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

Pull drm fixes from Dave Airlie:
 "I'm briefly working between holidays and LCA, so this is close to a
  couple of weeks of fixes,

  Two sets of amdkfd fixes, this is a new feature this kernel, and this
  pull fixes a few issues since it got merged, ordering when built-in to
  kernel and also the iommu vs gpu ordering patch, it also reworks the
  ioctl before the initial release.

  Otherwise:
   - radeon: some misc fixes all over, hdmi, 4k, dpm
   - nouveau: mcp77 init fixes, oops fix, bug on fix, msi fix
   - i915: power fixes, revert VGACNTR patch

  Probably be quiteer next week since I'll be at LCA anyways"

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux: (33 commits)
  drm/amdkfd: rewrite kfd_ioctl() according to drm_ioctl()
  drm/amdkfd: reformat IOCTL definitions to drm-style
  drm/amdkfd: Do copy_to/from_user in general kfd_ioctl()
  drm/radeon: integer underflow in radeon_cp_dispatch_texture()
  drm/radeon: adjust default bapm settings for KV
  drm/radeon: properly filter DP1.2 4k modes on non-DP1.2 hw
  drm/radeon: fix sad_count check for dce3
  drm/radeon: KV has three PPLLs (v2)
  drm/amdkfd: unmap VMID<-->PASID when relesing VMID (non-HWS)
  drm/radeon: Init amdkfd only if it was compiled
  amdkfd: actually allocate longs for the pasid bitmask
  drm/nouveau/nouveau: Do not BUG_ON(!spin_is_locked()) on UP
  drm/nv4c/mc: disable msi
  drm/nouveau/fb/ram/mcp77: enable NISO poller
  drm/nouveau/fb/ram/mcp77: use carveout reg to determine size
  drm/nouveau/fb/ram/mcp77: subclass nouveau_ram
  drm/nouveau: wake up the card if necessary during gem callbacks
  drm/nouveau/device: Add support for GK208B, resolves bug 86935
  drm/nouveau: fix missing return statement in nouveau_ttm_tt_unpopulate
  drm/nouveau/bios: fix oops on pre-nv50 chipsets
  ...

29 files changed, 391 insertions, 246 deletions

diff --git a/drivers/Makefile b/drivers/Makefile
index 67d2334dc41e..527a6da8d539 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -50,7 +50,10 @@ obj-$(CONFIG_RESET_CONTROLLER)	+= reset/
 obj-y				+= tty/
 obj-y				+= char/
 
-# gpu/ comes after char for AGP vs DRM startup
+# iommu/ comes before gpu as gpu are using iommu controllers
+obj-$(CONFIG_IOMMU_SUPPORT)	+= iommu/
+
+# gpu/ comes after char for AGP vs DRM startup and after iommu
 obj-y				+= gpu/
 
 obj-$(CONFIG_CONNECTOR)		+= connector/
@@ -141,7 +144,6 @@ obj-y				+= clk/
 
 obj-$(CONFIG_MAILBOX)		+= mailbox/
 obj-$(CONFIG_HWSPINLOCK)	+= hwspinlock/
-obj-$(CONFIG_IOMMU_SUPPORT)	+= iommu/
 obj-$(CONFIG_REMOTEPROC)	+= remoteproc/
 obj-$(CONFIG_RPMSG)		+= rpmsg/
 
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 66e40398b3d3..e620807418ea 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -37,6 +37,7 @@ obj-$(CONFIG_DRM_MIPI_DSI) += drm_mipi_dsi.o
 obj-$(CONFIG_DRM_TTM)	+= ttm/
 obj-$(CONFIG_DRM_TDFX)	+= tdfx/
 obj-$(CONFIG_DRM_R128)	+= r128/
+obj-$(CONFIG_HSA_AMD) += amd/amdkfd/
 obj-$(CONFIG_DRM_RADEON)+= radeon/
 obj-$(CONFIG_DRM_MGA)	+= mga/
 obj-$(CONFIG_DRM_I810)	+= i810/
@@ -67,4 +68,3 @@ obj-$(CONFIG_DRM_IMX) += imx/
 obj-y			+= i2c/
 obj-y			+= panel/
 obj-y			+= bridge/
-obj-$(CONFIG_HSA_AMD) += amd/amdkfd/
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 7d4974b83af7..fcfdf23e1913 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -31,7 +31,6 @@
 #include <uapi/linux/kfd_ioctl.h>
 #include <linux/time.h>
 #include <linux/mm.h>
-#include <linux/uaccess.h>
 #include <uapi/asm-generic/mman-common.h>
 #include <asm/processor.h>
 #include "kfd_priv.h"
@@ -127,17 +126,14 @@ static int kfd_open(struct inode *inode, struct file *filep)
 	return 0;
 }
 
-static long kfd_ioctl_get_version(struct file *filep, struct kfd_process *p,
-					void __user *arg)
+static int kfd_ioctl_get_version(struct file *filep, struct kfd_process *p,
+					void *data)
 {
-	struct kfd_ioctl_get_version_args args;
+	struct kfd_ioctl_get_version_args *args = data;
 	int err = 0;
 
-	args.major_version = KFD_IOCTL_MAJOR_VERSION;
-	args.minor_version = KFD_IOCTL_MINOR_VERSION;
-
-	if (copy_to_user(arg, &args, sizeof(args)))
-		err = -EFAULT;
+	args->major_version = KFD_IOCTL_MAJOR_VERSION;
+	args->minor_version = KFD_IOCTL_MINOR_VERSION;
 
 	return err;
 }
@@ -221,10 +217,10 @@ static int set_queue_properties_from_user(struct queue_properties *q_properties,
 	return 0;
 }
 
-static long kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
-					void __user *arg)
+static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
+					void *data)
 {
-	struct kfd_ioctl_create_queue_args args;
+	struct kfd_ioctl_create_queue_args *args = data;
 	struct kfd_dev *dev;
 	int err = 0;
 	unsigned int queue_id;
@@ -233,16 +229,13 @@ static long kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 
 	memset(&q_properties, 0, sizeof(struct queue_properties));
 
-	if (copy_from_user(&args, arg, sizeof(args)))
-		return -EFAULT;
-
 	pr_debug("kfd: creating queue ioctl\n");
 
-	err = set_queue_properties_from_user(&q_properties, &args);
+	err = set_queue_properties_from_user(&q_properties, args);
 	if (err)
 		return err;
 
-	dev = kfd_device_by_id(args.gpu_id);
+	dev = kfd_device_by_id(args->gpu_id);
 	if (dev == NULL)
 		return -EINVAL;
 
@@ -250,7 +243,7 @@ static long kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 
 	pdd = kfd_bind_process_to_device(dev, p);
 	if (IS_ERR(pdd)) {
-		err = PTR_ERR(pdd);
+		err = -ESRCH;
 		goto err_bind_process;
 	}
 
@@ -263,33 +256,26 @@ static long kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 	if (err != 0)
 		goto err_create_queue;
 
-	args.queue_id = queue_id;
+	args->queue_id = queue_id;
 
