From 1543e317f1da31b75942316931e8f491a8920811 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Thu, 04 Jan 2024 10:08:02 +0000
Subject: [PATCH] disable FB
---
kernel/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 217 ++++++++++++++++++++++++++++++------------------------
1 files changed, 120 insertions(+), 97 deletions(-)
diff --git a/kernel/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/kernel/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index de184a8..79c52c7 100644
--- a/kernel/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/kernel/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -21,6 +21,8 @@
*
*/
#include <linux/firmware.h>
+#include <linux/module.h>
+
#include "amdgpu.h"
#include "amdgpu_ih.h"
#include "amdgpu_gfx.h"
@@ -782,6 +784,25 @@
BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[18] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_1D_TILED_THICK) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16);
+ tilemode[19] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_XTHICK) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ TILE_SPLIT(split_equal_to_row_size);
+ tilemode[20] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THICK) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ TILE_SPLIT(split_equal_to_row_size);
tilemode[21] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
@@ -1552,10 +1573,10 @@
adev->gfx.config.double_offchip_lds_buf = 0;
}
-static void gfx_v6_0_gpu_init(struct amdgpu_device *adev)
+static void gfx_v6_0_constants_init(struct amdgpu_device *adev)
{
u32 gb_addr_config = 0;
- u32 mc_shared_chmap, mc_arb_ramcfg;
+ u32 mc_arb_ramcfg;
u32 sx_debug_1;
u32 hdp_host_path_cntl;
u32 tmp;
@@ -1657,7 +1678,6 @@
WREG32(mmBIF_FB_EN, BIF_FB_EN__FB_READ_EN_MASK | BIF_FB_EN__FB_WRITE_EN_MASK);
- mc_shared_chmap = RREG32(mmMC_SHARED_CHMAP);
adev->gfx.config.mc_arb_ramcfg = RREG32(mmMC_ARB_RAMCFG);
mc_arb_ramcfg = adev->gfx.config.mc_arb_ramcfg;
@@ -1775,18 +1795,15 @@
int r;
r = amdgpu_gfx_scratch_get(adev, &scratch);
- if (r) {
- DRM_ERROR("amdgpu: cp failed to get scratch reg (%d).\n", r);
+ if (r)
return r;
- }
+
WREG32(scratch, 0xCAFEDEAD);
r = amdgpu_ring_alloc(ring, 3);
- if (r) {
- DRM_ERROR("amdgpu: cp failed to lock ring %d (%d).\n", ring->idx, r);
- amdgpu_gfx_scratch_free(adev, scratch);
- return r;
- }
+ if (r)
+ goto error_free_scratch;
+
amdgpu_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
amdgpu_ring_write(ring, (scratch - PACKET3_SET_CONFIG_REG_START));
amdgpu_ring_write(ring, 0xDEADBEEF);
@@ -1796,15 +1813,13 @@
tmp = RREG32(scratch);
if (tmp == 0xDEADBEEF)
break;
- DRM_UDELAY(1);
+ udelay(1);
}
- if (i < adev->usec_timeout) {
- DRM_DEBUG("ring test on %d succeeded in %d usecs\n", ring->idx, i);
