Merge tag 'drm-next-2019-07-16' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "The biggest thing in this is the AMD Navi GPU support, this again
  contains a bunch of header files that are large. These are the new AMD
  RX5700 GPUs that just recently became available.

  New drivers:
   - ST-Ericsson MCDE driver
   - Ingenic JZ47xx SoC

  UAPI change:
   - HDR source metadata property

  Core:
   - HDR inforframes and EDID parsing
   - drm hdmi infoframe unpacking
   - remove prime sg_table caching into dma-buf
   - New gem vram helpers to reduce driver code
   - Lots of drmP.h removal
   - reservation fencing fix
   - documentation updates
   - drm_fb_helper_connector removed
   - mode name command handler rewrite

  fbcon:
   - Remove the fbcon notifiers

  ttm:
   - forward progress fixes

  dma-buf:
   - make mmap call optional
   - debugfs refcount fixes
   - dma-fence free with pending signals fix
   - each dma-buf gets an inode

  Panels:
   - Lots of additional panel bindings

  amdgpu:
   - initial navi10 support
   - avoid hw reset
   - HDR metadata support
   - new thermal sensors for vega asics
   - RAS fixes
   - use HMM rather than MMU notifier
   - xgmi topology via kfd
   - SR-IOV fixes
   - driver reload fixes
   - DC use a core bpc attribute
   - Aux fixes for DC
   - Bandwidth calc updates for DC
   - Clock handling refactor
   - kfd VEGAM support

  vmwgfx:
   - Coherent memory support changes

  i915:
   - HDR Support
   - HDMI i2c link
   - Icelake multi-segmented gamma support
   - GuC firmware update
   - Mule Creek Canyon PCH support for EHL
   - EHL platform updtes
   - move i915.alpha_support to i915.force_probe
   - runtime PM refactoring
   - VBT parsing refactoring
   - DSI fixes
   - struct mutex dependency reduction
   - GEM code reorg

  mali-dp:
   - Komeda driver features

  msm:
   - dsi vs EPROBE_DEFER fixes
   - msm8998 snapdragon 835 support
   - a540 gpu support
   - mdp5 and dpu interconnect support

  exynos:
   - drmP.h removal

  tegra:
   - misc fixes

  tda998x:
   - audio support improvements
   - pixel repeated mode support
   - quantisation range handling corrections
   - HDMI vendor info fix

  armada:
   - interlace support fix
   - overlay/video plane register handling refactor
   - add gamma support

  rockchip:
   - RX3328 support

  panfrost:
   - expose perf counters via hidden ioctls

  vkms:
   - enumerate CRC sources list

  ast:
   - rework BO handling

  mgag200:
   - rework BO handling

  dw-hdmi:
   - suspend/resume support

  rcar-du:
   - R8A774A1 Soc Support
   - LVDS dual-link mode support
   - Additional formats
   - Misc fixes

  omapdrm:
   - DSI command mode display support

  stm
   - fb modifier support
   - runtime PM support

  sun4i:
   - use vmap ops

  vc4:
   - binner bo binding rework

  v3d:
   - compute shader support
   - resync/sync fixes
   - job management refactoring

  lima:
   - NULL pointer in irq handler fix
   - scheduler default timeout

  virtio:
   - fence seqno support
   - trace events

  bochs:
   - misc fixes

  tc458767:
   - IRQ/HDP handling

  sii902x:
   - HDMI audio support

  atmel-hlcdc:
   - misc fixes

  meson:
   - zpos support"

* tag 'drm-next-2019-07-16' of git://anongit.freedesktop.org/drm/drm: (1815 commits)
  Revert "Merge branch 'vmwgfx-next' of git://people.freedesktop.org/~thomash/linux into drm-next"
  Revert "mm: adjust apply_to_pfn_range interface for dropped token."
  mm: adjust apply_to_pfn_range interface for dropped token.
  drm/amdgpu/navi10: add uclk activity sensor
  drm/amdgpu: properly guard the generic discovery code
  drm/amdgpu: add missing documentation on new module parameters
  drm/amdgpu: don't invalidate caches in RELEASE_MEM, only do the writeback
  drm/amd/display: avoid 64-bit division
  drm/amdgpu/psp11: simplify the ucode register logic
  drm/amdgpu: properly guard DC support in navi code
  drm/amd/powerplay: vega20: fix uninitialized variable use
  drm/amd/display: dcn20: include linux/delay.h
  amdgpu: make pmu support optional
  drm/amd/powerplay: Zero initialize current_rpm in vega20_get_fan_speed_percent
  drm/amd/powerplay: Zero initialize freq in smu_v11_0_get_current_clk_freq
  drm/amd/powerplay: Use memset to initialize metrics structs
  drm/amdgpu/mes10.1: Fix header guard
  drm/amd/powerplay: add temperature sensor support for navi10
  drm/amdgpu: fix scheduler timeout calc
  drm/amdgpu: Prepare for hmm_range_register API change (v2)
  ...

