Add 3 patches from Hans to fix various GPU issues

This commit is contained in:
Josh Boyer 2016-07-14 09:46:51 -04:00
parent aa9a2cd7f6
commit 37cc0dbb68
4 changed files with 351 additions and 0 deletions

View File

@ -0,0 +1,43 @@
From 89b9366047f51fcef7f7e36f2b351a98326c8656 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 12 Jul 2016 22:40:01 +0200
Subject: [PATCH] Revert "ALSA: hda - remove controller dependency on i915
power well for SKL"
This reverts commit 03b135cebc47d75ea2dc346770374ab741966955.
---
sound/pci/hda/hda_intel.c | 4 +++-
sound/pci/hda/patch_hdmi.c | 2 +-
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index e320c44..290d60f 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -361,7 +361,9 @@ enum {
#define CONTROLLER_IN_GPU(pci) (((pci)->device == 0x0a0c) || \
((pci)->device == 0x0c0c) || \
((pci)->device == 0x0d0c) || \
- ((pci)->device == 0x160c))
+ ((pci)->device == 0x160c) || \
+ ((pci)->device == 0xa170) || \
+ ((pci)->device == 0x9d70))
#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170)
#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70)
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index d0d5ad8..9203da1 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -2379,7 +2379,7 @@ static int patch_i915_hsw_hdmi(struct hda_codec *codec)
/* For Haswell/Broadwell, the controller is also in the power well and
* can cover the codec power request, and so need not set this flag.
*/
- if (!is_haswell(codec) && !is_broadwell(codec))
+ if (!is_haswell(codec) && !is_broadwell(codec) && !is_skylake(codec))
codec->core.link_power_control = 1;
codec->patch_ops.set_power_state = haswell_set_power_state;
--
2.7.4

View File

@ -0,0 +1,70 @@
From patchwork Fri Jul 8 15:37:35 2016
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Subject: drm/amdgpu: Disable RPM helpers while reprobing connectors on resume
From: cpaul@redhat.com
X-Patchwork-Id: 97837
Message-Id: <1467992256-23832-1-git-send-email-cpaul@redhat.com>
To: amd-gfx@lists.freedesktop.org
Cc: Tom St Denis <tom.stdenis@amd.com>, Jammy Zhou <Jammy.Zhou@amd.com>,
open list <linux-kernel@vger.kernel.org>, stable@vger.kernel.org,
"open list:RADEON and AMDGPU DRM DRIVERS"
<dri-devel@lists.freedesktop.org>,
Alex Deucher <alexander.deucher@amd.com>, Lyude <cpaul@redhat.com>,
Flora Cui <Flora.Cui@amd.com>,
=?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>,
Monk Liu <Monk.Liu@amd.com>
Date: Fri, 8 Jul 2016 11:37:35 -0400
Just about all of amdgpu's connector probing functions try to acquire
runtime PM refs. If we try to do this in the context of
amdgpu_resume_kms by calling drm_helper_hpd_irq_event(), we end up
deadlocking the system.
Since we're guaranteed to be holding the spinlock for RPM in
amdgpu_resume_kms, and we already know the GPU is in working order, we
need to prevent the RPM helpers from trying to run during the initial
connector reprobe on resume.
There's a couple of solutions I've explored for fixing this, but this
one by far seems to be the simplest and most reliable (plus I'm pretty
sure that's what disable_depth is there for anyway).
Reproduction recipe:
- Get any laptop dual GPUs using PRIME
- Make sure runtime PM is enabled for amdgpu
- Boot the machine
- If the machine managed to boot without hanging, switch out of X to
another VT. This should definitely cause X to hang infinitely.
Cc: stable@vger.kernel.org
Signed-off-by: Lyude <cpaul@redhat.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6e92008..46c1fee 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1841,7 +1841,19 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon)
}
drm_kms_helper_poll_enable(dev);
+
+ /*
+ * Most of the connector probing functions try to acquire runtime pm
+ * refs to ensure that the GPU is powered on when connector polling is
+ * performed. Since we're calling this from a runtime PM callback,
+ * trying to acquire rpm refs will cause us to deadlock.
+ *
+ * Since we're guaranteed to be holding the rpm lock, it's safe to
+ * temporarily disable the rpm helpers so this doesn't deadlock us.
+ */
+ dev->dev->power.disable_depth++;
drm_helper_hpd_irq_event(dev);
+ dev->dev->power.disable_depth--;
if (fbcon) {
amdgpu_fbdev_set_suspend(adev, 0);

