Merge tag 'drm-next-2022-03-24' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Lots of work all over, Intel improving DG2 support, amdkfd CRIU
  support, msm new hw support, and faster fbdev support.

  dma-buf:
   - rename dma-buf-map to iosys-map

  core:
   - move buddy allocator to core
   - add pci/platform init macros
   - improve EDID parser deep color handling
   - EDID timing type 7 support
   - add GPD Win Max quirk
   - add yes/no helpers to string_helpers
   - flatten syncobj chains
   - add nomodeset support to lots of drivers
   - improve fb-helper clipping support
   - add default property value interface

  fbdev:
   - improve fbdev ops speed

  ttm:
   - add a backpointer from ttm bo->ttm resource

  dp:
   - move displayport headers
   - add a dp helper module

  bridge:
   - anx7625 atomic support, HDCP support

  panel:
   - split out panel-lvds and lvds bindings
   - find panels in OF subnodes

  privacy:
   - add chromeos privacy screen support

  fb:
   - hot unplug fw fb on forced removal

  simpledrm:
   - request region instead of marking ioresource busy
   - add panel oreintation property

  udmabuf:
   - fix oops with 0 pages

  amdgpu:
   - power management code cleanup
   - Enable freesync video mode by default
   - RAS code cleanup
   - Improve VRAM access for debug using SDMA
   - SR-IOV rework special register access and fixes
   - profiling power state request ioctl
   - expose IP discovery via sysfs
   - Cyan skillfish updates
   - GC 10.3.7, SDMA 5.2.7, DCN 3.1.6 updates
   - expose benchmark tests via debugfs
   - add module param to disable XGMI for testing
   - GPU reset debugfs register dumping support

  amdkfd:
   - CRIU support
   - SDMA queue fixes

  radeon:
   - UVD suspend fix
   - iMac backlight fix

  i915:
   - minimal parallel submission for execlists
   - DG2-G12 subplatform added
   - DG2 programming workarounds
   - DG2 accelerated migration support
   - flat CCS and CCS engine support for XeHP
   - initial small BAR support
   - drop fake LMEM support
   - ADL-N PCH support
   - bigjoiner updates
   - introduce VMA resources and async unbinding
   - register definitions cleanups
   - multi-FBC refactoring
   - DG1 OPROM over SPI support
   - ADL-N platform enabling
   - opregion mailbox #5 support
   - DP MST ESI improvements
   - drm device based logging
   - async flip optimisation for DG2
   - CPU arch abstraction fixes
   - improve GuC ADS init to work on aarch64
   - tweak TTM LRU priority hint
   - GuC 69.0.3 support
   - remove short term execbuf pins

  nouveau:
   - higher DP/eDP bitrates
   - backlight fixes

  msm:
   - dpu + dp support for sc8180x
   - dp support for sm8350
   - dpu + dsi support for qcm2290
   - 10nm dsi phy tuning support
   - bridge support for dp encoder
   - gpu support for additional 7c3 SKUs

  ingenic:
   - HDMI support for JZ4780
   - aux channel EDID support

  ast:
   - AST2600 support
   - add wide screen support
   - create DP/DVI connectors

  omapdrm:
   - fix implicit dma_buf fencing

  vc4:
   - add CSC + full range support
   - better display firmware handoff

  panfrost:
   - add initial dual-core GPU support

  stm:
   - new revision support
   - fb handover support

  mediatek:
   - transfer display binding document to yaml format.
   - add mt8195 display device binding.
   - allow commands to be sent during video mode.
   - add wait_for_event for crtc disable by cmdq.

  tegra:
   - YUV format support

  rcar-du:
   - LVDS support for M3-W+ (R8A77961)

  exynos:
   - BGR pixel format for FIMD device"