- } else {
- DRM_ERROR("amdgpu: ring %d test failed (scratch(0x%04X)=0x%08X)\n",
- ring->idx, scratch, tmp);
- r = -EINVAL;
- }
+
+ if (i >= adev->usec_timeout)
+ r = -ETIMEDOUT;
+
+error_free_scratch:
amdgpu_gfx_scratch_free(adev, scratch);
return r;
}
@@ -1845,13 +1860,15 @@
}
static void gfx_v6_0_ring_emit_ib(struct amdgpu_ring *ring,
+ struct amdgpu_job *job,
struct amdgpu_ib *ib,
- unsigned vmid, bool ctx_switch)
+ uint32_t flags)
{
+ unsigned vmid = AMDGPU_JOB_GET_VMID(job);
u32 header, control = 0;
/* insert SWITCH_BUFFER packet before first IB in the ring frame */
- if (ctx_switch) {
+ if (flags & AMDGPU_HAVE_CTX_SWITCH) {
amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
amdgpu_ring_write(ring, 0);
}
@@ -1892,17 +1909,16 @@
long r;
r = amdgpu_gfx_scratch_get(adev, &scratch);
- if (r) {
- DRM_ERROR("amdgpu: failed to get scratch reg (%ld).\n", r);
+ if (r)
return r;
- }
+
WREG32(scratch, 0xCAFEDEAD);
memset(&ib, 0, sizeof(ib));
- r = amdgpu_ib_get(adev, NULL, 256, &ib);
- if (r) {
- DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
+ r = amdgpu_ib_get(adev, NULL, 256,
+ AMDGPU_IB_POOL_DIRECT, &ib);
+ if (r)
goto err1;
- }
+
ib.ptr[0] = PACKET3(PACKET3_SET_CONFIG_REG, 1);
ib.ptr[1] = ((scratch - PACKET3_SET_CONFIG_REG_START));
ib.ptr[2] = 0xDEADBEEF;
@@ -1914,22 +1930,16 @@
r = dma_fence_wait_timeout(f, false, timeout);
if (r == 0) {
- DRM_ERROR("amdgpu: IB test timed out\n");
r = -ETIMEDOUT;
goto err2;
} else if (r < 0) {
- DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
goto err2;
}
tmp = RREG32(scratch);
- if (tmp == 0xDEADBEEF) {
- DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
+ if (tmp == 0xDEADBEEF)
r = 0;
- } else {
- DRM_ERROR("amdgpu: ib test failed (scratch(0x%04X)=0x%08X)\n",
- scratch, tmp);
+ else
r = -EINVAL;
- }
err2:
amdgpu_ib_free(adev, &ib, NULL);
@@ -1941,7 +1951,6 @@
static void gfx_v6_0_cp_gfx_enable(struct amdgpu_device *adev, bool enable)
{
- int i;
if (enable) {
WREG32(mmCP_ME_CNTL, 0);
} else {
@@ -1949,10 +1958,6 @@
CP_ME_CNTL__PFP_HALT_MASK |
CP_ME_CNTL__CE_HALT_MASK));
WREG32(mmSCRATCH_UMSK, 0);
- for (i = 0; i < adev->gfx.num_gfx_rings; i++)
- adev->gfx.gfx_ring[i].ready = false;
- for (i = 0; i < adev->gfx.num_compute_rings; i++)
- adev->gfx.compute_ring[i].ready = false;
}
udelay(50);
}
@@ -2124,12 +2129,9 @@
/* start the rings */
gfx_v6_0_cp_gfx_start(adev);
- ring->ready = true;
- r = amdgpu_ring_test_ring(ring);
- if (r) {
- ring->ready = false;
+ r = amdgpu_ring_test_helper(ring);
+ if (r)
return r;
- }
return 0;
}
@@ -2227,14 +2229,11 @@
WREG32(mmCP_RB2_CNTL, tmp);
WREG32(mmCP_RB2_BASE, ring->gpu_addr >> 8);
- adev->gfx.compute_ring[0].ready = false;
- adev->gfx.compute_ring[1].ready = false;
