summaryrefslogtreecommitdiffstats
path: root/qemu/hw/ppc/spapr_pci_vfio.c
blob: cca45ed3129cc403777d89cec0f52fe29fff68f8 (plain)
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
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
/*
 * QEMU sPAPR PCI host for VFIO
 *
 * Copyright (c) 2011-2014 Alexey Kardashevskiy, IBM Corporation.
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License,
 *  or (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, see <http://www.gnu.org/licenses/>.
 */

#include "hw/ppc/spapr.h"
#include "hw/pci-host/spapr.h"
#include "hw/pci/msix.h"
#include "linux/vfio.h"
#include "hw/vfio/vfio.h"

static Property spapr_phb_vfio_properties[] = {
    DEFINE_PROP_INT32("iommu", sPAPRPHBVFIOState, iommugroupid, -1),
    DEFINE_PROP_END_OF_LIST(),
};

static void spapr_phb_vfio_finish_realize(sPAPRPHBState *sphb, Error **errp)
{
    sPAPRPHBVFIOState *svphb = SPAPR_PCI_VFIO_HOST_BRIDGE(sphb);
    struct vfio_iommu_spapr_tce_info info = { .argsz = sizeof(info) };
    int ret;
    sPAPRTCETable *tcet;
    uint32_t liobn = svphb->phb.dma_liobn;

    if (svphb->iommugroupid == -1) {
        error_setg(errp, "Wrong IOMMU group ID %d", svphb->iommugroupid);
        return;
    }

    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
                               VFIO_CHECK_EXTENSION,
                               (void *) VFIO_SPAPR_TCE_IOMMU);
    if (ret != 1) {
        error_setg_errno(errp, -ret,
                         "spapr-vfio: SPAPR extension is not supported");
        return;
    }

    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
                               VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info);
    if (ret) {
        error_setg_errno(errp, -ret,
                         "spapr-vfio: get info from container failed");
        return;
    }

    tcet = spapr_tce_new_table(DEVICE(sphb), liobn, info.dma32_window_start,
                               SPAPR_TCE_PAGE_SHIFT,
                               info.dma32_window_size >> SPAPR_TCE_PAGE_SHIFT,
                               true);
    if (!tcet) {
        error_setg(errp, "spapr-vfio: failed to create VFIO TCE table");
        return;
    }

    /* Register default 32bit DMA window */
    memory_region_add_subregion(&sphb->iommu_root, tcet->bus_offset,
                                spapr_tce_get_iommu(tcet));
}

static void spapr_phb_vfio_eeh_reenable(sPAPRPHBVFIOState *svphb)
{
    struct vfio_eeh_pe_op op = {
        .argsz = sizeof(op),
        .op    = VFIO_EEH_PE_ENABLE
    };

    vfio_container_ioctl(&svphb->phb.iommu_as,
                         svphb->iommugroupid, VFIO_EEH_PE_OP, &op);
}

static void spapr_phb_vfio_reset(DeviceState *qdev)
{
    /*
     * The PE might be in frozen state. To reenable the EEH
     * functionality on it will clean the frozen state, which
     * ensures that the contained PCI devices will work properly
     * after reboot.
     */
    spapr_phb_vfio_eeh_reenable(SPAPR_PCI_VFIO_HOST_BRIDGE(qdev));
}

static int spapr_phb_vfio_eeh_set_option(sPAPRPHBState *sphb,
                                         unsigned int addr, int option)
{
    sPAPRPHBVFIOState *svphb = SPAPR_PCI_VFIO_HOST_BRIDGE(sphb);
    struct vfio_eeh_pe_op op = { .argsz = sizeof(op) };
    int ret;

    switch (option) {
    case RTAS_EEH_DISABLE:
        op.op = VFIO_EEH_PE_DISABLE;
        break;
    case RTAS_EEH_ENABLE: {
        PCIHostState *phb;
        PCIDevice *pdev;

        /*
         * The EEH functionality is enabled on basis of PCI device,
         * instead of PE. We need check the validity of the PCI
         * device address.
         */
        phb = PCI_HOST_BRIDGE(sphb);
        pdev = pci_find_device(phb->bus,
                               (addr >> 16) & 0xFF, (addr >> 8) & 0xFF);
        if (!pdev) {
            return RTAS_OUT_PARAM_ERROR;
        }

        op.op = VFIO_EEH_PE_ENABLE;
        break;
    }
    case RTAS_EEH_THAW_IO:
        op.op = VFIO_EEH_PE_UNFREEZE_IO;
        break;
    case RTAS_EEH_THAW_DMA:
        op.op = VFIO_EEH_PE_UNFREEZE_DMA;
        break;
    default:
        return RTAS_OUT_PARAM_ERROR;
    }

    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
                               VFIO_EEH_PE_OP, &op);
    if (ret < 0) {
        return RTAS_OUT_HW_ERROR;
    }

    return RTAS_OUT_SUCCESS;
}

static int spapr_phb_vfio_eeh_get_state(sPAPRPHBState *sphb, int *state)
{
    sPAPRPHBVFIOState *svphb = SPAPR_PCI_VFIO_HOST_BRIDGE(sphb);
    struct vfio_eeh_pe_op op = { .argsz = sizeof(op) };
    int ret;

    op.op = VFIO_EEH_PE_GET_STATE;
    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
                               VFIO_EEH_PE_OP, &op);
    if (ret < 0) {
        return RTAS_OUT_PARAM_ERROR;
    }

