Merge tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "Cannonlake and Vega12 support are probably the two major things. This
  pull lacks nouveau, Ben had some unforseen leave and a few other
  blockers so we'll see how things look or maybe leave it for this merge
  window.

  core:
   - Device links to handle sound/gpu pm dependency
   - Color encoding/range properties
   - Plane clipping into plane check helper
   - Backlight helpers
   - DP TP4 + HBR3 helper support

  amdgpu:
   - Vega12 support
   - Enable DC by default on all supported GPUs
   - Powerplay restructuring and cleanup
   - DC bandwidth calc updates
   - DC backlight on pre-DCE11
   - TTM backing store dropping support
   - SR-IOV fixes
   - Adding "wattman" like functionality
   - DC crc support
   - Improved DC dual-link handling

  amdkfd:
   - GPUVM support for dGPU
   - KFD events for dGPU
   - Enable PCIe atomics for dGPUs
   - HSA process eviction support
   - Live-lock fixes for process eviction
   - VM page table allocation fix for large-bar systems

  panel:
   - Raydium RM68200
   - AUO G104SN02 V2
   - KEO TX31D200VM0BAA
   - ARM Versatile panels

  i915:
   - Cannonlake support enabled
   - AUX-F port support added
   - Icelake base enabling until internal milestone of forcewake support
   - Query uAPI interface (used for GPU topology information currently)
   - Compressed framebuffer support for sprites
   - kmem cache shrinking when GPU is idle
   - Avoid boosting GPU when waited item is being processed already
   - Avoid retraining LSPCON link unnecessarily
   - Decrease request signaling latency
   - Deprecation of I915_SET_COLORKEY_NONE
   - Kerneldoc and compiler warning cleanup for upcoming CI enforcements
   - Full range ycbcr toggling
   - HDCP support

  i915/gvt:
   - Big refactor for shadow ppgtt
   - KBL context save/restore via LRI cmd (Weinan)
   - Properly unmap dma for guest page (Changbin)

  vmwgfx:
   - Lots of various improvements

  etnaviv:
   - Use the drm gpu scheduler
   - prep work for GC7000L support

  vc4:
   - fix alpha blending
   - Expose perf counters to userspace

  pl111:
   - Bandwidth checking/limiting
   - Versatile panel support

  sun4i:
   - A83T HDMI support
   - A80 support
   - YUV plane support
   - H3/H5 HDMI support

  omapdrm:
   - HPD support for DVI connector
   - remove lots of static variables

  msm:
   - DSI updates from 10nm / SDM845
   - fix for race condition with a3xx/a4xx fence completion irq
   - some refactoring/prep work for eventual a6xx support (ie. when we
     have a userspace)
   - a5xx debugfs enhancements
   - some mdp5 fixes/cleanups to prepare for eventually merging
     writeback
   - support (ie. when we have a userspace)

  tegra:
   - mmap() fixes for fbdev devices
   - Overlay plane for hw cursor fix
   - dma-buf cache maintenance support

  mali-dp:
   - YUV->RGB conversion support

  rockchip:
   - rk3399/chromebook fixes and improvements

  rcar-du:
   - LVDS support move to drm bridge
   - DT bindings for R8A77995
   - Driver/DT support for R8A77970

  tilcdc:
   - DRM panel support"

* tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux: (1646 commits)
  drm/i915: Fix hibernation with ACPI S0 target state
  drm/i915/execlists: Use a locked clear_bit() for synchronisation with interrupt
  drm/i915: Specify which engines to reset following semaphore/event lockups
  drm/i915/dp: Write to SET_POWER dpcd to enable MST hub.
  drm/amdkfd: Use ordered workqueue to restore processes
  drm/amdgpu: Fix acquiring VM on large-BAR systems
  drm/amd/pp: clean header file hwmgr.h
  drm/amd/pp: use mlck_table.count for array loop index limit
  drm: Fix uabi regression by allowing garbage mode->type from userspace
  drm/amdgpu: Add an ATPX quirk for hybrid laptop
  drm/amdgpu: fix spelling mistake: "asssert" -> "assert"
  drm/amd/pp: Add new asic support in pp_psm.c
  drm/amd/pp: Clean up powerplay code on Vega12
  drm/amd/pp: Add smu irq handlers for legacy asics
  drm/amd/pp: Fix set wrong temperature range on smu7
  drm/amdgpu: Don't change preferred domian when fallback GTT v5
  drm/vmwgfx: Bump version patchlevel and date
  drm/vmwgfx: use monotonic event timestamps
  drm/vmwgfx: Unpin the screen object backup buffer when not used
  drm/vmwgfx: Stricter count of legacy surface device resources
  ...