for (i = 0; i < 2; i++) {
- r = amdgpu_ring_test_ring(&adev->gfx.compute_ring[i]);
+ r = amdgpu_ring_test_helper(&adev->gfx.compute_ring[i]);
if (r)
return r;
- adev->gfx.compute_ring[i].ready = true;
}
return 0;
@@ -2368,18 +2367,11 @@
amdgpu_ring_write(ring, val);
}
-static void gfx_v6_0_rlc_fini(struct amdgpu_device *adev)
-{
- amdgpu_bo_free_kernel(&adev->gfx.rlc.save_restore_obj, NULL, NULL);
- amdgpu_bo_free_kernel(&adev->gfx.rlc.clear_state_obj, NULL, NULL);
- amdgpu_bo_free_kernel(&adev->gfx.rlc.cp_table_obj, NULL, NULL);
-}
-
static int gfx_v6_0_rlc_init(struct amdgpu_device *adev)
{
const u32 *src_ptr;
volatile u32 *dst_ptr;
- u32 dws, i;
+ u32 dws;
u64 reg_list_mc_addr;
const struct cs_section_def *cs_data;
int r;
@@ -2394,26 +2386,10 @@
cs_data = adev->gfx.rlc.cs_data;
if (src_ptr) {
- /* save restore block */
- r = amdgpu_bo_create_reserved(adev, dws * 4, PAGE_SIZE,
- AMDGPU_GEM_DOMAIN_VRAM,
- &adev->gfx.rlc.save_restore_obj,
- &adev->gfx.rlc.save_restore_gpu_addr,
- (void **)&adev->gfx.rlc.sr_ptr);
- if (r) {
- dev_warn(adev->dev, "(%d) create RLC sr bo failed\n",
- r);
- gfx_v6_0_rlc_fini(adev);
+ /* init save restore block */
+ r = amdgpu_gfx_rlc_init_sr(adev, dws);
+ if (r)
return r;
- }
-
- /* write the sr buffer */
- dst_ptr = adev->gfx.rlc.sr_ptr;
- for (i = 0; i < adev->gfx.rlc.reg_list_size; i++)
- dst_ptr[i] = cpu_to_le32(src_ptr[i]);
-
- amdgpu_bo_kunmap(adev->gfx.rlc.save_restore_obj);
- amdgpu_bo_unreserve(adev->gfx.rlc.save_restore_obj);
}
if (cs_data) {
@@ -2428,7 +2404,7 @@
(void **)&adev->gfx.rlc.cs_ptr);
if (r) {
dev_warn(adev->dev, "(%d) create RLC c bo failed\n", r);
- gfx_v6_0_rlc_fini(adev);
+ amdgpu_gfx_rlc_fini(adev);
return r;
}
@@ -2549,8 +2525,8 @@
if (!adev->gfx.rlc_fw)
return -EINVAL;
- gfx_v6_0_rlc_stop(adev);
- gfx_v6_0_rlc_reset(adev);
+ adev->gfx.rlc.funcs->stop(adev);
+ adev->gfx.rlc.funcs->reset(adev);
gfx_v6_0_init_pg(adev);
gfx_v6_0_init_cg(adev);
@@ -2578,7 +2554,7 @@
WREG32(mmRLC_UCODE_ADDR, 0);
gfx_v6_0_enable_lbpw(adev, gfx_v6_0_lbpw_supported(adev));
- gfx_v6_0_rlc_start(adev);
+ adev->gfx.rlc.funcs->start(adev);
return 0;
}
@@ -3062,7 +3038,7 @@
}
static void gfx_v6_0_select_me_pipe_q(struct amdgpu_device *adev,
- u32 me, u32 pipe, u32 q)
+ u32 me, u32 pipe, u32 q, u32 vm)
{
DRM_INFO("Not implemented\n");
}
@@ -3075,6 +3051,14 @@
.select_me_pipe_q = &gfx_v6_0_select_me_pipe_q
};
+static const struct amdgpu_rlc_funcs gfx_v6_0_rlc_funcs = {
+ .init = gfx_v6_0_rlc_init,
+ .resume = gfx_v6_0_rlc_resume,
+ .stop = gfx_v6_0_rlc_stop,
+ .reset = gfx_v6_0_rlc_reset,
+ .start = gfx_v6_0_rlc_start
+};
+
static int gfx_v6_0_early_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -3082,6 +3066,7 @@
