Skip to contentSkip to conversation

drm/i915: Fix HSW parity test

PATCH In review Ben Widawsky 4 participants 27 messages Sep 18, 2013 – Sep 19, 2013

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

PATCH 1/6 drm/i915: Fix HSW parity test

Haswell changed the log registers to be WO, so we can no longer read them to determine the programming (which sucks, see later note). For now, simply use the cached value, and hope HW doesn't screw us over.

v2: Simplify the logic to avoid an extra !, remove last, and fix the buffer offset which broke along the rebase (Ville)

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=57441

CC Ville Syrjälä <[email protected]>
---
 drivers/gpu/drm/i915/i915_sysfs.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)
drivers/gpu/drm/i915/i915_sysfs.c +13 -1
index d572435..71f6de2 100644
@@ -133,6 +133,17 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
+	if (IS_HASWELL(drm_dev)) {
+		if (dev_priv->l3_parity.remap_info)
+			memcpy(buf,
+			       dev_priv->l3_parity.remap_info + (offset/4),
+			       count);
+		else
+			memset(buf, 0, count);
+
+		goto out;
+	}
+
 	misccpctl = I915_READ(GEN7_MISCCPCTL);
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
 
@@ -141,9 +152,10 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 
+out:
 	mutex_unlock(&drm_dev->struct_mutex);
 
-	return i;
+	return count;
 }
 
 static ssize_t
Signature · 6 lines
1.8.4

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

PATCH 2/6 drm/i915: Add second slice l3 remapping

Certain HSW SKUs have a second bank of L3. This L3 remapping has a separate register set, and interrupt from the first "slice". A slice is simply a term to define some subset of the GPU's l3 cache. This patch implements both the interrupt handler, and ability to communicate with userspace about this second slice.

v2: Remove redundant check about non-existent slice.
Change warning about interrupts of unknown slices to WARN_ON_ONCE Handle the case where we get 2 slice interrupts concurrently, and switch the tracking of interrupts to be non-destructive (all Ville) Don't enable/mask the second slice parity interrupt for ivb/vlv (even though all docs I can find claim it's rsvd) (Ville + Bryan) Keep BYT excluded from L3 parity

CC Ville Syrjälä <[email protected]>
---
 drivers/gpu/drm/i915/i915_drv.h         |  7 ++-
 drivers/gpu/drm/i915/i915_gem.c         | 26 +++++-----
 drivers/gpu/drm/i915/i915_irq.c         | 88 +++++++++++++++++++++------------
 drivers/gpu/drm/i915/i915_reg.h         |  7 +++
 drivers/gpu/drm/i915/i915_sysfs.c       | 34 ++++++++++---
 drivers/gpu/drm/i915/intel_ringbuffer.c |  7 ++-
 include/uapi/drm/i915_drm.h             |  8 +--
 7 files changed, 116 insertions(+), 61 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +5 -2
index 8b16d47..c6e8df7 100644
@@ -917,9 +917,11 @@ struct i915_ums_state {
 	int mm_suspended;
 };
 
+#define MAX_L3_SLICES 2
 struct intel_l3_parity {
-	u32 *remap_info;
+	u32 *remap_info[MAX_L3_SLICES];
 	struct work_struct error_work;
+	int which_slice;
 };
 
 struct i915_gem_mm {
@@ -1686,6 +1688,7 @@ struct drm_i915_file_private {
 #define HAS_FORCE_WAKE(dev) (INTEL_INFO(dev)->has_force_wake)
 
 #define HAS_L3_GPU_CACHE(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
+#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_GPU_CACHE(dev))
 
 #define GT_FREQUENCY_MULTIPLIER 50
 
@@ -1946,7 +1949,7 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
 int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
 int __must_check i915_gem_init(struct drm_device *dev);
 int __must_check i915_gem_init_hw(struct drm_device *dev);
-void i915_gem_l3_remap(struct drm_device *dev);
+void i915_gem_l3_remap(struct drm_device *dev, int slice);
 void i915_gem_init_swizzling(struct drm_device *dev);
 void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
 int __must_check i915_gpu_idle(struct drm_device *dev);
drivers/gpu/drm/i915/i915_gem.c +13 -13
index 3d3de6e..66bf75d 100644
@@ -4252,16 +4252,15 @@ i915_gem_idle(struct drm_device *dev)
 	return 0;
 }
 
-void i915_gem_l3_remap(struct drm_device *dev)
+void i915_gem_l3_remap(struct drm_device *dev, int slice)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
+	u32 reg_base = GEN7_L3LOG_BASE + (slice * 0x200);
+	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
 	u32 misccpctl;
 	int i;
 
-	if (!HAS_L3_GPU_CACHE(dev))
-		return;
-
-	if (!dev_priv->l3_parity.remap_info)
+	if (!HAS_L3_GPU_CACHE(dev) || !remap_info)
 		return;
 
 	misccpctl = I915_READ(GEN7_MISCCPCTL);
@@ -4269,17 +4268,17 @@ void i915_gem_l3_remap(struct drm_device *dev)
 	POSTING_READ(GEN7_MISCCPCTL);
 
 	for (i = 0; i < GEN7_L3LOG_SIZE; i += 4) {
-		u32 remap = I915_READ(GEN7_L3LOG_BASE + i);
-		if (remap && remap != dev_priv->l3_parity.remap_info[i/4])
+		u32 remap = I915_READ(reg_base + i);
+		if (remap && remap != remap_info[i/4])
 			DRM_DEBUG("0x%x was already programmed to %x\n",
-				  GEN7_L3LOG_BASE + i, remap);
-		if (remap && !dev_priv->l3_parity.remap_info[i/4])
+				  reg_base + i, remap);
+		if (remap && !remap_info[i/4])
 			DRM_DEBUG_DRIVER("Clearing remapped register\n");
-		I915_WRITE(GEN7_L3LOG_BASE + i, dev_priv->l3_parity.remap_info[i/4]);
+		I915_WRITE(reg_base + i, remap_info[i/4]);
 	}
 
 	/* Make sure all the writes land before disabling dop clock gating */
-	POSTING_READ(GEN7_L3LOG_BASE);
+	POSTING_READ(reg_base);
 
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 }
@@ -4373,7 +4372,7 @@ int
 i915_gem_init_hw(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	int ret;
+	int ret, i;
 
 	if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
 		return -EIO;
@@ -4392,7 +4391,8 @@ i915_gem_init_hw(struct drm_device *dev)
 		I915_WRITE(GEN7_MSG_CTL, temp);
 	}
 
-	i915_gem_l3_remap(dev);
+	for (i = 0; i < NUM_L3_SLICES(dev); i++)
+		i915_gem_l3_remap(dev, i);
 
 	i915_gem_init_swizzling(dev);
 
drivers/gpu/drm/i915/i915_irq.c +57 -31

136 lines not on this page · raw message

drivers/gpu/drm/i915/i915_reg.h +7 -0
index 384adfb..c94946f 100644
@@ -927,6 +927,7 @@
 #define GT_BLT_USER_INTERRUPT			(1 << 22)
 #define GT_BSD_CS_ERROR_INTERRUPT		(1 << 15)
 #define GT_BSD_USER_INTERRUPT			(1 << 12)
+#define GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1	(1 << 11) /* hsw+; rsvd on snb, ivb, vlv */
 #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT	(1 <<  5) /* !snb */
 #define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT	(1 <<  4)
 #define GT_RENDER_CS_MASTER_ERROR_INTERRUPT	(1 <<  3)
@@ -937,6 +938,10 @@
 #define PM_VEBOX_CS_ERROR_INTERRUPT		(1 << 12) /* hsw+ */
 #define PM_VEBOX_USER_INTERRUPT			(1 << 10) /* hsw+ */
 
+#define GT_PARITY_ERROR(dev) \
+	(GT_RENDER_L3_PARITY_ERROR_INTERRUPT | \
+	 IS_HASWELL(dev) ? GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1 : 0)
+
 /* These are all the "old" interrupts */
 #define ILK_BSD_USER_INTERRUPT				(1<<5)
 #define I915_PIPE_CONTROL_NOTIFY_INTERRUPT		(1<<18)
@@ -4743,6 +4748,7 @@
 
 /* IVYBRIDGE DPF */
 #define GEN7_L3CDERRST1			0xB008 /* L3CD Error Status 1 */
+#define HSW_L3CDERRST11			0xB208 /* L3CD Error Status register 1 slice 1 */
 #define   GEN7_L3CDERRST1_ROW_MASK	(0x7ff<<14)
 #define   GEN7_PARITY_ERROR_VALID	(1<<13)
 #define   GEN7_L3CDERRST1_BANK_MASK	(3<<11)
@@ -4756,6 +4762,7 @@
 #define   GEN7_L3CDERRST1_ENABLE	(1<<7)
 
 #define GEN7_L3LOG_BASE			0xB070
+#define HSW_L3LOG_BASE_SLICE1		0xB270
 #define GEN7_L3LOG_SIZE			0x80
 
 #define GEN7_HALF_SLICE_CHICKEN1	0xe100 /* IVB GT1 + VLV */
drivers/gpu/drm/i915/i915_sysfs.c +27 -7
index 71f6de2..3a8bf0c 100644
@@ -119,6 +119,7 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
 	uint32_t misccpctl;
+	int slice = (int)(uintptr_t)attr->private;
 	int i, ret;
 
 	count = round_down(count, 4);
@@ -134,9 +135,9 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 		return ret;
 
 	if (IS_HASWELL(drm_dev)) {
-		if (dev_priv->l3_parity.remap_info)
+		if (dev_priv->l3_parity.remap_info[slice])
 			memcpy(buf,
-			       dev_priv->l3_parity.remap_info + (offset/4),
+			       dev_priv->l3_parity.remap_info[slice] + (offset/4),
 			       count);
 		else
 			memset(buf, 0, count);
@@ -168,6 +169,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
 	u32 *temp = NULL; /* Just here to make handling failures easy */
+	int slice = (int)(uintptr_t)attr->private;
 	int ret;
 
 	ret = l3_access_valid(drm_dev, offset);
@@ -178,7 +180,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
-	if (!dev_priv->l3_parity.remap_info) {
+	if (!dev_priv->l3_parity.remap_info[slice]) {
 		temp = kzalloc(GEN7_L3LOG_SIZE, GFP_KERNEL);
 		if (!temp) {
 			mutex_unlock(&drm_dev->struct_mutex);
@@ -198,11 +200,11 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	 * at this point it is left as a TODO.
 	*/
 	if (temp)
-		dev_priv->l3_parity.remap_info = temp;
+		dev_priv->l3_parity.remap_info[slice] = temp;
 
-	memcpy(dev_priv->l3_parity.remap_info + (offset/4), buf, count);
+	memcpy(dev_priv->l3_parity.remap_info[slice] + (offset/4), buf, count);
 
-	i915_gem_l3_remap(drm_dev);
+	i915_gem_l3_remap(drm_dev, slice);
 
 	mutex_unlock(&drm_dev->struct_mutex);
 
@@ -214,7 +216,17 @@ static struct bin_attribute dpf_attrs = {
 	.size = GEN7_L3LOG_SIZE,
 	.read = i915_l3_read,
 	.write = i915_l3_write,
-	.mmap = NULL
+	.mmap = NULL,
+	.private = (void *)0
+};
+
+static struct bin_attribute dpf_attrs_1 = {
+	.attr = {.name = "l3_parity_slice_1", .mode = (S_IRUSR | S_IWUSR)},
+	.size = GEN7_L3LOG_SIZE,
+	.read = i915_l3_read,
+	.write = i915_l3_write,
+	.mmap = NULL,
+	.private = (void *)1
 };
 
 static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
@@ -525,6 +537,13 @@ void i915_setup_sysfs(struct drm_device *dev)
 		ret = device_create_bin_file(&dev->primary->kdev, &dpf_attrs);
 		if (ret)
 			DRM_ERROR("l3 parity sysfs setup failed\n");
+
+		if (NUM_L3_SLICES(dev) > 1) {
+			ret = device_create_bin_file(&dev->primary->kdev,
+						     &dpf_attrs_1);
+			if (ret)
+				DRM_ERROR("l3 parity slice 1 setup failed\n");
+		}
 	}
 
 	ret = 0;
@@ -548,6 +567,7 @@ void i915_teardown_sysfs(struct drm_device *dev)
 		sysfs_remove_files(&dev->primary->kdev.kobj, vlv_attrs);
 	else
 		sysfs_remove_files(&dev->primary->kdev.kobj, gen6_attrs);
+	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs_1);
 	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs);
 #ifdef CONFIG_PM
 	sysfs_unmerge_group(&dev->primary->kdev.kobj, &rc6_attr_group);
drivers/gpu/drm/i915/intel_ringbuffer.c +3 -4
index 686e5b2..958b7d8 100644
@@ -570,7 +570,7 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
 	if (HAS_L3_GPU_CACHE(dev))
-		I915_WRITE_IMR(ring, ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
+		I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 
 	return ret;
 }
@@ -1000,7 +1000,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring,
 				       ~(ring->irq_enable_mask |
-					 GT_RENDER_L3_PARITY_ERROR_INTERRUPT));
+					 GT_PARITY_ERROR(dev)));
 		else
 			I915_WRITE_IMR(ring, ~ring->irq_enable_mask);
 		ilk_enable_gt_irq(dev_priv, ring->irq_enable_mask);
@@ -1020,8 +1020,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
-			I915_WRITE_IMR(ring,
-				       ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
+			I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 		else
 			I915_WRITE_IMR(ring, ~0);
 		ilk_disable_gt_irq(dev_priv, ring->irq_enable_mask);
include/uapi/drm/i915_drm.h +4 -4
index 55bb572..3a4e97b 100644
@@ -38,10 +38,10 @@
  *
  * I915_L3_PARITY_UEVENT - Generated when the driver receives a parity mismatch
  *	event from the gpu l3 cache. Additional information supplied is ROW,
- *	BANK, SUBBANK of the affected cacheline. Userspace should keep track of
- *	these events and if a specific cache-line seems to have a persistent
- *	error remap it with the l3 remapping tool supplied in intel-gpu-tools.
- *	The value supplied with the event is always 1.
+ *	BANK, SUBBANK, SLICE of the affected cacheline. Userspace should keep
+ *	track of these events and if a specific cache-line seems to have a
+ *	persistent error remap it with the l3 remapping tool supplied in
+ *	intel-gpu-tools.  The value supplied with the event is always 1.
  *
  * I915_ERROR_UEVENT - Generated upon error detection, currently only via
  *	hangcheck. The error detection event is a good indicator of when things
Signature · 6 lines
1.8.4

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Reviewed-by on v1 2/6
#2 lore raw

Re: [PATCH 2/6] drm/i915: Add second slice l3 remapping

Quoted 152 lines · Ben Widawsky

Certain HSW SKUs have a second bank of L3. This L3 remapping has a separate register set, and interrupt from the first "slice". A slice is simply a term to define some subset of the GPU's l3 cache. This patch implements both the interrupt handler, and ability to communicate with userspace about this second slice.

v2: Remove redundant check about non-existent slice.
Change warning about interrupts of unknown slices to WARN_ON_ONCE Handle the case where we get 2 slice interrupts concurrently, and switch the tracking of interrupts to be non-destructive (all Ville) Don't enable/mask the second slice parity interrupt for ivb/vlv (even though all docs I can find claim it's rsvd) (Ville + Bryan) Keep BYT excluded from L3 parity

CC Ville Syrjälä <[email protected]>
---
 drivers/gpu/drm/i915/i915_drv.h         |  7 ++-
 drivers/gpu/drm/i915/i915_gem.c         | 26 +++++-----
 drivers/gpu/drm/i915/i915_irq.c         | 88 +++++++++++++++++++++------------
 drivers/gpu/drm/i915/i915_reg.h         |  7 +++
 drivers/gpu/drm/i915/i915_sysfs.c       | 34 ++++++++++---
 drivers/gpu/drm/i915/intel_ringbuffer.c |  7 ++-
 include/uapi/drm/i915_drm.h             |  8 +--
 7 files changed, 116 insertions(+), 61 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +5 -2
index 8b16d47..c6e8df7 100644
@@ -917,9 +917,11 @@ struct i915_ums_state {
 	int mm_suspended;
 };
 
+#define MAX_L3_SLICES 2
 struct intel_l3_parity {
-	u32 *remap_info;
+	u32 *remap_info[MAX_L3_SLICES];
 	struct work_struct error_work;
+	int which_slice;
 };
 
 struct i915_gem_mm {
@@ -1686,6 +1688,7 @@ struct drm_i915_file_private {
 #define HAS_FORCE_WAKE(dev) (INTEL_INFO(dev)->has_force_wake)
 
 #define HAS_L3_GPU_CACHE(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
+#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_GPU_CACHE(dev))
 
 #define GT_FREQUENCY_MULTIPLIER 50
 
@@ -1946,7 +1949,7 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
 int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
 int __must_check i915_gem_init(struct drm_device *dev);
 int __must_check i915_gem_init_hw(struct drm_device *dev);
-void i915_gem_l3_remap(struct drm_device *dev);
+void i915_gem_l3_remap(struct drm_device *dev, int slice);
 void i915_gem_init_swizzling(struct drm_device *dev);
 void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
 int __must_check i915_gpu_idle(struct drm_device *dev);
drivers/gpu/drm/i915/i915_gem.c +13 -13
index 3d3de6e..66bf75d 100644
@@ -4252,16 +4252,15 @@ i915_gem_idle(struct drm_device *dev)
 	return 0;
 }
 
-void i915_gem_l3_remap(struct drm_device *dev)
+void i915_gem_l3_remap(struct drm_device *dev, int slice)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
+	u32 reg_base = GEN7_L3LOG_BASE + (slice * 0x200);
+	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
 	u32 misccpctl;
 	int i;
 
-	if (!HAS_L3_GPU_CACHE(dev))
-		return;
-
-	if (!dev_priv->l3_parity.remap_info)
+	if (!HAS_L3_GPU_CACHE(dev) || !remap_info)
 		return;
 
 	misccpctl = I915_READ(GEN7_MISCCPCTL);
@@ -4269,17 +4268,17 @@ void i915_gem_l3_remap(struct drm_device *dev)
 	POSTING_READ(GEN7_MISCCPCTL);
 
 	for (i = 0; i < GEN7_L3LOG_SIZE; i += 4) {
-		u32 remap = I915_READ(GEN7_L3LOG_BASE + i);
-		if (remap && remap != dev_priv->l3_parity.remap_info[i/4])
+		u32 remap = I915_READ(reg_base + i);
+		if (remap && remap != remap_info[i/4])
 			DRM_DEBUG("0x%x was already programmed to %x\n",
-				  GEN7_L3LOG_BASE + i, remap);
-		if (remap && !dev_priv->l3_parity.remap_info[i/4])
+				  reg_base + i, remap);
+		if (remap && !remap_info[i/4])
 			DRM_DEBUG_DRIVER("Clearing remapped register\n");
-		I915_WRITE(GEN7_L3LOG_BASE + i, dev_priv->l3_parity.remap_info[i/4]);
+		I915_WRITE(reg_base + i, remap_info[i/4]);
 	}
 
 	/* Make sure all the writes land before disabling dop clock gating */
-	POSTING_READ(GEN7_L3LOG_BASE);
+	POSTING_READ(reg_base);
 
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 }
@@ -4373,7 +4372,7 @@ int
 i915_gem_init_hw(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	int ret;
+	int ret, i;
 
 	if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
 		return -EIO;
@@ -4392,7 +4391,8 @@ i915_gem_init_hw(struct drm_device *dev)
 		I915_WRITE(GEN7_MSG_CTL, temp);
 	}
 
-	i915_gem_l3_remap(dev);
+	for (i = 0; i < NUM_L3_SLICES(dev); i++)
+		i915_gem_l3_remap(dev, i);
 
 	i915_gem_init_swizzling(dev);
 
drivers/gpu/drm/i915/i915_irq.c +6 -1
index a42f30b..b11ee39 100644
@@ -888,9 +888,10 @@ static void ivybridge_parity_work(struct work_struct *work)
 	drm_i915_private_t *dev_priv = container_of(work, drm_i915_private_t,
 						    l3_parity.error_work);
 	u32 error_status, row, bank, subbank;
-	char *parity_event[5];
+	char *parity_event[6];
 	uint32_t misccpctl;
 	unsigned long flags;
+	uint8_t slice = 0;
 
 	/* We must turn off DOP level clock gating to access the L3 registers.
 	 * In order to prevent a get/put style interface, acquire struct mutex
@@ -898,45 +899,63 @@ static void ivybridge_parity_work(struct work_struct *work)
 	 */
 	mutex_lock(&dev_priv->dev->struct_mutex);
 
+	/* If we've screwed up tracking, just let the interrupt fire again */
+	if (WARN_ON(!dev_priv->l3_parity.which_slice))
+		goto out;
+

drivers/gpu/drm/i915/i915_irq.c static void ivybridge_parity_work(struct work_struct *work) · line 911

Quoted 10 lines
drivers/gpu/drm/i915/i915_irq.c +2 -4
 	misccpctl = I915_READ(GEN7_MISCCPCTL);
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
 	POSTING_READ(GEN7_MISCCPCTL);
 
-	error_status = I915_READ(GEN7_L3CDERRST1);
-	row = GEN7_PARITY_ERROR_ROW(error_status);
-	bank = GEN7_PARITY_ERROR_BANK(error_status);
-	subbank = GEN7_PARITY_ERROR_SUBBANK(error_status);
+	while ((slice = ffs(dev_priv->l3_parity.which_slice)) != 0) {
+		u32 reg;

ffs(1) == 1, so we need a slice-- here, don't we?

The rest looks OK to me, so once this one thing is fixed you can slap on a

sticker.

