Free Electrons

Embedded Linux Experts

  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
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
/*
 * Copyright 2014 IBM Corp.
 *
 * 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.
 */

#include <linux/pci.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <misc/cxl.h>
#include <linux/msi.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/sched/mm.h>

#include "cxl.h"

/*
 * Since we want to track memory mappings to be able to force-unmap
 * when the AFU is no longer reachable, we need an inode. For devices
 * opened through the cxl user API, this is not a problem, but a
 * userland process can also get a cxl fd through the cxl_get_fd()
 * API, which is used by the cxlflash driver.
 *
 * Therefore we implement our own simple pseudo-filesystem and inode
 * allocator. We don't use the anonymous inode, as we need the
 * meta-data associated with it (address_space) and it is shared by
 * other drivers/processes, so it could lead to cxl unmapping VMAs
 * from random processes.
 */

#define CXL_PSEUDO_FS_MAGIC	0x1697697f

static int cxl_fs_cnt;
static struct vfsmount *cxl_vfs_mount;

static const struct dentry_operations cxl_fs_dops = {
	.d_dname	= simple_dname,
};

static struct dentry *cxl_fs_mount(struct file_system_type *fs_type, int flags,
				const char *dev_name, void *data)
{
	return mount_pseudo(fs_type, "cxl:", NULL, &cxl_fs_dops,
			CXL_PSEUDO_FS_MAGIC);
}

static struct file_system_type cxl_fs_type = {
	.name		= "cxl",
	.owner		= THIS_MODULE,
	.mount		= cxl_fs_mount,
	.kill_sb	= kill_anon_super,
};


void cxl_release_mapping(struct cxl_context *ctx)
{
	if (ctx->kernelapi && ctx->mapping)
		simple_release_fs(&cxl_vfs_mount, &cxl_fs_cnt);
}

static struct file *cxl_getfile(const char *name,
				const struct file_operations *fops,
				void *priv, int flags)
{
	struct qstr this;
	struct path path;
	struct file *file;
	struct inode *inode = NULL;
	int rc;

	/* strongly inspired by anon_inode_getfile() */

	if (fops->owner && !try_module_get(fops->owner))
		return ERR_PTR(-ENOENT);

	rc = simple_pin_fs(&cxl_fs_type, &cxl_vfs_mount, &cxl_fs_cnt);
	if (rc < 0) {
		pr_err("Cannot mount cxl pseudo filesystem: %d\n", rc);
		file = ERR_PTR(rc);
		goto err_module;
	}

	inode = alloc_anon_inode(cxl_vfs_mount->mnt_sb);
	if (IS_ERR(inode)) {
		file = ERR_CAST(inode);
		goto err_fs;
	}

	file = ERR_PTR(-ENOMEM);
	this.name = name;
	this.len = strlen(name);
	this.hash = 0;
	path.dentry = d_alloc_pseudo(cxl_vfs_mount->mnt_sb, &this);
	if (!path.dentry)
		goto err_inode;

	path.mnt = mntget(cxl_vfs_mount);
	d_instantiate(path.dentry, inode);

	file = alloc_file(&path, OPEN_FMODE(flags), fops);
	if (IS_ERR(file))
		goto err_dput;
	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
	file->private_data = priv;

	return file;

err_dput:
	path_put(&path);
err_inode:
	iput(inode);
err_fs:
	simple_release_fs(&cxl_vfs_mount, &cxl_fs_cnt);
err_module:
	module_put(fops->owner);
	return file;
}

struct cxl_context *cxl_dev_context_init(struct pci_dev *dev)
{
	struct cxl_afu *afu;
	struct cxl_context  *ctx;
	int rc;

	afu = cxl_pci_to_afu(dev);
	if (IS_ERR(afu))
		return ERR_CAST(afu);

	ctx = cxl_context_alloc();
	if (!ctx)
		return ERR_PTR(-ENOMEM);

	ctx->kernelapi = true;