adev->gfx.num_gfx_rings = GFX6_NUM_GFX_RINGS;
adev->gfx.num_compute_rings = GFX6_NUM_COMPUTE_RINGS;
adev->gfx.funcs = &gfx_v6_0_gfx_funcs;
+ adev->gfx.rlc.funcs = &gfx_v6_0_rlc_funcs;
gfx_v6_0_set_ring_funcs(adev);
gfx_v6_0_set_irq_funcs(adev);
@@ -3094,15 +3079,15 @@
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
int i, r;
- r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 181, &adev->gfx.eop_irq);
+ r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, 181, &adev->gfx.eop_irq);
if (r)
return r;
- r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 184, &adev->gfx.priv_reg_irq);
+ r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, 184, &adev->gfx.priv_reg_irq);
if (r)
return r;
- r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 185, &adev->gfx.priv_inst_irq);
+ r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, 185, &adev->gfx.priv_inst_irq);
if (r)
return r;
@@ -3114,7 +3099,7 @@
return r;
}
- r = gfx_v6_0_rlc_init(adev);
+ r = adev->gfx.rlc.funcs->init(adev);
if (r) {
DRM_ERROR("Failed to init rlc BOs!\n");
return r;
@@ -3125,7 +3110,9 @@
ring->ring_obj = NULL;
sprintf(ring->name, "gfx");
r = amdgpu_ring_init(adev, ring, 1024,
- &adev->gfx.eop_irq, AMDGPU_CP_IRQ_GFX_EOP);
+ &adev->gfx.eop_irq,
+ AMDGPU_CP_IRQ_GFX_ME0_PIPE0_EOP,
+ AMDGPU_RING_PRIO_DEFAULT);
if (r)
return r;
}
@@ -3147,7 +3134,8 @@
sprintf(ring->name, "comp_%d.%d.%d", ring->me, ring->pipe, ring->queue);
irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP + ring->pipe;
r = amdgpu_ring_init(adev, ring, 1024,
- &adev->gfx.eop_irq, irq_type);
+ &adev->gfx.eop_irq, irq_type,
+ AMDGPU_RING_PRIO_DEFAULT);
if (r)
return r;
}
@@ -3165,7 +3153,7 @@
for (i = 0; i < adev->gfx.num_compute_rings; i++)
amdgpu_ring_fini(&adev->gfx.compute_ring[i]);
- gfx_v6_0_rlc_fini(adev);
+ amdgpu_gfx_rlc_fini(adev);
return 0;
}
@@ -3175,9 +3163,9 @@
int r;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- gfx_v6_0_gpu_init(adev);
+ gfx_v6_0_constants_init(adev);
- r = gfx_v6_0_rlc_resume(adev);
+ r = adev->gfx.rlc.funcs->resume(adev);
if (r)
return r;
@@ -3195,7 +3183,7 @@
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
gfx_v6_0_cp_enable(adev, false);
- gfx_v6_0_rlc_stop(adev);
+ adev->gfx.rlc.funcs->stop(adev);
gfx_v6_0_fini_pg(adev);
return 0;
@@ -3360,7 +3348,7 @@
enum amdgpu_interrupt_state state)
{
switch (type) {
- case AMDGPU_CP_IRQ_GFX_EOP:
+ case AMDGPU_CP_IRQ_GFX_ME0_PIPE0_EOP:
gfx_v6_0_set_gfx_eop_interrupt_state(adev, state);
break;
case AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP:
@@ -3393,12 +3381,31 @@
return 0;
}
+static void gfx_v6_0_fault(struct amdgpu_device *adev,
+ struct amdgpu_iv_entry *entry)
+{
+ struct amdgpu_ring *ring;
+
+ switch (entry->ring_id) {
+ case 0:
