aboutsummaryrefslogtreecommitdiff
path: root/hw/s390x/s390-pci-vfio.c
blob: 7dbbc76823a5240978acd03230a8022e53f676ed (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
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
/*
 * s390 vfio-pci interfaces
 *
 * Copyright 2020 IBM Corp.
 * Author(s): Matthew Rosato <mjrosato@linux.ibm.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or (at
 * your option) any later version. See the COPYING file in the top-level
 * directory.
 */

#include "qemu/osdep.h"

#include <sys/ioctl.h>
#include <linux/vfio.h>
#include <linux/vfio_zdev.h>

#include "trace.h"
#include "hw/s390x/s390-pci-bus.h"
#include "hw/s390x/s390-pci-clp.h"
#include "hw/s390x/s390-pci-vfio.h"
#include "hw/vfio/pci.h"
#include "hw/vfio/vfio-common.h"

/*
 * Get the current DMA available count from vfio.  Returns true if vfio is
 * limiting DMA requests, false otherwise.  The current available count read
 * from vfio is returned in avail.
 */
bool s390_pci_update_dma_avail(int fd, unsigned int *avail)
{
    uint32_t argsz = sizeof(struct vfio_iommu_type1_info);
    g_autofree struct vfio_iommu_type1_info *info = g_malloc0(argsz);

    assert(avail);

    /*
     * If the specified argsz is not large enough to contain all capabilities
     * it will be updated upon return from the ioctl.  Retry until we have
     * a big enough buffer to hold the entire capability chain.
     */
retry:
    info->argsz = argsz;

    if (ioctl(fd, VFIO_IOMMU_GET_INFO, info)) {
        return false;
    }

    if (info->argsz > argsz) {
        argsz = info->argsz;
        info = g_realloc(info, argsz);
        goto retry;
    }

    /* If the capability exists, update with the current value */
    return vfio_get_info_dma_avail(info, avail);
}

S390PCIDMACount *s390_pci_start_dma_count(S390pciState *s,
                                          S390PCIBusDevice *pbdev)
{
    S390PCIDMACount *cnt;
    uint32_t avail;
    VFIOPCIDevice *vpdev = container_of(pbdev->pdev, VFIOPCIDevice, pdev);
    int id;

    assert(vpdev);

    if (!vpdev->vbasedev.group) {
        return NULL;
    }

    id = vpdev->vbasedev.group->container->fd;

    if (!s390_pci_update_dma_avail(id, &avail)) {
        return NULL;
    }

    QTAILQ_FOREACH(cnt, &s->zpci_dma_limit, link) {
        if (cnt->id  == id) {
            cnt->users++;
            return cnt;
        }
    }

    cnt = g_new0(S390PCIDMACount, 1);
    cnt->id = id;
    cnt->users = 1;
    cnt->avail = avail;
    QTAILQ_INSERT_TAIL(&s->zpci_dma_limit, cnt, link);
    pbdev->iommu->max_dma_limit = avail;
    return cnt;
}

void s390_pci_end_dma_count(S390pciState *s, S390PCIDMACount *cnt)
{
    assert(cnt);

    cnt->users--;
    if (cnt->users == 0) {
        QTAILQ_REMOVE(&s->zpci_dma_limit, cnt, link);
    }
}

static void s390_pci_read_base(S390PCIBusDevice *pbdev,
                               struct vfio_device_info *info)
{
    struct vfio_info_cap_header *hdr;
    struct vfio_device_info_cap_zpci_base *cap;
    VFIOPCIDevice *vpci =  container_of(pbdev->pdev, VFIOPCIDevice, pdev);
    uint64_t vfio_size;

    hdr = vfio_get_device_info_cap(info, VFIO_DEVICE_INFO_CAP_ZPCI_BASE);

    /* If capability not provided, just leave the defaults in place */
    if (hdr == NULL) {
        trace_s390_pci_clp_cap(vpci->vbasedev.name,
                               VFIO_DEVICE_INFO_CAP_ZPCI_BASE);
        return;
    }
    cap = (void *) hdr;

    pbdev->zpci_fn.sdma = cap->start_dma;
    pbdev->zpci_fn.edma = cap->end_dma;
    pbdev->zpci_fn.pchid = cap->pchid;
    pbdev->zpci_fn.vfn = cap->vfn;
    pbdev->zpci_fn.pfgid = cap->gid;
    /* The following values remain 0 until we support other FMB formats */
    pbdev->zpci_fn.fmbl = 0;
    pbdev->zpci_fn.pft = 0;
    /* Store function type separately for type-specific behavior */
    pbdev->pft = cap->pft;

