summaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm/segment.h
blob: 9646c300f128154297a5a9df5cc28ee475e60722 (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
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_X86_SEGMENT_H
#define _ASM_X86_SEGMENT_H

#include <linux/const.h>
#include <asm/alternative.h>

/*
 * Constructor for a conventional segment GDT (or LDT) entry.
 * This is a macro so it can be used in initializers.
 */
#define GDT_ENTRY(flags, base, limit)			\
	((((base)  & _AC(0xff000000,ULL)) << (56-24)) |	\
	 (((flags) & _AC(0x0000f0ff,ULL)) << 40) |	\
	 (((limit) & _AC(0x000f0000,ULL)) << (48-16)) |	\
	 (((base)  & _AC(0x00ffffff,ULL)) << 16) |	\
	 (((limit) & _AC(0x0000ffff,ULL))))

/* Simple and small GDT entries for booting only: */

#define GDT_ENTRY_BOOT_CS	2
#define GDT_ENTRY_BOOT_DS	3
#define GDT_ENTRY_BOOT_TSS	4
#define __BOOT_CS		(GDT_ENTRY_BOOT_CS*8)
#define __BOOT_DS		(GDT_ENTRY_BOOT_DS*8)
#define __BOOT_TSS		(GDT_ENTRY_BOOT_TSS*8)

/*
 * Bottom two bits of selector give the ring
 * privilege level
 */
#define SEGMENT_RPL_MASK	0x3

/*
 * When running on Xen PV, the actual privilege level of the kernel is 1,
 * not 0. Testing the Requested Privilege Level in a segment selector to
 * determine whether the context is user mode or kernel mode with
 * SEGMENT_RPL_MASK is wrong because the PV kernel's privilege level
 * matches the 0x3 mask.
 *
 * Testing with USER_SEGMENT_RPL_MASK is valid for both native and Xen PV
 * kernels because privilege level 2 is never used.
 */
#define USER_SEGMENT_RPL_MASK	0x2

/* User mode is privilege level 3: */
#define USER_RPL		0x3

/* Bit 2 is Table Indicator (TI): selects between LDT or GDT */
#define SEGMENT_TI_MASK		0x4
/* LDT segment has TI set ... */
#define SEGMENT_LDT		0x4
/* ... GDT has it cleared */
#define SEGMENT_GDT		0x0

#define GDT_ENTRY_INVALID_SEG	0

#ifdef CONFIG_X86_32
/*
 * The layout of the per-CPU GDT under Linux:
 *
 *   0 - null								<=== cacheline #1
 *   1 - reserved
 *   2 - reserved
 *   3 - reserved
 *
 *   4 - unused								<=== cacheline #2
 *   5 - unused
 *
 *  ------- start of TLS (Thread-Local Storage) segments:
 *
 *   6 - TLS segment #1			[ glibc's TLS segment ]
 *   7 - TLS segment #2			[ Wine's %fs Win32 segment ]
 *   8 - TLS segment #3							<=== cacheline #3
 *   9 - reserved
 *  10 - reserved
 *  11 - reserved
 *
 *  ------- start of kernel segments:
 *
 *  12 - kernel code segment						<=== cacheline #4
 *  13 - kernel data segment
 *  14 - default user CS
 *  15 - default user DS
 *  16 - TSS								<=== cacheline #5
 *  17 - LDT
 *  18 - PNPBIOS support (16->32 gate)
 *  19 - PNPBIOS support
 *  20 - PNPBIOS support						<=== cacheline #6
 *  21 - PNPBIOS support
 *  22 - PNPBIOS support
 *  23 - APM BIOS support
 *  24 - APM BIOS support						<=== cacheline #7
 *  25 - APM BIOS support
 *
 *  26 - ESPFIX small SS
 *  27 - per-cpu			[ offset to per-cpu data area ]
 *  28 - stack_canary-20		[ for stack protector ]		<=== cacheline #8
 *  29 - unused
 *  30 - unused
 *  31 - TSS for double fault handler
 */
#define GDT_ENTRY_TLS_MIN		6
#define GDT_ENTRY_TLS_MAX 		(GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1)