Quoted 300 lines
drivers/gpu/drm/i915/i915_irq.c +49 -26
-	I915_WRITE(GEN7_L3CDERRST1, GEN7_PARITY_ERROR_VALID |
-				    GEN7_L3CDERRST1_ENABLE);
-	POSTING_READ(GEN7_L3CDERRST1);
+		if (WARN_ON_ONCE(slice >= NUM_L3_SLICES(dev_priv->dev)))
+			break;
 
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
+		dev_priv->l3_parity.which_slice &= ~(1<<slice);
 
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	ilk_enable_gt_irq(dev_priv, GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+		reg = GEN7_L3CDERRST1 + (slice * 0x200);
 
-	mutex_unlock(&dev_priv->dev->struct_mutex);
+		error_status = I915_READ(reg);
+		row = GEN7_PARITY_ERROR_ROW(error_status);
+		bank = GEN7_PARITY_ERROR_BANK(error_status);
+		subbank = GEN7_PARITY_ERROR_SUBBANK(error_status);
+
+		I915_WRITE(reg, GEN7_PARITY_ERROR_VALID | GEN7_L3CDERRST1_ENABLE);
+		POSTING_READ(reg);
+
+		parity_event[0] = I915_L3_PARITY_UEVENT "=1";
+		parity_event[1] = kasprintf(GFP_KERNEL, "ROW=%d", row);
+		parity_event[2] = kasprintf(GFP_KERNEL, "BANK=%d", bank);
+		parity_event[3] = kasprintf(GFP_KERNEL, "SUBBANK=%d", subbank);
+		parity_event[4] = kasprintf(GFP_KERNEL, "SLICE=%d", slice);
+		parity_event[5] = NULL;
+
+		kobject_uevent_env(&dev_priv->dev->primary->kdev.kobj,
+				   KOBJ_CHANGE, parity_event);
 
-	parity_event[0] = I915_L3_PARITY_UEVENT "=1";
-	parity_event[1] = kasprintf(GFP_KERNEL, "ROW=%d", row);
-	parity_event[2] = kasprintf(GFP_KERNEL, "BANK=%d", bank);
-	parity_event[3] = kasprintf(GFP_KERNEL, "SUBBANK=%d", subbank);
-	parity_event[4] = NULL;
+		DRM_DEBUG("Parity error: Slice = %d, Row = %d, Bank = %d, Sub bank = %d.\n",
+			  slice, row, bank, subbank);
 
-	kobject_uevent_env(&dev_priv->dev->primary->kdev.kobj,
-			   KOBJ_CHANGE, parity_event);
+		kfree(parity_event[4]);
+		kfree(parity_event[3]);
+		kfree(parity_event[2]);
+		kfree(parity_event[1]);
+	}
 
-	DRM_DEBUG("Parity error: Row = %d, Bank = %d, Sub bank = %d.\n",
-		  row, bank, subbank);
+	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 
-	kfree(parity_event[3]);
-	kfree(parity_event[2]);
-	kfree(parity_event[1]);
+out:
+	WARN_ON(dev_priv->l3_parity.which_slice);
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
+	ilk_enable_gt_irq(dev_priv, GT_PARITY_ERROR(dev_priv->dev));
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+
+	mutex_unlock(&dev_priv->dev->struct_mutex);
 }
 
-static void ivybridge_parity_error_irq_handler(struct drm_device *dev)
+static void ivybridge_parity_error_irq_handler(struct drm_device *dev, u32 iir)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 
@@ -944,9 +963,16 @@ static void ivybridge_parity_error_irq_handler(struct drm_device *dev)
 		return;
 
 	spin_lock(&dev_priv->irq_lock);
-	ilk_disable_gt_irq(dev_priv, GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
+	ilk_disable_gt_irq(dev_priv, GT_PARITY_ERROR(dev));
 	spin_unlock(&dev_priv->irq_lock);
 
+	iir &= GT_PARITY_ERROR(dev);
+	if (iir & GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1)
+		dev_priv->l3_parity.which_slice |= 1 << 1;
+
+	if (iir & GT_RENDER_L3_PARITY_ERROR_INTERRUPT)
+		dev_priv->l3_parity.which_slice |= 1 << 0;
+
 	queue_work(dev_priv->wq, &dev_priv->l3_parity.error_work);
 }
 
@@ -981,8 +1007,8 @@ static void snb_gt_irq_handler(struct drm_device *dev,
 		i915_handle_error(dev, false);
 	}
 
-	if (gt_iir & GT_RENDER_L3_PARITY_ERROR_INTERRUPT)
-		ivybridge_parity_error_irq_handler(dev);
+	if (gt_iir & GT_PARITY_ERROR(dev))
+		ivybridge_parity_error_irq_handler(dev, gt_iir);
 }
 
 #define HPD_STORM_DETECT_PERIOD 1000
@@ -2267,8 +2293,8 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev)
 	dev_priv->gt_irq_mask = ~0;
 	if (HAS_L3_GPU_CACHE(dev)) {
 		/* L3 parity interrupt is always unmasked. */
-		dev_priv->gt_irq_mask = ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
-		gt_irqs |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
+		dev_priv->gt_irq_mask = ~GT_PARITY_ERROR(dev);
+		gt_irqs |= GT_PARITY_ERROR(dev);
 	}
 
 	gt_irqs |= GT_RENDER_USER_INTERRUPT;
drivers/gpu/drm/i915/i915_reg.h +7 -0
index 384adfb..c94946f 100644
@@ -927,6 +927,7 @@
 #define GT_BLT_USER_INTERRUPT			(1 << 22)
 #define GT_BSD_CS_ERROR_INTERRUPT		(1 << 15)
 #define GT_BSD_USER_INTERRUPT			(1 << 12)
+#define GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1	(1 << 11) /* hsw+; rsvd on snb, ivb, vlv */
 #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT	(1 <<  5) /* !snb */
 #define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT	(1 <<  4)
 #define GT_RENDER_CS_MASTER_ERROR_INTERRUPT	(1 <<  3)
@@ -937,6 +938,10 @@
 #define PM_VEBOX_CS_ERROR_INTERRUPT		(1 << 12) /* hsw+ */
 #define PM_VEBOX_USER_INTERRUPT			(1 << 10) /* hsw+ */
 
+#define GT_PARITY_ERROR(dev) \
+	(GT_RENDER_L3_PARITY_ERROR_INTERRUPT | \
+	 IS_HASWELL(dev) ? GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1 : 0)
+
 /* These are all the "old" interrupts */
 #define ILK_BSD_USER_INTERRUPT				(1<<5)
 #define I915_PIPE_CONTROL_NOTIFY_INTERRUPT		(1<<18)
@@ -4743,6 +4748,7 @@
 
 /* IVYBRIDGE DPF */
 #define GEN7_L3CDERRST1			0xB008 /* L3CD Error Status 1 */
+#define HSW_L3CDERRST11			0xB208 /* L3CD Error Status register 1 slice 1 */
 #define   GEN7_L3CDERRST1_ROW_MASK	(0x7ff<<14)
 #define   GEN7_PARITY_ERROR_VALID	(1<<13)
 #define   GEN7_L3CDERRST1_BANK_MASK	(3<<11)
@@ -4756,6 +4762,7 @@
 #define   GEN7_L3CDERRST1_ENABLE	(1<<7)
 
 #define GEN7_L3LOG_BASE			0xB070
+#define HSW_L3LOG_BASE_SLICE1		0xB270
 #define GEN7_L3LOG_SIZE			0x80
 
 #define GEN7_HALF_SLICE_CHICKEN1	0xe100 /* IVB GT1 + VLV */
drivers/gpu/drm/i915/i915_sysfs.c +27 -7
index 71f6de2..3a8bf0c 100644
@@ -119,6 +119,7 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
 	uint32_t misccpctl;
+	int slice = (int)(uintptr_t)attr->private;
 	int i, ret;
 
 	count = round_down(count, 4);
@@ -134,9 +135,9 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 		return ret;
 
 	if (IS_HASWELL(drm_dev)) {
-		if (dev_priv->l3_parity.remap_info)
+		if (dev_priv->l3_parity.remap_info[slice])
 			memcpy(buf,
-			       dev_priv->l3_parity.remap_info + (offset/4),
+			       dev_priv->l3_parity.remap_info[slice] + (offset/4),
 			       count);
 		else
 			memset(buf, 0, count);
@@ -168,6 +169,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
 	u32 *temp = NULL; /* Just here to make handling failures easy */
+	int slice = (int)(uintptr_t)attr->private;
 	int ret;
 
 	ret = l3_access_valid(drm_dev, offset);
@@ -178,7 +180,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
-	if (!dev_priv->l3_parity.remap_info) {
+	if (!dev_priv->l3_parity.remap_info[slice]) {
 		temp = kzalloc(GEN7_L3LOG_SIZE, GFP_KERNEL);
 		if (!temp) {
 			mutex_unlock(&drm_dev->struct_mutex);
@@ -198,11 +200,11 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	 * at this point it is left as a TODO.
 	*/
 	if (temp)
-		dev_priv->l3_parity.remap_info = temp;
+		dev_priv->l3_parity.remap_info[slice] = temp;
 
-	memcpy(dev_priv->l3_parity.remap_info + (offset/4), buf, count);
+	memcpy(dev_priv->l3_parity.remap_info[slice] + (offset/4), buf, count);
 
-	i915_gem_l3_remap(drm_dev);
+	i915_gem_l3_remap(drm_dev, slice);
 
 	mutex_unlock(&drm_dev->struct_mutex);
 
@@ -214,7 +216,17 @@ static struct bin_attribute dpf_attrs = {
 	.size = GEN7_L3LOG_SIZE,
 	.read = i915_l3_read,
 	.write = i915_l3_write,
-	.mmap = NULL
+	.mmap = NULL,
+	.private = (void *)0
+};
+
+static struct bin_attribute dpf_attrs_1 = {
+	.attr = {.name = "l3_parity_slice_1", .mode = (S_IRUSR | S_IWUSR)},
+	.size = GEN7_L3LOG_SIZE,
+	.read = i915_l3_read,
+	.write = i915_l3_write,
+	.mmap = NULL,
+	.private = (void *)1
 };
 
 static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
@@ -525,6 +537,13 @@ void i915_setup_sysfs(struct drm_device *dev)
 		ret = device_create_bin_file(&dev->primary->kdev, &dpf_attrs);
 		if (ret)
 			DRM_ERROR("l3 parity sysfs setup failed\n");
+
+		if (NUM_L3_SLICES(dev) > 1) {
+			ret = device_create_bin_file(&dev->primary->kdev,
+						     &dpf_attrs_1);
+			if (ret)
+				DRM_ERROR("l3 parity slice 1 setup failed\n");
+		}
 	}
 
 	ret = 0;
@@ -548,6 +567,7 @@ void i915_teardown_sysfs(struct drm_device *dev)
 		sysfs_remove_files(&dev->primary->kdev.kobj, vlv_attrs);
 	else
 		sysfs_remove_files(&dev->primary->kdev.kobj, gen6_attrs);
+	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs_1);
 	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs);
 #ifdef CONFIG_PM
 	sysfs_unmerge_group(&dev->primary->kdev.kobj, &rc6_attr_group);
drivers/gpu/drm/i915/intel_ringbuffer.c +3 -4
index 686e5b2..958b7d8 100644
@@ -570,7 +570,7 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
 	if (HAS_L3_GPU_CACHE(dev))
-		I915_WRITE_IMR(ring, ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
+		I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 
 	return ret;
 }
@@ -1000,7 +1000,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring,
 				       ~(ring->irq_enable_mask |
-					 GT_RENDER_L3_PARITY_ERROR_INTERRUPT));
+					 GT_PARITY_ERROR(dev)));
 		else
 			I915_WRITE_IMR(ring, ~ring->irq_enable_mask);
 		ilk_enable_gt_irq(dev_priv, ring->irq_enable_mask);
@@ -1020,8 +1020,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
-			I915_WRITE_IMR(ring,
-				       ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
+			I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 		else
 			I915_WRITE_IMR(ring, ~0);
 		ilk_disable_gt_irq(dev_priv, ring->irq_enable_mask);
include/uapi/drm/i915_drm.h +4 -4
index 55bb572..3a4e97b 100644
@@ -38,10 +38,10 @@
  *
  * I915_L3_PARITY_UEVENT - Generated when the driver receives a parity mismatch
  *	event from the gpu l3 cache. Additional information supplied is ROW,
- *	BANK, SUBBANK of the affected cacheline. Userspace should keep track of
- *	these events and if a specific cache-line seems to have a persistent
- *	error remap it with the l3 remapping tool supplied in intel-gpu-tools.
- *	The value supplied with the event is always 1.
+ *	BANK, SUBBANK, SLICE of the affected cacheline. Userspace should keep
+ *	track of these events and if a specific cache-line seems to have a
+ *	persistent error remap it with the l3 remapping tool supplied in
+ *	intel-gpu-tools.  The value supplied with the event is always 1.
  *
  * I915_ERROR_UEVENT - Generated upon error detection, currently only via
  *	hangcheck. The error detection event is a good indicator of when things
Signature · 1 line
1.8.4
Signature · 2 lines
Ville Syrjälä
Intel OTC
#3 lore raw

Re: [PATCH 2/6] drm/i915: Add second slice l3 remapping

Quoted 166 lines · Ville Syrjälä
Quoted 152 lines · Ben Widawsky

Certain HSW SKUs have a second bank of L3. This L3 remapping has a separate register set, and interrupt from the first "slice". A slice is simply a term to define some subset of the GPU's l3 cache. This patch implements both the interrupt handler, and ability to communicate with userspace about this second slice.

v2: Remove redundant check about non-existent slice.
Change warning about interrupts of unknown slices to WARN_ON_ONCE Handle the case where we get 2 slice interrupts concurrently, and switch the tracking of interrupts to be non-destructive (all Ville) Don't enable/mask the second slice parity interrupt for ivb/vlv (even though all docs I can find claim it's rsvd) (Ville + Bryan) Keep BYT excluded from L3 parity

CC Ville Syrjälä <[email protected]>
---
 drivers/gpu/drm/i915/i915_drv.h         |  7 ++-
 drivers/gpu/drm/i915/i915_gem.c         | 26 +++++-----
 drivers/gpu/drm/i915/i915_irq.c         | 88 +++++++++++++++++++++------------
 drivers/gpu/drm/i915/i915_reg.h         |  7 +++
 drivers/gpu/drm/i915/i915_sysfs.c       | 34 ++++++++++---
 drivers/gpu/drm/i915/intel_ringbuffer.c |  7 ++-
 include/uapi/drm/i915_drm.h             |  8 +--
 7 files changed, 116 insertions(+), 61 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +5 -2
index 8b16d47..c6e8df7 100644
@@ -917,9 +917,11 @@ struct i915_ums_state {
 	int mm_suspended;
 };
 
+#define MAX_L3_SLICES 2
 struct intel_l3_parity {
-	u32 *remap_info;
+	u32 *remap_info[MAX_L3_SLICES];
 	struct work_struct error_work;
+	int which_slice;
 };
 
 struct i915_gem_mm {
@@ -1686,6 +1688,7 @@ struct drm_i915_file_private {
 #define HAS_FORCE_WAKE(dev) (INTEL_INFO(dev)->has_force_wake)
 
 #define HAS_L3_GPU_CACHE(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
+#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_GPU_CACHE(dev))
 
 #define GT_FREQUENCY_MULTIPLIER 50
 
@@ -1946,7 +1949,7 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
 int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
 int __must_check i915_gem_init(struct drm_device *dev);
 int __must_check i915_gem_init_hw(struct drm_device *dev);
-void i915_gem_l3_remap(struct drm_device *dev);
+void i915_gem_l3_remap(struct drm_device *dev, int slice);
 void i915_gem_init_swizzling(struct drm_device *dev);
 void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
 int __must_check i915_gpu_idle(struct drm_device *dev);
drivers/gpu/drm/i915/i915_gem.c +13 -13
index 3d3de6e..66bf75d 100644
@@ -4252,16 +4252,15 @@ i915_gem_idle(struct drm_device *dev)
 	return 0;
 }
 
-void i915_gem_l3_remap(struct drm_device *dev)
+void i915_gem_l3_remap(struct drm_device *dev, int slice)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
+	u32 reg_base = GEN7_L3LOG_BASE + (slice * 0x200);
+	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
 	u32 misccpctl;
 	int i;
 
-	if (!HAS_L3_GPU_CACHE(dev))
-		return;
-
-	if (!dev_priv->l3_parity.remap_info)
+	if (!HAS_L3_GPU_CACHE(dev) || !remap_info)
 		return;
 
 	misccpctl = I915_READ(GEN7_MISCCPCTL);
@@ -4269,17 +4268,17 @@ void i915_gem_l3_remap(struct drm_device *dev)
 	POSTING_READ(GEN7_MISCCPCTL);
 
 	for (i = 0; i < GEN7_L3LOG_SIZE; i += 4) {
-		u32 remap = I915_READ(GEN7_L3LOG_BASE + i);
-		if (remap && remap != dev_priv->l3_parity.remap_info[i/4])
+		u32 remap = I915_READ(reg_base + i);
+		if (remap && remap != remap_info[i/4])
 			DRM_DEBUG("0x%x was already programmed to %x\n",
-				  GEN7_L3LOG_BASE + i, remap);
-		if (remap && !dev_priv->l3_parity.remap_info[i/4])
+				  reg_base + i, remap);
+		if (remap && !remap_info[i/4])
 			DRM_DEBUG_DRIVER("Clearing remapped register\n");
-		I915_WRITE(GEN7_L3LOG_BASE + i, dev_priv->l3_parity.remap_info[i/4]);
+		I915_WRITE(reg_base + i, remap_info[i/4]);
 	}
 
 	/* Make sure all the writes land before disabling dop clock gating */
-	POSTING_READ(GEN7_L3LOG_BASE);
+	POSTING_READ(reg_base);
 
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 }
@@ -4373,7 +4372,7 @@ int
 i915_gem_init_hw(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	int ret;
+	int ret, i;
 
 	if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
 		return -EIO;
@@ -4392,7 +4391,8 @@ i915_gem_init_hw(struct drm_device *dev)
 		I915_WRITE(GEN7_MSG_CTL, temp);
 	}
 
-	i915_gem_l3_remap(dev);
+	for (i = 0; i < NUM_L3_SLICES(dev); i++)
+		i915_gem_l3_remap(dev, i);
 
 	i915_gem_init_swizzling(dev);
 
drivers/gpu/drm/i915/i915_irq.c +6 -1
index a42f30b..b11ee39 100644
@@ -888,9 +888,10 @@ static void ivybridge_parity_work(struct work_struct *work)
 	drm_i915_private_t *dev_priv = container_of(work, drm_i915_private_t,
 						    l3_parity.error_work);
 	u32 error_status, row, bank, subbank;
-	char *parity_event[5];
+	char *parity_event[6];
 	uint32_t misccpctl;
 	unsigned long flags;
+	uint8_t slice = 0;
 
 	/* We must turn off DOP level clock gating to access the L3 registers.
 	 * In order to prevent a get/put style interface, acquire struct mutex
@@ -898,45 +899,63 @@ static void ivybridge_parity_work(struct work_struct *work)
 	 */
 	mutex_lock(&dev_priv->dev->struct_mutex);
 
+	/* If we've screwed up tracking, just let the interrupt fire again */
+	if (WARN_ON(!dev_priv->l3_parity.which_slice))
+		goto out;
+

drivers/gpu/drm/i915/i915_irq.c static void ivybridge_parity_work(struct work_struct *work) · line 911

Quoted 10 lines
drivers/gpu/drm/i915/i915_irq.c +2 -4
 	misccpctl = I915_READ(GEN7_MISCCPCTL);
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
 	POSTING_READ(GEN7_MISCCPCTL);
 
-	error_status = I915_READ(GEN7_L3CDERRST1);
-	row = GEN7_PARITY_ERROR_ROW(error_status);
-	bank = GEN7_PARITY_ERROR_BANK(error_status);
-	subbank = GEN7_PARITY_ERROR_SUBBANK(error_status);
+	while ((slice = ffs(dev_priv->l3_parity.which_slice)) != 0) {
+		u32 reg;

ffs(1) == 1, so we need a slice-- here, don't we?

Quoted 4 lines

The rest looks OK to me, so once this one thing is fixed you can slap on a

sticker.

That's strange. I noticed this earlier (and don't remember actually fixing it). I wonder why my tests didn't fail horribly. Scary.

