Merge tag 'drm-next-2019-03-06' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for the 5.1 merge window.

  The big changes I'd highlight are:
   - nouveau has HMM support now, there is finally an in-tree user so we
     can quieten down the rip it out people.
   - i915 now enables fastboot by default on Skylake+
   - Displayport Multistream support has been refactored and should
     hopefully be more reliable.

  Core:
   - header cleanups aiming towards removing drmP.h
   - dma-buf fence seqnos to 64-bits
   - common helper for DP mst hotplug for radeon,i915,amdgpu + new
     refcounting scheme
   - MST i2c improvements
   - drm_syncobj_cb removal
   - ARM FB compression fourcc
   - P010 + P016 fourcc
   - allwinner tiled format modifier
   - i2c over aux I2C_M_STOP support
   - DRM_AUTH handling fixes

  TTM:
   - ref/unref renaming

  New driver:
   - ARM komeda display driver

  scheduler:
   - refactor mirror list handling
   - rework hw fence processing
   - 0 run queue entity fix

  bridge:
   - TI DS90C185 LVDS bridge
   - thc631lvdm83d bridge improvements
   - cadence + allwinner DSI ported to generic phy

  panels:
   - Sitronix ST7701 panel
   - Kingdisplay KD097D04
   - LeMaker BL035-RGB-002
   - PDA 91-00156-A0
   - Innolux EE101IA-01D

  i915:
   - Enable fastboot by default on SKL+/VLV/CHV
   - Export RPCS configuration for ICL media driver
   - Coffelake PCI ID
   - CNL clocks setup fixes
   - ACPI/PMIC support for MIPI/DSI
   - Per-engine WA init for all engines
   - Shrinker locking fixes
   - Kerneldoc updates
   - Lots of ring improvements and reset fixes
   - Coffeelake GVT Support
   - VFIO GVT EDID Region support
   - runtime PM wakeref tracking
   - ILK->IVB primary plane enable delays
   - userptr mutex locking fixes
   - DSI fixes
   - LVDS/TV cleanups
   - HW readout fixes
   - LUT robustness fixes
   - ICL display and watermark fixes
   - gem mmap race fix

  amdgpu:
   - add scheduled dependencies interface
   - DCC on scanout surfaces
   - vega10/20 BACO support
   - Multiple IH rings on soc15
   - XGMI locking fixes
   - DC i2c/aux cleanups
   - runtime SMU debug interface
   - Kexec improvmeents
   - SR-IOV fixes
   - DC freesync + ABM fixes
   - GDS fixes
   - GPUVM fixes
   - vega20 PCIE DPM switching fixes
   - Context priority handling fixes

  radeon:
   - fix missing break in evergreen parser

  nouveau:
   - SVM support via HMM

  msm:
   - QCOM Compressed modifier support

  exynos:
   - s5pv210 rotator support

  imx:
   - zpos property support
   - pending update fixes

  v3d:
   - cache flush improvments

  vc4:
   - reflection support
   - HDMI overscan support

  tegra:
   - CEC refactoring
   - HDMI audio fixes
   - Tegra186 prep work
   - SOR crossbar device tree fixes

  sun4i:
   - implicit fencing support
   - YUV and scalar support improvements
   - A23 support
   - tiling fixes

  atmel-hlcdc:
   - clipping and rotation property fixes

  qxl:
   - BO and PRIME improvements
   - generic fbdev emulation

  dw-hdmi:
   - HDMI 2.0 2160p
   - YUV420 ouput

  rockchip:
   - implicit fencing support
   - reflection proerties

  virtio-gpu:
   - use generic fbdev emulation

  tilcdc:
   - cpufreq vs crtc init fix

  rcar-du:
   - R8A774C0 support
   - D3/E3 RGB output routing fixes and DPAD0 support
   - RA87744 LVDS support

  bochs:
   - atomic and generic fbdev emulation
   - ID mismatch error on bochs load

  meson:
   - remove firmware fbs"

