[Intel-gfx] [PATCH] drm/i915: Add extra registers to GPU error dump

[Souza, Jose]

On Wed, 2022-06-01 at 14:06 -0700, Matt Roper wrote:
> From: Stuart Summers <stuart.summers at intel.com>
> 
> Our internal teams have identified a few additional engine registers
> that are worth inspecting in error state dumps during development &
> debug.  Let's capture and print them as part of our error dump.
> 
> For simplicity we'll just dump these registers on gen11 and beyond.
> Most of these registers have existed since earlier platforms (e.g., gen6
> or gen7) but were initially introduced only for a subset of the
> platforms' engines; gen11 seems to be where they became available on all
> engines.

Reviewed-by: José Roberto de Souza <jose.souza at intel.com>

> 
> Signed-off-by: Stuart Summers <stuart.summers at intel.com>
> Signed-off-by: Matt Roper <matthew.d.roper at intel.com>
> ---
>  drivers/gpu/drm/i915/gt/intel_engine_regs.h |  5 +++++
>  drivers/gpu/drm/i915/i915_gpu_error.c       | 19 +++++++++++++++++++
>  drivers/gpu/drm/i915/i915_gpu_error.h       |  7 +++++++
>  3 files changed, 31 insertions(+)
> 
> diff --git a/drivers/gpu/drm/i915/gt/intel_engine_regs.h b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
> index 44de10cf7837..889f0df3940b 100644
> --- a/drivers/gpu/drm/i915/gt/intel_engine_regs.h
> +++ b/drivers/gpu/drm/i915/gt/intel_engine_regs.h
> @@ -8,6 +8,7 @@
>  
>  #include "i915_reg_defs.h"
>  
> +#define RING_EXCC(base)				_MMIO((base) + 0x28)
>  #define RING_TAIL(base)				_MMIO((base) + 0x30)
>  #define   TAIL_ADDR				0x001FFFF8
>  #define RING_HEAD(base)				_MMIO((base) + 0x34)
> @@ -133,6 +134,8 @@
>  		(REG_FIELD_PREP(BLIT_CCTL_DST_MOCS_MASK, (dst) << 1) | \
>  		 REG_FIELD_PREP(BLIT_CCTL_SRC_MOCS_MASK, (src) << 1))
>  
> +#define RING_CSCMDOP(base)			_MMIO((base) + 0x20c)
> +
>  /*
>   * CMD_CCTL read/write fields take a MOCS value and _not_ a table index.
>   * The lsb of each can be considered a separate enabling bit for encryption.
> @@ -149,6 +152,7 @@
>  		 REG_FIELD_PREP(CMD_CCTL_READ_OVERRIDE_MASK, (read) << 1))
>  
>  #define RING_PREDICATE_RESULT(base)		_MMIO((base) + 0x3b8) /* gen12+ */
> +
>  #define MI_PREDICATE_RESULT_2(base)		_MMIO((base) + 0x3bc)
>  #define   LOWER_SLICE_ENABLED			(1 << 0)
>  #define   LOWER_SLICE_DISABLED			(0 << 0)
> @@ -172,6 +176,7 @@
>  #define	  CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT	REG_BIT(2)
>  #define	  CTX_CTRL_INHIBIT_SYN_CTX_SWITCH	REG_BIT(3)
>  #define	  GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE	REG_BIT(8)
> +#define RING_CTX_SR_CTL(base)			_MMIO((base) + 0x244)
>  #define RING_SEMA_WAIT_POLL(base)		_MMIO((base) + 0x24c)
>  #define GEN8_RING_PDP_UDW(base, n)		_MMIO((base) + 0x270 + (n) * 8 + 4)
>  #define GEN8_RING_PDP_LDW(base, n)		_MMIO((base) + 0x270 + (n) * 8)
> diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
> index 0512c66fa4f3..bff8a111424a 100644
> --- a/drivers/gpu/drm/i915/i915_gpu_error.c
> +++ b/drivers/gpu/drm/i915/i915_gpu_error.c
> @@ -581,6 +581,15 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
>  		err_printf(m, "  RC PSMI: 0x%08x\n", ee->rc_psmi);
>  		err_printf(m, "  FAULT_REG: 0x%08x\n", ee->fault_reg);
>  	}
> +	if (GRAPHICS_VER(m->i915) >= 11) {
> +		err_printf(m, "  NOPID: 0x%08x\n", ee->nopid);
> +		err_printf(m, "  EXCC: 0x%08x\n", ee->excc);
> +		err_printf(m, "  CMD_CCTL: 0x%08x\n", ee->cmd_cctl);
> +		err_printf(m, "  CSCMDOP: 0x%08x\n", ee->cscmdop);
> +		err_printf(m, "  CTX_SR_CTL: 0x%08x\n", ee->ctx_sr_ctl);
> +		err_printf(m, "  DMA_FADDR_HI: 0x%08x\n", ee->dma_faddr_hi);
> +		err_printf(m, "  DMA_FADDR_LO: 0x%08x\n", ee->dma_faddr_lo);
> +	}
>  	if (HAS_PPGTT(m->i915)) {
>  		err_printf(m, "  GFX_MODE: 0x%08x\n", ee->vm_info.gfx_mode);
>  
> @@ -1224,6 +1233,16 @@ static void engine_record_registers(struct intel_engine_coredump *ee)
>  		ee->ipehr = ENGINE_READ(engine, IPEHR);
>  	}
>  
> +	if (GRAPHICS_VER(i915) >= 11) {
> +		ee->cmd_cctl = ENGINE_READ(engine, RING_CMD_CCTL);
> +		ee->cscmdop = ENGINE_READ(engine, RING_CSCMDOP);
> +		ee->ctx_sr_ctl = ENGINE_READ(engine, RING_CTX_SR_CTL);
> +		ee->dma_faddr_hi = ENGINE_READ(engine, RING_DMA_FADD_UDW);
> +		ee->dma_faddr_lo = ENGINE_READ(engine, RING_DMA_FADD);
> +		ee->nopid = ENGINE_READ(engine, RING_NOPID);
> +		ee->excc = ENGINE_READ(engine, RING_EXCC);
> +	}
> +
>  	intel_engine_get_instdone(engine, &ee->instdone);
>  
>  	ee->instpm = ENGINE_READ(engine, RING_INSTPM);
> diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
> index a611abacd9c2..55a143b92d10 100644
> --- a/drivers/gpu/drm/i915/i915_gpu_error.h
> +++ b/drivers/gpu/drm/i915/i915_gpu_error.h
> @@ -84,6 +84,13 @@ struct intel_engine_coredump {
>  	u32 fault_reg;
>  	u64 faddr;
>  	u32 rc_psmi; /* sleep state */
> +	u32 nopid;
> +	u32 excc;
> +	u32 cmd_cctl;
> +	u32 cscmdop;
> +	u32 ctx_sr_ctl;
> +	u32 dma_faddr_hi;
> +	u32 dma_faddr_lo;
>  	struct intel_instdone instdone;
>  
>  	/* GuC matched capture-lists info */