[PATCH v2 1/2] drm/radeon: use writel to avoid gcc optimization

[Chen Li]

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]
[   11.309961] IPv6: ADDRCONF(NETDEV_UP): enp5s0f0: link is not ready
[   11.354628]  radeon_device_init+0x53c/0xbdc [radeon]
[   11.354693]  radeon_driver_load_kms+0x6c/0x1b0 [radeon]
[   11.364788]  drm_dev_register+0x130/0x1c0
[   11.364794]  drm_get_pci_dev+0x8c/0x14c
[   11.372704]  radeon_pci_probe+0xb0/0x110 [radeon]
[   11.372715]  local_pci_probe+0x3c/0xb0
[   11.381129]  pci_device_probe+0x114/0x1b0
[   11.385121]  really_probe+0x23c/0x400
[   11.388757]  driver_probe_device+0xdc/0x130
[   11.392921]  __driver_attach+0x128/0x150
[   11.396826]  bus_for_each_dev+0x70/0xbc
[   11.400643]  driver_attach+0x20/0x2c
[   11.404201]  bus_add_driver+0x160/0x260
[   11.408019]  driver_register+0x74/0x120
[   11.411837]  __pci_register_driver+0x40/0x50
[   11.416149]  radeon_init+0x78/0x1000 [radeon]
[   11.420489]  do_one_initcall+0x54/0x154
[   11.424310]  do_init_module+0x54/0x260
[   11.428041]  load_module+0x1ccc/0x20b0
[   11.431773]  __se_sys_finit_module+0xac/0x10c
[   11.436109]  __arm64_sys_finit_module+0x18/0x20
[   11.440622]  el0_svc_common+0x70/0x164
[   11.444353]  el0_svc_handler+0x2c/0x80
[   11.448084]  el0_svc+0x8/0xc
[   11.450954] Code: d65f03c0 cb0803e4 f2400c84 54000080 (a9001d07)

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.
Signed-off-by: chenli <chenli at uniontech.com>
---
v1->v2:
* Convert the other assignments of msg as well.
* Casting types to avoid static checker warnings.

---
 drivers/gpu/drm/radeon/radeon_uvd.c | 34 ++++++++++++++---------------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 39c1c339be7b..e576470402b9 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -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), (void __iomem *)&msg[0]);
+	writel(0x0, (void __iomem *)&msg[1]);
+	writel(cpu_to_le32(handle), (void __iomem *)&msg[2]);
+	writel(0x0, (void __iomem *)&msg[3]);
+	writel(0x0, (void __iomem *)&msg[4]);
+	writel(0x0, (void __iomem *)&msg[5]);
+	writel(0x0, (void __iomem *)&msg[6]);
+	writel(cpu_to_le32(0x00000780), (void __iomem *)&msg[7]);
+	writel(cpu_to_le32(0x00000440), (void __iomem *)&msg[8]);
+	writel(0x0, (void __iomem *)&msg[9]);
+	writel(cpu_to_le32(0x01b37000), (void __iomem *)&msg[10]);
 	for (i = 11; i < 1024; ++i)
-		msg[i] = cpu_to_le32(0x0);
+		writel(0x0, (void __iomem *)&msg[i]);
 
 	r = radeon_uvd_send_msg(rdev, ring, addr, fence);
 	radeon_bo_unreserve(rdev->uvd.vcpu_bo);
@@ -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), (void __iomem *)&msg[0]);
+	writel(cpu_to_le32(0x00000002), (void __iomem *)&msg[1]);
+	writel(cpu_to_le32(handle), (void __iomem *)&msg[2]);
+	writel(0x0, (void __iomem *)&msg[3]);
 	for (i = 4; i < 1024; ++i)
-		msg[i] = cpu_to_le32(0x0);
+		writel(0x0, (void __iomem *)&msg[i]);
 
 	r = radeon_uvd_send_msg(rdev, ring, addr, fence);
 	radeon_bo_unreserve(rdev->uvd.vcpu_bo);
-- 
2.29.2