac, radeon_crtc->crtc_id);
 	} else {
 		switch (dig->dig_encoder) {
 		case 0:
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index 226379e..969c275 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -348,7 +348,6 @@
 		WREG32(HDMI0_AUDIO_PACKET_CONTROL + offset,
 		       HDMI0_AUDIO_SAMPLE_SEND | /* send audio packets */
 		       HDMI0_AUDIO_DELAY_EN(1) | /* default audio delay */
-		       HDMI0_AUDIO_SEND_MAX_PACKETS | /* send NULL packets if no audio is available */
 		       HDMI0_AUDIO_PACKETS_PER_LINE(3) | /* should be suffient for all audio modes and small enough for all hblanks */
 		       HDMI0_60958_CS_UPDATE); /* allow 60958 channel status fields to be updated */
 	}
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 85dac33..fefcca5 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1374,9 +1374,9 @@
 
 struct si_asic {
 	unsigned max_shader_engines;
-	unsigned max_pipes_per_simd;
 	unsigned max_tile_pipes;
-	unsigned max_simds_per_se;
+	unsigned max_cu_per_sh;
+	unsigned max_sh_per_se;
 	unsigned max_backends_per_se;
 	unsigned max_texture_channel_caches;
 	unsigned max_gprs;
@@ -1387,7 +1387,6 @@
 	unsigned sc_hiz_tile_fifo_size;
 	unsigned sc_earlyz_tile_fifo_size;
 
-	unsigned num_shader_engines;
 	unsigned num_tile_pipes;
 	unsigned num_backends_per_se;
 	unsigned backend_disable_mask_per_asic;
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 79db56e..59d4493 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -476,12 +476,18 @@
 
 	mutex_lock(&vm->mutex);
 	if (last_pfn > vm->last_pfn) {
-		/* grow va space 32M by 32M */
-		unsigned align = ((32 << 20) >> 12) - 1;
+		/* release mutex and lock in right order */
+		mutex_unlock(&vm->mutex);
 		radeon_mutex_lock(&rdev->cs_mutex);
-		radeon_vm_unbind_locked(rdev, vm);
+		mutex_lock(&vm->mutex);
+		/* and check again */
+		if (last_pfn > vm->last_pfn) {
+			/* grow va space 32M by 32M */
+			unsigned align = ((32 << 20) >> 12) - 1;
+			radeon_vm_unbind_locked(rdev, vm);
+			vm->last_pfn = (last_pfn + align) & ~align;
+		}
 		radeon_mutex_unlock(&rdev->cs_mutex);
-		vm->last_pfn = (last_pfn + align) & ~align;
 	}
 	head = &vm->va;
 	last_offset = 0;
@@ -595,8 +601,8 @@
 	if (bo_va == NULL)
 		return 0;
 
-	mutex_lock(&vm->mutex);
 	radeon_mutex_lock(&rdev->cs_mutex);
+	mutex_lock(&vm->mutex);
 	radeon_vm_bo_update_pte(rdev, vm, bo, NULL);
 	radeon_mutex_unlock(&rdev->cs_mutex);
 	list_del(&bo_va->vm_list);
@@ -641,9 +647,8 @@
 	struct radeon_bo_va *bo_va, *tmp;
 	int r;
 
-	mutex_lock(&vm->mutex);
-
 	radeon_mutex_lock(&rdev->cs_mutex);
+	mutex_lock(&vm->mutex);
 	radeon_vm_unbind_locked(rdev, vm);
 	radeon_mutex_unlock(&rdev->cs_mutex);
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index f1016a5..5c58d7d 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -273,7 +273,7 @@
 		break;
 	case RADEON_INFO_MAX_PIPES:
 		if (rdev->family >= CHIP_TAHITI)
-			value = rdev->config.si.max_pipes_per_simd;
+			value = rdev->config.si.max_cu_per_sh;
 		else if (rdev->family >= CHIP_CAYMAN)
 			value = rdev->config.cayman.max_pipes_per_simd;
 		else if (rdev->family >= CHIP_CEDAR)
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 25f9eef..e95c5e6 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -908,12 +908,6 @@
 		return r;
 	}
 
-	r = r600_audio_init(rdev);
-	if (r) {
-		dev_err(rdev->dev, "failed initializing audio\n");
-		return r;
-	}
-
 	r = radeon_ib_pool_start(rdev);
 	if (r)
 		return r;
@@ -922,6 +916,12 @@
 	if (r)
 		return r;
 
+	r = r600_audio_init(rdev);
+	if (r) {
+		dev_err(rdev->dev, "failed initializing audio\n");
+		return r;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 3277dde..159b6a4 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -637,12 +637,6 @@
 		return r;
 	}
 
-	r = r600_audio_init(rdev);
-	if (r) {
-		dev_err(rdev->dev, "failed initializing audio\n");
-		return r;
-	}
-
 	r = radeon_ib_pool_start(rdev);
 	if (r)
 		return r;
@@ -651,6 +645,12 @@
 	if (r)
 		return r;
 
+	r = r600_audio_init(rdev);
+	if (r) {
+		dev_err(rdev->dev, "failed initializing audio\n");
+		return r;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 04ddc36..4ad0281 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -956,6 +956,12 @@
 	if (r)
 		return r;
 
+	r = r600_audio_init(rdev);
+	if (r) {
+		DRM_ERROR("radeon: audio init failed\n");
+		return r;
+	}
+
 	return 0;
 }
 
@@ -978,12 +984,6 @@
 		return r;
 	}
 
-	r = r600_audio_init(rdev);
-	if (r) {
-		dev_err(rdev->dev, "radeon: audio init failed\n");
-		return r;
-	}
-
 	return r;
 
