Skip to contentSkip to conversation

GEM/GuC Suspend/Resume/Reset fixes and restructuring

PATCH Superseded Sagar Arun Kamble 2 participants 11 messages Sep 26, 2017

Subsystems (2)

v9 of 13 Superseded Latest is v13 →

lore
Share & tools
lore
#0 lore raw

v9 cover GEM/GuC Suspend/Resume/Reset fixes and restructuring

Fixed patch 1 based on review inputs from Michal Winiarski. Rebased all patches. Updated ordering of cc, s-o-b, r-b tags for all patches.

Sagar Arun Kamble (8):
drm/i915: Create GEM runtime resume helper and handle GEM
suspend/resume errors
drm/i915: Update GEM suspend/resume flows considering GuC and GEM
fences
drm/i915: Create uC runtime and system suspend/resume helpers drm/i915/guc: Introduce intel_guc_sanitize drm/i915/guc: Update GuC ggtt.invalidate/interrupts/communication
across RPM suspend/resume
drm/i915/guc: Update GuC suspend functionality in intel_uc_suspend drm/i915/guc: Disable GuC submission and suspend it prior to i915
reset
drm/i915/guc: Fix GuC cleanup in unload path

 drivers/gpu/drm/i915/i915_drv.c            |  41 ++++++------
 drivers/gpu/drm/i915/i915_drv.h            |   5 +-
 drivers/gpu/drm/i915/i915_gem.c            |  85 ++++++++++++++++++++++--
 drivers/gpu/drm/i915/i915_guc_submission.c |  22 +++---
 drivers/gpu/drm/i915/i915_suspend.c        |   2 -
 drivers/gpu/drm/i915/intel_uc.c            | 103 +++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/intel_uc.h            |  10 ++-
 7 files changed, 221 insertions(+), 47 deletions(-)
Signature · 6 lines
1.9.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#1 lore raw

PATCH v9 1/8 drm/i915: Create GEM runtime resume helper and handle GEM suspend/resume errors

Prepared helper i915_gem_runtime_resume to recreate gem setup. Returning status from i915_gem_runtime_suspend and i915_gem_resume. This will be placeholder for handling any errors from uC suspend/resume in upcoming patches. Restructured the suspend/resume routines w.r.t setup creation and rollback order.
This also fixes issue of ordering of i915_gem_runtime_resume with intel_runtime_pm_enable_interrupts.

v2: Fixed return from intel_runtime_resume. (Michał Winiarski)

Cc Chris Wilson <[email protected]>
Cc Imre Deak <[email protected]>
Cc Paulo Zanoni <[email protected]>
Cc Rodrigo Vivi <[email protected]>
Cc Michal Wajdeczko <[email protected]>
Cc Michał Winiarski <[email protected]>
---
 drivers/gpu/drm/i915/i915_drv.c | 34 ++++++++++++++++++++--------------
 drivers/gpu/drm/i915/i915_drv.h |  5 +++--
 drivers/gpu/drm/i915/i915_gem.c | 20 ++++++++++++++++++--
 3 files changed, 41 insertions(+), 18 deletions(-)
drivers/gpu/drm/i915/i915_drv.c +20 -14
index 7056bb2..a3bbf18 100644
@@ -1655,6 +1655,7 @@ static int i915_suspend_switcheroo(struct drm_device *dev, pm_message_t state)
 static int i915_drm_resume(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct pci_dev *pdev = dev_priv->drm.pdev;
 	int ret;
 
 	disable_rpm_wakeref_asserts(dev_priv);
@@ -1666,7 +1667,9 @@ static int i915_drm_resume(struct drm_device *dev)
 
 	intel_csr_ucode_resume(dev_priv);
 
-	i915_gem_resume(dev_priv);
+	ret = i915_gem_resume(dev_priv);
+	if (ret)
+		dev_err(&pdev->dev, "GEM resume failed\n");
 
 	i915_restore_state(dev_priv);
 	intel_pps_unlock_regs_wa(dev_priv);
@@ -2495,7 +2498,11 @@ static int intel_runtime_suspend(struct device *kdev)
 	 * We are safe here against re-faults, since the fault handler takes
 	 * an RPM reference.
 	 */
-	i915_gem_runtime_suspend(dev_priv);
+	ret = i915_gem_runtime_suspend(dev_priv);
+	if (ret) {
+		enable_rpm_wakeref_asserts(dev_priv);
+		return ret;
+	}
 
 	intel_guc_suspend(dev_priv);
 
@@ -2515,6 +2522,8 @@ static int intel_runtime_suspend(struct device *kdev)
 		DRM_ERROR("Runtime suspend failed, disabling it (%d)\n", ret);
 		intel_runtime_pm_enable_interrupts(dev_priv);
 