Quoted 304 lines
Quoted 300 lines
drivers/gpu/drm/i915/i915_irq.c +49 -26
-	I915_WRITE(GEN7_L3CDERRST1, GEN7_PARITY_ERROR_VALID |
-				    GEN7_L3CDERRST1_ENABLE);
-	POSTING_READ(GEN7_L3CDERRST1);
+		if (WARN_ON_ONCE(slice >= NUM_L3_SLICES(dev_priv->dev)))
+			break;
 
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
+		dev_priv->l3_parity.which_slice &= ~(1<<slice);
 
-	spin_lock_irqsave(&dev_priv->irq_lock, flags);
-	ilk_enable_gt_irq(dev_priv, GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
-	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+		reg = GEN7_L3CDERRST1 + (slice * 0x200);
 
-	mutex_unlock(&dev_priv->dev->struct_mutex);
+		error_status = I915_READ(reg);
+		row = GEN7_PARITY_ERROR_ROW(error_status);
+		bank = GEN7_PARITY_ERROR_BANK(error_status);
+		subbank = GEN7_PARITY_ERROR_SUBBANK(error_status);
+
+		I915_WRITE(reg, GEN7_PARITY_ERROR_VALID | GEN7_L3CDERRST1_ENABLE);
+		POSTING_READ(reg);
+
+		parity_event[0] = I915_L3_PARITY_UEVENT "=1";
+		parity_event[1] = kasprintf(GFP_KERNEL, "ROW=%d", row);
+		parity_event[2] = kasprintf(GFP_KERNEL, "BANK=%d", bank);
+		parity_event[3] = kasprintf(GFP_KERNEL, "SUBBANK=%d", subbank);
+		parity_event[4] = kasprintf(GFP_KERNEL, "SLICE=%d", slice);
+		parity_event[5] = NULL;
+
+		kobject_uevent_env(&dev_priv->dev->primary->kdev.kobj,
+				   KOBJ_CHANGE, parity_event);
 
-	parity_event[0] = I915_L3_PARITY_UEVENT "=1";
-	parity_event[1] = kasprintf(GFP_KERNEL, "ROW=%d", row);
-	parity_event[2] = kasprintf(GFP_KERNEL, "BANK=%d", bank);
-	parity_event[3] = kasprintf(GFP_KERNEL, "SUBBANK=%d", subbank);
-	parity_event[4] = NULL;
+		DRM_DEBUG("Parity error: Slice = %d, Row = %d, Bank = %d, Sub bank = %d.\n",
+			  slice, row, bank, subbank);
 
-	kobject_uevent_env(&dev_priv->dev->primary->kdev.kobj,
-			   KOBJ_CHANGE, parity_event);
+		kfree(parity_event[4]);
+		kfree(parity_event[3]);
+		kfree(parity_event[2]);
+		kfree(parity_event[1]);
+	}
 
-	DRM_DEBUG("Parity error: Row = %d, Bank = %d, Sub bank = %d.\n",
-		  row, bank, subbank);
+	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 
-	kfree(parity_event[3]);
-	kfree(parity_event[2]);
-	kfree(parity_event[1]);
+out:
+	WARN_ON(dev_priv->l3_parity.which_slice);
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
+	ilk_enable_gt_irq(dev_priv, GT_PARITY_ERROR(dev_priv->dev));
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+
+	mutex_unlock(&dev_priv->dev->struct_mutex);
 }
 
-static void ivybridge_parity_error_irq_handler(struct drm_device *dev)
+static void ivybridge_parity_error_irq_handler(struct drm_device *dev, u32 iir)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 
@@ -944,9 +963,16 @@ static void ivybridge_parity_error_irq_handler(struct drm_device *dev)
 		return;
 
 	spin_lock(&dev_priv->irq_lock);
-	ilk_disable_gt_irq(dev_priv, GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
+	ilk_disable_gt_irq(dev_priv, GT_PARITY_ERROR(dev));
 	spin_unlock(&dev_priv->irq_lock);
 
+	iir &= GT_PARITY_ERROR(dev);
+	if (iir & GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1)
+		dev_priv->l3_parity.which_slice |= 1 << 1;
+
+	if (iir & GT_RENDER_L3_PARITY_ERROR_INTERRUPT)
+		dev_priv->l3_parity.which_slice |= 1 << 0;
+
 	queue_work(dev_priv->wq, &dev_priv->l3_parity.error_work);
 }
 
@@ -981,8 +1007,8 @@ static void snb_gt_irq_handler(struct drm_device *dev,
 		i915_handle_error(dev, false);
 	}
 
-	if (gt_iir & GT_RENDER_L3_PARITY_ERROR_INTERRUPT)
-		ivybridge_parity_error_irq_handler(dev);
+	if (gt_iir & GT_PARITY_ERROR(dev))
+		ivybridge_parity_error_irq_handler(dev, gt_iir);
 }
 
 #define HPD_STORM_DETECT_PERIOD 1000
@@ -2267,8 +2293,8 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev)
 	dev_priv->gt_irq_mask = ~0;
 	if (HAS_L3_GPU_CACHE(dev)) {
 		/* L3 parity interrupt is always unmasked. */
-		dev_priv->gt_irq_mask = ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
-		gt_irqs |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
+		dev_priv->gt_irq_mask = ~GT_PARITY_ERROR(dev);
+		gt_irqs |= GT_PARITY_ERROR(dev);
 	}
 
 	gt_irqs |= GT_RENDER_USER_INTERRUPT;
drivers/gpu/drm/i915/i915_reg.h +7 -0
index 384adfb..c94946f 100644
@@ -927,6 +927,7 @@
 #define GT_BLT_USER_INTERRUPT			(1 << 22)
 #define GT_BSD_CS_ERROR_INTERRUPT		(1 << 15)
 #define GT_BSD_USER_INTERRUPT			(1 << 12)
+#define GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1	(1 << 11) /* hsw+; rsvd on snb, ivb, vlv */
 #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT	(1 <<  5) /* !snb */
 #define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT	(1 <<  4)
 #define GT_RENDER_CS_MASTER_ERROR_INTERRUPT	(1 <<  3)
@@ -937,6 +938,10 @@
 #define PM_VEBOX_CS_ERROR_INTERRUPT		(1 << 12) /* hsw+ */
 #define PM_VEBOX_USER_INTERRUPT			(1 << 10) /* hsw+ */
 
+#define GT_PARITY_ERROR(dev) \
+	(GT_RENDER_L3_PARITY_ERROR_INTERRUPT | \
+	 IS_HASWELL(dev) ? GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1 : 0)
+
 /* These are all the "old" interrupts */
 #define ILK_BSD_USER_INTERRUPT				(1<<5)
 #define I915_PIPE_CONTROL_NOTIFY_INTERRUPT		(1<<18)
@@ -4743,6 +4748,7 @@
 
 /* IVYBRIDGE DPF */
 #define GEN7_L3CDERRST1			0xB008 /* L3CD Error Status 1 */
+#define HSW_L3CDERRST11			0xB208 /* L3CD Error Status register 1 slice 1 */
 #define   GEN7_L3CDERRST1_ROW_MASK	(0x7ff<<14)
 #define   GEN7_PARITY_ERROR_VALID	(1<<13)
 #define   GEN7_L3CDERRST1_BANK_MASK	(3<<11)
@@ -4756,6 +4762,7 @@
 #define   GEN7_L3CDERRST1_ENABLE	(1<<7)
 
 #define GEN7_L3LOG_BASE			0xB070
+#define HSW_L3LOG_BASE_SLICE1		0xB270
 #define GEN7_L3LOG_SIZE			0x80
 
 #define GEN7_HALF_SLICE_CHICKEN1	0xe100 /* IVB GT1 + VLV */
drivers/gpu/drm/i915/i915_sysfs.c +27 -7
index 71f6de2..3a8bf0c 100644
@@ -119,6 +119,7 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
 	uint32_t misccpctl;
+	int slice = (int)(uintptr_t)attr->private;
 	int i, ret;
 
 	count = round_down(count, 4);
@@ -134,9 +135,9 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 		return ret;
 
 	if (IS_HASWELL(drm_dev)) {
-		if (dev_priv->l3_parity.remap_info)
+		if (dev_priv->l3_parity.remap_info[slice])
 			memcpy(buf,
-			       dev_priv->l3_parity.remap_info + (offset/4),
+			       dev_priv->l3_parity.remap_info[slice] + (offset/4),
 			       count);
 		else
 			memset(buf, 0, count);
@@ -168,6 +169,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
 	u32 *temp = NULL; /* Just here to make handling failures easy */
+	int slice = (int)(uintptr_t)attr->private;
 	int ret;
 
 	ret = l3_access_valid(drm_dev, offset);
@@ -178,7 +180,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
-	if (!dev_priv->l3_parity.remap_info) {
+	if (!dev_priv->l3_parity.remap_info[slice]) {
 		temp = kzalloc(GEN7_L3LOG_SIZE, GFP_KERNEL);
 		if (!temp) {
 			mutex_unlock(&drm_dev->struct_mutex);
@@ -198,11 +200,11 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	 * at this point it is left as a TODO.
 	*/
 	if (temp)
-		dev_priv->l3_parity.remap_info = temp;
+		dev_priv->l3_parity.remap_info[slice] = temp;
 
-	memcpy(dev_priv->l3_parity.remap_info + (offset/4), buf, count);
+	memcpy(dev_priv->l3_parity.remap_info[slice] + (offset/4), buf, count);
 
-	i915_gem_l3_remap(drm_dev);
+	i915_gem_l3_remap(drm_dev, slice);
 
 	mutex_unlock(&drm_dev->struct_mutex);
 
@@ -214,7 +216,17 @@ static struct bin_attribute dpf_attrs = {
 	.size = GEN7_L3LOG_SIZE,
 	.read = i915_l3_read,
 	.write = i915_l3_write,
-	.mmap = NULL
+	.mmap = NULL,
+	.private = (void *)0
+};
+
+static struct bin_attribute dpf_attrs_1 = {
+	.attr = {.name = "l3_parity_slice_1", .mode = (S_IRUSR | S_IWUSR)},
+	.size = GEN7_L3LOG_SIZE,
+	.read = i915_l3_read,
+	.write = i915_l3_write,
+	.mmap = NULL,
+	.private = (void *)1
 };
 
 static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
@@ -525,6 +537,13 @@ void i915_setup_sysfs(struct drm_device *dev)
 		ret = device_create_bin_file(&dev->primary->kdev, &dpf_attrs);
 		if (ret)
 			DRM_ERROR("l3 parity sysfs setup failed\n");
+
+		if (NUM_L3_SLICES(dev) > 1) {
+			ret = device_create_bin_file(&dev->primary->kdev,
+						     &dpf_attrs_1);
+			if (ret)
+				DRM_ERROR("l3 parity slice 1 setup failed\n");
+		}
 	}
 
 	ret = 0;
@@ -548,6 +567,7 @@ void i915_teardown_sysfs(struct drm_device *dev)
 		sysfs_remove_files(&dev->primary->kdev.kobj, vlv_attrs);
 	else
 		sysfs_remove_files(&dev->primary->kdev.kobj, gen6_attrs);
+	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs_1);
 	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs);
 #ifdef CONFIG_PM
 	sysfs_unmerge_group(&dev->primary->kdev.kobj, &rc6_attr_group);
drivers/gpu/drm/i915/intel_ringbuffer.c +3 -4
index 686e5b2..958b7d8 100644
@@ -570,7 +570,7 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
 	if (HAS_L3_GPU_CACHE(dev))
-		I915_WRITE_IMR(ring, ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
+		I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 
 	return ret;
 }
@@ -1000,7 +1000,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring,
 				       ~(ring->irq_enable_mask |
-					 GT_RENDER_L3_PARITY_ERROR_INTERRUPT));
+					 GT_PARITY_ERROR(dev)));
 		else
 			I915_WRITE_IMR(ring, ~ring->irq_enable_mask);
 		ilk_enable_gt_irq(dev_priv, ring->irq_enable_mask);
@@ -1020,8 +1020,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
-			I915_WRITE_IMR(ring,
-				       ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
+			I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 		else
 			I915_WRITE_IMR(ring, ~0);
 		ilk_disable_gt_irq(dev_priv, ring->irq_enable_mask);
include/uapi/drm/i915_drm.h +4 -4
index 55bb572..3a4e97b 100644
@@ -38,10 +38,10 @@
  *
  * I915_L3_PARITY_UEVENT - Generated when the driver receives a parity mismatch
  *	event from the gpu l3 cache. Additional information supplied is ROW,
- *	BANK, SUBBANK of the affected cacheline. Userspace should keep track of
- *	these events and if a specific cache-line seems to have a persistent
- *	error remap it with the l3 remapping tool supplied in intel-gpu-tools.
- *	The value supplied with the event is always 1.
+ *	BANK, SUBBANK, SLICE of the affected cacheline. Userspace should keep
+ *	track of these events and if a specific cache-line seems to have a
+ *	persistent error remap it with the l3 remapping tool supplied in
+ *	intel-gpu-tools.  The value supplied with the event is always 1.
  *
  * I915_ERROR_UEVENT - Generated upon error detection, currently only via
  *	hangcheck. The error detection event is a good indicator of when things
Signature · 1 line
1.8.4
Signature · 2 lines
Ville Syrjälä
Intel OTC
Signature · 5 lines
Ben Widawsky, Intel Open Source Technology Center
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
#4 lore raw

PATCH v3 1/1 drm/i915: Add second slice l3 remapping

In reply to Ville Syrjälä

Certain HSW SKUs have a second bank of L3. This L3 remapping has a separate register set, and interrupt from the first "slice". A slice is simply a term to define some subset of the GPU's l3 cache. This patch implements both the interrupt handler, and ability to communicate with userspace about this second slice.

v2: Remove redundant check about non-existent slice.
Change warning about interrupts of unknown slices to WARN_ON_ONCE Handle the case where we get 2 slice interrupts concurrently, and switch the tracking of interrupts to be non-destructive (all Ville) Don't enable/mask the second slice parity interrupt for ivb/vlv (even though all docs I can find claim it's rsvd) (Ville + Bryan) Keep BYT excluded from L3 parity

v3: Fix the slice = ffs to be decremented by one (found by Ville). When I initially did my testing on the series, I was using 1-based slice counting, so this code was correct. Not sure why my simpler tests that I've been running since then didn't pick it up sooner.

---
 drivers/gpu/drm/i915/i915_drv.h         |  7 ++-
 drivers/gpu/drm/i915/i915_gem.c         | 26 +++++-----
 drivers/gpu/drm/i915/i915_irq.c         | 89 +++++++++++++++++++++------------
 drivers/gpu/drm/i915/i915_reg.h         |  7 +++
 drivers/gpu/drm/i915/i915_sysfs.c       | 34 ++++++++++---
 drivers/gpu/drm/i915/intel_ringbuffer.c |  7 ++-
 include/uapi/drm/i915_drm.h             |  8 +--
 7 files changed, 117 insertions(+), 61 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +5 -2
index 8b16d47..c6e8df7 100644
@@ -917,9 +917,11 @@ struct i915_ums_state {
 	int mm_suspended;
 };
 
+#define MAX_L3_SLICES 2
 struct intel_l3_parity {
-	u32 *remap_info;
+	u32 *remap_info[MAX_L3_SLICES];
 	struct work_struct error_work;
+	int which_slice;
 };
 
 struct i915_gem_mm {
@@ -1686,6 +1688,7 @@ struct drm_i915_file_private {
 #define HAS_FORCE_WAKE(dev) (INTEL_INFO(dev)->has_force_wake)
 
 #define HAS_L3_GPU_CACHE(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
+#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_GPU_CACHE(dev))
 
 #define GT_FREQUENCY_MULTIPLIER 50
 
@@ -1946,7 +1949,7 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
 int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
 int __must_check i915_gem_init(struct drm_device *dev);
 int __must_check i915_gem_init_hw(struct drm_device *dev);
-void i915_gem_l3_remap(struct drm_device *dev);
+void i915_gem_l3_remap(struct drm_device *dev, int slice);
 void i915_gem_init_swizzling(struct drm_device *dev);
 void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
 int __must_check i915_gpu_idle(struct drm_device *dev);
drivers/gpu/drm/i915/i915_gem.c +13 -13
index 3d3de6e..66bf75d 100644
@@ -4252,16 +4252,15 @@ i915_gem_idle(struct drm_device *dev)
 	return 0;
 }
 
-void i915_gem_l3_remap(struct drm_device *dev)
+void i915_gem_l3_remap(struct drm_device *dev, int slice)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
+	u32 reg_base = GEN7_L3LOG_BASE + (slice * 0x200);
+	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
 	u32 misccpctl;
 	int i;
 
-	if (!HAS_L3_GPU_CACHE(dev))
-		return;
-
-	if (!dev_priv->l3_parity.remap_info)
+	if (!HAS_L3_GPU_CACHE(dev) || !remap_info)
 		return;
 
 	misccpctl = I915_READ(GEN7_MISCCPCTL);
@@ -4269,17 +4268,17 @@ void i915_gem_l3_remap(struct drm_device *dev)
 	POSTING_READ(GEN7_MISCCPCTL);
 
 	for (i = 0; i < GEN7_L3LOG_SIZE; i += 4) {
-		u32 remap = I915_READ(GEN7_L3LOG_BASE + i);
-		if (remap && remap != dev_priv->l3_parity.remap_info[i/4])
+		u32 remap = I915_READ(reg_base + i);
+		if (remap && remap != remap_info[i/4])
 			DRM_DEBUG("0x%x was already programmed to %x\n",
-				  GEN7_L3LOG_BASE + i, remap);
-		if (remap && !dev_priv->l3_parity.remap_info[i/4])
+				  reg_base + i, remap);
+		if (remap && !remap_info[i/4])
 			DRM_DEBUG_DRIVER("Clearing remapped register\n");
-		I915_WRITE(GEN7_L3LOG_BASE + i, dev_priv->l3_parity.remap_info[i/4]);
+		I915_WRITE(reg_base + i, remap_info[i/4]);
 	}
 
 	/* Make sure all the writes land before disabling dop clock gating */
-	POSTING_READ(GEN7_L3LOG_BASE);
+	POSTING_READ(reg_base);
 
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 }
@@ -4373,7 +4372,7 @@ int
 i915_gem_init_hw(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	int ret;
+	int ret, i;
 
 	if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
 		return -EIO;
@@ -4392,7 +4391,8 @@ i915_gem_init_hw(struct drm_device *dev)
 		I915_WRITE(GEN7_MSG_CTL, temp);
 	}
 
-	i915_gem_l3_remap(dev);
+	for (i = 0; i < NUM_L3_SLICES(dev); i++)
+		i915_gem_l3_remap(dev, i);
 
 	i915_gem_init_swizzling(dev);
 
drivers/gpu/drm/i915/i915_irq.c +58 -31

137 lines not on this page · raw message

drivers/gpu/drm/i915/i915_reg.h +7 -0
index 384adfb..c94946f 100644
@@ -927,6 +927,7 @@
 #define GT_BLT_USER_INTERRUPT			(1 << 22)
 #define GT_BSD_CS_ERROR_INTERRUPT		(1 << 15)
 #define GT_BSD_USER_INTERRUPT			(1 << 12)
+#define GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1	(1 << 11) /* hsw+; rsvd on snb, ivb, vlv */
 #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT	(1 <<  5) /* !snb */
 #define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT	(1 <<  4)
 #define GT_RENDER_CS_MASTER_ERROR_INTERRUPT	(1 <<  3)
@@ -937,6 +938,10 @@
 #define PM_VEBOX_CS_ERROR_INTERRUPT		(1 << 12) /* hsw+ */
 #define PM_VEBOX_USER_INTERRUPT			(1 << 10) /* hsw+ */
 
+#define GT_PARITY_ERROR(dev) \
+	(GT_RENDER_L3_PARITY_ERROR_INTERRUPT | \
+	 IS_HASWELL(dev) ? GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1 : 0)
+
 /* These are all the "old" interrupts */
 #define ILK_BSD_USER_INTERRUPT				(1<<5)
 #define I915_PIPE_CONTROL_NOTIFY_INTERRUPT		(1<<18)
@@ -4743,6 +4748,7 @@
 
 /* IVYBRIDGE DPF */
 #define GEN7_L3CDERRST1			0xB008 /* L3CD Error Status 1 */
+#define HSW_L3CDERRST11			0xB208 /* L3CD Error Status register 1 slice 1 */
 #define   GEN7_L3CDERRST1_ROW_MASK	(0x7ff<<14)
 #define   GEN7_PARITY_ERROR_VALID	(1<<13)
 #define   GEN7_L3CDERRST1_BANK_MASK	(3<<11)
@@ -4756,6 +4762,7 @@
 #define   GEN7_L3CDERRST1_ENABLE	(1<<7)
 
 #define GEN7_L3LOG_BASE			0xB070
+#define HSW_L3LOG_BASE_SLICE1		0xB270
 #define GEN7_L3LOG_SIZE			0x80
 
 #define GEN7_HALF_SLICE_CHICKEN1	0xe100 /* IVB GT1 + VLV */
drivers/gpu/drm/i915/i915_sysfs.c +27 -7
index 71f6de2..3a8bf0c 100644
@@ -119,6 +119,7 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
 	uint32_t misccpctl;
+	int slice = (int)(uintptr_t)attr->private;
 	int i, ret;
 
 	count = round_down(count, 4);
@@ -134,9 +135,9 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 		return ret;
 
 	if (IS_HASWELL(drm_dev)) {
-		if (dev_priv->l3_parity.remap_info)
+		if (dev_priv->l3_parity.remap_info[slice])
 			memcpy(buf,
-			       dev_priv->l3_parity.remap_info + (offset/4),
+			       dev_priv->l3_parity.remap_info[slice] + (offset/4),
 			       count);
 		else
 			memset(buf, 0, count);
@@ -168,6 +169,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
 	u32 *temp = NULL; /* Just here to make handling failures easy */
+	int slice = (int)(uintptr_t)attr->private;
 	int ret;
 
 	ret = l3_access_valid(drm_dev, offset);
@@ -178,7 +180,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
-	if (!dev_priv->l3_parity.remap_info) {
+	if (!dev_priv->l3_parity.remap_info[slice]) {
 		temp = kzalloc(GEN7_L3LOG_SIZE, GFP_KERNEL);
 		if (!temp) {
 			mutex_unlock(&drm_dev->struct_mutex);
@@ -198,11 +200,11 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	 * at this point it is left as a TODO.
 	*/
 	if (temp)
-		dev_priv->l3_parity.remap_info = temp;
+		dev_priv->l3_parity.remap_info[slice] = temp;
 
-	memcpy(dev_priv->l3_parity.remap_info + (offset/4), buf, count);
+	memcpy(dev_priv->l3_parity.remap_info[slice] + (offset/4), buf, count);
 
-	i915_gem_l3_remap(drm_dev);
+	i915_gem_l3_remap(drm_dev, slice);
 
 	mutex_unlock(&drm_dev->struct_mutex);
 
@@ -214,7 +216,17 @@ static struct bin_attribute dpf_attrs = {
 	.size = GEN7_L3LOG_SIZE,
 	.read = i915_l3_read,
 	.write = i915_l3_write,
-	.mmap = NULL
+	.mmap = NULL,
+	.private = (void *)0
+};
+
+static struct bin_attribute dpf_attrs_1 = {
+	.attr = {.name = "l3_parity_slice_1", .mode = (S_IRUSR | S_IWUSR)},
+	.size = GEN7_L3LOG_SIZE,
+	.read = i915_l3_read,
+	.write = i915_l3_write,
+	.mmap = NULL,
+	.private = (void *)1
 };
 
 static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
@@ -525,6 +537,13 @@ void i915_setup_sysfs(struct drm_device *dev)
 		ret = device_create_bin_file(&dev->primary->kdev, &dpf_attrs);
 		if (ret)
 			DRM_ERROR("l3 parity sysfs setup failed\n");
+
+		if (NUM_L3_SLICES(dev) > 1) {
+			ret = device_create_bin_file(&dev->primary->kdev,
+						     &dpf_attrs_1);
+			if (ret)
+				DRM_ERROR("l3 parity slice 1 setup failed\n");
+		}
 	}
 
 	ret = 0;
@@ -548,6 +567,7 @@ void i915_teardown_sysfs(struct drm_device *dev)
 		sysfs_remove_files(&dev->primary->kdev.kobj, vlv_attrs);
 	else
 		sysfs_remove_files(&dev->primary->kdev.kobj, gen6_attrs);
+	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs_1);
 	device_remove_bin_file(&dev->primary->kdev,  &dpf_attrs);
 #ifdef CONFIG_PM
 	sysfs_unmerge_group(&dev->primary->kdev.kobj, &rc6_attr_group);
drivers/gpu/drm/i915/intel_ringbuffer.c +3 -4
index 686e5b2..958b7d8 100644
@@ -570,7 +570,7 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
 	if (HAS_L3_GPU_CACHE(dev))
-		I915_WRITE_IMR(ring, ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
+		I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 
 	return ret;
 }
@@ -1000,7 +1000,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring,
 				       ~(ring->irq_enable_mask |
-					 GT_RENDER_L3_PARITY_ERROR_INTERRUPT));
+					 GT_PARITY_ERROR(dev)));
 		else
 			I915_WRITE_IMR(ring, ~ring->irq_enable_mask);
 		ilk_enable_gt_irq(dev_priv, ring->irq_enable_mask);
@@ -1020,8 +1020,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
 		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
-			I915_WRITE_IMR(ring,
-				       ~GT_RENDER_L3_PARITY_ERROR_INTERRUPT);
+			I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 		else
 			I915_WRITE_IMR(ring, ~0);
 		ilk_disable_gt_irq(dev_priv, ring->irq_enable_mask);
include/uapi/drm/i915_drm.h +4 -4
index 55bb572..3a4e97b 100644
@@ -38,10 +38,10 @@
  *
  * I915_L3_PARITY_UEVENT - Generated when the driver receives a parity mismatch
  *	event from the gpu l3 cache. Additional information supplied is ROW,
- *	BANK, SUBBANK of the affected cacheline. Userspace should keep track of
- *	these events and if a specific cache-line seems to have a persistent
- *	error remap it with the l3 remapping tool supplied in intel-gpu-tools.
- *	The value supplied with the event is always 1.
+ *	BANK, SUBBANK, SLICE of the affected cacheline. Userspace should keep
+ *	track of these events and if a specific cache-line seems to have a
+ *	persistent error remap it with the l3 remapping tool supplied in
+ *	intel-gpu-tools.  The value supplied with the event is always 1.
  *
  * I915_ERROR_UEVENT - Generated upon error detection, currently only via
  *	hangcheck. The error detection event is a good indicator of when things
Signature · 6 lines
1.8.4

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

PATCH 3/6 drm/i915: Make l3 remapping use the ring

In reply to Ben Widawsky

Using LRI for setting the remapping registers allows us to stream l3 remapping information. This is necessary to handle per context remaps as we'll see implemented in an upcoming patch.