 }
@@ -1092,12 +1092,6 @@
 		rdev->accel_working = false;
 	}
 
-	r = r600_audio_init(rdev);
-	if (r) {
-		dev_err(rdev->dev, "radeon: audio init failed\n");
-		return r;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 549732e..c7b61f1 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -867,200 +867,6 @@
 /*
  * Core functions
  */
-static u32 si_get_tile_pipe_to_backend_map(struct radeon_device *rdev,
-					   u32 num_tile_pipes,
-					   u32 num_backends_per_asic,
-					   u32 *backend_disable_mask_per_asic,
-					   u32 num_shader_engines)
-{
-	u32 backend_map = 0;
-	u32 enabled_backends_mask = 0;
-	u32 enabled_backends_count = 0;
-	u32 num_backends_per_se;
-	u32 cur_pipe;
-	u32 swizzle_pipe[SI_MAX_PIPES];
-	u32 cur_backend = 0;
-	u32 i;
-	bool force_no_swizzle;
-
-	/* force legal values */
-	if (num_tile_pipes < 1)
-		num_tile_pipes = 1;
-	if (num_tile_pipes > rdev->config.si.max_tile_pipes)
-		num_tile_pipes = rdev->config.si.max_tile_pipes;
-	if (num_shader_engines < 1)
-		num_shader_engines = 1;
-	if (num_shader_engines > rdev->config.si.max_shader_engines)
-		num_shader_engines = rdev->config.si.max_shader_engines;
-	if (num_backends_per_asic < num_shader_engines)
-		num_backends_per_asic = num_shader_engines;
-	if (num_backends_per_asic > (rdev->config.si.max_backends_per_se * num_shader_engines))
-		num_backends_per_asic = rdev->config.si.max_backends_per_se * num_shader_engines;
-
-	/* make sure we have the same number of backends per se */
-	num_backends_per_asic = ALIGN(num_backends_per_asic, num_shader_engines);
-	/* set up the number of backends per se */
-	num_backends_per_se = num_backends_per_asic / num_shader_engines;
-	if (num_backends_per_se > rdev->config.si.max_backends_per_se) {
-		num_backends_per_se = rdev->config.si.max_backends_per_se;
-		num_backends_per_asic = num_backends_per_se * num_shader_engines;
-	}
-
-	/* create enable mask and count for enabled backends */
-	for (i = 0; i < SI_MAX_BACKENDS; ++i) {
-		if (((*backend_disable_mask_per_asic >> i) & 1) == 0) {
-			enabled_backends_mask |= (1 << i);
-			++enabled_backends_count;
-		}
-		if (enabled_backends_count == num_backends_per_asic)
-			break;
-	}
-
-	/* force the backends mask to match the current number of backends */
-	if (enabled_backends_count != num_backends_per_asic) {
-		u32 this_backend_enabled;
-		u32 shader_engine;
-		u32 backend_per_se;
-
-		enabled_backends_mask = 0;
-		enabled_backends_count = 0;
-		*backend_disable_mask_per_asic = SI_MAX_BACKENDS_MASK;
-		for (i = 0; i < SI_MAX_BACKENDS; ++i) {
-			/* calc the current se */
-			shader_engine = i / rdev->config.si.max_backends_per_se;
-			/* calc the backend per se */
-			backend_per_se = i % rdev->config.si.max_backends_per_se;
-			/* default to not enabled */
-			this_backend_enabled = 0;
-			if ((shader_engine < num_shader_engines) &&
-			    (backend_per_se < num_backends_per_se))
-				this_backend_enabled = 1;
-			if (this_backend_enabled) {
-				enabled_backends_mask |= (1 << i);
-				*backend_disable_mask_per_asic &= ~(1 << i);
-				++enabled_backends_count;
-			}
-		}
-	}
-
-
-	memset((uint8_t *)&swizzle_pipe[0], 0, sizeof(u32) * SI_MAX_PIPES);
-	switch (rdev->family) {
-	case CHIP_TAHITI:
-	case CHIP_PITCAIRN:
-	case CHIP_VERDE:
-		force_no_swizzle = true;
-		break;
-	default:
-		force_no_swizzle = false;
-		break;
-	}
-	if (force_no_swizzle) {
-		bool last_backend_enabled = false;
-
-		force_no_swizzle = false;
-		for (i = 0; i < SI_MAX_BACKENDS; ++i) {
-			if (((enabled_backends_mask >> i) & 1) == 1) {
-				if (last_backend_enabled)
-					force_no_swizzle = true;
-				last_backend_enabled = true;
-			} else
-				last_backend_enabled = false;
-		}
-	}
-
-	switch (num_tile_pipes) {
-	case 1:
-	case 3:
-	case 5:
-	case 7:
-		DRM_ERROR("odd number of pipes!\n");
-		break;
-	case 2:
-		swizzle_pipe[0] = 0;
-		swizzle_pipe[1] = 1;
-		break;
-	case 4:
-		if (force_no_swizzle) {
-			swizzle_pipe[0] = 0;
-			swizzle_pipe[1] = 1;
-			swizzle_pipe[2] = 2;
-			swizzle_pipe[3] = 3;
-		} else {
-			swizzle_pipe[0] = 0;
-			swizzle_pipe[1] = 2;
-			swizzle_pipe[2] = 1;
-			swizzle_pipe[3] = 3;
-		}
-		break;
-	case 6:
-		if (force_no_swizzle) {
-			swizzle_pipe[0] = 0;
-			swizzle_pipe[1] = 1;
-			swizzle_pipe[2] = 2;
-			swizzle_pipe[3] = 3;
-			swizzle_pipe[4] = 4;
-			swizzle_pipe[5] = 5;
-		} else {
-			swizzle_pipe[0] = 0;
-			swizzle_pipe[1] = 2;
-			swizzle_pipe[2] = 4;
-			swizzle_pipe[3] = 1;
-			swizzle_pipe[4] = 3;
-			swizzle_pipe[5] = 5;
-		}
-		break;
-	case 8:
-		if (force_no_swizzle) {
-			swizzle_pipe[0] = 0;
-			swizzle_pipe[1] = 1;
-			swizzle_pipe[2] = 2;
-			swizzle_pipe[3] = 3;
-			swizzle_pipe[4] = 4;
-			swizzle_pipe[5] = 5;
-			swizzle_pipe[6] = 6;
-			swizzle_pipe[7] = 7;
-		} else {
-			swizzle_pipe[0] = 0;
-			swizzle_pipe[1] = 2;
-			swizzle_pipe[2] = 4;
-			swizzle_pipe[3] = 6;
-			swizzle_pipe[4] = 1;
-			swizzle_pipe[5] = 3;
-			swizzle_pipe[6] = 5;
-			swizzle_pipe[7] = 7;
-		}
-		break;
-	}
-
-	for (cur_pipe = 0; cur_pipe < num_tile_pipes; ++cur_pipe) {
-		while (((1 << cur_backend) & enabled_backends_mask) == 0)
-			cur_backend = (cur_backend + 1) % SI_MAX_BACKENDS;
-
-		backend_map |= (((cur_backend & 0xf) << (swizzle_pipe[cur_pipe] * 4)));
-
-		cur_backend = (cur_backend + 1) % SI_MAX_BACKENDS;
-	}
-
-	return backend_map;
-}
-
-static u32 si_get_disable_mask_per_asic(struct radeon_device *rdev,
-					u32 disable_mask_per_se,
-					u32 max_disable_mask_per_se,
-					u32 num_shader_engines)
-{
-	u32 disable_field_width_per_se = r600_count_pipe_bits(disable_mask_per_se);
-	u32 disable_mask_per_asic = disable_mask_per_se & max_disable_mask_per_se;
-
-	if (num_shader_engines == 1)
-		return disable_mask_per_asic;
-	else if (num_shader_engines == 2)
-		return disable_mask_per_asic | (disable_mask_per_asic << disable_field_width_per_se);
-	else
-		return 0xffffffff;
-}
-
 static void si_tiling_mode_table_init(struct radeon_device *rdev)
 {
 	const u32 num_tile_mode_states = 32;
@@ -1562,18 +1368,151 @@
 		DRM_ERROR("unknown asic: 0x%x\n", rdev->family);
 }
 
