aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/tlb_64.c
blob: e64a32c4882525f292bba91e2fb98160c1078931 (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
#include <linux/init.h>

#include <linux/mm.h>
#include <linux/delay.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/kernel_stat.h>
#include <linux/mc146818rtc.h>
#include <linux/interrupt.h>

#include <asm/mtrr.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/apicdef.h>
#include <asm/idle.h>
#include <asm/uv/uv_hub.h>
#include <asm/uv/uv_bau.h>

DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate)
			= { &init_mm, 0, };

#include <mach_ipi.h>
/*
 *	Smarter SMP flushing macros.
 *		c/o Linus Torvalds.
 *
 *	These mean you can really definitely utterly forget about
 *	writing to user space from interrupts. (Its not allowed anyway).
 *
 *	Optimizations Manfred Spraul <manfred@colorfullife.com>
 *
 *	More scalable flush, from Andi Kleen
 *
 *	To avoid global state use 8 different call vectors.
 *	Each CPU uses a specific vector to trigger flushes on other
 *	CPUs. Depending on the received vector the target CPUs look into
 *	the right per cpu variable for the flush data.
 *
 *	With more than 8 CPUs they are hashed to the 8 available
 *	vectors. The limited global vector space forces us to this right now.
 *	In future when interrupts are split into per CPU domains this could be
 *	fixed, at the cost of triggering multiple IPIs in some cases.
 */

union smp_flush_state {
	struct {
		struct mm_struct *flush_mm;
		unsigned long flush_va;
		spinlock_t tlbstate_lock;
		DECLARE_BITMAP(flush_cpumask, NR_CPUS);
	};
	char pad[SMP_CACHE_BYTES];
} ____cacheline_aligned;

/* State is put into the per CPU data section, but padded
   to a full cache line because other CPUs can access it and we don't
   want false sharing in the per cpu data segment. */
static DEFINE_PER_CPU(union smp_flush_state, flush_state);

/*
 * We cannot call mmdrop() because we are in interrupt context,
 * instead update mm->cpu_vm_mask.
 */
void leave_mm(int cpu)
{
	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
		BUG();
	cpu_clear(cpu, percpu_read(cpu_tlbstate.active_mm)->cpu_vm_mask);
	load_cr3(swapper_pg_dir);
}
EXPORT_SYMBOL_GPL(leave_mm);

/*
 *
 * The flush IPI assumes that a thread switch happens in this order:
 * [cpu0: the cpu that switches]
 * 1) switch_mm() either 1a) or 1b)
 * 1a) thread switch to a different mm
 * 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask);
 *	Stop ipi delivery for the old mm. This is not synchronized with
 *	the other cpus, but smp_invalidate_interrupt ignore flush ipis
 *	for the wrong mm, and in the worst case we perform a superfluous
 *	tlb flush.
 * 1a2) set cpu mmu_state to TLBSTATE_OK
 *	Now the smp_invalidate_interrupt won't call leave_mm if cpu0
 *	was in lazy tlb mode.
 * 1a3) update cpu active_mm
 *	Now cpu0 accepts tlb flushes for the new mm.
 * 1a4) cpu_set(cpu, new_mm->cpu_vm_mask);
 *	Now the other cpus will send tlb flush ipis.
 * 1a4) change cr3.
 * 1b) thread switch without mm change
 *	cpu active_mm is correct, cpu0 already handles
 *	flush ipis.
 * 1b1) set cpu mmu_state to TLBSTATE_OK
 * 1b2) test_and_set the cpu bit in cpu_vm_mask.
 *	Atomically set the bit [other cpus will start sending flush ipis],
 *	and test the bit.
 * 1b3) if the bit was 0: leave_mm was called, flush the tlb.
 * 2) switch %%esp, ie current
 *
 * The interrupt must handle 2 special cases:
 * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm.
 * - the cpu performs speculative tlb reads, i.e. even if the cpu only
 *   runs in kernel space, the cpu could load tlb entries for user space
 *   pages.
 *
 * The good news is that cpu mmu_state is local to each cpu, no
 * write/read ordering problems.
 */