* tag 'drm-next-2019-03-06' of git://anongit.freedesktop.org/drm/drm: (1130 commits)
  drm/amd/display: Use vrr friendly pageflip throttling in DC.
  drm/imx: only send commit done event when all state has been applied
  drm/imx: allow building under COMPILE_TEST
  drm/imx: imx-tve: depend on COMMON_CLK
  drm/imx: ipuv3-plane: add zpos property
  drm/imx: ipuv3-plane: add function to query atomic update status
  gpu: ipu-v3: prg: add function to get channel configure status
  gpu: ipu-v3: pre: add double buffer status readback
  drm/amdgpu: Bump amdgpu version for context priority override.
  drm/amdgpu/powerplay: fix typo in BACO header guards
  drm/amdgpu/powerplay: fix return codes in BACO code
  drm/amdgpu: add missing license on baco files
  drm/bochs: Fix the ID mismatch error
  drm/nouveau/dmem: use dma addresses during migration copies
  drm/nouveau/dmem: use physical vram addresses during migration copies
  drm/nouveau/dmem: extend copy function to allow direct use of physical addresses
  drm/nouveau/svm: new ioctl to migrate process memory to GPU memory
  drm/nouveau/dmem: device memory helpers for SVM
  drm/nouveau/svm: initial support for shared virtual memory
  drm/nouveau: prepare for enabling svm with existing userspace interfaces
  ...

4 files changed, 40 insertions, 65 deletions

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 8372556b52eb..c6c9530e704e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -134,12 +134,18 @@ static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q)
 		 */
 		q->doorbell_id = q->properties.queue_id;
 	} else if (q->properties.type == KFD_QUEUE_TYPE_SDMA) {
-		/* For SDMA queues on SOC15, use static doorbell
-		 * assignments based on the engine and queue.
+		/* For SDMA queues on SOC15 with 8-byte doorbell, use static
+		 * doorbell assignments based on the engine and queue id.
+		 * The doobell index distance between RLC (2*i) and (2*i+1)
+		 * for a SDMA engine is 512.
 		 */
-		q->doorbell_id = dev->shared_resources.sdma_doorbell
-			[q->properties.sdma_engine_id]
-			[q->properties.sdma_queue_id];
+		uint32_t *idx_offset =
+				dev->shared_resources.sdma_doorbell_idx;
+
+		q->doorbell_id = idx_offset[q->properties.sdma_engine_id]
+			+ (q->properties.sdma_queue_id & 1)
+			* KFD_QUEUE_DOORBELL_MIRROR_OFFSET
+			+ (q->properties.sdma_queue_id >> 1);
 	} else {
 		/* For CP queues on SOC15 reserve a free doorbell ID */
 		unsigned int found;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index 8018163414ff..932007eb9168 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -23,22 +23,7 @@
 #include <linux/sched.h>
 #include <linux/device.h>
 #include "kfd_priv.h"
-
-static const struct kgd2kfd_calls kgd2kfd = {
-	.exit		= kgd2kfd_exit,
-	.probe		= kgd2kfd_probe,
-	.device_init	= kgd2kfd_device_init,
-	.device_exit	= kgd2kfd_device_exit,
-	.interrupt	= kgd2kfd_interrupt,
-	.suspend	= kgd2kfd_suspend,
-	.resume		= kgd2kfd_resume,
-	.quiesce_mm	= kgd2kfd_quiesce_mm,
-	.resume_mm	= kgd2kfd_resume_mm,
-	.schedule_evict_and_restore_process =
-			  kgd2kfd_schedule_evict_and_restore_process,
-	.pre_reset	= kgd2kfd_pre_reset,
-	.post_reset	= kgd2kfd_post_reset,
-};
+#include "amdgpu_amdkfd.h"
 
 static int kfd_init(void)
 {
@@ -91,20 +76,10 @@ static void kfd_exit(void)
 	kfd_chardev_exit();
 }
 
-int kgd2kfd_init(unsigned int interface_version,
-		const struct kgd2kfd_calls **g2f)
+int kgd2kfd_init()
 {
-	int err;
-
-	err = kfd_init();
-	if (err)
-		return err;
-
-	*g2f = &kgd2kfd;
-
-	return 0;
+	return kfd_init();
 }
-EXPORT_SYMBOL(kgd2kfd_init);
 
 void kgd2kfd_exit(void)
 {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 0689d4ccbbc0..0eeee3c6d6dc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -97,17 +97,29 @@
 #define KFD_CWSR_TBA_TMA_SIZE (PAGE_SIZE * 2)
 #define KFD_CWSR_TMA_OFFSET PAGE_SIZE
 
+#define KFD_MAX_NUM_OF_QUEUES_PER_DEVICE		\
+	(KFD_MAX_NUM_OF_PROCESSES *			\
+			KFD_MAX_NUM_OF_QUEUES_PER_PROCESS)
+
+#define KFD_KERNEL_QUEUE_SIZE 2048
+
+/*
+ * 512 = 0x200
+ * The doorbell index distance between SDMA RLC (2*i) and (2*i+1) in the
+ * same SDMA engine on SOC15, which has 8-byte doorbells for SDMA.
+ * 512 8-byte doorbell distance (i.e. one page away) ensures that SDMA RLC
+ * (2*i+1) doorbells (in terms of the lower 12 bit address) lie exactly in
+ * the OFFSET and SIZE set in registers like BIF_SDMA0_DOORBELL_RANGE.
+ */
+#define KFD_QUEUE_DOORBELL_MIRROR_OFFSET 512
+
+
 /*
  * Kernel module parameter to specify maximum number of supported queues per
  * device
  */
 extern int max_num_of_queues_per_device;
 
