drm/i915: Test all device memory on probing

This extends the previous sanitychecking of device memory to read/write
all the memory on the device during the device probe, ala memtest86,
as an optional module parameter: i915.memtest=1. This is not expected to
be fast, but a reasonably thorough verfification that the device memory
is accessible and doesn't return bit errors.

v2: Rebased.
Suggested-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211208153404.27546-4-ramalingam.c@intel.com

drivers/gpu/drm/i915/i915_params.c

@@ -140,6 +140,9 @@ i915_param_named_unsafe(invert_brightness, int, 0400,
 i915_param_named(disable_display, bool, 0400,
 	"Disable display (default: false)");
 
+i915_param_named(memtest, bool, 0400,
+	"Perform a read/write test of all device memory on module load (default: off)");
+
 i915_param_named(mmio_debug, int, 0400,
 	"Enable the MMIO debug code for the first N failures (default: off). "
 	"This may negatively affect performance.");

drivers/gpu/drm/i915/i915_params.h

@@ -64,6 +64,7 @@ struct drm_printer;
 	param(char *, guc_firmware_path, NULL, 0400) \
 	param(char *, huc_firmware_path, NULL, 0400) \
 	param(char *, dmc_firmware_path, NULL, 0400) \
+	param(bool, memtest, false, 0400) \
 	param(int, mmio_debug, -IS_ENABLED(CONFIG_DRM_I915_DEBUG_MMIO), 0600) \
 	param(int, edp_vswing, 0, 0400) \
 	param(unsigned int, reset, 3, 0600) \

drivers/gpu/drm/i915/intel_memory_region.c

@@ -93,9 +93,12 @@ static resource_size_t random_page(resource_size_t last)
 	return prandom_u32_max(last >> PAGE_SHIFT) << PAGE_SHIFT;
 }
 
-static int iomemtest(struct intel_memory_region *mem, const void *caller)
+static int iomemtest(struct intel_memory_region *mem,
+		     bool test_all,
+		     const void *caller)
 {
 	resource_size_t last = resource_size(&mem->region) - PAGE_SIZE;
+	resource_size_t page;
 	int err;
 
 	/*
@@ -109,6 +112,13 @@ static int iomemtest(struct intel_memory_region *mem, const void *caller)
 	 * a random offset within as a quick spot check for bad memory.
 	 */
 
+	if (test_all) {
+		for (page = 0; page <= last; page += PAGE_SIZE) {
+			err = iopagetest(mem, page, caller);
+			if (err)
+				return err;
+		}
+	} else {
 		err = iopagetest(mem, 0, caller);
 		if (err)
 			return err;
@@ -120,6 +130,7 @@ static int iomemtest(struct intel_memory_region *mem, const void *caller)
 		err = iopagetest(mem, random_page(last), caller);
 		if (err)
 			return err;
+	}
 
 	return 0;
 }
@@ -188,13 +199,14 @@ void intel_memory_region_debug(struct intel_memory_region *mr,
 static int intel_memory_region_memtest(struct intel_memory_region *mem,
 				       void *caller)
 {
+	struct drm_i915_private *i915 = mem->i915;
 	int err = 0;
 
 	if (!mem->io_start)
 		return 0;
 
-	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
-		err = iomemtest(mem, caller);
+	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) || i915->params.memtest)
+		err = iomemtest(mem, i915->params.memtest, caller);
 
 	return err;
 }