#define GDT_ENTRY_KERNEL_CS		12
#define GDT_ENTRY_KERNEL_DS		13
#define GDT_ENTRY_DEFAULT_USER_CS	14
#define GDT_ENTRY_DEFAULT_USER_DS	15
#define GDT_ENTRY_TSS			16
#define GDT_ENTRY_LDT			17
#define GDT_ENTRY_PNPBIOS_CS32		18
#define GDT_ENTRY_PNPBIOS_CS16		19
#define GDT_ENTRY_PNPBIOS_DS		20
#define GDT_ENTRY_PNPBIOS_TS1		21
#define GDT_ENTRY_PNPBIOS_TS2		22
#define GDT_ENTRY_APMBIOS_BASE		23

#define GDT_ENTRY_ESPFIX_SS		26
#define GDT_ENTRY_PERCPU		27
#define GDT_ENTRY_STACK_CANARY		28

#define GDT_ENTRY_DOUBLEFAULT_TSS	31

/*
 * Number of entries in the GDT table:
 */
#define GDT_ENTRIES			32

/*
 * Segment selector values corresponding to the above entries:
 */

#define __KERNEL_CS			(GDT_ENTRY_KERNEL_CS*8)
#define __KERNEL_DS			(GDT_ENTRY_KERNEL_DS*8)
#define __USER_DS			(GDT_ENTRY_DEFAULT_USER_DS*8 + 3)
#define __USER_CS			(GDT_ENTRY_DEFAULT_USER_CS*8 + 3)
#define __ESPFIX_SS			(GDT_ENTRY_ESPFIX_SS*8)

/* segment for calling fn: */
#define PNP_CS32			(GDT_ENTRY_PNPBIOS_CS32*8)
/* code segment for BIOS: */
#define PNP_CS16			(GDT_ENTRY_PNPBIOS_CS16*8)

/* "Is this PNP code selector (PNP_CS32 or PNP_CS16)?" */
#define SEGMENT_IS_PNP_CODE(x)		(((x) & 0xf4) == PNP_CS32)

/* data segment for BIOS: */
#define PNP_DS				(GDT_ENTRY_PNPBIOS_DS*8)
/* transfer data segment: */
#define PNP_TS1				(GDT_ENTRY_PNPBIOS_TS1*8)
/* another data segment: */
#define PNP_TS2				(GDT_ENTRY_PNPBIOS_TS2*8)

#ifdef CONFIG_SMP
# define __KERNEL_PERCPU		(GDT_ENTRY_PERCPU*8)
#else
# define __KERNEL_PERCPU		0
#endif

#ifdef CONFIG_STACKPROTECTOR
# define __KERNEL_STACK_CANARY		(GDT_ENTRY_STACK_CANARY*8)
#else
# define __KERNEL_STACK_CANARY		0
#endif

#else /* 64-bit: */

#include <asm/cache.h>

#define GDT_ENTRY_KERNEL32_CS		1
#define GDT_ENTRY_KERNEL_CS		2
#define GDT_ENTRY_KERNEL_DS		3

/*
 * We cannot use the same code segment descriptor for user and kernel mode,
 * not even in long flat mode, because of different DPL.
 *
 * GDT layout to get 64-bit SYSCALL/SYSRET support right. SYSRET hardcodes
 * selectors:
 *
 *   if returning to 32-bit userspace: cs = STAR.SYSRET_CS,
 *   if returning to 64-bit userspace: cs = STAR.SYSRET_CS+16,
 *
 * ss = STAR.SYSRET_CS+8 (in either case)
 *
 * thus USER_DS should be between 32-bit and 64-bit code selectors:
 */
#define GDT_ENTRY_DEFAULT_USER32_CS	4
#define GDT_ENTRY_DEFAULT_USER_DS	5
#define GDT_ENTRY_DEFAULT_USER_CS	6

