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
|
/*
* QEMU PowerPC pSeries Logical Partition NUMA associativity handling
*
* Copyright IBM Corp. 2020
*
* Authors:
* Daniel Henrique Barboza <danielhb413@gmail.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "hw/ppc/spapr_numa.h"
#include "hw/pci-host/spapr.h"
#include "hw/ppc/fdt.h"
/* Moved from hw/ppc/spapr_pci_nvlink2.c */
#define SPAPR_GPU_NUMA_ID (cpu_to_be32(1))
void spapr_numa_associativity_init(SpaprMachineState *spapr,
MachineState *machine)
{
SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);
int nb_numa_nodes = machine->numa_state->num_nodes;
int i, j, max_nodes_with_gpus;
/*
* For all associativity arrays: first position is the size,
* position MAX_DISTANCE_REF_POINTS is always the numa_id,
* represented by the index 'i'.
*
* This will break on sparse NUMA setups, when/if QEMU starts
* to support it, because there will be no more guarantee that
* 'i' will be a valid node_id set by the user.
*/
for (i = 0; i < nb_numa_nodes; i++) {
spapr->numa_assoc_array[i][0] = cpu_to_be32(MAX_DISTANCE_REF_POINTS);
spapr->numa_assoc_array[i][MAX_DISTANCE_REF_POINTS] = cpu_to_be32(i);
}
/*
* Initialize NVLink GPU associativity arrays. We know that
* the first GPU will take the first available NUMA id, and
* we'll have a maximum of NVGPU_MAX_NUM GPUs in the machine.
* At this point we're not sure if there are GPUs or not, but
* let's initialize the associativity arrays and allow NVLink
* GPUs to be handled like regular NUMA nodes later on.
*/
max_nodes_with_gpus = nb_numa_nodes + NVGPU_MAX_NUM;
for (i = nb_numa_nodes; i < max_nodes_with_gpus; i++) {
spapr->numa_assoc_array[i][0] = cpu_to_be32(MAX_DISTANCE_REF_POINTS);
for (j = 1; j < MAX_DISTANCE_REF_POINTS; j++) {
uint32_t gpu_assoc = smc->pre_5_1_assoc_refpoints ?
SPAPR_GPU_NUMA_ID : cpu_to_be32(i);
spapr->numa_assoc_array[i][j] = gpu_assoc;
}
spapr->numa_assoc_array[i][MAX_DISTANCE_REF_POINTS] = cpu_to_be32(i);
}
}
void spapr_numa_write_associativity_dt(SpaprMachineState *spapr, void *fdt,
int offset, int nodeid)
{
_FDT((fdt_setprop(fdt, offset, "ibm,associativity",
spapr->numa_assoc_array[nodeid],
sizeof(spapr->numa_assoc_array[nodeid]))));
}
static uint32_t *spapr_numa_get_vcpu_assoc(SpaprMachineState *spapr,
PowerPCCPU *cpu)
{
uint32_t *vcpu_assoc = g_new(uint32_t, VCPU_ASSOC_SIZE);
int index = spapr_get_vcpu_id(cpu);
/*
* VCPUs have an extra 'cpu_id' value in ibm,associativity
* compared to other resources. Increment the size at index
* 0, put cpu_id last, then copy the remaining associativity
* domains.