 	/* Return gpu_id as doorbell offset for mmap usage */
-	args.doorbell_offset = args.gpu_id << PAGE_SHIFT;
-
-	if (copy_to_user(arg, &args, sizeof(args))) {
-		err = -EFAULT;
-		goto err_copy_args_out;
-	}
+	args->doorbell_offset = args->gpu_id << PAGE_SHIFT;
 
 	mutex_unlock(&p->mutex);
 
-	pr_debug("kfd: queue id %d was created successfully\n", args.queue_id);
+	pr_debug("kfd: queue id %d was created successfully\n", args->queue_id);
 
 	pr_debug("ring buffer address == 0x%016llX\n",
-			args.ring_base_address);
+			args->ring_base_address);
 
 	pr_debug("read ptr address    == 0x%016llX\n",
-			args.read_pointer_address);
+			args->read_pointer_address);
 
 	pr_debug("write ptr address   == 0x%016llX\n",
-			args.write_pointer_address);
+			args->write_pointer_address);
 
 	return 0;
 
-err_copy_args_out:
-	pqm_destroy_queue(&p->pqm, queue_id);
 err_create_queue:
 err_bind_process:
 	mutex_unlock(&p->mutex);
@@ -297,99 +283,90 @@ err_bind_process:
 }
 
 static int kfd_ioctl_destroy_queue(struct file *filp, struct kfd_process *p,
-					void __user *arg)
+					void *data)
 {
 	int retval;
-	struct kfd_ioctl_destroy_queue_args args;
-
-	if (copy_from_user(&args, arg, sizeof(args)))
-		return -EFAULT;
+	struct kfd_ioctl_destroy_queue_args *args = data;
 
 	pr_debug("kfd: destroying queue id %d for PASID %d\n",
-				args.queue_id,
+				args->queue_id,
 				p->pasid);
 
 	mutex_lock(&p->mutex);
 
-	retval = pqm_destroy_queue(&p->pqm, args.queue_id);
+	retval = pqm_destroy_queue(&p->pqm, args->queue_id);
 
 	mutex_unlock(&p->mutex);
 	return retval;
 }
 
 static int kfd_ioctl_update_queue(struct file *filp, struct kfd_process *p,
-					void __user *arg)
+					void *data)
 {
 	int retval;
-	struct kfd_ioctl_update_queue_args args;
+	struct kfd_ioctl_update_queue_args *args = data;
 	struct queue_properties properties;
 
-	if (copy_from_user(&args, arg, sizeof(args)))
-		return -EFAULT;
-
-	if (args.queue_percentage > KFD_MAX_QUEUE_PERCENTAGE) {
+	if (args->queue_percentage > KFD_MAX_QUEUE_PERCENTAGE) {
 		pr_err("kfd: queue percentage must be between 0 to KFD_MAX_QUEUE_PERCENTAGE\n");
 		return -EINVAL;
 	}
 
-	if (args.queue_priority > KFD_MAX_QUEUE_PRIORITY) {
+	if (args->queue_priority > KFD_MAX_QUEUE_PRIORITY) {
 		pr_err("kfd: queue priority must be between 0 to KFD_MAX_QUEUE_PRIORITY\n");
 		return -EINVAL;
 	}
 
-	if ((args.ring_base_address) &&
+	if ((args->ring_base_address) &&
 		(!access_ok(VERIFY_WRITE,
-			(const void __user *) args.ring_base_address,
+			(const void __user *) args->ring_base_address,
 			sizeof(uint64_t)))) {
 		pr_err("kfd: can't access ring base address\n");
 		return -EFAULT;
 	}
 
-	if (!is_power_of_2(args.ring_size) && (args.ring_size != 0)) {
+	if (!is_power_of_2(args->ring_size) && (args->ring_size != 0)) {
 		pr_err("kfd: ring size must be a power of 2 or 0\n");
 		return -EINVAL;
 	}
 
-	properties.queue_address = args.ring_base_address;
-	properties.queue_size = args.ring_size;
-	properties.queue_percent = args.queue_percentage;
-	properties.priority = args.queue_priority;
+	properties.queue_address = args->ring_base_address;
+	properties.queue_size = args->ring_size;
+	properties.queue_percent = args->queue_percentage;
+	properties.priority = args->queue_priority;
 
 	pr_debug("kfd: updating queue id %d for PASID %d\n",
-			args.queue_id, p->pasid);
+			args->queue_id, p->pasid);
 
 	mutex_lock(&p->mutex);
 
-	retval = pqm_update_queue(&p->pqm, args.queue_id, &properties);
+	retval = pqm_update_queue(&p->pqm, args->queue_id, &properties);
 
 	mutex_unlock(&p->mutex);
 
 	return retval;
 }
 
-static long kfd_ioctl_set_memory_policy(struct file *filep,
-				struct kfd_process *p, void __user *arg)
+static int kfd_ioctl_set_memory_policy(struct file *filep,
+					struct kfd_process *p, void *data)
 {
-	struct kfd_ioctl_set_memory_policy_args args;
+	struct kfd_ioctl_set_memory_policy_args *args = data;
 	struct kfd_dev *dev;
 	int err = 0;
 	struct kfd_process_device *pdd;
 	enum cache_policy default_policy, alternate_policy;
 
-	if (copy_from_user(&args, arg, sizeof(args)))
-		return -EFAULT;
-
-	if (args.default_policy != KFD_IOC_CACHE_POLICY_COHERENT
-	    && args.default_policy != KFD_IOC_CACHE_POLICY_NONCOHERENT) {
+	if (args->default_policy != KFD_IOC_CACHE_POLICY_COHERENT
+	    && args->default_policy != KFD_IOC_CACHE_POLICY_NONCOHERENT) {
 		return -EINVAL;
 	}
 
-	if (args.alternate_policy != KFD_IOC_CACHE_POLICY_COHERENT
-	    && args.alternate_policy != KFD_IOC_CACHE_POLICY_NONCOHERENT) {
+	if (args->alternate_policy != KFD_IOC_CACHE_POLICY_COHERENT
+	    && args->alternate_policy != KFD_IOC_CACHE_POLICY_NONCOHERENT) {
 		return -EINVAL;
 	}
 
-	dev = kfd_device_by_id(args.gpu_id);
+	dev = kfd_device_by_id(args->gpu_id);
 	if (dev == NULL)
 		return -EINVAL;
 
@@ -397,23 +374,23 @@ static long kfd_ioctl_set_memory_policy(struct file *filep,
 
 	pdd = kfd_bind_process_to_device(dev, p);
 	if (IS_ERR(pdd)) {
-		err = PTR_ERR(pdd);
+		err = -ESRCH;
 		goto out;
 	}
 
