1 /*
2 * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
3 *
4 * This software is available to you under a choice of one of two
5 * licenses. You may choose to be licensed under the terms of the GNU
6 * General Public License (GPL) Version 2, available from the file
7 * COPYING in the main directory of this source tree, or the
8 * OpenIB.org BSD license below:
9 *
10 * Redistribution and use in source and binary forms, with or
11 * without modification, are permitted provided that the following
12 * conditions are met:
13 *
14 * - Redistributions of source code must retain the above
15 * copyright notice, this list of conditions and the following
16 * disclaimer.
17 *
18 * - Redistributions in binary form must reproduce the above
19 * copyright notice, this list of conditions and the following
20 * disclaimer in the documentation and/or other materials
21 * provided with the distribution.
22 *
23 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
24 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
25 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
26 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
27 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
28 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
29 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
30 * SOFTWARE.
31 */
32
33 #include <linux/highmem.h>
34 #include <linux/kernel.h>
35 #include <linux/delay.h>
36 #include <linux/mlx5/driver.h>
37 #include <linux/xarray.h>
38 #include "mlx5_core.h"
39 #include "lib/eq.h"
40 #include "lib/tout.h"
41
42 enum {
43 MLX5_PAGES_CANT_GIVE = 0,
44 MLX5_PAGES_GIVE = 1,
45 MLX5_PAGES_TAKE = 2
46 };
47
48 struct mlx5_pages_req {
49 struct mlx5_core_dev *dev;
50 u16 func_id;
51 u8 ec_function;
52 s32 npages;
53 struct work_struct work;
54 u8 release_all;
55 };
56
57 struct fw_page {
58 struct rb_node rb_node;
59 u64 addr;
60 struct page *page;
61 u32 function;
62 unsigned long bitmask;
63 struct list_head list;
64 unsigned int free_count;
65 };
66
67 enum {
68 MLX5_MAX_RECLAIM_TIME_MILI = 5000,
69 MLX5_NUM_4K_IN_PAGE = PAGE_SIZE / MLX5_ADAPTER_PAGE_SIZE,
70 };
71
get_function(u16 func_id,bool ec_function)72 static u32 get_function(u16 func_id, bool ec_function)
73 {
74 return (u32)func_id | (ec_function << 16);
75 }
76
func_id_to_type(struct mlx5_core_dev * dev,u16 func_id,bool ec_function)77 static u16 func_id_to_type(struct mlx5_core_dev *dev, u16 func_id, bool ec_function)
78 {
79 if (!func_id)
80 return mlx5_core_is_ecpf(dev) && !ec_function ? MLX5_HOST_PF : MLX5_PF;
81
82 return func_id <= mlx5_core_max_vfs(dev) ? MLX5_VF : MLX5_SF;
83 }
84
page_root_per_function(struct mlx5_core_dev * dev,u32 function)85 static struct rb_root *page_root_per_function(struct mlx5_core_dev *dev, u32 function)
86 {
87 struct rb_root *root;
88 int err;
89
90 root = xa_load(&dev->priv.page_root_xa, function);
91 if (root)
92 return root;
93
94 root = kzalloc(sizeof(*root), GFP_KERNEL);
95 if (!root)
96 return ERR_PTR(-ENOMEM);
97
98 err = xa_insert(&dev->priv.page_root_xa, function, root, GFP_KERNEL);
99 if (err) {
100 kfree(root);
101 return ERR_PTR(err);
102 }
103
104 *root = RB_ROOT;
105
106 return root;
107 }
108
insert_page(struct mlx5_core_dev * dev,u64 addr,struct page * page,u32 function)109 static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u32 function)
110 {
111 struct rb_node *parent = NULL;
112 struct rb_root *root;