	/* Make it a slave context.  We can promote it later? */
	rc = cxl_context_init(ctx, afu, false);
	if (rc)
		goto err_ctx;

	return ctx;

err_ctx:
	kfree(ctx);
	return ERR_PTR(rc);
}
EXPORT_SYMBOL_GPL(cxl_dev_context_init);

struct cxl_context *cxl_get_context(struct pci_dev *dev)
{
	return dev->dev.archdata.cxl_ctx;
}
EXPORT_SYMBOL_GPL(cxl_get_context);

int cxl_release_context(struct cxl_context *ctx)
{
	if (ctx->status >= STARTED)
		return -EBUSY;

	cxl_context_free(ctx);

	return 0;
}
EXPORT_SYMBOL_GPL(cxl_release_context);

static irq_hw_number_t cxl_find_afu_irq(struct cxl_context *ctx, int num)
{
	__u16 range;
	int r;

	for (r = 0; r < CXL_IRQ_RANGES; r++) {
		range = ctx->irqs.range[r];
		if (num < range) {
			return ctx->irqs.offset[r] + num;
		}
		num -= range;
	}
	return 0;
}

int _cxl_next_msi_hwirq(struct pci_dev *pdev, struct cxl_context **ctx, int *afu_irq)
{
	if (*ctx == NULL || *afu_irq == 0) {
		*afu_irq = 1;
		*ctx = cxl_get_context(pdev);
	} else {
		(*afu_irq)++;
		if (*afu_irq > cxl_get_max_irqs_per_process(pdev)) {
			*ctx = list_next_entry(*ctx, extra_irq_contexts);
			*afu_irq = 1;
		}
	}
	return cxl_find_afu_irq(*ctx, *afu_irq);
}
/* Exported via cxl_base */

int cxl_set_priv(struct cxl_context *ctx, void *priv)
{
	if (!ctx)
		return -EINVAL;

	ctx->priv = priv;

	return 0;
}
EXPORT_SYMBOL_GPL(cxl_set_priv);

void *cxl_get_priv(struct cxl_context *ctx)
{
	if (!ctx)
		return ERR_PTR(-EINVAL);

	return ctx->priv;
}
EXPORT_SYMBOL_GPL(cxl_get_priv);

int cxl_allocate_afu_irqs(struct cxl_context *ctx, int num)
{
	int res;
	irq_hw_number_t hwirq;

	if (num == 0)
		num = ctx->afu->pp_irqs;
	res = afu_allocate_irqs(ctx, num);
	if (res)
		return res;

	if (!cpu_has_feature(CPU_FTR_HVMODE)) {
		/* In a guest, the PSL interrupt is not multiplexed. It was
		 * allocated above, and we need to set its handler
		 */
		hwirq = cxl_find_afu_irq(ctx, 0);
		if (hwirq)
			cxl_map_irq(ctx->afu->adapter, hwirq, cxl_ops->psl_interrupt, ctx, "psl");
	}

	if (ctx->status == STARTED) {
		if (cxl_ops->update_ivtes)
			cxl_ops->update_ivtes(ctx);
		else WARN(1, "BUG: cxl_allocate_afu_irqs must be called prior to starting the context on this platform\n");
	}

	return res;
}
EXPORT_SYMBOL_GPL(cxl_allocate_afu_irqs);

void cxl_free_afu_irqs(struct cxl_context *ctx)
{
	irq_hw_number_t hwirq;
	unsigned int virq;

	if (!cpu_has_feature(CPU_FTR_HVMODE)) {
		hwirq = cxl_find_afu_irq(ctx, 0);
		if (hwirq) {
			virq = irq_find_mapping(NULL, hwirq);
			if (virq)
				cxl_unmap_irq(virq, ctx);
		}
	}
	afu_irq_name_free(ctx);
	cxl_ops->release_irq_ranges(&ctx->irqs, ctx->afu->adapter);
}
EXPORT_SYMBOL_GPL(cxl_free_afu_irqs);

int cxl_map_afu_irq(struct cxl_context *ctx, int num,
		    irq_handler_t handler, void *cookie, char *name)
{
	irq_hw_number_t hwirq;