/*
 * TLB flush IPI:
 *
 * 1) Flush the tlb entries if the cpu uses the mm that's being flushed.
 * 2) Leave the mm if we are in the lazy tlb mode.
 *
 * Interrupts are disabled.
 */

asmlinkage void smp_invalidate_interrupt(struct pt_regs *regs)
{
	int cpu;
	int sender;
	union smp_flush_state *f;

	cpu = smp_processor_id();
	/*
	 * orig_rax contains the negated interrupt vector.
	 * Use that to determine where the sender put the data.
	 */
	sender = ~regs->orig_ax - INVALIDATE_TLB_VECTOR_START;
	f = &per_cpu(flush_state, sender);

	if (!cpumask_test_cpu(cpu, to_cpumask(f->flush_cpumask)))
		goto out;
		/*
		 * This was a BUG() but until someone can quote me the
		 * line from the intel manual that guarantees an IPI to
		 * multiple CPUs is retried _only_ on the erroring CPUs
		 * its staying as a return
		 *
		 * BUG();
		 */

	if (f->flush_mm == percpu_read(cpu_tlbstate.active_mm)) {
		if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
			if (f->flush_va == TLB_FLUSH_ALL)
				local_flush_tlb();
			else
				__flush_tlb_one(f->flush_va);
		} else
			leave_mm(cpu);
	}
out:
	ack_APIC_irq();
	cpumask_clear_cpu(cpu, to_cpumask(f->flush_cpumask));
	inc_irq_stat(irq_tlb_count);
}

static void flush_tlb_others_ipi(const struct cpumask *cpumask,
				 struct mm_struct *mm, unsigned long va)
{
	int sender;
	union smp_flush_state *f;

	/* Caller has disabled preemption */
	sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS;
	f = &per_cpu(flush_state, sender);

	/*
	 * Could avoid this lock when
	 * num_online_cpus() <= NUM_INVALIDATE_TLB_VECTORS, but it is
	 * probably not worth checking this for a cache-hot lock.
	 */
	spin_lock(&f->tlbstate_lock);

	f->flush_mm = mm;
	f->flush_va = va;
	cpumask_andnot(to_cpumask(f->flush_cpumask),
		       cpumask, cpumask_of(smp_processor_id()));

	/*
	 * Make the above memory operations globally visible before
	 * sending the IPI.
	 */
	smp_mb();
	/*
	 * We have to send the IPI only to
	 * CPUs affected.
	 */
	send_IPI_mask(to_cpumask(f->flush_cpumask),
		      INVALIDATE_TLB_VECTOR_START + sender);

	while (!cpumask_empty(to_cpumask(f->flush_cpumask)))
		cpu_relax();

	f->flush_mm = NULL;
	f->flush_va = 0;
	spin_unlock(&f->tlbstate_lock);
}

void native_flush_tlb_others(const struct cpumask *cpumask,
			     struct mm_struct *mm, unsigned long va)
{
	if (is_uv_system()) {
		/* FIXME: could be an percpu_alloc'd thing */
		static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
		struct cpumask *after_uv_flush = &get_cpu_var(flush_tlb_mask);

		cpumask_andnot(after_uv_flush, cpumask,
			       cpumask_of(smp_processor_id()));
		if (!uv_flush_tlb_others(after_uv_flush, mm, va))
			flush_tlb_others_ipi(after_uv_flush, mm, va);

		put_cpu_var(flush_tlb_uv_cpumask);
		return;
	}
	flush_tlb_others_ipi(cpumask, mm, va);
}

static int __cpuinit init_smp_flush(void)
{
	int i;

	for_each_possible_cpu(i)
		spin_lock_init(&per_cpu(flush_state, i).tlbstate_lock);

	return 0;
}
core_initcall(init_smp_flush);

void flush_tlb_current_task(void)
{
	struct mm_struct *mm = current->mm;

	preempt_disable();

	local_flush_tlb();
	if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
		flush_tlb_others(&mm->cpu_vm_mask, mm, TLB_FLUSH_ALL);
	preempt_enable();
}

void flush_tlb_mm(struct mm_struct *mm)
{
	preempt_disable();

	if (current->active_mm == mm) {
		if (current->mm)
			local_flush_tlb();
		else
			leave_mm(smp_processor_id());
	}
	if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
		flush_tlb_others(&mm->cpu_vm_mask, mm, TLB_FLUSH_ALL);

	preempt_enable();
}

void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
{
	struct mm_struct *mm = vma->vm_mm;

	preempt_disable();

	if (current->active_mm == mm) {
		if (current->mm)
			__flush_tlb_one(va);
		else
			leave_mm(smp_processor_id());
	}

	if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
		flush_tlb_others(&mm->cpu_vm_mask, mm, va);

	preempt_enable();
}

static void do_flush_tlb_all(void *info)
{
	unsigned long cpu = smp_processor_id();

	__flush_tlb_all();
	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
		leave_mm(cpu);
}

void flush_tlb_all(void)
{
	on_each_cpu(do_flush_tlb_all, NULL, 1);
}