/* Needs two entries */
#define GDT_ENTRY_TSS			8
/* Needs two entries */
#define GDT_ENTRY_LDT			10

#define GDT_ENTRY_TLS_MIN		12
#define GDT_ENTRY_TLS_MAX		14

#define GDT_ENTRY_CPUNODE		15

/*
 * Number of entries in the GDT table:
 */
#define GDT_ENTRIES			16

/*
 * Segment selector values corresponding to the above entries:
 *
 * Note, selectors also need to have a correct RPL,
 * expressed with the +3 value for user-space selectors:
 */
#define __KERNEL32_CS			(GDT_ENTRY_KERNEL32_CS*8)
#define __KERNEL_CS			(GDT_ENTRY_KERNEL_CS*8)
#define __KERNEL_DS			(GDT_ENTRY_KERNEL_DS*8)
#define __USER32_CS			(GDT_ENTRY_DEFAULT_USER32_CS*8 + 3)
#define __USER_DS			(GDT_ENTRY_DEFAULT_USER_DS*8 + 3)
#define __USER32_DS			__USER_DS
#define __USER_CS			(GDT_ENTRY_DEFAULT_USER_CS*8 + 3)
#define __CPUNODE_SEG			(GDT_ENTRY_CPUNODE*8 + 3)

#endif

#ifndef CONFIG_PARAVIRT_XXL
# define get_kernel_rpl()		0
#endif

#define IDT_ENTRIES			256
#define NUM_EXCEPTION_VECTORS		32

/* Bitmask of exception vectors which push an error code on the stack: */
#define EXCEPTION_ERRCODE_MASK		0x00027d00

#define GDT_SIZE			(GDT_ENTRIES*8)
#define GDT_ENTRY_TLS_ENTRIES		3
#define TLS_SIZE			(GDT_ENTRY_TLS_ENTRIES* 8)

#ifdef CONFIG_X86_64

/* Bit size and mask of CPU number stored in the per CPU data (and TSC_AUX) */
#define VDSO_CPUNODE_BITS		12
#define VDSO_CPUNODE_MASK		0xfff

#ifndef __ASSEMBLY__

/* Helper functions to store/load CPU and node numbers */

static inline unsigned long vdso_encode_cpunode(int cpu, unsigned long node)
{
	return (node << VDSO_CPUNODE_BITS) | cpu;
}

static inline void vdso_read_cpunode(unsigned *cpu, unsigned *node)
{
	unsigned int p;

	/*
	 * Load CPU and node number from the GDT.  LSL is faster than RDTSCP
	 * and works on all CPUs.  This is volatile so that it orders
	 * correctly with respect to barrier() and to keep GCC from cleverly
	 * hoisting it out of the calling function.
	 *
	 * If RDPID is available, use it.
	 */
	alternative_io ("lsl %[seg],%[p]",
			".byte 0xf3,0x0f,0xc7,0xf8", /* RDPID %eax/rax */
			X86_FEATURE_RDPID,
			[p] "=a" (p), [seg] "r" (__CPUNODE_SEG));

	if (cpu)
		*cpu = (p & VDSO_CPUNODE_MASK);
	if (node)
		*node = (p >> VDSO_CPUNODE_BITS);
}

#endif /* !__ASSEMBLY__ */
#endif /* CONFIG_X86_64 */

#ifdef __KERNEL__

/*
 * early_idt_handler_array is an array of entry points referenced in the
 * early IDT.  For simplicity, it's a real array with one entry point
 * every nine bytes.  That leaves room for an optional 'push $0' if the
 * vector has no error code (two bytes), a 'push $vector_number' (two
 * bytes), and a jump to the common entry code (up to five bytes).
 */
#define EARLY_IDT_HANDLER_SIZE 9