    *state = ret;
    return RTAS_OUT_SUCCESS;
}

static void spapr_phb_vfio_eeh_clear_dev_msix(PCIBus *bus,
                                              PCIDevice *pdev,
                                              void *opaque)
{
    /* Check if the device is VFIO PCI device */
    if (!object_dynamic_cast(OBJECT(pdev), "vfio-pci")) {
        return;
    }

    /*
     * The MSIx table will be cleaned out by reset. We need
     * disable it so that it can be reenabled properly. Also,
     * the cached MSIx table should be cleared as it's not
     * reflecting the contents in hardware.
     */
    if (msix_enabled(pdev)) {
        uint16_t flags;

        flags = pci_host_config_read_common(pdev,
                                            pdev->msix_cap + PCI_MSIX_FLAGS,
                                            pci_config_size(pdev), 2);
        flags &= ~PCI_MSIX_FLAGS_ENABLE;
        pci_host_config_write_common(pdev,
                                     pdev->msix_cap + PCI_MSIX_FLAGS,
                                     pci_config_size(pdev), flags, 2);
    }

    msix_reset(pdev);
}

static void spapr_phb_vfio_eeh_clear_bus_msix(PCIBus *bus, void *opaque)
{
       pci_for_each_device(bus, pci_bus_num(bus),
                           spapr_phb_vfio_eeh_clear_dev_msix, NULL);
}

static void spapr_phb_vfio_eeh_pre_reset(sPAPRPHBState *sphb)
{
       PCIHostState *phb = PCI_HOST_BRIDGE(sphb);

       pci_for_each_bus(phb->bus, spapr_phb_vfio_eeh_clear_bus_msix, NULL);
}

static int spapr_phb_vfio_eeh_reset(sPAPRPHBState *sphb, int option)
{
    sPAPRPHBVFIOState *svphb = SPAPR_PCI_VFIO_HOST_BRIDGE(sphb);
    struct vfio_eeh_pe_op op = { .argsz = sizeof(op) };
    int ret;

    switch (option) {
    case RTAS_SLOT_RESET_DEACTIVATE:
        op.op = VFIO_EEH_PE_RESET_DEACTIVATE;
        break;
    case RTAS_SLOT_RESET_HOT:
        spapr_phb_vfio_eeh_pre_reset(sphb);
        op.op = VFIO_EEH_PE_RESET_HOT;
        break;
    case RTAS_SLOT_RESET_FUNDAMENTAL:
        spapr_phb_vfio_eeh_pre_reset(sphb);
        op.op = VFIO_EEH_PE_RESET_FUNDAMENTAL;
        break;
    default:
        return RTAS_OUT_PARAM_ERROR;
    }

    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
                               VFIO_EEH_PE_OP, &op);
    if (ret < 0) {
        return RTAS_OUT_HW_ERROR;
    }

    return RTAS_OUT_SUCCESS;
}

static int spapr_phb_vfio_eeh_configure(sPAPRPHBState *sphb)
{
    sPAPRPHBVFIOState *svphb = SPAPR_PCI_VFIO_HOST_BRIDGE(sphb);
    struct vfio_eeh_pe_op op = { .argsz = sizeof(op) };
    int ret;

    op.op = VFIO_EEH_PE_CONFIGURE;
    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
                               VFIO_EEH_PE_OP, &op);
    if (ret < 0) {
        return RTAS_OUT_PARAM_ERROR;
    }

    return RTAS_OUT_SUCCESS;
}

static void spapr_phb_vfio_class_init(ObjectClass *klass, void *data)
{
    DeviceClass *dc = DEVICE_CLASS(klass);
    sPAPRPHBClass *spc = SPAPR_PCI_HOST_BRIDGE_CLASS(klass);

    dc->props = spapr_phb_vfio_properties;
    dc->reset = spapr_phb_vfio_reset;
    spc->finish_realize = spapr_phb_vfio_finish_realize;
    spc->eeh_set_option = spapr_phb_vfio_eeh_set_option;
    spc->eeh_get_state = spapr_phb_vfio_eeh_get_state;
    spc->eeh_reset = spapr_phb_vfio_eeh_reset;
    spc->eeh_configure = spapr_phb_vfio_eeh_configure;
}

static const TypeInfo spapr_phb_vfio_info = {
    .name          = TYPE_SPAPR_PCI_VFIO_HOST_BRIDGE,
    .parent        = TYPE_SPAPR_PCI_HOST_BRIDGE,
    .instance_size = sizeof(sPAPRPHBVFIOState),
    .class_init    = spapr_phb_vfio_class_init,
    .class_size    = sizeof(sPAPRPHBClass),
};

static void spapr_pci_vfio_register_types(void)
{
    type_register_static(&spapr_phb_vfio_info);
}

type_init(spapr_pci_vfio_register_types)