113 struct rb_node **new;
114 struct fw_page *nfp;
115 struct fw_page *tfp;
116 int i;
117
118 root = page_root_per_function(dev, function);
119 if (IS_ERR(root))
120 return PTR_ERR(root);
121
122 new = &root->rb_node;
123
124 while (*new) {
125 parent = *new;
126 tfp = rb_entry(parent, struct fw_page, rb_node);
127 if (tfp->addr < addr)
128 new = &parent->rb_left;
129 else if (tfp->addr > addr)
130 new = &parent->rb_right;
131 else
132 return -EEXIST;
133 }
134
135 nfp = kzalloc(sizeof(*nfp), GFP_KERNEL);
136 if (!nfp)
137 return -ENOMEM;
138
139 nfp->addr = addr;
140 nfp->page = page;
141 nfp->function = function;
142 nfp->free_count = MLX5_NUM_4K_IN_PAGE;
143 for (i = 0; i < MLX5_NUM_4K_IN_PAGE; i++)
144 set_bit(i, &nfp->bitmask);
145
146 rb_link_node(&nfp->rb_node, parent, new);
147 rb_insert_color(&nfp->rb_node, root);
148 list_add(&nfp->list, &dev->priv.free_list);
149
150 return 0;
151 }
152
find_fw_page(struct mlx5_core_dev * dev,u64 addr,u32 function)153 static struct fw_page *find_fw_page(struct mlx5_core_dev *dev, u64 addr,
154 u32 function)
155 {
156 struct fw_page *result = NULL;
157 struct rb_root *root;
158 struct rb_node *tmp;
159 struct fw_page *tfp;
160
161 root = xa_load(&dev->priv.page_root_xa, function);
162 if (WARN_ON_ONCE(!root))
163 return NULL;
164
165 tmp = root->rb_node;
166
167 while (tmp) {
168 tfp = rb_entry(tmp, struct fw_page, rb_node);
169 if (tfp->addr < addr) {
170 tmp = tmp->rb_left;
171 } else if (tfp->addr > addr) {
172 tmp = tmp->rb_right;
173 } else {
174 result = tfp;
175 break;
176 }
177 }
178
179 return result;
180 }
181
mlx5_cmd_query_pages(struct mlx5_core_dev * dev,u16 * func_id,s32 * npages,int boot)182 static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
183 s32 *npages, int boot)
184 {
185 u32 out[MLX5_ST_SZ_DW(query_pages_out)] = {};
186 u32 in[MLX5_ST_SZ_DW(query_pages_in)] = {};
187 int err;
188
189 MLX5_SET(query_pages_in, in, opcode, MLX5_CMD_OP_QUERY_PAGES);
190 MLX5_SET(query_pages_in, in, op_mod, boot ?
191 MLX5_QUERY_PAGES_IN_OP_MOD_BOOT_PAGES :
192 MLX5_QUERY_PAGES_IN_OP_MOD_INIT_PAGES);
193 MLX5_SET(query_pages_in, in, embedded_cpu_function, mlx5_core_is_ecpf(dev));
194
195 err = mlx5_cmd_exec_inout(dev, query_pages, in, out);
196 if (err)
197 return err;
198
199 *npages = MLX5_GET(query_pages_out, out, num_pages);
200 *func_id = MLX5_GET(query_pages_out, out, function_id);
201
202 return err;
203 }
204
alloc_4k(struct mlx5_core_dev * dev,u64 * addr,u32 function)205 static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr, u32 function)
206 {
207 struct fw_page *fp = NULL;
208 struct fw_page *iter;
209 unsigned n;
210
211 list_for_each_entry(iter, &dev->priv.free_list, list) {
212 if (iter->function != function)
213 continue;
214 fp = iter;
215 }
216
217 if (list_empty(&dev->priv.free_list) || !fp)
218 return -ENOMEM;
219
220 n = find_first_bit(&fp->bitmask, 8 * sizeof(fp->bitmask));
221 if (n >= MLX5_NUM_4K_IN_PAGE) {
222 mlx5_core_warn(dev, "alloc 4k bug: fw page = 0x%llx, n = %u, bitmask: %lu, max num of 4K pages: %d\n",
223 fp->addr, n, fp->bitmask, MLX5_NUM_4K_IN_PAGE);
224 return -ENOENT;
225 }
226 clear_bit(n, &fp->bitmask);
227 fp->free_count--;
228 if (!fp->free_count)
229 list_del(&fp->list);
230
231 *addr = fp->addr + n * MLX5_ADAPTER_PAGE_SIZE;
232
233 return 0;
234 }
235
236 #define MLX5_U64_4K_PAGE_MASK ((~(u64)0U) << PAGE_SHIFT)
237
