summaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm/mmu_context.h
blob: 84280029cafd73a83e64efd3133a8f9d9575bcb3 (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
342
343
344
345
346
347
348
349
350
351
352
353
#ifndef _ASM_X86_MMU_CONTEXT_H
#define _ASM_X86_MMU_CONTEXT_H

#include <asm/desc.h>
#include <linux/atomic.h>
#include <linux/mm_types.h>

#include <trace/events/tlb.h>

#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/paravirt.h>
#include <asm/mpx.h>
#ifndef CONFIG_PARAVIRT
static inline void paravirt_activate_mm(struct mm_struct *prev,
					struct mm_struct *next)
{
}
#endif	/* !CONFIG_PARAVIRT */

#ifdef CONFIG_PERF_EVENTS
extern struct static_key rdpmc_always_available;

static inline void load_mm_cr4(struct mm_struct *mm)
{
	if (static_key_false(&rdpmc_always_available) ||
	    atomic_read(&mm->context.perf_rdpmc_allowed))
		cr4_set_bits(X86_CR4_PCE);
	else
		cr4_clear_bits(X86_CR4_PCE);
}
#else
static inline void load_mm_cr4(struct mm_struct *mm) {}
#endif

#ifdef CONFIG_MODIFY_LDT_SYSCALL
/*
 * ldt_structs can be allocated, used, and freed, but they are never
 * modified while live.
 */
struct ldt_struct {
	/*
	 * Xen requires page-aligned LDTs with special permissions.  This is
	 * needed to prevent us from installing evil descriptors such as
	 * call gates.  On native, we could merge the ldt_struct and LDT
	 * allocations, but it's not worth trying to optimize.
	 */
	struct desc_struct *entries;
	int size;
};

/*
 * Used for LDT copy/destruction.
 */
int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm);
void destroy_context_ldt(struct mm_struct *mm);
#else	/* CONFIG_MODIFY_LDT_SYSCALL */
static inline int init_new_context_ldt(struct task_struct *tsk,
				       struct mm_struct *mm)
{
	return 0;
}
static inline void destroy_context_ldt(struct mm_struct *mm) {}
#endif

static inline void load_mm_ldt(struct mm_struct *mm)
{
#ifdef CONFIG_MODIFY_LDT_SYSCALL
	struct ldt_struct *ldt;

	/* lockless_dereference synchronizes with smp_store_release */
	ldt = lockless_dereference(mm->context.ldt);

	/*
	 * Any change to mm->context.ldt is followed by an IPI to all
	 * CPUs with the mm active.  The LDT will not be freed until
	 * after the IPI is handled by all such CPUs.  This means that,
	 * if the ldt_struct changes before we return, the values we see
	 * will be safe, and the new values will be loaded before we run
	 * any user code.
	 *
	 * NB: don't try to convert this to use RCU without extreme care.
	 * We would still need IRQs off, because we don't want to change
	 * the local LDT after an IPI loaded a newer value than the one
	 * that we can see.
	 */

	if (unlikely(ldt))
		set_ldt(ldt->entries, ldt->size);
	else
		clear_LDT();
#else
	clear_LDT();
#endif

	DEBUG_LOCKS_WARN_ON(preemptible());
}

static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
#ifdef CONFIG_SMP
	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
		this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
#endif
}

static inline int init_new_context(struct task_struct *tsk,
				   struct mm_struct *mm)
{
	init_new_context_ldt(tsk, mm);
	return 0;
}
static inline void destroy_context(struct mm_struct *mm)
{
	destroy_context_ldt(mm);
}

static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
			     struct task_struct *tsk)
{
	unsigned cpu = smp_processor_id();

	if (likely(prev != next)) {
#ifdef CONFIG_SMP
		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
		this_cpu_write(cpu_tlbstate.active_mm, next);
#endif
		cpumask_set_cpu(cpu, mm_cpumask(next));

		/*
		 * Re-load page tables.
		 *
		 * This logic has an ordering constraint:
		 *
		 *  CPU 0: Write to a PTE for 'next'
		 *  CPU 0: load bit 1 in mm_cpumask.  if nonzero, send IPI.
		 *  CPU 1: set bit 1 in next's mm_cpumask
		 *  CPU 1: load from the PTE that CPU 0 writes (implicit)
		 *
		 * We need to prevent an outcome in which CPU 1 observes
		 * the new PTE value and CPU 0 observes bit 1 clear in
		 * mm_cpumask.  (If that occurs, then the IPI will never
		 * be sent, and CPU 0's TLB will contain a stale entry.)
		 *
		 * The bad outcome can occur if either CPU's load is
		 * reordered before that CPU's store, so both CPUs must
		 * execute full barriers to prevent this from happening.
		 *
		 * Thus, switch_mm needs a full barrier between the
		 * store to mm_cpumask and any operation that could load
		 * from next->pgd.  TLB fills are special and can happen
		 * due to instruction fetches or for no reason at all,
		 * and neither LOCK nor MFENCE orders them.
		 * Fortunately, load_cr3() is serializing and gives the
		 * ordering guarantee we need.
		 *
		 */
		load_cr3(next->pgd);

		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);

		/* Stop flush ipis for the previous mm */
		cpumask_clear_cpu(cpu, mm_cpumask(prev));

		/* Load per-mm CR4 state */
		load_mm_cr4(next);

