drm/i915: Sanitycheck device iomem on probe

As we setup the memory regions for the device, give each a quick test to
verify that we can read and write to the full iomem range. This ensures
that our physical addressing for the device's memory is correct, and
some reassurance that the memory is functional.

v2: wrapper for memtest [Chris]

v3: Removed the unused ptr i915 [Chris]

v4: used the %pa for the resource_size_t.
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/20211209162620.5218-1-ramalingam.c@intel.com

drivers/gpu/drm/i915/intel_memory_region.c

@@ -3,6 +3,8 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include <linux/prandom.h>
+
 #include "intel_memory_region.h"
 #include "i915_drv.h"
 #include "i915_ttm_buddy_manager.h"
@@ -29,6 +31,99 @@ static const struct {
 	},
 };
 
+static int __iopagetest(struct intel_memory_region *mem,
+			u8 __iomem *va, int pagesize,
+			u8 value, resource_size_t offset,
+			const void *caller)
+{
+	int byte = prandom_u32_max(pagesize);
+	u8 result[3];
+
+	memset_io(va, value, pagesize); /* or GPF! */
+	wmb();
+
+	result[0] = ioread8(va);
+	result[1] = ioread8(va + byte);
+	result[2] = ioread8(va + pagesize - 1);
+	if (memchr_inv(result, value, sizeof(result))) {
+		dev_err(mem->i915->drm.dev,
+			"Failed to read back from memory region:%pR at [%pa + %pa] for %ps; wrote %x, read (%x, %x, %x)\n",
+			&mem->region, &mem->io_start, &offset, caller,
+			value, result[0], result[1], result[2]);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int iopagetest(struct intel_memory_region *mem,
+		      resource_size_t offset,
+		      const void *caller)
+{
+	const u8 val[] = { 0x0, 0xa5, 0xc3, 0xf0 };
+	void __iomem *va;
+	int err;
+	int i;
+
+	va = ioremap_wc(mem->io_start + offset, PAGE_SIZE);
+	if (!va) {
+		dev_err(mem->i915->drm.dev,
+			"Failed to ioremap memory region [%pa + %pa] for %ps\n",
+			&mem->io_start, &offset, caller);
+		return -EFAULT;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(val); i++) {
+		err = __iopagetest(mem, va, PAGE_SIZE, val[i], offset, caller);
+		if (err)
+			break;
+
+		err = __iopagetest(mem, va, PAGE_SIZE, ~val[i], offset, caller);
+		if (err)
+			break;
+	}
+
+	iounmap(va);
+	return err;
+}
+
+static resource_size_t random_page(resource_size_t last)
+{
+	/* Limited to low 44b (16TiB), but should suffice for a spot check */
+	return prandom_u32_max(last >> PAGE_SHIFT) << PAGE_SHIFT;
+}
+
+static int iomemtest(struct intel_memory_region *mem, const void *caller)
+{
+	resource_size_t last = resource_size(&mem->region) - PAGE_SIZE;
+	int err;
+
+	/*
+	 * Quick test to check read/write access to the iomap (backing store).
+	 *
+	 * Write a byte, read it back. If the iomapping fails, we expect
+	 * a GPF preventing further execution. If the backing store does not
+	 * exist, the read back will return garbage. We check a couple of pages,
+	 * the first and last of the specified region to confirm the backing
+	 * store + iomap does cover the entire memory region; and we check
+	 * a random offset within as a quick spot check for bad memory.
+	 */
+
+	err = iopagetest(mem, 0, caller);
+	if (err)
+		return err;
+
+	err = iopagetest(mem, last, caller);
+	if (err)
+		return err;
+
+	err = iopagetest(mem, random_page(last), caller);
+	if (err)
+		return err;
+
+	return 0;
+}
+
 struct intel_memory_region *
 intel_memory_region_lookup(struct drm_i915_private *i915,
 			   u16 class, u16 instance)
@@ -90,6 +185,20 @@ void intel_memory_region_debug(struct intel_memory_region *mr,
 			   &mr->total, &mr->avail);
 }
 
+static int intel_memory_region_memtest(struct intel_memory_region *mem,
+				       void *caller)
+{
+	int err = 0;
+
+	if (!mem->io_start)
+		return 0;
+
+	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+		err = iomemtest(mem, caller);
+
+	return err;
+}
+
 struct intel_memory_region *
 intel_memory_region_create(struct drm_i915_private *i915,
 			   resource_size_t start,
@@ -126,8 +235,15 @@ intel_memory_region_create(struct drm_i915_private *i915,
 			goto err_free;
 	}
 
+	err = intel_memory_region_memtest(mem, (void *)_RET_IP_);
+	if (err)
+		goto err_release;
+
 	return mem;
 
+err_release:
+	if (mem->ops->release)
+		mem->ops->release(mem);
 err_free:
 	kfree(mem);
 	return ERR_PTR(err);