calling.h 9.8 KB
Newer Older
1
/* SPDX-License-Identifier: GPL-2.0 */
2
#include <linux/jump_label.h>
3
#include <asm/unwind_hints.h>
4 5
#include <asm/cpufeatures.h>
#include <asm/page_types.h>
6 7 8
#include <asm/percpu.h>
#include <asm/asm-offsets.h>
#include <asm/processor-flags.h>
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

 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.

*/

58 59
#ifdef CONFIG_X86_64

60
/*
T
Tao Guo 已提交
61 62
 * 64-bit system call stack frame layout defines and helpers,
 * for assembly code:
63
 */
L
Linus Torvalds 已提交
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
/* The layout forms the "struct pt_regs" on the stack: */
/*
 * C ABI says these regs are callee-preserved. They aren't saved on kernel entry
 * unless syscall needs a complete, fully filled "struct pt_regs".
 */
#define R15		0*8
#define R14		1*8
#define R13		2*8
#define R12		3*8
#define RBP		4*8
#define RBX		5*8
/* These regs are callee-clobbered. Always saved on kernel entry. */
#define R11		6*8
#define R10		7*8
#define R9		8*8
#define R8		9*8
#define RAX		10*8
#define RCX		11*8
#define RDX		12*8
#define RSI		13*8
#define RDI		14*8
/*
 * On syscall entry, this is syscall#. On CPU exception, this is error code.
 * On hw interrupt, it's IRQ number:
 */
#define ORIG_RAX	15*8
/* Return frame for iretq */
#define RIP		16*8
#define CS		17*8
#define EFLAGS		18*8
#define RSP		19*8
#define SS		20*8

98 99
#define SIZEOF_PTREGS	21*8

100
.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0
101 102 103 104 105 106 107
	/*
	 * Push registers and 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.
	 * Interleave XOR with PUSH for better uop scheduling:
	 */
108 109 110 111 112
	.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
113 114
	pushq   %rdi		/* pt_regs->di */
	pushq   %rsi		/* pt_regs->si */
115
	.endif
116
	pushq	\rdx		/* pt_regs->dx */
117
	pushq   %rcx		/* pt_regs->cx */
118
	pushq   \rax		/* pt_regs->ax */
119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139
	pushq   %r8		/* pt_regs->r8 */
	xorq    %r8, %r8	/* nospec   r8 */
	pushq   %r9		/* pt_regs->r9 */
	xorq    %r9, %r9	/* nospec   r9 */
	pushq   %r10		/* pt_regs->r10 */
	xorq    %r10, %r10	/* nospec   r10 */
	pushq   %r11		/* pt_regs->r11 */
	xorq    %r11, %r11	/* nospec   r11*/
	pushq	%rbx		/* pt_regs->rbx */
	xorl    %ebx, %ebx	/* nospec   rbx*/
	pushq	%rbp		/* pt_regs->rbp */
	xorl    %ebp, %ebp	/* nospec   rbp*/
	pushq	%r12		/* pt_regs->r12 */
	xorq    %r12, %r12	/* nospec   r12*/
	pushq	%r13		/* pt_regs->r13 */
	xorq    %r13, %r13	/* nospec   r13*/
	pushq	%r14		/* pt_regs->r14 */
	xorq    %r14, %r14	/* nospec   r14*/
	pushq	%r15		/* pt_regs->r15 */
	xorq    %r15, %r15	/* nospec   r15*/
	UNWIND_HINT_REGS
140 141 142
	.if \save_ret
	pushq	%rsi		/* return address on top of stack */
	.endif
143
.endm
144

145
.macro POP_REGS pop_rdi=1 skip_r11rcx=0
146 147 148 149 150 151
	popq %r15
	popq %r14
	popq %r13
	popq %r12
	popq %rbp
	popq %rbx
152 153 154
	.if \skip_r11rcx
	popq %rsi
	.else
155
	popq %r11
156
	.endif
157 158 159 160
	popq %r10
	popq %r9
	popq %r8
	popq %rax
161 162 163
	.if \skip_r11rcx
	popq %rsi
	.else
164
	popq %rcx
165
	.endif
166 167
	popq %rdx
	popq %rsi
168
	.if \pop_rdi
169
	popq %rdi
170
	.endif
171
.endm
172