free_fwp(struct mlx5_core_dev * dev,struct fw_page * fwp,bool in_free_list)238 static void free_fwp(struct mlx5_core_dev *dev, struct fw_page *fwp,
239 bool in_free_list)
240 {
241 struct rb_root *root;
242
243 root = xa_load(&dev->priv.page_root_xa, fwp->function);
244 if (WARN_ON_ONCE(!root))
245 return;
246
247 rb_erase(&fwp->rb_node, root);
248 if (in_free_list)
249 list_del(&fwp->list);
250 dma_unmap_page(mlx5_core_dma_dev(dev), fwp->addr & MLX5_U64_4K_PAGE_MASK,
251 PAGE_SIZE, DMA_BIDIRECTIONAL);
252 __free_page(fwp->page);
253 kfree(fwp);
254 }
255
free_4k(struct mlx5_core_dev * dev,u64 addr,u32 function)256 static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 function)
257 {
258 struct fw_page *fwp;
259 int n;
260
261 fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK, function);
262 if (!fwp) {
263 mlx5_core_warn_rl(dev, "page not found\n");
264 return;
265 }
266 n = (addr & ~MLX5_U64_4K_PAGE_MASK) >> MLX5_ADAPTER_PAGE_SHIFT;
267 fwp->free_count++;
268 set_bit(n, &fwp->bitmask);
269 if (fwp->free_count == MLX5_NUM_4K_IN_PAGE)
270 free_fwp(dev, fwp, fwp->free_count != 1);
271 else if (fwp->free_count == 1)
272 list_add(&fwp->list, &dev->priv.free_list);
273 }
274
alloc_system_page(struct mlx5_core_dev * dev,u32 function)275 static int alloc_system_page(struct mlx5_core_dev *dev, u32 function)
276 {
277 struct device *device = mlx5_core_dma_dev(dev);
278 int nid = dev_to_node(device);
279 struct page *page;
280 u64 zero_addr = 1;
281 u64 addr;
282 int err;
283
284 page = alloc_pages_node(nid, GFP_HIGHUSER, 0);
285 if (!page) {
286 mlx5_core_warn(dev, "failed to allocate page\n");
287 return -ENOMEM;
288 }
289 map:
290 addr = dma_map_page(device, page, 0, PAGE_SIZE, DMA_BIDIRECTIONAL);
291 if (dma_mapping_error(device, addr)) {
292 mlx5_core_warn(dev, "failed dma mapping page\n");
293 err = -ENOMEM;
294 goto err_mapping;
295 }
296
297 /* Firmware doesn't support page with physical address 0 */
298 if (addr == 0) {
299 zero_addr = addr;
300 goto map;
301 }
302
303 err = insert_page(dev, addr, page, function);
304 if (err) {
305 mlx5_core_err(dev, "failed to track allocated page\n");
306 dma_unmap_page(device, addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
307 }
308
309 err_mapping:
310 if (err)
311 __free_page(page);
312
313 if (zero_addr == 0)
314 dma_unmap_page(device, zero_addr, PAGE_SIZE,
315 DMA_BIDIRECTIONAL);
316
317 return err;
318 }
319
page_notify_fail(struct mlx5_core_dev * dev,u16 func_id,bool ec_function)320 static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id,
321 bool ec_function)
322 {
323 u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {};
324 int err;
325
326 MLX5_SET(manage_pages_in, in, opcode, MLX5_CMD_OP_MANAGE_PAGES);
327 MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_CANT_GIVE);
328 MLX5_SET(manage_pages_in, in, function_id, func_id);
329 MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
330
331 err = mlx5_cmd_exec_in(dev, manage_pages, in);
332 if (err)
333 mlx5_core_warn(dev, "page notify failed func_id(%d) err(%d)\n",
334 func_id, err);
335 }
336
give_pages(struct mlx5_core_dev * dev,u16 func_id,int npages,int event,bool ec_function)337 static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
338 int event, bool ec_function)
339 {
340 u32 function = get_function(func_id, ec_function);
341 u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0};
