summaryrefslogtreecommitdiff
path: root/arch/riscv/mm/cacheflush.c
blob: 55a34f2020a85a895932c92d94a7577bf410f8dc (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2017 SiFive
 */

#include <linux/acpi.h>
#include <linux/of.h>
#include <asm/acpi.h>
#include <asm/cacheflush.h>

#ifdef CONFIG_SMP

#include <asm/sbi.h>

static void ipi_remote_fence_i(void *info)
{
	return local_flush_icache_all();
}

void flush_icache_all(void)
{
	local_flush_icache_all();

	if (IS_ENABLED(CONFIG_RISCV_SBI) && !riscv_use_ipi_for_rfence())
		sbi_remote_fence_i(NULL);
	else
		on_each_cpu(ipi_remote_fence_i, NULL, 1);
}
EXPORT_SYMBOL(flush_icache_all);

/*
 * Performs an icache flush for the given MM context.  RISC-V has no direct
 * mechanism for instruction cache shoot downs, so instead we send an IPI that
 * informs the remote harts they need to flush their local instruction caches.
 * To avoid pathologically slow behavior in a common case (a bunch of
 * single-hart processes on a many-hart machine, ie 'make -j') we avoid the
 * IPIs for harts that are not currently executing a MM context and instead
 * schedule a deferred local instruction cache flush to be performed before
 * execution resumes on each hart.
 */
void flush_icache_mm(struct mm_struct *mm, bool local)
{
	unsigned int cpu;
	cpumask_t others, *mask;

	preempt_disable();

	/* Mark every hart's icache as needing a flush for this MM. */
	mask = &mm->context.icache_stale_mask;
	cpumask_setall(mask);
	/* Flush this hart's I$ now, and mark it as flushed. */
	cpu = smp_processor_id();
	cpumask_clear_cpu(cpu, mask);
	local_flush_icache_all();

	/*
	 * Flush the I$ of other harts concurrently executing, and mark them as
	 * flushed.
	 */
	cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu));
	local |= cpumask_empty(&others);
	if (mm == current->active_mm && local) {
		/*
		 * It's assumed that at least one strongly ordered operation is
		 * performed on this hart between setting a hart's cpumask bit
		 * and scheduling this MM context on that hart.  Sending an SBI
		 * remote message will do this, but in the case where no
		 * messages are sent we still need to order this hart's writes
		 * with flush_icache_deferred().
		 */
		smp_mb();
	} else if (IS_ENABLED(CONFIG_RISCV_SBI) &&
		   !riscv_use_ipi_for_rfence()) {
		sbi_remote_fence_i(&others);
	} else {
		on_each_cpu_mask(&others, ipi_remote_fence_i, NULL, 1);
	}

	preempt_enable();
}

#endif /* CONFIG_SMP */

#ifdef CONFIG_MMU
void flush_icache_pte(pte_t pte)
{
	struct folio *folio = page_folio(pte_page(pte));

	if (!test_bit(PG_dcache_clean, &folio->flags)) {
		flush_icache_all();
		set_bit(PG_dcache_clean, &folio->flags);
	}
}
#endif /* CONFIG_MMU */

unsigned int riscv_cbom_block_size;
EXPORT_SYMBOL_GPL(riscv_cbom_block_size);

unsigned int riscv_cboz_block_size;
EXPORT_SYMBOL_GPL(riscv_cboz_block_size);

static void __init cbo_get_block_size(struct device_node *node,
				      const char *name, u32 *block_size,
				      unsigned long *first_hartid)
{
	unsigned long hartid;
	u32 val;

	if (riscv_of_processor_hartid(node, &hartid))
		return;

	if (of_property_read_u32(node, name, &val))
		return;

	if (!*block_size) {
		*block_size = val;
		*first_hartid = hartid;
	} else if (*block_size != val) {
		pr_warn("%s mismatched between harts %lu and %lu\n",
			name, *first_hartid, hartid);
	}
}

void __init riscv_init_cbo_blocksizes(void)
{
	unsigned long cbom_hartid, cboz_hartid;
	u32 cbom_block_size = 0, cboz_block_size = 0;
	struct device_node *node;
	struct acpi_table_header *rhct;
	acpi_status status;

	if (acpi_disabled) {
		for_each_of_cpu_node(node) {
			/* set block-size for cbom and/or cboz extension if available */
			cbo_get_block_size(node, "riscv,cbom-block-size",
					   &cbom_block_size, &cbom_hartid);
			cbo_get_block_size(node, "riscv,cboz-block-size",
					   &cboz_block_size, &cboz_hartid);
		}
	} else {
		status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct);
		if (ACPI_FAILURE(status))
			return;

		acpi_get_cbo_block_size(rhct, &cbom_block_size, &cboz_block_size, NULL);
		acpi_put_table((struct acpi_table_header *)rhct);
	}

	if (cbom_block_size)
		riscv_cbom_block_size = cbom_block_size;

	if (cboz_block_size)
		riscv_cboz_block_size = cboz_block_size;
}