summaryrefslogtreecommitdiff
path: root/arch/x86/hyperv/mmu.c
blob: 56c9ebac946fe5a3778b992cb82a3a43ea32b0b8 (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
#define pr_fmt(fmt)  "Hyper-V: " fmt

#include <linux/hyperv.h>
#include <linux/log2.h>
#include <linux/slab.h>
#include <linux/types.h>

#include <asm/fpu/api.h>
#include <asm/mshyperv.h>
#include <asm/msr.h>
#include <asm/tlbflush.h>

#define CREATE_TRACE_POINTS
#include <asm/trace/hyperv.h>

/* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */
struct hv_flush_pcpu {
	u64 address_space;
	u64 flags;
	u64 processor_mask;
	u64 gva_list[];
};

/* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */
struct hv_flush_pcpu_ex {
	u64 address_space;
	u64 flags;
	struct {
		u64 format;
		u64 valid_bank_mask;
		u64 bank_contents[];
	} hv_vp_set;
	u64 gva_list[];
};

/* Each gva in gva_list encodes up to 4096 pages to flush */
#define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE)

static struct hv_flush_pcpu __percpu **pcpu_flush;

static struct hv_flush_pcpu_ex __percpu **pcpu_flush_ex;

/*
 * Fills in gva_list starting from offset. Returns the number of items added.
 */
static inline int fill_gva_list(u64 gva_list[], int offset,
				unsigned long start, unsigned long end)
{
	int gva_n = offset;
	unsigned long cur = start, diff;

	do {
		diff = end > cur ? end - cur : 0;

		gva_list[gva_n] = cur & PAGE_MASK;
		/*
		 * Lower 12 bits encode the number of additional
		 * pages to flush (in addition to the 'cur' page).
		 */
		if (diff >= HV_TLB_FLUSH_UNIT)
			gva_list[gva_n] |= ~PAGE_MASK;
		else if (diff)
			gva_list[gva_n] |= (diff - 1) >> PAGE_SHIFT;

		cur += HV_TLB_FLUSH_UNIT;
		gva_n++;

	} while (cur < end);

	return gva_n - offset;
}

/* Return the number of banks in the resulting vp_set */
static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush,
				    const struct cpumask *cpus)
{
	int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;

	/* valid_bank_mask can represent up to 64 banks */
	if (hv_max_vp_index / 64 >= 64)
		return 0;

	/*
	 * Clear all banks up to the maximum possible bank as hv_flush_pcpu_ex
	 * structs are not cleared between calls, we risk flushing unneeded
	 * vCPUs otherwise.
	 */
	for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++)
		flush->hv_vp_set.bank_contents[vcpu_bank] = 0;

	/*
	 * Some banks may end up being empty but this is acceptable.
	 */
	for_each_cpu(cpu, cpus) {
		vcpu = hv_cpu_number_to_vp_number(cpu);
		vcpu_bank = vcpu / 64;
		vcpu_offset = vcpu % 64;
		__set_bit(vcpu_offset, (unsigned long *)
			  &flush->hv_vp_set.bank_contents[vcpu_bank]);
		if (vcpu_bank >= nr_bank)
			nr_bank = vcpu_bank + 1;
	}
	flush->hv_vp_set.valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0);

	return nr_bank;
}

static void hyperv_flush_tlb_others(const struct cpumask *cpus,
				    const struct flush_tlb_info *info)
{
	int cpu, vcpu, gva_n, max_gvas;
	struct hv_flush_pcpu **flush_pcpu;
	struct hv_flush_pcpu *flush;
	u64 status = U64_MAX;
	unsigned long flags;

	trace_hyperv_mmu_flush_tlb_others(cpus, info);

	if (!pcpu_flush || !hv_hypercall_pg)
		goto do_native;

	if (cpumask_empty(cpus))
		return;

	local_irq_save(flags);

	flush_pcpu = this_cpu_ptr(pcpu_flush);

	if (unlikely(!*flush_pcpu))
		*flush_pcpu = page_address(alloc_page(GFP_ATOMIC));

	flush = *flush_pcpu;

	if (unlikely(!flush)) {
		local_irq_restore(flags);
		goto do_native;
	}

	if (info->mm) {
		/*
		 * AddressSpace argument must match the CR3 with PCID bits
		 * stripped out.
		 */
		flush->address_space = virt_to_phys(info->mm->pgd);
		flush->address_space &= CR3_ADDR_MASK;
		flush->flags = 0;
	} else {
		flush->address_space = 0;
		flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
	}

	flush->processor_mask = 0;
	if (cpumask_equal(cpus, cpu_present_mask)) {
		flush->flags |= HV_FLUSH_ALL_PROCESSORS;
	} else {
		for_each_cpu(cpu, cpus) {
			vcpu = hv_cpu_number_to_vp_number(cpu);
			if (vcpu >= 64)
				goto do_native;