342 int inlen = MLX5_ST_SZ_BYTES(manage_pages_in);
343 int notify_fail = event;
344 u16 func_type;
345 u64 addr;
346 int err;
347 u32 *in;
348 int i;
349
350 inlen += npages * MLX5_FLD_SZ_BYTES(manage_pages_in, pas[0]);
351 in = kvzalloc(inlen, GFP_KERNEL);
352 if (!in) {
353 err = -ENOMEM;
354 mlx5_core_warn(dev, "vzalloc failed %d\n", inlen);
355 goto out_free;
356 }
357
358 for (i = 0; i < npages; i++) {
359 retry:
360 err = alloc_4k(dev, &addr, function);
361 if (err) {
362 if (err == -ENOMEM)
363 err = alloc_system_page(dev, function);
364 if (err) {
365 dev->priv.fw_pages_alloc_failed += (npages - i);
366 goto out_4k;
367 }
368
369 goto retry;
370 }
371 MLX5_ARRAY_SET64(manage_pages_in, in, pas, i, addr);
372 }
373
374 MLX5_SET(manage_pages_in, in, opcode, MLX5_CMD_OP_MANAGE_PAGES);
375 MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_GIVE);
376 MLX5_SET(manage_pages_in, in, function_id, func_id);
377 MLX5_SET(manage_pages_in, in, input_num_entries, npages);
378 MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
379
380 err = mlx5_cmd_do(dev, in, inlen, out, sizeof(out));
381 if (err == -EREMOTEIO) {
382 notify_fail = 0;
383 /* if triggered by FW and failed by FW ignore */
384 if (event) {
385 err = 0;
386 goto out_dropped;
387 }
388 }
389 err = mlx5_cmd_check(dev, err, in, out);
390 if (err) {
391 mlx5_core_warn(dev, "func_id 0x%x, npages %d, err %d\n",
392 func_id, npages, err);
393 goto out_dropped;
394 }
395
396 func_type = func_id_to_type(dev, func_id, ec_function);
397 dev->priv.page_counters[func_type] += npages;
398 dev->priv.fw_pages += npages;
399
400 mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n",
401 npages, ec_function, func_id, err);
402
403 kvfree(in);
404 return 0;
405
406 out_dropped:
407 dev->priv.give_pages_dropped += npages;
408 out_4k:
409 for (i--; i >= 0; i--)
410 free_4k(dev, MLX5_GET64(manage_pages_in, in, pas[i]), function);
411 out_free:
412 kvfree(in);
413 if (notify_fail)
414 page_notify_fail(dev, func_id, ec_function);
415 return err;
416 }
417
release_all_pages(struct mlx5_core_dev * dev,u16 func_id,bool ec_function)418 static void release_all_pages(struct mlx5_core_dev *dev, u16 func_id,
419 bool ec_function)
420 {
421 u32 function = get_function(func_id, ec_function);
422 struct rb_root *root;
423 struct rb_node *p;
424 int npages = 0;
425 u16 func_type;
426
427 root = xa_load(&dev->priv.page_root_xa, function);
428 if (WARN_ON_ONCE(!root))
429 return;
430
431 p = rb_first(root);
432 while (p) {
433 struct fw_page *fwp = rb_entry(p, struct fw_page, rb_node);
434
435 p = rb_next(p);
436 npages += (MLX5_NUM_4K_IN_PAGE - fwp->free_count);
437 free_fwp(dev, fwp, fwp->free_count);
438 }
439
440 func_type = func_id_to_type(dev, func_id, ec_function);
441 dev->priv.page_counters[func_type] -= npages;
442 dev->priv.fw_pages -= npages;
443
444 mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x\n",
445 npages, ec_function, func_id);
446 }
447
fwp_fill_manage_pages_out(struct fw_page * fwp,u32 * out,u32 index,u32 npages)448 static u32 fwp_fill_manage_pages_out(struct fw_page *fwp, u32 *out, u32 index,
449 u32 npages)
450 {
451 u32 pages_set = 0;
452 unsigned int n;
453
454 for_each_clear_bit(n, &fwp->bitmask, MLX5_NUM_4K_IN_PAGE) {
455 MLX5_ARRAY_SET64(manage_pages_out, out, pas, index + pages_set,
456 fwp->addr + (n * MLX5_ADAPTER_PAGE_SIZE));
457 pages_set++;
458
459 if (!--npages)
460 break;
461 }
462