+		intel_guc_resume(dev_priv);
+		i915_gem_runtime_resume(dev_priv);
 		enable_rpm_wakeref_asserts(dev_priv);
 
 		return ret;
@@ -2567,7 +2576,7 @@ static int intel_runtime_resume(struct device *kdev)
 	struct pci_dev *pdev = to_pci_dev(kdev);
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	int ret = 0;
+	int err = 0, ret;
 
 	if (WARN_ON_ONCE(!HAS_RUNTIME_PM(dev_priv)))
 		return -ENODEV;
@@ -2593,16 +2602,9 @@ static int intel_runtime_resume(struct device *kdev)
 	} else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
 		hsw_disable_pc8(dev_priv);
 	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		ret = vlv_resume_prepare(dev_priv, true);
+		err = vlv_resume_prepare(dev_priv, true);
 	}
 
-	/*
-	 * No point of rolling back things in case of an error, as the best
-	 * we can do is to hope that things will still work (and disable RPM).
-	 */
-	i915_gem_init_swizzling(dev_priv);
-	i915_gem_restore_fences(dev_priv);
-
 	intel_runtime_pm_enable_interrupts(dev_priv);
 
 	/*
@@ -2615,14 +2617,18 @@ static int intel_runtime_resume(struct device *kdev)
 
 	intel_enable_ipc(dev_priv);
 
+	ret = i915_gem_runtime_resume(dev_priv);
+	if (!err)
+		err = ret;
+
 	enable_rpm_wakeref_asserts(dev_priv);
 
-	if (ret)
-		DRM_ERROR("Runtime resume failed, disabling it (%d)\n", ret);
+	if (err)
+		DRM_ERROR("Runtime resume failed, disabling it (%d)\n", err);
 	else
 		DRM_DEBUG_KMS("Device resumed\n");
 
-	return ret;
+	return err;
 }
 
 const struct dev_pm_ops i915_pm_ops = {
drivers/gpu/drm/i915/i915_drv.h +3 -2
index 61a4be9..69370c1 100644
@@ -3471,7 +3471,8 @@ struct i915_vma * __must_check
 int i915_gem_object_unbind(struct drm_i915_gem_object *obj);
 void i915_gem_release_mmap(struct drm_i915_gem_object *obj);
 
-void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv);
+int i915_gem_runtime_suspend(struct drm_i915_private *dev_priv);
+int i915_gem_runtime_resume(struct drm_i915_private *dev_priv);
 
 static inline int __sg_page_count(const struct scatterlist *sg)
 {
@@ -3674,7 +3675,7 @@ void i915_gem_reset_engine(struct intel_engine_cs *engine,
 int i915_gem_wait_for_idle(struct drm_i915_private *dev_priv,
 			   unsigned int flags);
 int __must_check i915_gem_suspend(struct drm_i915_private *dev_priv);
-void i915_gem_resume(struct drm_i915_private *dev_priv);
+int i915_gem_resume(struct drm_i915_private *dev_priv);
 int i915_gem_fault(struct vm_fault *vmf);
 int i915_gem_object_wait(struct drm_i915_gem_object *obj,
 			 unsigned int flags,
drivers/gpu/drm/i915/i915_gem.c +18 -2
index 73eeb6b..dbe181b 100644
@@ -2022,7 +2022,7 @@ int i915_gem_fault(struct vm_fault *vmf)
 	intel_runtime_pm_put(i915);
 }
 
-void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv)
+int i915_gem_runtime_suspend(struct drm_i915_private *dev_priv)
 {
 	struct drm_i915_gem_object *obj, *on;
 	int i;
@@ -2065,6 +2065,20 @@ void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv)
 		GEM_BUG_ON(!list_empty(&reg->vma->obj->userfault_link));
 		reg->dirty = true;
 	}
+
+	return 0;
+}
+
+int i915_gem_runtime_resume(struct drm_i915_private *dev_priv)
+{
+	/*
+	 * No point of rolling back things in case of an error, as the best
+	 * we can do is to hope that things will still work (and disable RPM).
+	 */
+	i915_gem_init_swizzling(dev_priv);
+	i915_gem_restore_fences(dev_priv);
+
+	return 0;
 }
 
 static int i915_gem_object_create_mmap_offset(struct drm_i915_gem_object *obj)
@@ -4587,7 +4601,7 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 	return ret;
 }
 
-void i915_gem_resume(struct drm_i915_private *dev_priv)
+int i915_gem_resume(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = &dev_priv->drm;
 
@@ -4603,6 +4617,8 @@ void i915_gem_resume(struct drm_i915_private *dev_priv)
 	dev_priv->gt.resume(dev_priv);
 
 	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
 }
 
 void i915_gem_init_swizzling(struct drm_i915_private *dev_priv)
Signature · 6 lines
1.9.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#2 lore raw

PATCH v9 2/8 drm/i915: Update GEM suspend/resume flows considering GuC and GEM fences

In reply to Sagar Arun Kamble

This patch moves GuC suspend/resume handlers to corresponding GEM handlers and orders them properly in the runtime and system suspend/resume flows. It also adds documentation for GEM suspend/resume handlers. i915_gem_restore_fences is GEM resumption task hence it is moved to i915_gem_resume from i915_restore_state.