    /*
     * If appropriate, reduce the size of the supported DMA aperture reported
     * to the guest based upon the vfio DMA limit.
     */
    vfio_size = pbdev->iommu->max_dma_limit << TARGET_PAGE_BITS;
    if (vfio_size > 0 && vfio_size < cap->end_dma - cap->start_dma + 1) {
        pbdev->zpci_fn.edma = cap->start_dma + vfio_size - 1;
    }
}

static bool get_host_fh(S390PCIBusDevice *pbdev, struct vfio_device_info *info,
                        uint32_t *fh)
{
    struct vfio_info_cap_header *hdr;
    struct vfio_device_info_cap_zpci_base *cap;
    VFIOPCIDevice *vpci = container_of(pbdev->pdev, VFIOPCIDevice, pdev);

    hdr = vfio_get_device_info_cap(info, VFIO_DEVICE_INFO_CAP_ZPCI_BASE);

    /* Can only get the host fh with version 2 or greater */
    if (hdr == NULL || hdr->version < 2) {
        trace_s390_pci_clp_cap(vpci->vbasedev.name,
                               VFIO_DEVICE_INFO_CAP_ZPCI_BASE);
        return false;
    }
    cap = (void *) hdr;

    *fh = cap->fh;
    return true;
}

static void s390_pci_read_group(S390PCIBusDevice *pbdev,
                                struct vfio_device_info *info)
{
    struct vfio_info_cap_header *hdr;
    struct vfio_device_info_cap_zpci_group *cap;
    S390pciState *s = s390_get_phb();
    ClpRspQueryPciGrp *resgrp;
    VFIOPCIDevice *vpci =  container_of(pbdev->pdev, VFIOPCIDevice, pdev);
    uint8_t start_gid = pbdev->zpci_fn.pfgid;

    hdr = vfio_get_device_info_cap(info, VFIO_DEVICE_INFO_CAP_ZPCI_GROUP);

    /*
     * If capability not provided or the underlying hostdev is simulated, just
     * use the default group.
     */
    if (hdr == NULL || pbdev->zpci_fn.pfgid >= ZPCI_SIM_GRP_START) {
        trace_s390_pci_clp_cap(vpci->vbasedev.name,
                               VFIO_DEVICE_INFO_CAP_ZPCI_GROUP);
        pbdev->zpci_fn.pfgid = ZPCI_DEFAULT_FN_GRP;
        pbdev->pci_group = s390_group_find(ZPCI_DEFAULT_FN_GRP);
        return;
    }
    cap = (void *) hdr;

    /*
     * For an intercept device, let's use an existing simulated group if one
     * one was already created for other intercept devices in this group.
     * If not, create a new simulated group if any are still available.
     * If all else fails, just fall back on the default group.
     */
    if (!pbdev->interp) {
        pbdev->pci_group = s390_group_find_host_sim(pbdev->zpci_fn.pfgid);
        if (pbdev->pci_group) {
            /* Use existing simulated group */
            pbdev->zpci_fn.pfgid = pbdev->pci_group->id;
            return;
        } else {
            if (s->next_sim_grp == ZPCI_DEFAULT_FN_GRP) {
                /* All out of simulated groups, use default */
                trace_s390_pci_clp_cap(vpci->vbasedev.name,
                                       VFIO_DEVICE_INFO_CAP_ZPCI_GROUP);
                pbdev->zpci_fn.pfgid = ZPCI_DEFAULT_FN_GRP;
                pbdev->pci_group = s390_group_find(ZPCI_DEFAULT_FN_GRP);
                return;
            } else {
                /* We can assign a new simulated group */
                pbdev->zpci_fn.pfgid = s->next_sim_grp;
                s->next_sim_grp++;
                /* Fall through to create the new sim group using CLP info */
            }
        }
    }

    /* See if the PCI group is already defined, create if not */
    pbdev->pci_group = s390_group_find(pbdev->zpci_fn.pfgid);

    if (!pbdev->pci_group) {
        pbdev->pci_group = s390_group_create(pbdev->zpci_fn.pfgid, start_gid);

        resgrp = &pbdev->pci_group->zpci_group;
        if (cap->flags & VFIO_DEVICE_INFO_ZPCI_FLAG_REFRESH) {
            resgrp->fr = 1;
        }
        resgrp->dasm = cap->dasm;
        resgrp->msia = cap->msi_addr;
        resgrp->mui = cap->mui;
        resgrp->i = cap->noi;
        if (pbdev->interp && hdr->version >= 2) {
            resgrp->maxstbl = cap->imaxstbl;
        } else {
            resgrp->maxstbl = cap->maxstbl;
        }
        resgrp->version = cap->version;
        resgrp->dtsm = ZPCI_DTSM;
    }
}

