[PATCH v3 0/3] Reduce context clear batch size to avoid gpu hang

[PATCH v3 0/3] Reduce context clear batch size to avoid gpu hang

[rwright]

From: Randy Wright <rwright@hpe.com>

For several months, I've been experiencing GPU hangs when  starting
Cinnamon on an HP Pavilion Mini 300-020 if I try to run an upstream
kernel.  I reported this recently in
https://gitlab.freedesktop.org/drm/intel/-/issues/2413 where I have
attached the requested evidence including the state collected from
/sys/class/drm/card0/error and debug output from dmesg.

I ran a bisect to find the problem, which indicates this is the
troublesome commit:

  [47f8253d2b8947d79fd3196bf96c1959c0f25f20] drm/i915/gen7: Clear all EU/L3 residual contexts

The nature of that commit suggested to me that reducing the
batch size used in the context clear operation might help this
relatively low-powered system to avoid the hang.... and it did!
I simply forced this system to take the smaller batch length that is
already used for non-Haswell systems.

The first two versions of this patch were posted as RFC
patches to the Intel-gfx list, implementing the same
algorithmic change in function batch_get_defaults,
but without employing a properly constructed quirk.

I've now cleaned up the patch to employ a new QUIRK_RENDERCLEAR_REDUCED.
The quirk is presently set only for the aforementioned HP Pavilion Mini
300-020.  The patch now touches three files to define the quirk, set it,
and then check for it in function batch_get_defaults.

Randy Wright (3):
  drm/i915: Introduce quirk QUIRK_RENDERCLEAR_REDUCED
  drm/i915/display: Add function quirk_renderclear_reduced
  drm/i915/gt: Force reduced batch size if new QUIRK_RENDERCLEAR_REDUCED
    is set.

 drivers/gpu/drm/i915/display/intel_quirks.c | 13 +++++++++++++
 drivers/gpu/drm/i915/gt/gen7_renderclear.c  |  2 +-
 drivers/gpu/drm/i915/i915_drv.h             |  1 +
 3 files changed, 15 insertions(+), 1 deletion(-)

-- 
2.25.1

[PATCH v3 1/3] drm/i915: Introduce quirk QUIRK_RENDERCLEAR_REDUCED

[rwright]

From: Randy Wright <rwright@hpe.com>

Introduce quirk QUIRK_RENDERCLEAR_REDUCED, which will be used
to force a limited batch buffer size for clearing
residual contexts in gen7_renderclear.c.

Signed-off-by: Randy Wright <rwright@hpe.com>
---
 drivers/gpu/drm/i915/i915_drv.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e4f7f6518945..e8873462eb2c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -525,6 +525,7 @@ struct i915_psr {
 #define QUIRK_PIN_SWIZZLED_PAGES (1<<5)
 #define QUIRK_INCREASE_T12_DELAY (1<<6)
 #define QUIRK_INCREASE_DDI_DISABLED_TIME (1<<7)
+#define QUIRK_RENDERCLEAR_REDUCED (1<<8)
 
 struct intel_fbdev;
 struct intel_fbc_work;
-- 
2.25.1

[PATCH v3 2/3] drm/i915/display: Add function quirk_renderclear_reduced

[rwright]

From: Randy Wright <rwright@hpe.com>

Added function quirk_renderclear_reduced to set QUIRK_RENDERCLEAR_REDUCED
for designated platforms.  Applying QUIRK_RENDERCLEAR_REDUCED for
the HP Pavilion Mini 300-020 prevents a GPU hang.

Signed-off-by: Randy Wright <rwright@hpe.com>
---
 drivers/gpu/drm/i915/display/intel_quirks.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_quirks.c b/drivers/gpu/drm/i915/display/intel_quirks.c
index 46beb155d835..630b984ba49c 100644
--- a/drivers/gpu/drm/i915/display/intel_quirks.c
+++ b/drivers/gpu/drm/i915/display/intel_quirks.c
@@ -53,6 +53,16 @@ static void quirk_increase_ddi_disabled_time(struct drm_i915_private *i915)
 	drm_info(&i915->drm, "Applying Increase DDI Disabled quirk\n");
 }
 
+/*
+ * Force use of smaller batch size in gen7_renderclear.c
+ * Needed on (at least) HP Pavilion Mini 300-020 to avoid GPU hang.
+ */
+static void quirk_renderclear_reduced(struct drm_i915_private *i915)
+{
+	i915->quirks |= QUIRK_RENDERCLEAR_REDUCED;
+	drm_info(&i915->drm, "Applying Renderclear Reduced quirk\n");
+}
+
 struct intel_quirk {
 	int device;
 	int subsystem_vendor;
@@ -141,6 +151,9 @@ static struct intel_quirk intel_quirks[] = {
 	/* HP Chromebook 14 (Celeron 2955U) */
 	{ 0x0a06, 0x103c, 0x21ed, quirk_backlight_present },
 
+	/* HP Mini 300-020 */
+	{ 0x0a06, 0x103c, 0x2b38, quirk_renderclear_reduced },
+
 	/* Dell Chromebook 11 */
 	{ 0x0a06, 0x1028, 0x0a35, quirk_backlight_present },
 
-- 
2.25.1

[PATCH v3 2/3] drm/i915/display: Add function quirk_renderclear_reduced

[rwright]

From: Randy Wright <rwright@hpe.com>

Added function quirk_renderclear_reduced to set QUIRK_RENDERCLEAR_REDUCED
for designated platforms.  Applying QUIRK_RENDERCLEAR_REDUCED for
the HP Pavilion Mini 300-020 prevents a GPU hang.

Signed-off-by: Randy Wright <rwright@hpe.com>
---
 drivers/gpu/drm/i915/display/intel_quirks.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_quirks.c b/drivers/gpu/drm/i915/display/intel_quirks.c
index 46beb155d835..630b984ba49c 100644
--- a/drivers/gpu/drm/i915/display/intel_quirks.c
+++ b/drivers/gpu/drm/i915/display/intel_quirks.c
@@ -53,6 +53,16 @@ static void quirk_increase_ddi_disabled_time(struct drm_i915_private *i915)
 	drm_info(&i915->drm, "Applying Increase DDI Disabled quirk\n");
 }
 
+/*
+ * Force use of smaller batch size in gen7_renderclear.c
+ * Needed on (at least) HP Pavilion Mini 300-020 to avoid GPU hang.
+ */
+static void quirk_renderclear_reduced(struct drm_i915_private *i915)
+{
+	i915->quirks |= QUIRK_RENDERCLEAR_REDUCED;
+	drm_info(&i915->drm, "Applying Renderclear Reduced quirk\n");
+}
+
 struct intel_quirk {
 	int device;
 	int subsystem_vendor;
@@ -141,6 +151,9 @@ static struct intel_quirk intel_quirks[] = {
 	/* HP Chromebook 14 (Celeron 2955U) */
 	{ 0x0a06, 0x103c, 0x21ed, quirk_backlight_present },
 
+	/* HP Mini 300-020 */
+	{ 0x0a06, 0x103c, 0x2b38, quirk_renderclear_reduced },
+
 	/* Dell Chromebook 11 */
 	{ 0x0a06, 0x1028, 0x0a35, quirk_backlight_present },
 
-- 
2.25.1