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
|
From 9247322ebaf48ca207d33c4dcb65b775a864fd29 Mon Sep 17 00:00:00 2001
From: Felix Kuehling <Felix.Kuehling@amd.com>
Date: Thu, 28 Sep 2017 15:01:32 -0400
Subject: [PATCH 2110/4131] drm/amdkfd: Clean up kfd_wait_on_events
Cleaned up the code while resolving some potential bugs and
inconsistencies in the process.
Clean-ups:
* Remove enum kfd_event_wait_result, which duplicates
KFD_IOC_EVENT_RESULT definitions
* alloc_event_waiters can be called without holding p->event_mutex
* Return an error code from copy_signaled_event_data instead of bool
* Clean up error handling code paths to minimize duplication in
kfd_wait_on_events
Fixes:
* Consistently return an error code from kfd_wait_on_events and set
wait_result to KFD_IOC_WAIT_RESULT_FAIL in all failure cases.
* Always call free_waiters while holding p->event_mutex
* copy_signaled_event_data might sleep. Don't call it while the task state
is TASK_INTERRUPTIBLE.
Change-Id: I6f1e979c0c59478e499f974a4aa906f4d05366f3
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 5 +--
drivers/gpu/drm/amd/amdkfd/kfd_events.c | 71 ++++++++++++++------------------
drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 8 +---
3 files changed, 32 insertions(+), 52 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 3a3de01..c7cae86 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1075,15 +1075,12 @@ static int kfd_ioctl_wait_events(struct file *filp, struct kfd_process *p,
void *data)
{
struct kfd_ioctl_wait_events_args *args = data;
- enum kfd_event_wait_result wait_result;
int err;
err = kfd_wait_on_events(p, args->num_events,
(void __user *)args->events_ptr,
(args->wait_for_all != 0),
- args->timeout, &wait_result);
-
- args->wait_result = wait_result;
+ args->timeout, &args->wait_result);
return err;
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index b130b64..f746cbc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -733,7 +733,7 @@ static bool test_event_condition(bool all, uint32_t num_events,
* Copy event specific data, if defined.
* Currently only memory exception events have additional data to copy to user
*/
-static bool copy_signaled_event_data(uint32_t num_events,
+static int copy_signaled_event_data(uint32_t num_events,
struct kfd_event_waiter *event_waiters,
struct kfd_event_data __user *data)
{
@@ -751,11 +751,11 @@ static bool copy_signaled_event_data(uint32_t num_events,
src = &event->memory_exception_data;
if (copy_to_user(dst, src,
sizeof(struct kfd_hsa_memory_exception_data)))
- return false;
+ return -EFAULT;
}
}
- return true;
+ return 0;
}
@@ -792,7 +792,7 @@ static void free_waiters(uint32_t num_events, struct kfd_event_waiter *waiters)
int kfd_wait_on_events(struct kfd_process *p,
uint32_t num_events, void __user *data,
bool all, uint32_t user_timeout_ms,
- enum kfd_event_wait_result *wait_result)
+ uint32_t *wait_result)
{
struct kfd_event_data __user *events =
(struct kfd_event_data __user *) data;
@@ -801,18 +801,18 @@ int kfd_wait_on_events(struct kfd_process *p,
struct kfd_event_waiter *event_waiters = NULL;
long timeout = user_timeout_to_jiffies(user_timeout_ms);
+ event_waiters = alloc_event_waiters(num_events);
+ if (!event_waiters) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
mutex_lock(&p->event_mutex);
/* Set to something unreasonable - this is really
* just a bool for now.