+static void si_select_se_sh(struct radeon_device *rdev,
+			    u32 se_num, u32 sh_num)
+{
+	u32 data = INSTANCE_BROADCAST_WRITES;
+
+	if ((se_num == 0xffffffff) && (sh_num == 0xffffffff))
+		data = SH_BROADCAST_WRITES | SE_BROADCAST_WRITES;
+	else if (se_num == 0xffffffff)
+		data |= SE_BROADCAST_WRITES | SH_INDEX(sh_num);
+	else if (sh_num == 0xffffffff)
+		data |= SH_BROADCAST_WRITES | SE_INDEX(se_num);
+	else
+		data |= SH_INDEX(sh_num) | SE_INDEX(se_num);
+	WREG32(GRBM_GFX_INDEX, data);
+}
+
+static u32 si_create_bitmask(u32 bit_width)
+{
+	u32 i, mask = 0;
+
+	for (i = 0; i < bit_width; i++) {
+		mask <<= 1;
+		mask |= 1;
+	}
+	return mask;
+}
+
+static u32 si_get_cu_enabled(struct radeon_device *rdev, u32 cu_per_sh)
+{
+	u32 data, mask;
+
+	data = RREG32(CC_GC_SHADER_ARRAY_CONFIG);
+	if (data & 1)
+		data &= INACTIVE_CUS_MASK;
+	else
+		data = 0;
+	data |= RREG32(GC_USER_SHADER_ARRAY_CONFIG);
+
+	data >>= INACTIVE_CUS_SHIFT;
+
+	mask = si_create_bitmask(cu_per_sh);
+
+	return ~data & mask;
+}
+
+static void si_setup_spi(struct radeon_device *rdev,
+			 u32 se_num, u32 sh_per_se,
+			 u32 cu_per_sh)
+{
+	int i, j, k;
+	u32 data, mask, active_cu;
+
+	for (i = 0; i < se_num; i++) {
+		for (j = 0; j < sh_per_se; j++) {
+			si_select_se_sh(rdev, i, j);
+			data = RREG32(SPI_STATIC_THREAD_MGMT_3);
+			active_cu = si_get_cu_enabled(rdev, cu_per_sh);
+
+			mask = 1;
+			for (k = 0; k < 16; k++) {
+				mask <<= k;
+				if (active_cu & mask) {
+					data &= ~mask;
+					WREG32(SPI_STATIC_THREAD_MGMT_3, data);
+					break;
+				}
+			}
+		}
+	}
+	si_select_se_sh(rdev, 0xffffffff, 0xffffffff);
+}
+
+static u32 si_get_rb_disabled(struct radeon_device *rdev,
+			      u32 max_rb_num, u32 se_num,
+			      u32 sh_per_se)
+{
+	u32 data, mask;
+
+	data = RREG32(CC_RB_BACKEND_DISABLE);
+	if (data & 1)
+		data &= BACKEND_DISABLE_MASK;
+	else
+		data = 0;
+	data |= RREG32(GC_USER_RB_BACKEND_DISABLE);
+
+	data >>= BACKEND_DISABLE_SHIFT;
+
+	mask = si_create_bitmask(max_rb_num / se_num / sh_per_se);
+
+	return data & mask;
+}
+
+static void si_setup_rb(struct radeon_device *rdev,
+			u32 se_num, u32 sh_per_se,
+			u32 max_rb_num)
+{
+	int i, j;
+	u32 data, mask;
+	u32 disabled_rbs = 0;
+	u32 enabled_rbs = 0;
+
+	for (i = 0; i < se_num; i++) {
+		for (j = 0; j < sh_per_se; j++) {
+			si_select_se_sh(rdev, i, j);
+			data = si_get_rb_disabled(rdev, max_rb_num, se_num, sh_per_se);
+			disabled_rbs |= data << ((i * sh_per_se + j) * TAHITI_RB_BITMAP_WIDTH_PER_SH);
+		}
+	}
+	si_select_se_sh(rdev, 0xffffffff, 0xffffffff);
+
+	mask = 1;
+	for (i = 0; i < max_rb_num; i++) {
+		if (!(disabled_rbs & mask))
+			enabled_rbs |= mask;
+		mask <<= 1;
+	}
+
+	for (i = 0; i < se_num; i++) {
+		si_select_se_sh(rdev, i, 0xffffffff);
+		data = 0;
+		for (j = 0; j < sh_per_se; j++) {
+			switch (enabled_rbs & 3) {
+			case 1:
+				data |= (RASTER_CONFIG_RB_MAP_0 << (i * sh_per_se + j) * 2);
+				break;
+			case 2:
+				data |= (RASTER_CONFIG_RB_MAP_3 << (i * sh_per_se + j) * 2);
+				break;
+			case 3:
+			default:
+				data |= (RASTER_CONFIG_RB_MAP_2 << (i * sh_per_se + j) * 2);
+				break;
+			}
+			enabled_rbs >>= 2;
+		}
+		WREG32(PA_SC_RASTER_CONFIG, data);
+	}
+	si_select_se_sh(rdev, 0xffffffff, 0xffffffff);
+}
+
 static void si_gpu_init(struct radeon_device *rdev)
 {
-	u32 cc_rb_backend_disable = 0;
-	u32 cc_gc_shader_array_config;
 	u32 gb_addr_config = 0;
 	u32 mc_shared_chmap, mc_arb_ramcfg;
-	u32 gb_backend_map;
-	u32 cgts_tcc_disable;
 	u32 sx_debug_1;
-	u32 gc_user_shader_array_config;
-	u32 gc_user_rb_backend_disable;
-	u32 cgts_user_tcc_disable;
 	u32 hdp_host_path_cntl;
 	u32 tmp;
 	int i, j;
@@ -1581,9 +1520,9 @@
 	switch (rdev->family) {
 	case CHIP_TAHITI:
 		rdev->config.si.max_shader_engines = 2;
-		rdev->config.si.max_pipes_per_simd = 4;
 		rdev->config.si.max_tile_pipes = 12;
-		rdev->config.si.max_simds_per_se = 8;
+		rdev->config.si.max_cu_per_sh = 8;
+		rdev->config.si.max_sh_per_se = 2;
 		rdev->config.si.max_backends_per_se = 4;
 		rdev->config.si.max_texture_channel_caches = 12;
 		rdev->config.si.max_gprs = 256;
@@ -1594,12 +1533,13 @@
 		rdev->config.si.sc_prim_fifo_size_backend = 0x100;
 		rdev->config.si.sc_hiz_tile_fifo_size = 0x30;
 		rdev->config.si.sc_earlyz_tile_fifo_size = 0x130;
+		gb_addr_config = TAHITI_GB_ADDR_CONFIG_GOLDEN;
 		break;
 	case CHIP_PITCAIRN:
 		rdev->config.si.max_shader_engines = 2;
-		rdev->config.si.max_pipes_per_simd = 4;
 		rdev->config.si.max_tile_pipes = 8;
-		rdev->config.si.max_simds_per_se = 5;
+		rdev->config.si.max_cu_per_sh = 5;
+		rdev->config.si.max_sh_per_se = 2;
 		rdev->config.si.max_backends_per_se = 4;
 		rdev->config.si.max_texture_channel_caches = 8;
 		rdev->config.si.max_gprs = 256;
@@ -1610,13 +1550,14 @@
 		rdev->config.si.sc_prim_fifo_size_backend = 0x100;
 		rdev->config.si.sc_hiz_tile_fifo_size = 0x30;
 		rdev->config.si.sc_earlyz_tile_fifo_size = 0x130;
+		gb_addr_config = TAHITI_GB_ADDR_CONFIG_GOLDEN;
 		break;
 	case CHIP_VERDE:
 	default:
 		rdev->config.si.max_shader_engines = 1;
-		rdev->config.si.max_pipes_per_simd = 4;
 		rdev->config.si.max_tile_pipes = 4;
-		rdev->config.si.max_simds_per_se = 2;
+		rdev->config.si.max_cu_per_sh = 2;
+		rdev->config.si.max_sh_per_se = 2;
 		rdev->config.si.max_backends_per_se = 4;
 		rdev->config.si.max_texture_channel_caches = 4;
 		rdev->config.si.max_gprs = 256;
@@ -1627,6 +1568,7 @@
 		rdev->config.si.sc_prim_fifo_size_backend = 0x40;
 		rdev->config.si.sc_hiz_tile_fifo_size = 0x30;
 		rdev->config.si.sc_earlyz_tile_fifo_size = 0x130;
+		gb_addr_config = VERDE_GB_ADDR_CONFIG_GOLDEN;
 		break;
 	}
 