* tag 'drm-next-2022-03-24' of git://anongit.freedesktop.org/drm/drm: (1529 commits)
  drm/i915/display: Do not re-enable PSR after it was marked as not reliable
  drm/i915/display: Fix HPD short pulse handling for eDP
  drm/amdgpu: Use drm_mode_copy()
  drm/radeon: Use drm_mode_copy()
  drm/amdgpu: Use ternary operator in `vcn_v1_0_start()`
  drm/amdgpu: Remove pointless on stack mode copies
  drm/amd/pm: fix indenting in __smu_cmn_reg_print_error()
  drm/amdgpu/dc: fix typos in comments
  drm/amdgpu: fix typos in comments
  drm/amd/pm: fix typos in comments
  drm/amdgpu: Add stolen reserved memory for MI25 SRIOV.
  drm/amdgpu: Merge get_reserved_allocation to get_vbios_allocations.
  drm/amdkfd: evict svm bo worker handle error
  drm/amdgpu/vcn: fix vcn ring test failure in igt reload test
  drm/amdgpu: only allow secure submission on rings which support that
  drm/amdgpu: fixed the warnings reported by kernel test robot
  drm/amd/display: 3.2.177
  drm/amd/display: [FW Promotion] Release 0.0.108.0
  drm/amd/display: Add save/restore PANEL_PWRSEQ_REF_DIV2
  drm/amd/display: Wait for hubp read line for Pollock
  ...

1 files changed, 43 insertions, 17 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 05117eda105b..c4283987bb1e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -31,6 +31,8 @@
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 
+#include "amdgpu_reset.h"
+
 #define EEPROM_I2C_MADDR_VEGA20         0x0
 #define EEPROM_I2C_MADDR_ARCTURUS       0x40000
 #define EEPROM_I2C_MADDR_ARCTURUS_D342  0x0
@@ -193,12 +195,12 @@ static int __write_table_header(struct amdgpu_ras_eeprom_control *control)
 	__encode_table_header_to_buf(&control->tbl_hdr, buf);
 
 	/* i2c may be unstable in gpu reset */
-	down_read(&adev->reset_sem);
-	res = amdgpu_eeprom_write(&adev->pm.smu_i2c,
+	down_read(&adev->reset_domain->sem);
+	res = amdgpu_eeprom_write(adev->pm.ras_eeprom_i2c_bus,
 				  control->i2c_address +
 				  control->ras_header_offset,
 				  buf, RAS_TABLE_HEADER_SIZE);
-	up_read(&adev->reset_sem);
+	up_read(&adev->reset_domain->sem);
 
 	if (res < 0) {
 		DRM_ERROR("Failed to write EEPROM table header:%d", res);
@@ -263,7 +265,9 @@ static int amdgpu_ras_eeprom_correct_header_tag(
  */
 int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control)
 {
+	struct amdgpu_device *adev = to_amdgpu_device(control);
 	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	u8 csum;
 	int res;
 
@@ -282,6 +286,12 @@ int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control)
 	control->ras_num_recs = 0;
 	control->ras_fri = 0;
 
+	amdgpu_dpm_send_hbm_bad_pages_num(adev, control->ras_num_recs);
+
+	control->bad_channel_bitmap = 0;
+	amdgpu_dpm_send_hbm_bad_channel_flag(adev, control->bad_channel_bitmap);
+	con->update_channel_flag = false;
+
 	amdgpu_ras_debugfs_set_ret_size(control);
 
 	mutex_unlock(&control->ras_tbl_mutex);
@@ -387,13 +397,13 @@ static int __amdgpu_ras_eeprom_write(struct amdgpu_ras_eeprom_control *control,
 	int res;
 
 	/* i2c may be unstable in gpu reset */
-	down_read(&adev->reset_sem);
+	down_read(&adev->reset_domain->sem);
 	buf_size = num * RAS_TABLE_RECORD_SIZE;
-	res = amdgpu_eeprom_write(&adev->pm.smu_i2c,
+	res = amdgpu_eeprom_write(adev->pm.ras_eeprom_i2c_bus,
 				  control->i2c_address +
 				  RAS_INDEX_TO_OFFSET(control, fri),
 				  buf, buf_size);
-	up_read(&adev->reset_sem);
+	up_read(&adev->reset_domain->sem);
 	if (res < 0) {
 		DRM_ERROR("Writing %d EEPROM table records error:%d",
 			  num, res);
@@ -415,6 +425,7 @@ amdgpu_ras_eeprom_append_table(struct amdgpu_ras_eeprom_control *control,
 			       struct eeprom_table_record *record,
 			       const u32 num)
 {
+	struct amdgpu_ras *con = amdgpu_ras_get_context(to_amdgpu_device(control));
 	u32 a, b, i;
 	u8 *buf, *pp;
 	int res;
@@ -426,9 +437,16 @@ amdgpu_ras_eeprom_append_table(struct amdgpu_ras_eeprom_control *control,
 	/* Encode all of them in one go.
 	 */
 	pp = buf;
-	for (i = 0; i < num; i++, pp += RAS_TABLE_RECORD_SIZE)
+	for (i = 0; i < num; i++, pp += RAS_TABLE_RECORD_SIZE) {
 		__encode_table_record_to_buf(control, &record[i], pp);
 