Cc Chris Wilson <[email protected]>
Cc Imre Deak <[email protected]>
Cc Paulo Zanoni <[email protected]>
Cc Rodrigo Vivi <[email protected]>
Cc Michal Wajdeczko <[email protected]>
Cc Michał Winiarski <[email protected]>
---
 drivers/gpu/drm/i915/i915_drv.c     |  6 -----
 drivers/gpu/drm/i915/i915_gem.c     | 47 ++++++++++++++++++++++++++++++++++---
 drivers/gpu/drm/i915/i915_suspend.c |  2 --
 3 files changed, 44 insertions(+), 11 deletions(-)
drivers/gpu/drm/i915/i915_drv.c +0 -6
index a3bbf18..8d67b8c 100644
@@ -1698,8 +1698,6 @@ static int i915_drm_resume(struct drm_device *dev)
 	}
 	mutex_unlock(&dev->struct_mutex);
 
-	intel_guc_resume(dev_priv);
-
 	intel_modeset_init_hw(dev);
 
 	spin_lock_irq(&dev_priv->irq_lock);
@@ -2504,8 +2502,6 @@ static int intel_runtime_suspend(struct device *kdev)
 		return ret;
 	}
 
-	intel_guc_suspend(dev_priv);
-
 	intel_runtime_pm_disable_interrupts(dev_priv);
 
 	ret = 0;
@@ -2591,8 +2587,6 @@ static int intel_runtime_resume(struct device *kdev)
 	if (intel_uncore_unclaimed_mmio(dev_priv))
 		DRM_DEBUG_DRIVER("Unclaimed access during suspend, bios?\n");
 
-	intel_guc_resume(dev_priv);
-
 	if (IS_GEN9_LP(dev_priv)) {
 		bxt_disable_dc9(dev_priv);
 		bxt_display_core_init(dev_priv, true);
drivers/gpu/drm/i915/i915_gem.c +44 -3

106 lines not on this page · raw message

drivers/gpu/drm/i915/i915_suspend.c +0 -2
index 5c86925a..8f3aa4d 100644
@@ -108,8 +108,6 @@ int i915_restore_state(struct drm_i915_private *dev_priv)
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
 
-	i915_gem_restore_fences(dev_priv);
-
 	if (IS_GEN4(dev_priv))
 		pci_write_config_word(pdev, GCDGMBUS,
 				      dev_priv->regfile.saveGCDGMBUS);
Signature · 6 lines
1.9.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#3 lore raw

PATCH v9 3/8 drm/i915: Create uC runtime and system suspend/resume helpers

In reply to Sagar Arun Kamble

Prepared generic helpers intel_uc_suspend, intel_uc_resume, intel_uc_runtime_suspend, intel_uc_runtime_resume. These are called from respective GEM functions.

v2: Rebase w.r.t removal of GuC code restructuring.

v3: Calling intel_uc_resume from i915_gem_resume post resuming i915 gem setup. This is symmetrical with i915_gem_suspend. Removed error messages from i915 suspend/resume routines as uC suspend/resume routines will have those. (Michal Wajdeczko) Declare wedged on uc_suspend failure and uc_resume failure. (Michał Winiarski)
Added DRM_DEBUG message about skipping changes in intel_uc_resume. Keeping the uC suspend/resume function definitions close to other uC functions.

Cc Chris Wilson <[email protected]>
Cc Michal Wajdeczko <[email protected]>
Cc Michał Winiarski <[email protected]>
---
 drivers/gpu/drm/i915/i915_drv.c |  1 -
 drivers/gpu/drm/i915/i915_gem.c | 32 +++++++++++++++++++++++---------
 drivers/gpu/drm/i915/intel_uc.c | 22 ++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_uc.h |  4 ++++
 4 files changed, 49 insertions(+), 10 deletions(-)
drivers/gpu/drm/i915/i915_drv.c +0 -1
index 8d67b8c..8bfebe3 100644
@@ -2518,7 +2518,6 @@ static int intel_runtime_suspend(struct device *kdev)
 		DRM_ERROR("Runtime suspend failed, disabling it (%d)\n", ret);
 		intel_runtime_pm_enable_interrupts(dev_priv);
 
-		intel_guc_resume(dev_priv);
 		i915_gem_runtime_resume(dev_priv);
 		enable_rpm_wakeref_asserts(dev_priv);
 
drivers/gpu/drm/i915/i915_gem.c +23 -9
index 5dcd8c0..8e6e2bd 100644
@@ -2034,9 +2034,11 @@ int i915_gem_fault(struct vm_fault *vmf)
 int i915_gem_runtime_suspend(struct drm_i915_private *dev_priv)
 {
 	struct drm_i915_gem_object *obj, *on;
-	int i;
+	int i, ret;
 
-	intel_guc_suspend(dev_priv);
+	ret = intel_uc_runtime_suspend(dev_priv);
+	if (ret)
+		return ret;
 
 	/*
 	 * Only called during RPM suspend. All users of the userfault_list
@@ -2077,7 +2079,7 @@ int i915_gem_runtime_suspend(struct drm_i915_private *dev_priv)
 		reg->dirty = true;
 	}
 
-	return 0;
+	return ret;
 }
 
 /**
@@ -2097,9 +2099,7 @@ int i915_gem_runtime_resume(struct drm_i915_private *dev_priv)
 	i915_gem_init_swizzling(dev_priv);
 	i915_gem_restore_fences(dev_priv);
 