Using the ring also means we don't need to frob the DOP clock gating bits.

v2: Add comment about lack of worry for concurrent register access (Daniel)

---
 drivers/gpu/drm/i915/i915_drv.h   |  2 +-
 drivers/gpu/drm/i915/i915_gem.c   | 38 ++++++++++++++++++--------------------
 drivers/gpu/drm/i915/i915_sysfs.c |  3 ++-
 3 files changed, 21 insertions(+), 22 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +1 -1
index c6e8df7..0c39805 100644
@@ -1949,7 +1949,7 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
 int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
 int __must_check i915_gem_init(struct drm_device *dev);
 int __must_check i915_gem_init_hw(struct drm_device *dev);
-void i915_gem_l3_remap(struct drm_device *dev, int slice);
+int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice);
 void i915_gem_init_swizzling(struct drm_device *dev);
 void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
 int __must_check i915_gpu_idle(struct drm_device *dev);
drivers/gpu/drm/i915/i915_gem.c +18 -20
index 66bf75d..2538138 100644
@@ -4252,35 +4252,33 @@ i915_gem_idle(struct drm_device *dev)
 	return 0;
 }
 
-void i915_gem_l3_remap(struct drm_device *dev, int slice)
+int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice)
 {
+	struct drm_device *dev = ring->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	u32 reg_base = GEN7_L3LOG_BASE + (slice * 0x200);
 	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
-	u32 misccpctl;
-	int i;
+	int i, ret;
 
 	if (!HAS_L3_GPU_CACHE(dev) || !remap_info)
-		return;
+		return 0;
 
-	misccpctl = I915_READ(GEN7_MISCCPCTL);
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
-	POSTING_READ(GEN7_MISCCPCTL);
+	ret = intel_ring_begin(ring, GEN7_L3LOG_SIZE / 4 * 3);
+	if (ret)
+		return ret;
 
+	/* XXX: We do not worry about the concurrent register cacheline hang
+	 * here because no other code should access these registers other than
+	 * at initialization time. */
 	for (i = 0; i < GEN7_L3LOG_SIZE; i += 4) {
-		u32 remap = I915_READ(reg_base + i);
-		if (remap && remap != remap_info[i/4])
-			DRM_DEBUG("0x%x was already programmed to %x\n",
-				  reg_base + i, remap);
-		if (remap && !remap_info[i/4])
-			DRM_DEBUG_DRIVER("Clearing remapped register\n");
-		I915_WRITE(reg_base + i, remap_info[i/4]);
+		intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
+		intel_ring_emit(ring, reg_base + i);
+		intel_ring_emit(ring, remap_info[i/4]);
 	}
 
-	/* Make sure all the writes land before disabling dop clock gating */
-	POSTING_READ(reg_base);
+	intel_ring_advance(ring);
 
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
+	return ret;
 }
 
 void i915_gem_init_swizzling(struct drm_device *dev)
@@ -4391,15 +4389,15 @@ i915_gem_init_hw(struct drm_device *dev)
 		I915_WRITE(GEN7_MSG_CTL, temp);
 	}
 
-	for (i = 0; i < NUM_L3_SLICES(dev); i++)
-		i915_gem_l3_remap(dev, i);
-
 	i915_gem_init_swizzling(dev);
 
 	ret = i915_gem_init_rings(dev);
 	if (ret)
 		return ret;
 
+	for (i = 0; i < NUM_L3_SLICES(dev); i++)
+		i915_gem_l3_remap(&dev_priv->ring[RCS], i);
+
 	/*
 	 * XXX: There was some w/a described somewhere suggesting loading
 	 * contexts before PPGTT.
drivers/gpu/drm/i915/i915_sysfs.c +2 -1
index 3a8bf0c..b07bdfb 100644
@@ -204,7 +204,8 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 
 	memcpy(dev_priv->l3_parity.remap_info[slice] + (offset/4), buf, count);
 
-	i915_gem_l3_remap(drm_dev, slice);
+	if (i915_gem_l3_remap(&dev_priv->ring[RCS], slice))
+		count = 0;
 
 	mutex_unlock(&drm_dev->struct_mutex);
 
Signature · 1 line
1.8.4
#6 lore raw

Re: [PATCH 3/6] drm/i915: Make l3 remapping use the ring

Quoted 11 lines · Ben Widawsky

Using LRI for setting the remapping registers allows us to stream l3 remapping information. This is necessary to handle per context remaps as we'll see implemented in an upcoming patch.

Using the ring also means we don't need to frob the DOP clock gating bits.

v2: Add comment about lack of worry for concurrent register access (Daniel)

I've done a s/XXX/Note on the comment and converted it into the preferred layout for multiline comments.
-Daniel

Quoted 114 lines
---
 drivers/gpu/drm/i915/i915_drv.h   |  2 +-
 drivers/gpu/drm/i915/i915_gem.c   | 38 ++++++++++++++++++--------------------
 drivers/gpu/drm/i915/i915_sysfs.c |  3 ++-
 3 files changed, 21 insertions(+), 22 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +1 -1
index c6e8df7..0c39805 100644
@@ -1949,7 +1949,7 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
 int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
 int __must_check i915_gem_init(struct drm_device *dev);
 int __must_check i915_gem_init_hw(struct drm_device *dev);
-void i915_gem_l3_remap(struct drm_device *dev, int slice);
+int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice);
 void i915_gem_init_swizzling(struct drm_device *dev);
 void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
 int __must_check i915_gpu_idle(struct drm_device *dev);
drivers/gpu/drm/i915/i915_gem.c +18 -20
index 66bf75d..2538138 100644
@@ -4252,35 +4252,33 @@ i915_gem_idle(struct drm_device *dev)
 	return 0;
 }
 
-void i915_gem_l3_remap(struct drm_device *dev, int slice)
+int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice)
 {
+	struct drm_device *dev = ring->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	u32 reg_base = GEN7_L3LOG_BASE + (slice * 0x200);
 	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
-	u32 misccpctl;
-	int i;
+	int i, ret;
 
 	if (!HAS_L3_GPU_CACHE(dev) || !remap_info)
-		return;
+		return 0;
 
-	misccpctl = I915_READ(GEN7_MISCCPCTL);
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
-	POSTING_READ(GEN7_MISCCPCTL);
+	ret = intel_ring_begin(ring, GEN7_L3LOG_SIZE / 4 * 3);
+	if (ret)
+		return ret;
 
+	/* XXX: We do not worry about the concurrent register cacheline hang
+	 * here because no other code should access these registers other than
+	 * at initialization time. */
 	for (i = 0; i < GEN7_L3LOG_SIZE; i += 4) {
-		u32 remap = I915_READ(reg_base + i);
-		if (remap && remap != remap_info[i/4])
-			DRM_DEBUG("0x%x was already programmed to %x\n",
-				  reg_base + i, remap);
-		if (remap && !remap_info[i/4])
-			DRM_DEBUG_DRIVER("Clearing remapped register\n");
-		I915_WRITE(reg_base + i, remap_info[i/4]);
+		intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
+		intel_ring_emit(ring, reg_base + i);
+		intel_ring_emit(ring, remap_info[i/4]);
 	}
 
-	/* Make sure all the writes land before disabling dop clock gating */
-	POSTING_READ(reg_base);
+	intel_ring_advance(ring);
 
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
+	return ret;
 }
 
 void i915_gem_init_swizzling(struct drm_device *dev)
@@ -4391,15 +4389,15 @@ i915_gem_init_hw(struct drm_device *dev)
 		I915_WRITE(GEN7_MSG_CTL, temp);
 	}
 
-	for (i = 0; i < NUM_L3_SLICES(dev); i++)
-		i915_gem_l3_remap(dev, i);
-
 	i915_gem_init_swizzling(dev);
 
 	ret = i915_gem_init_rings(dev);
 	if (ret)
 		return ret;
 
+	for (i = 0; i < NUM_L3_SLICES(dev); i++)
+		i915_gem_l3_remap(&dev_priv->ring[RCS], i);
+
 	/*
 	 * XXX: There was some w/a described somewhere suggesting loading
 	 * contexts before PPGTT.
drivers/gpu/drm/i915/i915_sysfs.c +2 -1
index 3a8bf0c..b07bdfb 100644
@@ -204,7 +204,8 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 
 	memcpy(dev_priv->l3_parity.remap_info[slice] + (offset/4), buf, count);
 
-	i915_gem_l3_remap(drm_dev, slice);
+	if (i915_gem_l3_remap(&dev_priv->ring[RCS], slice))
+		count = 0;
 
 	mutex_unlock(&drm_dev->struct_mutex);
 
Signature · 6 lines
1.8.4

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Signature · 3 lines
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
#7 lore raw

PATCH 4/6 drm/i915: Keep a list of all contexts

In reply to Ben Widawsky

I have implemented this patch before without creating a separate list (I'm having trouble finding the links, but the messages ids are:
<[email protected]> <[email protected]>)

However, the code is much simpler to just use a list and it makes the code from the next patch a lot more pretty.

As you'll see in the next patch, the reason for this is to be able to specify when a context needs to get L3 remapping. More details there.

---
 drivers/gpu/drm/i915/i915_debugfs.c     | 15 +++++++++------
 drivers/gpu/drm/i915/i915_drv.h         |  3 +++
 drivers/gpu/drm/i915/i915_gem.c         |  1 +
 drivers/gpu/drm/i915/i915_gem_context.c |  3 +++
 4 files changed, 16 insertions(+), 6 deletions(-)
drivers/gpu/drm/i915/i915_debugfs.c +9 -6
index 1d77624..ada0950 100644
@@ -1442,6 +1442,7 @@ static int i915_context_status(struct seq_file *m, void *unused)
 	struct drm_device *dev = node->minor->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct intel_ring_buffer *ring;
+	struct i915_hw_context *ctx;
 	int ret, i;
 
 	ret = mutex_lock_interruptible(&dev->mode_config.mutex);
@@ -1460,12 +1461,14 @@ static int i915_context_status(struct seq_file *m, void *unused)
 		seq_putc(m, '\n');
 	}
 
-	for_each_ring(ring, dev_priv, i) {
-		if (ring->default_context) {
-			seq_printf(m, "HW default context %s ", ring->name);
-			describe_obj(m, ring->default_context->obj);
-			seq_putc(m, '\n');
-		}
+	list_for_each_entry(ctx, &dev_priv->context_list, link) {
+		seq_puts(m, "HW context ");
+		for_each_ring(ring, dev_priv, i)
+			if (ring->default_context == ctx)
+				seq_printf(m, "(default context %s) ", ring->name);
+
+		describe_obj(m, ctx->obj);
+		seq_putc(m, '\n');
 	}
 
 	mutex_unlock(&dev->mode_config.mutex);
drivers/gpu/drm/i915/i915_drv.h +3 -0
index 0c39805..1795927 100644
@@ -605,6 +605,8 @@ struct i915_hw_context {
 	struct intel_ring_buffer *ring;
 	struct drm_i915_gem_object *obj;
 	struct i915_ctx_hang_stats hang_stats;
+
+	struct list_head link;
 };
 
 struct i915_fbc {
@@ -1343,6 +1345,7 @@ typedef struct drm_i915_private {
 
 	bool hw_contexts_disabled;
 	uint32_t hw_context_size;
+	struct list_head context_list;
 
 	u32 fdi_rx_config;
 
drivers/gpu/drm/i915/i915_gem.c +1 -0
index 2538138..18d07d7 100644
@@ -4569,6 +4569,7 @@ i915_gem_load(struct drm_device *dev)
 	INIT_LIST_HEAD(&dev_priv->vm_list);
 	i915_init_vm(dev_priv, &dev_priv->gtt.base);
 
+	INIT_LIST_HEAD(&dev_priv->context_list);
 	INIT_LIST_HEAD(&dev_priv->mm.unbound_list);
 	INIT_LIST_HEAD(&dev_priv->mm.bound_list);
 	INIT_LIST_HEAD(&dev_priv->mm.fence_list);
drivers/gpu/drm/i915/i915_gem_context.c +3 -0
index 26c3fcc..2bbdce8 100644
@@ -129,6 +129,7 @@ void i915_gem_context_free(struct kref *ctx_ref)
 	struct i915_hw_context *ctx = container_of(ctx_ref,
 						   typeof(*ctx), ref);
 
+	list_del(&ctx->link);
 	drm_gem_object_unreference(&ctx->obj->base);
 	kfree(ctx);
 }
@@ -147,6 +148,7 @@ create_hw_context(struct drm_device *dev,
 
 	kref_init(&ctx->ref);
 	ctx->obj = i915_gem_alloc_object(dev, dev_priv->hw_context_size);
+	INIT_LIST_HEAD(&ctx->link);
 	if (ctx->obj == NULL) {
 		kfree(ctx);
 		DRM_DEBUG_DRIVER("Context object allocated failed\n");
@@ -166,6 +168,7 @@ create_hw_context(struct drm_device *dev,
 	 * assertion in the context switch code.
 	 */
 	ctx->ring = &dev_priv->ring[RCS];
+	list_add_tail(&ctx->link, &dev_priv->context_list);
 
 	/* Default context will never have a file_priv */
 	if (file_priv == NULL)
Signature · 1 line
1.8.4
#8 lore raw

PATCH 5/6 drm/i915: Do remaps for all contexts

In reply to Ben Widawsky

On both Ivybridge and Haswell, row remapping information is saved and restored with context. This means, we never actually properly supported the l3 remapping because our sysfs interface is asynchronous (and not tied to any context), and the known faulty HW would be reused by the next context to run.

Not that due to the asynchronous nature of the sysfs entry, there is no point modifying the registers for the existing context. Instead we set a flag for all contexts to load the correct remapping information on the next run. Interested clients can use debugfs to determine whether or not the row has been remapped.

One could propose at this point that we just do the remapping in the kernel. I guess since we have to maintain the sysfs interface anyway, I'm not sure how useful it is, and I do like keeping the policy in userspace; (it wasn't my original decision to make the interface the way it is, so I'm not attached).

v2: Force a context switch when we have a remap on the next switch. (Ville)
Don't let userspace use the interface with disabled contexts.

---
 drivers/gpu/drm/i915/i915_debugfs.c     |  8 +++++++
 drivers/gpu/drm/i915/i915_drv.h         |  1 +
 drivers/gpu/drm/i915/i915_gem_context.c | 22 ++++++++++++++++----
 drivers/gpu/drm/i915/i915_sysfs.c       | 37 +++++++++++++--------------------
 4 files changed, 41 insertions(+), 27 deletions(-)
drivers/gpu/drm/i915/i915_debugfs.c +8 -0
index ada0950..80bed69 100644
@@ -145,6 +145,13 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		seq_printf(m, " (%s)", obj->ring->name);
 }
 
+static void describe_ctx(struct seq_file *m, struct i915_hw_context *ctx)
+{
+	seq_putc(m, ctx->is_initialized ? 'I' : 'i');
+	seq_putc(m, ctx->remap_slice ? 'R' : 'r');
+	seq_putc(m, ' ');
+}
+
 static int i915_gem_object_list_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
@@ -1463,6 +1470,7 @@ static int i915_context_status(struct seq_file *m, void *unused)
 
 	list_for_each_entry(ctx, &dev_priv->context_list, link) {
 		seq_puts(m, "HW context ");
+		describe_ctx(m, ctx);
 		for_each_ring(ring, dev_priv, i)
 			if (ring->default_context == ctx)
 				seq_printf(m, "(default context %s) ", ring->name);
drivers/gpu/drm/i915/i915_drv.h +1 -0
index 1795927..015df52 100644
@@ -601,6 +601,7 @@ struct i915_hw_context {
 	struct kref ref;
 	int id;
 	bool is_initialized;
+	uint8_t remap_slice;
 	struct drm_i915_file_private *file_priv;
 	struct intel_ring_buffer *ring;
 	struct drm_i915_gem_object *obj;
drivers/gpu/drm/i915/i915_gem_context.c +18 -4
index 2bbdce8..7e138cc 100644
@@ -140,7 +140,7 @@ create_hw_context(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_hw_context *ctx;
-	int ret;
+	int ret, i;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (ctx == NULL)
@@ -181,6 +181,8 @@ create_hw_context(struct drm_device *dev,
 
 	ctx->file_priv = file_priv;
 	ctx->id = ret;
+	for (i = 0; i < NUM_L3_SLICES(dev); i++)
+		ctx->remap_slice |= 1 << 1;
 
 	return ctx;
 
@@ -396,11 +398,11 @@ static int do_switch(struct i915_hw_context *to)
 	struct intel_ring_buffer *ring = to->ring;
 	struct i915_hw_context *from = ring->last_context;
 	u32 hw_flags = 0;
-	int ret;
+	int ret, i;
 
 	BUG_ON(from != NULL && from->obj != NULL && from->obj->pin_count == 0);
 
-	if (from == to)
+	if (from == to && !to->remap_slice)
 		return 0;
 
 	ret = i915_gem_obj_ggtt_pin(to->obj, CONTEXT_ALIGN, false, false);
@@ -423,7 +425,7 @@ static int do_switch(struct i915_hw_context *to)
 
 	if (!to->is_initialized || is_default_context(to))
 		hw_flags |= MI_RESTORE_INHIBIT;
-	else if (WARN_ON_ONCE(from == to)) /* not yet expected */
+	else if (from == to)
 		hw_flags |= MI_FORCE_RESTORE;
 
 	ret = mi_set_context(ring, to, hw_flags);
@@ -432,6 +434,18 @@ static int do_switch(struct i915_hw_context *to)
 		return ret;
 	}
 
+	for (i = 0; i < MAX_L3_SLICES; i++) {
+		if (!(to->remap_slice & (1<<i)))
+			continue;
+
+		ret = i915_gem_l3_remap(ring, i);
+		if (!ret) {
+			to->remap_slice &= ~(1<<i);
+			/* If it failed, try again next round */
+			DRM_DEBUG_DRIVER("L3 remapping failed\n");
+		}
+	}
+
 	/* The backing object for the context is done after switching to the
 	 * *next* context. Therefore we cannot retire the previous context until
 	 * the next context has already started running. In fact, the below code
drivers/gpu/drm/i915/i915_sysfs.c +14 -23
index b07bdfb..deb8787 100644
@@ -118,9 +118,8 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	struct drm_minor *dminor = container_of(dev, struct drm_minor, kdev);
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
-	uint32_t misccpctl;
 	int slice = (int)(uintptr_t)attr->private;
-	int i, ret;
+	int ret;
 
 	count = round_down(count, 4);
 
@@ -134,26 +133,13 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
-	if (IS_HASWELL(drm_dev)) {
-		if (dev_priv->l3_parity.remap_info[slice])
-			memcpy(buf,
-			       dev_priv->l3_parity.remap_info[slice] + (offset/4),
-			       count);
-		else
-			memset(buf, 0, count);
-
-		goto out;
-	}
-
-	misccpctl = I915_READ(GEN7_MISCCPCTL);
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
-
-	for (i = 0; i < count; i += 4)
-		*((uint32_t *)(&buf[i])) = I915_READ(GEN7_L3LOG_BASE + offset + i);
-
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
+	if (dev_priv->l3_parity.remap_info[slice])
+		memcpy(buf,
+		       dev_priv->l3_parity.remap_info[slice] + (offset/4),
+		       count);
+	else
+		memset(buf, 0, count);
 
-out:
 	mutex_unlock(&drm_dev->struct_mutex);
 
 	return count;
@@ -168,6 +154,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	struct drm_minor *dminor = container_of(dev, struct drm_minor, kdev);
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
+	struct i915_hw_context *ctx;
 	u32 *temp = NULL; /* Just here to make handling failures easy */
 	int slice = (int)(uintptr_t)attr->private;
 	int ret;
@@ -176,6 +163,9 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
+	if (dev_priv->hw_contexts_disabled)
+		return -ENXIO;
+
 	ret = i915_mutex_lock_interruptible(drm_dev);
 	if (ret)
 		return ret;
@@ -204,8 +194,9 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 
 	memcpy(dev_priv->l3_parity.remap_info[slice] + (offset/4), buf, count);
 
-	if (i915_gem_l3_remap(&dev_priv->ring[RCS], slice))
-		count = 0;
+	/* NB: We defer the remapping until we switch to the context */
+	list_for_each_entry(ctx, &dev_priv->context_list, link)
+		ctx->remap_slice |= (1<<slice);
 
 	mutex_unlock(&drm_dev->struct_mutex);
 
Signature · 1 line
1.8.4
#9 lore raw

Re: [PATCH 5/6] drm/i915: Do remaps for all contexts

Quoted 82 lines · Ben Widawsky

On both Ivybridge and Haswell, row remapping information is saved and restored with context. This means, we never actually properly supported the l3 remapping because our sysfs interface is asynchronous (and not tied to any context), and the known faulty HW would be reused by the next context to run.