-	default_policy = (args.default_policy == KFD_IOC_CACHE_POLICY_COHERENT)
+	default_policy = (args->default_policy == KFD_IOC_CACHE_POLICY_COHERENT)
 			 ? cache_policy_coherent : cache_policy_noncoherent;
 
 	alternate_policy =
-		(args.alternate_policy == KFD_IOC_CACHE_POLICY_COHERENT)
+		(args->alternate_policy == KFD_IOC_CACHE_POLICY_COHERENT)
 		   ? cache_policy_coherent : cache_policy_noncoherent;
 
 	if (!dev->dqm->set_cache_memory_policy(dev->dqm,
 				&pdd->qpd,
 				default_policy,
 				alternate_policy,
-				(void __user *)args.alternate_aperture_base,
-				args.alternate_aperture_size))
+				(void __user *)args->alternate_aperture_base,
+				args->alternate_aperture_size))
 		err = -EINVAL;
 
 out:
@@ -422,53 +399,44 @@ out:
 	return err;
 }
 
-static long kfd_ioctl_get_clock_counters(struct file *filep,
-				struct kfd_process *p, void __user *arg)
+static int kfd_ioctl_get_clock_counters(struct file *filep,
+				struct kfd_process *p, void *data)
 {
-	struct kfd_ioctl_get_clock_counters_args args;
+	struct kfd_ioctl_get_clock_counters_args *args = data;
 	struct kfd_dev *dev;
 	struct timespec time;
 
-	if (copy_from_user(&args, arg, sizeof(args)))
-		return -EFAULT;
-
-	dev = kfd_device_by_id(args.gpu_id);
+	dev = kfd_device_by_id(args->gpu_id);
 	if (dev == NULL)
 		return -EINVAL;
 
 	/* Reading GPU clock counter from KGD */
-	args.gpu_clock_counter = kfd2kgd->get_gpu_clock_counter(dev->kgd);
+	args->gpu_clock_counter = kfd2kgd->get_gpu_clock_counter(dev->kgd);
 
 	/* No access to rdtsc. Using raw monotonic time */
 	getrawmonotonic(&time);
-	args.cpu_clock_counter = (uint64_t)timespec_to_ns(&time);
+	args->cpu_clock_counter = (uint64_t)timespec_to_ns(&time);
 
 	get_monotonic_boottime(&time);
-	args.system_clock_counter = (uint64_t)timespec_to_ns(&time);
+	args->system_clock_counter = (uint64_t)timespec_to_ns(&time);
 
 	/* Since the counter is in nano-seconds we use 1GHz frequency */
-	args.system_clock_freq = 1000000000;
-
-	if (copy_to_user(arg, &args, sizeof(args)))
-		return -EFAULT;
+	args->system_clock_freq = 1000000000;
 
 	return 0;
 }
 
 
 static int kfd_ioctl_get_process_apertures(struct file *filp,
-				struct kfd_process *p, void __user *arg)
+				struct kfd_process *p, void *data)
 {
-	struct kfd_ioctl_get_process_apertures_args args;
+	struct kfd_ioctl_get_process_apertures_args *args = data;
 	struct kfd_process_device_apertures *pAperture;
 	struct kfd_process_device *pdd;
 
 	dev_dbg(kfd_device, "get apertures for PASID %d", p->pasid);
 
-	if (copy_from_user(&args, arg, sizeof(args)))
-		return -EFAULT;
-
-	args.num_of_nodes = 0;
+	args->num_of_nodes = 0;
 
 	mutex_lock(&p->mutex);
 
@@ -477,7 +445,8 @@ static int kfd_ioctl_get_process_apertures(struct file *filp,
 		/* Run over all pdd of the process */
 		pdd = kfd_get_first_process_device_data(p);
 		do {
-			pAperture = &args.process_apertures[args.num_of_nodes];
+			pAperture =
+				&args->process_apertures[args->num_of_nodes];
 			pAperture->gpu_id = pdd->dev->id;
 			pAperture->lds_base = pdd->lds_base;
 			pAperture->lds_limit = pdd->lds_limit;
@@ -487,7 +456,7 @@ static int kfd_ioctl_get_process_apertures(struct file *filp,
 			pAperture->scratch_limit = pdd->scratch_limit;
 
 			dev_dbg(kfd_device,
-				"node id %u\n", args.num_of_nodes);
+				"node id %u\n", args->num_of_nodes);
 			dev_dbg(kfd_device,
 				"gpu id %u\n", pdd->dev->id);
 			dev_dbg(kfd_device,
@@ -503,80 +472,131 @@ static int kfd_ioctl_get_process_apertures(struct file *filp,
 			dev_dbg(kfd_device,
 				"scratch_limit %llX\n", pdd->scratch_limit);
 
-			args.num_of_nodes++;
+			args->num_of_nodes++;
 		} while ((pdd = kfd_get_next_process_device_data(p, pdd)) != NULL &&
-				(args.num_of_nodes < NUM_OF_SUPPORTED_GPUS));
+				(args->num_of_nodes < NUM_OF_SUPPORTED_GPUS));
 	}
 
 	mutex_unlock(&p->mutex);
 
-	if (copy_to_user(arg, &args, sizeof(args)))
-		return -EFAULT;
-
 	return 0;
 }
 
+#define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \
+	[_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, .cmd_drv = 0, .name = #ioctl}
+
+/** Ioctl table */
+static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = {
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_GET_VERSION,
+			kfd_ioctl_get_version, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_CREATE_QUEUE,
+			kfd_ioctl_create_queue, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_DESTROY_QUEUE,
+			kfd_ioctl_destroy_queue, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_MEMORY_POLICY,
+			kfd_ioctl_set_memory_policy, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_GET_CLOCK_COUNTERS,
+			kfd_ioctl_get_clock_counters, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_GET_PROCESS_APERTURES,
+			kfd_ioctl_get_process_apertures, 0),
+
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_UPDATE_QUEUE,
+			kfd_ioctl_update_queue, 0),
+};
+
+#define AMDKFD_CORE_IOCTL_COUNT	ARRAY_SIZE(amdkfd_ioctls)
+
 static long kfd_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 {
 	struct kfd_process *process;
-	long err = -EINVAL;
+	amdkfd_ioctl_t *func;
+	const struct amdkfd_ioctl_desc *ioctl = NULL;
+	unsigned int nr = _IOC_NR(cmd);
+	char stack_kdata[128];
+	char *kdata = NULL;
+	unsigned int usize, asize;
+	int retcode = -EINVAL;
 
-	dev_dbg(kfd_device,
-		"ioctl cmd 0x%x (#%d), arg 0x%lx\n",
-		cmd, _IOC_NR(cmd), arg);
+	if (nr >= AMDKFD_CORE_IOCTL_COUNT)
+		goto err_i1;
+
+	if ((nr >= AMDKFD_COMMAND_START) && (nr < AMDKFD_COMMAND_END)) {
+		u32 amdkfd_size;
+
+		ioctl = &amdkfd_ioctls[nr];
+
+		amdkfd_size = _IOC_SIZE(ioctl->cmd);
+		usize = asize = _IOC_SIZE(cmd);
+		if (amdkfd_size > asize)
+			asize = amdkfd_size;
+
+		cmd = ioctl->cmd;
+	} else
+		goto err_i1;
+
+	dev_dbg(kfd_device, "ioctl cmd 0x%x (#%d), arg 0x%lx\n", cmd, nr, arg);
 
 	process = kfd_get_process(current);
-	if (IS_ERR(process))
-		return PTR_ERR(process);
+	if (IS_ERR(process)) {
+		dev_dbg(kfd_device, "no process\n");
+		goto err_i1;
+	}
 