-	intel_guc_resume(dev_priv);
-
-	return 0;
+	return intel_uc_runtime_resume(dev_priv);
 }
 
 static int i915_gem_object_create_mmap_offset(struct drm_i915_gem_object *obj)
@@ -4600,7 +4600,9 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 	if (WARN_ON(!intel_engines_are_idle(dev_priv)))
 		i915_gem_set_wedged(dev_priv); /* no hope, discard everything */
 
-	intel_guc_suspend(dev_priv);
+	ret = intel_uc_suspend(dev_priv);
+	if (ret)
+		i915_gem_set_wedged(dev_priv); /* no hope, discard everything */
 
 	/*
 	 * Neither the BIOS, ourselves or any other kernel
@@ -4644,6 +4646,7 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 int i915_gem_resume(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = &dev_priv->drm;
+	int ret;
 
 	WARN_ON(dev_priv->gt.awake);
 
@@ -4656,10 +4659,21 @@ int i915_gem_resume(struct drm_i915_private *dev_priv)
 	 * it and start again.
 	 */
 	dev_priv->gt.resume(dev_priv);
-	intel_guc_resume(dev_priv);
+
+	/*
+	 * NB: Full gem reinitialization is being done in i915_drm_resume
+	 * after gem_resume, so currently intel_uc_resume will be of no use.
+	 * Hence, intel_uc_resume is nop currently. If full reinitialization is
+	 * removed, will need to put functionality to resume from sleep in
+	 * intel_uc_resume.
+	 */
+	ret = intel_uc_resume(dev_priv);
+	if (ret)
+		i915_gem_set_wedged(dev_priv);
+
 	mutex_unlock(&dev->struct_mutex);
 
-	return 0;
+	return ret;
 }
 
 void i915_gem_init_swizzling(struct drm_i915_private *dev_priv)
drivers/gpu/drm/i915/intel_uc.c +22 -0
index 2774778..b9376e4 100644
@@ -481,6 +481,28 @@ void intel_uc_fini_hw(struct drm_i915_private *dev_priv)
 	i915_ggtt_disable_guc(dev_priv);
 }
 
+int intel_uc_runtime_suspend(struct drm_i915_private *dev_priv)
+{
+	return intel_guc_suspend(dev_priv);
+}
+
+int intel_uc_runtime_resume(struct drm_i915_private *dev_priv)
+{
+	return intel_guc_resume(dev_priv);
+}
+
+int intel_uc_suspend(struct drm_i915_private *dev_priv)
+{
+	return intel_guc_suspend(dev_priv);
+}
+
+int intel_uc_resume(struct drm_i915_private *dev_priv)
+{
+	DRM_DEBUG_DRIVER("uC resume does nothing as full reinit is done\n");
+
+	return 0;
+}
+
 int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len)
 {
 	WARN(1, "Unexpected send: action=%#x\n", *action);
drivers/gpu/drm/i915/intel_uc.h +4 -0
index 6966349..0a79e17 100644
@@ -208,6 +208,10 @@ struct intel_huc {
 void intel_uc_fini_fw(struct drm_i915_private *dev_priv);
 int intel_uc_init_hw(struct drm_i915_private *dev_priv);
 void intel_uc_fini_hw(struct drm_i915_private *dev_priv);
+int intel_uc_runtime_suspend(struct drm_i915_private *dev_priv);
+int intel_uc_runtime_resume(struct drm_i915_private *dev_priv);
+int intel_uc_suspend(struct drm_i915_private *dev_priv);
+int intel_uc_resume(struct drm_i915_private *dev_priv);
 int intel_guc_sample_forcewake(struct intel_guc *guc);
 int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len);
 int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len);
Signature · 6 lines
1.9.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#4 lore raw

PATCH v9 4/8 drm/i915/guc: Introduce intel_guc_sanitize

In reply to Sagar Arun Kamble

Currently GPU is reset at the end of suspend via i915_gem_sanitize. On resume, GuC will not be loaded until intel_uc_init_hw happens during GEM resume flow but action to exit sleep wll be send to GuC considering the FW load status. To make sure we don't invoke that action update GuC FW load status through new helper intel_guc_sanitize. Conditional check based on FW fetch status should take care of driver init flow.

v2: Rebase.

Cc Michal Wajdeczko <[email protected]>
Cc Michał Winiarski <[email protected]>
---
 drivers/gpu/drm/i915/i915_gem.c | 2 ++
 drivers/gpu/drm/i915/intel_uc.c | 8 ++++++++
 drivers/gpu/drm/i915/intel_uc.h | 1 +
 3 files changed, 11 insertions(+)
drivers/gpu/drm/i915/i915_gem.c +2 -0
index 8e6e2bd..0d9a107 100644
@@ -4528,6 +4528,8 @@ void i915_gem_sanitize(struct drm_i915_private *i915)
 		mutex_unlock(&i915->drm.struct_mutex);
 	}
 