@@ -1648,31 +1590,7 @@
 	mc_shared_chmap = RREG32(MC_SHARED_CHMAP);
 	mc_arb_ramcfg = RREG32(MC_ARB_RAMCFG);
 
-	cc_rb_backend_disable = RREG32(CC_RB_BACKEND_DISABLE);
-	cc_gc_shader_array_config = RREG32(CC_GC_SHADER_ARRAY_CONFIG);
-	cgts_tcc_disable = 0xffff0000;
-	for (i = 0; i < rdev->config.si.max_texture_channel_caches; i++)
-		cgts_tcc_disable &= ~(1 << (16 + i));
-	gc_user_rb_backend_disable = RREG32(GC_USER_RB_BACKEND_DISABLE);
-	gc_user_shader_array_config = RREG32(GC_USER_SHADER_ARRAY_CONFIG);
-	cgts_user_tcc_disable = RREG32(CGTS_USER_TCC_DISABLE);
-
-	rdev->config.si.num_shader_engines = rdev->config.si.max_shader_engines;
 	rdev->config.si.num_tile_pipes = rdev->config.si.max_tile_pipes;
-	tmp = ((~gc_user_rb_backend_disable) & BACKEND_DISABLE_MASK) >> BACKEND_DISABLE_SHIFT;
-	rdev->config.si.num_backends_per_se = r600_count_pipe_bits(tmp);
-	tmp = (gc_user_rb_backend_disable & BACKEND_DISABLE_MASK) >> BACKEND_DISABLE_SHIFT;
-	rdev->config.si.backend_disable_mask_per_asic =
-		si_get_disable_mask_per_asic(rdev, tmp, SI_MAX_BACKENDS_PER_SE_MASK,
-					     rdev->config.si.num_shader_engines);
-	rdev->config.si.backend_map =
-		si_get_tile_pipe_to_backend_map(rdev, rdev->config.si.num_tile_pipes,
-						rdev->config.si.num_backends_per_se *
-						rdev->config.si.num_shader_engines,
-						&rdev->config.si.backend_disable_mask_per_asic,
-						rdev->config.si.num_shader_engines);
-	tmp = ((~cgts_user_tcc_disable) & TCC_DISABLE_MASK) >> TCC_DISABLE_SHIFT;
-	rdev->config.si.num_texture_channel_caches = r600_count_pipe_bits(tmp);
 	rdev->config.si.mem_max_burst_length_bytes = 256;
 	tmp = (mc_arb_ramcfg & NOOFCOLS_MASK) >> NOOFCOLS_SHIFT;
 	rdev->config.si.mem_row_size_in_kb = (4 * (1 << (8 + tmp))) / 1024;
@@ -1683,55 +1601,8 @@
 	rdev->config.si.num_gpus = 1;
 	rdev->config.si.multi_gpu_tile_size = 64;
 
-	gb_addr_config = 0;
-	switch (rdev->config.si.num_tile_pipes) {
-	case 1:
-		gb_addr_config |= NUM_PIPES(0);
-		break;
-	case 2:
-		gb_addr_config |= NUM_PIPES(1);
-		break;
-	case 4:
-		gb_addr_config |= NUM_PIPES(2);
-		break;
-	case 8:
-	default:
-		gb_addr_config |= NUM_PIPES(3);
-		break;
-	}
-
-	tmp = (rdev->config.si.mem_max_burst_length_bytes / 256) - 1;
-	gb_addr_config |= PIPE_INTERLEAVE_SIZE(tmp);
-	gb_addr_config |= NUM_SHADER_ENGINES(rdev->config.si.num_shader_engines - 1);
-	tmp = (rdev->config.si.shader_engine_tile_size / 16) - 1;
-	gb_addr_config |= SHADER_ENGINE_TILE_SIZE(tmp);
-	switch (rdev->config.si.num_gpus) {
-	case 1:
-	default:
-		gb_addr_config |= NUM_GPUS(0);
-		break;
-	case 2:
-		gb_addr_config |= NUM_GPUS(1);
-		break;
-	case 4:
-		gb_addr_config |= NUM_GPUS(2);
-		break;
-	}
-	switch (rdev->config.si.multi_gpu_tile_size) {
-	case 16:
-		gb_addr_config |= MULTI_GPU_TILE_SIZE(0);
-		break;
-	case 32:
-	default:
-		gb_addr_config |= MULTI_GPU_TILE_SIZE(1);
-		break;
-	case 64:
-		gb_addr_config |= MULTI_GPU_TILE_SIZE(2);
-		break;
-	case 128:
-		gb_addr_config |= MULTI_GPU_TILE_SIZE(3);
-		break;
-	}
+	/* fix up row size */
+	gb_addr_config &= ~ROW_SIZE_MASK;
 	switch (rdev->config.si.mem_row_size_in_kb) {
 	case 1:
 	default:
@@ -1745,26 +1616,6 @@
 		break;
 	}
 
