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
|
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/jump_label.h>
#include <asm/unwind_hints.h>
#include <asm/cpufeatures.h>
#include <asm/page_types.h>
#include <asm/percpu.h>
#include <asm/asm-offsets.h>
#include <asm/processor-flags.h>
#include <asm/ptrace-abi.h>
/*
x86 function call convention, 64-bit:
-------------------------------------
arguments | callee-saved | extra caller-saved | return
[callee-clobbered] | | [callee-clobbered] |
---------------------------------------------------------------------------
rdi rsi rdx rcx r8-9 | rbx rbp [*] r12-15 | r10-11 | rax, rdx [**]
( rsp is obviously invariant across normal function calls. (gcc can 'merge'
functions when it sees tail-call optimization possibilities) rflags is
clobbered. Leftover arguments are passed over the stack frame.)
[*] In the frame-pointers case rbp is fixed to the stack frame.
[**] for struct return values wider than 64 bits the return convention is a
bit more complex: up to 128 bits width we return small structures
straight in rax, rdx. For structures larger than that (3 words or
larger) the caller puts a pointer to an on-stack return struct
[allocated in the caller's stack frame] into the first argument - i.e.
into rdi. All other arguments shift up by one in this case.
Fortunately this case is rare in the kernel.
For 32-bit we have the following conventions - kernel is built with
-mregparm=3 and -freg-struct-return:
x86 function calling convention, 32-bit:
----------------------------------------
arguments | callee-saved | extra caller-saved | return
[callee-clobbered] | | [callee-clobbered] |
-------------------------------------------------------------------------
eax edx ecx | ebx edi esi ebp [*] | <none> | eax, edx [**]
( here too esp is obviously invariant across normal function calls. eflags
is clobbered. Leftover arguments are passed over the stack frame. )
[*] In the frame-pointers case ebp is fixed to the stack frame.
[**] We build with -freg-struct-return, which on 32-bit means similar
semantics as on 64-bit: edx can be used for a second return value
(i.e. covering integer and structure sizes up to 64 bits) - after that
it gets more complex and more expensive: 3-word or larger struct returns
get done in the caller's frame and the pointer to the return struct goes
into regparm0, i.e. eax - the other arguments shift up and the
function's register parameters degenerate to regparm=2 in essence.
*/
#ifdef CONFIG_X86_64
/*
* 64-bit system call stack frame layout defines and helpers,
* for assembly code:
*/
.macro PUSH_REGS rdx=%rdx rax=%rax save_ret=0
.if \save_ret
pushq %rsi /* pt_regs->si */
movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */
movq %rdi, 8(%rsp) /* pt_regs->di (overwriting original return address) */
.else
pushq %rdi /* pt_regs->di */
pushq %rsi /* pt_regs->si */
.endif
pushq \rdx /* pt_regs->dx */
pushq %rcx /* pt_regs->cx */
pushq \rax /* pt_regs->ax */
pushq %r8 /* pt_regs->r8 */
pushq %r9 /* pt_regs->r9 */
pushq %r10 /* pt_regs->r10 */
pushq %r11 /* pt_regs->r11 */
pushq %rbx /* pt_regs->rbx */
pushq %rbp /* pt_regs->rbp */
pushq %r12 /* pt_regs->r12 */
pushq %r13 /* pt_regs->r13 */
pushq %r14 /* pt_regs->r14 */
pushq %r15 /* pt_regs->r15 */
UNWIND_HINT_REGS
.if \save_ret
pushq %rsi /* return address on top of stack */
.endif
.endm
.macro CLEAR_REGS
/*
* Sanitize registers of values that a speculation attack might
* otherwise want to exploit. The lower registers are likely clobbered
* well before they could be put to use in a speculative execution
* gadget.
*/
xorl %edx, %edx /* nospec dx */
xorl %ecx, %ecx /* nospec cx */
xorl %r8d, %r8d /* nospec r8 */
xorl %r9d, %r9d /* nospec r9 */
xorl %r10d, %r10d /* nospec r10 */
xorl %r11d, %r11d /* nospec r11 */
xorl %ebx, %ebx /* nospec rbx */
xorl %ebp, %ebp /* nospec rbp */
xorl %r12d, %r12d /* nospec r12 */
xorl %r13d, %r13d /* nospec r13 */
xorl %r14d, %r14d /* nospec r14 */
xorl %r15d, %r15d /* nospec r15 */
.endm
.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0
PUSH_REGS rdx=\rdx, rax=\rax, save_ret=\save_ret
CLEAR_REGS
.endm
.macro POP_REGS pop_rdi=1 skip_r11rcx=0
popq %r15
popq %r14
popq %r13
popq %r12
popq %rbp
popq %rbx
.if \skip_r11rcx
popq %rsi
.else
popq %r11
.endif
popq %r10
popq %r9
popq %r8
popq %rax
.if \skip_r11rcx
popq %rsi
.else
popq %rcx
.endif
popq %rdx
popq %rsi
.if \pop_rdi
popq %rdi
.endif
.endm
#ifdef CONFIG_PAGE_TABLE_ISOLATION
/*
* PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two
* halves:
*/
#define PTI_USER_PGTABLE_BIT PAGE_SHIFT
#define PTI_USER_PGTABLE_MASK (1 << PTI_USER_PGTABLE_BIT)
#define PTI_USER_PCID_BIT X86_CR3_PTI_PCID_USER_BIT
#define PTI_USER_PCID_MASK (1 << PTI_USER_PCID_BIT)
#define PTI_USER_PGTABLE_AND_PCID_MASK (PTI_USER_PCID_MASK | PTI_USER_PGTABLE_MASK)
.macro SET_NOFLUSH_BIT reg:req
bts $X86_CR3_PCID_NOFLUSH_BIT, \reg
.endm
.macro ADJUST_KERNEL_CR3 reg:req
ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID
/* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
andq $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg
.endm
.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
mov %cr3, \scratch_reg
ADJUST_KERNEL_CR3 \scratch_reg
mov \scratch_reg, %cr3
.Lend_\@:
.endm
#define THIS_CPU_user_pcid_flush_mask \
PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask
.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
mov %cr3, \scratch_reg
ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
/*
* Test if the ASID needs a flush.
