[Intel-gfx] [PATCH 1/5] drm/i915/error: capture execlist state on error

[Arun Siluvery]

On 29/01/2016 11:45, Chris Wilson wrote:
> On Fri, Jan 29, 2016 at 09:49:07AM +0200, Mika Kuoppala wrote:
>> Arun Siluvery <arun.siluvery at linux.intel.com> writes:
>>
>>> From: Dave Gordon <david.s.gordon at intel.com>
>>>
>>> At present, execlist status/ctx_id and CSBs, not the submission queue
>>>
>>> For: VIZ-2021
>>> Signed-off-by: Dave Gordon <david.s.gordon at intel.com>
>>> ---
>>>   drivers/gpu/drm/i915/i915_drv.h       |  9 +++++++++
>>>   drivers/gpu/drm/i915/i915_gpu_error.c | 38 +++++++++++++++++++++++++++++++++--
>>>   2 files changed, 45 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
>>> index 01cc982..8b30242 100644
>>> --- a/drivers/gpu/drm/i915/i915_drv.h
>>> +++ b/drivers/gpu/drm/i915/i915_drv.h
>>> @@ -552,6 +552,15 @@ struct drm_i915_error_state {
>>>   		u32 rc_psmi; /* sleep state */
>>>   		u32 semaphore_mboxes[I915_NUM_RINGS - 1];
>>>
>>> +		/* Execlists */
>>> +		u32 execlist_status;
>>> +		u32 execlist_ctx_id;
>>> +		u32 execlist_csb_raw_pointer;
>>> +		u32 execlist_csb_write_pointer;
>>> +		u32 execlist_csb_read_pointer;
>>> +		u32 execlist_csb[6];
>>> +		u32 execlist_ctx[6];
>>> +
>>>   		struct drm_i915_error_object {
>>>   			int page_count;
>>>   			u64 gtt_offset;
>>> diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
>>> index 978c026..bf53c2b 100644
>>> --- a/drivers/gpu/drm/i915/i915_gpu_error.c
>>> +++ b/drivers/gpu/drm/i915/i915_gpu_error.c
>>> @@ -247,6 +247,7 @@ static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
>>>   				  int ring_idx)
>>>   {
>>>   	struct drm_i915_error_ring *ring = &error->ring[ring_idx];
>>> +	int i;
>>>
>>>   	if (!ring->valid)
>>>   		return;
>>> @@ -288,7 +289,6 @@ static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
>>>   		err_printf(m, "  GFX_MODE: 0x%08x\n", ring->vm_info.gfx_mode);
>>>
>>>   		if (INTEL_INFO(dev)->gen >= 8) {
>>> -			int i;
>>>   			for (i = 0; i < 4; i++)
>>>   				err_printf(m, "  PDP%d: 0x%016llx\n",
>>>   					   i, ring->vm_info.pdp[i]);
>>> @@ -304,6 +304,17 @@ static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
>>>   	err_printf(m, "  hangcheck: %s [%d]\n",
>>>   		   hangcheck_action_to_str(ring->hangcheck_action),
>>>   		   ring->hangcheck_score);
>>> +
>>> +	err_printf(m, "  EXECLIST_STATUS: 0x%08x\n", ring->execlist_status);
>>> +	err_printf(m, "  EXECLIST_CTX_ID: 0x%08x\n", ring->execlist_ctx_id);
>>> +	err_printf(m, "  EXECLIST_CSBPTR: 0x%08x\n", ring->execlist_csb_raw_pointer);
>>> +	err_printf(m, "  EXECLIST_CSB_WR: 0x%08x\n", ring->execlist_csb_write_pointer);
>>> +	err_printf(m, "  EXECLIST_CSB_RD: 0x%08x\n", ring->execlist_csb_read_pointer);
>>> +
>>> +	for (i = 0; i < 6; i++) {
>>> +		err_printf(m, "  EXECLIST_CSB[%d]: 0x%08x\n", i, ring->execlist_csb[i]);
>>> +		err_printf(m, "  EXECLIST_CTX[%d]: 0x%08x\n", i, ring->execlist_ctx[i]);
>>> +	}
>>
>> Please output only if i915.enable_execlists.
>>
>>>   }
>>>
>>>   void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
>>> @@ -965,8 +976,27 @@ static void i915_record_ring_state(struct drm_device *dev,
>>>   					I915_READ(GEN8_RING_PDP_LDW(ring, i));
>>>   			}
>>>   	}
>>> -}
>>>
>>> +	if (i915.enable_execlists) {
>>> +		int i;
>>> +		u32 status_pointer = I915_READ(RING_CONTEXT_STATUS_PTR(ring));
>>> +		u8 write_pointer = status_pointer & 0x07;
>>> +		u8 read_pointer = ring->next_context_status_buffer;
>>> +		if (read_pointer > write_pointer)
>>> +			write_pointer += 6;
>>> +
>>> +		ering->execlist_status = I915_READ(RING_EXECLIST_STATUS_LO(ring));
>>> +		ering->execlist_ctx_id = I915_READ(RING_EXECLIST_STATUS_HI(ring));
>>> +		ering->execlist_csb_raw_pointer = status_pointer;
>>> +		ering->execlist_csb_write_pointer = write_pointer;
>>> +		ering->execlist_csb_read_pointer = read_pointer;
>
> Just the registers. How do you plan to use these to debug anything?
csb pointers are helpful when there is an inconsistency between sw and 
hw which can happen if we miss ctx switch interrupts.

regards
Arun

> -Chris
>