Not that due to the asynchronous nature of the sysfs entry, there is no point modifying the registers for the existing context. Instead we set a flag for all contexts to load the correct remapping information on the next run. Interested clients can use debugfs to determine whether or not the row has been remapped.

One could propose at this point that we just do the remapping in the kernel. I guess since we have to maintain the sysfs interface anyway, I'm not sure how useful it is, and I do like keeping the policy in userspace; (it wasn't my original decision to make the interface the way it is, so I'm not attached).

v2: Force a context switch when we have a remap on the next switch. (Ville)
Don't let userspace use the interface with disabled contexts.

---
 drivers/gpu/drm/i915/i915_debugfs.c     |  8 +++++++
 drivers/gpu/drm/i915/i915_drv.h         |  1 +
 drivers/gpu/drm/i915/i915_gem_context.c | 22 ++++++++++++++++----
 drivers/gpu/drm/i915/i915_sysfs.c       | 37 +++++++++++++--------------------
 4 files changed, 41 insertions(+), 27 deletions(-)
drivers/gpu/drm/i915/i915_debugfs.c +8 -0
index ada0950..80bed69 100644
@@ -145,6 +145,13 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		seq_printf(m, " (%s)", obj->ring->name);
 }
 
+static void describe_ctx(struct seq_file *m, struct i915_hw_context *ctx)
+{
+	seq_putc(m, ctx->is_initialized ? 'I' : 'i');
+	seq_putc(m, ctx->remap_slice ? 'R' : 'r');
+	seq_putc(m, ' ');
+}
+
 static int i915_gem_object_list_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
@@ -1463,6 +1470,7 @@ static int i915_context_status(struct seq_file *m, void *unused)
 
 	list_for_each_entry(ctx, &dev_priv->context_list, link) {
 		seq_puts(m, "HW context ");
+		describe_ctx(m, ctx);
 		for_each_ring(ring, dev_priv, i)
 			if (ring->default_context == ctx)
 				seq_printf(m, "(default context %s) ", ring->name);
drivers/gpu/drm/i915/i915_drv.h +1 -0
index 1795927..015df52 100644
@@ -601,6 +601,7 @@ struct i915_hw_context {
 	struct kref ref;
 	int id;
 	bool is_initialized;
+	uint8_t remap_slice;
 	struct drm_i915_file_private *file_priv;
 	struct intel_ring_buffer *ring;
 	struct drm_i915_gem_object *obj;
drivers/gpu/drm/i915/i915_gem_context.c +1 -1
index 2bbdce8..7e138cc 100644
@@ -140,7 +140,7 @@ create_hw_context(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_hw_context *ctx;
-	int ret;
+	int ret, i;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (ctx == NULL)

drivers/gpu/drm/i915/i915_gem_context.c create_hw_context(struct drm_device *dev, · line 185

Quoted 5 lines
drivers/gpu/drm/i915/i915_gem_context.c +2 -0
@@ -181,6 +181,8 @@ create_hw_context(struct drm_device *dev,
 
 	ctx->file_priv = file_priv;
 	ctx->id = ret;
+	for (i = 0; i < NUM_L3_SLICES(dev); i++)
+		ctx->remap_slice |= 1 << 1;
                                         ^

Still broken.

Quoted 18 lines
drivers/gpu/drm/i915/i915_gem_context.c +2 -2
 	return ctx;
 
@@ -396,11 +398,11 @@ static int do_switch(struct i915_hw_context *to)
 	struct intel_ring_buffer *ring = to->ring;
 	struct i915_hw_context *from = ring->last_context;
 	u32 hw_flags = 0;
-	int ret;
+	int ret, i;
 
 	BUG_ON(from != NULL && from->obj != NULL && from->obj->pin_count == 0);
 
-	if (from == to)
+	if (from == to && !to->remap_slice)
 		return 0;
 
 	ret = i915_gem_obj_ggtt_pin(to->obj, CONTEXT_ALIGN, false, false);

drivers/gpu/drm/i915/i915_gem_context.c static int do_switch(struct i915_hw_context *to) · line 429

Quoted 6 lines
drivers/gpu/drm/i915/i915_gem_context.c +1 -1
@@ -423,7 +425,7 @@ static int do_switch(struct i915_hw_context *to)
 
 	if (!to->is_initialized || is_default_context(to))
 		hw_flags |= MI_RESTORE_INHIBIT;
-	else if (WARN_ON_ONCE(from == to)) /* not yet expected */
+	else if (from == to)
 		hw_flags |= MI_FORCE_RESTORE;

Hmm. Why do we need to restore actually? Could just leave MI_SET_CONTEXT to be effectively a nop I think.

Quoted 6 lines
drivers/gpu/drm/i915/i915_gem_context.c +0 -0
 	ret = mi_set_context(ring, to, hw_flags);
@@ -432,6 +434,18 @@ static int do_switch(struct i915_hw_context *to)
 		return ret;
 	}
 

drivers/gpu/drm/i915/i915_gem_context.c static int do_switch(struct i915_hw_context *to) · line 446

Quoted 10 lines
drivers/gpu/drm/i915/i915_gem_context.c +10 -0
+	for (i = 0; i < MAX_L3_SLICES; i++) {
+		if (!(to->remap_slice & (1<<i)))
+			continue;
+
+		ret = i915_gem_l3_remap(ring, i);
+		if (!ret) {
+			to->remap_slice &= ~(1<<i);
+			/* If it failed, try again next round */
+			DRM_DEBUG_DRIVER("L3 remapping failed\n");
+		}

The debug message is on the wrong branch.

Quoted 90 lines
drivers/gpu/drm/i915/i915_gem_context.c +2 -0
+	}
+
 	/* The backing object for the context is done after switching to the
 	 * *next* context. Therefore we cannot retire the previous context until
 	 * the next context has already started running. In fact, the below code
drivers/gpu/drm/i915/i915_sysfs.c +14 -23
index b07bdfb..deb8787 100644
@@ -118,9 +118,8 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	struct drm_minor *dminor = container_of(dev, struct drm_minor, kdev);
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
-	uint32_t misccpctl;
 	int slice = (int)(uintptr_t)attr->private;
-	int i, ret;
+	int ret;
 
 	count = round_down(count, 4);
 
@@ -134,26 +133,13 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
-	if (IS_HASWELL(drm_dev)) {
-		if (dev_priv->l3_parity.remap_info[slice])
-			memcpy(buf,
-			       dev_priv->l3_parity.remap_info[slice] + (offset/4),
-			       count);
-		else
-			memset(buf, 0, count);
-
-		goto out;
-	}
-
-	misccpctl = I915_READ(GEN7_MISCCPCTL);
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
-
-	for (i = 0; i < count; i += 4)
-		*((uint32_t *)(&buf[i])) = I915_READ(GEN7_L3LOG_BASE + offset + i);
-
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
+	if (dev_priv->l3_parity.remap_info[slice])
+		memcpy(buf,
+		       dev_priv->l3_parity.remap_info[slice] + (offset/4),
+		       count);
+	else
+		memset(buf, 0, count);
 
-out:
 	mutex_unlock(&drm_dev->struct_mutex);
 
 	return count;
@@ -168,6 +154,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	struct drm_minor *dminor = container_of(dev, struct drm_minor, kdev);
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
+	struct i915_hw_context *ctx;
 	u32 *temp = NULL; /* Just here to make handling failures easy */
 	int slice = (int)(uintptr_t)attr->private;
 	int ret;
@@ -176,6 +163,9 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
+	if (dev_priv->hw_contexts_disabled)
+		return -ENXIO;
+
 	ret = i915_mutex_lock_interruptible(drm_dev);
 	if (ret)
 		return ret;
@@ -204,8 +194,9 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 
 	memcpy(dev_priv->l3_parity.remap_info[slice] + (offset/4), buf, count);
 
-	if (i915_gem_l3_remap(&dev_priv->ring[RCS], slice))
-		count = 0;
+	/* NB: We defer the remapping until we switch to the context */
+	list_for_each_entry(ctx, &dev_priv->context_list, link)
+		ctx->remap_slice |= (1<<slice);
 
 	mutex_unlock(&drm_dev->struct_mutex);
 
Signature · 6 lines
1.8.4

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Signature · 2 lines
Ville Syrjälä
Intel OTC
#10 lore raw

Re: [PATCH 5/6] drm/i915: Do remaps for all contexts

Quoted 84 lines · Ville Syrjälä
Quoted 83 lines · Ben Widawsky

On both Ivybridge and Haswell, row remapping information is saved and restored with context. This means, we never actually properly supported the l3 remapping because our sysfs interface is asynchronous (and not tied to any context), and the known faulty HW would be reused by the next context to run.

Not that due to the asynchronous nature of the sysfs entry, there is no point modifying the registers for the existing context. Instead we set a flag for all contexts to load the correct remapping information on the next run. Interested clients can use debugfs to determine whether or not the row has been remapped.

One could propose at this point that we just do the remapping in the kernel. I guess since we have to maintain the sysfs interface anyway, I'm not sure how useful it is, and I do like keeping the policy in userspace; (it wasn't my original decision to make the interface the way it is, so I'm not attached).

v2: Force a context switch when we have a remap on the next switch. (Ville)
Don't let userspace use the interface with disabled contexts.

---
 drivers/gpu/drm/i915/i915_debugfs.c     |  8 +++++++
 drivers/gpu/drm/i915/i915_drv.h         |  1 +
 drivers/gpu/drm/i915/i915_gem_context.c | 22 ++++++++++++++++----
 drivers/gpu/drm/i915/i915_sysfs.c       | 37 +++++++++++++--------------------
 4 files changed, 41 insertions(+), 27 deletions(-)
drivers/gpu/drm/i915/i915_debugfs.c +8 -0
index ada0950..80bed69 100644
@@ -145,6 +145,13 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		seq_printf(m, " (%s)", obj->ring->name);
 }
 
+static void describe_ctx(struct seq_file *m, struct i915_hw_context *ctx)
+{
+	seq_putc(m, ctx->is_initialized ? 'I' : 'i');
+	seq_putc(m, ctx->remap_slice ? 'R' : 'r');
+	seq_putc(m, ' ');
+}
+
 static int i915_gem_object_list_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
@@ -1463,6 +1470,7 @@ static int i915_context_status(struct seq_file *m, void *unused)
 
 	list_for_each_entry(ctx, &dev_priv->context_list, link) {
 		seq_puts(m, "HW context ");
+		describe_ctx(m, ctx);
 		for_each_ring(ring, dev_priv, i)
 			if (ring->default_context == ctx)
 				seq_printf(m, "(default context %s) ", ring->name);
drivers/gpu/drm/i915/i915_drv.h +1 -0
index 1795927..015df52 100644
@@ -601,6 +601,7 @@ struct i915_hw_context {
 	struct kref ref;
 	int id;
 	bool is_initialized;
+	uint8_t remap_slice;
 	struct drm_i915_file_private *file_priv;
 	struct intel_ring_buffer *ring;
 	struct drm_i915_gem_object *obj;
drivers/gpu/drm/i915/i915_gem_context.c +1 -1
index 2bbdce8..7e138cc 100644
@@ -140,7 +140,7 @@ create_hw_context(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_hw_context *ctx;
-	int ret;
+	int ret, i;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (ctx == NULL)
@@ -181,6 +181,8 @@ create_hw_context(struct drm_device *dev,
 
Quoted 7 lines

drivers/gpu/drm/i915/i915_gem_context.c create_hw_context(struct drm_device *dev, · line 185

Quoted 4 lines
drivers/gpu/drm/i915/i915_gem_context.c +2 -0
 	ctx->file_priv = file_priv;
 	ctx->id = ret;
+	for (i = 0; i < NUM_L3_SLICES(dev); i++)
+		ctx->remap_slice |= 1 << 1;
                                         ^

Still broken.

Or maybe I wanted it to always be the second slice!

Quoted 20 lines
Quoted 20 lines
drivers/gpu/drm/i915/i915_gem_context.c +2 -2
 	return ctx;
 
@@ -396,11 +398,11 @@ static int do_switch(struct i915_hw_context *to)
 	struct intel_ring_buffer *ring = to->ring;
 	struct i915_hw_context *from = ring->last_context;
 	u32 hw_flags = 0;
-	int ret;
+	int ret, i;
 
 	BUG_ON(from != NULL && from->obj != NULL && from->obj->pin_count == 0);
 
-	if (from == to)
+	if (from == to && !to->remap_slice)
 		return 0;
 
 	ret = i915_gem_obj_ggtt_pin(to->obj, CONTEXT_ALIGN, false, false);
@@ -423,7 +425,7 @@ static int do_switch(struct i915_hw_context *to)
 
Quoted 8 lines

drivers/gpu/drm/i915/i915_gem_context.c static int do_switch(struct i915_hw_context *to) · line 429

Quoted 5 lines
drivers/gpu/drm/i915/i915_gem_context.c +1 -1
 	if (!to->is_initialized || is_default_context(to))
 		hw_flags |= MI_RESTORE_INHIBIT;
-	else if (WARN_ON_ONCE(from == to)) /* not yet expected */
+	else if (from == to)
 		hw_flags |= MI_FORCE_RESTORE;

Hmm. Why do we need to restore actually? Could just leave MI_SET_CONTEXT to be effectively a nop I think.

I don't think so. You need it to restore the register, which I think it won't do unless you issue a force restore, I am just guessing.

Quoted 7 lines
Quoted 7 lines
drivers/gpu/drm/i915/i915_gem_context.c +0 -0
 	ret = mi_set_context(ring, to, hw_flags);
@@ -432,6 +434,18 @@ static int do_switch(struct i915_hw_context *to)
 		return ret;
 	}
 
Quoted 13 lines

drivers/gpu/drm/i915/i915_gem_context.c static int do_switch(struct i915_hw_context *to) · line 446

Quoted 10 lines
drivers/gpu/drm/i915/i915_gem_context.c +10 -0
+	for (i = 0; i < MAX_L3_SLICES; i++) {
+		if (!(to->remap_slice & (1<<i)))
+			continue;
+
+		ret = i915_gem_l3_remap(ring, i);
+		if (!ret) {
+			to->remap_slice &= ~(1<<i);
+			/* If it failed, try again next round */
+			DRM_DEBUG_DRIVER("L3 remapping failed\n");
+		}

The debug message is on the wrong branch.

And maybe I wanted the user to THINK it failed when it didn't; so they'll be pleasantly surprised.

Quoted 94 lines
Quoted 90 lines
drivers/gpu/drm/i915/i915_gem_context.c +2 -0
+	}
+
 	/* The backing object for the context is done after switching to the
 	 * *next* context. Therefore we cannot retire the previous context until
 	 * the next context has already started running. In fact, the below code
drivers/gpu/drm/i915/i915_sysfs.c +14 -23
index b07bdfb..deb8787 100644
@@ -118,9 +118,8 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	struct drm_minor *dminor = container_of(dev, struct drm_minor, kdev);
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
-	uint32_t misccpctl;
 	int slice = (int)(uintptr_t)attr->private;
-	int i, ret;
+	int ret;
 
 	count = round_down(count, 4);
 
@@ -134,26 +133,13 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
-	if (IS_HASWELL(drm_dev)) {
-		if (dev_priv->l3_parity.remap_info[slice])
-			memcpy(buf,
-			       dev_priv->l3_parity.remap_info[slice] + (offset/4),
-			       count);
-		else
-			memset(buf, 0, count);
-
-		goto out;
-	}
-
-	misccpctl = I915_READ(GEN7_MISCCPCTL);
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
-
-	for (i = 0; i < count; i += 4)
-		*((uint32_t *)(&buf[i])) = I915_READ(GEN7_L3LOG_BASE + offset + i);
-
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
+	if (dev_priv->l3_parity.remap_info[slice])
+		memcpy(buf,
+		       dev_priv->l3_parity.remap_info[slice] + (offset/4),
+		       count);
+	else
+		memset(buf, 0, count);
 
-out:
 	mutex_unlock(&drm_dev->struct_mutex);
 
 	return count;
@@ -168,6 +154,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	struct drm_minor *dminor = container_of(dev, struct drm_minor, kdev);
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
+	struct i915_hw_context *ctx;
 	u32 *temp = NULL; /* Just here to make handling failures easy */
 	int slice = (int)(uintptr_t)attr->private;
 	int ret;
@@ -176,6 +163,9 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
+	if (dev_priv->hw_contexts_disabled)
+		return -ENXIO;
+
 	ret = i915_mutex_lock_interruptible(drm_dev);
 	if (ret)
 		return ret;
@@ -204,8 +194,9 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 
 	memcpy(dev_priv->l3_parity.remap_info[slice] + (offset/4), buf, count);
 
-	if (i915_gem_l3_remap(&dev_priv->ring[RCS], slice))
-		count = 0;
+	/* NB: We defer the remapping until we switch to the context */
+	list_for_each_entry(ctx, &dev_priv->context_list, link)
+		ctx->remap_slice |= (1<<slice);
 
 	mutex_unlock(&drm_dev->struct_mutex);
 
Signature · 6 lines
1.8.4

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Signature · 2 lines
Ville Syrjälä
Intel OTC
Signature · 5 lines
Ben Widawsky, Intel Open Source Technology Center
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
#11 lore raw

Re: [PATCH 5/6] drm/i915: Do remaps for all contexts

Quoted 124 lines · Ben Widawsky
Quoted 84 lines · Ville Syrjälä
Quoted 83 lines · Ben Widawsky

On both Ivybridge and Haswell, row remapping information is saved and restored with context. This means, we never actually properly supported the l3 remapping because our sysfs interface is asynchronous (and not tied to any context), and the known faulty HW would be reused by the next context to run.

Not that due to the asynchronous nature of the sysfs entry, there is no point modifying the registers for the existing context. Instead we set a flag for all contexts to load the correct remapping information on the next run. Interested clients can use debugfs to determine whether or not the row has been remapped.

One could propose at this point that we just do the remapping in the kernel. I guess since we have to maintain the sysfs interface anyway, I'm not sure how useful it is, and I do like keeping the policy in userspace; (it wasn't my original decision to make the interface the way it is, so I'm not attached).

v2: Force a context switch when we have a remap on the next switch. (Ville)
Don't let userspace use the interface with disabled contexts.

---
 drivers/gpu/drm/i915/i915_debugfs.c     |  8 +++++++
 drivers/gpu/drm/i915/i915_drv.h         |  1 +
 drivers/gpu/drm/i915/i915_gem_context.c | 22 ++++++++++++++++----
 drivers/gpu/drm/i915/i915_sysfs.c       | 37 +++++++++++++--------------------
 4 files changed, 41 insertions(+), 27 deletions(-)
drivers/gpu/drm/i915/i915_debugfs.c +8 -0
index ada0950..80bed69 100644
@@ -145,6 +145,13 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		seq_printf(m, " (%s)", obj->ring->name);
 }
 
+static void describe_ctx(struct seq_file *m, struct i915_hw_context *ctx)
+{
+	seq_putc(m, ctx->is_initialized ? 'I' : 'i');
+	seq_putc(m, ctx->remap_slice ? 'R' : 'r');
+	seq_putc(m, ' ');
+}
+
 static int i915_gem_object_list_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
@@ -1463,6 +1470,7 @@ static int i915_context_status(struct seq_file *m, void *unused)
 
 	list_for_each_entry(ctx, &dev_priv->context_list, link) {
 		seq_puts(m, "HW context ");
+		describe_ctx(m, ctx);
 		for_each_ring(ring, dev_priv, i)
 			if (ring->default_context == ctx)
 				seq_printf(m, "(default context %s) ", ring->name);
drivers/gpu/drm/i915/i915_drv.h +1 -0
index 1795927..015df52 100644
@@ -601,6 +601,7 @@ struct i915_hw_context {
 	struct kref ref;
 	int id;
 	bool is_initialized;
+	uint8_t remap_slice;
 	struct drm_i915_file_private *file_priv;
 	struct intel_ring_buffer *ring;
 	struct drm_i915_gem_object *obj;
drivers/gpu/drm/i915/i915_gem_context.c +1 -1
index 2bbdce8..7e138cc 100644
@@ -140,7 +140,7 @@ create_hw_context(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_hw_context *ctx;
-	int ret;
+	int ret, i;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (ctx == NULL)
@@ -181,6 +181,8 @@ create_hw_context(struct drm_device *dev,
 
Quoted 7 lines

drivers/gpu/drm/i915/i915_gem_context.c create_hw_context(struct drm_device *dev, · line 185

Quoted 4 lines
drivers/gpu/drm/i915/i915_gem_context.c +2 -0
 	ctx->file_priv = file_priv;
 	ctx->id = ret;
+	for (i = 0; i < NUM_L3_SLICES(dev); i++)
+		ctx->remap_slice |= 1 << 1;
                                         ^

Still broken.

Or maybe I wanted it to always be the second slice!

Quoted 20 lines
Quoted 20 lines
drivers/gpu/drm/i915/i915_gem_context.c +2 -2
 	return ctx;
 
@@ -396,11 +398,11 @@ static int do_switch(struct i915_hw_context *to)
 	struct intel_ring_buffer *ring = to->ring;
 	struct i915_hw_context *from = ring->last_context;
 	u32 hw_flags = 0;
-	int ret;
+	int ret, i;
 
 	BUG_ON(from != NULL && from->obj != NULL && from->obj->pin_count == 0);
 
-	if (from == to)
+	if (from == to && !to->remap_slice)
 		return 0;
 
 	ret = i915_gem_obj_ggtt_pin(to->obj, CONTEXT_ALIGN, false, false);
@@ -423,7 +425,7 @@ static int do_switch(struct i915_hw_context *to)
 
Quoted 8 lines

drivers/gpu/drm/i915/i915_gem_context.c static int do_switch(struct i915_hw_context *to) · line 429

Quoted 5 lines
drivers/gpu/drm/i915/i915_gem_context.c +1 -1
 	if (!to->is_initialized || is_default_context(to))
 		hw_flags |= MI_RESTORE_INHIBIT;
-	else if (WARN_ON_ONCE(from == to)) /* not yet expected */
+	else if (from == to)
 		hw_flags |= MI_FORCE_RESTORE;

Hmm. Why do we need to restore actually? Could just leave MI_SET_CONTEXT to be effectively a nop I think.

