diff mbox

[v3,1/2] drm/i915/guc: Reset GuC and retry on firmware load failure

Message ID 1458844815-25925-1-git-send-email-david.s.gordon@intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

Dave Gordon March 24, 2016, 6:40 p.m. UTC
From: Arun Siluvery <arun.siluvery@linux.intel.com>

Due to timing issues in the HW some of the status bits required for GuC
authentication doesn't get set occassionally, when that happens, GuC cannot
be initialized and we will be left with a wedged GPU. The WA suggested is
to perform a soft reset of GuC and attempt to reload the fw again for few
times before giving up.

As the failure is dependent on timing, tests performed by triggering manual
full gpu reset (i915_wedged) showed that we could sometimes hit this after
several thousand iterations but sometimes tests ran even longer without any
issues. Reset and reload mechanism proved helpful when we indeed hit fw
load failure so it is better to include this to improve driver stability.

This change implements the following WA,

WaEnableuKernelHeaderValidFix:skl,bxt
WaEnableGuCBootHashCheckNotSet:skl,bxt

Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com>
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Reviewed-by: Alex Dai <yu.dai@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h         |  1 +
 drivers/gpu/drm/i915/i915_guc_reg.h     |  1 +
 drivers/gpu/drm/i915/i915_reg.h         |  1 +
 drivers/gpu/drm/i915/intel_guc_loader.c | 49 +++++++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/intel_uncore.c     | 19 +++++++++++++
 5 files changed, 69 insertions(+), 2 deletions(-)

Comments

Dave Gordon March 24, 2016, 6:44 p.m. UTC | #1
BTW, this two-item patchset was just a repost to get CI to pick it up, 
without getting confused by it previously being embedded in a longer set

.Dave.
Dave Gordon March 29, 2016, 12:35 p.m. UTC | #2
On 25/03/16 08:31, Patchwork wrote:
> == Series Details ==
>
> Series: series starting with [v3,1/2] drm/i915/guc: Reset GuC and retry on firmware load failure
> URL   : https://patchwork.freedesktop.org/series/4876/
> State : warning
>
> == Summary ==
>
> Series 4876v1 Series without cover letter
> http://patchwork.freedesktop.org/api/1.0/series/4876/revisions/1/mbox/
>
> Test kms_pipe_crc_basic:
>          Subgroup suspend-read-crc-pipe-c:
>                  pass       -> DMESG-WARN (bsw-nuc-2)

Unrelated, https://bugs.freedesktop.org/show_bug.cgi?id=94350
lockdep splat due to stop_machine() in ggtt pte programming

> Test pm_rpm:
>          Subgroup basic-pci-d3-state:
>                  pass       -> DMESG-WARN (bsw-nuc-2)

Unrelated, https://bugs.freedesktop.org/show_bug.cgi?id=94164
Unclaimed access detected prior to suspending

>          Subgroup basic-rte:
>                  dmesg-warn -> PASS       (byt-nuc) UNSTABLE
>
> bdw-nuci7        total:192  pass:179  dwarn:0   dfail:0   fail:1   skip:12
> bdw-ultra        total:192  pass:170  dwarn:0   dfail:0   fail:1   skip:21
> bsw-nuc-2        total:192  pass:153  dwarn:2   dfail:0   fail:0   skip:37
> byt-nuc          total:192  pass:157  dwarn:0   dfail:0   fail:0   skip:35
> hsw-brixbox      total:192  pass:170  dwarn:0   dfail:0   fail:0   skip:22
> hsw-gt2          total:192  pass:175  dwarn:0   dfail:0   fail:0   skip:17
> ivb-t430s        total:192  pass:167  dwarn:0   dfail:0   fail:0   skip:25
> skl-i7k-2        total:192  pass:169  dwarn:0   dfail:0   fail:0   skip:23
> snb-dellxps      total:192  pass:158  dwarn:0   dfail:0   fail:0   skip:34
> snb-x220t        total:192  pass:158  dwarn:0   dfail:0   fail:1   skip:33
>
> Results at /archive/results/CI_IGT_test/Patchwork_1717/
>
> f5d413cccefa1f93d64c34f357151d42add63a84 drm-intel-nightly: 2016y-03m-24d-14h-34m-29s UTC integration manifest
> cff00fb37026cf1e75d9317e8570938e89197515 drm/i915/guc: always reset GuC before loading firmware
> 6c406232a0289a937e4478901e3edc57c8f9f01a drm/i915/guc: Reset GuC and retry on firmware load failure
>
diff mbox