-#define KFD_MAX_NUM_OF_QUEUES_PER_DEVICE		\
-	(KFD_MAX_NUM_OF_PROCESSES *			\
-			KFD_MAX_NUM_OF_QUEUES_PER_PROCESS)
-
-#define KFD_KERNEL_QUEUE_SIZE 2048
 
 /* Kernel module parameter to specify the scheduling policy */
 extern int sched_policy;
@@ -266,14 +278,6 @@ struct kfd_dev {
 	bool pci_atomic_requested;
 };
 
-/* KGD2KFD callbacks */
-void kgd2kfd_exit(void);
-struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd,
-			struct pci_dev *pdev, const struct kfd2kgd_calls *f2g);
-bool kgd2kfd_device_init(struct kfd_dev *kfd,
-			const struct kgd2kfd_shared_resources *gpu_resources);
-void kgd2kfd_device_exit(struct kfd_dev *kfd);
-
 enum kfd_mempool {
 	KFD_MEMPOOL_SYSTEM_CACHEABLE = 1,
 	KFD_MEMPOOL_SYSTEM_WRITECOMBINE = 2,
@@ -541,11 +545,6 @@ struct qcm_process_device {
 /* Approx. time before evicting the process again */
 #define PROCESS_ACTIVE_TIME_MS 10
 
-int kgd2kfd_quiesce_mm(struct mm_struct *mm);
-int kgd2kfd_resume_mm(struct mm_struct *mm);
-int kgd2kfd_schedule_evict_and_restore_process(struct mm_struct *mm,
-					       struct dma_fence *fence);
-
 /* 8 byte handle containing GPU ID in the most significant 4 bytes and
  * idr_handle in the least significant 4 bytes
  */
@@ -800,20 +799,11 @@ int kfd_numa_node_to_apic_id(int numa_node_id);
 /* Interrupts */
 int kfd_interrupt_init(struct kfd_dev *dev);
 void kfd_interrupt_exit(struct kfd_dev *dev);
-void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry);
 bool enqueue_ih_ring_entry(struct kfd_dev *kfd,	const void *ih_ring_entry);
 bool interrupt_is_wanted(struct kfd_dev *dev,
 				const uint32_t *ih_ring_entry,
 				uint32_t *patched_ihre, bool *flag);
 
-/* Power Management */
-void kgd2kfd_suspend(struct kfd_dev *kfd);
-int kgd2kfd_resume(struct kfd_dev *kfd);
-
-/* GPU reset */
-int kgd2kfd_pre_reset(struct kfd_dev *kfd);
-int kgd2kfd_post_reset(struct kfd_dev *kfd);
-
 /* amdkfd Apertures */
 int kfd_init_apertures(struct kfd_process *process);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 80b36e860a0a..4bdae78bab8e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -607,13 +607,17 @@ static int init_doorbell_bitmap(struct qcm_process_device *qpd,
 	if (!qpd->doorbell_bitmap)
 		return -ENOMEM;
 
-	/* Mask out any reserved doorbells */
-	for (i = 0; i < KFD_MAX_NUM_OF_QUEUES_PER_PROCESS; i++)
-		if ((dev->shared_resources.reserved_doorbell_mask & i) ==
-		    dev->shared_resources.reserved_doorbell_val) {
+	/* Mask out doorbells reserved for SDMA, IH, and VCN on SOC15. */
+	for (i = 0; i < KFD_MAX_NUM_OF_QUEUES_PER_PROCESS / 2; i++) {
+		if (i >= dev->shared_resources.non_cp_doorbells_start
+			&& i <= dev->shared_resources.non_cp_doorbells_end) {
 			set_bit(i, qpd->doorbell_bitmap);
-			pr_debug("reserved doorbell 0x%03x\n", i);
+			set_bit(i + KFD_QUEUE_DOORBELL_MIRROR_OFFSET,
+				qpd->doorbell_bitmap);
+			pr_debug("reserved doorbell 0x%03x and 0x%03x\n", i,
+				i + KFD_QUEUE_DOORBELL_MIRROR_OFFSET);
 		}
+	}
 
 	return 0;
 }