Quoted 3 lines

I don't think so. You need it to restore the register, which I think it won't do unless you issue a force restore, I am just guessing.

I should really think a bit before I type. That isn't right - when I wrote this, I was still thinking we were using MMIO, which we're not.

In other words, you're right. All 3 fixes coming right up.

Quoted 121 lines
Quoted 7 lines
Quoted 7 lines
drivers/gpu/drm/i915/i915_gem_context.c +0 -0
 	ret = mi_set_context(ring, to, hw_flags);
@@ -432,6 +434,18 @@ static int do_switch(struct i915_hw_context *to)
 		return ret;
 	}
 
Quoted 13 lines

drivers/gpu/drm/i915/i915_gem_context.c static int do_switch(struct i915_hw_context *to) · line 446

Quoted 10 lines
drivers/gpu/drm/i915/i915_gem_context.c +10 -0
+	for (i = 0; i < MAX_L3_SLICES; i++) {
+		if (!(to->remap_slice & (1<<i)))
+			continue;
+
+		ret = i915_gem_l3_remap(ring, i);
+		if (!ret) {
+			to->remap_slice &= ~(1<<i);
+			/* If it failed, try again next round */
+			DRM_DEBUG_DRIVER("L3 remapping failed\n");
+		}

The debug message is on the wrong branch.

And maybe I wanted the user to THINK it failed when it didn't; so they'll be pleasantly surprised.

Quoted 94 lines
Quoted 90 lines
drivers/gpu/drm/i915/i915_gem_context.c +2 -0
+	}
+
 	/* The backing object for the context is done after switching to the
 	 * *next* context. Therefore we cannot retire the previous context until
 	 * the next context has already started running. In fact, the below code
drivers/gpu/drm/i915/i915_sysfs.c +14 -23
index b07bdfb..deb8787 100644
@@ -118,9 +118,8 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	struct drm_minor *dminor = container_of(dev, struct drm_minor, kdev);
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
-	uint32_t misccpctl;
 	int slice = (int)(uintptr_t)attr->private;
-	int i, ret;
+	int ret;
 
 	count = round_down(count, 4);
 
@@ -134,26 +133,13 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
-	if (IS_HASWELL(drm_dev)) {
-		if (dev_priv->l3_parity.remap_info[slice])
-			memcpy(buf,
-			       dev_priv->l3_parity.remap_info[slice] + (offset/4),
-			       count);
-		else
-			memset(buf, 0, count);
-
-		goto out;
-	}
-
-	misccpctl = I915_READ(GEN7_MISCCPCTL);
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
-
-	for (i = 0; i < count; i += 4)
-		*((uint32_t *)(&buf[i])) = I915_READ(GEN7_L3LOG_BASE + offset + i);
-
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
+	if (dev_priv->l3_parity.remap_info[slice])
+		memcpy(buf,
+		       dev_priv->l3_parity.remap_info[slice] + (offset/4),
+		       count);
+	else
+		memset(buf, 0, count);
 
-out:
 	mutex_unlock(&drm_dev->struct_mutex);
 
 	return count;
@@ -168,6 +154,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	struct drm_minor *dminor = container_of(dev, struct drm_minor, kdev);
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
+	struct i915_hw_context *ctx;
 	u32 *temp = NULL; /* Just here to make handling failures easy */
 	int slice = (int)(uintptr_t)attr->private;
 	int ret;
@@ -176,6 +163,9 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
+	if (dev_priv->hw_contexts_disabled)
+		return -ENXIO;
+
 	ret = i915_mutex_lock_interruptible(drm_dev);
 	if (ret)
 		return ret;
@@ -204,8 +194,9 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 
 	memcpy(dev_priv->l3_parity.remap_info[slice] + (offset/4), buf, count);
 
-	if (i915_gem_l3_remap(&dev_priv->ring[RCS], slice))
-		count = 0;
+	/* NB: We defer the remapping until we switch to the context */
+	list_for_each_entry(ctx, &dev_priv->context_list, link)
+		ctx->remap_slice |= (1<<slice);
 
 	mutex_unlock(&drm_dev->struct_mutex);
 
Signature · 6 lines
1.8.4

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Signature · 2 lines
Ville Syrjälä
Intel OTC
Signature · 1 line
Ben Widawsky, Intel Open Source Technology Center
Signature · 5 lines
Ben Widawsky, Intel Open Source Technology Center
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
#12 lore raw

PATCH v3 1/1 drm/i915: Do remaps for all contexts

In reply to Ville Syrjälä

On both Ivybridge and Haswell, row remapping information is saved and restored with context. This means, we never actually properly supported the l3 remapping because our sysfs interface is asynchronous (and not tied to any context), and the known faulty HW would be reused by the next context to run.

Not that due to the asynchronous nature of the sysfs entry, there is no point modifying the registers for the existing context. Instead we set a flag for all contexts to load the correct remapping information on the next run. Interested clients can use debugfs to determine whether or not the row has been remapped.

One could propose at this point that we just do the remapping in the kernel. I guess since we have to maintain the sysfs interface anyway, I'm not sure how useful it is, and I do like keeping the policy in userspace; (it wasn't my original decision to make the interface the way it is, so I'm not attached).

v2: Force a context switch when we have a remap on the next switch. (Ville)
Don't let userspace use the interface with disabled contexts.

v3: Don't force a context switch, just let it nop
Improper context slice remap initialization, 1<<1 instead of 1<<i, but I rewrote it to avoid a second round of confusion.
Error print moved to error path (All Ville)
Added a comment on why the slice remap initialization happens.

CC Ville Syrjälä <[email protected]>
---
 drivers/gpu/drm/i915/i915_debugfs.c     |  8 +++++++
 drivers/gpu/drm/i915/i915_drv.h         |  1 +
 drivers/gpu/drm/i915/i915_gem_context.c | 22 ++++++++++++++++----
 drivers/gpu/drm/i915/i915_sysfs.c       | 37 +++++++++++++--------------------
 4 files changed, 41 insertions(+), 27 deletions(-)
drivers/gpu/drm/i915/i915_debugfs.c +8 -0
index ada0950..80bed69 100644
@@ -145,6 +145,13 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		seq_printf(m, " (%s)", obj->ring->name);
 }
 
+static void describe_ctx(struct seq_file *m, struct i915_hw_context *ctx)
+{
+	seq_putc(m, ctx->is_initialized ? 'I' : 'i');
+	seq_putc(m, ctx->remap_slice ? 'R' : 'r');
+	seq_putc(m, ' ');
+}
+
 static int i915_gem_object_list_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
@@ -1463,6 +1470,7 @@ static int i915_context_status(struct seq_file *m, void *unused)
 
 	list_for_each_entry(ctx, &dev_priv->context_list, link) {
 		seq_puts(m, "HW context ");
+		describe_ctx(m, ctx);
 		for_each_ring(ring, dev_priv, i)
 			if (ring->default_context == ctx)
 				seq_printf(m, "(default context %s) ", ring->name);
drivers/gpu/drm/i915/i915_drv.h +1 -0
index 1795927..015df52 100644
@@ -601,6 +601,7 @@ struct i915_hw_context {
 	struct kref ref;
 	int id;
 	bool is_initialized;
+	uint8_t remap_slice;
 	struct drm_i915_file_private *file_priv;
 	struct intel_ring_buffer *ring;
 	struct drm_i915_gem_object *obj;
drivers/gpu/drm/i915/i915_gem_context.c +18 -4
index 2bbdce8..9af3fe7 100644
@@ -181,6 +181,10 @@ create_hw_context(struct drm_device *dev,
 
 	ctx->file_priv = file_priv;
 	ctx->id = ret;
+	/* NB: Mark all slices as needing a remap so that when the context first
+	 * loads it will restore whatever remap state already exists. If there
+	 * is no remap info, it will be a NOP. */
+	ctx->remap_slice = (1 << NUM_L3_SLICES(dev)) - 1;
 
 	return ctx;
 
@@ -396,11 +400,11 @@ static int do_switch(struct i915_hw_context *to)
 	struct intel_ring_buffer *ring = to->ring;
 	struct i915_hw_context *from = ring->last_context;
 	u32 hw_flags = 0;
-	int ret;
+	int ret, i;
 
 	BUG_ON(from != NULL && from->obj != NULL && from->obj->pin_count == 0);
 
-	if (from == to)
+	if (from == to && !to->remap_slice)
 		return 0;
 
 	ret = i915_gem_obj_ggtt_pin(to->obj, CONTEXT_ALIGN, false, false);
@@ -423,8 +427,6 @@ static int do_switch(struct i915_hw_context *to)
 
 	if (!to->is_initialized || is_default_context(to))
 		hw_flags |= MI_RESTORE_INHIBIT;
-	else if (WARN_ON_ONCE(from == to)) /* not yet expected */
-		hw_flags |= MI_FORCE_RESTORE;
 
 	ret = mi_set_context(ring, to, hw_flags);
 	if (ret) {
@@ -432,6 +434,18 @@ static int do_switch(struct i915_hw_context *to)
 		return ret;
 	}
 
+	for (i = 0; i < MAX_L3_SLICES; i++) {
+		if (!(to->remap_slice & (1<<i)))
+			continue;
+
+		ret = i915_gem_l3_remap(ring, i);
+		/* If it failed, try again next round */
+		if (ret)
+			DRM_DEBUG_DRIVER("L3 remapping failed\n");
+		else
+			to->remap_slice &= ~(1<<i);
+	}
+
 	/* The backing object for the context is done after switching to the
 	 * *next* context. Therefore we cannot retire the previous context until
 	 * the next context has already started running. In fact, the below code
drivers/gpu/drm/i915/i915_sysfs.c +14 -23
index b07bdfb..deb8787 100644
@@ -118,9 +118,8 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	struct drm_minor *dminor = container_of(dev, struct drm_minor, kdev);
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
-	uint32_t misccpctl;
 	int slice = (int)(uintptr_t)attr->private;
-	int i, ret;
+	int ret;
 
 	count = round_down(count, 4);
 
@@ -134,26 +133,13 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
-	if (IS_HASWELL(drm_dev)) {
-		if (dev_priv->l3_parity.remap_info[slice])
-			memcpy(buf,
-			       dev_priv->l3_parity.remap_info[slice] + (offset/4),
-			       count);
-		else
-			memset(buf, 0, count);
-
-		goto out;
-	}
-
-	misccpctl = I915_READ(GEN7_MISCCPCTL);
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
-
-	for (i = 0; i < count; i += 4)
-		*((uint32_t *)(&buf[i])) = I915_READ(GEN7_L3LOG_BASE + offset + i);
-
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
+	if (dev_priv->l3_parity.remap_info[slice])
+		memcpy(buf,
+		       dev_priv->l3_parity.remap_info[slice] + (offset/4),
+		       count);
+	else
+		memset(buf, 0, count);
 
-out:
 	mutex_unlock(&drm_dev->struct_mutex);
 
 	return count;
@@ -168,6 +154,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	struct drm_minor *dminor = container_of(dev, struct drm_minor, kdev);
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
+	struct i915_hw_context *ctx;
 	u32 *temp = NULL; /* Just here to make handling failures easy */
 	int slice = (int)(uintptr_t)attr->private;
 	int ret;
@@ -176,6 +163,9 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	if (ret)
 		return ret;
 
+	if (dev_priv->hw_contexts_disabled)
+		return -ENXIO;
+
 	ret = i915_mutex_lock_interruptible(drm_dev);
 	if (ret)
 		return ret;
@@ -204,8 +194,9 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 
 	memcpy(dev_priv->l3_parity.remap_info[slice] + (offset/4), buf, count);
 
-	if (i915_gem_l3_remap(&dev_priv->ring[RCS], slice))
-		count = 0;
+	/* NB: We defer the remapping until we switch to the context */
+	list_for_each_entry(ctx, &dev_priv->context_list, link)
+		ctx->remap_slice |= (1<<slice);
 
 	mutex_unlock(&drm_dev->struct_mutex);
 
Signature · 6 lines
1.8.4

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

PATCH 6/6 drm/i915: s/HAS_L3_GPU_CACHE/HAS_L3_DPF

In reply to Ben Widawsky

We'd only ever used this define to denote whether or not we have the dynamic parity feature (DPF) and never to determine whether or not L3 exists. Baytrail is a good example of where L3 exists, and not DPF.

This patch provides clarify in the code for future use cases which might want to actually query whether or not L3 exists.

---
 drivers/gpu/drm/i915/i915_drv.h         | 4 ++--
 drivers/gpu/drm/i915/i915_gem.c         | 2 +-
 drivers/gpu/drm/i915/i915_irq.c         | 4 ++--
 drivers/gpu/drm/i915/i915_sysfs.c       | 4 ++--
 drivers/gpu/drm/i915/intel_ringbuffer.c | 6 +++---
 5 files changed, 10 insertions(+), 10 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +2 -2
index 015df52..dd2753e 100644
@@ -1691,8 +1691,8 @@ struct drm_i915_file_private {
 
 #define HAS_FORCE_WAKE(dev) (INTEL_INFO(dev)->has_force_wake)
 
-#define HAS_L3_GPU_CACHE(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
-#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_GPU_CACHE(dev))
+#define HAS_L3_DPF(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
+#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_DPF(dev))
 
 #define GT_FREQUENCY_MULTIPLIER 50
 
drivers/gpu/drm/i915/i915_gem.c +1 -1
index 18d07d7..7859f91 100644
@@ -4260,7 +4260,7 @@ int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice)
 	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
 	int i, ret;
 
-	if (!HAS_L3_GPU_CACHE(dev) || !remap_info)
+	if (!HAS_L3_DPF(dev) || !remap_info)
 		return 0;
 
 	ret = intel_ring_begin(ring, GEN7_L3LOG_SIZE / 4 * 3);
drivers/gpu/drm/i915/i915_irq.c +2 -2
index b11ee39..0968c98 100644
@@ -959,7 +959,7 @@ static void ivybridge_parity_error_irq_handler(struct drm_device *dev, u32 iir)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 
-	if (!HAS_L3_GPU_CACHE(dev))
+	if (!HAS_L3_DPF(dev))
 		return;
 
 	spin_lock(&dev_priv->irq_lock);
@@ -2291,7 +2291,7 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev)
 	pm_irqs = gt_irqs = 0;
 
 	dev_priv->gt_irq_mask = ~0;
-	if (HAS_L3_GPU_CACHE(dev)) {
+	if (HAS_L3_DPF(dev)) {
 		/* L3 parity interrupt is always unmasked. */
 		dev_priv->gt_irq_mask = ~GT_PARITY_ERROR(dev);
 		gt_irqs |= GT_PARITY_ERROR(dev);
drivers/gpu/drm/i915/i915_sysfs.c +2 -2
index deb8787..7b4c79c 100644
@@ -97,7 +97,7 @@ static struct attribute_group rc6_attr_group = {
 
 static int l3_access_valid(struct drm_device *dev, loff_t offset)
 {
-	if (!HAS_L3_GPU_CACHE(dev))
+	if (!HAS_L3_DPF(dev))
 		return -EPERM;
 
 	if (offset % 4 != 0)
@@ -525,7 +525,7 @@ void i915_setup_sysfs(struct drm_device *dev)
 			DRM_ERROR("RC6 residency sysfs setup failed\n");
 	}
 #endif
-	if (HAS_L3_GPU_CACHE(dev)) {
+	if (HAS_L3_DPF(dev)) {
 		ret = device_create_bin_file(&dev->primary->kdev, &dpf_attrs);
 		if (ret)
 			DRM_ERROR("l3 parity sysfs setup failed\n");
drivers/gpu/drm/i915/intel_ringbuffer.c +3 -3
index 958b7d8..b67104a 100644
@@ -569,7 +569,7 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 	if (INTEL_INFO(dev)->gen >= 6)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
-	if (HAS_L3_GPU_CACHE(dev))
+	if (HAS_L3_DPF(dev))
 		I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 
 	return ret;
@@ -997,7 +997,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (ring->irq_refcount++ == 0) {
-		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
+		if (HAS_L3_DPF(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring,
 				       ~(ring->irq_enable_mask |
 					 GT_PARITY_ERROR(dev)));
@@ -1019,7 +1019,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
-		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
+		if (HAS_L3_DPF(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 		else
 			I915_WRITE_IMR(ring, ~0);
Signature · 1 line
1.8.4
Reviewed-by on v1 6/6
#14 lore raw

Re: [PATCH 6/6] drm/i915: s/HAS_L3_GPU_CACHE/HAS_L3_DPF

Quoted 21 lines · Ben Widawsky

We'd only ever used this define to denote whether or not we have the dynamic parity feature (DPF) and never to determine whether or not L3 exists. Baytrail is a good example of where L3 exists, and not DPF.

This patch provides clarify in the code for future use cases which might want to actually query whether or not L3 exists.

---
 drivers/gpu/drm/i915/i915_drv.h         | 4 ++--
 drivers/gpu/drm/i915/i915_gem.c         | 2 +-
 drivers/gpu/drm/i915/i915_irq.c         | 4 ++--
 drivers/gpu/drm/i915/i915_sysfs.c       | 4 ++--
 drivers/gpu/drm/i915/intel_ringbuffer.c | 6 +++---
 5 files changed, 10 insertions(+), 10 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +0 -0
index 015df52..dd2753e 100644

drivers/gpu/drm/i915/i915_drv.h struct drm_i915_file_private { · line 1695

Quoted 7 lines
drivers/gpu/drm/i915/i915_drv.h +2 -2
@@ -1691,8 +1691,8 @@ struct drm_i915_file_private {
 
 #define HAS_FORCE_WAKE(dev) (INTEL_INFO(dev)->has_force_wake)
 
-#define HAS_L3_GPU_CACHE(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
-#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_GPU_CACHE(dev))
+#define HAS_L3_DPF(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
+#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_DPF(dev))

Maybe add a comment saying /* DPF == dynamic parity feature */

Otherwise:

Quoted 98 lines
drivers/gpu/drm/i915/i915_drv.h +0 -0
 #define GT_FREQUENCY_MULTIPLIER 50
 
drivers/gpu/drm/i915/i915_gem.c +1 -1
index 18d07d7..7859f91 100644
@@ -4260,7 +4260,7 @@ int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice)
 	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
 	int i, ret;
 
-	if (!HAS_L3_GPU_CACHE(dev) || !remap_info)
+	if (!HAS_L3_DPF(dev) || !remap_info)
 		return 0;
 
 	ret = intel_ring_begin(ring, GEN7_L3LOG_SIZE / 4 * 3);
drivers/gpu/drm/i915/i915_irq.c +2 -2
index b11ee39..0968c98 100644
@@ -959,7 +959,7 @@ static void ivybridge_parity_error_irq_handler(struct drm_device *dev, u32 iir)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 
-	if (!HAS_L3_GPU_CACHE(dev))
+	if (!HAS_L3_DPF(dev))
 		return;
 
 	spin_lock(&dev_priv->irq_lock);
@@ -2291,7 +2291,7 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev)
 	pm_irqs = gt_irqs = 0;
 
 	dev_priv->gt_irq_mask = ~0;
-	if (HAS_L3_GPU_CACHE(dev)) {
+	if (HAS_L3_DPF(dev)) {
 		/* L3 parity interrupt is always unmasked. */
 		dev_priv->gt_irq_mask = ~GT_PARITY_ERROR(dev);
 		gt_irqs |= GT_PARITY_ERROR(dev);
drivers/gpu/drm/i915/i915_sysfs.c +2 -2
index deb8787..7b4c79c 100644
@@ -97,7 +97,7 @@ static struct attribute_group rc6_attr_group = {
 
 static int l3_access_valid(struct drm_device *dev, loff_t offset)
 {
-	if (!HAS_L3_GPU_CACHE(dev))
+	if (!HAS_L3_DPF(dev))
 		return -EPERM;
 
 	if (offset % 4 != 0)
@@ -525,7 +525,7 @@ void i915_setup_sysfs(struct drm_device *dev)
 			DRM_ERROR("RC6 residency sysfs setup failed\n");
 	}
 #endif
-	if (HAS_L3_GPU_CACHE(dev)) {
+	if (HAS_L3_DPF(dev)) {
 		ret = device_create_bin_file(&dev->primary->kdev, &dpf_attrs);
 		if (ret)
 			DRM_ERROR("l3 parity sysfs setup failed\n");
drivers/gpu/drm/i915/intel_ringbuffer.c +3 -3
index 958b7d8..b67104a 100644
@@ -569,7 +569,7 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 	if (INTEL_INFO(dev)->gen >= 6)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
-	if (HAS_L3_GPU_CACHE(dev))
+	if (HAS_L3_DPF(dev))
 		I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 
 	return ret;
@@ -997,7 +997,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (ring->irq_refcount++ == 0) {
-		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
+		if (HAS_L3_DPF(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring,
 				       ~(ring->irq_enable_mask |
 					 GT_PARITY_ERROR(dev)));
@@ -1019,7 +1019,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
-		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
+		if (HAS_L3_DPF(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 		else
 			I915_WRITE_IMR(ring, ~0);
Signature · 6 lines
1.8.4

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Signature · 2 lines
Ville Syrjälä
Intel OTC
#15 lore raw

PATCH v2 1/1 drm/i915: s/HAS_L3_GPU_CACHE/HAS_L3_DPF

We'd only ever used this define to denote whether or not we have the dynamic parity feature (DPF) and never to determine whether or not L3 exists. Baytrail is a good example of where L3 exists, and not DPF.