	/*
	 * Find interrupt we are to register.
	 */
	hwirq = cxl_find_afu_irq(ctx, num);
	if (!hwirq)
		return -ENOENT;

	return cxl_map_irq(ctx->afu->adapter, hwirq, handler, cookie, name);
}
EXPORT_SYMBOL_GPL(cxl_map_afu_irq);

void cxl_unmap_afu_irq(struct cxl_context *ctx, int num, void *cookie)
{
	irq_hw_number_t hwirq;
	unsigned int virq;

	hwirq = cxl_find_afu_irq(ctx, num);
	if (!hwirq)
		return;

	virq = irq_find_mapping(NULL, hwirq);
	if (virq)
		cxl_unmap_irq(virq, cookie);
}
EXPORT_SYMBOL_GPL(cxl_unmap_afu_irq);

/*
 * Start a context
 * Code here similar to afu_ioctl_start_work().
 */
int cxl_start_context(struct cxl_context *ctx, u64 wed,
		      struct task_struct *task)
{
	int rc = 0;
	bool kernel = true;

	pr_devel("%s: pe: %i\n", __func__, ctx->pe);

	mutex_lock(&ctx->status_mutex);
	if (ctx->status == STARTED)
		goto out; /* already started */

	/*
	 * Increment the mapped context count for adapter. This also checks
	 * if adapter_context_lock is taken.
	 */
	rc = cxl_adapter_context_get(ctx->afu->adapter);
	if (rc)
		goto out;

	if (task) {
		ctx->pid = get_task_pid(task, PIDTYPE_PID);
		kernel = false;
		ctx->real_mode = false;

		/* acquire a reference to the task's mm */
		ctx->mm = get_task_mm(current);

		/* ensure this mm_struct can't be freed */
		cxl_context_mm_count_get(ctx);

		/* decrement the use count */
		if (ctx->mm)
			mmput(ctx->mm);
	}

	/*
	 * Increment driver use count. Enables global TLBIs for hash
	 * and callbacks to handle the segment table
	 */
	cxl_ctx_get();

	if ((rc = cxl_ops->attach_process(ctx, kernel, wed, 0))) {
		put_pid(ctx->pid);
		ctx->pid = NULL;
		cxl_adapter_context_put(ctx->afu->adapter);
		cxl_ctx_put();
		if (task)
			cxl_context_mm_count_put(ctx);
		goto out;
	}

	ctx->status = STARTED;
out:
	mutex_unlock(&ctx->status_mutex);
	return rc;
}
EXPORT_SYMBOL_GPL(cxl_start_context);

int cxl_process_element(struct cxl_context *ctx)
{
	return ctx->external_pe;
}
EXPORT_SYMBOL_GPL(cxl_process_element);

/* Stop a context.  Returns 0 on success, otherwise -Errno */
int cxl_stop_context(struct cxl_context *ctx)
{
	return __detach_context(ctx);
}
EXPORT_SYMBOL_GPL(cxl_stop_context);

void cxl_set_master(struct cxl_context *ctx)
{
	ctx->master = true;
}
EXPORT_SYMBOL_GPL(cxl_set_master);

int cxl_set_translation_mode(struct cxl_context *ctx, bool real_mode)
{
	if (ctx->status == STARTED) {
		/*
		 * We could potentially update the PE and issue an update LLCMD
		 * to support this, but it doesn't seem to have a good use case
		 * since it's trivial to just create a second kernel context
		 * with different translation modes, so until someone convinces
		 * me otherwise:
		 */
		return -EBUSY;
	}

	ctx->real_mode = real_mode;
	return 0;
}
EXPORT_SYMBOL_GPL(cxl_set_translation_mode);

/* wrappers around afu_* file ops which are EXPORTED */
int cxl_fd_open(struct inode *inode, struct file *file)
{
	return afu_open(inode, file);
}
EXPORT_SYMBOL_GPL(cxl_fd_open);
int cxl_fd_release(struct inode *inode, struct file *file)
{
	return afu_release(inode, file);
}
EXPORT_SYMBOL_GPL(cxl_fd_release);
long cxl_fd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
	return afu_ioctl(file, cmd, arg);
}
EXPORT_SYMBOL_GPL(cxl_fd_ioctl);
int cxl_fd_mmap(struct file *file, struct vm_area_struct *vm)
{
	return afu_mmap(file, vm);
}
EXPORT_SYMBOL_GPL(cxl_fd_mmap);
unsigned int cxl_fd_poll(struct file *file, struct poll_table_struct *poll)
{
	return afu_poll(file, poll);
}
EXPORT_SYMBOL_GPL(cxl_fd_poll);
ssize_t cxl_fd_read(struct file *file, char __user *buf, size_t count,
			loff_t *off)
{
	return afu_read(file, buf, count, off);
}
EXPORT_SYMBOL_GPL(cxl_fd_read);