+ ring = &adev->gfx.gfx_ring[0];
+ break;
+ case 1:
+ case 2:
+ ring = &adev->gfx.compute_ring[entry->ring_id - 1];
+ break;
+ default:
+ return;
+ }
+ drm_sched_fault(&ring->sched);
+}
+
static int gfx_v6_0_priv_reg_irq(struct amdgpu_device *adev,
struct amdgpu_irq_src *source,
struct amdgpu_iv_entry *entry)
{
DRM_ERROR("Illegal register access in command stream\n");
- schedule_work(&adev->reset_work);
+ gfx_v6_0_fault(adev, entry);
return 0;
}
@@ -3407,7 +3414,7 @@
struct amdgpu_iv_entry *entry)
{
DRM_ERROR("Illegal instruction in command stream\n");
- schedule_work(&adev->reset_work);
+ gfx_v6_0_fault(adev, entry);
return 0;
}
@@ -3458,6 +3465,18 @@
return 0;
}
+static void gfx_v6_0_emit_mem_sync(struct amdgpu_ring *ring)
+{
+ amdgpu_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
+ amdgpu_ring_write(ring, PACKET3_TCL1_ACTION_ENA |
+ PACKET3_TC_ACTION_ENA |
+ PACKET3_SH_KCACHE_ACTION_ENA |
+ PACKET3_SH_ICACHE_ACTION_ENA); /* CP_COHER_CNTL */
+ amdgpu_ring_write(ring, 0xffffffff); /* CP_COHER_SIZE */
+ amdgpu_ring_write(ring, 0); /* CP_COHER_BASE */
+ amdgpu_ring_write(ring, 0x0000000A); /* poll interval */
+}
+
static const struct amd_ip_funcs gfx_v6_0_ip_funcs = {
.name = "gfx_v6_0",
.early_init = gfx_v6_0_early_init,
@@ -3488,7 +3507,8 @@
14 + 14 + 14 + /* gfx_v6_0_ring_emit_fence x3 for user fence, vm fence */
7 + 4 + /* gfx_v6_0_ring_emit_pipeline_sync */
SI_FLUSH_GPU_TLB_NUM_WREG * 5 + 7 + 6 + /* gfx_v6_0_ring_emit_vm_flush */
- 3 + 2, /* gfx_v6_ring_emit_cntxcntl including vgt flush */
+ 3 + 2 + /* gfx_v6_ring_emit_cntxcntl including vgt flush */
+ 5, /* SURFACE_SYNC */
.emit_ib_size = 6, /* gfx_v6_0_ring_emit_ib */
.emit_ib = gfx_v6_0_ring_emit_ib,
.emit_fence = gfx_v6_0_ring_emit_fence,
@@ -3499,6 +3519,7 @@
.insert_nop = amdgpu_ring_insert_nop,
.emit_cntxcntl = gfx_v6_ring_emit_cntxcntl,
.emit_wreg = gfx_v6_0_ring_emit_wreg,
+ .emit_mem_sync = gfx_v6_0_emit_mem_sync,
};
static const struct amdgpu_ring_funcs gfx_v6_0_ring_funcs_compute = {
@@ -3512,7 +3533,8 @@
5 + 5 + /* hdp flush / invalidate */
7 + /* gfx_v6_0_ring_emit_pipeline_sync */
SI_FLUSH_GPU_TLB_NUM_WREG * 5 + 7 + /* gfx_v6_0_ring_emit_vm_flush */
- 14 + 14 + 14, /* gfx_v6_0_ring_emit_fence x3 for user fence, vm fence */
+ 14 + 14 + 14 + /* gfx_v6_0_ring_emit_fence x3 for user fence, vm fence */
+ 5, /* SURFACE_SYNC */
.emit_ib_size = 6, /* gfx_v6_0_ring_emit_ib */
.emit_ib = gfx_v6_0_ring_emit_ib,
.emit_fence = gfx_v6_0_ring_emit_fence,
@@ -3522,6 +3544,7 @@
.test_ib = gfx_v6_0_ring_test_ib,
.insert_nop = amdgpu_ring_insert_nop,
.emit_wreg = gfx_v6_0_ring_emit_wreg,
+ .emit_mem_sync = gfx_v6_0_emit_mem_sync,
};
static void gfx_v6_0_set_ring_funcs(struct amdgpu_device *adev)
--
Gitblit v1.6.2