This patch provides clarify in the code for future use cases which might want to actually query whether or not L3 exists.

v2: Add /* DPF == dynamic parity feature */

---
 drivers/gpu/drm/i915/i915_drv.h         | 5 +++--
 drivers/gpu/drm/i915/i915_gem.c         | 2 +-
 drivers/gpu/drm/i915/i915_irq.c         | 4 ++--
 drivers/gpu/drm/i915/i915_sysfs.c       | 4 ++--
 drivers/gpu/drm/i915/intel_ringbuffer.c | 6 +++---
 5 files changed, 11 insertions(+), 10 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +3 -2
index 015df52..09a5c82 100644
@@ -1691,8 +1691,9 @@ struct drm_i915_file_private {
 
 #define HAS_FORCE_WAKE(dev) (INTEL_INFO(dev)->has_force_wake)
 
-#define HAS_L3_GPU_CACHE(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
-#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_GPU_CACHE(dev))
+/* DPF == dynamic parity feature */
+#define HAS_L3_DPF(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
+#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_DPF(dev))
 
 #define GT_FREQUENCY_MULTIPLIER 50
 
drivers/gpu/drm/i915/i915_gem.c +1 -1
index 18d07d7..7859f91 100644
@@ -4260,7 +4260,7 @@ int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice)
 	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
 	int i, ret;
 
-	if (!HAS_L3_GPU_CACHE(dev) || !remap_info)
+	if (!HAS_L3_DPF(dev) || !remap_info)
 		return 0;
 
 	ret = intel_ring_begin(ring, GEN7_L3LOG_SIZE / 4 * 3);
drivers/gpu/drm/i915/i915_irq.c +2 -2
index 1c7f6ab..cfaf434 100644
@@ -960,7 +960,7 @@ static void ivybridge_parity_error_irq_handler(struct drm_device *dev, u32 iir)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 
-	if (!HAS_L3_GPU_CACHE(dev))
+	if (!HAS_L3_DPF(dev))
 		return;
 
 	spin_lock(&dev_priv->irq_lock);
@@ -2292,7 +2292,7 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev)
 	pm_irqs = gt_irqs = 0;
 
 	dev_priv->gt_irq_mask = ~0;
-	if (HAS_L3_GPU_CACHE(dev)) {
+	if (HAS_L3_DPF(dev)) {
 		/* L3 parity interrupt is always unmasked. */
 		dev_priv->gt_irq_mask = ~GT_PARITY_ERROR(dev);
 		gt_irqs |= GT_PARITY_ERROR(dev);
drivers/gpu/drm/i915/i915_sysfs.c +2 -2
index deb8787..7b4c79c 100644
@@ -97,7 +97,7 @@ static struct attribute_group rc6_attr_group = {
 
 static int l3_access_valid(struct drm_device *dev, loff_t offset)
 {
-	if (!HAS_L3_GPU_CACHE(dev))
+	if (!HAS_L3_DPF(dev))
 		return -EPERM;
 
 	if (offset % 4 != 0)
@@ -525,7 +525,7 @@ void i915_setup_sysfs(struct drm_device *dev)
 			DRM_ERROR("RC6 residency sysfs setup failed\n");
 	}
 #endif
-	if (HAS_L3_GPU_CACHE(dev)) {
+	if (HAS_L3_DPF(dev)) {
 		ret = device_create_bin_file(&dev->primary->kdev, &dpf_attrs);
 		if (ret)
 			DRM_ERROR("l3 parity sysfs setup failed\n");
drivers/gpu/drm/i915/intel_ringbuffer.c +3 -3
index 958b7d8..b67104a 100644
@@ -569,7 +569,7 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 	if (INTEL_INFO(dev)->gen >= 6)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
-	if (HAS_L3_GPU_CACHE(dev))
+	if (HAS_L3_DPF(dev))
 		I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 
 	return ret;
@@ -997,7 +997,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (ring->irq_refcount++ == 0) {
-		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
+		if (HAS_L3_DPF(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring,
 				       ~(ring->irq_enable_mask |
 					 GT_PARITY_ERROR(dev)));
@@ -1019,7 +1019,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
-		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
+		if (HAS_L3_DPF(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 		else
 			I915_WRITE_IMR(ring, ~0);
Signature · 6 lines
1.8.4

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

PATCH v2 1/1 drm/i915: s/HAS_L3_GPU_CACHE/HAS_L3_DPF

In reply to Ville Syrjälä

We'd only ever used this define to denote whether or not we have the dynamic parity feature (DPF) and never to determine whether or not L3 exists. Baytrail is a good example of where L3 exists, and not DPF.

This patch provides clarify in the code for future use cases which might want to actually query whether or not L3 exists.

v2: Add /* DPF == dynamic parity feature */

---
 drivers/gpu/drm/i915/i915_drv.h         | 5 +++--
 drivers/gpu/drm/i915/i915_gem.c         | 2 +-
 drivers/gpu/drm/i915/i915_irq.c         | 4 ++--
 drivers/gpu/drm/i915/i915_sysfs.c       | 4 ++--
 drivers/gpu/drm/i915/intel_ringbuffer.c | 6 +++---
 5 files changed, 11 insertions(+), 10 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +3 -2
index 015df52..09a5c82 100644
@@ -1691,8 +1691,9 @@ struct drm_i915_file_private {
 
 #define HAS_FORCE_WAKE(dev) (INTEL_INFO(dev)->has_force_wake)
 
-#define HAS_L3_GPU_CACHE(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
-#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_GPU_CACHE(dev))
+/* DPF == dynamic parity feature */
+#define HAS_L3_DPF(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
+#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_DPF(dev))
 
 #define GT_FREQUENCY_MULTIPLIER 50
 
drivers/gpu/drm/i915/i915_gem.c +1 -1
index 18d07d7..7859f91 100644
@@ -4260,7 +4260,7 @@ int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice)
 	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
 	int i, ret;
 
-	if (!HAS_L3_GPU_CACHE(dev) || !remap_info)
+	if (!HAS_L3_DPF(dev) || !remap_info)
 		return 0;
 
 	ret = intel_ring_begin(ring, GEN7_L3LOG_SIZE / 4 * 3);
drivers/gpu/drm/i915/i915_irq.c +2 -2
index 1c7f6ab..cfaf434 100644
@@ -960,7 +960,7 @@ static void ivybridge_parity_error_irq_handler(struct drm_device *dev, u32 iir)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 
-	if (!HAS_L3_GPU_CACHE(dev))
+	if (!HAS_L3_DPF(dev))
 		return;
 
 	spin_lock(&dev_priv->irq_lock);
@@ -2292,7 +2292,7 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev)
 	pm_irqs = gt_irqs = 0;
 
 	dev_priv->gt_irq_mask = ~0;
-	if (HAS_L3_GPU_CACHE(dev)) {
+	if (HAS_L3_DPF(dev)) {
 		/* L3 parity interrupt is always unmasked. */
 		dev_priv->gt_irq_mask = ~GT_PARITY_ERROR(dev);
 		gt_irqs |= GT_PARITY_ERROR(dev);
drivers/gpu/drm/i915/i915_sysfs.c +2 -2
index deb8787..7b4c79c 100644
@@ -97,7 +97,7 @@ static struct attribute_group rc6_attr_group = {
 
 static int l3_access_valid(struct drm_device *dev, loff_t offset)
 {
-	if (!HAS_L3_GPU_CACHE(dev))
+	if (!HAS_L3_DPF(dev))
 		return -EPERM;
 
 	if (offset % 4 != 0)
@@ -525,7 +525,7 @@ void i915_setup_sysfs(struct drm_device *dev)
 			DRM_ERROR("RC6 residency sysfs setup failed\n");
 	}
 #endif
-	if (HAS_L3_GPU_CACHE(dev)) {
+	if (HAS_L3_DPF(dev)) {
 		ret = device_create_bin_file(&dev->primary->kdev, &dpf_attrs);
 		if (ret)
 			DRM_ERROR("l3 parity sysfs setup failed\n");
drivers/gpu/drm/i915/intel_ringbuffer.c +3 -3
index 958b7d8..b67104a 100644
@@ -569,7 +569,7 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 	if (INTEL_INFO(dev)->gen >= 6)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
-	if (HAS_L3_GPU_CACHE(dev))
+	if (HAS_L3_DPF(dev))
 		I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 
 	return ret;
@@ -997,7 +997,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (ring->irq_refcount++ == 0) {
-		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
+		if (HAS_L3_DPF(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring,
 				       ~(ring->irq_enable_mask |
 					 GT_PARITY_ERROR(dev)));
@@ -1019,7 +1019,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
-		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
+		if (HAS_L3_DPF(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 		else
 			I915_WRITE_IMR(ring, ~0);
Signature · 6 lines
1.8.4

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

Re: [PATCH] [v2] drm/i915: s/HAS_L3_GPU_CACHE/HAS_L3_DPF

Quoted 11 lines · Ben Widawsky

We'd only ever used this define to denote whether or not we have the dynamic parity feature (DPF) and never to determine whether or not L3 exists. Baytrail is a good example of where L3 exists, and not DPF.

This patch provides clarify in the code for future use cases which might want to actually query whether or not L3 exists.

v2: Add /* DPF == dynamic parity feature */

Ok, I've slurped all the kernel patches in. Like I've said I'd very much welcome a little testcase to inject an error and exercise this stuff a bit, if it's not a horrendous amount of work to get going. -Daniel

Quoted 119 lines
---
 drivers/gpu/drm/i915/i915_drv.h         | 5 +++--
 drivers/gpu/drm/i915/i915_gem.c         | 2 +-
 drivers/gpu/drm/i915/i915_irq.c         | 4 ++--
 drivers/gpu/drm/i915/i915_sysfs.c       | 4 ++--
 drivers/gpu/drm/i915/intel_ringbuffer.c | 6 +++---
 5 files changed, 11 insertions(+), 10 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +3 -2
index 015df52..09a5c82 100644
@@ -1691,8 +1691,9 @@ struct drm_i915_file_private {
 
 #define HAS_FORCE_WAKE(dev) (INTEL_INFO(dev)->has_force_wake)
 
-#define HAS_L3_GPU_CACHE(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
-#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_GPU_CACHE(dev))
+/* DPF == dynamic parity feature */
+#define HAS_L3_DPF(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
+#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_DPF(dev))
 
 #define GT_FREQUENCY_MULTIPLIER 50
 
drivers/gpu/drm/i915/i915_gem.c +1 -1
index 18d07d7..7859f91 100644
@@ -4260,7 +4260,7 @@ int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice)
 	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
 	int i, ret;
 
-	if (!HAS_L3_GPU_CACHE(dev) || !remap_info)
+	if (!HAS_L3_DPF(dev) || !remap_info)
 		return 0;
 
 	ret = intel_ring_begin(ring, GEN7_L3LOG_SIZE / 4 * 3);
drivers/gpu/drm/i915/i915_irq.c +2 -2
index 1c7f6ab..cfaf434 100644
@@ -960,7 +960,7 @@ static void ivybridge_parity_error_irq_handler(struct drm_device *dev, u32 iir)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 
-	if (!HAS_L3_GPU_CACHE(dev))
+	if (!HAS_L3_DPF(dev))
 		return;
 
 	spin_lock(&dev_priv->irq_lock);
@@ -2292,7 +2292,7 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev)
 	pm_irqs = gt_irqs = 0;
 
 	dev_priv->gt_irq_mask = ~0;
-	if (HAS_L3_GPU_CACHE(dev)) {
+	if (HAS_L3_DPF(dev)) {
 		/* L3 parity interrupt is always unmasked. */
 		dev_priv->gt_irq_mask = ~GT_PARITY_ERROR(dev);
 		gt_irqs |= GT_PARITY_ERROR(dev);
drivers/gpu/drm/i915/i915_sysfs.c +2 -2
index deb8787..7b4c79c 100644
@@ -97,7 +97,7 @@ static struct attribute_group rc6_attr_group = {
 
 static int l3_access_valid(struct drm_device *dev, loff_t offset)
 {
-	if (!HAS_L3_GPU_CACHE(dev))
+	if (!HAS_L3_DPF(dev))
 		return -EPERM;
 
 	if (offset % 4 != 0)
@@ -525,7 +525,7 @@ void i915_setup_sysfs(struct drm_device *dev)
 			DRM_ERROR("RC6 residency sysfs setup failed\n");
 	}
 #endif
-	if (HAS_L3_GPU_CACHE(dev)) {
+	if (HAS_L3_DPF(dev)) {
 		ret = device_create_bin_file(&dev->primary->kdev, &dpf_attrs);
 		if (ret)
 			DRM_ERROR("l3 parity sysfs setup failed\n");
drivers/gpu/drm/i915/intel_ringbuffer.c +3 -3
index 958b7d8..b67104a 100644
@@ -569,7 +569,7 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 	if (INTEL_INFO(dev)->gen >= 6)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
-	if (HAS_L3_GPU_CACHE(dev))
+	if (HAS_L3_DPF(dev))
 		I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 
 	return ret;
@@ -997,7 +997,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (ring->irq_refcount++ == 0) {
-		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
+		if (HAS_L3_DPF(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring,
 				       ~(ring->irq_enable_mask |
 					 GT_PARITY_ERROR(dev)));
@@ -1019,7 +1019,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
-		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
+		if (HAS_L3_DPF(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 		else
 			I915_WRITE_IMR(ring, ~0);
Signature · 6 lines
1.8.4

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Signature · 3 lines
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
#18 lore raw

Re: [PATCH] [v2] drm/i915: s/HAS_L3_GPU_CACHE/HAS_L3_DPF

Quoted 10 lines · Daniel Vetter
Quoted 9 lines · Ben Widawsky

We'd only ever used this define to denote whether or not we have the dynamic parity feature (DPF) and never to determine whether or not L3 exists. Baytrail is a good example of where L3 exists, and not DPF.

This patch provides clarify in the code for future use cases which might want to actually query whether or not L3 exists.

v2: Add /* DPF == dynamic parity feature */

Quoted 8 lines
Quoted 2 lines

Ok, I've slurped all the kernel patches in. Like I've said I'd very much welcome a little testcase to inject an error and exercise this stuff a bit, if it's not a horrendous amount of work to get going. -Daniel

I agree with you. I'm trying to get help from other internal groups to write that test case, but so far, no luck. It's on my TODO list behind about 4 other things right now.

Quoted 124 lines
Quoted 119 lines
---
 drivers/gpu/drm/i915/i915_drv.h         | 5 +++--
 drivers/gpu/drm/i915/i915_gem.c         | 2 +-
 drivers/gpu/drm/i915/i915_irq.c         | 4 ++--
 drivers/gpu/drm/i915/i915_sysfs.c       | 4 ++--
 drivers/gpu/drm/i915/intel_ringbuffer.c | 6 +++---
 5 files changed, 11 insertions(+), 10 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +3 -2
index 015df52..09a5c82 100644
@@ -1691,8 +1691,9 @@ struct drm_i915_file_private {
 
 #define HAS_FORCE_WAKE(dev) (INTEL_INFO(dev)->has_force_wake)
 
-#define HAS_L3_GPU_CACHE(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
-#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_GPU_CACHE(dev))
+/* DPF == dynamic parity feature */
+#define HAS_L3_DPF(dev) (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
+#define NUM_L3_SLICES(dev) (IS_HSW_GT3(dev) ? 2 : HAS_L3_DPF(dev))
 
 #define GT_FREQUENCY_MULTIPLIER 50
 
drivers/gpu/drm/i915/i915_gem.c +1 -1
index 18d07d7..7859f91 100644
@@ -4260,7 +4260,7 @@ int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice)
 	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
 	int i, ret;
 
-	if (!HAS_L3_GPU_CACHE(dev) || !remap_info)
+	if (!HAS_L3_DPF(dev) || !remap_info)
 		return 0;
 
 	ret = intel_ring_begin(ring, GEN7_L3LOG_SIZE / 4 * 3);
drivers/gpu/drm/i915/i915_irq.c +2 -2
index 1c7f6ab..cfaf434 100644
@@ -960,7 +960,7 @@ static void ivybridge_parity_error_irq_handler(struct drm_device *dev, u32 iir)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 
-	if (!HAS_L3_GPU_CACHE(dev))
+	if (!HAS_L3_DPF(dev))
 		return;
 
 	spin_lock(&dev_priv->irq_lock);
@@ -2292,7 +2292,7 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev)
 	pm_irqs = gt_irqs = 0;
 
 	dev_priv->gt_irq_mask = ~0;
-	if (HAS_L3_GPU_CACHE(dev)) {
+	if (HAS_L3_DPF(dev)) {
 		/* L3 parity interrupt is always unmasked. */
 		dev_priv->gt_irq_mask = ~GT_PARITY_ERROR(dev);
 		gt_irqs |= GT_PARITY_ERROR(dev);
drivers/gpu/drm/i915/i915_sysfs.c +2 -2
index deb8787..7b4c79c 100644
@@ -97,7 +97,7 @@ static struct attribute_group rc6_attr_group = {
 
 static int l3_access_valid(struct drm_device *dev, loff_t offset)
 {
-	if (!HAS_L3_GPU_CACHE(dev))
+	if (!HAS_L3_DPF(dev))
 		return -EPERM;
 
 	if (offset % 4 != 0)
@@ -525,7 +525,7 @@ void i915_setup_sysfs(struct drm_device *dev)
 			DRM_ERROR("RC6 residency sysfs setup failed\n");
 	}
 #endif
-	if (HAS_L3_GPU_CACHE(dev)) {
+	if (HAS_L3_DPF(dev)) {
 		ret = device_create_bin_file(&dev->primary->kdev, &dpf_attrs);
 		if (ret)
 			DRM_ERROR("l3 parity sysfs setup failed\n");
drivers/gpu/drm/i915/intel_ringbuffer.c +3 -3
index 958b7d8..b67104a 100644
@@ -569,7 +569,7 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 	if (INTEL_INFO(dev)->gen >= 6)
 		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
-	if (HAS_L3_GPU_CACHE(dev))
+	if (HAS_L3_DPF(dev))
 		I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 
 	return ret;
@@ -997,7 +997,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (ring->irq_refcount++ == 0) {
-		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
+		if (HAS_L3_DPF(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring,
 				       ~(ring->irq_enable_mask |
 					 GT_PARITY_ERROR(dev)));
@@ -1019,7 +1019,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
-		if (HAS_L3_GPU_CACHE(dev) && ring->id == RCS)
+		if (HAS_L3_DPF(dev) && ring->id == RCS)
 			I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
 		else
 			I915_WRITE_IMR(ring, ~0);
Signature · 6 lines
1.8.4

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Signature · 3 lines
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
Signature · 5 lines
Ben Widawsky, Intel Open Source Technology Center
_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
#19 lore raw

PATCH 7/14 intel_l3_parity: Fix indentation

In reply to Ben Widawsky
---
 tools/intel_l3_parity.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)
tools/intel_l3_parity.c +6 -6
index ad027ac..970dcd6 100644
@@ -58,12 +58,12 @@ static void dumpit(void)
 		for (j = 0; j < NUM_SUBBANKS; j++) {
 			struct l3_log_register *reg = &l3log[i][j];
 
-		if (reg->row0_enable)
-			printf("Row %d, Bank %d, Subbank %d is disabled\n",
-			       reg->row0, i, j);
-		if (reg->row1_enable)
-			printf("Row %d, Bank %d, Subbank %d is disabled\n",
-			       reg->row1, i, j);
+			if (reg->row0_enable)
+				printf("Row %d, Bank %d, Subbank %d is disabled\n",
+				       reg->row0, i, j);
+			if (reg->row1_enable)
+				printf("Row %d, Bank %d, Subbank %d is disabled\n",
+				       reg->row1, i, j);
 		}
 	}
 }
Signature · 1 line
1.8.4
#20 lore raw

PATCH 8/14 intel_l3_parity: Assert all GEN7+ support

In reply to Ben Widawsky

v2: Don't assert for Valleyview (Bryan)
Rework code to be a bit more readable.

CC "Bell, Bryan J" <[email protected]>
---
 tools/intel_l3_parity.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)
tools/intel_l3_parity.c +4 -5
index 970dcd6..715d095 100644
@@ -116,15 +116,14 @@ int main(int argc, char *argv[])
 	drm_fd = drm_open_any();
 	devid = intel_get_drm_devid(drm_fd);
 
+	if (intel_gen(devid) < 7 || IS_VALLEYVIEW(devid))
+		exit(EXIT_SUCCESS);
+
 	ret = asprintf(&path, "/sys/class/drm/card%d/l3_parity", device);
 	assert(ret != -1);
 
 	fd = open(path, O_RDWR);
-	if (fd == -1 && IS_IVYBRIDGE(devid)) {
-		perror("Opening sysfs");
-		exit(EXIT_FAILURE);
-	} else if (fd == -1)
-		exit(EXIT_SUCCESS);
+	assert(fd != -1);
 
 	ret = read(fd, l3log, NUM_REGS * sizeof(uint32_t));
 	if (ret == -1) {
Signature · 1 line
1.8.4
#21 lore raw

PATCH 9/14 intel_l3_parity: Use getopt for the l3 parity tool

In reply to Ben Widawsky

Add new command line arguments in addition to supporting the old features. This patch only introduces one feature, the -e argument to enable a specific row/bank/subbank. Previously you could only enable all. Otherwise, it has what you expect (we prefer -r -b -s for specifying the row/bank/subbank).

---
 tests/sysfs_l3_parity   |  12 ++---
 tools/intel_l3_parity.c | 122 ++++++++++++++++++++++++++++++++++++++++--------
 2 files changed, 109 insertions(+), 25 deletions(-)
tests/sysfs_l3_parity +6 -6
index 6f814a1..a0dfad9 100755
@@ -8,20 +8,20 @@ fi
 SOURCE_DIR="$( dirname "${BASH_SOURCE[0]}" )"
 . $SOURCE_DIR/drm_lib.sh
 
-$SOURCE_DIR/../tools/intel_l3_parity -c
+$SOURCE_DIR/../tools/intel_l3_parity -r 0 -b 0 -s 0 -e
 
 #Check that we can remap a row
-$SOURCE_DIR/../tools/intel_l3_parity 0,0,0
-disabled=`$SOURCE_DIR/../tools/intel_l3_parity | grep -c 'Row 0, Bank 0, Subbank 0 is disabled'`
+$SOURCE_DIR/../tools/intel_l3_parity -r 0 -b 0 -s 0 -d
+disabled=`$SOURCE_DIR/../tools/intel_l3_parity -l | grep -c 'Row 0, Bank 0, Subbank 0 is disabled'`
 if [ "$disabled" != "1" ] ; then
 	echo "Fail"
 	exit 1
 fi
 
-$SOURCE_DIR/../tools/intel_l3_parity -c
+$SOURCE_DIR/../tools/intel_l3_parity -r 0 -b 0 -s 0 -e
 
 #Check that we can clear remaps
-if [ `$SOURCE_DIR/../tools/intel_l3_parity | wc -c` != "0" ] ; then
-	echo "Fail"
+if [ `$SOURCE_DIR/../tools/intel_l3_parity -l | wc -c` != "0" ] ; then
+	echo "Fail 2"
 	exit 1
 fi
tools/intel_l3_parity.c +103 -19

158 lines not on this page · raw message

Signature · 1 line
1.8.4
#22 lore raw

PATCH 10/14 intel_l3_parity: Hardware info argument

In reply to Ben Widawsky

Add a new command line argument to the tool which will spit out various parameters for the giving hardware. As a result of this, some new defines are added to help with the various info.

