drm/radeon: use writel to avoid gcc optimization v3

When using e8860(gcn1) on arm64, the kernel crashed on drm/radeon:

[   11.240414] pc : __memset+0x4c/0x188
[   11.244101] lr : radeon_uvd_get_create_msg+0x114/0x1d0 [radeon]
[   11.249995] sp : ffff00000d7eb700
[   11.253295] x29: ffff00000d7eb700 x28: ffff8001f632a868
[   11.258585] x27: 0000000000040000 x26: ffff00000de00000
[   11.263875] x25: 0000000000000125 x24: 0000000000000001
[   11.269168] x23: 0000000000000000 x22: 0000000000000005
[   11.274459] x21: ffff00000df24000 x20: ffff8001f74b4000
[   11.279753] x19: 0000000000124000 x18: 0000000000000020
[   11.285043] x17: 0000000000000000 x16: 0000000000000000
[   11.290336] x15: ffff000009309000 x14: ffffffffffffffff
[   11.290340] x13: ffff0000094b6f88 x12: ffff0000094b6bd2
[   11.290343] x11: ffff00000d7eb700 x10: ffff00000d7eb700
[   11.306246] x9 : ffff00000d7eb700 x8 : ffff00000df2402c
[   11.306254] x7 : 0000000000000000 x6 : ffff0000094b626a
[   11.306257] x5 : 0000000000000000 x4 : 0000000000000004
[   11.306262] x3 : ffffffffffffffff x2 : 0000000000000fd4
[   11.306265] x1 : 0000000000000000 x0 : ffff00000df2402c
[   11.306272] Call trace:
[   11.306316]  __memset+0x4c/0x188
[   11.306638]  uvd_v1_0_ib_test+0x70/0x1c0 [radeon]
[   11.306758]  radeon_ib_ring_tests+0x54/0xe0 [radeon]
...

Obviously, the __memset call is generated by gcc(8.3.1). It optimizes
this for loop into memset. But this may break on some platforms which
cannot map device memory correctly. So, just invoke `writel` to handle this.

v3 (chk): minor cleanups in code and commit message
Signed-off-by: Chen Li <chenli@uniontech.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/radeon/radeon_uvd.c

@@ -781,7 +781,7 @@ int radeon_uvd_get_create_msg(struct radeon_device *rdev, int ring,
 	uint64_t offs = radeon_bo_size(rdev->uvd.vcpu_bo) -
 		RADEON_GPU_PAGE_SIZE;
 
-	uint32_t *msg = rdev->uvd.cpu_addr + offs;
+	uint32_t __iomem *msg = (void __iomem *)(rdev->uvd.cpu_addr + offs);
 	uint64_t addr = rdev->uvd.gpu_addr + offs;
 
 	int r, i;
@@ -791,19 +791,19 @@ int radeon_uvd_get_create_msg(struct radeon_device *rdev, int ring,
 		return r;
 
 	/* stitch together an UVD create msg */
-	msg[0] = cpu_to_le32(0x00000de4);
-	msg[1] = cpu_to_le32(0x00000000);
-	msg[2] = cpu_to_le32(handle);
-	msg[3] = cpu_to_le32(0x00000000);
-	msg[4] = cpu_to_le32(0x00000000);
-	msg[5] = cpu_to_le32(0x00000000);
-	msg[6] = cpu_to_le32(0x00000000);
-	msg[7] = cpu_to_le32(0x00000780);
-	msg[8] = cpu_to_le32(0x00000440);
-	msg[9] = cpu_to_le32(0x00000000);
-	msg[10] = cpu_to_le32(0x01b37000);
+	writel(cpu_to_le32(0x00000de4), &msg[0]);
+	writel(0x0, (void __iomem *)&msg[1]);
+	writel(cpu_to_le32(handle), &msg[2]);
+	writel(0x0, &msg[3]);
+	writel(0x0, &msg[4]);
+	writel(0x0, &msg[5]);
+	writel(0x0, &msg[6]);
+	writel(cpu_to_le32(0x00000780), &msg[7]);
+	writel(cpu_to_le32(0x00000440), &msg[8]);
+	writel(0x0, &msg[9]);
+	writel(cpu_to_le32(0x01b37000), &msg[10]);
 	for (i = 11; i < 1024; ++i)
-		msg[i] = cpu_to_le32(0x0);
+		writel(0x0, &msg[i]);
 
 	r = radeon_uvd_send_msg(rdev, ring, addr, fence);
 	radeon_bo_unreserve(rdev->uvd.vcpu_bo);
@@ -817,7 +817,7 @@ int radeon_uvd_get_destroy_msg(struct radeon_device *rdev, int ring,
 	uint64_t offs = radeon_bo_size(rdev->uvd.vcpu_bo) -
 		RADEON_GPU_PAGE_SIZE;
 
-	uint32_t *msg = rdev->uvd.cpu_addr + offs;
+	uint32_t __iomem *msg = (void __iomem *)(rdev->uvd.cpu_addr + offs);
 	uint64_t addr = rdev->uvd.gpu_addr + offs;
 
 	int r, i;
@@ -827,12 +827,12 @@ int radeon_uvd_get_destroy_msg(struct radeon_device *rdev, int ring,
 		return r;
 
 	/* stitch together an UVD destroy msg */
-	msg[0] = cpu_to_le32(0x00000de4);
-	msg[1] = cpu_to_le32(0x00000002);
-	msg[2] = cpu_to_le32(handle);
-	msg[3] = cpu_to_le32(0x00000000);
+	writel(cpu_to_le32(0x00000de4), &msg[0]);
+	writel(cpu_to_le32(0x00000002), &msg[1]);
+	writel(cpu_to_le32(handle), &msg[2]);
+	writel(0x0, &msg[3]);
 	for (i = 4; i < 1024; ++i)
-		msg[i] = cpu_to_le32(0x0);
+		writel(0x0, &msg[i]);
 
 	r = radeon_uvd_send_msg(rdev, ring, addr, fence);
 	radeon_bo_unreserve(rdev->uvd.vcpu_bo);