1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
|
From 437b7a31501b7a096e3cd9ea19d830895b2766a4 Mon Sep 17 00:00:00 2001
From: pding <Pixel.Ding@amd.com>
Date: Fri, 13 Oct 2017 15:38:35 +0800
Subject: [PATCH 2028/4131] drm/amdgpu: busywait KIQ register accessing (v4)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Register accessing is performed when IRQ is disabled. Never sleep in
this function.
Known issue: dead sleep in many use cases of index/data registers.
v2:
- wrap polling fence functions.
- don't trigger IRQ for polling in case of wrongly fence signal.
v3:
- handle wrap round gracefully.
- add comments for polling function
v4:
- don't return negative timeout confused with error code
Signed-off-by: pding <Pixel.Ding@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 8 ++---
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 50 ++++++++++++++++++++++++++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 4 +++
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 30 ++++++++----------
6 files changed, 71 insertions(+), 25 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index b13c94f..65860f7 100755
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -905,7 +905,7 @@ struct amdgpu_mec {
struct amdgpu_kiq {
u64 eop_gpu_addr;
struct amdgpu_bo *eop_obj;
- struct mutex ring_mutex;
+ spinlock_t ring_lock;
struct amdgpu_ring ring;
struct amdgpu_irq_src irq;
};
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 74a63c2..05f4be0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -110,10 +110,8 @@ uint32_t amdgpu_mm_rreg(struct amdgpu_device *adev, uint32_t reg,
{
uint32_t ret;
- if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev)) {
- BUG_ON(in_interrupt());
+ if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev))
return amdgpu_virt_kiq_rreg(adev, reg);
- }
if ((reg * 4) < adev->rmmio_size && !(acc_flags & AMDGPU_REGS_IDX))
ret = readl(((void __iomem *)adev->rmmio) + (reg * 4));
@@ -138,10 +136,8 @@ void amdgpu_mm_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v,
adev->last_mm_index = v;
}
- if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev)) {
- BUG_ON(in_interrupt());
+ if (!(acc_flags & AMDGPU_REGS_NO_KIQ) && amdgpu_sriov_runtime(adev))
return amdgpu_virt_kiq_wreg(adev, reg, v);
- }
if ((reg * 4) < adev->rmmio_size && !(acc_flags & AMDGPU_REGS_IDX))
writel(v, ((void __iomem *)adev->rmmio) + (reg * 4));
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 7bdedd7..fb9f88ef 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -169,6 +169,32 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f)
}
/**
+ * amdgpu_fence_emit_polling - emit a fence on the requeste ring
+ *
+ * @ring: ring the fence is associated with
+ * @s: resulting sequence number
+ *
+ * Emits a fence command on the requested ring (all asics).
+ * Used For polling fence.
+ * Returns 0 on success, -ENOMEM on failure.
+ */
+int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s)
+{
+ uint32_t seq;
+
+ if (!s)
+ return -EINVAL;
+
+ seq = ++ring->fence_drv.sync_seq;
+ amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
+ seq, AMDGPU_FENCE_FLAG_INT);
+
+ *s = seq;
+
+ return 0;
+}
+
+/**
* amdgpu_fence_schedule_fallback - schedule fallback check
*
* @ring: pointer to struct amdgpu_ring
@@ -282,6 +308,30 @@ int amdgpu_fence_wait_empty(struct amdgpu_ring *ring)
}
/**
+ * amdgpu_fence_wait_polling - busy wait for givn sequence number
+ *
+ * @ring: ring index the fence is associated with
+ * @wait_seq: sequence number to wait
+ * @timeout: the timeout for waiting in usecs
+ *
+ * Wait for all fences on the requested ring to signal (all asics).
+ * Returns left time if no timeout, 0 or minus if timeout.