+	intel_guc_sanitize(&i915->guc);
+
 	/*
 	 * If we inherit context state from the BIOS or earlier occupants
 	 * of the GPU, the GPU may be in an inconsistent state when we
drivers/gpu/drm/i915/intel_uc.c +8 -0
index b9376e4..29d43f8 100644
@@ -581,3 +581,11 @@ int intel_guc_sample_forcewake(struct intel_guc *guc)
 
 	return intel_guc_send(guc, action, ARRAY_SIZE(action));
 }
+
+void intel_guc_sanitize(struct intel_guc *guc)
+{
+	if (guc->fw.fetch_status == INTEL_UC_FIRMWARE_SUCCESS)
+		guc->fw.load_status = INTEL_UC_FIRMWARE_PENDING;
+	else
+		guc->fw.load_status = INTEL_UC_FIRMWARE_NONE;
+}
drivers/gpu/drm/i915/intel_uc.h +1 -0
index 0a79e17..6163ff9 100644
@@ -213,6 +213,7 @@ struct intel_huc {
 int intel_uc_suspend(struct drm_i915_private *dev_priv);
 int intel_uc_resume(struct drm_i915_private *dev_priv);
 int intel_guc_sample_forcewake(struct intel_guc *guc);
+void intel_guc_sanitize(struct intel_guc *guc);
 int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len);
 int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len);
 int intel_guc_auth_huc(struct intel_guc *guc, u32 rsa_offset);
Signature · 6 lines
1.9.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#5 lore raw

PATCH v9 5/8 drm/i915/guc: Update GuC ggtt.invalidate/interrupts/communication across RPM suspend/resume

In reply to Sagar Arun Kamble

Apart from configuring interrupts, we need to update the ggtt invalidate interface and GuC communication on suspend/resume. This functionality can be reused for other suspend and reset paths.

v2: Rebase w.r.t removal of GuC code restructuring.

v3: Removed GuC specific helpers as tasks other than send H2G for sleep/resume are to be done from uc generic functions. (Michal Wajdeczko)

v4: Simplified/Unified the error messaging in uc_runtime_suspend/resume. (Michal Wajdeczko). Rebase w.r.t i915_modparams change. Added documentation to intel_uc_runtime_suspend/resume.

---
 drivers/gpu/drm/i915/i915_guc_submission.c |  5 ---
 drivers/gpu/drm/i915/intel_uc.c            | 60 +++++++++++++++++++++++++++++-
 2 files changed, 58 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/i915_guc_submission.c +0 -5
index 04f1281..d1d6c0d 100644
@@ -1226,8 +1226,6 @@ int intel_guc_suspend(struct drm_i915_private *dev_priv)
 	if (guc->fw.load_status != INTEL_UC_FIRMWARE_SUCCESS)
 		return 0;
 
-	gen9_disable_guc_interrupts(dev_priv);
-
 	ctx = dev_priv->kernel_context;
 
 	data[0] = INTEL_GUC_ACTION_ENTER_S_STATE;
@@ -1252,9 +1250,6 @@ int intel_guc_resume(struct drm_i915_private *dev_priv)
 	if (guc->fw.load_status != INTEL_UC_FIRMWARE_SUCCESS)
 		return 0;
 
-	if (i915_modparams.guc_log_level >= 0)
-		gen9_enable_guc_interrupts(dev_priv);
-
 	ctx = dev_priv->kernel_context;
 
 	data[0] = INTEL_GUC_ACTION_EXIT_S_STATE;
drivers/gpu/drm/i915/intel_uc.c +58 -2

72 lines not on this page · raw message

Signature · 6 lines
1.9.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#6 lore raw

PATCH v9 6/8 drm/i915/guc: Update GuC suspend functionality in intel_uc_suspend

In reply to Sagar Arun Kamble

With this patch we disable GuC submission in i915_drm_suspend path. This will destroy the client which will be setup back again. We also reuse the complete sanitization done via intel_uc_runtime_suspend in this path. Post i915_drm_resume, this state is recreated by intel_uc_init_hw hence we need not have similar reuse for intel_uc_resume. This also fixes issue where intel_uc_fini_hw was being called after GPU reset happening in i915_gem_suspend during i915_driver_unload.

v2: Rebase w.r.t removal of GuC code restructuring. Added struct_mutex protection for i915_guc_submission_disable.

v3: Rebase w.r.t updated GuC suspend function name.

v4: Added lockdep assert in i915_guc_submission_enable/disable. Refined intel_uc_suspend to remove unnecessary locals and simplify return. (Michal Winiarski)
Removed comment in guc_client_free about ignoring failure for destroy_doorbell. (Oscar)
Rebase w.r.t i915_modparams change.