static void s390_pci_read_util(S390PCIBusDevice *pbdev,
                               struct vfio_device_info *info)
{
    struct vfio_info_cap_header *hdr;
    struct vfio_device_info_cap_zpci_util *cap;
    VFIOPCIDevice *vpci =  container_of(pbdev->pdev, VFIOPCIDevice, pdev);

    hdr = vfio_get_device_info_cap(info, VFIO_DEVICE_INFO_CAP_ZPCI_UTIL);

    /* If capability not provided, just leave the defaults in place */
    if (hdr == NULL) {
        trace_s390_pci_clp_cap(vpci->vbasedev.name,
                               VFIO_DEVICE_INFO_CAP_ZPCI_UTIL);
        return;
    }
    cap = (void *) hdr;

    if (cap->size > CLP_UTIL_STR_LEN) {
        trace_s390_pci_clp_cap_size(vpci->vbasedev.name, cap->size,
                                    VFIO_DEVICE_INFO_CAP_ZPCI_UTIL);
        return;
    }

    pbdev->zpci_fn.flags |= CLP_RSP_QPCI_MASK_UTIL;
    memcpy(pbdev->zpci_fn.util_str, cap->util_str, CLP_UTIL_STR_LEN);
}

static void s390_pci_read_pfip(S390PCIBusDevice *pbdev,
                               struct vfio_device_info *info)
{
    struct vfio_info_cap_header *hdr;
    struct vfio_device_info_cap_zpci_pfip *cap;
    VFIOPCIDevice *vpci =  container_of(pbdev->pdev, VFIOPCIDevice, pdev);

    hdr = vfio_get_device_info_cap(info, VFIO_DEVICE_INFO_CAP_ZPCI_PFIP);

    /* If capability not provided, just leave the defaults in place */
    if (hdr == NULL) {
        trace_s390_pci_clp_cap(vpci->vbasedev.name,
                               VFIO_DEVICE_INFO_CAP_ZPCI_PFIP);
        return;
    }
    cap = (void *) hdr;

    if (cap->size > CLP_PFIP_NR_SEGMENTS) {
        trace_s390_pci_clp_cap_size(vpci->vbasedev.name, cap->size,
                                    VFIO_DEVICE_INFO_CAP_ZPCI_PFIP);
        return;
    }

    memcpy(pbdev->zpci_fn.pfip, cap->pfip, CLP_PFIP_NR_SEGMENTS);
}

static struct vfio_device_info *get_device_info(S390PCIBusDevice *pbdev)
{
    VFIOPCIDevice *vfio_pci = container_of(pbdev->pdev, VFIOPCIDevice, pdev);

    return vfio_get_device_info(vfio_pci->vbasedev.fd);
}

/*
 * Get the host function handle from the vfio CLP capabilities chain.  Returns
 * true if a fh value was placed into the provided buffer.  Returns false
 * if a fh could not be obtained (ioctl failed or capability version does
 * not include the fh)
 */
bool s390_pci_get_host_fh(S390PCIBusDevice *pbdev, uint32_t *fh)
{
    g_autofree struct vfio_device_info *info = NULL;

    assert(fh);

    info = get_device_info(pbdev);
    if (!info) {
        return false;
    }

    return get_host_fh(pbdev, info, fh);
}

/*
 * This function will issue the VFIO_DEVICE_GET_INFO ioctl and look for
 * capabilities that contain information about CLP features provided by the
 * underlying host.
 * On entry, defaults have already been placed into the guest CLP response
 * buffers.  On exit, defaults will have been overwritten for any CLP features
 * found in the capability chain; defaults will remain for any CLP features not
 * found in the chain.
 */
void s390_pci_get_clp_info(S390PCIBusDevice *pbdev)
{
    g_autofree struct vfio_device_info *info = NULL;

    info = get_device_info(pbdev);
    if (!info) {
        return;
    }

    /*
     * Find the CLP features provided and fill in the guest CLP responses.
     * Always call s390_pci_read_base first as information from this could
     * determine which function group is used in s390_pci_read_group.
     * For any feature not found, the default values will remain in the CLP
     * response.
     */
    s390_pci_read_base(pbdev, info);
    s390_pci_read_group(pbdev, info);
    s390_pci_read_util(pbdev, info);
    s390_pci_read_pfip(pbdev, info);

    return;
}