-	switch (cmd) {
-	case KFD_IOC_GET_VERSION:
-		err = kfd_ioctl_get_version(filep, process, (void __user *)arg);
-		break;
-	case KFD_IOC_CREATE_QUEUE:
-		err = kfd_ioctl_create_queue(filep, process,
-						(void __user *)arg);
-		break;
-
-	case KFD_IOC_DESTROY_QUEUE:
-		err = kfd_ioctl_destroy_queue(filep, process,
-						(void __user *)arg);
-		break;
-
-	case KFD_IOC_SET_MEMORY_POLICY:
-		err = kfd_ioctl_set_memory_policy(filep, process,
-						(void __user *)arg);
-		break;
-
-	case KFD_IOC_GET_CLOCK_COUNTERS:
-		err = kfd_ioctl_get_clock_counters(filep, process,
-						(void __user *)arg);
-		break;
-
-	case KFD_IOC_GET_PROCESS_APERTURES:
-		err = kfd_ioctl_get_process_apertures(filep, process,
-						(void __user *)arg);
-		break;
-
-	case KFD_IOC_UPDATE_QUEUE:
-		err = kfd_ioctl_update_queue(filep, process,
-						(void __user *)arg);
-		break;
-
-	default:
-		dev_err(kfd_device,
-			"unknown ioctl cmd 0x%x, arg 0x%lx)\n",
-			cmd, arg);
-		err = -EINVAL;
-		break;
+	/* Do not trust userspace, use our own definition */
+	func = ioctl->func;
+
+	if (unlikely(!func)) {
+		dev_dbg(kfd_device, "no function\n");
+		retcode = -EINVAL;
+		goto err_i1;
 	}
 
-	if (err < 0)
-		dev_err(kfd_device,
-			"ioctl error %ld for ioctl cmd 0x%x (#%d)\n",
-			err, cmd, _IOC_NR(cmd));
+	if (cmd & (IOC_IN | IOC_OUT)) {
+		if (asize <= sizeof(stack_kdata)) {
+			kdata = stack_kdata;
+		} else {
+			kdata = kmalloc(asize, GFP_KERNEL);
+			if (!kdata) {
+				retcode = -ENOMEM;
+				goto err_i1;
+			}
+		}
+		if (asize > usize)
+			memset(kdata + usize, 0, asize - usize);
+	}
 
-	return err;
+	if (cmd & IOC_IN) {
+		if (copy_from_user(kdata, (void __user *)arg, usize) != 0) {
+			retcode = -EFAULT;
+			goto err_i1;
+		}
+	} else if (cmd & IOC_OUT) {
+		memset(kdata, 0, usize);
+	}
+
+	retcode = func(filep, process, kdata);
+
+	if (cmd & IOC_OUT)
+		if (copy_to_user((void __user *)arg, kdata, usize) != 0)
+			retcode = -EFAULT;
+
+err_i1:
+	if (!ioctl)
+		dev_dbg(kfd_device, "invalid ioctl: pid=%d, cmd=0x%02x, nr=0x%02x\n",
+			  task_pid_nr(current), cmd, nr);
+
+	if (kdata != stack_kdata)
+		kfree(kdata);
+
+	if (retcode)
+		dev_dbg(kfd_device, "ret = %d\n", retcode);
+
+	return retcode;
 }
 
 static int kfd_mmap(struct file *filp, struct vm_area_struct *vma)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 924e90c072e5..9c8961d22360 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -161,6 +161,9 @@ static void deallocate_vmid(struct device_queue_manager *dqm,
 {
 	int bit = qpd->vmid - KFD_VMID_START_OFFSET;
 
+	/* Release the vmid mapping */
+	set_pasid_vmid_mapping(dqm, 0, qpd->vmid);
+
 	set_bit(bit, (unsigned long *)&dqm->vmid_bitmap);
 	qpd->vmid = 0;
 	q->properties.vmid = 0;
@@ -272,6 +275,18 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 		return retval;
 	}
 
+	pr_debug("kfd: loading mqd to hqd on pipe (%d) queue (%d)\n",
+			q->pipe,
+			q->queue);
+
+	retval = mqd->load_mqd(mqd, q->mqd, q->pipe,
+			q->queue, q->properties.write_ptr);
+	if (retval != 0) {
+		deallocate_hqd(dqm, q);
+		mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+		return retval;
+	}
+
 	return 0;
 }
 
@@ -320,6 +335,7 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 {
 	int retval;
 	struct mqd_manager *mqd;
+	bool prev_active = false;
 
 	BUG_ON(!dqm || !q || !q->mqd);
 
@@ -330,10 +346,18 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 		return -ENOMEM;
 	}
 
-	retval = mqd->update_mqd(mqd, q->mqd, &q->properties);
 	if (q->properties.is_active == true)
+		prev_active = true;
+
+	/*
+	 *
+	 * check active state vs. the previous state
+	 * and modify counter accordingly
+	 */
+	retval = mqd->update_mqd(mqd, q->mqd, &q->properties);
+	if ((q->properties.is_active == true) && (prev_active == false))
 		dqm->queue_count++;
-	else
+	else if ((q->properties.is_active == false) && (prev_active == true))
 		dqm->queue_count--;
 
 	if (sched_policy != KFD_SCHED_POLICY_NO_HWS)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
index adc31474e786..4c3828cf45bf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
@@ -184,7 +184,7 @@ static bool is_occupied(struct mqd_manager *mm, void *mqd,
 			uint32_t queue_id)
 {
 
-	return kfd2kgd->hqd_is_occupies(mm->dev->kgd, queue_address,
+	return kfd2kgd->hqd_is_occupied(mm->dev->kgd, queue_address,
 					pipe_id, queue_id);
 
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
index 71699ad97d74..4c25ef504f79 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
@@ -32,7 +32,7 @@ int kfd_pasid_init(void)
 {
 	pasid_limit = max_num_of_processes;
 
-	pasid_bitmap = kzalloc(BITS_TO_LONGS(pasid_limit), GFP_KERNEL);
+	pasid_bitmap = kcalloc(BITS_TO_LONGS(pasid_limit), sizeof(long), GFP_KERNEL);
 	if (!pasid_bitmap)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index f9fb81e3bb09..a5edb29507e3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -463,6 +463,24 @@ struct kfd_process {
 	bool is_32bit_user_mode;
 };
 
+/**
+ * Ioctl function type.
+ *
+ * \param filep pointer to file structure.
+ * \param p amdkfd process pointer.
+ * \param data pointer to arg that was copied from user.
+ */
+typedef int amdkfd_ioctl_t(struct file *filep, struct kfd_process *p,
+				void *data);
+
+struct amdkfd_ioctl_desc {
+	unsigned int cmd;
+	int flags;
+	amdkfd_ioctl_t *func;
+	unsigned int cmd_drv;
+	const char *name;
+};
+
 void kfd_process_create_wq(void);
 void kfd_process_destroy_wq(void);
 struct kfd_process *kfd_create_process(const struct task_struct *);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index b11792d7e70e..cca1708fd811 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -921,7 +921,7 @@ static int kfd_build_sysfs_node_tree(void)
 	uint32_t i = 0;
 
 	list_for_each_entry(dev, &topology_device_list, list) {
-		ret = kfd_build_sysfs_node_entry(dev, 0);
+		ret = kfd_build_sysfs_node_entry(dev, i);
 		if (ret < 0)
 			return ret;
 		i++;
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 47b551970a14..96a512208fad 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -183,7 +183,7 @@ struct kfd2kgd_calls {
 	int (*hqd_load)(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 			uint32_t queue_id, uint32_t __user *wptr);
 