*/
movq \scratch_reg, \scratch_reg2
andq $(0x7FF), \scratch_reg /* mask ASID */
bt \scratch_reg, THIS_CPU_user_pcid_flush_mask
jnc .Lnoflush_\@
/* Flush needed, clear the bit */
btr \scratch_reg, THIS_CPU_user_pcid_flush_mask
movq \scratch_reg2, \scratch_reg
jmp .Lwrcr3_pcid_\@
.Lnoflush_\@:
movq \scratch_reg2, \scratch_reg
SET_NOFLUSH_BIT \scratch_reg
.Lwrcr3_pcid_\@:
/* Flip the ASID to the user version */
orq $(PTI_USER_PCID_MASK), \scratch_reg
.Lwrcr3_\@:
/* Flip the PGD to the user version */
orq $(PTI_USER_PGTABLE_MASK), \scratch_reg
mov \scratch_reg, %cr3
.Lend_\@:
.endm
.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
pushq %rax
SWITCH_TO_USER_CR3_NOSTACK scratch_reg=\scratch_reg scratch_reg2=%rax
popq %rax
.endm
.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
ALTERNATIVE "jmp .Ldone_\@", "", X86_FEATURE_PTI
movq %cr3, \scratch_reg
movq \scratch_reg, \save_reg
/*
* Test the user pagetable bit. If set, then the user page tables
* are active. If clear CR3 already has the kernel page table
* active.
*/
bt $PTI_USER_PGTABLE_BIT, \scratch_reg
jnc .Ldone_\@
ADJUST_KERNEL_CR3 \scratch_reg
movq \scratch_reg, %cr3
.Ldone_\@:
.endm
.macro RESTORE_CR3 scratch_reg:req save_reg:req
ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
/*
* KERNEL pages can always resume with NOFLUSH as we do
* explicit flushes.
*/
bt $PTI_USER_PGTABLE_BIT, \save_reg
jnc .Lnoflush_\@
/*
* Check if there's a pending flush for the user ASID we're
* about to set.
*/
movq \save_reg, \scratch_reg
andq $(0x7FF), \scratch_reg
bt \scratch_reg, THIS_CPU_user_pcid_flush_mask
jnc .Lnoflush_\@
btr \scratch_reg, THIS_CPU_user_pcid_flush_mask
jmp .Lwrcr3_\@
.Lnoflush_\@:
SET_NOFLUSH_BIT \save_reg
.Lwrcr3_\@:
/*
* The CR3 write could be avoided when not changing its value,
* but would require a CR3 read *and* a scratch register.
*/
movq \save_reg, %cr3
.Lend_\@:
.endm
#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */
.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
.endm
.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
.endm
.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
.endm
.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
.endm
.macro RESTORE_CR3 scratch_reg:req save_reg:req
.endm
#endif
/*
* Mitigate Spectre v1 for conditional swapgs code paths.
*
* FENCE_SWAPGS_USER_ENTRY is used in the user entry swapgs code path, to
* prevent a speculative swapgs when coming from kernel space.
*
* FENCE_SWAPGS_KERNEL_ENTRY is used in the kernel entry non-swapgs code path,
* to prevent the swapgs from getting speculatively skipped when coming from
* user space.
*/
.macro FENCE_SWAPGS_USER_ENTRY
ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_USER
.endm
.macro FENCE_SWAPGS_KERNEL_ENTRY
ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_KERNEL
.endm
.macro STACKLEAK_ERASE_NOCLOBBER
#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
PUSH_AND_CLEAR_REGS
call stackleak_erase
POP_REGS
#endif
.endm
.macro SAVE_AND_SET_GSBASE scratch_reg:req save_reg:req
rdgsbase \save_reg
GET_PERCPU_BASE \scratch_reg
wrgsbase \scratch_reg
.endm
#else /* CONFIG_X86_64 */
# undef UNWIND_HINT_IRET_REGS
# define UNWIND_HINT_IRET_REGS
#endif /* !CONFIG_X86_64 */
.macro STACKLEAK_ERASE
#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
call stackleak_erase
#endif
.endm
#ifdef CONFIG_SMP
/*
* CPU/node NR is loaded from the limit (size) field of a special segment
* descriptor entry in GDT.
*/
.macro LOAD_CPU_AND_NODE_SEG_LIMIT reg:req
movq $__CPUNODE_SEG, \reg
lsl \reg, \reg
.endm
/*
* Fetch the per-CPU GSBASE value for this processor and put it in @reg.
* We normally use %gs for accessing per-CPU data, but we are setting up
* %gs here and obviously can not use %gs itself to access per-CPU data.
*
* Do not use RDPID, because KVM loads guest's TSC_AUX on vm-entry and
* may not restore the host's value until the CPU returns to userspace.
* Thus the kernel would consume a guest's TSC_AUX if an NMI arrives
* while running KVM's run loop.
*/
.macro GET_PERCPU_BASE reg:req
LOAD_CPU_AND_NODE_SEG_LIMIT \reg
andq $VDSO_CPUNODE_MASK, \reg
movq __per_cpu_offset(, \reg, 8), \reg
.endm
#else
.macro GET_PERCPU_BASE reg:req
movq pcpu_unit_offsets(%rip), \reg
.endm
#endif /* CONFIG_SMP */
|