1 files changed, 167 insertions, 19 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 1e2cc9d68a05..1b0613c7cf95 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -22,21 +22,23 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
-#include <drm/drmP.h>
 #include <drm/amdgpu_drm.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_gem.h>
+#include <drm/drm_vblank.h>
 #include "amdgpu_drv.h"
 
 #include <drm/drm_pciids.h>
 #include <linux/console.h>
 #include <linux/module.h>
+#include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <linux/vga_switcheroo.h>
 #include <drm/drm_probe_helper.h>
 
 #include "amdgpu.h"
 #include "amdgpu_irq.h"
-#include "amdgpu_gem.h"
+#include "amdgpu_dma_buf.h"
 
 #include "amdgpu_amdkfd.h"
 
@@ -76,11 +78,14 @@
  * - 3.30.0 - Add AMDGPU_SCHED_OP_CONTEXT_PRIORITY_OVERRIDE.
  * - 3.31.0 - Add support for per-flip tiling attribute changes with DC
  * - 3.32.0 - Add syncobj timeline support to AMDGPU_CS.
+ * - 3.33.0 - Fixes for GDS ENOMEM failures in AMDGPU_CS.
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	32
+#define KMS_DRIVER_MINOR	33
 #define KMS_DRIVER_PATCHLEVEL	0
 
+#define AMDGPU_MAX_TIMEOUT_PARAM_LENTH	256
+
 int amdgpu_vram_limit = 0;
 int amdgpu_vis_vram_limit = 0;
 int amdgpu_gart_size = -1; /* auto */
@@ -93,7 +98,7 @@ int amdgpu_disp_priority = 0;
 int amdgpu_hw_i2c = 0;
 int amdgpu_pcie_gen2 = -1;
 int amdgpu_msi = -1;
-int amdgpu_lockup_timeout = 10000;
+char amdgpu_lockup_timeout[AMDGPU_MAX_TIMEOUT_PARAM_LENTH];
 int amdgpu_dpm = -1;
 int amdgpu_fw_load_type = -1;
 int amdgpu_aspm = -1;
@@ -106,7 +111,6 @@ int amdgpu_vm_fragment_size = -1;
 int amdgpu_vm_block_size = -1;
 int amdgpu_vm_fault_stop = 0;
 int amdgpu_vm_debug = 0;
-int amdgpu_vram_page_split = 512;
 int amdgpu_vm_update_mode = -1;
 int amdgpu_exp_hw_support = 0;
 int amdgpu_dc = -1;
@@ -134,6 +138,10 @@ int amdgpu_emu_mode = 0;
 uint amdgpu_smu_memory_pool_size = 0;
 /* FBC (bit 0) disabled by default*/
 uint amdgpu_dc_feature_mask = 0;
+int amdgpu_async_gfx_ring = 1;
+int amdgpu_mcbp = 0;
+int amdgpu_discovery = 0;
+int amdgpu_mes = 0;
 
 struct amdgpu_mgpu_info mgpu_info = {
 	.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
@@ -227,16 +235,28 @@ MODULE_PARM_DESC(msi, "MSI support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(msi, amdgpu_msi, int, 0444);
 
 /**
- * DOC: lockup_timeout (int)
- * Set GPU scheduler timeout value in ms. Value 0 is invalidated, will be adjusted to 10000.
- * Negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET). The default is 10000.
- */
-MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms > 0 (default 10000)");
-module_param_named(lockup_timeout, amdgpu_lockup_timeout, int, 0444);
+ * DOC: lockup_timeout (string)
+ * Set GPU scheduler timeout value in ms.
+ *
+ * The format can be [Non-Compute] or [GFX,Compute,SDMA,Video]. That is there can be one or
+ * multiple values specified. 0 and negative values are invalidated. They will be adjusted
+ * to default timeout.
+ *  - With one value specified, the setting will apply to all non-compute jobs.
+ *  - With multiple values specified, the first one will be for GFX. The second one is for Compute.
+ *    And the third and fourth ones are for SDMA and Video.
+ * By default(with no lockup_timeout settings), the timeout for all non-compute(GFX, SDMA and Video)
+ * jobs is 10000. And there is no timeout enforced on compute jobs.
+ */
+MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms (default: 10000 for non-compute jobs and infinity timeout for compute jobs."
+		" 0: keep default value. negative: infinity timeout), "
+		"format is [Non-Compute] or [GFX,Compute,SDMA,Video]");
+module_param_string(lockup_timeout, amdgpu_lockup_timeout, sizeof(amdgpu_lockup_timeout), 0444);
 