+		/* update bad channel bitmap */
+		if (!(control->bad_channel_bitmap & (1 << record[i].mem_channel))) {
+			control->bad_channel_bitmap |= 1 << record[i].mem_channel;
+			con->update_channel_flag = true;
+		}
+	}
+
 	/* a, first record index to write into.
 	 * b, last record index to write into.
 	 * a = first index to read (fri) + number of records in the table,
@@ -547,12 +565,12 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control)
 		goto Out;
 	}
 
-	down_read(&adev->reset_sem);
-	res = amdgpu_eeprom_read(&adev->pm.smu_i2c,
+	down_read(&adev->reset_domain->sem);
+	res = amdgpu_eeprom_read(adev->pm.ras_eeprom_i2c_bus,
 				 control->i2c_address +
 				 control->ras_record_offset,
 				 buf, buf_size);
-	up_read(&adev->reset_sem);
+	up_read(&adev->reset_domain->sem);
 	if (res < 0) {
 		DRM_ERROR("EEPROM failed reading records:%d\n",
 			  res);
@@ -642,13 +660,13 @@ static int __amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control,
 	int res;
 
 	/* i2c may be unstable in gpu reset */
-	down_read(&adev->reset_sem);
+	down_read(&adev->reset_domain->sem);
 	buf_size = num * RAS_TABLE_RECORD_SIZE;
-	res = amdgpu_eeprom_read(&adev->pm.smu_i2c,
+	res = amdgpu_eeprom_read(adev->pm.ras_eeprom_i2c_bus,
 				 control->i2c_address +
 				 RAS_INDEX_TO_OFFSET(control, fri),
 				 buf, buf_size);
-	up_read(&adev->reset_sem);
+	up_read(&adev->reset_domain->sem);
 	if (res < 0) {
 		DRM_ERROR("Reading %d EEPROM table records error:%d",
 			  num, res);
@@ -681,6 +699,7 @@ int amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control,
 			   const u32 num)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	int i, res;
 	u8 *buf, *pp;
 	u32 g0, g1;
@@ -748,8 +767,15 @@ int amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control,
 	/* Read up everything? Then transform.
 	 */
 	pp = buf;
-	for (i = 0; i < num; i++, pp += RAS_TABLE_RECORD_SIZE)
+	for (i = 0; i < num; i++, pp += RAS_TABLE_RECORD_SIZE) {
 		__decode_table_record_from_buf(control, &record[i], pp);
+
+		/* update bad channel bitmap */
+		if (!(control->bad_channel_bitmap & (1 << record[i].mem_channel))) {
+			control->bad_channel_bitmap |= 1 << record[i].mem_channel;
+			con->update_channel_flag = true;
+		}
+	}
 Out:
 	kfree(buf);
 	mutex_unlock(&control->ras_tbl_mutex);
@@ -1009,7 +1035,7 @@ static int __verify_ras_table_checksum(struct amdgpu_ras_eeprom_control *control
 		return -ENOMEM;
 	}
 
-	res = amdgpu_eeprom_read(&adev->pm.smu_i2c,
+	res = amdgpu_eeprom_read(adev->pm.ras_eeprom_i2c_bus,
 				 control->i2c_address +
 				 control->ras_header_offset,
 				 buf, buf_size);
@@ -1045,7 +1071,7 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
 		return 0;
 
 	/* Verify i2c adapter is initialized */
-	if (!adev->pm.smu_i2c.algo)
+	if (!adev->pm.ras_eeprom_i2c_bus || !adev->pm.ras_eeprom_i2c_bus->algo)
 		return -ENOENT;
 
 	if (!__get_eeprom_i2c_addr(adev, control))
@@ -1057,7 +1083,7 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
 	mutex_init(&control->ras_tbl_mutex);
 
 	/* Read the table header from EEPROM address */
-	res = amdgpu_eeprom_read(&adev->pm.smu_i2c,
+	res = amdgpu_eeprom_read(adev->pm.ras_eeprom_i2c_bus,
 				 control->i2c_address + control->ras_header_offset,
 				 buf, RAS_TABLE_HEADER_SIZE);
 	if (res < RAS_TABLE_HEADER_SIZE) {