summaryrefslogtreecommitdiffstats
path: root/arch/riscv/mm/tlbflush.c
blob: 893566e004b73fcf9a8dbc94f766e59cd00f1bb1 (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
// SPDX-License-Identifier: GPL-2.0

#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/sched.h>
#include <linux/hugetlb.h>
#include <asm/sbi.h>
#include <asm/mmu_context.h>

static inline void local_flush_tlb_all_asid(unsigned long asid)
{
	if (asid != FLUSH_TLB_NO_ASID)
		__asm__ __volatile__ ("sfence.vma x0, %0"
				:
				: "r" (asid)
				: "memory");
	else
		local_flush_tlb_all();
}

static inline void local_flush_tlb_page_asid(unsigned long addr,
		unsigned long asid)
{
	if (asid != FLUSH_TLB_NO_ASID)
		__asm__ __volatile__ ("sfence.vma %0, %1"
				:
				: "r" (addr), "r" (asid)
				: "memory");
	else
		local_flush_tlb_page(addr);
}

/*
 * Flush entire TLB if number of entries to be flushed is greater
 * than the threshold below.
 */
static unsigned long tlb_flush_all_threshold __read_mostly = 64;

static void local_flush_tlb_range_threshold_asid(unsigned long start,
						 unsigned long size,
						 unsigned long stride,
						 unsigned long asid)
{
	unsigned long nr_ptes_in_range = DIV_ROUND_UP(size, stride);
	int i;

	if (nr_ptes_in_range > tlb_flush_all_threshold) {
		local_flush_tlb_all_asid(asid);
		return;
	}

	for (i = 0; i < nr_ptes_in_range; ++i) {
		local_flush_tlb_page_asid(start, asid);
		start += stride;
	}
}

static inline void local_flush_tlb_range_asid(unsigned long start,
		unsigned long size, unsigned long stride, unsigned long asid)
{
	if (size <= stride)
		local_flush_tlb_page_asid(start, asid);
	else if (size == FLUSH_TLB_MAX_SIZE)
		local_flush_tlb_all_asid(asid);
	else
		local_flush_tlb_range_threshold_asid(start, size, stride, asid);
}

/* Flush a range of kernel pages without broadcasting */
void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
	local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID);
}

static void __ipi_flush_tlb_all(void *info)
{
	local_flush_tlb_all();
}

void flush_tlb_all(void)
{
	if (riscv_use_ipi_for_rfence())
		on_each_cpu(__ipi_flush_tlb_all, NULL, 1);
	else
		sbi_remote_sfence_vma_asid(NULL, 0, FLUSH_TLB_MAX_SIZE, FLUSH_TLB_NO_ASID);
}

struct flush_tlb_range_data {
	unsigned long asid;
	unsigned long start;
	unsigned long size;
	unsigned long stride;
};

static void __ipi_flush_tlb_range_asid(void *info)
{
	struct flush_tlb_range_data *d = info;

	local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
}

static void __flush_tlb_range(struct cpumask *cmask, unsigned long asid,
			      unsigned long start, unsigned long size,
			      unsigned long stride)
{
	struct flush_tlb_range_data ftd;
	bool broadcast;

	if (cpumask_empty(cmask))
		return;

	if (cmask != cpu_online_mask) {
		unsigned int cpuid;

		cpuid = get_cpu();
		/* check if the tlbflush needs to be sent to other CPUs */
		broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
	} else {
		broadcast = true;
	}

	if (broadcast) {
		if (riscv_use_ipi_for_rfence()) {
			ftd.asid = asid;
			ftd.start = start;
			ftd.size = size;
			ftd.stride = stride;
			on_each_cpu_mask(cmask,
					 __ipi_flush_tlb_range_asid,
					 &ftd, 1);
		} else
			sbi_remote_sfence_vma_asid(cmask,
						   start, size, asid);
	} else {
		local_flush_tlb_range_asid(start, size, stride, asid);
	}

	if (cmask != cpu_online_mask)
		put_cpu();
}

static inline unsigned long get_mm_asid(struct mm_struct *mm)
{
	return static_branch_unlikely(&use_asid_allocator) ?
			atomic_long_read(&mm->context.id) & asid_mask : FLUSH_TLB_NO_ASID;
}

void flush_tlb_mm(struct mm_struct *mm)
{
	__flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm),
			  0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
}

void flush_tlb_mm_range(struct mm_struct *mm,
			unsigned long start, unsigned long end,
			unsigned int page_size)
{
	__flush_tlb_range(mm_cpumask(mm), get_mm_asid(mm),
			  start, end - start, page_size);
}

void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
{
	__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
			  addr, PAGE_SIZE, PAGE_SIZE);
}

void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
		     unsigned long end)
{
	unsigned long stride_size;

	if (!is_vm_hugetlb_page(vma)) {
		stride_size = PAGE_SIZE;
	} else {
		stride_size = huge_page_size(hstate_vma(vma));

		/*
		 * As stated in the privileged specification, every PTE in a
		 * NAPOT region must be invalidated, so reset the stride in that
		 * case.
		 */
		if (has_svnapot()) {
			if (stride_size >= PGDIR_SIZE)
				stride_size = PGDIR_SIZE;
			else if (stride_size >= P4D_SIZE)
				stride_size = P4D_SIZE;
			else if (stride_size >= PUD_SIZE)
				stride_size = PUD_SIZE;
			else if (stride_size >= PMD_SIZE)
				stride_size = PMD_SIZE;
			else
				stride_size = PAGE_SIZE;
		}
	}

	__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
			  start, end - start, stride_size);
}

void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
	__flush_tlb_range((struct cpumask *)cpu_online_mask, FLUSH_TLB_NO_ASID,
			  start, end - start, PAGE_SIZE);
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
			unsigned long end)
{
	__flush_tlb_range(mm_cpumask(vma->vm_mm), get_mm_asid(vma->vm_mm),
			  start, end - start, PMD_SIZE);
}
#endif

bool arch_tlbbatch_should_defer(struct mm_struct *mm)
{
	return true;
}

void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
			       struct mm_struct *mm,
			       unsigned long uaddr)
{
	cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
}

void arch_flush_tlb_batched_pending(struct mm_struct *mm)
{
	flush_tlb_mm(mm);
}

void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
{
	__flush_tlb_range(&batch->cpumask, FLUSH_TLB_NO_ASID, 0,
			  FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
	cpumask_clear(&batch->cpumask);
}