 /**
  * DOC: dpm (int)
- * Override for dynamic power management setting (1 = enable, 0 = disable). The default is -1 (auto).
+ * Override for dynamic power management setting
+ * (0 = disable, 1 = enable, 2 = enable sw smu driver for vega20)
+ * The default is -1 (auto).
  */
 MODULE_PARM_DESC(dpm, "DPM support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(dpm, amdgpu_dpm, int, 0444);
@@ -332,13 +352,6 @@ MODULE_PARM_DESC(vm_update_mode, "VM update using CPU (0 = never (default except
 module_param_named(vm_update_mode, amdgpu_vm_update_mode, int, 0444);
 
 /**
- * DOC: vram_page_split (int)
- * Override the number of pages after we split VRAM allocations (default 512, -1 = disable). The default is 512.
- */
-MODULE_PARM_DESC(vram_page_split, "Number of pages after we split VRAM allocations (default 512, -1 = disable)");
-module_param_named(vram_page_split, amdgpu_vram_page_split, int, 0444);
-
-/**
  * DOC: exp_hw_support (int)
  * Enable experimental hw support (1 = enable). The default is 0 (disabled).
  */
@@ -561,6 +574,39 @@ MODULE_PARM_DESC(smu_memory_pool_size,
 		"0x1 = 256Mbyte, 0x2 = 512Mbyte, 0x4 = 1 Gbyte, 0x8 = 2GByte");
 module_param_named(smu_memory_pool_size, amdgpu_smu_memory_pool_size, uint, 0444);
 
+/**
+ * DOC: async_gfx_ring (int)
+ * It is used to enable gfx rings that could be configured with different prioritites or equal priorities
+ */
+MODULE_PARM_DESC(async_gfx_ring,
+	"Asynchronous GFX rings that could be configured with either different priorities (HP3D ring and LP3D ring), or equal priorities (0 = disabled, 1 = enabled (default))");
+module_param_named(async_gfx_ring, amdgpu_async_gfx_ring, int, 0444);
+
+/**
+ * DOC: mcbp (int)
+ * It is used to enable mid command buffer preemption. (0 = disabled (default), 1 = enabled)
+ */
+MODULE_PARM_DESC(mcbp,
+	"Enable Mid-command buffer preemption (0 = disabled (default), 1 = enabled)");
+module_param_named(mcbp, amdgpu_mcbp, int, 0444);
+
+/**
+ * DOC: discovery (int)
+ * Allow driver to discover hardware IP information from IP Discovery table at the top of VRAM.
+ */
+MODULE_PARM_DESC(discovery,
+	"Allow driver to discover hardware IPs from IP Discovery table at the top of VRAM");
+module_param_named(discovery, amdgpu_discovery, int, 0444);
+
+/**
+ * DOC: mes (int)
+ * Enable Micro Engine Scheduler. This is a new hw scheduling engine for gfx, sdma, and compute.
+ * (0 = disabled (default), 1 = enabled)
+ */
+MODULE_PARM_DESC(mes,
+	"Enable Micro Engine Scheduler (0 = disabled (default), 1 = enabled)");
+module_param_named(mes, amdgpu_mes, int, 0444);
+
 #ifdef CONFIG_HSA_AMD
 /**
  * DOC: sched_policy (int)
@@ -655,6 +701,24 @@ MODULE_PARM_DESC(noretry,
 int halt_if_hws_hang;
 module_param(halt_if_hws_hang, int, 0644);
 MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)");
+
+/**
+ * DOC: hws_gws_support(bool)
+ * Whether HWS support gws barriers. Default value: false (not supported)
+ * This will be replaced with a MEC firmware version check once firmware
+ * is ready
+ */
+bool hws_gws_support;
+module_param(hws_gws_support, bool, 0444);
+MODULE_PARM_DESC(hws_gws_support, "MEC FW support gws barriers (false = not supported (Default), true = supported)");
+
+/**
+  * DOC: queue_preemption_timeout_ms (int)
+  * queue preemption timeout in ms (1 = Minimum, 9000 = default)
+  */
+int queue_preemption_timeout_ms = 9000;
+module_param(queue_preemption_timeout_ms, int, 0644);
+MODULE_PARM_DESC(queue_preemption_timeout_ms, "queue preemption timeout in ms (1 = Minimum, 9000 = default)");
 #endif
 