463 return pages_set;
464 }
465
reclaim_pages_cmd(struct mlx5_core_dev * dev,u32 * in,int in_size,u32 * out,int out_size)466 static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
467 u32 *in, int in_size, u32 *out, int out_size)
468 {
469 struct rb_root *root;
470 struct fw_page *fwp;
471 struct rb_node *p;
472 bool ec_function;
473 u32 func_id;
474 u32 npages;
475 u32 i = 0;
476
477 if (!mlx5_cmd_is_down(dev))
478 return mlx5_cmd_do(dev, in, in_size, out, out_size);
479
480 /* No hard feelings, we want our pages back! */
481 npages = MLX5_GET(manage_pages_in, in, input_num_entries);
482 func_id = MLX5_GET(manage_pages_in, in, function_id);
483 ec_function = MLX5_GET(manage_pages_in, in, embedded_cpu_function);
484
485 root = xa_load(&dev->priv.page_root_xa, get_function(func_id, ec_function));
486 if (WARN_ON_ONCE(!root))
487 return -EEXIST;
488
489 p = rb_first(root);
490 while (p && i < npages) {
491 fwp = rb_entry(p, struct fw_page, rb_node);
492 p = rb_next(p);
493
494 i += fwp_fill_manage_pages_out(fwp, out, i, npages - i);
495 }
496
497 MLX5_SET(manage_pages_out, out, output_num_entries, i);
498 return 0;
499 }
500
reclaim_pages(struct mlx5_core_dev * dev,u16 func_id,int npages,int * nclaimed,bool event,bool ec_function)501 static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
502 int *nclaimed, bool event, bool ec_function)
503 {
504 u32 function = get_function(func_id, ec_function);
505 int outlen = MLX5_ST_SZ_BYTES(manage_pages_out);
506 u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {};
507 int num_claimed;
508 u16 func_type;
509 u32 *out;
510 int err;
511 int i;
512
513 if (nclaimed)
514 *nclaimed = 0;
515
516 outlen += npages * MLX5_FLD_SZ_BYTES(manage_pages_out, pas[0]);
517 out = kvzalloc(outlen, GFP_KERNEL);
518 if (!out)
519 return -ENOMEM;
520
521 MLX5_SET(manage_pages_in, in, opcode, MLX5_CMD_OP_MANAGE_PAGES);
522 MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_TAKE);
523 MLX5_SET(manage_pages_in, in, function_id, func_id);
524 MLX5_SET(manage_pages_in, in, input_num_entries, npages);
525 MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
526
527 mlx5_core_dbg(dev, "func 0x%x, npages %d, outlen %d\n",
528 func_id, npages, outlen);
529 err = reclaim_pages_cmd(dev, in, sizeof(in), out, outlen);
530 if (err) {
531 npages = MLX5_GET(manage_pages_in, in, input_num_entries);
532 dev->priv.reclaim_pages_discard += npages;
533 }
534 /* if triggered by FW event and failed by FW then ignore */
535 if (event && err == -EREMOTEIO) {
536 err = 0;
537 goto out_free;
538 }
539
540 err = mlx5_cmd_check(dev, err, in, out);
541 if (err) {
542 mlx5_core_err(dev, "failed reclaiming pages: err %d\n", err);
543 goto out_free;
544 }
545
546 num_claimed = MLX5_GET(manage_pages_out, out, output_num_entries);
547 if (num_claimed > npages) {
548 mlx5_core_warn(dev, "fw returned %d, driver asked %d => corruption\n",
549 num_claimed, npages);
550 err = -EINVAL;
551 goto out_free;
552 }
553
554 for (i = 0; i < num_claimed; i++)
555 free_4k(dev, MLX5_GET64(manage_pages_out, out, pas[i]), function);
556
557 if (nclaimed)
558 *nclaimed = num_claimed;
559
560 func_type = func_id_to_type(dev, func_id, ec_function);
561 dev->priv.page_counters[func_type] -= num_claimed;
562 dev->priv.fw_pages -= num_claimed;
563
564 out_free:
565 kvfree(out);
566 return err;
567 }
568
pages_work_handler(struct work_struct * work)569 static void pages_work_handler(struct work_struct *work)
