Revert "drm/amdgpu: fix transform feedback GDS hang on gfx10 (v2)"
Subsystems (2)
PATCH 1/1 Revert "drm/amdgpu: fix transform feedback GDS hang on gfx10 (v2)"
From: Marek Olšák <[email protected]>
This reverts commit b41335c6c0303d100abe89c843e52645d1974cd9.
SET_CONFIG_REG writes to memory if register shadowing is enabled, causing a VM fault.
NGG streamout is unstable anyway, so all UMDs should use legacy streamout. I think Mesa is the only driver using NGG streamout.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_gds.h | 1 - drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 12 +----------- 2 files changed, 1 insertion(+), 12 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_gds.h +0 -1
@@ -25,21 +25,20 @@#define __AMDGPU_GDS_H__struct amdgpu_ring ;struct amdgpu_bo ;struct amdgpu_gds {uint32_t gds_size;uint32_t gws_size;uint32_t oa_size;uint32_t gds_compute_max_wave_id; -uint32_t vgt_gs_max_wave_id; };struct amdgpu_gds_reg_offset {uint32_t mem_base;uint32_t mem_size;uint32_t gws;uint32_t oa; };#endif /* __AMDGPU_GDS_H__ */
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +1 -11
@@ -4269,29 +4269,20 @@ static void gfx_v10_0_ring_emit_hdp_flush(struct amdgpu_ring *ring) }static void gfx_v10_0_ring_emit_ib_gfx (struct amdgpu_ring *ring,struct amdgpu_job *job,struct amdgpu_ib *ib,uint32_t flags) {unsigned vmid =AMDGPU_JOB_GET_VMID (job);u32 header, control =0 ; -/* Prevent a hw deadlock due to a wave ID mismatch between ME and GDS. -* This resets the wave ID counters. (needed by transform feedback) -* TODO: This might only be needed on a VMID switch when we change -* the GDS OA mapping, not sure. -*/ -amdgpu_ring_write (ring,PACKET3 (PACKET3_SET_CONFIG_REG ,1 )); -amdgpu_ring_write (ring, mmVGT_GS_MAX_WAVE_ID); -amdgpu_ring_write (ring, ring->adev->gds.vgt_gs_max_wave_id); -if (ib->flags &AMDGPU_IB_FLAG_CE ) header =PACKET3 (PACKET3_INDIRECT_BUFFER_CNST ,2 );else header =PACKET3 (PACKET3_INDIRECT_BUFFER ,2 ); control |= ib->length_dw | (vmid <<24 );if (amdgpu_mcbp && (ib->flags &AMDGPU_IB_FLAG_PREEMPT )) { control |=INDIRECT_BUFFER_PRE_ENB (1 );
@@ -5023,21 +5014,21 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = {*/ 5 +/* COND_EXEC */ 7 +/* HDP_flush */ 4 +/* VGT_flush */ 14 +/* CE_META */ 31 +/* DE_META */ 3 +/* CNTX_CTRL */ 5 +/* HDP_INVL */ 8 +8 +/* FENCE x2 */ 2, /* SWITCH_BUFFER */ - .emit_ib_size = 7, /* gfx_v10_0_ring_emit_ib_gfx */ + .emit_ib_size = 4, /* gfx_v10_0_ring_emit_ib_gfx */ .emit_ib = gfx_v10_0_ring_emit_ib_gfx, .emit_fence = gfx_v10_0_ring_emit_fence, .emit_pipeline_sync = gfx_v10_0_ring_emit_pipeline_sync, .emit_vm_flush = gfx_v10_0_ring_emit_vm_flush, .emit_gds_switch = gfx_v10_0_ring_emit_gds_switch, .emit_hdp_flush = gfx_v10_0_ring_emit_hdp_flush, .test_ring = gfx_v10_0_ring_test_ring, .test_ib = gfx_v10_0_ring_test_ib, .insert_nop = amdgpu_ring_insert_nop, .pad_ib = amdgpu_ring_generic_pad_ib,
@@ -5175,21 +5166,20 @@ static void gfx_v10_0_set_rlc_funcs(struct amdgpu_device *adev) }static void gfx_v10_0_set_gds_init (struct amdgpu_device *adev) {/* init asic gds info */ switch (adev->asic_type) {case CHIP_NAVI10 :default : adev->gds.gds_size =0x10000 ; adev->gds.gds_compute_max_wave_id =0x4ff ; - adev->gds.vgt_gs_max_wave_id =0x3ff ;break ; } adev->gds.gws_size =64 ; adev->gds.oa_size =16 ; }static void gfx_v10_0_set_user_wgp_inactive_bitmap_per_sh (struct amdgpu_device *adev,u32 bitmap) {
Signature · 6 lines
2.17.1 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 20190802222703.428-1-maraeo-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org
Ma, Le
Reviewed-by Le Ma-----Original Message-----
From: amd-gfx <[email protected]> On Behalf Of Marek Ol?ák
Sent: Saturday, August 03, 2019 6:27 AM
To: [email protected]
Subject: [PATCH] Revert "drm/amdgpu: fix transform feedback GDS hang on gfx10 (v2)"
From: Marek Olšák <[email protected]>
This reverts commit b41335c6c0303d100abe89c843e52645d1974cd9.