*/
vcpu_assoc[0] = cpu_to_be32(MAX_DISTANCE_REF_POINTS + 1);
vcpu_assoc[VCPU_ASSOC_SIZE - 1] = cpu_to_be32(index);
memcpy(vcpu_assoc + 1, spapr->numa_assoc_array[cpu->node_id] + 1,
(VCPU_ASSOC_SIZE - 2) * sizeof(uint32_t));
return vcpu_assoc;
}
int spapr_numa_fixup_cpu_dt(SpaprMachineState *spapr, void *fdt,
int offset, PowerPCCPU *cpu)
{
g_autofree uint32_t *vcpu_assoc = NULL;
vcpu_assoc = spapr_numa_get_vcpu_assoc(spapr, cpu);
/* Advertise NUMA via ibm,associativity */
return fdt_setprop(fdt, offset, "ibm,associativity", vcpu_assoc,
VCPU_ASSOC_SIZE * sizeof(uint32_t));
}
int spapr_numa_write_assoc_lookup_arrays(SpaprMachineState *spapr, void *fdt,
int offset)
{
MachineState *machine = MACHINE(spapr);
int nb_numa_nodes = machine->numa_state->num_nodes;
int nr_nodes = nb_numa_nodes ? nb_numa_nodes : 1;
uint32_t *int_buf, *cur_index, buf_len;
int ret, i;
/* ibm,associativity-lookup-arrays */
buf_len = (nr_nodes * MAX_DISTANCE_REF_POINTS + 2) * sizeof(uint32_t);
cur_index = int_buf = g_malloc0(buf_len);
int_buf[0] = cpu_to_be32(nr_nodes);
/* Number of entries per associativity list */
int_buf[1] = cpu_to_be32(MAX_DISTANCE_REF_POINTS);
cur_index += 2;
for (i = 0; i < nr_nodes; i++) {
/*
* For the lookup-array we use the ibm,associativity array,
* from numa_assoc_array. without the first element (size).
*/
uint32_t *associativity = spapr->numa_assoc_array[i];
memcpy(cur_index, ++associativity,
sizeof(uint32_t) * MAX_DISTANCE_REF_POINTS);
cur_index += MAX_DISTANCE_REF_POINTS;
}
ret = fdt_setprop(fdt, offset, "ibm,associativity-lookup-arrays", int_buf,
(cur_index - int_buf) * sizeof(uint32_t));
g_free(int_buf);
return ret;
}
/*
* Helper that writes ibm,associativity-reference-points and
* max-associativity-domains in the RTAS pointed by @rtas
* in the DT @fdt.
*/
void spapr_numa_write_rtas_dt(SpaprMachineState *spapr, void *fdt, int rtas)
{
SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);
uint32_t refpoints[] = {
cpu_to_be32(0x4),
cpu_to_be32(0x4),
cpu_to_be32(0x2),
};
uint32_t nr_refpoints = ARRAY_SIZE(refpoints);
uint32_t maxdomain = cpu_to_be32(spapr->gpu_numa_id > 1 ? 1 : 0);
uint32_t maxdomains[] = {
cpu_to_be32(4),
maxdomain,
maxdomain,
maxdomain,
cpu_to_be32(spapr->gpu_numa_id),
};
if (smc->pre_5_1_assoc_refpoints) {
nr_refpoints = 2;
}
_FDT(fdt_setprop(fdt, rtas, "ibm,associativity-reference-points",
refpoints, nr_refpoints * sizeof(refpoints[0])));
_FDT(fdt_setprop(fdt, rtas, "ibm,max-associativity-domains",
maxdomains, sizeof(maxdomains)));
}
static target_ulong h_home_node_associativity(PowerPCCPU *cpu,
SpaprMachineState *spapr,
target_ulong opcode,
target_ulong *args)
{
target_ulong flags = args[0];
target_ulong procno = args[1];
PowerPCCPU *tcpu;
int idx;
/* only support procno from H_REGISTER_VPA */
if (flags != 0x1) {
return H_FUNCTION;
}
tcpu = spapr_find_cpu(procno);
if (tcpu == NULL) {
return H_P2;
}
/* sequence is the same as in the "ibm,associativity" property */
idx = 0;
#define ASSOCIATIVITY(a, b) (((uint64_t)(a) << 32) | \
((uint64_t)(b) & 0xffffffff))
args[idx++] = ASSOCIATIVITY(0, 0);
args[idx++] = ASSOCIATIVITY(0, tcpu->node_id);
args[idx++] = ASSOCIATIVITY(procno, -1);
for ( ; idx < 6; idx++) {
args[idx] = -1;
}
#undef ASSOCIATIVITY
return H_SUCCESS;
}
static void spapr_numa_register_types(void)
{
/* Virtual Processor Home Node */
spapr_register_hypercall(H_HOME_NODE_ASSOCIATIVITY,
h_home_node_associativity);
}
type_init(spapr_numa_register_types)
|