---
 drivers/gpu/drm/i915/i915_guc_submission.c | 15 ++++++++++++---
 drivers/gpu/drm/i915/intel_uc.c            | 11 +++++++----
 2 files changed, 19 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/i915_guc_submission.c +12 -3
index d1d6c0d..0c56765 100644
@@ -885,9 +885,6 @@ static void guc_client_free(struct i915_guc_client *client)
 	 * Be sure to drop any locks
 	 */
 
-	/* FIXME: in many cases, by the time we get here the GuC has been
-	 * reset, so we cannot destroy the doorbell properly. Ignore the
-	 * error message for now */
 	destroy_doorbell(client);
 	guc_stage_desc_fini(client->guc, client);
 	i915_gem_object_unpin_map(client->vma->obj);
@@ -1154,6 +1151,12 @@ int i915_guc_submission_enable(struct drm_i915_private *dev_priv)
 		     sizeof(struct guc_wq_item) *
 		     I915_NUM_ENGINES > GUC_WQ_SIZE);
 
+	/*
+	 * Assert that drm.struct_mutex is held.
+	 * Needed for GuC client vma binding.
+	 */
+	lockdep_assert_held(&dev_priv->drm.struct_mutex);
+
 	if (!client) {
 		client = guc_client_alloc(dev_priv,
 					  INTEL_INFO(dev_priv)->ring_mask,
@@ -1204,6 +1207,12 @@ void i915_guc_submission_disable(struct drm_i915_private *dev_priv)
 {
 	struct intel_guc *guc = &dev_priv->guc;
 
+	/*
+	 * Assert that drm.struct_mutex is held.
+	 * Needed for GuC client vma unbinding.
+	 */
+	lockdep_assert_held(&dev_priv->drm.struct_mutex);
+
 	guc_interrupts_release(dev_priv);
 
 	/* Revert back to manual ELSP submission */
drivers/gpu/drm/i915/intel_uc.c +7 -4
index 7c34bc6..d710f0d 100644
@@ -468,9 +468,6 @@ void intel_uc_fini_hw(struct drm_i915_private *dev_priv)
 	if (!i915_modparams.enable_guc_loading)
 		return;
 
-	if (i915_modparams.enable_guc_submission)
-		i915_guc_submission_disable(dev_priv);
-
 	guc_disable_communication(&dev_priv->guc);
 
 	if (i915_modparams.enable_guc_submission) {
@@ -549,7 +546,13 @@ int intel_uc_runtime_resume(struct drm_i915_private *dev_priv)
 
 int intel_uc_suspend(struct drm_i915_private *dev_priv)
 {
-	return intel_guc_suspend(dev_priv);
+	if (i915_modparams.enable_guc_submission) {
+		mutex_lock(&dev_priv->drm.struct_mutex);
+		i915_guc_submission_disable(dev_priv);
+		mutex_unlock(&dev_priv->drm.struct_mutex);
+	}
+
+	return intel_uc_runtime_suspend(dev_priv);
 }
 
 int intel_uc_resume(struct drm_i915_private *dev_priv)
Signature · 6 lines
1.9.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#7 lore raw

PATCH v9 7/8 drm/i915/guc: Disable GuC submission and suspend it prior to i915 reset

In reply to Sagar Arun Kamble

Before i915 reset, we need to disable GuC submission and suspend GuC operations as it is recreated during intel_uc_init_hw. We can't reuse the intel_uc_suspend functionality as reset path already holds struct_mutex.

v2: Rebase w.r.t removal of GuC code restructuring. Updated reset_prepare function as struct_mutex is not needed.

v3: Fixed typo in commit message. Made return from intel_uc_reset_prepare simpler. (Michal)
Rebase w.r.t i915_modparams change.

---
 drivers/gpu/drm/i915/i915_gem.c | 2 ++
 drivers/gpu/drm/i915/intel_uc.c | 8 ++++++++
 drivers/gpu/drm/i915/intel_uc.h | 1 +
 3 files changed, 11 insertions(+)
drivers/gpu/drm/i915/i915_gem.c +2 -0
index 0d9a107..64b278c 100644
@@ -2882,6 +2882,8 @@ int i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
 
 	i915_gem_revoke_fences(dev_priv);
 
+	intel_uc_reset_prepare(dev_priv);
+
 	return err;
 }
 
drivers/gpu/drm/i915/intel_uc.c +8 -0
index d710f0d..aec3f6b 100644
@@ -562,6 +562,14 @@ int intel_uc_resume(struct drm_i915_private *dev_priv)
 	return 0;
 }
 
+int intel_uc_reset_prepare(struct drm_i915_private *dev_priv)
+{
+	if (i915_modparams.enable_guc_submission)
+		i915_guc_submission_disable(dev_priv);
+
+	return intel_uc_runtime_suspend(dev_priv);
+}
+
 int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len)
 {
 	WARN(1, "Unexpected send: action=%#x\n", *action);
drivers/gpu/drm/i915/intel_uc.h +1 -0
index 6163ff9..9b12f3c 100644
@@ -212,6 +212,7 @@ struct intel_huc {
 int intel_uc_runtime_resume(struct drm_i915_private *dev_priv);
 int intel_uc_suspend(struct drm_i915_private *dev_priv);
 int intel_uc_resume(struct drm_i915_private *dev_priv);
+int intel_uc_reset_prepare(struct drm_i915_private *dev_priv);
 int intel_guc_sample_forcewake(struct intel_guc *guc);
 void intel_guc_sanitize(struct intel_guc *guc);
 int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len);
Signature · 6 lines
1.9.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#8 lore raw