#ifdef CONFIG_MODIFY_LDT_SYSCALL
		/*
		 * Load the LDT, if the LDT is different.
		 *
		 * It's possible that prev->context.ldt doesn't match
		 * the LDT register.  This can happen if leave_mm(prev)
		 * was called and then modify_ldt changed
		 * prev->context.ldt but suppressed an IPI to this CPU.
		 * In this case, prev->context.ldt != NULL, because we
		 * never set context.ldt to NULL while the mm still
		 * exists.  That means that next->context.ldt !=
		 * prev->context.ldt, because mms never share an LDT.
		 */
		if (unlikely(prev->context.ldt != next->context.ldt))
			load_mm_ldt(next);
#endif
	}
#ifdef CONFIG_SMP
	  else {
		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);

		if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
			/*
			 * On established mms, the mm_cpumask is only changed
			 * from irq context, from ptep_clear_flush() while in
			 * lazy tlb mode, and here. Irqs are blocked during
			 * schedule, protecting us from simultaneous changes.
			 */
			cpumask_set_cpu(cpu, mm_cpumask(next));

			/*
			 * We were in lazy tlb mode and leave_mm disabled
			 * tlb flush IPI delivery. We must reload CR3
			 * to make sure to use no freed page tables.
			 *
			 * As above, load_cr3() is serializing and orders TLB
			 * fills with respect to the mm_cpumask write.
			 */
			load_cr3(next->pgd);
			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
			load_mm_cr4(next);
			load_mm_ldt(next);
		}
	}
#endif
}

#define activate_mm(prev, next)			\
do {						\
	paravirt_activate_mm((prev), (next));	\
	switch_mm((prev), (next), NULL);	\
} while (0);

#ifdef CONFIG_X86_32
#define deactivate_mm(tsk, mm)			\
do {						\
	lazy_load_gs(0);			\
} while (0)
#else
#define deactivate_mm(tsk, mm)			\
do {						\
	load_gs_index(0);			\
	loadsegment(fs, 0);			\
} while (0)
#endif

static inline void arch_dup_mmap(struct mm_struct *oldmm,
				 struct mm_struct *mm)
{
	paravirt_arch_dup_mmap(oldmm, mm);
}

static inline void arch_exit_mmap(struct mm_struct *mm)
{
	paravirt_arch_exit_mmap(mm);
}

#ifdef CONFIG_X86_64
static inline bool is_64bit_mm(struct mm_struct *mm)
{
	return	!config_enabled(CONFIG_IA32_EMULATION) ||
		!(mm->context.ia32_compat == TIF_IA32);
}
#else
static inline bool is_64bit_mm(struct mm_struct *mm)
{
	return false;
}
#endif

static inline void arch_bprm_mm_init(struct mm_struct *mm,
		struct vm_area_struct *vma)
{
	mpx_mm_init(mm);
}

static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
			      unsigned long start, unsigned long end)
{
	/*
	 * mpx_notify_unmap() goes and reads a rarely-hot
	 * cacheline in the mm_struct.  That can be expensive
	 * enough to be seen in profiles.
	 *
	 * The mpx_notify_unmap() call and its contents have been
	 * observed to affect munmap() performance on hardware
	 * where MPX is not present.
	 *
	 * The unlikely() optimizes for the fast case: no MPX
	 * in the CPU, or no MPX use in the process.  Even if
	 * we get this wrong (in the unlikely event that MPX
	 * is widely enabled on some system) the overhead of
	 * MPX itself (reading bounds tables) is expected to
	 * overwhelm the overhead of getting this unlikely()
	 * consistently wrong.
	 */
	if (unlikely(cpu_feature_enabled(X86_FEATURE_MPX)))
		mpx_notify_unmap(mm, vma, start, end);
}

static inline int vma_pkey(struct vm_area_struct *vma)
{
	u16 pkey = 0;
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
	unsigned long vma_pkey_mask = VM_PKEY_BIT0 | VM_PKEY_BIT1 |
				      VM_PKEY_BIT2 | VM_PKEY_BIT3;
	pkey = (vma->vm_flags & vma_pkey_mask) >> VM_PKEY_SHIFT;
#endif
	return pkey;
}

static inline bool __pkru_allows_pkey(u16 pkey, bool write)
{
	u32 pkru = read_pkru();

	if (!__pkru_allows_read(pkru, pkey))
		return false;
	if (write && !__pkru_allows_write(pkru, pkey))
		return false;

	return true;
}

/*
 * We only want to enforce protection keys on the current process
 * because we effectively have no access to PKRU for other
 * processes or any way to tell *which * PKRU in a threaded
 * process we could use.
 *
 * So do not enforce things if the VMA is not from the current
 * mm, or if we are in a kernel thread.
 */
static inline bool vma_is_foreign(struct vm_area_struct *vma)
{
	if (!current->mm)
		return true;
	/*
	 * Should PKRU be enforced on the access to this VMA?  If
	 * the VMA is from another process, then PKRU has no
	 * relevance and should not be enforced.
	 */
	if (current->mm != vma->vm_mm)
		return true;

	return false;
}

static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
		bool write, bool execute, bool foreign)
{
	/* pkeys never affect instruction fetches */
	if (execute)
		return true;
	/* allow access if the VMA is not one from this process */
	if (foreign || vma_is_foreign(vma))
		return true;
	return __pkru_allows_pkey(vma_pkey(vma), write);
}

static inline bool arch_pte_access_permitted(pte_t pte, bool write)
{
	return __pkru_allows_pkey(pte_flags_pkey(pte_flags(pte)), write);
}

#endif /* _ASM_X86_MMU_CONTEXT_H */
OpenPOWER on IntegriCloud