-	bool (*hqd_is_occupies)(struct kgd_dev *kgd, uint64_t queue_address,
+	bool (*hqd_is_occupied)(struct kgd_dev *kgd, uint64_t queue_address,
 				uint32_t pipe_id, uint32_t queue_id);
 
 	int (*hqd_destroy)(struct kgd_dev *kgd, uint32_t reset_type,
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 70d0f0f06f1a..e9f891c432f8 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1756,8 +1756,6 @@ struct drm_i915_private {
 	 */
 	struct workqueue_struct *dp_wq;
 
-	uint32_t bios_vgacntr;
-
 	/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
 	struct {
 		int (*do_execbuf)(struct drm_device *dev, struct drm_file *file,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 52adcb680be3..c11603b4cf1d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1048,6 +1048,7 @@ int
 i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		      struct drm_file *file)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_pwrite *args = data;
 	struct drm_i915_gem_object *obj;
 	int ret;
@@ -1067,9 +1068,11 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 			return -EFAULT;
 	}
 
+	intel_runtime_pm_get(dev_priv);
+
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
-		return ret;
+		goto put_rpm;
 
 	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
 	if (&obj->base == NULL) {
@@ -1121,6 +1124,9 @@ out:
 	drm_gem_object_unreference(&obj->base);
 unlock:
 	mutex_unlock(&dev->struct_mutex);
+put_rpm:
+	intel_runtime_pm_put(dev_priv);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 996c2931c499..d0d3dfbe6d2a 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3725,8 +3725,6 @@ static bool i8xx_handle_vblank(struct drm_device *dev,
 	if ((iir & flip_pending) == 0)
 		goto check_page_flip;
 
-	intel_prepare_page_flip(dev, plane);
-
 	/* We detect FlipDone by looking for the change in PendingFlip from '1'
 	 * to '0' on the following vblank, i.e. IIR has the Pendingflip
 	 * asserted following the MI_DISPLAY_FLIP, but ISR is deasserted, hence
@@ -3736,6 +3734,7 @@ static bool i8xx_handle_vblank(struct drm_device *dev,
 	if (I915_READ16(ISR) & flip_pending)
 		goto check_page_flip;
 
+	intel_prepare_page_flip(dev, plane);
 	intel_finish_page_flip(dev, pipe);
 	return true;
 
@@ -3907,8 +3906,6 @@ static bool i915_handle_vblank(struct drm_device *dev,
 	if ((iir & flip_pending) == 0)
 		goto check_page_flip;
 
-	intel_prepare_page_flip(dev, plane);
-
 	/* We detect FlipDone by looking for the change in PendingFlip from '1'
 	 * to '0' on the following vblank, i.e. IIR has the Pendingflip
 	 * asserted following the MI_DISPLAY_FLIP, but ISR is deasserted, hence
@@ -3918,6 +3915,7 @@ static bool i915_handle_vblank(struct drm_device *dev,
 	if (I915_READ(ISR) & flip_pending)
 		goto check_page_flip;
 
+	intel_prepare_page_flip(dev, plane);
 	intel_finish_page_flip(dev, pipe);
 	return true;
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index fb3e3d429191..e2af1383b179 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -13057,11 +13057,7 @@ static void i915_disable_vga(struct drm_device *dev)
 	vga_put(dev->pdev, VGA_RSRC_LEGACY_IO);
 	udelay(300);
 
-	/*
-	 * Fujitsu-Siemens Lifebook S6010 (830) has problems resuming
-	 * from S3 without preserving (some of?) the other bits.
-	 */
-	I915_WRITE(vga_reg, dev_priv->bios_vgacntr | VGA_DISP_DISABLE);
+	I915_WRITE(vga_reg, VGA_DISP_DISABLE);
 	POSTING_READ(vga_reg);
 }
 
@@ -13146,8 +13142,6 @@ void intel_modeset_init(struct drm_device *dev)
 
 	intel_shared_dpll_init(dev);
 
-	/* save the BIOS value before clobbering it */
-	dev_priv->bios_vgacntr = I915_READ(i915_vgacntrl_reg(dev));
 	/* Just disable it once at startup */
 	i915_disable_vga(dev);
 	intel_setup_outputs(dev);
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index f5a78d53e297..ac6da7102fbb 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -615,29 +615,6 @@ static void chv_pipe_power_well_disable(struct drm_i915_private *dev_priv,
 		vlv_power_sequencer_reset(dev_priv);
 }
 
-static void check_power_well_state(struct drm_i915_private *dev_priv,
-				   struct i915_power_well *power_well)
-{
-	bool enabled = power_well->ops->is_enabled(dev_priv, power_well);
-
-	if (power_well->always_on || !i915.disable_power_well) {
-		if (!enabled)
-			goto mismatch;
-
-		return;
-	}
-
-	if (enabled != (power_well->count > 0))
-		goto mismatch;
-
-	return;
-
-mismatch:
-	WARN(1, "state mismatch for '%s' (always_on %d hw state %d use-count %d disable_power_well %d\n",
-		  power_well->name, power_well->always_on, enabled,
-		  power_well->count, i915.disable_power_well);
-}
-
 /**
  * intel_display_power_get - grab a power domain reference
  * @dev_priv: i915 device instance
@@ -669,8 +646,6 @@ void intel_display_power_get(struct drm_i915_private *dev_priv,
 			power_well->ops->enable(dev_priv, power_well);
 			power_well->hw_enabled = true;
 		}
-
-		check_power_well_state(dev_priv, power_well);
 	}
 
 	power_domains->domain_use_count[domain]++;
@@ -709,8 +684,6 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 			power_well->hw_enabled = false;
 			power_well->ops->disable(dev_priv, power_well);
 		}
-
-		check_power_well_state(dev_priv, power_well);
 	}
 
 	mutex_unlock(&power_domains->lock);
diff --git a/drivers/gpu/drm/nouveau/core/core/event.c b/drivers/gpu/drm/nouveau/core/core/event.c
index ff2b434b3db4..760947e380c9 100644
--- a/drivers/gpu/drm/nouveau/core/core/event.c
+++ b/drivers/gpu/drm/nouveau/core/core/event.c
@@ -26,7 +26,7 @@
 void
 nvkm_event_put(struct nvkm_event *event, u32 types, int index)
 {
-	BUG_ON(!spin_is_locked(&event->refs_lock));
+	assert_spin_locked(&event->refs_lock);
 	while (types) {
 		int type = __ffs(types); types &= ~(1 << type);
 		if (--event->refs[index * event->types_nr + type] == 0) {
@@ -39,7 +39,7 @@ nvkm_event_put(struct nvkm_event *event, u32 types, int index)
 void
 nvkm_event_get(struct nvkm_event *event, u32 types, int index)
 {
-	BUG_ON(!spin_is_locked(&event->refs_lock));
+	assert_spin_locked(&event->refs_lock);
 	while (types) {
 		int type = __ffs(types); types &= ~(1 << type);
 		if (++event->refs[index * event->types_nr + type] == 1) {
diff --git a/drivers/gpu/drm/nouveau/core/core/notify.c b/drivers/gpu/drm/nouveau/core/core/notify.c
index d1bcde55e9d7..839a32577680 100644
--- a/drivers/gpu/drm/nouveau/core/core/notify.c
+++ b/drivers/gpu/drm/nouveau/core/core/notify.c
@@ -98,7 +98,7 @@ nvkm_notify_send(struct nvkm_notify *notify, void *data, u32 size)
 	struct nvkm_event *event = notify->event;
 	unsigned long flags;
 
