summaryrefslogtreecommitdiff
path: root/drivers/xen/xen-pciback/pciback_ops.c
blob: fb0221434f814aa49eef41f6aea7a60c86a4c817 (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
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
/*
 * PCI Backend Operations - respond to PCI requests from Frontend
 *
 *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/module.h>
#include <linux/wait.h>
#include <linux/bitops.h>
#include <xen/events.h>
#include <linux/sched.h>
#include "pciback.h"

int verbose_request;
module_param(verbose_request, int, 0644);

static irqreturn_t xen_pcibk_guest_interrupt(int irq, void *dev_id);

/* Ensure a device is has the fake IRQ handler "turned on/off" and is
 * ready to be exported. This MUST be run after xen_pcibk_reset_device
 * which does the actual PCI device enable/disable.
 */
static void xen_pcibk_control_isr(struct pci_dev *dev, int reset)
{
	struct xen_pcibk_dev_data *dev_data;
	int rc;
	int enable = 0;

	dev_data = pci_get_drvdata(dev);
	if (!dev_data)
		return;

	/* We don't deal with bridges */
	if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL)
		return;

	if (reset) {
		dev_data->enable_intx = 0;
		dev_data->ack_intr = 0;
	}
	enable =  dev_data->enable_intx;

	/* Asked to disable, but ISR isn't runnig */
	if (!enable && !dev_data->isr_on)
		return;

	/* Squirrel away the IRQs in the dev_data. We need this
	 * b/c when device transitions to MSI, the dev->irq is
	 * overwritten with the MSI vector.
	 */
	if (enable)
		dev_data->irq = dev->irq;

	/*
	 * SR-IOV devices in all use MSI-X and have no legacy
	 * interrupts, so inhibit creating a fake IRQ handler for them.
	 */
	if (dev_data->irq == 0)
		goto out;

	dev_dbg(&dev->dev, "%s: #%d %s %s%s %s-> %s\n",
		dev_data->irq_name,
		dev_data->irq,
		pci_is_enabled(dev) ? "on" : "off",
		dev->msi_enabled ? "MSI" : "",
		dev->msix_enabled ? "MSI/X" : "",
		dev_data->isr_on ? "enable" : "disable",
		enable ? "enable" : "disable");

	if (enable) {
		/*
		 * The MSI or MSI-X should not have an IRQ handler. Otherwise
		 * if the guest terminates we BUG_ON in free_msi_irqs.
		 */
		if (dev->msi_enabled || dev->msix_enabled)
			goto out;

		rc = request_irq(dev_data->irq,
				xen_pcibk_guest_interrupt, IRQF_SHARED,
				dev_data->irq_name, dev);
		if (rc) {
			dev_err(&dev->dev, "%s: failed to install fake IRQ " \
				"handler for IRQ %d! (rc:%d)\n",
				dev_data->irq_name, dev_data->irq, rc);
			goto out;
		}
	} else {
		free_irq(dev_data->irq, dev);
		dev_data->irq = 0;
	}
	dev_data->isr_on = enable;
	dev_data->ack_intr = enable;
out:
	dev_dbg(&dev->dev, "%s: #%d %s %s%s %s\n",
		dev_data->irq_name,
		dev_data->irq,
		pci_is_enabled(dev) ? "on" : "off",
		dev->msi_enabled ? "MSI" : "",
		dev->msix_enabled ? "MSI/X" : "",
		enable ? (dev_data->isr_on ? "enabled" : "failed to enable") :
			(dev_data->isr_on ? "failed to disable" : "disabled"));
}

/* Ensure a device is "turned off" and ready to be exported.
 * (Also see xen_pcibk_config_reset to ensure virtual configuration space is
 * ready to be re-exported)
 */
void xen_pcibk_reset_device(struct pci_dev *dev)
{
	u16 cmd;

	xen_pcibk_control_isr(dev, 1 /* reset device */);

	/* Disable devices (but not bridges) */
	if (dev->hdr_type == PCI_HEADER_TYPE_NORMAL) {
#ifdef CONFIG_PCI_MSI
		/* The guest could have been abruptly killed without
		 * disabling MSI/MSI-X interrupts.*/
		if (dev->msix_enabled)
			pci_disable_msix(dev);
		if (dev->msi_enabled)
			pci_disable_msi(dev);
#endif
		if (pci_is_enabled(dev))
			pci_disable_device(dev);

		pci_write_config_word(dev, PCI_COMMAND, 0);

		dev->is_busmaster = 0;
	} else {
		pci_read_config_word(dev, PCI_COMMAND, &cmd);
		if (cmd & (PCI_COMMAND_INVALIDATE)) {
			cmd &= ~(PCI_COMMAND_INVALIDATE);
			pci_write_config_word(dev, PCI_COMMAND, cmd);

			dev->is_busmaster = 0;
		}
	}
}

#ifdef CONFIG_PCI_MSI
static
int xen_pcibk_enable_msi(struct xen_pcibk_device *pdev,
			 struct pci_dev *dev, struct xen_pci_op *op)
{
	struct xen_pcibk_dev_data *dev_data;
	int status;

	if (unlikely(verbose_request))
		printk(KERN_DEBUG DRV_NAME ": %s: enable MSI\n", pci_name(dev));

	if (dev->msi_enabled)
		status = -EALREADY;
	else if (dev->msix_enabled)
		status = -ENXIO;
	else
		status = pci_enable_msi(dev);

	if (status) {
		pr_warn_ratelimited("%s: error enabling MSI for guest %u: err %d\n",
				    pci_name(dev), pdev->xdev->otherend_id,
				    status);
		op->value = 0;
		return XEN_PCI_ERR_op_failed;
	}

