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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419
|
// SPDX-License-Identifier: MIT
/*
* Copyright © 2024 Intel Corporation
*/
#include <drm/drm_managed.h>
#include "abi/guc_actions_sriov_abi.h"
#include "xe_bo.h"
#include "xe_gt_sriov_pf_helpers.h"
#include "xe_gt_sriov_pf_migration.h"
#include "xe_gt_sriov_printk.h"
#include "xe_guc.h"
#include "xe_guc_ct.h"
#include "xe_sriov.h"
/* Return: number of dwords saved/restored/required or a negative error code on failure */
static int guc_action_vf_save_restore(struct xe_guc *guc, u32 vfid, u32 opcode,
u64 addr, u32 ndwords)
{
u32 request[PF2GUC_SAVE_RESTORE_VF_REQUEST_MSG_LEN] = {
FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_HOST) |
FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) |
FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION, GUC_ACTION_PF2GUC_SAVE_RESTORE_VF) |
FIELD_PREP(PF2GUC_SAVE_RESTORE_VF_REQUEST_MSG_0_OPCODE, opcode),
FIELD_PREP(PF2GUC_SAVE_RESTORE_VF_REQUEST_MSG_1_VFID, vfid),
FIELD_PREP(PF2GUC_SAVE_RESTORE_VF_REQUEST_MSG_2_ADDR_LO, lower_32_bits(addr)),
FIELD_PREP(PF2GUC_SAVE_RESTORE_VF_REQUEST_MSG_3_ADDR_HI, upper_32_bits(addr)),
FIELD_PREP(PF2GUC_SAVE_RESTORE_VF_REQUEST_MSG_4_SIZE, ndwords),
};
return xe_guc_ct_send_block(&guc->ct, request, ARRAY_SIZE(request));
}
/* Return: size of the state in dwords or a negative error code on failure */
static int pf_send_guc_query_vf_state_size(struct xe_gt *gt, unsigned int vfid)
{
int ret;
ret = guc_action_vf_save_restore(>->uc.guc, vfid, GUC_PF_OPCODE_VF_SAVE, 0, 0);
return ret ?: -ENODATA;
}
/* Return: number of state dwords saved or a negative error code on failure */
static int pf_send_guc_save_vf_state(struct xe_gt *gt, unsigned int vfid,
void *buff, size_t size)
{
const int ndwords = size / sizeof(u32);
struct xe_tile *tile = gt_to_tile(gt);
struct xe_device *xe = tile_to_xe(tile);
struct xe_guc *guc = >->uc.guc;
struct xe_bo *bo;
int ret;
xe_gt_assert(gt, size % sizeof(u32) == 0);
xe_gt_assert(gt, size == ndwords * sizeof(u32));
bo = xe_bo_create_pin_map(xe, tile, NULL,
ALIGN(size, PAGE_SIZE),
ttm_bo_type_kernel,
XE_BO_FLAG_SYSTEM |
XE_BO_FLAG_GGTT |
XE_BO_FLAG_GGTT_INVALIDATE);
if (IS_ERR(bo))
return PTR_ERR(bo);
ret = guc_action_vf_save_restore(guc, vfid, GUC_PF_OPCODE_VF_SAVE,
xe_bo_ggtt_addr(bo), ndwords);
if (!ret)
ret = -ENODATA;
else if (ret > ndwords)
ret = -EPROTO;
else if (ret > 0)
xe_map_memcpy_from(xe, buff, &bo->vmap, 0, ret * sizeof(u32));
xe_bo_unpin_map_no_vm(bo);
return ret;
}
/* Return: number of state dwords restored or a negative error code on failure */
static int pf_send_guc_restore_vf_state(struct xe_gt *gt, unsigned int vfid,
const void *buff, size_t size)
{
const int ndwords = size / sizeof(u32);
struct xe_tile *tile = gt_to_tile(gt);
struct xe_device *xe = tile_to_xe(tile);
struct xe_guc *guc = >->uc.guc;
struct xe_bo *bo;
int ret;
xe_gt_assert(gt, size % sizeof(u32) == 0);
xe_gt_assert(gt, size == ndwords * sizeof(u32));
bo = xe_bo_create_pin_map(xe, tile, NULL,
ALIGN(size, PAGE_SIZE),
ttm_bo_type_kernel,
XE_BO_FLAG_SYSTEM |
XE_BO_FLAG_GGTT |
XE_BO_FLAG_GGTT_INVALIDATE);
if (IS_ERR(bo))
return PTR_ERR(bo);
xe_map_memcpy_to(xe, &bo->vmap, 0, buff, size);
ret = guc_action_vf_save_restore(guc, vfid, GUC_PF_OPCODE_VF_RESTORE,
xe_bo_ggtt_addr(bo), ndwords);
if (!ret)
ret = -ENODATA;
else if (ret > ndwords)
ret = -EPROTO;
xe_bo_unpin_map_no_vm(bo);
return ret;
}
static bool pf_migration_supported(struct xe_gt *gt)
{
xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
return gt->sriov.pf.migration.supported;
}
static struct mutex *pf_migration_mutex(struct xe_gt *gt)
{
xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
return >->sriov.pf.migration.snapshot_lock;