View File

@ -0,0 +1,230 @@
From 5fc9d375bac02e054fcaaf14a06bebc6c7118008 Mon Sep 17 00:00:00 2001
From: "cpaul@redhat.com" <cpaul@redhat.com>
Date: Tue, 12 Jul 2016 13:36:03 -0400
Subject: [PATCH] drm/i915/skl: Add support for the SAGV, fix underrun hangs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Since the watermark calculations for Skylake are still broken, we're apt
to hitting underruns very easily under multi-monitor configurations.
While it would be lovely if this was fixed, it's not. Another problem
that's been coming from this however, is the mysterious issue of
underruns causing full system hangs. An easy way to reproduce this with
a skylake system:
- Get a laptop with a skylake GPU, and hook up two external monitors to
it
- Move the cursor from the built-in LCD to one of the external displays
as quickly as you can
- You'll get a few pipe underruns, and eventually the entire system will
just freeze.
After doing a lot of investigation and reading through the bspec, I
found the existence of the SAGV, which is responsible for adjusting the
system agent voltage and clock frequencies depending on how much power
we need. According to the bspec:
"The display engine access to system memory is blocked during the
adjustment time. SAGV defaults to enabled. Software must use the
GT-driver pcode mailbox to disable SAGV when the display engine is not
able to tolerate the blocking time."
The rest of the bspec goes on to explain that software can simply leave
the SAGV enabled, and disable it when we use interlaced pipes/have more
then one pipe active.
Sure enough, with this patchset the system hangs resulting from pipe
underruns on Skylake have completely vanished on my T460s. Additionally,
the bspec mentions turning off the SAGV with more then one pipe enabled
as a workaround for display underruns. While this patch doesn't entirely
fix that, it looks like it does improve the situation a little bit so
it's likely this is going to be required to make watermarks on Skylake
fully functional.
Changes since v2:
- Really apply minor style nitpicks to patch this time
Changes since v1:
- Added comments about this probably being one of the requirements to
fixing Skylake's watermark issues
- Minor style nitpicks from Matt Roper
- Disable these functions on Broxton, since it doesn't have an SAGV
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Lyude <cpaul@redhat.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 2 +
drivers/gpu/drm/i915/i915_reg.h | 5 ++
drivers/gpu/drm/i915/intel_pm.c | 110 ++++++++++++++++++++++++++++++++++++++++
3 files changed, 117 insertions(+)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 608f8e44f353..274b57ac1a91 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1942,6 +1942,8 @@ struct drm_i915_private {
struct i915_suspend_saved_registers regfile;
struct vlv_s0ix_state vlv_s0ix_state;
+ bool skl_sagv_enabled;
+
struct {
/*
* Raw watermark latency values:
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index b407411e31ba..9472949e8442 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7094,6 +7094,11 @@ enum skl_disp_power_wells {
#define HSW_PCODE_DE_WRITE_FREQ_REQ 0x17
#define DISPLAY_IPS_CONTROL 0x19
#define HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL 0x1A
+#define GEN9_PCODE_SAGV_CONTROL 0x21
+#define GEN9_SAGV_DISABLE 0x0
+#define GEN9_SAGV_LOW_FREQ 0x1
+#define GEN9_SAGV_HIGH_FREQ 0x2
+#define GEN9_SAGV_DYNAMIC_FREQ 0x3
#define GEN6_PCODE_DATA _MMIO(0x138128)
#define GEN6_PCODE_FREQ_IA_RATIO_SHIFT 8
#define GEN6_PCODE_FREQ_RING_RATIO_SHIFT 16
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index f764d284e6a0..439a38b08760 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2847,6 +2847,109 @@ skl_wm_plane_id(const struct intel_plane *plane)
}
static void
+skl_sagv_get_hw_state(struct drm_i915_private *dev_priv)
+{
+ u32 temp;
+ int ret;
+
+ if (IS_BROXTON(dev_priv))
+ return;
+
+ mutex_lock(&dev_priv->rps.hw_lock);
+ ret = sandybridge_pcode_read(dev_priv, GEN9_PCODE_SAGV_CONTROL, &temp);
+ mutex_unlock(&dev_priv->rps.hw_lock);
+
+ if (!ret) {
+ dev_priv->skl_sagv_enabled = !!(temp & GEN9_SAGV_DYNAMIC_FREQ);
+ } else {
+ /*
+ * If for some reason we can't access the SAGV state, follow
+ * the bspec and assume it's enabled
+ */
+ DRM_ERROR("Failed to get SAGV state, assuming enabled\n");
+ dev_priv->skl_sagv_enabled = true;
+ }
+}
+
+/*
+ * SAGV dynamically adjusts the system agent voltage and clock frequencies
+ * depending on power and performance requirements. The display engine access
+ * to system memory is blocked during the adjustment time. Having this enabled
+ * in multi-pipe configurations can cause issues (such as underruns causing
+ * full system hangs), and the bspec also suggests that software disable it
+ * when more then one pipe is enabled.
+ */
+static int
+skl_enable_sagv(struct drm_i915_private *dev_priv)
+{
+ int ret;
+
+ if (IS_BROXTON(dev_priv))
+ return 0;
+ if (dev_priv->skl_sagv_enabled)
+ return 0;
+
+ mutex_lock(&dev_priv->rps.hw_lock);
+ DRM_DEBUG_KMS("Enabling the SAGV\n");
+
+ ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL,
+ GEN9_SAGV_DYNAMIC_FREQ);
+ if (!ret)
+ dev_priv->skl_sagv_enabled = true;
+ else
+ DRM_ERROR("Failed to enable the SAGV\n");
+
+ /* We don't need to wait for SAGV when enabling */
+ mutex_unlock(&dev_priv->rps.hw_lock);
+ return ret;
+}
+
+static int
+skl_disable_sagv(struct drm_i915_private *dev_priv)
+{
+ int ret = 0;
+ unsigned long timeout;
+ u32 temp;
+
+ if (IS_BROXTON(dev_priv))
+ return 0;
+ if (!dev_priv->skl_sagv_enabled)
+ return 0;
+
+ mutex_lock(&dev_priv->rps.hw_lock);
+ DRM_DEBUG_KMS("Disabling the SAGV\n");
+
+ /* bspec says to keep retrying for at least 1 ms */
+ timeout = jiffies + msecs_to_jiffies(1);
+ do {
+ ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL,
+ GEN9_SAGV_DISABLE);
+ if (ret) {
+ DRM_ERROR("Failed to disable the SAGV\n");
+ goto out;
+ }
+
+ ret = sandybridge_pcode_read(dev_priv, GEN9_PCODE_SAGV_CONTROL,
+ &temp);
+ if (ret) {
+ DRM_ERROR("Failed to check the status of the SAGV\n");
+ goto out;
+ }
+ } while (!(temp & 0x1) && jiffies < timeout);
+
+ if (temp & 0x1) {
+ dev_priv->skl_sagv_enabled = false;
+ } else {
+ ret = -1;
+ DRM_ERROR("Request to disable SAGV timed out\n");
+ }
+
+out:
+ mutex_unlock(&dev_priv->rps.hw_lock);
+ return ret;
+}
+
+static void
skl_ddb_get_pipe_allocation_limits(struct drm_device *dev,
const struct intel_crtc_state *cstate,
struct skl_ddb_entry *alloc, /* out */
@@ -3525,6 +3628,11 @@ static void skl_write_wm_values(struct drm_i915_private *dev_priv,
struct drm_device *dev = dev_priv->dev;
struct intel_crtc *crtc;
+ if (dev_priv->active_crtcs == 1)
+ skl_enable_sagv(dev_priv);
+ else
+ skl_disable_sagv(dev_priv);
+
for_each_intel_crtc(dev, crtc) {
int i, level, max_level = ilk_wm_max_level(dev);
enum pipe pipe = crtc->pipe;
@@ -4072,6 +4180,8 @@ void skl_wm_get_hw_state(struct drm_device *dev)
skl_plane_relative_data_rate(cstate, pstate, 1);
}
}
+
+ skl_sagv_get_hw_state(dev_priv);
}
static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc)
--
2.7.4

