Commit d7c15d76 authored by Alan Previn's avatar Alan Previn Committed by Lucas De Marchi
Browse files

drm/i915/guc: Check sizing of guc_capture output 



Add intel_guc_capture_output_min_size_est function to
provide a reasonable minimum size for error-capture
region before allocating the shared buffer.

Signed-off-by: default avatarAlan Previn <alan.previn.teres.alexis@intel.com>
Reviewed-by: default avatarMatthew Brost <matthew.brost@intel.com>
Signed-off-by: default avatarLucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220321164527.2500062-10-alan.previn.teres.alexis@intel.com
parent daff407a

drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c

+49 −0
Original line number Diff line number Diff line
@@ -663,6 +663,55 @@ intel_guc_capture_getnullheader(struct intel_guc *guc, 
	return 0;

}



#define GUC_CAPTURE_OVERBUFFER_MULTIPLIER 3



int

intel_guc_capture_output_min_size_est(struct intel_guc *guc)

{

	struct intel_gt *gt = guc_to_gt(guc);

	struct intel_engine_cs *engine;

	enum intel_engine_id id;

	int worst_min_size = 0, num_regs = 0;

	size_t tmp = 0;



	/*

	 * If every single engine-instance suffered a failure in quick succession but

	 * were all unrelated, then a burst of multiple error-capture events would dump

	 * registers for every one engine instance, one at a time. In this case, GuC

	 * would even dump the global-registers repeatedly.

	 *

	 * For each engine instance, there would be 1 x guc_state_capture_group_t output

	 * followed by 3 x guc_state_capture_t lists. The latter is how the register

	 * dumps are split across different register types (where the '3' are global vs class

	 * vs instance). Finally, let's multiply the whole thing by 3x (just so we are

	 * not limited to just 1 round of data in a worst case full register dump log)

	 *

	 * NOTE: intel_guc_log that allocates the log buffer would round this size up to

	 * a power of two.

	 */



	for_each_engine(engine, gt, id) {

		worst_min_size += sizeof(struct guc_state_capture_group_header_t) +

				  (3 * sizeof(struct guc_state_capture_header_t));



		if (!intel_guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_GLOBAL, 0, &tmp))

			num_regs += tmp;



		if (!intel_guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_ENGINE_CLASS,

						   engine->class, &tmp)) {

			num_regs += tmp;

		}

		if (!intel_guc_capture_getlistsize(guc, 0, GUC_CAPTURE_LIST_TYPE_ENGINE_INSTANCE,

						   engine->class, &tmp)) {

			num_regs += tmp;

		}

	}



	worst_min_size += (num_regs * sizeof(struct guc_mmio_reg));



	return (worst_min_size * GUC_CAPTURE_OVERBUFFER_MULTIPLIER);

}



static void

guc_capture_free_ads_cache(struct intel_guc_state_capture *gc)

{

drivers/gpu/drm/i915/gt/uc/intel_guc_capture.h

+1 −0
Original line number Diff line number Diff line
@@ -11,6 +11,7 @@ 
struct guc_gt_system_info;

struct intel_guc;



int intel_guc_capture_output_min_size_est(struct intel_guc *guc);

int intel_guc_capture_getlist(struct intel_guc *guc, u32 owner, u32 type, u32 classid,

			      void **outptr);

int intel_guc_capture_getlistsize(struct intel_guc *guc, u32 owner, u32 type, u32 classid,

drivers/gpu/drm/i915/gt/uc/intel_guc_log.c

+5 −0
Original line number Diff line number Diff line
@@ -9,6 +9,7 @@ 
#include "i915_drv.h"

#include "i915_irq.h"

#include "i915_memcpy.h"

#include "intel_guc_capture.h"

#include "intel_guc_log.h"



static void guc_log_copy_debuglogs_for_relay(struct intel_guc_log *log);
@@ -465,6 +466,10 @@ int intel_guc_log_create(struct intel_guc_log *log) 
	 *  |         Capture logs          |

	 *  +===============================+ + CAPTURE_SIZE

	 */

	if (intel_guc_capture_output_min_size_est(guc) > CAPTURE_BUFFER_SIZE)

		DRM_WARN("GuC log buffer for state_capture maybe too small. %d < %d\n",

			 CAPTURE_BUFFER_SIZE, intel_guc_capture_output_min_size_est(guc));



	guc_log_size = PAGE_SIZE + CRASH_BUFFER_SIZE + DEBUG_BUFFER_SIZE +

		       CAPTURE_BUFFER_SIZE;