SET_CONFIG_REG writes to memory if register shadowing is enabled, causing a VM fault.
NGG streamout is unstable anyway, so all UMDs should use legacy streamout. I think Mesa is the only driver using NGG streamout.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_gds.h | 1 - drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 12 +----------- 2 files changed, 1 insertion(+), 12 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_gds.h +0 -1
@@ -25,21 +25,20 @@#define __AMDGPU_GDS_H__struct amdgpu_ring ;struct amdgpu_bo ;struct amdgpu_gds {uint32_t gds_size;uint32_t gws_size;uint32_t oa_size;uint32_t gds_compute_max_wave_id; -uint32_t vgt_gs_max_wave_id; };struct amdgpu_gds_reg_offset {uint32_t mem_base;uint32_t mem_size;uint32_t gws;uint32_t oa; };#endif /* __AMDGPU_GDS_H__ */
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +1 -12
@@ -4269,29 +4269,20 @@ static void gfx_v10_0_ring_emit_hdp_flush(struct amdgpu_ring *ring) }static void gfx_v10_0_ring_emit_ib_gfx (struct amdgpu_ring *ring,struct amdgpu_job *job,struct amdgpu_ib *ib,uint32_t flags) {unsigned vmid =AMDGPU_JOB_GET_VMID (job);u32 header, control =0 ; -/* Prevent a hw deadlock due to a wave ID mismatch between ME and GDS. -* This resets the wave ID counters. (needed by transform feedback) -* TODO: This might only be needed on a VMID switch when we change -* the GDS OA mapping, not sure. -*/ -amdgpu_ring_write (ring,PACKET3 (PACKET3_SET_CONFIG_REG ,1 )); -amdgpu_ring_write (ring, mmVGT_GS_MAX_WAVE_ID); -amdgpu_ring_write (ring, ring->adev->gds.vgt_gs_max_wave_id); -if (ib->flags &AMDGPU_IB_FLAG_CE ) header =PACKET3 (PACKET3_INDIRECT_BUFFER_CNST ,2 );else header =PACKET3 (PACKET3_INDIRECT_BUFFER ,2 ); control |= ib->length_dw | (vmid <<24 );if (amdgpu_mcbp && (ib->flags &AMDGPU_IB_FLAG_PREEMPT )) { control |=INDIRECT_BUFFER_PRE_ENB (1 );
@@ -5023,21 +5014,21 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = {*/ 5 +/* COND_EXEC */ 7 +/* HDP_flush */ 4 +/* VGT_flush */ 14 +/* CE_META */ 31 +/* DE_META */ 3 +/* CNTX_CTRL */ 5 +/* HDP_INVL */ 8 +8 +/* FENCE x2 */ 2, /* SWITCH_BUFFER */ - .emit_ib_size = 7, /* gfx_v10_0_ring_emit_ib_gfx */ + .emit_ib_size = 4, /* gfx_v10_0_ring_emit_ib_gfx */ .emit_ib = gfx_v10_0_ring_emit_ib_gfx, .emit_fence = gfx_v10_0_ring_emit_fence, .emit_pipeline_sync = gfx_v10_0_ring_emit_pipeline_sync, .emit_vm_flush = gfx_v10_0_ring_emit_vm_flush, .emit_gds_switch = gfx_v10_0_ring_emit_gds_switch, .emit_hdp_flush = gfx_v10_0_ring_emit_hdp_flush, .test_ring = gfx_v10_0_ring_test_ring, .test_ib = gfx_v10_0_ring_test_ib, .insert_nop = amdgpu_ring_insert_nop, .pad_ib = amdgpu_ring_generic_pad_ib,
@@ -5175,21 +5166,20 @@ static void gfx_v10_0_set_rlc_funcs(struct amdgpu_device *adev) }static void gfx_v10_0_set_gds_init (struct amdgpu_device *adev) {/* init asic gds info */ switch (adev->asic_type) {case CHIP_NAVI10 :default : adev->gds.gds_size =0x10000 ; adev->gds.gds_compute_max_wave_id =0x4ff ; - adev->gds.vgt_gs_max_wave_id =0x3ff ;break ; } adev->gds.gws_size =64 ; adev->gds.oa_size =16 ; }static void gfx_v10_0_set_user_wgp_inactive_bitmap_per_sh (struct amdgpu_device *adev,u32 bitmap) { --
2.17.1
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx