summaryrefslogtreecommitdiff
path: root/drivers/misc/cxl/fault.c
blob: 2c64f55cf01f8db08cc5a88a7da47bf5a32d3b53 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright 2014 IBM Corp.
 */

#include <linux/workqueue.h>
#include <linux/sched/signal.h>
#include <linux/sched/mm.h>
#include <linux/pid.h>
#include <linux/mm.h>
#include <linux/moduleparam.h>

#undef MODULE_PARAM_PREFIX
#define MODULE_PARAM_PREFIX "cxl" "."
#include <asm/current.h>
#include <asm/copro.h>
#include <asm/mmu.h>

#include "cxl.h"
#include "trace.h"

static bool sste_matches(struct cxl_sste *sste, struct copro_slb *slb)
{
	return ((sste->vsid_data == cpu_to_be64(slb->vsid)) &&
		(sste->esid_data == cpu_to_be64(slb->esid)));
}

/*
 * This finds a free SSTE for the given SLB, or returns NULL if it's already in
 * the segment table.
 */
static struct cxl_sste *find_free_sste(struct cxl_context *ctx,
				       struct copro_slb *slb)
{
	struct cxl_sste *primary, *sste, *ret = NULL;
	unsigned int mask = (ctx->sst_size >> 7) - 1; /* SSTP0[SegTableSize] */
	unsigned int entry;
	unsigned int hash;

	if (slb->vsid & SLB_VSID_B_1T)
		hash = (slb->esid >> SID_SHIFT_1T) & mask;
	else /* 256M */
		hash = (slb->esid >> SID_SHIFT) & mask;

	primary = ctx->sstp + (hash << 3);

	for (entry = 0, sste = primary; entry < 8; entry++, sste++) {
		if (!ret && !(be64_to_cpu(sste->esid_data) & SLB_ESID_V))
			ret = sste;
		if (sste_matches(sste, slb))
			return NULL;
	}
	if (ret)
		return ret;

	/* Nothing free, select an entry to cast out */
	ret = primary + ctx->sst_lru;
	ctx->sst_lru = (ctx->sst_lru + 1) & 0x7;

	return ret;
}

static void cxl_load_segment(struct cxl_context *ctx, struct copro_slb *slb)
{
	/* mask is the group index, we search primary and secondary here. */
	struct cxl_sste *sste;
	unsigned long flags;

	spin_lock_irqsave(&ctx->sste_lock, flags);
	sste = find_free_sste(ctx, slb);
	if (!sste)
		goto out_unlock;

	pr_devel("CXL Populating SST[%li]: %#llx %#llx\n",
			sste - ctx->sstp, slb->vsid, slb->esid);
	trace_cxl_ste_write(ctx, sste - ctx->sstp, slb->esid, slb->vsid);

	sste->vsid_data = cpu_to_be64(slb->vsid);
	sste->esid_data = cpu_to_be64(slb->esid);
out_unlock:
	spin_unlock_irqrestore(&ctx->sste_lock, flags);
}

static int cxl_fault_segment(struct cxl_context *ctx, struct mm_struct *mm,
			     u64 ea)
{
	struct copro_slb slb = {0,0};
	int rc;

	if (!(rc = copro_calculate_slb(mm, ea, &slb))) {
		cxl_load_segment(ctx, &slb);
	}

	return rc;
}

static void cxl_ack_ae(struct cxl_context *ctx)
{
	unsigned long flags;

	cxl_ops->ack_irq(ctx, CXL_PSL_TFC_An_AE, 0);

	spin_lock_irqsave(&ctx->lock, flags);
	ctx->pending_fault = true;
	ctx->fault_addr = ctx->dar;
	ctx->fault_dsisr = ctx->dsisr;
	spin_unlock_irqrestore(&ctx->lock, flags);

	wake_up_all(&ctx->wq);
}

static int cxl_handle_segment_miss(struct cxl_context *ctx,
				   struct mm_struct *mm, u64 ea)
{
	int rc;

	pr_devel("CXL interrupt: Segment fault pe: %i ea: %#llx\n", ctx->pe, ea);
	trace_cxl_ste_miss(ctx, ea);

	if ((rc = cxl_fault_segment(ctx, mm, ea)))
		cxl_ack_ae(ctx);
	else {

		mb(); /* Order seg table write to TFC MMIO write */
		cxl_ops->ack_irq(ctx, CXL_PSL_TFC_An_R, 0);
	}

	return IRQ_HANDLED;
}

int cxl_handle_mm_fault(struct mm_struct *mm, u64 dsisr, u64 dar)
{
	vm_fault_t flt = 0;
	int result;
	unsigned long access, flags, inv_flags = 0;

	/*
	 * Add the fault handling cpu to task mm cpumask so that we
	 * can do a safe lockless page table walk when inserting the
	 * hash page table entry. This function get called with a
	 * valid mm for user space addresses. Hence using the if (mm)
	 * check is sufficient here.
	 */
	if (mm && !cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) {
		cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
		/*
		 * We need to make sure we walk the table only after
		 * we update the cpumask. The other side of the barrier
		 * is explained in serialize_against_pte_lookup()
		 */
		smp_mb();
	}
	if ((result = copro_handle_mm_fault(mm, dar, dsisr, &flt))) {
		pr_devel("copro_handle_mm_fault failed: %#x\n", result);
		return result;
	}

	if (!radix_enabled()) {
		/*
		 * update_mmu_cache() will not have loaded the hash since current->trap
		 * is not a 0x400 or 0x300, so just call hash_page_mm() here.
		 */
		access = _PAGE_PRESENT | _PAGE_READ;
		if (dsisr & CXL_PSL_DSISR_An_S)
			access |= _PAGE_WRITE;