1 files changed, 78 insertions, 17 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index e7dfb7b44b4b..21adb1b6e5cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -22,7 +22,21 @@
  */
 
 #include "amdgpu.h"
-#define MAX_KIQ_REG_WAIT	100000000 /* in usecs */
+#define MAX_KIQ_REG_WAIT	5000 /* in usecs, 5ms */
+#define MAX_KIQ_REG_BAILOUT_INTERVAL	5 /* in msecs, 5ms */
+#define MAX_KIQ_REG_TRY 20
+
+uint64_t amdgpu_csa_vaddr(struct amdgpu_device *adev)
+{
+	uint64_t addr = adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT;
+
+	addr -= AMDGPU_VA_RESERVED_SIZE;
+
+	if (addr >= AMDGPU_VA_HOLE_START)
+		addr |= AMDGPU_VA_HOLE_END;
+
+	return addr;
+}
 
 bool amdgpu_virt_mmio_blocked(struct amdgpu_device *adev)
 {
@@ -55,14 +69,14 @@ void amdgpu_free_static_csa(struct amdgpu_device *adev) {
 
 /*
  * amdgpu_map_static_csa should be called during amdgpu_vm_init
- * it maps virtual address "AMDGPU_VA_RESERVED_SIZE - AMDGPU_CSA_SIZE"
- * to this VM, and each command submission of GFX should use this virtual
- * address within META_DATA init package to support SRIOV gfx preemption.
+ * it maps virtual address amdgpu_csa_vaddr() to this VM, and each command
+ * submission of GFX should use this virtual address within META_DATA init
+ * package to support SRIOV gfx preemption.
  */
-
 int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			  struct amdgpu_bo_va **bo_va)
 {
+	uint64_t csa_addr = amdgpu_csa_vaddr(adev) & AMDGPU_VA_HOLE_MASK;
 	struct ww_acquire_ctx ticket;
 	struct list_head list;
 	struct amdgpu_bo_list_entry pd;
@@ -90,7 +104,7 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		return -ENOMEM;
 	}
 
-	r = amdgpu_vm_alloc_pts(adev, (*bo_va)->base.vm, AMDGPU_CSA_VADDR,
+	r = amdgpu_vm_alloc_pts(adev, (*bo_va)->base.vm, csa_addr,
 				AMDGPU_CSA_SIZE);
 	if (r) {
 		DRM_ERROR("failed to allocate pts for static CSA, err=%d\n", r);
@@ -99,7 +113,7 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		return r;
 	}
 
-	r = amdgpu_vm_bo_map(adev, *bo_va, AMDGPU_CSA_VADDR, 0, AMDGPU_CSA_SIZE,
+	r = amdgpu_vm_bo_map(adev, *bo_va, csa_addr, 0, AMDGPU_CSA_SIZE,
 			     AMDGPU_PTE_READABLE | AMDGPU_PTE_WRITEABLE |
 			     AMDGPU_PTE_EXECUTABLE);
 
@@ -125,9 +139,9 @@ void amdgpu_virt_init_setting(struct amdgpu_device *adev)
 
 uint32_t amdgpu_virt_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
 {
-	signed long r;
+	signed long r, cnt = 0;
 	unsigned long flags;
-	uint32_t val, seq;
+	uint32_t seq;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 	struct amdgpu_ring *ring = &kiq->ring;
 
@@ -141,18 +155,39 @@ uint32_t amdgpu_virt_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
 	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 
 	r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
-	if (r < 1) {
-		DRM_ERROR("wait for kiq fence error: %ld\n", r);
-		return ~0;
+
+	/* don't wait anymore for gpu reset case because this way may
+	 * block gpu_recover() routine forever, e.g. this virt_kiq_rreg
+	 * is triggered in TTM and ttm_bo_lock_delayed_workqueue() will
+	 * never return if we keep waiting in virt_kiq_rreg, which cause
+	 * gpu_recover() hang there.
+	 *
+	 * also don't wait anymore for IRQ context
+	 * */
+	if (r < 1 && (adev->in_gpu_reset || in_interrupt()))
+		goto failed_kiq_read;
+
+	if (in_interrupt())
+		might_sleep();
+
+	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) {
+		msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
+		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
 	}
-	val = adev->wb.wb[adev->virt.reg_val_offs];
 
-	return val;
+	if (cnt > MAX_KIQ_REG_TRY)
+		goto failed_kiq_read;
+
+	return adev->wb.wb[adev->virt.reg_val_offs];
+
+failed_kiq_read:
+	pr_err("failed to read reg:%x\n", reg);
+	return ~0;
 }
 
 void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v)
 {
-	signed long r;
+	signed long r, cnt = 0;
 	unsigned long flags;
 	uint32_t seq;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
@@ -168,8 +203,34 @@ void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v)
 	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 
 	r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
-	if (r < 1)
-		DRM_ERROR("wait for kiq fence error: %ld\n", r);
+
+	/* don't wait anymore for gpu reset case because this way may
+	 * block gpu_recover() routine forever, e.g. this virt_kiq_rreg
+	 * is triggered in TTM and ttm_bo_lock_delayed_workqueue() will
+	 * never return if we keep waiting in virt_kiq_rreg, which cause
+	 * gpu_recover() hang there.
+	 *
+	 * also don't wait anymore for IRQ context
+	 * */
+	if (r < 1 && (adev->in_gpu_reset || in_interrupt()))
+		goto failed_kiq_write;
+
+	if (in_interrupt())
+		might_sleep();
+
+	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) {
+
+		msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
+		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+	}
+
+	if (cnt > MAX_KIQ_REG_TRY)
+		goto failed_kiq_write;
+
+	return;
+
+failed_kiq_write:
+	pr_err("failed to write reg:%x\n", reg);
 }
 
 /**