-	tmp = (gb_addr_config & NUM_PIPES_MASK) >> NUM_PIPES_SHIFT;
-	rdev->config.si.num_tile_pipes = (1 << tmp);
-	tmp = (gb_addr_config & PIPE_INTERLEAVE_SIZE_MASK) >> PIPE_INTERLEAVE_SIZE_SHIFT;
-	rdev->config.si.mem_max_burst_length_bytes = (tmp + 1) * 256;
-	tmp = (gb_addr_config & NUM_SHADER_ENGINES_MASK) >> NUM_SHADER_ENGINES_SHIFT;
-	rdev->config.si.num_shader_engines = tmp + 1;
-	tmp = (gb_addr_config & NUM_GPUS_MASK) >> NUM_GPUS_SHIFT;
-	rdev->config.si.num_gpus = tmp + 1;
-	tmp = (gb_addr_config & MULTI_GPU_TILE_SIZE_MASK) >> MULTI_GPU_TILE_SIZE_SHIFT;
-	rdev->config.si.multi_gpu_tile_size = 1 << tmp;
-	tmp = (gb_addr_config & ROW_SIZE_MASK) >> ROW_SIZE_SHIFT;
-	rdev->config.si.mem_row_size_in_kb = 1 << tmp;
-
-	gb_backend_map =
-		si_get_tile_pipe_to_backend_map(rdev, rdev->config.si.num_tile_pipes,
-						rdev->config.si.num_backends_per_se *
-						rdev->config.si.num_shader_engines,
-						&rdev->config.si.backend_disable_mask_per_asic,
-						rdev->config.si.num_shader_engines);
-
 	/* setup tiling info dword.  gb_addr_config is not adequate since it does
 	 * not have bank info, so create a custom tiling dword.
 	 * bits 3:0   num_pipes
@@ -1789,34 +1640,30 @@
 		rdev->config.si.tile_config |= (3 << 0);
 		break;
 	}
-	rdev->config.si.tile_config |=
-		((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) << 4;
+	if ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT)
+		rdev->config.si.tile_config |= 1 << 4;
+	else
+		rdev->config.si.tile_config |= 0 << 4;
 	rdev->config.si.tile_config |=
 		((gb_addr_config & PIPE_INTERLEAVE_SIZE_MASK) >> PIPE_INTERLEAVE_SIZE_SHIFT) << 8;
 	rdev->config.si.tile_config |=
 		((gb_addr_config & ROW_SIZE_MASK) >> ROW_SIZE_SHIFT) << 12;
 
-	rdev->config.si.backend_map = gb_backend_map;
 	WREG32(GB_ADDR_CONFIG, gb_addr_config);
 	WREG32(DMIF_ADDR_CONFIG, gb_addr_config);
 	WREG32(HDP_ADDR_CONFIG, gb_addr_config);
 
-	/* primary versions */
-	WREG32(CC_RB_BACKEND_DISABLE, cc_rb_backend_disable);
-	WREG32(CC_SYS_RB_BACKEND_DISABLE, cc_rb_backend_disable);
-	WREG32(CC_GC_SHADER_ARRAY_CONFIG, cc_gc_shader_array_config);
-
-	WREG32(CGTS_TCC_DISABLE, cgts_tcc_disable);
-
-	/* user versions */
-	WREG32(GC_USER_RB_BACKEND_DISABLE, cc_rb_backend_disable);
-	WREG32(GC_USER_SYS_RB_BACKEND_DISABLE, cc_rb_backend_disable);
-	WREG32(GC_USER_SHADER_ARRAY_CONFIG, cc_gc_shader_array_config);
-
-	WREG32(CGTS_USER_TCC_DISABLE, cgts_tcc_disable);
-
 	si_tiling_mode_table_init(rdev);
 
+	si_setup_rb(rdev, rdev->config.si.max_shader_engines,
+		    rdev->config.si.max_sh_per_se,
+		    rdev->config.si.max_backends_per_se);
+
+	si_setup_spi(rdev, rdev->config.si.max_shader_engines,
+		     rdev->config.si.max_sh_per_se,
+		     rdev->config.si.max_cu_per_sh);
+
+
 	/* set HW defaults for 3D engine */
 	WREG32(CP_QUEUE_THRESHOLDS, (ROQ_IB1_START(0x16) |
 				     ROQ_IB2_START(0x2b)));
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 53ea2c4..db40679 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -24,6 +24,11 @@
 #ifndef SI_H
 #define SI_H
 
+#define TAHITI_RB_BITMAP_WIDTH_PER_SH  2
+
+#define TAHITI_GB_ADDR_CONFIG_GOLDEN        0x12011003
+#define VERDE_GB_ADDR_CONFIG_GOLDEN         0x12010002
+
 #define	CG_MULT_THERMAL_STATUS					0x714
 #define		ASIC_MAX_TEMP(x)				((x) << 0)
 #define		ASIC_MAX_TEMP_MASK				0x000001ff
@@ -408,6 +413,12 @@
 #define		SOFT_RESET_IA					(1 << 15)
 
 #define GRBM_GFX_INDEX          			0x802C
+#define		INSTANCE_INDEX(x)			((x) << 0)
+#define		SH_INDEX(x)     			((x) << 8)
+#define		SE_INDEX(x)     			((x) << 16)
+#define		SH_BROADCAST_WRITES      		(1 << 29)
+#define		INSTANCE_BROADCAST_WRITES      		(1 << 30)
+#define		SE_BROADCAST_WRITES      		(1 << 31)
 
 #define GRBM_INT_CNTL                                   0x8060
 #       define RDERR_INT_ENABLE                         (1 << 0)
@@ -480,6 +491,8 @@
 #define	VGT_TF_MEMORY_BASE				0x89B8
 
 #define CC_GC_SHADER_ARRAY_CONFIG			0x89bc
+#define		INACTIVE_CUS_MASK			0xFFFF0000
+#define		INACTIVE_CUS_SHIFT			16
 #define GC_USER_SHADER_ARRAY_CONFIG			0x89c0
 
 #define	PA_CL_ENHANCE					0x8A14
@@ -688,6 +701,12 @@
 #define RLC_MC_CNTL                                       0xC344
 #define RLC_UCODE_CNTL                                    0xC348
 
+#define PA_SC_RASTER_CONFIG                             0x28350
+#       define RASTER_CONFIG_RB_MAP_0                   0
+#       define RASTER_CONFIG_RB_MAP_1                   1
+#       define RASTER_CONFIG_RB_MAP_2                   2
+#       define RASTER_CONFIG_RB_MAP_3                   3
+
 #define VGT_EVENT_INITIATOR                             0x28a90
 #       define SAMPLE_STREAMOUTSTATS1                   (1 << 0)
 #       define SAMPLE_STREAMOUTSTATS2                   (2 << 0)
diff --git a/fs/fuse/control.c b/fs/fuse/control.c
index 42593c5..03ff5b1 100644
--- a/fs/fuse/control.c
+++ b/fs/fuse/control.c
@@ -75,19 +75,13 @@
 				     unsigned global_limit)
 {
 	unsigned long t;
-	char tmp[32];
 	unsigned limit = (1 << 16) - 1;
 	int err;
 
-	if (*ppos || count >= sizeof(tmp) - 1)
+	if (*ppos)
 		return -EINVAL;
 
-	if (copy_from_user(tmp, buf, count))
-		return -EINVAL;
-
-	tmp[count] = '\0';
-
-	err = strict_strtoul(tmp, 0, &t);
+	err = kstrtoul_from_user(buf, count, 0, &t);
 	if (err)
 		return err;
 