PATCH v9 8/8 drm/i915/guc: Fix GuC cleanup in unload path

In reply to Sagar Arun Kamble

We ensure that GuC is completely suspended and client is destroyed in i915_gem_suspend during i915_driver_unload. So now intel_uc_fini_hw should just take care of cleanup,
hence s/intel_uc_fini_hw/intel_uc_cleanup. Correspondingly
we also updated as s/i915_guc_submission_fini/i915_guc_submission_cleanup Other functionality to disable communication, disable interrupts and update of ggtt.invalidate is taken care by intel_uc_suspend.

v2: Rebase w.r.t removal of GuC code restructuring.

v3: Removed intel_guc_cleanup. (Michal Wajdeczko)

v4: guc_free_load_err_log() needs to be called without checking i915.enable_guc_loading as this param is cleared on GuC load failure. (Michal Wajdeczko)

---
 drivers/gpu/drm/i915/i915_drv.c            |  2 +-
 drivers/gpu/drm/i915/i915_guc_submission.c |  2 +-
 drivers/gpu/drm/i915/intel_uc.c            | 14 ++++----------
 drivers/gpu/drm/i915/intel_uc.h            |  4 ++--
 4 files changed, 8 insertions(+), 14 deletions(-)
drivers/gpu/drm/i915/i915_drv.c +1 -1
index 8bfebe3..4c0a5b5 100644
@@ -603,7 +603,7 @@ static void i915_gem_fini(struct drm_i915_private *dev_priv)
 	i915_gem_drain_workqueue(dev_priv);
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	intel_uc_fini_hw(dev_priv);
+	intel_uc_cleanup(dev_priv);
 	i915_gem_cleanup_engines(dev_priv);
 	i915_gem_contexts_fini(dev_priv);
 	i915_gem_cleanup_userptr(dev_priv);
drivers/gpu/drm/i915/i915_guc_submission.c +1 -1
index 0c56765..176cf55 100644
@@ -1053,7 +1053,7 @@ int i915_guc_submission_init(struct drm_i915_private *dev_priv)
 	return ret;
 }
 
-void i915_guc_submission_fini(struct drm_i915_private *dev_priv)
+void i915_guc_submission_cleanup(struct drm_i915_private *dev_priv)
 {
 	struct intel_guc *guc = &dev_priv->guc;
 
drivers/gpu/drm/i915/intel_uc.c +4 -10
index aec3f6b..b8e1f97 100644
@@ -439,7 +439,7 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 	guc_capture_load_err_log(guc);
 err_submission:
 	if (i915_modparams.enable_guc_submission)
-		i915_guc_submission_fini(dev_priv);
+		i915_guc_submission_cleanup(dev_priv);
 err_guc:
 	i915_ggtt_disable_guc(dev_priv);
 
@@ -461,21 +461,15 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 	return ret;
 }
 
-void intel_uc_fini_hw(struct drm_i915_private *dev_priv)
+void intel_uc_cleanup(struct drm_i915_private *dev_priv)
 {
 	guc_free_load_err_log(&dev_priv->guc);
 
 	if (!i915_modparams.enable_guc_loading)
 		return;
 
-	guc_disable_communication(&dev_priv->guc);
-
-	if (i915_modparams.enable_guc_submission) {
-		gen9_disable_guc_interrupts(dev_priv);
-		i915_guc_submission_fini(dev_priv);
-	}
-
-	i915_ggtt_disable_guc(dev_priv);
+	if (i915_modparams.enable_guc_submission)
+		i915_guc_submission_cleanup(dev_priv);
 }
 
 /**
drivers/gpu/drm/i915/intel_uc.h +2 -2
index 9b12f3c..936d947 100644
@@ -207,7 +207,7 @@ struct intel_huc {
 void intel_uc_init_fw(struct drm_i915_private *dev_priv);
 void intel_uc_fini_fw(struct drm_i915_private *dev_priv);
 int intel_uc_init_hw(struct drm_i915_private *dev_priv);
-void intel_uc_fini_hw(struct drm_i915_private *dev_priv);
+void intel_uc_cleanup(struct drm_i915_private *dev_priv);
 int intel_uc_runtime_suspend(struct drm_i915_private *dev_priv);
 int intel_uc_runtime_resume(struct drm_i915_private *dev_priv);
 int intel_uc_suspend(struct drm_i915_private *dev_priv);
@@ -240,7 +240,7 @@ static inline void intel_guc_notify(struct intel_guc *guc)
 int i915_guc_submission_init(struct drm_i915_private *dev_priv);
 int i915_guc_submission_enable(struct drm_i915_private *dev_priv);
 void i915_guc_submission_disable(struct drm_i915_private *dev_priv);
-void i915_guc_submission_fini(struct drm_i915_private *dev_priv);
+void i915_guc_submission_cleanup(struct drm_i915_private *dev_priv);
 struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size);
 
 /* intel_guc_log.c */
Signature · 6 lines
1.9.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#9 lore raw

✓ Fi.CI.BAT: success for GEM/GuC Suspend/Resume/Reset fixes and restructuring (rev2)

In reply to Sagar Arun Kamble
== Series Details ==

== Series Details ==

Series: GEM/GuC Suspend/Resume/Reset fixes and restructuring (rev2)
URL : https://patchwork.freedesktop.org/series/30802/
State : success