	/* The value the guest needs is actually the IDT vector, not the
	 * the local domain's IRQ number. */

	op->value = dev->irq ? xen_pirq_from_irq(dev->irq) : 0;
	if (unlikely(verbose_request))
		printk(KERN_DEBUG DRV_NAME ": %s: MSI: %d\n", pci_name(dev),
			op->value);

	dev_data = pci_get_drvdata(dev);
	if (dev_data)
		dev_data->ack_intr = 0;

	return 0;
}

static
int xen_pcibk_disable_msi(struct xen_pcibk_device *pdev,
			  struct pci_dev *dev, struct xen_pci_op *op)
{
	if (unlikely(verbose_request))
		printk(KERN_DEBUG DRV_NAME ": %s: disable MSI\n",
		       pci_name(dev));

	if (dev->msi_enabled) {
		struct xen_pcibk_dev_data *dev_data;

		pci_disable_msi(dev);

		dev_data = pci_get_drvdata(dev);
		if (dev_data)
			dev_data->ack_intr = 1;
	}
	op->value = dev->irq ? xen_pirq_from_irq(dev->irq) : 0;
	if (unlikely(verbose_request))
		printk(KERN_DEBUG DRV_NAME ": %s: MSI: %d\n", pci_name(dev),
			op->value);
	return 0;
}

static
int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev,
			  struct pci_dev *dev, struct xen_pci_op *op)
{
	struct xen_pcibk_dev_data *dev_data;
	int i, result;
	struct msix_entry *entries;
	u16 cmd;

	if (unlikely(verbose_request))
		printk(KERN_DEBUG DRV_NAME ": %s: enable MSI-X\n",
		       pci_name(dev));

	if (op->value > SH_INFO_MAX_VEC)
		return -EINVAL;

	if (dev->msix_enabled)
		return -EALREADY;

	/*
	 * PCI_COMMAND_MEMORY must be enabled, otherwise we may not be able
	 * to access the BARs where the MSI-X entries reside.
	 * But VF devices are unique in which the PF needs to be checked.
	 */
	pci_read_config_word(pci_physfn(dev), PCI_COMMAND, &cmd);
	if (dev->msi_enabled || !(cmd & PCI_COMMAND_MEMORY))
		return -ENXIO;

	entries = kmalloc(op->value * sizeof(*entries), GFP_KERNEL);
	if (entries == NULL)
		return -ENOMEM;

	for (i = 0; i < op->value; i++) {
		entries[i].entry = op->msix_entries[i].entry;
		entries[i].vector = op->msix_entries[i].vector;
	}

	result = pci_enable_msix_exact(dev, entries, op->value);
	if (result == 0) {
		for (i = 0; i < op->value; i++) {
			op->msix_entries[i].entry = entries[i].entry;
			if (entries[i].vector) {
				op->msix_entries[i].vector =
					xen_pirq_from_irq(entries[i].vector);
				if (unlikely(verbose_request))
					printk(KERN_DEBUG DRV_NAME ": %s: " \
						"MSI-X[%d]: %d\n",
						pci_name(dev), i,
						op->msix_entries[i].vector);
			}
		}
	} else
		pr_warn_ratelimited("%s: error enabling MSI-X for guest %u: err %d!\n",
				    pci_name(dev), pdev->xdev->otherend_id,
				    result);
	kfree(entries);

	op->value = result;
	dev_data = pci_get_drvdata(dev);
	if (dev_data)
		dev_data->ack_intr = 0;

	return result > 0 ? 0 : result;
}

static
int xen_pcibk_disable_msix(struct xen_pcibk_device *pdev,
			   struct pci_dev *dev, struct xen_pci_op *op)
{
	if (unlikely(verbose_request))
		printk(KERN_DEBUG DRV_NAME ": %s: disable MSI-X\n",
			pci_name(dev));

	if (dev->msix_enabled) {
		struct xen_pcibk_dev_data *dev_data;

		pci_disable_msix(dev);