*/
- *wait_result = KFD_WAIT_TIMEOUT;
-
- event_waiters = alloc_event_waiters(num_events);
- if (!event_waiters) {
- ret = -ENOMEM;
- goto fail;
- }
+ *wait_result = KFD_IOC_WAIT_RESULT_TIMEOUT;
for (i = 0; i < num_events; i++) {
struct kfd_event_data event_data;
@@ -820,23 +820,21 @@ int kfd_wait_on_events(struct kfd_process *p,
if (copy_from_user(&event_data, &events[i],
sizeof(struct kfd_event_data))) {
ret = -EFAULT;
- goto fail;
+ goto out_unlock;
}
ret = init_event_waiter_get_status(p, &event_waiters[i],
event_data.event_id, i);
if (ret)
- goto fail;
+ goto out_unlock;
}
/* Check condition once. */
if (test_event_condition(all, num_events, event_waiters)) {
- if (copy_signaled_event_data(num_events,
- event_waiters, events))
- *wait_result = KFD_WAIT_COMPLETE;
- else
- *wait_result = KFD_WAIT_ERROR;
- free_waiters(num_events, event_waiters);
+ *wait_result = KFD_IOC_WAIT_RESULT_COMPLETE;
+ ret = copy_signaled_event_data(num_events,
+ event_waiters, events);
+ goto out_unlock;
} else {
/* Add to wait lists if we need to wait. */
for (i = 0; i < num_events; i++)
@@ -845,12 +843,6 @@ int kfd_wait_on_events(struct kfd_process *p,
mutex_unlock(&p->event_mutex);
- /* Return if all waits were already satisfied. */
- if (*wait_result != KFD_WAIT_TIMEOUT) {
- __set_current_state(TASK_RUNNING);
- return ret;
- }
-
while (true) {
if (fatal_signal_pending(current)) {
ret = -EINTR;
@@ -882,16 +874,12 @@ int kfd_wait_on_events(struct kfd_process *p,
set_current_state(TASK_INTERRUPTIBLE);
if (test_event_condition(all, num_events, event_waiters)) {
- if (copy_signaled_event_data(num_events,
- event_waiters, events))
- *wait_result = KFD_WAIT_COMPLETE;
- else
- *wait_result = KFD_WAIT_ERROR;
+ *wait_result = KFD_IOC_WAIT_RESULT_COMPLETE;
break;
}
if (timeout <= 0) {
- *wait_result = KFD_WAIT_TIMEOUT;
+ *wait_result = KFD_IOC_WAIT_RESULT_TIMEOUT;
break;
}
@@ -899,19 +887,20 @@ int kfd_wait_on_events(struct kfd_process *p,
}
__set_current_state(TASK_RUNNING);
+ /* copy_signaled_event_data may sleep. So this has to happen
+ * after the task state is set back to RUNNING.
+ */
+ if (!ret && *wait_result == KFD_IOC_WAIT_RESULT_COMPLETE)
+ ret = copy_signaled_event_data(num_events,
+ event_waiters, events);
+
mutex_lock(&p->event_mutex);
+out_unlock:
free_waiters(num_events, event_waiters);
mutex_unlock(&p->event_mutex);
-
- return ret;
-
-fail:
- if (event_waiters)
- free_waiters(num_events, event_waiters);
-
- mutex_unlock(&p->event_mutex);
-
- *wait_result = KFD_WAIT_ERROR;
+out:
+ if (ret)
+ *wait_result = KFD_IOC_WAIT_RESULT_FAIL;
return ret;
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index ccac951..1ac4db5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1037,19 +1037,13 @@ extern const struct kfd_event_interrupt_class event_interrupt_class_v9;
extern const struct kfd_device_global_init_class device_global_init_class_cik;
-enum kfd_event_wait_result {
- KFD_WAIT_COMPLETE,
- KFD_WAIT_TIMEOUT,
- KFD_WAIT_ERROR
-};
-
void kfd_event_init_process(struct kfd_process *p);
void kfd_event_free_process(struct kfd_process *p);
int kfd_event_mmap(struct kfd_process *process, struct vm_area_struct *vma);
int kfd_wait_on_events(struct kfd_process *p,
uint32_t num_events, void __user *data,
bool all, uint32_t user_timeout_ms,
- enum kfd_event_wait_result *wait_result);
+ uint32_t *wait_result);
void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
uint32_t valid_id_bits);
#if defined(CONFIG_AMD_IOMMU_V2_MODULE) || defined(CONFIG_AMD_IOMMU_V2)
--
2.7.4
|