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index df5ac04..334e0b1 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -775,6 +775,8 @@
 static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr,
 			  struct kstat *stat)
 {
+	unsigned int blkbits;
+
 	stat->dev = inode->i_sb->s_dev;
 	stat->ino = attr->ino;
 	stat->mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
@@ -790,7 +792,13 @@
 	stat->ctime.tv_nsec = attr->ctimensec;
 	stat->size = attr->size;
 	stat->blocks = attr->blocks;
-	stat->blksize = (1 << inode->i_blkbits);
+
+	if (attr->blksize != 0)
+		blkbits = ilog2(attr->blksize);
+	else
+		blkbits = inode->i_sb->s_blocksize_bits;
+
+	stat->blksize = 1 << blkbits;
 }
 
 static int fuse_do_getattr(struct inode *inode, struct kstat *stat,
@@ -863,6 +871,7 @@
 		if (stat) {
 			generic_fillattr(inode, stat);
 			stat->mode = fi->orig_i_mode;
+			stat->ino = fi->orig_ino;
 		}
 	}
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 9562109..b321a68 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2173,6 +2173,44 @@
 	return ret;
 }
 
+long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
+			    loff_t length)
+{
+	struct fuse_file *ff = file->private_data;
+	struct fuse_conn *fc = ff->fc;
+	struct fuse_req *req;
+	struct fuse_fallocate_in inarg = {
+		.fh = ff->fh,
+		.offset = offset,
+		.length = length,
+		.mode = mode
+	};
+	int err;
+
+	if (fc->no_fallocate)
+		return -EOPNOTSUPP;
+
+	req = fuse_get_req(fc);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	req->in.h.opcode = FUSE_FALLOCATE;
+	req->in.h.nodeid = ff->nodeid;
+	req->in.numargs = 1;
+	req->in.args[0].size = sizeof(inarg);
+	req->in.args[0].value = &inarg;
+	fuse_request_send(fc, req);
+	err = req->out.h.error;
+	if (err == -ENOSYS) {
+		fc->no_fallocate = 1;
+		err = -EOPNOTSUPP;
+	}
+	fuse_put_request(fc, req);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(fuse_file_fallocate);
+
 static const struct file_operations fuse_file_operations = {
 	.llseek		= fuse_file_llseek,
 	.read		= do_sync_read,
@@ -2190,6 +2228,7 @@
 	.unlocked_ioctl	= fuse_file_ioctl,
 	.compat_ioctl	= fuse_file_compat_ioctl,
 	.poll		= fuse_file_poll,
+	.fallocate	= fuse_file_fallocate,
 };
 
 static const struct file_operations fuse_direct_io_file_operations = {
@@ -2206,6 +2245,7 @@
 	.unlocked_ioctl	= fuse_file_ioctl,
 	.compat_ioctl	= fuse_file_compat_ioctl,
 	.poll		= fuse_file_poll,
+	.fallocate	= fuse_file_fallocate,
 	/* no splice_read */
 };
 
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 572cefc..771fb63 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -82,6 +82,9 @@
 	    preserve the original mode */
 	umode_t orig_i_mode;
 
+	/** 64 bit inode number */
+	u64 orig_ino;
+
 	/** Version of last attribute change */
 	u64 attr_version;
 
@@ -478,6 +481,9 @@
 	/** Are BSD file locking primitives not implemented by fs? */
 	unsigned no_flock:1;
 
+	/** Is fallocate not implemented by fs? */
+	unsigned no_fallocate:1;
+
 	/** The number of requests waiting for completion */
 	atomic_t num_waiting;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 42678a3..1cd6165 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -91,6 +91,7 @@
 	fi->nlookup = 0;
 	fi->attr_version = 0;
 	fi->writectr = 0;
+	fi->orig_ino = 0;
 	INIT_LIST_HEAD(&fi->write_files);
 	INIT_LIST_HEAD(&fi->queued_writes);
 	INIT_LIST_HEAD(&fi->writepages);
@@ -139,6 +140,18 @@
 	return 0;
 }
 
+/*
+ * ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down
+ * so that it will fit.
+ */
+static ino_t fuse_squash_ino(u64 ino64)
+{
+	ino_t ino = (ino_t) ino64;
+	if (sizeof(ino_t) < sizeof(u64))
+		ino ^= ino64 >> (sizeof(u64) - sizeof(ino_t)) * 8;
+	return ino;
+}
+
 void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
 				   u64 attr_valid)
 {
@@ -148,7 +161,7 @@
 	fi->attr_version = ++fc->attr_version;
 	fi->i_time = attr_valid;
 
-	inode->i_ino     = attr->ino;
+	inode->i_ino     = fuse_squash_ino(attr->ino);
 	inode->i_mode    = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
 	set_nlink(inode, attr->nlink);
 	inode->i_uid     = attr->uid;
@@ -174,6 +187,8 @@
 	fi->orig_i_mode = inode->i_mode;
 	if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
 		inode->i_mode &= ~S_ISVTX;
+
+	fi->orig_ino = attr->ino;
 }
 
 void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 58d0bda..81368ab 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -181,6 +181,7 @@
 	{0x1002, 0x6747, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6748, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6749, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x674A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6750, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6751, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6758, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
@@ -198,6 +199,7 @@
 	{0x1002, 0x6767, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6768, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6770, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6771, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6772, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6778, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6779, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
@@ -229,10 +231,11 @@
 	{0x1002, 0x6827, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6828, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6829, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x682B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x6830, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x6831, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6830, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6831, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6837, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6838, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6839, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
@@ -531,6 +534,7 @@
 	{0x1002, 0x9645, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
 	{0x1002, 0x9648, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
+	{0x1002, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
 	{0x1002, 0x964a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x964b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x964c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
@@ -550,6 +554,7 @@
 	{0x1002, 0x9807, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9808, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9809, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x980A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
@@ -561,11 +566,19 @@
 	{0x1002, 0x9909, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x990A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x990F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9910, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9913, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9917, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9918, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9919, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9990, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9991, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9992, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9993, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9994, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x99A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x99A2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x99A4, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0, 0, 0}
 
 #define r128_PCI_IDS \
diff --git a/include/linux/fuse.h b/include/linux/fuse.h
index 8f2ab8f..9303348 100644
--- a/include/linux/fuse.h
+++ b/include/linux/fuse.h
@@ -54,6 +54,9 @@
  * 7.18
  *  - add FUSE_IOCTL_DIR flag
  *  - add FUSE_NOTIFY_DELETE
+ *
+ * 7.19
+ *  - add FUSE_FALLOCATE
  */
 
 #ifndef _LINUX_FUSE_H
@@ -85,7 +88,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 18
+#define FUSE_KERNEL_MINOR_VERSION 19
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -278,6 +281,7 @@
 	FUSE_POLL          = 40,
 	FUSE_NOTIFY_REPLY  = 41,
 	FUSE_BATCH_FORGET  = 42,
+	FUSE_FALLOCATE     = 43,
 
 	/* CUSE specific operations */
 	CUSE_INIT          = 4096,
@@ -571,6 +575,14 @@
 	__u64	kh;
 };
 