570 {
571 struct mlx5_pages_req *req = container_of(work, struct mlx5_pages_req, work);
572 struct mlx5_core_dev *dev = req->dev;
573 int err = 0;
574
575 if (req->release_all)
576 release_all_pages(dev, req->func_id, req->ec_function);
577 else if (req->npages < 0)
578 err = reclaim_pages(dev, req->func_id, -1 * req->npages, NULL,
579 true, req->ec_function);
580 else if (req->npages > 0)
581 err = give_pages(dev, req->func_id, req->npages, 1, req->ec_function);
582
583 if (err)
584 mlx5_core_warn(dev, "%s fail %d\n",
585 req->npages < 0 ? "reclaim" : "give", err);
586
587 kfree(req);
588 }
589
590 enum {
591 EC_FUNCTION_MASK = 0x8000,
592 RELEASE_ALL_PAGES_MASK = 0x4000,
593 };
594
req_pages_handler(struct notifier_block * nb,unsigned long type,void * data)595 static int req_pages_handler(struct notifier_block *nb,
596 unsigned long type, void *data)
597 {
598 struct mlx5_pages_req *req;
599 struct mlx5_core_dev *dev;
600 struct mlx5_priv *priv;
601 struct mlx5_eqe *eqe;
602 bool ec_function;
603 bool release_all;
604 u16 func_id;
605 s32 npages;
606
607 priv = mlx5_nb_cof(nb, struct mlx5_priv, pg_nb);
608 dev = container_of(priv, struct mlx5_core_dev, priv);
609 eqe = data;
610
611 func_id = be16_to_cpu(eqe->data.req_pages.func_id);
612 npages = be32_to_cpu(eqe->data.req_pages.num_pages);
613 ec_function = be16_to_cpu(eqe->data.req_pages.ec_function) & EC_FUNCTION_MASK;
614 release_all = be16_to_cpu(eqe->data.req_pages.ec_function) &
615 RELEASE_ALL_PAGES_MASK;
616 mlx5_core_dbg(dev, "page request for func 0x%x, npages %d, release_all %d\n",
617 func_id, npages, release_all);
618 req = kzalloc(sizeof(*req), GFP_ATOMIC);
619 if (!req) {
620 mlx5_core_warn(dev, "failed to allocate pages request\n");
621 return NOTIFY_DONE;
622 }
623
624 req->dev = dev;
625 req->func_id = func_id;
626 req->npages = npages;
627 req->ec_function = ec_function;
628 req->release_all = release_all;
629 INIT_WORK(&req->work, pages_work_handler);
630 queue_work(dev->priv.pg_wq, &req->work);
631 return NOTIFY_OK;
632 }
633
mlx5_satisfy_startup_pages(struct mlx5_core_dev * dev,int boot)634 int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot)
635 {
636 u16 func_id;
637 s32 npages;
638 int err;
639
640 err = mlx5_cmd_query_pages(dev, &func_id, &npages, boot);
641 if (err)
642 return err;
643
644 mlx5_core_dbg(dev, "requested %d %s pages for func_id 0x%x\n",
645 npages, boot ? "boot" : "init", func_id);
646
647 return give_pages(dev, func_id, npages, 0, mlx5_core_is_ecpf(dev));
648 }
649
650 enum {
651 MLX5_BLKS_FOR_RECLAIM_PAGES = 12
652 };
653
optimal_reclaimed_pages(void)654 static int optimal_reclaimed_pages(void)
655 {
656 struct mlx5_cmd_prot_block *block;
657 struct mlx5_cmd_layout *lay;
658 int ret;
659
660 ret = (sizeof(lay->out) + MLX5_BLKS_FOR_RECLAIM_PAGES * sizeof(block->data) -
661 MLX5_ST_SZ_BYTES(manage_pages_out)) /
662 MLX5_FLD_SZ_BYTES(manage_pages_out, pas[0]);
663
664 return ret;
665 }
666
mlx5_reclaim_root_pages(struct mlx5_core_dev * dev,struct rb_root * root,u16 func_id)667 static int mlx5_reclaim_root_pages(struct mlx5_core_dev *dev,
668 struct rb_root *root, u16 func_id)
669 {
670 u64 recl_pages_to_jiffies = msecs_to_jiffies(mlx5_tout_ms(dev, RECLAIM_PAGES));
671 unsigned long end = jiffies + recl_pages_to_jiffies;
672
673 while (!RB_EMPTY_ROOT(root)) {
674 int nclaimed;
675 int err;
676
