Merge tag 'drm-next-2020-12-11' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Not a huge amount of big things here, AMD has support for a few new HW
  variants (vangogh, green sardine, dimgrey cavefish), Intel has some
  more DG1 enablement. We have a few big reworks of the TTM layers and
  interfaces, GEM and atomic internal API reworks cross tree. fbdev is
  marked orphaned in here as well to reflect the current reality.

  core:
   - documentation updates
   - deprecate DRM_FORMAT_MOD_NONE
   - atomic crtc enable/disable rework
   - GEM convert drivers to gem object functions
   - remove SCATTER_LIST_MAX_SEGMENT

  sched:
   - avoid infinite waits

  ttm:
   - remove AGP support
   - don't modify caching for swapout
   - ttm pinning rework
   - major TTM reworks
   - new backend allocator
   - multihop support

  vram-helper:
   - top down BO placement fix
   - TTM changes
   - GEM object support

  displayport:
   - DP 2.0 DPCD prep work
   - DP MST extended DPCD caps

  fbdev:
   - mark as orphaned

  amdgpu:
   - Initial Vangogh support
   - Green Sardine support
   - Dimgrey Cavefish support
   - SG display support for renoir
   - SMU7 improvements
   - gfx9+ modiifier support
   - CI BACO fixes

  radeon:
   - expose voltage via hwmon on SUMO

  amdkfd:
   - fix unique id handling

  i915:
   - more DG1 enablement
   - bigjoiner support
   - integer scaling filter support
   - async flip support
   - ICL+ DSI command mode
   - Improve display shutdown
   - Display refactoring
   - eLLC machine fbdev loading fix
   - dma scatterlist fixes
   - TGL hang fixes
   - eLLC display buffer caching on SKL+
   - MOCS PTE seeting for gen9+

  msm:
   - Shutdown hook
   - GPU cooling device support
   - DSI 7nm and 10nm phy/pll updates
   - sm8150/sm2850 DPU support
   - GEM locking re-work
   - LLCC system cache support

  aspeed:
   - sysfs output config support

  ast:
   - LUT fix
   - new display mode

  gma500:
   - remove 2d framebuffer accel

  panfrost:
   - move gpu reset to a worker

  exynos:
   - new HDMI mode support

  mediatek:
   - MT8167 support
   - yaml bindings
   - MIPI DSI phy code moved

  etnaviv:
   - new perf counter
   - more lockdep annotation

  hibmc:
   - i2c DDC support

  ingenic:
   - pixel clock reset fix
   - reserved memory support
   - allow both DMA channels at once
   - different pixel format support
   - 30/24/8-bit palette modes

  tilcdc:
   - don't keep vblank irq enabled

  vc4:
   - new maintainer added
   - DSI registration fix

  virtio:
   - blob resource support
   - host visible and cross-device support
   - uuid api support"

* tag 'drm-next-2020-12-11' of git://anongit.freedesktop.org/drm/drm: (1754 commits)
  drm/amdgpu: Initialise drm_gem_object_funcs for imported BOs
  drm/amdgpu: fix size calculation with stolen vga memory
  drm/amdgpu: remove amdgpu_ttm_late_init  and amdgpu_bo_late_init
  drm/amdgpu: free the pre-OS console framebuffer after the first modeset
  drm/amdgpu: enable runtime pm using BACO on CI dGPUs
  drm/amdgpu/cik: enable BACO reset on Bonaire
  drm/amd/pm: update smu10.h WORKLOAD_PPLIB setting for raven
  drm/amd/pm: remove one unsupported smu function for vangogh
  drm/amd/display: setup system context for APUs
  drm/amd/display: add S/G support for Vangogh
  drm/amdkfd: Fix leak in dmabuf import
  drm/amdgpu: use AMDGPU_NUM_VMID when possible
  drm/amdgpu: fix sdma instance fw version and feature version init
  drm/amd/pm: update driver if version for dimgrey_cavefish
  drm/amd/display: 3.2.115
  drm/amd/display: [FW Promotion] Release 0.0.45
  drm/amd/display: Revert DCN2.1 dram_clock_change_latency update
  drm/amd/display: Enable gpu_vm_support for dcn3.01
  drm/amd/display: Fixed the audio noise during mode switching with HDCP mode on
  drm/amd/display: Add wm table for Renoir
  ...