-	BUG_ON(!spin_is_locked(&event->list_lock));
+	assert_spin_locked(&event->list_lock);
 	BUG_ON(size != notify->size);
 
 	spin_lock_irqsave(&event->refs_lock, flags);
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nve0.c b/drivers/gpu/drm/nouveau/core/engine/device/nve0.c
index 674da1f095b2..732922690653 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nve0.c
@@ -249,6 +249,39 @@ nve0_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_ENGINE_PPP    ] = &nvc0_ppp_oclass;
 		device->oclass[NVDEV_ENGINE_PERFMON] = &nvf0_perfmon_oclass;
 		break;
+	case 0x106:
+		device->cname = "GK208B";
+		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nve0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
+		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
+		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
+		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
+		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nvc0_devinit_oclass;
+		device->oclass[NVDEV_SUBDEV_MC     ] =  gk20a_mc_oclass;
+		device->oclass[NVDEV_SUBDEV_BUS    ] =  nvc0_bus_oclass;
+		device->oclass[NVDEV_SUBDEV_TIMER  ] = &nv04_timer_oclass;
+		device->oclass[NVDEV_SUBDEV_FB     ] =  nve0_fb_oclass;
+		device->oclass[NVDEV_SUBDEV_LTC    ] =  gk104_ltc_oclass;
+		device->oclass[NVDEV_SUBDEV_IBUS   ] = &nve0_ibus_oclass;
+		device->oclass[NVDEV_SUBDEV_INSTMEM] =  nv50_instmem_oclass;
+		device->oclass[NVDEV_SUBDEV_VM     ] = &nvc0_vmmgr_oclass;
+		device->oclass[NVDEV_SUBDEV_BAR    ] = &nvc0_bar_oclass;
+		device->oclass[NVDEV_SUBDEV_PWR    ] =  nv108_pwr_oclass;
+		device->oclass[NVDEV_SUBDEV_VOLT   ] = &nv40_volt_oclass;
+		device->oclass[NVDEV_ENGINE_DMAOBJ ] =  nvd0_dmaeng_oclass;
+		device->oclass[NVDEV_ENGINE_FIFO   ] =  nv108_fifo_oclass;
+		device->oclass[NVDEV_ENGINE_SW     ] =  nvc0_software_oclass;
+		device->oclass[NVDEV_ENGINE_GR     ] =  nv108_graph_oclass;
+		device->oclass[NVDEV_ENGINE_DISP   ] =  nvf0_disp_oclass;
+		device->oclass[NVDEV_ENGINE_COPY0  ] = &nve0_copy0_oclass;
+		device->oclass[NVDEV_ENGINE_COPY1  ] = &nve0_copy1_oclass;
+		device->oclass[NVDEV_ENGINE_COPY2  ] = &nve0_copy2_oclass;
+		device->oclass[NVDEV_ENGINE_BSP    ] = &nve0_bsp_oclass;
+		device->oclass[NVDEV_ENGINE_VP     ] = &nve0_vp_oclass;
+		device->oclass[NVDEV_ENGINE_PPP    ] = &nvc0_ppp_oclass;
+		break;
 	case 0x108:
 		device->cname = "GK208";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/shadowramin.c b/drivers/gpu/drm/nouveau/core/subdev/bios/shadowramin.c
index 5e58bba0dd5c..a7a890fad1e5 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/shadowramin.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/shadowramin.c
@@ -44,8 +44,10 @@ static void
 pramin_fini(void *data)
 {
 	struct priv *priv = data;
-	nv_wr32(priv->bios, 0x001700, priv->bar0);
-	kfree(priv);
+	if (priv) {
+		nv_wr32(priv->bios, 0x001700, priv->bar0);
+		kfree(priv);
+	}
 }
 
 static void *
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvaa.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvaa.c
index 00f2ca7e44a5..033a8e999497 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvaa.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvaa.c
@@ -24,34 +24,71 @@
 
 #include "nv50.h"
 
+struct nvaa_ram_priv {
+	struct nouveau_ram base;
+	u64 poller_base;
+};
+
 static int
 nvaa_ram_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	      struct nouveau_oclass *oclass, void *data, u32 datasize,
 	      struct nouveau_object **pobject)
 {
-	const u32 rsvd_head = ( 256 * 1024) >> 12; /* vga memory */
-	const u32 rsvd_tail = (1024 * 1024) >> 12; /* vbios etc */
+	u32 rsvd_head = ( 256 * 1024); /* vga memory */
+	u32 rsvd_tail = (1024 * 1024); /* vbios etc */
 	struct nouveau_fb *pfb = nouveau_fb(parent);
-	struct nouveau_ram *ram;
+	struct nvaa_ram_priv *priv;
 	int ret;
 
-	ret = nouveau_ram_create(parent, engine, oclass, &ram);
-	*pobject = nv_object(ram);
+	ret = nouveau_ram_create(parent, engine, oclass, &priv);
+	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
 
-	ram->size = nv_rd32(pfb, 0x10020c);
-	ram->size = (ram->size & 0xffffff00) | ((ram->size & 0x000000ff) << 32);
+	priv->base.type   = NV_MEM_TYPE_STOLEN;
+	priv->base.stolen = (u64)nv_rd32(pfb, 0x100e10) << 12;
+	priv->base.size   = (u64)nv_rd32(pfb, 0x100e14) << 12;
 
-	ret = nouveau_mm_init(&pfb->vram, rsvd_head, (ram->size >> 12) -
-			      (rsvd_head + rsvd_tail), 1);
+	rsvd_tail += 0x1000;
+	priv->poller_base = priv->base.size - rsvd_tail;
+
+	ret = nouveau_mm_init(&pfb->vram, rsvd_head >> 12,
+			      (priv->base.size  - (rsvd_head + rsvd_tail)) >> 12,
+			      1);
 	if (ret)
 		return ret;
 