677 err = reclaim_pages(dev, func_id, optimal_reclaimed_pages(),
678 &nclaimed, false, mlx5_core_is_ecpf(dev));
679 if (err) {
680 mlx5_core_warn(dev, "failed reclaiming pages (%d) for func id 0x%x\n",
681 err, func_id);
682 return err;
683 }
684
685 if (nclaimed)
686 end = jiffies + recl_pages_to_jiffies;
687
688 if (time_after(jiffies, end)) {
689 mlx5_core_warn(dev, "FW did not return all pages. giving up...\n");
690 break;
691 }
692 }
693
694 return 0;
695 }
696
mlx5_reclaim_startup_pages(struct mlx5_core_dev * dev)697 int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
698 {
699 struct rb_root *root;
700 unsigned long id;
701 void *entry;
702
703 xa_for_each(&dev->priv.page_root_xa, id, entry) {
704 root = entry;
705 mlx5_reclaim_root_pages(dev, root, id);
706 xa_erase(&dev->priv.page_root_xa, id);
707 kfree(root);
708 }
709
710 WARN_ON(!xa_empty(&dev->priv.page_root_xa));
711
712 WARN(dev->priv.fw_pages,
713 "FW pages counter is %d after reclaiming all pages\n",
714 dev->priv.fw_pages);
715 WARN(dev->priv.page_counters[MLX5_VF],
716 "VFs FW pages counter is %d after reclaiming all pages\n",
717 dev->priv.page_counters[MLX5_VF]);
718 WARN(dev->priv.page_counters[MLX5_HOST_PF],
719 "External host PF FW pages counter is %d after reclaiming all pages\n",
720 dev->priv.page_counters[MLX5_HOST_PF]);
721
722 return 0;
723 }
724
mlx5_pagealloc_init(struct mlx5_core_dev * dev)725 int mlx5_pagealloc_init(struct mlx5_core_dev *dev)
726 {
727 INIT_LIST_HEAD(&dev->priv.free_list);
728 dev->priv.pg_wq = create_singlethread_workqueue("mlx5_page_allocator");
729 if (!dev->priv.pg_wq)
730 return -ENOMEM;
731
732 xa_init(&dev->priv.page_root_xa);
733 mlx5_pages_debugfs_init(dev);
734
735 return 0;
736 }
737
mlx5_pagealloc_cleanup(struct mlx5_core_dev * dev)738 void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev)
739 {
740 mlx5_pages_debugfs_cleanup(dev);
741 xa_destroy(&dev->priv.page_root_xa);
742 destroy_workqueue(dev->priv.pg_wq);
743 }
744
mlx5_pagealloc_start(struct mlx5_core_dev * dev)745 void mlx5_pagealloc_start(struct mlx5_core_dev *dev)
746 {
747 MLX5_NB_INIT(&dev->priv.pg_nb, req_pages_handler, PAGE_REQUEST);
748 mlx5_eq_notifier_register(dev, &dev->priv.pg_nb);
749 }
750
mlx5_pagealloc_stop(struct mlx5_core_dev * dev)751 void mlx5_pagealloc_stop(struct mlx5_core_dev *dev)
752 {
753 mlx5_eq_notifier_unregister(dev, &dev->priv.pg_nb);
754 flush_workqueue(dev->priv.pg_wq);
755 }
756
mlx5_wait_for_pages(struct mlx5_core_dev * dev,int * pages)757 int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages)
758 {
759 u64 recl_vf_pages_to_jiffies = msecs_to_jiffies(mlx5_tout_ms(dev, RECLAIM_VFS_PAGES));
760 unsigned long end = jiffies + recl_vf_pages_to_jiffies;
761 int prev_pages = *pages;
762
763 /* In case of internal error we will free the pages manually later */
764 if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
765 mlx5_core_warn(dev, "Skipping wait for vf pages stage");
766 return 0;
767 }
768
769 mlx5_core_dbg(dev, "Waiting for %d pages\n", prev_pages);
770 while (*pages) {
771 if (time_after(jiffies, end)) {
772 mlx5_core_warn(dev, "aborting while there are %d pending pages\n", *pages);
773 return -ETIMEDOUT;
774 }
775 if (*pages < prev_pages) {
776 end = jiffies + recl_vf_pages_to_jiffies;
777 prev_pages = *pages;
778 }
779 msleep(50);
780 }
781
782 mlx5_core_dbg(dev, "All pages received\n");
783 return 0;
784 }
785