View File

@ -630,6 +630,11 @@ Patch835: 0001-Work-around-for-addition-of-metag-def-but-not-reloca.patch
#CVE-2016-5389 CVE-2016-5969 rhbz 1354708 1355615 #CVE-2016-5389 CVE-2016-5969 rhbz 1354708 1355615
Patch836: tcp-make-challenge-acks-less-predictable.patch Patch836: tcp-make-challenge-acks-less-predictable.patch
# https://lists.fedoraproject.org/archives/list/kernel@lists.fedoraproject.org/message/A4YCP7OGMX6JLFT5V44H57GOMAQLC3M4/
Patch837: drm-amdgpu-Disable-RPM-helpers-while-reprobing.patch
Patch838: drm-i915-skl-Add-support-for-the-SAGV-fix-underrun-hangs.patch
Patch839: Revert-ALSA-hda-remove-controller-dependency-on-i915.patch
# END OF PATCH DEFINITIONS # END OF PATCH DEFINITIONS
%endif %endif
@ -2155,6 +2160,9 @@ fi
# #
# #
%changelog %changelog
* Thu Jul 14 2016 Josh Boyer <jwboyer@fedoraproject.org>
- Fix various i915 uncore oopses (rhbz 1340218 1325020 1342722 1347681)
* Wed Jul 13 2016 Justin M. Forbes <jforbes@fedoraproject.org> - 4.7.0-0.rc7.git2.1 * Wed Jul 13 2016 Justin M. Forbes <jforbes@fedoraproject.org> - 4.7.0-0.rc7.git2.1
- Linux v4.7-rc7-27-gf97d104 - Linux v4.7-rc7-27-gf97d104