-	ram->type   = NV_MEM_TYPE_STOLEN;
-	ram->stolen = (u64)nv_rd32(pfb, 0x100e10) << 12;
-	ram->get = nv50_ram_get;
-	ram->put = nv50_ram_put;
+	priv->base.get = nv50_ram_get;
+	priv->base.put = nv50_ram_put;
+	return 0;
+}
+
+static int
+nvaa_ram_init(struct nouveau_object *object)
+{
+	struct nouveau_fb *pfb = nouveau_fb(object);
+	struct nvaa_ram_priv *priv = (void *)object;
+	int ret;
+	u64 dniso, hostnb, flush;
+
+	ret = nouveau_ram_init(&priv->base);
+	if (ret)
+		return ret;
+
+	dniso  = ((priv->base.size - (priv->poller_base + 0x00)) >> 5) - 1;
+	hostnb = ((priv->base.size - (priv->poller_base + 0x20)) >> 5) - 1;
+	flush  = ((priv->base.size - (priv->poller_base + 0x40)) >> 5) - 1;
+
+	/* Enable NISO poller for various clients and set their associated
+	 * read address, only for MCP77/78 and MCP79/7A. (fd#25701)
+	 */
+	nv_wr32(pfb, 0x100c18, dniso);
+	nv_mask(pfb, 0x100c14, 0x00000000, 0x00000001);
+	nv_wr32(pfb, 0x100c1c, hostnb);
+	nv_mask(pfb, 0x100c14, 0x00000000, 0x00000002);
+	nv_wr32(pfb, 0x100c24, flush);
+	nv_mask(pfb, 0x100c14, 0x00000000, 0x00010000);
+
 	return 0;
 }
 
@@ -60,7 +97,7 @@ nvaa_ram_oclass = {
 	.ofuncs = &(struct nouveau_ofuncs) {
 		.ctor = nvaa_ram_ctor,
 		.dtor = _nouveau_ram_dtor,
-		.init = _nouveau_ram_init,
+		.init = nvaa_ram_init,
 		.fini = _nouveau_ram_fini,
 	},
 };
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
index a75c35ccf25c..165401c4045c 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c
@@ -24,13 +24,6 @@
 
 #include "nv04.h"
 
-static void
-nv4c_mc_msi_rearm(struct nouveau_mc *pmc)
-{
-	struct nv04_mc_priv *priv = (void *)pmc;
-	nv_wr08(priv, 0x088050, 0xff);
-}
-
 struct nouveau_oclass *
 nv4c_mc_oclass = &(struct nouveau_mc_oclass) {
 	.base.handle = NV_SUBDEV(MC, 0x4c),
@@ -41,5 +34,4 @@ nv4c_mc_oclass = &(struct nouveau_mc_oclass) {
 		.fini = _nouveau_mc_fini,
 	},
 	.intr = nv04_mc_intr,
-	.msi_rearm = nv4c_mc_msi_rearm,
 }.base;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 21ec561edc99..bba2960d3dfb 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1572,8 +1572,10 @@ nouveau_ttm_tt_unpopulate(struct ttm_tt *ttm)
 	 * so use the DMA API for them.
 	 */
 	if (!nv_device_is_cpu_coherent(device) &&
-	    ttm->caching_state == tt_uncached)
+	    ttm->caching_state == tt_uncached) {
 		ttm_dma_unpopulate(ttm_dma, dev->dev);
+		return;
+	}
 
 #if __OS_HAS_AGP
 	if (drm->agp.stat == ENABLED) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 42c34babc2e5..bf0f9e21d714 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -36,7 +36,14 @@ void
 nouveau_gem_object_del(struct drm_gem_object *gem)
 {
 	struct nouveau_bo *nvbo = nouveau_gem_object(gem);
+	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
 	struct ttm_buffer_object *bo = &nvbo->bo;
+	struct device *dev = drm->dev->dev;
+	int ret;
+
+	ret = pm_runtime_get_sync(dev);
+	if (WARN_ON(ret < 0 && ret != -EACCES))
+		return;
 
 	if (gem->import_attach)
 		drm_prime_gem_destroy(gem, nvbo->bo.sg);
@@ -46,6 +53,9 @@ nouveau_gem_object_del(struct drm_gem_object *gem)
 	/* reset filp so nouveau_bo_del_ttm() can test for it */
 	gem->filp = NULL;
 	ttm_bo_unref(&bo);
+
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
 }
 
 int
@@ -53,7 +63,9 @@ nouveau_gem_object_open(struct drm_gem_object *gem, struct drm_file *file_priv)
 {
 	struct nouveau_cli *cli = nouveau_cli(file_priv);
 	struct nouveau_bo *nvbo = nouveau_gem_object(gem);
+	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
 	struct nouveau_vma *vma;
+	struct device *dev = drm->dev->dev;
 	int ret;
 
 	if (!cli->vm)
@@ -71,11 +83,16 @@ nouveau_gem_object_open(struct drm_gem_object *gem, struct drm_file *file_priv)
 			goto out;
 		}
 
+		ret = pm_runtime_get_sync(dev);
+		if (ret < 0 && ret != -EACCES)
+			goto out;
+
 		ret = nouveau_bo_vma_add(nvbo, cli->vm, vma);
-		if (ret) {
+		if (ret)
 			kfree(vma);
-			goto out;
-		}
+
+		pm_runtime_mark_last_busy(dev);
+		pm_runtime_put_autosuspend(dev);
 	} else {
 		vma->refcount++;
 	}
@@ -129,6 +146,8 @@ nouveau_gem_object_close(struct drm_gem_object *gem, struct drm_file *file_priv)
 {
 	struct nouveau_cli *cli = nouveau_cli(file_priv);
 	struct nouveau_bo *nvbo = nouveau_gem_object(gem);
+	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
+	struct device *dev = drm->dev->dev;
 	struct nouveau_vma *vma;
 	int ret;
 
@@ -141,8 +160,14 @@ nouveau_gem_object_close(struct drm_gem_object *gem, struct drm_file *file_priv)
 
 	vma = nouveau_bo_vma_find(nvbo, cli->vm);
 	if (vma) {
-		if (--vma->refcount == 0)
-			nouveau_gem_object_unmap(nvbo, vma);
+		if (--vma->refcount == 0) {
+			ret = pm_runtime_get_sync(dev);
+			if (!WARN_ON(ret < 0 && ret != -EACCES)) {
+				nouveau_gem_object_unmap(nvbo, vma);
+				pm_runtime_mark_last_busy(dev);
+				pm_runtime_put_autosuspend(dev);
+			}
+		}
 	}
 	ttm_bo_unreserve(&nvbo->bo);
 }
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index d59ec491dbb9..ed644a4f6f57 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1851,10 +1851,9 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc)
 				return pll;
 		}
 		/* otherwise, pick one of the plls */
-		if ((rdev->family == CHIP_KAVERI) ||
-		    (rdev->family == CHIP_KABINI) ||
+		if ((rdev->family == CHIP_KABINI) ||
 		    (rdev->family == CHIP_MULLINS)) {
-			/* KB/KV/ML has PPLL1 and PPLL2 */
+			/* KB/ML has PPLL1 and PPLL2 */
 			pll_in_use = radeon_get_pll_use_mask(crtc);
 			if (!(pll_in_use & (1 << ATOM_PPLL2)))
 				return ATOM_PPLL2;
@@ -1863,7 +1862,7 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc)
 			DRM_ERROR("unable to allocate a PPLL\n");
 			return ATOM_PPLL_INVALID;
 		} else {
-			/* CI has PPLL0, PPLL1, and PPLL2 */
+			/* CI/KV has PPLL0, PPLL1, and PPLL2 */
 			pll_in_use = radeon_get_pll_use_mask(crtc);
 			if (!(pll_in_use & (1 << ATOM_PPLL2)))
 				return ATOM_PPLL2;
@@ -2155,6 +2154,7 @@ static void atombios_crtc_disable(struct drm_crtc *crtc)
 	case ATOM_PPLL0:
 		/* disable the ppll */
 		if ((rdev->family == CHIP_ARUBA) ||
+		    (rdev->family == CHIP_KAVERI) ||
 		    (rdev->family == CHIP_BONAIRE) ||
 		    (rdev->family == CHIP_HAWAII))
 			atombios_crtc_program_pll(crtc, radeon_crtc->crtc_id, radeon_crtc->pll_id,
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 11ba9d21b89b..db42a670f995 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -492,6 +492,10 @@ int radeon_dp_mode_valid_helper(struct drm_connector *connector,
 	struct radeon_connector_atom_dig *dig_connector;
 	int dp_clock;
 
