Merge tag 'drm-next-2019-11-27' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Lots of stuff in here, though it hasn't been too insane this merge
  apart from dealing with the security fun.

  uapi:
   - export different colorspace properties on DP vs HDMI
   - new fourcc for ARM 16x16 block format
   - syncobj: allow querying last submitted timeline value
   - DRM_FORMAT_BIG_ENDIAN defined as unsigned

  core:
   - allow using gem vma manager in ttm
   - connector/encoder/bridge doc fixes
   - allow more than 3 encoders for a connector
   - displayport mst suspend/resume reprobing support
   - vram lazy unmapping, uniform vram mm and gem vram
   - edid cleanups + AVI informframe bar info
   - displayport helpers - dpcd parser added

  dp_cec:
   - Allow a connector to be associated with a cec device

  ttm:
   - pipelining with no_gpu_wait fix
   - always keep BOs on the LRU

  sched:
   - allow free_job routine to sleep

  i915:
   - Block userptr from mappable GTT
   - i915 perf uapi versioning
   - OA stream dynamic reconfiguration
   - make context persistence optional
   - introduce DRM_I915_UNSTABLE Kconfig
   - add fake lmem testing under unstable
   - BT.2020 support for DP MSA
   - struct mutex elimination
   - Tigerlake display/PLL/power management improvements
   - Jasper Lake PCH support
   - refactor PMU for multiple GPUs
   - Icelake firmware update
   - Split out vga + switcheroo code

  amdgpu:
   - implement dma-buf import/export without helpers
   - vega20 RAS enablement
   - DC i2c over aux fixes
   - renoir GPU reset
   - DC HDCP support
   - BACO support for CI/VI asics
   - MSI-X support
   - Arcturus EEPROM support
   - Arcturus VCN encode support
   - VCN dynamic powergating on RV/RV2

  amdkfd:
   - add navi12/14/renoir support to kfd

  radeon:
   - SI dpm fix ported from amdgpu
   - fix bad DMA on ppc platforms

  gma500:
   - memory leak fixes

  qxl:
   - convert to new gem mmap

  exynos:
   - build warning fix

  komeda:
   - add aclk sysfs attribute

  v3d:
   - userspace cleanup uapi change

  i810:
   - fix for underflow in dispatch ioctls

  ast:
   - refactor show_cursor

  mgag200:
   - refactor show_cursor

  arcgpu:
   - encoder finding improvements

  mediatek:
   - mipi_tx, dsi and partial crtc support for MT8183 SoC
   - rotation support

  meson:
   - add suspend/resume support

  omap:
   - misc refactors

  tegra:
   - DisplayPort support for Tegra 210, 186 and 194.
   - IOMMU-backed DMA API fixes

  panfrost:
   - fix lockdep issue
   - simplify devfreq integration

  rcar-du:
   - R8A774B1 SoC support
   - fixes for H2 ES2.0

  sun4i:
   - vcc-dsi regulator support

  virtio-gpu:
   - vmexit vs spinlock fix
   - move to gem shmem helpers
   - handle large command buffers with cma"

* tag 'drm-next-2019-11-27' of git://anongit.freedesktop.org/drm/drm: (1855 commits)
  drm/amdgpu: invalidate mmhub semaphore workaround in gmc9/gmc10
  drm/amdgpu: initialize vm_inv_eng0_sem for gfxhub and mmhub
  drm/amd/amdgpu/sriov skip RLCG s/r list for arcturus VF.
  drm/amd/amdgpu/sriov temporarily skip ras,dtm,hdcp for arcturus VF
  drm/amdgpu/gfx10: re-init clear state buffer after gpu reset
  merge fix for "ftrace: Rework event_create_dir()"
  drm/amdgpu: Update Arcturus golden registers
  drm/amdgpu/gfx10: fix out-of-bound mqd_backup array access
  drm/amdgpu/gfx10: explicitly wait for cp idle after halt/unhalt
  Revert "drm/amd/display: enable S/G for RAVEN chip"
  drm/amdgpu: disable gfxoff on original raven
  drm/amdgpu: remove experimental flag for Navi14
  drm/amdgpu: disable gfxoff when using register read interface
  drm/amdgpu/powerplay: properly set PP_GFXOFF_MASK (v2)
  drm/amdgpu: fix bad DMA from INTERRUPT_CNTL2
  drm/radeon: fix bad DMA from INTERRUPT_CNTL2
  drm/amd/display: Fix debugfs on MST connectors
  drm/amdgpu/nv: add asic func for fetching vbios from rom directly
  drm/amdgpu: put flush_delayed_work at first
  drm/amdgpu/vcn2.5: fix the enc loop with hw fini
  ...