Patch

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index b93ef70..d1404b9 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2736,6 +2736,7 @@  extern long i915_compat_ioctl(struct file *filp, unsigned int cmd,
 extern int intel_gpu_reset(struct drm_device *dev, u32 engine_mask);
 extern bool intel_has_gpu_reset(struct drm_device *dev);
 extern int i915_reset(struct drm_device *dev);
+extern int intel_guc_reset(struct drm_i915_private *dev_priv);
 extern void intel_engine_init_hangcheck(struct intel_engine_cs *engine);
 extern unsigned long i915_chipset_val(struct drm_i915_private *dev_priv);
 extern unsigned long i915_mch_val(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_guc_reg.h b/drivers/gpu/drm/i915/i915_guc_reg.h
index e4ba582..94ceee5 100644
--- a/drivers/gpu/drm/i915/i915_guc_reg.h
+++ b/drivers/gpu/drm/i915/i915_guc_reg.h
@@ -27,6 +27,7 @@ 
 /* Definitions of GuC H/W registers, bits, etc */
 
 #define GUC_STATUS			_MMIO(0xc000)
+#define   GS_MIA_IN_RESET		(1 << 0)
 #define   GS_BOOTROM_SHIFT		1
 #define   GS_BOOTROM_MASK		  (0x7F << GS_BOOTROM_SHIFT)
 #define   GS_BOOTROM_RSA_FAILED		  (0x50 << GS_BOOTROM_SHIFT)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index c839ce9..6e63090 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -165,6 +165,7 @@  static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define  GEN6_GRDOM_MEDIA		(1 << 2)
 #define  GEN6_GRDOM_BLT			(1 << 3)
 #define  GEN6_GRDOM_VECS		(1 << 4)
+#define  GEN9_GRDOM_GUC			(1 << 5)
 #define  GEN8_GRDOM_MEDIA2		(1 << 7)
 
 #define RING_PP_DIR_BASE(ring)		_MMIO((ring)->mmio_base+0x228)
diff --git a/drivers/gpu/drm/i915/intel_guc_loader.c b/drivers/gpu/drm/i915/intel_guc_loader.c
index b4976f9..d84c560 100644
--- a/drivers/gpu/drm/i915/intel_guc_loader.c
+++ b/drivers/gpu/drm/i915/intel_guc_loader.c
@@ -353,6 +353,24 @@  static int guc_ucode_xfer(struct drm_i915_private *dev_priv)
 	return ret;
 }
 
+static int i915_reset_guc(struct drm_i915_private *dev_priv)
+{
+	int ret;
+	u32 guc_status;
+
+	ret = intel_guc_reset(dev_priv);
+	if (ret) {
+		DRM_ERROR("GuC reset failed, ret = %d\n", ret);
+		return ret;
+	}
+
+	guc_status = I915_READ(GUC_STATUS);
+	WARN(!(guc_status & GS_MIA_IN_RESET),
+	     "GuC status: 0x%x, MIA core expected to be in reset\n", guc_status);
+
+	return ret;
+}
+
 /**
  * intel_guc_ucode_load() - load GuC uCode into the device
  * @dev:	drm device
@@ -417,9 +435,36 @@  int intel_guc_ucode_load(struct drm_device *dev)
 	if (err)
 		goto fail;
 
+	/*
+	 * WaEnableuKernelHeaderValidFix:skl,bxt
+	 * For BXT, this is only upto B0 but below WA is required for later
+	 * steppings also so this is extended as well.
+	 */
+	/* WaEnableGuCBootHashCheckNotSet:skl,bxt */
 	err = guc_ucode_xfer(dev_priv);
-	if (err)
-		goto fail;
+	if (err) {
+		int retries = 3;
+
+		DRM_ERROR("GuC fw load failed, err=%d, attempting reset and retry\n", err);
+
+		while (retries--) {
+			err = i915_reset_guc(dev_priv);
+			if (err)
+				break;
+
+			err = guc_ucode_xfer(dev_priv);
+			if (!err) {
+				DRM_DEBUG_DRIVER("GuC fw reload succeeded after reset\n");
+				break;
+			}
+			DRM_DEBUG_DRIVER("GuC fw reload retries left: %d\n", retries);
+		}
+
+		if (err) {
+			DRM_ERROR("GuC fw reload attempt failed, ret=%d\n", err);
+			goto fail;
+		}
+	}
 
 	guc_fw->guc_fw_load_status = GUC_FIRMWARE_SUCCESS;
 
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 512b7fa..d44e07e 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1673,6 +1673,25 @@  bool intel_has_gpu_reset(struct drm_device *dev)
 	return intel_get_gpu_reset(dev) != NULL;
 }
 
+int intel_guc_reset(struct drm_i915_private *dev_priv)
+{
+	int ret;
+	unsigned long irqflags;
+
+	if (!i915.enable_guc_submission)
+		return -EINVAL;
+
+	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+
+	ret = gen6_hw_domain_reset(dev_priv, GEN9_GRDOM_GUC);
+
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+
+	return ret;
+}
+
 bool intel_uncore_unclaimed_mmio(struct drm_i915_private *dev_priv)
 {
 	return check_for_unclaimed_mmio(dev_priv);