}
static struct xe_gt_sriov_state_snapshot *pf_pick_vf_snapshot(struct xe_gt *gt,
unsigned int vfid)
{
xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
xe_gt_assert(gt, vfid <= xe_sriov_pf_get_totalvfs(gt_to_xe(gt)));
lockdep_assert_held(pf_migration_mutex(gt));
return >->sriov.pf.vfs[vfid].snapshot;
}
static unsigned int pf_snapshot_index(struct xe_gt *gt, struct xe_gt_sriov_state_snapshot *snapshot)
{
return container_of(snapshot, struct xe_gt_sriov_metadata, snapshot) - gt->sriov.pf.vfs;
}
static void pf_free_guc_state(struct xe_gt *gt, struct xe_gt_sriov_state_snapshot *snapshot)
{
struct xe_device *xe = gt_to_xe(gt);
drmm_kfree(&xe->drm, snapshot->guc.buff);
snapshot->guc.buff = NULL;
snapshot->guc.size = 0;
}
static int pf_alloc_guc_state(struct xe_gt *gt,
struct xe_gt_sriov_state_snapshot *snapshot,
size_t size)
{
struct xe_device *xe = gt_to_xe(gt);
void *p;
pf_free_guc_state(gt, snapshot);
if (!size)
return -ENODATA;
if (size % sizeof(u32))
return -EINVAL;
if (size > SZ_2M)
return -EFBIG;
p = drmm_kzalloc(&xe->drm, size, GFP_KERNEL);
if (!p)
return -ENOMEM;
snapshot->guc.buff = p;
snapshot->guc.size = size;
return 0;
}
static void pf_dump_guc_state(struct xe_gt *gt, struct xe_gt_sriov_state_snapshot *snapshot)
{
if (IS_ENABLED(CONFIG_DRM_XE_DEBUG_SRIOV)) {
unsigned int vfid __maybe_unused = pf_snapshot_index(gt, snapshot);
xe_gt_sriov_dbg_verbose(gt, "VF%u GuC state is %zu dwords:\n",
vfid, snapshot->guc.size / sizeof(u32));
print_hex_dump_bytes("state: ", DUMP_PREFIX_OFFSET,
snapshot->guc.buff, min(SZ_64, snapshot->guc.size));
}
}
static int pf_save_vf_guc_state(struct xe_gt *gt, unsigned int vfid)
{
struct xe_gt_sriov_state_snapshot *snapshot = pf_pick_vf_snapshot(gt, vfid);
size_t size;
int ret;
ret = pf_send_guc_query_vf_state_size(gt, vfid);
if (ret < 0)
goto fail;
size = ret * sizeof(u32);
xe_gt_sriov_dbg_verbose(gt, "VF%u state size is %d dwords (%zu bytes)\n", vfid, ret, size);
ret = pf_alloc_guc_state(gt, snapshot, size);
if (ret < 0)
goto fail;
ret = pf_send_guc_save_vf_state(gt, vfid, snapshot->guc.buff, size);
if (ret < 0)
goto fail;
size = ret * sizeof(u32);
xe_gt_assert(gt, size);
xe_gt_assert(gt, size <= snapshot->guc.size);
snapshot->guc.size = size;
pf_dump_guc_state(gt, snapshot);
return 0;
fail:
xe_gt_sriov_dbg(gt, "Unable to save VF%u state (%pe)\n", vfid, ERR_PTR(ret));
pf_free_guc_state(gt, snapshot);
return ret;
}
/**
* xe_gt_sriov_pf_migration_save_guc_state() - Take a GuC VF state snapshot.
* @gt: the &xe_gt
* @vfid: the VF identifier
*
* This function is for PF only.
*
* Return: 0 on success or a negative error code on failure.
*/
int xe_gt_sriov_pf_migration_save_guc_state(struct xe_gt *gt, unsigned int vfid)
{
int err;
xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
xe_gt_assert(gt, vfid != PFID);
xe_gt_assert(gt, vfid <= xe_sriov_pf_get_totalvfs(gt_to_xe(gt)));
if (!pf_migration_supported(gt))
return -ENOPKG;
mutex_lock(pf_migration_mutex(gt));
err = pf_save_vf_guc_state(gt, vfid);
mutex_unlock(pf_migration_mutex(gt));
return err;
}
static int pf_restore_vf_guc_state(struct xe_gt *gt, unsigned int vfid)
{
struct xe_gt_sriov_state_snapshot *snapshot = pf_pick_vf_snapshot(gt, vfid);
int ret;
if (!snapshot->guc.size)
return -ENODATA;
xe_gt_sriov_dbg_verbose(gt, "restoring %zu dwords of VF%u GuC state\n",
snapshot->guc.size / sizeof(u32), vfid);
ret = pf_send_guc_restore_vf_state(gt, vfid, snapshot->guc.buff, snapshot->guc.size);
if (ret < 0)
goto fail;
xe_gt_sriov_dbg_verbose(gt, "restored %d dwords of VF%u GuC state\n", ret, vfid);
return 0;
fail:
xe_gt_sriov_dbg(gt, "Failed to restore VF%u GuC state (%pe)\n", vfid, ERR_PTR(ret));
return ret;
}
/**
* xe_gt_sriov_pf_migration_restore_guc_state() - Restore a GuC VF state.
