The duplication of EOP packets for GFX7/8, with the former one have
seq-1 written and the latter one have seq written, seems to confuse some
hardware platform (e.g. Loongson 7A series PCIe controllers).
Make the content of the duplicated EOP packet the same with the real
one, only masking any possible interrupts.
Fixes: bf26da927a1c ("drm/amdgpu: add cache flush workaround to gfx8 emit_fence")
Fixes: a2e73f56fa62 ("drm/amdgpu: Add support for CIK parts")
Signed-off-by: Icenowy Zheng <uwu@xxxxxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 12 +++++-------
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 12 ++++--------
2 files changed, 9 insertions(+), 15 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 541dbd70d8c75..778f27f1a34fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -2117,9 +2117,8 @@ static void gfx_v7_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr,
{
bool write64bit = flags & AMDGPU_FENCE_FLAG_64BIT;
bool int_sel = flags & AMDGPU_FENCE_FLAG_INT;
- /* Workaround for cache flush problems. First send a dummy EOP
- * event down the pipe with seq one below.
- */
+
+ /* Workaround for cache flush problems, send EOP twice. */
amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN |
EOP_TC_ACTION_EN |
@@ -2127,11 +2126,10 @@ static void gfx_v7_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr,
EVENT_INDEX(5)));
amdgpu_ring_write(ring, addr & 0xfffffffc);
amdgpu_ring_write(ring, (upper_32_bits(addr) & 0xffff) |
- DATA_SEL(1) | INT_SEL(0));
- amdgpu_ring_write(ring, lower_32_bits(seq - 1));
- amdgpu_ring_write(ring, upper_32_bits(seq - 1));
+ DATA_SEL(write64bit ? 2 : 1) | INT_SEL(0));
+ amdgpu_ring_write(ring, lower_32_bits(seq));
+ amdgpu_ring_write(ring, upper_32_bits(seq));
- /* Then send the real EOP event down the pipe. */
amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN |
EOP_TC_ACTION_EN |
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 2f0e72caee1af..39a7d60f1fd69 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -6153,9 +6153,7 @@ static void gfx_v8_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr,
bool write64bit = flags & AMDGPU_FENCE_FLAG_64BIT;
bool int_sel = flags & AMDGPU_FENCE_FLAG_INT;
- /* Workaround for cache flush problems. First send a dummy EOP
- * event down the pipe with seq one below.
- */
+ /* Workaround for cache flush problems, send EOP twice. */
amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN |
EOP_TC_ACTION_EN |
@@ -6164,12 +6162,10 @@ static void gfx_v8_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr,
EVENT_INDEX(5)));
amdgpu_ring_write(ring, addr & 0xfffffffc);
amdgpu_ring_write(ring, (upper_32_bits(addr) & 0xffff) |
- DATA_SEL(1) | INT_SEL(0));
- amdgpu_ring_write(ring, lower_32_bits(seq - 1));
- amdgpu_ring_write(ring, upper_32_bits(seq - 1));
+ DATA_SEL(write64bit ? 2 : 1) | INT_SEL(0));
+ amdgpu_ring_write(ring, lower_32_bits(seq));
+ amdgpu_ring_write(ring, upper_32_bits(seq));
- /* Then send the real EOP event down the pipe:
- * EVENT_WRITE_EOP - flush caches, send int */
amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
amdgpu_ring_write(ring, (EOP_TCL1_ACTION_EN |
EOP_TC_ACTION_EN |
--
2.45.1