---
 tools/intel_l3_parity.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)
tools/intel_l3_parity.c +20 -4
index 507a522..28c47eb 100644
@@ -38,9 +38,19 @@
 #include "intel_gpu_tools.h"
 #include "drmtest.h"
 
-#define NUM_BANKS 4
+static unsigned int devid;
+/* L3 size is always a function of banks. The number of banks cannot be
+ * determined by number of slices however */
+#define MAX_BANKS 4
+#define NUM_BANKS \
+	((devid == PCI_CHIP_IVYBRIDGE_GT1 || devid == PCI_CHIP_IVYBRIDGE_M_GT1) ? 2 : 4)
 #define NUM_SUBBANKS 8
+#define BYTES_PER_BANK (128 << 10)
+/* Each row addresses [up to] 4b. This multiplied by the number of subbanks
+ * will give the L3 size per bank.
+ * TODO: Row size is fixed on IVB, and variable on HSW.*/
 #define MAX_ROW (1<<12)
+#define L3_SIZE ((MAX_ROW * 4) * NUM_SUBBANKS *  NUM_BANKS)
 #define NUM_REGS (NUM_BANKS * NUM_SUBBANKS)
 
 struct __attribute__ ((__packed__)) l3_log_register {
@@ -50,7 +60,7 @@ struct __attribute__ ((__packed__)) l3_log_register {
 	uint32_t row1_enable	: 1;
 	uint32_t rsvd1		: 4;
 	uint32_t row1		: 11;
-} l3log[NUM_BANKS][NUM_SUBBANKS];
+} l3log[MAX_BANKS][NUM_SUBBANKS];
 
 static void dumpit(void)
 {
@@ -118,6 +128,7 @@ static void usage(const char *name)
 		"  -s, --subbank=[subbank]		The subbank to act upon (default 0)\n"
 		" ACTIONS (only 1 may be specified at a time):\n"
 		"  -h, --help				Display this help\n"
+		"  -H, --hw-info				Display the current L3 properties\n"
 		"  -l, --list				List the current L3 logs\n"
 		"  -a, --clear-all			Clear all disabled rows\n"
 		"  -e, --enable				Enable row, bank, subbank (undo -d)\n"
@@ -129,7 +140,6 @@ int main(int argc, char *argv[])
 {
 	const int device = drm_get_card();
 	char *path;
-	unsigned int devid;
 	int row = 0, bank = 0, sbank = 0;
 	int drm_fd, fd, ret;
 	int action = '0';
@@ -162,13 +172,14 @@ int main(int argc, char *argv[])
 			{ "clear-all", no_argument, 0, 'a' },
 			{ "enable", no_argument, 0, 'e' },
 			{ "disable", optional_argument, 0, 'd' },
+			{ "hw-info", no_argument, 0, 'H' },
 			{ "row", required_argument, 0, 'r' },
 			{ "bank", required_argument, 0, 'b' },
 			{ "subbank", required_argument, 0, 's' },
 			{0, 0, 0, 0}
 		};
 
-		c = getopt_long(argc, argv, "hr:b:s:aled::", long_options,
+		c = getopt_long(argc, argv, "hHr:b:s:aled::", long_options,
 				&option_index);
 		if (c == -1)
 			break;
@@ -178,6 +189,11 @@ int main(int argc, char *argv[])
 			case 'h':
 				usage(argv[0]);
 				exit(EXIT_SUCCESS);
+			case 'H':
+				printf("Number of banks: %d\n", NUM_BANKS);
+				printf("Subbanks per bank: %d\n", NUM_SUBBANKS);
+				printf("L3 size: %dK\n", L3_SIZE >> 10);
+				exit(EXIT_SUCCESS);
 			case 'r':
 				row = atoi(optarg);
 				if (row >= MAX_ROW)
Signature · 1 line
1.8.4
#23 lore raw

PATCH 11/14 intel_l3_parity: slice support

In reply to Ben Widawsky

Haswell GT3 adds a new slice which is kept distinct from the old register interface. Plumb it into the code, though it's only 1 slice still.

---
 tools/intel_l3_parity.c | 106 +++++++++++++++++++++++++++++-------------------
 1 file changed, 65 insertions(+), 41 deletions(-)
tools/intel_l3_parity.c +65 -41
index 28c47eb..c98eb80 100644
@@ -52,6 +52,8 @@ static unsigned int devid;
 #define MAX_ROW (1<<12)
 #define L3_SIZE ((MAX_ROW * 4) * NUM_SUBBANKS *  NUM_BANKS)
 #define NUM_REGS (NUM_BANKS * NUM_SUBBANKS)
+#define MAX_SLICES 1
+#define REAL_MAX_SLICES 1
 
 struct __attribute__ ((__packed__)) l3_log_register {
 	uint32_t row0_enable	: 1;
@@ -60,15 +62,21 @@ struct __attribute__ ((__packed__)) l3_log_register {
 	uint32_t row1_enable	: 1;
 	uint32_t rsvd1		: 4;
 	uint32_t row1		: 11;
-} l3log[MAX_BANKS][NUM_SUBBANKS];
+} l3logs[REAL_MAX_SLICES][MAX_BANKS][NUM_SUBBANKS];
 
-static void dumpit(void)
+static int which_slice = -1;
+#define for_each_slice(__i) \
+	for ((__i) = (which_slice == -1) ? 0 : which_slice; \
+			(__i) < ((which_slice == -1) ? MAX_SLICES : (which_slice + 1)); \
+			(__i)++)
+
+static void dumpit(int slice)
 {
 	int i, j;
 
 	for (i = 0; i < NUM_BANKS; i++) {
 		for (j = 0; j < NUM_SUBBANKS; j++) {
-			struct l3_log_register *reg = &l3log[i][j];
+			struct l3_log_register *reg = &l3logs[slice][i][j];
 
 			if (reg->row0_enable)
 				printf("Row %d, Bank %d, Subbank %d is disabled\n",
@@ -80,9 +88,9 @@ static void dumpit(void)
 	}
 }
 
-static int disable_rbs(int row, int bank, int sbank)
+static int disable_rbs(int row, int bank, int sbank, int slice)
 {
-	struct l3_log_register *reg = &l3log[bank][sbank];
+	struct l3_log_register *reg = &l3logs[slice][bank][sbank];
 
 	// can't map more than 2 rows
 	if (reg->row0_enable && reg->row1_enable)
@@ -105,9 +113,9 @@ static int disable_rbs(int row, int bank, int sbank)
 	return 0;
 }
 
-static void enables_rbs(int row, int bank, int sbank)
+static void enables_rbs(int row, int bank, int sbank, int slice)
 {
-	struct l3_log_register *reg = &l3log[bank][sbank];
+	struct l3_log_register *reg = &l3logs[slice][bank][sbank];
 
 	if (!reg->row0_enable && !reg->row1_enable)
 		return;
@@ -126,6 +134,7 @@ static void usage(const char *name)
 		"  -r, --row=[row]			The row to act upon (default 0)\n"
 		"  -b, --bank=[bank]			The bank to act upon (default 0)\n"
 		"  -s, --subbank=[subbank]		The subbank to act upon (default 0)\n"
+		"  -w, --slice=[slice]			Which slice to act on (default: -1 [all])"
 		" ACTIONS (only 1 may be specified at a time):\n"
 		"  -h, --help				Display this help\n"
 		"  -H, --hw-info				Display the current L3 properties\n"
@@ -139,30 +148,30 @@ static void usage(const char *name)
 int main(int argc, char *argv[])
 {
 	const int device = drm_get_card();
-	char *path;
+	char *path[REAL_MAX_SLICES];
 	int row = 0, bank = 0, sbank = 0;
-	int drm_fd, fd, ret;
+	int fd[REAL_MAX_SLICES] = {0}, ret, i;
 	int action = '0';
-
-	drm_fd = drm_open_any();
+	int drm_fd = drm_open_any();
 	devid = intel_get_drm_devid(drm_fd);
 
 	if (intel_gen(devid) < 7 || IS_VALLEYVIEW(devid))
 		exit(EXIT_SUCCESS);
 
-	ret = asprintf(&path, "/sys/class/drm/card%d/l3_parity", device);
+	ret = asprintf(&path[0], "/sys/class/drm/card%d/l3_parity", device);
 	assert(ret != -1);
 
-	fd = open(path, O_RDWR);
-	assert(fd != -1);
-
-	ret = read(fd, l3log, NUM_REGS * sizeof(uint32_t));
-	if (ret == -1) {
-		perror("Reading sysfs");
-		exit(EXIT_FAILURE);
+	for_each_slice(i) {
+		fd[i] = open(path[i], O_RDWR);
+		assert(fd[i]);
+		ret = read(fd[i], l3logs[i], NUM_REGS * sizeof(uint32_t));
+		if (ret == -1) {
+			perror("Reading sysfs");
+			exit(EXIT_FAILURE);
+		}
+		assert(lseek(fd[i], 0, SEEK_SET) == 0);
 	}
 
-	assert(lseek(fd, 0, SEEK_SET) == 0);
 
 	while (1) {
 		int c, option_index = 0;
@@ -176,10 +185,11 @@ int main(int argc, char *argv[])
 			{ "row", required_argument, 0, 'r' },
 			{ "bank", required_argument, 0, 'b' },
 			{ "subbank", required_argument, 0, 's' },
+			{ "slice", required_argument, 0, 'w' },
 			{0, 0, 0, 0}
 		};
 
-		c = getopt_long(argc, argv, "hHr:b:s:aled::", long_options,
+		c = getopt_long(argc, argv, "hHr:b:s:w:aled::", long_options,
 				&option_index);
 		if (c == -1)
 			break;
@@ -190,6 +200,7 @@ int main(int argc, char *argv[])
 				usage(argv[0]);
 				exit(EXIT_SUCCESS);
 			case 'H':
+				printf("Number of slices: %d\n", MAX_SLICES);
 				printf("Number of banks: %d\n", NUM_BANKS);
 				printf("Subbanks per bank: %d\n", NUM_SUBBANKS);
 				printf("L3 size: %dK\n", L3_SIZE >> 10);
@@ -209,6 +220,11 @@ int main(int argc, char *argv[])
 				if (sbank >= NUM_SUBBANKS)
 					exit(EXIT_FAILURE);
 				break;
+			case 'w':
+				which_slice = atoi(optarg);
+				if (which_slice > 1)
+					exit(EXIT_FAILURE);
+				break;
 			case 'd':
 				if (optarg) {
 					ret = sscanf(optarg, "%d,%d,%d", &row, &bank, &sbank);
@@ -229,30 +245,38 @@ int main(int argc, char *argv[])
 		}
 	}
 
-	switch (action) {
-		case 'l':
-			dumpit();
-			exit(EXIT_SUCCESS);
-		case 'a':
-			memset(l3log, 0, sizeof(l3log));
-			break;
-		case 'e':
-			enables_rbs(row, bank, sbank);
-			break;
-		case 'd':
-			assert(disable_rbs(row, bank, sbank) == 0);
-			break;
-		default:
-			abort();
+	/* Per slice operations */
+	for_each_slice(i) {
+		switch (action) {
+			case 'l':
+				dumpit(i);
+				break;
+			case 'a':
+				memset(l3logs[i], 0, NUM_REGS * sizeof(struct l3_log_register));
+				break;
+			case 'e':
+				enables_rbs(row, bank, sbank, i);
+				break;
+			case 'd':
+				assert(disable_rbs(row, bank, sbank, i) == 0);
+				break;
+			default:
+				abort();
+		}
 	}
 
-	ret = write(fd, l3log, NUM_REGS * sizeof(uint32_t));
-	if (ret == -1) {
-		perror("Writing sysfs");
-		exit(EXIT_FAILURE);
+	if (action == 'l')
+		exit(EXIT_SUCCESS);
+
+	for_each_slice(i) {
+		ret = write(fd[i], l3logs[i], NUM_REGS * sizeof(uint32_t));
+		if (ret == -1) {
+			perror("Writing sysfs");
+			exit(EXIT_FAILURE);
+		}
+		close(fd[i]);
 	}
 
-	close(fd);
 
 	exit(EXIT_SUCCESS);
 }
Signature · 1 line
1.8.4
#24 lore raw

PATCH 12/14 intel_l3_parity: Actually support multiple slices

In reply to Ben Widawsky
---
 tools/intel_l3_parity.c | 45 ++++++++++++++++++++++++++++-----------------
 1 file changed, 28 insertions(+), 17 deletions(-)
tools/intel_l3_parity.c +28 -17
index c98eb80..ed7034a 100644
@@ -41,19 +41,28 @@
 static unsigned int devid;
 /* L3 size is always a function of banks. The number of banks cannot be
  * determined by number of slices however */
-#define MAX_BANKS 4
-#define NUM_BANKS \
-	((devid == PCI_CHIP_IVYBRIDGE_GT1 || devid == PCI_CHIP_IVYBRIDGE_M_GT1) ? 2 : 4)
+static inline int num_banks(void) {
+	if (IS_HSW_GT3(devid))
+		return 8; /* 4 per each slice */
+	else if (IS_HSW_GT1(devid) ||
+			devid == PCI_CHIP_IVYBRIDGE_GT1 ||
+			devid == PCI_CHIP_IVYBRIDGE_M_GT1)
+		return 2;
+	else
+		return 4;
+}
 #define NUM_SUBBANKS 8
 #define BYTES_PER_BANK (128 << 10)
 /* Each row addresses [up to] 4b. This multiplied by the number of subbanks
  * will give the L3 size per bank.
  * TODO: Row size is fixed on IVB, and variable on HSW.*/
 #define MAX_ROW (1<<12)
-#define L3_SIZE ((MAX_ROW * 4) * NUM_SUBBANKS *  NUM_BANKS)
-#define NUM_REGS (NUM_BANKS * NUM_SUBBANKS)
-#define MAX_SLICES 1
-#define REAL_MAX_SLICES 1
+#define MAX_BANKS_PER_SLICE 4
+#define NUM_REGS (MAX_BANKS_PER_SLICE * NUM_SUBBANKS)
+#define MAX_SLICES (IS_HSW_GT3(devid) ? 2 : 1)
+#define REAL_MAX_SLICES 2
+/* TODO support SLM config */
+#define L3_SIZE ((MAX_ROW * 4) * NUM_SUBBANKS *  num_banks())
 
 struct __attribute__ ((__packed__)) l3_log_register {
 	uint32_t row0_enable	: 1;
@@ -62,7 +71,7 @@ struct __attribute__ ((__packed__)) l3_log_register {
 	uint32_t row1_enable	: 1;
 	uint32_t rsvd1		: 4;
 	uint32_t row1		: 11;
-} l3logs[REAL_MAX_SLICES][MAX_BANKS][NUM_SUBBANKS];
+} l3logs[REAL_MAX_SLICES][MAX_BANKS_PER_SLICE][NUM_SUBBANKS];
 
 static int which_slice = -1;
 #define for_each_slice(__i) \
@@ -74,16 +83,16 @@ static void dumpit(int slice)
 {
 	int i, j;
 
-	for (i = 0; i < NUM_BANKS; i++) {
+	for (i = 0; i < MAX_BANKS_PER_SLICE; i++) {
 		for (j = 0; j < NUM_SUBBANKS; j++) {
 			struct l3_log_register *reg = &l3logs[slice][i][j];
 
 			if (reg->row0_enable)
-				printf("Row %d, Bank %d, Subbank %d is disabled\n",
-				       reg->row0, i, j);
+				printf("Slice %d, Row %d, Bank %d, Subbank %d is disabled\n",
+				       slice, reg->row0, i, j);
 			if (reg->row1_enable)
-				printf("Row %d, Bank %d, Subbank %d is disabled\n",
-				       reg->row1, i, j);
+				printf("Slice %d, Row %d, Bank %d, Subbank %d is disabled\n",
+				       slice, reg->row1, i, j);
 		}
 	}
 }
@@ -160,6 +169,8 @@ int main(int argc, char *argv[])
 
 	ret = asprintf(&path[0], "/sys/class/drm/card%d/l3_parity", device);
 	assert(ret != -1);
+	ret = asprintf(&path[1], "/sys/class/drm/card%d/l3_parity_slice_1", device);
+	assert(ret != -1);
 
 	for_each_slice(i) {
 		fd[i] = open(path[i], O_RDWR);
@@ -201,9 +212,9 @@ int main(int argc, char *argv[])
 				exit(EXIT_SUCCESS);
 			case 'H':
 				printf("Number of slices: %d\n", MAX_SLICES);
-				printf("Number of banks: %d\n", NUM_BANKS);
+				printf("Number of banks: %d\n", num_banks());
 				printf("Subbanks per bank: %d\n", NUM_SUBBANKS);
-				printf("L3 size: %dK\n", L3_SIZE >> 10);
+				printf("Max L3 size: %dK\n", L3_SIZE >> 10);
 				exit(EXIT_SUCCESS);
 			case 'r':
 				row = atoi(optarg);
@@ -212,7 +223,7 @@ int main(int argc, char *argv[])
 				break;
 			case 'b':
 				bank = atoi(optarg);
-				if (bank >= NUM_BANKS)
+				if (bank >= num_banks() || bank >= MAX_BANKS_PER_SLICE)
 					exit(EXIT_FAILURE);
 				break;
 			case 's':
@@ -222,7 +233,7 @@ int main(int argc, char *argv[])
 				break;
 			case 'w':
 				which_slice = atoi(optarg);
-				if (which_slice > 1)
+				if (which_slice >= MAX_SLICES)
 					exit(EXIT_FAILURE);
 				break;
 			case 'd':
Signature · 1 line
1.8.4
#25 lore raw

PATCH 13/14 intel_l3_parity: Support error injection

In reply to Ben Widawsky

Haswell added the ability to inject errors which is extremely useful for testing. Add two arguments to the tool to inject, and uninject.

---
 tests/sysfs_l3_parity   |  2 +-
 tools/intel_l3_parity.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 68 insertions(+), 3 deletions(-)
tests/sysfs_l3_parity +1 -1
index a0dfad9..e9d4411 100755
@@ -21,7 +21,7 @@ fi
 $SOURCE_DIR/../tools/intel_l3_parity -r 0 -b 0 -s 0 -e
 
 #Check that we can clear remaps
-if [ `$SOURCE_DIR/../tools/intel_l3_parity -l | wc -c` != "0" ] ; then
+if [ `$SOURCE_DIR/../tools/intel_l3_parity -l | wc -l` != 1 ] ; then
 	echo "Fail 2"
 	exit 1
 fi
tools/intel_l3_parity.c +67 -2

140 lines not on this page · raw message

Signature · 1 line
1.8.4
#26 lore raw

PATCH 14/14 intel_l3_parity: Support a daemonic mode

In reply to Ben Widawsky

v2: Add a comment explaining the dangers of directly accessing the DFT register (Daniel)

---
 tools/Makefile.am              |   6 ++-
 tools/intel_l3_parity.c        |  46 ++++++++++++++++--
 tools/intel_l3_parity.h        |  31 ++++++++++++
 tools/intel_l3_udev_listener.c | 108 +++++++++++++++++++++++++++++++++++++++++
 4 files changed, 186 insertions(+), 5 deletions(-)
 create mode 100644 tools/intel_l3_parity.h
 create mode 100644 tools/intel_l3_udev_listener.c
tools/Makefile.am +5 -1
index 47bd5b3..19810cf 100644
@@ -39,7 +39,7 @@ dist_bin_SCRIPTS = intel_gpu_abrt
 
 AM_CPPFLAGS = -I$(top_srcdir) -I$(top_srcdir)/lib
 AM_CFLAGS = $(DRM_CFLAGS) $(PCIACCESS_CFLAGS) $(CWARNFLAGS) $(CAIRO_CFLAGS)
-LDADD = $(top_builddir)/lib/libintel_tools.la $(DRM_LIBS) $(PCIACCESS_LIBS) $(CAIRO_LIBS)
+LDADD = $(top_builddir)/lib/libintel_tools.la $(DRM_LIBS) $(PCIACCESS_LIBS) $(CAIRO_LIBS) $(LIBUDEV_LIBS)
 
 intel_dump_decode_SOURCES = 	\
 	intel_dump_decode.c
@@ -50,3 +50,7 @@ intel_error_decode_SOURCES =	\
 intel_bios_reader_SOURCES =	\
 	intel_bios_reader.c	\
 	intel_bios.h
+
+intel_l3_parity_SOURCES =	\
+	intel_l3_parity.c	\
+	intel_l3_udev_listener.c
tools/intel_l3_parity.c +42 -4

109 lines not on this page · raw message

tools/intel_l3_parity.h new file +31 -0
new file mode 100644
index 0000000..65697c4
@@ -0,0 +1,31 @@
+#ifndef INTEL_L3_PARITY_H_
+#define INTEL_L3_PARITY_H_
+
+#include <stdint.h>
+#include <stdbool.h>
+
+struct l3_parity {
+	struct udev *udev;
+	struct udev_monitor *uevent_monitor;
+	int fd;
+	fd_set fdset;
+};
+
+struct l3_location {
+	uint8_t slice;
+	uint16_t row;
+	uint8_t bank;
+	uint8_t subbank;
+};
+
+#if HAVE_UDEV
+int l3_uevent_setup(struct l3_parity *par);
+/* Listens (blocks) for an l3 parity event. Returns the location of the error. */
+int l3_listen(struct l3_parity *par, bool daemon, struct l3_location *loc);
+#define l3_uevent_teardown(par) {}
+#else
+#define l3_uevent_setup(par, daemon, loc) -1
+#define l3_listen(par) -1
+#endif
+
+#endif
tools/intel_l3_udev_listener.c new file +108 -0

108 lines not on this page · raw message

Signature · 1 line
1.8.4