== Summary ==

Series 30802v2 GEM/GuC Suspend/Resume/Reset fixes and restructuring
https://patchwork.freedesktop.org/api/1.0/series/30802/revisions/2/mbox/

Test drv_module_reload:

        Subgroup basic-no-display:
                dmesg-warn -> PASS       (fi-glk-1) fdo#102777

fdo#102777 https://bugs.freedesktop.org/show_bug.cgi?id=102777

fi-bdw-5557u     total:289  pass:268  dwarn:0   dfail:0   fail:0   skip:21  time:442s
fi-bdw-gvtdvm    total:289  pass:265  dwarn:0   dfail:0   fail:0   skip:24  time:475s
fi-blb-e6850     total:289  pass:224  dwarn:1   dfail:0   fail:0   skip:64  time:422s
fi-bsw-n3050     total:289  pass:243  dwarn:0   dfail:0   fail:0   skip:46  time:518s
fi-bwr-2160      total:289  pass:184  dwarn:0   dfail:0   fail:0   skip:105 time:277s
fi-bxt-j4205     total:289  pass:260  dwarn:0   dfail:0   fail:0   skip:29  time:504s
fi-byt-j1900     total:289  pass:254  dwarn:1   dfail:0   fail:0   skip:34  time:491s
fi-byt-n2820     total:289  pass:250  dwarn:1   dfail:0   fail:0   skip:38  time:488s
fi-cfl-s         total:289  pass:223  dwarn:34  dfail:0   fail:0   skip:32  time:540s
fi-cnl-y         total:289  pass:256  dwarn:0   dfail:0   fail:6   skip:27  time:637s
fi-elk-e7500     total:289  pass:230  dwarn:0   dfail:0   fail:0   skip:59  time:411s
fi-glk-1         total:289  pass:260  dwarn:0   dfail:0   fail:0   skip:29  time:580s
fi-hsw-4770      total:289  pass:263  dwarn:0   dfail:0   fail:0   skip:26  time:425s
fi-hsw-4770r     total:289  pass:263  dwarn:0   dfail:0   fail:0   skip:26  time:407s
fi-ilk-650       total:289  pass:229  dwarn:0   dfail:0   fail:0   skip:60  time:436s
fi-ivb-3520m     total:289  pass:261  dwarn:0   dfail:0   fail:0   skip:28  time:490s
fi-ivb-3770      total:289  pass:261  dwarn:0   dfail:0   fail:0   skip:28  time:468s
fi-kbl-7500u     total:289  pass:264  dwarn:1   dfail:0   fail:0   skip:24  time:468s
fi-kbl-7560u     total:289  pass:270  dwarn:0   dfail:0   fail:0   skip:19  time:571s
fi-kbl-r         total:289  pass:262  dwarn:0   dfail:0   fail:0   skip:27  time:591s
fi-pnv-d510      total:289  pass:223  dwarn:1   dfail:0   fail:0   skip:65  time:548s
fi-skl-6260u     total:289  pass:269  dwarn:0   dfail:0   fail:0   skip:20  time:451s
fi-skl-6700k     total:289  pass:265  dwarn:0   dfail:0   fail:0   skip:24  time:747s
fi-skl-6770hq    total:289  pass:269  dwarn:0   dfail:0   fail:0   skip:20  time:485s
fi-skl-gvtdvm    total:289  pass:266  dwarn:0   dfail:0   fail:0   skip:23  time:471s
fi-snb-2520m     total:289  pass:251  dwarn:0   dfail:0   fail:0   skip:38  time:562s
fi-snb-2600      total:289  pass:250  dwarn:0   dfail:0   fail:0   skip:39  time:416s

bf490952b4a476211cb01f4f2fe3e44007983b8f drm-tip: 2017y-09m-26d-14h-00m-42s UTC integration manifest 51cce7cb1c70 drm/i915/guc: Fix GuC cleanup in unload path
9809effa85d1 drm/i915/guc: Disable GuC submission and suspend it prior to i915 reset 5fc1018c35e6 drm/i915/guc: Update GuC suspend functionality in intel_uc_suspend 4134124ca0ce drm/i915/guc: Update GuC ggtt.invalidate/interrupts/communication across RPM suspend/resume 0606b7832893 drm/i915/guc: Introduce intel_guc_sanitize
d00805fe6bc9 drm/i915: Create uC runtime and system suspend/resume helpers
a005dc836c4b drm/i915: Update GEM suspend/resume flows considering GuC and GEM fences 80712fec4a3e drm/i915: Create GEM runtime resume helper and handle GEM suspend/resume errors

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_5818/
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#10 lore raw

✓ Fi.CI.IGT: success for GEM/GuC Suspend/Resume/Reset fixes and restructuring (rev2)

In reply to Sagar Arun Kamble
== Series Details ==

== Series Details ==

Series: GEM/GuC Suspend/Resume/Reset fixes and restructuring (rev2)
URL : https://patchwork.freedesktop.org/series/30802/
State : success

== Summary ==

shard-hsw total:2429 pass:1328 dwarn:5 dfail:0 fail:13 skip:1083 time:9867s

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_5818/shards.html
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx