summaryrefslogtreecommitdiffstats
path: root/arch/x86/entry/common.c
blob: 93c60c0c9d4a7a25d91aef2d948d648e08006abe (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * common.c - C code for kernel entry and exit
 * Copyright (c) 2015 Andrew Lutomirski
 *
 * Based on asm and ptrace code by many authors.  The code here originated
 * in ptrace.c and signal.c.
 */

#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/entry-common.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/export.h>
#include <linux/nospec.h>
#include <linux/syscalls.h>
#include <linux/uaccess.h>

#ifdef CONFIG_XEN_PV
#include <xen/xen-ops.h>
#include <xen/events.h>
#endif

#include <asm/desc.h>
#include <asm/traps.h>
#include <asm/vdso.h>
#include <asm/cpufeature.h>
#include <asm/fpu/api.h>
#include <asm/nospec-branch.h>
#include <asm/io_bitmap.h>
#include <asm/syscall.h>
#include <asm/irq_stack.h>

#ifdef CONFIG_X86_64

static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr)
{
	/*
	 * Convert negative numbers to very high and thus out of range
	 * numbers for comparisons.
	 */
	unsigned int unr = nr;

	if (likely(unr < NR_syscalls)) {
		unr = array_index_nospec(unr, NR_syscalls);
		regs->ax = sys_call_table[unr](regs);
		return true;
	}
	return false;
}

static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
{
	/*
	 * Adjust the starting offset of the table, and convert numbers
	 * < __X32_SYSCALL_BIT to very high and thus out of range
	 * numbers for comparisons.
	 */
	unsigned int xnr = nr - __X32_SYSCALL_BIT;

	if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) {
		xnr = array_index_nospec(xnr, X32_NR_syscalls);
		regs->ax = x32_sys_call_table[xnr](regs);
		return true;
	}
	return false;
}

__visible noinstr void do_syscall_64(struct pt_regs *regs, int nr)
{
	add_random_kstack_offset();
	nr = syscall_enter_from_user_mode(regs, nr);

	instrumentation_begin();

	if (!do_syscall_x64(regs, nr) && !do_syscall_x32(regs, nr) && nr != -1) {
		/* Invalid system call, but still a system call. */
		regs->ax = __x64_sys_ni_syscall(regs);
	}

	instrumentation_end();
	syscall_exit_to_user_mode(regs);
}
#endif

#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
static __always_inline int syscall_32_enter(struct pt_regs *regs)
{
	if (IS_ENABLED(CONFIG_IA32_EMULATION))
		current_thread_info()->status |= TS_COMPAT;

	return (int)regs->orig_ax;
}

/*
 * Invoke a 32-bit syscall.  Called with IRQs on in CONTEXT_KERNEL.
 */
static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr)
{
	/*
	 * Convert negative numbers to very high and thus out of range
	 * numbers for comparisons.
	 */
	unsigned int unr = nr;

	if (likely(unr < IA32_NR_syscalls)) {
		unr = array_index_nospec(unr, IA32_NR_syscalls);
		regs->ax = ia32_sys_call_table[unr](regs);
	} else if (nr != -1) {
		regs->ax = __ia32_sys_ni_syscall(regs);
	}
}

/* Handles int $0x80 */
__visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
{
	int nr = syscall_32_enter(regs);

	add_random_kstack_offset();
	/*
	 * Subtlety here: if ptrace pokes something larger than 2^31-1 into
	 * orig_ax, the int return value truncates it. This matches
	 * the semantics of syscall_get_nr().
	 */
	nr = syscall_enter_from_user_mode(regs, nr);
	instrumentation_begin();

	do_syscall_32_irqs_on(regs, nr);

	instrumentation_end();
	syscall_exit_to_user_mode(regs);
}

static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
{
	int nr = syscall_32_enter(regs);
	int res;

	add_random_kstack_offset();
	/*
	 * This cannot use syscall_enter_from_user_mode() as it has to
	 * fetch EBP before invoking any of the syscall entry work
	 * functions.
	 */
	syscall_enter_from_user_mode_prepare(regs);

	instrumentation_begin();
	/* Fetch EBP from where the vDSO stashed it. */
	if (IS_ENABLED(CONFIG_X86_64)) {
		/*
		 * Micro-optimization: the pointer we're following is
		 * explicitly 32 bits, so it can't be out of range.
		 */
		res = __get_user(*(u32 *)&regs->bp,
			 (u32 __user __force *)(unsigned long)(u32)regs->sp);
	} else {
		res = get_user(*(u32 *)&regs->bp,
		       (u32 __user __force *)(unsigned long)(u32)regs->sp);
	}

	if (res) {
		/* User code screwed up. */
		regs->ax = -EFAULT;

		local_irq_disable();
		instrumentation_end();
		irqentry_exit_to_user_mode(regs);
		return false;
	}

	nr = syscall_enter_from_user_mode_work(regs, nr);