		if (!mm && (get_region_id(dar) != USER_REGION_ID))
			access |= _PAGE_PRIVILEGED;

		if (dsisr & DSISR_NOHPTE)
			inv_flags |= HPTE_NOHPTE_UPDATE;

		local_irq_save(flags);
		hash_page_mm(mm, dar, access, 0x300, inv_flags);
		local_irq_restore(flags);
	}
	return 0;
}

static void cxl_handle_page_fault(struct cxl_context *ctx,
				  struct mm_struct *mm,
				  u64 dsisr, u64 dar)
{
	trace_cxl_pte_miss(ctx, dsisr, dar);

	if (cxl_handle_mm_fault(mm, dsisr, dar)) {
		cxl_ack_ae(ctx);
	} else {
		pr_devel("Page fault successfully handled for pe: %i!\n", ctx->pe);
		cxl_ops->ack_irq(ctx, CXL_PSL_TFC_An_R, 0);
	}
}

/*
 * Returns the mm_struct corresponding to the context ctx.
 * mm_users == 0, the context may be in the process of being closed.
 */
static struct mm_struct *get_mem_context(struct cxl_context *ctx)
{
	if (ctx->mm == NULL)
		return NULL;

	if (!mmget_not_zero(ctx->mm))
		return NULL;

	return ctx->mm;
}

static bool cxl_is_segment_miss(struct cxl_context *ctx, u64 dsisr)
{
	if ((cxl_is_power8() && (dsisr & CXL_PSL_DSISR_An_DS)))
		return true;

	return false;
}

static bool cxl_is_page_fault(struct cxl_context *ctx, u64 dsisr)
{
	if ((cxl_is_power8()) && (dsisr & CXL_PSL_DSISR_An_DM))
		return true;

	if (cxl_is_power9())
		return true;

	return false;
}

void cxl_handle_fault(struct work_struct *fault_work)
{
	struct cxl_context *ctx =
		container_of(fault_work, struct cxl_context, fault_work);
	u64 dsisr = ctx->dsisr;
	u64 dar = ctx->dar;
	struct mm_struct *mm = NULL;

	if (cpu_has_feature(CPU_FTR_HVMODE)) {
		if (cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An) != dsisr ||
		    cxl_p2n_read(ctx->afu, CXL_PSL_DAR_An) != dar ||
		    cxl_p2n_read(ctx->afu, CXL_PSL_PEHandle_An) != ctx->pe) {
			/* Most likely explanation is harmless - a dedicated
			 * process has detached and these were cleared by the
			 * PSL purge, but warn about it just in case
			 */
			dev_notice(&ctx->afu->dev, "cxl_handle_fault: Translation fault regs changed\n");
			return;
		}
	}

	/* Early return if the context is being / has been detached */
	if (ctx->status == CLOSED) {
		cxl_ack_ae(ctx);
		return;
	}

	pr_devel("CXL BOTTOM HALF handling fault for afu pe: %i. "
		"DSISR: %#llx DAR: %#llx\n", ctx->pe, dsisr, dar);

	if (!ctx->kernel) {

		mm = get_mem_context(ctx);
		if (mm == NULL) {
			pr_devel("%s: unable to get mm for pe=%d pid=%i\n",
				 __func__, ctx->pe, pid_nr(ctx->pid));
			cxl_ack_ae(ctx);
			return;
		} else {
			pr_devel("Handling page fault for pe=%d pid=%i\n",
				 ctx->pe, pid_nr(ctx->pid));
		}
	}

	if (cxl_is_segment_miss(ctx, dsisr))
		cxl_handle_segment_miss(ctx, mm, dar);
	else if (cxl_is_page_fault(ctx, dsisr))
		cxl_handle_page_fault(ctx, mm, dsisr, dar);
	else
		WARN(1, "cxl_handle_fault has nothing to handle\n");

	if (mm)
		mmput(mm);
}

static u64 next_segment(u64 ea, u64 vsid)
{
	if (vsid & SLB_VSID_B_1T)
		ea |= (1ULL << 40) - 1;
	else
		ea |= (1ULL << 28) - 1;

	return ea + 1;
}

static void cxl_prefault_vma(struct cxl_context *ctx, struct mm_struct *mm)
{
	u64 ea, last_esid = 0;
	struct copro_slb slb;
	VMA_ITERATOR(vmi, mm, 0);
	struct vm_area_struct *vma;
	int rc;

	mmap_read_lock(mm);
	for_each_vma(vmi, vma) {
		for (ea = vma->vm_start; ea < vma->vm_end;
				ea = next_segment(ea, slb.vsid)) {
			rc = copro_calculate_slb(mm, ea, &slb);
			if (rc)
				continue;

			if (last_esid == slb.esid)
				continue;

			cxl_load_segment(ctx, &slb);
			last_esid = slb.esid;
		}
	}
	mmap_read_unlock(mm);
}

void cxl_prefault(struct cxl_context *ctx, u64 wed)
{
	struct mm_struct *mm = get_mem_context(ctx);

	if (mm == NULL) {
		pr_devel("cxl_prefault unable to get mm %i\n",
			 pid_nr(ctx->pid));
		return;
	}

	switch (ctx->afu->prefault_mode) {
	case CXL_PREFAULT_WED:
		cxl_fault_segment(ctx, mm, wed);
		break;
	case CXL_PREFAULT_ALL:
		cxl_prefault_vma(ctx, mm);
		break;
	default:
		break;
	}

	mmput(mm);
}