+ */
+signed long amdgpu_fence_wait_polling(struct amdgpu_ring *ring,
+ uint32_t wait_seq,
+ signed long timeout)
+{
+ uint32_t seq;
+
+ do {
+ seq = amdgpu_fence_read(ring);
+ udelay(5);
+ timeout -= 5;
+ } while ((int32_t)(wait_seq - seq) > 0 && timeout > 0);
+
+ return timeout > 0 ? timeout : 0;
+}
+/**
* amdgpu_fence_count_emitted - get the count of emitted fences
*
* @ring: ring the fence is associated with
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 9391db0..95f46b8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -201,7 +201,7 @@ int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev,
struct amdgpu_kiq *kiq = &adev->gfx.kiq;
int r = 0;
- mutex_init(&kiq->ring_mutex);
+ spin_lock_init(&kiq->ring_lock);
r = amdgpu_wb_get(adev, &adev->virt.reg_val_offs);
if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 494ff48..9fef7c7 100755
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -91,8 +91,12 @@ int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
void amdgpu_fence_driver_suspend(struct amdgpu_device *adev);
void amdgpu_fence_driver_resume(struct amdgpu_device *adev);
int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **fence);
+int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s);
void amdgpu_fence_process(struct amdgpu_ring *ring);
int amdgpu_fence_wait_empty(struct amdgpu_ring *ring);
+signed long amdgpu_fence_wait_polling(struct amdgpu_ring *ring,
+ uint32_t wait_seq,
+ signed long timeout);
unsigned amdgpu_fence_count_emitted(struct amdgpu_ring *ring);
/*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index ed7be2e..e97f80f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -22,7 +22,7 @@
*/
#include "amdgpu.h"
-#define MAX_KIQ_REG_WAIT 100000
+#define MAX_KIQ_REG_WAIT 100000000 /* in usecs */
int amdgpu_allocate_static_csa(struct amdgpu_device *adev)
{
@@ -114,27 +114,24 @@ void amdgpu_virt_init_setting(struct amdgpu_device *adev)
uint32_t amdgpu_virt_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
{
signed long r;
- uint32_t val;
- struct dma_fence *f;
+ uint32_t val, seq;
struct amdgpu_kiq *kiq = &adev->gfx.kiq;
struct amdgpu_ring *ring = &kiq->ring;
BUG_ON(!ring->funcs->emit_rreg);
- mutex_lock(&kiq->ring_mutex);
+ spin_lock(&kiq->ring_lock);
amdgpu_ring_alloc(ring, 32);
amdgpu_ring_emit_rreg(ring, reg);
- amdgpu_fence_emit(ring, &f);
+ amdgpu_fence_emit_polling(ring, &seq);
amdgpu_ring_commit(ring);
- mutex_unlock(&kiq->ring_mutex);
+ spin_unlock(&kiq->ring_lock);
- r = dma_fence_wait_timeout(f, false, msecs_to_jiffies(MAX_KIQ_REG_WAIT));
- dma_fence_put(f);
+ r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
if (r < 1) {
- DRM_ERROR("wait for kiq fence error: %ld.\n", r);
+ DRM_ERROR("wait for kiq fence error: %ld\n", r);
return ~0;
}
-
val = adev->wb.wb[adev->virt.reg_val_offs];
return val;
@@ -143,23 +140,22 @@ uint32_t amdgpu_virt_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v)
{
signed long r;
- struct dma_fence *f;
+ uint32_t seq;
struct amdgpu_kiq *kiq = &adev->gfx.kiq;
struct amdgpu_ring *ring = &kiq->ring;
BUG_ON(!ring->funcs->emit_wreg);
- mutex_lock(&kiq->ring_mutex);
+ spin_lock(&kiq->ring_lock);
amdgpu_ring_alloc(ring, 32);
amdgpu_ring_emit_wreg(ring, reg, v);
- amdgpu_fence_emit(ring, &f);
+ amdgpu_fence_emit_polling(ring, &seq);
amdgpu_ring_commit(ring);
- mutex_unlock(&kiq->ring_mutex);
+ spin_unlock(&kiq->ring_lock);
- r = dma_fence_wait_timeout(f, false, msecs_to_jiffies(MAX_KIQ_REG_WAIT));
+ r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
if (r < 1)
- DRM_ERROR("wait for kiq fence error: %ld.\n", r);
- dma_fence_put(f);
+ DRM_ERROR("wait for kiq fence error: %ld\n", r);
}
/**
--
2.7.4
|