	/* Now this is just like a normal syscall. */
	do_syscall_32_irqs_on(regs, nr);

	instrumentation_end();
	syscall_exit_to_user_mode(regs);
	return true;
}

/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
__visible noinstr long do_fast_syscall_32(struct pt_regs *regs)
{
	/*
	 * Called using the internal vDSO SYSENTER/SYSCALL32 calling
	 * convention.  Adjust regs so it looks like we entered using int80.
	 */
	unsigned long landing_pad = (unsigned long)current->mm->context.vdso +
					vdso_image_32.sym_int80_landing_pad;

	/*
	 * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
	 * so that 'regs->ip -= 2' lands back on an int $0x80 instruction.
	 * Fix it up.
	 */
	regs->ip = landing_pad;

	/* Invoke the syscall. If it failed, keep it simple: use IRET. */
	if (!__do_fast_syscall_32(regs))
		return 0;

#ifdef CONFIG_X86_64
	/*
	 * Opportunistic SYSRETL: if possible, try to return using SYSRETL.
	 * SYSRETL is available on all 64-bit CPUs, so we don't need to
	 * bother with SYSEXIT.
	 *
	 * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
	 * because the ECX fixup above will ensure that this is essentially
	 * never the case.
	 */
	return regs->cs == __USER32_CS && regs->ss == __USER_DS &&
		regs->ip == landing_pad &&
		(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)) == 0;
#else
	/*
	 * Opportunistic SYSEXIT: if possible, try to return using SYSEXIT.
	 *
	 * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
	 * because the ECX fixup above will ensure that this is essentially
	 * never the case.
	 *
	 * We don't allow syscalls at all from VM86 mode, but we still
	 * need to check VM, because we might be returning from sys_vm86.
	 */
	return static_cpu_has(X86_FEATURE_SEP) &&
		regs->cs == __USER_CS && regs->ss == __USER_DS &&
		regs->ip == landing_pad &&
		(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0;
#endif
}

/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
__visible noinstr long do_SYSENTER_32(struct pt_regs *regs)
{
	/* SYSENTER loses RSP, but the vDSO saved it in RBP. */
	regs->sp = regs->bp;

	/* SYSENTER clobbers EFLAGS.IF.  Assume it was set in usermode. */
	regs->flags |= X86_EFLAGS_IF;

	return do_fast_syscall_32(regs);
}
#endif

SYSCALL_DEFINE0(ni_syscall)
{
	return -ENOSYS;
}

#ifdef CONFIG_XEN_PV
#ifndef CONFIG_PREEMPTION
/*
 * Some hypercalls issued by the toolstack can take many 10s of
 * seconds. Allow tasks running hypercalls via the privcmd driver to
 * be voluntarily preempted even if full kernel preemption is
 * disabled.
 *
 * Such preemptible hypercalls are bracketed by
 * xen_preemptible_hcall_begin() and xen_preemptible_hcall_end()
 * calls.
 */
DEFINE_PER_CPU(bool, xen_in_preemptible_hcall);
EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall);

/*
 * In case of scheduling the flag must be cleared and restored after
 * returning from schedule as the task might move to a different CPU.
 */
static __always_inline bool get_and_clear_inhcall(void)
{
	bool inhcall = __this_cpu_read(xen_in_preemptible_hcall);

	__this_cpu_write(xen_in_preemptible_hcall, false);
	return inhcall;
}

static __always_inline void restore_inhcall(bool inhcall)
{
	__this_cpu_write(xen_in_preemptible_hcall, inhcall);
}
#else
static __always_inline bool get_and_clear_inhcall(void) { return false; }
static __always_inline void restore_inhcall(bool inhcall) { }
#endif

static void __xen_pv_evtchn_do_upcall(struct pt_regs *regs)
{
	struct pt_regs *old_regs = set_irq_regs(regs);

	inc_irq_stat(irq_hv_callback_count);

	xen_evtchn_do_upcall();

	set_irq_regs(old_regs);
}

__visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
{
	irqentry_state_t state = irqentry_enter(regs);
	bool inhcall;

	instrumentation_begin();
	run_sysvec_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs);

	inhcall = get_and_clear_inhcall();
	if (inhcall && !WARN_ON_ONCE(state.exit_rcu)) {
		irqentry_exit_cond_resched();
		instrumentation_end();
		restore_inhcall(inhcall);
	} else {
		instrumentation_end();
		irqentry_exit(regs, state);
	}
}
#endif /* CONFIG_XEN_PV */