/*
 * xen_early_idt_handler_array is for Xen pv guests: for each entry in
 * early_idt_handler_array it contains a prequel in the form of
 * pop %rcx; pop %r11; jmp early_idt_handler_array[i]; summing up to
 * max 8 bytes.
 */
#define XEN_EARLY_IDT_HANDLER_SIZE 8

#ifndef __ASSEMBLY__

extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
extern void early_ignore_irq(void);

#ifdef CONFIG_XEN_PV
extern const char xen_early_idt_handler_array[NUM_EXCEPTION_VECTORS][XEN_EARLY_IDT_HANDLER_SIZE];
#endif

/*
 * Load a segment. Fall back on loading the zero segment if something goes
 * wrong.  This variant assumes that loading zero fully clears the segment.
 * This is always the case on Intel CPUs and, even on 64-bit AMD CPUs, any
 * failure to fully clear the cached descriptor is only observable for
 * FS and GS.
 */
#define __loadsegment_simple(seg, value)				\
do {									\
	unsigned short __val = (value);					\
									\
	asm volatile("						\n"	\
		     "1:	movl %k0,%%" #seg "		\n"	\
									\
		     ".section .fixup,\"ax\"			\n"	\
		     "2:	xorl %k0,%k0			\n"	\
		     "		jmp 1b				\n"	\
		     ".previous					\n"	\
									\
		     _ASM_EXTABLE(1b, 2b)				\
									\
		     : "+r" (__val) : : "memory");			\
} while (0)

#define __loadsegment_ss(value) __loadsegment_simple(ss, (value))
#define __loadsegment_ds(value) __loadsegment_simple(ds, (value))
#define __loadsegment_es(value) __loadsegment_simple(es, (value))

#ifdef CONFIG_X86_32

/*
 * On 32-bit systems, the hidden parts of FS and GS are unobservable if
 * the selector is NULL, so there's no funny business here.
 */
#define __loadsegment_fs(value) __loadsegment_simple(fs, (value))
#define __loadsegment_gs(value) __loadsegment_simple(gs, (value))

#else

static inline void __loadsegment_fs(unsigned short value)
{
	asm volatile("						\n"
		     "1:	movw %0, %%fs			\n"
		     "2:					\n"

		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_clear_fs)

		     : : "rm" (value) : "memory");
}

/* __loadsegment_gs is intentionally undefined.  Use load_gs_index instead. */

#endif

#define loadsegment(seg, value) __loadsegment_ ## seg (value)

/*
 * Save a segment register away:
 */
#define savesegment(seg, value)				\
	asm("mov %%" #seg ",%0":"=r" (value) : : "memory")

/*
 * x86-32 user GS accessors:
 */
#ifdef CONFIG_X86_32
# ifdef CONFIG_X86_32_LAZY_GS
#  define get_user_gs(regs)		(u16)({ unsigned long v; savesegment(gs, v); v; })
#  define set_user_gs(regs, v)		loadsegment(gs, (unsigned long)(v))
#  define task_user_gs(tsk)		((tsk)->thread.gs)
#  define lazy_save_gs(v)		savesegment(gs, (v))
#  define lazy_load_gs(v)		loadsegment(gs, (v))
# else	/* X86_32_LAZY_GS */
#  define get_user_gs(regs)		(u16)((regs)->gs)
#  define set_user_gs(regs, v)		do { (regs)->gs = (v); } while (0)
#  define task_user_gs(tsk)		(task_pt_regs(tsk)->gs)
#  define lazy_save_gs(v)		do { } while (0)
#  define lazy_load_gs(v)		do { } while (0)
# endif	/* X86_32_LAZY_GS */
#endif	/* X86_32 */

#endif /* !__ASSEMBLY__ */
#endif /* __KERNEL__ */

#endif /* _ASM_X86_SEGMENT_H */