 /**
@@ -665,6 +729,22 @@ MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (defau
 MODULE_PARM_DESC(dcfeaturemask, "all stable DC features enabled (default))");
 module_param_named(dcfeaturemask, amdgpu_dc_feature_mask, uint, 0444);
 
+/**
+ * DOC: abmlevel (uint)
+ * Override the default ABM (Adaptive Backlight Management) level used for DC
+ * enabled hardware. Requires DMCU to be supported and loaded.
+ * Valid levels are 0-4. A value of 0 indicates that ABM should be disabled by
+ * default. Values 1-4 control the maximum allowable brightness reduction via
+ * the ABM algorithm, with 1 being the least reduction and 4 being the most
+ * reduction.
+ *
+ * Defaults to 0, or disabled. Userspace can still override this level later
+ * after boot.
+ */
+uint amdgpu_dm_abm_level = 0;
+MODULE_PARM_DESC(abmlevel, "ABM level (0 = off (default), 1-4 = backlight reduction level) ");
+module_param_named(abmlevel, amdgpu_dm_abm_level, uint, 0444);
+
 static const struct pci_device_id pciidlist[] = {
 #ifdef  CONFIG_DRM_AMDGPU_SI
 	{0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},
@@ -921,6 +1001,14 @@ static const struct pci_device_id pciidlist[] = {
 	/* Raven */
 	{0x1002, 0x15dd, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU},
 	{0x1002, 0x15d8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU},
+	/* Navi10 */
+	{0x1002, 0x7310, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
+	{0x1002, 0x7312, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
+	{0x1002, 0x7318, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
+	{0x1002, 0x7319, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
+	{0x1002, 0x731A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
+	{0x1002, 0x731B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
+	{0x1002, 0x731F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 
 	{0, 0, 0}
 };
@@ -1216,6 +1304,66 @@ int amdgpu_file_to_fpriv(struct file *filp, struct amdgpu_fpriv **fpriv)
 	return 0;
 }
 
+int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
+{
+	char *input = amdgpu_lockup_timeout;
+	char *timeout_setting = NULL;
+	int index = 0;
+	long timeout;
+	int ret = 0;
+
+	/*
+	 * By default timeout for non compute jobs is 10000.
+	 * And there is no timeout enforced on compute jobs.
+	 */
+	adev->gfx_timeout = msecs_to_jiffies(10000);
+	adev->sdma_timeout = adev->video_timeout = adev->gfx_timeout;
+	adev->compute_timeout = MAX_SCHEDULE_TIMEOUT;
+
+	if (strnlen(input, AMDGPU_MAX_TIMEOUT_PARAM_LENTH)) {
+		while ((timeout_setting = strsep(&input, ",")) &&
+				strnlen(timeout_setting, AMDGPU_MAX_TIMEOUT_PARAM_LENTH)) {
+			ret = kstrtol(timeout_setting, 0, &timeout);
+			if (ret)
+				return ret;
+
+			if (timeout == 0) {
+				index++;
+				continue;
+			} else if (timeout < 0) {
+				timeout = MAX_SCHEDULE_TIMEOUT;
+			} else {
+				timeout = msecs_to_jiffies(timeout);
+			}
+
+			switch (index++) {
+			case 0:
+				adev->gfx_timeout = timeout;
+				break;
+			case 1:
+				adev->compute_timeout = timeout;
+				break;
+			case 2:
+				adev->sdma_timeout = timeout;
+				break;
+			case 3:
+				adev->video_timeout = timeout;
+				break;
+			default:
+				break;
+			}
+		}
+		/*
+		 * There is only one value specified and
+		 * it should apply to all non-compute jobs.
+		 */
+		if (index == 1)
+			adev->sdma_timeout = adev->video_timeout = adev->gfx_timeout;
+	}
+
+	return ret;
+}
+
 static bool
 amdgpu_get_crtc_scanout_position(struct drm_device *dev, unsigned int pipe,
 				 bool in_vblank_irq, int *vpos, int *hpos,