+struct fuse_fallocate_in {
+	__u64	fh;
+	__u64	offset;
+	__u64	length;
+	__u32	mode;
+	__u32	padding;
+};
+
 struct fuse_in_header {
 	__u32	len;
 	__u32	opcode;
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index e4baff5..9e65eff 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -149,6 +149,7 @@
 	.normal_prio	= MAX_PRIO-20,					\
 	.policy		= SCHED_NORMAL,					\
 	.cpus_allowed	= CPU_MASK_ALL,					\
+	.nr_cpus_allowed= NR_CPUS,					\
 	.mm		= NULL,						\
 	.active_mm	= &init_mm,					\
 	.se		= {						\
@@ -157,7 +158,6 @@
 	.rt		= {						\
 		.run_list	= LIST_HEAD_INIT(tsk.rt.run_list),	\
 		.time_slice	= RR_TIMESLICE,				\
-		.nr_cpus_allowed = NR_CPUS,				\
 	},								\
 	.tasks		= LIST_HEAD_INIT(tsk.tasks),			\
 	INIT_PUSHABLE_TASKS(tsk)					\
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 0d04cd6..ffc444c 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -368,8 +368,11 @@
 			iter->index++;
 			if (likely(*slot))
 				return slot;
-			if (flags & RADIX_TREE_ITER_CONTIG)
+			if (flags & RADIX_TREE_ITER_CONTIG) {
+				/* forbid switching to the next chunk */
+				iter->next_index = 0;
 				break;
+			}
 		}
 	}
 	return NULL;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f34437e..6029d8c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -145,6 +145,7 @@
 
 
 extern void calc_global_load(unsigned long ticks);
+extern void update_cpu_load_nohz(void);
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
@@ -1187,7 +1188,6 @@
 	struct list_head run_list;
 	unsigned long timeout;
 	unsigned int time_slice;
-	int nr_cpus_allowed;
 
 	struct sched_rt_entity *back;
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -1252,6 +1252,7 @@
 #endif
 
 	unsigned int policy;
+	int nr_cpus_allowed;
 	cpumask_t cpus_allowed;
 
 #ifdef CONFIG_PREEMPT_RCU
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 39eb601..c46958e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -142,9 +142,8 @@
 #define SCHED_FEAT(name, enabled)	\
 	#name ,
 
-static __read_mostly char *sched_feat_names[] = {
+static const char * const sched_feat_names[] = {
 #include "features.h"
-	NULL
 };
 
 #undef SCHED_FEAT
@@ -2517,25 +2516,32 @@
 	sched_avg_update(this_rq);
 }
 
+#ifdef CONFIG_NO_HZ
+/*
+ * There is no sane way to deal with nohz on smp when using jiffies because the
+ * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
+ * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
+ *
+ * Therefore we cannot use the delta approach from the regular tick since that
+ * would seriously skew the load calculation. However we'll make do for those
+ * updates happening while idle (nohz_idle_balance) or coming out of idle
+ * (tick_nohz_idle_exit).
+ *
+ * This means we might still be one tick off for nohz periods.
+ */
+
 /*
  * Called from nohz_idle_balance() to update the load ratings before doing the
  * idle balance.
  */
 void update_idle_cpu_load(struct rq *this_rq)
 {
-	unsigned long curr_jiffies = jiffies;
+	unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
 	unsigned long load = this_rq->load.weight;
 	unsigned long pending_updates;
 
 	/*
-	 * Bloody broken means of dealing with nohz, but better than nothing..
-	 * jiffies is updated by one cpu, another cpu can drift wrt the jiffy
-	 * update and see 0 difference the one time and 2 the next, even though
-	 * we ticked at roughtly the same rate.
-	 *
-	 * Hence we only use this from nohz_idle_balance() and skip this
-	 * nonsense when called from the scheduler_tick() since that's
-	 * guaranteed a stable rate.
+	 * bail if there's load or we're actually up-to-date.
 	 */
 	if (load || curr_jiffies == this_rq->last_load_update_tick)
 		return;
@@ -2547,12 +2553,38 @@
 }
 
 /*
+ * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
+ */
+void update_cpu_load_nohz(void)
+{
+	struct rq *this_rq = this_rq();
+	unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
+	unsigned long pending_updates;
+
+	if (curr_jiffies == this_rq->last_load_update_tick)
+		return;
+
+	raw_spin_lock(&this_rq->lock);
+	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+	if (pending_updates) {
+		this_rq->last_load_update_tick = curr_jiffies;
+		/*
+		 * We were idle, this means load 0, the current load might be
+		 * !0 due to remote wakeups and the sort.
+		 */
+		__update_cpu_load(this_rq, 0, pending_updates);
+	}
+	raw_spin_unlock(&this_rq->lock);
+}
+#endif /* CONFIG_NO_HZ */
+
+/*
  * Called from scheduler_tick()
  */
 static void update_cpu_load_active(struct rq *this_rq)
 {
 	/*
-	 * See the mess in update_idle_cpu_load().
+	 * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
 	 */
 	this_rq->last_load_update_tick = jiffies;
 	__update_cpu_load(this_rq, this_rq->load.weight, 1);
@@ -4982,7 +5014,7 @@
 		p->sched_class->set_cpus_allowed(p, new_mask);
 
 	cpumask_copy(&p->cpus_allowed, new_mask);
-	p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
+	p->nr_cpus_allowed = cpumask_weight(new_mask);
 }
 
 /*
@@ -5997,11 +6029,14 @@
 
 		cpumask_or(covered, covered, sg_span);
 
-		sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span));
+		sg->sgp = *per_cpu_ptr(sdd->sgp, i);
 		atomic_inc(&sg->sgp->ref);
 
-		if (cpumask_test_cpu(cpu, sg_span))
+		if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
+			       cpumask_first(sg_span) == cpu) {
+			WARN_ON_ONCE(!cpumask_test_cpu(cpu, sg_span));
 			groups = sg;
+		}
 
 		if (!first)
 			first = sg;
@@ -6403,7 +6438,7 @@
 			return;
 
 		for (j = 0; j < nr_node_ids; j++) {
-			struct cpumask *mask = kzalloc_node(cpumask_size(), GFP_KERNEL, j);
+			struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
 			if (!mask)
 				return;
 
@@ -6691,7 +6726,6 @@
 	if (!doms_cur)
 		doms_cur = &fallback_doms;
 	cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
-	dattr_cur = NULL;
 	err = build_sched_domains(doms_cur[0], NULL);
 	register_sched_domain_sysctl();
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 940e6d1..b2a2d23 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2703,7 +2703,7 @@
 	int want_sd = 1;
 	int sync = wake_flags & WF_SYNC;
 
-	if (p->rt.nr_cpus_allowed == 1)
+	if (p->nr_cpus_allowed == 1)
 		return prev_cpu;
 
 	if (sd_flag & SD_BALANCE_WAKE) {
@@ -3503,15 +3503,22 @@
 unsigned long scale_rt_power(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	u64 total, available;
+	u64 total, available, age_stamp, avg;
 
-	total = sched_avg_period() + (rq->clock - rq->age_stamp);
+	/*
+	 * Since we're reading these variables without serialization make sure
+	 * we read them once before doing sanity checks on them.
+	 */
+	age_stamp = ACCESS_ONCE(rq->age_stamp);
+	avg = ACCESS_ONCE(rq->rt_avg);
 
