drm/i915: Dynamic Parity Detection handling

On IVB hardware we are given an interrupt whenever a L3 parity error
occurs in the L3 cache. The L3 cache is used by internal GPU clients
only.  This is a very rare occurrence (in fact to test this I need to
use specially instrumented silicon).

When a row in the L3 cache detects a parity error the HW generates an
interrupt. The interrupt is masked in GTIMR until we get a chance to
read some registers and alert userspace via a uevent. With this
information userspace can use a sysfs interface (follow-up patch) to
remap those rows.

Way above my level of understanding, but if a given row fails, it is
statistically more likely to fail again than a row which has not failed.
Therefore it is desirable for an operating system to maintain a lifelong
list of failing rows and always remap any bad rows on driver load.
Hardware limits the number of rows that are remappable per bank/subbank,
and should more than that many rows detect parity errors, software
should maintain a list of the most frequent errors, and remap those
rows.

V2: Drop WARN_ON(IS_GEN6) (Jesse)
DRM_DEBUG row/bank/subbank on errror (Jesse)
Comment updates (Jesse)

Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This commit is contained in:
Ben Widawsky 2012-05-25 16:56:22 -07:00 committed by Daniel Vetter
parent 6c982376de
commit e368919008
3 changed files with 105 additions and 0 deletions

View File

@ -816,6 +816,8 @@ typedef struct drm_i915_private {
struct drm_property *broadcast_rgb_property;
struct drm_property *force_audio_property;
struct work_struct parity_error_work;
} drm_i915_private_t;
/* Iterate over initialised rings */

View File

@ -398,6 +398,86 @@ static void gen6_pm_rps_work(struct work_struct *work)
mutex_unlock(&dev_priv->dev->struct_mutex);
}
/**
* ivybridge_parity_work - Workqueue called when a parity error interrupt
* occurred.
* @work: workqueue struct
*
* Doesn't actually do anything except notify userspace. As a consequence of
* this event, userspace should try to remap the bad rows since statistically
* it is likely the same row is more likely to go bad again.
*/
static void ivybridge_parity_work(struct work_struct *work)
{
drm_i915_private_t *dev_priv = container_of(work, drm_i915_private_t,
parity_error_work);
u32 error_status, row, bank, subbank;
char *parity_event[5];
uint32_t misccpctl;
unsigned long flags;
/* 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
* any time we access those registers.
*/
mutex_lock(&dev_priv->dev->struct_mutex);
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);
I915_WRITE(GEN7_L3CDERRST1, GEN7_PARITY_ERROR_VALID |
GEN7_L3CDERRST1_ENABLE);
POSTING_READ(GEN7_L3CDERRST1);
I915_WRITE(GEN7_MISCCPCTL, misccpctl);
spin_lock_irqsave(&dev_priv->irq_lock, flags);
dev_priv->gt_irq_mask &= ~GT_GEN7_L3_PARITY_ERROR_INTERRUPT;
I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
mutex_unlock(&dev_priv->dev->struct_mutex);
parity_event[0] = "L3_PARITY_ERROR=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;
kobject_uevent_env(&dev_priv->dev->primary->kdev.kobj,
KOBJ_CHANGE, parity_event);
DRM_DEBUG("Parity error: Row = %d, Bank = %d, Sub bank = %d.\n",
row, bank, subbank);
kfree(parity_event[3]);
kfree(parity_event[2]);
kfree(parity_event[1]);
}
void ivybridge_handle_parity_error(struct drm_device *dev)
{
drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
unsigned long flags;
if (!IS_IVYBRIDGE(dev))
return;
spin_lock_irqsave(&dev_priv->irq_lock, flags);
dev_priv->gt_irq_mask |= GT_GEN7_L3_PARITY_ERROR_INTERRUPT;
I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
queue_work(dev_priv->wq, &dev_priv->parity_error_work);
}
static void snb_gt_irq_handler(struct drm_device *dev,
struct drm_i915_private *dev_priv,
u32 gt_iir)
@ -417,6 +497,9 @@ static void snb_gt_irq_handler(struct drm_device *dev,
DRM_ERROR("GT error interrupt 0x%08x\n", gt_iir);
i915_handle_error(dev, false);
}
if (gt_iir & GT_GEN7_L3_PARITY_ERROR_INTERRUPT)
ivybridge_handle_parity_error(dev);
}
static void gen6_queue_rps_work(struct drm_i915_private *dev_priv,
@ -1641,6 +1724,9 @@ static void ironlake_irq_preinstall(struct drm_device *dev)
atomic_set(&dev_priv->irq_received, 0);
if (IS_IVYBRIDGE(dev))
INIT_WORK(&dev_priv->parity_error_work, ivybridge_parity_work);
I915_WRITE(HWSTAM, 0xeffe);
/* XXX hotplug from PCH */

View File

@ -4094,6 +4094,23 @@
#define GEN6_RC6 3
#define GEN6_RC7 4
#define GEN7_MISCCPCTL (0x9424)
#define GEN7_DOP_CLOCK_GATE_ENABLE (1<<0)
/* IVYBRIDGE DPF */
#define GEN7_L3CDERRST1 0xB008 /* L3CD Error Status 1 */
#define GEN7_L3CDERRST1_ROW_MASK (0x7ff<<14)
#define GEN7_PARITY_ERROR_VALID (1<<13)
#define GEN7_L3CDERRST1_BANK_MASK (3<<11)
#define GEN7_L3CDERRST1_SUBBANK_MASK (7<<8)
#define GEN7_PARITY_ERROR_ROW(reg) \
((reg & GEN7_L3CDERRST1_ROW_MASK) >> 14)
#define GEN7_PARITY_ERROR_BANK(reg) \
((reg & GEN7_L3CDERRST1_BANK_MASK) >> 11)
#define GEN7_PARITY_ERROR_SUBBANK(reg) \
((reg & GEN7_L3CDERRST1_SUBBANK_MASK) >> 8)
#define GEN7_L3CDERRST1_ENABLE (1<<7)
#define G4X_AUD_VID_DID 0x62020
#define INTEL_AUDIO_DEVCL 0x808629FB
#define INTEL_AUDIO_DEVBLC 0x80862801