+	if ((mode->clock > 340000) &&
+	    (!radeon_connector_is_dp12_capable(connector)))
+		return MODE_CLOCK_HIGH;
+
 	if (!radeon_connector->con_priv)
 		return MODE_CLOCK_HIGH;
 	dig_connector = radeon_connector->con_priv;
diff --git a/drivers/gpu/drm/radeon/cikd.h b/drivers/gpu/drm/radeon/cikd.h
index ba85986febea..03003f8a6de6 100644
--- a/drivers/gpu/drm/radeon/cikd.h
+++ b/drivers/gpu/drm/radeon/cikd.h
@@ -2156,4 +2156,6 @@
 #define ATC_VM_APERTURE1_HIGH_ADDR				0x330Cu
 #define ATC_VM_APERTURE1_LOW_ADDR				0x3304u
 
+#define IH_VMID_0_LUT						0x3D40u
+
 #endif
diff --git a/drivers/gpu/drm/radeon/dce3_1_afmt.c b/drivers/gpu/drm/radeon/dce3_1_afmt.c
index 2fe8cfc966d9..bafdf92a5732 100644
--- a/drivers/gpu/drm/radeon/dce3_1_afmt.c
+++ b/drivers/gpu/drm/radeon/dce3_1_afmt.c
@@ -103,7 +103,7 @@ static void dce3_2_afmt_write_sad_regs(struct drm_encoder *encoder)
 	}
 
 	sad_count = drm_edid_to_sad(radeon_connector->edid, &sads);
-	if (sad_count < 0) {
+	if (sad_count <= 0) {
 		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
 		return;
 	}
diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c
index 9b42001295ba..e3e9c10cfba9 100644
--- a/drivers/gpu/drm/radeon/kv_dpm.c
+++ b/drivers/gpu/drm/radeon/kv_dpm.c
@@ -2745,13 +2745,11 @@ int kv_dpm_init(struct radeon_device *rdev)
 	pi->enable_auto_thermal_throttling = true;
 	pi->disable_nb_ps3_in_battery = false;
 	if (radeon_bapm == -1) {
-		/* There are stability issues reported on with
-		 * bapm enabled on an asrock system.
-		 */
-		if (rdev->pdev->subsystem_vendor == 0x1849)
-			pi->bapm_enable = false;
-		else
+		/* only enable bapm on KB, ML by default */
+		if (rdev->family == CHIP_KABINI || rdev->family == CHIP_MULLINS)
 			pi->bapm_enable = true;
+		else
+			pi->bapm_enable = false;
 	} else if (radeon_bapm == 0) {
 		pi->bapm_enable = false;
 	} else {
diff --git a/drivers/gpu/drm/radeon/radeon_kfd.c b/drivers/gpu/drm/radeon/radeon_kfd.c
index 242fd8b1b221..8bf87f1203cc 100644
--- a/drivers/gpu/drm/radeon/radeon_kfd.c
+++ b/drivers/gpu/drm/radeon/radeon_kfd.c
@@ -72,7 +72,7 @@ static int kgd_init_pipeline(struct kgd_dev *kgd, uint32_t pipe_id,
 static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 			uint32_t queue_id, uint32_t __user *wptr);
 
-static bool kgd_hqd_is_occupies(struct kgd_dev *kgd, uint64_t queue_address,
+static bool kgd_hqd_is_occupied(struct kgd_dev *kgd, uint64_t queue_address,
 				uint32_t pipe_id, uint32_t queue_id);
 
 static int kgd_hqd_destroy(struct kgd_dev *kgd, uint32_t reset_type,
@@ -92,7 +92,7 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.init_memory = kgd_init_memory,
 	.init_pipeline = kgd_init_pipeline,
 	.hqd_load = kgd_hqd_load,
-	.hqd_is_occupies = kgd_hqd_is_occupies,
+	.hqd_is_occupied = kgd_hqd_is_occupied,
 	.hqd_destroy = kgd_hqd_destroy,
 	.get_fw_version = get_fw_version
 };
@@ -101,6 +101,7 @@ static const struct kgd2kfd_calls *kgd2kfd;
 
 bool radeon_kfd_init(void)
 {
+#if defined(CONFIG_HSA_AMD_MODULE)
 	bool (*kgd2kfd_init_p)(unsigned, const struct kfd2kgd_calls*,
 				const struct kgd2kfd_calls**);
 
@@ -117,6 +118,17 @@ bool radeon_kfd_init(void)
 	}
 
 	return true;
+#elif defined(CONFIG_HSA_AMD)
+	if (!kgd2kfd_init(KFD_INTERFACE_VERSION, &kfd2kgd, &kgd2kfd)) {
+		kgd2kfd = NULL;
+
+		return false;
+	}
+
+	return true;
+#else
+	return false;
+#endif
 }
 
 void radeon_kfd_fini(void)
@@ -378,6 +390,10 @@ static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
 		cpu_relax();
 	write_register(kgd, ATC_VMID_PASID_MAPPING_UPDATE_STATUS, 1U << vmid);
 
+	/* Mapping vmid to pasid also for IH block */
+	write_register(kgd, IH_VMID_0_LUT + vmid * sizeof(uint32_t),
+			pasid_mapping);
+
 	return 0;
 }
 
@@ -517,7 +533,7 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 	return 0;
 }
 
-static bool kgd_hqd_is_occupies(struct kgd_dev *kgd, uint64_t queue_address,
+static bool kgd_hqd_is_occupied(struct kgd_dev *kgd, uint64_t queue_address,
 				uint32_t pipe_id, uint32_t queue_id)
 {
 	uint32_t act;
@@ -556,6 +572,7 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, uint32_t reset_type,
 		if (timeout == 0) {
 			pr_err("kfd: cp queue preemption time out (%dms)\n",
 				temp);
+			release_queue(kgd);
 			return -ETIME;
 		}
 		msleep(20);
diff --git a/drivers/gpu/drm/radeon/radeon_state.c b/drivers/gpu/drm/radeon/radeon_state.c
index 535403e0c8a2..15aee723db77 100644
--- a/drivers/gpu/drm/radeon/radeon_state.c
+++ b/drivers/gpu/drm/radeon/radeon_state.c
@@ -1703,7 +1703,7 @@ static int radeon_cp_dispatch_texture(struct drm_device * dev,
 	u32 format;
 	u32 *buffer;
 	const u8 __user *data;
-	int size, dwords, tex_width, blit_width, spitch;
+	unsigned int size, dwords, tex_width, blit_width, spitch;
 	u32 height;
 	int i;
 	u32 texpitch, microtile;