1 files changed, 32 insertions, 11 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 6c76bb2a6843..f80fd3428c98 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -317,8 +317,6 @@ struct amdgpu_ras {
 	struct list_head head;
 	/* debugfs */
 	struct dentry *dir;
-	/* debugfs ctrl */
-	struct dentry *ent;
 	/* sysfs */
 	struct device_attribute features_attr;
 	struct bin_attribute badpages_attr;
@@ -334,7 +332,7 @@ struct amdgpu_ras {
 	struct mutex recovery_lock;
 
 	uint32_t flags;
-
+	bool reboot;
 	struct amdgpu_ras_eeprom_control eeprom_control;
 };
 
@@ -347,15 +345,14 @@ struct ras_err_data {
 	unsigned long ue_count;
 	unsigned long ce_count;
 	unsigned long err_addr_cnt;
-	uint64_t *err_addr;
+	struct eeprom_table_record *err_addr;
 };
 
 struct ras_err_handler_data {
-	/* point to bad pages array */
-	struct {
-		unsigned long bp;
-		struct amdgpu_bo *bo;
-	} *bps;
+	/* point to bad page records array */
+	struct eeprom_table_record *bps;
+	/* point to reserved bo array */
+	struct amdgpu_bo **bps_bo;
 	/* the count of entries */
 	int count;
 	/* the space can place new entries */
@@ -365,7 +362,7 @@ struct ras_err_handler_data {
 };
 
 typedef int (*ras_ih_cb)(struct amdgpu_device *adev,
-		struct ras_err_data *err_data,
+		void *err_data,
 		struct amdgpu_iv_entry *entry);
 
 struct ras_ih_data {
@@ -481,6 +478,7 @@ static inline int amdgpu_ras_is_supported(struct amdgpu_device *adev,
 	return ras && (ras->supported & (1 << block));
 }
 
+int amdgpu_ras_recovery_init(struct amdgpu_device *adev);
 int amdgpu_ras_request_reset_on_boot(struct amdgpu_device *adev,
 		unsigned int block);
 
@@ -492,7 +490,7 @@ unsigned long amdgpu_ras_query_error_count(struct amdgpu_device *adev,
 
 /* error handling functions */
 int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
-		unsigned long *bps, int pages);
+		struct eeprom_table_record *bps, int pages);
 
 int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev);
 
@@ -501,6 +499,12 @@ static inline int amdgpu_ras_reset_gpu(struct amdgpu_device *adev,
 {
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
+	/* save bad page to eeprom before gpu reset,
+	 * i2c may be unstable in gpu reset
+	 */
+	if (in_task())
+		amdgpu_ras_reserve_bad_pages(adev);
+
 	if (atomic_cmpxchg(&ras->in_recovery, 0, 1) == 0)
 		schedule_work(&ras->recovery_work);
 	return 0;
@@ -566,6 +570,13 @@ amdgpu_ras_error_to_ta(enum amdgpu_ras_error_type error) {
 int amdgpu_ras_init(struct amdgpu_device *adev);
 int amdgpu_ras_fini(struct amdgpu_device *adev);
 int amdgpu_ras_pre_fini(struct amdgpu_device *adev);
+int amdgpu_ras_late_init(struct amdgpu_device *adev,
+			 struct ras_common_if *ras_block,
+			 struct ras_fs_if *fs_info,
+			 struct ras_ih_if *ih_info);
+void amdgpu_ras_late_fini(struct amdgpu_device *adev,
+			  struct ras_common_if *ras_block,
+			  struct ras_ih_if *ih_info);
 
 int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 		struct ras_common_if *head, bool enable);
@@ -599,4 +610,14 @@ int amdgpu_ras_interrupt_remove_handler(struct amdgpu_device *adev,
 
 int amdgpu_ras_interrupt_dispatch(struct amdgpu_device *adev,
 		struct ras_dispatch_if *info);
+
+extern atomic_t amdgpu_ras_in_intr;
+
+static inline bool amdgpu_ras_intr_triggered(void)
+{
+	return !!atomic_read(&amdgpu_ras_in_intr);
+}
+
+void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev);
+
 #endif