			__set_bit(vcpu, (unsigned long *)
				  &flush->processor_mask);
		}
	}

	/*
	 * We can flush not more than max_gvas with one hypercall. Flush the
	 * whole address space if we were asked to do more.
	 */
	max_gvas = (PAGE_SIZE - sizeof(*flush)) / sizeof(flush->gva_list[0]);

	if (info->end == TLB_FLUSH_ALL) {
		flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY;
		status = hv_do_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE,
					 flush, NULL);
	} else if (info->end &&
		   ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) {
		status = hv_do_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE,
					 flush, NULL);
	} else {
		gva_n = fill_gva_list(flush->gva_list, 0,
				      info->start, info->end);
		status = hv_do_rep_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST,
					     gva_n, 0, flush, NULL);
	}

	local_irq_restore(flags);

	if (!(status & HV_HYPERCALL_RESULT_MASK))
		return;
do_native:
	native_flush_tlb_others(cpus, info);
}

static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
				       const struct flush_tlb_info *info)
{
	int nr_bank = 0, max_gvas, gva_n;
	struct hv_flush_pcpu_ex **flush_pcpu;
	struct hv_flush_pcpu_ex *flush;
	u64 status = U64_MAX;
	unsigned long flags;

	trace_hyperv_mmu_flush_tlb_others(cpus, info);

	if (!pcpu_flush_ex || !hv_hypercall_pg)
		goto do_native;

	if (cpumask_empty(cpus))
		return;

	local_irq_save(flags);

	flush_pcpu = this_cpu_ptr(pcpu_flush_ex);

	if (unlikely(!*flush_pcpu))
		*flush_pcpu = page_address(alloc_page(GFP_ATOMIC));

	flush = *flush_pcpu;

	if (unlikely(!flush)) {
		local_irq_restore(flags);
		goto do_native;
	}

	if (info->mm) {
		/*
		 * AddressSpace argument must match the CR3 with PCID bits
		 * stripped out.
		 */
		flush->address_space = virt_to_phys(info->mm->pgd);
		flush->address_space &= CR3_ADDR_MASK;
		flush->flags = 0;
	} else {
		flush->address_space = 0;
		flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
	}

	flush->hv_vp_set.valid_bank_mask = 0;

	if (!cpumask_equal(cpus, cpu_present_mask)) {
		flush->hv_vp_set.format = HV_GENERIC_SET_SPARCE_4K;
		nr_bank = cpumask_to_vp_set(flush, cpus);
	}

	if (!nr_bank) {
		flush->hv_vp_set.format = HV_GENERIC_SET_ALL;
		flush->flags |= HV_FLUSH_ALL_PROCESSORS;
	}

	/*
	 * We can flush not more than max_gvas with one hypercall. Flush the
	 * whole address space if we were asked to do more.
	 */
	max_gvas =
		(PAGE_SIZE - sizeof(*flush) - nr_bank *
		 sizeof(flush->hv_vp_set.bank_contents[0])) /
		sizeof(flush->gva_list[0]);

	if (info->end == TLB_FLUSH_ALL) {
		flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY;
		status = hv_do_rep_hypercall(
			HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX,
			0, nr_bank, flush, NULL);
	} else if (info->end &&
		   ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) {
		status = hv_do_rep_hypercall(
			HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX,
			0, nr_bank, flush, NULL);
	} else {
		gva_n = fill_gva_list(flush->gva_list, nr_bank,
				      info->start, info->end);
		status = hv_do_rep_hypercall(
			HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX,
			gva_n, nr_bank, flush, NULL);
	}

	local_irq_restore(flags);

	if (!(status & HV_HYPERCALL_RESULT_MASK))
		return;
do_native:
	native_flush_tlb_others(cpus, info);
}

void hyperv_setup_mmu_ops(void)
{
	if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED))
		return;

	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) {
		pr_info("Using hypercall for remote TLB flush\n");
		pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
	} else {
		pr_info("Using ext hypercall for remote TLB flush\n");
		pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others_ex;
	}
}

void hyper_alloc_mmu(void)
{
	if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED))
		return;

	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
		pcpu_flush = alloc_percpu(struct hv_flush_pcpu *);
	else
		pcpu_flush_ex = alloc_percpu(struct hv_flush_pcpu_ex *);
}