173 174 175 176 177 178
/*
 * This is a sneaky trick to help the unwinder find pt_regs on the stack.  The
 * frame pointer is replaced with an encoded pointer to pt_regs.  The encoding
 * is just setting the LSB, which makes it an invalid stack address and is also
 * a signal to the unwinder that it's a pt_regs pointer in disguise.
 *
179
 * NOTE: This macro must be used *after* PUSH_AND_CLEAR_REGS because it corrupts
180 181 182 183 184 185 186 187 188 189 190 191 192
 * the original rbp.
 */
.macro ENCODE_FRAME_POINTER ptregs_offset=0
#ifdef CONFIG_FRAME_POINTER
	.if \ptregs_offset
		leaq \ptregs_offset(%rsp), %rbp
	.else
		mov %rsp, %rbp
	.endif
	orq	$0x1, %rbp
#endif
.endm

193 194
#ifdef CONFIG_PAGE_TABLE_ISOLATION

195 196 197 198
/*
 * PAGE_TABLE_ISOLATION PGDs are 8k.  Flip bit 12 to switch between the two
 * halves:
 */
199 200 201 202 203
#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)
204

205 206
.macro SET_NOFLUSH_BIT	reg:req
	bts	$X86_CR3_PCID_NOFLUSH_BIT, \reg
207 208
.endm

209 210 211
.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: */
212
	andq    $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg
213 214 215
.endm

.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
216
	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
217 218 219
	mov	%cr3, \scratch_reg
	ADJUST_KERNEL_CR3 \scratch_reg
	mov	\scratch_reg, %cr3
220
.Lend_\@:
221 222
.endm

223 224 225 226
#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
227
	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
228
	mov	%cr3, \scratch_reg
229 230 231 232 233 234 235 236 237 238 239 240 241 242

	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
243
	jmp	.Lwrcr3_pcid_\@
244 245 246 247 248

.Lnoflush_\@:
	movq	\scratch_reg2, \scratch_reg
	SET_NOFLUSH_BIT \scratch_reg

249 250 251 252
.Lwrcr3_pcid_\@:
	/* Flip the ASID to the user version */
	orq	$(PTI_USER_PCID_MASK), \scratch_reg

253
.Lwrcr3_\@:
254 255
	/* Flip the PGD to the user version */
	orq     $(PTI_USER_PGTABLE_MASK), \scratch_reg
256
	mov	\scratch_reg, %cr3
257
.Lend_\@:
258 259
.endm

260 261 262 263 264 265
.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

266
.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
267
	ALTERNATIVE "jmp .Ldone_\@", "", X86_FEATURE_PTI
268 269 270
	movq	%cr3, \scratch_reg
	movq	\scratch_reg, \save_reg
	/*
271 272 273
	 * Test the user pagetable bit. If set, then the user page tables
	 * are active. If clear CR3 already has the kernel page table
	 * active.
274
	 */
275 276
	bt	$PTI_USER_PGTABLE_BIT, \scratch_reg
	jnc	.Ldone_\@
277 278 279 280 281 282 283

	ADJUST_KERNEL_CR3 \scratch_reg
	movq	\scratch_reg, %cr3

.Ldone_\@:
.endm

P
Peter Zijlstra 已提交
284
.macro RESTORE_CR3 scratch_reg:req save_reg:req
285
	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
P
Peter Zijlstra 已提交
286 287 288 289 290 291 292

	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID

	/*
	 * KERNEL pages can always resume with NOFLUSH as we do
	 * explicit flushes.
	 */
293
	bt	$PTI_USER_PGTABLE_BIT, \save_reg
P
Peter Zijlstra 已提交
294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311
	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_\@:
312 313 314 315 316
	/*
	 * 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
317
.Lend_\@:
318 319 320 321 322 323
.endm

#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */

.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
.endm
324 325 326
.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
.endm
.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
327 328 329
.endm
.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
.endm
P
Peter Zijlstra 已提交
330
.macro RESTORE_CR3 scratch_reg:req save_reg:req
331 332 333 334
.endm

#endif

335 336
#endif /* CONFIG_X86_64 */

337 338 339 340 341 342 343 344 345 346 347 348 349
/*
 * This does 'call enter_from_user_mode' unless we can avoid it based on
 * kernel config or using the static jump infrastructure.
 */
.macro CALL_enter_from_user_mode
#ifdef CONFIG_CONTEXT_TRACKING
#ifdef HAVE_JUMP_LABEL
	STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0
#endif
	call enter_from_user_mode
.Lafter_call_\@:
#endif
.endm