Merge tag 'drm-next-2020-10-15' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Not a major amount of change, the i915 trees got split into display
  and gt trees to better facilitate higher level review, and there's a
  major refactoring of i915 GEM locking to use more core kernel concepts
  (like ww-mutexes). msm gets per-process pagetables, older AMD SI cards
  get DC support, nouveau got a bump in displayport support with common
  code extraction from i915.

  Outside of drm this contains a couple of patches for hexint
  moduleparams which you've acked, and a virtio common code tree that
  you should also get via it's regular path.

  New driver:
   - Cadence MHDP8546 DisplayPort bridge driver

  core:
   - cross-driver scatterlist cleanups
   - devm_drm conversions
   - remove drm_dev_init
   - devm_drm_dev_alloc conversion

  ttm:
   - lots of refactoring and cleanups

  bridges:
   - chained bridge support in more drivers

  panel:
   - misc new panels

  scheduler:
   - cleanup priority levels

  displayport:
   - refactor i915 code into helpers for nouveau

  i915:
   - split into display and GT trees
   - WW locking refactoring in GEM
   - execbuf2 extension mechanism
   - syncobj timeline support
   - GEN 12 HOBL display powersaving
   - Rocket Lake display additions
   - Disable FBC on Tigerlake
   - Tigerlake Type-C + DP improvements
   - Hotplug interrupt refactoring

  amdgpu:
   - Sienna Cichlid updates
   - Navy Flounder updates
   - DCE6 (SI) support for DC
   - Plane rotation enabled
   - TMZ state info ioctl
   - PCIe DPC recovery support
   - DC interrupt handling refactor
   - OLED panel fixes

  amdkfd:
   - add SMI events for thermal throttling
   - SMI interface events ioctl update
   - process eviction counters

  radeon:
   - move to dma_ for allocations
   - expose sclk via sysfs

  msm:
   - DSI support for sm8150/sm8250
   - per-process GPU pagetable support
   - Displayport support

  mediatek:
   - move HDMI phy driver to PHY
   - convert mtk-dpi to bridge API
   - disable mt2701 tmds

  tegra:
   - bridge support

  exynos:
   - misc cleanups

  vc4:
   - dual display cleanups

  ast:
   - cleanups

  gma500:
   - conversion to GPIOd API

  hisilicon:
   - misc reworks

  ingenic:
   - clock handling and format improvements

  mcde:
   - DSI support

  mgag200:
   - desktop g200 support

  mxsfb:
   - i.MX7 + i.MX8M
   - alpha plane support

  panfrost:
   - devfreq support
   - amlogic SoC support

  ps8640:
   - EDID from eDP retrieval

  tidss:
   - AM65xx YUV workaround

  virtio:
   - virtio-gpu exported resources

  rcar-du:
   - R8A7742, R8A774E1 and R8A77961 support
   - YUV planar format fixes
   - non-visible plane handling
   - VSP device reference count fix
   - Kconfig fix to avoid displaying disabled options in .config"

* tag 'drm-next-2020-10-15' of git://anongit.freedesktop.org/drm/drm: (1494 commits)
  drm/ingenic: Fix bad revert
  drm/amdgpu: Fix invalid number of character '{' in amdgpu_acpi_init
  drm/amdgpu: Remove warning for virtual_display
  drm/amdgpu: kfd_initialized can be static
  drm/amd/pm: setup APU dpm clock table in SMU HW initialization
  drm/amdgpu: prevent spurious warning
  drm/amdgpu/swsmu: fix ARC build errors
  drm/amd/display: Fix OPTC_DATA_FORMAT programming
  drm/amd/display: Don't allow pstate if no support in blank
  drm/panfrost: increase readl_relaxed_poll_timeout values
  MAINTAINERS: Update entry for st7703 driver after the rename
  Revert "gpu/drm: ingenic: Add option to mmap GEM buffers cached"
  drm/amd/display: HDMI remote sink need mode validation for Linux
  drm/amd/display: Change to correct unit on audio rate
  drm/amd/display: Avoid set zero in the requested clk
  drm/amdgpu: align frag_end to covered address space
  drm/amdgpu: fix NULL pointer dereference for Renoir
  drm/vmwgfx: fix regression in thp code due to ttm init refactor.
  drm/amdgpu/swsmu: add interrupt work handler for smu11 parts
  drm/amdgpu/swsmu: add interrupt work function
  ...

1 files changed, 135 insertions, 3 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index c0096097bbcf..0e64c39a2372 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -46,6 +46,9 @@
 #define EEPROM_TABLE_HDR_VAL 0x414d4452
 #define EEPROM_TABLE_VER 0x00010000
 
+/* Bad GPU tag ‘BADG’ */
+#define EEPROM_TABLE_HDR_BAD 0x42414447
+
 /* Assume 2 Mbit size */
 #define EEPROM_SIZE_BYTES 256000
 #define EEPROM_PAGE__SIZE_BYTES 256
@@ -56,6 +59,15 @@
 
 #define to_amdgpu_device(x) (container_of(x, struct amdgpu_ras, eeprom_control))->adev
 
+static bool __is_ras_eeprom_supported(struct amdgpu_device *adev)
+{
+	if ((adev->asic_type == CHIP_VEGA20) ||
+	    (adev->asic_type == CHIP_ARCTURUS))
+		return true;
+
+	return false;
+}
+
 static bool __get_eeprom_i2c_addr_arct(struct amdgpu_device *adev,
 				       uint16_t *i2c_addr)
 {
@@ -213,6 +225,24 @@ static bool __validate_tbl_checksum(struct amdgpu_ras_eeprom_control *control,
 	return true;
 }
 