1 files changed, 15 insertions, 23 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 0e64c39a2372..1dd040166c63 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -27,9 +27,9 @@
 #include <linux/bits.h>
 #include "atom.h"
 
-#define EEPROM_I2C_TARGET_ADDR_VEGA20    	0xA0
-#define EEPROM_I2C_TARGET_ADDR_ARCTURUS  	0xA8
-#define EEPROM_I2C_TARGET_ADDR_ARCTURUS_D342  	0xA0
+#define EEPROM_I2C_TARGET_ADDR_VEGA20		0xA0
+#define EEPROM_I2C_TARGET_ADDR_ARCTURUS		0xA8
+#define EEPROM_I2C_TARGET_ADDR_ARCTURUS_D342	0xA0
 
 /*
  * The 2 macros bellow represent the actual size in bytes that
@@ -124,11 +124,11 @@ static void __decode_table_header_from_buff(struct amdgpu_ras_eeprom_table_heade
 {
 	uint32_t *pp = (uint32_t *)buff;
 
-	hdr->header 	      = le32_to_cpu(pp[0]);
-	hdr->version 	      = le32_to_cpu(pp[1]);
+	hdr->header	      = le32_to_cpu(pp[0]);
+	hdr->version	      = le32_to_cpu(pp[1]);
 	hdr->first_rec_offset = le32_to_cpu(pp[2]);
-	hdr->tbl_size 	      = le32_to_cpu(pp[3]);
-	hdr->checksum 	      = le32_to_cpu(pp[4]);
+	hdr->tbl_size	      = le32_to_cpu(pp[3]);
+	hdr->checksum	      = le32_to_cpu(pp[4]);
 }
 
 static int __update_table_header(struct amdgpu_ras_eeprom_control *control,
@@ -149,7 +149,11 @@ static int __update_table_header(struct amdgpu_ras_eeprom_control *control,
 
 	msg.addr = control->i2c_address;
 
+	/* i2c may be unstable in gpu reset */
+	down_read(&adev->reset_sem);
 	ret = i2c_transfer(&adev->pm.smu_i2c, &msg, 1);
+	up_read(&adev->reset_sem);
+
 	if (ret < 1)
 		DRM_ERROR("Failed to write EEPROM table header, ret:%d", ret);
 
@@ -475,7 +479,6 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 	int i, ret = 0;
 	struct i2c_msg *msgs, *msg;
 	unsigned char *buffs, *buff;
-	bool sched_ras_recovery = false;
 	struct eeprom_table_record *record;
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
@@ -513,7 +516,6 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 			"Saved bad pages(%d) reaches threshold value(%d).\n",
 			control->num_recs + num, ras->bad_page_cnt_threshold);
 		control->tbl_hdr.header = EEPROM_TABLE_HDR_BAD;
-		sched_ras_recovery = true;
 	}
 
 	/* In case of overflow just start from beginning to not lose newest records */
@@ -557,7 +559,11 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 		control->next_addr += EEPROM_TABLE_RECORD_SIZE;
 	}
 
+	/* i2c may be unstable in gpu reset */
+	down_read(&adev->reset_sem);
 	ret = i2c_transfer(&adev->pm.smu_i2c, msgs, num);
+	up_read(&adev->reset_sem);
+
 	if (ret < 1) {
 		DRM_ERROR("Failed to process EEPROM table records, ret:%d", ret);
 
@@ -595,20 +601,6 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 		__update_tbl_checksum(control, records, num, old_hdr_byte_sum);
 
 		__update_table_header(control, buffs);
-
-		if (sched_ras_recovery) {
-			/*
-			 * Before scheduling ras recovery, assert the related
-			 * flag first, which shall bypass common bad page
-			 * reservation execution in amdgpu_ras_reset_gpu.
-			 */
-			amdgpu_ras_get_context(adev)->flags |=
-				AMDGPU_RAS_FLAG_SKIP_BAD_PAGE_RESV;
-
-			dev_warn(adev->dev, "Conduct ras recovery due to bad "
-				"page threshold reached.\n");
-			amdgpu_ras_reset_gpu(adev);
-		}
 	} else if (!__validate_tbl_checksum(control, records, num)) {
 		DRM_WARN("EEPROM Table checksum mismatch!");
 		/* TODO Uncomment when EEPROM read/write is relliable */