#define PATCH_FOPS(NAME) if (!fops->NAME) fops->NAME = afu_fops.NAME

/* Get a struct file and fd for a context and attach the ops */
struct file *cxl_get_fd(struct cxl_context *ctx, struct file_operations *fops,
			int *fd)
{
	struct file *file;
	int rc, flags, fdtmp;
	char *name = NULL;

	/* only allow one per context */
	if (ctx->mapping)
		return ERR_PTR(-EEXIST);

	flags = O_RDWR | O_CLOEXEC;

	/* This code is similar to anon_inode_getfd() */
	rc = get_unused_fd_flags(flags);
	if (rc < 0)
		return ERR_PTR(rc);
	fdtmp = rc;

	/*
	 * Patch the file ops.  Needs to be careful that this is rentrant safe.
	 */
	if (fops) {
		PATCH_FOPS(open);
		PATCH_FOPS(poll);
		PATCH_FOPS(read);
		PATCH_FOPS(release);
		PATCH_FOPS(unlocked_ioctl);
		PATCH_FOPS(compat_ioctl);
		PATCH_FOPS(mmap);
	} else /* use default ops */
		fops = (struct file_operations *)&afu_fops;

	name = kasprintf(GFP_KERNEL, "cxl:%d", ctx->pe);
	file = cxl_getfile(name, fops, ctx, flags);
	kfree(name);
	if (IS_ERR(file))
		goto err_fd;

	cxl_context_set_mapping(ctx, file->f_mapping);
	*fd = fdtmp;
	return file;

err_fd:
	put_unused_fd(fdtmp);
	return NULL;
}
EXPORT_SYMBOL_GPL(cxl_get_fd);

struct cxl_context *cxl_fops_get_context(struct file *file)
{
	return file->private_data;
}
EXPORT_SYMBOL_GPL(cxl_fops_get_context);

void cxl_set_driver_ops(struct cxl_context *ctx,
			struct cxl_afu_driver_ops *ops)
{
	WARN_ON(!ops->fetch_event || !ops->event_delivered);
	atomic_set(&ctx->afu_driver_events, 0);
	ctx->afu_driver_ops = ops;
}
EXPORT_SYMBOL_GPL(cxl_set_driver_ops);

void cxl_context_events_pending(struct cxl_context *ctx,
				unsigned int new_events)
{
	atomic_add(new_events, &ctx->afu_driver_events);
	wake_up_all(&ctx->wq);
}
EXPORT_SYMBOL_GPL(cxl_context_events_pending);

int cxl_start_work(struct cxl_context *ctx,
		   struct cxl_ioctl_start_work *work)
{
	int rc;

	/* code taken from afu_ioctl_start_work */
	if (!(work->flags & CXL_START_WORK_NUM_IRQS))
		work->num_interrupts = ctx->afu->pp_irqs;
	else if ((work->num_interrupts < ctx->afu->pp_irqs) ||
		 (work->num_interrupts > ctx->afu->irqs_max)) {
		return -EINVAL;
	}

	rc = afu_register_irqs(ctx, work->num_interrupts);
	if (rc)
		return rc;

	rc = cxl_start_context(ctx, work->work_element_descriptor, current);
	if (rc < 0) {
		afu_release_irqs(ctx, ctx);
		return rc;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(cxl_start_work);

void __iomem *cxl_psa_map(struct cxl_context *ctx)
{
	if (ctx->status != STARTED)
		return NULL;

	pr_devel("%s: psn_phys%llx size:%llx\n",
		__func__, ctx->psn_phys, ctx->psn_size);
	return ioremap(ctx->psn_phys, ctx->psn_size);
}
EXPORT_SYMBOL_GPL(cxl_psa_map);

void cxl_psa_unmap(void __iomem *addr)
{
	iounmap(addr);
}
EXPORT_SYMBOL_GPL(cxl_psa_unmap);

int cxl_afu_reset(struct cxl_context *ctx)
{
	struct cxl_afu *afu = ctx->afu;
	int rc;