* @gt: the &xe_gt
* @vfid: the VF identifier
*
* This function is for PF only.
*
* Return: 0 on success or a negative error code on failure.
*/
int xe_gt_sriov_pf_migration_restore_guc_state(struct xe_gt *gt, unsigned int vfid)
{
int ret;
xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
xe_gt_assert(gt, vfid != PFID);
xe_gt_assert(gt, vfid <= xe_sriov_pf_get_totalvfs(gt_to_xe(gt)));
if (!pf_migration_supported(gt))
return -ENOPKG;
mutex_lock(pf_migration_mutex(gt));
ret = pf_restore_vf_guc_state(gt, vfid);
mutex_unlock(pf_migration_mutex(gt));
return ret;
}
#ifdef CONFIG_DEBUG_FS
/**
* xe_gt_sriov_pf_migration_read_guc_state() - Read a GuC VF state.
* @gt: the &xe_gt
* @vfid: the VF identifier
* @buf: the user space buffer to read to
* @count: the maximum number of bytes to read
* @pos: the current position in the buffer
*
* This function is for PF only.
*
* This function reads up to @count bytes from the saved VF GuC state buffer
* at offset @pos into the user space address starting at @buf.
*
* Return: the number of bytes read or a negative error code on failure.
*/
ssize_t xe_gt_sriov_pf_migration_read_guc_state(struct xe_gt *gt, unsigned int vfid,
char __user *buf, size_t count, loff_t *pos)
{
struct xe_gt_sriov_state_snapshot *snapshot;
ssize_t ret;
xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
xe_gt_assert(gt, vfid != PFID);
xe_gt_assert(gt, vfid <= xe_sriov_pf_get_totalvfs(gt_to_xe(gt)));
if (!pf_migration_supported(gt))
return -ENOPKG;
mutex_lock(pf_migration_mutex(gt));
snapshot = pf_pick_vf_snapshot(gt, vfid);
if (snapshot->guc.size)
ret = simple_read_from_buffer(buf, count, pos, snapshot->guc.buff,
snapshot->guc.size);
else
ret = -ENODATA;
mutex_unlock(pf_migration_mutex(gt));
return ret;
}
/**
* xe_gt_sriov_pf_migration_write_guc_state() - Write a GuC VF state.
* @gt: the &xe_gt
* @vfid: the VF identifier
* @buf: the user space buffer with GuC VF state
* @size: the size of GuC VF state (in bytes)
*
* This function is for PF only.
*
* This function reads @size bytes of the VF GuC state stored at user space
* address @buf and writes it into a internal VF state buffer.
*
* Return: the number of bytes used or a negative error code on failure.
*/
ssize_t xe_gt_sriov_pf_migration_write_guc_state(struct xe_gt *gt, unsigned int vfid,
const char __user *buf, size_t size)
{
struct xe_gt_sriov_state_snapshot *snapshot;
loff_t pos = 0;
ssize_t ret;
xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
xe_gt_assert(gt, vfid != PFID);
xe_gt_assert(gt, vfid <= xe_sriov_pf_get_totalvfs(gt_to_xe(gt)));
if (!pf_migration_supported(gt))
return -ENOPKG;
mutex_lock(pf_migration_mutex(gt));
snapshot = pf_pick_vf_snapshot(gt, vfid);
ret = pf_alloc_guc_state(gt, snapshot, size);
if (!ret) {
ret = simple_write_to_buffer(snapshot->guc.buff, size, &pos, buf, size);
if (ret < 0)
pf_free_guc_state(gt, snapshot);
else
pf_dump_guc_state(gt, snapshot);
}
mutex_unlock(pf_migration_mutex(gt));
return ret;
}
#endif /* CONFIG_DEBUG_FS */
static bool pf_check_migration_support(struct xe_gt *gt)
{
/* GuC 70.25 with save/restore v2 is required */
xe_gt_assert(gt, GUC_FIRMWARE_VER(>->uc.guc) >= MAKE_GUC_VER(70, 25, 0));
/* XXX: for now this is for feature enabling only */
return IS_ENABLED(CONFIG_DRM_XE_DEBUG);
}
/**
* xe_gt_sriov_pf_migration_init() - Initialize support for VF migration.
* @gt: the &xe_gt
*
* This function is for PF only.
*
* Return: 0 on success or a negative error code on failure.
*/
int xe_gt_sriov_pf_migration_init(struct xe_gt *gt)
{
struct xe_device *xe = gt_to_xe(gt);
int err;
xe_gt_assert(gt, IS_SRIOV_PF(xe));
gt->sriov.pf.migration.supported = pf_check_migration_support(gt);
if (!pf_migration_supported(gt))
return 0;
err = drmm_mutex_init(&xe->drm, >->sriov.pf.migration.snapshot_lock);
if (err)
return err;
return 0;
}
|