+static int amdgpu_ras_eeprom_correct_header_tag(
+				struct amdgpu_ras_eeprom_control *control,
+				uint32_t header)
+{
+	unsigned char buff[EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE];
+	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
+	int ret = 0;
+
+	memset(buff, 0, EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE);
+
+	mutex_lock(&control->tbl_mutex);
+	hdr->header = header;
+	ret = __update_table_header(control, buff);
+	mutex_unlock(&control->tbl_mutex);
+
+	return ret;
+}
+
 int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control)
 {
 	unsigned char buff[EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE] = { 0 };
@@ -238,12 +268,14 @@ int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control)
 
 }
 
-int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
+int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
+			bool *exceed_err_limit)
 {
 	int ret = 0;
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 	unsigned char buff[EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE] = { 0 };
 	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 	struct i2c_msg msg = {
 			.addr	= 0,
 			.flags	= I2C_M_RD,
@@ -251,6 +283,11 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 			.buf	= buff,
 	};
 
+	*exceed_err_limit = false;
+
+	if (!__is_ras_eeprom_supported(adev))
+		return 0;
+
 	/* Verify i2c adapter is initialized */
 	if (!adev->pm.smu_i2c.algo)
 		return -ENOENT;
@@ -279,6 +316,18 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 		DRM_DEBUG_DRIVER("Found existing EEPROM table with %d records",
 				 control->num_recs);
 
+	} else if ((hdr->header == EEPROM_TABLE_HDR_BAD) &&
+			(amdgpu_bad_page_threshold != 0)) {
+		if (ras->bad_page_cnt_threshold > control->num_recs) {
+			dev_info(adev->dev, "Using one valid bigger bad page "
+				"threshold and correcting eeprom header tag.\n");
+			ret = amdgpu_ras_eeprom_correct_header_tag(control,
+							EEPROM_TABLE_HDR_VAL);
+		} else {
+			*exceed_err_limit = true;
+			dev_err(adev->dev, "Exceeding the bad_page_threshold parameter, "
+				"disabling the GPU.\n");
+		}
 	} else {
 		DRM_INFO("Creating new EEPROM table");
 
@@ -375,6 +424,49 @@ static uint32_t __correct_eeprom_dest_address(uint32_t curr_address)
 	return curr_address;
 }
 
+int amdgpu_ras_eeprom_check_err_threshold(
+				struct amdgpu_ras_eeprom_control *control,
+				bool *exceed_err_limit)
+{
+	struct amdgpu_device *adev = to_amdgpu_device(control);
+	unsigned char buff[EEPROM_ADDRESS_SIZE +
+			EEPROM_TABLE_HEADER_SIZE] = { 0 };
+	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
+	struct i2c_msg msg = {
+			.addr = control->i2c_address,
+			.flags = I2C_M_RD,
+			.len = EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE,
+			.buf = buff,
+	};
+	int ret;
+
+	*exceed_err_limit = false;
+
+	if (!__is_ras_eeprom_supported(adev))
+		return 0;
+
+	/* read EEPROM table header */
+	mutex_lock(&control->tbl_mutex);
+	ret = i2c_transfer(&adev->pm.smu_i2c, &msg, 1);
+	if (ret < 1) {
+		dev_err(adev->dev, "Failed to read EEPROM table header.\n");
+		goto err;
+	}
+
+	__decode_table_header_from_buff(hdr, &buff[2]);
+
+	if (hdr->header == EEPROM_TABLE_HDR_BAD) {
+		dev_warn(adev->dev, "This GPU is in BAD status.");
+		dev_warn(adev->dev, "Please retire it or setting one bigger "
+				"threshold value when reloading driver.\n");
+		*exceed_err_limit = true;
+	}
+
+err:
+	mutex_unlock(&control->tbl_mutex);
+	return 0;
+}
+
 int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 					    struct eeprom_table_record *records,
 					    bool write,
@@ -383,10 +475,12 @@ 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);
 
-	if (adev->asic_type != CHIP_VEGA20 && adev->asic_type != CHIP_ARCTURUS)
+	if (!__is_ras_eeprom_supported(adev))
 		return 0;
 
 	buffs = kcalloc(num, EEPROM_ADDRESS_SIZE + EEPROM_TABLE_RECORD_SIZE,
@@ -402,11 +496,30 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 		goto free_buff;
 	}
 
+	/*
+	 * If saved bad pages number exceeds the bad page threshold for
+	 * the whole VRAM, update table header to mark the BAD GPU tag
+	 * and schedule one ras recovery after eeprom write is done,
+	 * this can avoid the missing for latest records.
+	 *
+	 * This new header will be picked up and checked in the bootup
+	 * by ras recovery, which may break bootup process to notify
+	 * user this GPU is in bad state and to retire such GPU for
+	 * further check.
+	 */
+	if (write && (amdgpu_bad_page_threshold != 0) &&
+		((control->num_recs + num) >= ras->bad_page_cnt_threshold)) {
+		dev_warn(adev->dev,
+			"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 */
 	if (write && (control->next_addr + EEPROM_TABLE_RECORD_SIZE * num > EEPROM_SIZE_BYTES))
 		control->next_addr = EEPROM_RECORD_START;
 
-
 	/*
 	 * TODO Currently makes EEPROM writes for each record, this creates
 	 * internal fragmentation. Optimized the code to do full page write of
@@ -482,6 +595,20 @@ 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 */
@@ -499,6 +626,11 @@ free_buff:
 	return ret == num ? 0 : -EIO;
 }
 
+inline uint32_t amdgpu_ras_eeprom_get_record_max_length(void)
+{
+	return EEPROM_MAX_RECORD_NUM;
+}
+
 /* Used for testing if bugs encountered */
 #if 0
 void amdgpu_ras_eeprom_test(struct amdgpu_ras_eeprom_control *control)