	rc = cxl_ops->afu_reset(afu);
	if (rc)
		return rc;

	return cxl_ops->afu_check_and_enable(afu);
}
EXPORT_SYMBOL_GPL(cxl_afu_reset);

void cxl_perst_reloads_same_image(struct cxl_afu *afu,
				  bool perst_reloads_same_image)
{
	afu->adapter->perst_same_image = perst_reloads_same_image;
}
EXPORT_SYMBOL_GPL(cxl_perst_reloads_same_image);

ssize_t cxl_read_adapter_vpd(struct pci_dev *dev, void *buf, size_t count)
{
	struct cxl_afu *afu = cxl_pci_to_afu(dev);
	if (IS_ERR(afu))
		return -ENODEV;

	return cxl_ops->read_adapter_vpd(afu->adapter, buf, count);
}
EXPORT_SYMBOL_GPL(cxl_read_adapter_vpd);

int cxl_set_max_irqs_per_process(struct pci_dev *dev, int irqs)
{
	struct cxl_afu *afu = cxl_pci_to_afu(dev);
	if (IS_ERR(afu))
		return -ENODEV;

	if (irqs > afu->adapter->user_irqs)
		return -EINVAL;

	/* Limit user_irqs to prevent the user increasing this via sysfs */
	afu->adapter->user_irqs = irqs;
	afu->irqs_max = irqs;

	return 0;
}
EXPORT_SYMBOL_GPL(cxl_set_max_irqs_per_process);

int cxl_get_max_irqs_per_process(struct pci_dev *dev)
{
	struct cxl_afu *afu = cxl_pci_to_afu(dev);
	if (IS_ERR(afu))
		return -ENODEV;

	return afu->irqs_max;
}
EXPORT_SYMBOL_GPL(cxl_get_max_irqs_per_process);

/*
 * This is a special interrupt allocation routine called from the PHB's MSI
 * setup function. When capi interrupts are allocated in this manner they must
 * still be associated with a running context, but since the MSI APIs have no
 * way to specify this we use the default context associated with the device.
 *
 * The Mellanox CX4 has a hardware limitation that restricts the maximum AFU
 * interrupt number, so in order to overcome this their driver informs us of
 * the restriction by setting the maximum interrupts per context, and we
 * allocate additional contexts as necessary so that we can keep the AFU
 * interrupt number within the supported range.
 */
int _cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
{
	struct cxl_context *ctx, *new_ctx, *default_ctx;
	int remaining;
	int rc;

	ctx = default_ctx = cxl_get_context(pdev);
	if (WARN_ON(!default_ctx))
		return -ENODEV;

	remaining = nvec;
	while (remaining > 0) {
		rc = cxl_allocate_afu_irqs(ctx, min(remaining, ctx->afu->irqs_max));
		if (rc) {
			pr_warn("%s: Failed to find enough free MSIs\n", pci_name(pdev));
			return rc;
		}
		remaining -= ctx->afu->irqs_max;

		if (ctx != default_ctx && default_ctx->status == STARTED) {
			WARN_ON(cxl_start_context(ctx,
				be64_to_cpu(default_ctx->elem->common.wed),
				NULL));
		}

		if (remaining > 0) {
			new_ctx = cxl_dev_context_init(pdev);
			if (IS_ERR(new_ctx)) {
				pr_warn("%s: Failed to allocate enough contexts for MSIs\n", pci_name(pdev));
				return -ENOSPC;
			}
			list_add(&new_ctx->extra_irq_contexts, &ctx->extra_irq_contexts);
			ctx = new_ctx;
		}
	}

	return 0;
}
/* Exported via cxl_base */

void _cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev)
{
	struct cxl_context *ctx, *pos, *tmp;

	ctx = cxl_get_context(pdev);
	if (WARN_ON(!ctx))
		return;

	cxl_free_afu_irqs(ctx);
	list_for_each_entry_safe(pos, tmp, &ctx->extra_irq_contexts, extra_irq_contexts) {
		cxl_stop_context(pos);
		cxl_free_afu_irqs(pos);
		list_del(&pos->extra_irq_contexts);
		cxl_release_context(pos);
	}
}
/* Exported via cxl_base */