-	if (unlikely(total < rq->rt_avg)) {
+	total = sched_avg_period() + (rq->clock - age_stamp);
+
+	if (unlikely(total < avg)) {
 		/* Ensures that power won't end up being negative */
 		available = 0;
 	} else {
-		available = total - rq->rt_avg;
+		available = total - avg;
 	}
 
 	if (unlikely((s64)total < SCHED_POWER_SCALE))
@@ -3574,11 +3581,26 @@
 
 	power = 0;
 
-	group = child->groups;
-	do {
-		power += group->sgp->power;
-		group = group->next;
-	} while (group != child->groups);
+	if (child->flags & SD_OVERLAP) {
+		/*
+		 * SD_OVERLAP domains cannot assume that child groups
+		 * span the current group.
+		 */
+
+		for_each_cpu(cpu, sched_group_cpus(sdg))
+			power += power_of(cpu);
+	} else  {
+		/*
+		 * !SD_OVERLAP domains can assume that child groups
+		 * span the current group.
+		 */ 
+
+		group = child->groups;
+		do {
+			power += group->sgp->power;
+			group = group->next;
+		} while (group != child->groups);
+	}
 
 	sdg->sgp->power = power;
 }
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index c5565c3..2a4e8df 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -274,13 +274,16 @@
 
 static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
+	struct task_struct *p;
+
 	if (!rt_entity_is_task(rt_se))
 		return;
 
+	p = rt_task_of(rt_se);
 	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
 
 	rt_rq->rt_nr_total++;
-	if (rt_se->nr_cpus_allowed > 1)
+	if (p->nr_cpus_allowed > 1)
 		rt_rq->rt_nr_migratory++;
 
 	update_rt_migration(rt_rq);
@@ -288,13 +291,16 @@
 
 static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
+	struct task_struct *p;
+
 	if (!rt_entity_is_task(rt_se))
 		return;
 
+	p = rt_task_of(rt_se);
 	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
 
 	rt_rq->rt_nr_total--;
-	if (rt_se->nr_cpus_allowed > 1)
+	if (p->nr_cpus_allowed > 1)
 		rt_rq->rt_nr_migratory--;
 
 	update_rt_migration(rt_rq);
@@ -1161,7 +1167,7 @@
 
 	enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
 
-	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
+	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
 
 	inc_nr_running(rq);
@@ -1225,7 +1231,7 @@
 
 	cpu = task_cpu(p);
 
-	if (p->rt.nr_cpus_allowed == 1)
+	if (p->nr_cpus_allowed == 1)
 		goto out;
 
 	/* For anything but wake ups, just return the task_cpu */
@@ -1260,9 +1266,9 @@
 	 * will have to sort it out.
 	 */
 	if (curr && unlikely(rt_task(curr)) &&
-	    (curr->rt.nr_cpus_allowed < 2 ||
+	    (curr->nr_cpus_allowed < 2 ||
 	     curr->prio <= p->prio) &&
-	    (p->rt.nr_cpus_allowed > 1)) {
+	    (p->nr_cpus_allowed > 1)) {
 		int target = find_lowest_rq(p);
 
 		if (target != -1)
@@ -1276,10 +1282,10 @@
 
 static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 {
-	if (rq->curr->rt.nr_cpus_allowed == 1)
+	if (rq->curr->nr_cpus_allowed == 1)
 		return;
 
-	if (p->rt.nr_cpus_allowed != 1
+	if (p->nr_cpus_allowed != 1
 	    && cpupri_find(&rq->rd->cpupri, p, NULL))
 		return;
 
@@ -1395,7 +1401,7 @@
 	 * The previous task needs to be made eligible for pushing
 	 * if it is still active
 	 */
-	if (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1)
+	if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
 }
 
@@ -1408,7 +1414,7 @@
 {
 	if (!task_running(rq, p) &&
 	    (cpu < 0 || cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) &&
-	    (p->rt.nr_cpus_allowed > 1))
+	    (p->nr_cpus_allowed > 1))
 		return 1;
 	return 0;
 }
@@ -1464,7 +1470,7 @@
 	if (unlikely(!lowest_mask))
 		return -1;
 
-	if (task->rt.nr_cpus_allowed == 1)
+	if (task->nr_cpus_allowed == 1)
 		return -1; /* No other targets possible */
 
 	if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
@@ -1586,7 +1592,7 @@
 
 	BUG_ON(rq->cpu != task_cpu(p));
 	BUG_ON(task_current(rq, p));
-	BUG_ON(p->rt.nr_cpus_allowed <= 1);
+	BUG_ON(p->nr_cpus_allowed <= 1);
 
 	BUG_ON(!p->on_rq);
 	BUG_ON(!rt_task(p));
@@ -1793,9 +1799,9 @@
 	if (!task_running(rq, p) &&
 	    !test_tsk_need_resched(rq->curr) &&
 	    has_pushable_tasks(rq) &&
-	    p->rt.nr_cpus_allowed > 1 &&
+	    p->nr_cpus_allowed > 1 &&
 	    rt_task(rq->curr) &&
-	    (rq->curr->rt.nr_cpus_allowed < 2 ||
+	    (rq->curr->nr_cpus_allowed < 2 ||
 	     rq->curr->prio <= p->prio))
 		push_rt_tasks(rq);
 }
@@ -1817,7 +1823,7 @@
 	 * Only update if the process changes its state from whether it
 	 * can migrate or not.
 	 */
-	if ((p->rt.nr_cpus_allowed > 1) == (weight > 1))
+	if ((p->nr_cpus_allowed > 1) == (weight > 1))
 		return;
 
 	rq = task_rq(p);
@@ -1979,6 +1985,8 @@
 
 static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 {
+	struct sched_rt_entity *rt_se = &p->rt;
+
 	update_curr_rt(rq);
 
 	watchdog(rq, p);
@@ -1996,12 +2004,15 @@
 	p->rt.time_slice = RR_TIMESLICE;
 
 	/*
-	 * Requeue to the end of queue if we are not the only element
-	 * on the queue:
+	 * Requeue to the end of queue if we (and all of our ancestors) are the
+	 * only element on the queue
 	 */
-	if (p->rt.run_list.prev != p->rt.run_list.next) {
-		requeue_task_rt(rq, p, 0);
-		set_tsk_need_resched(p);
+	for_each_sched_rt_entity(rt_se) {
+		if (rt_se->run_list.prev != rt_se->run_list.next) {
+			requeue_task_rt(rq, p, 0);
+			set_tsk_need_resched(p);
+			return;
+		}
 	}
 }
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index efd3866..da70c6d 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -576,6 +576,7 @@
 	/* Update jiffies first */
 	select_nohz_load_balancer(0);
 	tick_do_update_jiffies64(now);
+	update_cpu_load_nohz();
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 	/*
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index d7c878c..e796429 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -686,6 +686,9 @@
 	 * during iterating; it can be zero only at the beginning.
 	 * And we cannot overflow iter->next_index in a single step,
 	 * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG.
+	 *
+	 * This condition also used by radix_tree_next_slot() to stop
+	 * contiguous iterating, and forbid swithing to the next chunk.
 	 */
 	index = iter->next_index;
 	if (!index && iter->index)