		dev_data = pci_get_drvdata(dev);
		if (dev_data)
			dev_data->ack_intr = 1;
	}
	/*
	 * SR-IOV devices (which don't have any legacy IRQ) have
	 * an undefined IRQ value of zero.
	 */
	op->value = dev->irq ? xen_pirq_from_irq(dev->irq) : 0;
	if (unlikely(verbose_request))
		printk(KERN_DEBUG DRV_NAME ": %s: MSI-X: %d\n",
		       pci_name(dev), op->value);
	return 0;
}
#endif
/*
* Now the same evtchn is used for both pcifront conf_read_write request
* as well as pcie aer front end ack. We use a new work_queue to schedule
* xen_pcibk conf_read_write service for avoiding confict with aer_core
* do_recovery job which also use the system default work_queue
*/
void xen_pcibk_test_and_schedule_op(struct xen_pcibk_device *pdev)
{
	/* Check that frontend is requesting an operation and that we are not
	 * already processing a request */
	if (test_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags)
	    && !test_and_set_bit(_PDEVF_op_active, &pdev->flags)) {
		queue_work(xen_pcibk_wq, &pdev->op_work);
	}
	/*_XEN_PCIB_active should have been cleared by pcifront. And also make
	sure xen_pcibk is waiting for ack by checking _PCIB_op_pending*/
	if (!test_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags)
	    && test_bit(_PCIB_op_pending, &pdev->flags)) {
		wake_up(&xen_pcibk_aer_wait_queue);
	}
}

/* Performing the configuration space reads/writes must not be done in atomic
 * context because some of the pci_* functions can sleep (mostly due to ACPI
 * use of semaphores). This function is intended to be called from a work
 * queue in process context taking a struct xen_pcibk_device as a parameter */

void xen_pcibk_do_op(struct work_struct *data)
{
	struct xen_pcibk_device *pdev =
		container_of(data, struct xen_pcibk_device, op_work);
	struct pci_dev *dev;
	struct xen_pcibk_dev_data *dev_data = NULL;
	struct xen_pci_op *op = &pdev->op;
	int test_intx = 0;
#ifdef CONFIG_PCI_MSI
	unsigned int nr = 0;
#endif

	*op = pdev->sh_info->op;
	barrier();
	dev = xen_pcibk_get_pci_dev(pdev, op->domain, op->bus, op->devfn);

	if (dev == NULL)
		op->err = XEN_PCI_ERR_dev_not_found;
	else {
		dev_data = pci_get_drvdata(dev);
		if (dev_data)
			test_intx = dev_data->enable_intx;
		switch (op->cmd) {
		case XEN_PCI_OP_conf_read:
			op->err = xen_pcibk_config_read(dev,
				  op->offset, op->size, &op->value);
			break;
		case XEN_PCI_OP_conf_write:
			op->err = xen_pcibk_config_write(dev,
				  op->offset, op->size,	op->value);
			break;
#ifdef CONFIG_PCI_MSI
		case XEN_PCI_OP_enable_msi:
			op->err = xen_pcibk_enable_msi(pdev, dev, op);
			break;
		case XEN_PCI_OP_disable_msi:
			op->err = xen_pcibk_disable_msi(pdev, dev, op);
			break;
		case XEN_PCI_OP_enable_msix:
			nr = op->value;
			op->err = xen_pcibk_enable_msix(pdev, dev, op);
			break;
		case XEN_PCI_OP_disable_msix:
			op->err = xen_pcibk_disable_msix(pdev, dev, op);
			break;
#endif
		default:
			op->err = XEN_PCI_ERR_not_implemented;
			break;
		}
	}
	if (!op->err && dev && dev_data) {
		/* Transition detected */
		if ((dev_data->enable_intx != test_intx))
			xen_pcibk_control_isr(dev, 0 /* no reset */);
	}
	pdev->sh_info->op.err = op->err;
	pdev->sh_info->op.value = op->value;
#ifdef CONFIG_PCI_MSI
	if (op->cmd == XEN_PCI_OP_enable_msix && op->err == 0) {
		unsigned int i;

		for (i = 0; i < nr; i++)
			pdev->sh_info->op.msix_entries[i].vector =
				op->msix_entries[i].vector;
	}
#endif
	/* Tell the driver domain that we're done. */
	wmb();
	clear_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags);
	notify_remote_via_irq(pdev->evtchn_irq);

	/* Mark that we're done. */
	smp_mb__before_atomic(); /* /after/ clearing PCIF_active */
	clear_bit(_PDEVF_op_active, &pdev->flags);
	smp_mb__after_atomic(); /* /before/ final check for work */

	/* Check to see if the driver domain tried to start another request in
	 * between clearing _XEN_PCIF_active and clearing _PDEVF_op_active.
	*/
	xen_pcibk_test_and_schedule_op(pdev);
}

irqreturn_t xen_pcibk_handle_event(int irq, void *dev_id)
{
	struct xen_pcibk_device *pdev = dev_id;

	xen_pcibk_test_and_schedule_op(pdev);

	return IRQ_HANDLED;
}
static irqreturn_t xen_pcibk_guest_interrupt(int irq, void *dev_id)
{
	struct pci_dev *dev = (struct pci_dev *)dev_id;
	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);

	if (dev_data->isr_on && dev_data->ack_intr) {
		dev_data->handled++;
		if ((dev_data->handled % 1000) == 0) {
			if (xen_test_irq_shared(irq)) {
				pr_info("%s IRQ line is not shared "
					"with other domains. Turning ISR off\n",
					 dev_data->irq_name);
				dev_data->ack_intr = 0;
			}
		}
		return IRQ_HANDLED;
	}
	return IRQ_NONE;
}